From 749c5102487b558cc7d73961a6d0da2fceaa022d Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Fri, 12 Jun 2026 08:35:50 -0700 Subject: [PATCH 0001/1198] EDAC/mpc85xx: Orphan it Johannes doesn't have the hardware to test patches on it anymore and TTBOMK, no one else has shown interest so orphan the driver, for now at least. Signed-off-by: Borislav Petkov (AMD) Acked-by: Johannes Thumshirn Link: https://patch.msgid.link/20260612153839.GCaiwn_7qOic4KLF8P@fat_crate.local --- MAINTAINERS | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 15011f5752a9..7b37c88143f6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9414,9 +9414,8 @@ S: Maintained F: drivers/edac/igen6_edac.c EDAC-MPC85XX -M: Johannes Thumshirn L: linux-edac@vger.kernel.org -S: Maintained +S: Orphan F: drivers/edac/mpc85xx_edac.[ch] EDAC-NPCM From 90cfd27df4ba5f1c18a3454eb4b454bfe6baaf36 Mon Sep 17 00:00:00 2001 From: Yazen Ghannam Date: Mon, 29 Jun 2026 11:07:29 -0400 Subject: [PATCH 0002/1198] EDAC/debugfs: Remove the fake_inject debugfs interface The interface has a potential race condition between a real and fake error when updating the memory controller's error descriptor. There doesn't seem to be an active user base for this interface, so remove it. Closes: https://sashiko.dev/#/patchset/20260518160716.171578-1-yazen.ghannam%40amd.com Reported-by: sashiko-bot Suggested-by: Borislav Petkov Assisted-by: Claude:claude-opus-4-6 Signed-off-by: Yazen Ghannam Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/linux-edac/20260611012336.GHaioOGB0NBxv5BZXS@fat_crate.local --- drivers/edac/debugfs.c | 65 +----------------------------------------- include/linux/edac.h | 3 -- 2 files changed, 1 insertion(+), 67 deletions(-) diff --git a/drivers/edac/debugfs.c b/drivers/edac/debugfs.c index 8195fc9c9354..447d0c620082 100644 --- a/drivers/edac/debugfs.c +++ b/drivers/edac/debugfs.c @@ -1,50 +1,9 @@ // SPDX-License-Identifier: GPL-2.0-only -#include - #include "edac_module.h" static struct dentry *edac_debugfs; -static ssize_t edac_fake_inject_write(struct file *file, - const char __user *data, - size_t count, loff_t *ppos) -{ - struct device *dev = file->private_data; - struct mem_ctl_info *mci = to_mci(dev); - static enum hw_event_mc_err_type type; - u16 errcount = mci->fake_inject_count; - - if (!errcount) - errcount = 1; - - type = mci->fake_inject_ue ? HW_EVENT_ERR_UNCORRECTED - : HW_EVENT_ERR_CORRECTED; - - printk(KERN_DEBUG - "Generating %d %s fake error%s to %d.%d.%d to test core handling. NOTE: this won't test the driver-specific decoding logic.\n", - errcount, - (type == HW_EVENT_ERR_UNCORRECTED) ? "UE" : "CE", - str_plural(errcount), - mci->fake_inject_layer[0], - mci->fake_inject_layer[1], - mci->fake_inject_layer[2] - ); - edac_mc_handle_error(type, mci, errcount, 0, 0, 0, - mci->fake_inject_layer[0], - mci->fake_inject_layer[1], - mci->fake_inject_layer[2], - "FAKE ERROR", "for EDAC testing only"); - - return count; -} - -static const struct file_operations debug_fake_inject_fops = { - .open = simple_open, - .write = edac_fake_inject_write, - .llseek = generic_file_llseek, -}; - void __init edac_debugfs_init(void) { edac_debugfs = debugfs_create_dir("edac", NULL); @@ -57,29 +16,7 @@ void edac_debugfs_exit(void) void edac_create_debugfs_nodes(struct mem_ctl_info *mci) { - struct dentry *parent; - char name[80]; - int i; - - parent = debugfs_create_dir(mci->dev.kobj.name, edac_debugfs); - - for (i = 0; i < mci->n_layers; i++) { - sprintf(name, "fake_inject_%s", - edac_layer_name[mci->layers[i].type]); - debugfs_create_u8(name, S_IRUGO | S_IWUSR, parent, - &mci->fake_inject_layer[i]); - } - - debugfs_create_bool("fake_inject_ue", S_IRUGO | S_IWUSR, parent, - &mci->fake_inject_ue); - - debugfs_create_u16("fake_inject_count", S_IRUGO | S_IWUSR, parent, - &mci->fake_inject_count); - - debugfs_create_file("fake_inject", S_IWUSR, parent, &mci->dev, - &debug_fake_inject_fops); - - mci->debugfs = parent; + mci->debugfs = debugfs_create_dir(mci->dev.kobj.name, edac_debugfs); } /* Create a toplevel dir under EDAC's debugfs hierarchy */ diff --git a/include/linux/edac.h b/include/linux/edac.h index e6b4e51130e5..f7a8218f9cc0 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -598,9 +598,6 @@ struct mem_ctl_info { int op_state; struct dentry *debugfs; - u8 fake_inject_layer[EDAC_MAX_LAYERS]; - bool fake_inject_ue; - u16 fake_inject_count; /* * Memory Controller hierarchy From 07897bdf7a9c60455a175f6eb619c7d95e1d1765 Mon Sep 17 00:00:00 2001 From: Abhinav Ananthu Date: Fri, 20 Jun 2025 01:51:34 +0530 Subject: [PATCH 0003/1198] EDAC/sysfs: Use sysfs_emit_at() in dimmdev_location_show() Replace the use of scnprintf() with sysfs_emit_at() in dimmdev_location_show() to format the output into the sysfs buffer and thus improve clarity and ensure proper bounds checking in line with the preferred sysfs_emit() API usage for sysfs 'show' functions. No functional change intended. [ bp: Massage commit message. ] Signed-off-by: Abhinav Ananthu Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Qiuxu Zhuo Link: https://patch.msgid.link/20250619202133.11843-1-abhinav.ogl@gmail.com --- drivers/edac/edac_mc_sysfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c index c2ed6c696e54..9b4b5582fa9f 100644 --- a/drivers/edac/edac_mc_sysfs.c +++ b/drivers/edac/edac_mc_sysfs.c @@ -129,7 +129,7 @@ static ssize_t dimmdev_location_show(struct device *dev, ssize_t count; count = edac_dimm_info_location(dimm, data, PAGE_SIZE); - count += scnprintf(data + count, PAGE_SIZE - count, "\n"); + count += sysfs_emit_at(data, count, "\n"); return count; } From 97dfcb871ba776ba0e1ded1cdcbe94a357c2817e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Jul 2026 19:38:03 +0200 Subject: [PATCH 0004/1198] MAINTAINERS: Remove Mark Gross from relevant entries MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Sending mail to Mark's Intel address results in the Intel mail server rejecting the mail. Dave Hansen confirmed he left Intel. The kernel.org address seems to work, but there was no reply from Mark on the discussion about broken email settings and his maintainer entries. So drop him from all maintainer entries and move him to credits. Signed-off-by: Uwe Kleine-König Signed-off-by: Borislav Petkov (AMD) Acked-by: Dave Hansen Link: https://patch.msgid.link/20260703173803.3589003-2-ukleinek@kernel.org --- CREDITS | 4 ++++ MAINTAINERS | 7 ++----- 2 files changed, 6 insertions(+), 5 deletions(-) diff --git a/CREDITS b/CREDITS index 84793a967a0b..091412875a66 100644 --- a/CREDITS +++ b/CREDITS @@ -1503,6 +1503,10 @@ N: Andy Gross E: agross@kernel.org D: Qualcomm SoC subsystem and drivers +N: Mark Gross +E: markgross@kernel.org +D: x86/mellanox platform maintenance and various x86 specific drivers + N: Grant Grundler E: grantgrundler@gmail.com W: http://obmouse.sourceforge.net/ diff --git a/MAINTAINERS b/MAINTAINERS index 7b37c88143f6..f16c09f76e7b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9337,9 +9337,8 @@ S: Supported F: drivers/edac/dmc520_edac.c EDAC-E752X -M: Mark Gross L: linux-edac@vger.kernel.org -S: Maintained +S: Orphan F: drivers/edac/e752x_edac.c EDAC-E7XXX @@ -13201,7 +13200,6 @@ F: drivers/crypto/intel/keembay/ocs-aes.h INTEL KEEM BAY OCS ECC CRYPTO DRIVER M: Prabhjot Khurana -M: Mark Gross S: Maintained F: Documentation/devicetree/bindings/crypto/intel,keembay-ocs-ecc.yaml F: drivers/crypto/intel/keembay/Kconfig @@ -26642,8 +26640,7 @@ S: Maintained F: drivers/net/ethernet/tehuti/tn40* TELECOM CLOCK DRIVER FOR MCPL0010 -M: Mark Gross -S: Supported +S: Orphan F: drivers/char/tlclk.c TEMPO SEMICONDUCTOR DRIVERS From 4c3da04827dc01dc1cfc3d03654b7de656c42d80 Mon Sep 17 00:00:00 2001 From: Yazen Ghannam Date: Mon, 6 Jul 2026 16:21:15 -0500 Subject: [PATCH 0005/1198] RAS/AMD/ATL, EDAC/amd64: Only load ATL when needed The AMD Address Translation Library (ATL) will attempt to load on all AMD Zen/SMCA systems. However, only systems with DRAM ECC enabled will use the library. Other systems will fail to load the library and produce an unnecessary message to the user. More importantly, that thing is dead code loaded and unused. Remove the ATL module dependency table to prevent autoloading. Request ATL to load from EDAC once all system checks are complete. [ bp: Massage commit message. ] Fixes: 3f3174996be6 ("RAS: Introduce AMD Address Translation Library") Closes: https://lore.kernel.org/20260305154528.1171999-1-mario.limonciello@amd.com Reported-by: Mario Limonciello Signed-off-by: Yazen Ghannam Signed-off-by: Mario Limonciello Signed-off-by: Borislav Petkov (AMD) Tested-by: Deskhmukh Shrirang Link: https://lore.kernel.org/all/20260307144910.GA113343@yaz-khff2.amd.com --- drivers/edac/amd64_edac.c | 2 ++ drivers/ras/amd/atl/core.c | 1 - 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index c6aa69dbd9fb..475235c402e8 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -4173,6 +4173,8 @@ static int __init amd64_edac_init(void) goto err_pci; } + request_module_nowait("amd_atl"); + /* register stuff with EDAC MCE */ if (boot_cpu_data.x86 >= 0x17) { amd_register_ecc_decoder(decode_umc_error); diff --git a/drivers/ras/amd/atl/core.c b/drivers/ras/amd/atl/core.c index 0f7cd6dab0b0..d77dacdd4f56 100644 --- a/drivers/ras/amd/atl/core.c +++ b/drivers/ras/amd/atl/core.c @@ -190,7 +190,6 @@ static const struct x86_cpu_id amd_atl_cpuids[] = { X86_MATCH_FEATURE(X86_FEATURE_ZEN, NULL), { } }; -MODULE_DEVICE_TABLE(x86cpu, amd_atl_cpuids); static int __init amd_atl_init(void) { From d4486fc3098e176cb4a29fee037216484761f9ca Mon Sep 17 00:00:00 2001 From: Rounak Das Date: Wed, 8 Jul 2026 13:11:34 +0400 Subject: [PATCH 0006/1198] EDAC/altera: Use ECC manager compatible to select A10/S10 IRQ layout The SDMMC ECC IRQ layout selection uses CONFIG_64BIT to distinguish between Arria10 and Stratix10 paths. Detect the SoC once at probe via the device match table (.data) store it in struct altr_arria10_edac, and use it instead of CONFIG_64BIT. This keeps the decision correct for every ECC child device (OCRAM, SD/MMC, etc.) and avoids any runtime compatible lookup. Signed-off-by: Rounak Das Signed-off-by: Borislav Petkov (AMD) Acked-by: Dinh Nguyen Link: https://patch.msgid.link/20260708091135.94114-2-rounakdas2025@gmail.com --- drivers/edac/altera_edac.c | 107 +++++++++++++++++++------------------ drivers/edac/altera_edac.h | 1 + 2 files changed, 55 insertions(+), 53 deletions(-) diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c index 4edd2088c2db..24bdf7f5bac6 100644 --- a/drivers/edac/altera_edac.c +++ b/drivers/edac/altera_edac.c @@ -1507,6 +1507,7 @@ static int altr_portb_setup(struct altr_edac_device_dev *device) int edac_idx, rc; struct device_node *np; const struct edac_device_prv_data *prv = &a10_sdmmceccb_data; + bool is_s10 = device->edac->is_s10; rc = altr_check_ecc_deps(device); if (rc) @@ -1548,15 +1549,14 @@ static int altr_portb_setup(struct altr_edac_device_dev *device) /* * Update the PortB IRQs - A10 has 4, S10 has 2, Index accordingly - * - * FIXME: Instead of ifdefs with different architectures the driver - * should properly use compatibles. */ -#ifdef CONFIG_64BIT - altdev->sb_irq = irq_of_parse_and_map(np, 1); -#else - altdev->sb_irq = irq_of_parse_and_map(np, 2); -#endif + + /* Using compatibles to determine the IRQ Index */ + if (is_s10) + altdev->sb_irq = irq_of_parse_and_map(np, 1); + else + altdev->sb_irq = irq_of_parse_and_map(np, 2); + if (!altdev->sb_irq) { edac_printk(KERN_ERR, EDAC_DEVICE, "Error PortB SBIRQ alloc\n"); rc = -ENODEV; @@ -1570,29 +1570,28 @@ static int altr_portb_setup(struct altr_edac_device_dev *device) goto err_release_group_1; } -#ifdef CONFIG_64BIT - /* Use IRQ to determine SError origin instead of assigning IRQ */ - rc = of_property_read_u32_index(np, "interrupts", 1, &altdev->db_irq); - if (rc) { - edac_printk(KERN_ERR, EDAC_DEVICE, - "Error PortB DBIRQ alloc\n"); - goto err_release_group_1; + if (is_s10) { + /* Use IRQ to determine SError origin instead of assigning IRQ */ + rc = of_property_read_u32_index(np, "interrupts", 1, &altdev->db_irq); + if (rc) { + edac_printk(KERN_ERR, EDAC_DEVICE, "Error PortB DBIRQ alloc\n"); + goto err_release_group_1; + } + } else { + altdev->db_irq = irq_of_parse_and_map(np, 3); + if (!altdev->db_irq) { + edac_printk(KERN_ERR, EDAC_DEVICE, "Error PortB DBIRQ alloc\n"); + rc = -ENODEV; + goto err_release_group_1; + } + rc = devm_request_irq(&altdev->ddev, altdev->db_irq, + prv->ecc_irq_handler, IRQF_TRIGGER_HIGH, + ecc_name, altdev); + if (rc) { + edac_printk(KERN_ERR, EDAC_DEVICE, "PortB DBERR IRQ error\n"); + goto err_release_group_1; + } } -#else - altdev->db_irq = irq_of_parse_and_map(np, 3); - if (!altdev->db_irq) { - edac_printk(KERN_ERR, EDAC_DEVICE, "Error PortB DBIRQ alloc\n"); - rc = -ENODEV; - goto err_release_group_1; - } - rc = devm_request_irq(&altdev->ddev, altdev->db_irq, - prv->ecc_irq_handler, IRQF_TRIGGER_HIGH, - ecc_name, altdev); - if (rc) { - edac_printk(KERN_ERR, EDAC_DEVICE, "PortB DBERR IRQ error\n"); - goto err_release_group_1; - } -#endif rc = edac_device_add_device(dci); if (rc) { @@ -1974,29 +1973,29 @@ static int altr_edac_a10_device_add(struct altr_arria10_edac *edac, goto err_release_group1; } -#ifdef CONFIG_64BIT - /* Use IRQ to determine SError origin instead of assigning IRQ */ - rc = of_property_read_u32_index(np, "interrupts", 0, &altdev->db_irq); - if (rc) { - edac_printk(KERN_ERR, EDAC_DEVICE, - "Unable to parse DB IRQ index\n"); - goto err_release_group1; + if (edac->is_s10) { + /* Use IRQ to determine SError origin instead of assigning IRQ */ + rc = of_property_read_u32_index(np, "interrupts", 0, &altdev->db_irq); + if (rc) { + edac_printk(KERN_ERR, EDAC_DEVICE, + "Unable to parse DB IRQ index\n"); + goto err_release_group1; + } + } else { + altdev->db_irq = irq_of_parse_and_map(np, 1); + if (!altdev->db_irq) { + edac_printk(KERN_ERR, EDAC_DEVICE, "Error allocating DBIRQ\n"); + rc = -ENODEV; + goto err_release_group1; + } + rc = devm_request_irq(edac->dev, altdev->db_irq, prv->ecc_irq_handler, + IRQF_TRIGGER_HIGH, + ecc_name, altdev); + if (rc) { + edac_printk(KERN_ERR, EDAC_DEVICE, "No DBERR IRQ resource\n"); + goto err_release_group1; + } } -#else - altdev->db_irq = irq_of_parse_and_map(np, 1); - if (!altdev->db_irq) { - edac_printk(KERN_ERR, EDAC_DEVICE, "Error allocating DBIRQ\n"); - rc = -ENODEV; - goto err_release_group1; - } - rc = devm_request_irq(edac->dev, altdev->db_irq, prv->ecc_irq_handler, - IRQF_TRIGGER_HIGH, - ecc_name, altdev); - if (rc) { - edac_printk(KERN_ERR, EDAC_DEVICE, "No DBERR IRQ resource\n"); - goto err_release_group1; - } -#endif rc = edac_device_add_device(dci); if (rc) { @@ -2122,6 +2121,8 @@ static int altr_edac_a10_probe(struct platform_device *pdev) platform_set_drvdata(pdev, edac); INIT_LIST_HEAD(&edac->a10_ecc_devices); + edac->is_s10 = !!device_get_match_data(&pdev->dev); + edac->ecc_mgr_map = altr_sysmgr_regmap_lookup_by_phandle(pdev->dev.of_node, "altr,sysmgr-syscon"); @@ -2207,7 +2208,7 @@ static int altr_edac_a10_probe(struct platform_device *pdev) static const struct of_device_id altr_edac_a10_of_match[] = { { .compatible = "altr,socfpga-a10-ecc-manager" }, - { .compatible = "altr,socfpga-s10-ecc-manager" }, + { .compatible = "altr,socfpga-s10-ecc-manager", .data = (void *)1 }, {}, }; MODULE_DEVICE_TABLE(of, altr_edac_a10_of_match); diff --git a/drivers/edac/altera_edac.h b/drivers/edac/altera_edac.h index f3e84172caa9..9387056fd65e 100644 --- a/drivers/edac/altera_edac.h +++ b/drivers/edac/altera_edac.h @@ -394,6 +394,7 @@ struct altr_arria10_edac { struct irq_chip irq_chip; struct list_head a10_ecc_devices; struct notifier_block panic_notifier; + bool is_s10; }; #endif /* #ifndef _ALTERA_EDAC_H */ From 11f5fd36076a2ef229ec5062c06954c955d90f9d Mon Sep 17 00:00:00 2001 From: Rounak Das Date: Wed, 8 Jul 2026 13:11:35 +0400 Subject: [PATCH 0007/1198] EDAC/altera: Remove remaining CONFIG_64BIT ifdefs in the DB-error path MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Replace the remaining two CONFIG_64BIT ifdefs with the is_s10 flag, so driver behavior is fully determined by the ECC manager's compatible string rather than the build architecture. These two ifdefs guard the double-bit-error path, where SError handling and the arm_smccc_smc() reboot call are arm64-specific. Switching to is_s10 means s10_edac_dberr_handler() now compiles on 32-bit as well — this is safe because all the symbols it depends on (arm_smccc_smc, INTEL_SIP_SMC_ECC_DBE, and the S10 sysmgr defines) are already available on 32-bit socfpga. Since the function only executes when is_s10 is true, Arria10 behavior is unaffected. This is handled separately from the IRQ-index selection change, as the double-bit-error path is a distinct concern. Signed-off-by: Rounak Das Signed-off-by: Borislav Petkov (AMD) Acked-by: Dinh Nguyen Assisted-by: Claude:claude-sonnet-5 Link: https://patch.msgid.link/20260708091135.94114-3-rounakdas2025@gmail.com --- drivers/edac/altera_edac.c | 20 ++++++++------------ 1 file changed, 8 insertions(+), 12 deletions(-) diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c index 24bdf7f5bac6..1d1e2b5ca14c 100644 --- a/drivers/edac/altera_edac.c +++ b/drivers/edac/altera_edac.c @@ -2058,7 +2058,6 @@ static const struct irq_domain_ops a10_eccmgr_ic_ops = { /************** Stratix 10 EDAC Double Bit Error Handler ************/ #define to_a10edac(p, m) container_of(p, struct altr_arria10_edac, m) -#ifdef CONFIG_64BIT /* panic routine issues reboot on non-zero panic_timeout */ extern int panic_timeout; @@ -2105,7 +2104,6 @@ static int s10_edac_dberr_handler(struct notifier_block *this, return NOTIFY_DONE; } -#endif /****************** Arria 10 EDAC Probe Function *********************/ static int altr_edac_a10_probe(struct platform_device *pdev) @@ -2154,8 +2152,7 @@ static int altr_edac_a10_probe(struct platform_device *pdev) irq_set_chained_handler_and_data(edac->sb_irq, altr_edac_a10_irq_handler, edac); - -#ifdef CONFIG_64BIT + if (edac->is_s10) { int dberror, err_addr; @@ -2178,15 +2175,14 @@ static int altr_edac_a10_probe(struct platform_device *pdev) regmap_write(edac->ecc_mgr_map, S10_SYSMGR_UE_ADDR_OFST, 0); } - } -#else - edac->db_irq = platform_get_irq(pdev, 1); - if (edac->db_irq < 0) - return edac->db_irq; + } else { + edac->db_irq = platform_get_irq(pdev, 1); + if (edac->db_irq < 0) + return edac->db_irq; - irq_set_chained_handler_and_data(edac->db_irq, - altr_edac_a10_irq_handler, edac); -#endif + irq_set_chained_handler_and_data(edac->db_irq, + altr_edac_a10_irq_handler, edac); + } for_each_child_of_node(pdev->dev.of_node, child) { if (!of_device_is_available(child)) From e09afa69e3f5d5a304940cf4c6ea17642a1e3993 Mon Sep 17 00:00:00 2001 From: Radhey Shyam Pandey Date: Thu, 25 Jun 2026 16:07:49 +0530 Subject: [PATCH 0008/1198] MAINTAINERS: Add Radhey Shyam Pandey as Xilinx EDAC reviewer I have volunteered to review Xilinx EDAC related changes. Add myself as a reviewer to stay aligned with ongoing patch activity and actively contribute to this subsystem. Signed-off-by: Radhey Shyam Pandey Signed-off-by: Borislav Petkov (AMD) Link: https://patch.msgid.link/20260625103749.1416083-1-radhey.shyam.pandey@amd.com --- MAINTAINERS | 3 +++ 1 file changed, 3 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index f16c09f76e7b..d413dac5c8b3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -29589,12 +29589,14 @@ F: include/uapi/linux/xilinx-v4l2-controls.h XILINX VERSAL EDAC DRIVER M: Shubhrajyoti Datta M: Sai Krishna Potthuri +R: Radhey Shyam Pandey S: Maintained F: Documentation/devicetree/bindings/memory-controllers/xlnx,versal-ddrmc-edac.yaml F: drivers/edac/versal_edac.c XILINX VERSALNET EDAC DRIVER M: Shubhrajyoti Datta +R: Radhey Shyam Pandey S: Maintained F: Documentation/devicetree/bindings/memory-controllers/xlnx,versal-net-ddrmc5.yaml F: drivers/edac/versalnet_edac.c @@ -29632,6 +29634,7 @@ F: include/dt-bindings/dma/xlnx-zynqmp-dpdma.h XILINX ZYNQMP OCM EDAC DRIVER M: Shubhrajyoti Datta M: Sai Krishna Potthuri +R: Radhey Shyam Pandey S: Maintained F: Documentation/devicetree/bindings/memory-controllers/xlnx,zynqmp-ocmc-1.0.yaml F: drivers/edac/zynqmp_edac.c From 36a6518e746dcd2e30391c61ce6a8c4bcafd7bb7 Mon Sep 17 00:00:00 2001 From: Pan Chuang Date: Mon, 13 Jul 2026 21:15:10 +0800 Subject: [PATCH 0009/1198] EDAC: Remove redundant dev_err() Since 55b48e23f5c4 ("genirq/devres: Add error handling in devm_request_*_irq()"), devm_request_irq() and devm_request_threaded_irq() automatically log detailed error messages on failure. Remove the now-redundant driver-specific dev_err() calls. Signed-off-by: Pan Chuang Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Andrew Jeffery # aspeed Link: https://patch.msgid.link/20260713131510.332386-1-panchuang@vivo.com --- drivers/edac/al_mc_edac.c | 12 ++---------- drivers/edac/aspeed_edac.c | 4 +--- drivers/edac/highbank_mc_edac.c | 4 +--- drivers/edac/thunderx_edac.c | 4 +--- drivers/edac/xgene_edac.c | 5 +---- 5 files changed, 6 insertions(+), 23 deletions(-) diff --git a/drivers/edac/al_mc_edac.c b/drivers/edac/al_mc_edac.c index 178b9e581a72..bf6921d8890b 100644 --- a/drivers/edac/al_mc_edac.c +++ b/drivers/edac/al_mc_edac.c @@ -302,12 +302,8 @@ static int al_mc_edac_probe(struct platform_device *pdev) IRQF_SHARED, pdev->name, pdev); - if (ret != 0) { - dev_err(&pdev->dev, - "failed to request UE IRQ %d (%d)\n", - al_mc->irq_ue, ret); + if (ret != 0) return ret; - } } if (al_mc->irq_ce > 0) { @@ -317,12 +313,8 @@ static int al_mc_edac_probe(struct platform_device *pdev) IRQF_SHARED, pdev->name, pdev); - if (ret != 0) { - dev_err(&pdev->dev, - "failed to request CE IRQ %d (%d)\n", - al_mc->irq_ce, ret); + if (ret != 0) return ret; - } } return 0; diff --git a/drivers/edac/aspeed_edac.c b/drivers/edac/aspeed_edac.c index dadb8acbee3d..6e069b255595 100644 --- a/drivers/edac/aspeed_edac.c +++ b/drivers/edac/aspeed_edac.c @@ -214,10 +214,8 @@ static int config_irq(void *ctx, struct platform_device *pdev) rc = devm_request_irq(&pdev->dev, irq, mcr_isr, IRQF_TRIGGER_HIGH, DRV_NAME, ctx); - if (rc) { - dev_err(&pdev->dev, "unable to request irq %d\n", irq); + if (rc) return rc; - } /* enable interrupts */ regmap_update_bits(aspeed_regmap, ASPEED_MCR_INTR_CTRL, diff --git a/drivers/edac/highbank_mc_edac.c b/drivers/edac/highbank_mc_edac.c index a8879d72d064..68d16cc8298d 100644 --- a/drivers/edac/highbank_mc_edac.c +++ b/drivers/edac/highbank_mc_edac.c @@ -235,10 +235,8 @@ static int highbank_mc_probe(struct platform_device *pdev) irq = platform_get_irq(pdev, 0); res = devm_request_irq(&pdev->dev, irq, highbank_mc_err_handler, 0, dev_name(&pdev->dev), mci); - if (res < 0) { - dev_err(&pdev->dev, "Unable to request irq %d\n", irq); + if (res < 0) goto err2; - } devres_close_group(&pdev->dev, NULL); return 0; diff --git a/drivers/edac/thunderx_edac.c b/drivers/edac/thunderx_edac.c index 75c04dfc3962..9c0a1e48f96f 100644 --- a/drivers/edac/thunderx_edac.c +++ b/drivers/edac/thunderx_edac.c @@ -729,10 +729,8 @@ static int thunderx_lmc_probe(struct pci_dev *pdev, thunderx_lmc_err_isr, thunderx_lmc_threaded_isr, 0, "[EDAC] ThunderX LMC", mci); - if (ret) { - dev_err(&pdev->dev, "Cannot set ISR: %d\n", ret); + if (ret) goto err_free; - } lmc->node = FIELD_GET(THUNDERX_NODE, pci_resource_start(pdev, 0)); diff --git a/drivers/edac/xgene_edac.c b/drivers/edac/xgene_edac.c index 9955396c9a52..62b8166dc287 100644 --- a/drivers/edac/xgene_edac.c +++ b/drivers/edac/xgene_edac.c @@ -1924,11 +1924,8 @@ static int xgene_edac_probe(struct platform_device *pdev) rc = devm_request_irq(&pdev->dev, irq, xgene_edac_isr, IRQF_SHARED, dev_name(&pdev->dev), edac); - if (rc) { - dev_err(&pdev->dev, - "Could not request IRQ %d\n", irq); + if (rc) goto out_err; - } } } From 0c4775d3a756b923c815327dc585ee167057ed52 Mon Sep 17 00:00:00 2001 From: Sang-Heon Jeon Date: Fri, 24 Jul 2026 03:45:29 +0900 Subject: [PATCH 0010/1198] RAS/AMD/ATL: Remove conditional return with no effect Both branches of the check return the same value, so the check has no effect. Remove it and return the value directly. This is the result of running the Coccinelle script from scripts/coccinelle/misc/cond_return_no_effect.cocci. Signed-off-by: Sang-Heon Jeon Signed-off-by: Borislav Petkov (AMD) Link: https://patch.msgid.link/20260723184538.3888637-28-ekffu200098@gmail.com --- drivers/ras/amd/atl/map.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/ras/amd/atl/map.c b/drivers/ras/amd/atl/map.c index 24a05af747d5..4ec9333ef745 100644 --- a/drivers/ras/amd/atl/map.c +++ b/drivers/ras/amd/atl/map.c @@ -771,9 +771,5 @@ int get_address_map(struct addr_ctx *ctx) dump_address_map(&ctx->map); - ret = validate_address_map(ctx); - if (ret) - return ret; - - return ret; + return validate_address_map(ctx); } From 141556543c9917d7c3d527f7eca6e288ec6bb58b Mon Sep 17 00:00:00 2001 From: Qiuxu Zhuo Date: Thu, 30 Jul 2026 10:42:29 +0800 Subject: [PATCH 0011/1198] EDAC/ie31200: Decouple DIMM width decoding from enum order The current method to get DIMM width relied on DEV_* enum ordering via a linear offset (+ DEV_X8), tightly coupling hardware encoding to enum layout. Replace it with explicit decoding to remove this dependency, as the enum is expected to grow with additional device widths. Signed-off-by: Qiuxu Zhuo Signed-off-by: Tony Luck Link: https://patch.msgid.link/20260730024238.4096623-2-qiuxu.zhuo@intel.com --- drivers/edac/ie31200_edac.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/drivers/edac/ie31200_edac.c b/drivers/edac/ie31200_edac.c index e3bd6436669b..bfd54012ae47 100644 --- a/drivers/edac/ie31200_edac.c +++ b/drivers/edac/ie31200_edac.c @@ -416,7 +416,23 @@ static void populate_dimm_info(struct dimm_data *dd, u32 addr_decode, int dimm, { dd->size = field_get(cfg->reg_mad_dimm_size_mask[dimm], addr_decode) * cfg->reg_mad_dimm_size_granularity; dd->ranks = field_get(cfg->reg_mad_dimm_rank_mask[dimm], addr_decode) + 1; - dd->dtype = field_get(cfg->reg_mad_dimm_width_mask[dimm], addr_decode) + DEV_X8; + + switch (field_get(cfg->reg_mad_dimm_width_mask[dimm], addr_decode)) { + case 0: + dd->dtype = DEV_X8; + break; + case 1: + dd->dtype = DEV_X16; + break; + case 2: + dd->dtype = DEV_X32; + break; + case 3: + dd->dtype = DEV_X64; + break; + default: + dd->dtype = DEV_UNKNOWN; + } } static void ie31200_get_dimm_config(struct mem_ctl_info *mci, void __iomem *window, From f4008169bd320eedb9ddf2b39eeb21370ddac278 Mon Sep 17 00:00:00 2001 From: Qiuxu Zhuo Date: Thu, 30 Jul 2026 10:42:30 +0800 Subject: [PATCH 0012/1198] EDAC/igen6: Fix interleave boundary condition The address translation logic splits the memory space into interleaved and non-interleaved regions using a boundary at 2 * s_size. The current check uses '>' and incorrectly classifies the boundary address (2 * s_size) as part of the interleaved region. This leads to incorrect channel/sub-channel selection at the region boundary. Fix the classification by using '>=' so that the boundary address is handled in the non-interleaved region, matching the hardware layout. Fixes: 10590a9d4f23 ("EDAC/igen6: Add EDAC driver for Intel client SoCs using IBECC") Signed-off-by: Qiuxu Zhuo Signed-off-by: Tony Luck Link: https://patch.msgid.link/20260730024238.4096623-3-qiuxu.zhuo@intel.com --- drivers/edac/igen6_edac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c index f1fc20d4ebf6..43b56a2eb547 100644 --- a/drivers/edac/igen6_edac.c +++ b/drivers/edac/igen6_edac.c @@ -1035,7 +1035,7 @@ static void decode_addr(u64 addr, u32 hash, u64 s_size, int l_map, { int intlv_bit = CHANNEL_HASH_LSB_MASK_BIT(hash) + 6; - if (addr > 2 * s_size) { + if (addr >= 2 * s_size) { *sub_addr = addr - s_size; *idx = l_map; return; From 540b79536f3a89a66c5b6c490110298d43025618 Mon Sep 17 00:00:00 2001 From: Qiuxu Zhuo Date: Thu, 30 Jul 2026 10:42:31 +0800 Subject: [PATCH 0013/1198] EDAC/igen6: Fix channel selection hash In channel selection hash mode, the hardware decoding logic always includes the channel interleave bit in XOR operations. However, the hash mask may or may not include this channel interleave bit. When the mask does include this bit, the current igen6_edac code performs XOR on the interleave bit twice, effectively ignoring it - which is incorrect. Fix this issue by ensuring the hash mask always includes the interleave bit, so XOR is performed on the interleave bit exactly once. Fixes: 10590a9d4f23 ("EDAC/igen6: Add EDAC driver for Intel client SoCs using IBECC") Signed-off-by: Qiuxu Zhuo Signed-off-by: Tony Luck Link: https://patch.msgid.link/20260730024238.4096623-4-qiuxu.zhuo@intel.com --- drivers/edac/igen6_edac.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c index 43b56a2eb547..f1fb644154ae 100644 --- a/drivers/edac/igen6_edac.c +++ b/drivers/edac/igen6_edac.c @@ -1009,14 +1009,22 @@ static void set_dimm_params(struct igen6_imc *imc, int chan) static int decode_chan_idx(u64 addr, u64 mask, int intlv_bit) { - u64 hash_addr = addr & mask, hash = 0; - u64 intlv = (addr >> intlv_bit) & 1; + u64 hash_addr, hash = 0; int i; + /* + * In hash mode, the @intlv_bit is the lowest selected bit of @addr + * to be XORed. While @mask may or may not include this @intlv_bit, + * we enforce that @mask includes @intlv_bit to ensure @intlv_bit is + * XORed exactly once. + */ + mask |= 1 << intlv_bit; + hash_addr = addr & mask; + for (i = 6; i < 20; i++) hash ^= (hash_addr >> i) & 1; - return (int)hash ^ intlv; + return (int)hash; } static u64 decode_channel_addr(u64 addr, int intlv_bit) From 7b348d0d401d478f1923ba20a34a61681d1f7971 Mon Sep 17 00:00:00 2001 From: Qiuxu Zhuo Date: Thu, 30 Jul 2026 10:42:32 +0800 Subject: [PATCH 0014/1198] EDAC/igen6: Fix channel address decode for non-hash mode In non-hash mode, decode_channel_addr() and channel index extraction used a hardcoded interleave bit position 6 instead of the actual intlv_bit parameter, causing incorrect channel address decoding. Fix this by using intlv_bit consistently in both hash and non-hash modes. Fixes: 10590a9d4f23 ("EDAC/igen6: Add EDAC driver for Intel client SoCs using IBECC") Signed-off-by: Qiuxu Zhuo Signed-off-by: Tony Luck Link: https://patch.msgid.link/20260730024238.4096623-5-qiuxu.zhuo@intel.com --- drivers/edac/igen6_edac.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c index f1fb644154ae..ea5628d780eb 100644 --- a/drivers/edac/igen6_edac.c +++ b/drivers/edac/igen6_edac.c @@ -1049,13 +1049,12 @@ static void decode_addr(u64 addr, u32 hash, u64 s_size, int l_map, return; } - if (CHANNEL_HASH_MODE(hash)) { - *sub_addr = decode_channel_addr(addr, intlv_bit); + *sub_addr = decode_channel_addr(addr, intlv_bit); + + if (CHANNEL_HASH_MODE(hash)) *idx = decode_chan_idx(addr, CHANNEL_HASH_MASK(hash), intlv_bit); - } else { - *sub_addr = decode_channel_addr(addr, 6); - *idx = GET_BITFIELD(addr, 6, 6); - } + else + *idx = GET_BITFIELD(addr, intlv_bit, intlv_bit); } static int igen6_decode(struct decoded_addr *res) From 0361f576ec0dffca13edc94580c8666146a91e02 Mon Sep 17 00:00:00 2001 From: Qiuxu Zhuo Date: Thu, 30 Jul 2026 10:42:33 +0800 Subject: [PATCH 0015/1198] EDAC/igen6: Fix Raptor Lake-P logged error address Raptor Lake-P was treated as using a different IBECC (In-Band ECC) error address format and therefore had a dedicated extraction path that shifted the logged address. However, Raptor Lake-P uses the same cache-line-granularity error address format as other IBECC platforms. The special handling causes the logged address to be decoded incorrectly. Fix the issue by removing Raptor Lake-P specific extraction logic and using the common path instead. This also allows reusing Alder Lake resource configuration data. Fixes: d23627a7688f ("EDAC/igen6: Add Intel Raptor Lake-P SoCs support") Signed-off-by: Qiuxu Zhuo Signed-off-by: Tony Luck Link: https://patch.msgid.link/20260730024238.4096623-6-qiuxu.zhuo@intel.com --- drivers/edac/igen6_edac.c | 39 ++++++--------------------------------- 1 file changed, 6 insertions(+), 33 deletions(-) diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c index ea5628d780eb..12d718a50e1c 100644 --- a/drivers/edac/igen6_edac.c +++ b/drivers/edac/igen6_edac.c @@ -175,8 +175,6 @@ static struct res_config { /* Set imc->dimm_{l_size,s_size,l_map}[chan]. */ void (*set_dimm_params)(struct igen6_imc *imc, int chan); bool (*ibecc_available)(struct pci_dev *pdev); - /* Extract error address logged in IBECC */ - u64 (*err_addr)(u64 ecclog); /* Convert error address logged in IBECC to system physical address */ u64 (*err_addr_to_sys_addr)(u64 eaddr, int mc); /* Convert error address logged in IBECC to integrated memory controller address */ @@ -522,11 +520,6 @@ static u64 adl_err_addr_to_imc_addr(u64 eaddr, int mc) return imc_addr; } -static u64 rpl_p_err_addr(u64 ecclog) -{ - return field_get(res_cfg->reg_eccerrlog_addr_mask, ecclog); -} - static enum mem_type ptl_h_get_mem_type(struct igen6_imc *imc) { u32 mtype, val; @@ -716,22 +709,6 @@ static struct res_config adl_n_cfg = { .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, }; -static struct res_config rpl_p_cfg = { - .machine_check = true, - .num_imc = 2, - .reg_mchbar_mask = GENMASK_ULL(41, 17), - .reg_tom_mask = GENMASK_ULL(41, 20), - .reg_touud_mask = GENMASK_ULL(41, 20), - .reg_eccerrlog_addr_mask = GENMASK_ULL(45, 5), - .imc_base = 0xd800, - .ibecc_base = 0xd400, - .ibecc_error_log_offset = 0x68, - .ibecc_available = tgl_ibecc_available, - .err_addr = rpl_p_err_addr, - .err_addr_to_sys_addr = adl_err_addr_to_sys_addr, - .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, -}; - static struct res_config mtl_ps_cfg = { .machine_check = true, .num_imc = 2, @@ -877,11 +854,11 @@ static struct pci_device_id igen6_pci_tbl[] = { { PCI_VDEVICE(INTEL, DID_ASL_SKU1), .driver_data = (kernel_ulong_t)&adl_n_cfg }, { PCI_VDEVICE(INTEL, DID_ASL_SKU2), .driver_data = (kernel_ulong_t)&adl_n_cfg }, { PCI_VDEVICE(INTEL, DID_ASL_SKU3), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_RPL_P_SKU1), .driver_data = (kernel_ulong_t)&rpl_p_cfg }, - { PCI_VDEVICE(INTEL, DID_RPL_P_SKU2), .driver_data = (kernel_ulong_t)&rpl_p_cfg }, - { PCI_VDEVICE(INTEL, DID_RPL_P_SKU3), .driver_data = (kernel_ulong_t)&rpl_p_cfg }, - { PCI_VDEVICE(INTEL, DID_RPL_P_SKU4), .driver_data = (kernel_ulong_t)&rpl_p_cfg }, - { PCI_VDEVICE(INTEL, DID_RPL_P_SKU5), .driver_data = (kernel_ulong_t)&rpl_p_cfg }, + { PCI_VDEVICE(INTEL, DID_RPL_P_SKU1), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_RPL_P_SKU2), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_RPL_P_SKU3), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_RPL_P_SKU4), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_RPL_P_SKU5), .driver_data = (kernel_ulong_t)&adl_cfg }, { PCI_VDEVICE(INTEL, DID_MTL_PS_SKU1), .driver_data = (kernel_ulong_t)&mtl_ps_cfg }, { PCI_VDEVICE(INTEL, DID_MTL_PS_SKU2), .driver_data = (kernel_ulong_t)&mtl_ps_cfg }, { PCI_VDEVICE(INTEL, DID_MTL_PS_SKU3), .driver_data = (kernel_ulong_t)&mtl_ps_cfg }, @@ -1237,11 +1214,7 @@ static void ecclog_work_cb(struct work_struct *work) llist_for_each_entry_safe(node, tmp, head, llnode) { memset(&res, 0, sizeof(res)); - if (res_cfg->err_addr) - eaddr = res_cfg->err_addr(node->ecclog); - else - eaddr = node->ecclog & res_cfg->reg_eccerrlog_addr_mask; - + eaddr = node->ecclog & res_cfg->reg_eccerrlog_addr_mask; res.mc = node->mc; res.sys_addr = res_cfg->err_addr_to_sys_addr(eaddr, res.mc); res.imc_addr = res_cfg->err_addr_to_imc_addr(eaddr, res.mc); From a118a5e2f172a5122d387022e5d1d41d30750738 Mon Sep 17 00:00:00 2001 From: Qiuxu Zhuo Date: Thu, 30 Jul 2026 10:42:34 +0800 Subject: [PATCH 0016/1198] EDAC/igen6: Remove unnecessary XOR on the zero-valued interleave bit When reconstructing the removed interleave bit from an inflated memory slice address, where a zero was inserted at the interleave bit position, it's unnecessary to XOR this zero-valued interleave bit. Remove this unnecessary XOR operation. No functional changes intended. Signed-off-by: Qiuxu Zhuo Signed-off-by: Tony Luck Link: https://patch.msgid.link/20260730024238.4096623-7-qiuxu.zhuo@intel.com --- drivers/edac/igen6_edac.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c index 12d718a50e1c..71ed50daeb19 100644 --- a/drivers/edac/igen6_edac.c +++ b/drivers/edac/igen6_edac.c @@ -448,16 +448,16 @@ static u64 mem_addr_to_sys_addr(u64 maddr) return maddr; } -static u64 mem_slice_hash(u64 addr, u64 mask, u64 hash_init, int intlv_bit) +static u64 mem_slice_hash(u64 addr, u64 mask, u64 hash_init) { + /* The interleave bit in @addr is a zero. */ u64 hash_addr = addr & mask, hash = hash_init; - u64 intlv = (addr >> intlv_bit) & 1; int i; for (i = 6; i < 20; i++) hash ^= (hash_addr >> i) & 1; - return hash ^ intlv; + return hash; } static u64 tgl_err_addr_to_mem_addr(u64 eaddr, int mc) @@ -478,7 +478,7 @@ static u64 tgl_err_addr_to_mem_addr(u64 eaddr, int mc) maddr = GET_BITFIELD(eaddr, intlv_bit, 63) << (intlv_bit + 1) | GET_BITFIELD(eaddr, 0, intlv_bit - 1); - hash = mem_slice_hash(maddr, mask, mc, intlv_bit); + hash = mem_slice_hash(maddr, mask, mc); return maddr | (hash << intlv_bit); } From 8ac9136d79e960b8b8b9a41b9d4076e4afe6de5e Mon Sep 17 00:00:00 2001 From: Qiuxu Zhuo Date: Thu, 30 Jul 2026 10:42:35 +0800 Subject: [PATCH 0017/1198] EDAC/igen6: Simplify compute die ID comments The existing comments repeat information already implied by the code structure. Shorten them to SoC names only to reduce clutter and improve readability. No functional changes intended. Signed-off-by: Qiuxu Zhuo Signed-off-by: Tony Luck Link: https://patch.msgid.link/20260730024238.4096623-8-qiuxu.zhuo@intel.com --- drivers/edac/igen6_edac.c | 29 +++++++++++++++-------------- 1 file changed, 15 insertions(+), 14 deletions(-) diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c index 71ed50daeb19..2960af172c57 100644 --- a/drivers/edac/igen6_edac.c +++ b/drivers/edac/igen6_edac.c @@ -223,7 +223,8 @@ static char ecclog_buf[ECCLOG_POOL_SIZE]; static struct irq_work ecclog_irq_work; static struct work_struct ecclog_work; -/* Compute die IDs for Elkhart Lake with IBECC */ +/* SoC compute die IDs with IBECC capability. */ +/* Elkhart Lake */ #define DID_EHL_SKU5 0x4514 #define DID_EHL_SKU6 0x4528 #define DID_EHL_SKU7 0x452a @@ -236,22 +237,22 @@ static struct work_struct ecclog_work; #define DID_EHL_SKU14 0x4534 #define DID_EHL_SKU15 0x4536 -/* Compute die IDs for ICL-NNPI with IBECC */ +/* ICL-NNPI */ #define DID_ICL_SKU8 0x4581 #define DID_ICL_SKU10 0x4585 #define DID_ICL_SKU11 0x4589 #define DID_ICL_SKU12 0x458d -/* Compute die IDs for Tiger Lake with IBECC */ +/* Tiger Lake */ #define DID_TGL_SKU 0x9a14 -/* Compute die IDs for Alder Lake with IBECC */ +/* Alder Lake */ #define DID_ADL_SKU1 0x4601 #define DID_ADL_SKU2 0x4602 #define DID_ADL_SKU3 0x4621 #define DID_ADL_SKU4 0x4641 -/* Compute die IDs for Alder Lake-N with IBECC */ +/* Alder Lake-N */ #define DID_ADL_N_SKU1 0x4614 #define DID_ADL_N_SKU2 0x4617 #define DID_ADL_N_SKU3 0x461b @@ -265,38 +266,38 @@ static struct work_struct ecclog_work; #define DID_ADL_N_SKU11 0x467c #define DID_ADL_N_SKU12 0x4632 -/* Compute die IDs for Arizona Beach with IBECC */ +/* Arizona Beach */ #define DID_AZB_SKU1 0x4676 -/* Compute did IDs for Amston Lake with IBECC */ +/* Amston Lake */ #define DID_ASL_SKU1 0x464a #define DID_ASL_SKU2 0x4646 #define DID_ASL_SKU3 0x4652 -/* Compute die IDs for Raptor Lake-P with IBECC */ +/* Raptor Lake-P */ #define DID_RPL_P_SKU1 0xa706 #define DID_RPL_P_SKU2 0xa707 #define DID_RPL_P_SKU3 0xa708 #define DID_RPL_P_SKU4 0xa716 #define DID_RPL_P_SKU5 0xa718 -/* Compute die IDs for Meteor Lake-PS with IBECC */ +/* Meteor Lake-PS */ #define DID_MTL_PS_SKU1 0x7d21 #define DID_MTL_PS_SKU2 0x7d22 #define DID_MTL_PS_SKU3 0x7d23 #define DID_MTL_PS_SKU4 0x7d24 -/* Compute die IDs for Meteor Lake-P with IBECC */ +/* Meteor Lake-P */ #define DID_MTL_P_SKU1 0x7d01 #define DID_MTL_P_SKU2 0x7d02 #define DID_MTL_P_SKU3 0x7d14 -/* Compute die IDs for Arrow Lake-UH with IBECC */ +/* Arrow Lake-UH */ #define DID_ARL_UH_SKU1 0x7d06 #define DID_ARL_UH_SKU2 0x7d20 #define DID_ARL_UH_SKU3 0x7d30 -/* Compute die IDs for Panther Lake-H with IBECC */ +/* Panther Lake-H */ #define DID_PTL_H_SKU1 0xb000 #define DID_PTL_H_SKU2 0xb001 #define DID_PTL_H_SKU3 0xb002 @@ -312,10 +313,10 @@ static struct work_struct ecclog_work; #define DID_PTL_H_SKU13 0xb02a #define DID_PTL_H_SKU14 0xb00a -/* Compute die IDs for Wildcat Lake with IBECC */ +/* Wildcat Lake */ #define DID_WCL_SKU1 0xfd00 -/* Compute die IDs for Nova Lake-H/HX with IBECC */ +/* Nova Lake-H/HX */ #define DID_NVL_H_SKU1 0xd701 #define DID_NVL_H_SKU2 0xd702 #define DID_NVL_H_SKU3 0xd704 From e492449e39b7aee9bfcb1bda3181fa942d24cdd2 Mon Sep 17 00:00:00 2001 From: Qiuxu Zhuo Date: Thu, 30 Jul 2026 10:42:36 +0800 Subject: [PATCH 0018/1198] EDAC/igen6: Detect present memory controllers at runtime The igen6_edac currently relies on res_config::num_imc to describe the number of memory controllers supported by each SoC. As a result, adding support for a new platform requires updating this configuration even though the hardware can be discovered at runtime. Instead, detect the number of present memory controllers at runtime and size the driver state accordingly. This eliminates the need to update res_config whenever a new SoC variant is added. Signed-off-by: Qiuxu Zhuo Signed-off-by: Tony Luck Link: https://patch.msgid.link/20260730024238.4096623-9-qiuxu.zhuo@intel.com --- drivers/edac/igen6_edac.c | 97 ++++++++++++++++++++++++++------------- 1 file changed, 64 insertions(+), 33 deletions(-) diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c index 2960af172c57..d468c655348c 100644 --- a/drivers/edac/igen6_edac.c +++ b/drivers/edac/igen6_edac.c @@ -42,7 +42,8 @@ #define GET_BITFIELD(v, lo, hi) (((v) & GENMASK_ULL(hi, lo)) >> (lo)) -#define NUM_IMC 2 /* Max memory controllers */ +/* Probing upper bound, not a hardware capability limit. */ +#define MAX_IMC_TO_PROBE 8 #define NUM_CHANNELS 2 /* Max channels */ #define NUM_DIMMS 2 /* Max DIMMs per channel */ @@ -182,11 +183,11 @@ static struct res_config { } *res_cfg; static struct igen6_pvt { - struct igen6_imc imc[NUM_IMC]; void __iomem *memss_pma_cr; u64 ms_hash; u64 ms_s_size; int ms_l_map; + struct igen6_imc imc[]; } *igen6_pvt; /* The top of low usable DRAM */ @@ -353,6 +354,46 @@ static int get_mchbar(struct pci_dev *pdev, u64 *mchbar) return 0; } +/* Check whether the memory controller is absent. */ +static bool imc_absent(void __iomem *window) +{ + return readl(window + MAD_INTER_CHANNEL_OFFSET) == ~0; +} + +/* Return MMIO base address of the memory controller if it's present, otherwise return NULL. */ +static void __iomem *map_imc_window(u64 mchbar, int pmc) +{ + void __iomem *window; + + window = ioremap(mchbar + pmc * MCHBAR_SIZE, MCHBAR_SIZE); + if (!window) + return NULL; + + if (imc_absent(window)) { + iounmap(window); + return NULL; + } + + return window; +} + +/* Return the number of present memory controllers. */ +static int get_imc_num(u64 mchbar) +{ + void __iomem *window; + int lmc, pmc; + + for (lmc = 0, pmc = 0; pmc < MAX_IMC_TO_PROBE; pmc++) { + window = map_imc_window(mchbar, pmc); + if (window) { + iounmap(window); + lmc++; + } + } + + return lmc; +} + static bool ehl_ibecc_available(struct pci_dev *pdev) { u32 v; @@ -1457,18 +1498,27 @@ static struct igen6_pvt *igen6_pvt_setup(struct pci_dev *pdev) { void __iomem *memss_pma_cr; struct igen6_pvt *pvt; + int imc_num, rc; u64 mchbar; - int rc; - - pvt = kzalloc_obj(*igen6_pvt); - if (!pvt) - return NULL; rc = get_mchbar(pdev, &mchbar); - if (rc) { - kfree(pvt); + if (rc) + return NULL; + + imc_num = get_imc_num(mchbar); + if (!imc_num) { + igen6_printk(KERN_ERR, "No mc found.\n"); return NULL; } + edac_dbg(2, "%d mcs found.\n", imc_num); + + /* Use the runtime detected IMC count. */ + if (res_cfg->num_imc != imc_num) + res_cfg->num_imc = imc_num; + + pvt = kzalloc_flex(*pvt, imc, imc_num); + if (!pvt) + return NULL; memss_pma_cr = ioremap(mchbar, MCHBAR_SIZE * 2); if (!memss_pma_cr) { @@ -1553,12 +1603,6 @@ static void igen6_check(struct mem_ctl_info *mci) irq_work_queue(&ecclog_irq_work); } -/* Check whether the memory controller is absent. */ -static bool igen6_imc_absent(void __iomem *window) -{ - return readl(window + MAD_INTER_CHANNEL_OFFSET) == ~0; -} - static void imc_release(struct device *dev) { /* Nothing to do, the 'imc' owns the 'dev' and will also release it. */ @@ -1670,26 +1714,15 @@ static int igen6_register_mcis(struct pci_dev *pdev, u64 mchbar) { void __iomem *window; int lmc, pmc, rc; - u64 base; - for (lmc = 0, pmc = 0; pmc < NUM_IMC; pmc++) { - base = mchbar + pmc * MCHBAR_SIZE; - window = ioremap(base, MCHBAR_SIZE); - if (!window) { - igen6_printk(KERN_ERR, "Failed to ioremap 0x%llx for mc%d\n", base, pmc); - rc = -ENOMEM; - goto out_unregister_mcis; - } - - if (igen6_imc_absent(window)) { - iounmap(window); - edac_dbg(2, "Skip absent mc%d\n", pmc); + for (lmc = 0, pmc = 0; pmc < MAX_IMC_TO_PROBE; pmc++) { + window = map_imc_window(mchbar, pmc); + if (!window) continue; - } rc = igen6_register_mci(lmc, window, pdev); if (rc) - goto out_iounmap; + goto err_unregister; /* Done, if all present MCs are detected and registered. */ if (++lmc >= res_cfg->num_imc) @@ -1709,10 +1742,8 @@ static int igen6_register_mcis(struct pci_dev *pdev, u64 mchbar) return 0; -out_iounmap: +err_unregister: iounmap(window); - -out_unregister_mcis: igen6_unregister_mcis(); return rc; From 1f43c17ce550e8ed628afd7fb3226c904076f864 Mon Sep 17 00:00:00 2001 From: Qiuxu Zhuo Date: Thu, 30 Jul 2026 10:42:37 +0800 Subject: [PATCH 0019/1198] EDAC/igen6: Remove redundant resource configuration tables Several resource configuration tables differ only in their num_imc value, while all other fields are identical. Their only purpose is to describe the number of memory controllers supported by a platform. Since IMC count is now detected at runtime, these duplicate tables no longer carry any unique platform information. Reuse the shared configurations and remove the redundant tables. Signed-off-by: Qiuxu Zhuo Signed-off-by: Tony Luck Link: https://patch.msgid.link/20260730024238.4096623-10-qiuxu.zhuo@intel.com --- drivers/edac/igen6_edac.c | 66 +++++++++++---------------------------- 1 file changed, 19 insertions(+), 47 deletions(-) diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c index d468c655348c..e10e29f1a5f5 100644 --- a/drivers/edac/igen6_edac.c +++ b/drivers/edac/igen6_edac.c @@ -721,6 +721,7 @@ static struct res_config tgl_cfg = { .err_addr_to_imc_addr = tgl_err_addr_to_imc_addr, }; +/* Shared by Alder Lake, Alder Lake-N, Arizona Beach, Amston Lake, and Raptor Lake-P */ static struct res_config adl_cfg = { .machine_check = true, .num_imc = 2, @@ -736,21 +737,6 @@ static struct res_config adl_cfg = { .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, }; -static struct res_config adl_n_cfg = { - .machine_check = true, - .num_imc = 1, - .reg_mchbar_mask = GENMASK_ULL(41, 17), - .reg_tom_mask = GENMASK_ULL(41, 20), - .reg_touud_mask = GENMASK_ULL(41, 20), - .reg_eccerrlog_addr_mask = GENMASK_ULL(45, 5), - .imc_base = 0xd800, - .ibecc_base = 0xd400, - .ibecc_error_log_offset = 0x68, - .ibecc_available = tgl_ibecc_available, - .err_addr_to_sys_addr = adl_err_addr_to_sys_addr, - .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, -}; - static struct res_config mtl_ps_cfg = { .machine_check = true, .num_imc = 2, @@ -768,6 +754,7 @@ static struct res_config mtl_ps_cfg = { .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, }; +/* Shared by Meteor Lake-P, Arrow Lake-UH, and Wildcat Lake */ static struct res_config mtl_p_cfg = { .machine_check = true, .num_imc = 2, @@ -813,21 +800,6 @@ static struct res_config ptl_h_cfg = { .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, }; -static struct res_config wcl_cfg = { - .machine_check = true, - .num_imc = 1, - .reg_mchbar_mask = GENMASK_ULL(41, 17), - .reg_tom_mask = GENMASK_ULL(41, 20), - .reg_touud_mask = GENMASK_ULL(41, 20), - .reg_eccerrlog_addr_mask = GENMASK_ULL(38, 5), - .imc_base = 0xd800, - .ibecc_base = 0xd400, - .ibecc_error_log_offset = 0x170, - .ibecc_available = mtl_p_ibecc_available, - .err_addr_to_sys_addr = adl_err_addr_to_sys_addr, - .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, -}; - static struct res_config nvl_h_cfg = { .machine_check = true, .num_imc = 2, @@ -880,22 +852,22 @@ static struct pci_device_id igen6_pci_tbl[] = { { PCI_VDEVICE(INTEL, DID_ADL_SKU2), .driver_data = (kernel_ulong_t)&adl_cfg }, { PCI_VDEVICE(INTEL, DID_ADL_SKU3), .driver_data = (kernel_ulong_t)&adl_cfg }, { PCI_VDEVICE(INTEL, DID_ADL_SKU4), .driver_data = (kernel_ulong_t)&adl_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU1), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU2), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU3), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU4), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU5), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU6), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU7), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU8), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU9), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU10), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU11), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ADL_N_SKU12), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_AZB_SKU1), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ASL_SKU1), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ASL_SKU2), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_ASL_SKU3), .driver_data = (kernel_ulong_t)&adl_n_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU1), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU2), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU3), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU4), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU5), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU6), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU7), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU8), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU9), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU10), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU11), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU12), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_AZB_SKU1), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ASL_SKU1), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ASL_SKU2), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ASL_SKU3), .driver_data = (kernel_ulong_t)&adl_cfg }, { PCI_VDEVICE(INTEL, DID_RPL_P_SKU1), .driver_data = (kernel_ulong_t)&adl_cfg }, { PCI_VDEVICE(INTEL, DID_RPL_P_SKU2), .driver_data = (kernel_ulong_t)&adl_cfg }, { PCI_VDEVICE(INTEL, DID_RPL_P_SKU3), .driver_data = (kernel_ulong_t)&adl_cfg }, @@ -911,6 +883,7 @@ static struct pci_device_id igen6_pci_tbl[] = { { PCI_VDEVICE(INTEL, DID_ARL_UH_SKU1), .driver_data = (kernel_ulong_t)&mtl_p_cfg }, { PCI_VDEVICE(INTEL, DID_ARL_UH_SKU2), .driver_data = (kernel_ulong_t)&mtl_p_cfg }, { PCI_VDEVICE(INTEL, DID_ARL_UH_SKU3), .driver_data = (kernel_ulong_t)&mtl_p_cfg }, + { PCI_VDEVICE(INTEL, DID_WCL_SKU1), .driver_data = (kernel_ulong_t)&mtl_p_cfg }, { PCI_VDEVICE(INTEL, DID_PTL_H_SKU1), .driver_data = (kernel_ulong_t)&ptl_h_cfg }, { PCI_VDEVICE(INTEL, DID_PTL_H_SKU2), .driver_data = (kernel_ulong_t)&ptl_h_cfg }, { PCI_VDEVICE(INTEL, DID_PTL_H_SKU3), .driver_data = (kernel_ulong_t)&ptl_h_cfg }, @@ -925,7 +898,6 @@ static struct pci_device_id igen6_pci_tbl[] = { { PCI_VDEVICE(INTEL, DID_PTL_H_SKU12), .driver_data = (kernel_ulong_t)&ptl_h_cfg }, { PCI_VDEVICE(INTEL, DID_PTL_H_SKU13), .driver_data = (kernel_ulong_t)&ptl_h_cfg }, { PCI_VDEVICE(INTEL, DID_PTL_H_SKU14), .driver_data = (kernel_ulong_t)&ptl_h_cfg }, - { PCI_VDEVICE(INTEL, DID_WCL_SKU1), .driver_data = (kernel_ulong_t)&wcl_cfg }, { PCI_VDEVICE(INTEL, DID_NVL_H_SKU1), .driver_data = (kernel_ulong_t)&nvl_h_cfg }, { PCI_VDEVICE(INTEL, DID_NVL_H_SKU2), .driver_data = (kernel_ulong_t)&nvl_h_cfg }, { PCI_VDEVICE(INTEL, DID_NVL_H_SKU3), .driver_data = (kernel_ulong_t)&nvl_h_cfg }, From 377c68b988d9c36beb6dceedf81ed0ff55331aa9 Mon Sep 17 00:00:00 2001 From: Qiuxu Zhuo Date: Thu, 30 Jul 2026 10:42:38 +0800 Subject: [PATCH 0020/1198] EDAC/igen6: Refactor address translation logic The igen6 EDAC driver implements similar interleave and hash translation logic at multiple levels of the memory hierarchy. The separate implementations duplicate decoding logic, making future changes harder and increasing the risk of behavior diverging. Consolidate the common address translation operations into shared helpers so all decoding paths use a single implementation. No functional changes intended. Signed-off-by: Qiuxu Zhuo Signed-off-by: Tony Luck Link: https://patch.msgid.link/20260730024238.4096623-11-qiuxu.zhuo@intel.com --- drivers/edac/igen6_edac.c | 244 +++++++++++++++++++++++++------------- 1 file changed, 159 insertions(+), 85 deletions(-) diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c index e10e29f1a5f5..6abc9b203748 100644 --- a/drivers/edac/igen6_edac.c +++ b/drivers/edac/igen6_edac.c @@ -123,6 +123,43 @@ #define MEM_SLICE_HASH_MASK(v) (GET_BITFIELD(v, 6, 19) << 6) #define MEM_SLICE_HASH_LSB_MASK_BIT(v) GET_BITFIELD(v, 24, 26) +/* + * A slice represents a portion of memory space participating in an + * interleave relationship within the memory hierarchy. + * + * It can represent in different levels such as: + * + * - a pair of memory controllers + * - a memory controller + * - a memory channel + * - a memory sub-channel / DIMM + * + * +--------+ + * | | + * | Zone 1 | + * | | + * +--------+ +--------+ + * | | | | + * | | | | + * | Zone 0 | | Zone 0 | + * | | | | + * | | | | + * +--------+ +--------+ + * + * Slice L Slice S + * + * Memory space is divided into: + * + * - Zone 0 : Interleaved region + * - Zone 1 : Non-interleaved region (upper part of the large slice). + */ +struct slice { + /* Slice address. */ + u64 addr; + /* Slice that @addr belongs to. */ + int id; +}; + struct igen6_imc { int mc; struct mem_ctl_info *mci; @@ -323,6 +360,102 @@ static struct work_struct ecclog_work; #define DID_NVL_H_SKU3 0xd704 #define DID_NVL_H_SKU4 0xd705 +/* Remove the interleave bit and shift upper part down to fill gap. */ +static u64 squeeze_addr(u64 addr, int intlv_bit) +{ + u64 slice_addr; + + slice_addr = GET_BITFIELD(addr, intlv_bit + 1, 63) << intlv_bit; + slice_addr |= GET_BITFIELD(addr, 0, intlv_bit - 1); + + return slice_addr; +} + +/* Shift the upper bits up and insert a zero at the @intlv_bit bit position. */ +static u64 inflate_addr(u64 addr, int intlv_bit) +{ + u64 inflated_addr; + + /* Insert a zero at @intlv_bit position. */ + inflated_addr = GET_BITFIELD(addr, intlv_bit, 63) << (intlv_bit + 1); + inflated_addr |= GET_BITFIELD(addr, 0, intlv_bit - 1); + + return inflated_addr; +} + +static u64 compute_hash(u64 addr, u64 hash_mask, u64 hash_base, int intlv_bit) +{ + u64 hash_addr; + int i; + + /* + * In hash mode, @intlv_bit is the lowest selected bit of @addr + * to be XORed. While @mask may or may not include this @intlv_bit, + * we enforce that @mask includes @intlv_bit to ensure @intlv_bit is + * XORed exactly once. + */ + hash_mask |= BIT_ULL(intlv_bit); + hash_addr = addr & hash_mask; + + for (i = 6; i < 20; i++) + hash_base ^= (hash_addr >> i) & 1; + + return hash_base; +} + +/* + * Converts a higher-level address (system / IMC / channel) into a lower-level + * slice address and identifier. + */ +static void translate_to_lower_level(u64 addr, u64 hash_mask, u64 hash_base, + int intlv_bit, u64 s_size, int l_map, + struct slice *slice) +{ + /* In non-interleave zone. */ + if (addr >= 2 * s_size) { + slice->addr = addr - s_size; + slice->id = l_map; + return; + } + + /* In interleave zone. */ + slice->addr = squeeze_addr(addr, intlv_bit); + + /* Non-hash mode. */ + if (!hash_mask) { + slice->id = GET_BITFIELD(addr, intlv_bit, intlv_bit); + return; + } + + /* Hash mode. */ + slice->id = compute_hash(addr, hash_mask, hash_base, intlv_bit); +} + +/* Reconstruct address for upper memory hierarchy level. */ +static u64 translate_to_upper_level(u64 addr, u64 hash_mask, u64 hash_base, + int intlv_bit, u64 s_size) +{ + u64 inflated_addr, hash_val; + + /* In non-interleave zone. */ + if (addr >= s_size) + return addr + s_size; + + /* + * In interleave zone. + * + * Insert a zero at @intlv_bit position. + */ + inflated_addr = inflate_addr(addr, intlv_bit); + + /* + * Reconstruct the removed interleave bit and use it to replace + * the zero at @intlv_bit position. + */ + hash_val = compute_hash(inflated_addr, hash_mask, hash_base, intlv_bit); + return inflated_addr | (hash_val << intlv_bit); +} + static int get_mchbar(struct pci_dev *pdev, u64 *mchbar) { union { @@ -490,21 +623,9 @@ static u64 mem_addr_to_sys_addr(u64 maddr) return maddr; } -static u64 mem_slice_hash(u64 addr, u64 mask, u64 hash_init) -{ - /* The interleave bit in @addr is a zero. */ - u64 hash_addr = addr & mask, hash = hash_init; - int i; - - for (i = 6; i < 20; i++) - hash ^= (hash_addr >> i) & 1; - - return hash; -} - static u64 tgl_err_addr_to_mem_addr(u64 eaddr, int mc) { - u64 maddr, hash, mask, ms_s_size; + u64 mask, ms_s_size; int intlv_bit; u32 ms_hash; @@ -517,12 +638,7 @@ static u64 tgl_err_addr_to_mem_addr(u64 eaddr, int mc) mask = MEM_SLICE_HASH_MASK(ms_hash); intlv_bit = MEM_SLICE_HASH_LSB_MASK_BIT(ms_hash) + 6; - maddr = GET_BITFIELD(eaddr, intlv_bit, 63) << (intlv_bit + 1) | - GET_BITFIELD(eaddr, 0, intlv_bit - 1); - - hash = mem_slice_hash(maddr, mask, mc); - - return maddr | (hash << intlv_bit); + return translate_to_upper_level(eaddr, mask, mc, intlv_bit, ms_s_size); } static u64 tgl_err_addr_to_sys_addr(u64 eaddr, int mc) @@ -544,8 +660,9 @@ static u64 adl_err_addr_to_sys_addr(u64 eaddr, int mc) static u64 adl_err_addr_to_imc_addr(u64 eaddr, int mc) { - u64 imc_addr, ms_s_size = igen6_pvt->ms_s_size; + u64 ms_s_size = igen6_pvt->ms_s_size; struct igen6_imc *imc = &igen6_pvt->imc[mc]; + struct slice slice; int intlv_bit; u32 mc_hash; @@ -556,10 +673,8 @@ static u64 adl_err_addr_to_imc_addr(u64 eaddr, int mc) intlv_bit = MAC_MC_HASH_LSB(mc_hash) + 6; - imc_addr = GET_BITFIELD(eaddr, intlv_bit + 1, 63) << intlv_bit | - GET_BITFIELD(eaddr, 0, intlv_bit - 1); - - return imc_addr; + translate_to_lower_level(eaddr, 0, 0, intlv_bit, ms_s_size, 0, &slice); + return slice.addr; } static enum mem_type ptl_h_get_mem_type(struct igen6_imc *imc) @@ -998,62 +1113,13 @@ static void set_dimm_params(struct igen6_imc *imc, int chan) imc->dimm_s_size[chan] = MAD_DIMM_CH_DIMM_S_SIZE(val); } -static int decode_chan_idx(u64 addr, u64 mask, int intlv_bit) -{ - u64 hash_addr, hash = 0; - int i; - - /* - * In hash mode, the @intlv_bit is the lowest selected bit of @addr - * to be XORed. While @mask may or may not include this @intlv_bit, - * we enforce that @mask includes @intlv_bit to ensure @intlv_bit is - * XORed exactly once. - */ - mask |= 1 << intlv_bit; - hash_addr = addr & mask; - - for (i = 6; i < 20; i++) - hash ^= (hash_addr >> i) & 1; - - return (int)hash; -} - -static u64 decode_channel_addr(u64 addr, int intlv_bit) -{ - u64 channel_addr; - - /* Remove the interleave bit and shift upper part down to fill gap */ - channel_addr = GET_BITFIELD(addr, intlv_bit + 1, 63) << intlv_bit; - channel_addr |= GET_BITFIELD(addr, 0, intlv_bit - 1); - - return channel_addr; -} - -static void decode_addr(u64 addr, u32 hash, u64 s_size, int l_map, - int *idx, u64 *sub_addr) -{ - int intlv_bit = CHANNEL_HASH_LSB_MASK_BIT(hash) + 6; - - if (addr >= 2 * s_size) { - *sub_addr = addr - s_size; - *idx = l_map; - return; - } - - *sub_addr = decode_channel_addr(addr, intlv_bit); - - if (CHANNEL_HASH_MODE(hash)) - *idx = decode_chan_idx(addr, CHANNEL_HASH_MASK(hash), intlv_bit); - else - *idx = GET_BITFIELD(addr, intlv_bit, intlv_bit); -} - static int igen6_decode(struct decoded_addr *res) { struct igen6_imc *imc = &igen6_pvt->imc[res->mc]; - u64 addr = res->imc_addr, sub_addr, s_size; - int idx, l_map; - u32 hash; + u64 addr = res->imc_addr, s_size; + int intlv_bit, l_map; + u32 hash, hash_mask; + struct slice slice; if (addr >= igen6_tom) { edac_dbg(0, "Address 0x%llx out of range\n", addr); @@ -1064,17 +1130,25 @@ static int igen6_decode(struct decoded_addr *res) hash = readl(imc->window + CHANNEL_HASH_OFFSET); s_size = imc->ch_s_size; l_map = imc->ch_l_map; - decode_addr(addr, hash, s_size, l_map, &idx, &sub_addr); - res->channel_idx = idx; - res->channel_addr = sub_addr; + hash_mask = CHANNEL_HASH_MODE(hash) ? CHANNEL_HASH_MASK(hash) : 0; + intlv_bit = CHANNEL_HASH_LSB_MASK_BIT(hash) + 6; + + translate_to_lower_level(addr, hash_mask, 0, intlv_bit, s_size, l_map, &slice); + + res->channel_idx = slice.id; + res->channel_addr = slice.addr; /* Decode sub-channel/DIMM */ hash = readl(imc->window + CHANNEL_EHASH_OFFSET); - s_size = imc->dimm_s_size[idx]; - l_map = imc->dimm_l_map[idx]; - decode_addr(res->channel_addr, hash, s_size, l_map, &idx, &sub_addr); - res->sub_channel_idx = idx; - res->sub_channel_addr = sub_addr; + s_size = imc->dimm_s_size[res->channel_idx]; + l_map = imc->dimm_l_map[res->channel_idx]; + hash_mask = CHANNEL_HASH_MODE(hash) ? CHANNEL_HASH_MASK(hash) : 0; + intlv_bit = CHANNEL_HASH_LSB_MASK_BIT(hash) + 6; + + translate_to_lower_level(res->channel_addr, hash_mask, 0, intlv_bit, s_size, l_map, &slice); + + res->sub_channel_idx = slice.id; + res->sub_channel_addr = slice.addr; return 0; } From 1713cc6b0e1904cf2c2b477ff25faf163c43cbdf Mon Sep 17 00:00:00 2001 From: Qiuxu Zhuo Date: Thu, 30 Jul 2026 10:54:54 +0800 Subject: [PATCH 0021/1198] EDAC/igen6: Add Intel Starfire SoCs support Starfire is a derivative of Panther Lake SoC and shares a similar memory subsystem architecture. Add Starfire compute die ID and reuse Panther Lake's configuration data for EDAC support. Signed-off-by: Qiuxu Zhuo Signed-off-by: Tony Luck Tested-by: Jie Wang Link: https://patch.msgid.link/20260730025454.4099934-1-qiuxu.zhuo@intel.com --- drivers/edac/igen6_edac.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c index 6abc9b203748..776c5db2f598 100644 --- a/drivers/edac/igen6_edac.c +++ b/drivers/edac/igen6_edac.c @@ -351,6 +351,9 @@ static struct work_struct ecclog_work; #define DID_PTL_H_SKU13 0xb02a #define DID_PTL_H_SKU14 0xb00a +/* Starfire */ +#define DID_STF_SKU1 0xb02b + /* Wildcat Lake */ #define DID_WCL_SKU1 0xfd00 @@ -885,6 +888,7 @@ static struct res_config mtl_p_cfg = { .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, }; +/* Shared by Panther Lake-H and Starfire */ static struct res_config ptl_h_cfg = { .machine_check = true, .num_imc = 2, @@ -1013,6 +1017,7 @@ static struct pci_device_id igen6_pci_tbl[] = { { PCI_VDEVICE(INTEL, DID_PTL_H_SKU12), .driver_data = (kernel_ulong_t)&ptl_h_cfg }, { PCI_VDEVICE(INTEL, DID_PTL_H_SKU13), .driver_data = (kernel_ulong_t)&ptl_h_cfg }, { PCI_VDEVICE(INTEL, DID_PTL_H_SKU14), .driver_data = (kernel_ulong_t)&ptl_h_cfg }, + { PCI_VDEVICE(INTEL, DID_STF_SKU1), .driver_data = (kernel_ulong_t)&ptl_h_cfg }, { PCI_VDEVICE(INTEL, DID_NVL_H_SKU1), .driver_data = (kernel_ulong_t)&nvl_h_cfg }, { PCI_VDEVICE(INTEL, DID_NVL_H_SKU2), .driver_data = (kernel_ulong_t)&nvl_h_cfg }, { PCI_VDEVICE(INTEL, DID_NVL_H_SKU3), .driver_data = (kernel_ulong_t)&nvl_h_cfg }, From 66cc9dec919dd63d8e4b3d386f7aed3ae684e645 Mon Sep 17 00:00:00 2001 From: Jad Keskes Date: Thu, 30 Jul 2026 15:55:48 +0100 Subject: [PATCH 0022/1198] EDAC/device_sysfs: Use kstrtouint() for poll_msec to prevent truncation The poll_msec sysfs store file uses simple_strtoul() which accepts an unsigned long, but the target field (poll_msec) is unsigned int. On 64-bit systems, a value > UINT_MAX is silently truncated when stored. Fix the mismatch by using kstrtouint() instead. This rejects values larger than UINT_MAX at parse time, making truncation impossible. Also add a check for value < 1 to reject the 0-delay case, which would cause the poll work to spin without delay and consume 100% CPU. Fixes: e27e3dac6517 ("drivers/edac: add edac_device class") Signed-off-by: Jad Keskes Signed-off-by: Borislav Petkov (AMD) Link: https://patch.msgid.link/20260730145549.148229-1-inasj268@gmail.com --- drivers/edac/edac_device_sysfs.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/edac/edac_device_sysfs.c b/drivers/edac/edac_device_sysfs.c index b1c2717cd023..6995ce039db9 100644 --- a/drivers/edac/edac_device_sysfs.c +++ b/drivers/edac/edac_device_sysfs.c @@ -88,14 +88,21 @@ static ssize_t edac_device_ctl_poll_msec_store(struct edac_device_ctl_info *ctl_info, const char *data, size_t count) { - unsigned long value; + unsigned int value; + int ret; /* get the value and enforce that it is non-zero, must be at least * one millisecond for the delay period, between scans * Then cancel last outstanding delay for the work request * and set a new one. */ - value = simple_strtoul(data, NULL, 0); + ret = kstrtouint(data, 0, &value); + if (ret < 0) + return ret; + + if (value < 1) + return -EINVAL; + edac_device_reset_delay_period(ctl_info, value); return count; From 9987979189133486632842d894603813b22937e1 Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Fri, 7 Aug 2026 14:16:17 -0700 Subject: [PATCH 0023/1198] EDAC/device_sysfs: Cleanup around edac_device_ctl_poll_msec_store() - Align function args - Fix comment style - Fixup formatting around edac_device_reset_delay_period() too The not-too-trivial change is converting the edac_device_reset_delay_period() msec argument to unsigned int as that is what the rest of the code expects. Signed-off-by: Borislav Petkov (AMD) --- drivers/edac/edac_device.c | 10 +++------- drivers/edac/edac_device_sysfs.c | 12 +++++------- drivers/edac/edac_module.h | 3 +-- 3 files changed, 9 insertions(+), 16 deletions(-) diff --git a/drivers/edac/edac_device.c b/drivers/edac/edac_device.c index cf0d3c2dfc04..638be1f47c59 100644 --- a/drivers/edac/edac_device.c +++ b/drivers/edac/edac_device.c @@ -342,14 +342,10 @@ static void edac_device_workq_teardown(struct edac_device_ctl_info *edac_dev) } /* - * edac_device_reset_delay_period - * - * need to stop any outstanding workq queued up at this time - * because we will be resetting the sleep time. - * Then restart the workq on the new delay + * Stop any outstanding workq queued up at this time because sleep time will + * be reset. Then restart the workq on the new delay. */ -void edac_device_reset_delay_period(struct edac_device_ctl_info *edac_dev, - unsigned long msec) +void edac_device_reset_delay_period(struct edac_device_ctl_info *edac_dev, unsigned int msec) { edac_dev->poll_msec = msec; edac_dev->delay = msecs_to_jiffies(msec); diff --git a/drivers/edac/edac_device_sysfs.c b/drivers/edac/edac_device_sysfs.c index 6995ce039db9..6359007701ba 100644 --- a/drivers/edac/edac_device_sysfs.c +++ b/drivers/edac/edac_device_sysfs.c @@ -84,17 +84,15 @@ static ssize_t edac_device_ctl_poll_msec_show(struct edac_device_ctl_info return sprintf(data, "%u\n", ctl_info->poll_msec); } -static ssize_t edac_device_ctl_poll_msec_store(struct edac_device_ctl_info - *ctl_info, const char *data, - size_t count) +static ssize_t edac_device_ctl_poll_msec_store(struct edac_device_ctl_info *ctl_info, + const char *data, size_t count) { unsigned int value; int ret; - /* get the value and enforce that it is non-zero, must be at least - * one millisecond for the delay period, between scans - * Then cancel last outstanding delay for the work request - * and set a new one. + /* + * Get the value, make sure it is non-zero, must be at least one millisecond + * for the delay period between scans. */ ret = kstrtouint(data, 0, &value); if (ret < 0) diff --git a/drivers/edac/edac_module.h b/drivers/edac/edac_module.h index 47593afdc234..eceef5539186 100644 --- a/drivers/edac/edac_module.h +++ b/drivers/edac/edac_module.h @@ -52,8 +52,7 @@ bool edac_queue_work(struct delayed_work *work, unsigned long delay); bool edac_stop_work(struct delayed_work *work); bool edac_mod_work(struct delayed_work *work, unsigned long delay); -extern void edac_device_reset_delay_period(struct edac_device_ctl_info - *edac_dev, unsigned long msec); +extern void edac_device_reset_delay_period(struct edac_device_ctl_info *edac_dev, unsigned int msec); extern void edac_mc_reset_delay_period(unsigned long value); /* From d6eac3868143568cc68ab3cc4817227f4af115d3 Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Mon, 10 Aug 2026 06:40:13 -0700 Subject: [PATCH 0024/1198] EDAC/thunderx: Orphan it Robert doesn't have hardware to test patches anymore and no one else has shown interest in maintaining this driver, so orphan it, for now at least. Signed-off-by: Borislav Petkov (AMD) Acked-by: Robert Richter Link: https://lore.kernel.org/r/annRsN6UBDPsFLr2@rric.localdomain --- MAINTAINERS | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index d413dac5c8b3..671515d21bfc 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9308,9 +9308,8 @@ S: Maintained F: drivers/edac/octeon_edac* EDAC-CAVIUM THUNDERX -M: Robert Richter L: linux-edac@vger.kernel.org -S: Odd Fixes +S: Orphan F: drivers/edac/thunderx_edac* EDAC-CORE From 94579f24e2b526a04eb41050af0ba018c6f528e7 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 13 Aug 2026 10:08:09 +0300 Subject: [PATCH 0025/1198] drm/virtio: Fix a NULL vs ERR_PTR() bug in virtio_gpu_user_framebuffer_create() Smatch complains that returning a NULL here will lead to a NULL pointer dereference in drm_mode_addfb2(). Return an error pointer instead. Fixes: dc5698e80cf7 ("Add virtio gpu driver.") Signed-off-by: Dan Carpenter Signed-off-by: Dmitry Osipenko Link: https://patch.msgid.link/an1tWfHIHwtXd9SO@stanley.mountain --- drivers/gpu/drm/virtio/virtgpu_display.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c index 44ffffec550f..85ea252c658e 100644 --- a/drivers/gpu/drm/virtio/virtgpu_display.c +++ b/drivers/gpu/drm/virtio/virtgpu_display.c @@ -344,7 +344,7 @@ virtio_gpu_user_framebuffer_create(struct drm_device *dev, if (ret) { kfree(virtio_gpu_fb); drm_gem_object_put(obj); - return NULL; + return ERR_PTR(ret); } return &virtio_gpu_fb->base; From d96504ea631874220d89c455d735da51a796ead0 Mon Sep 17 00:00:00 2001 From: shechenglong Date: Tue, 11 Aug 2026 09:56:24 +0800 Subject: [PATCH 0026/1198] drm/virtio: check return value of vgdev_output_init() The return value of vgdev_output_init(), called by virtio_gpu_modeset_init(), is not checked. As a result, modeset initialization continues even if an output fails to initialize. check the return value and return the error to the caller. Signed-off-by: shechenglong Signed-off-by: Dmitry Osipenko Link: https://patch.msgid.link/20260811015624.830-1-shechenglong@xfusion.com --- drivers/gpu/drm/virtio/virtgpu_display.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c index 85ea252c658e..a1a875a0c706 100644 --- a/drivers/gpu/drm/virtio/virtgpu_display.c +++ b/drivers/gpu/drm/virtio/virtgpu_display.c @@ -378,8 +378,11 @@ int virtio_gpu_modeset_init(struct virtio_gpu_device *vgdev) vgdev->ddev->mode_config.fb_modifiers_not_supported = true; - for (i = 0 ; i < vgdev->num_scanouts; ++i) - vgdev_output_init(vgdev, i); + for (i = 0; i < vgdev->num_scanouts; ++i) { + ret = vgdev_output_init(vgdev, i); + if (ret) + return ret; + } ret = drm_vblank_init(vgdev->ddev, vgdev->num_scanouts); if (ret) From 61d85f99b5a55d4f717c4bb2f4c4acabf22ee3fc Mon Sep 17 00:00:00 2001 From: Anuj Bolewar Date: Sun, 2 Aug 2026 22:05:17 +0530 Subject: [PATCH 0027/1198] drm/virtio: reclaim pending vbufs before tearing down vqs virtio_gpu_free_vbufs() destroys the vbufs kmem_cache after the virtqueues have already been released. Commands that were queued but never completed by the device leave their vbuffers stranded in the virtqueue, so the cache still holds live objects when virtio_gpu_deinit() tears everything down. This triggers a WARNING in virtio_gpu_free_vbufs: BUG virtio-gpu-vbufs (Not tainted): Objects remaining in cache on __kmem_cache_shutdown() Drain any buffers still sitting in the control and cursor virtqueues in virtio_gpu_deinit() after the device has been reset and before the virtqueues are deleted, following the same pattern used by virtio_console's remove_vqs(). Each reclaimed buffer is released with free_vbuf(), dropping the reference on any GEM objects it holds. Pending RESOURCE_UNREF commands are handled as well: their resp_cb_data still references a GEM object, so it is cleaned up with virtio_gpu_cleanup_object() to avoid leaking it on teardown. Reported-by: syzbot+06f9b2a53ba4a5a47644@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=06f9b2a53ba4a5a47644 Signed-off-by: Anuj Bolewar Signed-off-by: Dmitry Osipenko Link: https://patch.msgid.link/20260802-virtio-gpu-reclaim-vbufs-v2-1-5767fb860691@gmail.com --- drivers/gpu/drm/virtio/virtgpu_drv.h | 1 + drivers/gpu/drm/virtio/virtgpu_kms.c | 1 + drivers/gpu/drm/virtio/virtgpu_vq.c | 15 +++++++++++++++ 3 files changed, 17 insertions(+) diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index 7449907754a4..3e491c808734 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -332,6 +332,7 @@ void virtio_gpu_array_put_free_work(struct work_struct *work); /* virtgpu_vq.c */ int virtio_gpu_alloc_vbufs(struct virtio_gpu_device *vgdev); void virtio_gpu_free_vbufs(struct virtio_gpu_device *vgdev); +void virtio_gpu_reclaim_vbufs(struct virtio_gpu_device *vgdev); void virtio_gpu_cmd_create_resource(struct virtio_gpu_device *vgdev, struct virtio_gpu_object *bo, struct virtio_gpu_object_params *params, diff --git a/drivers/gpu/drm/virtio/virtgpu_kms.c b/drivers/gpu/drm/virtio/virtgpu_kms.c index b4329f28e976..e5a6ae679f36 100644 --- a/drivers/gpu/drm/virtio/virtgpu_kms.c +++ b/drivers/gpu/drm/virtio/virtgpu_kms.c @@ -298,6 +298,7 @@ void virtio_gpu_deinit(struct drm_device *dev) flush_work(&vgdev->cursorq.dequeue_work); flush_work(&vgdev->config_changed_work); virtio_reset_device(vgdev->vdev); + virtio_gpu_reclaim_vbufs(vgdev); vgdev->vdev->config->del_vqs(vgdev->vdev); } diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c index e5e1af8b8e8a..ab6106f4bdfc 100644 --- a/drivers/gpu/drm/virtio/virtgpu_vq.c +++ b/drivers/gpu/drm/virtio/virtgpu_vq.c @@ -208,6 +208,21 @@ static void free_vbuf(struct virtio_gpu_device *vgdev, kmem_cache_free(vgdev->vbufs, vbuf); } +void virtio_gpu_reclaim_vbufs(struct virtio_gpu_device *vgdev) +{ + struct virtio_gpu_vbuffer *vbuf; + + while ((vbuf = virtqueue_detach_unused_buf(vgdev->ctrlq.vq))) { + if (vbuf->objs) + virtio_gpu_array_put_free(vbuf->objs); + if (vbuf->resp_cb_data) + virtio_gpu_cleanup_object(vbuf->resp_cb_data); + free_vbuf(vgdev, vbuf); + } + while ((vbuf = virtqueue_detach_unused_buf(vgdev->cursorq.vq))) + free_vbuf(vgdev, vbuf); +} + static void reclaim_vbufs(struct virtqueue *vq, struct list_head *reclaim_list) { struct virtio_gpu_vbuffer *vbuf; From 6a736d2f9d0c6e6217fe7532bc4c50ceca71db78 Mon Sep 17 00:00:00 2001 From: Benjamin Leggett Date: Thu, 6 Aug 2026 18:54:22 -0400 Subject: [PATCH 0028/1198] drm/virtio: use the DMA API for resource backing on Xen On a Xen PV domain page addresses bear no relation to the real machine addresses the host would have to use to reach it. virtio_ring.c handles this correctly, vring_use_map_api() returns true for any xen_domain() regardless of VIRTIO_F_ACCESS_PLATFORM. virtio-gpu makes the same decision independently, but its copy looks only at the feature bit: bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev); QEMU does not set iommu_platform on virtio-vga by default, so VIRTIO_F_ACCESS_PLATFORM is not negotiated, use_dma_api is false, and virtio_gpu_object_shmem_init() describes the framebuffer's backing pages to the host with sg_phys(). Those are guest-physical addresses. In a PV domain they resolve, on the host side, to pages belonging to some other domain, so the host scans out unrelated memory. Move the decision into virtio_gpu_use_dma_api() and give it the xen_domain() check, like vring_use_map_api() has. This additionally enables the dma_sync_sgtable_for_device() calls in virtgpu_vq.c, which are required for correctness whenever swiotlb is in play. Reproduced with a Xen 4.21 PV dom0 nested inside QEMU 8.2 with virtio-vga, on both a distro 6.8 kernel and 6.18 LTS. A PVH dom0 works fine and doesn't need this fix because it is identity-mapped, only PV dom0s are affected. Fixes: a3b815f09bb8 ("drm/virtio: add iommu support.") Signed-off-by: Ben Leggett Signed-off-by: Dmitry Osipenko Link: https://patch.msgid.link/20260806-virtgpu-xen-dma-v1-1-e499b345bbad@edera.io --- drivers/gpu/drm/virtio/virtgpu_drv.h | 20 ++++++++++++++++++++ drivers/gpu/drm/virtio/virtgpu_object.c | 2 +- drivers/gpu/drm/virtio/virtgpu_vq.c | 6 +++--- 3 files changed, 24 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index 3e491c808734..626aadf680bd 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -43,6 +43,8 @@ #include #include +#include + #define DRIVER_NAME "virtio_gpu" #define DRIVER_DESC "virtio GPU" @@ -60,6 +62,24 @@ /* See virtio_gpu_ctx_create. One additional character for NULL terminator. */ #define DEBUG_NAME_MAX_LEN 65 +/* + * Whether the host must be told about resource backing pages by DMA address + * rather than guest-physical address. + * + * This mirrors vring_use_map_api() in drivers/virtio/virtio_ring.c, including + * its xen_domain() case. + */ +static inline bool virtio_gpu_use_dma_api(const struct virtio_device *vdev) +{ + if (!virtio_has_dma_quirk(vdev)) + return true; + + if (xen_domain()) + return true; + + return false; +} + struct virtio_gpu_object_params { unsigned long size; bool dumb; diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c index ec9efacc6919..1527c62be88b 100644 --- a/drivers/gpu/drm/virtio/virtgpu_object.c +++ b/drivers/gpu/drm/virtio/virtgpu_object.c @@ -163,7 +163,7 @@ static int virtio_gpu_object_shmem_init(struct virtio_gpu_device *vgdev, struct virtio_gpu_mem_entry **ents, unsigned int *nents) { - bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev); + bool use_dma_api = virtio_gpu_use_dma_api(vgdev->vdev); struct scatterlist *sg; struct sg_table *pages; int si; diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c index ab6106f4bdfc..5e9b7b192db0 100644 --- a/drivers/gpu/drm/virtio/virtgpu_vq.c +++ b/drivers/gpu/drm/virtio/virtgpu_vq.c @@ -739,7 +739,7 @@ int virtio_gpu_panic_cmd_transfer_to_host_2d(struct virtio_gpu_device *vgdev, struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(objs->objs[0]); struct virtio_gpu_transfer_to_host_2d *cmd_p; struct virtio_gpu_vbuffer *vbuf; - bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev); + bool use_dma_api = virtio_gpu_use_dma_api(vgdev->vdev); if (virtio_gpu_is_shmem(bo) && use_dma_api) dma_sync_sgtable_for_device(vgdev->vdev->dev.parent, @@ -770,7 +770,7 @@ void virtio_gpu_cmd_transfer_to_host_2d(struct virtio_gpu_device *vgdev, struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(objs->objs[0]); struct virtio_gpu_transfer_to_host_2d *cmd_p; struct virtio_gpu_vbuffer *vbuf; - bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev); + bool use_dma_api = virtio_gpu_use_dma_api(vgdev->vdev); if (virtio_gpu_is_shmem(bo) && use_dma_api) dma_sync_sgtable_for_device(vgdev->vdev->dev.parent, @@ -1203,7 +1203,7 @@ void virtio_gpu_cmd_transfer_to_host_3d(struct virtio_gpu_device *vgdev, struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(objs->objs[0]); struct virtio_gpu_transfer_host_3d *cmd_p; struct virtio_gpu_vbuffer *vbuf; - bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev); + bool use_dma_api = virtio_gpu_use_dma_api(vgdev->vdev); if (virtio_gpu_is_shmem(bo) && use_dma_api) dma_sync_sgtable_for_device(vgdev->vdev->dev.parent, From ab243f74ab4084ca5c8dec608cb5b0deb27db067 Mon Sep 17 00:00:00 2001 From: Youssef Samir Date: Fri, 31 Jul 2026 17:23:44 +0200 Subject: [PATCH 0029/1198] accel/qaic: Address potential out-of-bounds read in resp_worker() Although 'commit 2feec5ae5df7 ("accel/qaic: Handle DBC deactivation if the owner went away")' fixes the scenario it was intended for by walking the message and only decoding QAIC_TRANS_DEACTIVATE_FROM_DEV, if present, it skipped over the bounds checking code that is included in decode_message(). This could lead to issues such as reading past the slab allocation's end, infinite loops or kernel panics. For those issues to happen, a malformed wire message is needed to be sent from the device. Instead of duplicating the bounds checking code already present in decode_message(), use the function inside resp_worker(). Reported-by: Ruikai Peng Fixes: 2feec5ae5df7 ("accel/qaic: Handle DBC deactivation if the owner went away") Reviewed-by: Jeff Hugo Reviewed-by: Lizhi Hou Signed-off-by: Youssef Samir Signed-off-by: Jeff Hugo Link: https://patch.msgid.link/20260731152344.1905882-1-youssef.abdulrahman@oss.qualcomm.com --- drivers/accel/qaic/qaic_control.c | 46 ++++++++++++++++--------------- 1 file changed, 24 insertions(+), 22 deletions(-) diff --git a/drivers/accel/qaic/qaic_control.c b/drivers/accel/qaic/qaic_control.c index 50bf3340e49c..2ccc55486aac 100644 --- a/drivers/accel/qaic/qaic_control.c +++ b/drivers/accel/qaic/qaic_control.c @@ -963,11 +963,13 @@ static int decode_status(struct qaic_device *qdev, void *trans, struct manage_ms static int decode_message(struct qaic_device *qdev, struct manage_msg *user_msg, struct wire_msg *msg, struct ioctl_resources *resources, - struct qaic_user *usr) + struct qaic_user *usr, bool orphaned_deactivate) { + u32 msg_hdr_count = le32_to_cpu(msg->hdr.count); u32 msg_hdr_len = le32_to_cpu(msg->hdr.len); struct wire_trans_hdr *trans_hdr; u32 msg_len = 0; + int trans_type; int ret; int i; @@ -975,10 +977,12 @@ static int decode_message(struct qaic_device *qdev, struct manage_msg *user_msg, msg_hdr_len > QAIC_MANAGE_MAX_MSG_LENGTH) return -EINVAL; - user_msg->len = 0; - user_msg->count = le32_to_cpu(msg->hdr.count); + if (user_msg) { + user_msg->len = 0; + user_msg->count = msg_hdr_count; + } - for (i = 0; i < user_msg->count; ++i) { + for (i = 0; i < msg_hdr_count; ++i) { u32 hdr_len; if (msg_len > msg_hdr_len - sizeof(*trans_hdr)) @@ -990,7 +994,20 @@ static int decode_message(struct qaic_device *qdev, struct manage_msg *user_msg, size_add(msg_len, hdr_len) > msg_hdr_len) return -EINVAL; - switch (le32_to_cpu(trans_hdr->type)) { + trans_type = le32_to_cpu(trans_hdr->type); + /* + * orphaned_deactivate is the case where a deactivate response + * is received from the device after the user owning the DBC, + * and the message requesting deactivation, has gone away. + * In this case, only process QAIC_TRANS_DEACTIVATE_FROM_DEV + * transaction and skip the others. + */ + if (orphaned_deactivate && trans_type != QAIC_TRANS_DEACTIVATE_FROM_DEV) { + msg_len += hdr_len; + continue; + } + + switch (trans_type) { case QAIC_TRANS_PASSTHROUGH_FROM_DEV: ret = decode_passthrough(qdev, trans_hdr, user_msg, &msg_len); break; @@ -1281,7 +1298,7 @@ static int qaic_manage(struct qaic_device *qdev, struct qaic_user *usr, struct m goto dma_cont_failed; } - ret = decode_message(qdev, user_msg, rsp, &resources, usr); + ret = decode_message(qdev, user_msg, rsp, &resources, usr, false); dma_cont_failed: free_dbc_buf(qdev, &resources); @@ -1446,22 +1463,7 @@ static void resp_worker(struct work_struct *work) * response to the QAIC_TRANS_TERMINATE_TO_DEV transaction, * otherwise, the user can issue an soc_reset to the device. */ - u32 msg_count = le32_to_cpu(msg->hdr.count); - u32 msg_len = le32_to_cpu(msg->hdr.len); - u32 len = 0; - int j; - - for (j = 0; j < msg_count && len < msg_len; ++j) { - struct wire_trans_hdr *trans_hdr; - - trans_hdr = (struct wire_trans_hdr *)(msg->data + len); - if (le32_to_cpu(trans_hdr->type) == QAIC_TRANS_DEACTIVATE_FROM_DEV) { - if (decode_deactivate(qdev, trans_hdr, &len, NULL)) - len += le32_to_cpu(trans_hdr->len); - } else { - len += le32_to_cpu(trans_hdr->len); - } - } + decode_message(qdev, NULL, msg, NULL, NULL, true); /* request must have timed out, drop packet */ kfree(msg); } From 5f01293930d18f8473681b378bb483b7087fc0dd Mon Sep 17 00:00:00 2001 From: Changwoo Min Date: Wed, 19 Aug 2026 01:04:29 +0900 Subject: [PATCH 0030/1198] sched_ext: Allow ops.cgroup_set_bandwidth() to be sleepable ops.cgroup_set_bandwidth() is delivered from scx_group_set_bandwidth(), which runs from the cpu.max cgroup interface write path (tg_set_bandwidth()) in process context. scx_group_set_bandwidth() holds percpu_down_read(&scx_cgroup_ops_rwsem), whose read side may sleep. The call site is therefore sleepable, like ops.cgroup_init(). bpf_scx_check_member() rejects a sleepable program on any member not on its allow-list, so a BPF scheduler cannot allocate -- which is sleepable -- when a cgroup gains a cpu.max limit at runtime; it must instead pre-reserve memory for a callback that cannot allocate. Add cgroup_set_bandwidth() to the allow-list so the callback can allocate on demand, and document that it may block. A scheduler must decide at load time whether to mark the callback sleepable, but the allow-list entry is a verifier property with no symbol to probe. Add a compatibility marker whose presence in the kernel's BTF lets userspace detect this support: DEFINE_SCX_COMPAT_MARKER() emits an empty, callerless function, here scx_compat_marker_cgroup_set_bandwidth_may_sleep(). It is __used __retain so neither the compiler nor the linker (under CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) drops it. The markers share the scx_compat_marker_ prefix and are collected near the end of ext.c so more can be added as further capabilities appear. Signed-off-by: Changwoo Min Signed-off-by: Tejun Heo --- kernel/sched/ext/ext.c | 14 ++++++++++++++ kernel/sched/ext/internal.h | 23 ++++++++++++++++++++++- 2 files changed, 36 insertions(+), 1 deletion(-) diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c index 10af28a9f2c0..b646711a45fe 100644 --- a/kernel/sched/ext/ext.c +++ b/kernel/sched/ext/ext.c @@ -8079,6 +8079,7 @@ static int bpf_scx_check_member(const struct btf_type *t, case offsetof(struct sched_ext_ops, cgroup_init): case offsetof(struct sched_ext_ops, cgroup_exit): case offsetof(struct sched_ext_ops, cgroup_prep_move): + case offsetof(struct sched_ext_ops, cgroup_set_bandwidth): #endif case offsetof(struct sched_ext_ops, cpu_online): case offsetof(struct sched_ext_ops, cpu_offline): @@ -11041,3 +11042,16 @@ static int __init scx_init(void) return 0; } __initcall(scx_init); + +/* + * Compatibility markers for userspace. Existence of a marker function + * represents that the kernel supports that sched-ext feature. + */ + +/* + * scx_compat_marker_cgroup_set_bandwidth_may_sleep: advertises that + * ops.cgroup_set_bandwidth() may be implemented as a sleepable callback. + */ +#ifdef CONFIG_EXT_GROUP_SCHED +DEFINE_SCX_COMPAT_MARKER(cgroup_set_bandwidth_may_sleep); +#endif /* CONFIG_EXT_GROUP_SCHED */ diff --git a/kernel/sched/ext/internal.h b/kernel/sched/ext/internal.h index 27bbf5e04d90..53e136a47924 100644 --- a/kernel/sched/ext/internal.h +++ b/kernel/sched/ext/internal.h @@ -753,7 +753,7 @@ struct sched_ext_ops { * @burst_us: bandwidth control burst * * Update @cgrp's bandwidth control parameters. This is from the cpu.max - * cgroup interface. + * cgroup interface. This operation may block. * * @quota_us / @period_us determines the CPU bandwidth @cgrp is entitled * to. For example, if @period_us is 1_000_000 and @quota_us is @@ -2001,6 +2001,27 @@ struct scx_bstr_buf { char line[SCX_EXIT_MSG_LEN]; }; +/* Internal helper for DEFINE_SCX_COMPAT_MARKER(). */ +#define DECLARE_SCX_COMPAT_MARKER(func) \ + extern void scx_compat_marker_##func(void) + +/** + * DEFINE_SCX_COMPAT_MARKER() - define a userspace capability marker + * @func: marker suffix; the defined symbol is scx_compat_marker_@func + * + * Emit an empty, callerless function that is retained in the kernel's BTF. + * Its presence is part of the kernel<->userspace contract: userspace probes + * scx_compat_marker_@func (e.g. via BTF) to detect that this kernel supports + * the corresponding feature. + * + * The leading declaration suppresses the missing-prototype warning; the + * trailing declaration consumes the semicolon at the use site. + */ +#define DEFINE_SCX_COMPAT_MARKER(func) \ + DECLARE_SCX_COMPAT_MARKER(func); \ + __used __retain void scx_compat_marker_##func(void) {} \ + DECLARE_SCX_COMPAT_MARKER(func) + extern struct scx_sched __rcu *scx_root; DECLARE_PER_CPU(struct rq *, scx_locked_rq_state); From 6eca8f94d84106d3754b9df27f46a14572af9e7f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 18 Aug 2026 08:47:21 -1000 Subject: [PATCH 0031/1198] workqueue: Annotate cb_lock nesting when draining a dead BH pool On PREEMPT_RT, bh_worker() wraps work item execution in pool->cb_lock to provide a handshake for canceling BH work items. When a CPU goes down, drain_dead_softirq_workfn() runs the dead pool's bh_worker() nested inside the local pool's bh_worker(), acquiring the cb_locks of two different pools without a nesting annotation. lockdep reports possible recursive locking: ============================================ WARNING: possible recursive locking detected -------------------------------------------- ktimers/0/16 is trying to acquire lock: ffff8880b873a990 (&pool->cb_lock){+...}-{3:3}, at: bh_worker+0x7d/0x880 but task is already holding lock: ffff8880b863a990 (&pool->cb_lock){+...}-{3:3}, at: bh_worker+0x7d/0x880 Call Trace: bh_worker+0x7d/0x880 kernel/workqueue.c:3688 drain_dead_softirq_workfn+0x95/0x220 kernel/workqueue.c:3763 process_scheduled_works+0xa8e/0x14e0 kernel/workqueue.c:3405 bh_worker+0x46a/0x880 kernel/workqueue.c:3708 tasklet_action+0xc/0x70 kernel/softirq.c:965 The nesting can't deadlock. A pool's bh_worker() runs nested only while the pool's CPU is dead, entered from a live pool's bh_worker() on the draining CPU, so the ordering is always live to dead. CPU hotplug operations are serialized and the drain is synchronous, so the nesting depth never exceeds two. Annotate the inner acquisition with SINGLE_DEPTH_NESTING. Signed-off-by: Tejun Heo Reported-by: syzbot+1bd20115328f8254ed62@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=1bd20115328f8254ed62 Fixes: ad7c7f4b9c6c ("workqueue: Provide a handshake for canceling BH workers") Cc: stable@vger.kernel.org # v6.18+ --- kernel/workqueue.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index bfeef512f6dd..c0b72dcc0f03 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3197,7 +3197,16 @@ __acquires(&pool->lock) #ifdef CONFIG_PREEMPT_RT static void worker_lock_callback(struct worker_pool *pool) { - spin_lock(&pool->cb_lock); + /* + * SINGLE_DEPTH_NESTING is for a dead pool's bh_worker() running from + * drain_dead_softirq_workfn() inside a live pool's bh_worker(). The + * unlocked read is stable: the flag is only set while @pool's CPU is + * dead, inside a serialized hotplug operation. data_race() as the value + * only affects the lockdep annotation and the read can be elided when + * lockdep is disabled. + */ + spin_lock_nested(&pool->cb_lock, + data_race(pool->flags) & POOL_BH_DRAINING ? SINGLE_DEPTH_NESTING : 0); } static void worker_unlock_callback(struct worker_pool *pool) From f83af377c148f6ad94b41c0e8313f12adf45e1c1 Mon Sep 17 00:00:00 2001 From: Yehyeong Lee Date: Tue, 18 Aug 2026 20:04:05 +0900 Subject: [PATCH 0032/1198] nvme-tcp: check the data direction of a C2HData PDU nvme_tcp_handle_c2h_data() finds the request by command id and checks that it has a payload, but it does not check that the command asked for data to be read. A controller that answers a write command with C2HData therefore reaches nvme_tcp_recv_data(), where _copy_to_iter() hits WARN_ON_ONCE(i->data_source) and returns 0. The receive path turns that into -EFAULT and resets the controller. No data is copied, so this is not memory corruption. What a controller gets is a kernel warning it can raise at will, which is fatal on a host booted with panic_on_warn. The send path already knows the direction - it consults rq_data_dir() when it builds a command - and nvme_tcp_handle_r2t() checks the length and the offset of the request it names. The C2HData path does not check the direction at all. Reject a C2HData PDU whose command is not a read. Rejecting it fails the command and resets the controller, as the neighbouring check in this function does; what goes away is the warning. [ 6.885580] ------------[ cut here ]------------ [ 6.886457] WARNING: lib/iov_iter.c:193 at _copy_to_iter+0x289/0x1330, CPU#0: kworker/0:1H/71 [ 6.888137] CPU: 0 UID: 0 PID: 71 Comm: kworker/0:1H Not tainted 7.2.0-rc5-NVMETCP-gf5098b6bae76 #1 PREEMPT(lazy) [ 6.891165] Workqueue: nvme_tcp_wq nvme_tcp_io_work [ 6.891875] RIP: 0010:_copy_to_iter+0x289/0x1330 [ 6.903739] Call Trace: [ 6.904085] [ 6.909254] __skb_datagram_iter+0x433/0x820 [ 6.911026] skb_copy_datagram_iter+0x37/0x120 [ 6.911622] nvme_tcp_recv_skb+0xa07/0x4320 [ 6.913378] __tcp_read_sock+0x1ab/0x810 [ 6.915788] nvme_tcp_try_recv+0x152/0x1e0 [ 6.918222] nvme_tcp_io_work+0x1e4/0x6c0 [ 6.926906] [ 6.927226] ---[ end trace 0000000000000000 ]--- [ 6.927878] nvme nvme0: queue 1 failed to copy request 0x71 data [ 6.928709] nvme nvme0: receive failed: -14 Fixes: 3f2304f8c6d6 ("nvme-tcp: add NVMe over TCP host driver") Cc: stable@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Yehyeong Lee Signed-off-by: Keith Busch --- drivers/nvme/host/tcp.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 5fda9661bdb7..643fc503a477 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -684,6 +684,13 @@ static int nvme_tcp_handle_c2h_data(struct nvme_tcp_queue *queue, return -ENOENT; } + if (rq_data_dir(rq) != READ) { + dev_err(queue->ctrl->ctrl.device, + "queue %d tag %#x unexpected data for a write\n", + nvme_tcp_queue_id(queue), rq->tag); + return -EIO; + } + req = blk_mq_rq_to_pdu(rq); if (!blk_rq_payload_bytes(rq) || !req->curr_bio || !req->data_len) { dev_err(queue->ctrl->ctrl.device, From 3838e80fcfb32e62baffb63c6dc0a60153665a4d Mon Sep 17 00:00:00 2001 From: Chao Shi Date: Mon, 17 Aug 2026 13:58:59 -0400 Subject: [PATCH 0033/1198] nvme: skip the zoned limits update if the zone info query failed nvme_query_zone_info() returns either a negative errno or a positive NVMe status code, but nvme_update_ns_info_block() only tests for the negative case: ret = nvme_query_zone_info(ns, lbaf, &zi); if (ret < 0) goto out; If the device fails the Identify Namespace (I/O Command Set specific) command, or the Identify Controller command issued by nvme_set_max_append(), the positive status falls through and setup continues with the zero-initialized zone info. nvme_update_zone_info() then marks the queue zoned with chunk_sectors and ns->head->zsze set to zero. blk_validate_zoned_limits() does not check chunk_sectors, so the limits commit succeeds. blk_revalidate_disk_zones() does reject the zero zone size, but by then the limits are live and nothing rolls them back, so I/O keeps being submitted to a zoned queue with a zero zone size and disk_zone_no() shifts by ilog2(0): nvme0n1: Invalid non power of two zone size (0) UBSAN: shift-out-of-bounds in include/linux/blkdev.h:747:16 shift exponent -1 is negative disk_zone_no include/linux/blkdev.h:747 [inline] bio_straddles_zones include/linux/blkdev.h:1058 [inline] blk_zone_wplug_handle_write block/blk-zoned.c:1423 [inline] blk_zone_plug_bio.cold+0x25/0x1c8 block/blk-zoned.c:1605 blk_mq_submit_bio+0x18fb/0x2870 block/blk-mq.c:3196 submit_bh_wbc+0x575/0x740 fs/buffer.c:2824 __block_write_full_folio+0x728/0xdd0 fs/buffer.c:1933 Any device, firmware or NVMe-oF target that fails this one command reaches this. Skip the zoned limits update in that case, and log which of the two things happened: during a revalidation the queue keeps the zone geometry it was last validated with, and on a first scan the namespace is registered without zoned limits, so that it is still available as a handle for admin commands. Neither of the paths in nvme_query_zone_info() that return a positive status logs anything, so the failure would otherwise be silent. zi.zone_size is an exact indicator: every path that returns a positive status returns before it is assigned, and after that the only failure left is -ENODEV, which the caller already handles. Found by FuzzNvme. Fixes: c85c9ab926a5 ("nvme: split nvme_update_zone_info") Cc: stable@vger.kernel.org Cc: Weidong Zhu Suggested-by: Keith Busch Reviewed-by: Christoph Hellwig Signed-off-by: Chao Shi Signed-off-by: Keith Busch --- drivers/nvme/host/core.c | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 1322c678f4eb..74b7393dbe85 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2468,9 +2468,26 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, if (!nvme_update_disk_info(ns, id, nvm, &lim)) capacity = 0; + /* + * A failed zone info query leaves zi zero-initialized, so skip the + * zoned limits update instead of configuring the queue from it. + * During a revalidation that keeps the zone geometry the queue was + * last validated with; on a first scan the namespace is registered + * without zoned limits, so that it is still available as a handle + * for admin commands. + */ if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && - ns->head->ids.csi == NVME_CSI_ZNS) - nvme_update_zone_info(ns, &lim, &zi); + ns->head->ids.csi == NVME_CSI_ZNS) { + if (zi.zone_size) + nvme_update_zone_info(ns, &lim, &zi); + else + dev_warn(ns->ctrl->device, + "zone info query failed for nsid %u, %s\n", + ns->head->ns_id, + blk_queue_is_zoned(ns->disk->queue) ? + "keeping the previous zone limits" : + "not enabling zoned mode"); + } if ((ns->ctrl->vwc & NVME_CTRL_VWC_PRESENT) && !info->no_vwc) lim.features |= BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA; From d61828199c6cb4b76d48403c77023cd4bb9d09fc Mon Sep 17 00:00:00 2001 From: Xixin Liu Date: Wed, 19 Aug 2026 14:30:00 +0800 Subject: [PATCH 0034/1198] nvme-rdma: fix -EIO cleanup order in queue_rq On -EIO, the RDMA queue_rq path reports a host path error and then still cleans up the command and unmaps the SQE DMA. The path error helper completes the request, so that is double cleanup and DMA unmap after the request is already complete. Unmap the SQE first, then report the host path error. Skip the outer command cleanup on that path. Fixes: 62eca39722fd ("nvme-rdma: handle nvme_rdma_post_send failures better") Reviewed-by: Christoph Hellwig Signed-off-by: Xixin Liu Signed-off-by: Keith Busch --- drivers/nvme/host/rdma.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 01743ae01466..29ecbe71bb2e 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -2034,7 +2034,7 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, struct ib_device *dev; bool queue_ready = test_bit(NVME_RDMA_Q_LIVE, &queue->flags); blk_status_t ret; - int err; + int err = 0; WARN_ON_ONCE(rq->tag < 0); @@ -2090,16 +2090,18 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, err_unmap: nvme_rdma_unmap_data(queue, rq); err: - if (err == -EIO) - ret = nvme_host_path_error(rq); - else if (err == -ENOMEM || err == -EAGAIN) - ret = BLK_STS_RESOURCE; - else - ret = BLK_STS_IOERR; - nvme_cleanup_cmd(rq); + if (err != -EIO) { + nvme_cleanup_cmd(rq); + if (err == -ENOMEM || err == -EAGAIN) + ret = BLK_STS_RESOURCE; + else + ret = BLK_STS_IOERR; + } unmap_qe: ib_dma_unmap_single(dev, req->sqe.dma, sizeof(struct nvme_command), DMA_TO_DEVICE); + if (err == -EIO) + return nvme_host_path_error(rq); return ret; } From c1888444dc28310222dcc6e5c301d60d0943787f Mon Sep 17 00:00:00 2001 From: Kanchan Joshi Date: Tue, 18 Aug 2026 11:32:52 +0530 Subject: [PATCH 0035/1198] nvme: set ns->head in nvme_alloc_ns_head so that it becomes possible to submit non-admin commands. This is a prep patch with no functional changes. Reviewed-by: Christoph Hellwig Signed-off-by: Kanchan Joshi Signed-off-by: Keith Busch --- drivers/nvme/host/core.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 74b7393dbe85..e7f945fefbc4 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -4018,10 +4018,11 @@ static void nvme_add_ns_cdev(struct nvme_ns *ns) set_bit(NVME_NS_CDEV_LIVE, &ns->flags); } -static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl, +static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info) - __must_hold(&ctrl->subsys->lock) + __must_hold(&ns->ctrl->subsys->lock) { + struct nvme_ctrl *ctrl = ns->ctrl; struct nvme_ns_head *head; size_t size = sizeof(*head); int ret = -ENOMEM; @@ -4049,6 +4050,7 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl, ratelimit_state_init(&head->rs_nuse, 5 * HZ, 1); ratelimit_set_flags(&head->rs_nuse, RATELIMIT_MSG_ON_RELEASE); kref_init(&head->ref); + ns->head = head; if (head->ids.csi) { ret = nvme_get_effects_log(ctrl, head->ids.csi, &head->effects); @@ -4072,6 +4074,7 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl, ida_free(&ctrl->subsys->ns_ida, head->instance); out_free_head: kfree(head); + ns->head = NULL; out: if (ret > 0) ret = blk_status_to_errno(nvme_error_status(ret)); @@ -4158,7 +4161,7 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info) info->nsid); goto out_unlock; } - head = nvme_alloc_ns_head(ctrl, info); + head = nvme_alloc_ns_head(ns, info); if (IS_ERR(head)) { ret = PTR_ERR(head); goto out_unlock; From 56e1c6bbe4bb084d7ecf61698afdf70be23dd35f Mon Sep 17 00:00:00 2001 From: Kanchan Joshi Date: Tue, 18 Aug 2026 11:32:53 +0530 Subject: [PATCH 0036/1198] nvme: fix racy access to FDP placement id array nvme_query_fdp_info() is called per-path and therefore prone to races. It populates head->nr_plids/head->plids for fdp registration. But nothing protects that pair from concurrent access - two paths scanning the same namespace can race to populate it. Avoid the race by moving this initialization work to nvme_alloc_ns_head() which is called once per shared namespace. Fixes: 30b5f20bb2dd ("nvme: register fdp parameters with the block layer") Reported-by: Hari Mishal Link: https://lore.kernel.org/linux-nvme/20260725135111.14041-2-harimishal1@gmail.com/ Reviewed-by: Christoph Hellwig Signed-off-by: Kanchan Joshi Signed-off-by: Keith Busch --- drivers/nvme/host/core.c | 30 +++++++++++------------------- drivers/nvme/host/nvme.h | 1 + 2 files changed, 12 insertions(+), 19 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index e7f945fefbc4..5f2744be7388 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2341,14 +2341,6 @@ static int nvme_query_fdp_info(struct nvme_ns *ns, struct nvme_ns_info *info) size_t size; int i, ret; - /* - * The FDP configuration is static for the lifetime of the namespace, - * so return immediately if we've already registered this namespace's - * streams. - */ - if (head->nr_plids) - return 0; - ret = nvme_get_features(ctrl, NVME_FEAT_FDP, info->endgid, NULL, 0, &fdp); if (ret) { @@ -2395,6 +2387,7 @@ static int nvme_query_fdp_info(struct nvme_ns *ns, struct nvme_ns_info *info) for (i = 0; i < head->nr_plids; i++) head->plids[i] = le16_to_cpu(ruhs->ruhsd[i].pid); + head->write_stream_granularity = min(info->runs, U32_MAX); free: kfree(ruhs); return ret; @@ -2442,12 +2435,6 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, goto out; } - if (ns->ctrl->ctratt & NVME_CTRL_ATTR_FDPS) { - ret = nvme_query_fdp_info(ns, info); - if (ret < 0) - goto out; - } - if (nvme_invalid_lba_sz(le64_to_cpu(id->nsze), id->lbaf[lbaf].ds - SECTOR_SHIFT, &capacity)) { dev_warn_once(ns->ctrl->device, @@ -2507,10 +2494,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, capacity = 0; lim.max_write_streams = ns->head->nr_plids; - if (lim.max_write_streams) - lim.write_stream_granularity = min(info->runs, U32_MAX); - else - lim.write_stream_granularity = 0; + lim.write_stream_granularity = ns->head->write_stream_granularity; /* * Only set the DEAC bit if the device guarantees that reads from @@ -4059,15 +4043,23 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ns *ns, } else head->effects = ctrl->effects; + if (ctrl->ctratt & NVME_CTRL_ATTR_FDPS) { + ret = nvme_query_fdp_info(ns, info); + if (ret < 0) + goto out_cleanup_srcu; + } + ret = nvme_mpath_alloc_disk(ctrl, head); if (ret) - goto out_cleanup_srcu; + goto out_cleanup_fdp; list_add_tail(&head->entry, &ctrl->subsys->nsheads); kref_get(&ctrl->subsys->ref); return head; +out_cleanup_fdp: + kfree(head->plids); out_cleanup_srcu: cleanup_srcu_struct(&head->srcu); out_ida_remove: diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 75e5d5a8a77c..c20e8ef8baa0 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -571,6 +571,7 @@ struct nvme_ns_head { u16 nr_plids; u16 *plids; + u32 write_stream_granularity; #ifdef CONFIG_NVME_MULTIPATH struct bio_list requeue_list __guarded_by(&requeue_lock); From 58e7c13c8f0468bdf7e10151d3fb556c6015ab2e Mon Sep 17 00:00:00 2001 From: Mohamed Khalfella Date: Tue, 11 Aug 2026 16:11:52 -0700 Subject: [PATCH 0037/1198] nvme: add opcode filtering for fault injection Currently NVMe fault injection applies to every command routed through nvme_should_fail(), which makes it hard to target a specific command type when reproducing an issue in error-handling paths. Add an "opcode" debugfs attribute alongside the existing "status" and "dont_retry" knobs. It defaults to 0xffff, meaning "match any opcode" and preserving the previous behavior. When set to a valid opcode (<= 0xff), fault injection is only considered for commands whose opcode matches. Reviewed-by: Christoph Hellwig Signed-off-by: Mohamed Khalfella Signed-off-by: Keith Busch --- .../fault-injection/nvme-fault-injection.rst | 65 +++++++++++++++++++ drivers/nvme/host/fault_inject.c | 14 +++- drivers/nvme/host/nvme.h | 1 + 3 files changed, 78 insertions(+), 2 deletions(-) diff --git a/Documentation/fault-injection/nvme-fault-injection.rst b/Documentation/fault-injection/nvme-fault-injection.rst index 1d4427890d75..09730acf0163 100644 --- a/Documentation/fault-injection/nvme-fault-injection.rst +++ b/Documentation/fault-injection/nvme-fault-injection.rst @@ -176,3 +176,68 @@ Message from dmesg:: secondary_startup_64+0xa4/0xb0 nvme nvme0: Could not set queue count (16385) nvme nvme0: IO queues not created + +Example 4: Inject an error into the first write command +------------------------------------------------------- + +:: + + echo 0x01 > /sys/kernel/debug/nvme0n1/fault_inject/opcode + echo 1 > /sys/kernel/debug/nvme0n1/fault_inject/times + echo 100 > /sys/kernel/debug/nvme0n1/fault_inject/probability + dd if=/dev/zero of=/dev/nvme0n1 oflag=direct bs=512 count=1 + +Expected Result:: + + The first write command sent to nvme0n1 fails + +Message from dmesg:: + + FAULT_INJECTION: forcing a failure. + name fault_inject, interval 1, probability 100, space 0, times 1 + CPU: 4 UID: 0 PID: 0 Comm: swapper/4 Not tainted 7.1.0+ #5 PREEMPT(full) + Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-20240910_120124-localhost 04/01/2014 + Call Trace: + + dump_stack_lvl+0x6e/0xa0 + dump_stack+0x10/0x16 + should_fail_ex+0x461/0x510 + should_fail+0xb/0x20 + nvme_should_fail+0x11b/0x240 [nvme_core] + nvme_poll_cq+0x6ad/0xb30 [nvme] + nvme_irq+0x84/0xe0 [nvme] + ? __pfx_nvme_irq+0x10/0x10 [nvme] + ? rcu_core+0xa40/0xa90 + ? __pfx_sched_balance_softirq+0x10/0x10 + ? debug_smp_processor_id+0x17/0x20 + ? rcu_is_watching+0x13/0xa0 + __handle_irq_event_percpu+0x396/0x610 + handle_irq_event_percpu+0xf/0x90 + handle_irq_event+0xab/0x110 + handle_edge_irq+0x1a3/0x210 + __common_interrupt+0xff/0x170 + common_interrupt+0x90/0xc0 + + + asm_common_interrupt+0x27/0x40 + RIP: 0010:pv_native_safe_halt+0x13/0x20 + Code: 1f 84 00 00 00 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 8b 05 0a 2a 58 01 85 c0 7e 07 0f 00 2d ff cc 0d 00 fb f4 cc 0 + RSP: 0018:ffff888100a67e40 EFLAGS: 00000242 + RAX: 0000000000000001 RBX: ffff888100a49c40 RCX: ffffed102b6c645b + RDX: ffffed102b6c645b RSI: ffffffff82a0d3c0 RDI: ffffffff81428b9b + RBP: ffff888100a67e48 R08: ffffed102b6c645b R09: 0000000000000004 + R10: ffffed102b6c645a R11: 0000000000000001 R12: 0000000000000000 + R13: 0000000000000000 R14: ffffed1020149388 R15: dffffc0000000000 + ? do_idle+0x19b/0x2c0 + ? default_idle+0x9/0x20 + arch_cpu_idle+0x9/0x10 + default_idle_call+0x6b/0xa0 + do_idle+0x19b/0x2c0 + ? __pfx_do_idle+0x10/0x10 + ? complete_with_flags+0x63/0x70 + cpu_startup_entry+0x55/0x60 + start_secondary+0x1df/0x1e0 + common_startup_64+0x13e/0x158 + + nvme0n1: Write(0x1) @ LBA 0, 1 blocks, Invalid Command Opcode (sct 0x0 / sc 0x1) DNR + operation not supported error, dev nvme0n1, sector 0 op 0x1:(WRITE) flags 0x8800 phys_seg 1 prio class 2 diff --git a/drivers/nvme/host/fault_inject.c b/drivers/nvme/host/fault_inject.c index 105d6cb41c72..783e1999fef4 100644 --- a/drivers/nvme/host/fault_inject.c +++ b/drivers/nvme/host/fault_inject.c @@ -42,9 +42,11 @@ void nvme_fault_inject_init(struct nvme_fault_inject *fault_inj, } fault_inj->parent = parent; - /* create debugfs for status code and dont_retry */ + /* create debugfs for opcode, status code, and dont_retry */ + fault_inj->opcode = 0xffff; fault_inj->status = NVME_SC_INVALID_OPCODE; fault_inj->dont_retry = true; + debugfs_create_x16("opcode", 0600, dir, &fault_inj->opcode); debugfs_create_x16("status", 0600, dir, &fault_inj->status); debugfs_create_bool("dont_retry", 0600, dir, &fault_inj->dont_retry); } @@ -59,6 +61,7 @@ void nvme_should_fail(struct request *req) { struct gendisk *disk = req->q->disk; struct nvme_fault_inject *fault_inject = NULL; + struct nvme_command *cmd = nvme_req(req)->cmd; u16 status; if (disk) { @@ -72,7 +75,14 @@ void nvme_should_fail(struct request *req) fault_inject = &nvme_req(req)->ctrl->fault_inject; } - if (fault_inject && should_fail(&fault_inject->attr, 1)) { + if (!fault_inject) + return; + + if (fault_inject->opcode <= 0xff && + fault_inject->opcode != cmd->common.opcode) + return; + + if (should_fail(&fault_inject->attr, 1)) { /* inject status code and DNR bit */ status = fault_inject->status; if (fault_inject->dont_retry) diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index c20e8ef8baa0..2cff9fcbf740 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -323,6 +323,7 @@ struct nvme_fault_inject { #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS struct fault_attr attr; struct dentry *parent; + u16 opcode; bool dont_retry; /* DNR, do not retry */ u16 status; /* status code */ #endif From fb1ed67788e21832b614c23767a088c08cfdd2f2 Mon Sep 17 00:00:00 2001 From: Xixin Liu Date: Thu, 13 Aug 2026 14:42:01 +0800 Subject: [PATCH 0038/1198] nvmet-rdma: fix queue leak when connect backlog is exceeded When pending disconnecting queues exceed the backlog limit, the connect path only drops the device reference and leaks the newly allocated queue and its IB resources. Fixes: badc53620fe8 ("nvme: target: rdma: fix ndev refcount leak on queue connect") Reviewed-by: Christoph Hellwig Signed-off-by: Xixin Liu Signed-off-by: Keith Busch --- drivers/nvme/target/rdma.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index de5a88fbb233..542138fd669f 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -1627,19 +1627,13 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id, mutex_unlock(&nvmet_rdma_queue_mutex); if (pending > NVMET_RDMA_BACKLOG) { ret = NVME_SC_CONNECT_CTRL_BUSY; - goto put_device; + goto free_queue; } } ret = nvmet_rdma_cm_accept(cm_id, queue, &event->param.conn); - if (ret) { - /* - * Don't destroy the cm_id in free path, as we implicitly - * destroy the cm_id here with non-zero ret code. - */ - queue->cm_id = NULL; + if (ret) goto free_queue; - } mutex_lock(&nvmet_rdma_queue_mutex); list_add_tail(&queue->queue_list, &nvmet_rdma_queue_list); @@ -1648,6 +1642,11 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id, return 0; free_queue: + /* + * Don't destroy the cm_id in free path, as we implicitly + * destroy the cm_id here with non-zero ret code. + */ + queue->cm_id = NULL; nvmet_rdma_free_queue(queue); put_device: kref_put(&ndev->ref, nvmet_rdma_free_dev); From dc14753664240cedf669623b27ae9922b0618b25 Mon Sep 17 00:00:00 2001 From: Taimuraz Kaitmazov Date: Tue, 18 Aug 2026 02:06:55 +0300 Subject: [PATCH 0039/1198] accel/amdxdna: return early from a zero-length flush SYNC_BO does not constrain its size, so a request for zero bytes reaches drm_clflush_virt_range(), which ends with an unconditional clflushopt(end - 1). For an empty range that is the byte before the mapping, and abo->mem.kva comes from vmap(), so the access lands in the guard page below the vmalloc area and faults: BUG: unable to handle page fault for address: ffffd16fbbc70fff #PF: supervisor read access in kernel mode Oops: Oops: 0000 [#1] SMP NOPTI CPU: 7 UID: 1000 Comm: sync_bo_probe RIP: 0010:drm_clflush_virt_range+0x3c/0x70 Call Trace: amdxdna_drm_sync_bo_ioctl+0x124/0x430 [amdxdna] drm_ioctl+0x301/0x4c0 __x64_sys_ioctl+0x115/0x2f0 do_syscall_64+0xa6/0x3d0 Any process that can open the render node can do this. Reproduced 3 of 3 times on a Strix Point NPU (1022:17f0), by calling SYNC_BO with size 0 on an AMDXDNA_BO_SHARE object. The import arm takes the same request but flushes the whole scatterlist, so it survives it. Nothing needs flushing for an empty range, so answer before choosing a path. Fixes: e252e3f3488a ("accel/amdxdna: Revise device bo creation and free") Cc: stable@vger.kernel.org Signed-off-by: Taimuraz Kaitmazov Reviewed-by: Lizhi Hou Signed-off-by: Lizhi Hou Link: https://patch.msgid.link/20260817230655.356785-1-taimuraz@kaitmazov.com --- drivers/accel/amdxdna/amdxdna_gem.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/accel/amdxdna/amdxdna_gem.c b/drivers/accel/amdxdna/amdxdna_gem.c index 1c63eff0a4a8..2a16de96e6a4 100644 --- a/drivers/accel/amdxdna/amdxdna_gem.c +++ b/drivers/accel/amdxdna/amdxdna_gem.c @@ -1247,6 +1247,9 @@ static int amdxdna_flush_bo(struct amdxdna_gem_obj *abo, u64 offset, u64 size) return -EINVAL; size = min(abo->mem.size, end) - offset; + if (!size) + return 0; + if (is_import_bo(abo)) drm_clflush_sg(abo->base.sgt); else if (amdxdna_gem_vmap(abo)) From 4fb8d6379d2c7ceecb2b3e111954d29089d59492 Mon Sep 17 00:00:00 2001 From: Liang Luo Date: Wed, 19 Aug 2026 11:12:44 +0800 Subject: [PATCH 0040/1198] sched_ext: Fix nonexistent field in sched-ext.rst example The ops.exit() example in sched-ext.rst reads ei->type, but struct scx_exit_info has never had a type field - the exit reason is exposed as ei->kind since the struct was introduced. A scheduler written following the example fails to compile with error: no member named 'type' in 'struct scx_exit_info' Use ei->kind. Fixes: fa48e8d2c7b5 ("sched_ext: Documentation: scheduler: Document extensible scheduler class") Signed-off-by: Liang Luo Signed-off-by: Tejun Heo --- Documentation/scheduler/sched-ext.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/scheduler/sched-ext.rst b/Documentation/scheduler/sched-ext.rst index 0e97fd019994..35b550671ca7 100644 --- a/Documentation/scheduler/sched-ext.rst +++ b/Documentation/scheduler/sched-ext.rst @@ -230,7 +230,7 @@ optional. The following modified excerpt is from void BPF_STRUCT_OPS(simple_exit, struct scx_exit_info *ei) { - exit_type = ei->type; + exit_type = ei->kind; } SEC(".struct_ops") From 0c893d170ff8efe7b4067552932d26e7defba307 Mon Sep 17 00:00:00 2001 From: Hemanth Selam Date: Wed, 19 Aug 2026 14:06:00 +0530 Subject: [PATCH 0041/1198] selftests/cgroup: set the test plan after the setup checks The cgroup tests announce their plan before checking whether cgroup v2 is available, so on a host without it they promise a number of results and then skip out after the first one: TAP version 13 1..3 ok 1 # SKIP cgroup v2 isn't mounted # Planned tests != run tests (3 != 1) # Totals: pass:0 fail:0 xfail:0 xpass:0 skip:1 error:0 ksft_exit_skip() can only emit a well formed "1..0 # SKIP" line while no plan has been printed, as the comment above it in kselftest.h points out. Move ksft_set_plan() below the setup checks that can skip, so that a skipped run reports: TAP version 13 1..0 # SKIP cgroup v2 isn't mounted Several of the tests skip more than once while setting up, for a missing or unwritable controller as well, so the plan goes after the last of them. test_core joins its two setup paths at the post_v2_setup label and sets the plan there. Reporting each planned test as skipped instead would keep the plan where it is, but the setup failures here mean the whole test cannot run rather than its individual cases being skipped, which is what "1..0 # SKIP" is for. Fixes: 1dc830ee4c15 ("selftests/cgroup: conform test to KTAP format output") Signed-off-by: Hemanth Selam Reviewed-by: Sarthak Sharma Signed-off-by: Tejun Heo --- tools/testing/selftests/cgroup/test_core.c | 2 +- tools/testing/selftests/cgroup/test_cpu.c | 2 +- tools/testing/selftests/cgroup/test_cpuset.c | 2 +- tools/testing/selftests/cgroup/test_freezer.c | 2 +- tools/testing/selftests/cgroup/test_kill.c | 2 +- tools/testing/selftests/cgroup/test_kmem.c | 2 +- tools/testing/selftests/cgroup/test_memcontrol.c | 2 +- tools/testing/selftests/cgroup/test_pids.c | 2 +- tools/testing/selftests/cgroup/test_zswap.c | 2 +- 9 files changed, 9 insertions(+), 9 deletions(-) diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c index e9bee164bb70..20d2b63774c3 100644 --- a/tools/testing/selftests/cgroup/test_core.c +++ b/tools/testing/selftests/cgroup/test_core.c @@ -919,7 +919,6 @@ int main(int argc, char *argv[]) int i; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), &nsdelegate)) { if (setup_named_v1_root(root, sizeof(root), CG_NAMED_NAME)) ksft_exit_skip("cgroup v2 isn't mounted and could not setup named v1 hierarchy\n"); @@ -932,6 +931,7 @@ int main(int argc, char *argv[]) ksft_exit_skip("Failed to set memory controller\n"); post_v2_setup: + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_cpu.c b/tools/testing/selftests/cgroup/test_cpu.c index f9f7017d9299..735a53bb222b 100644 --- a/tools/testing/selftests/cgroup/test_cpu.c +++ b/tools/testing/selftests/cgroup/test_cpu.c @@ -832,7 +832,6 @@ int main(int argc, char *argv[]) int i; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); @@ -840,6 +839,7 @@ int main(int argc, char *argv[]) if (cg_write(root, "cgroup.subtree_control", "+cpu")) ksft_exit_skip("Failed to set cpu controller\n"); + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_cpuset.c b/tools/testing/selftests/cgroup/test_cpuset.c index 8c2d4d4ef1fc..3dfadd280c1c 100644 --- a/tools/testing/selftests/cgroup/test_cpuset.c +++ b/tools/testing/selftests/cgroup/test_cpuset.c @@ -497,7 +497,6 @@ int main(int argc, char *argv[]) int i; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); @@ -505,6 +504,7 @@ int main(int argc, char *argv[]) if (cg_write(root, "cgroup.subtree_control", "+cpuset")) ksft_exit_skip("Failed to set cpuset controller\n"); + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_freezer.c b/tools/testing/selftests/cgroup/test_freezer.c index 0569e93fa6b0..f28bb02e9783 100644 --- a/tools/testing/selftests/cgroup/test_freezer.c +++ b/tools/testing/selftests/cgroup/test_freezer.c @@ -1491,9 +1491,9 @@ int main(int argc, char *argv[]) int i; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_kill.c b/tools/testing/selftests/cgroup/test_kill.c index f6cd23a8ecc7..99cafd9dc013 100644 --- a/tools/testing/selftests/cgroup/test_kill.c +++ b/tools/testing/selftests/cgroup/test_kill.c @@ -278,9 +278,9 @@ int main(int argc, char *argv[]) int i; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c index 1db0ba1226b9..cb47561b4b44 100644 --- a/tools/testing/selftests/cgroup/test_kmem.c +++ b/tools/testing/selftests/cgroup/test_kmem.c @@ -426,7 +426,6 @@ int main(int argc, char **argv) int i; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); @@ -441,6 +440,7 @@ int main(int argc, char **argv) if (cg_write(root, "cgroup.subtree_control", "+memory")) ksft_exit_skip("Failed to set memory controller\n"); + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c index 0ebf796f3cff..3a84d068fbf3 100644 --- a/tools/testing/selftests/cgroup/test_memcontrol.c +++ b/tools/testing/selftests/cgroup/test_memcontrol.c @@ -1798,7 +1798,6 @@ int main(int argc, char **argv) page_size = BUF_SIZE; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); @@ -1823,6 +1822,7 @@ int main(int argc, char **argv) ksft_exit_skip("Failed to query cgroup mount option\n"); has_localevents = proc_status; + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_pids.c b/tools/testing/selftests/cgroup/test_pids.c index 9a387c815d2c..710109b53dfe 100644 --- a/tools/testing/selftests/cgroup/test_pids.c +++ b/tools/testing/selftests/cgroup/test_pids.c @@ -148,7 +148,6 @@ int main(int argc, char **argv) char root[PATH_MAX]; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); @@ -163,6 +162,7 @@ int main(int argc, char **argv) if (cg_write(root, "cgroup.subtree_control", "+pids")) ksft_exit_skip("Failed to set pids controller\n"); + ksft_set_plan(ARRAY_SIZE(tests)); for (int i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_zswap.c b/tools/testing/selftests/cgroup/test_zswap.c index 49b36ee79160..6e7b89315bbf 100644 --- a/tools/testing/selftests/cgroup/test_zswap.c +++ b/tools/testing/selftests/cgroup/test_zswap.c @@ -810,7 +810,6 @@ int main(int argc, char **argv) page_size = BUF_SIZE; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); @@ -827,6 +826,7 @@ int main(int argc, char **argv) if (cg_write(root, "cgroup.subtree_control", "+memory")) ksft_exit_skip("Failed to set memory controller\n"); + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: From 7e2f2a377ac9f50296ad60bd331f0d4def7aee51 Mon Sep 17 00:00:00 2001 From: Zqiang Date: Thu, 16 Jul 2026 17:56:37 +0800 Subject: [PATCH 0042/1198] workqueue: Use raise_softirq() to trigger softirq in irq_work handler bh_pool_kick_normal() and bh_pool_kick_highpri() are registered via init_irq_work() without the IRQ_WORK_HARD_IRQ flag. On PREEMPT_RT, such irq_work items are processed by the per-CPU irq_workd kthread in preemptible task context with IRQs enabled. However, raise_softirq_irqoff() requires IRQs to be disabled. Calling it from irq_workd trips the lockdep assertion in __raise_softirq_irqoff() and the non-atomic update of the softirq pending mask can lose bits raised by an interrupt on the same CPU. Replace raise_softirq_irqoff() with raise_softirq() in the irq_work handlers. Fixes: 2f34d7337d98 ("workqueue: Fix queue_work_on() with BH workqueues") Cc: stable@vger.kernel.org # v6.9+ Signed-off-by: Zqiang Signed-off-by: Tejun Heo --- kernel/workqueue.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index c0b72dcc0f03..f2aed36cf7c0 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -8065,12 +8065,12 @@ static inline void wq_watchdog_init(void) { } static void bh_pool_kick_normal(struct irq_work *irq_work) { - raise_softirq_irqoff(TASKLET_SOFTIRQ); + raise_softirq(TASKLET_SOFTIRQ); } static void bh_pool_kick_highpri(struct irq_work *irq_work) { - raise_softirq_irqoff(HI_SOFTIRQ); + raise_softirq(HI_SOFTIRQ); } static void __init restrict_unbound_cpumask(const char *name, const struct cpumask *mask) From c7a2a3618290594867b4829900b434704ab31dbc Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Tue, 18 Aug 2026 16:05:10 +0300 Subject: [PATCH 0043/1198] x86/bpf: Make arch_bpf_trampoline_size allocate from EXECMEM_MODULE_DATA Jiri Olsa reports slowdown of tracing_multi benchmark that allocates huge number of trampolines [1]. The slowdown caused by extra protection changes in execmem_alloc_rw() and execmem_free(). With ROX caches enabled, all execmem allocations except EXECMEM_MODULE_DATA are ROX after the allocation. execmem_alloc_rw() temporarily sets them to W+NX and execmem_free() resets them back to ROX. The only user of bpf_jit_alloc_exec_rw() is x86::arch_bpf_trampoline_size() that only needs a temporary writable buffer in the modules address space. On x86 executable memory and module data are constrained to the same address range, so x86::arch_bpf_trampoline_size() can directly use execmem_alloc(EXECMEM_MODULE_DATA) Replace the call to bpf_jit_alloc_exec_rw() with a call to execmem_alloc(EXECMEM_MODULE_DATA) in x86::arch_bpf_trampoline_size() and drop bpf_jit_alloc_exec_rw() helper. Fixes: 5bf02dbf39fa ("bpf, x86: Make sure allocation in arch_bpf_trampoline_size() is writable") Reported-by: Jiri Olsa Signed-off-by: Mike Rapoport (Microsoft) Signed-off-by: Daniel Borkmann Tested-by: Jiri Olsa Link: https://lore.kernel.org/all/an8r7EODLIL-bZM3@krava Link: https://lore.kernel.org/bpf/20260818130510.3110054-1-rppt@kernel.org --- arch/x86/net/bpf_jit_comp.c | 8 +++++--- include/linux/filter.h | 1 - kernel/bpf/core.c | 5 ----- 3 files changed, 5 insertions(+), 9 deletions(-) diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 1a9fb530adc3..2853e87797a7 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -3818,15 +3819,16 @@ int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, * * We cannot use kvmalloc here, because we need image to be in * module memory range. - * Since it must be writable use bpf_jit_alloc_exec_rw(). + * Since it must be writable use execmem_alloc(EXECMEM_MODULE_DATA) + * that returns writable memory in the module address space. */ - image = bpf_jit_alloc_exec_rw(PAGE_SIZE); + image = execmem_alloc(EXECMEM_MODULE_DATA, PAGE_SIZE); if (!image) return -ENOMEM; ret = __arch_prepare_bpf_trampoline(&im, image, image + PAGE_SIZE, image, m, flags, tnodes, func_addr); - bpf_jit_free_exec(image); + execmem_free(image); return ret; } diff --git a/include/linux/filter.h b/include/linux/filter.h index 4a9bc6a848f2..39decde7fc73 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1376,7 +1376,6 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, void bpf_jit_binary_free(struct bpf_binary_header *hdr); u64 bpf_jit_alloc_exec_limit(void); void *bpf_jit_alloc_exec(unsigned long size); -void *bpf_jit_alloc_exec_rw(unsigned long size); void bpf_jit_free_exec(void *addr); void bpf_jit_free(struct bpf_prog *fp); struct bpf_binary_header * diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index d55e737ed75a..8b294dfc1ad4 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1128,11 +1128,6 @@ void *bpf_jit_alloc_exec(unsigned long size) return execmem_alloc(EXECMEM_BPF, size); } -void *bpf_jit_alloc_exec_rw(unsigned long size) -{ - return execmem_alloc_rw(EXECMEM_BPF, size); -} - void bpf_jit_free_exec(void *addr) { execmem_free(addr); From 37e5c4f4d2856290b1c56e573ced91dcd88db8ec Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 20 Aug 2026 04:20:18 +0200 Subject: [PATCH 0044/1198] bpf: Reject invalid LDSX instruction in disassembly The signed-load mnemonic table has entries for byte, half-word, and word loads because BPF_MEMSX does not support double-word loads. A BPF_MEMSX | BPF_DW instruction nevertheless selects index 3, past the end of this table. Program Structure diagnostics can disassemble a malformed instruction before check_and_resolve_insns() rejects its opcode. Placing the invalid signed double-word load at the end of a program therefore triggers an out-of-bounds access while reporting subprogram fallthrough. Treat signed double-word loads as invalid in the disassembler and use the existing BUG_ldx fallback instead. Fixes: a8f427835394 ("bpf: Report Program Structure CFG errors") Reported-by: syzbot+3544d9b2a9206be8ba37@syzkaller.appspotmail.com Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Daniel Borkmann Reviewed-by: Jiayuan Chen Link: https://lore.kernel.org/bpf/20260820022020.3450479-2-memxor@gmail.com --- kernel/bpf/disasm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index 50b3ca5149a0..b1a3fbe3fda5 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -295,7 +295,8 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, verbose(cbs->private_data, "BUG_st_%02x", insn->code); } } else if (class == BPF_LDX) { - if (BPF_MODE(insn->code) != BPF_MEM && BPF_MODE(insn->code) != BPF_MEMSX) { + if ((BPF_MODE(insn->code) != BPF_MEM && BPF_MODE(insn->code) != BPF_MEMSX) || + (BPF_MODE(insn->code) == BPF_MEMSX && BPF_SIZE(insn->code) == BPF_DW)) { verbose(cbs->private_data, "BUG_ldx_%02x", insn->code); return; } From 175a58668e2d5e96c571177fc7a0d8997bfbb205 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 20 Aug 2026 04:20:19 +0200 Subject: [PATCH 0045/1198] selftests/bpf: Test invalid DW LDSX diagnostics An invalid BPF_MEMSX | BPF_DW instruction can reach Program Structure diagnostics before opcode validation when placed at the end of a subprogram. Exercise this path and require the disassembler fallback so table bounds regressions are caught. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20260820022020.3450479-3-memxor@gmail.com --- tools/testing/selftests/bpf/progs/verifier_cfg.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/verifier_cfg.c b/tools/testing/selftests/bpf/progs/verifier_cfg.c index c1f55e1d80a4..3c3bb03e8217 100644 --- a/tools/testing/selftests/bpf/progs/verifier_cfg.c +++ b/tools/testing/selftests/bpf/progs/verifier_cfg.c @@ -3,6 +3,7 @@ #include #include +#include "../../../include/linux/filter.h" #include "bpf_misc.h" SEC("socket") @@ -55,6 +56,19 @@ __naked void out_of_range_jump2(void) " ::: __clobber_all); } +SEC("socket") +__description("invalid DW LDSX instruction in diagnostics") +__failure __msg("BUG_ldx_99") +__log_level(2) +__naked void invalid_dw_ldsx(void) +{ + asm volatile (" \ + .8byte %[ldsx_dw]; \ +" : + : __imm_insn(ldsx_dw, BPF_RAW_INSN(BPF_LDX | BPF_MEMSX | BPF_DW, BPF_REG_0, BPF_REG_0, 0, 0)) + : __clobber_all); +} + SEC("socket") __description("loop (back-edge)") __failure __msg("unreachable insn 1") From 72c5ae18ebe6588101f2c1e96be61618ce06f182 Mon Sep 17 00:00:00 2001 From: Liang Luo Date: Thu, 20 Aug 2026 10:37:44 +0800 Subject: [PATCH 0046/1198] Docs/admin-guide/cgroup-v2: document BPF scheduler callbacks for cpu.max and cpu.idle The cpu.weight and cpu.weight.nice entries already state that the files also affect a BPF scheduler through the cgroup_set_weight callback. However, cpu.max, cpu.max.burst and cpu.idle only mention the fair-class scheduler, even though sched_ext implements the cgroup_set_bandwidth (notified with the period/quota from cpu.max and the burst from cpu.max.burst) and cgroup_set_idle callbacks from these interfaces. Mirror the cpu.weight wording for the three entries and generalize the category preamble to refer to the corresponding cgroup_set_* callback so it keeps covering the entries below. Suggested-by: Tejun Heo Signed-off-by: Liang Luo Signed-off-by: Tejun Heo --- Documentation/admin-guide/cgroup-v2.rst | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index aed195a71cbf..3dc6889ebdb2 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1130,9 +1130,9 @@ policy and the underlying scheduler. From the point of view of the cpu controlle processes can be categorized as follows: * Processes under the fair-class scheduler -* Processes under a BPF scheduler with the ``cgroup_set_weight`` callback +* Processes under a BPF scheduler with the corresponding ``cgroup_set_*`` callback * Everything else: ``SCHED_{FIFO,RR,DEADLINE}`` and processes under a BPF scheduler - without the ``cgroup_set_weight`` callback + without the corresponding ``cgroup_set_*`` callback For details on when a process is under the fair-class scheduler or a BPF scheduler, check out :ref:`Documentation/scheduler/sched-ext.rst `. @@ -1202,7 +1202,9 @@ will be referred to. All time durations are in microseconds. $PERIOD duration. "max" for $MAX indicates no limit. If only one number is written, $MAX is updated. - This file affects only processes under the fair-class scheduler. + This file affects only processes under the fair-class scheduler and a BPF + scheduler with the ``cgroup_set_bandwidth`` callback depending on what + the callback actually does. cpu.max.burst A read-write single value file which exists on non-root @@ -1210,7 +1212,9 @@ will be referred to. All time durations are in microseconds. The burst in the range [0, $MAX]. - This file affects only processes under the fair-class scheduler. + This file affects only processes under the fair-class scheduler and a BPF + scheduler with the ``cgroup_set_bandwidth`` callback depending on what + the callback actually does. cpu.pressure A read-write nested-keyed file. @@ -1262,7 +1266,9 @@ will be referred to. All time durations are in microseconds. own relative priorities, but the cgroup itself will be treated as very low priority relative to its peers. - This file affects only processes under the fair-class scheduler. + This file affects only processes under the fair-class scheduler and a BPF + scheduler with the ``cgroup_set_idle`` callback depending on what the + callback actually does. Memory ------ From a8c6daab4b0e276508b7ffdd66c60fd3020a9178 Mon Sep 17 00:00:00 2001 From: Hongfu Li Date: Thu, 20 Aug 2026 15:09:44 +0800 Subject: [PATCH 0047/1198] selftests/cgroup: Fix cg_run_in_subcgroups ignoring arg parameter MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit cg_run_in_subcgroups() discards its arg and always passes NULL to cg_run(), turning the (void *)100 from test_kmem_dead_cgroups() into NULL so no allocation occurs. This makes test_kmem_dead_cgroups() falsely pass without exercising the "dying cgroup with charged slab" scenario it intends to test. Pass the arg through to cg_run() to fix this. Fixes: 933dc80ec262 ("kselftests: cgroup: add kernel memory accounting tests") Signed-off-by: Hongfu Li Reviewed-by: Michal Koutný Signed-off-by: Tejun Heo --- tools/testing/selftests/cgroup/test_kmem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c index cb47561b4b44..437f2d35f205 100644 --- a/tools/testing/selftests/cgroup/test_kmem.c +++ b/tools/testing/selftests/cgroup/test_kmem.c @@ -145,7 +145,7 @@ static int cg_run_in_subcgroups(const char *parent, return -1; } - if (cg_run(child, fn, NULL)) { + if (cg_run(child, fn, arg)) { cg_destroy(child); free(child); return -1; From 150aeba624e8b7cac51c39440d7e8e1fd11de9a0 Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Wed, 19 Aug 2026 20:58:29 +0800 Subject: [PATCH 0048/1198] bpf: Fix REG INVARIANTS VIOLATION on speculative pointer arithmetic Take the following unprivileged program as an example: r0 = bpf_map_lookup_elem(...) /* PTR_TO_MAP_VALUE, offset 0 */ ... 14: r0 += r1 /* r1 is a bounded scalar */ 15: r9 = r0 Loading it triggers a verifier warning from reg_bounds_sanity_check(): verifier bug: REG INVARIANTS VIOLATION (alu): const subreg tnum out of sync with range bounds r64={.base=0x0, .size=0x0} r32={.base=0x0, .size=0xffffffff} var_off=(0x0, 0x0) What happens: 1. Processing insn 14 (r0 += r1) in adjust_ptr_min_max_vals(), the new offset is computed into dst_reg's var_off and 32/64-bit ranges. 2. Because pointer registers do not track 32-bit subregister bounds, __mark_reg32_unbounded() first sets r32 to the full range; r32 is re-derived from the offset at the end of the function by reg_bounds_sync(). 3. On the unprivileged path, sanitize_ptr_alu() is called and, via sanitize_speculative_path() -> push_stack(), snapshots the current register state and schedules the next instruction (insn 15) to be verified directly as a speculative path. 4. That snapshot is taken between step 2 and the final reg_bounds_sync(): at this point dst_reg's var_off still holds the (const) original offset while r32 has just been blanked to the full range, i.e. the two are out of sync. When the speculative path later verifies insn 15 (r9 = r0), the inconsistent state reaches reg_bounds_sanity_check() and trips the warning. var_off and the 32-bit range must always be consistent. There are two ways to keep the snapshot consistent: 1. sync var_off and r32 before the snapshot so they match, or 2. leave r32 at its original (already consistent) value and blank it only after the snapshot. The whole point of sanitize_ptr_alu() is to insert a harmless masking sequence that keeps the access in bounds under speculation, so the state it snapshots should faithfully represent that. Take approach 2: move __mark_reg32_unbounded() to after sanitize_ptr_alu(), so the speculative snapshot keeps the pointer's original, consistent r32. The non-speculative path is unchanged: r32 is still blanked before the offset is applied and re-derived by reg_bounds_sync(). Fixes: 5f99f312bd3b ("bpf: add register bounds sanity checks and sanitization") Reported-by: Hiker Cl Closes: https://lore.kernel.org/bpf/CAGM=xGB1fJ9kT8XTitVo74B0WGqgjkoUHdLwzytwV0AyqeVApw@mail.gmail.com/ Signed-off-by: Jiayuan Chen Acked-by: Eduard Zingerman Link: https://lore.kernel.org/bpf/20260819125840.286434-1-jiayuan.chen@linux.dev Signed-off-by: Kumar Kartikeya Dwivedi --- kernel/bpf/verifier.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e421ea2b80c3..5e37ca75e5c4 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -14560,9 +14560,6 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, struct bpf_insn return -EINVAL; } - /* pointer types do not carry 32-bit bounds at the moment. */ - __mark_reg32_unbounded(dst_reg); - if (sanitize_needed(opcode)) { ret = sanitize_ptr_alu(env, insn, ptr_reg, off_reg, dst_reg, &info, false); @@ -14570,6 +14567,14 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, struct bpf_insn return sanitize_err(env, insn, ret); } + /* + * Pointer types do not carry 32-bit bounds at the moment. Blank r32 + * only after sanitize_ptr_alu() may have snapshotted dst_reg into a + * speculative path: otherwise reg_bounds_sanity_check() might hit some + * constraints violations. + */ + __mark_reg32_unbounded(dst_reg); + switch (opcode) { case BPF_ADD: /* From 7ee2f20bf20ed59fb269a260c4c4aff1e67f1b7c Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Wed, 19 Aug 2026 20:58:30 +0800 Subject: [PATCH 0049/1198] selftests/bpf: Add reg-invariants test for speculative pointer arithmetic An unprivileged socket filter does variable pointer arithmetic on a PTR_TO_MAP_VALUE whose offset collapses to a constant. The Spectre-v1 speculative path used to snapshot the pointer with a const offset and an unbounded r32, which tripped reg_bounds_sanity_check() on the following register move. Mark the test __success_unpriv (the speculative path only runs unprivileged) and flag it BPF_F_TEST_REG_INVARIANTS so the invariant violation becomes a hard load failure. The unprivileged run fails without the verifier fix and passes with it: verifier_bounds/spec_ptr_alu_const_offset @unpriv:FAIL # without fix verifier_bounds/spec_ptr_alu_const_offset @unpriv:OK # with fix Signed-off-by: Jiayuan Chen Tested-by: Eduard Zingerman Link: https://lore.kernel.org/bpf/20260819125840.286434-2-jiayuan.chen@linux.dev Signed-off-by: Kumar Kartikeya Dwivedi --- .../selftests/bpf/progs/verifier_bounds.c | 41 +++++++++++++++++++ 1 file changed, 41 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c index 1a273e416fed..df8d5309657e 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bounds.c +++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c @@ -2267,6 +2267,47 @@ __naked void deduce64_from_32_wrapping_32bit(void) : __clobber_all); } +/* + * Unprivileged variable pointer arithmetic on a PTR_TO_MAP_VALUE whose + * offset collapses to a constant. The Spectre-v1 speculative path snapshots + * the pointer while its r32 has just been blanked but its offset not yet + * synced; the following register move used to trip reg_bounds_sanity_check() + * ("const subreg tnum out of sync with range bounds"). With + * BPF_F_TEST_REG_INVARIANTS that violation turns into a load failure, so the + * unprivileged program must still load. + */ +SEC("socket") +__success __success_unpriv +__flag(BPF_F_TEST_REG_INVARIANTS) +__naked void spec_ptr_alu_const_offset(void) +{ + asm volatile (" \ + call %[bpf_ktime_get_ns]; \ + *(u64*)(r10 - 16) = r0; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + r1 = *(u64*)(r10 - 16); \ + r2 = 0x40000000; \ + if r1 > r2 goto l0_%=; \ + if r1 s> 1 goto l0_%=; /* r1 in [0, 1] */ \ + r0 += r1; /* ptr += bounded scalar */ \ + r9 = r0; /* used to trip the warning */ \ + *(u8*)(r0 + 0) = r1; \ +l0_%=: r0 = 0; \ + exit; \ + " + : + : __imm(bpf_ktime_get_ns), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + /* Check that range_within() compares cnum ranges, not min/max projections. */ SEC("socket") __failure __msg("div by zero") From efebf6496685c93150df5bb0794363ae70c5f58a Mon Sep 17 00:00:00 2001 From: Hui Su Date: Fri, 7 Aug 2026 01:56:00 +0800 Subject: [PATCH 0050/1198] bpf: Fix infinite loop in pcpu_freelist push with one possible CPU __pcpu_freelist_push() can loop forever when only one CPU is possible and an NMI re-enters pcpu_freelist_push() while the interrupted context holds that CPU's freelist lock. After the current-CPU fast path fails, the fallback loop walks cpu_possible_mask while skipping the current CPU. With CONFIG_SMP=n, or when an SMP kernel is limited to one possible CPU with nr_cpus=1 or possible_cpus=1, there are no other possible CPUs to examine. The loop therefore makes no lock acquisition attempt and can never make progress. The following stack was observed on a UP system: NMI context: pcpu_freelist_push free_htab_elem htab_map_delete_elem [perf-event BPF program] __perf_event_overflow perf_event_nmi_handler exc_nmi Interrupted context: __pcpu_freelist_push pcpu_freelist_push free_htab_elem htab_map_delete_elem [raw_tp/sys_enter BPF program] __bpf_trace_sys_enter do_syscall_64 raw_res_spin_lock() detects the same-CPU recursive acquisition and returns -EDEADLK, but the subsequent fallback loop has no candidate head on a system with one possible CPU. Restore the extra fallback head that existed before the rqspinlock conversion. Keep the current-CPU fast path, then try the other possible CPUs and finally the extra head. The additional head lets a push, which cannot fail without losing a preallocated element, make progress when the only per-CPU head is held by the interrupted context. Also check the extra head from the pop path so that nodes placed there can be reused. Fixes: f2ac0e5d1c4d ("bpf: Convert percpu_freelist.c to rqspinlock") Signed-off-by: Hui Su Cc: stable@vger.kernel.org Link: https://lore.kernel.org/bpf/20260806175600.1993595-1-sh_def@163.com Signed-off-by: Kumar Kartikeya Dwivedi --- kernel/bpf/percpu_freelist.c | 35 +++++++++++++++++++++++++++-------- kernel/bpf/percpu_freelist.h | 1 + 2 files changed, 28 insertions(+), 8 deletions(-) diff --git a/kernel/bpf/percpu_freelist.c b/kernel/bpf/percpu_freelist.c index 632762b57299..06ce588d13a3 100644 --- a/kernel/bpf/percpu_freelist.c +++ b/kernel/bpf/percpu_freelist.c @@ -17,6 +17,8 @@ int pcpu_freelist_init(struct pcpu_freelist *s) raw_res_spin_lock_init(&head->lock); head->first = NULL; } + raw_res_spin_lock_init(&s->extralist.lock); + s->extralist.first = NULL; return 0; } @@ -46,22 +48,28 @@ void __pcpu_freelist_push(struct pcpu_freelist *s, struct pcpu_freelist_node *node) { struct pcpu_freelist_head *head; - int cpu; + int cpu, this_cpu; if (___pcpu_freelist_push(this_cpu_ptr(s->freelist), node)) return; + this_cpu = raw_smp_processor_id(); while (true) { - for_each_cpu_wrap(cpu, cpu_possible_mask, raw_smp_processor_id()) { - if (cpu == raw_smp_processor_id()) + for_each_cpu_wrap(cpu, cpu_possible_mask, this_cpu) { + if (cpu == this_cpu) continue; + head = per_cpu_ptr(s->freelist, cpu); - if (raw_res_spin_lock(&head->lock)) - continue; - pcpu_freelist_push_node(head, node); - raw_res_spin_unlock(&head->lock); - return; + if (___pcpu_freelist_push(head, node)) + return; } + + /* + * Push cannot fail. Use the extra list when none of the + * per-CPU freelists can accept the node. + */ + if (___pcpu_freelist_push(&s->extralist, node)) + return; } } @@ -117,6 +125,17 @@ static struct pcpu_freelist_node *___pcpu_freelist_pop(struct pcpu_freelist *s) } raw_res_spin_unlock(&head->lock); } + + /* Per-CPU lists are empty or unavailable, try the extra list. */ + head = &s->extralist; + if (!READ_ONCE(head->first)) + return NULL; + if (raw_res_spin_lock(&head->lock)) + return NULL; + node = head->first; + if (node) + WRITE_ONCE(head->first, node->next); + raw_res_spin_unlock(&head->lock); return node; } diff --git a/kernel/bpf/percpu_freelist.h b/kernel/bpf/percpu_freelist.h index 914798b74967..980cf2884fd2 100644 --- a/kernel/bpf/percpu_freelist.h +++ b/kernel/bpf/percpu_freelist.h @@ -14,6 +14,7 @@ struct pcpu_freelist_head { struct pcpu_freelist { struct pcpu_freelist_head __percpu *freelist; + struct pcpu_freelist_head extralist; }; struct pcpu_freelist_node { From 511585987d27d8cb668acebd399fc4deda23404c Mon Sep 17 00:00:00 2001 From: Marek Czernohous Date: Thu, 13 Aug 2026 01:13:27 +0200 Subject: [PATCH 0051/1198] drm/nouveau: unsubscribe the channel-kill event before the fence context nouveau_channel_del() tears the fence context down first and only drops the channel-kill subscription later, in the middle of the nvif object teardown: if (chan->fence) nouveau_fence(chan->cli->drm)->context_del(chan); ... nvif_object_dtor(&chan->vram); nvif_event_dtor(&chan->kill); The subscribed handler is nouveau_channel_killed(), which calls nouveau_channel_kill() and from there nouveau_fence_context_kill() on chan->fence. A kill event delivered in that window takes fctx->lock and walks fctx->pending on a fence context that context_del() has already freed. Nothing reaches this below Fermi today, because the subscription is gated on FERMI_CHANNEL_GPFIFO and nothing kills a channel there. On Fermi and newer the window is real but narrow, since a kill has to land exactly while the channel is being destroyed. That is reason enough on its own, which is why this carries a Fixes: tag. The last patch in this series subscribes Tesla channels as well; nothing kills those today, so it does not widen the exposure now, but it is the groundwork for a recovery path that would, and the ordering is better fixed before that lands than alongside it. Drop the subscription before anything it depends on is torn down. Fixes: ea13e5abf807 ("drm/nouveau: signal pending fences when channel has been killed") Cc: stable@vger.kernel.org Assisted-by: Claude:claude-opus-5 Signed-off-by: Marek Czernohous Fixes: ea13e5abf807 ("drm/nouveau: signal pending fences when channel has been killed") Reviewed-by: Lyude Paul Signed-off-by: Lyude Paul Link: https://patch.msgid.link/20260812231330.705425-2-mczernohous@gmail.com --- drivers/gpu/drm/nouveau/nouveau_chan.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.c b/drivers/gpu/drm/nouveau/nouveau_chan.c index 598513f60449..f142f6310596 100644 --- a/drivers/gpu/drm/nouveau/nouveau_chan.c +++ b/drivers/gpu/drm/nouveau/nouveau_chan.c @@ -90,6 +90,14 @@ nouveau_channel_del(struct nouveau_channel **pchan) { struct nouveau_channel *chan = *pchan; if (chan) { + /* + * Drop the kill-event subscription first. Its handler + * dereferences chan->fence, which the fence context teardown + * below frees, so leaving it armed across the teardown leaves + * a window for a use-after-free. + */ + nvif_event_dtor(&chan->kill); + if (chan->fence) nouveau_fence(chan->cli->drm)->context_del(chan); @@ -100,7 +108,6 @@ nouveau_channel_del(struct nouveau_channel **pchan) nvif_object_dtor(&chan->nvsw); nvif_object_dtor(&chan->gart); nvif_object_dtor(&chan->vram); - nvif_event_dtor(&chan->kill); nvif_object_dtor(&chan->user); nvif_mem_dtor(&chan->mem_userd); nouveau_vma_del(&chan->sema.vma); From 41a28c865d1d5843f8cb9e0af17a8f4d9e2961ff Mon Sep 17 00:00:00 2001 From: Yun Zhou Date: Fri, 31 Jul 2026 11:10:10 +0800 Subject: [PATCH 0052/1198] xfs: don't hold buffer locks across sync transaction commit in xfs_sync_sb_buf xfs_sync_sb_buf() holds sb/rtsb buffer locks across a synchronous xfs_trans_commit(), which flushes the CIL push workqueue internally. If shutdown occurs during the CIL push, xfs_buf_item_unpin() needs to lock these buffers to fail them, causing a deadlock: setlabel: holds buf lock -> flush_workqueue(xfs-cil) CIL push worker: xfs_buf_item_unpin -> xfs_buf_lock(same buf) Remove the xfs_trans_bhold() calls so that commit releases the buffer locks normally. After the sync commit, re-acquire the buffers via mp->m_sb_bp / mp->m_rtsb_bp for the on-disk writeback. Fixes: f7664b31975b ("xfs: implement online get/set fs label") Reported-by: syzbot+837bcd54843dd6262f2f@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=837bcd54843dd6262f2f Cc: stable@vger.kernel.org Signed-off-by: Yun Zhou Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/libxfs/xfs_rtgroup.h | 6 +++++- fs/xfs/libxfs/xfs_sb.c | 37 +++++++++++++++++-------------------- 2 files changed, 22 insertions(+), 21 deletions(-) diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h index c0b9f9f2c413..fca2eb74908c 100644 --- a/fs/xfs/libxfs/xfs_rtgroup.h +++ b/fs/xfs/libxfs/xfs_rtgroup.h @@ -359,7 +359,11 @@ static inline int xfs_initialize_rtgroups(struct xfs_mount *mp, # define xfs_rtgroup_unlock(rtg, gf) ((void)0) # define xfs_rtgroup_trans_join(tp, rtg, gf) ((void)0) # define xfs_update_rtsb(bp, sb_bp) ((void)0) -# define xfs_log_rtsb(tp, sb_bp) (NULL) +static inline struct xfs_buf *xfs_log_rtsb(struct xfs_trans *tp, + const struct xfs_buf *sb_bp) +{ + return NULL; +} # define xfs_rtgroup_get_geometry(rtg, rgeo) (-EOPNOTSUPP) #endif /* CONFIG_XFS_RT */ diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 75f2a021ee6d..f0341adbb879 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -1470,36 +1470,33 @@ xfs_sync_sb_buf( bool update_rtsb) { struct xfs_trans *tp; - struct xfs_buf *bp; - struct xfs_buf *rtsb_bp = NULL; int error; error = xfs_trans_alloc(mp, &M_RES(mp)->tr_sb, 0, 0, 0, &tp); if (error) return error; - bp = xfs_trans_getsb(tp); xfs_log_sb(tp); - xfs_trans_bhold(tp, bp); - if (update_rtsb) { - rtsb_bp = xfs_log_rtsb(tp, bp); - if (rtsb_bp) - xfs_trans_bhold(tp, rtsb_bp); - } + if (update_rtsb) + xfs_log_rtsb(tp, xfs_trans_getsb(tp)); xfs_trans_set_sync(tp); error = xfs_trans_commit(tp); if (error) - goto out; - /* - * write out the sb buffer to get the changes to disk - */ - error = xfs_bwrite(bp); - if (!error && rtsb_bp) - error = xfs_bwrite(rtsb_bp); -out: - if (rtsb_bp) - xfs_buf_relse(rtsb_bp); - xfs_buf_relse(bp); + return error; + + /* Re-acquire and write the sb and rtsb to disk. */ + xfs_buf_lock(mp->m_sb_bp); + error = xfs_bwrite(mp->m_sb_bp); + xfs_buf_unlock(mp->m_sb_bp); + if (error) + return error; + + if (update_rtsb && mp->m_rtsb_bp) { + xfs_buf_lock(mp->m_rtsb_bp); + error = xfs_bwrite(mp->m_rtsb_bp); + xfs_buf_unlock(mp->m_rtsb_bp); + } + return error; } From b9b541e70d465a8c9cadf697eec7cb15b6653e7d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 20 Jul 2026 11:36:12 +0200 Subject: [PATCH 0053/1198] xfs: split an assert in xfs_trans_log_buf Split the "irst <= last && last < BBTOB(bp->b_length)" assert into two to make it clear which condition fired. Signed-off-by: Christoph Hellwig Reviewed-by: Carlos Maiolino Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_trans_buf.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c index 1e025848811a..a5d25b703dfc 100644 --- a/fs/xfs/xfs_trans_buf.c +++ b/fs/xfs/xfs_trans_buf.c @@ -521,7 +521,8 @@ xfs_trans_log_buf( { struct xfs_buf_log_item *bip = bp->b_log_item; - ASSERT(first <= last && last < BBTOB(bp->b_length)); + ASSERT(first <= last); + ASSERT(last < BBTOB(bp->b_length)); ASSERT(!(bip->bli_flags & XFS_BLI_ORDERED)); xfs_trans_dirty_buf(tp, bp); From 7fc296b379edc0fef83890097af3c9537fbf4364 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 20 Jul 2026 16:09:21 +0200 Subject: [PATCH 0054/1198] xfs: don't flush and invalidate internal RT device twice in xfs_shutdown_devices Check for an internal RT device to remove a bit of extra work. Fixes: bdc03eb5f98f ("xfs: allow internal RT devices for zoned mode") Signed-off-by: Christoph Hellwig Reviewed-by: Carlos Maiolino Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 4b2eeb7783f7..b24db75eaedc 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -445,7 +445,7 @@ xfs_shutdown_devices( blkdev_issue_flush(mp->m_logdev_targp->bt_bdev); invalidate_bdev(mp->m_logdev_targp->bt_bdev); } - if (mp->m_rtdev_targp) { + if (mp->m_rtdev_targp && mp->m_rtdev_targp != mp->m_ddev_targp) { blkdev_issue_flush(mp->m_rtdev_targp->bt_bdev); invalidate_bdev(mp->m_rtdev_targp->bt_bdev); } From 750a361bfc8a8c8178872f2aecb7507a6fbf41a4 Mon Sep 17 00:00:00 2001 From: Tal Zussman Date: Fri, 7 Aug 2026 06:58:51 -0400 Subject: [PATCH 0055/1198] xfs: remove kmem_to_page() kmem_to_page() has been unused since commit 5ced480d4886 ("xfs: simplify building the bio in xlog_write_iclog"), so remove it. This also removes the last instance of 'struct page' in fs/xfs/. Signed-off-by: Tal Zussman Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_platform.h | 11 ----------- 1 file changed, 11 deletions(-) diff --git a/fs/xfs/xfs_platform.h b/fs/xfs/xfs_platform.h index 59a33c60e0ca..5d542e95fe44 100644 --- a/fs/xfs/xfs_platform.h +++ b/fs/xfs/xfs_platform.h @@ -289,15 +289,4 @@ int xfs_rw_bdev(struct block_device *bdev, sector_t sector, unsigned int count, # define PTR_FMT "%p" #endif -/* - * Helper for IO routines to grab backing pages from allocated kernel memory. - */ -static inline struct page * -kmem_to_page(void *addr) -{ - if (is_vmalloc_addr(addr)) - return vmalloc_to_page(addr); - return virt_to_page(addr); -} - #endif /* _XFS_PLATFORM_H */ From 4e07cd78e159a8c6b028e5dc5f4e5bf06067d969 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 10 Aug 2026 08:38:38 -0700 Subject: [PATCH 0056/1198] xfs: use inode_init_always_gfp with __GFP_NOFAIL in xfs_inode_alloc Just like the inode allocation itself, allocation of the security data inside of inode_init_always(_gfp) must not fail here as we can be inside an already dirty transaction context. Note that we do not have to pass GFP_NOFS explicitly as we are already in a nofs context when in a transaction, as seen by the call to alloc_inode_sb. Also update the comment about this a bit to be more clear. Fixes: bf904248a2ad ("[XFS] Combine the XFS and Linux inodes") Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_icache.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 9d8dd30bd927..a857b8aa255c 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -82,24 +82,20 @@ static inline xa_mark_t ici_tag_to_mark(unsigned int tag) /* * Allocate and initialise an xfs_inode. + * + * This can happen in context of already dirtied transactions, so the memory + * allocations must not fail. */ struct xfs_inode * xfs_inode_alloc( struct xfs_mount *mp, xfs_ino_t ino) { + gfp_t gfp = GFP_KERNEL | __GFP_NOFAIL; struct xfs_inode *ip; - /* - * XXX: If this didn't occur in transactions, we could drop GFP_NOFAIL - * and return NULL here on ENOMEM. - */ - ip = alloc_inode_sb(mp->m_super, xfs_inode_cache, GFP_KERNEL | __GFP_NOFAIL); - - if (inode_init_always(mp->m_super, VFS_I(ip))) { - kmem_cache_free(xfs_inode_cache, ip); - return NULL; - } + ip = alloc_inode_sb(mp->m_super, xfs_inode_cache, gfp); + inode_init_always_gfp(mp->m_super, VFS_I(ip), gfp); VFS_I(ip)->i_ino = ino; /* VFS doesn't initialise i_mode! */ From ae285611891f8d1a691771d14ecb5c9de3319abf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 11 Aug 2026 10:48:37 -0600 Subject: [PATCH 0057/1198] xfs: handle NULL open_zone for merged ioends in xfs_ioend_put_open_zones In theory we could fail multiple ioends before an open zone was assigned to them, and the iomap code could merge them. Check for NULL not only for the main ioend but also all merged ones on ->io_list to handle this case. Fixes: 058dd70c65ab ("xfs: implement buffered writes to zoned RT devices") Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Reviewed-by: Hans Holmberg Reviewed-by: Damien Le Moal Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_aops.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 74a6089abadf..5a444ef04967 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -89,8 +89,10 @@ xfs_ioend_put_open_zones( /* * Put the open zone for all ioends merged into this one (if any). */ - list_for_each_entry(tmp, &ioend->io_list, io_list) - xfs_open_zone_put(tmp->io_private); + list_for_each_entry(tmp, &ioend->io_list, io_list) { + if (tmp->io_private) + xfs_open_zone_put(tmp->io_private); + } /* * The main ioend might not have an open zone if the submission failed From 2d829cc76777a5335269768d7caa750e102f74d2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 11 Aug 2026 10:48:38 -0600 Subject: [PATCH 0058/1198] xfs: fix racy open zone caching When testing on very fast storage devices, I've observed writers using io_uring creating many open zones with just a few kiB written to it, which then don't get used. I tracked this down to multiple io_uring helper threads finding a full zone in i_private, and then going on to select a one, with the final one winning the race and leaving it in i_private. Fix this by dropping full zones from i_private as soon we find them, checking cached for a cached zoned when a single writes needs a new zone, and by keeping an existing cached zone in xfs_set_cached_zone when it still has space available, dropping the newly found/allocated one instead. This uses i_flags_lock as a low-level spinlock for short hold times to avoid interactions with the ilock, which is used for completions. Signed-off-by: Christoph Hellwig Reviewed-by: Hans Holmberg Reviewed-by: Darrick J. Wong Reviewed-by: Damien Le Moal Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_zone_alloc.c | 72 ++++++++++++++++++++++++++++++++--------- 1 file changed, 56 insertions(+), 16 deletions(-) diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c index 7d13fa7ab30a..bdbb60cc5d5b 100644 --- a/fs/xfs/xfs_zone_alloc.c +++ b/fs/xfs/xfs_zone_alloc.c @@ -793,17 +793,35 @@ xfs_get_cached_zone( rcu_read_lock(); oz = VFS_I(ip)->i_private; - if (oz) { - /* - * GC only steals open zones at mount time, so no GC zones - * should end up in the cache. - */ - ASSERT(!oz->oz_is_gc); - if (!atomic_inc_not_zero(&oz->oz_ref)) - oz = NULL; - } - rcu_read_unlock(); + if (!oz) + goto out_unlock; + /* + * GC only steals open zones at mount time, so no GC zones should end up + * in the cache. + */ + ASSERT(!oz->oz_is_gc); + + /* + * Drop the old cached open zone if it is full. + */ + if (oz->oz_allocated == rtg_blocks(oz->oz_rtg)) { + spin_lock(&ip->i_flags_lock); + oz = VFS_I(ip)->i_private; + if (oz && oz->oz_allocated == rtg_blocks(oz->oz_rtg)) { + VFS_I(ip)->i_private = NULL; + spin_unlock(&ip->i_flags_lock); + xfs_open_zone_put(oz); + oz = NULL; + goto out_unlock; + } + spin_unlock(&ip->i_flags_lock); + } + + if (!atomic_inc_not_zero(&oz->oz_ref)) + oz = NULL; +out_unlock: + rcu_read_unlock(); return oz; } @@ -818,18 +836,41 @@ xfs_get_cached_zone( * that were every written to, but significantly simplifies the cached zone * lookup. Because the open_zone is clearly marked as full when all data * in the underlying RTG was written, the caching is always safe. + * + * Called with a reference on @oz held. And returns two references on the + * returned zone: one for the caller and one for pinning the zone in + * inode->i_private. */ -static void +static struct xfs_open_zone * xfs_set_cached_zone( struct xfs_inode *ip, struct xfs_open_zone *oz) { struct xfs_open_zone *old_oz; + /* + * If the open zone cached in the inode still has free space, use that + * instead of the new open zone just selected. This can happen when + * multiple threads race to perform zone selection for an inode. + * io_uring worker threads seem to be good way to trigger this. + * + * We need to grab an extra reference to this open zone as the caller + * owns a reference in addition to the i_private pointer. + */ + spin_lock(&ip->i_flags_lock); + old_oz = VFS_I(ip)->i_private; + if (old_oz && old_oz->oz_allocated < rtg_blocks(old_oz->oz_rtg) && + atomic_inc_not_zero(&old_oz->oz_ref)) { + spin_unlock(&ip->i_flags_lock); + xfs_open_zone_put(oz); + return old_oz; + } + VFS_I(ip)->i_private = oz; atomic_inc(&oz->oz_ref); - old_oz = xchg(&VFS_I(ip)->i_private, oz); + spin_unlock(&ip->i_flags_lock); if (old_oz) xfs_open_zone_put(old_oz); + return oz; } static void @@ -873,14 +914,13 @@ xfs_zone_alloc_and_submit( * the inode is still associated with a zone and use that if so. */ if (!*oz) - *oz = xfs_get_cached_zone(ip); - - if (!*oz) { select_zone: + *oz = xfs_get_cached_zone(ip); + if (!*oz) { *oz = xfs_select_zone(mp, write_hint, pack_tight); if (!*oz) goto out_error; - xfs_set_cached_zone(ip, *oz); + *oz = xfs_set_cached_zone(ip, *oz); } alloc_len = xfs_zone_alloc_blocks(*oz, XFS_B_TO_FSB(mp, ioend->io_size), From 4bc67fc800edcaae8a657e4d2fba12e64e856b9f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 11 Aug 2026 10:48:39 -0600 Subject: [PATCH 0059/1198] xfs: fix zoned write iomap flags assignments Don't overwrite IOMAP_F_DIRTY with IOMAP_F_ANON_WRITE, but ensure both flags are set instead. Note that in practice this is harmless as all zoned writes force a metadata transaction anyway, but incorrectly assigned flags are still a landmine that will cause problems at some point. Fixes: 058dd70c65ab ("xfs: implement buffered writes to zoned RT devices") Fixes: 2e2383405824 ("xfs: implement direct writes to zoned RT devices") Cc: stable@vger.kernel.org # v6.15 Signed-off-by: Christoph Hellwig Reviewed-by: Andrey Albershteyn Reviewed-by: Darrick J. Wong Reviewed-by: Hans Holmberg Reviewed-by: Damien Le Moal Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_aops.c | 3 +-- fs/xfs/xfs_iomap.c | 3 +-- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 5a444ef04967..53b94af92ac5 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -634,11 +634,10 @@ xfs_zoned_map_blocks( xfs_iunlock(ip, XFS_ILOCK_EXCL); wpc->iomap.type = IOMAP_MAPPED; - wpc->iomap.flags = IOMAP_F_DIRTY; wpc->iomap.bdev = mp->m_rtdev_targp->bt_bdev; wpc->iomap.offset = offset; wpc->iomap.length = XFS_FSB_TO_B(mp, count_fsb); - wpc->iomap.flags = IOMAP_F_ANON_WRITE; + wpc->iomap.flags = IOMAP_F_ANON_WRITE | IOMAP_F_DIRTY; trace_xfs_zoned_map_blocks(ip, offset, wpc->iomap.length); return 0; diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 71c45be8c652..d8c3c2be6760 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1084,11 +1084,10 @@ xfs_zoned_direct_write_iomap_begin( } iomap->type = IOMAP_MAPPED; - iomap->flags = IOMAP_F_DIRTY; iomap->bdev = ip->i_mount->m_rtdev_targp->bt_bdev; iomap->offset = offset; iomap->length = length; - iomap->flags = IOMAP_F_ANON_WRITE; + iomap->flags = IOMAP_F_ANON_WRITE | IOMAP_F_DIRTY; return 0; } From 0510346e8e308d2e2cb057ea7b408758b5d6f6cd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 11 Aug 2026 10:48:40 -0600 Subject: [PATCH 0060/1198] xfs: factor out a xfs_iomap_set_anon_write helper De-duplicate the iomap setup for zoned writes. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Reviewed-by: Hans Holmberg Reviewed-by: Damien Le Moal Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_aops.c | 8 ++------ fs/xfs/xfs_iomap.c | 6 +----- fs/xfs/xfs_iomap.h | 14 ++++++++++++++ 3 files changed, 17 insertions(+), 11 deletions(-) diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 53b94af92ac5..1dc51235982c 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -633,12 +633,8 @@ xfs_zoned_map_blocks( XFS_BMAPI_REMAP); xfs_iunlock(ip, XFS_ILOCK_EXCL); - wpc->iomap.type = IOMAP_MAPPED; - wpc->iomap.bdev = mp->m_rtdev_targp->bt_bdev; - wpc->iomap.offset = offset; - wpc->iomap.length = XFS_FSB_TO_B(mp, count_fsb); - wpc->iomap.flags = IOMAP_F_ANON_WRITE | IOMAP_F_DIRTY; - + xfs_iomap_set_anon_write(ip, &wpc->iomap, offset, + XFS_FSB_TO_B(mp, count_fsb)); trace_xfs_zoned_map_blocks(ip, offset, wpc->iomap.length); return 0; } diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index d8c3c2be6760..7c6238fed61e 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1083,11 +1083,7 @@ xfs_zoned_direct_write_iomap_begin( return error; } - iomap->type = IOMAP_MAPPED; - iomap->bdev = ip->i_mount->m_rtdev_targp->bt_bdev; - iomap->offset = offset; - iomap->length = length; - iomap->flags = IOMAP_F_ANON_WRITE | IOMAP_F_DIRTY; + xfs_iomap_set_anon_write(ip, iomap, offset, length); return 0; } diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index cffcec532ea6..c906c62d46f3 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -29,6 +29,20 @@ int xfs_zero_range(struct xfs_inode *ip, loff_t pos, loff_t len, int xfs_truncate_page(struct xfs_inode *ip, loff_t pos, struct xfs_zone_alloc_ctx *ac, bool *did_zero); +static inline void +xfs_iomap_set_anon_write( + struct xfs_inode *ip, + struct iomap *iomap, + loff_t offset, + loff_t length) +{ + iomap->type = IOMAP_MAPPED; + iomap->bdev = ip->i_mount->m_rtdev_targp->bt_bdev; + iomap->offset = offset; + iomap->length = length; + iomap->flags = IOMAP_F_ANON_WRITE | IOMAP_F_DIRTY; +} + static inline xfs_filblks_t xfs_aligned_fsb_count( xfs_fileoff_t offset_fsb, From 6b855256eb9e652caf8b14eb1f69b6eb00a9d9d1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 11 Aug 2026 10:48:41 -0600 Subject: [PATCH 0061/1198] xfs: split ioend handling into a separate source file The ioend handling used to be only for buffered writeback, but has been extended to direct I/O and reads. Split it into a new source file. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Reviewed-by: Hans Holmberg Reviewed-by: Damien Le Moal Signed-off-by: Carlos Maiolino --- fs/xfs/Makefile | 1 + fs/xfs/xfs_aops.c | 181 +------------------------------------------- fs/xfs/xfs_aops.h | 1 - fs/xfs/xfs_file.c | 2 +- fs/xfs/xfs_ioend.c | 184 +++++++++++++++++++++++++++++++++++++++++++++ fs/xfs/xfs_ioend.h | 16 ++++ 6 files changed, 203 insertions(+), 182 deletions(-) create mode 100644 fs/xfs/xfs_ioend.c create mode 100644 fs/xfs/xfs_ioend.h diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile index 9f7133e02576..399a207f2d0e 100644 --- a/fs/xfs/Makefile +++ b/fs/xfs/Makefile @@ -91,6 +91,7 @@ xfs-y += xfs_aops.o \ xfs_healthmon.o \ xfs_icache.o \ xfs_ioctl.o \ + xfs_ioend.o \ xfs_iomap.o \ xfs_iops.o \ xfs_inode.o \ diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 1dc51235982c..8b6119776fb3 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -20,6 +20,7 @@ #include "xfs_errortag.h" #include "xfs_error.h" #include "xfs_icache.h" +#include "xfs_ioend.h" #include "xfs_zone_alloc.h" #include "xfs_rtgroup.h" #include @@ -36,15 +37,6 @@ XFS_WPC(struct iomap_writepage_ctx *ctx) return container_of(ctx, struct xfs_writepage_ctx, ctx); } -/* - * Fast and loose check if this write could update the on-disk inode size. - */ -static inline bool xfs_ioend_is_append(struct iomap_ioend *ioend) -{ - return ioend->io_offset + ioend->io_size > - XFS_I(ioend->io_inode)->i_disk_size; -} - /* * Update on-disk file size now that data has been written to disk. */ @@ -80,177 +72,6 @@ xfs_setfilesize( return xfs_trans_commit(tp); } -static void -xfs_ioend_put_open_zones( - struct iomap_ioend *ioend) -{ - struct iomap_ioend *tmp; - - /* - * Put the open zone for all ioends merged into this one (if any). - */ - list_for_each_entry(tmp, &ioend->io_list, io_list) { - if (tmp->io_private) - xfs_open_zone_put(tmp->io_private); - } - - /* - * The main ioend might not have an open zone if the submission failed - * before xfs_zone_alloc_and_submit got called. - */ - if (ioend->io_private) - xfs_open_zone_put(ioend->io_private); -} - -/* - * IO write completion. - */ -STATIC void -xfs_end_ioend_write( - struct iomap_ioend *ioend) -{ - struct xfs_inode *ip = XFS_I(ioend->io_inode); - struct xfs_mount *mp = ip->i_mount; - bool is_zoned = xfs_is_zoned_inode(ip); - xfs_off_t offset = ioend->io_offset; - size_t size = ioend->io_size; - unsigned int nofs_flag; - int error; - - /* - * We can allocate memory here while doing writeback on behalf of - * memory reclaim. To avoid memory allocation deadlocks set the - * task-wide nofs context for the following operations. - */ - nofs_flag = memalloc_nofs_save(); - - /* - * Just clean up the in-memory structures if the fs has been shut down. - */ - if (xfs_is_shutdown(mp)) { - error = -EIO; - goto done; - } - - /* - * Clean up all COW blocks and underlying data fork delalloc blocks on - * I/O error. The delalloc punch is required because this ioend was - * mapped to blocks in the COW fork and the associated pages are no - * longer dirty. If we don't remove delalloc blocks here, they become - * stale and can corrupt free space accounting on unmount. - */ - error = blk_status_to_errno(ioend->io_bio.bi_status); - if (unlikely(error)) { - /* - * Zoned writes update the in-core open zone accounting before - * I/O submission. A failed write leaves that state - * inconsistent, so shut down the filesystem instead of letting - * later writers wait forever for open zone space to become - * available. - */ - if (is_zoned) { - xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR); - goto done; - } - if (ioend->io_flags & IOMAP_IOEND_SHARED) { - ASSERT(!is_zoned); - xfs_reflink_cancel_cow_range(ip, offset, size, true); - xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, offset, - offset + size, NULL); - } - goto done; - } - - /* - * Success: commit the COW or unwritten blocks if needed. - */ - if (is_zoned) - error = xfs_zoned_end_io(ip, offset, size, ioend->io_sector, - ioend->io_private, NULLFSBLOCK); - else if (ioend->io_flags & IOMAP_IOEND_SHARED) - error = xfs_reflink_end_cow(ip, offset, size); - else if (ioend->io_flags & IOMAP_IOEND_UNWRITTEN) - error = xfs_iomap_write_unwritten(ip, offset, size, false); - - if (!error && - !(ioend->io_flags & IOMAP_IOEND_DIRECT) && - xfs_ioend_is_append(ioend)) - error = xfs_setfilesize(ip, offset, size); -done: - if (is_zoned) - xfs_ioend_put_open_zones(ioend); - iomap_finish_ioends(ioend, error); - memalloc_nofs_restore(nofs_flag); -} - -/* - * Finish all pending IO completions that require transactional modifications. - * - * We try to merge physical and logically contiguous ioends before completion to - * minimise the number of transactions we need to perform during IO completion. - * Both unwritten extent conversion and COW remapping need to iterate and modify - * one physical extent at a time, so we gain nothing by merging physically - * discontiguous extents here. - * - * The ioend chain length that we can be processing here is largely unbound in - * length and we may have to perform significant amounts of work on each ioend - * to complete it. Hence we have to be careful about holding the CPU for too - * long in this loop. - */ -void -xfs_end_io( - struct work_struct *work) -{ - struct xfs_inode *ip = - container_of(work, struct xfs_inode, i_ioend_work); - struct iomap_ioend *ioend; - struct list_head tmp; - unsigned long flags; - - spin_lock_irqsave(&ip->i_ioend_lock, flags); - list_replace_init(&ip->i_ioend_list, &tmp); - spin_unlock_irqrestore(&ip->i_ioend_lock, flags); - - iomap_sort_ioends(&tmp); - while ((ioend = list_first_entry_or_null(&tmp, struct iomap_ioend, - io_list))) { - list_del_init(&ioend->io_list); - iomap_ioend_try_merge(ioend, &tmp); - if (bio_op(&ioend->io_bio) == REQ_OP_READ) - iomap_finish_ioends(ioend, - blk_status_to_errno(ioend->io_bio.bi_status)); - else - xfs_end_ioend_write(ioend); - cond_resched(); - } -} - -void -xfs_end_bio( - struct bio *bio) -{ - struct iomap_ioend *ioend = iomap_ioend_from_bio(bio); - struct xfs_inode *ip = XFS_I(ioend->io_inode); - struct xfs_mount *mp = ip->i_mount; - unsigned long flags; - - /* - * For Appends record the actually written block number and set the - * boundary flag if needed. - */ - if (IS_ENABLED(CONFIG_XFS_RT) && bio_is_zone_append(bio)) { - ioend->io_sector = bio->bi_iter.bi_sector; - xfs_mark_rtg_boundary(ioend); - } - - spin_lock_irqsave(&ip->i_ioend_lock, flags); - if (list_empty(&ip->i_ioend_list)) - WARN_ON_ONCE(!queue_work(mp->m_unwritten_workqueue, - &ip->i_ioend_work)); - list_add_tail(&ioend->io_list, &ip->i_ioend_list); - spin_unlock_irqrestore(&ip->i_ioend_lock, flags); -} - /* * We cannot cancel the ioend directly on error. We may have already set other * pages under writeback and hence we have to run I/O completion to mark the diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h index 5a7a0f1a0b49..d5ae5c9d4c26 100644 --- a/fs/xfs/xfs_aops.h +++ b/fs/xfs/xfs_aops.h @@ -10,6 +10,5 @@ extern const struct address_space_operations xfs_address_space_operations; extern const struct address_space_operations xfs_dax_aops; int xfs_setfilesize(struct xfs_inode *ip, xfs_off_t offset, size_t size); -void xfs_end_bio(struct bio *bio); #endif /* __XFS_AOPS_H__ */ diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 7bff07e31cbd..426a67b813a7 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -25,7 +25,7 @@ #include "xfs_iomap.h" #include "xfs_reflink.h" #include "xfs_file.h" -#include "xfs_aops.h" +#include "xfs_ioend.h" #include "xfs_zone_alloc.h" #include "xfs_error.h" #include "xfs_errortag.h" diff --git a/fs/xfs/xfs_ioend.c b/fs/xfs/xfs_ioend.c new file mode 100644 index 000000000000..40695d18dac0 --- /dev/null +++ b/fs/xfs/xfs_ioend.c @@ -0,0 +1,184 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2016-2025 Christoph Hellwig. + * All Rights Reserved. + */ +#include "xfs_platform.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_inode.h" +#include "xfs_iomap.h" +#include "xfs_trace.h" +#include "xfs_bmap_util.h" +#include "xfs_reflink.h" +#include "xfs_zone_alloc.h" +#include "xfs_ioend.h" + +static void +xfs_ioend_put_open_zones( + struct iomap_ioend *ioend) +{ + struct iomap_ioend *tmp; + + /* + * Put the open zone for all ioends merged into this one (if any). + */ + list_for_each_entry(tmp, &ioend->io_list, io_list) + xfs_open_zone_put(tmp->io_private); + + /* + * The main ioend might not have an open zone if the submission failed + * before xfs_zone_alloc_and_submit got called. + */ + if (ioend->io_private) + xfs_open_zone_put(ioend->io_private); +} + +static void +xfs_end_ioend_write( + struct iomap_ioend *ioend) +{ + struct xfs_inode *ip = XFS_I(ioend->io_inode); + struct xfs_mount *mp = ip->i_mount; + bool is_zoned = xfs_is_zoned_inode(ip); + xfs_off_t offset = ioend->io_offset; + size_t size = ioend->io_size; + unsigned int nofs_flag; + int error; + + /* + * We can allocate memory here while doing writeback on behalf of + * memory reclaim. To avoid memory allocation deadlocks set the + * task-wide nofs context for the following operations. + */ + nofs_flag = memalloc_nofs_save(); + + /* + * Just clean up the in-memory structures if the fs has been shut down. + */ + if (xfs_is_shutdown(mp)) { + error = -EIO; + goto done; + } + + /* + * Clean up all COW blocks and underlying data fork delalloc blocks on + * I/O error. The delalloc punch is required because this ioend was + * mapped to blocks in the COW fork and the associated pages are no + * longer dirty. If we don't remove delalloc blocks here, they become + * stale and can corrupt free space accounting on unmount. + */ + error = blk_status_to_errno(ioend->io_bio.bi_status); + if (unlikely(error)) { + /* + * Zoned writes update the in-core open zone accounting before + * I/O submission. A failed write leaves that state + * inconsistent, so shut down the filesystem instead of letting + * later writers wait forever for open zone space to become + * available. + */ + if (is_zoned) { + xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR); + goto done; + } + if (ioend->io_flags & IOMAP_IOEND_SHARED) { + ASSERT(!is_zoned); + xfs_reflink_cancel_cow_range(ip, offset, size, true); + xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, offset, + offset + size, NULL); + } + goto done; + } + + /* + * Success: commit the COW or unwritten blocks if needed. + */ + if (is_zoned) + error = xfs_zoned_end_io(ip, offset, size, ioend->io_sector, + ioend->io_private, NULLFSBLOCK); + else if (ioend->io_flags & IOMAP_IOEND_SHARED) + error = xfs_reflink_end_cow(ip, offset, size); + else if (ioend->io_flags & IOMAP_IOEND_UNWRITTEN) + error = xfs_iomap_write_unwritten(ip, offset, size, false); + + if (!error && + !(ioend->io_flags & IOMAP_IOEND_DIRECT) && + xfs_ioend_is_append(ioend)) + error = xfs_setfilesize(ip, offset, size); +done: + if (is_zoned) + xfs_ioend_put_open_zones(ioend); + iomap_finish_ioends(ioend, error); + memalloc_nofs_restore(nofs_flag); +} + +/* + * Finish all pending IO completions that require transactional modifications. + * + * We try to merge physical and logically contiguous ioends before completion to + * minimise the number of transactions we need to perform during IO completion. + * Both unwritten extent conversion and COW remapping need to iterate and modify + * one physical extent at a time, so we gain nothing by merging physically + * discontiguous extents here. + * + * The ioend chain length that we can be processing here is largely unbound in + * length and we may have to perform significant amounts of work on each ioend + * to complete it. Hence we have to be careful about holding the CPU for too + * long in this loop. + */ +void +xfs_end_io( + struct work_struct *work) +{ + struct xfs_inode *ip = + container_of(work, struct xfs_inode, i_ioend_work); + struct iomap_ioend *ioend; + struct list_head tmp; + unsigned long flags; + + spin_lock_irqsave(&ip->i_ioend_lock, flags); + list_replace_init(&ip->i_ioend_list, &tmp); + spin_unlock_irqrestore(&ip->i_ioend_lock, flags); + + iomap_sort_ioends(&tmp); + while ((ioend = list_first_entry_or_null(&tmp, struct iomap_ioend, + io_list))) { + list_del_init(&ioend->io_list); + iomap_ioend_try_merge(ioend, &tmp); + if (bio_op(&ioend->io_bio) == REQ_OP_READ) + iomap_finish_ioends(ioend, + blk_status_to_errno(ioend->io_bio.bi_status)); + else + xfs_end_ioend_write(ioend); + cond_resched(); + } +} + +void +xfs_end_bio( + struct bio *bio) +{ + struct iomap_ioend *ioend = iomap_ioend_from_bio(bio); + struct xfs_inode *ip = XFS_I(ioend->io_inode); + struct xfs_mount *mp = ip->i_mount; + unsigned long flags; + + /* + * For Appends record the actually written block number and set the + * boundary flag if needed. + */ + if (IS_ENABLED(CONFIG_XFS_RT) && bio_is_zone_append(bio)) { + ioend->io_sector = bio->bi_iter.bi_sector; + xfs_mark_rtg_boundary(ioend); + } + + spin_lock_irqsave(&ip->i_ioend_lock, flags); + if (list_empty(&ip->i_ioend_list)) + WARN_ON_ONCE(!queue_work(mp->m_unwritten_workqueue, + &ip->i_ioend_work)); + list_add_tail(&ioend->io_list, &ip->i_ioend_list); + spin_unlock_irqrestore(&ip->i_ioend_lock, flags); +} diff --git a/fs/xfs/xfs_ioend.h b/fs/xfs/xfs_ioend.h new file mode 100644 index 000000000000..525865767fca --- /dev/null +++ b/fs/xfs/xfs_ioend.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __XFS_IOEND_H +#define __XFS_IOEND_H + +/* + * Fast and loose check if this write could update the on-disk inode size. + */ +static inline bool xfs_ioend_is_append(struct iomap_ioend *ioend) +{ + return ioend->io_offset + ioend->io_size > + XFS_I(ioend->io_inode)->i_disk_size; +} + +void xfs_end_bio(struct bio *bio); + +#endif /* __XFS_IOEND_H */ From 885435535bb1d07746916d4c8832f95767bf2d7e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 13 Aug 2026 16:56:12 +0200 Subject: [PATCH 0062/1198] xfs: restore bi_bdev in xfs_zone_gc_write_chunk xfs_zone_gc_write_chunk relies on bi_bdev to still be valid, which is not true when XFS is used on top of a stacked block device. This can lead to misdirected GC writes, writing of plain text when using dm-crypt, or miscalculated I/O limits in xfs_zone_gc_split_write. Fix this by reassigning bi_bdev. Fixes: 080d01c41d44 ("xfs: implement zoned garbage collection") Signed-off-by: Christoph Hellwig Reviewed-by: Damien Le Moal Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_zone_gc.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/xfs/xfs_zone_gc.c b/fs/xfs/xfs_zone_gc.c index d0b85179a3d2..5fdcf98a2133 100644 --- a/fs/xfs/xfs_zone_gc.c +++ b/fs/xfs/xfs_zone_gc.c @@ -869,6 +869,11 @@ xfs_zone_gc_write_chunk( WRITE_ONCE(chunk->state, XFS_GC_BIO_NEW); list_move_tail(&chunk->entry, &data->writing); + /* + * If we run on top of stacked block device, the read I/O might have + * reset bi_bdev, restore it to the one we want. + */ + bio_set_dev(&chunk->bio, mp->m_rtdev_targp->bt_bdev); bio_reuse(&chunk->bio, REQ_OP_WRITE); while ((split_chunk = xfs_zone_gc_split_write(data, chunk))) xfs_zone_gc_submit_write(data, split_chunk); From e2f62a9744ebad3bcb6347a648e615026e9efeff Mon Sep 17 00:00:00 2001 From: Carlos Maiolino Date: Tue, 4 Aug 2026 11:45:51 +0200 Subject: [PATCH 0063/1198] xfs: fix capability check in xfs An user reported a bug where he managed to evade group's quota by changing a file's gid to a different group id the same user belonged to, even though quotas were enforced on both gids and the file's size was big enough to exceed the quota's hardlimit. Commit eba0549bc7d1 replaced a capable() call by a has_capability_noaudit() to prevent unnecessary selinux audit messages. Turns out that both calls have slightly different semantics even though their documentation seems similar. Where in a nutshell: capable() - Tests the task's effective credentials has_ns_capability_noaudit() - Tests the task's real credentials This most of the time has no practical difference but in some cases like changing attrs (specifically group id in this case) through a NFS client this will allow the quota code to use XFS_QMOPT_FORCE_RES, effectively bypassing quota accounting checks. Using instead ns_capable_noaudit() should fix this issue and prevent selinux audit messages. This also fix the remaining calls to has_capability_noaudit() Fixes: eba0549bc7d1 ("xfs: don't generate selinux audit messages for capability testing") Cc: stable@vger.kernel.org # v5.18 Reported-by: Dr. Thomas Orgis Signed-off-by: Carlos Maiolino Reviewed-by: Darrick J. Wong Reviewed-by: Serge Hallyn Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_fsmap.c | 2 +- fs/xfs/xfs_ioctl.c | 2 +- fs/xfs/xfs_iops.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c index b6a3bc9f143c..7c79fbe0a74c 100644 --- a/fs/xfs/xfs_fsmap.c +++ b/fs/xfs/xfs_fsmap.c @@ -1175,7 +1175,7 @@ xfs_getfsmap( return -EINVAL; use_rmap = xfs_has_rmapbt(mp) && - has_capability_noaudit(current, CAP_SYS_ADMIN); + ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN); head->fmh_entries = 0; /* Set up our device handlers. */ diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 1b53701bebea..1a8af827dde1 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -647,7 +647,7 @@ xfs_ioctl_setattr_get_trans( goto out_error; error = xfs_trans_alloc_ichange(ip, NULL, NULL, pdqp, - has_capability_noaudit(current, CAP_FOWNER), &tp); + ns_capable_noaudit(&init_user_ns, CAP_FOWNER), &tp); if (error) goto out_error; diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 4a3299abf774..36a22d4a8cc4 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -834,7 +834,7 @@ xfs_setattr_nonsize( } error = xfs_trans_alloc_ichange(ip, udqp, gdqp, NULL, - has_capability_noaudit(current, CAP_FOWNER), &tp); + ns_capable_noaudit(&init_user_ns, CAP_FOWNER), &tp); if (error) goto out_dqrele; From 1b91724d0bdc470ed8f353d1cc8d3e4123b51ed5 Mon Sep 17 00:00:00 2001 From: Carlos Maiolino Date: Tue, 4 Aug 2026 11:45:52 +0200 Subject: [PATCH 0064/1198] capability: Add new capable_noaudit In some situations (quota enforcement bypass in this case) we'd like to check for a specific capability without triggering spurious audit messages from security modules like selinux. Add a new helper so we don't need to use ns_capable_noaudit() directly. Signed-off-by: Carlos Maiolino Reviewed-by: Christoph Hellwig Reviewed-by: Serge Hallyn Signed-off-by: Carlos Maiolino --- include/linux/capability.h | 5 +++++ kernel/capability.c | 18 ++++++++++++++++++ 2 files changed, 23 insertions(+) diff --git a/include/linux/capability.h b/include/linux/capability.h index 37db92b3d6f8..f8532d92fcad 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -145,6 +145,7 @@ extern bool has_capability_noaudit(struct task_struct *t, int cap); extern bool has_ns_capability_noaudit(struct task_struct *t, struct user_namespace *ns, int cap); extern bool capable(int cap); +bool capable_noaudit(int cap); extern bool ns_capable(struct user_namespace *ns, int cap); extern bool ns_capable_noaudit(struct user_namespace *ns, int cap); extern bool ns_capable_setid(struct user_namespace *ns, int cap); @@ -167,6 +168,10 @@ static inline bool capable(int cap) { return true; } +static inline bool capable_noaudit(int cap) +{ + return true; +} static inline bool ns_capable(struct user_namespace *ns, int cap) { return true; diff --git a/kernel/capability.c b/kernel/capability.c index 829f49ae07b9..f4a7f1963c9d 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -416,6 +416,24 @@ bool capable(int cap) return ns_capable(&init_user_ns, cap); } EXPORT_SYMBOL(capable); + +/** + * capable_noaudit - Determine if the current task has a superior + * capability in effect by checking the process's effective + * capabilities (unaudited). + * @cap: The capability to be tested for + * + * This is the same as capable(), except it uses CAP_OPT_NOAUDIT as to prevent + * issuing spurious audit messages. + * + * This sets PF_SUPERPRIV on the task if the capability is available on the + * assumption that it's about to be used. + */ +bool capable_noaudit(int cap) +{ + return ns_capable_noaudit(&init_user_ns, cap); +} +EXPORT_SYMBOL(capable_noaudit); #endif /* CONFIG_MULTIUSER */ /** From 4642259374fc9eb99af4cf8b2d54d54ccb0de08e Mon Sep 17 00:00:00 2001 From: Carlos Maiolino Date: Tue, 4 Aug 2026 11:45:53 +0200 Subject: [PATCH 0065/1198] quota: Don't issue audit messages on quota enforcing Calling capable() to determine if we can bypass quota enforcement or not can trigger spurious audit messages. We don't really require it here so just use the capable_noaudit() version. Signed-off-by: Carlos Maiolino Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Acked-by: Jan Kara Signed-off-by: Carlos Maiolino --- fs/quota/dquot.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 204afc5e984b..1c78c695d0dd 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -1240,7 +1240,7 @@ static int ignore_hardlimit(struct dquot *dquot) { struct mem_dqinfo *info = &sb_dqopt(dquot->dq_sb)->info[dquot->dq_id.type]; - return capable(CAP_SYS_RESOURCE) && + return capable_noaudit(CAP_SYS_RESOURCE) && (info->dqi_format->qf_fmt_id != QFMT_VFS_OLD || !(info->dqi_flags & DQF_ROOT_SQUASH)); } From be9c45bdb19461889b16c91c185a284d665ea72d Mon Sep 17 00:00:00 2001 From: Carlos Maiolino Date: Tue, 4 Aug 2026 11:45:54 +0200 Subject: [PATCH 0066/1198] xfs: replace ns_capable_noaudit Now that capable_noaudit() is available, we don't need to keep using ns_capable_noaudit() and specifying the usernamespace every single time. Signed-off-by: Carlos Maiolino Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_fsmap.c | 3 +-- fs/xfs/xfs_ioctl.c | 2 +- fs/xfs/xfs_iops.c | 2 +- 3 files changed, 3 insertions(+), 4 deletions(-) diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c index 7c79fbe0a74c..041bb2105ec6 100644 --- a/fs/xfs/xfs_fsmap.c +++ b/fs/xfs/xfs_fsmap.c @@ -1174,8 +1174,7 @@ xfs_getfsmap( if (!xfs_getfsmap_check_keys(&head->fmh_keys[0], &head->fmh_keys[1])) return -EINVAL; - use_rmap = xfs_has_rmapbt(mp) && - ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN); + use_rmap = xfs_has_rmapbt(mp) && capable_noaudit(CAP_SYS_ADMIN); head->fmh_entries = 0; /* Set up our device handlers. */ diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 1a8af827dde1..96ca3e480cb9 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -647,7 +647,7 @@ xfs_ioctl_setattr_get_trans( goto out_error; error = xfs_trans_alloc_ichange(ip, NULL, NULL, pdqp, - ns_capable_noaudit(&init_user_ns, CAP_FOWNER), &tp); + capable_noaudit(CAP_FOWNER), &tp); if (error) goto out_error; diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 36a22d4a8cc4..d1306e723899 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -834,7 +834,7 @@ xfs_setattr_nonsize( } error = xfs_trans_alloc_ichange(ip, udqp, gdqp, NULL, - ns_capable_noaudit(&init_user_ns, CAP_FOWNER), &tp); + capable_noaudit(CAP_FOWNER), &tp); if (error) goto out_dqrele; From 412f89fb3988a344175899776c8bc7073524ad84 Mon Sep 17 00:00:00 2001 From: Carlos Maiolino Date: Tue, 4 Aug 2026 11:45:55 +0200 Subject: [PATCH 0067/1198] capability: unexport has_capability_noaudit This has been originally exported to be used in xfs. Giving we are not using it anymore, unexport for consistency. Signed-off-by: Carlos Maiolino Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Reviewed-by: Serge Hallyn Signed-off-by: Carlos Maiolino --- kernel/capability.c | 1 - 1 file changed, 1 deletion(-) diff --git a/kernel/capability.c b/kernel/capability.c index f4a7f1963c9d..90e6ab62f6db 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -326,7 +326,6 @@ bool has_capability_noaudit(struct task_struct *t, int cap) { return has_ns_capability_noaudit(t, &init_user_ns, cap); } -EXPORT_SYMBOL(has_capability_noaudit); static bool ns_capable_common(struct user_namespace *ns, int cap, From 0ecd56573c1f272c72298154a3854380876dbb7c Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 4 Aug 2026 12:41:13 +0200 Subject: [PATCH 0068/1198] ext4: Avoid entering writeback paths during fastcommit replay Fastcommit replay effectively happens in nojournal mode. This results in ext4_mark_iloc_dirty() setting I_METADATA_WRITEBACK flag and as a result we end up entering filesystem writeback functions. However during fastcommit replay s_writepages_rwsem isn't initialized yet and hence we crash. Fix the problem by avoiding setting I_METADATA_WRITEBACK during fastcommit replay. Journal replay flushes the whole block device after replay anyway so all metadata is properly persisted and replay is faster this way as a bonus. Fixes: c26339e1df33 ("ext4: Fix data integrity writeout issues in nojournal mode") Reported-by: Venkat Rao Bagalkote Reported-by: Ojaswin Mujoo Signed-off-by: Jan Kara Link: https://patch.msgid.link/20260804104112.93202-2-jack@suse.cz Tested-by: Venkat Rao Bagalkote Reviewed-by: Ojaswin Mujoo Signed-off-by: Christian Brauner (Amutable) --- fs/ext4/inode.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index bd4b778df9eb..26f0f9714f03 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -6456,9 +6456,10 @@ int ext4_chunk_trans_blocks(struct inode *inode, int nrblocks) int ext4_mark_iloc_dirty(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc) { + struct super_block *sb = inode->i_sb; int err = 0; - err = ext4_emergency_state(inode->i_sb); + err = ext4_emergency_state(sb); if (unlikely(err)) { put_bh(iloc->bh); return err; @@ -6473,9 +6474,13 @@ int ext4_mark_iloc_dirty(handle_t *handle, put_bh(iloc->bh); /* * Mark that there's metadata writeout pending for the inode so that it - * gets properly flushed on fsync(2) and similar. + * gets properly flushed on fsync(2) and similar. We don't bother for + * fastcommit replay as that flushes the whole bdev afterwards anyway. + * It is faster this way and we avoid entering fs writeback paths which + * aren't fully initialized yet. */ - if (!EXT4_SB(inode->i_sb)->s_journal) { + if (!ext4_handle_valid(handle) && + !(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)) { /* * Inode didn't need to go through dirtying, make sure it is * attached to wb so that writeback can handle it. From 82e9343260dfc6dda6349f285d9a5eac3e0738d7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=A9my=20Jean?= Date: Fri, 14 Aug 2026 10:20:05 +0000 Subject: [PATCH 0069/1198] nsfs: keep namespace tree fields stable until after RCU grace period MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit struct ns_common overlays struct ns_tree with the rcu_head used by kfree_rcu(). That lets the deferred-free machinery overwrite ns_id and __ns_ref_active as soon as a namespace is queued for freeing, even though nsfs tree walkers may still read those fields under RCU after ns_tree_remove(). KASAN reports slab UAF. Keep the tree state and deferred-free callback storage separate. Namespace tree readers can then continue to validate and take references until the grace period has elapsed. Signed-off-by: Jérémy Jean Link: https://patch.msgid.link/20260814102005.1939777-1-Jeremy.Jean@oss.cyber.gouv.fr Signed-off-by: Christian Brauner (Amutable) --- include/linux/ns/ns_common_types.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/include/linux/ns/ns_common_types.h b/include/linux/ns/ns_common_types.h index ea45c54e4435..6ed6b497831c 100644 --- a/include/linux/ns/ns_common_types.h +++ b/include/linux/ns/ns_common_types.h @@ -116,10 +116,8 @@ struct ns_common { struct dentry *stashed; const struct proc_ns_operations *ops; unsigned int inum; - union { - struct ns_tree; - struct rcu_head ns_rcu; - }; + struct ns_tree; + struct rcu_head ns_rcu; }; #define to_ns_common(__ns) \ From 445fcd33c501be4be41806715f5b7ec80200f9f7 Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Fri, 21 Aug 2026 11:29:51 +0200 Subject: [PATCH 0070/1198] HID: hyperv: fix build breakage with certain configs If CONFIG_HID_HYPERV is built-in (=y) while CONFIG_KUNIT is built as a module (=m), the linker fails to resolve kunit_mem_assert_format when creating vmlinux. Fix the dependencies in Kconfig. Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202608190536.d9qCkWWc-lkp@intel.com/ Fixes: 83df7b5fa6735b5084ecd2 ("HID: hyperv: add KUnit coverage for device info bounds") Acked-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- drivers/hid/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig index aa7fa11a0197..a81bf51cbcf1 100644 --- a/drivers/hid/Kconfig +++ b/drivers/hid/Kconfig @@ -1253,7 +1253,7 @@ config HID_HYPERV_MOUSE config HID_HYPERV_MOUSE_KUNIT_TEST bool "KUnit tests for Hyper-V mouse driver" if !KUNIT_ALL_TESTS - depends on KUNIT && HID_HYPERV_MOUSE + depends on KUNIT && (HID_HYPERV_MOUSE = KUNIT || KUNIT = y) default KUNIT_ALL_TESTS help Builds unit tests for the Hyper-V synthetic HID driver. From d0ad81b2b5feea2e8b08a529c0e0d1fbaca98333 Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Fri, 21 Aug 2026 15:39:15 +0200 Subject: [PATCH 0071/1198] HID: hyperv: make pointer arithmetics understandable for FORTIFY_SOURCE MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 83df7b5fa6735b5084ecd2 ("HID: hyperv: add KUnit coverage for device info bounds") introduced this piece of code report = ((u8 *)&info->hid_descriptor) + info->hid_descriptor.bLength; memset(report, 0x42, 4); to populate the report, making use of the fact that the report &info->hid_descriptor points to a struct hid_descriptor (which is a fixed-size struct). GCC's FORTIFY_SOURCE infer the object size from that specific struct field rather than the outer dynamically allocated info buffer. As a result, writing past sizeof(struct hid_descriptor) triggers the __write_overflow_field warning. Calculate the pointer offset using info directly, so the compiler evaluates the memory bounds against the allocated flexible layout of struct synthhid_device_info instead of the nested struct. Fixes: 83df7b5fa6735b5084ecd2 ("HID: hyperv: add KUnit coverage for device info bounds") Reported-by: Jürgen Groß Tested-by: Jürgen Groß Acked-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- drivers/hid/hid-hyperv.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/hid/hid-hyperv.c b/drivers/hid/hid-hyperv.c index 6579bd19da13..cfc061dbdd24 100644 --- a/drivers/hid/hid-hyperv.c +++ b/drivers/hid/hid-hyperv.c @@ -687,7 +687,7 @@ static void mousevsc_device_info_valid_descriptor(struct kunit *test) info->hid_descriptor.bLength = sizeof(struct hid_descriptor); info->hid_descriptor.rpt_desc.wDescriptorLength = cpu_to_le16(4); - report = ((u8 *)&info->hid_descriptor) + info->hid_descriptor.bLength; + report = (u8 *)(info + 1); memset(report, 0x42, 4); mousevsc_on_receive_device_info(input_dev, info, sizeof(*info) + 4); @@ -713,7 +713,7 @@ static void mousevsc_device_info_report_desc_oob(struct kunit *test) info->hid_descriptor.bLength = sizeof(struct hid_descriptor); info->hid_descriptor.rpt_desc.wDescriptorLength = cpu_to_le16(64); - report = ((u8 *)&info->hid_descriptor) + info->hid_descriptor.bLength; + report = (u8 *)(info + 1); memset(report, 0x42, 8); mousevsc_on_receive_device_info(input_dev, info, sizeof(*info) + 8); From ed54bf564ac52699cf4def3d0c2125d493e756f9 Mon Sep 17 00:00:00 2001 From: Hui Su Date: Fri, 14 Aug 2026 00:09:00 +0800 Subject: [PATCH 0072/1198] bpf: Fix BPF_F_CPU validation for sparse CPU IDs BPF_F_CPU stores the target CPU ID in the upper 32 bits of the map operation flags. bpf_map_check_op_flags() currently compares that ID with num_possible_cpus(), which is the number of possible CPUs rather than a bound on CPU IDs. On an arm64 QEMU guest with a CPU device-tree hole, the possible CPU mask was 0,2-3. A userspace program using raw bpf() syscalls creates a BPF_MAP_TYPE_PERCPU_ARRAY and performs update and lookup operations for each CPU by setting BPF_F_CPU and the CPU ID in the flags. With the old check, CPU 1 is incorrectly accepted while valid CPU 3 is rejected with -ERANGE. The CPU 1 update then reaches the per-CPU map access path and triggers: Unable to handle kernel paging request at virtual address ... pc : __pi_memcpy_generic+0x5c/0x22c lr : bpf_percpu_array_update+0x2dc/0x2e8 Call trace: __pi_memcpy_generic bpf_map_update_value map_update_elem __sys_bpf Check the CPU ID against nr_cpu_ids and cpu_possible() instead. This rejects CPU IDs outside the valid range and CPUs absent from the possible mask, while allowing valid sparse CPU IDs. Fixes: 2b421662c788 ("bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags") Signed-off-by: Hui Su Signed-off-by: Andrii Nakryiko Acked-by: Leon Hwang Link: https://lore.kernel.org/bpf/20260813160858.1042834-3-sh_def@163.com --- include/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index ffa5626411ac..b7dbf3d9b5c0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -4209,7 +4209,7 @@ static inline int bpf_map_check_op_flags(struct bpf_map *map, u64 flags, u64 all return -EINVAL; cpu = flags >> 32; - if ((flags & BPF_F_CPU) && cpu >= num_possible_cpus()) + if ((flags & BPF_F_CPU) && (cpu >= nr_cpu_ids || !cpu_possible(cpu))) return -ERANGE; } From 75b0a6db4300e4c2c9e97a0848deaa7acfb42fb7 Mon Sep 17 00:00:00 2001 From: Hui Su Date: Thu, 13 Aug 2026 23:51:33 +0800 Subject: [PATCH 0073/1198] bpf: Fix percpu map update indexing with sparse CPU IDs Per-CPU array, hash, and cgroup storage map updates without BPF_F_CPU or BPF_F_ALL_CPUS use a value buffer whose per-CPU slots are packed in possible-CPU order. The buffer is sized as: round_up(value_size, 8) * num_possible_cpus() The update paths iterate over possible CPUs, but use the logical CPU ID to calculate the source offset: value + size * cpu This only works when possible CPU IDs are contiguous starting at zero. For example, with a possible CPU mask of 0,2-3, the buffer contains three slots corresponding to CPUs 0, 2, and 3. CPU2 is therefore expected to use slot 1 and CPU3 slot 2. Instead, the current code uses slots 2 and 3 respectively, causing incorrect per-CPU values and an out-of-bounds read from the update buffer for CPU3. The corresponding lookup paths already use a dense offset while iterating over possible CPUs. Do the same for the array, hash, and cgroup storage update paths, advancing the source offset once for each possible CPU. BPF_F_ALL_CPUS continues to use the same value for every CPU. Fixes: 8eb76cb03f0f ("bpf: Add BPF_F_CPU and BPF_F_ALL_CPUS flags support for percpu_array maps") Fixes: c6936161fd55 ("bpf: Add BPF_F_CPU and BPF_F_ALL_CPUS flags support for percpu_hash and lru_percpu_hash maps") Fixes: 47c79f05aa0d ("bpf: Add BPF_F_CPU and BPF_F_ALL_CPUS flags support for percpu_cgroup_storage maps") Signed-off-by: Hui Su Signed-off-by: Andrii Nakryiko Acked-by: Leon Hwang Link: https://lore.kernel.org/bpf/20260813155131.1022745-3-sh_def@163.com --- kernel/bpf/arraymap.c | 5 +++-- kernel/bpf/hashtab.c | 5 +++-- kernel/bpf/local_storage.c | 5 +++-- 3 files changed, 9 insertions(+), 6 deletions(-) diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index ef315b168b29..0ce26b538075 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -436,7 +436,7 @@ int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, void __percpu *pptr; void *ptr, *val; u32 size; - int cpu; + int cpu, off = 0; if (unlikely((map_flags & BPF_F_LOCK) || (u32)map_flags > BPF_F_ALL_CPUS)) /* unknown flags */ @@ -468,9 +468,10 @@ int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, } for_each_possible_cpu(cpu) { ptr = per_cpu_ptr(pptr, cpu); - val = (map_flags & BPF_F_ALL_CPUS) ? value : value + size * cpu; + val = (map_flags & BPF_F_ALL_CPUS) ? value : value + off; copy_map_value(map, ptr, val); bpf_obj_cancel_fields(map, ptr); + off += size; } unlock: rcu_read_unlock(); diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index d40cb5dd446c..d8db1cebc193 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -1025,7 +1025,7 @@ static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr, } else { u32 size = round_up(htab->map.value_size, 8); void *val; - int cpu; + int cpu, off = 0; if (map_flags & BPF_F_CPU) { cpu = map_flags >> 32; @@ -1037,9 +1037,10 @@ static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr, for_each_possible_cpu(cpu) { ptr = per_cpu_ptr(pptr, cpu); - val = (map_flags & BPF_F_ALL_CPUS) ? value : value + size * cpu; + val = (map_flags & BPF_F_ALL_CPUS) ? value : value + off; copy_map_value(&htab->map, ptr, val); bpf_obj_cancel_fields(&htab->map, ptr); + off += size; } } } diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 23267213a17f..83cd527a2542 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -220,7 +220,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *key, struct bpf_cgroup_storage *storage; void *val; u32 size; - int cpu; + int cpu, off = 0; if ((u32)map_flags & ~(BPF_ANY | BPF_EXIST | BPF_F_CPU | BPF_F_ALL_CPUS)) return -EINVAL; @@ -245,8 +245,9 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *key, } size = round_up(_map->value_size, 8); for_each_possible_cpu(cpu) { - val = (map_flags & BPF_F_ALL_CPUS) ? value : value + size * cpu; + val = (map_flags & BPF_F_ALL_CPUS) ? value : value + off; copy_map_value(_map, per_cpu_ptr(storage->percpu_buf, cpu), val); + off += size; } unlock: rcu_read_unlock(); From e10b8b4931e10dbcce5b369583461d81c69187e8 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 18 Aug 2026 09:48:40 -1000 Subject: [PATCH 0074/1198] sched_ext: Sync tools autogen enum headers from the scx repo Regenerate enum_defs.autogen.h against the current tree, picking up the dispatch verdict enums and dropping the marker for the removed SCX_RQ_IN_BALANCE. Add enums_abi.autogen.h, a table of 64-bit scx enumerator values generated from vmlinux.h, used as the substitution source when the running kernel's BTF truncates 64-bit enum values to 32 bits. Signed-off-by: Tejun Heo --- .../sched_ext/include/scx/enum_defs.autogen.h | 5 +- .../sched_ext/include/scx/enums_abi.autogen.h | 223 ++++++++++++++++++ 2 files changed, 227 insertions(+), 1 deletion(-) create mode 100644 tools/sched_ext/include/scx/enums_abi.autogen.h diff --git a/tools/sched_ext/include/scx/enum_defs.autogen.h b/tools/sched_ext/include/scx/enum_defs.autogen.h index 19aa1de3e700..63b6b14b19bd 100644 --- a/tools/sched_ext/include/scx/enum_defs.autogen.h +++ b/tools/sched_ext/include/scx/enum_defs.autogen.h @@ -56,6 +56,10 @@ #define HAVE_SCX_DEQ_SLEEP #define HAVE_SCX_DEQ_CORE_SCHED_EXEC #define HAVE_SCX_DEQ_SCHED_CHANGE +#define HAVE_SCX_DSP_NONE +#define HAVE_SCX_DSP_LOCAL +#define HAVE_SCX_DSP_PREV +#define HAVE_SCX_DSP_RETRY #define HAVE_SCX_DSQ_FLAG_BUILTIN #define HAVE_SCX_DSQ_FLAG_LOCAL_ON #define HAVE_SCX_DSQ_INVALID @@ -188,7 +192,6 @@ #define HAVE_SCX_RQ_SUB_IDLE_RENOTIFY #define HAVE_SCX_RQ_ROOT_IDLE_RENOTIFY #define HAVE_SCX_RQ_IN_WAKEUP -#define HAVE_SCX_RQ_IN_BALANCE #define HAVE_SCX_RQ_IN_DISPATCH #define HAVE_SCX_SCHED_PCPU_BYPASSING #define HAVE_SCX_SLICE_OOB_DUR_BITS diff --git a/tools/sched_ext/include/scx/enums_abi.autogen.h b/tools/sched_ext/include/scx/enums_abi.autogen.h new file mode 100644 index 000000000000..d53899764f5a --- /dev/null +++ b/tools/sched_ext/include/scx/enums_abi.autogen.h @@ -0,0 +1,223 @@ +/* + * WARNING: This file is autogenerated from gen_enum_defs.py [1]. + * + * scx enumerator values from the vmlinux.h this tree is built against. + * Used as the substitution source when the running kernel's BTF lacks + * BTF_KIND_ENUM64 encoding and 64-bit enum values are truncated. + * + * [1] https://github.com/sched-ext/scx/blob/main/scripts/gen_enum_defs.py + */ + +#ifndef __ENUMS_ABI_AUTOGEN_H__ +#define __ENUMS_ABI_AUTOGEN_H__ + +struct __scx_enum_abi_val { + const char *type; + const char *name; + u64 val; +}; + +static const struct __scx_enum_abi_val __scx_enum_abi_vals[] + __attribute__((unused)) = { + { "scx_arena_consts", "SCX_ARENA_MIN_ORDER", 0x3LLU }, + { "scx_arena_consts", "SCX_ARENA_GROW_PAGES", 0x4LLU }, + { "scx_cap_flags", "__SCX_CAP_ENQ_IMMED", 0x0LLU }, + { "scx_cap_flags", "__SCX_CAP_ENQ", 0x1LLU }, + { "scx_cap_flags", "__SCX_CAP_PREEMPT", 0x2LLU }, + { "scx_cap_flags", "__SCX_CAP_PERF", 0x3LLU }, + { "scx_cap_flags", "__SCX_NR_CAPS", 0x4LLU }, + { "scx_cap_flags", "__SCX_CAP_ALL", 0xfLLU }, + { "scx_cap_flags", "SCX_CAP_ENQ_IMMED", 0x1LLU }, + { "scx_cap_flags", "SCX_CAP_ENQ", 0x2LLU }, + { "scx_cap_flags", "SCX_CAP_PREEMPT", 0x4LLU }, + { "scx_cap_flags", "SCX_CAP_PERF", 0x8LLU }, + { "scx_cap_flags", "SCX_CAP_BASE", 0x1LLU }, + { "scx_cap_flags", "SCX_CAPS_REENQ_ON_LOSS", 0x3LLU }, + { "scx_cid_consts", "SCX_CID_SHARD_SIZE_DFL", 0x18LLU }, + { "scx_cid_consts", "SCX_CID_SHARD_MAX_CPUS", 0x200LLU }, + { "scx_consts", "SCX_DSP_DFL_MAX_BATCH", 0x20LLU }, + { "scx_consts", "SCX_DSP_MAX_LOOPS", 0x20LLU }, + { "scx_consts", "SCX_WATCHDOG_MAX_TIMEOUT", 0x7530LLU }, + { "scx_consts", "SCX_RESCUE_DFL_BW_PPT", 0x14LLU }, + { "scx_consts", "SCX_RESCUE_MAX_BW_PPT", 0xfaLLU }, + { "scx_consts", "SCX_RESCUE_DISABLE", 0xffffffffLLU }, + { "scx_consts", "SCX_RESCUE_DFL_QUANTUM_US", 0x1388LLU }, + { "scx_consts", "SCX_RESCUE_MIN_QUANTUM_US", 0x3e8LLU }, + { "scx_consts", "SCX_RESCUE_MAX_QUANTUM_US", 0x186a0LLU }, + { "scx_consts", "SCX_RESCUE_MIN_SLICE_US", 0x3e8LLU }, + { "scx_consts", "SCX_RESCUE_OVERLOAD_MULT", 0x10LLU }, + { "scx_consts", "SCX_RESCUE_MIN_OVERLOAD_MS", 0x3e8LLU }, + { "scx_consts", "SCX_RESCUE_MAX_OVERLOAD_MS", 0x3a98LLU }, + { "scx_consts", "SCX_TID_CHUNK", 0x400LLU }, + { "scx_consts", "SCX_EXIT_BT_LEN", 0x40LLU }, + { "scx_consts", "SCX_EXIT_MSG_LEN", 0x400LLU }, + { "scx_consts", "SCX_EXIT_DUMP_DFL_LEN", 0x8000LLU }, + { "scx_consts", "SCX_CPUPERF_ONE", 0x400LLU }, + { "scx_consts", "SCX_TASK_ITER_BATCH", 0x20LLU }, + { "scx_consts", "SCX_BYPASS_HOST_NTH", 0x2LLU }, + { "scx_consts", "SCX_BYPASS_LB_DFL_INTV_US", 0x7a120LLU }, + { "scx_consts", "SCX_BYPASS_LB_DONOR_PCT", 0x7dLLU }, + { "scx_consts", "SCX_BYPASS_LB_MIN_DELTA_DIV", 0x4LLU }, + { "scx_consts", "SCX_BYPASS_LB_BATCH", 0x100LLU }, + { "scx_consts", "SCX_REENQ_MAX_REPEAT", 0x100LLU }, + { "scx_consts", "SCX_SUB_MAX_DEPTH", 0x4LLU }, + { "scx_cpu_preempt_reason", "SCX_CPU_PREEMPT_RT", 0x0LLU }, + { "scx_cpu_preempt_reason", "SCX_CPU_PREEMPT_DL", 0x1LLU }, + { "scx_cpu_preempt_reason", "SCX_CPU_PREEMPT_STOP", 0x2LLU }, + { "scx_cpu_preempt_reason", "SCX_CPU_PREEMPT_UNKNOWN", 0x3LLU }, + { "scx_deq_flags", "SCX_DEQ_SLEEP", 0x1LLU }, + { "scx_deq_flags", "SCX_DEQ_CORE_SCHED_EXEC", 0x100000000LLU }, + { "scx_deq_flags", "SCX_DEQ_SCHED_CHANGE", 0x200000000LLU }, + { "scx_dsp_verdict", "SCX_DSP_NONE", 0x0LLU }, + { "scx_dsp_verdict", "SCX_DSP_LOCAL", 0x1LLU }, + { "scx_dsp_verdict", "SCX_DSP_PREV", 0x2LLU }, + { "scx_dsp_verdict", "SCX_DSP_RETRY", 0x3LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_FLAG_BUILTIN", 0x8000000000000000LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_FLAG_LOCAL_ON", 0x4000000000000000LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_INVALID", 0x8000000000000000LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_GLOBAL", 0x8000000000000001LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_LOCAL", 0x8000000000000002LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_BYPASS", 0x8000000000000003LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_REJECT", 0x8000000000000004LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_RESCUE", 0x8000000000000005LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_LOCAL_ON", 0xc000000000000000LLU }, + { "scx_dsq_id_flags", "SCX_DSQ_LOCAL_CPU_MASK", 0xffffffffLLU }, + { "scx_dsq_iter_flags", "SCX_DSQ_ITER_REV", 0x10000LLU }, + { "scx_dsq_iter_flags", "__SCX_DSQ_ITER_HAS_SLICE", 0x40000000LLU }, + { "scx_dsq_iter_flags", "__SCX_DSQ_ITER_HAS_VTIME", 0x80000000LLU }, + { "scx_dsq_iter_flags", "__SCX_DSQ_ITER_USER_FLAGS", 0x10000LLU }, + { "scx_dsq_iter_flags", "__SCX_DSQ_ITER_ALL_FLAGS", 0xc0010000LLU }, + { "scx_dsq_lnode_flags", "SCX_DSQ_LNODE_ITER_CURSOR", 0x1LLU }, + { "scx_dsq_lnode_flags", "__SCX_DSQ_LNODE_PRIV_SHIFT", 0x10LLU }, + { "scx_enable_state", "SCX_ENABLING", 0x0LLU }, + { "scx_enable_state", "SCX_ENABLED", 0x1LLU }, + { "scx_enable_state", "SCX_DISABLING", 0x2LLU }, + { "scx_enable_state", "SCX_DISABLED", 0x3LLU }, + { "scx_enq_flags", "SCX_ENQ_WAKEUP", 0x1LLU }, + { "scx_enq_flags", "SCX_ENQ_HEAD", 0x10000LLU }, + { "scx_enq_flags", "SCX_ENQ_CPU_SELECTED", 0x100000LLU }, + { "scx_enq_flags", "SCX_ENQ_PREEMPT", 0x100000000LLU }, + { "scx_enq_flags", "SCX_ENQ_IMMED", 0x200000000LLU }, + { "scx_enq_flags", "SCX_ENQ_RESCUE", 0x400000000LLU }, + { "scx_enq_flags", "SCX_ENQ_REENQ", 0x10000000000LLU }, + { "scx_enq_flags", "SCX_ENQ_LAST", 0x20000000000LLU }, + { "scx_enq_flags", "__SCX_ENQ_INTERNAL_MASK", 0xff00000000000000LLU }, + { "scx_enq_flags", "SCX_ENQ_CLEAR_OPSS", 0x100000000000000LLU }, + { "scx_enq_flags", "SCX_ENQ_DSQ_PRIQ", 0x200000000000000LLU }, + { "scx_enq_flags", "SCX_ENQ_NESTED", 0x400000000000000LLU }, + { "scx_enq_flags", "SCX_ENQ_GDSQ_FALLBACK", 0x800000000000000LLU }, + { "scx_enq_flags", "SCX_ENQ_IGNORE_CAPS", 0x1000000000000000LLU }, + { "scx_enq_flags", "SCX_ENQ_APPLY_SLICE", 0x2000000000000000LLU }, + { "scx_enq_flags", "SCX_ENQ_SLICE_DFL", 0x4000000000000000LLU }, + { "scx_ent_dsq_flags", "SCX_TASK_DSQ_ON_PRIQ", 0x1LLU }, + { "scx_ent_flags", "SCX_TASK_QUEUED", 0x1LLU }, + { "scx_ent_flags", "SCX_TASK_IN_CUSTODY", 0x2LLU }, + { "scx_ent_flags", "SCX_TASK_RESET_RUNNABLE_AT", 0x4LLU }, + { "scx_ent_flags", "SCX_TASK_DEQD_FOR_SLEEP", 0x8LLU }, + { "scx_ent_flags", "SCX_TASK_SUB_INIT", 0x10LLU }, + { "scx_ent_flags", "SCX_TASK_IMMED", 0x20LLU }, + { "scx_ent_flags", "SCX_TASK_PROTECTED", 0x40LLU }, + { "scx_ent_flags", "SCX_TASK_STATE_SHIFT", 0x8LLU }, + { "scx_ent_flags", "SCX_TASK_STATE_BITS", 0x3LLU }, + { "scx_ent_flags", "SCX_TASK_STATE_MASK", 0x700LLU }, + { "scx_ent_flags", "SCX_TASK_NONE", 0x0LLU }, + { "scx_ent_flags", "SCX_TASK_INIT_BEGIN", 0x100LLU }, + { "scx_ent_flags", "SCX_TASK_INIT", 0x200LLU }, + { "scx_ent_flags", "SCX_TASK_READY", 0x300LLU }, + { "scx_ent_flags", "SCX_TASK_ENABLED", 0x400LLU }, + { "scx_ent_flags", "SCX_TASK_DEAD", 0x500LLU }, + { "scx_ent_flags", "SCX_TASK_REENQ_REASON_SHIFT", 0xcLLU }, + { "scx_ent_flags", "SCX_TASK_REENQ_REASON_BITS", 0x3LLU }, + { "scx_ent_flags", "SCX_TASK_REENQ_REASON_MASK", 0x7000LLU }, + { "scx_ent_flags", "SCX_TASK_REENQ_NONE", 0x0LLU }, + { "scx_ent_flags", "SCX_TASK_REENQ_KFUNC", 0x1000LLU }, + { "scx_ent_flags", "SCX_TASK_REENQ_IMMED", 0x2000LLU }, + { "scx_ent_flags", "SCX_TASK_REENQ_PREEMPTED", 0x3000LLU }, + { "scx_ent_flags", "SCX_TASK_REENQ_CAP", 0x4000LLU }, + { "scx_ent_flags", "SCX_TASK_CURSOR", 0xffffffff80000000LLU }, + { "scx_exit_code", "SCX_ECODE_RSN_HOTPLUG", 0x100000000LLU }, + { "scx_exit_code", "SCX_ECODE_RSN_CGROUP_OFFLINE", 0x200000000LLU }, + { "scx_exit_code", "SCX_ECODE_ACT_RESTART", 0x1000000000000LLU }, + { "scx_exit_flags", "SCX_EFLAG_INITIALIZED", 0x1LLU }, + { "scx_exit_kind", "SCX_EXIT_NONE", 0x0LLU }, + { "scx_exit_kind", "SCX_EXIT_DONE", 0x1LLU }, + { "scx_exit_kind", "SCX_EXIT_UNREG", 0x40LLU }, + { "scx_exit_kind", "SCX_EXIT_UNREG_BPF", 0x41LLU }, + { "scx_exit_kind", "SCX_EXIT_UNREG_KERN", 0x42LLU }, + { "scx_exit_kind", "SCX_EXIT_SYSRQ", 0x43LLU }, + { "scx_exit_kind", "SCX_EXIT_PARENT", 0x44LLU }, + { "scx_exit_kind", "SCX_EXIT_PARENT_KILL", 0x45LLU }, + { "scx_exit_kind", "SCX_EXIT_ERROR", 0x400LLU }, + { "scx_exit_kind", "SCX_EXIT_ERROR_BPF", 0x401LLU }, + { "scx_exit_kind", "SCX_EXIT_ERROR_STALL", 0x402LLU }, + { "scx_exit_kind", "SCX_EXIT_ERROR_REENQ", 0x403LLU }, + { "scx_exit_kind", "SCX_EXIT_ERROR_RESCUE", 0x404LLU }, + { "scx_kf_allow_flags", "SCX_KF_ALLOW_UNLOCKED", 0x1LLU }, + { "scx_kf_allow_flags", "SCX_KF_ALLOW_INIT_CIDS", 0x2LLU }, + { "scx_kf_allow_flags", "SCX_KF_ALLOW_CPU_RELEASE", 0x4LLU }, + { "scx_kf_allow_flags", "SCX_KF_ALLOW_DISPATCH", 0x8LLU }, + { "scx_kf_allow_flags", "SCX_KF_ALLOW_ENQUEUE", 0x10LLU }, + { "scx_kf_allow_flags", "SCX_KF_ALLOW_SELECT_CPU", 0x20LLU }, + { "scx_kick_flags", "SCX_KICK_IDLE", 0x1LLU }, + { "scx_kick_flags", "SCX_KICK_PREEMPT", 0x2LLU }, + { "scx_kick_flags", "SCX_KICK_WAIT", 0x4LLU }, + { "scx_opi", "SCX_OPI_BEGIN", 0x0LLU }, + { "scx_opi", "SCX_OPI_NORMAL_BEGIN", 0x0LLU }, + { "scx_opi", "SCX_OPI_NORMAL_END", 0x21LLU }, + { "scx_opi", "SCX_OPI_CPU_HOTPLUG_BEGIN", 0x21LLU }, + { "scx_opi", "SCX_OPI_CPU_HOTPLUG_END", 0x23LLU }, + { "scx_opi", "SCX_OPI_END", 0x23LLU }, + { "scx_ops_flags", "SCX_OPS_KEEP_BUILTIN_IDLE", 0x1LLU }, + { "scx_ops_flags", "SCX_OPS_ENQ_LAST", 0x2LLU }, + { "scx_ops_flags", "SCX_OPS_ENQ_EXITING", 0x4LLU }, + { "scx_ops_flags", "SCX_OPS_SWITCH_PARTIAL", 0x8LLU }, + { "scx_ops_flags", "SCX_OPS_ENQ_MIGRATION_DISABLED", 0x10LLU }, + { "scx_ops_flags", "SCX_OPS_ALLOW_QUEUED_WAKEUP", 0x20LLU }, + { "scx_ops_flags", "SCX_OPS_BUILTIN_IDLE_PER_NODE", 0x40LLU }, + { "scx_ops_flags", "SCX_OPS_ALWAYS_ENQ_IMMED", 0x80LLU }, + { "scx_ops_flags", "SCX_OPS_TID_TO_TASK", 0x100LLU }, + { "scx_ops_flags", "SCX_OPS_ALL_FLAGS", 0x1ffLLU }, + { "scx_ops_flags", "__SCX_OPS_INTERNAL_MASK", 0xff00000000000000LLU }, + { "scx_ops_flags", "SCX_OPS_HAS_CPU_PREEMPT", 0x100000000000000LLU }, + { "scx_ops_state", "SCX_OPSS_NONE", 0x0LLU }, + { "scx_ops_state", "SCX_OPSS_QUEUEING", 0x1LLU }, + { "scx_ops_state", "SCX_OPSS_QUEUED", 0x2LLU }, + { "scx_ops_state", "SCX_OPSS_DISPATCHING", 0x3LLU }, + { "scx_ops_state", "SCX_OPSS_QSEQ_SHIFT", 0x2LLU }, + { "scx_pick_idle_cpu_flags", "SCX_PICK_IDLE_CORE", 0x1LLU }, + { "scx_pick_idle_cpu_flags", "SCX_PICK_IDLE_IN_NODE", 0x2LLU }, + { "scx_public_consts", "SCX_OPS_NAME_LEN", 0x80LLU }, + { "scx_public_consts", "SCX_SLICE_DFL", 0x1312d00LLU }, + { "scx_public_consts", "SCX_SLICE_BYPASS", 0x4c4b40LLU }, + { "scx_public_consts", "SCX_SLICE_INF", 0xffffffffffffffffLLU }, + { "scx_reenq_flags", "SCX_REENQ_ANY", 0x1LLU }, + { "scx_reenq_flags", "SCX_REENQ_CAP_REVOKE", 0x2LLU }, + { "scx_reenq_flags", "__SCX_REENQ_FILTER_MASK", 0xffffLLU }, + { "scx_reenq_flags", "__SCX_REENQ_USER_MASK", 0x1LLU }, + { "scx_reenq_flags", "SCX_REENQ_TSR_RQ_OPEN", 0x100000000LLU }, + { "scx_reenq_flags", "SCX_REENQ_TSR_NOT_FIRST", 0x200000000LLU }, + { "scx_reenq_flags", "__SCX_REENQ_TSR_MASK", 0xf00000000LLU }, + { "scx_rq_flags", "SCX_RQ_ONLINE", 0x1LLU }, + { "scx_rq_flags", "SCX_RQ_CAN_STOP_TICK", 0x2LLU }, + { "scx_rq_flags", "SCX_RQ_CLK_VALID", 0x20LLU }, + { "scx_rq_flags", "SCX_RQ_BAL_CB_PENDING", 0x40LLU }, + { "scx_rq_flags", "SCX_RQ_SUB_IDLE_RENOTIFY", 0x80LLU }, + { "scx_rq_flags", "SCX_RQ_ROOT_IDLE_RENOTIFY", 0x100LLU }, + { "scx_rq_flags", "SCX_RQ_IN_WAKEUP", 0x10000LLU }, + { "scx_rq_flags", "SCX_RQ_IN_DISPATCH", 0x20000LLU }, + { "scx_sched_pcpu_flags", "SCX_SCHED_PCPU_BYPASSING", 0x1LLU }, + { "scx_slice_oob_consts", "SCX_SLICE_OOB_DUR_BITS", 0x2bLLU }, + { "scx_slice_oob_consts", "SCX_SLICE_OOB_ID_BITS", 0x14LLU }, + { "scx_slice_oob_consts", "SCX_SLICE_OOB_DUR_MASK", 0x7ffffffffffLLU }, + { "scx_slice_oob_consts", "SCX_SLICE_OOB_ID_SHIFT", 0x2bLLU }, + { "scx_slice_oob_consts", "SCX_SLICE_OOB_ID_MASK", 0xfffffLLU }, + { "scx_slice_oob_consts", "SCX_SLICE_OOB_PENDING", 0x8000000000000000LLU }, + { "scx_tg_flags", "SCX_TG_ONLINE", 0x1LLU }, + { "scx_tg_flags", "SCX_TG_INITED", 0x2LLU }, + { "scx_tg_flags", "SCX_TG_SUB_INIT", 0x4LLU }, + { "scx_wake_flags", "SCX_WAKE_FORK", 0x4LLU }, + { "scx_wake_flags", "SCX_WAKE_TTWU", 0x8LLU }, + { "scx_wake_flags", "SCX_WAKE_SYNC", 0x10LLU }, +}; + +#endif /* __ENUMS_ABI_AUTOGEN_H__ */ From 9e8581a090c02ffa35e8439b90b024956a735de9 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 18 Aug 2026 09:48:40 -1000 Subject: [PATCH 0075/1198] sched_ext: Sync common and compat headers from the scx repo Sync common.bpf.h, compat.bpf.h and compat.h with the scx repo, which accumulated the following: - __COMPAT_read_enum() can now recover 64-bit scx enum values from kernel BTF generated without BTF_KIND_ENUM64 support (pahole < 1.24 or --skip_encoding_btf_enum64, e.g. COS/GKE kernels), substituting values from the build-time vmlinux.h cross-checked against the low 32 bits the kernel does provide. - is_migration_disabled() no longer assumes the BPF prolog always disables migration. Since 8e4f0b1ebcf2 ("bpf: use rcu_read_lock_dont_migrate() for trampoline.c") the prolog only does so under CONFIG_PREEMPT_RCU, so the old current-task test under-reported on v6.18+ !PREEMPT_RCU kernels. A runtime probe on bpf_scx_reg() handles older kernels with backported trampoline behavior. - __COMPAT_scx_bpf_dsq_peek() is gated behind kernel v7.1 where 2f2ea7709266 ("sched_ext: Use dsq->first_task instead of list_empty() in dispatch_enqueue() FIFO-tail") fixed the kfunc spuriously returning NULL on non-empty FIFO DSQs, and the new scx_bpf_reenqueue_local_from_anywhere() provides a callable-from-anywhere reenqueue which prefers the generic scx_bpf_dsq_reenq(). Both were first posted by Gavin Guo and Changwoo Min and are picked up here with the review feedback folded in. - __COMPAT_scx_bpf_cpu_curr() and the scx_bpf_cpu_rq() declaration are restored. Schedulers built from these headers still run on pre-v6.18 kernels where scx_bpf_cpu_curr() does not resolve and the scx_bpf_cpu_rq() fallback still exists. - scx_clock_task() and scx_clock_pelt() document their stale-read behavior for remote idle CPUs under NO_HZ_IDLE. Link: https://lore.kernel.org/all/20260817143126.562923-1-changwoo@igalia.com Signed-off-by: Tejun Heo --- tools/sched_ext/include/scx/common.bpf.h | 140 +++++++++++++++++++---- tools/sched_ext/include/scx/compat.bpf.h | 68 +++++++++-- tools/sched_ext/include/scx/compat.h | 97 ++++++++++++++++ 3 files changed, 274 insertions(+), 31 deletions(-) diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h index 979d4cabfaf9..76f5e025e107 100644 --- a/tools/sched_ext/include/scx/common.bpf.h +++ b/tools/sched_ext/include/scx/common.bpf.h @@ -48,6 +48,7 @@ extern int LINUX_KERNEL_VERSION __kconfig; extern const char CONFIG_CC_VERSION_TEXT[64] __kconfig __weak; extern const char CONFIG_LOCALVERSION[64] __kconfig __weak; +extern bool CONFIG_PREEMPT_RCU __kconfig __weak; /* * Earlier versions of clang/pahole lost upper 32bits in 64bit enums which can @@ -97,6 +98,7 @@ s32 scx_bpf_pick_any_cpu_node(const cpumask_t *cpus_allowed, int node, u64 flags s32 scx_bpf_pick_any_cpu(const cpumask_t *cpus_allowed, u64 flags) __ksym; bool scx_bpf_task_running(const struct task_struct *p) __ksym; s32 scx_bpf_task_cpu(const struct task_struct *p) __ksym; +struct rq *scx_bpf_cpu_rq(s32 cpu) __ksym __weak; struct rq *scx_bpf_locked_rq(void) __ksym; struct task_struct *scx_bpf_cpu_curr(s32 cpu) __ksym __weak; struct task_struct *scx_bpf_tid_to_task(u64 tid) __ksym __weak; @@ -527,32 +529,103 @@ static __always_inline const struct cpumask *cast_mask(struct bpf_cpumask *mask) return (const struct cpumask *)mask; } +/* + * True if the non-sleepable BPF trampoline prolog (__bpf_prog_enter) calls + * migrate_disable() for the current task. Recorded once by + * scx_lib_init_probe, an fentry program on bpf_scx_reg() that fires during + * the natural scheduler-attach call chain (auto-attached by scx_ops_attach!). + * + * Defaults to true (conservative). Over-reporting in is_migration_disabled() + * causes local-only dispatch, which is safe. Under-reporting can crash the + * scheduler, so we err high if the probe somehow fails to run. + */ +bool __scx_prolog_disables_migration __weak = true; + +/* + * scx_lib_init_probe - non-sleepable prolog probe. + * + * Attached to bpf_scx_reg(), the .reg callback in bpf_sched_ext_ops + * (kernel/sched/ext.c). The kernel's struct_ops machinery invokes + * bpf_scx_reg when userspace creates the scheduler link, before + * ops.init() fires. Its address is taken in the vtable, so the symbol + * is non-inlinable and has been stable since introduction. + * + * Entering via fentry runs us through __bpf_prog_enter -- the + * non-sleepable prolog that consumers of is_migration_disabled() live + * under. + * + * Loud warning: the prolog adds at most 1 to migration_disabled. + * Reading > 1 means something upstream in the + * bpf_struct_ops_link_create -> bpf_scx_reg path disabled migration + * before the prolog ran, invalidating the probe; audit and adjust. + */ +SEC("fentry/bpf_scx_reg") __weak +int scx_lib_init_probe(void *ctx) +{ + if (bpf_core_field_exists(((struct task_struct *)0)->migration_disabled)) { + const struct task_struct *p = bpf_get_current_task_btf(); + unsigned int md = p->migration_disabled; + + if (md > 1) + bpf_printk("scx_lib_init_probe: unexpected migration_disabled=%u " + "upstream of BPF prolog; probe result unreliable", + md); + + __scx_prolog_disables_migration = md > 0; + } + return 0; +} + /* * Return true if task @p cannot migrate to a different CPU, false * otherwise. + * + * IMPORTANT: designed for NON-SLEEPABLE BPF contexts only. Sleepable + * contexts (BPF_STRUCT_OPS_SLEEPABLE, SEC("syscall"), + * SEC("fentry.s/...")) enter via __bpf_prog_enter_sleepable() or + * __bpf_prog_enter_sleepable_recur(), both of which unconditionally + * call migrate_disable(); this helper can yield a false negative for + * p == current there, which can crash the scheduler. */ static inline bool is_migration_disabled(const struct task_struct *p) { /* - * Testing p->migration_disabled in a BPF code is tricky because the - * migration is _always_ disabled while running the BPF code. - * The prolog (__bpf_prog_enter) and epilog (__bpf_prog_exit) for BPF - * code execution disable and re-enable the migration of the current - * task, respectively. So, the _current_ task of the sched_ext ops is - * always migration-disabled. Moreover, p->migration_disabled could be - * two or greater when a sched_ext ops BPF code (e.g., ops.tick) is - * executed in the middle of the other BPF code execution. + * Testing p->migration_disabled in BPF is tricky because the BPF prolog + * (__bpf_prog_enter) may call migrate_disable() for the current task, + * making migration_disabled == 1 even for tasks that are not truly + * migration-disabled. * - * Therefore, we should decide that the _current_ task is - * migration-disabled only when its migration_disabled count is greater - * than one. In other words, when p->migration_disabled == 1, there is - * an ambiguity, so we should check if @p is the current task or not. + * Since commit 8e4f0b1ebcf2 ("bpf: use rcu_read_lock_dont_migrate() for + * trampoline.c"), the BPF prolog calls migrate_disable() only when + * CONFIG_PREEMPT_RCU is enabled. Two fast paths cover the common cases: + * + * 1) CONFIG_PREEMPT_RCU: prolog always calls migrate_disable(), so + * migration_disabled == 1 for the current task is ambiguous. + * Disambiguate by checking p == current. + * + * 2) v6.18+ without CONFIG_PREEMPT_RCU: prolog never calls + * migrate_disable(), so migration_disabled == 1 is unambiguously + * a real migrate_disable() call. + * + * A slow path handles pre-v6.18 kernels without CONFIG_PREEMPT_RCU, + * where the prolog historically called migrate_disable() unconditionally + * but a cherry-picked downstream kernel may not. The runtime-probed flag + * __scx_prolog_disables_migration (set by scx_lib_init_probe) distinguishes + * the two cases without relying on the kernel version alone. */ if (bpf_core_field_exists(p->migration_disabled)) { - if (p->migration_disabled == 1) - return bpf_get_current_task_btf() != p; - else - return p->migration_disabled; + if (p->migration_disabled == 1) { + /* Fast path: prolog always disables migration */ + if (CONFIG_PREEMPT_RCU) + return bpf_get_current_task_btf() != p; + /* Fast path: prolog never disables migration */ + if (LINUX_KERNEL_VERSION >= KERNEL_VERSION(6, 18, 0)) + return true; + /* Slow path: pre-v6.18, !PREEMPT_RCU - use runtime flag */ + return __scx_prolog_disables_migration ? + bpf_get_current_task_btf() != p : true; + } + return p->migration_disabled; } return false; } @@ -1021,7 +1094,20 @@ static inline u64 scx_clock_task(u32 cpu) { struct rq___local *rq = get_current_rq(cpu); - /* Equivalent to the kernel's rq_clock_task(). */ + /* + * Equivalent to the kernel's rq_clock_task(): wall-clock time minus + * cumulative IRQ time (CONFIG_IRQ_TIME_ACCOUNTING) and hypervisor + * steal time (CONFIG_PARAVIRT_TIME_ACCOUNTING). Without those configs, + * it equals rq->clock. + * + * Conceptually this clock advances during idle (the idle task counts + * as a running task), but rq->clock_task is only updated on scheduling + * events. With NO_HZ_IDLE (the default), the periodic tick is stopped + * on idle CPUs, so rq->clock_task is not refreshed while a CPU is + * idle. Reading this clock for a remote idle CPU from a BPF timer + * callback returns the value from when the CPU last went idle, making + * the delta over an idle interval effectively zero. + */ return rq ? rq->clock_task : 0; } @@ -1032,9 +1118,23 @@ static inline u64 scx_clock_pelt(u32 cpu) /* * Equivalent to the kernel's rq_clock_pelt(): subtracts * lost_idle_time from clock_pelt to absorb the jump that occurs - * when clock_pelt resyncs with clock_task at idle exit. The result - * is a continuous, capacity-invariant clock safe for both task - * execution time stamping and cross-idle measurements. + * when clock_pelt resyncs with clock_task at idle exit. The intent + * is a continuous, capacity- and frequency-invariant clock that is + * frozen during idle, IRQ, and hypervisor steal. + * + * However, like scx_clock_task(), this clock has a stale-read issue + * for remote idle CPUs with NO_HZ_IDLE (the default). clock_pelt + * itself advances at wall-clock rate (hardware-clock based), but + * lost_idle_time is only updated via update_rq_clock_pelt(), which + * requires update_rq_clock() to be called. With NO_HZ_IDLE, the + * periodic tick is stopped on idle CPUs, so lost_idle_time is not + * refreshed during idle. Reading this clock for a remote idle CPU + * from a BPF timer callback therefore returns a value that drifts + * at wall-clock rate -- the same stale behaviour as scx_clock_task(). + * + * Without NO_HZ_IDLE, periodic ticks keep lost_idle_time nearly in + * sync (stale by at most one tick period, ~1 ms), so the result is + * accurate. */ return rq ? (rq->clock_pelt - rq->lost_idle_time) : 0; } diff --git a/tools/sched_ext/include/scx/compat.bpf.h b/tools/sched_ext/include/scx/compat.bpf.h index 3ab642f92c8a..6944221f96cc 100644 --- a/tools/sched_ext/include/scx/compat.bpf.h +++ b/tools/sched_ext/include/scx/compat.bpf.h @@ -92,15 +92,20 @@ int bpf_cpumask_populate(struct bpf_cpumask *dst, void *src, size_t src__sz) __k /* * v6.19: Introduce lockless peek API for user DSQs. + * v7.1: Fix scx_bpf_dsq_peek() spuriously returning NULL on non-empty + * FIFO DSQs (2f2ea7709266). * - * Preserve the following macro until v6.21. + * The kfunc exists from v6.19 but can return NULL for a non-empty FIFO DSQ + * before the v7.1 fix. Require kernel version >= 7.1.0 before calling it; + * otherwise fall through to the bpf_iter_scx_dsq fallback below. */ static inline struct task_struct *__COMPAT_scx_bpf_dsq_peek(u64 dsq_id) { struct task_struct *p = NULL; struct bpf_iter_scx_dsq it; - if (bpf_ksym_exists(scx_bpf_dsq_peek)) + if (bpf_ksym_exists(scx_bpf_dsq_peek) && + LINUX_KERNEL_VERSION >= KERNEL_VERSION(7, 1, 0)) return scx_bpf_dsq_peek(dsq_id); if (!bpf_iter_scx_dsq_new(&it, dsq_id, 0)) p = bpf_iter_scx_dsq_next(&it); @@ -238,6 +243,26 @@ static inline bool __COMPAT_is_enq_cpu_selected(u64 enq_flags) scx_bpf_pick_any_cpu_node(cpus_allowed, node, flags) : \ scx_bpf_pick_any_cpu(cpus_allowed, flags)) +/* + * v6.18: Add a helper to retrieve the current task running on a CPU. + * + * The kernel tree dropped this helper and scx_bpf_cpu_rq(), but schedulers in + * this tree still support pre-v6.18 kernels where scx_bpf_cpu_curr() doesn't + * resolve and the scx_bpf_cpu_rq() fallback still exists. Keep it until + * pre-v6.18 kernels fall out of the support window. + */ +static inline struct task_struct *__COMPAT_scx_bpf_cpu_curr(int cpu) +{ + struct rq *rq; + + if (bpf_ksym_exists(scx_bpf_cpu_curr)) + return scx_bpf_cpu_curr(cpu); + + rq = scx_bpf_cpu_rq(cpu); + + return rq ? rq->curr : NULL; +} + /* * v6.19: To work around BPF maximum parameter limit, the following kfuncs are * replaced with variants that pack scalar arguments in a struct. Wrappers are @@ -378,6 +403,17 @@ static inline void scx_bpf_task_set_dsq_vtime(struct task_struct *p, u64 vtime) p->scx.dsq_vtime = vtime; } +/* + * v7.1: New scx_bpf_dsq_reenq() that allows re-enqueues on more DSQs. This + * will eventually deprecate scx_bpf_reenqueue_local(). + */ +void scx_bpf_dsq_reenq___compat(u64 dsq_id, u64 reenq_flags) __ksym __weak; + +static inline bool __COMPAT_has_generic_reenq(void) +{ + return bpf_ksym_exists(scx_bpf_dsq_reenq___compat); +} + /* * v6.19: The new void variant can be called from anywhere while the older v1 * variant can only be called from ops.cpu_release(). The double ___ prefixes on @@ -395,21 +431,31 @@ static inline bool __COMPAT_scx_bpf_reenqueue_local_from_anywhere(void) static inline void scx_bpf_reenqueue_local(void) { - if (__COMPAT_scx_bpf_reenqueue_local_from_anywhere()) + if (__COMPAT_has_generic_reenq()) + scx_bpf_dsq_reenq___compat(SCX_DSQ_LOCAL, 0); + else if (__COMPAT_scx_bpf_reenqueue_local_from_anywhere()) scx_bpf_reenqueue_local___v2___compat(); else scx_bpf_reenqueue_local___v1(); } -/* - * v7.1: New scx_bpf_dsq_reenq() that allows re-enqueues on more DSQs. This - * will eventually deprecate scx_bpf_reenqueue_local(). - */ -void scx_bpf_dsq_reenq___compat(u64 dsq_id, u64 reenq_flags) __ksym __weak; - -static inline bool __COMPAT_has_generic_reenq(void) +static inline int scx_bpf_reenqueue_local_from_anywhere(void) { - return bpf_ksym_exists(scx_bpf_dsq_reenq___compat); + /* + * The generic reenq kfunc and the v2 reenqueue-local variant can both be + * called from anywhere; v1 cannot. Test each ksym in its own branch with a + * distinct call: combining them with || would fold into a bitwise OR of the + * two ksym addresses, which the verifier rejects. + */ + if (__COMPAT_has_generic_reenq()) { + scx_bpf_dsq_reenq___compat(SCX_DSQ_LOCAL, 0); + return 0; + } + if (__COMPAT_scx_bpf_reenqueue_local_from_anywhere()) { + scx_bpf_reenqueue_local___v2___compat(); + return 0; + } + return -EOPNOTSUPP; } static inline void scx_bpf_dsq_reenq(u64 dsq_id, u64 reenq_flags) diff --git a/tools/sched_ext/include/scx/compat.h b/tools/sched_ext/include/scx/compat.h index d2e4384df5af..7c12df45fdba 100644 --- a/tools/sched_ext/include/scx/compat.h +++ b/tools/sched_ext/include/scx/compat.h @@ -10,9 +10,14 @@ #include #include #include +#include +#include #include +#include #include +#include "enums_abi.autogen.h" + struct btf *__COMPAT_vmlinux_btf __attribute__((weak)); static inline void __COMPAT_load_vmlinux_btf(void) @@ -23,6 +28,85 @@ static inline void __COMPAT_load_vmlinux_btf(void) } } +/* + * Recover the true value of a 64-bit enum enumerator whose kernel BTF entry + * was truncated to its low 32 bits. + * + * Kernels whose BTF was generated without BTF_KIND_ENUM64 support encode + * 64-bit enums as 8-byte BTF_KIND_ENUM entries whose enumerator values only + * carry the low 32 bits. This happens with pahole < 1.24, which predates + * ENUM64, and with pahole passing --skip_encoding_btf_enum64 (e.g. Google's + * Container-Optimized OS / GKE kernels deliberately pass it for backward + * compatibility with older BTF consumers). The high bits + * can't be recovered from kernel BTF, so substitute the value from the + * vmlinux.h this tree was built against, cross-checked against the low 32 + * bits the kernel did provide. + * + * Note that this is a best-effort recovery, not a ground truth. The + * substitution assumes the running kernel agrees with this tree's vmlinux.h + * on the high 32 bits, but only the low 32 bits can actually be verified. + * The cross-check is vacuous for enumerators whose value has no low bits + * set (e.g. SCX_DSQ_FLAG_BUILTIN, __SCX_ENQ_INTERNAL_MASK, + * SCX_ENQ_CLEAR_OPSS, SCX_ECODE_*): their lo32 is 0 and matches anything, + * so those substitutions rest entirely on the high bits never moving. An + * enumerator missing from the table (a kernel newer than this tree's + * vmlinux.h, or a stale autogen table) can't be recovered at all. If a + * substitution is ever wrong, the scheduler operates on bogus values (e.g. + * dispatching to nonexistent DSQ ids or silently dropping flags) and can + * wildly malfunction, which is why the mismatch and table-miss paths refuse + * instead of guessing. + */ +static inline bool __COMPAT_recover_truncated_enum64(const char *type, + const char *name, + u32 lo32, u64 *v) +{ + static bool warned; + size_t i; + + for (i = 0; i < sizeof(__scx_enum_abi_vals) / sizeof(__scx_enum_abi_vals[0]); i++) { + const struct __scx_enum_abi_val *e = &__scx_enum_abi_vals[i]; + + if (strcmp(e->type, type) || strcmp(e->name, name)) + continue; + + if (e->val <= (u64)UINT32_MAX) { + *v = lo32; + return true; + } + + if ((u32)e->val != lo32) { + fprintf(stderr, "ERROR: kernel BTF value of %s::%s (0x%x) doesn't match the low 32 bits of the vmlinux.h value (0x%llx); refusing to substitute\n", + type, name, lo32, (unsigned long long)e->val); + return false; + } + + if (!warned) { + fprintf(stderr, + "WARNING: kernel BTF lacks BTF_KIND_ENUM64 encoding (generated by\n" + "WARNING: pahole < 1.24 or with --skip_encoding_btf_enum64), so 64-bit\n" + "WARNING: scx enum values are truncated to their low 32 bits in kernel\n" + "WARNING: BTF. Substituting the full 64-bit values from the vmlinux.h\n" + "WARNING: this binary was built against, cross-checked against the low\n" + "WARNING: 32 bits the kernel does provide. The high 32 bits cannot be\n" + "WARNING: verified: if the running kernel's actual values differ from\n" + "WARNING: the build-time vmlinux.h (e.g. an enum that moved in a newer\n" + "WARNING: kernel), the scheduler will operate on bogus values, such as\n" + "WARNING: dispatching to nonexistent DSQ ids, and can wildly malfunction.\n"); + warned = true; + } + *v = e->val; + return true; + } + + /* + * Unknown enumerator (likely a stale autogen table). Fail + * pessimistically to avoid returning an invalid value. + */ + fprintf(stderr, "ERROR: kernel BTF truncates 64-bit enum %s::%s to 0x%x; 64-bit variant not found in vmlinux.h\n", + type, name, lo32); + return false; +} + static inline bool __COMPAT_read_enum(const char *type, const char *name, u64 *v) { const struct btf_type *t; @@ -46,6 +130,19 @@ static inline bool __COMPAT_read_enum(const char *type, const char *name, u64 *v n = btf__name_by_offset(__COMPAT_vmlinux_btf, e[i].name_off); SCX_BUG_ON(!n, "btf__name_by_offset()"); if (!strcmp(n, name)) { + /* + * Try to recover a 64-bit enum from an 8-byte + * BTF_KIND_ENUM that was encoded without ENUM64 + * support (old pahole or + * --skip_encoding_btf_enum64). Only scx_* + * types are covered by the substitution table; + * non-scx types fall through to the raw value + * so this generic utility keeps working for + * them. + */ + if (t->size == 8 && !strncmp(type, "scx_", 4)) + return __COMPAT_recover_truncated_enum64(type, name, + (u32)e[i].val, v); *v = e[i].val; return true; } From 3c0ebc4c07ff1147724d8f370203e62390ae7ee7 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Fri, 21 Aug 2026 10:01:22 +0200 Subject: [PATCH 0076/1198] vt: hide cursor prior to font changes to avoid out-of-bound reads KASAN reports slab-out-of-bounds errors: BUG: KASAN: slab-out-of-bounds in soft_cursor+0x3eb/0xb70 drivers/video/fbdev/core/softcursor.c:70 When changing the size of a sceen font, the amount of columns and rows on a screen may change and thus the current position of the cursor and the selection may suddenly lay outside of the current screen limits. Clear the selection and hide the cursor before any font changes to avoid such possible out of bounds accesses. Reported-by: Jaeyoung Chung Signed-off-by: Helge Deller Link: https://lore.kernel.org/all/20260819163440.3702924-1-jjy600901@snu.ac.kr/ --- drivers/tty/vt/vt.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 8f467b22b799..57edf37495a8 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -4986,8 +4986,8 @@ static int con_font_set(struct vc_data *vc, const struct console_font_op *op) if (!vc->vc_sw->con_font_set) return -ENOSYS; - if (vc_is_sel(vc)) - clear_selection(); + /* hide selection and cursor prior font changes */ + hide_cursor(vc); return vc->vc_sw->con_font_set(vc, &font, vpitch, op->flags); } @@ -5011,8 +5011,9 @@ static int con_font_default(struct vc_data *vc, struct console_font_op *op) if (!vc->vc_sw->con_font_default) return -ENOSYS; - if (vc_is_sel(vc)) - clear_selection(); + /* hide selection and cursor prior font changes */ + hide_cursor(vc); + int ret = vc->vc_sw->con_font_default(vc, &font, s); if (ret) return ret; From cca061dccf563907061766191b2ce3f66b7c285a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 21 Aug 2026 09:05:52 -1000 Subject: [PATCH 0077/1198] sched_ext: Fix spurious aborts in scx_bpf_dsq_move() on ownership change races scx_dsq_move() verifies that the task belongs to the calling scheduler before taking any locks and aborts the scheduler on mismatch. The task can lose the sched association at any point: It can run and fully exit, which clears the association, or get rehomed to a different sub-sched. Both are benign races, but the early ownership check escalates them into scheduler aborts. Move the ownership check below the cursor-lost check. Every ownership change dequeues the task first, so a task that is still on the iterated DSQ under the lock while owned elsewhere indicates a genuine violation and should abort. Also fix two stale comments still referencing sched_ext_free(), which has been renamed to sched_ext_dead(). Fixes: bb4d9fd55158 ("sched_ext: scx_dsq_move() should validate the task belongs to the right scheduler") Signed-off-by: Tejun Heo --- kernel/sched/ext/ext.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c index b646711a45fe..c539d15cda63 100644 --- a/kernel/sched/ext/ext.c +++ b/kernel/sched/ext/ext.c @@ -7694,7 +7694,7 @@ static void scx_root_enable_workfn(struct kthread_work *work) /* * Enable ops for every task. Fork is excluded by scx_fork_rwsem * preventing new tasks from being added. No need to exclude tasks - * leaving as sched_ext_free() can handle both prepped and enabled + * leaving as sched_ext_dead() can handle both prepped and enabled * tasks. Prep all tasks first and then enable them with preemption * disabled. * @@ -7786,7 +7786,7 @@ static void scx_root_enable_workfn(struct kthread_work *work) /* * We're fully committed and can't fail. The task READY -> ENABLED - * transitions here are synchronized against sched_ext_free() through + * transitions here are synchronized against sched_ext_dead() through * scx_tasks_lock. */ percpu_down_write(&scx_fork_rwsem); @@ -9004,12 +9004,6 @@ static bool scx_dsq_move(struct bpf_iter_scx_dsq_kern *kit, if (unlikely(READ_ONCE(sch->aborting))) return false; - if (unlikely(!scx_task_on_sched(sch, p))) { - scx_error(sch, "scx_bpf_dsq_move[_vtime]() on %s[%d] but the task belongs to a different scheduler", - p->comm, p->pid); - return false; - } - /* * Can be called from either ops.dispatch() holding the dispatched rq's * lock or any context where no rq lock is held. If latter, lock @p's @@ -9041,6 +9035,17 @@ static bool scx_dsq_move(struct bpf_iter_scx_dsq_kern *kit, goto out; } + /* + * @p has been on $src_dsq and can't move anymore. If @p is not on @sch, + * the caller didn't have authority over @p at the time of the call. + */ + if (unlikely(!scx_task_on_sched(sch, p))) { + scx_error(sch, "scx_bpf_dsq_move[_vtime]() on %s[%d] but the task belongs to a different scheduler", + p->comm, p->pid); + raw_spin_unlock(&src_dsq->lock); + goto out; + } + /* @p is still on $src_dsq and stable, determine the destination */ dst_dsq = find_dsq_for_dispatch(sch, locked_rq ?: this_rq(), dsq_id, task_cpu(p)); From 500cb24cd61bad8a2747ddfc49b7034899c82d94 Mon Sep 17 00:00:00 2001 From: Deepanshu Kartikey Date: Sun, 16 Aug 2026 14:22:34 +0530 Subject: [PATCH 0078/1198] drm/gud: NUL-terminate TV mode names read from the device gud_connector_add_tv_mode() reads a buffer of fixed-size mode names from the USB device and passes pointers into it to drm_mode_create_tv_properties_legacy(), which calls strlen() on each one. Nothing guarantees the device NUL-terminates a name, so strlen() can run past the end of a slot and, for the last mode, past the end of the allocation. Terminate each name at the end of its slot before use. Fixes: 40e1a70b4aed ("drm: Add GUD USB Display driver") Reported-by: syzbot+916c888ba5f1a54c9526@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=916c888ba5f1a54c9526 Tested-by: syzbot+916c888ba5f1a54c9526@syzkaller.appspotmail.com Signed-off-by: Deepanshu Kartikey Acked-by: Ruben Wauters Cc: Signed-off-by: Ruben Wauters Link: https://patch.msgid.link/20260816085234.22053-1-kartikey406@gmail.com --- drivers/gpu/drm/gud/gud_connector.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/gud/gud_connector.c b/drivers/gpu/drm/gud/gud_connector.c index ea0cca58b7c8..5c0065c876a7 100644 --- a/drivers/gpu/drm/gud/gud_connector.c +++ b/drivers/gpu/drm/gud/gud_connector.c @@ -396,8 +396,13 @@ static int gud_connector_add_tv_mode(struct gud_device *gdrm, struct drm_connect } num_modes = ret / GUD_CONNECTOR_TV_MODE_NAME_LEN; - for (i = 0; i < num_modes; i++) - modes[i] = &buf[i * GUD_CONNECTOR_TV_MODE_NAME_LEN]; + for (i = 0; i < num_modes; i++) { + char *mode = &buf[i * GUD_CONNECTOR_TV_MODE_NAME_LEN]; + + /* The device is not trusted to NUL-terminate the name */ + mode[GUD_CONNECTOR_TV_MODE_NAME_LEN - 1] = '\0'; + modes[i] = mode; + } ret = drm_mode_create_tv_properties_legacy(connector->dev, num_modes, modes); free: From da1ea35fea67ad841f4ada28dd61b41be65e5437 Mon Sep 17 00:00:00 2001 From: Tao Yu Date: Wed, 19 Aug 2026 15:28:35 +0800 Subject: [PATCH 0079/1198] drm/gud: validate TV mode names before creating enum property The GUD protocol returns TV mode names as fixed-size GUD_CONNECTOR_TV_MODE_NAME_LEN entries and requires each name to be NUL-terminated. gud_connector_add_tv_mode() currently passes each fixed-size entry directly to drm_mode_create_tv_properties_legacy(), which eventually reaches drm_property_add_enum() and strlen(). If a device returns an entry without a terminating NUL byte, strlen() reads past the end of the slot and can run beyond the allocated buffer, triggering an out-of-bounds read. Validate that each returned TV mode name contains a NUL terminator within its fixed-size slot before passing it to the DRM property code. If a malformed entry is found, reject the device response with -EIO. This fixes the out-of-bounds read without changing the handling of valid devices, and avoids silently truncating malformed protocol data. Reported-by: syzbot+9ae8e7884e451eaed5b4@syzkaller.appspotmail.com Fixes: 40e1a70b4aed ("drm: Add GUD USB Display driver") Signed-off-by: Tao Yu Reviewed-by: Ruben Wauters Cc: Signed-off-by: Ruben Wauters Link: https://patch.msgid.link/20260819072835.4074130-1-tao1.yu@intel.com --- drivers/gpu/drm/gud/gud_connector.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/gud/gud_connector.c b/drivers/gpu/drm/gud/gud_connector.c index 5c0065c876a7..8141c3a1e30a 100644 --- a/drivers/gpu/drm/gud/gud_connector.c +++ b/drivers/gpu/drm/gud/gud_connector.c @@ -399,8 +399,11 @@ static int gud_connector_add_tv_mode(struct gud_device *gdrm, struct drm_connect for (i = 0; i < num_modes; i++) { char *mode = &buf[i * GUD_CONNECTOR_TV_MODE_NAME_LEN]; - /* The device is not trusted to NUL-terminate the name */ - mode[GUD_CONNECTOR_TV_MODE_NAME_LEN - 1] = '\0'; + if (!memchr(mode, '\0', GUD_CONNECTOR_TV_MODE_NAME_LEN)) { + ret = -EIO; + goto free; + } + modes[i] = mode; } From cb732d027aa18e1fcf9d2797f47d20b179ebc59c Mon Sep 17 00:00:00 2001 From: Sajal Gupta Date: Fri, 21 Aug 2026 12:46:13 +0530 Subject: [PATCH 0080/1198] drm/gud: validate GUD_ROTATION_0 is present in supported rotations The rotation argument to drm_plane_create_rotation_property() is set to DRM_MODE_ROTATE_0, and the device reported rotation bitmask is used as the supported_rotations argument. The driver never validates that GUD_ROTATION_0 is present, so a device that omits it from its GUD_PROPERTY_ROTATION triggers the WARN_ON(rotation & ~supported_rotations) in drm_plane_create_rotation_property() Fix this by skipping the creation of rotation property if the device doesn't have the GUD_ROTATION_0 bit Fixes: 40e1a70b4aed ("drm: Add GUD USB Display driver") Reported-by: syzbot+efe2810681f1b065d3a8@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=efe2810681f1b065d3a8 Tested-by: syzbot+efe2810681f1b065d3a8@syzkaller.appspotmail.com Signed-off-by: Sajal Gupta Acked-by: Ruben Wauters Signed-off-by: Ruben Wauters Link: https://patch.msgid.link/20260821071812.16500-1-sajal2005gupta@gmail.com --- drivers/gpu/drm/gud/gud_drv.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/gud/gud_drv.c b/drivers/gpu/drm/gud/gud_drv.c index 89bd6ca36003..3a1b9e2a2eaa 100644 --- a/drivers/gpu/drm/gud/gud_drv.c +++ b/drivers/gpu/drm/gud/gud_drv.c @@ -289,6 +289,8 @@ static int gud_plane_add_properties(struct gud_device *gdrm) * but mask out any additions on future devices. */ val &= GUD_ROTATION_MASK; + if (!(val & GUD_ROTATION_0)) + continue; ret = drm_plane_create_rotation_property(&gdrm->plane, DRM_MODE_ROTATE_0, val); break; From 72e91bba1190c91c76ef2f81476399eb66b87ed2 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Sat, 22 Aug 2026 11:43:08 +0200 Subject: [PATCH 0081/1198] fbdev: omapfb: Fix __be32 sparse warning in panel_enabled() This commit resolves a sparse warning in panel_enabled() by explicitly reading the display status into a __be32 variable. It then converts this value to CPU endianness using __be32_to_cpu() before checking the bits. This should fix this sparse warning: ../omapfb/displays/panel-sony-acx565akm.c:218:23: sparse: sparse: cast to restricted __be32 Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202608211811.lps93xao-lkp@intel.com/ Signed-off-by: Helge Deller --- .../video/fbdev/omap2/omapfb/displays/panel-sony-acx565akm.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/video/fbdev/omap2/omapfb/displays/panel-sony-acx565akm.c b/drivers/video/fbdev/omap2/omapfb/displays/panel-sony-acx565akm.c index 8f430d9e8054..0202ca8cbfc2 100644 --- a/drivers/video/fbdev/omap2/omapfb/displays/panel-sony-acx565akm.c +++ b/drivers/video/fbdev/omap2/omapfb/displays/panel-sony-acx565akm.c @@ -210,12 +210,13 @@ static void set_display_state(struct panel_drv_data *ddata, int enabled) static int panel_enabled(struct panel_drv_data *ddata) { + __be32 disp_status_be; u32 disp_status; int enabled; acx565akm_read(ddata, MIPID_CMD_READ_DISP_STATUS, - (u8 *)&disp_status, 4); - disp_status = __be32_to_cpu(disp_status); + (u8 *)&disp_status_be, 4); + disp_status = __be32_to_cpu(disp_status_be); enabled = (disp_status & (1 << 17)) && (disp_status & (1 << 10)); dev_dbg(&ddata->spi->dev, "LCD panel %senabled by bootloader (status 0x%04x)\n", From 94e6a058b16820e02f25e1221a4c4e713ba23550 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Sat, 22 Aug 2026 12:03:15 +0200 Subject: [PATCH 0082/1198] fbcon: Fix KASAN slab-out-of-bounds Read in fbcon_prepare_logo Ensure the logo will not exceed the screen size, which then should fix a reported KASAN: slab-out-of-bounds Read in fbcon_prepare_logo. Reported-by: syzbot+0c815b25cdb3678e7083@syzkaller.appspotmail.com Signed-off-by: Helge Deller --- drivers/video/fbdev/core/fbcon.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 23b3c536d53d..01715873ea49 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -660,6 +660,13 @@ static void fbcon_prepare_logo(struct vc_data *vc, struct fb_info *info, erase &= ~0x400; logo_height = fb_prepare_logo(info, par->rotate); logo_lines = DIV_ROUND_UP(logo_height, vc->vc_font.height); + logo_lines = min(logo_lines, rows); + logo_lines = min(logo_lines, new_rows - 1); + if (logo_lines <= 0) { + logo_lines = 0; + logo_shown = FBCON_LOGO_DONTSHOW; + return; + } q = (unsigned short *) (vc->vc_origin + vc->vc_size_row * rows); step = logo_lines * cols; From 30d0aff2c65a277135cfd8ea28fa1ee75e0ea4e0 Mon Sep 17 00:00:00 2001 From: Baineng Shou Date: Mon, 17 Aug 2026 13:04:54 +0800 Subject: [PATCH 0083/1198] dma-buf: dma-heap: don't publish fd before copy_to_user() succeeds MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit DMA_HEAP_IOCTL_ALLOC allocates a dma-buf and installs an fd into the caller's fd table via dma_buf_fd() -> fd_install() before dma_heap_ioctl() copies the result back to userspace. If the trailing copy_to_user() fails, userspace never learns the fd number, but the fd (and the underlying dma-buf reference) are already visible to other threads in the same process and are leaked for the lifetime of the process. The obvious "close it on the failure path" fix is unsafe: once fd_install() has run, another thread can already dup() the fd, send it via SCM_RIGHTS, or close() it and let its number be reused, so a subsequent close_fd() from the ioctl path can operate on an unrelated file. This was pointed out by Christian König on v1 [1]. Restructure the allocation path so that fd_install() is the last, unfailable step of a successful ioctl: 1. heap->ops->allocate() creates the dma_buf. 2. get_unused_fd_flags() reserves an fd number in the caller's fd table without publishing it, so no other thread can observe it. 3. copy_to_user() delivers the fd number to userspace; on failure the fd is returned with put_unused_fd() and the dma_buf reference is dropped with dma_buf_put(), leaving no user- visible state behind. 4. dma_buf_fd_install() publishes the fd and emits the trace_dma_buf_fd tracepoint -- from here on the ioctl cannot fail. A new dma_buf_fd_install() helper is introduced in dma-buf.c to wrap fd_install() together with the DMA_BUF_TRACE() call, preserving the export tracing that dma_buf_fd() provides. dma_heap_ioctl_allocate() is refactored to return the struct dma_buf * directly (returning ERR_PTR on failure) so the caller holds the dmabuf reference across steps 3 and 4. The failure at step 3 is easily reachable from userspace: pass a struct dma_heap_allocation_data that lives in a page whose protection is flipped to PROT_READ between copy_from_user() and copy_to_user() (e.g. via mprotect()). Before this change each such ioctl leaks one dmabuf fd; after it, the fd table is unchanged on failure and only /dev/dma_heap/ remains open. No UAPI or heap-driver interface change. [1] https://lore.kernel.org/dri-devel/175e98de-f414-47d7-81c1-c0fe0a8f7f62@amd.com/ Fixes: c02a81fba74f ("dma-buf: Add dma-buf heaps framework") Cc: stable@vger.kernel.org Reviewed-by: T.J. Mercier Acked-by: Christian König Acked-by: Sumit Semwal Signed-off-by: Baineng Shou Link: https://lore.kernel.org/r/20260817050457.1005285-2-shoubaineng@gmail.com Signed-off-by: Christian König --- drivers/dma-buf/dma-buf.c | 20 ++++++++++ drivers/dma-buf/dma-heap.c | 80 +++++++++++++++++++------------------- include/linux/dma-buf.h | 1 + 3 files changed, 61 insertions(+), 40 deletions(-) diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index d504c636dc29..4c9add51f9ef 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -803,6 +803,26 @@ int dma_buf_fd(struct dma_buf *dmabuf, int flags) } EXPORT_SYMBOL_NS_GPL(dma_buf_fd, "DMA_BUF"); +/** + * dma_buf_fd_install - install a reserved fd for a dma-buf + * @dmabuf: [in] pointer to dma_buf + * @fd: [in] fd reserved with get_unused_fd_flags() + * + * Publishes a previously reserved fd into the caller's fd table. + * Must only be called after all fallible work (e.g. copy_to_user) + * has succeeded, as it cannot be undone safely once called. + * + * The caller is responsible for having emitted the trace event + * (via dma_buf_fd() or get_unused_fd_flags() + this function) + * before calling this. + */ +void dma_buf_fd_install(struct dma_buf *dmabuf, int fd) +{ + DMA_BUF_TRACE(trace_dma_buf_fd, dmabuf, fd); + fd_install(fd, dmabuf->file); +} +EXPORT_SYMBOL_NS_GPL(dma_buf_fd_install, "DMA_BUF"); + /** * dma_buf_get - returns the struct dma_buf related to an fd * @fd: [in] fd associated with the struct dma_buf to be returned diff --git a/drivers/dma-buf/dma-heap.c b/drivers/dma-buf/dma-heap.c index a76bf3f8b071..43c32fb28313 100644 --- a/drivers/dma-buf/dma-heap.c +++ b/drivers/dma-buf/dma-heap.c @@ -55,33 +55,6 @@ MODULE_PARM_DESC(mem_accounting, "Enable cgroup-based memory accounting for dma-buf heap allocations (default=false)."); EXPORT_SYMBOL_NS_GPL(mem_accounting, "DMA_BUF_HEAP"); -static int dma_heap_buffer_alloc(struct dma_heap *heap, size_t len, - u32 fd_flags, - u64 heap_flags) -{ - struct dma_buf *dmabuf; - int fd; - - /* - * Allocations from all heaps have to begin - * and end on page boundaries. - */ - len = PAGE_ALIGN(len); - if (!len) - return -EINVAL; - - dmabuf = heap->ops->allocate(heap, len, fd_flags, heap_flags); - if (IS_ERR(dmabuf)) - return PTR_ERR(dmabuf); - - fd = dma_buf_fd(dmabuf, fd_flags); - if (fd < 0) { - dma_buf_put(dmabuf); - /* just return, as put will call release and that will free */ - } - return fd; -} - static int dma_heap_open(struct inode *inode, struct file *file) { struct dma_heap *heap; @@ -99,30 +72,42 @@ static int dma_heap_open(struct inode *inode, struct file *file) return 0; } -static long dma_heap_ioctl_allocate(struct file *file, void *data) +static struct dma_buf *dma_heap_ioctl_allocate(struct file *file, void *data) { struct dma_heap_allocation_data *heap_allocation = data; struct dma_heap *heap = file->private_data; + struct dma_buf *dmabuf; int fd; + size_t len; if (heap_allocation->fd) - return -EINVAL; + return ERR_PTR(-EINVAL); if (heap_allocation->fd_flags & ~DMA_HEAP_VALID_FD_FLAGS) - return -EINVAL; + return ERR_PTR(-EINVAL); if (heap_allocation->heap_flags & ~DMA_HEAP_VALID_HEAP_FLAGS) - return -EINVAL; + return ERR_PTR(-EINVAL); - fd = dma_heap_buffer_alloc(heap, heap_allocation->len, - heap_allocation->fd_flags, - heap_allocation->heap_flags); - if (fd < 0) - return fd; + len = PAGE_ALIGN(heap_allocation->len); + if (!len) + return ERR_PTR(-EINVAL); + + dmabuf = heap->ops->allocate(heap, len, heap_allocation->fd_flags, + heap_allocation->heap_flags); + + if (IS_ERR(dmabuf)) + return dmabuf; + + fd = get_unused_fd_flags(heap_allocation->fd_flags); + if (fd < 0) { + dma_buf_put(dmabuf); + return ERR_PTR(fd); + } heap_allocation->fd = fd; - return 0; + return dmabuf; } static unsigned int dma_heap_ioctl_cmds[] = { @@ -138,6 +123,8 @@ static long dma_heap_ioctl(struct file *file, unsigned int ucmd, unsigned int in_size, out_size, drv_size, ksize; int nr = _IOC_NR(ucmd); int ret = 0; + int fd; + struct dma_buf *dmabuf; if (nr >= ARRAY_SIZE(dma_heap_ioctl_cmds)) return -EINVAL; @@ -174,15 +161,28 @@ static long dma_heap_ioctl(struct file *file, unsigned int ucmd, switch (kcmd) { case DMA_HEAP_IOCTL_ALLOC: - ret = dma_heap_ioctl_allocate(file, kdata); + dmabuf = dma_heap_ioctl_allocate(file, kdata); + + if (IS_ERR(dmabuf)) { + ret = PTR_ERR(dmabuf); + break; + } + + fd = ((struct dma_heap_allocation_data *)kdata)->fd; + if (copy_to_user((void __user *)arg, kdata, out_size) != 0) { + put_unused_fd(fd); + dma_buf_put(dmabuf); + ret = -EFAULT; + } else { + dma_buf_fd_install(dmabuf, fd); + } + break; default: ret = -ENOTTY; goto err; } - if (copy_to_user((void __user *)arg, kdata, out_size) != 0) - ret = -EFAULT; err: if (kdata != stack_kdata) kfree(kdata); diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index d1203da56fc5..d15b2b31d3c9 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -567,6 +567,7 @@ void dma_buf_unpin(struct dma_buf_attachment *attach); struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info); int dma_buf_fd(struct dma_buf *dmabuf, int flags); +void dma_buf_fd_install(struct dma_buf *dmabuf, int fd); struct dma_buf *dma_buf_get(int fd); void dma_buf_put(struct dma_buf *dmabuf); From a4a1a2bfcb29785292d634d7787edc6fb550714d Mon Sep 17 00:00:00 2001 From: Baineng Shou Date: Mon, 17 Aug 2026 13:04:55 +0800 Subject: [PATCH 0084/1198] misc: fastrpc: don't publish fd before copy_to_user() succeeds MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit fastrpc_ioctl_alloc_dmabuf() calls dma_buf_fd() which installs the fd into the caller's fd table before copy_to_user() copies the fd number back to userspace. If copy_to_user() fails, the fd is already visible to other threads in the same process but the ioctl returns -EFAULT. The existing comment in the code even acknowledges the problem: "The usercopy failed, but we can't do much about it, as dma_buf_fd() already called fd_install()..." Now that dma_buf_fd_install() is available (introduced to fix the same issue in dma-heap), apply the same pattern here: reserve the fd with get_unused_fd_flags(), attempt copy_to_user(), and only on success call dma_buf_fd_install() to publish it atomically with the tracepoint. On copy_to_user() failure, put_unused_fd() and dma_buf_put() cleanly unwind without any user-visible side effects. Fixes: 6cffd79504ce ("misc: fastrpc: Add support for dmabuf exporter") Cc: stable@vger.kernel.org Acked-by: Christian König Acked-by: Sumit Semwal Signed-off-by: Baineng Shou Link: https://lore.kernel.org/r/20260817050457.1005285-3-shoubaineng@gmail.com Signed-off-by: Christian König --- drivers/misc/fastrpc.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index eb6c2a78d3c7..d7a9e12f5575 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -1712,24 +1712,20 @@ static int fastrpc_dmabuf_alloc(struct fastrpc_user *fl, char __user *argp) return err; } - bp.fd = dma_buf_fd(buf->dmabuf, O_ACCMODE); + bp.fd = get_unused_fd_flags(O_ACCMODE); if (bp.fd < 0) { dma_buf_put(buf->dmabuf); - return -EINVAL; + return bp.fd; } if (copy_to_user(argp, &bp, sizeof(bp))) { - /* - * The usercopy failed, but we can't do much about it, as - * dma_buf_fd() already called fd_install() and made the - * file descriptor accessible for the current process. It - * might already be closed and dmabuf no longer valid when - * we reach this point. Therefore "leak" the fd and rely on - * the process exit path to do any required cleanup. - */ + put_unused_fd(bp.fd); + dma_buf_put(buf->dmabuf); return -EFAULT; } + dma_buf_fd_install(buf->dmabuf, bp.fd); + return 0; } From 3e164bf592bbbdde269c5cadc60a96f69cc6eed7 Mon Sep 17 00:00:00 2001 From: Baineng Shou Date: Mon, 17 Aug 2026 13:04:56 +0800 Subject: [PATCH 0085/1198] drm/prime: use dma_buf_fd_install() to preserve export tracing MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit drm_gem_prime_handle_to_fd() open-codes fd reservation and install using get_unused_fd_flags() + fd_install() directly. This bypasses the DMA_BUF_TRACE() call that dma_buf_fd() emits, so observability tools relying on the trace_dma_buf_fd tracepoint silently miss all DRM PRIME exports. Replace the bare fd_install() with dma_buf_fd_install(), which wraps fd_install() together with DMA_BUF_TRACE(), restoring full tracepoint coverage. No functional change; the fd lifecycle (get_unused_fd_flags → work → install) is already correct. Note: this patch depends on dma_buf_fd_install() introduced in "dma-buf: dma-heap: don't publish fd before copy_to_user() succeeds" [1]. [1] https://lore.kernel.org/dri-devel/20260714114654.3885457-2-shoubaineng@gmail.com/ Suggested-by: Christian König Acked-by: Sumit Semwal Reviewed-by: Christian König Signed-off-by: Baineng Shou Link: https://lore.kernel.org/r/20260817050457.1005285-4-shoubaineng@gmail.com Signed-off-by: Christian König --- drivers/gpu/drm/drm_prime.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 9b44c78cd77f..fe3436d1235d 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -524,7 +524,7 @@ int drm_gem_prime_handle_to_fd(struct drm_device *dev, return PTR_ERR(dmabuf); } - fd_install(fd, dmabuf->file); + dma_buf_fd_install(dmabuf, fd); *prime_fd = fd; return 0; } From 8985cbc927fd3e23dfebaa099ae0b6d2b38d3258 Mon Sep 17 00:00:00 2001 From: Baineng Shou Date: Mon, 17 Aug 2026 13:04:57 +0800 Subject: [PATCH 0086/1198] selftests: dmabuf-heaps: add fd-leak-on-EFAULT regression test MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a test case that verifies no file descriptor is leaked when DMA_HEAP_IOCTL_ALLOC succeeds internally but copy_to_user() fails to deliver the fd number back to userspace. The failure is triggered by placing the ioctl argument in a private anonymous page and flipping it to PROT_READ (via mprotect) between the kernel's copy_from_user() and copy_to_user() calls. With the buggy kernel the ioctl returns -EFAULT but leaves an extra open fd in the process's fd table; with the fixed kernel the fd count is unchanged. This serves as a regression test for: "dma-buf: dma-heap: don't publish fd before copy_to_user() succeeds" Suggested-by: Sumit Semwal Reviewed-by: T.J. Mercier Acked-by: Sumit Semwal Signed-off-by: Baineng Shou Link: https://lore.kernel.org/r/20260817050457.1005285-5-shoubaineng@gmail.com Signed-off-by: Christian König --- .../selftests/dmabuf-heaps/dmabuf-heap.c | 113 +++++++++++++++++- 1 file changed, 112 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c index fc9694fc4e89..1d49df671919 100644 --- a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c +++ b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c @@ -390,6 +390,116 @@ static void test_alloc_errors(char *heap_name) close(heap_fd); } +/* + * count_open_fds - return the number of open file descriptors. + * + * The fd opened by opendir() itself is counted, but since it is opened + * and closed within each call, it cancels out when comparing two counts. + * Returns -1 on error. + */ +static int count_open_fds(void) +{ + DIR *d = opendir("/proc/self/fd"); + struct dirent *de; + int count = 0; + + if (!d) + return -1; + + while ((de = readdir(d))) + if (de->d_name[0] != '.') + count++; + closedir(d); + return count; +} + +/* + * test_alloc_no_fd_leak_on_efault - verify no fd is leaked when + * copy_to_user() fails during DMA_HEAP_IOCTL_ALLOC. + * + * The bug: dma_buf_fd() called fd_install() before copy_to_user(). + * If copy_to_user() then failed (e.g. via mprotect), the fd was + * silently installed in the fd table but never returned to userspace. + * + * The fix: reserve the fd with get_unused_fd_flags() first, attempt + * copy_to_user(), and only call fd_install() on success. + * + * We trigger the failure by placing the ioctl argument in a private + * anonymous page and flipping it to PROT_READ before the ioctl. + * Inside the kernel, copy_from_user() reads from the page (reads are + * allowed under PROT_READ, so it succeeds), but copy_to_user() that + * writes the fd number back faults, returning -EFAULT. We then + * count open file descriptors before and after; with the bug an extra + * fd is left in the table. + */ +static void test_alloc_no_fd_leak_on_efault(char *heap_name) +{ + int heap_fd = -1; + int fd_before, fd_after; + int ret; + long page_size; + struct dma_heap_allocation_data *req; + + ksft_print_msg("Testing fd leak when copy_to_user() fails:\n"); + + heap_fd = dmabuf_heap_open(heap_name); + + page_size = sysconf(_SC_PAGESIZE); + + /* + * Place the ioctl argument in its own private anonymous page so + * we can flip its protection independently. + */ + req = mmap(NULL, page_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (req == MAP_FAILED) { + ksft_test_result_fail("mmap failed: %s\n", strerror(errno)); + goto out; + } + + memset(req, 0, sizeof(*req)); + req->len = page_size; + req->fd_flags = O_RDWR | O_CLOEXEC; + + fd_before = count_open_fds(); + if (fd_before < 0) { + ksft_test_result_fail("count_open_fds: %s\n", strerror(errno)); + munmap(req, page_size); + goto out; + } + + /* + * Make the page read-only so copy_to_user() will fault. The + * ioctl must fail with -1; if it returns success the test setup + * is broken (mprotect is synchronous, so there is no race). + */ + mprotect(req, page_size, PROT_READ); + + ret = ioctl(heap_fd, DMA_HEAP_IOCTL_ALLOC, req); + + /* Re-allow writes so munmap can clean up */ + mprotect(req, page_size, PROT_READ | PROT_WRITE); + munmap(req, page_size); + + if (ret != -1) { + ksft_test_result_fail("ioctl returned %d, expected -1 EFAULT\n", + ret); + goto out; + } + + fd_after = count_open_fds(); + if (fd_after < 0) { + ksft_test_result_fail("count_open_fds: %s\n", strerror(errno)); + goto out; + } + + ksft_test_result(fd_before == fd_after, + "fd leak on EFAULT: before=%d after=%d\n", + fd_before, fd_after); +out: + close(heap_fd); +} + static int numer_of_heaps(void) { DIR *d = opendir(DEVPATH); @@ -420,7 +530,7 @@ int main(void) return KSFT_SKIP; } - ksft_set_plan(11 * numer_of_heaps()); + ksft_set_plan(12 * numer_of_heaps()); while ((dir = readdir(d))) { if (!strncmp(dir->d_name, ".", 2)) @@ -435,6 +545,7 @@ int main(void) test_alloc_zeroed(dir->d_name, ONE_MEG); test_alloc_compat(dir->d_name); test_alloc_errors(dir->d_name); + test_alloc_no_fd_leak_on_efault(dir->d_name); } closedir(d); From 72dd0ec09e7cc98ed58ddeac26575e5d1ab8a93d Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Tue, 4 Aug 2026 22:52:19 +0900 Subject: [PATCH 0087/1198] printk: Don't WARN on kthread_run failure. Since __kthread_create_on_node() returns -EINTR upon SIGKILL, we should not use WARN_ON() in order to catch kthread_run() failure. Reported-by: syzbot+1ebbc20f223b99446034@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=1ebbc20f223b99446034 Fixes: 5f53ca3ff83b ("printk: Implement legacy printer kthread for PREEMPT_RT") Fixes: 76f258bf3f2a ("printk: nbcon: Introduce printer kthreads") Signed-off-by: Tetsuo Handa Reviewed-by: John Ogness Reviewed-by: Petr Mladek Link: https://patch.msgid.link/76bb4c1c-5d85-4635-b3bb-fc06f292c59e@I-love.SAKURA.ne.jp Signed-off-by: Petr Mladek --- kernel/printk/nbcon.c | 2 +- kernel/printk/printk.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/printk/nbcon.c b/kernel/printk/nbcon.c index 4b03b019cd5e..a5921a84a80e 100644 --- a/kernel/printk/nbcon.c +++ b/kernel/printk/nbcon.c @@ -1382,7 +1382,7 @@ bool nbcon_kthread_create(struct console *con) return true; kt = kthread_run(nbcon_kthread_func, con, "pr/%s%d", con->name, con->index); - if (WARN_ON(IS_ERR(kt))) { + if (IS_ERR(kt)) { con_printk(KERN_ERR, con, "failed to start printing thread\n"); return false; } diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 3fcdf4b4e2e5..6d3d18a50da7 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -3732,7 +3732,7 @@ static bool legacy_kthread_create(void) lockdep_assert_console_list_lock_held(); kt = kthread_run(legacy_kthread_func, NULL, "pr/legacy"); - if (WARN_ON(IS_ERR(kt))) { + if (IS_ERR(kt)) { pr_err("failed to start legacy printing thread\n"); return false; } From b3709d354545e70388177500761f92d906c4dfd6 Mon Sep 17 00:00:00 2001 From: Lizhi Hou Date: Thu, 20 Aug 2026 20:35:43 -0700 Subject: [PATCH 0088/1198] accel/amdxdna: Remove __counted_by from struct amdxdna_cmd_chain struct amdxdna_cmd_chain contains a flexible array annotated with __counted_by(command_count). Since the structure is stored in shared AMDXDNA_BO_SHARE memory, userspace can modify command_count concurrently. If command_count is changed to zero, the bounds check generated from __counted_by may fail and trigger a kernel panic. Remove __counted_by to avoid relying on the userspace-controlled command_count for the flexible array bounds check. Fixes: aac243092b70 ("accel/amdxdna: Add command execution") Reviewed-by: Max Zhen Signed-off-by: Lizhi Hou Link: https://patch.msgid.link/20260821033543.1839719-1-lizhi.hou@amd.com --- drivers/accel/amdxdna/amdxdna_ctx.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/accel/amdxdna/amdxdna_ctx.h b/drivers/accel/amdxdna/amdxdna_ctx.h index b6bef3af7dab..6e78bab8a02c 100644 --- a/drivers/accel/amdxdna/amdxdna_ctx.h +++ b/drivers/accel/amdxdna/amdxdna_ctx.h @@ -55,7 +55,7 @@ struct amdxdna_cmd_chain { u32 submit_index; u32 error_index; u32 reserved[3]; - u64 data[] __counted_by(command_count); + u64 data[]; }; /* From ef6d27af71e1dc43181ec797a6aaa77c27c36786 Mon Sep 17 00:00:00 2001 From: Taimuraz Kaitmazov Date: Tue, 18 Aug 2026 03:00:19 +0300 Subject: [PATCH 0089/1198] accel/amdxdna: reject a command chain that carries no commands A chain whose command_count is zero passes the payload length check, because struct_size(payload, data, 0) is just the header. The fill loop then does not run, so offset stays zero and the request is submitted with a zero-length buffer. On firmware without AIE2_NPU_COMMAND that ends at the opcode check, since op is still ERT_INVALID_CMD and aie2_get_chain_msg_op() answers MSG_OP_MAX_OPCODE. aie2_get_npu_chain_msg_op() answers MSG_OP_CHAIN_EXEC_NPU whatever it is given, so there the submission continues to drm_clflush_virt_range(cmd_buf, 0), which reads the byte before the buffer and faults on the vmap guard page. EXEC_CMD is reachable by any process that can open the render node. Reject the request instead. Fixes: 8ed8b0239617 ("accel/amdxdna: Add debug prints for command submission") Signed-off-by: Taimuraz Kaitmazov Reviewed-by: Lizhi Hou Signed-off-by: Lizhi Hou Link: https://patch.msgid.link/20260818000019.369366-1-taimuraz@kaitmazov.com --- drivers/accel/amdxdna/aie2_message.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/accel/amdxdna/aie2_message.c b/drivers/accel/amdxdna/aie2_message.c index dfe0fbdf066d..b4c49259a1a2 100644 --- a/drivers/accel/amdxdna/aie2_message.c +++ b/drivers/accel/amdxdna/aie2_message.c @@ -994,7 +994,7 @@ int aie2_cmdlist_multi_execbuf(struct amdxdna_hwctx *hwctx, } ccnt = payload->command_count; - if (payload_len < struct_size(payload, data, ccnt)) { + if (!ccnt || payload_len < struct_size(payload, data, ccnt)) { XDNA_DBG(xdna, "Invalid command count %d", ccnt); return -EINVAL; } From 7e33ba3a1d48c2d20ed270dec9d2d08332585c8e Mon Sep 17 00:00:00 2001 From: Taimuraz Kaitmazov Date: Thu, 20 Aug 2026 02:08:52 +0300 Subject: [PATCH 0090/1198] accel/amdxdna: put the chained BO when its mapping fails amdxdna_cmd_set_error() looks up the first BO of a command chain, which takes a reference, and drops it at the end of the function. The mapping of that BO is established in between, and the failure path returns without the put, so the reference is leaked. Ordinary use does not reach it. The chain has been submitted before any of this runs, so aie2_cmdlist_fill_slot() has already called amdxdna_cmd_get_op() on that BO and amdxdna_gem_vmap() has cached its address. What makes it reachable is that the BO is resolved again by handle here, and the handle is userspace's to recycle: closing it after submission and importing a dma-buf whose exporter implements no vmap onto the same id leaves amdxdna_gem_get_obj() returning an object this cannot map, since prime_import() types every import AMDXDNA_BO_SHARE. Fixes: d76856beb4a4 ("accel/amdxdna: Refactor GEM BO handling and add helper APIs for address retrieval") Signed-off-by: Taimuraz Kaitmazov Reviewed-by: Lizhi Hou Signed-off-by: Lizhi Hou Link: https://patch.msgid.link/20260819230852.287751-1-taimuraz@kaitmazov.com --- drivers/accel/amdxdna/amdxdna_ctx.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/accel/amdxdna/amdxdna_ctx.c b/drivers/accel/amdxdna/amdxdna_ctx.c index 31a414c3f0d9..888e857ec558 100644 --- a/drivers/accel/amdxdna/amdxdna_ctx.c +++ b/drivers/accel/amdxdna/amdxdna_ctx.c @@ -183,8 +183,10 @@ int amdxdna_cmd_set_error(struct amdxdna_gem_obj *abo, if (!abo) return -EINVAL; cmd = amdxdna_gem_vmap(abo); - if (!cmd) + if (!cmd) { + amdxdna_gem_put_obj(abo); return -ENOMEM; + } } memset(cmd->data, 0xff, abo->mem.size - sizeof(*cmd)); From 909a3f0e9d8b0d8001cf6e99808f88eca8e44328 Mon Sep 17 00:00:00 2001 From: Cheng Lingfei Date: Mon, 24 Aug 2026 20:45:46 +0800 Subject: [PATCH 0091/1198] docs: cgroup-v2: fix misc.events key format description MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In misc cgroup, misc.events does not output a simple "max" key. Instead, each registered misc resource outputs a separate key suffixed with ".max" (i.e., ".max"). Update the documentation to clarify that the entry key is ".max". Suggested-by: Michal Koutný Signed-off-by: Cheng Lingfei Signed-off-by: Tejun Heo --- Documentation/admin-guide/cgroup-v2.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 0a4f4eb15626..2ec582985b5b 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -3019,7 +3019,7 @@ Miscellaneous controller provides 3 interface files. If two misc resources (res_ change in this file generates a file modified event. All fields in this file are hierarchical. - max + .max The number of times the cgroup's resource usage was about to go over the max boundary. From 2bf404b1bd94f50747443234c0a4a5e18e2569bf Mon Sep 17 00:00:00 2001 From: Guopeng Zhang Date: Mon, 24 Aug 2026 10:01:38 +0800 Subject: [PATCH 0092/1198] selftests/cgroup: Drop invalid boot isolation comparison check_isolcpus() clears ISOLCPUS before rebuilding it from sched domain data. Comparing that empty value with /sys/devices/system/cpu/isolated makes the test fail whenever isolcpus=domain is present. That sysfs file is generated from HK_TYPE_DOMAIN_BOOT and does not change when cpuset updates HK_TYPE_DOMAIN. Re-reading it cannot validate dynamic housekeeping updates. The cpuset.cpus.isolated and sched domain checks already cover the two dynamic interfaces, so remove the invalid comparison. This can be reproduced on a kernel booted with isolcpus=domain,15: # tools/testing/selftests/cgroup/test_cpuset_prs.sh The test fails its first state-matrix isolation check before the change and continues past that check afterward. Fixes: 6df415aa46ec ("cgroup/cpuset: Defer housekeeping_update() calls from CPU hotplug to workqueue") Signed-off-by: Guopeng Zhang Reviewed-by: Waiman Long Signed-off-by: Tejun Heo --- tools/testing/selftests/cgroup/test_cpuset_prs.sh | 6 ------ 1 file changed, 6 deletions(-) diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh index da8f7b920178..fdb3185570d4 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -797,7 +797,6 @@ check_isolcpus() EXPECTED_ISOLCPUS=$1 ISCPUS=${CGROUP2}/cpuset.cpus.isolated ISOLCPUS=$(cat $ISCPUS) - HKICPUS=$(cat /sys/devices/system/cpu/isolated) LASTISOLCPU= SCHED_DOMAINS=/sys/kernel/debug/sched/domains if [[ $EXPECTED_ISOLCPUS = . ]] @@ -835,11 +834,6 @@ check_isolcpus() ISOLCPUS= EXPECTED_ISOLCPUS=$EXPECTED_SDOMAIN - # - # The inverse of HK_TYPE_DOMAIN cpumask in $HKICPUS should match $ISOLCPUS - # - [[ "$ISOLCPUS" != "$HKICPUS" ]] && return 1 - # # Use the sched domain in debugfs to check isolated CPUs, if available # From 6c37d7e074a4be1ba8da59f4ed5df8977b3daa43 Mon Sep 17 00:00:00 2001 From: Guopeng Zhang Date: Mon, 24 Aug 2026 10:01:39 +0800 Subject: [PATCH 0093/1198] cgroup/cpuset: Preserve boot-isolated CPUs on partition release isolated_cpus tracks CPUs isolated with isolcpus= as well as CPUs in isolated cpuset partitions. When an isolated partition is released, isolated_cpus_update() removes its whole CPU mask. This also clears CPUs which were already isolated at boot. This can be reproduced on a cgroup v2 system booted with isolcpus=domain,15: cd /sys/fs/cgroup echo +cpuset > cgroup.subtree_control mkdir cpuset-repro echo 15 > cpuset-repro/cpuset.cpus echo isolated > cpuset-repro/cpuset.cpus.partition echo member > cpuset-repro/cpuset.cpus.partition cat cpuset.cpus.isolated CPU 15 is absent before the change. It must remain in cpuset.cpus.isolated after the partition is released. Update isolated_cpus one CPU at a time and keep CPUs outside the boot-time domain housekeeping mask isolated. Fixes: c188f33c864e ("cgroup/cpuset: Account for boot time isolated CPUs") Signed-off-by: Guopeng Zhang Acked-by: Waiman Long Signed-off-by: Tejun Heo --- kernel/cgroup/cpuset.c | 39 +++++++++++++++++++++++++++++---------- 1 file changed, 29 insertions(+), 10 deletions(-) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 0c34013eda8e..8f24171b6055 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1259,6 +1259,28 @@ static void reset_partition_data(struct cpuset *cs) cpumask_copy(cs->effective_cpus, parent->effective_cpus); } +/* Return true if isolated_cpus changes. */ +static bool isolated_cpu_update(int new_prs, int cpu) +{ + lockdep_assert_held(&callback_lock); + lockdep_assert_held(&cpuset_mutex); + + if (new_prs == PRS_ISOLATED) { + if (cpumask_test_cpu(cpu, isolated_cpus)) + return false; + cpumask_set_cpu(cpu, isolated_cpus); + return true; + } + + /* CPUs isolated at boot must remain isolated. */ + if (!cpumask_test_cpu(cpu, + housekeeping_cpumask(HK_TYPE_DOMAIN_BOOT)) || + !cpumask_test_cpu(cpu, isolated_cpus)) + return false; + cpumask_clear_cpu(cpu, isolated_cpus); + return true; +} + /* * isolated_cpus_update - Update the isolated_cpus mask * @old_prs: old partition_root_state @@ -1267,19 +1289,16 @@ static void reset_partition_data(struct cpuset *cs) */ static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus) { + bool updated = false; + int cpu; + WARN_ON_ONCE(old_prs == new_prs); lockdep_assert_held(&callback_lock); lockdep_assert_held(&cpuset_mutex); - if (new_prs == PRS_ISOLATED) { - if (cpumask_subset(xcpus, isolated_cpus)) - return; - cpumask_or(isolated_cpus, isolated_cpus, xcpus); - } else { - if (!cpumask_intersects(xcpus, isolated_cpus)) - return; - cpumask_andnot(isolated_cpus, isolated_cpus, xcpus); - } - update_housekeeping = true; + for_each_cpu(cpu, xcpus) + updated |= isolated_cpu_update(new_prs, cpu); + if (updated) + update_housekeeping = true; } /* From 87d347a8c8545a9234d1dd215023064413284c34 Mon Sep 17 00:00:00 2001 From: Guopeng Zhang Date: Mon, 24 Aug 2026 10:01:40 +0800 Subject: [PATCH 0094/1198] selftests/cgroup: Add test for preserving boot-isolated CPUs Put a CPU isolated at boot into an isolated partition, change the partition back to member and check that the CPU remains isolated. Signed-off-by: Guopeng Zhang Reviewed-by: Waiman Long Signed-off-by: Tejun Heo --- .../selftests/cgroup/test_cpuset_prs.sh | 58 +++++++++++++++++++ 1 file changed, 58 insertions(+) diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh index fdb3185570d4..131d8b4551ef 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -1155,6 +1155,63 @@ test_isolated() pause 0.05 } +# +# Select an online CPU isolated from scheduler domains at boot. +# $1: test name used in the skip message +# +get_boot_isolated_cpu() +{ + TEST_NAME=$1 + BOOT_ISOLATED_FILE=/sys/devices/system/cpu/isolated + + [[ -r $BOOT_ISOLATED_FILE ]] || { + echo "$TEST_NAME test SKIPPED: boot isolation state unavailable" + return 1 + } + BOOT_CPUS=$(cat $BOOT_ISOLATED_FILE) + [[ -n "$BOOT_CPUS" ]] || { + echo "$TEST_NAME test SKIPPED: no boot-isolated CPU" + return 1 + } + + BOOT_CPU=$(echo "$BOOT_CPUS" | sed -e 's/[,-].*//') + CPU_ONLINE=/sys/devices/system/cpu/cpu${BOOT_CPU}/online + [[ ! -e $CPU_ONLINE || $(cat $CPU_ONLINE) -eq 1 ]] || { + echo "$TEST_NAME test SKIPPED: CPU $BOOT_CPU is offline" + return 1 + } +} + +# +# A CPU isolated at boot must stay isolated after it is released by a dynamic +# isolated partition. +# +test_boot_isolated() +{ + TEST_NAME="Boot-isolated CPU partition release" + get_boot_isolated_cpu "$TEST_NAME" || return 0 + echo "Running $TEST_NAME test ..." + + cd $CGROUP2/test + echo member > cpuset.cpus.partition + echo $BOOT_CPU > cpuset.cpus + [[ $(cat cpuset.cpus.effective) = "$BOOT_CPU" ]] || { + echo "$TEST_NAME test SKIPPED: CPU $BOOT_CPU is unavailable" + echo "" > cpuset.cpus + cd $CGROUP2 + return 0 + } + test_partition isolated + test_partition member + check_isolcpus "." || { + echo "Boot-isolated CPU $BOOT_CPU was lost after partition release" + exit 1 + } + echo "" > cpuset.cpus + cd $CGROUP2 + echo "$TEST_NAME test PASSED." +} + # # Wait for inotify event for the given file and read it # $1: cgroup file to wait for @@ -1226,5 +1283,6 @@ trap cleanup 0 2 3 6 run_state_test TEST_MATRIX run_remote_state_test REMOTE_TEST_MATRIX test_isolated +test_boot_isolated test_inotify echo "All tests PASSED." From 6586705bc2dc06908309bf65d79efa53a347c9f0 Mon Sep 17 00:00:00 2001 From: Tao Cui Date: Mon, 24 Aug 2026 21:21:16 +0800 Subject: [PATCH 0095/1198] docs/sched_ext: document that cgroup CPU knobs are scheduler-dependent The scheduler core communicates the initial cpu controller settings to the BPF scheduler through ops.cgroup_init() and reports subsequent changes through the corresponding ops.cgroup_set_*() callbacks. Whether and how a knob takes effect is up to the loaded scheduler: it may implement the corresponding callback partially or not at all, so cpu.max, cpu.weight and friends can silently have no effect. Document this in the basics section of sched-ext.rst. Signed-off-by: Tao Cui Reviewed-by: Andrea Righi Signed-off-by: Tejun Heo --- Documentation/scheduler/sched-ext.rst | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/Documentation/scheduler/sched-ext.rst b/Documentation/scheduler/sched-ext.rst index 35b550671ca7..794ae80b3ba3 100644 --- a/Documentation/scheduler/sched-ext.rst +++ b/Documentation/scheduler/sched-ext.rst @@ -242,6 +242,21 @@ optional. The following modified excerpt is from .name = "simple", }; +Scheduler-Dependent Knobs +------------------------- + +The fair-class scheduler enforces CPU controller settings such as +``cpu.max``, ``cpu.weight`` and ``cpu.idle``. For sched_ext tasks, the +scheduler core communicates these settings to the BPF scheduler +through ``ops.cgroup_init()`` and reports subsequent changes through +the corresponding ``ops.cgroup_set_*()`` callbacks. Similarly, per-task +nice changes are converted to weights and reported through +``ops.set_weight()``. + +Each BPF scheduler is responsible for implementing the scheduling +semantics of these settings and may choose to ignore them. Consult the +loaded scheduler's documentation before relying on these controls. + Dispatch Queues --------------- From cf9c8aaea0d47410df8708bec195889f3a85cd3c Mon Sep 17 00:00:00 2001 From: Yao Kai Date: Mon, 24 Aug 2026 11:58:52 +0800 Subject: [PATCH 0096/1198] workqueue: Fix unbound pool lifetime for pending pwqs KASAN reports a use-after-free of an unbound worker_pool in node_activate_pending_pwq(): BUG: KASAN: slab-use-after-free in _raw_spin_trylock+0x6d/0x120 Read of size 4 at addr ffff8880089ce000 by task kworker/u22:0/318 CPU: 1 UID: 0 PID: 318 Comm: kworker/u22:0 Not tainted 7.2.0 #1 PREEMPT(lazy) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 Workqueue: 0x0 (flush-8:0) Call Trace: dump_stack_lvl+0x53/0x70 print_report+0xce/0x610 kasan_report+0xce/0x100 _raw_spin_trylock+0x6d/0x120 pwq_dec_nr_in_flight+0x4b4/0xcb0 process_one_work+0x921/0x11a0 worker_thread+0x4d0/0xd20 kthread+0x2de/0x3c0 ret_from_fork+0x3aa/0x620 ret_from_fork_asm+0x1a/0x30 Allocated by task 311: alloc_pwq+0x439/0xca0 apply_wqattrs_prepare+0x75e/0xd10 apply_workqueue_attrs_locked+0x44/0xa0 wq_nice_store+0x350/0x450 Freed by task 0: kfree+0x127/0x3b0 rcu_core+0x523/0x1780 handle_softirqs+0x1b3/0x610 Last potentially related work creation: put_unbound_pool+0x3f3/0x7d0 pwq_release_workfn+0x494/0x8e0 kthread_worker_fn+0x1ff/0x790 Canceling the last inactive work skips pwq_dec_nr_active(), so an empty pwq can remain on pending_pwqs when its refcnt reaches zero. pwq_release_workfn() currently puts the pool before removing that pwq. If this drops the last pool reference, the pool can be RCU-freed while the pwq remains reachable, and node_activate_pending_pwq() may trylock the freed pool->lock. Remove the pwq from pending_pwqs before putting the pool. Fixes: 5797b1c18919 ("workqueue: Implement system-wide nr_active enforcement for unbound workqueues") Cc: stable@vger.kernel.org Signed-off-by: Yao Kai Signed-off-by: Tejun Heo --- kernel/workqueue.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index f2aed36cf7c0..0ee73dcd4a14 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -5294,12 +5294,6 @@ static void pwq_release_workfn(struct kthread_work *work) mutex_unlock(&wq->mutex); } - if (!is_percpu_pool(pool)) { - mutex_lock(&wq_pool_mutex); - put_unbound_pool(pool); - mutex_unlock(&wq_pool_mutex); - } - if (!list_empty(&pwq->pending_node)) { struct wq_node_nr_active *nna = wq_node_nr_active(pwq->wq, pwq->pool->node); @@ -5309,6 +5303,12 @@ static void pwq_release_workfn(struct kthread_work *work) raw_spin_unlock_irq(&nna->lock); } + if (!is_percpu_pool(pool)) { + mutex_lock(&wq_pool_mutex); + put_unbound_pool(pool); + mutex_unlock(&wq_pool_mutex); + } + kfree_rcu(pwq, rcu); /* From 7ab64476a610fe65858fdc37c7a30caa13e334ac Mon Sep 17 00:00:00 2001 From: GuoHan Zhao Date: Thu, 16 Jul 2026 14:52:19 +0800 Subject: [PATCH 0097/1198] accel/ethosu: check MMIO mapping errors in probe devm_platform_ioremap_resource() returns an error pointer when the register resource cannot be mapped. ethosu_probe() stores it and continues until initialization dereferences it through MMIO accessors. Return the mapping error before initializing the device. Fixes: 5a5e9c0228e6 ("accel: Add Arm Ethos-U NPU driver") Cc: stable@vger.kernel.org Signed-off-by: GuoHan Zhao Link: https://patch.msgid.link/20260716065219.931088-1-zhaoguohan@kylinos.cn Signed-off-by: Rob Herring (Arm) --- drivers/accel/ethosu/ethosu_drv.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/accel/ethosu/ethosu_drv.c b/drivers/accel/ethosu/ethosu_drv.c index ed9c748a54ad..b2901eb8a7a0 100644 --- a/drivers/accel/ethosu/ethosu_drv.c +++ b/drivers/accel/ethosu/ethosu_drv.c @@ -342,6 +342,8 @@ static int ethosu_probe(struct platform_device *pdev) dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(40)); ethosudev->regs = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(ethosudev->regs)) + return PTR_ERR(ethosudev->regs); ethosudev->num_clks = devm_clk_bulk_get_all(&pdev->dev, ðosudev->clks); if (ethosudev->num_clks < 0) From db9deec5a345abc538d081fb221dc0b00a9695bd Mon Sep 17 00:00:00 2001 From: Tomeu Vizoso Date: Mon, 24 Aug 2026 17:26:11 +0200 Subject: [PATCH 0098/1198] accel: ethosu: Don't read the U65 rounding mode as a storage mode Bits 15:14 of NPU_SET_{IFM,OFM}_PRECISION select the activation storage mode on U85 only. On U65 the same field holds the rounding mode, and the command stream parser has read it as a storage mode since the driver was added. That went unnoticed while unknown values fell through the switch, but now that they are rejected, every U65 command stream that asks for natural rounding (2) fails CMDSTREAM_BO_CREATE with -EINVAL. Mesa emits it for average pooling, concatenation, split, unpack, strided slice, LUT and argmax, which is 72 failures of the Teflon test suite on an i.MX93. Truncating rounding (1) is misread as well: it picks the two-tile address path and computes a bogus feature map size from tile bases the command stream never set. Read the field as a storage mode only on the hardware where it is one. Fixes: 5a5e9c0228e6 ("accel: Add Arm Ethos-U NPU driver") Fixes: 6b7e0066294d ("accel: ethosu: Handle U85 internal chaining buffer") Assisted-by: Claude:claude-opus-5 Signed-off-by: Tomeu Vizoso Link: https://patch.msgid.link/20260824152612.751007-1-tomeu@tomeuvizoso.net Signed-off-by: Rob Herring (Arm) --- drivers/accel/ethosu/ethosu_gem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/accel/ethosu/ethosu_gem.c b/drivers/accel/ethosu/ethosu_gem.c index d50fed64d4d9..fa37a190e9ff 100644 --- a/drivers/accel/ethosu/ethosu_gem.c +++ b/drivers/accel/ethosu/ethosu_gem.c @@ -204,7 +204,7 @@ static u64 feat_matrix_length(struct ethosu_device *edev, struct feat_matrix *fm, u32 x, u32 y, u32 c, bool ofm) { - u32 element_size, storage = fm->precision >> 14; + u32 element_size, storage = ethosu_is_u65(edev) ? 0 : fm->precision >> 14; int tile = 0; u64 addr; From 1c942462c3969b287a86ab6dbb143324289d564e Mon Sep 17 00:00:00 2001 From: Vadim Klishko Date: Mon, 27 Jul 2026 22:17:18 -0600 Subject: [PATCH 0099/1198] HID: i2c-hid: Add a quirk for a Cirque I2C device. Cirque touchpads with PID D0C1 generate an error when probed by the I2C HID driver, resulting in no hidraw device created. Adding I2C_HID_QUIRK_NO_IRQ_AFTER_RESET fixes the issue. Signed-off-by: Vadim Klishko Signed-off-by: Benjamin Tissoires --- drivers/hid/hid-ids.h | 1 + drivers/hid/i2c-hid/i2c-hid-core.c | 2 ++ 2 files changed, 3 insertions(+) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 341bf587863b..b3aca5aa9176 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -338,6 +338,7 @@ #define I2C_VENDOR_ID_CIRQUE 0x0488 #define I2C_PRODUCT_ID_CIRQUE_1063 0x1063 +#define I2C_PRODUCT_ID_CIRQUE_D0C1 0xD0C1 #define USB_VENDOR_ID_CJTOUCH 0x24b8 #define USB_DEVICE_ID_CJTOUCH_MULTI_TOUCH_0020 0x0020 diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index 0e725a0f0abe..0ff07fdab442 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -136,6 +136,8 @@ static const struct i2c_hid_quirks { I2C_HID_QUIRK_BAD_INPUT_SIZE }, { I2C_VENDOR_ID_CIRQUE, I2C_PRODUCT_ID_CIRQUE_1063, I2C_HID_QUIRK_NO_SLEEP_ON_SUSPEND }, + { I2C_VENDOR_ID_CIRQUE, I2C_PRODUCT_ID_CIRQUE_D0C1, + I2C_HID_QUIRK_NO_IRQ_AFTER_RESET }, /* * Without additional power on command, at least some QTEC devices send garbage */ From e8e60b6439eed340a611e9d7a5b9bcbd0ef62725 Mon Sep 17 00:00:00 2001 From: Dave Carey Date: Thu, 30 Jul 2026 08:43:36 -0400 Subject: [PATCH 0100/1198] HID: multitouch: Fix stale MT slots when contact count drops to zero MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The INGENIC 17EF:6161 touchscreen (Lenovo Yoga Book 9 14IAH10) reports HID_DG_CONTACTCOUNT=0 in the frame immediately following the last finger lift rather than omitting the frame entirely. In mt_touch_report() the existing code only updates num_expected when contact_count is non-zero, so a zero contact count on the first packet of a new frame leaves num_expected at its previous value (e.g. 2 for a two-finger gesture). The sync check "num_received >= num_expected" then evaluates "0 >= 2" and never fires, preventing INPUT_MT_DROP_UNUSED from releasing the stale slots. Those slots remain active in the kernel MT layer until the next touch, at which point they are released in a batch alongside the new contact — causing the userspace event consumer to miss the intervening finger-up sequence and corrupt its gesture session state. Fix by resetting num_expected to 0 when contact_count is zero and num_received is still 0 (i.e., this is the first and only packet of the frame, not a continuation packet in a multi-packet sequence). With num_expected=0 the sync check "0 >= 0" fires immediately, calling input_mt_sync_frame() which drops the stale slots via INPUT_MT_DROP_UNUSED. The num_received==0 guard is critical: continuation packets in a multi-packet frame arrive after at least one contact has already been processed (num_received>0), so they are correctly excluded from this path and the existing multi-packet logic is unaffected. Signed-off-by: Dave Carey Tested-by: Dave Carey Signed-off-by: Benjamin Tissoires --- drivers/hid/hid-multitouch.c | 19 ++++++++----------- 1 file changed, 8 insertions(+), 11 deletions(-) diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 2c41bacab1ca..451c7324e6a0 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -1321,21 +1321,18 @@ static void mt_touch_report(struct hid_device *hid, * Includes multi-packet support where subsequent * packets are sent with zero contactcount. */ - if (contact_count >= 0) { + if (contact_count > 0) + app->num_expected = contact_count; + else if (app->num_received == 0 && app->prev_scantime != scantime) { /* + * New multi-report frame: + * * For Win8 PTPs the first packet (td->num_received == 0) may * have a contactcount of 0 if there only is a button event. - * We double check that this is not a continuation packet - * of a possible multi-packet frame be checking that the - * timestamp has changed. + * + * Some other devices use a sentinel frame with 0 to release all contacts */ - if ((app->quirks & MT_QUIRK_WIN8_PTP_BUTTONS) && - app->num_received == 0 && - app->prev_scantime != scantime) - app->num_expected = contact_count; - /* A non 0 contact count always indicates a first packet */ - else if (contact_count) - app->num_expected = contact_count; + app->num_expected = 0; } app->prev_scantime = scantime; From ffe0486b139e45cd9c9ca2584f04a1910fe4f8a6 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 19 Aug 2026 15:38:53 +0200 Subject: [PATCH 0101/1198] console: fix /dev/kmsg reference in flags kernel doc Fix typo in the CON_EXTENDED flag kernel doc which is supposed to refer to '/dev/kmsg'. Fixes: 717a5651b109 ("console: Use BIT() macros for @flags values") Signed-off-by: Johan Hovold Reviewed-by: Petr Mladek Link: https://patch.msgid.link/20260819133853.286658-1-johan@kernel.org Signed-off-by: Petr Mladek --- include/linux/console.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/console.h b/include/linux/console.h index d624200cfc17..502d1abe3f50 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -173,7 +173,7 @@ static inline void con_debug_leave(void) { } * @CON_BRL: Indicates a braille device which is exempt from * receiving the printk spam for obvious reasons. * @CON_EXTENDED: The console supports the extended output format of - * /dev/kmesg which requires a larger output buffer. + * /dev/kmsg which requires a larger output buffer. * @CON_SUSPENDED: Indicates if a console is suspended. If true, the * printing callbacks must not be called. * @CON_NBCON: Console can operate outside of the legacy style console_lock From a8e04f3f894ccb52cfcd7e60125a9f35da4a616d Mon Sep 17 00:00:00 2001 From: Ibrahim Hashimov Date: Mon, 13 Jul 2026 11:34:14 +0200 Subject: [PATCH 0102/1198] HID: wacom: validate report length in wacom_intuos_pro2_bt_irq wacom_intuos_pro2_bt_irq() receives the wire report length in `len` but never consults it before parsing. After the report-id gate it unconditionally calls wacom_intuos_pro2_bt_pen() and then, selected by features.type, a fixed chain of sub-parsers, none of which receive `len`: wacom_intuos_pro2_bt_pen(wacom); if (type == INTUOSP2_BT || type == INTUOSP2S_BT) { wacom_intuos_pro2_bt_touch(wacom); wacom_intuos_pro2_bt_pad(wacom); wacom_intuos_pro2_bt_battery(wacom); } else { wacom_intuos_gen3_bt_pad(wacom); wacom_intuos_gen3_bt_battery(wacom); } Each sub-parser dereferences wacom->data at fixed offsets. The furthest byte touched on each branch is: INTUOSP2_BT / INTUOSP2S_BT: wacom_intuos_pro2_bt_pad() reads data[285] (the touchring byte), so the report must be at least 286 bytes; INTUOSHT3_BT ("gen3"): wacom_intuos_gen3_bt_battery() reads data[45], so the report must be at least 46 bytes. features.type is selected from the VID/PID id_table entry and wacom_setup_device_quirks() force-registers the pen/pad/touch inputs for that type independent of the report descriptor, so a malicious or malfunctioning paired/spoofed Bluetooth peripheral can advertise that VID/PID and send an undersized report that still satisfies the data[0] == 0x80/0x81 gate. The driver then reads past the received report and forwards the bytes to userspace via evdev (MSC_SERIAL / ABS_MISC / ABS_WHEEL on the pen and pad input nodes), an out-of-bounds read with a concrete userspace read-back channel, and a true out-of-bounds read on transports whose backing buffer is sized to the (small) report descriptor rather than a fixed-size staging buffer. This is the same class of bug commit 2f1763f62909 ("HID: wacom: fix out-of-bounds read in wacom_intuos_bt_irq") already hardened in the sibling wacom_intuos_bt_irq(), which guards each report id against its minimum length before parsing. Guard wacom_intuos_pro2_bt_irq() the same way: before parsing, reject reports shorter than the furthest offset the selected branch actually dereferences, warn, and bail out. Because the whole pen/touch/pad/ battery chain runs unconditionally per branch, a single up-front check against the maximum offset (286 bytes for INTUOSP2_BT/INTUOSP2S_BT, 46 bytes for the gen3 branch) bounds every sub-parser. Returning 0 on a short report also skips those calls for the same malformed report, which is the safe, conservative behavior. Fixes: 4922cd26f03c ("HID: wacom: Support 2nd-gen Intuos Pro's Bluetooth classic interface") Cc: stable@vger.kernel.org Signed-off-by: Ibrahim Hashimov Assisted-by: AuditCode-AI:2026.07 Acked-by: Jason Gerecke Signed-off-by: Jiri Kosina --- drivers/hid/wacom_wac.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index a29bf051ada7..8feb8027be95 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -1550,6 +1550,19 @@ static int wacom_intuos_pro2_bt_irq(struct wacom_wac *wacom, size_t len) return 0; } + if (wacom->features.type == INTUOSP2_BT || + wacom->features.type == INTUOSP2S_BT) { + if (len < 286) { + dev_warn(wacom->pen_input->dev.parent, + "Pro2 BT report too short: %zu bytes\n", len); + return 0; + } + } else if (len < 46) { + dev_warn(wacom->pen_input->dev.parent, + "Pro2 BT report too short: %zu bytes\n", len); + return 0; + } + wacom_intuos_pro2_bt_pen(wacom); if (wacom->features.type == INTUOSP2_BT || wacom->features.type == INTUOSP2S_BT) { From 55a4c98abb9694b067c6a031d11501f06b6b523c Mon Sep 17 00:00:00 2001 From: Ali Ahmet Memis Date: Sat, 1 Aug 2026 10:12:57 +0300 Subject: [PATCH 0103/1198] ufs: create the root dentry after loading cylinder metadata ufs_fill_super() installed sb->s_root before it loaded the cylinder group structures for a writable mount: sb->s_root = d_make_root(inode); ... if (!sb_rdonly(sb)) if (!ufs_read_cylinder_structures(sb)) goto failed; When ufs_read_cylinder_structures() failed, the error path freed the in-core superblock information and set sb->s_fs_info to NULL while sb->s_root stayed installed. get_tree_bdev() then reached deactivate_locked_super(), and because s_root was present, generic_shutdown_super() called sync_filesystem() and the put_super operation. Both dereference UFS_SB(sb), which is now NULL, so a mount that fails only while reading the cylinder groups oopses during teardown. A crafted image whose first cylinder group cannot be read reaches this path. Load the cylinder group metadata first and create the root dentry last, so the superblock is published to the VFS only once it is fully set up. ufs_setup_cstotal() and ufs_read_cylinder_structures() take only the super_block and do not use the root inode, so the reordering is safe. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable@vger.kernel.org Signed-off-by: Ali Ahmet Memis Link: https://patch.msgid.link/20260801071306.59484-2-ali@iusegentoo.com Reviewed-by: Jan Kara Signed-off-by: Christian Brauner (Amutable) --- fs/ufs/super.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/fs/ufs/super.c b/fs/ufs/super.c index 6dcf6d048cce..3569ac92b065 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -1199,6 +1199,15 @@ static int ufs_fill_super(struct super_block *sb, struct fs_context *fc) sb->s_maxbytes = ufs_max_bytes(sb); sb->s_max_links = UFS_LINK_MAX; + ufs_setup_cstotal(sb); + /* + * Read cylinder group structures + */ + if (!sb_rdonly(sb)) + if (!ufs_read_cylinder_structures(sb)) + goto failed; + + /* create the root dentry last, once UFS_SB(sb) is fully set up */ inode = ufs_iget(sb, UFS_ROOTINO); if (IS_ERR(inode)) { ret = PTR_ERR(inode); @@ -1210,14 +1219,6 @@ static int ufs_fill_super(struct super_block *sb, struct fs_context *fc) goto failed; } - ufs_setup_cstotal(sb); - /* - * Read cylinder group structures - */ - if (!sb_rdonly(sb)) - if (!ufs_read_cylinder_structures(sb)) - goto failed; - UFSD("EXIT\n"); return 0; From c9d263be26806d388129fab8c6904bed197fc6af Mon Sep 17 00:00:00 2001 From: Ali Ahmet Memis Date: Sat, 1 Aug 2026 10:12:58 +0300 Subject: [PATCH 0104/1198] ufs: validate cylinder group metadata before caching it ufs_read_cylinder() copies the cylinder group index and the rotor positions straight from the on-disk group and caches them without any check: ucpi->c_cgx = fs32_to_cpu(sb, ucg->cg_cgx); ucpi->c_rotor = fs32_to_cpu(sb, ucg->cg_rotor); ucpi->c_frotor = fs32_to_cpu(sb, ucg->cg_frotor); ucpi->c_irotor = fs32_to_cpu(sb, ucg->cg_irotor); They are then used as indices during allocation and free: - c_cgx indexes the cylinder summary array as UFS_SB(sb)->fs_cs(ucpi->c_cgx), so a value past s_ncg writes a 32 bit count outside the s_csp allocation. - c_frotor becomes a bitmap scan start, start = c_frotor >> 3, and then length = ((s_fpg + 7) >> 3) - start. A start beyond the block bitmap wraps the unsigned length to a huge value, so ubh_scanc() walks far past the cylinder group buffers. c_irotor drives the inode bitmap the same way. A crafted image can set any of these freely, turning an ordinary allocation into an out of bounds access. Reject a cylinder group whose recorded index does not match the group being read, or whose rotors fall outside the group, before the metadata is cached. Valid filesystems keep cg_cgx equal to the group number and the rotors within the group, so only malformed images are rejected. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable@vger.kernel.org Signed-off-by: Ali Ahmet Memis Link: https://patch.msgid.link/20260801071306.59484-3-ali@iusegentoo.com Reviewed-by: Jan Kara Signed-off-by: Christian Brauner (Amutable) --- fs/ufs/cylinder.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/fs/ufs/cylinder.c b/fs/ufs/cylinder.c index a2813270c303..b930ee1cf853 100644 --- a/fs/ufs/cylinder.c +++ b/fs/ufs/cylinder.c @@ -68,6 +68,16 @@ static bool ufs_read_cylinder(struct super_block *sb, ucpi->c_clustersumoff = fs32_to_cpu(sb, ucg->cg_u.cg_44.cg_clustersumoff); ucpi->c_clusteroff = fs32_to_cpu(sb, ucg->cg_u.cg_44.cg_clusteroff); ucpi->c_nclusterblks = fs32_to_cpu(sb, ucg->cg_u.cg_44.cg_nclusterblks); + + /* these on-disk values become array and bitmap indices */ + if (ucpi->c_cgx != cgno || + ucpi->c_rotor >= uspi->s_fpg || + ucpi->c_frotor >= uspi->s_fpg || + ucpi->c_irotor >= uspi->s_ipg) { + ufs_error(sb, __func__, + "inconsistent metadata in cylinder group %u\n", cgno); + goto failed; + } UFSD("EXIT\n"); return true; From 08edfb34ee9ca54383970c65ed3a6013e84f5e16 Mon Sep 17 00:00:00 2001 From: Ali Ahmet Memis Date: Sat, 1 Aug 2026 04:39:32 +0300 Subject: [PATCH 0105/1198] ufs: do not treat unreadable directory blocks as empty ufs_empty_dir() scans every directory block to decide whether a directory is empty before rmdir() removes it. When ufs_get_folio() cannot read or validate a block it returns an error pointer, and the loop currently skips that block with continue and keeps scanning the remaining blocks. If none of the readable blocks hold an entry, the function returns 1 and the caller unlinks the directory. A directory whose contents live in a block that cannot be read, for example because of an I/O error or corrupted directory metadata, is therefore seen as empty and removed, losing the entries it still holds. Follow the ext2 behaviour and treat an unreadable block as a reason to consider the directory not empty, so rmdir() fails instead of discarding data that could not be verified. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Ali Ahmet Memis Link: https://patch.msgid.link/20260801013942.279992-1-ali@iusegentoo.com Reviewed-by: Jan Kara Signed-off-by: Christian Brauner (Amutable) --- fs/ufs/dir.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c index e62fe5667671..ce43cf20b07c 100644 --- a/fs/ufs/dir.c +++ b/fs/ufs/dir.c @@ -590,7 +590,7 @@ int ufs_empty_dir(struct inode * inode) kaddr = ufs_get_folio(inode, i, &folio); if (IS_ERR(kaddr)) - continue; + return 0; de = (struct ufs_dir_entry *)kaddr; kaddr += ufs_last_byte(inode, i) - UFS_DIR_REC_LEN(1); From fe967191e5851ea79818c5fe4e781c3882139218 Mon Sep 17 00:00:00 2001 From: Moritz Tanner Date: Fri, 21 Aug 2026 10:54:51 +0200 Subject: [PATCH 0106/1198] fs: don't return -EINVAL for successful nested thaw Commit 7366f8b6fc6a ("fs: handle freezing from multiple devices") replaced the freeze_holders bitmask with per-holder counters to allow nested freezes. In the bitmask version, a thaw that released a shared hold while another holder remained returned 0. Since the rework, thaw_super_locked() drops the freeze reference via freeze_dec() but then returns -EINVAL when other freezers remain, misinforming the caller: the thaw did succeed, the superblock just stays frozen for the remaining holders. This breaks bdev-initiated freezing. When a filesystem is frozen with FIFREEZE and additionally frozen via bdev_freeze() -- which nests by design, see fs_bdev_freeze() -- the subsequent bdev_thaw() receives -EINVAL from the holder op although its freeze reference was dropped, and therefore keeps bd_fsfreeze_count elevated. Then device-mapper's unlock_fs() ignores bdev_thaw()'s return value, so nothing rebalances the count. After the user's FITHAW and umount, the block device can never be mounted again: dm-1: Can't mount, blockdev is frozen There is no way for userspace to drop the leaked count; only destroying the block device (or a reboot) recovers the device. Reproducer (any kernel since v6.8): dmsetup create dut --table "0 $(blockdev --getsz "$DEV") linear $DEV 0" mkfs.ext4 /dev/mapper/dut mount /dev/mapper/dut /mnt fsfreeze --freeze /mnt # freeze_ucount == 1 dmsetup suspend dut # bd_fsfreeze_count == 1, ucount == 2 dmsetup resume dut # ucount 2 -> 1, but thaw_super() # returns -EINVAL, so bdev_thaw() # keeps bd_fsfreeze_count at 1 fsfreeze --unfreeze /mnt # filesystem thaws fine umount /mnt mount /dev/mapper/dut /mnt # EBUSY, forever The same happens with fsfreeze held across an LVM snapshot of the origin volume. fs_bdev_thaw()'s documentation already describes the intended semantics: "If this function returns zero it doesn't mean that the filesystem is unfrozen as it may have been frozen multiple times". Restore them by returning 0 when a nested thaw drops its hold while other freezers remain. Thawing without holding a freeze still fails with -EINVAL as may_unfreeze() rejects that case before the reference count is touched. Fixes: 7366f8b6fc6a ("fs: handle freezing from multiple devices") Cc: stable@vger.kernel.org # needs adjustments for < 6.17 (no may_unfreeze()) Signed-off-by: Moritz Tanner Link: https://patch.msgid.link/20260821085451.65206-1-moritz.tanner@linbit.com Tested-by: Lars Ellenberg Reviewed-by: Lars Ellenberg Signed-off-by: Christian Brauner (Amutable) --- fs/super.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/fs/super.c b/fs/super.c index 05e443173038..01db6124e409 100644 --- a/fs/super.c +++ b/fs/super.c @@ -2369,11 +2369,14 @@ static int thaw_super_locked(struct super_block *sb, enum freeze_holder who, goto out_unlock; /* - * All freezers share a single active reference. - * So just unlock in case there are any left. + * All freezers share a single active reference. If other freezers + * remain, drop our hold and report success; the superblock stays + * frozen until the last holder thaws it. */ - if (freeze_dec(sb, who)) + if (freeze_dec(sb, who)) { + error = 0; goto out_unlock; + } if (sb_rdonly(sb)) { sb->s_writers.frozen = SB_UNFROZEN; From 554ab79cfd104fbd76f3be82b0dfa8fc2b324799 Mon Sep 17 00:00:00 2001 From: Lyude Paul Date: Tue, 28 Apr 2026 23:03:40 -0400 Subject: [PATCH 0107/1198] drm/nouveau/disp/r535: Add scanline position support + head state support That's right! It looks like this never actually got finished, something which I just noticed today when I saw this fun message spamming one of my test machine's kernel logs when enabling display debug output for nouveau: [drm:drm_crtc_vblank_helper_get_vblank_timestamp_internal] crtc 0 : scanoutpos query failed. So it looks like we've been falling back to DRM's core fallback for a while now, whoops. So, while it seems that we do have the option of doing this through GSP - that doesn't seem like a great idea. Mainly because reading this from GSP would involve a lot more latency then we should have for vblank handling due to the RPC communication. So instead of implementing that, just use gv100_head_state and gv100_head_rgpos for implementing .state and .rgpos. It seems to work perfectly fine! Fixes: 9e9944449023 ("drm/nouveau/disp/r535: initial support") Cc: Ben Skeggs Cc: Dave Airlie Cc: Timur Tabi Cc: Ben Skeggs Cc: James Jones Cc: Faith Ekstrand Cc: Suraj Kandpal Cc: Lyude Paul Cc: Aaron Kling Cc: Danilo Krummrich Cc: Zhang Enpei Cc: # v6.7+ Signed-off-by: Lyude Paul Signed-off-by: Dave Airlie Reviewed-by: Dave Airlie Link: https://patch.msgid.link/20260429030348.3930866-1-lyude@redhat.com (cherry picked from commit 804cb093b245c752f15d17186e0d404f10303593) Signed-off-by: Lyude Paul --- drivers/gpu/drm/nouveau/nvkm/engine/disp/gv100.c | 4 ++-- drivers/gpu/drm/nouveau/nvkm/engine/disp/head.h | 2 ++ drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c | 8 ++------ 3 files changed, 6 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gv100.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gv100.c index dbd984da7501..0608266188d3 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gv100.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gv100.c @@ -253,7 +253,7 @@ gv100_head_vblank_get(struct nvkm_head *head) nvkm_mask(device, 0x611d80 + (head->id * 4), 0x00000004, 0x00000004); } -static void +void gv100_head_rgpos(struct nvkm_head *head, u16 *hline, u16 *vline) { struct nvkm_device *device = head->disp->engine.subdev.device; @@ -263,7 +263,7 @@ gv100_head_rgpos(struct nvkm_head *head, u16 *hline, u16 *vline) *hline = nvkm_rd32(device, 0x616334 + hoff) & 0x0000ffff; } -static void +void gv100_head_state(struct nvkm_head *head, struct nvkm_head_state *state) { struct nvkm_device *device = head->disp->engine.subdev.device; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/head.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/head.h index 856252bf559a..b642729c254f 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/head.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/head.h @@ -53,6 +53,8 @@ void gf119_head_rgclk(struct nvkm_head *, int); int gv100_head_cnt(struct nvkm_disp *, unsigned long *); int gv100_head_new(struct nvkm_disp *, int id); +void gv100_head_state(struct nvkm_head *head, struct nvkm_head_state *state); +void gv100_head_rgpos(struct nvkm_head *head, u16 *hline, u16 *vline); #define HEAD_MSG(h,l,f,a...) do { \ struct nvkm_head *_h = (h); \ diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c index 1155f079b0c3..e77733a5d9c3 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c @@ -625,14 +625,10 @@ r535_head_vblank_get(struct nvkm_head *head) nvkm_mask(device, 0x611d80 + (head->id * 4), 0x00000002, 0x00000002); } -static void -r535_head_state(struct nvkm_head *head, struct nvkm_head_state *state) -{ -} - static const struct nvkm_head_func r535_head = { - .state = r535_head_state, + .state = gv100_head_state, + .rgpos = gv100_head_rgpos, .vblank_get = r535_head_vblank_get, .vblank_put = r535_head_vblank_put, }; From c6659e0ffc19b4ef0b3273c185cb8409a154eada Mon Sep 17 00:00:00 2001 From: Mohamed Ahmed Date: Tue, 25 Aug 2026 04:13:59 +0400 Subject: [PATCH 0108/1198] drm/nouveau/disp: move GSP head-timing ISR and vblank helpers to tu102.c The GSP-RM display code in rm/r535/disp.c owns a handful of direct MMIO routines: the head-timing (vblank) interrupt handler and the per-head vblank enable/disable. They program display registers, not RM, so they belong with the rest of the per-chip register code in engine/disp/. Move them to tu102.c (Turing is the first GSP-capable generation) as tu102_disp_intr() and tu102_head_vblank_get()/put(), exported for rm/r535/disp.c, which keeps calling them by name for now. No functional change. Fixes: 6cc6e08d4542 ("drm/nouveau/kms: add support for GB20x") Cc: stable@vger.kernel.org Signed-off-by: Mohamed Ahmed Reviewed-by: Lyude Paul Signed-off-by: Lyude Paul Link: https://patch.msgid.link/20260825001408.14219-2-mohamedahmedegypt2001@gmail.com --- .../gpu/drm/nouveau/nvkm/engine/disp/head.h | 3 ++ .../gpu/drm/nouveau/nvkm/engine/disp/priv.h | 1 + .../gpu/drm/nouveau/nvkm/engine/disp/tu102.c | 50 ++++++++++++++++++ .../nouveau/nvkm/subdev/gsp/rm/r535/disp.c | 52 ++----------------- 4 files changed, 57 insertions(+), 49 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/head.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/head.h index b642729c254f..986043e87554 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/head.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/head.h @@ -56,6 +56,9 @@ int gv100_head_new(struct nvkm_disp *, int id); void gv100_head_state(struct nvkm_head *head, struct nvkm_head_state *state); void gv100_head_rgpos(struct nvkm_head *head, u16 *hline, u16 *vline); +void tu102_head_vblank_get(struct nvkm_head *); +void tu102_head_vblank_put(struct nvkm_head *); + #define HEAD_MSG(h,l,f,a...) do { \ struct nvkm_head *_h = (h); \ nvkm_##l(&_h->disp->engine.subdev, "head-%d: "f"\n", _h->id, ##a); \ diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/priv.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/priv.h index a3fd7cb7c488..722ec340e12a 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/priv.h @@ -72,6 +72,7 @@ int gv100_disp_wndw_cnt(struct nvkm_disp *, unsigned long *); int gv100_disp_caps_new(const struct nvkm_oclass *, void *, u32, struct nvkm_object **); int tu102_disp_init(struct nvkm_disp *); +irqreturn_t tu102_disp_intr(struct nvkm_inth *); void nv50_disp_dptmds_war_2(struct nvkm_disp *, struct dcb_output *); void nv50_disp_dptmds_war_3(struct nvkm_disp *, struct dcb_output *); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c index dcb9f8ba374c..7b70b466fa36 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c @@ -104,6 +104,56 @@ tu102_sor_new(struct nvkm_disp *disp, int id) return nvkm_ior_new_(&tu102_sor, disp, SOR, id, hda & BIT(id)); } +/* The GSP-RM display path leaves head-timing (vblank) interrupts and their + * enables to us. These program the RM head-timing line (bit 1 of the + * per-head enable, not the bit nvkm's own gv100 path uses). + */ +void +tu102_head_vblank_put(struct nvkm_head *head) +{ + struct nvkm_device *device = head->disp->engine.subdev.device; + + nvkm_mask(device, 0x611d80 + (head->id * 4), 0x00000002, 0x00000000); +} + +void +tu102_head_vblank_get(struct nvkm_head *head) +{ + struct nvkm_device *device = head->disp->engine.subdev.device; + + nvkm_wr32(device, 0x611800 + (head->id * 4), 0x00000002); + nvkm_mask(device, 0x611d80 + (head->id * 4), 0x00000002, 0x00000002); +} + +static void +tu102_disp_intr_head_timing(struct nvkm_disp *disp, int head) +{ + struct nvkm_subdev *subdev = &disp->engine.subdev; + struct nvkm_device *device = subdev->device; + u32 stat = nvkm_rd32(device, 0x611c00 + (head * 0x04)); + + if (stat & 0x00000002) { + nvkm_disp_vblank(disp, head); + + nvkm_wr32(device, 0x611800 + (head * 0x04), 0x00000002); + } +} + +irqreturn_t +tu102_disp_intr(struct nvkm_inth *inth) +{ + struct nvkm_disp *disp = container_of(inth, typeof(*disp), engine.subdev.inth); + struct nvkm_subdev *subdev = &disp->engine.subdev; + struct nvkm_device *device = subdev->device; + unsigned long mask = nvkm_rd32(device, 0x611ec0) & 0x000000ff; + int head; + + for_each_set_bit(head, &mask, 8) + tu102_disp_intr_head_timing(disp, head); + + return IRQ_HANDLED; +} + int tu102_disp_init(struct nvkm_disp *disp) { diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c index e77733a5d9c3..8e57bb6519e5 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c @@ -608,29 +608,12 @@ r535_sor_cnt(struct nvkm_disp *disp, unsigned long *pmask) return 4; } -static void -r535_head_vblank_put(struct nvkm_head *head) -{ - struct nvkm_device *device = head->disp->engine.subdev.device; - - nvkm_mask(device, 0x611d80 + (head->id * 4), 0x00000002, 0x00000000); -} - -static void -r535_head_vblank_get(struct nvkm_head *head) -{ - struct nvkm_device *device = head->disp->engine.subdev.device; - - nvkm_wr32(device, 0x611800 + (head->id * 4), 0x00000002); - nvkm_mask(device, 0x611d80 + (head->id * 4), 0x00000002, 0x00000002); -} - static const struct nvkm_head_func r535_head = { .state = gv100_head_state, .rgpos = gv100_head_rgpos, - .vblank_get = r535_head_vblank_get, - .vblank_put = r535_head_vblank_put, + .vblank_get = tu102_head_vblank_get, + .vblank_put = tu102_head_vblank_put, }; static struct nvkm_conn * @@ -1404,35 +1387,6 @@ static const struct nvkm_event_func r535_disp_event = { }; -static void -r535_disp_intr_head_timing(struct nvkm_disp *disp, int head) -{ - struct nvkm_subdev *subdev = &disp->engine.subdev; - struct nvkm_device *device = subdev->device; - u32 stat = nvkm_rd32(device, 0x611c00 + (head * 0x04)); - - if (stat & 0x00000002) { - nvkm_disp_vblank(disp, head); - - nvkm_wr32(device, 0x611800 + (head * 0x04), 0x00000002); - } -} - -static irqreturn_t -r535_disp_intr(struct nvkm_inth *inth) -{ - struct nvkm_disp *disp = container_of(inth, typeof(*disp), engine.subdev.inth); - struct nvkm_subdev *subdev = &disp->engine.subdev; - struct nvkm_device *device = subdev->device; - unsigned long mask = nvkm_rd32(device, 0x611ec0) & 0x000000ff; - int head; - - for_each_set_bit(head, &mask, 8) - r535_disp_intr_head_timing(disp, head); - - return IRQ_HANDLED; -} - static void r535_disp_fini(struct nvkm_disp *disp, bool suspend) { @@ -1708,7 +1662,7 @@ r535_disp_oneinit(struct nvkm_disp *disp) return ret; ret = nvkm_inth_add(&device->vfn->intr, ret, NVKM_INTR_PRIO_NORMAL, &disp->engine.subdev, - r535_disp_intr, &disp->engine.subdev.inth); + tu102_disp_intr, &disp->engine.subdev.inth); if (ret) return ret; From eb1ffc3dc72d379a41e367a44b99fb61a15bf8ba Mon Sep 17 00:00:00 2001 From: Mohamed Ahmed Date: Tue, 25 Aug 2026 04:14:00 +0400 Subject: [PATCH 0109/1198] drm/nouveau/disp: move the GSP HDMI GCP AVMute write to engine/disp r535_sor_hdmi_audio() pairs two RM controls (a SET_OD_PACKET carrying the same General Control Packet, and the audio mute-stream toggle) with a direct write of the GCP AVMute bit through the SF GCP unit. The controls are RM and stay, but the direct write is register programming and moves next to the other per-chip display code as tu102_sor_hdmi_gcp(). No functional change. Fixes: 6cc6e08d4542 ("drm/nouveau/kms: add support for GB20x") Cc: stable@vger.kernel.org Signed-off-by: Mohamed Ahmed Reviewed-by: Lyude Paul Signed-off-by: Lyude Paul Link: https://patch.msgid.link/20260825001408.14219-3-mohamedahmedegypt2001@gmail.com --- drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h | 1 + drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c | 15 +++++++++++++++ .../drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c | 9 +-------- 3 files changed, 17 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h index 3ba04bead2f9..5d682a774f2d 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h @@ -194,6 +194,7 @@ void gv100_sor_dp_audio_sym(struct nvkm_ior *, int, u16, u32); void gv100_sor_dp_watermark(struct nvkm_ior *, int, u8); extern const struct nvkm_ior_func_hda gv100_sor_hda; +void tu102_sor_hdmi_gcp(struct nvkm_ior *, int, bool); void tu102_sor_dp_vcpi(struct nvkm_ior *, int, u8, u8, u16, u16); int nv50_pior_cnt(struct nvkm_disp *, unsigned long *); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c index 7b70b466fa36..6cfd52c9056f 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c @@ -30,6 +30,21 @@ #include +/* General Control Packet: bracket an audio enable/disable with AVMute + * through the legacy GCP SF unit. Used by the GSP-RM path, which sends the + * equivalent packet via RM as well but keeps the direct write in sync. + */ +void +tu102_sor_hdmi_gcp(struct nvkm_ior *sor, int head, bool enable) +{ + struct nvkm_device *device = sor->disp->engine.subdev.device; + const u32 hdmi = head * 0x400; + + nvkm_mask(device, 0x6f00c0 + hdmi, 0x00000001, 0x00000000); + nvkm_wr32(device, 0x6f00cc + hdmi, !enable ? 0x00000001 : 0x00000010); + nvkm_mask(device, 0x6f00c0 + hdmi, 0x00000001, 0x00000001); +} + void tu102_sor_dp_vcpi(struct nvkm_ior *sor, int head, u8 slot, u8 slot_nr, u16 pbn, u16 aligned) { diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c index 8e57bb6519e5..cd4451e62512 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c @@ -545,16 +545,9 @@ r535_sor_hdmi_ctrl_audio(struct nvkm_outp *outp, bool enable) static void r535_sor_hdmi_audio(struct nvkm_ior *sor, int head, bool enable) { - struct nvkm_device *device = sor->disp->engine.subdev.device; - const u32 hdmi = head * 0x400; - r535_sor_hdmi_ctrl_audio(sor->asy.outp, enable); r535_sor_hdmi_ctrl_audio_mute(sor->asy.outp, !enable); - - /* General Control (GCP). */ - nvkm_mask(device, 0x6f00c0 + hdmi, 0x00000001, 0x00000000); - nvkm_wr32(device, 0x6f00cc + hdmi, !enable ? 0x00000001 : 0x00000010); - nvkm_mask(device, 0x6f00c0 + hdmi, 0x00000001, 0x00000001); + tu102_sor_hdmi_gcp(sor, head, enable); } static void From 9886aad51f4b5e7082209a153e404bcd8101356c Mon Sep 17 00:00:00 2001 From: Mohamed Ahmed Date: Tue, 25 Aug 2026 04:14:01 +0400 Subject: [PATCH 0110/1198] drm/nouveau/disp: route GSP-RM display MMIO through nvkm_disp_func hooks The GSP-RM display code in rm/r535/disp.c borrows a few register-programming routines from engine/disp (the head-timing interrupt handler, vblank enables, armed head state and scanout position readback, the AVI/VSI infoframe writers and the GCP AVMute write) and so far picked them by name, which means it has to know which chip it runs on the moment a generation changes any of them. Give nvkm_disp_func a .gsp table that each chip fills with exactly those hooks, add tu102_gsp_disp (TU1xx) and ga102_gsp_disp (GA10x onwards) carrying the current functions, hand them to r535_disp_new() instead of the full hardware tables, and make rm/r535/disp.c call through the hooks. The head hooks are a whole nvkm_head_func, so r535_head goes away and the chip's own table is handed to nvkm_head_new_(). r535_sor_hdmi gets infoframe forwarders, r535_sor_hdmi_audio() calls the GCP hook, and the interrupt handler comes from the table. The tables are per chip even though the two currently coincide, so a generation that changes a hook only touches its own file. rm/r535/disp.c no longer contains chip-specific register code, and a new display generation only has to provide its own table. No functional change. Fixes: 6cc6e08d4542 ("drm/nouveau/kms: add support for GB20x") Cc: stable@vger.kernel.org Signed-off-by: Mohamed Ahmed Reviewed-by: Lyude Paul Signed-off-by: Lyude Paul Link: https://patch.msgid.link/20260825001408.14219-4-mohamedahmedegypt2001@gmail.com --- .../gpu/drm/nouveau/nvkm/engine/disp/ga102.c | 13 +++++++- .../gpu/drm/nouveau/nvkm/engine/disp/head.h | 1 + .../gpu/drm/nouveau/nvkm/engine/disp/priv.h | 14 +++++++++ .../gpu/drm/nouveau/nvkm/engine/disp/tu102.c | 21 ++++++++++++- .../nouveau/nvkm/subdev/gsp/rm/r535/disp.c | 31 +++++++++++-------- 5 files changed, 65 insertions(+), 15 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ga102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ga102.c index ab0a85c92430..820834b5ee9b 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ga102.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ga102.c @@ -144,12 +144,23 @@ ga102_disp = { }, }; +static const struct nvkm_disp_func +ga102_gsp_disp = { + .uevent = &gv100_disp_chan_uevent, + .ramht_size = 0x2000, + .gsp.intr = tu102_disp_intr, + .gsp.head = &tu102_gsp_head, + .gsp.hdmi_gcp = tu102_sor_hdmi_gcp, + .gsp.hdmi_infoframe_avi = gv100_sor_hdmi_infoframe_avi, + .gsp.hdmi_infoframe_vsi = gv100_sor_hdmi_infoframe_vsi, +}; + int ga102_disp_new(struct nvkm_device *device, enum nvkm_subdev_type type, int inst, struct nvkm_disp **pdisp) { if (nvkm_gsp_rm(device->gsp)) - return r535_disp_new(&ga102_disp, device, type, inst, pdisp); + return r535_disp_new(&ga102_gsp_disp, device, type, inst, pdisp); return nvkm_disp_new_(&ga102_disp, device, type, inst, pdisp); } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/head.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/head.h index 986043e87554..784521c2aca1 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/head.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/head.h @@ -58,6 +58,7 @@ void gv100_head_rgpos(struct nvkm_head *head, u16 *hline, u16 *vline); void tu102_head_vblank_get(struct nvkm_head *); void tu102_head_vblank_put(struct nvkm_head *); +extern const struct nvkm_head_func tu102_gsp_head; #define HEAD_MSG(h,l,f,a...) do { \ struct nvkm_head *_h = (h); \ diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/priv.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/priv.h index 722ec340e12a..a9dbda67a7d4 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/priv.h @@ -5,6 +5,8 @@ #include #include struct nvkm_head; +struct nvkm_head_func; +struct nvkm_ior; struct nvkm_outp; struct dcb_output; @@ -34,6 +36,18 @@ struct nvkm_disp_func { int (*new)(struct nvkm_disp *, int id); } wndw, head, dac, sor, pior; + /* Register programming that the GSP-RM display path (rm/r535) needs from + * the chip, everything else on that path goes through RM. The hooks are + * called unconditionally and the head table is handed to nvkm_head_new_(). + */ + struct { + irqreturn_t (*intr)(struct nvkm_inth *); + const struct nvkm_head_func *head; + void (*hdmi_gcp)(struct nvkm_ior *, int head, bool enable); + void (*hdmi_infoframe_avi)(struct nvkm_ior *, int head, void *data, u32 size); + void (*hdmi_infoframe_vsi)(struct nvkm_ior *, int head, void *data, u32 size); + } gsp; + u16 ramht_size; struct nvkm_sclass root; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c index 6cfd52c9056f..948b1d2f954c 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c @@ -140,6 +140,14 @@ tu102_head_vblank_get(struct nvkm_head *head) nvkm_mask(device, 0x611d80 + (head->id * 4), 0x00000002, 0x00000002); } +const struct nvkm_head_func +tu102_gsp_head = { + .state = gv100_head_state, + .rgpos = gv100_head_rgpos, + .vblank_get = tu102_head_vblank_get, + .vblank_put = tu102_head_vblank_put, +}; + static void tu102_disp_intr_head_timing(struct nvkm_disp *disp, int head) { @@ -295,12 +303,23 @@ tu102_disp = { }, }; +static const struct nvkm_disp_func +tu102_gsp_disp = { + .uevent = &gv100_disp_chan_uevent, + .ramht_size = 0x2000, + .gsp.intr = tu102_disp_intr, + .gsp.head = &tu102_gsp_head, + .gsp.hdmi_gcp = tu102_sor_hdmi_gcp, + .gsp.hdmi_infoframe_avi = gv100_sor_hdmi_infoframe_avi, + .gsp.hdmi_infoframe_vsi = gv100_sor_hdmi_infoframe_vsi, +}; + int tu102_disp_new(struct nvkm_device *device, enum nvkm_subdev_type type, int inst, struct nvkm_disp **pdisp) { if (nvkm_gsp_rm(device->gsp)) - return r535_disp_new(&tu102_disp, device, type, inst, pdisp); + return r535_disp_new(&tu102_gsp_disp, device, type, inst, pdisp); return nvkm_disp_new_(&tu102_disp, device, type, inst, pdisp); } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c index cd4451e62512..bf97edcdfc95 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c @@ -547,7 +547,19 @@ r535_sor_hdmi_audio(struct nvkm_ior *sor, int head, bool enable) { r535_sor_hdmi_ctrl_audio(sor->asy.outp, enable); r535_sor_hdmi_ctrl_audio_mute(sor->asy.outp, !enable); - tu102_sor_hdmi_gcp(sor, head, enable); + sor->disp->func->gsp.hdmi_gcp(sor, head, enable); +} + +static void +r535_sor_hdmi_infoframe_avi(struct nvkm_ior *sor, int head, void *data, u32 size) +{ + sor->disp->func->gsp.hdmi_infoframe_avi(sor, head, data, size); +} + +static void +r535_sor_hdmi_infoframe_vsi(struct nvkm_ior *sor, int head, void *data, u32 size) +{ + sor->disp->func->gsp.hdmi_infoframe_vsi(sor, head, data, size); } static void @@ -575,8 +587,8 @@ r535_sor_hdmi = { .ctrl = r535_sor_hdmi_ctrl, .scdc = r535_sor_hdmi_scdc, /*TODO: SF_USER -> KMS. */ - .infoframe_avi = gv100_sor_hdmi_infoframe_avi, - .infoframe_vsi = gv100_sor_hdmi_infoframe_vsi, + .infoframe_avi = r535_sor_hdmi_infoframe_avi, + .infoframe_vsi = r535_sor_hdmi_infoframe_vsi, .audio = r535_sor_hdmi_audio, }; @@ -601,14 +613,6 @@ r535_sor_cnt(struct nvkm_disp *disp, unsigned long *pmask) return 4; } -static const struct nvkm_head_func -r535_head = { - .state = gv100_head_state, - .rgpos = gv100_head_rgpos, - .vblank_get = tu102_head_vblank_get, - .vblank_put = tu102_head_vblank_put, -}; - static struct nvkm_conn * r535_conn_new(struct nvkm_disp *disp, u32 id) { @@ -1606,7 +1610,7 @@ r535_disp_oneinit(struct nvkm_disp *disp) nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); for_each_set_bit(i, &disp->head.mask, disp->head.nr) { - ret = nvkm_head_new_(&r535_head, disp, i); + ret = nvkm_head_new_(disp->func->gsp.head, disp, i); if (ret) return ret; } @@ -1655,7 +1659,7 @@ r535_disp_oneinit(struct nvkm_disp *disp) return ret; ret = nvkm_inth_add(&device->vfn->intr, ret, NVKM_INTR_PRIO_NORMAL, &disp->engine.subdev, - tu102_disp_intr, &disp->engine.subdev.inth); + disp->func->gsp.intr, &disp->engine.subdev.inth); if (ret) return ret; @@ -1688,6 +1692,7 @@ r535_disp_new(const struct nvkm_disp_func *hw, struct nvkm_device *device, rm->uevent = hw->uevent; rm->sor.cnt = r535_sor_cnt; rm->sor.new = r535_sor_new; + rm->gsp = hw->gsp; rm->ramht_size = hw->ramht_size; rm->root.oclass = gpu->disp.class.root; From 92f09dcb4e8473ab25764e950994ab7b6abce6dd Mon Sep 17 00:00:00 2001 From: Mohamed Ahmed Date: Tue, 25 Aug 2026 04:14:02 +0400 Subject: [PATCH 0111/1198] drm/nouveau/disp: fix HDMI vendor infoframes on GB20x The GSP path reuses the GV100 direct-MMIO infoframe writers on every chip. On GB20x that is only half right as while the legacy SF AVI unit is unchanged, the legacy VSI unit at 0x6f0100 was removed, so gv100_sor_hdmi_infoframe_vsi() writes into a reserved area and no vendor infoframe ever reaches the HW. This affects HDMI-VIC signalling which can impact some 4K modes for legacy HDMI 1.4 sinks. GB20x (NVDisplay 5.0+) reorganised the SF HDMI packet units. Per NVIDIA's published C971/CA71 DISP_SF_USER class headers, only three legacy units remain (AVI at +0x000, GCP at +0x040, ACR at +0x080), and vendor infoframes must instead be sent through the shared generic infoframe units at +0x130, whose 9-dword packet slots are loaded through the shared data port at +0x3f0/+0x3f4. Add a VSI writer using the same programming sequence OpenRM uses on these chips (nvhdmipkt_C971.c, programAdvancedInfoframeC971()): disable the unit and wait for it to idle, clear the SENT status, write the packet through the data port with a zero inserted in HB3 after the three header bytes, then enable the unit for every-frame transmission during vblank. Generic unit 1 is used for the VSI, matching the slot assignment in NVIDIA's nvkms (NVHDMIPKT_TYPE_SHARED_GENERIC2, unit 0 is reserved for extended metadata packets and unit 2 for the HDR DRM infoframe, if those are wired up later). GB20x so far shared GA10x's display entry point. Give it its own, gb202_disp_new(), with a gb202_gsp_disp table that supplies the VSI writer to the GSP path and otherwise carries the same hooks as GA10x. The following fixes fill in the rest of the GB20x differences there. Fixes: 6cc6e08d4542 ("drm/nouveau/kms: add support for GB20x") Cc: stable@vger.kernel.org Signed-off-by: Mohamed Ahmed Reviewed-by: Lyude Paul Signed-off-by: Lyude Paul Link: https://patch.msgid.link/20260825001408.14219-5-mohamedahmedegypt2001@gmail.com --- .../drm/nouveau/include/nvkm/engine/disp.h | 1 + .../gpu/drm/nouveau/nvkm/engine/device/base.c | 10 +-- .../gpu/drm/nouveau/nvkm/engine/disp/Kbuild | 1 + .../gpu/drm/nouveau/nvkm/engine/disp/gb202.c | 88 +++++++++++++++++++ 4 files changed, 95 insertions(+), 5 deletions(-) create mode 100644 drivers/gpu/drm/nouveau/nvkm/engine/disp/gb202.c diff --git a/drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h b/drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h index 7903d7470d19..01145db32c53 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h @@ -87,4 +87,5 @@ int gp102_disp_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct int gv100_disp_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_disp **); int tu102_disp_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_disp **); int ga102_disp_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_disp **); +int gb202_disp_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_disp **); #endif diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c index ea62dc97f118..96c8a5b29999 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c @@ -2846,7 +2846,7 @@ nv1b2_chipset = { .pci = { 0x00000001, gh100_pci_new }, .timer = { 0x00000001, gk20a_timer_new }, .vfn = { 0x00000001, ga100_vfn_new }, - .disp = { 0x00000001, ga102_disp_new }, + .disp = { 0x00000001, gb202_disp_new }, .fifo = { 0x00000001, ga102_fifo_new }, }; @@ -2862,7 +2862,7 @@ nv1b3_chipset = { .pci = { 0x00000001, gh100_pci_new }, .timer = { 0x00000001, gk20a_timer_new }, .vfn = { 0x00000001, ga100_vfn_new }, - .disp = { 0x00000001, ga102_disp_new }, + .disp = { 0x00000001, gb202_disp_new }, .fifo = { 0x00000001, ga102_fifo_new }, }; @@ -2878,7 +2878,7 @@ nv1b5_chipset = { .pci = { 0x00000001, gh100_pci_new }, .timer = { 0x00000001, gk20a_timer_new }, .vfn = { 0x00000001, ga100_vfn_new }, - .disp = { 0x00000001, ga102_disp_new }, + .disp = { 0x00000001, gb202_disp_new }, .fifo = { 0x00000001, ga102_fifo_new }, }; @@ -2894,7 +2894,7 @@ nv1b6_chipset = { .pci = { 0x00000001, gh100_pci_new }, .timer = { 0x00000001, gk20a_timer_new }, .vfn = { 0x00000001, ga100_vfn_new }, - .disp = { 0x00000001, ga102_disp_new }, + .disp = { 0x00000001, gb202_disp_new }, .fifo = { 0x00000001, ga102_fifo_new }, }; @@ -2910,7 +2910,7 @@ nv1b7_chipset = { .pci = { 0x00000001, gh100_pci_new }, .timer = { 0x00000001, gk20a_timer_new }, .vfn = { 0x00000001, ga100_vfn_new }, - .disp = { 0x00000001, ga102_disp_new }, + .disp = { 0x00000001, gb202_disp_new }, .fifo = { 0x00000001, ga102_fifo_new }, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild index e1aecd3fe96c..98d6ca5ac311 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild @@ -27,6 +27,7 @@ nvkm-y += nvkm/engine/disp/gp102.o nvkm-y += nvkm/engine/disp/gv100.o nvkm-y += nvkm/engine/disp/tu102.o nvkm-y += nvkm/engine/disp/ga102.o +nvkm-y += nvkm/engine/disp/gb202.o nvkm-y += nvkm/engine/disp/udisp.o nvkm-y += nvkm/engine/disp/uconn.o diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gb202.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gb202.c new file mode 100644 index 000000000000..1e40de83e2bb --- /dev/null +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gb202.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright 2026 Valve Corp. + */ +#include "priv.h" +#include "head.h" +#include "ior.h" + +#include + +/* GB20x (NVD5.0) reorganised the SF HDMI packet units. The AVI unit is + * unchanged from GV100, but the legacy VSI unit is gone. Vendor infoframes + * are sent through the shared generic infoframe units instead. Register + * layout per NVIDIA's clc971.h/clca71.h, programming sequence per + * nvhdmipkt_C971.c:programAdvancedInfoframeC971(). + */ +static void +gb202_sor_hdmi_infoframe_vsi(struct nvkm_ior *ior, int head, void *data, u32 size) +{ + struct nvkm_device *device = ior->disp->engine.subdev.device; + const u32 hoff = head * 0x400; + /* Generic infoframe unit 1, the slot NVIDIA's driver uses for the VSI. */ + const u32 ctrl = 0x6f0138 + hoff; + u8 buf[36] = {}; + int i; + + /* Disable the unit and wait for it to go idle. */ + nvkm_mask(device, ctrl, 0x00000001, 0x00000000); + if (nvkm_msec(device, 2000, + if (!(nvkm_rd32(device, ctrl) & 0x00400000)) + break; + ) < 0) + return; + + if (!size) + return; + + /* Clear SENT status, and point the data port at unit 1's slot. */ + nvkm_mask(device, ctrl, 0x00800000, 0x00800000); + nvkm_wr32(device, 0x6f03f0 + hoff, 0x00000001); + + /* The data port takes the raw packet, except that a zero is inserted + * in HB3 after the three header bytes. A slot is 9 dwords (HB0-3 plus + * up to 32 payload bytes). An HDMI infoframe carries at most PB0-27, + * so the tail stays zero, and we always write the whole slot. + */ + size = min_t(u32, size, 31); + memcpy(buf, data, min_t(u32, size, 3)); + if (size > 3) + memcpy(&buf[4], (u8 *)data + 3, size - 3); + + for (i = 0; i < 36; i += 4) { + nvkm_wr32(device, 0x6f03f4 + hoff, buf[i + 0] | buf[i + 1] << 8 | + buf[i + 2] << 16 | + (u32)buf[i + 3] << 24); + } + + /* No flip ID or scanline matching. */ + nvkm_wr32(device, 0x6f013c + hoff, 0x00000000); + + /* ENABLE | RUN_MODE=ALWAYS | LOC=VBLANK | OFFSET=1 | SIZE=0. */ + nvkm_wr32(device, ctrl, 0x00000041); + + /* Audio priority low (the init value). */ + nvkm_wr32(device, 0x6f03f8 + hoff, 0x00000002); +} + +/* GB20x is GSP-only. This table supplies the register programming the + * GSP-RM display path needs from the chip. + */ +static const struct nvkm_disp_func +gb202_gsp_disp = { + .uevent = &gv100_disp_chan_uevent, + .ramht_size = 0x2000, + .gsp.intr = tu102_disp_intr, + .gsp.head = &tu102_gsp_head, + .gsp.hdmi_gcp = tu102_sor_hdmi_gcp, + /* The legacy AVI unit is unchanged on GB20x. */ + .gsp.hdmi_infoframe_avi = gv100_sor_hdmi_infoframe_avi, + .gsp.hdmi_infoframe_vsi = gb202_sor_hdmi_infoframe_vsi, +}; + +int +gb202_disp_new(struct nvkm_device *device, enum nvkm_subdev_type type, int inst, + struct nvkm_disp **pdisp) +{ + return r535_disp_new(&gb202_gsp_disp, device, type, inst, pdisp); +} From 764deff8450c9a83e335c17c32ea258ec25bb71e Mon Sep 17 00:00:00 2001 From: Mohamed Ahmed Date: Tue, 25 Aug 2026 04:14:03 +0400 Subject: [PATCH 0112/1198] drm/nouveau/disp: fix HDMI GCP AVMute register offsets on GB20x The GSP path brackets audio enablement with a General Control Packet AVMute toggle. r535_sor_hdmi_audio() calls the gsp.hdmi_gcp hook, which every chip so far serves with tu102_sor_hdmi_gcp() and the legacy GCP unit at 0x6f00c0/0x6f00cc. On GB20x the SF packet units were compacted and the old generic and VSI units are gone (ACR keeps slot 2) and the GCP unit moved from slot 3 to slot 1 (control 0x6f0040 and subpack 0x6f004c from NVIDIA's published clc971.h. The same offsets are also used by OpenRM's hdmiWriteGeneralCtrlPacketC871() on these chips). The old addresses are reserved on GB20x, so the AVMute writes were silent no-ops and mitigated only by the equivalent GCP r535_sor_hdmi_audio() already sends through the SET_OD_PACKET RM control. Add a GB20x GCP writer using the new offsets and hook it into gb202_gsp_disp, keeping the direct MMIO path in sync with the hardware as on earlier chips. Only SB0 (the AVMute bit) is written. On NVD5.0 the subpack register also carries SB1_CTRL (bit 24), which selects where the deep-color CD/PP fields are generated (hardware or from the driver, with the default being HW). hdmiWriteGeneralCtrlPacketC871() likewise writes only SB0-SB2. Fixes: 6cc6e08d4542 ("drm/nouveau/kms: add support for GB20x") Cc: stable@vger.kernel.org Signed-off-by: Mohamed Ahmed Reviewed-by: Lyude Paul Signed-off-by: Lyude Paul Link: https://patch.msgid.link/20260825001408.14219-6-mohamedahmedegypt2001@gmail.com --- .../gpu/drm/nouveau/nvkm/engine/disp/gb202.c | 20 ++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gb202.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gb202.c index 1e40de83e2bb..face801af080 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gb202.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gb202.c @@ -65,6 +65,24 @@ gb202_sor_hdmi_infoframe_vsi(struct nvkm_ior *ior, int head, void *data, u32 siz nvkm_wr32(device, 0x6f03f8 + hoff, 0x00000002); } +/* General Control Packet AVMute bracket. The GCP unit moved to slot 1 on + * NVD5.0. Only SB0 (the AVMute bit) is ours to write so we must not do a + * full write here: SB1 carries the deep-color CD/PP fields, and SB1_CTRL + * (bit 24, new with clc871.h) controls where their generation happens (HW + * or driver) on these chips, with the default being HW. + */ +static void +gb202_sor_hdmi_gcp(struct nvkm_ior *sor, int head, bool enable) +{ + struct nvkm_device *device = sor->disp->engine.subdev.device; + const u32 hdmi = head * 0x400; + + nvkm_mask(device, 0x6f0040 + hdmi, 0x00000001, 0x00000000); + nvkm_mask(device, 0x6f004c + hdmi, 0x000000ff, !enable ? 0x00000001 : + 0x00000010); + nvkm_mask(device, 0x6f0040 + hdmi, 0x00000001, 0x00000001); +} + /* GB20x is GSP-only. This table supplies the register programming the * GSP-RM display path needs from the chip. */ @@ -74,7 +92,7 @@ gb202_gsp_disp = { .ramht_size = 0x2000, .gsp.intr = tu102_disp_intr, .gsp.head = &tu102_gsp_head, - .gsp.hdmi_gcp = tu102_sor_hdmi_gcp, + .gsp.hdmi_gcp = gb202_sor_hdmi_gcp, /* The legacy AVI unit is unchanged on GB20x. */ .gsp.hdmi_infoframe_avi = gv100_sor_hdmi_infoframe_avi, .gsp.hdmi_infoframe_vsi = gb202_sor_hdmi_infoframe_vsi, From 39fd4b742720c68da8695ee1ffa85c5fea4f8e11 Mon Sep 17 00:00:00 2001 From: Mohamed Ahmed Date: Tue, 25 Aug 2026 04:14:04 +0400 Subject: [PATCH 0113/1198] drm/nouveau/gsp: use per-version DP_CONFIG_STREAM params on r570 firmware NVIDIA removed the deprecated actualPclkHz/linkClkFreqHz fields and the whole Legacy{activeCnt, activeFrac, activePolarity, mvidWarEnabled, MvidWarParams} block from the SST sub-struct of NV0073_CTRL_CMD_DP_CONFIG_STREAM_PARAMS between the 535 and 570 releases (compared in OpenRM tags 535.113.01 vs 570.144), shrinking the struct. Everything nouveau writes sits at identical offsets in both layouts except the trailing SST.bEnableAudioOverRightPanel (written as zero), but the size is wrong on r570, which means r535_sor_dp_sst() and r535_sor_dp_vcpi() are sent with an incorrect size. Route the .sst/.vcpi IOR functions through nvkm_rm_api_disp the same way bl_ctrl and dp.get_caps/set_indexed_link_rates already are. Keep the existing implementation for r535 and add an r570 implementation built against the 570.144 layout, which already exists in r570/nvrm/disp.h but was unused until now. Also add the NV0073_CTRL_CMD_DP_CONFIG_STREAM define that was missing from the layout. Other DP controls sent through shared r535 code did not change layout between the tags. Fixes: 6cc6e08d4542 ("drm/nouveau/kms: add support for GB20x") Cc: stable@vger.kernel.org Signed-off-by: Mohamed Ahmed Reviewed-by: Lyude Paul Signed-off-by: Lyude Paul Link: https://patch.msgid.link/20260825001408.14219-7-mohamedahmedegypt2001@gmail.com --- .../nouveau/nvkm/subdev/gsp/rm/r535/disp.c | 33 ++++++++-- .../nouveau/nvkm/subdev/gsp/rm/r570/disp.c | 64 +++++++++++++++++++ .../nvkm/subdev/gsp/rm/r570/nvrm/disp.h | 2 + .../gpu/drm/nouveau/nvkm/subdev/gsp/rm/rm.h | 5 ++ 4 files changed, 97 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c index bf97edcdfc95..7d1d4ee2af79 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c @@ -400,16 +400,16 @@ r535_sor_dp_audio(struct nvkm_ior *sor, int head, bool enable) r535_sor_dp_audio_mute(sor, false); } -static void -r535_sor_dp_vcpi(struct nvkm_ior *sor, int head, u8 slot, u8 slot_nr, u16 pbn, u16 aligned_pbn) +static int +r535_dp_vcpi(struct nvkm_ior *sor, int head, u8 slot, u8 slot_nr, u16 pbn, u16 aligned_pbn) { struct nvkm_disp *disp = sor->disp; struct NV0073_CTRL_CMD_DP_CONFIG_STREAM_PARAMS *ctrl; ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, NV0073_CTRL_CMD_DP_CONFIG_STREAM, sizeof(*ctrl)); - if (WARN_ON(IS_ERR(ctrl))) - return; + if (IS_ERR(ctrl)) + return PTR_ERR(ctrl); ctrl->subDeviceInstance = 0; ctrl->head = head; @@ -429,12 +429,20 @@ r535_sor_dp_vcpi(struct nvkm_ior *sor, int head, u8 slot, u8 slot_nr, u16 pbn, u ctrl->MST.sendACT = 0; ctrl->MST.singleHeadMSTPipeline = 0; ctrl->MST.bEnableAudioOverRightPanel = 0; - WARN_ON(nvkm_gsp_rm_ctrl_wr(&disp->rm.objcom, ctrl)); + return nvkm_gsp_rm_ctrl_wr(&disp->rm.objcom, ctrl); +} + +static void +r535_sor_dp_vcpi(struct nvkm_ior *sor, int head, u8 slot, u8 slot_nr, u16 pbn, u16 aligned_pbn) +{ + const struct nvkm_rm_api *rmapi = sor->disp->engine.subdev.device->gsp->rm->api; + + WARN_ON(rmapi->disp->dp.vcpi(sor, head, slot, slot_nr, pbn, aligned_pbn)); } static int -r535_sor_dp_sst(struct nvkm_ior *sor, int head, bool ef, - u32 watermark, u32 hblanksym, u32 vblanksym) +r535_dp_sst(struct nvkm_ior *sor, int head, bool ef, + u32 watermark, u32 hblanksym, u32 vblanksym) { struct nvkm_disp *disp = sor->disp; struct NV0073_CTRL_CMD_DP_CONFIG_STREAM_PARAMS *ctrl; @@ -461,6 +469,15 @@ r535_sor_dp_sst(struct nvkm_ior *sor, int head, bool ef, return nvkm_gsp_rm_ctrl_wr(&disp->rm.objcom, ctrl); } +static int +r535_sor_dp_sst(struct nvkm_ior *sor, int head, bool ef, + u32 watermark, u32 hblanksym, u32 vblanksym) +{ + const struct nvkm_rm_api *rmapi = sor->disp->engine.subdev.device->gsp->rm->api; + + return rmapi->disp->dp.sst(sor, head, ef, watermark, hblanksym, vblanksym); +} + static const struct nvkm_ior_func_dp r535_sor_dp = { .sst = r535_sor_dp_sst, @@ -1734,6 +1751,8 @@ r535_disp = { .dp = { .get_caps = r535_dp_get_caps, .set_indexed_link_rates = r535_dp_set_indexed_link_rates, + .sst = r535_dp_sst, + .vcpi = r535_dp_vcpi, }, .chan = { .set_pushbuf = r535_disp_chan_set_pushbuf, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/disp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/disp.c index a96e31c2d80b..8a23837f356e 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/disp.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/disp.c @@ -5,6 +5,7 @@ #include #include +#include #include #include "nvhw/drf.h" @@ -74,6 +75,67 @@ r570_disp_chan_set_pushbuf(struct nvkm_disp *disp, s32 oclass, int inst, struct return nvkm_gsp_rm_ctrl_wr(&gsp->internal.device.subdevice, ctrl); } +static int +r570_dp_vcpi(struct nvkm_ior *sor, int head, u8 slot, u8 slot_nr, u16 pbn, u16 aligned_pbn) +{ + struct nvkm_disp *disp = sor->disp; + NV0073_CTRL_CMD_DP_CONFIG_STREAM_PARAMS *ctrl; + + ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, + NV0073_CTRL_CMD_DP_CONFIG_STREAM, sizeof(*ctrl)); + if (IS_ERR(ctrl)) + return PTR_ERR(ctrl); + + ctrl->subDeviceInstance = 0; + ctrl->head = head; + ctrl->sorIndex = sor->id; + ctrl->dpLink = sor->asy.link == 2; + ctrl->bEnableOverride = 1; + ctrl->bMST = 1; + ctrl->hBlankSym = 0; + ctrl->vBlankSym = 0; + ctrl->colorFormat = 0; + ctrl->bEnableTwoHeadOneOr = 0; + ctrl->singleHeadMultistreamMode = 0; + ctrl->MST.slotStart = slot; + ctrl->MST.slotEnd = slot + slot_nr - 1; + ctrl->MST.PBN = pbn; + ctrl->MST.Timeslice = aligned_pbn; + ctrl->MST.sendACT = 0; + ctrl->MST.singleHeadMSTPipeline = 0; + ctrl->MST.bEnableAudioOverRightPanel = 0; + return nvkm_gsp_rm_ctrl_wr(&disp->rm.objcom, ctrl); +} + +static int +r570_dp_sst(struct nvkm_ior *sor, int head, bool ef, + u32 watermark, u32 hblanksym, u32 vblanksym) +{ + struct nvkm_disp *disp = sor->disp; + NV0073_CTRL_CMD_DP_CONFIG_STREAM_PARAMS *ctrl; + + ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, + NV0073_CTRL_CMD_DP_CONFIG_STREAM, sizeof(*ctrl)); + if (IS_ERR(ctrl)) + return PTR_ERR(ctrl); + + ctrl->subDeviceInstance = 0; + ctrl->head = head; + ctrl->sorIndex = sor->id; + ctrl->dpLink = sor->asy.link == 2; + ctrl->bEnableOverride = 1; + ctrl->bMST = 0; + ctrl->hBlankSym = hblanksym; + ctrl->vBlankSym = vblanksym; + ctrl->colorFormat = 0; + ctrl->bEnableTwoHeadOneOr = 0; + ctrl->SST.bEnhancedFraming = ef; + ctrl->SST.tuSize = 64; + ctrl->SST.waterMark = watermark; + ctrl->SST.bEnableAudioOverRightPanel = 0; + return nvkm_gsp_rm_ctrl_wr(&disp->rm.objcom, ctrl); +} + static int r570_dp_set_indexed_link_rates(struct nvkm_outp *outp) { @@ -255,6 +317,8 @@ r570_disp = { .dp = { .get_caps = r570_dp_get_caps, .set_indexed_link_rates = r570_dp_set_indexed_link_rates, + .sst = r570_dp_sst, + .vcpi = r570_dp_vcpi, }, .chan = { .set_pushbuf = r570_disp_chan_set_pushbuf, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/nvrm/disp.h b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/nvrm/disp.h index 06e972835d77..742b25a2a12d 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/nvrm/disp.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/nvrm/disp.h @@ -256,6 +256,8 @@ typedef struct NV0073_CTRL_DP_CTRL_PARAMS { NvU32 eightLaneDpcdBaseAddr; } NV0073_CTRL_DP_CTRL_PARAMS; +#define NV0073_CTRL_CMD_DP_CONFIG_STREAM (0x731362U) /* finn: Evaluated from "(FINN_NV04_DISPLAY_COMMON_DP_INTERFACE_ID << 8) | NV0073_CTRL_CMD_DP_CONFIG_STREAM_PARAMS_MESSAGE_ID" */ + typedef struct NV0073_CTRL_CMD_DP_CONFIG_STREAM_PARAMS { NvU32 subDeviceInstance; NvU32 head; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/rm.h b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/rm.h index a9af94adf9ef..fcd0221dcea1 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/rm.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/rm.h @@ -6,6 +6,7 @@ #ifndef __NVKM_RM_H__ #define __NVKM_RM_H__ #include "handles.h" +struct nvkm_ior; struct nvkm_outp; struct r535_gr; @@ -93,6 +94,10 @@ struct nvkm_rm_api { struct { int (*get_caps)(struct nvkm_disp *, int *link_bw, bool *mst, bool *wm); int (*set_indexed_link_rates)(struct nvkm_outp *); + int (*sst)(struct nvkm_ior *, int head, bool ef, + u32 watermark, u32 hblanksym, u32 vblanksym); + int (*vcpi)(struct nvkm_ior *, int head, + u8 slot, u8 slot_nr, u16 pbn, u16 aligned_pbn); } dp; struct { From 9421dfe912e55360e6b9301a110acb00df7e7320 Mon Sep 17 00:00:00 2001 From: Mohamed Ahmed Date: Tue, 25 Aug 2026 04:14:05 +0400 Subject: [PATCH 0114/1198] drm/nouveau/disp: fix head state readback on GB20x The GSP path reads armed head state and the RG scanout position through gv100_head_state() and gv100_head_rgpos() on every generation. gv100_head_state() reads the core channel's state mirror at a 0x400 per-head stride, which NVD5.0 (GB20x) doubled. Per NVIDIA's published CA7D class header every HEAD_SET method sits at 0x2000 + head * 0x800, while the mirror bases are unchanged (assembly at 0x680000, armed at +0x8000, per OpenRM's v03_00 channel-user-base HAL which is still used on DISPv0502). Add gb202_head_state(), the same readback at the 0x800 stride, and a gb202_gsp_head table to supply it. gv100_head_rgpos() is kept. The RG registers keep their per-head 0x800 stride on NVD5.0, and OpenRM's kdispReadRgLineCountAndFrameCount_v03_00 still reads NV_PDISP_RG_DPCA on DISPv0502. Fixes: 6cc6e08d4542 ("drm/nouveau/kms: add support for GB20x") Cc: stable@vger.kernel.org Signed-off-by: Mohamed Ahmed Reviewed-by: Lyude Paul Signed-off-by: Lyude Paul Link: https://patch.msgid.link/20260825001408.14219-8-mohamedahmedegypt2001@gmail.com --- .../gpu/drm/nouveau/nvkm/engine/disp/gb202.c | 51 ++++++++++++++++++- 1 file changed, 50 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gb202.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gb202.c index face801af080..765c42039a47 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gb202.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gb202.c @@ -83,6 +83,55 @@ gb202_sor_hdmi_gcp(struct nvkm_ior *sor, int head, bool enable) nvkm_mask(device, 0x6f0040 + hdmi, 0x00000001, 0x00000001); } +/* Same core-channel state mirror as gv100_head_state() (assembly at 0x680000, + * armed at +0x8000, per-head method offsets unchanged), but NVD5.0 spaces + * heads 0x800 apart (see NVCA7D_HEAD_SET_*(a) in clca7d.h). + */ +static void +gb202_head_state(struct nvkm_head *head, struct nvkm_head_state *state) +{ + struct nvkm_device *device = head->disp->engine.subdev.device; + const u32 hoff = (state == &head->arm) * 0x8000 + head->id * 0x800; + u32 data; + + data = nvkm_rd32(device, 0x682064 + hoff); + state->vtotal = (data & 0xffff0000) >> 16; + state->htotal = (data & 0x0000ffff); + data = nvkm_rd32(device, 0x682068 + hoff); + state->vsynce = (data & 0xffff0000) >> 16; + state->hsynce = (data & 0x0000ffff); + data = nvkm_rd32(device, 0x68206c + hoff); + state->vblanke = (data & 0xffff0000) >> 16; + state->hblanke = (data & 0x0000ffff); + data = nvkm_rd32(device, 0x682070 + hoff); + state->vblanks = (data & 0xffff0000) >> 16; + state->hblanks = (data & 0x0000ffff); + /* Bit 31 is ADJ1000DIV1001, not a HERTZ bit. We don't have enough bits + * to add the full clock in hz on Blackwell (35 bits), but state->hz + * is unused and obsolete under GSP so this is fine. + */ + state->hz = nvkm_rd32(device, 0x68200c + hoff) & 0x7fffffff; + + data = nvkm_rd32(device, 0x682004 + hoff); + switch ((data & 0x000000f0) >> 4) { + case 5: state->or.depth = 30; break; + case 4: state->or.depth = 24; break; + case 1: state->or.depth = 18; break; + default: + state->or.depth = 18; + WARN_ON(1); + break; + } +} + +static const struct nvkm_head_func +gb202_gsp_head = { + .state = gb202_head_state, + .rgpos = gv100_head_rgpos, + .vblank_get = tu102_head_vblank_get, + .vblank_put = tu102_head_vblank_put, +}; + /* GB20x is GSP-only. This table supplies the register programming the * GSP-RM display path needs from the chip. */ @@ -91,7 +140,7 @@ gb202_gsp_disp = { .uevent = &gv100_disp_chan_uevent, .ramht_size = 0x2000, .gsp.intr = tu102_disp_intr, - .gsp.head = &tu102_gsp_head, + .gsp.head = &gb202_gsp_head, .gsp.hdmi_gcp = gb202_sor_hdmi_gcp, /* The legacy AVI unit is unchanged on GB20x. */ .gsp.hdmi_infoframe_avi = gv100_sor_hdmi_infoframe_avi, From 5bb489b333237c1bf63a891a4362986253a0060a Mon Sep 17 00:00:00 2001 From: Mohamed Ahmed Date: Tue, 25 Aug 2026 04:14:06 +0400 Subject: [PATCH 0115/1198] drm/nouveau/gsp: fix vblank interrupts on GB20x The GSP path programs per-head timing (vblank) interrupts the same way on every generation. NVD5.0 (GB20x) reworked the FE interrupt frontend around four message-based kernel vectors (high latency, low latency, PMU, and GSP) and moved RM head-timing interrupts to the dedicated low-latency vector: - The enable is NV_PDISP_FE_RM_INTR_EN1_HEAD_TIMING, 0x611ef0 + head*4 (570.144 kernel_head_0501.c, renamed kernel_head_0502.c from 575.51.02 on, and v05_01 dev_disp.h). - The vector is reported as a separate interrupt table entry, MC_ENGINE_IDX_DISP_LOW (intr_gb202.c, intrCacheDispIntrVectors). - The vector must be re-armed through NV_PDISP_FE_INTR_RETRIGGER(1) at 0x611f34 after servicing (kdispServiceInterrupt -> kdispIntrRetrigger_v05_01). The event latch (0x611800), per-head status (0x611c00), and dispatch summary (0x611ec0) the interrupt handler uses are unchanged on GB20x (kheadReadPendingVblank_v03_00 and kheadResetPendingLastData_v03_00 remain for DISPv0502+). On GB20x the old code enables head timing onto the legacy vector, leaves its handler there, and never re-arms the message-based vectors. Page flips still complete (nv50 sends those events from the commit path), so the desktop looks fine while DRM vblank waits and vblank sequence queries are affected. Supply GB20x vblank enables and an interrupt handler that re-arms the vector after servicing through gb202_gsp_disp, translate the low-latency interrupt table entry as a second NVKM_ENGINE_DISP instance, and add a gsp.intr_low_latency flag so r535_disp_oneinit() attaches the handler to that instance. GB20x was the last cross-file user of the TU1xx vblank enables, so make those static and drop their head.h prototypes. Fixes: 6cc6e08d4542 ("drm/nouveau/kms: add support for GB20x") Cc: stable@vger.kernel.org Signed-off-by: Mohamed Ahmed Reviewed-by: Lyude Paul Signed-off-by: Lyude Paul Link: https://patch.msgid.link/20260825001408.14219-9-mohamedahmedegypt2001@gmail.com --- .../gpu/drm/nouveau/nvkm/engine/disp/gb202.c | 42 +++++++++++++++++-- .../gpu/drm/nouveau/nvkm/engine/disp/head.h | 2 - .../gpu/drm/nouveau/nvkm/engine/disp/priv.h | 2 + .../gpu/drm/nouveau/nvkm/engine/disp/tu102.c | 4 +- .../nouveau/nvkm/subdev/gsp/rm/r535/disp.c | 10 ++++- .../drm/nouveau/nvkm/subdev/gsp/rm/r570/gsp.c | 9 ++++ 6 files changed, 61 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gb202.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gb202.c index 765c42039a47..d0360610f9fa 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gb202.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gb202.c @@ -124,12 +124,46 @@ gb202_head_state(struct nvkm_head *head, struct nvkm_head_state *state) } } +/* NVD5.0 (GB20x and later) moved the RM head-timing interrupt enable to + * the low-latency vector's EN1 block. The event latch is unchanged. + */ +static void +gb202_head_vblank_put(struct nvkm_head *head) +{ + struct nvkm_device *device = head->disp->engine.subdev.device; + + nvkm_mask(device, 0x611ef0 + (head->id * 4), 0x00000002, 0x00000000); +} + +static void +gb202_head_vblank_get(struct nvkm_head *head) +{ + struct nvkm_device *device = head->disp->engine.subdev.device; + + nvkm_wr32(device, 0x611800 + (head->id * 4), 0x00000002); + nvkm_mask(device, 0x611ef0 + (head->id * 4), 0x00000002, 0x00000002); +} + +static irqreturn_t +gb202_disp_intr(struct nvkm_inth *inth) +{ + struct nvkm_disp *disp = container_of(inth, typeof(*disp), engine.subdev.inth); + irqreturn_t ret = tu102_disp_intr(inth); + + /* The FE interrupt vectors are message-based on NVD5.0. Re-arm the + * low-latency vector so it fires again for any event that latched + * while we were servicing. + */ + nvkm_wr32(disp->engine.subdev.device, 0x611f34, 0x00000001); + return ret; +} + static const struct nvkm_head_func gb202_gsp_head = { .state = gb202_head_state, .rgpos = gv100_head_rgpos, - .vblank_get = tu102_head_vblank_get, - .vblank_put = tu102_head_vblank_put, + .vblank_get = gb202_head_vblank_get, + .vblank_put = gb202_head_vblank_put, }; /* GB20x is GSP-only. This table supplies the register programming the @@ -139,7 +173,9 @@ static const struct nvkm_disp_func gb202_gsp_disp = { .uevent = &gv100_disp_chan_uevent, .ramht_size = 0x2000, - .gsp.intr = tu102_disp_intr, + /* Head timing arrives on the dedicated low-latency vector. */ + .gsp.intr = gb202_disp_intr, + .gsp.intr_low_latency = true, .gsp.head = &gb202_gsp_head, .gsp.hdmi_gcp = gb202_sor_hdmi_gcp, /* The legacy AVI unit is unchanged on GB20x. */ diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/head.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/head.h index 784521c2aca1..5976498da909 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/head.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/head.h @@ -56,8 +56,6 @@ int gv100_head_new(struct nvkm_disp *, int id); void gv100_head_state(struct nvkm_head *head, struct nvkm_head_state *state); void gv100_head_rgpos(struct nvkm_head *head, u16 *hline, u16 *vline); -void tu102_head_vblank_get(struct nvkm_head *); -void tu102_head_vblank_put(struct nvkm_head *); extern const struct nvkm_head_func tu102_gsp_head; #define HEAD_MSG(h,l,f,a...) do { \ diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/priv.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/priv.h index a9dbda67a7d4..fde321dbd7c8 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/priv.h @@ -42,6 +42,8 @@ struct nvkm_disp_func { */ struct { irqreturn_t (*intr)(struct nvkm_inth *); + /* Head-timing interrupts arrive on a second DISP vector. */ + bool intr_low_latency; const struct nvkm_head_func *head; void (*hdmi_gcp)(struct nvkm_ior *, int head, bool enable); void (*hdmi_infoframe_avi)(struct nvkm_ior *, int head, void *data, u32 size); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c index 948b1d2f954c..f6c163072ff6 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c @@ -123,7 +123,7 @@ tu102_sor_new(struct nvkm_disp *disp, int id) * enables to us. These program the RM head-timing line (bit 1 of the * per-head enable, not the bit nvkm's own gv100 path uses). */ -void +static void tu102_head_vblank_put(struct nvkm_head *head) { struct nvkm_device *device = head->disp->engine.subdev.device; @@ -131,7 +131,7 @@ tu102_head_vblank_put(struct nvkm_head *head) nvkm_mask(device, 0x611d80 + (head->id * 4), 0x00000002, 0x00000000); } -void +static void tu102_head_vblank_get(struct nvkm_head *head) { struct nvkm_device *device = head->disp->engine.subdev.device; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c index 7d1d4ee2af79..f5f22173fc2c 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/disp.c @@ -1671,7 +1671,15 @@ r535_disp_oneinit(struct nvkm_disp *disp) if (ret) return ret; - ret = nvkm_gsp_intr_stall(gsp, disp->engine.subdev.type, disp->engine.subdev.inst); + /* Chips that raise head-timing interrupts on a separate low-latency + * vector report it as a second DISP interrupt table entry, exposed + * as instance 1 by the RM engine-index translation (see + * r570_gsp_xlat_mc_engine_idx()). Their high-latency vector + * (instance 0) is left unhandled as no event nouveau enables is + * routed to it, and without a handler it stays masked. + */ + ret = nvkm_gsp_intr_stall(gsp, disp->engine.subdev.type, + disp->func->gsp.intr_low_latency ? 1 : disp->engine.subdev.inst); if (ret < 0) return ret; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/gsp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/gsp.c index 996941c668ba..1488771c63fc 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/gsp.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/gsp.c @@ -44,6 +44,15 @@ r570_gsp_xlat_mc_engine_idx(u32 mc_engine_idx, enum nvkm_subdev_type *ptype, int *ptype = NVKM_ENGINE_DISP; *pinst = 0; return true; + case MC_ENGINE_IDX_DISP_LOW: + /* GB20x+ report a separate low-latency display vector, used + * for head-timing interrupts. Expose it as a second DISP + * interrupt instance. r535_disp_oneinit() attaches the + * handler to it when the chip's gsp.intr_low_latency is set. + */ + *ptype = NVKM_ENGINE_DISP; + *pinst = 1; + return true; case MC_ENGINE_IDX_CE0 ... MC_ENGINE_IDX_CE19: *ptype = NVKM_ENGINE_CE; *pinst = mc_engine_idx - MC_ENGINE_IDX_CE0; From c6f48e59ece0123f6a11527ad4d89b21c2d65b87 Mon Sep 17 00:00:00 2001 From: Shixiong Ou Date: Tue, 25 Aug 2026 18:41:34 +0800 Subject: [PATCH 0116/1198] drm/sysfb: ofdrm: Fix integer overflow in fb_size calculation The framebuffer size calculation `fb_size = linebytes * height` can overflow when both values are large (e.g., 46341 * 46341 > INT_MAX). Since linebytes and height are both int types, the multiplication is performed as int * int, which results in undefined behavior on overflow. Use check_mul_overflow() to detect and prevent this overflow, consistent with the approach used in simpledrm.c and corebootdrm.c. Signed-off-by: Shixiong Ou Reviewed-by: Thomas Zimmermann Signed-off-by: Thomas Zimmermann Fixes: c8a17756c425 ("drm/ofdrm: Add ofdrm for Open Firmware framebuffers") Cc: # v6.2+ Link: https://patch.msgid.link/20260825104134.669676-1-oushixiong1025@163.com --- drivers/gpu/drm/sysfb/ofdrm.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/sysfb/ofdrm.c b/drivers/gpu/drm/sysfb/ofdrm.c index 819aed466727..a6dc34b9ec0f 100644 --- a/drivers/gpu/drm/sysfb/ofdrm.c +++ b/drivers/gpu/drm/sysfb/ofdrm.c @@ -2,6 +2,7 @@ #include #include +#include #include #include #include @@ -913,7 +914,10 @@ static struct ofdrm_device *ofdrm_device_create(struct drm_driver *drv, return ERR_PTR(-EINVAL); } - fb_size = linebytes * height; + if (check_mul_overflow(linebytes, height, &fb_size)) { + drm_err(dev, "framebuffer size exceeds maximum\n"); + return ERR_PTR(-EINVAL); + } /* * Try to figure out the address of the framebuffer. Unfortunately, Open From 958f35cbb8955ca3fa439cd9f2092cb42414aa8c Mon Sep 17 00:00:00 2001 From: Shixiong Ou Date: Fri, 31 Jul 2026 19:17:29 +0800 Subject: [PATCH 0117/1198] drm/sysfb: ofdrm: Fix is_avivo() constant comparison bug The is_avivo() function has a logic error where it compares a constant to another constant instead of checking the device parameter: (PCI_VENDOR_ID_ATI_R600 >= 0x9400) Signed-off-by: Shixiong Ou Reviewed-by: Thomas Zimmermann Fixes: f496834e1674 ("drm/ofdrm: Add per-model device function") Signed-off-by: Thomas Zimmermann Cc: # v6.2+ Link: https://patch.msgid.link/20260731111729.703116-1-oushixiong1025@163.com --- drivers/gpu/drm/sysfb/ofdrm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/sysfb/ofdrm.c b/drivers/gpu/drm/sysfb/ofdrm.c index a6dc34b9ec0f..9d60db45139c 100644 --- a/drivers/gpu/drm/sysfb/ofdrm.c +++ b/drivers/gpu/drm/sysfb/ofdrm.c @@ -239,7 +239,7 @@ static bool is_avivo(u32 vendor, u32 device) /* This will match most R5xx */ return (vendor == PCI_VENDOR_ID_ATI) && ((device >= PCI_VENDOR_ID_ATI_R520 && device < 0x7800) || - (PCI_VENDOR_ID_ATI_R600 >= 0x9400)); + (device >= PCI_VENDOR_ID_ATI_R600)); } static enum ofdrm_model display_get_model_of(struct drm_device *dev, struct device_node *of_node) From 92312d333bf700798f92f30406c721bce87506f3 Mon Sep 17 00:00:00 2001 From: Slawomir Stepien Date: Tue, 25 Aug 2026 14:07:29 +0200 Subject: [PATCH 0118/1198] drm/cirrus-qemu: Validate BAR0 size during probe The `cirrus-qemu` driver relies on `CIRRUS_VRAM_SIZE` (4 MB) to validate framebuffer sizes. However, during PCI probe, the driver mapped BAR0 without verifying that its size matches `CIRRUS_VRAM_SIZE`. If a PCI device with a BAR0 smaller than 4 MB is bound to the driver, the mapped VRAM will be smaller than expected. Because validation checks assume 4 MB VRAM, framebuffers larger than the mapped memory can be created. When the display plane is updated (e.g. during release), `cirrus_primary_plane_helper_atomic_update()` copies the framebuffer to VRAM using `drm_fb_memcpy()`. Writing past the end of the mapped I/O memory causes a supervisor write page fault: BUG: unable to handle page fault for address: ffffc9000389c000 ... RIP: 0010:memcpy_toio+0x7c/0xe0 arch/x86/lib/iomem.c:110 ... Call Trace: iosys_map_memcpy_to include/linux/iosys-map.h:285 [inline] drm_fb_memcpy+0x325/0x5d0 drivers/gpu/drm/drm_format_helper.c:442 cirrus_primary_plane_helper_atomic_update+0x98a/0xb00 drivers/gpu/drm/tiny/cirrus-qemu.c:358 drm_atomic_helper_commit_planes+0x626/0xea0 drivers/gpu/drm/drm_atomic_helper.c:3038 drm_atomic_helper_commit_tail+0x60/0x510 drivers/gpu/drm/drm_atomic_helper.c:1989 commit_tail+0x2b1/0x3c0 drivers/gpu/drm/drm_atomic_helper.c:2074 drm_atomic_helper_commit+0xa77/0xb10 drivers/gpu/drm/drm_atomic_helper.c:2312 Fix this by validating in `cirrus_pci_probe()` that the PCI BAR0 resource is not less than `CIRRUS_VRAM_SIZE`, returning `-ENODEV` if it is less. Fixes: ab3e023b1b4c ("drm/cirrus: rewrite and modernize driver.") Assisted-by: Gemini:gemini-3.6-flash Gemini:gemini-3.1-pro-preview syzbot Reported-by: syzbot+2442951a6abb004df963@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=2442951a6abb004df963 Link: https://syzkaller.appspot.com/ai_job?id=ba262a3a-bccf-4ad8-a1b0-583c55d34fd6 Signed-off-by: Slawomir Stepien Signed-off-by: Thomas Zimmermann Reviewed-by: Thomas Zimmermann Link: https://patch.msgid.link/20260825120729.493611-1-sst@poczta.fm --- drivers/gpu/drm/tiny/cirrus-qemu.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/tiny/cirrus-qemu.c b/drivers/gpu/drm/tiny/cirrus-qemu.c index 075221b431d3..3bf23fcf6574 100644 --- a/drivers/gpu/drm/tiny/cirrus-qemu.c +++ b/drivers/gpu/drm/tiny/cirrus-qemu.c @@ -582,6 +582,9 @@ static int cirrus_pci_probe(struct pci_dev *pdev, struct cirrus_device *cirrus; int ret; + if (pci_resource_len(pdev, 0) < CIRRUS_VRAM_SIZE) + return -ENODEV; + ret = aperture_remove_conflicting_pci_devices(pdev, cirrus_driver.name); if (ret) return ret; From d32b08284f44c20edb2ea3f64ba0a6a165036fb2 Mon Sep 17 00:00:00 2001 From: Thadeu Lima de Souza Cascardo Date: Mon, 17 Aug 2026 15:45:20 -0300 Subject: [PATCH 0119/1198] drm/atomic: remove bogus check for file_priv Since file_priv can never be NULL at prepare_signaling() as it is only called by drm_mode_atomic_ioctl(), remove the check. If that was not the case, skipping the rest of the block here would cause the drm_pending_vblank_event object to leak and fail to set up the fence in case out_fence_ptr is set. Since the check is unreachable, there is no possible leak. Signed-off-by: Thadeu Lima de Souza Cascardo Reviewed-by: Melissa Wen Signed-off-by: Melissa Wen Link: https://patch.msgid.link/20260817-drm_atomic_bogus_check-v2-1-2b9e60f32a7e@igalia.com --- drivers/gpu/drm/drm_atomic_uapi.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/gpu/drm/drm_atomic_uapi.c b/drivers/gpu/drm/drm_atomic_uapi.c index e997917819e8..657c15474ed5 100644 --- a/drivers/gpu/drm/drm_atomic_uapi.c +++ b/drivers/gpu/drm/drm_atomic_uapi.c @@ -1445,9 +1445,6 @@ static int prepare_signaling(struct drm_device *dev, if (arg->flags & DRM_MODE_PAGE_FLIP_EVENT) { struct drm_pending_vblank_event *e = crtc_state->event; - if (!file_priv) - continue; - ret = drm_event_reserve_init(dev, file_priv, &e->base, &e->event.base); if (ret) { From 4d4be202165e832d74849b4a68e289a2a377039c Mon Sep 17 00:00:00 2001 From: Thadeu Lima de Souza Cascardo Date: Mon, 27 Jul 2026 17:45:49 -0300 Subject: [PATCH 0120/1198] drm: Fix drm_crtc_commit leak if signaled when PAGE_FLIP_EVENT is used Commit 1c6ceeee6ebb ("drm/atomic: Fix memleak on ERESTARTSYS during non-blocking commits") fixed a very similar issue when the event was allocated by drm_atomic_helper_setup_commit() itself. However, if the event is allocated in prepare_signaling(), it will also be set to NULL in complete_signaling(), which prevents drm_crtc_commit from being put in __drm_atomic_helper_crtc_destroy_state(). Dropping the reference when the event is set to NULL at complete_signaling() fixes the leak. The leak can be reproduced by sending a signal to the thread using DRM_MODE_PAGE_FLIP_EVENT and using a sw_sync fence to cause the atomic ioctl to block at drm_atomic_helper_wait_for_fences(). It happened both with amdgpu and vkms. Fixes: 24835e442f28 ("drm: reference count event->completion") Cc: stable@vger.kernel.org Signed-off-by: Thadeu Lima de Souza Cascardo Reviewed-by: Melissa Wen Signed-off-by: Melissa Wen Link: https://patch.msgid.link/20260727-drm_crtc_atomic_commit_leak-v1-1-23d9948a9d7c@igalia.com --- drivers/gpu/drm/drm_atomic_uapi.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/drm_atomic_uapi.c b/drivers/gpu/drm/drm_atomic_uapi.c index 657c15474ed5..ae7667d1072d 100644 --- a/drivers/gpu/drm/drm_atomic_uapi.c +++ b/drivers/gpu/drm/drm_atomic_uapi.c @@ -1560,6 +1560,8 @@ static void complete_signaling(struct drm_device *dev, * to prevent a double free in drm_atomic_commit_clear. */ if (event && (event->base.fence || event->base.file_priv)) { + if (crtc_state->commit && crtc_state->commit->abort_completion) + drm_crtc_commit_put(crtc_state->commit); drm_event_cancel_free(dev, &event->base); crtc_state->event = NULL; } From 3d3de2aee17d1431694aa085039479b5679e5ad4 Mon Sep 17 00:00:00 2001 From: Baolin Liu Date: Fri, 21 Aug 2026 13:32:30 +0800 Subject: [PATCH 0121/1198] ntfs: return DT_UNKNOWN on inode lookup failure in readdir ntfs_reparse_tag_dt_types() returns PTR_ERR(vi) when ntfs_iget() fails, but its return type is unsigned int and the caller passes the value straight to dir_emit() as d_type. A stale or corrupt MFT reference in a directory index thus makes readdir report a garbage d_type value to userspace. Return DT_UNKNOWN on lookup failure instead. Fixes: fc053f05ca28 ("ntfs: add reparse and ea operations") Signed-off-by: Baolin Liu Reviewed-by: Hyunchul Lee Signed-off-by: Namjae Jeon --- fs/ntfs/reparse.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ntfs/reparse.c b/fs/ntfs/reparse.c index 5e483a2f9060..1cc6dfe19fed 100644 --- a/fs/ntfs/reparse.c +++ b/fs/ntfs/reparse.c @@ -405,7 +405,7 @@ unsigned int ntfs_reparse_tag_dt_types(struct ntfs_volume *vol, unsigned long mr vi = ntfs_iget(vol->sb, mref); if (IS_ERR(vi)) - return PTR_ERR(vi); + return DT_UNKNOWN; reparse_attr = (struct reparse_point *)ntfs_attr_readall(NTFS_I(vi), AT_REPARSE_POINT, NULL, 0, &attr_size); From 9692b1b4fc00cf89628bc43f71729ab21f14f8d3 Mon Sep 17 00:00:00 2001 From: Baolin Liu Date: Fri, 21 Aug 2026 13:32:32 +0800 Subject: [PATCH 0122/1198] ntfs: propagate reparse index insertion failure update_reparse_data() ignores the return value of set_reparse_index(). When index insertion fails, the code removes the just-written reparse data as cleanup but still returns 0, so symlink(2) (and WSL special file creation) reports success while no reparse data exists on disk. When there was no previous reparse data (oldsize == 0), the failure was likewise silently ignored. Propagate the error to the caller. Fixes: fc053f05ca28 ("ntfs: add reparse and ea operations") Signed-off-by: Baolin Liu Reviewed-by: Hyunchul Lee Signed-off-by: Namjae Jeon --- fs/ntfs/reparse.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/ntfs/reparse.c b/fs/ntfs/reparse.c index 1cc6dfe19fed..1a6073e22677 100644 --- a/fs/ntfs/reparse.c +++ b/fs/ntfs/reparse.c @@ -694,8 +694,9 @@ static int update_reparse_data(struct ntfs_inode *ni, struct ntfs_index_context goto put_rp_inode; } - if (set_reparse_index(ni, xr, ((const struct reparse_point *)value)->reparse_tag) && - oldsize > 0) { + err = set_reparse_index(ni, xr, + ((const struct reparse_point *)value)->reparse_tag); + if (err && oldsize > 0) { /* * If cannot index, try to remove the reparse * data and log the error. There will be an From ada728801999e25e610091362447372f1b25dd25 Mon Sep 17 00:00:00 2001 From: Baolin Liu Date: Fri, 21 Aug 2026 13:32:33 +0800 Subject: [PATCH 0123/1198] ntfs: return -ERANGE for undersized xattr buffer When the value buffer passed to getxattr(2) for system.dos_attrib, system.ntfs_attrib or system.ntfs_attrib_be is smaller than the attribute value, ntfs_getxattr() returns -ENODATA, which tells userspace the attribute does not exist. The xattr API expects -ERANGE in this case, and ntfs_get_ea() in the same file already returns -ERANGE for regular EAs. Fixes: fc053f05ca28 ("ntfs: add reparse and ea operations") Signed-off-by: Baolin Liu Reviewed-by: Hyunchul Lee Signed-off-by: Namjae Jeon --- fs/ntfs/ea.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ntfs/ea.c b/fs/ntfs/ea.c index cdd306933d73..f6dbdfe6ff15 100644 --- a/fs/ntfs/ea.c +++ b/fs/ntfs/ea.c @@ -615,7 +615,7 @@ static int ntfs_getxattr(const struct xattr_handler *handler, if (!buffer) { err = sizeof(u8); } else if (size < sizeof(u8)) { - err = -ENODATA; + err = -ERANGE; } else { err = sizeof(u8); *(u8 *)buffer = (u8)(le32_to_cpu(ni->flags) & 0x3F); @@ -628,7 +628,7 @@ static int ntfs_getxattr(const struct xattr_handler *handler, if (!buffer) { err = sizeof(u32); } else if (size < sizeof(u32)) { - err = -ENODATA; + err = -ERANGE; } else { err = sizeof(u32); *(u32 *)buffer = le32_to_cpu(ni->flags); From 8efe00b098b5b3618c885d2a35a5edccfbfbec7d Mon Sep 17 00:00:00 2001 From: Baolin Liu Date: Fri, 21 Aug 2026 13:32:34 +0800 Subject: [PATCH 0124/1198] ntfs: preserve error code in ntfs_resident_attr_record_add() ntfs_resident_attr_record_add() collapses every failure to -EIO at its put_err_out label. This defeats the resident-to-non-resident fallback in ntfs_attr_add(), which relies on seeing -ENOSPC to convert the attribute when the MFT record has no room, and also hides -EEXIST and -ENOMEM from callers. Return the actual error code. Every path reaching the label has err set to a negative errno. Fixes: 495e90fa3348 ("ntfs: update attrib operations") Signed-off-by: Baolin Liu Reviewed-by: Hyunchul Lee Signed-off-by: Namjae Jeon --- fs/ntfs/attrib.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index 60264833bb63..3663259f0b7d 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -2500,7 +2500,7 @@ int ntfs_resident_attr_record_add(struct ntfs_inode *ni, __le32 type, return offset; put_err_out: ntfs_attr_put_search_ctx(ctx); - return -EIO; + return err; } /* From ba1b61ddaa764f31b14abe1d547049682cc5824e Mon Sep 17 00:00:00 2001 From: Baolin Liu Date: Fri, 21 Aug 2026 13:32:35 +0800 Subject: [PATCH 0125/1198] ntfs: return real error from ntfs_non_resident_attr_record_add() ntfs_non_resident_attr_record_add() returns -1 at its put_err_out label, which callers propagate as -EPERM to userspace. Return the actual error code. Every path reaching the label has err set to a negative errno. Fixes: 495e90fa3348 ("ntfs: update attrib operations") Signed-off-by: Baolin Liu Reviewed-by: Hyunchul Lee Signed-off-by: Namjae Jeon --- fs/ntfs/attrib.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index 3663259f0b7d..4dff5c3f779b 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -2639,7 +2639,7 @@ static int ntfs_non_resident_attr_record_add(struct ntfs_inode *ni, __le32 type, return offset; put_err_out: ntfs_attr_put_search_ctx(ctx); - return -1; + return err; } /* From cf06dcd572845723821b54a608fc2da995c3c8e2 Mon Sep 17 00:00:00 2001 From: Baolin Liu Date: Fri, 21 Aug 2026 13:32:36 +0800 Subject: [PATCH 0126/1198] ntfs: fix kmap_local leak in write_mft_record_nolock() error paths write_mft_record_nolock() maps the MFT record folio with kmap_local_folio(), but the pre_write_mst_fixup() and bio_add_folio() failure paths jump to the error label without unmapping it. kmap_local mappings are stack-ordered per task, so leaking one corrupts the nesting for any outer mapping. Unmap the folio on those error paths too. Fixes: 115380f9a2f9 ("ntfs: update mft operations") Signed-off-by: Baolin Liu Reviewed-by: Hyunchul Lee Signed-off-by: Namjae Jeon --- fs/ntfs/mft.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c index 984a0827f9ac..69b007e574fc 100644 --- a/fs/ntfs/mft.c +++ b/fs/ntfs/mft.c @@ -580,7 +580,7 @@ int write_mft_record_nolock(struct ntfs_inode *ni, struct mft_record *m, int syn err = pre_write_mst_fixup((struct ntfs_record *)fixup_m, vol->mft_record_size); if (err) { ntfs_error(vol->sb, "Failed to apply mst fixups!"); - goto err_out; + goto unmap_err_out; } folio_size = vol->mft_record_size / ni->mft_lcn_count; @@ -645,6 +645,8 @@ int write_mft_record_nolock(struct ntfs_inode *ni, struct mft_record *m, int syn return 0; put_bio_out: bio_put(bio); +unmap_err_out: + kunmap_local(kaddr); err_out: /* * The caller should mark the base inode as bad so no more I/O From be9e89ccb8e52a3e4b67feeb03ebd8133091dc7e Mon Sep 17 00:00:00 2001 From: Baolin Liu Date: Fri, 21 Aug 2026 13:32:37 +0800 Subject: [PATCH 0127/1198] ntfs: only count successfully cleared runs when freeing clusters ntfs_cluster_free_from_rl_nolock() adds a run's length to nr_freed whenever the error bookkeeping condition is false, which includes cases where ntfs_bitmap_clear_run() actually failed - e.g. a second run failing with the same errno as an earlier one, or any failure after a non-ENOMEM error was already recorded. Since a failed ntfs_bitmap_clear_run() rolls back its partial modifications, no bits were cleared for that run, yet its length still inflates vol->free_clusters, corrupting statfs output and the allocator's free space gate. Only count runs whose bitmap clear succeeded. Fixes: 11ccc9107dc4 ("ntfs: update runlist handling and cluster allocator") Signed-off-by: Baolin Liu Reviewed-by: Hyunchul Lee Signed-off-by: Namjae Jeon --- fs/ntfs/lcnalloc.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/ntfs/lcnalloc.c b/fs/ntfs/lcnalloc.c index aa2e017a4384..795f71d26895 100644 --- a/fs/ntfs/lcnalloc.c +++ b/fs/ntfs/lcnalloc.c @@ -53,10 +53,10 @@ int ntfs_cluster_free_from_rl_nolock(struct ntfs_volume *vol, if (rl->lcn < 0) continue; err = ntfs_bitmap_clear_run(lcnbmp_vi, rl->lcn, rl->length); - if (unlikely(err && (!ret || ret == -ENOMEM) && ret != err)) - ret = err; - else + if (likely(!err)) nr_freed += rl->length; + else if (!ret || ret == -ENOMEM) + ret = err; } ntfs_inc_free_clusters(vol, nr_freed); ntfs_debug("Done."); From 5f2a22b36fe34c98f6d5e35ddb759ee53d684145 Mon Sep 17 00:00:00 2001 From: Baolin Liu Date: Fri, 21 Aug 2026 13:32:38 +0800 Subject: [PATCH 0128/1198] ntfs: skip free cluster decrement when rollback fails When the rollback in __ntfs_cluster_free() fails, the recursive call returns a negative errno and the subsequent ntfs_dec_free_clusters(vol, delta) subtracts that negative value, adding bogus clusters to the counter on an already-failing volume. Skip the decrement when the rollback failed. Fixes: 11ccc9107dc4 ("ntfs: update runlist handling and cluster allocator") Signed-off-by: Baolin Liu Reviewed-by: Hyunchul Lee Signed-off-by: Namjae Jeon --- fs/ntfs/lcnalloc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ntfs/lcnalloc.c b/fs/ntfs/lcnalloc.c index 795f71d26895..0d6cd08ee2e7 100644 --- a/fs/ntfs/lcnalloc.c +++ b/fs/ntfs/lcnalloc.c @@ -1045,8 +1045,9 @@ s64 __ntfs_cluster_free(struct ntfs_inode *ni, const s64 start_vcn, s64 count, "Failed to rollback (error %i). Leaving inconsistent metadata! Unmount and run chkdsk.", (int)delta); NVolSetErrors(vol); + } else { + ntfs_dec_free_clusters(vol, delta); } - ntfs_dec_free_clusters(vol, delta); up_write(&vol->lcnbmp_lock); memalloc_nofs_restore(memalloc_flags); ntfs_error(vol->sb, "Aborting (error %i).", err); From 0e4c839905418d55bafe571a92533a1d1ac7b0a8 Mon Sep 17 00:00:00 2001 From: Dennis Tighe Date: Sun, 23 Aug 2026 22:08:40 -0700 Subject: [PATCH 0129/1198] ntfs: do not mark the volume clean in sync_fs when errors were recorded ntfs_put_super() and the remount-read-only path both clear the dirty bit only when NVolErrors(vol) is false. ntfs_sync_fs() clears it unconditionally, so any sync() on a volume that recorded an error marks that volume clean. A volume without this set is then seen as not needing recovery and it does not run one, so whatever went wrong is never repaired. This change skips resetting the dirty bit when there are volume errors. Reproduced on a volume whose $MFTMirr does not match $MFT, which sets the error flag while leaving the mount read-write: after a write and a sync, the on-disk volume flags read 0x0000 with this driver and 0x0001 with the guard in place. Fixes: 6251f0b0de7d ("ntfs: update super block operations") Assisted-by: claude:claude-opus-5 Signed-off-by: Dennis Tighe Reviewed-by: Hyunchul Lee Signed-off-by: Namjae Jeon --- fs/ntfs/super.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 30481e5d5dd4..a4dc64fb89ed 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -1862,7 +1862,8 @@ static int ntfs_sync_fs(struct super_block *sb, int wait) return 0; /* If there are some dirty buffers in the bdev inode */ - if (ntfs_clear_volume_flags(vol, VOLUME_IS_DIRTY)) { + if (!NVolErrors(vol) && + ntfs_clear_volume_flags(vol, VOLUME_IS_DIRTY)) { ntfs_warning(sb, "Failed to clear dirty bit in volume information flags. Run chkdsk."); err = -EIO; } From 8d139e3635c86e2c97c78d55538ce0b00b6d9986 Mon Sep 17 00:00:00 2001 From: Hongling Zeng Date: Mon, 24 Aug 2026 13:41:15 +0800 Subject: [PATCH 0130/1198] ntfs: fix incorrect MFT record pointer passed to ntfs_attr_record_resize ntfs_new_attr_flags() passes the wrong MFT record to ntfs_attr_record_resize(). When the attribute is in an extent record, ctx->mrec points to the extent but the function receives the base record pointer m, causing incorrect size calculations in memmove. Fix by passing ctx->mrec (the actual MFT record containing the attribute) instead of m (the base MFT record) to ntfs_attr_record_resize(). Fixes: fc053f05ca28 ("ntfs: add reparse and ea operations") Cc: stable@vger.kernel.org Signed-off-by: Hongling Zeng Reviewed-by: Hyunchul Lee Signed-off-by: Namjae Jeon --- fs/ntfs/ea.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ntfs/ea.c b/fs/ntfs/ea.c index f6dbdfe6ff15..9f0222c172d9 100644 --- a/fs/ntfs/ea.c +++ b/fs/ntfs/ea.c @@ -764,7 +764,7 @@ static int ntfs_new_attr_flags(struct ntfs_inode *ni, __le32 fattr) memmove((u8 *)a + mp_ofs, (u8 *)a + old_mp_ofs, mp_size); } - err = ntfs_attr_record_resize(m, a, arec_size); + err = ntfs_attr_record_resize(ctx->mrec, a, arec_size); if (unlikely(err)) goto err_out; From 607a9478833db656e7ceac8e9e382fa4acfde545 Mon Sep 17 00:00:00 2001 From: Wentao Guan Date: Tue, 25 Aug 2026 13:46:59 +0800 Subject: [PATCH 0131/1198] ntfs: treat any nonzero dio zero-range return as an error ntfs_dio_zero_range() returns either 0 or a negative errno from blkdev_issue_zeroout(); it never returns a positive value. The zeroing failure check in ntfs_attr_fallocate() therefore never fired, so a failed zeroing operation was silently ignored: the loop kept going, the newly allocated clusters were folded into initialized_size and the write could succeed leaving stale on-disk data. Treat any nonzero return as an error and abort the allocation. Fixes: 495e90fa33482 ("ntfs: update attrib operations") Assisted-by: atomcode:deepseek-v4-flash Signed-off-by: Wentao Guan Signed-off-by: Namjae Jeon --- fs/ntfs/attrib.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index 4dff5c3f779b..c55dc47d2261 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -5704,7 +5704,7 @@ int ntfs_attr_fallocate(struct ntfs_inode *ni, loff_t start, loff_t byte_len, bo lcn << vol->cluster_size_bits, alloc_cnt << vol->cluster_size_bits); - if (err > 0) + if (err) goto out; } From a79899ca38af4ce5518a59a22f0eb1f59f7e6089 Mon Sep 17 00:00:00 2001 From: Hongling Zeng Date: Tue, 25 Aug 2026 17:54:05 +0800 Subject: [PATCH 0132/1198] ntfs: fix undefined behavior in mft/index record size calculation The boot sector validation allows clusters_per_mft_record and clusters_per_index_record to range from 0xE1 (-31) to 0xF7 (-9) when interpreted as signed values. When these are used as negative shift counts in expressions like `1 << -clusters_per_mft_record`, values like 0xE1 cause `1 << 31`, which shifts into the sign bit of a 32-bit signed integer, resulting in undefined behavior. Fix by using unsigned shift (1U << ...) instead of signed shift. This prevents undefined behavior while preserving the full valid range of negative values (-31 to -9) that may appear in NTFS boot sectors. The encoding scheme uses negative values to represent record sizes smaller than cluster_size: -log2(record_size). Common values include -10 (1024 bytes) for mft_record_size and -12 (4096 bytes) for index_record_size. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable@vger.kernel.org Signed-off-by: Hongling Zeng Reviewed-by: Baolin Liu Signed-off-by: Namjae Jeon --- fs/ntfs/super.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index a4dc64fb89ed..2df64712335a 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -695,7 +695,7 @@ static bool parse_ntfs_boot_sector(struct ntfs_volume *vol, * = -log2(mft_record_size) bytes. mft_record_size normaly is * 1024 bytes, which is encoded as 0xF6 (-10 in decimal). */ - vol->mft_record_size = 1 << -clusters_per_mft_record; + vol->mft_record_size = 1U << -clusters_per_mft_record; vol->mft_record_size_mask = vol->mft_record_size - 1; vol->mft_record_size_bits = ffs(vol->mft_record_size) - 1; ntfs_debug("vol->mft_record_size = %i (0x%x)", vol->mft_record_size, @@ -732,7 +732,7 @@ static bool parse_ntfs_boot_sector(struct ntfs_volume *vol, * index_record_size normaly equals 4096 bytes, which is * encoded as 0xF4 (-12 in decimal). */ - vol->index_record_size = 1 << -clusters_per_index_record; + vol->index_record_size = 1U << -clusters_per_index_record; vol->index_record_size_mask = vol->index_record_size - 1; vol->index_record_size_bits = ffs(vol->index_record_size) - 1; ntfs_debug("vol->index_record_size = %i (0x%x)", From c8504fc1245f5322af5fa5c325ab05f9cf792b87 Mon Sep 17 00:00:00 2001 From: Dennis Tighe Date: Tue, 25 Aug 2026 21:44:24 -0700 Subject: [PATCH 0133/1198] ntfs: bound $AttrDef table walk to the loaded table size ntfs_attr_find_in_attrdef() walks the in-memory $AttrDef table, but the loop condition bounds only the start of each entry, not the whole entry: for (ad = vol->attrdef; (u8 *)ad - (u8 *)vol->attrdef < vol->attrdef_size && ad->type; ++ad) struct attr_def is 160 bytes; the guard reads ad->type at offset 128 and the loop body reads further fields. vol->attrdef is kvzalloc(i_size), where i_size is the on-disk $AttrDef data size, checked in load_and_init_attrdef() only as 0 < i_size <= 0x7fffffff. A volume whose $AttrDef data size is smaller than one entry (e.g. 120 bytes) makes the read of ad->type run past the allocation. Creating a file reaches this through ntfs_attr_size_bounds_check() and reads out of bounds: BUG: KASAN: slab-out-of-bounds in ntfs_attr_find_in_attrdef+0x66/0xa0 Read of size 4 at addr ffff888005833280 by task init/1 ntfs_attr_find_in_attrdef ntfs_attr_size_bounds_check ntfs_attr_can_be_non_resident ntfs_attr_add Require the whole entry to lie within attrdef_size in the loop guard, and reject at mount a $AttrDef too small to hold one attr_def entry. Fixes: 1e9ea7e04472 ("Revert "fs: Remove NTFS classic"") Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Dennis Tighe Signed-off-by: Namjae Jeon --- fs/ntfs/attrib.c | 4 ++-- fs/ntfs/super.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index c55dc47d2261..b3e941423a3f 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -1737,8 +1737,8 @@ static struct attr_def *ntfs_attr_find_in_attrdef(const struct ntfs_volume *vol, struct attr_def *ad; WARN_ON(!type); - for (ad = vol->attrdef; (u8 *)ad - (u8 *)vol->attrdef < - vol->attrdef_size && ad->type; ++ad) { + for (ad = vol->attrdef; (u8 *)ad - (u8 *)vol->attrdef <= + vol->attrdef_size - (s32)sizeof(*ad) && ad->type; ++ad) { /* We have not found it yet, carry on searching. */ if (likely(le32_to_cpu(ad->type) < le32_to_cpu(type))) continue; diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 2df64712335a..155dca5db7a9 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -1241,9 +1241,9 @@ static bool load_and_init_attrdef(struct ntfs_volume *vol) goto failed; } NInoSetSparseDisabled(NTFS_I(ino)); - /* The size of FILE_AttrDef must be above 0 and fit inside 31 bits. */ + /* FILE_AttrDef must hold at least one entry and fit inside 31 bits. */ i_size = i_size_read(ino); - if (i_size <= 0 || i_size > 0x7fffffff) + if (i_size < (s64)sizeof(struct attr_def) || i_size > 0x7fffffff) goto iput_failed; vol->attrdef = kvzalloc(i_size, GFP_NOFS); if (!vol->attrdef) From 323751a604e7533fa473874d999371592a614207 Mon Sep 17 00:00:00 2001 From: Dennis Tighe Date: Tue, 25 Aug 2026 22:09:34 -0700 Subject: [PATCH 0134/1198] ntfs: reject invalid sectors_per_cluster in the boot sector is_boot_sector_ntfs() checks the boot sector's sectors_per_cluster field with a range test that rejects 0x81..0xf3 but accepts 0 and other non-power-of-two counts. A zero value reaches parse_ntfs_boot_sector(): sectors_per_cluster_bits = ffs(sectors_per_cluster) - 1; ... vol->cluster_size = vol->sector_size << sectors_per_cluster_bits; ffs(0) is 0, so sectors_per_cluster_bits becomes (unsigned)-1 and the shift is undefined: UBSAN: shift-out-of-bounds in fs/ntfs/super.c:673:39 shift exponent 4294967295 is too large for 32-bit type 'int' This change rejects any non-power-of-two value, since it feeds the aforementioned shift via ffs() - 1, which only yields the correct shift for a power of two. Fixes: 6251f0b0de7d ("ntfs: update super block operations") Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Dennis Tighe Signed-off-by: Namjae Jeon --- fs/ntfs/super.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 155dca5db7a9..60d43339c590 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -557,8 +557,8 @@ static bool is_boot_sector_ntfs(const struct super_block *sb, * Check sectors per cluster value is valid and the cluster size * is not above the maximum (2MB). */ - if (b->bpb.sectors_per_cluster > 0x80 && - b->bpb.sectors_per_cluster < 0xf4) + if (b->bpb.sectors_per_cluster < 0xf4 && + !is_power_of_2(b->bpb.sectors_per_cluster)) goto not_ntfs; /* Check reserved/unused fields are really zero. */ From 53676a5e28231186c9f56d87b7998b640699bc15 Mon Sep 17 00:00:00 2001 From: Frank Sorenson Date: Sun, 23 Aug 2026 18:26:46 -0500 Subject: [PATCH 0135/1198] cifs: add revalidation on FSCTL failure in smb2_duplicate_extents() smb2_duplicate_extents() has no handling for FSCTL_DUPLICATE_EXTENTS_TO_FILE failure: when the FSCTL fails, local inode metadata may be stale from the pre-extension or from concurrent remote writes, but is never refreshed. Force revalidation on FSCTL failure and use i_size_read() for the pre-extension check. Fixes: cfc63fc8126a ("smb3: fix cached file size problems in duplicate extents (reflink)") Cc: stable@vger.kernel.org Signed-off-by: Frank Sorenson Signed-off-by: Paulo Alcantara --- fs/smb/client/smb2ops.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 7d6738ffcb80..bea4876b58cb 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -2218,7 +2218,7 @@ smb2_duplicate_extents(const unsigned int xid, trgtfile->fid.volatile_fid, tcon->tid, tcon->ses->Suid, src_off, dest_off, len); inode = d_inode(trgtfile->dentry); - if (inode->i_size < dest_off + len) { + if (i_size_read(inode) < dest_off + len) { rc = smb2_set_file_size(xid, tcon, trgtfile, dest_off + len, false); if (rc) goto duplicate_extents_out; @@ -2235,7 +2235,10 @@ smb2_duplicate_extents(const unsigned int xid, if (ret_data_len > 0) cifs_dbg(FYI, "Non-zero response length in duplicate extents\n"); - if (rc == 0) { + if (rc) { + CIFS_I(inode)->time = 0; /* force reval */ + cifs_invalidate_cache(inode, 0); + } else { qrc = SMB2_query_info(xid, tcon, trgtfile->fid.persistent_fid, trgtfile->fid.volatile_fid, &file_inf); spin_lock(&inode->i_lock); From 2d2a3adc91950f9a18829dadc7317fb5180a15c5 Mon Sep 17 00:00:00 2001 From: GuoHan Zhao Date: Fri, 17 Jul 2026 14:11:45 +0800 Subject: [PATCH 0136/1198] accel/ethosu: fix job completion fence cleanup ethosu_ioctl_submit_job() allocates done_fence before validating buffer handles. Errors after allocation call ethosu_job_err_cleanup(), which frees the job but leaks the uninitialized fence. A scheduler dependency error also lets ethosu_job_run() return before dma_fence_init(). Normal cleanup then passes a zeroed refcount to dma_fence_put(). Release done_fence in the common cleanup path and use dma_fence_was_initialized() to distinguish initialized fences from raw allocations. Fixes: 5a5e9c0228e6 ("accel: Add Arm Ethos-U NPU driver") Cc: stable@vger.kernel.org Reported-by: Sashiko Link: https://sashiko.dev/#/patchset/20260716065219.931088-1-zhaoguohan@kylinos.cn?part=1 Signed-off-by: GuoHan Zhao Link: https://patch.msgid.link/20260717061145.1478139-6-zhaoguohan@kylinos.cn [robh: also fix goto] Signed-off-by: Rob Herring (Arm) --- drivers/accel/ethosu/ethosu_job.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/accel/ethosu/ethosu_job.c b/drivers/accel/ethosu/ethosu_job.c index 1e2465279aae..1e4b65f62933 100644 --- a/drivers/accel/ethosu/ethosu_job.c +++ b/drivers/accel/ethosu/ethosu_job.c @@ -152,6 +152,13 @@ static void ethosu_job_err_cleanup(struct ethosu_job *job) drm_gem_object_put(job->cmd_bo); + if (job->done_fence) { + if (dma_fence_was_initialized(job->done_fence)) + dma_fence_put(job->done_fence); + else + dma_fence_free(job->done_fence); + } + kfree(job); } @@ -162,7 +169,6 @@ static void ethosu_job_cleanup(struct kref *ref) pm_runtime_put_autosuspend(job->dev->base.dev); - dma_fence_put(job->done_fence); dma_fence_put(job->inference_done_fence); ethosu_job_err_cleanup(job); @@ -393,7 +399,7 @@ static int ethosu_ioctl_submit_job(struct drm_device *dev, struct drm_file *file ejob->done_fence = kzalloc_obj(*ejob->done_fence); if (!ejob->done_fence) { ret = -ENOMEM; - goto out_cleanup_job; + goto out_put_job; } ret = drm_sched_job_init(&ejob->base, From d3ef6c097ba078e1f8c7239d76a0ce8b61e75095 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Wed, 26 Aug 2026 11:18:44 -0700 Subject: [PATCH 0137/1198] bpf: check_cond_jmp_op(): properly infer if register is null Nicholas Carlini reported a bug when verifier can incorrectly infer that a pointer is non-null. The bug occurs when two pointers are compared and one of them has a type w/o PTR_MAYBE_NULL flag, but which allows a value to be NULL at runtime. Here is an example: // `a` is PTR_TO_MEM | MEM_RDONLY | PTR_UNTRUSTED // `a` is 0 at runtime. // `b` is PTR_TO_MAP_VALUE | PTR_MAYBE_NULL void *a = bpf_rdonly_cast(0, 0); int *b = bpf_map_lookup_elem(...); if (a == b) *b = 42; // verifier does not catch null pointer dereference This happens because of a special case in check_cond_jmp_op(), which attempts to strip PTR_MAYBE_NULL flags from pointer types, when processing comparisons like `rA == rB`, if either rA or rB can't be null. The non-null property is derived based on the absence of PTR_MAYBE_NULL flag on rA's or rB's type. But that is not sufficient for types like PTR_TO_MEM, as in the example. This patch replaces type_may_be_null() call with reg_not_null(), which contains an allowlist of types for which absence of PTR_MAYBE_NULL actually means that the value can't be NULL at runtime. At the moment, the list in the reg_not_null() omits two types for which PTR_MAYBE_NULL is applicable: PTR_TO_XDP_SOCK and PTR_TO_BUF. In order to remain backward compatible, and assuming that only comparison between pointers of the same type makes sense, this commit extends reg_not_null(). W/o such an extension e.g. verifier_jeq_infer_not_null/null_ptr_to_map_value fails. reg_not_null() can be extended further, but I deem that out of scope for the fix at hand. Explicit base_type(...) != PTR_TO_BTF_ID checks in the check_cond_jmp_op() can be removed with migration to reg_not_null(), but that is a behavioural change, as the special case would start matching for PTR_TO_BTF_ID that is also is_trusted_reg(). I omit the behavioural change from this commit. Fixes: befae75856ab ("bpf: propagate nullness information for reg to reg comparisons") Suggested-by: Nicholas Carlini Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260826-bug-029-bad-non-null-inference-v2-1-136789ace9e9@localhost Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 5e37ca75e5c4..e64035683795 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -355,6 +355,8 @@ static bool reg_not_null(struct bpf_verifier_env *env, const struct bpf_reg_stat type = base_type(type); return type == PTR_TO_SOCKET || type == PTR_TO_TCP_SOCK || + type == PTR_TO_XDP_SOCK || + type == PTR_TO_BUF || type == PTR_TO_MAP_VALUE || type == PTR_TO_MAP_KEY || type == PTR_TO_SOCK_COMMON || @@ -16968,7 +16970,6 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, */ if (!is_jmp32 && BPF_SRC(insn->code) == BPF_X && __is_pointer_value(false, src_reg) && __is_pointer_value(false, dst_reg) && - type_may_be_null(src_reg->type) != type_may_be_null(dst_reg->type) && base_type(src_reg->type) != PTR_TO_BTF_ID && base_type(dst_reg->type) != PTR_TO_BTF_ID) { eq_branch_regs = NULL; @@ -16984,9 +16985,11 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, break; } if (eq_branch_regs) { - if (type_may_be_null(src_reg->type)) + /* src == dst && dst != NULL => src != NULL */ + if (reg_not_null(env, dst_reg) && type_may_be_null(src_reg->type)) mark_ptr_not_null_reg(&eq_branch_regs[insn->src_reg]); - else + /* src == dst && src != NULL => dst != NULL */ + if (reg_not_null(env, src_reg) && type_may_be_null(dst_reg->type)) mark_ptr_not_null_reg(&eq_branch_regs[insn->dst_reg]); } } From ce6dcd0aed185432d02cafc82b738318af257ccd Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Wed, 26 Aug 2026 11:18:45 -0700 Subject: [PATCH 0138/1198] selftests/bpf: a demo for check_cond_jmp_op() non-null inference bug A comparison between PTR_TO_MEM | MEM_RDONLY | PTR_UNTRUSTED and PTR_TO_MAP_VALUE_OR_NULL should not infer that map pointer is not null. A bug in check_cond_jmp_op() made such inference possible. Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260826-bug-029-bad-non-null-inference-v2-2-136789ace9e9@localhost Signed-off-by: Alexei Starovoitov --- .../bpf/progs/verifier_jeq_infer_not_null.c | 52 +++++++++++++++++++ 1 file changed, 52 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/verifier_jeq_infer_not_null.c b/tools/testing/selftests/bpf/progs/verifier_jeq_infer_not_null.c index 3d1e8de4390c..b412a542ef76 100644 --- a/tools/testing/selftests/bpf/progs/verifier_jeq_infer_not_null.c +++ b/tools/testing/selftests/bpf/progs/verifier_jeq_infer_not_null.c @@ -3,7 +3,9 @@ #include #include +#include #include "bpf_misc.h" +#include "bpf_kfuncs.h" struct { __uint(type, BPF_MAP_TYPE_XSKMAP); @@ -12,6 +14,13 @@ struct { __type(value, int); } map_xskmap SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} map_hash SEC(".maps"); + /* This is equivalent to the following program: * * r6 = skb->sk; @@ -264,4 +273,47 @@ __naked void jne_reg_reg_null_check(void) : __clobber_all); } +/* + * A comparison between PTR_TO_MEM | MEM_RDONLY | PTR_UNTRUSTED and + * PTR_TO_MAP_VALUE_OR_NULL should not infer that map pointer is not null. + * A bug in check_cond_jmp_op() made such inference possible. + */ +SEC("raw_tp") +__failure +__msg("error: invalid dereference of R0 (a nullable map value pointer)") +__msg(">>> 11 | (61) r0 = *(u32 *)(r0 +0)") +__naked void untrusted_mem_does_not_infer_map_value_non_null(void) +{ + asm volatile (" \ + /* r6 = bpf_rdonly_cast(0, 0); */ \ + r1 = 0; \ + r2 = 0; \ + call %[bpf_rdonly_cast]; \ + r6 = r0; \ + /* r0 = bpf_map_lookup_elem(map_hash, &key); */ \ + *(u64 *)(r10 - 8) = 0; \ + r1 = %[map_hash] ll; \ + r2 = r10; \ + r2 += -8; \ + call %[bpf_map_lookup_elem]; \ + /* \ + * buggy verifier assumed that r6 can't be null \ + * and marked r0 non-null as well. \ + */ \ + if r6 != r0 goto 1f; \ + r0 = *(u32 *)(r0 + 0); \ +1: r0 = 0; \ + exit; \ +" : + : __imm(bpf_rdonly_cast), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash) + : __clobber_all); +} + +void kfunc_root(void) +{ + bpf_rdonly_cast(0, 0); +} + char _license[] SEC("license") = "GPL"; From 6faa235a649e78a82e3230b849607f446ba65ed5 Mon Sep 17 00:00:00 2001 From: Dennis Tighe Date: Sun, 23 Aug 2026 00:13:25 -0700 Subject: [PATCH 0139/1198] ntfs: compute bi_sector in 512-byte units bi_sector counts in 512 byte sectors and not in multiples of the volume's sector size. Under "normal" circumstances (with 512 byte sectors in NTFS) the current code works as is; however, when we have a 4k sector size on the volume the current usage of NTFS_B_TO_SECTOR() and ntfs_bytes_to_sector() end up converting to the number of 4k sectors after mount. Reads work today on 4k volumes as bdev-io.c as performing the shift correctly inline. With writes, we end up with significant silent disk corruption on these volumes. This fixes changes to use the new ntfs_bytes_to_bio_sector() function everywhere we're performing this calculation (including the existing read path). For the change in inode.c it removes a dead code block rather than updating. Fixes: 40796051991d ("ntfs: update in-memory, on-disk structures and headers") Assisted-by: Claude:claude-opus-5 Signed-off-by: Dennis Tighe Reviewed-by: Hyunchul Lee Signed-off-by: Namjae Jeon --- fs/ntfs/bdev-io.c | 2 +- fs/ntfs/compress.c | 2 +- fs/ntfs/inode.c | 10 ++-------- fs/ntfs/mft.c | 12 ++++++------ fs/ntfs/ntfs.h | 10 ++++------ 5 files changed, 14 insertions(+), 22 deletions(-) diff --git a/fs/ntfs/bdev-io.c b/fs/ntfs/bdev-io.c index 86db4d9298ed..4f27eed3b072 100644 --- a/fs/ntfs/bdev-io.c +++ b/fs/ntfs/bdev-io.c @@ -34,7 +34,7 @@ int ntfs_bdev_read(struct block_device *bdev, char *data, loff_t start, size_t s int error; struct bio *bio; blk_opf_t op; - sector_t sector = start >> SECTOR_SHIFT; + sector_t sector = ntfs_bytes_to_bio_sector(start); if (start & (SECTOR_SIZE - 1)) return -EINVAL; diff --git a/fs/ntfs/compress.c b/fs/ntfs/compress.c index 2225630b19d7..197d8607fc63 100644 --- a/fs/ntfs/compress.c +++ b/fs/ntfs/compress.c @@ -1414,7 +1414,7 @@ static int ntfs_write_cb(struct ntfs_inode *ni, loff_t pos, struct page **pages, bio_pos = ntfs_cluster_to_bytes(vol, bio_lcn); bio = bio_alloc(vol->sb->s_bdev, DIV_ROUND_UP(bio_size, PAGE_SIZE), REQ_OP_WRITE, GFP_NOIO); - bio->bi_iter.bi_sector = ntfs_bytes_to_sector(vol, bio_pos); + bio->bi_iter.bi_sector = ntfs_bytes_to_bio_sector(bio_pos); for (i = 0; bio_size; i++) { unsigned int len = min_t(unsigned int, bio_size, PAGE_SIZE); diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index 32edb4045178..5aedc045f65a 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -1852,7 +1852,7 @@ int ntfs_read_inode_mount(struct inode *vi) struct mft_record *m = NULL; struct attr_record *a; struct ntfs_attr_search_ctx *ctx; - unsigned int i, nr_blocks; + unsigned int i; int err; size_t new_rl_count; @@ -1896,11 +1896,6 @@ int ntfs_read_inode_mount(struct inode *vi) goto err_out; } - /* Determine the first block of the $MFT/$DATA attribute. */ - nr_blocks = ntfs_bytes_to_sector(vol, vol->mft_record_size); - if (!nr_blocks) - nr_blocks = 1; - /* Load $MFT/$DATA's first mft record. */ err = ntfs_bdev_read(sb->s_bdev, (char *)m, ntfs_cluster_to_bytes(vol, vol->mft_lcn), i); @@ -3780,8 +3775,7 @@ static s64 __ntfs_inode_non_resident_attr_pwrite(struct inode *vi, bio = bio_alloc(vol->sb->s_bdev, 1, REQ_OP_WRITE, GFP_NOIO); bio->bi_iter.bi_sector = - ntfs_bytes_to_sector(vol, - ntfs_cluster_to_bytes(vol, lcn) + + ntfs_bytes_to_bio_sector(ntfs_cluster_to_bytes(vol, lcn) + lcn_folio_off); length = min_t(unsigned long, diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c index 69b007e574fc..7e58c99f1728 100644 --- a/fs/ntfs/mft.c +++ b/fs/ntfs/mft.c @@ -499,8 +499,8 @@ int ntfs_sync_mft_mirror(struct ntfs_volume *vol, const u64 mft_no, bio = bio_alloc(vol->sb->s_bdev, 1, REQ_OP_WRITE, GFP_NOIO); bio->bi_iter.bi_sector = - NTFS_B_TO_SECTOR(vol, NTFS_CLU_TO_B(vol, vol->mftmirr_lcn) + - lcn_folio_off + folio_ofs); + ntfs_bytes_to_bio_sector(NTFS_CLU_TO_B(vol, vol->mftmirr_lcn) + + lcn_folio_off + folio_ofs); if (bio_add_folio(bio, folio, vol->mft_record_size, folio_ofs)) err = submit_bio_wait(bio); @@ -592,8 +592,8 @@ int write_mft_record_nolock(struct ntfs_inode *ni, struct mft_record *m, int syn bio = bio_alloc(vol->sb->s_bdev, 1, REQ_OP_WRITE, GFP_NOIO); bio->bi_iter.bi_sector = - NTFS_B_TO_SECTOR(vol, NTFS_CLU_TO_B(vol, ni->mft_lcn[i]) + - clu_off); + ntfs_bytes_to_bio_sector(NTFS_CLU_TO_B(vol, ni->mft_lcn[i]) + + clu_off); if (!bio_add_folio(bio, folio, folio_size, ni->folio_ofs + offset)) { @@ -2742,8 +2742,8 @@ static int ntfs_write_mft_block(struct folio *folio, struct writeback_control *w bio = bio_alloc(vol->sb->s_bdev, 1, REQ_OP_WRITE, GFP_NOIO); bio->bi_iter.bi_sector = - ntfs_bytes_to_sector(vol, - ntfs_cluster_to_bytes(vol, lcn) + off); + ntfs_bytes_to_bio_sector( + ntfs_cluster_to_bytes(vol, lcn) + off); } if (vol->cluster_size == NTFS_BLOCK_SIZE && diff --git a/fs/ntfs/ntfs.h b/fs/ntfs/ntfs.h index df5a75d506f6..45f77848a9cf 100644 --- a/fs/ntfs/ntfs.h +++ b/fs/ntfs/ntfs.h @@ -19,6 +19,7 @@ #include #include #include +#include #include #include "volume.h" @@ -71,8 +72,6 @@ #define NTFS_CLU_TO_POFS(vol, clu) (((u64)(clu) << (vol)->cluster_size_bits) & \ ~PAGE_MASK) -#define NTFS_B_TO_SECTOR(vol, b) ((b) >> ((vol)->sb)->s_blocksize_bits) - enum { NTFS_BLOCK_SIZE = 512, NTFS_BLOCK_SIZE_BITS = 9, @@ -154,11 +153,10 @@ static inline u64 ntfs_cluster_to_poff(const struct ntfs_volume *vol, return (clu << vol->cluster_size_bits) & ~PAGE_MASK; } -/* Convert byte offset to sector (block) number. */ -static inline sector_t ntfs_bytes_to_sector(const struct ntfs_volume *vol, - u64 bytes) +/* Convert a byte offset on the volume to a bio sector number. */ +static inline sector_t ntfs_bytes_to_bio_sector(u64 bytes) { - return bytes >> vol->sb->s_blocksize_bits; + return bytes >> SECTOR_SHIFT; } /* Global variables. */ From acb1095fd2db884b417cb70808c886e4b615ff05 Mon Sep 17 00:00:00 2001 From: Hongling Zeng Date: Mon, 24 Aug 2026 15:59:35 +0800 Subject: [PATCH 0140/1198] ntfs: fix memmove overlap in ntfs_new_attr_flags When the record shrinks while the payload offsets increase (e.g., enabling compression reduces padding, making arec_size < old_arec_size, but the header grows by 8 bytes), moving the name first can overwrite the old mapping_pairs before they are copied. Move mapping_pairs first in this case. Since mp_ofs is derived from name_ofs, they always change in the same direction. Checking name_ofs alone is sufficient. Fixes: fc053f05ca28 ("ntfs: add reparse and ea operations") Cc: stable@vger.kernel.org Signed-off-by: Hongling Zeng Reviewed-by: Hyunchul Lee Signed-off-by: Namjae Jeon --- fs/ntfs/ea.c | 33 +++++++++++++++++++++++++++------ 1 file changed, 27 insertions(+), 6 deletions(-) diff --git a/fs/ntfs/ea.c b/fs/ntfs/ea.c index 9f0222c172d9..0bc29bf1f050 100644 --- a/fs/ntfs/ea.c +++ b/fs/ntfs/ea.c @@ -753,15 +753,36 @@ static int ntfs_new_attr_flags(struct ntfs_inode *ni, __le32 fattr) old_arec_size = le32_to_cpu(a->length); /* - * Move payloads before shrinking the record. Otherwise resizing moves + * Move payloads before shrinking the record. Otherwise resizing moves * the following attribute over the old payload before it can be copied. + * + * When offsets increase, move mapping_pairs first to avoid name + * overwriting the start of mapping_pairs. */ if (arec_size < old_arec_size) { - if (a->name_length && name_ofs != old_name_ofs) - memmove((u8 *)a + name_ofs, (u8 *)a + old_name_ofs, - a->name_length * sizeof(__le16)); - if (mp_ofs != old_mp_ofs) - memmove((u8 *)a + mp_ofs, (u8 *)a + old_mp_ofs, mp_size); + if (name_ofs > old_name_ofs) { + /* Payload offsets increased: move mapping pairs first. */ + if (mp_ofs != old_mp_ofs) + memmove((u8 *)a + mp_ofs, + (u8 *)a + old_mp_ofs, + mp_size); + if (a->name_length && name_ofs != old_name_ofs) + memmove((u8 *)a + name_ofs, + (u8 *)a + old_name_ofs, + a->name_length * + sizeof(__le16)); + } else { + /* Payload offsets decreased or unchanged: move name first. */ + if (a->name_length && name_ofs != old_name_ofs) + memmove((u8 *)a + name_ofs, + (u8 *)a + old_name_ofs, + a->name_length * + sizeof(__le16)); + if (mp_ofs != old_mp_ofs) + memmove((u8 *)a + mp_ofs, + (u8 *)a + old_mp_ofs, + mp_size); + } } err = ntfs_attr_record_resize(ctx->mrec, a, arec_size); From 67aded1da114dc44808315f249bd9e7e440f799d Mon Sep 17 00:00:00 2001 From: Hongling Zeng Date: Thu, 27 Aug 2026 13:58:44 +0800 Subject: [PATCH 0141/1198] ntfs: fix race between fallocate and mmap reads The fallocate implementation only takes invalidate_lock for punch hole, collapse range, and insert range operations. For standard allocation modes (mode == 0, FALLOC_FL_KEEP_SIZE), the lock is not held. During ntfs_attr_fallocate(), new clusters are mapped to the runlist via ntfs_attr_map_cluster() before being zeroed by ntfs_dio_zero_range(). This creates a window where concurrent mmap page faults can read uninitialized disk data. Since mmap uses filemap_fault() which takes invalidate_lock in shared mode, it can fault in pages during this window and expose old disk contents to userspace. This is an information leak and data integrity issue. Fix by taking invalidate_lock for all fallocate operations, not just for punch/collapse/insert modes. This prevents concurrent page faults from accessing unzeroed clusters during the allocation window. Fixes: 495e90fa3348 ("ntfs: update attrib operations") Cc: stable@vger.kernel.org Reviewed-by: Baolin Liu Reviewed-by: Hyunchul Lee Signed-off-by: Hongling Zeng Signed-off-by: Namjae Jeon --- fs/ntfs/file.c | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 88747217ba61..1969e4f444f7 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -1116,7 +1116,6 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t offset, loff_t le struct ntfs_volume *vol = ni->vol; int err = 0; loff_t old_size; - bool map_locked = false; if (mode & ~(NTFS_FALLOC_FL_SUPPORTED)) return -EOPNOTSUPP; @@ -1148,16 +1147,13 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t offset, loff_t le inode_lock(vi); if (NInoCompressed(ni) || NInoEncrypted(ni) || NInoWofCompressed(ni)) { - err = -EOPNOTSUPP; - goto out; + inode_unlock(vi); + return -EOPNOTSUPP; } inode_dio_wait(vi); - if (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE | - FALLOC_FL_INSERT_RANGE)) { - filemap_invalidate_lock(vi->i_mapping); - map_locked = true; - } + /* Take invalidate_lock for all fallocate operations to prevent races */ + filemap_invalidate_lock(vi->i_mapping); switch (mode & FALLOC_FL_MODE_MASK) { case FALLOC_FL_ALLOCATE_RANGE: @@ -1182,8 +1178,7 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t offset, loff_t le err = file_modified(file); out: - if (map_locked) - filemap_invalidate_unlock(vi->i_mapping); + filemap_invalidate_unlock(vi->i_mapping); if (!err) { if (mode == 0 && NInoNonResident(ni) && offset > old_size) { From ac727d86fb84bdc9626ba9c756c26767459f3083 Mon Sep 17 00:00:00 2001 From: Baolin Liu Date: Thu, 27 Aug 2026 14:43:17 +0800 Subject: [PATCH 0142/1198] ntfs: leave HasEA flag untouched on setxattr failure In ntfs_set_ea(), the exit path unconditionally updates the HasEA flag based on ea_info_qsize. When an error occurs before ea_info_qsize is updated, NInoClearHasEA() hides existing on-disk EAs until the inode is evicted. Only update the flag on success. Fixes: fc053f05ca28 ("ntfs: add reparse and ea operations") Signed-off-by: Baolin Liu Signed-off-by: Namjae Jeon --- fs/ntfs/ea.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/fs/ntfs/ea.c b/fs/ntfs/ea.c index 0bc29bf1f050..3f4ba7667522 100644 --- a/fs/ntfs/ea.c +++ b/fs/ntfs/ea.c @@ -404,10 +404,12 @@ static int ntfs_set_ea(struct inode *inode, const char *name, size_t name_len, *packed_ea_size = p_ea_info->ea_length; mark_mft_record_dirty(ni); out: - if (ea_info_qsize > 0) - NInoSetHasEA(ni); - else - NInoClearHasEA(ni); + if (!err) { + if (ea_info_qsize > 0) + NInoSetHasEA(ni); + else + NInoClearHasEA(ni); + } kvfree(ea_buf); kvfree(old_ea_buf); From 20839d02c0cf7437bc508d4c5430538d9dc4f428 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Wed, 26 Aug 2026 12:54:21 +0200 Subject: [PATCH 0143/1198] drm/tegra: Add blend mode properties The default programming in the driver matches the "coverage" blend mode, so add the corresponding pixel blend mode property to let userspace know about it. Tested-by: Jon Hunter Acked-by: Jon Hunter Signed-off-by: Thierry Reding Link: https://patch.msgid.link/20260826105421.1825331-1-thierry.reding@kernel.org --- drivers/gpu/drm/tegra/dc.c | 6 ++++++ drivers/gpu/drm/tegra/hub.c | 2 ++ 2 files changed, 8 insertions(+) diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c index 0b3fcc7011b3..fefc3761a4bc 100644 --- a/drivers/gpu/drm/tegra/dc.c +++ b/drivers/gpu/drm/tegra/dc.c @@ -904,6 +904,7 @@ static struct drm_plane *tegra_primary_plane_create(struct drm_device *drm, struct tegra_dc *dc) { unsigned long possible_crtcs = tegra_plane_get_possible_crtcs(drm); + unsigned int blend_caps = BIT(DRM_MODE_BLEND_COVERAGE); enum drm_plane_type type = DRM_PLANE_TYPE_PRIMARY; struct tegra_plane *plane; unsigned int num_formats; @@ -939,6 +940,7 @@ static struct drm_plane *tegra_primary_plane_create(struct drm_device *drm, } drm_plane_helper_add(&plane->base, &tegra_plane_helper_funcs); + drm_plane_create_blend_mode_property(&plane->base, blend_caps); drm_plane_create_zpos_property(&plane->base, plane->index, 0, 255); err = drm_plane_create_rotation_property(&plane->base, @@ -1209,6 +1211,7 @@ static struct drm_plane *tegra_dc_cursor_plane_create(struct drm_device *drm, struct tegra_dc *dc) { unsigned long possible_crtcs = tegra_plane_get_possible_crtcs(drm); + unsigned int blend_caps = BIT(DRM_MODE_BLEND_COVERAGE); struct tegra_plane *plane; unsigned int num_formats; const u32 *formats; @@ -1252,6 +1255,7 @@ static struct drm_plane *tegra_dc_cursor_plane_create(struct drm_device *drm, } drm_plane_helper_add(&plane->base, &tegra_cursor_plane_helper_funcs); + drm_plane_create_blend_mode_property(&plane->base, blend_caps); drm_plane_create_zpos_immutable_property(&plane->base, 255); return &plane->base; @@ -1356,6 +1360,7 @@ static struct drm_plane *tegra_dc_overlay_plane_create(struct drm_device *drm, bool cursor) { unsigned long possible_crtcs = tegra_plane_get_possible_crtcs(drm); + unsigned int blend_caps = BIT(DRM_MODE_BLEND_COVERAGE); struct tegra_plane *plane; unsigned int num_formats; enum drm_plane_type type; @@ -1394,6 +1399,7 @@ static struct drm_plane *tegra_dc_overlay_plane_create(struct drm_device *drm, } drm_plane_helper_add(&plane->base, &tegra_plane_helper_funcs); + drm_plane_create_blend_mode_property(&plane->base, blend_caps); drm_plane_create_zpos_property(&plane->base, plane->index, 0, 255); err = drm_plane_create_rotation_property(&plane->base, diff --git a/drivers/gpu/drm/tegra/hub.c b/drivers/gpu/drm/tegra/hub.c index bd442bfd4540..448f49f3a7d7 100644 --- a/drivers/gpu/drm/tegra/hub.c +++ b/drivers/gpu/drm/tegra/hub.c @@ -759,6 +759,7 @@ struct drm_plane *tegra_shared_plane_create(struct drm_device *drm, unsigned int index, enum drm_plane_type type) { + unsigned int blend_caps = BIT(DRM_MODE_BLEND_COVERAGE); struct tegra_drm *tegra = drm->dev_private; struct tegra_display_hub *hub = tegra->hub; struct tegra_shared_plane *plane; @@ -797,6 +798,7 @@ struct drm_plane *tegra_shared_plane_create(struct drm_device *drm, } drm_plane_helper_add(p, &tegra_shared_plane_helper_funcs); + drm_plane_create_blend_mode_property(p, blend_caps); drm_plane_create_zpos_property(p, 0, 0, 255); return p; From 2f3536bff8823d3c5fdbbe15e17bfca696cc2b2e Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Thu, 27 Aug 2026 15:48:23 -0700 Subject: [PATCH 0144/1198] bpf: don't downgrade half-dead scalar zero spills to STACK_ZERO states.c:__clean_func_state() can downgrade scalar zero spill to STACK_ZERO in the following case: *(u64 *)(r10 - 8) = 0; ... checkpoint ... r1 = *(u32 *)(r10 - 4); ... no reads from r10-8 ... Here 4 bytes at r10-8 are dead and verifier changes scalar spill to a combination: 0000pppp (p stands for poison). Such a change breaks precision propagation chains. All places that produce STACK_ZERO should call bpf_mark_chain_precision() for the zero source. This patch fixes the bug in a simplest way possible: avoids converting stack spills of zero to STACK_ZERO. Two smarter approaches are possible: - do bpf_mark_chain_precision() from __clean_func_state() - check slot liveness information in check_stack_write_fixed_off() I investigated both and the changes required are a bit tricky, hence go with a simple fix for the time being. Fixes: be23266b4a08 ("bpf: 4-byte precise clean_verifier_state") Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260827-bug-011-cleanfunc-stack-zero-simple-v1-v1-1-c0e996589a52@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/states.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/kernel/bpf/states.c b/kernel/bpf/states.c index 4e6aafad33bd..66fb11b6c6a7 100644 --- a/kernel/bpf/states.c +++ b/kernel/bpf/states.c @@ -445,22 +445,19 @@ static void __clean_func_state(struct bpf_verifier_env *env, struct bpf_reg_state *spill = &st->stack[i].spilled_ptr; if (lo_live && stype == STACK_SPILL) { - u8 val = STACK_MISC; - if (spill->type != SCALAR_VALUE) continue; - /* - * 8 byte spill of scalar 0 where half slot is dead - * should become STACK_ZERO in lo 4 bytes. + * Can't replace with STACK_ZERO, because + * that requires bpf_mark_chain_precision(). */ if (bpf_register_is_null(spill)) - val = STACK_ZERO; + continue; for (j = 0; j < 4; j++) { u8 *t = &st->stack[i].slot_type[j]; if (*t == STACK_SPILL) - *t = val; + *t = STACK_MISC; } } bpf_mark_reg_not_init(env, spill); From c6ff14f1cd9e9b7d5631882ff509fbc29e90cfe0 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Thu, 27 Aug 2026 15:48:24 -0700 Subject: [PATCH 0145/1198] selftests/bpf: half-dead scalar zero stack spill test A test case demonstrating unsafe pruning when spill of a scalar zero spilled on a first pass in replaced by STACK_ZERO in the __clean_func_state(). Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260827-bug-011-cleanfunc-stack-zero-simple-v1-v1-2-c0e996589a52@gmail.com Signed-off-by: Alexei Starovoitov --- .../selftests/bpf/progs/verifier_spill_fill.c | 40 +++++++++++++++++++ 1 file changed, 40 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c index 8b166c42c4e0..39a1766dae3f 100644 --- a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c +++ b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c @@ -1403,6 +1403,46 @@ __naked void partial_fill_from_cleaned_pointer_spill(void) ::: __clobber_all); } +SEC("raw_tp") +__failure +__msg("access may be outside object bounds") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void imprecise_scalar_spill_half_dead(void) +{ + asm volatile ( + /* + * Fork two paths: the one explored first spills an imprecise zero, + * the one explored second, an imprecise non-zero scalar. + */ + "call %[bpf_get_prandom_u32];" + "if r0 > 42 goto 1f;" + "r6 = 0;" + "goto 2f;" +"1:" + /* causes out of bounds access on a second path. */ + "r6 = 100500;" +"2:" + /* Force a checkpoint before the spill. */ + "goto +0;" + "*(u64 *)(r10 - 8) = r6;" + /* + * Force stack cleanup, only the low half of the spill is alive, + * so the dead high half is degraded to raw stack bytes. + * Buggy verifier converted it to STACK_ZERO w/o proper precision propagation. + */ + "goto +0;" + "r7 = *(u32 *)(r10 - 4);" + /* Use r7 as an offset into a one-byte buffer. */ + "r1 = %[single_byte_buf] ll;" + "r1 += r7;" + "r0 = *(u8 *)(r1 + 0);" + "exit;" +: +: __imm(bpf_get_prandom_u32), + __imm_addr(single_byte_buf) +: __clobber_all); +} + /* check valid spill/fill, ptr to tp buffer */ SEC("raw_tracepoint.w") __success From 5046d2880fec7d49ebed2fd2866747ee1d06ad71 Mon Sep 17 00:00:00 2001 From: Zihan Xi Date: Thu, 27 Aug 2026 18:25:14 +0000 Subject: [PATCH 0146/1198] ipv4: avoid divide by zero in fib_rebalance fib_rebalance() computes the total eligible nexthop weight in one pass and programs upper bounds in a second pass. A concurrent change to ignore_routes_with_linkdown can make the first pass return zero while the second pass sees an eligible nexthop, resulting in division by zero. If the first pass reports a zero total, set each nexthop upper bound to -1 and skip the division. This matches the IPv6 fix in commit d2c26c2911dd ("ipv6: avoid divide by zero in rt6_multipath_rebalance") and preserves the lock-free rebalance path. Fixes: 0e884c78ee19 ("ipv4: L3 hash-based multipath") Cc: stable@vger.kernel.org Reported-by: Vega Signed-off-by: Zihan Xi Reviewed-by: Eric Dumazet Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/20260827182514.4667-2-zihanx@nebusec.ai Signed-off-by: Jakub Kicinski --- net/ipv4/fib_semantics.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 0483519b7fb0..7a362f2e2c2b 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -874,7 +874,7 @@ static void fib_rebalance(struct fib_info *fi) change_nexthops(fi) { int upper_bound; - if (nexthop_nh->fib_nh_flags & RTNH_F_DEAD) { + if (!total || nexthop_nh->fib_nh_flags & RTNH_F_DEAD) { upper_bound = -1; } else if (ip_ignore_linkdown(nexthop_nh->fib_nh_dev) && nexthop_nh->fib_nh_flags & RTNH_F_LINKDOWN) { From dddf197f29ba5e47a476dde82bf542ca2e0d5e5e Mon Sep 17 00:00:00 2001 From: Chengfeng Ye Date: Wed, 26 Aug 2026 03:01:41 +0800 Subject: [PATCH 0147/1198] tipc: protect node reset trace dump with node lock The tipc_node_reset_links trace event asks tipc_node_dump() to walk the node's link entries. Unlike the other node events that request link data, this event runs without the node lock. This permits bearer teardown to free a link while the trace callback is dumping it: CPU 0 CPU 1 trace_tipc_node_reset_links() tipc_node_dump() l = n->links[0].link tipc_node_write_lock() kfree(l) n->links[0].link = NULL tipc_node_write_unlock() tipc_link_dump(l) tipc_link_dump() then dereferences the stale pointer. KASAN reported: BUG: KASAN: slab-use-after-free in tipc_link_dump Read of size 4 by task poc/115 Call Trace: tipc_link_dump+0x10cb/0x16b0 tipc_node_dump+0x4bb/0x740 trace_event_raw_event_tipc_node_class+0x258/0x360 tipc_node_reset_links+0x14d/0x1a0 tipc_rcv+0x13f5/0x3030 tipc_udp_recv+0x4e3/0x670 Allocated by task 0: tipc_link_create+0x1e1/0x1020 tipc_node_check_dest+0x7d2/0x11a0 tipc_disc_rcv+0xdbf/0x1430 Freed by task 89: kfree+0x131/0x3c0 tipc_node_link_down+0x267/0x4b0 tipc_node_delete_links+0xec/0x160 bearer_disable+0x107/0x260 Take the node write lock around the trace event. This serializes the dump against tipc_node_link_down(delete=true), which frees the link under the same write lock. Fixes: eb18a510b5cd ("tipc: add trace_events for tipc node") Cc: stable@vger.kernel.org Signed-off-by: Chengfeng Ye Reviewed-by: Tung Nguyen Link: https://patch.msgid.link/20260825190141.242219-1-nicoyip.dev@gmail.com Signed-off-by: Jakub Kicinski --- net/tipc/node.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/tipc/node.c b/net/tipc/node.c index 683a136e53ef..bd91378b7540 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1333,7 +1333,9 @@ static void tipc_node_reset_links(struct tipc_node *n) pr_warn("Resetting all links to %x\n", n->addr); + tipc_node_write_lock(n); trace_tipc_node_reset_links(n, true, " "); + tipc_node_write_unlock_fast(n); for (i = 0; i < MAX_BEARERS; i++) { tipc_node_link_down(n, i, false); } From 7fcc2fe39fed1cb98a7374a113ff3800e8f9af80 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 25 Aug 2026 08:45:51 +0000 Subject: [PATCH 0148/1198] net: icmp: avoid invalid transport header access in icmp_send tracepoint syzbot reported a WARNING triggered by DEBUG_NET_WARN_ON_ONCE(): WARNING: at skb_transport_header include/linux/skbuff.h:3087 [inline] WARNING: at udp_hdr include/linux/udp.h:23 [inline] WARNING: at do_trace_event_raw_event_icmp_send include/trace/events/icmp.h:30 [inline] WARNING: at trace_event_raw_event_icmp_send+0x48c/0x6ec include/trace/events/icmp.h:11 Call trace: skb_transport_header include/linux/skbuff.h:3087 [inline] udp_hdr include/linux/udp.h:23 [inline] do_trace_event_raw_event_icmp_send include/trace/events/icmp.h:30 [inline] trace_event_raw_event_icmp_send+0x48c/0x6ec include/trace/events/icmp.h:11 __traceiter_icmp_send include/trace/events/icmp.h:11 [inline] __do_trace_icmp_send include/trace/events/icmp.h:11 [inline] trace_icmp_send+0x320/0x49c include/trace/events/icmp.h:11 __icmp_send+0xcfc/0x11d8 net/ipv4/icmp.c:1013 ipv4_send_dest_unreach net/ipv4/route.c:1280 [inline] ipv4_link_failure+0x57c/0x8dc net/ipv4/route.c:1287 dst_link_failure include/net/dst.h:438 [inline] vti_tunnel_xmit+0xe40/0x17a4 net/ipv4/ip_vti.c:307 TP_fast_assign() unconditionally calls udp_hdr(skb) before checking whether the packet is UDP. Furthermore, __icmp_send() can be invoked from paths (e.g., link failures, ARP errors, forwarding, AF_PACKET) where skb->transport_header was never initialized (~0U). Under CONFIG_DEBUG_NET=y, calling skb_transport_header(skb) triggers DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb)). Fix this by: 1. Only parsing transport info when iph->protocol == IPPROTO_UDP. 2. Using skb_header_pointer() at skb_network_offset(skb) + (iph->ihl << 2) to safely fetch the UDP header without assuming transport_header is set. Fixes: db3efdcf70c7 ("net/ipv4: add tracepoint for icmp_send") Reported-by: syzbot+6d2762674103618994b0@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/6a8d5538.91706f20.ef82.0009.GAE@google.com/T/#u Signed-off-by: Eric Dumazet Cc: Peilin He Cc: xu xin Cc: Steven Rostedt Reviewed-by: Jiayuan Chen Reviewed-by: David Ahern Link: https://patch.msgid.link/20260825084551.1562967-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/trace/events/icmp.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/include/trace/events/icmp.h b/include/trace/events/icmp.h index 09ae115099df..6937b778ae54 100644 --- a/include/trace/events/icmp.h +++ b/include/trace/events/icmp.h @@ -27,17 +27,20 @@ TRACE_EVENT(icmp_send, TP_fast_assign( struct iphdr *iph = ip_hdr(skb); - struct udphdr *uh = udp_hdr(skb); - int proto_4 = iph->protocol; + struct udphdr _uh, *uh = NULL; __be32 *p32; __entry->skbaddr = skb; __entry->type = type; __entry->code = code; - if (proto_4 != IPPROTO_UDP || (u8 *)uh < skb->head || - (u8 *)uh + sizeof(struct udphdr) - > skb_tail_pointer(skb)) { + if (iph->protocol == IPPROTO_UDP) + uh = skb_header_pointer(skb, + skb_network_offset(skb) + + (iph->ihl << 2), + sizeof(_uh), &_uh); + + if (!uh) { __entry->sport = 0; __entry->dport = 0; __entry->ulen = 0; From 2a004bfb62bdb847f25a8001e104bf33922a2cf4 Mon Sep 17 00:00:00 2001 From: Ilya Maximets Date: Thu, 27 Aug 2026 00:01:11 +0200 Subject: [PATCH 0149/1198] netlink: specs: fix the conntrack filter type MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The CTA_FILTER doesn't contain nested tuple attributes, instead it contains bit masks that specify which tuple attributes to filter on. The values for filtering are taken from the top-level CTA_TUPLE_ORIG and CTA_TUPLE_REPLY, which are also missing in the attribute list for the dump request. The bits themselves somehow are not in the public headers, so not defining them in the spec either for now. Once they are public in uAPI, they can be added here with enum-as-flags. Fixes: 23fc9311a526 ("netlink: specs: add conntrack dump and stats dump support") Cc: stable@vger.kernel.org Signed-off-by: Ilya Maximets Reviewed-by: Asbjørn Sloth Tønnesen Link: https://patch.msgid.link/20260826220444.4054714-2-i.maximets@ovn.org Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/conntrack.yaml | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/Documentation/netlink/specs/conntrack.yaml b/Documentation/netlink/specs/conntrack.yaml index db7cddcda50a..6ba28cb1c2ab 100644 --- a/Documentation/netlink/specs/conntrack.yaml +++ b/Documentation/netlink/specs/conntrack.yaml @@ -360,6 +360,17 @@ attribute-sets: name: tsoff type: u32 byte-order: big-endian + - + name: filter-attrs + attributes: + - + name: orig-flags + type: u32 + doc: bitmask of tuple fields to filter on, original direction + - + name: reply-flags + type: u32 + doc: bitmask of tuple fields to filter on, reply direction - name: conntrack-attrs attributes: @@ -466,7 +477,7 @@ attribute-sets: - name: filter type: nest - nested-attributes: tuple-attrs + nested-attributes: filter-attrs - name: status-mask type: u32 @@ -591,6 +602,8 @@ operations: request: value: 0x101 attributes: + - tuple-orig + - tuple-reply - mark - filter - status From 8b348496cbec0d5ca24a99f668096e2e16e8fbeb Mon Sep 17 00:00:00 2001 From: Ilya Maximets Date: Thu, 27 Aug 2026 00:01:12 +0200 Subject: [PATCH 0150/1198] netlink: specs: add missing mask attributes for conntrack dump MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 'mark-mask' and 'status-mask' are defined and supported by the conntrack dump, but missing from the list of arguments. While at it, the order of the arguments should follow the order of their definition in the enum ctattr_type. That appears to be a common convention for other spec files. Fixes: 23fc9311a526 ("netlink: specs: add conntrack dump and stats dump support") Cc: stable@vger.kernel.org Signed-off-by: Ilya Maximets Reviewed-by: Asbjørn Sloth Tønnesen Link: https://patch.msgid.link/20260826220444.4054714-3-i.maximets@ovn.org Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/conntrack.yaml | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/Documentation/netlink/specs/conntrack.yaml b/Documentation/netlink/specs/conntrack.yaml index 6ba28cb1c2ab..b1eb102ab843 100644 --- a/Documentation/netlink/specs/conntrack.yaml +++ b/Documentation/netlink/specs/conntrack.yaml @@ -604,10 +604,12 @@ operations: attributes: - tuple-orig - tuple-reply - - mark - - filter - status + - mark - zone + - mark-mask + - filter + - status-mask reply: value: 0x100 attributes: From 18666c73afe95eeca8707c699b63f96ce3acda42 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 27 Aug 2026 09:59:36 +0000 Subject: [PATCH 0151/1198] tcp: use GFP_ATOMIC in tcp_send_active_reset() tcp_send_active_reset() can be called from contexts where gfp_any() (in tcp_disconnect()) or sk->sk_allocation (in __tcp_close() and mptcp_do_fastclose()) evaluates to GFP_KERNEL, which includes __GFP_FS and __GFP_DIRECT_RECLAIM. Allocating with GFP_KERNEL while holding the socket lock (sk_lock) creates a lockdep dependency: sk_lock -> fs_reclaim This causes false-positive lockdep circular locking warnings with storage subsystems (such as nvme-tcp) that acquire socket locks in block I/O paths and invoke tcp_disconnect() or close sockets upon teardown: set->srcu -> sk_lock -> fs_reclaim -> elevator_lock -> set->srcu Active resets are small RST packet headers that should never enter direct reclaim or block while holding socket locks. Use sk_gfp_mask(sk, GFP_ATOMIC | __GFP_NOWARN) inside tcp_send_active_reset() and remove its priority argument. This preserves __GFP_MEMALLOC access for SOCK_MEMALLOC sockets, suppresses allocation failure warnings, and aligns with other control packet allocations (e.g. tcp_send_fin(), __tcp_send_ack(), tcp_xmit_probe_skb()). Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Acked-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260827095936.551524-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/net/tcp.h | 3 +-- net/ipv4/tcp.c | 14 ++++++-------- net/ipv4/tcp_output.c | 4 ++-- net/ipv4/tcp_timer.c | 6 +++--- net/mptcp/protocol.c | 3 +-- net/mptcp/protocol.h | 2 +- 6 files changed, 14 insertions(+), 18 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index 670c20876f26..436495ff2271 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -765,8 +765,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, void tcp_send_probe0(struct sock *); int tcp_write_wakeup(struct sock *, int mib); void tcp_send_fin(struct sock *sk); -void tcp_send_active_reset(struct sock *sk, gfp_t priority, - enum sk_rst_reason reason); +void tcp_send_active_reset(struct sock *sk, enum sk_rst_reason reason); int tcp_send_synack(struct sock *); void tcp_push_one(struct sock *, unsigned int mss_now); void __tcp_send_ack(struct sock *sk, u32 rcv_nxt, u16 flags); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b4237d0e994d..93d723d8c109 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3182,8 +3182,7 @@ void __tcp_close(struct sock *sk, long timeout) /* Unread data was tossed, zap the connection. */ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE); tcp_set_state(sk, TCP_CLOSE); - tcp_send_active_reset(sk, sk->sk_allocation, - SK_RST_REASON_TCP_ABORT_ON_CLOSE); + tcp_send_active_reset(sk, SK_RST_REASON_TCP_ABORT_ON_CLOSE); } else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) { /* Check zero linger _after_ checking for unread data. */ sk->sk_prot->disconnect(sk, 0); @@ -3257,7 +3256,7 @@ void __tcp_close(struct sock *sk, long timeout) struct tcp_sock *tp = tcp_sk(sk); if (READ_ONCE(tp->linger2) < 0) { tcp_set_state(sk, TCP_CLOSE); - tcp_send_active_reset(sk, GFP_ATOMIC, + tcp_send_active_reset(sk, SK_RST_REASON_TCP_ABORT_ON_LINGER); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONLINGER); @@ -3276,7 +3275,7 @@ void __tcp_close(struct sock *sk, long timeout) if (sk->sk_state != TCP_CLOSE) { if (tcp_check_oom(sk, 0)) { tcp_set_state(sk, TCP_CLOSE); - tcp_send_active_reset(sk, GFP_ATOMIC, + tcp_send_active_reset(sk, SK_RST_REASON_TCP_ABORT_ON_MEMORY); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); @@ -3377,14 +3376,14 @@ int tcp_disconnect(struct sock *sk, int flags) } else if (unlikely(tp->repair)) { WRITE_ONCE(sk->sk_err, ECONNABORTED); } else if (tcp_need_reset(old_state)) { - tcp_send_active_reset(sk, gfp_any(), SK_RST_REASON_TCP_STATE); + tcp_send_active_reset(sk, SK_RST_REASON_TCP_STATE); WRITE_ONCE(sk->sk_err, ECONNRESET); } else if (tp->snd_nxt != tp->write_seq && (1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK)) { /* The last check adjusts for discrepancy of Linux wrt. RFC * states */ - tcp_send_active_reset(sk, gfp_any(), + tcp_send_active_reset(sk, SK_RST_REASON_TCP_DISCONNECT_WITH_DATA); WRITE_ONCE(sk->sk_err, ECONNRESET); } else if (old_state == TCP_SYN_SENT) @@ -5147,8 +5146,7 @@ int tcp_abort(struct sock *sk, int err) bh_lock_sock(sk); if (tcp_need_reset(sk->sk_state)) - tcp_send_active_reset(sk, GFP_ATOMIC, - SK_RST_REASON_TCP_STATE); + tcp_send_active_reset(sk, SK_RST_REASON_TCP_STATE); tcp_done_with_error(sk, err); bh_unlock_sock(sk); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 6f4dca4a4de9..c5ffffee4349 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3849,9 +3849,9 @@ void tcp_send_fin(struct sock *sk) * was unread data in the receive queue. This behavior is recommended * by RFC 2525, section 2.17. -DaveM */ -void tcp_send_active_reset(struct sock *sk, gfp_t priority, - enum sk_rst_reason reason) +void tcp_send_active_reset(struct sock *sk, enum sk_rst_reason reason) { + gfp_t priority = sk_gfp_mask(sk, GFP_ATOMIC | __GFP_NOWARN); struct sk_buff *skb; TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTRSTS); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 1038e7ba9c2e..e56eae4bc341 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -126,7 +126,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset) (!tp->snd_wnd && !tp->packets_out)) do_reset = true; if (do_reset) - tcp_send_active_reset(sk, GFP_ATOMIC, + tcp_send_active_reset(sk, SK_RST_REASON_TCP_ABORT_ON_MEMORY); tcp_done(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); @@ -809,7 +809,7 @@ static void tcp_keepalive_timer(struct timer_list *t) goto out; } } - tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_TCP_STATE); + tcp_send_active_reset(sk, SK_RST_REASON_TCP_STATE); goto death; } @@ -836,7 +836,7 @@ static void tcp_keepalive_timer(struct timer_list *t) icsk->icsk_probes_out > 0) || (user_timeout == 0 && icsk->icsk_probes_out >= keepalive_probes(tp))) { - tcp_send_active_reset(sk, GFP_ATOMIC, + tcp_send_active_reset(sk, SK_RST_REASON_TCP_KEEPALIVE_TIMEOUT); tcp_write_err(sk); goto out; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index b474d03620a7..e1f08f71cdb1 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3109,8 +3109,7 @@ static void mptcp_do_fastclose(struct sock *sk) */ inet_csk(ssk)->icsk_ack.rcv_mss = TCP_MIN_MSS; - tcp_send_active_reset(ssk, ssk->sk_allocation, - SK_RST_REASON_TCP_ABORT_ON_CLOSE); + tcp_send_active_reset(ssk, SK_RST_REASON_TCP_ABORT_ON_CLOSE); unlock: release_sock(ssk); } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 06a107d4e839..87ccb84e9927 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -690,7 +690,7 @@ mptcp_send_active_reset_reason(struct sock *sk) enum sk_rst_reason reason; reason = sk_rst_convert_mptcp_reason(subflow->reset_reason); - tcp_send_active_reset(sk, GFP_ATOMIC, reason); + tcp_send_active_reset(sk, reason); } /* Made the fwd mem carried by the given skb available to the msk, From a5d946466a95621fa2769720d59ea336003aa1a5 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Wed, 26 Aug 2026 15:03:15 +0200 Subject: [PATCH 0152/1198] net: stmmac: fix dma mapping leak in stmmac_tso_xmit() In stmmac_tso_xmit(), if the DMA mapping of an skb fragment fails, the frame is dropped but the DMA mappings already created for the linear part and for the fragments mapped before the failure are never unmapped, leaking DMA mappings. Fix the leak by walking back over the descriptors used by the frame and releasing each of them with stmmac_free_tx_buffer(). Moreover, release the descriptors with stmmac_release_tx_desc() unmapping the DMA buffers. Fixes: f748be531d70 ("stmmac: support new GMAC4") Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20260826-stmmac_dma_unmap_tso-v1-1-a2753d1576ba@oss.qualcomm.com Signed-off-by: Jakub Kicinski --- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 53 ++++++++++++------- 1 file changed, 34 insertions(+), 19 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index f2fc89176654..d576059c04df 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -4319,6 +4319,7 @@ static bool stmmac_vlan_insert(struct stmmac_priv *priv, struct sk_buff *skb, /** * stmmac_tso_allocator - close entry point of the driver * @priv: driver private structure + * @entry: TX queue buffer index * @des: buffer start address * @total_len: total length to fill in descriptors * @last_segment: condition for the last descriptor @@ -4327,8 +4328,9 @@ static bool stmmac_vlan_insert(struct stmmac_priv *priv, struct sk_buff *skb, * This function fills descriptor and request new descriptors according to * buffer length to fill */ -static void stmmac_tso_allocator(struct stmmac_priv *priv, dma_addr_t des, - int total_len, bool last_segment, u32 queue) +static void stmmac_tso_allocator(struct stmmac_priv *priv, u32 *entry, + dma_addr_t des, int total_len, + bool last_segment, u32 queue) { struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[queue]; struct dma_desc *desc; @@ -4340,14 +4342,13 @@ static void stmmac_tso_allocator(struct stmmac_priv *priv, dma_addr_t des, while (tmp_len > 0) { dma_addr_t curr_addr; - tx_q->cur_tx = STMMAC_NEXT_ENTRY(tx_q->cur_tx, - priv->dma_conf.dma_tx_size); - WARN_ON(tx_q->tx_skbuff[tx_q->cur_tx]); + *entry = STMMAC_NEXT_ENTRY(*entry, priv->dma_conf.dma_tx_size); + WARN_ON(tx_q->tx_skbuff[*entry]); if (tx_q->tbs & STMMAC_TBS_AVAIL) - desc = &tx_q->dma_entx[tx_q->cur_tx].basic; + desc = &tx_q->dma_entx[*entry].basic; else - desc = &tx_q->dma_tx[tx_q->cur_tx]; + desc = &tx_q->dma_tx[*entry]; curr_addr = des + (total_len - tmp_len); stmmac_set_desc_addr(priv, desc, curr_addr); @@ -4486,7 +4487,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) { struct dma_desc *desc, *first, *mss_desc = NULL; struct stmmac_priv *priv = netdev_priv(dev); - unsigned int first_entry, tx_packets; + unsigned int first_entry, entry, tx_packets; struct stmmac_txq_stats *txq_stats; struct stmmac_tx_queue *tx_q; bool set_ic, is_last_segment; @@ -4549,22 +4550,24 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) } first_entry = tx_q->cur_tx; - WARN_ON(tx_q->tx_skbuff[first_entry]); + entry = first_entry; + + WARN_ON(tx_q->tx_skbuff[entry]); if (tx_q->tbs & STMMAC_TBS_AVAIL) - desc = &tx_q->dma_entx[first_entry].basic; + desc = &tx_q->dma_entx[entry].basic; else - desc = &tx_q->dma_tx[first_entry]; + desc = &tx_q->dma_tx[entry]; first = desc; /* first descriptor: fill Headers on Buf1 */ des = dma_map_single(priv->device, skb->data, skb_headlen(skb), DMA_TO_DEVICE); if (dma_mapping_error(priv->device, des)) - goto dma_map_err; + goto error; stmmac_set_desc_addr(priv, first, des); - stmmac_tso_allocator(priv, des + proto_hdr_len, pay_len, + stmmac_tso_allocator(priv, &entry, des + proto_hdr_len, pay_len, (nfrags == 0), queue); /* In case two or more DMA transmit descriptors are allocated for this @@ -4579,8 +4582,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) * this DMA buffer right after the DMA engine completely finishes the * full buffer transmission. */ - stmmac_set_tx_skb_dma_entry(tx_q, tx_q->cur_tx, des, skb_headlen(skb), - false); + stmmac_set_tx_skb_dma_entry(tx_q, entry, des, skb_headlen(skb), false); /* Prepare fragments */ for (i = 0; i < nfrags; i++) { @@ -4590,14 +4592,15 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) skb_frag_size(frag), DMA_TO_DEVICE); if (dma_mapping_error(priv->device, des)) - goto dma_map_err; + goto error_dma_unmap; - stmmac_tso_allocator(priv, des, skb_frag_size(frag), + stmmac_tso_allocator(priv, &entry, des, skb_frag_size(frag), (i == nfrags - 1), queue); - stmmac_set_tx_skb_dma_entry(tx_q, tx_q->cur_tx, des, + stmmac_set_tx_skb_dma_entry(tx_q, entry, des, skb_frag_size(frag), true); } + tx_q->cur_tx = entry; stmmac_set_tx_dma_last_segment(tx_q, tx_q->cur_tx); @@ -4702,7 +4705,19 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; -dma_map_err: +error_dma_unmap: + for (;;) { + desc = stmmac_get_tx_desc(priv, tx_q, first_entry); + stmmac_release_tx_desc(priv, desc, priv->descriptor_mode); + stmmac_free_tx_buffer(priv, &priv->dma_conf, queue, + first_entry); + if (first_entry == entry) + break; + + first_entry = STMMAC_NEXT_ENTRY(first_entry, + priv->dma_conf.dma_tx_size); + } +error: dev_err(priv->device, "Tx dma map failed\n"); dev_kfree_skb(skb); priv->xstats.tx_dropped++; From e01620844c5c88b6fcf819d171df8e3976a0e76f Mon Sep 17 00:00:00 2001 From: Jerome Tollet Date: Mon, 24 Aug 2026 16:16:44 +0200 Subject: [PATCH 0153/1198] net/mlx5e: Prevent stale XSK buffer release on refill retry When an XDP redirect to an AF_XDP socket fails because its RX ring is full, the XSK core frees the buffer. During the subsequent batched refill of a legacy cyclic RQ, mlx5e also releases the WQE's XSK buffer before allocating a replacement. If that refill succeeds only partially, a WQE left without a replacement retains its old buffer pointer. The buffer can meanwhile be allocated to another WQE. A later refill retry can then free the live buffer through the stale pointer and publish the same UMEM frame twice. Mark the WQE as released immediately after the driver-side free. The flag is already cleared when a replacement buffer is assigned, so refill retries no longer release stale pointers. The failure is silent and produces no kernel warning or splat. A standalone legacy cyclic-RQ zero-copy libxsk reproducer, using 64-byte UDP traffic offered at 12 Mpps, detected it: stock stopped after 2,854,914 packets in 4.094 seconds, with 4,542 xdp_rx_ring_full events and 64 ownership/double-publication errors. With this change it processed 356,904,225 packets in 30 seconds despite 571,405 xdp_rx_ring_full events, with no ownership or data errors. Fixes: 3f93f82988bc ("net/mlx5e: RX, Defer page release in legacy rq for better recycling") Cc: stable@vger.kernel.org Suggested-by: Daniel Borkmann Reviewed-by: Dragos Tatulea Signed-off-by: Jerome Tollet Link: https://patch.msgid.link/20260824141645.23700-2-jtollet@cisco.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 206cf9db3466..7bd0606a5253 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -410,8 +410,11 @@ static inline void mlx5e_free_rx_wqe(struct mlx5e_rq *rq, static void mlx5e_xsk_free_rx_wqe(struct mlx5e_wqe_frag_info *wi) { - if (!(wi->flags & BIT(MLX5E_WQE_FRAG_SKIP_RELEASE))) - xsk_buff_free(*wi->xskp); + if (wi->flags & BIT(MLX5E_WQE_FRAG_SKIP_RELEASE)) + return; + + xsk_buff_free(*wi->xskp); + wi->flags |= BIT(MLX5E_WQE_FRAG_SKIP_RELEASE); } static void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix) From 63811edf512584c946e5e96b100e9e280703bbb5 Mon Sep 17 00:00:00 2001 From: Jerome Tollet Date: Mon, 24 Aug 2026 16:16:45 +0200 Subject: [PATCH 0154/1198] net/mlx5e: Prevent stale XSK buffer release on MPWQE refill retry With AF_XDP on a striding RQ, mlx5e defers releasing XSK buffers until an MPWQE is refilled. If XSK allocation then returns -ENOMEM, actual_wq_head is not advanced and a later NAPI poll retries the same WQE. mlx5e_free_rx_mpwqe() leaves each released slot marked as releasable. On retry it can therefore call xsk_buff_free() again through stale pointers after the frames have returned to the XSK pool and been reallocated. Set all skip_release_bitmap bits in the common error path of mlx5e_xsk_alloc_rx_mpwqe(). This matches mlx5e_alloc_rx_mpwqe(). A successful allocation already clears the bitmap after replacing every buffer, so retries become idempotent without changing the success path. Fault injection forced three consecutive failures for one selected MPWQE. Both an early allocation failure and a partial 8-of-16-buffer unwind released the original 16 XSK buffers only once. Each error left a full bitmap, the following NAPI retry skipped the release, and a later successful allocation cleared it. A 20-second AF_XDP zero-copy pressure run exercised 1,575,262 buffer allocation failures without invalid descriptors, WQE errors, or kernel warnings. Fixes: 4c2a13236807 ("net/mlx5e: RX, Defer page release in striding rq for better recycling") Cc: stable@vger.kernel.org Signed-off-by: Jerome Tollet Reviewed-by: Dragos Tatulea Link: https://patch.msgid.link/20260824141645.23700-3-jtollet@cisco.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c index 4f984f6a2cb9..55ec6387ab28 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c @@ -3,6 +3,7 @@ #include "rx.h" #include "en/xdp.h" +#include #include #include @@ -156,6 +157,7 @@ int mlx5e_xsk_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) xsk_buff_free(xsk_buffs[batch]); err: + bitmap_fill(wi->skip_release_bitmap, rq->mpwqe.pages_per_wqe); rq->stats->buff_alloc_err++; return -ENOMEM; } From 28a57fb2c5df4deb42a06e52fd36c14b37aa0034 Mon Sep 17 00:00:00 2001 From: Dong Chenchen Date: Tue, 25 Aug 2026 20:39:09 +0800 Subject: [PATCH 0155/1198] net: iptunnel: fix stale transport header during tunnel decapsulation Syzbot reported a crash in qdisc_pkt_len_segs_init() caused by a stale transport_header offset after tunnel decapsulation. BUG: unable to handle page fault for address: ffffed102091a42e Oops: Oops: 0000 [#1] SMP KASAN NOPTI CPU: 0 UID: 0 PID: 340 Comm: qdisc_uaf_repro Not tainted 7.2.0-rc4-00061-g248951ddc14d #256 PREEMPT(full) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 RIP: 0010:__asan_load2 qdisc_pkt_len_segs_init (net/core/dev.c:4145) __dev_queue_xmit (net/core/dev.c:4787) br_dev_queue_push_xmit (net/bridge/br_forward.c:53) br_handle_frame_finish (net/bridge/br_input.c:229) br_handle_frame (net/bridge/br_input.c:315) __netif_receive_skb_core.constprop.0 (net/core/dev.c:6099) __netif_receive_skb_list_core (net/core/dev.c:6287) netif_receive_skb_list_internal (net/core/dev.c:6445) napi_complete_done (net/core/dev.c:6813) gro_cell_poll (net/core/gro_cells.c:74) __napi_poll (net/core/dev.c:7735) net_rx_action (net/core/dev.c:7798 net/core/dev.c:7955) handle_softirqs (kernel/softirq.c:622) do_softirq (kernel/softirq.c:523 kernel/softirq.c:510 ) __local_bh_enable_ip (kernel/softirq.c:450) tun_get_user (drivers/net/tun.c:1986 (discriminator 1)) tun_chr_write_iter (drivers/net/tun.c:2032) The issue is completely latent until qdisc read transport header in commit 7fb4c1967011 ("net: pull headers in qdisc_pkt_len_segs_init()"). The crash requires four conditions to line up: 1. The incoming packet is encapsulated and carries GSO metadata. The outer transport header offset is stored in skb->transport_header while the packet is still in the outer tunnel context. 2. The tunnel receiver strips the outer headers. skb->data is advanced to the inner frame, but skb->transport_header is left pointing to the now-removed outer L4 header, so it becomes a negative offset relative to the new data. 3. The inner frame is not delivered to the local IP stack. Instead, it is forwarded at L2 by a bridge or HSR, so ip_rcv_core() never runs and the transport header is not reset to the inner L4 offset. 4. The forwarding path calls __dev_queue_xmit(), which enters qdisc_pkt_len_segs_init(). That function computes the GSO header length from skb_transport_offset(skb). Because the offset is negative, the unsigned cast overflows and pskb_may_pull(skb, hdr_len + sizeof(struct tcphdr)) reads past the end of the skb, triggering a KASAN fault or page fault. The issue specifically requires GSO packets (shinfo->gso_size != 0), which are processed/aggregated through gro_cells. Fix this by clearing transport_header to the ~0U sentinel in gro_cell for all tunnnel driver. GTP does not support GRO/GSO, drop the evil GSO packets in GTP directly. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot+83181a31faf9455499c5@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/69de2bee.a00a0220.475f0.0041.GAE@google.com/T/ Suggested-by: Eric Dumazet Signed-off-by: Dong Chenchen Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20260825123909.1463121-1-dongchenchen2@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/gtp.c | 5 +++++ include/linux/skbuff.h | 5 +++++ net/core/gro_cells.c | 2 ++ 3 files changed, 12 insertions(+) diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 298efc76a56b..69fe5717846b 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -318,6 +318,11 @@ static int gtp_inner_proto(struct sk_buff *skb, unsigned int hdrlen, static int gtp_rx(struct pdp_ctx *pctx, struct sk_buff *skb, unsigned int hdrlen, unsigned int role, __u16 inner_proto) { + if (skb_is_gso(skb)) { + netdev_dbg(pctx->dev, "GSO is not supported in GTP\n"); + goto err; + } + if (!gtp_check_ms(skb, pctx, hdrlen, role, inner_proto)) { netdev_dbg(pctx->dev, "No PDP ctx for this MS\n"); return 1; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 671c13494566..421f6fc45451 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3082,6 +3082,11 @@ static inline bool skb_transport_header_was_set(const struct sk_buff *skb) return skb->transport_header != (typeof(skb->transport_header))~0U; } +static inline void skb_unset_transport_header(struct sk_buff *skb) +{ + skb->transport_header = (typeof(skb->transport_header))~0U; +} + static inline unsigned char *skb_transport_header(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb)); diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c index 1b84385c04bd..d8c0a2867120 100644 --- a/net/core/gro_cells.c +++ b/net/core/gro_cells.c @@ -22,6 +22,8 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb) if (unlikely(!(dev->flags & IFF_UP))) goto drop; + skb_unset_transport_header(skb); + if (!gcells->cells || skb_cloned(skb) || netif_elide_gro(dev)) { res = netif_rx(skb); goto unlock; From 13eb543cebef6d6c3ec42e31afe3856f51b7126b Mon Sep 17 00:00:00 2001 From: Victor Nogueira Date: Mon, 24 Aug 2026 12:39:00 -0300 Subject: [PATCH 0156/1198] net/sched: act_api: budget all shared attributes in notify skbs tcf_action_shared_attrs_size() is supposed to return an upper bound on the netlink attributes every action dump emits outside of TCA_ACT_OPTIONS, so that tcf_add_notify_msg(), tcf_del_notify_msg() and friends can allocate an skb large enough for the reply. It has fallen behind the dump path and is now an underestimate for every single action. Attributes, such as, TCA_ACT_IN_HW_COUNT and TCA_STATS_BASIC_HW are emitted unconditionally and never accounted for. TCA_STATS_PKT64, TCA_ACT_USED_HW_STATS, TCA_STATS_RATE_EST, TCA_STATS_RATE_EST64 require specific conditions, but are also not accounted for. Fix the issue by budgeting all of them so that we have a legitimate upper bound. Even tough for of them require specific conditions, they are cheap so, to avoid overcomplicating, we opted to account for them unconditionally as well to account for a real worst case scenario. Fixes: 4e76e75d6aba ("net sched actions: calculate add/delete event message size") Reported-by: Sashiko Closes: https://netdev-ai.bots.linux.dev/sashiko/#/patchset/20260810164357.1653956-1-victor%40mojatatu.com Acked-by: Jamal Hadi Salim Signed-off-by: Victor Nogueira Link: https://patch.msgid.link/20260824153903.4143642-2-victor@mojatatu.com Signed-off-by: Jakub Kicinski --- net/sched/act_api.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/net/sched/act_api.c b/net/sched/act_api.c index b4415d358c91..766162b0b810 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -443,12 +443,21 @@ static size_t tcf_action_shared_attrs_size(const struct tc_action *act) + nla_total_size(IFNAMSIZ) /* TCA_ACT_KIND */ + cookie_len /* TCA_ACT_COOKIE */ + nla_total_size(sizeof(struct nla_bitfield32)) /* TCA_ACT_HW_STATS */ + /* TCA_ACT_USED_HW_STATS */ + + nla_total_size(sizeof(struct nla_bitfield32)) + + nla_total_size(sizeof(u32)) /* TCA_ACT_IN_HW_COUNT */ + nla_total_size(0) /* TCA_ACT_STATS nested */ + nla_total_size(sizeof(struct nla_bitfield32)) /* TCA_ACT_FLAGS */ /* TCA_STATS_BASIC */ + nla_total_size_64bit(sizeof(struct gnet_stats_basic)) - /* TCA_STATS_PKT64 */ - + nla_total_size_64bit(sizeof(u64)) + /* TCA_STATS_BASIC_HW */ + + nla_total_size_64bit(sizeof(struct gnet_stats_basic)) + /* TCA_STATS_PKT64, emitted by both of the basic copies above */ + + 2 * nla_total_size_64bit(sizeof(u64)) + /* TCA_STATS_RATE_EST */ + + nla_total_size_64bit(sizeof(struct gnet_stats_rate_est)) + /* TCA_STATS_RATE_EST64 */ + + nla_total_size_64bit(sizeof(struct gnet_stats_rate_est64)) /* TCA_STATS_QUEUE */ + nla_total_size_64bit(sizeof(struct gnet_stats_queue)) + nla_total_size(0) /* TCA_ACT_OPTIONS nested */ From e9ca46ebc3262b498626c4095826b8fa034bbf21 Mon Sep 17 00:00:00 2001 From: Victor Nogueira Date: Mon, 24 Aug 2026 12:39:01 -0300 Subject: [PATCH 0157/1198] net/sched: act_api: size the RTM_GETACTION reply from the actions tca_action_gd() already walks every requested action and accumulates attr_size += tcf_action_fill_size(act), then wraps the result in tcf_action_full_attrs_size(). For RTM_DELACTION that value is handed to tcf_del_notify_msg(), which allocates max(attr_size, NLMSG_GOODSIZE). For RTM_GETACTION it is silently discarded and tcf_get_notify() allocates a fixed NLMSG_GOODSIZE skb instead. Any action whose dump exceeds that fixed budget therefore cannot be read back. For example, act_pedit overruns the budget with 32 actions of four munge keys each, act_police with 32 policers once the optional rate/peakrate/result/avrate attributes are present Fix this by passing attr_size through and allocate the reply the way the add and delete paths do. Note on exposure: RTM_GETACTION is the only one of the three action commands that is not capability checked - tc_ctl_action() requires CAP_NET_ADMIN for RTM_NEWACTION and RTM_DELACTION only - so this turns a fixed NLMSG_GOODSIZE reply into a user sized allocation on an unprivileged path. It is bounded by TCA_ACT_MAX_PRIO actions per request, and tca_action_gd() does not reject duplicate indices, so a single large action can be requested 32 times; an act_bpf program near BPF_MAXINSNS is about 32KB of dump, or roughly 1MB for one request. Creating such an action still requires CAP_NET_ADMIN, and the add and delete paths have sized their skbs this way since the Fixes commit. Should this ever need bounding, GFP_KERNEL_ACCOUNT would charge the reply to the caller's memcg. Fixes: 4e76e75d6aba ("net sched actions: calculate add/delete event message size") Reported-by: Sashiko Closes: https://netdev-ai.bots.linux.dev/sashiko/#/patchset/20260810164357.1653956-1-victor%40mojatatu.com Acked-by: Jamal Hadi Salim Signed-off-by: Victor Nogueira Link: https://patch.msgid.link/20260824153903.4143642-3-victor@mojatatu.com Signed-off-by: Jakub Kicinski --- net/sched/act_api.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 766162b0b810..20b6501fd33b 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -1697,12 +1697,12 @@ static int tca_get_fill(struct sk_buff *skb, struct tc_action *actions[], static int tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, - struct tc_action *actions[], int event, + struct tc_action *actions[], size_t attr_size, int event, struct netlink_ext_ack *extack) { struct sk_buff *skb; - skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + skb = alloc_skb(max(attr_size, NLMSG_GOODSIZE), GFP_KERNEL); if (!skb) return -ENOBUFS; if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, event, @@ -2053,7 +2053,8 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, attr_size = tcf_action_full_attrs_size(attr_size); if (event == RTM_GETACTION) - ret = tcf_get_notify(net, portid, n, actions, event, extack); + ret = tcf_get_notify(net, portid, n, actions, attr_size, event, + extack); else { /* delete */ ret = tcf_del_notify(net, n, actions, portid, attr_size, extack); if (ret) From 251367a0a3319fa565daf7468b0afd933b1f5ab1 Mon Sep 17 00:00:00 2001 From: Victor Nogueira Date: Mon, 24 Aug 2026 12:39:02 -0300 Subject: [PATCH 0158/1198] net/sched: act_api: fix skb sizing and action leak on reoffload delete tcf_reoffload_del_notify_msg() sizes the RTM_DELACTION skb with tcf_action_fill_size(action) alone. Unlike every other notification path it never wraps that in tcf_action_full_attrs_size(), so the nlmsg_put() header, struct tcamsg and the TCA_ACT_TAB nest that tca_get_fill() emits - 24 bytes on x86_64 - are not budgeted. As long as the single action stays well under NLMSG_GOODSIZE the floor in alloc_skb() hides this, but once its fill size crosses NLMSG_GOODSIZE the allocation is exactly 24 bytes short and tca_get_fill() runs out of tailroom. That is now easy to reach for an offloadable act_pedit with a large tcfp_nkeys, which commit 8e2efb3f45a5 ("net/sched: add get_fill_size callbacks for actions missing them") started accounting for properly. When that happens tcf_reoffload_del_notify() returns early, before tcf_idr_release_unsafe(), and tcf_action_reoffload_cb() discards the return value: if (tc_act_skip_sw(p->tcfa_flags) && !tc_act_in_hw(p)) tcf_reoffload_del_notify(net, p); The action has just lost its last hardware instance and is skip_sw, so it is left installed while processing no packets, and with no notification to tell userspace about it. An -ENOBUFS from alloc_skb() gets the same treatment. Fix this by budgeting the message header the way the add and delete paths do, and release the action even when the notification cannot be built - dropping the notification is strictly better than leaking a dead action, and there is no caller left to report the error to. Fixes: 13926d19a11e ("flow_offload: add reoffload process to update hw_count") Reported-by: Sashiko Closes: https://netdev-ai.bots.linux.dev/sashiko/#/patchset/20260810164357.1653956-1-victor%40mojatatu.com Acked-by: Jamal Hadi Salim Signed-off-by: Victor Nogueira Reviewed-by: Pedro Tammela Link: https://patch.msgid.link/20260824153903.4143642-4-victor@mojatatu.com Signed-off-by: Jakub Kicinski --- net/sched/act_api.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 20b6501fd33b..37eced84dfa5 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -1867,11 +1867,13 @@ static int tcf_action_delete(struct net *net, struct tc_action *actions[]) static struct sk_buff *tcf_reoffload_del_notify_msg(struct net *net, struct tc_action *action) { - size_t attr_size = tcf_action_fill_size(action); struct tc_action *actions[TCA_ACT_MAX_PRIO] = { [0] = action, }; struct sk_buff *skb; + size_t attr_size; + + attr_size = tcf_action_full_attrs_size(tcf_action_fill_size(action)); skb = alloc_skb(max(attr_size, NLMSG_GOODSIZE), GFP_KERNEL); if (!skb) @@ -1888,15 +1890,18 @@ static struct sk_buff *tcf_reoffload_del_notify_msg(struct net *net, static int tcf_reoffload_del_notify(struct net *net, struct tc_action *action) { const struct tc_action_ops *ops = action->ops; - struct sk_buff *skb; + struct sk_buff *skb = NULL; int ret; - if (!rtnl_notify_needed(net, 0, RTNLGRP_TC)) { - skb = NULL; - } else { + if (rtnl_notify_needed(net, 0, RTNLGRP_TC)) { skb = tcf_reoffload_del_notify_msg(net, action); + /* The action has already lost its hardware instance and is + * skip_sw, so it must be released whether or not the + * notification can be built. Drop the notification rather + * than leave an action behind that processes no packets. + */ if (IS_ERR(skb)) - return PTR_ERR(skb); + skb = NULL; } ret = tcf_idr_release_unsafe(action); From 5271b79b7ad68dcb222e893773f92bdabf7750f3 Mon Sep 17 00:00:00 2001 From: "Cen Zhang (Microsoft Security FORGE Labs)" Date: Thu, 27 Aug 2026 19:55:10 -0400 Subject: [PATCH 0159/1198] tcp: fix use-after-free in do_tcp_getsockopt(TCP_CONGESTION) do_tcp_getsockopt() reads icsk->icsk_ca_ops->name without holding rcu_read_lock(). Since commit 0baf26b0fcd7 ("bpf: tcp: Support tcp_congestion_ops in bpf"), icsk_ca_ops can point to dynamically allocated BPF struct_ops memory that may be freed concurrently via setsockopt(TCP_CONGESTION), leading to a use-after-free. BUG: KASAN: slab-use-after-free in _copy_to_user+0x37/0x60 Read of size 16 at addr ffff888013505260 by task exploit/149 _copy_to_user+0x37/0x60 do_tcp_getsockopt+0x158a/0x2460 (net/ipv4/tcp.c:4585) tcp_getsockopt+0x91/0xf0 __sys_getsockopt+0xf7/0x170 Fix this by holding rcu_read_lock() around the ca_ops->name access, using READ_ONCE() to load icsk_ca_ops, and copying the name to a stack buffer before releasing the lock. Also annotate the relevant icsk_ca_ops stores with WRITE_ONCE() to fix the accompanying KCSAN data-race issue. Fixes: 0baf26b0fcd7 ("bpf: tcp: Support tcp_congestion_ops in bpf") Suggested-by: Eric Dumazet Reported-by: Xiang Mei (Microsoft) Link: https://lore.kernel.org/all/20260821182449.79785-2-blbllhy@gmail.com/ Cc: AutonomousCodeSecurity@microsoft.com Cc: stable@vger.kernel.org Reviewed-by: Eric Dumazet Signed-off-by: Cen Zhang (Microsoft Security FORGE Labs) Reviewed-by: Jiayuan Chen Reviewed-by: Matthieu Baerts (NGI0) Reviewed-by: Breno Leitao Link: https://patch.msgid.link/d3f97f1acbf0010898148be6e6406e4b8b4a5c84.1787870710.git.blbllhy@gmail.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp.c | 14 +++++++++++--- net/ipv4/tcp_cong.c | 4 ++-- net/ipv4/tcp_dctcp.c | 2 +- net/ipv4/tcp_minisocks.c | 2 +- net/ipv4/tcp_output.c | 2 +- 5 files changed, 16 insertions(+), 8 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 93d723d8c109..740999c9efff 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4576,16 +4576,24 @@ int do_tcp_getsockopt(struct sock *sk, int level, val = !inet_csk_in_pingpong_mode(sk); break; - case TCP_CONGESTION: + case TCP_CONGESTION: { + char ca_name[TCP_CA_NAME_MAX] = {}; + if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; len = min_t(unsigned int, len, TCP_CA_NAME_MAX); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; - if (copy_to_sockptr(optval, icsk->icsk_ca_ops->name, len)) + + rcu_read_lock(); + memcpy(ca_name, READ_ONCE(icsk->icsk_ca_ops)->name, + sizeof(ca_name)); + rcu_read_unlock(); + + if (copy_to_sockptr(optval, ca_name, len)) return -EFAULT; return 0; - + } case TCP_ULP: if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index e9f6c77e0631..8e83ef81fc18 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -223,7 +223,7 @@ void tcp_assign_congestion_control(struct sock *sk) ca = rcu_dereference(net->ipv4.tcp_congestion_control); if (unlikely(!bpf_try_module_get(ca, ca->owner))) ca = &tcp_reno; - icsk->icsk_ca_ops = ca; + WRITE_ONCE(icsk->icsk_ca_ops, ca); rcu_read_unlock(); memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); @@ -253,7 +253,7 @@ static void tcp_reinit_congestion_control(struct sock *sk, struct inet_connection_sock *icsk = inet_csk(sk); tcp_cleanup_congestion_control(sk); - icsk->icsk_ca_ops = ca; + WRITE_ONCE(icsk->icsk_ca_ops, ca); icsk->icsk_ca_setsockopt = 1; memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 274e628e7cf8..99f68c2992d0 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -111,7 +111,7 @@ __bpf_kfunc static void dctcp_init(struct sock *sk) /* No ECN support? Fall back to Reno. Also need to clear * ECT from sk since it is set during 3WHS for DCTCP. */ - inet_csk(sk)->icsk_ca_ops = &dctcp_reno; + WRITE_ONCE(inet_csk(sk)->icsk_ca_ops, &dctcp_reno); INET_ECN_dontxmit(sk); } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index f3fa0b18eda0..0ddfd5af6e58 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -507,7 +507,7 @@ void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst) ca = tcp_ca_find_key(ca_key); if (likely(ca && bpf_try_module_get(ca, ca->owner))) { icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst); - icsk->icsk_ca_ops = ca; + WRITE_ONCE(icsk->icsk_ca_ops, ca); ca_got_dst = true; } rcu_read_unlock(); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index c5ffffee4349..d960e3de7d50 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -4092,7 +4092,7 @@ static void tcp_ca_dst_init(struct sock *sk, const struct dst_entry *dst) if (likely(ca && bpf_try_module_get(ca, ca->owner))) { bpf_module_put(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner); icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst); - icsk->icsk_ca_ops = ca; + WRITE_ONCE(icsk->icsk_ca_ops, ca); } rcu_read_unlock(); } From 385e474086c2e7e29e2dded690be40dc273e20ee Mon Sep 17 00:00:00 2001 From: "Cen Zhang (Microsoft Security FORGE Labs)" Date: Thu, 27 Aug 2026 19:55:11 -0400 Subject: [PATCH 0160/1198] tcp: fix use-after-free in do_tcp_getsockopt(TCP_CC_INFO) do_tcp_getsockopt() reads icsk->icsk_ca_ops and dereferences the get_info function pointer without rcu_read_lock(). With BPF struct_ops congestion control, ca_ops can point to dynamically allocated memory that is freed concurrently, resulting in a use-after-free when the kernel dereferences or calls through the stale pointer. BUG: KASAN: slab-use-after-free in do_tcp_getsockopt+0x2037/0x23e0 Read of size 8 at addr ffff888013701258 by task exploit/149 do_tcp_getsockopt+0x2037/0x23e0 (net/ipv4/tcp.c:4564) tcp_getsockopt+0x91/0xf0 __sys_getsockopt+0xf7/0x170 Fix this by wrapping the ca_ops load and get_info call within rcu_read_lock()/rcu_read_unlock(), and using READ_ONCE() to load the icsk_ca_ops pointer. Fixes: 0baf26b0fcd7 ("bpf: tcp: Support tcp_congestion_ops in bpf") Suggested-by: Eric Dumazet Cc: AutonomousCodeSecurity@microsoft.com Cc: stable@vger.kernel.org Reviewed-by: Eric Dumazet Signed-off-by: Cen Zhang (Microsoft Security FORGE Labs) Reviewed-by: Jiayuan Chen Reviewed-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/65fd3816ed5d541d9edd4bf4fcf97104a2cf907a.1787870710.git.blbllhy@gmail.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp.c | 4 +++- net/ipv4/tcp_dctcp.c | 2 +- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 740999c9efff..1c867a302444 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4561,9 +4561,11 @@ int do_tcp_getsockopt(struct sock *sk, int level, if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; - ca_ops = icsk->icsk_ca_ops; + rcu_read_lock(); + ca_ops = READ_ONCE(icsk->icsk_ca_ops); if (ca_ops && ca_ops->get_info) sz = ca_ops->get_info(sk, ~0U, &attr, &info); + rcu_read_unlock(); len = min_t(unsigned int, len, sz); if (copy_to_sockptr(optlen, &len, sizeof(int))) diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 99f68c2992d0..5b457f68a581 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -228,7 +228,7 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr, if (ext & (1 << (INET_DIAG_DCTCPINFO - 1)) || ext & (1 << (INET_DIAG_VEGASINFO - 1))) { memset(&info->dctcp, 0, sizeof(info->dctcp)); - if (inet_csk(sk)->icsk_ca_ops != &dctcp_reno) { + if (READ_ONCE(inet_csk(sk)->icsk_ca_ops) != &dctcp_reno) { info->dctcp.dctcp_enabled = 1; info->dctcp.dctcp_ce_state = (u16) ca->ce_state; info->dctcp.dctcp_alpha = ca->dctcp_alpha; From 2188569e7e1b0bc3f3b557dc97ab7a02befc11c8 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 26 Aug 2026 15:49:04 -0400 Subject: [PATCH 0161/1198] sctp: fix a TOCTOU race in SCTP_CMD_TIMER_START The SCTP_CMD_TIMER_START handler checks timer_pending() before calling timer_reduce(). The timer can expire and detach between these operations, causing timer_reduce() to rearm the timer without taking the association reference required for the newly armed timer. The timer callback later unconditionally drops its association reference, which can leave the association reference count unbalanced and result in use-after-free during association teardown. Use the return value of timer_reduce() to determine whether the timer was actually armed. Take the association reference only when timer_reduce() successfully starts a new timer, closing the race between checking the timer state and rearming it. This issue was reported by Nico Yip (@_cyeaa_) working with TrendAI Zero Day Initiative. Fixes: 20a785aa52c8 ("sctp: Don't add the shutdown timer if its already been added") Reported-by: Zero Day Initiative Signed-off-by: Xin Long Link: https://patch.msgid.link/9d8f1b5c50329d5ea7c642128d35681abaa9ed20.1787773744.git.lucien.xin@gmail.com Signed-off-by: Jakub Kicinski --- net/sctp/sm_sideeffect.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 94716406d602..0d99b7e8c082 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -1545,17 +1545,8 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type, timeout = asoc->timeouts[cmd->obj.to]; BUG_ON(!timeout); - /* - * SCTP has a hard time with timer starts. Because we process - * timer starts as side effects, it can be hard to tell if we - * have already started a timer or not, which leads to BUG - * halts when we call add_timer. So here, instead of just starting - * a timer, if the timer is already started, and just mod - * the timer with the shorter of the two expiration times - */ - if (!timer_pending(timer)) + if (!timer_reduce(timer, jiffies + timeout)) sctp_association_hold(asoc); - timer_reduce(timer, jiffies + timeout); break; case SCTP_CMD_TIMER_RESTART: From 98f0a1422e285f6132a73932ebd4fe5c6f513261 Mon Sep 17 00:00:00 2001 From: Linmao Li Date: Wed, 19 Aug 2026 19:42:41 +0800 Subject: [PATCH 0162/1198] scsi: fnic: Initialize the NVMe local port info before registering nvfnic_add_lport() declares struct nvme_fc_port_info on the stack and fills in four of its five members, leaving dev_loss_tmo holding whatever the stack happened to contain before the call. The structure is then handed to nvme_fc_register_localport(). nvfnic_add_tport(), which registers the remote port a few lines further down, memsets its own struct nvme_fc_port_info first, so only the local port path passes uninitialized data across the transport interface. The NVMe/FC transport documents dev_loss_tmo as "Used only on a remoteport" and does not read it in nvme_fc_register_localport(), so there is no behavioural change today. Initialize the structure anyway: the driver must not depend on which members the transport happens to consume, and any member added to struct nvme_fc_port_info later would silently start out as stack garbage. Signed-off-by: Linmao Li Tested-by: Karan Tilak Kumar Reviewed-by: Karan Tilak Kumar Link: https://patch.msgid.link/20260819114242.3598034-2-lilinmao@kylinos.cn Signed-off-by: Martin K. Petersen (Oracle) --- drivers/scsi/fnic/fnic_nvme.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/fnic/fnic_nvme.c b/drivers/scsi/fnic/fnic_nvme.c index b237948dcafd..00d9d5d439a3 100644 --- a/drivers/scsi/fnic/fnic_nvme.c +++ b/drivers/scsi/fnic/fnic_nvme.c @@ -2216,7 +2216,7 @@ int nvfnic_add_tport(struct fnic *fnic, struct fnic_tport_s *tport, int nvfnic_add_lport(struct fnic *fnic) { - struct nvme_fc_port_info pinfo; + struct nvme_fc_port_info pinfo = {}; struct fnic_iport_s *iport = &fnic->iport; int ret = 0; From 3f92a64545165bdbb36dee8fa35626b295463313 Mon Sep 17 00:00:00 2001 From: Runyu Xiao Date: Mon, 24 Aug 2026 19:36:18 +0800 Subject: [PATCH 0163/1198] scsi: pm8001: Use rollback index when freeing MSI-X vectors pm8001_request_msix() unwinds previously registered handlers with free_irq() when request_irq() fails. The rollback loop uses the failing index i for every iteration instead of the already registered vector index j. That passes the wrong IRQ/dev_id pair to free_irq() and leaves the earlier handlers installed. Use j for both pci_irq_vector() and the matching irq_vector entry in the rollback loop. Fixes: a76037ff3479 ("scsi: pm8001: switch to pci_irq_alloc_vectors") Cc: stable@vger.kernel.org Assisted-by: Codex:GPT-5 Signed-off-by: Runyu Xiao Acked-by: Jack Wang Link: https://patch.msgid.link/20260824113618.2239100-1-runyu.xiao@seu.edu.cn Signed-off-by: Martin K. Petersen (Oracle) --- drivers/scsi/pm8001/pm8001_init.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c index e93ea76b565e..54b35893261a 100644 --- a/drivers/scsi/pm8001/pm8001_init.c +++ b/drivers/scsi/pm8001/pm8001_init.c @@ -1029,8 +1029,8 @@ static u32 pm8001_request_msix(struct pm8001_hba_info *pm8001_ha) &(pm8001_ha->irq_vector[i])); if (rc) { for (j = 0; j < i; j++) { - free_irq(pci_irq_vector(pm8001_ha->pdev, i), - &(pm8001_ha->irq_vector[i])); + free_irq(pci_irq_vector(pm8001_ha->pdev, j), + &pm8001_ha->irq_vector[j]); } pci_free_irq_vectors(pm8001_ha->pdev); break; From 9a0716348dafe9c6d3529991a50b96c6d18abb51 Mon Sep 17 00:00:00 2001 From: Muhammad Falak R Wani Date: Thu, 27 Aug 2026 16:50:37 +0530 Subject: [PATCH 0164/1198] scsi: ibmvfc: Fix kernel-doc name for ibmvfc_scsi_relogin() Commit e0fca728a89f ("scsi: ibmvfc: delete NVMe/FC targets as well as SCSI") renamed ibmvfc_relogin() to ibmvfc_scsi_relogin() but left the kernel-doc comment referring to the old name, so a W=1 build warns: drivers/scsi/ibmvscsi/ibmvfc-core.c:1901: warning: expecting prototype for ibmvfc_relogin(). Prototype was for ibmvfc_scsi_relogin() instead Update the kernel-doc comment to use the current function name. Fixes: e0fca728a89f ("scsi: ibmvfc: delete NVMe/FC targets as well as SCSI") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202608271026.iMLmrwz4-lkp@intel.com/ Signed-off-by: Muhammad Falak R Wani Reviewed-by: Dave Marquardt Acked-by: Tyrel Datwyler Link: https://patch.msgid.link/dd866cf2321381694af027fbd726bcbd63ac3751.1787828961.git.falakreyaz@gmail.com Signed-off-by: Martin K. Petersen (Oracle) --- drivers/scsi/ibmvscsi/ibmvfc-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/ibmvscsi/ibmvfc-core.c b/drivers/scsi/ibmvscsi/ibmvfc-core.c index b3bc3ce872d6..78c59af769b5 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc-core.c +++ b/drivers/scsi/ibmvscsi/ibmvfc-core.c @@ -1894,7 +1894,7 @@ static void ibmvfc_log_error(struct ibmvfc_event *evt) } /** - * ibmvfc_relogin - Log back into the specified device + * ibmvfc_scsi_relogin - Log back into the specified device * @sdev: scsi device struct * **/ From 9a69cc5f192f356c1c7b4fa2821da4a8cf684829 Mon Sep 17 00:00:00 2001 From: Muhammad Falak R Wani Date: Thu, 27 Aug 2026 16:50:38 +0530 Subject: [PATCH 0165/1198] scsi: ibmvfc: Document protocol parameter of ibmvfc_alloc_target() Commit 249313b3f7b5 ("scsi: ibmvfc: allocate targets based on protocol") added a protocol parameter to ibmvfc_alloc_target() but did not describe it in the function's kernel-doc comment, so a W=1 build warns: drivers/scsi/ibmvscsi/ibmvfc-core.c:4996: warning: Function parameter or struct member 'protocol' not described in 'ibmvfc_alloc_target' Add the missing parameter description. Fixes: 249313b3f7b5 ("scsi: ibmvfc: allocate targets based on protocol") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202608270829.lHI1FAdO-lkp@intel.com/ Signed-off-by: Muhammad Falak R Wani Reviewed-by: Dave Marquardt Acked-by: Tyrel Datwyler Link: https://patch.msgid.link/b073968ae020b6ae0240e91341a92f428587ebd9.1787828961.git.falakreyaz@gmail.com Signed-off-by: Martin K. Petersen (Oracle) --- drivers/scsi/ibmvscsi/ibmvfc-core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/ibmvscsi/ibmvfc-core.c b/drivers/scsi/ibmvscsi/ibmvfc-core.c index 78c59af769b5..3534ac45e9b8 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc-core.c +++ b/drivers/scsi/ibmvscsi/ibmvfc-core.c @@ -4987,6 +4987,7 @@ static void ibmvfc_tgt_query_target(struct ibmvfc_target *tgt) * ibmvfc_alloc_target - Allocate and initialize an ibmvfc target * @vhost: ibmvfc host struct * @target: Holds SCSI ID to allocate target forand the WWPN + * @protocol: protocol of the target to allocate * * Returns: * 0 on success / other on failure From a3756f53baf1830c65149cfcb81cb96360976cf3 Mon Sep 17 00:00:00 2001 From: Nitin Rawat Date: Tue, 25 Aug 2026 20:22:02 +0530 Subject: [PATCH 0166/1198] scsi: ufs: ufs-qcom: Restore HS/LS link startup mode for Qualcomm UFS controller v6.2+ The link startup mode (HS LSS - high-speed link startup, or LS LSS - low-speed link startup) is decided in the boot stage based on the bootconfig GPIO. This selection is carried forward through the secondary stage bootloaders and finally to HLOS via the spare configuration register (REG_UFS_DEBUG_SPARE_CFG). On Qualcomm UFS controller v6.2 and later, bit 31 in the spare configuration register indicates the high-speed link startup mode selection, as per the Hardware Programming Guide (HPG). The spare register value is read during host driver initialization but gets cleared after UFS reset. Preserve the spare register value during initialization and restore it during link startup to maintain the bootloader-configured link startup mode. Signed-off-by: Nitin Rawat Tested-by: Mukesh Ojha Link: https://patch.msgid.link/20260825145203.265579-2-nitin.rawat@oss.qualcomm.com Signed-off-by: Martin K. Petersen (Oracle) --- drivers/ufs/host/ufs-qcom.c | 15 ++++++++++++--- drivers/ufs/host/ufs-qcom.h | 1 + 2 files changed, 13 insertions(+), 3 deletions(-) diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c index 62396212a0a7..8893ea7e4d84 100644 --- a/drivers/ufs/host/ufs-qcom.c +++ b/drivers/ufs/host/ufs-qcom.c @@ -715,6 +715,7 @@ static void ufs_qcom_link_startup_post_change(struct ufs_hba *hba) static int ufs_qcom_link_startup_notify(struct ufs_hba *hba, enum ufs_notify_change_status status) { + struct ufs_qcom_host *host = ufshcd_get_variant(hba); int err = 0; switch (status) { @@ -737,6 +738,14 @@ static int ufs_qcom_link_startup_notify(struct ufs_hba *hba, */ err = ufshcd_disable_host_tx_lcc(hba); + /* + * Restore HS/LS link startup mode set by bootloader + * after UFS reset clears REG_UFS_DEBUG_SPARE_CFG. + */ + if (host->hw_ver.major > 0x6 || + (host->hw_ver.major == 0x6 && host->hw_ver.minor >= 0x2)) + ufshcd_writel(hba, host->boot_spare_cfg, + REG_UFS_DEBUG_SPARE_CFG); break; case POST_CHANGE: ufs_qcom_link_startup_post_change(hba); @@ -1325,7 +1334,7 @@ static void ufs_qcom_advertise_quirks(struct ufs_hba *hba) static void ufs_qcom_set_phy_gear(struct ufs_qcom_host *host) { struct ufs_host_params *host_params = &host->host_params; - u32 val, dev_major; + u32 dev_major; /* * Default to powering up the PHY to the max gear possible, which is @@ -1344,8 +1353,8 @@ static void ufs_qcom_set_phy_gear(struct ufs_qcom_host *host) */ host->phy_gear = UFS_HS_G2; } else if (host->hw_ver.major >= 0x5) { - val = ufshcd_readl(host->hba, REG_UFS_DEBUG_SPARE_CFG); - dev_major = FIELD_GET(UFS_DEV_VER_MAJOR_MASK, val); + host->boot_spare_cfg = ufshcd_readl(host->hba, REG_UFS_DEBUG_SPARE_CFG); + dev_major = FIELD_GET(UFS_DEV_VER_MAJOR_MASK, host->boot_spare_cfg); /* * Since the UFS device version is populated, let's remove the diff --git a/drivers/ufs/host/ufs-qcom.h b/drivers/ufs/host/ufs-qcom.h index e20b3ca50577..a5ad5ce44a19 100644 --- a/drivers/ufs/host/ufs-qcom.h +++ b/drivers/ufs/host/ufs-qcom.h @@ -361,6 +361,7 @@ struct ufs_qcom_host { bool esi_enabled; u32 saved_tx_eq_g1_setting; + u32 boot_spare_cfg; }; struct ufs_qcom_drvdata { From b2ededcb271b37510366cbf6853be193d681ba5c Mon Sep 17 00:00:00 2001 From: Nitin Rawat Date: Tue, 25 Aug 2026 20:22:03 +0530 Subject: [PATCH 0167/1198] scsi: ufs: ufs-qcom: Fix sequential read variance The current devfreq downdifferential threshold of 5% causes overly aggressive frequency downscaling, leading to performance degradation sometimes during sequential read workloads. Update the UFS devfreq downdifferential threshold to 65. This widens the hysteresis window and prevents overly aggressive downscaling, ensuring that frequency is maintained for loads above 5% and scaling down occurs only when utilization falls below this level, while scale-up still triggers above the 70% threshold. Reviewed-by: Konrad Dybcio Signed-off-by: Nitin Rawat Link: https://patch.msgid.link/20260825145203.265579-3-nitin.rawat@oss.qualcomm.com Signed-off-by: Martin K. Petersen (Oracle) --- drivers/ufs/host/ufs-qcom.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c index 8893ea7e4d84..b31c04b5461e 100644 --- a/drivers/ufs/host/ufs-qcom.c +++ b/drivers/ufs/host/ufs-qcom.c @@ -2291,7 +2291,7 @@ static void ufs_qcom_config_scaling_param(struct ufs_hba *hba, p->polling_ms = 60; p->timer = DEVFREQ_TIMER_DELAYED; d->upthreshold = 70; - d->downdifferential = 5; + d->downdifferential = 65; hba->clk_scaling.suspend_on_no_request = true; } From dba9e2181ca5e875f98b8b9b4535cdaab87dcb0d Mon Sep 17 00:00:00 2001 From: "Milan P. Gandhi" Date: Wed, 12 Aug 2026 16:03:43 +0530 Subject: [PATCH 0168/1198] scsi: mpi3mr: Fix NULL pointer dereference in mpi3mr_sas_port_add() sas_port_alloc_num() can return NULL on memory allocation failure. The return value is passed directly to sas_port_add() without a NULL check, which causes a NULL pointer dereference. Additionally, if sas_port_add() fails, the allocated port is not freed before jumping to out_fail, leaking the sas_port structure. Call sas_port_free() to properly release it. Fixes: e22bae30667a ("scsi: mpi3mr: Add expander devices to STL") Signed-off-by: Milan P. Gandhi Reviewed-by: Laurence Oberman Link: https://patch.msgid.link/20260812103344.174247-2-mgandhi@redhat.com Signed-off-by: Martin K. Petersen (Oracle) --- drivers/scsi/mpi3mr/mpi3mr_transport.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/scsi/mpi3mr/mpi3mr_transport.c b/drivers/scsi/mpi3mr/mpi3mr_transport.c index 240f67a8e2e3..ea2c04384a0e 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_transport.c +++ b/drivers/scsi/mpi3mr/mpi3mr_transport.c @@ -1428,9 +1428,15 @@ static struct mpi3mr_sas_port *mpi3mr_sas_port_add(struct mpi3mr_ioc *mrioc, } port = sas_port_alloc_num(mr_sas_node->parent_dev); + if (!port) { + ioc_err(mrioc, "failure at %s:%d/%s()!\n", + __FILE__, __LINE__, __func__); + goto out_fail; + } if ((sas_port_add(port))) { ioc_err(mrioc, "failure at %s:%d/%s()!\n", __FILE__, __LINE__, __func__); + sas_port_free(port); goto out_fail; } From 419d129f970aaa6567dbac366b0c93784bf9ec97 Mon Sep 17 00:00:00 2001 From: "Milan P. Gandhi" Date: Wed, 12 Aug 2026 16:03:44 +0530 Subject: [PATCH 0169/1198] scsi: mpi3mr: Fix target device refcount leak in mpi3mr_sas_port_add() mpi3mr_get_tgtdev_by_addr() increments the target device kref when it returns a device. If a subsequent error triggers a goto out_fail after the tgtdev reference is acquired, the reference is never released because the out_fail path does not call mpi3mr_tgtdev_put(). This prevents the target device structure from ever being freed. Add a tgtdev put in the out_fail path, guarded by a NULL check since tgtdev is only acquired for SAS_END_DEVICE types and the same cleanup path is shared by earlier error cases where tgtdev is still NULL. Fixes: e22bae30667a ("scsi: mpi3mr: Add expander devices to STL") Signed-off-by: Milan P. Gandhi Reviewed-by: Laurence Oberman Link: https://patch.msgid.link/20260812103344.174247-3-mgandhi@redhat.com Signed-off-by: Martin K. Petersen (Oracle) --- drivers/scsi/mpi3mr/mpi3mr_transport.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/scsi/mpi3mr/mpi3mr_transport.c b/drivers/scsi/mpi3mr/mpi3mr_transport.c index ea2c04384a0e..232af978d737 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_transport.c +++ b/drivers/scsi/mpi3mr/mpi3mr_transport.c @@ -1507,6 +1507,8 @@ static struct mpi3mr_sas_port *mpi3mr_sas_port_add(struct mpi3mr_ioc *mrioc, list_for_each_entry_safe(mr_sas_phy, next, &mr_sas_port->phy_list, port_siblings) list_del(&mr_sas_phy->port_siblings); + if (tgtdev) + mpi3mr_tgtdev_put(tgtdev); kfree(mr_sas_port); return NULL; } From 11300f8ddee301dca9914561f24bea4168de076d Mon Sep 17 00:00:00 2001 From: Xu Rao Date: Mon, 6 Jul 2026 16:44:43 +0800 Subject: [PATCH 0170/1198] scsi: sg: Report request-table problems when any status is set SG_GET_REQUEST_TABLE reports per-request diagnostic state through sg_req_info::problem. The field is meant to indicate whether there is an error to report for a completed request. sg_fill_request_table() currently combines masked_status, host_status and driver_status with bitwise AND. This only reports a problem when all three status fields are non-zero at the same time. A normal target check condition, for example, has masked_status set while host_status and driver_status may both be zero, so the request is incorrectly reported as clean. Use the same condition as sg_new_read(), which sets SG_INFO_CHECK when any of the three status fields is non-zero. Signed-off-by: Xu Rao Reviewed-by: Bart Van Assche Cc: stable@vger.kernel.org Link: https://patch.msgid.link/26BF67F369E2123E+20260706084443.805598-1-raoxu@uniontech.com Signed-off-by: Martin K. Petersen (Oracle) --- drivers/scsi/sg.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 74cd4e8a61c2..5408f002e6c0 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -863,10 +863,9 @@ sg_fill_request_table(Sg_fd *sfp, sg_req_info_t *rinfo) if (val >= SG_MAX_QUEUE) break; rinfo[val].req_state = srp->done + 1; - rinfo[val].problem = - srp->header.masked_status & - srp->header.host_status & - srp->header.driver_status; + rinfo[val].problem = srp->header.masked_status || + srp->header.host_status || + srp->header.driver_status; if (srp->done) rinfo[val].duration = srp->header.duration; From ef675ea168453a9b3e635b8ac543f92938bdd03b Mon Sep 17 00:00:00 2001 From: sangram kumar yerra Date: Tue, 18 Aug 2026 16:58:29 +0530 Subject: [PATCH 0171/1198] scsi: ufs: ufs-pci: Add support for Intel UFS 4.0 HS-Gear5 Reliable HS-Gear5 operation on Intel UFS 4.0 controllers requires configuring PA_INITIAL_ADAPT before changing the power mode. Without this setting, the link fails to train reliably at Gear5. Add a pwr_change_notify() hook to configure the adaptation mode before the power mode transition. Enable this only for UFS 4.0 and later controllers by checking hba->ufs_version. Wire the hook into the existing Meteor Lake family variant operations table (ufs_intel_mtl_hba_vops) instead of introducing a separate table, since the Intel UFS 4.0 PCI variant (PCI ID 8086:D335) already uses this vops table and the hook is internally gated on UFS version >= 4.0. Use PA_INITIAL_ADAPT when the negotiated TX power mode is FAST_MODE or FASTAUTO_MODE. Otherwise, reset the adaptation mode to PA_NO_ADAPT, which is the default setting. Fixes: 096cd6b7adf2 ("scsi: ufs: ufs-pci: Add support for Intel Nova Lake") Signed-off-by: sangram kumar yerra Reviewed-by: Adrian Hunter Reviewed-by: Bart Van Assche Link: https://patch.msgid.link/20260818112830.453402-2-sangram.k.y@intel.com Signed-off-by: Martin K. Petersen (Oracle) --- drivers/ufs/host/ufshcd-pci.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/drivers/ufs/host/ufshcd-pci.c b/drivers/ufs/host/ufshcd-pci.c index f2433879b0eb..93bfafc25018 100644 --- a/drivers/ufs/host/ufshcd-pci.c +++ b/drivers/ufs/host/ufshcd-pci.c @@ -181,6 +181,25 @@ static int ufs_intel_lkf_pwr_change_notify(struct ufs_hba *hba, return err; } +static int ufs_intel_nvl_pwr_change_notify(struct ufs_hba *hba, + enum ufs_notify_change_status stage, + struct ufs_pa_layer_attr *dev_req_params) +{ + int adapt_val; + + if (stage != PRE_CHANGE || hba->ufs_version < ufshci_version(4, 0)) + return 0; + + if (dev_req_params->pwr_tx == FAST_MODE || dev_req_params->pwr_tx == FASTAUTO_MODE) + adapt_val = PA_INITIAL_ADAPT; + else + adapt_val = PA_NO_ADAPT; + + ufshcd_dme_configure_adapt(hba, dev_req_params->gear_tx, adapt_val); + + return 0; +} + static int ufs_intel_lkf_apply_dev_quirks(struct ufs_hba *hba) { u32 granularity, peer_granularity; @@ -527,6 +546,7 @@ static struct ufs_hba_variant_ops ufs_intel_mtl_hba_vops = { .exit = ufs_intel_common_exit, .hce_enable_notify = ufs_intel_hce_enable_notify, .link_startup_notify = ufs_intel_link_startup_notify, + .pwr_change_notify = ufs_intel_nvl_pwr_change_notify, .resume = ufs_intel_resume, .device_reset = ufs_intel_device_reset, }; From c46cc9cee39bd6f395ab9ac98b1794705df13d7c Mon Sep 17 00:00:00 2001 From: sangram kumar yerra Date: Tue, 18 Aug 2026 16:58:30 +0530 Subject: [PATCH 0172/1198] scsi: ufs: ufs-pci: Add MCQ support for Intel UFS 4.0 controllers The Intel UFS 4.0 PCI variant (PCI ID 8086:D335) advertises MCQ support in its capability register. However, ufshcd_alloc_mcq() also requires an .op_runtime_config hook to locate the per-queue operation and runtime (OPR) register blocks, which was not provided by this variant operations table. As a result, MCQ initialization fails and ufshcd_add_scsi_host() prints "MCQ mode is disabled, err=%d\n" before falling back to legacy single-doorbell (SDB) mode. Add ufs_intel_mcq_config_resource() to initialize the MCQ configuration base and add ufs_intel_op_runtime_config() to set up the OPR register offsets and stride. Wire both hooks into the variant operations table so MCQ is enabled when supported by the hardware. Fixes: 096cd6b7adf2 ("scsi: ufs: ufs-pci: Add support for Intel Nova Lake") Signed-off-by: sangram kumar yerra Reviewed-by: Adrian Hunter Reviewed-by: Bart Van Assche Link: https://patch.msgid.link/20260818112830.453402-3-sangram.k.y@intel.com Signed-off-by: Martin K. Petersen (Oracle) --- drivers/ufs/host/ufshcd-pci.c | 39 +++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) diff --git a/drivers/ufs/host/ufshcd-pci.c b/drivers/ufs/host/ufshcd-pci.c index 93bfafc25018..21bb11c724be 100644 --- a/drivers/ufs/host/ufshcd-pci.c +++ b/drivers/ufs/host/ufshcd-pci.c @@ -460,6 +460,43 @@ static int ufs_intel_mtl_init(struct ufs_hba *hba) return ufs_intel_common_init(hba); } +static int ufs_intel_mcq_config_resource(struct ufs_hba *hba) +{ + hba->mcq_base = hba->mmio_base + ufshcd_mcq_queue_cfg_addr(hba); + + return 0; +} + +/* + * This Intel UFS4.0 controller maps MCQ doorbell and interrupt-status + * registers into the same PCI BAR as the legacy HCI space, at this + * fixed offset/stride. + */ +#define UFS_INTEL_SQDAO0 0x2800 +#define UFS_INTEL_SQISAO0 0x2814 +#define UFS_INTEL_CQDAO0 0x281C +#define UFS_INTEL_CQISAO0 0x2824 +#define UFS_INTEL_MCQ_STRIDE 0x30 + +static int ufs_intel_op_runtime_config(struct ufs_hba *hba) +{ + struct ufshcd_mcq_opr_info_t *opr; + int i; + + hba->mcq_opr[OPR_SQD].offset = UFS_INTEL_SQDAO0; + hba->mcq_opr[OPR_SQIS].offset = UFS_INTEL_SQISAO0; + hba->mcq_opr[OPR_CQD].offset = UFS_INTEL_CQDAO0; + hba->mcq_opr[OPR_CQIS].offset = UFS_INTEL_CQISAO0; + + for (i = 0; i < OPR_MAX; i++) { + opr = &hba->mcq_opr[i]; + opr->stride = UFS_INTEL_MCQ_STRIDE; + opr->base = hba->mmio_base + opr->offset; + } + + return 0; +} + static int ufs_qemu_get_hba_mac(struct ufs_hba *hba) { return MAX_SUPP_MAC; @@ -547,6 +584,8 @@ static struct ufs_hba_variant_ops ufs_intel_mtl_hba_vops = { .hce_enable_notify = ufs_intel_hce_enable_notify, .link_startup_notify = ufs_intel_link_startup_notify, .pwr_change_notify = ufs_intel_nvl_pwr_change_notify, + .mcq_config_resource = ufs_intel_mcq_config_resource, + .op_runtime_config = ufs_intel_op_runtime_config, .resume = ufs_intel_resume, .device_reset = ufs_intel_device_reset, }; From d5869dae5080e976d4b03cc33eb7ceb527f242bf Mon Sep 17 00:00:00 2001 From: Maurizio Lombardi Date: Fri, 17 Jul 2026 16:38:28 +0200 Subject: [PATCH 0173/1198] scsi: target: iscsi: Fix hang for aborted WRITE_PENDING commands When a LUN_RESET aborts a WRITE command that is in the TRANSPORT_WRITE_PENDING state, the target core sets CMD_T_ABORTED and waits for the frontend to finish processing. If the initiator subsequently sends the remaining dataout PDUs, __iscsit_check_dataout_hdr() catches the payload, stops the dataout timer if the sequence is final and finally dumps the data. However, the iSCSI target doesn't trigger the completion process for these aborted commands. Because of this, the abort path hangs indefinitely in target_put_cmd_and_wait(), leading to a deadlocked target worker thread. Fix this by explicitly calling target_complete_cmd() when the final dataout PDU is received for an aborted WRITE command. target_complete_cmd() detects the CMD_T_ABORTED flag and cleanly routes the command into target_abort_work, allowing the abort completion to successfully unblock. Signed-off-by: Maurizio Lombardi Reviewed-by: Laurence Oberman Link: https://patch.msgid.link/20260717143828.76291-2-mlombard@redhat.com Signed-off-by: Martin K. Petersen (Oracle) --- drivers/target/iscsi/iscsi_target.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 62ada3a52210..124ff269b8e7 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -1533,8 +1533,10 @@ __iscsit_check_dataout_hdr(struct iscsit_conn *conn, void *buf, */ if (se_cmd->transport_state & CMD_T_ABORTED) { if (hdr->flags & ISCSI_FLAG_CMD_FINAL && - --cmd->outstanding_r2ts < 1) + --cmd->outstanding_r2ts < 1) { iscsit_stop_dataout_timer(cmd); + target_complete_cmd(se_cmd, SAM_STAT_TASK_ABORTED); + } return iscsit_dump_data_payload(conn, payload_length, 1); } From 28d75dd3eb60812b3a87cbdf0d52c42f51b28a78 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Fri, 28 Aug 2026 10:05:34 -0700 Subject: [PATCH 0174/1198] selftests/bpf: Bound the offset accumulator in __tld_fetch_key() The LLVM commit c7f4a76da024 [1] "[InstCombine] fold ((x - 1) | (2^k - 1)) + 1 to (x + (2^k - 1)) & -(2^k)" caused test_task_local_data.bpf.o to fail verification: The sequence of 8193 jumps is too complex. processed 188770 insns (limit 1000000) max_states_per_insn 34 total_states 8238 peak_states 12330 mark_read 0 TLD_ROUND_UP(x, 8) expands to ((((x) - 1) | 7) + 1), exactly the pattern that [1] rewrites, so the accumulation in __tld_fetch_key() off += TLD_ROUND_UP(metadata[i].size, 8); is now compiled as (x + 7) & -8 instead of ((x - 1) | 7) + 1. Both are correct, but they leave the verifier in very different states. Note that 'off' is marked as precise. Without [1], "size - 1" wraps at zero (size is a __u16), so the verifier loses all bounds on the increment: 211: (69) r1 = *(u16 *)(r1 +62) ; R1=scalar(...,umax32=0xffff,var_off=(0x0; 0xffff)) 212: (04) w1 += -1 ; R1=scalar(smin=0,smax=umax=0xffffffff,smin32=-1,smax32=0xfffe,var_off=(0x0; 0xffffffff)) 213: (44) w1 |= 7 ; R1=scalar(smin=umin=umin32=7,smax=umax=0xffffffff,var_off=(0x7; 0xfffffff8)) 214: (0c) w6 += w1 ; R6=scalar(smin=umin=umin32=7,smax=umax=0xffffffff,var_off=(0x7; 0xfffffff8)) 215: (04) w6 += 1 ; R6=scalar(smin=0,smax=umax=umax32=0xfffffff8,var_off=(0x0; 0xfffffff8)) Note that 'w6' will be used in the next iteration. In the next iteration after insn 215, the R6 range will be the same as previous iteration. The iterator loop converges at depth 2. With [1] the increment stays precisely bounded at [0, 0x10006]: 211: (69) r9 = *(u16 *)(r1 +62) ; R9=scalar(...,umax32=0xffff,var_off=(0x0; 0xffff)) 212: (04) w9 += 7 ; R9=scalar(...,umax32=0x10006,var_off=(0x0; 0x1ffff)) 213: (54) w9 &= 131064 ; R9=scalar(...,umax32=0x10006,var_off=(0x0; 0x1fff8)) 214: (0c) w9 += w6 ; R9=scalar(...,umax32=0x10006,var_off=(0x0; 0x1fff8)) 215: (bf) r1 = r10 216: (07) r1 += -8 217: (85) call bpf_iter_num_next 218: (bc) w6 = w9 In the next iteration, we will have 211: (69) r9 = *(u16 *)(r1 +62) ; R9=scalar(...,umax32=0xffff,var_off=(0x0; 0xffff)) 212: (04) w9 += 7 ; R9=scalar(...,umax32=0x10006,var_off=(0x0; 0x1ffff)) 213: (54) w9 &= 131064 ; R9=scalar(...,umax32=0x10006,var_off=(0x0; 0x1fff8)) 214: (0c) w9 += w6 ; R9=scalar(...,umax32=0x2000c,var_off=(0x0; 0x3fff8)) ... so 'off' umax grows by 0x10006 on every iteration and the loop-head state never repeats: 218: (bc) w6 = w9 ; R6=scalar(...,umax32=0x10006,var_off=(0x0; 0x1fff8)) 218: (bc) w6 = w9 ; R6=scalar(...,umax32=0x2000c,var_off=(0x0; 0x3fff8)) 218: (bc) w6 = w9 ; R6=scalar(...,umax32=0x30012,var_off=(0x0; 0x3fff8)) ... 218: (bc) w6 = w9 ; R6=scalar(...,umax32=0xff95fd6,var_off=(0x0; 0xffffff8)) That last one is iterator depth 4090. Saturating umax would take ~65531 iterations; the verifier gives up long before that. Note the loop does not diverge from the start. widen_imprecise_scalars() blows 'off' up to an unbounded scalar while it is still imprecise, and that alone converges the first three passes through the loop at depth 4. Once mark_chain_precision() reaches the loop body, maybe_widen_reg() starts skipping the register, and no widening ever happens again. In the failing log widening fires exactly 6 times out of 4098 arrivals at the iter_next() checkpoint, all of them before the umax starts accumulating. With [1] and this fix, here is one full trip through the loop body, entered with 'off' (R6) already clamped by the previous iteration: 208: frame1: R6=scalar(...,umax32=4088,var_off=(0x0; 0xff8)) 208: (67) r7 <<= 6 ; R7=scalar(...,umax32=3968,var_off=(0x0; 0xfc0)) 209: (bf) r1 = r9 ; R1=mem(id=54,sz=4036,imm=4) 210: (0f) r1 += r7 211: (69) r1 = *(u16 *)(r1 +62) ; R1=scalar(...,umax32=0xffff,var_off=(0x0; 0xffff)) 212: (04) w1 += 7 ; R1=scalar(...,umax32=0x10006,var_off=(0x0; 0x1ffff)) 213: (54) w1 &= 131064 ; R1=scalar(...,umax32=0x10006,var_off=(0x0; 0x1fff8)) 214: (0c) w1 += w6 ; R1=scalar(...,umax32=0x10ffe,var_off=(0x0; 0x1fff8)) R6=scalar(...,umax32=4088,var_off=(0x0; 0xff8)) 215: (bc) w6 = w1 ; R6=scalar(...,umax32=0x10ffe,var_off=(0x0; 0x1fff8)) 216: (26) if w1 > 0xff8 goto pc+1 ; R6=scalar(...,umax32=4088,var_off=(0x0; 0xff8)) 217: (05) goto pc-27 This makes the loop body a fixpoint. 'off' (w6) enters at 208 as [0, 4088] with var_off=(0x0; 0xff8); the increment computed at 212/213 is [0, 0x10006], so 214/215 leave it at [0, 0x10ffe]; then 216 truncates it straight back to [0, 4088]/(0x0; 0xff8), and only then is the back edge at 217 taken. Convergence no longer depends on the widening window above. Verification converges at iterator depth 3. [1] https://github.com/llvm/llvm-project/pull/216436 Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20260828170534.1011183-1-yonghong.song@linux.dev Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/progs/task_local_data.bpf.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/task_local_data.bpf.h b/tools/testing/selftests/bpf/progs/task_local_data.bpf.h index 0df8a12fd61e..a31a399870be 100644 --- a/tools/testing/selftests/bpf/progs/task_local_data.bpf.h +++ b/tools/testing/selftests/bpf/progs/task_local_data.bpf.h @@ -61,6 +61,7 @@ #define TLD_ROUND_UP(x, y) ((((x) - 1) | TLD_ROUND_MASK(x, y)) + 1) #define TLD_MAX_DATA_CNT (__PAGE_SIZE / sizeof(struct tld_metadata) - 1) +#define TLD_DATA_SIZE (__PAGE_SIZE - sizeof(__u64)) #ifndef TLD_NAME_LEN #define TLD_NAME_LEN 62 @@ -189,6 +190,8 @@ static int __tld_fetch_key(struct tld_object *tld_obj, const char *name, int i_s return start + off; off += TLD_ROUND_UP(metadata[i].size, 8); + if (off > TLD_DATA_SIZE) + break; } return -cnt; From 41a52ba4a5fe25b2cca431fe76fb5f3d8ad35139 Mon Sep 17 00:00:00 2001 From: Zhan Xusheng Date: Fri, 28 Aug 2026 12:58:43 +0800 Subject: [PATCH 0175/1198] ntfs: read WOF chunks outside the decompression lock WOF decompression uses four module-global workspaces, one per compression format, each with a static mutex. ntfs_read_wof_compressed_block() takes that mutex once and holds it across the whole chunk loop, so both block reads run inside it: mutex_lock(ws->lock); for each chunk { parse_wof_chunk_table(..., ws->input, ...); /* reads disk */ ntfs_read_wof_chunk(..., ws->input, ...); /* reads disk */ decompress into ws->output; } mutex_unlock(ws->lock); Readers of system-compressed files then serialise system-wide on the disk waits, not just on the decompressor scratch the lock exists for. One reader sleeping in submit_bio_wait() blocks all the rest. The waits dominate. Reading an 8 MiB xpress4k file (2048 chunks at a 48% compressed ratio, so 2048 acquisitions and 4096 block reads) and timing ws->lock against the part of it spent in ntfs_bdev_read(): backing store held of that in I/O held after virtio, host page cache 348 ms 321 ms (92%) 24.6 ms virtio, throttled 100 MB/s 978 ms 948 ms (96%) 36.6 ms The page-cache row is a lower bound, having no seek cost at all, and the share still grows with slower storage because only the wait scales while decompression stays near 26 ms. The reads are inside the lock only because they land in ws->input, a buffer shared through the workspace. Nothing else requires it: parse_wof_chunk_table() and ntfs_read_wof_chunk() already take the buffer as a parameter and both set *chunk_mem to a pointer inside it, so a caller-owned buffer works unchanged. Allocate that buffer per call, do both reads without the lock, and take the lock only around decompression, which is the step needing ws->output and ws->scratch. squashfs is arranged this way already: its squashfs_decompress() is handed a bio that has been read, and locks only for the CPU work. Block reads are unchanged in number, they just no longer run under the lock, and hold time stops tracking device speed. This also unnests two per-inode locks from the global one, runlist->lock taken by both reads and base_ni->mrec_lock taken for a resident stream. A resident chunk needs no I/O at all, yet used to queue behind a reader blocked in submit_bio_wait() and then take mrec_lock inside the global mutex. The buffer is 4608 bytes for xpress4k and at most 33280 for lzx32k. This path already does GFP_NOFS allocations per call in ntfs_attr_iget(), and in ntfs_attr_get_search_ctx() for a resident stream, so one more does not change how it behaves under memory pressure. The workspace keeps output and scratch, 4 KiB to 32 KiB and 6224 bytes (xpress) or 10240 (lzx), and its "already allocated" test moves from ws->input to ws->output. The lock is now taken per chunk rather than per call, which differs only for a folio spanning several chunks: a few more uncontended mutex operations in exchange for not holding it across the reads between them. Verified under QEMU against an uncompressed copy of the same data, on an 8 MiB file and a 100000 byte one, the latter covering the tail chunk that is not a full comp_unit. Signed-off-by: Zhan Xusheng Signed-off-by: Namjae Jeon --- fs/ntfs/wof.c | 127 +++++++++++++++++++++++++++++++------------------- 1 file changed, 79 insertions(+), 48 deletions(-) diff --git a/fs/ntfs/wof.c b/fs/ntfs/wof.c index 8f84c2212eee..9847259e5b1a 100644 --- a/fs/ntfs/wof.c +++ b/fs/ntfs/wof.c @@ -39,8 +39,6 @@ struct ntfs_wof_workspace { struct mutex *lock; const struct ntfs_codec_ops *codec; u32 comp_unit; - void *input; - size_t input_size; void *output; void *scratch; }; @@ -97,30 +95,36 @@ static struct ntfs_wof_workspace *ntfs_wof_workspace(u8 block_size_bits) } } +/* + * Size of the buffer a chunk is read into. A chunk is read straight off the + * device, so the buffer has to hold @comp_unit bytes plus the leading partial + * sector. + */ +static size_t ntfs_wof_input_size(const struct ntfs_wof_workspace *ws) +{ + return round_up((size_t)ws->comp_unit + 511, 512); +} + static int ntfs_wof_workspace_prepare(struct ntfs_wof_workspace *ws) { - void *input, *output, *scratch; + void *output, *scratch; size_t scratch_size; - if (ws->input) + if (ws->output) return 0; - ws->input_size = round_up((size_t)ws->comp_unit + 511, 512); scratch_size = ws->codec->scratch_size(ws->comp_unit); if (!scratch_size) return -EINVAL; - input = kvmalloc(ws->input_size, GFP_NOFS); output = kvmalloc(ws->comp_unit, GFP_NOFS); scratch = kvzalloc(scratch_size, GFP_NOFS); - if (!input || !output || !scratch) { - kvfree(input); + if (!output || !scratch) { kvfree(output); kvfree(scratch); return -ENOMEM; } - ws->input = input; ws->output = output; ws->scratch = scratch; return 0; @@ -134,10 +138,8 @@ void ntfs_wof_free_workspaces(void) struct ntfs_wof_workspace *ws = ntfs_wof_workspaces[i]; mutex_lock(ws->lock); - kvfree(ws->input); kvfree(ws->output); kvfree(ws->scratch); - ws->input = NULL; ws->output = NULL; ws->scratch = NULL; mutex_unlock(ws->lock); @@ -602,6 +604,51 @@ static int ntfs_wof_try_direct(struct ntfs_wof_workspace *ws, chunk_end, src, src_len, dst_len); } +/* + * Decompress one chunk into @folio. Only this step needs the workspace, so it + * is the only step that takes the workspace lock. + */ +static int ntfs_wof_decompress_chunk(struct ntfs_wof_workspace *ws, + struct ntfs_volume *vol, + struct address_space *mapping, + struct folio *folio, loff_t folio_start, + loff_t folio_end, u64 chunk_file_offset, + char *chunk_mem, u32 chunk_size, + u32 decomp_size) +{ + loff_t chunk_end = chunk_file_offset + decomp_size; + loff_t copy_start, copy_end; + int err; + + mutex_lock(ws->lock); + err = ntfs_wof_workspace_prepare(ws); + if (err) + goto out_unlock; + + err = ntfs_wof_try_direct(ws, mapping, folio, chunk_file_offset, + chunk_end, chunk_mem, chunk_size, + decomp_size); + if (err != -EAGAIN) + goto out_unlock; + + err = ntfs_wof_decode(ws, chunk_mem, chunk_size, ws->output, + decomp_size); + if (err) { + ntfs_error(vol->sb, "Decompression failed: %d", err); + err = -EINVAL; + goto out_unlock; + } + + copy_start = max_t(loff_t, folio_start, chunk_file_offset); + copy_end = min_t(loff_t, folio_end, chunk_file_offset + decomp_size); + memcpy_to_folio(folio, copy_start - folio_start, + ws->output + copy_start - chunk_file_offset, + copy_end - copy_start); +out_unlock: + mutex_unlock(ws->lock); + return err; +} + int ntfs_read_wof_compressed_block(struct folio *folio) { struct address_space *mapping = folio->mapping; @@ -613,6 +660,8 @@ int ntfs_read_wof_compressed_block(struct folio *folio) loff_t folio_start = folio_pos(folio); loff_t folio_end = folio_next_pos(folio); char *chunk_mem; + void *input; + size_t input_size; u32 decomp_size; u64 chunk_count, chunk_idx, last_chunk, chunk_offset; int err = 0; @@ -652,10 +701,12 @@ int ntfs_read_wof_compressed_block(struct folio *folio) goto out_iput; } - mutex_lock(ws->lock); - err = ntfs_wof_workspace_prepare(ws); - if (err) - goto out_unlock_ws; + input_size = ntfs_wof_input_size(ws); + input = kvmalloc(input_size, GFP_NOFS); + if (!input) { + err = -ENOMEM; + goto out_iput; + } chunk_idx = div_u64(folio_start, ws->comp_unit); last_chunk = @@ -663,55 +714,35 @@ int ntfs_read_wof_compressed_block(struct folio *folio) chunk_count = DIV_ROUND_UP_ULL(i_size, ws->comp_unit); for (; chunk_idx <= last_chunk; chunk_idx++) { u32 chunk_size; - u64 chunk_file_offset; - loff_t chunk_end, copy_start, copy_end; decomp_size = chunk_idx + 1 == chunk_count ? i_size - chunk_idx * ws->comp_unit : ws->comp_unit; err = parse_wof_chunk_table(ni, wof_ni, chunk_idx, chunk_count, decomp_size, &chunk_offset, - &chunk_size, ws->input, - ws->input_size); + &chunk_size, input, input_size); if (err) - goto out_unlock_ws; + goto out_free_input; err = ntfs_read_wof_chunk(vol, wof_ni, chunk_offset, chunk_size, - ws->input, ws->input_size, - &chunk_mem); + input, input_size, &chunk_mem); if (err) - goto out_unlock_ws; + goto out_free_input; - chunk_file_offset = chunk_idx * ws->comp_unit; - chunk_end = chunk_file_offset + decomp_size; - err = ntfs_wof_try_direct(ws, mapping, folio, chunk_file_offset, - chunk_end, chunk_mem, chunk_size, - decomp_size); - if (!err) - continue; - if (err != -EAGAIN) - goto out_unlock_ws; - - err = ntfs_wof_decode(ws, chunk_mem, chunk_size, ws->output, - decomp_size); - if (err) { - ntfs_error(vol->sb, "Decompression failed: %d", err); - err = -EINVAL; - goto out_unlock_ws; - } - copy_start = max_t(loff_t, folio_start, chunk_file_offset); - copy_end = min_t(loff_t, folio_end, - chunk_file_offset + decomp_size); - memcpy_to_folio(folio, copy_start - folio_start, - ws->output + copy_start - chunk_file_offset, - copy_end - copy_start); + err = ntfs_wof_decompress_chunk(ws, vol, mapping, folio, + folio_start, folio_end, + chunk_idx * ws->comp_unit, + chunk_mem, chunk_size, + decomp_size); + if (err) + goto out_free_input; } if (folio_end > i_size) folio_zero_segment(folio, i_size - folio_start, folio_size(folio)); -out_unlock_ws: - mutex_unlock(ws->lock); +out_free_input: + kvfree(input); out_iput: iput(wof_inode); out: From 03c6ecc4b4b13a3901f207152451fdd2d82e40c4 Mon Sep 17 00:00:00 2001 From: Jacopo Labardi Date: Sun, 30 Aug 2026 02:15:36 +0200 Subject: [PATCH 0176/1198] ntfs: fix FITRIM range alignment ntfs_trim_fs() aligns the start of a free extent up to the device discard granularity, but derives the discard length by aligning the original extent length down. When the free extent start is not discard-aligned, adding that length to the aligned start can extend the discard past the free extent and into allocated clusters. For example, with 4 KiB clusters and 32 KiB discard granularity, the free extent [4 KiB, 36 KiB) becomes the discard range [32 KiB, 64 KiB), so 28 KiB beyond the free extent may be discarded. Align the absolute end of the free extent down and derive the length from the two aligned endpoints. Skip extents that contain no full discard unit. Reproduced with a 4 KiB-cluster NTFS filesystem on scsi_debug configured for 32 KiB discard granularity and read-zero-after-trim. Before this change, FITRIM zeroed seven allocated 4 KiB clusters following an unaligned 32 KiB hole. With this change, the same data remains intact across FITRIM and remount. Fixes: 11ccc9107dc4 ("ntfs: update runlist handling and cluster allocator") Cc: stable@vger.kernel.org Assisted-by: OpenAI Codex:GPT-5.6 Sol Max Signed-off-by: Jacopo Labardi Signed-off-by: Namjae Jeon --- fs/ntfs/bitmap.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/fs/ntfs/bitmap.c b/fs/ntfs/bitmap.c index b1436b3151b9..1840b7d84c62 100644 --- a/fs/ntfs/bitmap.c +++ b/fs/ntfs/bitmap.c @@ -64,7 +64,7 @@ int ntfs_trim_fs(struct ntfs_volume *vol, struct fstrim_range *range) end = start_buf; while (end < end_buf) { - u64 aligned_start, aligned_count; + u64 aligned_start, aligned_end, aligned_count; u64 start = find_next_zero_bit(bitmap, end_buf - start_buf, end - start_buf) + start_buf; if (start >= end_buf) @@ -74,8 +74,10 @@ int ntfs_trim_fs(struct ntfs_volume *vol, struct fstrim_range *range) start - start_buf) + start_buf; aligned_start = ALIGN(ntfs_cluster_to_bytes(vol, start), dq); - aligned_count = - ALIGN_DOWN(ntfs_cluster_to_bytes(vol, end - start), dq); + aligned_end = ALIGN_DOWN(ntfs_cluster_to_bytes(vol, end), dq); + if (aligned_start >= aligned_end) + continue; + aligned_count = aligned_end - aligned_start; if (aligned_count >= range->minlen) { ret = blkdev_issue_discard(vol->sb->s_bdev, aligned_start >> 9, aligned_count >> 9, GFP_NOFS); From a155ac8f0c523bd53f412196dcbb104ad1f4595f Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Sat, 29 Aug 2026 14:34:12 -0700 Subject: [PATCH 0177/1198] interrupt: Disable interrupt before modifying hardirq_disable counter Currently a softirq may be pending longer then expected if the triggering interrupt happens in-between hardirq_disable_enter() and _local_interrupt_disable() in local_interrupt_disable(): local_interrupt_disable(): hardirq_disable_enter(); ... __irq_exit_rcu(): // false because hardirq_disable_count() is not 0 if (.. && !hardirq_disable_count() && ..) { invoke_softirq(); } _local_interrupt_disable(); , it'll defer the softirq to the next interrupt which can be forever. The order between hardirq_disable_enter() and _local_interrupt_disable() is to optimize re-disabling interrupts if they are already disabled, but as 1) local_interrupt_disable() is not widely used yet and 2) the proper way to achieve this optimization may need fixing up the counter at entry/exit time [1], so reverse the order for now to avoid the softirq pending issue. Because of this fix, the part of saving the current state is separated from irq disabling, and the logic of local_interrupt_disable() becomes: local_irq_save(flags); if (counter++ == 0) { this_cpu(local_interrupt_disable_state) = flags; } Therefore change the helper function _local_interrupt_disable() to _local_interrupt_save_state() which only saves the current irqflags (when interrupts get disabled the first time). Fixes: e901c1510e24 ("irq,spin_lock: Add counted interrupt disabling/enabling") Reported-by: Thomas Gleixner Signed-off-by: Boqun Feng Signed-off-by: Thomas Gleixner Reviewed-by: Bradley Morgan Link: https://patch.msgid.link/20260829213412.14303-1-boqun@kernel.org Link: https://lore.kernel.org/lkml/87v78wezid.ffs@fw13/ [1] Closes: https://lore.kernel.org/lkml/87jypbfu1t.ffs@fw13/ --- include/linux/interrupt_rc.h | 19 ++++++++----------- kernel/softirq.c | 17 ++++------------- 2 files changed, 12 insertions(+), 24 deletions(-) diff --git a/include/linux/interrupt_rc.h b/include/linux/interrupt_rc.h index b9a7f05ecf42..e68e1bedba66 100644 --- a/include/linux/interrupt_rc.h +++ b/include/linux/interrupt_rc.h @@ -20,11 +20,8 @@ /* Per-CPU interrupt disabling state for local_interrupt_{disable,enable}(). */ DECLARE_PER_CPU(unsigned long, local_interrupt_disable_state); -static __always_inline void __local_interrupt_disable(void) +static __always_inline void __local_interrupt_save_state(unsigned long flags) { - unsigned long flags; - - local_irq_save(flags); raw_cpu_write(local_interrupt_disable_state, flags); } @@ -36,9 +33,9 @@ static __always_inline void __local_interrupt_enable(void) } #ifndef INSTANTIATE_EXPORTED_INTERRUPT_DISABLE -static __always_inline void _local_interrupt_disable(void) +static __always_inline void _local_interrupt_save_state(unsigned long flags) { - __local_interrupt_disable(); + __local_interrupt_save_state(flags); } static __always_inline void _local_interrupt_enable(void) @@ -46,27 +43,27 @@ static __always_inline void _local_interrupt_enable(void) __local_interrupt_enable(); } #else -extern void _local_interrupt_disable(void); +extern void _local_interrupt_save_state(unsigned long flags); extern void _local_interrupt_enable(void); #endif #else /* !MODULE */ -extern void _local_interrupt_disable(void); +extern void _local_interrupt_save_state(unsigned long flags); extern void _local_interrupt_enable(void); #endif /* !MODULE */ static inline void local_interrupt_disable(void) { int new_count; + unsigned long flags; WARN_ON_ONCE(in_nmi()); + local_irq_save(flags); new_count = hardirq_disable_enter(); - /* Interrupts can happen here, but it's OK, see __irq_exit_rcu(). */ - if ((new_count & HARDIRQ_DISABLE_MASK) == HARDIRQ_DISABLE_OFFSET) - _local_interrupt_disable(); + _local_interrupt_save_state(flags); } static inline void local_interrupt_enable(void) diff --git a/kernel/softirq.c b/kernel/softirq.c index 7980a4a232f9..5d02c36c40e3 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -91,11 +91,11 @@ EXPORT_PER_CPU_SYMBOL_GPL(hardirq_context); DEFINE_PER_CPU(unsigned long, local_interrupt_disable_state); -void _local_interrupt_disable(void) +void _local_interrupt_save_state(unsigned long flags) { - __local_interrupt_disable(); + __local_interrupt_save_state(flags); } -EXPORT_SYMBOL(_local_interrupt_disable); +EXPORT_SYMBOL(_local_interrupt_save_state); void _local_interrupt_enable(void) { @@ -749,16 +749,7 @@ static inline void __irq_exit_rcu(void) #endif account_hardirq_exit(current); preempt_count_sub(HARDIRQ_OFFSET); - /* - * Interrupts may happen between hardirq_disable_enter() and - * local_irq_save() in local_interrupt_disable(), if irq_exit() invokes - * softirq here, we may have a softirq handler calling - * local_interrupt_disable() but it won't disable the IRQ because - * hardirq disabling count is already 1, hence we need to prevent - * invoking softirq when a local_interrupt_disable() is ongoing. - */ - if (!in_interrupt() && !hardirq_disable_count() && - local_softirq_pending()) { + if (!in_interrupt() && local_softirq_pending()) { /* * If we left hrtimers unarmed, make sure to arm them now, * before enabling interrupts to run softirq. From 1519dc88c87f5346dae0464d7d6da1b6bf1f6e8e Mon Sep 17 00:00:00 2001 From: Huiwen He Date: Fri, 28 Aug 2026 15:19:29 +0800 Subject: [PATCH 0178/1198] smb/client: validate new EOF for insert range smb3_insert_range() does not check if the new file size (i_size + len) is valid. This allows FALLOC_FL_INSERT_RANGE to bypass RLIMIT_FSIZE, exceed s_maxbytes, or produce a size outside the loff_t range. Use check_add_overflow() to calculate the new EOF. Validate it with inode_newsize_ok() before modifying the file. Reproducer, using a file on a CIFS mount: bash -c ' FILE=/mnt/cifs/repro trap "" SIGXFSZ ulimit -f 3072 # RLIMIT_FSIZE = 3 MiB # A regular write is stopped at 3 MiB. dd if=/dev/zero of="$FILE" bs=1M count=4 status=none stat -c "size after write: %s" "$FILE" # Insert 2 MiB into a 2 MiB file. truncate -s 2M "$FILE" fallocate -i -o 0 -l 2M "$FILE" stat -c "size after insert: %s" "$FILE" ' Before this change, the regular write stops at the 3 MiB limit, but insert range grows the file to 4 MiB: dd: error writing '/mnt/cifs/repro': File too large size after write: 3145728 size after insert: 4194304 After this change, insert range also fails at the limit and leaves the 2 MiB file unchanged: dd: error writing '/mnt/cifs/repro': File too large size after write: 3145728 fallocate: fallocate failed: File too large size after insert: 2097152 Fixes: 7fe6fe95b936 ("cifs: add FALLOC_FL_INSERT_RANGE support") Signed-off-by: Huiwen He Reviewed-by: ChenXiaoSong Reviewed-by: Namjae Jeon Signed-off-by: Paulo Alcantara --- fs/smb/client/smb2ops.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index bea4876b58cb..1ee67b4f1c77 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -3985,7 +3985,8 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, struct cifsFileInfo *cfile = file->private_data; struct inode *inode = file_inode(file); struct cifsInodeInfo *cifsi = CIFS_I(inode); - __u64 count, old_eof, new_eof; + u64 count; + loff_t old_eof, new_eof; xid = get_xid(); @@ -3995,8 +3996,15 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, goto out; } + if (check_add_overflow(old_eof, len, &new_eof)) { + rc = -EFBIG; + goto out; + } + rc = inode_newsize_ok(inode, new_eof); + if (rc) + goto out; + count = old_eof - off; - new_eof = old_eof + len; filemap_invalidate_lock(inode->i_mapping); rc = filemap_write_and_wait_range(inode->i_mapping, off, new_eof - 1); From 88972e35750792e717af287dc71f42a03b5cbce4 Mon Sep 17 00:00:00 2001 From: Huiwen He Date: Fri, 28 Aug 2026 15:19:30 +0800 Subject: [PATCH 0179/1198] smb/client: validate new EOF for zero range When FALLOC_FL_ZERO_RANGE is used without FALLOC_FL_KEEP_SIZE, smb3_zero_range() may extend EOF without checking RLIMIT_FSIZE, allowing the file to grow beyond the caller's file-size limit. Fix this by calling inode_newsize_ok() before sending the zero-range request when the operation would extend EOF. Reproducer, using a file on a CIFS mount: bash -c ' FILE=/mnt/cifs/repro trap "" SIGXFSZ ulimit -f 3072 truncate -s 2M "$FILE" fallocate --zero-range -o 0 -l 4M "$FILE" echo "fallocate rc=$?" stat -c "file size=%s" "$FILE" ' Before this change, the operation succeeds despite the 3 MiB limit: fallocate rc=0 file size=4194304 After this change, fallocate fails and leaves the file at 2 MiB. Fixes: 72c419d9b073 ("cifs: fix smb3_zero_range so it can expand the file-size when required") Signed-off-by: Huiwen He Reviewed-by: ChenXiaoSong Reviewed-by: Namjae Jeon Signed-off-by: Paulo Alcantara --- fs/smb/client/smb2ops.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 1ee67b4f1c77..f41fc71f1ba7 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -3444,6 +3444,13 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, trace_smb3_zero_enter(xid, cfile->fid.persistent_fid, tcon->tid, ses->Suid, offset, len); + new_size = offset + len; + if (!keep_size && i_size_read(inode) < new_size) { + rc = inode_newsize_ok(inode, new_size); + if (rc) + goto out; + } + filemap_invalidate_lock(inode->i_mapping); netfs_read_sizes(inode, &i_size, &remote_i_size, &zero_point); @@ -3474,7 +3481,6 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, /* * do we also need to change the size of the file? */ - new_size = offset + len; if (keep_size == false && (unsigned long long)i_size_read(inode) < new_size) { rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, cfile->pid, new_size); @@ -3491,6 +3497,7 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, zero_range_exit: filemap_invalidate_unlock(inode->i_mapping); + out: free_xid(xid); if (rc) trace_smb3_zero_err(xid, cfile->fid.persistent_fid, tcon->tid, From cd03ce4950d80147ac8f20bc03c42b75b0352407 Mon Sep 17 00:00:00 2001 From: Huiwen He Date: Fri, 28 Aug 2026 15:19:31 +0800 Subject: [PATCH 0180/1198] smb/client: mark file sparse before emulating insert range The SMB client emulates FALLOC_FL_INSERT_RANGE with SET_EOF, COPYCHUNK and SET_ZERO_DATA. SET_ZERO_DATA creates a hole only when the file is sparse. On a non-sparse file, it clears the inserted range but leaves its blocks allocated, causing the extent count check in xfstests generic/064 to fail. Fix this by marking the file sparse before modifying it. This patch produces the expected sparse extents in xfstests generic/064 only when the server-reported block size is compatible with the server's deallocation granularity. For ksmbd, the reported block size follows the backing filesystem, and the test passes. For Samba, the test passes with a block size matching the backend granularity, for example, 4 KiB on Btrfs, but not with the default 1 KiB value. For Windows Server 2022, 4 KiB inserts do not generate holes, while aligned inserts of 64 KiB or larger do. Fixes: 7fe6fe95b936 ("cifs: add FALLOC_FL_INSERT_RANGE support") Signed-off-by: Huiwen He Reviewed-by: ChenXiaoSong Reviewed-by: Namjae Jeon Signed-off-by: Paulo Alcantara --- fs/smb/client/smb2ops.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index f41fc71f1ba7..ac730eab382b 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -4013,6 +4013,11 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, count = old_eof - off; + /* SET_ZERO_DATA creates a hole only in a sparse file. */ + rc = smb2_set_sparse(xid, tcon, cfile, inode, true); + if (rc) + goto out; + filemap_invalidate_lock(inode->i_mapping); rc = filemap_write_and_wait_range(inode->i_mapping, off, new_eof - 1); if (rc < 0) From 0923ae9f23cc9460b0df6fc124cd56ec4436411b Mon Sep 17 00:00:00 2001 From: Huiwen He Date: Fri, 28 Aug 2026 15:19:32 +0800 Subject: [PATCH 0181/1198] smb/client: fix data corruption in emulated insert range smb3_insert_range() shifts [off, EOF) right with COPYCHUNK, copying from low to high offsets. When the ranges overlap, the copy can overwrite source data that has not yet been copied. For a 1 MiB insert at offset 0: offset: 0 1M 2M 3M 4M 5M before: | A | B | C | D | expected: | hole | A | B | C | D | current: | hole | A | A | A | A | (corrupted) Let x be the insertion offset, L the total length to move, delta the insert length, and C the normal chunk size allowed by the server. Insert range maps [x, x + L) -> [x + delta, x + delta + L). When delta >= L, the complete source and target ranges are disjoint, so the normal copy order and chunk size are safe: offset: 0 4 8 12 16 20 24 28 32 source: [--S0--][--S1--][--S2--][--S3--] target: [--T0--][--T1--][--T2--][--T3--] When delta < L, the complete source and target ranges overlap, so the copy must proceed from EOF backwards. There are two subcases. If delta >= C, each corresponding source and target chunk is disjoint. The 1 MiB example has L = 4 MiB and delta = C = 1 MiB: offset: 0 1M 2M 3M 4M 5M source: [--S0--][--S1--][--S2--][--S3--] target: [--T0--][--T1--][--T2--][--T3--] Copying S0 from [0, 1M) to [1M, 2M) overwrites S1 before it is copied. Processing chunks from EOF backwards prevents this inter-chunk overwrite. If delta < C, the source and target ranges of a normal chunk also overlap. For example, with L = 16, delta = 2 and C = 4: offset: 0 2 4 6 8 10 12 14 16 18 source: [--S0--][--S1--][--S2--][--S3--] target: [--T0--][--T1--][--T2--][--T3--] Here S0 and T0 overlap over [2,4), S1 and T1 over [6,8), and so on. Backward ordering cannot control how the server copies bytes inside one descriptor, so the chunk size must be limited to delta. Fix this by copying overlapping right shifts from EOF backwards. Limit the chunk size to delta when delta < C so that each chunk's source and target ranges do not overlap. Using larger chunks would require a way to identify servers that safely handle overlapping COPYCHUNK descriptors. Therefore: delta >= L: keep the normal copy order and chunk size delta < L: delta >= C: copy backwards and keep the normal chunk size delta < C: copy backwards and limit the chunk size to delta Only the delta < C subcase requires reducing the chunk size for data integrity. Reproducer: bash -c ' MNT=/mnt/scratch # Generate four 1 MiB random blocks: [A][B][C][D]. dd if=/dev/urandom of=/tmp/src bs=1M count=4 status=none # With C = 1 MiB, test delta = C and delta < C. for delta in 1M 1K; do truncate -s 0 /tmp/expected truncate -s "$delta" /tmp/expected cat /tmp/src >> /tmp/expected cp /tmp/src "$MNT/file" fallocate --insert-range -o 0 -l "$delta" "$MNT/file" if cmp -s /tmp/expected "$MNT/file"; then echo "delta=$delta: OK" else echo "delta=$delta: CORRUPTED" fi done ' The corruption reproduces with Samba and ksmbd, while Windows handles the overlapping COPYCHUNK ranges safely. The 1 MiB case tests delta >= C, while the 1 KiB case tests delta < C. Before this change, the reproducer reports: delta=1M: CORRUPTED delta=1K: CORRUPTED After this change, it passes against both ksmbd and Samba: delta=1M: OK delta=1K: OK Fixes: 7fe6fe95b936 ("cifs: add FALLOC_FL_INSERT_RANGE support") Signed-off-by: Huiwen He Reviewed-by: ChenXiaoSong Reviewed-by: Namjae Jeon Signed-off-by: Paulo Alcantara --- fs/smb/client/smb2ops.c | 132 ++++++++++++++++++++++++++++++++-------- 1 file changed, 106 insertions(+), 26 deletions(-) diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index ac730eab382b..2fe5223b8a26 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -1839,31 +1839,31 @@ smb2_ioctl_query_info(const unsigned int xid, * * @tcon: destination file tcon * @bytes_left: how many bytes are left to copy + * @chunk_size: maximum size of a single chunk * * Return: maximum number of chunks with which Chunks[] can be filled. */ static inline u32 -calc_chunk_count(struct cifs_tcon *tcon, u64 bytes_left) +calc_chunk_count(struct cifs_tcon *tcon, u64 bytes_left, u32 chunk_size) { u32 max_chunks = READ_ONCE(tcon->max_chunks); u32 max_bytes_copy = READ_ONCE(tcon->max_bytes_copy); - u32 max_bytes_chunk = READ_ONCE(tcon->max_bytes_chunk); u64 need; u32 allowed; - if (!max_bytes_chunk || !max_bytes_copy || !max_chunks) + if (!chunk_size || !max_bytes_copy || !max_chunks) return 0; /* chunks needed for the remaining bytes */ - need = DIV_ROUND_UP_ULL(bytes_left, max_bytes_chunk); + need = DIV_ROUND_UP_ULL(bytes_left, chunk_size); /* chunks allowed per cc request */ - allowed = DIV_ROUND_UP(max_bytes_copy, max_bytes_chunk); + allowed = DIV_ROUND_UP(max_bytes_copy, chunk_size); return (u32)umin(need, umin(max_chunks, allowed)); } /** - * smb2_copychunk_range - server-side copy of data range + * __smb2_copychunk_range - server-side copy of data range * * @xid: transaction id * @src_file: source file @@ -1875,15 +1875,15 @@ calc_chunk_count(struct cifs_tcon *tcon, u64 bytes_left) * Obtains a resume key for @src_file and issues FSCTL_SRV_COPYCHUNK_WRITE * IOCTLs, splitting the request into chunks limited by tcon->max_*. * - * Return: @len on success; negative errno on failure. + * Return: 0 on success; negative errno on failure. */ -static ssize_t -smb2_copychunk_range(const unsigned int xid, - struct cifsFileInfo *src_file, - struct cifsFileInfo *dst_file, - u64 src_off, - u64 len, - u64 dst_off) +static int +__smb2_copychunk_range(const unsigned int xid, + struct cifsFileInfo *src_file, + struct cifsFileInfo *dst_file, + u64 src_off, + u64 len, + u64 dst_off) { int rc = 0; unsigned int ret_data_len = 0; @@ -1891,12 +1891,14 @@ smb2_copychunk_range(const unsigned int xid, struct copychunk_ioctl_rsp *cc_rsp = NULL; struct cifs_tcon *tcon; struct srv_copychunk *chunk; - u32 chunks, chunk_count, chunk_bytes; + u32 chunks, chunk_count, chunk_bytes, chunk_size; u32 copy_bytes, copy_bytes_left; u32 chunks_written, bytes_written; u64 total_bytes_left = len; u64 src_off_prev, dst_off_prev; + u64 max_chunk = 0; u32 retries = 0; + bool reverse = false; tcon = tlink_tcon(dst_file->tlink); @@ -1904,8 +1906,50 @@ smb2_copychunk_range(const unsigned int xid, dst_file->fid.volatile_fid, tcon->tid, tcon->ses->Suid, src_off, dst_off, len); + /* + * Same-file left shifts are safe in forward order. For a right shift, + * let L be the copy length, delta the distance between the source and + * destination, and C the normal chunk size: + * + * delta >= L: copy forwards using C + * delta < L: + * delta >= C: copy backwards using C + * delta < C: copy backwards with chunks limited to delta + * + * Copying backwards prevents one chunk from overwriting data needed by + * a later chunk. Limiting the chunk size to delta prevents an individual + * chunk from overlapping itself. + * This limit can be removed once all supported servers handle overlapping + * descriptors safely. + * + * A small right shift over a large range may therefore require many + * chunks. + */ + if (src_file == dst_file && dst_off > src_off) { + u64 delta = dst_off - src_off; + + if (delta < len) { + reverse = true; + max_chunk = delta; + } + } + + /* + * A backward copy walks the offsets down from the end of the range. + * Do this once, outside the retry loop, so a retry does not move the + * offsets again. + */ + if (reverse) { + src_off += len; + dst_off += len; + } + retry: - chunk_count = calc_chunk_count(tcon, total_bytes_left); + chunk_size = READ_ONCE(tcon->max_bytes_chunk); + if (max_chunk && max_chunk < chunk_size) + chunk_size = (u32)max_chunk; + + chunk_count = calc_chunk_count(tcon, total_bytes_left, chunk_size); if (!chunk_count) { rc = -EOPNOTSUPP; goto out; @@ -1946,16 +1990,21 @@ smb2_copychunk_range(const unsigned int xid, while (copy_bytes_left > 0 && chunks < chunk_count) { chunk = &cc_req->Chunks[chunks++]; + chunk_bytes = umin(copy_bytes_left, chunk_size); + if (reverse) { + src_off -= chunk_bytes; + dst_off -= chunk_bytes; + } + chunk->SourceOffset = cpu_to_le64(src_off); chunk->TargetOffset = cpu_to_le64(dst_off); - - chunk_bytes = umin(copy_bytes_left, tcon->max_bytes_chunk); - chunk->Length = cpu_to_le32(chunk_bytes); /* Buffer is zeroed, no need to set chunk->Reserved = 0 */ - src_off += chunk_bytes; - dst_off += chunk_bytes; + if (!reverse) { + src_off += chunk_bytes; + dst_off += chunk_bytes; + } copy_bytes_left -= chunk_bytes; copy_bytes += chunk_bytes; @@ -2003,6 +2052,18 @@ smb2_copychunk_range(const unsigned int xid, goto out; } + /* + * A successful COPYCHUNK should copy every descriptor (MS-SMB2 + * 3.3.5.15.6). Reject a short backward copy because the rewind + * below only supports forward copying. + */ + if (unlikely(reverse && bytes_written < copy_bytes)) { + cifs_tcon_dbg(VFS, "Copychunk short write %u/%u (reverse)\n", + bytes_written, copy_bytes); + rc = -EIO; + goto out; + } + /* Partial write: rewind */ if (bytes_written < copy_bytes) { u32 delta = copy_bytes - bytes_written; @@ -2064,10 +2125,27 @@ smb2_copychunk_range(const unsigned int xid, trace_smb3_copychunk_done(xid, src_file->fid.volatile_fid, dst_file->fid.volatile_fid, tcon->tid, tcon->ses->Suid, src_off, dst_off, len); - return len; + return 0; } } +static ssize_t +smb2_copychunk_range(const unsigned int xid, + struct cifsFileInfo *src_file, + struct cifsFileInfo *dst_file, + u64 src_off, + u64 len, + u64 dst_off) +{ + int rc; + + rc = __smb2_copychunk_range(xid, src_file, dst_file, src_off, len, + dst_off); + if (rc) + return rc; + return len; +} + static int smb2_flush_file(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *fid) @@ -3992,7 +4070,6 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, struct cifsFileInfo *cfile = file->private_data; struct inode *inode = file_inode(file); struct cifsInodeInfo *cifsi = CIFS_I(inode); - u64 count; loff_t old_eof, new_eof; xid = get_xid(); @@ -4011,8 +4088,6 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, if (rc) goto out; - count = old_eof - off; - /* SET_ZERO_DATA creates a hole only in a sparse file. */ rc = smb2_set_sparse(xid, tcon, cfile, inode, true); if (rc) @@ -4036,7 +4111,12 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, spin_unlock(&inode->i_lock); fscache_resize_cookie(cifs_inode_cookie(inode), i_size_read(inode)); - rc = smb2_copychunk_range(xid, cfile, cfile, off, count, off + len); + /* + * Move [off, old_eof) right by len. The helper copies backwards if the + * source and destination ranges overlap. + */ + rc = __smb2_copychunk_range(xid, cfile, cfile, off, old_eof - off, + off + len); if (rc < 0) goto out_2; spin_lock(&inode->i_lock); From 7811701d6af7db76481a82b9bc3c4adf7863acf5 Mon Sep 17 00:00:00 2001 From: Huiwen He Date: Fri, 28 Aug 2026 15:19:33 +0800 Subject: [PATCH 0182/1198] smb/client: fix integer truncation in collapse range smb3_collapse_range() stores the ssize_t return value of smb2_copychunk_range() in an int. A successful copy larger than INT_MAX is truncated to a negative value and treated as an error. Reproducer: MNT=/mnt/scratch truncate -s 2056M "$MNT/file" fallocate --collapse-range -o 1M -l 1M "$MNT/file" Fix this by using __smb2_copychunk_range(), which reports success as zero instead of returning the copied byte count. Before this change, the reproducer fails with: fallocate: fallocate failed: Success and the file size remains unchanged at 2056 MiB. After this change, the reproducer succeeds and the file size becomes the expected 2055 MiB. Fixes: 5476b5dd82c8 ("cifs: add support for FALLOC_FL_COLLAPSE_RANGE") Signed-off-by: Huiwen He Reviewed-by: ChenXiaoSong Reviewed-by: Namjae Jeon Signed-off-by: Paulo Alcantara --- fs/smb/client/smb2ops.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 2fe5223b8a26..1d476a8af863 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -4036,8 +4036,8 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon, spin_unlock(&inode->i_lock); netfs_wait_for_outstanding_io(inode); - rc = smb2_copychunk_range(xid, cfile, cfile, off + len, - old_eof - off - len, off); + rc = __smb2_copychunk_range(xid, cfile, cfile, off + len, + old_eof - off - len, off); if (rc < 0) goto out_2; From 01261a6fa48b62f5ead8e88aaca1e27cb9ab9032 Mon Sep 17 00:00:00 2001 From: Huiwen He Date: Fri, 28 Aug 2026 15:19:34 +0800 Subject: [PATCH 0183/1198] smb/client: fix stale page cache in insert/collapse range smb3_insert_range() and smb3_collapse_range() use truncate_pagecache_range() to invalidate the affected page cache. However, if off or old_eof is not page-aligned, the boundary pages are only partially zeroed and remain uptodate. As a result, the client may return stale data after a successful insert/collapse range operation. For example, with 4K pages: page 0 page 1 page 2 0------4K 4K------8K 8K------12K ^ ^ off=2K old_eof=10K Page 1 is removed from the page cache, while the boundary pages are only partially zeroed. After COPYCHUNK moves the data on the server, these cached pages may still return stale data. This can be reproduced on a CIFS mount: bash -c ' FILE=/mnt/scratch/repro # Use a 6 KiB file so EOF is not page-aligned. dd if=/dev/urandom of=/tmp/src bs=1K count=6 status=none # Expected: a 4 KiB hole followed by the original data. rm -f /tmp/expected truncate -s 4K /tmp/expected cat /tmp/src >> /tmp/expected cp /tmp/src "$FILE" # Prime the page cache before moving data on the server. cat "$FILE" > /dev/null fallocate --insert-range -o 0 -l 4K "$FILE" if cmp -s /tmp/expected "$FILE"; then echo "readback: OK" else echo "readback: STALE DATA" fi ' Fix this by writing back dirty data and discarding the page cache from the start of the page containing off to EOF before moving data on the server. Fixes: 9c8b7a293f50 ("smb3: fix temporary data corruption in insert range") Fixes: fa30a81f255a ("smb3: fix temporary data corruption in collapse range") Signed-off-by: Huiwen He Reviewed-by: ChenXiaoSong Reviewed-by: Namjae Jeon Signed-off-by: Paulo Alcantara --- fs/smb/client/smb2ops.c | 23 ++++++++++++++++++----- 1 file changed, 18 insertions(+), 5 deletions(-) diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 1d476a8af863..cd5e31b578f9 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -4026,15 +4026,22 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon, } filemap_invalidate_lock(inode->i_mapping); - rc = filemap_write_and_wait_range(inode->i_mapping, off, old_eof - 1); + rc = filemap_write_and_wait_range(inode->i_mapping, + round_down(off, PAGE_SIZE), + old_eof - 1); if (rc < 0) goto out_2; - truncate_pagecache_range(inode, off, old_eof); + netfs_wait_for_outstanding_io(inode); + /* + * Invalidate cached folios from the page containing off to EOF before + * moving data on the server, so subsequent reads do not see stale data. + */ + truncate_pagecache_range(inode, round_down(off, PAGE_SIZE), -1); + spin_lock(&inode->i_lock); netfs_write_zero_point(inode, old_eof); spin_unlock(&inode->i_lock); - netfs_wait_for_outstanding_io(inode); rc = __smb2_copychunk_range(xid, cfile, cfile, off + len, old_eof - off - len, off); @@ -4094,11 +4101,17 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, goto out; filemap_invalidate_lock(inode->i_mapping); - rc = filemap_write_and_wait_range(inode->i_mapping, off, new_eof - 1); + rc = filemap_write_and_wait_range(inode->i_mapping, + round_down(off, PAGE_SIZE), + old_eof - 1); if (rc < 0) goto out_2; - truncate_pagecache_range(inode, off, old_eof); netfs_wait_for_outstanding_io(inode); + /* + * Invalidate cached folios from the page containing off to EOF before + * moving data on the server, so subsequent reads do not see stale data. + */ + truncate_pagecache_range(inode, round_down(off, PAGE_SIZE), -1); rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, cfile->pid, new_eof); From 448ba0ae65ca61064183564d2983c9aa59bd6ba7 Mon Sep 17 00:00:00 2001 From: Huiwen He Date: Fri, 28 Aug 2026 15:19:35 +0800 Subject: [PATCH 0184/1198] smb/client: invalidate fscache for fallocate range operations smb3_zero_range(), smb3_punch_hole(), smb3_insert_range(), and smb3_collapse_range() modify file contents through server-side range operations. These operations discard the affected page cache, but leave the FS-Cache cookie valid, so a later read may return data cached before the range operation. Fix this by invalidating FS-Cache after outstanding I/O has completed and before modifying the file on the server. Run the following as root on a CIFS mount with fsc enabled and an active CacheFiles backend: bash -c ' MNT=/mnt/cifs FILE="$MNT/repro" # Generate four 1 MiB random blocks: [A][B][C][D]. dd if=/dev/urandom of=/tmp/src bs=1M count=4 status=none # Expected contents after zeroing B: [A][zero][C][D]. cp /tmp/src /tmp/expected dd if=/dev/zero of=/tmp/expected bs=1M seek=1 count=1 \ conv=notrunc status=none cp /tmp/src "$FILE" # Populate FS-Cache, then discard the page cache. sync echo 1 > /proc/sys/vm/drop_caches cat "$FILE" > /dev/null sync echo 1 > /proc/sys/vm/drop_caches fallocate --zero-range -o 1M -l 1M "$FILE" if cmp -s /tmp/expected "$FILE"; then echo "readback: OK" else echo "readback: STALE DATA" fi ' Before this change, the readback differs from /tmp/expected: readback: STALE DATA After this change, it matches: readback: OK Fixes: 30175628bf7f ("[SMB3] Enable fallocate -z support for SMB3 mounts") Fixes: 31742c5a3317 ("enable fallocate punch hole ("fallocate -p") for SMB3") Fixes: 5476b5dd82c8 ("cifs: add support for FALLOC_FL_COLLAPSE_RANGE") Fixes: 7fe6fe95b936 ("cifs: add FALLOC_FL_INSERT_RANGE support") Signed-off-by: Huiwen He Suggested-by: Namjae Jeon Reviewed-by: ChenXiaoSong Reviewed-by: Namjae Jeon Signed-off-by: Paulo Alcantara --- fs/smb/client/smb2ops.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index cd5e31b578f9..cb4fd09f996e 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -3552,6 +3552,9 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, if (keep_size == false && !CIFS_CACHE_READ(cifsi)) goto zero_range_exit; + fscache_invalidate(cifs_inode_cookie(inode), NULL, + i_size_read(inode), 0); + rc = smb3_zero_data(file, tcon, offset, len, xid); if (rc < 0) goto zero_range_exit; @@ -3621,6 +3624,8 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, */ truncate_pagecache_range(inode, offset, offset + len - 1); netfs_wait_for_outstanding_io(inode); + fscache_invalidate(cifs_inode_cookie(inode), NULL, + i_size_read(inode), 0); cifs_dbg(FYI, "Offset %lld len %lld\n", offset, len); @@ -4038,6 +4043,7 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon, * moving data on the server, so subsequent reads do not see stale data. */ truncate_pagecache_range(inode, round_down(off, PAGE_SIZE), -1); + fscache_invalidate(cifs_inode_cookie(inode), NULL, old_eof, 0); spin_lock(&inode->i_lock); netfs_write_zero_point(inode, old_eof); @@ -4112,6 +4118,7 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, * moving data on the server, so subsequent reads do not see stale data. */ truncate_pagecache_range(inode, round_down(off, PAGE_SIZE), -1); + fscache_invalidate(cifs_inode_cookie(inode), NULL, old_eof, 0); rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, cfile->pid, new_eof); From d83a21bb26015bfdd79b0440fe816b271b8bbab3 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 25 Aug 2026 10:30:43 +0200 Subject: [PATCH 0185/1198] smb: client: transport: Fix debug printing in __release_mid() Long time ago during upgrading printk():s to the respective pr_() calls one misconversion happened and nobody has noticed that. So, previously printk(KERN_DEBUG) + printk() worked as one long debug print since the trailing '\n' is only present in the followup printk() format string. The culprit change missed that and split the message to two on the different levels. Restore the original behaviour to make users be less confused in the most likely never happen cases of partially getting that message. Fixes: 0b456f04bcdf ("cifs: convert printk(LEVEL...) to pr_") Signed-off-by: Andy Shevchenko Signed-off-by: Paulo Alcantara --- fs/smb/client/transport.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c index fdf4e50c27ce..e266859818a4 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -101,12 +101,11 @@ void __release_mid(struct TCP_Server_Info *server, struct mid_q_entry *midEntry) trace_smb3_slow_rsp(smb_cmd, midEntry->mid, midEntry->pid, midEntry->when_sent, midEntry->when_received); if (cifsFYI & CIFS_TIMER) { - pr_debug("slow rsp: cmd %d mid %llu", - midEntry->command, midEntry->mid); - cifs_info("A: 0x%lx S: 0x%lx R: 0x%lx\n", - now - midEntry->when_alloc, - now - midEntry->when_sent, - now - midEntry->when_received); + pr_debug("slow rsp: cmd %d mid %llu A: 0x%lx S: 0x%lx R: 0x%lx\n", + midEntry->command, midEntry->mid, + now - midEntry->when_alloc, + now - midEntry->when_sent, + now - midEntry->when_received); } } #endif From 69499395867332364ed4ac8b546537eb3bab6ebb Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Mon, 24 Aug 2026 16:59:12 -0300 Subject: [PATCH 0186/1198] smb: client: fix multiuser mount with krb5 Customer reported that they could no longer mount their SMB shares with multiuser mount option and krb5. Turned out that the client wasn't duplicating username option when creating multiuser connections, therefore failing to retrieve credentials as cifs.upcall(8) couldn't find them in keytab. Fix this by duplicating username option (if set) from original fs context before creating multiuser connections with krb5. Reproducer: ``` $ ktutil ktutil: add_entry -password -p testuser -k 1 -e aes256-cts Password for testuser@ZELDA.TEST: ktutil: write_kt /etc/krb5.keytab ktutil: quit $ klist -ke Keytab name: FILE:/etc/krb5.keytab KVNO Principal ---- ---------------------------------------------------------------- 1 testuser@ZELDA.TEST (aes256-cts-hmac-sha1-96) $ mount.cifs //w22-root2/scratch /mnt/1 -o \ uid=1000,sec=krb5,username=testuser@ZELDA.TEST,multiuser mount error(13): Permission denied Refer to the mount.cifs(8) manual page (e.g. man mount.cifs) and kernel log messages (dmesg) ``` Reported-by: Jacob Shivers Fixes: 12b4c5d98cd7 ("smb: client: fix krb5 mount with username option") Cc: Ronnie Sahlberg Cc: Shyam Prasad N Cc: Tom Talpey Cc: Bharath SM Cc: Namjae Jeon Cc: stable@vger.kernel.org Reviewed-by: Namjae Jeon Signed-off-by: Paulo Alcantara --- fs/smb/client/connect.c | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index bcd7f1ae99ba..b6e98eb31673 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -4189,14 +4189,25 @@ cifs_setup_session(const unsigned int xid, struct cifs_ses *ses, return rc; } -static int -cifs_set_vol_auth(struct smb3_fs_context *ctx, struct cifs_ses *ses) +static int set_fs_context_auth(struct smb3_fs_context *ctx, + struct cifs_ses *ses) { ctx->sectype = ses->sectype; - /* krb5 is special, since we don't need username or pw */ - if (ctx->sectype == Kerberos) + /* + * krb5 is special as we might need to pass username (passwordless) down + * to cifs.upcall(8) for keytab. + */ + if (ctx->sectype == Kerberos) { + if (ses->user_name && ses->user_name[0]) { + ctx->username = kstrndup(ses->user_name, + CIFS_MAX_USERNAME_LEN, + GFP_KERNEL); + if (!ctx->username) + return -ENOMEM; + } return 0; + } return cifs_set_cifscreds(ctx, ses); } @@ -4236,7 +4247,7 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) ctx->dfs_root_ses = master_tcon->ses->dfs_root_ses; ctx->unicode = master_tcon->ses->unicode; - rc = cifs_set_vol_auth(ctx, master_tcon->ses); + rc = set_fs_context_auth(ctx, master_tcon->ses); if (rc) { tcon = ERR_PTR(rc); goto out; From 1dac61e2c29d1a71784604b48cf3b1234a65ec29 Mon Sep 17 00:00:00 2001 From: Frank Sorenson Date: Wed, 26 Aug 2026 21:13:36 -0500 Subject: [PATCH 0187/1198] smb: client: fix heap overflow in cifs_do_set_acl() cifs_set_acl() validates ACL size using posix_acl_xattr_size(): 4 + (count * 8) // 4-byte header + 8 bytes per ACE cifs_do_set_acl() then calls posix_acl_to_cifs() to write the CIFS wire format into the same buffer: 6 + (count * 10) // 6-byte header + 10 bytes per ACE An ACL that passes the xattr-based check in cifs_set_acl() can overflow the heap when posix_acl_to_cifs() writes the larger CIFS format. Validate the CIFS format size against the remaining buffer space and USHRT_MAX before converting--data_count is __u16, so sizes above USHRT_MAX truncate the on-wire packet length, causing the server to apply a partial ACL. Replace MaxDataCount = 1000 with min(CIFSMaxBufSize, USHRT_MAX). Fixes: dc1af4c4b4721 ("cifs: implement set acl method") Cc: stable@vger.kernel.org Signed-off-by: Frank Sorenson Signed-off-by: Paulo Alcantara --- fs/smb/client/cifssmb.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index f5aad5f61dce..230af243247c 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -3555,6 +3555,7 @@ int cifs_do_set_acl(const unsigned int xid, struct cifs_tcon *tcon, int rc = 0; int bytes_returned = 0; __u16 params, byte_count, data_count, param_offset, offset; + size_t cifs_acl_size, bytes_available; cifs_dbg(FYI, "In SetPosixACL (Unix) for path %s\n", fileName); setAclRetry: @@ -3574,8 +3575,7 @@ int cifs_do_set_acl(const unsigned int xid, struct cifs_tcon *tcon, } params = 6 + name_len; pSMB->MaxParameterCount = cpu_to_le16(2); - /* BB find max SMB size from sess */ - pSMB->MaxDataCount = cpu_to_le16(1000); + pSMB->MaxDataCount = cpu_to_le16(min_t(unsigned int, CIFSMaxBufSize, USHRT_MAX)); pSMB->MaxSetupCount = 0; pSMB->Reserved = 0; pSMB->Flags = 0; @@ -3587,6 +3587,15 @@ int cifs_do_set_acl(const unsigned int xid, struct cifs_tcon *tcon, parm_data = ((char *)pSMB) + offset; pSMB->ParameterOffset = cpu_to_le16(param_offset); + /* make sure we can fit the larger cifs_posix_aces in the buffer */ + cifs_acl_size = sizeof(struct cifs_posix_acl) + + (acl->a_count * sizeof(struct cifs_posix_ace)); + bytes_available = (CIFSMaxBufSize + MAX_HEADER_SIZE(tcon->ses->server)) - offset; + if (cifs_acl_size > bytes_available || cifs_acl_size > USHRT_MAX) { + rc = -E2BIG; + goto setACLerrorExit; + } + /* convert to on the wire format for POSIX ACL */ data_count = posix_acl_to_cifs(parm_data, acl, acl_type); From fe39cd9d48f2346605f3746e0cc19e89d5f373eb Mon Sep 17 00:00:00 2001 From: Frank Sorenson Date: Wed, 26 Aug 2026 20:57:38 -0500 Subject: [PATCH 0188/1198] cifs: don't update i_size in cifs_do_truncate without a cached handle If find_writable_file() returns null, cifs_file_flush will return 0 without issuing set_file_size, and the outer 'if (!rc)' block will set i_size to 0 before telling the server to truncate. If the cifs_open() then fails, the inode will have size 0, while the server file is unchanged. Move the netfs_resize_file() and cifs_setsize() into the 'if (cfile)', so they only run after a successful set_file_size. In the no-handle else branch, evict stale pages with truncate_inode_pages before the O_TRUNC open to dispose of old cache pages, and let the open response set the i_size. Fixes: 110fee6b9bb5 ("smb: client: fix missing timestamp updates with O_TRUNC") Cc: stable@vger.kernel.org Signed-off-by: Frank Sorenson Acked-by: David Howells Signed-off-by: Paulo Alcantara --- fs/smb/client/file.c | 24 ++++++++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-) diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 389083f9ce00..100acc76e9be 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -1012,10 +1012,26 @@ static int cifs_do_truncate(const unsigned int xid, struct dentry *dentry) server = tcon->ses->server; rc = server->ops->set_file_size(xid, tcon, cfile, 0, false); - } - if (!rc) { - netfs_resize_file(&cinode->netfs, 0, true); - cifs_setsize(inode, 0); + if (!rc) { + inode_lock(inode); + filemap_invalidate_lock(inode->i_mapping); + netfs_resize_file(&cinode->netfs, 0, true); + cifs_setsize(inode, 0); + filemap_invalidate_unlock(inode->i_mapping); + inode_unlock(inode); + cifs_invalidate_cache(inode, 0); + } + } else { + /* + * No cached handle; evict stale pages so they can't + * be served after the file is later extended; let + * the server's O_TRUNC open response set the i_size + */ + inode_lock(inode); + filemap_invalidate_lock(inode->i_mapping); + truncate_inode_pages(inode->i_mapping, 0); + filemap_invalidate_unlock(inode->i_mapping); + inode_unlock(inode); cifs_invalidate_cache(inode, 0); } } From 2af470916a208b576ac9975d221d9a378cf8ace9 Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Thu, 27 Aug 2026 12:48:35 -0700 Subject: [PATCH 0189/1198] preempt: Remove hardirq_disable_count() It turns out the previous usage of hardirq_disable_count() in __irq_exit_rcu() would cause softirq pending issues. Without that usage, hardirq_disable_count() doesn't need to exist, so remove it. Also move hardirq_disable_enter/exit() into the Rust specific interrupt_rc header. [ tglx: Move the helpers over ] Signed-off-by: Boqun Feng Signed-off-by: Thomas Gleixner Link: https://patch.msgid.link/20260827194835.38968-1-boqun@kernel.org --- include/linux/interrupt_rc.h | 3 +++ include/linux/preempt.h | 4 ---- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/include/linux/interrupt_rc.h b/include/linux/interrupt_rc.h index e68e1bedba66..a9ed937a80e7 100644 --- a/include/linux/interrupt_rc.h +++ b/include/linux/interrupt_rc.h @@ -52,6 +52,9 @@ extern void _local_interrupt_save_state(unsigned long flags); extern void _local_interrupt_enable(void); #endif /* !MODULE */ +#define hardirq_disable_enter() __preempt_count_add_return(HARDIRQ_DISABLE_OFFSET) +#define hardirq_disable_exit() __preempt_count_sub_return(HARDIRQ_DISABLE_OFFSET) + static inline void local_interrupt_disable(void) { int new_count; diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 8299657f0f86..2e689de7b29a 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -168,10 +168,6 @@ static __always_inline unsigned char interrupt_context_level(void) #define in_softirq() (softirq_count()) #define in_interrupt() (irq_count()) -#define hardirq_disable_count() ((preempt_count() & HARDIRQ_DISABLE_MASK) >> HARDIRQ_DISABLE_SHIFT) -#define hardirq_disable_enter() __preempt_count_add_return(HARDIRQ_DISABLE_OFFSET) -#define hardirq_disable_exit() __preempt_count_sub_return(HARDIRQ_DISABLE_OFFSET) - /* * The preempt_count offset after preempt_disable(); */ From 2cb0b0b1ed69430bf73740377ea0a1c44c50db63 Mon Sep 17 00:00:00 2001 From: Henry Martin Date: Fri, 28 Aug 2026 12:24:25 +0800 Subject: [PATCH 0190/1198] sctp: fix soft lockup from unpadded ASCONF-ACK parameter iteration sctp_verify_asconf() walks ASCONF-ACK parameters with sctp_walk_params(), which advances by SCTP_PAD4(length), while the consumer sctp_get_asconf_response() iterates the same parameters advancing by the raw length, without padding. A single odd-length parameter desynchronises the two walks and makes the consumer interpret attacker-controlled bytes at a misaligned offset. When those bytes yield a length of zero, the while loop over asconf_ack_len makes no progress, spinning forever in softirq context, and the watchdog reports a soft lockup. All reads stay within the received skb, so the lockup is a pure remote denial of service. A remote peer can trigger it with a crafted ASCONF-ACK on an ADD-IP enabled association with an outstanding ASCONF (RFC 5061 section 4.1.2 requires the chunk to be authenticated, but the predefined empty key id 0 allows the peer to compute the same association HMAC from publicly exchanged parameters, so the gate does not help). The SCTP_PARAM_ERR_CAUSE case of sctp_verify_asconf() also performs no length check, letting a parameter without a complete error header reach the consumer, which reads errhdr.cause past the end of the parameter, an out-of-bounds read. Reject SCTP_PARAM_ERR_CAUSE parameters shorter than sizeof(struct sctp_addip_param) + sizeof(struct sctp_errhdr) at the verifier, and advance the consumer iterator with the same padding rule as the verifier to keep the two walks in lockstep. The verifier change guarantees a complete error header in every ERR_CAUSE parameter the consumer can see, so the consumer's asconf_ack_len check is dropped and it returns err_param->cause directly. The consumer padding fix is still required because odd lengths remain valid for SCTP_PARAM_ERR_CAUSE per RFC 5061. The issue was found by ZeroHive, a vulnerability hunting agent at Tencent Yunding Lab. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Henry Martin Acked-by: Xin Long Link: https://patch.msgid.link/20260828042431.3873725-1-bsdhenrymartin@gmail.com Signed-off-by: Jakub Kicinski --- net/sctp/sm_make_chunk.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 236e25abc7a4..84a4c97d0f75 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -3215,6 +3215,9 @@ bool sctp_verify_asconf(const struct sctp_association *asoc, *errp = param.p; switch (param.p->type) { case SCTP_PARAM_ERR_CAUSE: + if (length < sizeof(struct sctp_addip_param) + + sizeof(struct sctp_errhdr)) + return false; break; case SCTP_PARAM_IPV4_ADDRESS: if (length != sizeof(struct sctp_ipv4addr_param)) @@ -3448,20 +3451,15 @@ static __be16 sctp_get_asconf_response(struct sctp_chunk *asconf_ack, case SCTP_PARAM_ERR_CAUSE: length = sizeof(*asconf_ack_param); err_param = (void *)asconf_ack_param + length; - asconf_ack_len -= length; - if (asconf_ack_len > 0) - return err_param->cause; - else - return SCTP_ERROR_INV_PARAM; - break; + return err_param->cause; default: return SCTP_ERROR_INV_PARAM; } } length = ntohs(asconf_ack_param->param_hdr.length); - asconf_ack_param = (void *)asconf_ack_param + length; - asconf_ack_len -= length; + asconf_ack_param = (void *)asconf_ack_param + SCTP_PAD4(length); + asconf_ack_len -= SCTP_PAD4(length); } return err_code; From ac08d183dac0441e41f77bbad50798fe609d90f1 Mon Sep 17 00:00:00 2001 From: Xuanqiang Luo Date: Fri, 28 Aug 2026 09:29:18 +0800 Subject: [PATCH 0191/1198] raw: annotate disconnect-side IPv4 match writers raw_v4_match() reads inet_daddr, inet_rcv_saddr and sk_bound_dev_if locklessly under RCU. Bind and connect writers are annotated, but __udp_disconnect() still clears the same fields using plain stores. Commit 18f116931f52e ("raw: annotate lockless match fields in raw_v4_match()") added the lockless readers and annotated the raw bind and datagram connect writers. Its v4 revision intentionally left the shared disconnect-side IPv4 writers for follow-up cleanup. Complete that follow-up by using WRITE_ONCE() for the disconnect-side stores, including the inet_rcv_saddr reset in inet_reset_saddr(), to pair with the lockless raw socket matcher. Fixes: 0daf07e52709 ("raw: convert raw sockets to RCU") Link: https://lore.kernel.org/netdev/20260716142958.3064224-1-runyu.xiao@seu.edu.cn/ Suggested-by: Runyu Xiao Signed-off-by: Jackie Liu Signed-off-by: Xuanqiang Luo Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20260828012918.1461-1-xuanqiang.luo@linux.dev Signed-off-by: Jakub Kicinski --- include/net/ip.h | 3 ++- net/ipv4/udp.c | 4 ++-- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/include/net/ip.h b/include/net/ip.h index a8f57b4f4aa2..6f602df72ee6 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -704,7 +704,8 @@ static inline void ip_ipgre_mc_map(__be32 naddr, const unsigned char *broadcast, static __inline__ void inet_reset_saddr(struct sock *sk) { - inet_sk(sk)->inet_rcv_saddr = inet_sk(sk)->inet_saddr = 0; + inet_sk(sk)->inet_saddr = 0; + WRITE_ONCE(inet_sk(sk)->inet_rcv_saddr, 0); #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == PF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index af9603217444..6ff5670bf6ed 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2166,10 +2166,10 @@ int __udp_disconnect(struct sock *sk, int flags) */ sk->sk_state = TCP_CLOSE; - inet->inet_daddr = 0; + WRITE_ONCE(inet->inet_daddr, 0); inet->inet_dport = 0; sock_rps_reset_rxhash(sk); - sk->sk_bound_dev_if = 0; + WRITE_ONCE(sk->sk_bound_dev_if, 0); if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) { inet_reset_saddr(sk); if (sk->sk_prot->rehash && From ac8d6b28d48c5d951dcd923d33e461588e762a6d Mon Sep 17 00:00:00 2001 From: James Nugraha Date: Fri, 28 Aug 2026 09:22:19 +1000 Subject: [PATCH 0192/1198] net: amd-xgbe: discard rx packets with bad FCS amd-xgbe driver currently sets the MAC_RCR.DCRCC bit whenever RX is enabled. This disables hardware FCS validation, causing packets with bad FCS to be accepted unconditionally. This change unsets DCRCC so that packets with bad FCS will be dropped, in-line with typical behaviours of many other network controllers. Tests: - Verified that packets with bad FCS are now dropped. - Verified that receiving packets with bad FCS will increment the `rx_crc_errors` counter. Fixes: c5aa9e3b8156 ("amd-xgbe: Initial AMD 10GbE platform driver") Signed-off-by: James Nugraha Link: https://patch.msgid.link/20260827232220.69907-1-aslan.jnn@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/amd/xgbe/xgbe-dev.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index 2de974213090..e2e850c1b90b 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -3400,7 +3400,7 @@ static void xgbe_enable_rx(struct xgbe_prv_data *pdata) XGMAC_IOWRITE(pdata, MAC_RQC0R, reg_val); /* Enable MAC Rx */ - XGMAC_IOWRITE_BITS(pdata, MAC_RCR, DCRCC, 1); + XGMAC_IOWRITE_BITS(pdata, MAC_RCR, DCRCC, 0); XGMAC_IOWRITE_BITS(pdata, MAC_RCR, CST, 1); XGMAC_IOWRITE_BITS(pdata, MAC_RCR, ACS, 1); XGMAC_IOWRITE_BITS(pdata, MAC_RCR, RE, 1); @@ -3411,7 +3411,6 @@ static void xgbe_disable_rx(struct xgbe_prv_data *pdata) unsigned int i; /* Disable MAC Rx */ - XGMAC_IOWRITE_BITS(pdata, MAC_RCR, DCRCC, 0); XGMAC_IOWRITE_BITS(pdata, MAC_RCR, CST, 0); XGMAC_IOWRITE_BITS(pdata, MAC_RCR, ACS, 0); XGMAC_IOWRITE_BITS(pdata, MAC_RCR, RE, 0); From 6cfc1b90cb86f4aabc69fb8e30128e07e2cdfa3a Mon Sep 17 00:00:00 2001 From: Charles Vosburgh Date: Thu, 27 Aug 2026 17:32:53 -0400 Subject: [PATCH 0193/1198] sctp: validate chunk length in the inqueue parser SCTP chunks always include a four-byte generic header, but sctp_inq_pop() currently accepts shorter declared lengths. A zero-length chunk leaves chunk_end at the current header. When ASCONF is covered by the association's SCTP-AUTH policy, sctp_assoc_bh_rcv() can continue before the state machine performs its normal chunk-length check. sctp_inq_pop() then returns the same malformed chunk repeatedly and the receive softirq can lock up. A remote SCTP peer can trigger this after establishing an association on a kernel built with CONFIG_IP_SCTP and configured with net.sctp.addip_enable=1 and net.sctp.auth_enable=1. The reproducer did not require application credentials, a shared SCTP AUTH key, or net.sctp.addip_noauth_enable=1. On commit f967455fb2a5 ("seg6: reset IP6CB after IPv6 decapsulation"), one zero-length ASCONF caused repeated watchdog soft-lockup reports in a two-vCPU KVM guest. All 3 pre-trigger health probes succeeded, while 36 of 37 post-trigger probes failed. With this change, all 37 post-trigger probes succeeded and no equivalent soft-lockup signature appeared. Reject chunks shorter than the generic SCTP header at the shared inqueue parser boundary. Mark the packet for discard before either caller can continue processing it, while preserving the four-byte generic minimum. Declared-length 1 through 4 controls and kernel-generated ASCONF traffic remained healthy. The patched sctp_hello selftest passed for IPv4 and IPv6. The complete private reproducer and validation evidence are available directly to maintainers on request. Fixes: bbd0d59809f9 ("[SCTP]: Implement the receive and verification of AUTH chunk") Cc: stable@vger.kernel.org Signed-off-by: Charles Vosburgh Acked-by: Xin Long Link: https://patch.msgid.link/20260827-sctp-zero-chunk-inqueue-v2-1-2e7669c6a6cb@gmail.com Signed-off-by: Jakub Kicinski --- net/sctp/inqueue.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 5f988b3a8814..d666cec6b194 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -212,8 +212,10 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue) chunk->chunk_end = ((__u8 *)ch) + SCTP_PAD4(ntohs(ch->length)); skb_pull(chunk->skb, sizeof(*ch)); chunk->subh.v = NULL; /* Subheader is no longer valid. */ - - if (chunk->chunk_end + sizeof(*ch) <= skb_tail_pointer(chunk->skb)) { + if (unlikely(ntohs(ch->length) < sizeof(*ch))) { + chunk->pdiscard = 1; + } else if (chunk->chunk_end + sizeof(*ch) <= + skb_tail_pointer(chunk->skb)) { /* This is not a singleton */ chunk->singleton = 0; } else if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) { From 4aa61c88b4e292e10abdfd791334b8272108d68a Mon Sep 17 00:00:00 2001 From: Baul Lee Date: Thu, 27 Aug 2026 02:36:04 +0900 Subject: [PATCH 0194/1198] vxlan: mdb: Fix use-after-free in vxlan_mdb_remote_src_del() vxlan_mdb_is_valid_source(), which validates MDBE_ATTR_SOURCE and every MDBE_ATTR_SRC_LIST member, accepts the all-zeros address. A source list is only accepted on a (*, G) entry, whose source is the all-zeros address, and for each member of the list an (S, G) entry is derived from it by substituting the source. Entries are keyed by a plain memcmp() of struct vxlan_mdb_entry_key, so if MDBE_ATTR_SOURCE is present and holds the all-zeros address and the source list holds it as well, the derived (S, G) key is byte-identical to the (*, G) key and resolves to the same entry. Omitting MDBE_ATTR_SOURCE is not equivalent, as the key is then left with a zero address family. vxlan_mdb_remote_src_del() removes the forwarding entry of a source before freeing the source entry: vxlan_mdb_remote_src_fwd_del(vxlan, group, remote, &ent->addr); vxlan_mdb_remote_src_entry_del(ent); With the keys aliased, the first call deletes the remote of the entry that owns 'ent' instead of a separate (S, G) entry, and frees 'ent'. The second call then runs on the freed entry, and its hlist_del() reads ->pprev and ->next out of it and writes through them. Adding the (*, G) entry with NLM_F_REPLACE and no source list marks the all-zeros source for deletion and reaches this from the sweep at the end of vxlan_mdb_remote_srcs_replace(). BUG: KASAN: slab-use-after-free in __vxlan_mdb_add+0x1cd/0xd70 Read of size 8 at addr ffff888102852500 by task poc/84 __vxlan_mdb_add+0x1cd/0xd70 vxlan_mdb_add+0xc0/0x140 rtnl_mdb_add+0x157/0x2a0 rtnetlink_rcv_msg+0x207/0x5a0 Allocated by task 84: __kmalloc_cache_noprof+0x153/0x360 vxlan_mdb_remote_srcs_add+0x2eb/0x440 __vxlan_mdb_add+0x803/0xd70 Freed by task 84: kfree+0x14c/0x3b0 vxlan_mdb_remote_del+0x129/0x1a0 __vxlan_mdb_del+0x4f/0xe0 vxlan_mdb_remote_src_fwd_del.isra.0+0x162/0x1b0 __vxlan_mdb_add+0x1c5/0xd70 The MDB operations are netns-scoped, so an unprivileged user can perform them in a new user and network namespace. Reject the all-zeros address in vxlan_mdb_is_valid_source(), which covers both call sites. A (*, G) entry is expressed by omitting the source, so nothing legitimate is refused. Discovered by XBOW, triaged by Baul Lee Fixes: a3a48de5eade ("vxlan: mdb: Add MDB control path support") Signed-off-by: Baul Lee Reviewed-by: Ido Schimmel Reviewed-by: Nikolay Aleksandrov Link: https://patch.msgid.link/20260826173604.90158-1-baul.lee@xbow.com Signed-off-by: Jakub Kicinski --- drivers/net/vxlan/vxlan_mdb.c | 8 ++++++++ tools/testing/selftests/net/test_vxlan_mdb.sh | 6 ++++++ 2 files changed, 14 insertions(+) diff --git a/drivers/net/vxlan/vxlan_mdb.c b/drivers/net/vxlan/vxlan_mdb.c index d71e1925ecfd..841f42ffecb9 100644 --- a/drivers/net/vxlan/vxlan_mdb.c +++ b/drivers/net/vxlan/vxlan_mdb.c @@ -354,6 +354,10 @@ static bool vxlan_mdb_is_valid_source(const struct nlattr *attr, __be16 proto, NL_SET_ERR_MSG_MOD(extack, "IPv4 multicast source address is not allowed"); return false; } + if (ipv4_is_zeronet(nla_get_in_addr(attr))) { + NL_SET_ERR_MSG_MOD(extack, "IPv4 all-zeros source address is not allowed"); + return false; + } break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): { @@ -368,6 +372,10 @@ static bool vxlan_mdb_is_valid_source(const struct nlattr *attr, __be16 proto, NL_SET_ERR_MSG_MOD(extack, "IPv6 multicast source address is not allowed"); return false; } + if (ipv6_addr_any(&src)) { + NL_SET_ERR_MSG_MOD(extack, "IPv6 all-zeros source address is not allowed"); + return false; + } break; } #endif diff --git a/tools/testing/selftests/net/test_vxlan_mdb.sh b/tools/testing/selftests/net/test_vxlan_mdb.sh index 58da5de99ac4..f9600aabd4a2 100755 --- a/tools/testing/selftests/net/test_vxlan_mdb.sh +++ b/tools/testing/selftests/net/test_vxlan_mdb.sh @@ -685,6 +685,9 @@ star_g_common() run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp permanent filter_mode exclude source_list $grp dst $vtep_ip src_vni 10010" log_test $? 255 "Invalid source in source list" + run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp permanent filter_mode exclude source_list $all_zeros_grp dst $vtep_ip src_vni 10010" + log_test $? 255 "All-zeros source in source list" + run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp permanent source_list $src1 dst $vtep_ip src_vni 10010" log_test $? 255 "Source list without filter mode" } @@ -784,6 +787,9 @@ sg_common() run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp src $grp permanent dst $vtep_ip src_vni 10010" log_test $? 255 "(S, G) with an invalid source list" + run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp src $all_zeros_grp permanent dst $vtep_ip src_vni 10010" + log_test $? 255 "(S, G) with an all-zeros source" + run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $all_zeros_grp src $src permanent dst $vtep_ip src_vni 10010" log_test $? 255 "All-zeros group with source" } From a8455260b2e9c024d1872ac1c094793d55a7e537 Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Fri, 28 Aug 2026 18:49:18 +0200 Subject: [PATCH 0195/1198] ipvlan: unregister upper devices outside pnodes_lock syzbot reported the following circular locking dependency: xs->mutex -> netdev lock -> pnodes_lock -> net->xdp.lock -> xs->mutex The pnodes_lock -> net->xdp.lock edge is recorded when ipvlan_device_event(NETDEV_UNREGISTER) calls unregister_netdevice_many() while holding pnodes_lock. A nested NETDEV_UNREGISTER notification for an IPvlan device enters xsk_notifier(), which acquires net->xdp.lock. Keep pnodes_lock only while marking the upper devices as dying, removing them from port->ipvlans, and queueing them for unregistration. Once the devices have been detached from the protected list, release pnodes_lock before unregister_netdevice_many() invokes notifier callbacks. The port remains alive across unregistration because ipvlan_device_event() holds the reference acquired by ipvlan_port_get(). The dying flag prevents a concurrent ->dellink() callback from deleting a queued device again. Fixes: 35add1093e2f ("ipvlan: Protect ipvl_port.ipvlans with mutex.") Reported-by: syzbot+aa48b5fe7bfda62d1682@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=aa48b5fe7bfda62d1682 Signed-off-by: Maciej Fijalkowski Reviewed-by: Eric Dumazet Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20260828164918.451364-1-maciej.fijalkowski@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ipvlan/ipvlan_main.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 4939cf67b336..f29864db662a 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -848,7 +848,6 @@ static int ipvlan_device_event(struct notifier_block *unused, __ipvlan_link_delete(net, ipvlan->dev, &lst_kill); } - unregister_netdevice_many(&lst_kill); break; } case NETDEV_FEAT_CHANGE: @@ -899,6 +898,9 @@ static int ipvlan_device_event(struct notifier_block *unused, mutex_unlock(&port->pnodes_lock); + /* Avoid invoking nested netdevice notifiers under pnodes_lock. */ + unregister_netdevice_many(&lst_kill); + ipvlan_port_put(port); return ret; From aab55360fa11a2c054798a484ac67ad606f563e4 Mon Sep 17 00:00:00 2001 From: James Hilliard Date: Thu, 27 Aug 2026 22:42:31 -0600 Subject: [PATCH 0196/1198] watchdog: sunxi_wdt: preserve boot-enabled watchdog sunxi_wdt_probe() unconditionally stops the watchdog even when firmware left it running. This opens an unprotected interval during boot and prevents CONFIG_WATCHDOG_HANDLE_BOOT_ENABLED from taking over the active watchdog. Detect an enabled watchdog and decode its programmed interval. Preserve representable timeouts, and round the 0.5-second interval up to the minimum representable one-second timeout. Use the configured timeout for reserved interval encodings. Set the Linux reset mode and ping the watchdog without clearing its enable bit, then mark it hardware-running before registration so the watchdog core services it until userspace takes control. Leave disabled watchdogs untouched. Fixes: d00680ed0026 ("watchdog: sunxi: New watchdog driver for Allwinner A10/A13") Cc: stable@vger.kernel.org Signed-off-by: James Hilliard Link: https://patch.msgid.link/20260827-submit-sunxi-wdt-boot-enabled-v1-v2-1-610d37dccc97@gmail.com Signed-off-by: Guenter Roeck --- drivers/watchdog/sunxi_wdt.c | 45 +++++++++++++++++++++++++++++++++++- 1 file changed, 44 insertions(+), 1 deletion(-) diff --git a/drivers/watchdog/sunxi_wdt.c b/drivers/watchdog/sunxi_wdt.c index b6c761acc3de..3db34524ed13 100644 --- a/drivers/watchdog/sunxi_wdt.c +++ b/drivers/watchdog/sunxi_wdt.c @@ -128,6 +128,38 @@ static int sunxi_wdt_ping(struct watchdog_device *wdt_dev) return 0; } +static bool sunxi_wdt_is_running(struct watchdog_device *wdt_dev) +{ + struct sunxi_wdt_dev *sunxi_wdt = watchdog_get_drvdata(wdt_dev); + const struct sunxi_wdt_reg *regs = sunxi_wdt->wdt_regs; + + return readl(sunxi_wdt->wdt_base + regs->wdt_mode) & WDT_MODE_EN; +} + +static unsigned int sunxi_wdt_get_timeout(struct watchdog_device *wdt_dev) +{ + struct sunxi_wdt_dev *sunxi_wdt = watchdog_get_drvdata(wdt_dev); + const struct sunxi_wdt_reg *regs = sunxi_wdt->wdt_regs; + unsigned int timeout; + u32 interval; + + interval = readl(sunxi_wdt->wdt_base + regs->wdt_mode); + interval >>= regs->wdt_timeout_shift; + interval &= WDT_TIMEOUT_MASK; + /* Round the 0.5-second interval up to the minimum representable timeout. */ + if (!interval) + return WDT_MIN_TIMEOUT; + + for (timeout = WDT_MIN_TIMEOUT; + timeout < ARRAY_SIZE(wdt_timeout_map); timeout++) { + if (wdt_timeout_map[timeout] == interval) + return timeout; + } + + /* Reserved interval encoding. */ + return 0; +} + static int sunxi_wdt_set_timeout(struct watchdog_device *wdt_dev, unsigned int timeout) { @@ -259,6 +291,7 @@ static int sunxi_wdt_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct sunxi_wdt_dev *sunxi_wdt; + unsigned int running_timeout; int err; sunxi_wdt = devm_kzalloc(dev, sizeof(*sunxi_wdt), GFP_KERNEL); @@ -286,7 +319,17 @@ static int sunxi_wdt_probe(struct platform_device *pdev) watchdog_set_drvdata(&sunxi_wdt->wdt_dev, sunxi_wdt); - sunxi_wdt_stop(&sunxi_wdt->wdt_dev); + if (sunxi_wdt_is_running(&sunxi_wdt->wdt_dev)) { + running_timeout = sunxi_wdt_get_timeout(&sunxi_wdt->wdt_dev); + if (running_timeout) + sunxi_wdt->wdt_dev.timeout = running_timeout; + + err = sunxi_wdt_start(&sunxi_wdt->wdt_dev); + if (err) + return err; + + set_bit(WDOG_HW_RUNNING, &sunxi_wdt->wdt_dev.status); + } watchdog_stop_on_reboot(&sunxi_wdt->wdt_dev); err = devm_watchdog_register_device(dev, &sunxi_wdt->wdt_dev); From e3eceb76515910746e6268c4e4ac1c07516ebd7b Mon Sep 17 00:00:00 2001 From: Tzung-Bi Shih Date: Thu, 27 Aug 2026 04:46:59 +0000 Subject: [PATCH 0197/1198] watchdog: msc313e: Fix NULL pointer dereference in PM callbacks msc313e_wdt_probe() doesn't set the driver data for the platform device. As a result, dev_get_drvdata() in msc313e_wdt_suspend() and msc313e_wdt_resume() will return NULL, leading to a NULL pointer dereference afterward. Set the platform device driver data in msc313e_wdt_probe(). Fixes: e9800b799464 ("watchdog: Add Mstar MSC313e WDT driver") Signed-off-by: Tzung-Bi Shih Link: https://patch.msgid.link/20260827044700.554333-2-tzungbi@kernel.org Signed-off-by: Guenter Roeck --- drivers/watchdog/msc313e_wdt.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/watchdog/msc313e_wdt.c b/drivers/watchdog/msc313e_wdt.c index d962589e2c55..f69d66971c41 100644 --- a/drivers/watchdog/msc313e_wdt.c +++ b/drivers/watchdog/msc313e_wdt.c @@ -124,6 +124,7 @@ static int msc313e_wdt_probe(struct platform_device *pdev) set_bit(WDOG_HW_RUNNING, &priv->wdev.status); watchdog_set_drvdata(&priv->wdev, priv); + platform_set_drvdata(pdev, priv); watchdog_init_timeout(&priv->wdev, timeout, dev); watchdog_stop_on_reboot(&priv->wdev); From 72bd92bd8190d7869ecb462649ca40f297822a33 Mon Sep 17 00:00:00 2001 From: Jason Andryuk Date: Tue, 25 Aug 2026 17:48:02 -0400 Subject: [PATCH 0198/1198] x86/amd_node: Avoid divide by zero on virtualized systems On a virtualized system, the number of nodes does not have a relationship to the number of roots. A Xen PVH dom0 can calculate roots_per_node as 0, which crashes with a divide by zero in: if (count++ % roots_per_node) because the underlying topology code on Xen ends up making num_nodes 2 and num_roots 1 and the integer division result is 0. The issue is seen with Xen, but it could affect other systems. Set roots_per_node to 1 in this case. Print a firmware bug when this is performed for non-virtualized systems. [ bp: Massage commit message. ] Fixes: 0a4b61d9c2e4 ("x86/amd_node: Fix AMD root device caching") Suggested-by: Borislav Petkov Signed-off-by: Jason Andryuk Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Yazen Ghannam Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260825214805.39148-2-jason.andryuk@amd.com --- arch/x86/kernel/amd_node.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/x86/kernel/amd_node.c b/arch/x86/kernel/amd_node.c index 0be01725a2a4..408b9fd48349 100644 --- a/arch/x86/kernel/amd_node.c +++ b/arch/x86/kernel/amd_node.c @@ -287,6 +287,11 @@ static int __init amd_smn_init(void) return -ENOMEM; roots_per_node = num_roots / num_nodes; + if (!roots_per_node) { + if (!cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) + pr_warn(FW_BUG "Error detecting roots per node.\n"); + roots_per_node = 1; + } count = 0; node = 0; From ae9464c65e9d1ad4df4fed516cee9bca3bc614cc Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 25 Aug 2026 09:23:45 +0300 Subject: [PATCH 0199/1198] perf symbol: Do not use debug file as the binary type dso__load() sets the binary type of a DSO to the type of the first symbol source found. For a DSO with a separate debug file linked via .gnu-debuglink, that is DSO_BINARY_TYPE__DEBUGLINK, which makes dso__get_filename() return the name of the debug file instead of the file that was actually executed. Consumers that need to read instruction bytes, such as Intel PT decoding in 'perf script', then read from the debug file and produce wrong instructions. Prefer DSO_BINARY_TYPE__BUILD_ID_CACHE, and otherwise DSO_BINARY_TYPE__SYSTEM_PATH_DSO, over debug-only types, which restores the behaviour of using a file that contains the executed instructions. This is a workaround. Properly separating the binary file used for instructions from the file used for debug symbols is left for later. Example: Create a shared object with a separate .gnu_debuglink debug file. Note that 'objcopy --only-keep-debug' leaves .text as NOBITS, so instructions read from the debug file are zeros: # cat > foo.c << EOF unsigned long foo_work(unsigned long n) { unsigned long s = 0; for (unsigned long i = 0; i < n; i++) s = s * 31 + i; return s; } EOF # cat > main.c << EOF #include unsigned long foo_work(unsigned long n); int main(void) { printf("%lu\n", foo_work(1000)); return 0; } EOF # gcc -g -O2 -shared -fPIC -o libfoo.so foo.c # gcc -g -O2 -o main main.c -L. -lfoo -Wl,-rpath,'$ORIGIN' # objcopy --only-keep-debug libfoo.so libfoo.so.debug # objcopy --strip-debug libfoo.so # objcopy --add-gnu-debuglink=libfoo.so.debug libfoo.so # perf record -e intel_pt//u ./main Note that branch samples must be requested, because it is the resolving of the branch target symbol that causes dso__load() to be called, and hence the binary type to be set, before the decoder walks the code. With '--itrace=e' alone, nothing loads symbols for libfoo.so, the binary type is left as DSO_BINARY_TYPE__NOT_FOUND, the correct file is read anyway, and no errors are reported either way. Before: # perf.before script --itrace=be 2>&1 | grep "instruction trace error" instruction trace error type 1 time 2350.467489498 cpu 9 pid 75634 tid 75634 ip 0x77d48480718f code 6: Trace doesn't match instruction instruction trace error type 1 time 2350.467489832 cpu 9 pid 75634 tid 75634 ip 0x77d484807341 code 6: Trace doesn't match instruction instruction trace error type 1 time 2350.467496412 cpu 9 pid 75634 tid 75634 ip 0x5b4de37a8074 code 6: Trace doesn't match instruction instruction trace error type 1 time 2350.467593393 cpu 9 pid 75634 tid 75634 ip 0x77d4848070d0 code 6: Trace doesn't match instruction instruction trace error type 1 time 2350.467593954 cpu 9 pid 75634 tid 75634 ip 0x77d4848075a8 code 6: Trace doesn't match instruction instruction trace error type 1 time 2350.467595728 cpu 9 pid 75634 tid 75634 ip 0x77d4848324de code 6: Trace doesn't match instruction 6 instruction trace errors After: # perf script --itrace=be 2>&1 | grep "instruction trace error" # Fixes: 5363c306787c8 ("perf symbol: Set binary_type of dso when loading") Reported-by: Todd Lipcon Closes: https://lore.kernel.org/all/CAGH6UiG=RJLqBU3kLu9XJciPyPO1HZkbAPERguVUMRuWQgqf=A@mail.gmail.com/ Signed-off-by: Adrian Hunter Signed-off-by: Namhyung Kim --- tools/perf/util/symbol.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 94f9c8faedda..3587ad243159 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1947,7 +1947,16 @@ int dso__load(struct dso *dso, struct map *map) if (next_slot) { ss_pos++; - if (dso__binary_type(dso) == DSO_BINARY_TYPE__NOT_FOUND) + /* + * The binary type is used to find the file containing + * the executed instructions, so prefer the types that + * refer to the actual object over debug-only files such + * as DSO_BINARY_TYPE__DEBUGLINK. + */ + if (dso__binary_type(dso) == DSO_BINARY_TYPE__NOT_FOUND || + symtab_type == DSO_BINARY_TYPE__BUILD_ID_CACHE || + (symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_DSO && + dso__binary_type(dso) != DSO_BINARY_TYPE__BUILD_ID_CACHE)) dso__set_binary_type(dso, symtab_type); if (syms_ss && runtime_ss) From e11811a552252740bd396ec38378e9570ee16578 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Wed, 26 Aug 2026 14:19:57 +0100 Subject: [PATCH 0200/1198] OPP: of: Fix potential multiplication overflow when calculating freq The multiplication be32_to_cpup(val++) * 1000 is performed using 32 bit unsigned integers and hence uses a 32 bit multiplication; this will overflow if be32_to_cpup(val++) is greater than 4294967 (which is very unlikely at present). The result is assigned to an unsigned long (which is a 64 bit value on 64 bit systems), so fix this potential overflow by casting the first operand of the multiplication to an unsigned int. Fixes: b496dfbc94ab ("PM / OPP: Initialize OPP table from device tree") Signed-off-by: Colin Ian King Signed-off-by: Viresh Kumar --- drivers/opp/of.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/opp/of.c b/drivers/opp/of.c index c02e20632fa6..9c4fd1f0e944 100644 --- a/drivers/opp/of.c +++ b/drivers/opp/of.c @@ -1039,7 +1039,7 @@ static int _of_add_opp_table_v1(struct device *dev, struct opp_table *opp_table) val = prop->value; while (nr) { - unsigned long freq = be32_to_cpup(val++) * 1000; + unsigned long freq = (unsigned long)be32_to_cpup(val++) * 1000; unsigned long volt = be32_to_cpup(val++); struct dev_pm_opp_data data = { .freq = freq, From a5096d4927d1eb607d51a7342a7e7591a3838c19 Mon Sep 17 00:00:00 2001 From: Sumeet Pawnikar Date: Sat, 29 Aug 2026 19:19:24 +0530 Subject: [PATCH 0201/1198] opp: Use %pe to print symbolic error name Replace PTR_ERR() and %ld with %pe and pass the original pointer directly to dev_dbg(), dev_warn(), dev_err() or pr_err(). The %pe format specifier prints a symbolic error name (e.g. -ENOMEM) when CONFIG_SYMBOLIC_ERRNAME is enabled, otherwise it falls back gracefully and prints the raw integer value. This makes error messages more readable without any functional change. Signed-off-by: Sumeet Pawnikar Signed-off-by: Viresh Kumar --- drivers/opp/core.c | 24 ++++++++++++------------ drivers/opp/of.c | 4 ++-- 2 files changed, 14 insertions(+), 14 deletions(-) diff --git a/drivers/opp/core.c b/drivers/opp/core.c index cd0e82dae776..1e3b80a1f88e 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -453,8 +453,8 @@ int dev_pm_opp_get_opp_count(struct device *dev) _find_opp_table(dev); if (IS_ERR(opp_table)) { - dev_dbg(dev, "%s: OPP table not found (%ld)\n", - __func__, PTR_ERR(opp_table)); + dev_dbg(dev, "%s: OPP table not found (%pe)\n", + __func__, opp_table); return PTR_ERR(opp_table); } @@ -611,8 +611,8 @@ _find_key(struct device *dev, unsigned long *key, int index, bool available, _find_opp_table(dev); if (IS_ERR(opp_table)) { - dev_err(dev, "%s: OPP table not found (%ld)\n", __func__, - PTR_ERR(opp_table)); + dev_err(dev, "%s: OPP table not found (%pe)\n", __func__, + opp_table); return ERR_CAST(opp_table); } @@ -722,8 +722,8 @@ struct dev_pm_opp *dev_pm_opp_find_key_exact(struct device *dev, struct opp_table *opp_table __free(put_opp_table) = _find_opp_table(dev); if (IS_ERR(opp_table)) { - dev_err(dev, "%s: OPP table not found (%ld)\n", __func__, - PTR_ERR(opp_table)); + dev_err(dev, "%s: OPP table not found (%pe)\n", __func__, + opp_table); return ERR_CAST(opp_table); } @@ -1036,8 +1036,8 @@ static int _set_opp_voltage(struct device *dev, struct regulator *reg, /* Regulator not available for device */ if (IS_ERR(reg)) { - dev_dbg(dev, "%s: regulator not available: %ld\n", __func__, - PTR_ERR(reg)); + dev_dbg(dev, "%s: regulator not available: %pe\n", __func__, + reg); return 0; } @@ -1448,8 +1448,8 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) temp_freq = freq; opp = _find_freq_ceil(opp_table, &temp_freq); if (IS_ERR(opp)) { - dev_err(dev, "%s: failed to find OPP for freq %lu (%ld)\n", - __func__, freq, PTR_ERR(opp)); + dev_err(dev, "%s: failed to find OPP for freq %lu (%pe)\n", + __func__, freq, opp); return PTR_ERR(opp); } @@ -2869,8 +2869,8 @@ static int _opp_set_availability(struct device *dev, unsigned long freq, struct dev_pm_opp *opp __free(put_opp) = ERR_PTR(-ENODEV), *tmp_opp; if (IS_ERR(opp_table)) { - dev_warn(dev, "%s: Device OPP not found (%ld)\n", __func__, - PTR_ERR(opp_table)); + dev_warn(dev, "%s: Device OPP not found (%pe)\n", __func__, + opp_table); return PTR_ERR(opp_table); } diff --git a/drivers/opp/of.c b/drivers/opp/of.c index 9c4fd1f0e944..2f3bbde9a9e1 100644 --- a/drivers/opp/of.c +++ b/drivers/opp/of.c @@ -1345,8 +1345,8 @@ int of_get_required_opp_performance_state(struct device_node *np, int index) _find_table_of_opp_np(required_np); if (IS_ERR(opp_table)) { - pr_err("%s: Failed to find required OPP table %pOF: %ld\n", - __func__, np, PTR_ERR(opp_table)); + pr_err("%s: Failed to find required OPP table %pOF: %pe\n", + __func__, np, opp_table); return PTR_ERR(opp_table); } From aadea57f532882d8bab444646863c7ef8a778ff1 Mon Sep 17 00:00:00 2001 From: Wang Yan Date: Tue, 25 Aug 2026 17:47:33 +0800 Subject: [PATCH 0202/1198] perf powerpc-vpadtl: Fix raw_size of DTL samples In powerpc_vpadtl_sample(), raw_data of the synthetic sample points to a struct powerpc_vpadtl_entry (48 bytes), but raw_size is set to sizeof(record). record is a struct powerpc_vpadtl_entry pointer, so sizeof(record) is the size of the pointer (8 bytes on 64-bit) rather than the size of the record itself. As a result, consumers that bound their access to raw_data by raw_size only see or copy the first 8 bytes of each DTL entry instead of the full record. Use sizeof(*record) so that raw_size reflects the actual length of the raw data. Fixes: 8644834a482a ("perf powerpc: Process the DTL entries in queue and deliver samples") Signed-off-by: Wang Yan Reviewed-by: Athira Rajeev Reviewed-by: Arnaldo Carvalho de Melo Signed-off-by: Namhyung Kim --- tools/perf/util/powerpc-vpadtl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/powerpc-vpadtl.c b/tools/perf/util/powerpc-vpadtl.c index 710f3093f3f9..af6783cfdb53 100644 --- a/tools/perf/util/powerpc-vpadtl.c +++ b/tools/perf/util/powerpc-vpadtl.c @@ -196,7 +196,7 @@ static int powerpc_vpadtl_sample(struct powerpc_vpadtl_entry *record, sample.cpumode = PERF_RECORD_MISC_KERNEL; sample.time = save; sample.raw_data = record; - sample.raw_size = sizeof(record); + sample.raw_size = sizeof(*record); event.sample.header.type = PERF_RECORD_SAMPLE; event.sample.header.misc = sample.cpumode; event.sample.header.size = sizeof(struct perf_event_header); From a1530ef451f53b63dcf4a2805a5524b590a146ad Mon Sep 17 00:00:00 2001 From: Linmao Li Date: Tue, 18 Aug 2026 10:09:33 +0800 Subject: [PATCH 0203/1198] media: rppx1: describe the MAIN_POST white balance gains block MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit rppx1_ext_params_blocks_info[] is indexed by block type and is built with designated initialisers, so a block type without an entry is left as a zero-sized hole. RPPX1_PARAMS_BLOCK_TYPE_AWBG_POST is the only such hole: a block reporting that type and a size of zero passes v4l2_isp_params_validate_buffer(), which then has nothing to advance the walk with. Describe the block, so the array covers all block types the uAPI defines. The MAIN_POST white balance gains module is probed and started with the rest of the POST pipe, and RPPX1_PARAMS_MAX_SIZE already reserves room for all three white balance gains blocks. The block is not dispatched by rppx1_params(), in line with the other described blocks that have no users yet. Reviewed-by: Niklas Söderlund Reviewed-by: Jacopo Mondi Signed-off-by: Linmao Li Signed-off-by: Jacopo Mondi Signed-off-by: Hans Verkuil --- drivers/media/platform/dreamchip/rppx1/rpp_params.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/platform/dreamchip/rppx1/rpp_params.c b/drivers/media/platform/dreamchip/rppx1/rpp_params.c index a75a27a8afd0..5e6727d58946 100644 --- a/drivers/media/platform/dreamchip/rppx1/rpp_params.c +++ b/drivers/media/platform/dreamchip/rppx1/rpp_params.c @@ -25,6 +25,7 @@ rppx1_ext_params_blocks_info[] = { RPPX1_PARAMS_BLOCK_INFO(LSC_PRE2, lsc), RPPX1_PARAMS_BLOCK_INFO(AWBG_PRE1, awbg), RPPX1_PARAMS_BLOCK_INFO(AWBG_PRE2, awbg), + RPPX1_PARAMS_BLOCK_INFO(AWBG_POST, awbg), RPPX1_PARAMS_BLOCK_INFO(CCOR_POST, ccor), RPPX1_PARAMS_BLOCK_INFO(HIST_PRE1, hist), RPPX1_PARAMS_BLOCK_INFO(HIST_PRE2, hist), From e04ffff543db06308a8100f6aa3a65aebcd9834c Mon Sep 17 00:00:00 2001 From: Linmao Li Date: Tue, 18 Aug 2026 17:59:29 +0800 Subject: [PATCH 0204/1198] media: rppx1: bls: read the raw pattern from the PRE2 acquisition module MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit rppx1_bls_swap_regs() gets the Bayer pattern from the acquisition module. The PRE1 path uses pre1.acq, but the PRE2 path mistakenly uses pre2.bls. The BLS module does not store a Bayer pattern, so PRE2 would read zero (RGGB) and map fixed black levels to the wrong colour registers. PRE2 is not started or dispatched yet, so the bug is currently latent. Read the pattern from pre2.acq, as the PRE1 path does, so that enabling PRE2 does not start out with the wrong register mapping. Signed-off-by: Linmao Li Reviewed-by: Niklas Söderlund Reviewed-by: Jacopo Mondi Signed-off-by: Jacopo Mondi Signed-off-by: Hans Verkuil --- drivers/media/platform/dreamchip/rppx1/rppx1_bls.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/platform/dreamchip/rppx1/rppx1_bls.c b/drivers/media/platform/dreamchip/rppx1/rppx1_bls.c index 01a61db279bf..71c5561457d5 100644 --- a/drivers/media/platform/dreamchip/rppx1/rppx1_bls.c +++ b/drivers/media/platform/dreamchip/rppx1/rppx1_bls.c @@ -70,7 +70,7 @@ rppx1_bls_swap_regs(struct rpp_module *mod, const u32 input[4], u32 output[4]) /* Swap to pattern used in our path, PRE1 or PRE2. */ struct rpp_module *acq = mod == &mod->rpp->pre1.bls ? - &mod->rpp->pre1.acq : &mod->rpp->pre2.bls; + &mod->rpp->pre1.acq : &mod->rpp->pre2.acq; enum rpp_raw_pattern pattern = acq->info.acq.raw_pattern; for (unsigned int i = 0; i < 4; ++i) From b12e20c6ac156a307acdf0545432eb3b6cb41f8f Mon Sep 17 00:00:00 2001 From: Ahmet Eray Karadag Date: Mon, 15 Dec 2025 06:14:34 +0300 Subject: [PATCH 0205/1198] adfs: fix memory leak in sb->s_fs_info Syzbot reported a memory leak in adfs during the mount process. The issue arises because the ownership of the allocated (struct adfs_sb_info) is transferred from the filesystem context to the superblock via sget_fc(). This function sets fc->s_fs_info to NULL after the transfer. The ADFS filesystem previously used the default kill_block_super for superblock destruction. This helper performs generic cleanup but does not free the private sb->s_fs_info data. Since fc->s_fs_info is set to NULL during the transfer, the standard context cleanup (adfs_free_fc) also skips freeing this memory. As a result, if the superblock is destroyed, the allocated struct adfs_sb_info is leaked. Fix this by implementing a custom .kill_sb callback (adfs_kill_sb) that explicitly frees sb->s_fs_info before invoking the generic kill_block_super. Reported-by: syzbot+1c70732df5fd4f0e4fbb@syzkaller.appspotmail.com Signed-off-by: Ahmet Eray Karadag Link: https://patch.msgid.link/20251215031433.182205-2-eraykrdg1@gmail.com Signed-off-by: Christian Brauner (Amutable) --- fs/adfs/super.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/fs/adfs/super.c b/fs/adfs/super.c index a4cd0a5159dd..888aa81a6b39 100644 --- a/fs/adfs/super.c +++ b/fs/adfs/super.c @@ -92,10 +92,7 @@ static int adfs_checkdiscrecord(struct adfs_discrecord *dr) static void adfs_put_super(struct super_block *sb) { - struct adfs_sb_info *asb = ADFS_SB(sb); - adfs_free_map(sb); - kfree_rcu(asb, rcu); } static int adfs_show_options(struct seq_file *seq, struct dentry *root) @@ -365,7 +362,7 @@ static int adfs_fill_super(struct super_block *sb, struct fs_context *fc) ret = -EINVAL; } if (ret) - goto error; + return ret; /* set up enough so that we can read an inode */ sb->s_op = &adfs_sops; @@ -406,15 +403,9 @@ static int adfs_fill_super(struct super_block *sb, struct fs_context *fc) if (!sb->s_root) { adfs_free_map(sb); adfs_error(sb, "get root inode failed\n"); - ret = -EIO; - goto error; + return -EIO; } return 0; - -error: - sb->s_fs_info = NULL; - kfree(asb); - return ret; } static int adfs_get_tree(struct fs_context *fc) @@ -465,10 +456,19 @@ static int adfs_init_fs_context(struct fs_context *fc) return 0; } +static void adfs_kill_sb(struct super_block *sb) +{ + struct adfs_sb_info *asb = ADFS_SB(sb); + + kill_block_super(sb); + + kfree_rcu(asb, rcu); +} + static struct file_system_type adfs_fs_type = { .owner = THIS_MODULE, .name = "adfs", - .kill_sb = kill_block_super, + .kill_sb = adfs_kill_sb, .fs_flags = FS_REQUIRES_DEV, .init_fs_context = adfs_init_fs_context, .parameters = adfs_param_spec, From f18e8774f4d3137fa0a5fb8ffa83d59a719666d8 Mon Sep 17 00:00:00 2001 From: Karl Mehltretter Date: Thu, 27 Aug 2026 14:42:54 +0100 Subject: [PATCH 0206/1198] netfs: Fix uninitialized return value in netfs_unbuffered_write() If preparation of the first subrequest fails, netfs_unbuffered_write() exits its loop before ret is initialized. The empty-iterator check can do the same. For synchronous writes, netfs_unbuffered_write_iter_locked() may then return an unrelated error instead of wreq->error. This is reachable through CIFS if cifs_prepare_write() fails to reopen the file or obtain credits. Initialize ret to 0 so the caller returns wreq->error if no data was written, or the number of bytes already written otherwise. Found with Clang's -Wconditional-uninitialized. Fixes: a0b4c7a49137e ("netfs: Fix unbuffered/DIO writes to dispatch subrequests in strict sequence") Cc: stable@vger.kernel.org Signed-off-by: Karl Mehltretter Signed-off-by: David Howells Link: https://patch.msgid.link/20260827134304.2075713-2-dhowells@redhat.com Acked-by: Paulo Alcantara Signed-off-by: Christian Brauner (Amutable) --- fs/netfs/direct_write.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c index c16fbad286a1..b04019097ab8 100644 --- a/fs/netfs/direct_write.c +++ b/fs/netfs/direct_write.c @@ -95,7 +95,7 @@ static int netfs_unbuffered_write(struct netfs_io_request *wreq) { struct netfs_io_subrequest *subreq = NULL; struct netfs_io_stream *stream = &wreq->io_streams[0]; - int ret; + int ret = 0; _enter("%llx", wreq->len); From c753a33664e4e86246f7491a93d9a77c1a673b5d Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 27 Aug 2026 14:42:55 +0100 Subject: [PATCH 0207/1198] netfs: Fix unbuffered/DIO write partial transfer error return Fix unbuffered/DIO write to return the amount of data transferred in preference to an error if a partial transfer has been achieved, and to prefer an error stashed in the request over the one returned by netfs_unbuffered_write() (likely -EINTR or -ERESTARTSYS). Fixes: a0b4c7a49137e ("netfs: Fix unbuffered/DIO writes to dispatch subrequests in strict sequence") Link: https://sashiko.dev/#/patchset/20260824120224.504575-1-dhowells%40redhat.com Signed-off-by: David Howells Link: https://patch.msgid.link/20260827134304.2075713-3-dhowells@redhat.com Acked-by: Paulo Alcantara cc: Paulo Alcantara cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner (Amutable) --- fs/netfs/direct_write.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c index b04019097ab8..544a4243fc59 100644 --- a/fs/netfs/direct_write.c +++ b/fs/netfs/direct_write.c @@ -139,13 +139,11 @@ static int netfs_unbuffered_write(struct netfs_io_request *wreq) if (test_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) { retry = true; } else if (test_bit(NETFS_SREQ_FAILED, &subreq->flags)) { - ret = subreq->error; - wreq->error = ret; + wreq->error = subreq->error; netfs_see_subrequest(subreq, netfs_sreq_trace_see_failed); subreq = NULL; break; } - ret = 0; if (!retry) { netfs_unbuffered_write_collect(wreq, stream, subreq); @@ -288,11 +286,11 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter * ret = -EIOCBQUEUED; } else { ret = netfs_unbuffered_write(wreq); - if (ret < 0) { - _debug("begin = %zd", ret); - } else { + if (wreq->transferred) { iocb->ki_pos += wreq->transferred; - ret = wreq->transferred ?: wreq->error; + ret = wreq->transferred; + } else if (wreq->error) { + ret = wreq->error; } netfs_put_request(wreq, netfs_rreq_trace_put_complete); From 0bfe2571a6af653611860d0e24c4e4c83bae7a54 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 27 Aug 2026 14:42:56 +0100 Subject: [PATCH 0208/1198] netfs: Fix error vs transferred passed to ->ki_complete() Fix netfs_unbuffered_write_done() to pass the amount written to ->ki_complete() rather than the error in the event of a partially complete transfer. Fixes: a0b4c7a49137e ("netfs: Fix unbuffered/DIO writes to dispatch subrequests in strict sequence") Link: https://sashiko.dev/#/patchset/20260824120224.504575-1-dhowells%40redhat.com Signed-off-by: David Howells Link: https://patch.msgid.link/20260827134304.2075713-4-dhowells@redhat.com Acked-by: Paulo Alcantara cc: Paulo Alcantara cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner (Amutable) --- fs/netfs/direct_write.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c index 544a4243fc59..f7d7e1b54653 100644 --- a/fs/netfs/direct_write.c +++ b/fs/netfs/direct_write.c @@ -51,7 +51,7 @@ static void netfs_unbuffered_write_done(struct netfs_io_request *wreq) wreq->iocb->ki_pos += written; if (wreq->iocb->ki_complete) { trace_netfs_rreq(wreq, netfs_rreq_trace_ki_complete); - wreq->iocb->ki_complete(wreq->iocb, wreq->error ?: written); + wreq->iocb->ki_complete(wreq->iocb, written ?: wreq->error); } wreq->iocb = VFS_PTR_POISON; } From 741416a8003b77e636dafade408f808d96ac3f47 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 27 Aug 2026 14:42:57 +0100 Subject: [PATCH 0209/1198] netfs: Fix i_size update for partial transfer Fix netfs_unbuffered_write_done() to pass the amount written to netfs_update_i_size() in the event of a partial transfer that ends in an error. That said, it might be better for the filesystem to mark the inode data as invalid and recheck it in case something like a network error occurred that prevented the reply from the server from being received. Fixes: a0b4c7a49137e ("netfs: Fix unbuffered/DIO writes to dispatch subrequests in strict sequence") Link: https://sashiko.dev/#/patchset/20260824120224.504575-1-dhowells%40redhat.com Signed-off-by: David Howells Link: https://patch.msgid.link/20260827134304.2075713-5-dhowells@redhat.com Acked-by: Paulo Alcantara cc: Paulo Alcantara cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner (Amutable) --- fs/netfs/direct_write.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c index f7d7e1b54653..f33ccddaa826 100644 --- a/fs/netfs/direct_write.c +++ b/fs/netfs/direct_write.c @@ -21,7 +21,7 @@ static void netfs_unbuffered_write_done(struct netfs_io_request *wreq) /* Okay, declare that all I/O is complete. */ trace_netfs_rreq(wreq, netfs_rreq_trace_write_done); - if (!wreq->error) + if (wreq->transferred) netfs_update_i_size(ictx, &ictx->inode, wreq->start, wreq->transferred); if (wreq->origin == NETFS_DIO_WRITE && From 3c30087e27598d9d359763e8be9bd3017fe08348 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 27 Aug 2026 14:42:58 +0100 Subject: [PATCH 0210/1198] netfs: Fix subreq ref leak Fix a subrequest ref leak in netfs_unbuffered_write() in the event that subreq->io_iter ends up zero length during preparation. Fixes: a0b4c7a49137e ("netfs: Fix unbuffered/DIO writes to dispatch subrequests in strict sequence") Link: https://sashiko.dev/#/patchset/20260824120224.504575-1-dhowells%40redhat.com Signed-off-by: David Howells Link: https://patch.msgid.link/20260827134304.2075713-6-dhowells@redhat.com Acked-by: Paulo Alcantara cc: Paulo Alcantara cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner (Amutable) --- fs/netfs/direct_write.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c index f33ccddaa826..fbcfadb232ee 100644 --- a/fs/netfs/direct_write.c +++ b/fs/netfs/direct_write.c @@ -121,8 +121,14 @@ static int netfs_unbuffered_write(struct netfs_io_request *wreq) } iov_iter_truncate(&subreq->io_iter, wreq->len - wreq->transferred); - if (!iov_iter_count(&subreq->io_iter)) + if (!iov_iter_count(&subreq->io_iter)) { + pr_warn("netfs: Unexpected zero-length iterator R=%08x\n", + wreq->debug_id); + __set_bit(NETFS_SREQ_FAILED, &subreq->flags); + netfs_write_subrequest_terminated(subreq, -EIO); + wreq->error = -EIO; break; + } subreq->len = netfs_limit_iter(&subreq->io_iter, 0, stream->sreq_max_len, From 8fb45a934661419c04a44d4cfea1e0df7dcf2805 Mon Sep 17 00:00:00 2001 From: Edward Adam Davis Date: Thu, 27 Aug 2026 14:42:59 +0100 Subject: [PATCH 0211/1198] netfs: break unbuffered write when netfs_alloc_subrequest() fails syzbot reported a null-ptr-deref below [1] following a fault injection in netfs_alloc_subrequest(). [0] When netfs_alloc_subrequest() fails, subreq is NULL. Later, netfs_prepare_write() tries to initialize members of subreq(e.g., source), the issue in [1] is triggered. Let's handle the error of netfs_prepare_write() properly. [0] FAULT_INJECTION: forcing a failure. name failslab, interval 1, probability 0, space 0, times 0 Call Trace: netfs_alloc_subrequest+0x116/0x3f0 netfs_prepare_write+0x76/0x7b0 netfs_unbuffered_write+0x75c/0x2020 netfs_unbuffered_write_iter_locked+0x7d6/0xa80 netfs_unbuffered_write_iter+0x442/0x720 v9fs_file_write_iter+0xbf/0x100 vfs_write+0x6ac/0x1050 [1] KASAN: null-ptr-deref in range [0x00000000000000a8-0x00000000000000af] RIP: 0010:netfs_prepare_write+0xbc/0x7b0 fs/netfs/write_issue.c:173 Call Trace: netfs_unbuffered_write+0x75c/0x2020 fs/netfs/direct_write.c:111 netfs_unbuffered_write_iter_locked+0x7d6/0xa80 fs/netfs/direct_write.c:290 netfs_unbuffered_write_iter+0x442/0x720 fs/netfs/direct_write.c:382 v9fs_file_write_iter+0xbf/0x100 fs/9p/vfs_file.c:409 new_sync_write fs/read_write.c:595 [inline] Fixes: 288ace2f57c9 ("netfs: New writeback implementation") Reported-by: syzbot+6a13fc77eb6f0802be2d@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=6a13fc77eb6f0802be2d Tested-by: syzbot+6a13fc77eb6f0802be2d@syzkaller.appspotmail.com Signed-off-by: Edward Adam Davis Signed-off-by: David Howells Link: https://patch.msgid.link/20260827134304.2075713-7-dhowells@redhat.com Acked-by: Paulo Alcantara Signed-off-by: Christian Brauner (Amutable) --- fs/netfs/direct_write.c | 5 +++++ fs/netfs/write_issue.c | 2 ++ 2 files changed, 7 insertions(+) diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c index fbcfadb232ee..2361277416c7 100644 --- a/fs/netfs/direct_write.c +++ b/fs/netfs/direct_write.c @@ -110,6 +110,11 @@ static int netfs_unbuffered_write(struct netfs_io_request *wreq) if (!subreq) { netfs_prepare_write(wreq, stream, wreq->start + wreq->transferred); subreq = stream->construct; + if (!subreq) { + wreq->error = -ENOMEM; + ret = -ENOMEM; + break; + } stream->construct = NULL; } diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 2d9cfcd43658..851f6f93ad45 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -170,6 +170,8 @@ void netfs_prepare_write(struct netfs_io_request *wreq, rolling_buffer_make_space(&wreq->buffer, wreq->gfp); subreq = netfs_alloc_subrequest(wreq); + if (!subreq) + return; subreq->source = stream->source; subreq->start = start; subreq->stream_nr = stream->stream_nr; From fed0b33e6c584986ba70018ec9f9787a98216e64 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 27 Aug 2026 14:43:00 +0100 Subject: [PATCH 0212/1198] netfs: Fix readahead synchronisation issues by loading all folios upfront There are some synchronisation issues that derive from the app thread adding more folios to the rolling buffer whilst the collector thread is looking at them or trying to clear them, such as determining the setting of front_folio_order when the next folio hasn't been added yet, The reason for the rolling buffer approach is that loading the buffer upfront and then dropping all the refs just acquired is quite a slow operation, and loading progressively allows some of the cost to be deferred until after at least some of the I/O is started. Instead, a better way is to load all the folios into the rolling buffer upfront - and then drop the refs later, once the I/O is in progress. (Even better would be for the refs not to be there at all.) Fix this by changing the rolling buffer loader to load all the folios selected by the VM for readahead upfront into the folio queue. The folio queue is allocated a batch worth at a time as we don't know how many folios are involved (the readahead_control struct, alas, has a page count, not a folio count). The folio refs acquired from readahead are then dropped in bulk once the first subrequest is dispatched as it's quite a slow operation. The collector waits for NETFS_RREQ_NEED_PUT_RA_REFS to be cleared so that it doesn't unlock folios before the xarray has been scanned for them. This simplifies the buffer handling later and isn't noticeably slower as the xarray doesn't need to be modified and the folios are all already pre-locked. Fixes: ee4cdf7ba857 ("netfs: Speed up buffered reading") Link: https://sashiko.dev/#/patchset/20260824120224.504575-1-dhowells%40redhat.com Signed-off-by: David Howells Link: https://patch.msgid.link/20260827134304.2075713-8-dhowells@redhat.com Acked-by: Paulo Alcantara cc: Paulo Alcantara (Red Hat) cc: Matthew Wilcox cc: netfs@lists.linux.dev cc: linux-mm@kvack.org cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner (Amutable) --- fs/netfs/buffered_read.c | 101 ++++++++++++++++++++------------- fs/netfs/internal.h | 1 + fs/netfs/misc.c | 19 +++++++ fs/netfs/read_collect.c | 7 +++ fs/netfs/read_retry.c | 7 +++ fs/netfs/rolling_buffer.c | 79 +++++++++++++++++--------- include/linux/netfs.h | 1 + include/linux/rolling_buffer.h | 6 +- include/trace/events/netfs.h | 3 + 9 files changed, 153 insertions(+), 71 deletions(-) diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 7fdfa4f27e34..303fdce54fba 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -54,6 +54,42 @@ static void netfs_rreq_expand(struct netfs_io_request *rreq, } } +/* + * Drop the folio refs acquired from the readahead API. + */ +static void netfs_bulk_drop_ra_refs(struct netfs_io_request *rreq) +{ + struct folio_batch fbatch; + struct folio *folio; + pgoff_t nr_pages = DIV_ROUND_UP(rreq->len, PAGE_SIZE); + pgoff_t first = rreq->start / PAGE_SIZE; + XA_STATE(xas, &rreq->mapping->i_pages, first); + + folio_batch_init(&fbatch); + + rcu_read_lock(); + + xas_for_each(&xas, folio, first + nr_pages - 1) { + if (xas_retry(&xas, folio)) + continue; + + if (!folio_batch_add(&fbatch, folio)) + folio_batch_release(&fbatch); + } + + rcu_read_unlock(); + folio_batch_release(&fbatch); + trace_netfs_rreq(rreq, netfs_rreq_trace_ra_put_ref); + clear_bit_unlock(NETFS_RREQ_NEED_PUT_RA_REFS, &rreq->flags); + wake_up(&rreq->waitq); +} + +static void netfs_maybe_bulk_drop_ra_refs(struct netfs_io_request *rreq) +{ + if (test_bit(NETFS_RREQ_NEED_PUT_RA_REFS, &rreq->flags)) + netfs_bulk_drop_ra_refs(rreq); +} + /* * Begin an operation, and fetch the stored zero point value from the cookie if * available. @@ -74,12 +110,8 @@ static int netfs_begin_cache_read(struct netfs_io_request *rreq, struct netfs_in * * Returns the limited size if successful and -ENOMEM if insufficient memory * available. - * - * [!] NOTE: This must be run in the same thread as ->issue_read() was called - * in as we access the readahead_control struct. */ -static ssize_t netfs_prepare_read_iterator(struct netfs_io_subrequest *subreq, - struct readahead_control *ractl) +static ssize_t netfs_prepare_read_iterator(struct netfs_io_subrequest *subreq) { struct netfs_io_request *rreq = subreq->rreq; size_t rsize = subreq->len; @@ -87,30 +119,6 @@ static ssize_t netfs_prepare_read_iterator(struct netfs_io_subrequest *subreq, if (subreq->source == NETFS_DOWNLOAD_FROM_SERVER) rsize = umin(rsize, rreq->io_streams[0].sreq_max_len); - if (ractl) { - /* If we don't have sufficient folios in the rolling buffer, - * extract a folioq's worth from the readahead region at a time - * into the buffer. Note that this acquires a ref on each page - * that we will need to release later - but we don't want to do - * that until after we've started the I/O. - */ - struct folio_batch put_batch; - - folio_batch_init(&put_batch); - while (rreq->submitted < subreq->start + rsize) { - ssize_t added; - - added = rolling_buffer_load_from_ra(&rreq->buffer, ractl, - &put_batch); - if (added < 0) { - folio_batch_release(&put_batch); - return added; - } - rreq->submitted += added; - } - folio_batch_release(&put_batch); - } - subreq->len = rsize; if (unlikely(rreq->io_streams[0].sreq_max_segs)) { size_t limit = netfs_limit_iter(&rreq->buffer.iter, 0, rsize, @@ -208,8 +216,7 @@ static void netfs_issue_read(struct netfs_io_request *rreq, * slicing up the region to be read according to available cache blocks and * network rsize. */ -static void netfs_read_to_pagecache(struct netfs_io_request *rreq, - struct readahead_control *ractl) +static void netfs_read_to_pagecache(struct netfs_io_request *rreq) { unsigned long long start = rreq->start; ssize_t size = rreq->len; @@ -288,7 +295,7 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq, break; issue: - slice = netfs_prepare_read_iterator(subreq, ractl); + slice = netfs_prepare_read_iterator(subreq); if (slice < 0) { ret = slice; netfs_cancel_read(subreq, ret); @@ -302,6 +309,7 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq, } netfs_issue_read(rreq, subreq); + netfs_maybe_bulk_drop_ra_refs(rreq); if (test_bit(NETFS_RREQ_PAUSE, &rreq->flags)) netfs_wait_for_paused_read(rreq); @@ -339,7 +347,8 @@ void netfs_readahead(struct readahead_control *ractl) { struct netfs_io_request *rreq; struct netfs_inode *ictx = netfs_inode(ractl->mapping->host); - unsigned long long start = readahead_pos(ractl); + ssize_t added; + uoff_t start = readahead_pos(ractl); size_t size = readahead_length(ractl); int ret; @@ -360,11 +369,23 @@ void netfs_readahead(struct readahead_control *ractl) netfs_rreq_expand(rreq, ractl); - rreq->submitted = rreq->start; - if (rolling_buffer_init(&rreq->buffer, rreq->debug_id, ITER_DEST, rreq->gfp) < 0) + /* Load the folios to be read into a bvecq chain. Note that this + * acquires a ref on each folio that we will need to release later - + * but we don't want to do that until after we've started the I/O. + */ + added = rolling_buffer_bulk_load_from_ra(&rreq->buffer, ractl, + rreq->debug_id, rreq->gfp); + if (added < 0) { + ret = added; goto cleanup_free; - netfs_read_to_pagecache(rreq, ractl); + } + __set_bit(NETFS_RREQ_NEED_PUT_RA_REFS, &rreq->flags); + rreq->submitted = rreq->start + added; + rreq->cleaned_to = rreq->start; + + netfs_read_to_pagecache(rreq); + netfs_maybe_bulk_drop_ra_refs(rreq); return netfs_put_request(rreq, netfs_rreq_trace_put_return); cleanup_free: @@ -457,7 +478,7 @@ static int netfs_read_gaps(struct file *file, struct folio *folio) iov_iter_bvec(&rreq->buffer.iter, ITER_DEST, bvec, i, rreq->len); rreq->submitted = rreq->start + flen; - netfs_read_to_pagecache(rreq, NULL); + netfs_read_to_pagecache(rreq); ret = netfs_wait_for_read(rreq); if (ret >= 0) { @@ -532,7 +553,7 @@ int netfs_read_folio(struct file *file, struct folio *folio) if (ret < 0) goto discard; - netfs_read_to_pagecache(rreq, NULL); + netfs_read_to_pagecache(rreq); ret = netfs_wait_for_read(rreq); netfs_put_request(rreq, netfs_rreq_trace_put_return); return ret < 0 ? ret : 0; @@ -689,7 +710,7 @@ int netfs_write_begin(struct netfs_inode *ctx, if (ret < 0) goto error_put; - netfs_read_to_pagecache(rreq, NULL); + netfs_read_to_pagecache(rreq); ret = netfs_wait_for_read(rreq); netfs_put_request(rreq, netfs_rreq_trace_put_return); if (ret < 0) @@ -754,7 +775,7 @@ int netfs_prefetch_for_write(struct file *file, struct folio *folio, if (ret < 0) goto error_put; - netfs_read_to_pagecache(rreq, NULL); + netfs_read_to_pagecache(rreq); ret = netfs_wait_for_read(rreq); netfs_put_request(rreq, netfs_rreq_trace_put_return); return ret < 0 ? ret : 0; diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index 420ee7b26580..bd8b2d633f96 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -79,6 +79,7 @@ ssize_t netfs_wait_for_read(struct netfs_io_request *rreq); ssize_t netfs_wait_for_write(struct netfs_io_request *rreq); void netfs_wait_for_paused_read(struct netfs_io_request *rreq); void netfs_wait_for_paused_write(struct netfs_io_request *rreq); +void netfs_wait_for_put_ra_refs(struct netfs_io_request *rreq); /* * objects.c diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c index 5d554512ed23..f5c1c463f4ff 100644 --- a/fs/netfs/misc.c +++ b/fs/netfs/misc.c @@ -563,3 +563,22 @@ void netfs_wait_for_paused_write(struct netfs_io_request *rreq) { return netfs_wait_for_pause(rreq, netfs_write_collection); } + +/* + * Wait for the readahead-acquired refs to be put. + */ +void netfs_wait_for_put_ra_refs(struct netfs_io_request *rreq) +{ + DEFINE_WAIT(myself); + + for (;;) { + trace_netfs_rreq(rreq, netfs_rreq_trace_wait_put_ra_refs); + prepare_to_wait(&rreq->waitq, &myself, TASK_UNINTERRUPTIBLE); + if (!test_bit(NETFS_RREQ_NEED_PUT_RA_REFS, &rreq->flags)) + break; + schedule(); + } + + trace_netfs_rreq(rreq, netfs_rreq_trace_waited_put_ra_refs); + finish_wait(&rreq->waitq, &myself); +} diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index 23660a590124..edf7cea7e2f9 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -118,6 +118,13 @@ static void netfs_read_unlock_folios(struct netfs_io_request *rreq, slot = 0; } + /* We have to wait for readahead refs to have been released before we + * can unlock any folios as the ref-dropper walks i_pages and the only + * thing preventing these folios from being removed is the folio lock. + */ + if (test_bit(NETFS_RREQ_NEED_PUT_RA_REFS, &rreq->flags)) + netfs_wait_for_put_ra_refs(rreq); + for (;;) { struct folio *folio; unsigned long long fpos, fend; diff --git a/fs/netfs/read_retry.c b/fs/netfs/read_retry.c index 2b42758e01ec..dd463a485139 100644 --- a/fs/netfs/read_retry.c +++ b/fs/netfs/read_retry.c @@ -292,6 +292,13 @@ void netfs_unlock_abandoned_read_pages(struct netfs_io_request *rreq) { struct folio_queue *p; + /* We have to wait for readahead refs to have been released before we + * can unlock any folios as the ref-dropper walks i_pages and the only + * thing preventing these folios from being removed is the folio lock. + */ + if (test_bit(NETFS_RREQ_NEED_PUT_RA_REFS, &rreq->flags)) + netfs_wait_for_put_ra_refs(rreq); + for (p = rreq->buffer.tail; p; p = p->next) { for (int slot = 0; slot < folioq_count(p); slot++) { struct folio *folio = folioq_folio(p, slot); diff --git a/fs/netfs/rolling_buffer.c b/fs/netfs/rolling_buffer.c index 8c0026836f9c..424e77a9a109 100644 --- a/fs/netfs/rolling_buffer.c +++ b/fs/netfs/rolling_buffer.c @@ -115,42 +115,65 @@ int rolling_buffer_make_space(struct rolling_buffer *roll, gfp_t gfp) } /* - * Decant the list of folios to read into a rolling buffer. + * Decant the entire list of folios to read into a rolling buffer. */ -ssize_t rolling_buffer_load_from_ra(struct rolling_buffer *roll, - struct readahead_control *ractl, - struct folio_batch *put_batch) +ssize_t rolling_buffer_bulk_load_from_ra(struct rolling_buffer *roll, + struct readahead_control *ractl, + unsigned int rreq_id, gfp_t gfp) { struct folio_queue *fq; - struct page **vec; - int nr, ix, to; - ssize_t size = 0; + ssize_t loaded = 0; - if (rolling_buffer_make_space(roll, GFP_KERNEL) < 0) - return -ENOMEM; + while (ractl->_nr_pages - ractl->_batch_count > 0) { + unsigned int nr; - fq = roll->head; - vec = (struct page **)fq->vec.folios; - nr = __readahead_batch(ractl, vec + folio_batch_count(&fq->vec), - folio_batch_space(&fq->vec)); - ix = fq->vec.nr; - to = ix + nr; - fq->vec.nr = to; - for (; ix < to; ix++) { - struct folio *folio = folioq_folio(fq, ix); - unsigned int order = folio_order(folio); + /* Allocate a folioq to put some folios into and attach it to + * the rolling buffer. + */ + fq = netfs_folioq_alloc(rreq_id, gfp, + netfs_trace_folioq_make_space); + if (!fq) + goto nomem_unlock; + fq->prev = roll->head; + if (!roll->tail) + roll->tail = fq; + else + roll->head->next = fq; + roll->head = fq; - fq->orders[ix] = order; - size += PAGE_SIZE << order; - trace_netfs_folio(folio, netfs_folio_trace_read); - if (!folio_batch_add(put_batch, folio)) - folio_batch_release(put_batch); + /* Get a batch of folios and note their orders. */ + nr = __readahead_batch(ractl, (struct page **)fq->vec.folios, + folioq_nr_slots(fq)); + if (WARN_ON_ONCE(!nr)) + break; + fq->vec.nr = nr; + + for (int slot = 0; slot < nr; slot++) { + struct folio *folio = folioq_folio(fq, slot); + unsigned int order; + + order = folio_order(folio); + fq->orders[slot] = order; + loaded += PAGE_SIZE << order; + trace_netfs_folio(folio, netfs_folio_trace_read); + } } - WRITE_ONCE(roll->iter.count, roll->iter.count + size); - /* Store the counter after setting the slot. */ - smp_store_release(&roll->next_head_slot, to); - return size; + WRITE_ONCE(roll->iter.count, loaded); + iov_iter_folio_queue(&roll->iter, ITER_DEST, roll->tail, 0, 0, loaded); + return loaded; + +nomem_unlock: + for (fq = roll->tail; fq; fq = fq->next) { + for (int slot = 0; slot < folioq_count(fq); slot++) { + folio_unlock(fq->vec.folios[slot]); + folioq_mark(fq, slot); + } + } + rolling_buffer_clear(roll); + roll->head = NULL; + roll->tail = NULL; + return -ENOMEM; } /* diff --git a/include/linux/netfs.h b/include/linux/netfs.h index f837a501008c..5c538d0c5d79 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -278,6 +278,7 @@ struct netfs_io_request { #define NETFS_RREQ_FOLIO_COPY_TO_CACHE 10 /* Copy current folio to cache from read */ #define NETFS_RREQ_UPLOAD_TO_SERVER 11 /* Need to write to the server */ #define NETFS_RREQ_USE_IO_ITER 12 /* Use ->io_iter rather than ->i_pages */ +#define NETFS_RREQ_NEED_PUT_RA_REFS 17 /* Need to put the folio refs RA gave us */ #define NETFS_RREQ_USE_PGPRIV2 31 /* [DEPRECATED] Use PG_private_2 to mark * write to cache on read */ const struct netfs_request_ops *netfs_ops; diff --git a/include/linux/rolling_buffer.h b/include/linux/rolling_buffer.h index 9e5dad29669c..a97f7cfaacaa 100644 --- a/include/linux/rolling_buffer.h +++ b/include/linux/rolling_buffer.h @@ -45,9 +45,9 @@ struct rolling_buffer_snapshot { int rolling_buffer_init(struct rolling_buffer *roll, unsigned int rreq_id, unsigned int direction, gfp_t gfp); int rolling_buffer_make_space(struct rolling_buffer *roll, gfp_t gfp); -ssize_t rolling_buffer_load_from_ra(struct rolling_buffer *roll, - struct readahead_control *ractl, - struct folio_batch *put_batch); +ssize_t rolling_buffer_bulk_load_from_ra(struct rolling_buffer *roll, + struct readahead_control *ractl, + unsigned int rreq_id, gfp_t gfp); ssize_t rolling_buffer_append(struct rolling_buffer *roll, struct folio *folio, unsigned int flags, gfp_t gfp); struct folio_queue *rolling_buffer_delete_spent(struct rolling_buffer *roll); diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 082cb03c6131..9bda9302be90 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -59,6 +59,7 @@ EM(netfs_rreq_trace_free, "FREE ") \ EM(netfs_rreq_trace_intr, "INTR ") \ EM(netfs_rreq_trace_ki_complete, "KI-CMPL") \ + EM(netfs_rreq_trace_ra_put_ref, "RA-PUT ") \ EM(netfs_rreq_trace_recollect, "RECLLCT") \ EM(netfs_rreq_trace_redirty, "REDIRTY") \ EM(netfs_rreq_trace_resubmit, "RESUBMT") \ @@ -70,9 +71,11 @@ EM(netfs_rreq_trace_unpause, "UNPAUSE") \ EM(netfs_rreq_trace_wait_ip, "WAIT-IP") \ EM(netfs_rreq_trace_wait_pause, "--PAUSED--") \ + EM(netfs_rreq_trace_wait_put_ra_refs, "WAIT-P-RA") \ EM(netfs_rreq_trace_wait_quiesce, "WAIT-QUIESCE") \ EM(netfs_rreq_trace_waited_ip, "DONE-IP") \ EM(netfs_rreq_trace_waited_pause, "--UNPAUSED--") \ + EM(netfs_rreq_trace_waited_put_ra_refs, "DONE-P-RA") \ EM(netfs_rreq_trace_waited_quiesce, "DONE-QUIESCE") \ EM(netfs_rreq_trace_wake_ip, "WAKE-IP") \ EM(netfs_rreq_trace_wake_queue, "WAKE-Q ") \ From 533203c4183123dad8ffecd694e7573a0ccd0da0 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 27 Aug 2026 14:43:01 +0100 Subject: [PATCH 0213/1198] netfs: Mark folios with COPY_TO_CACHE whilst issuing subreqs Mark folios with NETFS_FOLIO_COPY_TO_CACHE whilst issuing subreqs rather than when collecting them. This means that the collector thread doesn't have to try and keep track of which subreqs contribute to which folios - and thus which folios will need to be copied to the cache because at least one byte wasn't in the cache. Instead, this is marked on the folios up front and the collector need only consider the folios. For PG_private_2-using filesystems, PG_private_2 is set instead of NETFS_FOLIO_COPY_TO_CACHE, but otherwise it works the same. The NETFS_RREQ_COPY_TO_CACHE is replaced with NETFS_RREQ_CANCEL_CACHING, which is now set if caching fails somewhere, thereby causing the collection thread to cancel the copy-to-cache marks on the remaining folios. Signed-off-by: David Howells Link: https://patch.msgid.link/20260827134304.2075713-9-dhowells@redhat.com Acked-by: Paulo Alcantara cc: Paulo Alcantara (Red Hat) cc: Matthew Wilcox cc: netfs@lists.linux.dev cc: linux-mm@kvack.org cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner (Amutable) --- fs/netfs/buffered_read.c | 61 +++++++++++++++++++++++++++++++- fs/netfs/internal.h | 1 + fs/netfs/read_collect.c | 67 ++++++++++++++++++++++-------------- fs/netfs/read_pgpriv2.c | 15 ++++---- fs/netfs/read_retry.c | 6 +++- include/linux/netfs.h | 2 +- include/trace/events/netfs.h | 6 ++-- 7 files changed, 121 insertions(+), 37 deletions(-) diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 303fdce54fba..16d4db776f6a 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -211,6 +211,56 @@ static void netfs_issue_read(struct netfs_io_request *rreq, } } +/* + * Mark folios that we want to copy to the cache. For filesystems that use + * netfslib fully, we set folio->private to NETFS_FOLIO_COPY_TO_CACHE; + * otherwise we set the deprecated PG_private_2. + */ +static void netfs_mark_copy_to_cache(struct netfs_io_request *rreq, + struct folio_queue **fq, + unsigned int *offset, + int *slot, + size_t len, + bool copy) +{ + while (len > 0) { + struct folio *folio; + size_t fsize, overlap; + + if (!*fq) + break; + if (*slot >= folioq_count(*fq)) { + *fq = (*fq)->next; + *slot = 0; + *offset = 0; + continue; + } + + /* Determine how much the subreq overlaps the folio, if at all. */ + fsize = folioq_folio_size(*fq, *slot); + overlap = min(len, fsize - *offset); + + if (overlap > 0 && copy) { + folio = folioq_folio(*fq, *slot); + if (unlikely(test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags))) { + if (!folio_test_private_2(folio)) + folio_start_private_2(folio); + } else { + if (!folio_get_private(folio)) + folio_attach_private(folio, NETFS_FOLIO_COPY_TO_CACHE); + } + trace_netfs_folio(folio, netfs_folio_trace_mark_copy); + } + + len -= overlap; + *offset += overlap; + if (*offset >= fsize) { + *slot += 1; + *offset = 0; + } + } +} + /* * Perform a read to the pagecache from a series of sources of different types, * slicing up the region to be read according to available cache blocks and @@ -218,9 +268,11 @@ static void netfs_issue_read(struct netfs_io_request *rreq, */ static void netfs_read_to_pagecache(struct netfs_io_request *rreq) { + struct folio_queue *fq = rreq->buffer.tail; unsigned long long start = rreq->start; + unsigned int offset = 0; ssize_t size = rreq->len; - int ret = 0; + int ret = 0, slot = 0; do { struct netfs_io_subrequest *subreq; @@ -308,6 +360,13 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq) set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); } + if (fq) { + /* See if the cache indicated this should be cached. */ + bool copy = test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); + + netfs_mark_copy_to_cache(rreq, &fq, &slot, &offset, slice, copy); + } + netfs_issue_read(rreq, subreq); netfs_maybe_bulk_drop_ra_refs(rreq); diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index bd8b2d633f96..dfe7939f35f3 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -110,6 +110,7 @@ static inline void netfs_see_subrequest(struct netfs_io_subrequest *subreq, /* * read_collect.c */ +void netfs_cancel_copy_to_cache(struct netfs_io_request *rreq, struct folio *folio); bool netfs_read_collection(struct netfs_io_request *rreq); void netfs_read_collection_worker(struct work_struct *work); void netfs_cancel_read(struct netfs_io_subrequest *subreq, int error); diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index edf7cea7e2f9..12a786be1ea2 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -19,7 +19,6 @@ #define MADE_PROGRESS 0x04 /* Made progress cleaning up a stream or the folio set */ #define BUFFERED 0x08 /* The pagecache needs cleaning up */ #define NEED_RETRY 0x10 /* A front op requests retrying */ -#define COPY_TO_CACHE 0x40 /* Need to copy subrequest to cache */ #define ABANDON_SREQ 0x80 /* Need to abandon untransferred part of subrequest */ /* @@ -34,6 +33,30 @@ static void netfs_clear_unread(struct netfs_io_subrequest *subreq) __set_bit(NETFS_SREQ_HIT_EOF, &subreq->flags); } +/* + * Cancel the copy-to-cache mark on a folio. + */ +void netfs_cancel_copy_to_cache(struct netfs_io_request *rreq, struct folio *folio) +{ + if (!test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) { + if (folio_get_private(folio) == NETFS_FOLIO_COPY_TO_CACHE) { + folio_detach_private(folio); + trace_netfs_folio(folio, netfs_folio_trace_cancel_copy); + } else if (netfs_folio_group(folio) == NETFS_FOLIO_COPY_TO_CACHE) { + struct netfs_folio *finfo = netfs_folio_info(folio); + + finfo->netfs_group = NULL; + trace_netfs_folio(folio, netfs_folio_trace_cancel_copy); + } + } else { + // TODO: Use of PG_private_2 is deprecated. + if (folio_test_private_2(folio)) { + folio_end_private_2(folio); + trace_netfs_folio(folio, netfs_folio_trace_cancel_copy); + } + } +} + /* * Flush, mark and unlock a folio that's now completely read. If we want to * cache the folio, we set the group to NETFS_FOLIO_COPY_TO_CACHE, mark it @@ -48,37 +71,37 @@ static void netfs_unlock_read_folio(struct netfs_io_request *rreq, if (unlikely(folio_pos(folio) < rreq->abandon_to)) { trace_netfs_folio(folio, netfs_folio_trace_abandon); + netfs_cancel_copy_to_cache(rreq, folio); goto just_unlock; } flush_dcache_folio(folio); folio_mark_uptodate(folio); - if (!test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) { - finfo = netfs_folio_info(folio); - if (finfo) { - trace_netfs_folio(folio, netfs_folio_trace_filled_gaps); - if (finfo->netfs_group) - folio_change_private(folio, finfo->netfs_group); - else - folio_detach_private(folio); - kfree(finfo); - } + if (unlikely(test_bit(NETFS_RREQ_CANCEL_CACHING, &rreq->flags))) + netfs_cancel_copy_to_cache(rreq, folio); - if (test_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &rreq->flags)) { - if (!WARN_ON_ONCE(folio_get_private(folio) != NULL)) { - trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); - folio_attach_private(folio, NETFS_FOLIO_COPY_TO_CACHE); - folio_mark_dirty(folio); - } + if (!test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) { + if (netfs_folio_group(folio) == NETFS_FOLIO_COPY_TO_CACHE) { + trace_netfs_folio(folio, netfs_folio_trace_sched_copy); + folio_mark_dirty(folio); } else { + finfo = netfs_folio_info(folio); + if (finfo) { + trace_netfs_folio(folio, netfs_folio_trace_filled_gaps); + if (finfo->netfs_group) + folio_change_private(folio, finfo->netfs_group); + else + folio_detach_private(folio); + kfree(finfo); + } trace_netfs_folio(folio, netfs_folio_trace_read_done); } folioq_clear(folioq, slot); } else { // TODO: Use of PG_private_2 is deprecated. - if (test_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &rreq->flags)) + if (folio_test_private_2(folio)) netfs_pgpriv2_copy_to_cache(rreq, folio); } @@ -131,9 +154,6 @@ static void netfs_read_unlock_folios(struct netfs_io_request *rreq, unsigned int order; size_t fsize; - if (*notes & COPY_TO_CACHE) - set_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &rreq->flags); - folio = folioq_folio(folioq, slot); if (WARN_ONCE(!folio_test_locked(folio), "R=%08x: folio %lx is not locked\n", @@ -156,8 +176,6 @@ static void netfs_read_unlock_folios(struct netfs_io_request *rreq, WRITE_ONCE(rreq->cleaned_to, fpos + fsize); *notes |= MADE_PROGRESS; - clear_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &rreq->flags); - /* Clean up the head folioq. If we clear an entire folioq, then * we can get rid of it provided it's not also the tail folioq * being filled by the issuer. @@ -255,9 +273,6 @@ static void netfs_collect_read_results(struct netfs_io_request *rreq) stream->collected_to = front->start + transferred; rreq->collected_to = stream->collected_to; - if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &front->flags)) - notes |= COPY_TO_CACHE; - if (test_bit(NETFS_SREQ_FAILED, &front->flags)) { rreq->abandon_to = front->start + front->len; front->transferred = front->len; diff --git a/fs/netfs/read_pgpriv2.c b/fs/netfs/read_pgpriv2.c index c31190993b76..a4b7bb88cbdb 100644 --- a/fs/netfs/read_pgpriv2.c +++ b/fs/netfs/read_pgpriv2.c @@ -54,8 +54,8 @@ static void netfs_pgpriv2_copy_folio(struct netfs_io_request *creq, struct folio /* Attach the folio to the rolling buffer. */ if (rolling_buffer_append(&creq->buffer, folio, 0, creq->gfp) < 0) { + set_bit(NETFS_RREQ_CANCEL_CACHING, &creq->flags); folio_end_private_2(folio); - clear_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &creq->flags); return; } @@ -122,13 +122,14 @@ static struct netfs_io_request *netfs_pgpriv2_begin_copy_to_cache( netfs_put_failed_request(creq); cancel: rreq->copy_to_cache = ERR_PTR(-ENOBUFS); - clear_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &rreq->flags); + set_bit(NETFS_RREQ_CANCEL_CACHING, &rreq->flags); return ERR_PTR(-ENOBUFS); } /* * [DEPRECATED] Mark page as requiring copy-to-cache using PG_private_2 and add - * it to the copy write request. + * it to the copy write request. PG_private_2 should already be set on the + * folio. */ void netfs_pgpriv2_copy_to_cache(struct netfs_io_request *rreq, struct folio *folio) { @@ -136,11 +137,13 @@ void netfs_pgpriv2_copy_to_cache(struct netfs_io_request *rreq, struct folio *fo if (!creq) creq = netfs_pgpriv2_begin_copy_to_cache(rreq, folio); - if (IS_ERR(creq)) + if (IS_ERR(creq)) { + set_bit(NETFS_RREQ_CANCEL_CACHING, &rreq->flags); + netfs_cancel_copy_to_cache(rreq, folio); return; + } - trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); - folio_start_private_2(folio); + trace_netfs_folio(folio, netfs_folio_trace_pgpriv2_copy); netfs_pgpriv2_copy_folio(creq, folio); } diff --git a/fs/netfs/read_retry.c b/fs/netfs/read_retry.c index dd463a485139..4f6a36c6e214 100644 --- a/fs/netfs/read_retry.c +++ b/fs/netfs/read_retry.c @@ -303,7 +303,11 @@ void netfs_unlock_abandoned_read_pages(struct netfs_io_request *rreq) for (int slot = 0; slot < folioq_count(p); slot++) { struct folio *folio = folioq_folio(p, slot); - if (folio && !folioq_is_marked2(p, slot)) { + if (!folio) + continue; + netfs_cancel_copy_to_cache(rreq, folio); + + if (!folioq_is_marked2(p, slot)) { if (folio == rreq->no_unlock_folio && test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) { diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 5c538d0c5d79..9881f4afdc0c 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -275,7 +275,7 @@ struct netfs_io_request { #define NETFS_RREQ_SHORT_TRANSFER 5 /* Set if we have a short transfer */ #define NETFS_RREQ_OFFLOAD_COLLECTION 8 /* Offload collection to workqueue */ #define NETFS_RREQ_NO_UNLOCK_FOLIO 9 /* Don't unlock no_unlock_folio on completion */ -#define NETFS_RREQ_FOLIO_COPY_TO_CACHE 10 /* Copy current folio to cache from read */ +#define NETFS_RREQ_CANCEL_CACHING 10 /* Set to cancel caching */ #define NETFS_RREQ_UPLOAD_TO_SERVER 11 /* Need to write to the server */ #define NETFS_RREQ_USE_IO_ITER 12 /* Use ->io_iter rather than ->i_pages */ #define NETFS_RREQ_NEED_PUT_RA_REFS 17 /* Need to put the folio refs RA gave us */ diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 9bda9302be90..a22084813cb5 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -198,7 +198,6 @@ EM(netfs_folio_trace_clear_cc, "clear-cc") \ EM(netfs_folio_trace_clear_g, "clear-g") \ EM(netfs_folio_trace_clear_s, "clear-s") \ - EM(netfs_folio_trace_copy_to_cache, "mark-copy") \ EM(netfs_folio_trace_end_copy, "end-copy") \ EM(netfs_folio_trace_filled_gaps, "filled-gaps") \ EM(netfs_folio_trace_invalidate_all, "inval-all") \ @@ -209,16 +208,19 @@ EM(netfs_folio_trace_kill_cc, "kill-cc") \ EM(netfs_folio_trace_kill_g, "kill-g") \ EM(netfs_folio_trace_kill_s, "kill-s") \ + EM(netfs_folio_trace_mark_copy, "mark-copy") \ EM(netfs_folio_trace_mkwrite, "mkwrite") \ EM(netfs_folio_trace_mkwrite_plus, "mkwrite+") \ - EM(netfs_folio_trace_not_under_wback, "!wback") \ EM(netfs_folio_trace_not_locked, "!locked") \ + EM(netfs_folio_trace_not_under_wback, "!wback") \ + EM(netfs_folio_trace_pgpriv2_copy, "pgpriv2-copy") \ EM(netfs_folio_trace_put, "put") \ EM(netfs_folio_trace_read, "read") \ EM(netfs_folio_trace_read_done, "read-done") \ EM(netfs_folio_trace_read_gaps, "read-gaps") \ EM(netfs_folio_trace_read_unlock, "read-unlock") \ EM(netfs_folio_trace_redirtied, "redirtied") \ + EM(netfs_folio_trace_sched_copy, "sched-copy") \ EM(netfs_folio_trace_store, "store") \ EM(netfs_folio_trace_store_copy, "store-copy") \ EM(netfs_folio_trace_store_plus, "store+") \ From e00827a4d0cfebf8d78dfd0a9a024237f57c9273 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 27 Aug 2026 14:43:02 +0100 Subject: [PATCH 0214/1198] netfs: Fix read progress reporting For really big read RPC ops that span multiple folios, netfslib allows the filesystem to give progress notifications to wake up the collector thread to do a collection of folios that have now been fetched, even if the RPC is still ongoing, thereby allowing the application to make progress. This works by taking the current rreq->cleaned_to value (which indicates which folios have been unlocked) and adding the stashed size of the next folio to it. cleaned_to, however, is subject to 64-bit tearing on a 32-bit arch. Fix this by stashing the next progress notification point as a size_t (which won't tear) to be added to rreq->start (which won't change), with the collector thread calculating that from cleaned_to plus the next folio size. Further, however, if the folios are small, the collector thread gets constantly woken up - which has a negative performance impact on the system. Fix that too by setting a minimum trigger of 256KiB or the size of the folio at the front of the queue, whichever is larger. Note that this has an issue that different subreqs have different need-to-be-cached properties; this is solved by a preceding patch that marks the property on the folios whilst issuing subreqs rather than when collecting them. Also, make sure rreq->cleaned_to is initialised up front, along with rreq->collected_to and stream->collected_to. Fixes: e2d46f2ec332 ("netfs: Change the read result collector to only use one work item") Link: https://sashiko.dev/#/patchset/20260804100224.2748935-1-dhowells%40redhat.com Signed-off-by: David Howells Link: https://patch.msgid.link/20260827134304.2075713-10-dhowells@redhat.com Acked-by: Paulo Alcantara cc: Paulo Alcantara cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner (Amutable) --- fs/netfs/buffered_read.c | 2 ++ fs/netfs/internal.h | 1 + fs/netfs/objects.c | 32 +++++++++++++-------- fs/netfs/read_collect.c | 54 ++++++++++++++++++++++++++++-------- fs/netfs/read_single.c | 2 ++ include/linux/netfs.h | 2 +- include/trace/events/netfs.h | 21 ++++++++++++++ 7 files changed, 89 insertions(+), 25 deletions(-) diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 16d4db776f6a..424df70a5c30 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -442,6 +442,7 @@ void netfs_readahead(struct readahead_control *ractl) rreq->submitted = rreq->start + added; rreq->cleaned_to = rreq->start; + netfs_read_set_unlock_at(rreq); netfs_read_to_pagecache(rreq); netfs_maybe_bulk_drop_ra_refs(rreq); @@ -467,6 +468,7 @@ static int netfs_create_singular_buffer(struct netfs_io_request *rreq, struct fo if (added < 0) return added; rreq->submitted = rreq->start + added; + rreq->progress_at = added; return 0; } diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index dfe7939f35f3..c79c8e69d60c 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -111,6 +111,7 @@ static inline void netfs_see_subrequest(struct netfs_io_subrequest *subreq, * read_collect.c */ void netfs_cancel_copy_to_cache(struct netfs_io_request *rreq, struct folio *folio); +void netfs_read_set_unlock_at(struct netfs_io_request *rreq); bool netfs_read_collection(struct netfs_io_request *rreq); void netfs_read_collection_worker(struct work_struct *work); void netfs_cancel_read(struct netfs_io_subrequest *subreq, int error); diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c index 01461a74642d..7f6a3e912602 100644 --- a/fs/netfs/objects.c +++ b/fs/netfs/objects.c @@ -41,24 +41,32 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, memset(rreq, 0, kmem_cache_size(cache)); INIT_WORK(&rreq->cleanup_work, netfs_free_request); - rreq->gfp = gfp; - rreq->start = start; - rreq->len = len; - rreq->origin = origin; - rreq->netfs_ops = ctx->ops; - rreq->mapping = mapping; - rreq->inode = inode; - rreq->i_size = i_size_read(inode); - rreq->debug_id = atomic_inc_return(&debug_ids); - rreq->wsize = INT_MAX; + rreq->gfp = gfp; + rreq->start = start; + rreq->collected_to = start; + rreq->cleaned_to = start; + rreq->len = len; + rreq->progress_at = 0; + rreq->origin = origin; + rreq->netfs_ops = ctx->ops; + rreq->mapping = mapping; + rreq->inode = inode; + rreq->i_size = i_size_read(inode); + rreq->debug_id = atomic_inc_return(&debug_ids); + rreq->wsize = INT_MAX; rreq->io_streams[0].sreq_max_len = ULONG_MAX; rreq->io_streams[0].sreq_max_segs = 0; spin_lock_init(&rreq->lock); - INIT_LIST_HEAD(&rreq->io_streams[0].subrequests); - INIT_LIST_HEAD(&rreq->io_streams[1].subrequests); init_waitqueue_head(&rreq->waitq); refcount_set(&rreq->ref, 2); + for (int s = 0; s < NR_IO_STREAMS; s++) { + struct netfs_io_stream *stream = &rreq->io_streams[s]; + + INIT_LIST_HEAD(&stream->subrequests); + stream->collected_to = rreq->start; + } + if (origin == NETFS_READAHEAD || origin == NETFS_READPAGE || origin == NETFS_READ_GAPS || diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index 12a786be1ea2..5cf22087d243 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -117,6 +117,35 @@ static void netfs_unlock_read_folio(struct netfs_io_request *rreq, folioq_clear(folioq, slot); } +/* + * Determine how much to gather before unlocking more folios. + */ +void netfs_read_set_unlock_at(struct netfs_io_request *rreq) +{ + struct folio_queue *folioq = rreq->buffer.tail; + unsigned int slot = rreq->buffer.first_tail_slot; + size_t cleaned_to = rreq->cleaned_to - rreq->start; + size_t progress_at = cleaned_to; + size_t minimum = 256 * 1024; + + while (progress_at < rreq->len) { + if (slot >= folioq_count(folioq)) { + folioq = folioq->next; + if (!folioq) + break; + slot = 0; + } + + progress_at += folioq_folio_size(folioq, slot); + if (progress_at - cleaned_to >= minimum) + break; + slot++; + } + + WRITE_ONCE(rreq->progress_at, progress_at); + trace_netfs_read_progress_at(rreq); +} + /* * Unlock any folios we've finished with. */ @@ -135,7 +164,7 @@ static void netfs_read_unlock_folios(struct netfs_io_request *rreq, if (slot >= folioq_nr_slots(folioq)) { folioq = rolling_buffer_delete_spent(&rreq->buffer); if (!folioq) { - rreq->front_folio_order = 0; + WRITE_ONCE(rreq->progress_at, rreq->len); return; } slot = 0; @@ -151,7 +180,6 @@ static void netfs_read_unlock_folios(struct netfs_io_request *rreq, for (;;) { struct folio *folio; unsigned long long fpos, fend; - unsigned int order; size_t fsize; folio = folioq_folio(folioq, slot); @@ -160,9 +188,7 @@ static void netfs_read_unlock_folios(struct netfs_io_request *rreq, rreq->debug_id, folio->index)) trace_netfs_folio(folio, netfs_folio_trace_not_locked); - order = folioq_folio_order(folioq, slot); - rreq->front_folio_order = order; - fsize = PAGE_SIZE << order; + fsize = folioq_folio_size(folioq, slot); fpos = folio_pos(folio); fend = fpos + fsize; @@ -197,6 +223,8 @@ static void netfs_read_unlock_folios(struct netfs_io_request *rreq, rreq->buffer.tail = folioq; done: rreq->buffer.first_tail_slot = slot; + + netfs_read_set_unlock_at(rreq); } /* @@ -257,7 +285,7 @@ static void netfs_collect_read_results(struct netfs_io_request *rreq) * subreqs. */ if (notes & BUFFERED) { - size_t fsize = PAGE_SIZE << rreq->front_folio_order; + uoff_t unlock_at = rreq->start + rreq->progress_at; /* Clear the tail of a short read. */ if (!(notes & HIT_PENDING) && @@ -279,7 +307,7 @@ static void netfs_collect_read_results(struct netfs_io_request *rreq) transferred = front->len; trace_netfs_rreq(rreq, netfs_rreq_trace_set_abandon); } - if (front->start + transferred >= rreq->cleaned_to + fsize || + if (front->start + transferred >= unlock_at || test_bit(NETFS_SREQ_HIT_EOF, &front->flags)) netfs_read_unlock_folios(rreq, ¬es); } else { @@ -499,20 +527,22 @@ void netfs_read_collection_worker(struct work_struct *work) void netfs_read_subreq_progress(struct netfs_io_subrequest *subreq) { struct netfs_io_request *rreq = subreq->rreq; - struct netfs_io_stream *stream = &rreq->io_streams[0]; - size_t fsize = PAGE_SIZE << rreq->front_folio_order; - - trace_netfs_sreq(subreq, netfs_sreq_trace_progress); + struct netfs_io_stream *stream = &rreq->io_streams[subreq->stream_nr]; + size_t progress_at = READ_ONCE(rreq->progress_at); + uoff_t update_at = rreq->start + progress_at; + uoff_t transferred_to = subreq->start + subreq->transferred; /* If we are at the head of the queue, wake up the collector, * getting a ref to it if we were the ones to do so. */ - if (subreq->start + subreq->transferred > rreq->cleaned_to + fsize && + if (progress_at < rreq->len && + transferred_to >= update_at && (rreq->origin == NETFS_READAHEAD || rreq->origin == NETFS_READPAGE || rreq->origin == NETFS_READ_FOR_WRITE) && list_is_first(&subreq->rreq_link, &stream->subrequests) ) { + trace_netfs_sreq(subreq, netfs_sreq_trace_progress); __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); netfs_wake_collector(rreq); } diff --git a/fs/netfs/read_single.c b/fs/netfs/read_single.c index 8833550d2eb6..de67ac41548d 100644 --- a/fs/netfs/read_single.c +++ b/fs/netfs/read_single.c @@ -170,6 +170,8 @@ ssize_t netfs_read_single(struct inode *inode, struct file *file, struct iov_ite if (IS_ERR(rreq)) return PTR_ERR(rreq); + rreq->progress_at = rreq->len; + ret = netfs_single_begin_cache_read(rreq, ictx); if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) goto cleanup_free; diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 9881f4afdc0c..b4dd32863dd4 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -246,6 +246,7 @@ struct netfs_io_request { unsigned long long submitted; /* Amount submitted for I/O so far */ unsigned long long len; /* Length of the request */ size_t transferred; /* Amount to be indicated as transferred */ + size_t progress_at; /* Report read progress when hit this much read */ long error; /* 0 or error that occurred */ unsigned long long i_size; /* Size of the file */ unsigned long long start; /* Start position */ @@ -262,7 +263,6 @@ struct netfs_io_request { atomic_t subreq_counter; /* Next subreq->debug_index */ unsigned int nr_group_rel; /* Number of refs to release on ->group */ spinlock_t lock; /* Lock for queuing subreqs */ - unsigned char front_folio_order; /* Order (size) of front folio */ enum netfs_io_origin origin; /* Origin of the request */ bool direct_bv_unpin; /* T if direct_bv[] must be unpinned */ refcount_t ref; diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index a22084813cb5..3fec3e8f91c8 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -791,6 +791,27 @@ TRACE_EVENT(netfs_folioq, __print_symbolic(__entry->trace, netfs_folioq_traces)) ); +TRACE_EVENT(netfs_read_progress_at, + TP_PROTO(const struct netfs_io_request *rreq), + + TP_ARGS(rreq), + + TP_STRUCT__entry( + __field(unsigned int, rreq) + __field(size_t, progress_at) + __field(size_t, cleaned_to) + ), + + TP_fast_assign( + __entry->rreq = rreq->debug_id; + __entry->cleaned_to = rreq->cleaned_to - rreq->start; + __entry->progress_at = rreq->progress_at; + ), + + TP_printk("R=%08x cln=%zx prg=%zx", + __entry->rreq, __entry->cleaned_to, __entry->progress_at) + ); + #undef EM #undef E_ #endif /* _TRACE_NETFS_H */ From a67632c8c2688d6e0091529bcefe54bc5ee80e9b Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 27 Aug 2026 14:43:03 +0100 Subject: [PATCH 0215/1198] cachefiles: Fix potential UAF/KASAN warning Currently, trace_cachefiles_coherency() is being passed a pointer to a __be64 lain over the coherency data in struct cachefiles_xattr so that it can display the first 8 bytes. However, the data is of variable length and could even be 0 bytes. This could lead to a UAF or KASAN warning. Fix this by making sure the buffer has room for at least 8 bytes and that those 8 bytes are pre-cleared. Further, those bytes are not 8-byte aligned, so fix the tracepoint to extract the data as four 2-byte words (they are 2-byte aligned) and reassemble the __be64. The compiler will convert this into a single 8-byte load where the CPU supports it. Fixes: 229105e5cfd9 ("cachefiles: Add auxiliary data trace") Link: https://sashiko.dev/#/patchset/20260810144746.574036-1-dhowells%40redhat.com Signed-off-by: David Howells Link: https://patch.msgid.link/20260827134304.2075713-11-dhowells@redhat.com Acked-by: Paulo Alcantara cc: Paulo Alcantara cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner (Amutable) --- fs/cachefiles/xattr.c | 16 ++++++++-------- include/trace/events/cachefiles.h | 19 +++++++++++++++++-- 2 files changed, 25 insertions(+), 10 deletions(-) diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c index f8ae78b3f7b6..c70bf67e52b0 100644 --- a/fs/cachefiles/xattr.c +++ b/fs/cachefiles/xattr.c @@ -13,6 +13,7 @@ #include #include #include +#include #include "internal.h" #define CACHEFILES_COOKIE_TYPE_DATA 1 @@ -50,7 +51,7 @@ int cachefiles_set_object_xattr(struct cachefiles_object *object) _enter("%x,#%d", object->debug_id, len); - buf = kmalloc(sizeof(struct cachefiles_xattr) + len, GFP_KERNEL); + buf = kmalloc(sizeof(struct cachefiles_xattr) + max(len, sizeof(__be64)), GFP_KERNEL); if (!buf) return -ENOMEM; @@ -60,6 +61,7 @@ int cachefiles_set_object_xattr(struct cachefiles_object *object) buf->content = object->content_info; if (test_bit(FSCACHE_COOKIE_LOCAL_WRITE, &object->cookie->flags)) buf->content = CACHEFILES_CONTENT_DIRTY; + put_unaligned_be64(0, (__be64 *)buf->data); if (len > 0) memcpy(buf->data, fscache_get_aux(object->cookie), len); @@ -77,8 +79,7 @@ int cachefiles_set_object_xattr(struct cachefiles_object *object) trace_cachefiles_vfs_error(object, file_inode(file), ret, cachefiles_trace_setxattr_error); trace_cachefiles_coherency(object, file_inode(file)->i_ino, - be64_to_cpup((__be64 *)buf->data), - buf->content, + buf->data, buf->content, cachefiles_coherency_set_fail); if (ret != -ENOMEM) cachefiles_io_error_obj( @@ -86,8 +87,7 @@ int cachefiles_set_object_xattr(struct cachefiles_object *object) "Failed to set xattr with error %d", ret); } else { trace_cachefiles_coherency(object, file_inode(file)->i_ino, - be64_to_cpup((__be64 *)buf->data), - buf->content, + buf->data, buf->content, cachefiles_coherency_set_ok); } @@ -110,9 +110,10 @@ int cachefiles_check_auxdata(struct cachefiles_object *object, struct file *file int ret = -ESTALE; tlen = sizeof(struct cachefiles_xattr) + len; - buf = kmalloc(tlen, GFP_KERNEL); + buf = kmalloc(sizeof(struct cachefiles_xattr) + max(len, sizeof(__be64)), GFP_KERNEL); if (!buf) return -ENOMEM; + put_unaligned_be64(0, (__be64 *)buf->data); xlen = cachefiles_inject_read_error(); if (xlen == 0) @@ -148,8 +149,7 @@ int cachefiles_check_auxdata(struct cachefiles_object *object, struct file *file out: trace_cachefiles_coherency(object, file_inode(file)->i_ino, - be64_to_cpup((__be64 *)buf->data), - buf->content, why); + buf->data, buf->content, why); kfree(buf); return ret; } diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index 9259bc71049e..e3101410e8b2 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -372,7 +372,7 @@ TRACE_EVENT(cachefiles_rename, TRACE_EVENT(cachefiles_coherency, TP_PROTO(struct cachefiles_object *obj, ino_t ino, - u64 disk_aux, + const void *disk_aux, enum cachefiles_content content, enum cachefiles_coherency_trace why), @@ -389,12 +389,27 @@ TRACE_EVENT(cachefiles_coherency, ), TP_fast_assign( + union { + __be16 s[4]; + __be64 ll; + } x; + __entry->obj = obj->debug_id; __entry->why = why; __entry->content = content; __entry->ino = ino; __entry->aux = be64_to_cpup((__be64 *)obj->cookie->inline_aux); - __entry->disk_aux = disk_aux; + + /* cachefiles_xattr::data is 2-byte aligned but not 8-byte aligned. */ + if (disk_aux) { + x.s[0] = ((__be16 *)disk_aux)[0]; + x.s[1] = ((__be16 *)disk_aux)[1]; + x.s[2] = ((__be16 *)disk_aux)[2]; + x.s[3] = ((__be16 *)disk_aux)[3]; + __entry->disk_aux = be64_to_cpu(x.ll); + } else { + __entry->disk_aux = 0; + } ), TP_printk("o=%08x %s B=%llx c=%u aux=%llx dsk=%llx", From 5a88f78df753993469dab4d1831f8fb4256a9468 Mon Sep 17 00:00:00 2001 From: "Cen Zhang (Microsoft)" Date: Fri, 14 Aug 2026 00:09:44 -0400 Subject: [PATCH 0216/1198] reboot: fix cad_pid use-after-free race cad_pid is a single kernel-wide struct pid pointer. proc_do_cad_pid() reads it and passes it to pid_vnr() without protecting the lifetime of the referenced struct pid. A concurrent writer can replace cad_pid and drop the final reference to the old struct pid after the reader has loaded the pointer but before pid_vnr() has finished dereferencing it, causing a use-after-free. kill_cad_pid() has the same lifetime race when it passes cad_pid to kill_pid(). At the time this issue was reported, an unprivileged user could reach the sysctl through user and PID namespaces because cad_pid was registered in pid_table[]. Moving cad_pid back to the global reboot sysctl table corrected that namespace and permission mismatch, but did not fix the underlying lifetime race. Fix this by treating cad_pid as an RCU-protected pointer at both read sites and by waiting for a grace period before dropping the old reference on the write side. call_rcu(&old_pid->rcu, ...) cannot be used here because free_pid() also queues pid->rcu; queueing the same rcu_head twice can corrupt the RCU callback list. Original KASAN crash stack: kernel/pid.c:545 pid_nr_ns() # reads freed pid->level kernel/pid.c:556 pid_vnr() # calls pid_nr_ns() kernel/pid.c:775 proc_do_cad_pid() # calls pid_vnr(cad_pid) Fixes: 9ec52099e4b8 ("[PATCH] replace cad_pid by a struct pid") Reported-by: AutonomousCodeSecurity@microsoft.com Closes: https://lore.kernel.org/all/20260717210143.4734-1-blbllhy@gmail.com/ Link: https://lore.kernel.org/all/alz5ZYLE4kaq_v2P@redhat.com/ Link: https://lore.kernel.org/all/al4ICz9biJKtdZc4@redhat.com/ Suggested-by: Mateusz Guzik Suggested-by: Bradley Morgan Suggested-by: Oleg Nesterov Suggested-by: Eric W. Biederman Suggested-by: Pavel Tikhomirov Cc: stable@vger.kernel.org Signed-off-by: Cen Zhang (Microsoft) Link: https://patch.msgid.link/20260814040944.16561-1-blbllhy@gmail.com Reviewed-by: Bradley Morgan Reviewed-by: Oleg Nesterov Reviewed-by: Pavel Tikhomirov Signed-off-by: Christian Brauner (Amutable) --- include/linux/sched.h | 2 +- include/linux/sched/signal.h | 5 +---- init/main.c | 2 +- kernel/reboot.c | 19 +++++++++++++++---- kernel/signal.c | 12 ++++++++++++ 5 files changed, 30 insertions(+), 10 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 3f100d69b053..fdafd164a42d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1778,7 +1778,7 @@ static inline bool is_lazy_mmu_mode_active(void) } #endif -extern struct pid *cad_pid; +extern struct pid __rcu *cad_pid; /* * Per process flags diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 584ae88b435e..d45a5476b97d 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -562,10 +562,7 @@ static inline sigset_t *sigmask_to_save(void) return res; } -static inline int kill_cad_pid(int sig, int priv) -{ - return kill_pid(cad_pid, sig, priv); -} +int kill_cad_pid(int sig, int priv); /* These can be the second arg to send_sig_info/send_group_sig_info. */ #define SEND_SIG_NOINFO ((struct kernel_siginfo *) 0) diff --git a/init/main.c b/init/main.c index 92d34e496a33..f46f3a8b3efd 100644 --- a/init/main.c +++ b/init/main.c @@ -1644,7 +1644,7 @@ static noinline void __init kernel_init_freeable(void) */ set_mems_allowed(node_states[N_MEMORY]); - cad_pid = get_pid(task_pid(current)); + rcu_assign_pointer(cad_pid, get_pid(task_pid(current))); smp_prepare_cpus(setup_max_cpus); diff --git a/kernel/reboot.c b/kernel/reboot.c index f070c5c1103a..d177d89fcc33 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -13,7 +13,9 @@ #include #include #include +#include #include +#include #include #include #include @@ -24,8 +26,7 @@ */ static int C_A_D = 1; -struct pid *cad_pid; -EXPORT_SYMBOL(cad_pid); +struct pid __rcu *cad_pid; #if defined(CONFIG_ARM) #define DEFAULT_REBOOT_MODE = REBOOT_HARD @@ -1371,10 +1372,14 @@ static int proc_do_cad_pid(const struct ctl_table *table, int write, void *buffe { struct ctl_table tmp_table = *table; struct pid *new_pid; + struct pid *old_pid; pid_t tmp_pid; int r; - tmp_pid = pid_vnr(cad_pid); + rcu_read_lock(); + tmp_pid = pid_vnr(rcu_dereference(cad_pid)); + rcu_read_unlock(); + tmp_table.data = &tmp_pid; r = proc_dointvec(&tmp_table, write, buffer, lenp, ppos); @@ -1385,7 +1390,13 @@ static int proc_do_cad_pid(const struct ctl_table *table, int write, void *buffe if (!new_pid) return -ESRCH; - put_pid(xchg(&cad_pid, new_pid)); + old_pid = unrcu_pointer(xchg(&cad_pid, RCU_INITIALIZER(new_pid))); + /* + * Wait for cad_pid readers before put_pid(). We cannot use + * call_rcu() here because free_pid() already owns pid->rcu. + */ + synchronize_rcu(); + put_pid(old_pid); return 0; } diff --git a/kernel/signal.c b/kernel/signal.c index bbc0fd4cc4d7..2162fad7b940 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1899,6 +1899,18 @@ int kill_pid(struct pid *pid, int sig, int priv) } EXPORT_SYMBOL(kill_pid); +int kill_cad_pid(int sig, int priv) +{ + int ret; + + rcu_read_lock(); + ret = kill_pid(rcu_dereference(cad_pid), sig, priv); + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL(kill_cad_pid); + #ifdef CONFIG_POSIX_TIMERS /* * These functions handle POSIX timer signals. POSIX timers use From c8329cb590df4a8b3a4e878d289d4b17824db8d1 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 30 Aug 2026 20:19:53 -0700 Subject: [PATCH 0217/1198] dma-buf: fix some kernel-doc warnings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - drop Excess description of @lock from kernel-doc - add missing function/macro short descriptions WARNING: include/linux/dma-fence-array.h:47 Excess struct member 'lock' description in 'dma_fence_array' WARNING: include/linux/dma-fence-chain.h:48 Excess struct member 'lock' description in 'dma_fence_chain' Warning: include/linux/dma-fence-chain.h:82 missing initial short description on line: * dma_fence_chain_alloc Warning: include/linux/dma-fence-chain.h:94 missing initial short description on line: * dma_fence_chain_free Fixes: 5943243914b9 ("dma-buf: use inline lock for the dma-fence-array") Fixes: a408c0ca0c41 ("dma-buf: use inline lock for the dma-fence-chain") Signed-off-by: Randy Dunlap Reviewed-by: Christian König Signed-off-by: Christian König Link: https://lore.kernel.org/r/20260831031956.3410813-1-rdunlap@infradead.org --- include/linux/dma-fence-array.h | 1 - include/linux/dma-fence-chain.h | 9 ++++----- 2 files changed, 4 insertions(+), 6 deletions(-) diff --git a/include/linux/dma-fence-array.h b/include/linux/dma-fence-array.h index 1b1d87579c38..0c49d7ccefb6 100644 --- a/include/linux/dma-fence-array.h +++ b/include/linux/dma-fence-array.h @@ -28,7 +28,6 @@ struct dma_fence_array_cb { /** * struct dma_fence_array - fence to represent an array of fences * @base: fence base class - * @lock: spinlock for fence handling * @num_fences: number of fences in the array * @num_pending: fences in the array still pending * @fences: array of the fences diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h index df3beadf1515..705c4394ac0d 100644 --- a/include/linux/dma-fence-chain.h +++ b/include/linux/dma-fence-chain.h @@ -20,7 +20,6 @@ * @prev: previous fence of the chain * @prev_seqno: original previous seqno before garbage collection * @fence: encapsulated fence - * @lock: spinlock for fence handling */ struct dma_fence_chain { struct dma_fence base; @@ -81,9 +80,8 @@ dma_fence_chain_contained(struct dma_fence *fence) } /** - * dma_fence_chain_alloc - * - * Returns a new struct dma_fence_chain object or NULL on failure. + * dma_fence_chain_alloc - Returns a new &struct dma_fence_chain object or + * %NULL on failure. * * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). The typecast is @@ -93,7 +91,8 @@ dma_fence_chain_contained(struct dma_fence *fence) kmalloc_obj(struct dma_fence_chain) /** - * dma_fence_chain_free + * dma_fence_chain_free - Frees an allocated but not used + * &struct dma_fence_chain object. * @chain: chain node to free * * Frees up an allocated but not used struct dma_fence_chain object. This From 1376afc7660bad2a1a5ee0876898312a486cf8bd Mon Sep 17 00:00:00 2001 From: Kiran Kumar K Date: Tue, 25 Aug 2026 10:47:25 +0530 Subject: [PATCH 0218/1198] octeontx2-af: fix CN20K default MCAM rule removal on port cleanup npc_mcam_free_all_entries() disables every MCAM entry mapped to a port before freeing it. On CN20K, that also disables the default broadcast, multicast, promiscuous, and unicast rules, which causes packet drops when all rules are removed per port. Only disable and free non-default entries. Leave CN20K default rules enabled when freeing the remaining port entries. Fixes: 013717353c03 ("octeontx2-af: npc: cn20k: Tear down default MCAM rules explicitly on free") Signed-off-by: Kiran Kumar K Signed-off-by: Ratheesh Kannoth Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 60922944675b..c34f8d86cc8a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -2957,10 +2957,9 @@ static void npc_mcam_free_all_entries(struct rvu *rvu, struct npc_mcam *mcam, } } - /* Disable the entry */ - npc_enable_mcam_entry(rvu, mcam, blkaddr, index, false); - if (!cn20k_dft_rl) { + /* Disable the entry */ + npc_enable_mcam_entry(rvu, mcam, blkaddr, index, false); mcam->entry2pfvf_map[index] = NPC_MCAM_INVALID_MAP; /* Free the entry in bitmap */ npc_mcam_clear_bit(mcam, index); From 6463655ab2946d13d2ec5efe04a5c2bf9d675f01 Mon Sep 17 00:00:00 2001 From: Chaitanya Kumar Borah Date: Thu, 6 Aug 2026 13:18:19 +0530 Subject: [PATCH 0219/1198] drm/i915/dp_mst: Remove duplicate intel_pfit_compute_config() call MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit mst_stream_compute_config() called intel_pfit_compute_config() twice in a row. commit 5ce9ac1531b8 ("drm/i915/mst: Call intel_pfit_compute_config() for sharpness filter") was erroneously cherry-picked to the fixes tree while commit ca97f5546f19 ("drm/i915/mst: Call intel_pfit_compute_config() for sharpness filter") was already in there. Drop the redundant duplicate call. Cc: Rodrigo Vivi Cc: Ville Syrjälä Cc: Nemesa Garg Cc: Jani Nikula Fixes: 5ce9ac1531b8 ("drm/i915/mst: Call intel_pfit_compute_config() for sharpness filter") Signed-off-by: Chaitanya Kumar Borah Reviewed-by: Nemesa Garg Link: https://patch.msgid.link/20260806074819.2631970-1-chaitanya.kumar.borah@intel.com Signed-off-by: Rodrigo Vivi [Rodrigo: adjusted commit message] (cherry picked from commit ea9f3470d33602fb776ea55443467baacf66f23a) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/display/intel_dp_mst.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index 3be1643f8d03..57daed0b0b36 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -761,10 +761,6 @@ static int mst_stream_compute_config(struct intel_atomic_state *state, pipe_config->sink_format = INTEL_OUTPUT_FORMAT_RGB; pipe_config->output_format = INTEL_OUTPUT_FORMAT_RGB; - ret = intel_pfit_compute_config(pipe_config, conn_state); - if (ret) - return ret; - ret = intel_pfit_compute_config(pipe_config, conn_state); if (ret) return ret; From 045b5bef916d1cb1a52cb6aa68f78fd8b1235cef Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Mon, 31 Aug 2026 12:04:46 +0300 Subject: [PATCH 0220/1198] usb: xhci: Fix HCS_ERST_MAX conversion This fixes one broken line in commit 6d45e9556d4a ("usb: xhci: standardize multi bit-field macros") included in 7.3-rc1 kernel HCS_ERST_MAX holds power of 2 value for maximum number of segments. In the culprit commit, this was incorrectly converted to "shift up 2". On hardware where this field is zero, this results in xhci_alloc_erst() calling dma_alloc_coherent() with size = 0, leading to a horrible splat and non-usable XHCI. Revert the shift-up-2 to the BIT() macro. Fixes: 6d45e9556d4a ("usb: xhci: standardize multi bit-field macros") Cc: Niklas Neronin Signed-off-by: Chen-Yu Tsai Signed-off-by: Mathias Nyman Tested-by: Pierre-David Belanger Link: https://patch.msgid.link/20260831090448.95644-2-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-mem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 7a21ac81f9c8..af8d4b74c4ba 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -2301,7 +2301,7 @@ xhci_alloc_interrupter(struct xhci_hcd *xhci, unsigned int segs, gfp_t flags) if (!segs) segs = ERST_DEFAULT_SEGS; - max_segs = FIELD_GET(HCS_ERST_MAX, xhci->hcs_params2) << 2; + max_segs = BIT(FIELD_GET(HCS_ERST_MAX, xhci->hcs_params2)); segs = min(segs, max_segs); ir = kzalloc_node(sizeof(*ir), flags, dev_to_node(dev)); From 05506a76f13a279a204b6f9b89b8352b646e54d3 Mon Sep 17 00:00:00 2001 From: Michal Pecio Date: Mon, 31 Aug 2026 12:04:47 +0300 Subject: [PATCH 0221/1198] usb: xhci: Fix isochronous scheduling regression An isoc URB without URB_ISO_ASAP should be scheduled immediately after the previous one, unless it's the first submission or prior URBs have completed without resubmitting and the endpoint became idle. An HCD_BH driver must consider URBs pending completion in the BH queue in addition to its own queue. Regrettably, core doesn't provide much information, we can only know if we are being called by completion now. This issue is as old as HCD_BH, affects ehci-hcd too and has no known reproducible impact, as drivers generally resubmit from completion. A recent patch tried to address it by looking at xHCI HW state instead. Obviously, HW has no knowledge of the BH giveback queue either, and the whole solution amounts to testing whether prior URBs have been unlinked instead of completing normally - then a new stream is assumed. This leads to false negatives when a driver simply allows the endpoint to empty out and begins a new stream. New URBs are scheduled into the past and promptly fail with -EXDEV status, causing data loss and worse, because drivers get confused by premature completion, particularly when multiple endpoints are started at once and required to stay in sync. snd-usb-audio underruns the OUT endpoint when userspace fails to supply playback data in time. If this is detected in duplex mode, IN URBs are unlinked and both streams restarted. OUT underruns again before IN even begins, another recovery is attempted and the cycle repeats. Fix this by using the best criteria we can muster, taken from ehci-hcd. This brings false negative rate back to zero and false positive rate to less than ever before in xhci-hcd. Traditional logic was equivalent to: if (list_empty(&ep_ring->td_list) || GET_EP_CTX_STATE(ep_ctx) != EP_STATE_RUNNING) // consider this URB a new stream While free of false negatives, it had easily avoidable false positives: * no check for completion in progress when the list is empty * the ep_ctx check doesn't make up for it at all, but it adds a race - EP state can remain "stopped" for a while after the first submission [mn: add debug message in possible false positive case where driver might incorrectly assume new stream starts mid stream just because td list is empty (URB enqueue is late), and workqueue isn't processing URB completions for this endpoint at the moment] Link: https://lore.kernel.org/linux-usb/20260813005635.34750f8c.michal.pecio@gmail.com/ Fixes: add8469b3e00 ("xhci: fix frame id calculation and checks for isoc URBs") Signed-off-by: Michal Pecio Signed-off-by: Mathias Nyman Link: https://patch.msgid.link/20260831090448.95644-3-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-ring.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 97a1b53c18ef..9847c5bfc41b 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -4312,11 +4312,16 @@ int xhci_queue_isoc_tx_prepare(struct xhci_hcd *xhci, gfp_t mem_flags, check_interval(urb, ep_ctx); /* - * Check if this starts the isoc data flow. Relies on hw setting ep ctx - * state after doorbell ring. Consider adding list_empty(td_list) check + * Schedule the URB discontiguously if all previous URBs have completed. + * XXX core can't tell if completions are pending but not running yet. */ - if (GET_EP_CTX_STATE(ep_ctx) != EP_STATE_RUNNING) + if (list_empty(&ep_ring->td_list) && + !hcd_periodic_completion_in_progress(xhci_to_hcd(xhci), urb->ep)) { + if (GET_EP_CTX_STATE(ep_ctx) == EP_STATE_RUNNING) + xhci_dbg(xhci, "Unexpected running ring at isoc stream start, uframe: %d\n", + xep->next_uframe); xep->next_uframe = -1; + } return xhci_queue_isoc_tx(xhci, mem_flags, urb, slot_id, ep_index); } From ff44dfb03a293bf30e31f98772a1dd316a6071d1 Mon Sep 17 00:00:00 2001 From: Arthur Gautier Date: Mon, 31 Aug 2026 12:04:48 +0300 Subject: [PATCH 0222/1198] xhci: fix lost bounce buffers on TDs spanning several ring segments When a TD reaches a link TRB with data that is not aligned to the endpoint's wMaxPacketSize, xhci_align_td() stages the unalignable tail through the bounce buffer of the ring segment holding that link TRB. xhci_unmap_td_bounce_buffer() later unmaps it and, for IN transfers, copies the data back into the URB's buffer. The enqueue path records the segment that was bounced in td->bounce_seg, under the assumption that a TD never spans more than two ring segments. That assumption does not hold: a TD large enough to span three or more segments crosses several link TRBs and can be bounced at each of them. Only the last one survives in td->bounce_seg, so every earlier bounce buffer is neither copied back nor DMA unmapped. The URB still completes with actual_length equal to the requested length and no error, so the transfer looks successful while a wMaxPacketSize sized hole in the destination buffer silently keeps its previous contents. It also leaks a DMA mapping per dropped bounce. Any sufficiently large and fragmented bulk transfer can hit this. It was found with a USB mass storage device behind xHCI backing a dm-verity target with 512 byte hash blocks, where the stale data is detected rather than silently consumed. The device enumerates as SuperSpeed, so wMaxPacketSize is 1024, while dm-bufio issues one 512 byte bio per hash block. verity_prefetch_io() makes the block layer merge hundreds of them into a single request of up to 512 scatterlist entries of 512 bytes each. At 256 TRBs per ring segment such a TD spans three segments, and every segment boundary falls on an odd multiple of 512, i.e. unaligned to wMaxPacketSize. dm-bufio then caches a hash block holding stale data and dm-verity declares the metadata block corrupted: device-mapper: verity: 8:2: metadata block 10850 is corrupted A reproducer running this under qemu is available at https://github.com/baloo/xhci-verity The bounce state (bounce_buf, bounce_dma, bounce_len, bounce_offs) already lives on the ring segment, so there is nothing extra to track. Keep recording the last bounced segment in td->bounce_seg and, on completion, walk the segments from td->start_seg up to it, unmapping every segment that still has a pending bounce. Stopping at td->bounce_seg rather than td->end_seg matters: a bounce implies the TD continues past that segment's link TRB, so bounce_seg is always strictly before end_seg, and a later TD may already have started in end_seg and been bounced there. Walking that far would copy a foreign bounce buffer into this URB and unmap it twice. It also keeps the walk correct if a TD ever wraps the whole ring so that end_seg == start_seg. [mn: Add ring->num_segs check to prevent unlikely infinite for loop.] Fixes: f9c589e142d0 ("xhci: TD-fragment, align the unsplittable case with a bounce buffer") Cc: stable@vger.kernel.org Suggested-by: Michal Pecio Signed-off-by: Arthur Gautier Signed-off-by: Mathias Nyman Link: https://patch.msgid.link/20260831090448.95644-4-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-ring.c | 32 ++++++++++++++++++++++++-------- 1 file changed, 24 insertions(+), 8 deletions(-) diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 9847c5bfc41b..ec278a9f9540 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -824,21 +824,18 @@ static void xhci_giveback_urb_in_irq(struct xhci_hcd *xhci, usb_hcd_giveback_urb(hcd, urb, status); } -static void xhci_unmap_td_bounce_buffer(struct xhci_hcd *xhci, - struct xhci_ring *ring, struct xhci_td *td) +static void xhci_unmap_one_bounce_buffer(struct xhci_hcd *xhci, + struct xhci_ring *ring, struct xhci_td *td, + struct xhci_segment *seg) { struct device *dev = xhci_to_hcd(xhci)->self.sysdev; - struct xhci_segment *seg = td->bounce_seg; struct urb *urb = td->urb; size_t len; - if (!ring || !seg || !urb) - return; - if (usb_urb_dir_out(urb)) { dma_unmap_single(dev, seg->bounce_dma, ring->bounce_buf_len, DMA_TO_DEVICE); - return; + goto done; } dma_unmap_single(dev, seg->bounce_dma, ring->bounce_buf_len, @@ -854,10 +851,29 @@ static void xhci_unmap_td_bounce_buffer(struct xhci_hcd *xhci, memcpy(urb->transfer_buffer + seg->bounce_offs, seg->bounce_buf, seg->bounce_len); } +done: seg->bounce_len = 0; seg->bounce_offs = 0; } +static void xhci_unmap_td_bounce_buffer(struct xhci_hcd *xhci, + struct xhci_ring *ring, struct xhci_td *td) +{ + struct xhci_segment *seg; + int i = 0; + + if (!td->bounce_seg || !ring || !td->urb) + return; + + /* td->bounce_seg is the last one bounced, unmap them all */ + for (seg = td->start_seg; i++ < ring->num_segs; seg = seg->next) { + if (seg->bounce_len) + xhci_unmap_one_bounce_buffer(xhci, ring, td, seg); + if (seg == td->bounce_seg) + break; + } +} + static void xhci_td_cleanup(struct xhci_hcd *xhci, struct xhci_td *td, struct xhci_ring *ep_ring, int status) { @@ -3685,7 +3701,7 @@ int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags, &trb_buff_len, ring->enq_seg)) { send_addr = ring->enq_seg->bounce_dma; - /* assuming TD won't span 2 segs */ + /* TD bounced at least, and last on this seg */ td->bounce_seg = ring->enq_seg; } } From 9fca7779ad18538188d640b1fdcfea924459542c Mon Sep 17 00:00:00 2001 From: Abel Vesa Date: Wed, 19 Aug 2026 08:55:08 +0300 Subject: [PATCH 0223/1198] Revert "pmdomain: qcom: rpmhpd: Add missing MXC and MMCX power domains for Eliza" This reverts commit b48a0a0a76ccecec60f0568e2af4d89994b08bec, which wrongfully added the MXC and MMCX power domains on Eliza. Even though they are indeed available in cmd-db, which has been the source of information for adding these two, at hardware level they are not actually wired up. Therefore they need to be dropped. Fixes: b48a0a0a76cc ("pmdomain: qcom: rpmhpd: Add missing MXC and MMCX power domains for Eliza") Signed-off-by: Abel Vesa Cc: stable@vger.kernel.org Signed-off-by: Ulf Hansson --- drivers/pmdomain/qcom/rpmhpd.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/pmdomain/qcom/rpmhpd.c b/drivers/pmdomain/qcom/rpmhpd.c index 96e4bd2f5a14..90743275942d 100644 --- a/drivers/pmdomain/qcom/rpmhpd.c +++ b/drivers/pmdomain/qcom/rpmhpd.c @@ -241,13 +241,9 @@ static struct rpmhpd *eliza_rpmhpds[] = { [RPMHPD_GFX] = &gfx, [RPMHPD_LCX] = &lcx, [RPMHPD_LMX] = &lmx, - [RPMHPD_MMCX] = &mmcx, - [RPMHPD_MMCX_AO] = &mmcx_ao, [RPMHPD_MSS] = &mss, [RPMHPD_MX] = &mx, [RPMHPD_MX_AO] = &mx_ao, - [RPMHPD_MXC] = &mxc, - [RPMHPD_MXC_AO] = &mxc_ao, [RPMHPD_NSP] = &nsp, }; From 900f48940abcb5294dac8f1b5335cdc562798734 Mon Sep 17 00:00:00 2001 From: Suraj Kandpal Date: Tue, 11 Aug 2026 23:28:42 +0530 Subject: [PATCH 0224/1198] drm/i915/ddi: add helper to compute DDI clock frequency Add intel_ddi_link_symbol_clock() to return the DDI clock frequency for a given port clock: DP 8b/10b : rate DP 128b/132b (UHBR) : (10 / 32) * rate HDMI FRL : (10 / 18) * rate HDMI TMDS : rate The DP case reuses intel_dp_link_symbol_clock(). This will help in upcoming commits to decide value to be written in DDI_CLK_VALFREQ. Signed-off-by: Suraj Kandpal Reviewed-by: Ankit Nautiyal Link: https://patch.msgid.link/20260811175844.2613721-2-suraj.kandpal@intel.com (cherry picked from commit 5abc20e39dd074e8696387ca6871d6e432baf0cd) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/display/intel_ddi.c | 11 +++++++++++ drivers/gpu/drm/i915/display/intel_ddi.h | 1 + 2 files changed, 12 insertions(+) diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index b8985e1e0a81..02a53c9848e1 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -1529,6 +1529,17 @@ int intel_ddi_level(struct intel_encoder *encoder, return level; } +int intel_ddi_link_symbol_clock(struct intel_encoder *encoder, int clock) +{ + if (intel_encoder_is_dp(encoder)) + return intel_dp_link_symbol_clock(clock); + + if (intel_hdmi_is_frl(clock)) + return DIV_ROUND_CLOSEST(clock * 10, 18); + + return clock; +} + static void hsw_set_signal_levels(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state) diff --git a/drivers/gpu/drm/i915/display/intel_ddi.h b/drivers/gpu/drm/i915/display/intel_ddi.h index 580ecb09b8b6..239d5a403f91 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.h +++ b/drivers/gpu/drm/i915/display/intel_ddi.h @@ -81,6 +81,7 @@ void intel_ddi_sanitize_encoder_pll_mapping(struct intel_encoder *encoder); int intel_ddi_level(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, int lane); +int intel_ddi_link_symbol_clock(struct intel_encoder *encoder, int clock); void intel_ddi_update_active_dpll(struct intel_atomic_state *state, struct intel_encoder *encoder, struct intel_crtc *crtc); From 0cd42b346d13486f8f31c0846f9f2a9241e191c2 Mon Sep 17 00:00:00 2001 From: Suraj Kandpal Date: Tue, 11 Aug 2026 23:28:43 +0530 Subject: [PATCH 0225/1198] drm/i915/cx0: program DDI_CLK_VALFREQ with DDI clock frequency DDI_CLK_VALFREQ is programmed with the port clock, which for DP is the symbol clock computed assuming 8b/10b encoding (link_rate / 10). For DP 128b/132b (UHBR) rates and for HDMI FRL the port clock needs to be modfied. DDI_CLK_VALFREQ does not have any functional impact on H/w, it only records the frequency S/w intends to set. Use intel_ddi_link_symbol_clock() to write the correct DDI clock in kHz. Fixes: 51390cc0e00a ("drm/i915/mtl: Add Support for C10 PHY message bus and pll programming") Fixes: 73fc3abcb797 ("drm/i915/mtl: Enabling/disabling sequence Thunderbolt pll") Signed-off-by: Suraj Kandpal Reviewed-by: Ankit Nautiyal Link: https://patch.msgid.link/20260811175844.2613721-3-suraj.kandpal@intel.com (cherry picked from commit 9ac3ee6c0f92cd09893bd442964fb6b0d6813b5e) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/display/intel_cx0_phy.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_cx0_phy.c b/drivers/gpu/drm/i915/display/intel_cx0_phy.c index 452062417ce9..dbebd7210848 100644 --- a/drivers/gpu/drm/i915/display/intel_cx0_phy.c +++ b/drivers/gpu/drm/i915/display/intel_cx0_phy.c @@ -3233,7 +3233,8 @@ static void intel_cx0pll_enable(struct intel_encoder *encoder, * 8. Program DDI_CLK_VALFREQ to match intended DDI * clock frequency. */ - intel_de_write(display, DDI_CLK_VALFREQ(encoder->port), port_clock); + intel_de_write(display, DDI_CLK_VALFREQ(encoder->port), + intel_ddi_link_symbol_clock(encoder, port_clock)); /* * 9. Set PORT_CLOCK_CTL register PCLK PLL Request @@ -3406,7 +3407,7 @@ void intel_mtl_tbt_pll_enable_clock(struct intel_encoder *encoder, int port_cloc * clock frequency. */ intel_de_write(display, DDI_CLK_VALFREQ(encoder->port), - port_clock); + intel_ddi_link_symbol_clock(encoder, port_clock)); } void intel_mtl_pll_enable(struct intel_encoder *encoder, From 1d79c50e2eeae42b8aad7b5d4d0fe57027174e8a Mon Sep 17 00:00:00 2001 From: Suraj Kandpal Date: Tue, 11 Aug 2026 23:28:44 +0530 Subject: [PATCH 0226/1198] drm/i915/lt_phy: program DDI_CLK_VALFREQ with DDI clock frequency DDI_CLK_VALFREQ is programmed with the port clock, which for DP is the symbol clock computed assuming 8b/10b encoding (link_rate / 10). For DP 128b/132b (UHBR) rates and for HDMI FRL the port clock needs to be modified. DDI_CLK_VALFREQ does not have any functional impact on H/w, it only records the frequency S/w intends to set. Use intel_ddi_link_symbol_clock() to write the correct DDI clock in kHz Fixes: 5ec58d714935 ("drm/i915/lt_phy: Add .enable_clock hook on DDI") Signed-off-by: Suraj Kandpal Reviewed-by: Ankit Nautiyal Link: https://patch.msgid.link/20260811175844.2613721-4-suraj.kandpal@intel.com (cherry picked from commit eaed815ca3483c227e4ec80b86d1b3ce5c2508be) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/display/intel_lt_phy.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_lt_phy.c b/drivers/gpu/drm/i915/display/intel_lt_phy.c index 8fc6d230493f..86492651b01d 100644 --- a/drivers/gpu/drm/i915/display/intel_lt_phy.c +++ b/drivers/gpu/drm/i915/display/intel_lt_phy.c @@ -1976,7 +1976,8 @@ void intel_lt_phy_pll_enable(struct intel_encoder *encoder, * Change. We handle this step in bxt_set_cdclk(). */ /* 10. Program DDI_CLK_VALFREQ to match intended DDI clock frequency. */ - intel_de_write(display, DDI_CLK_VALFREQ(encoder->port), port_clock); + intel_de_write(display, DDI_CLK_VALFREQ(encoder->port), + intel_ddi_link_symbol_clock(encoder, port_clock)); /* 11. Program PORT_CLOCK_CTL[PCLK PLL Request LN0] = 1. */ intel_de_rmw(display, XELPDP_PORT_CLOCK_CTL(display, port), @@ -2023,7 +2024,8 @@ void intel_lt_phy_pll_enable(struct intel_encoder *encoder, lane_phy_pulse_status, lane_phy_pulse_status); } else { - intel_de_write(display, DDI_CLK_VALFREQ(encoder->port), port_clock); + intel_de_write(display, DDI_CLK_VALFREQ(encoder->port), + intel_ddi_link_symbol_clock(encoder, port_clock)); } /* From 7f1172a2ac0d7e50850785e2e65789c8aac8411a Mon Sep 17 00:00:00 2001 From: Nemesa Garg Date: Tue, 18 Aug 2026 15:21:49 +0530 Subject: [PATCH 0227/1198] drm/i915/display: Clear SEL_FETCH_PLANE_CTL on plane disable MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit icl_plane_disable_sel_fetch_arm() wrote SEL_FETCH_PLANE_CTL = 0 only when crtc_state->enable_psr2_sel_fetch was set. If a plane was disabled after selective fetch had been turned off, the guard fired early and left the register's enable bit set in hardware. The bit is harmless until selective fetch is re-enabled. When it is, the hardware resumes fetching for the now-disabled plane and keeps its old DDB range reserved. i9xx_cursor_disable_sel_fetch_arm() has the same guard on SEL_FETCH_CUR_CTL and is fixed the same way. v2: Add same check for cursor also. [sashiko] Cc: stable@vger.kernel.org Fixes: b1f5279b5981 ("drm/i915/psr: Move plane sel fetch configuration into plane source files") Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/work_items/8739 Assisted-by: GitHub-Copilot:claude-opus-4.6 Signed-off-by: Nemesa Garg Reviewed-by: Jouni Högander Signed-off-by: Animesh Manna Link: https://patch.msgid.link/20260818095149.2172935-1-nemesa.garg@intel.com (cherry picked from commit 600a7c9d40e5e0c5544f42d1c9592c8d15224dc0) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/display/intel_cursor.c | 15 ++++++++++----- .../gpu/drm/i915/display/skl_universal_plane.c | 15 ++++++++++----- 2 files changed, 20 insertions(+), 10 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_cursor.c b/drivers/gpu/drm/i915/display/intel_cursor.c index 0673f16f6fd0..86bb96ac449b 100644 --- a/drivers/gpu/drm/i915/display/intel_cursor.c +++ b/drivers/gpu/drm/i915/display/intel_cursor.c @@ -530,13 +530,18 @@ static int i9xx_check_cursor(struct intel_crtc_state *crtc_state, } static void i9xx_cursor_disable_sel_fetch_arm(struct intel_dsb *dsb, - struct intel_plane *plane, - const struct intel_crtc_state *crtc_state) + struct intel_plane *plane) { struct intel_display *display = to_intel_display(plane); enum pipe pipe = plane->pipe; - if (!crtc_state->enable_psr2_sel_fetch) + /* + * Clear this whenever the hardware has selective fetch, not just when + * the current state uses it. The cursor may have been enabled with + * selective fetch earlier and had its enable bit orphaned when the + * feature was switched off. + */ + if (!HAS_PSR2_SEL_FETCH(display)) return; intel_de_write_dsb(display, dsb, SEL_FETCH_CUR_CTL(pipe), 0); @@ -586,7 +591,7 @@ static void i9xx_cursor_update_sel_fetch_arm(struct intel_dsb *dsb, if (crtc_state->enable_psr2_su_region_et) wa_16021440873(dsb, plane, crtc_state, plane_state); else - i9xx_cursor_disable_sel_fetch_arm(dsb, plane, crtc_state); + i9xx_cursor_disable_sel_fetch_arm(dsb, plane); } } @@ -695,7 +700,7 @@ static void i9xx_cursor_update_arm(struct intel_dsb *dsb, if (plane_state) i9xx_cursor_update_sel_fetch_arm(dsb, plane, crtc_state, plane_state); else - i9xx_cursor_disable_sel_fetch_arm(dsb, plane, crtc_state); + i9xx_cursor_disable_sel_fetch_arm(dsb, plane); if (plane->cursor.base != base || plane->cursor.size != fbc_ctl || diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c index 07a683293352..5cda1ab90e40 100644 --- a/drivers/gpu/drm/i915/display/skl_universal_plane.c +++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c @@ -879,13 +879,18 @@ skl_plane_disable_arm(struct intel_dsb *dsb, } static void icl_plane_disable_sel_fetch_arm(struct intel_dsb *dsb, - struct intel_plane *plane, - const struct intel_crtc_state *crtc_state) + struct intel_plane *plane) { struct intel_display *display = to_intel_display(plane); enum pipe pipe = plane->pipe; - if (!crtc_state->enable_psr2_sel_fetch) + /* + * Clear this whenever the hardware has selective fetch, not just when + * the current state uses it. The plane may have been enabled with + * selective fetch earlier and had its enable bit orphaned when the + * feature was switched off. + */ + if (!HAS_PSR2_SEL_FETCH(display)) return; intel_de_write_dsb(display, dsb, SEL_FETCH_PLANE_CTL(pipe, plane->id), 0); @@ -921,7 +926,7 @@ icl_plane_disable_arm(struct intel_dsb *dsb, skl_write_plane_wm(dsb, plane, crtc_state); - icl_plane_disable_sel_fetch_arm(dsb, plane, crtc_state); + icl_plane_disable_sel_fetch_arm(dsb, plane); if (plane_has_normalizer(plane)) intel_de_write_dsb(display, dsb, @@ -1641,7 +1646,7 @@ static void icl_plane_update_sel_fetch_arm(struct intel_dsb *dsb, intel_de_write_dsb(display, dsb, SEL_FETCH_PLANE_CTL(pipe, plane->id), SEL_FETCH_PLANE_CTL_ENABLE); else - icl_plane_disable_sel_fetch_arm(dsb, plane, crtc_state); + icl_plane_disable_sel_fetch_arm(dsb, plane); } static void From aad969968824e97ba8d70dd7a95691f750438ebd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Fri, 17 Jul 2026 18:51:06 +0300 Subject: [PATCH 0228/1198] drm/i915/cdclk: Avoid spurious cdclk sanitization on PTL+ MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Apparently PTL+ no longer has the cd2x pipe select field in CDCLK_CTL. Take that into account during CDCLK sanitization. This currently triggers a spurious CDCLK sanitization during driver load on PTL+ which will causes a visible glitch on all active displays. Cc: stable@vger.kernel.org Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/work_items/8550 Fixes: 2ee8dbd880b1 ("drm/i915/cdclk: Fix up CDCLK_FREQ_DECIMAL without a full PLL re-enable") Signed-off-by: Ville Syrjälä Link: https://patch.msgid.link/20260717155107.17801-1-ville.syrjala@linux.intel.com Reviewed-by: Suraj Kandpal (cherry picked from commit 1786d26887817a779641d3a093c66ac91382113b) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/display/intel_cdclk.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c index a53d88727177..9e5e15b0c4d1 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.c +++ b/drivers/gpu/drm/i915/display/intel_cdclk.c @@ -2381,8 +2381,10 @@ static void bxt_sanitize_cdclk(struct intel_display *display) * dividers both syncing to an active pipe, or asynchronously * (PIPE_NONE). */ - cdctl &= ~bxt_cdclk_cd2x_pipe_mask(display); - cdctl |= bxt_cdclk_cd2x_pipe(display, INVALID_PIPE); + if (DISPLAY_VER(display) < 30) { + cdctl &= ~bxt_cdclk_cd2x_pipe_mask(display); + cdctl |= bxt_cdclk_cd2x_pipe(display, INVALID_PIPE); + } if (cdctl != expected) { if (DISPLAY_VER(display) < 20) { From a154f2ae8eecbf2a4f97376d29b8d38c198b54e7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Wed, 26 Aug 2026 17:31:00 +0300 Subject: [PATCH 0229/1198] drm/i915/cdclk: Fix dg2_power_well_count() return type MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit dg2_power_well_count() is supposed to return an integer, not a boolean. Make it so. Fixes: 9112ce99c1d7 ("drm/i915/cdclk: Extract dg2_power_well_count()") Signed-off-by: Ville Syrjälä Link: https://patch.msgid.link/20260826143100.19401-1-ville.syrjala@linux.intel.com Reviewed-by: Matt Roper (cherry picked from commit dcf423710d0253d7d729c3992bbae0c6197c9c22) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/display/intel_cdclk.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c index 9e5e15b0c4d1..a1a5720996b7 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.c +++ b/drivers/gpu/drm/i915/display/intel_cdclk.c @@ -2715,8 +2715,8 @@ static void intel_set_cdclk(struct intel_display *display, } } -static bool dg2_power_well_count(struct intel_display *display, - const struct intel_cdclk_state *cdclk_state) +static int dg2_power_well_count(struct intel_display *display, + const struct intel_cdclk_state *cdclk_state) { return display->platform.dg2 ? hweight8(cdclk_state->active_pipes) : 0; } From 3785d40831ba5601296283e0197e10e089392757 Mon Sep 17 00:00:00 2001 From: Deepanshu Kartikey Date: Thu, 13 Aug 2026 12:19:02 +0530 Subject: [PATCH 0230/1198] drm/i915: Guard against NULL driver_data in i915_pci_probe() pci_match_device() can return the dummy pci_device_id_any entry when a device is force-bound via sysfs driver_override, in which case ->driver_data is unset (NULL). i915_pci_probe() casts it to struct intel_device_info * unconditionally and dereferences intel_info->require_force_probe, causing a NULL-ptr-deref. Reported-by: syzbot+db96c5ff032f4292a8dc@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=db96c5ff032f4292a8dc Tested-by: syzbot+db96c5ff032f4292a8dc@syzkaller.appspotmail.com Cc: stable@vger.kernel.org Signed-off-by: Deepanshu Kartikey Link: https://patch.msgid.link/20260813064902.367504-1-kartikey406@gmail.com Signed-off-by: Jani Nikula (cherry picked from commit 2727922084672cc274ecea726ea00363c2893731) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_pci.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index 82415af47d54..2f03f95945f1 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -958,6 +958,9 @@ static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) (struct intel_device_info *) ent->driver_data; int err; + if (!intel_info) + return -ENODEV; + if (intel_info->require_force_probe && !id_forced(pdev->device)) { dev_info(&pdev->dev, "Your graphics device %04x is not properly supported by i915 in this\n" From 0606f2114e2dc88fe293858fd991cda2688b8c3a Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Wed, 26 Aug 2026 10:45:32 +0200 Subject: [PATCH 0231/1198] cpuidle: psci: Fix support for probe deferral by dropping the faux device At the conversion to the faux driver/device we broke the support for probe deferral. In hindsight, the move to the faux device seems questionable, as it simply makes the code more complicated and for no good reason. To fix the support for the probe deferral let's therefore restore the old code and drop the faux device. Fixes: af5376a77e87 ("cpuidle: psci: Transition to the faux device interface") Fixes: 5836ebeb4a2b ("cpuidle: psci: Avoid initializing faux device if no DT idle states are present") Fixes: 39cdf87a97fd ("cpuidle: psci: Fix uninitialized variable in dt_idle_state_present()") Cc: stable@vger.kernel.org Reviewed-by: Abel Vesa Signed-off-by: Ulf Hansson Signed-off-by: Ulf Hansson --- drivers/cpuidle/cpuidle-psci.c | 42 +++++++++++++--------------------- 1 file changed, 16 insertions(+), 26 deletions(-) diff --git a/drivers/cpuidle/cpuidle-psci.c b/drivers/cpuidle/cpuidle-psci.c index dcf20ea5ef5e..b250d0dde760 100644 --- a/drivers/cpuidle/cpuidle-psci.c +++ b/drivers/cpuidle/cpuidle-psci.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include #include @@ -428,14 +428,14 @@ static int psci_idle_init_cpu(struct device *dev, int cpu) * to register cpuidle driver then rollback to cancel all CPUs * registration. */ -static int psci_cpuidle_probe(struct faux_device *fdev) +static int psci_cpuidle_probe(struct platform_device *pdev) { int cpu, ret; struct cpuidle_driver *drv; struct cpuidle_device *dev; for_each_present_cpu(cpu) { - ret = psci_idle_init_cpu(&fdev->dev, cpu); + ret = psci_idle_init_cpu(&pdev->dev, cpu); if (ret) goto out_fail; } @@ -455,36 +455,26 @@ static int psci_cpuidle_probe(struct faux_device *fdev) return ret; } -static struct faux_device_ops psci_cpuidle_ops = { +static struct platform_driver psci_cpuidle_driver = { .probe = psci_cpuidle_probe, + .driver = { + .name = "psci-cpuidle", + }, }; -static bool __init dt_idle_state_present(void) -{ - struct device_node *cpu_node __free(device_node) = - of_cpu_device_node_get(cpumask_first(cpu_possible_mask)); - if (!cpu_node) - return false; - - struct device_node *state_node __free(device_node) = - of_get_cpu_state_node(cpu_node, 0); - if (!state_node) - return false; - - return !!of_match_node(psci_idle_state_match, state_node); -} - static int __init psci_idle_init(void) { - struct faux_device *fdev; + struct platform_device *pdev; + int ret; - if (!dt_idle_state_present()) - return 0; + ret = platform_driver_register(&psci_cpuidle_driver); + if (ret) + return ret; - fdev = faux_device_create("psci-cpuidle", NULL, &psci_cpuidle_ops); - if (!fdev) { - pr_err("Failed to create psci-cpuidle device\n"); - return -ENODEV; + pdev = platform_device_register_simple("psci-cpuidle", -1, NULL, 0); + if (IS_ERR(pdev)) { + platform_driver_unregister(&psci_cpuidle_driver); + return PTR_ERR(pdev); } return 0; From a518e63c377574784f49653ef5314c70e2463b0c Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Tue, 25 Aug 2026 17:23:29 +0200 Subject: [PATCH 0232/1198] ovl: return EINVAL instead of EIO in case of mismatched user_ns The EIO was used to signal an internal error (commit 9efb069de4ba ("ovl: add warning on user_ns mismatch")), which is no longer the case. Fixes: 63981fc786da ("ovl: don't warn when the mount is completed from another user namespace") Signed-off-by: Miklos Szeredi Link: https://patch.msgid.link/20260825152330.850645-1-mszeredi@redhat.com Reviewed-by: Amir Goldstein Signed-off-by: Christian Brauner (Amutable) --- fs/overlayfs/super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index e487597337e8..bd0a3f9039d2 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1543,7 +1543,7 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc) struct ovl_fs *ofs = sb->s_fs_info; int err; - err = -EIO; + err = -EINVAL; /* The fscontext fd may have been passed to another user namespace. */ if (fc->user_ns != current_user_ns()) goto out_err; From 399aa12450a61a5c73dc77e73f069ece9687c95d Mon Sep 17 00:00:00 2001 From: Aleksandr Khromov Date: Mon, 24 Aug 2026 13:22:46 +0300 Subject: [PATCH 0233/1198] ksmbd: zero the FS_OBJECT_ID_INFORMATION buffer before filling it in smb2_get_info_filesystem() reports 64 bytes for FS_OBJECT_ID_INFORMATION, that is the whole of struct object_id_info, but writes only 46 of them: - objid[] is 16 bytes, and when the volume UUID is not available only sizeof(stfs.f_fsid) (8) bytes are copied into it; - extended_info.version_string[] is STRING_LENGTH (28) bytes, and only strlen("1.1.0") (5) bytes are copied into it. The response buffer is zeroed on allocation (kvzalloc() in smb2_allocate_rsp_buf()), so for a standalone request the remaining 31 bytes are zero. In a compound request they need not be. The offset of the next response is advanced by the length pinned for the previous one, so if a preceding command wrote its reply into the buffer and then failed, smb2_set_err_rsp() pins only the short error response and the next reply lands inside the area that has already been written. Only the header is cleared there: memset((char *)rsp_hdr, 0, sizeof(struct smb2_hdr) + 2); The client then receives up to 31 bytes of a response it was not meant to see, including one that failed with an access denied error. Clear the structure before filling it in. As a side effect version_string is now NUL terminated. Fixes: e2f34481b24d ("cifsd: add server-side procedures for SMB3") Suggested-by: ChenXiaoSong Cc: stable@vger.kernel.org Signed-off-by: Aleksandr Khromov Signed-off-by: Namjae Jeon --- fs/smb/server/smb2pdu.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index a8046f477d54..486cd745dd21 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -7444,6 +7444,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, struct object_id_info *info; info = (struct object_id_info *)(rsp->Buffer); + memset(info, 0, sizeof(*info)); if (path.mnt->mnt_sb->s_uuid_len == 16) memcpy(info->objid, path.mnt->mnt_sb->s_uuid.b, From c0cd3fc6824122014da2b3b0cb7ddeaa2946ec8e Mon Sep 17 00:00:00 2001 From: Aleksandr Khromov Date: Mon, 24 Aug 2026 21:23:32 +0900 Subject: [PATCH 0234/1198] ksmbd: initialize FileSystemControlFlags in FS_CONTROL_INFORMATION smb2_get_info_filesystem() reports 48 bytes for FS_CONTROL_INFORMATION, that is the whole of struct smb2_fs_control_info, but never assigns FileSystemControlFlags. Those four bytes go to the client as they are found in the response buffer. The buffer is zeroed on allocation, so a standalone request leaks nothing. A compound request can leak: the offset of the next response is advanced by the length pinned for the previous one, so a reply that was written into the buffer and then dropped in favour of the short error response of smb2_set_err_rsp() stays there, and the next reply is laid over it with only the header cleared. ksmbd does not implement quota tracking, so report no control flags. Fixes: e2f34481b24d ("cifsd: add server-side procedures for SMB3") Cc: stable@vger.kernel.org Signed-off-by: Aleksandr Khromov Signed-off-by: Namjae Jeon --- fs/smb/server/smb2pdu.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 486cd745dd21..2fbd9010513e 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -7500,6 +7500,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->FreeSpaceStopFiltering = 0; info->DefaultQuotaThreshold = cpu_to_le64(SMB2_NO_FID); info->DefaultQuotaLimit = cpu_to_le64(SMB2_NO_FID); + info->FileSystemControlFlags = 0; info->Padding = 0; rsp->OutputBufferLength = cpu_to_le32(48); fixed_len = 48; From db2267b27c054a6c2151ff7fbb67927e784f31d6 Mon Sep 17 00:00:00 2001 From: Aleksandr Khromov Date: Tue, 25 Aug 2026 10:19:21 +0900 Subject: [PATCH 0235/1198] ksmbd: fill in FileSysIdentifier in FS_POSIX_INFORMATION smb2_get_info_filesystem() reports 56 bytes for FS_POSIX_INFORMATION, that is the whole of FILE_SYSTEM_POSIX_INFO, but never assigns FileSysIdentifier. Those eight bytes go to the client as they are found in the response buffer. The buffer is zeroed on allocation, so a standalone request leaks nothing. A compound request can leak: the offset of the next response is advanced by the length pinned for the previous one, so a reply that was written into the buffer and then dropped in favour of the short error response of smb2_set_err_rsp() stays there, and the next reply is laid over it with only the header cleared. Report the file system id statfs() returned, which is what the field is for. FileSysIdentifier is __le64 and f_fsid is a pair of ints, so assemble the value first, val[0] as the low half, and convert it on the way out. Fixes: e2f34481b24d ("cifsd: add server-side procedures for SMB3") Cc: stable@vger.kernel.org Signed-off-by: Aleksandr Khromov Signed-off-by: Namjae Jeon --- fs/smb/server/smb2pdu.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 2fbd9010513e..08cb215c3729 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -7523,6 +7523,9 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->UserBlocksAvail = cpu_to_le64(stfs.f_bavail); info->TotalFileNodes = cpu_to_le64(stfs.f_files); info->FreeFileNodes = cpu_to_le64(stfs.f_ffree); + info->FileSysIdentifier = + cpu_to_le64((u64)(u32)stfs.f_fsid.val[1] << 32 | + (u32)stfs.f_fsid.val[0]); rsp->OutputBufferLength = cpu_to_le32(56); fixed_len = 56; } From edcd92df5e1f94e89f8cd410ce41c5cb56e24453 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Wed, 26 Aug 2026 23:03:01 +0900 Subject: [PATCH 0236/1198] MAINTAINERS: Add Paulo Alcantara as an SMBDIRECT co-maintainer Steve French passed away recently. He was a long-time maintainer of Linux's SMB support and will be greatly missed. Add Paulo Alcantara as a co-maintainer of SMBDIRECT. Acked-by: Paulo Alcantara Signed-off-by: Paulo Alcantara Acked-by: Stefan Metzmacher Signed-off-by: Namjae Jeon --- MAINTAINERS | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index e05570c393c5..7e1d14406619 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -25105,10 +25105,9 @@ F: Documentation/admin-guide/LSM/Smack.rst F: security/smack/ SMBDIRECT (RDMA Stream Transport with Read/Write-Offload, MS-SMBD) -M: Steve French -M: Steve French M: Namjae Jeon M: Namjae Jeon +M: Paulo Alcantara R: Stefan Metzmacher R: Tom Talpey L: linux-cifs@vger.kernel.org From 5c944895a94d0317669f1b3409deb0161eaf916b Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Wed, 26 Aug 2026 23:36:28 +0900 Subject: [PATCH 0237/1198] MAINTAINERS: Update the KSMBD entry Steve French passed away recently. He was a long-time maintainer of Linux's SMB support and will be greatly missed. Update the KSMBD entry to no longer list Steve French as a maintainer. Signed-off-by: Namjae Jeon --- MAINTAINERS | 2 -- 1 file changed, 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 7e1d14406619..2a81760e697b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14194,8 +14194,6 @@ F: tools/testing/selftests/ KERNEL SMB3 SERVER (KSMBD) M: Namjae Jeon M: Namjae Jeon -M: Steve French -M: Steve French R: Sergey Senozhatsky R: Tom Talpey R: ChenXiaoSong From d12168084c8c1b6d883c8eca5853929ac5136a9e Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Fri, 28 Aug 2026 10:46:44 +0900 Subject: [PATCH 0238/1198] ksmbd: safely drain sessions during logoff SMB3 multichannel allows requests for one session to run on multiple connections. Wait for all channels bound to a session before freeing shared session objects. A deferred byte-range lock remains counted as a running request and only wakes when its file closes. Wake blocked locks during the drain without unpublishing or modifying their file objects. Synchronous CANCEL requests must invoke their cancellation callback to wake pending operations, while CHANGE_NOTIFY completion remains specific to the asynchronous path. Serialize session teardown with channel registration and previous-session cleanup, and use atomic work-state transitions so LOGOFF, CANCEL, and connection teardown invoke cancellation callbacks only once. Fixes: 76e98a158b20 ("ksmbd: fix race condition between destroy_previous_session() and smb2 operations()") Reported-by: Cheryl Babcock Signed-off-by: Namjae Jeon --- fs/smb/server/connection.c | 8 ++++-- fs/smb/server/mgmt/user_session.c | 13 ++++++++- fs/smb/server/mgmt/user_session.h | 1 + fs/smb/server/smb2pdu.c | 47 +++++++++++++++++++++++++++---- fs/smb/server/vfs_cache.c | 17 +++++++++-- fs/smb/server/vfs_cache.h | 1 + 6 files changed, 77 insertions(+), 10 deletions(-) diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index 91fdd1ddc61f..4cb92d6599ee 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -13,6 +13,7 @@ #include "mgmt/ksmbd_ida.h" #include "mgmt/user_session.h" #include "connection.h" +#include "vfs_cache.h" #include "compress.h" #include "transport_tcp.h" #include "transport_rdma.h" @@ -384,12 +385,12 @@ static void ksmbd_conn_cancel_async_requests(struct ksmbd_conn *conn) spin_lock(&conn->request_lock); list_for_each_entry_safe(work, tmp, &conn->async_requests, async_request_entry) { - if (work->state != KSMBD_WORK_ACTIVE) + if (cmpxchg(&work->state, KSMBD_WORK_ACTIVE, + KSMBD_WORK_CANCELLED) != KSMBD_WORK_ACTIVE) continue; ksmbd_debug(CONN, "Cancel async request id %d\n", work->async_id); - work->state = KSMBD_WORK_CANCELLED; if (work->cancel_fn) work->cancel_fn(work->cancel_argv); } @@ -473,6 +474,9 @@ int ksmbd_conn_wait_idle_sess(struct ksmbd_conn *curr_conn, if (retry_count >= max_timeout) return -EIO; + /* A blocked byte-range lock cannot drain until teardown wakes it. */ + ksmbd_wake_session_blocked_works(sess); + down_read(&conn_list_lock); hash_for_each(conn_list, bkt, conn, hlist) { if (ksmbd_session_is_bound_to_conn(sess, conn)) { diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c index 7022d5d656b4..2eb8f730e99e 100644 --- a/fs/smb/server/mgmt/user_session.c +++ b/fs/smb/server/mgmt/user_session.c @@ -666,10 +666,21 @@ void destroy_previous_session(struct ksmbd_conn *conn, memcmp(user->passkey, prev_user->passkey, user->passkey_sz)) goto out; + down_write(&prev_sess->chann_lock); + if (prev_sess->tearing_down) { + up_write(&prev_sess->chann_lock); + goto out; + } + prev_sess->tearing_down = true; + up_write(&prev_sess->chann_lock); + ksmbd_all_conn_set_status(prev_sess, KSMBD_SESS_NEED_RECONNECT); err = ksmbd_conn_wait_idle_sess(conn, prev_sess); if (err) { - ksmbd_all_conn_set_status(prev_sess, KSMBD_SESS_NEED_SETUP); + down_write(&prev_sess->chann_lock); + prev_sess->tearing_down = false; + up_write(&prev_sess->chann_lock); + ksmbd_all_conn_set_status(prev_sess, KSMBD_SESS_GOOD); goto out; } diff --git a/fs/smb/server/mgmt/user_session.h b/fs/smb/server/mgmt/user_session.h index f8a24c33f7fe..3e52d4cc1324 100644 --- a/fs/smb/server/mgmt/user_session.h +++ b/fs/smb/server/mgmt/user_session.h @@ -42,6 +42,7 @@ struct ksmbd_session { bool sign; bool enc; + bool tearing_down; int state; __u8 *Preauth_HashValue; diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 08cb215c3729..ba0fe25bf366 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -97,6 +97,11 @@ static int register_session_channel(struct ksmbd_session *sess, int rc = 0; down_write(&sess->chann_lock); + if (sess->tearing_down) { + rc = -ESHUTDOWN; + goto out; + } + if (xa_load(&sess->ksmbd_chann_list, (long)conn)) goto out; @@ -3086,17 +3091,41 @@ int smb2_session_logoff(struct ksmbd_work *work) smb2_set_err_rsp(work); return -ENOENT; } + + down_write(&sess->chann_lock); + if (sess->tearing_down) { + up_write(&sess->chann_lock); + ksmbd_conn_unlock(conn); + rsp->hdr.Status = STATUS_USER_SESSION_DELETED; + smb2_set_err_rsp(work); + return -ENOENT; + } + sess->tearing_down = true; + up_write(&sess->chann_lock); + ksmbd_all_conn_set_status(sess, KSMBD_SESS_NEED_RECONNECT); ksmbd_conn_unlock(conn); + err = ksmbd_conn_wait_idle_sess(conn, sess); + if (err) { + down_write(&sess->chann_lock); + sess->tearing_down = false; + up_write(&sess->chann_lock); + ksmbd_all_conn_set_status(sess, KSMBD_SESS_GOOD); + rsp->hdr.Status = STATUS_UNEXPECTED_IO_ERROR; + smb2_set_err_rsp(work); + return err; + } + ksmbd_close_session_fds(work); - ksmbd_conn_wait_idle(conn); if (ksmbd_tree_conn_session_logoff(sess)) { ksmbd_debug(SMB, "Invalid tid %d\n", req->hdr.Id.SyncId.TreeId); rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; smb2_set_err_rsp(work); - return -ENOENT; + err = -ENOENT; + } else { + err = 0; } down_write(&conn->session_lock); @@ -3106,6 +3135,9 @@ int smb2_session_logoff(struct ksmbd_work *work) ksmbd_all_conn_set_status(sess, KSMBD_SESS_NEED_SETUP); + if (err) + return err; + rsp->StructureSize = cpu_to_le16(4); err = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_logoff_rsp)); if (err) { @@ -9685,14 +9717,14 @@ int smb2_cancel(struct ksmbd_work *work) * still on conn->async_requests with a live cancel_fn * pointing at the freed file_lock. */ - if (iter->state != KSMBD_WORK_ACTIVE) + if (cmpxchg(&iter->state, KSMBD_WORK_ACTIVE, + KSMBD_WORK_CANCELLED) != KSMBD_WORK_ACTIVE) break; ksmbd_debug(SMB, "smb2 with AsyncId %llu cancelled command = 0x%x\n", le64_to_cpu(hdr->Id.AsyncId), le16_to_cpu(chdr->Command)); - iter->state = KSMBD_WORK_CANCELLED; if (iter->cancel_fn == smb2_notify_cancel_fn) cancelled_notify = smb2_notify_cancel_claim(iter->cancel_argv); @@ -9721,11 +9753,16 @@ int smb2_cancel(struct ksmbd_work *work) iter == work) continue; + if (cmpxchg(&iter->state, KSMBD_WORK_ACTIVE, + KSMBD_WORK_CANCELLED) != KSMBD_WORK_ACTIVE) + break; + ksmbd_debug(SMB, "smb2 with mid %llu cancelled command = 0x%x\n", le64_to_cpu(hdr->MessageId), le16_to_cpu(chdr->Command)); - iter->state = KSMBD_WORK_CANCELLED; + if (iter->cancel_fn) + iter->cancel_fn(iter->cancel_argv); break; } spin_unlock(&conn->request_lock); diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index 81626d204249..fd2c595f0486 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -846,12 +846,25 @@ static void set_close_state_blocked_works(struct ksmbd_file *fp) spin_lock(&fp->f_lock); list_for_each_entry(cancel_work, &fp->blocked_works, fp_entry) { - cancel_work->state = KSMBD_WORK_CLOSED; - cancel_work->cancel_fn(cancel_work->cancel_argv); + if (xchg(&cancel_work->state, KSMBD_WORK_CLOSED) == + KSMBD_WORK_ACTIVE) + cancel_work->cancel_fn(cancel_work->cancel_argv); } spin_unlock(&fp->f_lock); } +void ksmbd_wake_session_blocked_works(struct ksmbd_session *sess) +{ + struct ksmbd_file_table *ft = &sess->file_table; + struct ksmbd_file *fp; + unsigned int id; + + read_lock(&ft->lock); + idr_for_each_entry(ft->idr, fp, id) + set_close_state_blocked_works(fp); + read_unlock(&ft->lock); +} + int ksmbd_close_fd(struct ksmbd_work *work, u64 id) { struct ksmbd_file *fp; diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index 502efb16f05f..1884f6deb9d0 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -226,6 +226,7 @@ void ksmbd_stop_durable_scavenger(void); bool ksmbd_durable_scavenger_active(void); void ksmbd_close_tree_conn_fds(struct ksmbd_work *work); void ksmbd_close_session_fds(struct ksmbd_work *work); +void ksmbd_wake_session_blocked_works(struct ksmbd_session *sess); int ksmbd_close_inode_fds(struct ksmbd_work *work, struct inode *inode); int ksmbd_init_global_file_table(void); void ksmbd_free_global_file_table(void); From 73f860489e3be2245598d1819226304fc5b87291 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Tue, 25 Aug 2026 09:31:35 +0900 Subject: [PATCH 0239/1198] ksmbd: zero pipe read compound padding Compound response handling extends the last response iov to an eight-byte boundary. smb2_read_pipe() allocates only the payload size, so the alignment padding can expose up to seven bytes of uninitialized kernel heap memory. Allocate the aligned size and clear the unused tail before pinning the response buffer. Fixes: e2b76ab8b5c9 ("ksmbd: add support for read compound") Reported-by: Cheryl Babcock Signed-off-by: Namjae Jeon --- fs/smb/server/smb2pdu.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index ba0fe25bf366..8c589110460a 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -8657,13 +8657,18 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work) } aux_payload_buf = - kvmalloc(rpc_resp->payload_sz, KSMBD_DEFAULT_GFP); + kvmalloc(ALIGN(rpc_resp->payload_sz, 8), + KSMBD_DEFAULT_GFP); if (!aux_payload_buf) { err = -ENOMEM; goto out; } memcpy(aux_payload_buf, rpc_resp->payload, rpc_resp->payload_sz); + if (rpc_resp->payload_sz & 7) + memset(aux_payload_buf + rpc_resp->payload_sz, 0, + ALIGN(rpc_resp->payload_sz, 8) - + rpc_resp->payload_sz); nbytes = rpc_resp->payload_sz; err = ksmbd_iov_pin_rsp_read(work, (void *)rsp, From c61dc7b1b4a3234b4aa3965502908a292238805c Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Tue, 25 Aug 2026 09:32:07 +0900 Subject: [PATCH 0240/1198] ksmbd: propagate DACL parsing errors parse_dacl() silently accepts truncated ACEs and allocation failures, allowing set_info_sec() to continue with an incomplete ACL conversion. Return parsing and allocation errors to parse_sec_desc() so malformed security descriptors are rejected before inode attributes or ACL xattrs are updated. Fixes: e2f34481b24d ("cifsd: add server-side procedures for SMB3") Reported-by: Cheryl Babcock Signed-off-by: Namjae Jeon --- fs/smb/server/smbacl.c | 63 +++++++++++++++++++++++++----------------- 1 file changed, 38 insertions(+), 25 deletions(-) diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c index 8ad2e5a5cca8..4496098eb559 100644 --- a/fs/smb/server/smbacl.c +++ b/fs/smb/server/smbacl.c @@ -383,10 +383,10 @@ void free_acl_state(struct posix_acl_state *state) kfree(state->groups); } -static void parse_dacl(struct mnt_idmap *idmap, - struct smb_acl *pdacl, char *end_of_acl, - struct smb_sid *pownersid, struct smb_sid *pgrpsid, - struct smb_fattr *fattr) +static int parse_dacl(struct mnt_idmap *idmap, + struct smb_acl *pdacl, char *end_of_acl, + struct smb_sid *pownersid, struct smb_sid *pgrpsid, + struct smb_fattr *fattr) { int i, ret; u16 num_aces = 0; @@ -400,13 +400,13 @@ static void parse_dacl(struct mnt_idmap *idmap, bool owner_found = false, group_found = false, others_found = false; if (!pdacl) - return; + return 0; /* validate that we do not go past end of acl */ if (end_of_acl < (char *)pdacl + sizeof(struct smb_acl) || end_of_acl < (char *)pdacl + le16_to_cpu(pdacl->size)) { pr_err("ACL too small to parse DACL\n"); - return; + return -EINVAL; } ksmbd_debug(SMB, "DACL revision %d size %d num aces %d\n", @@ -418,31 +418,31 @@ static void parse_dacl(struct mnt_idmap *idmap, num_aces = le16_to_cpu(pdacl->num_aces); if (num_aces <= 0) - return; + return 0; dacl_size = le16_to_cpu(pdacl->size); if (dacl_size < sizeof(struct smb_acl)) - return; + return -EINVAL; if (num_aces > (dacl_size - sizeof(struct smb_acl)) / (offsetof(struct smb_ace, sid) + offsetof(struct smb_sid, sub_auth) + sizeof(__le16))) - return; + return -EINVAL; ret = init_acl_state(&acl_state, num_aces); if (ret) - return; + return ret; ret = init_acl_state(&default_acl_state, num_aces); if (ret) { free_acl_state(&acl_state); - return; + return ret; } ppace = kmalloc_objs(struct smb_ace *, num_aces, KSMBD_DEFAULT_GFP); if (!ppace) { free_acl_state(&default_acl_state); free_acl_state(&acl_state); - return; + return -ENOMEM; } /* @@ -451,8 +451,10 @@ static void parse_dacl(struct mnt_idmap *idmap, * user/group/other have no permissions */ for (i = 0; i < num_aces; ++i) { - if (end_of_acl - acl_base < acl_size) - break; + if (end_of_acl - acl_base < acl_size) { + ret = -EINVAL; + goto out; + } ppace[i] = (struct smb_ace *)(acl_base + acl_size); acl_base = (char *)ppace[i]; @@ -465,8 +467,10 @@ static void parse_dacl(struct mnt_idmap *idmap, (end_of_acl - acl_base < acl_size + sizeof(__le32) * ppace[i]->sid.num_subauth) || (le16_to_cpu(ppace[i]->size) < - acl_size + sizeof(__le32) * ppace[i]->sid.num_subauth)) - break; + acl_size + sizeof(__le32) * ppace[i]->sid.num_subauth)) { + ret = -EINVAL; + goto out; + } acl_size = le16_to_cpu(ppace[i]->size); ppace[i]->access_req = @@ -541,7 +545,6 @@ static void parse_dacl(struct mnt_idmap *idmap, ((acl_mode & 0700) >> 6) | 0004; } } - kfree(ppace); if (owner_found) { /* The owner must be set to at least read-only. */ @@ -584,10 +587,12 @@ static void parse_dacl(struct mnt_idmap *idmap, fattr->cf_acls = posix_acl_alloc(acl_state.users->n + acl_state.groups->n + 4, KSMBD_DEFAULT_GFP); - if (fattr->cf_acls) { - cf_pace = fattr->cf_acls->a_entries; - posix_state_to_acl(&acl_state, cf_pace); + if (!fattr->cf_acls) { + ret = -ENOMEM; + goto out; } + cf_pace = fattr->cf_acls->a_entries; + posix_state_to_acl(&acl_state, cf_pace); } } @@ -598,14 +603,20 @@ static void parse_dacl(struct mnt_idmap *idmap, fattr->cf_dacls = posix_acl_alloc(default_acl_state.users->n + default_acl_state.groups->n + 4, KSMBD_DEFAULT_GFP); - if (fattr->cf_dacls) { - cf_pdace = fattr->cf_dacls->a_entries; - posix_state_to_acl(&default_acl_state, cf_pdace); + if (!fattr->cf_dacls) { + ret = -ENOMEM; + goto out; } + cf_pdace = fattr->cf_dacls->a_entries; + posix_state_to_acl(&default_acl_state, cf_pdace); } } + ret = 0; +out: + kfree(ppace); free_acl_state(&acl_state); free_acl_state(&default_acl_state); + return ret; } static void set_posix_acl_entries_dacl(struct mnt_idmap *idmap, @@ -966,8 +977,10 @@ int parse_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd, if (dacloffset < sizeof(struct smb_ntsd)) return -EINVAL; - parse_dacl(idmap, dacl_ptr, end_of_acl, - owner_sid_ptr, group_sid_ptr, fattr); + rc = parse_dacl(idmap, dacl_ptr, end_of_acl, + owner_sid_ptr, group_sid_ptr, fattr); + if (rc) + return rc; } return 0; From feca5e70fc963b088377b20879e8cd8237c2fd7d Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Tue, 25 Aug 2026 09:32:23 +0900 Subject: [PATCH 0241/1198] ksmbd: rate limit unmapped SID errors A client can include many structurally valid but unmapped SIDs in a DACL. Logging every mapping failure lets one request generate hundreds of kernel error messages. Rate limit the message to prevent an authenticated client from flooding the kernel log. Fixes: e2f34481b24d ("cifsd: add server-side procedures for SMB3") Reported-by: Cheryl Babcock Signed-off-by: Namjae Jeon --- fs/smb/server/smbacl.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c index 4496098eb559..1fad6ccf3a72 100644 --- a/fs/smb/server/smbacl.c +++ b/fs/smb/server/smbacl.c @@ -528,8 +528,8 @@ static int parse_dacl(struct mnt_idmap *idmap, temp_fattr.cf_uid = INVALID_UID; ret = sid_to_id(idmap, &ppace[i]->sid, SIDOWNER, &temp_fattr); if (ret || uid_eq(temp_fattr.cf_uid, INVALID_UID)) { - pr_err("%s: Error %d mapping Owner SID to uid\n", - __func__, ret); + pr_err_ratelimited("%s: Error %d mapping Owner SID to uid\n", + __func__, ret); continue; } From f25e93768fcc5d8287e50b1ec52a42e4c276df34 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Fri, 28 Aug 2026 08:39:57 +0900 Subject: [PATCH 0242/1198] ksmbd: prevent out-of-bounds reads in share config responses Validate IPC share configuration payload sizes before consuming variable-length fields. Bound veto list parsing and account for the separator byte when deriving the path length. Fixes: a677ebd8ca2f ("ksmbd: validate payload size in ipc response") Reported-by: Kanishka De Silva Reported-by: Farhad Alemi Signed-off-by: Namjae Jeon --- fs/smb/server/mgmt/share_config.c | 40 +++++++++++++++++++++---------- fs/smb/server/transport_ipc.c | 21 ++++++++++------ 2 files changed, 41 insertions(+), 20 deletions(-) diff --git a/fs/smb/server/mgmt/share_config.c b/fs/smb/server/mgmt/share_config.c index b2d9580bddc6..cc9f18ede80d 100644 --- a/fs/smb/server/mgmt/share_config.c +++ b/fs/smb/server/mgmt/share_config.c @@ -146,9 +146,9 @@ static struct ksmbd_share_config *__share_lookup(const char *name) static int parse_veto_list(struct ksmbd_share_config *share, char *veto_list, - int veto_list_sz) + size_t veto_list_sz) { - int sz = 0; + size_t sz; if (!veto_list_sz) return 0; @@ -156,7 +156,7 @@ static int parse_veto_list(struct ksmbd_share_config *share, while (veto_list_sz > 0) { struct ksmbd_veto_pattern *p; - sz = strlen(veto_list); + sz = strnlen(veto_list, veto_list_sz); if (!sz) break; @@ -164,7 +164,7 @@ static int parse_veto_list(struct ksmbd_share_config *share, if (!p) return -ENOMEM; - p->pattern = kstrdup(veto_list, KSMBD_DEFAULT_GFP); + p->pattern = kstrndup(veto_list, sz, KSMBD_DEFAULT_GFP); if (!p->pattern) { kfree(p); return -ENOMEM; @@ -172,6 +172,9 @@ static int parse_veto_list(struct ksmbd_share_config *share, list_add(&p->list, &share->veto_list); + if (sz == veto_list_sz) + break; + veto_list += sz + 1; veto_list_sz -= (sz + 1); } @@ -224,17 +227,28 @@ static struct ksmbd_share_config *share_config_request(struct ksmbd_work *work, } if (!test_share_config_flag(share, KSMBD_SHARE_FLAG_PIPE)) { - int path_len = PATH_MAX; + size_t path_len; - if (resp->payload_sz) - path_len = resp->payload_sz - resp->veto_list_sz; - - share->path = kstrndup(ksmbd_share_config_path(resp), path_len, - KSMBD_DEFAULT_GFP); - if (!share->path) { - ret = -ENOMEM; + if (resp->payload_sz <= resp->veto_list_sz) { + ret = -EINVAL; } else { - ret = 0; + path_len = resp->payload_sz - resp->veto_list_sz; + if (resp->veto_list_sz) + path_len--; + + if (!path_len) { + ret = -EINVAL; + } else { + share->path = kstrndup( + ksmbd_share_config_path(resp), + path_len, KSMBD_DEFAULT_GFP); + if (!share->path) + ret = -ENOMEM; + else + ret = 0; + } + } + if (share->path) { share->path_sz = strlen(share->path); while (share->path_sz > 1 && share->path[share->path_sz - 1] == '/') diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c index 4b0b572a3e1b..e550aa41ad2c 100644 --- a/fs/smb/server/transport_ipc.c +++ b/fs/smb/server/transport_ipc.c @@ -532,14 +532,21 @@ static int ipc_validate_msg(struct ipc_msg_table_entry *entry) if (entry->msg_sz < sizeof(struct ksmbd_share_config_response)) return -EINVAL; - if (resp->payload_sz) { - if (resp->payload_sz < resp->veto_list_sz) - return -EINVAL; + if (strnlen(resp->share_name, sizeof(resp->share_name)) == + sizeof(resp->share_name)) + return -EINVAL; - if (check_add_overflow(sizeof(struct ksmbd_share_config_response), - resp->payload_sz, &msg_sz)) - return -EINVAL; - } + if (resp->veto_list_sz > resp->payload_sz) + return -EINVAL; + + if (resp->flags != KSMBD_SHARE_FLAG_INVALID && + !(resp->flags & KSMBD_SHARE_FLAG_PIPE) && + resp->payload_sz <= resp->veto_list_sz) + return -EINVAL; + + if (check_add_overflow(sizeof(struct ksmbd_share_config_response), + resp->payload_sz, &msg_sz)) + return -EINVAL; break; } case KSMBD_EVENT_LOGIN_REQUEST_EXT: From a506290f59e1c6ce9ac0a13158640bb8fee93471 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Fri, 28 Aug 2026 09:24:49 +0900 Subject: [PATCH 0243/1198] ksmbd: fix listener task lifetime on netdev events The listener thread exits when its listening socket is shutdown. The netdevice notifier shuts down the socket before calling kthread_stop(), so the task_struct can be freed before kthread_stop() gets its reference. Create the listener in a stopped state and hold an extra task_struct reference until kthread_stop_put() completes. Also stop and release listeners before freeing their interface records during TCP teardown. Fixes: 3316a8fc840d ("ksmbd: server: avoid busy polling in accept loop") Reported-by: Farhad Alemi Signed-off-by: Namjae Jeon --- fs/smb/server/transport_tcp.c | 36 ++++++++++++++++++++++++++--------- 1 file changed, 27 insertions(+), 9 deletions(-) diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c index 832e93084605..4968cfc1a572 100644 --- a/fs/smb/server/transport_tcp.c +++ b/fs/smb/server/transport_tcp.c @@ -39,6 +39,7 @@ struct tcp_transport { static const struct ksmbd_transport_ops ksmbd_tcp_transport_ops; static void tcp_stop_kthread(struct task_struct *kthread); +static void ksmbd_tcp_stop_listener(struct interface *iface); static struct interface *alloc_iface(char *ifname); static void ksmbd_tcp_disconnect(struct ksmbd_transport *t); @@ -321,13 +322,20 @@ static int ksmbd_tcp_run_kthread(struct interface *iface) int rc; struct task_struct *kthread; - kthread = kthread_run(ksmbd_kthread_fn, (void *)iface, "ksmbd-%s", - iface->name); + kthread = kthread_create(ksmbd_kthread_fn, (void *)iface, "ksmbd-%s", + iface->name); if (IS_ERR(kthread)) { rc = PTR_ERR(kthread); return rc; } + + /* + * The listener can exit after its socket is shutdown, so keep the + * task_struct alive until the caller has stopped it. + */ + get_task_struct(kthread); iface->ksmbd_kthread = kthread; + wake_up_process(kthread); return 0; } @@ -598,12 +606,7 @@ static int ksmbd_netdev_event(struct notifier_block *nb, unsigned long event, if (iface && iface->state == IFACE_STATE_CONFIGURED) { ksmbd_debug(CONN, "netdev-down event: netdev(%s) is going down\n", iface->name); - kernel_sock_shutdown(iface->ksmbd_socket, SHUT_RDWR); - tcp_stop_kthread(iface->ksmbd_kthread); - iface->ksmbd_kthread = NULL; - sock_release(iface->ksmbd_socket); - iface->ksmbd_socket = NULL; - + ksmbd_tcp_stop_listener(iface); iface->state = IFACE_STATE_DOWN; break; } @@ -631,11 +634,25 @@ static void tcp_stop_kthread(struct task_struct *kthread) if (!kthread) return; - ret = kthread_stop(kthread); + ret = kthread_stop_put(kthread); if (ret) pr_err("failed to stop forker thread\n"); } +static void ksmbd_tcp_stop_listener(struct interface *iface) +{ + if (iface->ksmbd_socket) + kernel_sock_shutdown(iface->ksmbd_socket, SHUT_RDWR); + + tcp_stop_kthread(iface->ksmbd_kthread); + iface->ksmbd_kthread = NULL; + + if (iface->ksmbd_socket) { + sock_release(iface->ksmbd_socket); + iface->ksmbd_socket = NULL; + } +} + void ksmbd_tcp_destroy(void) { struct interface *iface, *tmp; @@ -643,6 +660,7 @@ void ksmbd_tcp_destroy(void) unregister_netdevice_notifier(&ksmbd_netdev_notifier); list_for_each_entry_safe(iface, tmp, &iface_list, entry) { + ksmbd_tcp_stop_listener(iface); list_del(&iface->entry); kfree(iface->name); kfree(iface); From ba9572bc43d04d71ba52ae7f20645f1eafe86875 Mon Sep 17 00:00:00 2001 From: Alon Shakevsky Date: Sat, 29 Aug 2026 06:27:46 +0000 Subject: [PATCH 0244/1198] ksmbd: validate normalized name response length FILE_NORMALIZED_NAME_INFORMATION converts the open file path to UTF-16. smb2_allocate_rsp_buf() leaves these responses in the 448-byte small buffer, and get_file_normalized_name_info() converts the path without checking the remaining space. An authenticated client can query a long path and make smbConvertToUTF16() write beyond work->response_buf. Use the large response buffer for normalized-name queries. Before conversion, verify that the response has room for the worst-case UTF-16 output and its terminator. Fixes: 10aeff72ab82 ("ksmbd: support normalized name information") Assisted-by: Antiproof:GPT-5.6-Sol Signed-off-by: Alon Shakevsky Signed-off-by: Namjae Jeon --- fs/smb/server/smb2pdu.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 8c589110460a..d656832d82ef 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -878,7 +878,8 @@ int smb2_allocate_rsp_buf(struct ksmbd_work *work) req = smb_get_msg(work->request_buf); if ((req->InfoType == SMB2_O_INFO_FILE && (req->FileInfoClass == FILE_FULL_EA_INFORMATION || - req->FileInfoClass == FILE_ALL_INFORMATION)) || + req->FileInfoClass == FILE_ALL_INFORMATION || + req->FileInfoClass == FILE_NORMALIZED_NAME_INFORMATION)) || req->InfoType == SMB2_O_INFO_SECURITY) sz = large_sz; } @@ -6789,7 +6790,7 @@ static int get_file_normalized_name_info(struct ksmbd_work *work, { struct smb2_file_alt_name_info *file_info; char *filename, *normalized, *stream_name; - int conv_len, filename_len; + int buf_free_len, conv_len, filename_len; if (work->conn->dialect < SMB311_PROT_ID) { rsp->hdr.Status = STATUS_NOT_SUPPORTED; @@ -6813,6 +6814,14 @@ static int get_file_normalized_name_info(struct ksmbd_work *work, return -ENOMEM; filename_len = strlen(normalized); + buf_free_len = smb2_resp_buf_len(work, sizeof(*rsp) + + sizeof(*file_info)); + if (buf_free_len < 0 || + (size_t)buf_free_len < (filename_len + 1) * sizeof(__le16)) { + kfree(normalized); + return -EINVAL; + } + file_info = (struct smb2_file_alt_name_info *)rsp->Buffer; conv_len = smbConvertToUTF16((__le16 *)file_info->FileName, normalized, filename_len, From 4dc8f4ee2d46d5d1e749ddd1b94912c72e796162 Mon Sep 17 00:00:00 2001 From: Hongling Zeng Date: Wed, 26 Aug 2026 13:59:53 +0800 Subject: [PATCH 0245/1198] ntfs: handle signal interruption in fallocate The ntfs_attr_fallocate() function checks for pending signals during allocation loops and exits early via 'out' label. However, when a signal interrupts the operation with err == 0, the function returns 0 (success) instead of -EINTR. The signal_pending() checks at the allocation loops jump to 'out' without setting err = -EINTR, so the function returns success even when interrupted by a signal. Set err = -EINTR when jumping to the signal exit path, and only override when no other error is pending. This ensures: - Allocation interrupted by signal returns -EINTR - Allocation that completed successfully before signal arrived returns 0 - Other errors are preserved and not overwritten by -EINTR Fixes: 495e90fa3348 ("ntfs: update attrib operations") Cc: stable@vger.kernel.org Signed-off-by: Hongling Zeng Reviewed-by: Baolin Liu Signed-off-by: Namjae Jeon --- fs/ntfs/attrib.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index b3e941423a3f..848a0d338b89 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -5709,7 +5709,7 @@ int ntfs_attr_fallocate(struct ntfs_inode *ni, loff_t start, loff_t byte_len, bo } if (signal_pending(current)) - goto out; + goto signal_out; vcn += alloc_cnt; try_alloc_cnt -= alloc_cnt; @@ -5730,7 +5730,7 @@ int ntfs_attr_fallocate(struct ntfs_inode *ni, loff_t start, loff_t byte_len, bo up_write(&ni->runlist.lock); mutex_unlock(&ni->mrec_lock); if (err || signal_pending(current)) - goto out; + goto signal_out; vcn += alloc_cnt; try_alloc_cnt -= alloc_cnt; @@ -5756,4 +5756,8 @@ int ntfs_attr_fallocate(struct ntfs_inode *ni, loff_t start, loff_t byte_len, bo mutex_unlock(&ni->mrec_lock); out: return err >= 0 ? 0 : err; +signal_out: + if (!err) + err = -EINTR; + goto out; } From 04cec690b1fd9d1c4c314b91a10d8c68a3acfe18 Mon Sep 17 00:00:00 2001 From: Jameson Thies Date: Tue, 25 Aug 2026 23:45:45 +0000 Subject: [PATCH 0246/1198] usb: typec: ucsi: displayport: Fix OOB altmode array index The UCSI displayport driver indexes the connector's port altmode array with the GET_CURRENT_CAM response after checking it is not 0xff. The port altmode array is UCSI_MAX_ALTMODES elements long. If the PPM returns an invalid GET_CURRENT_CAM response above UCSI_MAX_ALTMODES and not equal to 0xff, the kernel may crash with an array index OOB error. Update the UCSI displayport driver to verify the current cam is less than UCSI_MAX_ALTMODES before accessing the port altmode array. Fixes: af8622f6a585 ("usb: typec: ucsi: Support for DisplayPort alt mode") Cc: stable@vger.kernel.org Signed-off-by: Jameson Thies Reviewed-by: Benson Leung Link: https://patch.msgid.link/20260825234545.2076049-1-jthies@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/ucsi/displayport.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/typec/ucsi/displayport.c b/drivers/usb/typec/ucsi/displayport.c index 7067f2561b84..8d2032d0762c 100644 --- a/drivers/usb/typec/ucsi/displayport.c +++ b/drivers/usb/typec/ucsi/displayport.c @@ -74,7 +74,7 @@ static int ucsi_displayport_enter(struct typec_altmode *alt, u32 *vdo) cur = 0xff; } - if (cur != 0xff) { + if (cur < UCSI_MAX_ALTMODES) { ret = dp->con->port_altmode[cur] == alt ? 0 : -EBUSY; goto err_unlock; } From 9cc5761b8f28f9cef72061094eb5e37e2cd44d97 Mon Sep 17 00:00:00 2001 From: Hongling Zeng Date: Mon, 31 Aug 2026 16:30:14 +0800 Subject: [PATCH 0247/1198] ntfs: take invalidate_lock in ntfs_setattr_size() ntfs_setattr_size() updates i_size and resizes the on-disk attribute without holding mapping->invalidate_lock. Page faults take the lock shared, so a fault racing the resize can resolve a VCN against the transient runlist state of ntfs_non_resident_attr_expand() and fail with a spurious SIGBUS, and can interleave with the size-change epilogue (truncate_pagecache(), i_size_write(), pagecache_isize_extended()). Take invalidate_lock exclusively around the whole resize after inode_dio_wait(), matching the fallocate path and other filesystems such as xfs, which wraps truncate in its mmaplock (= invalidate_lock). Fixes: 9c87959601e8 ("ntfs: update file operations") Cc: stable@vger.kernel.org Reviewed-by: Hyunchul Lee Reviewed-by: Baolin Liu Signed-off-by: Hongling Zeng Signed-off-by: Namjae Jeon --- fs/ntfs/file.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 1969e4f444f7..585ab2145797 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -270,18 +270,25 @@ static int ntfs_setattr_size(struct inode *vi, struct iattr *attr) return err; inode_dio_wait(vi); + + /* + * Serialize with page faults and pagecache instantiation so that + * readers cannot observe the size change until the attribute + * updates below have completed. + */ + filemap_invalidate_lock(vi->i_mapping); if (attr->ia_size > old_size) { truncate_pagecache(vi, old_size); i_size_write(vi, attr->ia_size); pagecache_isize_extended(vi, old_size, attr->ia_size); - } else + } else { truncate_setsize(vi, attr->ia_size); + } err = ntfs_truncate_vfs(vi, attr->ia_size, old_size); - if (err) { + if (err) i_size_write(vi, old_size); - return err; - } + filemap_invalidate_unlock(vi->i_mapping); return err; } From 0fecc393f2060e6bc25138df32cb923ec7071c6b Mon Sep 17 00:00:00 2001 From: Hongling Zeng Date: Mon, 31 Aug 2026 16:32:52 +0800 Subject: [PATCH 0248/1198] ntfs: take invalidate_lock in ntfs_filemap_page_mkwrite() ntfs_filemap_page_mkwrite() calls iomap_page_mkwrite() without holding mapping->invalidate_lock, so a concurrent truncate or fallocate can be in the middle of invalidating pagecache and rewriting the runlist while the write fault maps blocks and dirties the folio. This races with ntfs_attr_fallocate(), which merges clusters into the in-memory runlist, drops the runlist lock, and only afterwards zeroes the newly allocated clusters on disk; and with the punch-hole/insert/collapse paths that free clusters after truncating the cache. Per Documentation/filesystems/locking.rst, ->page_mkwrite() must ensure there are no truncate/invalidate races, "usually mapping->invalidate_lock is suitable for proper serialization". xfs takes its mmaplock (= the invalidate_lock rwsem) shared in exactly this path. Take invalidate_lock shared around iomap_page_mkwrite(). The read-only fault path is already covered because filemap_fault() itself grabs invalidate_lock shared on instantiation/read paths; only page_mkwrite was bypassing it in this driver. Fixes: 9c87959601e8 ("ntfs: update file operations") Cc: stable@vger.kernel.org Reviewed-by: Hyunchul Lee Reviewed-by: Baolin Liu Signed-off-by: Hongling Zeng Co-developed-by: Namjae Jeon Signed-off-by: Namjae Jeon --- fs/ntfs/file.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 585ab2145797..8164326b7812 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -676,6 +676,7 @@ static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) static vm_fault_t ntfs_filemap_page_mkwrite(struct vm_fault *vmf) { struct inode *inode = file_inode(vmf->vma->vm_file); + struct address_space *mapping = inode->i_mapping; vm_fault_t ret; if (NInoWofCompressed(NTFS_I(inode))) @@ -684,7 +685,14 @@ static vm_fault_t ntfs_filemap_page_mkwrite(struct vm_fault *vmf) sb_start_pagefault(inode->i_sb); file_update_time(vmf->vma->vm_file); + /* + * Serialize against truncate/fallocate which hold the lock + * exclusively while invalidating pagecache and changing extents. + */ + filemap_invalidate_lock_shared(mapping); ret = iomap_page_mkwrite(vmf, &ntfs_page_mkwrite_iomap_ops, NULL); + filemap_invalidate_unlock_shared(mapping); + sb_end_pagefault(inode->i_sb); return ret; } @@ -1185,13 +1193,15 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t offset, loff_t le err = file_modified(file); out: + if (!err && mode == 0 && NInoNonResident(ni) && + offset > old_size) { + truncate_pagecache(vi, old_size); + pagecache_isize_extended(vi, old_size, offset); + } + filemap_invalidate_unlock(vi->i_mapping); + if (!err) { - if (mode == 0 && NInoNonResident(ni) && - offset > old_size) { - truncate_pagecache(vi, old_size); - pagecache_isize_extended(vi, old_size, offset); - } NInoSetFileNameDirty(ni); inode_set_mtime_to_ts(vi, inode_set_ctime_current(vi)); mark_inode_dirty(vi); From ca1f4a5ecab084af7f405baa902edbed171b57e6 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 13 Aug 2026 15:25:05 +0200 Subject: [PATCH 0249/1198] s390/time: Use jiffies instead of jiffies_64 Christoph Schlameuss and Alexander Egorenkov reported a data-race reported by KCSAN when jiffies_64 is read: ================================================================== BUG: KCSAN: data-race in do_account_vtime / tick_do_update_jiffies64 write to 0x0000016599ea8600 of 8 bytes by interrupt on cpu 6: tick_do_update_jiffies64+0x140/0x250 =============================================================> BUG: KCSAN: data-race in do_account_vtime / tick_do_update_ji> write to 0x0000016599ea8600 of 8 bytes by interrupt on cpu 6: tick_do_update_jiffies64+0x140/0x250 tick_nohz_handler+0x2e6/0x300 __run_hrtimer+0x156/0x4d0 __hrtimer_run_queues+0xd2/0x150 ... system_call+0x72/0x90 read to 0x0000016599ea8600 of 8 bytes by interrupt on cpu 12: do_account_vtime+0x7d6/0x860 vtime_flush+0x26/0xe0 update_process_times+0x32/0x160 tick_nohz_handler+0x12a/0x300 ... system_call+0x72/0x90 value changed: 0x00000000ffffaa6c -> 0x00000000ffffaa6d ... =============================================================> Problem is that jiffies_64 instead of jiffies is used. Both are at the same address, but only jiffies is of volatile type, which prevents this warning. Change the vtime code so jiffies instead of jiffies_64 is used everywhere. This addresses also the inconsistency that both jiffies and jiffies_64 were used in the original patch which introduced this. Fixes: f341b8dff982 ("s390/vtime: limit MT scaling value updates") Reported-by: Christoph Schlameuss Reported-by: Alexander Egorenkov Reviewed-by: Alexander Egorenkov Tested-by: Alexander Egorenkov Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/kernel/vtime.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index d804e1140c2e..efcbf406f03e 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -32,7 +32,7 @@ static atomic64_t virt_timer_elapsed; DEFINE_PER_CPU(u64, mt_cycles[8]); static DEFINE_PER_CPU(u64, mt_scaling_mult) = { 1 }; static DEFINE_PER_CPU(u64, mt_scaling_div) = { 1 }; -static DEFINE_PER_CPU(u64, mt_scaling_jiffies); +static DEFINE_PER_CPU(unsigned long, mt_scaling_jiffies); static inline void set_vtimer(u64 expires) { @@ -81,7 +81,7 @@ static void update_mt_scaling(void) memcpy(cycles_old, cycles_new, sizeof(u64) * (smp_cpu_mtid + 1)); } - __this_cpu_write(mt_scaling_jiffies, jiffies_64); + __this_cpu_write(mt_scaling_jiffies, jiffies); } static inline u64 update_tsk_timer(unsigned long *tsk_vtime, u64 new) @@ -144,7 +144,7 @@ static int do_account_vtime(struct task_struct *tsk) lc->system_timer += timer; /* Update MT utilization calculation */ - if (smp_cpu_mtid && time_after64(jiffies_64, __this_cpu_read(mt_scaling_jiffies))) + if (smp_cpu_mtid && time_after(jiffies, __this_cpu_read(mt_scaling_jiffies))) update_mt_scaling(); /* Calculate cputime delta */ From b00c10948fa4c9b1f3e2814b97f299ad970f94c8 Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Fri, 14 Aug 2026 14:15:25 +0200 Subject: [PATCH 0250/1198] s390/cpacf: Unpoison instruction results Stop KMSAN from complaining about CPACF outputs being uninitialized. Do not unpoison variable-length parameter blocks: mapping function codes (like CPACF_KIMD_SHA_256) to lengths will be ugly. So let the callers do this once the need arises. Also do not touch cpacf_kma(): this wrapper does not handle cc 1 and cc2 at the moment and has to be reworked. Reviewed-by: Harald Freudenberger Signed-off-by: Ilya Leoshkevich Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/include/asm/cpacf.h | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/s390/include/asm/cpacf.h b/arch/s390/include/asm/cpacf.h index a83683169d98..6174552d856d 100644 --- a/arch/s390/include/asm/cpacf.h +++ b/arch/s390/include/asm/cpacf.h @@ -301,6 +301,7 @@ static __always_inline void __cpacf_query(unsigned int opcode, cpacf_mask_t *mask) { __cpacf_query_insn(opcode, mask, CPACF_FC_QUERY); + kmsan_unpoison_memory(mask, sizeof(*mask)); } static __always_inline int __cpacf_check_opcode(unsigned int opcode) @@ -370,6 +371,7 @@ static __always_inline int cpacf_query_func(unsigned int opcode, static __always_inline void __cpacf_qai(unsigned int opcode, cpacf_qai_t *qai) { __cpacf_query_insn(opcode, qai, CPACF_FC_QUERY_AUTH_INFO); + kmsan_unpoison_memory(qai, sizeof(*qai)); } /** @@ -422,6 +424,7 @@ static inline int cpacf_km(unsigned long func, void *param, [opc] "i" (CPACF_KM) : "cc", "memory", "0", "1"); + kmsan_unpoison_memory(dest, src_len - s.odd); return src_len - s.odd; } @@ -454,6 +457,7 @@ static inline int cpacf_kmc(unsigned long func, void *param, [opc] "i" (CPACF_KMC) : "cc", "memory", "0", "1"); + kmsan_unpoison_memory(dest, src_len - s.odd); return src_len - s.odd; } @@ -587,6 +591,7 @@ static inline int cpacf_kmctr(unsigned long func, void *param, u8 *dest, [opc] "i" (CPACF_KMCTR) : "cc", "memory", "0", "1"); + kmsan_unpoison_memory(dest, src_len - s.odd); return src_len - s.odd; } @@ -619,6 +624,7 @@ static inline void cpacf_prno(unsigned long func, void *param, : [fc] "d" (func), [pba] "d" ((unsigned long)param), [seed] "d" (s.pair), [opc] "i" (CPACF_PRNO) : "cc", "memory", "0", "1"); + kmsan_unpoison_memory(dest, dest_len); } /** From f3c63b8cabbb121866347fe164c23635965b31d7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig=20=28The=20Capable=20Hub=29?= Date: Thu, 6 Aug 2026 18:21:19 +0200 Subject: [PATCH 0251/1198] s390/ap: Drop unused member from ap_device_id MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ap_device_id::driver_info is not used in the kernel. The structure is also not part of API/ABI, so the unused member can just be dropped. Signed-off-by: Uwe Kleine-König (The Capable Hub) Acked-by: Holger Dengler Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- include/linux/device-id/ap.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/include/linux/device-id/ap.h b/include/linux/device-id/ap.h index 0992333a34db..e050abebbf3d 100644 --- a/include/linux/device-id/ap.h +++ b/include/linux/device-id/ap.h @@ -4,7 +4,6 @@ #ifdef __KERNEL__ #include -typedef unsigned long kernel_ulong_t; #endif #define AP_DEVICE_ID_MATCH_CARD_TYPE 0x01 @@ -14,7 +13,6 @@ typedef unsigned long kernel_ulong_t; struct ap_device_id { __u16 match_flags; /* which fields to match against */ __u8 dev_type; /* device type */ - kernel_ulong_t driver_info; }; #endif /* ifndef LINUX_DEVICE_ID_AP_H */ From 7f918871112e8e7c581e99eb8e545af4e59c8367 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Thu, 13 Aug 2026 13:06:54 +0200 Subject: [PATCH 0252/1198] s390/ipl: Fix NULL deref in kdump without re-IPL parm block Some IPL types, like HMC FTP boot or QEMU direct kernel boot, might not provide an IPL parameter block. In this case, reipl_type_init() selects IPL_TYPE_UNKNOWN, and reipl_block_actual remains NULL. kdump passes the re-IPL parameter block to the dump kernel through os_info. Before commit 3b9678472bab ("s390/ipl: correct kdump reipl block checksum calculation"), the os_info entry was added only for IPL types which initialized reipl_block_actual. That commit moved the os_info update to machine_crash_shutdown(), making it unconditional. As a result, set_os_info_reipl_block() dereferences reipl_block_actual for IPL_TYPE_UNKNOWN. This may happen to work by chance when address zero contains readable lowcore data and the resulting empty os_info entry is ignored by the dump kernel. Skip the os_info update when no re-IPL parameter block is available. Kdump then collect the dump and reboot without setting re-IPL parameter block. Fixes: 3b9678472bab ("s390/ipl: correct kdump reipl block checksum calculation") Reviewed-by: Heiko Carstens Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/kernel/ipl.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index d74ef30155aa..8c672e36b397 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -1157,6 +1157,8 @@ static struct attribute_group reipl_nss_attr_group = { void set_os_info_reipl_block(void) { + if (!reipl_block_actual) + return; os_info_entry_add_data(OS_INFO_REIPL_BLOCK, reipl_block_actual, reipl_block_actual->hdr.len); } From 37f61b71cbc0caefc01022a19ee56fc2510e2e6e Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Thu, 13 Aug 2026 13:06:55 +0200 Subject: [PATCH 0253/1198] s390/ipl: Fix NULL deref in dump_reipl without re-IPL parm block Unlike kdump, which passes the re-IPL parameter block through os_info, the stand-alone dump passes it through the IPL parm block address and checksum in lowcore. Some IPL types, like HMC FTP boot or QEMU direct kernel boot, might not provide an IPL parameter block. In this case reipl_type_init() selects IPL_TYPE_UNKNOWN and reipl_block_actual remains NULL. Nevertheless, dump_reipl_run() unconditionally dereferences it when preparing the lowcore fields. This may happen to work by chance when address zero contains readable lowcore data. A zero IPL parameter block address is then stored in lowcore, causing the stand-alone dumper to enter disabled wait after completing the dump. Explicitly store a zero IPL parameter block address and checksum when no re-IPL parameter block is available. This does not change the behavior: the stand-alone dumper completes the dump and halts, while valid re-IPL parameter blocks continue to be handled as before. Fixes: 099b76513992 ("[S390] Automatic IPL after dump") Reviewed-by: Mikhail Zaslonko Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/kernel/ipl.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 8c672e36b397..b1e798f8e1dd 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -1929,7 +1929,8 @@ static struct shutdown_action __refdata dump_action = { static void dump_reipl_run(struct shutdown_trigger *trigger) { struct lowcore *abs_lc; - unsigned int csum; + unsigned long ipib = 0; + unsigned int csum = 0; /* * Set REIPL_CLEAR flag in os_info flags entry indicating @@ -1945,9 +1946,12 @@ static void dump_reipl_run(struct shutdown_trigger *trigger) reipl_type == IPL_TYPE_UNKNOWN) os_info_flags |= OS_INFO_FLAG_REIPL_CLEAR; os_info_entry_add_data(OS_INFO_FLAGS_ENTRY, &os_info_flags, sizeof(os_info_flags)); - csum = (__force unsigned int)cksm(reipl_block_actual, reipl_block_actual->hdr.len, 0); + if (reipl_block_actual) { + ipib = __pa(reipl_block_actual); + csum = (__force unsigned int)cksm(reipl_block_actual, reipl_block_actual->hdr.len, 0); + } abs_lc = get_abs_lowcore(); - abs_lc->ipib = __pa(reipl_block_actual); + abs_lc->ipib = ipib; abs_lc->ipib_checksum = csum; put_abs_lowcore(abs_lc); dump_run(trigger); From 8ac60ae2a307a50b599bf5d300b448d638f3ba29 Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Thu, 6 Aug 2026 11:43:39 +0200 Subject: [PATCH 0254/1198] s390/pci: Fix leak of uninitialized kernel data in SCLP report While report_error_write() checks that the provided buffer is at least as large as the header struct, but not that it is large enough to contain the report with the length claimed by report->length. If user-space provides a short buffer, meaning a larger report->length than the actually written payload, up to around 4K of kernel data from past the kmalloc(len + 1) sized buffer allocated in kernfs_fop_write_iter() will leak into the SCLP report. However, as the entity processing the SCLP is privileged and able to access at least the page including the report, this does not leak data that entity could not access but it is still an out of bounds read and a malformed error report that should be rejected. Fixes: 368704a65be8 ("s390/pci: add report_error attribute") Cc: stable@vger.kernel.org Signed-off-by: Niklas Schnelle Reviewed-by: Benjamin Block Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/pci/pci_sysfs.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/s390/pci/pci_sysfs.c b/arch/s390/pci/pci_sysfs.c index d98d97df792a..bbb76113a4d0 100644 --- a/arch/s390/pci/pci_sysfs.c +++ b/arch/s390/pci/pci_sysfs.c @@ -153,6 +153,9 @@ static ssize_t report_error_write(struct file *filp, struct kobject *kobj, if (off || (count < sizeof(*report))) return -EINVAL; + if (count < (report->length + sizeof(*report))) + return -EINVAL; + ret = sclp_pci_report(report, zdev->fh, zdev->fid); return ret ? ret : count; From a91a5c25a2c3f652178b591facc2395a7dbb59af Mon Sep 17 00:00:00 2001 From: Holger Dengler Date: Thu, 20 Aug 2026 17:50:03 +0200 Subject: [PATCH 0255/1198] s390/zcrypt: Validate length in reply before using it The length information in the reply is used to copy the key token to the target buffer. An invalid information in t->len of the reply may cause an over-read of the target buffer and also a over-write of the target buffer. To prevent that, check t->len before using it. As the available space in destination and source buffer is always larger than the valid length value in the parameter block in the reply, compare t->len with this (already validated) length information. As a side effect, this check also prevents buffer over-read and over-write. Reviewed-by: Harald Freudenberger Signed-off-by: Holger Dengler Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- drivers/s390/crypto/zcrypt_ccamisc.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/drivers/s390/crypto/zcrypt_ccamisc.c b/drivers/s390/crypto/zcrypt_ccamisc.c index d4ce6352b5b2..19909bf43dc9 100644 --- a/drivers/s390/crypto/zcrypt_ccamisc.c +++ b/drivers/s390/crypto/zcrypt_ccamisc.c @@ -1158,8 +1158,21 @@ static int _ip_cprb_helper(u16 cardnr, u16 domain, /* do not check the key here, it may be incomplete */ - /* copy the vlsc key token back */ + /* + * Copy the vlsc key token back. + * The available space in the destination (key_token) and the source + * (t) buffer is always larger as the valid range of prepparm->kb.len. + * Validate t->len by comparing it with the length information in the + * param block of the request (prepparm->kb.len) + * The value range of prepparm->kb.len has been checked above. + */ t = (struct cipherkeytoken *)prepparm->kb.tlv1.key_token; + if (t->len != prepparm->kb.len - 3 * sizeof(uint16_t)) { + ZCRYPT_DBF_ERR("%s reply with invalid key_token length %u\n", + __func__, t->len); + rc = -EIO; + goto out; + } memcpy(key_token, t, t->len); *key_token_size = t->len; From 439077c39d8f7108aea4dd8d4d819b9b864fe84c Mon Sep 17 00:00:00 2001 From: Sumanth Korikkar Date: Tue, 11 Aug 2026 16:23:06 +0200 Subject: [PATCH 0256/1198] s390/diag324: Preserve -EBUSY return code When diag324 reports -EBUSY, the error code is overwritten by the result of copy_to_user() and put_user(). As a result, the ioctl may incorrectly return success instead of -EBUSY. Preserve the original diag324 return code and only return -EFAULT when copying data to userspace fails. Fixes: 90e6f191e1ee ("s390/diag324: Retrieve power readings via diag 0x324") Signed-off-by: Sumanth Korikkar Reviewed-by: Heiko Carstens Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/kernel/diag/diag324.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/s390/kernel/diag/diag324.c b/arch/s390/kernel/diag/diag324.c index fe325c2a2d0d..3eec0cc8fb9e 100644 --- a/arch/s390/kernel/diag/diag324.c +++ b/arch/s390/kernel/diag/diag324.c @@ -182,8 +182,7 @@ long diag324_pibbuf(unsigned long arg) goto out; rc = copy_to_user((void __user *)address, data->pib, data->pib->len); rc |= put_user(data->sequence, &udata->sequence); - if (rc) - rc = -EFAULT; + rc = rc ? -EFAULT : data->rc; out: mutex_unlock(&pibmutex); return rc; From f3110e969ad226ffbb2d9b4bf5387e68d0d9ef40 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Wed, 19 Aug 2026 07:58:55 +0200 Subject: [PATCH 0257/1198] s390/pai: Handle multiple PMU stop callback invocations Handle the following scenario: The kernel protects itself against a very high sampling load and throttles the sampling using: perf_event_throttle() --> PMU->stop() Shortly later the scheduler may terminate the task and removes it from the CPU. It again calls PMU->stop() which results in two invocations of PMU->stop() called back to back. Protect against this and check the PERF_HES_STOPPED bit on function entry. If it is already set return. Clear bit PERF_HES_STOPPED in PMU->start(). Prohibit ioctl(fd, PERF_EVENT_IOC_PERIOD, ...) call for this event. It sets perf_event::event_limit to a positive value and causes perf_event_overflow() to invoke pai_stop() call back function when perf_event::event_limit hits zero. This is not supported because the sample events CRYPTO_ALL and NNPA_ALL are only taken at schedule out of a task. Use list_for_each_entry_safe() for safe iteration over syswide_list in pai_have_samples(). Fixes: 9f66572f2889 ("s390/pai_crypto: Enable per-task and system-wide sampling event") Fixes: 582cc1b28e8c ("s390/pai_ext: Enable per-task and system-wide sampling event") Cc: stable@vger.kernel.org # v6.19+ Signed-off-by: Thomas Richter Reviewed-by: Sumanth Korikkar Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/kernel/perf_pai.c | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-) diff --git a/arch/s390/kernel/perf_pai.c b/arch/s390/kernel/perf_pai.c index cdb8006220ca..05f74d74fad1 100644 --- a/arch/s390/kernel/perf_pai.c +++ b/arch/s390/kernel/perf_pai.c @@ -464,6 +464,7 @@ static void pai_start(struct perf_event *event, int flags, cpump->event = event; } } + event->hw.state &= ~PERF_HES_STOPPED; } static void paicrypt_start(struct perf_event *event, int flags) @@ -510,6 +511,13 @@ static void pai_stop(struct perf_event *event, int flags) struct pai_mapptr *mp = this_cpu_ptr(pai_root[idx].mapptr); struct pai_map *cpump = mp->mapptr; + /* Cope with multiple invocations: + * 1. perf_event_throttle() --> PMU->stop() + * 2. task schedules out --> PMU->stop() + * Check for event already stopped. + */ + if (event->hw.state & PERF_HES_STOPPED) + return; if (!event->attr.sample_period) { /* Counting */ pai_pmu[idx].pmu->read(event); } else { /* Sampling */ @@ -672,9 +680,9 @@ static void pai_have_samples(int idx) { struct pai_mapptr *mp = this_cpu_ptr(pai_root[idx].mapptr); struct pai_map *cpump = mp->mapptr; - struct perf_event *event; + struct perf_event *event, *e2; - list_for_each_entry(event, &cpump->syswide_list, hw.tp_list) + list_for_each_entry_safe(event, e2, &cpump->syswide_list, hw.tp_list) pai_have_sample(event, cpump); } @@ -691,6 +699,17 @@ static void paicrypt_sched_task(struct perf_event_pmu_context *pmu_ctx, pai_have_samples(PAI_PMU_CRYPTO); } +/* Prevent ioctl(fd, PERF_EVENT_IOC_PERIOD, ...) call. + * It sets perf_event::event_limit to a positive value and causes + * perf_event_overflow() to invoke pai_stop() call back function when + * perf_event::event_limit hits zero. This is not supported because the + * sample events CRYPTO_ALL and NNPA_ALL are always taken at schedule out + * of a task. + */ +static int pai_check_period(struct perf_event *event, u64 value) +{ + return -EINVAL; +} /* ============================= paiext ====================================*/ static void paiext_event_destroy(struct perf_event *event) @@ -804,6 +823,7 @@ static struct pmu paicrypt = { .stop = paicrypt_stop, .read = paicrypt_read, .sched_task = paicrypt_sched_task, + .check_period = pai_check_period, .attr_groups = paicrypt_attr_groups }; @@ -1015,6 +1035,7 @@ static struct pmu paiext = { .stop = paiext_stop, .read = paiext_read, .sched_task = paiext_sched_task, + .check_period = pai_check_period, .attr_groups = paiext_attr_groups, }; From 8cff0ac21658fedd4598e9904dd0c518bdaf5856 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 25 Aug 2026 11:49:25 +0200 Subject: [PATCH 0258/1198] s390/pai: Reduce excessive debug feature size The pai debug feature is registered with 256 areas, where each area contains 32 pages. This sums up to a total of 32MiB. The code does not use any debug exceptions, which means that 255 of those areas are never used. In addition all existing debug feature calls have a lower level (5) than the default level (3). This in turn means that without user interaction the debug feature is unused. Reduce the number of areas to 1, and also reduce the number of pages for the remaining area to 1. Since user interaction is required, the user can also increase the size of the remaining area, instead of wasting memory by default. This reduces the total size of the debug feature to 4KiB. Fixes: a3f8423622ef ("s390/pai_crypto: Add PAI crypto characteristics table for parameters") Reviewed-by: Thomas Richter Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/kernel/perf_pai.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/kernel/perf_pai.c b/arch/s390/kernel/perf_pai.c index 05f74d74fad1..5c18c8b82ab7 100644 --- a/arch/s390/kernel/perf_pai.c +++ b/arch/s390/kernel/perf_pai.c @@ -1242,7 +1242,7 @@ static int __init paipmu_setup(void) static int __init pai_init(void) { /* Setup s390dbf facility */ - paidbg = debug_register("pai", 32, 256, 128); + paidbg = debug_register("pai", 1, 1, 128); if (!paidbg) { pr_err("Registration of s390dbf pai failed\n"); return -ENOMEM; From bb06e5a2a031c89b1f1f60ff45ce80f8e4f6ee56 Mon Sep 17 00:00:00 2001 From: Mete Durlu Date: Tue, 25 Aug 2026 14:58:20 +0200 Subject: [PATCH 0259/1198] s390/topology: Switch to common cpu capacity code s390 implementation of cpu capacity management infrastructure code does not do anything different than its common code counterpart. Switch to common code functions and remove the smp_cpu_*_capacity() functions. Make s390 code better align with other architectures which utilize cpu_capacity. No functional changes. Allow cpu_capacity attributes inside sysfs to accurately reflect cpu capacity. ex: $ cat /sys/devices/system/cpu/cpu0/polarization vertical:high $ cat /sys/devices/system/cpu/cpu0/cpu_capacity 1024 $ cat /sys/devices/system/cpu/cpu40/polarization vertical:low $ cat /sys/devices/system/cpu/cpu40/cpu_capacity 128 Prior to commit 6bceea7a1e07 ("arch_topology: Relocate cpu_scale to topology.[h|c]") cpu_capacity attribute was only available to the common arch_topology driver's users. Reflect the correct values to the newly made available attributes. Signed-off-by: Mete Durlu Reviewed-by: Heiko Carstens Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/include/asm/processor.h | 1 - arch/s390/include/asm/smp.h | 4 +--- arch/s390/kernel/smp.c | 16 +++------------- arch/s390/kernel/topology.c | 2 +- 4 files changed, 5 insertions(+), 18 deletions(-) diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index be8369115f6d..9434c76c25b8 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -46,7 +46,6 @@ struct pcpu { unsigned long ec_mask; /* bit mask for ec_xxx functions */ unsigned long ec_clk; /* sigp timestamp for ec_xxx */ unsigned long flags; /* per CPU flags */ - unsigned long capacity; /* cpu capacity for scheduler */ signed char state; /* physical cpu state */ signed char polarization; /* physical polarization */ u16 address; /* physical cpu address */ diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h index fb2bdbf35da5..a6c621e0491c 100644 --- a/arch/s390/include/asm/smp.h +++ b/arch/s390/include/asm/smp.h @@ -30,7 +30,7 @@ static __always_inline unsigned int raw_smp_processor_id(void) return cpu; } -#define arch_scale_cpu_capacity smp_cpu_get_capacity +#define arch_scale_cpu_capacity topology_get_cpu_scale extern struct mutex smp_cpu_state_mutex; extern unsigned int smp_cpu_mt_shift; @@ -53,9 +53,7 @@ extern void smp_save_dump_secondary_cpus(void); extern void smp_yield_cpu(int cpu); extern void smp_cpu_set_polarization(int cpu, int val); extern int smp_cpu_get_polarization(int cpu); -extern void smp_cpu_set_capacity(int cpu, unsigned long val); extern void smp_set_core_capacity(int cpu, unsigned long val); -extern unsigned long smp_cpu_get_capacity(int cpu); extern int smp_cpu_get_cpu_address(int cpu); extern void smp_fill_possible_mask(void); extern void smp_detect_cpus(void); diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 167c72803ccf..32499cad86f0 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -659,23 +659,13 @@ int smp_cpu_get_polarization(int cpu) return per_cpu(pcpu_devices, cpu).polarization; } -void smp_cpu_set_capacity(int cpu, unsigned long val) -{ - per_cpu(pcpu_devices, cpu).capacity = val; -} - -unsigned long smp_cpu_get_capacity(int cpu) -{ - return per_cpu(pcpu_devices, cpu).capacity; -} - void smp_set_core_capacity(int cpu, unsigned long val) { int i; cpu = smp_get_base_cpu(cpu); for (i = cpu; (i <= cpu + smp_cpu_mtid) && (i < nr_cpu_ids); i++) - smp_cpu_set_capacity(i, val); + topology_set_cpu_scale(i, val); } int smp_cpu_get_cpu_address(int cpu) @@ -727,7 +717,7 @@ static int smp_add_core(struct sclp_core_entry *core, cpumask_t *avail, else pcpu->state = CPU_STATE_STANDBY; smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); - smp_cpu_set_capacity(cpu, CPU_CAPACITY_HIGH); + topology_set_cpu_scale(cpu, CPU_CAPACITY_HIGH); set_cpu_present(cpu, true); if (!early && arch_register_cpu(cpu)) set_cpu_present(cpu, false); @@ -967,7 +957,7 @@ void __init smp_prepare_boot_cpu(void) ipl_pcpu->state = CPU_STATE_CONFIGURED; lc->pcpu = (unsigned long)ipl_pcpu; smp_cpu_set_polarization(0, POLARIZATION_UNKNOWN); - smp_cpu_set_capacity(0, CPU_CAPACITY_HIGH); + topology_set_cpu_scale(0, CPU_CAPACITY_HIGH); } void __init smp_setup_processor_id(void) diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 1377c6f3f670..42fc0294f543 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -147,7 +147,7 @@ static void add_cpus_to_mask(struct topology_core *tl_core, cpumask_set_cpu(cpu, &book->mask); cpumask_set_cpu(cpu, &socket->mask); smp_cpu_set_polarization(cpu, tl_core->pp); - smp_cpu_set_capacity(cpu, CPU_CAPACITY_HIGH); + topology_set_cpu_scale(cpu, CPU_CAPACITY_HIGH); } } } From a8603b52b39f520ea8a34def74c23fba87396d3e Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Fri, 28 Aug 2026 19:08:09 -0300 Subject: [PATCH 0260/1198] smb: client: fix data corruption with concurrent writes and O_TRUNC cifs_do_truncate() flushes dirty pages with filemap_write_and_wait() and truncates the file on the server, but in the old code both operations ran without holding i_rwsem or invalidate_lock. A concurrent buffered write via netfs_perform_write() -- which only needs i_rwsem shared -- could dirty new pages after the flush but before the local truncation, and those pages would be silently discarded by cifs_setsize() -> truncate_pagecache(). Fix by acquiring inode_lock (exclusive i_rwsem) and filemap_invalidate_lock at the top of cifs_do_truncate(), so the entire flush-truncate-resize sequence is atomic with respect to: - buffered writes (blocked by exclusive i_rwsem, since netfs_start_io_write takes i_rwsem shared), - read page faults (blocked by exclusive invalidate_lock, since filemap_fault takes it shared), - writeback collection (blocked by netfs_wb_begin/netfs_wb_end around the server truncate and local resize, since netfs_writepages also acquires the wb lock). Fixes: 110fee6b9bb5 ("smb: client: fix missing timestamp updates with O_TRUNC") Signed-off-by: Paulo Alcantara Reviewed-by: Namjae Jeon Cc: Ronnie Sahlberg Cc: Shyam Prasad N Cc: Tom Talpey Cc: Bharath SM Cc: stable@vger.kernel.org --- fs/smb/client/file.c | 28 ++++++++++++++++++---------- 1 file changed, 18 insertions(+), 10 deletions(-) diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 100acc76e9be..61f9c6ccc6be 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -999,42 +999,50 @@ static int cifs_do_truncate(const unsigned int xid, struct dentry *dentry) struct cifs_tcon *tcon; int rc; - rc = filemap_write_and_wait(inode->i_mapping); - if (is_interrupt_error(rc)) + rc = inode_lock_killable(inode); + if (rc) return -ERESTARTSYS; + + filemap_invalidate_lock(inode->i_mapping); + + rc = filemap_write_and_wait(inode->i_mapping); + if (is_interrupt_error(rc)) { + rc = -ERESTARTSYS; + goto out; + } mapping_set_error(inode->i_mapping, rc); cfile = find_writable_file(cinode, FIND_FSUID_ONLY); rc = cifs_file_flush(xid, inode, cfile); if (!rc) { if (cfile) { + struct netfs_inode *ictx = netfs_inode(inode); + tcon = tlink_tcon(cfile->tlink); server = tcon->ses->server; + netfs_wb_begin(ictx, false); rc = server->ops->set_file_size(xid, tcon, cfile, 0, false); if (!rc) { - inode_lock(inode); - filemap_invalidate_lock(inode->i_mapping); netfs_resize_file(&cinode->netfs, 0, true); cifs_setsize(inode, 0); - filemap_invalidate_unlock(inode->i_mapping); - inode_unlock(inode); cifs_invalidate_cache(inode, 0); } + netfs_wb_end(ictx); } else { /* * No cached handle; evict stale pages so they can't * be served after the file is later extended; let * the server's O_TRUNC open response set the i_size */ - inode_lock(inode); - filemap_invalidate_lock(inode->i_mapping); truncate_inode_pages(inode->i_mapping, 0); - filemap_invalidate_unlock(inode->i_mapping); - inode_unlock(inode); cifs_invalidate_cache(inode, 0); } } + +out: + filemap_invalidate_unlock(inode->i_mapping); + inode_unlock(inode); if (cfile) cifsFileInfo_put(cfile); return rc; From 4aa2c106aef4bf3dfd97c30842db0767b26e8428 Mon Sep 17 00:00:00 2001 From: Yunpeng Tian Date: Sun, 30 Aug 2026 18:46:56 -0700 Subject: [PATCH 0261/1198] smb: client: reject SetEA requests that do not fit the request buffer CIFSSMBSetEA() copies the caller's extended attribute value into the SMB request buffer without checking that it fits. The requirement is stated in the source but was never implemented: /*BB add length check to see if it would fit in negotiated SMB buffer size BB */ /* if (ea_value_len > buffer_size - 512 (enough for header)) */ if (ea_value_len) memcpy(parm_data->list.name + name_len + 1, ea_value, ea_value_len); The only bound applied on the way in is in cifs_xattr_set(): #define MAX_EA_VALUE_SIZE CIFSMaxBufSize ... if (size > MAX_EA_VALUE_SIZE) CIFSMaxBufSize is the full payload capacity of the buffer, so a value of exactly that size leaves no room for the SMB header, the TRANS2 parameter block, the fealist header and the EA name that are written ahead of it in the same object. SendReceive() already enforces the correct limit on this very length: if (in_len > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE) but it is called after the copy has taken place. An unprivileged setxattr(2) on an SMB1 mount with a 250-byte name and a 16384-byte value writes 16384 bytes starting 345 bytes into a 16588-byte cifs_request object, ending 141 bytes past it: BUG: KASAN: slab-out-of-bounds in CIFSSMBSetEA+0xabc/0xde0 Write of size 16384 at addr ffff888003aa0159 by task init/68 __asan_memcpy+0x3c/0x60 CIFSSMBSetEA+0xabc/0xde0 cifs_xattr_set+0xd3a/0xff0 __vfs_setxattr+0x13e/0x1a0 The buggy address is located 345 bytes inside of allocated 16588-byte region Apply SendReceive()'s limit to the assembled request before the copy rather than after it, and widen the byte counters so the sum cannot wrap before it is tested. byte_count is also tested against U16_MAX, because it is stored in the 16-bit pSMB->ByteCount. That becomes reachable when CIFSMaxBufSize is raised at module load, where it may be set as high as 1024*127: with a 5-byte EA name and a 65521-byte value, count is exactly U16_MAX while byte_count is 65556, and cpu_to_le16() would truncate it to 20 and transmit a frame whose ByteCount does not match its length. Testing byte_count covers count as well, since byte_count is the larger of the two and count's only 16-bit consumer is written after this point. check_add_overflow() is evaluated first so that total_len is assigned before it is reported. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Yunpeng Tian Reported-by: Mingda Zhang Reported-by: Gongming Wang Reported-by: Qinrun Dai Cc: stable@vger.kernel.org Signed-off-by: Yunpeng Tian Reviewed-by: Namjae Jeon Signed-off-by: Paulo Alcantara --- fs/smb/client/cifssmb.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index 230af243247c..f8aa9e7b4bc6 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -6334,8 +6334,10 @@ CIFSSMBSetEA(const unsigned int xid, struct cifs_tcon *tcon, int name_len; int rc = 0; int bytes_returned = 0; - __u16 params, param_offset, byte_count, offset, count; + __u16 params, param_offset; + unsigned int byte_count, offset, count; int remap = cifs_remap(cifs_sb); + unsigned int total_len; cifs_dbg(FYI, "In SetEA\n"); SetEARetry: @@ -6387,6 +6389,13 @@ CIFSSMBSetEA(const unsigned int xid, struct cifs_tcon *tcon, pSMB->Reserved3 = 0; pSMB->SubCommand = cpu_to_le16(TRANS2_SET_PATH_INFORMATION); byte_count = 3 /* pad */ + params + count; + if (check_add_overflow(in_len, byte_count, &total_len) || + byte_count > U16_MAX || + total_len > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE) { + cifs_dbg(VFS, "EA request too large: %u bytes\n", total_len); + cifs_buf_release(pSMB); + return -E2BIG; + } pSMB->DataCount = cpu_to_le16(count); parm_data->list_len = cpu_to_le32(count); parm_data->list.EA_flags = 0; From 8e359920216689b3b79e0fe8961a77fe312a511f Mon Sep 17 00:00:00 2001 From: Etienne Perot Date: Fri, 28 Aug 2026 21:52:51 +0000 Subject: [PATCH 0262/1198] cgroup: fix spurious SIGKILL of CLONE_INTO_CGROUP children Since commit b69bb476dee9 ("cgroup: fix race between fork and cgroup.kill"), the fork path snapshots the kill_seq of the child's future cgroup into kargs->kill_seq, and cgroup_post_fork() SIGKILLs the child if that cgroup's kill_seq has changed in the meantime, to catch forks racing with a cgroup.kill sweep. For CLONE_INTO_CGROUP, however, the snapshot in cgroup_css_set_fork() is taken before the target cgroup has been resolved: kargs->cgrp is always NULL at this point (it is only set at the end of the function). So the "if (kargs->cgrp)" branch is dead code and the snapshot always records the kill_seq of the parent's cgroup. cgroup_post_fork() then compares it with the kill_seq of the target cgroup, so the child gets SIGKILLed whenever the two cgroups have been killed a different number of times. As a result, once cgroup.kill has been written to a cgroup, every child subsequently cloned into it with clone3(CLONE_INTO_CGROUP) is killed on the spot, for as long as the cgroup exists: kill_seq is not exposed to userspace and never resets. Re-snapshot kill_seq from the target cgroup once it has been resolved, and drop the dead branch at the early snapshot site. This does not reopen the race fixed by b69bb476dee9. For CLONE_INTO_CGROUP, everything from the snapshot to the check in cgroup_post_fork() runs with cgroup_mutex held, and kill_seq is only ever incremented under cgroup_mutex. tj: Updated the comment above kill_seq to reflect the new serialization rules as suggested by Shakeel Butt. Fixes: b69bb476dee9 ("cgroup: fix race between fork and cgroup.kill") Cc: stable@vger.kernel.org Cc: Shakeel Butt Assisted-by: LLM Signed-off-by: Etienne Perot Signed-off-by: Tejun Heo --- include/linux/cgroup-defs.h | 5 ++++- kernel/cgroup/cgroup.c | 6 ++---- 2 files changed, 6 insertions(+), 5 deletions(-) diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 7a631a257613..3754d697854b 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -527,7 +527,10 @@ struct cgroup { int nr_threaded_children; /* # of live threaded child cgroups */ - /* sequence number for cgroup.kill, serialized by css_set_lock. */ + /* + * Sequence number for cgroup.kill. Incremented with both cgroup_mutex + * and css_set_lock held. Readers hold either one. + */ unsigned int kill_seq; struct kernfs_node *kn; /* cgroup kernfs entry */ diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index f87fc4550081..353c8f83439a 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -6777,10 +6777,7 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs) spin_lock_irq(&css_set_lock); cset = task_css_set(current); get_css_set(cset); - if (kargs->cgrp) - kargs->kill_seq = kargs->cgrp->kill_seq; - else - kargs->kill_seq = cset->dfl_cgrp->kill_seq; + kargs->kill_seq = cset->dfl_cgrp->kill_seq; spin_unlock_irq(&css_set_lock); if (!(kargs->flags & CLONE_INTO_CGROUP)) { @@ -6844,6 +6841,7 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs) put_css_set(cset); kargs->cgrp = dst_cgrp; + kargs->kill_seq = dst_cgrp->kill_seq; return ret; err: From 3f4b7d1a49c5c826f3be9b684313eea5b83ac232 Mon Sep 17 00:00:00 2001 From: Etienne Perot Date: Fri, 28 Aug 2026 21:52:52 +0000 Subject: [PATCH 0263/1198] selftests/cgroup: test clone3() into a previously killed cgroup Once cgroup.kill had been written to a cgroup, a stale kill_seq snapshot (taken in cgroup_css_set_fork() before the target cgroup was resolved) caused every child subsequently cloned into that cgroup with clone3(CLONE_INTO_CGROUP) to be SIGKILLed on the spot. Add a regression test: create a cgroup, kill it while it is empty, then clone a child into it and check that the child runs and exits cleanly. On a kernel without the fix, the test fails: not ok 4 test_cgkill_clone_into_killed The test is skipped on kernels without clone3() or without CLONE_INTO_CGROUP. Cc: Shakeel Butt Assisted-by: LLM Signed-off-by: Etienne Perot Signed-off-by: Tejun Heo --- tools/testing/selftests/cgroup/test_kill.c | 55 ++++++++++++++++++++++ 1 file changed, 55 insertions(+) diff --git a/tools/testing/selftests/cgroup/test_kill.c b/tools/testing/selftests/cgroup/test_kill.c index 99cafd9dc013..bac1ddd8cb94 100644 --- a/tools/testing/selftests/cgroup/test_kill.c +++ b/tools/testing/selftests/cgroup/test_kill.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include "kselftest.h" @@ -261,6 +262,59 @@ static int test_cgkill_forkbomb(const char *root) return ret; } +/* + * Test that a cgroup that was killed in the past can still be the target + * of clone3(CLONE_INTO_CGROUP): writing cgroup.kill must only kill the + * tasks in the cgroup at the time of the write, not tasks cloned into + * it afterwards. + */ +static int test_cgkill_clone_into_killed(const char *root) +{ + pid_t pid; + int cgroup_fd = -EBADF; + int ret = KSFT_FAIL; + char *cgroup = NULL; + + cgroup = cg_name(root, "cg_test_clone_into_killed"); + if (!cgroup) + goto cleanup; + + if (cg_create(cgroup)) + goto cleanup; + + /* Kill the cgroup while it is still empty. */ + if (cg_write(cgroup, "cgroup.kill", "1")) + goto cleanup; + + cgroup_fd = dirfd_open_opath(cgroup); + if (cgroup_fd < 0) + goto cleanup; + + pid = clone_into_cgroup(cgroup_fd); + if (pid < 0) { + if (errno == ENOSYS) + ret = KSFT_SKIP; + goto cleanup; + } + + if (pid == 0) + exit(EXIT_SUCCESS); + + /* The child must not be SIGKILLed; it has to exit cleanly. */ + if (clone_reap(pid, WEXITED) != EXIT_SUCCESS) + goto cleanup; + + ret = KSFT_PASS; + +cleanup: + if (cgroup_fd >= 0) + close(cgroup_fd); + if (cgroup) + cg_destroy(cgroup); + free(cgroup); + return ret; +} + #define T(x) { x, #x } struct cgkill_test { int (*fn)(const char *root); @@ -269,6 +323,7 @@ struct cgkill_test { T(test_cgkill_simple), T(test_cgkill_tree), T(test_cgkill_forkbomb), + T(test_cgkill_clone_into_killed), }; #undef T From cd3b9cea675bbfebc223f007dc2f4e79524fa54c Mon Sep 17 00:00:00 2001 From: Amit Sunil Dhamne Date: Thu, 27 Aug 2026 21:16:17 +0000 Subject: [PATCH 0264/1198] usb: typec: tcpm: constrain TCPM_SOURCING_VBUS event handling When a sink detach occurs while waiting for TX send status, the old TCPM_SOURCING_VBUS event along with TCPM_VBUS_EVENT and TCPM_CC_EVENT can be queued in port->pd_events. Because TCPM_SOURCING_VBUS is evaluated after TCPM_VBUS_EVENT and TCPM_CC_EVENT in tcpm_pd_event_handler(), a stale TCPM_SOURCING_VBUS event can override the detach handling and incorrectly set port->vbus_source and port->vbus_present to true. Add a state guard to check that the port is either operating as a Source (tcpm_port_is_source(port)) or in a Fast Role Swap (FRS) state up to FR_SWAP_SNK_SRC_SOURCE_VBUS_APPLIED before processing TCPM_SOURCING_VBUS. Otherwise, discard and log the event. Log snippet for error condition before fix: [72792.204955] state change SRC_ATTACHED -> SRC_STARTUP [rev3 NONE_AMS] [72792.204960] sourcing vbus [72792.204962] VBUS on [72792.204970] AMS POWER_NEGOTIATION start [72792.204974] cc:=4 [72792.205319] state change SRC_STARTUP -> AMS_START [rev3 POWER_NEGOTIATION] [72792.205325] state change AMS_START -> SRC_SEND_CAPABILITIES [rev3 POWER_NEGOTIATION] [72792.205332] PD TX, header: 0x11a1 [72792.216911] PD TX complete, status: 2 [72792.216957] pending state change SRC_SEND_CAPABILITIES -> SRC_SEND_CAPABILITIES @ 150 ms [rev3 POWER_NEGOTIATION] [72792.218005] VBUS off [72792.218013] pending state change SRC_SEND_CAPABILITIES -> SNK_UNATTACHED @ 650 ms [rev3 POWER_NEGOTIATION] [72792.218020] VBUS VSAFE0V [72792.218024] state change SRC_SEND_CAPABILITIES -> SNK_UNATTACHED [rev3 POWER_NEGOTIATION] [72792.218458] CC1: 2 -> 0, CC2: 0 -> 0 [state SNK_UNATTACHED, polarity 0, disconnected] [72792.218467] VBUS on --> VBUS left on [72792.218980] disable vbus discharge ret:0 [72792.235193] Start toggling After fix: [ 1195.291691] state change SRC_ATTACHED -> SRC_STARTUP [rev3 NONE_AMS] [ 1195.291698] sourcing vbus [ 1195.291700] VBUS on [ 1195.291707] AMS POWER_NEGOTIATION start [ 1195.291710] cc:=4 [ 1195.291758] state change SRC_STARTUP -> AMS_START [rev3 POWER_NEGOTIATION] [ 1195.291794] state change AMS_START -> SRC_SEND_CAPABILITIES [rev3 POWER_NEGOTIATION] [ 1195.291798] PD TX, header: 0x11a1 [ 1195.297056] PD TX complete, status: 2 [ 1195.297092] pending state change SRC_SEND_CAPABILITIES -> SRC_SEND_CAPABILITIES @ 150 ms [rev3 POWER_NEGOTIATION] [ 1195.297177] VBUS off [ 1195.297184] pending state change SRC_SEND_CAPABILITIES -> SNK_UNATTACHED @ 650 ms [rev3 POWER_NEGOTIATION] [ 1195.297227] CC1: 2 -> 0, CC2: 0 -> 0 [state SRC_SEND_CAPABILITIES, polarity 0, disconnected] [ 1195.307469] cc:=2 [ 1195.307544] pending state change SRC_SEND_CAPABILITIES -> SNK_UNATTACHED @ 650 ms [rev3 POWER_NEGOTIATION] [ 1195.307555] Discarding sourcing vbus! Invalid state SRC_SEND_CAPABILITIES [ 1195.957636] state change SRC_SEND_CAPABILITIES -> SNK_UNATTACHED [delayed 650 ms] [ 1195.957732] disable vbus discharge ret:0 [ 1195.970196] Start toggling [ 1195.970468] VBUS off [ 1196.051637] VBUS off [ 1196.051642] VBUS VSAFE0V Fixes: 8dc4bd073663 ("usb: typec: tcpm: Add support for Sink Fast Role SWAP(FRS)") Cc: stable Assisted-by: Gemini:gemini-3.1-pro Signed-off-by: Amit Sunil Dhamne Reviewed-by: Badhri Jagan Sridharan Acked-by: Heikki Krogerus Link: https://patch.msgid.link/20260827-sourcing-vbus-v1-1-9be1aca991a0@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tcpm/tcpm.c | 28 ++++++++++++++++++++++------ 1 file changed, 22 insertions(+), 6 deletions(-) diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index a8cd1959c426..2d6b14aa2085 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -7119,16 +7119,32 @@ static void tcpm_pd_event_handler(struct kthread_work *work) } } if (events & TCPM_SOURCING_VBUS) { - tcpm_log(port, "sourcing vbus"); /* * In fast role swap case TCPC autonomously sources vbus. Set vbus_source - * true as TCPM wouldn't have called tcpm_set_vbus. + * true conditionally as TCPM wouldn't have called tcpm_set_vbus. + * If TCPM calls tcpm_set_vbus to source vbus, vbus_source would already + * be true. * - * When vbus is sourced on the command on TCPM i.e. TCPM called - * tcpm_set_vbus to source vbus, vbus_source would already be true. + * When TCPM_FRS_EVENT and TCPM_SOURCING_VBUS arrive simultaneously, + * handling TCPM_FRS_EVENT above transitions the state to AMS_START + * with upcoming_state FR_SWAP_SEND. */ - port->vbus_source = true; - _tcpm_pd_vbus_on(port); + + if (tcpm_port_is_source(port) || + tcpm_port_is_debug_source(port) || + (port->state == AMS_START && port->upcoming_state == FR_SWAP_SEND) || + port->state == FR_SWAP_SEND || + port->state == FR_SWAP_SEND_TIMEOUT || + port->state == FR_SWAP_SNK_SRC_TRANSITION_TO_OFF || + port->state == FR_SWAP_SNK_SRC_NEW_SINK_READY || + port->state == FR_SWAP_SNK_SRC_SOURCE_VBUS_APPLIED) { + tcpm_log(port, "sourcing vbus"); + port->vbus_source = true; + _tcpm_pd_vbus_on(port); + } else { + tcpm_log(port, "Discarding sourcing vbus! Invalid state %s", + tcpm_states[port->state]); + } } if (events & TCPM_PORT_CLEAN) { tcpm_log(port, "port clean"); From 23761359861ca4bb087540937dfea8b0716914c2 Mon Sep 17 00:00:00 2001 From: Wanwu Li Date: Thu, 27 Aug 2026 16:07:36 +0800 Subject: [PATCH 0265/1198] sched_ext: Fix timer pinning and return value in scx_central central_timerfn() re-arms the timer with a hardcoded BPF_F_TIMER_CPU_PIN flag and ignores the return value, defeating start_central_timer()'s -EINVAL fallback for kernels without the flag (<6.7): on such kernels the first tick kills the timer permanently with no diagnostic. Honor timer_pinned and check the return like the initial arm does. Fixes: 22a920209ab6 ("sched_ext: Implement tickless support") Signed-off-by: Wanwu Li Signed-off-by: Tejun Heo --- tools/sched_ext/scx_central.bpf.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/tools/sched_ext/scx_central.bpf.c b/tools/sched_ext/scx_central.bpf.c index 64dd60b3e922..65dae9e45400 100644 --- a/tools/sched_ext/scx_central.bpf.c +++ b/tools/sched_ext/scx_central.bpf.c @@ -299,6 +299,7 @@ static int central_timerfn(void *map, int *key, struct bpf_timer *timer) u64 now = scx_bpf_now(); u64 nr_to_kick = nr_queued; s32 i, curr_cpu; + int ret; curr_cpu = bpf_get_smp_processor_id(); if (timer_pinned && (curr_cpu != central_cpu)) { @@ -332,7 +333,10 @@ static int central_timerfn(void *map, int *key, struct bpf_timer *timer) scx_bpf_kick_cpu(cpu, SCX_KICK_PREEMPT); } - bpf_timer_start(timer, TIMER_INTERVAL_NS, BPF_F_TIMER_CPU_PIN); + ret = bpf_timer_start(timer, TIMER_INTERVAL_NS, + timer_pinned ? BPF_F_TIMER_CPU_PIN : 0); + if (ret) + scx_bpf_error("bpf_timer_start failed (%d)", ret); __sync_fetch_and_add(&nr_timers, 1); return 0; } From b6ee92d7f7f0498d1f776d0b125a2f6bcedf0891 Mon Sep 17 00:00:00 2001 From: Wanwu Li Date: Thu, 27 Aug 2026 16:07:37 +0800 Subject: [PATCH 0266/1198] sched_ext: Fix vtime delta loss in scx_flatcg cgroup migration fcg_cgroup_move() lost the signed vtime offset across cgroup migration in the mechanical conversion to time helpers: time_delta() clamps negative deltas to 0, so a queued task (whose dsq_vtime is normally behind the source frontier) loses its accumulated vtime credit and lands exactly at the destination frontier instead of keeping its relative position. Restore the wrapping signed subtraction. Fixes: 62addc6dbf36 ("sched_ext: Use time helpers in BPF schedulers") Signed-off-by: Wanwu Li Signed-off-by: Tejun Heo --- tools/sched_ext/scx_flatcg.bpf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/sched_ext/scx_flatcg.bpf.c b/tools/sched_ext/scx_flatcg.bpf.c index 64cf4dd964d6..454ebb820c5e 100644 --- a/tools/sched_ext/scx_flatcg.bpf.c +++ b/tools/sched_ext/scx_flatcg.bpf.c @@ -937,7 +937,7 @@ void BPF_STRUCT_OPS(fcg_cgroup_move, struct task_struct *p, if (!(from_cgc = find_cgrp_ctx(from)) || !(to_cgc = find_cgrp_ctx(to))) return; - delta = time_delta(p->scx.dsq_vtime, from_cgc->tvtime_now); + delta = (s64)(p->scx.dsq_vtime - from_cgc->tvtime_now); scx_bpf_task_set_dsq_vtime(p, to_cgc->tvtime_now + delta); } From 84590dbb9f3519e865ee8396494ac7186b625fef Mon Sep 17 00:00:00 2001 From: Wanwu Li Date: Thu, 27 Aug 2026 16:07:38 +0800 Subject: [PATCH 0267/1198] sched_ext: Check bpf_timer_start return values in scx_qmap monitor_timerfn(), lowpri_timerfn() and round_robin_timerfn() ignore bpf_timer_start()'s return value: a failed re-arm silently stops the periodic heartbeat, starving every task parked in LOWPRI_DSQ (lowpri) or freezing cid rotation (round-robin). Check the returns and raise scx_bpf_error(), matching the init paths. Signed-off-by: Wanwu Li Signed-off-by: Tejun Heo --- tools/sched_ext/scx_qmap.bpf.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c index 5bb8b90a275a..9f6e61d7ca07 100644 --- a/tools/sched_ext/scx_qmap.bpf.c +++ b/tools/sched_ext/scx_qmap.bpf.c @@ -1246,7 +1246,8 @@ static int monitor_timerfn(void *map, int *key, struct bpf_timer *timer) scx_read_event(&events, SCX_EV_BYPASS_ACTIVATE)); } - bpf_timer_start(timer, ONE_SEC_IN_NS, 0); + if (bpf_timer_start(timer, ONE_SEC_IN_NS, 0)) + scx_bpf_error("failed to re-arm stats timer"); return 0; } @@ -1268,7 +1269,8 @@ struct { static int lowpri_timerfn(void *map, int *key, struct bpf_timer *timer) { scx_bpf_dsq_reenq(LOWPRI_DSQ, 0); - bpf_timer_start(timer, LOWPRI_INTV_NS, 0); + if (bpf_timer_start(timer, LOWPRI_INTV_NS, 0)) + scx_bpf_error("failed to re-arm lowpri timer"); return 0; } @@ -1747,7 +1749,8 @@ static void rr_advance(void) static int round_robin_timerfn(void *map, int *key, struct bpf_timer *timer) { rr_advance(); - bpf_timer_start(timer, round_robin_ns, 0); + if (bpf_timer_start(timer, round_robin_ns, 0)) + scx_bpf_error("failed to re-arm round-robin timer"); return 0; } From 4881a13521886076e8d6d677f274320dcf66fea4 Mon Sep 17 00:00:00 2001 From: Wanwu Li Date: Thu, 27 Aug 2026 17:14:11 +0800 Subject: [PATCH 0268/1198] sched_ext: Fix several comment issues Fix several comment issues found during review: __setschduler_prio() -> __setscheduler_class() scx_iter_scx_dsq_new() -> bpf_iter_scx_dsq_new() scx_next_task_scx() -> set_next_task_scx() Signed-off-by: Wanwu Li Signed-off-by: Tejun Heo --- kernel/sched/ext/ext.c | 10 +++++----- kernel/sched/ext/internal.h | 2 +- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c index c539d15cda63..76a3f4ea237c 100644 --- a/kernel/sched/ext/ext.c +++ b/kernel/sched/ext/ext.c @@ -876,9 +876,9 @@ struct task_struct *scx_task_iter_next_locked(struct scx_task_iter *iter) * unloading. The init_tasks ("swappers") should be excluded * from the iteration because: * - * - It's unsafe to use __setschduler_prio() on an init_task to - * determine the sched_class to use as it won't preserve its - * idle_sched_class. + * - It's unsafe to use __setscheduler_class() on an init_task + * to determine the sched_class to use as it won't preserve + * its idle_sched_class. * * - ops.init/exit_task() can easily be confused if called with * init_tasks as they, e.g., share PID 0. @@ -5514,7 +5514,7 @@ static const struct kset_uevent_ops scx_uevent_ops = { }; /* - * Used by sched_fork() and __setscheduler_prio() to pick the matching + * Used by sched_fork() and __setscheduler_class() to pick the matching * sched_class. dl/rt are already handled. */ bool task_should_scx(int policy) @@ -9771,7 +9771,7 @@ __bpf_kfunc struct task_struct *bpf_iter_scx_dsq_next(struct bpf_iter_scx_dsq *i * bpf_iter_scx_dsq_destroy - Destroy a DSQ iterator * @it: iterator to destroy * - * Undo scx_iter_scx_dsq_new(). + * Undo bpf_iter_scx_dsq_new(). */ __bpf_kfunc void bpf_iter_scx_dsq_destroy(struct bpf_iter_scx_dsq *it) { diff --git a/kernel/sched/ext/internal.h b/kernel/sched/ext/internal.h index 53e136a47924..0967b99a4948 100644 --- a/kernel/sched/ext/internal.h +++ b/kernel/sched/ext/internal.h @@ -442,7 +442,7 @@ struct sched_ext_ops { * * Note that this callback may be called from a CPU other than the * one the task is going to run on. This can happen when a task - * property is changed (i.e., affinity), since scx_next_task_scx(), + * property is changed (i.e., affinity), since set_next_task_scx(), * which triggers this callback, may run on a CPU different from * the task's assigned CPU. * From ea2ee8b222306208d2b094d1a11894da6c106d42 Mon Sep 17 00:00:00 2001 From: Kiran K Date: Tue, 25 Aug 2026 22:53:00 +0530 Subject: [PATCH 0269/1198] Bluetooth: btintel_pcie: Clear automask on spurious interrupts On spurious interrupt where the TX and RX causes are not set, driver was not clearing the auto mask which can block all the interrupts. Driver needs to clear the automask even if no causes are set. Fixes: c2b636b3f788 ("Bluetooth: btintel_pcie: Add support for PCIe transport") Signed-off-by: Kiran K Signed-off-by: Luiz Augusto von Dentz --- drivers/bluetooth/btintel_pcie.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c index 005c77a4f5eb..eec95e5f3dbb 100644 --- a/drivers/bluetooth/btintel_pcie.c +++ b/drivers/bluetooth/btintel_pcie.c @@ -1696,6 +1696,9 @@ static irqreturn_t btintel_pcie_irq_msix_handler(int irq, void *dev_id) if (unlikely(!(intr_fh | intr_hw))) { /* Ignore interrupt, inta == 0 */ + bt_warn_ratelimited("Bluetooth: btintel_pcie: Received spurious interrupt\n"); + btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_MSIX_AUTOMASK_ST, + BIT(entry->entry)); return IRQ_NONE; } From 068e5a0bc57e57d24cbf38def29cc5fb4db9a0df Mon Sep 17 00:00:00 2001 From: Liang Luo Date: Tue, 25 Aug 2026 13:50:53 +0800 Subject: [PATCH 0270/1198] sched_ext: Fix missing @slice and @vtime descriptions in finish_dispatch() kernel-doc Commit 13f1eae3b662 ("sched_ext: Synchronize slice and dsq_vtime writes") added the slice and vtime parameters to finish_dispatch() but did not update its kernel-doc, which produces warnings: Warning: function parameter 'slice' not described in 'finish_dispatch' Warning: function parameter 'vtime' not described in 'finish_dispatch' Describe both parameters using the same wording as dispatch_to_local_dsq(), which receives the same values. Signed-off-by: Liang Luo Signed-off-by: Tejun Heo --- kernel/sched/ext/ext.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c index 76a3f4ea237c..713aa26b2828 100644 --- a/kernel/sched/ext/ext.c +++ b/kernel/sched/ext/ext.c @@ -2806,6 +2806,8 @@ static void dispatch_to_local_dsq(struct scx_sched *sch, struct rq *rq, * @p: task to finish dispatching * @qseq_at_dispatch: qseq when @p started getting dispatched * @dsq_id: destination DSQ ID + * @slice: slice carried by the insert verdict, 0 keeps the current value + * @vtime: vtime carried by the insert verdict, committed on PRIQ inserts * @enq_flags: %SCX_ENQ_* * * Dispatching to local DSQs may need to wait for queueing to complete or From 068c35b5d0546c8625b3d7c61910f73775cf1216 Mon Sep 17 00:00:00 2001 From: Jiacheng Xu Date: Tue, 25 Aug 2026 15:03:15 +0800 Subject: [PATCH 0271/1198] workqueue: reject watchdog thresholds that overflow jiffies The watchdog threshold is supplied in seconds but is multiplied by HZ before being used as a jiffies interval. Reject values that exceed MAX_JIFFY_OFFSET / HZ so the multiplication cannot wrap and the time_after() comparisons remain within their supported range. The check is performed before changing the threshold or watchdog timer. Zero remains the value used to disable the watchdog. Fixes: 82607adcf9cdf ("workqueue: implement lockup detector") Signed-off-by: Jiacheng Xu Signed-off-by: Tejun Heo --- kernel/workqueue.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 0ee73dcd4a14..b8bec1689b7a 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -8035,6 +8035,9 @@ static int wq_watchdog_param_set_thresh(const char *val, if (ret) return ret; + if (thresh > MAX_JIFFY_OFFSET / HZ) + return -ERANGE; + if (system_percpu_wq) wq_watchdog_set_thresh(thresh); else From a086c0892969bf8a0151b0f12bd14a68827c88b2 Mon Sep 17 00:00:00 2001 From: Laxman Acharya Padhya Date: Mon, 31 Aug 2026 15:44:21 +0545 Subject: [PATCH 0272/1198] Bluetooth: btintel: validate version TLV value lengths btintel_parse_version_tlv() verifies that a complete TLV is present in the response, but it does not ensure that the value is long enough for the specific TLV type. A short value can therefore cause an out-of-bounds read through get_unaligned_le16(), get_unaligned_le32(), or memcpy(). Reject values shorter than the minimum required by each known TLV type. Also reject responses that do not contain the Command Complete Status field. Fixes: 57375beef71a ("Bluetooth: btintel: Add infrastructure to read controller information") Reviewed-by: Ali Ahmet Memis Signed-off-by: Laxman Acharya Padhya Tested-by: Kiran K Signed-off-by: Luiz Augusto von Dentz --- drivers/bluetooth/btintel.c | 37 ++++++++++++++++++++++++++++++++++++- 1 file changed, 36 insertions(+), 1 deletion(-) diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index bcb2514b7bc0..352a1c83cd08 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -571,12 +571,44 @@ int btintel_version_info_tlv(struct hci_dev *hdev, } EXPORT_SYMBOL_GPL(btintel_version_info_tlv); +static u8 btintel_version_tlv_min_len(u8 type) +{ + switch (type) { + case INTEL_TLV_CNVI_TOP: + case INTEL_TLV_CNVR_TOP: + case INTEL_TLV_CNVI_BT: + case INTEL_TLV_CNVR_BT: + case INTEL_TLV_BUILD_NUM: + case INTEL_TLV_GIT_SHA1: + return sizeof(u32); + case INTEL_TLV_DEV_REV_ID: + case INTEL_TLV_TIME_STAMP: + return sizeof(u16); + case INTEL_TLV_IMAGE_TYPE: + case INTEL_TLV_BUILD_TYPE: + case INTEL_TLV_SECURE_BOOT: + case INTEL_TLV_OTP_LOCK: + case INTEL_TLV_API_LOCK: + case INTEL_TLV_DEBUG_LOCK: + case INTEL_TLV_LIMITED_CCE: + case INTEL_TLV_SBE_TYPE: + return sizeof(u8); + case INTEL_TLV_MIN_FW: + return 3; + case INTEL_TLV_OTP_BDADDR: + return sizeof(bdaddr_t); + default: + return 0; + } +} + int btintel_parse_version_tlv(struct hci_dev *hdev, struct intel_version_tlv *version, struct sk_buff *skb) { /* Consume Command Complete Status field */ - skb_pull(skb, 1); + if (!skb_pull(skb, 1)) + return -EINVAL; /* Event parameters contain multiple TLVs. Read each of them * and only keep the required data. Also, it use existing legacy @@ -596,6 +628,9 @@ int btintel_parse_version_tlv(struct hci_dev *hdev, if (skb->len < tlv->len + sizeof(*tlv)) return -EINVAL; + if (tlv->len < btintel_version_tlv_min_len(tlv->type)) + return -EINVAL; + switch (tlv->type) { case INTEL_TLV_CNVI_TOP: version->cnvi_top = get_unaligned_le32(tlv->val); From ac8aa9e0ec93a12a60230066f199f49c3b9aac3d Mon Sep 17 00:00:00 2001 From: Laxman Acharya Padhya Date: Mon, 31 Aug 2026 15:44:22 +0545 Subject: [PATCH 0273/1198] Bluetooth: btintel: bound firmware ID by TLV length The firmware ID is treated as a NUL-terminated string even though the TLV length is its only boundary. If the value does not contain a NUL terminator, snprintf() can read beyond the received response. Limit the conversion to the advertised TLV value length. Fixes: 164c62f958f8 ("Bluetooth: btintel: Add firmware ID to firmware name") Reviewed-by: Ali Ahmet Memis Signed-off-by: Laxman Acharya Padhya Tested-by: Kiran K Signed-off-by: Luiz Augusto von Dentz --- drivers/bluetooth/btintel.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index 352a1c83cd08..2f87047168d7 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -702,7 +702,7 @@ int btintel_parse_version_tlv(struct hci_dev *hdev, break; case INTEL_TLV_FW_ID: snprintf(version->fw_id, sizeof(version->fw_id), - "%s", tlv->val); + "%.*s", tlv->len, tlv->val); break; default: /* Ignore rest of information */ From 3a74624b5deae7f5e2b98e638687fbf9594a9781 Mon Sep 17 00:00:00 2001 From: Laxman Acharya Padhya Date: Mon, 31 Aug 2026 15:44:23 +0545 Subject: [PATCH 0274/1198] Bluetooth: btintel: propagate version TLV parsing errors btintel_read_version_tlv() ignores the parser return value, so setup continues with partially initialized version data after a malformed TLV causes parsing to stop. Return the parser error to the caller so an invalid response fails setup instead of being treated as successful. Keep this behavioral change separate from the bounds checks so it can be reverted independently if an existing controller sends malformed data. Signed-off-by: Laxman Acharya Padhya Reviewed-by: Ali Ahmet Memis Tested-by: Kiran K Signed-off-by: Luiz Augusto von Dentz --- drivers/bluetooth/btintel.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index 2f87047168d7..909a265fd906 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -721,6 +721,7 @@ static int btintel_read_version_tlv(struct hci_dev *hdev, { struct sk_buff *skb; const u8 param[1] = { 0xFF }; + int err; if (!version) return -EINVAL; @@ -739,10 +740,10 @@ static int btintel_read_version_tlv(struct hci_dev *hdev, return -EIO; } - btintel_parse_version_tlv(hdev, version, skb); + err = btintel_parse_version_tlv(hdev, version, skb); kfree_skb(skb); - return 0; + return err; } /* ------- REGMAP IBT SUPPORT ------- */ From 57938bbdb9bf7fd41cbd5cd509ec10c4b22bec18 Mon Sep 17 00:00:00 2001 From: Aleksandr Nogikh Date: Fri, 28 Aug 2026 08:55:09 +0000 Subject: [PATCH 0275/1198] Bluetooth: hci_core: Fix race condition during device registration In hci_register_dev(), the power_on work item is queued to hdev->req_workqueue before initializing hdev->adv_monitors_idr and registering the MSFT extension via msft_register(). For devices marked with quirks such as HCI_QUIRK_RAW_DEVICE, the HCI_UNCONFIGURED flag is set on the device. When the power_on work item runs concurrently on another CPU, hci_power_on() detects that the device is unconfigured and immediately invokes hci_dev_do_close(), which calls msft_do_close(). Concurrently, msft_register() allocates the msft structure and exposes it to hdev->msft_data prior to calling mutex_init(&msft->filter_lock). If msft_do_close() executes while hdev->msft_data is already assigned but the mutex has not yet been initialized, mutex_lock(&msft->filter_lock) operates on an uninitialized mutex, triggering a DEBUG_LOCKS warning: DEBUG_LOCKS_WARN_ON(lock->magic != lock) WARNING: kernel/locking/mutex.c:625 at __mutex_lock_common kernel/locking/mutex.c:625 [inline] WARNING: kernel/locking/mutex.c:625 at __mutex_lock+0x12d8/0x1550 kernel/locking/mutex.c:821 ... Call Trace: msft_do_close+0x308/0x7b0 net/bluetooth/msft.c:693 hci_dev_close_sync+0x86b/0x10a0 net/bluetooth/hci_sync.c:5522 hci_dev_do_close net/bluetooth/hci_core.c:499 [inline] hci_power_on+0x32c/0x750 net/bluetooth/hci_core.c:937 process_one_work kernel/workqueue.c:3322 [inline] process_scheduled_works+0xa8e/0x14e0 kernel/workqueue.c:3405 worker_thread+0x92d/0xe10 kernel/workqueue.c:3486 kthread+0x388/0x470 kernel/kthread.c:436 ret_from_fork+0x514/0xb70 arch/x86/kernel/process.c:158 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:245 Fix this by moving the queue_work() call in hci_register_dev() to after idr_init(&hdev->adv_monitors_idr) and msft_register(hdev) so that device structures and extensions are fully initialized before asynchronous tasks can access them. Additionally, assign hdev->msft_data in msft_register() only after mutex_init(&msft->filter_lock) has completed. Fixes: 9e14606d8f38 ("Bluetooth: msft: Extended monitor tracking by address filter") Assisted-by: Gemini:gemini-3.7-flash Gemini:gemini-3.1-pro-preview syzbot Reported-by: syzbot+14ce1b05b7d5a989abbe@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=14ce1b05b7d5a989abbe Link: https://syzkaller.appspot.com/ai_job?id=2bc9e8aa-ca6d-43e2-be2c-fd5d9f649d7e Signed-off-by: Aleksandr Nogikh Signed-off-by: Luiz Augusto von Dentz --- net/bluetooth/hci_core.c | 4 ++-- net/bluetooth/msft.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 35a1be57e386..d7355c73f93e 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2632,11 +2632,11 @@ int hci_register_dev(struct hci_dev *hdev) if (error) BT_WARN("register suspend notifier failed error:%d\n", error); - queue_work(hdev->req_workqueue, &hdev->power_on); - idr_init(&hdev->adv_monitors_idr); msft_register(hdev); + queue_work(hdev->req_workqueue, &hdev->power_on); + return id; err_wqueue: diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c index ded68568e6c9..d9dd722db3eb 100644 --- a/net/bluetooth/msft.c +++ b/net/bluetooth/msft.c @@ -769,8 +769,8 @@ void msft_register(struct hci_dev *hdev) INIT_LIST_HEAD(&msft->handle_map); INIT_LIST_HEAD(&msft->address_filters); - hdev->msft_data = msft; mutex_init(&msft->filter_lock); + hdev->msft_data = msft; } void msft_release(struct hci_dev *hdev) From 4ef05db5b08b176a551b4a6287372045998806b0 Mon Sep 17 00:00:00 2001 From: Pauli Virtanen Date: Sun, 30 Aug 2026 20:11:36 +0300 Subject: [PATCH 0276/1198] Bluetooth: L2CAP: fix chan mode for LE_CONN_REQ + EXT_FLOWCTL pchan l2cap_new_connection() sets default value of channel mode to match the parent channel. l2cap_le_connect_req() left this at the default, and created L2CAP_MODE_EXT_FLOWCTL channels if listening pchan has that mode. This causes FLAG_DEFER_SETUP channels to reply to L2CAP_LE_CONN_REQ with L2CAP_ECRED_CONN_RSP, which is incorrect. It can also result to stack OOB write (of l2cap_alloc_cid determined values) in l2cap_ecred_rsp_defer(), as l2cap_le_connect_req() does not limit maximum number of deferred channels or check for duplicate ident. Fix by setting chan->mode correctly in l2cap_le_connect_req(). Also check channel mode in l2cap_ecred_rsp_defer(), and do WARN_ON_ONCE instead of OOB write to make it less brittle. Fixes: 15f02b910562 ("Bluetooth: L2CAP: Add initial code for Enhanced Credit Based Mode") Signed-off-by: Pauli Virtanen Signed-off-by: Luiz Augusto von Dentz --- net/bluetooth/l2cap_core.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index ee459dd411f5..1c0b7884dc27 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -3894,6 +3894,9 @@ static void l2cap_ecred_rsp_defer(struct l2cap_chan *chan, void *data) struct l2cap_ecred_conn_rsp *rsp_flex = container_of(&rsp->pdu.rsp, struct l2cap_ecred_conn_rsp, hdr); + if (chan->mode != L2CAP_MODE_EXT_FLOWCTL) + return; + /* Check if channel for outgoing connection or if it wasn't deferred * since in those cases it must be skipped. */ @@ -3904,6 +3907,10 @@ static void l2cap_ecred_rsp_defer(struct l2cap_chan *chan, void *data) /* Reset ident so only one response is sent */ chan->ident = 0; + /* Unreachable, check in l2cap_ecred_conn_req. If reached, drop rest */ + if (WARN_ON_ONCE(rsp->count >= ARRAY_SIZE(rsp->pdu.scid))) + rsp->pdu.rsp.result = cpu_to_le16(L2CAP_CR_LE_NO_MEM); + /* Include all channels pending with the same ident */ if (!rsp->pdu.rsp.result) rsp_flex->dcid[rsp->count++] = cpu_to_le16(chan->scid); @@ -5063,6 +5070,7 @@ static int l2cap_le_connect_req(struct l2cap_conn *conn, __set_chan_timer(chan, chan->ops->get_sndtimeo(chan)); chan->ident = cmd->ident; + chan->mode = L2CAP_MODE_LE_FLOWCTL; if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) { l2cap_state_change(chan, BT_CONNECT2); From 56c2b5831d39dc84aad2573dc3e197af1a872a05 Mon Sep 17 00:00:00 2001 From: Pauli Virtanen Date: Sun, 30 Aug 2026 15:04:01 +0300 Subject: [PATCH 0277/1198] Bluetooth: L2CAP: fix out-of-bounds write in l2cap_ecred_connect l2cap_chan_connect() tries to ensure there are no more than L2CAP_ECRED_CONN_SCID_MAX pending ECRED channels, so they fit in the same L2CAP_ECRED_CONN_REQ that l2cap_ecred_connect() constructs. However, the check only counts deferred channels. If 6 L2CAP sockets are connected at the same time in order DDDDND (D=deferred, N=non-deferred), the last can bump the total to max+1. It results to one __le16 written out of bounds of the scid array, and an invalid ECRED_CONN_REQ being sent. Fix by leaving room for the non-deferred pending ECRED channels in the counting in l2cap_chan_connect(), so the limit can't be exceeded. Move counting under same critical section where the channel is added. Although race conditions involving this appear unreachable, it's easier to see. Also add WARN_ON_ONCE check in l2cap_ecred_defer_connect() to make this less brittle. Fixes: da49b602f7f7 ("Bluetooth: L2CAP: Use DEFER_SETUP to group ECRED connections") Signed-off-by: Pauli Virtanen Signed-off-by: Luiz Augusto von Dentz --- net/bluetooth/l2cap_core.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 1c0b7884dc27..60833fa2835b 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1337,7 +1337,7 @@ static void l2cap_le_connect(struct l2cap_chan *chan) struct l2cap_ecred_conn_data { struct { struct l2cap_ecred_conn_req_hdr req; - __le16 scid[5]; + __le16 scid[L2CAP_ECRED_CONN_SCID_MAX]; } __packed pdu; struct l2cap_chan *chan; struct pid *pid; @@ -1365,6 +1365,10 @@ static void l2cap_ecred_defer_connect(struct l2cap_chan *chan, void *data) if (test_and_set_bit(FLAG_ECRED_CONN_REQ_SENT, &chan->flags)) return; + /* Unreachable, checked in l2cap_connect (+timer drops it if reached) */ + if (WARN_ON_ONCE(conn->count >= ARRAY_SIZE(conn->pdu.scid))) + return; + l2cap_ecred_init(chan, 0); /* Set the same ident so we can match on the rsp */ @@ -7377,6 +7381,9 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, goto done; } + mutex_lock(&conn->lock); + l2cap_chan_lock(chan); + if (chan->mode == L2CAP_MODE_EXT_FLOWCTL) { struct l2cap_chan_data data; @@ -7384,19 +7391,20 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, data.pid = chan->ops->get_peer_pid(chan); data.count = 1; - l2cap_chan_list(conn, l2cap_chan_by_pid, &data); + __l2cap_chan_list(conn, l2cap_chan_by_pid, &data); + + /* Leave room for non-deferred channel that ends the group. */ + if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) + data.count += 1; /* Check if there isn't too many channels being connected */ if (data.count > L2CAP_ECRED_CONN_SCID_MAX) { hci_conn_drop(hcon); err = -EPROTO; - goto done; + goto chan_unlock; } } - mutex_lock(&conn->lock); - l2cap_chan_lock(chan); - if (cid && __l2cap_get_chan_by_dcid(conn, cid)) { hci_conn_drop(hcon); err = -EBUSY; From 0d77683237270702fa93489ca759c89b4e970554 Mon Sep 17 00:00:00 2001 From: Pauli Virtanen Date: Sun, 30 Aug 2026 15:04:02 +0300 Subject: [PATCH 0278/1198] Bluetooth: L2CAP: clear FLAG_DEFER_SETUP only for same PID/PSM l2cap_ecred_defer_connect() clears FLAG_DEFER_SETUP also for channels with different PID/PSM, which will not be added to the same ECRED_CONN_REQ in any case. Consequently, only one ECRED connection group can work at a time although it appears intended they would be separate for each PID/PSM combination. Fix by clearing FLAG_DEFER_SETUP only for the connections that could be added in the request. Retain test_bit(FLAG_DEFER_SETUP) before calling get_peer_pid as it may be NULL otherwise. Fixes: da49b602f7f7 ("Bluetooth: L2CAP: Use DEFER_SETUP to group ECRED connections") Signed-off-by: Pauli Virtanen Signed-off-by: Luiz Augusto von Dentz --- net/bluetooth/l2cap_core.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 60833fa2835b..644e31160d55 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1352,7 +1352,7 @@ static void l2cap_ecred_defer_connect(struct l2cap_chan *chan, void *data) if (chan == conn->chan) return; - if (!test_and_clear_bit(FLAG_DEFER_SETUP, &chan->flags)) + if (!test_bit(FLAG_DEFER_SETUP, &chan->flags)) return; pid = chan->ops->get_peer_pid(chan); @@ -1362,6 +1362,9 @@ static void l2cap_ecred_defer_connect(struct l2cap_chan *chan, void *data) chan->mode != L2CAP_MODE_EXT_FLOWCTL || chan->state != BT_CONNECT) return; + if (!test_and_clear_bit(FLAG_DEFER_SETUP, &chan->flags)) + return; + if (test_and_set_bit(FLAG_ECRED_CONN_REQ_SENT, &chan->flags)) return; From 2deb76c21b81e42b3282224f7dd2046fe73fd1e0 Mon Sep 17 00:00:00 2001 From: Gongwei Li Date: Tue, 25 Aug 2026 10:01:45 +0800 Subject: [PATCH 0279/1198] Bluetooth: hci_mrvl: Fix wrong return value check of wait_on_bit_timeout() wait_on_bit_timeout() returns 0 if the bit was cleared, -EINTR if the process received a signal and the mode permitted wake up on that signal, or -EAGAIN if the timeout elapsed. It never returns 1. Hence the check "err == 1" in mrvl_load_firmware() is dead code: when the waiting task is interrupted by a signal (-EINTR), the code falls into the "else if (err)" branch and misreports it as "Firmware request timeout" with -ETIMEDOUT instead of propagating -EINTR. Fix this by testing for -EINTR so that an interrupted firmware load is properly detected and reported. Fixes: 162f812f23ba ("Bluetooth: hci_uart: Add Marvell support") Signed-off-by: Gongwei Li Signed-off-by: Luiz Augusto von Dentz --- drivers/bluetooth/hci_mrvl.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/bluetooth/hci_mrvl.c b/drivers/bluetooth/hci_mrvl.c index 516b8f74c434..5798a8db016e 100644 --- a/drivers/bluetooth/hci_mrvl.c +++ b/drivers/bluetooth/hci_mrvl.c @@ -307,9 +307,8 @@ static int mrvl_load_firmware(struct hci_dev *hdev, const char *name) err = wait_on_bit_timeout(&mrvl->flags, STATE_FW_REQ_PENDING, TASK_INTERRUPTIBLE, msecs_to_jiffies(2000)); - if (err == 1) { + if (err == -EINTR) { bt_dev_err(hdev, "Firmware load interrupted"); - err = -EINTR; break; } else if (err) { bt_dev_err(hdev, "Firmware request timeout"); From 77d499e61d36e883a6ad1f10afe05f556aa7e0cc Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Fri, 14 Aug 2026 16:35:18 -0400 Subject: [PATCH 0280/1198] selinux: fix BPF token permission checks Avoid multiple lookups of the bpffs creator SID using the token's file descriptor when the same information can be found via the resolved path/dentry (in selinux_bpf_token_create()) or the token itself (in selinux_bpf_map_create() and selinux_bpf_prog_load()). Not only does this simplify the code, it avoids potential TOCTOU issues if the user changes the token file descriptor passed into the kernel. Cc: stable@vger.kernel.org Fixes: 5473a722f782 ("selinux: add support for BPF token access control") Reviewed-by: Stephen Smalley Tested-by: Stephen Smalley Signed-off-by: Paul Moore --- security/selinux/hooks.c | 36 ++++++++++-------------------------- 1 file changed, 10 insertions(+), 26 deletions(-) diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 035aaf113d1d..e5e17f100aae 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -7267,24 +7267,6 @@ static int selinux_bpf_prog(struct bpf_prog *prog) BPF__PROG_RUN, NULL); } -static u32 selinux_bpffs_creator_sid(u32 fd) -{ - struct path path; - struct super_block *sb; - struct superblock_security_struct *sbsec; - - CLASS(fd, f)(fd); - - if (fd_empty(f)) - return SECSID_NULL; - - path = fd_file(f)->f_path; - sb = path.dentry->d_sb; - sbsec = selinux_superblock(sb); - - return sbsec->creator_sid; -} - static int selinux_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, struct bpf_token *token, bool kernel) { @@ -7297,7 +7279,7 @@ static int selinux_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, if (!token) ssid = bpfsec->sid; else - ssid = selinux_bpffs_creator_sid(attr->map_token_fd); + ssid = selinux_bpf_token_security(token)->grantor_sid; return avc_has_perm(ssid, bpfsec->sid, SECCLASS_BPF, BPF__MAP_CREATE, NULL); @@ -7315,7 +7297,7 @@ static int selinux_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, if (!token) ssid = bpfsec->sid; else - ssid = selinux_bpffs_creator_sid(attr->prog_token_fd); + ssid = selinux_bpf_token_security(token)->grantor_sid; return avc_has_perm(ssid, bpfsec->sid, SECCLASS_BPF, BPF__PROG_LOAD, NULL); @@ -7329,12 +7311,14 @@ static int selinux_bpf_token_create(struct bpf_token *token, const struct path *path) { struct bpf_security_struct *bpfsec; - u32 sid = selinux_bpffs_creator_sid(attr->token_create.bpffs_fd); + struct superblock_security_struct *sbsec; int err; + sbsec = selinux_superblock(path->dentry->d_sb); + bpfsec = selinux_bpf_token_security(token); bpfsec->sid = current_sid(); - bpfsec->grantor_sid = sid; + bpfsec->grantor_sid = sbsec->creator_sid; bpfsec->perms = 0; /** @@ -7343,15 +7327,15 @@ static int selinux_bpf_token_create(struct bpf_token *token, * in the allowed_cmds bitmap. */ if (bpf_token_cmd(token, BPF_MAP_CREATE)) { - err = avc_has_perm(bpfsec->sid, sid, SECCLASS_BPF, - BPF__MAP_CREATE_AS, NULL); + err = avc_has_perm(bpfsec->sid, bpfsec->grantor_sid, + SECCLASS_BPF, BPF__MAP_CREATE_AS, NULL); if (err) return err; bpfsec->perms |= BPF__MAP_CREATE; } if (bpf_token_cmd(token, BPF_PROG_LOAD)) { - err = avc_has_perm(bpfsec->sid, sid, SECCLASS_BPF, - BPF__PROG_LOAD_AS, NULL); + err = avc_has_perm(bpfsec->sid, bpfsec->grantor_sid, + SECCLASS_BPF, BPF__PROG_LOAD_AS, NULL); if (err) return err; bpfsec->perms |= BPF__PROG_LOAD; From ee02ed6308fbbd851c4e5c1f642d029617049a12 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Arda=20Do=C4=9Fu=20Ari?= Date: Fri, 28 Aug 2026 02:51:39 +0300 Subject: [PATCH 0281/1198] platform/x86: hp-wmi: Fix board_params typo for 8DD6 board MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When adding support for board 8DD6, &omen_v1_no_ec_thermal_params was passed as driver_data instead of &omen_v1_no_ec_board_params. Because active_board_params expects a pointer to struct hp_wmi_board_params, dereferencing active_board_params->thermal_profile results in a type confusion bug and invalid memory access. Update the entry to point to omen_v1_no_ec_board_params. Fixes: a7320d6eb9c42 ("platform/x86: hp-wmi: Add support for OMEN MAX 16-ak0xxx (8DD6)") Cc: stable@vger.kernel.org Signed-off-by: Arda Doğu Ari Reviewed-by: Krishna Chomal Link: https://patch.msgid.link/20260827235139.154462-1-arfeliousheres@gmail.com Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen --- drivers/platform/x86/hp/hp-wmi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c index b2773fc1aca4..615b4cf6fc45 100644 --- a/drivers/platform/x86/hp/hp-wmi.c +++ b/drivers/platform/x86/hp/hp-wmi.c @@ -337,7 +337,7 @@ static const struct dmi_system_id hp_wmi_feature_boards[] __initconst = { }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8DD6") }, - .driver_data = (void *)&omen_v1_no_ec_thermal_params, + .driver_data = (void *)&omen_v1_no_ec_board_params, }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8E35") }, From 6bb4fb72c00dc2a9cb663e2d16adce15e4170cdf Mon Sep 17 00:00:00 2001 From: Armin Wolf Date: Mon, 31 Aug 2026 01:50:58 +0200 Subject: [PATCH 0282/1198] platform/x86: asus-laptop: Fix ACPI event handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The event codes inside asus_keymap[] span a wide range from 0x02 till 0xC5, but using ACPI_DEVICE_NOTIFY prevents us from receiving event codes below 0x80. Fix this by using ACPI_ALL_NOTIFY instead. Fixes: 378500dc1313 ("platform/x86: asus-laptop: Register ACPI notify handler directly") Reported-by: Mo Jun Closes: https://bugs.debian.org/1146124 Tested-by: Mo Jun Signed-off-by: Armin Wolf Reviewed-by: Rafael J. Wysocki Link: https://patch.msgid.link/20260830235058.324140-1-W_Armin@gmx.de Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen --- drivers/platform/x86/asus-laptop.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/platform/x86/asus-laptop.c b/drivers/platform/x86/asus-laptop.c index 449addd1ac7a..79a575d0f5b4 100644 --- a/drivers/platform/x86/asus-laptop.c +++ b/drivers/platform/x86/asus-laptop.c @@ -1882,7 +1882,7 @@ static int asus_acpi_probe(struct platform_device *pdev) if (result && result != -ENODEV) goto fail_pega_rfkill; - result = acpi_dev_install_notify_handler(device, ACPI_DEVICE_NOTIFY, + result = acpi_dev_install_notify_handler(device, ACPI_ALL_NOTIFY, asus_acpi_notify, asus); if (result) goto fail_pega_rfkill; @@ -1912,7 +1912,7 @@ static void asus_acpi_remove(struct platform_device *pdev) { struct asus_laptop *asus = platform_get_drvdata(pdev); - acpi_dev_remove_notify_handler(asus->device, ACPI_DEVICE_NOTIFY, + acpi_dev_remove_notify_handler(asus->device, ACPI_ALL_NOTIFY, asus_acpi_notify); asus_backlight_exit(asus); asus_rfkill_exit(asus); From 9ffed84a24d60ec506d8961fe138f0baa92fdbd0 Mon Sep 17 00:00:00 2001 From: Pedro Falcato Date: Mon, 31 Aug 2026 12:43:46 +0100 Subject: [PATCH 0283/1198] platform/x86/amd/pmf: fix build on !CONFIG_AMD_PMF_DEBUG MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit amd_pmf_get_ta_custom_bios_inputs() is used by non-debug features. Fix the build on !CONFIG_AMD_PMF_DEBUG by moving amd_pmf_get_ta_custom_bios_inputs() outside the ifdef CONFIG_AMD_PMF_DEBUG. Fixes: 5bda82c797c9 ("platform/x86/amd/pmf: Implement util layer ioctl handler") Reported-by: Oleksandr Natalenko Link: https://lore.kernel.org/all/fS7s9V_xTaedaqEAaxwKnQ@natalenko.name/ Signed-off-by: Pedro Falcato Reviewed-by: Mario Limonciello (AMD) > --- Tested-by: Oleksandr Natalenko Link: https://patch.msgid.link/20260831114346.2041361-1-pfalcato@suse.de Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen --- drivers/platform/x86/amd/pmf/spc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/platform/x86/amd/pmf/spc.c b/drivers/platform/x86/amd/pmf/spc.c index 94355b435a66..592ba4de4c7f 100644 --- a/drivers/platform/x86/amd/pmf/spc.c +++ b/drivers/platform/x86/amd/pmf/spc.c @@ -17,7 +17,6 @@ #include #include "pmf.h" -#ifdef CONFIG_AMD_PMF_DEBUG u32 amd_pmf_get_ta_custom_bios_inputs(struct ta_pmf_enact_table *in, int index) { switch (index) { @@ -31,6 +30,7 @@ u32 amd_pmf_get_ta_custom_bios_inputs(struct ta_pmf_enact_table *in, int index) } EXPORT_SYMBOL(amd_pmf_get_ta_custom_bios_inputs); +#ifdef CONFIG_AMD_PMF_DEBUG void amd_pmf_dump_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in) { int i; From d83b7502bb087fa54daf0fdd419d2910c34bc97d Mon Sep 17 00:00:00 2001 From: Antonio Borneo Date: Mon, 31 Aug 2026 17:36:46 +0200 Subject: [PATCH 0284/1198] MAINTAINERS: Update URI for watchdog tree The old git repository git://www.linux-watchdog.org/linux-watchdog.git is not accessible anymore, while the development of the watchdog framework is currently handled in git.kernel.org by Guenter's linux-staging repository. Update the URI. Signed-off-by: Antonio Borneo Link: https://patch.msgid.link/20260831153646.396038-1-antonio.borneo@foss.st.com Signed-off-by: Guenter Roeck --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 3a19da74d00c..5e0468e53257 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -29357,7 +29357,7 @@ M: Guenter Roeck L: linux-watchdog@vger.kernel.org S: Maintained W: http://www.linux-watchdog.org/ -T: git git://www.linux-watchdog.org/linux-watchdog.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging.git F: Documentation/devicetree/bindings/watchdog/ F: Documentation/watchdog/ F: drivers/watchdog/ From 93e257938aa67a6c957217db94091d9d9e5d403f Mon Sep 17 00:00:00 2001 From: Aaron Tomlin Date: Mon, 31 Aug 2026 14:15:53 -0400 Subject: [PATCH 0285/1198] tools/workqueue/wq_dump.py: Support backward compatibility for wq->attrs rename Commit 464e454e1cb4 ("workqueue: rename wq->unbound_attrs to wq->attrs") renamed wq->unbound_attrs to wq->attrs. When running wq_dump.py against older running kernels or vmcores where struct workqueue_struct still contains unbound_attrs, drgn raises an AttributeError. Add a wq_attrs() helper to allow wq_dump.py to inspect both older and newer kernel versions seamlessly. Fixes: 464e454e1cb4 ("workqueue: rename wq->unbound_attrs to wq->attrs") Signed-off-by: Aaron Tomlin Signed-off-by: Tejun Heo --- tools/workqueue/wq_dump.py | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/tools/workqueue/wq_dump.py b/tools/workqueue/wq_dump.py index 31afc24ef17b..9313ebe0c525 100644 --- a/tools/workqueue/wq_dump.py +++ b/tools/workqueue/wq_dump.py @@ -78,6 +78,12 @@ def cpumask_str(cpumask): wq_type_len = 9 +def wq_attrs(wq): + try: + return wq.attrs + except AttributeError: + return wq.unbound_attrs + def wq_type_str(wq): if wq.flags & WQ_BH: return f'{"bh":{wq_type_len}}' @@ -85,7 +91,7 @@ def wq_type_str(wq): if wq.flags & WQ_ORDERED: return f'{"ordered":{wq_type_len}}' else: - if wq.attrs.affn_strict: + if wq_attrs(wq).affn_strict: return f'{"unbound,S":{wq_type_len}}' else: return f'{"unbound":{wq_type_len}}' @@ -206,7 +212,7 @@ for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_( print(f'{wq.name.string_().decode():{WQ_NAME_LEN}}', end='') if wq.flags & WQ_UNBOUND: - print(f' {cpumask_str(wq.attrs.cpumask):{ucpus_len}}', end='') + print(f' {cpumask_str(wq_attrs(wq).cpumask):{ucpus_len}}', end='') else: print(f' {"":{ucpus_len}}', end='') From c4126f1db36e6b2e1c79b0e30a8a2de91c568f4c Mon Sep 17 00:00:00 2001 From: Arvind Yadav Date: Mon, 10 Aug 2026 14:58:45 +0530 Subject: [PATCH 0286/1198] drm/pagemap: Prevent double migration of device pages MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A device-private folio migrated to system memory by a CPU fault can remain reachable through the raw-PFN eviction path until migration finalization drops the source reference. If eviction selects the same device-private folio during this window, it can attempt to migrate the folio again. The second migration can leave an uncharged folio on an LRU list, causing folio_lruvec_lock_irqsave() to retry indefinitely and resulting in a soft lockup and RCU stall. Mark successfully migrated device-private folios using a low bit of their zone_device_data before migration finalization. Make both CPU-fault and raw-PFN migration paths skip device-private folios carrying this flag. Mask the flag when retrieving the drm_pagemap_zdd pointer and preserve it when a device-private folio is split. Keeping the state on the physical folio also avoids depending on a virtual address that may change before a fault occurs. v2: - Replace the retired-PFN XArray with an embedded bitmap. (Matthew Brost) - Mark every base page covered by a migrated folio so retirement remains valid if the folio is later split. v3: - Store the migrated state in a low bit of zone_device_data instead of adding virtual-range and bitmap tracking to the ZDD. (Matthew Brost) - Mask the flag when retrieving the ZDD and preserve it when splitting a folio. - Drop the pre-existing fixes already covered by Matthew Brost's series: https://patchwork.freedesktop.org/series/171651/ v4: - Advance by the folio size only for migration entries marked with MIGRATE_PFN_COMPOUND. (Sashiko) v5: - Simplify ZDD flag updates and folio iteration. (Matthew Brost) - Skip retired device-private folios in the CPU-fault path. (Matthew Brost) - Preserve flag bits while taking a new ZDD reference for split folios. v6: - Restore MIGRATE_PFN_COMPOUND-aware stepping so non-compound migration entries are processed one at a time. (Sashiko) - Drop the pre-existing fixes already covered by Matthew Brost's series: https://patchwork.freedesktop.org/series/171651/ The lockup was observed as: [10109.860465] watchdog: BUG: soft lockup - CPU#9 stuck for 26s! [kworker/u65:5:6557] [10109.860524] Tainted: [S]=CPU_OUT_OF_SPEC, [O]=OOT_MODULE [10109.860524] Hardware name: ASUS System Product Name/PRIME Z790-P WIFI, BIOS 0812 02/24/2023 [10109.860525] Workqueue: xe_page_fault_work_queue xe_pagefault_queue_work [xe] [10109.860644] RIP: 0010:_raw_spin_unlock_irqrestore+0x57/0x80 [10109.860655] Call Trace: [10109.860655] [10109.860657] folio_lruvec_lock_irqsave+0x216/0x220 [10109.860661] ? __pfx_lru_add+0x10/0x10 [10109.860665] folio_batch_move_lru+0xc8/0x450 [10109.860670] ? lock_acquire+0xc4/0x2d0 [10109.860674] ? __folio_batch_add_and_move+0x60/0x2e0 [10109.860677] ? folio_migrate_mapping+0xa6/0x110 [10109.860679] ? folio_migrate_flags+0x13b/0x1b0 [10109.860681] ? __pfx_lru_add+0x10/0x10 [10109.860683] __folio_batch_add_and_move+0xe7/0x2e0 [10109.860685] ? dma_iova_try_alloc+0xb0/0x140 [10109.860689] folio_add_lru+0x64/0x80 [10109.860691] __migrate_device_finalize+0x12c/0x270 [10109.860695] migrate_device_finalize+0x10/0x20 [10109.860698] drm_pagemap_evict_to_ram+0x185/0x370 [drm_gpusvm_helper] [10109.860704] ? drm_pagemap_evict_to_ram+0x96/0x370 [drm_gpusvm_helper] [10109.860709] xe_svm_bo_evict+0x15/0x20 [xe] [10109.860819] ? xe_svm_bo_evict+0x15/0x20 [xe] [10109.860921] xe_bo_move+0x107e/0x1570 [xe] [10109.860992] ? xe_ttm_tt_create+0x168/0x340 [xe] [10109.861059] ? __up_read+0x98/0x2b0 [10109.861061] ? lock_is_held_type+0xa3/0x130 [10109.861067] ttm_bo_handle_move_mem+0xe8/0x1e0 [ttm] [10109.861075] ttm_bo_evict+0x141/0x1c0 [ttm] [10109.861081] ttm_bo_evict_cb+0x9f/0x100 [ttm] [10109.861086] ttm_lru_walk_for_evict+0x84/0x190 [ttm] [10109.861091] ? xe_ttm_vram_mgr_new+0x258/0x3a0 [xe] [10109.861198] ttm_bo_alloc_resource+0x219/0x750 [ttm] [10109.861203] ? ttm_bo_alloc_resource+0xa9/0x750 [ttm] [10109.861208] ? lock_acquire+0xc4/0x2d0 [10109.861214] ttm_bo_validate+0x94/0x1c0 [ttm] [10109.861218] ? ww_mutex_trylock+0x19d/0x3d0 [10109.861219] ? _raw_write_unlock+0x22/0x50 [10109.861223] ttm_bo_init_reserved+0x17d/0x1f0 [ttm] [10109.861228] xe_bo_init_locked+0x20a/0x620 [xe] [10109.861294] ? __pfx_xe_ttm_bo_destroy+0x10/0x10 [xe] [10109.861359] ? mark_held_locks+0x46/0x90 [10109.861361] ? __create_object+0x68/0xc0 [10109.861366] __xe_bo_create_locked+0x384/0xa20 [xe] [10109.861432] ? lock_acquire+0xc4/0x2d0 [10109.861434] ? xe_drm_pagemap_populate_mm+0xd3/0x340 [xe] [10109.861542] xe_bo_create_locked+0x23/0x40 [xe] [10109.861609] xe_drm_pagemap_populate_mm+0x12e/0x340 [xe] [10109.861707] ? __lock_acquire+0x43e/0x2930 [10109.861716] drm_pagemap_populate_mm+0x74/0xe0 [drm_gpusvm_helper] [10109.861720] xe_svm_alloc_vram+0xb5/0x2c0 [xe] [10109.861817] ? seqcount_lockdep_reader_access.constprop.0+0x9f/0xc0 [10109.861819] ? ktime_get+0x23/0x130 [10109.861821] ? trace_hardirqs_on+0x22/0xe0 [10109.861823] ? seqcount_lockdep_reader_access.constprop.0+0x9f/0xc0 [10109.861826] __xe_svm_handle_pagefault+0x77d/0xbf0 [xe] [10109.861924] ? rwsem_down_write_slowpath+0x43a/0x9a0 [10109.861926] ? _raw_spin_unlock_irq+0x27/0x70 [10109.861928] ? rwsem_down_write_slowpath+0x43a/0x9a0 [10109.861929] ? trace_hardirqs_on+0x22/0xe0 [10109.861931] ? _raw_spin_unlock_irq+0x27/0x70 [10109.861933] ? rwsem_down_write_slowpath+0x459/0x9a0 [10109.861937] xe_svm_handle_pagefault+0x3d/0xb0 [xe] [10109.862030] xe_pagefault_queue_work+0x1a9/0x520 [xe] [10109.862122] process_one_work+0x239/0x730 [10109.862127] worker_thread+0x200/0x3f0 [10109.862130] ? __pfx_worker_thread+0x10/0x10 [10109.862132] kthread+0x10d/0x150 [10109.862133] ? __pfx_kthread+0x10/0x10 [10109.862135] ret_from_fork+0x3bd/0x470 [10109.862138] ? __pfx_kthread+0x10/0x10 [10109.862140] ret_from_fork_asm+0x1a/0x30 [10109.862146] Fixes: 99624bdff867 ("drm/gpusvm: Add support for GPU Shared Virtual Memory") Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: Matthew Brost Cc: Thomas Zimmermann Cc: David Airlie Cc: Simona Vetter Cc: Thomas Hellström Cc: Himal Prasad Ghimiray Assisted-by: Claude:claude-opus-4-8 Suggested-by: Matthew Brost Signed-off-by: Arvind Yadav Reviewed-by: Matthew Brost Signed-off-by: Matthew Brost Link: https://patch.msgid.link/20260810092845.2776097-1-arvind.yadav@intel.com --- drivers/gpu/drm/drm_pagemap.c | 127 ++++++++++++++++++++++++++++++++-- include/drm/drm_pagemap.h | 8 ++- 2 files changed, 129 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/drm_pagemap.c b/drivers/gpu/drm/drm_pagemap.c index 892b325fa99b..c5906f153ada 100644 --- a/drivers/gpu/drm/drm_pagemap.c +++ b/drivers/gpu/drm/drm_pagemap.c @@ -1102,12 +1102,117 @@ void drm_pagemap_put(struct drm_pagemap *dpagemap) } EXPORT_SYMBOL(drm_pagemap_put); +/** + * drm_pagemap_page_get_flags() - Read flags from a device-private folio + * @page: Pointer to a page of the device-private folio + * + * Return: The DRM_PAGEMAP_ZDD_FLAG_* bits encoded in zone_device_data. + */ +static unsigned long drm_pagemap_page_get_flags(struct page *page) +{ + struct folio *folio = page_folio(page); + + return (unsigned long)folio_zone_device_data(folio) & + DRM_PAGEMAP_ZDD_FLAG_MASK; +} + +/** + * drm_pagemap_page_set_flags() - Set flags on a device-private folio + * @page: Pointer to a page of the device-private folio + * @flags: DRM_PAGEMAP_ZDD_FLAG_* bits to set + * + * Preserve any flags already encoded alongside the ZDD pointer. + */ +static void drm_pagemap_page_set_flags(struct page *page, + unsigned long flags) +{ + struct folio *folio = page_folio(page); + unsigned long old; + + if (WARN_ON_ONCE(flags & ~DRM_PAGEMAP_ZDD_FLAG_MASK)) + return; + + old = (unsigned long)folio_zone_device_data(folio); + folio_set_zone_device_data(folio, (void *)(old | flags)); +} + +/** + * drm_pagemap_retire_migrated_pages() - Record migrated device-private folios + * @src_pfns: source array after migrate_vma_pages() or migrate_device_pages() + * @npages: number of entries in @src_pfns + * + * Flag device-private folios successfully migrated to RAM before finalize + * unlocks the sources. The migrated state is stored in the physical folio, so + * it survives later folio splits and subsequent migrations can skip it. + */ +static void drm_pagemap_retire_migrated_pages(unsigned long *src_pfns, + unsigned long npages) +{ + unsigned long i = 0; + + while (i < npages) { + struct page *page = migrate_pfn_to_page(src_pfns[i]); + unsigned long nr = 1; + + if (!page) { + i++; + continue; + } + + if (src_pfns[i] & MIGRATE_PFN_COMPOUND) + nr = folio_nr_pages(page_folio(page)); + + if ((src_pfns[i] & MIGRATE_PFN_MIGRATE) && + is_device_private_page(page)) + drm_pagemap_page_set_flags(page, + DRM_PAGEMAP_ZDD_FLAG_MIGRATED); + + i += nr; + } +} + +/** + * drm_pagemap_skip_retired_pages() - Skip retired device-private folios + * @src_pfns: MIGRATE_PFN-encoded source array + * @npages: number of entries in @src_pfns + * + * Skip source folios already migrated to RAM, identified by the migrated flag + * stored in the physical folio's zone_device_data. + */ +static void drm_pagemap_skip_retired_pages(unsigned long *src_pfns, + unsigned long npages) +{ + unsigned long i = 0; + + while (i < npages) { + struct page *page = migrate_pfn_to_page(src_pfns[i]); + unsigned long nr = 1; + + if (!page) { + i++; + continue; + } + + if (src_pfns[i] & MIGRATE_PFN_COMPOUND) + nr = folio_nr_pages(page_folio(page)); + + if ((src_pfns[i] & MIGRATE_PFN_MIGRATE) && + is_device_private_page(page) && + (drm_pagemap_page_get_flags(page) & + DRM_PAGEMAP_ZDD_FLAG_MIGRATED)) + src_pfns[i] &= ~MIGRATE_PFN_MIGRATE; + + i += nr; + } +} + /** * drm_pagemap_evict_to_ram() - Evict GPU SVM range to RAM * @devmem_allocation: Pointer to the device memory allocation * - * Similar to __drm_pagemap_migrate_to_ram but does not require mmap lock and - * migration done via migrate_device_* functions. + * Similar to __drm_pagemap_migrate_to_ram(), but uses the + * migrate_device_* helpers and does not require the mmap lock. + * Device-private PFNs already migrated to RAM by either path are skipped. * * Return: 0 on success, negative error code on failure. */ @@ -1148,6 +1253,8 @@ int drm_pagemap_evict_to_ram(struct drm_pagemap_devmem *devmem_allocation) if (err) goto err_free; + drm_pagemap_skip_retired_pages(src, npages); + err = drm_pagemap_migrate_populate_ram_pfn(NULL, NULL, npages, &mpages, src, dst, 0); if (err || !mpages) @@ -1178,6 +1285,7 @@ int drm_pagemap_evict_to_ram(struct drm_pagemap_devmem *devmem_allocation) if (err) drm_pagemap_migration_unlock_put_pages(npages, dst); migrate_device_pages(src, dst, npages); + drm_pagemap_retire_migrated_pages(src, npages); migrate_device_finalize(src, dst, npages); drm_pagemap_migrate_unmap_pages(devmem_allocation->dev, pagemap_addr, dst, npages, DMA_FROM_DEVICE, &state); @@ -1275,13 +1383,15 @@ static int __drm_pagemap_migrate_to_ram(struct vm_area_struct *vas, if (!migrate.cpages) goto err_free; + drm_pagemap_skip_retired_pages(migrate.src, npages); + ops = zdd->devmem_allocation->ops; dev = zdd->devmem_allocation->dev; err = drm_pagemap_migrate_populate_ram_pfn(vas, page, npages, &mpages, migrate.src, migrate.dst, start); - if (err) + if (err || !mpages) goto err_finalize; err = drm_pagemap_migrate_map_system_pages(dev, pagemap_addr, @@ -1308,6 +1418,7 @@ static int __drm_pagemap_migrate_to_ram(struct vm_area_struct *vas, if (err) drm_pagemap_migration_unlock_put_pages(npages, migrate.dst); migrate_vma_pages(&migrate); + drm_pagemap_retire_migrated_pages(migrate.src, npages); migrate_vma_finalize(&migrate); if (dev) drm_pagemap_migrate_unmap_pages(dev, pagemap_addr, migrate.dst, @@ -1360,13 +1471,19 @@ static vm_fault_t drm_pagemap_migrate_to_ram(struct vm_fault *vmf) static void drm_pagemap_folio_split(struct folio *orig_folio, struct folio *new_folio) { struct drm_pagemap_zdd *zdd; + unsigned long orig_data, new_data; if (!new_folio) return; new_folio->pgmap = orig_folio->pgmap; - zdd = folio_zone_device_data(orig_folio); - folio_set_zone_device_data(new_folio, drm_pagemap_zdd_get(zdd)); + + orig_data = (unsigned long)folio_zone_device_data(orig_folio); + zdd = (struct drm_pagemap_zdd *)(orig_data & ~DRM_PAGEMAP_ZDD_FLAG_MASK); + + new_data = (unsigned long)drm_pagemap_zdd_get(zdd); + new_data |= orig_data & DRM_PAGEMAP_ZDD_FLAG_MASK; + folio_set_zone_device_data(new_folio, (void *)new_data); } static const struct dev_pagemap_ops drm_pagemap_pagemap_ops = { diff --git a/include/drm/drm_pagemap.h b/include/drm/drm_pagemap.h index 95eb4b66b057..ebbd3b0ddf36 100644 --- a/include/drm/drm_pagemap.h +++ b/include/drm/drm_pagemap.h @@ -2,6 +2,7 @@ #ifndef _DRM_PAGEMAP_H_ #define _DRM_PAGEMAP_H_ +#include #include #include #include @@ -339,6 +340,9 @@ struct drm_pagemap_migrate_details { #if IS_ENABLED(CONFIG_ZONE_DEVICE) +#define DRM_PAGEMAP_ZDD_FLAG_MIGRATED BIT(0) +#define DRM_PAGEMAP_ZDD_FLAG_MASK DRM_PAGEMAP_ZDD_FLAG_MIGRATED + int drm_pagemap_migrate_to_devmem(struct drm_pagemap_devmem *devmem_allocation, struct mm_struct *mm, unsigned long start, unsigned long end, @@ -373,7 +377,9 @@ static inline struct drm_pagemap_zdd *drm_pagemap_page_zone_device_data(struct p { struct folio *folio = page_folio(page); - return folio_zone_device_data(folio); + return (struct drm_pagemap_zdd *) + ((unsigned long)folio_zone_device_data(folio) & + ~DRM_PAGEMAP_ZDD_FLAG_MASK); } #else From 8eae39cd0adf28ba81a46090b10484cf402c0ac8 Mon Sep 17 00:00:00 2001 From: Arvind Yadav Date: Tue, 28 Jul 2026 14:33:04 +0530 Subject: [PATCH 0287/1198] drm/pagemap: Reset migration page count on eviction retry MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit drm_pagemap_evict_to_ram() may retry eviction, but mpages retains the count from the previous attempt. A retry can therefore continue to the copy path even when no RAM pages were populated. Reset mpages at the retry label so it reflects only the current attempt. Fixes: 99624bdff867 ("drm/gpusvm: Add support for GPU Shared Virtual Memory") Cc: Matthew Brost Cc: Thomas Hellström Cc: Himal Prasad Ghimiray Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: Thomas Zimmermann Cc: David Airlie Cc: Simona Vetter Signed-off-by: Arvind Yadav Reviewed-by: Matthew Brost Signed-off-by: Matthew Brost Link: https://patch.msgid.link/20260728090304.1264759-1-arvind.yadav@intel.com --- drivers/gpu/drm/drm_pagemap.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_pagemap.c b/drivers/gpu/drm/drm_pagemap.c index c5906f153ada..097a900cf55d 100644 --- a/drivers/gpu/drm/drm_pagemap.c +++ b/drivers/gpu/drm/drm_pagemap.c @@ -1220,7 +1220,7 @@ int drm_pagemap_evict_to_ram(struct drm_pagemap_devmem *devmem_allocation) { const struct drm_pagemap_devmem_ops *ops = devmem_allocation->ops; struct drm_pagemap_iova_state state = {}; - unsigned long npages, mpages = 0; + unsigned long npages, mpages; struct page **pages; unsigned long *src, *dst; struct drm_pagemap_addr *pagemap_addr; @@ -1231,6 +1231,7 @@ int drm_pagemap_evict_to_ram(struct drm_pagemap_devmem *devmem_allocation) npages = devmem_allocation->size >> PAGE_SHIFT; retry: + mpages = 0; if (!mmget_not_zero(devmem_allocation->mm)) return -EFAULT; From ca12149896ed040dafef92eacd2af3f903afb177 Mon Sep 17 00:00:00 2001 From: Rudi Heitbaum Date: Mon, 24 Aug 2026 02:27:29 +0000 Subject: [PATCH 0288/1198] regulator: dt-bindings: fan53555: add tcs,tcs4526 The driver has accepted tcs,tcs4526 since commit 5eee5eced95f ("regulator: fan53555: add tcs4526"), which added the compatible to both the of_device_id and i2c_device_id tables for the TCS4526, a chip that reports id 0 rather than the TCS4525's id 12. The binding was converted to DT schema afterwards, in commit 6cea468b680e ("regulator: dt-bindings: Convert Fairchild FAN53555 to DT schema"), and only picked up tcs,tcs4525. No in-tree DTS used the 4526 string at the time, so nothing flagged the omission. RK3399Pro boards use the TCS4526 for vdd_gpu and vdd_cpu_b, so a DTS describing them fails dtbs_check today even though the driver binds correctly. Add the missing compatible. Signed-off-by: Rudi Heitbaum Acked-by: Conor Dooley Link: https://patch.msgid.link/aousEdwMni9ScZBn@0d3a7a881997 Signed-off-by: Mark Brown --- Documentation/devicetree/bindings/regulator/fcs,fan53555.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/regulator/fcs,fan53555.yaml b/Documentation/devicetree/bindings/regulator/fcs,fan53555.yaml index 9a18891f721e..b35b8f365b0f 100644 --- a/Documentation/devicetree/bindings/regulator/fcs,fan53555.yaml +++ b/Documentation/devicetree/bindings/regulator/fcs,fan53555.yaml @@ -23,6 +23,7 @@ properties: - silergy,syr827 - silergy,syr828 - tcs,tcs4525 + - tcs,tcs4526 - items: - const: rockchip,rk8601 - const: rockchip,rk8600 From fa5acd038ea657ad5033713d6916214cbd349151 Mon Sep 17 00:00:00 2001 From: Bryam Vargas Date: Fri, 28 Aug 2026 14:07:47 -0500 Subject: [PATCH 0289/1198] net/iucv: fix the recvmsg window update iucv_sock_recvmsg() sends the HiperSockets-only AF_IUCV_FLAG_WIN without testing the transport, so on a classic z/VM socket iucv_send_ctrl() sizes the skb through a NULL iucv->hs_dev. SO_MSGLIMIT accepts 1, so msglimit / 2 is zero and one recvmsg() on its own socket is enough for an unprivileged process to take a spurious disconnect. It also calls iucv_send_ctrl() under spin_lock_bh(&message_q.lock), which allocates GFP_KERNEL inside a section the code treats as atomic. Sending outside that lock lets two recvmsg() reach afiucv_hs_send() at once, where msg_recv is sampled for the advertised window and subtracted after dev_queue_xmit() -- and sendmsg reaches that counter under lock_sock() while recvmsg holds no socket lock, so both can subtract the same value, the counter goes negative and the credit reaches the peer twice. Test the transport, claim the credit with atomic_xchg() after the last error exit and hand it back if the transmit fails, and send once the lock is dropped. Fixes: 3881ac441f64 ("af_iucv: add HiperSockets transport") Fixes: 238965b71b96 ("net/af_iucv: build proper skbs for HiperTransport") Cc: stable@vger.kernel.org Tested-by: Aswin Karuvally Signed-off-by: Bryam Vargas Reviewed-by: Alexandra Winter Link: https://patch.msgid.link/20260828-b4-disp-33fac0ed-v3-1-e6d061880ee0@proton.me Signed-off-by: Jakub Kicinski --- net/iucv/af_iucv.c | 42 +++++++++++++++++++++++++----------------- 1 file changed, 25 insertions(+), 17 deletions(-) diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 4e5cc9da6e06..db261ecd19af 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -210,12 +210,6 @@ static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, phs_hdr->flags = flags; if (flags == AF_IUCV_FLAG_SYN) phs_hdr->window = iucv->msglimit; - else if ((flags == AF_IUCV_FLAG_WIN) || !flags) { - confirm_recv = atomic_read(&iucv->msg_recv); - phs_hdr->window = confirm_recv; - if (confirm_recv) - phs_hdr->flags = phs_hdr->flags | AF_IUCV_FLAG_WIN; - } memcpy(phs_hdr->destUserID, iucv->dst_user_id, 8); memcpy(phs_hdr->destAppName, iucv->dst_name, 8); memcpy(phs_hdr->srcUserID, iucv->src_user_id, 8); @@ -250,13 +244,22 @@ static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, } skb->protocol = cpu_to_be16(ETH_P_AF_IUCV); + /* Claim the receive credit here, not while building the header: every + * way this frame can be dropped has now been ruled out, so the window + * is zeroed only for as long as the transmit itself takes. + */ + if (flags == AF_IUCV_FLAG_WIN || !flags) { + confirm_recv = atomic_xchg(&iucv->msg_recv, 0); + phs_hdr->window = confirm_recv; + if (confirm_recv) + phs_hdr->flags = phs_hdr->flags | AF_IUCV_FLAG_WIN; + } + atomic_inc(&iucv->skbs_in_xmit); err = dev_queue_xmit(skb); if (net_xmit_eval(err)) { atomic_dec(&iucv->skbs_in_xmit); - } else { - atomic_sub(confirm_recv, &iucv->msg_recv); - WARN_ON(atomic_read(&iucv->msg_recv) < 0); + atomic_add(confirm_recv, &iucv->msg_recv); } return net_xmit_eval(err); @@ -1241,6 +1244,7 @@ static int iucv_sock_recvmsg(struct socket *sock, struct msghdr *msg, struct iucv_sock *iucv = iucv_sk(sk); unsigned int copied, rlen; struct sk_buff *skb, *rskb, *cskb; + bool send_win = false; int err = 0; u32 offset; @@ -1331,16 +1335,20 @@ static int iucv_sock_recvmsg(struct socket *sock, struct msghdr *msg, if (skb_queue_empty(&iucv->backlog_skb_q)) { if (!list_empty(&iucv->message_q.list)) iucv_process_message_q(sk); - if (atomic_read(&iucv->msg_recv) >= - iucv->msglimit / 2) { - err = iucv_send_ctrl(sk, AF_IUCV_FLAG_WIN); - if (err) { - sk->sk_state = IUCV_DISCONN; - sk->sk_state_change(sk); - } - } + if (iucv->transport == AF_IUCV_TRANS_HIPER && + atomic_read(&iucv->msg_recv) >= + iucv->msglimit / 2) + send_win = true; } spin_unlock_bh(&iucv->message_q.lock); + + if (send_win) { + err = iucv_send_ctrl(sk, AF_IUCV_FLAG_WIN); + if (err) { + sk->sk_state = IUCV_DISCONN; + sk->sk_state_change(sk); + } + } } done: From 5443d9c4f55d46634b95432e1e8a40b824019bbb Mon Sep 17 00:00:00 2001 From: Selvamani Rajagopal Date: Mon, 24 Aug 2026 14:57:58 -0700 Subject: [PATCH 0290/1198] net: ethernet: oa_tc6: Protect skb pointer used by two different kernel instances Threaded IRQ uses waiting_tx_skb. Transmit path also uses this pointer without any mutual exclusion protection. As a result, it might leak skb buffer, particularly if threaded IRQ sets disable_traffic true after start_xmit already checked and found that disable_traffic being false, if they happen to run on different cores. On fatal error, where disable_traffic is set, transmit function drops the packet and return NETDEV_TX_OK. Due to this change, skb_linearize call is moved up to the beginning of the transmit function. Since skb buffer may be freed from different contexts, dev_kfree_skb_any is used to free skb buffer now, replacing one of the kfree_skb call. oa_tc6_exit disables the irq before setting disable_traffic true. Fixes: b542d13fab0f ("net: ethernet: oa_tc6: Interrupt is active low, level triggered.") Signed-off-by: Selvamani Rajagopal Link: https://patch.msgid.link/20260824-fix-race-condition-and-crash-v7-1-4323279b18f2@onsemi.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/oa_tc6.c | 111 +++++++++++++++++++++++----------- 1 file changed, 77 insertions(+), 34 deletions(-) diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c index 417c15d1ff42..2f45001be0f5 100644 --- a/drivers/net/ethernet/oa_tc6.c +++ b/drivers/net/ethernet/oa_tc6.c @@ -693,6 +693,26 @@ static int oa_tc6_enable_data_transfer(struct oa_tc6 *tc6) return oa_tc6_write_register(tc6, OA_TC6_REG_CONFIG0, value); } +/* Called when a frame that is meant to be transmitted, is dropped. */ +static void oa_tc6_drop_tx_skb(struct oa_tc6 *tc6, struct sk_buff *skb) +{ + if (skb) { + tc6->netdev->stats.tx_dropped++; + dev_kfree_skb_any(skb); + } +} + +static struct sk_buff *oa_tc6_detach_waiting_tx_skb(struct oa_tc6 *tc6) +{ + struct sk_buff *skb; + + lockdep_assert_held(&tc6->tx_skb_lock); + skb = tc6->waiting_tx_skb; + tc6->waiting_tx_skb = NULL; + + return skb; +} + static void oa_tc6_cleanup_ongoing_rx_skb(struct oa_tc6 *tc6) { if (tc6->rx_skb) { @@ -704,26 +724,30 @@ static void oa_tc6_cleanup_ongoing_rx_skb(struct oa_tc6 *tc6) static void oa_tc6_cleanup_ongoing_tx_skb(struct oa_tc6 *tc6) { - if (tc6->ongoing_tx_skb) { - tc6->netdev->stats.tx_dropped++; - kfree_skb(tc6->ongoing_tx_skb); - tc6->ongoing_tx_skb = NULL; - } + oa_tc6_drop_tx_skb(tc6, tc6->ongoing_tx_skb); + tc6->ongoing_tx_skb = NULL; } static void oa_tc6_cleanup_waiting_tx_skb(struct oa_tc6 *tc6) { - if (tc6->waiting_tx_skb) { - tc6->netdev->stats.tx_dropped++; - kfree_skb(tc6->waiting_tx_skb); - tc6->waiting_tx_skb = NULL; - } + struct sk_buff *skb; + + spin_lock_bh(&tc6->tx_skb_lock); + skb = oa_tc6_detach_waiting_tx_skb(tc6); + spin_unlock_bh(&tc6->tx_skb_lock); + + oa_tc6_drop_tx_skb(tc6, skb); +} + +static void oa_tc6_free_ongoing_skbs(struct oa_tc6 *tc6) +{ + oa_tc6_cleanup_ongoing_tx_skb(tc6); + oa_tc6_cleanup_ongoing_rx_skb(tc6); } static void oa_tc6_free_pending_skbs(struct oa_tc6 *tc6) { - oa_tc6_cleanup_ongoing_tx_skb(tc6); - oa_tc6_cleanup_ongoing_rx_skb(tc6); + oa_tc6_free_ongoing_skbs(tc6); oa_tc6_cleanup_waiting_tx_skb(tc6); } @@ -734,9 +758,15 @@ static void oa_tc6_free_pending_skbs(struct oa_tc6 *tc6) static void oa_tc6_disable_traffic(struct oa_tc6 *tc6) { u32 regval = OA_TC6_INT_MASK0_ALL_INTERRUPTS; + struct sk_buff *skb; + spin_lock_bh(&tc6->tx_skb_lock); tc6->disable_traffic = true; - oa_tc6_free_pending_skbs(tc6); + skb = oa_tc6_detach_waiting_tx_skb(tc6); + spin_unlock_bh(&tc6->tx_skb_lock); + + oa_tc6_drop_tx_skb(tc6, skb); + oa_tc6_free_ongoing_skbs(tc6); oa_tc6_write_register(tc6, OA_TC6_REG_INT_MASK0, regval); oa_tc6_read_register(tc6, OA_TC6_REG_STATUS0, ®val); oa_tc6_write_register(tc6, OA_TC6_REG_STATUS0, regval); @@ -1177,8 +1207,7 @@ static int oa_tc6_try_spi_transfer(struct oa_tc6 *tc6) if (ret == -EAGAIN) continue; - oa_tc6_cleanup_ongoing_tx_skb(tc6); - oa_tc6_cleanup_ongoing_rx_skb(tc6); + oa_tc6_free_ongoing_skbs(tc6); netdev_err(tc6->netdev, "Device error: %d\n", ret); return ret; } @@ -1200,15 +1229,20 @@ static irqreturn_t oa_tc6_macphy_threaded_irq(int irq, void *data) * no need to attempt spi transfer, once it fails. Pending skbs * are already freed. */ - if (!tc6->disable_traffic) { - while (tc6->int_flag || - (tc6->waiting_tx_skb && tc6->tx_credits)) { - ret = oa_tc6_try_spi_transfer(tc6); - if (ret) { - disable_irq_nosync(tc6->spi->irq); - oa_tc6_disable_traffic(tc6); - break; - } + spin_lock_bh(&tc6->tx_skb_lock); + if (tc6->disable_traffic) { + spin_unlock_bh(&tc6->tx_skb_lock); + return IRQ_HANDLED; + } + spin_unlock_bh(&tc6->tx_skb_lock); + + while (tc6->int_flag || + (tc6->waiting_tx_skb && tc6->tx_credits)) { + ret = oa_tc6_try_spi_transfer(tc6); + if (ret) { + disable_irq_nosync(tc6->spi->irq); + oa_tc6_disable_traffic(tc6); + break; } } @@ -1287,23 +1321,30 @@ EXPORT_SYMBOL_GPL(oa_tc6_zero_align_receive_frame_enable); * @tc6: oa_tc6 struct. * @skb: socket buffer in which the ethernet frame is stored. * - * Return: NETDEV_TX_OK if the transmit ethernet frame skb added in the tx_skb_q - * otherwise returns NETDEV_TX_BUSY. + * Return: NETDEV_TX_OK either on successful queueing of the packet for + * transmission, or on packet getting dropped. Packet can be dropped due to + * failure in linearizing the buffer or disable_traffic is set due to + * earlier fatal error. Returns NETDEV_TX_BUSY when there is no room + * to queue the packet. */ netdev_tx_t oa_tc6_start_xmit(struct oa_tc6 *tc6, struct sk_buff *skb) { - if (tc6->disable_traffic || tc6->waiting_tx_skb) { - netif_stop_queue(tc6->netdev); - return NETDEV_TX_BUSY; - } - if (skb_linearize(skb)) { - dev_kfree_skb_any(skb); - tc6->netdev->stats.tx_dropped++; + oa_tc6_drop_tx_skb(tc6, skb); return NETDEV_TX_OK; } spin_lock_bh(&tc6->tx_skb_lock); + if (tc6->waiting_tx_skb) { + netif_stop_queue(tc6->netdev); + spin_unlock_bh(&tc6->tx_skb_lock); + return NETDEV_TX_BUSY; + } + if (tc6->disable_traffic) { + spin_unlock_bh(&tc6->tx_skb_lock); + oa_tc6_drop_tx_skb(tc6, skb); + return NETDEV_TX_OK; + } tc6->waiting_tx_skb = skb; spin_unlock_bh(&tc6->tx_skb_lock); @@ -1462,8 +1503,10 @@ EXPORT_SYMBOL_GPL(oa_tc6_init); */ void oa_tc6_exit(struct oa_tc6 *tc6) { - tc6->disable_traffic = true; disable_irq(tc6->spi->irq); + spin_lock_bh(&tc6->tx_skb_lock); + tc6->disable_traffic = true; + spin_unlock_bh(&tc6->tx_skb_lock); oa_tc6_phy_exit(tc6); oa_tc6_free_pending_skbs(tc6); } From 172c974113bffe5723b80b1acac17593bb50513c Mon Sep 17 00:00:00 2001 From: Selvamani Rajagopal Date: Mon, 24 Aug 2026 14:57:59 -0700 Subject: [PATCH 0291/1198] net: ethernet: oa_tc6: Improve the error recovery When oversubscribed traffic causes lot of buffer overflow errors, probably due to loss of data chunks, driver fails to find a data chunk with end_valid bit set, before it runs out of sk buffer space. As a result, assert is seen during skb_put. Now, check is made if skb buffer has enough tailroom for the incoming data before accepting. If there is no room, current frame is abandoned and it will start looking for a data chunk with start_valid bit, that is a new frame. SK buffer allocation error is considered as recoverable error. rx_buf_overflow flag is too specific and no longer the only condition this flag is used for. Therefore it is renamed as wait_until_start_valid. This is more appropriate as this flag is used to look for the next data chunk with SV bit set, after failures like buffer overflow, buffer allocation failure, skb pointer validity besides buffer overflow error. Not writing to status0 if it reads 0. Fixes: d70a0d8f2f2d ("net: ethernet: oa_tc6: implement receive path to receive rx ethernet frames") Signed-off-by: Selvamani Rajagopal Link: https://patch.msgid.link/20260824-fix-race-condition-and-crash-v7-2-4323279b18f2@onsemi.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/oa_tc6.c | 143 +++++++++++++++++++++++++--------- 1 file changed, 108 insertions(+), 35 deletions(-) diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c index 2f45001be0f5..657b1c6119da 100644 --- a/drivers/net/ethernet/oa_tc6.c +++ b/drivers/net/ethernet/oa_tc6.c @@ -83,7 +83,7 @@ struct oa_tc6 { u16 spi_data_tx_buf_offset; u16 tx_credits; u8 rx_chunks_available; - bool rx_buf_overflow; + bool wait_until_start_valid; bool int_flag; bool disable_traffic; bool prot_ctrl; @@ -751,6 +751,12 @@ static void oa_tc6_free_pending_skbs(struct oa_tc6 *tc6) oa_tc6_cleanup_waiting_tx_skb(tc6); } +static void oa_tc6_look_for_new_frame(struct oa_tc6 *tc6) +{ + tc6->wait_until_start_valid = true; + oa_tc6_cleanup_ongoing_rx_skb(tc6); +} + /* If the failure is at SPI interface level, masking and clearing * the interrupt of the device won't work. Since SPI interrupt is * disabled, it should stop the repeated interrupts. @@ -785,6 +791,13 @@ static int oa_tc6_process_extended_status(struct oa_tc6 *tc6) return ret; } + /* This function is called for each chunk received in a given SPI + * transaction. In case, extended status bit is set in more than + * one chunk, skip the write, if status0 is already cleared. + */ + if (!value) + return 0; + /* Clear the error interrupts status */ ret = oa_tc6_write_register(tc6, OA_TC6_REG_STATUS0, value); if (ret) { @@ -794,8 +807,7 @@ static int oa_tc6_process_extended_status(struct oa_tc6 *tc6) } if (FIELD_GET(OA_TC6_STATUS0_RX_BUFFER_OVERFLOW_ERROR, value)) { - tc6->rx_buf_overflow = true; - oa_tc6_cleanup_ongoing_rx_skb(tc6); + oa_tc6_look_for_new_frame(tc6); net_err_ratelimited("%s: Receive buffer overflow error\n", tc6->netdev->name); return -EAGAIN; @@ -821,6 +833,8 @@ static int oa_tc6_process_extended_status(struct oa_tc6 *tc6) static int oa_tc6_process_rx_chunk_footer(struct oa_tc6 *tc6, u32 footer) { + int ret = 0; + /* Process rx chunk footer for the following, * 1. tx credits * 2. errors if any from MAC-PHY @@ -831,9 +845,11 @@ static int oa_tc6_process_rx_chunk_footer(struct oa_tc6 *tc6, u32 footer) footer); if (FIELD_GET(OA_TC6_DATA_FOOTER_EXTENDED_STS, footer)) { - int ret = oa_tc6_process_extended_status(tc6); - - if (ret) + ret = oa_tc6_process_extended_status(tc6); + /* EAGAIN error is recoverable. Move on to check + * HEADER and SYNC errors before returning. + */ + if (ret && ret != -EAGAIN) return ret; } @@ -851,7 +867,7 @@ static int oa_tc6_process_rx_chunk_footer(struct oa_tc6 *tc6, u32 footer) return -ENODEV; } - return 0; + return ret; } static void oa_tc6_submit_rx_skb(struct oa_tc6 *tc6) @@ -876,13 +892,35 @@ static void oa_tc6_submit_rx_skb(struct oa_tc6 *tc6) tc6->rx_skb = NULL; } -static void oa_tc6_update_rx_skb(struct oa_tc6 *tc6, u8 *payload, u8 length) +/* On oversubscribed traffic condition, particularly with overwhelming rx + * buffer overflow errors, there could be data chunk loss. If tail + length + * goes beyond end pointer, that is an indication that the data chunk with + * end_valid bit is lost. Time to look for a data chunk with start_valid bit. + * + * If rx_skb is NULL, it is time to start looking for data chunk with + * start_bit. + */ +static int oa_tc6_update_rx_skb(struct oa_tc6 *tc6, u8 *payload, u8 length) { + if (!tc6->rx_skb || + skb_tailroom(tc6->rx_skb) < length) { + oa_tc6_look_for_new_frame(tc6); + return -EAGAIN; + } + memcpy(skb_put(tc6->rx_skb, length), payload, length); + return 0; } +/* On overwhelming rx buffer overflow errors, due to data chunk loss, it is + * possible that we get two data chunks with start_valid bit set, without + * end_valid bit set in between. In this case, rx_skb would have a valid + * buffer pointer. We should release, if a valid pointer is found before + * allocating a new one. + */ static int oa_tc6_allocate_rx_skb(struct oa_tc6 *tc6) { + oa_tc6_cleanup_ongoing_rx_skb(tc6); tc6->rx_skb = netdev_alloc_skb_ip_align(tc6->netdev, tc6->netdev->mtu + ETH_HLEN + ETH_FCS_LEN); if (!tc6->rx_skb) { @@ -902,7 +940,9 @@ static int oa_tc6_prcs_complete_rx_frame(struct oa_tc6 *tc6, u8 *payload, if (ret) return ret; - oa_tc6_update_rx_skb(tc6, payload, size); + ret = oa_tc6_update_rx_skb(tc6, payload, size); + if (ret) + return ret; oa_tc6_submit_rx_skb(tc6); @@ -917,22 +957,24 @@ static int oa_tc6_prcs_rx_frame_start(struct oa_tc6 *tc6, u8 *payload, u16 size) if (ret) return ret; - oa_tc6_update_rx_skb(tc6, payload, size); - - return 0; + return oa_tc6_update_rx_skb(tc6, payload, size); } -static void oa_tc6_prcs_rx_frame_end(struct oa_tc6 *tc6, u8 *payload, u16 size) +static int oa_tc6_prcs_rx_frame_end(struct oa_tc6 *tc6, u8 *payload, u16 size) { - oa_tc6_update_rx_skb(tc6, payload, size); + int ret; - oa_tc6_submit_rx_skb(tc6); + ret = oa_tc6_update_rx_skb(tc6, payload, size); + if (!ret) + oa_tc6_submit_rx_skb(tc6); + return ret; } -static void oa_tc6_prcs_ongoing_rx_frame(struct oa_tc6 *tc6, u8 *payload, - u32 footer) +static int oa_tc6_prcs_ongoing_rx_frame(struct oa_tc6 *tc6, u8 *payload, + u32 footer) { - oa_tc6_update_rx_skb(tc6, payload, OA_TC6_CHUNK_PAYLOAD_SIZE); + return oa_tc6_update_rx_skb(tc6, payload, + OA_TC6_CHUNK_PAYLOAD_SIZE); } static int oa_tc6_prcs_rx_chunk_payload(struct oa_tc6 *tc6, u8 *data, @@ -947,10 +989,10 @@ static int oa_tc6_prcs_rx_chunk_payload(struct oa_tc6 *tc6, u8 *data, u16 size; /* Restart the new rx frame after receiving rx buffer overflow error */ - if (start_valid && tc6->rx_buf_overflow) - tc6->rx_buf_overflow = false; + if (start_valid && tc6->wait_until_start_valid) + tc6->wait_until_start_valid = false; - if (tc6->rx_buf_overflow) + if (tc6->wait_until_start_valid) return 0; /* Process the chunk with complete rx frame */ @@ -972,8 +1014,7 @@ static int oa_tc6_prcs_rx_chunk_payload(struct oa_tc6 *tc6, u8 *data, /* Process the chunk with only rx frame end */ if (end_valid && !start_valid) { size = end_byte_offset + 1; - oa_tc6_prcs_rx_frame_end(tc6, data, size); - return 0; + return oa_tc6_prcs_rx_frame_end(tc6, data, size); } /* Process the chunk with previous rx frame end and next rx frame @@ -987,6 +1028,15 @@ static int oa_tc6_prcs_rx_chunk_payload(struct oa_tc6 *tc6, u8 *data, if (tc6->rx_skb) { size = end_byte_offset + 1; oa_tc6_prcs_rx_frame_end(tc6, data, size); + + /* Return value from oa_tc6_prcs_rx_frame_end is not + * checked. If it returned an error, it is to make + * the code to look for new frame. At this stage, + * code below is going to process a new frame. So, + * error condition is set to false, in case it is + * set before proceeding. + */ + tc6->wait_until_start_valid = false; } size = OA_TC6_CHUNK_PAYLOAD_SIZE - start_byte_offset; return oa_tc6_prcs_rx_frame_start(tc6, @@ -995,9 +1045,7 @@ static int oa_tc6_prcs_rx_chunk_payload(struct oa_tc6 *tc6, u8 *data, } /* Process the chunk with ongoing rx frame data */ - oa_tc6_prcs_ongoing_rx_frame(tc6, data, footer); - - return 0; + return oa_tc6_prcs_ongoing_rx_frame(tc6, data, footer); } static u32 oa_tc6_get_rx_chunk_footer(struct oa_tc6 *tc6, u16 footer_offset) @@ -1013,8 +1061,9 @@ static u32 oa_tc6_get_rx_chunk_footer(struct oa_tc6 *tc6, u16 footer_offset) static int oa_tc6_process_spi_data_rx_buf(struct oa_tc6 *tc6, u16 length) { u16 no_of_rx_chunks = length / OA_TC6_CHUNK_SIZE; + bool retry = false; + int ret = 0; u32 footer; - int ret; /* All the rx chunks in the receive SPI data buffer are examined here */ for (int i = 0; i < no_of_rx_chunks; i++) { @@ -1023,8 +1072,11 @@ static int oa_tc6_process_spi_data_rx_buf(struct oa_tc6 *tc6, u16 length) OA_TC6_CHUNK_PAYLOAD_SIZE); ret = oa_tc6_process_rx_chunk_footer(tc6, footer); - if (ret) - return ret; + if (ret) { + if (ret != -EAGAIN) + return ret; + retry = true; + } /* If there is a data valid chunks then process it for the * information needed to determine the validity and the location @@ -1036,12 +1088,35 @@ static int oa_tc6_process_spi_data_rx_buf(struct oa_tc6 *tc6, u16 length) ret = oa_tc6_prcs_rx_chunk_payload(tc6, payload, footer); - if (ret) - return ret; + if (ret) { + if (ret != -ENOMEM && ret != -EAGAIN) + return ret; + retry = true; + } } } - return 0; + /* Not bailing out on recoverable error codes, -EAGAIN and + * -ENOMEM. If subsequent loop iterations, if any, succeeds, + * error code would be overwritten. retry flag helps to + * make the caller to continue and retry. Since recovery + * action for -ENOMEM and -EAGAIN are same, we are returning + * one of the error codes, that is -EAGAIN. + * + * Successful recovery depends on how small the frames are, + * how many chunks, among the received chunks triggered the + * error, whether data is intact even with error conditions. + * As a result, there is no single, best method to recover + * most data when error conditions hit. We do our best by + * processing all the chunks with good "footer header" and + * "data valid" bit set. + */ + if (retry) { + ret = -EAGAIN; + oa_tc6_look_for_new_frame(tc6); + } + + return ret; } static __be32 oa_tc6_prepare_data_header(bool data_valid, bool start_valid, @@ -1203,10 +1278,8 @@ static int oa_tc6_try_spi_transfer(struct oa_tc6 *tc6) } ret = oa_tc6_process_spi_data_rx_buf(tc6, spi_len); - if (ret) { - if (ret == -EAGAIN) - continue; + if (ret && ret != -EAGAIN) { oa_tc6_free_ongoing_skbs(tc6); netdev_err(tc6->netdev, "Device error: %d\n", ret); return ret; From 349c366365876b7f67120827a0deb44899f59303 Mon Sep 17 00:00:00 2001 From: Selvamani Rajagopal Date: Mon, 24 Aug 2026 14:58:00 -0700 Subject: [PATCH 0292/1198] net: ethernet: oa_tc6: Disable tx queues on fatal error Previously, TX queue interface was stopped when disable_traffic flag was set, which would indicate fatal error. It is more appropriate to disable the queue as, unless driver is unloaded and reloaded, there is no recovery after disable_traffic is set. Queues may be re-enabled inadvertently by other layers. Intention of disable_traffic is only to stop the traffic from flowing on fatal error. Fixes: b542d13fab0f ("net: ethernet: oa_tc6: Interrupt is active low, level triggered.") Signed-off-by: Selvamani Rajagopal Link: https://patch.msgid.link/20260824-fix-race-condition-and-crash-v7-3-4323279b18f2@onsemi.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/oa_tc6.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c index 657b1c6119da..eea00b41fb8d 100644 --- a/drivers/net/ethernet/oa_tc6.c +++ b/drivers/net/ethernet/oa_tc6.c @@ -771,6 +771,10 @@ static void oa_tc6_disable_traffic(struct oa_tc6 *tc6) skb = oa_tc6_detach_waiting_tx_skb(tc6); spin_unlock_bh(&tc6->tx_skb_lock); + /* disable_traffic, when set, is a point of no return to + * working state. Keeping the TX queues disabled. + */ + netif_tx_disable(tc6->netdev); oa_tc6_drop_tx_skb(tc6, skb); oa_tc6_free_ongoing_skbs(tc6); oa_tc6_write_register(tc6, OA_TC6_REG_INT_MASK0, regval); From 3cc2aa96b97184abd6fc106aac626ddf14389813 Mon Sep 17 00:00:00 2001 From: Selvamani Rajagopal Date: Mon, 24 Aug 2026 14:58:01 -0700 Subject: [PATCH 0293/1198] net: ethernet: oa_tc6: Fix for the wrong data type Inadvertently bool data type is used where int is supposed to be used. This might turn a negative error code into true or false and sign of the return code would be lost. Fixes: 8f9bf857e43b ("net: ethernet: oa_tc6: implement internal PHY initialization") Signed-off-by: Selvamani Rajagopal Link: https://patch.msgid.link/20260824-fix-race-condition-and-crash-v7-4-4323279b18f2@onsemi.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/oa_tc6.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c index eea00b41fb8d..6fcc5f561d56 100644 --- a/drivers/net/ethernet/oa_tc6.c +++ b/drivers/net/ethernet/oa_tc6.c @@ -455,7 +455,7 @@ static int oa_tc6_mdiobus_read(struct mii_bus *bus, int addr, int regnum) { struct oa_tc6 *tc6 = bus->priv; u32 regval; - bool ret; + int ret; ret = oa_tc6_read_register(tc6, OA_TC6_PHY_STD_REG_ADDR_BASE | (regnum & OA_TC6_PHY_STD_REG_ADDR_MASK), From d7e7e98d23f42a92d9ab7e36302bd96bd9b33b5f Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Tue, 25 Aug 2026 04:10:51 -0400 Subject: [PATCH 0294/1198] net/sched: cls_u32: fix duplicate handle when node ID pool is exhausted MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit gen_new_kid() falls back to returning max (htid | 0xFFF) when both idr_alloc_u32() ranges are full, instead of reporting an error. u32_change() trusts that value and inserts a new knode with a handle that is already live in the hash table, breaking handle uniqueness within the table's node ID space. The handle was never reserved in ht->handle_idr, so every later error path that does idr_remove(&ht->handle_idr, handle) removes the reservation of a different, live knode, which is then reused — one failed add compounds into further duplicates. The 4095 limit is per (table, bucket) — ht->handle_idr is per hash table and the range is derived from htid (bucketid), so a table with divisor 256 can legitimately hold 256*4095 knodes. The sibling helper gen_new_htid() has the same silent in-band failure: it returns 0 when the tp_c handle pool (1..0x7FF) is full, and u32_init() publishes the root hash table with handle 0 without checking. Two root tables with handle 0 alias in u32_lookup_ht(), allowing cross-tcf_proto knode add/lookup/delete. Add the same exhaustion check that the divisor path already has. Return an error so u32_change() fails with ENOSPC/ENOMEM when the node ID space is exhausted, and so u32_init() fails with -ENOMEM when the hash table ID space is exhausted. The extack message distinguishes pool exhaustion (-ENOSPC) from a transient allocation failure (-ENOMEM). Conditions to recreate the bug: - CONFIG_NET_SCHED=y, CONFIG_CLS_U32=y (or =m with module loaded) - Create a clsact qdisc on a device, then add 4095 u32 filters with auto-generated handles to fill the node ID space for the root hash table (single bucket). The 4096th auto-handle filter add triggers the duplicate handle (fh 800::fff reused). Reachable at Level 2 (unshare -Urn, namespace-local CAP_NET_ADMIN). - For gen_new_htid: create 2047 u32 proto entries on the same block to fill the tp_c handle pool, then create one more. The root table gets handle 0 and aliases with other handle-0 root tables. Fixes: 7801db8aec95 ("net_sched: avoid generating same handle for u32 filters") Reported-by: vega@nebusec.ai Tested-by: Victor Nogueira Signed-off-by: Jamal Hadi Salim Link: https://patch.msgid.link/20260825081052.133898-1-jhs@mojatatu.com Signed-off-by: Jakub Kicinski --- net/sched/cls_u32.c | 32 ++++++++++++++++++++++++++------ 1 file changed, 26 insertions(+), 6 deletions(-) diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index ac6d0fa5a40e..a3e65c8cf29e 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -370,6 +370,10 @@ static int u32_init(struct tcf_proto *tp) refcount_set(&root_ht->refcnt, 1); root_ht->handle = tp_c ? gen_new_htid(tp_c, root_ht) : id2handle(0); + if (root_ht->handle == 0) { + kfree(root_ht); + return -ENOMEM; + } root_ht->prio = tp->prio; root_ht->is_root = true; idr_init(&root_ht->handle_idr); @@ -695,21 +699,33 @@ static int u32_delete(struct tcf_proto *tp, void *arg, bool *last, return ret; } -static u32 gen_new_kid(struct tc_u_hnode *ht, u32 htid) +static u32 gen_new_kid(struct tc_u_hnode *ht, u32 htid, int *err) { u32 index = htid | 0x800; u32 max = htid | 0xFFF; + *err = 0; + if (idr_alloc_u32(&ht->handle_idr, NULL, &index, max, GFP_KERNEL)) { index = htid + 1; - if (idr_alloc_u32(&ht->handle_idr, NULL, &index, max, - GFP_KERNEL)) - index = max; + *err = idr_alloc_u32(&ht->handle_idr, NULL, &index, max, + GFP_KERNEL); + if (*err) + return 0; } return index; } +static int u32_kid_extack(int err, struct netlink_ext_ack *extack) +{ + if (err == -ENOSPC) + NL_SET_ERR_MSG_MOD(extack, "Hash table node ID pool exhausted"); + else + NL_SET_ERR_MSG_MOD(extack, "Failed to allocate node ID"); + return err; +} + static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = { [TCA_U32_CLASSID] = { .type = NLA_U32 }, [TCA_U32_HASH] = { .type = NLA_U32 }, @@ -1079,7 +1095,9 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, * handle which is used to uniquely identify the match entry. */ if (!TC_U32_NODE(handle)) { - handle = gen_new_kid(ht, htid); + handle = gen_new_kid(ht, htid, &err); + if (err) + return u32_kid_extack(err, extack); } else { handle = htid | TC_U32_NODE(handle); err = idr_alloc_u32(&ht->handle_idr, NULL, &handle, @@ -1091,7 +1109,9 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, /* The user did not give us a handle; lets just generate one * from the table's pool of nodeids. */ - handle = gen_new_kid(ht, htid); + handle = gen_new_kid(ht, htid, &err); + if (err) + return u32_kid_extack(err, extack); } if (tb[TCA_U32_SEL] == NULL) { From 7b120a771943ffc3cbce787daecdd23eccb0505f Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Tue, 25 Aug 2026 04:10:52 -0400 Subject: [PATCH 0295/1198] selftests: tc-testing: add u32 node ID pool exhaustion test Add a tdc test case that fills the u32 node ID space with 4095 auto-generated handles, then attempts to add a 4096th. On the fixed kernel the 4096th filter is rejected with ENOSPC (exit 2). On the unfixed kernel it silently succeeds with a duplicate handle. The setup pipes the 4095 add commands directly into `tc -b -` inside a single bash -c (matching the existing test id 1234 pattern), avoiding any temp file. Signed-off-by: Jamal Hadi Salim Link: https://patch.msgid.link/20260825081052.133898-2-jhs@mojatatu.com Signed-off-by: Jakub Kicinski --- .../tc-testing/tc-tests/filters/u32.json | 23 +++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json b/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json index b2ca9d4e991b..e2b03f2b5e89 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json @@ -353,5 +353,28 @@ "teardown": [ "$TC qdisc del dev $DEV1 parent root drr" ] + }, + { + "id": "70fd", + "name": "Add u32 filter when node ID pool is exhausted (4096th filter rejected)", + "category": [ + "filter", + "u32" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DUMMY clsact", + "bash -c 'for i in {1..4095}; do echo filter add dev $DUMMY ingress prio 1 protocol ip u32 match u8 0 0 at 0; done | $TC -b -'" + ], + "cmdUnderTest": "$TC filter add dev $DUMMY ingress prio 1 protocol ip u32 match u8 0 0 at 0", + "expExitCode": "2", + "verifyCmd": "$TC -d filter show dev $DUMMY ingress", + "matchPattern": "fh 800::", + "matchCount": "4095", + "teardown": [ + "$TC qdisc del dev $DUMMY clsact" + ] } ] From dc0df5a0c62ccea1d0e08d39a4dc9064de81d411 Mon Sep 17 00:00:00 2001 From: Florian Schauer Date: Fri, 28 Aug 2026 08:08:22 +0200 Subject: [PATCH 0296/1198] page_pool: keep frag_offset aligned for odd-sized requests page_pool_alloc_frag_netmem() rounds the requested fragment size with size = ALIGN(size, dma_get_cache_alignment()); dma_get_cache_alignment() returns 1 unless the architecture defines ARCH_DMA_MINALIGN, which DMA-coherent architectures such as x86 do not. There the ALIGN() is a no-op and pool->frag_offset advances by the raw, unrounded size. A single caller asking for an odd size then leaves frag_offset misaligned for every fragment carved out of that page afterwards. The pool is shared, so the damage is not confined to the caller that caused it. The per-cpu system_page_pool used by generic XDP hits this. skb_pp_cow_data() allocates its fragments with the raw packet length: size = min_t(u32, len, PAGE_SIZE); truesize = size; page = page_pool_dev_alloc(pool, &page_off, &truesize); leaving frag_offset odd for whatever is carved out of that page next. Its own head allocation is already aligned -- SKB_HEAD_ALIGN(size) plus the XDP_PACKET_HEADROOM its callers pass -- so it is a later user of the shared pool that pays: page_pool_dev_alloc_va() returns a misaligned buffer, napi_build_skb() installs it as skb->head, and skb_shinfo(skb) == skb->head + skb->end is misaligned with it. skb_shinfo()->dataref is a 4-byte atomic_t at offset 0x20, so the atomic_inc() in __skb_clone() straddles a cache line. On x86 with split lock detection -- fatal for kernel split locks by default -- this panics the machine: Oops: Split lock detected RIP: 0010:skb_clone+0x154/0x1e0 Call Trace: raw_local_deliver+0x1ed/0x2c0 ip_protocol_deliver_rcu+0x54/0x1c0 ip_local_deliver_finish+0x85/0x100 ip_local_deliver+0x67/0x100 __netif_receive_skb_one_core+0x85/0xa0 process_backlog+0x87/0x130 Reproduced by attaching any generic-mode XDP program to loopback and opening a RAW IPPROTO_UDP socket, which makes raw_local_deliver() clone every locally delivered UDP packet; ordinary DNS traffic then triggers it, roughly once per 2500 clones. Observed on 6.12.101 and 7.1.8. Tracing page_pool_alloc_frag_netmem() over one such run shows the amplification -- two odd-sized requests, nine misaligned offsets: requested size & 7: 0: 17035 5: 1 7: 1 frag_offset & 7: 0: 17028 3: 1 4: 1 5: 1 6: 1 7: 5 and skb_pp_cow_data() returning heads that were aligned on entry: head 0xffff8f4c86aeac00 -> 0xffff8f4c53a9a9c4 (&7=4) head 0xffff8f4d6a8a42c0 -> 0xffff8f4c4f7b7a45 (&7=5) Round the fragment size up to at least the alignment struct skb_shared_info requires, so fragments are always suitably aligned for the objects callers build on them. Architectures needing a larger DMA alignment keep it. This also makes the remainder computed in page_pool_alloc_netmem(), *size = max_size - *offset; aligned, since max_size is a power of two -- which fixes the matching misalignment of skb->end. Verified with a controlled A/B under QEMU/KVM: same tree, same config, same compiler, same rootfs and identical traffic, differing only by this patch. A SEC("xdp.frags") XDP_PASS program on lo plus UDP datagrams larger than max_head_size drives skb_pp_cow_data()'s fragment loop, which passes raw packet lengths to the pool. Measured at the return of skb_pp_cow_data(): unpatched patched skb_pp_cow_data calls 40800 40800 misaligned skb->head 1120 0 dataref at line offset >60 80 0 The last row counts the accesses that actually fault: skb_shinfo()->dataref sits at head+end+0x20 and is a 4-byte atomic, so `lock incl` splits a 64-byte cache line only when that address lands at offset 61..63. All 80 occurrences were at offset 61; the panic reported above was at offset 62. Eliminating the misalignment removes every one of them. Same class of bug as commit 3bed3cc4156e ("net: Do not allocate page fragments that are not skb aligned"), which fixed the older netdev_alloc_frag()/napi_alloc_frag() allocators. Fixes: 53e0961da1c7 ("page_pool: add frag page recycling support in page pool") Cc: stable@vger.kernel.org Signed-off-by: Florian Schauer Acked-by: Jesper Dangaard Brouer Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20260828060822.2628276-1-florian@schauer.to Signed-off-by: Jakub Kicinski --- net/core/page_pool.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 8f8956fb061b..08d7f35cf608 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -1073,7 +1073,8 @@ netmem_ref page_pool_alloc_frag_netmem(struct page_pool *pool, if (WARN_ON(size > max_size)) return 0; - size = ALIGN(size, dma_get_cache_alignment()); + size = ALIGN(size, max_t(unsigned int, dma_get_cache_alignment(), + __alignof__(struct skb_shared_info))); *offset = pool->frag_offset; if (netmem && *offset + size > max_size) { From b6b9e6d4abe87b16ab55990b887c6fad8e7a01af Mon Sep 17 00:00:00 2001 From: Gary Guo Date: Fri, 28 Aug 2026 16:50:33 +0100 Subject: [PATCH 0297/1198] rust: pin-init: use irrefutable pattern for `stack_pin_init` In Rust 1.100.0, `Infallible` will become an alias of `!`. The let binding in `stack_pin_init` will thus become unreachable and produce an "unreachable expression" warning for the subsequent match, and thus will fail a `-Dwarnings` build. For this macro, all we need to know is that the error type is uninhabited, so replace this with an irrefutable pattern instead. [ The error looks like (dummy reproducer): error: unreachable expression --> rust/kernel/sync.rs:177:5 | 177 | pin_init::stack_pin_init!(let num = 42u32); | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ | | | unreachable expression | any code following this expression is unreachable | = note: `-D unreachable-code` implied by `-D warnings` = help: to override `-D warnings` add `#[allow(unreachable_code)]` = note: this error originates in the macro `pin_init::stack_pin_init` (in Nightly builds, run with -Z macro-backtrace for more info) - Miguel ] Reported-by: Mohamad Alsadhan Closes: https://github.com/Rust-for-Linux/pin-init/pull/171 Signed-off-by: Gary Guo Cc: stable@vger.kernel.org # Needed in 7.1.y and later (for 6.12.y and 6.18.y a custom one is needed). Link: https://patch.msgid.link/20260828155033.2101924-1-gary@kernel.org [ Reworded for typos. - Miguel ] Signed-off-by: Miguel Ojeda --- rust/pin-init/src/lib.rs | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/rust/pin-init/src/lib.rs b/rust/pin-init/src/lib.rs index 7600cdbbbf98..f1463be9479d 100644 --- a/rust/pin-init/src/lib.rs +++ b/rust/pin-init/src/lib.rs @@ -490,13 +490,7 @@ macro_rules! stack_pin_init { (let $var:ident $(: $t:ty)? = $val:expr) => { let val = $val; let mut $var = ::core::pin::pin!($crate::__internal::StackInit$(::<$t>)?::uninit()); - let mut $var = match $crate::__internal::StackInit::init($var, val) { - Ok(res) => res, - Err(x) => { - let x: ::core::convert::Infallible = x; - match x {} - } - }; + let Ok(mut $var) = $crate::__internal::StackInit::init($var, val); }; } From dee44f41f206becb41c492899c1996cfd7f82a1b Mon Sep 17 00:00:00 2001 From: Daehyeon Ko <4ncienth@gmail.com> Date: Wed, 26 Aug 2026 09:39:27 +0900 Subject: [PATCH 0298/1198] vsock/virtio: validate packet source for connected sockets virtio_transport_recv_pkt() looks up sockets first by the full source and destination tuple, then by destination only in the bound table. The fallback is needed for listening and connecting sockets, but sockets remain in the bound table after connect(), so it can also return a non-listening socket. The fallback does not validate the source address. In TCP_SYN_SENT, a RESPONSE from an unrelated source can transition the victim socket to TCP_ESTABLISHED while its stored remote address remains unchanged. Subsequent RW packets from that source are delivered through the same destination-only fallback. This was reproduced with capability-empty processes under different UIDs. The attacker discovered the target tuple through unprivileged AF_VSOCK sock_diag and caused the victim socket to read 16 attacker-chosen bytes; the intended peer-side socket read 0 of those 16 bytes. Add vsock_check_source() to validate the transport, source port and source CID against the peer stored in a non-listening socket. The local transport is the CID exception because its packets are generated internally with VMADDR_CID_LOCAL as their source, including connections using CID aliases. Use the helper after lock_sock() in the virtio receive path. Fixes: 06a8fc78367d ("VSOCK: Introduce virtio_vsock_common.ko") Closes: https://lore.kernel.org/netdev/20260813121236.2328599-1-4ncienth@gmail.com/ Cc: stable@vger.kernel.org Suggested-by: Stefano Garzarella Reviewed-by: Bobby Eshleman Signed-off-by: Daehyeon Ko <4ncienth@gmail.com> Link: https://patch.msgid.link/20260826003929.966160-2-4ncienth@gmail.com Signed-off-by: Jakub Kicinski --- include/net/af_vsock.h | 3 +++ net/vmw_vsock/af_vsock.c | 32 +++++++++++++++++++++++++ net/vmw_vsock/virtio_transport_common.c | 3 ++- 3 files changed, 37 insertions(+), 1 deletion(-) diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 3357ee62d10b..5549298c1ec6 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -229,6 +229,9 @@ struct sock *vsock_find_bound_socket_net(struct sockaddr_vm *addr, struct sock *vsock_find_connected_socket_net(struct sockaddr_vm *src, struct sockaddr_vm *dst, struct net *net); +bool vsock_check_source(const struct vsock_sock *vsk, + const struct vsock_transport *transport, + const struct sockaddr_vm *src); void vsock_remove_sock(struct vsock_sock *vsk); void vsock_for_each_connected_socket(struct vsock_transport *transport, void (*fn)(struct sock *sk)); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index a33b2a2d381d..f840498b58af 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -438,6 +438,38 @@ struct sock *vsock_find_connected_socket(struct sockaddr_vm *src, } EXPORT_SYMBOL_GPL(vsock_find_connected_socket); +/** + * vsock_check_source - validate a packet source against a socket peer + * @vsk: socket receiving the packet + * @transport: transport receiving the packet + * @src: source address from the packet + * + * Return: true if the packet arrived on the socket's assigned transport and + * its source matches the stored peer. Loopback packets are generated + * internally and always use the local CID as their source, including + * connections using a valid CID alias. + * + * The caller must hold the socket lock and must not call this for listening + * sockets, which accept packets from any source and have no assigned + * transport. + */ +bool vsock_check_source(const struct vsock_sock *vsk, + const struct vsock_transport *transport, + const struct sockaddr_vm *src) +{ + if (vsk->transport != transport) + return false; + + if (src->svm_port != vsk->remote_addr.svm_port) + return false; + + if (src->svm_cid == vsk->remote_addr.svm_cid) + return true; + + return transport->get_local_cid() == VMADDR_CID_LOCAL; +} +EXPORT_SYMBOL_GPL(vsock_check_source); + void vsock_remove_sock(struct vsock_sock *vsk) { /* Transport reassignment must not remove the binding. */ diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 88df82364f77..f225f53ed4ba 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1836,7 +1836,8 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, * lock_sock (note: listener sockets are not assigned to any transport) */ if (sock_flag(sk, SOCK_DONE) || - (sk->sk_state != TCP_LISTEN && vsk->transport != &t->transport)) { + (sk->sk_state != TCP_LISTEN && + !vsock_check_source(vsk, &t->transport, &src))) { (void)virtio_transport_reset_no_sock(t, skb, net); release_sock(sk); sock_put(sk); From ad9a7da3fa39c2d616ec0dd3cf6e30531d032fe7 Mon Sep 17 00:00:00 2001 From: Daehyeon Ko <4ncienth@gmail.com> Date: Wed, 26 Aug 2026 09:39:28 +0900 Subject: [PATCH 0299/1198] vsock/vmci: validate packet source for connected sockets vmci_transport_recv_stream_cb() looks up sockets first by the full source and destination tuple, then by destination only in the bound table. The fallback can select a non-listening socket without checking whether the packet came from its stored peer. This was reproduced with two VMCI contexts. A RST from the context not stored in a TCP_SYN_SENT socket reset that socket after it was selected by the destination-only lookup. VMCI can process notification packets in bottom-half context when the socket is not owned by user context, or defer packets to a workqueue. Use vsock_check_source() after taking the socket lock in the bottom-half path, and recheck after lock_sock() in the workqueue path. Listening sockets continue to accept packets from any source. Reply with a RST addressed from the received packet before dropping a source that fails validation. This preserves the existing reset behavior for bound non-listening and concurrently closed sockets without directing the reset to a connected socket's stored peer. Fixes: d021c344051a ("VSOCK: Introduce VM Sockets") Reported-by: Sashiko Closes: https://lore.kernel.org/netdev/20260814121255.6B5001F000E9@smtp.kernel.org/ Cc: stable@vger.kernel.org Suggested-by: Stefano Garzarella Suggested-by: Paolo Abeni Signed-off-by: Daehyeon Ko <4ncienth@gmail.com> Reviewed-by: Vishnu Dasa Link: https://patch.msgid.link/20260826003929.966160-3-4ncienth@gmail.com Signed-off-by: Jakub Kicinski --- net/vmw_vsock/vmci_transport.c | 34 ++++++++++++++++++++++++++++------ 1 file changed, 28 insertions(+), 6 deletions(-) diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 1c4ee039c166..1f186e8f8364 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -680,11 +680,13 @@ static int vmci_transport_recv_stream_cb(void *data, struct vmci_datagram *dg) struct vmci_transport_packet *pkt; struct vsock_sock *vsk; bool bh_process_pkt; + bool drop_pkt; int err; sk = NULL; err = VMCI_SUCCESS; bh_process_pkt = false; + drop_pkt = false; /* Ignore incoming packets from resources that aren't vsock * implementations. @@ -765,17 +767,29 @@ static int vmci_transport_recv_stream_cb(void *data, struct vmci_datagram *dg) bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { - /* The local context ID may be out of date, update it. */ - vsk->local_addr.svm_cid = dst.svm_cid; + if (sk->sk_state != TCP_LISTEN && + !vsock_check_source(vsk, &vmci_transport, &src)) { + drop_pkt = true; + err = VMCI_ERROR_NO_ACCESS; + } else { + /* The local context ID may be out of date, update it. */ + vsk->local_addr.svm_cid = dst.svm_cid; - if (sk->sk_state == TCP_ESTABLISHED) - vmci_trans(vsk)->notify_ops->handle_notify_pkt( - sk, pkt, true, &dst, &src, - &bh_process_pkt); + if (sk->sk_state == TCP_ESTABLISHED) + vmci_trans(vsk)->notify_ops->handle_notify_pkt(sk, pkt, true, + &dst, &src, + &bh_process_pkt); + } } bh_unlock_sock(sk); + if (drop_pkt) { + if (vmci_transport_send_reset_bh(&dst, &src, pkt) < 0) + pr_err("unable to send reset\n"); + goto out; + } + if (!bh_process_pkt) { struct vmci_transport_recv_pkt_info *recv_pkt_info; @@ -900,6 +914,7 @@ static void vmci_transport_recv_pkt_work(struct work_struct *work) { struct vmci_transport_recv_pkt_info *recv_pkt_info; struct vmci_transport_packet *pkt; + struct sockaddr_vm src; struct sock *sk; recv_pkt_info = @@ -908,6 +923,12 @@ static void vmci_transport_recv_pkt_work(struct work_struct *work) pkt = &recv_pkt_info->pkt; lock_sock(sk); + vsock_addr_init(&src, pkt->dg.src.context, pkt->src_port); + if (sk->sk_state != TCP_LISTEN && + !vsock_check_source(vsock_sk(sk), &vmci_transport, &src)) { + vmci_transport_reply_reset(pkt); + goto out; + } /* The local context ID may be out of date. */ vsock_sk(sk)->local_addr.svm_cid = pkt->dg.dst.context; @@ -937,6 +958,7 @@ static void vmci_transport_recv_pkt_work(struct work_struct *work) break; } +out: release_sock(sk); kfree(recv_pkt_info); /* Release reference obtained in the stream callback when we fetched From fee10655709c5c597e8e9f722f3035d9ea31ff3a Mon Sep 17 00:00:00 2001 From: Aohan Mei Date: Wed, 26 Aug 2026 10:51:20 +0800 Subject: [PATCH 0300/1198] net/sched: cls_flower: validate mask pointer after nla_next() fl_set_enc_opt() iterates the key's nested tunnel-option attributes with nla_for_each_attr() while advancing a single mask pointer via nla_next() at the bottom of each loop, so the mask cursor is driven by the number of key attributes rather than by the mask's own attributes. The nla_ok() added by commit c96adff956191 ("cls_flower: call nla_ok() before nla_next()") only validates the mask pointer that was just consumed; the pointer produced by nla_next() is used by the next iteration (fl_set_geneve_opt() and siblings) without any validation. The mask's nested attributes are validated with NL_VALIDATE_LIBERAL, which merely warns on trailing bytes that do not form a complete attribute. A mask carrying one valid attribute plus 1-3 residue bytes (or a non-aligned attribute length making msk_depth negative) therefore reaches the next iteration with msk_depth != 0, so neither the !msk_depth check in fl_set_enc_opt() nor the !depth check in the per-type helpers fires. nla_type() then reads past the mask payload and nla_parse_nested_deprecated() iterates with an nla_len taken from those bytes, reading well beyond the mask attribute (KASAN: slab-out-of-bounds read in __nla_validate_parse from fl_change()). Validate the advanced mask pointer as well: when the mask is not legitimately exhausted (msk_depth != 0) and the new pointer fails nla_ok(), reject the filter with -EINVAL. An exactly exhausted mask still skips the check, preserving exact-match behaviour for the remaining key attributes. Fixes: c96adff95619 ("cls_flower: call nla_ok() before nla_next()") Reported-by: TencentOS Corvus AI Cc: stable@vger.kernel.org Signed-off-by: Aohan Mei Link: https://patch.msgid.link/20260826025123.62758-1-ljp1205831794@gmail.com Signed-off-by: Jakub Kicinski --- net/sched/cls_flower.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 0e275b58151c..1cefea571efd 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1703,6 +1703,11 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, return -EINVAL; } nla_opt_msk = nla_next(nla_opt_msk, &msk_depth); + + if (msk_depth && !nla_ok(nla_opt_msk, msk_depth)) { + NL_SET_ERR_MSG(extack, "A mask attribute is invalid"); + return -EINVAL; + } } return 0; From e510334fbaeaa016ac76d80b4c5f47611c5f7860 Mon Sep 17 00:00:00 2001 From: Mehmet Koseoglu Date: Fri, 28 Aug 2026 04:50:20 +0300 Subject: [PATCH 0301/1198] rust: samples: add missing newlines in rust_print_main Calls to `pr_info!` in `arc_print` are missing trailing newlines, which are expected as the `pr_*!` documentation shows. Add the missing `\n` to all four formatting strings. Fixes: f431c5c581fa ("samples: rust: print: Add sample code for Arc printing") Fixes: 47cb6bf7860c ("rust: use derive(CoercePointee) on rustc >= 1.84.0") Suggested-by: Miguel Ojeda Link: https://github.com/Rust-for-Linux/linux/issues/1139 Signed-off-by: Mehmet Koseoglu Link: https://patch.msgid.link/20260828015148.221737-2-mehmet.mkoseoglu@gmail.com [ Reworded to fix the description of the missing-newline behavior. - Miguel ] Signed-off-by: Miguel Ojeda --- samples/rust/rust_print_main.rs | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/samples/rust/rust_print_main.rs b/samples/rust/rust_print_main.rs index 682207c81fc2..01729e87d6b5 100644 --- a/samples/rust/rust_print_main.rs +++ b/samples/rust/rust_print_main.rs @@ -23,10 +23,10 @@ fn arc_print() -> Result { let b = UniqueArc::new("hello, world", GFP_KERNEL)?; // Prints the value of data in `a`. - pr_info!("{}", a); + pr_info!("{}\n", a); // Uses ":?" to print debug fmt of `b`. - pr_info!("{:?}", b); + pr_info!("{:?}\n", b); let a: Arc<&str> = b.into(); let c = a.clone(); @@ -42,7 +42,7 @@ fn arc_print() -> Result { use kernel::fmt::Display; fn arc_dyn_print(arc: &Arc) { - pr_info!("Arc says {arc}"); + pr_info!("Arc says {arc}\n"); } let a_i32_display: Arc = Arc::new(42i32, GFP_KERNEL)?; @@ -53,7 +53,7 @@ fn arc_dyn_print(arc: &Arc) { } // Pretty-prints the debug formatting with lower-case hexadecimal integers. - pr_info!("{:#x?}", a); + pr_info!("{:#x?}\n", a); Ok(()) } From 2987ee196c88dbde0463dc87d5fb209c684e34a2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 27 Aug 2026 16:06:56 +0000 Subject: [PATCH 0302/1198] igmp: convert struct ip_sf_list to RCU Commit 23d2b94043ca ("igmp: Add ip_mc_list lock in ip_check_mc_rcu") added spin_lock_bh(&im->lock) to ip_check_mc_rcu() to prevent a use-after-free while iterating im->sources during concurrent deletions. However, ip_check_mc_rcu() is called from RCU read-side critical sections in packet receive and route lookup fast paths (e.g. __mkroute_output(), ip_route_input_rcu(), and __udp4_lib_rcv()). When igmpv3_send_cr() or igmpv3_send_report() holds &pmc->lock and calls add_grec() -> igmpv3_newpack() -> ip_route_output_ports(), an XFRM policy matching a multicast destination triggers xfrm_tmpl_resolve_one() -> xfrm4_get_saddr() -> __mkroute_output() -> ip_check_mc_rcu(). This attempts to acquire &im->lock while &pmc->lock is already held on the same CPU, triggering a lockdep recursive locking warning / deadlock. Fix this by converting IPv4 struct ip_sf_list to RCU, mirroring the IPv6 implementation in net/ipv6/mcast.c: 1. Add struct rcu_head to struct ip_sf_list and annotate sf_next, sources, and tomb as __rcu pointers. 2. Use rcu_assign_pointer() and kfree_rcu() for list updates and deletions. 3. Remove spin_lock_bh(&im->lock) from ip_check_mc_rcu() and traverse im->sources locklessly with for_each_psf_rcu(), reading and writing counter fields with READ_ONCE() and WRITE_ONCE(). Note: RCU conversion of /proc/net/mcfilter will be done in a separate patch. Fixes: 23d2b94043ca ("igmp: Add ip_mc_list lock in ip_check_mc_rcu") Reported-by: syzbot+3d99fb01bcd740f2fc1e@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=3d99fb01bcd740f2fc1e Signed-off-by: Eric Dumazet Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/20260827160656.903003-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/linux/igmp.h | 7 +- net/ipv4/igmp.c | 210 +++++++++++++++++++++++++++---------------- 2 files changed, 135 insertions(+), 82 deletions(-) diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 3a2d35a9f307..a0cf0398519f 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -57,20 +57,21 @@ struct ip_mc_socklist { }; struct ip_sf_list { - struct ip_sf_list *sf_next; + struct ip_sf_list __rcu *sf_next; unsigned long sf_count[2]; /* include/exclude counts */ __be32 sf_inaddr; unsigned char sf_gsresp; /* include in g & s response? */ unsigned char sf_oldin; /* change state */ unsigned char sf_crcount; /* retrans. left to send */ + struct rcu_head rcu; }; struct ip_mc_list { struct in_device *interface; __be32 multiaddr; unsigned int sfmode; - struct ip_sf_list *sources; - struct ip_sf_list *tomb; + struct ip_sf_list __rcu *sources; + struct ip_sf_list __rcu *tomb; unsigned long sfcount[2]; union { struct ip_mc_list *next; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index b80b8a92f46e..d56355aca797 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -188,6 +188,10 @@ static void ip_ma_put(struct ip_mc_list *im) } } +#define pmc_dereference(e, pmc) \ + rcu_dereference_protected(e, lockdep_is_held(&(pmc)->lock) || \ + lockdep_is_held(&(pmc)->interface->mc_tomb_lock)) + #define for_each_pmc_rcu(in_dev, pmc) \ for (pmc = rcu_dereference(in_dev->mc_list); \ pmc != NULL; \ @@ -198,13 +202,28 @@ static void ip_ma_put(struct ip_mc_list *im) pmc != NULL; \ pmc = rtnl_dereference(pmc->next_rcu)) +#define for_each_psf_mclock(pmc, psf) \ + for (psf = pmc_dereference((pmc)->sources, pmc); \ + psf; \ + psf = pmc_dereference(psf->sf_next, pmc)) + +#define for_each_psf_rcu(im, psf) \ + for (psf = rcu_dereference((im)->sources); \ + psf; \ + psf = rcu_dereference(psf->sf_next)) + +#define for_each_psf_tomb(pmc, psf) \ + for (psf = pmc_dereference((pmc)->tomb, pmc); \ + psf; \ + psf = pmc_dereference(psf->sf_next, pmc)) + static void ip_sf_list_clear_all(struct ip_sf_list *psf) { struct ip_sf_list *next; while (psf) { - next = psf->sf_next; - kfree(psf); + next = rcu_dereference_protected(psf->sf_next, 1); + kfree_rcu(psf, rcu); psf = next; } } @@ -349,7 +368,7 @@ igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) struct ip_sf_list *psf; int scount = 0; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (!is_in(pmc, psf, type, gdeleted, sdeleted)) continue; scount++; @@ -494,7 +513,8 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, struct net *net = dev_net(dev); struct igmpv3_report *pih; struct igmpv3_grec *pgr = NULL; - struct ip_sf_list *psf, *psf_next, *psf_prev, **psf_list; + struct ip_sf_list *psf, *psf_next, *psf_prev; + struct ip_sf_list __rcu **psf_list; int scount, stotal, first, isquery, truncate; unsigned int mtu; @@ -517,7 +537,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, psf_list = sdeleted ? &pmc->tomb : &pmc->sources; - if (!*psf_list) + if (!rcu_access_pointer(*psf_list)) goto empty_source; pih = skb ? igmpv3_report_hdr(skb) : NULL; @@ -533,10 +553,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, } first = 1; psf_prev = NULL; - for (psf = *psf_list; psf; psf = psf_next) { + for (psf = pmc_dereference(*psf_list, pmc); + psf; + psf = psf_next) { __be32 *psrc; - psf_next = psf->sf_next; + psf_next = pmc_dereference(psf->sf_next, pmc); if (!is_in(pmc, psf, type, gdeleted, sdeleted)) { psf_prev = psf; @@ -583,10 +605,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, psf->sf_crcount--; if ((sdeleted || gdeleted) && psf->sf_crcount == 0) { if (psf_prev) - psf_prev->sf_next = psf->sf_next; + rcu_assign_pointer(psf_prev->sf_next, + psf_next); else - *psf_list = psf->sf_next; - kfree(psf); + rcu_assign_pointer(*psf_list, + psf_next); + kfree_rcu(psf, rcu); continue; } } @@ -655,28 +679,29 @@ static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) /* * remove zero-count source records from a source filter list */ -static void igmpv3_clear_zeros(struct ip_sf_list **ppsf) +static void igmpv3_clear_zeros(struct ip_sf_list __rcu **ppsf) { struct ip_sf_list *psf_prev, *psf_next, *psf; psf_prev = NULL; - for (psf = *ppsf; psf; psf = psf_next) { - psf_next = psf->sf_next; + for (psf = rcu_dereference_protected(*ppsf, 1); psf; psf = psf_next) { + psf_next = rcu_dereference_protected(psf->sf_next, 1); if (psf->sf_crcount == 0) { if (psf_prev) - psf_prev->sf_next = psf->sf_next; + rcu_assign_pointer(psf_prev->sf_next, psf_next); else - *ppsf = psf->sf_next; - kfree(psf); - } else + rcu_assign_pointer(*ppsf, psf_next); + kfree_rcu(psf, rcu); + } else { psf_prev = psf; + } } } static void kfree_pmc(struct ip_mc_list *pmc) { - ip_sf_list_clear_all(pmc->sources); - ip_sf_list_clear_all(pmc->tomb); + ip_sf_list_clear_all(rcu_dereference_protected(pmc->sources, 1)); + ip_sf_list_clear_all(rcu_dereference_protected(pmc->tomb, 1)); kfree(pmc); } @@ -710,7 +735,8 @@ static void igmpv3_send_cr(struct in_device *in_dev) igmpv3_clear_zeros(&pmc->sources); } } - if (pmc->crcount == 0 && !pmc->tomb && !pmc->sources) { + if (pmc->crcount == 0 && !rcu_access_pointer(pmc->tomb) && + !rcu_access_pointer(pmc->sources)) { if (pmc_prev) pmc_prev->next = pmc_next; else @@ -896,7 +922,7 @@ static int igmp_xmarksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) int i, scount; scount = 0; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) { @@ -927,7 +953,7 @@ static int igmp_marksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) /* mark INCLUDE-mode sources */ scount = 0; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) @@ -1228,11 +1254,12 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im, if (pmc->sfmode == MCAST_INCLUDE) { struct ip_sf_list *psf; + for_each_psf_mclock(im, psf) + psf->sf_crcount = pmc->crcount; pmc->tomb = im->tomb; pmc->sources = im->sources; - im->tomb = im->sources = NULL; - for (psf = pmc->sources; psf; psf = psf->sf_next) - psf->sf_crcount = pmc->crcount; + RCU_INIT_POINTER(im->tomb, NULL); + RCU_INIT_POINTER(im->sources, NULL); } spin_unlock_bh(&im->lock); @@ -1271,9 +1298,18 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im) if (pmc) { im->interface = pmc->interface; if (im->sfmode == MCAST_INCLUDE) { - swap(im->tomb, pmc->tomb); - swap(im->sources, pmc->sources); - for (psf = im->sources; psf; psf = psf->sf_next) + struct ip_sf_list *sources, *tomb; + + tomb = rcu_replace_pointer(im->tomb, + rcu_dereference_protected(pmc->tomb, 1), + lockdep_is_held(&im->lock)); + rcu_assign_pointer(pmc->tomb, tomb); + + sources = rcu_replace_pointer(im->sources, + rcu_dereference_protected(pmc->sources, 1), + lockdep_is_held(&im->lock)); + rcu_assign_pointer(pmc->sources, sources); + for_each_psf_mclock(im, psf) psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); } else { @@ -1310,8 +1346,8 @@ static void igmpv3_clear_delrec(struct in_device *in_dev) struct ip_sf_list *psf; spin_lock_bh(&pmc->lock); - psf = pmc->tomb; - pmc->tomb = NULL; + psf = pmc_dereference(pmc->tomb, pmc); + RCU_INIT_POINTER(pmc->tomb, NULL); spin_unlock_bh(&pmc->lock); ip_sf_list_clear_all(psf); } @@ -1990,7 +2026,7 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, int rv = 0; psf_prev = NULL; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (psf->sf_inaddr == *psfsrc) break; psf_prev = psf; @@ -1999,7 +2035,7 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, /* source filter not found, or count wrong => bug */ return -ESRCH; } - psf->sf_count[sfmode]--; + WRITE_ONCE(psf->sf_count[sfmode], psf->sf_count[sfmode] - 1); if (psf->sf_count[sfmode] == 0) { ip_rt_multicast_event(pmc->interface); } @@ -2011,19 +2047,28 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, /* no more filters for this source */ if (psf_prev) - psf_prev->sf_next = psf->sf_next; + rcu_assign_pointer(psf_prev->sf_next, + pmc_dereference(psf->sf_next, pmc)); else - pmc->sources = psf->sf_next; + rcu_assign_pointer(pmc->sources, + pmc_dereference(psf->sf_next, pmc)); #ifdef CONFIG_IP_MULTICAST if (psf->sf_oldin && !IGMP_V1_SEEN(in_dev) && !IGMP_V2_SEEN(in_dev)) { - psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); - psf->sf_next = pmc->tomb; - pmc->tomb = psf; - rv = 1; - } else + struct ip_sf_list *dpsf = kmalloc_obj(*dpsf, GFP_ATOMIC); + + if (dpsf) { + *dpsf = *psf; + dpsf->sf_crcount = in_dev->mr_qrv ?: + READ_ONCE(net->ipv4.sysctl_igmp_qrv); + rcu_assign_pointer(dpsf->sf_next, + pmc_dereference(pmc->tomb, pmc)); + rcu_assign_pointer(pmc->tomb, dpsf); + rv = 1; + } + } #endif - kfree(psf); + kfree_rcu(psf, rcu); } return rv; } @@ -2060,7 +2105,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, err = -EINVAL; if (!pmc->sfcount[sfmode]) goto out_unlock; - pmc->sfcount[sfmode]--; + WRITE_ONCE(pmc->sfcount[sfmode], pmc->sfcount[sfmode] - 1); } err = 0; for (i = 0; i < sfcount; i++) { @@ -2083,7 +2128,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, #ifdef CONFIG_IP_MULTICAST pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); - for (psf = pmc->sources; psf; psf = psf->sf_next) + for_each_psf_mclock(pmc, psf) psf->sf_crcount = 0; igmp_ifc_event(pmc->interface); } else if (sf_setstate(pmc) || changerec) { @@ -2104,7 +2149,7 @@ static int ip_mc_add1_src(struct ip_mc_list *pmc, int sfmode, struct ip_sf_list *psf, *psf_prev; psf_prev = NULL; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (psf->sf_inaddr == *psfsrc) break; psf_prev = psf; @@ -2114,12 +2159,12 @@ static int ip_mc_add1_src(struct ip_mc_list *pmc, int sfmode, if (!psf) return -ENOBUFS; psf->sf_inaddr = *psfsrc; - if (psf_prev) { - psf_prev->sf_next = psf; - } else - pmc->sources = psf; + if (psf_prev) + rcu_assign_pointer(psf_prev->sf_next, psf); + else + rcu_assign_pointer(pmc->sources, psf); } - psf->sf_count[sfmode]++; + WRITE_ONCE(psf->sf_count[sfmode], psf->sf_count[sfmode] + 1); if (psf->sf_count[sfmode] == 1) { ip_rt_multicast_event(pmc->interface); } @@ -2132,13 +2177,15 @@ static void sf_markstate(struct ip_mc_list *pmc) struct ip_sf_list *psf; int mca_xcount = pmc->sfcount[MCAST_EXCLUDE]; - for (psf = pmc->sources; psf; psf = psf->sf_next) + for_each_psf_mclock(pmc, psf) { if (pmc->sfcount[MCAST_EXCLUDE]) { psf->sf_oldin = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; - } else + } else { psf->sf_oldin = psf->sf_count[MCAST_INCLUDE] != 0; + } + } } static int sf_setstate(struct ip_mc_list *pmc) @@ -2149,27 +2196,31 @@ static int sf_setstate(struct ip_mc_list *pmc) int new_in, rv; rv = 0; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (pmc->sfcount[MCAST_EXCLUDE]) { new_in = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; - } else + } else { new_in = psf->sf_count[MCAST_INCLUDE] != 0; + } if (new_in) { if (!psf->sf_oldin) { struct ip_sf_list *prev = NULL; - for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) { + for_each_psf_tomb(pmc, dpsf) { if (dpsf->sf_inaddr == psf->sf_inaddr) break; prev = dpsf; } if (dpsf) { + struct ip_sf_list *dpsf_next; + + dpsf_next = pmc_dereference(dpsf->sf_next, pmc); if (prev) - prev->sf_next = dpsf->sf_next; + rcu_assign_pointer(prev->sf_next, dpsf_next); else - pmc->tomb = dpsf->sf_next; - kfree(dpsf); + rcu_assign_pointer(pmc->tomb, dpsf_next); + kfree_rcu(dpsf, rcu); } psf->sf_crcount = qrv; rv++; @@ -2181,17 +2232,19 @@ static int sf_setstate(struct ip_mc_list *pmc) * add or update "delete" records if an active filter * is now inactive */ - for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) + for_each_psf_tomb(pmc, dpsf) { if (dpsf->sf_inaddr == psf->sf_inaddr) break; + } if (!dpsf) { dpsf = kmalloc_obj(*dpsf, GFP_ATOMIC); if (!dpsf) continue; *dpsf = *psf; /* pmc->lock held by callers */ - dpsf->sf_next = pmc->tomb; - pmc->tomb = dpsf; + rcu_assign_pointer(dpsf->sf_next, + pmc_dereference(pmc->tomb, pmc)); + rcu_assign_pointer(pmc->tomb, dpsf); } dpsf->sf_crcount = qrv; rv++; @@ -2231,7 +2284,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, #endif isexclude = pmc->sfmode == MCAST_EXCLUDE; if (!delta) - pmc->sfcount[sfmode]++; + WRITE_ONCE(pmc->sfcount[sfmode], pmc->sfcount[sfmode] + 1); err = 0; for (i = 0; i < sfcount; i++) { err = ip_mc_add1_src(pmc, sfmode, &psfsrc[i]); @@ -2242,7 +2295,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int j; if (!delta) - pmc->sfcount[sfmode]--; + WRITE_ONCE(pmc->sfcount[sfmode], pmc->sfcount[sfmode] - 1); for (j = 0; j < i; j++) (void) ip_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->sfcount[MCAST_EXCLUDE] != 0)) { @@ -2262,7 +2315,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); - for (psf = pmc->sources; psf; psf = psf->sf_next) + for_each_psf_mclock(pmc, psf) psf->sf_crcount = 0; igmp_ifc_event(in_dev); } else if (sf_setstate(pmc)) { @@ -2278,13 +2331,13 @@ static void ip_mc_clear_src(struct ip_mc_list *pmc) struct ip_sf_list *tomb, *sources; spin_lock_bh(&pmc->lock); - tomb = pmc->tomb; - pmc->tomb = NULL; - sources = pmc->sources; - pmc->sources = NULL; + tomb = pmc_dereference(pmc->tomb, pmc); + RCU_INIT_POINTER(pmc->tomb, NULL); + sources = pmc_dereference(pmc->sources, pmc); + RCU_INIT_POINTER(pmc->sources, NULL); pmc->sfmode = MCAST_EXCLUDE; - pmc->sfcount[MCAST_INCLUDE] = 0; - pmc->sfcount[MCAST_EXCLUDE] = 1; + WRITE_ONCE(pmc->sfcount[MCAST_INCLUDE], 0); + WRITE_ONCE(pmc->sfcount[MCAST_EXCLUDE], 1); spin_unlock_bh(&pmc->lock); ip_sf_list_clear_all(tomb); @@ -2866,20 +2919,19 @@ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u rv = 1; } else if (im) { if (src_addr) { - spin_lock_bh(&im->lock); - for (psf = im->sources; psf; psf = psf->sf_next) { + for_each_psf_rcu(im, psf) { if (psf->sf_inaddr == src_addr) break; } if (psf) - rv = psf->sf_count[MCAST_INCLUDE] || - psf->sf_count[MCAST_EXCLUDE] != - im->sfcount[MCAST_EXCLUDE]; + rv = READ_ONCE(psf->sf_count[MCAST_INCLUDE]) || + READ_ONCE(psf->sf_count[MCAST_EXCLUDE]) != + READ_ONCE(im->sfcount[MCAST_EXCLUDE]); else - rv = im->sfcount[MCAST_EXCLUDE] != 0; - spin_unlock_bh(&im->lock); - } else + rv = READ_ONCE(im->sfcount[MCAST_EXCLUDE]) != 0; + } else { rv = 1; /* unspecified source; tentatively allow */ + } } return rv; } @@ -3043,7 +3095,7 @@ static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq) im = rcu_dereference(idev->mc_list); if (likely(im)) { spin_lock_bh(&im->lock); - psf = im->sources; + psf = pmc_dereference(im->sources, im); if (likely(psf)) { state->im = im; state->idev = idev; @@ -3059,7 +3111,7 @@ static struct ip_sf_list *igmp_mcf_get_next(struct seq_file *seq, struct ip_sf_l { struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); - psf = psf->sf_next; + psf = pmc_dereference(psf->sf_next, state->im); while (!psf) { spin_unlock_bh(&state->im->lock); state->im = state->im->next; @@ -3075,7 +3127,7 @@ static struct ip_sf_list *igmp_mcf_get_next(struct seq_file *seq, struct ip_sf_l state->im = rcu_dereference(state->idev->mc_list); } spin_lock_bh(&state->im->lock); - psf = state->im->sources; + psf = pmc_dereference(state->im->sources, state->im); } out: return psf; From 9feb069e5ed03582fbf6272539f1caa2a17dc6d5 Mon Sep 17 00:00:00 2001 From: Qingfang Deng Date: Fri, 28 Aug 2026 15:32:36 +0800 Subject: [PATCH 0303/1198] ppp: ppp_async: simplify tty disc_data access tty_ldisc_hangup() invokes the hangup callback while holding only a read lock on tty->ldisc_sem, so it can run concurrently with other line discipline callbacks. This currently forces async PPP to maintain separate lifetime protection around tty->disc_data. Line discipline close is called under the write lock during hangup processing. Remove the hangup callback and rely on close for teardown, as done for SLIP by commit 23c53269f2ba ("slip: remove slip_hangup() to fix use-after-free in slip_receive_buf()"). This serializes teardown with all other line discipline operations. disc_data_lock, refcount and completion are redundant with that serialization. Remove them and access tty->disc_data directly. This also eliminates a lockdep warning reported by syzbot. The warning does not indicate a real deadlock because the write side runs only in process context with hardirqs disabled. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot+8e808eb853386f575d86@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/0000000000002fbad30611e25849@google.com/ Signed-off-by: Qingfang Deng Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20260828073245.126804-1-qingfang.deng@linux.dev Signed-off-by: Jakub Kicinski --- drivers/net/ppp/ppp_async.c | 82 ++++--------------------------------- 1 file changed, 7 insertions(+), 75 deletions(-) diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c index 583426d06381..ea7fe9608ffd 100644 --- a/drivers/net/ppp/ppp_async.c +++ b/drivers/net/ppp/ppp_async.c @@ -63,8 +63,6 @@ struct asyncppp { struct tasklet_struct tsk; - refcount_t refcnt; - struct completion dead; struct ppp_channel chan; /* interface to generic ppp layer */ unsigned char obuf[OBUFSIZE]; }; @@ -114,38 +112,6 @@ static const struct ppp_channel_ops async_ops = { * Routines implementing the PPP line discipline. */ -/* - * We have a potential race on dereferencing tty->disc_data, - * because the tty layer provides no locking at all - thus one - * cpu could be running ppp_asynctty_receive while another - * calls ppp_asynctty_close, which zeroes tty->disc_data and - * frees the memory that ppp_asynctty_receive is using. The best - * way to fix this is to use a rwlock in the tty struct, but for now - * we use a single global rwlock for all ttys in ppp line discipline. - * - * FIXME: this is no longer true. The _close path for the ldisc is - * now guaranteed to be sane. - */ -static DEFINE_RWLOCK(disc_data_lock); - -static struct asyncppp *ap_get(struct tty_struct *tty) -{ - struct asyncppp *ap; - - read_lock(&disc_data_lock); - ap = tty->disc_data; - if (ap != NULL) - refcount_inc(&ap->refcnt); - read_unlock(&disc_data_lock); - return ap; -} - -static void ap_put(struct asyncppp *ap) -{ - if (refcount_dec_and_test(&ap->refcnt)) - complete(&ap->dead); -} - /* * Called when a tty is put into PPP line discipline. Called in process * context. @@ -180,9 +146,6 @@ ppp_asynctty_open(struct tty_struct *tty) skb_queue_head_init(&ap->rqueue); tasklet_setup(&ap->tsk, ppp_async_process); - refcount_set(&ap->refcnt, 1); - init_completion(&ap->dead); - ap->chan.private = ap; ap->chan.ops = &async_ops; ap->chan.mtu = PPP_MRU; @@ -203,34 +166,18 @@ ppp_asynctty_open(struct tty_struct *tty) } /* - * Called when the tty is put into another line discipline - * or it hangs up. We have to wait for any cpu currently - * executing in any of the other ppp_asynctty_* routines to - * finish before we can call ppp_unregister_channel and free - * the asyncppp struct. This routine must be called from - * process context, not interrupt or softirq context. + * Called when the tty is put into another line discipline or it hangs up. + * This call is serialized against other ldisc functions. */ static void ppp_asynctty_close(struct tty_struct *tty) { - struct asyncppp *ap; + struct asyncppp *ap = tty->disc_data; - write_lock_irq(&disc_data_lock); - ap = tty->disc_data; - tty->disc_data = NULL; - write_unlock_irq(&disc_data_lock); if (!ap) return; - /* - * We have now ensured that nobody can start using ap from now - * on, but we have to wait for all existing users to finish. - * Note that ppp_unregister_channel ensures that no calls to - * our channel ops (i.e. ppp_async_send/ioctl) are in progress - * by the time it returns. - */ - if (!refcount_dec_and_test(&ap->refcnt)) - wait_for_completion(&ap->dead); + tty->disc_data = NULL; tasklet_kill(&ap->tsk); ppp_unregister_channel(&ap->chan); @@ -240,17 +187,6 @@ ppp_asynctty_close(struct tty_struct *tty) kfree(ap); } -/* - * Called on tty hangup in process context. - * - * Wait for I/O to driver to complete and unregister PPP channel. - * This is already done by the close routine, so just call that. - */ -static void ppp_asynctty_hangup(struct tty_struct *tty) -{ - ppp_asynctty_close(tty); -} - /* * Read does nothing - no data is ever available this way. * Pppd reads and writes packets via /dev/ppp instead. @@ -281,7 +217,7 @@ ppp_asynctty_write(struct tty_struct *tty, struct file *file, const u8 *buf, static int ppp_asynctty_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { - struct asyncppp *ap = ap_get(tty); + struct asyncppp *ap = tty->disc_data; int err, val; int __user *p = (int __user *)arg; @@ -322,7 +258,6 @@ ppp_asynctty_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) err = tty_mode_ioctl(tty, cmd, arg); } - ap_put(ap); return err; } @@ -331,7 +266,7 @@ static void ppp_asynctty_receive(struct tty_struct *tty, const u8 *buf, const u8 *cflags, size_t count) { - struct asyncppp *ap = ap_get(tty); + struct asyncppp *ap = tty->disc_data; unsigned long flags; if (!ap) @@ -341,21 +276,19 @@ ppp_asynctty_receive(struct tty_struct *tty, const u8 *buf, const u8 *cflags, spin_unlock_irqrestore(&ap->recv_lock, flags); if (!skb_queue_empty(&ap->rqueue)) tasklet_schedule(&ap->tsk); - ap_put(ap); tty_unthrottle(tty); } static void ppp_asynctty_wakeup(struct tty_struct *tty) { - struct asyncppp *ap = ap_get(tty); + struct asyncppp *ap = tty->disc_data; clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags); if (!ap) return; set_bit(XMIT_WAKEUP, &ap->xmit_flags); tasklet_schedule(&ap->tsk); - ap_put(ap); } @@ -365,7 +298,6 @@ static struct tty_ldisc_ops ppp_ldisc = { .name = "ppp", .open = ppp_asynctty_open, .close = ppp_asynctty_close, - .hangup = ppp_asynctty_hangup, .read = ppp_asynctty_read, .write = ppp_asynctty_write, .ioctl = ppp_asynctty_ioctl, From d8d4d1cf40d541a5d7cc3b15d57e42d0815c7d53 Mon Sep 17 00:00:00 2001 From: Qingfang Deng Date: Fri, 28 Aug 2026 15:32:37 +0800 Subject: [PATCH 0304/1198] ppp: ppp_synctty: simplify tty disc_data access Apply the same simplification as the preceding ppp_async change. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot+b503105c2410c3433459@syzkaller.appspotmail.com Closes: https://syzbot.org/bug?extid=b503105c2410c3433459 Signed-off-by: Qingfang Deng Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20260828073245.126804-2-qingfang.deng@linux.dev Signed-off-by: Jakub Kicinski --- drivers/net/ppp/ppp_synctty.c | 83 +++-------------------------------- 1 file changed, 7 insertions(+), 76 deletions(-) diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c index 0b1bd1635c39..f87d43faeeab 100644 --- a/drivers/net/ppp/ppp_synctty.c +++ b/drivers/net/ppp/ppp_synctty.c @@ -38,11 +38,9 @@ #include #include #include -#include #include #include #include -#include #include #include @@ -67,8 +65,6 @@ struct syncppp { struct tasklet_struct tsk; - refcount_t refcnt; - struct completion dead_cmp; struct ppp_channel chan; /* interface to generic ppp layer */ }; @@ -116,37 +112,6 @@ ppp_print_buffer (const char *name, const __u8 *buf, int count) * Routines implementing the synchronous PPP line discipline. */ -/* - * We have a potential race on dereferencing tty->disc_data, - * because the tty layer provides no locking at all - thus one - * cpu could be running ppp_synctty_receive while another - * calls ppp_synctty_close, which zeroes tty->disc_data and - * frees the memory that ppp_synctty_receive is using. The best - * way to fix this is to use a rwlock in the tty struct, but for now - * we use a single global rwlock for all ttys in ppp line discipline. - * - * FIXME: Fixed in tty_io nowadays. - */ -static DEFINE_RWLOCK(disc_data_lock); - -static struct syncppp *sp_get(struct tty_struct *tty) -{ - struct syncppp *ap; - - read_lock(&disc_data_lock); - ap = tty->disc_data; - if (ap != NULL) - refcount_inc(&ap->refcnt); - read_unlock(&disc_data_lock); - return ap; -} - -static void sp_put(struct syncppp *ap) -{ - if (refcount_dec_and_test(&ap->refcnt)) - complete(&ap->dead_cmp); -} - /* * Called when a tty is put into sync-PPP line discipline. */ @@ -177,9 +142,6 @@ ppp_sync_open(struct tty_struct *tty) skb_queue_head_init(&ap->rqueue); tasklet_setup(&ap->tsk, ppp_sync_process); - refcount_set(&ap->refcnt, 1); - init_completion(&ap->dead_cmp); - ap->chan.private = ap; ap->chan.ops = &sync_ops; ap->chan.mtu = PPP_MRU; @@ -201,34 +163,18 @@ ppp_sync_open(struct tty_struct *tty) } /* - * Called when the tty is put into another line discipline - * or it hangs up. We have to wait for any cpu currently - * executing in any of the other ppp_synctty_* routines to - * finish before we can call ppp_unregister_channel and free - * the syncppp struct. This routine must be called from - * process context, not interrupt or softirq context. + * Called when the tty is put into another line discipline or it hangs up. + * This call is serialized against other ldisc functions. */ static void ppp_sync_close(struct tty_struct *tty) { - struct syncppp *ap; + struct syncppp *ap = tty->disc_data; - write_lock_irq(&disc_data_lock); - ap = tty->disc_data; - tty->disc_data = NULL; - write_unlock_irq(&disc_data_lock); if (!ap) return; - /* - * We have now ensured that nobody can start using ap from now - * on, but we have to wait for all existing users to finish. - * Note that ppp_unregister_channel ensures that no calls to - * our channel ops (i.e. ppp_sync_send/ioctl) are in progress - * by the time it returns. - */ - if (!refcount_dec_and_test(&ap->refcnt)) - wait_for_completion(&ap->dead_cmp); + tty->disc_data = NULL; tasklet_kill(&ap->tsk); ppp_unregister_channel(&ap->chan); @@ -237,17 +183,6 @@ ppp_sync_close(struct tty_struct *tty) kfree(ap); } -/* - * Called on tty hangup in process context. - * - * Wait for I/O to driver to complete and unregister PPP channel. - * This is already done by the close routine, so just call that. - */ -static void ppp_sync_hangup(struct tty_struct *tty) -{ - ppp_sync_close(tty); -} - /* * Read does nothing - no data is ever available this way. * Pppd reads and writes packets via /dev/ppp instead. @@ -273,7 +208,7 @@ ppp_sync_write(struct tty_struct *tty, struct file *file, const u8 *buf, static int ppp_synctty_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { - struct syncppp *ap = sp_get(tty); + struct syncppp *ap = tty->disc_data; int __user *p = (int __user *)arg; int err, val; @@ -314,7 +249,6 @@ ppp_synctty_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) break; } - sp_put(ap); return err; } @@ -323,7 +257,7 @@ static void ppp_sync_receive(struct tty_struct *tty, const u8 *buf, const u8 *cflags, size_t count) { - struct syncppp *ap = sp_get(tty); + struct syncppp *ap = tty->disc_data; unsigned long flags; if (!ap) @@ -333,21 +267,19 @@ ppp_sync_receive(struct tty_struct *tty, const u8 *buf, const u8 *cflags, spin_unlock_irqrestore(&ap->recv_lock, flags); if (!skb_queue_empty(&ap->rqueue)) tasklet_schedule(&ap->tsk); - sp_put(ap); tty_unthrottle(tty); } static void ppp_sync_wakeup(struct tty_struct *tty) { - struct syncppp *ap = sp_get(tty); + struct syncppp *ap = tty->disc_data; clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags); if (!ap) return; set_bit(XMIT_WAKEUP, &ap->xmit_flags); tasklet_schedule(&ap->tsk); - sp_put(ap); } @@ -357,7 +289,6 @@ static struct tty_ldisc_ops ppp_sync_ldisc = { .name = "pppsync", .open = ppp_sync_open, .close = ppp_sync_close, - .hangup = ppp_sync_hangup, .read = ppp_sync_read, .write = ppp_sync_write, .ioctl = ppp_synctty_ioctl, From 4825ef699cda4c6f2f0586b17a5e225560481da6 Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Sun, 16 Aug 2026 17:04:41 +0800 Subject: [PATCH 0305/1198] klp-build: Fix wrong index in funcs cleanup error path In the object allocation loop, when kzalloc() for funcs fails, the cleanup loop uses `objs[i].funcs` instead of `objs[j].funcs`. Since `objs[i].funcs` is still NULL at that point, it repeatedly calls kfree(NULL) and leaks all previously allocated funcs arrays. Fixes: 59adee07b568 ("livepatch/klp-build: Add stub init code for livepatch modules") Signed-off-by: Yafang Shao Acked-by: Song Liu Reviewed-by: Petr Mladek Acked-by: Miroslav Benes Link: https://patch.msgid.link/20260816090442.18128-2-laoar.shao@gmail.com Signed-off-by: Josh Poimboeuf --- scripts/livepatch/init.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/livepatch/init.c b/scripts/livepatch/init.c index f14d8c8fb35f..16aff8f736eb 100644 --- a/scripts/livepatch/init.c +++ b/scripts/livepatch/init.c @@ -51,7 +51,7 @@ static int __init livepatch_mod_init(void) if (!funcs) { ret = -ENOMEM; for (int j = 0; j < i; j++) - kfree(objs[i].funcs); + kfree(objs[j].funcs); goto err_free_objs; } From 738ef4cd82818b13f492fd5ddec7e00f177ffe60 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 31 Aug 2026 08:04:37 -0700 Subject: [PATCH 0306/1198] uprobes: guard trace cleanup against error pointers Sashiko pointed out the some of the scope cleanups for free_uprobe could get an error pointer. Handle this case in free_uprobe to prevent a crash. On the other hand the macro doesn't need the guard because free_uprobe itself already does the check. Link: https://lore.kernel.org/all/20260831150651.1134594-2-ak@kernel.org/ Assisted-by: omp:gpt-5.6-luna sashiko Signed-off-by: Andi Kleen Signed-off-by: Masami Hiramatsu (Google) --- kernel/trace/trace_uprobe.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 861d857adadb..22cc3c8181b8 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -368,7 +368,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) static void free_trace_uprobe(struct trace_uprobe *tu) { - if (!tu) + if (IS_ERR_OR_NULL(tu)) return; path_put(&tu->path); @@ -533,7 +533,7 @@ static int register_trace_uprobe(struct trace_uprobe *tu) return ret; } -DEFINE_FREE(free_trace_uprobe, struct trace_uprobe *, if (_T) free_trace_uprobe(_T)) +DEFINE_FREE(free_trace_uprobe, struct trace_uprobe *, free_trace_uprobe(_T)) /* * Argument syntax: From ac323c9467092479dc1e5bc138c9abbe015b0069 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 28 Aug 2026 10:48:50 -0700 Subject: [PATCH 0307/1198] objtool/klp: Fix checksums for constant pool references Adding a line of code to __link_shadow_page() with a literal string causes a false positive changed function with GCC: arch/x86/kvm/kvm.ko.o: changed function: kvm_tdp_mmu_map_private_pfn While the patch only touched __link_shadow_page(), the string addition triggered a rename of .LC64 -> .LC65 in kvm_tdp_mmu_map_private_pfn() even though the underlying referenced constant data didn't change. So for .LC* symbols, the suffix is arbitrary but the data isn't. Add the underlying data to the checksum calculation rather than the symbol name. Clang also uses .LC* symbols, but also uses anonymous data. Both compilers put this data in .rodata.cst sections. Fixes: 0d83da43b1e1 ("objtool/klp: Add --checksum option to generate per-function checksums") Link: https://patch.msgid.link/f3a9e74ceebc6475ce94bcfe985401140857814a.1787939301.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf --- tools/objtool/klp-checksum.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/tools/objtool/klp-checksum.c b/tools/objtool/klp-checksum.c index b8e47f28997e..ebe25f9c5260 100644 --- a/tools/objtool/klp-checksum.c +++ b/tools/objtool/klp-checksum.c @@ -54,6 +54,19 @@ static int checksum_debug_init(struct objtool_file *file) return 0; } +/* + * Detect a reference to anonymous constant pool data which the compiler places + * in .rodata.cst and which either has an .LC symbol associated with + * it or (with Clang) no symbol at all. These are typically initializers for + * local function stack data, so they're considered part of the function rather + * than data per se. + */ +static bool is_anonymous_const_data(struct symbol *sym) +{ + return strstarts(sym->sec->name, ".rodata.cst") && + (is_sec_sym(sym) || strstarts(sym->name, ".LC")); +} + static void checksum_update_insn(struct objtool_file *file, struct symbol *func, struct instruction *insn) { @@ -129,6 +142,14 @@ static void checksum_update_insn(struct objtool_file *file, struct symbol *func, goto alts; } + if (is_anonymous_const_data(sym)) { + void *cst; + + cst = sym->sec->data->d_buf + sym->offset + offset; + __checksum_update_insn(func, insn, cst, sym->sec->sh.sh_entsize); + goto alts; + } + if (is_sec_sym(sym)) { sym = find_symbol_containing(reloc->sym->sec, offset); if (!sym) From 93b49239840b91313adbd77b8b52993eff2d08c1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 28 Aug 2026 08:45:27 +0000 Subject: [PATCH 0308/1198] ipv6: mcast: fix RCU list diversion in ip6_mc_del1_src() When removing a source filter whose count reaches zero, ip6_mc_del1_src() unlinks psf from pmc->mca_sources. If the filter was previously active, the code moved psf directly into pmc->mca_tomb by updating psf->sf_next. Because pmc->mca_sources is traversed locklessly under RCU (e.g. by ipv6_chk_mcast_addr()), mutating psf->sf_next before a grace period elapses diverts concurrent readers to the tombstone list. Consequently, readers miss remaining active sources in pmc->mca_sources and improperly examine deleted tombstone entries. Fix this by allocating a new tombstone node for pmc->mca_tomb (as done in sf_setstate()) and retiring the original psf via kfree_rcu(). Fixes: 4b200e398953 ("mld: convert ip6_sf_list to RCU") Signed-off-by: Eric Dumazet Cc: Taehee Yoo Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/20260828084531.1826790-2-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv6/mcast.c | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index aaba4c2aae23..ec7fac511c8d 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -2351,14 +2351,18 @@ static int ip6_mc_del1_src(struct ifmcaddr6 *pmc, int sfmode, if (psf->sf_oldin && !(pmc->mca_flags & MAF_NOREPORT) && !mld_in_v1_mode(idev)) { - psf->sf_crcount = idev->mc_qrv; - rcu_assign_pointer(psf->sf_next, - mc_dereference(pmc->mca_tomb, idev)); - rcu_assign_pointer(pmc->mca_tomb, psf); - rv = 1; - } else { - kfree_rcu(psf, rcu); + struct ip6_sf_list *dpsf = kmalloc_obj(*dpsf); + + if (dpsf) { + *dpsf = *psf; + dpsf->sf_crcount = idev->mc_qrv; + rcu_assign_pointer(dpsf->sf_next, + mc_dereference(pmc->mca_tomb, idev)); + rcu_assign_pointer(pmc->mca_tomb, dpsf); + rv = 1; + } } + kfree_rcu(psf, rcu); } return rv; } From c073d1b070f171d206b19c98d71739a97f15b3f1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 28 Aug 2026 08:45:28 +0000 Subject: [PATCH 0309/1198] ipv6: mcast: use copy-on-write RCU updates in ip6_mc_source() pmc->sflist is read locklessly under rcu_read_lock() by inet6_mc_check() during packet reception in the UDP and RAW multicast receive paths. ip6_mc_source() mutated psl->sl_addr and psl->sl_count in-place when adding or removing a source filter. Additionally, when expanding the filter buffer, newpsl was published via rcu_assign_pointer() before writing the new source into the array. Because 16-byte struct in6_addr writes are not atomic and array shifting is not synchronized with RCU readers, concurrent readers in inet6_mc_check() could read torn IPv6 addresses or observe duplicated/missed source entries. Fix this by switching ip6_mc_source() to copy-on-write RCU updates: allocate and fully populate newpsl before publishing it via rcu_assign_pointer(), and reclaim the old filter via kfree_rcu(), matching ip6_mc_msfilter(). Also remove the now unused IP6_SFBLOCK macro. Fixes: 882ba1f73c06 ("mld: convert ipv6_mc_socklist->sflist to RCU") Signed-off-by: Eric Dumazet Cc: Taehee Yoo Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/20260828084531.1826790-3-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/net/if_inet6.h | 2 - net/ipv6/mcast.c | 98 ++++++++++++++++++++++++------------------ 2 files changed, 56 insertions(+), 44 deletions(-) diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 238ad3349456..795fb41b45f5 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -88,8 +88,6 @@ struct ip6_sf_socklist { struct in6_addr sl_addr[] __counted_by(sl_max); }; -#define IP6_SFBLOCK 10 /* allocate this many at once */ - struct ipv6_mc_socklist { struct in6_addr addr; int ifindex; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index ec7fac511c8d..66f5858e5fea 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -355,12 +355,12 @@ int ip6_mc_source(int add, int omode, struct sock *sk, { struct ipv6_pinfo *inet6 = inet6_sk(sk); struct in6_addr *source, *group; + struct ip6_sf_socklist *newpsl, *psl; struct net *net = sock_net(sk); struct ipv6_mc_socklist *pmc; - struct ip6_sf_socklist *psl; struct inet6_dev *idev; int leavegroup = 0; - int i, j, rv; + int i, j; int err; source = &((struct sockaddr_in6 *)&pgsr->gsr_source)->sin6_addr; @@ -409,13 +409,11 @@ int ip6_mc_source(int add, int omode, struct sock *sk, if (!add) { if (!psl) goto done; /* err = -EADDRNOTAVAIL */ - rv = !0; for (i = 0; i < psl->sl_count; i++) { - rv = !ipv6_addr_equal(&psl->sl_addr[i], source); - if (rv == 0) + if (ipv6_addr_equal(&psl->sl_addr[i], source)) break; } - if (rv) /* source not found */ + if (i == psl->sl_count) /* source not found */ goto done; /* err = -EADDRNOTAVAIL */ /* special case - (INCLUDE, empty) == LEAVE_GROUP */ @@ -424,58 +422,74 @@ int ip6_mc_source(int add, int omode, struct sock *sk, goto done; } + atomic_sub(struct_size(psl, sl_addr, psl->sl_max), + &sk->sk_omem_alloc); + + if (psl->sl_count == 1) { + newpsl = NULL; + } else { + newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, + psl->sl_count - 1), + GFP_KERNEL); + if (!newpsl) { + atomic_add(struct_size(psl, sl_addr, psl->sl_max), + &sk->sk_omem_alloc); + err = -ENOBUFS; + goto done; + } + newpsl->sl_max = psl->sl_count - 1; + newpsl->sl_count = psl->sl_count - 1; + for (j = 0; j < i; j++) + newpsl->sl_addr[j] = psl->sl_addr[j]; + for (j = i + 1; j < psl->sl_count; j++) + newpsl->sl_addr[j - 1] = psl->sl_addr[j]; + } + /* update the interface filter */ ip6_mc_del_src(idev, group, omode, 1, source, 1); - for (j = i+1; j < psl->sl_count; j++) - psl->sl_addr[j-1] = psl->sl_addr[j]; - psl->sl_count--; + rcu_assign_pointer(pmc->sflist, newpsl); + kfree_rcu(psl, rcu); err = 0; goto done; } /* else, add a new source to the filter */ - if (psl && psl->sl_count >= sysctl_mld_max_msf) { + if (psl && psl->sl_count >= READ_ONCE(sysctl_mld_max_msf)) { err = -ENOBUFS; goto done; } - if (!psl || psl->sl_count == psl->sl_max) { - struct ip6_sf_socklist *newpsl; - int count = IP6_SFBLOCK; + if (psl) { + for (i = 0; i < psl->sl_count; i++) { + if (ipv6_addr_equal(&psl->sl_addr[i], source)) + goto done; /* err = -EADDRNOTAVAIL */ + } + } - if (psl) - count += psl->sl_max; - newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, count), - GFP_KERNEL); - if (!newpsl) { - err = -ENOBUFS; - goto done; - } - newpsl->sl_max = count; - newpsl->sl_count = count - IP6_SFBLOCK; - if (psl) { - for (i = 0; i < psl->sl_count; i++) - newpsl->sl_addr[i] = psl->sl_addr[i]; - atomic_sub(struct_size(psl, sl_addr, psl->sl_max), - &sk->sk_omem_alloc); - } - rcu_assign_pointer(pmc->sflist, newpsl); - kfree_rcu(psl, rcu); - psl = newpsl; + i = psl ? psl->sl_count + 1 : 1; + newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, i), + GFP_KERNEL); + if (!newpsl) { + err = -ENOBUFS; + goto done; } - rv = 1; /* > 0 for insert logic below if sl_count is 0 */ - for (i = 0; i < psl->sl_count; i++) { - rv = !ipv6_addr_equal(&psl->sl_addr[i], source); - if (rv == 0) /* There is an error in the address. */ - goto done; + newpsl->sl_max = i; + newpsl->sl_count = i; + if (psl) { + for (j = 0; j < psl->sl_count; j++) + newpsl->sl_addr[j] = psl->sl_addr[j]; } - for (j = psl->sl_count-1; j >= i; j--) - psl->sl_addr[j+1] = psl->sl_addr[j]; - psl->sl_addr[i] = *source; - psl->sl_count++; - err = 0; + newpsl->sl_addr[i - 1] = *source; + /* update the interface list */ ip6_mc_add_src(idev, group, omode, 1, source, 1); + + if (psl) + atomic_sub(struct_size(psl, sl_addr, psl->sl_max), + &sk->sk_omem_alloc); + rcu_assign_pointer(pmc->sflist, newpsl); + kfree_rcu(psl, rcu); + err = 0; done: mutex_unlock(&idev->mc_lock); in6_dev_put(idev); From 75fa9caeb8aaba19c2463dee0b0a1e09d39c04af Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 28 Aug 2026 08:45:29 +0000 Subject: [PATCH 0310/1198] ipv6: mcast: fix delay calculation in igmp6_join_group() When joining a multicast group, if a report work is already pending (e.g. scheduled by a query or a previous join), igmp6_join_group() cancels the delayed work and recalculates the delay: if (cancel_delayed_work(&ma->mca_work)) { refcount_dec(&ma->mca_refcnt); delay = ma->mca_work.timer.expires - jiffies; } Unlike igmp6_group_queried(), igmp6_join_group() did not check if delay >= interval. This leads to two issues: 1. If the timer has already expired (timer.expires <= jiffies), the stale expiry is reused by mod_delayed_work(), causing the second unsolicited report to fire on the very next tick without a randomized delay. 2. If the timer was originally armed by a query with a large maximum response delay, delay could exceed unsolicited_report_interval(ma->idev). Fix this by initializing delay to unsolicited_report_interval(ma->idev) and re-randomizing it with get_random_u32_below(interval) when delay >= interval, mirroring the logic in igmp6_group_queried(). Fixes: 2d9a93b4902b ("mld: convert from timer to delayed work") Signed-off-by: Eric Dumazet Cc: Taehee Yoo Reviewed-by: Ido Schimmel Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Link: https://patch.msgid.link/20260828084531.1826790-4-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv6/mcast.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 66f5858e5fea..4423b90dc9ab 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -2639,7 +2639,7 @@ static void ip6_mc_clear_src(struct ifmcaddr6 *pmc) static void igmp6_join_group(struct ifmcaddr6 *ma) { - unsigned long delay; + unsigned long delay, interval; mc_assert_locked(ma->idev); @@ -2648,13 +2648,17 @@ static void igmp6_join_group(struct ifmcaddr6 *ma) igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REPORT); - delay = get_random_u32_below(unsolicited_report_interval(ma->idev)); + interval = unsolicited_report_interval(ma->idev); + delay = interval; if (cancel_delayed_work(&ma->mca_work)) { refcount_dec(&ma->mca_refcnt); delay = ma->mca_work.timer.expires - jiffies; } + if (delay >= interval) + delay = get_random_u32_below(interval); + if (!mod_delayed_work(mld_wq, &ma->mca_work, delay)) refcount_inc(&ma->mca_refcnt); WRITE_ONCE(ma->mca_flags, ma->mca_flags | From 0c8f56c583c3250408367880c98e4d6fbc929315 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 28 Aug 2026 08:45:30 +0000 Subject: [PATCH 0311/1198] ipv6: mcast: use rcu_assign_pointer() for __rcu list updates Several places in net/ipv6/mcast.c update RCU-protected lists (np->ipv6_mc_list, idev->mc_list, idev->mc_tomb) using direct pointer assignments instead of rcu_assign_pointer(): 1. In __ipv6_dev_mc_dec(), unlinking a group from idev->mc_list did: *map = ma->next; without rcu_assign_pointer() while concurrent readers traverse idev->mc_list locklessly under rcu_read_lock(). 2. In ipv6_sock_mc_drop() and __ipv6_sock_mc_close(), unlinking a group from np->ipv6_mc_list directly assigned *lnk = mc_lst->next and np->ipv6_mc_list = mc_lst->next without rcu_assign_pointer(), racing with lockless readers in inet6_mc_check(). 3. In __ipv6_sock_mc_join(), mc_lst->next was initialized to np->ipv6_mc_list via raw assignment before publishing mc_lst. 4. In mld_del_delrec() and __ipv6_dev_mc_inc(), __rcu source pointers passed into rcu_assign_pointer() lacked explicit dereference helpers. Fix these by consistently using rcu_assign_pointer() along with mc_dereference() / sock_dereference(). Fixes: 456b61bca8ee ("ipv6: mcast: RCU conversion") Fixes: 88e2ca308094 ("mld: convert ifmcaddr6 to RCU") Signed-off-by: Eric Dumazet Cc: Taehee Yoo Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/20260828084531.1826790-5-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv6/mcast.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 4423b90dc9ab..2290457eb8d3 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -240,7 +240,8 @@ static int __ipv6_sock_mc_join(struct sock *sk, int ifindex, return err; } - mc_lst->next = np->ipv6_mc_list; + rcu_assign_pointer(mc_lst->next, + sock_dereference(np->ipv6_mc_list, sk)); rcu_assign_pointer(np->ipv6_mc_list, mc_lst); return 0; @@ -300,7 +301,8 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) lnk = &mc_lst->next) { if ((ifindex == 0 || mc_lst->ifindex == ifindex) && ipv6_addr_equal(&mc_lst->addr, addr)) { - *lnk = mc_lst->next; + rcu_assign_pointer(*lnk, + sock_dereference(mc_lst->next, sk)); __ipv6_sock_mc_drop(sk, mc_lst); return 0; } @@ -333,7 +335,8 @@ void __ipv6_sock_mc_close(struct sock *sk) struct ipv6_mc_socklist *mc_lst; while ((mc_lst = sock_dereference(np->ipv6_mc_list, sk)) != NULL) { - np->ipv6_mc_list = mc_lst->next; + rcu_assign_pointer(np->ipv6_mc_list, + sock_dereference(mc_lst->next, sk)); __ipv6_sock_mc_drop(sk, mc_lst); } } @@ -798,9 +801,11 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) if (!pmc) return; if (pmc_prev) - rcu_assign_pointer(pmc_prev->next, pmc->next); + rcu_assign_pointer(pmc_prev->next, + mc_dereference(pmc->next, idev)); else - rcu_assign_pointer(idev->mc_tomb, pmc->next); + rcu_assign_pointer(idev->mc_tomb, + mc_dereference(pmc->next, idev)); im->idev = pmc->idev; if (im->mca_sfmode == MCAST_INCLUDE) { @@ -980,7 +985,7 @@ static int __ipv6_dev_mc_inc(struct net_device *dev, return -ENOMEM; } - rcu_assign_pointer(mc->next, idev->mc_list); + rcu_assign_pointer(mc->next, mc_dereference(idev->mc_list, idev)); rcu_assign_pointer(idev->mc_list, mc); mld_del_delrec(idev, mc); @@ -1014,7 +1019,8 @@ int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr) WRITE_ONCE(ma->mca_users, new_users); if (new_users == 0) { - *map = ma->next; + rcu_assign_pointer(*map, + mc_dereference(ma->next, idev)); igmp6_group_dropped(ma); inet6_ifmcaddr_notify(idev->dev, ma, From b4cf4a092a7bdaa62acca39c28f386b6d1674968 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 28 Aug 2026 08:45:31 +0000 Subject: [PATCH 0312/1198] ipv6: mcast: use jiffies_delta_to_clock_t() in igmp6_mc_seq_show() If a multicast group timer has expired but the delayed work has not yet run to clear MAF_TIMER_RUNNING, expires - jiffies produces a negative value. Because unsigned arithmetic was used with jiffies_to_clock_t(), expires - jiffies underflows to a huge value and reports invalid timer durations in /proc/net/igmp6. Use jiffies_delta_to_clock_t() with a signed long delta to properly cap expired deltas to 0, matching IPv4 igmp_mc_seq_show() and commit a399a8053164 ("time: jiffies_delta_to_clock_t() helper to the rescue"). Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/20260828084531.1826790-6-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv6/mcast.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 2290457eb8d3..ecef55f26189 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -3029,7 +3029,7 @@ static int igmp6_mc_seq_show(struct seq_file *seq, void *v) struct ifmcaddr6 *im = (struct ifmcaddr6 *)v; struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); unsigned int mca_flags = READ_ONCE(im->mca_flags); - unsigned long expires = READ_ONCE(im->mca_work.timer.expires); + long delta = READ_ONCE(im->mca_work.timer.expires) - jiffies; seq_printf(seq, "%-4d %-15s %pi6 %5d %08X %ld\n", @@ -3037,7 +3037,7 @@ static int igmp6_mc_seq_show(struct seq_file *seq, void *v) &im->mca_addr, READ_ONCE(im->mca_users), mca_flags, (mca_flags & MAF_TIMER_RUNNING) ? - jiffies_to_clock_t(expires - jiffies) : 0); + jiffies_delta_to_clock_t(delta) : 0); return 0; } From 97cc84dad1d7f68a36b71b69b361d88482707673 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 28 Aug 2026 10:37:31 +0000 Subject: [PATCH 0313/1198] ip6_gre: check tunnel info before xmit in ip6gre_tunnel_xmit Shuangpeng Bai reported a KASAN slab-use-after-free in ip6gre_tunnel_xmit(). The precise KASAN bug was caused by ip6_tnl_xmit() consuming the skb during headroom expansion and returning an error, while ip6gre_tunnel_xmit() still held the stale pointer and called skb_tunnel_info_txcheck(skb) at tx_err. That specific bug was fixed by commit 87f21b59ddc6 ("ip6_tunnel: use skb_cow_head() in ip6_tnl_xmit()"). However, calling skb_tunnel_info_txcheck(skb) at the tx_err label after the transmission attempt remains problematic: Downstream helpers like ip6_tnl_xmit() call skb_scrub_packet(), which drops the skb's metadata_dst before transmission. If an error occurs later during transmit, inspecting skb at tx_err sees a scrubbed dst and misclassifies tx_errors vs tx_dropped. Commit e5f7e211b6aa ("ip6gre: avoid tx_error when sending MLD/DAD on external tunnels") already handled this correctly in ip6erspan_tunnel_xmit() by checking and caching tun_info before transmit. Align ip6gre_tunnel_xmit() with ip6erspan_tunnel_xmit() by caching tun_info before xmit and checking it at tx_err. Fixes: e5f7e211b6aa ("ip6gre: avoid tx_error when sending MLD/DAD on external tunnels") Reported-by: Shuangpeng Bai Closes: https://lore.kernel.org/netdev/20260819062224.3197349-1-shuangpeng.kernel@gmail.com/ Cc: Davide Caratti Signed-off-by: Eric Dumazet Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/20260828103731.1951815-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv6/ip6_gre.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 69c51f1a5bf0..8ebda0b6a78b 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -878,6 +878,7 @@ static int ip6gre_xmit_other(struct sk_buff *skb, struct net_device *dev) static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { + struct ip_tunnel_info *tun_info = NULL; struct ip6_tnl *t = netdev_priv(dev); __be16 payload_protocol; int ret; @@ -888,6 +889,9 @@ static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb, if (!ip6_tnl_xmit_ctl(t, &t->parms.laddr, &t->parms.raddr)) goto tx_err; + if (t->parms.collect_md) + tun_info = skb_tunnel_info_txcheck(skb); + payload_protocol = skb_protocol(skb, true); switch (payload_protocol) { case htons(ETH_P_IP): @@ -907,7 +911,7 @@ static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb, return NETDEV_TX_OK; tx_err: - if (!t->parms.collect_md || !IS_ERR(skb_tunnel_info_txcheck(skb))) + if (!IS_ERR(tun_info)) DEV_STATS_INC(dev, tx_errors); DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); From bdc46e507b59ac44c8e1dab505121f18c2add1ab Mon Sep 17 00:00:00 2001 From: Xiaofeng Yuan Date: Mon, 31 Aug 2026 19:11:22 -0600 Subject: [PATCH 0314/1198] riscv: mm: make EXECMEM_KPROBES writable without CONFIG_STRICT_MODULE_RWX When CONFIG_STRICT_MODULE_RWX is not set, execmem cannot create temporary writable mappings for read-only executable pages. In this case, the execmem ranges must already have writable permissions. Currently EXECMEM_KPROBES unconditionally uses PAGE_KERNEL_READ_EXEC, which causes kprobe instruction slot writes to trigger page faults on systems where CONFIG_STRICT_MODULE_RWX is not enabled. Fix this by using PAGE_KERNEL_EXEC when CONFIG_STRICT_MODULE_RWX is not available. Signed-off-by: Xiaofeng Yuan Tested-by: Lad Prabhakar Reviewed-by: Nam Cao Link: https://patch.msgid.link/20260814082742.148403-2-xiaofengmian@163.com Signed-off-by: Paul Walmsley --- arch/riscv/mm/init.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index f8994caefc70..fb37b0b67efe 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -1465,7 +1465,9 @@ struct execmem_info __init *execmem_arch_setup(void) [EXECMEM_KPROBES] = { .start = VMALLOC_START, .end = VMALLOC_END, - .pgprot = PAGE_KERNEL_READ_EXEC, + .pgprot = IS_ENABLED(CONFIG_STRICT_MODULE_RWX) ? + PAGE_KERNEL_READ_EXEC : + PAGE_KERNEL_EXEC, .alignment = 1, }, [EXECMEM_BPF] = { From 8718e5a3090bbfd759801d088b700aab21e8e989 Mon Sep 17 00:00:00 2001 From: Xiaofeng Yuan Date: Mon, 31 Aug 2026 19:11:23 -0600 Subject: [PATCH 0315/1198] riscv: patch: skip fixmap mapping when kernel text is already writable patch_map() always creates a temporary writable mapping via fixmap for kernel text addresses, even when CONFIG_STRICT_KERNEL_RWX is disabled and the kernel text is already mapped with _PAGE_WRITE. This is unnecessary overhead at best, and on minimal configurations it can cause page faults. Skip the fixmap path for kernel text when CONFIG_STRICT_KERNEL_RWX is not enabled, since the text pages are already writable in that case. The module text path is already gated on CONFIG_STRICT_MODULE_RWX and is kept unchanged. Reported-by: Klara Modin Closes: https://lore.kernel.org/all/ant_8TaBbov_GS4i@soda.int.kasm.eu/ Reported-by: Lad Prabhakar Closes: https://lore.kernel.org/all/CA+V-a8tQK8rih9SGGTyqrEBGpNkx4H0eX2YccCRrgkVAPr+EBg@mail.gmail.com/ Tested-by: Klara Modin Tested-by: Lad Prabhakar Link: https://patch.msgid.link/20260814082742.148403-3-xiaofengmian@163.com Signed-off-by: Paul Walmsley --- arch/riscv/kernel/patch.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c index 16b243376f36..2239c28981bc 100644 --- a/arch/riscv/kernel/patch.c +++ b/arch/riscv/kernel/patch.c @@ -45,6 +45,8 @@ static __always_inline void *patch_map(void *addr, const unsigned int fixmap) phys_addr_t phys; if (core_kernel_text(uintaddr) || is_kernel_exittext(uintaddr)) { + if (!IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)) + return addr; phys = __pa_symbol(addr); } else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) { struct page *page = vmalloc_to_page(addr); From 2d2184ac90365a4af3274e23c98d469f09f91749 Mon Sep 17 00:00:00 2001 From: Samuel Holland Date: Mon, 31 Aug 2026 19:11:23 -0600 Subject: [PATCH 0316/1198] Revert "riscv: Reset pmm when PR_TAGGED_ADDR_ENABLE is not set" This reverts commit 3033b2b1e3949274f33a140e2a97571b5a307298. The reverted patch is userspace-visible behavior change, not a bug fix. The two variables here (pmm and pmlen) control two independent features: pmm is the _hardware_ pointer masking mode that applies while executing in userspace. pmlen is the shift amount that the _kernel_ uses when untagging addresses; PMLEN_0 means no untagging occurs, so the kernel does not accept tagged addresses in syscall arguments. It is valid (as documented and tested by the self test) to enable pointer masking without enabling the tagged address ABI. This separation is necessary to allow userspace to create an execution environment similar to what the kernel supports on arm64 by default, where TBI is enabled but the tagged address ABI is not. (On arm64, there is no equivalent to PR_PMLEN_MASK because TBI is always enabled.) Signed-off-by: Samuel Holland Link: https://patch.msgid.link/20260820014551.1979772-1-samuel.holland@sifive.com Cc: stable@vger.kernel.org Fixes: 3033b2b1e394 ("riscv: Reset pmm when PR_TAGGED_ADDR_ENABLE is not set") Signed-off-by: Paul Walmsley --- arch/riscv/kernel/process.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index b2df7f72241a..7cc5a6a5c020 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -349,10 +349,8 @@ long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg) if (arg & PR_TAGGED_ADDR_ENABLE && (tagged_addr_disabled || !pmlen)) return -EINVAL; - if (!(arg & PR_TAGGED_ADDR_ENABLE)) { + if (!(arg & PR_TAGGED_ADDR_ENABLE)) pmlen = PMLEN_0; - pmm = ENVCFG_PMM_PMLEN_0; - } if (mmap_write_lock_killable(mm)) return -EINTR; From 12381af01024f4a59cd3f673fb3644bbe2ca3aad Mon Sep 17 00:00:00 2001 From: Dmitry Antipov Date: Mon, 31 Aug 2026 19:11:23 -0600 Subject: [PATCH 0317/1198] riscv: use string helper in setup_global_riscv_enable() Prefer the convenient string choice 'str_disabled_enabled()' helper over hardcoded strings in 'setup_global_riscv_enable()'. Signed-off-by: Dmitry Antipov Link: https://patch.msgid.link/20260819160546.3219942-1-dmantipov@yandex.ru Signed-off-by: Paul Walmsley --- arch/riscv/kernel/usercfi.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/riscv/kernel/usercfi.c b/arch/riscv/kernel/usercfi.c index f027e6e05251..dec0ba5eff5e 100644 --- a/arch/riscv/kernel/usercfi.c +++ b/arch/riscv/kernel/usercfi.c @@ -525,9 +525,8 @@ static int __init setup_global_riscv_enable(char *str) if (riscv_nousercfi) pr_info("RISC-V user CFI disabled via cmdline - shadow stack status : %s, landing pad status : %s\n", - (riscv_nousercfi & CMDLINE_DISABLE_RISCV_USERCFI_BCFI) ? "disabled" : - "enabled", (riscv_nousercfi & CMDLINE_DISABLE_RISCV_USERCFI_FCFI) ? - "disabled" : "enabled"); + str_disabled_enabled(riscv_nousercfi & CMDLINE_DISABLE_RISCV_USERCFI_BCFI), + str_disabled_enabled(riscv_nousercfi & CMDLINE_DISABLE_RISCV_USERCFI_FCFI)); return 1; } From d0fc6fab20460add1f27402cd8b945d094a56b21 Mon Sep 17 00:00:00 2001 From: Andy Chiu Date: Mon, 31 Aug 2026 19:11:23 -0600 Subject: [PATCH 0318/1198] riscv: hwprobe: initialize pair->value in hwprobe_one_pair() The vendor-extension handlers reached from hwprobe_one_pair() (hwprobe_isa_vendor_ext_thead_0() and friends) only OR the present bits into pair->value via VENDOR_EXTENSION_SUPPORTED() and clear their own missing bits; they assume the caller has already zeroed pair->value. That holds for hwprobe_get_values() (it zeroes each pair) and hwprobe_get_cpus() (it re-initializes its scratch pair per key), but not for complete_hwprobe_vdso_data(), which reuses a single pair across all keys without re-zeroing. A vendor key therefore inherits stale bits from the previously probed key, and the wrong value is cached in the vDSO all_cpu_hwprobe_values[] and handed to userspace on the fast patih. Zero pair->value once at the top of hwprobe_one_pair() so every handler starts from a clean value regardless of the caller, and drop the now redundant zeroing in the *_BLOCK_SIZE cases. hwprobe_isa_ext0() keeps its own zeroing because hwprobe_ext0_has() calls it directly, bypassing hwprobe_one_pair(). Fixes: a5ea53da65c5 ("riscv: hwprobe: Add thead vendor extension probing") Signed-off-by: Andy Chiu Reviewed-by: Jesse Taube Link: https://patch.msgid.link/20260725001614.2578617-2-tchiu@tenstorrent.com Cc: stable@vger.kernel.org Signed-off-by: Paul Walmsley --- arch/riscv/kernel/sys_hwprobe.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c index bd6ca7d769da..7818e1d32622 100644 --- a/arch/riscv/kernel/sys_hwprobe.c +++ b/arch/riscv/kernel/sys_hwprobe.c @@ -297,6 +297,8 @@ static u64 hwprobe_vec_misaligned(const struct cpumask *cpus) static void hwprobe_one_pair(struct riscv_hwprobe *pair, const struct cpumask *cpus) { + pair->value = 0; + switch (pair->key) { case RISCV_HWPROBE_KEY_MVENDORID: case RISCV_HWPROBE_KEY_MARCHID: @@ -331,17 +333,14 @@ static void hwprobe_one_pair(struct riscv_hwprobe *pair, break; case RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE: - pair->value = 0; if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOZ)) pair->value = riscv_cboz_block_size; break; case RISCV_HWPROBE_KEY_ZICBOM_BLOCK_SIZE: - pair->value = 0; if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOM)) pair->value = riscv_cbom_block_size; break; case RISCV_HWPROBE_KEY_ZICBOP_BLOCK_SIZE: - pair->value = 0; if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOP)) pair->value = riscv_cbop_block_size; break; From ddeaa39406c4cf680643412cd1f75bb98a641f6c Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Mon, 31 Aug 2026 19:11:23 -0600 Subject: [PATCH 0319/1198] riscv: bug: Make RV32 use GENERIC_BUG_RELATIVE_POINTERS x86 did this in commit b0a848f4a47a ("x86/bugs: Make i386 use GENERIC_BUG_RELATIVE_POINTERS") powerpc did this in commit 1baa1f70ef77 ("powerpc: Allow relative pointers in bug table entries") Similar as x86 and powerpc does, make RV32 use GENERIC_BUG_RELATIVE_POINTERS for "there is only one code path." and "less #ifdef is more better". Signed-off-by: Jisheng Zhang Link: https://patch.msgid.link/20260221024255.3552-1-jszhang@kernel.org Signed-off-by: Paul Walmsley --- arch/riscv/Kconfig | 2 +- arch/riscv/include/asm/bug.h | 5 ----- 2 files changed, 1 insertion(+), 6 deletions(-) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index f8e26c4bed2b..d6c2dbf8455c 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -326,7 +326,7 @@ config STACKTRACE_SUPPORT config GENERIC_BUG def_bool y depends on BUG - select GENERIC_BUG_RELATIVE_POINTERS if 64BIT + select GENERIC_BUG_RELATIVE_POINTERS config GENERIC_BUG_RELATIVE_POINTERS bool diff --git a/arch/riscv/include/asm/bug.h b/arch/riscv/include/asm/bug.h index 6f581b84d8fc..699c0cf3e4ef 100644 --- a/arch/riscv/include/asm/bug.h +++ b/arch/riscv/include/asm/bug.h @@ -29,13 +29,8 @@ typedef u32 bug_insn_t; -#ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS #define __BUG_ENTRY_ADDR RISCV_INT " 1b - ." #define __BUG_ENTRY_FILE(file) RISCV_INT " " file " - ." -#else -#define __BUG_ENTRY_ADDR RISCV_PTR " 1b" -#define __BUG_ENTRY_FILE(file) RISCV_PTR " " file -#endif #ifdef CONFIG_DEBUG_BUGVERBOSE #define __BUG_ENTRY(file, line, flags) \ From 6693171c8c540b3a54e671992f0561613076fc3b Mon Sep 17 00:00:00 2001 From: Xixin Liu Date: Tue, 18 Aug 2026 17:10:00 +0800 Subject: [PATCH 0320/1198] perf: RISC-V: use BIT_ULL for u64 overflow masks Overflow status and restart masks are u64, but bits were built with BIT(). On RV32 that is an unsigned long shift, so indices >= 32 truncate or wrap and corrupt the mask. Use BIT_ULL() for those u64 bitops. Fixes: a8625217a054 ("drivers/perf: riscv: Implement SBI PMU snapshot function") Assisted-by: DeepSeek:deepseek-v3 Signed-off-by: Xixin Liu Link: https://patch.msgid.link/prpmask01bitul.v2.1786434000.git.liuxixin@kylinos.cn Cc: stable@vger.kernel.org [pjw@kernel.org: updated to apply] Signed-off-by: Paul Walmsley --- drivers/perf/riscv_pmu_sbi.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 50220f7b46d9..8ea5ae617347 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -1002,7 +1002,7 @@ static inline void pmu_sbi_start_ovf_ctrs_snapshot(struct cpu_hw_events *cpu_hw_ struct riscv_pmu_snapshot_data *sdata = cpu_hw_evt->snapshot_addr; for_each_set_bit(idx, cpu_hw_evt->used_hw_ctrs, RISCV_MAX_COUNTERS) { - if (ctr_ovf_mask & BIT(idx)) { + if (ctr_ovf_mask & BIT_ULL(idx)) { event = cpu_hw_evt->events[idx]; hwc = &event->hw; max_period = riscv_pmu_ctr_get_width_mask(event); @@ -1109,14 +1109,14 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev) hidx = info->csr - CSR_CYCLE; /* check if the corresponding bit is set in scountovf or overflow mask in shmem */ - if (!(overflow & BIT(hidx))) + if (!(overflow & BIT_ULL(hidx))) continue; /* * Keep a track of overflowed counters so that they can be started * with updated initial value. */ - overflowed_ctrs |= BIT(lidx); + overflowed_ctrs |= BIT_ULL(lidx); hw_evt = &event->hw; /* Update the event states here so that we know the state while reading */ hw_evt->state |= PERF_HES_STOPPED; From cd51b74bdd0b75aedf255dc67306a16dd057f7ee Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Fri, 28 Aug 2026 22:23:41 +0300 Subject: [PATCH 0321/1198] ipv6: Fix redirect exception creation for UDP/RAW sockets When an ICMP Redirect Message is matched to a socket, both IPv4 and IPv6 verify that the source IP of the ICMP packet is the current gateway for the quoted packet. Both also pass the socket's bound device as the expected nexthop device. The difference is that IPv4 treats "oif=0" as "any", whereas IPv6 always requires an exact match (see ip6_redirect_nh_match()), since the gateway address is usually a link-local address. Therefore, when an IPv6 UDP/RAW socket is not bound to a device, the above verification fails and an exception is not created. This also happens when the socket is bound to a VRF, as l3mdev_update_flow() resets the oif to 0. Fix this by passing the ifindex of the ingress device as the expected nexthop device. This is consistent with the existing callers of ip6_redirect(). Note that for ICMPv6 Redirect Message packets the VRF driver does not reset skb->dev to the VRF device, so skb->dev is correct, even when it is a VRF port. Fixes: b55b76b22144 ("ipv6:introduce function to find route for redirect") Cc: stable@vger.kernel.org Reviewed-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: Ido Schimmel Link: https://patch.msgid.link/20260828192344.2596928-2-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- net/ipv6/route.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 6a40c5074543..9658939511e0 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3255,7 +3255,7 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif) void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk) { - ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, + ip6_redirect(skb, sock_net(sk), skb->dev->ifindex, READ_ONCE(sk->sk_mark), sk_uid(sk)); } From 4c3499f79f8c7e8561266bcc220a18538cec0458 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Fri, 28 Aug 2026 22:23:42 +0300 Subject: [PATCH 0322/1198] ipv4: udp: Create exceptions before socket matching Currently, when ICMP Fragmentation Needed and Redirect Message packets are locally delivered and quote a UDP packet, a FIB nexthop exception (FNHE) is only created if the kernel can match the UDP packet to an existing socket. This behavior allows off-path attackers to conduct a side-channel attack on the FNHE cache in order to discover the ephemeral port used by a connected UDP socket. Commit 6457378fe796 ("ipv4: use siphash instead of Jenkins in fnhe_hashfun()") and commit 67d6d681e15b ("ipv4: make exception cache less predictible") tried to mitigate such attacks by making it harder for attackers to discover hash collisions in the FNHE cache and by randomizing the number of exceptions a hash bucket can hold, respectively. Unfortunately, both of the mitigations can be bypassed. Instead, mitigate such attacks by always creating a FNHE, even before trying to find a matching socket. Do that by calling ipv4_update_pmtu() and ipv4_redirect(), the helpers used when the quoted packet did not originate from a socket. This means that guesses (right or wrong) from an off-path attacker will always result in a FNHE being created or updated in the cache that the attacker can observe. Pass an oif of 0, in a similar fashion to icmp_err(). This is also the oif used by the socket path for sockets that are not bound to a device. Note that this does not allow attackers to create FNHEs that they could not create before, as both helpers can already be reached with little to no validation. For example, by sending an ICMP error that quotes an ICMP Echo Reply or one that quotes a UDP source port that matches a wildcard socket. Also note that in the good case (matched socket) the above scheme comes at the cost of an extra route lookup, as the no socket helpers perform their own lookup before the one performed by ipv4_sk_update_pmtu() / ipv4_sk_redirect(). When the two resolve to different nexthops, it also results in two exceptions being created for the same destination IP. One in the FNHE cache of the nexthop resolved by the no socket helpers and another in the FNHE cache of the nexthop used by the socket. Fixes: 4895c771c7f0 ("ipv4: Add FIB nexthop exceptions.") Cc: stable@vger.kernel.org Reported-by: Amit Klein Reported-by: Noam Caspi Signed-off-by: Ido Schimmel Reviewed-by: David Ahern Link: https://patch.msgid.link/20260828192344.2596928-3-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- net/ipv4/udp.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 6ff5670bf6ed..bb8cfc62cb00 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -900,6 +900,15 @@ static struct sock *__udp4_lib_err_encap(struct net *net, return sk; } +static void udp_err_update_exception(struct net *net, struct sk_buff *skb, + int type, int code, u32 info) +{ + if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) + ipv4_update_pmtu(skb, net, info, 0, IPPROTO_UDP); + else if (type == ICMP_REDIRECT) + ipv4_redirect(skb, net, 0, IPPROTO_UDP); +} + /* * This routine is called by the ICMP module when it gets some * sort of error condition. If err < 0 then the socket should @@ -923,6 +932,8 @@ int udp_err(struct sk_buff *skb, u32 info) int harderr; int err; + udp_err_update_exception(net, skb, type, code, info); + uh = (struct udphdr *)(skb->data + (iph->ihl << 2)); sk = __udp4_lib_lookup(net, iph->daddr, uh->dest, iph->saddr, uh->source, skb->dev->ifindex, From ac76cab50e899a7346408b8d3c3a4192c2eefb9f Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Fri, 28 Aug 2026 22:23:43 +0300 Subject: [PATCH 0323/1198] ipv6: udp: Create exceptions before socket matching Currently, when ICMPv6 Packet Too Big and Redirect Message packets are locally delivered and quote a UDP packet, an exception is only created in the IPv6 exception cache if the kernel can match the UDP packet to an existing socket. This behavior allows off-path attackers to conduct a side-channel attack on the exception cache in order to discover the ephemeral port used by a connected UDP socket. Commit 4785305c05b2 ("ipv6: use siphash in rt6_exception_hash()") and commit a00df2caffed ("ipv6: make exception cache less predictible") tried to mitigate such attacks by making it harder for attackers to discover hash collisions in the exception cache and by randomizing the number of exceptions a hash bucket can hold, respectively. Unfortunately, both of the mitigations can be bypassed. Instead, mitigate such attacks by always creating an exception, even before trying to find a matching socket. Do that by calling ip6_update_pmtu() and ip6_redirect(), the helpers used when the quoted packet did not originate from a socket. This means that guesses (right or wrong) from an off-path attacker will always result in an exception being created or updated in the cache that the attacker can observe. Pass the ifindex of the ingress device and the default uid, in a similar fashion to icmpv6_err(). Unlike IPv4, an oif of 0 would not match any nexthop in ip6_redirect_nh_match() and no exception would be created in response to a Redirect Message. Note that this does not allow attackers to create exceptions that they could not create before, as both helpers can already be reached with little to no validation. For example, by sending an ICMPv6 error that quotes an ICMPv6 Echo Reply or one that quotes a UDP source port that matches a wildcard socket. Also note that in the good case (matched socket) the above scheme comes at the cost of an extra route lookup, as the no socket helpers perform their own lookup before the one performed by ip6_sk_update_pmtu() / ip6_sk_redirect(). When the two resolve to different nexthops, it also results in two exceptions being created for the same destination IP. One in the exception cache of the nexthop resolved by the no socket helpers and another in the exception cache of the nexthop used by the socket. Fixes: 2b760fcf5cfb ("ipv6: hook up exception table to store dst cache") Cc: stable@vger.kernel.org Reported-by: Amit Klein Reported-by: Noam Caspi Signed-off-by: Ido Schimmel Reviewed-by: David Ahern Link: https://patch.msgid.link/20260828192344.2596928-4-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- net/ipv6/udp.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index fd875908ac0c..93478d1ad576 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -690,6 +690,17 @@ static struct sock *__udp6_lib_err_encap(struct net *net, return sk; } +static void udpv6_err_update_exception(struct net *net, struct sk_buff *skb, + u8 type, __be32 info) +{ + if (type == ICMPV6_PKT_TOOBIG) + ip6_update_pmtu(skb, net, info, skb->dev->ifindex, 0, + sock_net_uid(net, NULL)); + else if (type == NDISC_REDIRECT) + ip6_redirect(skb, net, skb->dev->ifindex, 0, + sock_net_uid(net, NULL)); +} + static int udpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { @@ -703,6 +714,8 @@ static int udpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, int harderr; int err; + udpv6_err_update_exception(net, skb, type, info); + daddr = seg6_get_daddr(skb, opt) ? : &hdr->daddr; saddr = &hdr->saddr; sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source, From c923c14942b164cfc2c1efa4e6324214f2fc248a Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Fri, 28 Aug 2026 22:23:44 +0300 Subject: [PATCH 0324/1198] selftests: net: Add exception cache tests Add a test for the IPv4 and IPv6 exception caches, covering the exceptions that are created in response to ICMP errors quoting a UDP packet. The topology consists of a host (h1) that reaches a remote host (h2) via a router (r1), with a second router (r2) attached to the segment shared by h1 and r1. UDP packets are injected using a packet socket, so that an ICMP error quoting them is only matched to a socket when one was opened separately with the same source port. PMTU errors are provoked by lowering the MTU of the far end of the path and redirects by pointing r1's route towards h2 back over the segment it received the packet from. The following is tested for both address families and for both PMTU and redirect exceptions: * An error that is not matched to a socket creates an exception that carries the new MTU or gateway. * An error that is matched to a socket creates the same exception. The PMTU tests further verify that a lower PMTU replaces the one stored in the exception whereas a higher one does not, and that a socket which disabled PMTU discovery using IP{,V6}_PMTUDISC_OMIT gets the same exception as the other cases. Without "ipv4: udp: Create exceptions before socket matching" and "ipv6: udp: Create exceptions before socket matching", the tests that do not open a socket fail: # ./exception_cache.sh TEST: IPv4: PMTU: exception without a matching socket [FAIL] No socket: exception does not carry an MTU of 1400 TEST: IPv6: PMTU: exception without a matching socket [FAIL] No socket: exception does not carry an MTU of 1400 TEST: IPv4: PMTU: exception with a matching socket [ OK ] TEST: IPv6: PMTU: exception with a matching socket [ OK ] TEST: IPv4: PMTU: exception with a socket ignoring it [FAIL] PMTU discovery disabled: exception does not carry an MTU of 1400 TEST: IPv6: PMTU: exception with a socket ignoring it [FAIL] PMTU discovery disabled: exception does not carry an MTU of 1400 TEST: IPv4: Redirect: exception without a matching socket [FAIL] No socket: exception does not carry the new gateway TEST: IPv6: Redirect: exception without a matching socket [FAIL] No socket: exception does not carry the new gateway TEST: IPv4: Redirect: exception with a matching socket [ OK ] TEST: IPv6: Redirect: exception with a matching socket [ OK ] Signed-off-by: Ido Schimmel Link: https://patch.msgid.link/20260828192344.2596928-5-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/Makefile | 1 + .../testing/selftests/net/exception_cache.sh | 521 ++++++++++++++++++ 2 files changed, 522 insertions(+) create mode 100755 tools/testing/selftests/net/exception_cache.sh diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 0f5c178bc224..517c09d60bef 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -28,6 +28,7 @@ TEST_PROGS := \ double_udp_encap.sh \ drop_monitor_tests.sh \ ecmp_rehash.sh \ + exception_cache.sh \ fcnal-ipv4.sh \ fcnal-ipv6.sh \ fcnal-other.sh \ diff --git a/tools/testing/selftests/net/exception_cache.sh b/tools/testing/selftests/net/exception_cache.sh new file mode 100755 index 000000000000..8d3eed5c532a --- /dev/null +++ b/tools/testing/selftests/net/exception_cache.sh @@ -0,0 +1,521 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test that the state of the route exception cache after an ICMP error is +# processed does not depend on whether the quoted packet was matched to a +# socket. Otherwise, an off-path attacker can probe the cache to discover the +# ephemeral port used by a connected UDP socket. +# +# When the quoted packet is not matched to a socket, the same exception is +# created as when it is matched, so that neither its presence nor its contents +# reveal the result of socket matching. +# +# +----+ +# +---------| r1 | +# | +----+ +# +----+ +--------+ | .1 +# | h1 |---| bridge | | 198.51.100.0/30 +# +----+ +--------+ | 2001:db8:2::/64 +# .1 | | .2 +# | +----+ +----+ +# +---------| r2 |-----------| h2 | +# .2 .3 +----+ .1 .2 +----+ +# 203.0.113.0/24 +# 2001:db8:3::/64 +# 192.0.2.0/24 +# 2001:db8:1::/64 +# +# Traffic from h1 to h2 is routed via r1, which reaches h2's network via r2 +# over the point-to-point link. The MTU of the r2 - h2 link is lowered so that +# r2 emits ICMP errors towards h1. +# +# For the redirect tests r1's route to h2's network is replaced with one via r2 +# on the shared segment, so that r1 forwards the packet back to the segment it +# arrived from and emits a redirect towards h1. +# +# The packets that provoke the ICMP errors are injected with a packet socket so +# that no socket is ever associated with them. A socket is created separately, +# with socat, when a test needs the ICMP error to be matched. + +# shellcheck disable=SC1091,SC2034,SC2154,SC2329 +source lib.sh + +require_command jq +require_command mausezahn +require_command nstat +require_command socat + +ALL_TESTS=" + pmtu_no_socket_ipv4 + pmtu_no_socket_ipv6 + pmtu_socket_ipv4 + pmtu_socket_ipv6 + pmtu_omit_ipv4 + pmtu_omit_ipv6 + redirect_no_socket_ipv4 + redirect_no_socket_ipv6 + redirect_socket_ipv4 + redirect_socket_ipv6 +" + +# Shared segment. +H1_ADDR4=192.0.2.1 +R1_ADDR4=192.0.2.2 +R2_ADDR4=192.0.2.3 +H1_ADDR6=2001:db8:1::1 +R1_ADDR6=2001:db8:1::2 +R2_ADDR6=2001:db8:1::3 + +# r1 - r2 link. +R2_R1_ADDR4=198.51.100.2 +R2_R1_ADDR6=2001:db8:2::2 + +# r2 - h2 link. +H2_ADDR4=203.0.113.2 +H2_NET4=203.0.113.0/24 +H2_ADDR6=2001:db8:3::2 +H2_NET6=2001:db8:3::/64 + +SPORT=12345 +DPORT=54321 + +# The MTU of the shared segment and of the r1 - r2 link. Large enough for the +# injected packets to reach r2 intact. +SEGMENT_MTU=2000 +# Size of the injected packets. The PMTU tests need a size that exceeds every +# MTU used for the r2 - h2 link, so that r2 responds with an ICMP error. The +# redirect tests need a size that does not, otherwise r2 would respond with an +# ICMP error in addition to the redirect emitted by r1. +PMTU_PACKET_SIZE=1800 +REDIRECT_PACKET_SIZE=100 + +# The MTUs used for the r2 - h2 link. All of them must be at least +# IPV6_MIN_MTU, otherwise IPv6 silently ignores the error instead of creating +# an exception. +MTU_MID=1400 +MTU_LOW=1300 + +# Values for the IP{,V6}_MTU_DISCOVER socket option. +PMTUDISC_DONT=0 +PMTUDISC_OMIT=5 + +SOCAT_PID= + +linklocal_get() +{ + local ns=$1; shift + local dev=$1; shift + + ip -n "$ns" -j -6 addr show dev "$dev" | \ + jq -r '.[]["addr_info"][] | select(.scope == "link") | .local' +} + +linklocal_exists() +{ + local ns=$1; shift + local dev=$1; shift + + [ -n "$(linklocal_get "$ns" "$dev")" ] +} + +family_vars_set() +{ + local family=$1; shift + + FAMILY=$family + + if [ "$family" -eq 4 ]; then + H1_ADDR=$H1_ADDR4 + H2_ADDR=$H2_ADDR4 + MZ_FAMILY_OPT=() + # Without the Don't Fragment bit set r2 fragments the packet + # instead of reporting the MTU of the next hop. + MZ_IP_OPTS="df," + SOCAT_DST="UDP4-CONNECT:$H2_ADDR4:$DPORT" + SOCAT_BIND="bind=$H1_ADDR4:$SPORT" + SOCAT_PMTUDISC="ip-mtu-discover" + else + H1_ADDR=$H1_ADDR6 + H2_ADDR=$H2_ADDR6 + MZ_FAMILY_OPT=(-6) + MZ_IP_OPTS= + SOCAT_DST="UDP6-CONNECT:[$H2_ADDR6]:$DPORT" + SOCAT_BIND="bind=[$H1_ADDR6]:$SPORT" + SOCAT_PMTUDISC="ipv6-mtu-discover" + fi +} + +topology_setup() +{ + local ns + + setup_ns h1 r1 r2 h2 sw + defer cleanup_all_ns + + # Link-local addresses are generated from the MAC address and read + # back during setup, so request that generation mode explicitly and + # make the addresses available as soon as the devices are brought up. + for ns in "$h1" "$r1" "$r2" "$h2" "$sw"; do + ip netns exec "$ns" sysctl -qw \ + net.ipv6.conf.default.addr_gen_mode=0 \ + net.ipv6.conf.default.accept_dad=0 \ + net.ipv6.conf.all.accept_dad=0 + done + + ip -n "$sw" link add name br0 type bridge + ip -n "$sw" link set dev br0 mtu "$SEGMENT_MTU" up + + ip -n "$h1" link add name eth0 mtu "$SEGMENT_MTU" type veth \ + peer name swp1 mtu "$SEGMENT_MTU" netns "$sw" + ip -n "$r1" link add name eth0 mtu "$SEGMENT_MTU" type veth \ + peer name swp2 mtu "$SEGMENT_MTU" netns "$sw" + ip -n "$r2" link add name eth0 mtu "$SEGMENT_MTU" type veth \ + peer name swp3 mtu "$SEGMENT_MTU" netns "$sw" + ip -n "$r1" link add name eth1 mtu "$SEGMENT_MTU" type veth \ + peer name eth1 mtu "$SEGMENT_MTU" netns "$r2" + ip -n "$r2" link add name eth2 type veth peer name eth0 netns "$h2" + + ip -n "$sw" link set dev swp1 master br0 up + ip -n "$sw" link set dev swp2 master br0 up + ip -n "$sw" link set dev swp3 master br0 up + + ip -n "$h1" link set dev eth0 up + ip -n "$r1" link set dev eth0 up + ip -n "$r1" link set dev eth1 up + ip -n "$r2" link set dev eth0 up + ip -n "$r2" link set dev eth1 up + ip -n "$r2" link set dev eth2 up + ip -n "$h2" link set dev eth0 up + + ip -n "$h1" address add "$H1_ADDR4/24" dev eth0 + ip -n "$r1" address add "$R1_ADDR4/24" dev eth0 + ip -n "$r2" address add "$R2_ADDR4/24" dev eth0 + ip -n "$r1" address add 198.51.100.1/30 dev eth1 + ip -n "$r2" address add "$R2_R1_ADDR4/30" dev eth1 + ip -n "$r2" address add 203.0.113.1/24 dev eth2 + ip -n "$h2" address add "$H2_ADDR4/24" dev eth0 + + ip -n "$h1" -6 address add "$H1_ADDR6/64" dev eth0 nodad + ip -n "$r1" -6 address add "$R1_ADDR6/64" dev eth0 nodad + ip -n "$r2" -6 address add "$R2_ADDR6/64" dev eth0 nodad + ip -n "$r1" -6 address add 2001:db8:2::1/64 dev eth1 nodad + ip -n "$r2" -6 address add "$R2_R1_ADDR6/64" dev eth1 nodad + ip -n "$r2" -6 address add 2001:db8:3::1/64 dev eth2 nodad + ip -n "$h2" -6 address add "$H2_ADDR6/64" dev eth0 nodad + + ip netns exec "$r1" sysctl -qw net.ipv4.ip_forward=1 + ip netns exec "$r1" sysctl -qw net.ipv4.conf.all.send_redirects=1 + ip netns exec "$r1" sysctl -qw net.ipv6.conf.all.forwarding=1 + ip netns exec "$r2" sysctl -qw net.ipv4.ip_forward=1 + ip netns exec "$r2" sysctl -qw net.ipv6.conf.all.forwarding=1 + + ip netns exec "$h1" sysctl -qw net.ipv4.conf.all.accept_redirects=1 + ip netns exec "$h1" sysctl -qw net.ipv4.conf.eth0.accept_redirects=1 + ip netns exec "$h1" sysctl -qw net.ipv6.conf.all.accept_redirects=1 + ip netns exec "$h1" sysctl -qw net.ipv6.conf.eth0.accept_redirects=1 + + slowwait 5 linklocal_exists "$r1" eth0 + check_err $? "r1: link-local address was not generated" + slowwait 5 linklocal_exists "$r2" eth0 + check_err $? "r2: link-local address was not generated" + + R1_LLADDR=$(linklocal_get "$r1" eth0) + R2_LLADDR=$(linklocal_get "$r2" eth0) + R1_MAC=$(ip -n "$r1" -j link show dev eth0 | jq -r '.[]["address"]') + R2_MAC=$(ip -n "$r2" -j link show dev eth0 | jq -r '.[]["address"]') + + ip -n "$h1" route add "$H2_NET4" via "$R1_ADDR4" dev eth0 + ip -n "$h1" -6 route add "$H2_NET6" via "$R1_LLADDR" dev eth0 + ip -n "$r1" route add "$H2_NET4" via "$R2_R1_ADDR4" dev eth1 + ip -n "$r1" -6 route add "$H2_NET6" via "$R2_R1_ADDR6" dev eth1 + ip -n "$h2" route add default via 203.0.113.1 dev eth0 + ip -n "$h2" -6 route add default via 2001:db8:3::1 dev eth0 + + far_mtu_set "$MTU_MID" +} + +# Make r1 forward towards h2's network over the segment it receives the packet +# from, so that it emits a redirect towards h1. +redirect_route_set() +{ + ip -n "$r1" route replace "$H2_NET4" via "$R2_ADDR4" dev eth0 + ip -n "$r1" -6 route replace "$H2_NET6" via "$R2_LLADDR" dev eth0 + + # __ip_do_redirect() only creates an exception if the new gateway is + # already a valid neighbour. Otherwise it merely triggers address + # resolution. IPv6 resolves the target itself, in rt6_do_redirect(). + ip -n "$h1" neigh replace "$R2_ADDR4" lladdr "$R2_MAC" dev eth0 \ + nud permanent +} + +far_mtu_set() +{ + local mtu=$1; shift + + ip -n "$r2" link set dev eth2 mtu "$mtu" + ip -n "$h2" link set dev eth0 mtu "$mtu" +} + +socket_is_open() +{ + ip netns exec "$h1" ss -uHn "sport = :$SPORT" | grep -q . +} + +socket_start() +{ + # Disable PMTU discovery by default so that ICMP errors are not + # reported to the socket. Otherwise socat would exit when the first one + # arrives and later packets in the same test would not be matched to a + # socket. The exception is still created, as ip{,6}_sk_accept_pmtu() + # only rejects IP{,V6}_PMTUDISC_{INTERFACE,OMIT}. + local pmtudisc=${1:-$PMTUDISC_DONT} + + # Send socat's diagnostics to /dev/null. It reports the ICMP errors + # that reach the socket, which is exactly what the tests provoke. + ip netns exec "$h1" socat -u -lf/dev/null \ + "$SOCAT_DST,$SOCAT_BIND,$SOCAT_PMTUDISC=$pmtudisc" \ + OPEN:/dev/null,wronly=1 & + SOCAT_PID=$! + defer socket_stop + + slowwait 5 socket_is_open + check_err $? "socket did not open" +} + +socket_stop() +{ + [ -z "$SOCAT_PID" ] && return 0 + + kill "$SOCAT_PID" &> /dev/null + wait "$SOCAT_PID" 2> /dev/null + SOCAT_PID= +} + +# Inject a packet towards h2 with a packet socket. No socket is associated with +# it, so an ICMP error quoting it is matched to a socket only if one was +# created separately with the same source port. +packet_send() +{ + local size=$1; shift + + ip netns exec "$h1" mausezahn "${MZ_FAMILY_OPT[@]}" eth0 \ + -a own -b "$R1_MAC" -A "$H1_ADDR" -B "$H2_ADDR" \ + -t udp "${MZ_IP_OPTS}sp=$SPORT,dp=$DPORT" \ + -p "$size" -c 1 -q +} + +exception_show() +{ + if [ "$FAMILY" -eq 4 ]; then + # IPv4 exceptions without a bound route are not dumped, but + # "route get" reports the exception and binds a route to it. + ip -n "$h1" route get "$H2_ADDR" + else + # IPv6 does not report a cache indication in "route get" + # output, so dump the exceptions instead. + ip -n "$h1" -6 route show cache | grep -F "$H2_ADDR" || true + fi +} + +exception_mtu_get() +{ + exception_show | grep -o "mtu [0-9]*" | cut -d ' ' -f 2 +} + +exception_gw_get() +{ + exception_show | grep -o "via [0-9a-f.:]*" | cut -d ' ' -f 2 +} + +exception_mtu_check() +{ + local expected=$1; shift + + [ "$(exception_mtu_get)" = "$expected" ] +} + +icmp_errors_get() +{ + local ctr=IcmpInDestUnreachs + + [ "$FAMILY" -eq 6 ] && ctr=Icmp6InPktTooBigs + + ip netns exec "$h1" nstat -asz "$ctr" | \ + awk -v ctr="$ctr" '$1 == ctr { print $2 }' +} + +exception_pmtu_check() +{ + local mtu=$1; shift + local desc=$1; shift + + busywait "$BUSYWAIT_TIMEOUT" exception_mtu_check "$mtu" + check_err $? "$desc: exception does not carry an MTU of $mtu" +} + +pmtu_no_socket() +{ + local family=$1; shift + + RET=0 + family_vars_set "$family" + topology_setup + + packet_send "$PMTU_PACKET_SIZE" + exception_pmtu_check "$MTU_MID" "No socket" + + log_test "IPv$family: PMTU: exception without a matching socket" +} + +pmtu_no_socket_ipv4() +{ + pmtu_no_socket 4 +} + +pmtu_no_socket_ipv6() +{ + pmtu_no_socket 6 +} + +pmtu_socket() +{ + local family=$1; shift + local t0 + + RET=0 + family_vars_set "$family" + topology_setup + socket_start + + packet_send "$PMTU_PACKET_SIZE" + exception_pmtu_check "$MTU_MID" "Matching socket" + + # A lower PMTU replaces the one currently stored in the exception. + far_mtu_set "$MTU_LOW" + packet_send "$PMTU_PACKET_SIZE" + exception_pmtu_check "$MTU_LOW" "Lower PMTU" + + # A higher PMTU is ignored, so the exception is left as it is. Wait + # for the error to be received, as otherwise the check below would + # pass even if it never was. + far_mtu_set "$MTU_MID" + t0=$(icmp_errors_get) + packet_send "$PMTU_PACKET_SIZE" + busywait "$BUSYWAIT_TIMEOUT" until_counter_is ">= $((t0 + 1))" \ + icmp_errors_get > /dev/null + check_err $? "Higher PMTU: ICMP error was not received" + + exception_mtu_check "$MTU_LOW" + check_err $? "Higher PMTU: exception does not carry an MTU of $MTU_LOW" + + log_test "IPv$family: PMTU: exception with a matching socket" +} + +pmtu_socket_ipv4() +{ + pmtu_socket 4 +} + +pmtu_socket_ipv6() +{ + pmtu_socket 6 +} + +pmtu_omit() +{ + local family=$1; shift + + RET=0 + family_vars_set "$family" + topology_setup + socket_start "$PMTUDISC_OMIT" + + packet_send "$PMTU_PACKET_SIZE" + exception_pmtu_check "$MTU_MID" "PMTU discovery disabled" + + log_test "IPv$family: PMTU: exception with a socket ignoring it" +} + +pmtu_omit_ipv4() +{ + pmtu_omit 4 +} + +pmtu_omit_ipv6() +{ + pmtu_omit 6 +} + +exception_gw_check() +{ + local expected=$1; shift + + [ -n "$expected" ] && [ "$(exception_gw_get)" = "$expected" ] +} + +redirect_gw_new() +{ + if [ "$FAMILY" -eq 4 ]; then + echo "$R2_ADDR4" + else + echo "$R2_LLADDR" + fi +} + +redirect_no_socket() +{ + local family=$1; shift + + RET=0 + family_vars_set "$family" + topology_setup + redirect_route_set + + packet_send "$REDIRECT_PACKET_SIZE" + busywait "$BUSYWAIT_TIMEOUT" exception_gw_check "$(redirect_gw_new)" + check_err $? "No socket: exception does not carry the new gateway" + + log_test "IPv$family: Redirect: exception without a matching socket" +} + +redirect_no_socket_ipv4() +{ + redirect_no_socket 4 +} + +redirect_no_socket_ipv6() +{ + redirect_no_socket 6 +} + +redirect_socket() +{ + local family=$1; shift + + RET=0 + family_vars_set "$family" + topology_setup + redirect_route_set + socket_start + + packet_send "$REDIRECT_PACKET_SIZE" + busywait "$BUSYWAIT_TIMEOUT" exception_gw_check "$(redirect_gw_new)" + check_err $? "Matching socket: exception does not carry the new gateway" + + log_test "IPv$family: Redirect: exception with a matching socket" +} + +redirect_socket_ipv4() +{ + redirect_socket 4 +} + +redirect_socket_ipv6() +{ + redirect_socket 6 +} + +trap defer_scopes_cleanup EXIT +tests_run + +exit "$EXIT_STATUS" From b3b76e9f4f2476f1135b2ba7743a821db4a0df4b Mon Sep 17 00:00:00 2001 From: Tung Nguyen Date: Thu, 27 Aug 2026 18:13:46 +0700 Subject: [PATCH 0325/1198] tipc: fix NULL deref in tipc_named_node_up() on empty publication list User-space applications can bind a large number of service addresses to one or more sockets. Each binding of a local-scope service address inserts one entry (publication) into the TIPC name table. If the number of these publications exceeds TIPC_MAX_PUBL (65535), protocol service types (such as node state and link state) are no longer inserted into the name table. This causes two issues: 1. User-space applications subscribing to node or link up/down events stop receiving notifications. 2. A NULL pointer dereference can occur: BUG: kernel NULL pointer dereference, address: 00000000000000d0 ... CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 7.2.0-rc4-default+ #5 PREEMPT(full) ... RIP: 0010:tipc_named_node_up (./include/linux/skbuff.h:2251 net/tipc/name_distr.c:195 net/tipc/name_distr.c:221) ... Call Trace: tipc_node_write_unlock (net/tipc/node.c:428) tipc_rcv (net/tipc/node.c:934 net/tipc/node.c:2189) tipc_udp_recv (net/tipc/udp_media.c:389) Thread 1 (tipc_net_finalize) | Thread 2 (named_distribute) -----------------------------|----------------------------- | ... | list_for_each_entry(publ, pls, binding_node) { | ... | __skb_queue_tail(list, skb); | ... | } | ... | hdr = buf_msg(skb_peek_tail(list)); ... | tipc_nametbl_publish(); | If 'tipc_nametbl_publish()' (Thread 1) fails because the number of local publications reaches TIPC_MAX_PUBL, list (Thread 2) will be empty. As a result, NULL is passed to 'buf_msg()', leading to a NULL pointer dereference. Fix these issues by allowing protocol service types (node state, link state, and topology server) to be inserted into the name table unconditionally. This ensures that users subscribing to these types always receive notifications. In addition, the maximum number of local user publications is reduced to (TIPC_MAX_PUBL - 1). This ensures that the maximum bulk size calculated in tipc_link_set_queue_limits() remains valid. Fixes: a5e7ac5ce134 ("tipc: fix regression bug where node events are not being generated") Reported-by: Xiang Mei Tested-by: Weiming Shi Signed-off-by: Tung Nguyen Link: https://patch.msgid.link/20260827111418.164957-1-tung.quang.nguyen@est.tech Signed-off-by: Jakub Kicinski --- net/tipc/name_table.c | 32 +++++++++++++++++++++++++++----- 1 file changed, 27 insertions(+), 5 deletions(-) diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 253c72d1366e..6fda36ab1766 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -763,21 +763,40 @@ struct publication *tipc_nametbl_publish(struct net *net, struct tipc_uaddr *ua, struct tipc_socket_addr *sk, u32 key) { struct name_table *nt = tipc_name_table(net); + u32 max_user_pub = TIPC_MAX_PUBL - 1; struct tipc_net *tn = tipc_net(net); struct publication *p = NULL; struct sk_buff *skb = NULL; + bool protocol_type = false; u32 rc_dests; - spin_lock_bh(&tn->nametbl_lock); + if (ua->sr.type == TIPC_NODE_STATE || ua->sr.type == TIPC_LINK_STATE || + ua->sr.type == TIPC_TOP_SRV) + protocol_type = true; - if (nt->local_publ_count >= TIPC_MAX_PUBL) { - pr_warn("Bind failed, max limit %u reached\n", TIPC_MAX_PUBL); + spin_lock_bh(&tn->nametbl_lock); + if (protocol_type) + goto insert; + + /* Reserve one entry for node state service type because it has cluster + * scope and it is distributed in bulk. So, the maximum number of user's + * publications is (TIPC_MAX_PUBL - 1). + */ + if (nt->local_publ_count >= max_user_pub) { + pr_warn("Bind failed, max limit %u reached\n", max_user_pub); goto exit; } +insert: p = tipc_nametbl_insert_publ(net, ua, sk, key); if (p) { - nt->local_publ_count++; + /* Not count node state, link state and topology server types + * so that maximum nt->local_publ_count does not prevent + * protocol service types from being inserted into the name + * table. + */ + if (!protocol_type) + nt->local_publ_count++; skb = tipc_named_publish(net, p); } rc_dests = nt->rc_dests; @@ -810,7 +829,10 @@ void tipc_nametbl_withdraw(struct net *net, struct tipc_uaddr *ua, p = tipc_nametbl_remove_publ(net, ua, sk, key); if (p) { - nt->local_publ_count--; + if (p->sr.type != TIPC_NODE_STATE && + p->sr.type != TIPC_LINK_STATE && + p->sr.type != TIPC_TOP_SRV) + nt->local_publ_count--; skb = tipc_named_withdraw(net, p); list_del_init(&p->binding_sock); kfree_rcu(p, rcu); From 81c600c26302a27852ed8b19c5f2f647ea3555c9 Mon Sep 17 00:00:00 2001 From: David Laight Date: Sat, 29 Aug 2026 12:58:12 +0100 Subject: [PATCH 0326/1198] tipc: Dont send random pad bytes in RESET/ACTIVATE messages The interface name is passed in a fixed length (TIPC_MAX_IF_NAME) buffer. Replace the strcpy(data, l->if_name) with memcpy() so that the pad bytes are actually written (l->if_name[] is zero padded) rather than sending random bytes from the skb to the remote system. Replace two other strcpy() with strscpy(). Fixes: e74a386d70c7 ("tipc: remove pre-allocated message header in link struct") Signed-off-by: David Laight Reviewed-by: Tung Nguyen Link: https://patch.msgid.link/20260829115813.188600-1-david.laight.linux@gmail.com Signed-off-by: Jakub Kicinski --- net/tipc/link.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/tipc/link.c b/net/tipc/link.c index 49dfc098d89b..6427c69f8929 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -504,7 +504,7 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id, snprintf(l->name, sizeof(l->name), "%s:%s-%s:unknown", self_str, if_name, peer_str); - strcpy(l->if_name, if_name); + strscpy(l->if_name, if_name); l->addr = peer; l->peer_caps = peer_caps; l->net = net; @@ -574,7 +574,7 @@ bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer, u8 *peer_id, snprintf(l->name, sizeof(l->name), "%s:%s", tipc_bclink_name, peer_str); } else { - strcpy(l->name, tipc_bclink_name); + strscpy(l->name, tipc_bclink_name); } trace_tipc_link_reset(l, TIPC_DUMP_ALL, "bclink created!"); tipc_link_reset(l); @@ -1898,7 +1898,7 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, msg_set_dest_session(hdr, l->peer_session); } msg_set_max_pkt(hdr, l->advertised_mtu); - strcpy(data, l->if_name); + memcpy(data, l->if_name, TIPC_MAX_IF_NAME); msg_set_size(hdr, INT_H_SIZE + TIPC_MAX_IF_NAME); skb_trim(skb, INT_H_SIZE + TIPC_MAX_IF_NAME); } From 975b5b067f525a1b1338c4a3bee1c46545801518 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 28 Aug 2026 14:17:27 +0000 Subject: [PATCH 0327/1198] ipv6: sr: restore network header before routing and forwarding ipv6_srh_rcv() runs with skb->data at the Segment Routing Header (SRH) while skb_network_header() points at the IPv6 header. When segments_left > 0, ipv6_srh_rcv() previously restored the skb->data position by pushing sizeof(struct ipv6hdr), assuming the SRH immediately followed the fixed IPv6 header. If another extension header (such as a Hop-by-Hop options header) precedes the SRH, skb_network_offset() remained negative. This led to two problems: 1. During ip6_route_input(), fib6_rules_early_flow_dissect() invokes __skb_flow_dissect() which passes the negative skb_network_offset() to flow dissection, breaking BPF and C flow dissector logic. 2. If forwarded via ip6_forward() or redirected via act_mirred, downstream handlers (like sch_fragment() or neighbour output) pass the negative offset as an unsigned length, triggering OOB memcpy or buffer overflows. Fix this by pushing -skb_network_offset(skb) before routing, ensuring skb_network_offset(skb) is 0 for route lookup / flow dissection as well as downstream forwarding. On the loopback path, pull skb_transport_offset(skb) to restore skb->data to the SRH before looping back. Fixes: 1ababeba4a21 ("ipv6: implement dataplane support for rthdr type 4 (Segment Routing Header)") Reported-by: TencentOS Corvus AI Reported-by: Jun Yang Reported-by: Fourie Zhang Closes: https://lore.kernel.org/netdev/20260817104128.22681-1-juny24602@gmail.com/ Closes: https://lore.kernel.org/netdev/20260827092345.2301937-1-fouriezhang@tencent.com/ Signed-off-by: Eric Dumazet Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/20260828141727.2372570-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv6/exthdrs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 51941ad656a3..09a4552f7f08 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -445,7 +445,7 @@ static int ipv6_srh_rcv(struct sk_buff *skb, struct inet6_dev *idev) hdr->segments_left--; addr = hdr->segments + hdr->segments_left; - skb_push(skb, sizeof(struct ipv6hdr)); + skb_push(skb, -skb_network_offset(skb)); if (skb->ip_summed == CHECKSUM_COMPLETE) seg6_update_csum(skb); @@ -469,7 +469,7 @@ static int ipv6_srh_rcv(struct sk_buff *skb, struct inet6_dev *idev) } ipv6_hdr(skb)->hop_limit--; - skb_pull(skb, sizeof(struct ipv6hdr)); + skb_pull(skb, skb_transport_offset(skb)); goto looped_back; } From 545b63503c696c4ce0663b3fcd37f41169aec1eb Mon Sep 17 00:00:00 2001 From: Koichiro Den Date: Mon, 31 Aug 2026 00:16:17 +0900 Subject: [PATCH 0328/1198] net: ntb_netdev: Fix statistics races ntb_netdev updates shared net_device stats from per-QP RX and TX callbacks. Once multiple queues are enabled, concurrent updates can be lost. Use per-CPU tstats for packet and byte counters and DEV_STATS_INC() for less frequent drop and error counters. Callbacks can run synchronously in the xmit path or asynchronously from a tasklet or the memcpy kthread. Pin TX updates against migration in the kthread path. Use the IRQ-safe u64_stats helpers because netpoll can invoke the synchronous path with IRQs disabled. Let the core manage tstats while keeping transport teardown after unregister_netdev(), outside RTNL. RCU lets unregister wait for TX completions already updating stats, while later completions only consume the skb and skip accounting and queue wake. Fixes: 24d9e73c7e00 ("net: ntb_netdev: Support ethtool channels for multi-queue") Cc: stable@vger.kernel.org Suggested-by: Jakub Kicinski Signed-off-by: Koichiro Den Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20260830151617.3546585-1-den@valinux.co.jp Signed-off-by: Jakub Kicinski --- drivers/net/ntb_netdev.c | 47 +++++++++++++++++++++++++++++----------- 1 file changed, 34 insertions(+), 13 deletions(-) diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c index 9c171697e762..2c04be6d61a8 100644 --- a/drivers/net/ntb_netdev.c +++ b/drivers/net/ntb_netdev.c @@ -127,8 +127,10 @@ static void ntb_netdev_rx_handler(struct ntb_transport_qp *qp, void *qp_data, { struct ntb_netdev_queue *q = qp_data; struct ntb_netdev *dev = q->ntdev; + struct pcpu_sw_netstats *tstats; struct sk_buff *skb, *new_skb; struct net_device *ndev; + unsigned long flags; int rc; ndev = dev->ndev; @@ -139,17 +141,20 @@ static void ntb_netdev_rx_handler(struct ntb_transport_qp *qp, void *qp_data, netdev_dbg(ndev, "%s: %d byte payload received\n", __func__, len); if (len < 0) { - ndev->stats.rx_errors++; - ndev->stats.rx_length_errors++; + DEV_STATS_INC(ndev, rx_errors); + DEV_STATS_INC(ndev, rx_length_errors); goto enqueue_again; } - ndev->stats.rx_packets++; - ndev->stats.rx_bytes += len; + tstats = this_cpu_ptr(ndev->tstats); + flags = u64_stats_update_begin_irqsave(&tstats->syncp); + u64_stats_inc(&tstats->rx_packets); + u64_stats_add(&tstats->rx_bytes, len); + u64_stats_update_end_irqrestore(&tstats->syncp, flags); new_skb = netdev_alloc_skb(ndev, ndev->mtu + ETH_HLEN); if (!new_skb) { - ndev->stats.rx_dropped++; + DEV_STATS_INC(ndev, rx_dropped); goto enqueue_again; } @@ -166,8 +171,8 @@ static void ntb_netdev_rx_handler(struct ntb_transport_qp *qp, void *qp_data, rc = ntb_transport_rx_enqueue(qp, skb, skb->data, ndev->mtu + ETH_HLEN); if (rc) { dev_kfree_skb_any(skb); - ndev->stats.rx_errors++; - ndev->stats.rx_fifo_errors++; + DEV_STATS_INC(ndev, rx_errors); + DEV_STATS_INC(ndev, rx_fifo_errors); } } @@ -210,25 +215,39 @@ static void ntb_netdev_tx_handler(struct ntb_transport_qp *qp, void *qp_data, { struct ntb_netdev_queue *q = qp_data; struct ntb_netdev *dev = q->ntdev; + struct pcpu_sw_netstats *tstats; struct net_device *ndev; struct sk_buff *skb; + unsigned long flags; + bool registered; ndev = dev->ndev; skb = data; if (!skb || !ndev) return; + rcu_read_lock(); + registered = READ_ONCE(ndev->reg_state) == NETREG_REGISTERED; + if (!registered) + goto free_skb; + if (len > 0) { - ndev->stats.tx_packets++; - ndev->stats.tx_bytes += skb->len; + /* The memcpy kthread can migrate, so pin the per-CPU update. */ + tstats = get_cpu_ptr(ndev->tstats); + flags = u64_stats_update_begin_irqsave(&tstats->syncp); + u64_stats_inc(&tstats->tx_packets); + u64_stats_add(&tstats->tx_bytes, skb->len); + u64_stats_update_end_irqrestore(&tstats->syncp, flags); + put_cpu_ptr(ndev->tstats); } else { - ndev->stats.tx_errors++; - ndev->stats.tx_aborted_errors++; + DEV_STATS_INC(ndev, tx_errors); + DEV_STATS_INC(ndev, tx_aborted_errors); } +free_skb: dev_kfree_skb_any(skb); - if (ntb_transport_tx_free_entry(qp) >= tx_start) { + if (registered && ntb_transport_tx_free_entry(qp) >= tx_start) { /* Make sure anybody stopping the queue after this sees the new * value of ntb_transport_tx_free_entry() */ @@ -237,6 +256,7 @@ static void ntb_netdev_tx_handler(struct ntb_transport_qp *qp, void *qp_data, ntb_transport_link_query(q->qp)) netif_wake_subqueue(ndev, q->qid); } + rcu_read_unlock(); } static const struct ntb_queue_handlers ntb_netdev_handlers = { @@ -277,7 +297,7 @@ static netdev_tx_t ntb_netdev_start_xmit(struct sk_buff *skb, drop: dev_kfree_skb_any(skb); - ndev->stats.tx_dropped++; + DEV_STATS_INC(ndev, tx_dropped); return NETDEV_TX_OK; } @@ -647,6 +667,7 @@ static int ntb_netdev_probe(struct device *client_dev) } ndev->features = NETIF_F_HIGHDMA; + ndev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE; From 3f9c7a108c0e8f14425384912017071b71341e3b Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Mon, 31 Aug 2026 11:50:50 +0900 Subject: [PATCH 0329/1198] block: flag zoned disks with GENHD_FL_NO_PART Zoned block devices do not support partitions. However, the partition table is nevertheless still inspected, and any partition found ignored with a warning in add_partition(). While this is generally not a problem, and in fact beneficial to the user as it indicates an invalid use of a zoned block device, scanning for a partition table on the device may result in issuing read operations to offline zones (e.g. after a disk head is depopulated for disks that support head management operations). Since partitions are ignored anyway, completely disable partition scanning for zoned gendisks by setting the flag GENHD_FL_NO_PART in __add_disk(). The existing check in add_partition() is left as-is to ensure that we still get a warning if for whatever reason, despite GENHD_FL_NO_PART, we still endup trying to add partitions. Flagging zoned disks with GENHD_FL_NO_PART also has the benefit to expose through sysfs the ext_range attribute with the value of 1 instead of the default DISK_MAX_PARTS, thus correctly advertizing the fact that zoned disks do not support partitions. Fixes: 5eac3eb30c9a ("block: Remove partition support for zoned block devices") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Reviewed-by: Bart Van Assche Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Link: https://patch.msgid.link/20260831025050.667758-1-dlemoal@kernel.org Signed-off-by: Jens Axboe --- block/genhd.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/block/genhd.c b/block/genhd.c index f1990c7cdfb9..10ca8b4d6eea 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -447,6 +447,13 @@ static int __add_disk(struct device *parent, struct gendisk *disk, bdev_set_flag(disk->part0, BD_HAS_SUBMIT_BIO); } + /* + * We do not support partitions with zoned block devices, so do not try + * to scan the partitions table. + */ + if (blk_queue_is_zoned(disk->queue)) + disk->flags |= GENHD_FL_NO_PART; + /* * If the driver provides an explicit major number it also must provide * the number of minors numbers supported, and those will be used to From 412a6ceb56d501ef2f8202e26ab4b5d4dfbca566 Mon Sep 17 00:00:00 2001 From: Zhenhao Wan Date: Tue, 11 Aug 2026 16:46:28 +0800 Subject: [PATCH 0330/1198] drm/nouveau/uvmm: fix NULL deref unwinding an OP_MAP_SPARSE op Each bind_job_op is zeroed by kzalloc_obj() in bind_job_op_from_uop(), and the OP_MAP_SPARSE case in nouveau_uvmm_bind_job_submit() only creates a region, so op->ops stays NULL for a successfully processed sparse map. If a later op in the same job fails, the reverse unwind loop revisits that op and calls drm_gpuva_ops_free(&uvmm->base, op->ops) unconditionally. drm_gpuva_ops_free() dereferences its argument right away (list_for_each_entry_safe on &ops->list), so a NULL op->ops oopses. The path is reachable by any render-node fd holder, since NOUVEAU_VM_BIND is DRM_RENDER_ALLOW. Guard the free with IS_ERR_OR_NULL(), as nouveau_uvmm_bind_job_cleanup() already does for the identical free. Fixes: b88baab82871 ("drm/nouveau: implement new VM_BIND uAPI") Reported-by: Yuhao Jiang Assisted-by: Claude:claude-opus-5 Cc: stable@vger.kernel.org Signed-off-by: Zhenhao Wan Reviewed-by: Lyude Paul Link: https://patch.msgid.link/20260811-nouveau-uvmm-vmbind-fixes-v2-1-aaee4b395d04@gmail.com Signed-off-by: Danilo Krummrich --- drivers/gpu/drm/nouveau/nouveau_uvmm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c index f5e4756b4de4..19e758a20c24 100644 --- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c +++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c @@ -1489,7 +1489,8 @@ nouveau_uvmm_bind_job_submit(struct nouveau_job *job, break; } - drm_gpuva_ops_free(&uvmm->base, op->ops); + if (!IS_ERR_OR_NULL(op->ops)) + drm_gpuva_ops_free(&uvmm->base, op->ops); op->ops = NULL; op->reg = NULL; } From ccf930812f23b8259ef64fd3394d53b093e4651a Mon Sep 17 00:00:00 2001 From: Zhenhao Wan Date: Tue, 11 Aug 2026 16:46:29 +0800 Subject: [PATCH 0331/1198] drm/nouveau/uvmm: fix premature region free on failed OP_UNMAP_SPARSE In nouveau_uvmm_bind_job_submit()'s OP_UNMAP_SPARSE arm, op->reg is set from nouveau_uvma_region_find(), which only looks the region up and takes no reference; a region's sole reference is its membership in uvmm->region_mt. Two failure paths leave op->reg set: the -ENOENT check when the region is busy, and the drm_gpuvm_sm_unmap_ops_create() failure. The sibling nouveau_uvmm_sm_unmap_prepare() failure just below clears op->reg; these two do not. unwind_continue steps back one op, so the failing op is skipped by the unwind loop and its op->reg stays set. nouveau_uvmm_bind_job_cleanup() then enters its if (op->reg) branch and calls nouveau_uvma_region_remove() and nouveau_uvma_region_put() on it, dropping the tree's sole reference and freeing a region this job never created. The comment above the cleanup loop documents the broken invariant: op->reg must be NULL on submit failure. This frees a live region on an unrelated failure, reachable single-job when drm_gpuvm_sm_unmap_ops_create() returns -ENOMEM; if another job owns the same region, its cleanup then removes and puts the freed region, a use-after-free. Clear op->reg on both failure paths. Fixes: b88baab82871 ("drm/nouveau: implement new VM_BIND uAPI") Reported-by: Yuhao Jiang Assisted-by: Claude:claude-opus-5 Cc: stable@vger.kernel.org Signed-off-by: Zhenhao Wan Reviewed-by: Lyude Paul Link: https://patch.msgid.link/20260811-nouveau-uvmm-vmbind-fixes-v2-2-aaee4b395d04@gmail.com Signed-off-by: Danilo Krummrich --- drivers/gpu/drm/nouveau/nouveau_uvmm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c index 19e758a20c24..d30ec3709e79 100644 --- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c +++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c @@ -1319,6 +1319,7 @@ nouveau_uvmm_bind_job_submit(struct nouveau_job *job, op->va.range); if (!op->reg || op->reg->dirty) { ret = -ENOENT; + op->reg = NULL; goto unwind_continue; } @@ -1327,6 +1328,7 @@ nouveau_uvmm_bind_job_submit(struct nouveau_job *job, op->va.range); if (IS_ERR(op->ops)) { ret = PTR_ERR(op->ops); + op->reg = NULL; goto unwind_continue; } From 38a62306c4266bcb3cd89e33c7111ee33096ebb3 Mon Sep 17 00:00:00 2001 From: Zhenhao Wan Date: Tue, 11 Aug 2026 16:46:30 +0800 Subject: [PATCH 0332/1198] drm/nouveau/uvmm: clear the dirty flag when unwinding an OP_UNMAP_SPARSE A successful OP_UNMAP_SPARSE marks its region dirty with nouveau_uvma_region_dirty() and defers the teardown to nouveau_uvmm_bind_job_cleanup(); it does not remove the region from uvmm->region_mt. If a later op in the job fails, the unwind path never clears reg->dirty (set in one place, cleared nowhere) and sets op->reg = NULL, so cleanup skips the teardown. The region is left in the tree with dirty set and its completion never signalled. Later binds over that range then fail permanently -- -ENOENT or -EINVAL from the dirty checks, or an unkillable wait_for_completion() in bind_validate_region() -- for the lifetime of the uvmm. Clear reg->dirty when the unwind reverts the sparse unmap, restoring the region to the state it was found in. Fixes: b88baab82871 ("drm/nouveau: implement new VM_BIND uAPI") Reported-by: Yuhao Jiang Assisted-by: Claude:claude-opus-5 Cc: stable@vger.kernel.org Signed-off-by: Zhenhao Wan Reviewed-by: Lyude Paul Link: https://patch.msgid.link/20260811-nouveau-uvmm-vmbind-fixes-v2-3-aaee4b395d04@gmail.com Signed-off-by: Danilo Krummrich --- drivers/gpu/drm/nouveau/nouveau_uvmm.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c index d30ec3709e79..fc125fd44a9b 100644 --- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c +++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c @@ -1475,6 +1475,7 @@ nouveau_uvmm_bind_job_submit(struct nouveau_job *job, op->va.range); break; case OP_UNMAP_SPARSE: + op->reg->dirty = false; __nouveau_uvma_region_insert(uvmm, op->reg); nouveau_uvmm_sm_unmap_prepare_unwind(uvmm, &op->new, op->ops); From 73e594c19b4f815d8343461cec7074c4713bbde7 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Sun, 30 Aug 2026 18:09:12 +0000 Subject: [PATCH 0333/1198] af_packet: Don't cast tpacket_hdr.tp_len to int in tpacket_parse_header(). syzbot reported BUG() in sock_sendmsg_nosec(). [0] The problem is that tpacket_parse_header() casts user-provided tpacket_hdr.tp_len, which is u32, to int. If the length is larger than INT_MAX, the following condition in tpacket_parse_header() passes, if (unlikely(tp_len > size_max)) and any negative value can be returned to the caller, up to sock_sendmsg_nosec(). The repro set tpacket_hdr.tp_len to 0xfffffdef, which is cast to -EIOCBQUEUED (-529), triggering BUG() in sock_sendmsg_nosec(). *(uint64_t*)0x200000000008 = 0xfffffdef; ... syscall(__NR_write, /*fd=*/r[0], /*buf=*/0x200000000000ul, /*count=*/1ul); Let's define the local tp_len as u32 in tpacket_parse_header(). [0]: kernel BUG at net/socket.c:803! Oops: invalid opcode: 0000 [#1] SMP KASAN PTI CPU: 0 UID: 0 PID: 5628 Comm: syz-executor176 Not tainted syzkaller #0 PREEMPT(full) Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/24/2026 RIP: 0010:sock_sendmsg_nosec+0x145/0x180 net/socket.c:803 Code: 06 67 48 0f b9 3a eb 95 e8 e8 3a 22 f8 48 89 df 4c 89 f6 4c 89 e2 4d 89 fb 2e e8 32 a5 5c 16 e9 51 ff ff ff e8 cc 3a 22 f8 90 <0f> 0b e8 c4 3a 22 f8 48 83 c3 18 48 89 d8 48 c1 e8 03 42 80 3c 28 RSP: 0018:ffffc90003aefb48 EFLAGS: 00010293 RAX: ffffffff89a578d4 RBX: ffff8880764c67c0 RCX: ffff88807fb23e80 RDX: 0000000000000000 RSI: 00000000fffffdef RDI: 00000000fffffdef RBP: 00000000fffffdef R08: ffffc90003aef747 R09: 1ffff9200075dee8 R10: dffffc0000000000 R11: fffff5200075dee9 R12: 0000000000000001 R13: dffffc0000000000 R14: ffffc90003aefbc0 R15: ffffffff8aac4310 FS: 000055559101b400(0000) GS:ffff888124ce0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000200000000210 CR3: 0000000073dca000 CR4: 00000000003526f0 Call Trace: __sock_sendmsg net/socket.c:815 [inline] sock_write_iter+0x2de/0x3e0 net/socket.c:1266 new_sync_write fs/read_write.c:595 [inline] vfs_write+0x612/0xba0 fs/read_write.c:687 ksys_write+0x150/0x270 fs/read_write.c:739 do_syscall_x64 arch/x86/entry/syscall_64.c:61 [inline] do_syscall_64+0x166/0x520 arch/x86/entry/syscall_64.c:84 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f173130ecb9 Code: c0 79 93 eb d5 48 8d 7c 1d 00 eb 99 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 d8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffd67e44248 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000200000000000 RCX: 00007f173130ecb9 RDX: 0000000000000001 RSI: 0000200000000000 RDI: 0000000000000003 RBP: 0000000000000001 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007ffd67e44388 R13: 0000000000000002 R14: 00002000000000c0 R15: 0000000000000002 Fixes: 69e3c75f4d54 ("net: TX_RING and packet mmap") Reported-by: syzbot+73df3f89e1e13089e466@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/6a946ffa.1d9ded08.62e62.0123.GAE@google.com/ Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20260830180915.260225-1-kuniyu@google.com Signed-off-by: Paolo Abeni --- net/packet/af_packet.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index b22cda322136..76bde7906d49 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2675,7 +2675,8 @@ static int tpacket_parse_header(struct packet_sock *po, void *frame, int size_max, void **data) { union tpacket_uhdr ph; - int tp_len, off; + u32 tp_len; + int off; ph.raw = frame; @@ -2695,7 +2696,7 @@ static int tpacket_parse_header(struct packet_sock *po, void *frame, break; } if (unlikely(tp_len > size_max)) { - pr_err("packet size is too long (%d > %d)\n", tp_len, size_max); + pr_err("packet size is too long (%u > %d)\n", tp_len, size_max); return -EMSGSIZE; } From deced5fa01c5e9813384b6c176379e5baaf5ec10 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 25 Aug 2026 13:06:15 +1000 Subject: [PATCH 0334/1198] nouveau/instmem: handle iomapping already existing Turns out sashiko was right, and I should protect this properly Fixes: 34e27b90552a ("nouveau/instmem: use iomapping interface for instmem handling") Signed-off-by: Dave Airlie Link: https://patch.msgid.link/20260825030615.3464436-1-airlied@gmail.com Signed-off-by: Danilo Krummrich --- drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c index f4489efc94a7..22b0fde6ba34 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c @@ -195,6 +195,9 @@ check_io_mapping(struct nv50_instmem *imem) { struct nvkm_device *device = imem->base.subdev.device; + if (imem->iomap.size) + return true; + return io_mapping_init_wc(&imem->iomap, device->func->resource_addr(device, NVKM_BAR2_INST), device->func->resource_size(device, NVKM_BAR2_INST)) != NULL; From caa1bc2a0a6ca19dcb90bbf88208b0fe2decd66f Mon Sep 17 00:00:00 2001 From: Zhenhao Wan Date: Tue, 11 Aug 2026 22:28:50 +0800 Subject: [PATCH 0335/1198] drm/nouveau/dmem: fix mismatched DMA unmap size for large folios Device-private THP migration maps migration buffers with page_size() and records that length in dma_info->size. For a compound folio page_size() is PAGE_SIZE << order, but two teardown sites still pass a literal PAGE_SIZE to dma_unmap_page(): - nouveau_dmem_migrate_to_ram() on the success path, and - nouveau_dmem_migrate_copy_one() on the copy-error path. For an order > 0 folio this unmaps less than was mapped, leaking the remainder of the IOMMU/IOVA mapping. The other unmap sites, in nouveau_dmem_migrate_chunk() and nouveau_dmem_evict_chunk(), already use the saved size; use it here too. Fixes: c32287471077 ("gpu/drm/nouveau: enable THP support for GPU memory migration") Reported-by: Yuhao Jiang Assisted-by: Claude:claude-opus-5 Cc: stable@vger.kernel.org Signed-off-by: Zhenhao Wan Link: https://patch.msgid.link/20260811-b4-nouveau-dmem-thp-fixes-v1-1-2cdf9860af2a@gmail.com Signed-off-by: Danilo Krummrich --- drivers/gpu/drm/nouveau/nouveau_dmem.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 9442ec6e1f6c..d2abee3efb9a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -267,7 +267,7 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf) nouveau_fence_new(&fence, dmem->migrate.chan); migrate_vma_pages(&args); nouveau_dmem_fence_done(&fence); - dma_unmap_page(drm->dev->dev, dma_info.dma_addr, PAGE_SIZE, + dma_unmap_page(drm->dev->dev, dma_info.dma_addr, dma_info.size, DMA_BIDIRECTIONAL); done: migrate_vma_finalize(&args); @@ -772,7 +772,7 @@ static unsigned long nouveau_dmem_migrate_copy_one(struct nouveau_drm *drm, return mpfn; out_dma_unmap: - dma_unmap_page(dev, dma_info->dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL); + dma_unmap_page(dev, dma_info->dma_addr, dma_info->size, DMA_BIDIRECTIONAL); out_free_page: nouveau_dmem_page_free_locked(drm, dpage); out: From c2256c044a1df39c8aad4dd2d6f709b2533e2d7a Mon Sep 17 00:00:00 2001 From: Zhenhao Wan Date: Tue, 11 Aug 2026 22:28:51 +0800 Subject: [PATCH 0336/1198] drm/nouveau/dmem: fix callocated underflow on large folio split nouveau_dmem_folio_free() drops chunk->callocated once per freed folio, while a large (compound) device-private folio is only counted once when it is allocated. When such a folio is split, the mm core invokes ->folio_split() (nouveau_dmem_folio_split()) once for each new sub-folio, but the hook only fixes up the sub-folio metadata and leaves chunk->callocated unchanged. Each resulting sub-folio is later freed separately, so after a split the single allocation (+1) is met by N frees (-N), leaving chunk->callocated short by N-1. On the first split/free cycle it underflows: WARN_ON(!chunk->callocated) fires, the unsigned counter wraps and never returns to zero, so the chunk can no longer be reclaimed (nouveau_dmem_fini() also warns on the leaked count). Account for the new sub-folio in the split hook, under the same lock as nouveau_dmem_folio_free(), so the count stays balanced. Fixes: c32287471077 ("gpu/drm/nouveau: enable THP support for GPU memory migration") Reported-by: Yuhao Jiang Assisted-by: Claude:claude-opus-5 Cc: stable@vger.kernel.org Signed-off-by: Zhenhao Wan Reviewed-by: Lyude Paul Link: https://patch.msgid.link/20260811-b4-nouveau-dmem-thp-fixes-v1-2-2cdf9860af2a@gmail.com Signed-off-by: Danilo Krummrich --- drivers/gpu/drm/nouveau/nouveau_dmem.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index d2abee3efb9a..ad4570c50be7 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -279,11 +279,25 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf) static void nouveau_dmem_folio_split(struct folio *head, struct folio *tail) { + struct nouveau_dmem_chunk *chunk; + struct nouveau_dmem *dmem; + if (tail == NULL) return; tail->pgmap = head->pgmap; tail->mapping = head->mapping; folio_set_zone_device_data(tail, folio_zone_device_data(head)); + + /* + * The split hands out a new independently-freeable folio that will + * later be released via nouveau_dmem_folio_free(); account for it so + * chunk->callocated stays balanced. + */ + chunk = nouveau_page_to_chunk(&head->page); + dmem = chunk->drm->dmem; + spin_lock(&dmem->lock); + chunk->callocated++; + spin_unlock(&dmem->lock); } static const struct dev_pagemap_ops nouveau_dmem_pagemap_ops = { From c037915f80c4db47f7d061d68e703ffd551b1a34 Mon Sep 17 00:00:00 2001 From: Kaiwen Shi Date: Sun, 30 Aug 2026 07:05:51 +0800 Subject: [PATCH 0337/1198] mac802154: fix data race and NULL deref on local->assoc_dev local->assoc_dev is shared between the association path and the association-response worker without common synchronization. mac802154_perform_association() stores the coordinator pointer and waits for a response. Its timeout and error paths clear the pointer and return to mac802154_associate(), which may then free the coordinator object. Meanwhile, mac802154_rx_mac_cmd_worker() may observe the associating bit and enter mac802154_process_association_resp(), which dereferences assoc_dev. The worker's bit test and the handler's pointer dereference are not atomic with respect to cleanup. Cleanup can clear assoc_dev between them, causing a NULL dereference, or free the coordinator while the response handler still uses the pointer. The recorded result is exposed to the same window. assoc_status and assoc_addr are written by the handler but read by the association path while the associating bit is still set, so a second response for the same request - a malicious one, for instance - can replace them between those reads and leave the caller with an incoherent status and address pair. The response handler only needs the coordinator extended address. Replace assoc_dev with a cached address, removing the pointer lifetime dependency. Protect the cached address and the associating bit with a dedicated spinlock. A READ_ONCE()/WRITE_ONCE() pair would not guarantee an atomic __le64 access on all 32-bit architectures. wpan_dev->association_lock cannot be reused here: nl802154_associate() holds it across rdev_associate(), hence for the whole of mac802154_perform_association() including the wait for the response. A response handler taking that lock would only get it once the association has already given up. Reset the completion, publish the cached address, and set the associating bit while holding the lock. The response handler takes the lock, rechecks the bit and the cached address, records the response, clears the bit, and only then completes the waiter. Thus cleanup cannot pass the handler between its state check and completion, and the cached 64-bit value cannot tear. The handler clears the bit before completing, not the woken waiter: otherwise complete() is issued under the lock and a second (e.g. malicious) response can reacquire it before the waiter and replace the result. So a wait that returns success implies the bit is already clear, and the success and negative-response paths return directly. The transmit-error and timeout paths still clear it under assoc_lock, which serializes any racing response against the cleanup while the call returns the error it already selected. Both paths snapshot assoc_status and assoc_addr under the same lock. Both users run in process context, so a plain spinlock is sufficient. The lock is not held while waiting for the completion. Suggested-by: Miquel Raynal Suggested-by: Xuanqiang Luo Fixes: fefd19807fe9 ("mac802154: Handle associating") Cc: stable@vger.kernel.org Signed-off-by: Kaiwen Shi Reviewed-by: Xuanqiang Luo Reviewed-by: Miquel Raynal Link: https://patch.msgid.link/20260829230551.1787432-1-skwkevin@mail.ustc.edu.cn Signed-off-by: Paolo Abeni --- net/mac802154/ieee802154_i.h | 7 ++++- net/mac802154/main.c | 1 + net/mac802154/scan.c | 51 +++++++++++++++++++++++++++--------- 3 files changed, 45 insertions(+), 14 deletions(-) diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h index 8f2bff268392..c53aa293a222 100644 --- a/net/mac802154/ieee802154_i.h +++ b/net/mac802154/ieee802154_i.h @@ -76,7 +76,12 @@ struct ieee802154_local { struct work_struct rx_mac_cmd_work; /* Association */ - struct ieee802154_pan_device *assoc_dev; + /* assoc_lock protects assoc_dev_extended_addr, assoc_addr, + * assoc_status, the assoc_done reinit/complete pairing and the + * IEEE802154_IS_ASSOCIATING bit in @ongoing. + */ + spinlock_t assoc_lock; + __le64 assoc_dev_extended_addr; struct completion assoc_done; __le16 assoc_addr; u8 assoc_status; diff --git a/net/mac802154/main.c b/net/mac802154/main.c index ea1efef3572a..63e89bd586e3 100644 --- a/net/mac802154/main.c +++ b/net/mac802154/main.c @@ -104,6 +104,7 @@ ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops) INIT_WORK(&local->rx_mac_cmd_work, mac802154_rx_mac_cmd_worker); init_completion(&local->assoc_done); + spin_lock_init(&local->assoc_lock); /* init supported flags with 802.15.4 default ranges */ phy->supported.max_minbe = 8; diff --git a/net/mac802154/scan.c b/net/mac802154/scan.c index 005338f89b75..dd156c01ac49 100644 --- a/net/mac802154/scan.c +++ b/net/mac802154/scan.c @@ -536,7 +536,9 @@ int mac802154_perform_association(struct ieee802154_sub_if_data *sdata, struct ieee802154_association_req_frame frame = {}; struct ieee802154_local *local = sdata->local; struct wpan_dev *wpan_dev = &sdata->wpan_dev; + __le16 resp_short_addr; struct sk_buff *skb; + u8 resp_status; int ret; frame.mhr.fc.type = IEEE802154_FC_TYPE_MAC_CMD; @@ -578,9 +580,11 @@ int mac802154_perform_association(struct ieee802154_sub_if_data *sdata, return ret; } - local->assoc_dev = coord; + spin_lock(&local->assoc_lock); reinit_completion(&local->assoc_done); + local->assoc_dev_extended_addr = coord->extended_addr; set_bit(IEEE802154_IS_ASSOCIATING, &local->ongoing); + spin_unlock(&local->assoc_lock); ret = ieee802154_mlme_tx_one_locked(local, sdata, skb); if (ret) { @@ -599,25 +603,37 @@ int mac802154_perform_association(struct ieee802154_sub_if_data *sdata, goto clear_assoc; } - if (local->assoc_status != IEEE802154_ASSOCIATION_SUCCESSFUL) { - if (local->assoc_status == IEEE802154_PAN_AT_CAPACITY) + /* The association is complete: mac802154_process_association_resp() + * cleared the associating bit before waking us, so a second (e.g. + * malicious) ASSOC RESP can no longer pass the recheck and overwrite + * the result. Snapshot assoc_status/assoc_addr under the lock. + */ + spin_lock(&local->assoc_lock); + resp_status = local->assoc_status; + resp_short_addr = local->assoc_addr; + spin_unlock(&local->assoc_lock); + + if (resp_status != IEEE802154_ASSOCIATION_SUCCESSFUL) { + if (resp_status == IEEE802154_PAN_AT_CAPACITY) ret = -ERANGE; else ret = -EPERM; dev_warn(&sdata->dev->dev, "Negative ASSOC RESP received from %8phC: %s\n", &ceaddr, - local->assoc_status == IEEE802154_PAN_AT_CAPACITY ? + resp_status == IEEE802154_PAN_AT_CAPACITY ? "PAN at capacity" : "access denied"); - goto clear_assoc; + return ret; } - ret = 0; - *short_addr = local->assoc_addr; + *short_addr = resp_short_addr; + + return 0; clear_assoc: + spin_lock(&local->assoc_lock); clear_bit(IEEE802154_IS_ASSOCIATING, &local->ongoing); - local->assoc_dev = NULL; + spin_unlock(&local->assoc_lock); return ret; } @@ -639,19 +655,28 @@ int mac802154_process_association_resp(struct ieee802154_sub_if_data *sdata, dest->mode != IEEE802154_EXTENDED_ADDRESSING)) return -EINVAL; - if (unlikely(dest->extended_addr != wpan_dev->extended_addr || - src->extended_addr != local->assoc_dev->extended_addr)) + spin_lock(&local->assoc_lock); + if (unlikely(!test_bit(IEEE802154_IS_ASSOCIATING, &local->ongoing) || + dest->extended_addr != wpan_dev->extended_addr || + src->extended_addr != local->assoc_dev_extended_addr)) { + spin_unlock(&local->assoc_lock); return -ENODEV; + } memcpy(&resp_pl, skb->data, sizeof(resp_pl)); local->assoc_addr = resp_pl.short_addr; local->assoc_status = resp_pl.status; + /* Clear the associating bit before waking the waiter: once the result + * is saved, any subsequent (e.g. malicious) ASSOC RESP must fail the + * test_bit() recheck above and can no longer overwrite the result. + */ + clear_bit(IEEE802154_IS_ASSOCIATING, &local->ongoing); + complete(&local->assoc_done); + spin_unlock(&local->assoc_lock); dev_dbg(&skb->dev->dev, "ASSOC RESP 0x%x received from %8phC, getting short address %04x\n", - local->assoc_status, &deaddr, local->assoc_addr); - - complete(&local->assoc_done); + resp_pl.status, &deaddr, resp_pl.short_addr); return 0; } From f576944a59f31bcffff121117ebf452c5dd162b7 Mon Sep 17 00:00:00 2001 From: Hui Su Date: Fri, 7 Aug 2026 23:09:55 +0800 Subject: [PATCH 0338/1198] staging: fbtft: make dirty_lock IRQ-safe fbtft_mkdirty() can be reached from the fbcon rendering path while processing printk() in hardirq context. Meanwhile, dirty_lock is also taken by fbtft_deferred_io() in workqueue context with local interrupts enabled. Lockdep reports a possible IRQ lock inversion involving dirty_lock and console_owner. A hardirq can interrupt a CPU holding dirty_lock and enter the console rendering path, which can attempt to acquire dirty_lock again. The following lockdep report was observed on an RK3566 system with CONFIG_PROVE_LOCKING enabled: WARNING: possible irq lock inversion dependency detected swapper/2/0 just changed the state of lock: (console_owner){-...}-{0:0} but this lock took another, HARDIRQ-unsafe lock in the past: (&par->dirty_lock){+.+.}-{2:2} CPU0 CPU1 ---- ---- lock(&par->dirty_lock); local_irq_disable(); lock(console_owner); lock(&par->dirty_lock); lock(console_owner); *** DEADLOCK *** Use spin_lock_irqsave() for fbtft_mkdirty() and spin_lock_irq() for fbtft_deferred_io(). They only access the dirty line range, so the IRQ-off regions remain short. Fixes: c296d5f9957c ("staging: fbtft: core support") Signed-off-by: Hui Su Link: https://lore.kernel.org/lkml/20260804173712.176017-1-sh_def@163.com/ Reviewed-by: Nam Cao Link: https://patch.msgid.link/20260807150953.2811933-3-sh_def@163.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/fbtft/fbtft-core.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/staging/fbtft/fbtft-core.c b/drivers/staging/fbtft/fbtft-core.c index ca0c38221c16..7925d974de80 100644 --- a/drivers/staging/fbtft/fbtft-core.c +++ b/drivers/staging/fbtft/fbtft-core.c @@ -298,14 +298,15 @@ static void fbtft_mkdirty(struct fb_info *info, int y, int height) { struct fbtft_par *par = info->par; struct fb_deferred_io *fbdefio = info->fbdefio; + unsigned long flags; /* Mark display lines/area as dirty */ - spin_lock(&par->dirty_lock); + spin_lock_irqsave(&par->dirty_lock, flags); if (y < par->dirty_lines_start) par->dirty_lines_start = y; if (y + height - 1 > par->dirty_lines_end) par->dirty_lines_end = y + height - 1; - spin_unlock(&par->dirty_lock); + spin_unlock_irqrestore(&par->dirty_lock, flags); /* Schedule deferred_io to update display (no-op if already on queue)*/ schedule_delayed_work(&info->deferred_work, fbdefio->delay); @@ -318,13 +319,13 @@ static void fbtft_deferred_io(struct fb_info *info, struct list_head *pagereflis struct fb_deferred_io_pageref *pageref; unsigned int y_low = 0, y_high = 0; - spin_lock(&par->dirty_lock); + spin_lock_irq(&par->dirty_lock); dirty_lines_start = par->dirty_lines_start; dirty_lines_end = par->dirty_lines_end; /* set display line markers as clean */ par->dirty_lines_start = par->info->var.yres - 1; par->dirty_lines_end = 0; - spin_unlock(&par->dirty_lock); + spin_unlock_irq(&par->dirty_lock); /* Mark display lines as dirty */ list_for_each_entry(pageref, pagereflist, list) { From 99aa998dec83ba180822f70e6d48a514fc81c20d Mon Sep 17 00:00:00 2001 From: Muhammad Bilal Date: Tue, 28 Jul 2026 17:54:54 +0500 Subject: [PATCH 0339/1198] staging: rtl8723bs: fix OOB read / stack overflow in rtw_get_wps_attr() rtw_get_wps_attr() walks WPS attributes inside a WPS IE taken from a wireless management frame. For each candidate attribute it only checks that the fixed 4-byte attribute header (2-byte ID + 2-byte length) fits inside the IE: if (attr_ptr + 4 > wps_ie + wps_ielen) break; u16 attr_id = get_unaligned_be16(attr_ptr); u16 attr_data_len = get_unaligned_be16(attr_ptr + 2); u16 attr_len = attr_data_len + 4; attr_data_len (and therefore attr_len) is read directly from the wire and is never checked against the remaining bytes in the IE before being used as the size of: memcpy(buf_attr, attr_ptr, attr_len); Since attr_len is fully attacker controlled (0 to 65535+4), this is both a heap OOB read of wps_ie, and, more seriously, a stack buffer overflow at several call sites where buf_attr is a single-byte stack variable, e.g. rtw_get_wps_attr_content()'s callers passing WPS_ATTR_SELECTED_REGISTRAR into a stack "u8 sr"/"u8 selected_registrar" (drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c, drivers/staging/rtl8723bs/core/rtw_mlme_ext.c). A crafted WPS IE in a beacon or probe response processed during scanning can therefore smash the stack of the parsing thread. rtw_get_wps_attr_content() itself has no independent length check and simply trusts the attr_len it gets back from rtw_get_wps_attr(), so fixing the bound here also fixes that caller. The "attr_ptr + 4 > wps_ie + wps_ielen" header check above was added by commit 1463ca3ec6601 ("staging: rtl8723bs: fix OOB reads in rtw_get_sec_ie(), rtw_get_wapi_ie(), and rtw_get_wps_attr()"), which bounded the fixed header but never extended the check to cover the variable-length attribute data that follows it. Add that missing check before attr_len is used as a memcpy() length or accepted as a match. Fixes: 554c0a3abf216 ("staging: Add rtl8723bs sdio wifi driver") Cc: stable@vger.kernel.org Signed-off-by: Muhammad Bilal Link: https://patch.msgid.link/20260728125456.32359-2-meatuni001@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8723bs/core/rtw_ieee80211.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/staging/rtl8723bs/core/rtw_ieee80211.c b/drivers/staging/rtl8723bs/core/rtw_ieee80211.c index 66f476a46aad..2a58a5cdd9f5 100644 --- a/drivers/staging/rtl8723bs/core/rtw_ieee80211.c +++ b/drivers/staging/rtl8723bs/core/rtw_ieee80211.c @@ -741,6 +741,10 @@ u8 *rtw_get_wps_attr(u8 *wps_ie, uint wps_ielen, u16 target_attr_id, u8 *buf_att u16 attr_data_len = get_unaligned_be16(attr_ptr + 2); u16 attr_len = attr_data_len + 4; + /* Reject attributes whose claimed length runs past the IE */ + if (attr_ptr + attr_len > wps_ie + wps_ielen) + break; + if (attr_id == target_attr_id) { target_attr_ptr = attr_ptr; From ff917923f4fb9c83717ba135ee47d7e4c1567bb7 Mon Sep 17 00:00:00 2001 From: Muhammad Bilal Date: Tue, 28 Jul 2026 17:54:55 +0500 Subject: [PATCH 0340/1198] staging: rtl8723bs: fix OOB read in rtw_action_frame_parse() rtw_action_frame_parse() takes a frame_len parameter but never actually checks it before indexing into the frame body: const u8 *frame_body = frame + sizeof(struct ieee80211_hdr_3addr); ... c = frame_body[0]; ... a = frame_body[1]; frame_body already points 24 bytes (sizeof(struct ieee80211_hdr_3addr)) into frame, so reading frame_body[0] and frame_body[1] requires frame_len >= 26. A management action frame shorter than that (e.g. exactly 24 bytes, the minimum a malicious peer can send) causes a 1-2 byte out-of-bounds read. This is reachable from rtw_cfg80211_monitor_if_xmit_entry() and cfg80211_rtw_mgmt_tx() in ioctl_cfg80211.c, both of which pass attacker/user-influenced frame buffers and lengths straight through. Add the missing length check before frame_body is dereferenced. Fixes: 554c0a3abf216 ("staging: Add rtl8723bs sdio wifi driver") Cc: stable@vger.kernel.org Signed-off-by: Muhammad Bilal Link: https://patch.msgid.link/20260728125456.32359-3-meatuni001@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8723bs/core/rtw_ieee80211.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/staging/rtl8723bs/core/rtw_ieee80211.c b/drivers/staging/rtl8723bs/core/rtw_ieee80211.c index 2a58a5cdd9f5..4d211711f2ba 100644 --- a/drivers/staging/rtl8723bs/core/rtw_ieee80211.c +++ b/drivers/staging/rtl8723bs/core/rtw_ieee80211.c @@ -1153,6 +1153,9 @@ int rtw_action_frame_parse(const u8 *frame, u32 frame_len, u8 *category, u8 *act u8 c; u8 a = ACT_PUBLIC_MAX; + if (frame_len < sizeof(struct ieee80211_hdr_3addr) + 2) + return false; + fc = le16_to_cpu(((struct ieee80211_hdr_3addr *)frame)->frame_control); if ((fc & (IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) != From 28a289beaf226b30b1e6e7d7b1a2946fe2d6e852 Mon Sep 17 00:00:00 2001 From: Muhammad Bilal Date: Tue, 28 Jul 2026 17:54:56 +0500 Subject: [PATCH 0341/1198] staging: rtl8723bs: fix OOB read in rtw_restruct_wmm_ie() rtw_restruct_wmm_ie() scans in_ie for a WMM IE with: while (i < in_len) { ... if (i + 5 < in_len && in_ie[i] == 0xDD && ...) { ... break; } i += (in_ie[i + 1] + 2); /* to the next IE element */ } When the "i + 5 < in_len" match check fails simply because i is within 5 bytes of the end of the buffer (i.e. no WMM IE was found near the tail of in_ie), execution falls through to "i += (in_ie[i + 1] + 2)", which reads in_ie[i + 1]. If i == in_len - 1 at that point, this is a 1-byte out-of-bounds read of an attacker-influenced IE buffer built from association/scan data. Commit a75281626fc8f ("staging: rtl8723bs: fix potential out-of-bounds read in rtw_restruct_wmm_ie") added the "i + 5 < in_len" guard to the match condition itself, but did not add an equivalent guard before the fallthrough advance, so the same class of OOB read remained reachable through the non-matching path. Add an explicit bounds check before advancing to the next IE. Fixes: 554c0a3abf216 ("staging: Add rtl8723bs sdio wifi driver") Cc: stable@vger.kernel.org Signed-off-by: Muhammad Bilal Link: https://patch.msgid.link/20260728125456.32359-4-meatuni001@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8723bs/core/rtw_mlme.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/staging/rtl8723bs/core/rtw_mlme.c b/drivers/staging/rtl8723bs/core/rtw_mlme.c index fc46b33b836a..d18768a51b19 100644 --- a/drivers/staging/rtl8723bs/core/rtw_mlme.c +++ b/drivers/staging/rtl8723bs/core/rtw_mlme.c @@ -1975,6 +1975,9 @@ int rtw_restruct_wmm_ie(struct adapter *adapter, u8 *in_ie, u8 *out_ie, uint in_ break; } + if (i + 1 >= in_len) + break; + i += (in_ie[i + 1] + 2); /* to the next IE element */ } From bc93419130bb70fabf6561e197054caae85c160c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 31 Aug 2026 08:10:27 +0000 Subject: [PATCH 0342/1198] net: bonding: annotate lockless writes with WRITE_ONCE() Several fields in bonding are read locklessly using READ_ONCE() (or ACCESS_ONCE() previously) but have corresponding writes that do not use WRITE_ONCE(). Add WRITE_ONCE() annotations to: - bond->send_peer_notif decrements in bond_peer_notify_may_events() and reset in bond_close(). - bond->slave_cnt increments and decrements in bond_enslave() and __bond_release_one(). - bond->recv_probe updates in bond_open(), bond_option_arp_interval_set() and rlb_initialize(). - slaves->count decrement in bond_skip_slave(). Fixes: 4d97480b1806 ("bonding: use local function pointer of bond->recv_probe in bond_handle_frame") Fixes: 9a72c2da690d ("bonding: fix div by zero while enslaving and transmitting") Fixes: ee6377147409 ("bonding: Simplify the xmit function for modes that use xmit_hash") Fixes: 429208aab9db ("net: bonding: add the READ_ONCE/WRITE_ONCE for outside lock accessing") Signed-off-by: Eric Dumazet Cc: Jay Vosburgh Reviewed-by: Xuanqiang Luo Reviewed-by: Hangbin Liu Link: https://patch.msgid.link/20260831081027.3209554-1-edumazet@google.com Signed-off-by: Paolo Abeni --- drivers/net/bonding/bond_alb.c | 2 +- drivers/net/bonding/bond_main.c | 14 +++++++------- drivers/net/bonding/bond_options.c | 4 ++-- 3 files changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 839f7482dc18..d2fb67a47cf9 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -875,7 +875,7 @@ static int rlb_initialize(struct bonding *bond) spin_unlock_bh(&bond->mode_lock); /* register to receive ARPs */ - bond->recv_probe = rlb_arp_recv; + WRITE_ONCE(bond->recv_probe, rlb_arp_recv); return 0; } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index ef9eb0c53c66..947d92a669b6 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1245,7 +1245,7 @@ static void bond_peer_notify_may_events(struct bonding *bond, bool force) } if (notified || force) - bond->send_peer_notif--; + WRITE_ONCE(bond->send_peer_notif, bond->send_peer_notif - 1); } /** @@ -2284,7 +2284,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, } } - bond->slave_cnt++; + WRITE_ONCE(bond->slave_cnt, bond->slave_cnt + 1); netdev_compute_master_upper_features(bond->dev, true); bond_set_carrier(bond); @@ -2533,7 +2533,7 @@ static int __bond_release_one(struct net_device *bond_dev, unblock_netpoll_tx(); synchronize_rcu(); - bond->slave_cnt--; + WRITE_ONCE(bond->slave_cnt, bond->slave_cnt - 1); if (!bond_has_slaves(bond)) { call_netdevice_notifiers(NETDEV_CHANGEADDR, bond->dev); @@ -4385,13 +4385,13 @@ static int bond_open(struct net_device *bond_dev) if (bond->params.arp_interval) { /* arp interval, in milliseconds. */ queue_delayed_work(bond->wq, &bond->arp_work, 0); - bond->recv_probe = bond_rcv_validate; + WRITE_ONCE(bond->recv_probe, bond_rcv_validate); } if (BOND_MODE(bond) == BOND_MODE_8023AD) { queue_delayed_work(bond->wq, &bond->ad_work, 0); /* register to receive LACPDUs */ - bond->recv_probe = bond_3ad_lacpdu_recv; + WRITE_ONCE(bond->recv_probe, bond_3ad_lacpdu_recv); bond_3ad_initiate_agg_selection(bond, 1); bond_for_each_slave(bond, slave, iter) @@ -4413,7 +4413,7 @@ static int bond_close(struct net_device *bond_dev) struct slave *slave; bond_work_cancel_all(bond); - bond->send_peer_notif = 0; + WRITE_ONCE(bond->send_peer_notif, 0); WRITE_ONCE(bond->recv_probe, NULL); /* Wait for any in-flight RX handlers */ @@ -5118,7 +5118,7 @@ static void bond_skip_slave(struct bond_up_slave *slaves, if (skipslave == slaves->arr[idx]) { slaves->arr[idx] = slaves->arr[slaves->count - 1]; - slaves->count--; + WRITE_ONCE(slaves->count, slaves->count - 1); break; } } diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 36b8d89387ee..9efadeff6a22 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -1147,11 +1147,11 @@ static int bond_option_arp_interval_set(struct bonding *bond, */ if (!newval->value) { if (bond->params.arp_validate) - bond->recv_probe = NULL; + WRITE_ONCE(bond->recv_probe, NULL); cancel_delayed_work_sync(&bond->arp_work); } else { /* arp_validate can be set only in active-backup mode */ - bond->recv_probe = bond_rcv_validate; + WRITE_ONCE(bond->recv_probe, bond_rcv_validate); cancel_delayed_work_sync(&bond->mii_work); queue_delayed_work(bond->wq, &bond->arp_work, 0); } From a0c798ed4103316c23938bdf625af364fbd38016 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Wed, 19 Aug 2026 12:30:05 +0200 Subject: [PATCH 0343/1198] s390/boot: Fix physical memory search range search_mem_end() calculates the number of 1MB blocks with a signed int literal. CONFIG_MAX_PHYSMEM_BITS values of 51 and above either overflow the signed int or shift beyond its width. This produces an invalid search range when the binary-search memory detection fallback is used. Use an unsigned long literal so the full supported physical address range is represented. Fixes: 54c57795e848 ("s390/mem_detect: replace tprot loop with binary search") Reviewed-by: Heiko Carstens Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/boot/physmem_info.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/boot/physmem_info.c b/arch/s390/boot/physmem_info.c index 1f2ca5435838..0ebb2174713f 100644 --- a/arch/s390/boot/physmem_info.c +++ b/arch/s390/boot/physmem_info.c @@ -141,7 +141,7 @@ static int tprot(unsigned long addr) static unsigned long search_mem_end(void) { - unsigned long range = 1 << (MAX_PHYSMEM_BITS - 20); /* in 1MB blocks */ + unsigned long range = 1UL << (MAX_PHYSMEM_BITS - 20); /* in 1MB blocks */ unsigned long offset = 0; unsigned long pivot; From d76181dfabdaa720703167393704efacba343442 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Wed, 19 Aug 2026 12:30:33 +0200 Subject: [PATCH 0344/1198] s390/boot: Avoid IPL parameter append past command line A command line may occupy all but the terminating byte of COMMAND_LINE_SIZE. In that case append_ipl_block_parm() passes a zero size to the IPL parameter conversion helpers and points the destination one byte past early_command_line. The helpers subtract one from the unsigned size and write the converted parameter outside the command line buffer. Convert the IPL parameter in the command line parsing buffer first. A parameter beginning with '=' can then replace the existing command line regardless of its length, while other parameters are appended only when space remains. Fixes: 5ecb2da660ab ("s390: support command lines longer than 896 bytes") Reviewed-by: Heiko Carstens Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/boot/ipl_parm.c | 26 ++++++++++++-------------- 1 file changed, 12 insertions(+), 14 deletions(-) diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c index 6bc950b92be7..59eabf4a2de0 100644 --- a/arch/s390/boot/ipl_parm.c +++ b/arch/s390/boot/ipl_parm.c @@ -23,6 +23,7 @@ struct parmarea parmarea __section(".parmarea") = { }; char __bootdata(early_command_line)[COMMAND_LINE_SIZE]; +static char command_line_buf[COMMAND_LINE_SIZE]; unsigned int __bootdata_preserved(zlib_dfltcc_support) = ZLIB_DFLTCC_FULL; struct ipl_parameter_block __bootdata_preserved(ipl_block); @@ -135,31 +136,29 @@ static size_t ipl_block_get_ascii_scpdata(char *dest, size_t size, static void append_ipl_block_parm(void) { - char *parm, *delim; - size_t len, rc = 0; + size_t len, extra = 0; + char *delim; len = strlen(early_command_line); - - delim = early_command_line + len; /* '\0' character position */ - parm = early_command_line + len + 1; /* append right after '\0' */ + delim = early_command_line + len; /* '\0' character position */ switch (ipl_block.pb0_hdr.pbt) { case IPL_PBT_CCW: - rc = ipl_block_get_ascii_vmparm( - parm, COMMAND_LINE_SIZE - len - 1, &ipl_block); + extra = ipl_block_get_ascii_vmparm(command_line_buf, sizeof(command_line_buf), &ipl_block); break; case IPL_PBT_FCP: case IPL_PBT_NVME: case IPL_PBT_ECKD: - rc = ipl_block_get_ascii_scpdata( - parm, COMMAND_LINE_SIZE - len - 1, &ipl_block); + extra = ipl_block_get_ascii_scpdata(command_line_buf, sizeof(command_line_buf), &ipl_block); break; } - if (rc) { - if (*parm == '=') - memmove(early_command_line, parm + 1, rc); - else + if (extra) { + if (command_line_buf[0] == '=') { + memmove(early_command_line, command_line_buf + 1, extra); + } else if (len < COMMAND_LINE_SIZE - 2) { *delim = ' '; /* replace '\0' with space */ + sized_strscpy(delim + 1, command_line_buf, COMMAND_LINE_SIZE - len - 1); + } } } @@ -245,7 +244,6 @@ static void modify_fac_list(char *str) check_cleared_facilities(); } -static char command_line_buf[COMMAND_LINE_SIZE]; void parse_boot_command_line(void) { char *param, *val; From 12373ea918a0e72483662095686556eea21d67bc Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Wed, 19 Aug 2026 12:31:10 +0200 Subject: [PATCH 0345/1198] s390/boot: Bound command line facility ranges The facilities and debug-alternative command line parsers iterate over inclusive numeric ranges. If a range ends at ULONG_MAX, incrementing the current value wraps to zero and the loop never terminates. Large finite out-of-range values also cause unnecessary early boot iterations even though the bitmap helpers ignore them. Stop each loop at the size of the bitmap it modifies. This preserves all meaningful range values while guaranteeing termination. Reviewed-by: Heiko Carstens Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/boot/alternative.c | 5 +++-- arch/s390/boot/ipl_parm.c | 2 +- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/arch/s390/boot/alternative.c b/arch/s390/boot/alternative.c index 19ea7934b918..77e8bad560c5 100644 --- a/arch/s390/boot/alternative.c +++ b/arch/s390/boot/alternative.c @@ -45,11 +45,12 @@ static void alt_debug_modify(int type, unsigned int nr, bool clear) static char *alt_debug_parse(int type, char *str) { - unsigned long val, endval; + unsigned long val, endval, limit; char *endp; bool clear; int i; + limit = type == ALT_TYPE_FACILITY ? MAX_FACILITY_BIT : MAX_MFEATURE_BIT; if (*str == ':') { str++; } else { @@ -73,7 +74,7 @@ static char *alt_debug_parse(int type, char *str) if (str == endp) break; str = endp; - while (val <= endval) { + while (val <= endval && val < limit) { alt_debug_modify(type, val, clear); val++; } diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c index 59eabf4a2de0..c1b43e5e688a 100644 --- a/arch/s390/boot/ipl_parm.c +++ b/arch/s390/boot/ipl_parm.c @@ -230,7 +230,7 @@ static void modify_fac_list(char *str) if (str == endp) break; str = endp; - while (val <= endval) { + while (val <= endval && val < MAX_FACILITY_BIT) { modify_facility(val, clear); val++; } From 33123ff9cbcb35640f56efb8ede1d6f0d97376fd Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 27 Aug 2026 12:28:32 +0200 Subject: [PATCH 0346/1198] s390/mm: Simplify crst_table_upgrade() In case of an upgrade from four to five level page tables, and a failing pgd allocation, the exit path of crst_table_upgrade() would incorrectly dereference the p4d NULL pointer via pagetable_dtor(). Address this by reworking crst_table_upgrade(), which basically is a revert of [1]. Take into account that GFP_KERNEL order-2 allocation failures are very unlikely. Therefore keep the code as simple as possible: In case of an upgrade from three to five levels, and an allocation failure of the fifth page table level, keep the upgrade to four levels instead of reverting back to three levels. This allows to keep error handling minimal. [1] commit 31932757c612 ("s390/mm: optimize page table upgrade routine") Reviewed-by: Alexander Gordeev Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/mm/pgalloc.c | 89 +++++++++++++++++------------------------- 1 file changed, 36 insertions(+), 53 deletions(-) diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index 9610770fcf6d..4b160eedc5a0 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -55,63 +55,46 @@ static void __crst_table_upgrade(void *arg) int crst_table_upgrade(struct mm_struct *mm, unsigned long end) { - unsigned long *pgd = NULL, *p4d = NULL, *__pgd; - unsigned long asce_limit = mm->context.asce_limit; + unsigned long *table, *pgd; + int rc, notify; mmap_assert_write_locked(mm); - /* upgrade should only happen from 3 to 4, 3 to 5, or 4 to 5 levels */ - VM_BUG_ON(asce_limit < _REGION2_SIZE); - - if (end <= asce_limit) - return 0; - - if (asce_limit == _REGION2_SIZE) { - p4d = crst_table_alloc(mm); - if (unlikely(!p4d)) - goto err_p4d; - crst_table_init(p4d, _REGION2_ENTRY_EMPTY); - pagetable_p4d_ctor(virt_to_ptdesc(p4d)); + VM_BUG_ON(mm->context.asce_limit < _REGION2_SIZE); + rc = 0; + notify = 0; + while (mm->context.asce_limit < end) { + table = crst_table_alloc(mm); + if (!table) { + rc = -ENOMEM; + break; + } + spin_lock_bh(&mm->page_table_lock); + pgd = (unsigned long *)mm->pgd; + if (mm->context.asce_limit == _REGION2_SIZE) { + crst_table_init(table, _REGION2_ENTRY_EMPTY); + p4d_populate(mm, (p4d_t *)table, (pud_t *)pgd); + pagetable_p4d_ctor(virt_to_ptdesc(table)); + mm->pgd = (pgd_t *)table; + mm->context.asce_limit = _REGION1_SIZE; + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_REGION2; + mm_inc_nr_puds(mm); + } else { + crst_table_init(table, _REGION1_ENTRY_EMPTY); + pgd_populate(mm, (pgd_t *)table, (p4d_t *)pgd); + pagetable_pgd_ctor(virt_to_ptdesc(table)); + mm->pgd = (pgd_t *)table; + mm->context.asce_limit = TASK_SIZE_MAX; + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_REGION1; + } + notify = 1; + spin_unlock_bh(&mm->page_table_lock); } - if (end > _REGION1_SIZE) { - pgd = crst_table_alloc(mm); - if (unlikely(!pgd)) - goto err_pgd; - crst_table_init(pgd, _REGION1_ENTRY_EMPTY); - pagetable_pgd_ctor(virt_to_ptdesc(pgd)); - } - - spin_lock_bh(&mm->page_table_lock); - - if (p4d) { - __pgd = (unsigned long *) mm->pgd; - p4d_populate(mm, (p4d_t *) p4d, (pud_t *) __pgd); - mm->pgd = (pgd_t *) p4d; - mm->context.asce_limit = _REGION1_SIZE; - mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | - _ASCE_USER_BITS | _ASCE_TYPE_REGION2; - mm_inc_nr_puds(mm); - } - if (pgd) { - __pgd = (unsigned long *) mm->pgd; - pgd_populate(mm, (pgd_t *) pgd, (p4d_t *) __pgd); - mm->pgd = (pgd_t *) pgd; - mm->context.asce_limit = TASK_SIZE_MAX; - mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | - _ASCE_USER_BITS | _ASCE_TYPE_REGION1; - } - - spin_unlock_bh(&mm->page_table_lock); - - on_each_cpu(__crst_table_upgrade, mm, 0); - - return 0; - -err_pgd: - pagetable_dtor(virt_to_ptdesc(p4d)); - crst_table_free(mm, p4d); -err_p4d: - return -ENOMEM; + if (notify) + on_each_cpu(__crst_table_upgrade, mm, 0); + return rc; } unsigned long *page_table_alloc_noprof(struct mm_struct *mm) From 98d23edcd41432286cf03672252507a841323c8c Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Tue, 25 Aug 2026 18:01:54 +0200 Subject: [PATCH 0347/1198] s390/zcrypt: Fix uninitialized padding in CRT key structure The zcrypt_type6_crt_key() function leaves padding bytes uninitialized between key components and the modulus in the CCA CRT key token. These padding bytes are sent to the crypto card, potentially leaking kernel memory contents. The initial memset() only zeros fixed structure fields, not the flexible array member key_parts[] where the padding resides. While key components are properly copied from userspace, the calculated pad_len bytes between them remain uninitialized. Fix by explicitly zeroing the padding bytes after copying the CRT key components. Signed-off-by: Harald Freudenberger Reviewed-by: Finn Callies Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- drivers/s390/crypto/zcrypt_cca_key.h | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/s390/crypto/zcrypt_cca_key.h b/drivers/s390/crypto/zcrypt_cca_key.h index f5907b67db29..8a69eed75040 100644 --- a/drivers/s390/crypto/zcrypt_cca_key.h +++ b/drivers/s390/crypto/zcrypt_cca_key.h @@ -219,6 +219,7 @@ static inline int zcrypt_type6_crt_key(struct ica_rsa_modexpo_crt *crt, void *p) copy_from_user(key->key_parts + 2 * long_len + 2 * short_len, crt->u_mult_inv, long_len)) return -EFAULT; + memset(key->key_parts + 3 * long_len + 2 * short_len, 0, pad_len); memset(key->key_parts + 3 * long_len + 2 * short_len + pad_len, 0xff, crt->inputdatalength); pub = (struct cca_public_sec *)(key->key_parts + key_len); From 148845aa1921d95ef5dc851c76e6a284f6657df6 Mon Sep 17 00:00:00 2001 From: Ben Cressey Date: Wed, 26 Aug 2026 00:25:33 +0000 Subject: [PATCH 0348/1198] dm-crypt: fix a tiny race condition in crypt_dec_pending crypt_dec_pending reads io->error before calling atomic_dec_and_test. Another context, for example crypt_endio called from an interrupt, may set io->error and drop its reference between the read and the decrement. crypt_dec_pending then drops the last reference and completes the bio with the stale status - so a read that failed and was never decrypted, or a write that failed, is reported as successful. The read was placed before the decrement by commit b35f8caa0890 ("dm crypt: wait for endio to complete before destruction"), because that commit freed dm_crypt_io before calling bio_endio. This is no longer the case, dm_crypt_io lives in the per-bio data now. Read io->error after atomic_dec_and_test instead. atomic_dec_and_test is fully ordered, so no additional barrier is needed. Fixes: b35f8caa0890 ("dm crypt: wait for endio to complete before destruction") Cc: stable@vger.kernel.org Reviewed-by: Jose Fernandez (Anthropic) Signed-off-by: Ben Cressey Assisted-by: Claude:unspecified Signed-off-by: Mikulas Patocka --- drivers/md/dm-crypt.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 608b617fb817..9e170de50ad3 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1745,7 +1745,6 @@ static void crypt_dec_pending(struct dm_crypt_io *io) { struct crypt_config *cc = io->cc; struct bio *base_bio = io->base_bio; - blk_status_t error = io->error; if (!atomic_dec_and_test(&io->io_pending)) return; @@ -1767,7 +1766,7 @@ static void crypt_dec_pending(struct dm_crypt_io *io) else kfree(io->integrity_metadata); - base_bio->bi_status = error; + base_bio->bi_status = io->error; bio_endio(base_bio); } From bc9781c0247de107876f32929f1637db93a42b34 Mon Sep 17 00:00:00 2001 From: Benjamin Marzinski Date: Tue, 25 Aug 2026 15:22:26 -0400 Subject: [PATCH 0349/1198] dm cache: fix issue with background work locking dm cache used a rw_semaphore for background_work_lock. Write locks on rw_semaphores have strict owner semantics, but there was no guarantee that the process that locked background_work_lock was the same process that unlocked it. This can be easily seen using a kernel compiled with CONFIG_DEBUG_RWSEMS. Given a dm cache device , run: 'dmsetup suspend && dmsetup resume '. This will trigger a kernel warning: DEBUG_RWSEMS_WARN_ON((rwsem_owner(sem) != current) && !rwsem_test_oflags(sem, RWSEM_NONSPINNABLE)) triggered by cache_resume(). To fix this, switch from a rw_semaphore to a spinlock and a wait queue. dm cache already has a wait queue and associated counter, migration_wait and nr_allocated_migrations, that was getting woken up when background work was getting completed, but wasn't actually used by anything. This is replaced by the background_work queue and counter. Fixes: b29d4986d0da ("dm cache: significant rework to leverage dm-bio-prison-v2") Cc: stable@vger.kernel.org Signed-off-by: Benjamin Marzinski Reviewed-by: Matthew Sakai Reviewed-by: Ming-Hung Tsai Signed-off-by: Mikulas Patocka --- drivers/md/dm-cache-target.c | 55 ++++++++++++++++++------------------ 1 file changed, 28 insertions(+), 27 deletions(-) diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 33dbc71b730f..d8d9c63d2a67 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -340,8 +340,6 @@ struct cache { struct list_head invalidation_requests; sector_t migration_threshold; - wait_queue_head_t migration_wait; - atomic_t nr_allocated_migrations; /* * The number of in flight migrations that are performing @@ -397,7 +395,11 @@ struct cache { bool loaded_mappings:1; bool loaded_discards:1; - struct rw_semaphore background_work_lock; + /* background work management */ + bool background_work_allowed; + unsigned background_work_nr; + spinlock_t background_work_lock; + wait_queue_head_t background_work_wait; struct batcher committer; struct work_struct commit_ws; @@ -488,19 +490,13 @@ static struct dm_cache_migration *alloc_migration(struct cache *cache) memset(mg, 0, sizeof(*mg)); mg->cache = cache; - atomic_inc(&cache->nr_allocated_migrations); return mg; } static void free_migration(struct dm_cache_migration *mg) { - struct cache *cache = mg->cache; - - if (atomic_dec_and_test(&cache->nr_allocated_migrations)) - wake_up(&cache->migration_wait); - - mempool_free(mg, &cache->migration_pool); + mempool_free(mg, &mg->cache->migration_pool); } /*----------------------------------------------------------------*/ @@ -1030,34 +1026,39 @@ static void calc_discard_block_range(struct cache *cache, struct bio *bio, static void prevent_background_work(struct cache *cache) { - lockdep_off(); - down_write(&cache->background_work_lock); - lockdep_on(); + spin_lock_irq(&cache->background_work_lock); + cache->background_work_allowed = false; + wait_event_lock_irq(cache->background_work_wait, + cache->background_work_nr == 0, + cache->background_work_lock); + spin_unlock_irq(&cache->background_work_lock); } static void allow_background_work(struct cache *cache) { - lockdep_off(); - up_write(&cache->background_work_lock); - lockdep_on(); + spin_lock_irq(&cache->background_work_lock); + cache->background_work_allowed = true; + spin_unlock_irq(&cache->background_work_lock); } static bool background_work_begin(struct cache *cache) { bool r; - lockdep_off(); - r = down_read_trylock(&cache->background_work_lock); - lockdep_on(); - + spin_lock_irq(&cache->background_work_lock); + r = cache->background_work_allowed; + if (r) + cache->background_work_nr++; + spin_unlock_irq(&cache->background_work_lock); return r; } static void background_work_end(struct cache *cache) { - lockdep_off(); - up_read(&cache->background_work_lock); - lockdep_on(); + spin_lock_irq(&cache->background_work_lock); + if (--cache->background_work_nr == 0) + wake_up(&cache->background_work_wait); + spin_unlock_irq(&cache->background_work_lock); } /*----------------------------------------------------------------*/ @@ -2507,9 +2508,7 @@ static int cache_create(struct cache_args *ca, struct cache **result) spin_lock_init(&cache->lock); bio_list_init(&cache->deferred_bios); - atomic_set(&cache->nr_allocated_migrations, 0); atomic_set(&cache->nr_io_migrations, 0); - init_waitqueue_head(&cache->migration_wait); r = -ENOMEM; atomic_set(&cache->nr_dirty, 0); @@ -2592,8 +2591,10 @@ static int cache_create(struct cache_args *ca, struct cache **result) issue_op, cache, cache->wq); dm_iot_init(&cache->tracker); - init_rwsem(&cache->background_work_lock); - prevent_background_work(cache); + init_waitqueue_head(&cache->background_work_wait); + spin_lock_init(&cache->background_work_lock); + cache->background_work_allowed = false; + cache->background_work_nr = 0; *result = cache; return 0; From b2fd92f016e9d692fd3c8c08d0ee014e9212279d Mon Sep 17 00:00:00 2001 From: Chen Cheng Date: Mon, 24 Aug 2026 19:34:49 +0800 Subject: [PATCH 0350/1198] dm-integrity: require stable writes for internal hash modes dm-integrity direct, bitmap and inline internal-hash modes compute integrity tags from the pages carried by the write bio. The lower data write also uses those pages, so the tag and the data write depend on the same memory contents staying unchanged while writeback is in flight. Without stable writes, a buffered writer can modify a writeback folio after dm-integrity has submitted the data bio and before the lower device has consumed the data. After a crash, this can leave data from the later contents with a tag calculated from the earlier contents, causing permanent checksum failures on read. Set BLK_FEAT_STABLE_WRITES for internal-hash D, B and I modes so filesystems wait for writeback folios to become stable before modifying them again. Journal mode is left unchanged because it copies data into the journal before computing and persisting the tag. Tested using dm-delay over a virtio-blk test disk, dm-integrity internal_hash:crc32c and no-journal ext4. The D and B reproducers both failed with checksum errors before this change and completed with READ_RC=0 and zero mismatches after it. Fixes: 7eada909bfd7 ("dm: add integrity target") Cc: stable@vger.kernel.org Reported-by: Sun Yangkai Link: https://github.com/chencheng-fnnas/reproducer/blob/main/dm-integrity-writeback-race.py Signed-off-by: Chen Cheng Signed-off-by: Mikulas Patocka --- drivers/md/dm-integrity.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index c50feaa98bf9..0370d7d7ce72 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -4130,6 +4130,10 @@ static void dm_integrity_io_hints(struct dm_target *ti, struct queue_limits *lim limits->dma_alignment = limits->logical_block_size - 1; limits->discard_granularity = ic->sectors_per_block << SECTOR_SHIFT; + if (ic->internal_hash && + (ic->mode == 'D' || ic->mode == 'B' || ic->mode == 'I')) + limits->features |= BLK_FEAT_STABLE_WRITES; + if (!ic->internal_hash) { struct blk_integrity *bi = &limits->integrity; From 59e6f919d77d72ec79cbf171256f2f7819737580 Mon Sep 17 00:00:00 2001 From: Ben Cressey Date: Thu, 20 Aug 2026 21:44:57 +0000 Subject: [PATCH 0351/1198] dm-integrity: fix buffer overflow with keyed discard Since commit 68c5c42567bc ("dm-integrity: replace forgeable discard filler with a keyed sector marker"), integrity_metadata computes a checksum for every discarded block into the "checksums" buffer. integrity_sector_checksum always writes the whole digest. So if the tag size is smaller than the digest size, the checksum of the last block that fits into the buffer is written past the end of it. For example, with hmac(sha256) and tag size 16, a 4MiB discard writes 16 bytes past the kmalloc'ed page. Fix this by subtracting extra_space from the buffer size when computing max_blocks, like we do for writes. Fixes: 68c5c42567bc ("dm-integrity: replace forgeable discard filler with a keyed sector marker") Reviewed-by: Jose Fernandez (Anthropic) Signed-off-by: Ben Cressey Assisted-by: Claude:unspecified Signed-off-by: Mikulas Patocka --- drivers/md/dm-integrity.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 0370d7d7ce72..d4fe85d61d33 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -1980,7 +1980,7 @@ static void integrity_metadata(struct work_struct *w) if (unlikely(dio->op == REQ_OP_DISCARD)) { unsigned int bi_size = dio->bio_details.bi_iter.bi_size; unsigned int max_size = likely(checksums != checksums_onstack) ? PAGE_SIZE : HASH_MAX_DIGESTSIZE; - unsigned int max_blocks = max_size / ic->tag_size; + unsigned int max_blocks = (max_size - extra_space) / ic->tag_size; sector_t sector = dio->range.logical_sector; if (!ic->discard_keyed) From 18d80c77b4c7dd20699e81cedfbbff4e9d198f28 Mon Sep 17 00:00:00 2001 From: Ben Cressey Date: Thu, 20 Aug 2026 21:44:58 +0000 Subject: [PATCH 0352/1198] dm-integrity: fix infinite loop on discard with large tag size When integrity_metadata handles a discard, it fills a buffer with DISCARD_FILLER and writes it over the tags, max_blocks blocks at a time. If the kmalloc fails, the buffer is the on-stack array checksums_onstack and max_size is set to HASH_MAX_DIGESTSIZE. So if the tag size is larger than HASH_MAX_DIGESTSIZE, max_blocks is zero, bi_size is never decremented and the loop never terminates. Fix this by using sizeof(checksums_onstack) as max_size. The array has MAX_TAG_SIZE bytes since commit b93b6643e9b5 ("dm integrity: fix a crash with unusually large tag size"), so max_blocks is at least 1. Fixes: 84597a44a9d8 ("dm integrity: add optional discard support") Cc: stable@vger.kernel.org Reviewed-by: Jose Fernandez (Anthropic) Signed-off-by: Ben Cressey Assisted-by: Claude:unspecified Signed-off-by: Mikulas Patocka --- drivers/md/dm-integrity.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index d4fe85d61d33..5327d7c6a71c 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -1979,7 +1979,7 @@ static void integrity_metadata(struct work_struct *w) if (unlikely(dio->op == REQ_OP_DISCARD)) { unsigned int bi_size = dio->bio_details.bi_iter.bi_size; - unsigned int max_size = likely(checksums != checksums_onstack) ? PAGE_SIZE : HASH_MAX_DIGESTSIZE; + unsigned int max_size = likely(checksums != checksums_onstack) ? PAGE_SIZE : sizeof(checksums_onstack); unsigned int max_blocks = (max_size - extra_space) / ic->tag_size; sector_t sector = dio->range.logical_sector; From 1d2929d0850fff683b8aff051275945e65f082c8 Mon Sep 17 00:00:00 2001 From: Norbert Szetei Date: Sat, 29 Aug 2026 18:56:18 +0200 Subject: [PATCH 0353/1198] net: psp: do not inherit the Rx association on clone sk->psp_assoc sits past sk_dontcopy_end, so sock_copy() copies it into every socket accepted from a listener without taking a reference, while inet_sock_destruct() puts for every inet socket. psp_twsk_init() does refcount_inc() for the timewait socket, so a child closing through TIME_WAIT cancels its own put and leaves the association with one reference and N timewait sockets holding the same pointer. Closing the listener frees it, and the timewait timers then put freed memory. Rejecting the association on a listening socket is not sufficient: a socket can acquire one while established and then be turned back into a listener, because tcp_disconnect() leaves sk->psp_assoc in place. BUG: KASAN: slab-use-after-free in psp_twsk_assoc_free+0x6f/0xf0 Write of size 4 at addr ffff888110f9255c by task swapper/7/0 psp_twsk_assoc_free+0x6f/0xf0 inet_twsk_put+0xda/0x1b0 call_timer_fn+0x53/0x2e0 __run_timers+0x764/0xa80 Freed by task 99: kfree+0x1a7/0x500 process_one_work+0x7ec/0x1100 An association carries a per-connection SPI and key, so a child must not inherit the parent's. Clear it on clone. Fixes: 6b46ca260e22 ("net: psp: add socket security association code") Cc: stable@vger.kernel.org Assisted-by: Claude:claude-opus-5 Signed-off-by: Norbert Szetei Reviewed-by: Daniel Zahka Link: https://patch.msgid.link/BC10EB92-ABB3-41B2-AB16-266BEEBE18C0@doyensec.com Signed-off-by: Paolo Abeni --- net/core/sock.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/core/sock.c b/net/core/sock.c index 1ad41904db25..fa60b7494c58 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2494,6 +2494,9 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority, #ifdef CONFIG_BPF_SYSCALL RCU_INIT_POINTER(newsk->sk_bpf_storage, NULL); #endif +#if IS_ENABLED(CONFIG_INET_PSP) + RCU_INIT_POINTER(newsk->psp_assoc, NULL); +#endif /* SANITY */ if (likely(newsk->sk_net_refcnt)) { From 2ccb8878c149443c6acf628b438c9c942c20abb2 Mon Sep 17 00:00:00 2001 From: Ming-Hung Tsai Date: Tue, 18 Aug 2026 18:05:47 +0800 Subject: [PATCH 0354/1198] dm cache: fix demotion stats in passthrough mode The demotion counter is incremented per incoming write bio before the invalidation begins, causing the demotion count to exceed the actual number of cached blocks when multiple bios target the same cached block. Additionally, the counter is incremented unconditionally regardless of invalidation failure. Reproduce steps: 1. Create a cache device consisting of 512 cache entries modprobe brd rd_size=262144 dmsetup create cmeta --table "0 8192 linear /dev/ram0 0" dmsetup create cdata --table "0 65536 linear /dev/ram0 8192" dmsetup create corig --table "0 65536 linear /dev/ram0 262144" dd if=/dev/zero of=/dev/mapper/cmeta bs=4k count=1 oflag=direct dmsetup create cache --table "0 65536 cache /dev/mapper/cmeta \ /dev/mapper/cdata /dev/mapper/corig 128 2 metadata2 writethrough smq 0" 2. Populate the cache, and record the number of cached blocks fio --name=populate --filename=/dev/mapper/cache --rw=randwrite --bs=4k \ --direct=1 --ioengine=libaio --iodepth=32 --io_size=2048m nr_cached=$(dmsetup status cache | awk '{split($7, a, "/"); print a[1]}') 3. Reload the cache into passthrough mode dmsetup suspend cache dmsetup reload cache --table "0 65536 cache /dev/mapper/cmeta \ /dev/mapper/cdata /dev/mapper/corig 128 2 metadata2 passthrough smq 0" dmsetup resume cache 4. Write to the passthrough cache with multiple jobs to trigger multiple bios hitting the same cached block. fio --filename=/dev/mapper/cache --name=test --rw=write --bs=4k \ --direct=1 --ioengine=libaio --iodepth=32 --numjobs=4 5. Check if demoted matches cached block count. These numbers should match but may differ due to overcounting per bio. nr_demoted=$(dmsetup status cache | awk '{print $12}') echo "$nr_cached, $nr_demoted" Fix by moving the demotion counter increment into invalidate_complete(), gated on the success flag. Reported-by: Ben Marzinski Fixes: b29d4986d0da ("dm cache: significant rework to leverage dm-bio-prison-v2") Cc: stable@vger.kernel.org Signed-off-by: Ming-Hung Tsai Reviewed-by: Benjamin Marzinski Signed-off-by: Mikulas Patocka --- drivers/md/dm-cache-target.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index d8d9c63d2a67..1a5072425c4a 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -1463,6 +1463,9 @@ static void invalidate_complete(struct dm_cache_migration *mg, bool success) struct bio_list bios; struct cache *cache = mg->cache; + if (success) + atomic_inc(&cache->stats.demotion); + bio_list_init(&bios); if (mg->cell) { if (dm_cell_unlock_v2(cache->prison, mg->cell, &bios)) @@ -1734,7 +1737,6 @@ static int map_bio(struct cache *cache, struct bio *bio, dm_oblock_t block, if (passthrough_mode(cache)) { if (bio_data_dir(bio) == WRITE) { bio_drop_shared_lock(cache, bio); - atomic_inc(&cache->stats.demotion); invalidate_start(cache, cblock, block, bio); return DM_MAPIO_SUBMITTED; } else From cc7cd2a9228175c975f62ad56ed7c767701cb4fa Mon Sep 17 00:00:00 2001 From: Muhammad Bilal Date: Tue, 1 Sep 2026 16:30:31 +0500 Subject: [PATCH 0355/1198] staging: sm750fb: fix mono image source stride mismatch in lynxfb_ops_imageblit() sm750_hw_imageblit() advances its monochrome source pointer by src_delta per scanline, and computes the correct rounded-up stride internally as: bytes_per_scan = (width + start_bit + 7) / 8; Its only caller, lynxfb_ops_imageblit(), instead passed src_delta as image->width >> 3. For widths not a multiple of 8 this under-counted the stride, so the source pointer fell further behind the real per-scanline layout on every line, corrupting the rendered image. Rather than just fixing the caller's calculation, remove src_delta as a parameter entirely and have sm750_hw_imageblit() advance by the bytes_per_scan it already computes for itself. There has only ever been one caller, and that caller was passing an out-of-sync derivative of the same width/start_bit values sm750_hw_imageblit() already has, so keeping stride as a separate parameter served no purpose beyond letting the two calculations drift apart, which is exactly what happened here. Rounding up, rather than down, is the direction consistent with the rest of the fbdev core: struct fb_image mono bitmap data (the same image->data this driver receives) is walked elsewhere with byte strides derived from a ceiling division of width by 8. The generic mono bit iterator in drivers/video/fbdev/core/fb_imageblit.h advances scanlines with "iter->data += BITS_TO_BYTES(iter->width)", and BITS_TO_BYTES() (include/linux/bitops.h) is a ceiling division. sm750_hw_imageblit()'s own "(width + start_bit + 7) / 8" is that same ceiling division with an added start_bit offset, so the caller's ">> 3" (floor) was the one calculation out of step with how this data layout is handled everywhere else. Found by code review of sm750_hw_imageblit()'s internal stride calculation against what its only caller was passing in, and confirmed with a clean -Werror build. I do not have this hardware, so this has not been exercised at runtime on real sm750 silicon. Fixes: 81dee67e215b2 ("staging: sm750fb: add sm750 to staging") Cc: stable@vger.kernel.org Reviewed-by: Dan Carpenter Signed-off-by: Muhammad Bilal Link: https://patch.msgid.link/20260901113031.161610-1-meatuni001@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/sm750fb/sm750.c | 2 +- drivers/staging/sm750fb/sm750.h | 2 +- drivers/staging/sm750fb/sm750_accel.c | 6 ++---- drivers/staging/sm750fb/sm750_accel.h | 4 +--- 4 files changed, 5 insertions(+), 9 deletions(-) diff --git a/drivers/staging/sm750fb/sm750.c b/drivers/staging/sm750fb/sm750.c index 039e2033f84e..8b93bfeb217b 100644 --- a/drivers/staging/sm750fb/sm750.c +++ b/drivers/staging/sm750fb/sm750.c @@ -252,7 +252,7 @@ static void lynxfb_ops_imageblit(struct fb_info *info, spin_lock(&sm750_dev->slock); sm750_dev->accel.de_imageblit(&sm750_dev->accel, - image->data, image->width >> 3, 0, + image->data, 0, base, pitch, bpp, image->dx, image->dy, image->width, image->height, diff --git a/drivers/staging/sm750fb/sm750.h b/drivers/staging/sm750fb/sm750.h index 89a61bf80779..fd1cf9eb5797 100644 --- a/drivers/staging/sm750fb/sm750.h +++ b/drivers/staging/sm750fb/sm750.h @@ -64,7 +64,7 @@ struct lynx_accel { u32 rop2); int (*de_imageblit)(struct lynx_accel *accel, const char *p_srcbuf, - u32 src_delta, u32 start_bit, u32 d_base, u32 d_pitch, + u32 start_bit, u32 d_base, u32 d_pitch, u32 byte_per_pixel, u32 dx, u32 dy, u32 width, u32 height, u32 f_color, u32 b_color, u32 rop2); diff --git a/drivers/staging/sm750fb/sm750_accel.c b/drivers/staging/sm750fb/sm750_accel.c index 0316ea69d009..bac9a209899c 100644 --- a/drivers/staging/sm750fb/sm750_accel.c +++ b/drivers/staging/sm750fb/sm750_accel.c @@ -288,8 +288,6 @@ static unsigned int de_get_transparency(struct lynx_accel *accel) * sm750_hw_imageblit * @accel: Acceleration device data * @src_buf: pointer to start of source buffer in system memory - * @src_delta: Pitch value (in bytes) of the source buffer, +ive means top down - * and -ive mean button up * @start_bit: Mono data can start at any bit in a byte, this value should be * 0 to 7 * @dest_base: Address of destination: offset in frame buffer @@ -304,7 +302,7 @@ static unsigned int de_get_transparency(struct lynx_accel *accel) * @rop2: ROP value */ int sm750_hw_imageblit(struct lynx_accel *accel, const char *src_buf, - u32 src_delta, u32 start_bit, u32 dest_base, u32 dest_pitch, + u32 start_bit, u32 dest_base, u32 dest_pitch, u32 byte_per_pixel, u32 dx, u32 dy, u32 width, u32 height, u32 fg_color, u32 bg_color, u32 rop2) { @@ -395,7 +393,7 @@ int sm750_hw_imageblit(struct lynx_accel *accel, const char *src_buf, write_dp_port(accel, *(unsigned int *)remain); } - src_buf += src_delta; + src_buf += bytes_per_scan; } return 0; diff --git a/drivers/staging/sm750fb/sm750_accel.h b/drivers/staging/sm750fb/sm750_accel.h index 617885431661..efceefaaafb0 100644 --- a/drivers/staging/sm750fb/sm750_accel.h +++ b/drivers/staging/sm750fb/sm750_accel.h @@ -220,8 +220,6 @@ int sm750_hw_copyarea(struct lynx_accel *accel, /** * sm750_hw_imageblit * @src_buf: pointer to start of source buffer in system memory - * @src_delta: Pitch value (in bytes) of the source buffer, +ive means top down - *>----- and -ive mean button up * @start_bit: Mono data can start at any bit in a byte, this value should be *>----- 0 to 7 * @dest_base: Address of destination: offset in frame buffer @@ -236,7 +234,7 @@ int sm750_hw_copyarea(struct lynx_accel *accel, * @rop2: ROP value */ int sm750_hw_imageblit(struct lynx_accel *accel, const char *src_buf, - u32 src_delta, u32 start_bit, u32 dest_base, u32 dest_pitch, + u32 start_bit, u32 dest_base, u32 dest_pitch, u32 byte_per_pixel, u32 dx, u32 dy, u32 width, u32 height, u32 fg_color, u32 bg_color, u32 rop2); From 67bfe48a29fbddfff77e13d4d327e49fca2c2be5 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Tue, 25 Aug 2026 11:55:11 +0200 Subject: [PATCH 0356/1198] HID: bpf: mark struct hid_device as safe BPF pointer Commit ee9ad135b208 ("bpf: Reject a store through a fault prone pointer") in the BPF tree makes the verifier reject any writes to hid_device->{name,uniq,phys}. A simple solution is to mark the struct hid_device as safe from a BPF point of view. Suggested-by: Daniel Borkmann Signed-off-by: Benjamin Tissoires --- drivers/hid/bpf/hid_bpf_struct_ops.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/hid/bpf/hid_bpf_struct_ops.c b/drivers/hid/bpf/hid_bpf_struct_ops.c index 702c22fae136..56c53aca4511 100644 --- a/drivers/hid/bpf/hid_bpf_struct_ops.c +++ b/drivers/hid/bpf/hid_bpf_struct_ops.c @@ -62,6 +62,10 @@ struct hid_bpf_offset_write_range { u32 end; }; +struct hid_bpf_ctx__safe_trusted { + struct hid_device *hid; +}; + static int hid_bpf_ops_btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size) @@ -86,6 +90,8 @@ static int hid_bpf_ops_btf_struct_access(struct bpf_verifier_log *log, const char *cur = NULL; int i; + BTF_TYPE_EMIT(struct hid_bpf_ctx__safe_trusted); + t = btf_type_by_id(reg->btf, reg->btf_id); for (i = 0; i < ARRAY_SIZE(write_ranges); i++) { From 1fb68c2e76386ac663819036c2c75cd476e433c1 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Tue, 25 Aug 2026 11:55:12 +0200 Subject: [PATCH 0357/1198] selftests/hid: Add a test to ensure we can write fields in hid_device hid_device->{name,uniq,phys} are all writeable fields, we need to have tests for them in case the verifier becomes too much strict. Signed-off-by: Benjamin Tissoires --- tools/testing/selftests/hid/hid_bpf.c | 26 +++++++++++++++++++ tools/testing/selftests/hid/progs/hid.c | 26 +++++++++++++++++++ .../selftests/hid/progs/hid_bpf_helpers.h | 3 +++ 3 files changed, 55 insertions(+) diff --git a/tools/testing/selftests/hid/hid_bpf.c b/tools/testing/selftests/hid/hid_bpf.c index b851339308c2..069ebdbb4d1c 100644 --- a/tools/testing/selftests/hid/hid_bpf.c +++ b/tools/testing/selftests/hid/hid_bpf.c @@ -909,6 +909,32 @@ TEST_F(hid_bpf, test_rdesc_fixup_get_data_overflow) ASSERT_EQ(self->skel->bss->get_data_overflow_check, 1); } +TEST_F(hid_bpf, test_rdesc_fixup_change_uniq_name_phys) +{ + const struct test_program progs[] = { + { .name = "hid_rdesc_fixup_change_uniq_name_phys" }, + }; + char expected[256], buf[256] = {}; + int err; + + LOAD_PROGRAMS(progs); + + err = ioctl(self->hidraw_fd, HIDIOCGRAWNAME(sizeof(buf)), buf); + ASSERT_GE(err, 0) TH_LOG("HIDIOCGRAWNAME"); + ASSERT_STREQ("name coming from bpf", buf); + + snprintf(expected, sizeof(expected), "%d phys:coming:from:bpf", self->hid.dev_id); + + err = ioctl(self->hidraw_fd, HIDIOCGRAWPHYS(sizeof(buf)), buf); + ASSERT_GE(err, 0) TH_LOG("HIDIOCGRAWPHYS"); + ASSERT_STREQ(expected, buf); + + err = ioctl(self->hidraw_fd, HIDIOCGRAWUNIQ(sizeof(buf)), buf); + ASSERT_GE(err, 0) TH_LOG("HIDIOCGRAWUNIQ"); + ASSERT_STREQ("uniq:coming:from:bpf", buf); + +} + static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va_list args) { diff --git a/tools/testing/selftests/hid/progs/hid.c b/tools/testing/selftests/hid/progs/hid.c index b21fbb13c926..361dc7eaad22 100644 --- a/tools/testing/selftests/hid/progs/hid.c +++ b/tools/testing/selftests/hid/progs/hid.c @@ -255,6 +255,32 @@ struct hid_bpf_ops rdesc_fixup_get_data_overflow = { .hid_rdesc_fixup = (void *)hid_rdesc_fixup_get_data_overflow, }; +SEC("?struct_ops.s/hid_rdesc_fixup") +int BPF_PROG(hid_rdesc_fixup_change_uniq_name_phys, struct hid_bpf_ctx *hid_ctx) +{ +#define HID_BPF_MEMCPY(target, str) \ + __builtin_memcpy(target, str, sizeof(str)) + + HID_BPF_MEMCPY(hid_ctx->hid->name, "name coming from bpf"); + HID_BPF_MEMCPY(hid_ctx->hid->uniq, "uniq:coming:from:bpf"); + /* hid_bpf relies on a phys being a rand % 1024 */ + for (int i = 0; i < 5; i++) { + if (!hid_ctx->hid->phys[i]) { + HID_BPF_MEMCPY(hid_ctx->hid->phys + i, " phys:coming:from:bpf"); + break; + } + } + +#undef HID_BPF_MEMCPY + + return 0; +} + +SEC(".struct_ops.link") +struct hid_bpf_ops rdesc_fixup_change_uniq_name_phys = { + .hid_rdesc_fixup = (void *)hid_rdesc_fixup_change_uniq_name_phys, +}; + SEC("?struct_ops/hid_device_event") int BPF_PROG(hid_test_insert1, struct hid_bpf_ctx *hid_ctx, enum hid_report_type type) { diff --git a/tools/testing/selftests/hid/progs/hid_bpf_helpers.h b/tools/testing/selftests/hid/progs/hid_bpf_helpers.h index cdca912f3afd..05698793762a 100644 --- a/tools/testing/selftests/hid/progs/hid_bpf_helpers.h +++ b/tools/testing/selftests/hid/progs/hid_bpf_helpers.h @@ -61,6 +61,9 @@ enum hid_report_type { struct hid_device { unsigned int id; + char name[128]; + char phys[64]; + char uniq[64]; } __attribute__((preserve_access_index)); struct bpf_wq { From ce58f5a1843235d800ad724e86a3cf5c9c6f08ab Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Tue, 25 Aug 2026 11:55:13 +0200 Subject: [PATCH 0358/1198] selftests/hid: prepare test_rdesc_fixup_get_data_overflow for the new verifier The new verifier in the bpf-next branch is now capable of detecting the overflow that was triggered by test_rdesc_fixup_get_data_overflow. This is better in terms of UI, but now the test is failing and should be marked as expected to fail. Add a new parameter to load_programs() when we expect the test to fail, and dynamically validate the test by checkcing if it loads (it should fail to load with new verifier), but if it still loads, HID-BPF should detect the overflow itself and return an error in hid_bpf_get_data(). Signed-off-by: Benjamin Tissoires --- tools/testing/selftests/hid/hid_bpf.c | 25 +++++++++++++++++-------- 1 file changed, 17 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/hid/hid_bpf.c b/tools/testing/selftests/hid/hid_bpf.c index 069ebdbb4d1c..7ab86296ff23 100644 --- a/tools/testing/selftests/hid/hid_bpf.c +++ b/tools/testing/selftests/hid/hid_bpf.c @@ -67,14 +67,17 @@ struct test_program { int insert_head; }; #define LOAD_PROGRAMS(progs) \ - load_programs(progs, ARRAY_SIZE(progs), _metadata, self, variant) + load_programs(progs, ARRAY_SIZE(progs), false, _metadata, self, variant) +#define LOAD_PROGRAMS_MAY_FAIL(progs) \ + load_programs(progs, ARRAY_SIZE(progs), true, _metadata, self, variant) #define LOAD_BPF \ - load_programs(NULL, 0, _metadata, self, variant) -static void load_programs(const struct test_program programs[], - const size_t progs_count, - struct __test_metadata *_metadata, - FIXTURE_DATA(hid_bpf) * self, - const FIXTURE_VARIANT(hid_bpf) * variant) + load_programs(NULL, 0, false, _metadata, self, variant) +static int load_programs(const struct test_program programs[], + const size_t progs_count, + bool load_may_fail, + struct __test_metadata *_metadata, + FIXTURE_DATA(hid_bpf) * self, + const FIXTURE_VARIANT(hid_bpf) * variant) { struct bpf_map *iter_map; int err = -EINVAL; @@ -128,6 +131,9 @@ static void load_programs(const struct test_program programs[], } err = hid__load(self->skel); + if (err && load_may_fail) + return err; + ASSERT_OK(err) TH_LOG("hid_skel_load failed: %d", err); for (int i = 0; i < progs_count; i++) { @@ -147,6 +153,7 @@ static void load_programs(const struct test_program programs[], self->hidraw_fd = open_hidraw(&self->hid); ASSERT_GE(self->hidraw_fd, 0) TH_LOG("open_hidraw"); + return 0; } /* @@ -904,7 +911,9 @@ TEST_F(hid_bpf, test_rdesc_fixup_get_data_overflow) { .name = "hid_rdesc_fixup_get_data_overflow" }, }; - LOAD_PROGRAMS(progs); + /* newer verifier can detect the overflow at load time */ + if (LOAD_PROGRAMS_MAY_FAIL(progs)) + return; ASSERT_EQ(self->skel->bss->get_data_overflow_check, 1); } From 2430eb81e44111b30eeb5273bbcf8b24ca517ef9 Mon Sep 17 00:00:00 2001 From: Griffin Kroah-Hartman Date: Wed, 19 Aug 2026 12:04:25 +0200 Subject: [PATCH 0359/1198] usb: image: mdc800: change kmalloc() to kzalloc() Change the kmalloc() calls in usb_mdc800_init() for irq_urb_buffer and download_urb_buffer to kzalloc(), avoiding potential stack leaks if a shorter message is received in mdc800_usb_irq() and mdc800_usb_download_notify() Assisted-by: gkh_clanker_t1000 Cc: stable Signed-off-by: Griffin Kroah-Hartman Link: https://patch.msgid.link/20260819-usb_misc_random-v1-1-43a0dcee3a32@kroah.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/image/mdc800.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/usb/image/mdc800.c b/drivers/usb/image/mdc800.c index ca287b770e8c..f7caa1c5cbb7 100644 --- a/drivers/usb/image/mdc800.c +++ b/drivers/usb/image/mdc800.c @@ -1000,13 +1000,13 @@ static int __init usb_mdc800_init (void) mdc800->downloaded = 0; mdc800->written = 0; - mdc800->irq_urb_buffer=kmalloc (8, GFP_KERNEL); + mdc800->irq_urb_buffer=kzalloc (8, GFP_KERNEL); if (!mdc800->irq_urb_buffer) goto cleanup_on_fail; mdc800->write_urb_buffer=kmalloc (8, GFP_KERNEL); if (!mdc800->write_urb_buffer) goto cleanup_on_fail; - mdc800->download_urb_buffer=kmalloc (64, GFP_KERNEL); + mdc800->download_urb_buffer=kzalloc (64, GFP_KERNEL); if (!mdc800->download_urb_buffer) goto cleanup_on_fail; From dea99705bc8fcda12590cfeeae6d2ba47a7ef572 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Mon, 17 Aug 2026 20:22:39 +0200 Subject: [PATCH 0360/1198] usb: typec: mux: Fix typec_switch_match() The fwnode_typec_switch_get() sporadically returns NULL instead of an -EPROBE_DEFER for orientation-switch described in DT. This makes it impossible to discern whether the DT does describe an orientation-switch which did not probe yet, or whether the DT does not describe the switch. This happens with gpio-sbu-mux connected to an I2C GPIO expander. The class_find_device() on typec_switch_match() may return NULL in case the mux did not probe just yet early on boot. The sw_devs[] array can be empty on boot as well. If these two conditions occur, then the conditional if (to_typec_switch_dev(dev) == sw_devs[i]) evaluates to true and the match function returns NULL, which propagates to fwnode_typec_switch_get() which makes it look as if the orientation-switch was not described in DT. This is incorrect, because the mux driver will probe a bit later on, but at that point, the caller of fwnode_typec_switch_get() already got the NULL return value. The NULL return value also does not trigger IS_ERR(), therefore the caller driver interprets this as if the orientation-switch is not described in DT, and does not return -EPROBE_DEFER to try again, even if it should. Fix this by checking the class_find_device() return value, and return -EPROBE_DEFER if it is NULL right away. If the return value is not NULL, perform the deduplication test, and if that test passes, consider the return value to be already non-NULL. Fixes: a53b4f9c51a9 ("usb: typec: mux: avoid duplicated orientation switches") Cc: stable Signed-off-by: Marek Vasut Reviewed-by: Sebastian Reichel Tested-by: Jens Glathe Reviewed-by: Heikki Krogerus Link: https://patch.msgid.link/20260817182302.146546-1-marex@nabladev.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/mux.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/usb/typec/mux.c b/drivers/usb/typec/mux.c index 9b908c46bd7d..2bc7e8edb3cb 100644 --- a/drivers/usb/typec/mux.c +++ b/drivers/usb/typec/mux.c @@ -57,6 +57,8 @@ static void *typec_switch_match(const struct fwnode_handle *fwnode, */ dev = class_find_device(&typec_mux_class, NULL, fwnode, switch_fwnode_match); + if (!dev) + return ERR_PTR(-EPROBE_DEFER); /* Skip duplicates */ for (i = 0; i < TYPEC_MUX_MAX_DEVS; i++) @@ -65,7 +67,7 @@ static void *typec_switch_match(const struct fwnode_handle *fwnode, return NULL; } - return dev ? to_typec_switch_dev(dev) : ERR_PTR(-EPROBE_DEFER); + return to_typec_switch_dev(dev); } /** From d50b6442bef66abbe4694f918f8ad013f81d75cf Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sat, 22 Aug 2026 09:24:58 +0200 Subject: [PATCH 0361/1198] usb: typec: mux: avoid duplicated mux switches Some devices use combo PHYs (i.e. USB3 + DisplayPort), which also handle the lane muxing. These PHYs are referenced twice from the USB-C connector (USB super-speed lines and SBU/AUX lines) resulting in the mux being configured twice. Avoid this by dropping duplicates. This is a re-application of b145c3f29d62 ("usb: typec: mux: avoid duplicated mux switches"), with fix derived from usb: typec: mux: Fix typec_switch_match() . Fixes: f576c75f95a5 ("Revert "usb: typec: mux: avoid duplicated mux switches"") Cc: stable Signed-off-by: Sebastian Reichel Co-developed-by: Sebastian Reichel Signed-off-by: Marek Vasut Tested-by: Jens Glathe Reviewed-by: Heikki Krogerus Link: https://patch.msgid.link/20260822072556.490594-1-marex@nabladev.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/mux.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/drivers/usb/typec/mux.c b/drivers/usb/typec/mux.c index 2bc7e8edb3cb..afa6fc181397 100644 --- a/drivers/usb/typec/mux.c +++ b/drivers/usb/typec/mux.c @@ -277,7 +277,9 @@ static int mux_fwnode_match(struct device *dev, const void *fwnode) static void *typec_mux_match(const struct fwnode_handle *fwnode, const char *id, void *data) { + struct typec_mux_dev **mux_devs = data; struct device *dev; + int i; /* * Device graph (OF graph) does not give any means to identify the @@ -292,8 +294,18 @@ static void *typec_mux_match(const struct fwnode_handle *fwnode, dev = class_find_device(&typec_mux_class, NULL, fwnode, mux_fwnode_match); + if (!dev) + return ERR_PTR(-EPROBE_DEFER); - return dev ? to_typec_mux_dev(dev) : ERR_PTR(-EPROBE_DEFER); + /* Skip duplicates */ + for (i = 0; i < TYPEC_MUX_MAX_DEVS; i++) + if (to_typec_mux_dev(dev) == mux_devs[i]) { + put_device(dev); + return NULL; + } + + + return to_typec_mux_dev(dev); } /** @@ -318,7 +330,8 @@ struct typec_mux *fwnode_typec_mux_get(struct fwnode_handle *fwnode) return ERR_PTR(-ENOMEM); count = fwnode_connection_find_matches(fwnode, "mode-switch", - NULL, typec_mux_match, + (void **)mux_devs, + typec_mux_match, (void **)mux_devs, ARRAY_SIZE(mux_devs)); if (count <= 0) { From 6b2a674fcc953378e5e750d47a888bbe51229de5 Mon Sep 17 00:00:00 2001 From: Radhey Shyam Pandey Date: Wed, 19 Aug 2026 23:51:58 +0530 Subject: [PATCH 0362/1198] usb: dwc3: google: Initialise probe properties with DWC3_DEFAULT_PROPERTIES dwc3_google_probe() zero initialises struct dwc3_probe_data and never assigns its properties member. The unspecified state of gsbuscfg0_reqinfo is encoded as DWC3_GSBUSCFG0_REQINFO_UNSPECIFIED (0xffffffff), not as zero, so dwc3_get_software_properties() reads the zeroed field as a value the glue explicitly requested: if (properties->gsbuscfg0_reqinfo != DWC3_GSBUSCFG0_REQINFO_UNSPECIFIED) { dwc->gsbuscfg0_reqinfo = properties->gsbuscfg0_reqinfo; return; } Two things follow. dwc3_config_soc_bus() programs GSBUSCFG0.REQINFO with zero on hardware that never asked for it, and the early return skips the walk over the parent devices, so a swnode or device tree supplied snps,gsbuscfg0-reqinfo would be ignored. Assign DWC3_DEFAULT_PROPERTIES so the unset fields carry their unspecified sentinels and the controller is left alone. Fixes: 8995a37371bf ("usb: dwc3: Add Google Tensor SoC DWC3 glue driver") Cc: stable Signed-off-by: Radhey Shyam Pandey Acked-by: Thinh Nguyen Link: https://patch.msgid.link/20260819182158.1351869-1-radhey.shyam.pandey@amd.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/dwc3-google.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/dwc3/dwc3-google.c b/drivers/usb/dwc3/dwc3-google.c index 60ee4cc99b28..a01ca23cb6a8 100644 --- a/drivers/usb/dwc3/dwc3-google.c +++ b/drivers/usb/dwc3/dwc3-google.c @@ -442,6 +442,7 @@ static int dwc3_google_probe(struct platform_device *pdev) probe_data.dwc = &google->dwc; probe_data.res = res; probe_data.ignore_clocks_and_resets = true; + probe_data.properties = DWC3_DEFAULT_PROPERTIES; ret = dwc3_core_probe(&probe_data); if (ret) { ret = dev_err_probe(dev, ret, "failed to register DWC3 Core\n"); From b58e6200450d350314db0ecda7d6d1bde3281e80 Mon Sep 17 00:00:00 2001 From: Elson Serrao Date: Thu, 13 Aug 2026 08:14:56 -0700 Subject: [PATCH 0363/1198] usb: dwc3: clear forceRM when issuing EndTransfer The forceRM bit of the DEPCMD register controls the behavior of the EndTransfer command used to stop an active transfer. Older DWC3 programming guide revisions recommended setting forceRM=1 when issuing EndTransfer. Newer programming guide revisions recommend issuing EndTransfer with forceRM cleared. With forceRM=1 on DWC_usb31 v2.00a and v2.10a controllers, a transfer aborted through the ep_dequeue path was observed to remain active after EndTransfer completion. A subsequent StartTransfer issued on the same endpoint triggered writes associated with the aborted transfer. This resulted in an SMMU fault because the transfer buffer had already been unmapped during EndTransfer command-completion cleanup. Using forceRM=0 eliminates the issue. Although older DWC3 programming guide revisions recommended setting forceRM=1, no issues are known from using forceRM=0. Clear forceRM when issuing EndTransfer to provide consistent EndTransfer behavior and align with newer programming guide recommendations. Fixes: 1e43c86d84fb ("usb: dwc3: core: Add DWC31 version 2.00a controller") Cc: stable Signed-off-by: Elson Serrao Acked-by: Thinh Nguyen Link: https://patch.msgid.link/20260813151456.867008-1-elson.serrao@oss.qualcomm.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/ep0.c | 2 +- drivers/usb/dwc3/gadget.c | 21 +++++++++++++-------- 2 files changed, 14 insertions(+), 9 deletions(-) diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c index bfe616194dfa..310b5ffb236a 100644 --- a/drivers/usb/dwc3/ep0.c +++ b/drivers/usb/dwc3/ep0.c @@ -304,7 +304,7 @@ void dwc3_ep0_out_start(struct dwc3 *dwc) dwc3_ep->flags &= ~DWC3_EP_DELAY_STOP; if (dwc->connected) - dwc3_stop_active_transfer(dwc3_ep, true, true); + dwc3_stop_active_transfer(dwc3_ep, false, true); else dwc3_remove_requests(dwc, dwc3_ep, -ESHUTDOWN); } diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index fa944856f956..f245e66cd13d 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1004,7 +1004,7 @@ static int __dwc3_gadget_ep_enable(struct dwc3_ep *dep, unsigned int action) * controller to generate an ERDY to initiate the * stream. */ - dwc3_stop_active_transfer(dep, true, true); + dwc3_stop_active_transfer(dep, false, true); /* * All stream eps will reinitiate stream on NoStream @@ -1032,7 +1032,7 @@ void dwc3_remove_requests(struct dwc3 *dwc, struct dwc3_ep *dep, int status) { struct dwc3_request *req; - dwc3_stop_active_transfer(dep, true, false); + dwc3_stop_active_transfer(dep, false, false); /* If endxfer is delayed, avoid unmapping requests */ if (dep->flags & DWC3_EP_DELAY_STOP) @@ -1720,7 +1720,7 @@ static int __dwc3_gadget_kick_transfer(struct dwc3_ep *dep) if (ret == -EAGAIN) return ret; - dwc3_stop_active_transfer(dep, true, true); + dwc3_stop_active_transfer(dep, false, true); list_for_each_entry_safe(req, tmp, &dep->started_list, list) dwc3_gadget_move_cancelled_request(req, DWC3_REQUEST_STATUS_DEQUEUED); @@ -1757,6 +1757,11 @@ static int __dwc3_gadget_get_frame(struct dwc3 *dwc) * the controller won't update the TRB progress on command * completion. It also won't clear the HWO bit in the TRB. * The command will also not complete immediately in that case. + * + * Older programming guide revisions recommended setting ForceRM to 1 + * when ending a transfer. Newer programming guide revisions now + * recommend keeping ForceRM cleared, and TRBs are properly updated + * on command completion. */ static int __dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, bool interrupt) { @@ -1882,7 +1887,7 @@ static int dwc3_gadget_start_isoc_quirk(struct dwc3_ep *dep) * to wait for the next XferNotReady to test the command again */ if (cmd_status == 0) { - dwc3_stop_active_transfer(dep, true, true); + dwc3_stop_active_transfer(dep, false, true); return 0; } } @@ -2165,7 +2170,7 @@ static int dwc3_gadget_ep_dequeue(struct usb_ep *ep, struct dwc3_request *t; /* wait until it is processed */ - dwc3_stop_active_transfer(dep, true, true); + dwc3_stop_active_transfer(dep, false, true); /* * Remove any started request if the transfer is @@ -2242,7 +2247,7 @@ int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value, int protocol) return 0; } - dwc3_stop_active_transfer(dep, true, true); + dwc3_stop_active_transfer(dep, false, true); list_for_each_entry_safe(req, tmp, &dep->started_list, list) dwc3_gadget_move_cancelled_request(req, DWC3_REQUEST_STATUS_STALLED); @@ -3368,7 +3373,7 @@ static void dwc3_nostream_work(struct work_struct *work) dwc3_send_gadget_generic_command(dwc, cmd, dep->number); } else { dep->flags |= DWC3_EP_DELAY_START; - dwc3_stop_active_transfer(dep, true, true); + dwc3_stop_active_transfer(dep, false, true); spin_unlock_irqrestore(&dwc->lock, flags); return; } @@ -3726,7 +3731,7 @@ static bool dwc3_gadget_endpoint_trbs_complete(struct dwc3_ep *dep, if (usb_endpoint_xfer_isoc(dep->endpoint.desc) && list_empty(&dep->started_list) && (list_empty(&dep->pending_list) || status == -EXDEV)) - dwc3_stop_active_transfer(dep, true, true); + dwc3_stop_active_transfer(dep, false, true); else if (dwc3_gadget_ep_should_continue(dep)) if (__dwc3_gadget_kick_transfer(dep) == 0) no_started_trb = false; From c9a48db776d7184981630ecc01a3ad30a8f7dc24 Mon Sep 17 00:00:00 2001 From: Chang Wu Date: Wed, 19 Aug 2026 23:20:27 +0800 Subject: [PATCH 0364/1198] usb: typec: hd3ss3220: track VBUS enable state per consumer regulator_is_enabled() reports the aggregate regulator state, not whether this consumer holds an enable reference. If another consumer enables VBUS first, the driver can skip its own regulator_enable() call and later attempt to drop a reference it never acquired, triggering an unbalanced regulator disable warning. Track successful enable and disable calls locally. Keep the state unchanged when an operation fails so a later role or ID notification retries the operation while this consumer keeps balanced references. Fixes: b3f9d6e491fd ("usb: typec: hd3ss3220: Check if regulator needs to be switched") Cc: stable Link: https://github.com/qualcomm-linux/kernel/issues/472 Signed-off-by: Chang Wu Reviewed-by: Heikki Krogerus Tested-by: Jan Remmet Reviewed-by: Krishna Kurapati Link: https://patch.msgid.link/20260819152027.90994-1-kunjinkao.jp@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/hd3ss3220.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/usb/typec/hd3ss3220.c b/drivers/usb/typec/hd3ss3220.c index d0de5a2488f9..4eec90c82bae 100644 --- a/drivers/usb/typec/hd3ss3220.c +++ b/drivers/usb/typec/hd3ss3220.c @@ -62,6 +62,7 @@ struct hd3ss3220 { int id_irq; struct regulator *vbus; + bool vbus_enabled; }; static int hd3ss3220_set_power_opmode(struct hd3ss3220 *hd3ss3220, int power_opmode) @@ -208,7 +209,7 @@ static void hd3ss3220_regulator_control(struct hd3ss3220 *hd3ss3220, bool on) { int ret; - if (regulator_is_enabled(hd3ss3220->vbus) == on) + if (hd3ss3220->vbus_enabled == on) return; if (on) @@ -216,9 +217,13 @@ static void hd3ss3220_regulator_control(struct hd3ss3220 *hd3ss3220, bool on) else ret = regulator_disable(hd3ss3220->vbus); - if (ret) + if (ret) { dev_err(hd3ss3220->dev, "vbus regulator %s failed: %d\n", on ? "enable" : "disable", ret); + return; + } + + hd3ss3220->vbus_enabled = on; } static void hd3ss3220_set_role(struct hd3ss3220 *hd3ss3220) From f0efaf1872949e96d213c8e910fd9517f7d7c406 Mon Sep 17 00:00:00 2001 From: Aleksandr Nogikh Date: Wed, 29 Jul 2026 09:04:54 +0000 Subject: [PATCH 0365/1198] usb: gadget: midi2: Fix null-pointer dereference in f_midi2_free_ep_reqs A null-pointer dereference occurs in f_midi2_free_ep_reqs() when attempting to clean up an endpoint that was never initialized. When configuring the MIDI 2.0 gadget via configfs and setting the block direction to SNDRV_UMP_DIR_INPUT, the initialization of the midi1_ep_out endpoint is explicitly skipped during the gadget bind phase (f_midi2_bind()). As a result, the usb_ep->card field remains NULL. Later, when the host sets the alternate setting, f_midi2_set_alt() unconditionally stops both the IN and OUT endpoints by calling f_midi2_stop_eps(), which in turn calls f_midi2_free_ep_reqs() for both endpoints. When f_midi2_free_ep_reqs() is called for the uninitialized midi1_ep_out, it attempts to dereference usb_ep->card to determine the number of requests to free, leading to a crash. Fix this by using usb_ep->num_reqs instead of usb_ep->card->info.num_reqs in f_midi2_free_ep_reqs(). usb_ep->num_reqs is correctly set during f_midi2_init_ep() and remains 0 if the endpoint was never initialized, safely avoiding the loop. For consistency, apply the same change to f_midi2_alloc_ep_reqs(). Oops: general protection fault, probably for non-canonical address 0xdffffc00000000ee: 0000 [#1] SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x0000000000000770-0x0000000000000777] ... RIP: 0010:f_midi2_free_ep_reqs drivers/usb/gadget/function/f_midi2.c:1166 [inline] RIP: 0010:f_midi2_stop_eps+0x28e/0x4d0 drivers/usb/gadget/function/f_midi2.c:1246 ... Call Trace: f_midi2_set_alt+0x11c/0xf00 drivers/usb/gadget/function/f_midi2.c:1296 composite_setup+0x1ffd/0x3480 drivers/usb/gadget/composite.c:1933 configfs_composite_setup+0xbd/0x100 drivers/usb/gadget/configfs.c:1877 Fixes: 8b645922b223 ("usb: gadget: Add support for USB MIDI 2.0 function driver") Cc: stable Assisted-by: Gemini:gemini-3.5-flash Gemini:gemini-3.1-pro-preview syzbot Reported-by: syzbot+bbb6dad313f4aaa8da6b@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=bbb6dad313f4aaa8da6b Link: https://syzkaller.appspot.com/ai_job?id=8ce30b1a-8cf7-4e38-bcf7-1f69e6f6313f Signed-off-by: Aleksandr Nogikh Reviewed-by: Takashi Iwai Closes: https://syzkaller.appspot.com/bug?extid=01a17afb30637396955e Link: https://patch.msgid.link/cafe65f4-e1bb-46a3-901d-732814b861b2@mail.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_midi2.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/usb/gadget/function/f_midi2.c b/drivers/usb/gadget/function/f_midi2.c index a4b72a6fad8a..e0b743dfaba5 100644 --- a/drivers/usb/gadget/function/f_midi2.c +++ b/drivers/usb/gadget/function/f_midi2.c @@ -1145,7 +1145,7 @@ static int f_midi2_alloc_ep_reqs(struct f_midi2_usb_ep *usb_ep) if (!usb_ep->reqs) return -EINVAL; - for (i = 0; i < midi2->info.num_reqs; i++) { + for (i = 0; i < usb_ep->num_reqs; i++) { if (usb_ep->reqs[i].req) continue; usb_ep->reqs[i].req = alloc_ep_req(usb_ep->usb_ep, @@ -1160,10 +1160,9 @@ static int f_midi2_alloc_ep_reqs(struct f_midi2_usb_ep *usb_ep) /* Free allocated requests */ static void f_midi2_free_ep_reqs(struct f_midi2_usb_ep *usb_ep) { - struct f_midi2 *midi2 = usb_ep->card; int i; - for (i = 0; i < midi2->info.num_reqs; i++) { + for (i = 0; i < usb_ep->num_reqs; i++) { if (!usb_ep->reqs[i].req) continue; free_ep_req(usb_ep->usb_ep, usb_ep->reqs[i].req); From e24e3370356bddb65d667985a332b5f8aeeb5f97 Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Thu, 13 Aug 2026 20:16:15 +0200 Subject: [PATCH 0366/1198] usb: typec: tipd: Fix Thunderbolt altmode VDOs for cd321x The Intel VID status register is actually 9 bytes long and doesn't contain the raw VDOs but only the upper 16bits for device mode and enter mode. Shift those two fields into place and reconstruct the cable discover mode VDO from the data status register instead since it's not directly accessible. With this fixed now the correct VDOs are forwarded to the PHY and the to-be-submitted Thunderbolt/USB4 native host interface so that the right mode can be negotiated and the link actually comes up. Link: https://www.ti.com/lit/ug/slvubh2b/slvubh2b.pdf Fixes: 0b31c978935f ("usb: typec: tipd: Read USB4, Thunderbolt and DisplayPort status for cd321x") Fixes: 82432bbfb9e8 ("usb: typec: tipd: Handle mode transitions for CD321x") Cc: stable Signed-off-by: Sven Peter Tested-by: Rafay Acked-by: Heikki Krogerus Link: https://patch.msgid.link/20260813-b4-tipd-vdo-fix-v1-1-70317f2cd554@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tipd/core.c | 17 +++++++++++++---- drivers/usb/typec/tipd/tps6598x.h | 4 ++-- 2 files changed, 15 insertions(+), 6 deletions(-) diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c index 522f56742aa9..f76f563dc42b 100644 --- a/drivers/usb/typec/tipd/core.c +++ b/drivers/usb/typec/tipd/core.c @@ -114,7 +114,6 @@ struct tps6598x_intel_vid_status_reg { __le32 attention_vdo; __le16 enter_vdo; __le16 device_mode; - __le16 cable_mode; } __packed; /* Standard Task return codes */ @@ -731,9 +730,19 @@ static void cd321x_typec_update_mode(struct tps6598x *tps, struct cd321x_status cd321x->state.mode == TYPEC_TBT_MODE) return; - tbt_data.cable_mode = le16_to_cpu(st->intel_vid_status.cable_mode); - tbt_data.device_mode = le16_to_cpu(st->intel_vid_status.device_mode); - tbt_data.enter_vdo = le16_to_cpu(st->intel_vid_status.enter_vdo); + tbt_data.cable_mode = TBT_MODE | + TBT_SET_CABLE_SPEED(TPS_DATA_STATUS_TBT_CABLE_SPEED(st->data_status)) | + TBT_SET_CABLE_ROUNDED(TPS_DATA_STATUS_TBT_CABLE_GEN(st->data_status)); + if (st->data_status & TPS_DATA_STATUS_OPTICAL_CABLE) + tbt_data.cable_mode |= TBT_CABLE_OPTICAL; + if (st->data_status & TPS_DATA_STATUS_ACTIVE_LINK_TRAIN) + tbt_data.cable_mode |= TBT_CABLE_LINK_TRAINING; + if (st->data_status & TPS_DATA_STATUS_ACTIVE_CABLE) + tbt_data.cable_mode |= TBT_CABLE_ACTIVE_PASSIVE; + tbt_data.device_mode = TBT_MODE | + (u32)le16_to_cpu(st->intel_vid_status.device_mode) << 16; + tbt_data.enter_vdo = + (u32)le16_to_cpu(st->intel_vid_status.enter_vdo) << 16; cd321x->state.alt = cd321x->port_altmode_tbt; cd321x->state.mode = TYPEC_TBT_MODE; cd321x->state.data = &tbt_data; diff --git a/drivers/usb/typec/tipd/tps6598x.h b/drivers/usb/typec/tipd/tps6598x.h index d4140f4da5bb..11ab58ba9a18 100644 --- a/drivers/usb/typec/tipd/tps6598x.h +++ b/drivers/usb/typec/tipd/tps6598x.h @@ -210,10 +210,10 @@ #define TPS_DATA_STATUS_DP_PIN_ASSIGNMENT(x) \ TPS_FIELD_GET(TPS_DATA_STATUS_DP_PIN_ASSIGNMENT_MASK, (x)) #define TPS_DATA_STATUS_TBT_CABLE_SPEED_MASK GENMASK(27, 25) -#define TPS_DATA_STATUS_TBT_CABLE_SPEED \ +#define TPS_DATA_STATUS_TBT_CABLE_SPEED(x) \ TPS_FIELD_GET(TPS_DATA_STATUS_TBT_CABLE_SPEED_MASK, (x)) #define TPS_DATA_STATUS_TBT_CABLE_GEN_MASK GENMASK(29, 28) -#define TPS_DATA_STATUS_TBT_CABLE_GEN \ +#define TPS_DATA_STATUS_TBT_CABLE_GEN(x) \ TPS_FIELD_GET(TPS_DATA_STATUS_TBT_CABLE_GEN_MASK, (x)) /* Map data status to DP spec assignments */ From fed0aa7c6eaedc6c0d4e362fc91724aa47be4a7b Mon Sep 17 00:00:00 2001 From: Ivy Lopez Date: Sat, 15 Aug 2026 18:54:33 -0600 Subject: [PATCH 0367/1198] usb: gadget: f_midi2: fix use-after-free in string attribute show path f_midi2_opts_str_show() takes the string lock internally, but its callers dereference the opts->info. pointer before calling it, outside the lock. This races with f_midi2_opts_str_store(), which frees the old string under opts->lock when the attribute is written concurrently, the show path can read a pointer that gets freed before the lock inside str_show() is even taken. Change f_midi2_opts_str_show() to take a pointer to the string field, matching the existing pattern in f_midi2_opts_str_store(), and dereference it only after the lock is held. Update all three callers (iface_name, block name, and the EP string option macro) accordingly. Reported-by: syzbot+2280f1cca5e6b0c353e4@syzkaller.appspotmail.com Cc: stable Closes: https://syzkaller.appspot.com/bug?extid=2280f1cca5e6b0c353e4 Signed-off-by: Ivy Lopez Reviewed-by: Takashi Iwai Link: https://patch.msgid.link/20260816005434.34018-1-skunkolee@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_midi2.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/usb/gadget/function/f_midi2.c b/drivers/usb/gadget/function/f_midi2.c index e0b743dfaba5..5b8b18281989 100644 --- a/drivers/usb/gadget/function/f_midi2.c +++ b/drivers/usb/gadget/function/f_midi2.c @@ -2177,13 +2177,13 @@ static ssize_t f_midi2_opts_bool_store(struct f_midi2_opts *opts, /* generic show/store for string */ static ssize_t f_midi2_opts_str_show(struct f_midi2_opts *opts, - const char *str, char *page) + const char **strp, char *page) { int result = 0; mutex_lock(&opts->lock); - if (str) - result = scnprintf(page, PAGE_SIZE, "%s\n", str); + if (*strp) + result = scnprintf(page, PAGE_SIZE, "%s\n", *strp); mutex_unlock(&opts->lock); return result; } @@ -2277,7 +2277,7 @@ static ssize_t f_midi2_block_opts_name_show(struct config_item *item, { struct f_midi2_block_opts *opts = to_f_midi2_block_opts(item); - return f_midi2_opts_str_show(opts->ep->opts, opts->info.name, page); + return f_midi2_opts_str_show(opts->ep->opts, &opts->info.name, page); } static ssize_t f_midi2_block_opts_name_store(struct config_item *item, @@ -2434,7 +2434,7 @@ static ssize_t f_midi2_ep_opts_##name##_show(struct config_item *item, \ char *page) \ { \ struct f_midi2_ep_opts *opts = to_f_midi2_ep_opts(item); \ - return f_midi2_opts_str_show(opts->opts, opts->info.name, page);\ + return f_midi2_opts_str_show(opts->opts, &opts->info.name, page);\ } \ \ static ssize_t f_midi2_ep_opts_##name##_store(struct config_item *item, \ @@ -2589,7 +2589,7 @@ static ssize_t f_midi2_opts_iface_name_show(struct config_item *item, { struct f_midi2_opts *opts = to_f_midi2_opts(item); - return f_midi2_opts_str_show(opts, opts->info.iface_name, page); + return f_midi2_opts_str_show(opts, &opts->info.iface_name, page); } static ssize_t f_midi2_opts_iface_name_store(struct config_item *item, From 7e07d3e4c389217d7d7171d80edf2e23ac70f1ea Mon Sep 17 00:00:00 2001 From: Jeffin Philip Date: Sat, 15 Aug 2026 11:10:06 +0530 Subject: [PATCH 0368/1198] usb: gadget: f_midi: initialize work in f_midi_alloc() f_midi_alloc initializes free_ref to 1 and it can only be incremented when a sound card is registered via f_midi_register_card(). f_midi_register_card() is only called in f_midi_bind() which actually performs INIT_WORK. If f_midi_bind() is never run, work is not initialized and the if condition in f_midi_free becomes true, this results in a warning later in __flush_work as work->func = 0. Fix this by moving INIT_WORK from f_midi_bind() to f_midi_alloc(). Reported-by: syzbot+d5fa3d224505c8610702@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=d5fa3d224505c8610702 Fixes: 8653d71ce376 ("usb/gadget: f_midi: Replace tasklet with work") Cc: stable Signed-off-by: Jeffin Philip Reviewed-by: Takashi Iwai Link: https://patch.msgid.link/20260815054006.102325-1-jeffinphilip14@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_midi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/gadget/function/f_midi.c b/drivers/usb/gadget/function/f_midi.c index fba8cf787d6c..63fb6ee70a3d 100644 --- a/drivers/usb/gadget/function/f_midi.c +++ b/drivers/usb/gadget/function/f_midi.c @@ -879,7 +879,6 @@ static int f_midi_bind(struct usb_configuration *c, struct usb_function *f) int status, n, jack = 1, i = 0, endpoint_descriptor_index = 0; midi->gadget = cdev->gadget; - INIT_WORK(&midi->work, f_midi_in_work); status = f_midi_register_card(midi); if (status < 0) goto fail_register; @@ -1377,6 +1376,7 @@ static struct usb_function *f_midi_alloc(struct usb_function_instance *fi) status = -ENOMEM; goto midi_free; } + INIT_WORK(&midi->work, f_midi_in_work); midi->out_ports = opts->out_ports; midi->index = opts->index; midi->buflen = opts->buflen; From dd0eed9e165b1a6292f49e622e3dd0b7d99b106d Mon Sep 17 00:00:00 2001 From: Lovekesh Solanki Date: Tue, 25 Aug 2026 22:43:43 +0530 Subject: [PATCH 0369/1198] USB: gadget: fix NULL pointer dereference in gadget_dev_ioctl() gadget_dev_ioctl() reads dev->gadget before acquiring dev->lock, but dev->state is checked after acquiring the lock. Therefore a concurrent bind can change the device state between these operations, which can leave ioctl with a stale NULL gadget pointer and causing a NULL pointer dereference at gadget->ops->ioctl. Read dev->gadget while holding dev->lock so that the gadget pointer and device state are sampled consistently. Cc: stable Reported-by: Eulgyu Kim Link: https://lore.kernel.org/all/20260824113510.1141236-1-jjy600901@snu.ac.kr/ Reported-by: Jaeyoung Chung Link: https://lore.kernel.org/all/20260824113510.1141236-1-jjy600901@snu.ac.kr/ Signed-off-by: Lovekesh Solanki Reviewed-by: Alan Stern Link: https://patch.msgid.link/20260825171343.459630-1-lovekeshsolanki00@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/legacy/inode.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index db961aaa3740..67c6ffaf4f72 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -1260,10 +1260,11 @@ ep0_poll (struct file *fd, poll_table *wait) static long gadget_dev_ioctl (struct file *fd, unsigned code, unsigned long value) { struct dev_data *dev = fd->private_data; - struct usb_gadget *gadget = dev->gadget; + struct usb_gadget *gadget; long ret = -ENOTTY; spin_lock_irq(&dev->lock); + gadget = dev->gadget; if (dev->state == STATE_DEV_OPENED || dev->state == STATE_DEV_UNBOUND) { /* Not bound to a UDC */ From 96c8ea3c5add7920b3c43840d1ea76b3354c8d2d Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 19 Aug 2026 08:49:37 -0700 Subject: [PATCH 0370/1198] block: save page offset gaps in cloned bio The cloned bio needs to inherit the accumulated gaps between vectors so that we can know if this bio can subscribe to the iova coalescing optimization. When cloning for a split, the gap only applies to the front bio since that's as far as has been processed. The remaining bio can reset its gaps to 0 since it advanced past the checked vectors, and will start its accounting from there on the next split check. Fixes: 2f6b2565d43c ("block: accumulate memory segment gaps per bio") Reported-by: Eric Auger Tested-by: Eric Auger Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Link: https://patch.msgid.link/20260819154937.3903312-1-kbusch@meta.com Signed-off-by: Jens Axboe --- block/bio.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/block/bio.c b/block/bio.c index 898b2f5ef8c8..f95b63c0604a 100644 --- a/block/bio.c +++ b/block/bio.c @@ -859,6 +859,7 @@ static int __bio_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp) bio->bi_ioprio = bio_src->bi_ioprio; bio->bi_write_hint = bio_src->bi_write_hint; bio->bi_write_stream = bio_src->bi_write_stream; + bio->bi_bvec_gap_bit = bio_src->bi_bvec_gap_bit; bio->bi_iter = bio_src->bi_iter; bio->bi_io_vec = bio_src->bi_io_vec; @@ -1972,6 +1973,14 @@ struct bio *bio_split(struct bio *bio, int sectors, bio_advance(bio, split->bi_iter.bi_size); + /* + * The gap bit is set when splitting to limits and only applies to the + * front bio that was split off. The remaining bio will calcualte its + * gap value when it is subsequently split to limits, so it is safe to + * re-initialize the value back to 0. + */ + bio->bi_bvec_gap_bit = 0; + if (bio_flagged(bio, BIO_TRACE_COMPLETION)) bio_set_flag(split, BIO_TRACE_COMPLETION); From e52349a5ea6a74d46dfb703fcb64e08b5af28e8c Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Mon, 10 Aug 2026 09:42:17 -0700 Subject: [PATCH 0371/1198] loop, zloop: fix dma_alignment for large or unreported limits A file system sets STATX_DIOALIGN with zeroed alignments when the file can't be used for direct I/O. The zero underflowed to UINT_MAX and triggered a queue limits validation warning. Fall back to the block device's limits when dio_mem_align isn't reported. A file system with a block size larger than PAGE_SIZE may also report a memory alignment that can't be expressed as a queue limit. File systems fall back to buffered I/O for requests that don't meet their alignment, so cap the reported limit to the largest possible value. Fixes: 6c8dec275ccc ("loop: set dma_alignment from the backing file for direct I/O") Fixes: c5059c1af2bd ("zloop: set dma_alignment from the backing files for direct I/O") Reported-by: syzbot+ac00e7bf7ac8c91af921@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=ac00e7bf7ac8c91af921 Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Link: https://patch.msgid.link/20260810164218.3721636-1-kbusch@meta.com Signed-off-by: Jens Axboe --- drivers/block/loop.c | 8 +++++--- drivers/block/zloop.c | 8 +++++--- 2 files changed, 10 insertions(+), 6 deletions(-) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 6f12976035b0..758c20678bf6 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -458,12 +458,14 @@ static void loop_update_dio_alignment(struct loop_device *lo) * Use the dio alignment of the file system if provided. The incomoing * request's bio_vec is forwarded to the backing file unchanged, so its * required memory alignment becomes the device's dma_alignment when - * used for direct-io. + * used for direct-io. The file system reports zeroed alignments if the + * file can't be used for direct-io at all, so fall back to the block + * device limits in that case. */ if (!vfs_getattr(&file->f_path, &st, STATX_DIOALIGN, 0) && - (st.result_mask & STATX_DIOALIGN)) { + (st.result_mask & STATX_DIOALIGN) && st.dio_mem_align) { lo->lo_min_dio_size = st.dio_offset_align; - lo->lo_dio_mem_align = st.dio_mem_align - 1; + lo->lo_dio_mem_align = min(st.dio_mem_align - 1, PAGE_SIZE - 1); return; } diff --git a/drivers/block/zloop.c b/drivers/block/zloop.c index 4323ac108cae..f0ca221524db 100644 --- a/drivers/block/zloop.c +++ b/drivers/block/zloop.c @@ -1042,12 +1042,14 @@ static int zloop_get_block_size(struct zloop_device *zlo, * Use the dio alignment of the file system if provided. The incoming * request's bio_vec is forwarded to the backing file unchanged, so its * required memory alignment becomes the device's dma_alignment when - * used for direct-io. + * used for direct-io. The file system reports zeroed alignments if the + * file can't be used for direct-io at all, so fall back to the block + * device limits in that case. */ if (!vfs_getattr(&zone->file->f_path, &st, STATX_DIOALIGN, 0) && - (st.result_mask & STATX_DIOALIGN)) { + (st.result_mask & STATX_DIOALIGN) && st.dio_mem_align) { zlo->block_size = st.dio_offset_align; - zlo->dio_mem_align = st.dio_mem_align - 1; + zlo->dio_mem_align = min(st.dio_mem_align - 1, PAGE_SIZE - 1); } else if (sb_bdev) { zlo->block_size = bdev_physical_block_size(sb_bdev); zlo->dio_mem_align = bdev_dma_alignment(sb_bdev); From 445fc368c6bc73eff0aeb3818cf5f355facfbb16 Mon Sep 17 00:00:00 2001 From: Liu Qi Date: Fri, 21 Aug 2026 17:04:16 +0800 Subject: [PATCH 0372/1198] usb-storage: ene_ub6250: fix race between scan work and probe ene_ub6250_probe() calls usb_stor_probe2(), which starts the usb-storage infrastructure and schedules the delayed scan work. The driver then calls ene_get_card_type(), which sends an ENE command through ene_send_scsi_cmd() and the usb-storage bulk transfer helpers. Both the delayed scan work, through usb_stor_Bulk_max_lun(), and ene_get_card_type() use us->current_urb. The scan work serializes this access with us->dev_mutex, but the ENE card-type probe does not. If the scan work runs while ene_get_card_type() is still using us->current_urb, usb_submit_urb() warns that the URB is already active. Serialize ene_get_card_type() with us->dev_mutex, matching the locking used by the scan path. Reported-by: syzbot+22ea20ef3afb6785b122@syzkaller.appspotmail.com Cc: stable Closes: https://syzkaller.appspot.com/bug?extid=22ea20ef3afb6785b122 Assisted-by: Qwen:Qwen3.6 Signed-off-by: Liu Qi Acked-by: Alan Stern Link: https://patch.msgid.link/20260821090416.1247127-1-liuqi@longcheer.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/storage/ene_ub6250.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/storage/ene_ub6250.c b/drivers/usb/storage/ene_ub6250.c index ed49a3bc859c..895f90c7a3fa 100644 --- a/drivers/usb/storage/ene_ub6250.c +++ b/drivers/usb/storage/ene_ub6250.c @@ -2357,7 +2357,9 @@ static int ene_ub6250_probe(struct usb_interface *intf, return result; /* probe card type */ + mutex_lock(&us->dev_mutex); result = ene_get_card_type(us, REG_CARD_STATUS, info->bbuf); + mutex_unlock(&us->dev_mutex); if (result != USB_STOR_XFER_GOOD) { usb_stor_disconnect(intf); return USB_STOR_TRANSPORT_ERROR; From eae6460f617382044c5afe5ef202f4d8b2c099b5 Mon Sep 17 00:00:00 2001 From: Pawel Laszczak Date: Thu, 20 Aug 2026 12:45:31 +0200 Subject: [PATCH 0373/1198] usb: cdnsp: fix wakeup from S3 after controller context loss CDNSP controller may lose its runtime register programming across S3 suspend/resume, depending on SoC power domain configuration. After resume the operational and interrupter registers may contain reset values, which prevents the gadget side from recovering correctly and breaks wakeup from S3. Fix this by detecting whether the controller lost its register context after resume and handling both cases: - If context was lost (CFG_3XPORT_U1_PIPE_CLK_GATE_EN set or power lost): reset the controller and reprogram the state required for normal operation, including the command ring, DCBAA pointer, doorbell base, event ring, ERST base/size and event ring dequeue pointer. - If context was retained: restart the controller directly without reprogramming registers. Issue a wakeup if the link was in U3 before suspend. Move the basic controller register programming out of the one-time memory initialization path and make it reusable from the resume path. Also separate ring allocation from ring initialization so that rings can be reinitialized without reallocating DMA memory. Always perform the full suspend sequence regardless of the current link state. Previously, if the device was already in U3, the suspend callback returned early without stopping the controller, which could lead to commands being issued on a disabled slot during resume. Fixes: 3d82904559f4 ("usb: cdnsp: cdns3 Add main part of Cadence USBSSP DRD Driver") Cc: stable Signed-off-by: Pawel Laszczak Acked-by: Peter Chen Link: https://patch.msgid.link/20260820-suspend_resume_fix-v3-1-5a713098b977@cadence.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/cdns3/cdnsp-gadget.c | 111 +++++++++++++++++++++++++++++-- drivers/usb/cdns3/cdnsp-gadget.h | 1 + drivers/usb/cdns3/cdnsp-mem.c | 98 ++++++++++----------------- 3 files changed, 142 insertions(+), 68 deletions(-) diff --git a/drivers/usb/cdns3/cdnsp-gadget.c b/drivers/usb/cdns3/cdnsp-gadget.c index 7a516e509198..e84405352caa 100644 --- a/drivers/usb/cdns3/cdnsp-gadget.c +++ b/drivers/usb/cdns3/cdnsp-gadget.c @@ -1338,7 +1338,6 @@ static int cdnsp_run(struct cdnsp_device *pdev, cdnsp_gadget_ep0_desc.wMaxPacketSize = cpu_to_le16(512); - ret = cdnsp_start(pdev); if (ret) { ret = -ENODEV; @@ -1837,6 +1836,82 @@ static void cdnsp_get_rev_cap(struct cdnsp_device *pdev) readl(&pdev->rev_cap->tx_buff_size)); } +static void cdnsp_set_event_deq(struct cdnsp_device *pdev) +{ + dma_addr_t deq; + u64 temp; + + deq = cdnsp_trb_virt_to_dma(pdev->event_ring->deq_seg, + pdev->event_ring->dequeue); + + /* Update controller event ring dequeue pointer */ + temp = cdnsp_read_64(&pdev->ir_set->erst_dequeue); + temp &= ERST_PTR_MASK; + + /* + * Don't clear the EHB bit (which is RW1C) because + * there might be more events to service. + */ + temp &= ~ERST_EHB; + + cdnsp_write_64(((u64)deq & (u64)~ERST_PTR_MASK) | temp, + &pdev->ir_set->erst_dequeue); +} + +static void cdnsp_add_interrupter(struct cdnsp_device *pdev) +{ + u64 erst_base; + u32 erst_size; + + /* Set ERST count with the number of entries in the segment table. */ + erst_size = readl(&pdev->ir_set->erst_size); + erst_size &= ERST_SIZE_MASK; + erst_size |= ERST_NUM_SEGS; + writel(erst_size, &pdev->ir_set->erst_size); + + /* Set the segment table base address. */ + erst_base = cdnsp_read_64(&pdev->ir_set->erst_base); + erst_base &= ERST_PTR_MASK; + erst_base |= (pdev->erst.erst_dma_addr & (u64)~ERST_PTR_MASK); + cdnsp_write_64(erst_base, &pdev->ir_set->erst_base); + + /* Set the event ring dequeue address. */ + cdnsp_set_event_deq(pdev); +} + +/* Set up basic CDNSP registers */ +static void cdnsp_init(struct cdnsp_device *pdev) +{ + unsigned int val; + u64 val_64; + + val = readl(&pdev->op_regs->config_reg); + val |= ((val & ~MAX_DEVS) | CDNSP_DEV_MAX_SLOTS) | CONFIG_U3E; + writel(val, &pdev->op_regs->config_reg); + + /* Initialize the Command ring */ + cdnsp_ring_init(pdev, pdev->cmd_ring); + + /* Set the address in the Command Ring Control register */ + val_64 = cdnsp_read_64(&pdev->op_regs->cmd_ring); + val_64 = (val_64 & (u64)CMD_RING_RSVD_BITS) | + (pdev->cmd_ring->first_seg->dma & (u64)~CMD_RING_RSVD_BITS) | + pdev->cmd_ring->cycle_state; + cdnsp_write_64(val_64, &pdev->op_regs->cmd_ring); + + /* Set Device Context Base Address Array pointer */ + cdnsp_write_64(pdev->dcbaa->dma, &pdev->op_regs->dcbaa_ptr); + + /* Set Doorbell array pointer */ + val = readl(&pdev->cap_regs->db_off); + val &= DBOFF_MASK; + pdev->dba = (void __iomem *)pdev->cap_regs + val; + + /* Initialize the Primary interrupter */ + cdnsp_ring_init(pdev, pdev->event_ring); + cdnsp_add_interrupter(pdev); +} + static int cdnsp_gen_setup(struct cdnsp_device *pdev) { int ret; @@ -1902,6 +1977,8 @@ static int cdnsp_gen_setup(struct cdnsp_device *pdev) if (ret) return ret; + cdnsp_init(pdev); + /* * Software workaround for U1: after transition * to U1 the controller starts gating clock, and in some cases, @@ -2031,9 +2108,6 @@ static int cdnsp_gadget_suspend(struct cdns *cdns, bool do_wakeup) struct cdnsp_device *pdev = cdns->gadget_dev; unsigned long flags; - if (pdev->link_state == XDEV_U3) - return 0; - spin_lock_irqsave(&pdev->lock, flags); cdnsp_disconnect_gadget(pdev); cdnsp_stop(pdev); @@ -2047,12 +2121,38 @@ static int cdnsp_gadget_resume(struct cdns *cdns, bool lost_power) struct cdnsp_device *pdev = cdns->gadget_dev; enum usb_device_speed max_speed; unsigned long flags; + bool context_lost; + u32 val; int ret; if (!pdev->gadget_driver) return 0; spin_lock_irqsave(&pdev->lock, flags); + val = readl(&pdev->port3x_regs->mode_2); + context_lost = !!(val & CFG_3XPORT_U1_PIPE_CLK_GATE_EN) || lost_power; + + if (context_lost) { + cdnsp_halt(pdev); + cdnsp_set_apb_timeout_value(pdev); + + /* Reset the internal controller memory state and registers. */ + ret = cdnsp_reset(pdev); + if (ret) + goto unlock; + + val = readl(&pdev->port3x_regs->mode_2); + val &= ~CFG_3XPORT_U1_PIPE_CLK_GATE_EN; + writel(val, &pdev->port3x_regs->mode_2); + + cdnsp_clear_cmd_ring(pdev); + + memset(pdev->event_ring->first_seg->trbs, 0, + sizeof(union cdnsp_trb) * (TRBS_PER_SEGMENT)); + + cdnsp_init(pdev); + } + max_speed = pdev->gadget_driver->max_speed; /* Limit speed if necessary. */ @@ -2060,9 +2160,10 @@ static int cdnsp_gadget_resume(struct cdns *cdns, bool lost_power) ret = cdnsp_run(pdev, max_speed); - if (pdev->link_state == XDEV_U3) + if (!context_lost && pdev->link_state == XDEV_U3) __cdnsp_gadget_wakeup(pdev); +unlock: spin_unlock_irqrestore(&pdev->lock, flags); return ret; diff --git a/drivers/usb/cdns3/cdnsp-gadget.h b/drivers/usb/cdns3/cdnsp-gadget.h index c44bca348a41..c3ae5040f9cc 100644 --- a/drivers/usb/cdns3/cdnsp-gadget.h +++ b/drivers/usb/cdns3/cdnsp-gadget.h @@ -1510,6 +1510,7 @@ int cdnsp_endpoint_init(struct cdnsp_device *pdev, int cdnsp_ring_expansion(struct cdnsp_device *pdev, struct cdnsp_ring *ring, unsigned int num_trbs, gfp_t flags); +void cdnsp_ring_init(struct cdnsp_device *pdev, struct cdnsp_ring *ring); struct cdnsp_ring *cdnsp_dma_to_transfer_ring(struct cdnsp_ep *ep, u64 address); int cdnsp_alloc_stream_info(struct cdnsp_device *pdev, struct cdnsp_ep *pep, diff --git a/drivers/usb/cdns3/cdnsp-mem.c b/drivers/usb/cdns3/cdnsp-mem.c index 83f3384b735d..419309c8439e 100644 --- a/drivers/usb/cdns3/cdnsp-mem.c +++ b/drivers/usb/cdns3/cdnsp-mem.c @@ -394,13 +394,6 @@ static struct cdnsp_ring *cdnsp_ring_alloc(struct cdnsp_device *pdev, if (ret) goto fail; - /* Only event ring does not use link TRB. */ - if (type != TYPE_EVENT) - ring->last_seg->trbs[TRBS_PER_SEGMENT - 1].link.control |= - cpu_to_le32(LINK_TOGGLE); - - cdnsp_initialize_ring_info(ring); - trace_cdnsp_ring_alloc(ring); return ring; fail: kfree(ring); @@ -603,6 +596,7 @@ int cdnsp_alloc_stream_info(struct cdnsp_device *pdev, if (!cur_ring) goto cleanup_rings; + cdnsp_ring_init(pdev, cur_ring); cur_ring->stream_id = cur_stream; cur_ring->trb_address_map = &stream_info->trb_address_map; @@ -698,6 +692,8 @@ static int cdnsp_alloc_priv_device(struct cdnsp_device *pdev) if (!pdev->eps[0].ring) goto fail; + cdnsp_ring_init(pdev, pdev->eps[0].ring); + /* Point to output device context in dcbaa. */ pdev->dcbaa->dev_context_ptrs[1] = cpu_to_le64(pdev->out_ctx.dma); pdev->cmd.in_ctx = &pdev->in_ctx; @@ -991,6 +987,8 @@ int cdnsp_endpoint_init(struct cdnsp_device *pdev, if (!pep->ring) return -ENOMEM; + cdnsp_ring_init(pdev, pep->ring); + pep->skip = false; /* Fill the endpoint context */ @@ -1096,28 +1094,6 @@ void cdnsp_mem_cleanup(struct cdnsp_device *pdev) pdev->active_port = NULL; } -static void cdnsp_set_event_deq(struct cdnsp_device *pdev) -{ - dma_addr_t deq; - u64 temp; - - deq = cdnsp_trb_virt_to_dma(pdev->event_ring->deq_seg, - pdev->event_ring->dequeue); - - /* Update controller event ring dequeue pointer */ - temp = cdnsp_read_64(&pdev->ir_set->erst_dequeue); - temp &= ERST_PTR_MASK; - - /* - * Don't clear the EHB bit (which is RW1C) because - * there might be more events to service. - */ - temp &= ~ERST_EHB; - - cdnsp_write_64(((u64)deq & (u64)~ERST_PTR_MASK) | temp, - &pdev->ir_set->erst_dequeue); -} - static void cdnsp_add_in_port(struct cdnsp_device *pdev, struct cdnsp_port *port, __le32 __iomem *addr) @@ -1226,6 +1202,36 @@ static int cdnsp_setup_port_arrays(struct cdnsp_device *pdev) return 0; } +static void cdnsp_initialize_ring_segments(struct cdnsp_device *pdev, struct cdnsp_ring *ring) +{ + struct cdnsp_segment *seg; + + /* Only event ring does not use link TRB. */ + if (ring->type == TYPE_EVENT) + return; + + seg = ring->first_seg; + + while (seg) { + struct cdnsp_segment *next = seg->next; + + cdnsp_link_segments(pdev, seg, next, ring->type); + if (next == ring->first_seg) + break; + + seg = next; + } + + ring->last_seg->trbs[TRBS_PER_SEGMENT - 1].link.control |= cpu_to_le32(LINK_TOGGLE); +} + +void cdnsp_ring_init(struct cdnsp_device *pdev, struct cdnsp_ring *ring) +{ + cdnsp_initialize_ring_segments(pdev, ring); + cdnsp_initialize_ring_info(ring); + trace_cdnsp_ring_alloc(ring); +} + /* * Initialize memory for CDNSP (one-time init). * @@ -1237,10 +1243,8 @@ int cdnsp_mem_init(struct cdnsp_device *pdev) { struct device *dev = pdev->dev; int ret = -ENOMEM; - unsigned int val; dma_addr_t dma; u32 page_size; - u64 val_64; /* * Use 4K pages, since that's common and the minimum the @@ -1248,10 +1252,6 @@ int cdnsp_mem_init(struct cdnsp_device *pdev) */ page_size = 1 << 12; - val = readl(&pdev->op_regs->config_reg); - val |= ((val & ~MAX_DEVS) | CDNSP_DEV_MAX_SLOTS) | CONFIG_U3E; - writel(val, &pdev->op_regs->config_reg); - /* * Doorbell array must be physically contiguous * and 64-byte (cache line) aligned. @@ -1263,8 +1263,6 @@ int cdnsp_mem_init(struct cdnsp_device *pdev) pdev->dcbaa->dma = dma; - cdnsp_write_64(dma, &pdev->op_regs->dcbaa_ptr); - /* * Initialize the ring segment pool. The ring must be a contiguous * structure comprised of TRBs. The TRBs must be 16 byte aligned, @@ -1290,17 +1288,6 @@ int cdnsp_mem_init(struct cdnsp_device *pdev) if (!pdev->cmd_ring) goto destroy_device_pool; - /* Set the address in the Command Ring Control register */ - val_64 = cdnsp_read_64(&pdev->op_regs->cmd_ring); - val_64 = (val_64 & (u64)CMD_RING_RSVD_BITS) | - (pdev->cmd_ring->first_seg->dma & (u64)~CMD_RING_RSVD_BITS) | - pdev->cmd_ring->cycle_state; - cdnsp_write_64(val_64, &pdev->op_regs->cmd_ring); - - val = readl(&pdev->cap_regs->db_off); - val &= DBOFF_MASK; - pdev->dba = (void __iomem *)pdev->cap_regs + val; - /* Set ir_set to interrupt register set 0 */ pdev->ir_set = &pdev->run_regs->ir_set[0]; @@ -1317,21 +1304,6 @@ int cdnsp_mem_init(struct cdnsp_device *pdev) if (ret) goto free_event_ring; - /* Set ERST count with the number of entries in the segment table. */ - val = readl(&pdev->ir_set->erst_size); - val &= ERST_SIZE_MASK; - val |= ERST_NUM_SEGS; - writel(val, &pdev->ir_set->erst_size); - - /* Set the segment table base address. */ - val_64 = cdnsp_read_64(&pdev->ir_set->erst_base); - val_64 &= ERST_PTR_MASK; - val_64 |= (pdev->erst.erst_dma_addr & (u64)~ERST_PTR_MASK); - cdnsp_write_64(val_64, &pdev->ir_set->erst_base); - - /* Set the event ring dequeue address. */ - cdnsp_set_event_deq(pdev); - ret = cdnsp_setup_port_arrays(pdev); if (ret) goto free_erst; From 6e2b571b0a54755b06e092501913e1dfefe75d6c Mon Sep 17 00:00:00 2001 From: Kanishka De Silva Date: Sun, 30 Aug 2026 12:31:33 +0530 Subject: [PATCH 0374/1198] ublk: clear VM_MAYWRITE on read-only ublk char device mmap ublk_ch_mmap() rejects mmap requests with VM_WRITE set, but never clears VM_MAYWRITE on the resulting read-only mapping. This allows a userspace daemon to mmap the per-queue command buffer PROT_READ, then upgrade it to PROT_WRITE via mprotect(), since VM_MAYWRITE was never cleared. The command buffer holds struct ublksrv_io_desc entries that are kernel-written ABI; a writable mapping lets an unprivileged daemon process corrupt fields such as addr, op_flags, nr_sectors, and start_sector. Same bug class as the drm/panthor and drm/vc4 VM_MAYWRITE fixes, and the 2026-08-13 ptp/vmclock fix (a5edadbae57e). Verified via mprotect() PoC: before the fix, a PROT_READ mapping can be upgraded to PROT_READ|PROT_WRITE and a write into the command buffer corrupts io_desc fields (confirmed under KASAN). After the fix, mprotect() returns -EACCES. Fixes: 3fee8d7599e1 ("ublk_drv: add io_uring based userspace block driver") Cc: stable@vger.kernel.org Signed-off-by: Kanishka De Silva Reviewed-by: Ming Lei Link: https://patch.msgid.link/20260830070133.559-1-kpskanna1915@gmail.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 6c5bec7da97c..e5ba07d8d281 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -2653,6 +2653,12 @@ static int ublk_ch_mmap(struct file *filp, struct vm_area_struct *vma) if (vma->vm_flags & VM_WRITE) return -EPERM; + /* + * The per-queue command buffer is kernel-written ABI; prevent + * the daemon from upgrading to writable via mprotect(). + */ + vm_flags_clear(vma, VM_MAYWRITE); + end = UBLKSRV_CMD_BUF_OFFSET + ub->dev_info.nr_hw_queues * max_sz; if (phys_off < UBLKSRV_CMD_BUF_OFFSET || phys_off >= end) return -EINVAL; From 4ffee1aebb0c0ffcda9faffd17834ea9b00d42cc Mon Sep 17 00:00:00 2001 From: Myeonghun Pak Date: Mon, 27 Jul 2026 21:34:14 +0900 Subject: [PATCH 0375/1198] usb: storage: realtek_cr: fix use-after-free on disconnect realtek_cr_destructor() calls timer_delete() before the chip containing the timer is freed. The timer callback may still be running and can rearm itself, resulting in a use-after-free. Use timer_shutdown_sync() to wait for the callback and prevent further rearming. Do this unconditionally because ss_en may be changed after the timer is armed. Move timer_setup() into init_realtek_cr() so the timer is initialized before any failure path can invoke the destructor. Found by static analysis. Fixes: e931830bb877 ("Realtek cr: Add autosuspend function.") Cc: stable Co-developed-by: Ijae Kim Signed-off-by: Ijae Kim Signed-off-by: Myeonghun Pak Link: https://patch.msgid.link/20260727123414.44700-1-mhun512@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/storage/realtek_cr.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/usb/storage/realtek_cr.c b/drivers/usb/storage/realtek_cr.c index af038b897c6b..c4b28744693b 100644 --- a/drivers/usb/storage/realtek_cr.c +++ b/drivers/usb/storage/realtek_cr.c @@ -916,7 +916,6 @@ static int realtek_cr_autosuspend_setup(struct us_data *us) us->proto_handler = rts51x_invoke_transport; chip->timer_expires = 0; - timer_setup(&chip->rts51x_suspend_timer, rts51x_suspend_timer_fn, 0); fw5895_init(us); /* enable autosuspend function of the usb device */ @@ -934,10 +933,7 @@ static void realtek_cr_destructor(void *extra) return; #ifdef CONFIG_REALTEK_AUTOPM - if (ss_en) { - timer_delete(&chip->rts51x_suspend_timer); - chip->timer_expires = 0; - } + timer_shutdown_sync(&chip->rts51x_suspend_timer); #endif kfree(chip->status); } @@ -982,6 +978,9 @@ static int init_realtek_cr(struct us_data *us) us->extra = chip; us->extra_destructor = realtek_cr_destructor; +#ifdef CONFIG_REALTEK_AUTOPM + timer_setup(&chip->rts51x_suspend_timer, rts51x_suspend_timer_fn, 0); +#endif us->max_lun = chip->max_lun = rts51x_get_max_lun(us); chip->us = us; From 9f6f095beec82a80daa666a3b2186a5b95841e9a Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 17 Aug 2026 18:11:30 +0200 Subject: [PATCH 0376/1198] usb: f_mass_storage: Bump local buffer size in fsg_common_create_luns() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit GCC (Debian 14.2.0-19) is not happy about the buffer size: drivers/usb/gadget/function/f_mass_storage.c:2970:48: error: ‘%d’ directive output may be truncated writing between 1 and 9 bytes into a region of size 5 [-Werror=format-truncation=] Bump the size to get it enough for all possible values. Note, although cfg->nluns is limited to FSG_MAX_LUNS (16), the compiler doesn't realize this and complains about the buffer size. Also note, the existing comment is wrong as size 8 for the whole buffer doesn't cover 100 mil numbers, hence drop it altogether. Fixes: b27c08c953e9 ("usb: gadget: f_mass_storage: create lun creation helpers for use in fsg_common_init") Cc: stable Acked-by: Alan Stern Signed-off-by: Andy Shevchenko Link: https://patch.msgid.link/20260817161239.1448582-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_mass_storage.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c index a50743caf083..1a0fbc808ee2 100644 --- a/drivers/usb/gadget/function/f_mass_storage.c +++ b/drivers/usb/gadget/function/f_mass_storage.c @@ -2960,7 +2960,7 @@ EXPORT_SYMBOL_GPL(fsg_common_create_lun); int fsg_common_create_luns(struct fsg_common *common, struct fsg_config *cfg) { - char buf[8]; /* enough for 100000000 different numbers, decimal */ + char buf[14]; int i, rc; fsg_common_remove_luns(common); From 2c0f5ca48674a5b5f9fa4a9c3325aa48053af0bc Mon Sep 17 00:00:00 2001 From: Jeffin Philip Date: Tue, 18 Aug 2026 09:29:04 +0530 Subject: [PATCH 0377/1198] usb: gadget: f_mass_storage: fix null pointer dereference in fsg_common_set_num_buffers() Previously fsg_num_buffers_validate() was removed as it was not necessary due to Kconfig setting the limits for n from 2 to 256 with default as 2. However, setting the page content in such a way that kstrtou8() reflects n value as either 0 or 1 bypasses these restrictions leading to a null pointer dereference if n is 0. Fix this by adding a check for n < 2 and returning -EINVAL if n is either 0 or 1 consistent with Kconfig logic. Reported-by: syzbot+791be35f1fbcc85d06d7@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=791be35f1fbcc85d06d7 Fixes: fe5a6c48fd95 ("usb: gadget: storage: get rid of fsg_num_buffers_validate()") Cc: stable Signed-off-by: Jeffin Philip Acked-by: Alan Stern Link: https://patch.msgid.link/20260818035904.10324-1-jeffinphilip14@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_mass_storage.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c index 1a0fbc808ee2..fc4818fb2a8b 100644 --- a/drivers/usb/gadget/function/f_mass_storage.c +++ b/drivers/usb/gadget/function/f_mass_storage.c @@ -2747,6 +2747,9 @@ int fsg_common_set_num_buffers(struct fsg_common *common, unsigned int n) struct fsg_buffhd *bh, *buffhds; int i; + if (n < 2) + return -EINVAL; + buffhds = kzalloc_objs(*buffhds, n); if (!buffhds) return -ENOMEM; From 7b0df6efd143f8085bdb68778a013a46f1349913 Mon Sep 17 00:00:00 2001 From: Fan Wu Date: Wed, 19 Aug 2026 16:14:48 +0000 Subject: [PATCH 0378/1198] usb: typec: qcom-pmic: cancel reset_work on stop pdphy_stop() disables IRQs but leaves reset_work pending. If the IRQ handler schedules it just before disable_irq(), the work runs after remove() frees the struct via devm. Call cancel_work_sync() after disabling IRQs to close the window. This issue was found by an in-house static analysis tool. Fixes: a4422ff22142 ("usb: typec: qcom: Add Qualcomm PMIC Type-C driver") Cc: stable Assisted-by: Codex:gpt-5.6 Signed-off-by: Fan Wu Reviewed-by: Konrad Dybcio Reviewed-by: Bryan O'Donoghue Reviewed-by: Heikki Krogerus Link: https://patch.msgid.link/20260819161448.76597-1-fanwu01@zju.edu.cn Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c index e6b28648f440..926fa017ebaf 100644 --- a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c +++ b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c @@ -543,6 +543,8 @@ static void qcom_pmic_typec_pdphy_stop(struct pmic_typec *tcpm) for (i = 0; i < pmic_typec_pdphy->nr_irqs; i++) disable_irq(pmic_typec_pdphy->irq_data[i].irq); + cancel_work_sync(&pmic_typec_pdphy->reset_work); + qcom_pmic_typec_pdphy_reset_on(pmic_typec_pdphy); regulator_disable(pmic_typec_pdphy->vdd_pdphy); From 6e74ac5c596fd246e37eadfc354567179ccbe9aa Mon Sep 17 00:00:00 2001 From: Jeffin Philip Date: Sun, 16 Aug 2026 11:47:12 +0530 Subject: [PATCH 0379/1198] usb: gadget: fix null pointer dereference in usb_put_function_instance() usb_put_function_instance() attempts to dereference fd inside fi struct to get mod in uvc_alloc_inst() error path. However, fd is not allocated until later in try_get_usb_function_instance() after allocating fi in uvc_alloc_inst() and thus guranteed to be null in error path. Fix this by adding a null check for fi->fd that returns if fd is null. Reported-by: syzbot+fd6ef980cf1c722be639@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=fd6ef980cf1c722be639 Fixes: 0062f6e56f70 ("usb: gadget: add a forward pointer from usb_function to its "instance"") Cc: stable Signed-off-by: Jeffin Philip Link: https://patch.msgid.link/20260816061712.15547-1-jeffinphilip14@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/functions.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/gadget/functions.c b/drivers/usb/gadget/functions.c index 203361a64212..70e31c40e267 100644 --- a/drivers/usb/gadget/functions.c +++ b/drivers/usb/gadget/functions.c @@ -70,7 +70,7 @@ void usb_put_function_instance(struct usb_function_instance *fi) { struct module *mod; - if (!fi) + if (!fi || !fi->fd) return; mod = fi->fd->mod; From 263f7d61a4201cde16849b2d016251806e7418be Mon Sep 17 00:00:00 2001 From: Fan Wu Date: Thu, 20 Aug 2026 13:53:06 +0000 Subject: [PATCH 0380/1198] usb: typec: qcom-pmic-typec: disable cc_debounce_dwork on stop cc_debounce_dwork is queued from the set_cc() and start_toggling() callbacks, which run from TCPM's kthread worker. port_stop() returns before tcpm_unregister_port() destroys that worker. Flushing the worker during unregister may therefore run a callback which queues the delayed work after port_stop() has returned. The delayed work can then run after devres has freed pmic_typec_port. Use disable_delayed_work_sync() in port_stop() to cancel a pending instance and prevent the TCPM callbacks from queueing another one. This issue was found by an in-house static analysis tool. Fixes: a4422ff22142 ("usb: typec: qcom: Add Qualcomm PMIC Type-C driver") Cc: stable # v6.10+ Assisted-by: Codex:gpt-5.6 Signed-off-by: Fan Wu Acked-by: Heikki Krogerus Link: https://patch.msgid.link/20260820135307.153773-2-fanwu01@zju.edu.cn Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_port.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_port.c b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_port.c index bf985efe1cd6..d43799f43184 100644 --- a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_port.c +++ b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_port.c @@ -693,6 +693,8 @@ static void qcom_pmic_typec_port_stop(struct pmic_typec *tcpm) for (i = 0; i < pmic_typec_port->nr_irqs; i++) disable_irq(pmic_typec_port->irq_data[i].irq); + + disable_delayed_work_sync(&pmic_typec_port->cc_debounce_dwork); } int qcom_pmic_typec_port_probe(struct platform_device *pdev, From c9273c83885835dbd1e8835d5665dfb8503d65e0 Mon Sep 17 00:00:00 2001 From: Fan Wu Date: Thu, 20 Aug 2026 13:53:07 +0000 Subject: [PATCH 0381/1198] usb: typec: qcom-pmic-typec: drain cc_debounce_dwork if port_start() fails cc_debounce_dwork can be queued before port_start() fails: tcpm_register_port() runs first, and its state machine may invoke set_cc() or start_toggling() from the TCPM worker. The error path then calls tcpm_unregister_port(), whose worker flush may queue the delayed work before devres frees pmic_typec_port. Disable and drain the delayed work directly at port_start()'s error exit. Do not use port_stop() for this path: its IRQs use IRQF_NO_AUTOEN and are enabled only after a successful port_start(). This issue was found by an in-house static analysis tool. Fixes: a4422ff22142 ("usb: typec: qcom: Add Qualcomm PMIC Type-C driver") Cc: stable # v6.10+ Suggested-by: Bryan O'Donoghue Assisted-by: Codex:gpt-5.6 Signed-off-by: Fan Wu Acked-by: Heikki Krogerus Link: https://patch.msgid.link/20260820135307.153773-3-fanwu01@zju.edu.cn Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_port.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_port.c b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_port.c index d43799f43184..d3523435f3e0 100644 --- a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_port.c +++ b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_port.c @@ -683,6 +683,9 @@ static int qcom_pmic_typec_port_start(struct pmic_typec *tcpm, enable_irq(pmic_typec_port->irq_data[i].irq); done: + if (ret) + disable_delayed_work_sync(&pmic_typec_port->cc_debounce_dwork); + return ret; } From bb3a94a6828336dcc2dd891e51ebd92dcdd0b576 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 20 Aug 2026 17:23:29 +0200 Subject: [PATCH 0382/1198] drivers: base: test: DRIVER_PE_KUNIT_TEST should not select OF Enabling a (modular) test should not silently enable additional kernel functionality, as that may increase the attack vector for a product. Fix this by skipping the new test when OF support is disabled instead of selecting OF support. Note that when OF support is disabled, the compiler optimizes away the then unused reference to of_fwnode_ops in of_node_init(), so linking succeeds. Fixes: 0e6f8ccd4618afdb ("device property: add test cases for fwnode_for_each_child_node()") Signed-off-by: Geert Uytterhoeven Link: https://patch.msgid.link/8dfb4afaf70b59cd33af9296464395470405187e.1787239268.git.geert@linux-m68k.org Signed-off-by: Danilo Krummrich --- drivers/base/test/Kconfig | 1 - drivers/base/test/property-entry-test.c | 3 +++ 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/base/test/Kconfig b/drivers/base/test/Kconfig index 542ce07530a1..1ecf0791241a 100644 --- a/drivers/base/test/Kconfig +++ b/drivers/base/test/Kconfig @@ -17,7 +17,6 @@ config DM_KUNIT_TEST config DRIVER_PE_KUNIT_TEST tristate "KUnit Tests for property entry API" if !KUNIT_ALL_TESTS depends on KUNIT - select OF default KUNIT_ALL_TESTS config DRIVER_SWNODE_KUNIT_TEST diff --git a/drivers/base/test/property-entry-test.c b/drivers/base/test/property-entry-test.c index 855e73b9b21f..89cdfc2f8498 100644 --- a/drivers/base/test/property-entry-test.c +++ b/drivers/base/test/property-entry-test.c @@ -523,6 +523,9 @@ static void pe_test_child_iteration(struct kunit *test) struct fwnode_handle *child; int error, i, num; + if (!IS_ENABLED(CONFIG_OF)) + kunit_skip(test, "requires CONFIG_OF"); + static const struct software_node node = { .name = "sw" }; static const struct software_node node1 = { .name = "sw-1", .parent = &node}; static const struct software_node node2 = { .name = "sw-2", .parent = &node}; From 6d94c47a2e3a38170a0a141547e4c52fbe232cc3 Mon Sep 17 00:00:00 2001 From: Christian Marangi Date: Fri, 21 Aug 2026 10:52:15 +0200 Subject: [PATCH 0383/1198] pmdomain: airoha: fix unselectable AIROHA_CPU_PM_DOMAIN kconfig The AIROHA_CPU_PM_DOMAIN config was wrongly guarded under the Mediatek PM Domains menu and was unselectable. Move it outside the menu so it's now visible and correctly selectable by default on Airoha SoC. Cc: stable@vger.kernel.org Fixes: 82e703dd438b ("pmdomain: airoha: Add Airoha CPU PM Domain support") Signed-off-by: Christian Marangi Reviewed-by: Abel Vesa Signed-off-by: Ulf Hansson --- drivers/pmdomain/mediatek/Kconfig | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/pmdomain/mediatek/Kconfig b/drivers/pmdomain/mediatek/Kconfig index 8923e6516441..a2eb704a773c 100644 --- a/drivers/pmdomain/mediatek/Kconfig +++ b/drivers/pmdomain/mediatek/Kconfig @@ -43,9 +43,12 @@ config MTK_MFG_PM_DOMAIN This driver is required for the Mali GPU to work at all on MT8196 and MT6991. +endmenu + config AIROHA_CPU_PM_DOMAIN tristate "Airoha CPU power domain" default ARCH_AIROHA + depends on ARCH_AIROHA || COMPILE_TEST depends on HAVE_ARM_SMCCC depends on PM select PM_GENERIC_DOMAINS @@ -54,5 +57,3 @@ config AIROHA_CPU_PM_DOMAIN CPU frequency and power is controlled by ATF with SMC command to set performance states. - -endmenu From 4956993bb3befdf791d71a4952d8d13bcfd44c7b Mon Sep 17 00:00:00 2001 From: Wei Jie Law <98lawweijie@gmail.com> Date: Tue, 25 Aug 2026 18:31:17 +0800 Subject: [PATCH 0384/1198] HID: rmi: fix OOB access with undersized RMI reports The hid-rmi driver sizes its writeReport/readReport buffer purely from the report descriptor supplied by the device, with no minimum bound: data->input_report_size = hid_report_len(input_report); data->output_report_size = hid_report_len(output_report); alloc_size = data->output_report_size + data->input_report_size; data->writeReport = devm_kzalloc(&hdev->dev, alloc_size, GFP_KERNEL); data->readReport = data->writeReport + data->output_report_size; but then reads and writes fixed offsets into it. A device declaring a 1-byte output and a 1-byte input report makes hid_report_len() return 2 for each, so alloc_size is 4, while rmi_set_page() -- reached unconditionally at probe time through rmi_input_configured() -- stores writeReport[4] and rmi_hid_read_block() stores writeReport[0..5]. Since readReport lives at writeReport + output_report_size, those stores also corrupt the window the next reply is parsed out of. The read path is worse: the copy length comes from readReport[1], which the device fills in and can be up to 255, and the copy starts at &readReport[2] with no regard for input_report_size, so it runs past the end of the allocation into adjacent slab objects. This does not even need a lying device -- rmi_f01_probe() issues a fixed 21-byte register read, so any device declaring an input report smaller than 23 bytes reads out of bounds even when it answers truthfully. Those bytes become the register values the RMI core acts on: rmi_f01_probe() prints them to the kernel log as the product id and exports them through the mode 0444 sysfs attribute of the same name, and rmi_driver_set_irq_bits() sends them back to the device as the interrupt mask, so an undersized report descriptor leaks heap contents both to unprivileged userspace and to the device itself. The write path has no bound either: rmi_hid_write_block() copies an unbounded len to &writeReport[4], and the largest caller a device can drive at probe time is rmi_driver_set_irq_bits(), whose length is derived from the interrupt source counts the device declares in its Page Description Table. Finally, the read loop cannot terminate on a zero-length reply: such a reply copies nothing and advances neither bytes_read nor bytes_needed, and because a reply did arrive the one second wait_event_timeout() does not fire either, so a device answering 0 forever keeps the loop running inside the probe worker with page_mutex held. khungtaskd does not notice, because every reply wakes the task. Reject reports too small for what the driver builds -- 6 output bytes for the write reports and 3 input bytes for the read handshake -- at probe time, clamp the write and the read copy to the report sizes the device declared, and treat a zero-length reply as an error. A device refused this way is started as an ordinary HID device, like one that does not carry the RMI report ids at all. RMI_DEVICE must not be left set in device_flags on that path, because rmi_input_configured() would then run the RMI setup and reach rmi_set_page(), which writes the writeReport buffer the refusal just skipped allocating. The bit can arrive set: rmi_probe() copies id->driver_data into device_flags before the report checks, and a bind through the new_id sysfs attribute can supply driver_data with RMI_DEVICE (BIT(0)) set. Strip the bit where driver_data is copied, so RMI_DEVICE keeps meaning exactly "this probe validated the reports"; the three jumps to start that predate this patch are covered as well. The error path also clears RMI_READ_DATA_PENDING on its way out, because that flag is what the wait at the top of the loop tests: leaving it set would make every later wait_event_timeout() return immediately on the stale reply and kill the read path for the rest of the device's life. Clamping does not regress working hardware: the read loop already handles a reply carrying fewer bytes than requested, and a write longer than the output report was overrunning the buffer already. Verified on v6.12.69 and on v6.12.105 built with CONFIG_KASAN=y and booted kasan_multi_shot, whose hid-rmi.c is identical to mainline here. An emulated RMI4 device driven over /dev/uhid, and the same device again over dummy_hcd plus raw-gadget, give identical results: BUG: KASAN: slab-out-of-bounds in rmi_hid_read_block+0x409/0x750 [hid_rmi] Read of size 21 at addr ffff88800bf33bba by task kworker/0:3/285 __asan_memcpy+0x23/0x60 rmi_hid_read_block+0x409/0x750 [hid_rmi] rmi_f01_probe+0x5dd/0x1dc0 [rmi_core] BUG: KASAN: slab-out-of-bounds in rmi_hid_write_block+0x1a9/0x350 [hid_rmi] Write of size 35 at addr ffff88810a2b24ac by task kworker/1:10/666 __asan_memcpy+0x3c/0x60 rmi_hid_write_block+0x1a9/0x350 [hid_rmi] rmi_driver_set_irq_bits+0x1f6/0x4d0 [rmi_core] rmi_driver_probe+0x636/0xbf0 [rmi_core] rmi_input_configured+0x184/0x2e0 [hid_rmi] rmi_probe+0x952/0xcf0 [hid_rmi] and, for the zero-length reply, a probe worker left in D state in rmi_hid_read_block() after 225 replies at 200 ms intervals. After this change the undersized descriptor is refused at probe with "rmi reports too small (out=2 in=2)", the oversized read and write are both rejected, the zero-length reply fails the read with -EIO while later reads on the same device keep working, and a device declaring reports large enough for a 21-byte register read still probes normally and reports its real product id. A device bound through new_id with RMI_DEVICE in its driver_data no longer reaches rmi_set_page() with an unallocated writeReport either. Link: https://lore.kernel.org/linux-input/20260822121007.153988-1-98lawweijie@gmail.com/ Link: https://lore.kernel.org/linux-input/00a489f38b240624dcb5a4bae36a53fcba9cfb47.1787549195.git.98lawweijie@gmail.com/ Link: https://lore.kernel.org/linux-input/20260824122708.76168-1-98lawweijie@gmail.com/ Link: https://lore.kernel.org/linux-input/20260825060954.104890-1-98lawweijie@gmail.com/ Fixes: 9fb6bf02e3ad ("HID: rmi: introduce RMI driver for Synaptics touchpads") Cc: stable@vger.kernel.org Assisted-by: Claude:claude-opus-5 Assisted-by: GLM:glm-5.3 Signed-off-by: Wei Jie Law <98lawweijie@gmail.com> Signed-off-by: Jiri Kosina --- drivers/hid/hid-rmi.c | 46 ++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 43 insertions(+), 3 deletions(-) diff --git a/drivers/hid/hid-rmi.c b/drivers/hid/hid-rmi.c index 2bd781f1e0f5..ecc19387f6b0 100644 --- a/drivers/hid/hid-rmi.c +++ b/drivers/hid/hid-rmi.c @@ -235,7 +235,23 @@ static int rmi_hid_read_block(struct rmi_transport_dev *xport, u16 addr, break; } - read_input_count = data->readReport[1]; + read_input_count = min_t(int, data->readReport[1], + data->input_report_size - 2); + if (!read_input_count) { + /* + * A zero length reply advances neither + * bytes_read nor bytes_needed, and because a + * reply did arrive the wait above does not + * time out either, so a device answering 0 + * forever would spin here indefinitely with + * page_mutex held. + */ + hid_warn(hdev, "%s: zero-length read reply\n", + __func__); + clear_bit(RMI_READ_DATA_PENDING, &data->flags); + ret = -EIO; + break; + } memcpy(buf + bytes_read, &data->readReport[2], min(read_input_count, bytes_needed)); @@ -271,6 +287,11 @@ static int rmi_hid_write_block(struct rmi_transport_dev *xport, u16 addr, goto exit; } + if (len + 4 > data->output_report_size) { + ret = -EINVAL; + goto exit; + } + data->writeReport[0] = RMI_WRITE_REPORT_ID; data->writeReport[1] = len; data->writeReport[2] = addr & 0xFF; @@ -666,8 +687,16 @@ static int rmi_probe(struct hid_device *hdev, const struct hid_device_id *id) return ret; } - if (id->driver_data) - data->device_flags = id->driver_data; + /* + * RMI_DEVICE can only mean "this probe validated the RMI reports and + * allocated writeReport": every bail-out to start below skips that + * allocation, and device_flags left carrying RMI_DEVICE from + * driver_data would send rmi_input_configured() into rmi_set_page() + * with writeReport still NULL. A bind through the new_id sysfs + * attribute can supply driver_data with the bit set, so do not let + * driver_data grant it. + */ + data->device_flags = id->driver_data & ~RMI_DEVICE; /* * Check for the RMI specific report ids. If they are misisng @@ -696,6 +725,17 @@ static int rmi_probe(struct hid_device *hdev, const struct hid_device_id *id) data->output_report_size = hid_report_len(output_report); + /* + * The write reports built by this driver occupy 6 bytes and the read + * handshake looks at the first 3 bytes of an input report, so refuse + * to drive a device whose reports cannot hold them. + */ + if (data->output_report_size < 6 || data->input_report_size < 3) { + hid_err(hdev, "rmi reports too small (out=%u in=%u)\n", + data->output_report_size, data->input_report_size); + goto start; + } + data->device_flags |= RMI_DEVICE; alloc_size = data->output_report_size + data->input_report_size; From 7b15d6cf25e6c2aea77129179b75c191b20d79a9 Mon Sep 17 00:00:00 2001 From: Hengyu Liang Date: Sat, 22 Aug 2026 01:17:05 -0400 Subject: [PATCH 0385/1198] kernfs: preserve security xattrs without allocating iattrs Commit d5e81a5650b5 ("kernfs: avoid iattr allocation in listxattr") made kernfs_iop_listxattr() return an empty list when the kernfs node has no allocated kernfs_iattrs. However, this also skips security xattr names provided by simple_xattr_list(). As of now, applications can retrieve the SELinux label of a sysfs file with getxattr(), but cannot do it through listxattr(). A similar issue happened before in commit b09e0fa4b4ea ("tmpfs: implement generic xattr support"). It was fixed by commit 8b0ba61df5a1c ("fs/xattr.c: fix simple_xattr_list to always include security.* xattrs"). Perhaps this recent commit needs a fix as well. The issue can be reproduced with a simple python program: python3 - <<'PY' import os path = "/sys/kernel/warn_count" print("getxattr:", os.getxattr(path, "security.selinux")) print("listxattr:", os.listxattr(path)) PY Before commit d5e81a5650b5 ("kernfs: avoid iattr allocation in listxattr"), the result is: getxattr: b'system_u:object_r:sysfs_t:s0\x00' listxattr: ['security.selinux'] After that commit, the result is: getxattr: b'system_u:object_r:sysfs_t:s0\x00' listxattr: [] This patch will keep listxattr() consistent with getxattr() when security xattrs are available. Fixes: d5e81a5650b5 ("kernfs: avoid iattr allocation in listxattr") Signed-off-by: Hengyu Liang Acked-by: Tejun Heo Link: https://patch.msgid.link/20260822051705.1761850-1-hengyul@cs.unc.edu Signed-off-by: Danilo Krummrich --- fs/kernfs/inode.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index 237dcdd73fc2..abb286bc3474 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -142,10 +142,8 @@ ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size) struct kernfs_iattrs *attrs; attrs = kernfs_iattrs_noalloc(kn); - if (!attrs) - return 0; - return simple_xattr_list(d_inode(dentry), &attrs->xattrs, buf, size); + return simple_xattr_list(d_inode(dentry), attrs ? &attrs->xattrs : NULL, buf, size); } static inline void set_default_inode_attr(struct inode *inode, umode_t mode) From 2b0ac85512b7f67479127b2713254490662eb13d Mon Sep 17 00:00:00 2001 From: Linkai Gong Date: Fri, 21 Aug 2026 15:57:28 +0800 Subject: [PATCH 0386/1198] cpuidle: dt_idle_genpd: kfree() the original name allocation dt_idle_pd_alloc() kasprintf()s the full node path, then points pd->name at kbasename() of that string. dt_idle_pd_free() kfree()s pd->name, which is no longer the start of the allocation. Copy the basename instead. Fixes: 9d976d6721df ("cpuidle: Factor-out power domain related code from PSCI domain driver") Signed-off-by: Linkai Gong Cc: stable@vger.kernel.org Signed-off-by: Ulf Hansson --- drivers/cpuidle/dt_idle_genpd.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/cpuidle/dt_idle_genpd.c b/drivers/cpuidle/dt_idle_genpd.c index d292975cc468..ed41a90eeeb7 100644 --- a/drivers/cpuidle/dt_idle_genpd.c +++ b/drivers/cpuidle/dt_idle_genpd.c @@ -99,7 +99,7 @@ struct generic_pm_domain *dt_idle_pd_alloc(struct device_node *np, if (!pd) goto out; - pd->name = kasprintf(GFP_KERNEL, "%pOF", np); + pd->name = kstrdup(kbasename(of_node_full_name(np)), GFP_KERNEL); if (!pd->name) goto free_pd; @@ -112,7 +112,6 @@ struct generic_pm_domain *dt_idle_pd_alloc(struct device_node *np, goto free_name; pd->free_states = pd_free_states; - pd->name = kbasename(pd->name); pd->states = states; pd->state_count = state_count; From 3663c8d1f31e65771bd73ee3259f35fd397f9933 Mon Sep 17 00:00:00 2001 From: Lu Yao Date: Mon, 31 Aug 2026 09:42:18 +0800 Subject: [PATCH 0387/1198] drm/xe/oa: Remove sysfs entry on idr_alloc failure in xe_oa_add_config_ioctl() If idr_alloc() fails after create_dynamic_oa_sysfs_entry() has succeeded, the error path frees the OA config without removing the metrics sysfs group. Remove the sysfs group before releasing the config, and fix up the misleading error message copied from the sysfs creation failure path. Fixes: cdf02fe1a94a ("drm/xe/oa/uapi: Add/remove OA config perf ops") Signed-off-by: Lu Yao Link: https://patch.msgid.link/20260831014218.28515-1-yaolu@kylinos.cn Reviewed-by: Rodrigo Vivi Signed-off-by: Rodrigo Vivi (cherry picked from commit 2c6fbda5fdde461d6dedb82a59285182720b8fef) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/xe_oa.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c index 9c5384b95c63..ab09dcff5860 100644 --- a/drivers/gpu/drm/xe/xe_oa.c +++ b/drivers/gpu/drm/xe/xe_oa.c @@ -2435,9 +2435,9 @@ int xe_oa_add_config_ioctl(struct drm_device *dev, u64 data, struct drm_file *fi oa_config->id = idr_alloc(&oa->metrics_idr, oa_config, 1, 0, GFP_KERNEL); if (oa_config->id < 0) { - drm_dbg(&oa->xe->drm, "Failed to create sysfs entry for OA config\n"); + drm_dbg(&oa->xe->drm, "Failed to allocate id for OA config\n"); err = oa_config->id; - goto sysfs_err; + goto id_alloc_err; } id = oa_config->id; @@ -2448,6 +2448,8 @@ int xe_oa_add_config_ioctl(struct drm_device *dev, u64 data, struct drm_file *fi return id; +id_alloc_err: + sysfs_remove_group(oa->metrics_kobj, &oa_config->sysfs_metric); sysfs_err: mutex_unlock(&oa->metrics_lock); reg_err: From 8d7b3e41ffecc69388a566ecc52093d292074c2a Mon Sep 17 00:00:00 2001 From: Sophon Zhang Date: Tue, 1 Sep 2026 01:09:53 +0800 Subject: [PATCH 0388/1198] rust: pci: reject IRQ vector indices that do not fit in u32 IrqVectorRegistration::index() accepts a usize, but pci_irq_vector() takes an unsigned int. On 64-bit architectures, casting an index larger than u32::MAX wraps it before the PCI core can validate it. In particular, u32::MAX + 1 becomes zero and can resolve to the first allocated vector. Use a checked conversion and return EINVAL when the index cannot be represented by the C API. Fixes: 2fb7755b0a7e ("rust: pci: resolve IRQ in index() and embed IrqRequest in IrqVector") Signed-off-by: Sophon Zhang Reviewed-by: Gary Guo Reviewed-by: Alexandre Courbot Link: https://patch.msgid.link/20260901-fix-pci-irq-vector-index-truncation-v4-1-f94aa6932fd9@hotmail.com Signed-off-by: Danilo Krummrich --- rust/kernel/pci/irq.rs | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/rust/kernel/pci/irq.rs b/rust/kernel/pci/irq.rs index 6741046ec1c0..22e2cdf82a21 100644 --- a/rust/kernel/pci/irq.rs +++ b/rust/kernel/pci/irq.rs @@ -151,8 +151,10 @@ pub fn irq_type(&self) -> IrqType { /// [`Self::len()`]. #[inline] pub fn index(&self, index: usize) -> Result> { + let index = u32::try_from(index)?; + // SAFETY: `self.dev.as_raw()` is a valid pointer to a `struct pci_dev`. - let irq = unsafe { bindings::pci_irq_vector(self.dev.as_raw(), index as u32) }; + let irq = unsafe { bindings::pci_irq_vector(self.dev.as_raw(), index) }; if irq < 0 { return Err(Error::from_errno(irq)); } From 6db237eb516774a76b0d6ab8b4090185f6f2f956 Mon Sep 17 00:00:00 2001 From: Russ Weight Date: Tue, 18 Aug 2026 13:46:46 -0600 Subject: [PATCH 0389/1198] firmware_loader: Change contact for sysfs nodes Change the contact name for the firmware_loader sysfs nodes to driver-core@lists.linux.dev. Signed-off-by: Russ Weight Link: https://patch.msgid.link/20260818194648.1014604-2-russ.weight@linux.dev [ Since we have a driver-core mailing list, use it as contact information instead of myself. - Danilo ] Signed-off-by: Danilo Krummrich --- Documentation/ABI/testing/sysfs-class-firmware | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-class-firmware b/Documentation/ABI/testing/sysfs-class-firmware index fba87a55f3ca..44ca1b78a0e1 100644 --- a/Documentation/ABI/testing/sysfs-class-firmware +++ b/Documentation/ABI/testing/sysfs-class-firmware @@ -1,7 +1,7 @@ What: /sys/class/firmware/.../data Date: July 2022 KernelVersion: 5.19 -Contact: Russ Weight +Contact: driver-core@lists.linux.dev Description: The data sysfs file is used for firmware-fallback and for firmware uploads. Cat a firmware image to this sysfs file after you echo 1 to the loading sysfs file. When the firmware @@ -13,7 +13,7 @@ Description: The data sysfs file is used for firmware-fallback and for What: /sys/class/firmware/.../cancel Date: July 2022 KernelVersion: 5.19 -Contact: Russ Weight +Contact: driver-core@lists.linux.dev Description: Write-only. For firmware uploads, write a "1" to this file to request that the transfer of firmware data to the lower-level device be canceled. This request will be rejected (EBUSY) if @@ -23,7 +23,7 @@ Description: Write-only. For firmware uploads, write a "1" to this file to What: /sys/class/firmware/.../error Date: July 2022 KernelVersion: 5.19 -Contact: Russ Weight +Contact: driver-core@lists.linux.dev Description: Read-only. Returns a string describing a failed firmware upload. This string will be in the form of :, where will be one of the status strings described @@ -37,7 +37,7 @@ Description: Read-only. Returns a string describing a failed firmware What: /sys/class/firmware/.../loading Date: July 2022 KernelVersion: 5.19 -Contact: Russ Weight +Contact: driver-core@lists.linux.dev Description: The loading sysfs file is used for both firmware-fallback and for firmware uploads. Echo 1 onto the loading file to indicate you are writing a firmware file to the data sysfs node. Echo @@ -49,7 +49,7 @@ Description: The loading sysfs file is used for both firmware-fallback and What: /sys/class/firmware/.../remaining_size Date: July 2022 KernelVersion: 5.19 -Contact: Russ Weight +Contact: driver-core@lists.linux.dev Description: Read-only. For firmware upload, this file contains the size of the firmware data that remains to be transferred to the lower-level device driver. The size value is initialized to @@ -62,7 +62,7 @@ Description: Read-only. For firmware upload, this file contains the size What: /sys/class/firmware/.../status Date: July 2022 KernelVersion: 5.19 -Contact: Russ Weight +Contact: driver-core@lists.linux.dev Description: Read-only. Returns a string describing the current status of a firmware upload. The string will be one of the following: idle, "receiving", "preparing", "transferring", "programming". @@ -70,7 +70,7 @@ Description: Read-only. Returns a string describing the current status of What: /sys/class/firmware/.../timeout Date: July 2022 KernelVersion: 5.19 -Contact: Russ Weight +Contact: driver-core@lists.linux.dev Description: This file supports the timeout mechanism for firmware fallback. This file has no affect on firmware uploads. For more information on timeouts please see the documentation From 0d3e690c112939d869931a5c8c0bb23718d58370 Mon Sep 17 00:00:00 2001 From: Russ Weight Date: Tue, 18 Aug 2026 13:46:47 -0600 Subject: [PATCH 0390/1198] CREDITS: Add CREDITS entry for Firmware Upload Add an entry to the CREDITS file for the Firmware Upload functionality of the Firmware Loader. Signed-off-by: Russ Weight Link: https://patch.msgid.link/20260818194648.1014604-3-russ.weight@linux.dev Signed-off-by: Danilo Krummrich --- CREDITS | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/CREDITS b/CREDITS index a1455b471051..8d52aa65a858 100644 --- a/CREDITS +++ b/CREDITS @@ -4305,6 +4305,10 @@ N: Juergen Weigert E: jnweiger@immd4.informatik.uni-erlangen.de D: The Linux Support Team Erlangen +N: Russ Weight +E: russ.weight@gmail.com +D: Added support for Firmware Upload to the Firmware Loader + N: David Weinehall E: tao@acc.umu.se P: 1024D/DC47CA16 7ACE 0FB0 7A74 F994 9B36 E1D1 D14E 8526 DC47 CA16 From f6d752278c13839888425294c110174fb6c87e3d Mon Sep 17 00:00:00 2001 From: Russ Weight Date: Tue, 18 Aug 2026 13:46:48 -0600 Subject: [PATCH 0391/1198] MAINTAINERS: Remove Russ Weight from Firmware Loader Remove Russ Weight from the MAINTAINERS for FIRMWARE LOADER. Signed-off-by: Russ Weight Link: https://patch.msgid.link/20260818194648.1014604-4-russ.weight@linux.dev Signed-off-by: Danilo Krummrich --- MAINTAINERS | 1 - 1 file changed, 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 3a19da74d00c..36159e6437d5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10193,7 +10193,6 @@ F: include/linux/arm_ffa.h FIRMWARE LOADER (request_firmware) M: Luis Chamberlain -M: Russ Weight M: Danilo Krummrich L: driver-core@lists.linux.dev S: Maintained From 9cdc7e6dc7a99ad7311ad5e7c145f2b9ce4e24b0 Mon Sep 17 00:00:00 2001 From: Shen Yongchao Date: Mon, 3 Aug 2026 22:31:57 +0800 Subject: [PATCH 0392/1198] HID: bpf: serialize device reference release in struct_ops destroy path __hid_bpf_ops_destroy_device() and hid_bpf_unreg() can race on the same registration reference, double-putting struct hid_device and freeing it while hid_destroy_device() still uses it. Serialize the remove/NULL decision under hdev->bpf.prog_list_lock so exactly one path releases each registration reference: unreg re-checks ops->hdev under the lock and returns without putting when the destroy path already cleared it; all put_device() calls happen after the lock is dropped, which is safe because a concurrent unreg then observes ops->hdev == NULL under the lock. Background: each successful attach (hid_bpf_ops_reg) acquires one device reference (hid_get_device()). Two paths can release it: - device destruction: hid_destroy_device() -> hid_bpf_destroy_device() -> __hid_bpf_ops_destroy_device(), which walks hdev->bpf.prog_list under rcu_read_lock() and drops one reference per attached program; - BPF link release: bpf map delete (no BPF_F_LINK) synchronously calls st_ops->unreg() -> hid_bpf_unreg(), which drops the reference for its own registration. The coordination handshake (e->hdev = NULL on the destroy side vs "if (!hdev) return" on the unreg side) is a TOCTOU check: the two paths run under different lock domains (rcu_read_lock vs prog_list_lock), so a concurrent unreg can read ops->hdev as non-NULL, block on prog_list_lock, and then proceed while the destroy traversal executes - both paths then drop the same reference. The refcount reaches zero legitimately (each decrement is individually valid), so no refcount_t saturation fires: the device is simply freed while the transport is still inside hid_destroy_device(), and subsequent teardown touches freed memory. The fix serializes the remove/NULL decision under prog_list_lock on both sides and moves the destroy-side puts outside the lock. With the lock held, plain reads/writes of ops->hdev are sufficient; no READ_ONCE/WRITE_ONCE are added, keeping the patch minimal. Unlocked-read safety: the unlocked read of ops->hdev at the top of hid_bpf_unreg() cannot touch a freed device, because the unreg path itself still holds this registration's reference (released only by its own hid_put_device() after the lock is dropped), and a destroy traversal that already cleared ops->hdev makes the lock-internal re-check return early without any put. At most one of the two paths releases each registration reference. Fixes: ebc0d8093e8c ("HID: bpf: implement HID-BPF through bpf_struct_ops") Cc: stable@vger.kernel.org Signed-off-by: Shen Yongchao Assisted-by: Hermes:kimi-k3 Signed-off-by: Benjamin Tissoires --- drivers/hid/bpf/hid_bpf_struct_ops.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/drivers/hid/bpf/hid_bpf_struct_ops.c b/drivers/hid/bpf/hid_bpf_struct_ops.c index 56c53aca4511..c90b68956cb3 100644 --- a/drivers/hid/bpf/hid_bpf_struct_ops.c +++ b/drivers/hid/bpf/hid_bpf_struct_ops.c @@ -256,6 +256,11 @@ static void hid_bpf_unreg(void *kdata, struct bpf_link *link) mutex_lock(&hdev->bpf.prog_list_lock); + if (!ops->hdev) { + mutex_unlock(&hdev->bpf.prog_list_lock); + return; + } + list_del_rcu(&ops->list); synchronize_srcu(&hdev->bpf.srcu); ops->hdev = NULL; @@ -316,13 +321,17 @@ static struct bpf_struct_ops bpf_hid_bpf_ops = { void __hid_bpf_ops_destroy_device(struct hid_device *hdev) { struct hid_bpf_ops *e; + int count = 0; - rcu_read_lock(); - list_for_each_entry_rcu(e, &hdev->bpf.prog_list, list) { - hid_put_device(hdev); + mutex_lock(&hdev->bpf.prog_list_lock); + list_for_each_entry(e, &hdev->bpf.prog_list, list) { e->hdev = NULL; + count++; } - rcu_read_unlock(); + mutex_unlock(&hdev->bpf.prog_list_lock); + + while (count--) + hid_put_device(hdev); } static int __init hid_bpf_struct_ops_init(void) From 0ba8e0f90039da68342febf613019f4a68d86620 Mon Sep 17 00:00:00 2001 From: Taimuraz Kaitmazov Date: Thu, 20 Aug 2026 01:44:57 +0300 Subject: [PATCH 0393/1198] accel/amdxdna: refuse to flush an imported BO MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit SYNC_BO clflushes an imported BO's scatterlist. An importer may not do that: the memory belongs to the exporter, and dma-buf gives the importer no interface to ask for maintenance on it. Refuse the request instead. is_import_bo() is (obj)->attach, which covers more than foreign buffers. A userptr BO arrives through a ubuf, and on a carveout device every share BO and the device heap arrive through a cbuf, so SYNC_BO answers -EOPNOTSUPP for those too, including the AMDXDNA_BO_DEV path that flushes through its heap. Only the ubuf case gives up maintenance it was getting: on a 64 MiB userptr BO a 4 KiB sync and a full sync both cost 659 us, this arm having ignored the range. amdxdna_cbuf_map() fills in only the DMA address and length, so drm_clflush_sg() already walks zero pages on carveout memory. Userspace maintains these through the mapping it already holds, as XRT's buffer::sync() does unless it is told to sync through the driver. Fixes: dbc8fd7a03cb ("accel/amdxdna: Add expandable device heap support") Reported-by: Christian König Link: https://lore.kernel.org/dri-devel/a505f9e5-b416-43e9-934d-c5c29b8a70e9@amd.com/ Suggested-by: Lizhi Hou Signed-off-by: Taimuraz Kaitmazov Reviewed-by: Lizhi Hou Signed-off-by: Lizhi Hou Link: https://patch.msgid.link/20260819224458.257346-5-taimuraz@kaitmazov.com --- drivers/accel/amdxdna/amdxdna_gem.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/accel/amdxdna/amdxdna_gem.c b/drivers/accel/amdxdna/amdxdna_gem.c index d18de7eb7af4..4b0d58d0329b 100644 --- a/drivers/accel/amdxdna/amdxdna_gem.c +++ b/drivers/accel/amdxdna/amdxdna_gem.c @@ -1246,6 +1246,9 @@ static int amdxdna_flush_bo(struct amdxdna_gem_obj *abo, u64 offset, u64 size) { u64 end; + if (is_import_bo(abo)) + return -EOPNOTSUPP; + if (offset >= abo->mem.size) return -EINVAL; @@ -1256,9 +1259,7 @@ static int amdxdna_flush_bo(struct amdxdna_gem_obj *abo, u64 offset, u64 size) if (!size) return 0; - if (is_import_bo(abo)) - drm_clflush_sg(abo->base.sgt); - else if (amdxdna_gem_vmap(abo)) + if (amdxdna_gem_vmap(abo)) drm_clflush_virt_range(amdxdna_gem_vmap(abo) + offset, size); else if (abo->base.pages) drm_clflush_pages(abo->base.pages, abo->mem.size >> PAGE_SHIFT); From 4a819ee5f2834330656d6ac168c4c8cf27fdeec2 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 31 Aug 2026 22:07:10 +0200 Subject: [PATCH 0394/1198] ACPI: bus: Drop two fields from struct acpi_device_pnp There are two fields in struct acpi_device_pnp, device_name and device_class, that were supposed to be populated and used by device drivers, but they have never been used consistently and now they are only set for the bus object in acpi_set_pnp_ids() (and never read afterward). Drop them along with all of the associated symbols except for MAX_ACPI_CLASS_NAME_LEN and the acpi_device_class typedef that are used by the ACPI netlink messaging code. Move those two definitions closer to the struct acpi_bus_event that refers to the acpi_device_class type. No intentional functional impact. Signed-off-by: Rafael J. Wysocki Reviewed-by: Hans de Goede Reviewed-by: Andy Shevchenko Link: https://patch.msgid.link/6314925.lOV4Wx5bFT@rafael.j.wysocki --- drivers/acpi/scan.c | 4 ---- include/acpi/acpi_bus.h | 11 +++-------- 2 files changed, 3 insertions(+), 12 deletions(-) diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index f48715ed827c..163a3cccf197 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -28,9 +28,7 @@ #include "internal.h" #include "sleep.h" -#define ACPI_BUS_CLASS "system_bus" #define ACPI_BUS_HID "LNXSYBUS" -#define ACPI_BUS_DEVICE_NAME "System Bus" #define INVALID_ACPI_HANDLE ((acpi_handle)ZERO_PAGE(0)) @@ -1450,8 +1448,6 @@ static void acpi_set_pnp_ids(acpi_handle handle, struct acpi_device_pnp *pnp, acpi_object_is_system_bus(handle)) { /* \_SB, \_TZ, LNXSYBUS */ acpi_add_id(pnp, ACPI_BUS_HID); - strscpy(pnp->device_name, ACPI_BUS_DEVICE_NAME); - strscpy(pnp->device_class, ACPI_BUS_CLASS); } break; diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 1a45e0d521d8..a10a591c18b2 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -202,12 +202,8 @@ struct acpi_device_dir { /* Plug and Play */ -#define MAX_ACPI_DEVICE_NAME_LEN 40 -#define MAX_ACPI_CLASS_NAME_LEN 20 typedef char acpi_bus_id[8]; typedef u64 acpi_bus_address; -typedef char acpi_device_name[MAX_ACPI_DEVICE_NAME_LEN]; -typedef char acpi_device_class[MAX_ACPI_CLASS_NAME_LEN]; struct acpi_hardware_id { struct list_head list; @@ -229,16 +225,12 @@ struct acpi_device_pnp { acpi_bus_address bus_address; /* _ADR */ char *unique_id; /* _UID */ struct list_head ids; /* _HID and _CIDs */ - acpi_device_name device_name; /* Driver-determined */ - acpi_device_class device_class; /* " */ }; #define acpi_device_bid(d) ((d)->pnp.bus_id) #define acpi_device_adr(d) ((d)->pnp.bus_address) const char *acpi_device_hid(struct acpi_device *device); #define acpi_device_uid(d) ((d)->pnp.unique_id) -#define acpi_device_name(d) ((d)->pnp.device_name) -#define acpi_device_class(d) ((d)->pnp.device_class) /* Power Management */ @@ -578,6 +570,9 @@ int acpi_dev_for_each_child_reverse(struct acpi_device *adev, * ------ */ +#define MAX_ACPI_CLASS_NAME_LEN 20 +typedef char acpi_device_class[MAX_ACPI_CLASS_NAME_LEN]; + struct acpi_bus_event { struct list_head node; acpi_device_class device_class; From 774b73428e6eabb4f0382aeeb76e569c7b106a29 Mon Sep 17 00:00:00 2001 From: Faith Ekstrand Date: Fri, 21 Aug 2026 23:42:59 -0500 Subject: [PATCH 0395/1198] drm/nouveau: Use write-combined maps for coherent On Tegra devices, uncached maps translate to device memory, causing unaligned accesses by userspace resulting in a SIGBUS. Instead, use write-combined maps to ensure proper access. This would also affect discrete cards on any Arm device. It was determined that discrete cards regardless of cpu arch should use write-combined maps for coherent anyways. Thus this change is made for all gpu types. Cc: stable@vger.kernel.org Signed-off-by: Faith Ekstrand Co-developed-by: Aaron Kling Signed-off-by: Aaron Kling Fixes: 1b4ea4c5980f ("drm/ttm: set the tt caching state at creation time") Link: https://patch.msgid.link/20260821-tegra-coherent-wc-v2-1-2b1ddb67bf18@gmail.com Signed-off-by: Danilo Krummrich --- drivers/gpu/drm/nouveau/nouveau_sgdma.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_sgdma.c b/drivers/gpu/drm/nouveau/nouveau_sgdma.c index fa3b4ebf38a8..2bd0376193ae 100644 --- a/drivers/gpu/drm/nouveau/nouveau_sgdma.c +++ b/drivers/gpu/drm/nouveau/nouveau_sgdma.c @@ -72,9 +72,7 @@ nouveau_sgdma_create_ttm(struct ttm_buffer_object *bo, uint32_t page_flags) struct nouveau_sgdma_be *nvbe; enum ttm_caching caching; - if (nvbo->force_coherent) - caching = ttm_uncached; - else if (drm->agp.bridge) + if (nvbo->force_coherent || drm->agp.bridge) caching = ttm_write_combined; else caching = ttm_cached; From f4a771cc684c7354b6200147f7252c58d17408ff Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 28 Aug 2026 09:41:53 -0400 Subject: [PATCH 0396/1198] tracing: Have show_event_filters/triggers files take trace array ref The newly added files show_event_filters and show_event_triggers that show all filters or triggers that are set within the trace array do not take a reference for the trace array it is showing. Without taking a reference, the trace_array may be freed via "rmdir" while a task is reading one of theses files. Those files iterate all the events within an instance (trace_array) and nothing prevents that instance from being freed while its data is being read. This causes a use-after-free crash. Have the open of both those files take the trace_array reference via the trace_array_get() that prevents the trace_array from being freed while the files are opened. Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260828094153.17b95037@gandalf.local.home Fixes: 729757b96a662 ("tracing: Add show_event_filters to expose active event filters") Fixes: 6a80838814eea ("tracing: Add show_event_triggers to expose active event triggers") Reported-by: Farhad Alemi Closes: https://lore.kernel.org/all/CA+0ovCjerKZJLwXScM9bF2ga2rLi4_XOpUfK41NDbENpeu98jA@mail.gmail.com/ Reviewed-by: Aaron Tomlin Signed-off-by: Steven Rostedt --- kernel/trace/trace_events.c | 28 ++++++++++++++++++++++++---- 1 file changed, 24 insertions(+), 4 deletions(-) diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 1d39eaf6a0f7..9dbc2441763b 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2736,14 +2736,14 @@ static const struct file_operations ftrace_show_event_filters_fops = { .open = ftrace_event_show_filters_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = ftrace_event_release, }; static const struct file_operations ftrace_show_event_triggers_fops = { .open = ftrace_event_show_triggers_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = ftrace_event_release, }; static const struct file_operations ftrace_set_event_pid_fops = { @@ -2908,7 +2908,17 @@ ftrace_event_set_open(struct inode *inode, struct file *file) static int ftrace_event_show_filters_open(struct inode *inode, struct file *file) { - return ftrace_event_open(inode, file, &show_show_event_filters_seq_ops); + struct trace_array *tr = inode->i_private; + int ret; + + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; + + ret = ftrace_event_open(inode, file, &show_show_event_filters_seq_ops); + if (ret < 0) + trace_array_put(tr); + return ret; } /** @@ -2922,7 +2932,17 @@ ftrace_event_show_filters_open(struct inode *inode, struct file *file) static int ftrace_event_show_triggers_open(struct inode *inode, struct file *file) { - return ftrace_event_open(inode, file, &show_show_event_triggers_seq_ops); + struct trace_array *tr = inode->i_private; + int ret; + + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; + + ret = ftrace_event_open(inode, file, &show_show_event_triggers_seq_ops); + if (ret < 0) + trace_array_put(tr); + return ret; } static int From 9100191e5acb2e5ea2313f436667bb5fce129f47 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 28 Aug 2026 22:39:01 -0400 Subject: [PATCH 0397/1198] ftrace: Take trace_array reference before accessing its ftrace_ops The trace instance files set_ftrace_filter and set_ftrace_notrace was updated to work with specific trace instances (trace_arrays). The issue is that when these files are opened, there is a small race window where it will use the ftrace_ops from the inode->private pointer to get a reference to the trace_array and then take its reference. The problem is that the ftrace_ops itself could be freed. If the rmdir on the instance happens at the same time the set_ftrace_filter file is opened, the rmdir could have also freed the ftrace_ops and referencing it will cause a use-after-free bug and crash the kernel. Instead, pass in the trace_array as the file private data (NULL for the top level instance), and then pass both the trace_array and the ftrace_ops to the ftrace_regex_open() function. If the trace_array is NULL, then it just uses the ftrace_ops without the need to take its reference (like normal). If the ftrace_ops is NULL, that is only the case for the top level instance and the global_ops can be used. This allows the trace_array to have its reference incremented before touching the ftrace_ops that could also be freed when the instance is. Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260828223901.29e26edb@robin Fixes: 591dffdade9f0 ("ftrace: Allow for function tracing instance to filter functions") Reported-by: Breno Leitao Tested-by: Breno Leitao Closes: https://lore.kernel.org/all/apGORjltZgAiAYHT@gmail.com/ Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 5 +-- kernel/trace/ftrace.c | 57 ++++++++++++++++++++++------------ kernel/trace/trace.h | 5 +-- kernel/trace/trace_functions.c | 2 +- kernel/trace/trace_stack.c | 2 +- 5 files changed, 45 insertions(+), 26 deletions(-) diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 02bc5027523a..bd76a16a63af 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -866,8 +866,9 @@ unsigned long ftrace_get_addr_new(struct dyn_ftrace *rec); unsigned long ftrace_get_addr_curr(struct dyn_ftrace *rec); extern ftrace_func_t ftrace_trace_function; +struct trace_array; -int ftrace_regex_open(struct ftrace_ops *ops, int flag, +int ftrace_regex_open(struct trace_array *tr, struct ftrace_ops *ops, int flag, struct inode *inode, struct file *file); ssize_t ftrace_filter_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos); @@ -1077,7 +1078,7 @@ static inline unsigned long ftrace_location(unsigned long ip) * have them defined when ftrace is not enabled, but these * functions may still be called. Use a macro instead of inline. */ -#define ftrace_regex_open(ops, flag, inod, file) ({ -ENODEV; }) +#define ftrace_regex_open(tr, ops, flag, inode, file) ({ -ENODEV; }) #define ftrace_set_early_filter(ops, buf, enable) do { } while (0) #define ftrace_set_filter_ip(ops, ip, remove, reset) ({ -ENODEV; }) #define ftrace_set_filter_ips(ops, ips, cnt, remove, reset) ({ -ENODEV; }) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index f9d80c7bd9f1..c7cf36f2dd7b 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4677,7 +4677,8 @@ ftrace_avail_addrs_open(struct inode *inode, struct file *file) /** * ftrace_regex_open - initialize function tracer filter files - * @ops: The ftrace_ops that hold the hash filters + * @tr: The trace_array that holds the ftrace_ops [optional] + * @ops: The ftrace_ops that hold the hash filters [optional] * @flag: The type of filter to process * @inode: The inode, usually passed in to your open routine * @file: The file, usually passed in to your open routine @@ -4691,26 +4692,45 @@ ftrace_avail_addrs_open(struct inode *inode, struct file *file) * tracing_lseek() should be used as the lseek routine, and * release must call ftrace_regex_release(). * + * Note, If @tr is not NULL, its reference has to be taken before + * @ops may be referenced. + * If @ops is NULL and @tr is not, then @tr->ops is used. + * If @tr is NULL and @ops is not then @ops->private is uesd for @tr. + * If both @tr and @ops are NULL, then the &global_ops is + * to be used, and @tr will be the global_ops.private pointer. + * * Returns: 0 on success or a negative errno value on failure */ int -ftrace_regex_open(struct ftrace_ops *ops, int flag, +ftrace_regex_open(struct trace_array *tr, struct ftrace_ops *ops, int flag, struct inode *inode, struct file *file) { - struct ftrace_iterator *iter; + struct ftrace_iterator *iter = NULL; struct ftrace_hash *hash; struct list_head *mod_head; - struct trace_array *tr = ops->private; - int ret = -ENOMEM; - - ftrace_ops_init(ops); + int ret = -ENODEV; if (unlikely(ftrace_disabled)) return -ENODEV; + if (!tr) { + if (!ops) + ops = &global_ops; + tr = ops->private; + } + if (tracing_check_open_get_tr(tr)) return -ENODEV; + if (!ops) + ops = tr->ops; + + if (WARN_ON_ONCE(!ops)) + goto out; + + ftrace_ops_init(ops); + + ret = -ENOMEM; iter = kzalloc_obj(*iter); if (!iter) goto out; @@ -4788,21 +4808,19 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag, static int ftrace_filter_open(struct inode *inode, struct file *file) { - struct ftrace_ops *ops = inode->i_private; + struct trace_array *tr = inode->i_private; - /* Checks for tracefs lockdown */ - return ftrace_regex_open(ops, - FTRACE_ITER_FILTER | FTRACE_ITER_DO_PROBES, - inode, file); + return ftrace_regex_open(tr, NULL, + FTRACE_ITER_FILTER | FTRACE_ITER_DO_PROBES, + inode, file); } static int ftrace_notrace_open(struct inode *inode, struct file *file) { - struct ftrace_ops *ops = inode->i_private; + struct trace_array *tr = inode->i_private; - /* Checks for tracefs lockdown */ - return ftrace_regex_open(ops, FTRACE_ITER_NOTRACE, + return ftrace_regex_open(tr, NULL, FTRACE_ITER_NOTRACE, inode, file); } @@ -7492,15 +7510,15 @@ static const struct file_operations ftrace_graph_notrace_fops = { }; #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ -void ftrace_create_filter_files(struct ftrace_ops *ops, +void ftrace_create_filter_files(struct trace_array *tr, struct dentry *parent) { trace_create_file("set_ftrace_filter", TRACE_MODE_WRITE, parent, - ops, &ftrace_filter_fops); + tr, &ftrace_filter_fops); trace_create_file("set_ftrace_notrace", TRACE_MODE_WRITE, parent, - ops, &ftrace_notrace_fops); + tr, &ftrace_notrace_fops); } /* @@ -7525,7 +7543,6 @@ void ftrace_destroy_filter_files(struct ftrace_ops *ops) static __init int ftrace_init_dyn_tracefs(struct dentry *d_tracer) { - trace_create_file("available_filter_functions", TRACE_MODE_READ, d_tracer, NULL, &ftrace_avail_fops); @@ -7538,7 +7555,7 @@ static __init int ftrace_init_dyn_tracefs(struct dentry *d_tracer) trace_create_file("touched_functions", TRACE_MODE_READ, d_tracer, NULL, &ftrace_touched_fops); - ftrace_create_filter_files(&global_ops, d_tracer); + ftrace_create_filter_files(NULL, d_tracer); #ifdef CONFIG_FUNCTION_GRAPH_TRACER trace_create_file("set_graph_function", TRACE_MODE_WRITE, d_tracer, diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 74a7a50d1e78..3c111ca88e32 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1340,7 +1340,7 @@ extern void clear_ftrace_function_probes(struct trace_array *tr); int register_ftrace_command(struct ftrace_func_command *cmd); int unregister_ftrace_command(struct ftrace_func_command *cmd); -void ftrace_create_filter_files(struct ftrace_ops *ops, +void ftrace_create_filter_files(struct trace_array *tr, struct dentry *parent); void ftrace_destroy_filter_files(struct ftrace_ops *ops); @@ -1363,11 +1363,12 @@ static inline void clear_ftrace_function_probes(struct trace_array *tr) { } +static inline void ftrace_create_filter_files(struct trace_array *tr, + struct dentry *parent) { } /* * The ops parameter passed in is usually undefined. * This must be a macro. */ -#define ftrace_create_filter_files(ops, parent) do { } while (0) #define ftrace_destroy_filter_files(ops) do { } while (0) #endif /* CONFIG_FUNCTION_TRACER && CONFIG_DYNAMIC_FTRACE */ diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index cd37f2013758..c879d43a5fbb 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -101,7 +101,7 @@ int ftrace_create_function_files(struct trace_array *tr, return ret; } - ftrace_create_filter_files(tr->ops, parent); + ftrace_create_filter_files(tr, parent); return 0; } diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 0aa2514a6593..e7f4e523587d 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -499,7 +499,7 @@ stack_trace_filter_open(struct inode *inode, struct file *file) struct ftrace_ops *ops = inode->i_private; /* Checks for tracefs lockdown */ - return ftrace_regex_open(ops, FTRACE_ITER_FILTER, + return ftrace_regex_open(NULL, ops, FTRACE_ITER_FILTER, inode, file); } From 40fe154ba049a33f063c0058cd185d7f682088f3 Mon Sep 17 00:00:00 2001 From: Guanghui Yang <3497809730@qq.com> Date: Sat, 8 Aug 2026 14:38:32 +0800 Subject: [PATCH 0398/1198] btrfs: clean up target device if block group marking fails btrfs_dev_replace_start() adds the replacement target to the device list before marking block groups to copy. If marking fails, returning directly leaves the target linked and keeps the device accounting incremented. Jump to the existing cleanup path so the target device is removed and released on failure. The issue was found by a failure-path metadata residual analyzer and verified with targeted failure injection on v6.14. Assisted-by: Codex:gpt-5 Reviewed-by: Qu Wenruo Signed-off-by: Guanghui Yang <3497809730@qq.com> Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/dev-replace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 318ddb790429..bf0b78790171 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -626,7 +626,7 @@ static int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, ret = mark_block_group_to_copy(fs_info, src_device); if (ret) - return ret; + goto leave; down_write(&dev_replace->rwsem); dev_replace->replace_task = current; From c93b3c43df561cd9f592cee20ae058b563f9e5b6 Mon Sep 17 00:00:00 2001 From: Guanghui Yang <3497809730@qq.com> Date: Mon, 10 Aug 2026 20:16:04 +0800 Subject: [PATCH 0399/1198] btrfs: detach failed sprout device from transaction update list When creating the first metadata chunk for a sprout filesystem, create_chunk() adds the new device to the transaction dev_update_list through device->post_commit_list. If the subsequent system chunk creation fails, btrfs_init_new_device() aborts the transaction and releases the device while post_commit_list is still linked. This triggers a warning in btrfs_free_device() and leaves the transaction list referencing freed memory. Detach the device while holding chunk_mutex before releasing it. Fixes: bbbf7243d62d ("btrfs: combine device update operations during transaction commit") Assisted-by: Codex:gpt-5 Reviewed-by: Qu Wenruo Signed-off-by: Guanghui Yang <3497809730@qq.com> Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/volumes.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index a8e27db8e4bc..cbb491c6d4be 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3036,6 +3036,8 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path btrfs_sysfs_remove_device(device); mutex_lock(&fs_info->fs_devices->device_list_mutex); mutex_lock(&fs_info->chunk_mutex); + if (!list_empty(&device->post_commit_list)) + list_del_init(&device->post_commit_list); list_del_rcu(&device->dev_list); list_del(&device->dev_alloc_list); fs_info->fs_devices->num_devices--; From e0b54613aabeb8e9da597f23b90c6a03d0981986 Mon Sep 17 00:00:00 2001 From: Guanghui Yang <3497809730@qq.com> Date: Mon, 10 Aug 2026 20:16:05 +0800 Subject: [PATCH 0400/1198] btrfs: restore active device pointers after failed sprout btrfs_init_new_device() switches latest_dev and possibly s_bdev from the seed device to the new sprout device before creating the first writable chunks. If chunk creation or the subsequent sprout setup fails, the error path releases the new device without switching those pointers back. btrfs_show_devname() can then dereference the freed latest_dev and crash. Restore the active device pointers to the latest seed device before removing and releasing the failed sprout device. Fixes: b7cb29e666fe ("btrfs: update latest_dev when we create a sprout device") Assisted-by: Codex:gpt-5 Reviewed-by: Qu Wenruo Signed-off-by: Guanghui Yang <3497809730@qq.com> Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/volumes.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index cbb491c6d4be..427aa8e24fc3 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3035,6 +3035,8 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path error_sysfs: btrfs_sysfs_remove_device(device); mutex_lock(&fs_info->fs_devices->device_list_mutex); + if (seeding_dev) + btrfs_assign_next_active_device(device, seed_devices->latest_dev); mutex_lock(&fs_info->chunk_mutex); if (!list_empty(&device->post_commit_list)) list_del_init(&device->post_commit_list); From e8a0095c7df170945b4740eda4e2738a50f97fc6 Mon Sep 17 00:00:00 2001 From: Sam Ho Date: Fri, 14 Aug 2026 13:01:11 +0000 Subject: [PATCH 0401/1198] btrfs: preserve the compression property when other inode flags change Setting the compression property on an inode also sets BTRFS_INODE_COMPRESS on it, and btrfs_inode_flags_to_fsflags() reports that back as FS_COMPR_FL to FS_IOC_GETFLAGS. chattr(1), like any other FS_IOC_SETFLAGS caller, reads the current flags, flips only the bit the user asked for and writes the whole set back, so a request as unrelated as "chattr +i" reaches btrfs_fileattr_set() with FS_COMPR_FL set. btrfs_fileattr_set() takes that as a request to enable compression and overwrites the compression property with the algorithm from the mount options, falling back to zlib when the filesystem was not mounted with -o compress. The algorithm the user selected is silently replaced: # btrfs property set /mnt/foo compression zstd # btrfs property get /mnt/foo compression compression=zstd # chattr +i /mnt/foo # btrfs property get /mnt/foo compression compression=zlib Every chattr operation triggers this, not just +i, and directories are affected as well, so files created afterwards inherit the wrong algorithm too. On a filesystem mounted with -o compress=lzo the property is replaced with lzo instead. Recovering needs a chattr -i first, because the immutable flag rejects the setxattr that "btrfs property set" issues. Prefer the algorithm recorded in the compression property and only fall back to the mount default when there is no property, so that unrelated flag changes no longer overwrite the user's choice. Inodes that have the compress flag set but no property still get the default, so they behave as before. Reviewed-by: Qu Wenruo Signed-off-by: Sam Ho Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ioctl.c | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index ebfb258161c8..21c4e755f9c5 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -384,6 +384,7 @@ int btrfs_fileattr_set(struct mnt_idmap *idmap, inode_flags &= ~BTRFS_INODE_COMPRESS; inode_flags |= BTRFS_INODE_NOCOMPRESS; } else if (fsflags & FS_COMPR_FL) { + enum btrfs_compression_type comp_type; if (IS_SWAPFILE(&inode->vfs_inode)) return -ETXTBSY; @@ -391,9 +392,23 @@ int btrfs_fileattr_set(struct mnt_idmap *idmap, inode_flags |= BTRFS_INODE_COMPRESS; inode_flags &= ~BTRFS_INODE_NOCOMPRESS; - comp = btrfs_compress_type2str(fs_info->compress_type); - if (!comp || comp[0] == 0) - comp = btrfs_compress_type2str(BTRFS_COMPRESS_ZLIB); + /* + * Keep the algorithm recorded in the compression property, + * otherwise changing an unrelated attribute would reset it to + * the mount default, since FS_IOC_SETFLAGS callers write back + * the whole flag set they got from FS_IOC_GETFLAGS and that + * includes FS_COMPR_FL for any inode carrying the property. + * + * Inodes with the compress flag set but no property keep using + * the mount default, so they behave as before. + */ + if (inode->prop_compress) + comp_type = inode->prop_compress; + else if (fs_info->compress_type) + comp_type = fs_info->compress_type; + else + comp_type = BTRFS_COMPRESS_ZLIB; + comp = btrfs_compress_type2str(comp_type); } else { inode_flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS); } From 2625480a1bf79c62ffb09aafdf61778e682da492 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 1 Sep 2026 23:50:02 +0100 Subject: [PATCH 0402/1198] hardening: Default randstruct off with rust for better allmodconfig support Currently randstruct does not support rust so we have Kconfig dependencies which prevent rust being enabled when randstruct is. Unfortunately this prevents rust being enabled in allmodconfig, our standard coverage build. randstruct gets turned on by default, then the dependency on !RANDSTRUCT causes rust to get disabled. Work around this by disabling randstruct by default if we have a usable rust toolchain and rust support for the architecture, circular dependencies prevent us directly depending on !RUST. This means we might end up with a configuration that disables both rust and randstruct but hopefully it's more likely go give the expected result. Signed-off-by: Mark Brown Acked-by: Miguel Ojeda Link: https://patch.msgid.link/20260901-rust-reverse-randstruct-dep-v4-1-3bfa19efe1fa@kernel.org Signed-off-by: Kees Cook --- security/Kconfig.hardening | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening index 6923036e1a2f..81c81ad983ad 100644 --- a/security/Kconfig.hardening +++ b/security/Kconfig.hardening @@ -278,7 +278,7 @@ config CC_HAS_RANDSTRUCT choice prompt "Randomize layout of sensitive kernel structures" - default RANDSTRUCT_FULL if COMPILE_TEST && (GCC_PLUGINS || CC_HAS_RANDSTRUCT) + default RANDSTRUCT_FULL if !(RUST_IS_AVAILABLE && HAVE_RUST) && COMPILE_TEST && (GCC_PLUGINS || CC_HAS_RANDSTRUCT) default RANDSTRUCT_NONE help If you enable this, the layouts of structures that are entirely From b264d8422779d69febce914efc47a92a85cc382c Mon Sep 17 00:00:00 2001 From: Aswin Karuvally Date: Thu, 27 Aug 2026 08:34:08 +0200 Subject: [PATCH 0403/1198] s390/ctcm: Prevent XID null dereference The mpc_validate_xid() function sets grp->saved_xid2->xid2_flag2 to 0x40 to signal XID validation error. If peer XID is NULL or r/w channel pairing mismatch happens, grp->saved_xid2 is never initialized. An attempt to set the flag in such case leads to NULL dereference. Fix this by using the always available priv->xid->xid2_flag2 instead of grp->saved_xid2->xid2_flag2 for validation errors. Fixes: 293d984f0e36 ("ctcm: infrastructure for replaced ctc driver") Cc: stable@vger.kernel.org Signed-off-by: Aswin Karuvally Link: https://patch.msgid.link/20260827063408.2168914-1-aswin@linux.ibm.com Signed-off-by: Jakub Kicinski --- drivers/s390/net/ctcm_mpc.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/s390/net/ctcm_mpc.c b/drivers/s390/net/ctcm_mpc.c index 08e36685e578..61c88fe853c5 100644 --- a/drivers/s390/net/ctcm_mpc.c +++ b/drivers/s390/net/ctcm_mpc.c @@ -826,7 +826,7 @@ static void mpc_action_go_ready(fsm_instance *fsm, int event, void *arg) fsm_deltimer(&grp->timer); - if (grp->saved_xid2->xid2_flag2 == 0x40) { + if (priv->xid->xid2_flag2 == 0x40) { priv->xid->xid2_flag2 = 0x00; if (grp->estconnfunc) { grp->estconnfunc(grp->port_num, 1, @@ -1636,7 +1636,6 @@ static int mpc_validate_xid(struct mpcg_info *mpcginfo) "The XID used in the MPC protocol is not valid, " "rc = %d\n", rc); priv->xid->xid2_flag2 = 0x40; - grp->saved_xid2->xid2_flag2 = 0x40; } return rc; From 70f3995830d3f1e79faa14eb0605914f778feca9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 31 Aug 2026 19:46:26 +0000 Subject: [PATCH 0404/1198] bonding: alb: fix uninitialized transport header access in alb_determine_nd() alb_determine_nd() uses icmp6_hdr(skb) to inspect ICMPv6 headers. However, in xmit paths (e.g. packets sent via AF_PACKET / raw sockets or forwarded packets), skb->transport_header is not guaranteed to be initialized. While pskb_network_may_pull() ensures the packet data is linear starting from the network header, it does not set or adjust the transport header offset. Dereferencing icmp6_hdr(skb) can therefore access out-of-bounds memory. Fetch the icmp6hdr directly after ipv6hdr following pskb_network_may_pull(), and reload ipv6hdr in case pskb_may_pull() reallocated skb->head. Also remove the unused bond argument from alb_determine_nd(). Fixes: 0da8aa00bfcf ("net: bonding: Add support for IPV6 ns/na to balance-alb/balance-tlb mode") Signed-off-by: Eric Dumazet Reviewed-by: Joe Damato Link: https://patch.msgid.link/20260831194626.119371-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- drivers/net/bonding/bond_alb.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index d2fb67a47cf9..654f051d0023 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -1281,10 +1281,10 @@ static int alb_set_mac_address(struct bonding *bond, void *addr) } /* determine if the packet is NA or NS */ -static bool alb_determine_nd(struct sk_buff *skb, struct bonding *bond) +static bool alb_determine_nd(struct sk_buff *skb) { - struct ipv6hdr *ip6hdr; - struct icmp6hdr *hdr; + const struct ipv6hdr *ip6hdr; + const struct icmp6hdr *hdr; if (!pskb_network_may_pull(skb, sizeof(*ip6hdr))) return true; @@ -1296,7 +1296,8 @@ static bool alb_determine_nd(struct sk_buff *skb, struct bonding *bond) if (!pskb_network_may_pull(skb, sizeof(*ip6hdr) + sizeof(*hdr))) return true; - hdr = icmp6_hdr(skb); + ip6hdr = ipv6_hdr(skb); + hdr = (const struct icmp6hdr *)(ip6hdr + 1); return hdr->icmp6_type == NDISC_NEIGHBOUR_ADVERTISEMENT || hdr->icmp6_type == NDISC_NEIGHBOUR_SOLICITATION; } @@ -1381,7 +1382,7 @@ struct slave *bond_xmit_tlb_slave_get(struct bonding *bond, if (!is_multicast_ether_addr(eth_data->h_dest)) { switch (skb->protocol) { case htons(ETH_P_IPV6): - if (alb_determine_nd(skb, bond)) + if (alb_determine_nd(skb)) break; fallthrough; case htons(ETH_P_IP): @@ -1467,7 +1468,7 @@ struct slave *bond_xmit_alb_slave_get(struct bonding *bond, break; } - if (alb_determine_nd(skb, bond)) { + if (alb_determine_nd(skb)) { do_tx_balance = false; break; } From 6809da6e9c08ccc9a09cb0a48c61471679274aaa Mon Sep 17 00:00:00 2001 From: Xixin Liu Date: Tue, 18 Aug 2026 17:10:00 +0800 Subject: [PATCH 0405/1198] perf: RISC-V: store available counter mask as bitmap The available-counter mask was a single unsigned long, but iteration uses RISCV_MAX_COUNTERS, which is 64. On RV32 that reads past the object. Filling with an unsigned-long bit at index 32 and above is also wrong. Use DECLARE_BITMAP and set_bit/bitmap helpers. Walk each bitmap word into CFG_MATCH when checking events, when allocating an index, and when stopping all counters. Set the counter base to i times BITS_PER_LONG. Share the CFG_MATCH ecall through a small helper so the 32-bit argument split is not duplicated. On qemu-system-riscv32 the probe bitmap has bits above XLEN set, so the first word alone is not enough. Fixes: e9991434596f ("RISC-V: Add perf platform driver based on SBI PMU extension") Assisted-by: DeepSeek:deepseek-v3 Signed-off-by: Xixin Liu Link: https://patch.msgid.link/prpmask02cmap.v2.1786434000.git.liuxixin@kylinos.cn Cc: stable@kernel.org [pjw@kernel.org: updated to apply; fixed checkpatch.pl issues] Signed-off-by: Paul Walmsley --- drivers/perf/riscv_pmu_legacy.c | 5 +- drivers/perf/riscv_pmu_sbi.c | 88 +++++++++++++++++++++++---------- include/linux/perf/riscv_pmu.h | 2 +- 3 files changed, 66 insertions(+), 29 deletions(-) diff --git a/drivers/perf/riscv_pmu_legacy.c b/drivers/perf/riscv_pmu_legacy.c index 4d6461d6a74f..1b8e4789cb3c 100644 --- a/drivers/perf/riscv_pmu_legacy.c +++ b/drivers/perf/riscv_pmu_legacy.c @@ -110,8 +110,9 @@ static void pmu_legacy_init(struct riscv_pmu *pmu) { pr_info("Legacy PMU implementation is available\n"); - pmu->cmask = BIT(RISCV_PMU_LEGACY_CYCLE) | - BIT(RISCV_PMU_LEGACY_INSTRET); + bitmap_zero(pmu->cmask, RISCV_MAX_COUNTERS); + set_bit(RISCV_PMU_LEGACY_CYCLE, pmu->cmask); + set_bit(RISCV_PMU_LEGACY_INSTRET, pmu->cmask); pmu->ctr_start = pmu_legacy_ctr_start; pmu->ctr_stop = NULL; pmu->event_map = pmu_legacy_event_map; diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 8ea5ae617347..2c50a6ba2a80 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -97,7 +97,7 @@ static unsigned int riscv_pmu_irq_mask; static unsigned int riscv_pmu_irq; /* Cache the available counters in a bitmask */ -static unsigned long cmask; +static DECLARE_BITMAP(cmask, RISCV_MAX_COUNTERS); static int pmu_event_find_cache(u64 config); struct sbi_pmu_event_data { @@ -359,16 +359,38 @@ static int pmu_sbi_check_event_info(void) return result; } +static struct sbiret pmu_sbi_ctr_cfg_match(unsigned long cbase, + unsigned long ctr_mask, + unsigned long cflags, + unsigned long event_idx, + u64 config) +{ +#if defined(CONFIG_32BIT) + return sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase, + ctr_mask, cflags, event_idx, config, config >> 32); +#else + return sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase, + ctr_mask, cflags, event_idx, config, 0); +#endif +} + static void pmu_sbi_check_event(struct sbi_pmu_event_data *edata) { - struct sbiret ret; + struct sbiret ret = { .error = SBI_ERR_NOT_SUPPORTED }; + int i; - ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, - 0, cmask, 0, edata->event_idx, 0, 0); - if (!ret.error) { - sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP, - ret.value, 0x1, SBI_PMU_STOP_FLAG_RESET, 0, 0, 0); - } else if (ret.error == SBI_ERR_NOT_SUPPORTED) { + for (i = 0; i < BITS_TO_LONGS(RISCV_MAX_COUNTERS); i++) { + if (!cmask[i]) + continue; + ret = pmu_sbi_ctr_cfg_match(i * BITS_PER_LONG, cmask[i], 0, + edata->event_idx, 0); + if (!ret.error) { + sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP, + ret.value, 0x1, SBI_PMU_STOP_FLAG_RESET, 0, 0, 0); + return; + } + } + if (ret.error == SBI_ERR_NOT_SUPPORTED) { /* This event cannot be monitored by any counter */ edata->event_idx = -ENOENT; } @@ -488,10 +510,10 @@ int riscv_pmu_get_hpm_info(u32 *hw_ctr_width, u32 *num_hw_ctr) union sbi_pmu_ctr_info *info; u32 hpm_width = 0, hpm_count = 0; - if (!cmask) + if (bitmap_empty(cmask, RISCV_MAX_COUNTERS)) return -EINVAL; - for_each_set_bit(i, &cmask, RISCV_MAX_COUNTERS) { + for_each_set_bit(i, cmask, RISCV_MAX_COUNTERS) { info = &pmu_ctr_list[i]; if (!info) continue; @@ -540,8 +562,8 @@ static int pmu_sbi_ctr_get_idx(struct perf_event *event) struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu); struct cpu_hw_events *cpuc = this_cpu_ptr(rvpmu->hw_events); struct sbiret ret; - int idx; - uint64_t cbase = 0, cmask = rvpmu->cmask; + int idx, i; + u64 cbase = 0, cmask = 0; unsigned long cflags = 0; cflags = pmu_sbi_get_filter_flags(event); @@ -562,14 +584,21 @@ static int pmu_sbi_ctr_get_idx(struct perf_event *event) } /* retrieve the available counter index */ -#if defined(CONFIG_32BIT) - ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase, - cmask, cflags, hwc->event_base, hwc->config, - hwc->config >> 32); -#else - ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase, - cmask, cflags, hwc->event_base, hwc->config, 0); -#endif + if (cmask) { + ret = pmu_sbi_ctr_cfg_match(cbase, cmask, cflags, hwc->event_base, + hwc->config); + } else { + ret.error = SBI_ERR_NOT_SUPPORTED; + for (i = 0; i < BITS_TO_LONGS(RISCV_MAX_COUNTERS); i++) { + if (!rvpmu->cmask[i]) + continue; + cbase = i * BITS_PER_LONG; + ret = pmu_sbi_ctr_cfg_match(cbase, rvpmu->cmask[i], cflags, + hwc->event_base, hwc->config); + if (!ret.error) + break; + } + } if (ret.error) { pr_debug("Not able to find a counter for event %lx config %llx\n", hwc->event_base, hwc->config); @@ -577,7 +606,7 @@ static int pmu_sbi_ctr_get_idx(struct perf_event *event) } idx = ret.value; - if (!test_bit(idx, &rvpmu->cmask) || !pmu_ctr_list[idx].value) + if (!test_bit(idx, rvpmu->cmask) || !pmu_ctr_list[idx].value) return -ENOENT; /* Additional sanity check for the counter id */ @@ -881,7 +910,7 @@ static int pmu_sbi_get_ctrinfo(int nctr, unsigned long *mask) /* The logical counter ids are not expected to be contiguous */ continue; - *mask |= BIT(i); + set_bit(i, mask); cinfo.value = ret.value; if (cinfo.type == SBI_PMU_CTR_TYPE_FW) @@ -898,12 +927,19 @@ static int pmu_sbi_get_ctrinfo(int nctr, unsigned long *mask) static inline void pmu_sbi_stop_all(struct riscv_pmu *pmu) { + int i; + /* * No need to check the error because we are disabling all the counters * which may include counters that are not enabled yet. */ - sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP, - 0, pmu->cmask, SBI_PMU_STOP_FLAG_RESET, 0, 0, 0); + for (i = 0; i < BITS_TO_LONGS(RISCV_MAX_COUNTERS); i++) { + if (!pmu->cmask[i]) + continue; + sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP, + i * BITS_PER_LONG, pmu->cmask[i], + SBI_PMU_STOP_FLAG_RESET, 0, 0, 0); + } } static inline void pmu_sbi_stop_hw_ctrs(struct riscv_pmu *pmu) @@ -1451,7 +1487,7 @@ static int pmu_sbi_device_probe(struct platform_device *pdev) } /* cache all the information about counters now */ - if (pmu_sbi_get_ctrinfo(num_counters, &cmask)) + if (pmu_sbi_get_ctrinfo(num_counters, cmask)) goto out_free; ret = pmu_sbi_setup_irqs(pmu, pdev); @@ -1464,7 +1500,7 @@ static int pmu_sbi_device_probe(struct platform_device *pdev) pmu->pmu.attr_groups = riscv_pmu_attr_groups; pmu->pmu.parent = &pdev->dev; - pmu->cmask = cmask; + bitmap_copy(pmu->cmask, cmask, RISCV_MAX_COUNTERS); pmu->ctr_start = pmu_sbi_ctr_start; pmu->ctr_stop = pmu_sbi_ctr_stop; pmu->event_map = pmu_sbi_event_map; diff --git a/include/linux/perf/riscv_pmu.h b/include/linux/perf/riscv_pmu.h index f82a28040594..ecaa40370830 100644 --- a/include/linux/perf/riscv_pmu.h +++ b/include/linux/perf/riscv_pmu.h @@ -55,7 +55,7 @@ struct riscv_pmu { irqreturn_t (*handle_irq)(int irq_num, void *dev); - unsigned long cmask; + DECLARE_BITMAP(cmask, RISCV_MAX_COUNTERS); u64 (*ctr_read)(struct perf_event *event); int (*ctr_get_idx)(struct perf_event *event); int (*ctr_get_width)(int idx); From 248dbaf7770c0843702355a9fb724a882c669062 Mon Sep 17 00:00:00 2001 From: JinRui Date: Tue, 11 Aug 2026 08:15:13 +0000 Subject: [PATCH 0406/1198] riscv: report Zfhmin/Zvfhmin when Zfh/Zvfh are present The RISC-V ISA manual specifies that Zfh implies Zfhmin, a normative rule clarified in https://github.com/riscv/riscv-isa-manual/pull/3070. Zvfh likewise implies Zvfhmin, as stated by the vector extension specification. The kernel currently reports ZFH and ZFHMIN (and ZVFH and ZVFHMIN) as independent hwprobe bits derived only from what the device tree declares. Platforms that declare just "zfh" (Zfh being a superset that already contains all Zfhmin instructions) therefore report RISCV_HWPROBE_EXT_ZFHMIN=0, which breaks userspace RVA23 conformance checks (e.g. snapd installing core26 on riscv64). Use the existing superset mechanism to set the implied subset bits: - zfh implies zfhmin - zvfh implies zvfhmin Add a hwprobe selftest asserting the implication holds and update the hwprobe documentation accordingly. This is complementary to the rva23u64 base behavior discussion: the RVA23 conformance query proposed there is derived from the per-extension bits fixed here, so correct EXT_0 reporting is a prerequisite for it to work on harts whose device tree declares only "zfh". Tested on a RISC-V QEMU VM whose device tree only declares "zfh" and "zvfh": with this change both /proc/cpuinfo and the hwprobe RISCV_HWPROBE_KEY_IMA_EXT_0 bitmap report ZFHMIN and ZVFHMIN, and the hwprobe selftest (including the new implication check) passes. Link: https://lore.kernel.org/kvm-riscv/20260206002349.96740-1-andrew.jones@oss.qualcomm.com/ Signed-off-by: JinRui Link: https://patch.msgid.link/7190E4DB338251C3+20260811081513.2849980-1-jinrui@haiwei.tech [pjw@kernel.org: trimmed superfluous blank line in tags] Signed-off-by: Paul Walmsley --- Documentation/arch/riscv/hwprobe.rst | 8 +++++--- arch/riscv/kernel/cpufeature.c | 20 +++++++++++++++++-- .../testing/selftests/riscv/hwprobe/hwprobe.c | 20 ++++++++++++++++++- 3 files changed, 42 insertions(+), 6 deletions(-) diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst index 893e1a1215d2..bb1e0cbab36f 100644 --- a/Documentation/arch/riscv/hwprobe.rst +++ b/Documentation/arch/riscv/hwprobe.rst @@ -155,7 +155,8 @@ The following keys are defined: defined in version 1.0 of the RISC-V Cryptography Extensions Volume II. * :c:macro:`RISCV_HWPROBE_EXT_ZFH`: The Zfh extension version 1.0 is supported - as defined in the RISC-V ISA manual. + as defined in the RISC-V ISA manual. Zfh is a superset of Zfhmin, so + RISCV_HWPROBE_EXT_ZFHMIN is reported whenever RISCV_HWPROBE_EXT_ZFH is. * :c:macro:`RISCV_HWPROBE_EXT_ZFHMIN`: The Zfhmin extension version 1.0 is supported as defined in the RISC-V ISA manual. @@ -164,8 +165,9 @@ The following keys are defined: is supported as defined in the RISC-V ISA manual. * :c:macro:`RISCV_HWPROBE_EXT_ZVFH`: The Zvfh extension is supported as - defined in the RISC-V Vector manual starting from commit e2ccd0548d6c - ("Remove draft warnings from Zvfh[min]"). + defined in the RISC-V Vector manual starting from commit e2ccd0548d6c + ("Remove draft warnings from Zvfh[min]"). Zvfh is a superset of Zvfhmin, + so RISCV_HWPROBE_EXT_ZVFHMIN is reported whenever RISCV_HWPROBE_EXT_ZVFH is. * :c:macro:`RISCV_HWPROBE_EXT_ZVFHMIN`: The Zvfhmin extension is supported as defined in the RISC-V Vector manual starting from commit e2ccd0548d6c diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index d2ec96843456..61d21f714830 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -412,6 +412,19 @@ static const unsigned int riscv_zvbb_exts[] = { RISCV_ISA_EXT_ZVKB }; +/* + * The RISC-V ISA manual specifies that Zfh implies Zfhmin and Zvfh implies + * Zvfhmin. Report the implied subset extensions whenever the supersets are + * detected (see https://github.com/riscv/riscv-isa-manual/pull/3070). + */ +static const unsigned int riscv_zfh_exts[] = { + RISCV_ISA_EXT_ZFHMIN +}; + +static const unsigned int riscv_zvfh_exts[] = { + RISCV_ISA_EXT_ZVFHMIN +}; + #define RISCV_ISA_EXT_ZVE64F_IMPLY_LIST \ RISCV_ISA_EXT_ZVE64X, \ RISCV_ISA_EXT_ZVE32F, \ @@ -550,7 +563,8 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = { __RISCV_ISA_EXT_DATA(zawrs, RISCV_ISA_EXT_ZAWRS), __RISCV_ISA_EXT_DATA_VALIDATE(zfa, RISCV_ISA_EXT_ZFA, riscv_ext_f_depends), __RISCV_ISA_EXT_DATA_VALIDATE(zfbfmin, RISCV_ISA_EXT_ZFBFMIN, riscv_ext_f_depends), - __RISCV_ISA_EXT_DATA_VALIDATE(zfh, RISCV_ISA_EXT_ZFH, riscv_ext_f_depends), + __RISCV_ISA_EXT_SUPERSET_VALIDATE(zfh, RISCV_ISA_EXT_ZFH, + riscv_zfh_exts, riscv_ext_f_depends), __RISCV_ISA_EXT_DATA_VALIDATE(zfhmin, RISCV_ISA_EXT_ZFHMIN, riscv_ext_f_depends), __RISCV_ISA_EXT_DATA(zca, RISCV_ISA_EXT_ZCA), __RISCV_ISA_EXT_DATA_VALIDATE(zcb, RISCV_ISA_EXT_ZCB, riscv_ext_zca_depends), @@ -586,7 +600,9 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = { __RISCV_ISA_EXT_SUPERSET_VALIDATE(zve64x, RISCV_ISA_EXT_ZVE64X, riscv_zve64x_exts, riscv_ext_vector_x_validate), __RISCV_ISA_EXT_DATA_VALIDATE(zvfbfmin, RISCV_ISA_EXT_ZVFBFMIN, riscv_vector_f_validate), __RISCV_ISA_EXT_DATA_VALIDATE(zvfbfwma, RISCV_ISA_EXT_ZVFBFWMA, riscv_ext_zvfbfwma_validate), - __RISCV_ISA_EXT_DATA(zvfh, RISCV_ISA_EXT_ZVFH), + __RISCV_ISA_EXT_SUPERSET_VALIDATE(zvfh, RISCV_ISA_EXT_ZVFH, + riscv_zvfh_exts, + riscv_ext_vector_float_validate), __RISCV_ISA_EXT_DATA(zvfhmin, RISCV_ISA_EXT_ZVFHMIN), __RISCV_ISA_EXT_DATA_VALIDATE(zvkb, RISCV_ISA_EXT_ZVKB, riscv_ext_vector_crypto_validate), __RISCV_ISA_EXT_DATA_VALIDATE(zvkg, RISCV_ISA_EXT_ZVKG, riscv_ext_vector_crypto_validate), diff --git a/tools/testing/selftests/riscv/hwprobe/hwprobe.c b/tools/testing/selftests/riscv/hwprobe/hwprobe.c index 54c435af9923..eca4441ee77f 100644 --- a/tools/testing/selftests/riscv/hwprobe/hwprobe.c +++ b/tools/testing/selftests/riscv/hwprobe/hwprobe.c @@ -9,7 +9,7 @@ int main(int argc, char **argv) long out; ksft_print_header(); - ksft_set_plan(5); + ksft_set_plan(6); /* Fake the CPU_SET ops. */ cpus = -1; @@ -62,5 +62,23 @@ int main(int argc, char **argv) pairs[1].key == 1 && pairs[1].value != 0xAAAA, "Unknown key overwritten with -1 and doesn't block other elements\n"); + pairs[0].key = RISCV_HWPROBE_KEY_IMA_EXT_0; + out = riscv_hwprobe(pairs, 1, 0, 0, 0); + if (out != 0) + ksft_exit_fail_msg("hwprobe(IMA_EXT_0) failed with %ld\n", out); + + /* + * The RISC-V ISA manual specifies that Zfh implies Zfhmin and Zvfh + * implies Zvfhmin, so hwprobe must report the implied subset + * extensions whenever the supersets are present. + */ + if ((pairs[0].value & RISCV_HWPROBE_EXT_ZFH) && + !(pairs[0].value & RISCV_HWPROBE_EXT_ZFHMIN)) + ksft_exit_fail_msg("Zfh reported without implied Zfhmin\n"); + if ((pairs[0].value & RISCV_HWPROBE_EXT_ZVFH) && + !(pairs[0].value & RISCV_HWPROBE_EXT_ZVFHMIN)) + ksft_exit_fail_msg("Zvfh reported without implied Zvfhmin\n"); + ksft_test_result_pass("Zfh/Zvfh imply Zfhmin/Zvfhmin\n"); + ksft_finished(); } From f643f520c4c6998fa27dce90dd3b3ff6414e0bae Mon Sep 17 00:00:00 2001 From: Xixin Liu Date: Tue, 11 Aug 2026 11:51:00 +0800 Subject: [PATCH 0407/1198] perf: RISC-V: check cpu_hw_evt before dereference in overflow IRQ The overflow IRQ handler dereferences cpu_hw_evt before the null check. Move the check first. Defensive only; the cookie is valid on the normal path today. Fixes: a8625217a054 ("drivers/perf: riscv: Implement SBI PMU snapshot function") Assisted-by: DeepSeek:deepseek-v3 Signed-off-by: Xixin Liu Link: https://patch.msgid.link/fdd42c791752.v2.1786420235.git.liuxixin@kylinos.cn Signed-off-by: Paul Walmsley --- drivers/perf/riscv_pmu_sbi.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 2c50a6ba2a80..2991dd92def2 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -1086,11 +1086,13 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev) u64 overflowed_ctrs = 0; struct cpu_hw_events *cpu_hw_evt = dev; u64 start_clock = sched_clock(); - struct riscv_pmu_snapshot_data *sdata = cpu_hw_evt->snapshot_addr; + struct riscv_pmu_snapshot_data *sdata; if (WARN_ON_ONCE(!cpu_hw_evt)) return IRQ_NONE; + sdata = cpu_hw_evt->snapshot_addr; + /* Firmware counter don't support overflow yet */ fidx = find_first_bit(cpu_hw_evt->used_hw_ctrs, RISCV_MAX_COUNTERS); if (fidx == RISCV_MAX_COUNTERS) { From 93a27367bacdc32e2cdb478597102175db3fb80c Mon Sep 17 00:00:00 2001 From: Ivy Lopez Date: Mon, 31 Aug 2026 19:37:46 -0600 Subject: [PATCH 0408/1198] riscv: hwprobe: simplify has_fpu() to check D extension only The kernel never supports D without F, since D depends on F. The D-extension flag is cleared during devicetree/ACPI parsing whenever F is not present, so has_fpu() checking either extension with '||' never actually produces a different result than checking D alone - F without D cannot occur in practice, and there is no observable impact on RISCV_HWPROBE_IMA_FD or userspace. Simplify has_fpu() to check D only, matching the expectations set elsewhere in the kernel for this dependency, rather than relying on a redundant OR condition. sys_hwprobe.c already calls has_fpu() and needs no changes. Link: https://bugzilla.kernel.org/show_bug.cgi?id=221874 Suggested-by: Conor Dooley Suggested-by: Andreas Schwab Signed-off-by: Ivy Lopez Reviewed-by: Conor Dooley Link: https://patch.msgid.link/20260901013746.19386-1-skunkolee@gmail.com [pjw@kernel.org: updated to apply] Signed-off-by: Paul Walmsley --- arch/riscv/include/asm/switch_to.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h index 04f10a949066..123c89b694e8 100644 --- a/arch/riscv/include/asm/switch_to.h +++ b/arch/riscv/include/asm/switch_to.h @@ -61,8 +61,8 @@ static inline void __switch_to_fpu(struct task_struct *prev, static __always_inline bool has_fpu(void) { - return riscv_has_extension_likely(RISCV_ISA_EXT_F) || - riscv_has_extension_likely(RISCV_ISA_EXT_D); + /* D extension depends on F, so checking D alone is sufficient. */ + return riscv_has_extension_likely(RISCV_ISA_EXT_D); } #else static __always_inline bool has_fpu(void) { return false; } From 817ecd588fa5820527ee3affa43b5116276d2520 Mon Sep 17 00:00:00 2001 From: Jia Wang Date: Mon, 24 Aug 2026 13:54:14 +0800 Subject: [PATCH 0409/1198] dt-bindings: riscv: cpus: Fix yamllint style issues Wrap an overlong description line and normalize the inline dependency lists to satisfy yamllint. Signed-off-by: Jia Wang Acked-by: Conor Dooley Link: https://patch.msgid.link/20260824-ultrarisc-dts-v1-1-61ab7aebe9e5@ultrarisc.com Signed-off-by: Paul Walmsley --- Documentation/devicetree/bindings/riscv/cpus.yaml | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml index 5feeb2203050..0da219ae6769 100644 --- a/Documentation/devicetree/bindings/riscv/cpus.yaml +++ b/Documentation/devicetree/bindings/riscv/cpus.yaml @@ -117,8 +117,8 @@ properties: $ref: /schemas/types.yaml#/definitions/uint32 description: VLEN/8, the vector register length in bytes. This property is required on - thead systems where the vector register length is not identical on all harts, or - the vlenb CSR is not available. + thead systems where the vector register length is not identical on all + harts, or the vlenb CSR is not available. # RISC-V has multiple properties for cache op block sizes as the sizes # differ between individual CBO extensions @@ -151,8 +151,8 @@ anyOf: - riscv,isa-base dependencies: - riscv,isa-base: [ "riscv,isa-extensions" ] - riscv,isa-extensions: [ "riscv,isa-base" ] + riscv,isa-base: ["riscv,isa-extensions"] + riscv,isa-extensions: ["riscv,isa-base"] required: - interrupt-controller From 74e26c692c40565448b8a1d1398c69e221a299cf Mon Sep 17 00:00:00 2001 From: Yukai Wu Date: Sat, 29 Aug 2026 10:23:27 +0800 Subject: [PATCH 0410/1198] docs/zh_CN: Update arch/riscv/patch-acceptance.rst translation Update Documentation/arch/riscv/patch-acceptance.rst translation. Update the translation through commit ed843ae947f8 ("docs: move riscv under arch") Signed-off-by: Yukai Wu Reviewed-by: Dongliang Mu Acked-by: Weijie Yuan Link: https://patch.msgid.link/20260829022344.192491-1-xiaoyewuz.Ruster@gmail.com Signed-off-by: Paul Walmsley --- .../zh_CN/arch/riscv/patch-acceptance.rst | 44 ++++++++++++++----- 1 file changed, 33 insertions(+), 11 deletions(-) diff --git a/Documentation/translations/zh_CN/arch/riscv/patch-acceptance.rst b/Documentation/translations/zh_CN/arch/riscv/patch-acceptance.rst index c8eb230ca8ee..20b91d0433a9 100644 --- a/Documentation/translations/zh_CN/arch/riscv/patch-acceptance.rst +++ b/Documentation/translations/zh_CN/arch/riscv/patch-acceptance.rst @@ -15,19 +15,41 @@ arch/riscv 开发者维护指南 概述 ---- -RISC-V指令集体系结构是公开开发的： +RISC-V 指令集体系结构是公开开发的： 正在进行的草案可供所有人查看和测试实现。新模块或者扩展草案可能会在开发过程中发 -生更改---有时以不兼容的方式对以前的草案进行更改。这种灵活性可能会给RISC-V Linux -维护者带来挑战。Linux开发过程更喜欢经过良好检查和测试的代码，而不是试验代码。我 -们希望推广同样的规则到即将被内核合并的RISC-V相关代码。 +生更改 --- 有时以不兼容的方式对以前的草案进行更改。这种灵活性可能会给 RISC-V +Linux 维护者带来挑战。Linux 维护者不赞成频繁的变更，且 Linux 开发过程更喜欢经过 +良好检查和测试的代码，而不是试验代码。我们希望推广同样的规则到即将被内核合并的 +RISC-V 相关代码。 + +Patchwork +--------- + +RISC-V 有一个 patchwork 实例，可以在那里查看补丁的状态： + + https://patchwork.kernel.org/project/linux-riscv/list/ + +如果你的补丁不在默认视图中出现，那么 RISC-V 维护者很有可能已要求修改，或者希望 +将其应用到另一个代码树上。 + +自动化流程会在该 patchwork 实例上运行，在每个补丁到达时立刻对其进行构建/测试。 +自动化流程会根据补丁是否被识别为修复，选用 RISC-V `for-next` 或 `fixes` 分支 +当前的 HEAD；若上述均应用失败，则使用 RISC-V `master` 分支。补丁系列被应用到的具 +体提交将标注在 patchwork 上。任何检查未通过的补丁通常不会被应用，并且在大多数情 +况下将需要重新提交。 附加的提交检查单 ---------------- -我们仅接受相关标准已经被RISC-V基金会标准为“已批准”或“已冻结”的扩展或模块的补丁。 -（开发者当然可以维护自己的Linux内核树，其中包含所需代码扩展草案的代码。） +我们仅接受针对新模块或扩展的补丁，前提是这些模块或扩展的规范被列为未来不太可能发 +生不兼容的变更。对于来自 RISC-V 基金会的规范，这意味着“已冻结”或“已批准”，对于 +UEFI 论坛的规范，这意味着已发布的 ECR。（开发者当然可以维护自己的 Linux 内核树， +其中包含他们所需的任何扩展草案的代码。） -此外，RISC-V规范允许爱好者创建自己的自定义扩展。这些自定义拓展不需要通过RISC-V -基金会的任何审核或批准。为了避免将爱好者一些特别的RISC-V拓展添加进内核代码带来 -的维护复杂性和对性能的潜在影响，我们将只接受RISC-V基金会正式冻结或批准的的扩展 -补丁。（开发者当然可以维护自己的Linux内核树，其中包含他们想要的任何自定义扩展 -的代码。） +此外，RISC-V 规范允许实现者创建自己的自定义扩展。这些自定义扩展不需要通过 RISC-V +基金会的任何审核或批准流程。为了避免因添加实现者特定的 RISC-V 扩展带来的维护复杂 +性和对性能的潜在影响，我们将只考虑符合以下任一条件的扩展补丁： + +- 已由 RISC-V 基金会正式冻结或批准 +- 已按照标准 Linux 惯例，在广泛可用的硬件中实现 + +（实现者当然可以维护自己的 Linux 内核树，其中包含他们所需的任何自定义扩展的代码。） From 2464ac8a6ff8d8a18b50088eb1d1d638f9cee2f1 Mon Sep 17 00:00:00 2001 From: Thomas Huth Date: Thu, 13 Aug 2026 09:53:04 +0200 Subject: [PATCH 0411/1198] kselftest/riscv: Replace __ASSEMBLY__ with __ASSEMBLER__ While the GCC and Clang compilers already define __ASSEMBLER__ automatically when compiling assembly code, __ASSEMBLY__ is a macro that only gets defined by the Makefiles in the kernel. This can be very confusing when switching between userspace and kernelspace coding, or when dealing with uapi headers that rather should use __ASSEMBLER__ instead. So let's standardize now on the __ASSEMBLER__ macro that is provided by the compilers. Signed-off-by: Thomas Huth Reviewed-by: Nick Desaulniers Link: https://patch.msgid.link/20260813075304.75988-1-thuth@redhat.com Signed-off-by: Paul Walmsley --- tools/testing/selftests/riscv/cfi/cfi_rv_test.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/riscv/cfi/cfi_rv_test.h b/tools/testing/selftests/riscv/cfi/cfi_rv_test.h index 1c8043f2b778..184df6903d01 100644 --- a/tools/testing/selftests/riscv/cfi/cfi_rv_test.h +++ b/tools/testing/selftests/riscv/cfi/cfi_rv_test.h @@ -56,7 +56,7 @@ #define CSR_SSP 0x011 -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ #define __ASM_STR(x) x #else #define __ASM_STR(x) #x From 839f075aabdf5c21048f9801b87c0b841dd3d064 Mon Sep 17 00:00:00 2001 From: Jingbo Xu Date: Wed, 2 Sep 2026 09:50:39 +0800 Subject: [PATCH 0412/1198] erofs: add sysfs feature entry for xattr prefixes Let /sys/fs/erofs/features/xattr_prefixes advertise that this kernel supports the EROFS_FEATURE_INCOMPAT_XATTR_PREFIXES on-disk format. Fixes: 6a318ccd7e08 ("erofs: enable long extended attribute name prefixes") Cc: stable@vger.kernel.org # 6.4+ Reviewed-by: Gao Xiang Signed-off-by: Jingbo Xu Signed-off-by: Gao Xiang --- Documentation/ABI/testing/sysfs-fs-erofs | 2 +- fs/erofs/sysfs.c | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/Documentation/ABI/testing/sysfs-fs-erofs b/Documentation/ABI/testing/sysfs-fs-erofs index e4cf6fc6a106..0b8b4354e40b 100644 --- a/Documentation/ABI/testing/sysfs-fs-erofs +++ b/Documentation/ABI/testing/sysfs-fs-erofs @@ -5,7 +5,7 @@ Description: Shows all enabled kernel features. Supported features: compr_cfgs, big_pcluster, chunked_file, device_table, compr_head2, sb_chksum, ztailpacking, dedupe, fragments, - 48bit, metabox. + xattr_prefixes, 48bit, metabox. What: /sys/fs/erofs//sync_decompress Date: November 2021 diff --git a/fs/erofs/sysfs.c b/fs/erofs/sysfs.c index 6734483a440f..dfcec9376cd5 100644 --- a/fs/erofs/sysfs.c +++ b/fs/erofs/sysfs.c @@ -95,6 +95,7 @@ EROFS_ATTR_FEATURE(sb_chksum); EROFS_ATTR_FEATURE(ztailpacking); EROFS_ATTR_FEATURE(fragments); EROFS_ATTR_FEATURE(dedupe); +EROFS_ATTR_FEATURE(xattr_prefixes); EROFS_ATTR_FEATURE(48bit); EROFS_ATTR_FEATURE(metabox); @@ -108,6 +109,7 @@ static struct attribute *erofs_feat_attrs[] = { ATTR_LIST(ztailpacking), ATTR_LIST(fragments), ATTR_LIST(dedupe), + ATTR_LIST(xattr_prefixes), ATTR_LIST(48bit), ATTR_LIST(metabox), NULL, From f4825922d2fb371e2b969697d792077f1b62b62c Mon Sep 17 00:00:00 2001 From: Sujal Tuladhar Date: Sat, 1 Aug 2026 21:30:00 +0545 Subject: [PATCH 0413/1198] scsi: target: iscsi: Reserve a terminator byte for the login payload iscsi_target_check_login_request() rejects a login PDU whose DataSegmentLength exceeds MAX_KEY_VALUE_PAIRS, but the test is '>' and login->req_buf is allocated with exactly MAX_KEY_VALUE_PAIRS bytes. Since iscsit_get_login_rx() receives payload_length + padding bytes, where padding = ((-payload_length) & 3); any payload_length from 8189 to 8192 fills the whole 8192 byte buffer. The write stays in bounds, but no byte is left for a NUL terminator. The buffer is subsequently consumed as a C string. In the CHAP path chap_check_algorithm() calls kstrdup(a_str), and extract_param() calls strstr(in_buf, pattern) followed by strlen_semi(), none of which take a length. convert_null_to_semi() additionally rewrites every embedded NUL to ';', so even a payload made of well formed NUL separated key=value records is left without a terminator. These walk past the end of the object into adjacent slab memory. It is reachable by an unauthenticated initiator against a portal configured for CHAP; when authentication is not required iscsi_login_zero_tsih_s2() rewrites AuthMethod to None and the CHAP path is never entered. Allocate one extra byte. kzalloc() zeroes it and nothing ever writes to it, as every writer copies to offset 0 for at most MAX_KEY_VALUE_PAIRS bytes, so the buffer is always terminated. Fixes: e48354ce078c ("iscsi-target: Add iSCSI fabric support for target v4.1") Assisted-by: Claude Opus5 (custom harness) Cc: stable@vger.kernel.org Signed-off-by: Sujal Tuladhar Signed-off-by: Martin K. Petersen (Oracle) --- drivers/target/iscsi/iscsi_target_login.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index aafc94bcb635..c282b6a70296 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -47,7 +47,7 @@ static struct iscsi_login *iscsi_login_init_conn(struct iscsit_conn *conn) login->conn = conn; login->first_request = 1; - login->req_buf = kzalloc(MAX_KEY_VALUE_PAIRS, GFP_KERNEL); + login->req_buf = kzalloc(MAX_KEY_VALUE_PAIRS + 1, GFP_KERNEL); if (!login->req_buf) { pr_err("Unable to allocate memory for response buffer.\n"); goto out_login; From 139f57343b3d6b26d9f01580123b2ba2d2150337 Mon Sep 17 00:00:00 2001 From: Laurence Oberman Date: Mon, 31 Aug 2026 07:59:17 -0400 Subject: [PATCH 0414/1198] scsi: mpi3mr: Fix use-after-free on tgt_dev->starget during target device refresh/update mpi3mr_refresh_tgtdevs() and mpi3mr_devinfochg_evt_bh() read tgt_dev->starget and immediately pass it to starget_for_each_device() without holding mrioc->tgtdev_lock. Every writer of this field -- mpi3mr_target_alloc(), mpi3mr_target_destroy(), mpi3mr_slave_destroy() and mpi3mr_sdev_init() -- correctly serializes access under tgtdev_lock, but these two read sites do not, which leaves a check-then-use window against the SCSI core's target teardown path (scsi_remove_target(), invoked e.g. via a concurrent host reset, sysfs "delete", or SCSI EH device offlining running independently of the fwevt workqueue). Sequence observed on production hardware, triggered on the mpi3mr0_fwevt_wrkr workqueue during a SAS topology change shortly after a controller reset: BUG: kernel NULL pointer dereference, address: 0000000000000058 RIP: scsi_is_host_device+0x7/0x20 Call Trace: starget_for_each_device+0x34/0x100 mpi3mr_refresh_tgtdevs+0x152/0x1d0 [mpi3mr] mpi3mr_fwevt_bh+0x514/0x6c0 [mpi3mr] mpi3mr_fwevt_worker+0x1a/0x50 [mpi3mr] process_one_work+0x194/0x380 worker_thread+0x2fe/0x410 mpi3mr_refresh_tgtdevs() reads tgt_dev->starget as non-NULL, but by the time starget_for_each_device() dereferences it, a concurrent mpi3mr_target_destroy() has already cleared tgt_dev->starget under tgtdev_lock and the SCSI/device core has freed the underlying scsi_target (and its embedded struct device). The stale pointer is then walked by dev_to_shost() -> scsi_is_host_device(), producing the NULL/garbage dereference above. Fix this by taking mrioc->tgtdev_lock around every read of tgt_dev->starget, matching the existing writer-side discipline. Since starget_for_each_device() and mpi3mr_update_sdev() can end up doing non-atomic work (e.g. queue_limits_commit_update()), the lock cannot be held across the whole call, so instead pin the target's device with get_device() while holding the lock, drop the lock, then run starget_for_each_device() against the pinned reference and put_device() afterwards. This closes the TOCTOU window instead of merely narrowing it. The same unlocked read-and-dereference pattern also exists earlier in mpi3mr_refresh_tgtdevs()'s first removal-scan loop (tgt_dev->starget->hostdata); fix it the same way by holding tgtdev_lock across that check, which is cheap since it only touches plain struct fields. Assisted-by: Claude:Sonnet5 [Claude Code] Signed-off-by: Laurence Oberman Acked-by: Chandrakanth Patil Link: https://patch.msgid.link/20260831120047.14690-1-loberman@redhat.com Signed-off-by: Martin K. Petersen (Oracle) --- drivers/scsi/mpi3mr/mpi3mr_os.c | 45 +++++++++++++++++++++++++-------- 1 file changed, 35 insertions(+), 10 deletions(-) diff --git a/drivers/scsi/mpi3mr/mpi3mr_os.c b/drivers/scsi/mpi3mr/mpi3mr_os.c index f80a21ec161b..0f7380448718 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_os.c +++ b/drivers/scsi/mpi3mr/mpi3mr_os.c @@ -1094,10 +1094,13 @@ static void mpi3mr_refresh_tgtdevs(struct mpi3mr_ioc *mrioc) { struct mpi3mr_tgt_dev *tgtdev, *tgtdev_next; struct mpi3mr_stgt_priv_data *tgt_priv; + struct scsi_target *starget; + unsigned long flags; dprint_reset(mrioc, "refresh target devices: check for removals\n"); list_for_each_entry_safe(tgtdev, tgtdev_next, &mrioc->tgtdev_list, list) { + spin_lock_irqsave(&mrioc->tgtdev_lock, flags); if (((tgtdev->dev_handle == MPI3MR_INVALID_DEV_HANDLE) || tgtdev->is_hidden) && tgtdev->host_exposed && tgtdev->starget && @@ -1106,6 +1109,7 @@ static void mpi3mr_refresh_tgtdevs(struct mpi3mr_ioc *mrioc) tgt_priv->dev_removed = 1; atomic_set(&tgt_priv->block_io, 0); } + spin_unlock_irqrestore(&mrioc->tgtdev_lock, flags); } list_for_each_entry_safe(tgtdev, tgtdev_next, &mrioc->tgtdev_list, @@ -1127,15 +1131,25 @@ static void mpi3mr_refresh_tgtdevs(struct mpi3mr_ioc *mrioc) tgtdev = NULL; list_for_each_entry(tgtdev, &mrioc->tgtdev_list, list) { if ((tgtdev->dev_handle != MPI3MR_INVALID_DEV_HANDLE) && - !tgtdev->is_hidden) { - if (!tgtdev->host_exposed) + !tgtdev->is_hidden) { + if (!tgtdev->host_exposed) { mpi3mr_report_tgtdev_to_host(mrioc, - tgtdev->perst_id); - else if (tgtdev->starget) - starget_for_each_device(tgtdev->starget, - (void *)tgtdev, mpi3mr_update_sdev); - } + tgtdev->perst_id); + continue; + } + spin_lock_irqsave(&mrioc->tgtdev_lock, flags); + starget = tgtdev->starget; + if (starget) + get_device(&starget->dev); + spin_unlock_irqrestore(&mrioc->tgtdev_lock, flags); + if (starget) { + starget_for_each_device(starget, (void *)tgtdev, + mpi3mr_update_sdev); + put_device(&starget->dev); + } + } } + dprint_reset(mrioc, "refresh target devices: done\n"); } /** @@ -1515,6 +1529,8 @@ static void mpi3mr_devinfochg_evt_bh(struct mpi3mr_ioc *mrioc, struct mpi3_device_page0 *dev_pg0) { struct mpi3mr_tgt_dev *tgtdev = NULL; + struct scsi_target *starget; + unsigned long flags; u16 dev_handle = 0, perst_id = 0; perst_id = le16_to_cpu(dev_pg0->persistent_id); @@ -1535,9 +1551,18 @@ static void mpi3mr_devinfochg_evt_bh(struct mpi3mr_ioc *mrioc, mpi3mr_report_tgtdev_to_host(mrioc, perst_id); if (tgtdev->is_hidden && tgtdev->host_exposed) mpi3mr_remove_tgtdev_from_host(mrioc, tgtdev); - if (!tgtdev->is_hidden && tgtdev->host_exposed && tgtdev->starget) - starget_for_each_device(tgtdev->starget, (void *)tgtdev, - mpi3mr_update_sdev); + if (!tgtdev->is_hidden && tgtdev->host_exposed) { + spin_lock_irqsave(&mrioc->tgtdev_lock, flags); + starget = tgtdev->starget; + if (starget) + get_device(&starget->dev); + spin_unlock_irqrestore(&mrioc->tgtdev_lock, flags); + if (starget) { + starget_for_each_device(starget, (void *)tgtdev, + mpi3mr_update_sdev); + put_device(&starget->dev); + } + } out: if (tgtdev) mpi3mr_tgtdev_put(tgtdev); From e0d26fe176a8db6ccad4ab38c5bab29391c1946b Mon Sep 17 00:00:00 2001 From: Ivy Lopez Date: Tue, 25 Aug 2026 13:03:13 -0600 Subject: [PATCH 0415/1198] scsi: mpt3sas: Avoid out-of-bounds cpumask_of_node() call in _base_assign_reply_queues() dev_to_node() can return NUMA_NO_NODE (-1) on systems without NUMA topology information for the PCI device, such as single-socket boards that don't expose device-to-node affinity. Passing -1 directly into cpumask_of_node() indexes node_to_cpumask_map[-1], an out-of-bounds array read caught by UBSAN: UBSAN: array-index-out-of-bounds in arch/x86/include/asm/topology.h:72:28 index -1 is out of range for type 'cpumask *[1024]' Fall back to cpu_online_mask when no NUMA node is available, rather than assuming dev_to_node() always returns a valid node index. Link: https://bugzilla.kernel.org/show_bug.cgi?id=221294 Suggested-by: Johannes Thumshirn Fixes: 728bbc6cbff7 ("scsi: mpt3sas: Affinity high iops queues IRQs to local node") Signed-off-by: Ivy Lopez Reviewed-by: John Garry Link: https://patch.msgid.link/20260825190313.24013-1-skunkolee@gmail.com Signed-off-by: Martin K. Petersen (Oracle) --- drivers/scsi/mpt3sas/mpt3sas_base.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index fed7aeffec58..1af25a22611a 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -3238,7 +3238,10 @@ _base_assign_reply_queues(struct MPT3SAS_ADAPTER *ioc) * corresponding to high iops queues. */ if (ioc->high_iops_queues) { - mask = cpumask_of_node(dev_to_node(&ioc->pdev->dev)); + int node = dev_to_node(&ioc->pdev->dev); + + mask = (node == NUMA_NO_NODE) ? + cpu_online_mask : cpumask_of_node(node); for (index = 0; index < ioc->high_iops_queues; index++) { irq = pci_irq_vector(ioc->pdev, index); From ab84c314417e4743f72f4d3d5e58cf96e07213cc Mon Sep 17 00:00:00 2001 From: Frederick Lawler Date: Wed, 19 Aug 2026 18:45:22 -0500 Subject: [PATCH 0416/1198] configfs: move CONFIGFS_MAGIC definition to magic.h IMA shouldn't measure or appraise configfs, but currently does because it's missing from the default exclusion policies. Move CONFIGFS_MAGIC to magic.h to expose the file system's magic to IMA, as well as other userland applications. Suggested-by: Mimi Zohar Signed-off-by: Frederick Lawler Acked-by: Breno Leitao Signed-off-by: Mimi Zohar --- fs/configfs/mount.c | 4 +--- include/uapi/linux/magic.h | 1 + 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c index 4929f3431189..d8cac1cbf3bd 100644 --- a/fs/configfs/mount.c +++ b/fs/configfs/mount.c @@ -9,6 +9,7 @@ */ #include +#include #include #include #include @@ -19,9 +20,6 @@ #include #include "configfs_internal.h" -/* Random magic number */ -#define CONFIGFS_MAGIC 0x62656570 - static struct vfsmount *configfs_mount = NULL; struct kmem_cache *configfs_dir_cachep; static int configfs_mnt_count = 0; diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index fd5f0e95648e..66a91c8b1cb9 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -8,6 +8,7 @@ #define AUTOFS_SUPER_MAGIC 0x0187 #define CEPH_SUPER_MAGIC 0x00c36400 #define CODA_SUPER_MAGIC 0x73757245 +#define CONFIGFS_MAGIC 0x62656570 /* some random number */ #define CRAMFS_MAGIC 0x28cd3d45 /* some random number */ #define CRAMFS_MAGIC_WEND 0x453dcd28 /* magic number with the wrong endianess */ #define DEBUGFS_MAGIC 0x64626720 From 8e22ce504f8a332c57ca9676ab804da5ac4a1325 Mon Sep 17 00:00:00 2001 From: Frederick Lawler Date: Wed, 19 Aug 2026 18:45:23 -0500 Subject: [PATCH 0417/1198] ima: don't measure/appraise files on configfs IMA measurement of a configfs file causes process_measurement() to hold iint->mutex while performing a kernel_read() to hash it, which re-enters configfs's own file locking (buffer->mutex, frag_sem). Separately, opening any file with O_TRUNC now causes ima_file_truncate() to take iint->mutex to reset the cached action flags, while sb_writers is already held for that mount. When a configfs-backed nvmet namespace is involved, these two independent lock chains combine into a cycle: iint->mutex -> configfs locks -> subsys->lock -> sb_writers -> iint->mutex Add configfs to the builtin don't measure/appraise rules, similarly to other pseudo file systems, so IMA never takes iint->mutex for configfs file in the first place. Reported-by: syzbot+448c2e24b1ceff13ed2a@syzkaller.appspotmail.com Link: https://lore.kernel.org/all/6a77c7cd.b50370da.49fe0.0031.GAE@google.com/ Suggested-by: Mimi Zohar Signed-off-by: Frederick Lawler Signed-off-by: Mimi Zohar --- Documentation/ABI/testing/ima_policy | 3 +++ security/integrity/ima/ima_policy.c | 7 ++++++- 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/Documentation/ABI/testing/ima_policy b/Documentation/ABI/testing/ima_policy index 19258471b7b2..b8a763e4c9fb 100644 --- a/Documentation/ABI/testing/ima_policy +++ b/Documentation/ABI/testing/ima_policy @@ -108,6 +108,9 @@ Description: # NSFS_MAGIC dont_measure fsmagic=0x6e736673 dont_appraise fsmagic=0x6e736673 + # CONFIGFS_MAGIC + dont_measure fsmagic=0x62656570 + dont_appraise fsmagic=0x62656570 measure func=BPRM_CHECK measure func=FILE_MMAP mask=MAY_EXEC diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index f79d07bb63c6..68d9a5e6c232 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -165,7 +165,10 @@ static struct ima_rule_entry dont_measure_rules[] __ro_after_init = { {.action = DONT_MEASURE, .fsmagic = CGROUP2_SUPER_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_MEASURE, .fsmagic = NSFS_MAGIC, .flags = IMA_FSMAGIC}, - {.action = DONT_MEASURE, .fsmagic = EFIVARFS_MAGIC, .flags = IMA_FSMAGIC} + {.action = DONT_MEASURE, .fsmagic = EFIVARFS_MAGIC, + .flags = IMA_FSMAGIC}, + {.action = DONT_MEASURE, .fsmagic = CONFIGFS_MAGIC, + .flags = IMA_FSMAGIC} }; static struct ima_rule_entry original_measurement_rules[] __ro_after_init = { @@ -211,6 +214,8 @@ static struct ima_rule_entry default_appraise_rules[] __ro_after_init = { {.action = DONT_APPRAISE, .fsmagic = EFIVARFS_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_APPRAISE, .fsmagic = CGROUP_SUPER_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_APPRAISE, .fsmagic = CGROUP2_SUPER_MAGIC, .flags = IMA_FSMAGIC}, + {.action = DONT_APPRAISE, .fsmagic = CONFIGFS_MAGIC, + .flags = IMA_FSMAGIC}, #ifdef CONFIG_IMA_WRITE_POLICY {.action = APPRAISE, .func = POLICY_CHECK, .flags = IMA_FUNC | IMA_DIGSIG_REQUIRED}, From 8861f6d5c0678a7c5089c7b272509fc5931b8437 Mon Sep 17 00:00:00 2001 From: Bradley Morgan Date: Thu, 27 Aug 2026 17:43:38 +0000 Subject: [PATCH 0418/1198] ima: Check for ERR_PTR from dentry_path() in validate_hash_algo() dentry_path() returns ERR_PTR(-ENAMETOOLONG) when the path exceeds the buffer. validate_hash_algo() passes the result straight to integrity_audit_msg() without checking. ERR_PTR is not NULL, so integrity_audit_message() sees a valid pointer and calls strlen() on it, which faults: BUG: unable to handle page fault for address: ffffffffffffffdc RIP: 0010:strlen+0x30/0xa0 Call Trace: audit_log_untrustedstring+0x19/0x30 integrity_audit_message+0x366/0x4f0 ima_inode_setxattr+0x512/0x5f0 Check for IS_ERR() and use NULL instead, which makes the audit message skip the name= field instead of crashing. Fixes: 4f2946aa0c45 ("IMA: introduce a new policy option func=SETXATTR_CHECK") Cc: stable@vger.kernel.org Reported-by: syzbot+5ebeb3089ea6439c37be@syzkaller.appspotmail.com Link: https://lore.kernel.org/all/6a8f89e5.1d9ded08.62e62.00bf.GAE@google.com/ Signed-off-by: Bradley Morgan Signed-off-by: Mimi Zohar --- security/integrity/ima/ima_appraise.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c index ced2e131b061..b280488e15fc 100644 --- a/security/integrity/ima/ima_appraise.c +++ b/security/integrity/ima/ima_appraise.c @@ -748,6 +748,8 @@ static int validate_hash_algo(struct dentry *dentry, return -EACCES; path = dentry_path(dentry, pathbuf, PATH_MAX); + if (IS_ERR(path)) + path = NULL; integrity_audit_msg(AUDIT_INTEGRITY_DATA, d_inode(dentry), path, "set_data", errmsg, -EACCES, 0); From 617d0d8d199ba1790c94310fd75a22d01c97a8d6 Mon Sep 17 00:00:00 2001 From: Nikhil Gurudasani Date: Sun, 30 Aug 2026 16:11:09 +0530 Subject: [PATCH 0419/1198] erofs: preserve LZMA decoders on resize failure The pool-resize path frees each stream's old decoder before allocating its replacement. If an allocation fails after some streams have already been replaced, the failed stream is put back on the list with state == NULL. z_erofs_lzma_max_dictsize is still advanced as if the whole pool had been resized. An existing LZMA mount can select the broken stream and pass NULL to xz_dec_microlzma_reset(). A retry at the same size also skip another resize attempt. Since the global maximum was advanced, thus, the invalid state is left unrepaired. Allocate each replacement before freeing the old decoder, temporarily retaining one old decoder during allocation. Stop at the first failure and advance z_erofs_lzma_max_dictsize only after all streams satisfy the request. Record each stream's dictionary capacity so retries can skip streams already enlarged before a partial failure. Fixes: 622ceaddb764 ("erofs: lzma compression support") Cc: stable@vger.kernel.org Signed-off-by: Nikhil Gurudasani Reviewed-by: Gao Xiang Signed-off-by: Gao Xiang --- fs/erofs/decompressor_lzma.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/fs/erofs/decompressor_lzma.c b/fs/erofs/decompressor_lzma.c index 6b0cdb446c6a..9d15f94cbee1 100644 --- a/fs/erofs/decompressor_lzma.c +++ b/fs/erofs/decompressor_lzma.c @@ -5,6 +5,7 @@ struct z_erofs_lzma { struct z_erofs_lzma *next; struct xz_dec_microlzma *state; + unsigned int dict_size; u8 bounce[PAGE_SIZE]; }; @@ -128,11 +129,19 @@ static int z_erofs_load_lzma_config(struct super_block *sb, err = 0; /* 2. walk each isolated stream and grow max dict_size if needed */ for (strm = head; strm; strm = strm->next) { + struct xz_dec_microlzma *state; + + if (strm->dict_size >= dict_size) + continue; + state = xz_dec_microlzma_alloc(XZ_PREALLOC, dict_size); + if (!state) { + err = -ENOMEM; + break; + } if (strm->state) xz_dec_microlzma_end(strm->state); - strm->state = xz_dec_microlzma_alloc(XZ_PREALLOC, dict_size); - if (!strm->state) - err = -ENOMEM; + strm->state = state; + strm->dict_size = dict_size; } /* 3. push back all to the global list and update max dict_size */ @@ -142,7 +151,8 @@ static int z_erofs_load_lzma_config(struct super_block *sb, spin_unlock(&z_erofs_lzma_lock); wake_up_all(&z_erofs_lzma_wq); - z_erofs_lzma_max_dictsize = dict_size; + if (!err) + z_erofs_lzma_max_dictsize = dict_size; mutex_unlock(&lzma_resize_mutex); return err; } From 7b8a8ae4dd176a232e973017d2aa3c536a7275e2 Mon Sep 17 00:00:00 2001 From: Sourav Panda Date: Tue, 11 Aug 2026 05:29:09 +0000 Subject: [PATCH 0420/1198] mm/hugetlb_cma: fix null nodemask dereference in hugetlb_cma_alloc_frozen_folio alloc_buddy_hugetlb_folio_with_mpol() can pass a NULL nodemask to alloc_fresh_hugetlb_folio() as a fallback to allocate from all nodes. If order is gigantic, alloc_fresh_hugetlb_folio() propagates the NULL nodemask down to hugetlb_cma_alloc_frozen_folio() via alloc_gigantic_frozen_folio(). Additionally, hugetlb_cma_alloc_frozen_folio() previously attempted allocation on hugetlb_cma[nid] without verifying if nid is included in the caller's nodemask. Adding a node_isset(nid, *nodemask) check ensures the initial preferred node allocation honors the memory policy / nodemask. However, hugetlb_cma_alloc_frozen_folio() dereferences the nodemask in node_isset(nid, *nodemask) and for_each_node_mask(node, *nodemask), leading to a null pointer dereference kernel panic when nodemask is NULL. Fix this by checking if nodemask is NULL in hugetlb_cma_alloc_frozen_folio() and defaulting it to cpuset_current_mems_allowed. Enclose the allocation attempts within the cpuset seqcount retry loop so that if the cpuset changes concurrently during allocation, the attempts are retried using the updated nodemask. This ensures that the initial node check and fallback loop safely honor the task's cpuset without violating cpuset constraints or causing NULL pointer dereferences or unexpected allocation failures. From a userspace perspective, this bug allows an unprivileged user to crash the kernel (trigger a panic) by requesting a gigantic hugepage allocation with MPOL_PREFERRED_MANY on a system where CMA is only configured on a subset of NUMA nodes. This can be reproduced by booting a VM with two NUMA nodes, restricting CMA to Node 1 (e.g., hugetlb_cma=1:1G default_hugepagesz=1G hugepagesz=1G hugepages=0), and running a program that allocates a 1GB hugepage area without reserving, restricts allocation to Node 0 using mbind() with MPOL_PREFERRED_MANY, and triggers a page fault: void *ptr = mmap(NULL, 1UL << 30, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB | MAP_HUGE_1GB | MAP_NORESERVE, -1, 0); unsigned long nodemask = 1; /* Node 0 */ mbind(ptr, 1UL << 30, MPOL_PREFERRED_MANY, &nodemask, sizeof(nodemask) * 8, 0); memset(ptr, 0, 1UL << 30); /* Trigger fault */ This results in a NULL pointer dereference: BUG: kernel NULL pointer dereference, address: 0000000000000000 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page Oops: Oops: 0000 [#1] SMP NOPTI RIP: 0010:hugetlb_cma_alloc_frozen_folio+0x75/0x120 Call Trace: only_alloc_fresh_hugetlb_folio.isra.0+0x2c/0x160 alloc_surplus_hugetlb_folio+0x6d/0x100 alloc_hugetlb_folio+0x3c5/0x660 hugetlb_no_page+0x3d9/0x650 Link: https://lore.kernel.org/20260811052909.475635-1-souravpanda@google.com Fixes: eb02f14c4a2b ("mm/hugetlb: allow overcommitting gigantic hugepages") Signed-off-by: Sourav Panda Reviewed-by: Muchun Song Reviewed-by: Anshuman Khandual Cc: David Hildenbrand Cc: Frank van der Linden Cc: Greg Thelen Cc: Johannes Weiner Cc: Kefeng Wang Cc: Michal Hocko Cc: Oscar Salvador Cc: Rik van Riel Cc: SeongJae Park Cc: Shakeel Butt Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton --- mm/hugetlb_cma.c | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) diff --git a/mm/hugetlb_cma.c b/mm/hugetlb_cma.c index db0680e82847..95fd2d190f0d 100644 --- a/mm/hugetlb_cma.c +++ b/mm/hugetlb_cma.c @@ -3,6 +3,7 @@ #include #include #include +#include #include #include @@ -55,15 +56,25 @@ struct folio *hugetlb_cma_alloc_frozen_folio(int order, gfp_t gfp_mask, int node; struct folio *folio; struct page *page = NULL; + const nodemask_t *nmask; + unsigned int cpuset_mems_cookie; if (!hugetlb_cma_size) return NULL; - if (hugetlb_cma[nid]) +retry_cpuset: + if (!nodemask) { + cpuset_mems_cookie = read_mems_allowed_begin(); + nmask = &cpuset_current_mems_allowed; + } else { + nmask = nodemask; + } + + if (hugetlb_cma[nid] && node_isset(nid, *nmask)) page = cma_alloc_frozen_compound(hugetlb_cma[nid], order); if (!page && !(gfp_mask & __GFP_THISNODE)) { - for_each_node_mask(node, *nodemask) { + for_each_node_mask(node, *nmask) { if (node == nid || !hugetlb_cma[node]) continue; @@ -73,8 +84,12 @@ struct folio *hugetlb_cma_alloc_frozen_folio(int order, gfp_t gfp_mask, } } - if (!page) + if (!page) { + if (!nodemask && + unlikely(read_mems_allowed_retry(cpuset_mems_cookie))) + goto retry_cpuset; return NULL; + } folio = page_folio(page); folio_set_hugetlb_cma(folio); From a3417097fb107cea3358b19bcbb4eb655fd67f8c Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Tue, 11 Aug 2026 13:31:55 -0700 Subject: [PATCH 0421/1198] memcg: make the v1 soft limit knob inert The v1 soft limit has been deprecated since v6.12 and nobody has reported depending on it. Start the removal by decoupling the interface from the implementation: keep memory.soft_limit_in_bytes, but ignore writes to it and always report the maximum value on read similar to what memory.kmem.limit_in_bytes already does. Writes are still parsed, so malformed input keeps returning -EINVAL. The knob now also behaves the same everywhere: it used to return -EOPNOTSUPP on PREEMPT_RT, where soft limit reclaim has always been disabled. This also fixes the syzbot report linked below. Soft limit reclaim is the only caller that runs shrink_lruvec() from kswapd against a specific memcg, so it is the only way to reach lru_gen_shrink_lruvec() and in turn set_mm_walk(), which warns when called from kswapd. Link: https://lore.kernel.org/20260811203203.3456029-2-shakeel.butt@linux.dev Signed-off-by: Shakeel Butt Reported-by: syzbot+12ee2725d5fde63a9c96@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/6a7a6929.b50370da.49fe0.005e.GAE@google.com/ Acked-by: Michal Hocko Cc: Axel Rasmussen Cc: Barry Song Cc: David Hildenbrand Cc: Johannes Weiner Cc: Kairui Song Cc: Lorenzo Stoakes Cc: Muchun Song Cc: Roman Gushchin Cc: Signed-off-by: Andrew Morton --- .../admin-guide/cgroup-v1/memory.rst | 49 +++---------------- mm/memcontrol-v1.c | 43 +++++++++------- 2 files changed, 32 insertions(+), 60 deletions(-) diff --git a/Documentation/admin-guide/cgroup-v1/memory.rst b/Documentation/admin-guide/cgroup-v1/memory.rst index 7db63c002922..7d2a44af52c9 100644 --- a/Documentation/admin-guide/cgroup-v1/memory.rst +++ b/Documentation/admin-guide/cgroup-v1/memory.rst @@ -47,7 +47,6 @@ Features: - pages are linked to per-memcg LRU exclusively, and there is no global LRU. - optionally, memory+swap usage can be accounted and limited. - hierarchical accounting - - soft limit - moving (recharging) account at moving a task is selectable. - usage threshold notifier - memory pressure notifier @@ -76,10 +75,9 @@ Brief summary of control files. memory.memsw.failcnt show the number of memory+Swap hits limits memory.max_usage_in_bytes show max memory usage recorded memory.memsw.max_usage_in_bytes show max memory+Swap usage recorded - memory.soft_limit_in_bytes set/show soft limit of memory usage - This knob is not available on CONFIG_PREEMPT_RT systems. - This knob is deprecated and shouldn't be - used. + memory.soft_limit_in_bytes This knob is deprecated and has no effect. + Writes are ignored and reads always + return the maximum value. memory.stat show various statistics memory.use_hierarchy set/show hierarchical account enabled This knob is deprecated and shouldn't be @@ -340,9 +338,6 @@ memory.kmem.usage_in_bytes, or in a separate counter when it makes sense. The main "kmem" counter is fed into the main counter, so kmem charges will also be visible from the user counter. -Currently no soft limit is implemented for kernel memory. It is future work -to trigger slab reclaim when those limits are reached. - 2.7.1 Current Kernel Memory resources accounted ----------------------------------------------- @@ -710,42 +705,10 @@ For compatibility reasons writing 1 to memory.use_hierarchy will always pass:: THIS IS DEPRECATED! -Soft limits allow for greater sharing of memory. The idea behind soft limits -is to allow control groups to use as much of the memory as needed, provided +Writing to memory.soft_limit_in_bytes has no effect and reading it will +always return the maximum value. -a. There is no memory contention -b. They do not exceed their hard limit - -When the system detects memory contention or low memory, control groups -are pushed back to their soft limits. If the soft limit of each control -group is very high, they are pushed back as much as possible to make -sure that one control group does not starve the others of memory. - -Please note that soft limits is a best-effort feature; it comes with -no guarantees, but it does its best to make sure that when memory is -heavily contended for, memory is allocated based on the soft limit -hints/setup. Currently soft limit based reclaim is set up such that -it gets invoked from balance_pgdat (kswapd). - -7.1 Interface -------------- - -Soft limits can be setup by using the following commands (in this example we -assume a soft limit of 256 MiB):: - - # echo 256M > memory.soft_limit_in_bytes - -If we want to change this to 1G, we can at any time use:: - - # echo 1G > memory.soft_limit_in_bytes - -.. note:: - Soft limits take effect over a long period of time, since they involve - reclaiming memory for balancing between memory cgroups - -.. note:: - It is recommended to set the soft limit always below the hard limit, - otherwise the hard limit will take precedence. +Use memory.low and memory.min in cgroup v2 instead. .. _cgroup-v1-memory-move-charges: diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c index 835fc8e51184..05ef55cae4dc 100644 --- a/mm/memcontrol-v1.c +++ b/mm/memcontrol-v1.c @@ -96,7 +96,6 @@ enum { RES_LIMIT, RES_MAX_USAGE, RES_FAILCNT, - RES_SOFT_LIMIT, }; #ifdef CONFIG_LOCKDEP @@ -1888,6 +1887,30 @@ static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css, return -EINVAL; } +static u64 mem_cgroup_soft_limit_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return (u64)PAGE_COUNTER_MAX * PAGE_SIZE; +} + +static ssize_t mem_cgroup_soft_limit_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + unsigned long nr_pages; + int ret; + + ret = page_counter_memparse(strstrip(buf), "-1", &nr_pages); + if (ret) + return ret; + + pr_warn_once("soft_limit_in_bytes is deprecated and will be removed. " + "Writing any value to this file has no effect. " + "Please report your usecase to linux-mm@kvack.org if you " + "depend on this functionality.\n"); + + return nbytes; +} + static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css, struct cftype *cft) { @@ -1924,8 +1947,6 @@ static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css, return (u64)counter->watermark * PAGE_SIZE; case RES_FAILCNT: return counter->failcnt; - case RES_SOFT_LIMIT: - return (u64)READ_ONCE(memcg->soft_limit) * PAGE_SIZE; default: BUG(); } @@ -2020,17 +2041,6 @@ static ssize_t mem_cgroup_write(struct kernfs_open_file *of, break; } break; - case RES_SOFT_LIMIT: - if (IS_ENABLED(CONFIG_PREEMPT_RT)) { - ret = -EOPNOTSUPP; - } else { - pr_warn_once("soft_limit_in_bytes is deprecated and will be removed. " - "Please report your usecase to linux-mm@kvack.org if you " - "depend on this functionality.\n"); - WRITE_ONCE(memcg->soft_limit, nr_pages); - ret = 0; - } - break; } return ret ?: nbytes; } @@ -2384,9 +2394,8 @@ struct cftype mem_cgroup_legacy_files[] = { }, { .name = "soft_limit_in_bytes", - .private = MEMFILE_PRIVATE(_MEM, RES_SOFT_LIMIT), - .write = mem_cgroup_write, - .read_u64 = mem_cgroup_read_u64, + .write = mem_cgroup_soft_limit_write, + .read_u64 = mem_cgroup_soft_limit_read, }, { .name = "failcnt", From eedc8474d469a2e88f4dc61f8cfe05c147478b43 Mon Sep 17 00:00:00 2001 From: Narek Jilavyan Date: Mon, 17 Aug 2026 10:34:33 +0000 Subject: [PATCH 0422/1198] mm/hugetlb_cgroup: call page_counter_set_max() outside VM_BUG_ON() hugetlb_cgroup_css_alloc() rounds the counter limit down to a multiple of the huge page size and then applies it inside an assertion: VM_BUG_ON(page_counter_set_max(fault, limit)); VM_BUG_ON(page_counter_set_max(rsvd, limit)); With CONFIG_DEBUG_VM=n, VM_BUG_ON(cond) is BUILD_BUG_ON_INVALID(cond), i.e. ((void)(sizeof((__force long)(cond)))), whose operand is never evaluated. page_counter_set_max() is not a predicate - it performs xchg(&counter->max, nr_pages) - so on every non-debug kernel the limit is never applied and the counters keep page_counter_init()'s PAGE_COUNTER_MAX. That is user-visible, because hugetlb_cgroup_read_u64_max() recomputes the same rounded value and uses equality as its "unlimited" sentinel. PAGE_COUNTER_MAX is LONG_MAX / PAGE_SIZE = 2251799813685247, which is odd, so round_down() really does change it and the two sides disagree. With CONFIG_DEBUG_VM=n: $ cat /sys/fs/cgroup/t/hugetlb.2MB.max 9223372036854771712 and with this patch: $ cat /sys/fs/cgroup/t/hugetlb.2MB.max max A debug option should not change cgroup output. Call the function, then assert the result, as v6.12 did. Use VM_WARN_ON_ONCE() rather than restoring VM_BUG_ON(): the two are identical under CONFIG_DEBUG_VM=n, and checkpatch asks that new code not use BUG() variants. Link: https://lore.kernel.org/20260817103433.191266-1-njilav@gmail.com Fixes: 0e2759afcaf9 ("page_counter: track failcnt only for legacy cgroups") Signed-off-by: Narek Jilavyan Reviewed-by: Muchun Song Cc: David Hildenbrand Cc: Oscar Salvador Cc: Shakeel Butt Cc: Signed-off-by: Andrew Morton --- mm/hugetlb_cgroup.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index e0083de1ca82..ecb6e0b7819a 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -97,6 +97,7 @@ static void hugetlb_cgroup_init(struct hugetlb_cgroup *h_cgroup, struct page_counter *fault, *fault_parent = NULL; struct page_counter *rsvd, *rsvd_parent = NULL; unsigned long limit; + int ret; if (parent_h_cgroup) { fault_parent = hugetlb_cgroup_counter_from_cgroup( @@ -118,8 +119,10 @@ static void hugetlb_cgroup_init(struct hugetlb_cgroup *h_cgroup, limit = round_down(PAGE_COUNTER_MAX, pages_per_huge_page(&hstates[idx])); - VM_BUG_ON(page_counter_set_max(fault, limit)); - VM_BUG_ON(page_counter_set_max(rsvd, limit)); + ret = page_counter_set_max(fault, limit); + VM_WARN_ON_ONCE(ret); + ret = page_counter_set_max(rsvd, limit); + VM_WARN_ON_ONCE(ret); } } From dc41e961a269f2ca4196e669d6d8e05480899cd4 Mon Sep 17 00:00:00 2001 From: Hui Su Date: Mon, 17 Aug 2026 20:08:00 +0800 Subject: [PATCH 0423/1198] mm/migrate_device: avoid out-of-bounds writes for compound folios migrate_device_range() and migrate_device_pfns() clear the entries following a compound folio so that the PFN arrays retain their page-granular representation. If a compound folio extends beyond the end of the caller-provided range, the loops clear all following folio entries without limiting them to the number of slots remaining in the npages-sized array, causing an out-of-bounds write. Do not proceed with a compound folio if its page-granular representation does not fit entirely in the remaining PFN array. If this happens, drop any reference and lock acquired for the folio, clear the remaining entries, and stop collecting. Observed with a KASAN x86 QEMU kernel using the HMM migrate_anon_huge_zero selftest. Closing /dev/hmm_dmirror0 after migrating an anonymous huge page to device memory exercises: dmirror_fops_release() -> dmirror_device_evict_chunk() -> migrate_device_range() Link: https://lore.kernel.org/20260817120758.669807-3-sh_def@163.com Fixes: a30b48bf1b24 ("mm/migrate_device: implement THP migration of zone device pages") Signed-off-by: Hui Su Cc: Alistair Popple Cc: Balbir Singh Cc: Byungchul Park Cc: David Hildenbrand Cc: Gregory Price Cc: "Huang, Ying" Cc: Joshua Hahn Cc: Matthew Brost Cc: Rakie Kim Cc: Zi Yan Cc: Signed-off-by: Andrew Morton --- mm/migrate_device.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/mm/migrate_device.c b/mm/migrate_device.c index 762c5cee8fec..009bfa8b212d 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -1423,6 +1423,15 @@ int migrate_device_range(unsigned long *src_pfns, unsigned long start, src_pfns[i] = migrate_device_pfn_lock(pfn); nr = folio_nr_pages(folio); + if (nr > npages - i) { + if (src_pfns[i] & MIGRATE_PFN_MIGRATE) { + folio_unlock(folio); + folio_put(folio); + } + memset(&src_pfns[i], 0, + (npages - i) * sizeof(*src_pfns)); + break; + } if (nr > 1) { src_pfns[i] |= MIGRATE_PFN_COMPOUND; for (j = 1; j < nr; j++) @@ -1457,6 +1466,15 @@ int migrate_device_pfns(unsigned long *src_pfns, unsigned long npages) src_pfns[i] = migrate_device_pfn_lock(src_pfns[i]); nr = folio_nr_pages(folio); + if (nr > npages - i) { + if (src_pfns[i] & MIGRATE_PFN_MIGRATE) { + folio_unlock(folio); + folio_put(folio); + } + memset(&src_pfns[i], 0, + (npages - i) * sizeof(*src_pfns)); + break; + } if (nr > 1) { src_pfns[i] |= MIGRATE_PFN_COMPOUND; for (j = 1; j < nr; j++) From 267bede12d3b108ca29997ce280e927a570ec97f Mon Sep 17 00:00:00 2001 From: Longlong Xia Date: Fri, 14 Aug 2026 16:30:27 +0800 Subject: [PATCH 0424/1198] mm/hugetlb: keep max_huge_pages when dissolving surplus folios dissolve_free_hugetlb_folio() can remove a free folio as surplus when its node has surplus pages. In that case remove_hugetlb_folio() decrements both nr_huge_pages and surplus_huge_pages, leaving the persistent pool size unchanged. Updating max_huge_pages as if a persistent folio had been removed can therefore corrupt the persistent pool target and underflow it when max_huge_pages is zero. Keep max_huge_pages unchanged for surplus folios, including the vmemmap restoration rollback path. Link: https://lore.kernel.org/20260814083027.1419487-1-xialonglong2025@163.com Fixes: cb402bbdabca ("mm/hugetlb: fix surplus pages in dissolve_free_huge_page()") Assisted-by: Codex:gpt-5.6-sol Signed-off-by: Longlong Xia Reviewed-by: Muchun Song Cc: David Hildenbrand Cc: Jinjiang Tu Cc: Longlong Xia Cc: Oscar Salvador Cc: Signed-off-by: Andrew Morton --- mm/hugetlb.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 785772845795..885017e26fd4 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1992,7 +1992,8 @@ int dissolve_free_hugetlb_folio(struct folio *folio) if (h->surplus_huge_pages_node[folio_nid(folio)]) adjust_surplus = true; remove_hugetlb_folio(h, folio, adjust_surplus); - h->max_huge_pages--; + if (!adjust_surplus) + h->max_huge_pages--; spin_unlock_irq(&hugetlb_lock); /* @@ -2012,7 +2013,8 @@ int dissolve_free_hugetlb_folio(struct folio *folio) if (rc) { spin_lock_irq(&hugetlb_lock); add_hugetlb_folio(h, folio, adjust_surplus); - h->max_huge_pages++; + if (!adjust_surplus) + h->max_huge_pages++; goto out; } } else { From 2fd4e7693674b17807a6d082feb01a3fbf86f5f8 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Tue, 18 Aug 2026 10:47:26 +0800 Subject: [PATCH 0425/1198] mm: fix incorrect vm_flags usage when checking allowable orders for tmpfs Lance reported that when nothing else causes the mm to be considered for khugepaged collapse, an MADV_HUGEPAGE-advised tmpfs VMA alone does not trigger scanning. After commit 6beeab870e70 ("mm: shmem: move shmem_huge_global_enabled() into shmem_allowable_huge_orders()"), the shmem/tmpfs allowable order check reads vma->flags directly. However, when MADV_HUGEPAGE is handled, khugepaged_enter_vma() is called before the VMA's flags have been updated, so the check uses stale flags and incorrectly rejects the VMA for collapse. As a result, khugepaged does not collapse the tmpfs file into PMD order in time. Fix this by calling khugepaged_enter_vma() with the new VMA flags in madvise_update_vma(). Meanwhile we can remove the khugepaged_enter_vma() in hugepage_madvise(). Link: https://lore.kernel.org/7d5b5eb27be798f89d563b06254c947ff53db0b2.1787020910.git.baolin.wang@linux.alibaba.com Fixes: 6beeab870e70 ("mm: shmem: move shmem_huge_global_enabled() into shmem_allowable_huge_orders()") Signed-off-by: Baolin Wang Reported-by: Lance Yang Closes: https://lore.kernel.org/all/20260815181632.21453-1-lance.yang@linux.dev/ Suggested-by: Lorenzo Stoakes (ARM) Reviewed-by: Zi Yan Reviewed-by: Lorenzo Stoakes (ARM) Cc: Barry Song Cc: David Hildenbrand Cc: Dev Jain Cc: Hugh Dickins Cc: Lance Yang Cc: Liam R. Howlett Cc: Ryan Roberts Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton --- mm/khugepaged.c | 6 ------ mm/madvise.c | 8 ++++++++ 2 files changed, 8 insertions(+), 6 deletions(-) diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 11ff98d55c76..75639298efc2 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -454,12 +454,6 @@ int hugepage_madvise(struct vm_area_struct *vma, case MADV_HUGEPAGE: *vm_flags &= ~VM_NOHUGEPAGE; *vm_flags |= VM_HUGEPAGE; - /* - * If the vma become good for khugepaged to scan, - * register it here without waiting a page fault that - * may not happen any time soon. - */ - khugepaged_enter_vma(vma, *vm_flags); break; case MADV_NOHUGEPAGE: *vm_flags &= ~VM_HUGEPAGE; diff --git a/mm/madvise.c b/mm/madvise.c index 96f2387b2f46..eeee82cf2b3f 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -178,6 +178,14 @@ static int madvise_update_vma(vm_flags_t new_flags, /* vm_flags is protected by the mmap_lock held in write mode. */ vma_start_write(vma); vma->flags = new_vma_flags; + /* + * If the vma become good for khugepaged to scan, + * register it here without waiting a page fault that + * may not happen any time soon. + */ + if (vma_flags_test(&new_vma_flags, VMA_HUGEPAGE_BIT)) + khugepaged_enter_vma(vma, vma_flags_to_legacy(new_vma_flags)); + if (set_new_anon_name) return replace_anon_vma_name(vma, anon_name); From f025ca73decda1f895a4b80b961d3bc88825298a Mon Sep 17 00:00:00 2001 From: Bryan Lim Date: Wed, 19 Aug 2026 10:08:24 +0700 Subject: [PATCH 0426/1198] userfaultfd: reset err to be 0 when move_pages_ptes succeeded During move_pages() operation, when move_pages_ptes() returns EAGAIN, the error code is not cleared even after we processed it. This leads to a successful retry but then the same pages are retried again due to the stale error code. This time move fails because pages are already moved, loop is terminated and move_pages() reports a failure. Clear the error code once we processes EAGAIN. Link: https://lore.kernel.org/e1e0b5f8-c3c6-0537-670b-4397f822f980@gmail.com Fixes: 50944692052b ("userfaultfd: opportunistic TLB-flush batching for present pages in MOVE") Assisted-by: ChatGPT:GPT-5.6-Luna Signed-off-by: Bryan Lim Reviewed-by: Suren Baghdasaryan Acked-by: Mike Rapoport (Microsoft) Cc: Peter Xu Cc: Signed-off-by: Andrew Morton --- mm/userfaultfd.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 23fb68fce000..74f04c323c50 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -2171,8 +2171,10 @@ static ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start, } if (err) { - if (err == -EAGAIN) + if (err == -EAGAIN) { + err = 0; continue; + } break; } From 6e0803a170552a6ab48538721df6467582fc940c Mon Sep 17 00:00:00 2001 From: Lance Yang Date: Thu, 20 Aug 2026 09:45:35 +0800 Subject: [PATCH 0427/1198] MAINTAINERS: add Lance Yang as a hung task detector co-maintainer I've been a hung_task reviewer for over a year now and plan to stay involved. Take on more responsibility for hung_task as a co-maintainer. Link: https://lore.kernel.org/20260820014535.79105-1-lance.yang@linux.dev Signed-off-by: Lance Yang Acked-by: Petr Mladek Cc: "Masami Hiramatsu (Google)" Signed-off-by: Andrew Morton --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 4dfc1fb14ef7..00843d667a4f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -12221,7 +12221,7 @@ F: drivers/tty/hvc/ HUNG TASK DETECTOR M: Andrew Morton -R: Lance Yang +M: Lance Yang R: Masami Hiramatsu R: Petr Mladek L: linux-kernel@vger.kernel.org From fe6cf984939d8e12cb33a99673c8d026c5135e68 Mon Sep 17 00:00:00 2001 From: Usama Arif Date: Wed, 19 Aug 2026 03:12:22 -0700 Subject: [PATCH 0428/1198] mm/huge_memory: transfer the pmd dirty bit to the folio on zap zap_huge_pmd_folio() propagates the pmd young bit to the folio for the file case, but not the dirty bit. The pte path does propagate it, in zap_present_folio_ptes() and so does the pmd split path, in __split_huge_pmd_locked(). For most file mappings the omission is harmless, because writing to a shared file mapping goes through page_mkwrite(), which dirties the folio. tmpfs is different: it has no page_mkwrite(), and vma_wants_writenotify() is false for it, so a *read* fault on a MAP_SHARED tmpfs mapping installs a writable pmd via do_read_fault(). do_read_fault() does not call fault_dirty_shared_page(), so subsequent stores through that mapping set only the hardware dirty bit in the pmd and never call folio_mark_dirty(). A shmem folio allocated by a fault is marked uptodate but not dirty (see the clear: block in shmem_get_folio_gfp()), so PG_dirty is never set at all. Unmapping such a folio - munmap(), or exit_mmap() when the process dies - then loses the only record that it was written, because zap_huge_pmd() drops the pmd without transferring the dirty bit. Reclaim afterwards sees a clean shmem folio: the whole swap-out block in shrink_folio_list() is inside "if (folio_test_dirty(folio))", so pageout() is skipped and the folio falls into __remove_mapping(). There, folio_is_file_lru() is false for a swapbacked folio, so no shadow entry is created and __filemap_remove_folio(folio, NULL) simply empties the i_pages slot. The data is freed without ever being written to swap, and the next fault on that index returns a freshly zeroed folio. This is silent data loss for any process that keeps state in a MAP_SHARED tmpfs segment across an unmap - for example a cache handed from one process generation to the next through /dev/shm. It requires the folio to be PMD-mapped, so it only shows up once shmem THP is enabled (which is what we did in Meta fleet and started noticing crashes); with THP off the pte path transfers the dirty bit correctly. It also only becomes visible when swap is enabled, because with no swap device shmem folios (which are on the anon LRU) are not scanned by reclaim at all, so the clean folio is never dropped. Reproduced on x86_64 with a tmpfs mounted huge=within_size: read-fault a 2MB-backed region, write a known pattern through the resulting mapping, munmap, force reclaim of the cgroup, then re-map and read back. Without this patch the region reads back as zeros and vmstat shows zswpout 0 - the data was discarded rather than swapped. With this patch the region reads back correctly and the pages are swapped out as expected. With huge=never, or when the first touch is a write, the test passes either way. Link: https://lore.kernel.org/20260819101222.3732660-1-usama.arif@linux.dev Fixes: b5072380eb61 ("thp: support file pages in zap_huge_pmd()") Signed-off-by: Usama Arif Acked-by: David Hildenbrand (Arm) Reviewed-by: Kiryl Shutsemau Acked-by: Hugh Dickins Tested-by: Lance Yang Reviewed-by: Zi Yan Reviewed-by: Lorenzo Stoakes (ARM) Reviewed-by: Baolin Wang Cc: Barry Song Cc: Dev Jain Cc: Johannes Weiner Cc: Liam R. Howlett Cc: Nhat Pham Cc: Rik van Riel Cc: Ryan Roberts Cc: Shakeel Butt Cc: Signed-off-by: Andrew Morton --- mm/huge_memory.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index ced400f72d43..afbb5974bd22 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2449,6 +2449,8 @@ static void zap_huge_pmd_folio(struct mm_struct *mm, struct vm_area_struct *vma, add_mm_counter(mm, mm_counter_file(folio), -HPAGE_PMD_NR); + if (is_present && pmd_dirty(pmdval)) + folio_mark_dirty(folio); if (is_present && pmd_young(pmdval) && likely(vma_has_recency(vma))) folio_mark_accessed(folio); From 540e583b66d6402bf556fde5e53c817a54c1afe5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 21 Aug 2026 17:04:07 +0000 Subject: [PATCH 0429/1198] mm/mempolicy: fix sleeping allocation in alloc_pages_bulk_weighted_interleave() syzbot reported a sleeping function called from invalid context splat in bucket_table_alloc(). When rhashtable_insert_slow() rehashes the table under rcu_read_lock(), it calls bucket_table_alloc(..., GFP_ATOMIC | __GFP_NOWARN). If the bucket table allocation uses vmalloc, __vmalloc_node_range_noprof() invokes vm_area_alloc_pages() -> alloc_pages_bulk_mempolicy_noprof() with the passed GFP_ATOMIC flags. If the current task has an MPOL_WEIGHTED_INTERLEAVE mempolicy, alloc_pages_bulk_weighted_interleave() is called and currently hardcodes GFP_KERNEL when allocating the temporary weights array, triggering a might_alloc() splat in atomic/RCU contexts. Pass the gfp flags (masked with GFP_RECLAIM_MASK to strip page-allocator zone modifiers like __GFP_HIGHMEM) received by alloc_pages_bulk_weighted_interleave() to kmalloc() instead of hardcoding GFP_KERNEL. Since the weights buffer is immediately initialized in full, kmalloc() is sufficient. Link: https://lore.kernel.org/20260821170407.3721004-1-edumazet@google.com Fixes: fa3bea4e1f82 ("mm/mempolicy: introduce MPOL_WEIGHTED_INTERLEAVE for weighted interleaving") Signed-off-by: Eric Dumazet Reported-by: syzbot+0dbf6d295b3350944f0b@syzkaller.appspotmail.com Closes: https://lore.kernel.org/lkml/6a88837e.ae6ddae5.3da009.0040.GAE@google.com/T/#u Reviewed-by: Andrew Morton Reviewed-by: Gregory Price (Meta) Acked-by: David Hildenbrand (Arm) Cc: Alistair Popple Cc: Byungchul Park Cc: "Huang, Ying" Cc: Joshua Hahn Cc: Matthew Brost Cc: Rakie Kim Cc: Zi Yan Cc: Signed-off-by: Andrew Morton --- mm/mempolicy.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 3498a5651d50..79053ece02cd 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2679,7 +2679,7 @@ static unsigned long alloc_pages_bulk_weighted_interleave(gfp_t gfp, prev_node = node; /* create a local copy of node weights to operate on outside rcu */ - weights = kzalloc(nr_node_ids, GFP_KERNEL); + weights = kmalloc(nr_node_ids, gfp & GFP_RECLAIM_MASK); if (!weights) return total_allocated; From 8ee1ef0f2f8ce29338f4ab00a3d344c010208058 Mon Sep 17 00:00:00 2001 From: Wupeng Ma Date: Tue, 7 Jul 2026 19:02:54 +0800 Subject: [PATCH 0430/1198] mm/hugetlb: fix missing migratable flag on same-node hugetlb migration Commit ba23f58de896 ("mm/migrate: don't call folio_putback_active_hugetlb() on dst hugetlb folio") moved setting of the migratable flag and active-list placement from folio_putback_active_hugetlb(dst) into move_hugetlb_state(), so that the freshly allocated destination folio is handled where allocation is known to have succeeded. Unfortunately, the new code was appended after the existing temporary-folio block in move_hugetlb_state(), which contains an early return added earlier by commit 5af1ab1d24e08 ("mm/hugetlb: optimize the surplus state transfer code in move_hugetlb_state()"): if (folio_test_hugetlb_temporary(new_folio)) { ... if (new_nid == old_nid) return; <-- skips the new code ... } /* added by ba23f58 */ folio_set_hugetlb_migratable(new_folio); list_move_tail(&new_folio->lru, ...&h->hugepage_activelist); When the destination folio is temporary (i.e. the hugetlb pool was exhausted and the migration callback fell back to alloc_migrate_hugetlb_folio()) and the migration does not cross a node -- the common case, and always true on a single-NUMA system -- move_hugetlb_state() returns before setting the migratable flag or adding the new folio to the active list. The destination folio is then installed in the page table but cannot be isolated afterwards, since folio_isolate_hugetlb() rejects folios without the migratable flag; a subsequent soft-offline, hard-offline or memory-hotplug offline of that folio fails with -EBUSY. This was reproduced on a single-NUMA arm64 VM: a second MADV_SOFT_OFFLINE on an already-migrated hugetlb page returned EBUSY and logged "hugepage isolation failed". Keep the surplus adjustment, which is the only part that depends on the node crossing, guarded by `if (new_nid != old_nid)', while making the migratable flag and active-list placement unconditional. This preserves the cleanup intent of ba23f58 and closes the early-return hole. Link: https://lore.kernel.org/20260707110254.3147686-1-mawupeng1@huawei.com Fixes: ba23f58de896 ("mm/migrate: don't call folio_putback_active_hugetlb() on dst hugetlb folio") Signed-off-by: Wupeng Ma Acked-by: David Hildenbrand (Arm) Cc: Baolin Wang Cc: Muchun Song Cc: Oscar Salvador Cc: Signed-off-by: Andrew Morton --- mm/hugetlb.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 885017e26fd4..4f6f58bf3db6 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -7332,14 +7332,14 @@ void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, * There is no need to transfer the per-node surplus state * when we do not cross the node. */ - if (new_nid == old_nid) - return; - spin_lock_irq(&hugetlb_lock); - if (h->surplus_huge_pages_node[old_nid]) { - h->surplus_huge_pages_node[old_nid]--; - h->surplus_huge_pages_node[new_nid]++; + if (new_nid != old_nid) { + spin_lock_irq(&hugetlb_lock); + if (h->surplus_huge_pages_node[old_nid]) { + h->surplus_huge_pages_node[old_nid]--; + h->surplus_huge_pages_node[new_nid]++; + } + spin_unlock_irq(&hugetlb_lock); } - spin_unlock_irq(&hugetlb_lock); } /* From 0ba6912f7e974045dcdd170f022cba19247e00bc Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 25 Aug 2026 14:25:15 +0000 Subject: [PATCH 0431/1198] Revert "once: don't use a work queue to reset sleepable static key" This reverts commit e8eef69a99f185e75909adb24ab93d706e07bf27. While DO_ONCE_SLEEPABLE() is used from sleepable/process context, callers may still be holding arbitrary subsystem locks. For instance, __inet_hash_connect() uses get_random_sleepable_once() which invokes DO_ONCE_SLEEPABLE() while holding the socket lock (sk_lock): lock_sock(sk) __inet_hash_connect() get_random_sleepable_once() DO_ONCE_SLEEPABLE() __do_once_sleepable_done() static_branch_disable() static_key_disable() cpus_read_lock() Calling static_branch_disable() directly from __do_once_sleepable_done() causes static_key_disable() to synchronously acquire cpus_read_lock() (cpu_hotplug_lock) and jump_label_mutex inside the caller's lock context. This introduces an unwanted lockdep dependency: sk_lock -> cpu_hotplug_lock Because cpu_hotplug_lock depends on fs_reclaim (via workqueue CPU bringup allocating memory with GFP_KERNEL), and storage/block layers (such as NVMe-TCP) acquire sk_lock during I/O dispatch, lockdep reports circular locking dependencies: set->srcu -> sk_lock -> cpu_hotplug_lock -> fs_reclaim -> q_usage_counter -> elevator_lock -> set->srcu This false positive previously prompted commit 19bdb70c77d3 ("nvme-tcp: lockdep: use dynamic lockdep keys per socket instance") to work around the warning using per-socket dynamic keys in NVMe-TCP. That in turn broke asynchronous socket teardown and caused syzbot warnings in tcp_tsq_handler(). Restoring once_disable_jump() in __do_once_sleepable_done() ensures that static_branch_disable() is executed asynchronously from a system workqueue without holding the caller's locks. Link: https://lore.kernel.org/20260825142515.1965654-1-edumazet@google.com Fixes: e8eef69a99f1 ("once: don't use a work queue to reset sleepable static key") Signed-off-by: Eric Dumazet Closes: https://lore.kernel.org/lkml/ao0mwtt8ePAINFni@shinhome/ Reported-by: Shin'ichiro Kawasaki Cc: Tony Luck Cc: Reinette Chatre Cc: Keith Busch Cc: Nilay Shroff Cc: Signed-off-by: Andrew Morton --- lib/once.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/once.c b/lib/once.c index d801bfa945e6..0a0a919156e0 100644 --- a/lib/once.c +++ b/lib/once.c @@ -93,6 +93,6 @@ void __do_once_sleepable_done(bool *done, struct static_key_true *once_key, { *done = true; mutex_unlock(&once_mutex); - static_branch_disable(once_key); + once_disable_jump(once_key, mod); } EXPORT_SYMBOL(__do_once_sleepable_done); From 627824f20f237902e696efe5b563c18422443370 Mon Sep 17 00:00:00 2001 From: "Lorenzo Stoakes (ARM)" Date: Wed, 26 Aug 2026 10:56:39 +0100 Subject: [PATCH 0432/1198] MAINTAINERS: remove Lorenzo as THP co-maintainer Unfortunately my workload is such that I simply no longer have the time to give THP the focus that it deserves. So, at least temporarily, step down from the role. Link: https://lore.kernel.org/20260826-drop-thp-maintainership-v1-1-3d102748fa17@kernel.org Signed-off-by: Lorenzo Stoakes (ARM) Cc: Baolin Wang Cc: Barry Song Cc: David Hildenbrand Cc: Dev Jain Cc: Lance Yang Cc: Liam R. Howlett Cc: Lorenzo Stoakes Cc: Ryan Roberts Cc: Zi Yan Cc: Kiryl Shutsemau Signed-off-by: Andrew Morton --- MAINTAINERS | 1 - 1 file changed, 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 00843d667a4f..85a2983e430a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17412,7 +17412,6 @@ F: mm/swapfile.c MEMORY MANAGEMENT - THP (TRANSPARENT HUGE PAGE) M: Andrew Morton M: David Hildenbrand -M: Lorenzo Stoakes R: Zi Yan R: Baolin Wang R: Liam R. Howlett From 341b9b4f8f540fc03e928e67351e4be9461bc56d Mon Sep 17 00:00:00 2001 From: Thorsten Blum Date: Tue, 25 Aug 2026 18:49:27 +0200 Subject: [PATCH 0433/1198] MAINTAINERS: mailmap: update entries for Thorsten Blum Map my previously used email addresses to blum@kernel.org. Link: https://lore.kernel.org/20260825164933.105605-2-blum@kernel.org Signed-off-by: Thorsten Blum Cc: Jakub Kacinski Cc: Martin Kepplinger Signed-off-by: Andrew Morton --- .mailmap | 3 ++- MAINTAINERS | 4 ++-- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/.mailmap b/.mailmap index 6803f3bd2865..9dc7096b79f7 100644 --- a/.mailmap +++ b/.mailmap @@ -898,7 +898,8 @@ Thomas Graf Thomas Gleixner Thomas Körper Thomas Pedersen -Thorsten Blum +Thorsten Blum +Thorsten Blum Tiezhu Yang Tingwei Zhang Tirupathi Reddy diff --git a/MAINTAINERS b/MAINTAINERS index 85a2983e430a..85cc77fe75b7 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17693,7 +17693,7 @@ F: Documentation/devicetree/bindings/serial/atmel,at91-usart.yaml F: drivers/spi/spi-at91-usart.c MICROCHIP ATSHA204A DRIVER -M: Thorsten Blum +M: Thorsten Blum L: linux-crypto@vger.kernel.org S: Maintained F: drivers/crypto/atmel-sha204a.c @@ -17717,7 +17717,7 @@ F: Documentation/devicetree/bindings/media/microchip,csi2dc.yaml F: drivers/media/platform/microchip/microchip-csi2dc.c MICROCHIP ECC DRIVER -M: Thorsten Blum +M: Thorsten Blum L: linux-crypto@vger.kernel.org S: Maintained F: drivers/crypto/atmel-ecc.c From dc3565a4ae538e584e5e63b3b3cd1eaf502593c1 Mon Sep 17 00:00:00 2001 From: Hajo Noerenberg Date: Mon, 31 Aug 2026 14:43:03 +0200 Subject: [PATCH 0434/1198] ata: ahci: work around lost interrupts on Marvell 88SE61xx ahci_single_level_irq_intr() services the ports first and clears the global HOST_IRQ_STAT afterwards, as recommended by AHCI 1.1 section 10.6.2. The Marvell 88SE6111/6121/6145 family stops reporting interrupts for a port when HOST_IRQ_STAT is cleared while PxIS still holds bits: PxIS keeps its content, HOST_IRQ_STAT reads back as 0, the port is never looked at again, and the command in flight only ends in a timeout. Measured on a Seagate Blackarmor NAS440 (Marvell 88F6281 Kirkwood, 88SE6121 rev B2 behind PCIe) by polling the AHCI registers from userspace while an IDENTIFY was outstanding: t=303.046 irqs 127 PxIS 0x00000000 PxCI 0x00000001 IDENTIFY issued t=303.057 irqs 128 PxIS 0x00000020 PxCI 0x00000000 CI cleared, DPS set, one interrupt taken ... PxIS stays 0x00000020, HOST_IRQ_STAT stays 0 ... t~308.05 qc timeout after 5000 msecs The command had completed - PxCI was clear and PxIS had DPS set - so ahci_qc_complete() would have completed it. It never got the chance because the handler read HOST_IRQ_STAT as 0 and returned IRQ_NONE. Marvell's own driver for these chips clears the two registers in the opposite order and says so ("clear global before channel"), and ahci_xgene handles its broken edge latch the same way. Since the reordering costs at most one spurious interrupt per valid one on conforming controllers, do it in a private interrupt handler selected for board_ahci_mv instead of changing libahci for everyone. With this applied, SATA-2 and SATA-3 disks work at 3.0 Gbps on the 88SE6121 without the drive-side 1.5 Gbps jumper that was needed before. Time from link up to a successful IDENTIFY: WDC WD5000AADS-00S9B0 port 0 7 ms (never identified before) WDC WD3202ABYS-01B7A0 port 1 28 ms WDC WD30EFRX-68EUZN0 port 1 200 ms (3 TB, HPA detection ok) Only the 88SE6121 was tested; board_ahci_mv also covers the 88SE6145, which Marvell's driver treats identically. Fixes: cd70c26617f4 ("[libata] AHCI: Add support for Marvell AHCI-like chips (initially 6145)") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/linux-ide/db6b48b7-d69a-564b-24f0-75fbd6a9e543@noerenberg.de/ Link: https://bugzilla.kernel.org/show_bug.cgi?id=216094 Signed-off-by: Hajo Noerenberg Reviewed-by: Damien Le Moal Acked-by: Pali Rohar Link: https://lore.kernel.org/r/20260831124303.920391-1-hajo-linux-ide@noerenberg.de Signed-off-by: Niklas Cassel --- drivers/ata/ahci.c | 49 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 58f512f8952a..9b8c0935001c 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -2614,6 +2614,51 @@ static irqreturn_t ahci_thunderx_irq_handler(int irq, void *dev_instance) } #endif +/* + * The Marvell 88SE6111/6121/6145 ("Thor") family stops reporting interrupts + * for a port when HOST_IRQ_STAT is cleared while PxIS still holds bits: PxIS + * keeps its content, HOST_IRQ_STAT reads back as 0, the port is never looked + * at again and the command in flight only ends in a timeout. On a 88SE6121 + * this makes every SATA-2 or SATA-3 disk fail to IDENTIFY, while SATA-1 disks + * happen to win the race often enough to work. + * + * Clearing the host status before servicing the ports avoids it. Marvell's + * own driver for these chips does the same and says so ("clear global before + * channel"), and ahci_xgene handles its broken edge latch the same way. The + * price is at most one spurious interrupt per valid one, which is why this is + * not the generic behaviour - see AHCI 1.1 section 10.6.2. + * + * Link: https://bugzilla.kernel.org/show_bug.cgi?id=216094 + */ +static irqreturn_t ahci_mv_irq_handler(int irq, void *dev_instance) +{ + struct ata_host *host = dev_instance; + struct ahci_host_priv *hpriv = host->private_data; + void __iomem *mmio = hpriv->mmio; + unsigned int rc; + u32 irq_stat, irq_masked; + + irq_stat = readl(mmio + HOST_IRQ_STAT); + if (!irq_stat) + return IRQ_NONE; + + irq_masked = irq_stat & hpriv->port_map; + + spin_lock(&host->lock); + + /* + * Use the unmasked value to clear the interrupt, as a spurious pending + * event on a dummy port might cause a screaming IRQ. + */ + writel(irq_stat, mmio + HOST_IRQ_STAT); + + rc = ahci_handle_port_intr(host, irq_masked); + + spin_unlock(&host->lock); + + return IRQ_RETVAL(rc); +} + static void ahci_remap_check(struct pci_dev *pdev, int bar, struct ahci_host_priv *hpriv) { @@ -2917,6 +2962,10 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) return -ENOMEM; hpriv->flags |= (unsigned long)pi.private_data; + /* the Marvell "Thor" family needs HOST_IRQ_STAT cleared first */ + if (board_id == board_ahci_mv) + hpriv->irq_handler = ahci_mv_irq_handler; + /* MCP65 revision A1 and A2 can't do MSI */ if (board_id == board_ahci_mcp65 && (pdev->revision == 0xa1 || pdev->revision == 0xa2)) From 9012da455ab9a05d8205b90d0ad7c8b526f89062 Mon Sep 17 00:00:00 2001 From: Chenguang Zhao Date: Thu, 6 Aug 2026 17:10:45 +0800 Subject: [PATCH 0435/1198] net: 6lowpan: fix mismatched comments Rename @_nexthdrlen to @_hdrlen and drop stale @nhc from lowpan_nhc_do_uncompression docs Signed-off-by: Chenguang Zhao Reviewed-by: Simon Horman Link: https://lore.kernel.org/20260806091045.1701326-1-chenguang.zhao@linux.dev Signed-off-by: Stefan Schmidt --- net/6lowpan/nhc.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/6lowpan/nhc.h b/net/6lowpan/nhc.h index ab7b4977c32b..c995029696d0 100644 --- a/net/6lowpan/nhc.h +++ b/net/6lowpan/nhc.h @@ -15,7 +15,7 @@ * @__nhc: variable name of the lowpan_nhc struct. * @_name: const char * of common header compression name. * @_nexthdr: ipv6 nexthdr field for the header compression. - * @_nexthdrlen: ipv6 nexthdr len for the reserved space. + * @_hdrlen: ipv6 nexthdr len for the reserved space. * @_id: one byte nhc id value. * @_idmask: one byte nhc id mask value. * @_uncompress: callback for uncompression call. @@ -102,7 +102,6 @@ int lowpan_nhc_do_compression(struct sk_buff *skb, const struct ipv6hdr *hdr, /** * lowpan_nhc_do_uncompression - calling uncompress callback for nhc * - * @nhc: 6LoWPAN nhc context, get by lowpan_nhc_by_ functions. * @skb: skb of 6LoWPAN header, skb->data should be pointed to nhc id value. * @dev: netdevice for print logging information. * @hdr: ipv6hdr for setting nexthdr value. From 1719d035a6fa90b7467b6daf45a573f5180013b2 Mon Sep 17 00:00:00 2001 From: Zhan Xusheng Date: Sat, 22 Aug 2026 18:59:30 +0800 Subject: [PATCH 0436/1198] sched/fair: Use update_curr_eevdf() for the remaining root cfs_rq callers pick_task_fair() and yield_task_fair() call update_curr(&rq->cfs) to bring curr up to date before they look at the eevdf state. With cgroups that does not happen: update_curr() reads ->h_curr, which on the root cfs_rq is the top level group entity, and returns at the !entity_is_task() check before touching vruntime. Both then read ->curr, so the guard and the update disagree about which entity they mean. Counting how often ->h_curr and ->curr differ at pick_task_fair(), on one CPU for 10s with three busy tasks and one 200us-periodic task: all tasks in the root cgroup 43321 calls, 0 no-ops busy tasks in G0, periodic in G1 45211 calls, 45193 no-ops Whether that matters depends on what precedes the pick. Since commit 68e37487810a ("sched/fair: Fix flat hierarchy") the tick and enqueue/dequeue all update curr correctly, so on the normal reschedule path only the microseconds between those and the pick are missing, and I could not measure a latency difference there. Three paths have nothing before them on that rq though: - pick_task() on the sibling rqs of a core under core scheduling (kernel/sched/core.c), which updates that rq's clock first for exactly this reason - fair_server_pick_task() - yield_task_fair(), where the stale value feeds the entity_eligible() test that guards forfeiting the remaining vruntime There curr can be a full tick behind, as it was before that commit. No new behaviour for the entity being updated: without cgroups ->h_curr is already the task, so these two call sites already run the full update_curr() including update_deadline(), dl_server_update() and the resched_curr_lazy() at the end. This makes the cgroup case do the same. Fixes: 85570f10a4c6 ("sched/eevdf: Move to a single runqueue") Signed-off-by: Zhan Xusheng Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Vincent Guittot Link: https://patch.msgid.link/20260822105930.2352761-1-zhanxusheng1024@gmail.com --- kernel/sched/fair.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 8dff37059faf..5d47de512f32 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -10057,7 +10057,7 @@ struct task_struct *pick_task_fair(struct rq *rq, struct rq_flags *rf) /* Might not have done put_prev_entity() */ if (cfs_rq->curr && cfs_rq->curr->on_rq) - update_curr(cfs_rq); + update_curr_eevdf(cfs_rq); se = pick_next_entity(rq, true); if (!se) @@ -10160,7 +10160,7 @@ static void yield_task_fair(struct rq *rq) /* * Update run-time statistics of the 'current'. */ - update_curr(cfs_rq); + update_curr_eevdf(cfs_rq); /* * Tell update_rq_clock() that we've just updated, * so we don't do microscopic update in schedule() From dae5c0292080dd7b9c7d784268dcf443f1f3d15e Mon Sep 17 00:00:00 2001 From: Seiji Nishikawa Date: Sun, 30 Aug 2026 16:37:46 +0900 Subject: [PATCH 0437/1198] sched/rt,dl: Skip migrate-disabled tasks when picking a push candidate A migrate_disable()'d RT task cannot be moved to another CPU, but the scheduler still keeps such a task on that CPU's pushable list (rq->rt.pushable_tasks) and still marks the runqueue RT-overloaded (rq->rt.overloaded = 1). So the RT balancer keeps treating this CPU as having a task to move away, and keeps trying to move the task, but the push can never succeed. When the head is pinned, push_rt_task() does not give up either. It falls back to pushing rq->curr instead, using the per-CPU stopper, as added by commit a7c81556ec4d ("sched: Fix migrate_disable() vs rt/dl balancing"). The CPU spends tens of milliseconds in this retry loop. The core is isolated for real-time work, but during the loop nearly half of its time is consumed by pushes that cannot succeed. An ftrace capture of the affected CPU, with sched_switch enabled and commit 94894c9c477e ("sched/rt: Skip currently executing CPU in rto_next_cpu()") applied, shows where the CPU time went. Two SCHED_FIFO tasks at equal priority shared the CPU, taskA migrate_disable()'d and queued, taskB as rq->curr. In one 89 ms window, taskB got only 52 ms of CPU. The other 37 ms went to the stopper thread. The scheduler kept trying to push taskA, the pinned head of the pushable list, fell back to pushing taskB instead, and woke the stopper 5204 times. Every one of those pushes failed and no task was moved. taskA stayed runnable and queued the whole time, and never ran. Pushing taskB fails on a re-check. find_lock_lowest_rq() drops the rq lock to take the target rq lock, then checks again with "task != pick_next_pushable_task(rq)". The task being pushed is taskB, but the pick returns taskA, the head of the pushable list. taskB is rq->curr, and set_next_task_rt() removes the running task from that list, so taskB can never be the head. The check expects a candidate taken from the pushable list, but the fallback pushes rq->curr, which is never on that list. So the check fails every time. .--> push-IPI arrives | | | v | pushable head = taskA -> pinned, cannot be pushed | | | v | so push taskB instead -> wake migration/N, a stop-class | | thread, so it preempts taskB | v | re-check compares taskB against the pushable head, | which is still taskA -> give up | | | v | nothing moved, taskA still queued, rq still overloaded | | '----------' repeats every ~17 us, 5204 times, for 89 ms The loop cannot stop itself. Every round leaves the runqueue exactly as it was, so the next push-IPI does the same thing. In the capture it ended only when taskB went to sleep on its own. taskA was then picked locally and left the pushable list. CPU time per task in the window, from sched_switch: taskB 51.95 ms real work migration/N 37.18 ms nothing moved taskA 0.00 ms queued the whole time, never picked idle 0.01 ms Counts over the same window: 7667 push-IPIs handled on this CPU 17481 pick_next_pushable_task() returned taskA, still pinned 5204 find_lock_lowest_rq() gave up on the re-check 1 push that actually completed 0 migrations of taskA The CPU times and the window length come from the standard sched_switch tracepoint. The counts needed tracepoints added inside the RT balancer for this investigation. The self-IPI path is closed by the rto_next_cpu() fix above, and that part works. But the runqueue is still marked overloaded, because the pinned task is still advertised as pushable. Other CPUs now send the push-IPIs during their own RT balancing, and the same loop runs again. Closing the self-IPI path did not stop a pinned task from triggering push balancing. A pinned task should never have been returned as a push candidate in the first place. A migrate_disable()'d task cannot be migrated, so it belongs in the same skip that was added for on_cpu tasks by commit e0ca8991b2de ("sched: Make class_schedulers avoid pushing current, and get rid of proxy_tag_curr()"). Add is_migration_disabled() to the skip condition in pick_next_pushable_task() and pick_next_pushable_dl_task(). With the skip in place, if the pinned task is the only extra runnable task the helpers return NULL, push_rt_task() and push_dl_task() give up early, and no stopper is woken. The pinned task then runs locally once curr yields. If a task that really can be migrated is queued behind the pinned head, it is now picked and pushed for real. This makes the fallback that pushes rq->curr unreachable when the pushable head is migrate-disabled. Nothing is lost, because that path was always stopped by the re-check described above. In the capture it ran 5204 times and moved nothing. Fixes: a7c81556ec4d ("sched: Fix migrate_disable() vs rt/dl balancing") Signed-off-by: Seiji Nishikawa Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20260830073746.2189355-1-snishika@redhat.com --- kernel/sched/deadline.c | 4 ++-- kernel/sched/rt.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 857dbe3519a8..0663c00c41c0 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -3028,8 +3028,8 @@ static struct task_struct *pick_next_pushable_dl_task(struct rq *rq) next_node = rb_first_cached(&rq->dl.pushable_dl_tasks_root); while (next_node) { i = __node_2_pdl(next_node); - /* make sure task isn't on_cpu (possible with proxy-exec) */ - if (!task_on_cpu(rq, i)) { + /* skip tasks that cannot be migrated */ + if (!task_on_cpu(rq, i) && !is_migration_disabled(i)) { p = i; break; } diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index e6e5f8a2caaf..85303add726d 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1872,8 +1872,8 @@ static struct task_struct *pick_next_pushable_task(struct rq *rq) return NULL; plist_for_each_entry(i, head, pushable_tasks) { - /* make sure task isn't on_cpu (possible with proxy-exec) */ - if (!task_on_cpu(rq, i)) { + /* skip tasks that cannot be migrated */ + if (!task_on_cpu(rq, i) && !is_migration_disabled(i)) { p = i; break; } From c6dcd97c8be75f052a1ca52cf79b03e7292962f1 Mon Sep 17 00:00:00 2001 From: "Shubhang Kaushik (Ampere)" Date: Fri, 7 Aug 2026 13:38:52 -0700 Subject: [PATCH 0438/1198] sched/core: Skip rq->avg_idle update without a valid idle_stamp Commit 4b603f1551a73 ("sched: Update rq->avg_idle when a task is moved to an idle CPU") moved rq->avg_idle accounting out of the wakeup path and into put_prev_task_idle(), so that the idle interval is consumed whenever the idle task is switched out. The wakeup-side accounting that it replaced only updated rq->avg_idle when rq->idle_stamp was non-zero. The new helper lost that validity check and unconditionally computes: rq_clock(rq) - rq->idle_stamp If rq->idle_stamp is zero, this uses rq_clock(rq) as the sample. That is not a valid idle duration and can immediately drive rq->avg_idle to its clamp. This can happen when sched_balance_newidle() returns before setting rq->idle_stamp, for example when this_rq->ttwu_pending is set. In that case the rq can switch to the idle task with idle_stamp still zero and leave idle again when the pending wakeup is processed. Other paths can also switch to the idle task without setting rq->idle_stamp via newidle_balance(), for example find_proxy_task() or force-idling. Restore the idle_stamp validity check in update_rq_avg_idle() and skip the rq->avg_idle update when there is no measured idle interval. Fixes: 4b603f1551a73 ("sched: Update rq->avg_idle when a task is moved to an idle CPU") Signed-off-by: Shubhang Kaushik (Ampere) Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: K Prateek Nayak Reviewed-by: Vincent Guittot Acked-by: John Stultz Link: https://patch.msgid.link/20260807-master-v3-1-c328354efed3@gentwo.org --- kernel/sched/core.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f78275192036..74724501c623 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3742,11 +3742,17 @@ static inline void ttwu_do_wakeup(struct task_struct *p) void update_rq_avg_idle(struct rq *rq) { - u64 delta = rq_clock(rq) - rq->idle_stamp; - u64 max = 2*rq->max_idle_balance_cost; + u64 idle_stamp = rq->idle_stamp; + u64 delta, max; + + if (!idle_stamp) + return; + + delta = rq_clock(rq) - idle_stamp; update_avg(&rq->avg_idle, delta); + max = 2 * rq->max_idle_balance_cost; if (rq->avg_idle > max) rq->avg_idle = max; rq->idle_stamp = 0; From f8610c57f4078c63d1d4e2f3d7134f3dc1768403 Mon Sep 17 00:00:00 2001 From: Wanwu Li Date: Mon, 31 Aug 2026 18:11:40 +0800 Subject: [PATCH 0439/1198] sched/fair: Use cfs_rq->h_curr in throttle_cfs_rq() After commit 85570f10a4c6 ("sched/eevdf: Move to a single runqueue"), cfs_rq->curr is only maintained on the root cfs_rq (set/cleared from set_next_task_fair()/put_prev_task_fair()), while cfs_rq->h_curr is the per-level current entity, set by set_next_entity() at every level of the hierarchy. For an intermediate cfs_rq (a cgroup), cfs_rq->curr is always NULL, but cfs_rq->h_curr is the group entity at that level. throttle_cfs_rq() reads cfs_rq->curr to decide whether there is a running entity at the throttled level, in which case it should request a full sched_cfs_bandwidth_slice() of runtime and arm the deferred throttle task_work via task_throttle_setup_work(). For intermediate cfs_rqs the check is always false, so bandwidth-controlled cgroups always get just 1ns of runtime and never arm the deferred throttle work; the running task then escapes throttling until the next pick arms the work instead, even though there is an on-rq entity at this level. Switch the read to cfs_rq->h_curr so intermediate bandwidth-controlled cgroups behave consistently with the root cfs_rq, matching the existing usage of cfs_rq->h_curr in update_curr() and check_enqueue_throttle(). Fixes: 85570f10a4c6 ("sched/eevdf: Move to a single runqueue") Signed-off-by: Wanwu Li Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Aaron Lu Tested-by: Aaron Lu Link: https://patch.msgid.link/20260831101141.391382-2-liwanwu@kylinos.cn --- kernel/sched/fair.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 5d47de512f32..73797d661486 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6978,14 +6978,14 @@ static int tg_throttle_down(struct task_group *tg, void *data) static bool throttle_cfs_rq(struct cfs_rq *cfs_rq) { struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); - struct sched_entity *curr = cfs_rq->curr; + struct sched_entity *curr = cfs_rq->h_curr; struct rq *rq = rq_of(cfs_rq); scoped_guard(raw_spinlock, &cfs_b->lock) { u64 target_runtime = 1; /* - * If cfs_rq->curr is still runnable, we are here from an + * If cfs_rq->h_curr is still runnable, we are here from an * update_curr(). Request sysctl_sched_cfs_bandwidth_slice * worth of bandwidth to continue running. * From b038383526d8c7883ea0486dd1911102b6dda414 Mon Sep 17 00:00:00 2001 From: Wanwu Li Date: Mon, 31 Aug 2026 18:11:41 +0800 Subject: [PATCH 0440/1198] sched/fair: Use cfs_rq->h_curr in distribute_cfs_runtime() distribute_cfs_runtime() refreshes the rq clock and accounts elapsed runtime with update_curr() before redistributing bandwidth, but gates this on cfs_rq->curr. Since commit 85570f10a4c6 ("sched/eevdf: Move to a single runqueue") cfs_rq->curr is only maintained on the root cfs_rq, so for the cgroup cfs_rqs it walks, the check never fires and the refresh is dead code. Use cfs_rq->h_curr, the per-level current entity, restoring the intended behaviour: only refresh when something is actually running at the throttled level, i.e. within the deferred throttle window. Without this, runtime consumed by a still-running task of the throttled hierarchy is not docked before redistribution; unthrottle_cfs_rq() catches up unconditionally since commit 28ad5427682b ("sched/fair: Call update_curr() before unthrottling the hierarchy"), so this is not a correctness hole today, but the refresh the check was written for is gone. Fixes: 85570f10a4c6 ("sched/eevdf: Move to a single runqueue") Signed-off-by: Wanwu Li Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Aaron Lu Tested-by: Aaron Lu Link: https://patch.msgid.link/20260831101141.391382-3-liwanwu@kylinos.cn --- kernel/sched/fair.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 73797d661486..97021a5033fb 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -7192,7 +7192,7 @@ static bool distribute_cfs_runtime(struct cfs_bandwidth *cfs_b) if (!list_empty(&cfs_rq->throttled_csd_list)) continue; - if (cfs_rq->curr) { + if (cfs_rq->h_curr) { update_rq_clock(rq); update_curr(cfs_rq); } From eaece4849991d62fcd6f46637c55dcce00e25d70 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Mon, 31 Aug 2026 00:38:33 -0500 Subject: [PATCH 0441/1198] x86/itmt: Don't make ITMT enablement depend on debugfs sched_set_itmt_support() treats debugfs file creation failures as fatal. When CONFIG_DEBUG_FS is disabled, debugfs stubs return ERR_PTR(-ENODEV), causing ITMT to be silently disabled. debugfs is a debug-only facility; its return values should be ignored. Drop the fatal error handling and enable ITMT unconditionally. Fixes: d04013a4b21b ("x86/itmt: Move the "sched_itmt_enabled" sysctl to debugfs") Reported-by: Klaus Kusche Signed-off-by: Mario Limonciello Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Tim Chen Reviewed-by: K Prateek Nayak Tested-by: K Prateek Nayak Link: https://patch.msgid.link/20260831053836.1881864-1-mario.limonciello@amd.com --- arch/x86/kernel/itmt.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c index 243a769fdd97..85ebde361d6a 100644 --- a/arch/x86/kernel/itmt.c +++ b/arch/x86/kernel/itmt.c @@ -110,18 +110,14 @@ int sched_set_itmt_support(void) arch_debugfs_dir, &sysctl_sched_itmt_enabled, &dfs_sched_itmt_fops); - if (IS_ERR_OR_NULL(dfs_sched_itmt)) { + if (IS_ERR(dfs_sched_itmt)) dfs_sched_itmt = NULL; - return -ENOMEM; - } dfs_sched_core_prio = debugfs_create_file("sched_core_priority", 0644, arch_debugfs_dir, NULL, &sched_core_priority_fops); - if (IS_ERR_OR_NULL(dfs_sched_core_prio)) { + if (IS_ERR(dfs_sched_core_prio)) dfs_sched_core_prio = NULL; - return -ENOMEM; - } sched_itmt_capable = true; From f0d243a96f2684ad771d678767d17972cf840bd7 Mon Sep 17 00:00:00 2001 From: Tim Chen Date: Mon, 31 Aug 2026 10:40:53 -0700 Subject: [PATCH 0442/1198] sched/fair: Avoid creating misfits during cache-aware balancing Cache-aware load balancing biases tasks toward their preferred LLC. On asymmetric CPU capacity systems (e.g. big.LITTLE) the destination LLC may contain CPUs that are too small to run the task. Pulling the task there turns it into a misfit, trading a cache-locality gain for a capacity loss that's more detrimental to performance. Guard both cache-aware migration entry points against this: - can_migrate_llc_task(): forbid the LLC migration when the task fits its source CPU but would not fit the destination CPU. - alb_break_llc(): veto the active balance under the same condition so the runnable task is not pushed onto a CPU that cannot accommodate it. Both checks are gated with checks for hybrid processors, so symmetric systems are unaffected. Tasks that already do not fit their source CPU are left to the existing LLC policy, since the move cannot make their fitness worse (this also preserves misfit up-migration to bigger CPUs). Additionally, if there are misfit tasks found in the load balancing classification phase, prioritize misfit task migrations over LLC load aggregation on asymmetric systems. A better fitting CPU will boost performance more than better cache locality. Reviewed-by: Ricardo Neri Tested-by: Ricardo Neri Reviewed-by: Chen Yu Signed-off-by: Tim Chen Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/edbb2503d554c63dc9b72e201fb4a17e1cb119e7.camel@linux.intel.com --- kernel/sched/fair.c | 50 ++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 45 insertions(+), 5 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 97021a5033fb..ade1eceb39b8 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -10691,17 +10691,40 @@ static enum llc_mig can_migrate_llc(int src_cpu, int dst_cpu, return mig_llc; } +static inline bool task_misfits_asym_cpu(struct lb_env *env, struct task_struct *p) +{ + /* + * On asymmetric CPU capacity domains, do not let cache-aware + * balancing pull the task onto a destination CPU that cannot + * accommodate it. Doing so would turn the task into a misfit on + * the destination, trading a cache-locality gain for a capacity + * loss. If the task already does not fit its source CPU, the move + * cannot make things worse, so let the LLC preference decide. + */ + if ((env->sd->flags & SD_ASYM_CPUCAPACITY) && p && + !task_fits_cpu(p, env->dst_cpu) && + task_fits_cpu(p, env->src_cpu)) + return true; + + return false; +} + /* * Check if task p can migrate from source LLC to * destination LLC in terms of cache aware load balance. */ -static enum llc_mig can_migrate_llc_task(int src_cpu, int dst_cpu, +static enum llc_mig can_migrate_llc_task(struct lb_env *env, struct task_struct *p) { struct mm_struct *mm; bool to_pref; - int cpu; + int cpu, src_cpu, dst_cpu; + if (task_misfits_asym_cpu(env, p)) + return mig_forbid; + + src_cpu = env->src_cpu; + dst_cpu = env->dst_cpu; mm = p->mm; if (!mm) return mig_unrestricted; @@ -10758,6 +10781,14 @@ alb_break_llc(struct lb_env *env) unsigned long util = 0; struct task_struct *cur; + /* + * Migrating misfit tasks from current CPU + * to CPU with a better fit. + * Prioritize that over LLC preference. + */ + if (env->migration_type == migrate_misfit) + return false; + if (env->src_rq->nr_running <= 1) return true; @@ -10765,7 +10796,8 @@ alb_break_llc(struct lb_env *env) if (cur && cur->sched_class == &fair_sched_class) util = task_util(cur); - if (can_migrate_llc(env->src_cpu, env->dst_cpu, + if (task_misfits_asym_cpu(env, cur) || + can_migrate_llc(env->src_cpu, env->dst_cpu, util, false) == mig_forbid) return true; } @@ -10805,8 +10837,7 @@ static bool migrate_degrades_llc(struct task_struct *p, struct lb_env *env) READ_ONCE(p->preferred_llc) != llc_id(env->dst_cpu)) return true; - if (can_migrate_llc_task(env->src_cpu, - env->dst_cpu, p) != mig_forbid) + if (can_migrate_llc_task(env, p) != mig_forbid) return false; return true; @@ -11869,6 +11900,15 @@ static inline bool llc_balance(struct lb_env *env, struct sg_lb_stats *sgs, if (env->sd->flags & SD_SHARE_LLC) return false; + /* + * On asymmetric domains, group_misfit_task_load + * should be prioritized to move tasks to CPU that fit them + * over aggregating tasks to their preferred LLC. + */ + if ((env->sd->flags & SD_ASYM_CPUCAPACITY) && + sgs->group_misfit_task_load) + return false; + /* * Skip cache aware tagging if nr_balanced_failed is sufficiently high. * Threshold of cache_nice_tries is set to 1 higher than nr_balance_failed From 8a7f5b5e860b5c113ca99acd5b1e9074f5c5af3c Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Tue, 25 Aug 2026 11:37:06 +0100 Subject: [PATCH 0443/1198] perf/core: Skip empty AUX records with only format flags perf_aux_output_end() emits a PERF_RECORD_AUX when the recorded size is nonzero or when any flag other than PERF_AUX_FLAG_OVERWRITE is set. PMU format flags describe how an AUX payload is encoded. TRBE driver sets PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW for raw trace buffers, causing an AUX record to be emitted even when no trace data. This is noticeable when tracing a task with strace. Ptrace stops repeatedly end empty AUX transactions, producing many zero-sized PERF_RECORD_AUX records. For example: perf record -e cs_etm//u -m,128M -- strace ls perf script -D 2>&1 | awk '/PERF_RECORD_AUX offset/ { for (i = 1; i <= NF; i++) if ($i == "size:" && $(i + 1) == "0") count++ } END { print count }' 165 This recording contains 165 zero-sized AUX records which provide no useful information to userspace. Ignore PERF_AUX_FLAG_PMU_FORMAT_TYPE_MASK, together with PERF_AUX_FLAG_OVERWRITE, when deciding whether an empty AUX record is useful. Zero-sized records carrying TRUNCATED, PARTIAL or COLLISION are still emitted. Fixes: 547b60988e63 ("perf: aux: Add flags for the buffer format") Reported-by: Tamas Petz Signed-off-by: Leo Yan Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20260825-perf_core_fix_zero_aux_records-v1-1-23b95e8d5df3@arm.com --- kernel/events/ring_buffer.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 9fe92161715e..1b1ffe0533e5 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -509,7 +509,10 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) /* * Only send RECORD_AUX if we have something useful to communicate * - * Note: the OVERWRITE records by themselves are not considered + * PMU_FORMAT bits identify the PMU type rather than an AUX event + * has occurred, so ignore them for zero-sized records. + * + * The OVERWRITE records by themselves are not considered * useful, as they don't communicate any *new* information, * aside from the short-lived offset, that becomes history at * the next event sched-in and therefore isn't useful. @@ -518,7 +521,9 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) * offset. So, from now on we don't output AUX records that * have *only* OVERWRITE flag set. */ - if (size || (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE)) + if (size || + (handle->aux_flags & ~(u64)(PERF_AUX_FLAG_PMU_FORMAT_TYPE_MASK | + PERF_AUX_FLAG_OVERWRITE))) perf_event_aux_event(handle->event, aux_head, size, handle->aux_flags); From 58a8108bc73de0740d5b88150465d6690ea5f85f Mon Sep 17 00:00:00 2001 From: Yilin Zhang Date: Tue, 1 Sep 2026 00:21:55 +0800 Subject: [PATCH 0444/1198] perf: Fix use-after-free when perf mmap() revival races with the last munmap() perf_mmap_close() drops rb->mmap_count *without* holding event->mmap_mutex (the refcount_dec_and_test() right before the refcount_dec_and_mutex_lock() of event->mmap_count). A concurrent perf_mmap_rb() can slot its entire "revival" path into that window (perf_mmap holds event->mmap_mutex for its whole duration, including rb_alloc): munmap side (perf_mmap_close) mmap side (perf_mmap_rb) ----------------------------------- -------------------------------- rb->mmap_count 1 -> 0 (no lock) (holds event->mmap_mutex) inc_not_zero(rb->mmap_count) fails ring_buffer_attach(event, NULL) rb_alloc() + attach new rb refcount_set(&event->mmap_count, 1) lock; event->mmap_count 1 -> 0 ring_buffer_attach(event, NULL) ring_buffer_put() -> frees the *new* rb The revival's refcount_set(&event->mmap_count, 1) is an invisible 1 -> 1 write: the close frees the just-revived buffer although the other process still has it mapped -- a page-level use-after-free allowing local privilege escalation to root by any unprivileged user (default kernel.perf_event_paranoid=2). Swap the order of the two counter updates: event->mmap_count is dropped first via refcount_dec_and_mutex_lock(), so its 1 -> 0 transition and the ring_buffer_attach() stay serialized with perf_mmap(). rb->mmap_count == 0 then implies every event using the buffer is detached already, so the result of the rb->mmap_count drop can gate the remaining teardown directly and detach_rest is no longer needed. An earlier fix for this race from Kyle Zeng and David Lee takes event->mmap_mutex around both counter updates [0]; here the not-last close stays lockless. Fixes: 59741451b49c ("perf: Identify the 0->1 transition for event::mmap_count") Reported-by: Kimi Security Team Suggested-by: Peter Zijlstra Co-developed-by: Weiming Shi Signed-off-by: Weiming Shi Signed-off-by: Yilin Zhang Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/linux-perf-users/20260804060931.711308-1-david.lee@trailofbits.com/ [0] Cc: Cc: stable@vger.kernel.org # 6.18+ Link: https://patch.msgid.link/20260831162155.1437652-1-yilinzhang@moonshot.ai --- kernel/events/core.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index a6c8e38a3110..f02780529b43 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7029,7 +7029,6 @@ static void perf_mmap_close(struct vm_area_struct *vma) mapped_f unmapped = get_mapped(event, event_unmapped); struct perf_buffer *rb = ring_buffer_get(event); struct user_struct *mmap_user = rb->mmap_user; - bool detach_rest = false; /* FIXIES vs perf_pmu_unregister() */ if (unmapped) @@ -7060,17 +7059,18 @@ static void perf_mmap_close(struct vm_area_struct *vma) mutex_unlock(&rb->aux_mutex); } - if (refcount_dec_and_test(&rb->mmap_count)) - detach_rest = true; - - if (!refcount_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex)) - goto out_put; - - ring_buffer_attach(event, NULL); - mutex_unlock(&event->mmap_mutex); + /* + * Drop references in reverse order of perf_mmap() to prevent + * rb revival after rb->mmap_count reaches zero. + */ + if (refcount_dec_and_mutex_lock(&event->mmap_count, + &event->mmap_mutex)) { + ring_buffer_attach(event, NULL); + mutex_unlock(&event->mmap_mutex); + } /* If there's still other mmap()s of this buffer, we're done. */ - if (!detach_rest) + if (!refcount_dec_and_test(&rb->mmap_count)) goto out_put; /* From 02c6be7d675b21d81f0ba3a524346850a8c0e3bf Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 24 Aug 2026 15:51:29 +0000 Subject: [PATCH 0445/1198] locking/lockdep: Invalidate stale class_cache entries for zapped classes syzbot reported a lockdep splat hitting DEBUG_LOCKS_WARN_ON(1) in hlock_class() due to an invalid class_idx: WARNING: kernel/locking/lockdep.c:238 at __lock_acquire+0x382/0x2cf0 kernel/locking/lockdep.c:5203 Workqueue: wg-crypt-wg0 wg_packet_tx_worker RIP: 0010:hlock_class kernel/locking/lockdep.c:238 [inline] RIP: 0010:check_wait_context kernel/locking/lockdep.c:4870 [inline] RIP: 0010:__lock_acquire+0x389/0x2cf0 kernel/locking/lockdep.c:5203 Call Trace: lock_acquire+0x106/0x350 kernel/locking/lockdep.c:5886 _raw_spin_lock+0x2e/0x40 kernel/locking/spinlock.c:173 tcp_tsq_handler+0x29/0x200 net/ipv4/tcp_output.c:1291 tcp_tsq_workfn+0x384/0x410 net/ipv4/tcp_output.c:1325 ... When a lock class is zapped (e.g. during module unload or key unregistration), zap_class() clears the class's bit in lock_classes_in_use and removes it from the class hash table. However, existing lockdep_map instances embedded in data structures may still retain a pointer to the zapped class in their class_cache[] array. When __lock_acquire() subsequently runs on such a lock, it finds lock->class_cache[subclass] != NULL, skipping register_lock_class() and assigning hlock->class_idx to the index of the zapped class. When check_wait_context() or hlock_class() inspects the held_lock, it finds !test_bit(class_idx, lock_classes_in_use) and warns. Furthermore, if the zapped slot is subsequently re-allocated to an unrelated lock key, the stale class_cache entry would erroneously match the unrelated class (ABA issue). Add lock_class_cache_is_valid() to validate that the cached class is within lock_classes bounds, still allocated in lock_classes_in_use (using uninstrumented arch_test_bit() in __always_inline context so it is safe in noinstr contexts like match_held_lock()), and that class->key matches the expected subkey (taking lockdep_set_subclass() overrides into account). Also use READ_ONCE()/WRITE_ONCE() when accessing class_cache[]. If the entry is invalid or stale, fall back to register_lock_class() / look_up_lock_class(). Fixes: a0b0fd53e1e6 ("locking/lockdep: Free lock classes that are no longer in use") Closes: https://lore.kernel.org/netdev/6a8c66dc.4d75e56a.c9a88.0050.GAE@google.com/T/#u Reported-by: syzbot+2d770620059281e225a4@syzkaller.appspotmail.com Assisted-by: Gemini:gemini-3.1-pro Signed-off-by: Eric Dumazet Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20260824155129.676096-1-edumazet@google.com --- kernel/locking/lockdep.c | 50 +++++++++++++++++++++++++++++++++------- 1 file changed, 42 insertions(+), 8 deletions(-) diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 25d77d4a1061..763f79806bd8 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -963,6 +963,34 @@ look_up_lock_class(const struct lockdep_map *lock, unsigned int subclass) return NULL; } +static __always_inline bool lock_class_cache_is_valid(const struct lockdep_map *lock, + const struct lock_class *class, + unsigned int subclass) +{ + unsigned int class_subclass; + + if (!class) + return false; + + if (unlikely(class < lock_classes || class >= lock_classes + MAX_LOCKDEP_KEYS)) + return false; + + if (unlikely(!arch_test_bit(class - lock_classes, lock_classes_in_use))) + return false; + + if (unlikely(!lock->key)) + return false; + + class_subclass = subclass ? subclass : class->subclass; + if (unlikely(class_subclass >= MAX_LOCKDEP_SUBCLASSES)) + return false; + + if (unlikely(READ_ONCE(class->key) != lock->key->subkeys + class_subclass)) + return false; + + return true; +} + /* * Static locks do not have their class-keys yet - for them the key is * the lock object itself. If the lock is in the per cpu area, the @@ -1395,9 +1423,9 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) out_set_class_cache: if (!subclass || force) - lock->class_cache[0] = class; + WRITE_ONCE(lock->class_cache[0], class); else if (subclass < NR_LOCKDEP_CACHING_CLASSES) - lock->class_cache[subclass] = class; + WRITE_ONCE(lock->class_cache[subclass], class); /* * Hash collision, did we smoke some? We found a class with a matching @@ -4957,7 +4985,7 @@ void lockdep_init_map_type(struct lockdep_map *lock, const char *name, int i; for (i = 0; i < NR_LOCKDEP_CACHING_CLASSES; i++) - lock->class_cache[i] = NULL; + WRITE_ONCE(lock->class_cache[i], NULL); #ifdef CONFIG_LOCK_STAT lock->cpu = raw_smp_processor_id(); @@ -5022,12 +5050,15 @@ EXPORT_SYMBOL_GPL(__lockdep_no_track__); void lockdep_set_lock_cmp_fn(struct lockdep_map *lock, lock_cmp_fn cmp_fn, lock_print_fn print_fn) { - struct lock_class *class = lock->class_cache[0]; + struct lock_class *class = READ_ONCE(lock->class_cache[0]); unsigned long flags; raw_local_irq_save(flags); lockdep_recursion_inc(); + if (!lock_class_cache_is_valid(lock, class, 0)) + class = NULL; + if (!class) class = register_lock_class(lock, 0, 0); @@ -5119,8 +5150,11 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, if (DEBUG_LOCKS_WARN_ON(subclass >= MAX_LOCKDEP_SUBCLASSES)) return 0; - if (subclass < NR_LOCKDEP_CACHING_CLASSES) - class = lock->class_cache[subclass]; + if (subclass < NR_LOCKDEP_CACHING_CLASSES) { + class = READ_ONCE(lock->class_cache[subclass]); + if (!lock_class_cache_is_valid(lock, class, subclass)) + class = NULL; + } /* * Not cached? */ @@ -5323,9 +5357,9 @@ static noinstr int match_held_lock(const struct held_lock *hlock, return 1; if (hlock->references) { - const struct lock_class *class = lock->class_cache[0]; + const struct lock_class *class = READ_ONCE(lock->class_cache[0]); - if (!class) + if (!lock_class_cache_is_valid(lock, class, 0)) class = look_up_lock_class(lock, 0); /* From ff5891b266a7fc6a062710836be84f1cc19338b5 Mon Sep 17 00:00:00 2001 From: Fan Wu Date: Wed, 12 Aug 2026 06:17:14 +0000 Subject: [PATCH 0446/1198] ieee802154: cc2520: fix FIFOP work use-after-free The FIFOP interrupt handler queues cc2520_fifop_irqwork. On removal, cc2520_remove() only flushes the work. The devm-managed FIFOP IRQ remains active until after ->remove() returns and can queue the work again after that flush, allowing it to run after the private data is released. Disable the work with disable_work_sync() instead of flushing it, so the handler can no longer queue it once removal begins. Destroy the buffer mutex last, since the worker and the stop callback invoked through ieee802154_unregister_hw() both take it. Found by an in-house static analysis tool. Fixes: 0da6bc8cc341 ("ieee802154: cc2520: adds driver for TI CC2520 radio") Cc: stable@vger.kernel.org # v6.10+ Suggested-by: Miquel Raynal Reviewed-by: Miquel Raynal Assisted-by: Codex:gpt-5.6 Signed-off-by: Fan Wu Link: https://lore.kernel.org/20260812061714.175966-1-fanwu01@zju.edu.cn Signed-off-by: Stefan Schmidt --- drivers/net/ieee802154/cc2520.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/net/ieee802154/cc2520.c b/drivers/net/ieee802154/cc2520.c index 2b7034193a00..abfcfe07246a 100644 --- a/drivers/net/ieee802154/cc2520.c +++ b/drivers/net/ieee802154/cc2520.c @@ -1156,11 +1156,10 @@ static void cc2520_remove(struct spi_device *spi) { struct cc2520_private *priv = spi_get_drvdata(spi); - mutex_destroy(&priv->buffer_mutex); - flush_work(&priv->fifop_irqwork); - + disable_work_sync(&priv->fifop_irqwork); ieee802154_unregister_hw(priv->hw); ieee802154_free_hw(priv->hw); + mutex_destroy(&priv->buffer_mutex); } static const struct spi_device_id cc2520_ids[] = { From bf79662bc85e820ac3b846e2f347da29fbf6ac95 Mon Sep 17 00:00:00 2001 From: Zhiling Zou Date: Sat, 29 Aug 2026 18:07:23 +0800 Subject: [PATCH 0447/1198] ieee802154: 6lowpan: fix NULL dereference in lowpan_newlink TUNSETLINK allows a TUN device to change its link-layer type to ARPHRD_IEEE802154 without initializing ieee802154_ptr. lowpan_newlink() checks only the device type before dereferencing the pointer, so an RTM_NEWLINK request can trigger a NULL pointer dereference. Reject devices without ieee802154_ptr along with devices of the wrong type. Fixes: 51e0e5d8124e ("ieee802154: 6lowpan: remove multiple lowpan per wpan support") Cc: stable@vger.kernel.org Reported-by: Vega Signed-off-by: Zhiling Zou Link: https://lore.kernel.org/0b715da69bd15a86ddc47dad5cf12da648211050.1787997209.git.zhilinz@nebusec.ai Signed-off-by: Stefan Schmidt --- net/ieee802154/6lowpan/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 018929563c6b..6a8d6852cb93 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -150,7 +150,7 @@ static int lowpan_newlink(struct net_device *ldev, wdev = dev_get_by_index(dev_net(ldev), nla_get_u32(tb[IFLA_LINK])); if (!wdev) return -ENODEV; - if (wdev->type != ARPHRD_IEEE802154) { + if (wdev->type != ARPHRD_IEEE802154 || !wdev->ieee802154_ptr) { dev_put(wdev); return -EINVAL; } From 979d5b8de8ed4e1f997aef12da5694b99be7b871 Mon Sep 17 00:00:00 2001 From: David Carlier Date: Thu, 9 Jul 2026 23:18:58 +0100 Subject: [PATCH 0448/1198] ieee802154: hwsim: serialize pib updates to fix double-free hwsim_update_pib() does an unserialized read-swap-free of phy->pib: pib_old = rtnl_dereference(phy->pib); ... rcu_assign_pointer(phy->pib, pib); kfree_rcu(pib_old, rcu); It assumes the RTNL is held, but ->set_channel is not always called under it: the mac802154 scan worker changes channels via drv_set_channel() without the RTNL. Such an update can race an RTNL-held one on the same phy; both read the same pib_old and both kfree_rcu() it, double-freeing the object. With SLUB percpu sheaves batching kfree_rcu(), this surfaces as a KASAN invalid-free in rcu_free_sheaf(). struct hwsim_phy has no lock for pib. Add one and make the swap atomic with rcu_replace_pointer() under it, dropping the misleading rtnl_dereference(). Reported-by: syzbot+60332fd095f8bb2946ad@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=60332fd095f8bb2946ad Fixes: f25da51fdc38 ("ieee802154: hwsim: add replacement for fakelb") Signed-off-by: David Carlier Cc: stable@vger.kernel.org Link: https://lore.kernel.org/20260709221858.158063-1-devnexen@gmail.com Signed-off-by: Stefan Schmidt --- drivers/net/ieee802154/mac802154_hwsim.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c index 6daa0f198b9f..a9bd1555d2dc 100644 --- a/drivers/net/ieee802154/mac802154_hwsim.c +++ b/drivers/net/ieee802154/mac802154_hwsim.c @@ -72,6 +72,8 @@ struct hwsim_phy { struct ieee802154_hw *hw; u32 idx; + /* Serializes phy->pib_updates. */ + spinlock_t pib_lock; struct hwsim_pib __rcu *pib; bool suspended; @@ -102,8 +104,6 @@ static int hwsim_update_pib(struct ieee802154_hw *hw, u8 page, u8 channel, if (!pib) return -ENOMEM; - pib_old = rtnl_dereference(phy->pib); - pib->page = page; pib->channel = channel; pib->filt.short_addr = filt->short_addr; @@ -112,7 +112,10 @@ static int hwsim_update_pib(struct ieee802154_hw *hw, u8 page, u8 channel, pib->filt.pan_coord = filt->pan_coord; pib->filt_level = filt_level; - rcu_assign_pointer(phy->pib, pib); + spin_lock_bh(&phy->pib_lock); + pib_old = rcu_replace_pointer(phy->pib, pib, + lockdep_is_held(&phy->pib_lock)); + spin_unlock_bh(&phy->pib_lock); kfree_rcu(pib_old, rcu); return 0; } @@ -952,6 +955,7 @@ static int hwsim_add_one(struct genl_info *info, struct device *dev, goto err_pib; } + spin_lock_init(&phy->pib_lock); pib->channel = 13; pib->filt.short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST); pib->filt.pan_id = cpu_to_le16(IEEE802154_PANID_BROADCAST); From f695390ea63941a9e412bf1f3afe65ab245fc681 Mon Sep 17 00:00:00 2001 From: Sunil Goutham Date: Fri, 28 Aug 2026 14:49:45 +0530 Subject: [PATCH 0449/1198] octeontx2-af: Fix limiting SRIOV VF count logic When RVU PF0/AF's VFs are SDP instead of LBK, limiting the VF count based on the LBK channel count is incorrect. Apply LBK channel-based VF limits only when the VF device ID matches the LBK RVU AFVF device. Fixes: 9bd6caf33567 ("octeontx2-af: Enable sriov on AF to create VFs") Signed-off-by: Sunil Goutham Signed-off-by: Nitin Shetty J Signed-off-by: David S. Miller --- .../net/ethernet/marvell/octeontx2/af/rvu.c | 33 +++++++++++-------- 1 file changed, 19 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 74c041ab5280..937b085582b5 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -3468,6 +3468,8 @@ int rvu_get_num_lbk_chans(void) return ret; } +#define PCI_DEVID_OCTEONTX2_RVU_AFVF 0xA0F8 + static int rvu_enable_sriov(struct rvu *rvu) { struct pci_dev *pdev = rvu->pdev; @@ -3486,24 +3488,27 @@ static int rvu_enable_sriov(struct rvu *rvu) return 0; pci_read_config_word(pdev, pos + PCI_SRIOV_VF_DID, &rvu->vf_devid); - chans = rvu_get_num_lbk_chans(); - if (chans < 0) - return chans; - vfs = pci_sriov_get_totalvfs(pdev); - - /* Limit VFs in case we have more VFs than LBK channels available. */ - if (vfs > chans) - vfs = chans; - if (!vfs) return 0; - /* LBK channel number 63 is used for switching packets between - * CGX mapped VFs. Hence limit LBK pairs till 62 only. - */ - if (vfs > 62) - vfs = 62; + if (rvu->vf_devid == PCI_DEVID_OCTEONTX2_RVU_AFVF) { + chans = rvu_get_num_lbk_chans(); + if (chans < 0) + return chans; + + /* The last LBK channel is reserved for switching packets between + * CGX mapped VFs. Also, since LBK VFs work in pairs, limit VF + * count to available LBK channels minus 2. + */ + vfs = min(vfs, chans - 2); + + if (vfs <= 0) { + dev_warn(&pdev->dev, + "Skipping SRIOV enablement, not enough LBK channels available\n"); + return 0; + } + } /* Save VFs number for reference in VF interrupts handlers. * Since interrupts might start arriving during SRIOV enablement From 636abbe7a66d80e179011a31754d55001cd44f63 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Wed, 2 Sep 2026 13:23:52 +0900 Subject: [PATCH 0450/1198] ksmbd: fix sparc build with atomic work state Use an unsigned int for the work state so xchg() uses a supported 4-byte operation on sparc. Fixes: d12168084c8c ("ksmbd: safely drain sessions during logoff") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202609021157.8f7Wx34I-lkp@intel.com/ Signed-off-by: Namjae Jeon --- fs/smb/server/ksmbd_work.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/smb/server/ksmbd_work.h b/fs/smb/server/ksmbd_work.h index 5f1d3ebab4fb..0844aa929f55 100644 --- a/fs/smb/server/ksmbd_work.h +++ b/fs/smb/server/ksmbd_work.h @@ -82,7 +82,7 @@ struct ksmbd_work { /* Contiguous SMB2 compression transform owned by this work item. */ void *compress_buf; - unsigned char state; + unsigned int state; /* No response for cancelled request */ bool send_no_response:1; /* Request is encrypted */ From 0e753899627b5e28a9fea8bca98262a6f65a2452 Mon Sep 17 00:00:00 2001 From: Abdifatah Suruur Date: Sat, 29 Aug 2026 18:40:22 +0300 Subject: [PATCH 0451/1198] ksmbd: fix use-after-free in oplock break notification smb2_oplock_break_noti() reads opinfo->conn without any lock and dereferences it after two allocations which may sleep. When the durable handle owning the oplock is disconnected, session_fd_check() clears opinfo->conn and drops its conn reference under ci->m_lock, and the last ksmbd_conn_put() frees the connection. A break triggered by another connection that races with the teardown can then resurrect the freed connection: ksmbd_conn_get() is a plain atomic_inc, and the queued break work later dereferences the stale conn via ksmbd_conn_write(), a use-after-free reachable by any authenticated client holding a durable batch oplock. Thread the caller's inode into the notification path instead of taking a new reference on it. Every caller of oplock_break() already holds a live ksmbd_file (or an explicit ksmbd_inode_lookup_lock() reference, in the parent lease break paths) on the inode that owns the break target's oplock list, so ci cannot be freed during the call, and its lock can be taken without dereferencing opinfo->o_fp, which a concurrent close may free. Select and pin the connection under ci->m_lock, the same lock session_fd_check() and ksmbd_reopen_durable_fd() use to update opinfo->conn, so a concurrent detach either loses the race to the clear or keeps the connection alive until the notification work releases it. Transfer the reference to the work item and release it on allocation failures. Fixes: b003086d7696 ("ksmbd: fix NULL-deref of opinfo->conn in oplock/lease break notifiers") Cc: stable@vger.kernel.org Signed-off-by: Abdifatah Suruur Signed-off-by: Namjae Jeon --- fs/smb/server/oplock.c | 73 +++++++++++++++++++++++++++++++++--------- 1 file changed, 57 insertions(+), 16 deletions(-) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 58af0fddf39f..1b8c3482d1e4 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -924,31 +924,69 @@ static void __smb2_oplock_break_noti(struct work_struct *wk) ksmbd_conn_put(conn); } +/* + * Select and pin the connection used for an oplock break before doing any + * allocations which may sleep. The caller of oplock_break() holds a live + * reference on ci (a file being opened, a file being operated on, or an + * explicit ksmbd_inode_lookup_lock() reference in the parent lease break + * paths), so the inode cannot be freed during the call and its lock is + * reachable without dereferencing opinfo->o_fp, which is not pinned by + * the oplock reference and may be freed by a concurrent close. + * + * opinfo->conn is cleared under ci->m_lock by session_fd_check() when the + * durable handle owning the oplock is disconnected, reassigned by + * ksmbd_reopen_durable_fd() under the same lock, and the last + * ksmbd_conn_put() of the old connection frees it. Holding the read lock + * excludes both writers, so the connection cannot be freed while it is + * selected. + */ +static struct ksmbd_conn *smb2_oplock_break_conn_get(struct oplock_info *opinfo, + struct ksmbd_inode *ci) +{ + struct ksmbd_conn *conn; + + down_read(&ci->m_lock); + conn = READ_ONCE(opinfo->conn); + if (conn && !ksmbd_conn_releasing(conn)) + conn = ksmbd_conn_get(conn); + else + conn = NULL; + up_read(&ci->m_lock); + + return conn; +} + /** * smb2_oplock_break_noti() - send smb2 exclusive/batch to level2 oplock * break command from server to client * @opinfo: oplock info object + * @ci: inode owning the break target's oplock list, pinned by + * the caller * * Return: 0 on success, otherwise error */ -static int smb2_oplock_break_noti(struct oplock_info *opinfo) +static int smb2_oplock_break_noti(struct oplock_info *opinfo, + struct ksmbd_inode *ci) { struct ksmbd_conn *conn; struct oplock_break_info *br_info; int ret = 0; struct ksmbd_work *work; - conn = READ_ONCE(opinfo->conn); + conn = smb2_oplock_break_conn_get(opinfo, ci); if (!conn) return ksmbd_invalidate_durable_fd(opinfo->fid); work = ksmbd_alloc_work_struct(); - if (!work) + if (!work) { + ksmbd_conn_put(conn); return -ENOMEM; + } br_info = kmalloc_obj(struct oplock_break_info, KSMBD_DEFAULT_GFP); if (!br_info) { ksmbd_free_work_struct(work); + ksmbd_conn_put(conn); return -ENOMEM; } @@ -957,7 +995,8 @@ static int smb2_oplock_break_noti(struct oplock_info *opinfo) br_info->open_trunc = opinfo->open_trunc; work->request_buf = (char *)br_info; - work->conn = ksmbd_conn_get(conn); + /* Transfer the reference acquired by smb2_oplock_break_conn_get(). */ + work->conn = conn; work->sess = opinfo->sess; ksmbd_conn_r_count_inc(conn); @@ -1154,9 +1193,9 @@ static void wait_lease_breaking(struct oplock_info *opinfo) } } -static int oplock_break(struct oplock_info *brk_opinfo, int req_op_level, - struct ksmbd_work *in_work, bool share_break, - bool sync_lease_break) +static int oplock_break(struct oplock_info *brk_opinfo, struct ksmbd_inode *ci, + int req_op_level, struct ksmbd_work *in_work, + bool share_break, bool sync_lease_break) { int err = 0; bool sent_interim = false; @@ -1298,7 +1337,7 @@ static int oplock_break(struct oplock_info *brk_opinfo, int req_op_level, } } - err = smb2_oplock_break_noti(brk_opinfo); + err = smb2_oplock_break_noti(brk_opinfo, ci); ksmbd_debug(OPLOCK, "oplock granted = %d\n", brk_opinfo->level); if (brk_opinfo->op_state == OPLOCK_CLOSING) @@ -1326,13 +1365,14 @@ static int oplock_break_add(struct list_head *head, struct oplock_info *opinfo) return 0; } -static void oplock_break_drain_none(struct list_head *head) +static void oplock_break_drain_none(struct list_head *head, + struct ksmbd_inode *ci) { struct oplock_break_entry *ent, *tmp; list_for_each_entry_safe(ent, tmp, head, list) { - oplock_break(ent->opinfo, SMB2_OPLOCK_LEVEL_NONE, NULL, false, - false); + oplock_break(ent->opinfo, ci, SMB2_OPLOCK_LEVEL_NONE, NULL, + false, false); list_del(&ent->list); opinfo_put(ent->opinfo); kfree(ent); @@ -1481,7 +1521,7 @@ void smb_send_parent_lease_break_noti(struct ksmbd_file *fp, } up_read(&p_ci->m_lock); - oplock_break_drain_none(&brk_list); + oplock_break_drain_none(&brk_list, p_ci); ksmbd_inode_put(p_ci); } @@ -1525,7 +1565,7 @@ void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp) } up_read(&p_ci->m_lock); - oplock_break_drain_none(&brk_list); + oplock_break_drain_none(&brk_list, p_ci); ksmbd_inode_put(p_ci); } @@ -1665,7 +1705,7 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, prev_durable_detached = prev_op_snapshot.durable_detached; prev_fid = prev_op_snapshot.fid; - err = oplock_break(prev_opinfo, break_level, work, + err = oplock_break(prev_opinfo, ci, break_level, work, share_ret < 0 && prev_opinfo->is_lease, false); if (prev_durable_detached || (prev_durable_open && err == -ENOENT)) ksmbd_invalidate_durable_fd(prev_fid); @@ -1771,7 +1811,8 @@ static bool smb_break_all_write_oplock(struct ksmbd_work *work, } brk_opinfo->open_trunc = is_trunc; - oplock_break(brk_opinfo, SMB2_OPLOCK_LEVEL_II, work, false, false); + oplock_break(brk_opinfo, fp->f_ci, SMB2_OPLOCK_LEVEL_II, work, false, + false); sent_break = true; opinfo_put(brk_opinfo); @@ -1863,7 +1904,7 @@ static void __smb_break_all_levII_oplock(struct ksmbd_work *work, brk_op->op_state = OPLOCK_STATE_NONE; spin_unlock(&brk_op->state_lock); } else { - oplock_break(brk_op, + oplock_break(brk_op, ci, brk_op->is_lease && !is_trunc ? SMB2_OPLOCK_LEVEL_II : SMB2_OPLOCK_LEVEL_NONE, send_interim && !sent_interim ? work : NULL, From 0480cee8cc3cc906124d398a9779eda144de6b41 Mon Sep 17 00:00:00 2001 From: Alon Shakevsky Date: Tue, 1 Sep 2026 00:05:31 +0000 Subject: [PATCH 0452/1198] ksmbd: validate COPYCHUNK source and target ranges ksmbd_vfs_copy_file_ranges() rejects negative source offsets in the copy loop, but it does not validate target offsets. It also calculates lock and overlap endpoints before ensuring that either range fits within MAX_LFS_FILESIZE. When the target is an alternate data stream, the buffered path passes a negative target offset to ksmbd_vfs_stream_write(). Let n be Length and let -d be TargetOffset, where 0 < d < n <= XATTR_SIZE_MAX. For an empty stream, the writer allocates n - d bytes, then copies n bytes starting d bytes before the allocation. An authenticated SMB client can control d and the source data, overwrite kernel heap memory, and crash the host. Validate both ranges before lock, overlap, or I/O calculations. Fixes: 8482150a0743 ("ksmbd: support copychunk for alternate data streams") Assisted-by: Antiproof:GPT-5.6-Sol Signed-off-by: Alon Shakevsky Signed-off-by: Namjae Jeon --- fs/smb/server/vfs.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index d2b524f79cbe..c2c9aaa5de1b 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -2007,6 +2007,11 @@ static ssize_t ksmbd_vfs_copy_file_range_buffered(struct ksmbd_work *work, return ret; } +static bool ksmbd_vfs_copy_range_valid(loff_t offset, size_t len) +{ + return offset >= 0 && (loff_t)len <= MAX_LFS_FILESIZE - offset; +} + int ksmbd_vfs_copy_file_ranges(struct ksmbd_work *work, struct ksmbd_file *src_fp, struct ksmbd_file *dst_fp, @@ -2042,6 +2047,10 @@ int ksmbd_vfs_copy_file_ranges(struct ksmbd_work *work, dst_off = le64_to_cpu(chunks[i].TargetOffset); len = le32_to_cpu(chunks[i].Length); + if (!ksmbd_vfs_copy_range_valid(src_off, len) || + !ksmbd_vfs_copy_range_valid(dst_off, len)) + return -E2BIG; + if (check_lock_range(src_fp->filp, src_off, src_off + len - 1, READ)) return -EAGAIN; @@ -2134,7 +2143,8 @@ int ksmbd_vfs_copy_file_ranges(struct ksmbd_work *work, len = le32_to_cpu(chunks[i].Length); copy_len = len; - if (src_off < 0) + if (!ksmbd_vfs_copy_range_valid(src_off, len) || + !ksmbd_vfs_copy_range_valid(dst_off, len)) return -E2BIG; if (src_off > src_file_size || len > src_file_size - src_off) { From b5ec6c462aab1062cf5d1e667ba7c6442f737055 Mon Sep 17 00:00:00 2001 From: "Cen Zhang (Microsoft Security FORGE Labs)" Date: Tue, 1 Sep 2026 14:21:36 -0400 Subject: [PATCH 0453/1198] ksmbd: fix tree connection use-after-free in smb2_tree_connect() ksmbd_tree_conn_connect() publishes a new tree connection in sess->tree_conns with a single reference and returns its pointer to smb2_tree_connect(). The handler continues to initialize the object and build the response after publication. A concurrent session logoff can erase the connection and drop that reference, freeing the object while the handler still uses it. BUG: KASAN: slab-use-after-free in smb2_tree_connect+0xe3d/0xf90 smb2_tree_connect (fs/smb/server/smb2pdu.c:2872) handle_ksmbd_work process_one_work worker_thread kthread After xa_store() succeeds, take a second reference before releasing tree_conns_lock. The original reference belongs to the xarray entry and the second belongs to the creating smb2_tree_connect() handler. Keep the references balanced in every path: - On normal exit or an error after publication, smb2_tree_connect() drops its creator reference. Error cleanup also calls ksmbd_tree_conn_disconnect(), which drops the xarray reference only if it removes the exact entry. - SMB2 TREE_DISCONNECT uses the same helper to remove the entry and drop its xarray reference. The request's existing lookup reference remains owned by the request and is released by the existing cleanup. - Session LOGOFF removes each entry and drops its xarray reference. If it wins the race, later cleanup sees that the entry is gone and does not drop that reference again. To enforce this ownership, claim the disconnected state and erase the exact entry atomically under tree_conns_lock. This guarantees one drop for the xarray reference and one drop by each in-flight user, regardless of which teardown path wins. If logoff removes the entry before initialization completes, fail the connect instead of marking the detached object TREE_CONNECTED. Fixes: 33b235a6e6eb ("ksmbd: fix race condition between tree conn lookup and disconnect") Reported-by: Xiang Mei (Microsoft) Cc: AutonomousCodeSecurity@microsoft.com Cc: stable@vger.kernel.org Signed-off-by: Cen Zhang (Microsoft Security FORGE Labs) Signed-off-by: Namjae Jeon --- fs/smb/server/mgmt/tree_connect.c | 8 ++++++++ fs/smb/server/smb2pdu.c | 28 +++++++++++++--------------- 2 files changed, 21 insertions(+), 15 deletions(-) diff --git a/fs/smb/server/mgmt/tree_connect.c b/fs/smb/server/mgmt/tree_connect.c index 5f63e236267a..dd1db3554cae 100644 --- a/fs/smb/server/mgmt/tree_connect.c +++ b/fs/smb/server/mgmt/tree_connect.c @@ -82,6 +82,8 @@ ksmbd_tree_conn_connect(struct ksmbd_work *work, const char *share_name) down_write(&sess->tree_conns_lock); ret = xa_err(xa_store(&sess->tree_conns, tree_conn->id, tree_conn, KSMBD_DEFAULT_GFP)); + if (!ret) + atomic_inc(&tree_conn->refcount); up_write(&sess->tree_conns_lock); if (ret) { status.ret = -ENOMEM; @@ -129,6 +131,12 @@ int ksmbd_tree_conn_disconnect(struct ksmbd_session *sess, struct ksmbd_tree_connect *tree_conn) { down_write(&sess->tree_conns_lock); + if (tree_conn->t_state == TREE_DISCONNECTED || + xa_load(&sess->tree_conns, tree_conn->id) != tree_conn) { + up_write(&sess->tree_conns_lock); + return -ENOENT; + } + tree_conn->t_state = TREE_DISCONNECTED; xa_erase(&sess->tree_conns, tree_conn->id); up_write(&sess->tree_conns_lock); diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index d656832d82ef..0ecc52fde69c 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -2790,6 +2790,7 @@ int smb2_tree_connect(struct ksmbd_work *work) struct ksmbd_session *sess = work->sess; char *treename = NULL, *name = NULL; struct ksmbd_tree_conn_status status; + struct ksmbd_tree_connect *tree_conn = NULL; struct ksmbd_share_config *share = NULL; int rc = -EINVAL; @@ -2817,6 +2818,7 @@ int smb2_tree_connect(struct ksmbd_work *work) status = ksmbd_tree_conn_connect(work, name); if (status.ret == KSMBD_TREE_CONN_STATUS_OK) { + tree_conn = status.tree_conn; rsp->hdr.Id.SyncId.TreeId = cpu_to_le32(status.tree_conn->id); share = status.tree_conn->share_conf; @@ -2860,8 +2862,15 @@ int smb2_tree_connect(struct ksmbd_work *work) status.tree_conn->posix_extensions = true; down_write(&sess->tree_conns_lock); - status.tree_conn->t_state = TREE_CONNECTED; + if (status.tree_conn->t_state == TREE_DISCONNECTED) { + status.ret = KSMBD_TREE_CONN_STATUS_ERROR; + share = NULL; + } else { + status.tree_conn->t_state = TREE_CONNECTED; + } up_write(&sess->tree_conns_lock); + if (status.ret != KSMBD_TREE_CONN_STATUS_OK) + goto out_err1; rsp->StructureSize = cpu_to_le16(16); out_err1: /* @@ -2888,9 +2897,6 @@ int smb2_tree_connect(struct ksmbd_work *work) rc = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_tree_connect_rsp)); if (rc) { if (status.ret == KSMBD_TREE_CONN_STATUS_OK) { - down_write(&sess->tree_conns_lock); - status.tree_conn->t_state = TREE_DISCONNECTED; - up_write(&sess->tree_conns_lock); ksmbd_tree_conn_disconnect(sess, status.tree_conn); status.tree_conn = NULL; } @@ -2931,6 +2937,9 @@ int smb2_tree_connect(struct ksmbd_work *work) if (status.ret != KSMBD_TREE_CONN_STATUS_OK) smb2_set_err_rsp(work); + if (tree_conn) + ksmbd_tree_connect_put(tree_conn); + return rc; } @@ -3034,17 +3043,6 @@ int smb2_tree_disconnect(struct ksmbd_work *work) ksmbd_close_tree_conn_fds(work); - down_write(&sess->tree_conns_lock); - if (tcon->t_state == TREE_DISCONNECTED) { - up_write(&sess->tree_conns_lock); - rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; - err = -ENOENT; - goto err_out; - } - - tcon->t_state = TREE_DISCONNECTED; - up_write(&sess->tree_conns_lock); - err = ksmbd_tree_conn_disconnect(sess, tcon); if (err) { rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; From 0433632bbe8d279e978f3f85212f36281a89946c Mon Sep 17 00:00:00 2001 From: John Ogness Date: Tue, 1 Sep 2026 11:37:42 +0206 Subject: [PATCH 0454/1198] printk/nbcon: Flush nbcon_irq_work in nbcon_free() Ensure any pending nbcon_irq_work is flushed before allowing the console to be recycled. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Link: https://patch.msgid.link/20260901093245.344455-2-john.ogness@linutronix.de Signed-off-by: Petr Mladek --- kernel/printk/nbcon.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/printk/nbcon.c b/kernel/printk/nbcon.c index 4b03b019cd5e..354f274d8a42 100644 --- a/kernel/printk/nbcon.c +++ b/kernel/printk/nbcon.c @@ -1837,6 +1837,8 @@ void nbcon_free(struct console *con) /* Synchronize the kthread stop. */ lockdep_assert_console_list_lock_held(); + irq_work_sync(&con->irq_work); + if (printk_kthreads_running) { nbcon_kthread_stop(con); From 560f4deda32785e260056200f8bb911c475c5b88 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Tue, 1 Sep 2026 11:37:43 +0206 Subject: [PATCH 0455/1198] printk/nbcon: Change nbcon_irq_work to IRQ_WORK_LAZY Change the nbcon_irq_work to be IRQ_WORK_LAZY, thus not raising an IRQ upon irq_work queuing. The irq_work is then handled on the next kernel tick. This additional delay is acceptable because nbcon_irq_work is only responsible for non-emergency deferred printing, which is delayed anyway. This has the benefit of not needing to raise an IRQ for each printk() call. On a side note, the Tegra20 and Tegra30 platforms can hang if an irq_work IRQ is raised while entering cpuidle states. This problem was reproducible by calling printk() while entering cpuidle. So this change also provides a workaround for these platforms (as long as they are not running tickless). Link: https://lore.kernel.org/lkml/f3757a75-0ba1-4558-bf57-f19ab7e59a4c@nvidia.com Fixes: 76f258bf3f2a ("printk: nbcon: Introduce printer kthreads") Signed-off-by: John Ogness Reviewed-by: Sebastian Andrzej Siewior Reviewed-by: Petr Mladek Tested-by: Jon Hunter Link: https://patch.msgid.link/20260901093245.344455-3-john.ogness@linutronix.de Signed-off-by: Petr Mladek --- kernel/printk/nbcon.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/printk/nbcon.c b/kernel/printk/nbcon.c index 354f274d8a42..c8502fc4f4e5 100644 --- a/kernel/printk/nbcon.c +++ b/kernel/printk/nbcon.c @@ -1782,7 +1782,7 @@ bool nbcon_alloc(struct console *con) } rcuwait_init(&con->rcuwait); - init_irq_work(&con->irq_work, nbcon_irq_work); + con->irq_work = IRQ_WORK_INIT_LAZY(nbcon_irq_work); atomic_long_set(&ACCESS_PRIVATE(con, nbcon_prev_seq), -1UL); nbcon_state_set(con, &state); From a61c6ae1dae2611082b831b4aaa780878099c012 Mon Sep 17 00:00:00 2001 From: Max Kellermann Date: Mon, 24 Aug 2026 18:47:07 +0200 Subject: [PATCH 0456/1198] ceph: lock mutex in ceph_mds_check_access() MDS session OPEN handling replaces mdsc->s_cap_auths under mdsc->mutex, freeing the previous array and its strings. ceph_mds_check_access() traverses this array without holding the mutex. A concurrent session reopen can therefore free the array while it is being inspected, resulting in a use-after-free like this: Unable to handle kernel paging request at virtual address 003aaad64b2c8bb9 [...] Internal error: Oops: 0000000096000004 [#1] SMP Modules linked in: CPU: 56 UID: 2953037534 PID: 1253231 Comm: php-cgi8.4 Not tainted 6.18.45-i2-ampere #1146 NONE [..] pc : ceph_mds_check_access+0xd4/0x550 lr : ceph_mds_check_access+0xc8/0x550 [...] Call trace: ceph_mds_check_access+0xd4/0x550 (P) ceph_atomic_open+0x138/0xbe8 path_openat+0xa24/0xfa8 do_filp_open+0x94/0x158 do_sys_openat2+0x88/0xf8 Cc: stable@vger.kernel.org Fixes: 596afb0b8933 ("ceph: add ceph_mds_check_access() helper") Signed-off-by: Max Kellermann Reviewed-by: Alex Markuze Signed-off-by: Ilya Dryomov --- fs/ceph/mds_client.c | 4 ++++ fs/ceph/mds_client.h | 1 + 2 files changed, 5 insertions(+) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index a091f77cedaf..c4a35547dcc6 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -6600,11 +6600,13 @@ int ceph_mds_check_access(struct ceph_mds_client *mdsc, char *tpath, int mask) doutc(cl, "tpath '%s', mask %d, caller_uid %d, caller_gid %d\n", tpath, mask, caller_uid, caller_gid); + mutex_lock(&mdsc->mutex); for (i = 0; i < mdsc->s_cap_auths_num; i++) { struct ceph_mds_cap_auth *s = &mdsc->s_cap_auths[i]; err = ceph_mds_auth_match(mdsc, s, cred, tpath); if (err < 0) { + mutex_unlock(&mdsc->mutex); put_cred(cred); return err; } else if (err > 0) { @@ -6626,6 +6628,7 @@ int ceph_mds_check_access(struct ceph_mds_client *mdsc, char *tpath, int mask) doutc(cl, "root_squash_perms %d, rw_perms_s %p\n", root_squash_perms, rw_perms_s); if (root_squash_perms && rw_perms_s == NULL) { + mutex_unlock(&mdsc->mutex); doutc(cl, "access allowed\n"); return 0; } @@ -6640,6 +6643,7 @@ int ceph_mds_check_access(struct ceph_mds_client *mdsc, char *tpath, int mask) !!(mask & MAY_READ), !!(mask & MAY_WRITE)); } doutc(cl, "access denied\n"); + mutex_unlock(&mdsc->mutex); return -EACCES; } diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 3c62e3c3530b..e7a262c9c2ab 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -604,6 +604,7 @@ struct ceph_mds_client { struct rw_semaphore pool_perm_rwsem; struct rb_root pool_perm_tree; + /* protected by mutex */ u32 s_cap_auths_num; struct ceph_mds_cap_auth *s_cap_auths; From f75987e543c243e19f49fe32ce870b2e24ab8c23 Mon Sep 17 00:00:00 2001 From: Tal Zussman Date: Tue, 25 Aug 2026 11:41:38 -0400 Subject: [PATCH 0457/1198] libceph: remove pinning assertion in ceph_msg_data_iter_next() ceph_msg_data_iter_next() gets a page reference from iov_iter_get_pages2() only to immediately drop it, asserting that the page is pinned some other way. The assertion is the last caller of PageWriteback() in the tree, blocking removal of the PG_writeback page flag accessors. Remove the assertion, as it is a CONFIG_DEBUG_VM-only check of an assumption the FIXME comment already documents. Converting to iov_iter_extract_pages() instead was considered, but the messenger never releases what it extracts, so it would still rely entirely on the caller holding the pages. That would be just as much of an abuse of the API, so leave it as-is for now. Signed-off-by: Tal Zussman Reviewed-by: Christoph Hellwig Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- net/ceph/messenger.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 9c1b6cf8c36f..212e7797f9e4 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1003,7 +1003,6 @@ static struct page *ceph_msg_data_iter_next(struct ceph_msg_data_cursor *cursor, * we'll get an iov_iter_get_pages2 variant that doesn't take * page refs. Until then, just put the page ref. */ - VM_BUG_ON_PAGE(!PageWriteback(page) && page_count(page) < 2, page); put_page(page); *length = min_t(size_t, len, cursor->resid); From dc173b37415e8f738fc4de477490056b479ddc9f Mon Sep 17 00:00:00 2001 From: Alex Markuze Date: Thu, 27 Aug 2026 15:16:21 +0000 Subject: [PATCH 0458/1198] ceph: apply nearfull_sync option on remount ceph_parse_mount_param() stores nearfull_sync / nonearfull_sync on the temporary fs_context options, but ceph_reconfigure_fc() never copied CEPH_MOUNT_OPT_NEARFULL_SYNC onto the live mount. Remount therefore succeeded while writes and /proc/mounts kept the original-mount flag. Apply the flag the same way as ASYNC_DIROPS and SPARSEREAD so remount can enable or disable NEARFULL IOCB_DSYNC promotion. Fixes: c7a12c20bfba ("ceph: make nearfull sync writes opt-in") Signed-off-by: Alex Markuze Reviewed-by: Xiubo Li Signed-off-by: Ilya Dryomov --- fs/ceph/super.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 15edea30dc8b..72935f665f11 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -1420,6 +1420,11 @@ static int ceph_reconfigure_fc(struct fs_context *fc) else ceph_clear_mount_opt(fsc, SPARSEREAD); + if (fsopt->flags & CEPH_MOUNT_OPT_NEARFULL_SYNC) + ceph_set_mount_opt(fsc, NEARFULL_SYNC); + else + ceph_clear_mount_opt(fsc, NEARFULL_SYNC); + if (strcmp_null(fsc->mount_options->mon_addr, fsopt->mon_addr)) { kfree(fsc->mount_options->mon_addr); fsc->mount_options->mon_addr = fsopt->mon_addr; From 544d85de4dc22c01badfd8cefa59829ce35c4858 Mon Sep 17 00:00:00 2001 From: Chris Lew Date: Thu, 27 Aug 2026 17:48:46 +0530 Subject: [PATCH 0459/1198] net: qrtr: Send HELLO message on endpoint register HELLO is currently handled entirely by the name server (NS): it is sent once as a broadcast when the NS initializes, and again as a reply whenever the NS receives an inbound HELLO from a remote. Some remote QRTR endpoints (e.g. an external WLAN chipset attached over MHI) operate in a slave role: they only ever send a HELLO in response to one they receive, and never initiate. Since the host cannot tell in advance which remotes behave this way, if the host also only replies, both sides wait on the other to speak first and no HELLO is ever exchanged, stalling further communication. To fix this: - Transfer HELLO handshake ownership to the core layer. A HELLO is now sent once, per endpoint, at registration time. - Schedule a delayed work item on endpoint registration to send a HELLO once the name server is bound. The work reschedules itself with a 100ms backoff if the name server socket is not yet bound or if allocating the control packet fails, so a transient startup condition does not abandon the handshake permanently. - Enforce HELLO-first ordering by dropping non-HELLO packets and returning -EAGAIN until the HELLO is confirmed sent, using bool hello_sent guarded by ep_lock to make the gate check atomic with xmit(). - Skip nodes with nid == QRTR_EP_NID_AUTO in bcast_enqueue(), to avoid broadcasting control packets with QRTR_EP_NID_AUTO as the destination node ID. - Remove say_hello() from the name server's ctrl_cmd_hello() handler and from qrtr_ns_init(); the core layer is now the sole sender of the outbound HELLO. This removes the NS's reply-on-receive behaviour without a replacement. Signed-off-by: Chris Lew Co-developed-by: Deepak Kumar Singh Signed-off-by: Deepak Kumar Singh Co-developed-by: Pranav Mahesh Phansalkar Signed-off-by: Pranav Mahesh Phansalkar Signed-off-by: David S. Miller --- net/qrtr/af_qrtr.c | 66 ++++++++++++++++++++++++++++++++++++++++++++-- net/qrtr/ns.c | 35 +----------------------- 2 files changed, 65 insertions(+), 36 deletions(-) diff --git a/net/qrtr/af_qrtr.c b/net/qrtr/af_qrtr.c index a30fa56e6aa3..78347c937af7 100644 --- a/net/qrtr/af_qrtr.c +++ b/net/qrtr/af_qrtr.c @@ -9,6 +9,7 @@ #include /* For TIOCINQ/OUTQ */ #include #include +#include #include @@ -120,8 +121,10 @@ static DEFINE_XARRAY_ALLOC(qrtr_ports); * @nid: node id * @qrtr_tx_flow: xarray of qrtr_tx_flow, keyed by node << 32 | port * @qrtr_tx_lock: lock for qrtr_tx_flow inserts + * @hello_sent: hello packet send successful * @rx_queue: receive queue * @item: list item for broadcast list + * @say_hello: delayed work for sending hello packet */ struct qrtr_node { struct mutex ep_lock; @@ -132,8 +135,11 @@ struct qrtr_node { struct xarray qrtr_tx_flow; struct mutex qrtr_tx_lock; /* for qrtr_tx_flow */ + bool hello_sent; + struct sk_buff_head rx_queue; struct list_head item; + struct delayed_work say_hello; }; /** @@ -187,6 +193,8 @@ static void __qrtr_node_release(struct kref *kref) list_del(&node->item); mutex_unlock(&qrtr_node_lock); + cancel_delayed_work_sync(&node->say_hello); + skb_queue_purge(&node->rx_queue); /* Free tx flow counters */ @@ -341,6 +349,14 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, size_t len = skb->len; int rc, confirm_rx; + mutex_lock(&node->ep_lock); + if (!node->hello_sent && type != QRTR_TYPE_HELLO) { + mutex_unlock(&node->ep_lock); + kfree_skb(skb); + return -EAGAIN; + } + mutex_unlock(&node->ep_lock); + confirm_rx = qrtr_tx_wait(node, to->sq_node, to->sq_port, type); if (confirm_rx < 0) { kfree_skb(skb); @@ -353,7 +369,7 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, hdr->src_node_id = cpu_to_le32(from->sq_node); hdr->src_port_id = cpu_to_le32(from->sq_port); if (to->sq_port == QRTR_PORT_CTRL) { - hdr->dst_node_id = cpu_to_le32(node->nid); + hdr->dst_node_id = cpu_to_le32(READ_ONCE(node->nid)); hdr->dst_port_id = cpu_to_le32(QRTR_PORT_CTRL); } else { hdr->dst_node_id = cpu_to_le32(to->sq_node); @@ -372,6 +388,8 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, rc = node->ep->xmit(node->ep, skb); else kfree_skb(skb); + if (!rc && type == QRTR_TYPE_HELLO) + node->hello_sent = true; mutex_unlock(&node->ep_lock); } /* Need to ensure that a subsequent message carries the otherwise lost @@ -379,6 +397,9 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, if (rc && confirm_rx) qrtr_tx_flow_failed(node, to->sq_node, to->sq_port); + if (rc == -EAGAIN && type == QRTR_TYPE_HELLO) + schedule_delayed_work(&node->say_hello, msecs_to_jiffies(100)); + return rc; } @@ -416,7 +437,7 @@ static void qrtr_node_assign(struct qrtr_node *node, unsigned int nid) spin_lock_irqsave(&qrtr_nodes_lock, flags); radix_tree_insert(&qrtr_nodes, nid, node); if (node->nid == QRTR_EP_NID_AUTO) - node->nid = nid; + WRITE_ONCE(node->nid, nid); spin_unlock_irqrestore(&qrtr_nodes_lock, flags); } @@ -570,6 +591,38 @@ static struct sk_buff *qrtr_alloc_ctrl_packet(struct qrtr_ctrl_pkt **pkt, return skb; } +static void qrtr_hello_work(struct work_struct *work) +{ + struct sockaddr_qrtr from = {AF_QIPCRTR, 0, QRTR_PORT_CTRL}; + struct sockaddr_qrtr to = {AF_QIPCRTR, 0, QRTR_PORT_CTRL}; + struct qrtr_ctrl_pkt *pkt; + struct qrtr_node *node; + struct qrtr_sock *ctrl; + struct sk_buff *skb; + + node = container_of(to_delayed_work(work), struct qrtr_node, say_hello); + + /* NS must be bound before we can send; retry with backoff if not ready */ + ctrl = qrtr_port_lookup(QRTR_PORT_CTRL); + if (!ctrl) { + schedule_delayed_work(&node->say_hello, msecs_to_jiffies(100)); + return; + } + + skb = qrtr_alloc_ctrl_packet(&pkt, GFP_KERNEL); + if (!skb) { + qrtr_port_put(ctrl); + schedule_delayed_work(&node->say_hello, msecs_to_jiffies(100)); + return; + } + + pkt->cmd = cpu_to_le32(QRTR_TYPE_HELLO); + from.sq_node = qrtr_local_nid; + to.sq_node = node->nid; + qrtr_node_enqueue(node, skb, QRTR_TYPE_HELLO, &from, &to); + qrtr_port_put(ctrl); +} + /** * qrtr_endpoint_register() - register a new endpoint * @ep: endpoint to register @@ -595,6 +648,9 @@ int qrtr_endpoint_register(struct qrtr_endpoint *ep, unsigned int nid) node->nid = QRTR_EP_NID_AUTO; node->ep = ep; + node->hello_sent = false; + INIT_DELAYED_WORK(&node->say_hello, qrtr_hello_work); + xa_init(&node->qrtr_tx_flow); mutex_init(&node->qrtr_tx_lock); @@ -605,6 +661,9 @@ int qrtr_endpoint_register(struct qrtr_endpoint *ep, unsigned int nid) mutex_unlock(&qrtr_node_lock); ep->node = node; + /* Initiate HELLO handshake from the core layer */ + schedule_delayed_work(&node->say_hello, 0); + return 0; } EXPORT_SYMBOL_GPL(qrtr_endpoint_register); @@ -879,6 +938,9 @@ static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb, mutex_lock(&qrtr_node_lock); list_for_each_entry(node, &qrtr_all_nodes, item) { + /* Skip nodes with no assigned node ID yet. */ + if (READ_ONCE(node->nid) == QRTR_EP_NID_AUTO) + continue; skbn = pskb_copy(skb, GFP_KERNEL); if (!skbn) break; diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index c5e7e01db249..bcb090ee79d4 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -212,6 +212,7 @@ static void lookup_notify(struct sockaddr_qrtr *to, struct qrtr_server *srv, pr_err("failed to send lookup notification\n"); } +/* Announce the list of servers registered on the local node */ static int announce_servers(struct sockaddr_qrtr *sq) { struct qrtr_server *srv; @@ -326,38 +327,8 @@ static int server_del(struct qrtr_node *node, unsigned int port, bool bcast) return 0; } -static int say_hello(struct sockaddr_qrtr *dest) -{ - struct qrtr_ctrl_pkt pkt; - struct msghdr msg = { }; - struct kvec iv; - int ret; - - iv.iov_base = &pkt; - iv.iov_len = sizeof(pkt); - - memset(&pkt, 0, sizeof(pkt)); - pkt.cmd = cpu_to_le32(QRTR_TYPE_HELLO); - - msg.msg_name = (struct sockaddr *)dest; - msg.msg_namelen = sizeof(*dest); - - ret = kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt)); - if (ret < 0) - pr_err("failed to send hello msg\n"); - - return ret; -} - -/* Announce the list of servers registered on the local node */ static int ctrl_cmd_hello(struct sockaddr_qrtr *sq) { - int ret; - - ret = say_hello(sq); - if (ret < 0) - return ret; - return announce_servers(sq); } @@ -774,10 +745,6 @@ int qrtr_ns_init(void) qrtr_ns.bcast_sq.sq_node = QRTR_NODE_BCAST; qrtr_ns.bcast_sq.sq_port = QRTR_PORT_CTRL; - ret = say_hello(&qrtr_ns.bcast_sq); - if (ret < 0) - goto err_wq; - /* As the qrtr ns socket owner and creator is the same module, we have * to decrease the qrtr module reference count to guarantee that it * remains zero after the ns socket is created, otherwise, executing From 355b6558dd7be049aff4f0d438b0128f91a982eb Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Sun, 30 Aug 2026 04:15:05 -0700 Subject: [PATCH 0460/1198] platform/x86: x86-android-tablets: fix Arizona GPIO swnode references MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The standalone arizona_gpiochip_node was created when gpiolib supported matching a software node name against the GPIO chip label ("arizona"). Later, gpiolib replaced name matching with firmware node identity mapping (and eventually dropped the fallback mechanism), causing GPIO lookups on unattached software nodes to fail. In gpio-arizona, the GPIO chip inherits the firmware node of the parent codec device. Fix the lookups by pointing the GPIO property entries directly to the codec device software node (which is attached to the parent device) and dropping the obsolete arizona_gpiochip_node. Fixes: 611fd6cfe139 ("gpio: swnode: remove deprecated lookup mechanism") Assisted-by: LLM Signed-off-by: Dmitry Torokhov Tested-by: Hans de Goede # Yoga tab 2 1380, yt3 Reviewed-by: Hans de Goede Reviewed-by: Andy Shevchenko Reviewed-by: Linus Walleij Link: https://patch.msgid.link/20260830-x86-android-lenovo-swnode-v1-1-066a91acb4ba@gmail.com Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen --- .../platform/x86/x86-android-tablets/lenovo.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/drivers/platform/x86/x86-android-tablets/lenovo.c b/drivers/platform/x86/x86-android-tablets/lenovo.c index 8d825e0b4661..c34f62bdf8f9 100644 --- a/drivers/platform/x86/x86-android-tablets/lenovo.c +++ b/drivers/platform/x86/x86-android-tablets/lenovo.c @@ -61,10 +61,6 @@ static struct lp855x_platform_data lenovo_lp8557_reg_only_pdata = { .initial_brightness = 128, }; -static const struct software_node arizona_gpiochip_node = { - .name = "arizona", -}; - static const struct software_node crystalcove_gpiochip_node = { .name = "gpio_crystalcove", }; @@ -416,15 +412,17 @@ static const struct platform_device_info lenovo_yoga_tab2_830_1050_pdevs[] __ini #define LENOVO_YOGA_TAB2_830_1050_CODEC_NAME "spi-10WM5102:00" +static const struct software_node lenovo_yoga_tab2_830_1050_wm5102; + static const struct property_entry lenovo_yoga_tab2_830_1050_wm1502_props[] = { PROPERTY_ENTRY_GPIO("reset-gpios", &crystalcove_gpiochip_node, 3, GPIO_ACTIVE_HIGH), PROPERTY_ENTRY_GPIO("wlf,ldoena-gpios", &baytrail_gpiochip_nodes[1], 23, GPIO_ACTIVE_HIGH), PROPERTY_ENTRY_GPIO("wlf,spkvdd-ena-gpios", - &arizona_gpiochip_node, 2, GPIO_ACTIVE_HIGH), + &lenovo_yoga_tab2_830_1050_wm5102, 2, GPIO_ACTIVE_HIGH), PROPERTY_ENTRY_GPIO("wlf,micd-pol-gpios", - &arizona_gpiochip_node, 4, GPIO_ACTIVE_LOW), + &lenovo_yoga_tab2_830_1050_wm5102, 4, GPIO_ACTIVE_LOW), { } }; @@ -434,7 +432,6 @@ static const struct software_node lenovo_yoga_tab2_830_1050_wm5102 = { static const struct software_node *lenovo_yoga_tab2_830_1050_swnodes[] = { &crystalcove_gpiochip_node, - &arizona_gpiochip_node, &lenovo_yoga_tab2_830_1050_wm5102, &generic_lipo_hv_4v35_battery_node, NULL @@ -985,13 +982,15 @@ static struct arizona_pdata lenovo_yt3_wm5102_pdata = { }, }; +static const struct software_node lenovo_yt3_wm5102; + static const struct property_entry lenovo_yt3_wm1502_props[] = { PROPERTY_ENTRY_GPIO("wlf,spkvdd-ena-gpios", &cherryview_gpiochip_nodes[0], 75, GPIO_ACTIVE_HIGH), PROPERTY_ENTRY_GPIO("wlf,ldoena-gpios", &cherryview_gpiochip_nodes[0], 81, GPIO_ACTIVE_HIGH), PROPERTY_ENTRY_GPIO("reset-gpios", &cherryview_gpiochip_nodes[0], 82, GPIO_ACTIVE_HIGH), - PROPERTY_ENTRY_GPIO("wlf,micd-pol-gpios", &arizona_gpiochip_node, 2, GPIO_ACTIVE_HIGH), + PROPERTY_ENTRY_GPIO("wlf,micd-pol-gpios", &lenovo_yt3_wm5102, 2, GPIO_ACTIVE_HIGH), { } }; @@ -1001,7 +1000,6 @@ static const struct software_node lenovo_yt3_wm5102 = { }; static const struct software_node *lenovo_yt3_swnodes[] = { - &arizona_gpiochip_node, &lenovo_yt3_wm5102, NULL }; From 144113b0a70fa18033a747ee5db6803308f7688c Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Sun, 30 Aug 2026 04:15:06 -0700 Subject: [PATCH 0461/1198] platform/x86: x86-android-tablets: hold device reference for secondary fwnode teardown MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In gpio_secondary_fwnode_init(), acpi_bus_find_device_by_name() returns a device reference, but the local dev variable is declared with __free(put_device), dropping the reference at the end of each iteration. Meanwhile, devm_add_action_or_reset() saves the dev pointer for gpio_secondary_unset() without incrementing its reference count, which could lead to a use-after-free during driver teardown if the device is released in the interim. Acquire an explicit device reference with get_device() when registering the devres action, and drop it with put_device() inside gpio_secondary_unset(). Fixes: 1448c2d2ca5c ("platform/x86: x86-android-tablets: enable fwnode matching of GPIO chips") Assisted-by: LLM Signed-off-by: Dmitry Torokhov Tested-by: Hans de Goede # Yoga tab 2 1380, yt3 Reviewed-by: Hans de Goede Reviewed-by: Andy Shevchenko Reviewed-by: Linus Walleij Link: https://patch.msgid.link/20260830-x86-android-lenovo-swnode-v1-2-066a91acb4ba@gmail.com Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen --- drivers/platform/x86/x86-android-tablets/core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/platform/x86/x86-android-tablets/core.c b/drivers/platform/x86/x86-android-tablets/core.c index 5db794d65eb5..722c0ae4ecd1 100644 --- a/drivers/platform/x86/x86-android-tablets/core.c +++ b/drivers/platform/x86/x86-android-tablets/core.c @@ -367,6 +367,7 @@ static void gpio_secondary_unset(void *data) struct device *dev = data; set_secondary_fwnode(dev, NULL); + put_device(dev); } static void gpio_secondary_unregister_node_group(void *data) @@ -409,7 +410,7 @@ static int gpio_secondary_fwnode_init(struct device *parent) set_secondary_fwnode(dev, fwnode); - ret = devm_add_action_or_reset(parent, gpio_secondary_unset, dev); + ret = devm_add_action_or_reset(parent, gpio_secondary_unset, get_device(dev)); if (ret) return ret; } From aab060ec969c3859b81f80f3444fd5a2edfc3cf5 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Sun, 30 Aug 2026 04:15:07 -0700 Subject: [PATCH 0462/1198] platform/x86: x86-android-tablets: pass node group to gpio_secondary_fwnode_init() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently gpio_secondary_fwnode_init() uses a file-scope static gpiochip_node_group variable initialized in probe. Pass the node group directly to gpio_secondary_fwnode_init() as an argument instead of using a global variable. This allows reusing the helper for additional GPIO controllers in subsequent patches. Assisted-by: LLM Signed-off-by: Dmitry Torokhov Tested-by: Hans de Goede # Yoga tab 2 1380, yt3 Reviewed-by: Hans de Goede Reviewed-by: Andy Shevchenko Reviewed-by: Linus Walleij Link: https://patch.msgid.link/20260830-x86-android-lenovo-swnode-v1-3-066a91acb4ba@gmail.com Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen --- drivers/platform/x86/x86-android-tablets/core.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/platform/x86/x86-android-tablets/core.c b/drivers/platform/x86/x86-android-tablets/core.c index 722c0ae4ecd1..45673bfc0b7b 100644 --- a/drivers/platform/x86/x86-android-tablets/core.c +++ b/drivers/platform/x86/x86-android-tablets/core.c @@ -156,7 +156,6 @@ static struct platform_device **pdevs; static struct serdev_device **serdevs; static const struct software_node **gpio_button_swnodes; static const struct software_node **swnode_group; -static const struct software_node **gpiochip_node_group; static void (*exit_handler)(void); static __init struct i2c_adapter * @@ -377,26 +376,27 @@ static void gpio_secondary_unregister_node_group(void *data) software_node_unregister_node_group(nodes); } -static int gpio_secondary_fwnode_init(struct device *parent) +static int gpio_secondary_fwnode_init(struct device *parent, + const struct software_node * const *node_group) { const struct software_node *const *swnode; struct fwnode_handle *fwnode; int ret; - if (!gpiochip_node_group) + if (!node_group) return 0; - ret = software_node_register_node_group(gpiochip_node_group); + ret = software_node_register_node_group(node_group); if (ret) return ret; ret = devm_add_action_or_reset(parent, gpio_secondary_unregister_node_group, - gpiochip_node_group); + (void *)node_group); if (ret) return ret; - for (swnode = gpiochip_node_group; *swnode; swnode++) { + for (swnode = node_group; *swnode; swnode++) { struct device *dev __free(put_device) = acpi_bus_find_device_by_name((*swnode)->name); if (!dev) @@ -453,6 +453,7 @@ static void x86_android_tablet_remove(struct platform_device *pdev) static __init int x86_android_tablet_probe(struct platform_device *pdev) { + const struct software_node * const *gpiochip_node_group; const struct x86_dev_info *dev_info; const struct dmi_system_id *id; int i, ret = 0; @@ -484,7 +485,7 @@ static __init int x86_android_tablet_probe(struct platform_device *pdev) break; } - ret = gpio_secondary_fwnode_init(&pdev->dev); + ret = gpio_secondary_fwnode_init(&pdev->dev, gpiochip_node_group); if (ret) { x86_android_tablet_remove(pdev); return ret; From 7872c625cd83a0247821cedd6c6f63938d4bddbc Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Sun, 30 Aug 2026 04:15:08 -0700 Subject: [PATCH 0463/1198] platform/x86: x86-android-tablets: add Crystal Cove GPIO swnode support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The crystalcove_gpiochip_node was created when gpiolib supported matching a software node name against the GPIO chip label. Later, gpiolib replaced name matching with firmware node identity mapping, and support for dynamically attaching software nodes to ACPI GPIO chips as secondary firmware nodes was added for Baytrail and Cherryview, but Crystal Cove ("INT33FD:00") was omitted. Consequently, lookups on the unattached Crystal Cove software node fail. Add support for attaching crystalcove_gpiochip_node to the INT33FD:00 ACPI device as a secondary firmware node, and enable it on Lenovo Yoga Tab 2 models. Fixes: 611fd6cfe139 ("gpio: swnode: remove deprecated lookup mechanism") Assisted-by: LLM Signed-off-by: Dmitry Torokhov Tested-by: Hans de Goede # Yoga tab 2 1380, yt3 Reviewed-by: Hans de Goede Reviewed-by: Andy Shevchenko Reviewed-by: Linus Walleij Link: https://patch.msgid.link/20260830-x86-android-lenovo-swnode-v1-4-066a91acb4ba@gmail.com Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen --- drivers/platform/x86/x86-android-tablets/core.c | 17 +++++++++++++++++ .../platform/x86/x86-android-tablets/lenovo.c | 6 ++---- .../x86-android-tablets/x86-android-tablets.h | 2 ++ 3 files changed, 21 insertions(+), 4 deletions(-) diff --git a/drivers/platform/x86/x86-android-tablets/core.c b/drivers/platform/x86/x86-android-tablets/core.c index 45673bfc0b7b..b028af1c9942 100644 --- a/drivers/platform/x86/x86-android-tablets/core.c +++ b/drivers/platform/x86/x86-android-tablets/core.c @@ -361,6 +361,15 @@ static const struct software_node *cherryview_gpiochip_node_group[] = { NULL }; +const struct software_node crystalcove_gpiochip_node = { + .name = "INT33FD:00", +}; + +static const struct software_node *crystalcove_gpiochip_node_group[] = { + &crystalcove_gpiochip_node, + NULL +}; + static void gpio_secondary_unset(void *data) { struct device *dev = data; @@ -491,6 +500,14 @@ static __init int x86_android_tablet_probe(struct platform_device *pdev) return ret; } + if (dev_info->has_crystalcove) { + ret = gpio_secondary_fwnode_init(&pdev->dev, crystalcove_gpiochip_node_group); + if (ret) { + x86_android_tablet_remove(pdev); + return ret; + } + } + ret = software_node_register_node_group(dev_info->swnode_group); if (ret) { x86_android_tablet_remove(pdev); diff --git a/drivers/platform/x86/x86-android-tablets/lenovo.c b/drivers/platform/x86/x86-android-tablets/lenovo.c index c34f62bdf8f9..54068a0f4633 100644 --- a/drivers/platform/x86/x86-android-tablets/lenovo.c +++ b/drivers/platform/x86/x86-android-tablets/lenovo.c @@ -61,9 +61,6 @@ static struct lp855x_platform_data lenovo_lp8557_reg_only_pdata = { .initial_brightness = 128, }; -static const struct software_node crystalcove_gpiochip_node = { - .name = "gpio_crystalcove", -}; /* Lenovo Yoga Book X90F / X90L's Android factory image has everything hardcoded */ @@ -431,7 +428,6 @@ static const struct software_node lenovo_yoga_tab2_830_1050_wm5102 = { }; static const struct software_node *lenovo_yoga_tab2_830_1050_swnodes[] = { - &crystalcove_gpiochip_node, &lenovo_yoga_tab2_830_1050_wm5102, &generic_lipo_hv_4v35_battery_node, NULL @@ -454,6 +450,7 @@ const struct x86_dev_info lenovo_yoga_tab2_830_1050_info __initconst = { .gpio_button_swnodes = lenovo_yoga_tab2_830_1050_lid_swnodes, .swnode_group = lenovo_yoga_tab2_830_1050_swnodes, .modules = lenovo_yoga_tab2_modules, + .has_crystalcove = true, .gpiochip_type = X86_GPIOCHIP_BAYTRAIL, .init = lenovo_yoga_tab2_830_1050_init, .exit = lenovo_yoga_tab2_830_1050_exit, @@ -799,6 +796,7 @@ const struct x86_dev_info lenovo_yoga_tab2_1380_info __initconst = { .gpio_button_swnodes = lenovo_yoga_tab2_830_1050_lid_swnodes, .swnode_group = lenovo_yoga_tab2_830_1050_swnodes, .modules = lenovo_yoga_tab2_modules, + .has_crystalcove = true, .gpiochip_type = X86_GPIOCHIP_BAYTRAIL, .init = lenovo_yoga_tab2_1380_init, .exit = lenovo_yoga_tab2_830_1050_exit, diff --git a/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h b/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h index c756961ae5fd..6e6534f8fa6c 100644 --- a/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h +++ b/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h @@ -96,6 +96,7 @@ struct x86_dev_info { int (*init)(struct device *dev); void (*exit)(void); bool use_pci; + bool has_crystalcove; enum x86_gpiochip_type gpiochip_type; }; @@ -107,6 +108,7 @@ int x86_acpi_irq_helper_get(const struct x86_acpi_irq_data *data); /* Software nodes representing GPIO chips used by various tablets */ extern const struct software_node baytrail_gpiochip_nodes[]; extern const struct software_node cherryview_gpiochip_nodes[]; +extern const struct software_node crystalcove_gpiochip_node; /* * Extern declarations of x86_dev_info structs so there can be a single From 74884436a53df0bbaf6d92d2922f643a4581b247 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Sun, 30 Aug 2026 04:15:09 -0700 Subject: [PATCH 0464/1198] platform/x86: x86-android-tablets: drop redundant swnode group on YT3 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The WM5102 codec software node lenovo_yt3_wm5102 is assigned to the board info swnode pointer in lenovo_yt3_spi_devs. When spi_new_device() instantiates the SPI device, device_add_software_node() automatically registers the software node. Therefore, explicitly registering lenovo_yt3_swnodes via software_node_register_node_group() and listing it in .swnode_group is redundant. Drop the unused node group and registration. Assisted-by: LLM Signed-off-by: Dmitry Torokhov Tested-by: Hans de Goede # Yoga tab 2 1380, yt3 Reviewed-by: Hans de Goede Reviewed-by: Andy Shevchenko Reviewed-by: Linus Walleij Link: https://patch.msgid.link/20260830-x86-android-lenovo-swnode-v1-5-066a91acb4ba@gmail.com Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen --- drivers/platform/x86/x86-android-tablets/lenovo.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/platform/x86/x86-android-tablets/lenovo.c b/drivers/platform/x86/x86-android-tablets/lenovo.c index 54068a0f4633..cd8cee1f4aed 100644 --- a/drivers/platform/x86/x86-android-tablets/lenovo.c +++ b/drivers/platform/x86/x86-android-tablets/lenovo.c @@ -997,10 +997,6 @@ static const struct software_node lenovo_yt3_wm5102 = { .name = "wm5102", }; -static const struct software_node *lenovo_yt3_swnodes[] = { - &lenovo_yt3_wm5102, - NULL -}; static const struct x86_spi_dev_info lenovo_yt3_spi_devs[] __initconst = { { @@ -1068,7 +1064,6 @@ const struct x86_dev_info lenovo_yt3_info __initconst = { .i2c_client_count = ARRAY_SIZE(lenovo_yt3_i2c_clients), .spi_dev_info = lenovo_yt3_spi_devs, .spi_dev_count = ARRAY_SIZE(lenovo_yt3_spi_devs), - .swnode_group = lenovo_yt3_swnodes, .modules = lenovo_yt3_modules, .gpiochip_type = X86_GPIOCHIP_CHERRYVIEW, .init = lenovo_yt3_init, From 312fd3f3a85b89aa0d4fb5417043d640daa3732c Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Sun, 30 Aug 2026 04:15:10 -0700 Subject: [PATCH 0465/1198] platform/x86: x86-android-tablets: use shared battery swnode group on Yoga Tab 2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The WM5102 codec software node lenovo_yoga_tab2_830_1050_wm5102 is registered automatically when attached to the codec device via device_add_software_node() in lenovo_yoga_tab2_830_1050_init_codec(). Including it in lenovo_yoga_tab2_830_1050_swnodes is therefore redundant, leaving generic_lipo_hv_4v35_battery_node as the only node needing registration. Switch lenovo_yoga_tab2_830_1050_info and lenovo_yoga_tab2_1380_info to use the shared generic_lipo_hv_4v35_battery_swnodes group directly and drop the custom lenovo_yoga_tab2_830_1050_swnodes array. Assisted-by: LLM Signed-off-by: Dmitry Torokhov Tested-by: Hans de Goede # Yoga tab 2 1380, yt3 Reviewed-by: Hans de Goede Reviewed-by: Andy Shevchenko Reviewed-by: Linus Walleij Link: https://patch.msgid.link/20260830-x86-android-lenovo-swnode-v1-6-066a91acb4ba@gmail.com Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen --- drivers/platform/x86/x86-android-tablets/lenovo.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/drivers/platform/x86/x86-android-tablets/lenovo.c b/drivers/platform/x86/x86-android-tablets/lenovo.c index cd8cee1f4aed..52d96ae89078 100644 --- a/drivers/platform/x86/x86-android-tablets/lenovo.c +++ b/drivers/platform/x86/x86-android-tablets/lenovo.c @@ -427,12 +427,6 @@ static const struct software_node lenovo_yoga_tab2_830_1050_wm5102 = { .properties = lenovo_yoga_tab2_830_1050_wm1502_props, }; -static const struct software_node *lenovo_yoga_tab2_830_1050_swnodes[] = { - &lenovo_yoga_tab2_830_1050_wm5102, - &generic_lipo_hv_4v35_battery_node, - NULL -}; - static int __init lenovo_yoga_tab2_830_1050_init(struct device *dev); static void lenovo_yoga_tab2_830_1050_exit(void); @@ -448,7 +442,7 @@ const struct x86_dev_info lenovo_yoga_tab2_830_1050_info __initconst = { .pdev_info = lenovo_yoga_tab2_830_1050_pdevs, .pdev_count = ARRAY_SIZE(lenovo_yoga_tab2_830_1050_pdevs), .gpio_button_swnodes = lenovo_yoga_tab2_830_1050_lid_swnodes, - .swnode_group = lenovo_yoga_tab2_830_1050_swnodes, + .swnode_group = generic_lipo_hv_4v35_battery_swnodes, .modules = lenovo_yoga_tab2_modules, .has_crystalcove = true, .gpiochip_type = X86_GPIOCHIP_BAYTRAIL, @@ -794,7 +788,7 @@ const struct x86_dev_info lenovo_yoga_tab2_1380_info __initconst = { .pdev_info = lenovo_yoga_tab2_1380_pdevs, .pdev_count = ARRAY_SIZE(lenovo_yoga_tab2_1380_pdevs), .gpio_button_swnodes = lenovo_yoga_tab2_830_1050_lid_swnodes, - .swnode_group = lenovo_yoga_tab2_830_1050_swnodes, + .swnode_group = generic_lipo_hv_4v35_battery_swnodes, .modules = lenovo_yoga_tab2_modules, .has_crystalcove = true, .gpiochip_type = X86_GPIOCHIP_BAYTRAIL, From 950ae84b5cc944fbe27d81806d0b76af765f779c Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 2 Sep 2026 13:10:19 +0100 Subject: [PATCH 0466/1198] afs: Fix missing kunmap in afs_dir_search_bucket() Fix afs_dir_search_bucket() to kunmap the block it's using in the "bad:" path. Fixes: a5b5beebcf96 ("afs: Use the contained hashtable to search a directory") Closes: https://sashiko.dev/#/patchset/20260716103030.3065561-1-dhowells%40redhat.com Signed-off-by: David Howells Link: https://patch.msgid.link/20260902121024.3328255-2-dhowells@redhat.com cc: Marc Dionne cc: linux-afs@lists.infradead.org cc: linux-fsdevel@vger.kernel.org cc: stable@vger.kernel.org Signed-off-by: Christian Brauner (Amutable) --- fs/afs/dir_search.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/afs/dir_search.c b/fs/afs/dir_search.c index 104411c0692f..4977ad81fa82 100644 --- a/fs/afs/dir_search.c +++ b/fs/afs/dir_search.c @@ -173,12 +173,11 @@ int afs_dir_search_bucket(struct afs_dir_iter *iter, const struct qstr *name, ret = -ENOENT; found: +bad: if (iter->block) { kunmap_local(iter->block); iter->block = NULL; } - -bad: if (ret == -ESTALE) afs_invalidate_dir(iter->dvnode, afs_dir_invalid_iter_stale); _leave(" = %d", ret); From e3cfd3eb7d5be7787cc69530b423f788f14d084f Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 2 Sep 2026 13:10:20 +0100 Subject: [PATCH 0467/1198] afs: Fix double-unmap of directory block Fix afs_edit_dir_remove() to use a cleanup function to unmap the block pointed to by afs_dir_iter::block if it's left pointing to something rather than manually kunmapping the blocks. Manually kunmapping without clearing iter.blocks can result in a double-kunmap if afs_dir_find_block() is called twice in a row (which would be the case if the block being modified is not first in the hash chain). Fixes: a5b5beebcf96 ("afs: Use the contained hashtable to search a directory") Closes: https://sashiko.dev/#/patchset/20260716103030.3065561-1-dhowells%40redhat.com Signed-off-by: David Howells Link: https://patch.msgid.link/20260902121024.3328255-3-dhowells@redhat.com cc: Marc Dionne cc: linux-afs@lists.infradead.org cc: linux-fsdevel@vger.kernel.org cc: stable@vger.kernel.org Signed-off-by: Christian Brauner (Amutable) --- fs/afs/dir_edit.c | 9 ++------- fs/afs/dir_search.c | 10 ++-------- fs/afs/internal.h | 8 ++++++++ 3 files changed, 12 insertions(+), 15 deletions(-) diff --git a/fs/afs/dir_edit.c b/fs/afs/dir_edit.c index 3ead36a07048..c31303059444 100644 --- a/fs/afs/dir_edit.c +++ b/fs/afs/dir_edit.c @@ -442,7 +442,7 @@ void afs_edit_dir_remove(struct afs_vnode *vnode, /* Check and clear the entry. */ de = &block->dirents[slot]; if (de->u.valid != 1) - goto error_unmap; + goto error; trace_afs_edit_dir(vnode, why, afs_edit_dir_delete, b, slot, ntohl(de->u.vnode), ntohl(de->u.unique), @@ -458,7 +458,6 @@ void afs_edit_dir_remove(struct afs_vnode *vnode, /* Clear the constituent entries. */ next = de->u.hash_next; memset(de, 0, sizeof(*de) * iter.nr_slots); - kunmap_local(block); /* Adjust the hash chain: if iter->prev_entry is 0, the hashtable head * index is previous; otherwise it's slot number of the previous entry. @@ -485,7 +484,6 @@ void afs_edit_dir_remove(struct afs_vnode *vnode, pde = &pblock->dirents[ps]; prev_next = pde->u.hash_next; if (prev_next != htons(entry)) { - kunmap_local(pblock); pr_warn("%llx:%llx:%x: not prev in chain b=%x p=%x,%x e=%x %*s", vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique, iter.bucket, iter.prev_entry, prev_next, entry, @@ -493,7 +491,6 @@ void afs_edit_dir_remove(struct afs_vnode *vnode, goto error; } pde->u.hash_next = next; - kunmap_local(pblock); } netfs_single_mark_inode_dirty(&vnode->netfs.inode); @@ -503,18 +500,16 @@ void afs_edit_dir_remove(struct afs_vnode *vnode, _debug("Remove %s from %u[%u]", name->name, b, slot); out_unmap: + afs_dir_end_iter(&iter); kunmap_local(meta); _leave(""); return; already_invalidated: - kunmap_local(block); trace_afs_edit_dir(vnode, why, afs_edit_dir_delete_inval, 0, 0, 0, 0, name->name); goto out_unmap; -error_unmap: - kunmap_local(block); error: trace_afs_edit_dir(vnode, why, afs_edit_dir_delete_error, 0, 0, 0, 0, name->name); diff --git a/fs/afs/dir_search.c b/fs/afs/dir_search.c index 4977ad81fa82..11ebdfffcb1d 100644 --- a/fs/afs/dir_search.c +++ b/fs/afs/dir_search.c @@ -75,10 +75,7 @@ union afs_xdr_dir_block *afs_dir_find_block(struct afs_dir_iter *iter, size_t bl _enter("%zx,%d", block, slot); - if (iter->block) { - kunmap_local(iter->block); - iter->block = NULL; - } + afs_dir_end_iter(iter); if (dvnode->directory_size < blend) goto fail; @@ -174,10 +171,7 @@ int afs_dir_search_bucket(struct afs_dir_iter *iter, const struct qstr *name, ret = -ENOENT; found: bad: - if (iter->block) { - kunmap_local(iter->block); - iter->block = NULL; - } + afs_dir_end_iter(iter); if (ret == -ESTALE) afs_invalidate_dir(iter->dvnode, afs_dir_invalid_iter_stale); _leave(" = %d", ret); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 290873bac89b..330654ed16ec 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -1133,6 +1133,14 @@ int afs_dir_search_bucket(struct afs_dir_iter *iter, const struct qstr *name, int afs_dir_search(struct afs_vnode *dvnode, const struct qstr *name, struct afs_fid *_fid, afs_dataversion_t *_dir_version); +static inline void afs_dir_end_iter(struct afs_dir_iter *iter) +{ + if (iter->block) { + kunmap_local(iter->block); + iter->block = NULL; + } +} + /* * dir_silly.c */ From 044d596094af4b769fb8e1173dff0d08bd68db6c Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 2 Sep 2026 13:10:21 +0100 Subject: [PATCH 0468/1198] afs: Fix incorrect free in candidate cleanup in afs_lookup_server() Fix afs_lookup_server() to not free an existing server's endpoint state when cleaning up a candidate server. The candidate record doesn't have an endpoint state yet at this point, so the free for that can just be removed. Fixes: 4882ba78574e ("afs: Fix afs_server ref accounting") Link: https://sashiko.dev/#/patchset/20260729160108.2031453-1-dhowells%40redhat.com Signed-off-by: David Howells Link: https://patch.msgid.link/20260902121024.3328255-4-dhowells@redhat.com cc: Marc Dionne cc: linux-afs@lists.infradead.org cc: linux-fsdevel@vger.kernel.org cc: stable@vger.kernel.org Signed-off-by: Christian Brauner (Amutable) --- fs/afs/server.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/afs/server.c b/fs/afs/server.c index 0fe162ea2a36..189138bd6d71 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -242,7 +242,6 @@ struct afs_server *afs_lookup_server(struct afs_cell *cell, struct key *key, out: afs_put_addrlist(alist, afs_alist_trace_put_server_create); if (candidate) { - kfree(rcu_access_pointer(server->endpoint_state)); kfree(candidate); afs_dec_servers_outstanding(cell->net); } From ba0623fc19a424f4745394c499f9f28a8d88d397 Mon Sep 17 00:00:00 2001 From: Chengfeng Ye Date: Wed, 2 Sep 2026 13:10:22 +0100 Subject: [PATCH 0469/1198] afs: Clear stale peer app data after address list changes afs_fs_probe_fileserver() fetches the current endpoint state under server->fs_lock, but leaves old_alist as NULL. Consequently, afs_set_peer_appdata() treats every address list replacement as initial setup and only binds the new peers; it never unbinds peers removed from the old list. An address refresh can therefore proceed as follows. CPU 0 replaces server S's list and drops Pold without clearing Pold->app_data. The server destroyer then clears only S's current peers and lets S reach its RCU callback. After the callback frees S, CPU 1 handles a callback through an RxRPC connection that still pins Pold, reads Pold->app_data, and calls afs_use_server() on the freed object. KASAN reported: BUG: KASAN: slab-use-after-free in afs_find_server+0x3c/0xa0 Read of size 4 at addr ffff8881013e1af0 by task krxrpcio/7001/74 Call Trace: afs_find_server+0x3c/0xa0 afs_rx_new_call+0x15c/0x390 rxrpc_new_incoming_call+0x97c/0x1730 rxrpc_input_packet.constprop.0+0xd03/0xec0 rxrpc_io_thread+0x967/0x1640 Allocated by task 93: afs_lookup_server+0x1a7/0x14c0 afs_alloc_server_list+0x43f/0xb60 afs_create_volume+0x923/0x1490 afs_get_tree+0x1c6/0x10a0 Freed by task 0: kfree+0x131/0x3c0 rcu_core+0x50a/0x1850 Last potentially related work creation: __call_rcu_common.constprop.0+0x71/0xa10 afs_put_server+0x213/0x2b0 Preserve old->addresses for the peer app-data update so that removed peers are cleared before the endpoint state is replaced. Also advance both cursors when the old and new lists share a peer; activating the old/new comparison without this would otherwise loop forever on the shared entry. Fixes: 40e8b52fe8c8 ("afs: Use the per-peer app data provided by rxrpc") Signed-off-by: Chengfeng Ye Signed-off-by: Qi Zhang Signed-off-by: David Howells Link: https://patch.msgid.link/20260902121024.3328255-5-dhowells@redhat.com cc: Marc Dionne cc: linux-afs@lists.infradead.org cc: linux-fsdevel@vger.kernel.org cc: stable@vger.kernel.org Signed-off-by: Christian Brauner (Amutable) --- fs/afs/addr_list.c | 5 ++++- fs/afs/fs_probe.c | 1 + 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/afs/addr_list.c b/fs/afs/addr_list.c index 63bf096b721a..73195d76b481 100644 --- a/fs/afs/addr_list.c +++ b/fs/afs/addr_list.c @@ -394,8 +394,11 @@ void afs_set_peer_appdata(struct afs_server *server, struct rxrpc_peer *pn = new_alist->addrs[n].peer; struct rxrpc_peer *po = old_alist->addrs[o].peer; - if (pn == po) + if (pn == po) { + n++; + o++; continue; + } if (pn < po) { rxrpc_kernel_set_peer_data(pn, data); n++; diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c index a91ad1938d07..8c62334dbfe7 100644 --- a/fs/afs/fs_probe.c +++ b/fs/afs/fs_probe.c @@ -258,6 +258,7 @@ int afs_fs_probe_fileserver(struct afs_net *net, struct afs_server *server, lockdep_is_held(&server->fs_lock)); if (old) { estate->responsive_set = old->responsive_set; + old_alist = old->addresses; if (!new_alist) new_alist = old->addresses; } From 387b1baefbb776e3f48dc2261e77a49213f470f7 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Wed, 2 Sep 2026 00:28:34 -0700 Subject: [PATCH 0470/1198] bpf: backtrack_insn(): Handle ld_{abs,ind} subprog exit edge Nicholas Carlini reported a bug in precision backtracking mechanism for BPF_LD | BPF_{IND,ABS} instructions. These instructions are modelled as two branches: - fallthrough; - implicit exit from current subprogram. The implicit exit case was not handled by the backtrack_insn() function. When backtracking such a path backtrack_insn() did not call bt_subprog_enter(), which meant that backtracking continued manipulating precision marks in a caller frame, while looking at instructions in a callee frame. This lead to segmentation faults during verification (see the selftest), or unsound state pruning. Fixes: ee861486e377 ("bpf: Fix ld_{abs,ind} failure path analysis in subprogs") Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Eduard Zingerman Signed-off-by: Daniel Borkmann Acked-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20260901-bug-016-backtrack-ld-abs-v1-1-59368f1be435@gmail.com --- kernel/bpf/backtrack.c | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-) diff --git a/kernel/bpf/backtrack.c b/kernel/bpf/backtrack.c index a2b18a9f1694..eaf7438b9ebf 100644 --- a/kernel/bpf/backtrack.c +++ b/kernel/bpf/backtrack.c @@ -582,16 +582,29 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, */ } } else if (class == BPF_LD) { - if (!bt_is_reg_set(bt, dreg)) - return 0; - bt_clear_reg(bt, dreg); /* It's ld_imm64 or ld_abs or ld_ind. * For ld_imm64 no further tracking of precision * into parent is necessary */ - if (mode == BPF_IND || mode == BPF_ABS) - /* to be analyzed */ - return -ENOTSUPP; + if (mode == BPF_IMM) { + bt_clear_reg(bt, dreg); + return 0; + } + /* + * BPF_{IND,ABS} are modelled as two branches: + * - fallthrough; + * - implicit subprogram exit. + * It is necessary to switch current frame if + * implicit subprogram exit branch is backtracked. + */ + if (mode == BPF_IND || mode == BPF_ABS) { + if (bt_is_reg_set(bt, dreg)) + return -ENOTSUPP; + if (subseq_idx != idx + 1) + if (bt_subprog_enter(bt)) + return -EFAULT; + return 0; + } } /* Propagate precision marks to linked registers, to account for * registers marked as precise in this function. From ce6b9e5dd873de532cd924e2abc928220cdc2738 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Wed, 2 Sep 2026 00:28:35 -0700 Subject: [PATCH 0471/1198] selftests/bpf: Precision tracking across BPF_ABS subprog exit A test case checking that the verifier properly backtracks both fallthrough and implicit subprogram exit paths modelled for BPF_LD | BPF_ABS instruction. Without the previous patch: - the verifier did not call bt_subprog_enter() on the implicit subprogram exit path; - bpf_pseudo_call() branch in backtrack_insn() executed 'bpf_bt_set_frame_reg(bt, bt->frame - 1, i);' with bt->frame == 0; - causing a segmentation fault. Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Eduard Zingerman Signed-off-by: Daniel Borkmann Acked-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20260901-bug-016-backtrack-ld-abs-v1-2-59368f1be435@gmail.com --- .../bpf/progs/verifier_subprog_precision.c | 51 +++++++++++++++++++ 1 file changed, 51 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c index d21d32f6a676..e174a905c562 100644 --- a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c +++ b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c @@ -846,4 +846,55 @@ __naked int subprog_result_tail_call(void) ); } +__naked __noinline __used +static int ld_abs_subprog(void) +{ + asm volatile ( + "r6 = r1;" + "r7 = r1;" + ".8byte %[ld_abs];" + "exit;" + : + : __imm_insn(ld_abs, BPF_LD_ABS(BPF_W, 0)) + : __clobber_all); +} + +/* + * Buggy verifier did not properly backtrack early subprogram exit + * modelled for BPF_LD | BPF_ABS instruction, causing a segfault. + */ +SEC("socket") +__success +__log_level(2) +/* early exit path */ +__msg("3: (0f) r1 += r7") +__msg("mark_precise: frame0: regs=r7 stack= before 2: (bf) r1 = r10") +__msg("mark_precise: frame0: regs=r7 stack= before 9: (20) r0 = *(u32 *)skb[0]") +__msg("mark_precise: frame1: regs= stack= before 8: (bf) r7 = r1") +__msg("mark_precise: frame1: regs= stack= before 7: (bf) r6 = r1") +__msg("mark_precise: frame1: regs= stack= before 1: (85) call pc+5") +__msg("mark_precise: frame0: regs=r7 stack= before 0: (b7) r7 = -8") +/* fallthrough path */ +__msg("3: (0f) r1 += r7") +__msg("mark_precise: frame0: regs=r7 stack= before 2: (bf) r1 = r10") +__msg("mark_precise: frame0: regs=r7 stack= before 10: (95) exit") +__msg("mark_precise: frame1: regs= stack= before 9: (20) r0 = *(u32 *)skb[0]") +__msg("mark_precise: frame1: regs= stack= before 8: (bf) r7 = r1") +__msg("mark_precise: frame1: regs= stack= before 7: (bf) r6 = r1") +__msg("mark_precise: frame1: regs= stack= before 1: (85) call pc+5") +__msg("mark_precise: frame0: regs=r7 stack= before 0: (b7) r7 = -8") +__naked int ld_abs_backtrack_both_paths(void) +{ + asm volatile ( + "r7 = -8;" + "call ld_abs_subprog;" + "r1 = r10;" + "r1 += r7;" /* mark r7 as precise */ + "*(u64 *)(r1 + 0) = 0;" + "r0 = 0;" + "exit;" + ::: __clobber_all + ); +} + char _license[] SEC("license") = "GPL"; From 7d4d4f3b668d708d94f62ecdd33ac330a6fd8a84 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Wed, 2 Sep 2026 16:36:26 +0200 Subject: [PATCH 0472/1198] dm-integrity: fix NULL pointer dereference when the 'R' flag is used If the dm-integrity device has the SB_FLAG_DIRTY_BITMAP flag set and the user activates the device in the 'R' mode, a crash in dm_integrity_resume happens because the function attempts to read the journal containing the bitmap. This patch makes dm-integrity skip any writes to the device in dm_integrity_resume if the device is activated in the 'R' mode. Signed-off-by: Mikulas Patocka Fixes: 468dfca38b1a ("dm integrity: add a bitmap mode") Cc: stable@vger.kernel.org --- drivers/md/dm-integrity.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 5327d7c6a71c..92970e12267a 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -3875,6 +3875,10 @@ static void dm_integrity_resume(struct dm_target *ti) r = sync_rw_sb(ic, REQ_OP_READ); if (r) dm_integrity_io_error(ic, "reading superblock", r); + + if (ic->mode == 'R') + goto skip_writes; + if ((ic->sb->flags & flags) != flags) { ic->sb->flags |= flags; r = sync_rw_sb(ic, REQ_OP_WRITE | REQ_FUA); @@ -3984,6 +3988,7 @@ static void dm_integrity_resume(struct dm_target *ti) } } +skip_writes: ic->reboot_notifier.notifier_call = dm_integrity_reboot; ic->reboot_notifier.next = NULL; ic->reboot_notifier.priority = INT_MAX - 1; /* be notified after md and before hardware drivers */ From ece06de726737e887dc0225c8283477624f8ae21 Mon Sep 17 00:00:00 2001 From: Yang Xiuwei Date: Mon, 17 Aug 2026 16:07:28 +0800 Subject: [PATCH 0473/1198] scsi: bsg: Cap io_uring sense copy to max_response_len Completion copied scmd->sense_len to the user response buffer without honoring max_response_len. After a valid sense, the midlayer sets sense_len to the real length (up to SCSI_SENSE_BUFFERSIZE), so a smaller user buffer was overrun. Fixes: 7b6d3255e7f8 ("scsi: bsg: add io_uring passthrough handler") Cc: stable@vger.kernel.org Signed-off-by: Yang Xiuwei Link: https://patch.msgid.link/20260817080730.967879-2-yangxiuwei@kylinos.cn Signed-off-by: Martin K. Petersen (Oracle) --- drivers/scsi/scsi_bsg.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/scsi_bsg.c b/drivers/scsi/scsi_bsg.c index e80dec53174e..b3c4b1063d6f 100644 --- a/drivers/scsi/scsi_bsg.c +++ b/drivers/scsi/scsi_bsg.c @@ -18,6 +18,7 @@ struct scsi_bsg_uring_cmd_pdu { struct bio *bio; /* mapped user buffer, unmap in task work */ struct request *req; /* block request, freed in task work */ u64 response_addr; /* user space response buffer address */ + u32 max_response_len; /* user response buffer size */ }; static_assert(sizeof(struct scsi_bsg_uring_cmd_pdu) <= sizeof_field(struct io_uring_cmd, pdu)); @@ -45,8 +46,8 @@ static void scsi_bsg_uring_task_cb(struct io_tw_req tw_req, io_tw_token_t tw) if (scsi_status_is_check_condition(scmd->result)) { driver_status = DRIVER_SENSE; if (pdu->response_addr) - sense_len_wr = min_t(u8, scmd->sense_len, - SCSI_SENSE_BUFFERSIZE); + sense_len_wr = min_t(unsigned int, pdu->max_response_len, + scmd->sense_len); } if (sense_len_wr) { @@ -155,8 +156,7 @@ static int scsi_bsg_uring_cmd(struct request_queue *q, struct io_uring_cmd *iouc } pdu->response_addr = cmd->response; - scmd->sense_len = cmd->max_response_len ? - min(cmd->max_response_len, SCSI_SENSE_BUFFERSIZE) : SCSI_SENSE_BUFFERSIZE; + pdu->max_response_len = cmd->max_response_len; if (cmd->dout_xfer_len || cmd->din_xfer_len) { ret = scsi_bsg_map_user_buffer(req, ioucmd, issue_flags, gfp_mask); From 4b3c5965fca99f62d31c963294bd5b23cc488e97 Mon Sep 17 00:00:00 2001 From: Rahul Chandelkar Date: Mon, 17 Aug 2026 16:07:29 +0800 Subject: [PATCH 0474/1198] scsi: bsg: Fix TOCTOU in io_uring passthrough command setup scsi_bsg_uring_cmd() reads bsg_uring_cmd from the shared mmap'd SQE. Userspace can change a field after we check it and before we use it. request_len is the sharp case: it can grow past sizeof(scmd->cmnd) after the bound check and overflow scmd->cmnd in copy_from_user(). READ_ONCE() the SQE fields we check or use into locals before use. Fixes: 7b6d3255e7f8 ("scsi: bsg: add io_uring passthrough handler") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20260527105931.3950913-1-rc@rexion.ai Signed-off-by: Rahul Chandelkar Co-developed-by: Yang Xiuwei Signed-off-by: Yang Xiuwei Link: https://patch.msgid.link/20260817080730.967879-3-yangxiuwei@kylinos.cn Signed-off-by: Martin K. Petersen (Oracle) --- drivers/scsi/scsi_bsg.c | 39 +++++++++++++++++++++++++-------------- 1 file changed, 25 insertions(+), 14 deletions(-) diff --git a/drivers/scsi/scsi_bsg.c b/drivers/scsi/scsi_bsg.c index b3c4b1063d6f..5eec248a77a6 100644 --- a/drivers/scsi/scsi_bsg.c +++ b/drivers/scsi/scsi_bsg.c @@ -77,12 +77,10 @@ static enum rq_end_io_ret scsi_bsg_uring_cmd_done(struct request *req, static int scsi_bsg_map_user_buffer(struct request *req, struct io_uring_cmd *ioucmd, - unsigned int issue_flags, gfp_t gfp_mask) + unsigned int issue_flags, gfp_t gfp_mask, + bool is_write, u64 buf_addr, + unsigned long buf_len) { - const struct bsg_uring_cmd *cmd = io_uring_sqe128_cmd(ioucmd->sqe, struct bsg_uring_cmd); - bool is_write = cmd->dout_xfer_len > 0; - u64 buf_addr = is_write ? cmd->dout_xferp : cmd->din_xferp; - unsigned long buf_len = is_write ? cmd->dout_xfer_len : cmd->din_xfer_len; struct iov_iter iter; int ret; @@ -105,21 +103,28 @@ static int scsi_bsg_uring_cmd(struct request_queue *q, struct io_uring_cmd *iouc unsigned int issue_flags, bool open_for_write) { struct scsi_bsg_uring_cmd_pdu *pdu = scsi_bsg_uring_cmd_pdu(ioucmd); - const struct bsg_uring_cmd *cmd = io_uring_sqe128_cmd(ioucmd->sqe, struct bsg_uring_cmd); + const struct bsg_uring_cmd *cmd = + io_uring_sqe128_cmd(ioucmd->sqe, struct bsg_uring_cmd); struct scsi_cmnd *scmd; struct request *req; blk_mq_req_flags_t blk_flags = 0; gfp_t gfp_mask = GFP_KERNEL; + u64 request = READ_ONCE(cmd->request); + u32 request_len = READ_ONCE(cmd->request_len); + u64 dout_xferp = READ_ONCE(cmd->dout_xferp); + u32 dout_xfer_len = READ_ONCE(cmd->dout_xfer_len); + u64 din_xferp = READ_ONCE(cmd->din_xferp); + u32 din_xfer_len = READ_ONCE(cmd->din_xfer_len); int ret; if (cmd->protocol != BSG_PROTOCOL_SCSI || cmd->subprotocol != BSG_SUB_PROTOCOL_SCSI_CMD) return -EINVAL; - if (!cmd->request || cmd->request_len == 0) + if (!request || request_len == 0) return -EINVAL; - if (cmd->dout_xfer_len && cmd->din_xfer_len) { + if (dout_xfer_len && din_xfer_len) { pr_warn_once("BIDI support in bsg has been removed.\n"); return -EOPNOTSUPP; } @@ -132,20 +137,20 @@ static int scsi_bsg_uring_cmd(struct request_queue *q, struct io_uring_cmd *iouc gfp_mask = GFP_NOWAIT; } - req = scsi_alloc_request(q, cmd->dout_xfer_len ? + req = scsi_alloc_request(q, dout_xfer_len ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, blk_flags); if (IS_ERR(req)) return PTR_ERR(req); scmd = blk_mq_rq_to_pdu(req); - if (cmd->request_len > sizeof(scmd->cmnd)) { + if (request_len > sizeof(scmd->cmnd)) { ret = -EINVAL; goto out_free_req; } - scmd->cmd_len = cmd->request_len; + scmd->cmd_len = request_len; scmd->allowed = SG_DEFAULT_RETRIES; - if (copy_from_user(scmd->cmnd, uptr64(cmd->request), cmd->request_len)) { + if (copy_from_user(scmd->cmnd, uptr64(request), request_len)) { ret = -EFAULT; goto out_free_req; } @@ -158,8 +163,14 @@ static int scsi_bsg_uring_cmd(struct request_queue *q, struct io_uring_cmd *iouc pdu->response_addr = cmd->response; pdu->max_response_len = cmd->max_response_len; - if (cmd->dout_xfer_len || cmd->din_xfer_len) { - ret = scsi_bsg_map_user_buffer(req, ioucmd, issue_flags, gfp_mask); + if (dout_xfer_len || din_xfer_len) { + bool is_write = dout_xfer_len > 0; + u64 buf_addr = is_write ? dout_xferp : din_xferp; + unsigned long buf_len = is_write ? dout_xfer_len : din_xfer_len; + + ret = scsi_bsg_map_user_buffer(req, ioucmd, issue_flags, + gfp_mask, is_write, buf_addr, + buf_len); if (ret) goto out_free_req; pdu->bio = req->bio; From 7ac81e2d2240f2c57bd073b0733e0b2abca38e82 Mon Sep 17 00:00:00 2001 From: Genjian Zhang Date: Fri, 7 Aug 2026 23:57:15 +0800 Subject: [PATCH 0475/1198] dm-ebs: fix incorrect device offset check in ebs_ctr() is a backing-device sector offset; ti->len is the virtual target length. Comparing them rejects valid tables, e.g.: dmsetup create ebs0 --table "0 1048576 ebs /dev/sda 2097152 1 8" -> ebs: Invalid device offset sector (-EINVAL) Drop the check. Bounds against the backing device are already enforced later by device_area_is_invalid() via ebs_iterate_devices(). Cc: stable@vger.kernel.org Fixes: d3c7b35c20d6 ("dm: add emulated block size target") Signed-off-by: Genjian Zhang Signed-off-by: Mikulas Patocka --- drivers/md/dm-ebs-target.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/md/dm-ebs-target.c b/drivers/md/dm-ebs-target.c index 1e52bde48b91..5d67c6c19d4b 100644 --- a/drivers/md/dm-ebs-target.c +++ b/drivers/md/dm-ebs-target.c @@ -265,8 +265,7 @@ static int ebs_ctr(struct dm_target *ti, unsigned int argc, char **argv) r = -EINVAL; if (sscanf(argv[1], "%llu%c", &tmp, &dummy) != 1 || - tmp != (sector_t)tmp || - (sector_t)tmp >= ti->len) { + tmp != (sector_t)tmp) { ti->error = "Invalid device offset sector"; goto bad; } From 4617721c502b2ddaa4e324e86da4997edf738fa5 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 2 Sep 2026 09:55:01 -0400 Subject: [PATCH 0476/1198] ftrace: Synchronize the initialization of ftrace_ops There's some internal state that ftrace_ops needs to have set, but since it can be declared outside of the ftrace.c code, it calls ftrace_ops_init() on the ops in every global function. The issue is that if two tasks call it on the same ops at the same time it is possible to have the initialization of one corrupt the initialization of the other call. Create a ops_mutex to use to synchronize every initialization of the ftrace_ops. The mutex is taken within checking the ftrace_ops flag that states it was initializied but the flag is checked again after the mutex has been taken. Checking first outside the mutex allows it to shortcut having to take the mutex. But then the check needs to be done again after the mute is taken in case of races. Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260902095501.6b59af20@gandalf.local.home Fixes: f04f24fb7e48d ("ftrace, kprobes: Fix a deadlock on ftrace_regex_lock") Reported-by: sashiko-bot@kernel.org Close: https://lore.kernel.org/all/20260829025528.49A831F000E9@smtp.kernel.org/ Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index c7cf36f2dd7b..53d5db60bfa5 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -75,6 +75,8 @@ .func_hash = &opsname.local_hash, \ .local_hash.regex_lock = __MUTEX_INITIALIZER(opsname.local_hash.regex_lock), \ .subop_list = LIST_HEAD_INIT(opsname.subop_list), +/* Used only to synchronize the initialization of ftrace_ops */ +static DEFINE_MUTEX(ops_mutex); #else #define INIT_OPS_HASH(opsname) #endif @@ -159,11 +161,18 @@ const struct ftrace_ops ftrace_nop_ops = { static inline void ftrace_ops_init(struct ftrace_ops *ops) { #ifdef CONFIG_DYNAMIC_FTRACE - if (!(ops->flags & FTRACE_OPS_FL_INITIALIZED)) { + unsigned long flags = smp_load_acquire(&ops->flags); + + if (!(flags & FTRACE_OPS_FL_INITIALIZED)) { + guard(mutex)(&ops_mutex); + /* Could have been initialized before lock taken */ + if (unlikely(ops->flags & FTRACE_OPS_FL_INITIALIZED)) + return; mutex_init(&ops->local_hash.regex_lock); INIT_LIST_HEAD(&ops->subop_list); ops->func_hash = &ops->local_hash; - ops->flags |= FTRACE_OPS_FL_INITIALIZED; + flags = ops->flags | FTRACE_OPS_FL_INITIALIZED; + smp_store_release(&ops->flags, flags); } #endif } From af8c27375733fb6a6df9fa484cda77cc3dd0cb80 Mon Sep 17 00:00:00 2001 From: Thomas Lamprecht Date: Thu, 27 Aug 2026 19:24:24 +0200 Subject: [PATCH 0477/1198] scsi: megaraid_sas: Limit NVMe request size to the PRP chain frame megasas_make_prp_nvme() builds a command's PRP list in cmd->sg_frame, a DMA pool buffer of instance->max_chain_frame_sz bytes, spending one entry per NVMe page of the transfer plus one per page of the buffer for the chain pointer. The loop runs until the transfer is described and never checks the buffer bound. max_hw_sectors comes straight from the MDTS the firmware reports for the drive. On drives with a large MDTS the only thing keeping the list inside the buffer was the block layer default of 1280 KiB, which needs 320 entries, which fit into a 4 KiB frame as that holds 512. But since commit 9b8b84879d4a ("block: Increase BLK_DEF_MAX_SECTORS_CAP") that default is 4 MiB, and such a transfer needs 1025 entries, so the list runs a full page past the end of the frame: sd 1:0:1:0: [sdb] tag#630 page boundary ptr_sgl: 0x00000000ba62d13f BUG: unable to handle page fault for address: ff663bcb81e7c000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page RIP: 0010:megasas_build_and_issue_cmd_fusion+0xeaa/0x1870 [megaraid_sas] If the page after the frame happens to be mapped, the overrun does not fault but silently corrupts the neighbouring pool entry, which is another in-flight command's PRP list. Cap max_hw_sectors at what the chain frame can describe, less one page for transfers that do not start on a page boundary and so need one entry more. This is the megaraid_sas counterpart of commit 04631f55afc5 ("scsi: mpt3sas: Limit NVMe request size to 2 MiB"), but derives the limit from max_chain_frame_sz rather than hardcoding it. Cc: stable@vger.kernel.org Fixes: 9b8b84879d4a ("block: Increase BLK_DEF_MAX_SECTORS_CAP") Reported-by: Lukasz Magiera Closes: https://lore.kernel.org/all/GPhsSM0vkgyIrs0DIZ62qeUZX7X4RxwQXVKiuvMx-lHQVSPDxpztUyQOGS0xikqvJ-Z94hMV-dW_5KN_0CX2hsfV7kTf_t0MTf6vdAAaSEc=@magik.net/ Reported-by: Mira Limbeck Closes: https://lore.kernel.org/all/d171cc76-bf25-48ce-b482-d344669dfc24@proxmox.com/ Suggested-by: Martin K. Petersen Link: https://lore.kernel.org/all/yq17bmzd5jr.fsf@ca-mkp.ca.oracle.com/ Signed-off-by: Thomas Lamprecht Closes: https://lore.kernel.org/linux-scsi/20260827182106.535D61F000E9@smtp.kernel.org Link: https://patch.msgid.link/20260827175743.734593-1-t.lamprecht@proxmox.com Signed-off-by: Martin K. Petersen (Oracle) --- drivers/scsi/megaraid/megaraid_sas_base.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index f0152b043e18..b95f187297ae 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -1973,12 +1973,23 @@ megasas_set_nvme_device_properties(struct scsi_device *sdev, { struct megasas_instance *instance; u32 mr_nvme_pg_size; + u64 max_prp_io; instance = (struct megasas_instance *)sdev->host->hostdata; mr_nvme_pg_size = max_t(u32, instance->nvme_page_size, MR_DEFAULT_NVME_PAGE_SIZE); - lim->max_hw_sectors = max_io_size / 512; + /* + * megasas_make_prp_nvme() builds the PRP list in cmd->sg_frame without + * bounding it against that buffer, and spends one entry per page of + * it on the chain pointer. Cap the transfer at what the buffer holds, + * less one page for lists that start off a page boundary. + */ + max_prp_io = (u64)((instance->max_chain_frame_sz / sizeof(u64)) - + (instance->max_chain_frame_sz / mr_nvme_pg_size) - 1) * + mr_nvme_pg_size; + + lim->max_hw_sectors = min_t(u64, max_io_size, max_prp_io) >> SECTOR_SHIFT; lim->virt_boundary_mask = mr_nvme_pg_size - 1; } From b94cec5761d22624d109d859467d7d4ce0a1b88b Mon Sep 17 00:00:00 2001 From: Andy Chiu Date: Tue, 1 Sep 2026 14:23:32 -0500 Subject: [PATCH 0478/1198] riscv: skip software algning code for HAVE_EFFICIENT_UNALIGNED_ACCESS We can jump straight into the copy loop if the kernel is compiled for a hardware that natively supports misaligned access. The user copy bandwidth improvement on K3 and Ascaolon is shown as below: Misaligned user copy, size: 512B (offset: [0:15] except 0, 8) BW Improvement | Write | Read | K3 | 6.19% | 3.43% | Ascalon | 10.0% | 11.4% | Aligned user copy, size: 512B (offset: 0, 8) BW Improvement | Write | Read | K3 | 1.69% | 0.90% | Ascalon | 1.25% | 3.32% | Suggested-by: Anton Blanchard Signed-off-by: Andy Chiu Link: https://patch.msgid.link/20260901192334.3543340-1-tchiu@tenstorrent.com Signed-off-by: Paul Walmsley --- arch/riscv/lib/uaccess.S | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S index 4efea1b3326c..cf8586a937de 100644 --- a/arch/riscv/lib/uaccess.S +++ b/arch/riscv/lib/uaccess.S @@ -76,6 +76,7 @@ SYM_FUNC_START(fallback_scalar_usercopy_sum_enabled) li a3, 9*SZREG-1 /* size must >= (word_copy stride + SZREG-1) */ bltu a2, a3, .Lbyte_copy_tail +#if !defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) /* * Copy first bytes until dst is aligned to word boundary. * a0 - start of dst @@ -103,7 +104,7 @@ SYM_FUNC_START(fallback_scalar_usercopy_sum_enabled) /* a1 - start of src */ andi a3, a1, SZREG-1 bnez a3, .Lshift_copy - +#endif .Lword_copy: /* * Both src and dst are aligned, unrolled word copy @@ -137,6 +138,7 @@ SYM_FUNC_START(fallback_scalar_usercopy_sum_enabled) addi t0, t0, 8*SZREG /* revert to original value */ j .Lbyte_copy_tail +#if !defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) .Lshift_copy: /* @@ -189,6 +191,7 @@ SYM_FUNC_START(fallback_scalar_usercopy_sum_enabled) /* Revert src to original unaligned value */ add a1, a1, a3 +#endif .Lbyte_copy_tail: /* From e3e4f66cc4b72333d0886ae2673c360248987889 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Mon, 31 Aug 2026 18:36:09 -0700 Subject: [PATCH 0479/1198] bpf: backtracking shouldn't clear outer frame R1-R5 for callbacks When processing calls to bpf_loop() verifier marks R1 (and R4) as precise. R1 tracks loop iterations number and because of the 'callback_depth < R1' mechanics in check_helper_call() must be marked precise. However, precision propagation for R1 was broken, when bpf_loop() call was verified on a second iteration. Consider the following verification trace: - main: bpf_loop(nr_loops, callback ...) - callback: BPF_EXIT - main: bpf_loop(nr_loops, callback ...) - ... While the first visit of the call to bpf_loop() propagated R1 precision as expected, the second call to mark_chain_precision() in the check_helper_call() set R1, but it was immediately reset when backtrack_insn() processed preceding BPF_EXIT in the loop deleted in this patch. Because of that, the second visit of the call to bpf_loop() injected checkpoint with R1 not marked as precise. Which could trick the verifier into accepting unsafe programs. See the next patch for an example of such program. Commit is structured in a way to minimize conflicts when 'bpf' would be eventually merged with 'bpf-next'. Fixes: ab5cfac139ab ("bpf: verify callbacks as if they are called unknown number of times") Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260831-bug-015-backtrack-cb-args-precise-v1-1-68a8e2a821e0@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/backtrack.c | 39 ++++++++++++++++++--------------------- 1 file changed, 18 insertions(+), 21 deletions(-) diff --git a/kernel/bpf/backtrack.c b/kernel/bpf/backtrack.c index eaf7438b9ebf..47282ffeeaf9 100644 --- a/kernel/bpf/backtrack.c +++ b/kernel/bpf/backtrack.c @@ -520,24 +520,7 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, return -EFAULT; } } else if (opcode == BPF_EXIT) { - bool r0_precise; - - /* Backtracking to a nested function call, 'idx' is a part of - * the inner frame 'subseq_idx' is a part of the outer frame. - * In case of a regular function call, instructions giving - * precision to registers R1-R5 should have been found already. - * In case of a callback, it is ok to have R1-R5 marked for - * backtracking, as these registers are set by the function - * invoking callback. - */ - if (subseq_idx >= 0 && bpf_calls_callback(env, subseq_idx)) - for (i = BPF_REG_1; i <= BPF_REG_5; i++) - bt_clear_reg(bt, i); - if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) { - verifier_bug(env, "backtracking exit unexpected regs %x", - bt_reg_mask(bt)); - return -EFAULT; - } + bool from_subprog_call, r0_precise; /* BPF_EXIT in subprog or callback always returns * right after the call instruction, so by checking @@ -547,9 +530,23 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, * case, we need to propagate r0 precision, if * necessary. In the former we never do that. */ - r0_precise = subseq_idx - 1 >= 0 && - bpf_pseudo_call(&env->prog->insnsi[subseq_idx - 1]) && - bt_is_reg_set(bt, BPF_REG_0); + from_subprog_call = subseq_idx - 1 >= 0 && + bpf_pseudo_call(&env->prog->insnsi[subseq_idx - 1]); + + r0_precise = from_subprog_call && bt_is_reg_set(bt, BPF_REG_0); + + /* Backtracking to a nested function call, 'idx' is a part of + * the inner frame 'subseq_idx' is a part of the outer frame. + * In case of a regular function call, instructions giving + * precision to registers R1-R5 should have been found already. + * In case of a callback from bpf_loop(), R{1,4} in the calling + * frame would be set as precise and that is correct. + */ + if (from_subprog_call && (bt_reg_mask(bt) & BPF_REGMASK_ARGS)) { + verifier_bug(env, "backtracking exit unexpected regs %x", + bt_reg_mask(bt)); + return -EFAULT; + } bt_clear_reg(bt, BPF_REG_0); if (bt_subprog_enter(bt)) From 7ac9662189069914a088ec61ad85dc46b5cb1563 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Mon, 31 Aug 2026 18:36:10 -0700 Subject: [PATCH 0480/1198] selftests/bpf: test case for unsafe pruning of bpf_loop checkpoints The following BPF program was erroneously accepted by the verifier: static int cb(int i, __u64 *ctx) { /* unsafe on a second iteration */ small_arr[*ctx] = i; *ctx = 100500; return 0; } int main(void *ctx) { int nr_loops = 1; u64 ctx = 0; if (unlikely(bpf_get_prandom_u32() == 42)) nr_loops = 2; bpf_loop(nr_loops, cb, &ctx, 0); return 0; } The branch with nr_loops == 1 was explored first and injected a checkpoint at the entry to 'cb', such that nr_loops in the main's frame was not marked as precise. This checkpoint pruned the state with nr_loops == 2 and the program was accepted. This test case corresponds to the program above. Entry point is written in assembly to ensure branch processing order. Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260831-bug-015-backtrack-cb-args-precise-v1-2-68a8e2a821e0@gmail.com Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/progs/iters.c | 39 +++++++++++++++++++++++ 1 file changed, 39 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c index 62d7df9e80be..c6699159dacd 100644 --- a/tools/testing/selftests/bpf/progs/iters.c +++ b/tools/testing/selftests/bpf/progs/iters.c @@ -2149,4 +2149,43 @@ __naked int stack_misc_vs_scalar_in_a_loop(void) ); } +__used +static int loop_cb5(int i, __u64 *ctx) +{ + /* unsafe on a second iteration */ + small_arr[*ctx] = i; + *ctx = 100500; + return 0; +} + +SEC("raw_tp") +__flag(BPF_F_TEST_STATE_FREQ) +__failure __msg("memory access is {{.*}} and is outside of the object of size 64") +__naked void loop_counter_precision_2nd_iter(void) +{ + asm volatile ( + "call %[bpf_get_prandom_u32];" + "*(u64 *)(r10 - 8) = 0;" + "r1 = 2;" + "if r0 == 42 goto +1;" + "r1 = 1;" + "r2 = loop_cb5 ll;" + "r3 = r10;" + "r3 += -8;" + "r4 = 0;" + /* + * Explore with nr_loops=1 on a first path and nr_loops=2 on a second path. + * Buggy verifier did not propagate r1 precision properly, + * and thus checkpoints created for nr_loops=1 case matched nr_loops=2 case. + */ + "call %[bpf_loop];" + "r0 = 0;" + "exit;" + : + : __imm(bpf_loop), + __imm(bpf_get_prandom_u32) + : __clobber_all + ); +} + char _license[] SEC("license") = "GPL"; From e6142a8bfc230c7263eb8b0475249c958ce49367 Mon Sep 17 00:00:00 2001 From: Diego Oliva Date: Wed, 2 Sep 2026 11:42:06 +0100 Subject: [PATCH 0481/1198] smb: client: reject short READ responses in CIFSSMBRead() CIFSSMBRead() reads DataLengthHigh, DataLength and DataOffset out of the READ_RSP returned by the server without first checking that a whole READ_RSP was actually received. The length of the response is recorded in rsp_iov.iov_len, but nothing constrains it to be at least read_rsp_size before those fields are dereferenced. A malicious or compromised SMB1 server can return a response shorter than the READ_RSP header, so that parsing the header itself reads past the end of the receive buffer. SMB1 is not negotiated by default; reaching this code requires an explicit vers=1.0 mount. Reject the response unless it is at least read_rsp_size bytes long. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Suggested-by: Paulo Alcantara Cc: stable@vger.kernel.org # 6.19.x Assisted-by: Bynario AI Signed-off-by: Diego Oliva Reviewed-by: David Howells Signed-off-by: Paulo Alcantara --- fs/smb/client/cifssmb.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index f8aa9e7b4bc6..be13ab37039d 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -1719,6 +1719,14 @@ CIFSSMBRead(const unsigned int xid, struct cifs_io_parms *io_parms, pSMBr = (READ_RSP *)rsp_iov.iov_base; if (rc) { cifs_dbg(VFS, "Send error in read = %d\n", rc); + } else if (rsp_iov.iov_len < tcon->ses->server->vals->read_rsp_size) { + /* check that the received response can hold a whole READ_RSP */ + cifs_dbg(FYI, "%s: server returned short header. got=%zu expected=%zu\n", + __func__, rsp_iov.iov_len, + tcon->ses->server->vals->read_rsp_size); + rc = smb_EIO2(smb_eio_trace_read_rsp_short, + rsp_iov.iov_len, tcon->ses->server->vals->read_rsp_size); + *nbytes = 0; } else { int data_length = le16_to_cpu(pSMBr->DataLengthHigh); data_length = data_length << 16; From c3080b58d81d3699cbf4dfd5ba860630fca96f4a Mon Sep 17 00:00:00 2001 From: Melissa Wen Date: Wed, 26 Aug 2026 12:37:05 +0200 Subject: [PATCH 0482/1198] drm/atomic-state-helper: set pixel_blend_mode to prop default on reset MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In __drm_atomic_helper_plane_state_init(), pixel_blend_mode is always reset to DRM_MODE_BLEND_PREMULTI. That was consistent while drm_plane_create_blend_mode_property() required PREMULTI in the supported modes, but it now falls back to COVERAGE or PIXEL_NONE when the driver doesn't support PREMULTI. The hardcoded default may therefore not be a blend mode the hardware can do, nor one the property advertises. Initialize pixel_blend_mode from the blend mode property default instead, keeping DRM_MODE_BLEND_PREMULTI for planes without the property. Fixes: 9813e158d13d ("drm/drm_blend: allow blend mode property without PREMULTI") Tested-by: Mikhail Gavrilov Tested-by: Dan Wheeler Reviewed-by: Timur Kristóf Reviewed-by: Alex Hung Reviewed-by: Leandro Ribeiro Signed-off-by: Melissa Wen Link: https://patch.msgid.link/20260826104143.39077-2-mwen@igalia.com --- drivers/gpu/drm/drm_atomic_state_helper.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/gpu/drm/drm_atomic_state_helper.c b/drivers/gpu/drm/drm_atomic_state_helper.c index d90d1d7c9cf9..a2ef272e9f27 100644 --- a/drivers/gpu/drm/drm_atomic_state_helper.c +++ b/drivers/gpu/drm/drm_atomic_state_helper.c @@ -278,7 +278,14 @@ void __drm_atomic_helper_plane_state_init(struct drm_plane_state *plane_state, plane_state->rotation = DRM_MODE_ROTATE_0; plane_state->alpha = DRM_BLEND_ALPHA_OPAQUE; + plane_state->pixel_blend_mode = DRM_MODE_BLEND_PREMULTI; + if (plane->blend_mode_property) { + if (!drm_object_property_get_default_value(&plane->base, + plane->blend_mode_property, + &val)) + plane_state->pixel_blend_mode = val; + } if (plane->color_encoding_property) { if (!drm_object_property_get_default_value(&plane->base, From f0c75da0a6b4084e00cd6faefebcc976ffaccf52 Mon Sep 17 00:00:00 2001 From: Melissa Wen Date: Wed, 26 Aug 2026 12:37:06 +0200 Subject: [PATCH 0483/1198] drm/amd/display: fix missing blend-mode-prop warning for DCN MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit validate_blend_mode_for_alpha_formats() warns when a plane supports formats with alpha but doesn't expose the blend mode property. Fix this by adding the same overlay plane blend modes to primary plane, since they are all universal planes in DCN-generation. Cursor planes support ARGB8888 format and CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA is set by default (other color formats are not implemented), so only expose support to PREMULTI, which is the default blend mode on DRM. Fixes: 860e748bddcc ("drm: ensure blend mode supported if pixel format with alpha exposed") Tested-by: Mikhail Gavrilov Tested-by: Dan Wheeler Reviewed-by: Timur Kristóf Reviewed-by: Alex Hung Reviewed-by: Leandro Ribeiro Signed-off-by: Melissa Wen Link: https://patch.msgid.link/20260826104143.39077-3-mwen@igalia.com --- .../amd/display/amdgpu_dm/amdgpu_dm_plane.c | 21 ++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c index 824ef3ce5de0..423e3cd7b9c9 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c @@ -2208,16 +2208,31 @@ int amdgpu_dm_plane_init(struct amdgpu_display_manager *dm, if (res) return res; - if (plane->type == DRM_PLANE_TYPE_OVERLAY && - plane_cap && plane_cap->per_pixel_alpha) { + /* TODO: Check which blend modes are supported in DCE-generation + * planes, i.e. DC_PLANE_TYPE_DCE_RGB/UNDERLAY and expose blend mode + * property accordingly. + */ + if ((plane->type == DRM_PLANE_TYPE_OVERLAY || + plane->type == DRM_PLANE_TYPE_PRIMARY) && + plane_cap && plane_cap->per_pixel_alpha && + plane_cap->type == DC_PLANE_TYPE_DCN_UNIVERSAL) { unsigned int blend_caps = BIT(DRM_MODE_BLEND_PIXEL_NONE) | BIT(DRM_MODE_BLEND_PREMULTI) | BIT(DRM_MODE_BLEND_COVERAGE); - drm_plane_create_alpha_property(plane); drm_plane_create_blend_mode_property(plane, blend_caps); + + if (plane->type == DRM_PLANE_TYPE_OVERLAY) + drm_plane_create_alpha_property(plane); } + /* Cursor color format is set to CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA + * by default, so only advertise DRM_MODE_BLEND_PREMULTI blend mode for + * this type of plane. + */ + if (plane->type == DRM_PLANE_TYPE_CURSOR) + drm_plane_create_blend_mode_property(plane, BIT(DRM_MODE_BLEND_PREMULTI)); + if (plane->type == DRM_PLANE_TYPE_PRIMARY) { /* * Allow OVERLAY planes to be used as underlays by assigning an From 332ad707e38fb82dd998b4d0782c15579e5784f1 Mon Sep 17 00:00:00 2001 From: Melissa Wen Date: Wed, 26 Aug 2026 12:37:07 +0200 Subject: [PATCH 0484/1198] drm/amd/display: advertise PIXEL_NONE and PREMULTI blend mode for DCE MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit DCE can support PREMULTI and COVERAGE blend mode depending on its generation, however current driver implementation either doesn't expose more than primary and cursor plane, or doesn't program registers for any blend mode other than PIXEL_NONE. To fix the missing-blend-mode-prop warning according to current DCE plane caps, create blend mode property with PIXEL_NONE and PREMULTI for primary planes. As long as the background is black and there is no overlay plane, PIXEL_NONE and PREMULTI are equivalent, and PREMULTI has been the mandatory/default mode for years, so keep it to avoid regressions. Fixes: 860e748bddcc ("drm: ensure blend mode supported if pixel format with alpha exposed") Tested-by: Viktor Jägersküpper Tested-by: Dan Wheeler #v3 Reviewed-by: Timur Kristóf Reviewed-by: Alex Hung Reviewed-by: Leandro Ribeiro #v2 Signed-off-by: Melissa Wen Link: https://patch.msgid.link/20260826104143.39077-4-mwen@igalia.com --- .../amd/display/amdgpu_dm/amdgpu_dm_plane.c | 24 +++++++++++++------ 1 file changed, 17 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c index 423e3cd7b9c9..e13b96358208 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c @@ -2208,14 +2208,24 @@ int amdgpu_dm_plane_init(struct amdgpu_display_manager *dm, if (res) return res; - /* TODO: Check which blend modes are supported in DCE-generation - * planes, i.e. DC_PLANE_TYPE_DCE_RGB/UNDERLAY and expose blend mode - * property accordingly. + /* Blend mode support varies on DCE generations according to HW caps + * and number of planes per CRTC. However, as current driver + * implementation only creates one primary and one cursor plane per + * CRTC for DCE (overlay is only created if + * DC_PLANE_TYPE_DCN_UNIVERSAL), the primary plane blend mode is + * ignored across DCE versions. Keep PREMULTI to avoid uAPI + * regressions: it was the default/mandatory mode for many years and, + * with no overlay plane, primary composes on top of a black + * background, where PREMULTI and PIXEL_NONE are equivalent. */ - if ((plane->type == DRM_PLANE_TYPE_OVERLAY || - plane->type == DRM_PLANE_TYPE_PRIMARY) && - plane_cap && plane_cap->per_pixel_alpha && - plane_cap->type == DC_PLANE_TYPE_DCN_UNIVERSAL) { + if (plane_cap && plane_cap->type != DC_PLANE_TYPE_DCN_UNIVERSAL) { + unsigned int blend_caps = BIT(DRM_MODE_BLEND_PIXEL_NONE) | + BIT(DRM_MODE_BLEND_PREMULTI); + + drm_plane_create_blend_mode_property(plane, blend_caps); + } else if ((plane->type == DRM_PLANE_TYPE_OVERLAY || + plane->type == DRM_PLANE_TYPE_PRIMARY) && + plane_cap && plane_cap->per_pixel_alpha) { unsigned int blend_caps = BIT(DRM_MODE_BLEND_PIXEL_NONE) | BIT(DRM_MODE_BLEND_PREMULTI) | BIT(DRM_MODE_BLEND_COVERAGE); From f2951ebd15c36a1ea4820a7f0cbb0b5f1c028b73 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 2 Sep 2026 12:19:18 -0400 Subject: [PATCH 0485/1198] tracing: Take trace_array reference when opening options file The options files do not take the trace_array reference for the options they represent. This could cause a use-after-free kernel crash if one of these files is opened by one task and another task removes the instance that the option is for. Because it doesn't take a reference upon opening, it will not stop the removal which will free the options descriptor that is being used. As the options are somewhat dynamic in their creation at boot up, each file represents a flag in the trace_array. The trace_array has an array of indexes to represent each of these flags that is stored in the trace_flags_index array. The address of the index array element is used to pass to the inode->i_private pointer. Then that element is read which holds the index (which represents the flag) and then the index is used to calculate the trace_array descriptor from its trace_flags_index array. One issue is that the index element can not be referenced until the trace_array's reference is taken. To handle this, create a new helper function called: trace_array_options_get() that will iterate all the existing trace_arrays in the ftrace_trace_arrays list (under the trace_types_lock), and compare the passed in address of the index element with the entire array of the trace_array's trace_flags_index array. If it matches, then up the corresponding trace_array's reference and return. Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260902121918.5a9e9d1b@gandalf.local.home Fixes: 577b785f55168 ("tracing: add tracer dependent options to options directory") Reported-by: sashiko-bot@kernel.org Closes: https://lore.kernel.org/linux-trace-kernel/20260828135858.2AC501F000E9@smtp.kernel.org/ Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 67 +++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 63 insertions(+), 4 deletions(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a946e0183fd1..722d0ba2d233 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -7842,11 +7842,70 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt, return cnt; } +/* + * The tr_index is the address of a trace_array->trace_flags_index[] + * element that holds the index of the trace flag. But since the + * trace_array reference has not been taken yet, it cannot be referenced + * as it could have been freed by a rmdir of the instance the trace_array + * represents. + * + * Search the list of trace_arrays and compare the tr_index to the + * address of the entire trace_array trace_flags_index array for each + * trace_array in the list. If one is matched, then take the reference + * and return it. If not, the trace_array no longer exits. + */ +static int trace_array_options_get(void *tr_index) +{ + struct trace_array *tr; + int ret; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + + if (tracing_disabled) + return -ENODEV; + + guard(mutex)(&trace_types_lock); + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + if (tr_index >= (void *)&tr->trace_flags_index[0] && + tr_index < (void *)&tr->trace_flags_index[TRACE_FLAGS_MAX_SIZE]) + return __trace_array_get(tr); + } + return -ENODEV; +} + +static int trace_options_open(struct inode *inode, struct file *filp) +{ + void *tr_index = inode->i_private; + + if (trace_array_options_get(tr_index) < 0) + return -ENODEV; + + filp->private_data = tr_index; + + return 0; +} + +static int trace_options_release(struct inode *inode, struct file *filp) +{ + void *tr_index = filp->private_data; + struct trace_array *tr; + unsigned int index; + + get_tr_index(tr_index, &tr, &index); + + trace_array_put(tr); + + return 0; +} + static const struct file_operations trace_options_core_fops = { - .open = tracing_open_generic, - .read = trace_options_core_read, - .write = trace_options_core_write, - .llseek = generic_file_llseek, + .open = trace_options_open, + .read = trace_options_core_read, + .write = trace_options_core_write, + .llseek = generic_file_llseek, + .release = trace_options_release, }; struct dentry *trace_create_file(const char *name, From 9e6372ec2a3990662ae0a67f56ac0aee19848d5b Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Tue, 1 Sep 2026 23:35:03 -0700 Subject: [PATCH 0486/1198] drm/pagemap: dma-unmap pages before handling migration errors drm_pagemap_migrate_unmap_pages() relies on the pages array to determine which pages require DMA unmapping. However, drm_pagemap_migration_unlock_put_pages() clears the array as part of its cleanup, leaving drm_pagemap_migrate_unmap_pages() with no valid page information if it is called afterward. Call drm_pagemap_migrate_unmap_pages() before drm_pagemap_migration_unlock_put_pages() so the pages array remains valid during DMA unmapping. Reported-by: Sashiko Fixes: f86ad0ed620c ("drm/gpusvm, drm/pagemap: Move migration functionality to drm_pagemap") Cc: stable@vger.kernel.org Signed-off-by: Matthew Brost Reviewed-by: Himal Prasad Ghimiray Link: https://patch.msgid.link/20260902063504.3024362-1-matthew.brost@intel.com --- drivers/gpu/drm/drm_pagemap.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/drm_pagemap.c b/drivers/gpu/drm/drm_pagemap.c index 097a900cf55d..6aa745682270 100644 --- a/drivers/gpu/drm/drm_pagemap.c +++ b/drivers/gpu/drm/drm_pagemap.c @@ -1283,13 +1283,13 @@ int drm_pagemap_evict_to_ram(struct drm_pagemap_devmem *devmem_allocation) goto err_finalize; err_finalize: + drm_pagemap_migrate_unmap_pages(devmem_allocation->dev, pagemap_addr, dst, npages, + DMA_FROM_DEVICE, &state); if (err) drm_pagemap_migration_unlock_put_pages(npages, dst); migrate_device_pages(src, dst, npages); drm_pagemap_retire_migrated_pages(src, npages); migrate_device_finalize(src, dst, npages); - drm_pagemap_migrate_unmap_pages(devmem_allocation->dev, pagemap_addr, dst, npages, - DMA_FROM_DEVICE, &state); err_free: kvfree(buf); @@ -1416,15 +1416,15 @@ static int __drm_pagemap_migrate_to_ram(struct vm_area_struct *vas, goto err_finalize; err_finalize: + if (dev) + drm_pagemap_migrate_unmap_pages(dev, pagemap_addr, migrate.dst, + npages, DMA_FROM_DEVICE, + &state); if (err) drm_pagemap_migration_unlock_put_pages(npages, migrate.dst); migrate_vma_pages(&migrate); drm_pagemap_retire_migrated_pages(migrate.src, npages); migrate_vma_finalize(&migrate); - if (dev) - drm_pagemap_migrate_unmap_pages(dev, pagemap_addr, migrate.dst, - npages, DMA_FROM_DEVICE, - &state); err_free: kvfree(buf); err_out: From df72e55e754c8d449321ddddad19a8bd3cb8d032 Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Tue, 1 Sep 2026 23:35:04 -0700 Subject: [PATCH 0487/1198] drm/pagemap: Fix folio allocation fallback and use-after-put drm_pagemap_migrate_populate_ram_pfn() had two issues when populating RAM PFNs with higher-order folios: 1. The higher-order vma_alloc_folio()/folio_alloc() calls did not pass __GFP_NOWARN, so a THP allocation failure under memory pressure would spam the kernel log, and there was no fallback path despite a TODO comment stating one was needed. Add __GFP_NOWARN to the higher-order allocation and, on failure, fall back to order-0 allocations for the entire range originally covered by the failed higher-order allocation, leaving MIGRATE_PFN_COMPOUND unset for those PFNs. 2. In the free_pages error path, order was computed via folio_order(page_folio(page)) *after* put_page(page) had already dropped the reference, resulting in a use-after-free/put when that was the last reference on the page. Compute order before releasing the page. Introducing the fallback in 1. also requires the source page array handed to ->copy_to_ram() to be built differently. Both callers only populated the entry at the head of each source folio, relying on the copy callback to derive the rest of the folio from the order recorded in the matching drm_pagemap_addr. Once the destination has been demoted to order-0 folios the drm_pagemap_addr entries are per-page, so a source page is needed for every one of them; leaving them NULL makes the copy callback stop after the first page and the remainder of the range is never copied. The source folio is only split later, by migrate_vma_pages() / migrate_device_pages(), so its order cannot be used to detect the demotion - test the destination for MIGRATE_PFN_COMPOUND instead. Factor the array population out into drm_pagemap_migrate_populate_src_pages() and use it from both drm_pagemap_evict_to_ram() and __drm_pagemap_migrate_to_ram(). Fixes: ddeda6136038 ("drm/pagemap: Allocate folios when possible") Cc: stable@vger.kernel.org Assisted-by: GitHub_Copilot:claude-opus-5 Signed-off-by: Matthew Brost Reviewed-by: Himal Prasad Ghimiray Link: https://patch.msgid.link/20260902063504.3024362-2-matthew.brost@intel.com --- drivers/gpu/drm/drm_pagemap.c | 128 +++++++++++++++++++++++++++------- 1 file changed, 103 insertions(+), 25 deletions(-) diff --git a/drivers/gpu/drm/drm_pagemap.c b/drivers/gpu/drm/drm_pagemap.c index 6aa745682270..a0546955d0b9 100644 --- a/drivers/gpu/drm/drm_pagemap.c +++ b/drivers/gpu/drm/drm_pagemap.c @@ -383,6 +383,58 @@ drm_pagemap_migrate_map_system_pages(struct device *dev, return 0; } +/** + * drm_pagemap_migrate_populate_src_pages() - Populate the source page array + * @pages: Array of source pages to populate + * @src_mpfn: Source array of migrate PFNs + * @dst_mpfn: Destination array of migrate PFNs + * @npages: Number of pages in the arrays + * + * Populate @pages with the device pages the copy callback is to read from. + * + * Entries are normally only populated at the head of each source folio, with + * the copy callback deriving the rest of the folio from the order recorded in + * the corresponding drm_pagemap_addr. That does not work where + * drm_pagemap_migrate_populate_ram_pfn() had to demote a higher-order source + * folio to order-0 destination folios: the drm_pagemap_addr entries are then + * per-page, and the copy callback needs a source page for each of them. + * Populate every entry for those ranges. + * + * Note that the source folio itself is only split later, by + * migrate_vma_pages() / migrate_device_pages(), so its order cannot be used to + * detect the demotion - the destination has to be inspected instead. + */ +static void drm_pagemap_migrate_populate_src_pages(struct page **pages, + unsigned long *src_mpfn, + unsigned long *dst_mpfn, + unsigned long npages) +{ + unsigned long i; + + for (i = 0; i < npages;) { + struct page *page = migrate_pfn_to_page(src_mpfn[i]); + unsigned int order = 0; + unsigned long j, nr; + + if (!page) { + i++; + continue; + } + + order = folio_order(page_folio(page)); + nr = NR_PAGES(order); + + if (order && !(dst_mpfn[i] & MIGRATE_PFN_COMPOUND)) { + for (j = 0; j < nr && i + j < npages; j++) + pages[i + j] = folio_page(page_folio(page), j); + } else { + pages[i] = page; + } + + i += nr; + } +} + /** * drm_pagemap_migrate_unmap_pages() - Unmap pages previously mapped for GPU SVM migration * @dev: The device for which the pages were mapped @@ -875,6 +927,7 @@ static int drm_pagemap_migrate_populate_ram_pfn(struct vm_area_struct *vas, struct page *page = NULL, *src_page; struct folio *folio; unsigned int order = 0; + gfp_t gfp = GFP_HIGHUSER; if (!(src_mpfn[i] & MIGRATE_PFN_MIGRATE)) goto next; @@ -891,11 +944,51 @@ static int drm_pagemap_migrate_populate_ram_pfn(struct vm_area_struct *vas, order = folio_order(page_folio(src_page)); - /* TODO: Support fallback to single pages if THP allocation fails */ + /* + * A large source folio is always collected whole, at its head + * page, PMD aligned and flagged MIGRATE_PFN_COMPOUND: anything + * else is split before it reaches us, either by + * migrate_vma_collect_pmd() or, for the eviction path, by + * migrate_device_pfns(). Both the order-0 fallback below and + * drm_pagemap_migrate_populate_src_pages() rely on that, as + * they index the folio from @i. + */ + WARN_ON_ONCE(order && + (src_page != folio_page(page_folio(src_page), 0) || + !(src_mpfn[i] & MIGRATE_PFN_COMPOUND))); + + if (order) + gfp |= __GFP_NOWARN; + if (vas) - folio = vma_alloc_folio(GFP_HIGHUSER, order, vas, addr); + folio = vma_alloc_folio(gfp, order, vas, addr); else - folio = folio_alloc(GFP_HIGHUSER, order); + folio = folio_alloc(gfp, order); + + if (!folio && order) { + /* + * Higher-order allocation failed, fall back to + * order-0 allocations for the entire range covered + * by the original higher-order allocation, without + * setting MIGRATE_PFN_COMPOUND, until we move past + * that range. + */ + unsigned long nr = NR_PAGES(order); + unsigned long j; + + gfp &= ~__GFP_NOWARN; + for (j = 0; j < nr && i < npages; j++, i++, addr += PAGE_SIZE) { + folio = vas ? + vma_alloc_folio(gfp, 0, vas, addr) : + folio_alloc(gfp, 0); + if (!folio) + goto free_pages; + + page = folio_page(folio, 0); + mpfn[i] = migrate_pfn(page_to_pfn(page)); + } + continue; + } if (!folio) goto free_pages; @@ -940,11 +1033,11 @@ static int drm_pagemap_migrate_populate_ram_pfn(struct vm_area_struct *vas, if (!page) goto next_put; + order = folio_order(page_folio(page)); + put_page(page); mpfn[i] = 0; - order = folio_order(page_folio(page)); - next_put: i += NR_PAGES(order); } @@ -1225,7 +1318,7 @@ int drm_pagemap_evict_to_ram(struct drm_pagemap_devmem *devmem_allocation) unsigned long *src, *dst; struct drm_pagemap_addr *pagemap_addr; void *buf; - int i, err = 0; + int err = 0; unsigned int retry_count = 2; npages = devmem_allocation->size >> PAGE_SHIFT; @@ -1268,15 +1361,7 @@ int drm_pagemap_evict_to_ram(struct drm_pagemap_devmem *devmem_allocation) if (err) goto err_finalize; - for (i = 0; i < npages;) { - unsigned int order = 0; - - pages[i] = migrate_pfn_to_page(src[i]); - if (pages[i]) - order = folio_order(page_folio(pages[i])); - - i += NR_PAGES(order); - } + drm_pagemap_migrate_populate_src_pages(pages, src, dst, npages); err = ops->copy_to_ram(pages, pagemap_addr, npages, NULL); if (err) @@ -1344,7 +1429,7 @@ static int __drm_pagemap_migrate_to_ram(struct vm_area_struct *vas, struct drm_pagemap_addr *pagemap_addr; unsigned long start, end; void *buf; - int i, err = 0; + int err = 0; zdd = drm_pagemap_page_zone_device_data(page); if (time_before64(get_jiffies_64(), zdd->devmem_allocation->timeslice_expiration)) @@ -1401,15 +1486,8 @@ static int __drm_pagemap_migrate_to_ram(struct vm_area_struct *vas, if (err) goto err_finalize; - for (i = 0; i < npages;) { - unsigned int order = 0; - - pages[i] = migrate_pfn_to_page(migrate.src[i]); - if (pages[i]) - order = folio_order(page_folio(pages[i])); - - i += NR_PAGES(order); - } + drm_pagemap_migrate_populate_src_pages(pages, migrate.src, migrate.dst, + npages); err = ops->copy_to_ram(pages, pagemap_addr, npages, NULL); if (err) From 33ce0aa4c57611c3a3485ec7c01ad67b3751447d Mon Sep 17 00:00:00 2001 From: "James C. Owens" Date: Fri, 14 Aug 2026 12:24:05 -0400 Subject: [PATCH 0488/1198] btrfs: scrub: report the failing sector's address, not the stripe base scrub_stripe_report_errors() iterates over the sectors of a stripe, but every message it emits passes stripe->logical, the address of the first sector of the 64KiB stripe, rather than the address of the sector being reported. The physical address is likewise computed once, before the loop, from stripe->logical. This matters because scrub_print_common_warning() uses that logical address for the backref walk which produces the "root %llu inode %llu offset %llu ... (path: ...)" part of the message. As the address is always the stripe base, the reported root/inode/offset/path can identify a different file from the one whose sector actually failed. A 64KiB stripe routinely spans several extents belonging to unrelated files. On the machine where this was found, the stripe at logical 0x17D9380000 holds four sectors of /usr/share/plasma/emoji/bg.dict, then a file inside a docker volume, then sectors referenced only by snapshots. Every error anywhere in that stripe is attributed to bg.dict. The effect is visible statistically: across ten months and four kernel series that machine logged 81 distinct flagged logical addresses, and every one of them is exactly 64KiB aligned. Since BTRFS_STRIPE_LEN is 64KiB and stripe->logical is stripe aligned by construction, real failures distributed across sectors could not produce that. Report the address of the sector actually being examined. Adding the sector offset to the physical address is valid because BTRFS_STRIPE_LEN is the unit contiguous on a single device for every profile, so a stripe never crosses a device boundary. Fixes: 0096580713ff ("btrfs: scrub: introduce error reporting functionality for scrub_stripe") Reviewed-by: Qu Wenruo Signed-off-by: James C. Owens Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/scrub.c | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index f209e75f0ff5..c09d4213ad89 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -1023,6 +1023,10 @@ static void scrub_stripe_report_errors(struct scrub_ctx *sctx, skip: for_each_set_bit(sector_nr, &extent_bitmap, stripe->nr_sectors) { + const u64 sector_logical = stripe->logical + + ((u64)sector_nr << fs_info->sectorsize_bits); + const u64 sector_physical = physical + + ((u64)sector_nr << fs_info->sectorsize_bits); bool repaired = false; if (scrub_bitmap_test_bit_is_metadata(stripe, sector_nr)) { @@ -1051,12 +1055,12 @@ static void scrub_stripe_report_errors(struct scrub_ctx *sctx, if (dev) { btrfs_err_rl(fs_info, "scrub: fixed up error at logical %llu on dev %s physical %llu", - stripe->logical, btrfs_dev_name(dev), - physical); + sector_logical, btrfs_dev_name(dev), + sector_physical); } else { btrfs_err_rl(fs_info, "scrub: fixed up error at logical %llu on mirror %u", - stripe->logical, stripe->mirror_num); + sector_logical, stripe->mirror_num); } continue; } @@ -1065,30 +1069,30 @@ static void scrub_stripe_report_errors(struct scrub_ctx *sctx, if (dev) { btrfs_err_rl(fs_info, "scrub: unable to fixup (regular) error at logical %llu on dev %s physical %llu", - stripe->logical, btrfs_dev_name(dev), - physical); + sector_logical, btrfs_dev_name(dev), + sector_physical); } else { btrfs_err_rl(fs_info, "scrub: unable to fixup (regular) error at logical %llu on mirror %u", - stripe->logical, stripe->mirror_num); + sector_logical, stripe->mirror_num); } if (scrub_bitmap_test_bit_io_error(stripe, sector_nr)) if (__ratelimit(&rs) && dev) scrub_print_common_warning("i/o error", dev, false, - stripe->logical, physical); + sector_logical, sector_physical); if (scrub_bitmap_test_bit_csum_error(stripe, sector_nr)) if (__ratelimit(&rs) && dev) scrub_print_common_warning("checksum error", dev, false, - stripe->logical, physical); + sector_logical, sector_physical); if (scrub_bitmap_test_bit_meta_error(stripe, sector_nr)) if (__ratelimit(&rs) && dev) scrub_print_common_warning("header error", dev, false, - stripe->logical, physical); + sector_logical, sector_physical); if (scrub_bitmap_test_bit_meta_gen_error(stripe, sector_nr)) if (__ratelimit(&rs) && dev) scrub_print_common_warning("generation error", dev, false, - stripe->logical, physical); + sector_logical, sector_physical); } /* Update the device stats. */ From a8813a923f9e43f788b357fb55c35f7f6ed6f98c Mon Sep 17 00:00:00 2001 From: Shuangpeng Bai Date: Sun, 16 Aug 2026 22:15:12 -0400 Subject: [PATCH 0489/1198] btrfs: fix transaction use-after-free in raid stripe insertion If allocation of a RAID stripe extent fails, btrfs_insert_one_raid_extent() aborts and ends the transaction before returning -ENOMEM. btrfs_finish_one_ordered(), the production caller through btrfs_insert_raid_extent(), still owns the transaction handle. It handles the error by aborting the transaction and then reaches the common exit path, which ends the transaction again. The premature end can free the handle and drop its transaction reference. Transaction cleanup can then free the transaction before the caller's second abort accesses the handle and transaction, resulting in use-after-free. Keep the abort at the failure site, but let the caller's common exit path end the transaction once, after it has finished using both objects. Fixes: 02c372e1f016 ("btrfs: add support for inserting raid stripe extents") Assisted-by: Codex:GPT-5 Reviewed-by: Qu Wenruo Signed-off-by: Shuangpeng Bai Signed-off-by: David Sterba --- fs/btrfs/raid-stripe-tree.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/btrfs/raid-stripe-tree.c b/fs/btrfs/raid-stripe-tree.c index b210371ce91e..89e259a47d8d 100644 --- a/fs/btrfs/raid-stripe-tree.c +++ b/fs/btrfs/raid-stripe-tree.c @@ -337,7 +337,6 @@ int btrfs_insert_one_raid_extent(struct btrfs_trans_handle *trans, stripe_extent = kzalloc(item_size, GFP_NOFS); if (unlikely(!stripe_extent)) { btrfs_abort_transaction(trans, -ENOMEM); - btrfs_end_transaction(trans); return -ENOMEM; } From afbe73778338e6d1ac8c4486fbdf33f0cc1f2624 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Mon, 17 Aug 2026 14:43:53 +0930 Subject: [PATCH 0490/1198] btrfs: fix the possible bioc_list memory leak during error There are two possible ways to leak bioc memory on btrfs_ordered_extent::bioc_list: - An error occurred for btrfs_insert_one_raid_extent() Then the function btrfs_insert_raid_extent() immediately return without freeing any bioc in the bioc_list. - An ordered extent hit an IO error In that case the ordered extent will have BTRFS_ORDERED_IOERR set, and skip the call on btrfs_insert_raid_extent() completely. Fix the problem by: - Introduce a new helper, btrfs_cleanup_ordered_bioc_list() Which will remove all bioc from the bioc_list, and release the bioc. - Call the above helper for btrfs_insert_raid_extent() So that the cleanup helper is always called no matter what. - Call the above helper for btrfs_finish_one_ordered() This is called just before the final release on the ordered extent. This was reported by Sashiko when reviewing another patch. Link: https://sashiko.dev/#/patchset/20260817021512.3010812-1-shuangpeng.kernel%40gmail.com Fixes: 02c372e1f016 ("btrfs: add support for inserting raid stripe extents") Reviewed-by: Johannes Thumshirn Signed-off-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/inode.c | 3 +++ fs/btrfs/raid-stripe-tree.c | 18 ++++++++++++------ fs/btrfs/raid-stripe-tree.h | 1 + 3 files changed, 16 insertions(+), 6 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 50c6640543b9..3668cbc7598e 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3436,6 +3436,9 @@ int btrfs_finish_one_ordered(struct btrfs_ordered_extent *ordered_extent) */ btrfs_remove_ordered_extent(ordered_extent); + /* Cleanup any remaining biocs attached to the OE. */ + btrfs_cleanup_ordered_bioc_list(ordered_extent); + /* once for us */ btrfs_put_ordered_extent(ordered_extent); /* once for the tree */ diff --git a/fs/btrfs/raid-stripe-tree.c b/fs/btrfs/raid-stripe-tree.c index 89e259a47d8d..6291775dbe0e 100644 --- a/fs/btrfs/raid-stripe-tree.c +++ b/fs/btrfs/raid-stripe-tree.c @@ -373,7 +373,7 @@ int btrfs_insert_raid_extent(struct btrfs_trans_handle *trans, struct btrfs_ordered_extent *ordered_extent) { struct btrfs_io_context *bioc; - int ret; + int ret = 0; if (!btrfs_fs_incompat(trans->fs_info, RAID_STRIPE_TREE)) return 0; @@ -381,17 +381,23 @@ int btrfs_insert_raid_extent(struct btrfs_trans_handle *trans, list_for_each_entry(bioc, &ordered_extent->bioc_list, rst_ordered_entry) { ret = btrfs_insert_one_raid_extent(trans, bioc); if (ret) - return ret; + break; } - while (!list_empty(&ordered_extent->bioc_list)) { - bioc = list_first_entry(&ordered_extent->bioc_list, + btrfs_cleanup_ordered_bioc_list(ordered_extent); + return ret; +} + +void btrfs_cleanup_ordered_bioc_list(struct btrfs_ordered_extent *ordered) +{ + while (!list_empty(&ordered->bioc_list)) { + struct btrfs_io_context *bioc; + + bioc = list_first_entry(&ordered->bioc_list, typeof(*bioc), rst_ordered_entry); list_del(&bioc->rst_ordered_entry); btrfs_put_bioc(bioc); } - - return 0; } int btrfs_get_raid_extent_offset(struct btrfs_fs_info *fs_info, diff --git a/fs/btrfs/raid-stripe-tree.h b/fs/btrfs/raid-stripe-tree.h index 69942ad43140..eb02cf48511b 100644 --- a/fs/btrfs/raid-stripe-tree.h +++ b/fs/btrfs/raid-stripe-tree.h @@ -28,6 +28,7 @@ int btrfs_get_raid_extent_offset(struct btrfs_fs_info *fs_info, u32 stripe_index, struct btrfs_io_stripe *stripe); int btrfs_insert_raid_extent(struct btrfs_trans_handle *trans, struct btrfs_ordered_extent *ordered_extent); +void btrfs_cleanup_ordered_bioc_list(struct btrfs_ordered_extent *ordered); #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS int btrfs_insert_one_raid_extent(struct btrfs_trans_handle *trans, From a03fa65184545837d6461413275da71f30527385 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Mon, 17 Aug 2026 14:43:54 +0930 Subject: [PATCH 0491/1198] btrfs: return proper negative error code for update_raid_extent_item() The function btrfs_abort_transaction() only accepts negative error code, and have the macro VERIFY_NEGATIVE_ERROR() to verify that error code. But inside update_raid_extent_item(), if there is such key found, we return 1, breaking the negative error code scheme. Furthermore if we hit some real error during the tree search, e.g. -EIO, then the error code is always over-written to -EINVAL. Fix both problems by following other call sites by overwriting @ret to -ENOENT if the btrfs_search_slot() failed to locate the key. This is very unlikely to hit, as we only enter update_raid_extent_item() if there is a conflicting key already in the raid stripe tree. This was reported by Sashiko when reviewing another patch. Link: https://sashiko.dev/#/patchset/20260817021512.3010812-1-shuangpeng.kernel%40gmail.com Fixes: 8c4cba2adbb0 ("btrfs: update stripe extents for existing logical addresses") Reviewed-by: Johannes Thumshirn Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/raid-stripe-tree.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/raid-stripe-tree.c b/fs/btrfs/raid-stripe-tree.c index 6291775dbe0e..d9e660447205 100644 --- a/fs/btrfs/raid-stripe-tree.c +++ b/fs/btrfs/raid-stripe-tree.c @@ -310,8 +310,10 @@ static int update_raid_extent_item(struct btrfs_trans_handle *trans, ret = btrfs_search_slot(trans, trans->fs_info->stripe_root, key, path, 0, 1); - if (ret) - return (ret == 1 ? ret : -EINVAL); + if (ret > 0) + ret = -ENOENT; + if (ret < 0) + return ret; leaf = path->nodes[0]; slot = path->slots[0]; From 0853dc4f2678bbb21ff3d7572b0e9b812985bd65 Mon Sep 17 00:00:00 2001 From: ZhengYuan Huang Date: Mon, 17 Aug 2026 21:20:51 +0800 Subject: [PATCH 0492/1198] btrfs: send: reject extents for non-regular inodes [BUG] A corrupted subvolume tree can leave an EXTENT_DATA item attached to an inode whose mode is not S_IFREG or S_IFLNK. During send, such an item can be treated as file data and crash through a NULL address_space operation: BUG: kernel NULL pointer dereference, address: 0000000000000000 #PF: supervisor instruction fetch in kernel mode #PF: error_code(0x0010) - not-present page Call Trace: read_pages+0x80b/0xb30 mm/readahead.c:173 page_cache_ra_unbounded+0x40d/0x890 mm/readahead.c:302 do_page_cache_ra mm/readahead.c:332 [inline] page_cache_ra_order+0xa16/0xcd0 mm/readahead.c:535 page_cache_sync_ra+0x5ce/0x9d0 mm/readahead.c:626 page_cache_sync_readahead include/linux/pagemap.h:1379 [inline] put_file_data fs/btrfs/send.c:5224 [inline] send_write fs/btrfs/send.c:5291 [inline] send_extent_data+0x16b2/0x29b0 fs/btrfs/send.c:5715 send_write_or_clone fs/btrfs/send.c:6135 [inline] process_extent+0x5d4/0x17b0 fs/btrfs/send.c:6504 changed_extent fs/btrfs/send.c:7079 [inline] changed_cb+0x22f9/0x3cd0 fs/btrfs/send.c:7245 full_send_tree fs/btrfs/send.c:7318 [inline] send_subvol fs/btrfs/send.c:7910 [inline] btrfs_ioctl_send+0x46a9/0x57f0 fs/btrfs/send.c:8248 ... [CAUSE] process_extent() skips extent items for symlinks but assumes every other inode with an extent item is a regular file. For a corrupted non-regular inode, btrfs_iget() does not install the regular file address_space operations. The readahead fallback can then call a NULL read_folio callback before the existing validation in btrfs_get_extent() can run. [FIX] Reject extent items for inode types other than regular files and symlinks at the common send extent-processing boundary. Symlink handling is left unchanged because send emits symlink data from read_symlink(). This covers full, incremental and new-generation sends without adding a check to the regular I/O path. Reviewed-by: Qu Wenruo Signed-off-by: ZhengYuan Huang Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/send.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index dca3570168c7..f88623bbc491 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -6417,6 +6417,13 @@ static int process_extent(struct send_ctx *sctx, if (S_ISLNK(sctx->cur_inode_mode)) return 0; + if (unlikely(!S_ISREG(sctx->cur_inode_mode))) { + btrfs_crit(sctx->send_root->fs_info, + "send: extent for non-regular inode %llu root %llu mode 0%llo", + key->objectid, btrfs_root_id(sctx->send_root), + sctx->cur_inode_mode & S_IFMT); + return -EUCLEAN; + } if (sctx->parent_root && !sctx->cur_inode_new) { ret = is_extent_unchanged(sctx, path, key); From a18a6b93a2843b9d103d3456bbd4b3f90282a379 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Wed, 19 Aug 2026 12:26:36 +0200 Subject: [PATCH 0493/1198] btrfs: zoned: finish active block group cleanup if call_zone_finish() fails do_zone_finish() clears BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE before finishing the zones. If call_zone_finish() then fails it returned early, leaving the now inactive block group on fs_info->zone_active_bgs, leaking its reference, the BTRFS_FS_NEED_ZONE_FINISH waiters are never woken, and as its alloc_offset equals the zone capacity btrfs_zone_finish_one_bg() keeps selecting it, spinning btrfs_zoned_activate_one_bg(). Fall through to the cleanup on failure too and return the error, but keep the block group read-only as its zones are left inconsistent. Fixes: d70cbdda75da ("btrfs: zoned: consolidate zone finish functions") Link: https://sashiko.dev/#/patchset/20260818100037.1366563-1-johannes.thumshirn%40wdc.com Reviewed-by: Qu Wenruo Signed-off-by: Johannes Thumshirn Signed-off-by: David Sterba --- fs/btrfs/zoned.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index a016cb471beb..7f0dde6398d4 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -2626,16 +2626,13 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ down_read(&dev_replace->rwsem); map = block_group->physical_map; for (i = 0; i < map->num_stripes; i++) { - ret = call_zone_finish(block_group, &map->stripes[i]); - if (ret) { - up_read(&dev_replace->rwsem); - return ret; - } + if (ret) + break; } up_read(&dev_replace->rwsem); - if (!fully_written) + if (!ret && !fully_written) btrfs_dec_block_group_ro(block_group); spin_lock(&fs_info->zone_active_bgs_lock); @@ -2648,7 +2645,7 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ clear_and_wake_up_bit(BTRFS_FS_NEED_ZONE_FINISH, &fs_info->flags); - return 0; + return ret; } int btrfs_zone_finish(struct btrfs_block_group *block_group) From c428b763f29bf2d7c67b69e5be964c7fb4eee282 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Tue, 18 Aug 2026 12:00:37 +0200 Subject: [PATCH 0494/1198] btrfs: zoned: propagate do_zone_finish() error in btrfs_zone_finish_endio() btrfs_zone_finish_endio() ignored the return value of do_zone_finish() and always returned 0, silently dropping a failed zone finish. Instead propagate any error from do_zone_finish() as the caller btrfs_finish_ordered_io() already handles it. Reviewed-by: Qu Wenruo Signed-off-by: Johannes Thumshirn Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/zoned.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 7f0dde6398d4..9cc2c9c1a606 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -2710,6 +2710,7 @@ int btrfs_zone_finish_endio(struct btrfs_fs_info *fs_info, u64 logical, u64 leng { struct btrfs_block_group *block_group; u64 min_alloc_bytes; + int ret = 0; if (!btrfs_is_zoned(fs_info)) return 0; @@ -2729,11 +2730,11 @@ int btrfs_zone_finish_endio(struct btrfs_fs_info *fs_info, u64 logical, u64 leng block_group->start + block_group->zone_capacity) goto out; - do_zone_finish(block_group, true); + ret = do_zone_finish(block_group, true); out: btrfs_put_block_group(block_group); - return 0; + return ret; } static void btrfs_zone_finish_endio_workfn(struct work_struct *work) From 529c01c3dc0d322c103611c35b01d71ea04562b2 Mon Sep 17 00:00:00 2001 From: Leo Martins Date: Tue, 18 Aug 2026 17:40:10 -0700 Subject: [PATCH 0495/1198] btrfs: abort transaction before releasing tree_log_mutex on commit failure When transaction metadata writeout fails in btrfs_commit_transaction(), the current code only logs the error, drops tree_log_mutex and then goes through cleanup_transaction(), which aborts the transaction and records the fs error. That is too late for the tree log side. A log sync can already be waiting on tree_log_mutex, because the committing transaction is moved to TRANS_STATE_UNBLOCKED while that mutex is held, which lets fsyncs join the next transaction and queue up in btrfs_sync_log(). Once the failed commit drops tree_log_mutex, such a log sync acquires it, sees BTRFS_FS_ERROR() still clear, and writes super_for_commit. That superblock holds the roots prepared for the transaction that has just failed to write out its metadata, so it can point at tree blocks that never reached the disk, and the next mount fails with a parent transid mismatch. Commit 165ea85f1483 ("btrfs: do not write supers if we have an fs error") fixed this class of problem by making btrfs_sync_log() check for an fs error right after taking tree_log_mutex. That check only works if the commit path publishes the fs error before it releases the same mutex, and commit 68d4ece9c30e ("btrfs: don't call btrfs_handle_fs_error() in btrfs_commit_transaction()") removed the only thing that did so. Restore the ordering by aborting the transaction while tree_log_mutex is still held. We have a transaction handle here, so this does not need to bring back the btrfs_handle_fs_error() call: __btrfs_abort_transaction() records the fs error itself, which is all btrfs_sync_log() looks at, and the error message put in its place is kept. This is what commit 3810ab40afa5 ("btrfs: abort transaction on error in write_all_supers()") already does for the next call in this function. This is reproducible on an unmodified kernel by failing the first couple of bios of a transaction commit with fail_make_request while a concurrent fsync workload keeps log syncs queued on tree_log_mutex. Fixes: 68d4ece9c30e ("btrfs: don't call btrfs_handle_fs_error() in btrfs_commit_transaction()") CC: stable@vger.kernel.org # 7.0+ Reviewed-by: Boris Burkov Reviewed-by: jlayton@meta.com Signed-off-by: Leo Martins Reviewed-by: Filipe Manana Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/transaction.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index bafc62cf5ebc..39909d363591 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -2583,6 +2583,12 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) ret = btrfs_write_and_wait_transaction(trans); if (unlikely(ret)) { btrfs_err(fs_info, "error while writing out transaction: %pe", ERR_PTR(ret)); + /* + * Abort before releasing tree_log_mutex, so a log sync waiting + * on it sees the fs error and skips writing super_for_commit + * for this failed transaction. See btrfs_sync_log(). + */ + btrfs_abort_transaction(trans, ret); mutex_unlock(&fs_info->tree_log_mutex); goto scrub_continue; } From d0285dfbc3b46f41395b26ee2f4a16d99fb3e736 Mon Sep 17 00:00:00 2001 From: Avi Weiss Date: Mon, 10 Aug 2026 12:47:01 +0300 Subject: [PATCH 0496/1198] btrfs: send: fix lost error return value in will_overwrite_ref() The direct-return refactoring in commit b3047a42f55d ("btrfs: send: directly return from will_overwrite_ref() and simplify it") changed will_overwrite_ref() to return directly instead of going through the common out label. That resulted in a negative return value from is_inode_existent() to start being converted to 0, making lookup errors unable to be distinguished from the inode not existing. process_recorded_refs() expects negative errors from will_overwrite_ref() and aborts processing when it receives one. Return the value from is_inode_existent() to restore the previous error propagation behavior as it was before the refactor. Fixes: b3047a42f55d ("btrfs: send: directly return from will_overwrite_ref() and simplify it") Signed-off-by: Avi Weiss Reviewed-by: Filipe Manana Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/send.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index f88623bbc491..5c59b9abedcd 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -2065,7 +2065,7 @@ static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen, ret = is_inode_existent(sctx, dir, dir_gen, NULL, &parent_root_dir_gen); if (ret <= 0) - return 0; + return ret; /* * If we have a parent root we need to verify that the parent dir was From cacf35832292997018837e484283f95a9301ebf5 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Thu, 20 Aug 2026 18:28:48 +0930 Subject: [PATCH 0497/1198] btrfs: do not force reloc root creation during qgroup_account_snapshot() [BUG] When running btrfs/252 with quota enabled through MKFS_OPTIONS="-O quota", it has a high chance to trigger the following kernel warning and flips the fs RO: BTRFS info (device dm-2): relocating block group 30408704 flags metadata|dup ------------[ cut here ]------------ WARNING: fs/btrfs/extent-tree.c:879 at lookup_inline_extent_backref+0x74b/0x960 [btrfs], CPU#4: btrfs/2173 CPU: 4 UID: 0 PID: 2173 Comm: btrfs Not tainted 7.2.0-rc6-custom+ #457 PREEMPT(full) 3adc6528fb66f7a55fe1095385818e742f200aab Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS unknown 02/02/2022 RIP: 0010:lookup_inline_extent_backref+0x74b/0x960 [btrfs] Call Trace: insert_inline_extent_backref+0x7c/0x160 [btrfs 32f09462c54d9c922fca74a3e4866f4aa7737b72] __btrfs_inc_extent_ref+0xa9/0x270 [btrfs 32f09462c54d9c922fca74a3e4866f4aa7737b72] __btrfs_run_delayed_refs+0x4af/0x11c0 [btrfs 32f09462c54d9c922fca74a3e4866f4aa7737b72] btrfs_run_delayed_refs+0x9d/0xf0 [btrfs 32f09462c54d9c922fca74a3e4866f4aa7737b72] create_pending_snapshot+0x39d/0xf00 [btrfs 32f09462c54d9c922fca74a3e4866f4aa7737b72] create_pending_snapshots+0x9b/0xc0 [btrfs 32f09462c54d9c922fca74a3e4866f4aa7737b72] btrfs_commit_transaction+0x280/0xeb0 [btrfs 32f09462c54d9c922fca74a3e4866f4aa7737b72] prepare_to_relocate+0x147/0x200 [btrfs 32f09462c54d9c922fca74a3e4866f4aa7737b72] relocate_block_group+0x6b/0x5e0 [btrfs 32f09462c54d9c922fca74a3e4866f4aa7737b72] btrfs_relocate_block_group+0x92c/0x2380 [btrfs 32f09462c54d9c922fca74a3e4866f4aa7737b72] btrfs_relocate_chunk+0x3f/0x1a0 [btrfs 32f09462c54d9c922fca74a3e4866f4aa7737b72] btrfs_balance+0xa2c/0x19c0 [btrfs 32f09462c54d9c922fca74a3e4866f4aa7737b72] btrfs_ioctl+0x2839/0x2d30 [btrfs 32f09462c54d9c922fca74a3e4866f4aa7737b72] __x64_sys_ioctl+0x416/0x9a0 do_syscall_64+0xe1/0x790 entry_SYSCALL_64_after_hwframe+0x4b/0x53 ---[ end trace 0000000000000000 ]--- BTRFS info (device dm-2): leaf 4593991680 gen 233 total ptrs 175 free space 5953 owner 2 BTRFS info (device dm-2): refs 3 lock_owner 2173 current 2173 item 0 key (166772736 METADATA_ITEM 1) itemoff 16250 itemsize 33 extent refs 1 gen 222 flags 2 ref#0: tree block backref root 266 [ Skip the tree dump ] item 174 key (263225344 METADATA_ITEM 0) itemoff 10328 itemsize 33 extent refs 1 gen 162 flags 258 ref#0: tree block backref root 267 BTRFS error (device dm-2): extent item not found for insert, bytenr 179847168 num_bytes 16384 parent 4594335744 root_objectid 273 owner 0 offset 0 BTRFS error (device dm-2): failed to run delayed ref for logical 179847168 num_bytes 16384 type 182 action 1 ref_mod 1: -117 [CAUSE] The above error is showing that there is a tree reference to a metadata extent that is no longer there. With "ref_verify" mount option (requires CONFIG_BTRFS_DEBUG), there is some extra debug output: BTRFS error (device dm-2): dumping block entry [180961280 16384], num_refs 0, metadata 1, from disk 0 BTRFS error (device dm-2): root entry 256, num_refs 18446744073709551615 BTRFS error (device dm-2): root entry 273, num_refs 18446744073709551615 BTRFS error (device dm-2): Ref action 3, root 273, ref_root 273, parent 0, owner 0, offset 0, num_refs 1 btrfs_force_cow_block+0x129/0x7d0 [btrfs] btrfs_cow_block+0x10a/0x250 [btrfs] btrfs_search_slot+0x5eb/0xf40 [btrfs] btrfs_insert_empty_items+0x3a/0x70 [btrfs] insert_with_overflow+0x53/0x130 [btrfs] btrfs_insert_dir_item+0x125/0x290 [btrfs] btrfs_add_link+0xaa/0x410 [btrfs] btrfs_rename+0x5ea/0xcd0 [btrfs] btrfs_rename2+0x28/0x60 [btrfs] vfs_rename+0x5b2/0xe10 filename_renameat2+0x244/0x430 __x64_sys_rename+0x48/0x70 do_syscall_64+0xe1/0x790 entry_SYSCALL_64_after_hwframe+0x4b/0x53 BTRFS error (device dm-2): Ref action 2, root 273, ref_root 273, parent 0, owner 0, offset 0, num_refs 18446744073709551615 btrfs_force_cow_block+0x327/0x7d0 [btrfs] btrfs_cow_block+0x10a/0x250 [btrfs] btrfs_search_slot+0x5eb/0xf40 [btrfs] btrfs_lookup_file_extent+0x4d/0x70 [btrfs] btrfs_drop_extents+0x151/0xf00 [btrfs] insert_reserved_file_extent+0xfe/0x3e0 [btrfs] btrfs_finish_one_ordered+0x549/0xc40 [btrfs] btrfs_work_helper+0xde/0x350 [btrfs] process_one_work+0x198/0x380 worker_thread+0x1c8/0x330 kthread+0xee/0x120 ret_from_fork+0x28f/0x310 ret_from_fork_asm+0x11/0x20 BTRFS error (device dm-2): Ref action 1, root 273, ref_root 0, parent 4594335744, owner 0, offset 0, num_refs 1 __btrfs_mod_ref+0x1c5/0x2d0 [btrfs] btrfs_copy_root+0x262/0x390 [btrfs] create_reloc_root+0xb9/0x370 [btrfs] btrfs_init_reloc_root+0xb0/0x1b0 [btrfs] record_root_in_trans+0xa6/0xd0 [btrfs] create_pending_snapshot+0x383/0xf00 [btrfs] create_pending_snapshots+0x9b/0xc0 [btrfs] btrfs_commit_transaction+0x280/0xeb0 [btrfs] prepare_to_relocate+0x147/0x200 [btrfs] relocate_block_group+0x6b/0x5e0 [btrfs] btrfs_relocate_block_group+0x92c/0x2380 [btrfs] btrfs_relocate_chunk+0x3f/0x1a0 [btrfs] btrfs_balance+0xa2c/0x19c0 [btrfs] btrfs_ioctl+0x2839/0x2d30 [btrfs] __x64_sys_ioctl+0x416/0x9a0 do_syscall_64+0xe1/0x790 The above shows the direct cause, Ref action 3 is the oldest operation, which shows the tree block is created by COW. Then ref action 2 shows it's COWed away, by a metadata update, meaning the tree block is already released, should not be referred any more. Then the final one, is trying to create a reloc tree for subvolume 273, and that reloc root creation is referring to the already dropped tree block. The root cause is that, during qgroup_account_snapshot(), we are calling record_root_in_trans() with "force = true". So if the root has no reloc root, we will create one, but at that timing it's already too late. Normally reloc root should be created before the commit and current roots diverge, to avoid the same problem we are hitting. But during relocation initialization, we are committing the current running transaction, with a new reloc_control attached halfway. And if qgroup is enabled, the record_root_in_trans() with "force = true" calls will force reloc root creation even if we do not and should not create reloc root at that timing. [FIX] Do not force reloc root creation during record_root_in_trans() with "force = true" cases, which is only called by qgroup_account_snapshot(). If we're really under relocation, the reloc root should be created way early, before the commit and current root diverge. If the root has no reloc tree yet, it means we're still initializing the reloc, and do not need a reloc root. So skipping the reloc tree creation in qgroup_account_snapshot() should be safe. Link: https://bugzilla.suse.com/show_bug.cgi?id=1275740 Fixes: 4d31778aa2fa ("btrfs: qgroup: Fix root item corruption when multiple same source snapshots are created with quota enabled") Assisted-by: LLM (initial analysis, but incorrect conclusion with too many burnt tokens) Tested-by: Disha Goel Reviewed-by: Filipe Manana Signed-off-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/transaction.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 39909d363591..6802b94ed76f 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -458,8 +458,19 @@ static int record_root_in_trans(struct btrfs_trans_handle *trans, * through btrfs_record_root_in_trans without having to take the * lock. smp_wmb() makes sure that all the writes above are * done before we pop in the zero below + * + * If @force is true, it means the call is from + * qgroup_account_snapshot(), which only requires radix tree + * tracking. + * We should not force reloc root creation here, as the root + * may have already been modified, and in that case + * root->commit_root has already been dropped. + * + * Using that commit root will cause the reloc root to refer + * to a deleted extent, causing extent tree corruption. */ - ret = btrfs_init_reloc_root(trans, root); + if (!force) + ret = btrfs_init_reloc_root(trans, root); smp_mb__before_atomic(); clear_bit(BTRFS_ROOT_IN_TRANS_SETUP, &root->state); } From 2acb9f3d1cc8f65dc81ed55e238cbf8e5b60bff7 Mon Sep 17 00:00:00 2001 From: FAN YE Date: Fri, 21 Aug 2026 17:50:09 +0000 Subject: [PATCH 0498/1198] btrfs: zstd: fix lost wakeup when waiting for a workspace A writer can sleep forever in zstd_get_workspace() even though a workspace is free. When zstd_alloc_workspace() fails, the task is queued on zwsm->wait and schedules unconditionally, never re-testing the pool. zstd_put_workspace() publishes the workspace and then calls cond_wake_up(), which only wakes when a sleeper is already visible, so a workspace returned between the failed allocation and prepare_to_wait() wakes nobody. The window is wide: zstd_alloc_workspace() goes through kvmalloc() and may enter reclaim. Only a max level workspace triggers the wakeup and one is deliberately kept allocated as the fallback every waiter waits for, so once its wakeup is lost the writer stays in TASK_UNINTERRUPTIBLE until some other task happens to return one. Re-check the pool after prepare_to_wait() has published the waiter, and use the workspace if one turned up. Fixes: 3f93aef535c8 ("btrfs: add zstd compression level support") Assisted-by: Claude:claude-opus-5 Reviewed-by: Qu Wenruo Signed-off-by: FAN YE Signed-off-by: David Sterba --- fs/btrfs/zstd.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c index 86919293fd54..58d9ff76fe07 100644 --- a/fs/btrfs/zstd.c +++ b/fs/btrfs/zstd.c @@ -307,8 +307,17 @@ struct list_head *zstd_get_workspace(struct btrfs_fs_info *fs_info, int level) DEFINE_WAIT(wait); prepare_to_wait(&zwsm->wait, &wait, TASK_UNINTERRUPTIBLE); - schedule(); + /* + * Re-check after being queued: zstd_put_workspace() only wakes + * a queue that already has a sleeper, so a workspace returned + * since the failed allocation woke nobody. + */ + ws = zstd_find_workspace(fs_info, level); + if (!ws) + schedule(); finish_wait(&zwsm->wait, &wait); + if (ws) + return ws; goto again; } From 0c1032c8c3e9dc8b9a9fa5f6ef23966e236466ed Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Tue, 11 Aug 2026 15:31:49 +0930 Subject: [PATCH 0499/1198] btrfs: tests: do not touch page cache if root/inode allocation failed Inside test_find_delalloc() of extent-io-tests.c, if we fail to allocate a dummy root or the test inode, we go to out label to clean up. But at that stage, @inode is still NULL and we will call process_page_range() to access the page cache of the inode, this will cause NULL pointer dereference. This is a very minor bug, as it only affects selftests which are not compiled in by default for most distros, and very hard to trigger. Fix it by adding a new out_root_info label to handle root and inode allocation failure. This is a pre-existing bug reported by Sashiko while reviewing another patch. Link: https://sashiko.dev/#/patchset/cover.1786095309.git.wqu%40suse.com Reviewed-by: Boris Burkov Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/tests/extent-io-tests.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c index b2aacf846c8b..23459cd4e503 100644 --- a/fs/btrfs/tests/extent-io-tests.c +++ b/fs/btrfs/tests/extent-io-tests.c @@ -133,14 +133,14 @@ static int test_find_delalloc(u32 sectorsize, u32 nodesize) if (IS_ERR(root)) { test_std_err(TEST_ALLOC_ROOT); ret = PTR_ERR(root); - goto out; + goto out_root_info; } inode = btrfs_new_test_inode(); if (!inode) { test_std_err(TEST_ALLOC_INODE); ret = -ENOMEM; - goto out; + goto out_root_info; } tmp = &BTRFS_I(inode)->io_tree; BTRFS_I(inode)->root = root; @@ -333,6 +333,7 @@ static int test_find_delalloc(u32 sectorsize, u32 nodesize) process_page_range(inode, 0, total_dirty - 1, PROCESS_UNLOCK | PROCESS_RELEASE); iput(inode); +out_root_info: btrfs_free_dummy_root(root); btrfs_free_dummy_fs_info(fs_info); return ret; From 6a7a45b1d94799a5eb8e6d26e65cf31a3fcda9e5 Mon Sep 17 00:00:00 2001 From: Chris Mason Date: Thu, 27 Aug 2026 12:29:16 -0700 Subject: [PATCH 0500/1198] MAINTAINERS: update Chris Mason's email address David Sterba has been doing the Btrfs maintainership work for years, and my email update to mason@kernel.org seems like a good time to make the MAINTAINERS file a little more accurate. Link: https://lore.kernel.org/all/20260827193032.786461-1-clm@meta.com/ Signed-off-by: Chris Mason Signed-off-by: David Sterba --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 58a0875d4f01..3f09f9cabe59 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5616,8 +5616,8 @@ W: http://bu3sch.de/btgpio.php F: drivers/gpio/gpio-bt8xx.c BTRFS FILE SYSTEM -M: Chris Mason M: David Sterba +R: Chris Mason L: linux-btrfs@vger.kernel.org S: Maintained W: https://btrfs.readthedocs.io From 94e25cb6ab7f4f025bcdcd8ea79fda30f12843a4 Mon Sep 17 00:00:00 2001 From: Priya Hosur Date: Thu, 27 Aug 2026 15:02:46 +0530 Subject: [PATCH 0501/1198] drm/amdkfd: Add TLB flush after MES queue eviction/suspension MES (Micro Engine Scheduler) does not perform heavy-weight TLB invalidation after unmapping queues, unlike HWS which does this automatically. This causes a race condition where in-flight DMA descriptors can access memory that has been unmapped, leading to page faults and GPU queue hangs during SVM page migration. The issue manifests as KFDSVMRangeTest.MultiThreadMigrationTest failures on gfx1151 (Strix Point) with XNACK mode 1 enabled - the GPU compute queue hangs with packets submitted but never consumed. Add kfd_flush_tlb() calls after MES queue removal in two locations: - evict_process_queues_cpsch(): after all queues removed during eviction - suspend_queues(): after debug/criu queue suspension (with mem_fence barrier) This ensures all in-flight memory accesses from unmapped queues are flushed before memory is freed or migrated. Signed-off-by: Priya Hosur Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher (cherry picked from commit f5c4f88e0f9c45a8fb9dfac0c1df726c95e41b77) Cc: stable@vger.kernel.org --- .../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 4bc947c3bd0d..9811e4e10291 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -1455,6 +1455,14 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm, dqm_evict_mqd_bo(dqm, q); } + /* + * Heavy-weight TLB flush after MES removes queues to ensure + * in-flight memory accesses complete before memory is freed/migrated. + * HWS does this automatically, MES does not. + */ + if (dqm->dev->kfd->shared_resources.enable_mes) + kfd_flush_tlb(pdd); + if (!dqm->dev->kfd->shared_resources.enable_mes) { pdd->last_evict_timestamp = get_jiffies_64(); retval = execute_queues_cpsch(dqm, @@ -3746,8 +3754,11 @@ int suspend_queues(struct kfd_process *p, if (!per_device_suspended) { dqm_unlock(dqm); mutex_unlock(&p->event_mutex); - if (total_suspended) + if (total_suspended) { amdgpu_amdkfd_debug_mem_fence(dqm->dev->adev); + /* Heavy-weight TLB flush after MES suspends queues */ + kfd_flush_tlb(pdd); + } continue; } From bd1f08246b8a2564d8ac61df715b6bcd5f994729 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Wed, 26 Aug 2026 13:51:02 -0500 Subject: [PATCH 0502/1198] drm/amdgpu: restrict BAR0 fallback read to SR-IOV VFs only The BAR0 fallback read path was introduced as a workaround for SR-IOV VFs where the VRAM aperture is not available during early init. Restrict this workaround to only SR-IOV VFs where it's needed. Reported-by: gloveless@jqluv.com Fixes: cba4928cdffa ("drm/amdgpu: reduce early full GPU access during SR-IOV init") Acked-by: Alex Deucher Link: https://patch.msgid.link/20260826185102.2269511-1-mario.limonciello@amd.com Signed-off-by: Mario Limonciello Signed-off-by: Alex Deucher (cherry picked from commit d8a0affd207c813bd063fa2c27786f449eaf92b8) --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 44bed0ba64a3..104d1d2cbad9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -771,6 +771,9 @@ static int amdgpu_device_read_fb_via_bar0(struct amdgpu_device *adev, if (!buf || !size) return -EINVAL; + if (!amdgpu_sriov_vf(adev)) + return -EINVAL; + flags = pci_resource_flags(adev->pdev, 0); if ((flags & IORESOURCE_UNSET) || !(flags & IORESOURCE_MEM)) return -EINVAL; From 7346a046c6a9b9f30cb1f7d301449300a9174c71 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 20 Aug 2026 09:02:01 -0400 Subject: [PATCH 0503/1198] drm/amdgpu/gfx8: only apply compute quantums to KCQs Don't apply to KIQ. Seems to cause problems on KIQ on some ARM platforms. Closes: https://gitlab.freedesktop.org/drm/amd/-/work_items/5658 Fixes: 91cf34bc5a55 ("drm/amdgpu/gfx8: align mqd settings with KFD") Reviewed-by: Jesse Zhang Reviewed-by: Kent Russell Signed-off-by: Alex Deucher (cherry picked from commit 6aae7bab029cdccae9a7157facfe36bfc35fc940) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 6cf427995078..7f91186ef1d1 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -4546,9 +4546,11 @@ static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring) /* set static priority for a queue/ring */ gfx_v8_0_mqd_set_priority(ring, mqd); tmp = RREG32(mmCP_HQD_QUANTUM); - tmp = REG_SET_FIELD(tmp, CP_HQD_QUANTUM, QUANTUM_EN, 1); - tmp = REG_SET_FIELD(tmp, CP_HQD_QUANTUM, QUANTUM_SCALE, 1); - tmp = REG_SET_FIELD(tmp, CP_HQD_QUANTUM, QUANTUM_DURATION, 10); + if (ring != &adev->gfx.kiq[0].ring) { + tmp = REG_SET_FIELD(tmp, CP_HQD_QUANTUM, QUANTUM_EN, 1); + tmp = REG_SET_FIELD(tmp, CP_HQD_QUANTUM, QUANTUM_SCALE, 1); + tmp = REG_SET_FIELD(tmp, CP_HQD_QUANTUM, QUANTUM_DURATION, 10); + } mqd->cp_hqd_quantum = tmp; /* map_queues packet doesn't need activate the queue, From b428f83c7c2542837c15231c519583cc26b60156 Mon Sep 17 00:00:00 2001 From: Amber Lin Date: Thu, 27 Aug 2026 15:02:53 -0400 Subject: [PATCH 0504/1198] drm/amdgpu: Update queue reset support version Update queue reset required MES version for MES 12.1 to 0x7b since we change the implementation from detect-and-reset method to per-queue-reset method. Signed-off-by: Amber Lin Reviewed-by: Michael Chen Signed-off-by: Alex Deucher (cherry picked from commit 2160a5cbf0b7917adce4b55421306b614b4a2c8f) --- drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c index b96f94e5169f..1a86a47406b1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c @@ -879,7 +879,7 @@ bool amdgpu_mes_queue_reset_by_mes_supported(struct amdgpu_device *adev) return (ip_maj == 11 && mes_sched >= 0x8c) || ((ip_maj == 12 && ip_min == 0) && mes_sched >= 0x8d) || - ((ip_maj == 12 && ip_min == 1) && mes_sched >= 0x73); + ((ip_maj == 12 && ip_min == 1) && mes_sched >= 0x7b); } /* Fix me -- node_id is used to identify the correct MES instances in the future */ From d6e16df7df4d2c39e2b04b355d0434fb90e2d62c Mon Sep 17 00:00:00 2001 From: Sunil Khatri Date: Thu, 27 Aug 2026 20:33:35 +0530 Subject: [PATCH 0505/1198] drm/amdgpu: use AMDGPU_GPU_PAGE_SHIFT instead of PAGE_SHIFT For different address types the variable PAGE_SHIFT might not work well and it's better to use the GPU specific one Signed-off-by: Sunil Khatri Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher (cherry picked from commit 3494b77d10375e0f9ab784e9b20763339844b55b) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index aedf72c2333e..28f29f2d7c14 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -2090,7 +2090,7 @@ int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev, after->start = eaddr + 1; after->last = tmp->last; after->offset = tmp->offset; - after->offset += (after->start - tmp->start) << PAGE_SHIFT; + after->offset += (after->start - tmp->start) << AMDGPU_GPU_PAGE_SHIFT; after->flags = tmp->flags; after->bo_va = tmp->bo_va; list_add(&after->list, &tmp->bo_va->invalids); From 90ce19bd11b2864e26e4b43e7acbffabf037b69b Mon Sep 17 00:00:00 2001 From: Sunil Khatri Date: Thu, 27 Aug 2026 21:00:22 +0530 Subject: [PATCH 0506/1198] drm/amdgpu: fix Idle BOs list in VM debugfs status info amdgpu_debugfs_vm_bo_status_info() prints the "Idle BOs" section by iterating lists->needs_update, the same list already printed just above under "Moved BOs". struct amdgpu_vm_bo_status has a dedicated idle list, populated whenever a BO's state machine settles, but it was never read here, so genuinely idle BOs never show up in the debugfs output and the "Idle BOs" section duplicates "Moved BOs" instead. Iterate lists->idle for the "Idle BOs" section. Fixes: 4cdbba5a16aa ("drm/amdgpu: restructure VM state machine v4") Signed-off-by: Sunil Khatri Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher (cherry picked from commit 451bfc778a8c364841837def00ba15936f72762b) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 28f29f2d7c14..bb04101b0fb5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -3122,7 +3122,7 @@ static void amdgpu_debugfs_vm_bo_status_info(struct seq_file *m, id = 0; seq_puts(m, "\tIdle BOs:\n"); - list_for_each_entry(base, &lists->needs_update, vm_status) { + list_for_each_entry(base, &lists->idle, vm_status) { if (!base->bo) continue; From ef0e9d12727d0fec762eea5053ff02ba555b8895 Mon Sep 17 00:00:00 2001 From: Ivan Lipski Date: Wed, 12 Aug 2026 23:15:18 -0400 Subject: [PATCH 0507/1198] drm/amd/display: Fix DCN5/6 DML2 compilation warnings [WHY] A kernel compilation warning was reported caused by upstream of DCN5/6. [HOW] Using plain integer as NULL pointer. Assign NULL to the VActiveLatencyHidingMargin/VActiveLatencyHidingUs pointer members in dml2_core_dcn5_funcs_mode_programming.c, and pass NULL for the pointer arguments to calculate_first_second_splitting() in dml2_pmo_dcn6_stage_optimizers.c. Fixes: 7f7d7ea1fa51 ("drm/amd/display: Add new sources for DCN6") Reviewed-by: Dillon Varone Signed-off-by: Ivan Lipski Signed-off-by: Alex Hung Tested-by: Dan Wheeler Signed-off-by: Alex Deucher (cherry picked from commit d96880560e9f35ba7f8de1b3f90032c8c3eaea88) --- .../src/dml2_core/dml2_core_dcn5_funcs_mode_programming.c | 4 ++-- .../dml21/src/dml2_pmo/dml2_pmo_dcn6_stage_optimizers.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_core/dml2_core_dcn5_funcs_mode_programming.c b/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_core/dml2_core_dcn5_funcs_mode_programming.c index 8497eaea012e..297e21e7c68d 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_core/dml2_core_dcn5_funcs_mode_programming.c +++ b/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_core/dml2_core_dcn5_funcs_mode_programming.c @@ -1128,8 +1128,8 @@ static bool dcn5_mode_programming(struct dml2_core_calcs_mode_programming_ex *in CalculateWatermarks_params->USRRetrainingSupport = &mode_lib->mp.USRRetrainingSupport; CalculateWatermarks_params->temp_read_or_ppt_support = mode_lib->mp.temp_read_or_ppt_support; CalculateWatermarks_params->global_temp_read_or_ppt_supported = &mode_lib->mp.global_temp_read_or_ppt_supported; - CalculateWatermarks_params->VActiveLatencyHidingMargin = 0; - CalculateWatermarks_params->VActiveLatencyHidingUs = 0; + CalculateWatermarks_params->VActiveLatencyHidingMargin = NULL; + CalculateWatermarks_params->VActiveLatencyHidingUs = NULL; dcn5_calculate_watermarks_and_dram_speed_change_support(&mode_lib->scratch, CalculateWatermarks_params); diff --git a/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_pmo/dml2_pmo_dcn6_stage_optimizers.c b/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_pmo/dml2_pmo_dcn6_stage_optimizers.c index 0b884a8661c8..6d6611a6b5a6 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_pmo/dml2_pmo_dcn6_stage_optimizers.c +++ b/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_pmo/dml2_pmo_dcn6_stage_optimizers.c @@ -1414,7 +1414,7 @@ static bool find_shift_for_valid_cache_id_assignment(const int *mcache_boundarie success = true; for (pipe_index = 0; pipe_index < pipe_count; pipe_index++) { if (!calculate_first_second_splitting(mcache_boundaries, num_boundaries, *shift, - pipe_vp_startx[pipe_index], pipe_vp_endx[pipe_index], 0, 0)) { + pipe_vp_startx[pipe_index], pipe_vp_endx[pipe_index], NULL, NULL)) { success = false; break; } From 9ce3169430f1db035d491481086e2fae2552569c Mon Sep 17 00:00:00 2001 From: Roman Li Date: Fri, 14 Aug 2026 18:03:17 -0400 Subject: [PATCH 0508/1198] drm/amd/display: Set gpuvm min page size to 4K on dcn35/36 [WHY] Splash screen corruption on some 8K monitors. [HOW] Set GPUVM min page size to 4K for DCN35/36 to use the correct DML2 calculations, avoiding the corruption path observed during splash. Fixes: 115009d11ccf ("drm/amd/display: Add DCN35 DML2 support") Cc: Mario Limonciello Cc: Alex Deucher Reviewed-by: Alex Hung Signed-off-by: Roman Li Signed-off-by: Alex Hung Tested-by: Dan Wheeler Signed-off-by: Alex Deucher (cherry picked from commit 2cbfb03dead5088a7bdfe2ce392a5caa3d1b3719) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/display/dc/dml2_0/dml2_translation_helper.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/display/dc/dml2_0/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2_0/dml2_translation_helper.c index 166f10b8862f..c82886323a51 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2_0/dml2_translation_helper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2_0/dml2_translation_helper.c @@ -301,6 +301,7 @@ void dml2_init_socbb_params(struct dml2_context *dml2, const struct dc *in_dc, s out->smn_latency_us = 2; out->dispclk_dppclk_vco_speed_mhz = 3600; out->pct_ideal_dram_bw_after_urgent_pixel_only = 65.0; + out->gpuvm_min_page_size_kbytes = 4; break; From 93a77d353cb26772ae2fba50ae7321ae996b7f00 Mon Sep 17 00:00:00 2001 From: Austin Zheng Date: Wed, 19 Aug 2026 09:33:57 -0400 Subject: [PATCH 0509/1198] drm/amd/display: Remove const Qualifier From Non-Pointer Fields [WHY/HOW] Integer values for dml2_core_calcs_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport_params should not have the const qualifier. This prevents using different values of the inputs when the function is called again. Reviewed-by: Dillon Varone Signed-off-by: Austin Zheng Signed-off-by: Alex Hung Tested-by: Dan Wheeler Signed-off-by: Alex Deucher (cherry picked from commit 342280aae4f33816e8d07c15cb538a3b375a7f8f) Cc: stable@vger.kernel.org --- .../dc/dml2_0/dml21/src/dml2_core/dml2_core_shared_types.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_core/dml2_core_shared_types.h b/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_core/dml2_core_shared_types.h index 8a371bd1a7a5..28f4a53d0617 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_core/dml2_core_shared_types.h +++ b/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_core/dml2_core_shared_types.h @@ -1819,8 +1819,8 @@ struct dml2_core_calcs_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport_param bool UnboundedRequestEnabled; unsigned int CompressedBufferSizeInkByte; bool max_outstanding_when_urgent_expected; - const unsigned int max_outstanding_requests; - const unsigned int max_request_size_bytes; + unsigned int max_outstanding_requests; + unsigned int max_request_size_bytes; const unsigned int *meta_row_height_l; const unsigned int *meta_row_height_c; const enum dml2_pstate_method *uclk_pstate_switch_modes; From 5a67d2e055897a36acb4e48082986fb4a4eebdd3 Mon Sep 17 00:00:00 2001 From: Roman Li Date: Fri, 21 Aug 2026 12:19:10 -0400 Subject: [PATCH 0510/1198] drm/amd/display: Fix backlight control for luminance-capable OLED [WHY] For some eDP panels VESA aux backlight control is necessary, otherwise they stay black. [HOW] When AUX backlight control is used, select BACKLIGHT_CONTROL_VESA_AUX for panels that advertise panel_luminance_control. Reviewed-by: Hansen Dsouza Signed-off-by: Roman Li Signed-off-by: Alex Hung Tested-by: Dan Wheeler Signed-off-by: Alex Deucher (cherry picked from commit 42f698bd061d76d5f4c84a195e465cfbeec775e4) --- .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_backlight.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_backlight.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_backlight.c index e61bbc310f33..b9e90ea449ca 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_backlight.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_backlight.c @@ -534,8 +534,12 @@ void amdgpu_dm_update_connector_ext_caps(struct amdgpu_dm_connector *aconnector) else if (!IS_ERR_OR_NULL(panel_backlight_quirk) && panel_backlight_quirk->force_pwm) caps->aux_support = false; - if (caps->aux_support) - aconnector->dc_link->backlight_control_type = BACKLIGHT_CONTROL_AMD_AUX; + if (caps->aux_support) { + if (aconnector->dc_link->dpcd_caps.panel_luminance_control) + aconnector->dc_link->backlight_control_type = BACKLIGHT_CONTROL_VESA_AUX; + else + aconnector->dc_link->backlight_control_type = BACKLIGHT_CONTROL_AMD_AUX; + } luminance_range = &conn_base->display_info.luminance_range; From 4278d65a41a2f6530437738f158f69e379bddb1c Mon Sep 17 00:00:00 2001 From: Melissa Wen Date: Thu, 20 Aug 2026 11:26:37 +0200 Subject: [PATCH 0511/1198] drm/amd/display: use halving distribution for all encode-to-linear curves In encode-to-linear conversions, LUT entries should be uniformly distributed across the input range: non-linear encodings are already approximately perceptually uniform, so every input code carries the same weight. A fixed count per region does the opposite, concentrating entries on the darker values and leaving few for the bright end, whereas halving distribution spaces all 256 entries uniformly. This holds for any encoded input, so remove the PQ/sRGB condition from commit "drm/amd/display: use halving distribution for PQ/sRGB linearizing LUT" and apply halving to all encode-to-linear operations (pre-defined TF or user LUTs). It fixes the following IGT kms_colorop subtests: - plane-XR30-XR30-srgb_inv_eotf_lut-srgb_eotf_lut - plane-XR30-XR30-gamma_2_2-gamma_2_2_inv-gamma_2_2 Fixes: a71d2b051f33 ("drm/amd/display: use halving distribution for PQ/sRGB linearizing LUT") Reviewed-by: Alex Hung Reviewed-by: Harry Wentland Signed-off-by: Melissa Wen Signed-off-by: Alex Deucher (cherry picked from commit 6df7c9c307e72e7f13829e94edc89134f0764775) --- .../amd/display/dc/dcn30/dcn30_cm_common.c | 34 ++++++------------- 1 file changed, 10 insertions(+), 24 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c index 66fe7f313ea3..62ca235cd649 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c @@ -320,6 +320,8 @@ static struct fixed31_32 interp_tf_pts(const struct fixed31_32 *output_tf_channe return value; } +#define NUM_DEGAMMA_REGIONS 9 + bool cm3_helper_translate_curve_to_degamma_hw_format( const struct dc_transfer_func *output_tf, struct pwl_params *lut_params) @@ -343,31 +345,15 @@ bool cm3_helper_translate_curve_to_degamma_hw_format( memset(lut_params, 0, sizeof(struct pwl_params)); memset(seg_distr, 0, sizeof(seg_distr)); - if (output_tf->tf == TRANSFER_FUNCTION_PQ || - output_tf->tf == TRANSFER_FUNCTION_SRGB) { - /* 9 segments - * segments are from 2^-9 to 0 - */ - const uint8_t SEG_COUNT = 9; - seg_distr[0] = 0; // Since we only have one point in darkest region - for (k = 1; k < SEG_COUNT; k++) - seg_distr[k] = k - 1; // 2^(k-1) points per region; halves as k decreases + /* 9 segments + * segments are from 2^-9 to 2^0 + */ + seg_distr[0] = 0; // Since we only have one point in darkest region + for (k = 1; k < NUM_DEGAMMA_REGIONS; k++) + seg_distr[k] = k - 1; // 2^(k-1) points per region; halves as k decreases - region_start = -SEG_COUNT; - region_end = 0; - } else { - /* 12 segments - * segments are from 2^-12 to 2^0 - * There are less than 256 points, for optimization - */ - const uint8_t SEG_COUNT = 12; - - for (i = 0; i < SEG_COUNT; i++) - seg_distr[i] = 4; - - region_start = -SEG_COUNT; - region_end = 0; - } + region_start = -NUM_DEGAMMA_REGIONS; + region_end = 0; for (i = region_end - region_start; i < MAX_REGIONS_NUMBER ; i++) seg_distr[i] = -1; From f63de9054da858d57054474c32464106f8375e0d Mon Sep 17 00:00:00 2001 From: Hari Mishal Date: Sat, 22 Aug 2026 16:57:51 +0200 Subject: [PATCH 0512/1198] drm/amd/display: fix division by zero in get_estimated_bw() get_estimated_bw() divides by link->dpia_bw_alloc_config.bw_granularity, which is zeroed by reset_bw_alloc_struct() and only populated once DP_TUNNELING_BW_ALLOC_CAP_CHANGED has been handled. link_dp_dpia_handle_bw_alloc_status(), the DPCD interrupt handler, calls get_estimated_bw() whenever DP_TUNNELING_ESTIMATED_BW_CHANGED is set, independently of whether DP_TUNNELING_BW_ALLOC_CAP_CHANGED has ever fired for that link. A connected USB4/DPIA tunneling device that reports an estimated-bandwidth change before ever reporting a capability change drives a division by zero in this IRQ path. link_dpia_send_bw_alloc_request() already guards the same bw_granularity division; add the identical guard here rather than introducing a new pattern. Fixes: 8e5cfe547bf3 ("drm/amd/display: upstream link_dp_dpia_bw.c") Reviewed-by: Alex Hung Assisted-by: gkh_clanker_t1000 Signed-off-by: Hari Mishal Signed-off-by: Alex Deucher (cherry picked from commit f2a961457c33dc34223aad5c9e8971de34a4eed3) Cc: stable@vger.kernel.org --- .../gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c index dd854d992692..f43fc4b78a8d 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c @@ -103,6 +103,11 @@ static int get_estimated_bw(struct dc_link *link) { uint8_t bw_estimated_bw = 0; + if (link->dpia_bw_alloc_config.bw_granularity == 0) { + DC_LOG_ERROR("%s: BW granularity is zero!\n", __func__); + return 0; + } + core_link_read_dpcd( link, ESTIMATED_BW, From 012a026bae0212952b423a842b7e2c0bf21f8e7a Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Mon, 31 Aug 2026 08:00:51 -0500 Subject: [PATCH 0513/1198] drm/amdkfd: fix scope of mqd_mgr dereference in pqm_debugfs_mqds Reading /sys/kernel/debug/kfd/mqds while a process holds an active KFD queue triggers a NULL pointer dereference because the for loop that calls mqd_mgr->debugfs_show_mqd() is incorrectly placed outside the if (pqn->q) block that initializes mqd_mgr. The queue list can contain entries where pqn->q is NULL (kernel queues where only pqn->kq is valid). In the original code: if (pqn->q) { ... mqd_mgr = q->device->dqm->mqd_mgrs[mqd_type]; size = mqd_mgr->mqd_stride(...); } for (xcc = 0; xcc < num_xccs; xcc++) { // WRONG: outside if block mqd = q->mqd + size * xcc; r = mqd_mgr->debugfs_show_mqd(m, mqd); } When iterating over a queue node where pqn->q is NULL: 1. The if (pqn->q) block is skipped 2. mqd_mgr remains uninitialized (NULL from declaration) 3. The for loop executes anyway 4. mqd_mgr->debugfs_show_mqd(m, mqd) dereferences NULL The crash manifests as: BUG: kernel NULL pointer dereference, address: 0000000000000000 #PF: supervisor instruction fetch in kernel mode RIP: 0010:0x0 Call Trace: pqm_debugfs_mqds+0x10c/0x1d0 [amdgpu] kfd_debugfs_mqds_by_process+0x9b/0x110 [amdgpu] seq_read_iter+0x132/0x4b0 ... Fix by moving the for loop inside the if (pqn->q) block, so mqd_mgr and related variables are only used when properly initialized. Closes: https://gitlab.freedesktop.org/drm/amd/-/work_items/5689 Reviewed-by: Alex Deucher Link: https://patch.msgid.link/20260831130051.2031435-1-mario.limonciello@amd.com Signed-off-by: Mario Limonciello Signed-off-by: Alex Deucher (cherry picked from commit 8bfe29d5c798940f797aa24135d2734c3ffce9de) Cc: stable@vger.kernel.org --- .../gpu/drm/amd/amdkfd/kfd_process_queue_manager.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index ef1d1cb46152..4fe40e9fcfc8 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -1169,13 +1169,13 @@ int pqm_debugfs_mqds(struct seq_file *m, void *data) mqd_mgr = q->device->dqm->mqd_mgrs[mqd_type]; size = mqd_mgr->mqd_stride(mqd_mgr, &q->properties); - } - for (xcc = 0; xcc < num_xccs; xcc++) { - mqd = q->mqd + size * xcc; - r = mqd_mgr->debugfs_show_mqd(m, mqd); - if (r != 0) - break; + for (xcc = 0; xcc < num_xccs; xcc++) { + mqd = q->mqd + size * xcc; + r = mqd_mgr->debugfs_show_mqd(m, mqd); + if (r != 0) + break; + } } } From 3b5c4f4a479d0e58a7500cbd2b09d62f719f48b8 Mon Sep 17 00:00:00 2001 From: Sunil Khatri Date: Mon, 31 Aug 2026 21:01:39 +0530 Subject: [PATCH 0514/1198] drm/amdgpu: fix byte/dword unit mismatch in coredump IB dump MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In amdgpu_devcoredump_print_ibs(), the NO_CPU_ACCESS VRAM path passed cursor.start/4 and cursor.size/4 to amdgpu_device_mm_access(), but that function's pos/size parameters are byte offsets/lengths (confirmed by amdgpu_ttm_vram_mm_access() and leading to wrong size calculation. Similarly with that change the off index needs to be calculated based on dword since that is a u32 type. Fixes: 7b15fc2d1f1a ("drm/amdgpu: dump job ibs in the devcoredump") Signed-off-by: Sunil Khatri Reviewed-by: Vitaly Prosyak Acked-by: Christian König Signed-off-by: Alex Deucher (cherry picked from commit 1bd613b0ed98a23575b18674c94b8b3392614681) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c index 87e15e39eb30..ec6e5bde7f80 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c @@ -299,10 +299,10 @@ amdgpu_devcoredump_print_ibs(struct drm_printer *p, amdgpu_res_first(abo->tbo.resource, offset, coredump->ibs[i].ib_size_dw * 4, &cursor); while (cursor.remaining) { - amdgpu_device_mm_access(adev, cursor.start / 4, - &ib_content[off], cursor.size / 4, + amdgpu_device_mm_access(adev, cursor.start, + &ib_content[off], cursor.size, false); - off += cursor.size; + off += cursor.size / 4; amdgpu_res_next(&cursor, cursor.size); } emit_content = true; From c748dd03df33360549ad60cdccee13570e9c0f90 Mon Sep 17 00:00:00 2001 From: Sunil Khatri Date: Mon, 31 Aug 2026 20:17:17 +0530 Subject: [PATCH 0515/1198] drm/amdgpu: update the fw version for gfx11 userqueues Update to the latest stable fw versions where userqueues is working as it is expected with major fixes. Signed-off-by: Sunil Khatri Acked-by: Alex Deucher Signed-off-by: Alex Deucher (cherry picked from commit d50201b891604ab97f305d4a20d888ba93305b48) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index 69776dbe188d..0ff5a80aa918 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -1651,10 +1651,10 @@ static int gfx_v11_0_sw_init(struct amdgpu_ip_block *ip_block) case IP_VERSION(11, 0, 2): case IP_VERSION(11, 0, 3): if (!adev->gfx.disable_uq && - adev->gfx.me_fw_version >= 2420 && - adev->gfx.pfp_fw_version >= 2580 && - adev->gfx.mec_fw_version >= 2650 && - adev->mes.fw_version[0] >= 120) { + adev->gfx.me_fw_version >= 3090 && + adev->gfx.pfp_fw_version >= 3190 && + adev->gfx.mec_fw_version >= 3450 && + adev->mes.fw_version[0] >= 147) { adev->userq_funcs[AMDGPU_HW_IP_GFX] = &userq_mes_funcs; adev->userq_funcs[AMDGPU_HW_IP_COMPUTE] = &userq_mes_funcs; } From 49a74a2388528c1a2e96f01114c4513e635605fe Mon Sep 17 00:00:00 2001 From: Sunil Khatri Date: Mon, 31 Aug 2026 20:18:31 +0530 Subject: [PATCH 0516/1198] drm/amdgpu: update the fw version for gfx12 userqueues Update to the latest stable fw versions where userqueues is working as it is expected with major fixes. Signed-off-by: Sunil Khatri Acked-by: Alex Deucher Signed-off-by: Alex Deucher (cherry picked from commit 69fa36e3ac92f2544ee7a1b719ec212b8247a2da) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c index 1e5fd1ef8f1d..e2a81a55c63b 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c @@ -1436,10 +1436,10 @@ static int gfx_v12_0_sw_init(struct amdgpu_ip_block *ip_block) case IP_VERSION(12, 0, 0): case IP_VERSION(12, 0, 1): if (!adev->gfx.disable_uq && - adev->gfx.me_fw_version >= 2780 && - adev->gfx.pfp_fw_version >= 2840 && - adev->gfx.mec_fw_version >= 3050 && - adev->mes.fw_version[0] >= 123) { + adev->gfx.me_fw_version >= 3090 && + adev->gfx.pfp_fw_version >= 3190 && + adev->gfx.mec_fw_version >= 3450 && + adev->mes.fw_version[0] >= 147) { adev->userq_funcs[AMDGPU_HW_IP_GFX] = &userq_mes_funcs; adev->userq_funcs[AMDGPU_HW_IP_COMPUTE] = &userq_mes_funcs; } From a26301203a196a991527f7b1ab884d4dd0e7c95e Mon Sep 17 00:00:00 2001 From: Kanala Ramalingeswara Reddy Date: Mon, 31 Aug 2026 19:59:11 +0530 Subject: [PATCH 0517/1198] drm/amdgpu: Skip accessing psp rum time db for APUs Psp runtime DB is for dGPUs only. Signed-off-by: Kanala Ramalingeswara Reddy Acked-by: Alex Deucher Signed-off-by: Alex Deucher (cherry picked from commit dce8195027f146467c9378efb2bb1b0859cb735e) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 04f6ebf31cca..42adc8e738d8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -396,6 +396,12 @@ static bool psp_get_runtime_db_entry(struct amdgpu_device *adev, bool ret = false; int i; + /* + * Runtime DB is for dGPUs only. + */ + if (adev->flags & AMD_IS_APU) + return false; + if (amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(13, 0, 6) || amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(13, 0, 12) || amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(13, 0, 14) || From 8b4a4193f3c0b532054990783f40930083c37618 Mon Sep 17 00:00:00 2001 From: Sunil Khatri Date: Tue, 1 Sep 2026 16:30:35 +0530 Subject: [PATCH 0518/1198] drm/amdgpu/userq: dont overwrite the error of subsequent map call If a queue fails to map that we need to return the error code back to the caller and not overwrite with a success specifically. Accumulate the failure and return that. Signed-off-by: Sunil Khatri Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher (cherry picked from commit 42a0197d10039e9518c0324c43331eb22b44d5f8) --- drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c index 0a816b3c5ff9..e43bda0cab3f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c @@ -1544,7 +1544,7 @@ int amdgpu_userq_post_reset(struct amdgpu_device *adev, bool vram_lost) struct amdgpu_usermode_queue *queue; const struct amdgpu_userq_funcs *userq_funcs; unsigned long queue_id; - int r = 0; + int ret = 0, r; xa_for_each(&adev->userq_doorbell_xa, queue_id, queue) { if (queue->state == AMDGPU_USERQ_STATE_HUNG && !vram_lost) { @@ -1555,6 +1555,7 @@ int amdgpu_userq_post_reset(struct amdgpu_device *adev, bool vram_lost) r = userq_funcs->map(queue); if (r) { dev_err(adev->dev, "Failed to remap queue %ld\n", queue_id); + ret = r; continue; } trace_amdgpu_userq_state_changed(queue, AMDGPU_USERQ_STATE_MAPPED); @@ -1562,5 +1563,5 @@ int amdgpu_userq_post_reset(struct amdgpu_device *adev, bool vram_lost) } } - return r; + return ret; } From 6293f2e1439fb440be1b606e647ce88e65562a38 Mon Sep 17 00:00:00 2001 From: Yuling Li Date: Tue, 1 Sep 2026 15:37:18 +0800 Subject: [PATCH 0519/1198] drm/amd/display: Fix cursor disable with horizontally split planes [WHY] resource_can_pipe_disable_cursor() disables the hardware cursor on a pipe when a higher layer fully covers that pipe's recout, to avoid double-cursor and scaling artifacts. When merging pipe-split halves of the same overlay layer, the inner loop walks every pipe above the current one and looks for siblings sharing test_pipe's layer_index. Because test_pipe itself satisfies that condition, it can be treated as its own split partner. That incorrectly doubles r2.width and makes the covering check succeed even when the overlay does not fully contain the underlying pipe. On horizontally split or multi-quadrant layouts this causes the cursor to disappear over overlay regions while input/coordinate mapping remains correct. [HOW] Skip test_pipe when searching for a pipe-split sibling on the same layer, so only the other half of the split plane is merged into r2. Signed-off-by: Yuling Li Reviewed-by: Leo Li Signed-off-by: Alex Deucher (cherry picked from commit 85ccd2c39cca9351d4db393e24acea8bf943d350) --- drivers/gpu/drm/amd/display/dc/core/dc_resource.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 7eaaf38cd9ab..fc9080f0c093 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1797,7 +1797,11 @@ bool resource_can_pipe_disable_cursor(struct pipe_ctx *pipe_ctx) * pipe-split, merge together per same height. */ for (split_pipe = pipe_ctx->top_pipe; split_pipe; - split_pipe = split_pipe->top_pipe) + split_pipe = split_pipe->top_pipe) { + + if (split_pipe == test_pipe) + continue; + if (split_pipe->plane_state->layer_index == test_pipe->plane_state->layer_index) { struct rect r2_half; @@ -1809,6 +1813,7 @@ bool resource_can_pipe_disable_cursor(struct pipe_ctx *pipe_ctx) r2_bottom = min(r2_bottom, r2_half.y + r2_half.height); break; } + } if (r1.x >= r2.x && r1.y >= r2.y && r1_right <= r2_right && r1_bottom <= r2_bottom) return true; From 13af55f71399f5e562f6cb59ad413476e513c4d4 Mon Sep 17 00:00:00 2001 From: Yogesh Mohan Marimuthu Date: Thu, 20 Aug 2026 09:52:50 +0530 Subject: [PATCH 0520/1198] drm/amdgpu/userq: fix struct drm_amdgpu_info_device padding for 32bit compile MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit need to pad before __u64 tcc_disabled_mask variable. This patch fixes 64bit Kernel + 32 bit mesa combination. But at the same time it will break 32bit Kernel(using this patch) + older 32bit mesa(not using this patch). This issue was discussd with alexander.deucher@amd.com, christian.koenig@amd.com and pierre-eric.pelloux-prayer@amd.com. Currently today 32 bit kernel + 32 bit userspace and 64 bit kernel and 64 bit userspace work. Mixed 64 bit kernel and 32 bit userspace is currently broken. Since 32 bit kernel and userspace is probably pretty rare these days and the data affected by this is not critical, Hence we can go ahead with this patch. Fixes: cf21e76a6005 ("drm/amdgpu: return tcc_disabled_mask to userspace") Signed-off-by: Yogesh Mohan Marimuthu Reviewed-by: Christian König Signed-off-by: Alex Deucher (cherry picked from commit 497b5090f2857ef8ad9a162aa31ada0de5814663) --- include/uapi/drm/amdgpu_drm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index b32c72a662b6..42a5fa8ad6b0 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -1512,6 +1512,7 @@ struct drm_amdgpu_info_device { __u64 high_va_max; /* gfx10 pa_sc_tile_steering_override */ __u32 pa_sc_tile_steering_override; + __u32 pad; /* disabled TCCs */ __u64 tcc_disabled_mask; __u64 min_engine_clock; @@ -1536,7 +1537,6 @@ struct drm_amdgpu_info_device { __u32 csa_alignment; /* Userq IP mask (1 << AMDGPU_HW_IP_*) */ __u32 userq_ip_mask; - __u32 pad; }; struct drm_amdgpu_info_hw_ip { From 5be5bdda5863eacc964b609ba927764f253431b3 Mon Sep 17 00:00:00 2001 From: Diego Oliva Date: Wed, 2 Sep 2026 11:42:07 +0100 Subject: [PATCH 0521/1198] smb: client: reject out-of-bounds DataOffset in CIFSSMBRead() The SMB1 synchronous read helper CIFSSMBRead() validates the server's DataLength against CIFSMaxBufSize and the caller's count, but never validates DataOffset. The copy source is formed as &pSMBr->hdr.Protocol + le16_to_cpu(pSMBr->DataOffset) and memcpy()'d for DataLength bytes with no check that the [DataOffset, DataOffset + DataLength) range lies within the response actually received from the server. A malicious or compromised SMB1 server can return a response carrying an in-range DataLength and a large DataOffset, driving the source pointer past the end of the response buffer. The memcpy() then copies adjacent kernel heap into the caller's read buffer (information disclosure), or reads unmapped memory and oopses (denial of service). SMB1 is not negotiated by default; reaching this code requires an explicit vers=1.0 mount. Both DataOffset and the received response length recorded in rsp_iov.iov_len are relative to the start of the SMB header, so reject the response unless DataOffset + DataLength fits within that length, using overflow-safe arithmetic, before forming the source pointer. The response length has been validated by the previous patch, so the DataOffset and DataLength fields can be read safely here. While here, make data_length unsigned. It holds a length derived from unsigned on-the-wire fields and is only ever compared against unsigned quantities; print it with %u accordingly, and add __func__ to the cifs_dbg() calls in this function. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable@vger.kernel.org # 6.19.x Assisted-by: Bynario AI Signed-off-by: Diego Oliva Reviewed-by: David Howells Signed-off-by: Paulo Alcantara --- fs/smb/client/cifssmb.c | 18 +++++++++++++----- fs/smb/client/trace.h | 1 + 2 files changed, 14 insertions(+), 5 deletions(-) diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index be13ab37039d..f9aff0712794 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -1728,7 +1728,8 @@ CIFSSMBRead(const unsigned int xid, struct cifs_io_parms *io_parms, rsp_iov.iov_len, tcon->ses->server->vals->read_rsp_size); *nbytes = 0; } else { - int data_length = le16_to_cpu(pSMBr->DataLengthHigh); + unsigned int data_length = le16_to_cpu(pSMBr->DataLengthHigh); + __u16 data_offset = le16_to_cpu(pSMBr->DataOffset); data_length = data_length << 16; data_length += le16_to_cpu(pSMBr->DataLength); *nbytes = data_length; @@ -1736,14 +1737,21 @@ CIFSSMBRead(const unsigned int xid, struct cifs_io_parms *io_parms, /*check that DataLength would not go beyond end of SMB */ if ((data_length > CIFSMaxBufSize) || (data_length > count)) { - cifs_dbg(FYI, "bad length %d for count %d\n", - data_length, count); + cifs_dbg(FYI, "%s: bad length %u for count %u\n", + __func__, data_length, count); rc = smb_EIO2(smb_eio_trace_read_overlarge, data_length, count); *nbytes = 0; + } else if (data_offset < sizeof(*pSMBr) || + (size_t)data_offset + data_length > rsp_iov.iov_len) { + /* check that the data lies within the received response */ + cifs_dbg(FYI, "%s: bad data offset %u length %u for response of %zu\n", + __func__, data_offset, data_length, rsp_iov.iov_len); + rc = smb_EIO2(smb_eio_trace_read_bad_offset, + data_offset, data_length); + *nbytes = 0; } else { - pReadData = (char *) (&pSMBr->hdr.Protocol) + - le16_to_cpu(pSMBr->DataOffset); + pReadData = (char *) (&pSMBr->hdr.Protocol) + data_offset; /* if (rc = copy_to_user(buf, pReadData, data_length)) { cifs_dbg(VFS, "Faulting on read rc = %d\n",rc); rc = -EFAULT; diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h index 12241abb8e2e..b442cccd1530 100644 --- a/fs/smb/client/trace.h +++ b/fs/smb/client/trace.h @@ -79,6 +79,7 @@ EM(smb_eio_trace_qreparse_setup_count, "qreparse_setup_count") \ EM(smb_eio_trace_qreparse_sizes_wrong, "qreparse_sizes_wrong") \ EM(smb_eio_trace_qsym_bcc_too_small, "qsym_bcc_too_small") \ + EM(smb_eio_trace_read_bad_offset, "read_bad_offset") \ EM(smb_eio_trace_read_mid_state_unknown, "read_mid_state_unknown") \ EM(smb_eio_trace_read_overlarge, "read_overlarge") \ EM(smb_eio_trace_read_rsp_malformed, "read_rsp_malformed") \ From d9d7eeb0cea5b55b82888f443622fd8d4ee064f3 Mon Sep 17 00:00:00 2001 From: Aohan Mei Date: Wed, 2 Sep 2026 20:52:13 +0800 Subject: [PATCH 0522/1198] smb: client: reject userspace cifs.idmap descriptions cifs.idmap key descriptions carry authority-bearing fields (owner and group SIDs and uid/gid values in "os:"/"gs:"/"oi:"/"gi:" form) that the cifs.idmap upcall helper treats as kernel-originating inputs. Unlike its sibling cifs.spnego, the cifs.idmap key type has no vet_description hook, so userspace can create keys of this type through request_key(2)/add_key(2) and supply those fields without CIFS origin. A request_key(2) call with a non-NULL callout then drives a root usermodehelper upcall (/sbin/request-key -> cifs.idmap) that consumes the unvetted description in root context. Only accept cifs.idmap descriptions while CIFS is using its private root_cred to request the key. id_to_sid()/sid_to_id() already run under override_creds(root_cred), so the kernel-originated path is unaffected. This mirrors commit 3da1fdf4efbc ("smb: client: reject userspace cifs.spnego descriptions"), which applied the same restriction to cifs.spnego. Fixes: 4d79dba0e007 ("cifs: Add idmap key and related data structures and functions (try #17 repost)") Reported-by: TencentOS Corvus AI Cc: stable@vger.kernel.org Assisted-by: CodeBuddy:Kimi-K3 Signed-off-by: Aohan Mei Acked-by: David Howells Signed-off-by: Paulo Alcantara --- fs/smb/client/cifsacl.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/fs/smb/client/cifsacl.c b/fs/smb/client/cifsacl.c index 12005f46307d..213a421bf8e9 100644 --- a/fs/smb/client/cifsacl.c +++ b/fs/smb/client/cifsacl.c @@ -100,8 +100,23 @@ cifs_idmap_key_destroy(struct key *key) kfree(key->payload.data[0]); } +static int +cifs_idmap_key_vet_description(const char *description) +{ + /* + * cifs.idmap descriptions are authority-bearing inputs to the + * cifs.idmap upcall helper. Only allow the kernel to create this + * type of key using the private root_cred installed in + * init_cifs_idmap; reject userspace request_key(2)/add_key(2). + */ + if (current_cred() != root_cred) + return -EPERM; + return 0; +} + static struct key_type cifs_idmap_key_type = { .name = "cifs.idmap", + .vet_description = cifs_idmap_key_vet_description, .instantiate = cifs_idmap_key_instantiate, .destroy = cifs_idmap_key_destroy, .describe = user_describe, From d806d5a85dcbe2a0f181b2f0f9f61ddfbefa1818 Mon Sep 17 00:00:00 2001 From: Karl Mehltretter Date: Wed, 2 Sep 2026 20:28:14 +0200 Subject: [PATCH 0523/1198] smb: client: pin DFS superblock in iterator callback tcon_super_cb() stores a raw superblock pointer, but __cifs_get_super() takes its active reference only after iterate_supers_type() has dropped s_umount and its passive reference. Concurrent DFS automount expiry can therefore free the superblock before cifs_sb_active() uses it. A deterministic KASAN test reproduces the race as: BUG: KASAN: slab-use-after-free in cifs_sb_active+0x77/0x80 The same test passes with this change applied. Take the active reference in the callback while iterate_supers_type() still holds s_umount shared. cifs_put_tcp_super() remains the matching release. Fixes: bacd704a95ad ("cifs: handle prefix paths in reconnect") Cc: stable@vger.kernel.org Assisted-by: LLM Signed-off-by: Karl Mehltretter Signed-off-by: Paulo Alcantara --- fs/smb/client/misc.c | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c index 46e1382e8e04..d4db3f91a91f 100644 --- a/fs/smb/client/misc.c +++ b/fs/smb/client/misc.c @@ -891,8 +891,14 @@ static void tcon_super_cb(struct super_block *sb, void *arg) t1->ses->dfs_root_ses == t2->ses->dfs_root_ses) && t1->ses->server == t2->ses->server && t2->origin_fullpath && - dfs_src_pathname_equal(t2->origin_fullpath, t1->origin_fullpath)) + dfs_src_pathname_equal(t2->origin_fullpath, t1->origin_fullpath)) { + /* + * Take the active reference while iterate_supers_type() still + * holds s_umount shared. + */ + cifs_sb_active(sb); sd->sb = sb; + } spin_unlock(&t2->tc_lock); } @@ -909,15 +915,8 @@ static struct super_block *__cifs_get_super(void (*f)(struct super_block *, void for (; *fs_type; fs_type++) { iterate_supers_type(*fs_type, f, &sd); - if (sd.sb) { - /* - * Grab an active reference in order to prevent automounts (DFS links) - * of expiring and then freeing up our cifs superblock pointer while - * we're doing failover. - */ - cifs_sb_active(sd.sb); + if (sd.sb) return sd.sb; - } } pr_warn_once("%s: could not find dfs superblock\n", __func__); return ERR_PTR(-EINVAL); From 74cb39735b6cd0aff4b5584158f09376fd97aadf Mon Sep 17 00:00:00 2001 From: Kyle Zeng Date: Mon, 10 Aug 2026 15:10:34 -0700 Subject: [PATCH 0524/1198] ipvs: reject invalid states in connection template sync records IPVS sync receivers validate protocol states before creating or updating a connection. For connection templates, however, they only log states outside the template state range and still store the value in the connection. A template can be returned by ordinary connection lookup. TCP and SCTP then use the invalid state as an index into their transition tables. Reject invalid template states in both sync protocol versions before looking up or modifying a connection. The version 1 path handles both IPv4 and IPv6 records. Fixes: 275411430f89 ("ipvs: add assured state for conn templates") Cc: stable@vger.kernel.org Assisted-by: Codex:gpt-5.6-sol Signed-off-by: Kyle Zeng Acked-by: Julian Anastasov Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipvs/ip_vs_sync.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index ea5fdd4f4ce7..1deb063cd72c 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -999,10 +999,10 @@ static void ip_vs_process_message_v0(struct netns_ipvs *ipvs, const char *buffer pp->name, state); continue; } - } else { - if (state >= IP_VS_CTPL_S_LAST) - IP_VS_DBG(7, "BACKUP v0, Invalid tpl state %u\n", - state); + } else if (state >= IP_VS_CTPL_S_LAST) { + IP_VS_DBG(7, "BACKUP v0, Invalid tpl state %u\n", + state); + continue; } ip_vs_conn_fill_param(ipvs, AF_INET, s->protocol, @@ -1159,10 +1159,10 @@ static inline int ip_vs_proc_sync_conn(struct netns_ipvs *ipvs, __u8 *p, __u8 *m retc = 40; goto out; } - } else { - if (state >= IP_VS_CTPL_S_LAST) - IP_VS_DBG(7, "BACKUP, Invalid tpl state %u\n", - state); + } else if (state >= IP_VS_CTPL_S_LAST) { + IP_VS_DBG(7, "BACKUP, Invalid tpl state %u\n", state); + retc = 40; + goto out; } if (ip_vs_conn_fill_param_sync(ipvs, af, s, ¶m, pe_data, pe_data_len, pe_name, pe_name_len)) { From b04578b74f2d3755548fe9e829e3b2a6c6f966a1 Mon Sep 17 00:00:00 2001 From: Kyle Zeng Date: Mon, 10 Aug 2026 15:13:47 -0700 Subject: [PATCH 0525/1198] ipvs: fix reversed sequence option serialization hton_seq() expects the host-order source first and the unaligned network-order destination second. The version 1 sync sender passes these arguments in reverse for both sequence blocks. This leaves 24 bytes of the kmalloc-backed message unwritten. It may disclose stale heap data and replace the live connection sequence state with values read from the buffer. Pass the connection sequence state as the source and the message payload as the destination for both blocks. Fixes: 986a07579533 ("IPVS: Backup, Change sending to Version 1 format") Assisted-by: Codex:gpt-5.6-sol Signed-off-by: Kyle Zeng Acked-by: Julian Anastasov Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipvs/ip_vs_sync.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 1deb063cd72c..5383aeafb0ae 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -747,9 +747,9 @@ void ip_vs_sync_conn(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, int pkts) if (cp->flags & IP_VS_CONN_F_SEQ_MASK) { *(p++) = IPVS_OPT_SEQ_DATA; *(p++) = sizeof(struct ip_vs_sync_conn_options); - hton_seq((struct ip_vs_seq *)p, &cp->in_seq); + hton_seq(&cp->in_seq, (struct ip_vs_seq *)p); p += sizeof(struct ip_vs_seq); - hton_seq((struct ip_vs_seq *)p, &cp->out_seq); + hton_seq(&cp->out_seq, (struct ip_vs_seq *)p); p += sizeof(struct ip_vs_seq); } /* Handle pe data */ From e8f8231824b5815f57ce62cba116e511b10196de Mon Sep 17 00:00:00 2001 From: Joas Antonio dos Santos Date: Tue, 18 Aug 2026 06:31:43 -0700 Subject: [PATCH 0526/1198] netfilter: nf_conntrack_sip: fix OOB read in sip_skip_whitespace() sip_skip_whitespace() returns dptr unchanged when its own loop exhausts the buffer (dptr == limit), instead of NULL like its sibling sip_follow_continuation() returns on its own "no more data" path. ct_sip_get_header() only checks for NULL after calling it: dptr = sip_skip_whitespace(dptr, limit); if (dptr == NULL) break; if (*dptr != ':' || ++dptr >= limit) break; so a recognized header name followed only by spaces/tabs running to the exact end of the SIP payload, with no colon, makes the very next statement read one byte past the buffer. Make both "no more data" outcomes return NULL, matching the convention sip_follow_continuation() already uses and that both existing callers already check for. Fixes: ea45f12a2766d ("[NETFILTER]: nf_conntrack_sip: parse SIP headers properly") Signed-off-by: Joas Antonio dos Santos Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_sip.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 3ccf34fc1c53..64bc440b1181 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -423,7 +423,7 @@ static const char *sip_skip_whitespace(const char *dptr, const char *limit) dptr = sip_follow_continuation(dptr, limit); break; } - return dptr; + return dptr < limit ? dptr : NULL; } /* Search within a SIP header value, dealing with continuation lines */ From fec9b1de0d02de8dafa3cc344bcb91cf28660643 Mon Sep 17 00:00:00 2001 From: Chengfeng Ye Date: Mon, 24 Aug 2026 20:12:38 +0800 Subject: [PATCH 0527/1198] netfilter: cttimeout: prevent UAF during module unload nf_ct_set_timeout() protects the timeout hook dereference and policy lookup with rcu_read_lock(). cttimeout_exit(), however, unregisters the per-net operations before it clears the hook. This allows the following interleaving: CPU 0 CPU 1 cttimeout_exit() nf_ct_set_timeout() unregister_pernet_subsys() rcu_read_lock() kfree(pernet) h = nf_ct_timeout_hook h->timeout_find_get() nfct_timeout_pernet() The hook still points to ctnl_timeout_find_get() when CPU 1 looks up the already freed per-net timeout list. KASAN reported: BUG: KASAN: slab-use-after-free in ctnl_timeout_find_get Read of size 8 by task poc/90 Call Trace: ctnl_timeout_find_get+0x271/0x2a0 [nfnetlink_cttimeout] nf_ct_set_timeout+0x7b/0x3c0 xt_ct_tg_check+0x724/0xb20 xt_check_target+0x234/0xa90 do_ipt_set_ctl+0x570/0x1270 Allocated by task 89: __kmalloc_noprof+0x16e/0x460 ops_init+0x6d/0x420 register_pernet_operations+0x2f6/0x670 Freed by task 91: kfree+0x131/0x390 ops_undo_list+0x3d4/0x730 unregister_pernet_operations+0x232/0x490 unregister_pernet_subsys+0x1c/0x30 cttimeout_exit+0x52/0x970 [nfnetlink_cttimeout] Clear the hook and wait for existing readers before unregistering the per-net operations. This blocks new policy lookups and ensures readers that observed the hook finish before the per-net storage is freed. Fixes: ebfbe67568a7 ("netfilter: cttimeout: use net_generic infra") Cc: stable@vger.kernel.org Signed-off-by: Chengfeng Ye Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink_cttimeout.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 66c2016f6049..132c02ac7c4e 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -652,9 +652,9 @@ static void __exit cttimeout_exit(void) { nfnetlink_subsys_unregister(&cttimeout_subsys); - unregister_pernet_subsys(&cttimeout_ops); RCU_INIT_POINTER(nf_ct_timeout_hook, NULL); synchronize_net(); + unregister_pernet_subsys(&cttimeout_ops); } module_init(cttimeout_init); From 2c018cc4842c33f0c732962e2ab58635e8ae5823 Mon Sep 17 00:00:00 2001 From: Chengfeng Ye Date: Mon, 24 Aug 2026 01:05:38 +0800 Subject: [PATCH 0528/1198] netfilter: nf_log: unregister loggers before per-net teardown nf_log_syslog and nfnetlink_log unregister their per-network namespace operations before unregistering their global logger backends. This leaves a window where a sysctl or netlink writer can rebind the still- registered logger after the per-net pre-exit callback cleared the old selection. The race looks like this: CPU 0 CPU 1 ---- ---- unregister_pernet_subsys() nf_log_unset(net, logger) net->nf.nf_loggers[pf] = NULL lock nf_log_mutex find logger in loggers[][] net->nf.nf_loggers[pf] = logger unlock nf_log_mutex nf_log_unregister(logger) lock nf_log_mutex loggers[pf][type] = NULL unlock nf_log_mutex synchronize_rcu() module exit returns module core frees backend memory Later, a sysctl read or packet logging operation can dereference the stale per-net logger pointer. Fix this by unregistering the global logger backends before tearing down per-net state. Once the global registrations are gone, later writers can no longer rebind the logger. unregister_pernet_subsys() already waits for an RCU grace period after the pre-exit callback clears the per-net selection, while nf_log_unregister() continues to cover readers of the global logger table. Apply this ordering fix to both nf_log backends that combine per-net teardown with global logger registration. Fixes: 5b023fc8d8e0 ("netfilter: enable per netns support for nf_loggers") Cc: stable@vger.kernel.org Signed-off-by: Chengfeng Ye Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_log_syslog.c | 2 +- net/netfilter/nfnetlink_log.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nf_log_syslog.c b/net/netfilter/nf_log_syslog.c index f24288088c0d..c3fd398ffcd7 100644 --- a/net/netfilter/nf_log_syslog.c +++ b/net/netfilter/nf_log_syslog.c @@ -1073,12 +1073,12 @@ static int __init nf_log_syslog_init(void) static void __exit nf_log_syslog_exit(void) { - unregister_pernet_subsys(&nf_log_syslog_net_ops); nf_log_unregister(&nf_ip_logger); nf_log_unregister(&nf_arp_logger); nf_log_unregister(&nf_ip6_logger); nf_log_unregister(&nf_netdev_logger); nf_log_unregister(&nf_bridge_logger); + unregister_pernet_subsys(&nf_log_syslog_net_ops); } module_init(nf_log_syslog_init); diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 6c7fa2ed34f5..9d7fec570abe 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -1233,8 +1233,8 @@ static void __exit nfnetlink_log_fini(void) { nfnetlink_subsys_unregister(&nfulnl_subsys); netlink_unregister_notifier(&nfulnl_rtnl_notifier); - unregister_pernet_subsys(&nfnl_log_net_ops); nf_log_unregister(&nfulnl_logger); + unregister_pernet_subsys(&nfnl_log_net_ops); } MODULE_DESCRIPTION("netfilter userspace logging"); From f36d94a20ca185bcadef3a10b980cd2cfd72d53a Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Tue, 1 Sep 2026 23:21:37 +0900 Subject: [PATCH 0529/1198] tracing/probes: Fix anon_stack check for unnamed bitfields in btf_find_struct_member btf_find_struct_member() traverses into nested anonymous structures and unions by pushing members with !member->name_off onto anon_stack. However, it does not consider the unnamed bitfields (e.g. `int : 5` or `unsigned int : 0`) which also have member->name_off == 0. If such an unnamed bitfield is pushed to anon_stack, the btf_find_struct_member() return an error even if there are other valid entries in anon_stack. To fix this, only push unnamed struct/union members to anon_stack. Also move the btf_type_is_struct() check to the entry of this function because now it is sure only struct/union are pushed to anon_stack. Link: https://lore.kernel.org/all/178827249775.123716.7813217688423513612.stgit@devnote2/ Fixes: 302db0f5b3d8 ("tracing/probes: Add a function to search a member of a struct/union") Cc: stable@vger.kernel.org Reported-by: Sashiko Closes: https://lore.kernel.org/all/20260830143859.D56991F00A3D@smtp.kernel.org/ Signed-off-by: Masami Hiramatsu (Google) Reviewed-by: Steven Rostedt --- kernel/trace/trace_btf.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/kernel/trace/trace_btf.c b/kernel/trace/trace_btf.c index 00172f301f25..d3ba356d5503 100644 --- a/kernel/trace/trace_btf.c +++ b/kernel/trace/trace_btf.c @@ -74,24 +74,24 @@ const struct btf_member *btf_find_struct_member(struct btf *btf, { struct btf_anon_stack *anon_stack; const struct btf_member *member; + const struct btf_type *mtype; u32 tid, cur_offset = 0; const char *name; int i, top = 0; + if (!btf_type_is_struct(type)) + return ERR_PTR(-EINVAL); + anon_stack = kzalloc_objs(*anon_stack, BTF_ANON_STACK_MAX); if (!anon_stack) return ERR_PTR(-ENOMEM); retry: - if (!btf_type_is_struct(type)) { - member = ERR_PTR(-EINVAL); - goto out; - } - for_each_member(i, type, member) { if (!member->name_off) { /* Anonymous union/struct: push it for later use */ - if (btf_type_skip_modifiers(btf, member->type, &tid) && + mtype = btf_type_skip_modifiers(btf, member->type, &tid); + if (mtype && btf_type_is_struct(mtype) && top < BTF_ANON_STACK_MAX) { anon_stack[top].tid = tid; anon_stack[top++].offset = From 47e93045a2db80d24f5fef65adecc6b2b32efa23 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Tue, 1 Sep 2026 23:21:49 +0900 Subject: [PATCH 0530/1198] tracing/probes: Fix BTF kflag check for anonymous struct member access btf_find_struct_member() traverses into nested anonymous structures and unions to find a struct member. However, get_bitoffset_of_field() in trace_probe.c checked btf_type_kflag(type) using the outer parent type instead of the actual anonymous structure/union that directly contains the found member. If the parent structure and anonymous structure have mismatched kflags (e.g., the parent has kflag=0 while the anonymous structure has kflag=1 because it contains bitfields), the bitfield size encoded in the upper 8 bits of member->offset is erroneously treated as part of the byte/bit offset, corrupting the resolved offset and failing to set last_bitsize. Similarly, btf_find_struct_member() pushed anonymous member offsets onto anon_stack without masking BTF_MEMBER_BIT_OFFSET() when kflag is set. To fix this problem, update btf_find_struct_member() to return actual containing structure/union type via member_type, use appropriate __btf_member_bit_offset() to get bit offset, and use member_type for btf_type_kflag() in get_bitoffset_of_field(). Link: https://lore.kernel.org/all/178827250904.123716.17452648791331881284.stgit@devnote2/ Fixes: c440adfbe302 ("tracing/probes: Support BTF based data structure field access") Cc: stable@vger.kernel.org Reported-by: Sashiko Closes: https://lore.kernel.org/all/20260822095110.0772E1F000E9@smtp.kernel.org/ Assisted-by: Antigravity:gemini-3.7-flash Signed-off-by: Masami Hiramatsu (Google) Reviewed-by: Steven Rostedt --- kernel/trace/trace_btf.c | 19 +++++++++++-------- kernel/trace/trace_btf.h | 3 ++- kernel/trace/trace_probe.c | 5 +++-- 3 files changed, 16 insertions(+), 11 deletions(-) diff --git a/kernel/trace/trace_btf.c b/kernel/trace/trace_btf.c index d3ba356d5503..ee7a04886bf6 100644 --- a/kernel/trace/trace_btf.c +++ b/kernel/trace/trace_btf.c @@ -61,16 +61,17 @@ struct btf_anon_stack { /* * Find a member of data structure/union by name and return it. - * Return NULL if not found, or -EINVAL if parameter is invalid. - * If the member is an member of anonymous union/structure, the offset - * of that anonymous union/structure is stored into @anon_offset. Caller - * can calculate the correct offset from the root data structure by - * adding anon_offset to the member's offset. + * Return NULL if not found, or ERR_PTR(-EINVAL) if parameter is invalid. + * If the member is a member of an anonymous union/structure, the bit offset + * of that anonymous union/structure is stored into @anon_offset. + * If @member_type is non-NULL, the actual containing structure/union type + * of the found member is stored into @member_type. */ const struct btf_member *btf_find_struct_member(struct btf *btf, const struct btf_type *type, const char *member_name, - u32 *anon_offset) + u32 *anon_offset, + const struct btf_type **member_type) { struct btf_anon_stack *anon_stack; const struct btf_member *member; @@ -94,14 +95,16 @@ const struct btf_member *btf_find_struct_member(struct btf *btf, if (mtype && btf_type_is_struct(mtype) && top < BTF_ANON_STACK_MAX) { anon_stack[top].tid = tid; - anon_stack[top++].offset = - cur_offset + member->offset; + anon_stack[top++].offset = cur_offset + + __btf_member_bit_offset(type, member); } } else { name = btf_name_by_offset(btf, member->name_off); if (name && !strcmp(member_name, name)) { if (anon_offset) *anon_offset = cur_offset; + if (member_type) + *member_type = type; goto out; } } diff --git a/kernel/trace/trace_btf.h b/kernel/trace/trace_btf.h index 4bc44bc261e6..4bd26bceae23 100644 --- a/kernel/trace/trace_btf.h +++ b/kernel/trace/trace_btf.h @@ -8,4 +8,5 @@ const struct btf_param *btf_get_func_param(const struct btf_type *func_proto, const struct btf_member *btf_find_struct_member(struct btf *btf, const struct btf_type *type, const char *member_name, - u32 *anon_offset); + u32 *anon_offset, + const struct btf_type **member_type); diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index c4163904ba74..144e790077c6 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -625,6 +625,7 @@ static int get_bitoffset_of_field(char **pfieldname, const struct btf_type **pty { const struct btf_type *type = *ptype; const struct btf_member *field; + const struct btf_type *mtype; struct btf *btf = ctx_btf(ctx); char *fieldname = *pfieldname; int bitoffs = 0; @@ -640,7 +641,7 @@ static int get_bitoffset_of_field(char **pfieldname, const struct btf_type **pty anon_offs = 0; field = btf_find_struct_member(btf, type, fieldname, - &anon_offs); + &anon_offs, &mtype); if (IS_ERR(field)) { trace_probe_log_err(ctx->offset, BAD_BTF_TID); return PTR_ERR(field); @@ -653,7 +654,7 @@ static int get_bitoffset_of_field(char **pfieldname, const struct btf_type **pty bitoffs += anon_offs; /* Accumulate the bit-offsets of the dot-connected fields */ - if (btf_type_kflag(type)) { + if (btf_type_kflag(mtype)) { bitoffs += BTF_MEMBER_BIT_OFFSET(field->offset); ctx->last_bitsize = BTF_MEMBER_BITFIELD_SIZE(field->offset); } else { From 871e07b6e3841cc9a258572c9ce8d1ea65f6ce7b Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Tue, 1 Sep 2026 23:22:00 +0900 Subject: [PATCH 0531/1198] tracing/probes: Fix code indent in get_bitoffset_of_field() Fix code block indentation introduced by commit f21834524025 ("tracing/probes: Support field specifier option for typecast"). Link: https://lore.kernel.org/all/178827252027.123716.7095571176291547259.stgit@devnote2/ Signed-off-by: Masami Hiramatsu (Google) Reviewed-by: Steven Rostedt --- kernel/trace/trace_probe.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 144e790077c6..908b4b6bc2df 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -662,11 +662,11 @@ static int get_bitoffset_of_field(char **pfieldname, const struct btf_type **pty ctx->last_bitsize = 0; } - type = btf_type_skip_modifiers(btf, field->type, NULL); - if (!type) { - trace_probe_log_err(ctx->offset, BAD_BTF_TID); - return -EINVAL; - } + type = btf_type_skip_modifiers(btf, field->type, NULL); + if (!type) { + trace_probe_log_err(ctx->offset, BAD_BTF_TID); + return -EINVAL; + } if (next) ctx->offset += next - fieldname; From 86b7a239ec6b14a7544200ede85474c6f5526049 Mon Sep 17 00:00:00 2001 From: Henry Martin Date: Wed, 26 Aug 2026 11:00:09 +0800 Subject: [PATCH 0532/1198] tracing/probes: Fix use-after-free on field name/type of events with multiple probes The fields of a probe-based dynamic event (kprobe, uprobe, eprobe and fprobe events) are created in traceprobe_define_arg_fields() by handing the probe_arg name/type strings to trace_define_field(), which only stores the pointers without copying. Those strings are owned by the trace_probe and are freed when that probe is removed. An event can have several probes attached. The field list is defined only once, by the first probe that registers the event, but it is kept alive by any surviving sibling probe. Deleting just that first probe by symbol - # primary A: fields are defined from A's args echo 'p:kprobes/ev vfs_read a1=$arg1' > kprobe_events # append B: shares A's event call echo 'p:kprobes/ev vfs_write a1=$arg1' >> kprobe_events # delete only A (matched by symbol), B survives echo '-:kprobes/ev vfs_read' >> kprobe_events frees A's args (trace_probe_cleanup() -> traceprobe_free_probe_arg()), but trace_probe_unlink() keeps the trace_probe_event because the probe list is not empty. The event call stays registered via B while its fields now reference freed memory. Any field lookup then reads it, e.g. echo 'a1 == 1' > events/kprobes/ev/filter BUG: KASAN: slab-use-after-free in strcmp+0xa7/0xb0 Call Trace: strcmp trace_find_event_field parse_pred process_preds create_filter apply_event_filter event_filter_write field->name references parg->name (kstrdup'd, freed with the probe) and, for array arguments, field->type references parg->fmt (kmalloc'd, freed with the probe) - the scalar type otherwise points at the static fmttype rodata, which is safe. Have traceprobe_define_arg_fields() duplicate the name and type strings and anchor the copies on the trace_probe_event, which embeds the event call and outlives every individual probe; trace_probe_event_free() releases them. The reproducer above triggers reliably; the field lookup and the delete both run under event_mutex, so this is a dangling reference after removal rather than a race. The issue was found by the autokbug dynamic kernel fuzzer at Tencent Yunding Lab. Link: https://lore.kernel.org/all/20260826030009.1855331-1-bsdhenrymartin@gmail.com/ Fixes: ca89bc071d5e4 ("tracing/kprobe: Add multi-probe per event support") Signed-off-by: Henry Martin Signed-off-by: Masami Hiramatsu (Google) --- kernel/trace/trace_probe.c | 48 +++++++++++++++++++++++++++++++++++++- kernel/trace/trace_probe.h | 2 ++ 2 files changed, 49 insertions(+), 1 deletion(-) diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 908b4b6bc2df..804442b2f7d2 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -2553,19 +2553,60 @@ int traceprobe_set_print_fmt(struct trace_probe *tp, enum probe_print_type ptype int traceprobe_define_arg_fields(struct trace_event_call *event_call, size_t offset, struct trace_probe *tp) { + struct trace_probe_event *tpe = trace_probe_event_from_call(event_call); int ret, i; + /* + * A field created by trace_define_field() only stores the name and + * type pointers, it does not copy the strings. Here they point into + * the probe_arg of @tp, which is freed when @tp is removed. For an + * event with multiple probes attached, the field list is defined + * once by the first probe but kept alive by the surviving siblings, + * so removing that first probe would leave the fields referencing + * freed memory. Duplicate the strings and anchor the copies on the + * trace_probe_event, which lives as long as the field list itself. + * + * event_define_fields() ignores the return value of this hook, so + * if a previous attempt failed before creating any field, it may + * call here again. Release duplicates left behind by such an + * attempt before starting over. + */ + for (i = 0; i < tpe->nr_field_strings; i++) + kfree(tpe->field_strings[i]); + kfree(tpe->field_strings); + tpe->field_strings = NULL; + tpe->nr_field_strings = 0; + + if (tp->nr_args) { + tpe->field_strings = kcalloc(tp->nr_args * 2, sizeof(char *), + GFP_KERNEL); + if (!tpe->field_strings) + return -ENOMEM; + } + /* Set argument names as fields */ for (i = 0; i < tp->nr_args; i++) { struct probe_arg *parg = &tp->args[i]; const char *fmt = parg->type->fmttype; int size = parg->type->size; + char *name, *type; if (parg->fmt) fmt = parg->fmt; if (parg->count) size *= parg->count; - ret = trace_define_field(event_call, fmt, parg->name, + + name = kstrdup(parg->name, GFP_KERNEL); + type = kstrdup(fmt, GFP_KERNEL); + if (!name || !type) { + kfree(name); + kfree(type); + return -ENOMEM; + } + tpe->field_strings[tpe->nr_field_strings++] = name; + tpe->field_strings[tpe->nr_field_strings++] = type; + + ret = trace_define_field(event_call, type, name, offset + parg->offset, size, parg->type->is_signed, FILTER_OTHER); @@ -2577,6 +2618,11 @@ int traceprobe_define_arg_fields(struct trace_event_call *event_call, static void trace_probe_event_free(struct trace_probe_event *tpe) { + int i; + + for (i = 0; i < tpe->nr_field_strings; i++) + kfree(tpe->field_strings[i]); + kfree(tpe->field_strings); kfree(tpe->class.system); kfree(tpe->call.name); kfree(tpe->call.print_fmt); diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index fba1af092a9b..d1fb3520700f 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -264,6 +264,8 @@ struct trace_probe_event { struct trace_event_call call; struct list_head files; struct list_head probes; + char **field_strings; + int nr_field_strings; struct trace_uprobe_filter filter[]; }; From 0c4256196b3a105307e2235fbfd85e768bbcdd0f Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Sun, 30 Aug 2026 23:27:23 +0900 Subject: [PATCH 0533/1198] kprobes: Protect kprobe_blacklist with RCU __within_kprobe_blacklist() traverses kprobe_blacklist without holding kprobe_mutex. When a module is unloaded, kprobe_remove_area_blacklist() removes blacklist entries and immediately frees them with kfree(). A concurrent call to within_kprobe_blacklist() can therefore dereference freed memory. Furthermore, within_kprobe_blacklist() can be called in atomic or non-preemptible contexts where the sleeping kprobe_mutex cannot be taken. Protect kprobe_blacklist with RCU. Use guard(rcu)() and list_for_each_entry_rcu() for traversal, list_add_tail_rcu() for insertions, list_del_rcu() for deletions, and kfree_rcu() to reclaim entries safely after a grace period. Link: https://lore.kernel.org/all/178810004323.64882.16493230858653316962.stgit@devnote2/ Fixes: 376e242429bf ("kprobes: Introduce NOKPROBE_SYMBOL() macro to maintain kprobes blacklist") Cc: stable@vger.kernel.org Reported-by: Sashiko Closes: https://lore.kernel.org/all/20260807155802.F06041F000E9@smtp.kernel.org/ Assisted-by: Antigravity:gemini-3.7-flash Signed-off-by: Masami Hiramatsu (Google) --- include/linux/kprobes.h | 1 + kernel/kprobes.c | 14 ++++++++++---- 2 files changed, 11 insertions(+), 4 deletions(-) diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 8c4f3bb24429..e6de7ae55bda 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -181,6 +181,7 @@ struct kprobe_blacklist_entry { struct list_head list; unsigned long start_addr; unsigned long end_addr; + struct rcu_head rcu; }; #ifdef CONFIG_KPROBES diff --git a/kernel/kprobes.c b/kernel/kprobes.c index bfc89083daa9..6337da5cab9e 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1447,8 +1447,14 @@ static bool __within_kprobe_blacklist(unsigned long addr) /* * If 'kprobe_blacklist' is defined, check the address and * reject any probe registration in the prohibited area. + * Note: this can return true during transition period where + * (start_addr, end_addr) in the black list is shrinking + * but old entry has not been removed yet. This is acceptable + * because the worst case is that we reject more probes than + * we should. */ - list_for_each_entry(ent, &kprobe_blacklist, list) { + guard(rcu)(); + list_for_each_entry_rcu(ent, &kprobe_blacklist, list) { if (addr >= ent->start_addr && addr < ent->end_addr) return true; } @@ -2509,7 +2515,7 @@ int kprobe_add_ksym_blacklist(unsigned long entry) ent->start_addr = entry; ent->end_addr = entry + size; INIT_LIST_HEAD(&ent->list); - list_add_tail(&ent->list, &kprobe_blacklist); + list_add_tail_rcu(&ent->list, &kprobe_blacklist); return (int)size; } @@ -2603,8 +2609,8 @@ static void kprobe_remove_area_blacklist(unsigned long start, unsigned long end) list_for_each_entry_safe(ent, n, &kprobe_blacklist, list) { if (ent->start_addr < start || ent->start_addr >= end) continue; - list_del(&ent->list); - kfree(ent); + list_del_rcu(&ent->list); + kfree_rcu(ent, rcu); } } From 374b2c5561db80fcdd7cdce44af37a49416f61c7 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Wed, 2 Sep 2026 16:36:57 -0700 Subject: [PATCH 0534/1198] bpf: reject BPF_PSEUDO_FUNC reference to the main program fixups.c:jit_subprogs() rewrites BPF_PSEUDO_FUNC loads to contain real function addresses. This function is invoked from bpf_jit_subprogs() only when env->subprog_cnt > 1. Meaning that for any program like below: int main(void *ctx) { void *ptr = main; ... bpf_timer_set_callback(..., ptr); ... } The 'ptr' won't be ever converted to contain an address. In combination with e.g. bpf_timer_set_callback() this would lead to a function call at a bogus address. Instead of complicating the implementation, just assume that no useful program needs main to be a sync or async callback and reject BPF_PSEUDO_FUNC loads for the main subprogram. Fixes: 69c087ba6225 ("bpf: Add bpf_for_each_map_elem() helper") Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260902233658.1186477-1-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e64035683795..7d8ddb1bee00 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -17089,6 +17089,15 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) verbose(env, "callback function not static\n"); return -EINVAL; } + /* + * When env->subprog_cnt == 1 this instruction won't be rewritten + * to hold a real function address. Assume that no usable program + * combines e.g. main and timer callback and just reject here. + */ + if (subprogno == 0) { + verbose(env, "callback function cannot be the main program\n"); + return -EINVAL; + } dst_reg->type = PTR_TO_FUNC; dst_reg->subprogno = subprogno; From ac0aaef0aa997fcdcb2458bd584539ba8608d33e Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Wed, 2 Sep 2026 16:36:58 -0700 Subject: [PATCH 0535/1198] selftests/bpf: BPF_PSEUDO_FUNC reference to the main program Add a test case for a BPF_PSEUDO_FUNC load instruction that references the entry function of the program it belongs to. W/o the previous patch the verifier accepts this program thus allowing a runtime call at a bogus address. See previous patch for detailed description. Main function needs to be marked with BTF_FUNC_STATIC for the test to trigger the bug, the patch uses test_verifier harness instead of test_prog because libbpf has no way to convey this. Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260902233658.1186477-2-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov --- .../selftests/bpf/verifier/pseudo_func.c | 45 +++++++++++++++++++ 1 file changed, 45 insertions(+) create mode 100644 tools/testing/selftests/bpf/verifier/pseudo_func.c diff --git a/tools/testing/selftests/bpf/verifier/pseudo_func.c b/tools/testing/selftests/bpf/verifier/pseudo_func.c new file mode 100644 index 000000000000..63c5c67d51de --- /dev/null +++ b/tools/testing/selftests/bpf/verifier/pseudo_func.c @@ -0,0 +1,45 @@ +/* + * Buggy verifier accepted the program below while not patching BPF_PSEUDO_FUNC + * load instruction to contain a real address. Which resulted in a function call + * to a bogus address. + */ +{ + "BPF_PSEUDO_FUNC reference to the main program", + .insns = { + /* r6 = bpf_map_lookup_elem(&timer_map, &(int){0}); */ + BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 10), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + /* bpf_timer_init(r6, &timer_map, 0); */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_timer_init), + /* bpf_timer_set_callback(r6, ); */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, BPF_REG_2, BPF_PSEUDO_FUNC, 0, -15), + BPF_RAW_INSN(0, 0, 0, 0, 0), + BPF_EMIT_CALL(BPF_FUNC_timer_set_callback), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .fixup_map_timer = { 3, 9 }, + .result = REJECT, + .errstr = "callback function cannot be the main program", + .func_info = { { 0, 4 /* main_prog */ } }, + .func_info_cnt = 1, + .btf_strings = "\0int\0ctx\0main_prog", + .btf_types = { + /* 1: int */ BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), + /* 2: void* */ BTF_PTR_ENC(0), + /* 3: int __(void *) */ BTF_FUNC_PROTO_ENC(1, 1), + BTF_FUNC_PROTO_ARG_ENC(5, 2), + /* 4: main_prog */ BTF_FUNC_ENC(9, 3), + BTF_END_RAW + } +}, From af602c7aa5fedc9be3043244017aef4f26c96b70 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 31 Aug 2026 20:30:42 +0000 Subject: [PATCH 0536/1198] bonding: do not clear curr_active_slave prematurely when releasing all slaves When releasing all slaves during bond destruction (all == true), __bond_release_one() unconditionally clears bond->curr_active_slave to NULL in every iteration. If a backup slave is released before the active slave, bond_alb_deinit_slave() triggers rlb_teach_disabled_mac_on_primary(), which increments the active slave dev promiscuity counter and sets bond_info->primary_is_promisc = 1. Because bond->curr_active_slave was prematurely cleared to NULL when releasing the backup slave, the subsequent iteration releasing the active slave evaluates oldcurrent as NULL, so bond_change_active_slave(bond, NULL) is skipped. Consequently, bond_alb_handle_active_change() is never called to decrement the promiscuity counter, permanently leaking promiscuous mode on the physical device after bond teardown. When oldcurrent == slave, bond_change_active_slave(bond, NULL) already sets bond->curr_active_slave to NULL. We only need to avoid selecting a new active slave when all == true. Replace the if (all) branch with if (!all && oldcurrent == slave). Fixes: 0896341a44bf ("bonding: fix bond_release_all inconsistencies") Signed-off-by: Eric Dumazet Acked-by: Jay Vosburgh Reviewed-by: Nikolay Aleksandrov Link: https://patch.msgid.link/20260831203042.164466-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- drivers/net/bonding/bond_main.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 947d92a669b6..a9bff7663eec 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2517,9 +2517,7 @@ static int __bond_release_one(struct net_device *bond_dev, bond_alb_deinit_slave(bond, slave); } - if (all) { - RCU_INIT_POINTER(bond->curr_active_slave, NULL); - } else if (oldcurrent == slave) { + if (!all && oldcurrent == slave) { /* Note that we hold RTNL over this sequence, so there * is no concern that another slave add/remove event * will interfere. From 5a3f7a683aee56e1f15c9d53041f3236767eaae7 Mon Sep 17 00:00:00 2001 From: Jun Yang Date: Mon, 31 Aug 2026 19:13:04 +0800 Subject: [PATCH 0537/1198] net: bridge: mcast: don't truncate the port group walk on teardown __br_multicast_disable_port_ctx() and br_multicast_del_port() walk port->mglist with hlist_for_each_entry_safe(). However, br_multicast_find_del_pg() can also delete other entries from the same list through br_multicast_fwd_src_remove() or __fwd_del_star_excl(). If such an entry is the iterator's saved next node, hlist_del_init() clears its ->next and terminates the walk early. The reproducer triggers this in both teardown walks, leaving port groups in the bridge mdb with a dangling ->key.port after del_nbp() frees the port: BUG: KASAN: slab-use-after-free in __mdb_fill_info+0x1191/0x1320 __mdb_fill_info+0x1191/0x1320 br_mdb_dump+0x594/0xe40 rtnl_mdb_dump+0x1cf/0x5d0 Use hlist_del_init_rcu() to unlink the group while preserving ->next. br_multicast_del_pg() and the teardown walks run under br->multicast_lock. The GC worker must acquire the same lock before detaching the group for destruction, so the node remains alive while the walk uses the preserved pointer. Preserving ->next means a walk can now reach a group that an earlier iteration already deleted as a side effect. That group is off mp->ports, so br_multicast_find_del_pg() would fall through its port scan and hit the trailing WARN_ON(1). Skip such groups at the top of that helper: a port group is put on port->mglist when it is created and only unlinked when it is deleted, so hlist_unhashed() identifies exactly this case. Fixes: b08123684bd5 ("net: bridge: mcast: install S,G entries automatically based on reports") Cc: stable@vger.kernel.org Suggested-by: Nikolay Aleksandrov Reported-by: TencentOS Corvus AI Signed-off-by: Jun Yang Reviewed-by: Nikolay Aleksandrov Link: https://patch.msgid.link/20260831111330.199543-1-junvyyang@tencent.com Signed-off-by: Jakub Kicinski --- net/bridge/br_multicast.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 3ef5d8bbf552..3e9b10f8abf1 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -808,7 +808,11 @@ void br_multicast_del_pg(struct net_bridge_mdb_entry *mp, struct hlist_node *tmp; rcu_assign_pointer(*pp, pg->next); - hlist_del_init(&pg->mglist); + /* Keep ->next (held under multicast_lock, freed later by the GC work): + * a port->mglist teardown walk may have latched this node as its next, + * and deleting other groups of the same port must not truncate it. + */ + hlist_del_init_rcu(&pg->mglist); br_multicast_eht_clean_sets(pg); hlist_for_each_entry_safe(ent, tmp, &pg->src_list, node) br_multicast_del_group_src(ent, false); @@ -835,6 +839,13 @@ static void br_multicast_find_del_pg(struct net_bridge *br, struct net_bridge_mdb_entry *mp; struct net_bridge_port_group *p; + /* A teardown walk over port->mglist can reach a group that an earlier + * iteration already deleted as a side effect. It is off mp->ports by + * now, so skip it instead of falling through to the WARN_ON() below. + */ + if (hlist_unhashed(&pg->mglist)) + return; + mp = br_mdb_ip_get(br, &pg->key.addr); if (WARN_ON(!mp)) return; From debac3a20dec524a59625cf10fa2f18571127824 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Tue, 1 Sep 2026 00:55:44 +0000 Subject: [PATCH 0538/1198] net: Remove conflicting altnames for dying netns in __dev_change_net_namespace(). syzbot reported the warning in cfg80211_pernet_exit(). [0] The repro does the following: 1. create two device in root netns and non-root netns 2. assign the same altname for the two devices 3. remove the non-root netns Since commit 7663d522099e ("net: check for altname conflicts when changing netdev's netns"), cfg80211_switch_netns() and cfg802154_switch_netns() fail if init_net has a device with the conflicting altname. default_device_exit_net() had the same issue and commit d09486a04f5d ("net: fix removing a namespace with conflicting altnames") fixed it. cfg80211_pernet_exit() and cfg802154_pernet_exit() need the same fix. Let's generalise the fix by removing conflicting altnames for dying netns in __dev_change_net_namespace(). [0]: cfg80211_switch_netns(rdev, &init_net) WARNING: net/wireless/core.c:1871 at cfg80211_pernet_exit+0xd5/0x120 net/wireless/core.c:1871, CPU#1: kworker/u8:9/1160 Modules linked in: CPU: 1 UID: 0 PID: 1160 Comm: kworker/u8:9 Not tainted syzkaller #0 PREEMPT(full) Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/24/2026 Workqueue: netns cleanup_net RIP: 0010:cfg80211_pernet_exit+0xd5/0x120 net/wireless/core.c:1871 Code: e8 03 42 80 3c 20 00 74 08 4c 89 f7 e8 b4 ef 0e f7 4d 8b 36 49 81 fe 20 10 4a 90 74 12 e8 03 3d 9f f6 eb 85 e8 fc 3c 9f f6 90 <0f> 0b 90 eb cc e8 f1 3c 9f f6 eb 05 e8 ea 3c 9f f6 5b 41 5c 41 5e RSP: 0018:ffffc900057a78f0 EFLAGS: 00010293 RAX: ffffffff8b287154 RBX: ffff88807ba72780 RCX: ffff8880213e8000 RDX: 0000000000000000 RSI: 00000000ffffffef RDI: 0000000000000000 RBP: 00000000ffffffef R08: ffffffff9024cc67 R09: 0000000000000000 R10: fffff52000af4eb0 R11: fffffbfff204998d R12: dffffc0000000000 R13: ffffffff904a1080 R14: ffff888144ed0008 R15: ffff888144ed0e20 FS: 0000000000000000(0000) GS:ffff888124de6000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00005642de0a8a70 CR3: 000000007a40c000 CR4: 00000000003526f0 Call Trace: ops_exit_list net/core/net_namespace.c:200 [inline] ops_undo_list+0x43d/0x8d0 net/core/net_namespace.c:253 cleanup_net+0x572/0x810 net/core/net_namespace.c:706 process_one_work kernel/workqueue.c:3387 [inline] process_scheduled_works+0xc3d/0x1630 kernel/workqueue.c:3470 worker_thread+0xa47/0xfb0 kernel/workqueue.c:3551 kthread+0x38b/0x480 kernel/kthread.c:436 ret_from_fork+0x514/0xb70 arch/x86/kernel/process.c:158 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:245 Fixes: 36fbf1e52bd3 ("net: rtnetlink: add linkprop commands to add and delete alternative ifnames") Reported-by: syzbot+74f338e09f1ef3ee6457@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/6a96219e.04428c52.29b18.0001.GAE@google.com/T/ Signed-off-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20260901005550.2042357-1-kuniyu@google.com Signed-off-by: Jakub Kicinski --- net/core/dev.c | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) diff --git a/net/core/dev.c b/net/core/dev.c index 38336858c168..290e0f099e6b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -12703,7 +12703,7 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat, int new_ifindex, struct netlink_ext_ack *extack) { - struct netdev_name_node *name_node; + struct netdev_name_node *name_node, *tmp; struct net *net_old = dev_net(dev); char new_name[IFNAMSIZ] = {}; int err, new_nsid; @@ -12749,13 +12749,19 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, } /* Check that none of the altnames conflicts. */ err = -EEXIST; - netdev_for_each_altname(dev, name_node) { - if (netdev_name_in_use(net, name_node->name)) { - NL_SET_ERR_MSG_FMT(extack, - "An interface with the altname %s exists in the target netns", - name_node->name); - goto out; + netdev_for_each_altname_safe(dev, name_node, tmp) { + if (!netdev_name_in_use(net, name_node->name)) + continue; + + if (!check_net(net_old)) { + __netdev_name_node_alt_destroy(name_node); + continue; } + + NL_SET_ERR_MSG_FMT(extack, + "An interface with the altname %s exists in the target netns", + name_node->name); + goto out; } /* Check that new_ifindex isn't used yet. */ @@ -13210,7 +13216,6 @@ static struct pernet_operations __net_initdata netdev_net_ops = { static void __net_exit default_device_exit_net(struct net *net) { - struct netdev_name_node *name_node, *tmp; struct net_device *dev, *aux; /* * Push all migratable network devices back to the @@ -13234,10 +13239,6 @@ static void __net_exit default_device_exit_net(struct net *net) if (netdev_name_in_use(&init_net, fb_name)) snprintf(fb_name, IFNAMSIZ, "dev%%d"); - netdev_for_each_altname_safe(dev, name_node, tmp) - if (netdev_name_in_use(&init_net, name_node->name)) - __netdev_name_node_alt_destroy(name_node); - err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { pr_emerg("%s: failed to move %s to init_net: %d\n", From d85f521a9afb786b1d95bbcb218d3afdf3fe73ab Mon Sep 17 00:00:00 2001 From: Nicolai Buchwitz Date: Mon, 31 Aug 2026 13:31:28 +0200 Subject: [PATCH 0539/1198] net: macb: exclude software FCS from TX byte statistics Frames for which macb_pad_and_fcs() supplies the FCS have four FCS bytes appended, and TX completion then accounts the grown skb->len. tx_bytes is defined to exclude the FCS, so these frames are reported four bytes too large. Track only the number of FCS bytes appended in software, 0 or ETH_FCS_LEN, and subtract that from skb->len at completion. skb->len already reflects the padded length by then, so there is nothing else to store. macb_pad_and_fcs() already returns 0 on every non-error path. Return the FCS length from there instead, rather than recomputing the same check in the caller. BQL stays on the padded skb->len that netdev_tx_sent_queue() saw. Fixes: 653e92a9175e ("net: macb: add support for padding and fcs computation") Signed-off-by: Nicolai Buchwitz Link: https://patch.msgid.link/20260831113128.1678674-1-nb@tipi-net.de Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/cadence/macb.h | 3 +++ drivers/net/ethernet/cadence/macb_main.c | 21 +++++++++++++-------- 2 files changed, 16 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index 1e1f52285a39..d6931c41f39d 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -968,6 +968,8 @@ struct macb_dma_desc_ptp { * of the frame * @mapping: DMA address of the skb's fragment buffer * @size: size of the DMA mapped buffer + * @fcs_len: FCS bytes appended in software, 0 or ETH_FCS_LEN, only + * set for the last buffer of the frame * @mapped_as_page: true when buffer was mapped with skb_frag_dma_map(), * false when buffer was mapped with dma_map_single() */ @@ -975,6 +977,7 @@ struct macb_tx_skb { struct sk_buff *skb; dma_addr_t mapping; size_t size; + u8 fcs_len; bool mapped_as_page; }; diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 76ee4f506033..b1939da4c95a 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1322,8 +1322,8 @@ static void macb_tx_error_task(struct work_struct *work) bp->netdev->stats.tx_packets++; queue->stats.tx_packets++; packets++; - bp->netdev->stats.tx_bytes += skb->len; - queue->stats.tx_bytes += skb->len; + bp->netdev->stats.tx_bytes += skb->len - tx_skb->fcs_len; + queue->stats.tx_bytes += skb->len - tx_skb->fcs_len; bytes += skb->len; } } else { @@ -1450,8 +1450,8 @@ static int macb_tx_complete(struct macb_queue *queue, int budget) skb->data); bp->netdev->stats.tx_packets++; queue->stats.tx_packets++; - bp->netdev->stats.tx_bytes += skb->len; - queue->stats.tx_bytes += skb->len; + bp->netdev->stats.tx_bytes += skb->len - tx_skb->fcs_len; + queue->stats.tx_bytes += skb->len - tx_skb->fcs_len; packets++; bytes += skb->len; } @@ -2199,7 +2199,8 @@ static void macb_poll_controller(struct net_device *netdev) static unsigned int macb_tx_map(struct macb *bp, struct macb_queue *queue, struct sk_buff *skb, - unsigned int hdrlen) + unsigned int hdrlen, + u8 fcs_len) { unsigned int f, nr_frags = skb_shinfo(skb)->nr_frags; unsigned int len, i, tx_head = queue->tx_head; @@ -2284,6 +2285,7 @@ static unsigned int macb_tx_map(struct macb *bp, /* This is the last buffer of the frame: save socket buffer */ tx_skb->skb = skb; + tx_skb->fcs_len = fcs_len; /* Update TX ring: update buffer descriptors in reverse order * to avoid race condition @@ -2417,6 +2419,7 @@ static inline int macb_clear_csum(struct sk_buff *skb) return 0; } +/* Returns a negative errno, or the FCS bytes appended (0 or ETH_FCS_LEN). */ static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *netdev) { bool cloned = skb_cloned(*skb) || skb_header_cloned(*skb) || @@ -2465,7 +2468,7 @@ static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *netdev) skb_put_u8(*skb, (fcs >> 16) & 0xff); skb_put_u8(*skb, (fcs >> 24) & 0xff); - return 0; + return ETH_FCS_LEN; } static netdev_tx_t macb_start_xmit(struct sk_buff *skb, @@ -2478,6 +2481,7 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, netdev_tx_t ret = NETDEV_TX_OK; unsigned int hdrlen; unsigned long flags; + int fcs_len; bool is_lso; if (macb_clear_csum(skb)) { @@ -2485,7 +2489,8 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, return ret; } - if (macb_pad_and_fcs(&skb, netdev)) { + fcs_len = macb_pad_and_fcs(&skb, netdev); + if (fcs_len < 0) { dev_kfree_skb_any(skb); return ret; } @@ -2548,7 +2553,7 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, } /* Map socket buffer for DMA transfer */ - if (macb_tx_map(bp, queue, skb, hdrlen)) { + if (macb_tx_map(bp, queue, skb, hdrlen, fcs_len)) { dev_kfree_skb_any(skb); goto unlock; } From 08710f033e3e35704e45adf8a95b5043ece34899 Mon Sep 17 00:00:00 2001 From: Ian Lin Date: Mon, 31 Aug 2026 16:41:24 +0800 Subject: [PATCH 0540/1198] net: usb: qmi_wwan: add Compal EXM-G1x support The Compal EXM-G1x is a Qualcomm SDX12-based LTE modem. Add support for its QMI WWAN interface 8 using the DTR quirk. Tested on a Compal EXM-G1x modem. Signed-off-by: Ian Lin Link: https://patch.msgid.link/20260831084124.65074-1-jisayme@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/usb/qmi_wwan.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 8178a8758cd3..fdfdcf24ddcf 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1446,6 +1446,7 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x2c7c, 0x0316, 3)}, /* Quectel RG255C */ {QMI_QUIRK_SET_DTR(0x2cb7, 0x0104, 4)}, /* Fibocom NL678 series */ {QMI_QUIRK_SET_DTR(0x2cb7, 0x0112, 0)}, /* Fibocom FG132 */ + {QMI_QUIRK_SET_DTR(0x04b7, 0x8217, 8)}, /* Compal EXM-G1x */ {QMI_FIXED_INTF(0x0489, 0xe0b4, 0)}, /* Foxconn T77W968 LTE */ {QMI_FIXED_INTF(0x0489, 0xe0b5, 0)}, /* Foxconn T77W968 LTE with eSIM support*/ {QMI_FIXED_INTF(0x2692, 0x9025, 4)}, /* Cellient MPL200 (rebranded Qualcomm 05c6:9025) */ From 6d0c8b7073913011459cf968cbbadd341e166bc3 Mon Sep 17 00:00:00 2001 From: Allison Henderson Date: Fri, 28 Aug 2026 15:39:15 -0700 Subject: [PATCH 0541/1198] net/rds: use wq_has_sleeper() in release_in_xmit() release_in_xmit() clears RDS_IN_XMIT with clear_bit_unlock() and then checks waitqueue_active() to decide whether anyone needs waking. clear_bit_unlock() is only a release operation: it orders the critical section before the bit clear, but does not order the subsequent plain load of the wait queue head after it. The waiter side does the mirror image - it adds itself to the wait queue and then tests the bit. That is the classic store-buffering pattern: the releasing CPU can read the wait queue as empty while the waiting CPU still reads the bit as set, so the sleeper is never woken. The waiters are rds_conn_shutdown() and rds_tcp_reset_callbacks(), both in uninterruptible wait_event() with no timeout. A lost wake-up strands the shutdown worker on its single-threaded workqueue until some other sender releases the bit again - and on a connection that is being torn down precisely because it failed, there may never be another sender. The barrier used to be there: release_in_xmit() did clear_bit() followed by smp_mb__after_atomic() until commit 1422f28826d2 ("rds: introduce acquire/release ordering in acquire/release_in_xmit()") folded both into clear_bit_unlock(), which strengthened the lock hand-off but silently dropped the full barrier the wake-up check depends on. The refill counterpart, release_refill() in net/rds/ib_recv.c, still carries its smp_mb__after_atomic() for exactly this reason. Use wq_has_sleeper(), which is waitqueue_active() preceded by the required full barrier. Fixes: 1422f28826d2 ("rds: introduce acquire/release ordering in acquire/release_in_xmit()") Signed-off-by: Allison Henderson Link: https://patch.msgid.link/20260828223921.202913-2-achender@kernel.org Signed-off-by: Jakub Kicinski --- net/rds/send.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/rds/send.c b/net/rds/send.c index 15a1b97f13e7..8aad185e4b1a 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -114,8 +114,13 @@ static void release_in_xmit(struct rds_conn_path *cp) * hot path and finding waiters is very rare. We don't want to walk * the system-wide hashed waitqueue buckets in the fast path only to * almost never find waiters. + * + * wq_has_sleeper() supplies the full barrier that orders the wait + * queue read after the bit clear; clear_bit_unlock() alone is only + * a release and would let this check read a stale empty queue, + * losing the wake-up. */ - if (waitqueue_active(&cp->cp_waitq)) + if (wq_has_sleeper(&cp->cp_waitq)) wake_up_all(&cp->cp_waitq); } From 17c4476dbb9c3bfd34193a6c22f2c3da8747134a Mon Sep 17 00:00:00 2001 From: Allison Henderson Date: Fri, 28 Aug 2026 15:39:16 -0700 Subject: [PATCH 0542/1198] net/rds: use clear_bit_unlock() in release_refill() release_refill() drops the RDS_RECV_REFILL bit with a plain clear_bit(). clear_bit() has no ordering semantics, and the smp_mb__after_atomic() that follows it sits on the wrong side for a lock release: it orders the clear against the waitqueue_active() load below it, but does nothing to order the refill critical section's ring and descriptor stores before the clear itself. That matters once connection teardown owns RDS_RECV_REFILL as a lock across the transport shutdown and path reset, rather than sampling it clear, which "net/rds: acquire the fastpath locks in rds_conn_shutdown()" later in this series arranges: on a weakly ordered architecture the teardown can win the bit and start the shutdown and reset while some of the refill's stores are not yet visible to it. The same gap existed under the sample-based scheme - a waiter that saw the bit clear had no guarantee it also observed the refill's stores - but taking the bit as a lock makes the missing release pairing load-bearing. Switch to clear_bit_unlock(), which orders the critical section before the release, and replace the open-coded barrier-plus-waitqueue_active() with wq_has_sleeper(), whose internal full barrier keeps the store-buffering guarantee between clearing the bit and checking for sleepers. This mirrors what "net/rds: use wq_has_sleeper() in release_in_xmit()" does for RDS_IN_XMIT. The fast-path acquire side, acquire_refill(), uses test_and_set_bit(), a full-barrier RMW that pairs with this release. The teardown at this point in the series still samples the bit, so on its own this change is release-side hardening; the shutdown-conversion patch named above makes the teardown acquire the bit with the same RMW, completing the pairing at the end of the series. Fixes: 73ce4317bf98 ("RDS: make sure we post recv buffers") Signed-off-by: Allison Henderson Link: https://patch.msgid.link/20260828223921.202913-3-achender@kernel.org Signed-off-by: Jakub Kicinski --- net/rds/ib_recv.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 357128d34a54..a6983861eec7 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -363,15 +363,14 @@ static int acquire_refill(struct rds_connection *conn) static void release_refill(struct rds_connection *conn) { - clear_bit(RDS_RECV_REFILL, &conn->c_flags); - smp_mb__after_atomic(); + clear_bit_unlock(RDS_RECV_REFILL, &conn->c_flags); /* We don't use wait_on_bit()/wake_up_bit() because our waking is in a * hot path and finding waiters is very rare. We don't want to walk * the system-wide hashed waitqueue buckets in the fast path only to * almost never find waiters. */ - if (waitqueue_active(&conn->c_waitq)) + if (wq_has_sleeper(&conn->c_waitq)) wake_up_all(&conn->c_waitq); } From 103c4b13c4f50322910078d1c02f29334a574122 Mon Sep 17 00:00:00 2001 From: Allison Henderson Date: Fri, 28 Aug 2026 15:39:17 -0700 Subject: [PATCH 0543/1198] net/rds: clear cp_flags bits individually in rds_conn_path_reset() rds_conn_path_reset() wipes the whole flag word with a plain cp->cp_flags = 0 store. Every other accessor of that word uses atomic bitops, and some of them can run concurrently with the reset: RDS_LL_SEND_FULL is set from rds_send_xmit() and cleared from the transport completion paths, neither of which holds anything that excludes the shutdown worker. A plain store racing an atomic read-modify-write on the same word is a data race, and whichever side loses has its update silently discarded. Clear the two bits the reset is actually responsible for instead. RDS_IN_XMIT and RDS_RECV_REFILL need no store at all here: they belong to the caller, rds_conn_shutdown(), which waits for both to be clear before calling the transport shutdown and this reset. This also gives every bit in cp_flags a single well-defined writer discipline, which the following patches rely on when they turn RDS_IN_XMIT and RDS_RECV_REFILL into bit locks held across the teardown: a blanket store mid-teardown would destroy lock ownership that an atomic clear preserves. Oracle UEK carries the same conversion ("net/rds: Preserve essential connection state flags"), motivated by its asynchronous shutdown state machine, whose progress and destroy flags must survive the reset. UEK's variant also clears RDS_IN_XMIT and RDS_RECV_REFILL because there the reset runs as the final step of a teardown that owns both bits, making those clears its unlock. Upstream that release belongs in rds_conn_shutdown(): once a later patch in this series turns the two bits into locks held across the teardown, ending ownership needs release semantics and a wake-up that a plain clear inside the reset would not provide. Based on Oracle UEK commit "net/rds: Preserve essential connection state flags" by Gerd Rausch. Fixes: 00e0f34c6166 ("RDS: Connection handling") Signed-off-by: Allison Henderson Link: https://patch.msgid.link/20260828223921.202913-4-achender@kernel.org Signed-off-by: Jakub Kicinski --- net/rds/connection.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/net/rds/connection.c b/net/rds/connection.c index 7c8ab8e973e1..46ac72088f84 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -120,7 +120,15 @@ static void rds_conn_path_reset(struct rds_conn_path *cp) rds_stats_inc(s_conn_reset); rds_send_path_reset(cp); - cp->cp_flags = 0; + + /* Clear the bits the reset is responsible for individually: a + * blanket cp_flags = 0 is a plain store that can clobber a + * concurrent atomic read-modify-write on the same word. + * RDS_IN_XMIT and RDS_RECV_REFILL belong to the caller, + * rds_conn_shutdown(), and are left alone here. + */ + clear_bit(RDS_LL_SEND_FULL, &cp->cp_flags); + clear_bit(RDS_RECONNECT_PENDING, &cp->cp_flags); /* Do not clear next_rx_seq here, else we cannot distinguish * retransmitted packets from new packets, and will hand all From e8e60d74fec49ccae2aea9b04a6eb162feb8d9af Mon Sep 17 00:00:00 2001 From: Gerd Rausch Date: Fri, 28 Aug 2026 15:39:18 -0700 Subject: [PATCH 0544/1198] net/rds: tcp: don't force RDS_CONN_RESETTING over a concurrent shutdown rds_tcp_reset_callbacks() resolves a duelling SYN by storing RDS_CONN_RESETTING into cp_state unconditionally. Nothing serializes that store against the shutdown path: rds_tcp_accept_one() checks for RDS_CONN_CONNECTING or RDS_CONN_ERROR under t_conn_path_lock, but neither rds_conn_path_drop(), which forces RDS_CONN_ERROR, nor rds_conn_shutdown(), which moves the path to RDS_CONN_DISCONNECTING under cp_cm_lock, takes that lock. The store can therefore land on top of a shutdown that is already in progress, or that gets queued right after the accept-side check. When it does, the shutdown worker's final DISCONNECTING -> DOWN transition fails and the path goes through rds_conn_path_error() and a second drop/shutdown cycle instead of a clean reconnect, tearing down the socket the accept path has just installed. Before commit ad22d24be635 ("net/rds: No shortcut out of RDS_CONN_ERROR") a path found in RDS_CONN_RESETTING even made rds_conn_shutdown() bail out altogether. Make the transition conditional: move CONNECTING -> RESETTING (or stay in RESETTING from an earlier duel), and drop the path in any other state. The drop has side effects of its own: it replaces the shutdown's RDS_CONN_DISCONNECTING (or RDS_CONN_ERROR) with RDS_CONN_ERROR and queues one more cp_down_w run. The difference is that rds_conn_shutdown() accepts RDS_CONN_ERROR in its final transition to RDS_CONN_DOWN, so the shutdown in flight completes normally instead of through rds_conn_path_error(); the extra down-work pass then finds the path already down and falls through to the reconnect check, or catches a reconnect that has already started and restarts it. The accept path still installs the new socket, rds_connect_path_complete() then fails its RESETTING -> UP transition and drops it: the raced socket ends up torn down as it does today. The comment at that call site, which promised that rds_connect_path_complete() marks the path RDS_CONN_UP, is updated to name this outcome as well. The state can change again between the failed transitions and the drop. That is inherent to rds_conn_path_drop(), which the socket state-change callbacks also call unconditionally, and costs at most one extra drop/reconnect cycle. Based on Oracle UEK commit "net/rds: Don't force state RDS_CONN_RESETTING" by Gerd Rausch. Fixes: 9c79440e2c5e ("RDS: TCP: fix race windows in send-path quiescence by rds_tcp_accept_one()") Signed-off-by: Gerd Rausch [achender: port to net-next: use the two-argument rds_conn_path_transition()/rds_conn_path_drop() and rewrite the changelog for the upstream shutdown path] Signed-off-by: Allison Henderson Link: https://patch.msgid.link/20260828223921.202913-5-achender@kernel.org Signed-off-by: Jakub Kicinski --- net/rds/tcp.c | 17 +++++++++++++++-- net/rds/tcp_listen.c | 6 +++++- 2 files changed, 20 insertions(+), 3 deletions(-) diff --git a/net/rds/tcp.c b/net/rds/tcp.c index b263634ac750..ad14217867a4 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -150,9 +150,22 @@ void rds_tcp_reset_callbacks(struct socket *sock, * end up deadlocking with tcp_sendmsg(), and the RDS_IN_XMIT * would not get set. As a result, we set c_state to * RDS_CONN_RESETTTING, to ensure that rds_tcp_state_change - * cannot mark rds_conn_path_up() in the window before lock_sock() + * cannot mark rds_conn_path_up() in the window before lock_sock(). + * + * Only make that transition if the path is still connecting + * (or already resetting from an earlier duel). A path in any + * other state - typically RDS_CONN_DISCONNECTING or + * RDS_CONN_ERROR with a shutdown in flight - is dropped + * instead. That still replaces its state, with RDS_CONN_ERROR, + * and queues one more shutdown pass, but rds_conn_shutdown() + * accepts RDS_CONN_ERROR in its final transition to + * RDS_CONN_DOWN, so the shutdown in flight completes normally. */ - atomic_set(&cp->cp_state, RDS_CONN_RESETTING); + if (!rds_conn_path_transition(cp, RDS_CONN_CONNECTING, + RDS_CONN_RESETTING) && + !rds_conn_path_transition(cp, RDS_CONN_RESETTING, + RDS_CONN_RESETTING)) + rds_conn_path_drop(cp, 0); wait_event(cp->cp_waitq, !test_bit(RDS_IN_XMIT, &cp->cp_flags)); /* reset receive side state for rds_tcp_data_recv() for osock */ cancel_delayed_work_sync(&cp->cp_send_w); diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index a3db9b057084..13fa60c1985b 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -295,7 +295,11 @@ int rds_tcp_accept_one(struct rds_tcp_net *rtn) if (rs_tcp->t_sock) { /* Duelling SYN has been handled in rds_tcp_accept_one() */ rds_tcp_reset_callbacks(new_sock, cp); - /* rds_connect_path_complete() marks RDS_CONN_UP */ + /* rds_connect_path_complete() marks RDS_CONN_UP, or, + * if a concurrent shutdown won the duel, drops the + * path again and the pass that drop queues reaps the + * socket installed above. + */ rds_connect_path_complete(cp, RDS_CONN_RESETTING); } else { rds_tcp_set_callbacks(new_sock, cp); From 02c5f9dc2efd823e061954d564ce00bacd1bebeb Mon Sep 17 00:00:00 2001 From: Allison Henderson Date: Fri, 28 Aug 2026 15:39:19 -0700 Subject: [PATCH 0545/1198] net/rds: acquire RDS_IN_XMIT in rds_tcp_reset_callbacks() rds_tcp_reset_callbacks() quiesces the transmit path by setting the path state to RDS_CONN_RESETTING and then waiting for RDS_IN_XMIT to be sampled clear before swapping the underlying socket and calling rds_send_path_reset(). Sampling the bit clear is not the same as owning it: rds_send_xmit() can re-acquire RDS_IN_XMIT right after the wait_event() returns. Its state recheck after taking the lock is a store-buffering pattern (the resetter writes the state and reads the bit, the sender writes the bit and reads the state) and acquire_in_xmit() is only an acquire operation, so on weakly ordered architectures both sides can miss each other's write and the transmit path then runs concurrently with rds_send_path_reset() rewriting cp_xmit_* state - which is exactly what the comment above rds_send_path_reset() tells its callers to prevent. Take the lock instead, hold it across the socket swap and rds_send_path_reset(), and release it with a wake-up at the end. The lock-ordering constraint documented above the wait still holds: the lock is acquired before lock_sock(), so a sender inside tcp_sendmsg() can never be waited on while we hold the socket lock. Two details of the old code go away with the same change: - t_sock is now read only after the lock is acquired. The old code cached it before waiting; the teardown in rds_conn_shutdown() releases that socket and clears t_sock, so a pointer cached before the wait can be stale by the time the accept path resumes. Reading it under RDS_IN_XMIT is what makes the exclusion complete once the teardown owns the same lock, which the next patch arranges; until then the teardown still only samples the bit, and the two paths remain as exposed to each other as they are today. - The old !osock early path called rds_send_path_reset() with no serialization at all. It now runs under the lock like the normal path. The conditional RDS_CONN_RESETTING transition of the previous patch happens before the socket check either way: a path found without a socket is either still connecting (its reconnect worker blocked on t_conn_path_lock) and legitimately goes RESETTING -> UP on the new socket, or it has been torn down meanwhile and is dropped. The in-function comment describing the old wait-based quiesce is rewritten to describe the lock-based one, and the stale block comment above the function (which still described a return value and an incomplete list of t_sock writers) is refreshed to name all four writers - the connect, accept, teardown and swap paths - and what serializes each of them. Fixes: 335b48d980f6 ("RDS: TCP: Add/use rds_tcp_reset_callbacks to reset tcp socket safely") Signed-off-by: Allison Henderson Link: https://patch.msgid.link/20260828223921.202913-6-achender@kernel.org Signed-off-by: Jakub Kicinski --- net/rds/tcp.c | 70 +++++++++++++++++++++++++++++++++------------------ 1 file changed, 45 insertions(+), 25 deletions(-) diff --git a/net/rds/tcp.c b/net/rds/tcp.c index ad14217867a4..f4c83e368390 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -115,42 +115,48 @@ void rds_tcp_restore_callbacks(struct socket *sock, } /* - * rds_tcp_reset_callbacks() switches the to the new sock and - * returns the existing tc->t_sock. + * rds_tcp_reset_callbacks() switches a path to a new socket and + * releases the old one it finds in tc->t_sock, resolving a duelling + * SYN. * - * The only functions that set tc->t_sock are rds_tcp_set_callbacks - * and rds_tcp_reset_callbacks. Send and receive trust that - * it is set. The absence of RDS_CONN_UP bit protects those paths - * from being called while it isn't set. + * tc->t_sock is set by rds_tcp_set_callbacks() and cleared by + * rds_tcp_restore_callbacks(). Four paths write it: the active + * connect in rds_tcp_conn_path_connect(), which sets it and clears it + * again on failure; the accept path in rds_tcp_accept_one(), which + * sets it for a path with no socket yet; the teardown in + * rds_tcp_conn_path_shutdown(), which clears it; and the swap done + * here, which does both. The connect and accept paths are serialized + * against each other by t_conn_path_lock. Send and receive trust + * that it is set: the absence of RDS_CONN_UP protects those paths + * from being called while it isn't, and the swap done here runs under + * RDS_IN_XMIT so that it cannot interleave with a sender already + * inside rds_send_xmit(). */ void rds_tcp_reset_callbacks(struct socket *sock, struct rds_conn_path *cp) { struct rds_tcp_connection *tc = cp->cp_transport_data; - struct socket *osock = tc->t_sock; - - if (!osock) - goto newsock; + struct socket *osock; /* Need to resolve a duelling SYN between peers. * We have an outstanding SYN to this peer, which may * potentially have transitioned to the RDS_CONN_UP state, * so we must quiesce any send threads before resetting - * cp_transport_data. We quiesce these threads by setting - * cp_state to something other than RDS_CONN_UP, and then - * waiting for any existing threads in rds_send_xmit to - * complete release_in_xmit(). (Subsequent threads entering - * rds_send_xmit() will bail on !rds_conn_up(). + * cp_transport_data. Setting cp_state to something other + * than RDS_CONN_UP stops new senders, and owning RDS_IN_XMIT + * excludes any thread already inside rds_send_xmit() for the + * whole socket swap and the rds_send_path_reset() below. * - * However an incoming syn-ack at this point would end up - * marking the conn as RDS_CONN_UP, and would again permit - * rds_send_xmi() threads through, so ideally we would - * synchronize on RDS_CONN_UP after lock_sock(), but cannot - * do that: waiting on !RDS_IN_XMIT after lock_sock() may - * end up deadlocking with tcp_sendmsg(), and the RDS_IN_XMIT - * would not get set. As a result, we set c_state to - * RDS_CONN_RESETTTING, to ensure that rds_tcp_state_change - * cannot mark rds_conn_path_up() in the window before lock_sock(). + * An incoming syn-ack at this point would end up marking the + * conn as RDS_CONN_UP, and would again permit rds_send_xmit() + * threads through, so ideally we would synchronize on + * RDS_CONN_UP after lock_sock(), but cannot do that: acquiring + * RDS_IN_XMIT after lock_sock() may end up deadlocking with + * tcp_sendmsg(), which takes the socket lock while holding + * RDS_IN_XMIT. As a result, we set c_state to + * RDS_CONN_RESETTING, to ensure that rds_tcp_state_change + * cannot mark rds_conn_path_up() in the window before + * lock_sock(). * * Only make that transition if the path is still connecting * (or already resetting from an earlier duel). A path in any @@ -166,7 +172,18 @@ void rds_tcp_reset_callbacks(struct socket *sock, !rds_conn_path_transition(cp, RDS_CONN_RESETTING, RDS_CONN_RESETTING)) rds_conn_path_drop(cp, 0); - wait_event(cp->cp_waitq, !test_bit(RDS_IN_XMIT, &cp->cp_flags)); + wait_event(cp->cp_waitq, + !test_and_set_bit_lock(RDS_IN_XMIT, &cp->cp_flags)); + + /* Read t_sock only while owning RDS_IN_XMIT, never before the + * wait: the teardown in rds_conn_shutdown() releases the old + * socket and clears t_sock, so a pointer sampled earlier can + * be stale by the time we wake up. + */ + osock = tc->t_sock; + if (!osock) + goto newsock; + /* reset receive side state for rds_tcp_data_recv() for osock */ cancel_delayed_work_sync(&cp->cp_send_w); cancel_delayed_work_sync(&cp->cp_recv_w); @@ -185,6 +202,9 @@ void rds_tcp_reset_callbacks(struct socket *sock, lock_sock(sock->sk); rds_tcp_set_callbacks(sock, cp); release_sock(sock->sk); + + clear_bit_unlock(RDS_IN_XMIT, &cp->cp_flags); + wake_up_all(&cp->cp_waitq); } /* Add tc to rds_tcp_tc_list and set tc->t_sock. See comments From 813f3582ac7ae9f60f917937d54660e0952d5f2d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?H=C3=A5kon=20Bugge?= Date: Fri, 28 Aug 2026 15:39:20 -0700 Subject: [PATCH 0546/1198] net/rds: acquire the fastpath locks in rds_conn_shutdown() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit rds_conn_shutdown() quiesces the transmit and receive-refill paths by waiting for RDS_IN_XMIT and RDS_RECV_REFILL to be sampled clear, and then runs the transport shutdown and rds_conn_path_reset(). Sampling the bits clear is not the same as owning them: the moment after the wait_event() returns, rds_send_xmit() can re-acquire RDS_IN_XMIT (or rds_ib_recv_refill() can re-acquire RDS_RECV_REFILL) and run concurrently with the teardown. The sender does recheck the connection state after taking the lock, but that recheck is a classic store-buffering pattern: teardown writes the state and reads the bit while the sender writes the bit and reads the state. acquire_in_xmit() is only an acquire operation, so on weakly ordered architectures both sides can miss each other's write, and the transmit path then runs while the transport zeroes its rings (e.g. rds_ib_ring_init()) and rds_send_path_reset() rewrites the transmit state under it. Oracle UEK fixed the same class of crashes - a 14-year tail of BUG_ON()s in rds_ib_sub_signaled(), unexpected op-codes and NULL dereferences in rds_ib_send_cqe_handler() during failover testing - by making the teardown path *acquire* the fastpath bit locks instead of testing them ("rds: Make sure transmit path and connection tear-down does not run concurrently"). Ownership of a single word is decided by RMW atomicity, so no cross-variable ordering is needed. Do the same here: take both locks before calling the transport shutdown, hold them across rds_conn_path_reset(), and release them explicitly with a wake-up afterwards. Both are released with clear_bit_unlock(), so that the ring re-initialization done by the transport shutdown and the transmit state rewritten by rds_send_path_reset() are ordered before either bit is seen clear by the next acquire_in_xmit() or acquire_refill(). The fastpath users of these bits - rds_send_xmit() and rds_ib_recv_refill() - are trylock style and back off while teardown owns the locks, so no new lock dependency is introduced for them. rds_tcp_reset_callbacks() is different: since the previous patch it acquires RDS_IN_XMIT as well, and it blocks doing so, so its wait now spans the teardown instead of at most one send batch. That waiter runs from rds_tcp_accept_one() on the single-threaded krdsd workqueue and holds rds_tcp_accept_lock and t_conn_path_lock while it waits, so a duelling SYN accepted while its path is being torn down parks accept processing for the duration of the teardown - for TCP bounded by the (up to 5 s) drain loop in rds_tcp_conn_path_shutdown(). An IB path's drain in rds_ib_conn_path_shutdown() has no round cap, but no blocking waiter either: rds_tcp_reset_callbacks() is the only blocking acquirer of these bits and waits only on its own TCP path, and the fastpaths are trylock-and-back-off on both transports, so a long IB drain lengthens only that path's own quiesce. The window is narrow: the accept-side state check has to pass before the teardown moves the path to RDS_CONN_DISCONNECTING. Because krdsd is a single global workqueue, everything else queued there - accept processing for other connections and network namespaces, and the flush_workqueue(rds_wq) in rds_tcp_listen_stop() during namespace teardown - waits behind the parked accept worker for that time. It cannot deadlock, although the waits do point at each other: the teardown blocks until the bit's holder releases it, and the holder may be that krdsd accept worker. The holder finishes without needing anything the teardown owns: the sync cancels rds_tcp_reset_callbacks() issues target cp_send_w and cp_recv_w on the path's ordered cp_wq, whose only execution slot is occupied by the blocked cp_down_w itself, so they are pending at most and cancel without flushing - a reliance on cp_wq being ordered that is now noted next to those cancels (on the allocation-failure fallback where a path shares rds_wq, the work items simply serialize). Nor is the blocking wait itself new: rds_tcp_reset_callbacks() has waited on RDS_IN_XMIT from the krdsd work item since commit 335b48d980f6 ("RDS: TCP: Add/use rds_tcp_reset_callbacks to reset tcp socket safely"); this patch stretches its worst case from a sender's batch to the teardown's drain. The alternative to parking is the accept path racing the teardown, which is what these patches close; making the teardown itself non-blocking is a separate item. One observable side effect: the SENDING flag reported by rds-info has always mirrored RDS_IN_XMIT, so it now also covers the window where teardown owns the bit. The comments that describe the old sample-based handshake or name rds_send_xmit() as the only other holder of these bits - in rds_send_xmit(), above rds_conn_path_reset(), in rds_ib_recv_refill() and in rds_tcp_reset_callbacks() - are updated to match. For anyone backporting this patch standalone: it depends on "net/rds: clear cp_flags bits individually in rds_conn_path_reset()" and "net/rds: acquire RDS_IN_XMIT in rds_tcp_reset_callbacks()" earlier in this series. Without the former, the blanket cp_flags clear in rds_conn_path_reset() would drop both held bits in the middle of the teardown; without the latter, rds_tcp_reset_callbacks() would still sample t_sock without owning RDS_IN_XMIT. "net/rds: use clear_bit_unlock() in release_refill()" is needed for the refill side's release to pair with the acquire added here, and the follow-up "net/rds: don't let rds_conn_shutdown() consume a concurrent drop" completes the teardown-state handling for the waiter this patch parks; a backport should carry all four. Fixes: 0f4b1c7e89e6 ("rds: fix rds_send_xmit() serialization") Signed-off-by: Håkon Bugge [achender: reimplement for net-next shutdown path: acquire the existing RDS_IN_XMIT/RDS_RECV_REFILL bit locks in rds_conn_shutdown() and release after teardown; update comments and commit message] Signed-off-by: Allison Henderson Link: https://patch.msgid.link/20260828223921.202913-7-achender@kernel.org Signed-off-by: Jakub Kicinski --- net/rds/connection.c | 40 ++++++++++++++++++++++++++++++++-------- net/rds/ib_recv.c | 4 +++- net/rds/send.c | 7 +++++-- net/rds/tcp.c | 19 +++++++++++++++---- 4 files changed, 55 insertions(+), 15 deletions(-) diff --git a/net/rds/connection.c b/net/rds/connection.c index 46ac72088f84..fbbac55a0e81 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -106,10 +106,12 @@ static struct rds_connection *rds_conn_lookup(struct net *net, } /* - * This is called by transports as they're bringing down a connection. - * It clears partial message state so that the transport can start sending - * and receiving over this connection again in the future. It is up to - * the transport to have serialized this call with its send and recv. + * This is called by rds_conn_shutdown() once the transport has brought + * a path down. It clears partial message state so that the transport + * can start sending and receiving over this path again in the future. + * The caller owns RDS_IN_XMIT and RDS_RECV_REFILL across this call, + * which is what serializes it against the send and receive-refill + * paths. */ static void rds_conn_path_reset(struct rds_conn_path *cp) { @@ -124,8 +126,9 @@ static void rds_conn_path_reset(struct rds_conn_path *cp) /* Clear the bits the reset is responsible for individually: a * blanket cp_flags = 0 is a plain store that can clobber a * concurrent atomic read-modify-write on the same word. - * RDS_IN_XMIT and RDS_RECV_REFILL belong to the caller, - * rds_conn_shutdown(), and are left alone here. + * RDS_IN_XMIT and RDS_RECV_REFILL are held as locks by the + * caller, rds_conn_shutdown(), which releases them once the + * teardown is complete. */ clear_bit(RDS_LL_SEND_FULL, &cp->cp_flags); clear_bit(RDS_RECONNECT_PENDING, &cp->cp_flags); @@ -414,14 +417,35 @@ void rds_conn_shutdown(struct rds_conn_path *cp) } mutex_unlock(&cp->cp_cm_lock); + /* Quiesce the transmit and receive-refill paths by + * acquiring their bit locks, not merely waiting for + * them to be released: with a plain wait, either path + * can re-take its lock the instant after we sample it + * clear and then run concurrently with the transport + * shutdown and the path reset below. Holding both + * locks across the teardown makes that structurally + * impossible. + */ wait_event(cp->cp_waitq, - !test_bit(RDS_IN_XMIT, &cp->cp_flags)); + !test_and_set_bit_lock(RDS_IN_XMIT, &cp->cp_flags)); wait_event(cp->cp_waitq, - !test_bit(RDS_RECV_REFILL, &cp->cp_flags)); + !test_and_set_bit(RDS_RECV_REFILL, &cp->cp_flags)); conn->c_trans->conn_path_shutdown(cp); rds_conn_path_reset(cp); + /* Release the two locks and wake any waiter (e.g. + * rds_tcp_reset_callbacks()) that blocked on them while + * we held them. The unlock orders the transport's ring + * re-initialization and the path reset above before + * either bit is seen clear. rds_conn_path_reset() leaves + * both bits alone: ownership ends here, not inside the + * reset. + */ + clear_bit_unlock(RDS_IN_XMIT, &cp->cp_flags); + clear_bit_unlock(RDS_RECV_REFILL, &cp->cp_flags); + wake_up_all(&cp->cp_waitq); + if (!rds_conn_path_transition(cp, RDS_CONN_DISCONNECTING, RDS_CONN_DOWN) && !rds_conn_path_transition(cp, RDS_CONN_ERROR, diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index a6983861eec7..bd6cb3ffaa57 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -391,7 +391,9 @@ void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp) /* the goal here is to just make sure that someone, somewhere * is posting buffers. If we can't get the refill lock, - * let them do their thing + * let them do their thing. The holder may also be + * rds_conn_shutdown() tearing the path down, in which case + * there is nothing to post. */ if (!acquire_refill(conn)) return; diff --git a/net/rds/send.c b/net/rds/send.c index 8aad185e4b1a..1afa981e5c06 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -244,8 +244,11 @@ int rds_send_xmit(struct rds_conn_path *cp) WRITE_ONCE(cp->cp_send_gen, send_gen); /* - * rds_conn_shutdown() sets the conn state and then tests RDS_IN_XMIT, - * we do the opposite to avoid races. + * rds_conn_shutdown() sets the conn state and then acquires + * RDS_IN_XMIT; we take the lock first and then check the state. + * Ownership is decided by the atomic RMW on the cp_flags word: + * if the teardown won the bit we back off here, and if we won + * it the teardown waits until we release it. */ if (!rds_conn_path_up(cp)) { release_in_xmit(cp); diff --git a/net/rds/tcp.c b/net/rds/tcp.c index f4c83e368390..69c6d3145b5a 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -144,8 +144,10 @@ void rds_tcp_reset_callbacks(struct socket *sock, * so we must quiesce any send threads before resetting * cp_transport_data. Setting cp_state to something other * than RDS_CONN_UP stops new senders, and owning RDS_IN_XMIT - * excludes any thread already inside rds_send_xmit() for the - * whole socket swap and the rds_send_path_reset() below. + * excludes any thread already inside rds_send_xmit() - or a + * teardown in rds_conn_shutdown(), which holds the same lock + * for the duration of the transport shutdown - for the whole + * socket swap and the rds_send_path_reset() below. * * An incoming syn-ack at this point would end up marking the * conn as RDS_CONN_UP, and would again permit rds_send_xmit() @@ -178,13 +180,22 @@ void rds_tcp_reset_callbacks(struct socket *sock, /* Read t_sock only while owning RDS_IN_XMIT, never before the * wait: the teardown in rds_conn_shutdown() releases the old * socket and clears t_sock, so a pointer sampled earlier can - * be stale by the time we wake up. + * be stale by the time we wake up. The teardown holds the + * same lock while it does so, so what we read here cannot + * change under us until we release it. */ osock = tc->t_sock; if (!osock) goto newsock; - /* reset receive side state for rds_tcp_data_recv() for osock */ + /* reset receive side state for rds_tcp_data_recv() for osock. + * + * The sync cancels while owning RDS_IN_XMIT rely on cp_wq + * being ordered: a teardown blocked on the bit occupies + * cp_wq's only execution slot, so cp_send_w and cp_recv_w are + * pending at most and the cancels never flush. Nothing here + * may flush or wait on cp_wq itself. + */ cancel_delayed_work_sync(&cp->cp_send_w); cancel_delayed_work_sync(&cp->cp_recv_w); lock_sock(osock->sk); From 260c6308fe2e19ad519389d44d582e292aecc3af Mon Sep 17 00:00:00 2001 From: Allison Henderson Date: Fri, 28 Aug 2026 15:39:21 -0700 Subject: [PATCH 0547/1198] net/rds: don't let rds_conn_shutdown() consume a concurrent drop rds_conn_shutdown() finishes by moving the path from RDS_CONN_DISCONNECTING to RDS_CONN_DOWN, and also accepts RDS_CONN_ERROR as the starting state of that final transition, so that a FIN processed in softirq context during the teardown does not derail the shutdown into a noisy error path. But consuming that RDS_CONN_ERROR also consumes the shutdown pass that came with it: rds_conn_path_drop() sets RDS_CONN_ERROR and then queues cp_down_w, and a pass that starts on a path already in RDS_CONN_DOWN is a no-op. For the FIN case that is harmless - the socket the FIN arrived on is the very socket the teardown just released. It is not harmless for a dropper that attached something to the path first. rds_tcp_accept_one() is such a dropper. Its path claim in rds_tcp_accept_one_path() transitions RDS_CONN_DOWN -> RDS_CONN_CONNECTING, and a concurrent drop - a FIN on a previous socket in softirq context, an administrative reset - can put the path into RDS_CONN_ERROR between that claim and the state check that follows, which accepts RDS_CONN_ERROR. The accept then installs the freshly accepted socket with rds_tcp_set_callbacks() while the queued teardown - which sampled tc->t_sock before this socket existed - is still running. rds_connect_path_complete() fails its transition to RDS_CONN_UP and drops the path again, queueing the pass that should reap the socket it just installed. If the in-flight shutdown's final transition consumes that drop's RDS_CONN_ERROR, the queued pass finds the path in RDS_CONN_DOWN and does nothing. The installed socket is never torn down: it sits established with its callbacks armed and its rds_tcp_connection on rds_tcp_tc_list, the peer sees a connection that nothing ever reads, and the path is wedged in RDS_CONN_DOWN until some later event drops it again. Reproduced with widened race windows as an ever-growing receive queue on a socket owned by a path stuck in RDS_CONN_DOWN, with the peer's send path wedged behind it. Make the final transition only DISCONNECTING -> DOWN. If it fails because the path is in RDS_CONN_ERROR, a drop raced the teardown: cancel the reconnect timer and clear RDS_RECONNECT_PENDING - the one piece of the skipped tail that must not be left behind - and return, letting the pass the drop queued finish the job: it tears down whatever attached to the path in the meantime, completes the transition to RDS_CONN_DOWN, and re-arms the reconnect from its own tail. The timer quiesce in that branch matters because the racing drop does not always queue that pass: rds_conn_path_drop() returns without queueing when a destroy is pending - exactly the situation during a netns teardown or module unload, when a FIN on the dying socket is processed while rds_conn_path_destroy() flushes cp_down_w. If the flushed pass is the one that takes this return, no later pass exists, and rds_conn_path_destroy() would find cp_conn_w still armed (WARN_ON) and then free a path whose reconnect timer can still fire. With the cancel in the branch, every exit of a shutdown pass leaves the timer quiesced no matter which pass completes the transition. The FIN case keeps making progress, one pass later and still without noisy logging. Any other state keeps today's rds_conn_path_error() handling; no current cp_state writer can leave a DISCONNECTING path in anything but RDS_CONN_ERROR (every other writer is a cmpxchg from a non-DISCONNECTING state), so that branch is defensive. On kernels without the preceding patches the same hazard exists with the sample-based quiesce; the fix applies there equally. Fixes: e97656d03ca0 ("rds: tcp: allow progress of rds_conn_shutdown if the rds_connection is marked ERROR by an intervening FIN") Signed-off-by: Allison Henderson Link: https://patch.msgid.link/20260828223921.202913-8-achender@kernel.org Signed-off-by: Jakub Kicinski --- net/rds/connection.c | 43 ++++++++++++++++++++++++++++++++----------- net/rds/tcp.c | 9 ++++++--- 2 files changed, 38 insertions(+), 14 deletions(-) diff --git a/net/rds/connection.c b/net/rds/connection.c index fbbac55a0e81..b6c4beb50eaf 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -447,19 +447,40 @@ void rds_conn_shutdown(struct rds_conn_path *cp) wake_up_all(&cp->cp_waitq); if (!rds_conn_path_transition(cp, RDS_CONN_DISCONNECTING, - RDS_CONN_DOWN) && - !rds_conn_path_transition(cp, RDS_CONN_ERROR, RDS_CONN_DOWN)) { - /* This can happen - eg when we're in the middle of tearing - * down the connection, and someone unloads the rds module. - * Quite reproducible with loopback connections. - * Mostly harmless. + /* The path was dropped again while we tore it + * down: by a socket state-change callback in + * irq context on receipt of a FIN, or by an + * accept that claimed the path just before a + * drop put it back to RDS_CONN_ERROR and then + * installed a fresh socket on it. Unless a + * pending destroy suppressed it, the drop also + * queued another shutdown pass, and that pass + * must run, because it is what tears down + * whatever attached to the path after the + * transport shutdown above sampled its state. + * Consuming the RDS_CONN_ERROR here would turn + * that pass into a no-op: leave the state + * alone, and let the pass finish the job. * - * Note that this also happens with rds-tcp because - * we could have triggered rds_conn_path_drop in irq - * mode from rds_tcp_state change on the receipt of - * a FIN, thus we need to recheck for RDS_CONN_ERROR - * here. + * Quiesce the reconnect timer before bailing + * out, though. When a pending destroy did + * suppress the queue, no later pass runs, and + * rds_conn_path_destroy() is about to flush + * cp_down_w and free the path: it must not + * find cp_conn_w still armed. A successor + * pass, when there is one, re-arms the + * reconnect from its own tail. + */ + cancel_delayed_work_sync(&cp->cp_conn_w); + clear_bit(RDS_RECONNECT_PENDING, &cp->cp_flags); + + if (rds_conn_path_state(cp) == RDS_CONN_ERROR) + return; + /* No current cp_state writer leaves a + * DISCONNECTING path in any state but + * RDS_CONN_ERROR; report loudly if one ever + * does. */ rds_conn_path_error(cp, "%s: failed to transition " "to state DOWN, current state " diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 69c6d3145b5a..774a71f88d37 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -165,9 +165,12 @@ void rds_tcp_reset_callbacks(struct socket *sock, * other state - typically RDS_CONN_DISCONNECTING or * RDS_CONN_ERROR with a shutdown in flight - is dropped * instead. That still replaces its state, with RDS_CONN_ERROR, - * and queues one more shutdown pass, but rds_conn_shutdown() - * accepts RDS_CONN_ERROR in its final transition to - * RDS_CONN_DOWN, so the shutdown in flight completes normally. + * and, unless a pending destroy is about to reap the whole + * connection anyway, queues one more shutdown pass. A shutdown + * already in flight leaves that RDS_CONN_ERROR alone when it + * finishes; the queued pass then completes the transition to + * RDS_CONN_DOWN and tears down anything that attached to the + * path in the meantime. */ if (!rds_conn_path_transition(cp, RDS_CONN_CONNECTING, RDS_CONN_RESETTING) && From 88f8113ab118ed0e187331324d6b60c694b2e0e2 Mon Sep 17 00:00:00 2001 From: Melissa Wen Date: Fri, 7 Aug 2026 13:56:21 +0200 Subject: [PATCH 0548/1198] drm/amd/display: use plane color_mgmt_changed to track colorop changes This is a resubmission of commit d79716401a95 ("drm/amd/display: use plane color_mgmt_changed to track colorop changes") whose change was reverted by commit 0461ba9a7994 ("Merge tag 'amd-drm-next-7.3-2026-07-02' of https://gitlab.freedesktop.org/agd5f/linux into drm-next") during a merge conflict resolution. Original commit message: ``` Ensure the driver tracks changes in any colorop property of a plane color pipeline by using the same mechanism of CRTC color management and update plane color blocks when any colorop property changes. It fixes an issue observed on gamescope settings for night mode which is done via shaper/3D-LUT updates. ``` Fixes: 0461ba9a7994 ("Merge tag 'amd-drm-next-7.3-2026-07-02' of https://gitlab.freedesktop.org/agd5f/linux into drm-next") Acked-by: Alex Deucher Signed-off-by: Melissa Wen Link: https://patch.msgid.link/20260807115712.22423-1-mwen@igalia.com --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index ec483276d753..2fe934036e36 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -3879,7 +3879,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_commit *state, continue; bundle->surface_updates[planes_count].surface = dc_plane; - if (new_pcrtc_state->color_mgmt_changed) { + if (new_pcrtc_state->color_mgmt_changed || new_plane_state->color_mgmt_changed) { bundle->surface_updates[planes_count].gamma = &dc_plane->gamma_correction; bundle->surface_updates[planes_count].in_transfer_func = &dc_plane->in_transfer_func; bundle->surface_updates[planes_count].gamut_remap_matrix = &dc_plane->gamut_remap_matrix; @@ -5698,6 +5698,10 @@ static bool should_reset_plane(struct drm_atomic_commit *state, if (new_crtc_state->color_mgmt_changed) return true; + /* Plane color pipeline or its colorop changes. */ + if (new_plane_state->color_mgmt_changed) + return true; + /* * On zpos change, planes need to be reordered by removing and re-adding * them one by one to the dc state, in order of descending zpos. From 115bf3e51538e74159e9fa46199468b69fd5df70 Mon Sep 17 00:00:00 2001 From: Sun Jian Date: Tue, 1 Sep 2026 04:40:11 -0700 Subject: [PATCH 0549/1198] exec: Drop bprm loader before closing bprm->file free_bprm() currently drops what may be the final reference to bprm->file before calling bprm_drop_loader(). Since bprm_drop_loader() is attachable via BPF fentry and bprm->file is exposed as a BTF_TYPE_SAFE_TRUSTED pointer, the file can be observed after its reference has been released. Move bprm_drop_loader() before do_close_execat(bprm->file), keeping the file reference held while the hook runs. This preserves the existing trusted BTF contract without changing verifier behavior. The loader file and bprm->file have independent references, so this reordering does not change their required teardown ordering. Link: https://sashiko.dev/#/patchset/20260831092305.42062-1-tasos.papagiannnis@gmail.com?part=3 Signed-off-by: Sun Jian Link: https://patch.msgid.link/20260901114011.112375-1-sun.jian.kdev@gmail.com Signed-off-by: Christian Brauner (Amutable) --- fs/exec.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/exec.c b/fs/exec.c index a14f28b15607..263b1f67f1f8 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1469,9 +1469,9 @@ static void free_bprm(struct linux_binprm *bprm) /* exec swapped the mm but failed before setup_new_exec() freed it */ if (bprm->old_mm) exec_mm_put_old(bprm->old_mm); - do_close_execat(bprm->file); /* An unconsumed PT_INTERP substitute from a binfmt_misc loader entry. */ bprm_drop_loader(bprm); + do_close_execat(bprm->file); do_close_execat(bprm->executable); /* If a binfmt changed the interp, free it. */ if (bprm->interp != bprm->filename) From d3609b540838945ab2ca5b65f32a2eb67bb284c8 Mon Sep 17 00:00:00 2001 From: Aditya Garg Date: Thu, 23 Jul 2026 10:01:36 +0000 Subject: [PATCH 0550/1198] MAINTAINERS, mailmap: use Aditya Garg's linux.dev account Due to non standard IMAP and SMTP protocols by Proton Mail, the account was giving trouble. Since my linux.dev account has been approved, all communication related to Linux development shall now be done there. Signed-off-by: Aditya Garg Acked-by: Thomas Zimmermann Signed-off-by: Thomas Zimmermann Link: https://patch.msgid.link/20260723100136.14467-1-aditya.garg@linux.dev --- .mailmap | 3 ++- MAINTAINERS | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/.mailmap b/.mailmap index 6803f3bd2865..08c84f5c90d2 100644 --- a/.mailmap +++ b/.mailmap @@ -19,7 +19,8 @@ Abhinav Kumar Ahmad Masri Adam Oldham Adam Radford -Aditya Garg +Aditya Garg +Aditya Garg Adriana Reus Adrian Bunk Ajay Kaher diff --git a/MAINTAINERS b/MAINTAINERS index 3a19da74d00c..c7e62407de32 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8039,7 +8039,7 @@ F: drivers/gpu/drm/sun4i/sun8i* DRM DRIVER FOR APPLE TOUCH BARS M: Aun-Ali Zaidi -M: Aditya Garg +M: Aditya Garg L: dri-devel@lists.freedesktop.org S: Maintained T: git https://gitlab.freedesktop.org/drm/misc/kernel.git From 2f37fba846c9fdff5fc15b6d93656057ccd13031 Mon Sep 17 00:00:00 2001 From: Ibrahim Hashimov Date: Sat, 25 Jul 2026 15:51:54 +0200 Subject: [PATCH 0551/1198] mac802154: fix use-after-free of sdata via queued RX frames The RX softirq producer ieee802154_subif_frame() queues received beacon and MAC-command frames onto local->rx_beacon_list / rx_mac_cmd_list and schedules a process-context worker, storing a raw mac_pkt->sdata (and skb->dev == sdata->dev) with neither a reference nor any locking: - the lists have no lock: the softirq producer list_add_tail()s while the mac_wq worker list_del()s, so sibling interfaces on the same phy corrupt the list; - the workers dereference the interface after it may have been freed. mac802154_rx_mac_cmd_worker() touches mac_pkt->sdata directly, and mac802154_rx_beacon_worker() -> mac802154_process_beacon() dereferences skb->dev (== sdata->dev). Removing an interface frees its sdata (netdev_priv) while a queued frame still points at it, so a later worker run is a use-after-free. Reproduced under KASAN by flooding a victim interface with MAC command frames and removing it (the beacon path is the same class via skb->dev): BUG: KASAN: slab-use-after-free in mac802154_rx_mac_cmd_worker+0x463/0x630 [mac802154] Read of size 4 at addr ffff888002f9ea18 by task kworker/u8:1/31 Workqueue: phy0-mac-cmds mac802154_rx_mac_cmd_worker [mac802154] Call Trace: mac802154_rx_mac_cmd_worker+0x463/0x630 [mac802154] process_one_work+0x611/0xe80 worker_thread+0x52e/0xdc0 kthread+0x30c/0x630 ret_from_fork+0x2fd/0x3e0 Fix both lists together: - add local->rx_lock and take it around every list access: the softirq producer (plain spin_lock, softirq context) and the workers and flush (spin_lock_bh, process context); - pin the interface for the lifetime of a queued frame with netdev_hold()/netdev_put(), so the worker can safely dereference sdata / skb->dev even while the interface is being removed; - dequeue under the lock at the head and loop-drain the whole list in the workers (they previously processed one frame per run and relied on a later enqueue to drain the rest); - drop not-yet-started frames of an interface before it is unregistered, from ieee802154_if_remove() (after the RCU grace period) and from the ieee802154_remove_interfaces() loop -- the latter is the whole-phy teardown path, which does not go through ieee802154_if_remove(). An in-flight worker that already dequeued a frame keeps its own netdev reference; unregister_netdevice() then waits it out in netdev_run_todo(), which runs at rtnl_unlock() (rtnl released) and after the interface has been closed, so it does not pin rtnl. A worker blocked in an association TX only delays that one interface's unregister (the usual "waiting for %s to become free"), it does not hold rtnl. netdev_hold() is used for this reason instead of a cancel_work_sync() under rtnl, which would block on the worker's unbounded MLME TX wait via ieee802154_sync_queue(). The mac-command worker additionally skips processing for a stopped interface (ieee802154_sdata_running()), avoiding a needless association response during teardown. Fixes: 57588c71177f ("mac802154: Handle passive scanning") Cc: stable@vger.kernel.org Signed-off-by: Ibrahim Hashimov Assisted-by: AuditCode-AI:2026.07 Reviewed-by: Miquel Raynal Link: https://lore.kernel.org/20260725135154.99876-1-security@auditcode.ai Signed-off-by: Stefan Schmidt --- include/net/cfg802154.h | 1 + net/mac802154/ieee802154_i.h | 8 +++ net/mac802154/iface.c | 6 ++ net/mac802154/main.c | 1 + net/mac802154/rx.c | 120 ++++++++++++++++++++++++++++------- net/mac802154/scan.c | 10 +-- 6 files changed, 117 insertions(+), 29 deletions(-) diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index 76d2cd2e2b30..2e960441ea49 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -376,6 +376,7 @@ struct cfg802154_mac_pkt { struct list_head node; struct sk_buff *skb; struct ieee802154_sub_if_data *sdata; + netdevice_tracker dev_tracker; u8 page; u8 channel; }; diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h index c53aa293a222..992ce6698c20 100644 --- a/net/mac802154/ieee802154_i.h +++ b/net/mac802154/ieee802154_i.h @@ -74,6 +74,10 @@ struct ieee802154_local { struct work_struct rx_beacon_work; struct list_head rx_mac_cmd_list; struct work_struct rx_mac_cmd_work; + /* Serializes rx_beacon_list and rx_mac_cmd_list against the RX + * softirq producer, the mac_wq workers and the teardown flush. + */ + spinlock_t rx_lock; /* Association */ /* assoc_lock protects assoc_dev_extended_addr, assoc_addr, @@ -305,6 +309,10 @@ static inline bool mac802154_is_beaconing(struct ieee802154_local *local) } void mac802154_rx_mac_cmd_worker(struct work_struct *work); +void mac802154_flush_list(struct list_head *list, + struct ieee802154_sub_if_data *sdata); +void mac802154_flush_queued_pkts(struct ieee802154_local *local, + struct ieee802154_sub_if_data *sdata); int mac802154_perform_association(struct ieee802154_sub_if_data *sdata, struct ieee802154_pan_device *coord, diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c index b823720630e7..31353795fa24 100644 --- a/net/mac802154/iface.c +++ b/net/mac802154/iface.c @@ -694,6 +694,7 @@ void ieee802154_if_remove(struct ieee802154_sub_if_data *sdata) mutex_unlock(&sdata->local->iflist_mtx); synchronize_rcu(); + mac802154_flush_queued_pkts(sdata->local, sdata); unregister_netdevice(sdata->dev); } @@ -705,6 +706,11 @@ void ieee802154_remove_interfaces(struct ieee802154_local *local) list_for_each_entry_safe(sdata, tmp, &local->interfaces, list) { list_del_rcu(&sdata->list); + /* Best-effort: a frame the RX softirq queues for this sdata + * after the flush still pins the netdev, so the + * unregister_netdevice() below waits it out. + */ + mac802154_flush_queued_pkts(local, sdata); unregister_netdevice(sdata->dev); } mutex_unlock(&local->iflist_mtx); diff --git a/net/mac802154/main.c b/net/mac802154/main.c index 63e89bd586e3..8ed6de111f5a 100644 --- a/net/mac802154/main.c +++ b/net/mac802154/main.c @@ -91,6 +91,7 @@ ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops) INIT_LIST_HEAD(&local->interfaces); INIT_LIST_HEAD(&local->rx_beacon_list); INIT_LIST_HEAD(&local->rx_mac_cmd_list); + spin_lock_init(&local->rx_lock); mutex_init(&local->iflist_mtx); tasklet_setup(&local->tasklet, ieee802154_tasklet_handler); diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c index cd8f2a11920d..19b5382e85a8 100644 --- a/net/mac802154/rx.c +++ b/net/mac802154/rx.c @@ -35,16 +35,23 @@ void mac802154_rx_beacon_worker(struct work_struct *work) container_of(work, struct ieee802154_local, rx_beacon_work); struct cfg802154_mac_pkt *mac_pkt; - mac_pkt = list_first_entry_or_null(&local->rx_beacon_list, - struct cfg802154_mac_pkt, node); - if (!mac_pkt) - return; + for (;;) { + spin_lock_bh(&local->rx_lock); + mac_pkt = list_first_entry_or_null(&local->rx_beacon_list, + struct cfg802154_mac_pkt, node); + if (mac_pkt) + list_del(&mac_pkt->node); + spin_unlock_bh(&local->rx_lock); + if (!mac_pkt) + break; - mac802154_process_beacon(local, mac_pkt->skb, mac_pkt->page, mac_pkt->channel); + mac802154_process_beacon(local, mac_pkt->skb, + mac_pkt->page, mac_pkt->channel); - list_del(&mac_pkt->node); - kfree_skb(mac_pkt->skb); - kfree(mac_pkt); + netdev_put(mac_pkt->sdata->dev, &mac_pkt->dev_tracker); + kfree_skb(mac_pkt->skb); + kfree(mac_pkt); + } } static bool mac802154_should_answer_beacon_req(struct ieee802154_local *local) @@ -68,22 +75,15 @@ static bool mac802154_should_answer_beacon_req(struct ieee802154_local *local) return interval == IEEE802154_ACTIVE_SCAN_DURATION; } -void mac802154_rx_mac_cmd_worker(struct work_struct *work) +static void mac802154_rx_mac_cmd(struct ieee802154_local *local, + struct cfg802154_mac_pkt *mac_pkt) { - struct ieee802154_local *local = - container_of(work, struct ieee802154_local, rx_mac_cmd_work); - struct cfg802154_mac_pkt *mac_pkt; u8 mac_cmd; int rc; - mac_pkt = list_first_entry_or_null(&local->rx_mac_cmd_list, - struct cfg802154_mac_pkt, node); - if (!mac_pkt) - return; - rc = ieee802154_get_mac_cmd(mac_pkt->skb, &mac_cmd); if (rc) - goto out; + return; switch (mac_cmd) { case IEEE802154_CMD_BEACON_REQ: @@ -121,11 +121,81 @@ void mac802154_rx_mac_cmd_worker(struct work_struct *work) default: break; } +} -out: - list_del(&mac_pkt->node); - kfree_skb(mac_pkt->skb); - kfree(mac_pkt); +void mac802154_rx_mac_cmd_worker(struct work_struct *work) +{ + struct ieee802154_local *local = + container_of(work, struct ieee802154_local, rx_mac_cmd_work); + struct cfg802154_mac_pkt *mac_pkt; + + for (;;) { + spin_lock_bh(&local->rx_lock); + mac_pkt = list_first_entry_or_null(&local->rx_mac_cmd_list, + struct cfg802154_mac_pkt, node); + if (mac_pkt) + list_del(&mac_pkt->node); + spin_unlock_bh(&local->rx_lock); + if (!mac_pkt) + break; + + /* A stopped interface cannot transmit; skipping avoids a + * needless association response (and the !netif_running() + * warning it would trip) during teardown. The beacon worker + * needs no such check as it never transmits. + */ + if (ieee802154_sdata_running(mac_pkt->sdata)) + mac802154_rx_mac_cmd(local, mac_pkt); + + netdev_put(mac_pkt->sdata->dev, &mac_pkt->dev_tracker); + kfree_skb(mac_pkt->skb); + kfree(mac_pkt); + } +} + +/** + * mac802154_flush_list - free queued RX frames on @list + * @list: rx_beacon_list or rx_mac_cmd_list + * @sdata: only free frames received on this interface, or %NULL for all + * + * Each frame pins the net_device it was received on (via netdev_hold()), + * so release that reference as the frame is dropped. Caller must hold + * local->rx_lock. + */ +void mac802154_flush_list(struct list_head *list, + struct ieee802154_sub_if_data *sdata) +{ + struct cfg802154_mac_pkt *mac_pkt, *tmp; + + list_for_each_entry_safe(mac_pkt, tmp, list, node) { + if (sdata && mac_pkt->sdata != sdata) + continue; + list_del(&mac_pkt->node); + netdev_put(mac_pkt->sdata->dev, &mac_pkt->dev_tracker); + kfree_skb(mac_pkt->skb); + kfree(mac_pkt); + } +} + +/** + * mac802154_flush_queued_pkts - drop queued RX work referencing @sdata + * @local: the mac802154 device + * @sdata: interface being removed + * + * The workers dereference the queued frame's interface directly + * (mac_pkt->sdata) or through skb->dev in mac802154_process_beacon(). Drop + * the not-yet-started entries belonging to @sdata before it is unregistered + * so their netdev reference is released; an entry already dequeued by a + * running worker keeps its own reference until the worker completes, which + * unregister_netdevice() then waits out. + */ +void mac802154_flush_queued_pkts(struct ieee802154_local *local, + struct ieee802154_sub_if_data *sdata) +{ + spin_lock_bh(&local->rx_lock); + mac802154_flush_list(&local->rx_beacon_list, sdata); + mac802154_flush_list(&local->rx_mac_cmd_list, sdata); + spin_unlock_bh(&local->rx_lock); } static int @@ -221,7 +291,10 @@ ieee802154_subif_frame(struct ieee802154_sub_if_data *sdata, mac_pkt->sdata = sdata; mac_pkt->page = sdata->local->scan_page; mac_pkt->channel = sdata->local->scan_channel; + netdev_hold(sdata->dev, &mac_pkt->dev_tracker, GFP_ATOMIC); + spin_lock(&sdata->local->rx_lock); list_add_tail(&mac_pkt->node, &sdata->local->rx_beacon_list); + spin_unlock(&sdata->local->rx_lock); queue_work(sdata->local->mac_wq, &sdata->local->rx_beacon_work); return NET_RX_SUCCESS; @@ -233,7 +306,10 @@ ieee802154_subif_frame(struct ieee802154_sub_if_data *sdata, mac_pkt->skb = skb_get(skb); mac_pkt->sdata = sdata; + netdev_hold(sdata->dev, &mac_pkt->dev_tracker, GFP_ATOMIC); + spin_lock(&sdata->local->rx_lock); list_add_tail(&mac_pkt->node, &sdata->local->rx_mac_cmd_list); + spin_unlock(&sdata->local->rx_lock); queue_work(sdata->local->mac_wq, &sdata->local->rx_mac_cmd_work); return NET_RX_SUCCESS; diff --git a/net/mac802154/scan.c b/net/mac802154/scan.c index dd156c01ac49..d393b1f4e74e 100644 --- a/net/mac802154/scan.c +++ b/net/mac802154/scan.c @@ -104,13 +104,9 @@ static unsigned int mac802154_scan_get_channel_time(u8 duration_order, static void mac802154_flush_queued_beacons(struct ieee802154_local *local) { - struct cfg802154_mac_pkt *mac_pkt, *tmp; - - list_for_each_entry_safe(mac_pkt, tmp, &local->rx_beacon_list, node) { - list_del(&mac_pkt->node); - kfree_skb(mac_pkt->skb); - kfree(mac_pkt); - } + spin_lock_bh(&local->rx_lock); + mac802154_flush_list(&local->rx_beacon_list, NULL); + spin_unlock_bh(&local->rx_lock); } static void From 2c1dde8a69a3a7d64425a6de0add6e289a5a402f Mon Sep 17 00:00:00 2001 From: Shrikanth Hegde Date: Fri, 28 Aug 2026 11:08:11 +0530 Subject: [PATCH 0552/1198] powerpc/entry: Clear TIF_SYSCALL_RET before syscall error return Shivaprasad reported a boot failure due to userspace processes crash on abort() from libc.so.6. It was bisected to merge request commit '3424d8c18a7d ("Merge tag 'core-entry-2026-08-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip")' Upon checking the merge, when syscall_enter_from_user_mode_randomize_stack fails, which could happen when a tracer like seccomp or ptrace intercepts and skips the syscall, the code returns to userspace immediately without clearing the intermediate flag which was set. When the next syscall is made, it immediately aborts the valid syscall since the flag is still set. Hence clear the flag on occurrence of first failure. Reported-by: Shivaprasad G Bhat Closes: https://lore.kernel.org/all/e301014d-568f-4ed5-bc64-b8a85ca0b1e1@linux.ibm.com/ Fixes: 3424d8c18a7d ("Merge tag 'core-entry-2026-08-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip") Signed-off-by: Shrikanth Hegde Tested-by: Venkat Rao Bagalkote Tested-by: Shivaprasad G Bhat Reviewed-by: Mukesh Kumar Chaurasiya (IBM) Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260828053811.1042300-1-sshegde@linux.ibm.com --- arch/powerpc/kernel/syscall.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c index 4916c205c4bb..fbefe1927b10 100644 --- a/arch/powerpc/kernel/syscall.c +++ b/arch/powerpc/kernel/syscall.c @@ -18,8 +18,10 @@ notrace long system_call_exception(struct pt_regs *regs, unsigned long r0) long ret; syscall_fn f; - if (unlikely(!syscall_enter_from_user_mode_randomize_stack(regs, &r0))) + if (unlikely(!syscall_enter_from_user_mode_randomize_stack(regs, &r0))) { + clear_thread_flag(TIF_SYSCALL_RET); return syscall_get_error(current, regs); + } if (unlikely(test_and_clear_thread_flag(TIF_SYSCALL_RET))) return syscall_get_error(current, regs); From c7585b8e99ad97a0f5dd21e45c90a33aeab0d92b Mon Sep 17 00:00:00 2001 From: "Ritesh Harjani (IBM)" Date: Sat, 29 Aug 2026 09:49:00 +0530 Subject: [PATCH 0553/1198] powerpc: Don't drop _TIF_RESTOREALL on syscall restart So the syscall return sequence is as follows: A syscall return to userspace is prepared and then a short asm sequence that actually does the RFI. Note that this asm range is restartable i.e. EE is still on, so an interrupt (e.g. decrementer or external interrupt) can hit while SRR/GPRs are being loaded. This is defined via: RESTART_TABLE(.Lsyscall_rst_start, .Lsyscall_rst_end, syscall_restart) This restart table then sends us to syscall_restart rather than resuming in the middle of the RFI. The same stub is also used if irq_happened already has a pending bit (soft-masked irq that has not been replayed yet (PowerPC special case of local_irq_disable())). Here is a bit of a flow of sequence of code to visualize: syscall_exit_prepare decide full-GPR restore (_TIF_RESTOREALL) for signal, rt_sigreturn or syscall trace save that in regs->exit_result and return it in r3 | v .Lsyscall_rst_start .. _end EE still on irq_happened set or interrupt in this range? | no | yes v v cmpdi r3,0 syscall_exit_restart restore all / zero replay irq, try exit again volatiles; RFI must return flags in r3 again for the same cmpdi Now r3 after prepare is the flags word, not the actual syscall return. A nested interrupt clobbers it, so the restart stub reloads RESULT into r3 and the C handler (syscall_exit_restart()) should put the flags back (because later asm checks whether r3 returned from C has _TIF_RESTOREALL set or not): cmpdi r3, 0 bne .Lsyscall_restore_regs Note that syscall_exit_restart() already ORs any new _TIF_RESTOREALL into exit_result, but then it only returns the new sample and not the full regs->exit_result. That sample could be often 0 even when restore-all is still required: - rt_sigreturn / syscall trace set the bit in prepare's local ret and in exit_result. They never set exit_flags, which is what restart samples. - a signal does set exit_flags but restart clears it. A second pass through the stub then returns 0 while exit_result still has the bit. The asm as mentioned earlier then treats r3==0 as the fast path and zeros r0/r4-r12. That means the userspace that needed the full register set could SIGSEGVs, (which could happen often in ld64.so.2 like while doing a parallel kernel build as reported by Venkat). So we should instead return the accumulated exit_result, like how we do in interrupt_exit_user_restart(). Note that prior to this commit 263e5159e00a ("powerpc: Fix exit_flags field placement in pt_regs for ptrace") we were returning regs->exit_result from syscall_exit_restart(), but this commit changed that behaviour. Fixes: 263e5159e00a ("powerpc: Fix exit_flags field placement in pt_regs for ptrace") Reported-by: Venkat Rao Bagalkote Closes: https://lore.kernel.org/all/75419f88-eab9-444b-bf97-28a9765819ad@linux.ibm.com/ Signed-off-by: Ritesh Harjani (IBM) Tested-by: Amit Machhiwal Tested-by: Shrikanth Hegde Tested-by: Venkat Rao Bagalkote Reviewed-by: Amit Machhiwal Reviewed-by: Shrikanth Hegde Reviewed-by: Mukesh Kumar Chaurasiya (IBM) Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/10c86c909f870d90b3094f76b692b44ebe9caeac.1787976185.git.ritesh.list@gmail.com --- arch/powerpc/kernel/interrupt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c index 5b88bf72786c..55f9c0c9922a 100644 --- a/arch/powerpc/kernel/interrupt.c +++ b/arch/powerpc/kernel/interrupt.c @@ -175,7 +175,7 @@ notrace unsigned long syscall_exit_restart(unsigned long r3, struct pt_regs *reg current_thread_info()->exit_flags &= ~_TIF_RESTOREALL; regs->exit_result |= ret; - return ret; + return regs->exit_result; } #endif From c2549d749539487239475fbc8c614a1f9244d655 Mon Sep 17 00:00:00 2001 From: "Ritesh Harjani (IBM)" Date: Sun, 30 Aug 2026 20:24:30 +0530 Subject: [PATCH 0554/1198] powerpc: Do not restore KUAP in arch_exit_to_user_mode_prepare() KUAP means kernel cannot touch user memory unless it explicitly is enabled. In the kernel it should stay AMR_KUAP_BLOCKED. While returning to userspace just before RFI, kernel should restore the user AMR value back. Looks like GENERIC_ENTRY might be treating arch_exit_to_user_mode_prepare() as the last architecture step before returning to userspace. commit bee25f97ad24 ("powerpc: Enable GENERIC_ENTRY feature") therefore called kuap_user_restore() from that hook. But on PowerPC that is too early. After irqentry_exit() / syscall_exit_to_user_mode() we still run platform specific exit routines. e.g. code snippets showing both exception handling and system call handling as the callers of function arch_exit_to_user_mode_prepare() which does kuap_user_restore(). The below path shows that calling kuap_user_restore() is too early when called from arch_exit_to_user_mode_prepare(). Exception handling in exceptions-64s.S ======================================= bl CFUNC(do_page_fault) ..DEFINE_INTERRUPT_HANDLER_ASYNC(do_page_fault) arch_interrupt_async_enter_prepare(regs); state = irqentry_enter(regs); instrumentation_begin(); irq_enter_rcu(); handler(regs); nap_adjust_return(regs); irq_exit_rcu(); instrumentation_end(); arch_interrupt_async_exit_prepare(regs); irqentry_exit(regs, state); <<< too early irqentry_exit_to_user_mode() __exit_to_user_mode_prepare(regs, EXIT_TO_USER_MODE_WORK_IRQ); arch_exit_to_user_mode_prepare(regs, ti_work); <<< too early b interrupt_return_srr .. bl CFUNC(interrupt_exit_user_prepare) <<< already calls kuap_user_restore prep_irq_for_enabled_exit() retry can run kernel code with IRQs on. So only when that routine is fully finished is when the user KUAP should be fully restored which interrupt_exit_user_prepare() already takes care of before returning. Similarly for system call handling in interrupt_64.S ====================================================== bl CFUNC(system_call_exception) .Lsyscall_exit: addi r4,r1,STACK_INT_FRAME_REGS li r5,0 /* !scv */ bl CFUNC(syscall_exit_prepare) .. kuap_assert_locked(); syscall_exit_to_user_mode(regs); <<< too early syscall_exit_to_user_mode_prepare(regs); <<< too early kuap_user_restore(regs); <<< already calls syscall_exit_prepare(), which can enable IRQs, replay a pending interrupt, and only then rfi. Those functions already restore KUAP immediately before rfi. Note that if we restore the user AMR too early like in the current code as shown from the code snippets above, then we get the following warning when CONFIG_PPC_KUAP_DEBUG is enabled: WARNING: arch/powerpc/include/asm/book3s/64/kup.h:293 at interrupt_exit_user_prepare+0x1a0/0x1c0 Hardware name: IBM pSeries (emulated by qemu) POWER10 (architected) TRAP: 0700 LR: c00000000000d8d4 CTR: c0000000021fe500 MSR: CR: 44000804 XER: 20040000 interrupt_exit_user_prepare+0x1a0/0x1c0 interrupt_return_srr_user+0x8/0x12c Fixes: bee25f97ad24 ("powerpc: Enable GENERIC_ENTRY feature") Fixes: 02565a782c1ee ("powerpc: Introduce syscall exit arch functions") Signed-off-by: Ritesh Harjani (IBM) Tested-by: Venkat Rao Bagalkote Reviewed-by: Mukesh Kumar Chaurasiya (IBM) Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/52fee44fd23acf8e1c024ace668728e626a783a8.1788101609.git.ritesh.list@gmail.com --- arch/powerpc/include/asm/entry-common.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/include/asm/entry-common.h b/arch/powerpc/include/asm/entry-common.h index c5adb5006361..94083516df57 100644 --- a/arch/powerpc/include/asm/entry-common.h +++ b/arch/powerpc/include/asm/entry-common.h @@ -515,8 +515,14 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, #ifdef CONFIG_PPC_TRANSACTIONAL_MEM local_paca->tm_scratch = regs->msr; #endif - /* Restore user access locks last */ - kuap_user_restore(regs); + /* + * Do not restore KUAP here. Generic entry might treat this as the last + * arch step before userspace but PowerPC still has kernel work after + * irqentry_exit()/syscall_exit_to_user_mode() i.e. in + * interrupt_exit_user_prepare() / syscall_exit_prepare() may enable + * IRQs and retry. Those functions restore KUAP immediately before rfi, + * which is where it should belong. + */ } #define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare From 7db28abbea0f7dc1ec4fdfdc149db5fbd9e4c994 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Sun, 30 Aug 2026 14:28:27 +0200 Subject: [PATCH 0555/1198] net: airoha: enable RX_DONE interrupt for RX queue 31 RX queue 31 has always been allocated and filled by airoha_qdma_init_rx() since RX_DONE_INT_MASK spans queues 0-31, but none of the RX_IRQ* _BANK_PIN_MASK values covered BIT(31). As a consequence the RX_DONE interrupt for queue 31 was never enabled, airoha_qdma_rx_process() never ran on that queue and its buffers were never reaped. Route RX queue 31's RX_DONE interrupt to IRQ bank 1 so that the queue is drained and its buffers returned to the page pool. Fixes: f252493e1835 ("net: airoha: Enable multiple IRQ lines support in airoha_eth driver.") Signed-off-by: Lorenzo Bianconi Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260830-airoha-rxdone-rxq31-v1-1-830a91503f2f@kernel.org Signed-off-by: Paolo Abeni --- drivers/net/ethernet/airoha/airoha_eth.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h index fa9a8edce22f..8277c1c87bb3 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.h +++ b/drivers/net/ethernet/airoha/airoha_eth.h @@ -538,7 +538,7 @@ struct airoha_wdma_info { /* RX queue to IRQ mapping: BIT(q) in IRQ(n) */ #define RX_IRQ0_BANK_PIN_MASK 0x839f -#define RX_IRQ1_BANK_PIN_MASK 0x7fe00000 +#define RX_IRQ1_BANK_PIN_MASK 0xffe00000 #define RX_IRQ2_BANK_PIN_MASK 0x20 #define RX_IRQ3_BANK_PIN_MASK 0x40 #define RX_IRQ_BANK_PIN_MASK(_n) \ From 6b8fed2675fb75d23e6cf2b7e49c94926e884b34 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Mon, 31 Aug 2026 19:06:38 +0200 Subject: [PATCH 0556/1198] net: stmmac: reconfigure RX packet parser table in stmmac_hw_setup() after reset The core software reset issued in stmmac_init_dma_engine() during ndo_open() callback clears the MTL RX packet parser registers, but stmmac_rxp_config() is only invoked from the cls_u32 add/delete paths. After an ifdown/ifup cycle the hardware therefore runs with the default all-pass table while priv->tc_entries still reports the filters as installed. Re-apply the RX packet parser table from priv->tc_entries in stmmac_hw_setup(), right after the software reset, so the filters are restored when the interface is brought up again. Fixes: 4dbbe8dde848 ("net: stmmac: Add support for U32 TC filter using Flexible RX Parser") Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20260831-stmmac_tc_cls32_reconfigure-v1-1-21cb459e64ae@oss.qualcomm.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index d576059c04df..24656b35350b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3676,6 +3676,14 @@ static int stmmac_hw_setup(struct net_device *dev) /* Initialize MTL*/ stmmac_mtl_configuration(priv); + /* Apply the RX packet parser table */ + if (priv->tc_entries) { + ret = stmmac_rxp_config(priv, priv->hw->pcsr, priv->tc_entries, + priv->tc_entries_max); + if (ret) + return ret; + } + /* Initialize Safety Features */ stmmac_safety_feat_configuration(priv); From 66817a9794263cd2a5dc4e99bf8e5fcc5ff7181e Mon Sep 17 00:00:00 2001 From: HW He Date: Tue, 1 Sep 2026 16:23:12 +0800 Subject: [PATCH 0557/1198] net: gro: Fix nesting of TCP GSO SKBs in skb_gro_receive_list() Fraglist GRO and hardware GRO can create an fraglist of HW-GRO packets. This cannot be segmented back into the original form on TCP tethering scenario. Avoid constructing such a GSO packet, by flushing an already built fraglist GRO packet if a hardware GRO packet arrives. Scenario (Tethering/Forwarding): 1.Driver submits a single TCP packet, P1. P1 is kept in the gro_list as the first packet. 2. The driver submits a TCP GSO skb, P2. P2 has already aggregated multiple TCP packets by HW_GRO, and its non-linear data is stored in frags[]. 3. P1 and P2 match the GRO rules, and since there is no local socket, they are aggregated by skb_gro_receive_list(). The resulting skb, P3, has a frag_list entry that still contains frags[]: P3: [ Linear Data ] -> frag_list -> [ Linear Data ] [ frag[1] ] [ frag[2] ] ... 4. Later, tcp4_gso_segment() or tcp6_gso_segment() calls skb_segment_list() to segment P3. However, skb_segment_list() only segments the entries in frag_list. It does not segment the frags[] inside P2, so P3 is not restored to the original packets, which leads to IP fragmentation or packet drop in the following path. Check skb_is_gso(skb) and current GRO method, make sure fraglist GRO applies to consecutive non-GSO skb, others adopt regular GRO path. Fixes: 8d95dc474f85 ("net: add code for TCP fraglist GRO") Signed-off-by: Zhaoping Shu Signed-off-by: HW He Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20260901082312.14596-1-zhaoping.shu@mediatek.com Signed-off-by: Paolo Abeni --- net/ipv4/tcp_offload.c | 22 ++++++++++++++++------ net/ipv6/tcpv6_offload.c | 15 +++++++++++++-- 2 files changed, 29 insertions(+), 8 deletions(-) diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 3b1fdcd3cb29..e74d99ca9fac 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -332,6 +332,7 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb, flush |= skb->ip_summed != p->ip_summed; flush |= skb->csum_level != p->csum_level; flush |= NAPI_GRO_CB(p)->count >= 64; + flush |= NAPI_GRO_CB(p)->is_flist != NAPI_GRO_CB(skb)->is_flist; skb_set_network_header(skb, skb_gro_receive_network_offset(skb)); if (flush || skb_gro_receive_list(p, skb)) @@ -395,12 +396,20 @@ static void tcp4_check_fraglist_gro(struct list_head *head, struct sk_buff *skb, struct net *net; int iif, sdif; - if (likely(!(skb->dev->features & NETIF_F_GRO_FRAGLIST))) - return; - p = tcp_gro_lookup(head, th); if (p) { - NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist; + /* flist GRO applies to consecutive non-GSO skbs */ + if (!skb_is_gso(skb) || !NAPI_GRO_CB(p)->is_flist) { + NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist; + return; + } + + /* Fall back to the regular GRO path */ + if (NAPI_GRO_CB(p)->count == 1) + NAPI_GRO_CB(p)->is_flist = 0; + + NAPI_GRO_CB(skb)->is_flist = 0; + return; } @@ -410,7 +419,7 @@ static void tcp4_check_fraglist_gro(struct list_head *head, struct sk_buff *skb, sk = __inet_lookup_established(net, iph->saddr, th->source, iph->daddr, ntohs(th->dest), iif, sdif); - NAPI_GRO_CB(skb)->is_flist = !sk; + NAPI_GRO_CB(skb)->is_flist = !sk && !skb_is_gso(skb); if (sk) sock_gen_put(sk); } @@ -430,7 +439,8 @@ struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb) if (!th) goto flush; - tcp4_check_fraglist_gro(head, skb, th); + if (unlikely(skb->dev->features & NETIF_F_GRO_FRAGLIST)) + tcp4_check_fraglist_gro(head, skb, th); return tcp_gro_receive(head, skb, th); diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index f2a659cd6183..eec3778855eb 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -26,7 +26,18 @@ static void tcp6_check_fraglist_gro(struct list_head *head, struct sk_buff *skb, p = tcp_gro_lookup(head, th); if (p) { - NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist; + /* flist GRO applies to consecutive non-GSO skbs */ + if (!skb_is_gso(skb) || !NAPI_GRO_CB(p)->is_flist) { + NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist; + return; + } + + /* Fall back to the regular GRO path */ + if (NAPI_GRO_CB(p)->count == 1) + NAPI_GRO_CB(p)->is_flist = 0; + + NAPI_GRO_CB(skb)->is_flist = 0; + return; } @@ -36,7 +47,7 @@ static void tcp6_check_fraglist_gro(struct list_head *head, struct sk_buff *skb, sk = __inet6_lookup_established(net, &hdr->saddr, th->source, &hdr->daddr, ntohs(th->dest), iif, sdif); - NAPI_GRO_CB(skb)->is_flist = !sk; + NAPI_GRO_CB(skb)->is_flist = !sk && !skb_is_gso(skb); if (sk) sock_gen_put(sk); #endif /* IS_ENABLED(CONFIG_IPV6) */ From a77644d009dece1104b6fcc6e322b0e4503db0d6 Mon Sep 17 00:00:00 2001 From: Karl Mehltretter Date: Fri, 28 Aug 2026 19:41:31 +0200 Subject: [PATCH 0558/1198] arm64: mm: Fix the lockless page-table walk in show_pte() show_pte() walks page tables locklessly and can run with interrupts enabled. A concurrent teardown can free a table page while it is being walked. It can also clear a parent entry after show_pte() checked it; the regular pXd_offset() helpers then reread the cleared entry and can derive a bogus lower-level pointer and fault again. Use the lockless offset helpers with the saved parent entries, as gup_fast() does, and pass the saved PMD to pte_offset_map(). For task page tables, arm64 selects MMU_GATHER_RCU_TABLE_FREE. Disable local interrupts around the walk to hold off RCU-deferred table frees and block the tlb_remove_table_sync_one() IPI until the walk is finished. Place the IRQ guard after the header print. This does not make the output a consistent snapshot, but prevents the task page-table walk from dereferencing a released table page or deriving a pointer from a different parent value. Fixes: 1d18c47c735e ("arm64: MMU fault handling and page table management") Cc: stable@vger.kernel.org Assisted-by: LLM Signed-off-by: Karl Mehltretter Signed-off-by: Will Deacon --- arch/arm64/mm/fault.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 0b52557652be..75c3e463df2e 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -154,6 +155,9 @@ static void show_pte(unsigned long addr) pr_alert("%s pgtable: %luk pages, %llu-bit VAs, pgdp=%016lx\n", mm == &init_mm ? "swapper" : "user", PAGE_SIZE / SZ_1K, vabits_actual, mm_to_pgd_phys(mm)); + + guard(irqsave)(); + pgdp = pgd_offset(mm, addr); pgd = READ_ONCE(*pgdp); pr_alert("[%016lx] pgd=%016llx", addr, pgd_val(pgd)); @@ -167,25 +171,25 @@ static void show_pte(unsigned long addr) if (pgd_none(pgd) || pgd_bad(pgd)) break; - p4dp = p4d_offset(pgdp, addr); + p4dp = p4d_offset_lockless(pgdp, pgd, addr); p4d = READ_ONCE(*p4dp); pr_cont(", p4d=%016llx", p4d_val(p4d)); if (p4d_none(p4d) || p4d_bad(p4d)) break; - pudp = pud_offset(p4dp, addr); + pudp = pud_offset_lockless(p4dp, p4d, addr); pud = READ_ONCE(*pudp); pr_cont(", pud=%016llx", pud_val(pud)); if (pud_none(pud) || pud_bad(pud)) break; - pmdp = pmd_offset(pudp, addr); + pmdp = pmd_offset_lockless(pudp, pud, addr); pmd = READ_ONCE(*pmdp); pr_cont(", pmd=%016llx", pmd_val(pmd)); if (pmd_none(pmd) || pmd_bad(pmd)) break; - ptep = pte_offset_map(pmdp, addr); + ptep = pte_offset_map(&pmd, addr); if (!ptep) break; From 1537e55728ec2bc506c74ea69b93cd859da58fb8 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Fri, 28 Aug 2026 02:28:18 -0700 Subject: [PATCH 0559/1198] arm64: trans_pgd: clone only the linear map that exists at runtime kexec_file_load() fails on arm64 if we have CONFIG_ARM64_VA_BITS_52 but it runs on a !FEAT_LPA2 host (such as my loving Grace machine). That is because trans_pgd_create_copy() uses the compile time PAGE_OFFSET (VA 52) instead of the actual VA size (48 -- due to the lack of LPA2). With the fifth level folded, pgd_none() is always false, so the walk cannot skip the 15 extra PGDIR_SIZE slots, and they all alias back to the same table: the whole kernel page table gets cloned 16 times, KASAN shadow included. Without KASAN it does not blow up, it just wastes ~RAM/32 in page tables. Fix it by copying the linear map that is the actual one, not the compiled one. Fixes: a6bbf5d4d9d1 ("arm64: mm: Add definitions to support 5 levels of paging") Signed-off-by: Breno Leitao Tested-by: Yury Smirnov Signed-off-by: Will Deacon --- arch/arm64/kernel/machine_kexec.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index c5693a32e49b..8f9bc2327dc8 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -129,7 +129,8 @@ int machine_kexec_post_load(struct kimage *kimage) } /* Create a copy of the linear map */ - rc = trans_pgd_create_copy(&info, &trans_pgd, PAGE_OFFSET, PAGE_END); + rc = trans_pgd_create_copy(&info, &trans_pgd, + _PAGE_OFFSET(vabits_actual), PAGE_END); if (rc) return rc; kimage->arch.ttbr1 = __pa(trans_pgd); From 5541432e09dc2031978188f3e8a00b9fc78cf097 Mon Sep 17 00:00:00 2001 From: Khushit Shah Date: Mon, 31 Aug 2026 10:54:44 +0000 Subject: [PATCH 0560/1198] arm64: errata: pass REVIDR when matching target implementation CPUs When target implementation CPUs are provided, is_affected_midr_range() accidentally passed the MIDR as both arguments to __is_affected_midr_range(), so the REVIDR mask check operated on the wrong register. Pass REVIDR as intended. Fixes: 86edf6bdcf05 ("smccc/kvm_guest: Enable errata based on implementation CPUs") Cc: stable@vger.kernel.org Signed-off-by: Khushit Shah Reviewed-by: Zenghui Yu (Huawei) Acked-by: Marc Zyngier Reviewed-by: Shameer Kolothum Signed-off-by: Will Deacon --- arch/arm64/kernel/cpu_errata.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 5db8f0619e4b..b33dccfafaf8 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -82,7 +82,7 @@ is_affected_midr_range(const struct arm64_cpu_capabilities *entry, int scope) for (i = 0; i < target_impl_cpu_num; i++) { if (__is_affected_midr_range(entry, target_impl_cpus[i].midr, - target_impl_cpus[i].midr)) + target_impl_cpus[i].revidr)) return true; } return false; From 5445d64199626974269fcdf347769ad44b0bb53b Mon Sep 17 00:00:00 2001 From: Fuad Tabba Date: Thu, 27 Aug 2026 19:59:37 +0100 Subject: [PATCH 0561/1198] arm64: Don't read GMID_EL1 when MTE is disabled __cpuinfo_store_cpu() gates the GMID_EL1 read on the raw ID_AA64PFR1_EL1, so it reads the register even when the kernel has disabled MTE (CONFIG_ARM64_MTE=n or arm64.nomte). KVM sets HCR_EL2.TID5 in that case, and pKVM injects an UNDEF the host cannot handle: Internal error: Oops - Undefined instruction: 0000000002000000 [#1] SMP pc : __cpuinfo_store_cpu+0xf4/0x264 Kernel panic - not syncing: Attempted to kill the idle task! Only pKVM reaches it, and only after a CPU is offlined and brought back online: its CPU_ON relay sets the host HCR before the CPU enters EL1, while plain nVHE sets it at CPUHP_AP_KVM_ONLINE. Gate the read on the CPU's own ID_AA64PFR1_EL1 with the command-line override applied, and on CONFIG_ARM64_MTE, which no register reflects. The boot CPU stores its registers before init_cpu_features() strips an unsafe override, so clamp against the hardware value here too. Fixes: f35abcbb8a084 ("KVM: arm64: Trap MTE access and discovery when MTE is disabled") Cc: stable@vger.kernel.org Signed-off-by: Fuad Tabba Reviewed-by: Catalin Marinas Signed-off-by: Will Deacon --- arch/arm64/include/asm/cpu.h | 1 + arch/arm64/include/asm/cpufeature.h | 7 ------ arch/arm64/kernel/cpufeature.c | 33 +++++++++++++++++++++++++---- arch/arm64/kernel/cpuinfo.c | 2 +- 4 files changed, 31 insertions(+), 12 deletions(-) diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h index 71493b760b83..3c008821219c 100644 --- a/arch/arm64/include/asm/cpu.h +++ b/arch/arm64/include/asm/cpu.h @@ -78,5 +78,6 @@ void __init cpuinfo_store_boot_cpu(void); void __init init_cpu_features(struct cpuinfo_arm64 *info); void update_cpu_features(int cpu, struct cpuinfo_arm64 *info, struct cpuinfo_arm64 *boot); +bool gmid_el1_accessible(const struct cpuinfo_arm64 *info); #endif /* __ASM_CPU_H */ diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 7404a6e83a93..4f04ad82ea34 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -627,13 +627,6 @@ static inline bool id_aa64pfr1_mpamfrac(u64 pfr1) return val > 0; } -static inline bool id_aa64pfr1_mte(u64 pfr1) -{ - u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_EL1_MTE_SHIFT); - - return val >= ID_AA64PFR1_EL1_MTE_MTE2; -} - void __init setup_boot_cpu_features(void); void __init setup_system_features(void); void __init setup_user_features(void); diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 17b83a2518a8..32102c3912fa 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1178,6 +1178,33 @@ static bool detect_ftr_has_mpam(void) return id_aa64pfr0_mpam(pfr0) || id_aa64pfr1_mpamfrac(pfr1); } +bool gmid_el1_accessible(const struct cpuinfo_arm64 *info) +{ + const struct arm64_ftr_bits *ftrp; + s64 mte, ovr; + u64 ftr_mask; + + /* No ID register reflects CONFIG_ARM64_MTE. */ + if (!IS_ENABLED(CONFIG_ARM64_MTE)) + return false; + + for (ftrp = ftr_id_aa64pfr1; ftrp->width; ftrp++) { + if (ftrp->shift == ID_AA64PFR1_EL1_MTE_SHIFT) + break; + } + + ftr_mask = arm64_ftr_mask(ftrp); + mte = arm64_ftr_value(ftrp, info->reg_id_aa64pfr1); + + /* The boot CPU runs before init_cpu_ftr_reg() strips unsafe overrides. */ + if ((id_aa64pfr1_override.mask & ftr_mask) == ftr_mask) { + ovr = arm64_ftr_value(ftrp, id_aa64pfr1_override.val); + mte = arm64_ftr_safe_value(ftrp, ovr, mte); + } + + return mte >= ID_AA64PFR1_EL1_MTE_MTE2; +} + void __init init_cpu_features(struct cpuinfo_arm64 *info) { /* Before we start using the tables, make sure it is sorted */ @@ -1230,7 +1257,7 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info) init_cpu_ftr_reg(SYS_MPAMIDR_EL1, info->reg_mpamidr); } - if (id_aa64pfr1_mte(info->reg_id_aa64pfr1)) + if (gmid_el1_accessible(info)) init_cpu_ftr_reg(SYS_GMID_EL1, info->reg_gmid); } @@ -1492,11 +1519,9 @@ void update_cpu_features(int cpu, * they read/write depends on the GMID_EL1.BS field. Check that the * value is the same on all CPUs. */ - if (IS_ENABLED(CONFIG_ARM64_MTE) && - id_aa64pfr1_mte(info->reg_id_aa64pfr1)) { + if (gmid_el1_accessible(info)) taint |= check_update_ftr_reg(SYS_GMID_EL1, cpu, info->reg_gmid, boot->reg_gmid); - } /* * If we don't have AArch32 at all then skip the checks entirely diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index d50e2a9b066b..45c63f3d75c5 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -502,7 +502,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) info->reg_id_aa64smfr0 = read_cpuid(ID_AA64SMFR0_EL1); info->reg_id_aa64fpfr0 = read_cpuid(ID_AA64FPFR0_EL1); - if (id_aa64pfr1_mte(info->reg_id_aa64pfr1)) + if (gmid_el1_accessible(info)) info->reg_gmid = read_cpuid(GMID_EL1); if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) From bc69439d983cc491cc86e01fafc1deb94e1bb85e Mon Sep 17 00:00:00 2001 From: Yudi Yang <2000jedi@gmail.com> Date: Tue, 1 Sep 2026 14:55:11 -0500 Subject: [PATCH 0562/1198] drm/rockchip: analogix_dp: fix unchecked bound endpoint name length rockchip_dp_drm_encoder_enable() uses sprintf() to format a device tree path into a 32-byte stack buffer. Device tree paths are not limited to this size, so a sufficiently long path can overflow the buffer. Use snprintf() with the destination size to truncate the generated name and keep the writes within bounds. Fixes: 729f8eefdcad ("drm/rockchip: analogix_dp: Add support for RK3588") Cc: stable@vger.kernel.org Signed-off-by: Yudi Yang <2000jedi@gmail.com> Signed-off-by: Heiko Stuebner Link: https://patch.msgid.link/20260901195511.2761251-1-2000jedi@gmail.com --- drivers/gpu/drm/rockchip/analogix_dp-rockchip.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c index 587e60232ec7..efd5a98e80bd 100644 --- a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c +++ b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c @@ -241,10 +241,11 @@ static void rockchip_dp_drm_encoder_enable(struct drm_encoder *encoder, of_graph_get_remote_port(endpoint.local_node); of_property_read_u32(remote_port, "reg", &port_id); - sprintf(name, "%s vp%d", remote_port_parent->full_name, port_id); + snprintf(name, sizeof(name), "%s vp%d", + remote_port_parent->full_name, port_id); } else { - sprintf(name, "%s %s", - remote_port_parent->full_name, endpoint.id ? "vopl" : "vopb"); + snprintf(name, sizeof(name), "%s %s", + remote_port_parent->full_name, endpoint.id ? "vopl" : "vopb"); } DRM_DEV_DEBUG(dp->dev, "vop %s output to dp\n", (ret) ? "LIT" : "BIG"); From 6d81700ad7c4871f94fb72e469cb0f3f55843ef7 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Wed, 2 Sep 2026 11:08:28 +0900 Subject: [PATCH 0563/1198] ata: libata-scsi: do not raise UA for storage element depopulation and restoration The libata command completion for the ATA commands REMOVE ELEMENT AND TRUNCATE and RESTORE ELEMENTS AND REBUILD is handled using the function ata_scsi_depop_ua_cap_changed_complete(). This completion function raises a UNIT ATTENTION with the additional sense code CAPACITY DATA HAS CHANGED. But doing so, the scsi layer seeing the UNIT ATTENTION sense key ends up failing the command, even if the command result is in fact OK. The SAT specifications do provide more details about the capacity change should be notified, and that relies on the ACCESSIBLE CAPACITY field of the IDENTIFY DATA retrieved before or after the command is issued, and then raising a UNIT ATTENTION if the capacity has really changed. However, we do not have any simple mean to raise a unit attention from libata-scsi. So rather than seeing the REMOVE ELEMENT AND TRUNCATE and RESTORE ELEMENTS AND REBUILD commands failing, remove the function ata_scsi_depop_ua_cap_changed_complete() and rely on the regular completion callback. Since for now these commands can only be issued as passthrough commands, the user is responsible for revalidating the device capacity after executing these commands. Fixes: db496721cb0d ("ata: libata-scsi: add support for the REMOVE ELEMENT AND TRUNCATE command") Fixes: 1e307ca61a9c ("ata: libata-scsi: add support for the RESTORE ELEMENTS AND REBUILD command") Signed-off-by: Damien Le Moal Link: https://lore.kernel.org/r/20260902020828.1436048-1-dlemoal@kernel.org Signed-off-by: Niklas Cassel --- drivers/ata/libata-scsi.c | 24 ------------------------ 1 file changed, 24 deletions(-) diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index a7d667cfcfec..b3666519b648 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -4823,28 +4823,6 @@ ata_scsi_get_phys_element_status_xlat(struct ata_queued_cmd *qc) return 0; } -static void ata_scsi_depop_ua_cap_changed_complete(struct ata_queued_cmd *qc) -{ - struct scsi_cmnd *scmd = qc->scsicmd; - u8 *cdb = scmd->cmnd; - bool is_ata_passthru = cdb[0] == ATA_16 || cdb[0] == ATA_12; - bool is_success = qc->err_mask == 0; - - /* - * For successful non-passthrough commands, raise a UNIT ATTENTION with - * the additional sense code set to CAPACITY DATA HAS CHANGED to be - * raised. Note that this should be done only if the capacity has - * actually changed, which may not be the case if the element that was - * specified for depopulation was already depopulated, or we did not - * restore any removed element. But a capacity change unit attention is - * harmless, so always raise the unit attention. - */ - if (is_success && !is_ata_passthru) - ata_scsi_set_sense(qc->dev, scmd, UNIT_ATTENTION, - UA_CHANGED_ASC, CAPACITY_CHANGED_ASCQ); - ata_scsi_qc_complete(qc); -} - static unsigned int ata_scsi_remove_element_and_truncate_xlat(struct ata_queued_cmd *qc) { @@ -4884,7 +4862,6 @@ ata_scsi_remove_element_and_truncate_xlat(struct ata_queued_cmd *qc) tf->flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE | ATA_TFLAG_LBA48; qc->flags |= ATA_QCFLAG_RESULT_TF; - qc->complete_fn = ata_scsi_depop_ua_cap_changed_complete; return 0; } @@ -4937,7 +4914,6 @@ ata_scsi_restore_elements_and_rebuild_xlat(struct ata_queued_cmd *qc) tf->flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE | ATA_TFLAG_LBA48; qc->flags |= ATA_QCFLAG_RESULT_TF; - qc->complete_fn = ata_scsi_depop_ua_cap_changed_complete; return 0; } From 6365c44a824ff138e7926413932bb5c2e28a4c8c Mon Sep 17 00:00:00 2001 From: Vincent Donnefort Date: Tue, 1 Sep 2026 16:54:42 +0100 Subject: [PATCH 0564/1198] ring-buffer: Allow splice reads on static buffers ring_buffer_read_page() rejects splice (full=1) reads on static buffers (that is user-mapped, persistent or remote) because !read check assumes unread pages must be swapped. However for those buffers we have no other choice than memcpy the data. For the memcpy case, only return an error when the writer is still on the reader page for the splice interface to wait. Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260901155445.1475405-2-vdonnefort@google.com Fixes: 117c39200d9d ("ring-buffer: Introducing ring-buffer mapping functions") Signed-off-by: Vincent Donnefort Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index b0963ac6fd16..84fd4cdd486f 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -7193,15 +7193,8 @@ int ring_buffer_read_page(struct trace_buffer *buffer, unsigned int event_size; unsigned int flags = 0; - /* - * If a full page is expected, this can still be returned - * if there's been a previous partial read and the - * rest of the page can be read and the commit page is off - * the reader page. - */ - if (full && - (!read || (len < (size - read)) || - cpu_buffer->reader_page == cpu_buffer->commit_page)) + /* If a full page is requested, it cannot be the commit page */ + if (full && cpu_buffer->reader_page == cpu_buffer->commit_page) return -1; if (len > (size - read)) From 42d3358bf145f27d32350037e67d3527e9098c1e Mon Sep 17 00:00:00 2001 From: Fredric Cover Date: Wed, 2 Sep 2026 17:49:01 -0700 Subject: [PATCH 0565/1198] smb: client: fill cache fields after populating cache in copy_ref_data() In copy_ref_data(), struct cache_entry *ce has its fields populated at the beginning of the function. Later, if alloc_target fails with an ERR_PTR, free_tgts() is called on the cache, leaving the cache metadata populated without any targets. Critically, this extends ce->etime, making the cache appear valid for longer without any targets. Also, free_tgts() does not set ce->numtgts to zero. On error, when the cache is freed, ce->numtgts is not zeroed, and other cache users may attempt to access nonexistent entries. Update fields after copying targets to prevent partial-state updates. Set ce->numtgts to zero at the end of free_tgts(). Signed-off-by: Fredric Cover Signed-off-by: Paulo Alcantara --- fs/smb/client/dfs_cache.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/fs/smb/client/dfs_cache.c b/fs/smb/client/dfs_cache.c index 86dba25b7a5a..611e18fe8204 100644 --- a/fs/smb/client/dfs_cache.c +++ b/fs/smb/client/dfs_cache.c @@ -123,6 +123,7 @@ static inline void free_tgts(struct cache_entry *ce) kfree(t); } + ce->numtgts = 0; WRITE_ONCE(ce->tgthint, NULL); } @@ -388,13 +389,6 @@ static int copy_ref_data(const struct dfs_info3_param *refs, int numrefs, struct cache_dfs_tgt *target; int i; - ce->ttl = max_t(int, refs[0].ttl, CACHE_MIN_TTL); - ce->etime = get_expire_time(ce->ttl); - ce->srvtype = refs[0].server_type; - ce->hdr_flags = refs[0].flags; - ce->ref_flags = refs[0].ref_flag; - ce->path_consumed = refs[0].path_consumed; - for (i = 0; i < numrefs; i++) { struct cache_dfs_tgt *t; @@ -409,12 +403,19 @@ static int copy_ref_data(const struct dfs_info3_param *refs, int numrefs, } else { list_add_tail(&t->list, &ce->tlist); } - ce->numtgts++; } target = list_first_entry_or_null(&ce->tlist, struct cache_dfs_tgt, list); + WRITE_ONCE(ce->tgthint, target); + ce->ttl = max_t(int, refs[0].ttl, CACHE_MIN_TTL); + ce->etime = get_expire_time(ce->ttl); + ce->srvtype = refs[0].server_type; + ce->hdr_flags = refs[0].flags; + ce->ref_flags = refs[0].ref_flag; + ce->path_consumed = refs[0].path_consumed; + ce->numtgts = numrefs; return 0; } @@ -634,7 +635,6 @@ static int update_cache_entry_locked(struct cache_entry *ce, const struct dfs_in } free_tgts(ce); - ce->numtgts = 0; rc = copy_ref_data(refs, numrefs, ce, th); From 82e664cf1219c459c33aae931b222cf951af9cb7 Mon Sep 17 00:00:00 2001 From: Gao Xiang Date: Thu, 3 Sep 2026 22:28:41 +0800 Subject: [PATCH 0566/1198] erofs: disable LZ4 rolling decompression for now MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit LZ4 rolling decompression [1] was introduced to reduce the memory footprint of temporary pages: For many cases, it is needed for users to read small data within a compressed extent (pcluster), either due to random small read, or since uptodate folios (typically order-0) cannot be reused for decompression again since decompression algorithm refills already-uptodate folios. Rolling decompression works because LZ4 is LZ77-based and only refers to the most recent 64 KiB of decompressed data, so in theory only a bounded rolling window of temporary pages is needed when decompressing. It can save a lot of temporary memory, e.g. 601,960-byte data can be compressed into a 256k LZ4 compressed extent, which means it needs 146 extra pages per request in the worst case if rolling decompression is disabled. However, the upstream LZ4 implementation is not under EROFS' control: For example, the literal copy memmove() may still **copy long literals backward** on x86 based on the address comparison even when the source and destination ranges do not overlap (IOWs, inline decompression doesn't need to be considered here). That breaks the rolling assumption and makes the optimization broken. Disable it for now to make sure the data correctness first since EROFS is used everywhere now: The rolling window approach can be revived once we either ensure that the official LZ4 code always copies forward for non-overlapping ranges or maintain our own LZ4 implementation in EROFS. The main impact is a higher runtime memory footprint; However, recent commit 0f6273ab4637 ("erofs: add a reserved buffer pool for lz4 decompression") helps mitigate this when enabled but it's still not perfect. [1] https://www.usenix.org/conference/atc19/presentation/gao § 3.3 Decompression Reported-by: "Walther, Jens-Uwe" Closes: https://lore.kernel.org/r/BEZP281MB2102E57CD31862B8D958B33DD2AC2@BEZP281MB2102.DEUP281.PROD.OUTLOOK.COM Fixes: 8e6c8fa9f2e9 ("erofs: enable big pcluster feature") Cc: Yann Collet Signed-off-by: Gao Xiang --- fs/erofs/decompressor.c | 55 +++++++++-------------------------------- fs/erofs/internal.h | 6 +---- fs/erofs/zdata.c | 18 +++----------- 3 files changed, 16 insertions(+), 63 deletions(-) diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c index 27caf4bebddc..d387b27c4ee2 100644 --- a/fs/erofs/decompressor.c +++ b/fs/erofs/decompressor.c @@ -7,8 +7,6 @@ #include "compress.h" #include -#define LZ4_MAX_DISTANCE_PAGES (DIV_ROUND_UP(LZ4_DISTANCE_MAX, PAGE_SIZE) + 1) - static int z_erofs_load_lz4_config(struct super_block *sb, struct erofs_super_block *dsb, void *data, int size) { @@ -21,8 +19,6 @@ static int z_erofs_load_lz4_config(struct super_block *sb, erofs_err(sb, "invalid lz4 cfgs, size=%u", size); return -EINVAL; } - distance = le16_to_cpu(lz4->max_distance); - sbi->lz4.max_pclusterblks = le16_to_cpu(lz4->max_pclusterblks); if (!sbi->lz4.max_pclusterblks) { sbi->lz4.max_pclusterblks = 1; /* reserved case */ @@ -39,45 +35,25 @@ static int z_erofs_load_lz4_config(struct super_block *sb, sbi->lz4.max_pclusterblks = 1; sbi->available_compr_algs = 1 << Z_EROFS_COMPRESSION_LZ4; } - - sbi->lz4.max_distance_pages = distance ? - DIV_ROUND_UP(distance, PAGE_SIZE) + 1 : - LZ4_MAX_DISTANCE_PAGES; return z_erofs_gbuf_growsize(sbi->lz4.max_pclusterblks); } /* - * Fill all gaps with bounce pages if it's a sparse page list. Also check if - * all physical pages are consecutive, which can be seen for moderate CR. + * Fill all gaps with bounce pages if it's a sparse page list (for example some + * folios are already uptodate and thus can be mapped into userspace). Also + * check if pages are physically consecutive, which can be seen for moderate CR. */ -static int z_erofs_lz4_prepare_dstpages(struct z_erofs_decompress_req *rq, - struct page **pagepool) +static int z_erofs_oneshot_prepare_dstpages(struct z_erofs_decompress_req *rq, + struct page **pagepool) { - struct page *availables[LZ4_MAX_DISTANCE_PAGES] = { NULL }; - unsigned long bounced[DIV_ROUND_UP(LZ4_MAX_DISTANCE_PAGES, - BITS_PER_LONG)] = { 0 }; - unsigned int lz4_max_distance_pages = - EROFS_SB(rq->sb)->lz4.max_distance_pages; void *kaddr = NULL; - unsigned int i, j, top; + unsigned int i; - top = 0; - for (i = j = 0; i < rq->outpages; ++i, ++j) { - struct page *const page = rq->out[i]; - struct page *victim; - - if (j >= lz4_max_distance_pages) - j = 0; - - /* 'valid' bounced can only be tested after a complete round */ - if (!rq->fillgaps && test_bit(j, bounced)) { - DBG_BUGON(i < lz4_max_distance_pages); - DBG_BUGON(top >= lz4_max_distance_pages); - availables[top++] = rq->out[i - lz4_max_distance_pages]; - } + for (i = 0; i < rq->outpages; ++i) { + struct page *page, *victim; + page = rq->out[i]; if (page) { - __clear_bit(j, bounced); if (!PageHighMem(page)) { if (!i) { kaddr = page_address(page); @@ -89,21 +65,14 @@ static int z_erofs_lz4_prepare_dstpages(struct z_erofs_decompress_req *rq, continue; } } - kaddr = NULL; - continue; - } - kaddr = NULL; - __set_bit(j, bounced); - - if (top) { - victim = availables[--top]; } else { victim = __erofs_allocpage(pagepool, rq->gfp, true); if (!victim) return -ENOMEM; set_page_private(victim, Z_EROFS_SHORTLIVED_PAGE); + rq->out[i] = victim; } - rq->out[i] = victim; + kaddr = NULL; } return kaddr ? 1 : 0; } @@ -266,7 +235,7 @@ static const char *z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, dst_maptype = 0; } else { /* general decoding path which can be used for all cases */ - ret = z_erofs_lz4_prepare_dstpages(rq, pagepool); + ret = z_erofs_oneshot_prepare_dstpages(rq, pagepool); if (ret < 0) return ERR_PTR(ret); if (ret > 0) { diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 65974e57aebf..12e3a5b80a5a 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -71,12 +71,8 @@ struct erofs_dev_context { bool flatdev; }; -/* all filesystem-wide lz4 configurations */ struct erofs_sb_lz4_info { - /* # of pages needed for EROFS lz4 rolling decompression */ - u16 max_distance_pages; - /* maximum possible blocks for pclusters in the filesystem */ - u16 max_pclusterblks; + u16 max_pclusterblks; /* maximum physical blocks for LZ4 pclusters */ }; struct erofs_xattr_prefix_item { diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index e1e25ca0d190..6b07e73ee2aa 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1259,7 +1259,7 @@ static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, bool eio) const struct z_erofs_decompressor *alg = z_erofs_decomp[pcl->algorithmformat]; bool try_free = true; - int i, j, jtop, err2, err = eio ? -EIO : 0; + int i, err2, err = eio ? -EIO : 0; struct page *page; bool overlapped; const char *reason; @@ -1348,7 +1348,6 @@ static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, bool eio) be->compressed_pages >= be->onstack_pages + Z_EROFS_ONSTACK_PAGES) kvfree(be->compressed_pages); - jtop = 0; z_erofs_fill_other_copies(be, err); for (i = 0; i < be->nr_pages; ++i) { page = be->decompressed_pages[i]; @@ -1356,22 +1355,11 @@ static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, bool eio) continue; DBG_BUGON(z_erofs_page_is_invalidated(page)); - if (!z_erofs_is_shortlived_page(page)) { + if (!z_erofs_is_shortlived_page(page)) erofs_onlinefolio_end(page_folio(page), err, true); - continue; - } - if (pcl->algorithmformat != Z_EROFS_COMPRESSION_LZ4) { + else erofs_pagepool_add(be->pagepool, page); - continue; - } - for (j = 0; j < jtop && be->decompressed_pages[j] != page; ++j) - ; - if (j >= jtop) /* this bounce page is newly detected */ - be->decompressed_pages[jtop++] = page; } - while (jtop) - erofs_pagepool_add(be->pagepool, - be->decompressed_pages[--jtop]); if (be->decompressed_pages != be->onstack_pages) kvfree(be->decompressed_pages); From c83e3e806d4c115f1dad9ef756db4cd91448a262 Mon Sep 17 00:00:00 2001 From: Igor Paunovic Date: Thu, 13 Aug 2026 16:40:18 +0200 Subject: [PATCH 0567/1198] drm/rockchip: dw_dp: Select DRM_BRIDGE_CONNECTOR dw_dp-rockchip.c calls drm_bridge_connector_init(), but ROCKCHIP_DW_DP does not select DRM_BRIDGE_CONNECTOR. A configuration with ROCKCHIP_DW_DP as the only enabled Rockchip output option fails to link: aarch64-linux-gnu-ld: drivers/gpu/drm/rockchip/dw_dp-rockchip.o: in function `dw_dp_rockchip_bind': dw_dp-rockchip.c:(.text+0x1d4): undefined reference to `drm_bridge_connector_init' Five other Rockchip encoder options that call drm_bridge_connector_init() (ROCKCHIP_ANALOGIX_DP, ROCKCHIP_CDN_DP, ROCKCHIP_DW_HDMI_QP, ROCKCHIP_LVDS, ROCKCHIP_RGB) already select it, which masks the gap in any configuration that enables one of them. ROCKCHIP_INNO_HDMI is covered through its DRM_INNO_HDMI core option. The same change was posted by Marius Dinu in March and dropped when the failure stopped reproducing in his build. The failure is configuration-dependent - any other enabled option that selects DRM_BRIDGE_CONNECTOR hides it - and it still reproduces on current drm-misc-next with the configuration described above. Select DRM_BRIDGE_CONNECTOR like the other users do. Fixes: d68ba7bac955 ("drm/rockchip: Add RK3588 DPTX output support") Link: https://lore.kernel.org/r/aneNCDU12OzG99UX@venus # ack to handle this apart from the dw-dp series Link: https://lore.kernel.org/r/20260319155051.1944-1-m95d+git@psihoexpert.ro # earlier submission by Marius Dinu Signed-off-by: Igor Paunovic Signed-off-by: Heiko Stuebner Link: https://patch.msgid.link/20260813144019.12089-2-royalnet026@gmail.com --- drivers/gpu/drm/rockchip/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/rockchip/Kconfig b/drivers/gpu/drm/rockchip/Kconfig index e7f49fe845ea..697c0748eeca 100644 --- a/drivers/gpu/drm/rockchip/Kconfig +++ b/drivers/gpu/drm/rockchip/Kconfig @@ -68,6 +68,7 @@ config ROCKCHIP_CDN_DP config ROCKCHIP_DW_DP bool "Rockchip specific extensions for Synopsys DW DP" + select DRM_BRIDGE_CONNECTOR help This selects support for Rockchip SoC specific extensions to enable Synopsys DesignWare Cores based DisplayPort transmit From d72aa5cf045a69d5fd433cde5dd4e113d9558fd1 Mon Sep 17 00:00:00 2001 From: Igor Paunovic Date: Thu, 13 Aug 2026 16:40:19 +0200 Subject: [PATCH 0568/1198] drm/rockchip: rk3066_hdmi: Add missing Kconfig selects rk3066_hdmi.c calls drm_bridge_connector_init(), but ROCKCHIP_RK3066_HDMI selects neither DRM_BRIDGE_CONNECTOR nor DRM_DISPLAY_HELPER, whose module carries the bridge-connector code. A configuration with ROCKCHIP_RK3066_HDMI as the only enabled Rockchip output option fails to link: aarch64-linux-gnu-ld: drivers/gpu/drm/rockchip/rk3066_hdmi.o: in function `rk3066_hdmi_bind': rk3066_hdmi.c:(.text+0x7a4): undefined reference to `drm_bridge_connector_init' aarch64-linux-gnu-ld: drivers/gpu/drm/rockchip/rk3066_hdmi.o: in function `rk3066_hdmi_bridge_atomic_enable': rk3066_hdmi.c:(.text+0xe74): undefined reference to `drm_atomic_helper_connector_hdmi_update_infoframes' Select both, like ROCKCHIP_CDN_DP, ROCKCHIP_LVDS and ROCKCHIP_RGB do. DRM_BRIDGE_CONNECTOR in turn selects DRM_DISPLAY_HDMI_STATE_HELPER, which resolves the second symbol. Fixes: 57d6811e8a6d ("drm/rockchip: rk3066_hdmi: switch to drm bridge") Signed-off-by: Igor Paunovic Signed-off-by: Heiko Stuebner Link: https://patch.msgid.link/20260813144019.12089-3-royalnet026@gmail.com --- drivers/gpu/drm/rockchip/Kconfig | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/rockchip/Kconfig b/drivers/gpu/drm/rockchip/Kconfig index 697c0748eeca..4e58685f58ff 100644 --- a/drivers/gpu/drm/rockchip/Kconfig +++ b/drivers/gpu/drm/rockchip/Kconfig @@ -146,6 +146,8 @@ config ROCKCHIP_RGB config ROCKCHIP_RK3066_HDMI bool "Rockchip specific extensions for RK3066 HDMI" depends on DRM_ROCKCHIP + select DRM_DISPLAY_HELPER + select DRM_BRIDGE_CONNECTOR help This selects support for Rockchip SoC specific extensions for the RK3066 HDMI driver. If you want to enable From 0895a0c0734703be5532f3883c42db95615fd98b Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Tue, 1 Sep 2026 18:47:35 +0800 Subject: [PATCH 0569/1198] bpf: Reject key-less BTF for hash maps map_check_btf() allows a key-less BTF (btf_key_type_id == 0) only for maps that have a ->map_check_btf callback, and leaves the actual decision to that callback. Hash maps used to have no ->map_check_btf, so a key-less BTF was rejected outright. That changed when htab and rhtab gained a ->map_check_btf to register a dtor - htab in commit 1df97a7453ee ("bpf: Register dtor for freeing special fields") and rhtab in commit 6905f8601298 ("bpf: Allow special fields in resizable hashtab"). Neither looks at the key, so a key-less hash map now passes map_check_btf() and gets created. Reading it back through bpffs feeds the key type_id 0 into btf_type_seq_show(); btf_type_by_id() returns the void type, kind_ops[BTF_KIND_UNKN] is NULL, and btf_type_show() dereferences it: RIP: 0010:btf_type_show+0x223/0x2e0 kernel/bpf/btf.c:8232 RSP: 0018:ffffc9000399f868 EFLAGS: 00010206 RAX: dffffc0000000000 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000005 RSI: 0000000000000000 RDI: 0000000000000028 RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000000 R10: ffffc9000399f970 R11: 0000000000000001 R12: ffffffff9b96b140 R13: ffffc9000399f8e0 R14: ffff88803d393c00 R15: 0000000000000003 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000200000000000 CR3: 000000003d213000 CR4: 0000000000352ef0 DR0: 0000000039ae8f55 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Call Trace: btf_type_seq_show_flags+0xca/0x120 kernel/bpf/btf.c:8250 htab_map_seq_show_elem+0x12e/0x350 kernel/bpf/hashtab.c:1669 map_seq_show+0x13d/0x1e0 kernel/bpf/inode.c:293 traverse.part.0.constprop.0+0x107/0x650 fs/seq_file.c:112 traverse fs/seq_file.c:99 [inline] seq_read_iter+0x93f/0x1270 fs/seq_file.c:196 seq_read+0x344/0x4d0 fs/seq_file.c:163 vfs_read+0x1e4/0xb40 fs/read_write.c:572 ksys_pread64 fs/read_write.c:764 [inline] __do_sys_pread64 fs/read_write.c:772 [inline] __se_sys_pread64 fs/read_write.c:769 [inline] __x64_sys_pread64+0x1eb/0x250 fs/read_write.c:769 do_syscall_x64 arch/x86/entry/syscall_64.c:61 [inline] do_syscall_64+0x123/0x790 arch/x86/entry/syscall_64.c:84 entry_SYSCALL_64_after_hwframe+0x77/0x7f Reject a key-less BTF in htab_map_check_btf() and rhtab_map_check_btf(), restoring the previous behavior. Fixes: 1df97a7453ee ("bpf: Register dtor for freeing special fields") Fixes: 6905f8601298 ("bpf: Allow special fields in resizable hashtab") Reported-by: syzbot+37b56485bbbf90ad8489@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/6a8f4e88.27659fcc.2ceef7.0008.GAE@google.com/T/ Signed-off-by: Jiayuan Chen Acked-by: Ihor Solodrai Link: https://lore.kernel.org/r/20260901104924.346187-2-jiayuan.chen@linux.dev Signed-off-by: Alexei Starovoitov --- kernel/bpf/hashtab.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index d8db1cebc193..e89fde188389 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -530,6 +530,9 @@ static int htab_map_check_btf(struct bpf_map *map, const struct btf *btf, { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + if (btf_type_is_void(key_type)) + return -EINVAL; + if (htab_is_prealloc(htab)) return 0; /* @@ -3111,6 +3114,9 @@ static int rhtab_map_check_btf(struct bpf_map *map, const struct btf *btf, { struct bpf_rhtab *rhtab = container_of(map, struct bpf_rhtab, map); + if (btf_type_is_void(key_type)) + return -EINVAL; + return bpf_ma_set_dtor(map, &rhtab->ma, rhtab_mem_dtor); } From 4ea508b9ebd78bce7f212166d2e2cba66b875f08 Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Tue, 1 Sep 2026 18:47:36 +0800 Subject: [PATCH 0570/1198] bpf: Fix NULL-ptr-deref when showing a void BTF type btf_modifier_show() resolves the modifier and then calls btf_type_ops(t)->show() unconditionally. For the void type (type_id 0, BTF_KIND_UNKN) kind_ops[] has no entry, so ->show is NULL. A "const void" (a modifier resolving to void) cannot be a map key or value - map_check_btf() rejects it because void has no size - so the map dump path does not reach it. But bpf_snprintf_btf() takes a type_id straight from the BPF program, and passing such a "const void" from the vmlinux BTF NULL-derefs: KASAN: null-ptr-deref in range [0x0000000000000028-0x000000000000002f] RIP: 0010:btf_modifier_show (kernel/bpf/btf.c:2914) Call Trace: btf_type_show (kernel/bpf/btf.c:8251) btf_type_snprintf_show (kernel/bpf/btf.c:8321) bpf_snprintf_btf (kernel/trace/bpf_trace.c:1047) bpf_prog_test_run_raw_tp (net/bpf/test_run.c:829) __sys_bpf (kernel/bpf/syscall.c:4804) do_syscall_64 (arch/x86/entry/syscall_64.c:94) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:121) Fall back to btf_df_show() when the resolved type has no show op; it emits the "" placeholder already used for kinds like FWD and FUNC. bpf_snprintf_btf() then returns the length as usual. Fixes: c4d0bfb45068 ("bpf: Add bpf_snprintf_btf helper") Signed-off-by: Jiayuan Chen Acked-by: Ihor Solodrai Link: https://lore.kernel.org/r/20260901104924.346187-3-jiayuan.chen@linux.dev Signed-off-by: Alexei Starovoitov --- kernel/bpf/btf.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index da36d4b9d31a..df5f0d059ad1 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -2911,7 +2911,14 @@ static void btf_modifier_show(const struct btf *btf, else t = btf_type_skip_modifiers(btf, type_id, NULL); - btf_type_ops(t)->show(btf, t, type_id, data, bits_offset, show); + /* + * A modifier can resolve to void, which has no show op; print a + * placeholder rather than dereferencing NULL. + */ + if (!btf_type_ops(t)) + btf_df_show(btf, t, type_id, data, bits_offset, show); + else + btf_type_ops(t)->show(btf, t, type_id, data, bits_offset, show); } static void btf_var_show(const struct btf *btf, const struct btf_type *t, From 5403a383f52fc0905703b488f7c3db4b2447dc58 Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Tue, 1 Sep 2026 18:47:37 +0800 Subject: [PATCH 0571/1198] bpf: Fix NULL-ptr-deref in btf_var_show() btf_var_show() calls btf_type_id_resolve() unconditionally, which dereferences btf->resolved_ids. That is NULL for a base BTF - e.g. the vmlinux BTF that bpf_snprintf_btf() renders against - since base BTF is not resolved during parsing. btf_modifier_show() guards this with 'if (btf->resolved_ids)', but btf_var_show() does not. A BPF program that passes the type_id of a BTF_KIND_VAR from the vmlinux BTF to bpf_snprintf_btf() thus NULL-derefs: KASAN: probably user-memory-access in range [0x46638-0x4663f] RIP: 0010:btf_var_show (kernel/bpf/btf.c:2929) Call Trace: btf_type_show (kernel/bpf/btf.c:8259) btf_type_snprintf_show (kernel/bpf/btf.c:8329) bpf_snprintf_btf (kernel/trace/bpf_trace.c:1047) bpf_prog_test_run_raw_tp (net/bpf/test_run.c:829) __sys_bpf (kernel/bpf/syscall.c:4804) do_syscall_64 (arch/x86/entry/syscall_64.c:84) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:121) Resolve the var's type directly with btf_type_skip_modifiers() when resolved_ids is NULL, mirroring btf_modifier_show(). Fixes: c4d0bfb45068 ("bpf: Add bpf_snprintf_btf helper") Signed-off-by: Jiayuan Chen Acked-by: Ihor Solodrai Link: https://lore.kernel.org/r/20260901104924.346187-4-jiayuan.chen@linux.dev Signed-off-by: Alexei Starovoitov --- kernel/bpf/btf.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index df5f0d059ad1..85ae92c920e4 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -2925,7 +2925,15 @@ static void btf_var_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct btf_show *show) { - t = btf_type_id_resolve(btf, &type_id); + /* + * btf_type_id_resolve() dereferences btf->resolved_ids, which is NULL + * for a base BTF (e.g. the vmlinux BTF that bpf_snprintf_btf() uses). + * Resolve the var's type directly in that case. + */ + if (btf->resolved_ids) + t = btf_type_id_resolve(btf, &type_id); + else + t = btf_type_skip_modifiers(btf, t->type, &type_id); btf_type_ops(t)->show(btf, t, type_id, data, bits_offset, show); } From 6265b44f2c3bb2839a306d6088d6e65a58d7e80e Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Tue, 1 Sep 2026 18:47:38 +0800 Subject: [PATCH 0572/1198] selftests/bpf: Add test for key-less BTF hash map Create a hash and an rhash map with btf_key_type_id == 0 and expect bpf_map_create() to fail with -EINVAL; a positive control with a real key type confirms the rejection is about the key-less BTF and not some unrelated failure. Such a map used to be accepted and then NULL-deref in btf_type_show() when dumped through bpffs. Signed-off-by: Jiayuan Chen Link: https://lore.kernel.org/r/20260901104924.346187-5-jiayuan.chen@linux.dev Signed-off-by: Alexei Starovoitov --- .../bpf/prog_tests/btf_map_keyless.c | 59 +++++++++++++++++++ 1 file changed, 59 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/btf_map_keyless.c diff --git a/tools/testing/selftests/bpf/prog_tests/btf_map_keyless.c b/tools/testing/selftests/bpf/prog_tests/btf_map_keyless.c new file mode 100644 index 000000000000..3248bccc3557 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/btf_map_keyless.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include + +/* + * A hash map with a key-less BTF (btf_key_type_id == 0) used to be accepted + * and then NULL-deref in btf_type_show() when dumped through bpffs. A fixed + * kernel rejects it at creation; verify that rejection, with a keyed positive + * control so the -EINVAL is about the missing key type and not some unrelated + * failure. + */ +static void check_keyless(int map_type, __u32 map_flags, int btf_fd, int val_id) +{ + LIBBPF_OPTS(bpf_map_create_opts, opts); + int map_fd; + + opts.map_flags = map_flags; + opts.btf_fd = btf_fd; + opts.btf_value_type_id = val_id; + + /* Positive control: the same map with a real key type is accepted. */ + opts.btf_key_type_id = val_id; + map_fd = bpf_map_create(map_type, "keyed_map", 4, 4, 8, &opts); + if (!ASSERT_GE(map_fd, 0, "keyed create is accepted")) + return; + close(map_fd); + + /* A key-less BTF must be rejected. */ + opts.btf_key_type_id = 0; + map_fd = bpf_map_create(map_type, "keyless_map", 4, 4, 8, &opts); + ASSERT_EQ(map_fd, -EINVAL, "key-less create is rejected"); + if (map_fd >= 0) + close(map_fd); +} + +void test_btf_map_keyless(void) +{ + int btf_fd, val_id; + struct btf *btf; + + btf = btf__new_empty(); + if (!ASSERT_OK_PTR(btf, "btf__new_empty")) + return; + + val_id = btf__add_int(btf, "int", 4, BTF_INT_SIGNED); + if (!ASSERT_GT(val_id, 0, "btf__add_int")) + goto out; + + if (!ASSERT_OK(btf__load_into_kernel(btf), "btf__load_into_kernel")) + goto out; + btf_fd = btf__fd(btf); + + if (test__start_subtest("hash")) + check_keyless(BPF_MAP_TYPE_HASH, 0, btf_fd, val_id); + if (test__start_subtest("rhash")) + check_keyless(BPF_MAP_TYPE_RHASH, BPF_F_NO_PREALLOC, btf_fd, val_id); +out: + btf__free(btf); +} From 1ae6aa61958a0ee6f254cefbee20663ffbadb195 Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Tue, 1 Sep 2026 18:47:39 +0800 Subject: [PATCH 0573/1198] selftests/bpf: Add test for showing a void BTF type Extend the snprintf_btf test with type_ids from the vmlinux BTF that used to NULL-deref in the BTF show path: a "const void", checked to render the "" placeholder, and a BTF_KIND_VAR, checked to resolve and render without error. The program renders from its own buffer and the test picks a VAR whose resolved type fits it, so the render stays in bounds. Signed-off-by: Jiayuan Chen Link: https://lore.kernel.org/r/20260901104924.346187-6-jiayuan.chen@linux.dev Signed-off-by: Alexei Starovoitov --- .../selftests/bpf/prog_tests/snprintf_btf.c | 79 +++++++++++++++++++ .../selftests/bpf/progs/snprintf_btf_void.c | 24 ++++++ 2 files changed, 103 insertions(+) create mode 100644 tools/testing/selftests/bpf/progs/snprintf_btf_void.c diff --git a/tools/testing/selftests/bpf/prog_tests/snprintf_btf.c b/tools/testing/selftests/bpf/prog_tests/snprintf_btf.c index dd41b826be30..edce9c1b54fb 100644 --- a/tools/testing/selftests/bpf/prog_tests/snprintf_btf.c +++ b/tools/testing/selftests/bpf/prog_tests/snprintf_btf.c @@ -1,7 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 #include #include +#include #include "netif_receive_skb.skel.h" +#include "snprintf_btf_void.skel.h" /* Demonstrate that bpf_snprintf_btf succeeds and that various data types * are formatted correctly. @@ -58,3 +60,80 @@ void serial_test_snprintf_btf(void) cleanup: netif_receive_skb__destroy(skel); } + +/* + * bpf_snprintf_btf() renders a type_id taken straight from the vmlinux BTF. + * Two such type_ids used to NULL-deref in the BTF show path: + * - a "const void" (a modifier resolving to void) in btf_modifier_show() + * - a BTF_KIND_VAR in btf_var_show() (base BTF has no resolved_ids) + * A fixed kernel renders both without crashing. + */ +static long run(struct snprintf_btf_void *skel, __u32 type_id) +{ + LIBBPF_OPTS(bpf_test_run_opts, topts); + char ctx[8] = {}; + + skel->bss->type_id = type_id; + topts.ctx_in = ctx; + topts.ctx_size_in = sizeof(ctx); + if (!ASSERT_OK(bpf_prog_test_run_opts(bpf_program__fd(skel->progs.dump_type), + &topts), "test_run")) + return -1; + return skel->bss->ret; +} + +void test_snprintf_btf_void(void) +{ + const struct btf_type *t; + struct snprintf_btf_void *skel; + int i, n, cv = 0, var = 0; + struct btf *btf; + + btf = btf__parse("/sys/kernel/btf/vmlinux", NULL); + if (!btf) { + test__skip(); + return; + } + + skel = snprintf_btf_void__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open_and_load")) + goto out_btf; + + n = btf__type_cnt(btf); + for (i = 1; i < n && !(cv && var); i++) { + t = btf__type_by_id(btf, i); + if (!cv && btf_kind(t) == BTF_KIND_CONST && t->type == 0) + cv = i; + /* Pick a VAR small enough to render from the program's buffer. */ + if (!var && btf_kind(t) == BTF_KIND_VAR) { + long sz = btf__resolve_size(btf, t->type); + + if (sz > 0 && sz <= (long)sizeof(skel->bss->obj)) + var = i; + } + } + + /* "const void" renders the "" placeholder. */ + if (test__start_subtest("const_void")) { + if (cv) { + ASSERT_EQ(run(skel, cv), + sizeof("") - 1, "ret"); + ASSERT_STREQ(skel->bss->out, "", + "placeholder"); + } else { + test__skip(); + } + } + + /* A BTF_KIND_VAR must resolve and render without error. */ + if (test__start_subtest("var")) { + if (var) + ASSERT_GT(run(skel, var), 0, "ret"); + else + test__skip(); + } + + snprintf_btf_void__destroy(skel); +out_btf: + btf__free(btf); +} diff --git a/tools/testing/selftests/bpf/progs/snprintf_btf_void.c b/tools/testing/selftests/bpf/progs/snprintf_btf_void.c new file mode 100644 index 000000000000..44af80fbbb80 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/snprintf_btf_void.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "btf_ptr.h" +#include + +__u32 type_id; +/* A buffer we own to render the selected type from, kept in bounds. */ +char obj[256]; +char out[64]; +long ret; + +SEC("raw_tp/sys_enter") +int dump_type(void *ctx) +{ + struct btf_ptr ptr = { + .ptr = obj, + .type_id = type_id, + .flags = 0, + }; + + ret = bpf_snprintf_btf(out, sizeof(out), &ptr, sizeof(ptr), 0); + return 0; +} + +char _license[] SEC("license") = "GPL"; From 77515ab12e4983e6416f8c35039a3f0c0822ac70 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 3 Sep 2026 16:44:19 +0200 Subject: [PATCH 0574/1198] bpf: Mark signal tracepoint siginfo arguments as scalar The signal_generate and signal_deliver tracepoints declare their info argument as a struct kernel_siginfo pointer. btf_ctx_access() therefore treats it as a trusted pointer for tp_btf programs. Signal delivery also uses SEND_SIG_NOINFO and SEND_SIG_PRIV as special values for this argument. Those values are zero and one respectively, and are not pointers. A tp_btf program can currently dereference either value and fault the kernel. In particular, signal_generate can run from timer interrupt context, turning the fault into a kernel panic. Record both tracepoints in raw_tp_null_args[] and mark argument one as a non-pointer. This preserves scalar access to the cookie while rejecting direct and helper-mediated pointer use. Merely marking it nullable would not suffice because SEND_SIG_PRIV is nonzero. Fixes: 838a10bd2ebf ("bpf: Augment raw_tp arguments with PTR_MAYBE_NULL") Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260903144433.1716731-2-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/btf.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 85ae92c920e4..b5aa802451bd 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6732,6 +6732,9 @@ static const struct bpf_raw_tp_null_args raw_tp_null_args[] = { { "rxrpc_resend", 0x10 }, { "rxrpc_tq", 0x10 }, { "rxrpc_client", 0x1 }, + /* signal */ + { "signal_generate", 0x20 }, + { "signal_deliver", 0x20 }, /* skb */ {"kfree_skb", 0x1000}, /* sunrpc */ From d7719a1736e6be77d0682f7395acd3701949f1fa Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 3 Sep 2026 16:44:20 +0200 Subject: [PATCH 0575/1198] selftests/bpf: Cover signal tracepoint siginfo sentinels Add load-only verifier coverage for the signal_generate and signal_deliver info arguments. The signal_generate case performs a NULL check before dereferencing info, ensuring that merely making it nullable cannot satisfy the test when the nonzero SEND_SIG_PRIV sentinel is used. Both programs load successfully without the verifier fix, contrary to their expected-failure annotations. With the fix, info is a scalar and the attempted dereferences are rejected. Also add success cases showing that plain raw tracepoint and tp_btf programs can continue to read and compare the context word as a scalar. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260903144433.1716731-3-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- .../selftests/bpf/progs/raw_tp_null_fail.c | 36 +++++++++++++++++++ 1 file changed, 36 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c b/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c index 0d58114a4955..7e8842bf9000 100644 --- a/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c +++ b/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c @@ -22,3 +22,39 @@ int test_raw_tp_null_sched_pi_setprio_arg_2(void *ctx) { asm volatile("r1 = *(u64 *)(r1 +8); r1 = *(u64 *)(r1 +0);" ::: __clobber_all); return 0; } + +/* Plain raw tracepoint arguments remain scalar values. */ +SEC("raw_tp/signal_generate") +__success +int test_raw_tp_signal_generate_info_scalar(void *ctx) +{ + asm volatile("r1 = *(u64 *)(r1 +8); if r1 != 1 goto +0;" ::: __clobber_all); + return 0; +} + +/* tp_btf programs may inspect the sentinel as a scalar value. */ +SEC("tp_btf/signal_generate") +__success +int test_tp_btf_signal_generate_info_scalar(void *ctx) +{ + asm volatile("r1 = *(u64 *)(r1 +8); if r1 != 1 goto +0;" ::: __clobber_all); + return 0; +} + +/* SEND_SIG_PRIV is non-NULL, so a NULL check cannot make info safe. */ +SEC("tp_btf/signal_generate") +__failure __msg("R1 invalid mem access 'scalar'") +int test_tp_btf_signal_generate_info_no_deref(void *ctx) +{ + asm volatile("r1 = *(u64 *)(r1 +8); if r1 == 0 goto +1; " + "r1 = *(u32 *)(r1 +0);" ::: __clobber_all); + return 0; +} + +SEC("tp_btf/signal_deliver") +__failure __msg("R1 invalid mem access 'scalar'") +int test_tp_btf_signal_deliver_info_no_deref(void *ctx) +{ + asm volatile("r1 = *(u64 *)(r1 +8); r1 = *(u32 *)(r1 +0);" ::: __clobber_all); + return 0; +} From 266aa4ad0b2e82397cd9045752c9bff03d98eddd Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 3 Sep 2026 16:44:21 +0200 Subject: [PATCH 0576/1198] bpf: Reject tail calls directly from callback frames A tail call from a non-zero frame is modeled as a return from that frame. The verifier makes R0 unknown and calls prepare_func_exit() for the taken branch. When the current frame is a synchronous callback, prepare_func_exit() enforces the callback return-value contract and marks R0 precise. Since the tail-call path synthesized R0 rather than deriving it from an instruction, precision backtracking reaches the callback-calling instruction with R0 still requested and triggers the "callback unexpected regs" verifier bug. A CAP_BPF task can therefore cause a WARN and an -EFAULT BPF_PROG_LOAD. Tail calls reachable from callbacks are already rejected later by check_max_stack_depth(). Reject a tail call made directly by a callback before constructing the inconsistent return state, using the existing diagnostic. Tail calls from ordinary subprograms keep their current behavior. Fixes: e3245f899043 ("bpf: properly verify tail call behavior") Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260903144433.1716731-4-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 7d8ddb1bee00..f540279ff4ab 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -11228,6 +11228,17 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn if (env->cur_state->curframe) { struct bpf_verifier_state *branch; + /* + * A taken tail call is modeled as a return from the current + * frame. A callback frame cannot be left that way because + * prepare_func_exit() would apply its return contract to the + * unknown R0 synthesized below. Stack-depth validation rejects + * this construct anyway. + */ + if (cur_func(env)->in_callback_fn) { + verbose(env, "cannot tail call within callback\n"); + return -EINVAL; + } mark_reg_scratched(env, BPF_REG_0); branch = push_stack(env, env->insn_idx + 1, env->insn_idx, false); if (IS_ERR(branch)) From d9ae3e4c7fb5bfaccc9ca295692d54130862f3b2 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 3 Sep 2026 16:44:22 +0200 Subject: [PATCH 0577/1198] selftests/bpf: Test direct tail calls from callbacks tailcall_callback tests a tail call one static subprogram below a callback. That reaches the later stack-depth rejection, but it does not exercise the tail-call helper while the current frame is itself a callback. Add a callback that calls bpf_tail_call directly and expect the existing "cannot tail call within callback" diagnostic. On an affected kernel, the load instead reaches the "callback unexpected regs" verifier bug, so the expected message is absent and the test fails. The existing ordinary subprogram case remains a success control for legitimate tail calls. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260903144433.1716731-5-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- .../selftests/bpf/progs/tailcall_callback.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/tailcall_callback.c b/tools/testing/selftests/bpf/progs/tailcall_callback.c index c41632cf423b..14fa7a87028e 100644 --- a/tools/testing/selftests/bpf/progs/tailcall_callback.c +++ b/tools/testing/selftests/bpf/progs/tailcall_callback.c @@ -44,6 +44,13 @@ int callback_loop(int index, void **cb_ctx) return ret ? 1 : 0; } +static __noinline +int callback_tail(int index, void **cb_ctx) +{ + bpf_tail_call_static(*cb_ctx, &jmp_table, 0); + return 0; +} + static __noinline int callback_empty(int index, void *data) { @@ -78,4 +85,13 @@ int tailcall_callback_2(struct __sk_buff *skb) return 0; } +/* callback with a direct tail call is rejected without a verifier bug */ +SEC("tc") +__failure __msg("cannot tail call within callback") +int tailcall_callback_3(struct __sk_buff *skb) +{ + bpf_loop(1, callback_tail, &skb, 0); + return 0; +} + char __license[] SEC("license") = "GPL"; From 7b7b8b5960102566bd625ae829d1f330c5b5d104 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 3 Sep 2026 16:44:23 +0200 Subject: [PATCH 0578/1198] bpf: Reject resilient lock operations in rbtree callbacks __bpf_rbtree_add() keeps parent and link pointers live across calls to the program-supplied comparison callback. The verifier therefore requires the root's lock to remain held throughout the callback. The helper path enforces this rule for bpf_spin_lock() and bpf_spin_unlock(), but the resilient lock kfunc argument path does not. Since resilient locks may protect BPF rbtree roots, a callback can release the root lock and let another CPU remove and free the node referenced by the in-progress tree walk. The walk then resumes using freed pointers. Reject resilient lock kfuncs in an rbtree comparison callback, matching the existing policy for the spin lock helpers. Resilient-lock-protected trees remain valid when their comparison callbacks leave lock state alone. Fixes: 0de2046137f9 ("bpf: Implement verifier support for rqspinlock") Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260903144433.1716731-6-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f540279ff4ab..32d31fa67036 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -13241,6 +13241,11 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_call_arg_me { int flags = PROCESS_RES_LOCK; + if (in_rbtree_lock_required_cb(env)) { + verbose(env, "can't res_spin_{lock,unlock} in rbtree cb\n"); + return -EACCES; + } + if (reg->type != PTR_TO_MAP_VALUE && reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { verbose(env, "%s doesn't point to map value or allocated object\n", reg_arg_name(env, argno)); From 08b4dc83d981bf9136d37aaa4f5cd021ba0d8f2b Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 3 Sep 2026 16:44:24 +0200 Subject: [PATCH 0579/1198] selftests/bpf: Reject resilient unlock in rbtree callback Add a load-only verifier regression for a resilient lock operation in an rbtree comparison callback. The program holds the rbtree's regular spin lock and a separate resilient lock, then releases the resilient lock from the callback. This isolates the missing kfunc policy check without running a concurrent tree mutation. Release the resilient lock before the regular lock on the outer fall-through. The broken verifier therefore accepts the balanced program, while the fixed verifier rejects the resilient unlock specifically while verifying the callback. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260903144433.1716731-7-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- .../testing/selftests/bpf/progs/rbtree_fail.c | 29 +++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/rbtree_fail.c b/tools/testing/selftests/bpf/progs/rbtree_fail.c index 555379952dcc..803419a47c62 100644 --- a/tools/testing/selftests/bpf/progs/rbtree_fail.c +++ b/tools/testing/selftests/bpf/progs/rbtree_fail.c @@ -16,6 +16,7 @@ struct node_data { private(A) struct bpf_spin_lock glock; private(A) struct bpf_rb_root groot __contains(node_data, node); private(A) struct bpf_rb_root groot2 __contains(node_data, node); +private(B) struct bpf_res_spin_lock res_glock; static bool less(struct bpf_rb_node *a, const struct bpf_rb_node *b) { @@ -265,6 +266,12 @@ static bool less__bad_fn_call_first_unlock_after(struct bpf_rb_node *a, const st return node_a->key < node_b->key; } +static bool less__bad_res_spin_unlock(struct bpf_rb_node *a, const struct bpf_rb_node *b) +{ + bpf_res_spin_unlock(&res_glock); + return false; +} + static __always_inline long add_with_cb(bool (cb)(struct bpf_rb_node *a, const struct bpf_rb_node *b)) { @@ -301,4 +308,26 @@ long rbtree_api_add_bad_cb_bad_fn_call_first_unlock_after(void *ctx) return add_with_cb(less__bad_fn_call_first_unlock_after); } +SEC("?tc") +__failure __msg("can't res_spin_{lock,unlock} in rbtree cb") +long rbtree_api_add_bad_cb_res_spin_unlock(void *ctx) +{ + struct node_data *n; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + + bpf_spin_lock(&glock); + if (bpf_res_spin_lock(&res_glock)) { + bpf_spin_unlock(&glock); + bpf_obj_drop(n); + return 1; + } + bpf_rbtree_add(&groot, &n->node, less__bad_res_spin_unlock); + bpf_res_spin_unlock(&res_glock); + bpf_spin_unlock(&glock); + return 0; +} + char _license[] SEC("license") = "GPL"; From a453d6e3b8e8e1a321c8744d6189d763af9287d0 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 3 Sep 2026 16:44:25 +0200 Subject: [PATCH 0580/1198] bpf: Mark sched_process_wait argument as nullable do_wait() passes wo->wo_pid to the sched_process_wait tracepoint. kernel_wait4() leaves wo_pid NULL for wait4(-1), and kernel_waitid_prepare() does likewise for waitid(P_ALL). btf_ctx_access() currently types argument 0 as PTR_TO_BTF_ID | PTR_TRUSTED. Without PTR_MAYBE_NULL, the verifier accepts an unchecked dereference. Trusted pointer loads have no fault protection, so a wait for any child can then cause a NULL pointer dereference in JITed BPF code. Add sched_process_wait to raw_tp_null_args[] with argument 0 marked nullable. The verifier rejects an unchecked dereference while preserving access after the program checks the pointer for NULL. Fixes: 838a10bd2ebf ("bpf: Augment raw_tp arguments with PTR_MAYBE_NULL") Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260903144433.1716731-8-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/btf.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index b5aa802451bd..5d93fd82e764 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6672,6 +6672,10 @@ struct bpf_raw_tp_null_args { static const struct bpf_raw_tp_null_args raw_tp_null_args[] = { /* sched */ { "sched_pi_setprio", 0x10 }, + /* + * do_wait() passes NULL for wait4(-1) and waitid(P_ALL). + */ + { "sched_process_wait", 0x1 }, /* ... from sched_numa_pair_template event class */ { "sched_stick_numa", 0x100 }, { "sched_swap_numa", 0x100 }, From c1992ba73b0339166906eb2224494e04052a8150 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 3 Sep 2026 16:44:26 +0200 Subject: [PATCH 0581/1198] selftests/bpf: Test sched_process_wait nullable argument Add a load-time verifier test that dereferences argument 0 of the sched_process_wait tp_btf program without checking it. The test expects the nullable-pointer diagnostic, so it is accepted unexpectedly before the fix and rejected as expected after it. Add a successful control that checks the argument for NULL before the dereference. This ensures the nullable marking preserves legitimate access to the pid when the tracepoint supplies one. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260903144433.1716731-9-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- .../selftests/bpf/progs/raw_tp_null_fail.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c b/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c index 7e8842bf9000..725d73c9ffe1 100644 --- a/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c +++ b/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c @@ -58,3 +58,20 @@ int test_tp_btf_signal_deliver_info_no_deref(void *ctx) asm volatile("r1 = *(u64 *)(r1 +8); r1 = *(u32 *)(r1 +0);" ::: __clobber_all); return 0; } + +SEC("tp_btf/sched_process_wait") +__failure __msg("R1 invalid mem access 'trusted_ptr_or_null_'") +int test_raw_tp_null_sched_process_wait_arg_1(void *ctx) +{ + asm volatile("r1 = *(u64 *)(r1 +0); r1 = *(u32 *)(r1 +0);" ::: __clobber_all); + return 0; +} + +SEC("tp_btf/sched_process_wait") +__success +int test_raw_tp_null_sched_process_wait_arg_1_checked(void *ctx) +{ + asm volatile("r1 = *(u64 *)(r1 +0); if r1 == 0 goto +1; " + "r1 = *(u32 *)(r1 +0);" ::: __clobber_all); + return 0; +} From d05524794240b52fdc3b6c1220dd05505715824d Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 3 Sep 2026 16:44:27 +0200 Subject: [PATCH 0582/1198] bpf: Mark syscall helpers as sleepable bpf_sys_bpf() executes the bpf(2) syscall body, which can take mutexes, allocate with GFP_KERNEL, and wait for an RCU grace period. bpf_sys_close() reaches close_fd() and filp_close(), which can sleep as well. Both helpers are limited to BPF_PROG_TYPE_SYSCALL, whose main program is sleepable. That does not make every callback sleepable: a syscall program can register a bpf_timer callback, and the verifier checks that callback in a non-sleepable context while retaining the syscall helper set. Without .might_sleep on the prototypes, such a callback can invoke bpf_sys_bpf() from hrtimer softirq context and trigger a scheduling-while-atomic failure. bpf_sys_close() is exposed through the same missing context check. Set .might_sleep on both prototypes so the existing helper-context check rejects them from timer callbacks and other atomic regions. Calls from the sleepable main body remain valid. Fixes: 79a7f8bdb159 ("bpf: Introduce bpf_sys_bpf() helper and program type.") Fixes: 3abea089246f ("bpf: Add bpf_sys_close() helper.") Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260903144433.1716731-10-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/syscall.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 6874ba1424af..c7bc9ba9b331 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -6568,6 +6568,7 @@ EXPORT_SYMBOL_NS(kern_sys_bpf, "BPF_INTERNAL"); static const struct bpf_func_proto bpf_sys_bpf_proto = { .func = bpf_sys_bpf, .gpl_only = false, + .might_sleep = true, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, @@ -6593,6 +6594,7 @@ BPF_CALL_1(bpf_sys_close, u32, fd) static const struct bpf_func_proto bpf_sys_close_proto = { .func = bpf_sys_close, .gpl_only = false, + .might_sleep = true, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, }; From 26a3a510cd3433e15f37ea1d5a6f2c17a0170316 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 3 Sep 2026 16:44:28 +0200 Subject: [PATCH 0583/1198] selftests/bpf: Check syscall helpers in timer callbacks A BPF_PROG_TYPE_SYSCALL program is sleepable, but its bpf_timer callbacks run in a non-sleepable hrtimer softirq context. Add verifier cases that call bpf_sys_bpf() and bpf_sys_close() from timer callbacks. Without the syscall helper prototype annotations these programs load, so their failure expectations expose the bug. Also add successful controls that call each helper from the syscall program main body, ensuring that the intended sleepable use remains accepted. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260903144433.1716731-11-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- .../bpf/progs/verifier_async_cb_context.c | 64 +++++++++++++++++++ 1 file changed, 64 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c b/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c index 6bf95550a024..a7c84d3fa4c7 100644 --- a/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c +++ b/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c @@ -62,6 +62,70 @@ int timer_sleepable_prog(void *ctx) return 0; } +static int timer_sys_bpf_cb(void *map, int *key, struct bpf_timer *timer) +{ + __u64 attr = 0; + + bpf_sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr)); + return 0; +} + +SEC("syscall") +__failure __msg("sleepable helper bpf_sys_bpf#{{[0-9]+}} in non-sleepable prog") +int timer_sys_bpf_prog(void *ctx) +{ + struct timer_elem *val; + int key = 0; + + val = bpf_map_lookup_elem(&timer_map, &key); + if (!val) + return 0; + + bpf_timer_init(&val->t, &timer_map, 0); + bpf_timer_set_callback(&val->t, timer_sys_bpf_cb); + return 0; +} + +static int timer_sys_close_cb(void *map, int *key, struct bpf_timer *timer) +{ + bpf_sys_close(0); + return 0; +} + +SEC("syscall") +__failure __msg("sleepable helper bpf_sys_close#{{[0-9]+}} in non-sleepable prog") +int timer_sys_close_prog(void *ctx) +{ + struct timer_elem *val; + int key = 0; + + val = bpf_map_lookup_elem(&timer_map, &key); + if (!val) + return 0; + + bpf_timer_init(&val->t, &timer_map, 0); + bpf_timer_set_callback(&val->t, timer_sys_close_cb); + return 0; +} + +SEC("syscall") +__success +int syscall_sys_bpf_prog(void *ctx) +{ + __u64 attr = 0; + + bpf_sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr)); + return 0; +} + +SEC("syscall") +__success +int syscall_sys_close_prog(void *ctx) +{ + bpf_sys_close(0); + return 0; +} + /* Workqueue tests */ struct wq_elem { From b3c8d4672f7a8735e2884cefcd89286268e88b2e Mon Sep 17 00:00:00 2001 From: "Rob Herring (Arm)" Date: Thu, 27 Aug 2026 15:33:00 -0500 Subject: [PATCH 0584/1198] accel: ethosu: Fix ethosu_job_open() return value A WARN_ON() returns a 0 or 1, not the original negative errno. Just drop the WARN_ON() as the FD open will pass the return code to userspace and there's only one possible source of the error (drm_sched_entity_init()). Fixes: 5a5e9c0228e6 ("accel: Add Arm Ethos-U NPU driver") Cc: stable@vger.kernel.org Reviewed-by: Frank Li Link: https://patch.msgid.link/20260827-ethosu-fixes-v1-1-346f9ea8791c@kernel.org Signed-off-by: Rob Herring (Arm) --- drivers/accel/ethosu/ethosu_job.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/accel/ethosu/ethosu_job.c b/drivers/accel/ethosu/ethosu_job.c index 4ced44a65f23..6aa305b1dce3 100644 --- a/drivers/accel/ethosu/ethosu_job.c +++ b/drivers/accel/ethosu/ethosu_job.c @@ -374,12 +374,10 @@ int ethosu_job_open(struct ethosu_file_priv *ethosu_priv) { struct ethosu_device *dev = ethosu_priv->edev; struct drm_gpu_scheduler *sched = &dev->sched; - int ret; - ret = drm_sched_entity_init(ðosu_priv->sched_entity, - DRM_SCHED_PRIORITY_NORMAL, - &sched, 1, NULL); - return WARN_ON(ret); + return drm_sched_entity_init(ðosu_priv->sched_entity, + DRM_SCHED_PRIORITY_NORMAL, + &sched, 1, NULL); } void ethosu_job_close(struct ethosu_file_priv *ethosu_priv) From 2cbd3691565f7c86c0eaca305f5beb3435b4ba70 Mon Sep 17 00:00:00 2001 From: "Rob Herring (Arm)" Date: Thu, 27 Aug 2026 15:33:01 -0500 Subject: [PATCH 0585/1198] accel: ethosu: Drop IRQF_SHARED flag The IRQF_SHARED flag doesn't work with runtime-pm as the IRQ handler could run without resuming the device. This could also be fixed with runtime-pm calls in the IRQ handler, but there is no known need for a shared IRQ. Fixes: 5a5e9c0228e6 ("accel: Add Arm Ethos-U NPU driver") Cc: stable@vger.kernel.org Reviewed-by: Frank Li Link: https://patch.msgid.link/20260827-ethosu-fixes-v1-2-346f9ea8791c@kernel.org Signed-off-by: Rob Herring (Arm) --- drivers/accel/ethosu/ethosu_job.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/accel/ethosu/ethosu_job.c b/drivers/accel/ethosu/ethosu_job.c index 6aa305b1dce3..4532ff13edb6 100644 --- a/drivers/accel/ethosu/ethosu_job.c +++ b/drivers/accel/ethosu/ethosu_job.c @@ -343,7 +343,7 @@ int ethosu_job_init(struct ethosu_device *edev) ret = devm_request_threaded_irq(dev, edev->irq, ethosu_job_irq_handler, ethosu_job_irq_handler_thread, - IRQF_SHARED, KBUILD_MODNAME, + 0, KBUILD_MODNAME, edev); if (ret) { dev_err(dev, "failed to request irq\n"); From eb3a41fd35e352fba387c4320a1fa0352f3e551c Mon Sep 17 00:00:00 2001 From: "Rob Herring (Arm)" Date: Thu, 27 Aug 2026 15:33:02 -0500 Subject: [PATCH 0586/1198] accel: ethosu: Ensure cmd stream ends with a stop op While the QSIZE register setting should prevent an out of bounds access of the command stream, it is not clear whether the h/w generates an interrupt in this case as is required (to prevent a timeout). As a stop op is expected end of the command stream, let's just ensure it is present. A stop op in the middle of the command stream also makes no sense. Fixes: 5a5e9c0228e6 ("accel: Add Arm Ethos-U NPU driver") Cc: stable@vger.kernel.org Reviewed-by: Frank Li Link: https://patch.msgid.link/20260827-ethosu-fixes-v1-3-346f9ea8791c@kernel.org Signed-off-by: Rob Herring (Arm) --- drivers/accel/ethosu/ethosu_device.h | 1 + drivers/accel/ethosu/ethosu_gem.c | 9 +++++++++ 2 files changed, 10 insertions(+) diff --git a/drivers/accel/ethosu/ethosu_device.h b/drivers/accel/ethosu/ethosu_device.h index d4458eac8447..1eca8590e68d 100644 --- a/drivers/accel/ethosu/ethosu_device.h +++ b/drivers/accel/ethosu/ethosu_device.h @@ -87,6 +87,7 @@ struct gen_pool; #define PMU_EV_TYPE_IDLE 0x20 enum ethosu_cmds { + NPU_OP_STOP = 0x0, NPU_OP_CONV = 0x2, NPU_OP_DEPTHWISE = 0x3, NPU_OP_POOL = 0x5, diff --git a/drivers/accel/ethosu/ethosu_gem.c b/drivers/accel/ethosu/ethosu_gem.c index fa37a190e9ff..9afe2549ec84 100644 --- a/drivers/accel/ethosu/ethosu_gem.c +++ b/drivers/accel/ethosu/ethosu_gem.c @@ -390,6 +390,7 @@ static int ethosu_gem_cmdstream_copy_and_validate(struct drm_device *ddev, struct ethosu_validated_cmdstream_info __free(kfree) *info = kzalloc_obj(*info); struct ethosu_device *edev = to_ethosu_device(ddev); u32 *bocmds = bo->base.vaddr; + bool ends_with_stop = false; struct cmd_state st; int i, ret; @@ -426,6 +427,11 @@ static int ethosu_gem_cmdstream_copy_and_validate(struct drm_device *ddev, } switch (cmd) { + case NPU_OP_STOP: + if (i != size / 4 - 1) + return -EINVAL; + ends_with_stop = true; + break; case NPU_OP_DMA_START: srclen = dma_length(info, &st.dma, &st.dma.src); dstlen = dma_length(info, &st.dma, &st.dma.dst); @@ -688,6 +694,9 @@ static int ethosu_gem_cmdstream_copy_and_validate(struct drm_device *ddev, } } + if (!ends_with_stop) + return -EINVAL; + for (i = 0; i < NPU_BASEP_REGION_MAX; i++) { if (!info->region_size[i]) continue; From f5376d7e0fb703876199d3b6f9f97e128fa2f8a4 Mon Sep 17 00:00:00 2001 From: "Rob Herring (Arm)" Date: Thu, 27 Aug 2026 15:33:03 -0500 Subject: [PATCH 0587/1198] accel: ethosu: Ensure SRAM size is 0 on mapping failure On a mapping failure of the SRAM, the SRAM size is left as non-zero. The probe will succeed as the error return is not checked since having SRAM is not a hard requirement. The non-zero size allows jobs to access SRAM which is left pointing to physical base address 0x0. Fixes: 5a5e9c0228e6 ("accel: Add Arm Ethos-U NPU driver") Cc: stable@vger.kernel.org Reviewed-by: Frank Li Link: https://patch.msgid.link/20260827-ethosu-fixes-v1-4-346f9ea8791c@kernel.org Signed-off-by: Rob Herring (Arm) --- drivers/accel/ethosu/ethosu_drv.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/accel/ethosu/ethosu_drv.c b/drivers/accel/ethosu/ethosu_drv.c index 1cf284e7f300..8108622de258 100644 --- a/drivers/accel/ethosu/ethosu_drv.c +++ b/drivers/accel/ethosu/ethosu_drv.c @@ -281,8 +281,6 @@ static int ethosu_device_suspend(struct device *dev) static int ethosu_sram_init(struct ethosu_device *ethosudev) { - ethosudev->npu_info.sram_size = 0; - ethosudev->srampool = of_gen_pool_get(ethosudev->base.dev->of_node, "sram", 0); if (!ethosudev->srampool) return 0; @@ -293,6 +291,7 @@ static int ethosu_sram_init(struct ethosu_device *ethosudev) ethosudev->npu_info.sram_size, ðosudev->sramphys); if (!ethosudev->sram) { + ethosudev->npu_info.sram_size = 0; dev_err(ethosudev->base.dev, "failed to allocate from SRAM pool\n"); return -ENOMEM; } From 2b39d680c9e0fb4d625f2916980977622e84248c Mon Sep 17 00:00:00 2001 From: "Rob Herring (Arm)" Date: Thu, 27 Aug 2026 15:33:04 -0500 Subject: [PATCH 0588/1198] accel: ethosu: Ensure SRAM region size matches job It is possible for userspace to set the job SRAM size to 0, but then still have SRAM accesses in the command stream. When the job SRAM size is 0, setting the region base register is skipped and a stale base address from a prior job is used. Check the region size against the job's SRAM size instead of just the size of the SRAM. The job's SRAM size was already checked against the total SRAM size. Fixes: 9cff90774872 ("accel: ethosu: Validate SRAM size on submit") Cc: stable@vger.kernel.org Reviewed-by: Frank Li Link: https://patch.msgid.link/20260827-ethosu-fixes-v1-5-346f9ea8791c@kernel.org Signed-off-by: Rob Herring (Arm) --- drivers/accel/ethosu/ethosu_job.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/accel/ethosu/ethosu_job.c b/drivers/accel/ethosu/ethosu_job.c index 4532ff13edb6..8dce74db0cb4 100644 --- a/drivers/accel/ethosu/ethosu_job.c +++ b/drivers/accel/ethosu/ethosu_job.c @@ -447,13 +447,13 @@ static int ethosu_ioctl_submit_job(struct drm_device *dev, struct drm_file *file if (!cmd_info->region_size[i]) continue; if (i == ETHOSU_SRAM_REGION) { - if (cmd_info->region_size[i] <= edev->npu_info.sram_size) + if (cmd_info->region_size[i] <= ejob->sram_size) continue; dev_err(dev->dev, - "cmd stream region %d size greater than SRAM size (%llu > %u)\n", + "cmd stream region %d size greater than job SRAM size (%llu > %u)\n", i, cmd_info->region_size[i], - edev->npu_info.sram_size); + ejob->sram_size); ret = -EINVAL; goto out_cleanup_job; } From 70ded7a57443f41075625f29b9eb88dca154decb Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 27 Aug 2026 09:20:56 +0200 Subject: [PATCH 0589/1198] MAINTAINERS: cover all of RAID While commit 3626738bc7147d52 ("raid6: move to lib/raid/") handled the move of RAID6, it didn't take into account there was already more RAID code under lib/raid/, as XOR got moved over in commit 9e229025e2474115 ("xor: move to lib/raid/") before. Link: https://lore.kernel.org/7a2e5de234cc0286e3fe9bc11b810433775f2280.1787815121.git.geert+renesas@glider.be Signed-off-by: Geert Uytterhoeven Reported-by: Andrew Morton Closes: https://lore.kernel.org/20260826205058.a6ff019d0584f75c7f50430b@linux-foundation.org Cc: Christoph Hellwig Cc: Song Liu Cc: Yu Kuai Cc: Li Nan Cc: Xiao Ni Signed-off-by: Andrew Morton --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 85cc77fe75b7..90ce4def17d9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -25405,7 +25405,7 @@ F: drivers/md/md* F: drivers/md/raid* F: include/linux/raid/ F: include/uapi/linux/raid/ -F: lib/raid/raid6/ +F: lib/raid/ SOLIDRUN CLEARFOG SUPPORT M: Russell King From ed334880e5e6855820855d76f594d973747cbf8a Mon Sep 17 00:00:00 2001 From: "Kiryl Shutsemau (Meta)" Date: Thu, 27 Aug 2026 11:34:35 +0100 Subject: [PATCH 0590/1198] MAINTAINERS: add Kiryl as a THP reviewer I have been working on transparent hugepages since 2012, starting with the huge zero page and file-backed THP. A lot of the code that causes pain now traces back to me. It is only fair if I share the review load for THP. Add myself to the reviewer list so get_maintainer.pl puts me on Cc: as well. It is also my commitment to be more active in reviewing this code. Link: https://lore.kernel.org/20260827103435.1371882-1-kas@kernel.org Signed-off-by: Kiryl Shutsemau (Meta) Acked-by: David Hildenbrand (Arm) Acked-by: Lorenzo Stoakes (ARM) Reviewed-by: Barry Song Acked-by: Zi Yan Reviewed-by: Lance Yang Acked-by: Usama Arif Acked-by: Baolin Wang Acked-by: SJ Park Cc: Dev Jain Cc: Liam R. Howlett Cc: Ryan Roberts Signed-off-by: Andrew Morton --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 90ce4def17d9..2133aec4a200 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17421,6 +17421,7 @@ R: Dev Jain R: Barry Song R: Lance Yang R: Usama Arif +R: Kiryl Shutsemau L: linux-mm@kvack.org S: Maintained W: http://www.linux-mm.org From 35b0fb391b0df57383bc15985bb769f4555c97ba Mon Sep 17 00:00:00 2001 From: "Lorenzo Stoakes (ARM)" Date: Tue, 25 Aug 2026 08:55:26 +0100 Subject: [PATCH 0591/1198] mm/mremap: reset unfaulted VMA page offset for MREMAP_DONTUNMAP Uniquely an mremap() invocation using the MREMAP_DONTUNMAP flag can reset a faulted VMA into an unfaulted one. It does so after the page tables have been moved to the copied VMA with MREMAP_DONTUNMAP leaving the old VMA in place which is naturally unfaulted as the page tables it had are no longer present. However, in doing so, it violates the invariant that the anonymous page offset of an unfaulted VMA is vma->vm_start >> PAGE_SHIFT. This is because a VMA may have been faulted in, mremap()'d (causing a delta between its page offset and vma->vm_start >> PAGE_SHIFT), and then mremap()'d again with MREMAP_DONTUNMAP resulting in the unfaulting. This condition is a violation of a fundamental assumption in mm, but now also triggers an assert in assert_sane_pgoff() which explicitly checks for this condition. Correct it by resetting the VMA's page offset at the point of completing the MREMAP_DONTUNMAP operation. Link: https://lore.kernel.org/20260825-fix-mremap-dontunmap-pgoff-v1-1-39a40b2c98b3@kernel.org Fixes: 1583aa278f5f ("mm: mremap: unlink anon_vmas when mremap with MREMAP_DONTUNMAP success") Signed-off-by: Lorenzo Stoakes (ARM) Reported-by: syzbot+f12658786a4153df5113@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/6a87853b.ae6ddae5.3da009.0023.GAE@google.com/ Tested-by: syzbot+f12658786a4153df5113@syzkaller.appspotmail.com Acked-by: Vlastimil Babka (SUSE) Reviewed-by: Kunwu Chan Reviewed-by: Pedro Falcato Cc: Jann Horn Cc: Liam R. Howlett Cc: Li Xinhai Cc: Signed-off-by: Andrew Morton --- mm/mremap.c | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) diff --git a/mm/mremap.c b/mm/mremap.c index e8df5cdb0ac9..2b4b523a86b8 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -1331,18 +1331,30 @@ static void dontunmap_complete(struct vma_remap_struct *vrm, { unsigned long start = vrm->addr; unsigned long end = vrm->addr + vrm->old_len; - unsigned long old_start = vrm->vma->vm_start; - unsigned long old_end = vrm->vma->vm_end; + struct vm_area_struct *vma = vrm->vma; + unsigned long old_start = vma->vm_start; + unsigned long old_end = vma->vm_end; /* We always clear VMA_LOCKED[ONFAULT]_BIT on the old VMA. */ - vma_clear_flags_mask(vrm->vma, VMA_LOCKED_MASK); + vma_clear_flags_mask(vma, VMA_LOCKED_MASK); /* * anon_vma links of the old vma is no longer needed after its page * table has been moved. */ - if (new_vma != vrm->vma && start == old_start && end == old_end) - unlink_anon_vmas(vrm->vma); + if (new_vma != vma && start == old_start && end == old_end) { + const pgoff_t pgoff_unfaulted = vma->vm_start >> PAGE_SHIFT; + + unlink_anon_vmas(vma); + /* + * The VMA is now unfaulted and it is an invariant that + * unfaulted anonymous VMAs have page offset equal to + * vma->vm_start >> PAGE_SHIFT. + */ + vma_set_anon_pgoff(vma, pgoff_unfaulted); + if (vma_is_anonymous(vma) && !vma->vm_file) + vma_set_pgoff(vma, pgoff_unfaulted); + } /* Because we won't unmap we don't need to touch locked_vm. */ } From 97d34aa65c29cca85e3e9050f4c936389b38a054 Mon Sep 17 00:00:00 2001 From: "Lorenzo Stoakes (ARM)" Date: Wed, 26 Aug 2026 17:30:35 +0100 Subject: [PATCH 0592/1198] mm/secretmem: properly account locked pages secretmem accounts folios by treating memory as if it were mlock()'d and thus limited by the RLIMIT_MEMLOCK limit. However the folios are unevictable and remain so until the inode is evicted, eliminating usual mlock() semantics - mapping folios then unmapping them does not clear their unevictable state, since it depends on AS_UNEVICTABLE, not PG_mlocked. A user can therefore easily work around the RLIMIT_MEMLOCK limit - simply map then unmap and VmLck no longer counts the secretmem range. Worse, folios are not accounted in the process's RSS, meaning the OOM killer won't know to kill the process. Repeatedly mapping/unmapping (or forking) can then result in the consumption of all available system memory with unevictable folios and cause system instability. A secretmem fd can be passed between processes and over fork so a per-process limit simply does not make sense, so follow the precedent set by io_uring, perf, skbuff, iommufd and xdp by tracking the number of locked pages in user_struct->locked_vm. Since the scope tracked is actually inode lifetime, the RLIMIT_MEMLOCK applies per-user not per-process, so it doesn't make sense to bypass for users with CAP_IPC_LOCK, therefore remove this bypass. There is simply no reason to carry on marking the mapping as mlock()'d since it's misleading and the lifecycle is now correctly handled, so remove this too. Note that secretmem does not support any form of truncation (including hole punching) and the folios are unreclaimable, so the folios need only be accounted on fault and unaccounted on inode destruction. __secretmem_account_pages() is more or less a duplicate of the code that io_uring etc. use, but since this is a bug fix that needs backporting, defer any de-duplication efforts to a follow-up. test_mlock_limit() asserts mlock_future_ok() on mmap(), however this has been removed, so remove the test altogether for the fix. A new test will be sent separately for upstream. Link: https://lore.kernel.org/20260826-secretmem-accounting-v3-1-94cb04399510@kernel.org Fixes: 1507f51255c9 ("mm: introduce memfd_secret system call to create "secret" memory areas") Signed-off-by: Lorenzo Stoakes (ARM) Reported-by: Daehyeon Ko <4ncienth@gmail.com> Closes: https://lore.kernel.org/linux-mm/20260813225328.2010303-1-4ncienth@gmail.com/ Reviewed-by: Mike Rapoport (Microsoft) Acked-by: David Hildenbrand (Arm) Tested-by: Daehyeon Ko <4ncienth@gmail.com> Cc: Alexei Starovoitov Cc: David Hildenbrand Cc: David S. Miller Cc: Hagen Paul Pfeifer Cc: Jakub Kacinski Cc: James Bottomley Cc: Jesper Dangaard Brouer Cc: John Fastabend Cc: Liam R. Howlett Cc: Michal Hocko Cc: Stanislav Fomichev Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton --- include/linux/sched/user.h | 3 +- mm/secretmem.c | 116 ++++++++++++++++++++-- tools/testing/selftests/mm/memfd_secret.c | 30 +----- 3 files changed, 110 insertions(+), 39 deletions(-) diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h index 4cc52698e214..8d7e5521f7cd 100644 --- a/include/linux/sched/user.h +++ b/include/linux/sched/user.h @@ -25,7 +25,8 @@ struct user_struct { #if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) || \ defined(CONFIG_NET) || defined(CONFIG_IO_URING) || \ - defined(CONFIG_VFIO_PCI_ZDEV_KVM) || IS_ENABLED(CONFIG_IOMMUFD) + defined(CONFIG_VFIO_PCI_ZDEV_KVM) || IS_ENABLED(CONFIG_IOMMUFD) || \ + defined(CONFIG_SECRETMEM) atomic_long_t locked_vm; #endif #ifdef CONFIG_WATCH_QUEUE diff --git a/mm/secretmem.c b/mm/secretmem.c index d29865075b6e..384f5cfc457f 100644 --- a/mm/secretmem.c +++ b/mm/secretmem.c @@ -18,6 +18,8 @@ #include #include #include +#include +#include #include @@ -47,10 +49,69 @@ bool secretmem_active(void) return !!atomic_read(&secretmem_users); } +struct secretmem_inode_state { + struct user_struct *user; + atomic_long_t nr_pages_accounted; +}; + +static bool __secretmem_account_pages(struct user_struct *user, + unsigned long nr_pages) +{ + unsigned long page_limit, cur_pages, new_pages; + + if (!nr_pages) + return true; + + page_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + + cur_pages = atomic_long_read(&user->locked_vm); + do { + new_pages = cur_pages + nr_pages; + if (new_pages > page_limit) + return false; + } while (!atomic_long_try_cmpxchg(&user->locked_vm, + &cur_pages, new_pages)); + return true; +} + +static bool secretmem_account_folio(struct secretmem_inode_state *state, + const struct folio *folio) +{ + const unsigned long nr_pages = folio_nr_pages(folio); + + if (!__secretmem_account_pages(state->user, nr_pages)) + return false; + + atomic_long_add(nr_pages, &state->nr_pages_accounted); + return true; +} + +static void __secretmem_unaccount_pages(struct secretmem_inode_state *state, + unsigned long nr_pages) +{ + atomic_long_sub(nr_pages, &state->user->locked_vm); + atomic_long_sub(nr_pages, &state->nr_pages_accounted); +} + +static void secretmem_unaccount_folio(struct secretmem_inode_state *state, + struct folio *folio) +{ + __secretmem_unaccount_pages(state, folio_nr_pages(folio)); +} + +static void secretmem_unaccount_all_folios(struct secretmem_inode_state *state) +{ + const unsigned long nr_pages_accounted = + atomic_long_read(&state->nr_pages_accounted); + + __secretmem_unaccount_pages(state, nr_pages_accounted); +} + static vm_fault_t secretmem_fault(struct vm_fault *vmf) { struct address_space *mapping = vmf->vma->vm_file->f_mapping; struct inode *inode = file_inode(vmf->vma->vm_file); + struct secretmem_inode_state *state = inode->i_private; pgoff_t offset = vmf->pgoff; gfp_t gfp = vmf->gfp_mask; unsigned long addr; @@ -72,8 +133,15 @@ static vm_fault_t secretmem_fault(struct vm_fault *vmf) goto out; } + if (!secretmem_account_folio(state, folio)) { + folio_put(folio); + ret = VM_FAULT_SIGBUS; + goto out; + } + err = set_direct_map_invalid_noflush(folio_page(folio, 0)); if (err) { + secretmem_unaccount_folio(state, folio); folio_put(folio); ret = vmf_error(err); goto out; @@ -82,6 +150,7 @@ static vm_fault_t secretmem_fault(struct vm_fault *vmf) __folio_mark_uptodate(folio); err = filemap_add_folio(mapping, folio, offset, gfp); if (unlikely(err)) { + secretmem_unaccount_folio(state, folio); /* * If a split of large page was required, it * already happened when we marked the page invalid @@ -112,22 +181,30 @@ static const struct vm_operations_struct secretmem_vm_ops = { .fault = secretmem_fault, }; +static void secretmem_destroy_inode_priv(struct inode *inode) +{ + struct secretmem_inode_state *state = inode->i_private; + + secretmem_unaccount_all_folios(state); + free_uid(state->user); + kfree(state); + inode->i_private = NULL; +} + static int secretmem_release(struct inode *inode, struct file *file) { atomic_dec(&secretmem_users); + secretmem_destroy_inode_priv(inode); + return 0; } static int secretmem_mmap_prepare(struct vm_area_desc *desc) { - const unsigned long len = vma_desc_size(desc); - if (!vma_desc_test_any(desc, VMA_SHARED_BIT, VMA_MAYSHARE_BIT)) return -EINVAL; - vma_desc_set_flags(desc, VMA_LOCKED_BIT, VMA_DONTDUMP_BIT); - if (!mlock_future_ok(desc->mm, /*is_vma_locked=*/ true, len)) - return -EAGAIN; + vma_desc_set_flags(desc, VMA_DONTDUMP_BIT); desc->vm_ops = &secretmem_vm_ops; return 0; @@ -187,20 +264,40 @@ static const struct inode_operations secretmem_iops = { static struct vfsmount *secretmem_mnt; +static int secretmem_init_inode_priv(struct inode *inode) +{ + struct secretmem_inode_state *state; + + state = kzalloc_obj(*state); + if (!state) + return -ENOMEM; + + state->user = get_uid(current_user()); + inode->i_private = state; + return 0; +} + static struct file *secretmem_file_create(unsigned long flags) { struct file *file; struct inode *inode; const char *anon_name = "[secretmem]"; + int err; inode = anon_inode_make_secure_inode(secretmem_mnt->mnt_sb, anon_name, NULL); if (IS_ERR(inode)) return ERR_CAST(inode); + err = secretmem_init_inode_priv(inode); + if (err) + goto err_free_inode; + file = alloc_file_pseudo(inode, secretmem_mnt, "secretmem", O_RDWR | O_LARGEFILE, &secretmem_fops); - if (IS_ERR(file)) - goto err_free_inode; + if (IS_ERR(file)) { + err = PTR_ERR(file); + goto err_free_priv; + } mapping_set_gfp_mask(inode->i_mapping, GFP_USER); mapping_set_unevictable(inode->i_mapping); @@ -215,10 +312,11 @@ static struct file *secretmem_file_create(unsigned long flags) atomic_inc(&secretmem_users); return file; - +err_free_priv: + secretmem_destroy_inode_priv(inode); err_free_inode: iput(inode); - return file; + return ERR_PTR(err); } SYSCALL_DEFINE1(memfd_secret, unsigned int, flags) diff --git a/tools/testing/selftests/mm/memfd_secret.c b/tools/testing/selftests/mm/memfd_secret.c index aac4f795c327..c55d84c5e613 100644 --- a/tools/testing/selftests/mm/memfd_secret.c +++ b/tools/testing/selftests/mm/memfd_secret.c @@ -57,33 +57,6 @@ static void test_file_apis(int fd) pass("file IO is blocked as expected\n"); } -static void test_mlock_limit(int fd) -{ - size_t len; - char *mem; - - len = mlock_limit_cur; - if (len % page_size != 0) - len = (len/page_size) * page_size; - - mem = mmap(NULL, len, prot, mode, fd, 0); - if (mem == MAP_FAILED) { - fail("unable to mmap secret memory\n"); - return; - } - munmap(mem, len); - - len = mlock_limit_max * 2; - mem = mmap(NULL, len, prot, mode, fd, 0); - if (mem != MAP_FAILED) { - fail("unexpected mlock limit violation\n"); - munmap(mem, len); - return; - } - - pass("mlock limit is respected\n"); -} - static void test_vmsplice(int fd, const char *desc) { ssize_t transferred; @@ -297,7 +270,7 @@ static void prepare(void) strerror(errno)); } -#define NUM_TESTS 6 +#define NUM_TESTS 5 int main(int argc, char *argv[]) { @@ -319,7 +292,6 @@ int main(int argc, char *argv[]) if (ftruncate(fd, page_size)) ksft_exit_fail_msg("ftruncate failed: %s\n", strerror(errno)); - test_mlock_limit(fd); test_file_apis(fd); /* * We have to run the first vmsplice test before any secretmem page was From 6c001a62c34f13fe1c6a24304c289b387d9e697d Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 3 Sep 2026 13:27:28 -0400 Subject: [PATCH 0593/1198] ring-buffer: Add checking nr_subbufs to persistent ring buffer validation Sashiko reported that the code was using meta->nr_subbufs without making sure that it matched the nr_pages + 1 on data that was assuming the two were the same. Add a check to the persistent ring buffer validation code to make sure that the saved nr_subbufs matches what we expect. Link: https://patch.msgid.link/20260903132728.7fb27d34@gandalf.local.home Fixes: f5b95f1fa2ef3 ("ring-buffer: Validate the persistent meta data subbuf array") Reported-by: sashiko-bot@kernel.org Closes: https://lore.kernel.org/all/20260901164836.D962D1F000E9@smtp.kernel.org/ Reviewed-by: Vincent Donnefort Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 84fd4cdd486f..ff0a44aa578d 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1856,6 +1856,11 @@ static bool rb_cpu_meta_valid(struct ring_buffer_cpu_meta *meta, int cpu, return false; } + if (meta->nr_subbufs != nr_pages + 1) { + pr_info("Ring buffer boot meta [%d] invalid nr_subbufs\n", cpu); + return false; + } + buffers_start = meta->first_buffer; buffers_end = meta->first_buffer + (subbuf_size * meta->nr_subbufs); From 0e68c74e44da81a4599c52437ee1f63a2c234470 Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Wed, 2 Sep 2026 13:41:20 +0100 Subject: [PATCH 0594/1198] drm/xe/vram: report FLAT_CCS base misalignment MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit So we can easily check if a machine had the CCS bug, when looking back over bug reports where we have the same machine with newer kernel. Example print for a machine with the CCS bug: FLAT_CCS base:27bbff800, aligned:no v2 (Matt B): - Unconditionally print the base + alignment Fixes: 37173392741c ("drm/xe/vram: fix ccs offset calculation") Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Matthew Brost Cc: Rodrigo Vivi Cc: stable@kernel.org Reviewed-by: Matthew Brost Link: https://patch.msgid.link/20260902124117.918018-9-matthew.auld@intel.com (cherry picked from commit d00b7f4f03bbeb2efad872f1686130e18c2b4141) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/xe_vram.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/xe/xe_vram.c b/drivers/gpu/drm/xe/xe_vram.c index 7b4478fb1697..56cff1e44530 100644 --- a/drivers/gpu/drm/xe/xe_vram.c +++ b/drivers/gpu/drm/xe/xe_vram.c @@ -90,6 +90,9 @@ static int get_flat_ccs_offset(struct xe_gt *gt, u64 tile_size, u64 *poffset) offset |= offset_lo << 6; /* HW view bits 31:6 */ offset *= num_enabled; /* convert to SW view */ + drm_info(&xe->drm, "FLAT_CCS base:%llx, aligned:%s\n", offset, + str_yes_no(IS_ALIGNED(offset, SZ_128K))); + /* * Everything below this offset is handed to the VRAM * allocator, so it has to be the *first* address the From 4299767d772d4e498998e32157e45841178ab192 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ondrej=20Mosn=C3=A1=C4=8Dek?= Date: Thu, 3 Sep 2026 17:56:15 +0200 Subject: [PATCH 0595/1198] =?UTF-8?q?MAINTAINERS,=20mailmap:=20update=20em?= =?UTF-8?q?ail=20address=20for=20Ondrej=20Mosn=C3=A1=C4=8Dek?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit I'm going to use my personal email for kernel contributions from now on. Update MAINTAINERS and .mailmap to reflect this. Also switch to use proper spelling with diacritics, since I normally use the full Unicode name with my personal email address. I'm leaving in-code occurences unchanged though, as that would be just unnecessary churn. Link: https://lore.kernel.org/lkml/CAFqZXNvOGbzy8-ZnJtKi94jfu2H173Tz7VYpK8KuseMQS-9tNA@mail.gmail.com/ Signed-off-by: Ondrej Mosnáček Signed-off-by: Paul Moore --- .mailmap | 1 + MAINTAINERS | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/.mailmap b/.mailmap index 6803f3bd2865..0e672a60afdc 100644 --- a/.mailmap +++ b/.mailmap @@ -699,6 +699,7 @@ Oliver Hartkopp Oliver Hartkopp Oliver Upton Oliver Upton +Ondrej Mosnáček Ondřej Jirman Oza Pawandeep Pali Rohár diff --git a/MAINTAINERS b/MAINTAINERS index 3a19da74d00c..5dcc75e75aa2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -24778,7 +24778,7 @@ K: \bsecurity_[a-z_0-9]\+\b SELINUX SECURITY MODULE M: Paul Moore M: Stephen Smalley -R: Ondrej Mosnacek +R: Ondrej Mosnáček L: selinux@vger.kernel.org S: Supported W: https://github.com/SELinuxProject From afdee49a1b88ed9bb44e2b30e855297c169bcc53 Mon Sep 17 00:00:00 2001 From: Xu Rao Date: Thu, 13 Aug 2026 16:31:07 +0800 Subject: [PATCH 0596/1198] nvme-fabrics: fix DHCHAP secret leak on parse failure nvmf_parse_options() duplicates dhchap_secret and dhchap_ctrl_secret with match_strdup() before validating the DHHC-1: representation. If validation fails, the parser returns -EINVAL before the temporary string in p is assigned to opts->dhchap_secret or opts->dhchap_ctrl_secret. nvmf_create_ctrl() subsequently frees opts, but nvmf_free_options() cannot release the unassigned temporary string. Each rejected option therefore leaks one allocation. This is easy to miss because valid secrets transfer ownership to opts and are freed normally, while the malformed-secret path still returns the expected -EINVAL to userspace. With CONFIG_NVME_HOST_AUTH enabled, the leak is reachable before the required-option checks and transport lookup. No NVMe-oF target or working transport connection is required; for example, repeatedly writing dhchap_secret=BAD or dhchap_ctrl_secret=BAD to /dev/nvme-fabrics deterministically takes the leaking parse path. Free the temporary string before leaving both validation error paths. Use kfree_sensitive() because the copied option may contain secret material even when its representation is rejected, matching the sensitive cleanup used for stored DHCHAP secrets. Fixes: f50fff73d620 ("nvme: implement In-Band authentication") Cc: stable@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Xu Rao Signed-off-by: Keith Busch --- drivers/nvme/host/fabrics.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index fd5abd04e080..59f823dfbbcc 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -1028,6 +1028,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, } if (strlen(p) < 11 || strncmp(p, "DHHC-1:", 7)) { pr_err("Invalid DH-CHAP secret %s\n", p); + kfree_sensitive(p); ret = -EINVAL; goto out; } @@ -1042,6 +1043,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, } if (strlen(p) < 11 || strncmp(p, "DHHC-1:", 7)) { pr_err("Invalid DH-CHAP secret %s\n", p); + kfree_sensitive(p); ret = -EINVAL; goto out; } From ef248d5de4469fb6bbaf8dbe0c4c47800080d648 Mon Sep 17 00:00:00 2001 From: Tristan Madani Date: Sat, 15 Aug 2026 00:14:27 +0000 Subject: [PATCH 0597/1198] nvme: add missing SRCU grace period in error path nvme_alloc_ns() error path at out_unlink_ns removes ns from the namespace head siblings list with list_del_rcu(&ns->siblings) but does not wait for SRCU readers before freeing the namespace struct. Multipath code iterates the head->list under srcu_read_lock() in nvme_find_path() and nvme_mpath_revalidate_paths(), so a concurrent reader can still hold a reference to ns when kfree(ns) runs. The normal removal path in nvme_ns_remove() correctly calls synchronize_srcu(&ns->head->srcu) after list_del_rcu() to wait for in-progress readers. Add the same grace period in the error path. Fixes: ed754e5deeb1 ("nvme: track shared namespaces") Cc: stable@vger.kernel.org Signed-off-by: Tristan Madani Reviewed-by: Sagi Grimberg Reviewed-by: John Garry Reviewed-by: Christoph Hellwig Signed-off-by: Keith Busch --- drivers/nvme/host/core.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 5f2744be7388..9739ce38b73a 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -4345,6 +4345,9 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info) last_path = true; } mutex_unlock(&ctrl->subsys->lock); + + /* guarantee not available in head->list */ + synchronize_srcu(&ns->head->srcu); if (last_path) nvme_put_ns_head(ns->head); nvme_put_ns_head(ns->head); From 4ed7f3d7d435bf5b63da2814dc9270f5ba896011 Mon Sep 17 00:00:00 2001 From: Mohamed Khalfella Date: Sat, 22 Aug 2026 17:46:41 -0700 Subject: [PATCH 0598/1198] nvme: remove stale namespaces by NSID range during scan nvme_scan_ns_list() drops the stale namespaces in each gap in the reported NSID list one NSID at a time. Every iteration calls nvme_find_get_ns() to look the namespace up and removes it if it is present. The loop runs once per NSID in the gap rather than once per namespace actually present. NSIDs are 32-bit, so a target with a sparse NSID space can make a single gap spin the loop billions of times with nothing to remove. watchdog: BUG: soft lockup - CPU#4 stuck for 26s! Workqueue: nvme-wq nvme_scan_work [nvme_core] RIP: 0010:__srcu_read_unlock+0xb/0x20 Call Trace: nvme_find_get_ns+0x7d/0xb0 [nvme_core] nvme_scan_ns_list+0xe8/0x280 [nvme_core] nvme_scan_work+0x18a/0x280 [nvme_core] process_one_work+0x197/0x380 worker_thread+0x2fe/0x410 kthread+0xe0/0x100 Rename nvme_remove_invalid_namespaces() to nvme_remove_nsid_range() and give it an open (start, end) NSID range. ctrl->namespaces is sorted by NSID, so the whole gap is dropped in a single walk that stops once end is reached. This bounds the work by the namespaces that are present instead of by the size of the gap. Fixes: 540c801c65eb ("NVMe: Implement namespace list scanning") Signed-off-by: Mohamed Khalfella Reviewed-by: Sagi Grimberg Reviewed-by: Randy Jennings Signed-off-by: Keith Busch --- drivers/nvme/host/core.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 9739ce38b73a..32cd1e9a1193 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -155,8 +155,6 @@ static const struct class nvme_ns_chr_class = { }; static void nvme_put_subsystem(struct nvme_subsystem *subsys); -static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl, - unsigned nsid); static void nvme_update_keep_alive(struct nvme_ctrl *ctrl, struct nvme_command *cmd); static int nvme_get_log_lsi(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, @@ -4516,15 +4514,16 @@ static void nvme_scan_ns_async(void *data, async_cookie_t cookie) nvme_scan_ns(scan_info->ctrl, nsid); } -static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl, - unsigned nsid) +static void nvme_remove_nsid_range(struct nvme_ctrl *ctrl, u32 start, u32 end) { struct nvme_ns *ns, *next; LIST_HEAD(rm_list); mutex_lock(&ctrl->namespaces_lock); list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) { - if (ns->head->ns_id > nsid) { + if (ns->head->ns_id >= end) + break; + if (ns->head->ns_id > start) { list_del_rcu(&ns->list); synchronize_srcu(&ctrl->srcu); list_add_tail_rcu(&ns->list, &rm_list); @@ -4574,13 +4573,14 @@ static int nvme_scan_ns_list(struct nvme_ctrl *ctrl) goto out; async_schedule_domain(nvme_scan_ns_async, &scan_info, &domain); - while (++prev < nsid) - nvme_ns_remove_by_nsid(ctrl, prev); + if (prev + 1 < nsid) + nvme_remove_nsid_range(ctrl, prev, nsid); + prev = max(prev + 1, nsid); } async_synchronize_full_domain(&domain); } out: - nvme_remove_invalid_namespaces(ctrl, prev); + nvme_remove_nsid_range(ctrl, prev, UINT_MAX); free: async_synchronize_full_domain(&domain); kfree(ns_list); @@ -4600,7 +4600,7 @@ static void nvme_scan_ns_sequential(struct nvme_ctrl *ctrl) for (i = 1; i <= nn; i++) nvme_scan_ns(ctrl, i); - nvme_remove_invalid_namespaces(ctrl, nn); + nvme_remove_nsid_range(ctrl, nn, UINT_MAX); } static void nvme_clear_changed_ns_log(struct nvme_ctrl *ctrl) From b2d8f2a3723103abd0f8b388691ad95817d4fff4 Mon Sep 17 00:00:00 2001 From: Mohamed Khalfella Date: Fri, 21 Aug 2026 16:03:09 -0700 Subject: [PATCH 0599/1198] nvme: print namespace IDs as unsigned 32bit value NSIDs are 32-bit unsigned values, but a number of log messages print them with %d. An NSID larger than 0x7fffffff is rendered as a negative number, which is confusing in the kernel log and makes the message hard to correlate with the namespace it talks about. Sparse NSID spaces where high NSIDs are common are the most likely to hit this. The nsid sysfs attribute has the same problem, and there it is worse because userspace parses the value. For example: $ grep . /sys/class/block/nvme0*/nsid /sys/class/block/nvme0c0n1/nsid:10 /sys/class/block/nvme0c0n2/nsid:-16 /sys/class/block/nvme0c0n3/nsid:11 /sys/class/block/nvme0c0n4/nsid:-2000000016 /sys/class/block/nvme0n1/nsid:10 /sys/class/block/nvme0n2/nsid:-16 /sys/class/block/nvme0n3/nsid:11 /sys/class/block/nvme0n4/nsid:-2000000016 $ Print all of them with %u. Several messages in these files, including two in zns.c right next to the ones being changed, already use %u, so this only makes the rest consistent with them. No functional change other than how the NSID is formatted. Fixes: 2b9b6e86bca7 ("NVMe: Export namespace attributes to sysfs") Fixes: 1d5df6af8c74 ("nvme: don't blindly overwrite identifiers on disk revalidate") Fixes: ed754e5deeb1 ("nvme: track shared namespaces") Fixes: 9ad1927a3bc2 ("nvme: always search for namespace head") Fixes: 71010c309454 ("nvme: implement multiple I/O Command Set support") Fixes: 2f4c9ba23b88 ("nvme: export zoned namespaces without Zone Append support read-only") Fixes: 0ec84df4953b ("nvme-core: check ctrl css before setting up zns") Fixes: 2079f41ec6ff ("nvme: check that EUI/GUID/UUID are globally unique") Fixes: ce8d78616a6b ("nvme: warn about shared namespaces without CONFIG_NVME_MULTIPATH") Fixes: ac522fc6c316 ("nvme: don't reject probe due to duplicate IDs for single-ported PCIe devices") Signed-off-by: Mohamed Khalfella Reviewed-by: Sagi Grimberg Signed-off-by: Keith Busch --- drivers/nvme/host/core.c | 18 +++++++++--------- drivers/nvme/host/sysfs.c | 2 +- drivers/nvme/host/zns.c | 4 ++-- 3 files changed, 12 insertions(+), 12 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 32cd1e9a1193..758245c799a1 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1610,7 +1610,7 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, } if (nvme_multi_css(ctrl) && !csi_seen) { - dev_warn(ctrl->device, "Command set not reported for nsid:%d\n", + dev_warn(ctrl->device, "Command set not reported for nsid:%u\n", info->nsid); status = -EINVAL; } @@ -4126,13 +4126,13 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info) ((ns->ctrl->subsys->cmic & NVME_CTRL_CMIC_MULTI_CTRL) && info->is_shared)) { dev_err(ctrl->device, - "ignoring nsid %d because of duplicate IDs\n", + "ignoring nsid %u because of duplicate IDs\n", info->nsid); return ret; } dev_err(ctrl->device, - "clearing duplicate IDs for nsid %d\n", info->nsid); + "clearing duplicate IDs for nsid %u\n", info->nsid); dev_err(ctrl->device, "use of /dev/disk/by-id/ may cause data corruption\n"); memset(&info->ids.nguid, 0, sizeof(info->ids.nguid)); @@ -4147,7 +4147,7 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info) ret = nvme_subsys_check_duplicate_ids(ctrl->subsys, &info->ids); if (ret) { dev_err(ctrl->device, - "duplicate IDs in subsystem for nsid %d\n", + "duplicate IDs in subsystem for nsid %u\n", info->nsid); goto out_unlock; } @@ -4161,20 +4161,20 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info) if ((!info->is_shared || !head->shared) && !list_empty(&head->list)) { dev_err(ctrl->device, - "Duplicate unshared namespace %d\n", + "Duplicate unshared namespace %u\n", info->nsid); goto out_put_ns_head; } if (!nvme_ns_ids_equal(&head->ids, &info->ids)) { dev_err(ctrl->device, - "IDs don't match for shared namespace %d\n", + "IDs don't match for shared namespace %u\n", info->nsid); goto out_put_ns_head; } if (!multipath) { dev_warn(ctrl->device, - "Found shared namespace %d, but multipathing not supported.\n", + "Found shared namespace %u, but multipathing not supported.\n", info->nsid); dev_warn_once(ctrl->device, "Shared namespace support requires core_nvme.multipath=Y.\n"); @@ -4423,7 +4423,7 @@ static void nvme_validate_ns(struct nvme_ns *ns, struct nvme_ns_info *info) if (!nvme_ns_ids_equal(&ns->head->ids, &info->ids)) { dev_err(ns->ctrl->device, - "identifiers changed for nsid %d\n", ns->head->ns_id); + "identifiers changed for nsid %u\n", ns->head->ns_id); goto out; } @@ -4450,7 +4450,7 @@ static void nvme_scan_ns(struct nvme_ctrl *ctrl, unsigned nsid) if (info.ids.csi != NVME_CSI_NVM && !nvme_multi_css(ctrl)) { dev_warn(ctrl->device, - "command set not reported for nsid: %d\n", nsid); + "command set not reported for nsid: %u\n", nsid); return; } diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c index abf8edaae371..02a2490a9ed7 100644 --- a/drivers/nvme/host/sysfs.c +++ b/drivers/nvme/host/sysfs.c @@ -166,7 +166,7 @@ static DEVICE_ATTR_RO(eui); static ssize_t nsid_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sysfs_emit(buf, "%d\n", dev_to_ns_head(dev)->ns_id); + return sysfs_emit(buf, "%u\n", dev_to_ns_head(dev)->ns_id); } static DEVICE_ATTR_RO(nsid); diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c index 2a152e87bd76..e31ec6f4f94f 100644 --- a/drivers/nvme/host/zns.c +++ b/drivers/nvme/host/zns.c @@ -48,12 +48,12 @@ int nvme_query_zone_info(struct nvme_ns *ns, unsigned lbaf, NVME_CMD_EFFECTS_CSUPP)) { if (test_and_clear_bit(NVME_NS_FORCE_RO, &ns->flags)) dev_warn(ns->ctrl->device, - "Zone Append supported for zoned namespace:%d. Remove read-only mode\n", + "Zone Append supported for zoned namespace:%u. Remove read-only mode\n", ns->head->ns_id); } else { set_bit(NVME_NS_FORCE_RO, &ns->flags); dev_warn(ns->ctrl->device, - "Zone Append not supported for zoned namespace:%d. Forcing to read-only mode\n", + "Zone Append not supported for zoned namespace:%u. Forcing to read-only mode\n", ns->head->ns_id); } From 59fe1cbc57235495a5f08dd53db176e3e3250356 Mon Sep 17 00:00:00 2001 From: Mohamed Khalfella Date: Fri, 21 Aug 2026 16:03:10 -0700 Subject: [PATCH 0600/1198] nvmet: print namespace IDs as unsigned 32bit value struct nvmet_ns.nsid is a u32, but a few messages print it with %d. An NSID larger than 0x7fffffff is rendered as a negative number, which is misleading in general and particularly so for the configfs messages that echo back the NSID the user just asked for. For example: [ T200] nvmet: adding nsid -16 to subsystem mysubsystem Print them with %u. The invalid-NSID error in nvmet_ns_make() keeps its %#x because the two values it rejects, 0 and NVME_NSID_ALL, are more readable in hex format. No functional change other than how the NSID is formatted. Fixes: a07b4970f464 ("nvmet: add a generic NVMe target") Fixes: c6925093d0b2 ("nvmet: Optionally use PCI P2P memory") Fixes: 5a47c2080a73 ("nvmet: support reservation feature") Signed-off-by: Mohamed Khalfella Reviewed-by: Sagi Grimberg Signed-off-by: Keith Busch --- drivers/nvme/target/configfs.c | 4 ++-- drivers/nvme/target/core.c | 2 +- drivers/nvme/target/pr.c | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index 413ee2d16d29..6286e38436dd 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -814,7 +814,7 @@ static ssize_t nvmet_ns_resv_enable_store(struct config_item *item, mutex_lock(&ns->subsys->lock); if (ns->enabled) { - pr_err("the ns:%d is already enabled.\n", ns->nsid); + pr_err("the ns:%u is already enabled.\n", ns->nsid); mutex_unlock(&ns->subsys->lock); return -EINVAL; } @@ -880,7 +880,7 @@ static struct config_group *nvmet_ns_make(struct config_group *group, goto out; config_group_init_type_name(&ns->group, name, &nvmet_ns_type); - pr_info("adding nsid %d to subsystem %s\n", nsid, subsys->subsysnqn); + pr_info("adding nsid %u to subsystem %s\n", nsid, subsys->subsysnqn); return &ns->group; out: diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index d74c01c98f19..ad60b91ced6c 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -558,7 +558,7 @@ static void nvmet_p2pmem_ns_add_p2p(struct nvmet_ctrl *ctrl, if (ret < 0) pci_dev_put(p2p_dev); - pr_info("using p2pmem on %s for nsid %d\n", pci_name(p2p_dev), + pr_info("using p2pmem on %s for nsid %u\n", pci_name(p2p_dev), ns->nsid); } diff --git a/drivers/nvme/target/pr.c b/drivers/nvme/target/pr.c index 0948a690a1c0..09d8c63f5680 100644 --- a/drivers/nvme/target/pr.c +++ b/drivers/nvme/target/pr.c @@ -145,7 +145,7 @@ static void nvmet_pr_add_resv_log(struct nvmet_ctrl *ctrl, u8 log_type, log.nsid = cpu_to_le32(nsid); if (!kfifo_put(&log_mgr->log_queue, log)) { - pr_info("a reservation log lost, cntlid:%d, log_type:%d, nsid:%d\n", + pr_info("a reservation log lost, cntlid:%d, log_type:%d, nsid:%u\n", ctrl->cntlid, log_type, nsid); log_mgr->lost_count++; } From df7197ebc7280be9f34dfee9757a933ef0b18741 Mon Sep 17 00:00:00 2001 From: Yehyeong Lee Date: Sun, 23 Aug 2026 16:46:16 +0900 Subject: [PATCH 0601/1198] nvme-tcp: return -EPROTO for a C2HData on a write The direction check in nvme_tcp_handle_c2h_data() returns -EIO. A C2HData PDU naming a command that did not ask for data is a protocol violation, and the check that rejects a PDU on those grounds a few lines below it - SUCCESS set without LAST - returns -EPROTO. No caller distinguishes the two, so this changes the error code alone. Suggested-by: Sagi Grimberg Signed-off-by: Yehyeong Lee Reviewed-by: Sagi Grimberg Signed-off-by: Keith Busch --- drivers/nvme/host/tcp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 643fc503a477..2a15c6143f2a 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -688,7 +688,7 @@ static int nvme_tcp_handle_c2h_data(struct nvme_tcp_queue *queue, dev_err(queue->ctrl->ctrl.device, "queue %d tag %#x unexpected data for a write\n", nvme_tcp_queue_id(queue), rq->tag); - return -EIO; + return -EPROTO; } req = blk_mq_rq_to_pdu(rq); From 14cc5a7e77731497d5bea70f3bb05df7eda982e4 Mon Sep 17 00:00:00 2001 From: Shivam Kumar Date: Fri, 14 Aug 2026 15:48:11 -0400 Subject: [PATCH 0602/1198] nvmet-tcp: fix out-of-bounds write when receiving an over-long PDU nvmet_tcp_try_recv_pdu() reads a PDU header into the fixed 128-byte queue->pdu union, then computes the remaining payload length as queue->left = hdr->hlen - queue->offset + hdgst; and reads that many more bytes into &queue->pdu + queue->offset, without ever bounding the result against sizeof(queue->pdu). A struct nvme_tcp_icreq_pdu is itself 128 bytes, exactly the size of the union. Once a header digest has been negotiated (hdgst = 4), a second ICReq passes the hlen == nvmet_tcp_pdu_size() check but yields queue->left = 128 - 8 + 4 = 124, so bytes 8..132 are written into the 128-byte buffer -- 4 bytes past its end, over queue->hdr_digest and queue->data_digest. Those bytes are attacker-controlled (an ICReq carries no digest), and the duplicate ICReq is only rejected later, after the overflow. A remote unauthenticated host can thus corrupt kernel memory adjacent to the receive buffer. Reject any PDU whose declared length would read past the end of queue->pdu before the second recv. Fixes: 872d26a391da ("nvmet-tcp: add NVMe over TCP target driver") Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Shivam Kumar Cc: stable@vger.kernel.org Reviewed-by: Sagi Grimberg Signed-off-by: Keith Busch --- drivers/nvme/target/tcp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index e4f603b2ace7..1e2346ede900 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -1244,6 +1244,8 @@ static int nvmet_tcp_try_recv_pdu(struct nvmet_tcp_queue *queue) } queue->left = hdr->hlen - queue->offset + hdgst; + if (queue->left > sizeof(queue->pdu) - queue->offset) + return -EPROTO; goto recv; } From 08acb54b063a33730eb1ae1e0f89bf36542bac9f Mon Sep 17 00:00:00 2001 From: Xixin Liu Date: Wed, 19 Aug 2026 08:50:00 +0800 Subject: [PATCH 0603/1198] nvme-tcp: defer TLS inline send to io_work blk_mq holds set->srcu while queuing and running requests. The kTLS software send path takes ctx->tx_lock. lockdep knows that tx_lock nests under elevator_lock which then waits on srcu, so an inline send from that path under TLS triggers circular locking. Skip the inline send optimization for TLS queues so the send runs from the workqueue instead. The same workqueue already retries TLS sends on write-space notifications. Plain TCP keeps the inline path. Fixes: be8e82caa685 ("nvme-tcp: enable TLS handshake upcall") Reviewed-by: Hannes Reinecke Signed-off-by: Xixin Liu Signed-off-by: Keith Busch --- drivers/nvme/host/tcp.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 2a15c6143f2a..921934028e0b 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -413,8 +413,13 @@ static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req, * if we're the first on the send_list and we can try to send * directly, otherwise queue io_work. Also, only do that if we * are on the same cpu, so we don't introduce contention. + * + * TLS kTLS send takes ctx->tx_lock while blk_mq holds set->srcu. + * lockdep reports circular locking via elevator_lock. Defer TLS + * sends to the io workqueue instead of inline from this path. */ if (queue->io_cpu == raw_smp_processor_id() && + !nvme_tcp_queue_tls(queue) && empty && mutex_trylock(&queue->send_mutex)) { nvme_tcp_send_all(queue); mutex_unlock(&queue->send_mutex); From db62b35cbca052860c519cbcabe7650708528738 Mon Sep 17 00:00:00 2001 From: Shivam Kumar Date: Thu, 27 Aug 2026 15:24:55 -0400 Subject: [PATCH 0604/1198] nvmet-tcp: reject unsolicited H2CData PDUs nvmet_tcp_handle_h2c_data_pdu() accepts an H2CData PDU after only checking that its TTAG is a valid in-range command index and that the command's data buffers are mapped. It never checks that the target has actually solicited that data by sending an R2T for the command. A remote host can abuse this. It submits a write command that takes the R2T path and, before the target transmits the R2T, sends an H2CData PDU for that command's tag. The data completes the command early, and when the command then fails synchronously (e.g. a length mismatch caught by nvmet_check_transfer_len()), it is completed a second time. Each completion calls nvmet_tcp_queue_response(), so the same command is added to queue->resp_list twice while it is still linked; the second llist_add() makes the node point to itself (lentry->next == lentry). nvmet_tcp_process_resp_list() then walks that self-referential node and adds the command to resp_send_list twice. With CONFIG_DEBUG_LIST this trips the "list_add double add" check (kernel BUG); without it the loop never terminates and the nvmet_tcp workqueue wedges (soft-lockup). It is remotely triggerable and needs no authentication on an allow_any_host subsystem. Track whether an R2T has been transmitted for a command and reject an H2CData PDU that arrives before it. The flag is cleared on command reuse (nvmet_tcp_get_cmd() zeroes cmd->flags) and stays set across the multiple H2CData PDUs of a single solicited transfer. Fixes: 872d26a391da ("nvmet-tcp: add NVMe over TCP target driver") Cc: stable@vger.kernel.org Reviewed-by: Sagi Grimberg Signed-off-by: Shivam Kumar Signed-off-by: Keith Busch --- drivers/nvme/target/tcp.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 1e2346ede900..e59810175262 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -103,6 +103,7 @@ enum nvmet_tcp_recv_state { enum { NVMET_TCP_F_INIT_FAILED = (1 << 0), + NVMET_TCP_F_R2T_SENT = (1 << 1), }; struct nvmet_tcp_cmd { @@ -776,6 +777,7 @@ static int nvmet_try_send_r2t(struct nvmet_tcp_cmd *cmd, bool last_in_batch) return -EAGAIN; cmd->queue->snd_cmd = NULL; + cmd->flags |= NVMET_TCP_F_R2T_SENT; return 1; } @@ -1009,6 +1011,12 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue) cmd = &queue->connect; } + if (unlikely(!(cmd->flags & NVMET_TCP_F_R2T_SENT))) { + pr_err("queue %d: unsolicited H2CData (ttag %u)\n", + queue->idx, data->ttag); + goto err_proto; + } + if (le32_to_cpu(data->data_offset) != cmd->rbytes_done) { pr_err("ttag %u unexpected data offset %u (expected %u)\n", data->ttag, le32_to_cpu(data->data_offset), From 5cdd07a6882504c4b6e61169cce79e0720f77fca Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Tue, 1 Sep 2026 09:46:31 -0700 Subject: [PATCH 0605/1198] MAINTAINERS: update nvme entry Update Jens' entry to match the mail address of his other entries. Acked-by: Jens Axboe Signed-off-by: Keith Busch --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 46d98b53729d..91d6086196e2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -19366,7 +19366,7 @@ F: include/linux/platform_data/x86/nvidia-wmi-ec-backlight.h NVM EXPRESS DRIVER M: Keith Busch -M: Jens Axboe +M: Jens Axboe M: Christoph Hellwig M: Sagi Grimberg L: linux-nvme@lists.infradead.org From eaa948c0e19b1bb2d93262207bca0c3d19cc3406 Mon Sep 17 00:00:00 2001 From: Kazuki Hanai Date: Sun, 30 Aug 2026 22:11:05 +0900 Subject: [PATCH 0606/1198] nvmet-auth: Synchronize timeout work during SQ teardown nvmet_auth_sq_free() cancels auth_expired_work with cancel_delayed_work(). If the work has already started, cancellation does not wait for the callback. Transport teardown can consequently free or reuse the queue containing struct nvmet_sq while nvmet_auth_expired_work() still accesses that SQ. Add a teardown-specific helper that synchronously drains the delayed work before freeing authentication state, and use it from nvmet_sq_destroy(). Keep the non-synchronous helper for in-band authentication state cleanup, where the SQ owner remains alive. Fixes: 1a70200f404a ("nvmet-auth: expire authentication sessions") Cc: stable@vger.kernel.org Signed-off-by: Kazuki Hanai Reviewed-by: Sagi Grimberg Reviewed-by: Christoph Hellwig Signed-off-by: Keith Busch --- drivers/nvme/target/auth.c | 6 ++++++ drivers/nvme/target/core.c | 2 +- drivers/nvme/target/nvmet.h | 2 ++ 3 files changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/target/auth.c b/drivers/nvme/target/auth.c index edb9627d97b0..a55319bcdbd1 100644 --- a/drivers/nvme/target/auth.c +++ b/drivers/nvme/target/auth.c @@ -238,6 +238,12 @@ void nvmet_auth_sq_free(struct nvmet_sq *sq) sq->dhchap_skey = NULL; } +void nvmet_auth_sq_destroy(struct nvmet_sq *sq) +{ + cancel_delayed_work_sync(&sq->auth_expired_work); + nvmet_auth_sq_free(sq); +} + void nvmet_destroy_auth(struct nvmet_ctrl *ctrl) { ctrl->shash_id = 0; diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index ad60b91ced6c..1663ab7ac607 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -980,7 +980,7 @@ void nvmet_sq_destroy(struct nvmet_sq *sq) wait_for_completion(&sq->confirm_done); wait_for_completion(&sq->free_done); percpu_ref_exit(&sq->ref); - nvmet_auth_sq_free(sq); + nvmet_auth_sq_destroy(sq); nvmet_cq_put(sq->cq); /* diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index e362d7913a38..dbda55895f4f 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -924,6 +924,7 @@ u8 nvmet_setup_auth(struct nvmet_ctrl *ctrl, struct nvmet_sq *sq, bool reset); void nvmet_auth_sq_init(struct nvmet_sq *sq); void nvmet_destroy_auth(struct nvmet_ctrl *ctrl); void nvmet_auth_sq_free(struct nvmet_sq *sq); +void nvmet_auth_sq_destroy(struct nvmet_sq *sq); int nvmet_setup_dhgroup(struct nvmet_ctrl *ctrl, u8 dhgroup_id); bool nvmet_check_auth_status(struct nvmet_req *req); int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response, @@ -950,6 +951,7 @@ static inline void nvmet_auth_sq_init(struct nvmet_sq *sq) } static inline void nvmet_destroy_auth(struct nvmet_ctrl *ctrl) {}; static inline void nvmet_auth_sq_free(struct nvmet_sq *sq) {}; +static inline void nvmet_auth_sq_destroy(struct nvmet_sq *sq) {}; static inline bool nvmet_check_auth_status(struct nvmet_req *req) { return true; From 09d0c07bd9ce3b2f2d993f672698d32a17543c32 Mon Sep 17 00:00:00 2001 From: Seokgyu Choi Date: Thu, 27 Aug 2026 07:52:21 +0000 Subject: [PATCH 0607/1198] nvmet: reject namespace enable without device path A newly allocated namespace has a NULL device_path until userspace configures the device_path attribute. If buffered_io is enabled before device_path is configured, nvmet_bdev_ns_enable() returns -ENOTBLK and nvmet_ns_enable() falls back to nvmet_file_ns_enable(). The latter passes the NULL device_path to filp_open(), causing a NULL pointer dereference in getname_kernel(). Reject namespace enable when device_path has not been configured. Reported-by: syzbot+f613f9f010ec98eb9d86@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=f613f9f010ec98eb9d86 Signed-off-by: Seokgyu Choi Reviewed-by: Sagi Grimberg Reviewed-by: Christoph Hellwig Signed-off-by: Keith Busch --- drivers/nvme/target/core.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 1663ab7ac607..43871a8f56ca 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -591,6 +591,11 @@ int nvmet_ns_enable(struct nvmet_ns *ns) if (ns->enabled) goto out_unlock; + if (!ns->device_path) { + ret = -EINVAL; + goto out_unlock; + } + ret = nvmet_bdev_ns_enable(ns); if (ret == -ENOTBLK) ret = nvmet_file_ns_enable(ns); From 56e6279266f6962bb2d38a54397e3c605165b0c5 Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Fri, 14 Aug 2026 16:38:34 +0200 Subject: [PATCH 0608/1198] nvme-fc: fix double free of fabrics options when nvme_add_ctrl() fails nvmf_create_ctrl() owns the fabrics options and frees them whenever ->create_ctrl() returns an error, so a transport must not free them on its own error paths. nvme-fc tracks this by testing ctrl->ctrl.opts in nvme_fc_ctrl_free(), which requires nvme_fc_init_ctrl() to clear that pointer on every error exit. The coupling is implicit, and commit 1a9e218195a5 ("nvme: split device add from initialization") broke it by adding a second error exit. When nvme_add_ctrl() fails, nvme_fc_init_ctrl() jumps to out_put_ctrl:, past the "ctrl->ctrl.opts = NULL" that only sits on the fail_ctrl: path, so nvme_fc_ctrl_free() frees the options and nvmf_create_ctrl() frees them a second time: BUG: KASAN: slab-use-after-free in nvmf_free_options+0x30/0x190 nvmf_free_options+0x30/0x190 drivers/nvme/host/fabrics.c:1284 nvmf_create_ctrl drivers/nvme/host/fabrics.c:1374 [inline] Freed by task 5534: nvme_fc_ctrl_free drivers/nvme/host/fc.c:2374 [inline] nvme_fc_init_ctrl+0xe17/0x1450 drivers/nvme/host/fc.c:3605 nvme_add_ctrl() fails when dev_set_name() cannot allocate, so this is reachable under memory pressure or fault injection. Without KASAN the options are freed twice. Rather than clear the pointer on the second exit as well, derive ownership the way nvme-tcp, nvme-rdma and nvme-loop do, from list membership: their free_ctrl leaves the options alone unless the controller made it onto the transport list. The list cannot simply be populated on the success path as it is there. nvme-fc runs the initial connect synchronously via flush_delayed_work(), and the controller has to be reachable on rport->ctrl_list for the whole of it: nvme_fc_unregister_remoteport() needs to find it to signal connectivity loss, nvme_fc_match_disconn_ls() matches an incoming Disconnect Association LS against ctrl->association_id, which is only assigned during that window, nvme_fc_resume_controller() needs it on remoteport re-registration, and nvme_fc_existing_controller() uses it to reject a duplicate connect racing the one in flight. Keep the insertion where it is and add a fail_unlist: label, falling into fail_ctrl:, for the error paths that run after it. The earlier error paths never reach the insertion and keep using fail_ctrl: directly, so the list is only touched where the controller is actually on it. nvme_fc_ctrl_free() cannot use the plain "goto free_ctrl" the other transports use, because it still has to put_device(), release the rport reference and free the ida entry for resources taken before the insertion. Sample list_empty() under rport->lock instead. ctrl->ctrl.opts also stays valid for the whole teardown now. That is not the bug being fixed, but it removes some fragility around the old idiom: nvme_free_ctrl() calls nvme_auth_free() before ->free_ctrl(), and ctrl_max_dhchaps() dereferences ctrl->opts without a NULL check when ctrl->dhchap_ctxs is set, which nvme-fc permits since NVMF_ALLOWED_OPTS allows the dhchap options. The nvme sysfs attributes that dereference ctrl->opts, such as hostnqn and address, evaluate their is_visible() test once at device_add() time and stay readable until cdev_device_del(). Fixes: 1a9e218195a5 ("nvme: split device add from initialization") Cc: stable@vger.kernel.org Reported-by: syzbot+f58e57380a6083c4041d@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=f58e57380a6083c4041d Signed-off-by: Niklas Cassel Tested-by: Rihyeon Kim Reviewed-by: Hannes Reinecke Signed-off-by: Keith Busch --- drivers/nvme/host/fc.c | 26 ++++++++++++++++++++------ 1 file changed, 20 insertions(+), 6 deletions(-) diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 023710e08e0d..48454cb7a0fc 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2364,9 +2364,15 @@ nvme_fc_ctrl_free(struct kref *ref) struct nvme_fc_ctrl *ctrl = container_of(ref, struct nvme_fc_ctrl, ref); unsigned long flags; + bool owns_opts; - /* remove from rport list */ + /* + * Presence on the rport list means nvme_fc_init_ctrl() completed, + * and with it ownership of the fabrics options passed to it. If it + * failed instead, the options still belong to nvmf_create_ctrl(). + */ spin_lock_irqsave(&ctrl->rport->lock, flags); + owns_opts = !list_empty(&ctrl->ctrl_list); list_del(&ctrl->ctrl_list); spin_unlock_irqrestore(&ctrl->rport->lock, flags); @@ -2376,7 +2382,7 @@ nvme_fc_ctrl_free(struct kref *ref) nvme_fc_rport_put(ctrl->rport); ida_free(&nvme_fc_ctrl_cnt, ctrl->cnum); - if (ctrl->ctrl.opts) + if (owns_opts) nvmf_free_options(ctrl->ctrl.opts); kfree(ctrl); } @@ -3575,14 +3581,14 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) { dev_err(ctrl->ctrl.device, "NVME-FC{%d}: failed to init ctrl state\n", ctrl->cnum); - goto fail_ctrl; + goto fail_unlist; } if (!queue_delayed_work(nvme_wq, &ctrl->connect_work, 0)) { dev_err(ctrl->ctrl.device, "NVME-FC{%d}: failed to schedule initial connect\n", ctrl->cnum); - goto fail_ctrl; + goto fail_unlist; } flush_delayed_work(&ctrl->connect_work); @@ -3593,14 +3599,22 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, return &ctrl->ctrl; +fail_unlist: + /* + * Leaving the list hands the options back to nvmf_create_ctrl(); + * see nvme_fc_ctrl_free(). Re-init so that list_empty() there + * reports the controller as unlisted. + */ + spin_lock_irqsave(&rport->lock, flags); + list_del_init(&ctrl->ctrl_list); + spin_unlock_irqrestore(&rport->lock, flags); + fail_ctrl: nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING); cancel_work_sync(&ctrl->ioerr_work); cancel_work_sync(&ctrl->ctrl.reset_work); cancel_delayed_work_sync(&ctrl->connect_work); - ctrl->ctrl.opts = NULL; - if (ctrl->ctrl.admin_tagset) nvme_remove_admin_tag_set(&ctrl->ctrl); /* initiate nvme ctrl ref counting teardown */ From fd9beb8870736e1c6a0b2351d88a161aaeb2b326 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 30 Aug 2026 23:05:01 -0700 Subject: [PATCH 0609/1198] nvme-tcp.h: drop kernel-doc comments, fix a few descriptions Expand @fei into @feil and @feih because the field was split due to it not being 32-bit aligned. Struct member @hdr was described twice in struct nvme_tcp_rsp_pdu, so drop one of them. These structs are defined in a spec outside of the kernel, so kernel-doc comments for them aren't needed here as well. This avoids kernel-doc warnings: Warning: include/linux/nvme-tcp.h:95 struct member 'rsvd2' not described in 'nvme_tcp_icreq_pdu' Warning: include/linux/nvme-tcp.h:113 struct member 'rsvd' not described in 'nvme_tcp_icresp_pdu' Warning: include/linux/nvme-tcp.h:128 struct member 'feil' not described in 'nvme_tcp_term_pdu' Warning: include/linux/nvme-tcp.h:128 struct member 'feiu' not described in 'nvme_tcp_term_pdu' Warning: include/linux/nvme-tcp.h:128 struct member 'rsvd' not described in 'nvme_tcp_term_pdu' Warning: include/linux/nvme-tcp.h:169 struct member 'rsvd' not described in 'nvme_tcp_r2t_pdu' Warning: include/linux/nvme-tcp.h:187 struct member 'rsvd' not described in 'nvme_tcp_data_pdu' Signed-off-by: Randy Dunlap Reviewed-by: Christoph Hellwig Signed-off-by: Keith Busch --- include/linux/nvme-tcp.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/include/linux/nvme-tcp.h b/include/linux/nvme-tcp.h index e435250fcb4d..859338da8573 100644 --- a/include/linux/nvme-tcp.h +++ b/include/linux/nvme-tcp.h @@ -77,7 +77,7 @@ struct nvme_tcp_hdr { __le32 plen; }; -/** +/* * struct nvme_tcp_icreq_pdu - nvme tcp initialize connection request pdu * * @hdr: pdu generic header @@ -95,7 +95,7 @@ struct nvme_tcp_icreq_pdu { __u8 rsvd2[112]; }; -/** +/* * struct nvme_tcp_icresp_pdu - nvme tcp initialize connection response pdu * * @hdr: pdu common header @@ -113,12 +113,13 @@ struct nvme_tcp_icresp_pdu { __u8 rsvd[112]; }; -/** +/* * struct nvme_tcp_term_pdu - nvme tcp terminate connection pdu * * @hdr: pdu common header * @fes: fatal error status - * @fei: fatal error information + * @feil: fatal error information (low 16 bits) + * @feih: fatal error information (high 16 bits) */ struct nvme_tcp_term_pdu { struct nvme_tcp_hdr hdr; @@ -128,7 +129,7 @@ struct nvme_tcp_term_pdu { __u8 rsvd[10]; }; -/** +/* * struct nvme_tcp_cmd_pdu - nvme tcp command capsule pdu * * @hdr: pdu common header @@ -139,10 +140,9 @@ struct nvme_tcp_cmd_pdu { struct nvme_command cmd; }; -/** +/* * struct nvme_tcp_rsp_pdu - nvme tcp response capsule pdu * - * @hdr: pdu common header * @hdr: nvme-tcp generic header * @cqe: nvme completion queue entry */ @@ -151,7 +151,7 @@ struct nvme_tcp_rsp_pdu { struct nvme_completion cqe; }; -/** +/* * struct nvme_tcp_r2t_pdu - nvme tcp ready-to-transfer pdu * * @hdr: pdu common header @@ -169,7 +169,7 @@ struct nvme_tcp_r2t_pdu { __u8 rsvd[4]; }; -/** +/* * struct nvme_tcp_data_pdu - nvme tcp data pdu * * @hdr: pdu common header From 97f8cb91a8c5658fe2ae6f5c2ff6e95474a5eb2f Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Wed, 26 Aug 2026 16:56:42 +0200 Subject: [PATCH 0610/1198] drm/panic: clean new `clippy::needless_range_loop` lint for Rust 1.100.0 Starting with Rust 1.100.0 (expected 2026-11-12), Clippy warns: warning: the loop variable `i` is only used to index `self.decimals` --> drivers/gpu/drm/drm_panic_qr.rs:410:18 | 410 | for i in 0..len { | ^^^^^^ | note: for this index operation --> drivers/gpu/drm/drm_panic_qr.rs:411:13 | 411 | self.decimals[i] = (chunk % 10) as u8; | ^^^^^^^^^^^^^^^^ = help: for further information visit https://rust-lang.github.io/rust-clippy/main/index.html#needless_range_loop = note: `-W clippy::needless-range-loop` implied by `-W clippy::all` = help: to override `-W clippy::all` add `#[allow(clippy::needless_range_loop)]` help: consider using an iterator | 410 - for i in 0..len { 410 + for in self.decimals.iter_mut().take(len) { | The lint did not trigger here before because it could not handle arrays behind a field access such as `self.decimals` -- Clippy was improved to catch those cases [1][2]. Thus clean the warning by iterating over a slice rather than using `take()` so that an out-of-range `len` still triggers the same bounds check as the indexed loop. Cc: stable@vger.kernel.org # Needed in 6.18.y and later. Link: https://github.com/rust-lang/rust-clippy/issues/16631 [1] Link: https://github.com/rust-lang/rust-clippy/pull/16634 [2] Assisted-by: LLM Reviewed-by: Alexandre Courbot Reviewed-by: Jocelyn Falempe Link: https://patch.msgid.link/20260826145642.43807-1-ojeda@kernel.org Signed-off-by: Miguel Ojeda --- drivers/gpu/drm/drm_panic_qr.rs | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/drm_panic_qr.rs b/drivers/gpu/drm/drm_panic_qr.rs index ac27e86c601c..4d7eb75a3afc 100644 --- a/drivers/gpu/drm/drm_panic_qr.rs +++ b/drivers/gpu/drm/drm_panic_qr.rs @@ -407,8 +407,8 @@ fn push(&mut self, data: u64, len: usize) { for i in (0..self.len).rev() { self.decimals[i + len] = self.decimals[i]; } - for i in 0..len { - self.decimals[i] = (chunk % 10) as u8; + for decimal in &mut self.decimals[..len] { + *decimal = (chunk % 10) as u8; chunk = div10(chunk); } self.len += len; From 18e5e0ec0e9282c897e2aa81a3e43ccaee03b003 Mon Sep 17 00:00:00 2001 From: Justin Chen Date: Mon, 31 Aug 2026 11:42:34 -0700 Subject: [PATCH 0611/1198] net: bcmasp: clear txcb->last before writing each descriptor bcmasp_xmit() only wrote txcb->last = true for the final fragment of an SKB; non-final fragments left the field untouched. If a descriptor slot was reused while it still held a stale true from a previous SKB (possible when tx_spb_ring_full() underreported fullness), bcmasp_tx_reclaim() would see last == true mid-SKB and call dev_consume_skb_any() prematurely, freeing the sk_buff while its remaining fragments were still in flight. Unconditionally clear txcb->last before the conditional set so every descriptor slot starts from a known false state regardless of what a prior transmission left behind. Fixes: 490cb412007d ("net: bcmasp: Add support for ASP2.0 Ethernet controller") Signed-off-by: Justin Chen Signed-off-by: Danesh Petigara Reviewed-by: Florian Fainelli Link: https://patch.msgid.link/20260831184235.4133351-2-danesh.petigara@broadcom.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c index ed0977832ce4..2bd035f74fa2 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c @@ -301,6 +301,7 @@ static netdev_tx_t bcmasp_xmit(struct sk_buff *skb, struct net_device *dev) txcb->bytes_sent = total_bytes; dma_unmap_addr_set(txcb, dma_addr, mapping); dma_unmap_len_set(txcb, dma_len, size); + txcb->last = false; if (!i) { desc->flags |= DESC_SOF; if (csum_hw) From 0c5cf62e72d7a666ee4da757e122dc1600df1ecc Mon Sep 17 00:00:00 2001 From: Justin Chen Date: Mon, 31 Aug 2026 11:42:35 -0700 Subject: [PATCH 0612/1198] net: bcmasp: fix tx_spb_ring_full() checking same slot cnt times The loop initialised next_index from intf->tx_spb_index on every iteration, so incr_ring() always produced the same result and only one slot was ever tested. Move the initialisation before the loop so each iteration advances next_index and the function correctly checks that cnt consecutive descriptor slots are available before allowing a new transmission. Fixes: 490cb412007d ("net: bcmasp: Add support for ASP2.0 Ethernet controller") Signed-off-by: Justin Chen Signed-off-by: Danesh Petigara Reviewed-by: Florian Fainelli Link: https://patch.msgid.link/20260831184235.4133351-3-danesh.petigara@broadcom.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c index 2bd035f74fa2..f2176ef3a127 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c @@ -148,8 +148,9 @@ static int tx_spb_ring_full(struct bcmasp_intf *intf, int cnt) int next_index, i; /* Check if we have enough room for cnt descriptors */ + next_index = intf->tx_spb_index; for (i = 0; i < cnt; i++) { - next_index = incr_ring(intf->tx_spb_index, DESC_RING_COUNT); + next_index = incr_ring(next_index, DESC_RING_COUNT); if (next_index == intf->tx_spb_clean_index) return 1; } From efdfb1e27a3328085b79540dfe781d537b576ea1 Mon Sep 17 00:00:00 2001 From: Zihan Xi Date: Tue, 1 Sep 2026 10:59:04 +0000 Subject: [PATCH 0613/1198] ipv4: fib: bound automatic table ID allocation fib_empty_table() probes every table ID from 1 until it finds a free one. IPv4 tables are stored in a 256-bucket hash table, so a dense set of IDs makes each probe walk a growing hash chain while RTNL is held. Automatic table assignment ("ip rule ... table 0") is an IPv4-only legacy path. Bound the automatically allocated ID to 4096 so the RTNL hold stays bounded, without changing lookups of explicitly specified table IDs. This changes user-visible behavior. A table-0 rule previously received the lowest free ID in 1..RT_TABLE_MAX (0xFFFFFFFF). After this patch the search stops at 4096 and the rule add fails with ENOBUFS if that range is fully occupied. Explicit table IDs above 4096 remain usable. The automatic path is unused in practice: it is IPv4-only, not documented by ip-rule, uncovered by kernel selftests, and both NetworkManager and systemd refuse table 0. Fixes: b801f54917b7 ("[NET]: Increate RT_TABLE_MAX to 2^32") Cc: stable@vger.kernel.org Reported-by: Vega Suggested-by: Ido Schimmel Signed-off-by: Zihan Xi Reviewed-by: Ido Schimmel Reviewed-by: Petr Vorel Link: https://patch.msgid.link/6f2f2a7a136aee005512a2e1ac8ede62ac8c7bb6.1788258884.git.zihanx@nebusec.ai Signed-off-by: Jakub Kicinski --- net/ipv4/fib_rules.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 4edb0dca7be8..060501b376a8 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -214,6 +214,8 @@ INDIRECT_CALLABLE_SCOPE int fib4_rule_match(struct fib_rule *rule, return 1; } +#define FIB_MAX_AUTO_TABLE_ID 4096 + static struct fib_table *fib_empty_table(struct net *net) { u32 id = 1; @@ -222,7 +224,7 @@ static struct fib_table *fib_empty_table(struct net *net) if (!fib_get_table(net, id)) return fib_new_table(net, id); - if (id++ == RT_TABLE_MAX) + if (id++ == FIB_MAX_AUTO_TABLE_ID) break; } return NULL; From 2ac174dfcdde399fa95ba889541fb5e688d8bb35 Mon Sep 17 00:00:00 2001 From: Taylor Bates Date: Tue, 1 Sep 2026 22:49:46 -0400 Subject: [PATCH 0614/1198] mlxsw: spectrum_ptp: Fix napi_gro_receive() call from GC workqueue context Currently mlxsw_sp1_ptp_ht_gc_collect() is run from the PTP garbage-collection workqueue, rather than the NAPI poll context. For any unmatched PTP entries carrying an SKB, it calls mlxsw_sp1_ptp_unmatched_finish() -> mlxsw_sp1_ptp_packet_finish(). For ingress packets, this calls mlxsw_sp_rx_listener_no_mark_func(). The end of that function is the following: skb->protocol = eth_type_trans(skb, skb->dev); napi_gro_receive(mlxsw_skb_cb(skb)->rx_md_info.napi, skb); The napi pointer is one that was placed in the SKB control block when the trapped packet was received in the NAPI context. Later, when the GC reaps the unmatched entry (up to MLXSW_SP1_PTP_HT_GC_TIMEOUT later), the call to napi_gro_receive() mutates the NAPI instance's GRO list, which is unsafe if the poll is running concurrently on another CPU. In mlxsw_sp1_ptp_ht_gc_collect(), local_bh_disable() is called to prevent softirq processing, but this only applies to the local CPU. Additionally, its comment is stale. It states that mlxsw_sp1_ptp_unmatched_finish() invokes netif_receive_skb(). This has not been accurate since the referenced commit; this patch makes that comment accurate again. mlxsw_pci_napi_devs_init() calls netif_threaded_enable() on the NAPI RX net_device without any conditions. The NAPI instance's poll, which may be running concurrent to the GC, is running as an independently-scheduled kthread which may be on a different CPU. The call to local_bh_disable() does not guard against this. If a tx-timestamp timeout produces an unmatched entry (which can be easily reproduced by running ptp4l and waiting for a port to reach the UNCALIBRATED/SLAVE state) while the owning NAPI thread is in the middle of a poll on another CPU, both sides mutate the GRO list concurrently, as shown below: [39.846] port 1 (swp1): MASTER to UNCALIBRATED on RS_SLAVE list_add corruption. next->prev should be prev (ffff8d620faf4138), but was ffff8d624150f700. (next=ffff8d620faf4138). kernel BUG at lib/list_debug.c:29! Oops: invalid opcode: 0000 [#1] SMP PTI CPU: 1 UID: 0 PID: 539 Comm: napi/mlxsw_rx-0 Not tainted 6.18.48 #1-NixOS PREEMPT(lazy) Hardware name: Mellanox Technologies Ltd. MSN2410/VMOD0001, BIOS 4.6.5 09/13/2018 RIP: 0010:__list_add_valid_or_report+0x79/0xb0 RSP: 0018:ffffcdf8c0f27c08 EFLAGS: 00010246 RAX: 0000000000000075 RBX: ffff8d624150fd00 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff8d6315d1e540 RBP: ffff8d620faf4070 R08: 0000000000000000 R09: 00000000ffffdfff R10: ffffffffa5c60fe0 R11: ffffcdf8c0f27ab8 R12: 0000000000000003 R13: 000000000000003d R14: 00000000000001bc R15: 0000000000000001 FS: 0000000000000000(0000) GS:ffff8d636f63f000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000562689a60c24 CR3: 000000015f224004 CR4: 00000000001726f0 Call Trace: gro_receive_skb+0xee/0x230 mlxsw_sp1_ptp_got_packet+0x61/0x140 [mlxsw_spectrum] mlxsw_core_skb_receive+0xdf/0x1b0 [mlxsw_core] mlxsw_pci_napi_poll_cq_rx+0x780/0x9d0 [mlxsw_pci] __napi_poll+0x31/0x1e0 napi_threaded_poll_loop+0x16b/0x1c0 napi_threaded_poll+0x71/0xa0 kthread+0xfb/0x260 ret_from_fork+0x22d/0x260 ret_from_fork_asm+0x1a/0x30 Kernel panic - not syncing: Fatal exception in interrupt The machinery that leads to this kernel panic has not been changed between 6.18.48 and mainline. This patch adds an ingress-delivery helper for the PTP packet_finish() path that calls netif_receive_skb() instead of napi_gro_receive(). netif_receive_skb(), unlike napi_gro_receive(), can be called from outside of the NAPI instance's poll context, which can occur at the call site for this path. RX stats accounting and the skb->dev assignment are still preserved; the only change is the delivery call itself. This removes GRO batching for any PTP event traffic received by the mlxsw trap, but given the relatively low volume of traffic characteristic of the protocol, and impact limited to only Spectrum-1 ASICs, this is an acceptable solution. Fixes: 1ba06ca96ca2 ("mlxsw: Switch to napi_gro_receive()") Signed-off-by: Taylor Bates Reviewed-by: Petr Machata Link: https://patch.msgid.link/20260902024949.2273997-1-tmbates12@gmail.com Signed-off-by: Jakub Kicinski --- .../ethernet/mellanox/mlxsw/spectrum_ptp.c | 34 ++++++++++++++++++- 1 file changed, 33 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c index 9939749c47bc..9c5862f4e16a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c @@ -572,6 +572,38 @@ mlxsw_sp1_ptp_unmatched_remove(struct mlxsw_sp *mlxsw_sp, mlxsw_sp1_ptp_unmatched_ht_params); } +/* mlxsw_sp1_ptp_packet_finish() is reached both from the NAPI poll context + * (mlxsw_sp1_ptp_got_packet(), mlxsw_sp1_ptp_got_piece() and + * mlxsw_sp1_packet_timestamp()) and from process context, by way of the GC + * workqueue (mlxsw_sp1_ptp_ht_gc_collect() -> + * mlxsw_sp1_ptp_unmatched_finish()). + * + * mlxsw_sp_rx_listener_no_mark_func() ends in napi_gro_receive(), using the + * NAPI pointer that was placed in the SKB control block when the trapped + * packet was received in the NAPI context. That pointer may only be used + * from its own poll context, which this call site cannot guarantee. + * + * netif_receive_skb(), unlike napi_gro_receive(), can be called from outside + * of the NAPI instance's poll context. RX stats accounting and the skb->dev + * assignment are still preserved; the only change is the delivery call. + */ +static void mlxsw_sp1_ptp_rx_finish(struct mlxsw_sp_port *mlxsw_sp_port, + struct sk_buff *skb) +{ + struct mlxsw_sp_port_pcpu_stats *pcpu_stats; + + skb->dev = mlxsw_sp_port->dev; + + pcpu_stats = this_cpu_ptr(mlxsw_sp_port->pcpu_stats); + u64_stats_update_begin(&pcpu_stats->syncp); + pcpu_stats->rx_packets++; + pcpu_stats->rx_bytes += skb->len; + u64_stats_update_end(&pcpu_stats->syncp); + + skb->protocol = eth_type_trans(skb, skb->dev); + netif_receive_skb(skb); +} + /* This function is called in the following scenarios: * * 1) When a packet is matched with its timestamp. @@ -600,7 +632,7 @@ static void mlxsw_sp1_ptp_packet_finish(struct mlxsw_sp *mlxsw_sp, if (ingress) { if (hwtstamps) *skb_hwtstamps(skb) = *hwtstamps; - mlxsw_sp_rx_listener_no_mark_func(skb, local_port, mlxsw_sp); + mlxsw_sp1_ptp_rx_finish(mlxsw_sp_port, skb); } else { /* skb_tstamp_tx() allows hwtstamps to be NULL. */ skb_tstamp_tx(skb, hwtstamps); From 6a1094c34d176827b2b173e163dcc964a13af93f Mon Sep 17 00:00:00 2001 From: XingWang Xiang Date: Wed, 2 Sep 2026 17:43:17 +0900 Subject: [PATCH 0615/1198] genetlink: pin family module during policy dump The generic netlink controller's policy dump keeps pointers to the target family's operation and policy tables in its callback state. A dump may be split across multiple skbs and remain pending after the initial request. Netlink pins the module which owns the dump callback, but in this case that is the controller's owner rather than the target family's owner. The target family can consequently be unregistered and its module unloaded while a policy dump is pending. Advancing the dump then dereferences policy memory from the unloaded module. Take a reference to the target family's module when the dump starts. Drop it from the error and done paths. This matches the lifetime for which the dump context retains the family and policy pointers. Fixes: d07dcf9aadd6 ("netlink: add infrastructure to expose policies to userspace") Cc: stable@vger.kernel.org Signed-off-by: XingWang Xiang Link: https://patch.msgid.link/20260902084317.4092542-1-v3rdant.xiang@gmail.com Signed-off-by: Jakub Kicinski --- net/netlink/genetlink.c | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 0da39eaed255..41d37442f186 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -1513,6 +1513,7 @@ struct ctrl_dump_policy_ctx { struct netlink_policy_dump_state *state; const struct genl_family *rt; struct genl_op_iter *op_iter; + struct module *owner; u32 op; u16 fam_id; u8 dump_map:1, @@ -1555,6 +1556,9 @@ static int ctrl_dumppolicy_start(struct netlink_callback *cb) return -ENOENT; ctx->rt = rt; + ctx->owner = rt->module; + if (!try_module_get(ctx->owner)) + return -ENOENT; if (tb[CTRL_ATTR_OP]) { struct genl_split_ops doit, dump; @@ -1565,7 +1569,7 @@ static int ctrl_dumppolicy_start(struct netlink_callback *cb) err = genl_get_cmd_both(ctx->op, rt, &doit, &dump); if (err) { NL_SET_BAD_ATTR(cb->extack, tb[CTRL_ATTR_OP]); - return err; + goto err_put_owner; } if (doit.policy) { @@ -1583,16 +1587,20 @@ static int ctrl_dumppolicy_start(struct netlink_callback *cb) goto err_free_state; } - if (!ctx->state) - return -ENODATA; + if (!ctx->state) { + err = -ENODATA; + goto err_put_owner; + } ctx->dump_map = 1; return 0; } ctx->op_iter = kmalloc_obj(*ctx->op_iter); - if (!ctx->op_iter) - return -ENOMEM; + if (!ctx->op_iter) { + err = -ENOMEM; + goto err_put_owner; + } genl_op_iter_init(rt, ctx->op_iter); ctx->dump_map = genl_op_iter_next(ctx->op_iter); @@ -1624,6 +1632,8 @@ static int ctrl_dumppolicy_start(struct netlink_callback *cb) netlink_policy_dump_free(ctx->state); err_free_op_iter: kfree(ctx->op_iter); +err_put_owner: + module_put(ctx->owner); return err; } @@ -1760,6 +1770,7 @@ static int ctrl_dumppolicy_done(struct netlink_callback *cb) kfree(ctx->op_iter); netlink_policy_dump_free(ctx->state); + module_put(ctx->owner); return 0; } From b58d749633203d92c265317b45fccee555090352 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 2 Sep 2026 22:01:12 +0300 Subject: [PATCH 0616/1198] tunnels: Drop stale dst when building an ICMP error for PMTUD Bridged UDP tunnels such as VXLAN and GENEVE build an ICMP error packet around an overlay packet if the packet is going to exceed the underlay path MTU. The ICMP error packet is then injected back into the Rx path with the source and destination addresses swapped, so that it will be delivered to the overlay source. If the overlay packet was routed to the UDP tunnel or locally generated, then it is already carrying a valid dst entry and this entry is not dropped when transforming the packet to an ICMP error packet. This causes the IP layer to reuse the dst entry, leading to the ICMP error packet being dropped or routed out of the UDP tunnel interface in case of forwarding. Prior to the blamed commit this could not happen, as skb_tunnel_check_pmtu() did not build ICMP errors for PACKET_HOST packets. Such packets were instead encapsulated and, unless the DF bit was set in the outer header, fragmented by the underlay. Fix this by making sure that the ICMP error packet does not have a valid dst entry, thereby forcing the IP layer to perform a route lookup. Adjust the bridged PMTU exception selftests accordingly. When the local sender in ns_a pings the overlay destination with a deadline (-w), ping exits on the first socket error before any reply is received and returns a non-zero exit code. The test therefore only passed because the ICMP error was never delivered. Use a packet count (-c) like the ns_c line above it, so that the ICMP error counts against the packet budget and the exit code depends on whether echo replies were received. This passes with and without the fix. Fixes: 8930424777e4 ("tunnels: Accept PACKET_HOST in skb_tunnel_check_pmtu().") Cc: stable@vger.kernel.org Reported-by: Laika Price Closes: https://lore.kernel.org/netdev/20260614-master-v3-1-9f5060ba1ed1@gmail.com/ Reported-by: Yaroslav Dudkov Closes: https://lore.kernel.org/netdev/20260901081825.287173-1-aroslavdudkov622@gmail.com/ Reported-by: Charles Bordet Closes: https://lore.kernel.org/netdev/aHVhQLPJIhq-SYPM@eldamar.lan/ Signed-off-by: Ido Schimmel Tested-by: Yaroslav Dudkov Reviewed-by: David Ahern Reviewed-by: Stefano Brivio Reviewed-by: Guillaume Nault Link: https://patch.msgid.link/20260902190112.4126199-1-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- net/ipv4/ip_tunnel_core.c | 6 ++++++ tools/testing/selftests/net/pmtu.sh | 2 +- 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index d3c677e9bff2..5168d546ea2f 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -268,6 +268,9 @@ static int iptunnel_pmtud_build_icmp(struct sk_buff *skb, int mtu) eth_header(skb, skb->dev, ntohs(eh.h_proto), eh.h_source, eh.h_dest, 0); skb_reset_mac_header(skb); + if (skb_valid_dst(skb)) + skb_dst_drop(skb); + return skb->len; } @@ -371,6 +374,9 @@ static int iptunnel_pmtud_build_icmpv6(struct sk_buff *skb, int mtu) eth_header(skb, skb->dev, ntohs(eh.h_proto), eh.h_source, eh.h_dest, 0); skb_reset_mac_header(skb); + if (skb_valid_dst(skb)) + skb_dst_drop(skb); + return skb->len; } diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index a3323c21f001..c7cd271714ef 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -1457,7 +1457,7 @@ test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception() { mtu "${ns_b}" ${type}_b $((${ll_mtu} + 1000)) run_cmd ${ns_c} ${ping} -q -M want -i 0.1 -c 10 -s $((${ll_mtu} + 500)) ${dst} || return 1 - run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${dst} || return 1 + run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -c 10 -s $((${ll_mtu} + 500)) ${dst} || return 1 # Check that exceptions were created pmtu="$(route_get_dst_pmtu_from_exception "${ns_c}" ${dst})" From a09ceadff95b0075a9b6a5d9dbeb6c1c5f311c60 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 1 Sep 2026 11:21:24 +0200 Subject: [PATCH 0617/1198] mailmap: add entries for Lorenzo Bianconi Add the active email address for Lorenzo Bianconi and map the old, no-longer-used addresses to it, so that git can attribute his contributions to a single identity. This is done to avoid bouncing emails sent to email addresses that are no longer active. Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20260901-lorenzo-mailmap-v2-1-0ee832de0caf@kernel.org Signed-off-by: Jakub Kicinski --- .mailmap | 3 +++ 1 file changed, 3 insertions(+) diff --git a/.mailmap b/.mailmap index 6803f3bd2865..5fd5c834e0ac 100644 --- a/.mailmap +++ b/.mailmap @@ -550,6 +550,9 @@ Li Yang Lior David Loic Poulain Loic Poulain +Lorenzo Bianconi +Lorenzo Bianconi +Lorenzo Bianconi Lorenzo Pieralisi Lorenzo Stoakes Lorenzo Stoakes From 39b23c1c40e1f73d2b94a09282cc476af647e438 Mon Sep 17 00:00:00 2001 From: Joe Damato Date: Wed, 2 Sep 2026 14:39:54 -0700 Subject: [PATCH 0618/1198] bnxt_en: Prevent queue stop with deferred completions When the driver receives a burst of packets, it can mark a BD with the NO_CMPL bit to defer completions. The expectation is that the last packet in the ring will have this bit unset and the completion generated by that packet will cleanup that packet and the ones preceding it. This helps to reduce the number of completions fired. The suppressed completions are controlled by the driver and the number of packets with suppressed completions scales with the size of the ring. SW USO packets, on the other hand, have an upper bound on the maximum number of BDs which can be consumed which does not scale with the ring size. So, for small rings it is possible that: a burst of packets is handed to the driver, the driver defers completions for all of the packets because the number of free descriptors stays above the threshold in the driver. Then, a USO packet arrives, but the number of BDs available is not enough and the USO code exits early. In this case, you end up in a state where the ring is full of packets with their completions suppressed, which can cause the queue to stop and never be restarted. Assuming default CONFIG_MAX_SKB_FRAGS, this is only possible for small rings (<= 457 descriptors, below the driver default value) when a burst of packets fills the ring, followed by a large USO packet that can't fit. For larger rings, the delta between the completion suppression threshold and the BDs required for SW USO is large enough that completions will fire and this case is unreachable. This issue was pointed out by Sashiko and while it seems fairly unlikely given that the queue size must be small to trigger this, it is indeed possible. Fix this by tracking the last BD which deferred completions and centralizing the logic for deciding when to ring the doorbell. The NO_CMPL bit is now cleared in bnxt_txr_db_kick(), so every doorbell site is covered, including the SW USO early exit. This guarantees the ring always ends in a BD which generates a completion to clean it and wake the queue. Fixes: cc5d90667db8 ("net: bnxt: Implement software USO") Cc: # v7.1+: 4e15e89faac9: net: bnxt: ring the doorbell when SW USO exits early Signed-off-by: Joe Damato Link: https://patch.msgid.link/20260902213956.4160615-1-joe@dama.to Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 42 +++++++++++++++---- drivers/net/ethernet/broadcom/bnxt/bnxt.h | 1 + drivers/net/ethernet/broadcom/bnxt/bnxt_gso.c | 21 ++++++---- drivers/net/ethernet/broadcom/bnxt/bnxt_gso.h | 6 +-- 4 files changed, 48 insertions(+), 22 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index d59bcca73a2b..8c6e2ee6bee4 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -462,6 +462,16 @@ u16 bnxt_xmit_get_cfa_action(struct sk_buff *skb) static void bnxt_txr_db_kick(struct bnxt *bp, struct bnxt_tx_ring_info *txr, u16 prod) { + /* If the most recent BD has its completion suppressed, unset the bit + * so that a completion is generated, otherwise nothing is left to + * clean the ring and wake the queue. + */ + if (txr->kick_txbd0) { + txr->kick_txbd0->tx_bd_len_flags_type &= + cpu_to_le32(~TX_BD_FLAGS_NO_CMPL); + txr->kick_txbd0 = NULL; + } + /* Sync BD data before updating doorbell */ wmb(); bnxt_db_write(bp, &txr->tx_db, prod); @@ -485,7 +495,6 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev) struct bnxt_sw_tx_bd *tx_buf; __le32 lflags = 0; skb_frag_t *frag; - netdev_tx_t ret; i = skb_get_queue_mapping(skb); if (unlikely(i >= bp->tx_nr_rings)) { @@ -509,11 +518,22 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev) if (skb_is_gso(skb) && (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) && !(bp->flags & BNXT_FLAG_UDP_GSO_CAP)) { - ret = bnxt_sw_udp_gso_xmit(bp, txr, txq, skb); - if (txr->kick_pending) + int rc = bnxt_sw_udp_gso_xmit(bp, txr, txq, skb); + + /* if SW USO queued a packet, the doorbell will be written + * below and there is no reason to track the last BD with + * suppressed completions + */ + if (rc > 0) + txr->kick_txbd0 = NULL; + + /* if a packet was queued by SW USO or a doorbell was pending + * from a previous xmit that was deferred, write the doorbell. + */ + if (rc > 0 || txr->kick_pending) bnxt_txr_db_kick(bp, txr, txr->tx_prod); - return ret; + return rc < 0 ? NETDEV_TX_BUSY : NETDEV_TX_OK; } free_size = bnxt_tx_avail(bp, txr); @@ -751,23 +771,23 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev) prod = NEXT_TX(prod); WRITE_ONCE(txr->tx_prod, prod); + txr->kick_txbd0 = NULL; if (!netdev_xmit_more() || netif_xmit_stopped(txq)) { bnxt_txr_db_kick(bp, txr, prod); } else { - if (free_size >= bp->tx_wake_thresh) + if (free_size >= bp->tx_wake_thresh) { txbd0->tx_bd_len_flags_type |= cpu_to_le32(TX_BD_FLAGS_NO_CMPL); + txr->kick_txbd0 = txbd0; + } txr->kick_pending = 1; } tx_done: if (unlikely(bnxt_tx_avail(bp, txr) <= MAX_SKB_FRAGS + 1)) { - if (netdev_xmit_more() && !tx_buf->is_push) { - txbd0->tx_bd_len_flags_type &= - cpu_to_le32(~TX_BD_FLAGS_NO_CMPL); + if (txr->kick_pending) bnxt_txr_db_kick(bp, txr, prod); - } netif_txq_try_stop(txq, bnxt_tx_avail(bp, txr), bp->tx_wake_thresh); @@ -5427,6 +5447,8 @@ static void bnxt_clear_ring_indices(struct bnxt *bp) txr->tx_prod = 0; txr->tx_cons = 0; txr->tx_hw_cons = 0; + txr->kick_pending = 0; + txr->kick_txbd0 = NULL; } rxr = bnapi->rx_ring; @@ -11772,6 +11794,8 @@ static int bnxt_tx_queue_start(struct bnxt *bp, int idx) txr->tx_prod = 0; txr->tx_cons = 0; txr->tx_hw_cons = 0; + txr->kick_pending = 0; + txr->kick_txbd0 = NULL; start_tx: WRITE_ONCE(txr->dev_state, 0); synchronize_net(); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index ab894f8addef..dc5a16ec5943 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -993,6 +993,7 @@ struct bnxt_tx_ring_info { u16 txq_index; u8 tx_napi_idx; u8 kick_pending; + struct tx_bd *kick_txbd0; struct bnxt_db_info tx_db; struct tx_bd *tx_desc_ring[MAX_TX_PAGES]; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_gso.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_gso.c index f7e18bea0fb8..6c1060fa2ea5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_gso.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_gso.c @@ -31,10 +31,14 @@ static u32 bnxt_sw_gso_lhint(unsigned int len) return TX_BD_FLAGS_LHINT_2048_AND_LARGER; } -netdev_tx_t bnxt_sw_udp_gso_xmit(struct bnxt *bp, - struct bnxt_tx_ring_info *txr, - struct netdev_queue *txq, - struct sk_buff *skb) +/* Transmit an skb requiring software UDP segmentation. + * + * Returns 1 if the skb was queued and new BDs were produced, 0 if the skb + * was dropped, or -1 if the ring is full and the skb should be retried. + * The caller owns the doorbell for all three cases. + */ +int bnxt_sw_udp_gso_xmit(struct bnxt *bp, struct bnxt_tx_ring_info *txr, + struct netdev_queue *txq, struct sk_buff *skb) { unsigned int last_unmap_len __maybe_unused = 0; dma_addr_t last_unmap_addr __maybe_unused = 0; @@ -69,7 +73,7 @@ netdev_tx_t bnxt_sw_udp_gso_xmit(struct bnxt *bp, if (unlikely(bnxt_tx_avail(bp, txr) < bds_needed)) { netif_txq_try_stop(txq, bnxt_tx_avail(bp, txr), bp->tx_wake_thresh); - return NETDEV_TX_BUSY; + return -1; } /* BD backpressure alone cannot prevent overwriting in-flight @@ -77,7 +81,7 @@ netdev_tx_t bnxt_sw_udp_gso_xmit(struct bnxt *bp, */ if (!netif_txq_maybe_stop(txq, bnxt_inline_avail(txr), num_segs, num_segs)) - return NETDEV_TX_BUSY; + return -1; if (unlikely(tso_dma_map_init(&map, &pdev->dev, skb, hdr_len))) goto drop; @@ -223,16 +227,15 @@ netdev_tx_t bnxt_sw_udp_gso_xmit(struct bnxt *bp, netdev_tx_sent_queue(txq, skb->len); WRITE_ONCE(txr->tx_prod, prod); - txr->kick_pending = 1; if (unlikely(bnxt_tx_avail(bp, txr) <= bp->tx_wake_thresh)) netif_txq_try_stop(txq, bnxt_tx_avail(bp, txr), bp->tx_wake_thresh); - return NETDEV_TX_OK; + return 1; drop: dev_kfree_skb_any(skb); dev_core_stats_tx_dropped_inc(bp->dev); - return NETDEV_TX_OK; + return 0; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_gso.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_gso.h index 47528c20f311..77d9af97cc22 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_gso.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_gso.h @@ -38,9 +38,7 @@ static inline int bnxt_min_tx_desc_cnt(struct bnxt *bp, return BNXT_MIN_TX_DESC_CNT; } -netdev_tx_t bnxt_sw_udp_gso_xmit(struct bnxt *bp, - struct bnxt_tx_ring_info *txr, - struct netdev_queue *txq, - struct sk_buff *skb); +int bnxt_sw_udp_gso_xmit(struct bnxt *bp, struct bnxt_tx_ring_info *txr, + struct netdev_queue *txq, struct sk_buff *skb); #endif From 4814ed6406f3493bd554ad046da5f7fc04833571 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Thu, 3 Sep 2026 10:15:39 -0700 Subject: [PATCH 0619/1198] bpf: zero extend the result of an arena 32-bit cmpxchg bpf_convert_ctx_accesses() rewrites an atomic on an arena pointer from BPF_STX | BPF_ATOMIC to BPF_STX | BPF_PROBE_ATOMIC, and it runs before bpf_opt_subreg_zext_lo32_rnd_hi32(). That pass emits an explicit zero extension for a 32-bit cmpxchg even when bpf_jit_needs_zext() is false. This is done because on some architectures 32-bit cmpxchg requires explicit zero extension for the dst register. E.g. on x86-64 'lock cmpxchg' does not change the %eax if comparison is successful, while BPF semantics declare that each operation on a 32-bit register zero extends it's upper half. is_cmpxchg_insn() matches BPF_MODE == BPF_ATOMIC only, so an arena cmpxchg misses said zero extension adjustment. This patch adjusts is_cmpxchg_insn() to match BPF_PROBE_ATOMIC alongside BPF_ATOMIC. Fixes: d503a04f8bc0 ("bpf: Add support for certain atomics in bpf_arena to x86 JIT") Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260903171542.1438050-1-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/fixups.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/kernel/bpf/fixups.c b/kernel/bpf/fixups.c index 65b441e4a351..52d3cec33672 100644 --- a/kernel/bpf/fixups.c +++ b/kernel/bpf/fixups.c @@ -13,10 +13,15 @@ #define verbose(env, fmt, args...) bpf_verifier_log_write(env, fmt, ##args) +/* + * Matches BPF_PROBE_ATOMIC too: bpf_convert_ctx_accesses() rewrites arena + * atomics before bpf_opt_subreg_zext_lo32_rnd_hi32() runs. + */ static bool is_cmpxchg_insn(const struct bpf_insn *insn) { return BPF_CLASS(insn->code) == BPF_STX && - BPF_MODE(insn->code) == BPF_ATOMIC && + (BPF_MODE(insn->code) == BPF_ATOMIC || + BPF_MODE(insn->code) == BPF_PROBE_ATOMIC) && insn->imm == BPF_CMPXCHG; } From 1f3cd9719c40715a7d6328bdbef817d5731bf61c Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Thu, 3 Sep 2026 10:15:40 -0700 Subject: [PATCH 0620/1198] bpf: update disasm.c to print BPF_PROBE_ATOMIC as atomics bpf_convert_ctx_accesses() rewrites an atomic on an arena pointer from BPF_STX | BPF_ATOMIC to BPF_STX | BPF_PROBE_ATOMIC, this patch adjusts print_bpf_insn() to print such instructions as regular atomics with a 'probe_' prefix (instead of printing them as BUG_XX). Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260903171542.1438050-2-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/disasm.c | 47 ++++++++++++++++++++++++--------------------- 1 file changed, 25 insertions(+), 22 deletions(-) diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index b1a3fbe3fda5..3ce8d74b0e40 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -7,6 +7,9 @@ #include "disasm.h" +/* Only defined by the non-UAPI linux/filter.h, which this file cannot use. */ +#define BPF_PROBE_ATOMIC 0xe0 + #define __BPF_FUNC_STR_FN(x) [BPF_FUNC_ ## x] = __stringify(bpf_ ## x) static const char * const func_id_str[] = { __BPF_FUNC_MAPPER(__BPF_FUNC_STR_FN) @@ -226,57 +229,57 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, insn->imm); } } else if (class == BPF_STX) { + const char *probe_pfx = BPF_MODE(insn->code) == BPF_PROBE_ATOMIC ? "probe " : ""; + bool atomic = BPF_MODE(insn->code) == BPF_ATOMIC || + BPF_MODE(insn->code) == BPF_PROBE_ATOMIC; + if (BPF_MODE(insn->code) == BPF_MEM) verbose(cbs->private_data, "(%02x) *(%s *)(r%d %+d) = r%d", insn->code, bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, insn->src_reg); - else if (BPF_MODE(insn->code) == BPF_ATOMIC && + else if (atomic && (insn->imm == BPF_ADD || insn->imm == BPF_AND || insn->imm == BPF_OR || insn->imm == BPF_XOR)) { - verbose(cbs->private_data, "(%02x) lock *(%s *)(r%d %+d) %s r%d", - insn->code, + verbose(cbs->private_data, "(%02x) %slock *(%s *)(r%d %+d) %s r%d", + insn->code, probe_pfx, bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, bpf_alu_string[BPF_OP(insn->imm) >> 4], insn->src_reg); - } else if (BPF_MODE(insn->code) == BPF_ATOMIC && + } else if (atomic && (insn->imm == (BPF_ADD | BPF_FETCH) || insn->imm == (BPF_AND | BPF_FETCH) || insn->imm == (BPF_OR | BPF_FETCH) || insn->imm == (BPF_XOR | BPF_FETCH))) { - verbose(cbs->private_data, "(%02x) r%d = atomic%s_fetch_%s((%s *)(r%d %+d), r%d)", - insn->code, insn->src_reg, + verbose(cbs->private_data, "(%02x) %sr%d = atomic%s_fetch_%s((%s *)(r%d %+d), r%d)", + insn->code, probe_pfx, insn->src_reg, BPF_SIZE(insn->code) == BPF_DW ? "64" : "", bpf_atomic_alu_string[BPF_OP(insn->imm) >> 4], bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, insn->src_reg); - } else if (BPF_MODE(insn->code) == BPF_ATOMIC && - insn->imm == BPF_CMPXCHG) { - verbose(cbs->private_data, "(%02x) r0 = atomic%s_cmpxchg((%s *)(r%d %+d), r0, r%d)", - insn->code, + } else if (atomic && insn->imm == BPF_CMPXCHG) { + verbose(cbs->private_data, "(%02x) %sr0 = atomic%s_cmpxchg((%s *)(r%d %+d), r0, r%d)", + insn->code, probe_pfx, BPF_SIZE(insn->code) == BPF_DW ? "64" : "", bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, insn->src_reg); - } else if (BPF_MODE(insn->code) == BPF_ATOMIC && - insn->imm == BPF_XCHG) { - verbose(cbs->private_data, "(%02x) r%d = atomic%s_xchg((%s *)(r%d %+d), r%d)", - insn->code, insn->src_reg, + } else if (atomic && insn->imm == BPF_XCHG) { + verbose(cbs->private_data, "(%02x) %sr%d = atomic%s_xchg((%s *)(r%d %+d), r%d)", + insn->code, probe_pfx, insn->src_reg, BPF_SIZE(insn->code) == BPF_DW ? "64" : "", bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, insn->src_reg); - } else if (BPF_MODE(insn->code) == BPF_ATOMIC && - insn->imm == BPF_LOAD_ACQ) { - verbose(cbs->private_data, "(%02x) r%d = load_acquire((%s *)(r%d %+d))", - insn->code, insn->dst_reg, + } else if (atomic && insn->imm == BPF_LOAD_ACQ) { + verbose(cbs->private_data, "(%02x) %sr%d = load_acquire((%s *)(r%d %+d))", + insn->code, probe_pfx, insn->dst_reg, bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->src_reg, insn->off); - } else if (BPF_MODE(insn->code) == BPF_ATOMIC && - insn->imm == BPF_STORE_REL) { - verbose(cbs->private_data, "(%02x) store_release((%s *)(r%d %+d), r%d)", - insn->code, + } else if (atomic && insn->imm == BPF_STORE_REL) { + verbose(cbs->private_data, "(%02x) %sstore_release((%s *)(r%d %+d), r%d)", + insn->code, probe_pfx, bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, insn->src_reg); } else { From 54ed91950363c116bec9be1b7015ff2bfa989950 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Thu, 3 Sep 2026 10:15:41 -0700 Subject: [PATCH 0621/1198] selftests/bpf: check zero extension of an arena 32-bit cmpxchg Add a test to verify that destination register of a 32-bit cmpxchg operating on an arena pointer is explicitly zero extended. W/o patch #1 this did not happen. Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260903171542.1438050-3-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov --- .../selftests/bpf/progs/verifier_zext.c | 26 +++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/verifier_zext.c b/tools/testing/selftests/bpf/progs/verifier_zext.c index 8f2362da91d6..572017fe28fb 100644 --- a/tools/testing/selftests/bpf/progs/verifier_zext.c +++ b/tools/testing/selftests/bpf/progs/verifier_zext.c @@ -356,6 +356,32 @@ __naked void arena_ptr(void) : __clobber_all); } +/* + * Result of a 32-bit cmpxchg is always explicitly zero extended. + * Check that this holds for arenas (BPF_PROBE_ATOMIC instruction flavor). + */ +SEC("socket") +__success +__xlated("probe r0 = atomic_cmpxchg((u32 *)(r1 +0), r0, r2)") +__xlated("w0 = w0") +__naked void zext_arena_cmpxchg32(void) +{ + asm volatile (" \ + r9 = %[arena] ll; /* associate the arena with the program */ \ + r1 = 0; \ + r1 = addr_space_cast(r1, 0, 1); \ + r0 = 0; \ + r2 = 0; \ + .8byte %[cmpxchg32]; \ + r0 >>= 32; /* make the upper half live */ \ + exit; \ +" : + : __imm_addr(arena), + __imm_insn(cmpxchg32, + BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, BPF_REG_1, BPF_REG_2, 0)) + : __clobber_all); +} + #endif /* Check if probe mem loads keep their zero extension. */ From 0b1c83dc3c4401cd7e846548f62e3caf3d06742e Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Thu, 3 Sep 2026 13:58:19 -0700 Subject: [PATCH 0622/1198] bpf: don't rewrite bpf_fastcall patterns entered by a jump mark_fastcall_pattern_for_call() must ensure that matched "spill; call; fill" instruction series is not interrupted by a jump. Otherwise the rewrite applied by bpf_remove_fastcall_spills_fills() is not sound. Record the instructions targeted by jumps in insn_aux_data[*].jump_target when the CFG is built and use this flag to stop growing a pattern at such an instruction. Jumps to the first spill are fine. Note that existing insn_aux_data[*].jmp_point field can't be reused, as it marks subprogram return instructions. Fixes: 5b5f51bff1b6 ("bpf: no_caller_saved_registers attribute for helper calls") Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260903205820.1743087-1-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 12 ++++++++++++ kernel/bpf/cfg.c | 3 +++ kernel/bpf/verifier.c | 8 ++++++++ 3 files changed, 23 insertions(+) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 5fad59fdab0d..1339c2f028db 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -706,6 +706,8 @@ struct bpf_insn_aux_data { */ u32 calls_callback:1; u32 indirect_target:1; /* if it is an indirect jump target */ + /* true if some jump or call instruction targets this instruction */ + u32 jump_target:1; /* * CFG strongly connected component this instruction belongs to, * zero if it is a singleton SCC. @@ -1142,6 +1144,16 @@ static inline void mark_jmp_point(struct bpf_verifier_env *env, int idx) env->insn_aux_data[idx].jmp_point = true; } +static inline void mark_jump_target(struct bpf_verifier_env *env, int idx) +{ + env->insn_aux_data[idx].jump_target = true; +} + +static inline bool bpf_is_jump_target(struct bpf_verifier_env *env, int insn_idx) +{ + return env->insn_aux_data[insn_idx].jump_target; +} + static inline struct bpf_func_state *cur_func(struct bpf_verifier_env *env) { struct bpf_verifier_state *cur = env->cur_state; diff --git a/kernel/bpf/cfg.c b/kernel/bpf/cfg.c index 0f13c13f4133..842c7d1eabcc 100644 --- a/kernel/bpf/cfg.c +++ b/kernel/bpf/cfg.c @@ -125,6 +125,7 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env) /* mark branch target for state pruning */ mark_prune_point(env, w); mark_jmp_point(env, w); + mark_jump_target(env, w); } if (insn_state[w] == 0) { @@ -403,6 +404,7 @@ static int visit_gotox_insn(int t, struct bpf_verifier_env *env) } mark_jmp_point(env, w); + mark_jump_target(env, w); /* EXPLORED || DISCOVERED */ if (insn_state[w]) @@ -564,6 +566,7 @@ static int visit_insn(int t, struct bpf_verifier_env *env) mark_prune_point(env, t + off + 1); mark_jmp_point(env, t + off + 1); + mark_jump_target(env, t + off + 1); return ret; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 32d31fa67036..2ed17edf77f2 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -17656,6 +17656,10 @@ bool bpf_get_call_summary(struct bpf_verifier_env *env, struct bpf_insn *call, * r0 = *(u64 *)(r10 - 8); r0 += r1; * r0 += r1; exit; * exit; + * + * Both uses of the marks assume that a pattern is entered at its first + * spill and thus executes as a unit, hence a pattern is not grown past + * an instruction targeted by a jump. */ static void mark_fastcall_pattern_for_call(struct bpf_verifier_env *env, struct bpf_subprog_info *subprog, @@ -17694,6 +17698,10 @@ static void mark_fastcall_pattern_for_call(struct bpf_verifier_env *env, for (i = 1, off = lowest_off; i <= ARRAY_SIZE(caller_saved); ++i, off += BPF_REG_SIZE) { if (insn_idx - i < 0 || insn_idx + i >= env->prog->len) break; + /* stx/ldx/call must not be a jump targets, a jump to the first stx is fine */ + if (bpf_is_jump_target(env, insn_idx - i + 1) || + bpf_is_jump_target(env, insn_idx + i)) + break; stx = &insns[insn_idx - i]; ldx = &insns[insn_idx + i]; /* must be a stack spill/fill pair */ From 65b1518c995c590ab01f1e87f37d4eb47e8d050f Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Thu, 3 Sep 2026 13:58:20 -0700 Subject: [PATCH 0623/1198] selftests/bpf: bpf_fastcall patterns entered by a jump Check bpf_fastcall pattern detection when the pattern is entered at an instruction other than the first spill: - a jump to the first spill allows the rewrite; - conditional/unconditional a jump to the call or to the fill does not allow the rewrite. Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260903205820.1743087-2-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov --- .../bpf/progs/verifier_bpf_fastcall.c | 110 ++++++++++++++++++ 1 file changed, 110 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c index 328cf630210a..a73b837553fb 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c +++ b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c @@ -621,6 +621,116 @@ __naked void helper_call_does_not_prevent_bpf_fastcall(void) : __clobber_all); } +/* A jump to the first spill executes the whole pattern, rewrite is safe. */ +SEC("raw_tp") +__arch_x86_64 +__log_level(4) +__msg("subprog 0 (jump_to_first_spill) main {{.*}} stack 0") +__xlated("2: if r0 == 0x2a goto pc+0") +__xlated("3: r0 = ") +__xlated("4: r0 = &(void __percpu *)(r0)") +__success +__naked void jump_to_first_spill(void) +{ + asm volatile ( + "call %[bpf_get_prandom_u32];" + "r1 = 1;" + "if r0 == 42 goto l0_%=;" +"l0_%=:" + "*(u64 *)(r10 - 8) = r1;" + "call %[bpf_get_smp_processor_id];" + "r1 = *(u64 *)(r10 - 8);" + "exit;" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_get_smp_processor_id) + : __clobber_all); +} + +/* A jump to the call skips the spill, the pattern must be kept. */ +SEC("raw_tp") +__arch_x86_64 +__log_level(4) +__msg("subprog 0 (jump_to_call) main {{.*}} stack 8") +__xlated("2: if r0 == 0x2a goto pc+1") +__xlated("3: *(u64 *)(r10 -8) = r1") +__xlated("...") +__xlated("7: r1 = *(u64 *)(r10 -8)") +__success +__naked void jump_to_call(void) +{ + asm volatile ( + "call %[bpf_get_prandom_u32];" + "r1 = 1;" + "if r0 == 42 goto l0_%=;" + "*(u64 *)(r10 - 8) = r1;" +"l0_%=:" + "call %[bpf_get_smp_processor_id];" + "r1 = *(u64 *)(r10 - 8);" + "exit;" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_get_smp_processor_id) + : __clobber_all); +} + +/* A jump to the fill skips the spill, the pattern must be kept. */ +SEC("raw_tp") +__arch_x86_64 +__log_level(4) +__msg("subprog 0 (jump_to_fill) main {{.*}} stack 8") +__xlated("2: if r0 == 0x2a goto pc+4") +__xlated("3: *(u64 *)(r10 -8) = r1") +__xlated("...") +__xlated("7: r1 = *(u64 *)(r10 -8)") +__success +__naked void jump_to_fill(void) +{ + asm volatile ( + "call %[bpf_get_prandom_u32];" + "r1 = 1;" + "if r0 == 42 goto l0_%=;" + "*(u64 *)(r10 - 8) = r1;" + "call %[bpf_get_smp_processor_id];" +"l0_%=:" + "r1 = *(u64 *)(r10 - 8);" + "exit;" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_get_smp_processor_id) + : __clobber_all); +} + +/* Same as above, but the fill is entered by an unconditional jump. */ +SEC("raw_tp") +__arch_x86_64 +__log_level(4) +__msg("subprog 0 (unconditional_jump_to_fill) main {{.*}} stack 8") +__xlated("3: *(u64 *)(r10 -8) = r1") +__xlated("...") +__xlated("7: r1 = *(u64 *)(r10 -8)") +__xlated("8: exit") +__xlated("9: goto pc-3") +__success +__naked void unconditional_jump_to_fill(void) +{ + asm volatile ( + "call %[bpf_get_prandom_u32];" + "r1 = 1;" + "if r0 == 42 goto l1_%=;" + "*(u64 *)(r10 - 8) = r1;" + "call %[bpf_get_smp_processor_id];" +"l0_%=:" + "r1 = *(u64 *)(r10 - 8);" + "exit;" +"l1_%=:" + "goto l0_%=;" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_get_smp_processor_id) + : __clobber_all); +} + SEC("raw_tp") __arch_x86_64 __log_level(4) From b752e041d5845d03f285cf7a1f30b38ca7ef92bf Mon Sep 17 00:00:00 2001 From: Satish Kharat Date: Sun, 30 Aug 2026 15:22:52 -0700 Subject: [PATCH 0624/1198] enic: preserve V2 VF carrier across netdev reopen A V2 VF receives carrier state only from PF MBOX notifications. enic_stop() forces carrier off, but enic_open() does not request a fresh notification or restore the previous one. An ordinary down/up cycle therefore leaves the VF in NO-CARRIER and unable to pass traffic until the PF repeats the link-state command, even when the physical link remained up. Cache each valid PF link-state notification. Serialize updates with the V2 VF datapath running state. Keep carrier off while the netdev is stopped. Restore the cached state after an ordinary open. Before either internal reset reopens the datapath, invalidate the cache. Carrier then remains off until re-registration receives a fresh PF link-state notification. Fixes: 72b65c94058e ("enic: add MBOX VF handlers for capability, register and link state") Signed-off-by: Satish Kharat Link: https://patch.msgid.link/20260830-b4-enic-v2-mbox-fixes-net-v1-1-23adf9bfd426@cisco.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/cisco/enic/enic.h | 13 ++++++++ drivers/net/ethernet/cisco/enic/enic_main.c | 12 ++++++- drivers/net/ethernet/cisco/enic/enic_mbox.c | 37 ++++++++++++++++++--- drivers/net/ethernet/cisco/enic/enic_mbox.h | 2 ++ 4 files changed, 59 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h index 4a67947cfb9f..2822fbfb6474 100644 --- a/drivers/net/ethernet/cisco/enic/enic.h +++ b/drivers/net/ethernet/cisco/enic/enic.h @@ -137,6 +137,12 @@ struct enic_port_profile { u8 mac_addr[ETH_ALEN]; }; +enum enic_vf_link_state { + ENIC_VF_LINK_STATE_UNKNOWN, + ENIC_VF_LINK_STATE_DOWN, + ENIC_VF_LINK_STATE_UP, +}; + /* enic_rfs_fltr_node - rfs filter node in hash table * @@keys: IPv4 5 tuple * @flow_id: flow_id of clsf filter provided by kernel @@ -312,6 +318,13 @@ struct enic { unsigned int admin_msg_count; /* current depth of admin_msg_list */ void (*admin_rq_handler)(struct enic *enic, void *buf, unsigned int len); + /* The PF is authoritative for a V2 VF's carrier. Keep the last + * notification across an ordinary netdev close/open and serialize it + * against the open/stop carrier transition. + */ + spinlock_t vf_link_state_lock; + enum enic_vf_link_state vf_link_state; + bool vf_link_running; /* MBOX protocol state — mbox_lock serializes admin WQ sends */ struct mutex mbox_lock; diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index 0baef7a120ec..48d16ef18c49 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -1800,6 +1800,8 @@ static int enic_open(struct net_device *netdev) enic_notify_timer_start(enic); enic_rfs_timer_start(enic); + if (enic_is_sriov_vf_v2(enic)) + enic_mbox_vf_link_state_set_running(enic, true); return 0; @@ -1853,7 +1855,10 @@ static int enic_stop(struct net_device *netdev) for (i = 0; i < enic->rq_count; i++) napi_disable(&enic->napi[i]); - netif_carrier_off(netdev); + if (enic_is_sriov_vf_v2(enic)) + enic_mbox_vf_link_state_set_running(enic, false); + else + netif_carrier_off(netdev); if (vnic_dev_get_intr_mode(enic->vdev) == VNIC_DEV_INTR_MODE_MSIX) for (i = 0; i < enic->wq_count; i++) napi_disable(&enic->napi[enic_cq_wq(enic, i)]); @@ -2271,6 +2276,8 @@ static void enic_reset(struct work_struct *work) enic_admin_channel_close(enic); enic_stop(enic->netdev); + if (enic_is_sriov_vf_v2(enic)) + enic_mbox_vf_link_state_reset(enic); enic_dev_soft_reset(enic); enic_reset_addr_lists(enic); @@ -2315,6 +2322,8 @@ static void enic_tx_hang_reset(struct work_struct *work) enic_dev_hang_notify(enic); enic_stop(enic->netdev); + if (enic_is_sriov_vf_v2(enic)) + enic_mbox_vf_link_state_reset(enic); enic_dev_hang_reset(enic); enic_reset_addr_lists(enic); @@ -3015,6 +3024,7 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) enic = netdev_priv(netdev); enic->netdev = netdev; enic->pdev = pdev; + spin_lock_init(&enic->vf_link_state_lock); /* Setup PCI resources */ diff --git a/drivers/net/ethernet/cisco/enic/enic_mbox.c b/drivers/net/ethernet/cisco/enic/enic_mbox.c index 2fb0f1e2ff50..ad79d3951f3d 100644 --- a/drivers/net/ethernet/cisco/enic/enic_mbox.c +++ b/drivers/net/ethernet/cisco/enic/enic_mbox.c @@ -396,25 +396,32 @@ static void enic_mbox_vf_handle_link_state(struct enic *enic, void *payload) { struct enic_mbox_pf_link_state_notif_msg *notif = payload; struct enic_mbox_pf_link_state_ack_msg ack = {}; + u32 link_state = le32_to_cpu(notif->link_state); int err; - switch (le32_to_cpu(notif->link_state)) { + spin_lock_bh(&enic->vf_link_state_lock); + switch (link_state) { case ENIC_MBOX_LINK_STATE_ENABLE: - if (!netif_carrier_ok(enic->netdev)) + enic->vf_link_state = ENIC_VF_LINK_STATE_UP; + if (enic->vf_link_running && + !netif_carrier_ok(enic->netdev)) netif_carrier_on(enic->netdev); netdev_dbg(enic->netdev, "MBOX: link state -> UP\n"); break; case ENIC_MBOX_LINK_STATE_DISABLE: - if (netif_carrier_ok(enic->netdev)) + enic->vf_link_state = ENIC_VF_LINK_STATE_DOWN; + if (enic->vf_link_running && + netif_carrier_ok(enic->netdev)) netif_carrier_off(enic->netdev); netdev_dbg(enic->netdev, "MBOX: link state -> DOWN\n"); break; default: netdev_warn(enic->netdev, "MBOX: unknown link state %u\n", - le32_to_cpu(notif->link_state)); + link_state); ack.ack.ret_major = cpu_to_le16(ENIC_MBOX_ERR_GENERIC); break; } + spin_unlock_bh(&enic->vf_link_state_lock); err = enic_mbox_send_msg(enic, ENIC_MBOX_PF_LINK_STATE_ACK, ENIC_MBOX_DST_PF, &ack, sizeof(ack)); @@ -423,6 +430,28 @@ static void enic_mbox_vf_handle_link_state(struct enic *enic, void *payload) "MBOX: failed to send link state ACK: %d\n", err); } +void enic_mbox_vf_link_state_reset(struct enic *enic) +{ + spin_lock_bh(&enic->vf_link_state_lock); + enic->vf_link_state = ENIC_VF_LINK_STATE_UNKNOWN; + if (enic->vf_link_running && netif_carrier_ok(enic->netdev)) + netif_carrier_off(enic->netdev); + spin_unlock_bh(&enic->vf_link_state_lock); +} + +void enic_mbox_vf_link_state_set_running(struct enic *enic, bool running) +{ + spin_lock_bh(&enic->vf_link_state_lock); + enic->vf_link_running = running; + if (running && enic->vf_link_state == ENIC_VF_LINK_STATE_UP) { + if (!netif_carrier_ok(enic->netdev)) + netif_carrier_on(enic->netdev); + } else if (netif_carrier_ok(enic->netdev)) { + netif_carrier_off(enic->netdev); + } + spin_unlock_bh(&enic->vf_link_state_lock); +} + static bool enic_mbox_vf_payload_ok(struct enic *enic, u8 msg_type, u16 payload_len, size_t min_len) { diff --git a/drivers/net/ethernet/cisco/enic/enic_mbox.h b/drivers/net/ethernet/cisco/enic/enic_mbox.h index 15e30ee2b0ed..60409bad2f28 100644 --- a/drivers/net/ethernet/cisco/enic/enic_mbox.h +++ b/drivers/net/ethernet/cisco/enic/enic_mbox.h @@ -88,6 +88,8 @@ void enic_mbox_init(struct enic *enic); int enic_mbox_send_msg(struct enic *enic, u8 msg_type, u16 dst_vnic_id, void *payload, u16 payload_len); int enic_mbox_send_link_state(struct enic *enic, u16 vf_id, u32 link_state); +void enic_mbox_vf_link_state_reset(struct enic *enic); +void enic_mbox_vf_link_state_set_running(struct enic *enic, bool running); int enic_mbox_vf_capability_check(struct enic *enic); int enic_mbox_vf_register(struct enic *enic); int enic_mbox_vf_unregister(struct enic *enic); From 8972d252f495d4be4bbfb32d4d9d6c2ff778fea4 Mon Sep 17 00:00:00 2001 From: Satish Kharat Date: Sun, 30 Aug 2026 15:22:53 -0700 Subject: [PATCH 0625/1198] enic: match mailbox replies to request numbers The version-1 VF mailbox protocol identifies every message with a message number, and a reply or acknowledgment echoes the number of the message it answers. ENIC instead generates a new number for outgoing replies and accepts a VF reply by message type alone. If a request times out, a delayed reply can therefore satisfy a subsequent request of the same type and cause the VF to consume the result of the old request. Allow replies to reuse the initiating message number. Make the in-tree PF handlers and the VF link-state acknowledgment echo that number. Record the expected reply type and message number on the VF, and require both values to match before accepting a reply. Protect expected-reply state with a lock so reply acceptance and timeout invalidation cannot race. Keep message numbers monotonic across an admin- channel reopen so a delayed reply from an earlier channel generation cannot match a new request. Reply-number echo is part of the established version-1 protocol, so this remains compatible with deployed V2-capable PF implementations that already echo msg_num. Fixes: 72b65c94058e ("enic: add MBOX VF handlers for capability, register and link state") Signed-off-by: Satish Kharat Link: https://patch.msgid.link/20260830-b4-enic-v2-mbox-fixes-net-v1-2-23adf9bfd426@cisco.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/cisco/enic/enic.h | 13 +- drivers/net/ethernet/cisco/enic/enic_main.c | 13 +- drivers/net/ethernet/cisco/enic/enic_mbox.c | 284 ++++++++++++-------- 3 files changed, 180 insertions(+), 130 deletions(-) diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h index 2822fbfb6474..7a509a056990 100644 --- a/drivers/net/ethernet/cisco/enic/enic.h +++ b/drivers/net/ethernet/cisco/enic/enic.h @@ -329,15 +329,14 @@ struct enic { /* MBOX protocol state — mbox_lock serializes admin WQ sends */ struct mutex mbox_lock; u64 mbox_msg_num; - /* MBOX request-reply state. mbox_expected_reply is written and - * cleared by the process-context request helpers (capability/register/ - * unregister) and only read by the admin_msg_work receive handlers, so - * it is annotated with READ_ONCE()/WRITE_ONCE() rather than locked: - * only one request is in flight at a time (requesters run under RTNL or - * single-threaded probe/remove), so each request is serialized and its - * reply completes mbox_comp before the next request is issued. + /* MBOX request-reply state. Existing request callers allow only one + * request in flight. The state lock arbitrates reply acceptance against + * timeout invalidation, while mbox_comp publishes the accepted result to + * the requester. */ struct completion mbox_comp; + spinlock_t mbox_state_lock; /* protects expected reply state */ + u64 mbox_expected_msg_num; u8 mbox_expected_reply; bool mbox_initialized; diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index 48d16ef18c49..14d1637a4342 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -2206,9 +2206,10 @@ static void enic_admin_chan_reopen(struct enic *enic) { int err; - /* Install the MBOX receive handler and reset the sequence number - * before opening the channel, so the handler is in place before the - * admin interrupt is unmasked and no early completion is dropped. + /* Install the MBOX receive handler and clear pending reply state before + * opening the channel, so the handler is in place before the admin + * interrupt is unmasked and no early completion is dropped. Keep the + * sequence number monotonic across channel generations. */ enic_mbox_init(enic); @@ -2220,7 +2221,7 @@ static void enic_admin_chan_reopen(struct enic *enic) * registration over a dead channel. */ if (enic_is_sriov_vf_v2(enic)) - enic->vf_registered = false; + WRITE_ONCE(enic->vf_registered, false); err = enic_admin_channel_open(enic); if (err) { @@ -3349,7 +3350,7 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err_out_admin_close: if (enic_is_sriov_vf_v2(enic)) { - if (enic->vf_registered) { + if (READ_ONCE(enic->vf_registered)) { int unreg_err = enic_mbox_vf_unregister(enic); if (unreg_err) @@ -3402,7 +3403,7 @@ static void enic_remove(struct pci_dev *pdev) * touching a netdev that is being torn down. */ if (enic_is_sriov_vf_v2(enic)) { - if (enic->vf_registered) { + if (READ_ONCE(enic->vf_registered)) { int unreg_err = enic_mbox_vf_unregister(enic); if (unreg_err) diff --git a/drivers/net/ethernet/cisco/enic/enic_mbox.c b/drivers/net/ethernet/cisco/enic/enic_mbox.c index ad79d3951f3d..5c93ca49552a 100644 --- a/drivers/net/ethernet/cisco/enic/enic_mbox.c +++ b/drivers/net/ethernet/cisco/enic/enic_mbox.c @@ -18,22 +18,25 @@ #define ENIC_MBOX_POLL_TIMEOUT_US 5000000 #define ENIC_MBOX_POLL_INTERVAL_US 100 -static void enic_mbox_fill_hdr(struct enic *enic, struct enic_mbox_hdr *hdr, - u8 msg_type, u16 dst_vnic_id, u16 msg_len) +static void enic_mbox_fill_hdr(struct enic_mbox_hdr *hdr, u8 msg_type, + u16 dst_vnic_id, u16 msg_len, u64 msg_num) { memset(hdr, 0, sizeof(*hdr)); hdr->dst_vnic_id = cpu_to_le16(dst_vnic_id); hdr->msg_type = msg_type; hdr->msg_len = cpu_to_le16(msg_len); - hdr->msg_num = cpu_to_le64(++enic->mbox_msg_num); + hdr->msg_num = cpu_to_le64(msg_num); } -int enic_mbox_send_msg(struct enic *enic, u8 msg_type, u16 dst_vnic_id, - void *payload, u16 payload_len) +static int enic_mbox_send_msg_id(struct enic *enic, u8 msg_type, + u16 dst_vnic_id, void *payload, + u16 payload_len, u64 msg_num, bool reuse_msg_num, + u8 expected_reply) { size_t total_len = sizeof(struct enic_mbox_hdr) + payload_len; struct vnic_wq *wq = &enic->admin_wq; struct wq_enet_desc *desc; + bool reply_expected = false; unsigned long timeout; dma_addr_t dma_addr; u16 vlan_tag; @@ -68,7 +71,21 @@ int enic_mbox_send_msg(struct enic *enic, u8 msg_type, u16 dst_vnic_id, goto unlock; } - enic_mbox_fill_hdr(enic, buf, msg_type, dst_vnic_id, total_len); + /* Replies reuse the initiating message number. Requests and + * notifications allocate a new one. + */ + if (!reuse_msg_num) + msg_num = ++enic->mbox_msg_num; + if (expected_reply) { + reinit_completion(&enic->mbox_comp); + spin_lock_bh(&enic->mbox_state_lock); + enic->mbox_expected_reply = expected_reply; + enic->mbox_expected_msg_num = msg_num; + spin_unlock_bh(&enic->mbox_state_lock); + reply_expected = true; + } + + enic_mbox_fill_hdr(buf, msg_type, dst_vnic_id, total_len, msg_num); if (payload_len) { void *dst = buf + sizeof(struct enic_mbox_hdr); @@ -139,18 +156,66 @@ int enic_mbox_send_msg(struct enic *enic, u8 msg_type, u16 dst_vnic_id, "MBOX send msg_type %u dst %u vlan %u err %d\n", msg_type, dst_vnic_id, vlan_tag, err); unlock: + if (err && reply_expected) { + spin_lock_bh(&enic->mbox_state_lock); + if (enic->mbox_expected_reply == expected_reply && + enic->mbox_expected_msg_num == msg_num) { + enic->mbox_expected_reply = 0; + enic->mbox_expected_msg_num = 0; + } + spin_unlock_bh(&enic->mbox_state_lock); + } mutex_unlock(&enic->mbox_lock); return err; } +int enic_mbox_send_msg(struct enic *enic, u8 msg_type, u16 dst_vnic_id, + void *payload, u16 payload_len) +{ + return enic_mbox_send_msg_id(enic, msg_type, dst_vnic_id, payload, + payload_len, 0, false, 0); +} + +static int enic_mbox_send_reply(struct enic *enic, u8 msg_type, + u16 dst_vnic_id, void *payload, u16 payload_len, + u64 msg_num) +{ + return enic_mbox_send_msg_id(enic, msg_type, dst_vnic_id, payload, + payload_len, msg_num, true, 0); +} + +static int enic_mbox_vf_send_request(struct enic *enic, u8 request_type, + u8 expected_reply, void *payload, + u16 payload_len) +{ + return enic_mbox_send_msg_id(enic, request_type, ENIC_MBOX_DST_PF, + payload, payload_len, 0, false, + expected_reply); +} + static int enic_mbox_wait_reply(struct enic *enic, unsigned long timeout_ms) { unsigned long left; + int err = 0; left = wait_for_completion_timeout(&enic->mbox_comp, msecs_to_jiffies(timeout_ms)); + if (left) + return 0; - return left ? 0 : -ETIMEDOUT; + /* Invalidate a request that the handler has not already accepted. A + * delayed reply cannot match a later request because message numbers are + * monotonic across channel reopen. + */ + spin_lock_bh(&enic->mbox_state_lock); + if (enic->mbox_expected_reply) { + enic->mbox_expected_reply = 0; + enic->mbox_expected_msg_num = 0; + err = -ETIMEDOUT; + } + spin_unlock_bh(&enic->mbox_state_lock); + + return err; } int enic_mbox_send_link_state(struct enic *enic, u16 vf_id, u32 link_state) @@ -178,8 +243,8 @@ static int enic_mbox_pf_handle_capability(struct enic *enic, void *msg, reply.reply.ret_major = cpu_to_le16(0); reply.version = cpu_to_le32(ENIC_MBOX_CAP_VERSION_1); - return enic_mbox_send_msg(enic, ENIC_MBOX_VF_CAPABILITY_REPLY, vf_id, - &reply, sizeof(reply)); + return enic_mbox_send_reply(enic, ENIC_MBOX_VF_CAPABILITY_REPLY, vf_id, + &reply, sizeof(reply), msg_num); } static int enic_mbox_pf_handle_register(struct enic *enic, void *msg, @@ -208,8 +273,8 @@ static int enic_mbox_pf_handle_register(struct enic *enic, void *msg, } reply.reply.ret_major = cpu_to_le16(0); - err = enic_mbox_send_msg(enic, ENIC_MBOX_VF_REGISTER_REPLY, vf_id, - &reply, sizeof(reply)); + err = enic_mbox_send_reply(enic, ENIC_MBOX_VF_REGISTER_REPLY, vf_id, + &reply, sizeof(reply), msg_num); if (err) return err; @@ -253,8 +318,8 @@ static int enic_mbox_pf_handle_unregister(struct enic *enic, void *msg, enic->vf_state[vf_id].registered = false; reply.reply.ret_major = cpu_to_le16(0); - err = enic_mbox_send_msg(enic, ENIC_MBOX_VF_UNREGISTER_REPLY, vf_id, - &reply, sizeof(reply)); + err = enic_mbox_send_reply(enic, ENIC_MBOX_VF_UNREGISTER_REPLY, vf_id, + &reply, sizeof(reply), msg_num); if (net_ratelimit()) netdev_info(enic->netdev, @@ -324,75 +389,57 @@ static void enic_mbox_pf_process_msg(struct enic *enic, hdr->msg_type, vf_id, err); } -static void enic_mbox_vf_handle_capability_reply(struct enic *enic, - void *payload) +static void enic_mbox_vf_handle_reply(struct enic *enic, u8 reply_type, + void *payload, u64 msg_num) { - struct enic_mbox_vf_capability_reply_msg *reply = payload; + struct enic_mbox_generic_reply *reply = payload; + u16 ret_major = le16_to_cpu(reply->ret_major); + u64 expected_msg_num; + u8 expected_type; - if (READ_ONCE(enic->mbox_expected_reply) != ENIC_MBOX_VF_CAPABILITY_REPLY) { + spin_lock_bh(&enic->mbox_state_lock); + expected_type = enic->mbox_expected_reply; + expected_msg_num = enic->mbox_expected_msg_num; + if (expected_type != reply_type || expected_msg_num != msg_num) { + spin_unlock_bh(&enic->mbox_state_lock); netdev_warn(enic->netdev, - "MBOX: stale capability reply (expected %u), drop\n", - READ_ONCE(enic->mbox_expected_reply)); + "MBOX: stale reply %u/%llu (expected %u/%llu), drop\n", + reply_type, (unsigned long long)msg_num, + expected_type, (unsigned long long)expected_msg_num); return; } - if (le16_to_cpu(reply->reply.ret_major) == 0) - enic->pf_cap_version = le32_to_cpu(reply->version); - else - netdev_warn(enic->netdev, - "MBOX: PF rejected capability request: %u/%u\n", - le16_to_cpu(reply->reply.ret_major), - le16_to_cpu(reply->reply.ret_minor)); + if (!ret_major) { + switch (reply_type) { + case ENIC_MBOX_VF_CAPABILITY_REPLY: { + struct enic_mbox_vf_capability_reply_msg *cap = payload; + + WRITE_ONCE(enic->pf_cap_version, + le32_to_cpu(cap->version)); + break; + } + case ENIC_MBOX_VF_REGISTER_REPLY: + WRITE_ONCE(enic->vf_registered, true); + break; + case ENIC_MBOX_VF_UNREGISTER_REPLY: + WRITE_ONCE(enic->vf_registered, false); + break; + } + } + enic->mbox_expected_reply = 0; + enic->mbox_expected_msg_num = 0; complete(&enic->mbox_comp); + spin_unlock_bh(&enic->mbox_state_lock); + + if (ret_major) + netdev_warn(enic->netdev, + "MBOX: PF rejected reply type %u: %u/%u\n", + reply_type, ret_major, + le16_to_cpu(reply->ret_minor)); } -static void enic_mbox_vf_handle_register_reply(struct enic *enic, - void *payload) -{ - struct enic_mbox_vf_register_reply_msg *reply = payload; - - if (READ_ONCE(enic->mbox_expected_reply) != ENIC_MBOX_VF_REGISTER_REPLY) { - netdev_warn(enic->netdev, - "MBOX: stale register reply (expected %u), drop\n", - READ_ONCE(enic->mbox_expected_reply)); - return; - } - - if (le16_to_cpu(reply->reply.ret_major)) { - netdev_warn(enic->netdev, - "MBOX: VF register rejected by PF: %u/%u\n", - le16_to_cpu(reply->reply.ret_major), - le16_to_cpu(reply->reply.ret_minor)); - } else { - enic->vf_registered = true; - } - complete(&enic->mbox_comp); -} - -static void enic_mbox_vf_handle_unregister_reply(struct enic *enic, - void *payload) -{ - struct enic_mbox_vf_register_reply_msg *reply = payload; - - if (READ_ONCE(enic->mbox_expected_reply) != ENIC_MBOX_VF_UNREGISTER_REPLY) { - netdev_warn(enic->netdev, - "MBOX: stale unregister reply (expected %u), drop\n", - READ_ONCE(enic->mbox_expected_reply)); - return; - } - - if (le16_to_cpu(reply->reply.ret_major)) { - netdev_warn(enic->netdev, - "MBOX: VF unregister rejected by PF: %u/%u\n", - le16_to_cpu(reply->reply.ret_major), - le16_to_cpu(reply->reply.ret_minor)); - } else { - enic->vf_registered = false; - } - complete(&enic->mbox_comp); -} - -static void enic_mbox_vf_handle_link_state(struct enic *enic, void *payload) +static void enic_mbox_vf_handle_link_state(struct enic *enic, void *payload, + u64 msg_num) { struct enic_mbox_pf_link_state_notif_msg *notif = payload; struct enic_mbox_pf_link_state_ack_msg ack = {}; @@ -423,8 +470,8 @@ static void enic_mbox_vf_handle_link_state(struct enic *enic, void *payload) } spin_unlock_bh(&enic->vf_link_state_lock); - err = enic_mbox_send_msg(enic, ENIC_MBOX_PF_LINK_STATE_ACK, - ENIC_MBOX_DST_PF, &ack, sizeof(ack)); + err = enic_mbox_send_reply(enic, ENIC_MBOX_PF_LINK_STATE_ACK, + ENIC_MBOX_DST_PF, &ack, sizeof(ack), msg_num); if (err && net_ratelimit()) netdev_warn(enic->netdev, "MBOX: failed to send link state ACK: %d\n", err); @@ -468,6 +515,8 @@ static void enic_mbox_vf_process_msg(struct enic *enic, struct enic_mbox_hdr *hdr, void *payload, u16 payload_len) { + u64 msg_num = le64_to_cpu(hdr->msg_num); + switch (hdr->msg_type) { case ENIC_MBOX_VF_CAPABILITY_REPLY: { size_t exp = sizeof(struct enic_mbox_vf_capability_reply_msg); @@ -475,7 +524,7 @@ static void enic_mbox_vf_process_msg(struct enic *enic, if (!enic_mbox_vf_payload_ok(enic, hdr->msg_type, payload_len, exp)) return; - enic_mbox_vf_handle_capability_reply(enic, payload); + enic_mbox_vf_handle_reply(enic, hdr->msg_type, payload, msg_num); break; } case ENIC_MBOX_VF_REGISTER_REPLY: { @@ -484,7 +533,7 @@ static void enic_mbox_vf_process_msg(struct enic *enic, if (!enic_mbox_vf_payload_ok(enic, hdr->msg_type, payload_len, exp)) return; - enic_mbox_vf_handle_register_reply(enic, payload); + enic_mbox_vf_handle_reply(enic, hdr->msg_type, payload, msg_num); break; } case ENIC_MBOX_VF_UNREGISTER_REPLY: { @@ -493,7 +542,7 @@ static void enic_mbox_vf_process_msg(struct enic *enic, if (!enic_mbox_vf_payload_ok(enic, hdr->msg_type, payload_len, exp)) return; - enic_mbox_vf_handle_unregister_reply(enic, payload); + enic_mbox_vf_handle_reply(enic, hdr->msg_type, payload, msg_num); break; } case ENIC_MBOX_PF_LINK_STATE_NOTIF: { @@ -502,7 +551,7 @@ static void enic_mbox_vf_process_msg(struct enic *enic, if (!enic_mbox_vf_payload_ok(enic, hdr->msg_type, payload_len, exp)) return; - enic_mbox_vf_handle_link_state(enic, payload); + enic_mbox_vf_handle_link_state(enic, payload, msg_num); break; } default: @@ -571,32 +620,31 @@ static void enic_mbox_recv_handler(struct enic *enic, void *buf, int enic_mbox_vf_capability_check(struct enic *enic) { struct enic_mbox_vf_capability_msg req = {}; + u32 version; int err; - enic->pf_cap_version = 0; - reinit_completion(&enic->mbox_comp); - WRITE_ONCE(enic->mbox_expected_reply, ENIC_MBOX_VF_CAPABILITY_REPLY); + WRITE_ONCE(enic->pf_cap_version, 0); req.version = cpu_to_le32(ENIC_MBOX_CAP_VERSION_1); - err = enic_mbox_send_msg(enic, ENIC_MBOX_VF_CAPABILITY_REQUEST, - ENIC_MBOX_DST_PF, &req, sizeof(req)); - if (err) { - WRITE_ONCE(enic->mbox_expected_reply, 0); + err = enic_mbox_vf_send_request(enic, + ENIC_MBOX_VF_CAPABILITY_REQUEST, + ENIC_MBOX_VF_CAPABILITY_REPLY, + &req, sizeof(req)); + if (err) return err; - } err = enic_mbox_wait_reply(enic, 3000); - WRITE_ONCE(enic->mbox_expected_reply, 0); + version = READ_ONCE(enic->pf_cap_version); if (err) { netdev_warn(enic->netdev, "MBOX: no capability reply from PF\n"); return err; } - if (enic->pf_cap_version < ENIC_MBOX_CAP_VERSION_1) { + if (version < ENIC_MBOX_CAP_VERSION_1) { netdev_warn(enic->netdev, "MBOX: PF rejected capability request or reported unsupported version %u\n", - enic->pf_cap_version); + version); return -EOPNOTSUPP; } @@ -605,28 +653,25 @@ int enic_mbox_vf_capability_check(struct enic *enic) int enic_mbox_vf_register(struct enic *enic) { + bool registered; int err; - enic->vf_registered = false; - reinit_completion(&enic->mbox_comp); - WRITE_ONCE(enic->mbox_expected_reply, ENIC_MBOX_VF_REGISTER_REPLY); + WRITE_ONCE(enic->vf_registered, false); - err = enic_mbox_send_msg(enic, ENIC_MBOX_VF_REGISTER_REQUEST, - ENIC_MBOX_DST_PF, NULL, 0); - if (err) { - WRITE_ONCE(enic->mbox_expected_reply, 0); + err = enic_mbox_vf_send_request(enic, ENIC_MBOX_VF_REGISTER_REQUEST, + ENIC_MBOX_VF_REGISTER_REPLY, NULL, 0); + if (err) return err; - } err = enic_mbox_wait_reply(enic, 3000); - WRITE_ONCE(enic->mbox_expected_reply, 0); + registered = READ_ONCE(enic->vf_registered); if (err) { netdev_warn(enic->netdev, "MBOX: VF registration with PF timed out\n"); return err; } - if (!enic->vf_registered) + if (!registered) return -ENODEV; return 0; @@ -634,43 +679,48 @@ int enic_mbox_vf_register(struct enic *enic) int enic_mbox_vf_unregister(struct enic *enic) { + bool registered; int err; - if (!enic->vf_registered) + if (!READ_ONCE(enic->vf_registered)) return 0; - reinit_completion(&enic->mbox_comp); - WRITE_ONCE(enic->mbox_expected_reply, ENIC_MBOX_VF_UNREGISTER_REPLY); - - err = enic_mbox_send_msg(enic, ENIC_MBOX_VF_UNREGISTER_REQUEST, - ENIC_MBOX_DST_PF, NULL, 0); - if (err) { - WRITE_ONCE(enic->mbox_expected_reply, 0); - return err; - } - - err = enic_mbox_wait_reply(enic, 3000); - WRITE_ONCE(enic->mbox_expected_reply, 0); + err = enic_mbox_vf_send_request(enic, + ENIC_MBOX_VF_UNREGISTER_REQUEST, + ENIC_MBOX_VF_UNREGISTER_REPLY, + NULL, 0); if (err) return err; - if (enic->vf_registered) + + err = enic_mbox_wait_reply(enic, 3000); + registered = READ_ONCE(enic->vf_registered); + if (err) + return err; + if (registered) return -EACCES; return 0; } void enic_mbox_init(struct enic *enic) { - /* mbox_lock and mbox_comp must be initialized exactly once per + bool reinit = enic->mbox_initialized; + + /* MBOX locks and mbox_comp must be initialized exactly once per * device lifetime; the PF sriov_configure path can re-enter this * on each enable cycle where these primitives are already set up. */ - if (!enic->mbox_initialized) { + if (!reinit) { mutex_init(&enic->mbox_lock); init_completion(&enic->mbox_comp); + spin_lock_init(&enic->mbox_state_lock); + enic->mbox_msg_num = 0; enic->mbox_initialized = true; } else { reinit_completion(&enic->mbox_comp); } - enic->mbox_msg_num = 0; + spin_lock_bh(&enic->mbox_state_lock); + enic->mbox_expected_reply = 0; + enic->mbox_expected_msg_num = 0; + spin_unlock_bh(&enic->mbox_state_lock); enic->admin_rq_handler = enic_mbox_recv_handler; } From 369f4ce734570bdfedaa4b5ca50e2a3f6a892728 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 3 Sep 2026 23:47:47 +0200 Subject: [PATCH 0626/1198] bpf: Check ancestor frames for rbtree callbacks bpf_rbtree_add() invokes its comparator while the caller holds the root lock. The native insertion code retains raw parent and link pointers across the callback, so the verifier prohibits unlocking, consuming tree nodes, or changing RCU state from that callback. in_rbtree_lock_required_cb() only checks the innermost verifier frame. Static subprogram calls are permitted while holding a spin lock, and such a call pushes a frame without in_callback_fn set. Consequently, all callback restrictions disappear in the nested frame. The subprogram can unlock the tree, remove and drop the node being compared, then relock. Native insertion resumes with the stale parent pointer and links freed memory into the tree. Walk all active frames for the rbtree callback instead. Benign static subprograms remain permitted, while callback restrictions follow execution into nested frames. Fixes: a44b1334aadd ("bpf: Allow calling static subprogs while holding a bpf_spin_lock") Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Kumar Kartikeya Dwivedi Acked-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260903214758.2727663-2-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 25 ++++++++++++++----------- 1 file changed, 14 insertions(+), 11 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 2ed17edf77f2..2b7e5c9b3ffc 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -10235,9 +10235,10 @@ static void account_current_path(struct bpf_verifier_env *env) frame ? state->frame[frame - 1] : NULL); } -/* Are we currently verifying the callback for a rbtree helper that must - * be called with lock held? If so, no need to complain about unreleased - * lock +/* + * Are we currently verifying the callback for an rbtree kfunc that must + * be called with a lock held, or one of that callback's subprogs? If so, + * no need to complain about an unreleased lock. */ static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env) { @@ -10245,17 +10246,19 @@ static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env) struct bpf_insn *insn = env->prog->insnsi; struct bpf_func_state *callee; int kfunc_btf_id; + u32 frame; - if (!state->curframe) - return false; + for (frame = state->curframe; frame; frame--) { + callee = state->frame[frame]; + if (!callee->in_callback_fn) + continue; - callee = state->frame[state->curframe]; + kfunc_btf_id = insn[callee->callsite].imm; + if (is_rbtree_lock_required_kfunc(kfunc_btf_id)) + return true; + } - if (!callee->in_callback_fn) - return false; - - kfunc_btf_id = insn[callee->callsite].imm; - return is_rbtree_lock_required_kfunc(kfunc_btf_id); + return false; } static bool retval_range_within(struct bpf_retval_range range, const struct bpf_reg_state *reg) From 22ab49afe1c901b2c0b9482f38bdb647d46e6a34 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 3 Sep 2026 23:47:48 +0200 Subject: [PATCH 0627/1198] selftests/bpf: Check rbtree callback restrictions in subprogs Add a verifier failure case where an rbtree comparator enters two nested static subprograms and the innermost subprogram unlocks and relocks the tree. Restoring the lock keeps the surrounding callback state balanced, so the test specifically exercises whether the callback restriction follows the nested calls. Also add a load-only positive control whose comparator calls a harmless static subprogram. This preserves the intended support for verified static subprogram calls while holding the tree lock. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260903214758.2727663-3-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- .../testing/selftests/bpf/progs/rbtree_fail.c | 55 +++++++++++++++++++ 1 file changed, 55 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/rbtree_fail.c b/tools/testing/selftests/bpf/progs/rbtree_fail.c index 803419a47c62..4504608196ab 100644 --- a/tools/testing/selftests/bpf/progs/rbtree_fail.c +++ b/tools/testing/selftests/bpf/progs/rbtree_fail.c @@ -272,6 +272,47 @@ static bool less__bad_res_spin_unlock(struct bpf_rb_node *a, const struct bpf_rb return false; } +static __noinline void rbtree_cb_unlock_relock(void) +{ + bpf_spin_unlock(&glock); + bpf_spin_lock(&glock); +} + +static __noinline void rbtree_cb_nested_unlock(void) +{ + rbtree_cb_unlock_relock(); + asm volatile (""); +} + +static bool less__bad_subprog_unlock(struct bpf_rb_node *a, const struct bpf_rb_node *b) +{ + struct node_data *node_a; + struct node_data *node_b; + + node_a = container_of(a, struct node_data, node); + node_b = container_of(b, struct node_data, node); + rbtree_cb_nested_unlock(); + + return node_a->key < node_b->key; +} + +static __noinline void rbtree_cb_noop(void) +{ + asm volatile (""); +} + +static bool less__subprog_allowed(struct bpf_rb_node *a, const struct bpf_rb_node *b) +{ + struct node_data *node_a; + struct node_data *node_b; + + node_a = container_of(a, struct node_data, node); + node_b = container_of(b, struct node_data, node); + rbtree_cb_noop(); + + return node_a->key < node_b->key; +} + static __always_inline long add_with_cb(bool (cb)(struct bpf_rb_node *a, const struct bpf_rb_node *b)) { @@ -330,4 +371,18 @@ long rbtree_api_add_bad_cb_res_spin_unlock(void *ctx) return 0; } +SEC("?tc") +__failure __msg("can't spin_{lock,unlock} in rbtree cb") +long rbtree_api_add_bad_cb_subprog_unlock(void *ctx) +{ + return add_with_cb(less__bad_subprog_unlock); +} + +SEC("?tc") +__success +long rbtree_api_add_cb_subprog_allowed(void *ctx) +{ + return add_with_cb(less__subprog_allowed); +} + char _license[] SEC("license") = "GPL"; From 620614bf7672130c43b3cff375525a2202f61979 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 3 Sep 2026 23:47:49 +0200 Subject: [PATCH 0628/1198] bpf: Mark bpf_btf_find_by_name_kind() as sleepable When bpf_btf_find_by_name_kind() finds a type in module BTF, it returns a new BTF object fd through __btf_new_fd(). This reaches anon_inode_getfd(), which can sleep while allocating or expanding the current task fd table. The helper prototype does not set might_sleep, so the verifier allows the helper in non-sleepable contexts such as BPF timer callbacks. The fd allocation can then sleep in softirq context and install the fd into the interrupted task. Mark the helper as sleepable. This preserves calls from the main body of a sleepable syscall program while rejecting calls from its non-sleepable regions. Fixes: 3d78417b60fb ("bpf: Add bpf_btf_find_by_name_kind() helper.") Reported-by: Sashiko Link: https://lore.kernel.org/bpf/20260903155150.D57251F000E9@smtp.kernel.org Signed-off-by: Kumar Kartikeya Dwivedi Acked-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260903214758.2727663-4-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/btf.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 5d93fd82e764..9f33e95d5741 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -8749,6 +8749,7 @@ BPF_CALL_4(bpf_btf_find_by_name_kind, char *, name, int, name_sz, u32, kind, int const struct bpf_func_proto bpf_btf_find_by_name_kind_proto = { .func = bpf_btf_find_by_name_kind, .gpl_only = false, + .might_sleep = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_MEM_SIZE, From 687b2729ce4c90a3cec76db85d3649e8f5086f85 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 3 Sep 2026 23:47:50 +0200 Subject: [PATCH 0629/1198] selftests/bpf: Test btf lookup helper sleepability Add an expected failure case which calls bpf_btf_find_by_name_kind() from a BPF timer callback. Without the helper prototype being marked sleepable, the verifier accepts the program and the load unexpectedly succeeds. Also add a positive control which calls the helper directly from a syscall program. This verifies that marking the helper sleepable only rejects it in non-sleepable regions. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260903214758.2727663-5-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- .../bpf/progs/verifier_async_cb_context.c | 34 +++++++++++++++++++ 1 file changed, 34 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c b/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c index a7c84d3fa4c7..e0926767bbd3 100644 --- a/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c +++ b/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c @@ -108,6 +108,30 @@ int timer_sys_close_prog(void *ctx) return 0; } +static int timer_btf_find_cb(void *map, int *key, struct bpf_timer *timer) +{ + char name[] = "task_struct"; + + bpf_btf_find_by_name_kind(name, sizeof(name), BTF_KIND_STRUCT, 0); + return 0; +} + +SEC("syscall") +__failure __msg("sleepable helper bpf_btf_find_by_name_kind#{{[0-9]+}} in non-sleepable prog") +int timer_btf_find_prog(void *ctx) +{ + struct timer_elem *val; + int key = 0; + + val = bpf_map_lookup_elem(&timer_map, &key); + if (!val) + return 0; + + bpf_timer_init(&val->t, &timer_map, 0); + bpf_timer_set_callback(&val->t, timer_btf_find_cb); + return 0; +} + SEC("syscall") __success int syscall_sys_bpf_prog(void *ctx) @@ -126,6 +150,16 @@ int syscall_sys_close_prog(void *ctx) return 0; } +SEC("syscall") +__success +int syscall_btf_find_prog(void *ctx) +{ + char name[] = "task_struct"; + + bpf_btf_find_by_name_kind(name, sizeof(name), BTF_KIND_STRUCT, 0); + return 0; +} + /* Workqueue tests */ struct wq_elem { From 9d02927fdf4e930893c92e35fed01a2704496900 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 3 Sep 2026 23:47:51 +0200 Subject: [PATCH 0630/1198] bpf: Mark faultable stack helpers as sleepable The faultable variants of bpf_get_stack() and bpf_get_task_stack() pass may_fault=true into the common stack collection code. Resolving user-space build IDs may then call build_id_parse_file() and block on filesystem reads. Neither helper prototype sets might_sleep. Since prototype selection uses the sleepability of the whole program, the verifier can still allow these helpers from a non-sleepable region within that program, such as an explicit RCU or preemption-disabled region. The task-stack helper can also be called from a non-sleepable timer callback of a sleepable program. Mark both faultable prototypes as sleepable. The existing helper context check then rejects these calls while continuing to allow them in genuinely sleepable contexts. Fixes: d4dd9775ec24 ("bpf: wire up sleepable bpf_get_stack() and bpf_get_task_stack() helpers") Signed-off-by: Kumar Kartikeya Dwivedi Acked-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260903214758.2727663-6-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/stackmap.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index a839041e0d00..d09d4c3fe547 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -875,6 +875,7 @@ BPF_CALL_4(bpf_get_stack_sleepable, struct pt_regs *, regs, void *, buf, u32, si const struct bpf_func_proto bpf_get_stack_sleepable_proto = { .func = bpf_get_stack_sleepable, .gpl_only = true, + .might_sleep = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_UNINIT_MEM, @@ -928,6 +929,7 @@ BPF_CALL_4(bpf_get_task_stack_sleepable, struct task_struct *, task, void *, buf const struct bpf_func_proto bpf_get_task_stack_sleepable_proto = { .func = bpf_get_task_stack_sleepable, .gpl_only = false, + .might_sleep = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], From 1ba0d0d8b6757eaf107f1f0fa0830c9585853db7 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 3 Sep 2026 23:47:52 +0200 Subject: [PATCH 0631/1198] selftests/bpf: Check faultable stack helper contexts Add verifier coverage for the sleepable bpf_get_stack() and bpf_get_task_stack() implementations. Call each helper while preemption is disabled and require the verifier to reject it as sleepable. Both programs load when the prototypes lack might_sleep, so the expected-failure tests fail. Keep success controls outside the non-preemptible region to ensure ordinary calls from sleepable uprobes remain valid. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260903214758.2727663-7-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- .../selftests/bpf/progs/preempt_lock.c | 52 +++++++++++++++++++ 1 file changed, 52 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/preempt_lock.c b/tools/testing/selftests/bpf/progs/preempt_lock.c index 6d5fce7e6ffc..81c459435680 100644 --- a/tools/testing/selftests/bpf/progs/preempt_lock.c +++ b/tools/testing/selftests/bpf/progs/preempt_lock.c @@ -115,6 +115,58 @@ int preempt_sleepable_helper(void *ctx) return 0; } +SEC("?uprobe.s") +__failure __msg("sleepable helper bpf_get_stack#") +int preempt_sleepable_get_stack(struct pt_regs *ctx) +{ + struct bpf_stack_build_id stack; + + bpf_preempt_disable(); + bpf_get_stack(ctx, &stack, sizeof(stack), + BPF_F_USER_STACK | BPF_F_USER_BUILD_ID); + bpf_preempt_enable(); + return 0; +} + +SEC("?uprobe.s") +__failure __msg("sleepable helper bpf_get_task_stack#") +int preempt_sleepable_get_task_stack(void *ctx) +{ + struct bpf_stack_build_id stack; + struct task_struct *task; + + task = bpf_get_current_task_btf(); + bpf_preempt_disable(); + bpf_get_task_stack(task, &stack, sizeof(stack), + BPF_F_USER_STACK | BPF_F_USER_BUILD_ID); + bpf_preempt_enable(); + return 0; +} + +SEC("?uprobe.s") +__success +int sleepable_get_stack(struct pt_regs *ctx) +{ + struct bpf_stack_build_id stack; + + bpf_get_stack(ctx, &stack, sizeof(stack), + BPF_F_USER_STACK | BPF_F_USER_BUILD_ID); + return 0; +} + +SEC("?uprobe.s") +__success +int sleepable_get_task_stack(void *ctx) +{ + struct bpf_stack_build_id stack; + struct task_struct *task; + + task = bpf_get_current_task_btf(); + bpf_get_task_stack(task, &stack, sizeof(stack), + BPF_F_USER_STACK | BPF_F_USER_BUILD_ID); + return 0; +} + SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") __failure __msg("kernel func bpf_copy_from_user_str is sleepable within non-preemptible region") int preempt_sleepable_kfunc(void *ctx) From e7d28823c662128caae63f14e16bd394916c139b Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 3 Sep 2026 23:47:53 +0200 Subject: [PATCH 0632/1198] bpf: Reject legacy packet loads from callbacks check_ld_abs() models a failed BPF_LD_ABS or BPF_LD_IND in a subprogram as an implicit return with R0 set to zero. It calls prepare_func_exit() to explore this synthesized path. When the load is reached directly from a synchronous callback, prepare_func_exit() enforces the callback return contract and marks R0 precise. R0 is not derived from a real instruction on this path, so precision backtracking reaches the callback call with R0 still requested and triggers the "callback unexpected regs" verifier bug. A privileged program loader can therefore cause a verifier warning and an -EFAULT BPF_PROG_LOAD. These legacy packet-load instructions are deprecated. Reject them from callbacks rather than complicating their implicit-return model. Check all active frames before constructing the implicit return so nested static subprograms cannot hide the callback context. Global functions are verified independently with a fresh frame zero, so an active-frame check cannot identify a global function called from a callback. Also check the complete subprogram call graph during stack-depth validation and reject a function containing a legacy load when any caller is a callback. This covers global and static descendants without making has_ld_abs transitive, preserving its per-function BTF return-type check. Ordinary uses outside callbacks remain supported. Fixes: ee861486e377 ("bpf: Fix ld_{abs,ind} failure path analysis in subprogs") Reported-by: Sashiko Link: https://lore.kernel.org/bpf/20260903152147.C0E241F00A3A@smtp.kernel.org Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260903214758.2727663-8-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 2b7e5c9b3ffc..d7dd0befbd10 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5302,6 +5302,15 @@ static int check_max_stack_depth_subprog(struct bpf_verifier_env *env, int idx, if (!priv_stack_supported) subprog[idx].priv_stack_mode = NO_PRIV_STACK; process_func: + if (subprog[idx].has_ld_abs) { + for (tmp = idx; tmp >= 0; tmp = dinfo[tmp].caller) { + if (subprog[tmp].is_cb) { + verbose(env, "cannot use BPF_LD_[ABS|IND] within callback\n"); + return -EINVAL; + } + } + } + /* protect against potential stack overflow that might happen when * bpf2bpf calls get combined with tailcalls. Limit the caller's stack * depth for such case down to 256 so that the worst case scenario @@ -17182,6 +17191,7 @@ static bool may_access_skb(enum bpf_prog_type type) */ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) { + struct bpf_verifier_state *state = env->cur_state; struct bpf_reg_state *regs = cur_regs(env); static const int ctx_reg = BPF_REG_6; u8 mode = BPF_MODE(insn->code); @@ -17192,6 +17202,13 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EINVAL; } + for (i = state->curframe; i; i--) { + if (state->frame[i]->in_callback_fn) { + verbose(env, "cannot use BPF_LD_[ABS|IND] within callback\n"); + return -EINVAL; + } + } + if (!env->ops->gen_ld_abs) { verifier_bug(env, "gen_ld_abs is null"); return -EFAULT; From 23724e009f65838bd8e1b42bed69e3daa4ecfdab Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 3 Sep 2026 23:47:54 +0200 Subject: [PATCH 0633/1198] selftests/bpf: Reject legacy packet loads from callbacks Add verifier coverage for the callback restriction on legacy packet loads. Exercise BPF_LD_ABS directly in a bpf_loop callback and BPF_LD_IND from a static subprogram called by the callback, ensuring that callback context follows nested static calls. Also exercise a callback which reaches BPF_LD_IND through a global function and its static descendant. A sibling success case calls the same global chain outside a callback, preserving support for ordinary global packet loads. Existing success cases continue to cover loads from ordinary static subprograms. The failure cases expect the policy-specific rejection instead of reaching the implicit-return path, triggering a verifier warning, or being accepted through a function boundary. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260903214758.2727663-9-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- .../selftests/bpf/progs/verifier_ld_ind.c | 96 +++++++++++++++++++ 1 file changed, 96 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/verifier_ld_ind.c b/tools/testing/selftests/bpf/progs/verifier_ld_ind.c index 09e81b99eecb..32989f981fb6 100644 --- a/tools/testing/selftests/bpf/progs/verifier_ld_ind.c +++ b/tools/testing/selftests/bpf/progs/verifier_ld_ind.c @@ -194,6 +194,102 @@ __naked void ld_ind_subprog_both_paths_safe(void) ::: __clobber_all); } +__naked __noinline __used +static int ld_abs_callback(void) +{ + asm volatile ( + "r6 = *(u64 *)(r2 + 0);" + ".8byte %[ld_abs];" + "r0 = 0;" + "exit;" + : + : __imm_insn(ld_abs, BPF_LD_ABS(BPF_W, 0)) + : __clobber_all); +} + +SEC("socket") +__description("ld_abs: reject in callback") +__failure __msg("cannot use BPF_LD_[ABS|IND] within callback") +int ld_abs_callback_reject(struct __sk_buff *skb) +{ + bpf_loop(1, ld_abs_callback, &skb, 0); + return 0; +} + +__naked __noinline __used +static int ld_ind_callback_subprog(void) +{ + asm volatile ( + "r6 = r1;" + "r7 = 0;" + ".8byte %[ld_ind];" + "r0 = 0;" + "exit;" + : + : __imm_insn(ld_ind, BPF_LD_IND(BPF_W, BPF_REG_7, 0)) + : __clobber_all); +} + +__naked __noinline __used +static int ld_ind_callback(void) +{ + asm volatile ( + "r1 = *(u64 *)(r2 + 0);" + "call ld_ind_callback_subprog;" + "exit;" + ::: __clobber_all); +} + +SEC("socket") +__description("ld_ind: reject in callback subprog") +__failure __msg("cannot use BPF_LD_[ABS|IND] within callback") +int ld_ind_callback_subprog_reject(struct __sk_buff *skb) +{ + bpf_loop(1, ld_ind_callback, &skb, 0); + return 0; +} + +static __noinline int ld_ind_global_static(struct __sk_buff *skb) +{ + asm volatile ( + "r6 = %[skb];" + "r7 = 0;" + ".8byte %[ld_ind];" + : + : [skb] "r"(skb), + __imm_insn(ld_ind, BPF_LD_IND(BPF_W, BPF_REG_7, 0)) + : __clobber_common, "r6", "r7"); + return skb->mark; +} + +__noinline int ld_ind_global(struct __sk_buff *skb) +{ + return ld_ind_global_static(skb); +} + +static int ld_ind_global_callback(__u32 index, struct __sk_buff **ctx) +{ + ld_ind_global(*ctx); + return 0; +} + +SEC("socket") +__description("ld_ind: reject in callback global subprog") +__failure __msg("cannot use BPF_LD_[ABS|IND] within callback") +int ld_ind_global_callback_reject(struct __sk_buff *skb) +{ + bpf_loop(1, ld_ind_global_callback, &skb, 0); + return 0; +} + +SEC("socket") +__description("ld_ind: allow in non-callback global subprog") +__success +int ld_ind_global_subprog_ok(struct __sk_buff *skb) +{ + return ld_ind_global(skb); +} + /* * ld_{abs,ind} in subprogs require scalar (int) return type in BTF. * A test with void return must be rejected. From 254c881fe0554c5efb16d355c273702a27a32a20 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 3 Sep 2026 08:58:45 +0200 Subject: [PATCH 0634/1198] selftests/bpf: Add tests to assert that netfilter progs cannot write to skb The netfilter framework is allergic to ip header changing after validation done by ip/ipv6 stack. Assert that bpf netfilter programs do not allow skb write access. Following additional tests are expected to be rejected by verifier: 1. alter skb->len. 2. alter skb->data. 3. prog calls bpf_dynptr_slice_rdwr. 4. alter location returned by dynptr API. Add following test case for bpf runtime: - alter skb data via bpf_dynptr_write() Test checks via __retval() that bpf_dynptr_write() returned nonzero value. Signed-off-by: Florian Westphal Reviewed-by: Jiayuan Chen Link: https://lore.kernel.org/r/20260903065845.22762-1-fw@strlen.de Signed-off-by: Alexei Starovoitov --- .../bpf/progs/verifier_netfilter_ctx.c | 78 +++++++++++++++++++ 1 file changed, 78 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/verifier_netfilter_ctx.c b/tools/testing/selftests/bpf/progs/verifier_netfilter_ctx.c index e2cbc5bda65e..b5d7f567d0d4 100644 --- a/tools/testing/selftests/bpf/progs/verifier_netfilter_ctx.c +++ b/tools/testing/selftests/bpf/progs/verifier_netfilter_ctx.c @@ -113,4 +113,82 @@ int with_valid_ctx_access_test6(struct bpf_nf_ctx *ctx) return th->dest == bpf_htons(22) ? NF_ACCEPT : NF_DROP; } +SEC("netfilter") +__description("netfilter test prog with skb write access") +__failure __msg("only read is supported") +int skb_len_write(struct bpf_nf_ctx *ctx) +{ + ctx->skb->len = 1; + return 1; +} + +SEC("netfilter") +__description("netfilter test prog with skb data write access") +__failure __msg("cannot write into rdonly_untrusted_mem") +int skb_data_write(struct bpf_nf_ctx *ctx) +{ + ctx->skb->data[0] = 0; + return 1; +} + +SEC("netfilter") +__description("netfilter test prog with bpf_dynptr_write") +__success __failure_unpriv +__retval(0) +int with_dynptr_write(struct bpf_nf_ctx *ctx) +{ + struct __sk_buff *skb = (struct __sk_buff *)ctx->skb; + struct bpf_dynptr ptr; + u8 buffer[1] = {}; + + if (bpf_dynptr_from_skb(skb, 0, &ptr)) + return 1; + + if (bpf_dynptr_write(&ptr, 0, buffer, sizeof(buffer), 0)) + return 0; /* must always fail */ + + return 1; +} + +SEC("netfilter") +__description("netfilter test prog with bpf_dynptr_slice_rdwr") +__failure __msg("the prog does not allow writes to packet data") +int with_dynptr_rdwr(struct bpf_nf_ctx *ctx) +{ + struct __sk_buff *skb = (struct __sk_buff *)ctx->skb; + u8 buffer_iph[20] = {}; + struct bpf_dynptr ptr; + struct iphdr *iph; + + if (bpf_dynptr_from_skb(skb, 0, &ptr)) + return 1; + + iph = bpf_dynptr_slice_rdwr(&ptr, 0, buffer_iph, sizeof(buffer_iph)); + if (!iph) + return 0; + + return 1; +} + +SEC("netfilter") +__description("netfilter test prog with bpf_dynptr_slice + write") +__failure __msg("cannot write into rdonly_mem") +int with_dynptr_store(struct bpf_nf_ctx *ctx) +{ + struct __sk_buff *skb = (struct __sk_buff *)ctx->skb; + u8 buffer_iph[20] = {}; + struct bpf_dynptr ptr; + struct iphdr *iph; + + if (bpf_dynptr_from_skb(skb, 0, &ptr)) + return 1; + + iph = bpf_dynptr_slice(&ptr, 0, buffer_iph, sizeof(buffer_iph)); + if (!iph) + return 0; + iph->protocol = 42; + + return 1; +} + char _license[] SEC("license") = "GPL"; From 912edebe8501a36c6bedcef03bd238ab90a7e060 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 1 Sep 2026 15:54:51 +0200 Subject: [PATCH 0635/1198] futex: Provide rt_mutex_.*_schedule() equivalents for futex scheduling There is rt_mutex_{pre|post}_schedule() around rt_mutex_wait_proxy_lock() to ensure that sched_submit_work()/ sched_update_worker() is invoked before we schedule out and block on rt_mutex while waiting for it become available. The reason is that blocking on rt_mutex assigns a pi_waiter for the PI chain and sched_submit_work() will also assign a pi_waiter if it blocks on lock but a this point we already have a waiter assigned. We can't skip sched_submit_work() entirely because I/O relies on the fact that I/O queue is flushed while it blocks on a sleeping lock. Therefore sched_submit_work() is moved before we block on the lock. Sleeping lock in this context means mutex or rw_semaphore not spinlock_t on PREEMPT_RT. Because the mutex abstraction on PREEMPT_RT uses the same abstraction as the futex proxy lock, the futex code ended up using rt_mutex_{pre|post}_schedule(), too. Using it is/ was just to keep the task_struct::sched_rt_mutex assertion happy. Futex proxy lock is used only in the syscall context of a task. At this point it never got any I/O that needs to be flushed and it can't be a workqueue that needs to notify that it will be scheduled out. Therefore sched_submit_work() does nothing here. By mistake futex_wait_requeue_pi() -> rt_mutex_wait_proxy_lock() did not get the rt_mutex_{pre|post}_schedule() annotation. This was not noticed because in this callchain the lock is (usually) not contended and so rt_mutex_slowlock_block() does not schedule, triggering the assert. Adding rt_mutex_pre_schedule() here looks wrong (as noted by PeterZ) because at this point there is a pi_waiter recorded and invoking sched_submit_work() with a possible lock contention would be wrong. Add rt_mutex_futex_{pre|post}_schedule() which toggles the sched_rt_mutex assert and does not involve sched_submit_work(). Add asserts here to ensure that sched_submit_work() would do nothing. Use it only in futex proxy lock case which is rt_mutex_wait_proxy_lock(). Remove it from futex_lock_pi(). Fixes: d14f9e930b90 ("locking/rtmutex: Use rt_mutex specific scheduler helpers") Reported-by: Yao Kai Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260901135453.3121948-2-bigeasy@linutronix.de Closes: https://lore.kernel.org/all/20260717084922.4153317-2-yaokai34@huawei.com --- include/linux/sched/rt.h | 2 ++ kernel/futex/pi.c | 16 +++------------- kernel/locking/rtmutex_api.c | 2 ++ kernel/sched/core.c | 16 ++++++++++++++++ 4 files changed, 23 insertions(+), 13 deletions(-) diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h index 4e3338103654..922935cc3383 100644 --- a/include/linux/sched/rt.h +++ b/include/linux/sched/rt.h @@ -52,8 +52,10 @@ static inline bool rt_or_dl_task_policy(struct task_struct *tsk) #ifdef CONFIG_RT_MUTEXES extern void rt_mutex_pre_schedule(void); +extern void rt_mutex_futex_pre_schedule(void); extern void rt_mutex_schedule(void); extern void rt_mutex_post_schedule(void); +extern void rt_mutex_futex_post_schedule(void); /* * Must hold either p->pi_lock or task_rq(p)->lock. diff --git a/kernel/futex/pi.c b/kernel/futex/pi.c index 88788e584ec8..98f1b962e59a 100644 --- a/kernel/futex/pi.c +++ b/kernel/futex/pi.c @@ -1070,17 +1070,11 @@ int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int tryl * Caution; releasing @hb in-scope. The hb->lock is still locked * while the reference is dropped. The reference can not be dropped * after the unlock because if a user initiated resize is in progress - * then we might need to wake him. This can not be done after the - * rt_mutex_pre_schedule() invocation. The hb will remain valid because - * the thread, performing resize, will block on hb->lock during - * the requeue. + * then we might need to wake him. The hb will remain valid + * because the thread, performing resize, will block on + * hb->lock during the requeue. */ futex_private_hash_put(no_free_ptr(hbr.fph)); - /* - * Must be done before we enqueue the waiter, here is unfortunately - * under the hb lock, but that *should* work because it does nothing. - */ - rt_mutex_pre_schedule(); rt_mutex_init_waiter(&rt_waiter); @@ -1146,10 +1140,6 @@ int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int tryl * the */ futex_q_lockptr_lock(&q); - /* - * Waiter is unqueued. - */ - rt_mutex_post_schedule(); no_block: /* * Fixup the pi_state owner and possibly acquire the lock if we diff --git a/kernel/locking/rtmutex_api.c b/kernel/locking/rtmutex_api.c index 5d48d64725b1..eb18b094473c 100644 --- a/kernel/locking/rtmutex_api.c +++ b/kernel/locking/rtmutex_api.c @@ -423,6 +423,7 @@ int __sched rt_mutex_wait_proxy_lock(struct rt_mutex_base *lock, { int ret; + rt_mutex_futex_pre_schedule(); raw_spin_lock_irq(&lock->wait_lock); /* sleep on the mutex */ set_current_state(TASK_INTERRUPTIBLE); @@ -433,6 +434,7 @@ int __sched rt_mutex_wait_proxy_lock(struct rt_mutex_base *lock, */ fixup_rt_mutex_waiters(lock, true); raw_spin_unlock_irq(&lock->wait_lock); + rt_mutex_futex_post_schedule(); return ret; } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f78275192036..449ccd871be8 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7637,6 +7637,17 @@ void rt_mutex_pre_schedule(void) sched_submit_work(current); } +/* + * Used within the futex syscall context, skips sched_submit_work() because none + * its work will be done. Asserts ensure that it is indeed the case. + */ +void rt_mutex_futex_pre_schedule(void) +{ + lockdep_assert(!(current->flags & (PF_WQ_WORKER | PF_IO_WORKER))); + lockdep_assert(!current->plug); + lockdep_assert(!fetch_and_set(current->sched_rt_mutex, 1)); +} + void rt_mutex_schedule(void) { lockdep_assert(current->sched_rt_mutex); @@ -7649,6 +7660,11 @@ void rt_mutex_post_schedule(void) lockdep_assert(fetch_and_set(current->sched_rt_mutex, 0)); } +void rt_mutex_futex_post_schedule(void) +{ + lockdep_assert(fetch_and_set(current->sched_rt_mutex, 0)); +} + /* * rt_mutex_setprio - set the current priority of a task * @p: task to boost From a3b8d46fe401cba3a5c46dea610e6eb3dc15370e Mon Sep 17 00:00:00 2001 From: Yao Kai Date: Tue, 1 Sep 2026 15:54:52 +0200 Subject: [PATCH 0636/1198] futex: Prevent rcuwait use-after-free during requeue PI On PREEMPT_RT, FUTEX_CMP_REQUEUE_PI can trigger a KASAN report (slab-out-of-bounds) in futex_requeue_pi_complete() invocation of rcuwait_wake_up(). The futex_q used by futex_wait_requeue_pi() is allocated on the waiter's stack. An early wakeup can race with a PI requeue as follows: waiter requeue task ------ ------------ futex_wait_requeue_pi() futex_do_wait() schedule() futex_requeue futex_proxy_trylock_atomic() futex_requeue_pi_prepare() Q_REQUEUE_PI_NONE -> Q_REQUEUE_PI_IN_PROGRESS * timeout/ signal wakes waiter * futex_requeue_pi_wakeup_sync() Q_REQUEUE_PI_IN_PROGRESS -> Q_REQUEUE_PI_WAIT requeue_pi_wake_futex futex_requeue_pi_complete() cmpxchg Q_REQUEUE_PI_WAIT -> Q_REQUEUE_PI_LOCKED rcuwait_wait_event() if (atomic_read(&q->requeue_state) != Q_REQUEUE_PI_WAIT) break /* no schedule() */ /* q.pi_state->owner == current */ futex_private_hash_put() /* return from syscall */ rcuwait_wake_up(&q->requeue_wait) /* q is gone */ futex_requeue_pi_complete() publishes Q_REQUEUE_PI_LOCKED before calling rcuwait_wake_up(). The waiter observes this state in rcuwait_wait_event() before invoking schedule() in rcuwait_wait_event(). Here, the waiter is free leave the syscall before requeue task can complete the wake. To address this race skip rcuwait_wake_up() in the Q_REQUEUE_PI_LOCKED case. This state is only published by requeue_pi_wake_futex(), which saves q->task before futex_requeue_pi_complete() and wakes the waiter via wake_up_state(). This wake is intended to wake the waiter from its futex_do_wait() sleep. If the waiter is still sleeping there, it can not get into the Q_REQUEUE_PI_WAIT state (and require this removed wake). Should the waiter be woken up from futex_do_wait() by other means (as in this example) and sleep in futex_requeue_pi_wakeup_sync() then the wake_up_state() from requeue_pi_wake_futex() will wake it, too. Should the waiter task terminate before wake_up_state() had a chance to wake the task then the task pointer does not become invalid because the futex_hash_bucket::lock is held and the task pointer is RCU protected. [bigeasy: Updated comment and commit message] Fixes: 07d91ef510fb1 ("futex: Prevent requeue_pi() lock nesting issue on RT") Signed-off-by: Yao Kai Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260901135453.3121948-3-bigeasy@linutronix.de --- kernel/futex/requeue.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/kernel/futex/requeue.c b/kernel/futex/requeue.c index 79823ad13683..b3f4a4bccb12 100644 --- a/kernel/futex/requeue.c +++ b/kernel/futex/requeue.c @@ -154,8 +154,16 @@ static inline void futex_requeue_pi_complete(struct futex_q *q, int locked) } while (!atomic_try_cmpxchg(&q->requeue_state, &old, new)); #ifdef CONFIG_PREEMPT_RT - /* If the waiter interleaved with the requeue let it know */ - if (unlikely(old == Q_REQUEUE_PI_WAIT)) + /* + * The waiter in futex_requeue_pi_wakeup_sync() can interleave with the + * wake below: It will assign Q_REQUEUE_PI_IN_PROGRESS and here it will + * be updated to Q_REQUEUE_PI_LOCKED (locked = 1). The rcuwait_wait_event() + * will already read Q_REQUEUE_PI_LOCKED and skip the schedule() invocation, + * leading to an access of futex_q::requeue_wait after the waiter returned. + * In this case only we skip the wake here and rely on following wake in + * requeue_pi_wake_futex() to perform the wake if needed. + */ + if (unlikely(old == Q_REQUEUE_PI_WAIT) && new != Q_REQUEUE_PI_LOCKED) rcuwait_wake_up(&q->requeue_wait); #endif } From 797b13a7de957792c1b4773aa2cc3dab4621fd9c Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Tue, 1 Sep 2026 09:04:48 +0200 Subject: [PATCH 0637/1198] irqdomain: Delete irq_domain_add_linear() 7.3-rc1 is free of calls to irq_domain_add_linear(), so it can be finally deleted. According to Dongliang Mu, the related paragraph in the Chinese docs is now obsolete. So drop it completely. Signed-off-by: Jiri Slaby (SUSE) Signed-off-by: Thomas Gleixner Reviewed-by: Dongliang Mu Reviewed-by: Yanteng Si Link: https://patch.msgid.link/20260901070450.255507-1-jirislaby@kernel.org --- .../zh_CN/core-api/irq/irq-domain.rst | 4 ---- include/linux/irqdomain.h | 18 ------------------ 2 files changed, 22 deletions(-) diff --git a/Documentation/translations/zh_CN/core-api/irq/irq-domain.rst b/Documentation/translations/zh_CN/core-api/irq/irq-domain.rst index aaefeda0e164..7317cf5355c9 100644 --- a/Documentation/translations/zh_CN/core-api/irq/irq-domain.rst +++ b/Documentation/translations/zh_CN/core-api/irq/irq-domain.rst @@ -90,10 +90,6 @@ irq_domain映射的类型 映射的优点是固定时间查找IRQ号，而且irq_descs只分配给在用的IRQ。 缺点是该表 必须尽可能大的hwirq号。 -irq_domain_add_linear()和irq_domain_create_linear()在功能上是等价的， -除了第一个参数不同--前者接受一个Open Firmware特定的 'struct device_node' 而 -后者接受一个更通用的抽象 'struct fwnode_handle' 。 - 大多数驱动应该使用线性映射 树状映射 diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 73c25d40846c..3ba75a4ed3da 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -752,24 +752,6 @@ static inline void msi_device_domain_free_wired(struct irq_domain *domain, unsig } #endif -static inline struct irq_domain *irq_domain_add_linear(struct device_node *of_node, - unsigned int size, - const struct irq_domain_ops *ops, - void *host_data) -{ - struct irq_domain_info info = { - .fwnode = of_fwnode_handle(of_node), - .size = size, - .hwirq_max = size, - .ops = ops, - .host_data = host_data, - }; - struct irq_domain *d; - - d = irq_domain_instantiate(&info); - return IS_ERR(d) ? NULL : d; -} - #else /* CONFIG_IRQ_DOMAIN */ static inline void irq_dispose_mapping(unsigned int virq) { } static inline struct irq_domain *irq_find_matching_fwnode(struct fwnode_handle *fwnode, From 5ab54837fce04a1c9923d0bfd3d5de51fdc768b3 Mon Sep 17 00:00:00 2001 From: Jeffin Philip Date: Thu, 3 Sep 2026 13:40:48 +0530 Subject: [PATCH 0638/1198] fs: autofs: fix memory leak in autofs_fill_super() In autofs_fill_super(), we create a new inode using autofs_new_ino(), however, if we fail to create root_inode, (that is, root_inode failure path), we return -ENOMEM without freeing the new inode(ino) that we created causing a memory leak. Fix this by adding autofs_free_ino() to free the inode we created in root_inode failure path before returning ENOMEM. Reported-by: syzbot+df1db6e034b3953e19f5@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=df1db6e034b3953e19f5 Fixes: 66917f85db60 ("autofs: add: new_inode check in autofs_fill_super()") Cc: stable@vger.kernel.org Signed-off-by: Jeffin Philip Link: https://patch.msgid.link/20260903081048.132524-1-jeffinphilip14@gmail.com Signed-off-by: Ian Kent Signed-off-by: Christian Brauner (Amutable) --- fs/autofs/inode.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c index c1e210cec436..6b15a3717ba7 100644 --- a/fs/autofs/inode.c +++ b/fs/autofs/inode.c @@ -323,8 +323,10 @@ static int autofs_fill_super(struct super_block *s, struct fs_context *fc) return -ENOMEM; root_inode = autofs_get_inode(s, S_IFDIR | 0755); - if (!root_inode) + if (!root_inode) { + autofs_free_ino(ino); return -ENOMEM; + } root_inode->i_uid = ctx->uid; root_inode->i_gid = ctx->gid; From ac53977611428db3bc0b4ac0225e19c3e08ae50b Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 31 Aug 2026 14:17:15 -0700 Subject: [PATCH 0639/1198] crypto: x86/aria - add missing vzeroupper in AVX2 code Since the AVX2 optimized ARIA code uses YMM registers, execute vzeroupper before returning from it. This is needed to avoid degrading the performance of any later SSE code that may happen to be executed. Fixes: 37d8d3ae7a58 ("crypto: x86/aria - implement aria-avx2") Cc: stable@vger.kernel.org Cc: Taehee Yoo Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- arch/x86/crypto/aria-aesni-avx2-asm_64.S | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/x86/crypto/aria-aesni-avx2-asm_64.S b/arch/x86/crypto/aria-aesni-avx2-asm_64.S index ed53d4f46bd7..fda8cb8a99a8 100644 --- a/arch/x86/crypto/aria-aesni-avx2-asm_64.S +++ b/arch/x86/crypto/aria-aesni-avx2-asm_64.S @@ -982,6 +982,7 @@ SYM_TYPED_FUNC_START(aria_aesni_avx2_encrypt_32way) %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, %ymm15, %rax); + vzeroupper; FRAME_END RET; SYM_FUNC_END(aria_aesni_avx2_encrypt_32way) @@ -1007,6 +1008,7 @@ SYM_TYPED_FUNC_START(aria_aesni_avx2_decrypt_32way) %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, %ymm15, %rax); + vzeroupper; FRAME_END RET; SYM_FUNC_END(aria_aesni_avx2_decrypt_32way) @@ -1209,6 +1211,7 @@ SYM_TYPED_FUNC_START(aria_aesni_avx2_ctr_crypt_32way) %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, %ymm15, %r10); + vzeroupper; FRAME_END RET; SYM_FUNC_END(aria_aesni_avx2_ctr_crypt_32way) @@ -1359,6 +1362,7 @@ SYM_TYPED_FUNC_START(aria_aesni_avx2_gfni_encrypt_32way) %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, %ymm15, %rax); + vzeroupper; FRAME_END RET; SYM_FUNC_END(aria_aesni_avx2_gfni_encrypt_32way) @@ -1384,6 +1388,7 @@ SYM_TYPED_FUNC_START(aria_aesni_avx2_gfni_decrypt_32way) %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, %ymm15, %rax); + vzeroupper; FRAME_END RET; SYM_FUNC_END(aria_aesni_avx2_gfni_decrypt_32way) @@ -1428,6 +1433,7 @@ SYM_TYPED_FUNC_START(aria_aesni_avx2_gfni_ctr_crypt_32way) %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, %ymm15, %r10); + vzeroupper; FRAME_END RET; SYM_FUNC_END(aria_aesni_avx2_gfni_ctr_crypt_32way) From 60892a384aa1e65d0e703e1c513417bdf0c80777 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 31 Aug 2026 14:18:12 -0700 Subject: [PATCH 0640/1198] crypto: x86/aria - add missing vzeroupper in AVX-512 code Since the AVX-512 optimized ARIA code uses ZMM registers, execute vzeroupper before returning from it. This is needed to avoid degrading the performance of any later SSE code that may happen to be executed. Fixes: c970d42001f2 ("crypto: x86/aria - implement aria-avx512") Cc: stable@vger.kernel.org Cc: Taehee Yoo Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- arch/x86/crypto/aria-gfni-avx512-asm_64.S | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/x86/crypto/aria-gfni-avx512-asm_64.S b/arch/x86/crypto/aria-gfni-avx512-asm_64.S index 860887e5d02e..ca83eb126e06 100644 --- a/arch/x86/crypto/aria-gfni-avx512-asm_64.S +++ b/arch/x86/crypto/aria-gfni-avx512-asm_64.S @@ -800,6 +800,7 @@ SYM_TYPED_FUNC_START(aria_gfni_avx512_encrypt_64way) %zmm9, %zmm8, %zmm11, %zmm10, %zmm12, %zmm13, %zmm14, %zmm15, %rax); + vzeroupper; FRAME_END RET; SYM_FUNC_END(aria_gfni_avx512_encrypt_64way) @@ -825,6 +826,7 @@ SYM_TYPED_FUNC_START(aria_gfni_avx512_decrypt_64way) %zmm9, %zmm8, %zmm11, %zmm10, %zmm12, %zmm13, %zmm14, %zmm15, %rax); + vzeroupper; FRAME_END RET; SYM_FUNC_END(aria_gfni_avx512_decrypt_64way) @@ -966,6 +968,7 @@ SYM_TYPED_FUNC_START(aria_gfni_avx512_ctr_crypt_64way) %zmm9, %zmm8, %zmm11, %zmm10, %zmm12, %zmm13, %zmm14, %zmm15, %r10); + vzeroupper; FRAME_END RET; SYM_FUNC_END(aria_gfni_avx512_ctr_crypt_64way) From cdd812d0683dee14ead02c9eded568685e61b23f Mon Sep 17 00:00:00 2001 From: Daehyeon Ko <4ncienth@gmail.com> Date: Mon, 31 Aug 2026 09:12:21 +0900 Subject: [PATCH 0641/1198] exit: hold a reference to thread_pid across proc_flush_pid Commit 0a36bad01731 ("release_task: kill the no longer needed get/put_pid(thread_pid)") removed the reference around proc_flush_pid(). It assumed that free_pids(post.pids) at the end of release_task() would keep thread_pid alive until then. That assumption is wrong. __change_pid() only records a detached PID in post.pids when pid_has_task() is false for every PIDTYPE. If another task still uses the exiting task's PID as its process group or session ID, __unhash_process() removes the exiting task's PIDTYPE_PID link but leaves the PID out of post.pids. release_task() therefore holds no reference to it after dropping tasklist_lock. The other task can then remove the remaining PIDTYPE links. Its free_pids() call schedules delayed_put_pid(), and the RCU callback can free the PID before the first release_task() reaches proc_flush_pid(). An unprivileged reproducer races wait4(-1) against setsid() to trigger this ordering. Three of three fresh v7.2 KASAN boots reported: BUG: KASAN: slab-use-after-free in proc_invalidate_siblings_dcache+0x3e2/0x3f0 Read of size 8 by task h7_pid_reaper/1921 Call Trace: proc_invalidate_siblings_dcache release_task wait_consider_task __do_wait do_wait kernel_wait4 Freed by task 0: kmem_cache_free put_pid delayed_put_pid rcu_core Last potentially related work creation: __call_rcu_common free_pids ksys_setsid KASAN identified a 144-byte object from the pid cache and located the bad read 80 bytes into the freed object, matching pid->inodes. With an explicit reference, three of three fresh boots completed without a KASAN report. The concurrent RCU callback dropped its reference while proc_flush_pid() was protected, and the balancing put_pid() performed the final free afterward. Take a reference before __unhash_process() clears p->thread_pid and release it after proc_flush_pid() completes. A tested source reproducer is available privately on request. No controlled read or write, information leak, or privilege escalation is claimed. The mainline patch applies directly to v6.19.y and newer; v6.16.y through v6.18.y need a context-adjusted backport. Fixes: 0a36bad01731 ("release_task: kill the no longer needed get/put_pid(thread_pid)") Reported-by: syzbot+0aee5e8066eddbbe7397@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=0aee5e8066eddbbe7397 Reported-by: syzbot+e8b3520b53e78e90034e@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=e8b3520b53e78e90034e Cc: stable@vger.kernel.org # see patch description, needs adjustments for 6.16.y-6.18.y Signed-off-by: Daehyeon Ko <4ncienth@gmail.com> Link: https://patch.msgid.link/20260831001221.3755948-1-4ncienth@gmail.com Acked-by: Oleg Nesterov Reviewed-by: Bradley Morgan Signed-off-by: Christian Brauner (Amutable) --- kernel/exit.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/kernel/exit.c b/kernel/exit.c index 182c06671c78..e12072f1507c 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -261,8 +261,11 @@ void release_task(struct task_struct *p) pidfs_exit(p); cgroup_task_release(p); - /* Retrieve @thread_pid before __unhash_process() may set it to NULL. */ - thread_pid = task_pid(p); + /* + * Pin @thread_pid before __unhash_process() clears it. The last + * PIDTYPE detach can otherwise free it before proc_flush_pid(). + */ + thread_pid = get_pid(task_pid(p)); write_lock_irq(&tasklist_lock); ptrace_release_task(p); @@ -291,8 +294,8 @@ void release_task(struct task_struct *p) } write_unlock_irq(&tasklist_lock); - /* @thread_pid can't go away until free_pids() below */ proc_flush_pid(thread_pid); + put_pid(thread_pid); exit_cred_namespaces(p); add_device_randomness(&p->se.sum_exec_runtime, sizeof(p->se.sum_exec_runtime)); From 5541d897584127b795dbbdc51a78a2348b4eaaa4 Mon Sep 17 00:00:00 2001 From: "Vlastimil Babka (SUSE)" Date: Mon, 31 Aug 2026 18:02:38 +0200 Subject: [PATCH 0642/1198] mm/slab: disallow kfree_rcu_sheaf() on PREEMPT_RT again This partially reverts commit 2a8bb29ec9b2 ("mm/slab: allow kfree_rcu_sheaf() on PREEMPT_RT"). It was based on the assumption that local_trylock() is safe on PREEMPT_RT from any context. However kvfree_rcu() is also called by set_cpus_allowed_force() with task_struct::pi_lock acquired and there it's not safe, as syzbot has reported. For the immediate fix, skip kfree_rcu_sheaf() on PREEMPT_RT again from kvfree_call_rcu(). In theory, kfree_rcu_nolock() would have the same problem when called from under pi_lock on PREEMPT_RT but that can be addressed if such a caller is proposed. Add an explanation comment, courtesy of Sebastian. Reported-by: syzbot+acf142088e0182172e58@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=acf142088e0182172e58 Reported-by: ThangNN99 Fixes: 2a8bb29ec9b2 ("mm/slab: allow kfree_rcu_sheaf() on PREEMPT_RT") Reviewed-by: Sebastian Andrzej Siewior Link: https://patch.msgid.link/20260831-b4-kfree_rcu_hotfix-v1-1-4f0fb882638b@kernel.org Reviewed-by: Harry Yoo (Meta) Signed-off-by: Vlastimil Babka (SUSE) --- mm/slab_common.c | 18 ++++++++---------- mm/slub.c | 5 +++-- 2 files changed, 11 insertions(+), 12 deletions(-) diff --git a/mm/slab_common.c b/mm/slab_common.c index b19ba1b31484..7223a7596dab 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -1667,14 +1667,6 @@ static bool kfree_rcu_sheaf(void *obj) { struct kmem_cache *s; struct slab *slab; - unsigned int free_flags = SLAB_FREE_DEFAULT; - - /* - * It is not safe to spin on PREEMPT_RT because the kernel might be - * holding a raw spinlock and slab acquires sleeping locks. - */ - if (IS_ENABLED(CONFIG_PREEMPT_RT)) - free_flags = SLAB_FREE_NOLOCK; if (is_vmalloc_addr(obj)) return false; @@ -1685,7 +1677,7 @@ static bool kfree_rcu_sheaf(void *obj) s = slab->slab_cache; if (likely(!IS_ENABLED(CONFIG_NUMA) || slab_nid(slab) == numa_mem_id())) - return __kfree_rcu_sheaf(s, obj, free_flags); + return __kfree_rcu_sheaf(s, obj, SLAB_FREE_DEFAULT); return false; } @@ -2034,7 +2026,13 @@ void kvfree_call_rcu(struct kvfree_rcu_head *head, void *ptr) if (!head) might_sleep(); - if (kfree_rcu_sheaf(ptr)) + /* + * kvfree_rcu() is called by set_cpus_allowed_force() with + * task_struct::pi_lock acquired. On PREEMPT_RT the local_trylock() + * usage below will acquire the waitlock which must be avoided. + * Therefore avoid it on PREEMPT_RT. + */ + if (!IS_ENABLED(CONFIG_PREEMPT_RT) && kfree_rcu_sheaf(ptr)) return; // Queue the object but don't yet schedule the batch. diff --git a/mm/slub.c b/mm/slub.c index f9b56cb439e7..7a7e906a0e44 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -6088,8 +6088,9 @@ static void rcu_free_sheaf(struct rcu_head *head) /* * kvfree_call_rcu() can be called while holding a raw_spinlock_t. Since * __kfree_rcu_sheaf() may acquire a spinlock_t (sleeping lock on PREEMPT_RT), - * this would violate lock nesting rules. Therefore, kvfree_call_rcu() avoids - * this problem by passing SLAB_FREE_NOLOCK on PREEMPT_RT. + * this would violate lock nesting rules. Therefore, kfree_call_rcu_nolock() + * avoids this problem by passing SLAB_FREE_NOLOCK. kvfree_call_rcu() is + * bypassing the sheaves layer completely on PREEMPT_RT. * * However, lockdep still complains that it is invalid to acquire spinlock_t * while holding raw_spinlock_t, even on !PREEMPT_RT where spinlock_t is a From 4a724bcf5d703e18957397914d79156fa2cf1174 Mon Sep 17 00:00:00 2001 From: "Harry Yoo (Meta)" Date: Thu, 3 Sep 2026 15:32:26 +0100 Subject: [PATCH 0643/1198] mm/slab: take n->list_lock in __slab_try_return_freelist() to avoid race Commit ba7425312607 ("mm, slab: add an optimistic __slab_try_return_freelist()") incorrectly assumed that nobody has freed an object to the slab as long as slab->freelist is NULL and cmpxchg succeeds. However, as reported by Hyunwoo Kim [1], other CPUs might have freed an object to the slab, insert the slab to the partial list, then allocated an object from the slab, and be in the middle of removing the slab from the list under n->list_lock. Since __refill_objects_node() puts the slab back on pc.slabs outside n->list_lock, it might insert the slab into that list while the slab is concurrently being removed from n->partial. This led to a list corruption [1]: list_add corruption. next->prev should be prev (ffff888100000248), but was dead000000000122. (next=ffffea000416e410). kernel BUG at lib/list_debug.c:29! Oops: invalid opcode: 0000 [#1] SMP NOPTI CPU: 1 UID: 65534 PID: 144 Comm: poc Not tainted 7.2.0-16172-gcf72cbb39da8-dirty #1 PREEMPT(lazy) RIP: 0010:__list_add_valid_or_report+0x80/0xd0 ... Call Trace: alloc_from_new_slab+0x183/0x300 ___slab_alloc+0x31c/0x890 __kmalloc_noprof+0x3d4/0x800 lsm_blob_alloc+0x2d/0x50 security_msg_msg_alloc+0x26/0x90 load_msg+0x1aa/0x210 do_msgsnd+0x91/0x800 do_syscall_64+0x109/0x5d0 entry_SYSCALL_64_after_hwframe+0x77/0x7f ... Kernel panic - not syncing: Fatal exception This is a classic ABA problem where cmpxchg succeeds but the state has changed since __refill_objects_node() took the freelist from the slab. As Vlastimil Babka mentioned [2], it should be rare to return more than one slab (due to the racy read of slab->counters in get_partial_node_bulk()). Therefore, instead of introducing additional complexity, acquire and release n->list_lock twice in the worst case. Return the slab directly to the partial list and hold n->list_lock across the cmpxchg and add_partial(). This is similar to the initial version of commit ba7425312607 [3]. This is enough to avoid the race as the list manipulation is serialized by n->list_lock. While at it, bring back unlikely() hint now that the condition is unlikely. Reported-by: Hyunwoo Kim Closes: https://lore.kernel.org/linux-mm/apPa-cGLcyt90l-E@v4bel [1] Link: https://lore.kernel.org/linux-mm/ae25c193-b95f-40c1-83b6-1c2546467e41@kernel.org [2] Link: https://lore.kernel.org/all/20260421-b4-refill-optimistic-return-v1-1-24f0bfc1acff@kernel.org [3] Fixes: ba7425312607 ("mm, slab: add an optimistic __slab_try_return_freelist()") Cc: stable@vger.kernel.org Signed-off-by: Harry Yoo (Meta) Link: https://patch.msgid.link/20260903-slab-fix-aba-v3-1-b44cb6badd54@kernel.org Reviewed-by: Hao Li Signed-off-by: Vlastimil Babka (SUSE) --- mm/slub.c | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) diff --git a/mm/slub.c b/mm/slub.c index 7a7e906a0e44..54ec12503357 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -5680,10 +5680,12 @@ static noinline void free_to_partial_list( * * Fail if the slab isn't full anymore due to a concurrent free. */ -static bool __slab_try_return_freelist(struct kmem_cache *s, struct slab *slab, - void *head, int cnt) +static bool __slab_try_return_freelist(struct kmem_cache *s, + struct kmem_cache_node *n, + struct slab *slab, void *head, int cnt) { struct freelist_counters old, new; + unsigned long flags; old.freelist = slab->freelist; old.counters = slab->counters; @@ -5695,9 +5697,15 @@ static bool __slab_try_return_freelist(struct kmem_cache *s, struct slab *slab, new.counters = old.counters; new.inuse -= cnt; - if (!slab_update_freelist(s, slab, &old, &new, "__slab_try_return_freelist")) - return false; + spin_lock_irqsave(&n->list_lock, flags); + if (!slab_update_freelist(s, slab, &old, &new, "__slab_try_return_freelist")) { + spin_unlock_irqrestore(&n->list_lock, flags); + return false; + } + + add_partial(n, slab, ADD_TO_TAIL); + spin_unlock_irqrestore(&n->list_lock, flags); return true; } @@ -7297,10 +7305,8 @@ __refill_objects_node(struct kmem_cache *s, void **p, gfp_t gfp, unsigned int mi void *head = object; void *tail; - if (__slab_try_return_freelist(s, slab, head, count)) { - list_add(&slab->slab_list, &pc.slabs); + if (__slab_try_return_freelist(s, n, slab, head, count)) break; - } do { tail = object; @@ -7313,7 +7319,7 @@ __refill_objects_node(struct kmem_cache *s, void **p, gfp_t gfp, unsigned int mi break; } - if (!list_empty(&pc.slabs)) { + if (unlikely(!list_empty(&pc.slabs))) { spin_lock_irqsave(&n->list_lock, flags); list_for_each_entry(slab, &pc.slabs, slab_list) From 67b529f521a6676cdfc78b91b0217d7eaa84216b Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Fri, 4 Sep 2026 01:33:18 -0700 Subject: [PATCH 0644/1198] bpf: Don't infer non-NULL from a pointer with an unbounded offset reg_not_null() decides that a register holds a non-NULL value by looking at its type alone. For pointer types that allow arithmetic the type only guarantees a non-NULL base, in case of an unbound offset the runtime offset value might still add up to NULL. Consider the followng program: r6 = bpf_map_lookup_elem(map, &0); /* present */ if (r6 == 0) return 0; r7 = bpf_map_lookup_elem(map, &1); /* absent, NULL at runtime */ r8 = r7; r8 -= r6; /* pointer - pointer: unknown scalar, -r6 */ r8 <<= 1; r8 >>= 1; /* any non-negative offset is accepted by */ /* check_reg_sane_offset_ptr() */ r6 += r8; /* verifier: map value; runtime: zero */ if (r7 != r6) return 0; *(u8 *)(r7 + 0); /* r7 is inferred non-NULL, both are zero */ At runtime both registers are zero, the comparison is true and the load faults with NULL pointer dereference. Require the offset to be within +-BPF_MAX_VAR_OFF in reg_not_null(). Fixes: cac616db39c2 ("bpf: Verifier track null pointer branch_taken with JNE and JEQ") Reported-by: Nicholas Carlini Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/bpf/20260904083325.2083493-1-eddyz87@gmail.com Signed-off-by: Kumar Kartikeya Dwivedi --- kernel/bpf/verifier.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index d7dd0befbd10..faf1c8ff243d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -352,6 +352,13 @@ static bool reg_not_null(struct bpf_verifier_env *env, const struct bpf_reg_stat if (type_may_be_null(type)) return false; + /* + * The types below guarantee a non-NULL base, an unbounded offset can + * still wrap base + offset to zero. + */ + if (reg_smin(reg) <= -BPF_MAX_VAR_OFF || reg_smax(reg) >= BPF_MAX_VAR_OFF) + return false; + type = base_type(type); return type == PTR_TO_SOCKET || type == PTR_TO_TCP_SOCK || From 6752b90ccfb378e311e428932facf37c8625abae Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Fri, 4 Sep 2026 01:33:19 -0700 Subject: [PATCH 0645/1198] selftests/bpf: No non-NULL inference from unbounded offset pointers Check that a comparison against a pointer whose offset is not bounded from above does not make the verifier infer that a nullable pointer is not NULL, and that a bounded offset still does. W/o the previous patch the first test is accepted. Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/bpf/20260904083325.2083493-2-eddyz87@gmail.com Signed-off-by: Kumar Kartikeya Dwivedi --- .../bpf/progs/verifier_jeq_infer_not_null.c | 80 +++++++++++++++++++ 1 file changed, 80 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/verifier_jeq_infer_not_null.c b/tools/testing/selftests/bpf/progs/verifier_jeq_infer_not_null.c index b412a542ef76..8657e4a0d601 100644 --- a/tools/testing/selftests/bpf/progs/verifier_jeq_infer_not_null.c +++ b/tools/testing/selftests/bpf/progs/verifier_jeq_infer_not_null.c @@ -311,6 +311,86 @@ __naked void untrusted_mem_does_not_infer_map_value_non_null(void) : __clobber_all); } +/* + * A pointer with an offset that is not bounded from above may be null at + * runtime, hence it is not a witness for the pointer it is compared with. + */ +SEC("socket") +__failure +__msg("error: invalid dereference of R7 (a nullable map value pointer)") +__naked void unbounded_offset_does_not_infer_map_value_non_null(void) +{ + asm volatile (" \ + /* r6 = bpf_map_lookup_elem(map_hash, &0); */ \ + *(u64 *)(r10 - 8) = 0; \ + r1 = %[map_hash] ll; \ + r2 = r10; \ + r2 += -8; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto 1f; \ + r6 = r0; \ + /* r7 = bpf_map_lookup_elem(map_hash, &1); */ \ + *(u64 *)(r10 - 8) = 1; \ + r1 = %[map_hash] ll; \ + r2 = r10; \ + r2 += -8; \ + call %[bpf_map_lookup_elem]; \ + r7 = r0; \ + /* pointer - pointer is an unknown scalar */ \ + r8 = r7; \ + r8 -= r6; \ + /* r8 is in [0, S64_MAX] */ \ + r8 <<= 1; \ + r8 >>= 1; \ + /* r6 may wrap to zero at runtime */ \ + r6 += r8; \ + if r7 != r6 goto 1f; \ + r0 = *(u8 *)(r7 + 0); \ +1: r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash) + : __clobber_all); +} + +/* Same, but the offset is bounded, so the inference is still done. */ +SEC("socket") +__success +__naked void bounded_offset_infers_map_value_non_null(void) +{ + asm volatile (" \ + /* r6 = bpf_map_lookup_elem(map_hash, &0); */ \ + *(u64 *)(r10 - 8) = 0; \ + r1 = %[map_hash] ll; \ + r2 = r10; \ + r2 += -8; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto 1f; \ + r6 = r0; \ + /* r7 = bpf_map_lookup_elem(map_hash, &1); */ \ + *(u64 *)(r10 - 8) = 1; \ + r1 = %[map_hash] ll; \ + r2 = r10; \ + r2 += -8; \ + call %[bpf_map_lookup_elem]; \ + r7 = r0; \ + /* pointer - pointer is an unknown scalar */ \ + r8 = r7; \ + r8 -= r6; \ + /* r8 is in [0, 3] */ \ + r8 &= 3; \ + r6 += r8; \ + if r7 != r6 goto 1f; \ + r0 = *(u8 *)(r7 + 0); \ +1: r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash) + : __clobber_all); +} + void kfunc_root(void) { bpf_rdonly_cast(0, 0); From 73a98f96811e2cb0f4210b1caa8cb322f92f2a2b Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Fri, 4 Sep 2026 01:33:20 -0700 Subject: [PATCH 0646/1198] bpf: Don't resurrect a scalar id dropped by collect_linked_regs() check_cond_jmp_op() copies the compared registers into env->{false,true}_reg{1,2} before collect_linked_regs() runs and copies those snapshots back into both branch states afterwards. collect_linked_regs() records at most LINKED_REGS_MAX members of a linked registers group in the jump history and calls clear_scalar_id() for every member that does not fit. The compared register is not exempt from that. As a consequence, sync_linked_regs() might adjust ranges for more registers than bpf_bt_sync_linked_regs() can propagate precision to. Collect the linked registers before the snapshots are taken instead. This might lead to some unnecessary clear_scalar_id's, but from previous testing situations with many linked registers are extremely rare. Fixes: ec1d77cb0ee9 ("bpf: Use bpf_verifier_env buffers for reg_set_min_max") Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/bpf/20260904083325.2083493-3-eddyz87@gmail.com Signed-off-by: Kumar Kartikeya Dwivedi --- kernel/bpf/verifier.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index faf1c8ff243d..1fb0c832611c 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -16898,6 +16898,16 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, return err; } + /* + * Collect the linked registers before env->{true,false}_reg{1,2} setup, + * otherwise ids dropped by collect_linked_regs() would be resurrected + * when env->{true,false}_reg{1,2} are copied back. + */ + if (BPF_SRC(insn->code) == BPF_X && src_reg->type == SCALAR_VALUE && src_reg->id) + collect_linked_regs(env, this_branch, src_reg->id, &linked_regs); + if (dst_reg->type == SCALAR_VALUE && dst_reg->id) + collect_linked_regs(env, this_branch, dst_reg->id, &linked_regs); + is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32; env->false_reg1 = *dst_reg; env->false_reg2 = *src_reg; @@ -16952,10 +16962,6 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, * 'this_branch' and 'other_branch' share this history * if parent state is created. */ - if (BPF_SRC(insn->code) == BPF_X && src_reg->type == SCALAR_VALUE && src_reg->id) - collect_linked_regs(env, this_branch, src_reg->id, &linked_regs); - if (dst_reg->type == SCALAR_VALUE && dst_reg->id) - collect_linked_regs(env, this_branch, dst_reg->id, &linked_regs); if (linked_regs.cnt > 1) { err = bpf_push_jmp_history(env, this_branch, 0, 0, 0, linked_regs_pack(&linked_regs)); if (err) From bc412b3fb185540112fcc99ac91a14e57418d28e Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Fri, 4 Sep 2026 01:33:21 -0700 Subject: [PATCH 0647/1198] selftests/bpf: Check the linked regs cap for the compared register linked_regs_too_many_regs checks that collect_linked_regs() ties at most LINKED_REGS_MAX registers for a single jump. Compare r5 instead of r0, so that the register the jump compares is itself the member that does not fit, and check that it comes out of the jump unlinked. W/o the previous patch env->{false,true}_reg{1,2} bring r5's id back and insn 7 is logged as "R5=scalar(id=1,...)". Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/bpf/20260904083325.2083493-4-eddyz87@gmail.com Signed-off-by: Kumar Kartikeya Dwivedi --- .../selftests/bpf/progs/verifier_scalar_ids.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c index 663d15fc5fd2..256547048cc4 100644 --- a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c +++ b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c @@ -380,13 +380,14 @@ SEC("socket") __success __log_level(2) __flag(BPF_F_TEST_STATE_FREQ) /* - * check that r0 and r5 have different IDs after 'if', - * collect_linked_regs() can't tie more than 5 registers for a single insn. + * check that r5 is unlinked after 'if', collect_linked_regs() can't tie + * more than 5 registers for a single insn and the register compared by + * the jump is not exempt from that. */ -__msg("7: (25) if r0 > 0x7 goto pc+0 ; R0=scalar(id=1") +__msg("7: (25) if r5 > 0x7 goto pc+0 ; R5=scalar(smin=") __msg("12: (bf) r5 = r5 ; R5=scalar(id=2") /* check that r{0-4} are marked precise after 'if' */ -__msg("frame0: regs=r0 stack= before 7: (25) if r0 > 0x7 goto pc+0") +__msg("frame0: regs=r0 stack= before 7: (25) if r5 > 0x7 goto pc+0") __msg("frame0: parent state regs=r0,r1,r2,r3,r4 stack=:") __naked void linked_regs_too_many_regs(void) { @@ -400,8 +401,8 @@ __naked void linked_regs_too_many_regs(void) "r3 = r0;" "r4 = r0;" "r5 = r0;" - /* propagate range for r{0-5} */ - "if r0 > 7 goto +0;" + /* r{0-4} fill the record, r5 does not fit and is unlinked */ + "if r5 > 7 goto +0;" /* keep r{1-4} live */ "r1 = r1;" "r2 = r2;" From e51179a4e09846f8fd0f26a05068520de2b301bf Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Fri, 4 Sep 2026 01:33:22 -0700 Subject: [PATCH 0648/1198] bpf: Don't predict JMP32 pointer vs zero comparisons Consider the following program: r1 = map_value; /* low 32 bits are zero at runtime */ r6 = 0xdead000000000000; if w1 != 0 goto l1; l0: r1 += r6; r2 = *(u64 *)(r1 + 0); exit; l1: r6 = 0; goto l0; At the moment is_branch_taken() reports the jump as always taken, because it does not distinguish between BPF_JMP and BPF_JMP32 comparisons when processing 'if w1 != 0 ...'. Fixes: cac616db39c2 ("bpf: Verifier track null pointer branch_taken with JNE and JEQ") Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/bpf/20260904083325.2083493-5-eddyz87@gmail.com Signed-off-by: Kumar Kartikeya Dwivedi --- kernel/bpf/verifier.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1fb0c832611c..303368460ec1 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -16337,6 +16337,13 @@ static int is_branch_taken(struct bpf_verifier_env *env, struct bpf_reg_state *r if (__is_pointer_value(false, reg1) || __is_pointer_value(false, reg2)) { u64 val; + /* + * The low 32 bits of a valid pointer may well be zero, hence + * nothing below applies to a 32-bit comparison. + */ + if (is_jmp32) + return -1; + /* arrange that reg2 is a scalar, and reg1 is a pointer */ if (!is_reg_const(reg2, is_jmp32)) { opcode = flip_opcode(opcode); From 836b2fe544a5e9b5ce116622cb36fba33838c6fd Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Fri, 4 Sep 2026 01:33:23 -0700 Subject: [PATCH 0649/1198] selftests/bpf: Check that JMP32 pointer vs zero jumps are not predicted Add jmp32_ptr_vs_zero_jne: the fall-through of the 32-bit compare, which the verifier used to skip, contains an out of bounds map value access, hence w/o the previous patch the program is accepted. See previous patch for detailed description. Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/bpf/20260904083325.2083493-6-eddyz87@gmail.com Signed-off-by: Kumar Kartikeya Dwivedi --- .../bpf/progs/verifier_jeq_infer_not_null.c | 27 +++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/verifier_jeq_infer_not_null.c b/tools/testing/selftests/bpf/progs/verifier_jeq_infer_not_null.c index 8657e4a0d601..410acbf658c7 100644 --- a/tools/testing/selftests/bpf/progs/verifier_jeq_infer_not_null.c +++ b/tools/testing/selftests/bpf/progs/verifier_jeq_infer_not_null.c @@ -391,6 +391,33 @@ __naked void bounded_offset_infers_map_value_non_null(void) : __clobber_all); } +/* + * The low 32 bits of a map value pointer may be zero, hence a 32-bit + * compare with zero cannot be predicted from the pointer being non-NULL + * and both successors of such a jump have to be verified. + */ +SEC("socket") +__failure __msg("invalid access to map value, value_size=4 off=32 size=4") +__naked void jmp32_ptr_vs_zero_jne(void) +{ + asm volatile (" \ + /* r0 = bpf_map_lookup_elem(map_hash, &key); */ \ + *(u64 *)(r10 - 8) = 0; \ + r1 = %[map_hash] ll; \ + r2 = r10; \ + r2 += -8; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto 1f; \ + if w0 != 0 goto 1f; \ + r0 = *(u32 *)(r0 + 32); \ +1: r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash) + : __clobber_all); +} + void kfunc_root(void) { bpf_rdonly_cast(0, 0); From 6aed0134d3cda6382385a734ae0158eb7df6b142 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Fri, 4 Sep 2026 01:33:24 -0700 Subject: [PATCH 0650/1198] bpf: Mark the zero register precise for a register-form NULL check check_cond_jmp_op() accepts "if rA rB" as a NULL check for a nullable pointer rA when rB is a scalar known to be zero, lifts PTR_MAYBE_NULL from rA in the corresponding branch and does not mark rB precise. Consider the following program: r0 = bpf_get_prandom_u32(); r6 = 1; /* the r6 == 0 path is explored first */ if (r0 == 0) goto 1f; r6 = 0; 1: r0 = bpf_map_lookup_elem(map, &0); /* absent, NULL at runtime */ if (r0 == r6) goto 2f; /* taken as a NULL check for r0 */ *(u8 *)(r0 + 0); /* verifier: map value; runtime: zero */ 2: return 0; The r6 == 0 path is explored first and the dereference is accepted. The r6 == 1 path is pruned at the checkpoint recorded for (1), so the comparison is never verified with a non-zero r6. At runtime a failed lookup returns NULL, NULL != 1 takes the non-NULL edge and the program dereferences a pointer that is zero. Fixes: 2f4cb53eed44 ("bpf: detect non null pointer with register operand in JEQ/JNE.") Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/bpf/20260904083325.2083493-7-eddyz87@gmail.com Signed-off-by: Kumar Kartikeya Dwivedi --- kernel/bpf/verifier.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 303368460ec1..fde5d046b6e3 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -17052,6 +17052,15 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, type_may_be_null(dst_reg->type) && ((BPF_SRC(insn->code) == BPF_K && insn->imm == 0) || (BPF_SRC(insn->code) == BPF_X && bpf_register_is_null(src_reg)))) { + /* + * For BPF_X the zero is a property of this execution path, + * hence src_reg has to be precise. + */ + if (BPF_SRC(insn->code) == BPF_X) { + err = mark_chain_precision(env, insn->src_reg); + if (err) + return err; + } /* Mark all identical registers in each branch as either * safe or unknown depending R == 0 or R != 0 conditional. */ From 6b31560c6bc1a8a7a70792c7b3ca4c1ea322063b Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Fri, 4 Sep 2026 01:33:25 -0700 Subject: [PATCH 0651/1198] selftests/bpf: No non-NULL inference from an imprecise zero register Check that a register-form NULL check does not lift PTR_MAYBE_NULL on a path where the compared register is non-zero. W/o the previous patch the program is accepted. Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/bpf/20260904083325.2083493-8-eddyz87@gmail.com Signed-off-by: Kumar Kartikeya Dwivedi --- .../bpf/progs/verifier_jeq_infer_not_null.c | 34 +++++++++++++++++++ 1 file changed, 34 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/verifier_jeq_infer_not_null.c b/tools/testing/selftests/bpf/progs/verifier_jeq_infer_not_null.c index 410acbf658c7..3c789c565b18 100644 --- a/tools/testing/selftests/bpf/progs/verifier_jeq_infer_not_null.c +++ b/tools/testing/selftests/bpf/progs/verifier_jeq_infer_not_null.c @@ -418,6 +418,40 @@ __naked void jmp32_ptr_vs_zero_jne(void) : __clobber_all); } +/* + * The below program is explored in two paths: r6 == 0 and r6 == 1. + * On the first path comparison "if r0 == r6 goto 2f" should mark r6 as precise, + * otherwise unsafe path with r6 == 1 would be incorrectly pruned. + */ +SEC("socket") +__failure +__flag(BPF_F_TEST_STATE_FREQ) +__msg("error: invalid dereference of R0 (a nullable map value pointer)") +__naked void imprecise_zero_does_not_infer_map_value_non_null(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + /* r6 is 0 on the path explored first, 1 on the other */\ + r6 = 1; \ + if r0 == 0 goto 1f; \ + r6 = 0; \ + /* r0 = bpf_map_lookup_elem(map_hash, &0); */ \ +1: *(u64 *)(r10 - 8) = 0; \ + r1 = %[map_hash] ll; \ + r2 = r10; \ + r2 += -8; \ + call %[bpf_map_lookup_elem]; \ + if r0 == r6 goto 2f; \ + r0 = *(u8 *)(r0 + 0); \ +2: r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32), + __imm(bpf_map_lookup_elem), + __imm_addr(map_hash) + : __clobber_all); +} + void kfunc_root(void) { bpf_rdonly_cast(0, 0); From 63b6a48c951d63bf39d44603ada48a987ccf66eb Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Fri, 4 Sep 2026 21:44:23 +0800 Subject: [PATCH 0652/1198] LoongArch: Do not select HAVE_RUST when KASAN is enabled After commit 2625480a1bf7 ("hardening: Default randstruct off with rust for better allmodconfig support"), which allows Rust to be enabled for allmodconfig, ARCH=loongarch allmodconfig starts failing with: error: kernel-address sanitizer is not supported for this target error: aborting due to 1 previous error make[4]: *** [rust/Makefile:741: rust/core.o] Error 1 For the same reason as the commit 84a0f7caafc679f7 ("ARM: Do not select HAVE_RUST when KASAN is enabled"), do not select HAVE_RUST when KASAN is enabled until the loongarch64-unknown-none-softfloat target in rustc supports KASAN. Cc: stable@vger.kernel.org Fixes: 90868ff9cade ("LoongArch: Enable initial Rust support") Acked-by: Miguel Ojeda Signed-off-by: Nathan Chancellor Signed-off-by: Huacai Chen --- arch/loongarch/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index a21f51e5815e..2067d1f2ad7a 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -175,7 +175,7 @@ config LOONGARCH select HAVE_RELIABLE_STACKTRACE if UNWINDER_ORC select HAVE_RETHOOK select HAVE_RSEQ - select HAVE_RUST + select HAVE_RUST if !KASAN select HAVE_SAMPLE_FTRACE_DIRECT select HAVE_SAMPLE_FTRACE_DIRECT_MULTI select HAVE_SETUP_PER_CPU_AREA if NUMA From 20a9e97137caaa3fbb27f22f83a5ad80cbd03b01 Mon Sep 17 00:00:00 2001 From: Hemanth Selam Date: Fri, 4 Sep 2026 21:44:24 +0800 Subject: [PATCH 0653/1198] LoongArch: Fix typo "avaliable" in comment of vmlinux.lds.S Correct "avaliable" to "available", reported by scripts/checkpatch.pl using the misspelling list in scripts/spelling.txt. It only touches the comments, no code changes. Assisted-by: Cursor:claude-opus-5 Signed-off-by: Hemanth Selam Signed-off-by: Huacai Chen --- arch/loongarch/kernel/vmlinux.lds.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/loongarch/kernel/vmlinux.lds.S b/arch/loongarch/kernel/vmlinux.lds.S index 840d944c2f73..ce097e25881f 100644 --- a/arch/loongarch/kernel/vmlinux.lds.S +++ b/arch/loongarch/kernel/vmlinux.lds.S @@ -23,7 +23,7 @@ #include "image-vars.h" /* - * Max avaliable Page Size is 64K, so we set SectionAlignment + * Max available Page Size is 64K, so we set SectionAlignment * field of EFI application to 64K. */ PECOFF_FILE_ALIGN = 0x200; From 3e1b64bd8cd2bc15c514d90b3dd0a55c53302f3a Mon Sep 17 00:00:00 2001 From: Anthony Iliopoulos Date: Fri, 4 Sep 2026 21:44:43 +0800 Subject: [PATCH 0654/1198] LoongArch: Remove unused setup_profiling_timer() function setup_profiling_timer() is not used by any code at this point. Since a default weak implementation exists, there is no need to still keep this arch-specific definition around. Remove it along with the now-redundant profile header includes. Signed-off-by: Anthony Iliopoulos Signed-off-by: Huacai Chen --- arch/loongarch/kernel/smp.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index d4b5d1b6bb01..11f54837f56c 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -14,7 +14,6 @@ #include #include #include -#include #include #include #include @@ -716,13 +715,6 @@ void smp_send_stop(void) smp_call_function(stop_this_cpu, NULL, 0); } -#ifdef CONFIG_PROFILING -int setup_profiling_timer(unsigned int multiplier) -{ - return 0; -} -#endif - static void flush_tlb_all_ipi(void *info) { local_flush_tlb_all(); From c3f2feace5e4f4b01b68b9f947b19adb4155c32e Mon Sep 17 00:00:00 2001 From: Wentao Guan Date: Fri, 4 Sep 2026 21:44:43 +0800 Subject: [PATCH 0655/1198] LoongArch: Do not save/restore percpu base register in rethook trampoline The rethook trampoline saves $r21 ($u0), the percpu base, into its frame at entry and restores it at exit. Inbetween rethook_trampoline_handler() may schedule via preempt_enable_notrace(). If the task migrates to another CPU, the frame's $r21 holds the old CPU's percpu base, and restoring it poisons $r21 on the new CPU. Until the next user->kernel transition heals $r21, all this_cpu_*() accesses (runqueues, RCU per-CPU data, timer tick programming, FPU ownership) hit the wrong CPU's percpu area. Under kretprobe-heavy preemptible load this can corrupt scheduler and timer state: scheduling-while-atomic splats, wrong-CPU RCU warnings, WARN_ON_ONCE(rq != this_rq()) in nohz_balance_exit_idle(), and CPUs parking in the idle loop with the constant timer never re-armed (hard lockup). Reproduces on a Loongson-3A6000 with kretprobes on VFS paths plus heavy file churn (OS install / unsquashfs). By convention $r21 always holds the current CPU's percpu base in kernel mode: SAVE_SOME() at exception entry reloads it only when coming from user mode, and RESTORE_SOME() restores it only when returning to user mode; the context-switch path never writes it. Therefore the live $r21 at trampoline exit is already correct, and nothing inbetween can change it legitimately (kernel C code cannot write a global register variable). The same flaw existed even in the pre-rethook kretprobe trampoline since v6.3; it was carried over when rethook replaced it. Drop both the save and the restore here. Drop the restore is enough to solve the issue, and drop the save is to keep the code tidy and no need to clear it. Cc: stable@vger.kernel.org # v6.3+ Fixes: 3f5536860086d ("LoongArch: Add kretprobes support") Assisted-by: Kimi:Kimi-K3 # debug and root-cause analysis Signed-off-by: Wentao Guan Signed-off-by: Huacai Chen --- arch/loongarch/kernel/rethook_trampoline.S | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/loongarch/kernel/rethook_trampoline.S b/arch/loongarch/kernel/rethook_trampoline.S index 2e009fbea53f..160189444684 100644 --- a/arch/loongarch/kernel/rethook_trampoline.S +++ b/arch/loongarch/kernel/rethook_trampoline.S @@ -24,7 +24,6 @@ cfi_st t6, PT_R18 cfi_st t7, PT_R19 cfi_st t8, PT_R20 - cfi_st u0, PT_R21 cfi_st fp, PT_R22 cfi_st s0, PT_R23 cfi_st s1, PT_R24 @@ -59,7 +58,6 @@ cfi_ld t6, PT_R18 cfi_ld t7, PT_R19 cfi_ld t8, PT_R20 - cfi_ld u0, PT_R21 cfi_ld fp, PT_R22 cfi_ld s0, PT_R23 cfi_ld s1, PT_R24 From 72ce4b24676e8b3b75376c4c559dd81c1ac52d5a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=A9my=20Jean?= Date: Fri, 4 Sep 2026 21:44:43 +0800 Subject: [PATCH 0656/1198] LoongArch: Avoid preempt count underflow without probe MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit LoongArch uses break 11 for the breakpoint placed after an instruction that Kprobes executes out of line. Since userspace can issue the same break instruction, do_bp() can reach kprobe_singlestep_handler() when there is no current probe. The handler actually returns false in this case, but it first calls preempt_enable_no_resched(). The corresponding preempt_disable() is done by kprobe_breakpoint_handler() on a real Kprobe hit, so it has not run here. As a result, an ordinary userspace breakpoint (code 11) underflows the current task's preempt count. This also makes in_interrupt() return true until the task schedules. One visible consequence is the socket cgroup attribution: cgroup_sk_alloc() treats the allocation as interrupt context and assigns the socket to the root cgroup. A socket opened from the SIGTRAP handler can then avoid a BPF_CGROUP_INET_SOCK_CREATE policy attached to the task's own cgroup. Return as soon as kprobe_running() reports no active probe. The same check has appeared in [PATCH v10 2/4] of the original LoongArch Kprobes series, but was dropped before the feature reached mainline. Cc: stable@vger.kernel.org Fixes: 6d4cc40fb5f5 ("LoongArch: Add kprobes support") Link: https://lore.kernel.org/loongarch/1670575981-14389-3-git-send-email-yangtiezhu@loongson.cn/ Assisted-by: Codex:gpt-5 Signed-off-by: Jérémy Jean Signed-off-by: Huacai Chen --- arch/loongarch/kernel/kprobes.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/loongarch/kernel/kprobes.c b/arch/loongarch/kernel/kprobes.c index 1985ed30dd16..ddfefea17472 100644 --- a/arch/loongarch/kernel/kprobes.c +++ b/arch/loongarch/kernel/kprobes.c @@ -275,6 +275,9 @@ bool kprobe_singlestep_handler(struct pt_regs *regs) struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); unsigned long addr = instruction_pointer(regs); + if (!cur) + return false; + if (cur && (kcb->kprobe_status & (KPROBE_HIT_SS | KPROBE_REENTER)) && ((unsigned long)&cur->ainsn.insn[1] == addr)) { restore_local_irqflag(kcb, regs); From 30419a0aa128135a81be917eaa3bd2f1a10c9ca3 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Fri, 4 Sep 2026 21:44:43 +0800 Subject: [PATCH 0657/1198] LoongArch: BPF: Fix off-by-one error for insn_is_cast_user() In the LoongArch BPF JIT code, the branch offset represents the number of instructions. An offset of 1 means the target of the "beq" is the current PC plus 1 instruction (PC + 4 bytes). This matches the exact same path as the sequential non-branch execution, the "or" instruction is always executed for the cast_user JIT arm in build_insn(). If the pointer is not NULL, there is no side effect. But if the pointer is NULL, it is incorrectly combined with the base address and turns into a non-zero address, meaning a zero arena offset no longer casts to NULL. Fix this by changing the branch offset from 1 to 2, which properly skips the "or" instruction and jumps directly to the "move_reg" instruction if the pointer is NULL, ensuring the destination register is safely cleared to 0. Cc: stable@vger.kernel.org Fixes: 4fdb5dd8aeba ("LoongArch: BPF: Implement bpf_addr_space_cast instruction") Signed-off-by: Tiezhu Yang Signed-off-by: Huacai Chen --- arch/loongarch/net/bpf_jit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c index 1eb588e443c9..4da278900938 100644 --- a/arch/loongarch/net/bpf_jit.c +++ b/arch/loongarch/net/bpf_jit.c @@ -717,7 +717,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext move_reg(ctx, t1, src); emit_zext_32(ctx, t1, true); move_imm(ctx, dst, (ctx->user_vm_start >> 32) << 32, false); - emit_insn(ctx, beq, t1, LOONGARCH_GPR_ZERO, 1); + emit_insn(ctx, beq, t1, LOONGARCH_GPR_ZERO, 2); emit_insn(ctx, or, t1, dst, t1); move_reg(ctx, dst, t1); break; From f7a1064cce3b100b54780c68529176232d8eb01e Mon Sep 17 00:00:00 2001 From: Chaithanya Lagisetty Date: Fri, 4 Sep 2026 21:44:53 +0800 Subject: [PATCH 0658/1198] LoongArch: KVM: Free init resources if kvm_init() fails kvm_loongarch_init() calls kvm_loongarch_env_init() to allocate the per-CPU kvm_context (vmcs) and kvm_loongarch_ops and to register the perf callbacks, and then calls kvm_init(). If kvm_init() fails its result is returned directly, but since module_init() does not run the module_exit() stuff on failure, so kvm_loongarch_env_exit() is never called and those resources are leaked. So call kvm_loongarch_env_exit() when kvm_init() fails, matching the teardown-on-failure pattern used by riscv_kvm_init(). Cc: stable@vger.kernel.org Fixes: 2bd6ac687261 ("LoongArch: KVM: Implement kvm module related interface") Reviewed-by: Bibo Mao Signed-off-by: Chaithanya Lagisetty Signed-off-by: Huacai Chen --- arch/loongarch/kvm/main.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/arch/loongarch/kvm/main.c b/arch/loongarch/kvm/main.c index 3e1005526f4b..b6ddf5827c03 100644 --- a/arch/loongarch/kvm/main.c +++ b/arch/loongarch/kvm/main.c @@ -428,7 +428,11 @@ static int kvm_loongarch_init(void) if (r) return r; - return kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE); + r = kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE); + if (r) + kvm_loongarch_env_exit(); + + return r; } static void kvm_loongarch_exit(void) From 4af22177032ab2357bf551fbfcdebc8fd9f2502d Mon Sep 17 00:00:00 2001 From: Chaithanya Lagisetty Date: Fri, 4 Sep 2026 21:44:53 +0800 Subject: [PATCH 0659/1198] LoongArch: KVM: Add unregister helpers for the KVM interrupt devices The IPI/EIOINTC/PCH-PIC/DMSINTC KVM devices each have a helper that registers their kvm_device_ops, but there is no counterpart to remove them, so a caller that needs to undo a registration has to open-code kvm_unregister_device_ops() with the matching device type. Add kvm_loongarch_unregister_{ipi,eiointc,pch_pic,dmsintc}_device() next to the existing register helpers. kvm_unregister_device_ops() is a no-op when the corresponding device type is not currently registered. No functional change, as there are no callers yet. Cc: stable@vger.kernel.org Suggested-by: Bibo Mao Reviewed-by: Bibo Mao Signed-off-by: Chaithanya Lagisetty Signed-off-by: Huacai Chen --- arch/loongarch/include/asm/kvm_dmsintc.h | 1 + arch/loongarch/include/asm/kvm_eiointc.h | 1 + arch/loongarch/include/asm/kvm_ipi.h | 1 + arch/loongarch/include/asm/kvm_pch_pic.h | 1 + arch/loongarch/kvm/intc/dmsintc.c | 5 +++++ arch/loongarch/kvm/intc/eiointc.c | 5 +++++ arch/loongarch/kvm/intc/ipi.c | 5 +++++ arch/loongarch/kvm/intc/pch_pic.c | 5 +++++ 8 files changed, 24 insertions(+) diff --git a/arch/loongarch/include/asm/kvm_dmsintc.h b/arch/loongarch/include/asm/kvm_dmsintc.h index 5a71b9ccbe78..7c0158764d84 100644 --- a/arch/loongarch/include/asm/kvm_dmsintc.h +++ b/arch/loongarch/include/asm/kvm_dmsintc.h @@ -20,6 +20,7 @@ struct dmsintc_state { }; int kvm_loongarch_register_dmsintc_device(void); +void kvm_loongarch_unregister_dmsintc_device(void); void dmsintc_inject_irq(struct kvm_vcpu *vcpu); int dmsintc_set_irq(struct kvm *kvm, u64 addr, int data, int level); int dmsintc_deliver_msi_to_vcpu(struct kvm *kvm, struct kvm_vcpu *vcpu, u32 vector, int level); diff --git a/arch/loongarch/include/asm/kvm_eiointc.h b/arch/loongarch/include/asm/kvm_eiointc.h index 8b7a2fa3f7f8..9633fbfc066d 100644 --- a/arch/loongarch/include/asm/kvm_eiointc.h +++ b/arch/loongarch/include/asm/kvm_eiointc.h @@ -79,6 +79,7 @@ struct loongarch_eiointc { }; int kvm_loongarch_register_eiointc_device(void); +void kvm_loongarch_unregister_eiointc_device(void); void eiointc_set_irq(struct loongarch_eiointc *s, int irq, int level); #endif /* __ASM_KVM_EIOINTC_H */ diff --git a/arch/loongarch/include/asm/kvm_ipi.h b/arch/loongarch/include/asm/kvm_ipi.h index 060163dfb4a3..d1d72d4bb8d1 100644 --- a/arch/loongarch/include/asm/kvm_ipi.h +++ b/arch/loongarch/include/asm/kvm_ipi.h @@ -41,5 +41,6 @@ struct ipi_state { #define IOCSR_ANY_SEND 0x158 int kvm_loongarch_register_ipi_device(void); +void kvm_loongarch_unregister_ipi_device(void); #endif diff --git a/arch/loongarch/include/asm/kvm_pch_pic.h b/arch/loongarch/include/asm/kvm_pch_pic.h index e74b3b742634..887b0431fd20 100644 --- a/arch/loongarch/include/asm/kvm_pch_pic.h +++ b/arch/loongarch/include/asm/kvm_pch_pic.h @@ -70,6 +70,7 @@ struct loongarch_pch_pic { struct kvm_kernel_irq_routing_entry; int kvm_loongarch_register_pch_pic_device(void); +void kvm_loongarch_unregister_pch_pic_device(void); void pch_pic_set_irq(struct loongarch_pch_pic *s, int irq, int level); int pch_msi_set_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, int level); diff --git a/arch/loongarch/kvm/intc/dmsintc.c b/arch/loongarch/kvm/intc/dmsintc.c index bb7285c49df3..c7d8841df96f 100644 --- a/arch/loongarch/kvm/intc/dmsintc.c +++ b/arch/loongarch/kvm/intc/dmsintc.c @@ -180,3 +180,8 @@ int kvm_loongarch_register_dmsintc_device(void) { return kvm_register_device_ops(&kvm_dmsintc_dev_ops, KVM_DEV_TYPE_LOONGARCH_DMSINTC); } + +void kvm_loongarch_unregister_dmsintc_device(void) +{ + kvm_unregister_device_ops(KVM_DEV_TYPE_LOONGARCH_DMSINTC); +} diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c index 84d84bd432d7..80f78e07c74a 100644 --- a/arch/loongarch/kvm/intc/eiointc.c +++ b/arch/loongarch/kvm/intc/eiointc.c @@ -695,3 +695,8 @@ int kvm_loongarch_register_eiointc_device(void) { return kvm_register_device_ops(&kvm_eiointc_dev_ops, KVM_DEV_TYPE_LOONGARCH_EIOINTC); } + +void kvm_loongarch_unregister_eiointc_device(void) +{ + kvm_unregister_device_ops(KVM_DEV_TYPE_LOONGARCH_EIOINTC); +} diff --git a/arch/loongarch/kvm/intc/ipi.c b/arch/loongarch/kvm/intc/ipi.c index fcfaf1a66790..7b333a4a0430 100644 --- a/arch/loongarch/kvm/intc/ipi.c +++ b/arch/loongarch/kvm/intc/ipi.c @@ -463,3 +463,8 @@ int kvm_loongarch_register_ipi_device(void) { return kvm_register_device_ops(&kvm_ipi_dev_ops, KVM_DEV_TYPE_LOONGARCH_IPI); } + +void kvm_loongarch_unregister_ipi_device(void) +{ + kvm_unregister_device_ops(KVM_DEV_TYPE_LOONGARCH_IPI); +} diff --git a/arch/loongarch/kvm/intc/pch_pic.c b/arch/loongarch/kvm/intc/pch_pic.c index e7b77705c516..83fa2386cf81 100644 --- a/arch/loongarch/kvm/intc/pch_pic.c +++ b/arch/loongarch/kvm/intc/pch_pic.c @@ -500,3 +500,8 @@ int kvm_loongarch_register_pch_pic_device(void) { return kvm_register_device_ops(&kvm_pch_pic_dev_ops, KVM_DEV_TYPE_LOONGARCH_PCHPIC); } + +void kvm_loongarch_unregister_pch_pic_device(void) +{ + kvm_unregister_device_ops(KVM_DEV_TYPE_LOONGARCH_PCHPIC); +} From 910132bc7d72f26a8b288c2a38c32445a48d5be0 Mon Sep 17 00:00:00 2001 From: Chaithanya Lagisetty Date: Fri, 4 Sep 2026 21:44:54 +0800 Subject: [PATCH 0660/1198] LoongArch: KVM: Fix resource leak in kvm_loongarch_env_init() error path kvm_loongarch_env_init() allocates the per-CPU kvm_context (vmcs) and kvm_loongarch_ops, registers the perf callbacks, and then registers the IPI/EIOINTC/PCH-PIC/DMSINTC KVM devices. If any of those device registrations fails, the function returned the error directly, leaving everything acquired so far in place: vmcs and kvm_loongarch_ops are never freed, the perf callbacks stay registered, and all previously registered KVM device operations remain registered. kvm_loongarch_init() propagates the errors without calling kvm_loongarch_env_exit(), so nothing else cleans up either. Unwind the error path in reverse order of registration, so that each failure only undoes what had actually been set up. Use the same helpers in kvm_loongarch_env_exit() to remove the device registrations during normal teardown as well. Cc: stable@vger.kernel.org Fixes: c532de5a67a7 ("LoongArch: KVM: Add IPI device support") Reviewed-by: Bibo Mao Signed-off-by: Chaithanya Lagisetty Signed-off-by: Huacai Chen --- arch/loongarch/kvm/main.c | 33 +++++++++++++++++++++++++++++---- 1 file changed, 29 insertions(+), 4 deletions(-) diff --git a/arch/loongarch/kvm/main.c b/arch/loongarch/kvm/main.c index b6ddf5827c03..236523d2449d 100644 --- a/arch/loongarch/kvm/main.c +++ b/arch/loongarch/kvm/main.c @@ -385,27 +385,52 @@ static int kvm_loongarch_env_init(void) /* Register LoongArch IPI interrupt controller interface. */ ret = kvm_loongarch_register_ipi_device(); if (ret) - return ret; + goto err_env; /* Register LoongArch EIOINTC interrupt controller interface. */ ret = kvm_loongarch_register_eiointc_device(); if (ret) - return ret; + goto err_ipi; /* Register LoongArch PCH-PIC interrupt controller interface. */ ret = kvm_loongarch_register_pch_pic_device(); if (ret) - return ret; + goto err_eiointc; /* Register LoongArch DMSINTC interrupt contrroller interface */ - if (cpu_has_msgint) + if (cpu_has_msgint) { ret = kvm_loongarch_register_dmsintc_device(); + if (ret) + goto err_pch_pic; + } + + return 0; + +err_pch_pic: + kvm_loongarch_unregister_pch_pic_device(); +err_eiointc: + kvm_loongarch_unregister_eiointc_device(); +err_ipi: + kvm_loongarch_unregister_ipi_device(); +err_env: + kvm_unregister_perf_callbacks(); + kfree(kvm_loongarch_ops); + kvm_loongarch_ops = NULL; + free_percpu(vmcs); + vmcs = NULL; return ret; } static void kvm_loongarch_env_exit(void) { + if (cpu_has_msgint) + kvm_loongarch_unregister_dmsintc_device(); + + kvm_loongarch_unregister_pch_pic_device(); + kvm_loongarch_unregister_eiointc_device(); + kvm_loongarch_unregister_ipi_device(); + if (vmcs) free_percpu(vmcs); From 40bdbb4bfa730400e8b383d6f5931f90aebb5f54 Mon Sep 17 00:00:00 2001 From: Bibo Mao Date: Fri, 4 Sep 2026 21:44:54 +0800 Subject: [PATCH 0661/1198] LoongArch: KVM: Remove unused function kvm_arch_flush_remote_tlbs_memslot() Function kvm_arch_flush_remote_tlbs_memslot() is not called any more, so remove this API. Reviewed-by: Tao Cui Signed-off-by: Bibo Mao Signed-off-by: Huacai Chen --- arch/loongarch/include/asm/kvm_host.h | 1 - arch/loongarch/kvm/mmu.c | 6 ------ 2 files changed, 7 deletions(-) diff --git a/arch/loongarch/include/asm/kvm_host.h b/arch/loongarch/include/asm/kvm_host.h index 23cfbecebbd7..5682b8c847d1 100644 --- a/arch/loongarch/include/asm/kvm_host.h +++ b/arch/loongarch/include/asm/kvm_host.h @@ -350,7 +350,6 @@ static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} static inline void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) {} void kvm_check_vpid(struct kvm_vcpu *vcpu); enum hrtimer_restart kvm_swtimer_wakeup(struct hrtimer *timer); -void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm, const struct kvm_memory_slot *memslot); void kvm_init_vmcs(struct kvm *kvm); void kvm_exc_entry(void); int kvm_enter_guest(struct kvm_run *run, struct kvm_vcpu *vcpu); diff --git a/arch/loongarch/kvm/mmu.c b/arch/loongarch/kvm/mmu.c index e104897aa532..2c08402bfd3e 100644 --- a/arch/loongarch/kvm/mmu.c +++ b/arch/loongarch/kvm/mmu.c @@ -939,9 +939,3 @@ int kvm_handle_mm_fault(struct kvm_vcpu *vcpu, unsigned long gpa, bool write, in void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) { } - -void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm, - const struct kvm_memory_slot *memslot) -{ - kvm_flush_remote_tlbs(kvm); -} From 27a9bfee3bbcb3cabb77797354f07e0e44e49831 Mon Sep 17 00:00:00 2001 From: Zeng Chi Date: Fri, 4 Sep 2026 21:45:13 +0800 Subject: [PATCH 0662/1198] LoongArch: KVM: Preserve memslot arch flags on KVM_MR_FLAGS_ONLY kvm_arch_prepare_memory_region() computes new->arch.flags, i.e. whether a memslot is KVM_MEM_HUGEPAGE_CAPABLE or KVM_MEM_HUGEPAGE_INCAPABLE, only for KVM_MR_CREATE and KVM_MR_MOVE, and returns early for every other change. But the generic code allocates a zeroed memslot for every change and never copies old->arch, so after a KVM_MR_FLAGS_ONLY update, e.g. toggling KVM_MEM_LOG_DIRTY_PAGES for live migration, the active memslot has arch.flags == 0. With both flags clear, fault_supports_huge_mapping() falls through to the alignment check on the HVA range alone, which no longer verifies that the GPA and HVA have the same offset within a PMD. A memslot that was marked KVM_MEM_HUGEPAGE_INCAPABLE because of a GPA/HVA offset mismatch can then be mapped with PMD entries on read faults, and since kvm_map_page() aligns the gfn and the pfn independently, the guest ends up accessing the wrong host pages, exactly the "d -> f, e -> g" case described in the comment above the check. Carry the arch flags over from the old memslot for KVM_MR_FLAGS_ONLY, as the GPA, HVA and size are guaranteed to be unchanged for that case. Cc: stable@vger.kernel.org Fixes: 7ab6fb505b2a ("LoongArch: KVM: Optimization for memslot hugepage checking") Tested-by: Tao Cui Reviewed-by: Tao Cui Reviewed-by: Bibo Mao Signed-off-by: Zeng Chi Signed-off-by: Huacai Chen --- arch/loongarch/kvm/mmu.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/arch/loongarch/kvm/mmu.c b/arch/loongarch/kvm/mmu.c index 2c08402bfd3e..3e9a0b285fd2 100644 --- a/arch/loongarch/kvm/mmu.c +++ b/arch/loongarch/kvm/mmu.c @@ -383,6 +383,16 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, const struct kvm_memory_slot hva_t hva_start; size_t size, gpa_offset, hva_offset; + /* + * The generic code allocates a fresh, zeroed memslot for every change, + * so the arch flags computed below must be carried over when only the + * userspace flags change, e.g. when dirty logging is toggled. + */ + if (change == KVM_MR_FLAGS_ONLY) { + new->arch = old->arch; + return 0; + } + if ((change != KVM_MR_MOVE) && (change != KVM_MR_CREATE)) return 0; /* From 501514d6ebd2111c353a1296f25dbe22fbd64657 Mon Sep 17 00:00:00 2001 From: Zeng Chi Date: Fri, 4 Sep 2026 21:45:13 +0800 Subject: [PATCH 0663/1198] LoongArch: KVM: Validate MSI data before routing it to EIOINTC pch_msi_set_irq() passes e->msi.data straight into eiointc_set_irq() as the irq number. The MSI data comes from userspace, that either via a KVM_IRQ_ROUTING_MSI entry set with KVM_SET_GSI_ROUTING (used by irqfd and KVM_IRQ_LINE) or directly via KVM_SIGNAL_MSI, and is never checked against EIOINTC_IRQS. eiointc_set_irq() uses the value with __set_bit()/__clear_bit() on the 256-bit isr bitmap, eiointc_update_irq() then indexes sw_coremap[] and the per-cpu coreisr/sw_coreisr bitmaps with it. Therefore a data value >= 256 reads and writes memory past the end of those arrays, i.e. any process holding a VM fd can corrupt kernel memory beyond the allocation of loongarch_eiointc. Reject MSI data that doesn't fit in the EIOINTC irq space. The DMSINTC path is unaffected as it decodes the vector from the address and masks it. Cc: stable@vger.kernel.org Fixes: 1928254c5ccb ("LoongArch: KVM: Add irqfd support") Reported-by: Sashiko Closes: https://lore.kernel.org/all/20260531140921.1B1181F00893@smtp.kernel.org/ Reviewed-by: Tao Cui Reviewed-by: Bibo Mao Signed-off-by: Zeng Chi Signed-off-by: Huacai Chen --- arch/loongarch/kvm/intc/pch_pic.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/loongarch/kvm/intc/pch_pic.c b/arch/loongarch/kvm/intc/pch_pic.c index 83fa2386cf81..2b63b0c2c7ce 100644 --- a/arch/loongarch/kvm/intc/pch_pic.c +++ b/arch/loongarch/kvm/intc/pch_pic.c @@ -78,6 +78,9 @@ int pch_msi_set_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, int return dmsintc_set_irq(kvm, msg_addr, e->msi.data, level); } + if (e->msi.data >= EIOINTC_IRQS) + return -EINVAL; + eiointc_set_irq(kvm->arch.eiointc, e->msi.data, level); return 0; From 9296375902579f9b0e456bbb76e5cf179e5a4e0b Mon Sep 17 00:00:00 2001 From: Tao Cui Date: Fri, 4 Sep 2026 21:45:13 +0800 Subject: [PATCH 0664/1198] LoongArch: KVM: Fix TOCTOU race on pv_features In kvm_loongarch_cpucfg_set_attr() the check-then-set on kvm->arch.pv_features is lockless, so two vCPUs can race past the validation and set different values. Add a spinlock to protect it. Cc: stable@vger.kernel.org Reviewed-by: Bibo Mao Signed-off-by: Tao Cui Signed-off-by: Huacai Chen --- arch/loongarch/include/asm/kvm_host.h | 1 + arch/loongarch/kvm/vcpu.c | 6 +++++- arch/loongarch/kvm/vm.c | 1 + 3 files changed, 7 insertions(+), 1 deletion(-) diff --git a/arch/loongarch/include/asm/kvm_host.h b/arch/loongarch/include/asm/kvm_host.h index 5682b8c847d1..65d91c3ce313 100644 --- a/arch/loongarch/include/asm/kvm_host.h +++ b/arch/loongarch/include/asm/kvm_host.h @@ -125,6 +125,7 @@ struct kvm_arch { unsigned int pte_shifts[MAX_PGTABLE_LEVELS]; unsigned int root_level; spinlock_t phyid_map_lock; + spinlock_t pv_setting_lock; struct kvm_phyid_map *phyid_map; /* Enabled PV features */ unsigned long pv_features; diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c index ed9e092c97ba..8e028be3f0a9 100644 --- a/arch/loongarch/kvm/vcpu.c +++ b/arch/loongarch/kvm/vcpu.c @@ -1165,10 +1165,14 @@ static int kvm_loongarch_cpucfg_set_attr(struct kvm_vcpu *vcpu, return -EINVAL; /* All vCPUs need set the same PV features */ + spin_lock(&kvm->arch.pv_setting_lock); if ((kvm->arch.pv_features & LOONGARCH_PV_FEAT_UPDATED) - && ((kvm->arch.pv_features & valid) != val)) + && ((kvm->arch.pv_features & valid) != val)) { + spin_unlock(&kvm->arch.pv_setting_lock); return -EINVAL; + } kvm->arch.pv_features = val | LOONGARCH_PV_FEAT_UPDATED; + spin_unlock(&kvm->arch.pv_setting_lock); return 0; default: return -ENXIO; diff --git a/arch/loongarch/kvm/vm.c b/arch/loongarch/kvm/vm.c index 0a51931d6f6e..6dabb227a732 100644 --- a/arch/loongarch/kvm/vm.c +++ b/arch/loongarch/kvm/vm.c @@ -76,6 +76,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) return -ENOMEM; } spin_lock_init(&kvm->arch.phyid_map_lock); + spin_lock_init(&kvm->arch.pv_setting_lock); kvm_init_vmcs(kvm); kvm_vm_init_features(kvm); From a2628ce4ddb6873e35380a42396d17a66e704a1a Mon Sep 17 00:00:00 2001 From: Haiyong Sun Date: Fri, 4 Sep 2026 21:45:27 +0800 Subject: [PATCH 0665/1198] perf build: Add clang and rust target flags for LoongArch Add missing CLANG_TARGET_FLAGS_loongarch and RUST_TARGET_FLAGS_loongarch so that perf can be built with clang and enable rust cross compilation. Cc: stable@vger.kernel.org Acked-by: Miguel Ojeda Acked-by: Dmitrii Dolgov <9erthalion6@gmail.com> Signed-off-by: Haiyong Sun Signed-off-by: WANG Rui Signed-off-by: Huacai Chen --- tools/perf/Makefile.config | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 0ba307e78fe1..4d5993da9f94 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -27,6 +27,7 @@ CFLAGS += -fno-strict-aliasing ifeq ($(CC_NO_CLANG), 0) CLANG_TARGET_FLAGS_arm := arm-linux-gnueabi CLANG_TARGET_FLAGS_arm64 := aarch64-linux-gnu + CLANG_TARGET_FLAGS_loongarch := loongarch64-linux-gnu CLANG_TARGET_FLAGS_m68k := m68k-linux-gnu CLANG_TARGET_FLAGS_mips := mipsel-linux-gnu CLANG_TARGET_FLAGS_powerpc := powerpc64le-linux-gnu @@ -1142,6 +1143,7 @@ ifndef NO_RUST ifneq ($(CROSS_COMPILE),) RUST_TARGET_FLAGS_arm := arm-unknown-linux-gnueabi RUST_TARGET_FLAGS_arm64 := aarch64-unknown-linux-gnu + RUST_TARGET_FLAGS_loongarch := loongarch64-unknown-linux-gnu RUST_TARGET_FLAGS_m68k := m68k-unknown-linux-gnu RUST_TARGET_FLAGS_mips := mipsel-unknown-linux-gnu RUST_TARGET_FLAGS_powerpc := powerpc64le-unknown-linux-gnu From 5ad0af4f4367202b1bc71813052fe39b5116cdb9 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 17 Aug 2026 12:33:24 +0200 Subject: [PATCH 0666/1198] thermal: sysfs: switch to use scnprintf() to suppress truncation warning Switch the sysfs code to use scnprintf() to avoid warnings about potential truncation of the names of the sysfs attributes. We can't increase the buffer size because the size is the part of an ABI for some reason. Note, with the current size of buffer the affected attributes have a room for up to 1000 names, which ought to be enough for all cases. There is no functional change, as the same limitation was implied before. Fixes: c56f5c0342df ("Thermal: Make Thermal trip points writeable") Signed-off-by: Andy Shevchenko Reviewed-by: Lukasz Luba Link: https://patch.msgid.link/20260817103324.1020212-1-andriy.shevchenko@linux.intel.com Signed-off-by: Rafael J. Wysocki --- drivers/thermal/thermal_sysfs.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/thermal/thermal_sysfs.c b/drivers/thermal/thermal_sysfs.c index adbcb2c011e8..96fe5d591a0a 100644 --- a/drivers/thermal/thermal_sysfs.c +++ b/drivers/thermal/thermal_sysfs.c @@ -400,8 +400,8 @@ static int create_trip_attrs(struct thermal_zone_device *tz) struct thermal_trip_attrs *trip_attrs = &td->trip_attrs; /* create trip type attribute */ - snprintf(trip_attrs->type.name, THERMAL_NAME_LENGTH, - "trip_point_%d_type", i); + scnprintf(trip_attrs->type.name, sizeof(trip_attrs->type.name), + "trip_point_%d_type", i); sysfs_attr_init(&trip_attrs->type.attr.attr); trip_attrs->type.attr.attr.name = trip_attrs->type.name; @@ -410,8 +410,8 @@ static int create_trip_attrs(struct thermal_zone_device *tz) attrs[i] = &trip_attrs->type.attr.attr; /* create trip temp attribute */ - snprintf(trip_attrs->temp.name, THERMAL_NAME_LENGTH, - "trip_point_%d_temp", i); + scnprintf(trip_attrs->temp.name, sizeof(trip_attrs->temp.name), + "trip_point_%d_temp", i); sysfs_attr_init(&trip_attrs->temp.attr.attr); trip_attrs->temp.attr.attr.name = trip_attrs->temp.name; @@ -423,8 +423,8 @@ static int create_trip_attrs(struct thermal_zone_device *tz) } attrs[i + tz->num_trips] = &trip_attrs->temp.attr.attr; - snprintf(trip_attrs->hyst.name, THERMAL_NAME_LENGTH, - "trip_point_%d_hyst", i); + scnprintf(trip_attrs->hyst.name, sizeof(trip_attrs->hyst.name), + "trip_point_%d_hyst", i); sysfs_attr_init(&trip_attrs->hyst.attr.attr); trip_attrs->hyst.attr.attr.name = trip_attrs->hyst.name; From e67091609cf85962f64391c1b0f93d4cbfcd4e22 Mon Sep 17 00:00:00 2001 From: caina Date: Fri, 21 Aug 2026 17:17:20 +0800 Subject: [PATCH 0667/1198] Revert "irqchip/mbigen: Fix mbigen node address layout" This reverts commit 6be6cba9c4371d27f78d900ccfe34bb880d9ee20. Commit 6be6cba9c437 ("irqchip/mbigen: Fix mbigen node address layout") appears to cause a regression on Hi1616. On-board hns NIC has two ports, enahisic2i0 and enahisic2i1, both behind mbigen-v2. Port 0 works; port 1 cannot pass any traffic. Their interrupt pins fall on different mbigen nodes: enahisic2i0: pins 1152-1198 -> all in node 9 enahisic2i1: pins 1200-1246 -> node 9 (1200-1215) + node 10 (1216-1246) (nid = (hwirq - 64) / 128 + 1; pin 1215 = node 9, pin 1216 = node 10) /proc/interrupts shows the break happens exactly at the node boundary: enahisic2i1-rx0 pin 1200 count 102 <- node 9 enahisic2i1-rx5 pin 1215 count 1 <- node 9, last pin enahisic2i1-tx5 pin 1216 count 0 <- node 10, first pin enahisic2i1-rx6 pin 1218 count 0 <- node 10 ...all node 10 pins stay at zero. Port 0 (entirely node 9) is unaffected. Reverting the commit restores normal operation. The commit assumes CLEAR occupies a full 4 KB page at [0xa000, 0xb000) and collides with node 10, so node 10+ gets shifted by 0x1000. But get_mbigen_clear_reg() uses flat, chip-wide addressing -- it never multiplies by the node ID: *addr = (hwirq / 32) * 4 + REG_MBIGEN_CLEAR_OFFSET; /* 0xa000 */ Over the valid hwirq range [64, 1407], CLEAR only spans 0xa008-0xa0af (168 bytes). Node 10's registers are: TYPE: 0xa000-0xa00f (16 B) overlaps CLEAR by 8 B (0xa008-0xa00f) VEC: 0xa200-0xa3ff (512 B) no overlap with CLEAR Shifting the whole page moves VEC from 0xa200 to 0xb200. The hardware reads the event ID from the fixed silicon address 0xa200 on interrupt firing, but software wrote it to 0xb200 -- so the hardware gets an uninitialised value and the interrupt is lost. The only real overlap is 8 bytes of TYPE. It can only trigger when a single mbigen instance has devices on both node 1 (CLEAR 0xa008) and node 10 (TYPE 0xa008). On Hi1616 those nodes are on separate mbigen instances, so it never triggers. Fixes: 6be6cba9c4371d27f78d900ccfe34bb880d9ee20 ("irqchip/mbigen: Fix mbigen node address layout") Suggested-by: Marc Zyngier Signed-off-by: caina Signed-off-by: Thomas Gleixner Acked-by: Yipeng Zou Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260821091720.16665-1-caina@uniontech.com --- drivers/irqchip/irq-mbigen.c | 20 ++++---------------- 1 file changed, 4 insertions(+), 16 deletions(-) diff --git a/drivers/irqchip/irq-mbigen.c b/drivers/irqchip/irq-mbigen.c index 6f69f4e5dbac..12919836dadb 100644 --- a/drivers/irqchip/irq-mbigen.c +++ b/drivers/irqchip/irq-mbigen.c @@ -64,20 +64,6 @@ struct mbigen_device { void __iomem *base; }; -static inline unsigned int get_mbigen_node_offset(unsigned int nid) -{ - unsigned int offset = nid * MBIGEN_NODE_OFFSET; - - /* - * To avoid touched clear register in unexpected way, we need to directly - * skip clear register when access to more than 10 mbigen nodes. - */ - if (nid >= (REG_MBIGEN_CLEAR_OFFSET / MBIGEN_NODE_OFFSET)) - offset += MBIGEN_NODE_OFFSET; - - return offset; -} - static inline unsigned int get_mbigen_vec_reg(irq_hw_number_t hwirq) { unsigned int nid, pin; @@ -86,7 +72,8 @@ static inline unsigned int get_mbigen_vec_reg(irq_hw_number_t hwirq) nid = hwirq / IRQS_PER_MBIGEN_NODE + 1; pin = hwirq % IRQS_PER_MBIGEN_NODE; - return pin * 4 + get_mbigen_node_offset(nid) + REG_MBIGEN_VEC_OFFSET; + return pin * 4 + nid * MBIGEN_NODE_OFFSET + + REG_MBIGEN_VEC_OFFSET; } static inline void get_mbigen_type_reg(irq_hw_number_t hwirq, @@ -101,7 +88,8 @@ static inline void get_mbigen_type_reg(irq_hw_number_t hwirq, *mask = 1 << (irq_ofst % 32); ofst = irq_ofst / 32 * 4; - *addr = ofst + get_mbigen_node_offset(nid) + REG_MBIGEN_TYPE_OFFSET; + *addr = ofst + nid * MBIGEN_NODE_OFFSET + + REG_MBIGEN_TYPE_OFFSET; } static inline void get_mbigen_clear_reg(irq_hw_number_t hwirq, From d31fbbade43f880b7e59e2b3a72722fe2725d93f Mon Sep 17 00:00:00 2001 From: Ju Nan Date: Fri, 21 Aug 2026 10:47:57 +0800 Subject: [PATCH 0668/1198] irqchip/stm32mp-exti: Fix the unit of the hwspinlock timeout HWSPNLCK_TIMEOUT is passed to hwspin_lock_timeout_in_atomic(), whose timeout argument is in milliseconds, not microseconds: atomic_delay += HWSPINLOCK_RETRY_DELAY_US; if (atomic_delay > to * 1000) return -ETIMEDOUT; So stm32mp_exti_set_type() asks for a 1 second timeout where the comment next to the macro says it wants 1 millisecond. The semaphore is polled with udelay() from a section that holds chip_data->rlock, a raw_spinlock_t, so preemption stays disabled for the whole wait on every configuration, PREEMPT_RT included. The hwspinlock core documents this explicitly: If the mode is HWLOCK_IN_ATOMIC (called from an atomic context) the timeout is handled with busy-waiting delays, hence shall not exceed few msecs. Fixes: 5257169ade8c ("irqchip/stm32-exti: Use the hwspin_lock_timeout_in_atomic() API") Signed-off-by: Ju Nan Signed-off-by: Thomas Gleixner Reviewed-by: Radu Rendec Reviewed-by: Antonio Borneo Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260821024756.24927-2-junan76@163.com --- drivers/irqchip/irq-stm32mp-exti.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/irqchip/irq-stm32mp-exti.c b/drivers/irqchip/irq-stm32mp-exti.c index bf3a2def69ca..a19e91fbd010 100644 --- a/drivers/irqchip/irq-stm32mp-exti.c +++ b/drivers/irqchip/irq-stm32mp-exti.c @@ -22,7 +22,7 @@ #define IRQS_PER_BANK 32 -#define HWSPNLCK_TIMEOUT 1000 /* usec */ +#define HWSPNLCK_TIMEOUT_MS 1 #define EXTI_EnCIDCFGR(n) (0x180 + (n) * 4) #define EXTI_HWCFGR1 0x3f0 @@ -376,7 +376,7 @@ static int stm32mp_exti_set_type(struct irq_data *d, unsigned int type) raw_spin_lock(&chip_data->rlock); if (hwlock) { - err = hwspin_lock_timeout_in_atomic(hwlock, HWSPNLCK_TIMEOUT); + err = hwspin_lock_timeout_in_atomic(hwlock, HWSPNLCK_TIMEOUT_MS); if (err) { pr_err("%s can't get hwspinlock (%d)\n", __func__, err); goto unlock; From 048029ba1c793f8cabc4ad5eea765da01903f8f1 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 4 Sep 2026 10:43:14 +0200 Subject: [PATCH 0669/1198] bpf: Require MEM_PERCPU for percpu kptr stores map_kptr_match_type() treats perm_flags as the set of register type flags that a kptr field permits. Adding MEM_PERCPU to that set for BPF_KPTR_PERCPU does not require the source register to carry it, however. The subset test consequently accepts both a plain bpf_obj_new() allocation and a referenced kernel pointer into a __percpu_kptr map field. Loads from the field are always marked MEM_PERCPU. Consumers then treat the stored value as the cookie returned by bpf_percpu_obj_new(): per-CPU pointer helpers relocate it, and map teardown selects the per-CPU free path. A plain allocation can therefore provide an arbitrary kernel read/write, while a kernel pointer can be relocated into an invalid address or sent through a missing destructor. Require the source MEM_PERCPU flag to match the destination field kind. This preserves valid bpf_percpu_obj_new() stores and rejects both the program-BTF and kernel-BTF variants. Fixes: 36d8bdf75a93 ("bpf: Add alloc/xchg/direct_access support for local percpu kptr") Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260904084325.52250-2-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index fde5d046b6e3..19c932e8c533 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4495,6 +4495,13 @@ static int map_kptr_match_type(struct bpf_verifier_env *env, if (type_flag(reg->type) & ~perm_flags) goto bad_type; + /* + * A BPF_KPTR_PERCPU field is read back as MEM_PERCPU, so the value + * stored in it must carry the same flag. + */ + if ((kptr_field->type == BPF_KPTR_PERCPU) != !!(reg->type & MEM_PERCPU)) + goto bad_type; + /* We need to verify reg->type and reg->btf, before accessing reg->btf */ reg_name = btf_type_name(reg->btf, reg->btf_id); From 17487b31f479c85eda3685e8e44242358bd68f23 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 4 Sep 2026 10:43:15 +0200 Subject: [PATCH 0670/1198] selftests/bpf: Reject non-percpu values in percpu kptr fields Add verifier coverage for the two ways a non-percpu pointer can be stored in a __percpu_kptr field: a program-BTF local allocation returned by bpf_obj_new(), and a referenced kernel-BTF task_struct pointer. Without the verifier fix, both programs are unexpectedly accepted and the negative tests fail. Requiring MEM_PERCPU makes both programs fail verification with the expected invalid-kptr diagnostic. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260904084325.52250-3-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- .../selftests/bpf/progs/percpu_alloc_fail.c | 59 +++++++++++++++++++ 1 file changed, 59 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c b/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c index 08379c3b6a03..3701f4ea58c7 100644 --- a/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c +++ b/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c @@ -33,6 +33,20 @@ struct { __type(value, struct elem); } array SEC(".maps"); +struct kernel_percpu_elem { + struct task_struct __percpu_kptr *task; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct kernel_percpu_elem); +} kernel_percpu_array SEC(".maps"); + +struct task_struct *bpf_task_from_pid(s32 pid) __ksym; +void bpf_task_release(struct task_struct *p) __ksym; + long ret; SEC("?fentry/bpf_fentry_test1") @@ -137,6 +151,51 @@ int BPF_PROG(test_array_map_5) return 0; } +SEC("?syscall") +__failure __msg("invalid kptr access, R2 type=trusted_ptr_ expected=ptr_task_struct") +int reject_kernel_ptr_into_percpu_kptr(void *ctx) +{ + struct kernel_percpu_elem *e; + struct task_struct *p, *old; + int index = 0; + + e = bpf_map_lookup_elem(&kernel_percpu_array, &index); + if (!e) + return 0; + + p = bpf_task_from_pid(1); + if (!p) + return 0; + + old = bpf_kptr_xchg(&e->task, p); + if (old) + bpf_task_release(old); + return 0; +} + +SEC("?fentry.s/bpf_fentry_test1") +__failure __msg("invalid kptr access, R2 type=ptr_ expected=ptr_val_t") +int BPF_PROG(reject_plain_alloc_into_percpu_kptr) +{ + struct val_t __percpu_kptr *old; + struct val_t *p; + struct elem *e; + int index = 0; + + e = bpf_map_lookup_elem(&array, &index); + if (!e) + return 0; + + p = bpf_obj_new(struct val_t); + if (!p) + return 0; + + old = bpf_kptr_xchg(&e->pc, p); + if (old) + bpf_percpu_obj_drop(old); + return 0; +} + SEC("?fentry.s/bpf_fentry_test1") __failure __msg("bpf_percpu_obj_new type ID argument must be of a struct of scalars") int BPF_PROG(test_array_map_6) From dc36739e5cc9f60485418a910b42bc95339218d2 Mon Sep 17 00:00:00 2001 From: Ning Ding Date: Fri, 4 Sep 2026 10:43:16 +0200 Subject: [PATCH 0671/1198] bpf: Keep refcount_acquire nullable for borrowed RCU kptrs bpf_refcount_acquire() is fallible for a borrowed reference because the object may have reached a zero refcount. The verifier therefore keeps KF_RET_NULL on the return value unless the argument is an owning reference. An RCU-protected load of a local kptr is marked MEM_ALLOC, but it only receives NON_OWN_REF when the pointee contains a graph node. A refcounted object without a graph node consequently looks like an owning reference even though the loaded register has no acquired reference state. If the program drops the last real reference while remaining in the RCU critical section, refcount_inc_not_zero() returns NULL while the verifier treats the result as non-NULL. Only classify the argument as owning when it is backed by a verifier-tracked reference. This retains the non-NULL return for pointers from bpf_obj_new(), bpf_kptr_xchg(), or an earlier successful acquisition, while requiring a NULL check for borrowed RCU kptrs. Fixes: 1b12171533a9 ("bpf: Mark direct ld of stashed bpf_{rb,list}_node as non-owning ref") Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Ning Ding [ kkd: Rewrote commit log ] Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260904084325.52250-4-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 19c932e8c533..3af8bd838b82 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -13185,7 +13185,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_call_arg_me bpf_diag_reg_type_plain(env, reg->type)); return -EINVAL; } - if (!type_is_non_owning_ref(reg->type)) + if (!type_is_non_owning_ref(reg->type) && reg_is_referenced(env, reg)) meta->arg_owning_ref = true; rec = reg_btf_record(reg); From 2edd8339468e4bf0feecb3398aaad25fd7b84286 Mon Sep 17 00:00:00 2001 From: Ning Ding Date: Fri, 4 Sep 2026 10:43:17 +0200 Subject: [PATCH 0672/1198] selftests/bpf: Test borrowed refcount acquisition nullability Add verifier coverage for the distinction between owning and borrowed arguments to bpf_refcount_acquire(). An owning pointer returned by bpf_obj_new() must continue producing a non-NULL result without an extra check. An RCU-loaded local kptr is only borrowed, so a checked result must load successfully while passing an unchecked result to bpf_obj_drop() must be rejected as possibly NULL. Use a sleepable syscall program for the borrowed cases so the explicit RCU critical section is what permits the local kptr load. Without the verifier fix, the unchecked case is incorrectly accepted. With it, the verifier rejects the possibly NULL argument. Signed-off-by: Ning Ding [ kkd: Rewrote commit log ] Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260904084325.52250-5-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- .../selftests/bpf/progs/refcounted_kptr.c | 61 +++++++++++++++++++ .../bpf/progs/refcounted_kptr_fail.c | 48 +++++++++++++++ 2 files changed, 109 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/refcounted_kptr.c b/tools/testing/selftests/bpf/progs/refcounted_kptr.c index 61906f48025c..cae00f7b0a24 100644 --- a/tools/testing/selftests/bpf/progs/refcounted_kptr.c +++ b/tools/testing/selftests/bpf/progs/refcounted_kptr.c @@ -23,6 +23,15 @@ struct map_value { struct node_data __kptr *node; }; +struct node_refcount_only { + long key; + struct bpf_refcount refcount; +}; + +struct map_value_refcount_only { + struct node_refcount_only __kptr *node; +}; + struct { __uint(type, BPF_MAP_TYPE_ARRAY); __type(key, int); @@ -30,6 +39,13 @@ struct { __uint(max_entries, 2); } stashed_nodes SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, struct map_value_refcount_only); + __uint(max_entries, 1); +} stashed_refcount_only SEC(".maps"); + struct node_acquire { long key; long data; @@ -832,6 +848,51 @@ long rbtree_refcounted_node_ref_escapes_owning_input(void *ctx) return 0; } +SEC("tc") +__success +long refcount_acquire_owning_input_no_null_check(void *ctx) +{ + struct node_refcount_only *n, *m; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + + m = bpf_refcount_acquire(n); + bpf_obj_drop(m); + bpf_obj_drop(n); + + return 0; +} + +SEC("?syscall") +__success +long refcount_acquire_rcu_map_kptr_null_checked(void *ctx) +{ + struct map_value_refcount_only *mapval; + struct node_refcount_only *n, *m; + int idx = 0; + + mapval = bpf_map_lookup_elem(&stashed_refcount_only, &idx); + if (!mapval) + return 1; + + bpf_rcu_read_lock(); + n = mapval->node; + if (!n) { + bpf_rcu_read_unlock(); + return 2; + } + m = bpf_refcount_acquire(n); + bpf_rcu_read_unlock(); + + if (!m) + return 3; + bpf_obj_drop(m); + + return 0; +} + static long __stash_map_empty_xchg(struct node_data *n, int idx) { struct map_value *mapval = bpf_map_lookup_elem(&stashed_nodes, &idx); diff --git a/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c index eaaed0859f94..7d2f8897e5ad 100644 --- a/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c +++ b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c @@ -19,6 +19,15 @@ struct node_refcounted { struct bpf_refcount refcount; }; +struct node_refcount_only { + long key; + struct bpf_refcount refcount; +}; + +struct map_value_refcount_only { + struct node_refcount_only __kptr *node; +}; + extern void bpf_rcu_read_lock(void) __ksym; extern void bpf_rcu_read_unlock(void) __ksym; @@ -28,6 +37,13 @@ private(A) struct bpf_rb_root groot __contains(node_acquire, node); private(B) struct bpf_spin_lock lock; private(B) struct bpf_list_head head __contains(node_refcounted, list); +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, struct map_value_refcount_only); + __uint(max_entries, 1); +} stashed_refcount_only SEC(".maps"); + static bool less(struct bpf_rb_node *a, const struct bpf_rb_node *b) { struct node_acquire *node_a; @@ -89,6 +105,38 @@ long refcount_acquire_non_object(void *ctx) return bpf_refcount_acquire(ctx) != NULL; } +SEC("?syscall") +__failure __msg("Possibly NULL pointer passed to trusted R1") +long refcount_acquire_rcu_map_kptr_unchecked_drop(void *ctx) +{ + struct map_value_refcount_only *mapval; + struct node_refcount_only *tmp, *n, *m; + int idx = 0; + + /* Force Clang to emit complete BTF for struct node_refcount_only. */ + tmp = bpf_obj_new(typeof(*tmp)); + if (!tmp) + return 3; + bpf_obj_drop(tmp); + + mapval = bpf_map_lookup_elem(&stashed_refcount_only, &idx); + if (!mapval) + return 1; + + bpf_rcu_read_lock(); + n = mapval->node; + if (!n) { + bpf_rcu_read_unlock(); + return 2; + } + m = bpf_refcount_acquire(n); + bpf_rcu_read_unlock(); + + bpf_obj_drop(m); + + return 0; +} + SEC("?tc") __failure __msg("Unreleased reference id=3 alloc_insn={{[0-9]+}}") long rbtree_refcounted_node_ref_escapes_owning_input(void *ctx) From cd6f72d7f38e10aa82fcbc745a6a9e58e0d8e366 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 4 Sep 2026 10:43:18 +0200 Subject: [PATCH 0673/1198] bpf: Clear NON_OWN_REF after RCU protection ends A local kptr load of an object containing a graph node is marked MEM_RCU and NON_OWN_REF while protected by RCU. When the last RCU read-side critical section ends, invalidate_rcu_protected_refs() removes MEM_RCU and marks the pointer PTR_UNTRUSTED, but leaves NON_OWN_REF set. The stale flag lets graph kfunc argument checks continue treating the pointer as a live borrowed reference. In particular, bpf_rbtree_remove() can accept a pointer after its protection ended and return it as a new owning reference, even though the object may already have been freed. Clear NON_OWN_REF when an RCU-protected pointer is demoted. A spin lock also provides implicit RCU protection, so invalidate non-owning references before demoting RCU-protected pointers when releasing the lock. Otherwise the demotion would clear the flag before invalidate_non_owning_refs() can find and invalidate those aliases. The demoted pointer remains available for fault-protected reads. Exempt such reads from the allocated-object reference-state assertion; writes through a fault-prone pointer are already rejected, and bpf_may_fault_on_deref() makes the surviving loads use BPF_PROBE_MEM. Fixes: 1b12171533a9 ("bpf: Mark direct ld of stashed bpf_{rb,list}_node as non-owning ref") Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260904084325.52250-6-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 3af8bd838b82..9c6ad157a61e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6045,7 +6045,13 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, return -EACCES; } - if (type_is_alloc(reg->type) && !type_is_non_owning_ref(reg->type) && + /* + * A fault-prone allocated object may still be read through a + * BPF_PROBE_MEM load after its lifetime protection ends. Writes + * through such pointers were rejected above. + */ + if (type_is_alloc(reg->type) && !bpf_may_fault_on_deref(reg->type) && + !type_is_non_owning_ref(reg->type) && !(reg->type & MEM_RCU) && !reg_is_referenced(env, reg)) { verifier_bug(env, "allocated object must have a referenced id"); return -EFAULT; @@ -7423,10 +7429,14 @@ static int process_spin_lock(struct bpf_verifier_env *env, struct bpf_reg_state lock); return -EINVAL; } + /* + * Invalidate non-owning refs before RCU demotion clears their + * NON_OWN_REF flag. + */ + invalidate_non_owning_refs(env); + if (!in_rcu_cs(env)) invalidate_rcu_protected_refs(env); - - invalidate_non_owning_refs(env); } return 0; } @@ -9526,7 +9536,7 @@ static void invalidate_rcu_protected_refs(struct bpf_verifier_env *env) bpf_for_each_reg_in_vstate_mask(env->cur_state, state, reg, stack, clear_mask, ({ if (reg->type & MEM_RCU) { bpf_diag_mod_begin(env, reg, NULL, BPF_DIAG_MOD_WRITE); - reg->type &= ~(MEM_RCU | PTR_MAYBE_NULL); + reg->type &= ~(MEM_RCU | PTR_MAYBE_NULL | NON_OWN_REF); reg->type |= PTR_UNTRUSTED; bpf_diag_mod_end(env); } From 6668ed271eaefaa63e686bdfbedaeb7b8e492722 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 4 Sep 2026 10:43:19 +0200 Subject: [PATCH 0674/1198] selftests/bpf: Reject graph kptr use after RCU unlock Add a sleepable verifier test that loads a graph-node local kptr in an explicit RCU read-side critical section, then passes its node to bpf_rbtree_remove() after the section ends. Before the verifier fix, the stale NON_OWN_REF flag makes the node look like a live borrowed reference and the program is accepted. After the fix, the pointer is demoted without NON_OWN_REF and the graph kfunc argument is rejected. Also exercise a graph kptr loaded while a spin lock provides implicit RCU protection. The pointer must be invalidated when the lock is released, which guards the required ordering between non-owning-reference invalidation and RCU demotion. Update the existing fault-protected load test state description. The post-unlock pointer no longer carries NON_OWN_REF, but remains readable because the load is rewritten to use BPF_PROBE_MEM. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260904084325.52250-7-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- .../selftests/bpf/progs/rcu_read_lock.c | 6 +- .../bpf/progs/refcounted_kptr_fail.c | 75 +++++++++++++++++++ 2 files changed, 78 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/bpf/progs/rcu_read_lock.c b/tools/testing/selftests/bpf/progs/rcu_read_lock.c index 31d4081c3a9f..cdb255addbc3 100644 --- a/tools/testing/selftests/bpf/progs/rcu_read_lock.c +++ b/tools/testing/selftests/bpf/progs/rcu_read_lock.c @@ -592,9 +592,9 @@ int non_own_ref_untrusted_ld(void *ctx) } bpf_rcu_read_unlock(); /* - * The unlock leaves node as PTR_TO_BTF_ID | MEM_ALLOC | PTR_UNTRUSTED - * | NON_OWN_REF, and the load below has to get the BPF_PROBE_MEM - * rewrite for it, otherwise a bad address panics the kernel. + * The unlock leaves node as PTR_TO_BTF_ID | MEM_ALLOC | PTR_UNTRUSTED, + * and the load below has to get the BPF_PROBE_MEM rewrite for it, + * otherwise a bad address panics the kernel. */ non_own_ref_key = node->key; return 0; diff --git a/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c index 7d2f8897e5ad..f787ecf189d8 100644 --- a/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c +++ b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c @@ -28,6 +28,17 @@ struct map_value_refcount_only { struct node_refcount_only __kptr *node; }; +struct rcu_graph_node { + struct bpf_rb_node node; + long data; +}; + +struct rcu_graph_node *just_here_because_btf_bug; + +struct map_value_rcu_graph { + struct rcu_graph_node __kptr *node; +}; + extern void bpf_rcu_read_lock(void) __ksym; extern void bpf_rcu_read_unlock(void) __ksym; @@ -36,6 +47,8 @@ private(A) struct bpf_spin_lock glock; private(A) struct bpf_rb_root groot __contains(node_acquire, node); private(B) struct bpf_spin_lock lock; private(B) struct bpf_list_head head __contains(node_refcounted, list); +private(C) struct bpf_spin_lock graph_lock; +private(C) struct bpf_rb_root graph_root __contains(rcu_graph_node, node); struct { __uint(type, BPF_MAP_TYPE_ARRAY); @@ -44,6 +57,13 @@ struct { __uint(max_entries, 1); } stashed_refcount_only SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, struct map_value_rcu_graph); + __uint(max_entries, 1); +} stashed_rcu_graph SEC(".maps"); + static bool less(struct bpf_rb_node *a, const struct bpf_rb_node *b) { struct node_acquire *node_a; @@ -137,6 +157,61 @@ long refcount_acquire_rcu_map_kptr_unchecked_drop(void *ctx) return 0; } +SEC("?syscall") +__failure +__msg("bpf_rbtree_remove can only take non-owning or refcounted " + "bpf_rb_node pointer") +long rbtree_remove_after_rcu_unlock(void *ctx) +{ + struct map_value_rcu_graph *mapval; + struct bpf_rb_node *rb_node; + struct rcu_graph_node *node; + int idx = 0; + + mapval = bpf_map_lookup_elem(&stashed_rcu_graph, &idx); + if (!mapval) + return 0; + + bpf_rcu_read_lock(); + node = mapval->node; + if (!node) { + bpf_rcu_read_unlock(); + return 0; + } + bpf_rcu_read_unlock(); + + bpf_spin_lock(&graph_lock); + rb_node = bpf_rbtree_remove(&graph_root, &node->node); + bpf_spin_unlock(&graph_lock); + if (rb_node) + bpf_obj_drop(container_of(rb_node, struct rcu_graph_node, node)); + + return 0; +} + +SEC("?syscall") +__failure __msg("invalid mem access 'scalar'") +long graph_kptr_after_spin_unlock(void *ctx) +{ + struct map_value_rcu_graph *mapval; + struct rcu_graph_node *node; + int idx = 0; + + mapval = bpf_map_lookup_elem(&stashed_rcu_graph, &idx); + if (!mapval) + return 0; + + bpf_spin_lock(&graph_lock); + node = mapval->node; + if (!node) { + bpf_spin_unlock(&graph_lock); + return 0; + } + bpf_spin_unlock(&graph_lock); + + return node->data; +} + SEC("?tc") __failure __msg("Unreleased reference id=3 alloc_insn={{[0-9]+}}") long rbtree_refcounted_node_ref_escapes_owning_input(void *ctx) From 7441ee8276641bddaf1cba7bb75ef9c1458ceb3b Mon Sep 17 00:00:00 2001 From: Ning Ding Date: Fri, 4 Sep 2026 10:43:20 +0200 Subject: [PATCH 0675/1198] bpf: Reject untrusted allocated-object pointers When the final RCU read-side critical section ends, a local kptr is demoted to PTR_UNTRUSTED but retains MEM_ALLOC. The pointer may be NULL or may refer to an object whose lifetime is no longer protected. type_is_ptr_alloc_obj() nevertheless recognizes any PTR_TO_BTF_ID with MEM_ALLOC as a live allocated object. In particular, a refcount-only local kptr never carries NON_OWN_REF, so it still passes the bpf_refcount_acquire() argument check after RCU protection ends. The kfunc can then dereference NULL or stale memory. Make type_is_ptr_alloc_obj() reject PTR_UNTRUSTED pointers. Since type_is_non_owning_ref() is based on the same predicate, graph kfunc arguments obey the same live-object requirement. Fault-protected reads of the demoted pointer remain valid: writes are already rejected, and read fixups use bpf_may_fault_on_deref() rather than this predicate. Fixes: 1b12171533a9 ("bpf: Mark direct ld of stashed bpf_{rb,list}_node as non-owning ref") Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Ning Ding [ kkd: Rewrote commit log ] Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260904084325.52250-8-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 1339c2f028db..36b65797877d 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -1381,7 +1381,9 @@ static inline bool bpf_type_has_unsafe_modifiers(u32 type) static inline bool type_is_ptr_alloc_obj(u32 type) { - return base_type(type) == PTR_TO_BTF_ID && type_flag(type) & MEM_ALLOC; + return base_type(type) == PTR_TO_BTF_ID && + type_flag(type) & MEM_ALLOC && + !(type_flag(type) & PTR_UNTRUSTED); } static inline bool type_is_non_owning_ref(u32 type) From 9492baf8532ca285c58b82a269acd7a57e205ae9 Mon Sep 17 00:00:00 2001 From: Ning Ding Date: Fri, 4 Sep 2026 10:43:21 +0200 Subject: [PATCH 0676/1198] selftests/bpf: Reject refcount acquisition after RCU unlock Add a sleepable verifier test that loads a refcount-only local kptr in an explicit RCU read-side critical section, ends the section, and passes the pointer to bpf_refcount_acquire(). The loaded pointer never carries NON_OWN_REF. After RCU unlock it retains MEM_ALLOC while becoming PTR_UNTRUSTED, which previously made the kfunc argument check accept it as a live allocated object. Expect verification to reject the untrusted argument instead. Signed-off-by: Ning Ding [ kkd: Rewrote commit log ] Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260904084325.52250-9-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- .../bpf/progs/refcounted_kptr_fail.c | 27 +++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c index f787ecf189d8..338e43822ffe 100644 --- a/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c +++ b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c @@ -189,6 +189,33 @@ long rbtree_remove_after_rcu_unlock(void *ctx) return 0; } +SEC("?syscall") +__failure __msg("R1 is neither owning or non-owning ref") +long refcount_acquire_after_rcu_unlock(void *ctx) +{ + struct map_value_refcount_only *mapval; + struct node_refcount_only *node, *ref; + int idx = 0; + + mapval = bpf_map_lookup_elem(&stashed_refcount_only, &idx); + if (!mapval) + return 0; + + bpf_rcu_read_lock(); + node = mapval->node; + if (!node) { + bpf_rcu_read_unlock(); + return 0; + } + bpf_rcu_read_unlock(); + + ref = bpf_refcount_acquire(node); + if (ref) + bpf_obj_drop(ref); + + return 0; +} + SEC("?syscall") __failure __msg("invalid mem access 'scalar'") long graph_kptr_after_spin_unlock(void *ctx) From 3e5d1bf4bd687beb2cb4e32a07af695455925588 Mon Sep 17 00:00:00 2001 From: Runyu Xiao Date: Wed, 2 Sep 2026 12:19:15 +0800 Subject: [PATCH 0677/1198] cpufreq: initialize policy rwsem before sysfs publication cpufreq_policy_alloc() initializes policy->rwsem after kobject_init_and_add() has created the policy sysfs directory and its default attributes. A sysfs access can therefore reach a policy callback before the semaphore has been initialized. Initialize policy->rwsem before publishing the policy kobject so sysfs callbacks always see an initialized semaphore. Fixes: 2fc3384dc75b ("cpufreq: Initialize policy->kobj while allocating policy") Cc: All Applicable Link: https://lore.kernel.org/all/20260830155301.2713780-1-runyu.xiao@seu.edu.cn/ Reviewed-by: Zhongqiu Han Signed-off-by: Runyu Xiao Acked-by: Viresh Kumar Link: https://patch.msgid.link/20260902041915.3453421-1-runyu.xiao@seu.edu.cn Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/cpufreq.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 0d0df986fa3d..9efbf5b1781a 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1258,6 +1258,8 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu) if (!zalloc_cpumask_var(&policy->real_cpus, GFP_KERNEL)) goto err_free_rcpumask; + init_rwsem(&policy->rwsem); + init_completion(&policy->kobj_unregister); ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq, cpufreq_global_kobject, "policy%u", cpu); @@ -1272,8 +1274,6 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu) goto err_free_real_cpus; } - init_rwsem(&policy->rwsem); - freq_constraints_init(&policy->constraints); policy->nb_min.notifier_call = cpufreq_notifier_min; From d7dbdd2ee01e12211046d4a535623ac732b749fb Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Fri, 4 Sep 2026 08:25:04 +0900 Subject: [PATCH 0678/1198] tracing: Fix to avoid creating trace instances with duplicate names Since commit e645535a954a ("tracing: Add option to use memmapped memory for trace boot instance") changed trace_array_get_by_name() to trace_array_create_systems(), enable_instances() does not reuse the same name instance. Therefore, if an administrator mistakenly specifies multiple `trace_instance=` options with duplicate names, all are created but only the first is accessible via tracefs. Check whether an instance with the same name already exists before creating a new one, and reject duplicates with a warning. Link: https://patch.msgid.link/178847790399.283263.5313150997200138426.stgit@devnote2 Fixes: e645535a954a ("tracing: Add option to use memmapped memory for trace boot instance") Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 722d0ba2d233..138e983c3c2f 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -9710,6 +9710,11 @@ __init static void enable_instances(void) if (flag_delim) *flag_delim++ = '\0'; + if (trace_array_find(name)) { + pr_warn("Tracing: Instance %s already exists\n", name); + continue; + } + if (backup) { if (backup_instance_area(backup, &addr, &size) < 0) continue; From 54d37bcf2f497140b9207968557ddb484058e749 Mon Sep 17 00:00:00 2001 From: Zhongqiu Han Date: Tue, 1 Sep 2026 22:36:35 +0800 Subject: [PATCH 0679/1198] cpufreq: zero-initialize policy cpumask before sysfs publication cpufreq_policy_alloc() allocates policy->cpus with alloc_cpumask_var(), i.e. without __GFP_ZERO, unlike the sibling related_cpus and real_cpus masks. With CONFIG_CPUMASK_OFFSTACK=y the mask is a separate kmalloc_node() allocation, so its bitmap holds whatever the slab allocator left behind: cpufreq_online() cpufreq_policy_alloc() alloc_cpumask_var(&policy->cpus) /* bitmap is uninitialized */ kobject_init_and_add() /* policy%u/ appears in sysfs */ cpufreq_policy_online() cpumask_copy(policy->cpus, cpumask_of(cpu)) /* first valid value */ This leaves a window in which the sysfs attributes are already reachable while policy->cpus is still garbage. show()/store() gate on policy_is_inactive(), i.e. cpumask_empty(policy->cpus), so a non-zero bitmap makes them run the attribute callbacks on a policy that is not initialized yet. Fix this by using zalloc_cpumask_var() for policy->cpus. Fixes: 2fc3384dc75b ("cpufreq: Initialize policy->kobj while allocating policy") Cc: All applicable Signed-off-by: Zhongqiu Han Acked-by: Viresh Kumar Link: https://patch.msgid.link/20260901143635.4106960-1-zhongqiu.han@oss.qualcomm.com Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/cpufreq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 9efbf5b1781a..96515880b4ac 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1249,7 +1249,7 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu) if (!policy) return NULL; - if (!alloc_cpumask_var(&policy->cpus, GFP_KERNEL)) + if (!zalloc_cpumask_var(&policy->cpus, GFP_KERNEL)) goto err_free_policy; if (!zalloc_cpumask_var(&policy->related_cpus, GFP_KERNEL)) From 90feea391c64fc43bf44184fcf2b243ab991ce47 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 3 Sep 2026 11:05:58 -0700 Subject: [PATCH 0680/1198] drm/amd/display: Fix harmless type mismatch in allocation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit While converting to kmalloc_obj() API, a type assignment mismatch was found between the desired struct dcn42_resource_pool and the allocated struct dcn401_resource_pool. Fix the type (it is harmless: the objects have the same contents and size). Signed-off-by: Kees Cook --- Cc: Harry Wentland Cc: Leo Li Cc: Rodrigo Siqueira Cc: Alex Deucher Cc: "Christian König" Cc: David Airlie Cc: Simona Vetter Cc: Dan Wheeler Cc: Roman Li Cc: Ovidiu Bunea Cc: Charlene Liu Cc: Leo Chen Cc: Ivan Lipski Cc: Gaghik Khachatrian Cc: Cc: --- drivers/gpu/drm/amd/display/dc/resource/dcn42/dcn42_resource.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn42/dcn42_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn42/dcn42_resource.c index 6370d3903eb5..b93d608b64a9 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn42/dcn42_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn42/dcn42_resource.c @@ -2441,7 +2441,7 @@ struct resource_pool *dcn42_create_resource_pool( struct dc *dc) { struct dcn42_resource_pool *pool = - kzalloc(sizeof(struct dcn401_resource_pool), GFP_KERNEL); + kzalloc(sizeof(struct dcn42_resource_pool), GFP_KERNEL); if (!pool) return NULL; From 5e8c349bc8d790fe031a4332e502f5d4f9878644 Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Fri, 4 Sep 2026 15:37:39 +0800 Subject: [PATCH 0681/1198] selftests/bpf: Fix flaky bpf_nf test when random NAT port is 0 The bpf_nf test allocs a ct, sets snat and dnat with random addr and port via bpf_ct_set_nat_info(), then looks the ct up and checks the reply tuple against what was set. The port comes from bpf_get_prandom_u32() and can be 0. For bpf_ct_set_nat_info(), port 0 means "port not specified", so only the addr is mapped and the kernel keeps the original port. The check then compares that port with 0 and fails, which shows up as a flaky "Test for source natting" failure in CI [1][2]. Keep the random port in 1..65535 so it is always specified. [1] https://github.com/kernel-patches/bpf/actions/runs/33830002889/job/100893868791 [2] https://github.com/kernel-patches/bpf/actions/runs/33829976794/job/100893220999 Fixes: b06b45e82b59 ("selftests/bpf: add tests for bpf_ct_set_nat_info kfunc") Signed-off-by: Jiayuan Chen Link: https://lore.kernel.org/r/20260904073745.363314-1-jiayuan.chen@linux.dev Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/progs/test_bpf_nf.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/bpf/progs/test_bpf_nf.c b/tools/testing/selftests/bpf/progs/test_bpf_nf.c index df43649ecb78..eda9b7bbab75 100644 --- a/tools/testing/selftests/bpf/progs/test_bpf_nf.c +++ b/tools/testing/selftests/bpf/progs/test_bpf_nf.c @@ -190,8 +190,8 @@ nf_ct_test(struct nf_conn *(*lookup_fn)(void *, struct bpf_sock_tuple *, u32, ct = alloc_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def)); if (ct) { - __u16 sport = bpf_get_prandom_u32(); - __u16 dport = bpf_get_prandom_u32(); + __u16 sport = bpf_get_prandom_u32() % 65535 + 1; + __u16 dport = bpf_get_prandom_u32() % 65535 + 1; union nf_inet_addr saddr = {}; union nf_inet_addr daddr = {}; struct nf_conn *ct_ins; @@ -293,8 +293,8 @@ nf_ct_opts_new_test(struct nf_conn *(*lookup_fn)(void *, struct bpf_sock_tuple * ct = alloc_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def)); if (ct) { - __u16 sport = bpf_get_prandom_u32(); - __u16 dport = bpf_get_prandom_u32(); + __u16 sport = bpf_get_prandom_u32() % 65535 + 1; + __u16 dport = bpf_get_prandom_u32() % 65535 + 1; union nf_inet_addr saddr = {}; union nf_inet_addr daddr = {}; struct nf_conn *ct_ins; From 6903878d4654bdef4e08e38cdf1ae306ce7de5f9 Mon Sep 17 00:00:00 2001 From: Julian Braha Date: Fri, 4 Sep 2026 12:09:11 +0100 Subject: [PATCH 0682/1198] ima: allow users to specify the pcr index with IMA_MEASURE_PCR_IDX The IMA_MEASURE_PCR_IDX option is currently not visible in the kconfig frontend, so it always uses its default, 10. This means that the 'range 8 14' is dead code, and users are unable to specify the pcr index value. In a previous discussion, Mimi explained that users should be able to use this config option to specify the pcr index. [1] Let's add a prompt for users to specify the pcr index, when EXPERT is enabled. This dead range was found by kconfirm, a static analysis tool for Kconfig. Link: https://lore.kernel.org/all/1feff118-4afa-4b9c-86f1-271a7a88208f@gmail.com/T/#mc4efa2491b4937eb7c9e532c29ffba516a70e662 [1] Signed-off-by: Julian Braha Signed-off-by: Mimi Zohar --- security/integrity/ima/Kconfig | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig index b3a9f86809b0..72654cf797cd 100644 --- a/security/integrity/ima/Kconfig +++ b/security/integrity/ima/Kconfig @@ -46,12 +46,16 @@ config IMA_KEXEC config IMA_MEASURE_PCR_IDX int + prompt "PCR Index for Aggregate" if EXPERT range 8 14 default 10 help IMA_MEASURE_PCR_IDX determines the TPM PCR register index that IMA uses to maintain the integrity aggregate of the - measurement list. If unsure, use the default 10. + measurement list. Most attestation tooling expects PCR 10. + + The default is almost always what you want. Only change this + if you know what you are doing. config IMA_LSM_RULES bool From 5df46ddcb7b36878c1b691e9057a0509042a2567 Mon Sep 17 00:00:00 2001 From: Yuan Chen Date: Fri, 4 Sep 2026 12:41:52 +0200 Subject: [PATCH 0683/1198] bpf: Preserve special fields in recycled rhtab elements rhtab_map_update_elem() initializes special fields after obtaining an element from bpf_mem_cache_alloc(). The allocator can return a fresh, zeroed unit, or recycle one from its RCU-pending lists before the registered destructor has run. A BPF program can retain a map-value pointer after deleting its element and initialize and arm a timer through that pointer. If the deleted unit is recycled, check_and_init_map_value() clears the only pointer to the timer. Neither a later deletion nor rhtab_mem_dtor() can then cancel it, and the callback can run with its key and value pointing into freed memory. Do not reinitialize special fields on insertion. Fresh allocator units are already zeroed. For recycled units, the special fields are ownership state that must remain visible to the eventual destructor. copy_map_value() already skips those fields, matching the non-preallocated hash-map path and the lifecycle established by commit 275c30bcee66 ("bpf: Don't reinit map value in prealloc_lru_pop"). Fixes: 6905f8601298 ("bpf: Allow special fields in resizable hashtab") Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Yuan Chen [ kkd: Split out the fix and rewrote the commit log ] Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260904104203.345917-2-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/hashtab.c | 1 - 1 file changed, 1 deletion(-) diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index e89fde188389..527cc5716ee8 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -3070,7 +3070,6 @@ static long rhtab_map_update_elem(struct bpf_map *map, void *key, void *value, u memcpy(elem->data, key, map->key_size); copy_map_value(map, rhtab_elem_value(elem, map->key_size), value); - check_and_init_map_value(map, rhtab_elem_value(elem, map->key_size)); /* Prevent deadlock for NMI programs attempting to take bucket lock */ bpf_disable_instrumentation(); From dbf6806dc81553edbab72fcec9a6d637dedff2f4 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 4 Sep 2026 12:41:53 +0200 Subject: [PATCH 0684/1198] selftests/bpf: Test timer field on recycled rhtab element Exercise the rhtab special-field lifecycle with the sequence from the original report. A bpf_for_each_map_elem() callback deletes the sole element, then initializes and arms a timer through the callback value pointer while it remains valid. Use a one-element map and pin userspace and BPF execution to one CPU. Repeated delete-and-replace cycles drain the per-CPU allocator cache, and periodic RCU synchronization makes the deleted units available for recycling. After each replacement, a second BPF program calls bpf_timer_cancel() on its value. A successful cancellation proves both that a timer-bearing unit was recycled and that insertion preserved the timer field. Without the fix, insertion clears that field and cancellation keeps returning -EINVAL. A long expiration keeps the timer callback out of the test, so the regression is detected without accessing freed memory. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260904104203.345917-3-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- .../selftests/bpf/prog_tests/rhash_timer.c | 141 ++++++++++++++++++ .../testing/selftests/bpf/progs/rhash_timer.c | 98 ++++++++++++ 2 files changed, 239 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/rhash_timer.c create mode 100644 tools/testing/selftests/bpf/progs/rhash_timer.c diff --git a/tools/testing/selftests/bpf/prog_tests/rhash_timer.c b/tools/testing/selftests/bpf/prog_tests/rhash_timer.c new file mode 100644 index 000000000000..3aad9fc02e06 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/rhash_timer.c @@ -0,0 +1,141 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include + +#include +#include "rhash_timer.skel.h" + +#define MAX_ATTEMPTS 256 +#define RCU_SYNC_INTERVAL 64 + +static int pin_to_first_cpu(cpu_set_t *old_mask) +{ + cpu_set_t new_mask; + int cpu; + + if (sched_getaffinity(0, sizeof(*old_mask), old_mask)) + return -errno; + + for (cpu = 0; cpu < CPU_SETSIZE; cpu++) + if (CPU_ISSET(cpu, old_mask)) + break; + if (cpu == CPU_SETSIZE) + return -EINVAL; + + CPU_ZERO(&new_mask); + CPU_SET(cpu, &new_mask); + if (sched_setaffinity(0, sizeof(new_mask), &new_mask)) + return -errno; + return 0; +} + +static int update_timer_map(int map_fd, __u64 key) +{ + __u64 value[3] = {}; + + return bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST); +} + +static int run_prog(int prog_fd, struct bpf_test_run_opts *opts) +{ + int err; + + err = bpf_prog_test_run_opts(prog_fd, opts); + if (err) + return err; + return opts->retval; +} + +void test_rhash_timer(void) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts); + struct rhash_timer *skel = NULL; + cpu_set_t old_mask; + int map_fd = -1, arm_fd, cancel_fd; + bool affinity_set = false; + __u64 key = 1; + int attempt, err; + + err = pin_to_first_cpu(&old_mask); + if (!ASSERT_OK(err, "pin_to_first_cpu")) + return; + affinity_set = true; + + skel = rhash_timer__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + goto out; + + map_fd = bpf_map__fd(skel->maps.timer_map); + if (!ASSERT_GE(map_fd, 0, "timer_map fd")) + goto out; + arm_fd = bpf_program__fd(skel->progs.arm_deleted_timer); + if (!ASSERT_GE(arm_fd, 0, "arm_deleted_timer fd")) + goto out; + cancel_fd = bpf_program__fd(skel->progs.cancel_recycled_timer); + if (!ASSERT_GE(cancel_fd, 0, "cancel_recycled_timer fd")) + goto out; + + err = update_timer_map(map_fd, key); + if (!ASSERT_OK(err, "seed_timer_map")) + goto out; + + for (attempt = 0; attempt < MAX_ATTEMPTS; attempt++) { + err = run_prog(arm_fd, &opts); + if (err) { + ASSERT_OK(err, "arm_deleted_timer"); + goto out; + } + if (skel->bss->armed != attempt + 1) { + ASSERT_EQ(skel->bss->armed, attempt + 1, "armed"); + goto out; + } + if (skel->bss->timer_init_err) { + ASSERT_OK(skel->bss->timer_init_err, "timer_init_err"); + goto out; + } + if (skel->bss->timer_set_callback_err) { + ASSERT_OK(skel->bss->timer_set_callback_err, + "timer_set_callback_err"); + goto out; + } + if (skel->bss->timer_start_err) { + ASSERT_OK(skel->bss->timer_start_err, "timer_start_err"); + goto out; + } + + if ((attempt + 1) % RCU_SYNC_INTERVAL == 0) { + err = kern_sync_rcu(); + if (err) { + ASSERT_OK(err, "kern_sync_rcu"); + goto out; + } + } + + err = update_timer_map(map_fd, ++key); + if (err) { + ASSERT_OK(err, "replace_timer_map"); + goto out; + } + + err = run_prog(cancel_fd, &opts); + if (err) { + ASSERT_OK(err, "cancel_recycled_timer"); + goto out; + } + if (skel->bss->timer_cancel_err) { + ASSERT_OK(skel->bss->timer_cancel_err, "timer_cancel_err"); + goto out; + } + if (skel->bss->cancelled) + break; + } + + ASSERT_GT(skel->bss->cancelled, 0, "preserved timer"); +out: + if (map_fd >= 0) + bpf_map_delete_elem(map_fd, &key); + rhash_timer__destroy(skel); + if (affinity_set) + sched_setaffinity(0, sizeof(old_mask), &old_mask); +} diff --git a/tools/testing/selftests/bpf/progs/rhash_timer.c b/tools/testing/selftests/bpf/progs/rhash_timer.c new file mode 100644 index 000000000000..2e06a463c605 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/rhash_timer.c @@ -0,0 +1,98 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include + +#define CLOCK_MONOTONIC 1 +#define TIMER_NSEC (60ULL * 1000 * 1000 * 1000) + +struct timer_value { + struct bpf_timer timer; + u64 data; +}; + +struct { + __uint(type, BPF_MAP_TYPE_RHASH); + __uint(map_flags, BPF_F_NO_PREALLOC); + __uint(max_entries, 1); + __type(key, u64); + __type(value, struct timer_value); +} timer_map SEC(".maps"); + +u64 armed; +u64 cancelled; +long timer_init_err; +long timer_set_callback_err; +long timer_start_err; +long timer_cancel_err; + +static int timer_cb(void *map, u64 *key, struct timer_value *value) +{ + return 0; +} + +static long arm_timer_cb(struct bpf_map *map, u64 *key, + struct timer_value *value, void *ctx) +{ + u64 key_copy = *key; + long err; + + err = bpf_map_delete_elem(map, &key_copy); + if (err) + return 1; + + err = bpf_timer_init(&value->timer, map, CLOCK_MONOTONIC); + if (err) { + timer_init_err = err; + return 1; + } + + err = bpf_timer_set_callback(&value->timer, timer_cb); + if (err) { + timer_set_callback_err = err; + return 1; + } + + err = bpf_timer_start(&value->timer, TIMER_NSEC, BPF_F_TIMER_CPU_PIN); + if (err) { + timer_start_err = err; + return 1; + } + + __sync_fetch_and_add(&armed, 1); + return 1; +} + +static long cancel_timer_cb(struct bpf_map *map, u64 *key, + struct timer_value *value, void *ctx) +{ + long err; + + err = bpf_timer_cancel(&value->timer); + if (err == -EINVAL) + return 1; + if (err < 0) { + timer_cancel_err = err; + return 1; + } + + __sync_fetch_and_add(&cancelled, 1); + return 1; +} + +SEC("syscall") +int arm_deleted_timer(void *ctx) +{ + bpf_for_each_map_elem(&timer_map, arm_timer_cb, NULL, 0); + return 0; +} + +SEC("syscall") +int cancel_recycled_timer(void *ctx) +{ + bpf_for_each_map_elem(&timer_map, cancel_timer_cb, NULL, 0); + return 0; +} + +char _license[] SEC("license") = "GPL"; From 65cc95eba9e8b46312cac38c227473605a4b996a Mon Sep 17 00:00:00 2001 From: Nuoqi Gui Date: Fri, 4 Sep 2026 12:41:54 +0200 Subject: [PATCH 0685/1198] bpf: Cancel special fields when recycling rhtab elements rhtab_map_update_existing() and rhtab_delete_elem() call bpf_obj_free_fields() when replacing or deleting a value. These map operations can run from BPF programs in NMI context, where releasing a referenced kptr or another complex field is not generally safe. Array and hash maps avoid that problem by cancelling only the asynchronous fields which can be stopped safely in the caller context. Other ownership state remains attached to the allocation until its memory allocator destructor performs the final cleanup. Use bpf_obj_cancel_fields() for the corresponding rhtab paths as well. This cancels timers, workqueues, and task work while allowing rhtab_mem_dtor() to release referenced kptrs when the allocation is eventually destroyed. Fixes: 6905f8601298 ("bpf: Allow special fields in resizable hashtab") Signed-off-by: Nuoqi Gui Acked-by: Mykyta Yatsenko [ kkd: Rebased, used direct helper calls, and rewrote the commit log ] Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260904104203.345917-4-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/hashtab.c | 17 +++-------------- 1 file changed, 3 insertions(+), 14 deletions(-) diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 527cc5716ee8..cc60e99ffbe9 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -2868,16 +2868,6 @@ static int rhtab_map_alloc_check(union bpf_attr *attr) return htab_map_alloc_check(attr); } -static void rhtab_check_and_free_fields(struct bpf_rhtab *rhtab, - struct rhtab_elem *elem) -{ - if (IS_ERR_OR_NULL(rhtab->map.record)) - return; - - bpf_obj_free_fields(rhtab->map.record, - rhtab_elem_value(elem, rhtab->map.key_size)); -} - static void rhtab_mem_dtor(void *obj, void *ctx) { struct htab_btf_record *hrec = ctx; @@ -2967,8 +2957,8 @@ static int rhtab_delete_elem(struct bpf_rhtab *rhtab, struct rhtab_elem *elem, v rhtab_read_elem_value(&rhtab->map, copy, elem, flags); check_and_init_map_value(&rhtab->map, copy); } - /* Release internal structs: kptr, bpf_timer, task_work, wq */ - rhtab_check_and_free_fields(rhtab, elem); + bpf_obj_cancel_fields(&rhtab->map, + rhtab_elem_value(elem, rhtab->map.key_size)); bpf_mem_cache_free_rcu(&rhtab->ma, elem); return 0; } @@ -3009,7 +2999,6 @@ static int rhtab_map_lookup_and_delete_elem(struct bpf_map *map, void *key, void static long rhtab_map_update_existing(struct bpf_map *map, struct rhtab_elem *elem, void *value, u64 map_flags) { - struct bpf_rhtab *rhtab = container_of(map, struct bpf_rhtab, map); void *old_val = rhtab_elem_value(elem, map->key_size); if (map_flags & BPF_NOEXIST) @@ -3029,7 +3018,7 @@ static long rhtab_map_update_existing(struct bpf_map *map, struct rhtab_elem *el * kptrs/etc. still sit in the slot. Cancel them after the copy * to match arraymap's update semantics. */ - rhtab_check_and_free_fields(rhtab, elem); + bpf_obj_cancel_fields(map, old_val); return 0; } From 2b97956af60810cd382b86b9ce9aea421b889861 Mon Sep 17 00:00:00 2001 From: Nuoqi Gui Date: Fri, 4 Sep 2026 12:41:55 +0200 Subject: [PATCH 0686/1198] selftests/bpf: Test rhtab kptr cancellation semantics Resizable hash-map updates and deletions must not perform full special-field destruction in their caller context. In particular, a referenced kptr must remain attached to the allocation until the memory allocator destructor can release it safely. Add separate coverage for both affected paths. The update test stores a task kptr, replaces the ordinary value bytes with BPF_EXIST, and verifies that the kptr survived. The delete test removes an element and exchanges its kptr through the still-valid map-value pointer before the allocation is reclaimed. Both cases observe a NULL kptr when rhtab uses bpf_obj_free_fields(). They recover and release the reference after rhtab switches to cancellation semantics. Signed-off-by: Nuoqi Gui [ kkd: Split update and delete coverage and rewrote the commit log ] Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260904104203.345917-5-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- .../testing/selftests/bpf/prog_tests/rhash.c | 6 + tools/testing/selftests/bpf/progs/rhash.c | 112 ++++++++++++++++++ 2 files changed, 118 insertions(+) diff --git a/tools/testing/selftests/bpf/prog_tests/rhash.c b/tools/testing/selftests/bpf/prog_tests/rhash.c index 98bb66907b7f..0641bd5b0a9e 100644 --- a/tools/testing/selftests/bpf/prog_tests/rhash.c +++ b/tools/testing/selftests/bpf/prog_tests/rhash.c @@ -172,6 +172,12 @@ void test_rhash(void) if (test__start_subtest("test_rhash_delete_nonexistent")) rhash_run("test_rhash_delete_nonexistent"); + if (test__start_subtest("test_rhash_kptr_update")) + rhash_run("test_rhash_kptr_update"); + + if (test__start_subtest("test_rhash_kptr_delete")) + rhash_run("test_rhash_kptr_delete"); + if (test__start_subtest("test_rhash_map_extra_presize")) rhash_map_extra_presize(); diff --git a/tools/testing/selftests/bpf/progs/rhash.c b/tools/testing/selftests/bpf/progs/rhash.c index fc2dac3a719e..aea4de8dc781 100644 --- a/tools/testing/selftests/bpf/progs/rhash.c +++ b/tools/testing/selftests/bpf/progs/rhash.c @@ -19,6 +19,11 @@ struct elem { int val; }; +struct special_elem { + struct task_struct __kptr *task; + int val; +}; + struct { __uint(type, BPF_MAP_TYPE_RHASH); __uint(map_flags, BPF_F_NO_PREALLOC); @@ -27,6 +32,17 @@ struct { __type(value, struct elem); } rhmap SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_RHASH); + __uint(map_flags, BPF_F_NO_PREALLOC); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct special_elem); +} special_fields SEC(".maps"); + +extern struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym; +extern void bpf_task_release(struct task_struct *p) __ksym; + SEC("syscall") int test_rhash_lookup_update(void *ctx) { @@ -246,3 +262,99 @@ int test_rhash_delete_nonexistent(void *ctx) err = 0; return 0; } + +SEC("syscall") +int test_rhash_kptr_update(void *ctx) +{ + struct special_elem val1 = { .val = 1 }; + struct special_elem val2 = { .val = 2 }; + struct task_struct *task, *old; + struct special_elem *elem; + int key = 0; + + err = 1; + if (bpf_map_update_elem(&special_fields, &key, &val1, BPF_NOEXIST)) + return 1; + + err = 2; + elem = bpf_map_lookup_elem(&special_fields, &key); + if (!elem) + return 2; + + err = 3; + task = bpf_task_acquire(bpf_get_current_task_btf()); + if (!task) + return 3; + + err = 4; + old = bpf_kptr_xchg(&elem->task, task); + if (old) { + bpf_task_release(old); + return 4; + } + + err = 5; + if (bpf_map_update_elem(&special_fields, &key, &val2, BPF_EXIST)) + return 5; + + err = 6; + elem = bpf_map_lookup_elem(&special_fields, &key); + if (!elem || elem->val != 2) + return 6; + + err = 7; + old = bpf_kptr_xchg(&elem->task, NULL); + if (!old) + return 7; + bpf_task_release(old); + + err = 8; + if (bpf_map_delete_elem(&special_fields, &key)) + return 8; + + err = 0; + return 0; +} + +SEC("syscall") +int test_rhash_kptr_delete(void *ctx) +{ + struct special_elem val = {}; + struct task_struct *task, *old; + struct special_elem *elem; + int key = 0; + + err = 1; + if (bpf_map_update_elem(&special_fields, &key, &val, BPF_NOEXIST)) + return 1; + + err = 2; + elem = bpf_map_lookup_elem(&special_fields, &key); + if (!elem) + return 2; + + err = 3; + task = bpf_task_acquire(bpf_get_current_task_btf()); + if (!task) + return 3; + + err = 4; + old = bpf_kptr_xchg(&elem->task, task); + if (old) { + bpf_task_release(old); + return 4; + } + + err = 5; + if (bpf_map_delete_elem(&special_fields, &key)) + return 5; + + err = 6; + old = bpf_kptr_xchg(&elem->task, NULL); + if (!old) + return 6; + bpf_task_release(old); + + err = 0; + return 0; +} From ecdc5043794c9184aa8e6c814603899479c46b35 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 4 Sep 2026 12:41:56 +0200 Subject: [PATCH 0687/1198] bpf: Mark NULL kptr stores precise check_map_kptr_access() permits a scalar store into an untrusted kptr field only when the register is known to contain zero. Unlike other verifier checks whose outcome depends on a scalar value, it does not mark that register precise. A state checkpoint reached with an imprecise zero can therefore prune a second path that reaches the store with an arbitrary nonzero scalar. The program can write attacker-controlled bits into the kptr field and load them back as a PTR_TO_BTF_ID. Call mark_chain_precision() before accepting a known-zero register. This forces state equivalence to compare its scalar range and makes the verifier visit and reject a path carrying a nonzero value. Fixes: 61df10c7799e ("bpf: Allow storing unreferenced kptr in map") Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Kumar Kartikeya Dwivedi Acked-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260904104203.345917-6-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 9c6ad157a61e..b71c5274b3dc 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4708,8 +4708,15 @@ static int check_map_kptr_access(struct bpf_verifier_env *env, return ret; } else if (class == BPF_STX) { val_reg = reg_state(env, value_regno); - if (!bpf_register_is_null(val_reg) && - map_kptr_match_type(env, kptr_field, val_reg, value_regno)) + if (bpf_register_is_null(val_reg)) { + /* + * This store is valid only because the scalar is known to be + * zero. Mark it precise so another scalar cannot be pruned + * against this state. + */ + return mark_chain_precision(env, value_regno); + } + if (map_kptr_match_type(env, kptr_field, val_reg, value_regno)) return -EACCES; } else if (class == BPF_ST) { if (insn->imm) { From 9dcddf30ac1a14f18c3221db9292bcaa0735ee2f Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 4 Sep 2026 12:41:57 +0200 Subject: [PATCH 0688/1198] selftests/bpf: Test imprecise scalar kptr stores Add a verifier regression where an imprecise zero scalar reaches a kptr store first and a nonzero scalar reaches the same instruction on a second path. Without the corresponding verifier fix, the second path is pruned and the program is unexpectedly accepted. With the fix, the scalar range is compared and the invalid store is rejected. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260904104203.345917-7-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- .../selftests/bpf/progs/map_kptr_fail.c | 37 +++++++++++++++++++ 1 file changed, 37 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/map_kptr_fail.c b/tools/testing/selftests/bpf/progs/map_kptr_fail.c index 5e25ca806060..eee35d203b66 100644 --- a/tools/testing/selftests/bpf/progs/map_kptr_fail.c +++ b/tools/testing/selftests/bpf/progs/map_kptr_fail.c @@ -409,4 +409,41 @@ int reject_scalar_store_to_kptr(struct __sk_buff *ctx) return 0; } +SEC("?tc") +__description("reject imprecise scalar store to kptr after state pruning") +__failure __msg("invalid kptr access, R7 type=scalar") +__naked void reject_imprecise_scalar_store_to_kptr(void) +{ + asm volatile ( + "r0 = 0;" + "*(u32 *)(r10 - 4) = r0;" + "r2 = r10;" + "r2 += -4;" + "r1 = %[array_map] ll;" + "call %[bpf_map_lookup_elem];" + "if r0 == 0 goto l2_%=;" + "r6 = r0;" + "r9 = *(u64 *)(r6 + 0);" + "if r9 != 0 goto l0_%=;" + "r7 = 0;" + ".rept 10;" + "r5 = 1;" + ".endr;" + "goto l1_%=;" + "l0_%=:" + "r7 = 0x4141414141414141 ll;" + ".rept 10;" + "r5 = 1;" + ".endr;" + "l1_%=:" + "*(u64 *)(r6 + 8) = r7;" + "l2_%=:" + "r0 = 0;" + "exit;" + : + : __imm(bpf_map_lookup_elem), + __imm_addr(array_map) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; From b90c5d770dad910fb89e6c1b15052a8a1e8db752 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 4 Sep 2026 12:41:58 +0200 Subject: [PATCH 0689/1198] bpf: Preserve inner map identity in callback frames Callback frame constructors initialize map-typed argument registers with __mark_reg_known_zero() and then restore map_ptr. This clears map_uid, which is the only field distinguishing inner maps that share an inner_map_meta template. When a timer callback invokes bpf_for_each_map_elem() on a second inner map, both the saved first map and the second map value can reach the nested callback as the same template with map_uid zero. bpf_timer_init() then accepts pairing the timer from the second map with the first map. The runtime records the first map in the timer without taking a reference. Freeing that map does not find the timer stored in the second map, so a later timer callback dereferences the freed map. Copy map_uid from the same caller register as map_ptr when constructing for-each, timer/workqueue, and task-work callback arguments. The existing identity check can then reject mismatched inner maps while allowing a callback value to be paired with its actual map. Fixes: 3e8ce29850f1 ("bpf: Prevent pointer mismatch in bpf_timer_init.") Fixes: 69c087ba6225 ("bpf: Add bpf_for_each_map_elem() helper") Fixes: 5c8fd7e2b5b0 ("bpf: bpf task work plumbing") Reported-by: Nicholas Carlini Suggested-by: Nicholas Carlini Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260904104203.345917-8-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index b71c5274b3dc..c8699a8831df 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -10018,10 +10018,12 @@ int map_set_for_each_callback_args(struct bpf_verifier_env *env, callee->regs[BPF_REG_2].type = PTR_TO_MAP_KEY; __mark_reg_known_zero(&callee->regs[BPF_REG_2]); callee->regs[BPF_REG_2].map_ptr = caller->regs[BPF_REG_1].map_ptr; + callee->regs[BPF_REG_2].map_uid = caller->regs[BPF_REG_1].map_uid; callee->regs[BPF_REG_3].type = PTR_TO_MAP_VALUE; __mark_reg_known_zero(&callee->regs[BPF_REG_3]); callee->regs[BPF_REG_3].map_ptr = caller->regs[BPF_REG_1].map_ptr; + callee->regs[BPF_REG_3].map_uid = caller->regs[BPF_REG_1].map_uid; /* pointer to stack or null */ callee->regs[BPF_REG_4] = caller->regs[BPF_REG_3]; @@ -10099,6 +10101,7 @@ static int set_timer_callback_state(struct bpf_verifier_env *env, int insn_idx) { struct bpf_map *map_ptr = caller->regs[BPF_REG_1].map_ptr; + u32 map_uid = caller->regs[BPF_REG_1].map_uid; /* bpf_timer_set_callback(struct bpf_timer *timer, void *callback_fn); * callback_fn(struct bpf_map *map, void *key, void *value); @@ -10106,14 +10109,17 @@ static int set_timer_callback_state(struct bpf_verifier_env *env, callee->regs[BPF_REG_1].type = CONST_PTR_TO_MAP; __mark_reg_known_zero(&callee->regs[BPF_REG_1]); callee->regs[BPF_REG_1].map_ptr = map_ptr; + callee->regs[BPF_REG_1].map_uid = map_uid; callee->regs[BPF_REG_2].type = PTR_TO_MAP_KEY; __mark_reg_known_zero(&callee->regs[BPF_REG_2]); callee->regs[BPF_REG_2].map_ptr = map_ptr; + callee->regs[BPF_REG_2].map_uid = map_uid; callee->regs[BPF_REG_3].type = PTR_TO_MAP_VALUE; __mark_reg_known_zero(&callee->regs[BPF_REG_3]); callee->regs[BPF_REG_3].map_ptr = map_ptr; + callee->regs[BPF_REG_3].map_uid = map_uid; /* unused */ bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_4]); @@ -10213,6 +10219,7 @@ static int set_task_work_schedule_callback_state(struct bpf_verifier_env *env, int insn_idx) { struct bpf_map *map_ptr = caller->regs[BPF_REG_3].map_ptr; + u32 map_uid = caller->regs[BPF_REG_3].map_uid; /* * callback_fn(struct bpf_map *map, void *key, void *value); @@ -10220,14 +10227,17 @@ static int set_task_work_schedule_callback_state(struct bpf_verifier_env *env, callee->regs[BPF_REG_1].type = CONST_PTR_TO_MAP; __mark_reg_known_zero(&callee->regs[BPF_REG_1]); callee->regs[BPF_REG_1].map_ptr = map_ptr; + callee->regs[BPF_REG_1].map_uid = map_uid; callee->regs[BPF_REG_2].type = PTR_TO_MAP_KEY; __mark_reg_known_zero(&callee->regs[BPF_REG_2]); callee->regs[BPF_REG_2].map_ptr = map_ptr; + callee->regs[BPF_REG_2].map_uid = map_uid; callee->regs[BPF_REG_3].type = PTR_TO_MAP_VALUE; __mark_reg_known_zero(&callee->regs[BPF_REG_3]); callee->regs[BPF_REG_3].map_ptr = map_ptr; + callee->regs[BPF_REG_3].map_uid = map_uid; /* unused */ bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_4]); From e615b9fd4d9df602030d9b57a5eca206abbb0aff Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 4 Sep 2026 12:41:59 +0200 Subject: [PATCH 0690/1198] selftests/bpf: Test inner map identities in callbacks Add load-only timer_mim coverage for inner map identities propagated through nested timer and bpf_for_each_map_elem() callbacks. The negative case initializes a timer in the second inner map with the map saved from the first inner map timer callback. The positive case pairs the timer value with the map supplied to the same for-each callback. Without the verifier fix, the mismatched-map program is accepted while the same-map control is rejected. Preserving map_uid reverses both verdicts. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260904104203.345917-9-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- .../selftests/bpf/prog_tests/timer_mim.c | 29 ++++++- .../selftests/bpf/progs/timer_mim_reject.c | 84 ++++++++++++++++++- 2 files changed, 109 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/timer_mim.c b/tools/testing/selftests/bpf/prog_tests/timer_mim.c index c930c7d7105b..fa7bb769ca31 100644 --- a/tools/testing/selftests/bpf/prog_tests/timer_mim.c +++ b/tools/testing/selftests/bpf/prog_tests/timer_mim.c @@ -59,10 +59,32 @@ void serial_test_timer_mim(void) int err; old_print_fn = libbpf_set_print(NULL); - timer_reject_skel = timer_mim_reject__open_and_load(); - libbpf_set_print(old_print_fn); - if (!ASSERT_ERR_PTR(timer_reject_skel, "timer_reject_skel_load")) + timer_reject_skel = timer_mim_reject__open(); + if (!ASSERT_OK_PTR(timer_reject_skel, "timer_reject_skel_open")) goto cleanup; + bpf_program__set_autoload(timer_reject_skel->progs.test1, true); + err = timer_mim_reject__load(timer_reject_skel); + ASSERT_ERR(err, "timer_reject_skel_load"); + timer_mim_reject__destroy(timer_reject_skel); + + timer_reject_skel = timer_mim_reject__open(); + if (!ASSERT_OK_PTR(timer_reject_skel, "callback_reject_skel_open")) + goto cleanup; + bpf_program__set_autoload(timer_reject_skel->progs.callback_map_uid_mismatch, true); + err = timer_mim_reject__load(timer_reject_skel); + ASSERT_ERR(err, "callback_reject_skel_load"); + timer_mim_reject__destroy(timer_reject_skel); + + timer_reject_skel = timer_mim_reject__open(); + if (!ASSERT_OK_PTR(timer_reject_skel, "callback_accept_skel_open")) + goto cleanup; + bpf_program__set_autoload(timer_reject_skel->progs.callback_map_uid_match, true); + err = timer_mim_reject__load(timer_reject_skel); + if (!ASSERT_OK(err, "callback_accept_skel_load")) + goto cleanup; + timer_mim_reject__destroy(timer_reject_skel); + timer_reject_skel = NULL; + libbpf_set_print(old_print_fn); timer_skel = timer_mim__open_and_load(); if (!timer_skel && errno == EOPNOTSUPP) { @@ -75,6 +97,7 @@ void serial_test_timer_mim(void) err = timer_mim(timer_skel); ASSERT_OK(err, "timer_mim"); cleanup: + libbpf_set_print(old_print_fn); timer_mim__destroy(timer_skel); timer_mim_reject__destroy(timer_reject_skel); } diff --git a/tools/testing/selftests/bpf/progs/timer_mim_reject.c b/tools/testing/selftests/bpf/progs/timer_mim_reject.c index dd3f1ed6d6e6..83f31138336b 100644 --- a/tools/testing/selftests/bpf/progs/timer_mim_reject.c +++ b/tools/testing/selftests/bpf/progs/timer_mim_reject.c @@ -43,7 +43,7 @@ static int timer_cb(void *map, int *key, struct hmap_elem *val) return 0; } -SEC("fentry/bpf_fentry_test1") +SEC("?fentry/bpf_fentry_test1") int BPF_PROG(test1, int a) { struct hmap_elem init = {}; @@ -72,3 +72,85 @@ int BPF_PROG(test1, int a) err |= 8; return 0; } + +struct callback_ctx { + void *map; +}; + +static int mismatch_iter_cb(void *map, int *key, struct hmap_elem *val, struct callback_ctx *ctx) +{ + bpf_timer_init(&val->timer, ctx->map, CLOCK_MONOTONIC); + return 0; +} + +static int timer_mismatch_cb(void *map, int *key, struct hmap_elem *val) +{ + struct callback_ctx ctx = { .map = map }; + struct bpf_map *inner_map2; + int array_key2 = ARRAY_KEY2; + + inner_map2 = bpf_map_lookup_elem(&outer_arr, &array_key2); + if (!inner_map2) + return 0; + bpf_for_each_map_elem(inner_map2, mismatch_iter_cb, &ctx, 0); + return 0; +} + +static int match_iter_cb(void *map, int *key, struct hmap_elem *val, struct callback_ctx *ctx) +{ + bpf_timer_init(&val->timer, map, CLOCK_MONOTONIC); + return 0; +} + +static int timer_match_cb(void *map, int *key, struct hmap_elem *val) +{ + struct callback_ctx ctx = {}; + struct bpf_map *inner_map2; + int array_key2 = ARRAY_KEY2; + + inner_map2 = bpf_map_lookup_elem(&outer_arr, &array_key2); + if (!inner_map2) + return 0; + bpf_for_each_map_elem(inner_map2, match_iter_cb, &ctx, 0); + return 0; +} + +SEC("?fentry/bpf_fentry_test1") +int BPF_PROG(callback_map_uid_mismatch, int a) +{ + struct hmap_elem *val; + struct bpf_map *inner_map; + int array_key = ARRAY_KEY; + int hash_key = HASH_KEY; + + inner_map = bpf_map_lookup_elem(&outer_arr, &array_key); + if (!inner_map) + return 0; + val = bpf_map_lookup_elem(inner_map, &hash_key); + if (!val) + return 0; + + bpf_timer_init(&val->timer, inner_map, CLOCK_MONOTONIC); + bpf_timer_set_callback(&val->timer, timer_mismatch_cb); + return 0; +} + +SEC("?fentry/bpf_fentry_test1") +int BPF_PROG(callback_map_uid_match, int a) +{ + struct hmap_elem *val; + struct bpf_map *inner_map; + int array_key = ARRAY_KEY; + int hash_key = HASH_KEY; + + inner_map = bpf_map_lookup_elem(&outer_arr, &array_key); + if (!inner_map) + return 0; + val = bpf_map_lookup_elem(inner_map, &hash_key); + if (!val) + return 0; + + bpf_timer_init(&val->timer, inner_map, CLOCK_MONOTONIC); + bpf_timer_set_callback(&val->timer, timer_match_cb); + return 0; +} From dae8dda341d2d9034a90d59e8a7d502e1263813f Mon Sep 17 00:00:00 2001 From: Vincent Donnefort Date: Fri, 4 Sep 2026 17:44:48 +0100 Subject: [PATCH 0691/1198] tracing: Fix subbuf resize races with trace_pipe_raw readers Concurrent subbuffer resizes may crash trace_pipe_raw readers or leak uninitialized memory to userspace due to stale size values. Modify ring_buffer_alloc_read_page() to handle the resizing of an existing buffer_data_read_page if necessary and add a new ring_buffer_read_page_size(). This new function enables ring-buffer buffer_data_read_page users to not call the racy ring_buffer_subbuf_size_get(). This makes the spare_size member of ftrace_buffer_info redundant. Finally, handle buffer_data_read_page/reader_page order discrepancy in ring_buffer_read_page(). On a mismatch simply copy manually the data to the buffer_data_read_page. Link: https://lore.kernel.org/all/20260817140812.2C7D41F00A3A@smtp.kernel.org/ Link: https://patch.msgid.link/20260904164450.1345852-3-vdonnefort@google.com Fixes: bce761d75745 ("ring-buffer: Read and write to ring buffers with custom sub buffer size") Signed-off-by: Vincent Donnefort Signed-off-by: Steven Rostedt --- include/linux/ring_buffer.h | 5 +- kernel/trace/ring_buffer.c | 135 ++++++++++++++++++--------- kernel/trace/ring_buffer_benchmark.c | 6 +- kernel/trace/trace.c | 99 +++++++++----------- kernel/trace/trace.h | 9 +- 5 files changed, 145 insertions(+), 109 deletions(-) diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 0670742b2d60..afc7daa6ee7d 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -218,14 +218,15 @@ bool ring_buffer_time_stamp_abs(struct trace_buffer *buffer); size_t ring_buffer_nr_dirty_pages(struct trace_buffer *buffer, int cpu); struct buffer_data_read_page; -struct buffer_data_read_page * -ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu); +int ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu, + struct buffer_data_read_page **rpage); void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, struct buffer_data_read_page *page); int ring_buffer_read_page(struct trace_buffer *buffer, struct buffer_data_read_page *data_page, size_t len, int cpu, int full); void *ring_buffer_read_page_data(struct buffer_data_read_page *page); +unsigned int ring_buffer_read_page_size(struct buffer_data_read_page *rpage); struct trace_seq; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index ff0a44aa578d..077d6940af0c 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -330,6 +330,11 @@ struct buffer_data_read_page { struct buffer_data_page *data; /* actual data, stored in this page */ }; +static __always_inline unsigned int rb_read_page_capacity(struct buffer_data_read_page *rpage) +{ + return (PAGE_SIZE << rpage->order) - BUF_PAGE_HDR_SIZE; +} + /* * Note, the buffer_page list must be first. The buffer pages * are allocated in cache lines, which means that each buffer @@ -6998,56 +7003,78 @@ EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu); * ring_buffer_alloc_read_page - allocate a page to read from buffer * @buffer: the buffer to allocate for. * @cpu: the cpu buffer to allocate. + * @rpage: pointer to pass in an already allocated page (can be NULL) + * and returns the allocated page. * - * This function is used in conjunction with ring_buffer_read_page. + * This function is used in conjunction with ring_buffer_read_page(). * When reading a full page from the ring buffer, these functions * can be used to speed up the process. The calling function should * allocate a few pages first with this function. Then when it * needs to get pages from the ring buffer, it passes the result - * of this function into ring_buffer_read_page, which will swap + * of this function into ring_buffer_read_page(), which will swap * the page that was allocated, with the read page of the buffer. * + * If @rpage is provided, and it has a different order than the current + * subbuffer order, its payload will be freed and re-allocated. If it + * already matches the order, it is simply returned. + * * Returns: - * The page allocated, or ERR_PTR + * 0 on success, < 0 on error */ -struct buffer_data_read_page * -ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu) +int ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu, + struct buffer_data_read_page **rpage) { struct ring_buffer_per_cpu *cpu_buffer; - struct buffer_data_read_page *bpage = NULL; unsigned long flags; + unsigned int order; if (!cpumask_test_cpu(cpu, buffer->cpumask)) - return ERR_PTR(-ENODEV); + return -ENODEV; - bpage = kzalloc_obj(*bpage); - if (!bpage) - return ERR_PTR(-ENOMEM); + if (!rpage) + return -EINVAL; - bpage->order = buffer->subbuf_order; + order = READ_ONCE(buffer->subbuf_order); + + if (*rpage) { + if ((*rpage)->order == order) + return 0; + + /* We can reuse rpage, but we discard the payload */ + free_pages((unsigned long)(*rpage)->data, (*rpage)->order); + (*rpage)->data = NULL; + } else { + *rpage = kzalloc_obj(**rpage); + if (!*rpage) + return -ENOMEM; + } + + (*rpage)->order = order; cpu_buffer = buffer->buffers[cpu]; + local_irq_save(flags); arch_spin_lock(&cpu_buffer->lock); if (cpu_buffer->free_page.data) { - *bpage = cpu_buffer->free_page; + **rpage = cpu_buffer->free_page; cpu_buffer->free_page.data = NULL; } arch_spin_unlock(&cpu_buffer->lock); local_irq_restore(flags); - if (bpage->data) { - rb_init_data_page(bpage->data); + if ((*rpage)->data) { + rb_init_data_page((*rpage)->data); } else { - bpage->data = alloc_cpu_data(cpu, bpage->order); - if (!bpage->data) { - kfree(bpage); - return ERR_PTR(-ENOMEM); + (*rpage)->data = alloc_cpu_data(cpu, (*rpage)->order); + if (!(*rpage)->data) { + kfree(*rpage); + *rpage = NULL; + return -ENOMEM; } } - return bpage; + return 0; } EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page); @@ -7055,21 +7082,30 @@ EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page); * ring_buffer_free_read_page - free an allocated read page * @buffer: the buffer the page was allocate for * @cpu: the cpu buffer the page came from - * @data_page: the page to free + * @rpage: the buffer_data_read_page to free * * Free a page allocated from ring_buffer_alloc_read_page. */ void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, - struct buffer_data_read_page *data_page) + struct buffer_data_read_page *rpage) { struct ring_buffer_per_cpu *cpu_buffer; - struct buffer_data_page *dpage = data_page->data; - struct page *page = virt_to_page(dpage); + struct buffer_data_page *dpage; unsigned long flags; + struct page *page; if (!buffer || !buffer->buffers || !buffer->buffers[cpu]) return; + if (!rpage) + return; + + dpage = rpage->data; + if (!dpage) + goto out; + + page = virt_to_page(dpage); + cpu_buffer = buffer->buffers[cpu]; /* @@ -7077,14 +7113,14 @@ void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, * is different from the subbuffer order of the buffer - * we can't reuse it */ - if (page_ref_count(page) > 1 || data_page->order != buffer->subbuf_order) + if (page_ref_count(page) > 1 || rpage->order != READ_ONCE(buffer->subbuf_order)) goto out; local_irq_save(flags); arch_spin_lock(&cpu_buffer->lock); if (!cpu_buffer->free_page.data) { - cpu_buffer->free_page = *data_page; + cpu_buffer->free_page = *rpage; dpage = NULL; } @@ -7092,8 +7128,8 @@ void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, local_irq_restore(flags); out: - free_pages((unsigned long)dpage, data_page->order); - kfree(data_page); + free_pages((unsigned long)dpage, rpage->order); + kfree(rpage); } EXPORT_SYMBOL_GPL(ring_buffer_free_read_page); @@ -7164,10 +7200,9 @@ int ring_buffer_read_page(struct trace_buffer *buffer, if (!dpage) return -1; - guard(raw_spinlock_irqsave)(&cpu_buffer->reader_lock); + len = min_t(size_t, len, rb_read_page_capacity(data_page)); - if (data_page->order != cpu_buffer->reader_page->order) - return -1; + guard(raw_spinlock_irqsave)(&cpu_buffer->reader_lock); reader = rb_get_reader_page(cpu_buffer); if (!reader) @@ -7182,16 +7217,18 @@ int ring_buffer_read_page(struct trace_buffer *buffer, /* Check if any events were dropped */ missed_events = cpu_buffer->lost_events; - /* - * If this page has been partially read or - * if len is not big enough to read the rest of the page or - * a writer is still on the page, then - * we must copy the data from the page to the buffer. - * Otherwise, we can simply swap the page with the one passed in. - */ + /* + * It is not possible to swap the reader page if: + * - It has been partially read + * - len is not big enough to read it entirely + * - A writer is still on it + * - The ring buffer is static + * - The order doesn't match + */ if (read || (len < (size - read)) || cpu_buffer->reader_page == cpu_buffer->commit_page || - rb_is_static(cpu_buffer)) { + rb_is_static(cpu_buffer) || + data_page->order != reader->order) { struct buffer_data_page *rpage = cpu_buffer->reader_page->page; unsigned int rpos = read; unsigned int pos = 0; @@ -7285,7 +7322,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer, * missed events, then record it there. */ if (missed_events > 0 && - rb_page_capacity(reader) - size >= sizeof(missed_events)) { + rb_read_page_capacity(data_page) - size >= sizeof(missed_events)) { memcpy(&dpage->data[size], &missed_events, sizeof(missed_events)); local_add(RB_MISSED_STORED, &dpage->commit); @@ -7305,8 +7342,8 @@ int ring_buffer_read_page(struct trace_buffer *buffer, /* * This page may be off to user land. Zero it out here. */ - if (size < rb_page_capacity(reader)) - memset(&dpage->data[size], 0, rb_page_capacity(reader) - size); + if (size < rb_read_page_capacity(data_page)) + memset(&dpage->data[size], 0, rb_read_page_capacity(data_page) - size); return read; } @@ -7324,6 +7361,18 @@ void *ring_buffer_read_page_data(struct buffer_data_read_page *page) } EXPORT_SYMBOL_GPL(ring_buffer_read_page_data); +/** + * ring_buffer_read_page_size - get size of the read page. + * @page: the page to get the size from + * + * Returns size of the page in bytes. + */ +unsigned int ring_buffer_read_page_size(struct buffer_data_read_page *rpage) +{ + return rpage ? PAGE_SIZE << rpage->order : 0; +} +EXPORT_SYMBOL_GPL(ring_buffer_read_page_size); + /** * ring_buffer_subbuf_size_get - get size of the sub buffer. * @buffer: the buffer to get the sub buffer size from @@ -7409,7 +7458,7 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order) /* Make sure all commits have finished */ synchronize_rcu(); - buffer->subbuf_order = order; + WRITE_ONCE(buffer->subbuf_order, order); /* Make sure all new buffers are allocated, before deleting the old ones */ for_each_buffer_cpu(buffer, cpu) { @@ -7513,7 +7562,7 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order) return 0; error: - buffer->subbuf_order = old_order; + WRITE_ONCE(buffer->subbuf_order, old_order); atomic_dec(&buffer->record_disabled); diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c index 593e3b59e42e..c3d34c0e64e2 100644 --- a/kernel/trace/ring_buffer_benchmark.c +++ b/kernel/trace/ring_buffer_benchmark.c @@ -104,7 +104,7 @@ static enum event_status read_event(int cpu) static enum event_status read_page(int cpu) { - struct buffer_data_read_page *bpage; + struct buffer_data_read_page *bpage = NULL; struct ring_buffer_event *event; struct rb_page *rpage; unsigned long commit; @@ -114,8 +114,8 @@ static enum event_status read_page(int cpu) int inc; int i; - bpage = ring_buffer_alloc_read_page(buffer, cpu); - if (IS_ERR(bpage)) + ret = ring_buffer_alloc_read_page(buffer, cpu, &bpage); + if (ret < 0) return EVENT_DROPPED; page_size = ring_buffer_subbuf_size_get(buffer); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 138e983c3c2f..b26c4c277ce5 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -7082,8 +7082,8 @@ ssize_t tracing_buffers_read(struct file *filp, char __user *ubuf, { struct ftrace_buffer_info *info = filp->private_data; struct trace_iterator *iter = &info->iter; + unsigned int spare_size; void *trace_data; - int page_size; ssize_t ret = 0; ssize_t size; @@ -7093,36 +7093,22 @@ ssize_t tracing_buffers_read(struct file *filp, char __user *ubuf, if (iter->snapshot && tracer_uses_snapshot(iter->tr->current_trace)) return -EBUSY; - page_size = ring_buffer_subbuf_size_get(iter->array_buffer->buffer); - - /* Make sure the spare matches the current sub buffer size */ - if (info->spare) { - if (page_size != info->spare_size) { - ring_buffer_free_read_page(iter->array_buffer->buffer, - info->spare_cpu, info->spare); - info->spare = NULL; - } - } - - if (!info->spare) { - info->spare = ring_buffer_alloc_read_page(iter->array_buffer->buffer, - iter->cpu_file); - if (IS_ERR(info->spare)) { - ret = PTR_ERR(info->spare); - info->spare = NULL; - } else { - info->spare_cpu = iter->cpu_file; - info->spare_size = page_size; - } - } - if (!info->spare) - return ret; + spare_size = ring_buffer_read_page_size(info->spare); +again: /* Do we have previous read data to read? */ - if (info->read < page_size) + if (info->read < spare_size) goto read; - again: + ret = ring_buffer_alloc_read_page(iter->array_buffer->buffer, iter->cpu_file, + &info->spare); + if (ret) + return ret; + + spare_size = ring_buffer_read_page_size(info->spare); + info->read = spare_size; + info->spare_cpu = iter->cpu_file; + trace_access_lock(iter->cpu_file); ret = ring_buffer_read_page(iter->array_buffer->buffer, info->spare, @@ -7148,8 +7134,9 @@ ssize_t tracing_buffers_read(struct file *filp, char __user *ubuf, } info->read = 0; + read: - size = page_size - info->read; + size = spare_size - info->read; if (size > count) size = count; trace_data = ring_buffer_read_page_data(info->spare); @@ -7190,26 +7177,24 @@ int tracing_buffers_release(struct inode *inode, struct file *file) __trace_array_put(iter->tr); - if (info->spare) - ring_buffer_free_read_page(iter->array_buffer->buffer, - info->spare_cpu, info->spare); + ring_buffer_free_read_page(iter->array_buffer->buffer, info->spare_cpu, info->spare); kvfree(info); return 0; } struct buffer_ref { - struct trace_buffer *buffer; - void *page; - int cpu; - refcount_t refcount; + struct trace_buffer *buffer; + struct buffer_data_read_page *rpage; + int cpu; + refcount_t refcount; }; static void buffer_ref_release(struct buffer_ref *ref) { if (!refcount_dec_and_test(&ref->refcount)) return; - ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page); + ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->rpage); kfree(ref); } @@ -7268,25 +7253,15 @@ ssize_t tracing_buffers_splice_read(struct file *file, loff_t *ppos, .ops = &buffer_pipe_buf_ops, .spd_release = buffer_spd_release, }; + unsigned int page_size = 0; struct buffer_ref *ref; bool woken = false; - int page_size; int entries, i; ssize_t ret = 0; if (iter->snapshot && tracer_uses_snapshot(iter->tr->current_trace)) return -EBUSY; - page_size = ring_buffer_subbuf_size_get(iter->array_buffer->buffer); - if (*ppos & (page_size - 1)) - return -EINVAL; - - if (len & (page_size - 1)) { - if (len < page_size) - return -EINVAL; - len &= (~(page_size - 1)); - } - if (splice_grow_spd(pipe, &spd)) return -ENOMEM; @@ -7306,25 +7281,37 @@ ssize_t tracing_buffers_splice_read(struct file *file, loff_t *ppos, refcount_set(&ref->refcount, 1); ref->buffer = iter->array_buffer->buffer; - ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file); - if (IS_ERR(ref->page)) { - ret = PTR_ERR(ref->page); - ref->page = NULL; + + ret = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file, &ref->rpage); + if (ret) { kfree(ref); break; } ref->cpu = iter->cpu_file; - r = ring_buffer_read_page(ref->buffer, ref->page, - len, iter->cpu_file, 1); + page_size = ring_buffer_read_page_size(ref->rpage); + + r = -EINVAL; + if (IS_ALIGNED(*ppos, page_size) && len >= page_size) { + r = ring_buffer_read_page(ref->buffer, ref->rpage, len, iter->cpu_file, 1); + } else if (!i) { + /* + * We failed to read because the length is too small + * or unaligned. If this is the first iteration, it's + * an invalid userspace input. Otherwise, this is due + * to a subbuf order change. Do not report an error + * and just finish the read. + */ + ret = -EINVAL; + } + if (r < 0) { - ring_buffer_free_read_page(ref->buffer, ref->cpu, - ref->page); + ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->rpage); kfree(ref); break; } - page = virt_to_page(ring_buffer_read_page_data(ref->page)); + page = virt_to_page(ring_buffer_read_page_data(ref->rpage)); spd.pages[i] = page; spd.partial[i].len = page_size; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 3c111ca88e32..5e76f94e7a80 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -745,11 +745,10 @@ static inline int tracing_get_cpu(struct inode *inode) void tracing_reset_cpu(struct array_buffer *buf, int cpu); struct ftrace_buffer_info { - struct trace_iterator iter; - void *spare; - unsigned int spare_cpu; - unsigned int spare_size; - unsigned int read; + struct trace_iterator iter; + struct buffer_data_read_page *spare; + unsigned int spare_cpu; + unsigned int read; }; /** From f2b2b645595c82b4e824880f6cb987e077a8da19 Mon Sep 17 00:00:00 2001 From: Vincent Donnefort Date: Fri, 4 Sep 2026 17:44:49 +0100 Subject: [PATCH 0692/1198] ring-buffer: Cap static ring buffer nr_pages Static ring buffers (i.e. persistent, user-mapped and remote) rely on the bpage::id field. The number of pages for those ring buffers must fit into that variable. Enforce this limit on ring buffer creation or user-mapping. While at it, prevent nr_pages underflow when allocating a persistent buffer. Link: https://patch.msgid.link/20260904164450.1345852-4-vdonnefort@google.com Fixes: be68d63a139b ("ring-buffer: Add ring_buffer_alloc_range()") Signed-off-by: Vincent Donnefort Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 077d6940af0c..76fed01f1c49 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -657,6 +657,15 @@ static bool rb_is_static(struct ring_buffer_per_cpu *cpu_buffer) return cpu_buffer->user_mapped || cpu_buffer->remote || cpu_buffer->ring_meta; } +static unsigned long rb_static_max_pages(void) +{ + /* + * Static ring buffers are using bpage::id and must account for the + * reader page. + */ + return (1UL << 30) - 1; +} + struct ring_buffer_iter { struct ring_buffer_per_cpu *cpu_buffer; unsigned long head; @@ -2838,6 +2847,8 @@ static struct trace_buffer *alloc_buffer(unsigned long size, unsigned flags, size = end - buffers_start; size = size / nr_cpu_ids; + if (size < sizeof(struct ring_buffer_cpu_meta)) + goto fail_free_buffers; /* * The number of sub-buffers (nr_pages) is determined by the * total size allocated minus the meta data size. @@ -2847,6 +2858,10 @@ static struct trace_buffer *alloc_buffer(unsigned long size, unsigned flags, */ nr_pages = (size - sizeof(struct ring_buffer_cpu_meta)) / (subbuf_size + sizeof(int)); + + if (nr_pages > rb_static_max_pages()) + goto fail_free_buffers; + /* Need at least two pages plus the reader page */ if (nr_pages < 3) goto fail_free_buffers; @@ -2879,6 +2894,10 @@ static struct trace_buffer *alloc_buffer(unsigned long size, unsigned flags, /* The writer is remote. This ring-buffer is read-only */ atomic_inc(&buffer->record_disabled); nr_pages = desc->nr_page_va - 1; + + if (nr_pages > rb_static_max_pages()) + goto fail_free_buffers; + if (nr_pages < 2) goto fail_free_buffers; } else { @@ -7841,6 +7860,9 @@ int ring_buffer_map(struct trace_buffer *buffer, int cpu, /* prevent another thread from changing buffer/sub-buffer sizes */ guard(mutex)(&buffer->mutex); + if (cpu_buffer->nr_pages > rb_static_max_pages()) + return -E2BIG; + err = rb_alloc_meta_page(cpu_buffer); if (err) return err; From c843fd3c73c94cb90b01c6bfe8d83796e652864d Mon Sep 17 00:00:00 2001 From: Vincent Donnefort Date: Fri, 4 Sep 2026 17:44:50 +0100 Subject: [PATCH 0693/1198] ring-buffer: Prevent truncation of nr_pages / nr_subbufs Although ring_buffer_per_cpu::nr_pages is defined as unsigned long, it is capped to 32-bits in a few places, limiting the operations possible on a very large buffer. Use `unsigned long` where appropriate and prevent truncation of values using nr_pages (or nr_subbufs). While at it, subbuf_size must be at least `unsigned int`. Note that persistent, remote and user-mapped ring buffers are capping the number of pages to 30 bits already, making "int" safe in many places. Link: https://patch.msgid.link/20260904164450.1345852-5-vdonnefort@google.com Signed-off-by: Vincent Donnefort Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 61 +++++++++++++++++++------------------- 1 file changed, 30 insertions(+), 31 deletions(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 76fed01f1c49..220b8405adfc 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1683,7 +1683,7 @@ static void rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer) * This is used to help find the next per cpu subbuffer within a mapped range. */ static unsigned long -rb_range_align_subbuf(unsigned long addr, int subbuf_size, int nr_subbufs) +rb_range_align_subbuf(unsigned long addr, unsigned int subbuf_size, unsigned long nr_subbufs) { addr += sizeof(struct ring_buffer_cpu_meta) + sizeof(int) * nr_subbufs; @@ -1693,13 +1693,12 @@ rb_range_align_subbuf(unsigned long addr, int subbuf_size, int nr_subbufs) /* * Return the ring_buffer_meta for a given @cpu. */ -static void *rb_range_meta(struct trace_buffer *buffer, int nr_pages, int cpu) +static void *rb_range_meta(struct trace_buffer *buffer, unsigned long nr_pages, int cpu) { - int subbuf_size = rb_subbuf_size(buffer); + unsigned int subbuf_size = rb_subbuf_size(buffer); struct ring_buffer_cpu_meta *meta; struct ring_buffer_meta *bmeta; - unsigned long ptr; - int nr_subbufs; + unsigned long ptr, nr_subbufs; bmeta = buffer->meta; if (!bmeta) @@ -1745,7 +1744,7 @@ static void *rb_range_meta(struct trace_buffer *buffer, int nr_pages, int cpu) /* Return the start of subbufs given the meta pointer */ static void *rb_subbufs_from_meta(struct ring_buffer_cpu_meta *meta) { - int subbuf_size = meta->subbuf_size; + unsigned int subbuf_size = meta->subbuf_size; unsigned long ptr; ptr = (unsigned long)meta; @@ -1757,11 +1756,11 @@ static void *rb_subbufs_from_meta(struct ring_buffer_cpu_meta *meta) /* * Return a specific sub-buffer for a given @cpu defined by @idx. */ -static void *rb_range_buffer(struct ring_buffer_per_cpu *cpu_buffer, int idx) +static void *rb_range_buffer(struct ring_buffer_per_cpu *cpu_buffer, unsigned long idx) { struct ring_buffer_cpu_meta *meta; + unsigned int subbuf_size; unsigned long ptr; - int subbuf_size; meta = rb_range_meta(cpu_buffer->buffer, 0, cpu_buffer->cpu); if (!meta) @@ -1777,7 +1776,7 @@ static void *rb_range_buffer(struct ring_buffer_per_cpu *cpu_buffer, int idx) ptr = (unsigned long)rb_subbufs_from_meta(meta); - ptr += subbuf_size * idx; + ptr += (unsigned long)subbuf_size * idx; if (ptr + subbuf_size > cpu_buffer->buffer->range_addr_end) return NULL; @@ -1854,13 +1853,12 @@ static bool rb_meta_init(struct trace_buffer *buffer, int scratch_size) * must be the same. */ static bool rb_cpu_meta_valid(struct ring_buffer_cpu_meta *meta, int cpu, - struct trace_buffer *buffer, int nr_pages, + struct trace_buffer *buffer, unsigned long nr_pages, unsigned long *subbuf_mask) { - int subbuf_size = PAGE_SIZE; unsigned long buffers_start; unsigned long buffers_end; - int i; + unsigned long i; if (!subbuf_mask) return false; @@ -1876,7 +1874,7 @@ static bool rb_cpu_meta_valid(struct ring_buffer_cpu_meta *meta, int cpu, } buffers_start = meta->first_buffer; - buffers_end = meta->first_buffer + (subbuf_size * meta->nr_subbufs); + buffers_end = meta->first_buffer + (meta->nr_subbufs * PAGE_SIZE); /* Is the head and commit buffers within the range of buffers? */ if (meta->head_buffer < buffers_start || @@ -2114,8 +2112,8 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer) struct buffer_page *head_page, *orig_head, *orig_reader; struct rb_validation_state state = { 0 }; bool skip = false; + unsigned long i; int ret; - int i; if (!meta || !meta->head_buffer) return; @@ -2166,7 +2164,7 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer) rb_validate_buffer(head_page, cpu_buffer, meta, &state, 0, state.ts); } if (i) - pr_info("Ring buffer [%d] rewound %d pages\n", cpu_buffer->cpu, i); + pr_info("Ring buffer [%d] rewound %lu pages\n", cpu_buffer->cpu, i); /* The last rewound page must be skipped. */ if (head_page != orig_head) @@ -2250,7 +2248,8 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer) } } -static void rb_range_meta_init(struct trace_buffer *buffer, int nr_pages, int scratch_size) +static void rb_range_meta_init(struct trace_buffer *buffer, unsigned long nr_pages, + int scratch_size) { struct ring_buffer_cpu_meta *meta; unsigned long *subbuf_mask; @@ -2350,8 +2349,8 @@ static int rbm_show(struct seq_file *m, void *v) rb_meta_subbuf_idx(meta, (void *)meta->head_buffer)); seq_printf(m, "commit_buffer: %d\n", rb_meta_subbuf_idx(meta, (void *)meta->commit_buffer)); - seq_printf(m, "subbuf_size: %d\n", meta->subbuf_size); - seq_printf(m, "nr_subbufs: %d\n", meta->nr_subbufs); + seq_printf(m, "subbuf_size: %u\n", meta->subbuf_size); + seq_printf(m, "nr_subbufs: %u\n", meta->nr_subbufs); return 0; } @@ -2436,7 +2435,7 @@ static void *ring_buffer_desc_page(struct ring_buffer_desc *desc, unsigned int p } static int __rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, - long nr_pages, struct list_head *pages) + unsigned long nr_pages, struct list_head *pages) { struct trace_buffer *buffer = cpu_buffer->buffer; struct ring_buffer_cpu_meta *meta = NULL; @@ -2564,7 +2563,7 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, } static struct ring_buffer_per_cpu * -rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu) +rb_allocate_cpu_buffer(struct trace_buffer *buffer, unsigned long nr_pages, int cpu) { struct ring_buffer_per_cpu *cpu_buffer __free(kfree) = alloc_cpu_buffer(cpu); @@ -2721,8 +2720,8 @@ static void rb_test_inject_invalid_pages(struct trace_buffer *buffer) struct ring_buffer_cpu_meta *meta; struct buffer_data_page *dpage; unsigned long entry_bytes = 0; + unsigned int subbuf_size; unsigned long ptr; - int subbuf_size; int invalid = 0; int cpu; int i; @@ -2792,8 +2791,8 @@ static struct trace_buffer *alloc_buffer(unsigned long size, unsigned flags, struct ring_buffer_remote *remote) { struct trace_buffer *buffer __free(kfree) = NULL; - long nr_pages; - int subbuf_size; + unsigned int subbuf_size; + unsigned long nr_pages; int bsize; int cpu; int ret; @@ -5882,12 +5881,12 @@ __rb_get_reader_page_from_remote(struct ring_buffer_per_cpu *cpu_buffer) static struct buffer_page * __rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) { - int max_loops = cpu_buffer->ring_meta ? cpu_buffer->nr_pages : 3; + unsigned long max_loops = cpu_buffer->ring_meta ? cpu_buffer->nr_pages : 3; struct buffer_page *reader = NULL; + unsigned long nr_loops = 0; unsigned long overwrite; unsigned long flags; int missed_events = 0; - int nr_loops = 0; bool ret; local_irq_save(flags); @@ -6205,8 +6204,8 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) struct trace_buffer *buffer; struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_event *event; - int nr_loops = 0; - int max_loops; + unsigned long nr_loops = 0; + unsigned long max_loops; if (ts) *ts = 0; @@ -7446,8 +7445,8 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order) struct ring_buffer_per_cpu *cpu_buffer; struct buffer_page *bpage, *tmp; unsigned int old_capacity; + unsigned long nr_pages; int old_order; - int nr_pages; int psize; int err; int cpu; @@ -7629,10 +7628,10 @@ static void rb_setup_ids_meta_page(struct ring_buffer_per_cpu *cpu_buffer, struct buffer_page **subbuf_ids) { struct trace_buffer_meta *meta = cpu_buffer->meta_page; - unsigned int nr_subbufs = cpu_buffer->nr_pages + 1; + unsigned long nr_subbufs = cpu_buffer->nr_pages + 1; struct buffer_page *first_subbuf, *subbuf; - int cnt = 0; - int id = 0; + unsigned int cnt = 0; + unsigned int id = 0; id = rb_page_id(cpu_buffer, cpu_buffer->reader_page, id); subbuf_ids[id++] = cpu_buffer->reader_page; From 5cbea500775dd1944995f23320af030b9b24b24b Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 4 Sep 2026 14:49:02 -0400 Subject: [PATCH 0694/1198] tracing: Fix comment in tracing_buffers_splice_read() The comment about returning an error if the read fails on the first iteration is slightly incorrect. It makes it sound like the only reason it could fail on a later iteration is if the subbuf order changed. That is incorrect, it could also fail if the length passed in was not a multiple of the subbuf size. Fix the comment. Link: https://lore.kernel.org/all/20260904143527.40e73d36@gandalf.local.home/ Link: https://patch.msgid.link/20260904144902.506862a1@gandalf.local.home Fixes: dae8dda341d2 ("tracing: Fix subbuf resize races with trace_pipe_raw readers") Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index b26c4c277ce5..8658cad53cb5 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -7296,11 +7296,13 @@ ssize_t tracing_buffers_splice_read(struct file *file, loff_t *ppos, r = ring_buffer_read_page(ref->buffer, ref->rpage, len, iter->cpu_file, 1); } else if (!i) { /* - * We failed to read because the length is too small - * or unaligned. If this is the first iteration, it's - * an invalid userspace input. Otherwise, this is due - * to a subbuf order change. Do not report an error - * and just finish the read. + * If this fails to read on the first iteration, it + * means the length was too small and an error should + * be returned to user space. Otherwise, at least + * one sub-buffer was successfully read but this failed + * due to either the length was unaligned or the + * subbuf order changed. Either case, do not report + * an error. */ ret = -EINVAL; } From d80e12156f1fd490adf29a8d28489725a3ac817a Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 4 Sep 2026 15:16:41 -0400 Subject: [PATCH 0695/1198] ring-buffer: Use a macro for static buffer bits Instead of hard coding 30 for the number of bits used for the static buffer ids in two places, create a macro. This way if it changes in the future, it will change in all the locations that use it. Link: https://patch.msgid.link/20260904151641.17eae0aa@gandalf.local.home Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 220b8405adfc..b88c75b52e8f 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -335,6 +335,9 @@ static __always_inline unsigned int rb_read_page_capacity(struct buffer_data_rea return (PAGE_SIZE << rpage->order) - BUF_PAGE_HDR_SIZE; } +/* The number of bits for static buffer ids */ +#define RB_STATIC_BITS 30 + /* * Note, the buffer_page list must be first. The buffer pages * are allocated in cache lines, which means that each buffer @@ -350,7 +353,7 @@ struct buffer_page { local_t entries; /* entries on this page */ unsigned long real_end; /* real end of data */ unsigned order; /* order of the page */ - u32 id:30; /* ID for external mapping */ + u32 id:RB_STATIC_BITS; /* ID for external mapping */ u32 range:1; /* Mapped via a range */ struct buffer_data_page *page; /* Actual data page */ }; @@ -663,7 +666,7 @@ static unsigned long rb_static_max_pages(void) * Static ring buffers are using bpage::id and must account for the * reader page. */ - return (1UL << 30) - 1; + return (1UL << RB_STATIC_BITS) - 1; } struct ring_buffer_iter { From 5bd9e4e7cdaa03879e9b73b12ab52cceb1edd55b Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 3 Sep 2026 11:02:59 +0300 Subject: [PATCH 0696/1198] nexthop: Initialize extack in remove_nh_grp_entry() remove_nh_grp_entry() prints the extack message when a listener fails to replace the reduced nexthop group. However, extack is not initialized and listeners are not required to set a message when returning an error. Neither netdevsim nor mlxsw do so when an allocation fails, resulting in the dereference of an uninitialized stack pointer. Fix by zero-initializing extack, as was done in commit 6347c5314cee ("nexthop: initialize extack in nh_res_bucket_migrate()"). Fixes: 833a1065eeb1 ("nexthop: Emit a notification when a nexthop group is reduced") Signed-off-by: Ido Schimmel Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20260903080259.10378-1-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- net/ipv4/nexthop.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index a7c2b8dced4e..42e55b5a755e 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -2036,7 +2036,7 @@ remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, { struct nh_grp_entry *nhges, *new_nhges; struct nexthop *nhp = nhge->nh_parent; - struct netlink_ext_ack extack; + struct netlink_ext_ack extack = {}; struct nexthop *nh = nhge->nh; struct nh_group *nhg, *newg; int i, j, err; From 1746ef2e2df2ad71c66eca56364d56bde284523b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 3 Sep 2026 14:39:40 +0000 Subject: [PATCH 0697/1198] bonding: use skb_cow_head() in bond_do_alb_xmit() and rlb_arp_xmit() In bond_do_alb_xmit() and rlb_arp_xmit(), make sure to unclone skb head via skb_cow_head() before modifying the source MAC address (Ethernet header and ARP payload) to avoid silent corruption if the skb is shared or cloned. Avoid caching the header pointers across skb_cow_head(). In rlb_arp_xmit(), only modify arp->mac_src if it differs from tx_slave->dev->dev_addr to avoid an unnecessary copy and head reallocation. Also, we should not assume mac header is set in output path. Use skb_eth_hdr() instead of eth_hdr() to fix the issue, and remove now redundant skb_reset_mac_header() calls. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Reviewed-by: Hangbin Liu Cc: Jay Vosburgh Reviewed-by: Nikolay Aleksandrov Link: https://patch.msgid.link/20260903143940.1180513-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- drivers/net/bonding/bond_alb.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 654f051d0023..43ac8e28e418 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -678,9 +678,15 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond) if (arp->op_code == htons(ARPOP_REPLY)) { /* the arp must be sent on the selected rx channel */ tx_slave = rlb_choose_channel(skb, bond, arp); - if (tx_slave) + if (tx_slave && + !ether_addr_equal_64bits(arp->mac_src, + tx_slave->dev->dev_addr)) { + if (unlikely(skb_cow_head(skb, 0))) + return NULL; + arp = (struct arp_pkt *)skb_network_header(skb); bond_hw_addr_copy(arp->mac_src, tx_slave->dev->dev_addr, tx_slave->dev->addr_len); + } netdev_dbg(bond->dev, "(slave %s): Server sent ARP Reply packet\n", tx_slave ? tx_slave->dev->name : "NULL"); } else if (arp->op_code == htons(ARPOP_REQUEST)) { @@ -1340,7 +1346,6 @@ static netdev_tx_t bond_do_alb_xmit(struct sk_buff *skb, struct bonding *bond, struct slave *tx_slave) { struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); - struct ethhdr *eth_data = eth_hdr(skb); if (!tx_slave) { /* unbalanced or unassigned, send through primary */ @@ -1351,7 +1356,9 @@ static netdev_tx_t bond_do_alb_xmit(struct sk_buff *skb, struct bonding *bond, if (tx_slave && bond_slave_can_tx(tx_slave)) { if (tx_slave != rcu_access_pointer(bond->curr_active_slave)) { - ether_addr_copy(eth_data->h_source, + if (unlikely(skb_cow_head(skb, 0))) + return bond_tx_drop(bond->dev, skb); + ether_addr_copy(skb_eth_hdr(skb)->h_source, tx_slave->dev->dev_addr); } @@ -1375,8 +1382,7 @@ struct slave *bond_xmit_tlb_slave_get(struct bonding *bond, struct ethhdr *eth_data; u32 hash_index; - skb_reset_mac_header(skb); - eth_data = eth_hdr(skb); + eth_data = skb_eth_hdr(skb); /* Do not TX balance any multicast or broadcast */ if (!is_multicast_ether_addr(eth_data->h_dest)) { @@ -1428,8 +1434,7 @@ struct slave *bond_xmit_alb_slave_get(struct bonding *bond, u32 hash_index = 0; int hash_size = 0; - skb_reset_mac_header(skb); - eth_data = eth_hdr(skb); + eth_data = skb_eth_hdr(skb); switch (ntohs(skb->protocol)) { case ETH_P_IP: { From cdb719f4b8596d9ccee2d56d204c2c4dce982f46 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 2 Sep 2026 20:26:07 -0700 Subject: [PATCH 0698/1198] net: dsa: bcm_sf2: bound the CFP rule dump by the caller's buffer size bcm_sf2_cfp_rule_get_all() walks the whole cfp.unique bitmap into rule_locs[] without consulting nfc->rule_cnt, which is how many entries the caller had room for. ETHTOOL_GRXCLSRLALL requires no CAP_NET_ADMIN and the ioctl sizes the buffer from the rule_cnt userspace passes in, so once an admin has installed CFP rules any user can ask for fewer slots than there are rules and run off the end of the allocation. A rule_cnt of 0 leaves the buffer pointer NULL and the walk dereferences it. Fixes: 7318166cacad ("net: dsa: bcm_sf2: Add support for ethtool::rxnfc") Reviewed-by: Jonas Gorski Reviewed-by: Florian Fainelli Reviewed-by: Joe Damato Link: https://patch.msgid.link/20260903032611.3000029-2-kuba@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/dsa/bcm_sf2_cfp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c index 50d3a818eb1b..84a086c3e99b 100644 --- a/drivers/net/dsa/bcm_sf2_cfp.c +++ b/drivers/net/dsa/bcm_sf2_cfp.c @@ -1088,6 +1088,8 @@ static int bcm_sf2_cfp_rule_get_all(struct bcm_sf2_priv *priv, unsigned int index = 1, rules_cnt = 0; for_each_set_bit_from(index, priv->cfp.unique, priv->num_cfp_rules) { + if (rules_cnt == nfc->rule_cnt) + return -EMSGSIZE; rule_locs[rules_cnt] = index; rules_cnt++; } From f1986bf87b0709c95126fe196cf39e5b8c8453a1 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 2 Sep 2026 20:26:08 -0700 Subject: [PATCH 0699/1198] eth: nfp: bound the ntuple rule dump by the caller's buffer size nfp_net_get_fs_loc() dumps every entry of nn->fs.list into rule_locs[] without consulting cmd->rule_cnt, which is how many entries the caller had room for. ETHTOOL_GRXCLSRLALL requires no CAP_NET_ADMIN and the ioctl sizes the buffer from the rule_cnt userspace passes in, so once an admin has installed flow steering rules any user can ask for fewer slots than there are rules and run off the end of the allocation. A rule_cnt of 0 leaves the buffer pointer NULL and the walk dereferences it. Bail out with -EMSGSIZE when the buffer fills up, the way the other ntuple capable drivers do, and report how many locations were filled so a shrinking rule list does not leave the caller reading stale slots. Reported-by: VEGA Fixes: 9eb03bb1c035 ("nfp: add ethtool flow steering callbacks") Reviewed-by: Joe Damato Link: https://patch.msgid.link/20260903032611.3000029-3-kuba@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index a2a89d48e3ca..9419e1ed8466 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -1421,7 +1421,8 @@ static int nfp_net_get_fs_rule(struct nfp_net *nn, struct ethtool_rxnfc *cmd) return -ENOENT; } -static int nfp_net_get_fs_loc(struct nfp_net *nn, u32 *rule_locs) +static int nfp_net_get_fs_loc(struct nfp_net *nn, struct ethtool_rxnfc *cmd, + u32 *rule_locs) { struct nfp_fs_entry *entry; u32 count = 0; @@ -1429,8 +1430,12 @@ static int nfp_net_get_fs_loc(struct nfp_net *nn, u32 *rule_locs) if (!(nn->cap_w1 & NFP_NET_CFG_CTRL_FLOW_STEER)) return -EOPNOTSUPP; - list_for_each_entry(entry, &nn->fs.list, node) + list_for_each_entry(entry, &nn->fs.list, node) { + if (count == cmd->rule_cnt) + return -EMSGSIZE; rule_locs[count++] = entry->loc; + } + cmd->rule_cnt = count; return 0; } @@ -1455,7 +1460,7 @@ static int nfp_net_get_rxnfc(struct net_device *netdev, return nfp_net_get_fs_rule(nn, cmd); case ETHTOOL_GRXCLSRLALL: cmd->data = NFP_FS_MAX_ENTRY; - return nfp_net_get_fs_loc(nn, rule_locs); + return nfp_net_get_fs_loc(nn, cmd, rule_locs); default: return -EOPNOTSUPP; } From 108bb2142e3a12c9ad625ad662973127a113ddc6 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 2 Sep 2026 20:26:09 -0700 Subject: [PATCH 0700/1198] eth: nfp: drop the replaced rule from the list when reprogramming fails nfp_net_fs_add() replaces an existing rule by deleting it from the hardware, decrementing nn->fs.count and programming the new one. If nfp_net_fs_add_hw() fails the old entry stays on nn->fs.list - only the success path reaches list_replace() - so the list is one longer than nn->fs.count, and it advertises a rule whose hardware entry has already been torn down. nn->fs.count is what ETHTOOL_GRXCLSRLCNT reports, so userspace then sizes its buffer one entry short of what the GRXCLSRLALL walk wants to write. That used to overwrite one u32 past the allocation; since the walk is bounded it is a permanent -EMSGSIZE instead, as nothing ever resyncs the counter. Fixes: 9eb03bb1c035 ("nfp: add ethtool flow steering callbacks") Reviewed-by: Joe Damato Link: https://patch.msgid.link/20260903032611.3000029-4-kuba@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index 9419e1ed8466..4e83637715e0 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -1703,8 +1703,14 @@ static int nfp_net_fs_add(struct nfp_net *nn, struct ethtool_rxnfc *cmd) nn->fs.count--; err = nfp_net_fs_add_hw(nn, new); - if (err) + if (err) { + /* mbox broken, adding the old rule back will + * likely also fail. + */ + list_del(&entry->node); + kfree(entry); goto err; + } nn->fs.count++; list_replace(&entry->node, &new->node); From b1fffc273112e7284c5b705e186b43b5770cd3d5 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 2 Sep 2026 20:26:10 -0700 Subject: [PATCH 0701/1198] net: dsa: mv88e6xxx: bound the policy rule dump by the caller's buffer size mv88e6xxx_get_rxnfc() uses rxnfc->rule_cnt as the write index while dumping the policy IDR, clobbering the input value before it has been looked at. That input is the number of entries the caller had room for. ETHTOOL_GRXCLSRLALL requires no CAP_NET_ADMIN and the ioctl sizes the buffer from the rule_cnt userspace passes in, so once an admin has installed policy rules any user can ask for fewer slots than there are rules and run off the end of the allocation. A rule_cnt of 0 leaves the buffer pointer NULL and the walk dereferences it. Count into a local so the caller's limit survives the walk, and stop with -EMSGSIZE once it is reached. Fixes: da7dc8755304 ("net: dsa: mv88e6xxx: add RXNFC support") Reviewed-by: Joe Damato Link: https://patch.msgid.link/20260903032611.3000029-5-kuba@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/dsa/mv88e6xxx/chip.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 80b877c74513..7f68a0c55802 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2438,6 +2438,7 @@ static int mv88e6xxx_get_rxnfc(struct dsa_switch *ds, int port, struct ethtool_rx_flow_spec *fs = &rxnfc->fs; struct mv88e6xxx_chip *chip = ds->priv; struct mv88e6xxx_policy *policy; + u32 cnt = 0; int err; int id; @@ -2463,11 +2464,18 @@ static int mv88e6xxx_get_rxnfc(struct dsa_switch *ds, int port, break; case ETHTOOL_GRXCLSRLALL: rxnfc->data = 0; - rxnfc->rule_cnt = 0; - idr_for_each_entry(&chip->policies, policy, id) - if (policy->port == port) - rule_locs[rxnfc->rule_cnt++] = id; err = 0; + idr_for_each_entry(&chip->policies, policy, id) { + if (policy->port != port) + continue; + if (cnt == rxnfc->rule_cnt) { + err = -EMSGSIZE; + break; + } + rule_locs[cnt++] = id; + } + if (!err) + rxnfc->rule_cnt = cnt; break; default: err = -EOPNOTSUPP; From 47a582b2b0e7bb5753e4803988e150a405b57f51 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 2 Sep 2026 20:26:11 -0700 Subject: [PATCH 0702/1198] ethtool: document that GRXCLSRLALL rule_cnt is a caller-provided limit Three drivers have shipped a get_rxnfc() which dumps its entire rule table into rule_locs, reading rule_cnt as "how many rules do I have" rather than "how many entries did the caller allocate". Nothing in the callback's documentation contradicted that reading. The distinction only matters because the ioctl lets an unprivileged caller pick rule_cnt directly, so getting it wrong is a heap overflow rather than a truncated dump. Reviewed-by: Joe Damato Link: https://patch.msgid.link/20260903032611.3000029-6-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/ethtool.h | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 12683b5d125e..253600c0eccd 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -1057,6 +1057,12 @@ struct kernel_ethtool_ts_info { * @get_sset_count: Get number of strings that @get_strings will write. * @get_rxnfc: Get RX flow classification rules. Returns a negative * error code or zero. + * Note that for %ETHTOOL_GRXCLSRLALL rule_cnt and size of the arrays + * is user-provided, and not guaranteed to match what driver would + * have reported via %ETHTOOL_GRXCLSRLCNT. Drivers must return -%EMSGSIZE + * when rule_cnt is too small. rule_locs is %NULL when rule_cnt is zero. + * On success drivers must set rule_cnt to the number of locations they + * filled in, the core copies out exactly that many. * @set_rxnfc: Set RX flow classification rules. Returns a negative * error code or zero. * @flash_device: Write a firmware image to device's flash memory. From 4b772869a1e5f9da5cef5b9c722ec0aa424ee0a0 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Thu, 3 Sep 2026 12:38:51 +0300 Subject: [PATCH 0703/1198] net: bridge: mcast: properly convert mglist to rcu Sashiko reported a bug [1] that br_multicast_del_port_group unlists the port group not using proper rcu helper that preserves the next pointer and after that immediately frees the port group without waiting for rcu grace period. The only rcu walker of mglist is br_multicast_list_adjacent() and it turns out that function has always been buggy because mglist was never properly converted to RCU. Fix it by converting it to rcu and moving its initialization after eth_addr's. Initializing p->next can use RCU_INIT_POINTER because we have a barrier from the hlist_add_head_rcu call later, besides we're initializing an unpublished structure anyway. [1] https://netdev-ai.bots.linux.dev/sashiko/#/patchset/20260826014200.362304-1-littleddfu%40gmail.com Fixes: 07f8ac4a1e26 ("bridge: add export of multicast database adjacent to net_dev") Signed-off-by: Nikolay Aleksandrov Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/20260903093851.1494297-1-razor@blackwall.org Signed-off-by: Jakub Kicinski --- net/bridge/br_multicast.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 3e9b10f8abf1..2f9bb30e1a1f 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1441,16 +1441,17 @@ struct net_bridge_port_group *br_multicast_new_port_group( goto free_out; } - rcu_assign_pointer(p->next, next); timer_setup(&p->timer, br_multicast_port_group_expired, 0); timer_setup(&p->rexmit_timer, br_multicast_port_group_rexmit, 0); - hlist_add_head(&p->mglist, &port->mglist); if (src) memcpy(p->eth_addr, src, ETH_ALEN); else eth_broadcast_addr(p->eth_addr); + RCU_INIT_POINTER(p->next, next); + hlist_add_head_rcu(&p->mglist, &port->mglist); + return p; free_out: @@ -1465,11 +1466,11 @@ void br_multicast_del_port_group(struct net_bridge_port_group *p) struct net_bridge_port *port = p->key.port; __u16 vid = p->key.addr.vid; - hlist_del_init(&p->mglist); + hlist_del_init_rcu(&p->mglist); if (!br_multicast_is_star_g(&p->key.addr)) rhashtable_remove_fast(&port->br->sg_port_tbl, &p->rhnode, br_sg_port_rht_params); - kfree(p); + kfree_rcu(p, rcu); br_multicast_port_ngroups_dec(port, vid); } From 1f29543126dde307e8b5fb6a740c54e59deaa2ff Mon Sep 17 00:00:00 2001 From: Viswajith Murali Date: Tue, 1 Sep 2026 15:13:17 +0530 Subject: [PATCH 0704/1198] octeontx2-af: mcs: Clear stale X2P calibration state before calibration Some firmware versions leave MCSX_MIL_GLOBAL bit 5 set on boot. If the bit is already set when the driver attempts X2P calibration, the hardware sees no rising edge and calibration never triggers. Clear the bit and wait briefly before starting calibration to ensure a clean rising edge. Fixes: ca7f49ff8846 ("octeontx2-af: cn10k: Introduce driver for macsec block.") Signed-off-by: Nitin Shetty J Signed-off-by: Viswajith Murali Link: https://patch.msgid.link/20260901094318.1395356-1-nshettyj@marvell.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/marvell/octeontx2/af/mcs.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs.c b/drivers/net/ethernet/marvell/octeontx2/af/mcs.c index a07e0b3d8d00..211c10aa5880 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mcs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs.c @@ -1417,6 +1417,16 @@ static int mcs_x2p_calibration(struct mcs *mcs) int i, err = 0; u64 val; + /* Clear any stale calibration state left by firmware/bootloader. + * Some firmware versions may leave MCSX_MIL_GLOBAL bit 5 set, + * preventing the hardware from detecting the rising edge needed to + * trigger X2P calibration. + */ + val = mcs_reg_read(mcs, MCSX_MIL_GLOBAL); + val &= ~BIT_ULL(5); + mcs_reg_write(mcs, MCSX_MIL_GLOBAL, val); + usleep_range(100, 200); + /* set X2P calibration */ val = mcs_reg_read(mcs, MCSX_MIL_GLOBAL); val |= BIT_ULL(5); From c91b4d6e5cc30ceea3f23ebe29aec012709a065f Mon Sep 17 00:00:00 2001 From: "Nikhil P. Rao" Date: Tue, 1 Sep 2026 05:56:27 +0000 Subject: [PATCH 0705/1198] ionic: use netif_txq_maybe_stop() in ionic_tx() Commit 061b9bedbef1 ("ionic: Rework Tx start/stop flow") replaced ionic_maybe_stop_tx() with netif_txq_maybe_stop() to get the memory barriers around the stop/start bits right, but did not cover the stop in ionic_tx() added by commit 138506ab249b ("ionic: Check stop no restart"). Convert the remaining site. netif_txq_maybe_stop() requires the ring indexes to be updated before it is invoked, so the post has to come first. But ring_dbell comes from __netdev_tx_sent_queue(), which runs after that and reads the stop bit, so it is not known in time to pass to ionic_txq_post(). Post without the doorbell and ring it separately. The stop condition is unchanged. The re-check only clears the stop bit when space has become available, so the doorbell starvation fixed by commit 138506ab249b ("ionic: Check stop no restart") cannot recur. Fixes: 138506ab249b ("ionic: Check stop no restart") Signed-off-by: Nikhil P. Rao Reviewed-by: Brett Creeley Link: https://patch.msgid.link/20260901055627.1373129-1-nikhil.rao@amd.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/pensando/ionic/ionic_txrx.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index e436e3231e86..2543a8ff8547 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -1672,15 +1672,22 @@ static int ionic_tx(struct net_device *netdev, struct ionic_queue *q, stats->pkts++; stats->bytes += skb->len; + ionic_txq_post(q, false); + if (likely(!ionic_txq_hwstamp_enabled(q))) { struct netdev_queue *ndq = q_to_ndq(netdev, q); - if (unlikely(!ionic_q_has_space(q, MAX_SKB_FRAGS + 1))) - netif_tx_stop_queue(ndq); + netif_txq_maybe_stop(ndq, ionic_q_space_avail(q), + MAX_SKB_FRAGS + 1, MAX_SKB_FRAGS + 1); ring_dbell = __netdev_tx_sent_queue(ndq, skb->len, netdev_xmit_more()); } - ionic_txq_post(q, ring_dbell); + + if (ring_dbell) { + ionic_dbell_ring(q->lif->kern_dbpage, q->hw_type, + q->dbval | q->head_idx); + q->dbell_jiffies = jiffies; + } return 0; } From 78a86d75a70e1e227711c72865c59b1422d0a5ae Mon Sep 17 00:00:00 2001 From: Fourie Zhang Date: Wed, 2 Sep 2026 17:27:12 +0800 Subject: [PATCH 0706/1198] net: mpls: clear inner_protocol when the last label is popped skb_mpls_push() records the pre-encapsulation network header once, gated on !skb->inner_protocol. skb_mpls_pop() never clears that record, so it outlives the encapsulation it describes. Open vSwitch can then re-push MPLS onto a packet whose inner_network_header still points at the older, deeper offset: push a label, pop every label, recirculate (ovs_flow_key_update() re-derives key->eth.type and resets network_header, but leaves inner_*), then push again. ovs_fragment() trusts the record: skb->network_header = skb->inner_network_header; so skb_network_offset() goes negative. The bound check is signed: if (skb_network_offset(skb) > MAX_L2_LEN) a negative offset passes it, and prepare_frag() widens the value: unsigned int hlen = skb_network_offset(skb); memcpy(&data->l2_data, skb->data, hlen); which is a ~4GiB memcpy out of a 30-byte per-CPU buffer. Reproduced on v7.3-rc1. RDX is the truncated length, (unsigned int)(-8): BUG: unable to handle page fault for address: ffffe8ffffc16000 #PF: supervisor write access in kernel mode Oops: 0002 [#1] SMP KASAN NOPTI RIP: 0010:memcpy+0x8/0x20 RDX: 00000000fffffff8 RSI: ffff888105d732db RDI: ffffe8ffffc16000 prepare_frag+0x3df/0x4e0 ovs_fragment+0x589/0x7e0 do_output+0x4ce/0x5e0 do_execute_actions+0x55d2/0x7b30 ovs_execute_actions+0xea/0x450 Same root-cause shape as commit 975b5b067f52 ("ipv6: sr: restore network header before routing and forwarding"): a stale network header offset reaching a consumer that widens it. Here it originates in the MPLS push/pop path. Clear inner_protocol once the packet is no longer MPLS, so a later push re-records the current header. net/sched/act_mpls.c is the only other skb_mpls_pop() caller and gets the same fix; sch_frag.c saves and restores inner_protocol around fragmentation in the same way OVS does. Fixes: 48d2ab609b6b ("net: mpls: Fixups for GSO") Cc: stable@vger.kernel.org Signed-off-by: Fourie Zhang Acked-by: Jiri Benc Link: https://patch.msgid.link/20260902092719.2874481-1-fouriezhang@tencent.com Signed-off-by: Jakub Kicinski --- net/core/skbuff.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 966af3beed94..cc3b4b70288b 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -6690,6 +6690,13 @@ int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, } skb->protocol = next_proto; + /* The last label is gone, so the inner header recorded by + * skb_mpls_push() no longer describes this packet. Drop it, or a + * later push keeps the stale offset. + */ + if (!eth_p_mpls(next_proto)) + skb->inner_protocol = 0; + return 0; } EXPORT_SYMBOL_GPL(skb_mpls_pop); From 5d50e90add8b4a978395e893e81954d19d58a7c5 Mon Sep 17 00:00:00 2001 From: Jason Winter Date: Wed, 2 Sep 2026 10:40:41 +0200 Subject: [PATCH 0707/1198] net: usb: cx82310_eth: drop URB after 0xffff reboot sentinel to prevent partial_data heap overflow The 0xffff length sentinel detects a router reboot and schedules re-enabling of ethernet mode, but then falls through to the rest of the loop body. The next check is } else if (len > CX82310_MTU) { which is the else of the just-matched if -- it never fires for len == 0xffff. The MTU bound that normally caps the incomplete-packet save path is silently bypassed. With 0xffff > skb->len always true (rx_urb_size is 4096), the incomplete-packet branch saves dev->partial_len = skb->len bytes into dev->partial_data. partial_data is kmalloc(hard_mtu) = kmalloc(CX82310_MTU + 2) = 1516 bytes, but skb->len after the 2-byte header pull can be up to 4094. A device that sends a 4096-byte URB starting with [0xff 0xff] therefore copies 4094 device-provided bytes into a buffer allocated for 1516 bytes, exceeding its requested size by 2578 bytes. The next URB then reads dev->partial_len (4094) back from the same 1516-byte buffer and dev->partial_rem (65535 - 4094 = 61441) from the new URB's ~4KB skb, both well past their allocations, and delivers the spliced result as a 64KB "frame" to the network stack. Bail out of rx_fixup after scheduling the re-enable work; the remainder of a reboot-marker URB is not meaningful packet data. This restores the invariant that partial_len < CX82310_MTU + 2 on the save path, since every other route there has already passed the MTU check. Fixes: ca139d76b0d9 ("cx82310_eth: re-enable ethernet mode after router reboot") Signed-off-by: Jason Winter Link: https://patch.msgid.link/BESP194MB283265DDDC63B6B78D8D34FBB8B72@BESP194MB2832.EURP194.PROD.OUTLOOK.COM Signed-off-by: Jakub Kicinski --- drivers/net/usb/cx82310_eth.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/usb/cx82310_eth.c b/drivers/net/usb/cx82310_eth.c index 068acb052adb..5df657acf3d5 100644 --- a/drivers/net/usb/cx82310_eth.c +++ b/drivers/net/usb/cx82310_eth.c @@ -282,6 +282,7 @@ static int cx82310_rx_fixup(struct usbnet *dev, struct sk_buff *skb) if (len == 0xffff) { netdev_info(dev->net, "router was rebooted, re-enabling ethernet mode"); schedule_work(&priv->reenable_work); + return 0; } else if (len > CX82310_MTU) { netdev_err(dev->net, "RX packet too long: %d B\n", len); return 0; From 1668a31e3b1ad358d981ddb6dbd3db1fe0533621 Mon Sep 17 00:00:00 2001 From: Alexandra Winter Date: Wed, 2 Sep 2026 16:34:38 +0200 Subject: [PATCH 0708/1198] dibs: Unregister dibs_class after error In case dibs_loopback_init() fails, e.g. because of -ENOMEM, dibs_init() must unregister dibs_class. Otherwise dibs_class and /sys/class/dibs exist even though the functionality is not available. A retry to load the module fails with -EEXIST. Unregister dibs_class in the error path of dibs_init. Note that before commit ad3dfa80be76 ("dibs: change dibs_class to a const struct") class_destroy(dibs_class) is required instead of class_unregister(&dibs_class). Fixes: 804737349813 ("dibs: Create class dibs") Signed-off-by: Alexandra Winter Link: https://patch.msgid.link/20260902143438.426664-1-wintera@linux.ibm.com Signed-off-by: Jakub Kicinski --- drivers/dibs/dibs_main.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/dibs/dibs_main.c b/drivers/dibs/dibs_main.c index 2b53a9d277dc..20c50997a7cf 100644 --- a/drivers/dibs/dibs_main.c +++ b/drivers/dibs/dibs_main.c @@ -251,13 +251,19 @@ static int __init dibs_init(void) rc = class_register(&dibs_class); if (rc) - return rc; + goto err; rc = dibs_loopback_init(); if (rc) - pr_err("%s fails with %d\n", __func__, rc); + goto err_unregister; return rc; + +err_unregister: + class_unregister(&dibs_class); +err: + pr_err("%s fails with %d\n", __func__, rc); + return rc; } static void __exit dibs_exit(void) From 907a56ab3eb8a58500a58daa76087f17bb2b6826 Mon Sep 17 00:00:00 2001 From: Alexandra Winter Date: Wed, 2 Sep 2026 16:37:33 +0200 Subject: [PATCH 0709/1198] s390/ism: folio_put() after error dmb->cpu_addr was allocated via folio_alloc(). Use folio_put() instead of kfree() in the error exit of ism_alloc_dmb() to avoid slab allocator corruption. While at it, reset dmb->cpu_addr after folio_put to avoid unintentional UAF by future callers. Fixes: 83781384a96b ("s390/ism: Properly fix receive message buffer allocation") Signed-off-by: Alexandra Winter Reviewed-by: Gerd Bayer Link: https://patch.msgid.link/20260902143733.433574-1-wintera@linux.ibm.com Signed-off-by: Jakub Kicinski --- drivers/s390/net/ism_drv.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c index 242da20f27e0..035b233abb4e 100644 --- a/drivers/s390/net/ism_drv.c +++ b/drivers/s390/net/ism_drv.c @@ -231,6 +231,7 @@ static void ism_free_dmb(struct ism_dev *ism, struct dibs_dmb *dmb) dma_unmap_page(&ism->pdev->dev, dmb->dma_addr, dmb->dmb_len, DMA_FROM_DEVICE); folio_put(virt_to_folio(dmb->cpu_addr)); + dmb->cpu_addr = NULL; } static int ism_alloc_dmb(struct ism_dev *ism, struct dibs_dmb *dmb) @@ -274,7 +275,8 @@ static int ism_alloc_dmb(struct ism_dev *ism, struct dibs_dmb *dmb) return 0; out_free: - kfree(dmb->cpu_addr); + folio_put(folio); + dmb->cpu_addr = NULL; out_bit: clear_bit(dmb->idx, ism->sba_bitmap); return rc; From 98fc57d167446b95b4e719815fe79edef93f8e7a Mon Sep 17 00:00:00 2001 From: Seungwon Bae Date: Thu, 3 Sep 2026 00:59:56 +0900 Subject: [PATCH 0710/1198] vxlan: reject dynamic fdb entries that reference a nexthop id The commit cited in the Fixes tag allowed VXLAN FDB entries to point to FDB nexthops so that overlay traffic could be load balanced across multiple VTEPs. Such entries can only be configured from user space, cannot be learned and cannot roam. They only make sense with a user space control plane such as E-VPN where data plane learning is disabled. Despite that, the VXLAN driver does not currently prevent such entries from being configured with the "dynamic" flag. The per-nexthop FDB list is only protected by the per-device hash lock, which is not sufficient when two VXLAN devices point to the same FDB nexthop and therefore share the list. Aging runs in softirq context without RTNL, so an entry deleted by one device can race with an addition or deletion from the other, leading to list corruption: list_del corruption. next->prev should be ffff8881069d9548, but was dead000000000122. (next=ffff8881069d9448) WARNING: CPU: 0 PID: 90 at lib/list_debug.c:65 __list_del_entry_valid_or_report+0x1aa/0x210 ... vxlan_fdb_destroy+0x5b8/0xad0 vxlan_cleanup+0x328/0x450 call_timer_fn+0x2a/0x1c0 run_timer_softirq+0x18c/0x210 BUG: KASAN: slab-use-after-free in vxlan_fdb_destroy Fix this by rejecting the bogus configuration of dynamic FDB entries that point to FDB nexthops, both when created and when an existing entry is updated. As such, the per-nexthop FDB list is only ever mutated under the RTNL lock. Add test cases to make sure that this does not regress in the future. Fixes: 1274e1cc4226 ("vxlan: ecmp support for mac fdb entries") Suggested-by: Ido Schimmel Signed-off-by: Seungwon Bae Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/20260902155956.296699-1-qotmddnjs@ajou.ac.kr Signed-off-by: Jakub Kicinski --- drivers/net/vxlan/vxlan_core.c | 11 ++++++++ tools/testing/selftests/net/fib_nexthops.sh | 28 +++++++++++++++++++++ 2 files changed, 39 insertions(+) diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 459f19f7071e..be95af64a1f5 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -996,6 +996,12 @@ static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan, return -EOPNOTSUPP; } + if (rcu_access_pointer(f->nh) && + !(state & (NUD_PERMANENT | NUD_NOARP))) { + NL_SET_ERR_MSG(extack, "Cannot make a nexthop fdb dynamic"); + return -EOPNOTSUPP; + } + /* Do not allow an externally learned entry to take over an entry added * by the user. */ @@ -1257,6 +1263,11 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], if (err) return err; + if (nhid && !(ndm->ndm_state & (NUD_PERMANENT | NUD_NOARP))) { + NL_SET_ERR_MSG(extack, "A nexthop fdb cannot be dynamic"); + return -EINVAL; + } + if (vxlan->default_dst.remote_ip.sa.sa_family != ip.sa.sa_family) return -EAFNOSUPPORT; diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index 3d347126730a..431d7bed7622 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -533,6 +533,20 @@ ipv6_fdb_grp_fcnal() run_cmd "$BRIDGE fdb add 02:02:00:00:00:14 dev vx10 nhid 61 self" log_test $? 255 "Fdb mac add with nexthop" + # fdb entries with a nexthop group cannot be aged out + run_cmd "$BRIDGE fdb add 02:02:00:00:00:15 dev vx10 nhid 102 self static" + log_test $? 0 "Fdb mac add with nexthop group and static state" + + run_cmd "$BRIDGE fdb add 02:02:00:00:00:16 dev vx10 nhid 102 self dynamic" + log_test $? 255 "Fdb mac add with nexthop group and dynamic state" + + run_cmd "$BRIDGE fdb add 02:02:00:00:00:17 dev vx10 nhid 102 self" + run_cmd "$BRIDGE fdb replace 02:02:00:00:00:17 dev vx10 dst 2001:db8:91::11 self dynamic" + log_test $? 255 "Fdb mac replace with nexthop group and dynamic state" + + run_cmd "$BRIDGE fdb append 02:02:00:00:00:17 dev vx10 dst 2001:db8:91::11 self dynamic" + log_test $? 255 "Fdb mac append with nexthop group and dynamic state" + run_cmd "$IP -6 ro add 2001:db8:101::1/128 nhid 66" log_test $? 2 "Route add with fdb nexthop" @@ -669,6 +683,20 @@ ipv4_fdb_grp_fcnal() run_cmd "$BRIDGE fdb add 02:02:00:00:00:14 dev vx10 nhid 12 self" log_test $? 255 "Fdb mac add with nexthop" + # fdb entries with a nexthop group cannot be aged out + run_cmd "$BRIDGE fdb add 02:02:00:00:00:15 dev vx10 nhid 102 self static" + log_test $? 0 "Fdb mac add with nexthop group and static state" + + run_cmd "$BRIDGE fdb add 02:02:00:00:00:16 dev vx10 nhid 102 self dynamic" + log_test $? 255 "Fdb mac add with nexthop group and dynamic state" + + run_cmd "$BRIDGE fdb add 02:02:00:00:00:17 dev vx10 nhid 102 self" + run_cmd "$BRIDGE fdb replace 02:02:00:00:00:17 dev vx10 dst 10.0.0.3 self dynamic" + log_test $? 255 "Fdb mac replace with nexthop group and dynamic state" + + run_cmd "$BRIDGE fdb append 02:02:00:00:00:17 dev vx10 dst 10.0.0.3 self dynamic" + log_test $? 255 "Fdb mac append with nexthop group and dynamic state" + run_cmd "$IP ro add 172.16.0.0/22 nhid 16" log_test $? 2 "Route add with fdb nexthop" From 66ab4c59b74db7ab53a1c9083feaaede393a96a0 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Wed, 2 Sep 2026 17:29:08 -0400 Subject: [PATCH 0711/1198] net: cap tx_queue_len at S16_MAX to prevent oversized ring allocations Several subsystems allocate ring buffers sized by dev->tx_queue_len with no upper bound. An unprivileged user (via unshare -Urn) can set a huge tx_queue_len and exhaust global memory with ring allocations: - pfifo_fast: pfifo_fast_init() and pfifo_fast_change_tx_queue_len() allocate 3 skb_array rings of tx_queue_len entries each. - tun: tun_queue_resize() and the queue-attach path resize ptr_rings to tx_queue_len on the NETDEV_CHANGE_TX_QUEUE_LEN notifier. - tap (macvtap/ipvtap): tap_queue_resize() and tap_init() resize/init ptr_rings to tx_queue_len on the same notifier. netif_change_tx_queue_len() is the single entry point for IFLA_TXQLEN, sysfs, and the SIOCSIFTXQLEN ioctl. Cap new_len at S16_MAX (32767) there so the oversized value is rejected at set time. This takes effect whether the device is up or down, before dev->tx_queue_len is written, before any notifier fires, and before any ring is allocated. The "> S16_MAX" check also subsumes the previous unsigned-long truncation test, and a negative ifr_qlen from the ioctl lands far above the cap after conversion, so both old failure modes are covered by the one comparison. tx_queue_len is ambigious: both a per-ring sizing multiplier and a default queue-length/limit knob for consumers that allocate nothing at set time (pfifo/bfifo/gred/plug/sfb limits, htb direct_qlen, qfq max_classes, teql). 32767 is chosen as the largest value NLA_POLICY_FULL_RANGE can express for the u32 IFLA_TXQLEN policy in patch 2/3 while staying a legitimate queue length on high-BDP paths; the ring-memory trade-off of a shared knob is disclosed below. Conditions to recreate the bug: - CONFIG_NET_SCHED=y, CONFIG_VETH=y, CONFIG_USER_NS=y, CONFIG_NET_NS=y. - Unprivileged user in a fresh user+net namespace (unshare -Urn). - pfifo_fast: create veth pairs, set tx_queue_len to 500000, attach mq+pfifo_fast. ~28 iterations OOMs a 2GB guest. - tun: create 50 tun devices with IFF_MULTI_QUEUE, set tx_queue_len to 500000, open 8 queues each. ~1.6GB of ptr_ring allocations OOMs a 512MB guest. - tap: same as tun with IFF_TAP. ~960MB OOMs a 512MB guest. - On the fixed kernel the oversized tx_queue_len is rejected with -ERANGE at set time (all four paths: RTM_SETLINK, RTM_NEWLINK create, sysfs, ioctl - the latter two via this check, the former two via this check and the 2/3 parse policy respectively). Fixes: 6a643ddb5624 ("net: introduce helper dev_change_tx_queue_len()") Reported-by: Vega Closes: https://lore.kernel.org/netdev/20260828121902.66837-1-jhs@mojatatu.com/ Tested-by: Victor Nogueira Signed-off-by: Jamal Hadi Salim Link: https://patch.msgid.link/QDISC-2899.v2.20260901233641@mojatatu.com Signed-off-by: Jakub Kicinski --- net/core/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/dev.c b/net/core/dev.c index 290e0f099e6b..ecfbd72d5d1a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -9982,7 +9982,7 @@ int netif_change_tx_queue_len(struct net_device *dev, unsigned long new_len) unsigned int orig_len = dev->tx_queue_len; int res; - if (new_len != (unsigned int)new_len) + if (new_len > S16_MAX) return -ERANGE; if (new_len != orig_len) { From 1aa9e143bf51405665a793d4cc925e1c4f0c5922 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Wed, 2 Sep 2026 17:29:09 -0400 Subject: [PATCH 0712/1198] net: reject oversized tx_queue_len at netlink parse time rtnl_create_link() assigns IFLA_TXQLEN directly to dev->tx_queue_len without going through netif_change_tx_queue_len(), so a device created with "ip link add ... txqueuelen 500000" bypasses the S16_MAX cap and still triggers the oversized ring allocations in pfifo_fast, tun and tap. The veth peer nest (rtnl_nla_parse_ifinfomsg()) and the RTM_NEWLINK-on-existing-device path reach the same sinks. Enforce the cap in ifla_policy instead: IFLA_TXQLEN becomes NLA_POLICY_FULL_RANGE(NLA_U32, &txqlen_range) with txqlen_range = { .min = 0, .max = S16_MAX }. All netlink consumers parse against this policy - rtnl_setlink(), rtnl_newlink() (create and change), and the veth peer nest - so every netlink path is capped at parse time and rejects the attribute with -ERANGE plus a proper "integer out of range" extack message before any device state is modified (the RTM_SETLINK half-application wart is gone with it). Document the bound in the rt-link.yaml netlink spec. Conditions to recreate the bug: - CONFIG_NET_SCHED=y, CONFIG_VETH=y, CONFIG_USER_NS=y, CONFIG_NET_NS=y. - Unprivileged user in a fresh user+net namespace (unshare -Urn): ip link add v0 txqueuelen 500000 type veth peer name v1 -> on the fixed kernel this is rejected with -ERANGE ("integer out of range" extack) instead of installing an oversized tx_queue_len that later inflates pfifo_fast/tun/tap ring allocations. - ip link set v0 txqueuelen 500000 is likewise rejected at parse time. Fixes: 38f7b870d4a6 ("[RTNETLINK]: Link creation API") Reported-by: Vega Tested-by: Victor Nogueira Signed-off-by: Jamal Hadi Salim Link: https://patch.msgid.link/QDISC-2899.v2.20260901233641@mojatatu.com.2 Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/rt-link.yaml | 2 ++ net/core/rtnetlink.c | 7 ++++++- 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/Documentation/netlink/specs/rt-link.yaml b/Documentation/netlink/specs/rt-link.yaml index b80c2ac3ac31..99f6fba456cc 100644 --- a/Documentation/netlink/specs/rt-link.yaml +++ b/Documentation/netlink/specs/rt-link.yaml @@ -898,6 +898,8 @@ attribute-sets: - name: txqlen type: u32 + checks: + max: 32767 - name: map type: binary diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 81c5a6104dea..be9d1625bac3 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2287,6 +2287,11 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, return -EMSGSIZE; } +static const struct netlink_range_validation txqlen_range = { + .min = 0, + .max = S16_MAX, +}; + static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_UNSPEC] = { .strict_start_type = IFLA_DPLL_PIN }, [IFLA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ-1 }, @@ -2297,7 +2302,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_LINK] = { .type = NLA_U32 }, [IFLA_MASTER] = { .type = NLA_U32 }, [IFLA_CARRIER] = { .type = NLA_U8 }, - [IFLA_TXQLEN] = { .type = NLA_U32 }, + [IFLA_TXQLEN] = NLA_POLICY_FULL_RANGE(NLA_U32, &txqlen_range), [IFLA_WEIGHT] = { .type = NLA_U32 }, [IFLA_OPERSTATE] = { .type = NLA_U8 }, [IFLA_LINKMODE] = { .type = NLA_U8 }, From 0a7252d7f85478080385de4c1072085e30849fe3 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Wed, 2 Sep 2026 17:29:10 -0400 Subject: [PATCH 0713/1198] selftests: tc-testing: add tx_queue_len cap regression tests Add nine test cases for the S16_MAX tx_queue_len cap to the pfifo_fast suite. Netlink cases exercise the ifla_policy bound (2/3); the two new sysfs cases exercise the netif_change_tx_queue_len() choke point that 1/3 owns (SIOCSIFTXQLEN shares it; the ioctl is not portably reachable from tdc): - dbe3: set txqueuelen 32767 (S16_MAX) - accepted, pins the exact boundary value. - b50e: set txqueuelen 32768 - rejected with -ERANGE. - 40f8: write 32768 to /sys/class/net/*/tx_queue_len - rejected (covers patch 1/3 directly; netlink cannot reach this path). - 4b6e: write 32767 via sysfs - accepted, boundary positive control for the patch-1 path. - b90d: create a dummy with txqueuelen 32767 - accepted. - 57ab: create a dummy with txqueuelen 32768 - rejected at netlink parse time. - e777: create a dummy with txqueuelen 500000 - rejected (the v1 bypass path flagged by review). - 31ac: create a veth with an oversized txqueuelen on the peer nest - rejected (the peer nest is parsed against ifla_policy too). - b567: create a veth with txqueuelen on both ends within the cap - accepted (positive control for the peer nest). The three negative-creation verifies assert device absence ("ip -o link show" must not contain the device), not merely absence of a qlen pattern - the device does not exist when creation fails, so the exit code carries the signal and the verify adds content. The v1 04b5 "resize rollback" case is dropped: with the cap checked first, netif_change_tx_queue_len() returns -ERANGE before the write, the notifier or any qdisc resize, so the case exercised no resize and no rollback. It was also nondeterministic: pre-patch, the resize issues three ~11 MB kvmallocs for qlen 500000 which normally succeed, so the case passed on an unfixed kernel only under memory pressure - its outcome depended on the test host's free memory. Test commands run inside the netns, but nsPlugin creates the veth peer in the root namespace, so the teardown deletes the in-ns end only; deleting the peer via the pair is implicit. Note: iproute2 treats "txqueuelen" appearing after "type X" as a link-type attribute and silently drops it, so the creation cases place it before "type" to actually reach the kernel. Signed-off-by: Jamal Hadi Salim Link: https://patch.msgid.link/QDISC-2899.v2.20260901233641@mojatatu.com.3 Signed-off-by: Jakub Kicinski --- .../tc-tests/qdiscs/pfifo_fast.json | 204 ++++++++++++++++++ 1 file changed, 204 insertions(+) diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/pfifo_fast.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/pfifo_fast.json index 30da27fe8806..a6e25e76ecb1 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/pfifo_fast.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/pfifo_fast.json @@ -105,5 +105,209 @@ "teardown": [ "$TC qdisc del dev $DUMMY handle 1: root" ] + }, + { + "id": "dbe3", + "name": "Set tx_queue_len to S16_MAX boundary (32767 accepted)", + "category": [ + "qdisc", + "pfifo_fast" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [], + "cmdUnderTest": "$IP link set dev $DUMMY txqueuelen 32767", + "expExitCode": "0", + "verifyCmd": "$IP link show dev $DUMMY", + "matchPattern": "qlen 32767$", + "matchCount": "1", + "teardown": [] + }, + { + "id": "b50e", + "name": "Reject tx_queue_len above S16_MAX at set time (32768)", + "category": [ + "qdisc", + "pfifo_fast" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [], + "cmdUnderTest": "$IP link set dev $DUMMY txqueuelen 32768", + "expExitCode": "2", + "verifyCmd": "$IP link show dev $DUMMY", + "matchPattern": "qlen 1000$", + "matchCount": "1", + "teardown": [] + }, + { + "id": "40f8", + "name": "Reject tx_queue_len above S16_MAX via sysfs (32768)", + "category": [ + "qdisc", + "pfifo_fast" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [], + "cmdUnderTest": "sh -c 'echo 32768 > /sys/class/net/$DUMMY/tx_queue_len'", + "expExitCode": "1", + "verifyCmd": "$IP link show dev $DUMMY", + "matchPattern": "qlen 1000$", + "matchCount": "1", + "teardown": [] + }, + { + "id": "4b6e", + "name": "Set tx_queue_len to S16_MAX via sysfs (32767 accepted)", + "category": [ + "qdisc", + "pfifo_fast" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [], + "cmdUnderTest": "sh -c 'echo 32767 > /sys/class/net/$DUMMY/tx_queue_len'", + "expExitCode": "0", + "verifyCmd": "$IP link show dev $DUMMY", + "matchPattern": "qlen 32767$", + "matchCount": "1", + "teardown": [] + }, + { + "id": "b90d", + "name": "Create device with tx_queue_len at S16_MAX boundary (32767 accepted)", + "category": [ + "qdisc", + "pfifo_fast" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$IP link del dev $DUMMY", + 0, + 1 + ] + ], + "cmdUnderTest": "$IP link add dev $DUMMY txqueuelen 32767 type dummy", + "expExitCode": "0", + "verifyCmd": "$IP link show dev $DUMMY", + "matchPattern": "qlen 32767$", + "matchCount": "1", + "teardown": [ + [ + "$IP link del dev $DUMMY", + 0, + 1 + ] + ] + }, + { + "id": "57ab", + "name": "Reject creating device with tx_queue_len above S16_MAX (32768)", + "category": [ + "qdisc", + "pfifo_fast" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$IP link del dev $DUMMY", + 0, + 1 + ] + ], + "cmdUnderTest": "$IP link add dev $DUMMY txqueuelen 32768 type dummy", + "expExitCode": "2", + "verifyCmd": "$IP -o link show", + "matchPattern": "^[0-9]+: $DUMMY", + "matchCount": "0", + "teardown": [] + }, + { + "id": "e777", + "name": "Reject creating device with oversized tx_queue_len (500000)", + "category": [ + "qdisc", + "pfifo_fast" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$IP link del dev $DUMMY", + 0, + 1 + ] + ], + "cmdUnderTest": "$IP link add dev $DUMMY txqueuelen 500000 type dummy", + "expExitCode": "2", + "verifyCmd": "$IP -o link show", + "matchPattern": "^[0-9]+: $DUMMY", + "matchCount": "0", + "teardown": [] + }, + { + "id": "31ac", + "name": "Reject veth peer nest tx_queue_len above S16_MAX at create", + "category": [ + "qdisc", + "pfifo_fast" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$IP link del dev $DEV1", + 0, + 1 + ] + ], + "cmdUnderTest": "$IP link add dev $DEV1 type veth peer name $DEV0 txqueuelen 500000", + "expExitCode": "2", + "verifyCmd": "$IP -o link show", + "matchPattern": "^[0-9]+: $DEV1", + "matchCount": "0", + "teardown": [] + }, + { + "id": "b567", + "name": "Accept veth peer nest tx_queue_len within S16_MAX", + "category": [ + "qdisc", + "pfifo_fast" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$IP link del dev $DEV1", + 0, + 1 + ] + ], + "cmdUnderTest": "$IP link add dev $DEV1 txqueuelen 100 type veth peer name $DEV0 txqueuelen 200", + "expExitCode": "0", + "verifyCmd": "$IP link show", + "matchPattern": "qlen (100|200)$", + "matchCount": "2", + "teardown": [ + [ + "$IP link del dev $DEV0", + 0, + 1 + ] + ] } ] From 7980325b2f71e3f65c1323c39792e2455da6fab6 Mon Sep 17 00:00:00 2001 From: "Nikhil P. Rao" Date: Tue, 1 Sep 2026 04:42:17 +0000 Subject: [PATCH 0714/1198] pds_core: fix cmd_regs access racing BAR unmap on reset pdsc_reset_prepare() and pdsc_reset_done()'s pdsc_map_bars() error path clear/iounmap cmd_regs without devcmd_lock, and pdsc_legacy_firmware_update()'s download loop derefs cmd_regs after dropping and retaking the lock without re-checking. An FLR concurrent with a devlink flash can unmap cmd_regs under an in-flight devcmd, causing a NULL deref or a write to unmapped MMIO. Take devcmd_lock across the BAR unmap/remap, and re-check cmd_regs in the download loop. Only the PF maps cmd_regs and runs devcmd, so skip the unmap on a VF, as pdsc_remove() and pdsc_reset_done() already do. A reset that completes entirely within the unlocked window is not a correctness problem for the image: the device clears its update session, so a resumed download is rejected, and it verifies the staged image before writing a flash slot, reporting PDS_RC_BAD_FW rather than activating it. pdsc_unmap_bars() also clears info_regs, intr_status and intr_ctrl. The interrupt and start/stop readers of those are quiesced before the unmap by pdsc_fw_down(), which frees the interrupts and tears down the queues. The debugfs readers are not, since those files outlive a reset; that is pre-existing and out of scope here. Fixes: e96094c1d11c ("pds_core: Clear BARs on reset") Reported-by: sashiko-bot Closes: https://sashiko.dev/#/patchset/20260708212222.296202-1-nikhil.rao%40amd.com?part=3 Signed-off-by: Nikhil P. Rao Link: https://patch.msgid.link/20260901044219.1361466-2-nikhil.rao@amd.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/amd/pds_core/fw.c | 10 +++++++++- drivers/net/ethernet/amd/pds_core/main.c | 8 +++++++- 2 files changed, 16 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/amd/pds_core/fw.c b/drivers/net/ethernet/amd/pds_core/fw.c index 5ccf017f6af4..19899bf38d40 100644 --- a/drivers/net/ethernet/amd/pds_core/fw.c +++ b/drivers/net/ethernet/amd/pds_core/fw.c @@ -171,8 +171,10 @@ pdsc_legacy_firmware_update(struct pdsc *pdsc, dev_info(pdsc->dev, "Installing firmware\n"); - if (!pdsc->cmd_regs) + if (!pdsc->cmd_regs) { + NL_SET_ERR_MSG_MOD(extack, "BARs not mapped"); return -ENXIO; + } dl = priv_to_devlink(pdsc); devlink_flash_update_status_notify(dl, "Preparing to flash", @@ -198,6 +200,12 @@ pdsc_legacy_firmware_update(struct pdsc *pdsc, copy_sz = min_t(unsigned int, buf_sz, fw->size - offset); mutex_lock(&pdsc->devcmd_lock); + if (!pdsc->cmd_regs) { + mutex_unlock(&pdsc->devcmd_lock); + err = -ENXIO; + NL_SET_ERR_MSG_MOD(extack, "Device reset during flash"); + goto err_out; + } memcpy_toio(&pdsc->cmd_regs->data, fw->data + offset, copy_sz); err = pdsc_devcmd_fw_download_locked(pdsc, data_addr, offset, copy_sz); diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c index bb79e7476370..6e1079f9ba0f 100644 --- a/drivers/net/ethernet/amd/pds_core/main.c +++ b/drivers/net/ethernet/amd/pds_core/main.c @@ -513,7 +513,11 @@ static void pdsc_reset_prepare(struct pci_dev *pdev) pdsc_auxbus_dev_del(pdsc, pdsc, &pdsc->padev); } - pdsc_unmap_bars(pdsc); + if (!pdev->is_virtfn) { + mutex_lock(&pdsc->devcmd_lock); + pdsc_unmap_bars(pdsc); + mutex_unlock(&pdsc->devcmd_lock); + } pci_release_regions(pdev); if (pci_is_enabled(pdev)) pci_disable_device(pdev); @@ -543,7 +547,9 @@ static void pdsc_reset_done(struct pci_dev *pdev) return; } + mutex_lock(&pdsc->devcmd_lock); err = pdsc_map_bars(pdsc); + mutex_unlock(&pdsc->devcmd_lock); if (err) return; } From 73608de7e59246b4b533c1ffaee158a7048e186e Mon Sep 17 00:00:00 2001 From: "Nikhil P. Rao" Date: Tue, 1 Sep 2026 04:42:18 +0000 Subject: [PATCH 0715/1198] pds_core: don't release PCI regions for VFs on reset pdsc_reset_prepare() called pci_release_regions() unconditionally, but only PFs call pci_request_regions() (pdsc_init_pf). On a VF FLR this makes the kernel warn "Trying to free nonexistent resource". Fixes: ffa55858330f ("pds_core: implement pci reset handlers") Reported-by: sashiko-bot Closes: https://netdev-ai.bots.linux.dev/sashiko/#/patchset/20260804235946.177762-1-nikhil.rao%40amd.com Signed-off-by: Nikhil P. Rao Link: https://patch.msgid.link/20260901044219.1361466-3-nikhil.rao@amd.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/amd/pds_core/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c index 6e1079f9ba0f..a971c66d36f9 100644 --- a/drivers/net/ethernet/amd/pds_core/main.c +++ b/drivers/net/ethernet/amd/pds_core/main.c @@ -517,8 +517,8 @@ static void pdsc_reset_prepare(struct pci_dev *pdev) mutex_lock(&pdsc->devcmd_lock); pdsc_unmap_bars(pdsc); mutex_unlock(&pdsc->devcmd_lock); + pci_release_regions(pdev); } - pci_release_regions(pdev); if (pci_is_enabled(pdev)) pci_disable_device(pdev); pdsc_deferred_dma_free(pdsc); From 1a3a10b030c96ea88868ccc060a16827c01eaa5a Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Fri, 4 Sep 2026 17:05:52 -0700 Subject: [PATCH 0716/1198] bpf: mark a NULL call argument precise check_func_arg() allows bpf_register_is_null() for nullable arguments w/o marking the underlying scalar register precise. Hence a checkpoint created on such a path would prune against arbitrary scalar value. check_helper_call() enforces second parameter of the bpf_get_local_storage() to be zero, w/o marking the underlying scalar register precise. Hence a checkpoint created on such a path would prune against arbitrary scalar value. Grouping these two into one patch, as they share the same fixes tag. Fixes: b5dc0163d8fd ("bpf: precise scalar_value tracking") Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260904-register-is-null-precise-fixes-v1-1-0f5a360ff15d@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 9 ++++++++- .../selftests/bpf/progs/verifier_subprog_precision.c | 12 ++++++------ 2 files changed, 14 insertions(+), 7 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c8699a8831df..b107f551a62d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8759,11 +8759,15 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg, return err; } - if (bpf_register_is_null(reg) && type_may_be_null(arg_type)) + if (bpf_register_is_null(reg) && type_may_be_null(arg_type)) { /* A NULL register has a SCALAR_VALUE type, so skip * type checking. */ + err = mark_chain_precision(env, regno); + if (err) + return err; goto skip_type_check; + } /* arg_btf_id and arg_size are in a union. */ if (base_type(arg_type) == ARG_PTR_TO_BTF_ID || @@ -10923,6 +10927,9 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn verbose(env, "get_local_storage() doesn't support non-zero flags\n"); return -EINVAL; } + err = mark_chain_precision(env, BPF_REG_2); + if (err) + return err; break; case BPF_FUNC_for_each_map_elem: err = push_callback_call(env, insn, insn_idx, meta.subprogno, diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c index e174a905c562..dc0c7034c04f 100644 --- a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c +++ b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c @@ -287,9 +287,9 @@ __msg("17: (b7) r0 = 0") __msg("18: (95) exit") __msg("returning from callee:") __msg("to caller at 9:") -__msg("frame 0: propagating r1,r4") +__msg("frame 0: propagating r1,r3,r4") __msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1") -__msg("mark_precise: frame0: regs=r1,r4 stack= before 18: (95) exit") +__msg("mark_precise: frame0: regs=r1,r3,r4 stack= before 18: (95) exit") __msg("from 18 to 9: safe") __naked int callback_result_precise(void) { @@ -419,9 +419,9 @@ __msg("to caller at 9:") /* r1, r4 are always precise for bpf_loop(), * r6 was marked before backtracking to callback body. */ -__msg("frame 0: propagating r1,r4,r6") +__msg("frame 0: propagating r1,r3,r4,r6") __msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1") -__msg("mark_precise: frame0: regs=r1,r4,r6 stack= before 16: (95) exit") +__msg("mark_precise: frame0: regs=r1,r3,r4,r6 stack= before 16: (95) exit") __msg("mark_precise: frame1: regs= stack= before 15: (b7) r0 = 0") __msg("mark_precise: frame1: regs= stack= before 9: (85) call bpf_loop") __msg("mark_precise: frame0: parent state regs= stack=:") @@ -575,9 +575,9 @@ __msg("to caller at 10:") /* r1, r4 are always precise for bpf_loop(), * fp-8 was marked before backtracking to callback body. */ -__msg("frame 0: propagating r1,r4,fp-8") +__msg("frame 0: propagating r1,r3,r4,fp-8") __msg("mark_precise: frame0: last_idx 10 first_idx 10 subseq_idx -1") -__msg("mark_precise: frame0: regs=r1,r4 stack=-8 before 18: (95) exit") +__msg("mark_precise: frame0: regs=r1,r3,r4 stack=-8 before 18: (95) exit") __msg("mark_precise: frame1: regs= stack= before 17: (b7) r0 = 0") __msg("mark_precise: frame1: regs= stack= before 10: (85) call bpf_loop#181") __msg("mark_precise: frame0: parent state regs= stack=:") From 593c8eb0fb91a24c39244a7f9e7d04412d750544 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Fri, 4 Sep 2026 17:05:53 -0700 Subject: [PATCH 0717/1198] selftests/bpf: precision of a NULL helper argument Check that mark_chain_precision() is called for a NULL nullable memory argument and for the zero flags argument of bpf_get_local_storage(). Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260904-register-is-null-precise-fixes-v1-2-0f5a360ff15d@gmail.com Signed-off-by: Alexei Starovoitov --- .../bpf/progs/verifier_cgroup_storage.c | 29 ++++++++++++++++ .../selftests/bpf/progs/verifier_precision.c | 34 +++++++++++++++++++ 2 files changed, 63 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/verifier_cgroup_storage.c b/tools/testing/selftests/bpf/progs/verifier_cgroup_storage.c index 9a13f5c11ac7..884080a5bffc 100644 --- a/tools/testing/selftests/bpf/progs/verifier_cgroup_storage.c +++ b/tools/testing/selftests/bpf/progs/verifier_cgroup_storage.c @@ -305,4 +305,33 @@ __naked void cpu_cgroup_storage_access_6(void) : __clobber_all); } +/* + * Verification takes two paths: with r2 being scalar zero on path (1) + * and with r2 being some other scalar on path (2). + * Check that the verifier does not use checkpoints created + * on path (1) to prune path (2). + */ +SEC("cgroup/skb") +__failure +__flag(BPF_F_TEST_STATE_FREQ) +__msg("get_local_storage() doesn't support non-zero flags") +__naked void non_zero_flags_on_a_pruned_path(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + /* r2 is 0 on the path explored first, 1 on the other */\ + r2 = 1; \ + if r0 == 0 goto 1f; \ + r2 = 0; \ +1: r1 = %[cgroup_storage] ll; \ + call %[bpf_get_local_storage]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32), + __imm(bpf_get_local_storage), + __imm_addr(cgroup_storage) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_precision.c b/tools/testing/selftests/bpf/progs/verifier_precision.c index 6f325876efdd..3e290b07f672 100644 --- a/tools/testing/selftests/bpf/progs/verifier_precision.c +++ b/tools/testing/selftests/bpf/progs/verifier_precision.c @@ -642,4 +642,38 @@ __naked int bpf_atomic_cmpxchg_32bit_precision(void) : __clobber_all); } +/* + * Verification takes two paths: with r1 being scalar zero on path (1) + * and with r1 being some other scalar on path (2). + * Check that the verifier does not use checkpoints created + * on path (1) to prune path (2). + */ +SEC("?tc") +__flag(BPF_F_TEST_STATE_FREQ) +__failure __msg("R1 type=scalar expected=fp") +__naked int null_mem_arg_zero_size(void) +{ + asm volatile ( + "call %[bpf_get_prandom_u32];" + "r1 = 42;" + "if r0 > 42 goto 1f;" + "r1 = 0;" + "1:" + "r2 = 0;" + "r3 = 0;" + "r4 = 0;" + "r5 = 0;" + /* + * ARG_PTR_TO_MEM | PTR_MAYBE_NULL parameter can be NULL, + * but can't be some other scalar value. + */ + "call %[bpf_csum_diff];" + "r0 = 0;" + "exit;" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_csum_diff) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; From f1e418129f2ebb5376df2f1cd19720fa80f8adb4 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Fri, 4 Sep 2026 17:05:54 -0700 Subject: [PATCH 0718/1198] bpf: mark a NULL memory argument of a call precise check_mem_reg() allows bpf_register_is_null() for nullable arguments w/o marking the underlying scalar register precise. Hence a checkpoint created on such a path would prune against arbitrary scalar value. The argument may live on the stack rather than in a register when a call has more than MAX_BPF_FUNC_REG_ARGS arguments, hence the new mark_arg_precision() helper. Fixes: e5069b9c23b3 ("bpf: Support pointers in global func args") Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260904-register-is-null-precise-fixes-v1-3-0f5a360ff15d@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index b107f551a62d..7926e131b1cb 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4246,6 +4246,15 @@ static int mark_stack_arg_precision(struct bpf_verifier_env *env, int arg_idx) return mark_chain_precision_batch(env, env->cur_state); } +static int mark_arg_precision(struct bpf_verifier_env *env, argno_t argno) +{ + int regno = reg_from_argno(argno); + + if (regno >= 0) + return mark_chain_precision(env, regno); + return mark_stack_arg_precision(env, arg_idx_from_argno(argno)); +} + static int check_outgoing_stack_args(struct bpf_verifier_env *env, struct bpf_func_state *caller, int nargs, const char *callee_name, const struct btf *btf, const struct btf_param *args) @@ -7175,7 +7184,7 @@ static int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg int size, err = 0; if (bpf_register_is_null(reg)) - return 0; + return mark_arg_precision(env, argno); if (known_memory) *known_memory = true; From 100f4cc0d59be88d2b4d6eb42e51910ea2548d04 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Fri, 4 Sep 2026 17:05:55 -0700 Subject: [PATCH 0719/1198] selftests/bpf: precision of a NULL global subprogram memory argument Check that mark_chain_precision() is called for a NULL pointer passed as a nullable pointer argument of a global subprogram. (Pointer arguments of the global subprograms are nullable by default). Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260904-register-is-null-precise-fixes-v1-4-0f5a360ff15d@gmail.com Signed-off-by: Alexei Starovoitov --- .../selftests/bpf/progs/verifier_precision.c | 32 +++++++++++++++++++ 1 file changed, 32 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/verifier_precision.c b/tools/testing/selftests/bpf/progs/verifier_precision.c index 3e290b07f672..fb7dfa1246ef 100644 --- a/tools/testing/selftests/bpf/progs/verifier_precision.c +++ b/tools/testing/selftests/bpf/progs/verifier_precision.c @@ -676,4 +676,36 @@ __naked int null_mem_arg_zero_size(void) : __clobber_all); } +__weak int subprog_mem_arg(int *p) +{ + if (p) + return *p; + return 0; +} + +/* + * Verification takes two paths: with r1 being scalar zero on path (1) + * and with r1 being some other scalar on path (2). + * Check that the verifier does not use checkpoints created + * on path (1) to prune path (2). + */ +SEC("?raw_tp") +__flag(BPF_F_TEST_STATE_FREQ) +__failure __msg("R1 type=scalar expected=fp") +__naked int null_mem_arg_global_subprog(void) +{ + asm volatile ( + "call %[bpf_get_prandom_u32];" + "r1 = 42;" + "if r0 > 42 goto 1f;" + "r1 = 0;" + "1:" + "call subprog_mem_arg;" + "r0 = 0;" + "exit;" + : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; From 506ada89629ec7059b96ecfb0dc7d33ece0103ca Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Fri, 4 Sep 2026 17:05:56 -0700 Subject: [PATCH 0720/1198] bpf: mark a NULL kfunc argument precise check_kfunc_arg() allows bpf_register_is_null() for nullable arguments w/o marking the underlying scalar register precise. Hence a checkpoint created on such a path would prune against arbitrary scalar value. Fixes: 3bda08b63670 ("bpf: Allow NULL buffers in bpf_dynptr_slice(_rw)") Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260904-register-is-null-precise-fixes-v1-5-0f5a360ff15d@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 7926e131b1cb..2117c39ac332 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -12733,8 +12733,12 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_call_arg_me if (reg_is_referenced(env, reg)) update_ref_obj(&meta->ref_obj, reg); - if (bpf_register_is_null(reg) && type_may_be_null(kf_arg_type)) + if (bpf_register_is_null(reg) && type_may_be_null(kf_arg_type)) { + ret = mark_arg_precision(env, argno); + if (ret) + return ret; continue; + } if (is_kfunc_arg_map(btf, &args[i])) { ref_id = *reg2btf_ids[CONST_PTR_TO_MAP]; From 562d266d3fae571617e72417753df648db261c56 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Fri, 4 Sep 2026 17:05:57 -0700 Subject: [PATCH 0721/1198] selftests/bpf: precision of a NULL kfunc argument Check that mark_chain_precision() is called for a NULL pointer passed as a __nullable kfunc memory argument. Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260904-register-is-null-precise-fixes-v1-6-0f5a360ff15d@gmail.com Signed-off-by: Alexei Starovoitov --- .../selftests/bpf/progs/verifier_precision.c | 34 +++++++++++++++++++ 1 file changed, 34 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/verifier_precision.c b/tools/testing/selftests/bpf/progs/verifier_precision.c index fb7dfa1246ef..f4459561bf39 100644 --- a/tools/testing/selftests/bpf/progs/verifier_precision.c +++ b/tools/testing/selftests/bpf/progs/verifier_precision.c @@ -2,8 +2,10 @@ /* Copyright (C) 2023 SUSE LLC */ #include #include +#include #include "../../../include/linux/filter.h" #include "bpf_misc.h" +#include "bpf_kfuncs.h" struct { __uint(type, BPF_MAP_TYPE_ARRAY); @@ -708,4 +710,36 @@ __naked int null_mem_arg_global_subprog(void) : __clobber_all); } +/* Same as above, check that path with r3 == 0 does not prune the path with r3 != 0 */ +SEC("?tc") +__flag(BPF_F_TEST_STATE_FREQ) +__failure __msg("R3 type=scalar expected=fp") +int null_kfunc_arg_dynptr_slice(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr; + + bpf_dynptr_from_skb(skb, 0, &ptr); + asm volatile ( + "call %[bpf_get_prandom_u32];" + "r3 = 42;" + "if r0 > 42 goto 1f;" + "r3 = 0;" + "1:" + "r1 = %[ptr];" + "r2 = 0;" + "r4 = 8;" + "call %[bpf_dynptr_slice];" + : + : __imm_ptr(ptr), + __imm(bpf_get_prandom_u32), + __imm(bpf_dynptr_slice) + : __clobber_common); + return 0; +} + +void __kfunc_btf_root(void) +{ + bpf_dynptr_slice(0, 0, 0, 0); +} + char _license[] SEC("license") = "GPL"; From e726fc6b9afe6b3a446a31d0f0767b7b9cb5085e Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Fri, 4 Sep 2026 17:05:58 -0700 Subject: [PATCH 0722/1198] bpf: mark a NULL BTF_ID argument of a global subprogram precise btf_check_func_arg_match() accepts a NULL register for an ARG_PTR_TO_BTF_ID argument tagged __arg_nullable and skips check_reg_type() and check_func_arg_reg_off() without marking the register precise. Hence a checkpoint created on such a path would prune against arbitrary scalar value. Fixes: e2b3c4ff5d18 ("bpf: add __arg_trusted global func arg tag") Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260904-register-is-null-precise-fixes-v1-7-0f5a360ff15d@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 2117c39ac332..1b9fcbe4621a 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -9774,8 +9774,12 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog, struct bpf_call_arg_meta meta; int err; - if (bpf_register_is_null(reg) && type_may_be_null(arg->arg_type)) + if (bpf_register_is_null(reg) && type_may_be_null(arg->arg_type)) { + err = mark_arg_precision(env, argno); + if (err) + return err; continue; + } memset(&meta, 0, sizeof(meta)); /* leave func_id as zero */ err = check_reg_type(env, reg, argno, arg->arg_type, &arg->btf_id, &meta, From 91957791663f49561848c40e982061799b8f86b0 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Fri, 4 Sep 2026 17:05:59 -0700 Subject: [PATCH 0723/1198] selftests/bpf: precision of a NULL global subprogram BTF_ID argument Check that mark_chain_precision() is called for a NULL pointer passed as an __arg_trusted __arg_nullable argument of a global subprogram. Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260904-register-is-null-precise-fixes-v1-8-0f5a360ff15d@gmail.com Signed-off-by: Alexei Starovoitov --- .../bpf/progs/verifier_global_ptr_args.c | 24 +++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c b/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c index 0bdeb7bc4687..a3d2af8dc839 100644 --- a/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c +++ b/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c @@ -56,6 +56,30 @@ int trusted_task_arg_nullable(void *ctx) return res; } +/* + * Check that the verifier does not use checkpoints created + * on path with r1 == 0 to prune path with r1 != 0. + */ +SEC("?tp_btf/task_newtask") +__failure +__flag(BPF_F_TEST_STATE_FREQ) +__msg("R1 type=scalar expected=ptr_, trusted_ptr_, rcu_ptr_") +__naked int null_btf_id_arg_global_subprog(void) +{ + asm volatile ( + "call %[bpf_get_prandom_u32];" + "r1 = 42;" + "if r0 > 42 goto 1f;" + "r1 = 0;" + "1:" + "call subprog_trusted_task_nullable;" + "r0 = 0;" + "exit;" + : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + __weak int subprog_trusted_task_nonnull(struct task_struct *task __arg_trusted) { return task->pid + task->tgid; From 1d7f8f191c06f967a85922c4652dc33c132b585d Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Fri, 4 Sep 2026 17:06:00 -0700 Subject: [PATCH 0724/1198] bpf: propagate mark_chain_precision() errors out of loop_flag_is_zero() Stop verification if mark_chain_precision() fails when called from loop_flag_is_zero(). No functional change intended for the paths where backtracking succeeds. Fixes: 1ade23711971 ("bpf: Inline calls to bpf_loop when callback is known") Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260904-register-is-null-precise-fixes-v1-9-0f5a360ff15d@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 36 +++++++++++++++++++++++++----------- 1 file changed, 25 insertions(+), 11 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1b9fcbe4621a..e8af1d3dbdeb 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -10702,33 +10702,45 @@ static struct bpf_insn_aux_data *cur_aux(const struct bpf_verifier_env *env) return &env->insn_aux_data[env->insn_idx]; } -static bool loop_flag_is_zero(struct bpf_verifier_env *env) +/* Returns 1 if R4 is a known zero, 0 if it is not, a negative errno on error. */ +static int loop_flag_is_zero(struct bpf_verifier_env *env) { struct bpf_reg_state *reg = reg_state(env, BPF_REG_4); - bool reg_is_null = bpf_register_is_null(reg); + int err; - if (reg_is_null) - mark_chain_precision(env, BPF_REG_4); + if (!bpf_register_is_null(reg)) + return 0; - return reg_is_null; + err = mark_chain_precision(env, BPF_REG_4); + if (err) + return err; + return 1; } -static void update_loop_inline_state(struct bpf_verifier_env *env, u32 subprogno) +static int update_loop_inline_state(struct bpf_verifier_env *env, u32 subprogno) { struct bpf_loop_inline_state *state = &cur_aux(env)->loop_inline_state; + int flag_is_zero; if (!state->initialized) { + flag_is_zero = loop_flag_is_zero(env); + if (flag_is_zero < 0) + return flag_is_zero; state->initialized = 1; - state->fit_for_inline = loop_flag_is_zero(env); + state->fit_for_inline = flag_is_zero; state->callback_subprogno = subprogno; - return; + return 0; } if (!state->fit_for_inline) - return; + return 0; - state->fit_for_inline = (loop_flag_is_zero(env) && + flag_is_zero = loop_flag_is_zero(env); + if (flag_is_zero < 0) + return flag_is_zero; + state->fit_for_inline = (flag_is_zero && state->callback_subprogno == subprogno); + return 0; } /* Returns whether or not the given map can potentially elide @@ -10960,7 +10972,9 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn err = check_bpf_snprintf_call(env, regs); break; case BPF_FUNC_loop: - update_loop_inline_state(env, meta.subprogno); + err = update_loop_inline_state(env, meta.subprogno); + if (err) + return err; /* Verifier relies on R1 value to determine if bpf_loop() iteration * is finished, thus mark it precise. */ From cf2475616b11c0efefdd969d42913f56ca39f918 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Fri, 4 Sep 2026 17:06:01 -0700 Subject: [PATCH 0725/1198] bpf: use mark_arg_precision() in check_mem_size_reg() Use newly added mark_arg_precision() helper in check_mem_size_reg(). Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260904-register-is-null-precise-fixes-v1-10-0f5a360ff15d@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e8af1d3dbdeb..1c3039f3fc32 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -7160,14 +7160,8 @@ static int check_mem_size_reg(struct bpf_verifier_env *env, if (err && failure) *failure = BPF_MEM_SIZE_FAIL_MEMORY; - if (!err) { - int regno = reg_from_argno(size_argno); - - if (regno >= 0) - err = mark_chain_precision(env, regno); - else - err = mark_stack_arg_precision(env, arg_idx_from_argno(size_argno)); - } + if (!err) + err = mark_arg_precision(env, size_argno); return err; From 80dd7e754b3aa9637a0758ad93fa209f9650ec48 Mon Sep 17 00:00:00 2001 From: Sahil Chandna Date: Tue, 1 Sep 2026 07:17:58 -0500 Subject: [PATCH 0726/1198] net: mana: Reserve extra CQ slot for the fence completion CQE The RX completion queue is sized to hold exactly one CQE per posted RX WQE. MANA_FENCE_RQ makes hardware post an additional CQE_RX_OBJECT_FENCE after the packet CQEs. The current sizing reserves no extra slot for it and in rare cases, CQ has no guaranteed slot for the fence CQE when it is full of packet CQEs. This can lead to dropping the fence completion while the driver waits holding RTNL lock throughout the timeout duration. Reserve one extra CQE slot for CQE_RX_OBJECT_FENCE. mana_gd_alloc_memory() requires queue_size to be a power-of-two and at least MANA_PAGE_SIZE; the reservation pushes cq_size past a power-of-two, so round up the CQ size in mana_create_rxq(). Cc: stable@vger.kernel.org Fixes: 6cc74443a773 ("net: mana: Add RX fencing") Signed-off-by: Sahil Chandna Reviewed-by: Haiyang Zhang Link: https://patch.msgid.link/20260901121837.3503240-1-sahilchandna@linux.microsoft.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/microsoft/mana/mana_en.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 7a1ac853e3ab..45a7520491a6 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -2986,6 +2986,10 @@ static int mana_alloc_rx_wqe(struct mana_port_context *apc, *cq_size += COMP_ENTRY_SIZE; } + /* Reserve an extra slot for Fence completion + * event (CQE_RX_OBJECT_FENCE) in case RX CQ is full. + */ + *cq_size += COMP_ENTRY_SIZE; return 0; } @@ -3080,7 +3084,7 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, goto out; rq_size = MANA_PAGE_ALIGN(rq_size); - cq_size = MANA_PAGE_ALIGN(cq_size); + cq_size = MANA_PAGE_ALIGN(roundup_pow_of_two(cq_size)); /* Create RQ */ memset(&spec, 0, sizeof(spec)); From 3a2c4d55e32ad65efebdb6de44eef3bfa08bb49d Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 2 Sep 2026 15:31:14 -0700 Subject: [PATCH 0727/1198] treewide: refresh kmalloc_obj() conversions This is another run of the Coccinelle script for converting kmalloc() family of allocations to kmalloc_obj() via the existing rules in scripts/coccinelle/api/kmalloc_objs.cocci This catches both the set of kmalloc() uses added since the first kmalloc_obj() conversions in v7.0 and adds a large group missed in the first pass due to Coccinelle not interacting well with the cleanup.h scoped_...() family of macros[1]. I worked around this with spatch's "--macro-file" argument to a file with all the scoped_...() macros mapped to Coccinelle's YACFE_ITERATOR[2] as that was the closest viable control flow indicator I could find. Build tested allmodconfig on x86, arm64, arm, loongarch, mips, powerpc, riscv, and s390 with no new warnings. Link: https://lore.kernel.org/lkml/202609021314.8A9C0B8@keescook/ [1] Link: https://github.com/coccinelle/coccinelle/blob/master/standard.h [2] Signed-off-by: Kees Cook --- arch/arm64/crypto/aes-neonbs-glue.c | 4 +- arch/arm64/kvm/nested.c | 2 +- arch/loongarch/kvm/intc/dmsintc.c | 2 +- arch/mips/bcm47xx/buttons.c | 8 +-- arch/powerpc/sysdev/xive/common.c | 2 +- arch/riscv/kvm/vcpu_pmu.c | 4 +- arch/s390/kvm/s390/s390.c | 4 +- drivers/accel/rocket/rocket_job.c | 2 +- drivers/acpi/irq.c | 8 +-- drivers/base/property.c | 2 +- drivers/block/drbd/drbd_nl_gen.c | 40 +++++++------- drivers/block/ublk_drv.c | 4 +- drivers/block/zram/backend_lz4.c | 2 +- drivers/clk/ti/composite.c | 2 +- drivers/clk/ti/mux.c | 2 +- drivers/cpufreq/amd-pstate.c | 2 +- .../crypto/inside-secure/eip93/eip93-common.c | 5 +- .../intel/qat/qat_common/qat_comp_algs.c | 3 +- drivers/crypto/ti/dthev2-aes.c | 8 +-- drivers/devfreq/hisi_uncore_freq.c | 2 +- drivers/dma-buf/st-dma-fence.c | 2 +- drivers/dma-buf/udmabuf.c | 4 +- drivers/dma/switchtec_dma.c | 7 ++- drivers/edac/versalnet_edac.c | 2 +- drivers/firmware/arm_scmi/driver.c | 2 +- drivers/firmware/qcom/qcom_tzmem.c | 8 ++- drivers/firmware/ti_sci.c | 2 +- drivers/fpga/dfl-afu-dma-region.c | 2 +- drivers/gpio/gpio-aggregator.c | 4 +- drivers/gpio/gpio-mpsse.c | 2 +- drivers/gpio/gpio-sim.c | 3 +- drivers/gpio/gpio-virtuser.c | 3 +- drivers/gpio/gpiolib-cdev.c | 2 +- drivers/gpio/gpiolib.c | 4 +- drivers/gpu/buddy.c | 13 ++--- .../gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c | 5 +- drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c | 4 +- drivers/gpu/drm/amd/amdgpu/amdgpu_lockdep.c | 2 +- .../gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 5 +- drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c | 4 +- .../gpu/drm/amd/amdgpu/amdgpu_userq_fence.c | 6 +-- drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 6 +-- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 12 ++--- .../tests/amdgpu_dm_connector_test.c | 2 +- .../amdgpu_dm/tests/amdgpu_dm_crtc_test.c | 8 +-- .../amdgpu_dm/tests/amdgpu_dm_irq_test.c | 18 +++---- .../amdgpu_dm/tests/amdgpu_dm_plane_test.c | 4 +- .../display/amdgpu_dm/tests/amdgpu_dm_test.c | 2 +- .../gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c | 2 +- .../display/dc/clk_mgr/dcn60/dcn60_clk_mgr.c | 4 +- drivers/gpu/drm/amd/display/dc/core/dc.c | 3 +- .../gpu/drm/amd/display/dc/core/dc_surface.c | 2 +- .../amd/display/dc/dccg/dcn42/dcn42_dccg.c | 2 +- .../amd/display/dc/dccg/dcn60/dcn60_dccg.c | 2 +- drivers/gpu/drm/amd/display/dc/gpio/hw_ddc.c | 2 +- .../display/dc/irq/dcn42/irq_service_dcn42.c | 2 +- .../display/dc/irq/dcn60/irq_service_dcn60.c | 3 +- .../amd/display/dc/pg/dcn42/dcn42_pg_cntl.c | 2 +- .../dc/resource/dcn30/dcn30_resource.c | 4 +- .../dc/resource/dcn302/dcn302_resource.c | 4 +- .../dc/resource/dcn303/dcn303_resource.c | 4 +- .../dc/resource/dcn31/dcn31_resource.c | 4 +- .../dc/resource/dcn314/dcn314_resource.c | 4 +- .../dc/resource/dcn315/dcn315_resource.c | 4 +- .../dc/resource/dcn316/dcn316_resource.c | 4 +- .../dc/resource/dcn32/dcn32_resource.c | 4 +- .../dc/resource/dcn321/dcn321_resource.c | 4 +- .../dc/resource/dcn35/dcn35_resource.c | 4 +- .../dc/resource/dcn351/dcn351_resource.c | 4 +- .../dc/resource/dcn36/dcn36_resource.c | 4 +- .../dc/resource/dcn401/dcn401_resource.c | 4 +- .../dc/resource/dcn42/dcn42_resource.c | 50 ++++++++---------- .../dc/resource/dcn42b/dcn42b_resource.c | 46 ++++++++-------- .../dc/resource/dcn60/dcn60_resource.c | 42 +++++++-------- .../gpu/drm/amd/display/modules/power/power.c | 5 +- .../drm/amd/display/modules/power/power_abm.c | 3 +- .../drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c | 2 +- .../drm/amd/pm/swsmu/smu15/smu_v15_0_8_ppt.c | 4 +- drivers/gpu/drm/amd/ras/core/cmd.c | 4 +- drivers/gpu/drm/drm_exec.c | 2 +- drivers/gpu/drm/drm_syncobj.c | 2 +- drivers/gpu/drm/qxl/qxl_display.c | 2 +- drivers/gpu/drm/tilcdc/tilcdc_panel_legacy.c | 2 +- drivers/gpu/drm/verisilicon/vs_plane.c | 4 +- drivers/gpu/drm/virtio/virtgpu_prime.c | 4 +- drivers/gpu/drm/vkms/vkms_configfs.c | 8 +-- drivers/gpu/drm/xe/xe_amc.c | 2 +- drivers/gpu/drm/xe/xe_vm.c | 2 +- drivers/hid/hid-asus.c | 6 +-- drivers/hid/hid-steam.c | 4 +- drivers/hid/hid-steelseries-arctis.c | 2 +- drivers/hv/channel.c | 5 +- drivers/hv/hv_balloon.c | 2 +- drivers/hwmon/applesmc.c | 17 +++--- drivers/hwtracing/coresight/coresight-core.c | 2 +- drivers/i2c/busses/i2c-gpio.c | 2 +- drivers/i3c/master/amd-i3c-master.c | 4 +- drivers/iio/adc/ad7280a.c | 4 +- .../buffer/industrialio-buffer-dmaengine.c | 2 +- drivers/iio/inkern.c | 2 +- drivers/infiniband/core/nldev.c | 2 +- drivers/infiniband/hw/hns/hns_roce_debugfs.c | 3 +- drivers/input/input.c | 2 +- drivers/input/keyboard/adp5585-keys.c | 4 +- drivers/input/keyboard/atkbd.c | 2 +- drivers/input/misc/ims-pcu.c | 2 +- drivers/input/mouse/psmouse-smbus.c | 2 +- drivers/input/serio/serio_raw.c | 2 +- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 2 +- drivers/iommu/iommufd/device.c | 2 +- drivers/iommu/iommufd/driver.c | 2 +- drivers/iommu/iommufd/hwpt_noiommu.c | 2 +- drivers/iommu/vsi-iommu.c | 2 +- drivers/irqchip/irq-gic-v5-irs.c | 2 +- drivers/irqchip/irq-loongarch-ir.c | 2 +- drivers/irqchip/irq-realtek-rtl.c | 2 +- drivers/mailbox/riscv-sbi-mpxy-mbox.c | 2 +- drivers/md/dm-inlinecrypt.c | 2 +- drivers/md/md-llbitmap.c | 4 +- .../media/platform/allegro-dvt/allegro-core.c | 2 +- .../media/platform/amd/isp4/isp4_interface.c | 6 +-- .../media/platform/renesas/rcar-isp/core.c | 2 +- drivers/media/rc/igorplugusb.c | 2 +- drivers/mfd/mfd-core.c | 4 +- drivers/mfd/ucb1x00-assabet.c | 2 +- drivers/mtd/mtd_virt_concat.c | 4 +- drivers/mtd/mtdconcat.c | 2 +- drivers/net/dsa/mv88e6xxx/tcflower.c | 2 +- drivers/net/ethernet/alibaba/eea/eea_adminq.c | 7 ++- drivers/net/ethernet/alibaba/eea/eea_net.c | 8 +-- drivers/net/ethernet/alibaba/eea/eea_pci.c | 2 +- drivers/net/ethernet/alibaba/eea/eea_ring.c | 2 +- drivers/net/ethernet/alibaba/eea/eea_rx.c | 5 +- drivers/net/ethernet/alibaba/eea/eea_tx.c | 3 +- drivers/net/ethernet/amd/pds_core/core.c | 3 +- drivers/net/ethernet/amd/pds_core/fw.c | 6 +-- drivers/net/ethernet/cadence/macb_main.c | 2 +- drivers/net/ethernet/cisco/enic/enic_admin.c | 2 +- drivers/net/ethernet/cisco/enic/enic_main.c | 6 +-- .../ethernet/freescale/dpaa2/dpaa2-switch.c | 5 +- drivers/net/ethernet/intel/libie/controlq.c | 3 +- .../ethernet/marvell/octeontx2/af/cn20k/npc.c | 13 ++--- .../net/ethernet/mellanox/mlx5/core/eswitch.c | 3 +- .../mellanox/mlx5/core/eswitch_offloads.c | 2 +- .../ethernet/mellanox/mlx5/core/sf/hw_table.c | 2 +- .../mlx5/core/steering/sws/dr_icm_pool.c | 2 +- drivers/net/ethernet/meta/fbnic/fbnic_irq.c | 2 +- .../net/ethernet/microsoft/mana/gdma_main.c | 8 +-- drivers/net/ntb_netdev.c | 3 +- drivers/net/wireless/ath/ath12k/ahb.c | 2 +- .../wireless/intel/iwlwifi/mld/regulatory.c | 3 +- .../net/wireless/mediatek/mt76/mt7921/regd.c | 2 +- .../net/wireless/mediatek/mt76/mt7925/main.c | 2 +- .../net/wireless/mediatek/mt76/mt7925/regd.c | 2 +- drivers/net/wireless/morsemicro/mm81x/mac.c | 9 ++-- drivers/net/wireless/morsemicro/mm81x/yaps.c | 10 ++-- drivers/net/wireless/nxp/nxpwifi/cfg80211.c | 14 ++--- drivers/net/wireless/nxp/nxpwifi/cmdevt.c | 2 +- drivers/net/wireless/nxp/nxpwifi/ie.c | 14 ++--- drivers/net/wireless/nxp/nxpwifi/init.c | 2 +- drivers/net/wireless/nxp/nxpwifi/main.c | 8 +-- drivers/net/wireless/nxp/nxpwifi/scan.c | 13 +++-- drivers/net/wireless/nxp/nxpwifi/sta_cfg.c | 2 +- drivers/net/wireless/nxp/nxpwifi/sta_cmd.c | 2 +- drivers/net/wireless/nxp/nxpwifi/uap_event.c | 2 +- drivers/nvdimm/region_devs.c | 3 +- drivers/nvme/host/core.c | 3 +- drivers/nvme/host/pci.c | 2 +- drivers/opp/core.c | 4 +- drivers/pci/endpoint/pci-ep-msi.c | 4 +- drivers/platform/x86/amd/hsmp/acpi.c | 5 +- .../x86/hp/hp-bioscfg/enum-attributes.c | 4 +- .../platform/x86/intel/pmc/pwrm_telemetry.c | 3 +- drivers/pmdomain/core.c | 2 +- drivers/power/reset/reboot-mode.c | 6 +-- drivers/power/sequencing/core.c | 2 +- drivers/power/sequencing/pwrseq-pcie-m2.c | 2 +- drivers/power/supply/power_supply_core.c | 6 +-- drivers/ptp/ptp_chardev.c | 2 +- drivers/s390/block/dasd.c | 2 +- drivers/scsi/fnic/fnic_debugfs.c | 2 +- drivers/scsi/leapraid/leapraid_func.c | 52 ++++++++----------- drivers/scsi/scsi_scan.c | 2 +- drivers/soc/bcm/brcmstb/common.c | 2 +- drivers/spi/spi-offload.c | 2 +- drivers/staging/greybus/raw.c | 2 +- drivers/staging/media/atomisp/pci/sh_css.c | 30 ++++------- .../media/atomisp/pci/sh_css_firmware.c | 4 +- drivers/tee/qcomtee/user_obj.c | 3 +- drivers/thunderbolt/stream.c | 12 ++--- drivers/tty/moxa.c | 3 +- drivers/tty/vt/consolemap.c | 3 +- drivers/ufs/core/ufs-txeq.c | 2 +- drivers/ufs/host/ufs-qcom.c | 2 +- drivers/usb/gadget/function/f_ncm.c | 2 +- drivers/usb/usbip/usbip_common.c | 2 +- drivers/xen/grant-table.c | 2 +- fs/9p/vfs_dentry.c | 3 +- fs/afs/dir.c | 2 +- fs/afs/symlink.c | 3 +- fs/binfmt_misc.c | 7 ++- fs/ceph/addr.c | 2 +- fs/ceph/mds_client.c | 2 +- fs/ceph/subvolume_metrics.c | 2 +- fs/coredump.c | 2 +- fs/ext4/fast_commit.c | 4 +- fs/fuse/file.c | 3 +- fs/fuse/readdir.c | 2 +- fs/hfs/bnode.c | 2 +- fs/namespace.c | 2 +- fs/nfsd/export.c | 7 ++- fs/nfsd/nfs4callback.c | 4 +- fs/nfsd/nfs4state.c | 7 +-- fs/nfsd/nfsctl.c | 2 +- fs/ntfs/bitmap.c | 2 +- fs/ntfs/compress.c | 8 +-- fs/ntfs/dir.c | 16 +++--- fs/ntfs/ea.c | 2 +- fs/ntfs/index.c | 2 +- fs/ntfs/logfile.c | 2 +- fs/ntfs/mft.c | 10 ++-- fs/ntfs/runlist.c | 14 ++--- fs/ntfs/super.c | 2 +- fs/overlayfs/readdir.c | 2 +- fs/smb/client/cifs_swn.c | 2 +- fs/smb/client/dfs_cache.c | 2 +- fs/smb/client/smb2inode.c | 2 +- fs/smb/server/ksmbd_work.c | 2 +- fs/smb/server/smb2pdu.c | 2 +- fs/xfs/libxfs/xfs_da_btree.c | 4 +- init/initramfs_test.c | 2 +- io_uring/napi.c | 2 +- io_uring/zcrx.c | 4 +- kernel/bpf/diagnostics.c | 2 +- kernel/bpf/hashtab.c | 2 +- kernel/bpf/liveness.c | 2 +- kernel/bpf/log.c | 2 +- kernel/bpf/verifier.c | 5 +- kernel/dma/map_benchmark.c | 3 +- kernel/events/core.c | 5 +- kernel/futex/core.c | 6 +-- kernel/irq/manage.c | 2 +- kernel/jump_label.c | 5 +- kernel/kthread.c | 2 +- kernel/sched/ext/cid.c | 16 +++--- kernel/sched/ext/ext.c | 2 +- kernel/sched/ext/sub.c | 2 +- kernel/trace/fprobe.c | 2 +- kernel/trace/ring_buffer.c | 4 +- kernel/trace/trace_eprobe.c | 2 +- kernel/trace/trace_remote.c | 10 ++-- lib/test_rhashtable.c | 2 +- lib/test_workqueue.c | 4 +- lib/tests/kunit_iov_iter.c | 2 +- mm/damon/tests/vaddr-kunit.h | 2 +- net/batman-adv/hard-interface.c | 2 +- net/bluetooth/hci_sync.c | 3 +- net/devlink/netlink.c | 2 +- net/devlink/param.c | 7 ++- net/ipv4/tcp_ipv4.c | 4 +- net/mac80211/nan.c | 3 +- net/mctp/test/route-test.c | 2 +- net/mctp/test/utils.c | 2 +- net/netfilter/nf_tables_api.c | 2 +- net/netfilter/nfnetlink_cttimeout.c | 2 +- net/rds/info.c | 2 +- net/rxrpc/key.c | 2 +- net/sched/act_gate.c | 4 +- net/sched/act_tunnel_key.c | 2 +- net/sunrpc/auth_gss/gss_krb5_crypto.c | 5 +- net/sunrpc/svcauth_unix.c | 4 +- net/sunrpc/xdr.c | 3 +- net/unix/af_unix.c | 4 +- net/wireless/core.c | 5 +- net/wireless/nl80211.c | 9 ++-- security/integrity/ima/ima_queue.c | 3 +- sound/core/compress_offload.c | 4 +- sound/core/control.c | 6 +-- sound/core/control_led.c | 2 +- sound/core/init.c | 2 +- sound/core/misc.c | 2 +- sound/core/oss/mixer_oss.c | 2 +- sound/core/pcm_native.c | 2 +- sound/core/seq/oss/seq_oss_synth.c | 2 +- sound/core/seq/seq_clientmgr.c | 2 +- sound/core/seq/seq_virmidi.c | 2 +- sound/core/timer.c | 2 +- sound/drivers/aloop.c | 4 +- sound/isa/gus/gus_dma.c | 2 +- sound/pci/cs46xx/cs46xx_lib.c | 2 +- sound/pci/ctxfi/ctamixer.c | 4 +- sound/pci/ctxfi/ctdaio.c | 4 +- sound/pci/ctxfi/ctsrc.c | 4 +- sound/pci/ctxfi/cttimer.c | 2 +- sound/pci/emu10k1/emufx.c | 2 +- sound/soc/codecs/simple-amplifier.c | 2 +- sound/soc/generic/simple-card-utils.c | 2 +- sound/soc/meson/gx-formatter.c | 2 +- sound/soc/qcom/qdsp6/q6afe.c | 2 +- sound/soc/sdca/sdca_functions.c | 19 ++++--- sound/soc/sof/sof-client-probes-ipc4.c | 2 +- sound/soc/sof/sof-client.c | 2 +- sound/sparc/amd7930.c | 2 +- 304 files changed, 637 insertions(+), 726 deletions(-) diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c index 5bcbac979893..7cb1aede9a48 100644 --- a/arch/arm64/crypto/aes-neonbs-glue.c +++ b/arch/arm64/crypto/aes-neonbs-glue.c @@ -66,7 +66,7 @@ static int aesbs_setkey(struct crypto_skcipher *tfm, const u8 *in_key, struct crypto_aes_ctx *rk; int err; - rk = kmalloc(sizeof(*rk), GFP_KERNEL); + rk = kmalloc_obj(*rk); if (!rk) return -ENOMEM; @@ -128,7 +128,7 @@ static int aesbs_cbc_ctr_setkey(struct crypto_skcipher *tfm, const u8 *in_key, struct crypto_aes_ctx *rk; int err; - rk = kmalloc(sizeof(*rk), GFP_KERNEL); + rk = kmalloc_obj(*rk); if (!rk) return -ENOMEM; diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c index 17123f0b6dab..3c4fc566eafc 100644 --- a/arch/arm64/kvm/nested.c +++ b/arch/arm64/kvm/nested.c @@ -93,7 +93,7 @@ int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu) num_mmus = atomic_read(&kvm->online_vcpus) * S2_MMU_PER_VCPU; if (num_mmus > kvm->arch.nested_mmus_size) { - tmp = kvcalloc(num_mmus, sizeof(*tmp), GFP_KERNEL_ACCOUNT); + tmp = kvzalloc_objs(*tmp, num_mmus, GFP_KERNEL_ACCOUNT); if (!tmp) return -ENOMEM; diff --git a/arch/loongarch/kvm/intc/dmsintc.c b/arch/loongarch/kvm/intc/dmsintc.c index bb7285c49df3..5518cafada55 100644 --- a/arch/loongarch/kvm/intc/dmsintc.c +++ b/arch/loongarch/kvm/intc/dmsintc.c @@ -149,7 +149,7 @@ static int kvm_dmsintc_create(struct kvm_device *dev, u32 type) return -EINVAL; } - s = kzalloc(sizeof(struct loongarch_dmsintc), GFP_KERNEL); + s = kzalloc_obj(struct loongarch_dmsintc); if (!s) return -ENOMEM; diff --git a/arch/mips/bcm47xx/buttons.c b/arch/mips/bcm47xx/buttons.c index 151a4ee2803f..7bb338da8e42 100644 --- a/arch/mips/bcm47xx/buttons.c +++ b/arch/mips/bcm47xx/buttons.c @@ -523,24 +523,24 @@ bcm47xx_buttons_add(const struct bcm47xx_gpio_key *buttons, int nbuttons) /* 1 node for gpio-keys device, 1 node for each button, 1 terminator */ const struct software_node **node_group __free(kfree) = - kcalloc(1 + nbuttons + 1, sizeof(*node_group), GFP_KERNEL); + kzalloc_objs(*node_group, 1 + nbuttons + 1); if (!node_group) return -ENOMEM; /* 1 code property, 1 gpio property, 1 terminator */ struct property_entry *props __free(kfree) = - kcalloc(nbuttons * 3, sizeof(*props), GFP_KERNEL); + kzalloc_objs(*props, nbuttons * 3); if (!props) return -ENOMEM; /* 1 node for gpio-keys device, 1 node for each button */ struct software_node *nodes __free(kfree) = - kcalloc(1 + nbuttons, sizeof(*nodes), GFP_KERNEL); + kzalloc_objs(*nodes, 1 + nbuttons); if (!nodes) return -ENOMEM; struct software_node_ref_args *ref_args __free(kfree) = - kcalloc(nbuttons, sizeof(*ref_args), GFP_KERNEL); + kzalloc_objs(*ref_args, nbuttons); if (!ref_args) return -ENOMEM; diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index 8ae088632337..ed3d3e26c136 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -1134,7 +1134,7 @@ static int __init xive_init_ipis(void) if (!ipi_domain) goto out_free_fwnode; - xive_ipis = kzalloc_objs(*xive_ipis, nr_node_ids, GFP_KERNEL); + xive_ipis = kzalloc_objs(*xive_ipis, nr_node_ids); if (!xive_ipis) goto out_free_domain; diff --git a/arch/riscv/kvm/vcpu_pmu.c b/arch/riscv/kvm/vcpu_pmu.c index 752f1014d633..6ff741ee7803 100644 --- a/arch/riscv/kvm/vcpu_pmu.c +++ b/arch/riscv/kvm/vcpu_pmu.c @@ -503,8 +503,8 @@ int kvm_riscv_vcpu_pmu_event_info(struct kvm_vcpu *vcpu, unsigned long saddr_low } } - einfo = kvcalloc(num_events, sizeof(*einfo), - GFP_KERNEL_ACCOUNT | __GFP_NOWARN); + einfo = kvzalloc_objs(*einfo, num_events, + GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (!einfo) { ret = SBI_ERR_FAILURE; goto out; diff --git a/arch/s390/kvm/s390/s390.c b/arch/s390/kvm/s390/s390.c index b0839e887221..5c73f43782a7 100644 --- a/arch/s390/kvm/s390/s390.c +++ b/arch/s390/kvm/s390/s390.c @@ -2168,7 +2168,7 @@ static int kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) if (args->count < 1 || args->count > KVM_S390_SKEYS_MAX) return -EINVAL; - keys = kvmalloc_array(args->count, sizeof(*keys), GFP_KERNEL_ACCOUNT); + keys = kvmalloc_objs(*keys, args->count, GFP_KERNEL_ACCOUNT); if (!keys) return -ENOMEM; @@ -2205,7 +2205,7 @@ static int kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) if (args->count < 1 || args->count > KVM_S390_SKEYS_MAX) return -EINVAL; - keys = kvmalloc_array(args->count, sizeof(*keys), GFP_KERNEL_ACCOUNT); + keys = kvmalloc_objs(*keys, args->count, GFP_KERNEL_ACCOUNT); if (!keys) return -ENOMEM; diff --git a/drivers/accel/rocket/rocket_job.c b/drivers/accel/rocket/rocket_job.c index 3141f210fcd1..f40435505818 100644 --- a/drivers/accel/rocket/rocket_job.c +++ b/drivers/accel/rocket/rocket_job.c @@ -196,7 +196,7 @@ static int rocket_job_push(struct rocket_job *job) if (check_add_overflow(job->in_bo_count, job->out_bo_count, &bo_count)) return -EINVAL; - bos = kvmalloc_array(bo_count, sizeof(*bos), GFP_KERNEL); + bos = kvmalloc_objs(*bos, bo_count); if (!bos) return -ENOMEM; memcpy(bos, job->in_bos, job->in_bo_count * sizeof(void *)); diff --git a/drivers/acpi/irq.c b/drivers/acpi/irq.c index e4293458bf61..a670722ddd5a 100644 --- a/drivers/acpi/irq.c +++ b/drivers/acpi/irq.c @@ -486,7 +486,8 @@ static u32 acpi_add_prt_dep(acpi_handle handle) if (ACPI_FAILURE(status)) continue; dep_devices.count = 1; - dep_devices.handles = kcalloc(1, sizeof(*dep_devices.handles), GFP_KERNEL); + dep_devices.handles = kzalloc_objs(*dep_devices.handles, + 1); if (!dep_devices.handles) { acpi_handle_err(handle, "failed to allocate memory\n"); continue; @@ -499,7 +500,8 @@ static u32 acpi_add_prt_dep(acpi_handle handle) if (!gsi_handle) continue; dep_devices.count = 1; - dep_devices.handles = kcalloc(1, sizeof(*dep_devices.handles), GFP_KERNEL); + dep_devices.handles = kzalloc_objs(*dep_devices.handles, + 1); if (!dep_devices.handles) { acpi_handle_err(handle, "failed to allocate memory\n"); continue; @@ -526,7 +528,7 @@ static u32 acpi_add_irq_dep(acpi_handle handle) continue; dep_devices.count = 1; - dep_devices.handles = kcalloc(1, sizeof(*dep_devices.handles), GFP_KERNEL); + dep_devices.handles = kzalloc_objs(*dep_devices.handles, 1); if (!dep_devices.handles) { acpi_handle_err(handle, "failed to allocate memory\n"); continue; diff --git a/drivers/base/property.c b/drivers/base/property.c index b136c339ddae..cceaa3240ca4 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -526,7 +526,7 @@ int fwnode_property_match_string(const struct fwnode_handle *fwnode, if (nval == 0) return -ENODATA; - const char **values __free(kfree) = kcalloc(nval, sizeof(*values), GFP_KERNEL); + const char **values __free(kfree) = kzalloc_objs(*values, nval); if (!values) return -ENOMEM; diff --git a/drivers/block/drbd/drbd_nl_gen.c b/drivers/block/drbd/drbd_nl_gen.c index fb44b948cec8..9753dc789bde 100644 --- a/drivers/block/drbd/drbd_nl_gen.c +++ b/drivers/block/drbd/drbd_nl_gen.c @@ -656,7 +656,7 @@ static int __drbd_cfg_context_from_attrs(struct drbd_cfg_context *s, *ret_nested_attribute_table = NULL; if (!tla) return -ENOMSG; - ntb = kcalloc(DRBD_A_DRBD_CFG_CONTEXT_CTX_PEER_ADDR + 1, sizeof(*ntb), GFP_KERNEL); + ntb = kzalloc_objs(*ntb, DRBD_A_DRBD_CFG_CONTEXT_CTX_PEER_ADDR + 1); if (!ntb) return -ENOMEM; err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_drbd_cfg_context_nl_policy, NULL); @@ -714,7 +714,7 @@ static int __disk_conf_from_attrs(struct disk_conf *s, *ret_nested_attribute_table = NULL; if (!tla) return -ENOMSG; - ntb = kcalloc(DRBD_A_DISK_CONF_DISABLE_WRITE_SAME + 1, sizeof(*ntb), GFP_KERNEL); + ntb = kzalloc_objs(*ntb, DRBD_A_DISK_CONF_DISABLE_WRITE_SAME + 1); if (!ntb) return -ENOMEM; err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_disk_conf_nl_policy, NULL); @@ -871,7 +871,7 @@ static int __res_opts_from_attrs(struct res_opts *s, *ret_nested_attribute_table = NULL; if (!tla) return -ENOMSG; - ntb = kcalloc(DRBD_A_RES_OPTS_ON_NO_DATA + 1, sizeof(*ntb), GFP_KERNEL); + ntb = kzalloc_objs(*ntb, DRBD_A_RES_OPTS_ON_NO_DATA + 1); if (!ntb) return -ENOMEM; err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_res_opts_nl_policy, NULL); @@ -921,7 +921,7 @@ static int __net_conf_from_attrs(struct net_conf *s, *ret_nested_attribute_table = NULL; if (!tla) return -ENOMSG; - ntb = kcalloc(DRBD_A_NET_CONF_SOCK_CHECK_TIMEO + 1, sizeof(*ntb), GFP_KERNEL); + ntb = kzalloc_objs(*ntb, DRBD_A_NET_CONF_SOCK_CHECK_TIMEO + 1); if (!ntb) return -ENOMEM; err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_net_conf_nl_policy, NULL); @@ -1087,7 +1087,7 @@ static int __set_role_parms_from_attrs(struct set_role_parms *s, *ret_nested_attribute_table = NULL; if (!tla) return -ENOMSG; - ntb = kcalloc(DRBD_A_SET_ROLE_PARMS_ASSUME_UPTODATE + 1, sizeof(*ntb), GFP_KERNEL); + ntb = kzalloc_objs(*ntb, DRBD_A_SET_ROLE_PARMS_ASSUME_UPTODATE + 1); if (!ntb) return -ENOMEM; err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_set_role_parms_nl_policy, NULL); @@ -1133,7 +1133,7 @@ static int __resize_parms_from_attrs(struct resize_parms *s, *ret_nested_attribute_table = NULL; if (!tla) return -ENOMSG; - ntb = kcalloc(DRBD_A_RESIZE_PARMS_AL_STRIPE_SIZE + 1, sizeof(*ntb), GFP_KERNEL); + ntb = kzalloc_objs(*ntb, DRBD_A_RESIZE_PARMS_AL_STRIPE_SIZE + 1); if (!ntb) return -ENOMEM; err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_resize_parms_nl_policy, NULL); @@ -1195,7 +1195,7 @@ static int __start_ov_parms_from_attrs(struct start_ov_parms *s, *ret_nested_attribute_table = NULL; if (!tla) return -ENOMSG; - ntb = kcalloc(DRBD_A_START_OV_PARMS_OV_STOP_SECTOR + 1, sizeof(*ntb), GFP_KERNEL); + ntb = kzalloc_objs(*ntb, DRBD_A_START_OV_PARMS_OV_STOP_SECTOR + 1); if (!ntb) return -ENOMEM; err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_start_ov_parms_nl_policy, NULL); @@ -1245,7 +1245,7 @@ static int __new_c_uuid_parms_from_attrs(struct new_c_uuid_parms *s, *ret_nested_attribute_table = NULL; if (!tla) return -ENOMSG; - ntb = kcalloc(DRBD_A_NEW_C_UUID_PARMS_CLEAR_BM + 1, sizeof(*ntb), GFP_KERNEL); + ntb = kzalloc_objs(*ntb, DRBD_A_NEW_C_UUID_PARMS_CLEAR_BM + 1); if (!ntb) return -ENOMEM; err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_new_c_uuid_parms_nl_policy, NULL); @@ -1291,7 +1291,7 @@ static int __disconnect_parms_from_attrs(struct disconnect_parms *s, *ret_nested_attribute_table = NULL; if (!tla) return -ENOMSG; - ntb = kcalloc(DRBD_A_DISCONNECT_PARMS_FORCE_DISCONNECT + 1, sizeof(*ntb), GFP_KERNEL); + ntb = kzalloc_objs(*ntb, DRBD_A_DISCONNECT_PARMS_FORCE_DISCONNECT + 1); if (!ntb) return -ENOMEM; err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_disconnect_parms_nl_policy, NULL); @@ -1337,7 +1337,7 @@ static int __detach_parms_from_attrs(struct detach_parms *s, *ret_nested_attribute_table = NULL; if (!tla) return -ENOMSG; - ntb = kcalloc(DRBD_A_DETACH_PARMS_FORCE_DETACH + 1, sizeof(*ntb), GFP_KERNEL); + ntb = kzalloc_objs(*ntb, DRBD_A_DETACH_PARMS_FORCE_DETACH + 1); if (!ntb) return -ENOMEM; err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_detach_parms_nl_policy, NULL); @@ -1383,7 +1383,7 @@ static int __resource_info_from_attrs(struct resource_info *s, *ret_nested_attribute_table = NULL; if (!tla) return -ENOMSG; - ntb = kcalloc(DRBD_A_RESOURCE_INFO_RES_SUSP_FEN + 1, sizeof(*ntb), GFP_KERNEL); + ntb = kzalloc_objs(*ntb, DRBD_A_RESOURCE_INFO_RES_SUSP_FEN + 1); if (!ntb) return -ENOMEM; err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_resource_info_nl_policy, NULL); @@ -1441,7 +1441,7 @@ static int __device_info_from_attrs(struct device_info *s, *ret_nested_attribute_table = NULL; if (!tla) return -ENOMSG; - ntb = kcalloc(DRBD_A_DEVICE_INFO_DEV_DISK_STATE + 1, sizeof(*ntb), GFP_KERNEL); + ntb = kzalloc_objs(*ntb, DRBD_A_DEVICE_INFO_DEV_DISK_STATE + 1); if (!ntb) return -ENOMEM; err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_device_info_nl_policy, NULL); @@ -1487,7 +1487,7 @@ static int __connection_info_from_attrs(struct connection_info *s, *ret_nested_attribute_table = NULL; if (!tla) return -ENOMSG; - ntb = kcalloc(DRBD_A_CONNECTION_INFO_CONN_ROLE + 1, sizeof(*ntb), GFP_KERNEL); + ntb = kzalloc_objs(*ntb, DRBD_A_CONNECTION_INFO_CONN_ROLE + 1); if (!ntb) return -ENOMEM; err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_connection_info_nl_policy, NULL); @@ -1537,7 +1537,8 @@ static int __peer_device_info_from_attrs(struct peer_device_info *s, *ret_nested_attribute_table = NULL; if (!tla) return -ENOMSG; - ntb = kcalloc(DRBD_A_PEER_DEVICE_INFO_PEER_RESYNC_SUSP_DEPENDENCY + 1, sizeof(*ntb), GFP_KERNEL); + ntb = kzalloc_objs(*ntb, + DRBD_A_PEER_DEVICE_INFO_PEER_RESYNC_SUSP_DEPENDENCY + 1); if (!ntb) return -ENOMEM; err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_peer_device_info_nl_policy, NULL); @@ -1599,7 +1600,8 @@ static int __resource_statistics_from_attrs(struct resource_statistics *s, *ret_nested_attribute_table = NULL; if (!tla) return -ENOMSG; - ntb = kcalloc(DRBD_A_RESOURCE_STATISTICS_RES_STAT_WRITE_ORDERING + 1, sizeof(*ntb), GFP_KERNEL); + ntb = kzalloc_objs(*ntb, + DRBD_A_RESOURCE_STATISTICS_RES_STAT_WRITE_ORDERING + 1); if (!ntb) return -ENOMEM; err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_resource_statistics_nl_policy, NULL); @@ -1645,7 +1647,7 @@ static int __device_statistics_from_attrs(struct device_statistics *s, *ret_nested_attribute_table = NULL; if (!tla) return -ENOMSG; - ntb = kcalloc(DRBD_A_DEVICE_STATISTICS_HISTORY_UUIDS + 1, sizeof(*ntb), GFP_KERNEL); + ntb = kzalloc_objs(*ntb, DRBD_A_DEVICE_STATISTICS_HISTORY_UUIDS + 1); if (!ntb) return -ENOMEM; err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_device_statistics_nl_policy, NULL); @@ -1743,7 +1745,8 @@ static int __connection_statistics_from_attrs(struct connection_statistics *s, *ret_nested_attribute_table = NULL; if (!tla) return -ENOMSG; - ntb = kcalloc(DRBD_A_CONNECTION_STATISTICS_CONN_CONGESTED + 1, sizeof(*ntb), GFP_KERNEL); + ntb = kzalloc_objs(*ntb, + DRBD_A_CONNECTION_STATISTICS_CONN_CONGESTED + 1); if (!ntb) return -ENOMEM; err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_connection_statistics_nl_policy, NULL); @@ -1789,7 +1792,8 @@ static int __peer_device_statistics_from_attrs(struct peer_device_statistics *s, *ret_nested_attribute_table = NULL; if (!tla) return -ENOMSG; - ntb = kcalloc(DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_FLAGS + 1, sizeof(*ntb), GFP_KERNEL); + ntb = kzalloc_objs(*ntb, + DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_FLAGS + 1); if (!ntb) return -ENOMEM; err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_peer_device_statistics_nl_policy, NULL); diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 6c5bec7da97c..47574a98fc86 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -5390,7 +5390,7 @@ static int __ublk_ctrl_reg_buf(struct ublk_device *ub, page_to_pfn(pages[i + 1]) == pfn + (i - start) + 1) i++; - range = kzalloc(sizeof(*range), GFP_KERNEL); + range = kzalloc_obj(*range); if (!range) { ret = -ENOMEM; goto unwind; @@ -5453,7 +5453,7 @@ static int ublk_ctrl_reg_buf(struct ublk_device *ub, nr_pages = buf_reg.len >> PAGE_SHIFT; /* Pin pages before any locks (may sleep) */ - pages = kvmalloc_array(nr_pages, sizeof(*pages), GFP_KERNEL); + pages = kvmalloc_objs(*pages, nr_pages); if (!pages) return -ENOMEM; diff --git a/drivers/block/zram/backend_lz4.c b/drivers/block/zram/backend_lz4.c index 1e28104ad964..1e4ad31d39a6 100644 --- a/drivers/block/zram/backend_lz4.c +++ b/drivers/block/zram/backend_lz4.c @@ -42,7 +42,7 @@ static int lz4_setup_params(struct zcomp_params *params) if (!params->dict || !params->dict_sz) return 0; - dict_stream = kzalloc_obj(*dict_stream, GFP_KERNEL); + dict_stream = kzalloc_obj(*dict_stream); if (!dict_stream) return -ENOMEM; diff --git a/drivers/clk/ti/composite.c b/drivers/clk/ti/composite.c index 01eae8995254..83c3592cd179 100644 --- a/drivers/clk/ti/composite.c +++ b/drivers/clk/ti/composite.c @@ -248,7 +248,7 @@ int __init ti_clk_add_component(struct device_node *node, struct clk_hw *hw, return -EINVAL; } - parent_data = kcalloc(num_parents, sizeof(*parent_data), GFP_KERNEL); + parent_data = kzalloc_objs(*parent_data, num_parents); if (!parent_data) return -ENOMEM; diff --git a/drivers/clk/ti/mux.c b/drivers/clk/ti/mux.c index 0fef60e82107..baf90a3fb49e 100644 --- a/drivers/clk/ti/mux.c +++ b/drivers/clk/ti/mux.c @@ -181,7 +181,7 @@ static void of_mux_clk_setup(struct device_node *node) pr_err("mux-clock %pOFn must have parents\n", node); return; } - parent_data = kcalloc(num_parents, sizeof(*parent_data), GFP_KERNEL); + parent_data = kzalloc_objs(*parent_data, num_parents); if (!parent_data) return; diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index d4ff8b228f86..8bfd46d60843 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -1624,7 +1624,7 @@ static struct freq_attr **get_freq_attrs(void) /* amd_pstate_{max_freq, lowest_nonlinear_freq, highest_perf} should always be visible */ BUG_ON(!count); - attrs = kcalloc(count + 1, sizeof(struct freq_attr *), GFP_KERNEL); + attrs = kzalloc_objs(struct freq_attr *, count + 1); if (!attrs) return ERR_PTR(-ENOMEM); diff --git a/drivers/crypto/inside-secure/eip93/eip93-common.c b/drivers/crypto/inside-secure/eip93/eip93-common.c index 4c163d7281b3..dacf586b2641 100644 --- a/drivers/crypto/inside-secure/eip93/eip93-common.c +++ b/drivers/crypto/inside-secure/eip93/eip93-common.c @@ -533,7 +533,7 @@ int eip93_send_req(struct crypto_async_request *async, memcpy(iv, reqiv, rctx->ivsize); - rctx->sa_state = kzalloc(sizeof(*rctx->sa_state), GFP_KERNEL); + rctx->sa_state = kzalloc_obj(*rctx->sa_state); if (!rctx->sa_state) return -ENOMEM; @@ -561,8 +561,7 @@ int eip93_send_req(struct crypto_async_request *async, iv[3] = 0xffffffff; crypto_inc((u8 *)iv, AES_BLOCK_SIZE); - rctx->sa_state_ctr = kzalloc(sizeof(*rctx->sa_state_ctr), - GFP_KERNEL); + rctx->sa_state_ctr = kzalloc_obj(*rctx->sa_state_ctr); if (!rctx->sa_state_ctr) { err = -ENOMEM; goto free_sa_state; diff --git a/drivers/crypto/intel/qat/qat_common/qat_comp_algs.c b/drivers/crypto/intel/qat/qat_common/qat_comp_algs.c index e0d003b50358..50e444da97e6 100644 --- a/drivers/crypto/intel/qat/qat_common/qat_comp_algs.c +++ b/drivers/crypto/intel/qat/qat_common/qat_comp_algs.c @@ -59,8 +59,7 @@ static void *qat_zstd_alloc_scratch(void) if (!scratch->literals) goto error; - scratch->out_seqs = kvcalloc(QAT_MAX_SEQUENCES, sizeof(ZSTD_Sequence), - GFP_KERNEL); + scratch->out_seqs = kvzalloc_objs(ZSTD_Sequence, QAT_MAX_SEQUENCES); if (!scratch->out_seqs) goto error; diff --git a/drivers/crypto/ti/dthev2-aes.c b/drivers/crypto/ti/dthev2-aes.c index eb5cd902dfb5..a3c069ca2baf 100644 --- a/drivers/crypto/ti/dthev2-aes.c +++ b/drivers/crypto/ti/dthev2-aes.c @@ -387,7 +387,7 @@ static int dthe_aes_run(struct crypto_engine *engine, void *areq) src_nents++; dst_nents++; - src = kmalloc_array(src_nents, sizeof(*src), GFP_ATOMIC); + src = kmalloc_objs(*src, src_nents, GFP_ATOMIC); if (!src) { ret = -ENOMEM; goto aes_ctr_src_alloc_err; @@ -399,7 +399,7 @@ static int dthe_aes_run(struct crypto_engine *engine, void *areq) sg_set_buf(sg, pad_buf, pad_size); if (diff_dst) { - dst = kmalloc_array(dst_nents, sizeof(*dst), GFP_ATOMIC); + dst = kmalloc_objs(*dst, dst_nents, GFP_ATOMIC); if (!dst) { ret = -ENOMEM; goto aes_ctr_dst_alloc_err; @@ -624,7 +624,7 @@ static struct scatterlist *dthe_aead_prep_aad(struct scatterlist *sg, if (assoclen % AES_BLOCK_SIZE) aad_nents++; - aad_sg = kmalloc_array(aad_nents, sizeof(struct scatterlist), GFP_ATOMIC); + aad_sg = kmalloc_objs(struct scatterlist, aad_nents, GFP_ATOMIC); if (!aad_sg) return ERR_PTR(-ENOMEM); @@ -680,7 +680,7 @@ static struct scatterlist *dthe_aead_prep_crypt(struct scatterlist *sg, if (cryptlen % AES_BLOCK_SIZE) crypt_nents++; - crypt_sg = kmalloc_array(crypt_nents, sizeof(struct scatterlist), GFP_ATOMIC); + crypt_sg = kmalloc_objs(struct scatterlist, crypt_nents, GFP_ATOMIC); if (!crypt_sg) { err = -ENOMEM; goto dthe_aead_prep_crypt_mem_err; diff --git a/drivers/devfreq/hisi_uncore_freq.c b/drivers/devfreq/hisi_uncore_freq.c index e1f64b723082..ac55641b0259 100644 --- a/drivers/devfreq/hisi_uncore_freq.c +++ b/drivers/devfreq/hisi_uncore_freq.c @@ -474,7 +474,7 @@ static int hisi_uncore_mark_related_cpus(struct hisi_uncore_freq *uncore, return -EINVAL; len = rc; - u32 *num __free(kfree) = kcalloc(len, sizeof(*num), GFP_KERNEL); + u32 *num __free(kfree) = kzalloc_objs(*num, len); if (!num) return -ENOMEM; diff --git a/drivers/dma-buf/st-dma-fence.c b/drivers/dma-buf/st-dma-fence.c index 856d0d302a5d..cb62e606d0a2 100644 --- a/drivers/dma-buf/st-dma-fence.c +++ b/drivers/dma-buf/st-dma-fence.c @@ -27,7 +27,7 @@ static struct dma_fence *mock_fence(void) { struct dma_fence *f; - f = kmalloc(sizeof(*f), GFP_KERNEL); + f = kmalloc_obj(*f); if (!f) return NULL; diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c index 4a9ab5822ffc..df6dd0046242 100644 --- a/drivers/dma-buf/udmabuf.c +++ b/drivers/dma-buf/udmabuf.c @@ -359,7 +359,7 @@ static long udmabuf_create(struct miscdevice *device, long ret = -EINVAL; u32 i, flags; - ubuf = kzalloc(sizeof(*ubuf), GFP_KERNEL); + ubuf = kzalloc_obj(*ubuf); if (!ubuf) return -ENOMEM; @@ -387,7 +387,7 @@ static long udmabuf_create(struct miscdevice *device, if (ret) goto err; - folios = kvmalloc_array(max_nr_folios, sizeof(*folios), GFP_KERNEL); + folios = kvmalloc_objs(*folios, max_nr_folios); if (!folios) { ret = -ENOMEM; goto err; diff --git a/drivers/dma/switchtec_dma.c b/drivers/dma/switchtec_dma.c index c133535d3765..c8e2169877e9 100644 --- a/drivers/dma/switchtec_dma.c +++ b/drivers/dma/switchtec_dma.c @@ -1056,7 +1056,7 @@ static int switchtec_dma_chan_init(struct switchtec_dma_dev *swdma_dev, int se_buf_len, irq, rc; struct dma_chan *chan; - swdma_chan = kzalloc_obj(*swdma_chan, GFP_KERNEL); + swdma_chan = kzalloc_obj(*swdma_chan); if (!swdma_chan) return -ENOMEM; @@ -1162,8 +1162,7 @@ static int switchtec_dma_chans_enumerate(struct switchtec_dma_dev *swdma_dev, struct dma_device *dma = &swdma_dev->dma_dev; int base, cnt, rc, i; - swdma_dev->swdma_chans = kcalloc(chan_cnt, sizeof(*swdma_dev->swdma_chans), - GFP_KERNEL); + swdma_dev->swdma_chans = kzalloc_objs(*swdma_dev->swdma_chans, chan_cnt); if (!swdma_dev->swdma_chans) return -ENOMEM; @@ -1222,7 +1221,7 @@ static int switchtec_dma_create(struct pci_dev *pdev) /* * Create the switchtec dma device */ - swdma_dev = kzalloc_obj(*swdma_dev, GFP_KERNEL); + swdma_dev = kzalloc_obj(*swdma_dev); if (!swdma_dev) return -ENOMEM; diff --git a/drivers/edac/versalnet_edac.c b/drivers/edac/versalnet_edac.c index 97ec05d68bbb..9e65c4b1d99d 100644 --- a/drivers/edac/versalnet_edac.c +++ b/drivers/edac/versalnet_edac.c @@ -813,7 +813,7 @@ static int init_one_mc(struct mc_priv *priv, struct platform_device *pdev, int i layers[1].is_virt_csrow = false; rc = -ENOMEM; - dev = kzalloc(sizeof(*dev), GFP_KERNEL); + dev = kzalloc_obj(*dev); if (!dev) return rc; diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index ef29fd223287..922777e86d58 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -1792,7 +1792,7 @@ static void *scmi_iterator_init(const struct scmi_protocol_handle *ph, { int ret; - struct scmi_iterator *i __free(kfree) = kzalloc(sizeof(*i), GFP_KERNEL); + struct scmi_iterator *i __free(kfree) = kzalloc_obj(*i); if (!i) return ERR_PTR(-ENOMEM); diff --git a/drivers/firmware/qcom/qcom_tzmem.c b/drivers/firmware/qcom/qcom_tzmem.c index 0fd9581275f1..f926c1f64822 100644 --- a/drivers/firmware/qcom/qcom_tzmem.c +++ b/drivers/firmware/qcom/qcom_tzmem.c @@ -169,7 +169,7 @@ static int qcom_tzmem_init_area(struct qcom_tzmem_area *area) { int ret; - u64 *handle __free(kfree) = kzalloc(sizeof(*handle), GFP_KERNEL); + u64 *handle __free(kfree) = kzalloc_obj(*handle); if (!handle) return -ENOMEM; @@ -197,8 +197,7 @@ static int qcom_tzmem_pool_add_memory(struct qcom_tzmem_pool *pool, { int ret; - struct qcom_tzmem_area *area __free(kfree) = kzalloc(sizeof(*area), - gfp); + struct qcom_tzmem_area *area __free(kfree) = kzalloc_obj(*area, gfp); if (!area) return -ENOMEM; @@ -415,8 +414,7 @@ void *qcom_tzmem_alloc(struct qcom_tzmem_pool *pool, size_t size, gfp_t gfp) size = PAGE_ALIGN(size); - struct qcom_tzmem_chunk *chunk __free(kfree) = kzalloc(sizeof(*chunk), - gfp); + struct qcom_tzmem_chunk *chunk __free(kfree) = kzalloc_obj(*chunk, gfp); if (!chunk) return NULL; diff --git a/drivers/firmware/ti_sci.c b/drivers/firmware/ti_sci.c index cc747ab0237f..33d7c4a4181e 100644 --- a/drivers/firmware/ti_sci.c +++ b/drivers/firmware/ti_sci.c @@ -2386,7 +2386,7 @@ static int ti_sci_set_irq(const struct ti_sci_handle *handle, u32 valid_params, if (ret || !(info->fw_caps & MSG_FLAG_CAPS_LPM_IRQ_CONTEXT_LOST)) goto end; - irq = kzalloc_obj(*irq, GFP_KERNEL); + irq = kzalloc_obj(*irq); if (!irq) { ti_sci_manage_irq(handle, valid_params, src_id, src_index, dst_id, dst_host_irq, ia_id, vint, diff --git a/drivers/fpga/dfl-afu-dma-region.c b/drivers/fpga/dfl-afu-dma-region.c index 87652d58d03f..1b3a1af8658d 100644 --- a/drivers/fpga/dfl-afu-dma-region.c +++ b/drivers/fpga/dfl-afu-dma-region.c @@ -316,7 +316,7 @@ int afu_dma_map_region(struct dfl_feature_dev_data *fdata, if (user_addr + length < user_addr) return -EINVAL; - region = kzalloc(sizeof(*region), GFP_KERNEL); + region = kzalloc_obj(*region); if (!region) return -ENOMEM; diff --git a/drivers/gpio/gpio-aggregator.c b/drivers/gpio/gpio-aggregator.c index 5ce89f52b4b5..b0b65416d74d 100644 --- a/drivers/gpio/gpio-aggregator.c +++ b/drivers/gpio/gpio-aggregator.c @@ -886,8 +886,8 @@ gpio_aggregator_make_device_sw_node(struct gpio_aggregator *aggr) if (num_lines == 0) return NULL; - const char **line_names __free(kfree) = kcalloc( - num_lines, sizeof(*line_names), GFP_KERNEL); + const char **line_names __free(kfree) = kzalloc_objs(*line_names, + num_lines); if (!line_names) return ERR_PTR(-ENOMEM); diff --git a/drivers/gpio/gpio-mpsse.c b/drivers/gpio/gpio-mpsse.c index a859deab2bca..30e8009b5fcc 100644 --- a/drivers/gpio/gpio-mpsse.c +++ b/drivers/gpio/gpio-mpsse.c @@ -518,7 +518,7 @@ static void gpio_mpsse_irq_enable(struct irq_data *irqd) * Can't be devm because it uses a non-raw spinlock (illegal in * this context, where a raw spinlock is held by our caller) */ - worker = kzalloc(sizeof(*worker), GFP_NOWAIT); + worker = kzalloc_obj(*worker, GFP_NOWAIT); if (!worker) return; diff --git a/drivers/gpio/gpio-sim.c b/drivers/gpio/gpio-sim.c index ef1b779e8ea6..0c73bec04267 100644 --- a/drivers/gpio/gpio-sim.c +++ b/drivers/gpio/gpio-sim.c @@ -790,8 +790,7 @@ gpio_sim_make_bank_swnode(struct gpio_sim_bank *bank, line_names_size = gpio_sim_get_line_names_size(bank); if (line_names_size) { - line_names = kcalloc(line_names_size, sizeof(*line_names), - GFP_KERNEL); + line_names = kzalloc_objs(*line_names, line_names_size); if (!line_names) return ERR_PTR(-ENOMEM); diff --git a/drivers/gpio/gpio-virtuser.c b/drivers/gpio/gpio-virtuser.c index 7d0d366be37a..449fb1aed24b 100644 --- a/drivers/gpio/gpio-virtuser.c +++ b/drivers/gpio/gpio-virtuser.c @@ -1429,8 +1429,7 @@ gpio_virtuser_make_device_swnode(struct gpio_virtuser_device *dev) memset(properties, 0, sizeof(properties)); num_ids = list_count_nodes(&dev->lookup_list); - char **ids __free(kfree) = kcalloc(num_ids + 1, sizeof(*ids), - GFP_KERNEL); + char **ids __free(kfree) = kzalloc_objs(*ids, num_ids + 1); if (!ids) return ERR_PTR(-ENOMEM); diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c index 9f3b628d5793..d1105b7ae437 100644 --- a/drivers/gpio/gpiolib-cdev.c +++ b/drivers/gpio/gpiolib-cdev.c @@ -2653,7 +2653,7 @@ static int gpio_chrdev_open(struct inode *inode, struct file *file) struct gpio_chardev_data *cdev; int ret = -ENOMEM; - cdev = kzalloc(sizeof(*cdev), GFP_KERNEL); + cdev = kzalloc_obj(*cdev); if (!cdev) return -ENOMEM; diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index ef8ccaf17c9c..66d2325bfae8 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1178,7 +1178,7 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, int base = 0; int ret; - gdev = kzalloc(sizeof(*gdev), GFP_KERNEL); + gdev = kzalloc_obj(*gdev); if (!gdev) return -ENOMEM; gc->gpiodev = gdev; @@ -1218,7 +1218,7 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, goto err_put_device; gdev->ngpio = gc->ngpio; - gdev->descs = kcalloc(gc->ngpio, sizeof(*gdev->descs), GFP_KERNEL); + gdev->descs = kzalloc_objs(*gdev->descs, gc->ngpio); if (!gdev->descs) { ret = -ENOMEM; goto err_put_device; diff --git a/drivers/gpu/buddy.c b/drivers/gpu/buddy.c index a5553fcec28c..26e7a48b55f3 100644 --- a/drivers/gpu/buddy.c +++ b/drivers/gpu/buddy.c @@ -411,16 +411,13 @@ int gpu_buddy_init(struct gpu_buddy *mm, u64 size, u64 chunk_size) if (!mm->used_scoreboard) goto out_free_free_scoreboard; - mm->free_trees = kmalloc_array(GPU_BUDDY_MAX_FREE_TREES, - sizeof(*mm->free_trees), - GFP_KERNEL); + mm->free_trees = kmalloc_objs(*mm->free_trees, GPU_BUDDY_MAX_FREE_TREES); if (!mm->free_trees) goto out_free_used_scoreboard; for_each_free_tree(i) { - mm->free_trees[i] = kmalloc_array(mm->max_order + 1, - sizeof(struct rb_root), - GFP_KERNEL); + mm->free_trees[i] = kmalloc_objs(struct rb_root, + mm->max_order + 1); if (!mm->free_trees[i]) goto out_free_tree; @@ -430,9 +427,7 @@ int gpu_buddy_init(struct gpu_buddy *mm, u64 size, u64 chunk_size) mm->n_roots = hweight64(size); - mm->roots = kmalloc_array(mm->n_roots, - sizeof(struct gpu_buddy_block *), - GFP_KERNEL); + mm->roots = kmalloc_objs(struct gpu_buddy_block *, mm->n_roots); if (!mm->roots) goto out_free_tree; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c index 87e15e39eb30..6ff9ffe47f35 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c @@ -603,9 +603,8 @@ void amdgpu_coredump(struct amdgpu_device *adev, bool skip_vram_check, ring_count++; } if (ring_count) - coredump->rings = kvcalloc(ring_count, - sizeof(struct amdgpu_coredump_ring), - GFP_NOWAIT); + coredump->rings = kvzalloc_objs(struct amdgpu_coredump_ring, + ring_count, GFP_NOWAIT); if (coredump->rings) { for (i = 0, idx = 0; i < adev->num_rings && idx < ring_count; i++) { struct amdgpu_coredump_ring *cdump_ring; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index 164e85b66e2d..62f5c5cbd7f9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -1608,11 +1608,11 @@ int amdgpu_discovery_sysfs_early_init(struct amdgpu_device *adev, struct pci_dev discovery_bin = adev->discovery.bin; - early_entry = kzalloc(sizeof(*early_entry), GFP_KERNEL); + early_entry = kzalloc_obj(*early_entry); if (!early_entry) return -ENOMEM; - ip_top = kzalloc(sizeof(*ip_top), GFP_KERNEL); + ip_top = kzalloc_obj(*ip_top); if (!ip_top) { kfree(early_entry); return -ENOMEM; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_lockdep.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_lockdep.c index d5787d848d04..4a7f63fb2fad 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_lockdep.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_lockdep.c @@ -98,7 +98,7 @@ int amdgpu_lockdep_init(void) struct amdgpu_lockdep_dummy_locks *locks; unsigned long flags; - locks = kzalloc(sizeof(*locks), GFP_KERNEL); + locks = kzalloc_obj(*locks); if (!locks) return -ENOMEM; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c index 95468b9463fb..78adfc839ef8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c @@ -1293,7 +1293,7 @@ amdgpu_ras_debugfs_table_read_uniras(struct amdgpu_device *adev, return -ENOMEM; if (num_recs) { - records = kvcalloc(num_recs, sizeof(*records), GFP_KERNEL); + records = kvzalloc_objs(*records, num_recs); if (!records) { res = -ENOMEM; goto out; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index d5a419776e93..05abf4c31dce 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -2361,9 +2361,8 @@ void amdgpu_ttm_enable_buffer_funcs(struct amdgpu_device *adev) num_clear_entities = MIN(adev->mman.num_buffer_funcs_scheds, TTM_NUM_MOVE_FENCES); num_move_entities = MIN(adev->mman.num_buffer_funcs_scheds, TTM_NUM_MOVE_FENCES); - adev->mman.clear_entities = kcalloc(num_clear_entities, - sizeof(struct amdgpu_ttm_buffer_entity), - GFP_KERNEL); + adev->mman.clear_entities = kzalloc_objs(struct amdgpu_ttm_buffer_entity, + num_clear_entities); atomic_set(&adev->mman.next_clear_entity, 0); if (!adev->mman.clear_entities) goto error_free_default_entity; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c index a98a6cfd4fba..71d34fd09385 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c @@ -159,8 +159,8 @@ void amdgpu_umc_handle_bad_pages(struct amdgpu_device *adev, adev->umc.ras->ecc_info_query_ras_error_address && adev->umc.max_ras_err_cnt_per_query) { err_data->err_addr = - kcalloc(adev->umc.max_ras_err_cnt_per_query, - sizeof(struct eeprom_table_record), GFP_KERNEL); + kzalloc_objs(struct eeprom_table_record, + adev->umc.max_ras_err_cnt_per_query); /* still call query_ras_error_address to clear error status * even NOMEM error is encountered diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c index 4b023e024d9f..743b41db5b7c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c @@ -227,7 +227,7 @@ static int amdgpu_userq_fence_alloc(struct amdgpu_usermode_queue *userq, struct amdgpu_userq_fence *userq_fence; void *entry; - userq_fence = kmalloc(sizeof(*userq_fence), GFP_KERNEL); + userq_fence = kmalloc_obj(*userq_fence); if (!userq_fence) return -ENOMEM; @@ -244,9 +244,7 @@ static int amdgpu_userq_fence_alloc(struct amdgpu_usermode_queue *userq, } while (xas_retry(&xas, entry)); rcu_read_unlock(); - userq_fence->fence_drv_array = kvmalloc_array(xas.xa_index, - sizeof(fence_drv), - GFP_KERNEL); + userq_fence->fence_drv_array = kvmalloc_objs(fence_drv, xas.xa_index); if (!userq_fence->fence_drv_array) { mutex_unlock(&userq->fence_drv_lock); kfree(userq_fence); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c index b43fc643668d..7a007f4916bc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c @@ -316,8 +316,8 @@ static int amdgpu_virt_ras_realloc_eh_data_space(struct amdgpu_device *adev, if (align_space > AMDGPU_VIRT_RAS_BAD_PAGE_TABLE_MAX_CAPACITY) return -ENOMEM; - new_bps = kmalloc_array(align_space, sizeof(*data->bps), GFP_KERNEL); - new_bo = kcalloc(align_space, sizeof(*data->bps_bo), GFP_KERNEL); + new_bps = kmalloc_objs(*data->bps, align_space); + new_bo = kzalloc_objs(*data->bps_bo, align_space); if (!new_bps || !new_bo) { kfree(new_bps); kfree(new_bo); @@ -355,7 +355,7 @@ static int amdgpu_virt_init_ras_err_handler_data(struct amdgpu_device *adev) if (!bps) goto bps_failure; - bps_bo = kcalloc(align_space, sizeof(*(*data)->bps_bo), GFP_KERNEL); + bps_bo = kzalloc_objs(*(*data)->bps_bo, align_space); if (!bps_bo) goto bps_bo_failure; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 7fcfc150a7fc..504a286368eb 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1921,13 +1921,13 @@ static int criu_checkpoint_devices(struct kfd_process *p, struct kfd_criu_device_bucket *device_buckets = NULL; int ret = 0, i; - device_buckets = kvcalloc(num_devices, sizeof(*device_buckets), GFP_KERNEL); + device_buckets = kvzalloc_objs(*device_buckets, num_devices); if (!device_buckets) { ret = -ENOMEM; goto exit; } - device_priv = kvcalloc(num_devices, sizeof(*device_priv), GFP_KERNEL); + device_priv = kvzalloc_objs(*device_priv, num_devices); if (!device_priv) { ret = -ENOMEM; goto exit; @@ -2047,17 +2047,17 @@ static int criu_checkpoint_bos(struct kfd_process *p, int ret = 0, pdd_index, bo_index = 0, id; void *mem; - bo_buckets = kvcalloc(num_bos, sizeof(*bo_buckets), GFP_KERNEL); + bo_buckets = kvzalloc_objs(*bo_buckets, num_bos); if (!bo_buckets) return -ENOMEM; - bo_privs = kvcalloc(num_bos, sizeof(*bo_privs), GFP_KERNEL); + bo_privs = kvzalloc_objs(*bo_privs, num_bos); if (!bo_privs) { ret = -ENOMEM; goto exit; } - files = kvcalloc(num_bos, sizeof(struct file *), GFP_KERNEL); + files = kvzalloc_objs(struct file *, num_bos); if (!files) { ret = -ENOMEM; goto exit; @@ -2588,7 +2588,7 @@ static int criu_restore_bos(struct kfd_process *p, if (!bo_buckets) return -ENOMEM; - files = kvcalloc(args->num_bos, sizeof(struct file *), GFP_KERNEL); + files = kvzalloc_objs(struct file *, args->num_bos); if (!files) { ret = -ENOMEM; goto exit; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_connector_test.c b/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_connector_test.c index a54fd9529dc9..0d2f9dbce0a9 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_connector_test.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_connector_test.c @@ -4180,7 +4180,7 @@ dm_test_destroy_connector(struct kunit *test, struct drm_device *drm) { struct amdgpu_dm_connector *aconnector; - aconnector = kzalloc(sizeof(*aconnector), GFP_KERNEL); + aconnector = kzalloc_obj(*aconnector); KUNIT_ASSERT_NOT_NULL(test, aconnector); KUNIT_ASSERT_EQ(test, diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_crtc_test.c b/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_crtc_test.c index 4dacddd23878..0d998f204250 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_crtc_test.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_crtc_test.c @@ -1445,7 +1445,7 @@ static void dm_test_crtc_destroy_state_no_stream(struct kunit *test) struct dm_crtc_state *dm_state; /* destroy_state kfree()s the state, so use a plain (unmanaged) alloc. */ - dm_state = kzalloc_obj(*dm_state, GFP_KERNEL); + dm_state = kzalloc_obj(*dm_state); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dm_state); amdgpu_dm_crtc_destroy_state(NULL, &dm_state->base); @@ -1475,7 +1475,7 @@ static void dm_test_crtc_destroy_state_releases_stream(struct kunit *test) kref_get(&stream->refcount); /* destroy_state kfree()s the state, so use a plain (unmanaged) alloc. */ - dm_state = kzalloc_obj(*dm_state, GFP_KERNEL); + dm_state = kzalloc_obj(*dm_state); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dm_state); dm_state->stream = stream; @@ -1569,7 +1569,7 @@ static void dm_test_crtc_handle_vblank_completes_cursor_only(struct kunit *test) KUNIT_ASSERT_NOT_ERR_OR_NULL(test, acrtc); /* drm_crtc_send_vblank_event() consumes (kfree()s) the event. */ - event = kzalloc_obj(*event, GFP_KERNEL); + event = kzalloc_obj(*event); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, event); acrtc->base.dev = &adev->ddev; @@ -1628,7 +1628,7 @@ dm_test_vblank_control_worker_setup(struct kunit *test, bool enable, kref_get(&stream->refcount); /* Worker kfree()s the work item, so it must be a plain allocation. */ - work = kzalloc_obj(*work, GFP_KERNEL); + work = kzalloc_obj(*work); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, work); work->dm = &adev->dm; work->acrtc = acrtc; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_irq_test.c b/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_irq_test.c index 28c36217f6a2..861ee9eaa032 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_irq_test.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_irq_test.c @@ -103,7 +103,7 @@ static enum dc_status dm_test_dp_read_hpd_rx_irq_data_ok(struct dc_link *link, */ static struct dc_sink *dm_test_sink_create(struct dc_link *link) { - struct dc_sink *sink = kzalloc(sizeof(*sink), GFP_KERNEL); + struct dc_sink *sink = kzalloc_obj(*sink); if (!sink) return NULL; @@ -2131,7 +2131,7 @@ static void dm_test_hpd_rx_offload_work_no_connector(struct kunit *test) offload_wq = kunit_kzalloc(test, sizeof(*offload_wq), GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, offload_wq); - offload_work = kzalloc(sizeof(*offload_work), GFP_KERNEL); + offload_work = kzalloc_obj(*offload_work); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, offload_work); offload_work->offload_wq = offload_wq; offload_work->adev = adev; @@ -2177,7 +2177,7 @@ static void dm_test_hpd_rx_offload_work_no_connection(struct kunit *test) link->dc = dc; aconn->dc_link = link; - offload_work = kzalloc(sizeof(*offload_work), GFP_KERNEL); + offload_work = kzalloc_obj(*offload_work); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, offload_work); offload_work->offload_wq = offload_wq; offload_work->adev = adev; @@ -2244,7 +2244,7 @@ static void dm_test_hpd_rx_offload_work_automated_test(struct kunit *test) link->connector_signal = SIGNAL_TYPE_DISPLAY_PORT; aconn->dc_link = link; - offload_work = kzalloc(sizeof(*offload_work), GFP_KERNEL); + offload_work = kzalloc_obj(*offload_work); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, offload_work); offload_work->offload_wq = offload_wq; offload_work->adev = adev; @@ -2315,7 +2315,7 @@ static void dm_test_hpd_rx_offload_work_link_loss(struct kunit *test) link->connector_signal = SIGNAL_TYPE_DISPLAY_PORT; aconn->dc_link = link; - offload_work = kzalloc(sizeof(*offload_work), GFP_KERNEL); + offload_work = kzalloc_obj(*offload_work); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, offload_work); offload_work->offload_wq = offload_wq; offload_work->adev = adev; @@ -3452,9 +3452,9 @@ static void dm_test_handle_hpd_work_out_of_range(struct kunit *test) struct amdgpu_device *adev; adev = dm_kunit_alloc_adev(test); - hpd_work = kzalloc(sizeof(*hpd_work), GFP_KERNEL); + hpd_work = kzalloc_obj(*hpd_work); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, hpd_work); - hpd_work->dmub_notify = kzalloc(sizeof(*hpd_work->dmub_notify), GFP_KERNEL); + hpd_work->dmub_notify = kzalloc_obj(*hpd_work->dmub_notify); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, hpd_work->dmub_notify); hpd_work->dmub_notify->type = (enum dmub_notification_type)ARRAY_SIZE(adev->dm.dmub_callback); @@ -3899,9 +3899,9 @@ static void dm_test_handle_vmin_vmax_update(struct kunit *test) kref_get(&stream->refcount); /* The worker kfree()s both, so they must come from the slab. */ - work = kzalloc(sizeof(*work), GFP_KERNEL); + work = kzalloc_obj(*work); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, work); - adjust = kzalloc(sizeof(*adjust), GFP_KERNEL); + adjust = kzalloc_obj(*adjust); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, adjust); work->adev = adev; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_plane_test.c b/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_plane_test.c index ba97092c7bb8..23ac8ae41c68 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_plane_test.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_plane_test.c @@ -2945,7 +2945,7 @@ static void dm_test_plane_reset_initializes_state(struct kunit *test) * destroy-existing-state path. The destroy hook frees this state, so it * must be a plain (non-KUnit-managed) allocation. */ - old_state = kzalloc(sizeof(*old_state), GFP_KERNEL); + old_state = kzalloc_obj(*old_state); KUNIT_ASSERT_NOT_NULL(test, old_state); plane->funcs = &dm_test_plane_reset_funcs; plane->state = &old_state->base; @@ -3018,7 +3018,7 @@ static void dm_test_plane_destroy_state_minimal(struct kunit *test) KUNIT_ASSERT_NOT_NULL(test, plane); /* destroy_state frees the state itself, so use a plain allocation. */ - dm_plane_state = kzalloc(sizeof(*dm_plane_state), GFP_KERNEL); + dm_plane_state = kzalloc_obj(*dm_plane_state); KUNIT_ASSERT_NOT_NULL(test, dm_plane_state); amdgpu_dm_plane_drm_plane_destroy_state(plane, &dm_plane_state->base); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_test.c b/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_test.c index 3c10eec9b1e0..5645866610fc 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_test.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_test.c @@ -239,7 +239,7 @@ static void dm_test_atomic_destroy_state_no_context(struct kunit *test) * Use kzalloc(), not kunit_kzalloc(): dm_atomic_destroy_state() frees * the state itself, so KUnit-managed memory would be double-freed. */ - dm_state = kzalloc(sizeof(*dm_state), GFP_KERNEL); + dm_state = kzalloc_obj(*dm_state); KUNIT_ASSERT_NOT_NULL(test, dm_state); /* context == NULL: dc_state_release() is skipped and the state is freed. */ diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c index e2148cb3b8ab..bf80eaf23e9a 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c @@ -377,7 +377,7 @@ struct clk_mgr *dc_clk_mgr_create(struct dc_context *ctx, struct pp_smu_funcs *p } break; case AMDGPU_FAMILY_GC_11_5_4: { - struct clk_mgr_dcn42 *clk_mgr = kzalloc(sizeof(*clk_mgr), GFP_KERNEL); + struct clk_mgr_dcn42 *clk_mgr = kzalloc_obj(*clk_mgr); if (clk_mgr == NULL) { BREAK_TO_DEBUGGER(); diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn60/dcn60_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn60/dcn60_clk_mgr.c index d71b0aed90c9..7dd88d90eba2 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn60/dcn60_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn60/dcn60_clk_mgr.c @@ -1595,7 +1595,7 @@ struct clk_mgr_internal *dcn60_clk_mgr_construct( struct dccg *dccg) { struct clk_log_info log_info = {0}; - struct dcn60_clk_mgr *clk_mgr60 = kzalloc(sizeof(struct dcn60_clk_mgr), GFP_KERNEL); + struct dcn60_clk_mgr *clk_mgr60 = kzalloc_obj(struct dcn60_clk_mgr); struct clk_mgr_internal *clk_mgr; if (!clk_mgr60) @@ -1644,7 +1644,7 @@ struct clk_mgr_internal *dcn60_clk_mgr_construct( clk_mgr->smu_present = false; - clk_mgr->base.bw_params = kzalloc(sizeof(*clk_mgr->base.bw_params), GFP_KERNEL); + clk_mgr->base.bw_params = kzalloc_obj(*clk_mgr->base.bw_params); if (!clk_mgr->base.bw_params) goto fail; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 68f228014305..a98ed4617a03 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -914,8 +914,7 @@ static bool dc_construct_update_scratch_pool(struct dc *dc) unsigned int i; for (i = 0; i < ARRAY_SIZE(dc->update_scratch_pool); i++) { - dc->update_scratch_pool[i] = kzalloc( - sizeof(struct dc_update_scratch_space), GFP_KERNEL); + dc->update_scratch_pool[i] = kzalloc_obj(struct dc_update_scratch_space); if (!dc->update_scratch_pool[i]) return false; dc->update_scratch_in_use[i] = false; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c index 88e825a6582c..0b135a9e6c4f 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c @@ -290,7 +290,7 @@ static void dc_plane_cm_free(struct kref *kref) struct dc_plane_cm *dc_plane_cm_create(void) { - struct dc_plane_cm *cm = kvzalloc(sizeof(*cm), GFP_KERNEL); + struct dc_plane_cm *cm = kvzalloc_obj(*cm); if (cm == NULL) goto alloc_fail; diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn42/dcn42_dccg.c b/drivers/gpu/drm/amd/display/dc/dccg/dcn42/dcn42_dccg.c index 3b03b152da22..c2fa7fd56acf 100644 --- a/drivers/gpu/drm/amd/display/dc/dccg/dcn42/dcn42_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn42/dcn42_dccg.c @@ -358,7 +358,7 @@ struct dccg *dccg42_create( const struct dccg_shift *dccg_shift, const struct dccg_mask *dccg_mask) { - struct dcn_dccg *dccg_dcn = kzalloc(sizeof(*dccg_dcn), GFP_KERNEL); + struct dcn_dccg *dccg_dcn = kzalloc_obj(*dccg_dcn); struct dccg *base; if (dccg_dcn == NULL) { diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn60/dcn60_dccg.c b/drivers/gpu/drm/amd/display/dc/dccg/dcn60/dcn60_dccg.c index 8e2f88913e4c..1d6d193b23c7 100644 --- a/drivers/gpu/drm/amd/display/dc/dccg/dcn60/dcn60_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn60/dcn60_dccg.c @@ -167,7 +167,7 @@ struct dccg *dccg60_create( const struct dccg_shift *dccg_shift, const struct dccg_mask *dccg_mask) { - struct dcn_dccg *dccg_dcn = kzalloc(sizeof(*dccg_dcn), GFP_KERNEL); + struct dcn_dccg *dccg_dcn = kzalloc_obj(*dccg_dcn); struct dccg *base; if (dccg_dcn == NULL) { diff --git a/drivers/gpu/drm/amd/display/dc/gpio/hw_ddc.c b/drivers/gpu/drm/amd/display/dc/gpio/hw_ddc.c index b75bfea635fd..cf9c7a2089a1 100644 --- a/drivers/gpu/drm/amd/display/dc/gpio/hw_ddc.c +++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_ddc.c @@ -542,7 +542,7 @@ void dal_hw_ddc_init_i3cpad( *hw_ddc = NULL; } - *hw_ddc = kzalloc(sizeof(struct hw_ddc), GFP_KERNEL); + *hw_ddc = kzalloc_obj(struct hw_ddc); if (!*hw_ddc) { ASSERT_CRITICAL(false); return; diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn42/irq_service_dcn42.c b/drivers/gpu/drm/amd/display/dc/irq/dcn42/irq_service_dcn42.c index f4d1ce9079de..3a87c1a26488 100644 --- a/drivers/gpu/drm/amd/display/dc/irq/dcn42/irq_service_dcn42.c +++ b/drivers/gpu/drm/amd/display/dc/irq/dcn42/irq_service_dcn42.c @@ -405,7 +405,7 @@ static void dcn42_irq_construct(struct irq_service *irq_service, struct irq_service *dal_irq_service_dcn42_create(struct irq_service_init_data *init_data) { - struct irq_service *irq_service = kzalloc(sizeof(*irq_service), GFP_KERNEL); + struct irq_service *irq_service = kzalloc_obj(*irq_service); if (!irq_service) return NULL; diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn60/irq_service_dcn60.c b/drivers/gpu/drm/amd/display/dc/irq/dcn60/irq_service_dcn60.c index 99163346e7d9..651bae6b5ede 100644 --- a/drivers/gpu/drm/amd/display/dc/irq/dcn60/irq_service_dcn60.c +++ b/drivers/gpu/drm/amd/display/dc/irq/dcn60/irq_service_dcn60.c @@ -406,8 +406,7 @@ static void dcn60_irq_construct( struct irq_service *dal_irq_service_dcn60_create( struct irq_service_init_data *init_data) { - struct irq_service *irq_service = kzalloc(sizeof(*irq_service), - GFP_KERNEL); + struct irq_service *irq_service = kzalloc_obj(*irq_service); if (!irq_service) return NULL; diff --git a/drivers/gpu/drm/amd/display/dc/pg/dcn42/dcn42_pg_cntl.c b/drivers/gpu/drm/amd/display/dc/pg/dcn42/dcn42_pg_cntl.c index 78b33b2dbae8..2c87e33e909e 100644 --- a/drivers/gpu/drm/amd/display/dc/pg/dcn42/dcn42_pg_cntl.c +++ b/drivers/gpu/drm/amd/display/dc/pg/dcn42/dcn42_pg_cntl.c @@ -615,7 +615,7 @@ struct pg_cntl *pg_cntl42_create( const struct pg_cntl_shift *pg_cntl_shift, const struct pg_cntl_mask *pg_cntl_mask) { - struct dcn_pg_cntl *pg_cntl_dcn = kzalloc(sizeof(*pg_cntl_dcn), GFP_KERNEL); + struct dcn_pg_cntl *pg_cntl_dcn = kzalloc_obj(*pg_cntl_dcn); struct pg_cntl *base; if (pg_cntl_dcn == NULL) { diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn30/dcn30_resource.c index dbb8bb7fc20d..aecbcd28c2d9 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn30/dcn30_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn30/dcn30_resource.c @@ -1135,7 +1135,7 @@ static struct hpo_frl_stream_encoder *dcn30_hpo_frl_stream_encoder_create(enum e } /* allocate HPO stream encoder and create VPG sub-block */ - hpo_enc3 = kzalloc(sizeof(struct dcn30_hpo_frl_stream_encoder), GFP_KERNEL); + hpo_enc3 = kzalloc_obj(struct dcn30_hpo_frl_stream_encoder); vpg = dcn30_vpg_create(ctx, vpg_inst); afmt = dcn30_afmt_create(ctx, afmt_inst); @@ -1166,7 +1166,7 @@ static struct hpo_frl_link_encoder *dcn30_hpo_frl_link_encoder_create(enum engin ASSERT((eng_id == ENGINE_ID_HPO_0) || (eng_id == ENGINE_ID_HPO_1)); /* allocate HPO link encoder */ - hpo_enc3 = kzalloc(sizeof(struct dcn30_hpo_frl_link_encoder), GFP_KERNEL); + hpo_enc3 = kzalloc_obj(struct dcn30_hpo_frl_link_encoder); if (!hpo_enc3) return NULL; /* out of memory */ diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn302/dcn302_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn302/dcn302_resource.c index 88dcf8166378..f67b3e00bd86 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn302/dcn302_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn302/dcn302_resource.c @@ -492,7 +492,7 @@ static struct hpo_frl_stream_encoder *dcn302_hpo_frl_stream_encoder_create(enum return NULL; /* allocate HPO stream encoder and create VPG sub-block */ - hpo_enc3 = kzalloc(sizeof(struct dcn30_hpo_frl_stream_encoder), GFP_KERNEL); + hpo_enc3 = kzalloc_obj(struct dcn30_hpo_frl_stream_encoder); vpg = dcn302_vpg_create(ctx, vpg_inst); afmt = dcn302_afmt_create(ctx, afmt_inst); @@ -531,7 +531,7 @@ static struct hpo_frl_link_encoder *dcn302_hpo_frl_link_encoder_create(enum engi ASSERT((eng_id == ENGINE_ID_HPO_0) || (eng_id == ENGINE_ID_HPO_1)); /* allocate HPO link encoder */ - hpo_enc3 = kzalloc(sizeof(struct dcn30_hpo_frl_link_encoder), GFP_KERNEL); + hpo_enc3 = kzalloc_obj(struct dcn30_hpo_frl_link_encoder); if (!hpo_enc3) return NULL; /* out of memory */ diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn303/dcn303_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn303/dcn303_resource.c index 50b7c7b85fac..9e1bf34cca2a 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn303/dcn303_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn303/dcn303_resource.c @@ -479,7 +479,7 @@ static struct hpo_frl_stream_encoder *dcn303_hpo_frl_stream_encoder_create(enum return NULL; /* allocate HPO stream encoder and create VPG sub-block */ - hpo_enc3 = kzalloc(sizeof(struct dcn30_hpo_frl_stream_encoder), GFP_KERNEL); + hpo_enc3 = kzalloc_obj(struct dcn30_hpo_frl_stream_encoder); vpg = dcn303_vpg_create(ctx, vpg_inst); afmt = dcn303_afmt_create(ctx, afmt_inst); @@ -518,7 +518,7 @@ static struct hpo_frl_link_encoder *dcn303_hpo_frl_link_encoder_create(enum engi ASSERT((eng_id == ENGINE_ID_HPO_0) || (eng_id == ENGINE_ID_HPO_1)); /* allocate HPO link encoder */ - hpo_enc3 = kzalloc(sizeof(struct dcn30_hpo_frl_link_encoder), GFP_KERNEL); + hpo_enc3 = kzalloc_obj(struct dcn30_hpo_frl_link_encoder); if (!hpo_enc3) return NULL; /* out of memory */ diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c index db56e30cf259..6359fbb574df 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c @@ -1346,7 +1346,7 @@ static struct hpo_frl_stream_encoder *dcn31_hpo_frl_stream_encoder_create(enum e } /* allocate HPO stream encoder and create VPG, AFMT sub-blocks */ - hpo_enc3 = kzalloc(sizeof(struct dcn30_hpo_frl_stream_encoder), GFP_KERNEL); + hpo_enc3 = kzalloc_obj(struct dcn30_hpo_frl_stream_encoder); vpg = dcn31_vpg_create(ctx, vpg_inst); afmt = dcn31_afmt_create(ctx, afmt_inst); @@ -1377,7 +1377,7 @@ static struct hpo_frl_link_encoder *dcn31_hpo_frl_link_encoder_create(enum engin ASSERT((eng_id == ENGINE_ID_HPO_0) || (eng_id == ENGINE_ID_HPO_1)); /* allocate HPO link encoder */ - hpo_enc3 = kzalloc(sizeof(struct dcn30_hpo_frl_link_encoder), GFP_KERNEL); + hpo_enc3 = kzalloc_obj(struct dcn30_hpo_frl_link_encoder); if (!hpo_enc3) return NULL; /* out of memory */ diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c index 63f92e9da6d8..0ddfceca69dd 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c @@ -1404,7 +1404,7 @@ static struct hpo_frl_stream_encoder *dcn31_hpo_frl_stream_encoder_create(enum e } /* allocate HPO stream encoder and create VPG, AFMT sub-blocks */ - hpo_enc3 = kzalloc(sizeof(struct dcn30_hpo_frl_stream_encoder), GFP_KERNEL); + hpo_enc3 = kzalloc_obj(struct dcn30_hpo_frl_stream_encoder); vpg = dcn31_vpg_create(ctx, vpg_inst); afmt = dcn31_afmt_create(ctx, afmt_inst); @@ -1436,7 +1436,7 @@ static struct hpo_frl_link_encoder *dcn31_hpo_frl_link_encoder_create(enum engin ASSERT((eng_id == ENGINE_ID_HPO_0) || (eng_id == ENGINE_ID_HPO_1)); /* allocate HPO link encoder */ - hpo_enc3 = kzalloc(sizeof(struct dcn30_hpo_frl_link_encoder), GFP_KERNEL); + hpo_enc3 = kzalloc_obj(struct dcn30_hpo_frl_link_encoder); if (!hpo_enc3) return NULL; /* out of memory */ diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn315/dcn315_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn315/dcn315_resource.c index 15c1615c5f45..a1894be8cbb2 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn315/dcn315_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn315/dcn315_resource.c @@ -1347,7 +1347,7 @@ static struct hpo_frl_stream_encoder *dcn31_hpo_frl_stream_encoder_create(enum e } /* allocate HPO stream encoder and create VPG, AFMT sub-blocks */ - hpo_enc3 = kzalloc(sizeof(struct dcn30_hpo_frl_stream_encoder), GFP_KERNEL); + hpo_enc3 = kzalloc_obj(struct dcn30_hpo_frl_stream_encoder); vpg = dcn31_vpg_create(ctx, vpg_inst); afmt = dcn31_afmt_create(ctx, afmt_inst); @@ -1379,7 +1379,7 @@ static struct hpo_frl_link_encoder *dcn31_hpo_frl_link_encoder_create(enum engin ASSERT((eng_id == ENGINE_ID_HPO_0) || (eng_id == ENGINE_ID_HPO_1)); /* allocate HPO link encoder */ - hpo_enc3 = kzalloc(sizeof(struct dcn30_hpo_frl_link_encoder), GFP_KERNEL); + hpo_enc3 = kzalloc_obj(struct dcn30_hpo_frl_link_encoder); if (!hpo_enc3) return NULL; /* out of memory */ diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn316/dcn316_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn316/dcn316_resource.c index a5ea35e45791..4a2d56a196b4 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn316/dcn316_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn316/dcn316_resource.c @@ -1340,7 +1340,7 @@ static struct hpo_frl_stream_encoder *dcn31_hpo_frl_stream_encoder_create(enum e } /* allocate HPO stream encoder and create VPG, AFMT sub-blocks */ - hpo_enc3 = kzalloc(sizeof(struct dcn30_hpo_frl_stream_encoder), GFP_KERNEL); + hpo_enc3 = kzalloc_obj(struct dcn30_hpo_frl_stream_encoder); vpg = dcn31_vpg_create(ctx, vpg_inst); afmt = dcn31_afmt_create(ctx, afmt_inst); @@ -1372,7 +1372,7 @@ static struct hpo_frl_link_encoder *dcn31_hpo_frl_link_encoder_create(enum engin ASSERT((eng_id == ENGINE_ID_HPO_0) || (eng_id == ENGINE_ID_HPO_1)); /* allocate HPO link encoder */ - hpo_enc3 = kzalloc(sizeof(struct dcn30_hpo_frl_link_encoder), GFP_KERNEL); + hpo_enc3 = kzalloc_obj(struct dcn30_hpo_frl_link_encoder); if (!hpo_enc3) return NULL; /* out of memory */ diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c index 7c2a79015f4e..a2e66761b8ec 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c @@ -1339,7 +1339,7 @@ static struct hpo_frl_stream_encoder *dcn32_hpo_frl_stream_encoder_create(enum e } /* allocate HPO stream encoder and create VPG, AFMT sub-blocks */ - hpo_enc3 = kzalloc(sizeof(struct dcn30_hpo_frl_stream_encoder), GFP_KERNEL); + hpo_enc3 = kzalloc_obj(struct dcn30_hpo_frl_stream_encoder); vpg = dcn32_vpg_create(ctx, vpg_inst); afmt = dcn32_afmt_create(ctx, afmt_inst); @@ -1375,7 +1375,7 @@ static struct hpo_frl_link_encoder *dcn32_hpo_frl_link_encoder_create(enum engin hpo_frl_link_encoder_reg_list(0); /* allocate HPO link encoder */ - hpo_enc3 = kzalloc(sizeof(struct dcn30_hpo_frl_link_encoder), GFP_KERNEL); + hpo_enc3 = kzalloc_obj(struct dcn30_hpo_frl_link_encoder); if (!hpo_enc3) return NULL; /* out of memory */ diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c index 5ee9a5a8ec3c..4097093d9012 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c @@ -1314,7 +1314,7 @@ static struct hpo_frl_stream_encoder *dcn321_hpo_frl_stream_encoder_create(enum } /* allocate HPO stream encoder and create VPG, AFMT sub-blocks */ - hpo_enc3 = kzalloc(sizeof(struct dcn30_hpo_frl_stream_encoder), GFP_KERNEL); + hpo_enc3 = kzalloc_obj(struct dcn30_hpo_frl_stream_encoder); vpg = dcn321_vpg_create(ctx, vpg_inst); afmt = dcn321_afmt_create(ctx, afmt_inst); @@ -1350,7 +1350,7 @@ static struct hpo_frl_link_encoder *dcn321_hpo_frl_link_encoder_create(enum engi hpo_frl_link_encoder_reg_list(0); /* allocate HPO link encoder */ - hpo_enc3 = kzalloc(sizeof(struct dcn30_hpo_frl_link_encoder), GFP_KERNEL); + hpo_enc3 = kzalloc_obj(struct dcn30_hpo_frl_link_encoder); if (!hpo_enc3) return NULL; /* out of memory */ diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c index 52826e96c184..fd7a22fcca59 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c @@ -1398,7 +1398,7 @@ static struct hpo_frl_stream_encoder *dcn31_hpo_frl_stream_encoder_create( return NULL; /* allocate HPO stream encoder and create VPG, AFMT sub-blocks */ - hpo_enc3 = kzalloc(sizeof(struct dcn30_hpo_frl_stream_encoder), GFP_KERNEL); + hpo_enc3 = kzalloc_obj(struct dcn30_hpo_frl_stream_encoder); vpg = dcn31_vpg_create(ctx, vpg_inst); afmt = dcn31_afmt_create(ctx, afmt_inst); @@ -1430,7 +1430,7 @@ static struct hpo_frl_link_encoder *dcn31_hpo_frl_link_encoder_create( hpo_frl_link_encoder_reg_list(0); /* allocate HPO link encoder */ - hpo_enc3 = kzalloc(sizeof(struct dcn30_hpo_frl_link_encoder), GFP_KERNEL); + hpo_enc3 = kzalloc_obj(struct dcn30_hpo_frl_link_encoder); if (!hpo_enc3) return NULL; /* out of memory */ diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c index e3fc71307c91..83248ee01d11 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c @@ -1378,7 +1378,7 @@ static struct hpo_frl_stream_encoder *dcn31_hpo_frl_stream_encoder_create( return NULL; /* allocate HPO stream encoder and create VPG, AFMT sub-blocks */ - hpo_enc3 = kzalloc(sizeof(struct dcn30_hpo_frl_stream_encoder), GFP_KERNEL); + hpo_enc3 = kzalloc_obj(struct dcn30_hpo_frl_stream_encoder); vpg = dcn31_vpg_create(ctx, vpg_inst); afmt = dcn31_afmt_create(ctx, afmt_inst); @@ -1410,7 +1410,7 @@ static struct hpo_frl_link_encoder *dcn31_hpo_frl_link_encoder_create( hpo_frl_link_encoder_reg_list(0); /* allocate HPO link encoder */ - hpo_enc3 = kzalloc(sizeof(struct dcn30_hpo_frl_link_encoder), GFP_KERNEL); + hpo_enc3 = kzalloc_obj(struct dcn30_hpo_frl_link_encoder); if (!hpo_enc3) return NULL; /* out of memory */ diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c index c019a657005d..8d1baa76c347 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c @@ -1385,7 +1385,7 @@ static struct hpo_frl_stream_encoder *dcn31_hpo_frl_stream_encoder_create( return NULL; /* allocate HPO stream encoder and create VPG, AFMT sub-blocks */ - hpo_enc3 = kzalloc(sizeof(struct dcn30_hpo_frl_stream_encoder), GFP_KERNEL); + hpo_enc3 = kzalloc_obj(struct dcn30_hpo_frl_stream_encoder); vpg = dcn31_vpg_create(ctx, vpg_inst); afmt = dcn31_afmt_create(ctx, afmt_inst); @@ -1417,7 +1417,7 @@ static struct hpo_frl_link_encoder *dcn31_hpo_frl_link_encoder_create( hpo_frl_link_encoder_reg_list(0); /* allocate HPO link encoder */ - hpo_enc3 = kzalloc(sizeof(struct dcn30_hpo_frl_link_encoder), GFP_KERNEL); + hpo_enc3 = kzalloc_obj(struct dcn30_hpo_frl_link_encoder); if (!hpo_enc3) return NULL; /* out of memory */ diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c index aced8ff657bf..0cfdca82bef0 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c @@ -1322,7 +1322,7 @@ static struct hpo_frl_stream_encoder *dcn401_hpo_frl_stream_encoder_create( return NULL; /* allocate HPO stream encoder and create VPG, AFMT sub-blocks */ - hpo_enc401 = kzalloc(sizeof(struct dcn401_hpo_frl_stream_encoder), GFP_KERNEL); + hpo_enc401 = kzalloc_obj(struct dcn401_hpo_frl_stream_encoder); vpg = dcn401_vpg_create(ctx, vpg_inst); afmt = dcn401_afmt_create(ctx, afmt_inst); @@ -1353,7 +1353,7 @@ static struct hpo_frl_link_encoder *dcn401_hpo_frl_link_encoder_create( hpo_frl_link_encoder_reg_list(0); /* allocate HPO link encoder */ - hpo_link_enc = kzalloc(sizeof(struct dcn30_hpo_frl_link_encoder), GFP_KERNEL); + hpo_link_enc = kzalloc_obj(struct dcn30_hpo_frl_link_encoder); if (!hpo_link_enc) return NULL; /* out of memory */ diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn42/dcn42_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn42/dcn42_resource.c index b93d608b64a9..28192d6dda7a 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn42/dcn42_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn42/dcn42_resource.c @@ -818,7 +818,7 @@ static struct dce_aux *dcn42_aux_engine_create( uint32_t inst) { struct aux_engine_dce110 *aux_engine = - kzalloc(sizeof(struct aux_engine_dce110), GFP_KERNEL); + kzalloc_obj(struct aux_engine_dce110); if (!aux_engine) return NULL; @@ -884,7 +884,7 @@ static struct dce_i2c_hw *dcn42_i2c_hw_create( uint32_t inst) { struct dce_i2c_hw *dce_i2c_hw = - kzalloc(sizeof(struct dce_i2c_hw), GFP_KERNEL); + kzalloc_obj(struct dce_i2c_hw); if (!dce_i2c_hw) return NULL; @@ -910,7 +910,7 @@ static struct clock_source *dcn42_clock_source_create( bool dp_clk_src) { struct dce110_clk_src *clk_src = - kzalloc(sizeof(struct dce110_clk_src), GFP_KERNEL); + kzalloc_obj(struct dce110_clk_src); if (!clk_src) return NULL; @@ -929,8 +929,7 @@ static struct hubbub *dcn42_hubbub_create(struct dc_context *ctx) { int i; - struct dcn20_hubbub *hubbub3 = kzalloc(sizeof(struct dcn20_hubbub), - GFP_KERNEL); + struct dcn20_hubbub *hubbub3 = kzalloc_obj(struct dcn20_hubbub); if (!hubbub3) return NULL; @@ -983,7 +982,7 @@ static struct hubp *dcn42_hubp_create( uint32_t inst) { struct dcn20_hubp *hubp2 = - kzalloc(sizeof(struct dcn20_hubp), GFP_KERNEL); + kzalloc_obj(struct dcn20_hubp); if (!hubp2) return NULL; @@ -1025,7 +1024,7 @@ static struct dpp *dcn42_dpp_create( uint32_t inst) { struct dcn42_dpp *dpp42 = - kzalloc(sizeof(struct dcn42_dpp), GFP_KERNEL); + kzalloc_obj(struct dcn42_dpp); if (!dpp42) return NULL; @@ -1051,8 +1050,7 @@ static struct mpc *dcn42_mpc_create( int num_mpcc, int num_rmu) { - struct dcn42_mpc *mpc401 = kzalloc(sizeof(struct dcn42_mpc), - GFP_KERNEL); + struct dcn42_mpc *mpc401 = kzalloc_obj(struct dcn42_mpc); if (!mpc401) return NULL; @@ -1075,7 +1073,7 @@ static struct output_pixel_processor *dcn42_opp_create( struct dc_context *ctx, uint32_t inst) { struct dcn20_opp *opp4 = - kzalloc(sizeof(struct dcn20_opp), GFP_KERNEL); + kzalloc_obj(struct dcn20_opp); if (!opp4) { BREAK_TO_DEBUGGER(); @@ -1098,7 +1096,7 @@ static struct timing_generator *dcn42_timing_generator_create( uint32_t instance) { struct optc *tgn10 = - kzalloc(sizeof(struct optc), GFP_KERNEL); + kzalloc_obj(struct optc); if (!tgn10) return NULL; @@ -1136,7 +1134,7 @@ static struct link_encoder *dcn42_link_encoder_create( const struct encoder_init_data *enc_init_data) { struct dcn20_link_encoder *enc20 = - kzalloc(sizeof(struct dcn20_link_encoder), GFP_KERNEL); + kzalloc_obj(struct dcn20_link_encoder); if (!enc20 || enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs)) return NULL; @@ -1202,7 +1200,7 @@ static struct vpg *dcn42_vpg_create( struct dc_context *ctx, uint32_t inst) { - struct dcn31_vpg *vpg4 = kzalloc(sizeof(struct dcn31_vpg), GFP_KERNEL); + struct dcn31_vpg *vpg4 = kzalloc_obj(struct dcn31_vpg); if (!vpg4) return NULL; @@ -1231,7 +1229,7 @@ static struct apg *dcn42_apg_create( struct dc_context *ctx, uint32_t inst) { - struct dcn31_apg *apg31 = kzalloc(sizeof(struct dcn31_apg), GFP_KERNEL); + struct dcn31_apg *apg31 = kzalloc_obj(struct dcn31_apg); if (!apg31) return NULL; @@ -1275,7 +1273,7 @@ static struct stream_encoder *dcn42_stream_encoder_create( } else return NULL; - enc1 = kzalloc(sizeof(struct dcn10_stream_encoder), GFP_KERNEL); + enc1 = kzalloc_obj(struct dcn10_stream_encoder); vpg = dcn42_vpg_create(ctx, vpg_inst); apg = dcn42_apg_create(ctx, apg_inst); @@ -1325,7 +1323,7 @@ static struct hpo_frl_stream_encoder *dcn42_hpo_frl_stream_encoder_create( return NULL; /* allocate HPO stream encoder and create VPG sub-block */ - hpo_enc42 = kzalloc(sizeof(struct dcn42_hpo_frl_stream_encoder), GFP_KERNEL); + hpo_enc42 = kzalloc_obj(struct dcn42_hpo_frl_stream_encoder); vpg = dcn42_vpg_create(ctx, vpg_inst); apg = dcn42_apg_create(ctx, apg_inst); @@ -1357,7 +1355,7 @@ static struct hpo_frl_link_encoder *dcn42_hpo_frl_link_encoder_create( hpo_frl_link_encoder_reg_list(0); /* allocate HPO link encoder */ - hpo_link_enc = kzalloc(sizeof(struct dcn30_hpo_frl_link_encoder), GFP_KERNEL); + hpo_link_enc = kzalloc_obj(struct dcn30_hpo_frl_link_encoder); if (!hpo_link_enc) return NULL; /* out of memory */ @@ -1399,7 +1397,7 @@ static struct hpo_dp_stream_encoder *dcn42_hpo_dp_stream_encoder_create( apg_inst = hpo_dp_inst + 5; /* allocate HPO stream encoder and create VPG sub-block */ - hpo_dp_enc31 = kzalloc(sizeof(struct dcn31_hpo_dp_stream_encoder), GFP_KERNEL); + hpo_dp_enc31 = kzalloc_obj(struct dcn31_hpo_dp_stream_encoder); vpg = dcn42_vpg_create(ctx, vpg_inst); apg = dcn42_apg_create(ctx, apg_inst); @@ -1432,7 +1430,7 @@ static struct hpo_dp_link_encoder *dcn42_hpo_dp_link_encoder_create( struct dcn31_hpo_dp_link_encoder *hpo_dp_enc31; /* allocate HPO link encoder */ - hpo_dp_enc31 = kzalloc(sizeof(struct dcn31_hpo_dp_link_encoder), GFP_KERNEL); + hpo_dp_enc31 = kzalloc_obj(struct dcn31_hpo_dp_link_encoder); if (!hpo_dp_enc31) return NULL; /* out of memory */ @@ -1453,7 +1451,7 @@ static struct hpo_dp_link_encoder *dcn42_hpo_dp_link_encoder_create( static struct dce_hwseq *dcn42_hwseq_create( struct dc_context *ctx) { - struct dce_hwseq *hws = kzalloc(sizeof(struct dce_hwseq), GFP_KERNEL); + struct dce_hwseq *hws = kzalloc_obj(struct dce_hwseq); #undef REG_STRUCT #define REG_STRUCT hwseq_reg @@ -1727,8 +1725,7 @@ static bool dcn42_dwbc_create(struct dc_context *ctx, struct resource_pool *pool uint32_t dwb_count = pool->res_cap->num_dwb; for (i = 0; i < dwb_count; i++) { - struct dcn30_dwbc *dwbc42 = kzalloc(sizeof(struct dcn30_dwbc), - GFP_KERNEL); + struct dcn30_dwbc *dwbc42 = kzalloc_obj(struct dcn30_dwbc); if (!dwbc42) { dm_error("DC: failed to create dwbc42!\n"); @@ -1764,8 +1761,7 @@ static bool dcn42_mmhubbub_create(struct dc_context *ctx, struct resource_pool * uint32_t pipe_count = pool->res_cap->num_dwb; for (i = 0; i < pipe_count; i++) { - struct dcn30_mmhubbub *mcif_wb30 = kzalloc(sizeof(struct dcn30_mmhubbub), - GFP_KERNEL); + struct dcn30_mmhubbub *mcif_wb30 = kzalloc_obj(struct dcn30_mmhubbub); if (!mcif_wb30) { dm_error("DC: failed to create mcif_wb30!\n"); @@ -1793,7 +1789,7 @@ static struct display_stream_compressor *dcn42_dsc_create( struct dc_context *ctx, uint32_t inst) { struct dcn401_dsc *dsc = - kzalloc(sizeof(struct dcn401_dsc), GFP_KERNEL); + kzalloc_obj(struct dcn401_dsc); if (!dsc) { BREAK_TO_DEBUGGER(); @@ -1890,7 +1886,7 @@ static struct link_encoder *dcn42_link_enc_create_minimal( if ((unsigned int)(eng_id - ENGINE_ID_DIGA) >= ctx->dc->res_pool->res_cap->num_dig_link_enc) return NULL; - enc20 = kzalloc(sizeof(struct dcn20_link_encoder), GFP_KERNEL); + enc20 = kzalloc_obj(struct dcn20_link_encoder); if (!enc20) return NULL; @@ -2441,7 +2437,7 @@ struct resource_pool *dcn42_create_resource_pool( struct dc *dc) { struct dcn42_resource_pool *pool = - kzalloc(sizeof(struct dcn42_resource_pool), GFP_KERNEL); + kzalloc_obj(struct dcn42_resource_pool); if (!pool) return NULL; diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn42b/dcn42b_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn42b/dcn42b_resource.c index 41f0c67f57ff..f36d0f828166 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn42b/dcn42b_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn42b/dcn42b_resource.c @@ -870,7 +870,7 @@ static struct dce_aux *dcn42b_aux_engine_create( uint32_t inst) { struct aux_engine_dce110 *aux_engine = - kzalloc(sizeof(struct aux_engine_dce110), GFP_KERNEL); + kzalloc_obj(struct aux_engine_dce110); if (!aux_engine) return NULL; @@ -940,7 +940,7 @@ static struct dce_i2c_hw *dcn42b_i2c_hw_create( uint32_t inst) { struct dce_i2c_hw *dce_i2c_hw = - kzalloc(sizeof(struct dce_i2c_hw), GFP_KERNEL); + kzalloc_obj(struct dce_i2c_hw); if (!dce_i2c_hw) return NULL; @@ -968,7 +968,7 @@ static struct clock_source *dcn42b_clock_source_create( bool dp_clk_src) { struct dce110_clk_src *clk_src = - kzalloc(sizeof(struct dce110_clk_src), GFP_KERNEL); + kzalloc_obj(struct dce110_clk_src); if (!clk_src) return NULL; @@ -988,8 +988,7 @@ static struct hubbub *dcn42b_hubbub_create(struct dc_context *ctx) { int i; - struct dcn20_hubbub *hubbub3 = kzalloc(sizeof(struct dcn20_hubbub), - GFP_KERNEL); + struct dcn20_hubbub *hubbub3 = kzalloc_obj(struct dcn20_hubbub); if (!hubbub3) return NULL; @@ -1042,7 +1041,7 @@ static struct hubp *dcn42b_hubp_create( uint32_t inst) { struct dcn20_hubp *hubp2 = - kzalloc(sizeof(struct dcn20_hubp), GFP_KERNEL); + kzalloc_obj(struct dcn20_hubp); if (!hubp2) return NULL; @@ -1084,7 +1083,7 @@ static struct dpp *dcn42b_dpp_create( uint32_t inst) { struct dcn42_dpp *dpp42b = - kzalloc(sizeof(struct dcn42_dpp), GFP_KERNEL); + kzalloc_obj(struct dcn42_dpp); if (!dpp42b) return NULL; @@ -1110,8 +1109,7 @@ static struct mpc *dcn42b_mpc_create( int num_mpcc, int num_rmu) { - struct dcn42_mpc *mpc42b = kzalloc(sizeof(struct dcn42_mpc), - GFP_KERNEL); + struct dcn42_mpc *mpc42b = kzalloc_obj(struct dcn42_mpc); if (!mpc42b) return NULL; @@ -1134,7 +1132,7 @@ static struct output_pixel_processor *dcn42b_opp_create( struct dc_context *ctx, uint32_t inst) { struct dcn20_opp *opp4 = - kzalloc(sizeof(struct dcn20_opp), GFP_KERNEL); + kzalloc_obj(struct dcn20_opp); if (!opp4) { BREAK_TO_DEBUGGER(); @@ -1158,7 +1156,7 @@ static struct timing_generator *dcn42b_timing_generator_create( uint32_t instance) { struct optc *tgn10 = - kzalloc(sizeof(struct optc), GFP_KERNEL); + kzalloc_obj(struct optc); if (!tgn10) return NULL; @@ -1196,7 +1194,7 @@ static struct link_encoder *dcn42b_link_encoder_create( const struct encoder_init_data *enc_init_data) { struct dcn20_link_encoder *enc20 = - kzalloc(sizeof(struct dcn20_link_encoder), GFP_KERNEL); + kzalloc_obj(struct dcn20_link_encoder); if (!enc20 || enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs)) return NULL; @@ -1271,7 +1269,7 @@ static struct vpg *dcn42b_vpg_create( struct dc_context *ctx, uint32_t inst) { - struct dcn31_vpg *vpg4 = kzalloc(sizeof(struct dcn31_vpg), GFP_KERNEL); + struct dcn31_vpg *vpg4 = kzalloc_obj(struct dcn31_vpg); if (!vpg4) return NULL; @@ -1300,7 +1298,7 @@ static struct apg *dcn42b_apg_create( struct dc_context *ctx, uint32_t inst) { - struct dcn31_apg *apg31 = kzalloc(sizeof(struct dcn31_apg), GFP_KERNEL); + struct dcn31_apg *apg31 = kzalloc_obj(struct dcn31_apg); if (!apg31) return NULL; @@ -1344,7 +1342,7 @@ static struct stream_encoder *dcn42b_stream_encoder_create( } else return NULL; - enc1 = kzalloc(sizeof(struct dcn10_stream_encoder), GFP_KERNEL); + enc1 = kzalloc_obj(struct dcn10_stream_encoder); vpg = dcn42b_vpg_create(ctx, vpg_inst); apg = dcn42b_apg_create(ctx, apg_inst); @@ -1404,7 +1402,7 @@ static struct hpo_dp_stream_encoder *dcn42b_hpo_dp_stream_encoder_create( apg_inst = hpo_dp_inst + 6; /* allocate HPO stream encoder and create VPG sub-block */ - hpo_dp_enc31 = kzalloc(sizeof(struct dcn31_hpo_dp_stream_encoder), GFP_KERNEL); + hpo_dp_enc31 = kzalloc_obj(struct dcn31_hpo_dp_stream_encoder); vpg = dcn42b_vpg_create(ctx, vpg_inst); apg = dcn42b_apg_create(ctx, apg_inst); @@ -1437,7 +1435,7 @@ static struct hpo_dp_link_encoder *dcn42b_hpo_dp_link_encoder_create( struct dcn31_hpo_dp_link_encoder *hpo_dp_enc31; /* allocate HPO link encoder */ - hpo_dp_enc31 = kzalloc(sizeof(struct dcn31_hpo_dp_link_encoder), GFP_KERNEL); + hpo_dp_enc31 = kzalloc_obj(struct dcn31_hpo_dp_link_encoder); if (!hpo_dp_enc31) return NULL; /* out of memory */ @@ -1457,7 +1455,7 @@ static struct hpo_dp_link_encoder *dcn42b_hpo_dp_link_encoder_create( static struct dce_hwseq *dcn42b_hwseq_create( struct dc_context *ctx) { - struct dce_hwseq *hws = kzalloc(sizeof(struct dce_hwseq), GFP_KERNEL); + struct dce_hwseq *hws = kzalloc_obj(struct dce_hwseq); #undef REG_STRUCT #define REG_STRUCT hwseq_reg @@ -1716,8 +1714,7 @@ static bool dcn42b_dwbc_create(struct dc_context *ctx, struct resource_pool *poo uint32_t dwb_count = pool->res_cap->num_dwb; for (i = 0; i < dwb_count; i++) { - struct dcn30_dwbc *dwbc42 = kzalloc(sizeof(struct dcn30_dwbc), - GFP_KERNEL); + struct dcn30_dwbc *dwbc42 = kzalloc_obj(struct dcn30_dwbc); if (!dwbc42) { dm_error("DC: failed to create dwbc42!\n"); @@ -1753,8 +1750,7 @@ static bool dcn42b_mmhubbub_create(struct dc_context *ctx, struct resource_pool uint32_t pipe_count = pool->res_cap->num_dwb; for (i = 0; i < pipe_count; i++) { - struct dcn30_mmhubbub *mcif_wb30 = kzalloc(sizeof(struct dcn30_mmhubbub), - GFP_KERNEL); + struct dcn30_mmhubbub *mcif_wb30 = kzalloc_obj(struct dcn30_mmhubbub); if (!mcif_wb30) { dm_error("DC: failed to create mcif_wb30!\n"); @@ -1782,7 +1778,7 @@ static struct display_stream_compressor *dcn42b_dsc_create( struct dc_context *ctx, uint32_t inst) { struct dcn401_dsc *dsc = - kzalloc(sizeof(struct dcn401_dsc), GFP_KERNEL); + kzalloc_obj(struct dcn401_dsc); if (!dsc) { BREAK_TO_DEBUGGER(); @@ -1875,7 +1871,7 @@ static struct link_encoder *dcn42b_link_enc_create_minimal( if ((unsigned int)(eng_id - ENGINE_ID_DIGA) >= ctx->dc->res_pool->res_cap->num_dig_link_enc) return NULL; - enc20 = kzalloc(sizeof(struct dcn20_link_encoder), GFP_KERNEL); + enc20 = kzalloc_obj(struct dcn20_link_encoder); if (!enc20) return NULL; @@ -2439,7 +2435,7 @@ struct resource_pool *dcn42b_create_resource_pool( struct dc *dc) { struct dcn42b_resource_pool *pool = - kzalloc(sizeof(struct dcn42b_resource_pool), GFP_KERNEL); + kzalloc_obj(struct dcn42b_resource_pool); if (!pool) return NULL; diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn60/dcn60_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn60/dcn60_resource.c index 4b7668abf4dc..d091ea55cb5d 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn60/dcn60_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn60/dcn60_resource.c @@ -998,7 +998,7 @@ static struct dce_aux *dcn60_aux_engine_create( uint32_t inst) { struct aux_engine_dce110 *aux_engine = - kzalloc(sizeof(struct aux_engine_dce110), GFP_KERNEL); + kzalloc_obj(struct aux_engine_dce110); if (!aux_engine) return NULL; @@ -1037,7 +1037,7 @@ static struct dce_i2c_hw *dcn60_i2c_hw_create( uint32_t inst) { struct dce_i2c_hw *dce_i2c_hw = - kzalloc(sizeof(struct dce_i2c_hw), GFP_KERNEL); + kzalloc_obj(struct dce_i2c_hw); if (!dce_i2c_hw) return NULL; @@ -1061,7 +1061,7 @@ static struct clock_source *dcn60_clock_source_create( bool dp_clk_src) { struct dce110_clk_src *clk_src = - kzalloc(sizeof(struct dce110_clk_src), GFP_KERNEL); + kzalloc_obj(struct dce110_clk_src); if (!clk_src) return NULL; @@ -1081,8 +1081,7 @@ static struct hubbub *dcn60_hubbub_create(struct dc_context *ctx) { int i; - struct dcn20_hubbub *hubbub2 = kzalloc(sizeof(struct dcn20_hubbub), - GFP_KERNEL); + struct dcn20_hubbub *hubbub2 = kzalloc_obj(struct dcn20_hubbub); if (!hubbub2) return NULL; @@ -1136,7 +1135,7 @@ static struct hubp *dcn60_hubp_create( uint32_t inst) { struct dcn20_hubp *hubp2 = - kzalloc(sizeof(struct dcn20_hubp), GFP_KERNEL); + kzalloc_obj(struct dcn20_hubp); if (!hubp2) return NULL; @@ -1168,7 +1167,7 @@ static struct dpp *dcn60_dpp_create( uint32_t inst) { struct dcn60_dpp *dpp60 = - kzalloc(sizeof(struct dcn60_dpp), GFP_KERNEL); + kzalloc_obj(struct dcn60_dpp); if (!dpp60) return NULL; @@ -1194,8 +1193,7 @@ static struct mpc *dcn60_mpc_create( int num_mpcc, int num_rmu) { - struct dcn60_mpc *mpc60 = kzalloc(sizeof(struct dcn60_mpc), - GFP_KERNEL); + struct dcn60_mpc *mpc60 = kzalloc_obj(struct dcn60_mpc); if (!mpc60) return NULL; @@ -1218,7 +1216,7 @@ static struct output_pixel_processor *dcn60_opp_create( struct dc_context *ctx, uint32_t inst) { struct dcn20_opp *opp2 = - kzalloc(sizeof(struct dcn20_opp), GFP_KERNEL); + kzalloc_obj(struct dcn20_opp); if (!opp2) { BREAK_TO_DEBUGGER(); @@ -1242,7 +1240,7 @@ static struct timing_generator *dcn60_timing_generator_create( uint32_t instance) { struct optc *tgn10 = - kzalloc(sizeof(struct optc), GFP_KERNEL); + kzalloc_obj(struct optc); if (!tgn10) return NULL; @@ -1282,7 +1280,7 @@ static struct link_encoder *dcn60_link_encoder_create( const struct encoder_init_data *enc_init_data) { struct dcn20_link_encoder *enc20 = - kzalloc(sizeof(struct dcn20_link_encoder), GFP_KERNEL); + kzalloc_obj(struct dcn20_link_encoder); if (!enc20 || enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs)) { kfree(enc20); @@ -1349,7 +1347,7 @@ static struct vpg *dcn60_vpg_create( struct dc_context *ctx, uint32_t inst) { - struct dcn31_vpg *vpg6 = kzalloc(sizeof(struct dcn31_vpg), GFP_KERNEL); + struct dcn31_vpg *vpg6 = kzalloc_obj(struct dcn31_vpg); if (!vpg6) return NULL; @@ -1378,7 +1376,7 @@ static struct apg *dcn60_apg_create( struct dc_context *ctx, uint32_t inst) { - struct dcn31_apg *apg60 = kzalloc(sizeof(struct dcn31_apg), GFP_KERNEL); + struct dcn31_apg *apg60 = kzalloc_obj(struct dcn31_apg); if (!apg60) return NULL; @@ -1415,7 +1413,7 @@ static struct stream_encoder *dcn60_stream_encoder_create( } else return NULL; - enc1 = kzalloc(sizeof(struct dcn10_stream_encoder), GFP_KERNEL); + enc1 = kzalloc_obj(struct dcn10_stream_encoder); vpg = dcn60_vpg_create(ctx, vpg_inst); apg = dcn60_apg_create(ctx, apg_inst); @@ -1462,7 +1460,7 @@ static struct hpo_frl_stream_encoder *dcn60_hpo_frl_stream_encoder_create( return NULL; /* allocate HPO stream encoder and create VPG, APG sub-blocks */ - hpo_enc60 = kzalloc(sizeof(struct dcn401_hpo_frl_stream_encoder), GFP_KERNEL); + hpo_enc60 = kzalloc_obj(struct dcn401_hpo_frl_stream_encoder); vpg = dcn60_vpg_create(ctx, vpg_inst); apg = dcn60_apg_create(ctx, apg_inst); @@ -1493,7 +1491,7 @@ static struct hpo_frl_link_encoder *dcn60_hpo_frl_link_encoder_create( hpo_frl_link_encoder_reg_list(0); /* allocate HPO link encoder */ - hpo_link_enc = kzalloc(sizeof(struct dcn30_hpo_frl_link_encoder), GFP_KERNEL); + hpo_link_enc = kzalloc_obj(struct dcn30_hpo_frl_link_encoder); if (!hpo_link_enc) return NULL; /* out of memory */ @@ -1535,7 +1533,7 @@ static struct hpo_dp_stream_encoder *dcn60_hpo_dp_stream_encoder_create( apg_inst = hpo_dp_inst; /* allocate HPO stream encoder and create VPG sub-block */ - hpo_dp_enc60 = kzalloc(sizeof(struct dcn31_hpo_dp_stream_encoder), GFP_KERNEL); + hpo_dp_enc60 = kzalloc_obj(struct dcn31_hpo_dp_stream_encoder); vpg = dcn60_vpg_create(ctx, vpg_inst); apg = dcn60_apg_create(ctx, apg_inst); @@ -1568,7 +1566,7 @@ static struct hpo_dp_link_encoder *dcn60_hpo_dp_link_encoder_create( struct dcn31_hpo_dp_link_encoder *hpo_dp_enc60; /* allocate HPO link encoder */ - hpo_dp_enc60 = kzalloc(sizeof(struct dcn31_hpo_dp_link_encoder), GFP_KERNEL); + hpo_dp_enc60 = kzalloc_obj(struct dcn31_hpo_dp_link_encoder); if (!hpo_dp_enc60) return NULL; /* out of memory */ @@ -1589,7 +1587,7 @@ static struct hpo_dp_link_encoder *dcn60_hpo_dp_link_encoder_create( static struct dce_hwseq *dcn60_hwseq_create( struct dc_context *ctx) { - struct dce_hwseq *hws = kzalloc(sizeof(struct dce_hwseq), GFP_KERNEL); + struct dce_hwseq *hws = kzalloc_obj(struct dce_hwseq); #undef REG_STRUCT #define REG_STRUCT hwseq_reg @@ -1784,7 +1782,7 @@ static struct display_stream_compressor *dcn60_dsc_create( struct dc_context *ctx, uint32_t inst) { struct dcn60_dsc *dsc = - kzalloc(sizeof(struct dcn60_dsc), GFP_KERNEL); + kzalloc_obj(struct dcn60_dsc); if (!dsc) { BREAK_TO_DEBUGGER(); @@ -2363,7 +2361,7 @@ struct resource_pool *dcn60_create_resource_pool( struct dc *dc) { struct dcn60_resource_pool *pool = - kzalloc(sizeof(struct dcn60_resource_pool), GFP_KERNEL); + kzalloc_obj(struct dcn60_resource_pool); if (!pool) return NULL; diff --git a/drivers/gpu/drm/amd/display/modules/power/power.c b/drivers/gpu/drm/amd/display/modules/power/power.c index ee15c14a899e..2f9690e65ca9 100644 --- a/drivers/gpu/drm/amd/display/modules/power/power.c +++ b/drivers/gpu/drm/amd/display/modules/power/power.c @@ -111,7 +111,7 @@ struct mod_power *mod_power_create(struct dc *dc, if (dc == NULL) goto fail_dc_null; - core_power = kzalloc(sizeof(struct core_power), GFP_KERNEL); + core_power = kzalloc_obj(struct core_power); if (core_power == NULL) goto fail_alloc_context; @@ -129,8 +129,7 @@ struct mod_power *mod_power_create(struct dc *dc, for (i = 0; i < MOD_POWER_MAX_CONCURRENT_STREAMS; i++) { core_power->map[i].psr_context = - kzalloc(sizeof(struct mod_power_psr_context), - GFP_KERNEL); + kzalloc_obj(struct mod_power_psr_context); if (core_power->map[i].psr_context == NULL) goto fail_construct; } diff --git a/drivers/gpu/drm/amd/display/modules/power/power_abm.c b/drivers/gpu/drm/amd/display/modules/power/power_abm.c index 5e86889eaa84..5f27dea4aa0a 100644 --- a/drivers/gpu/drm/amd/display/modules/power/power_abm.c +++ b/drivers/gpu/drm/amd/display/modules/power/power_abm.c @@ -705,8 +705,7 @@ void initialize_backlight_caps(struct core_power *core_power, unsigned int inst) * (do not want to use 256 bytes on the stack) */ ext_backlight_caps = (struct dm_acpi_atif_backlight_caps *) - (kzalloc(sizeof(struct dm_acpi_atif_backlight_caps), - GFP_KERNEL)); + (kzalloc_obj(struct dm_acpi_atif_backlight_caps)); if (ext_backlight_caps == NULL) return; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index 2393fa8d4e4b..bdf1e489369e 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -2988,7 +2988,7 @@ static int smu7_init_voltage_dependency_on_display_clock_table(struct pp_hwmgr * if (!amdgpu_device_ip_get_ip_block(hwmgr->adev, AMD_IP_BLOCK_TYPE_DCE)) return 0; - table = kzalloc(struct_size(table, entries, 4), GFP_KERNEL); + table = kzalloc_flex(*table, entries, 4); if (!table) return -ENOMEM; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_8_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_8_ppt.c index aa4daf8f7d6f..4f820db5f8dd 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_8_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_8_ppt.c @@ -222,7 +222,7 @@ static int smu_v15_0_8_tables_init(struct smu_context *smu) smu_table->metrics_time = 0; - driver_pptable = kzalloc(sizeof(PPTable_t), GFP_KERNEL); + driver_pptable = kzalloc_obj(PPTable_t); if (!driver_pptable) return -ENOMEM; @@ -1026,7 +1026,7 @@ static int smu_v15_0_8_fru_get_product_info(struct smu_context *smu, struct amdgpu_device *adev = smu->adev; if (!adev->fru_info) { - adev->fru_info = kzalloc(sizeof(*adev->fru_info), GFP_KERNEL); + adev->fru_info = kzalloc_obj(*adev->fru_info); if (!adev->fru_info) return -ENOMEM; } diff --git a/drivers/gpu/drm/amd/ras/core/cmd.c b/drivers/gpu/drm/amd/ras/core/cmd.c index 6c37dc519eed..446b935c1fc9 100644 --- a/drivers/gpu/drm/amd/ras/core/cmd.c +++ b/drivers/gpu/drm/amd/ras/core/cmd.c @@ -222,7 +222,7 @@ static int ras_cmd_get_cper_records(struct ras_core_context *ras_core, if (!buffer) return RAS_CMD__ERROR_GENERIC; - trace = kcalloc(trace_count, sizeof(*trace), GFP_KERNEL); + trace = kzalloc_objs(*trace, trace_count); if (!trace) { ret = RAS_CMD__ERROR_GENERIC; goto out; @@ -316,7 +316,7 @@ static int ras_cmd_get_batch_trace_records(struct ras_core_context *ras_core, (input_data->start_batch_id >= overview.last_batch_id)) return RAS_CMD__ERROR_INVALID_INPUT_SIZE; - trace_arry = kcalloc(trace_count, sizeof(*trace_arry), GFP_KERNEL); + trace_arry = kzalloc_objs(*trace_arry, trace_count); if (!trace_arry) return RAS_CMD__ERROR_GENERIC; diff --git a/drivers/gpu/drm/drm_exec.c b/drivers/gpu/drm/drm_exec.c index fa923852fae4..41034a5996ff 100644 --- a/drivers/gpu/drm/drm_exec.c +++ b/drivers/gpu/drm/drm_exec.c @@ -79,7 +79,7 @@ void drm_exec_init(struct drm_exec *exec, u32 flags, unsigned nr) nr = PAGE_SIZE / sizeof(void *); exec->flags = flags; - exec->objects = kvmalloc_objs(*exec->objects, nr, GFP_KERNEL); + exec->objects = kvmalloc_objs(*exec->objects, nr); /* If allocation here fails, just delay that till the first use */ exec->max_objects = exec->objects ? nr : 0; diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c index 2fa170a29a62..c23a5de27eff 100644 --- a/drivers/gpu/drm/drm_syncobj.c +++ b/drivers/gpu/drm/drm_syncobj.c @@ -1619,7 +1619,7 @@ drm_syncobj_timeline_signal_ioctl(struct drm_device *dev, void *data, goto err_points; } - chains = kmalloc_objs(*chains, args->count_handles, GFP_KERNEL); + chains = kmalloc_objs(*chains, args->count_handles); if (!chains) { ret = -ENOMEM; goto err_points; diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c index 7f4178800afd..2fc41fb90aaa 100644 --- a/drivers/gpu/drm/qxl/qxl_display.c +++ b/drivers/gpu/drm/qxl/qxl_display.c @@ -981,7 +981,7 @@ static struct drm_plane *qxl_create_plane(struct qxl_device *qdev, return ERR_PTR(-EINVAL); } - plane = kzalloc(sizeof(*plane), GFP_KERNEL); + plane = kzalloc_obj(*plane); if (!plane) return ERR_PTR(-ENOMEM); diff --git a/drivers/gpu/drm/tilcdc/tilcdc_panel_legacy.c b/drivers/gpu/drm/tilcdc/tilcdc_panel_legacy.c index 2e7b3e87fea1..7583b6ebba2a 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_panel_legacy.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_panel_legacy.c @@ -22,7 +22,7 @@ tilcdc_panel_update_prop(struct of_changeset *ocs, struct device_node *node, { struct property *prop; - prop = kzalloc(sizeof(*prop), GFP_KERNEL); + prop = kzalloc_obj(*prop); if (!prop) return -ENOMEM; diff --git a/drivers/gpu/drm/verisilicon/vs_plane.c b/drivers/gpu/drm/verisilicon/vs_plane.c index d81f7b8f4c65..7ddb9d2dcb83 100644 --- a/drivers/gpu/drm/verisilicon/vs_plane.c +++ b/drivers/gpu/drm/verisilicon/vs_plane.c @@ -136,7 +136,7 @@ struct drm_plane_state *vs_plane_duplicate_state(struct drm_plane *plane) vs_state_old = to_vs_plane_state(plane->state); - vs_state = kzalloc_obj(*vs_state, GFP_KERNEL); + vs_state = kzalloc_obj(*vs_state); if (!vs_state) return NULL; @@ -166,7 +166,7 @@ void vs_plane_reset(struct drm_plane *plane) plane->state = NULL; } - vs_state = kzalloc_obj(*vs_state, GFP_KERNEL); + vs_state = kzalloc_obj(*vs_state); if (!vs_state) return; diff --git a/drivers/gpu/drm/virtio/virtgpu_prime.c b/drivers/gpu/drm/virtio/virtgpu_prime.c index 216c77cd0d21..149e6bcb5878 100644 --- a/drivers/gpu/drm/virtio/virtgpu_prime.c +++ b/drivers/gpu/drm/virtio/virtgpu_prime.c @@ -293,9 +293,7 @@ int virtgpu_dma_buf_obj_resubmit(struct virtio_gpu_device *vgdev, return -ENOMEM; } - ents = kvmalloc_array(bo->sgt->nents, - sizeof(struct virtio_gpu_mem_entry), - GFP_KERNEL); + ents = kvmalloc_objs(struct virtio_gpu_mem_entry, bo->sgt->nents); if (!ents) { DRM_ERROR("failed to allocate ent list\n"); return -ENOMEM; diff --git a/drivers/gpu/drm/vkms/vkms_configfs.c b/drivers/gpu/drm/vkms/vkms_configfs.c index 7551b8c7766d..601e3f128c9f 100644 --- a/drivers/gpu/drm/vkms/vkms_configfs.c +++ b/drivers/gpu/drm/vkms/vkms_configfs.c @@ -212,7 +212,7 @@ static struct config_group *make_crtc_group(struct config_group *group, if (dev->enabled) return ERR_PTR(-EBUSY); - crtc = kzalloc(sizeof(*crtc), GFP_KERNEL); + crtc = kzalloc_obj(*crtc); if (!crtc) return ERR_PTR(-ENOMEM); @@ -368,7 +368,7 @@ static struct config_group *make_plane_group(struct config_group *group, if (dev->enabled) return ERR_PTR(-EBUSY); - plane = kzalloc(sizeof(*plane), GFP_KERNEL); + plane = kzalloc_obj(*plane); if (!plane) return ERR_PTR(-ENOMEM); @@ -484,7 +484,7 @@ static struct config_group *make_encoder_group(struct config_group *group, if (dev->enabled) return ERR_PTR(-EBUSY); - encoder = kzalloc(sizeof(*encoder), GFP_KERNEL); + encoder = kzalloc_obj(*encoder); if (!encoder) return ERR_PTR(-ENOMEM); @@ -651,7 +651,7 @@ static struct config_group *make_connector_group(struct config_group *group, if (dev->enabled) return ERR_PTR(-EBUSY); - connector = kzalloc(sizeof(*connector), GFP_KERNEL); + connector = kzalloc_obj(*connector); if (!connector) return ERR_PTR(-ENOMEM); diff --git a/drivers/gpu/drm/xe/xe_amc.c b/drivers/gpu/drm/xe/xe_amc.c index 8ecadee6eea3..edd50bf8261e 100644 --- a/drivers/gpu/drm/xe/xe_amc.c +++ b/drivers/gpu/drm/xe/xe_amc.c @@ -177,7 +177,7 @@ int xe_amc_init(struct xe_i2c *i2c) { struct xe_amc *amc; - amc = kzalloc(sizeof(*amc), GFP_KERNEL); + amc = kzalloc_obj(*amc); if (!amc) return -ENOMEM; diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 9e0176861cb6..23952ad8951e 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -4148,7 +4148,7 @@ static int fill_faults(struct xe_vm *vm, entry_size = sizeof(struct xe_vm_fault); count = args->size / entry_size; - fault_list = kcalloc(count, sizeof(struct xe_vm_fault), GFP_KERNEL); + fault_list = kzalloc_objs(struct xe_vm_fault, count); if (!fault_list) return -ENOMEM; diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index ec966fc0a411..c38a2b3b33d9 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -406,7 +406,7 @@ static int asus_kbd_fn_lock_set(struct asus_drvdata *drvdata, bool enabled) struct asus_work_action *action; unsigned long flags; - action = kzalloc(sizeof(struct asus_work_action), GFP_ATOMIC); + action = kzalloc_obj(struct asus_work_action, GFP_ATOMIC); if (!action) return -ENOMEM; @@ -433,7 +433,7 @@ static int asus_kbd_wmi_fan_send(struct asus_drvdata *drvdata, u8 *report_data, return -EINVAL; } - action = kzalloc(sizeof(struct asus_work_action), GFP_NOWAIT); + action = kzalloc_obj(struct asus_work_action, GFP_NOWAIT); if (!action) return -ENOMEM; @@ -746,7 +746,7 @@ static void asus_kbd_backlight_set(struct asus_hid_listener *listener, int brigh drvdata->kbd_backlight_brightness = brightness; - action = kzalloc(sizeof(struct asus_work_action), GFP_NOWAIT); + action = kzalloc_obj(struct asus_work_action, GFP_NOWAIT); if (!action) return; diff --git a/drivers/hid/hid-steam.c b/drivers/hid/hid-steam.c index ac08cb2d0368..0f364d43aa4b 100644 --- a/drivers/hid/hid-steam.c +++ b/drivers/hid/hid-steam.c @@ -759,7 +759,7 @@ static inline int steam_haptic_pulse(struct steam_device *steam, u8 pad, if (steam->quirks & STEAM_QUIRK_IBEX) { struct steam_ibex_output_report *report = - kzalloc(sizeof(struct steam_ibex_output_report), GFP_KERNEL); + kzalloc_obj(struct steam_ibex_output_report); if (!report) return -ENOMEM; @@ -798,7 +798,7 @@ static inline int steam_haptic_rumble(struct steam_device *steam, if (steam->quirks & STEAM_QUIRK_IBEX) { struct steam_ibex_output_report *report = - kzalloc(sizeof(struct steam_ibex_output_report), GFP_KERNEL); + kzalloc_obj(struct steam_ibex_output_report); if (!report) return -ENOMEM; diff --git a/drivers/hid/hid-steelseries-arctis.c b/drivers/hid/hid-steelseries-arctis.c index 23fb0cebd72a..7a855b66730a 100644 --- a/drivers/hid/hid-steelseries-arctis.c +++ b/drivers/hid/hid-steelseries-arctis.c @@ -469,7 +469,7 @@ static int steelseries_arctis_probe(struct hid_device *hdev, return hid_hw_start(hdev, HID_CONNECT_DEFAULT); if (interface_num == info->sync_interface) { - sd = kzalloc_obj(*sd, GFP_KERNEL); + sd = kzalloc_obj(*sd); if (!sd) return -ENOMEM; diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index f4370617deac..7e4cc6f55237 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -694,12 +694,11 @@ void *vmbus_alloc_buffer(struct vmbus_channel *channel, return vzalloc(nr_pages << PAGE_SHIFT); /* Worst case: every chunk is a single page. */ - chunks = kvmalloc_array(nr_pages, sizeof(*chunks), - GFP_KERNEL | __GFP_ZERO); + chunks = kvmalloc_objs(*chunks, nr_pages, GFP_KERNEL | __GFP_ZERO); if (!chunks) goto err; - pages = kvmalloc_array(nr_pages, sizeof(*pages), GFP_KERNEL); + pages = kvmalloc_objs(*pages, nr_pages); if (!pages) goto err; diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index 9cba97e81111..39c1b793a893 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -939,7 +939,7 @@ static unsigned long process_hot_add(unsigned long pg_start, */ if (rg_size != 0) { - ha_region = kzalloc(sizeof(struct hv_hotadd_state), GFP_KERNEL); + ha_region = kzalloc_obj(struct hv_hotadd_state); if (!ha_region) return 0; diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c index ca56bd8b170e..00e603b5e401 100644 --- a/drivers/hwmon/applesmc.c +++ b/drivers/hwmon/applesmc.c @@ -1476,9 +1476,9 @@ static int __init applesmc_init(void) applesmc_fan_config[smcreg.fan_count] = 0; applesmc_pwm_config[smcreg.fan_count] = 0; - applesmc_info_temp = kzalloc_obj(*applesmc_info_temp, GFP_KERNEL); - applesmc_info_fan = kzalloc_obj(*applesmc_info_fan, GFP_KERNEL); - applesmc_info_pwm = kzalloc_obj(*applesmc_info_pwm, GFP_KERNEL); + applesmc_info_temp = kzalloc_obj(*applesmc_info_temp); + applesmc_info_fan = kzalloc_obj(*applesmc_info_fan); + applesmc_info_pwm = kzalloc_obj(*applesmc_info_pwm); if (!applesmc_info_temp || !applesmc_info_fan || !applesmc_info_pwm) { ret = -ENOMEM; goto out_info; @@ -1493,7 +1493,7 @@ static int __init applesmc_init(void) applesmc_info_pwm->type = hwmon_pwm; applesmc_info_pwm->config = applesmc_pwm_config; - applesmc_info_arr = kcalloc(4, sizeof(*applesmc_info_arr), GFP_KERNEL); + applesmc_info_arr = kzalloc_objs(*applesmc_info_arr, 4); if (!applesmc_info_arr) { ret = -ENOMEM; goto out_info; @@ -1504,7 +1504,7 @@ static int __init applesmc_init(void) applesmc_info_arr[2] = applesmc_info_pwm; applesmc_info_arr[3] = NULL; - applesmc_chip = kzalloc_obj(*applesmc_chip, GFP_KERNEL); + applesmc_chip = kzalloc_obj(*applesmc_chip); if (!applesmc_chip) { ret = -ENOMEM; goto out_info; @@ -1514,10 +1514,9 @@ static int __init applesmc_init(void) applesmc_chip->info = applesmc_info_arr; /* Create non-standard fanX_safe attributes group */ - fan_safe_attrs = kcalloc(smcreg.fan_count, - sizeof(*fan_safe_attrs), GFP_KERNEL); - fan_safe_attr_list = kcalloc(smcreg.fan_count + 1, - sizeof(*fan_safe_attr_list), GFP_KERNEL); + fan_safe_attrs = kzalloc_objs(*fan_safe_attrs, smcreg.fan_count); + fan_safe_attr_list = kzalloc_objs(*fan_safe_attr_list, + smcreg.fan_count + 1); if (!fan_safe_attrs || !fan_safe_attr_list) { ret = -ENOMEM; goto out_info; diff --git a/drivers/hwtracing/coresight/coresight-core.c b/drivers/hwtracing/coresight/coresight-core.c index 6d65c43d574f..928488a216d4 100644 --- a/drivers/hwtracing/coresight/coresight-core.c +++ b/drivers/hwtracing/coresight/coresight-core.c @@ -1679,7 +1679,7 @@ coresight_allocate_device_list(const char *prefix) return list; } - list = kzalloc(sizeof(*list), GFP_KERNEL); + list = kzalloc_obj(*list); if (!list) return NULL; diff --git a/drivers/i2c/busses/i2c-gpio.c b/drivers/i2c/busses/i2c-gpio.c index b7521b7ece37..6294b0b0cc8f 100644 --- a/drivers/i2c/busses/i2c-gpio.c +++ b/drivers/i2c/busses/i2c-gpio.c @@ -418,7 +418,7 @@ static struct i2c_gpio_scl_data *i2c_gpio_create_scl(struct device *dev) } } - scl = kzalloc(sizeof(*scl), GFP_KERNEL); + scl = kzalloc_obj(*scl); if (!scl) { if (sharable) fwnode_handle_put(args.fwnode); diff --git a/drivers/i3c/master/amd-i3c-master.c b/drivers/i3c/master/amd-i3c-master.c index ef5ad5abb788..e4da9c38eccb 100644 --- a/drivers/i3c/master/amd-i3c-master.c +++ b/drivers/i3c/master/amd-i3c-master.c @@ -376,7 +376,7 @@ static struct xi3c_xfer *xi3c_master_alloc_xfer(unsigned int ncmds) { struct xi3c_xfer *xfer; - xfer = kzalloc_flex(*xfer, cmds, ncmds, GFP_KERNEL); + xfer = kzalloc_flex(*xfer, cmds, ncmds); if (!xfer) return NULL; @@ -735,7 +735,7 @@ static int xi3c_master_send_bdcast_ccc_cmd(struct xi3c_master *master, if (!xfer) return -ENOMEM; - buf = kmalloc_objs(*buf, xfer_len, GFP_KERNEL); + buf = kmalloc_objs(*buf, xfer_len); if (!buf) return -ENOMEM; diff --git a/drivers/iio/adc/ad7280a.c b/drivers/iio/adc/ad7280a.c index 505fa68ee539..5ae0d694d20c 100644 --- a/drivers/iio/adc/ad7280a.c +++ b/drivers/iio/adc/ad7280a.c @@ -796,8 +796,8 @@ static irqreturn_t ad7280_event_handler(int irq, void *private) struct ad7280_state *st = iio_priv(indio_dev); int i, ret; - unsigned int *channels __free(kfree) = kcalloc(st->scan_cnt, sizeof(*channels), - GFP_KERNEL); + unsigned int *channels __free(kfree) = kzalloc_objs(*channels, + st->scan_cnt); if (!channels) return IRQ_HANDLED; diff --git a/drivers/iio/buffer/industrialio-buffer-dmaengine.c b/drivers/iio/buffer/industrialio-buffer-dmaengine.c index ecc02a427b92..1bd82d3db5ea 100644 --- a/drivers/iio/buffer/industrialio-buffer-dmaengine.c +++ b/drivers/iio/buffer/industrialio-buffer-dmaengine.c @@ -109,7 +109,7 @@ static int iio_dmaengine_buffer_submit_block(struct iio_dma_buffer_queue *queue, if (nents < 0) return nents; - vecs = kmalloc_array(nents, sizeof(*vecs), GFP_ATOMIC); + vecs = kmalloc_objs(*vecs, nents, GFP_ATOMIC); if (!vecs) return -ENOMEM; diff --git a/drivers/iio/inkern.c b/drivers/iio/inkern.c index fb08e4f02520..1f22275de55c 100644 --- a/drivers/iio/inkern.c +++ b/drivers/iio/inkern.c @@ -345,7 +345,7 @@ static struct iio_channel *iio_channel_get_sys(const char *name, return ERR_PTR(-ENODEV); struct iio_channel *channel __free(kfree) = - kzalloc(sizeof(*channel), GFP_KERNEL); + kzalloc_obj(*channel); if (!channel) { err = -ENOMEM; goto error_no_mem; diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index a4014a230639..4e8fbee34745 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -2943,7 +2943,7 @@ static int nldev_frmr_pools_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh, u32 aging_period; int err; - tb = kzalloc_objs(*tb, RDMA_NLDEV_ATTR_MAX, GFP_KERNEL); + tb = kzalloc_objs(*tb, RDMA_NLDEV_ATTR_MAX); if (!tb) return -ENOMEM; diff --git a/drivers/infiniband/hw/hns/hns_roce_debugfs.c b/drivers/infiniband/hw/hns/hns_roce_debugfs.c index 05630f7c9155..103b8c9ca969 100644 --- a/drivers/infiniband/hw/hns/hns_roce_debugfs.c +++ b/drivers/infiniband/hw/hns/hns_roce_debugfs.c @@ -267,8 +267,7 @@ static int hns_roce_alloc_scc_param(struct hns_roce_dev *hr_dev) struct hns_roce_scc_param *scc_param; int i; - scc_param = kvcalloc(HNS_ROCE_SCC_ALGO_TOTAL, sizeof(*scc_param), - GFP_KERNEL); + scc_param = kvzalloc_objs(*scc_param, HNS_ROCE_SCC_ALGO_TOTAL); if (!scc_param) return -ENOMEM; diff --git a/drivers/input/input.c b/drivers/input/input.c index 78c10eea7328..01c91fec9b7e 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -2344,7 +2344,7 @@ static int input_device_tune_vals(struct input_dev *dev) if (dev->max_vals >= max_vals) return 0; - vals = kcalloc(max_vals, sizeof(*vals), GFP_KERNEL); + vals = kzalloc_objs(*vals, max_vals); if (!vals) return -ENOMEM; diff --git a/drivers/input/keyboard/adp5585-keys.c b/drivers/input/keyboard/adp5585-keys.c index 017c95029180..f2c1ba017d20 100644 --- a/drivers/input/keyboard/adp5585-keys.c +++ b/drivers/input/keyboard/adp5585-keys.c @@ -115,8 +115,8 @@ static int adp5585_keys_parse_fw(const struct adp5585_dev *adp5585, "Too many keypad pins (%d) defined (max=%d)\n", n_pins, adp5585->n_pins); - unsigned int *keypad_pins __free(kfree) = kcalloc(n_pins, sizeof(*keypad_pins), - GFP_KERNEL); + unsigned int *keypad_pins __free(kfree) = kzalloc_objs(*keypad_pins, + n_pins); if (!keypad_pins) return -ENOMEM; diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c index 5736f4bc5a50..b9ad2381f885 100644 --- a/drivers/input/keyboard/atkbd.c +++ b/drivers/input/keyboard/atkbd.c @@ -1070,7 +1070,7 @@ static int atkbd_get_keymap_from_fwnode(struct atkbd *atkbd) if (n <= 0 || n > ATKBD_KEYMAP_SIZE) return -ENXIO; - u32 *ptr __free(kfree) = kcalloc(n, sizeof(*ptr), GFP_KERNEL); + u32 *ptr __free(kfree) = kzalloc_objs(*ptr, n); if (!ptr) return -ENOMEM; diff --git a/drivers/input/misc/ims-pcu.c b/drivers/input/misc/ims-pcu.c index b1a0edcc49b4..c3244c1a3751 100644 --- a/drivers/input/misc/ims-pcu.c +++ b/drivers/input/misc/ims-pcu.c @@ -1844,7 +1844,7 @@ static int ims_pcu_line_setup(struct ims_pcu *pcu) { struct usb_host_interface *interface = pcu->ctrl_intf->cur_altsetting; struct usb_cdc_line_coding *line __free(kfree) = - kmalloc(sizeof(*line), GFP_KERNEL); + kmalloc_obj(*line); int error; if (!line) diff --git a/drivers/input/mouse/psmouse-smbus.c b/drivers/input/mouse/psmouse-smbus.c index 7fb4cbb2aca2..98d9c860d2db 100644 --- a/drivers/input/mouse/psmouse-smbus.c +++ b/drivers/input/mouse/psmouse-smbus.c @@ -232,7 +232,7 @@ int psmouse_smbus_init(struct psmouse *psmouse, struct psmouse_smbus_dev *smbdev; int error; - smbdev = kzalloc(sizeof(*smbdev), GFP_KERNEL); + smbdev = kzalloc_obj(*smbdev); if (!smbdev) return -ENOMEM; diff --git a/drivers/input/serio/serio_raw.c b/drivers/input/serio/serio_raw.c index a7ccedfa459c..868dee9a2ed8 100644 --- a/drivers/input/serio/serio_raw.c +++ b/drivers/input/serio/serio_raw.c @@ -84,7 +84,7 @@ static int serio_raw_open(struct inode *inode, struct file *file) if (serio_raw->dead) return -ENODEV; - client = kzalloc(sizeof(*client), GFP_KERNEL); + client = kzalloc_obj(*client); if (!client) return -ENOMEM; diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h index 50f8321e979c..dd2fee2f560e 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -796,7 +796,7 @@ static inline struct arm_smmu_invs *arm_smmu_invs_alloc(size_t num_invs) { struct arm_smmu_invs *new_invs; - new_invs = kzalloc(struct_size(new_invs, inv, num_invs), GFP_KERNEL); + new_invs = kzalloc_flex(*new_invs, inv, num_invs); if (!new_invs) return NULL; new_invs->max_invs = num_invs; diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c index 5c4b06eda546..a664c70a6fe7 100644 --- a/drivers/iommu/iommufd/device.c +++ b/drivers/iommu/iommufd/device.c @@ -76,7 +76,7 @@ static struct iommufd_group *iommufd_alloc_group(struct iommufd_ctx *ictx, { struct iommufd_group *new_igroup; - new_igroup = kzalloc_obj(*new_igroup, GFP_KERNEL); + new_igroup = kzalloc_obj(*new_igroup); if (!new_igroup) return ERR_PTR(-ENOMEM); diff --git a/drivers/iommu/iommufd/driver.c b/drivers/iommu/iommufd/driver.c index 3b8067976eac..e4d17a748178 100644 --- a/drivers/iommu/iommufd/driver.c +++ b/drivers/iommu/iommufd/driver.c @@ -49,7 +49,7 @@ int _iommufd_alloc_mmap(struct iommufd_ctx *ictx, struct iommufd_object *owner, if (!length || !PAGE_ALIGNED(length)) return -EINVAL; - immap = kzalloc(sizeof(*immap), GFP_KERNEL); + immap = kzalloc_obj(*immap); if (!immap) return -ENOMEM; immap->owner = owner; diff --git a/drivers/iommu/iommufd/hwpt_noiommu.c b/drivers/iommu/iommufd/hwpt_noiommu.c index 9b8b5eb71491..a80209a7429a 100644 --- a/drivers/iommu/iommufd/hwpt_noiommu.c +++ b/drivers/iommu/iommufd/hwpt_noiommu.c @@ -54,7 +54,7 @@ noiommu_alloc_paging_flags(struct device *dev, u32 flags, (BIT(PT_FEAT_DYNAMIC_TOP) | BIT(PT_FEAT_AMDV1_ENCRYPT_TABLES) | BIT(PT_FEAT_AMDV1_FORCE_COHERENCE)); - dom = kzalloc(sizeof(*dom), GFP_KERNEL); + dom = kzalloc_obj(*dom); if (!dom) return ERR_PTR(-ENOMEM); diff --git a/drivers/iommu/vsi-iommu.c b/drivers/iommu/vsi-iommu.c index 42c424496d07..5dac20b143a5 100644 --- a/drivers/iommu/vsi-iommu.c +++ b/drivers/iommu/vsi-iommu.c @@ -231,7 +231,7 @@ static struct iommu_domain *vsi_iommu_domain_alloc_paging(struct device *dev) struct vsi_iommu *iommu = dev_iommu_priv_get(dev); struct vsi_iommu_domain *vsi_domain; - vsi_domain = kzalloc(sizeof(*vsi_domain), GFP_KERNEL); + vsi_domain = kzalloc_obj(*vsi_domain); if (!vsi_domain) return NULL; diff --git a/drivers/irqchip/irq-gic-v5-irs.c b/drivers/irqchip/irq-gic-v5-irs.c index b3feb6340b59..4486645a4b6f 100644 --- a/drivers/irqchip/irq-gic-v5-irs.c +++ b/drivers/irqchip/irq-gic-v5-irs.c @@ -618,7 +618,7 @@ static int __init gicv5_irs_of_init_affinity(struct device_node *node, if (niaffids != ncpus) return -EINVAL; - u16 *iaffids __free(kfree) = kcalloc(niaffids, sizeof(*iaffids), GFP_KERNEL); + u16 *iaffids __free(kfree) = kzalloc_objs(*iaffids, niaffids); if (!iaffids) return -ENOMEM; diff --git a/drivers/irqchip/irq-loongarch-ir.c b/drivers/irqchip/irq-loongarch-ir.c index 21c649a89a70..cb4ad34da058 100644 --- a/drivers/irqchip/irq-loongarch-ir.c +++ b/drivers/irqchip/irq-loongarch-ir.c @@ -331,7 +331,7 @@ static int redirect_domain_alloc(struct irq_domain *domain, unsigned int virq, struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq + i); struct redirect_item *item; - item = kzalloc(sizeof(*item), GFP_KERNEL); + item = kzalloc_obj(*item); if (!item) { pr_err("Alloc redirect descriptor failed\n"); goto out_free_resources; diff --git a/drivers/irqchip/irq-realtek-rtl.c b/drivers/irqchip/irq-realtek-rtl.c index 26e52c3f8c68..f1ab5a77dcef 100644 --- a/drivers/irqchip/irq-realtek-rtl.c +++ b/drivers/irqchip/irq-realtek-rtl.c @@ -188,7 +188,7 @@ static int __init realtek_setup_parents(struct device_node *node) struct irq_domain *domain; cnt = max(1, num_parents); - output = kcalloc(cnt, sizeof(*output), GFP_KERNEL); + output = kzalloc_objs(*output, cnt); if (!output) return -ENOMEM; diff --git a/drivers/mailbox/riscv-sbi-mpxy-mbox.c b/drivers/mailbox/riscv-sbi-mpxy-mbox.c index 714f7fb97a2f..ea69c6b6b4f9 100644 --- a/drivers/mailbox/riscv-sbi-mpxy-mbox.c +++ b/drivers/mailbox/riscv-sbi-mpxy-mbox.c @@ -783,7 +783,7 @@ static int mpxy_mbox_populate_channels(struct mpxy_mbox *mbox) return dev_err_probe(mbox->dev, -ENODEV, "no MPXY channels available\n"); /* Allocate and fetch all channel IDs */ - channel_ids = kcalloc(mbox->channel_count, sizeof(*channel_ids), GFP_KERNEL); + channel_ids = kzalloc_objs(*channel_ids, mbox->channel_count); if (!channel_ids) return -ENOMEM; rc = mpxy_get_channel_ids(mbox->channel_count, channel_ids); diff --git a/drivers/md/dm-inlinecrypt.c b/drivers/md/dm-inlinecrypt.c index 66fa2f9d1fdc..3479dfe5f708 100644 --- a/drivers/md/dm-inlinecrypt.c +++ b/drivers/md/dm-inlinecrypt.c @@ -322,7 +322,7 @@ static int inlinecrypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) return -EINVAL; } - ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + ctx = kzalloc_obj(*ctx); if (!ctx) { ti->error = "Out of memory"; return -ENOMEM; diff --git a/drivers/md/md-llbitmap.c b/drivers/md/md-llbitmap.c index e1a783ee2032..1c9fcc746ec6 100644 --- a/drivers/md/md-llbitmap.c +++ b/drivers/md/md-llbitmap.c @@ -810,7 +810,7 @@ static int llbitmap_expand_pages(struct llbitmap *llbitmap, if (nr_pages <= old_nr_pages) return 0; - pctl = kcalloc(nr_pages, sizeof(*pctl), GFP_NOIO); + pctl = kzalloc_objs(*pctl, nr_pages, GFP_NOIO); if (!pctl) return -ENOMEM; @@ -846,7 +846,7 @@ static int llbitmap_alloc_pages(struct llbitmap *llbitmap) unsigned int nr_pages = max(used_pages, llbitmap_reserved_pages(llbitmap)); int i; - llbitmap->pctl = kcalloc(nr_pages, sizeof(*llbitmap->pctl), GFP_NOIO); + llbitmap->pctl = kzalloc_objs(*llbitmap->pctl, nr_pages, GFP_NOIO); if (!llbitmap->pctl) return -ENOMEM; diff --git a/drivers/media/platform/allegro-dvt/allegro-core.c b/drivers/media/platform/allegro-dvt/allegro-core.c index eac3bc9af990..4f3299a66b37 100644 --- a/drivers/media/platform/allegro-dvt/allegro-core.c +++ b/drivers/media/platform/allegro-dvt/allegro-core.c @@ -3105,7 +3105,7 @@ static int allegro_open(struct file *file) unsigned int cpb_size_max; unsigned int cpb_size_def; - channel = kzalloc(sizeof(*channel), GFP_KERNEL); + channel = kzalloc_obj(*channel); if (!channel) return -ENOMEM; diff --git a/drivers/media/platform/amd/isp4/isp4_interface.c b/drivers/media/platform/amd/isp4/isp4_interface.c index 4801617f9559..218aad5d7dfb 100644 --- a/drivers/media/platform/amd/isp4/isp4_interface.c +++ b/drivers/media/platform/amd/isp4/isp4_interface.c @@ -127,7 +127,7 @@ isp4if_gpu_mem_alloc(struct isp4_interface *ispif, u32 mem_size) struct device *dev = ispif->dev; int ret; - mem_info = kmalloc_obj(*mem_info, GFP_KERNEL); + mem_info = kmalloc_obj(*mem_info); if (!mem_info) return NULL; @@ -368,7 +368,7 @@ static int isp4if_send_fw_cmd(struct isp4_interface *ispif, u32 cmd_id, /* Allocate the sync command object early and outside of the lock */ if (sync) { - ele = kmalloc_obj(*ele, GFP_KERNEL); + ele = kmalloc_obj(*ele); if (!ele) return -ENOMEM; @@ -738,7 +738,7 @@ isp4if_alloc_buffer_node(struct isp4if_img_buf_info *buf_info) { struct isp4if_img_buf_node *node; - node = kmalloc_obj(*node, GFP_KERNEL); + node = kmalloc_obj(*node); if (node) node->buf_info = *buf_info; diff --git a/drivers/media/platform/renesas/rcar-isp/core.c b/drivers/media/platform/renesas/rcar-isp/core.c index b5861d0cd0e8..586a5adbedfa 100644 --- a/drivers/media/platform/renesas/rcar-isp/core.c +++ b/drivers/media/platform/renesas/rcar-isp/core.c @@ -232,7 +232,7 @@ int risp_core_job_prepare(struct rcar_isp_core *core) } /* Memory is released when the job is consumed. */ - job = kzalloc(sizeof(*job), GFP_KERNEL); + job = kzalloc_obj(*job); if (!job) return -ENOMEM; diff --git a/drivers/media/rc/igorplugusb.c b/drivers/media/rc/igorplugusb.c index b5117ee9f5fa..7758487da3d3 100644 --- a/drivers/media/rc/igorplugusb.c +++ b/drivers/media/rc/igorplugusb.c @@ -164,7 +164,7 @@ static int igorplugusb_probe(struct usb_interface *intf, if (!ir) return -ENOMEM; - ir->request = kzalloc_obj(*ir->request, GFP_KERNEL); + ir->request = kzalloc_obj(*ir->request); if (!ir->request) goto fail; diff --git a/drivers/mfd/mfd-core.c b/drivers/mfd/mfd-core.c index 7aa32b90cf1e..16ad4fd26357 100644 --- a/drivers/mfd/mfd-core.c +++ b/drivers/mfd/mfd-core.c @@ -135,7 +135,7 @@ static int mfd_match_of_node_to_dev(struct platform_device *pdev, return -EAGAIN; allocate_of_node: - of_entry = kzalloc(sizeof(*of_entry), GFP_KERNEL); + of_entry = kzalloc_obj(*of_entry); if (!of_entry) return -ENOMEM; @@ -174,7 +174,7 @@ static int mfd_add_device(struct device *parent, int id, if (!pdev->mfd_cell) goto fail_device; - res = kcalloc(cell->num_resources, sizeof(*res), GFP_KERNEL); + res = kzalloc_objs(*res, cell->num_resources); if (!res) goto fail_device; diff --git a/drivers/mfd/ucb1x00-assabet.c b/drivers/mfd/ucb1x00-assabet.c index ee49ac779d1a..698f60aa9756 100644 --- a/drivers/mfd/ucb1x00-assabet.c +++ b/drivers/mfd/ucb1x00-assabet.c @@ -96,7 +96,7 @@ static int ucb1x00_assabet_add(struct ucb1x00_dev *dev) struct ucb1x00_assabet_priv *priv; - priv = kzalloc_obj(*priv, GFP_KERNEL); + priv = kzalloc_obj(*priv); if (!priv) return -ENOMEM; diff --git a/drivers/mtd/mtd_virt_concat.c b/drivers/mtd/mtd_virt_concat.c index da4277ced4d6..25cf33fe1ec1 100644 --- a/drivers/mtd/mtd_virt_concat.c +++ b/drivers/mtd/mtd_virt_concat.c @@ -166,7 +166,7 @@ static int mtd_virt_concat_create_item(struct device_node *parts, return 0; } - item = kzalloc_flex(*item, nodes, count, GFP_KERNEL); + item = kzalloc_flex(*item, nodes, count); if (!item) return -ENOMEM; @@ -182,7 +182,7 @@ static int mtd_virt_concat_create_item(struct device_node *parts, for (i = 1; i < count; i++) item->nodes[i] = of_parse_phandle(parts, CONCAT_PROP, (i - 1)); - concat = kzalloc_flex(*concat, subdev, count, GFP_KERNEL); + concat = kzalloc_flex(*concat, subdev, count); if (!concat) { kfree(item); return -ENOMEM; diff --git a/drivers/mtd/mtdconcat.c b/drivers/mtd/mtdconcat.c index c97167d51fe2..d54d309c30a0 100644 --- a/drivers/mtd/mtdconcat.c +++ b/drivers/mtd/mtdconcat.c @@ -639,7 +639,7 @@ struct mtd_info *mtd_concat_create(struct mtd_info *subdev[], /* subdevices to c printk(KERN_NOTICE "into device \"%s\"\n", name); /* allocate the device structure */ - concat = kzalloc_flex(*concat, subdev, num_devs, GFP_KERNEL); + concat = kzalloc_flex(*concat, subdev, num_devs); if (!concat) { printk ("memory allocation error while creating concatenated device \"%s\"\n", diff --git a/drivers/net/dsa/mv88e6xxx/tcflower.c b/drivers/net/dsa/mv88e6xxx/tcflower.c index d67604a55b9f..2ddfeaaa0690 100644 --- a/drivers/net/dsa/mv88e6xxx/tcflower.c +++ b/drivers/net/dsa/mv88e6xxx/tcflower.c @@ -97,7 +97,7 @@ int mv88e6xxx_cls_flower_add(struct dsa_switch *ds, int port, goto err_unlock; } - entry = kzalloc(sizeof(*entry), GFP_KERNEL); + entry = kzalloc_obj(*entry); if (!entry) { err = -ENOMEM; goto err_unlock; diff --git a/drivers/net/ethernet/alibaba/eea/eea_adminq.c b/drivers/net/ethernet/alibaba/eea/eea_adminq.c index dfad1bdbc44d..73d0caf25700 100644 --- a/drivers/net/ethernet/alibaba/eea/eea_adminq.c +++ b/drivers/net/ethernet/alibaba/eea/eea_adminq.c @@ -439,8 +439,7 @@ int eea_adminq_dev_status(struct eea_net *enet, q_num = enet->cfg.rx_ring_num + enet->cfg.tx_ring_num + 1; io_num = enet->cfg.rx_ring_num + enet->cfg.tx_ring_num; - req = kcalloc(q_num, sizeof(struct eea_aq_queue_drv_status), - GFP_KERNEL); + req = kzalloc_objs(struct eea_aq_queue_drv_status, q_num); if (!req) return -ENOMEM; @@ -486,11 +485,11 @@ void eea_adminq_config_host_info(struct eea_net *enet) struct eea_aq_host_info_rep *rep; int rc = -ENOMEM; - cfg = kzalloc(sizeof(*cfg), GFP_KERNEL); + cfg = kzalloc_obj(*cfg); if (!cfg) return; - rep = kzalloc(sizeof(*rep), GFP_KERNEL); + rep = kzalloc_obj(*rep); if (!rep) goto err_free_cfg; diff --git a/drivers/net/ethernet/alibaba/eea/eea_net.c b/drivers/net/ethernet/alibaba/eea/eea_net.c index 63e68580de94..0af6c95b5e63 100644 --- a/drivers/net/ethernet/alibaba/eea/eea_net.c +++ b/drivers/net/ethernet/alibaba/eea/eea_net.c @@ -62,7 +62,7 @@ static int eea_alloc_irq_blks(struct eea_net *enet) num = enet->edev->rx_num; - irq_blks = kvcalloc(num, sizeof(*blk), GFP_KERNEL); + irq_blks = kvzalloc_objs(*blk, num); if (!irq_blks) return -ENOMEM; @@ -194,11 +194,11 @@ static int eea_alloc_rxtx_q_mem(struct eea_net_init_ctx *ctx) struct eea_net_tx *tx; int err, i; - ctx->tx = kvcalloc(ctx->cfg.tx_ring_num, sizeof(*ctx->tx), GFP_KERNEL); + ctx->tx = kvzalloc_objs(*ctx->tx, ctx->cfg.tx_ring_num); if (!ctx->tx) return -ENOMEM; - ctx->rx = kvcalloc(ctx->cfg.rx_ring_num, sizeof(*ctx->rx), GFP_KERNEL); + ctx->rx = kvzalloc_objs(*ctx->rx, ctx->cfg.rx_ring_num); if (!ctx->rx) goto err_free_tx; @@ -601,7 +601,7 @@ static int eea_netdev_init_features(struct net_device *netdev, int err; u32 mtu; - cfg = kzalloc(sizeof(*cfg), GFP_KERNEL); + cfg = kzalloc_obj(*cfg); if (!cfg) return -ENOMEM; diff --git a/drivers/net/ethernet/alibaba/eea/eea_pci.c b/drivers/net/ethernet/alibaba/eea/eea_pci.c index 9872e360dd5d..c625b58b26f0 100644 --- a/drivers/net/ethernet/alibaba/eea/eea_pci.c +++ b/drivers/net/ethernet/alibaba/eea/eea_pci.c @@ -651,7 +651,7 @@ static int eea_pci_probe(struct pci_dev *pci_dev, struct eea_device *edev; int err; - ep_dev = kzalloc(sizeof(*ep_dev), GFP_KERNEL); + ep_dev = kzalloc_obj(*ep_dev); if (!ep_dev) return -ENOMEM; diff --git a/drivers/net/ethernet/alibaba/eea/eea_ring.c b/drivers/net/ethernet/alibaba/eea/eea_ring.c index 99dcabd094b8..fac7d4647ecb 100644 --- a/drivers/net/ethernet/alibaba/eea/eea_ring.c +++ b/drivers/net/ethernet/alibaba/eea/eea_ring.c @@ -217,7 +217,7 @@ struct eea_ring *eea_ering_alloc(u32 index, u32 num, struct eea_device *edev, if (!cq_desc_size || !is_power_of_2(cq_desc_size)) return NULL; - ering = kzalloc(sizeof(*ering), GFP_KERNEL); + ering = kzalloc_obj(*ering); if (!ering) return NULL; diff --git a/drivers/net/ethernet/alibaba/eea/eea_rx.c b/drivers/net/ethernet/alibaba/eea/eea_rx.c index a3f0d2a79ad8..5dfb7cb2ba6d 100644 --- a/drivers/net/ethernet/alibaba/eea/eea_rx.c +++ b/drivers/net/ethernet/alibaba/eea/eea_rx.c @@ -764,7 +764,7 @@ struct eea_net_rx *eea_alloc_rx(struct eea_net_init_ctx *ctx, u32 idx) struct eea_net_rx *rx; int err; - rx = kzalloc(sizeof(*rx), GFP_KERNEL); + rx = kzalloc_obj(*rx); if (!rx) return rx; @@ -786,8 +786,7 @@ struct eea_net_rx *eea_alloc_rx(struct eea_net_init_ctx *ctx, u32 idx) rx->dma_dev = ctx->edev->dma_dev; /* meta */ - rx->meta = kvcalloc(ctx->cfg.rx_ring_depth, - sizeof(*rx->meta), GFP_KERNEL); + rx->meta = kvzalloc_objs(*rx->meta, ctx->cfg.rx_ring_depth); if (!rx->meta) goto err_free_rx; diff --git a/drivers/net/ethernet/alibaba/eea/eea_tx.c b/drivers/net/ethernet/alibaba/eea/eea_tx.c index 85fb0e9ca5ba..c9292bca1a8b 100644 --- a/drivers/net/ethernet/alibaba/eea/eea_tx.c +++ b/drivers/net/ethernet/alibaba/eea/eea_tx.c @@ -480,8 +480,7 @@ int eea_alloc_tx(struct eea_net_init_ctx *ctx, struct eea_net_tx *tx, u32 idx) tx->dma_dev = ctx->edev->dma_dev; /* meta */ - tx->meta = kvcalloc(ctx->cfg.tx_ring_depth, - sizeof(*tx->meta), GFP_KERNEL); + tx->meta = kvzalloc_objs(*tx->meta, ctx->cfg.tx_ring_depth); if (!tx->meta) goto err_free_tx; diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c index 922e3ec8af1b..419e4b6ac983 100644 --- a/drivers/net/ethernet/amd/pds_core/core.c +++ b/drivers/net/ethernet/amd/pds_core/core.c @@ -810,8 +810,7 @@ void pdsc_host_mem_add(struct pdsc *pdsc) if (count == 0) return; - pdsc->host_mem_reqs = kzalloc_objs(*pdsc->host_mem_reqs, count, - GFP_KERNEL); + pdsc->host_mem_reqs = kzalloc_objs(*pdsc->host_mem_reqs, count); if (!pdsc->host_mem_reqs) { dev_err(pdsc->dev, "failed to alloc host_mem_reqs array\n"); return; diff --git a/drivers/net/ethernet/amd/pds_core/fw.c b/drivers/net/ethernet/amd/pds_core/fw.c index 5ccf017f6af4..8551ce3cd86a 100644 --- a/drivers/net/ethernet/amd/pds_core/fw.c +++ b/drivers/net/ethernet/amd/pds_core/fw.c @@ -382,7 +382,7 @@ static int pdsc_send_package_data(struct pldmfw *context, const u8 *data, if (!length) return 0; - deferred = kmalloc_obj(*deferred, GFP_KERNEL); + deferred = kmalloc_obj(*deferred); if (!deferred) return -ENOMEM; @@ -505,7 +505,7 @@ static int pdsc_send_component_table(struct pldmfw *context, component->version_string, component->index, component->component_size, transfer_flag); - component_priv = kzalloc_obj(*component_priv, GFP_KERNEL); + component_priv = kzalloc_obj(*component_priv); if (!component_priv) return -ENOMEM; @@ -710,7 +710,7 @@ static int pdsc_flash_component_chunk(struct pdsc *pdsc, struct device *dev, u8 *component_data; int err; - deferred = kmalloc_obj(*deferred, GFP_KERNEL); + deferred = kmalloc_obj(*deferred); if (!deferred) return -ENOMEM; diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index b1939da4c95a..daa8a4a149e9 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -4334,7 +4334,7 @@ static int macb_taprio_setup_replace(struct net_device *netdev, return -EINVAL; } - enst_queue = kcalloc(conf->num_entries, sizeof(*enst_queue), GFP_KERNEL); + enst_queue = kzalloc_objs(*enst_queue, conf->num_entries); if (unlikely(!enst_queue)) return -ENOMEM; diff --git a/drivers/net/ethernet/cisco/enic/enic_admin.c b/drivers/net/ethernet/cisco/enic/enic_admin.c index 7188f1b81c04..61c82b48044d 100644 --- a/drivers/net/ethernet/cisco/enic/enic_admin.c +++ b/drivers/net/ethernet/cisco/enic/enic_admin.c @@ -137,7 +137,7 @@ static void enic_admin_msg_enqueue(struct enic *enic, void *buf, { struct enic_admin_msg *msg; - msg = kmalloc(struct_size(msg, data, len), GFP_KERNEL); + msg = kmalloc_flex(*msg, data, len); if (!msg) return; diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index 0baef7a120ec..65830c1d3ff6 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -2858,7 +2858,7 @@ enic_sriov_v2_enable(struct enic *enic, int num_vfs) return -EOPNOTSUPP; } - enic->vf_state = kcalloc(num_vfs, sizeof(*enic->vf_state), GFP_KERNEL); + enic->vf_state = kzalloc_objs(*enic->vf_state, num_vfs); if (!enic->vf_state) return -ENOMEM; @@ -2946,7 +2946,7 @@ enic_sriov_configure(struct pci_dev *pdev, int num_vfs) if (enic->vf_type == ENIC_VF_TYPE_V2) return enic_sriov_v2_enable(enic, num_vfs); - pp = kcalloc(num_vfs, sizeof(*pp), GFP_KERNEL); + pp = kzalloc_objs(*pp, num_vfs); if (!pp) return -ENOMEM; @@ -2971,7 +2971,7 @@ enic_sriov_configure(struct pci_dev *pdev, int num_vfs) return 0; } - pp = kzalloc_obj(*enic->pp, GFP_KERNEL); + pp = kzalloc_obj(*enic->pp); if (!pp) return -ENOMEM; diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index 79d4a77f72bd..8cabce0eb2ab 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -616,7 +616,7 @@ static int dpaa2_switch_lag_fdb_add(struct dpaa2_switch_lag *lag, goto out; } - a = kzalloc(sizeof(*a), GFP_KERNEL); + a = kzalloc_obj(*a); if (!a) { err = -ENOMEM; goto out; @@ -4131,8 +4131,7 @@ static int dpaa2_switch_probe(struct fsl_mc_device *sw_dev) goto err_free_fdbs; } - ethsw->lags = kcalloc(ethsw->sw_attr.num_ifs, sizeof(*ethsw->lags), - GFP_KERNEL); + ethsw->lags = kzalloc_objs(*ethsw->lags, ethsw->sw_attr.num_ifs); if (!ethsw->lags) { err = -ENOMEM; goto err_free_filter; diff --git a/drivers/net/ethernet/intel/libie/controlq.c b/drivers/net/ethernet/intel/libie/controlq.c index 45a49eba6a82..6214fc036ce5 100644 --- a/drivers/net/ethernet/intel/libie/controlq.c +++ b/drivers/net/ethernet/intel/libie/controlq.c @@ -157,8 +157,7 @@ static void libie_ctlq_free_tx_msgs(struct libie_ctlq_info *ctlq, */ static int libie_ctlq_alloc_tx_msgs(struct libie_ctlq_info *ctlq) { - ctlq->tx_msg = kvzalloc_objs(*ctlq->tx_msg, ctlq->ring_len, - GFP_KERNEL); + ctlq->tx_msg = kvzalloc_objs(*ctlq->tx_msg, ctlq->ring_len); if (!ctlq->tx_msg) return -ENOMEM; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c index 3070700b952b..2b67671a2bd8 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c @@ -3647,7 +3647,7 @@ static int npc_defrag_add_2_show_list(struct rvu *rvu, u16 old_midx, { struct npc_defrag_show_node *node; - node = kcalloc(1, sizeof(*node), GFP_KERNEL); + node = kzalloc_objs(*node, 1); if (!node) return -ENOMEM; @@ -4082,7 +4082,7 @@ int npc_cn20k_defrag(struct rvu *rvu) INIT_LIST_HEAD(&x4lh); INIT_LIST_HEAD(&x2lh); - node = kcalloc(npc_priv->num_subbanks, sizeof(*node), GFP_KERNEL); + node = kzalloc_objs(*node, npc_priv->num_subbanks); if (!node) return -ENOMEM; @@ -4711,7 +4711,7 @@ static int npc_priv_init(struct rvu *rvu) return -EINVAL; } - npc_priv = kcalloc(1, sizeof(*npc_priv), GFP_KERNEL); + npc_priv = kzalloc_objs(*npc_priv, 1); if (!npc_priv) return -ENOMEM; @@ -4729,8 +4729,7 @@ static int npc_priv_init(struct rvu *rvu) num_banks, bank_depth, num_subbanks, subbank_depth, npc_kw_name[npc_priv->kw]); - npc_priv->sb = kcalloc(num_subbanks, sizeof(struct npc_subbank), - GFP_KERNEL); + npc_priv->sb = kzalloc_objs(struct npc_subbank, num_subbanks); if (!npc_priv->sb) goto fail1; @@ -4757,9 +4756,7 @@ static int npc_priv_init(struct rvu *rvu) /* Get number of pcifuncs in the system */ npc_priv->pf_cnt = npc_pcifunc_map_create(rvu); - npc_priv->xa_pf2idx_map = kcalloc(npc_priv->pf_cnt, - sizeof(struct xarray), - GFP_KERNEL); + npc_priv->xa_pf2idx_map = kzalloc_objs(struct xarray, npc_priv->pf_cnt); if (!npc_priv->xa_pf2idx_map) { ret = -ENOMEM; goto fail3; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index b6e2c153b4f7..60d477c4eb25 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -2288,8 +2288,7 @@ static int mlx5_esw_spfs_init(struct mlx5_eswitch *esw) if (!num_entries) goto out_free; - esw_funcs->spfs = kcalloc(num_entries, sizeof(*esw_funcs->spfs), - GFP_KERNEL); + esw_funcs->spfs = kzalloc_objs(*esw_funcs->spfs, num_entries); if (!esw_funcs->spfs) { err = -ENOMEM; goto out_free; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index d603e294ee0e..eb74b6260168 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1524,7 +1524,7 @@ struct mlx5_flow_handle * mlx5_esw_lag_demux_rule_create(struct mlx5_eswitch *esw, u16 vport_num, struct mlx5_flow_table *lag_ft) { - struct mlx5_flow_spec *spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + struct mlx5_flow_spec *spec = kvzalloc_obj(*spec); struct mlx5_flow_destination dest = {}; struct mlx5_flow_act flow_act = {}; struct mlx5_flow_handle *ret; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c index 95a8b1e64ba4..1724bf7e0e7a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c @@ -317,7 +317,7 @@ int mlx5_sf_hw_table_init(struct mlx5_core_dev *dev) num_spfs = mlx5_esw_get_num_spfs(dev); num_hwc = MLX5_SF_HWC_FIRST_SPF + num_spfs; - table->hwc = kcalloc(num_hwc, sizeof(*table->hwc), GFP_KERNEL); + table->hwc = kzalloc_objs(*table->hwc, num_hwc); if (!table->hwc) { err = -ENOMEM; goto hwc_alloc_err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_icm_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_icm_pool.c index fa4d24b3dfaa..1b928b40686e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_icm_pool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_icm_pool.c @@ -239,7 +239,7 @@ static int dr_icm_buddy_init_ste_cache(struct mlx5dr_icm_buddy_mem *buddy) if (!buddy->hw_ste_arr) goto free_ste_arr; - buddy->miss_list = kvmalloc_array(num_of_entries, sizeof(struct list_head), GFP_KERNEL); + buddy->miss_list = kvmalloc_objs(struct list_head, num_of_entries); if (!buddy->miss_list) goto free_hw_ste_arr; diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_irq.c b/drivers/net/ethernet/meta/fbnic/fbnic_irq.c index 5e383d40abc7..ec3b628ecb2d 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_irq.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_irq.c @@ -282,7 +282,7 @@ enum fbnic_msix_self_test_codes fbnic_msix_test(struct fbnic_dev *fbd) int i; /* Allocate bitmap and IRQ vector table */ - test_data = kzalloc_obj(*test_data, GFP_KERNEL); + test_data = kzalloc_obj(*test_data); /* memory allocation failure */ if (!test_data) diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index f92b2d0bf926..8e9bfc1d6a2a 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -429,11 +429,11 @@ int mana_gd_alloc_memory(struct gdma_context *gc, unsigned int length, /* length is a power of 2 above PAGE_SIZE, so this divides exactly. */ npages = length / PAGE_SIZE; - gmi->pages_va = kvcalloc(npages, sizeof(*gmi->pages_va), GFP_KERNEL); + gmi->pages_va = kvzalloc_objs(*gmi->pages_va, npages); if (!gmi->pages_va) return -ENOMEM; - gmi->pages_dma = kvcalloc(npages, sizeof(*gmi->pages_dma), GFP_KERNEL); + gmi->pages_dma = kvzalloc_objs(*gmi->pages_dma, npages); if (!gmi->pages_dma) goto free_va; @@ -825,7 +825,7 @@ int mana_schedule_serv_work(struct gdma_context *gc, enum gdma_eqe_type type) return -ENODEV; } - mns_wk = kzalloc(sizeof(*mns_wk), GFP_ATOMIC); + mns_wk = kzalloc_obj(*mns_wk, GFP_ATOMIC); if (!mns_wk) { module_put(THIS_MODULE); clear_bit(GC_IN_SERVICE, &gc->flags); @@ -1991,7 +1991,7 @@ struct gdma_irq_context *mana_gd_get_gic(struct gdma_context *gc, *msi_requested = msi; } - gic = kzalloc(sizeof(*gic), GFP_KERNEL); + gic = kzalloc_obj(*gic); if (!gic) { gic = ERR_PTR(-ENOMEM); if (irq_map.virq) diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c index 2c04be6d61a8..7a0d5e892a1a 100644 --- a/drivers/net/ntb_netdev.c +++ b/drivers/net/ntb_netdev.c @@ -659,8 +659,7 @@ static int ntb_netdev_probe(struct device *client_dev) dev->client_dev = client_dev; dev->num_queues = 0; - dev->queues = kzalloc_objs(*dev->queues, NTB_NETDEV_MAX_QUEUES, - GFP_KERNEL); + dev->queues = kzalloc_objs(*dev->queues, NTB_NETDEV_MAX_QUEUES); if (!dev->queues) { rc = -ENOMEM; goto err_free_netdev; diff --git a/drivers/net/wireless/ath/ath12k/ahb.c b/drivers/net/wireless/ath/ath12k/ahb.c index 0fc55c9169e1..d89a49c6ebb7 100644 --- a/drivers/net/wireless/ath/ath12k/ahb.c +++ b/drivers/net/wireless/ath/ath12k/ahb.c @@ -870,7 +870,7 @@ static struct ath12k_ahb_rproc_info *ath12k_ahb_rproc_info_alloc(struct ath12k_b lockdep_assert_held(&ath12k_rproc_info_lock); - rproc_info = kzalloc_obj(*rproc_info, GFP_KERNEL); + rproc_info = kzalloc_obj(*rproc_info); if (!rproc_info) return NULL; diff --git a/drivers/net/wireless/intel/iwlwifi/mld/regulatory.c b/drivers/net/wireless/intel/iwlwifi/mld/regulatory.c index 533870cf443f..6db84c2117f2 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/regulatory.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/regulatory.c @@ -514,8 +514,7 @@ void iwl_mld_init_ap_type_tables(struct iwl_mld *mld) return; if (iwl_fw_lookup_cmd_ver(mld->fw, cmd.id, 1) == 1) { - struct iwl_mcc_allowed_ap_type_cmd_v1 *cmd_v1 = - kzalloc(sizeof(*cmd_v1), GFP_KERNEL); + struct iwl_mcc_allowed_ap_type_cmd_v1 *cmd_v1 = kzalloc_obj(*cmd_v1); if (!cmd_v1) return; diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/regd.c b/drivers/net/wireless/mediatek/mt76/mt7921/regd.c index 4a8ea4624fee..fcdeb65cd8ef 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/regd.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/regd.c @@ -289,7 +289,7 @@ int mt7921_regd_update(struct mt792x_phy *phy, char *alpha2) goto err; } - regd = kzalloc(struct_size(regd, reg_rules, num_of_rules), GFP_KERNEL); + regd = kzalloc_flex(*regd, reg_rules, num_of_rules); if (!regd) { ret = -ENOMEM; goto err; diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c index 84b55f008b3d..5993b31e1aae 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c @@ -1105,7 +1105,7 @@ mt7925_mac_sta_add_links(struct mt792x_dev *dev, struct ieee80211_vif *vif, mlink = &msta->deflink; is_deflink = true; } else { - mlink = kzalloc(sizeof(*mlink), GFP_KERNEL); + mlink = kzalloc_obj(*mlink); if (!mlink) { err = -ENOMEM; break; diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/regd.c b/drivers/net/wireless/mediatek/mt76/mt7925/regd.c index f4beb7f52043..57f1736b54a3 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/regd.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/regd.c @@ -336,7 +336,7 @@ int mt7925_regd_update(struct mt792x_phy *phy, char *alpha2) goto err; } - regd = kzalloc(struct_size(regd, reg_rules, num_of_rules), GFP_KERNEL); + regd = kzalloc_flex(*regd, reg_rules, num_of_rules); if (!regd) { ret = -ENOMEM; goto err; diff --git a/drivers/net/wireless/morsemicro/mm81x/mac.c b/drivers/net/wireless/morsemicro/mm81x/mac.c index 08ca116a68b4..0fa80b1488aa 100644 --- a/drivers/net/wireless/morsemicro/mm81x/mac.c +++ b/drivers/net/wireless/morsemicro/mm81x/mac.c @@ -706,8 +706,7 @@ static int mm81x_hw_scan_h_init_chan_list(struct mm81x_hw_scan_params *params, params->num_chans = 0; params->allocated_chans = 0; - params->channels = kcalloc(chans_to_allocate, sizeof(*params->channels), - GFP_KERNEL); + params->channels = kzalloc_objs(*params->channels, chans_to_allocate); if (!params->channels) return -ENOMEM; @@ -728,8 +727,8 @@ static int mm81x_hw_scan_h_init_chan_list(struct mm81x_hw_scan_params *params, } } - params->powers_qdbm = kmalloc_array( - num_pwrs_coarse, sizeof(*params->powers_qdbm), GFP_KERNEL); + params->powers_qdbm = kmalloc_objs(*params->powers_qdbm, + num_pwrs_coarse); if (!params->powers_qdbm) return -ENOMEM; @@ -822,7 +821,7 @@ __mm81x_hw_scan_h_init_params(struct mm81x *mors) struct mm81x_hw_scan_params *params = mors->hw_scan.params; if (!params) { - params = kzalloc_obj(*params, GFP_KERNEL); + params = kzalloc_obj(*params); if (params) mors->hw_scan.params = params; } else { diff --git a/drivers/net/wireless/morsemicro/mm81x/yaps.c b/drivers/net/wireless/morsemicro/mm81x/yaps.c index e98a2a58726f..2d1728c1a6de 100644 --- a/drivers/net/wireless/morsemicro/mm81x/yaps.c +++ b/drivers/net/wireless/morsemicro/mm81x/yaps.c @@ -22,15 +22,13 @@ static int mm81x_yaps_alloc_pkt_buffers(struct mm81x_yaps *yaps) { - yaps->hw.to_chip_pkts = kcalloc(MAX_PKTS_PER_TX_TXN, - sizeof(*yaps->hw.to_chip_pkts), - GFP_KERNEL); + yaps->hw.to_chip_pkts = kzalloc_objs(*yaps->hw.to_chip_pkts, + MAX_PKTS_PER_TX_TXN); if (!yaps->hw.to_chip_pkts) return -ENOMEM; - yaps->hw.from_chip_pkts = kcalloc(MAX_PKTS_PER_RX_TXN, - sizeof(*yaps->hw.from_chip_pkts), - GFP_KERNEL); + yaps->hw.from_chip_pkts = kzalloc_objs(*yaps->hw.from_chip_pkts, + MAX_PKTS_PER_RX_TXN); if (!yaps->hw.from_chip_pkts) { kfree(yaps->hw.to_chip_pkts); yaps->hw.to_chip_pkts = NULL; diff --git a/drivers/net/wireless/nxp/nxpwifi/cfg80211.c b/drivers/net/wireless/nxp/nxpwifi/cfg80211.c index 5cc8cdf594d3..86304ea3331c 100644 --- a/drivers/net/wireless/nxp/nxpwifi/cfg80211.c +++ b/drivers/net/wireless/nxp/nxpwifi/cfg80211.c @@ -641,7 +641,7 @@ nxpwifi_cfg80211_set_wiphy_params(struct wiphy *wiphy, int radio_idx, u32 change switch (priv->bss_role) { case NXPWIFI_BSS_ROLE_UAP: - bss_cfg = kzalloc_obj(*bss_cfg, GFP_KERNEL); + bss_cfg = kzalloc_obj(*bss_cfg); if (!bss_cfg) { ret = -ENOMEM; break; @@ -1713,7 +1713,7 @@ static int nxpwifi_cfg80211_start_ap(struct wiphy *wiphy, if (!nxpwifi_is_channel_setting_allowable(priv, params->chandef.chan)) return -EOPNOTSUPP; - bss_cfg = kzalloc_obj(*bss_cfg, GFP_KERNEL); + bss_cfg = kzalloc_obj(*bss_cfg); if (!bss_cfg) return -ENOMEM; @@ -1866,7 +1866,7 @@ nxpwifi_cfg80211_scan(struct wiphy *wiphy, if (!nxpwifi_stop_bg_scan(priv)) cfg80211_sched_scan_stopped_locked(priv->wdev.wiphy, 0); - user_scan_cfg = kzalloc_obj(*user_scan_cfg, GFP_KERNEL); + user_scan_cfg = kzalloc_obj(*user_scan_cfg); if (!user_scan_cfg) return -ENOMEM; @@ -1973,7 +1973,7 @@ nxpwifi_cfg80211_sched_scan_start(struct wiphy *wiphy, request->n_channels, request->scan_plans->interval, (int)request->ie_len); - bgscan_cfg = kzalloc_obj(*bgscan_cfg, GFP_KERNEL); + bgscan_cfg = kzalloc_obj(*bgscan_cfg); if (!bgscan_cfg) return -ENOMEM; @@ -2304,7 +2304,7 @@ nxpwifi_setup_he_caps(struct nxpwifi_private *priv, if (!hw_he_cap_len) return; - iftype_data = kmalloc_obj(*iftype_data, GFP_KERNEL); + iftype_data = kmalloc_obj(*iftype_data); if (!iftype_data) return; memset(iftype_data, 0, sizeof(*iftype_data)); @@ -2759,7 +2759,7 @@ static int nxpwifi_set_mef_filter(struct nxpwifi_private *priv, if (wowlan->n_patterns || wowlan->magic_pkt) num_entries++; - mef_entry = kzalloc_objs(*mef_entry, num_entries, GFP_KERNEL); + mef_entry = kzalloc_objs(*mef_entry, num_entries); if (!mef_entry) return -ENOMEM; @@ -3227,7 +3227,7 @@ static int nxpwifi_tm_cmd(struct wiphy *wiphy, struct wireless_dev *wdev, if (!tb[NXPWIFI_TM_ATTR_DATA]) return -EINVAL; - hostcmd = kzalloc_obj(*hostcmd, GFP_KERNEL); + hostcmd = kzalloc_obj(*hostcmd); if (!hostcmd) return -ENOMEM; diff --git a/drivers/net/wireless/nxp/nxpwifi/cmdevt.c b/drivers/net/wireless/nxp/nxpwifi/cmdevt.c index 4eb17ada5db8..fc1950a125b6 100644 --- a/drivers/net/wireless/nxp/nxpwifi/cmdevt.c +++ b/drivers/net/wireless/nxp/nxpwifi/cmdevt.c @@ -302,7 +302,7 @@ int nxpwifi_alloc_cmd_buffer(struct nxpwifi_adapter *adapter) /* Allocate and initialize struct cmd_ctrl_node */ cmd_array = kzalloc_objs(struct cmd_ctrl_node, - NXPWIFI_NUM_OF_CMD_BUFFER, GFP_KERNEL); + NXPWIFI_NUM_OF_CMD_BUFFER); if (!cmd_array) return -ENOMEM; diff --git a/drivers/net/wireless/nxp/nxpwifi/ie.c b/drivers/net/wireless/nxp/nxpwifi/ie.c index 158755c0c905..86b18d50feaf 100644 --- a/drivers/net/wireless/nxp/nxpwifi/ie.c +++ b/drivers/net/wireless/nxp/nxpwifi/ie.c @@ -143,7 +143,7 @@ nxpwifi_update_uap_custom_ie(struct nxpwifi_private *priv, u16 len; int ret; - ap_custom_ie = kzalloc_obj(*ap_custom_ie, GFP_KERNEL); + ap_custom_ie = kzalloc_obj(*ap_custom_ie); if (!ap_custom_ie) return -ENOMEM; @@ -209,7 +209,7 @@ static int nxpwifi_update_vs_ie(const u8 *ies, int ies_len, vendor_ie = cfg80211_find_vendor_ie(oui, oui_type, ies, ies_len); if (vendor_ie) { if (!*ie_ptr) { - *ie_ptr = kzalloc_obj(struct nxpwifi_ie, GFP_KERNEL); + *ie_ptr = kzalloc_obj(struct nxpwifi_ie); if (!*ie_ptr) return -ENOMEM; ie = *ie_ptr; @@ -309,7 +309,7 @@ static int nxpwifi_uap_parse_tail_ies(struct nxpwifi_private *priv, if (!info->tail || !info->tail_len) return 0; - gen_ie = kzalloc_obj(*gen_ie, GFP_KERNEL); + gen_ie = kzalloc_obj(*gen_ie); if (!gen_ie) return -ENOMEM; @@ -417,7 +417,7 @@ int nxpwifi_del_mgmt_ies(struct nxpwifi_private *priv) int ret = 0; if (priv->gen_idx != NXPWIFI_AUTO_IDX_MASK) { - gen_ie = kmalloc_obj(*gen_ie, GFP_KERNEL); + gen_ie = kmalloc_obj(*gen_ie); if (!gen_ie) return -ENOMEM; @@ -434,7 +434,7 @@ int nxpwifi_del_mgmt_ies(struct nxpwifi_private *priv) } if (priv->beacon_idx != NXPWIFI_AUTO_IDX_MASK) { - beacon_ie = kmalloc_obj(*beacon_ie, GFP_KERNEL); + beacon_ie = kmalloc_obj(*beacon_ie); if (!beacon_ie) { ret = -ENOMEM; goto done; @@ -444,7 +444,7 @@ int nxpwifi_del_mgmt_ies(struct nxpwifi_private *priv) beacon_ie->ie_length = 0; } if (priv->proberesp_idx != NXPWIFI_AUTO_IDX_MASK) { - pr_ie = kmalloc_obj(*pr_ie, GFP_KERNEL); + pr_ie = kmalloc_obj(*pr_ie); if (!pr_ie) { ret = -ENOMEM; goto done; @@ -454,7 +454,7 @@ int nxpwifi_del_mgmt_ies(struct nxpwifi_private *priv) pr_ie->ie_length = 0; } if (priv->assocresp_idx != NXPWIFI_AUTO_IDX_MASK) { - ar_ie = kmalloc_obj(*ar_ie, GFP_KERNEL); + ar_ie = kmalloc_obj(*ar_ie); if (!ar_ie) { ret = -ENOMEM; goto done; diff --git a/drivers/net/wireless/nxp/nxpwifi/init.c b/drivers/net/wireless/nxp/nxpwifi/init.c index b128fc9fe31a..7c75dca5d0a8 100644 --- a/drivers/net/wireless/nxp/nxpwifi/init.c +++ b/drivers/net/wireless/nxp/nxpwifi/init.c @@ -20,7 +20,7 @@ static int nxpwifi_add_bss_prio_tbl(struct nxpwifi_private *priv) struct nxpwifi_bss_prio_node *bss_prio; struct nxpwifi_bss_prio_tbl *tbl = adapter->bss_prio_tbl; - bss_prio = kzalloc_obj(*bss_prio, GFP_KERNEL); + bss_prio = kzalloc_obj(*bss_prio); if (!bss_prio) return -ENOMEM; diff --git a/drivers/net/wireless/nxp/nxpwifi/main.c b/drivers/net/wireless/nxp/nxpwifi/main.c index b4c63829024a..55b962430f37 100644 --- a/drivers/net/wireless/nxp/nxpwifi/main.c +++ b/drivers/net/wireless/nxp/nxpwifi/main.c @@ -32,7 +32,7 @@ static struct nxpwifi_adapter *nxpwifi_register(void *card, struct device *dev, int ret = 0; int i; - adapter = kzalloc_obj(*adapter, GFP_KERNEL); + adapter = kzalloc_obj(*adapter); if (!adapter) return ERR_PTR(-ENOMEM); @@ -55,7 +55,7 @@ static struct nxpwifi_adapter *nxpwifi_register(void *card, struct device *dev, for (i = 0; i < NXPWIFI_MAX_BSS_NUM; i++) { /* Allocate memory for private structure */ adapter->priv[i] = - kzalloc_obj(struct nxpwifi_private, GFP_KERNEL); + kzalloc_obj(struct nxpwifi_private); if (!adapter->priv[i]) { ret = -ENOMEM; goto error; @@ -1106,7 +1106,7 @@ void nxpwifi_drv_info_dump(struct nxpwifi_adapter *adapter) p += adapter->if_ops.reg_dump(adapter, p); } p += sprintf(p, "\n=== more debug information\n"); - debug_info = kzalloc_obj(*debug_info, GFP_KERNEL); + debug_info = kzalloc_obj(*debug_info); if (debug_info) { for (i = 0; i < adapter->priv_num; i++) { if (!adapter->priv[i]->netdev) @@ -1242,7 +1242,7 @@ void nxpwifi_init_priv_params(struct nxpwifi_private *priv, if (GET_BSS_ROLE(priv) == NXPWIFI_BSS_ROLE_STA || GET_BSS_ROLE(priv) == NXPWIFI_BSS_ROLE_UAP) { - priv->hist_data = kmalloc_obj(*priv->hist_data, GFP_KERNEL); + priv->hist_data = kmalloc_obj(*priv->hist_data); if (priv->hist_data) nxpwifi_hist_data_reset(priv); } diff --git a/drivers/net/wireless/nxp/nxpwifi/scan.c b/drivers/net/wireless/nxp/nxpwifi/scan.c index b77056983e83..67d7ff2f10c5 100644 --- a/drivers/net/wireless/nxp/nxpwifi/scan.c +++ b/drivers/net/wireless/nxp/nxpwifi/scan.c @@ -1341,15 +1341,14 @@ int nxpwifi_scan_networks(struct nxpwifi_private *priv, adapter->scan_processing = true; spin_unlock_bh(&adapter->nxpwifi_cmd_lock); - scan_cfg_out = kzalloc_obj(union nxpwifi_scan_cmd_config_tlv, - GFP_KERNEL); + scan_cfg_out = kzalloc_obj(union nxpwifi_scan_cmd_config_tlv); if (!scan_cfg_out) { ret = -ENOMEM; goto done; } scan_chan_list = kzalloc_objs(struct nxpwifi_chan_scan_param_set, - NXPWIFI_USER_SCAN_CHAN_MAX, GFP_KERNEL); + NXPWIFI_USER_SCAN_CHAN_MAX); if (!scan_chan_list) { kfree(scan_cfg_out); ret = -ENOMEM; @@ -1471,7 +1470,7 @@ static int nxpwifi_save_hidden_ssid_channels(struct nxpwifi_private *priv, int chid; /* Allocate and fill new bss descriptor */ - bss_desc = kzalloc_obj(*bss_desc, GFP_KERNEL); + bss_desc = kzalloc_obj(*bss_desc); if (!bss_desc) return -ENOMEM; @@ -1512,7 +1511,7 @@ static int nxpwifi_update_curr_bss_params(struct nxpwifi_private *priv, int ret; /* Allocate and fill new bss descriptor */ - bss_desc = kzalloc_obj(*bss_desc, GFP_KERNEL); + bss_desc = kzalloc_obj(*bss_desc); if (!bss_desc) return -ENOMEM; @@ -1751,7 +1750,7 @@ nxpwifi_active_scan_req_for_passive_chan(struct nxpwifi_private *priv) nxpwifi_dbg(adapter, INFO, "No BSS with hidden SSID found on DFS channels\n"); return 0; } - user_scan_cfg = kzalloc_obj(*user_scan_cfg, GFP_KERNEL); + user_scan_cfg = kzalloc_obj(*user_scan_cfg); if (!user_scan_cfg) return -ENOMEM; @@ -2258,7 +2257,7 @@ int nxpwifi_stop_bg_scan(struct nxpwifi_private *priv) return 0; } - bgscan_cfg = kzalloc_obj(*bgscan_cfg, GFP_KERNEL); + bgscan_cfg = kzalloc_obj(*bgscan_cfg); if (!bgscan_cfg) return -ENOMEM; diff --git a/drivers/net/wireless/nxp/nxpwifi/sta_cfg.c b/drivers/net/wireless/nxp/nxpwifi/sta_cfg.c index 702fa1531da1..56cf63fbf7fe 100644 --- a/drivers/net/wireless/nxp/nxpwifi/sta_cfg.c +++ b/drivers/net/wireless/nxp/nxpwifi/sta_cfg.c @@ -245,7 +245,7 @@ int nxpwifi_bss_start(struct nxpwifi_private *priv, struct cfg80211_bss *bss, return -EINVAL; /* Allocate and fill new bss descriptor */ - bss_desc = kzalloc_obj(*bss_desc, GFP_KERNEL); + bss_desc = kzalloc_obj(*bss_desc); if (!bss_desc) return -ENOMEM; diff --git a/drivers/net/wireless/nxp/nxpwifi/sta_cmd.c b/drivers/net/wireless/nxp/nxpwifi/sta_cmd.c index 5e8ffd306b31..9bfa4aebc3e5 100644 --- a/drivers/net/wireless/nxp/nxpwifi/sta_cmd.c +++ b/drivers/net/wireless/nxp/nxpwifi/sta_cmd.c @@ -2822,7 +2822,7 @@ nxpwifi_create_custom_regdomain(struct nxpwifi_private *priv, if (WARN_ON_ONCE(num_chan > NL80211_MAX_SUPP_REG_RULES)) return ERR_PTR(-EINVAL); - regd = kzalloc_flex(*regd, reg_rules, num_chan, GFP_KERNEL); + regd = kzalloc_flex(*regd, reg_rules, num_chan); if (!regd) return ERR_PTR(-ENOMEM); diff --git a/drivers/net/wireless/nxp/nxpwifi/uap_event.c b/drivers/net/wireless/nxp/nxpwifi/uap_event.c index 9f717a3d7ec5..ab5c15686f54 100644 --- a/drivers/net/wireless/nxp/nxpwifi/uap_event.c +++ b/drivers/net/wireless/nxp/nxpwifi/uap_event.c @@ -88,7 +88,7 @@ nxpwifi_uap_event_sta_assoc(struct nxpwifi_private *priv) struct nxpwifi_sta_node *node; int len, i; - sinfo = kzalloc_obj(*sinfo, GFP_KERNEL); + sinfo = kzalloc_obj(*sinfo); if (!sinfo) return -ENOMEM; diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index 24f42b4650ba..09842ca68110 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -1002,8 +1002,7 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus, nd_region->num_lanes = ndr_desc->num_lanes; if (!nd_region->num_lanes) goto err_percpu; - nd_region->lane = kcalloc(nd_region->num_lanes, - sizeof(*nd_region->lane), GFP_KERNEL); + nd_region->lane = kzalloc_objs(*nd_region->lane, nd_region->num_lanes); if (!nd_region->lane) goto err_percpu; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 1322c678f4eb..b16cec1ff51f 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2382,8 +2382,7 @@ static int nvme_query_fdp_info(struct nvme_ns *ns, struct nvme_ns_info *info) if (!head->nr_plids) goto free; - head->plids = kcalloc(head->nr_plids, sizeof(*head->plids), - GFP_KERNEL); + head->plids = kzalloc_objs(*head->plids, head->nr_plids); if (!head->plids) { dev_warn(ctrl->device, "failed to allocate %u FDP placement IDs\n", diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index da93b505d239..5440cf18b55b 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -201,7 +201,7 @@ static int quirks_param_set(const char *value, const struct kernel_param *kp) count++; } - qlist = kcalloc(count, sizeof(*qlist), GFP_KERNEL); + qlist = kzalloc_objs(*qlist, count); if (!qlist) { err = -ENOMEM; goto out_free_val; diff --git a/drivers/opp/core.c b/drivers/opp/core.c index cd0e82dae776..2fafd983de8f 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -348,7 +348,7 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev) count = opp_table->regulator_count; - uV = kmalloc_array(count, sizeof(*uV), GFP_KERNEL); + uV = kmalloc_objs(*uV, count); if (!uV) return 0; @@ -1505,7 +1505,7 @@ struct opp_device *_add_opp_dev(const struct device *dev, { struct opp_device *opp_dev; - opp_dev = kzalloc(sizeof(*opp_dev), GFP_KERNEL); + opp_dev = kzalloc_obj(*opp_dev); if (!opp_dev) return NULL; diff --git a/drivers/pci/endpoint/pci-ep-msi.c b/drivers/pci/endpoint/pci-ep-msi.c index 0855c7930abb..9c13f193537d 100644 --- a/drivers/pci/endpoint/pci-ep-msi.c +++ b/drivers/pci/endpoint/pci-ep-msi.c @@ -57,7 +57,7 @@ static int pci_epf_alloc_doorbell_embedded(struct pci_epf *epf, u16 num_db) return -ENODEV; struct pci_epc_aux_resource *res __free(kfree) = - kcalloc(count, sizeof(*res), GFP_KERNEL); + kzalloc_objs(*res, count); if (!res) return -ENOMEM; @@ -98,7 +98,7 @@ static int pci_epf_alloc_doorbell_embedded(struct pci_epf *epf, u16 num_db) addr = iova_base + off; } - msg = kcalloc(num_db, sizeof(*msg), GFP_KERNEL); + msg = kzalloc_objs(*msg, num_db); if (!msg) { ret = -ENOMEM; goto err_unmap; diff --git a/drivers/platform/x86/amd/hsmp/acpi.c b/drivers/platform/x86/amd/hsmp/acpi.c index 8257cd1da48e..ddd7a04ee753 100644 --- a/drivers/platform/x86/amd/hsmp/acpi.c +++ b/drivers/platform/x86/amd/hsmp/acpi.c @@ -720,9 +720,8 @@ static int hsmp_acpi_probe(struct platform_device *pdev) return -ENODEV; } - hsmp_pdev->sock = kcalloc(hsmp_pdev->num_sockets, - sizeof(*hsmp_pdev->sock), - GFP_KERNEL); + hsmp_pdev->sock = kzalloc_objs(*hsmp_pdev->sock, + hsmp_pdev->num_sockets); if (!hsmp_pdev->sock) return -ENOMEM; diff --git a/drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c b/drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c index 446dd18d2cee..72a4c2107d7e 100644 --- a/drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c +++ b/drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c @@ -96,8 +96,8 @@ int hp_alloc_enumeration_data(void) if (!bioscfg_drv.enumeration_instances_count) return -EINVAL; - bioscfg_drv.enumeration_data = kvcalloc(bioscfg_drv.enumeration_instances_count, - sizeof(*bioscfg_drv.enumeration_data), GFP_KERNEL); + bioscfg_drv.enumeration_data = kvzalloc_objs(*bioscfg_drv.enumeration_data, + bioscfg_drv.enumeration_instances_count); if (!bioscfg_drv.enumeration_data) { bioscfg_drv.enumeration_instances_count = 0; diff --git a/drivers/platform/x86/intel/pmc/pwrm_telemetry.c b/drivers/platform/x86/intel/pmc/pwrm_telemetry.c index 4cde241e01d6..013f779f20a4 100644 --- a/drivers/platform/x86/intel/pmc/pwrm_telemetry.c +++ b/drivers/platform/x86/intel/pmc/pwrm_telemetry.c @@ -93,8 +93,7 @@ acpi_disc_t pmc_parse_telem_dsd(union acpi_object *obj, if (header->num_entries != num_regions) return ERR_PTR(-EINVAL); - acpi_disc_t disc __free(kfree) = kmalloc_array(num_regions, sizeof(*disc), - GFP_KERNEL); + acpi_disc_t disc __free(kfree) = kmalloc_objs(*disc, num_regions); if (!disc) return ERR_PTR(-ENOMEM); diff --git a/drivers/pmdomain/core.c b/drivers/pmdomain/core.c index 842c4169e290..052ec478dfcc 100644 --- a/drivers/pmdomain/core.c +++ b/drivers/pmdomain/core.c @@ -2962,7 +2962,7 @@ int of_genpd_add_child_ids(struct device_node *np, return -EINVAL; /* Allocate tracking array for error unwind (parent/child pairs) */ - pairs = kmalloc_array(count * 2, sizeof(*pairs), GFP_KERNEL); + pairs = kmalloc_objs(*pairs, count * 2); if (!pairs) return -ENOMEM; diff --git a/drivers/power/reset/reboot-mode.c b/drivers/power/reset/reboot-mode.c index af00c00eceee..3611bed341e1 100644 --- a/drivers/power/reset/reboot-mode.c +++ b/drivers/power/reset/reboot-mode.c @@ -122,14 +122,14 @@ static int reboot_mode_create_device(struct reboot_mode_driver *reboot) struct mode_info *info; int ret; - priv = kzalloc_obj(*priv, GFP_KERNEL); + priv = kzalloc_obj(*priv); if (!priv) return -ENOMEM; INIT_LIST_HEAD(&priv->head); list_for_each_entry(info, &reboot->head, list) { - sysfs_info = kzalloc_obj(*sysfs_info, GFP_KERNEL); + sysfs_info = kzalloc_obj(*sysfs_info); if (!sysfs_info) { ret = -ENOMEM; goto error; @@ -188,7 +188,7 @@ int reboot_mode_register(struct reboot_mode_driver *reboot) continue; } - info = kzalloc_obj(*info, GFP_KERNEL); + info = kzalloc_obj(*info); if (!info) { ret = -ENOMEM; goto error; diff --git a/drivers/power/sequencing/core.c b/drivers/power/sequencing/core.c index 721e888b658d..0cb71efbb268 100644 --- a/drivers/power/sequencing/core.c +++ b/drivers/power/sequencing/core.c @@ -480,7 +480,7 @@ pwrseq_device_register(const struct pwrseq_config *config) !config->targets[0]) return ERR_PTR(-EINVAL); - pwrseq = kzalloc(sizeof(*pwrseq), GFP_KERNEL); + pwrseq = kzalloc_obj(*pwrseq); if (!pwrseq) return ERR_PTR(-ENOMEM); diff --git a/drivers/power/sequencing/pwrseq-pcie-m2.c b/drivers/power/sequencing/pwrseq-pcie-m2.c index de9848a9a9f1..471ffe914a4e 100644 --- a/drivers/power/sequencing/pwrseq-pcie-m2.c +++ b/drivers/power/sequencing/pwrseq-pcie-m2.c @@ -291,7 +291,7 @@ static int pwrseq_pcie_m2_create_serdev_one(struct pwrseq_pcie_m2_ctx *ctx, } } - pci_dev = kzalloc(sizeof(*pci_dev), GFP_KERNEL); + pci_dev = kzalloc_obj(*pci_dev); if (!pci_dev) { ret = -ENOMEM; goto err_put_ctrl; diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c index 00d8bc98d588..47e307709e5e 100644 --- a/drivers/power/supply/power_supply_core.c +++ b/drivers/power/supply/power_supply_core.c @@ -904,7 +904,7 @@ int power_supply_get_battery_info(struct power_supply *psy, goto out_put_node; } - u32 *propdata __free(kfree) = kcalloc(proplen, sizeof(*propdata), GFP_KERNEL); + u32 *propdata __free(kfree) = kzalloc_objs(*propdata, proplen); if (!propdata) { power_supply_put_battery_info(psy, info); err = -EINVAL; @@ -944,7 +944,7 @@ int power_supply_get_battery_info(struct power_supply *psy, goto out_put_node; } - propdata = kcalloc(proplen, sizeof(*propdata), GFP_KERNEL); + propdata = kzalloc_objs(*propdata, proplen); if (!propdata) { power_supply_put_battery_info(psy, info); err = -ENOMEM; @@ -1726,7 +1726,7 @@ __power_supply_register(struct device *parent, pr_warn("%s: Expected proper parent device for '%s'\n", __func__, desc->name); - psy = kzalloc(sizeof(*psy), GFP_KERNEL); + psy = kzalloc_obj(*psy); if (!psy) return ERR_PTR(-ENOMEM); diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c index dc23cd708cfe..f63b45f5ee6a 100644 --- a/drivers/ptp/ptp_chardev.c +++ b/drivers/ptp/ptp_chardev.c @@ -136,7 +136,7 @@ int ptp_open(struct posix_clock_context *pccontext, fmode_t fmode) struct timestamp_event_queue *queue; char debugfsname[32]; - queue = kzalloc(sizeof(*queue), GFP_KERNEL); + queue = kzalloc_obj(*queue); if (!queue) return -EINVAL; queue->mask = bitmap_alloc(PTP_MAX_CHANNELS, GFP_KERNEL); diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 5979758311c8..2ffe404b890f 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -87,7 +87,7 @@ struct dasd_device *dasd_alloc_device(void) { struct dasd_device *device; - device = kzalloc_obj(struct dasd_device, GFP_KERNEL); + device = kzalloc_obj(struct dasd_device); if (!device) return ERR_PTR(-ENOMEM); diff --git a/drivers/scsi/fnic/fnic_debugfs.c b/drivers/scsi/fnic/fnic_debugfs.c index 61f167e20574..21b7e9666b74 100644 --- a/drivers/scsi/fnic/fnic_debugfs.c +++ b/drivers/scsi/fnic/fnic_debugfs.c @@ -767,7 +767,7 @@ static int fnic_nvmef_debugfs_open(struct inode *inode, struct file *file) struct fnic_nvmef_info *info; int buf_size = 2 * PAGE_SIZE; - info = kzalloc_obj(struct fnic_nvmef_info, GFP_KERNEL); + info = kzalloc_obj(struct fnic_nvmef_info); if (!info) return -ENOMEM; diff --git a/drivers/scsi/leapraid/leapraid_func.c b/drivers/scsi/leapraid/leapraid_func.c index 089d0810bd13..66b43c1c72e1 100644 --- a/drivers/scsi/leapraid/leapraid_func.c +++ b/drivers/scsi/leapraid/leapraid_func.c @@ -2984,8 +2984,7 @@ static void leapraid_fw_evt_put(struct leapraid_fw_evt_work *fw_work) static struct leapraid_fw_evt_work *leapraid_alloc_fw_evt_work(void) { - struct leapraid_fw_evt_work *fw_evt = - kzalloc(sizeof(*fw_evt), GFP_ATOMIC); + struct leapraid_fw_evt_work *fw_evt = kzalloc_obj(*fw_evt, GFP_ATOMIC); if (fw_evt) kref_init(&fw_evt->refcnt); @@ -3644,8 +3643,7 @@ static void leapraid_sas_host_add(struct leapraid_adapter *adapter, return; adapter->dev_topo.card.card_phy = - kcalloc(phys_num, - sizeof(struct leapraid_card_phy), GFP_KERNEL); + kzalloc_objs(struct leapraid_card_phy, phys_num); if (!adapter->dev_topo.card.card_phy) return; @@ -3763,8 +3761,7 @@ static int leapraid_internal_exp_add(struct leapraid_adapter *adapter, } topo_node_exp->card_phy = - kcalloc(topo_node_exp->phys_num, - sizeof(struct leapraid_card_phy), GFP_KERNEL); + kzalloc_objs(struct leapraid_card_phy, topo_node_exp->phys_num); if (!topo_node_exp->card_phy) { dev_err(&adapter->pdev->dev, "%s: Failed to alloc expander phy array, count=%u\n", @@ -4352,7 +4349,7 @@ static void leapraid_sas_volume_add( return; } - raid_volume = kzalloc(sizeof(*raid_volume), GFP_KERNEL); + raid_volume = kzalloc_obj(*raid_volume); if (!raid_volume) return; @@ -6090,17 +6087,15 @@ static void leapraid_update_card_port_after_reset( if (!adapter->dev_topo.card.card_phy) { adapter->dev_topo.card.card_phy = - kcalloc(nr_phys, sizeof(struct leapraid_card_phy), - GFP_KERNEL); + kzalloc_objs(struct leapraid_card_phy, nr_phys); if (!adapter->dev_topo.card.card_phy) return; } adapter->dev_topo.card.phys_num = nr_phys; - new_card_port_table = kcalloc(adapter->dev_topo.card.phys_num, - sizeof(struct leapraid_card_port), - GFP_KERNEL); + new_card_port_table = kzalloc_objs(struct leapraid_card_port, + adapter->dev_topo.card.phys_num); if (!new_card_port_table) return; @@ -7224,8 +7219,8 @@ static int leapraid_set_legacy_int(struct leapraid_adapter *adapter) adapter->notification_desc.iopoll_qdex, adapter->notification_desc.iopoll_qcnt); adapter->notification_desc.int_rqs = - kcalloc(adapter->notification_desc.iopoll_qdex, - sizeof(struct leapraid_int_rq), GFP_KERNEL); + kzalloc_objs(struct leapraid_int_rq, + adapter->notification_desc.iopoll_qdex); if (!adapter->notification_desc.int_rqs) return -ENOMEM; @@ -7268,9 +7263,8 @@ static int leapraid_set_msix(struct leapraid_adapter *adapter) } if (iopoll_qcnt) { adapter->notification_desc.blk_mq_poll_rqs = - kcalloc(iopoll_qcnt, - sizeof(struct leapraid_blk_mq_poll_rq), - GFP_KERNEL); + kzalloc_objs(struct leapraid_blk_mq_poll_rq, + iopoll_qcnt); if (!adapter->notification_desc.blk_mq_poll_rqs) return -ENOMEM; adapter->adapter_attr.rq_cnt = @@ -7289,8 +7283,8 @@ static int leapraid_set_msix(struct leapraid_adapter *adapter) adapter->notification_desc.iopoll_qcnt); adapter->notification_desc.int_rqs = - kcalloc(adapter->notification_desc.iopoll_qdex, - sizeof(struct leapraid_int_rq), GFP_KERNEL); + kzalloc_objs(struct leapraid_int_rq, + adapter->notification_desc.iopoll_qdex); if (!adapter->notification_desc.int_rqs) return -ENOMEM; @@ -7365,9 +7359,8 @@ static int leapraid_set_msi(struct leapraid_adapter *adapter) if (iopoll_qcnt) { adapter->notification_desc.blk_mq_poll_rqs = - kcalloc(iopoll_qcnt, - sizeof(struct leapraid_blk_mq_poll_rq), - GFP_KERNEL); + kzalloc_objs(struct leapraid_blk_mq_poll_rq, + iopoll_qcnt); if (!adapter->notification_desc.blk_mq_poll_rqs) return -ENOMEM; @@ -7404,9 +7397,8 @@ static int leapraid_set_msi(struct leapraid_adapter *adapter) adapter->notification_desc.iopoll_qcnt); adapter->notification_desc.int_rqs = - kcalloc(adapter->notification_desc.iopoll_qdex, - sizeof(struct leapraid_int_rq), - GFP_KERNEL); + kzalloc_objs(struct leapraid_int_rq, + adapter->notification_desc.iopoll_qdex); if (!adapter->notification_desc.int_rqs) return -ENOMEM; @@ -7958,18 +7950,16 @@ static int leapraid_request_host_memory(struct leapraid_adapter *adapter) DIV_ROUND_UP(adapter->adapter_attr.rq_cnt, LEAPRAID_REP_DESC_CHUNK_SIZE); adapter->mem_desc.rep_desc_seg_maint = - kcalloc(adapter->adapter_attr.rep_desc_q_seg_cnt, - sizeof(struct leapraid_rep_desc_seg_maint), - GFP_KERNEL); + kzalloc_objs(struct leapraid_rep_desc_seg_maint, + adapter->adapter_attr.rep_desc_q_seg_cnt); if (!adapter->mem_desc.rep_desc_seg_maint) return -ENOMEM; rep_desc_q_cnt_allocated = 0; for (i = 0; i < adapter->adapter_attr.rep_desc_q_seg_cnt; i++) { adapter->mem_desc.rep_desc_seg_maint[i].rep_desc_maint = - kcalloc(LEAPRAID_REP_DESC_CHUNK_SIZE, - sizeof(struct leapraid_rep_desc_maint), - GFP_KERNEL); + kzalloc_objs(struct leapraid_rep_desc_maint, + LEAPRAID_REP_DESC_CHUNK_SIZE); if (!adapter->mem_desc.rep_desc_seg_maint[i].rep_desc_maint) return -ENOMEM; diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index 3b82e80e807a..0f0f243c2561 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -158,7 +158,7 @@ int scsi_complete_async_scans(void) * sleep a little. Even if we never get memory, the async * scans will finish eventually. */ - data = kmalloc(sizeof(*data), GFP_KERNEL); + data = kmalloc_obj(*data); if (!data) msleep(1); } while (!data); diff --git a/drivers/soc/bcm/brcmstb/common.c b/drivers/soc/bcm/brcmstb/common.c index 7be0374f5943..a903fa44e4e5 100644 --- a/drivers/soc/bcm/brcmstb/common.c +++ b/drivers/soc/bcm/brcmstb/common.c @@ -65,7 +65,7 @@ static int __init brcmstb_soc_device_init(void) goto out_put_node; } - soc_info = kzalloc(sizeof(*soc_info), GFP_KERNEL); + soc_info = kzalloc_obj(*soc_info); if (!soc_info) { ret = -ENOMEM; goto out_unmap; diff --git a/drivers/spi/spi-offload.c b/drivers/spi/spi-offload.c index a579ef33b2d2..a446927a51d3 100644 --- a/drivers/spi/spi-offload.c +++ b/drivers/spi/spi-offload.c @@ -434,7 +434,7 @@ int devm_spi_offload_trigger_register(struct device *dev, if (!info->fwnode || !info->ops || !info->ops->match) return -EINVAL; - trigger = kzalloc(sizeof(*trigger), GFP_KERNEL); + trigger = kzalloc_obj(*trigger); if (!trigger) return -ENOMEM; diff --git a/drivers/staging/greybus/raw.c b/drivers/staging/greybus/raw.c index 459aed0f1240..4f1b3f4db404 100644 --- a/drivers/staging/greybus/raw.c +++ b/drivers/staging/greybus/raw.c @@ -178,7 +178,7 @@ static int gb_raw_probe(struct gb_bundle *bundle, if (minor < 0) return minor; - raw = kzalloc_obj(*raw, GFP_KERNEL); + raw = kzalloc_obj(*raw); if (!raw) { ida_free(&minors, minor); return -ENOMEM; diff --git a/drivers/staging/media/atomisp/pci/sh_css.c b/drivers/staging/media/atomisp/pci/sh_css.c index 00082276f1db..4a182dc384ca 100644 --- a/drivers/staging/media/atomisp/pci/sh_css.c +++ b/drivers/staging/media/atomisp/pci/sh_css.c @@ -5820,36 +5820,31 @@ static int ia_css_pipe_create_cas_scaler_desc_single_output( } descr->in_info = kmalloc_objs(*descr->in_info, - descr->num_stage, - GFP_KERNEL); + descr->num_stage); if (!descr->in_info) { err = -ENOMEM; goto ERR; } descr->internal_out_info = kmalloc_objs(*descr->internal_out_info, - descr->num_stage, - GFP_KERNEL); + descr->num_stage); if (!descr->internal_out_info) { err = -ENOMEM; goto ERR; } descr->out_info = kmalloc_objs(*descr->out_info, - descr->num_stage, - GFP_KERNEL); + descr->num_stage); if (!descr->out_info) { err = -ENOMEM; goto ERR; } descr->vf_info = kmalloc_objs(*descr->vf_info, - descr->num_stage, - GFP_KERNEL); + descr->num_stage); if (!descr->vf_info) { err = -ENOMEM; goto ERR; } descr->is_output_stage = kmalloc_objs(*descr->is_output_stage, - descr->num_stage, - GFP_KERNEL); + descr->num_stage); if (!descr->is_output_stage) { err = -ENOMEM; goto ERR; @@ -5970,36 +5965,31 @@ ia_css_pipe_create_cas_scaler_desc(struct ia_css_pipe *pipe, descr->num_stage = num_stages; descr->in_info = kmalloc_objs(*descr->in_info, - descr->num_stage, - GFP_KERNEL); + descr->num_stage); if (!descr->in_info) { err = -ENOMEM; goto ERR; } descr->internal_out_info = kmalloc_objs(*descr->internal_out_info, - descr->num_stage, - GFP_KERNEL); + descr->num_stage); if (!descr->internal_out_info) { err = -ENOMEM; goto ERR; } descr->out_info = kmalloc_objs(*descr->out_info, - descr->num_stage, - GFP_KERNEL); + descr->num_stage); if (!descr->out_info) { err = -ENOMEM; goto ERR; } descr->vf_info = kmalloc_objs(*descr->vf_info, - descr->num_stage, - GFP_KERNEL); + descr->num_stage); if (!descr->vf_info) { err = -ENOMEM; goto ERR; } descr->is_output_stage = kmalloc_objs(*descr->is_output_stage, - descr->num_stage, - GFP_KERNEL); + descr->num_stage); if (!descr->is_output_stage) { err = -ENOMEM; goto ERR; diff --git a/drivers/staging/media/atomisp/pci/sh_css_firmware.c b/drivers/staging/media/atomisp/pci/sh_css_firmware.c index af12df2f9b09..b895dee77568 100644 --- a/drivers/staging/media/atomisp/pci/sh_css_firmware.c +++ b/drivers/staging/media/atomisp/pci/sh_css_firmware.c @@ -254,8 +254,8 @@ sh_css_load_firmware(struct device *dev, const char *fw_data, /* Only allocate memory for ISP blob info */ if (sh_css_num_binaries > NUM_OF_SPS) { sh_css_blob_info = - kmalloc_array(sh_css_num_binaries - NUM_OF_SPS, - sizeof(*sh_css_blob_info), GFP_KERNEL); + kmalloc_objs(*sh_css_blob_info, + sh_css_num_binaries - NUM_OF_SPS); if (!sh_css_blob_info) return -ENOMEM; } else { diff --git a/drivers/tee/qcomtee/user_obj.c b/drivers/tee/qcomtee/user_obj.c index 10452fcc7ccb..a06eb94e0bae 100644 --- a/drivers/tee/qcomtee/user_obj.c +++ b/drivers/tee/qcomtee/user_obj.c @@ -230,8 +230,7 @@ static int qcomtee_user_object_dispatch(struct qcomtee_object_invoke_ctx *oic, struct qcomtee_context_data *ctxdata = uo->ctx->data; int errno; - struct qcomtee_ureq *ureq __free(kfree) = kzalloc(sizeof(*ureq), - GFP_KERNEL); + struct qcomtee_ureq *ureq __free(kfree) = kzalloc_obj(*ureq); if (!ureq) return -ENOMEM; diff --git a/drivers/thunderbolt/stream.c b/drivers/thunderbolt/stream.c index c737dd0ca6e7..25c259dd0760 100644 --- a/drivers/thunderbolt/stream.c +++ b/drivers/thunderbolt/stream.c @@ -408,8 +408,7 @@ static int tbstream_dev_alloc_rx_buffers(struct tbstream_dev *sdev) size_t ring_size = tb_ring_size(sdev->rx_ring.ring); int i; - sdev->rx_ring.frames = kcalloc(ring_size, sizeof(struct tbstream_frame), - GFP_KERNEL); + sdev->rx_ring.frames = kzalloc_objs(struct tbstream_frame, ring_size); if (!sdev->rx_ring.frames) return -ENOMEM; @@ -463,8 +462,7 @@ static int tbstream_dev_alloc_tx_buffers(struct tbstream_dev *sdev) size_t ring_size = tb_ring_size(sdev->tx_ring.ring); int i; - sdev->tx_ring.frames = kcalloc(ring_size, sizeof(struct tbstream_frame), - GFP_KERNEL); + sdev->tx_ring.frames = kzalloc_objs(struct tbstream_frame, ring_size); if (!sdev->tx_ring.frames) return -ENOMEM; @@ -1498,7 +1496,7 @@ tbstream_dev_make_group(struct config_group *group, const char *name) if (strlen(name) > TB_PROPERTY_KEY_SIZE) return ERR_PTR(-ENAMETOOLONG); - sdev = kzalloc_obj(*sdev, GFP_KERNEL); + sdev = kzalloc_obj(*sdev); if (!sdev) return ERR_PTR(-ENOMEM); @@ -1592,7 +1590,7 @@ tbstream_make_group(struct config_group *group, const char *name) if (sscanf(name, "%u-%llx.%u", &domain, &route, &index) != 3) return ERR_PTR(-EINVAL); - sg = kzalloc_obj(*sg, GFP_KERNEL); + sg = kzalloc_obj(*sg); if (!sg) return ERR_PTR(-ENOMEM); @@ -1698,7 +1696,7 @@ static int tbstream_probe(struct tb_service *svc) { struct tbstream *stream; - stream = kzalloc_obj(*stream, GFP_KERNEL); + stream = kzalloc_obj(*stream); if (!stream) return -ENOMEM; diff --git a/drivers/tty/moxa.c b/drivers/tty/moxa.c index 1bb2376af85c..40a1c614e23b 100644 --- a/drivers/tty/moxa.c +++ b/drivers/tty/moxa.c @@ -954,8 +954,7 @@ static int moxa_init_board(struct moxa_board_conf *brd, struct device *dev) unsigned int i, first_idx; int ret; - brd->ports = kcalloc(MAX_PORTS_PER_BOARD, sizeof(*brd->ports), - GFP_KERNEL); + brd->ports = kzalloc_objs(*brd->ports, MAX_PORTS_PER_BOARD); if (brd->ports == NULL) { printk(KERN_ERR "cannot allocate memory for ports\n"); ret = -ENOMEM; diff --git a/drivers/tty/vt/consolemap.c b/drivers/tty/vt/consolemap.c index 3fa89a2dbeba..7d564341a7eb 100644 --- a/drivers/tty/vt/consolemap.c +++ b/drivers/tty/vt/consolemap.c @@ -776,7 +776,8 @@ int con_get_unimap(struct vc_data *vc, ushort ct, ushort __user *uct, struct uni_pagedict *dict; unsigned int d, r, g; - struct unipair *unilist __free(kvfree) = kvmalloc_array(ct, sizeof(*unilist), GFP_KERNEL); + struct unipair *unilist __free(kvfree) = kvmalloc_objs(*unilist, ct, + GFP_KERNEL); if (!unilist) return -ENOMEM; diff --git a/drivers/ufs/core/ufs-txeq.c b/drivers/ufs/core/ufs-txeq.c index fa5f539632eb..6192512e29de 100644 --- a/drivers/ufs/core/ufs-txeq.c +++ b/drivers/ufs/core/ufs-txeq.c @@ -1073,7 +1073,7 @@ static int __ufshcd_tx_eqtr(struct ufs_hba *hba, struct ufs_pa_layer_attr *pwr_mode) { struct ufshcd_tx_eqtr_data *eqtr_data __free(kfree) = - kzalloc(sizeof(*eqtr_data), GFP_KERNEL); + kzalloc_obj(*eqtr_data); struct tx_eqtr_iter h_iter = {}; struct tx_eqtr_iter d_iter = {}; u32 gear = pwr_mode->gear_tx; diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c index 62396212a0a7..65c0816bc675 100644 --- a/drivers/ufs/host/ufs-qcom.c +++ b/drivers/ufs/host/ufs-qcom.c @@ -2761,7 +2761,7 @@ static int ufs_qcom_get_rx_fom(struct ufs_hba *hba, struct tx_eqtr_iter *d_iter) { struct ufshcd_tx_eq_params *params __free(kfree) = - kzalloc(sizeof(*params), GFP_KERNEL); + kzalloc_obj(*params); struct ufs_qcom_host *host = ufshcd_get_variant(hba); struct ufs_pa_layer_attr old_pwr_info; u32 fom[PA_MAXDATALANES] = { 0 }; diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c index bf02545b37a2..500c9c19c78b 100644 --- a/drivers/usb/gadget/function/f_ncm.c +++ b/drivers/usb/gadget/function/f_ncm.c @@ -1766,7 +1766,7 @@ static struct usb_function *ncm_alloc(struct usb_function_instance *fi) int status; /* allocate and initialize one new instance */ - ncm = kzalloc(sizeof(*ncm), GFP_KERNEL); + ncm = kzalloc_obj(*ncm); if (!ncm) return ERR_PTR(-ENOMEM); diff --git a/drivers/usb/usbip/usbip_common.c b/drivers/usb/usbip/usbip_common.c index a5837c0feb05..100f8920624b 100644 --- a/drivers/usb/usbip/usbip_common.c +++ b/drivers/usb/usbip/usbip_common.c @@ -696,7 +696,7 @@ int usbip_recv_iso(struct usbip_device *ud, struct urb *urb) size = np * sizeof(*iso); - buff = kcalloc(np, sizeof(*iso), GFP_KERNEL); + buff = kzalloc_objs(*iso, np); if (!buff) return -ENOMEM; diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 69922be28b54..076c1b0ab87f 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -1478,7 +1478,7 @@ static int gnttab_map(unsigned int start_idx, unsigned int end_idx) /* No need for kzalloc as it is initialized in following hypercall * GNTTABOP_setup_table. */ - frames = kmalloc_array(nr_gframes, sizeof(*frames), GFP_ATOMIC); + frames = kmalloc_objs(*frames, nr_gframes, GFP_ATOMIC); if (!frames) return -ENOMEM; diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c index e549e222602e..fa6b7143db98 100644 --- a/fs/9p/vfs_dentry.c +++ b/fs/9p/vfs_dentry.c @@ -113,8 +113,7 @@ void v9fs_dentry_fid_remove(struct dentry *dentry) */ static int v9fs_dentry_init(struct dentry *dentry) { - struct v9fs_dentry *v9fs_dentry = kzalloc(sizeof(*v9fs_dentry), - GFP_KERNEL); + struct v9fs_dentry *v9fs_dentry = kzalloc_obj(*v9fs_dentry); if (!v9fs_dentry) return -ENOMEM; diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 81565366d937..2db534a2c7cc 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -1801,7 +1801,7 @@ static int afs_symlink(struct mnt_idmap *idmap, struct inode *dir, goto error; ret = -ENOMEM; - symlink = kmalloc_flex(struct afs_symlink, content, clen + 1, GFP_KERNEL); + symlink = kmalloc_flex(struct afs_symlink, content, clen + 1); if (!symlink) goto error; refcount_set(&symlink->ref, 1); diff --git a/fs/afs/symlink.c b/fs/afs/symlink.c index 16b4823cb7b7..6b8c122877ca 100644 --- a/fs/afs/symlink.c +++ b/fs/afs/symlink.c @@ -119,8 +119,7 @@ static ssize_t afs_do_read_symlink(struct afs_vnode *vnode) vnode->directory_size = i_size; /* Copy the symlink. */ - symlink = kmalloc_flex(struct afs_symlink, content, i_size + 1, - GFP_KERNEL); + symlink = kmalloc_flex(struct afs_symlink, content, i_size + 1); if (!symlink) return -ENOMEM; diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index ddfd3aa57ac8..620da85948b4 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -331,8 +331,8 @@ static int entry_attach_interpreter(struct binfmt_misc_entry *e, return -ENOSPC; /* One allocation, both strings in it, like the entry's own buffer. */ - interp = kmalloc(struct_size(interp, name, nlen + plen + 2), - GFP_KERNEL_ACCOUNT); + interp = kmalloc_flex(*interp, name, nlen + plen + 2, + GFP_KERNEL_ACCOUNT); if (!interp) { dec_ucount(ucounts, UCOUNT_BINFMT_MISC_INTERPRETERS); return -ENOMEM; @@ -858,8 +858,7 @@ static struct binfmt_misc_entry *create_entry(const char __user *buffer, if ((count < 11) || (count > MAX_REGISTER_LENGTH)) return ERR_PTR(-EINVAL); - e = kmalloc(struct_size(e, buf, count + MISC_DELIM_PAD), - GFP_KERNEL_ACCOUNT); + e = kmalloc_flex(*e, buf, count + MISC_DELIM_PAD, GFP_KERNEL_ACCOUNT); if (!e) return ERR_PTR(-ENOMEM); diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 657c2cb0f881..e598b2d424ec 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -2546,7 +2546,7 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, } pool_ns_len = pool_ns ? pool_ns->len : 0; - perm = kmalloc_flex(*perm, pool_ns, pool_ns_len + 1, GFP_KERNEL); + perm = kmalloc_flex(*perm, pool_ns, pool_ns_len + 1); if (!perm) { err = -ENOMEM; goto out_unlock; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index a091f77cedaf..cc5fea0a9012 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -5492,7 +5492,7 @@ static void ceph_mdsc_reset_workfn(struct work_struct *work) goto out_complete; } - sessions = kcalloc(max_sessions, sizeof(*sessions), GFP_KERNEL); + sessions = kzalloc_objs(*sessions, max_sessions); if (!sessions) { mutex_unlock(&mdsc->mutex); ret = -ENOMEM; diff --git a/fs/ceph/subvolume_metrics.c b/fs/ceph/subvolume_metrics.c index 03fda1f9257b..01419c9482f1 100644 --- a/fs/ceph/subvolume_metrics.c +++ b/fs/ceph/subvolume_metrics.c @@ -245,7 +245,7 @@ int ceph_subvolume_metrics_snapshot(struct ceph_subvolume_metrics_tracker *track return 0; } - snap = kcalloc(count, sizeof(*snap), GFP_NOFS); + snap = kzalloc_objs(*snap, count, GFP_NOFS); if (!snap) { atomic64_inc(&tracker->snapshot_failures); return -ENOMEM; diff --git a/fs/coredump.c b/fs/coredump.c index ac3cd74808c6..6114839f5178 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -1000,7 +1000,7 @@ static bool coredump_pipe(struct core_name *cn, struct coredump_params *cprm, return false; } - helper_argv = kmalloc_array(argc + 1, sizeof(*helper_argv), GFP_KERNEL); + helper_argv = kmalloc_objs(*helper_argv, argc + 1); if (!helper_argv) { coredump_report_failure("%s failed to allocate memory", __func__); return false; diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index 062103e42cd8..0cac890cf370 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -1116,7 +1116,7 @@ static int ext4_fc_snapshot_inode(struct inode *inode, else if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) inode_len += ei->i_extra_isize; - snap = kmalloc(struct_size(snap, inode_buf, inode_len), GFP_NOFS); + snap = kmalloc_flex(*snap, inode_buf, inode_len, GFP_NOFS); if (!snap) { atomic64_inc(&stats->snap_fail_nomem); ext4_fc_set_snap_err(snap_err, EXT4_FC_SNAP_ERR_NOMEM); @@ -1522,7 +1522,7 @@ static int ext4_fc_alloc_snapshot_inodes(struct super_block *sb, if (nr_inodes > EXT4_FC_SNAPSHOT_MAX_INODES) return -E2BIG; - inodes = kvcalloc(nr_inodes, sizeof(*inodes), GFP_NOFS); + inodes = kvzalloc_objs(*inodes, nr_inodes, GFP_NOFS); if (!inodes) return -ENOMEM; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 8d6135a6108a..9a36d0329e22 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1597,8 +1597,7 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii, * manually extract pages using iov_iter_extract_pages() and then * copy that to a folios array. */ - struct page **pages = kcalloc(max_pages, sizeof(struct page *), - GFP_KERNEL); + struct page **pages = kzalloc_objs(struct page *, max_pages); if (!pages) { ret = -ENOMEM; goto out; diff --git a/fs/fuse/readdir.c b/fs/fuse/readdir.c index 5ca87151d70d..d2599043f7ec 100644 --- a/fs/fuse/readdir.c +++ b/fs/fuse/readdir.c @@ -336,7 +336,7 @@ static int parse_dirplusfile(char *buf, size_t nbytes, struct file *file, static struct page **fuse_readdir_alloc_buf(struct fuse_args_pages *ap, size_t *bufsize) { unsigned int i, nr_alloc, nr_pages = DIV_ROUND_UP(*bufsize, PAGE_SIZE); - struct page **pages = kcalloc(nr_pages, sizeof(*pages), GFP_KERNEL); + struct page **pages = kzalloc_objs(*pages, nr_pages); if (!pages) return NULL; diff --git a/fs/hfs/bnode.c b/fs/hfs/bnode.c index 1b331108d9c0..fcb5b9cd17f6 100644 --- a/fs/hfs/bnode.c +++ b/fs/hfs/bnode.c @@ -312,7 +312,7 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid) return NULL; } - node = kzalloc_flex(*node, page, tree->pages_per_bnode, GFP_KERNEL); + node = kzalloc_flex(*node, page, tree->pages_per_bnode); if (!node) return NULL; node->tree = tree; diff --git a/fs/namespace.c b/fs/namespace.c index 1ecd96c918b3..ae5dc64f8b45 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -5999,7 +5999,7 @@ SYSCALL_DEFINE4(statmount, const struct mnt_id_req __user *, req, return -EPERM; } - ks = kmalloc(sizeof(*ks), GFP_KERNEL_ACCOUNT); + ks = kmalloc_obj(*ks, GFP_KERNEL_ACCOUNT); if (!ks) return -ENOMEM; diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index a47c90f40422..a7ebce53faec 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -358,7 +358,7 @@ int nfsd_nl_expkey_get_reqs_dumpit(struct sk_buff *skb, goto out_unlock; } - items = kcalloc(cnt, sizeof(*items), GFP_KERNEL); + items = kzalloc_objs(*items, cnt); seqnos = kcalloc(cnt, sizeof(*seqnos), GFP_KERNEL); if (!items || !seqnos) { ret = -ENOMEM; @@ -685,7 +685,7 @@ int nfsd_nl_svc_export_get_reqs_dumpit(struct sk_buff *skb, goto out_unlock; } - items = kcalloc(cnt, sizeof(*items), GFP_KERNEL); + items = kzalloc_objs(*items, cnt); seqnos = kcalloc(cnt, sizeof(*seqnos), GFP_KERNEL); pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); if (!items || !seqnos || !pathbuf) { @@ -786,8 +786,7 @@ static int nfsd_nl_parse_fslocations(struct nlattr *attr, if (!count) return 0; - fsloc->locations = kcalloc(count, sizeof(struct nfsd4_fs_location), - GFP_KERNEL); + fsloc->locations = kzalloc_objs(struct nfsd4_fs_location, count); if (!fsloc->locations) return -ENOMEM; diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index a901bbe67e03..19dc337502ca 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -1981,12 +1981,12 @@ int nfsd_net_cb_init(struct nfsd_net *nn) { struct nfsd_net_cb *cb; - cb = kzalloc(sizeof(*cb), GFP_KERNEL); + cb = kzalloc_obj(*cb); if (!cb) return -ENOMEM; cb->version4.counts = kzalloc_objs(unsigned int, - ARRAY_SIZE(nfs4_cb_procedures), GFP_KERNEL); + ARRAY_SIZE(nfs4_cb_procedures)); if (!cb->version4.counts) { kfree(cb); return -ENOMEM; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 18e17232cf94..9c4adf3110ae 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1341,7 +1341,7 @@ alloc_init_dir_deleg(struct nfs4_client *clp, struct nfs4_file *fp) return NULL; } - ncn->ncn_nf = kcalloc(NOTIFY4_EVENT_QUEUE_SIZE, sizeof(*ncn->ncn_nf), GFP_KERNEL); + ncn->ncn_nf = kzalloc_objs(*ncn->ncn_nf, NOTIFY4_EVENT_QUEUE_SIZE); if (!ncn->ncn_nf) { nfs4_put_stid(&dp->dl_stid); return NULL; @@ -10419,8 +10419,9 @@ alloc_nfsd_notify_event(u32 mask, const struct qstr *q, struct dentry *dentry, newnamelen = newname.name.len; } - ne = kmalloc(struct_size(ne, ne_name, q->len + 1 + - (newnamelen ? newnamelen + 1 : 0)), GFP_NOFS); + ne = kmalloc_flex(*ne, ne_name, + q->len + 1 + (newnamelen ? newnamelen + 1 : 0), + GFP_NOFS); if (!ne) goto out; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index adb032b7311a..5abb2d4274c9 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1647,7 +1647,7 @@ static int nfsd_nl_fh_key_set(const struct nlattr *attr, struct nfsd_net *nn) k1 = get_unaligned_le64(nla_data(attr) + 8); if (!fh_key) { - fh_key = kmalloc(sizeof(siphash_key_t), GFP_KERNEL); + fh_key = kmalloc_obj(siphash_key_t); if (!fh_key) { trace_nfsd_ctl_fh_key_set(false, -ENOMEM); return -ENOMEM; diff --git a/fs/ntfs/bitmap.c b/fs/ntfs/bitmap.c index 1840b7d84c62..5a4457551306 100644 --- a/fs/ntfs/bitmap.c +++ b/fs/ntfs/bitmap.c @@ -40,7 +40,7 @@ int ntfs_trim_fs(struct ntfs_volume *vol, struct fstrim_range *range) end_cluster = vol->nr_clusters; } - ra = kzalloc(sizeof(*ra), GFP_NOFS); + ra = kzalloc_obj(*ra, GFP_NOFS); if (!ra) return -ENOMEM; diff --git a/fs/ntfs/compress.c b/fs/ntfs/compress.c index 197d8607fc63..99a3ea2b5c55 100644 --- a/fs/ntfs/compress.c +++ b/fs/ntfs/compress.c @@ -514,8 +514,8 @@ int ntfs_read_compressed_block(struct folio *folio) return -EIO; } - pages = kmalloc_array(nr_pages, sizeof(struct page *), GFP_NOFS); - completed_pages = kmalloc_array(nr_pages + 1, sizeof(int), GFP_NOFS); + pages = kmalloc_objs(struct page *, nr_pages, GFP_NOFS); + completed_pages = kmalloc_objs(int, nr_pages + 1, GFP_NOFS); if (unlikely(!pages || !completed_pages)) { kfree(pages); @@ -1262,7 +1262,7 @@ static int ntfs_compress_workspace_init(struct ntfs_inode *ni, size = ni->itype.compressed.block_size + 2 * (ni->itype.compressed.block_size / NTFS_SB_SIZE) + 2; ws->nr_pages = DIV_ROUND_UP(size, PAGE_SIZE); - ws->pages = kcalloc(ws->nr_pages, sizeof(*ws->pages), GFP_NOFS); + ws->pages = kzalloc_objs(*ws->pages, ws->nr_pages, GFP_NOFS); if (!ws->pages) return -ENOMEM; @@ -1483,7 +1483,7 @@ int ntfs_compress_write(struct ntfs_inode *ni, loff_t pos, size_t count, pages_per_cb = DIV_ROUND_UP(offset_in_page(pos & ~(cb_size - 1)) + cb_size, PAGE_SIZE); - pages = kmalloc_array(pages_per_cb, sizeof(struct page *), GFP_NOFS); + pages = kmalloc_objs(struct page *, pages_per_cb, GFP_NOFS); if (!pages) return -ENOMEM; ctx = kvzalloc_obj(*ctx, GFP_NOFS); diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c index 2d594cbb4ebe..df60138f9b2d 100644 --- a/fs/ntfs/dir.c +++ b/fs/ntfs/dir.c @@ -166,8 +166,8 @@ u64 ntfs_lookup_inode_by_name(struct ntfs_inode *dir_ni, const __le16 *uname, */ if (ie->key.file_name.file_name_type == FILE_NAME_DOS) { if (!name) { - name = kmalloc(sizeof(struct ntfs_name), - GFP_NOFS); + name = kmalloc_obj(struct ntfs_name, + GFP_NOFS); if (!name) { err = -ENOMEM; goto err_out; @@ -401,8 +401,8 @@ u64 ntfs_lookup_inode_by_name(struct ntfs_inode *dir_ni, const __le16 *uname, */ if (ie->key.file_name.file_name_type == FILE_NAME_DOS) { if (!name) { - name = kmalloc(sizeof(struct ntfs_name), - GFP_NOFS); + name = kmalloc_obj(struct ntfs_name, + GFP_NOFS); if (!name) { err = -ENOMEM; goto unm_err_out; @@ -700,7 +700,7 @@ static int ntfs_ia_blocks_readahead(struct ntfs_inode *ia_ni, loff_t pos) if (dir_start_index >= dir_end_index) return 0; - dir_ra = kzalloc(sizeof(*dir_ra), GFP_NOFS); + dir_ra = kzalloc_obj(*dir_ra, GFP_NOFS); if (!dir_ra) return -ENOMEM; @@ -777,7 +777,7 @@ static int ntfs_readdir(struct file *file, struct dir_context *actor) return -ENOMEM; } - ra = kzalloc(sizeof(struct file_ra_state), GFP_NOFS); + ra = kzalloc_obj(struct file_ra_state, GFP_NOFS); if (!ra) { kfree(name); ntfs_index_ctx_put(ictx); @@ -813,7 +813,7 @@ static int ntfs_readdir(struct file *file, struct dir_context *actor) goto out; } } else if (!private) { - private = kzalloc(sizeof(struct ntfs_file_private), GFP_KERNEL); + private = kzalloc_obj(struct ntfs_file_private); if (!private) { err = -ENOMEM; goto out; @@ -949,7 +949,7 @@ static int ntfs_readdir(struct file *file, struct dir_context *actor) } if (!nir) { - nir = kzalloc(sizeof(struct ntfs_index_ra), GFP_KERNEL); + nir = kzalloc_obj(struct ntfs_index_ra); if (nir) { nir->start_index = index; nir->count = 1; diff --git a/fs/ntfs/ea.c b/fs/ntfs/ea.c index 3f4ba7667522..b4fcfbe2da4c 100644 --- a/fs/ntfs/ea.c +++ b/fs/ntfs/ea.c @@ -235,7 +235,7 @@ static int ntfs_set_ea(struct inode *inode, const char *name, size_t name_len, ea_info_qsize = le32_to_cpu(p_ea_info->ea_query_length); } else { create_ea_info: - p_ea_info = kzalloc(sizeof(struct ea_information), GFP_NOFS); + p_ea_info = kzalloc_obj(struct ea_information, GFP_NOFS); if (!p_ea_info) return -ENOMEM; diff --git a/fs/ntfs/index.c b/fs/ntfs/index.c index 46a8b19c0723..580998990bc9 100644 --- a/fs/ntfs/index.c +++ b/fs/ntfs/index.c @@ -1660,7 +1660,7 @@ static int ntfs_ib_split(struct ntfs_index_context *icx, struct index_block *ib) goto out; } } else { - si = kzalloc(sizeof(struct split_info), GFP_NOFS); + si = kzalloc_obj(struct split_info, GFP_NOFS); if (!si) { ntfs_ibm_clear(icx, new_vcn); ret = -ENOMEM; diff --git a/fs/ntfs/logfile.c b/fs/ntfs/logfile.c index 024ddee42dc8..1404664dacc0 100644 --- a/fs/ntfs/logfile.c +++ b/fs/ntfs/logfile.c @@ -691,7 +691,7 @@ bool ntfs_empty_logfile(struct inode *log_vi) memset(empty_buf, 0xff, vol->cluster_size); - ra = kzalloc(sizeof(*ra), GFP_NOFS); + ra = kzalloc_obj(*ra, GFP_NOFS); if (!ra) goto err; diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c index 7e58c99f1728..98ab686a5ea2 100644 --- a/fs/ntfs/mft.c +++ b/fs/ntfs/mft.c @@ -2635,11 +2635,13 @@ static int ntfs_write_mft_block(struct folio *folio, struct writeback_control *w struct ntfs_inode *ni = NTFS_I(vi); struct ntfs_volume *vol = ni->vol; u8 *kaddr; - struct ntfs_inode **locked_nis __free(kfree) = kmalloc_array(PAGE_SIZE / NTFS_BLOCK_SIZE, - sizeof(struct ntfs_inode *), GFP_NOFS); + struct ntfs_inode **locked_nis __free(kfree) = kmalloc_objs(struct ntfs_inode *, + PAGE_SIZE / NTFS_BLOCK_SIZE, + GFP_NOFS); int nr_locked_nis = 0, err = 0, mft_ofs, prev_mft_ofs; - struct inode **ref_inos __free(kfree) = kmalloc_array(PAGE_SIZE / NTFS_BLOCK_SIZE, - sizeof(struct inode *), GFP_NOFS); + struct inode **ref_inos __free(kfree) = kmalloc_objs(struct inode *, + PAGE_SIZE / NTFS_BLOCK_SIZE, + GFP_NOFS); int nr_ref_inos = 0; struct bio *bio = NULL; u64 mft_no; diff --git a/fs/ntfs/runlist.c b/fs/ntfs/runlist.c index 00373e450ea7..3a61f19bcbee 100644 --- a/fs/ntfs/runlist.c +++ b/fs/ntfs/runlist.c @@ -1804,7 +1804,7 @@ struct runlist_element *ntfs_rl_insert_range(struct runlist_element *dst_rl, int new_2nd_cnt = src_cnt; new_cnt = new_1st_cnt + new_2nd_cnt + new_3rd_cnt; new_cnt += dst_rl_split.lcn >= LCN_HOLE ? 1 : 0; - new_rl = kvcalloc(new_cnt, sizeof(*new_rl), GFP_NOFS); + new_rl = kvzalloc_objs(*new_rl, new_cnt, GFP_NOFS); if (!new_rl) return ERR_PTR(-ENOMEM); @@ -1888,13 +1888,13 @@ struct runlist_element *ntfs_rl_punch_hole(struct runlist_element *dst_rl, int d punch_cnt = (int)(e_rl - s_rl) + 1; - *punch_rl = kvcalloc(punch_cnt + 1, sizeof(struct runlist_element), - GFP_NOFS); + *punch_rl = kvzalloc_objs(struct runlist_element, punch_cnt + 1, + GFP_NOFS); if (!*punch_rl) return ERR_PTR(-ENOMEM); new_cnt = dst_cnt - (int)(e_rl - s_rl + 1) + 3; - new_rl = kvcalloc(new_cnt, sizeof(struct runlist_element), GFP_NOFS); + new_rl = kvzalloc_objs(struct runlist_element, new_cnt, GFP_NOFS); if (!new_rl) { kvfree(*punch_rl); *punch_rl = NULL; @@ -2038,13 +2038,13 @@ struct runlist_element *ntfs_rl_collapse_range(struct runlist_element *dst_rl, i one_split_3 = e_rl == s_rl && begin_split && end_split; punch_cnt = (int)(e_rl - s_rl) + 1; - *punch_rl = kvcalloc(punch_cnt + 1, sizeof(struct runlist_element), - GFP_NOFS); + *punch_rl = kvzalloc_objs(struct runlist_element, punch_cnt + 1, + GFP_NOFS); if (!*punch_rl) return ERR_PTR(-ENOMEM); new_cnt = dst_cnt - (int)(e_rl - s_rl + 1) + 3; - new_rl = kvcalloc(new_cnt, sizeof(struct runlist_element), GFP_NOFS); + new_rl = kvzalloc_objs(struct runlist_element, new_cnt, GFP_NOFS); if (!new_rl) { kvfree(*punch_rl); *punch_rl = NULL; diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 60d43339c590..5aad2d2a36bb 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -2539,7 +2539,7 @@ static int ntfs_init_fs_context(struct fs_context *fc) struct ntfs_volume *vol; /* Allocate a new struct ntfs_volume and place it in sb->s_fs_info. */ - vol = kmalloc(sizeof(struct ntfs_volume), GFP_NOFS); + vol = kmalloc_obj(struct ntfs_volume, GFP_NOFS); if (!vol) return -ENOMEM; diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index e7fe29cb6028..7d6f7f6022eb 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -1044,7 +1044,7 @@ static int ovl_dir_open(struct inode *inode, struct file *file) struct ovl_dir_file *od; enum ovl_path_type type; - od = kzalloc(sizeof(struct ovl_dir_file), GFP_KERNEL); + od = kzalloc_obj(struct ovl_dir_file); if (!od) return -ENOMEM; diff --git a/fs/smb/client/cifs_swn.c b/fs/smb/client/cifs_swn.c index fe10719e627e..c49ecddf4a33 100644 --- a/fs/smb/client/cifs_swn.c +++ b/fs/smb/client/cifs_swn.c @@ -443,7 +443,7 @@ static struct cifs_swn_reg *cifs_get_swn_reg(struct cifs_tcon *tcon) goto unlock; } - reg = kmalloc_obj(struct cifs_swn_reg, GFP_KERNEL); + reg = kmalloc_obj(struct cifs_swn_reg); if (reg == NULL) { ret = -ENOMEM; goto fail_unlock; diff --git a/fs/smb/client/dfs_cache.c b/fs/smb/client/dfs_cache.c index 86dba25b7a5a..f6c4259479c5 100644 --- a/fs/smb/client/dfs_cache.c +++ b/fs/smb/client/dfs_cache.c @@ -365,7 +365,7 @@ static struct cache_dfs_tgt *alloc_target(const char *name, int path_consumed) { struct cache_dfs_tgt *t; - t = kmalloc_obj(*t, GFP_KERNEL); + t = kmalloc_obj(*t); if (!t) return ERR_PTR(-ENOMEM); t->name = kstrdup(name, GFP_KERNEL); diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index 98ea5c6c34af..96063e355186 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -237,7 +237,7 @@ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, num_rqst = 0; server = cifs_pick_channel(ses); - vars = kzalloc_obj(*vars, GFP_KERNEL); + vars = kzalloc_obj(*vars); if (vars == NULL) { rc = -ENOMEM; goto out; diff --git a/fs/smb/server/ksmbd_work.c b/fs/smb/server/ksmbd_work.c index f35335307670..d307aefe0aec 100644 --- a/fs/smb/server/ksmbd_work.c +++ b/fs/smb/server/ksmbd_work.c @@ -30,7 +30,7 @@ static int ksmbd_reserve_iov(struct ksmbd_work *work, int need_iov_cnt) } while (new_alloc_cnt < work->iov_cnt + need_iov_cnt); if (work->iov == work->iov_inline) { - new = kcalloc(new_alloc_cnt, sizeof(*new), KSMBD_DEFAULT_GFP); + new = kzalloc_objs(*new, new_alloc_cnt, KSMBD_DEFAULT_GFP); if (!new) return -ENOMEM; diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 0ecc52fde69c..b7ce67094626 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -11820,7 +11820,7 @@ static void smb2_notify_cancel_fn(void **argv) return; conn = in_work->conn; - ctx = kmalloc(sizeof(*ctx), GFP_ATOMIC); + ctx = kmalloc_obj(*ctx, GFP_ATOMIC); if (!ctx) { /* Can't defer the response -- free without sending one. */ list_del_init(&in_work->async_request_entry); diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c index f190c088591b..7938d2324e87 100644 --- a/fs/xfs/libxfs/xfs_da_btree.c +++ b/fs/xfs/libxfs/xfs_da_btree.c @@ -2746,8 +2746,8 @@ xfs_dabuf_map( * larger one that needs to be free by the caller. */ if (nirecs > 1) { - map = kcalloc(nirecs, sizeof(struct xfs_buf_map), - GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); + map = kzalloc_objs(struct xfs_buf_map, nirecs, + GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); *mapp = map; } diff --git a/init/initramfs_test.c b/init/initramfs_test.c index 9cf316c13ffa..1154547721ea 100644 --- a/init/initramfs_test.c +++ b/init/initramfs_test.c @@ -514,7 +514,7 @@ static void __init initramfs_test_hdr_hex(struct kunit *test) char fdata[] = "this file data will not be unpacked"; struct initramfs_test_bufs { char cpio_src[(CPIO_HDRLEN + PATH_MAX + 3 + sizeof(fdata)) * 2]; - } *tbufs = kzalloc(sizeof(struct initramfs_test_bufs), GFP_KERNEL); + } *tbufs = kzalloc_obj(struct initramfs_test_bufs); struct initramfs_test_cpio c[] = { { .magic = "070701", .ino = 1, diff --git a/io_uring/napi.c b/io_uring/napi.c index bfc771445912..ca1c814fa73a 100644 --- a/io_uring/napi.c +++ b/io_uring/napi.c @@ -58,7 +58,7 @@ int __io_napi_add_id(struct io_ring_ctx *ctx, unsigned int napi_id, } } - e = kmalloc(sizeof(*e), GFP_NOWAIT); + e = kmalloc_obj(*e, GFP_NOWAIT); if (!e) return -ENOMEM; diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c index 1b3b11405dac..86d580d4410d 100644 --- a/io_uring/zcrx.c +++ b/io_uring/zcrx.c @@ -483,8 +483,8 @@ static int io_zcrx_append_area(struct io_zcrx_ifq *ifq, old_areas = ifq->areas; old_nr = ifq->nr_areas; - areas = kmalloc_array(old_nr + 1, sizeof(areas[0]), - GFP_KERNEL_ACCOUNT | __GFP_ZERO); + areas = kmalloc_objs(areas[0], old_nr + 1, + GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!areas) return -ENOMEM; if (old_areas) diff --git a/kernel/bpf/diagnostics.c b/kernel/bpf/diagnostics.c index b682fd2be443..0abbbe177e31 100644 --- a/kernel/bpf/diagnostics.c +++ b/kernel/bpf/diagnostics.c @@ -266,7 +266,7 @@ static char *diag_fmt_alloc(struct bpf_verifier_env *env, size_t size) } capacity = max_t(size_t, BPF_DIAG_FMT_CHUNK_SIZE, size); - chunk = kmalloc(struct_size(chunk, data, capacity), GFP_KERNEL_ACCOUNT); + chunk = kmalloc_flex(*chunk, data, capacity, GFP_KERNEL_ACCOUNT); if (!chunk) return NULL; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index d40cb5dd446c..c2796e8d29ea 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -511,7 +511,7 @@ static int bpf_ma_set_dtor(struct bpf_map *map, struct bpf_mem_alloc *ma, if (IS_ERR_OR_NULL(map->record)) return 0; - hrec = kzalloc(sizeof(*hrec), GFP_KERNEL); + hrec = kzalloc_obj(*hrec); if (!hrec) return -ENOMEM; hrec->key_size = map->key_size; diff --git a/kernel/bpf/liveness.c b/kernel/bpf/liveness.c index 74fc4b3f80d6..301fc60bddc4 100644 --- a/kernel/bpf/liveness.c +++ b/kernel/bpf/liveness.c @@ -85,7 +85,7 @@ static struct func_instance *call_instance(struct bpf_verifier_env *env, if (f) return f; - f = kvzalloc(sizeof(*f), GFP_KERNEL_ACCOUNT); + f = kvzalloc_obj(*f, GFP_KERNEL_ACCOUNT); if (!f) return ERR_PTR(-ENOMEM); f->callsite = lookup_key; diff --git a/kernel/bpf/log.c b/kernel/bpf/log.c index 589770ca3d3a..fb032dfdc0de 100644 --- a/kernel/bpf/log.c +++ b/kernel/bpf/log.c @@ -862,7 +862,7 @@ struct bpf_verifier_log *bpf_log_attr_create_vlog(struct bpf_log_attr *attr_log, if (!size) return NULL; - log = kzalloc_obj(*log, GFP_KERNEL); + log = kzalloc_obj(*log); if (!log) return ERR_PTR(-ENOMEM); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e421ea2b80c3..a68e5435ca5f 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5483,7 +5483,7 @@ static int check_max_stack_depth(struct bpf_verifier_env *env) bool priv_stack_supported; int ret; - dinfo = kvcalloc(env->subprog_cnt, sizeof(*dinfo), GFP_KERNEL_ACCOUNT); + dinfo = kvzalloc_objs(*dinfo, env->subprog_cnt, GFP_KERNEL_ACCOUNT); if (!dinfo) return -ENOMEM; @@ -20536,8 +20536,7 @@ static int process_fd_array_continuous(struct bpf_verifier_env *env, return -E2BIG; } - env->fd_array = kvcalloc(cnt, sizeof(*env->fd_array), - GFP_KERNEL_ACCOUNT); + env->fd_array = kvzalloc_objs(*env->fd_array, cnt, GFP_KERNEL_ACCOUNT); if (!env->fd_array) return -ENOMEM; env->fd_array_cnt = cnt; diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c index fdc070f419f6..957707158ff6 100644 --- a/kernel/dma/map_benchmark.c +++ b/kernel/dma/map_benchmark.c @@ -51,8 +51,7 @@ struct dma_single_map_param { static void *dma_single_map_benchmark_prepare(struct map_benchmark_data *map) { - struct dma_single_map_param *params __free(kfree) = kzalloc(sizeof(*params), - GFP_KERNEL); + struct dma_single_map_param *params __free(kfree) = kzalloc_obj(*params); if (!params) return NULL; diff --git a/kernel/events/core.c b/kernel/events/core.c index a6c8e38a3110..a7adc8e34089 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -13558,9 +13558,8 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, return ERR_PTR(err); if (has_addr_filter(event)) { - event->addr_filter_ranges = kcalloc(pmu->nr_addr_filters, - sizeof(struct perf_addr_filter_range), - GFP_KERNEL); + event->addr_filter_ranges = kzalloc_objs(struct perf_addr_filter_range, + pmu->nr_addr_filters); if (!event->addr_filter_ranges) return ERR_PTR(-ENOMEM); diff --git a/kernel/futex/core.c b/kernel/futex/core.c index 51ba5e1257c0..a061f54b606d 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -1874,8 +1874,8 @@ static int futex_hash_allocate(unsigned int hash_slots, unsigned int flags) free_percpu(ref); } - fph = kvzalloc(struct_size(fph, queues, hash_slots), - GFP_KERNEL_ACCOUNT | __GFP_NOWARN); + fph = kvzalloc_flex(*fph, queues, hash_slots, + GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (!fph) return -ENOMEM; @@ -2103,7 +2103,7 @@ static int __init futex_init(void) size = sizeof(struct futex_hash_bucket) * hashsize; order = get_order(size); - __futex_queues = kcalloc(nr_node_ids, sizeof(*__futex_queues), GFP_KERNEL); + __futex_queues = kzalloc_objs(*__futex_queues, nr_node_ids); kmemleak_not_leak(__futex_queues); runtime_const_init(shift, __futex_shift); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 2fbff2618a1e..57eff26fa646 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -2306,7 +2306,7 @@ int request_nmi(unsigned int irq, irq_handler_t handler, !irq_supports_nmi(desc)) return -EINVAL; - action = kzalloc(sizeof(struct irqaction), GFP_KERNEL); + action = kzalloc_obj(struct irqaction); if (!action) return -ENOMEM; diff --git a/kernel/jump_label.c b/kernel/jump_label.c index e851e4b37d0e..ab6b774bcfd7 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -726,12 +726,11 @@ static int jump_label_add_module(struct module *mod) if (static_key_sealed(key)) goto do_poke; - jlm = kzalloc(sizeof(struct static_key_mod), GFP_KERNEL); + jlm = kzalloc_obj(struct static_key_mod); if (!jlm) return -ENOMEM; if (!static_key_linked(key)) { - jlm2 = kzalloc(sizeof(struct static_key_mod), - GFP_KERNEL); + jlm2 = kzalloc_obj(struct static_key_mod); if (!jlm2) { kfree(jlm); return -ENOMEM; diff --git a/kernel/kthread.c b/kernel/kthread.c index 63beb59b7a3d..a3f95c90456b 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -852,7 +852,7 @@ int kthread_affine_preferred(struct task_struct *p, const struct cpumask *mask) if (!zalloc_cpumask_var(&affinity, GFP_KERNEL)) return -ENOMEM; - kthread->preferred_affinity = kzalloc(sizeof(struct cpumask), GFP_KERNEL); + kthread->preferred_affinity = kzalloc_obj(struct cpumask); if (!kthread->preferred_affinity) { ret = -ENOMEM; goto out; diff --git a/kernel/sched/ext/cid.c b/kernel/sched/ext/cid.c index 39f88deb94bc..bc4eee5bb4cb 100644 --- a/kernel/sched/ext/cid.c +++ b/kernel/sched/ext/cid.c @@ -98,16 +98,16 @@ static struct scx_cid_tables *scx_cid_alloc_tables(void) u32 npossible = num_possible_cpus(); struct scx_cid_tables *tbls; - tbls = kzalloc_obj(*tbls, GFP_KERNEL); + tbls = kzalloc_obj(*tbls); if (!tbls) return NULL; - tbls->cid_to_cpu = kvcalloc(npossible, sizeof(*tbls->cid_to_cpu), GFP_KERNEL); - tbls->cpu_to_cid = kvcalloc(nr_cpu_ids, sizeof(*tbls->cpu_to_cid), GFP_KERNEL); - tbls->cid_to_shard = kvcalloc(npossible, sizeof(*tbls->cid_to_shard), GFP_KERNEL); - tbls->shard_node = kvcalloc(npossible, sizeof(*tbls->shard_node), GFP_KERNEL); - tbls->shard_ranges = kvcalloc(npossible, sizeof(*tbls->shard_ranges), GFP_KERNEL); - tbls->topo = kvcalloc(npossible, sizeof(*tbls->topo), GFP_KERNEL); + tbls->cid_to_cpu = kvzalloc_objs(*tbls->cid_to_cpu, npossible); + tbls->cpu_to_cid = kvzalloc_objs(*tbls->cpu_to_cid, nr_cpu_ids); + tbls->cid_to_shard = kvzalloc_objs(*tbls->cid_to_shard, npossible); + tbls->shard_node = kvzalloc_objs(*tbls->shard_node, npossible); + tbls->shard_ranges = kvzalloc_objs(*tbls->shard_ranges, npossible); + tbls->topo = kvzalloc_objs(*tbls->topo, npossible); if (!tbls->cid_to_cpu || !tbls->cpu_to_cid || !tbls->cid_to_shard || !tbls->shard_node || !tbls->shard_ranges || !tbls->topo) { @@ -490,7 +490,7 @@ __bpf_kfunc void scx_bpf_cid_override(const s32 *cpu_to_cid__arena, u32 cpu_to_c * region that arena fault recovery covers. */ alloced = zalloc_cpumask_var(&seen, GFP_KERNEL); - node_counts = kcalloc(nr_node_ids, sizeof(*node_counts), GFP_KERNEL); + node_counts = kzalloc_objs(*node_counts, nr_node_ids); if (cpu_to_cid_cnt == nr_cpu_ids) cpu_to_cid = kmemdup(cpu_to_cid__arena, cpu_to_cid_cnt * sizeof(s32), GFP_KERNEL); diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c index 713aa26b2828..51de1d8b72a1 100644 --- a/kernel/sched/ext/ext.c +++ b/kernel/sched/ext/ext.c @@ -5449,7 +5449,7 @@ static ssize_t scx_attr_caps_show(struct kobject *kobj, struct scx_sched *sch = container_of(kobj, struct scx_sched, kobj); u32 npossible = num_possible_cpus(); struct scx_cmask *agg __free(kfree) = - kzalloc(struct_size(agg, bits, SCX_CMASK_NR_WORDS(npossible)), GFP_KERNEL); + kzalloc_flex(*agg, bits, SCX_CMASK_NR_WORDS(npossible)); unsigned long *agg_bm __free(bitmap) = bitmap_zalloc(npossible, GFP_KERNEL); ssize_t count = 0; s32 cap, si; diff --git a/kernel/sched/ext/sub.c b/kernel/sched/ext/sub.c index 0554448835bd..9e7040482bde 100644 --- a/kernel/sched/ext/sub.c +++ b/kernel/sched/ext/sub.c @@ -194,7 +194,7 @@ s32 scx_alloc_pshards(struct scx_sched *sch) shard_node = rcu_dereference_protected(scx_shard_node, lockdep_is_held(&scx_enable_mutex)); - pshard = kzalloc_objs(pshard[0], scx_nr_cid_shards, GFP_KERNEL); + pshard = kzalloc_objs(pshard[0], scx_nr_cid_shards); if (!pshard) return -ENOMEM; diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index ddb0b12a5c4a..1e9b00997ff2 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -945,7 +945,7 @@ int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter if (num < 0) return num; - addrs = kcalloc(num, sizeof(*addrs), GFP_KERNEL); + addrs = kzalloc_objs(*addrs, num); if (!addrs) return -ENOMEM; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index b0963ac6fd16..9726413a6385 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2600,8 +2600,8 @@ rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu) cpu_buffer->remote = buffer->remote; cpu_buffer->meta_page = (struct trace_buffer_meta *)(void *)desc->meta_va; cpu_buffer->nr_pages = nr_pages; - cpu_buffer->subbuf_ids = kcalloc(cpu_buffer->nr_pages + 1, - sizeof(*cpu_buffer->subbuf_ids), GFP_KERNEL); + cpu_buffer->subbuf_ids = kzalloc_objs(*cpu_buffer->subbuf_ids, + cpu_buffer->nr_pages + 1); if (!cpu_buffer->subbuf_ids) goto fail_free_reader; diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c index 78fa1cbda9ac..998e6390937a 100644 --- a/kernel/trace/trace_eprobe.c +++ b/kernel/trace/trace_eprobe.c @@ -930,7 +930,7 @@ static int __trace_eprobe_create(int argc, const char *argv[]) } else ep->filter_str = NULL; - ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + ctx = kzalloc_obj(*ctx); if (!ctx) return -ENOMEM; ctx->event = ep->event; diff --git a/kernel/trace/trace_remote.c b/kernel/trace/trace_remote.c index e6724f947170..75fa1ffc4c96 100644 --- a/kernel/trace/trace_remote.c +++ b/kernel/trace/trace_remote.c @@ -251,8 +251,8 @@ static int trace_remote_get(struct trace_remote *remote, int cpu) if (cpu != RING_BUFFER_ALL_CPUS && !remote->pcpu_reader_locks) { int lock_cpu; - remote->pcpu_reader_locks = kcalloc(nr_cpu_ids, sizeof(*remote->pcpu_reader_locks), - GFP_KERNEL); + remote->pcpu_reader_locks = kzalloc_objs(*remote->pcpu_reader_locks, + nr_cpu_ids); if (!remote->pcpu_reader_locks) { trace_remote_try_unload(remote); return -ENOMEM; @@ -324,7 +324,7 @@ static int __alloc_ring_buffer_iter(struct trace_remote_iterator *iter, int cpu) return iter->rb_iter ? 0 : -ENOMEM; } - iter->rb_iters = kcalloc(nr_cpu_ids, sizeof(*iter->rb_iters), GFP_KERNEL); + iter->rb_iters = kzalloc_objs(*iter->rb_iters, nr_cpu_ids); if (!iter->rb_iters) return -ENOMEM; @@ -1204,7 +1204,7 @@ remote_events_dir_header_page_read(struct file *filp, char __user *ubuf, size_t struct trace_seq *s; int ret; - s = kmalloc(sizeof(*s), GFP_KERNEL); + s = kmalloc_obj(*s); if (!s) return -ENOMEM; @@ -1227,7 +1227,7 @@ remote_events_dir_header_event_read(struct file *filp, char __user *ubuf, size_t struct trace_seq *s; int ret; - s = kmalloc(sizeof(*s), GFP_KERNEL); + s = kmalloc_obj(*s); if (!s) return -ENOMEM; diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c index b767a38a74f9..2f922b63d545 100644 --- a/lib/test_rhashtable.c +++ b/lib/test_rhashtable.c @@ -696,7 +696,7 @@ static int __init test_rhashtable_next_key(void) if (err) return err; - objs = kcalloc(n, sizeof(*objs), GFP_KERNEL); + objs = kzalloc_objs(*objs, n); if (!objs) { rhashtable_destroy(&ht); return -ENOMEM; diff --git a/lib/test_workqueue.c b/lib/test_workqueue.c index 99e160bd5ad1..2bdfcbbcabb4 100644 --- a/lib/test_workqueue.c +++ b/lib/test_workqueue.c @@ -149,11 +149,11 @@ static int __init run_bench(int n_threads, const char *scope, const char *label) if (ret) return ret; - ctxs = kcalloc(n_threads, sizeof(*ctxs), GFP_KERNEL); + ctxs = kzalloc_objs(*ctxs, n_threads); if (!ctxs) return -ENOMEM; - tasks = kcalloc(n_threads, sizeof(*tasks), GFP_KERNEL); + tasks = kzalloc_objs(*tasks, n_threads); if (!tasks) { kfree(ctxs); return -ENOMEM; diff --git a/lib/tests/kunit_iov_iter.c b/lib/tests/kunit_iov_iter.c index d9690ba1db88..32e42d8c7ca1 100644 --- a/lib/tests/kunit_iov_iter.c +++ b/lib/tests/kunit_iov_iter.c @@ -57,7 +57,7 @@ static void *__init iov_kunit_create_buffer(struct kunit *test, void *buffer; unsigned int i; - pages = kzalloc_objs(struct page *, npages, GFP_KERNEL); + pages = kzalloc_objs(struct page *, npages); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, pages); *ppages = pages; diff --git a/mm/damon/tests/vaddr-kunit.h b/mm/damon/tests/vaddr-kunit.h index 6a95441d193a..d61b503e319a 100644 --- a/mm/damon/tests/vaddr-kunit.h +++ b/mm/damon/tests/vaddr-kunit.h @@ -136,7 +136,7 @@ static void damon_do_test_apply_three_regions(struct kunit *test, if (!t) kunit_skip(test, "target alloc fail"); - ranges = kmalloc_array(nr_regions / 2, sizeof(*ranges), GFP_KERNEL); + ranges = kmalloc_objs(*ranges, nr_regions / 2); if (!ranges) { damon_destroy_target(t, NULL); kunit_skip(test, "ranges alloc fail"); diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index e7ad295504e4..c5bc60d16e40 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -981,7 +981,7 @@ batadv_wifi_net_device_insert(struct net_device *net_dev, u32 wifi_flags) ASSERT_RTNL(); - device_state = kzalloc_obj(*device_state, GFP_KERNEL); + device_state = kzalloc_obj(*device_state); if (!device_state) return -ENOMEM; diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index ffd7b37e7401..3f121099eb22 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -6423,8 +6423,7 @@ static int hci_update_event_filter_sync(struct hci_dev *hdev) goto update_scan; } - accept_list = kmalloc_array(num_entries, sizeof(*accept_list), - GFP_KERNEL); + accept_list = kmalloc_objs(*accept_list, num_entries); if (!accept_list) { hci_dev_unlock(hdev); return -ENOMEM; diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c index 300580c1a217..a8eda727bff1 100644 --- a/net/devlink/netlink.c +++ b/net/devlink/netlink.c @@ -251,7 +251,7 @@ devlink_get_parent_from_attrs_lock(struct net *net, struct nlattr **attrs) if (!attrs[DEVLINK_ATTR_PARENT_DEV]) return ERR_PTR(-EINVAL); - tb = kcalloc(maxtype + 1, sizeof(*tb), GFP_KERNEL); + tb = kzalloc_objs(*tb, maxtype + 1); if (!tb) return ERR_PTR(-ENOMEM); diff --git a/net/devlink/param.c b/net/devlink/param.c index 8ca0f3ed646c..95ac9db8c993 100644 --- a/net/devlink/param.c +++ b/net/devlink/param.c @@ -330,13 +330,12 @@ static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink, int err; int i; - default_value = kcalloc(DEVLINK_PARAM_CMODE_MAX + 1, - sizeof(*default_value), GFP_KERNEL); + default_value = kzalloc_objs(*default_value, + DEVLINK_PARAM_CMODE_MAX + 1); if (!default_value) return -ENOMEM; - param_value = kcalloc(DEVLINK_PARAM_CMODE_MAX + 1, - sizeof(*param_value), GFP_KERNEL); + param_value = kzalloc_objs(*param_value, DEVLINK_PARAM_CMODE_MAX + 1); if (!param_value) { kfree(default_value); return -ENOMEM; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 9f053eb8b46e..04dbb2babbcd 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2931,8 +2931,8 @@ static int bpf_iter_tcp_realloc_batch(struct bpf_tcp_iter_state *iter, { union bpf_tcp_iter_batch_item *new_batch; - new_batch = kvmalloc_array(new_batch_sz, sizeof(*new_batch), - flags | __GFP_NOWARN); + new_batch = kvmalloc_objs(*new_batch, new_batch_sz, + flags | __GFP_NOWARN); if (!new_batch) return -ENOMEM; diff --git a/net/mac80211/nan.c b/net/mac80211/nan.c index 19e08661be43..c7769da9617b 100644 --- a/net/mac80211/nan.c +++ b/net/mac80211/nan.c @@ -659,8 +659,7 @@ int ieee80211_nan_set_peer_sched(struct ieee80211_sub_if_data *sdata, if (!sta) return -ENOENT; - new_sched = kzalloc(struct_size(new_sched, channels, sched->n_channels), - GFP_KERNEL); + new_sched = kzalloc_flex(*new_sched, channels, sched->n_channels); if (!new_sched) return -ENOMEM; diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c index c92e3abb40d7..f05f75bf93e0 100644 --- a/net/mctp/test/route-test.c +++ b/net/mctp/test/route-test.c @@ -193,7 +193,7 @@ static void __mctp_route_test_init(struct kunit *test, if (netid != MCTP_NET_ANY) WRITE_ONCE(dev->mdev->net, netid); - dev->mdev->addrs = kmalloc_objs(u8, 1, GFP_KERNEL); + dev->mdev->addrs = kmalloc_objs(u8, 1); dev->mdev->num_addrs = 1; dev->mdev->addrs[0] = 8; diff --git a/net/mctp/test/utils.c b/net/mctp/test/utils.c index 6eef8d485c25..6b131084a249 100644 --- a/net/mctp/test/utils.c +++ b/net/mctp/test/utils.c @@ -88,7 +88,7 @@ struct mctp_test_dev *mctp_test_create_dev_with_addr(mctp_eid_t addr) if (!dev) return NULL; - dev->mdev->addrs = kmalloc_objs(u8, 1, GFP_KERNEL); + dev->mdev->addrs = kmalloc_objs(u8, 1); if (!dev->mdev->addrs) { mctp_test_destroy_dev(dev); return NULL; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 765a92fa90d6..31fbd5a28937 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3215,7 +3215,7 @@ static int nft_trans_delhook(struct nft_hook *hook, { struct nft_trans_hook *trans_hook; - trans_hook = kmalloc_obj(*trans_hook, GFP_KERNEL); + trans_hook = kmalloc_obj(*trans_hook); if (!trans_hook) return -ENOMEM; diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 66c2016f6049..f43bf768b31c 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -150,7 +150,7 @@ static int cttimeout_new_timeout(struct sk_buff *skb, goto err_proto_put; } - timeout = kzalloc(sizeof(*timeout), GFP_KERNEL); + timeout = kzalloc_obj(*timeout); if (timeout == NULL) { ret = -ENOMEM; goto err_proto_put; diff --git a/net/rds/info.c b/net/rds/info.c index 31e7ad108459..a57f81a05c87 100644 --- a/net/rds/info.c +++ b/net/rds/info.c @@ -205,7 +205,7 @@ int rds_info_getsockopt(struct socket *sock, int optname, sockopt_t *opt) * iterator code to allocate and hand it back. */ npages = iov_iter_npages(&opt->iter_out, INT_MAX); - pages = kvmalloc_array(npages, sizeof(*pages), GFP_KERNEL); + pages = kvmalloc_objs(*pages, npages); if (!pages) { ret = -ENOMEM; goto out; diff --git a/net/rxrpc/key.c b/net/rxrpc/key.c index a0aa78d89289..cbd26da44951 100644 --- a/net/rxrpc/key.c +++ b/net/rxrpc/key.c @@ -210,7 +210,7 @@ static int rxrpc_preparse_xdr_yfs_rxgk(struct key_preparsed_payload *prep, if (!token) goto nomem; - token->rxgk = kzalloc(struct_size_t(struct rxgk_key, _key, raw_keylen), GFP_KERNEL); + token->rxgk = kzalloc_flex(struct rxgk_key, _key, raw_keylen); if (!token->rxgk) goto nomem_token; diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c index fdbfcaa3e2ab..5d228a402204 100644 --- a/net/sched/act_gate.c +++ b/net/sched/act_gate.c @@ -240,7 +240,7 @@ static int tcf_gate_copy_entries(struct tcf_gate_params *dst, list_for_each_entry(entry, &src->entries, list) { struct tcfg_gate_entry *new; - new = kzalloc(sizeof(*new), GFP_ATOMIC); + new = kzalloc_obj(*new, GFP_ATOMIC); if (!new) { NL_SET_ERR_MSG(extack, "Not enough memory for entry"); return -ENOMEM; @@ -415,7 +415,7 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, if (err < 0) goto release_idr; - p = kzalloc(sizeof(*p), GFP_KERNEL); + p = kzalloc_obj(*p); if (!p) { err = -ENOMEM; goto chain_put; diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index ff401ace4f3d..503834853306 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -526,7 +526,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, } t = to_tunnel_key(*a); - params_new = kzalloc(sizeof(*params_new), GFP_KERNEL); + params_new = kzalloc_obj(*params_new); if (unlikely(!params_new)) { NL_SET_ERR_MSG(extack, "Cannot allocate tunnel key parameters"); ret = -ENOMEM; diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index cf461ebcdde5..09a7c97e87da 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -282,9 +282,8 @@ int gss_krb5_mic_build_sg(const struct xdr_buf *body, unsigned int overflow_nents = nsg - XDR_BUF_TO_SG_NENTS + 1; - *sg_overflow = kmalloc_array(overflow_nents, - sizeof(**sg_overflow), - GFP_NOFS); + *sg_overflow = kmalloc_objs(**sg_overflow, overflow_nents, + GFP_NOFS); if (!*sg_overflow) return -ENOMEM; diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index aebd97e7f66c..31a1bc60a5f6 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -625,7 +625,7 @@ int sunrpc_nl_unix_gid_get_reqs_dumpit(struct sk_buff *skb, if (!cnt) return 0; - items = kcalloc(cnt, sizeof(*items), GFP_KERNEL); + items = kzalloc_objs(*items, cnt); seqnos = kcalloc(cnt, sizeof(*seqnos), GFP_KERNEL); if (!items || !seqnos) { ret = -ENOMEM; @@ -1326,7 +1326,7 @@ int sunrpc_nl_ip_map_get_reqs_dumpit(struct sk_buff *skb, if (!cnt) return 0; - items = kcalloc(cnt, sizeof(*items), GFP_KERNEL); + items = kzalloc_objs(*items, cnt); seqnos = kcalloc(cnt, sizeof(*seqnos), GFP_KERNEL); if (!items || !seqnos) { ret = -ENOMEM; diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index cb2ef428651f..c42fd338c607 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -371,8 +371,7 @@ int xdr_buf_to_sg_alloc(const struct xdr_buf *buf, unsigned int offset, unsigned int overflow_nents = nsg - sg_head_nents + 1; struct scatterlist *overflow; - overflow = kmalloc_array(overflow_nents, sizeof(*overflow), - gfp); + overflow = kmalloc_objs(*overflow, overflow_nents, gfp); if (!overflow) return -ENOMEM; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 13f9926bf205..79c3921c583c 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -3667,8 +3667,8 @@ static int bpf_iter_unix_realloc_batch(struct bpf_unix_iter_state *iter, { struct sock **new_batch; - new_batch = kvmalloc_array(new_batch_sz, sizeof(*new_batch), - GFP_USER | __GFP_NOWARN); + new_batch = kvmalloc_objs(*new_batch, new_batch_sz, + GFP_USER | __GFP_NOWARN); if (!new_batch) return -ENOMEM; diff --git a/net/wireless/core.c b/net/wireless/core.c index d13310fef691..3032993ba5dc 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -311,9 +311,8 @@ int cfg80211_nan_set_local_schedule(struct cfg80211_registered_device *rdev, if (!sched->n_channels) return 0; - wdev->u.nan.chandefs = kcalloc(sched->n_channels, - sizeof(*wdev->u.nan.chandefs), - GFP_KERNEL); + wdev->u.nan.chandefs = kzalloc_objs(*wdev->u.nan.chandefs, + sched->n_channels); if (!wdev->u.nan.chandefs) return -ENOMEM; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 44f2bad08670..899b6374c550 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -17330,8 +17330,7 @@ static int nl80211_parse_nan_channel(struct cfg80211_registered_device *rdev, u8 n_rx_nss; int ret; - channel_parsed = kcalloc(NL80211_ATTR_MAX + 1, sizeof(*channel_parsed), - GFP_KERNEL); + channel_parsed = kzalloc_objs(*channel_parsed, NL80211_ATTR_MAX + 1); if (!channel_parsed) return -ENOMEM; @@ -17554,8 +17553,7 @@ static int nl80211_nan_set_peer_sched(struct sk_buff *skb, } if (n_channels) { - nan_channels = kcalloc(n_channels, sizeof(*nan_channels), - GFP_KERNEL); + nan_channels = kzalloc_objs(*nan_channels, n_channels); if (!nan_channels) return -ENOMEM; } @@ -17693,8 +17691,7 @@ static int nl80211_nan_set_local_sched(struct sk_buff *skb, info->nlhdr, GENL_HDRLEN, rem) n_channels++; - sched = kzalloc(struct_size(sched, nan_channels, n_channels), - GFP_KERNEL); + sched = kzalloc_flex(*sched, nan_channels, n_channels); if (!sched) return -ENOMEM; diff --git a/security/integrity/ima/ima_queue.c b/security/integrity/ima/ima_queue.c index f89f0ca3d4ed..0f1b7e4113c4 100644 --- a/security/integrity/ima/ima_queue.c +++ b/security/integrity/ima/ima_queue.c @@ -75,8 +75,7 @@ static struct hlist_head *ima_alloc_replace_htable(void) struct hlist_head *old_htable, *new_htable; /* Initializing to zeros is equivalent to call HLIST_HEAD_INIT. */ - new_htable = kcalloc(IMA_MEASURE_HTABLE_SIZE, sizeof(struct hlist_head), - GFP_KERNEL); + new_htable = kzalloc_objs(struct hlist_head, IMA_MEASURE_HTABLE_SIZE); if (!new_htable) return ERR_PTR(-ENOMEM); diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c index 23d62fede06e..7c397b1c9231 100644 --- a/sound/core/compress_offload.c +++ b/sound/core/compress_offload.c @@ -107,7 +107,7 @@ static int snd_compr_open(struct inode *inode, struct file *f) return -EINVAL; } - data = kzalloc(sizeof(*data), GFP_KERNEL); + data = kzalloc_obj(*data); if (!data) { snd_card_unref(compr->card); return -ENOMEM; @@ -119,7 +119,7 @@ static int snd_compr_open(struct inode *inode, struct file *f) data->stream.direction = dirn; data->stream.private_data = compr->private_data; data->stream.device = compr; - runtime = kzalloc(sizeof(*runtime), GFP_KERNEL); + runtime = kzalloc_obj(*runtime); if (!runtime) { kfree(data); snd_card_unref(compr->card); diff --git a/sound/core/control.c b/sound/core/control.c index 78ce7bc936d2..4199342d4ffe 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -69,7 +69,7 @@ static int snd_ctl_open(struct inode *inode, struct file *file) err = -ENODEV; goto __error2; } - ctl = kzalloc(sizeof(*ctl), GFP_KERNEL); + ctl = kzalloc_obj(*ctl); if (ctl == NULL) { err = -ENOMEM; goto __error; @@ -174,7 +174,7 @@ void snd_ctl_notify(struct snd_card *card, unsigned int mask, goto _found; } } - ev = kzalloc(sizeof(*ev), GFP_ATOMIC); + ev = kzalloc_obj(*ev, GFP_ATOMIC); if (ev) { ev->id = *id; ev->mask = mask; @@ -871,7 +871,7 @@ static int snd_ctl_card_info(struct snd_card *card, struct snd_ctl_file * ctl, unsigned int cmd, void __user *arg) { struct snd_ctl_card_info *info __free(kfree) = - kzalloc(sizeof(*info), GFP_KERNEL); + kzalloc_obj(*info); ssize_t n; if (! info) diff --git a/sound/core/control_led.c b/sound/core/control_led.c index 3d13bbec1c54..ec0e6c7ad657 100644 --- a/sound/core/control_led.c +++ b/sound/core/control_led.c @@ -158,7 +158,7 @@ static void snd_ctl_led_set_state(struct snd_card *card, unsigned int access, UPDATE_ROUTE(route, snd_ctl_led_get(lctl)); } if (!found && kctl && card) { - lctl = kzalloc(sizeof(*lctl), GFP_KERNEL); + lctl = kzalloc_obj(*lctl); if (lctl) { lctl->card = card; lctl->access = access; diff --git a/sound/core/init.c b/sound/core/init.c index 2f7f83a7611b..9693e646b3bb 100644 --- a/sound/core/init.c +++ b/sound/core/init.c @@ -364,7 +364,7 @@ static int snd_card_init(struct snd_card *card, struct device *parent, sound_debugfs_root); #endif #ifdef CONFIG_SND_CTL_DEBUG - card->value_buf = kmalloc(sizeof(*card->value_buf), GFP_KERNEL); + card->value_buf = kmalloc_obj(*card->value_buf); if (!card->value_buf) return -ENOMEM; #endif diff --git a/sound/core/misc.c b/sound/core/misc.c index 4772b2a3b808..066fb9ecdcdc 100644 --- a/sound/core/misc.c +++ b/sound/core/misc.c @@ -125,7 +125,7 @@ int snd_fasync_helper(int fd, struct file *file, int on, struct snd_fasync *fasync = NULL; if (on) { - fasync = kzalloc(sizeof(*fasync), GFP_KERNEL); + fasync = kzalloc_obj(*fasync); if (!fasync) return -ENOMEM; INIT_LIST_HEAD(&fasync->list); diff --git a/sound/core/oss/mixer_oss.c b/sound/core/oss/mixer_oss.c index ff9d7fd60a7e..c533d767c29a 100644 --- a/sound/core/oss/mixer_oss.c +++ b/sound/core/oss/mixer_oss.c @@ -890,7 +890,7 @@ static int snd_mixer_oss_build_test(struct snd_mixer_oss *mixer, struct slot *sl int err; struct snd_ctl_elem_info *info __free(kfree) = - kmalloc(sizeof(*info), GFP_KERNEL); + kmalloc_obj(*info); if (!info) return -ENOMEM; scoped_guard(rwsem_read, &card->controls_rwsem) { diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 62324282fcae..6d32c12fb79b 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -2330,7 +2330,7 @@ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd) return -EINVAL; struct snd_pcm_group *group __free(kfree) = - kzalloc(sizeof(*group), GFP_KERNEL); + kzalloc_obj(*group); if (!group) return -ENOMEM; snd_pcm_group_init(group); diff --git a/sound/core/seq/oss/seq_oss_synth.c b/sound/core/seq/oss/seq_oss_synth.c index c4b82e29ab05..21a0a98c8e92 100644 --- a/sound/core/seq/oss/seq_oss_synth.c +++ b/sound/core/seq/oss/seq_oss_synth.c @@ -86,7 +86,7 @@ snd_seq_oss_synth_probe(struct snd_seq_device *dev) struct seq_oss_synth *rec; struct snd_seq_oss_reg *reg = SNDRV_SEQ_DEVICE_ARGPTR(dev); - rec = kzalloc(sizeof(*rec), GFP_KERNEL); + rec = kzalloc_obj(*rec); if (!rec) return -ENOMEM; rec->seq_device = -1; diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 5b86e75c2658..239809ce48d7 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -210,7 +210,7 @@ static struct snd_seq_client *seq_create_client1(int client_index, int poolsize) struct snd_seq_client *client; /* init client data */ - client = kzalloc(sizeof(*client), GFP_KERNEL); + client = kzalloc_obj(*client); if (client == NULL) return NULL; client->pool = snd_seq_pool_new(poolsize); diff --git a/sound/core/seq/seq_virmidi.c b/sound/core/seq/seq_virmidi.c index 6208bf7f57bf..a01785a6de9b 100644 --- a/sound/core/seq/seq_virmidi.c +++ b/sound/core/seq/seq_virmidi.c @@ -188,7 +188,7 @@ static int snd_virmidi_input_open(struct snd_rawmidi_substream *substream) struct snd_rawmidi_runtime *runtime = substream->runtime; struct snd_virmidi *vmidi; - vmidi = kzalloc(sizeof(*vmidi), GFP_KERNEL); + vmidi = kzalloc_obj(*vmidi); if (vmidi == NULL) return -ENOMEM; vmidi->substream = substream; diff --git a/sound/core/timer.c b/sound/core/timer.c index f666f05e9d45..679b26435670 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -1855,7 +1855,7 @@ static int snd_timer_user_info(struct file *file, return -EBADFD; struct snd_timer_info *info __free(kfree) = - kzalloc(sizeof(*info), GFP_KERNEL); + kzalloc_obj(*info); if (! info) return -ENOMEM; info->card = t->card ? t->card->number : -1; diff --git a/sound/drivers/aloop.c b/sound/drivers/aloop.c index 4e3ea23ca913..81cb1f59f703 100644 --- a/sound/drivers/aloop.c +++ b/sound/drivers/aloop.c @@ -1365,7 +1365,7 @@ static int loopback_open(struct snd_pcm_substream *substream) int dev = get_cable_index(substream); guard(mutex)(&loopback->cable_lock); - dpcm = kzalloc(sizeof(*dpcm), GFP_KERNEL); + dpcm = kzalloc_obj(*dpcm); if (!dpcm) return -ENOMEM; dpcm->loopback = loopback; @@ -1373,7 +1373,7 @@ static int loopback_open(struct snd_pcm_substream *substream) cable = loopback->cables[substream->number][dev]; if (!cable) { - cable = kzalloc(sizeof(*cable), GFP_KERNEL); + cable = kzalloc_obj(*cable); if (!cable) { err = -ENOMEM; goto unlock; diff --git a/sound/isa/gus/gus_dma.c b/sound/isa/gus/gus_dma.c index 30bd76eee96e..7be6ff201ecb 100644 --- a/sound/isa/gus/gus_dma.c +++ b/sound/isa/gus/gus_dma.c @@ -214,7 +214,7 @@ int snd_gf1_dma_transfer_block(struct snd_gus_card * gus, struct snd_gf1_dma_block *block; struct snd_gf1_dma_block *free_block = NULL; - block = kmalloc(sizeof(*block), atomic ? GFP_ATOMIC : GFP_KERNEL); + block = kmalloc_obj(*block, atomic ? GFP_ATOMIC : GFP_KERNEL); if (!block) return -ENOMEM; diff --git a/sound/pci/cs46xx/cs46xx_lib.c b/sound/pci/cs46xx/cs46xx_lib.c index 19a6927c079d..f6db08b75649 100644 --- a/sound/pci/cs46xx/cs46xx_lib.c +++ b/sound/pci/cs46xx/cs46xx_lib.c @@ -1444,7 +1444,7 @@ static int _cs46xx_playback_open_channel (struct snd_pcm_substream *substream,in struct snd_cs46xx_pcm * cpcm; struct snd_pcm_runtime *runtime = substream->runtime; - cpcm = kzalloc(sizeof(*cpcm), GFP_KERNEL); + cpcm = kzalloc_obj(*cpcm); if (cpcm == NULL) return -ENOMEM; if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, &chip->pci->dev, diff --git a/sound/pci/ctxfi/ctamixer.c b/sound/pci/ctxfi/ctamixer.c index 5fc1c922620a..f356917cb6ac 100644 --- a/sound/pci/ctxfi/ctamixer.c +++ b/sound/pci/ctxfi/ctamixer.c @@ -236,7 +236,7 @@ static int get_amixer_rsc(struct amixer_mgr *mgr, *ramixer = NULL; /* Allocate mem for amixer resource */ - amixer = kzalloc(sizeof(*amixer), GFP_KERNEL); + amixer = kzalloc_obj(*amixer); if (!amixer) return -ENOMEM; @@ -390,7 +390,7 @@ static int get_sum_rsc(struct sum_mgr *mgr, *rsum = NULL; /* Allocate mem for sum resource */ - sum = kzalloc(sizeof(*sum), GFP_KERNEL); + sum = kzalloc_obj(*sum); if (!sum) return -ENOMEM; diff --git a/sound/pci/ctxfi/ctdaio.c b/sound/pci/ctxfi/ctdaio.c index 69aacd06716c..9be70c6862ab 100644 --- a/sound/pci/ctxfi/ctdaio.c +++ b/sound/pci/ctxfi/ctdaio.c @@ -540,7 +540,7 @@ static int get_daio_rsc(struct daio_mgr *mgr, err = -ENOMEM; /* Allocate mem for daio resource */ if (desc->output) { - struct dao *dao = kzalloc(sizeof(*dao), GFP_KERNEL); + struct dao *dao = kzalloc_obj(*dao); if (!dao) goto error; @@ -552,7 +552,7 @@ static int get_daio_rsc(struct daio_mgr *mgr, *rdaio = &dao->daio; } else { - struct dai *dai = kzalloc(sizeof(*dai), GFP_KERNEL); + struct dai *dai = kzalloc_obj(*dai); if (!dai) goto error; diff --git a/sound/pci/ctxfi/ctsrc.c b/sound/pci/ctxfi/ctsrc.c index 46dc1f509234..1fadaf22309f 100644 --- a/sound/pci/ctxfi/ctsrc.c +++ b/sound/pci/ctxfi/ctsrc.c @@ -432,9 +432,9 @@ get_src_rsc(struct src_mgr *mgr, const struct src_desc *desc, struct src **rsrc) /* Allocate mem for master src resource */ if (MEMRD == desc->mode) - src = kcalloc(desc->multi, sizeof(*src), GFP_KERNEL); + src = kzalloc_objs(*src, desc->multi); else - src = kzalloc(sizeof(*src), GFP_KERNEL); + src = kzalloc_obj(*src); if (!src) { err = -ENOMEM; diff --git a/sound/pci/ctxfi/cttimer.c b/sound/pci/ctxfi/cttimer.c index cc379d880cad..9d6f5df2bc7e 100644 --- a/sound/pci/ctxfi/cttimer.c +++ b/sound/pci/ctxfi/cttimer.c @@ -318,7 +318,7 @@ ct_timer_instance_new(struct ct_timer *atimer, struct ct_atc_pcm *apcm) { struct ct_timer_instance *ti; - ti = kzalloc(sizeof(*ti), GFP_KERNEL); + ti = kzalloc_obj(*ti); if (!ti) return NULL; spin_lock_init(&ti->lock); diff --git a/sound/pci/emu10k1/emufx.c b/sound/pci/emu10k1/emufx.c index 49cabb2eb2b7..a33817aba17f 100644 --- a/sound/pci/emu10k1/emufx.c +++ b/sound/pci/emu10k1/emufx.c @@ -2470,7 +2470,7 @@ static int snd_emu10k1_fx8010_ioctl(struct snd_hwdep * hw, struct file *file, un emu->support_tlv = 1; return put_user(SNDRV_EMU10K1_VERSION, (int __user *)argp); case SNDRV_EMU10K1_IOCTL_INFO: - info = kzalloc(sizeof(*info), GFP_KERNEL); + info = kzalloc_obj(*info, GFP_KERNEL); if (!info) return -ENOMEM; snd_emu10k1_fx8010_info(emu, info); diff --git a/sound/soc/codecs/simple-amplifier.c b/sound/soc/codecs/simple-amplifier.c index ca53b08c0b33..07c040355c37 100644 --- a/sound/soc/codecs/simple-amplifier.c +++ b/sound/soc/codecs/simple-amplifier.c @@ -371,7 +371,7 @@ static unsigned int *simple_amp_alloc_tlv_ranges(const struct simple_amp_ranges unsigned int *t; unsigned int i; - tlv = kzalloc_objs(*tlv, 2 + ranges->nb_ranges * 6, GFP_KERNEL); + tlv = kzalloc_objs(*tlv, 2 + ranges->nb_ranges * 6); if (!tlv) return NULL; diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c index 42019daa5e04..5f3423129b13 100644 --- a/sound/soc/generic/simple-card-utils.c +++ b/sound/soc/generic/simple-card-utils.c @@ -168,7 +168,7 @@ int simple_util_parse_tdm_width_map(struct simple_util_priv *priv, struct device if (!dai->tdm_width_map) return simple_ret(priv, ret); /* see NOTE */ - u32 *array_values __free(kfree) = kcalloc(n, sizeof(*array_values), GFP_KERNEL); + u32 *array_values __free(kfree) = kzalloc_objs(*array_values, n); if (!array_values) goto end; diff --git a/sound/soc/meson/gx-formatter.c b/sound/soc/meson/gx-formatter.c index 311e63affb23..2d3218cce426 100644 --- a/sound/soc/meson/gx-formatter.c +++ b/sound/soc/meson/gx-formatter.c @@ -253,7 +253,7 @@ struct gx_stream *gx_stream_alloc(struct gx_iface *iface) { struct gx_stream *ts; - ts = kzalloc(sizeof(*ts), GFP_KERNEL); + ts = kzalloc_obj(*ts); if (ts) { INIT_LIST_HEAD(&ts->formatter_list); mutex_init(&ts->lock); diff --git a/sound/soc/qcom/qdsp6/q6afe.c b/sound/soc/qcom/qdsp6/q6afe.c index 1d68a80e8e0c..f0ff1350e9dd 100644 --- a/sound/soc/qcom/qdsp6/q6afe.c +++ b/sound/soc/qcom/qdsp6/q6afe.c @@ -1857,7 +1857,7 @@ struct q6afe_port *q6afe_port_get_from_id(struct device *dev, int id) return ERR_PTR(-EINVAL); } - port = kzalloc(sizeof(*port), GFP_KERNEL); + port = kzalloc_obj(*port, GFP_KERNEL); if (!port) return ERR_PTR(-ENOMEM); diff --git a/sound/soc/sdca/sdca_functions.c b/sound/soc/sdca/sdca_functions.c index e01d91eb3cc8..32d9b7f30a4f 100644 --- a/sound/soc/sdca/sdca_functions.c +++ b/sound/soc/sdca/sdca_functions.c @@ -1249,8 +1249,7 @@ static int find_sdca_entity_pde(struct device *dev, return -EINVAL; } - u32 *delay_list __free(kfree) = kcalloc(num_delays, sizeof(*delay_list), - GFP_KERNEL); + u32 *delay_list __free(kfree) = kzalloc_objs(*delay_list, num_delays); if (!delay_list) return -ENOMEM; @@ -1313,8 +1312,8 @@ static int find_sdca_entity_ge(struct device *dev, return -EINVAL; } - u8 *affected_list __free(kfree) = kcalloc(num_affected, sizeof(*affected_list), - GFP_KERNEL); + u8 *affected_list __free(kfree) = kzalloc_objs(*affected_list, + num_affected); if (!affected_list) return -ENOMEM; @@ -1552,8 +1551,8 @@ static int find_sdca_entities(struct device *dev, struct fwnode_handle *function if (!entities) return -ENOMEM; - u32 *entity_list __free(kfree) = kcalloc(num_entities, sizeof(*entity_list), - GFP_KERNEL); + u32 *entity_list __free(kfree) = kzalloc_objs(*entity_list, + num_entities); if (!entity_list) return -ENOMEM; @@ -1715,8 +1714,8 @@ static int find_sdca_entity_connection_pde(struct device *dev, if (!managed) return -ENOMEM; - u32 *managed_list __free(kfree) = kcalloc(num_managed, sizeof(*managed_list), - GFP_KERNEL); + u32 *managed_list __free(kfree) = kzalloc_objs(*managed_list, + num_managed); if (!managed_list) return -ENOMEM; @@ -2033,8 +2032,8 @@ static int find_sdca_clusters(struct device *dev, if (!clusters) return -ENOMEM; - u32 *cluster_list __free(kfree) = kcalloc(num_clusters, sizeof(*cluster_list), - GFP_KERNEL); + u32 *cluster_list __free(kfree) = kzalloc_objs(*cluster_list, + num_clusters); if (!cluster_list) return -ENOMEM; diff --git a/sound/soc/sof/sof-client-probes-ipc4.c b/sound/soc/sof/sof-client-probes-ipc4.c index 2eef32b55395..c547ea61fb3d 100644 --- a/sound/soc/sof/sof-client-probes-ipc4.c +++ b/sound/soc/sof/sof-client-probes-ipc4.c @@ -260,7 +260,7 @@ static int ipc4_probes_points_info(struct sof_client_dev *cdev, *num_desc = info->num_elems; dev_dbg(dev, "%s: got %zu probe points", __func__, *num_desc); - *desc = kcalloc(*num_desc, sizeof(**desc), GFP_KERNEL); + *desc = kzalloc_objs(**desc, *num_desc); if (!*desc) { kfree(msg.data_ptr); return -ENOMEM; diff --git a/sound/soc/sof/sof-client.c b/sound/soc/sof/sof-client.c index c7bbf09e547f..64da8df15bf2 100644 --- a/sound/soc/sof/sof-client.c +++ b/sound/soc/sof/sof-client.c @@ -230,7 +230,7 @@ int sof_client_dev_register(struct snd_sof_dev *sdev, const char *name, u32 id, struct sof_client_dev *cdev; int ret; - centry = kzalloc(sizeof(*centry), GFP_KERNEL); + centry = kzalloc_obj(*centry); if (!centry) return -ENOMEM; diff --git a/sound/sparc/amd7930.c b/sound/sparc/amd7930.c index da04ed5cbac4..d746b2586d88 100644 --- a/sound/sparc/amd7930.c +++ b/sound/sparc/amd7930.c @@ -903,7 +903,7 @@ static int snd_amd7930_create(struct snd_card *card, int err; *ramd = NULL; - amd = kzalloc(sizeof(*amd), GFP_KERNEL); + amd = kzalloc_obj(*amd); if (amd == NULL) return -ENOMEM; From d96171d911e3b89ca2957c04264019cf2f96287b Mon Sep 17 00:00:00 2001 From: Shivaprasad G Bhat Date: Wed, 19 Aug 2026 17:58:22 +0000 Subject: [PATCH 0728/1198] powerpc: pci-ioda: Fix the stale irq chip reference The commit f0ac60e6e311 ("powerpc/powernv/pci: Switch to use msi_create_parent_irq_domain()") removed the legacy MSI irq chip pnv_pci_msi_irq_chip but left behind the static definition of it and its reference in is_pnv_opal_msi(). The KVM IRQ bypass for vfio devices is broken because the comparision in is_pnv_opal_msi() fails on the comparision with stale unused variable showing the below errors in dmesg. kvmppc_set_passthru_irq_hv: Could not assign IRQ map for (X,Y) kvmppc_set_passthru_irq (irq X, gsi Y) fails: -2 vfio-pci A:B:C.D irq bypass producer (eventfd Z) registration fails: -2 The patch removes the stale variable definition and fixes the is_pnv_opal_msi() by comparing against the chip name prefix. Fixes: f0ac60e6e311 ("powerpc/powernv/pci: Switch to use msi_create_parent_irq_domain()") Cc: stable@kernel.org Signed-off-by: Shivaprasad G Bhat Tested-by: Gautam Menghani Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/178716225364.1437.6201568081502251835.stgit@linux.ibm.com --- arch/powerpc/platforms/powernv/pci-ioda.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 32ecbc46e74b..728a5610d167 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -1623,15 +1623,13 @@ int64_t pnv_opal_pci_msi_eoi(struct irq_data *d) return opal_pci_msi_eoi(phb->opal_id, d->parent_data->hwirq); } -static struct irq_chip pnv_pci_msi_irq_chip; - /* * Returns true iff chip is something that we could call * pnv_opal_pci_msi_eoi for. */ bool is_pnv_opal_msi(struct irq_chip *chip) { - return chip == &pnv_pci_msi_irq_chip; + return chip && chip->name && str_has_prefix(chip->name, "PNV-"); } EXPORT_SYMBOL_GPL(is_pnv_opal_msi); @@ -1728,7 +1726,7 @@ static const struct msi_parent_ops pnv_msi_parent_ops = { .chip_flags = MSI_CHIP_FLAG_SET_EOI, .bus_select_token = DOMAIN_BUS_NEXUS, .bus_select_mask = MATCH_PCI_MSI, - .prefix = "PNV-", + .prefix = "PNV-", /* Note: is_pnv_opal_msi() uses this */ .init_dev_msi_info = pnv_init_dev_msi_info, }; From c5e68706527968282e49de205cc2b935823cb88a Mon Sep 17 00:00:00 2001 From: Shivaprasad G Bhat Date: Tue, 14 Jul 2026 17:16:23 +0000 Subject: [PATCH 0729/1198] powerpc/eeh: Fix recursive locking on devices without EEH sensitive driver The commit 1010b4c012b0 ("powerpc/eeh: Make EEH driver device hotplug safe") refactored the EEH code such that the pci_rescan_remove_lock is held at the beginning of eeh_handle_normal_event() and the eeh_reset_device() is called with that lock being held. Looks like the commit missed to remove the existing lock/unlock inside eeh_rmv_device() which is no longer necessary. This is causing the eehd to hang on the lock which it actually holds when that code path is taken. [<0>] 0xc00000011c78f870 [<0>] __switch_to+0xfc/0x1a0 [<0>] pci_lock_rescan_remove+0x30/0x44 [<0>] eeh_rmv_device+0x290/0x2e0 [<0>] eeh_pe_dev_traverse+0x80/0x130 [<0>] eeh_reset_device+0xcc/0x23c [<0>] eeh_handle_normal_event+0x830/0xa80 [<0>] eeh_event_handler+0xf8/0x190 [<0>] kthread+0x194/0x1b0 [<0>] start_kernel_thread+0x14/0x18 The issue is seen for cases where the errors are detected on the PHB directly AND|OR for devices where the driver error_detected() returns PCI_ERS_RESULT_NEED_RESET, and driver being not EEH sensitive(i.e no error handlers like slot_reset(), resume() etc defined). Fixes: 1010b4c012b0 ("powerpc/eeh: Make EEH driver device hotplug safe") Cc: stable Reviewed-by: Ritesh Harjani (IBM) Signed-off-by: Shivaprasad G Bhat Reviewed-by: Amit Machhiwal Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/178404937381.913.2759874335293830160.stgit@linux.ibm.com --- arch/powerpc/kernel/eeh_driver.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 028f69158532..d64cce17a4e0 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -533,9 +533,7 @@ static void eeh_rmv_device(struct eeh_dev *edev, void *userdata) if (rmv_data) list_add(&edev->rmv_entry, &rmv_data->removed_vf_list); } else { - pci_lock_rescan_remove(); pci_stop_and_remove_bus_device(dev); - pci_unlock_rescan_remove(); } } From 8a4978c17a144a6583478cce933bcb2dbb25298d Mon Sep 17 00:00:00 2001 From: Shivaprasad G Bhat Date: Fri, 26 Jun 2026 09:13:03 +0000 Subject: [PATCH 0730/1198] powerpc/rtas_pci: No hotplug on permanently removed device on pSeries The eeh_driver disables and offlines the PE permanently when it exceeds the freeze count beyond eeh_max_freeze within the last hour. The PE is only offline, so the device tree entries, eeh device references are all intact till the real unplug of the device from the guest/host takes place. On pSeries, with a new hotplug of any PCI device, the drmgr initiates a system-wide PCI rescan, which finds devices offlined by the eeh_driver and there will be attempts to bring them online. This leads to recurring EEHs either at the config read time itself or a bit later depending on the type of the problem. For PowerNV, the commit d2b0f6f77ee5 ("powerpc/eeh: No hotplug on permanently removed dev") introduced the EEH_DEV_REMOVED flag to prevent such inadvertent rescans on hierarchical toplogies relavent in Baremetal setups. For pSeries, such topologies don't really make sense as the devices are either part of the same PE OR exposed as independent devices on multiple virtual PHBs. However, the inadvertent rescans are still a possibility with either hotplug of a new device or otherwise with manual system-wide pci bus rescan attempts. So the patch checks for EEH_DEV_REMOVED before allowing config space access just like PowerNV, making the PCI core omit the PE, and thus preventing subsequent EEH recurances. The patch is tested on PowerVM and KVM machines with single and multi-function devices, and on the devices behind a switch. The unplug of the affected devices post EEH removal is also working fine as expected. Signed-off-by: Shivaprasad G Bhat Reported-by: Tasmiya Nalatwad Tested-by: Tasmiya Nalatwad Reviewed-by: Harsh Prateek Bora References: d2b0f6f77ee5 ("powerpc/eeh: No hotplug on permanently removed dev") Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/178246517230.1267.12206176311111155505.stgit@linux.ibm.com --- arch/powerpc/kernel/rtas_pci.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c index fccf96e897f6..206c825225c2 100644 --- a/arch/powerpc/kernel/rtas_pci.c +++ b/arch/powerpc/kernel/rtas_pci.c @@ -54,6 +54,10 @@ int rtas_pci_dn_read_config(struct pci_dn *pdn, int where, int size, u32 *val) if (!config_access_valid(pdn, where)) return PCIBIOS_BAD_REGISTER_NUMBER; #ifdef CONFIG_EEH + if (pdn->edev && + (pdn->edev->mode & EEH_DEV_REMOVED)) + return PCIBIOS_DEVICE_NOT_FOUND; + if (pdn->edev && pdn->edev->pe && (pdn->edev->pe->state & EEH_PE_CFG_BLOCKED)) return PCIBIOS_SET_FAILED; @@ -105,6 +109,10 @@ int rtas_pci_dn_write_config(struct pci_dn *pdn, int where, int size, u32 val) if (!config_access_valid(pdn, where)) return PCIBIOS_BAD_REGISTER_NUMBER; #ifdef CONFIG_EEH + if (pdn->edev && + (pdn->edev->mode & EEH_DEV_REMOVED)) + return PCIBIOS_DEVICE_NOT_FOUND; + if (pdn->edev && pdn->edev->pe && (pdn->edev->pe->state & EEH_PE_CFG_BLOCKED)) return PCIBIOS_SET_FAILED; From c6755be4838d6ccd641effbcdc3d917b82631ff9 Mon Sep 17 00:00:00 2001 From: Thorsten Blum Date: Sun, 9 Aug 2026 18:24:01 +0200 Subject: [PATCH 0731/1198] powerpc/kexec_file: Use inclusive range checks in add_usable_mem() add_usable_mem() adds usable memory ranges for the kdump kernel. The ranges are inclusive, but the partial overlap check uses exclusive comparisons. This skips ranges with base == loc_end or end == loc_base. Use inclusive comparisons instead. Fixes: 7c64e21a1c5a ("powerpc/kexec_file: Restrict memory usage of kdump kernel") Signed-off-by: Thorsten Blum Reviewed-by: Sourabh Jain Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260809162403.18142-2-thorsten.blum@linux.dev --- arch/powerpc/kexec/file_load_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c index 6075b1c88511..c2ed0d1c92e7 100644 --- a/arch/powerpc/kexec/file_load_64.c +++ b/arch/powerpc/kexec/file_load_64.c @@ -113,7 +113,7 @@ static int add_usable_mem(struct umem_info *um_info, u64 base, u64 end) loc_end = um_info->ranges[i].end; if (loc_base >= base && loc_end <= end) add = true; - else if (base < loc_end && end > loc_base) { + else if (base <= loc_end && end >= loc_base) { if (loc_base < base) loc_base = base; if (loc_end > end) From 68832eb08751b4ce23e90bd90e9414a465a99da3 Mon Sep 17 00:00:00 2001 From: Thorsten Blum Date: Thu, 30 Jul 2026 15:19:40 +0200 Subject: [PATCH 0732/1198] powerpc/kexec: Simplify kdump_extra_elfcorehdr_size() Return the size directly and drop the extra_sz variable to simplify kdump_extra_elfcorehdr_size(). The two warning paths now fall through to the existing return 0 at the end of the function. Signed-off-by: Thorsten Blum Reviewed-by: Christophe Leroy (CS GROUP) Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260730131940.597739-2-thorsten.blum@linux.dev --- arch/powerpc/kexec/file_load_64.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c index c2ed0d1c92e7..4a499a69e2d8 100644 --- a/arch/powerpc/kexec/file_load_64.c +++ b/arch/powerpc/kexec/file_load_64.c @@ -377,16 +377,12 @@ static int load_backup_segment(struct kimage *image, struct kexec_buf *kbuf) static unsigned int kdump_extra_elfcorehdr_size(struct crash_mem *cmem) { #if defined(CONFIG_CRASH_HOTPLUG) && defined(CONFIG_MEMORY_HOTPLUG) - unsigned int extra_sz = 0; - if (CONFIG_CRASH_MAX_MEMORY_RANGES > (unsigned int)PN_XNUM) pr_warn("Number of Phdrs %u exceeds max\n", CONFIG_CRASH_MAX_MEMORY_RANGES); else if (cmem->nr_ranges >= CONFIG_CRASH_MAX_MEMORY_RANGES) pr_warn("Configured crash mem ranges may not be enough\n"); else - extra_sz = (CONFIG_CRASH_MAX_MEMORY_RANGES - cmem->nr_ranges) * sizeof(Elf64_Phdr); - - return extra_sz; + return (CONFIG_CRASH_MAX_MEMORY_RANGES - cmem->nr_ranges) * sizeof(Elf64_Phdr); #endif return 0; } From 449f60f99f8f3cbe80a9bd2242945e827c5ed003 Mon Sep 17 00:00:00 2001 From: Thorsten Blum Date: Mon, 10 Aug 2026 16:58:27 +0200 Subject: [PATCH 0733/1198] powerpc/kexec_file: Use inclusive range checks for excluded memory arch_check_excluded_range() checks if a kexec segment overlaps an excluded memory range. Both ranges use inclusive end addresses, but the overlap check uses exclusive comparisons. This skips ranges with start == ->ranges[i].end or end == ->ranges[i].start. Use inclusive comparisons instead. Fixes: 6e5250eaa665 ("powerpc/crash: use generic APIs to locate memory hole for kdump") Signed-off-by: Thorsten Blum Reviewed-by: Sourabh Jain Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260810145827.157972-3-thorsten.blum@linux.dev --- arch/powerpc/kexec/file_load_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c index 4a499a69e2d8..bd80c5fb1b1f 100644 --- a/arch/powerpc/kexec/file_load_64.c +++ b/arch/powerpc/kexec/file_load_64.c @@ -57,7 +57,7 @@ int arch_check_excluded_range(struct kimage *image, unsigned long start, emem = image->arch.exclude_ranges; for (i = 0; i < emem->nr_ranges; i++) - if (start < emem->ranges[i].end && end > emem->ranges[i].start) + if (start <= emem->ranges[i].end && end >= emem->ranges[i].start) return 1; return 0; From b1824233b19c1dffdb5e81283805a9e52e763caa Mon Sep 17 00:00:00 2001 From: Jiangshan Yi Date: Thu, 13 Aug 2026 14:37:31 +0800 Subject: [PATCH 0734/1198] powerpc/pseries/pci: Fix misleading VF limit error message When the number of requested VFs exceeds MAX_VFS_FOR_MAP_PE, the message prints that limit but labels it "Configurable VFs". Report the configurable VF limit and the PE mapping limit with separate error messages. Suggested-by: Christophe Leroy Signed-off-by: Jiangshan Yi Reviewed-by: Christophe Leroy [Maddy: Fixed Christophe's reviewed by tag] Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260813063731.399598-1-yijiangshan@kylinos.cn --- arch/powerpc/platforms/pseries/pci.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c index d11a64a086c1..6fc13f4a79a3 100644 --- a/arch/powerpc/platforms/pseries/pci.c +++ b/arch/powerpc/platforms/pseries/pci.c @@ -132,11 +132,14 @@ static int pseries_pci_sriov_enable(struct pci_dev *pdev, u16 num_vfs) /* First integer stores max config */ max_config_vfs = of_read_number(&max_vfs[0], 1); - if (max_config_vfs < num_vfs || num_vfs > MAX_VFS_FOR_MAP_PE) { - dev_err(&pdev->dev, - "Num VFs %x > %x Configurable VFs\n", - num_vfs, (num_vfs > MAX_VFS_FOR_MAP_PE) ? - MAX_VFS_FOR_MAP_PE : max_config_vfs); + if (max_config_vfs < num_vfs) { + dev_err(&pdev->dev, "Num VFs %x > %x Configurable VFs\n", + num_vfs, max_config_vfs); + return -EINVAL; + } + if (num_vfs > MAX_VFS_FOR_MAP_PE) { + dev_err(&pdev->dev, "Num VFs %x > %x PE mapping limit\n", + num_vfs, MAX_VFS_FOR_MAP_PE); return -EINVAL; } From 2b4707a149a55e8fa75c9ef32b359d60f470a566 Mon Sep 17 00:00:00 2001 From: XingWang Xiang Date: Wed, 2 Sep 2026 15:01:18 +0900 Subject: [PATCH 0735/1198] net: mctp: i3c: serialize probe with bus removal mctp_i3c_probe() drops busdevs_lock after finding the matching bus. A concurrent I3C_NOTIFY_BUS_REMOVE can then unregister and free the bus netdev before probe passes its private data to mctp_i3c_add_device(). The latter consequently adds a list node through a freed mbus pointer. Keep busdevs_lock held until the device has been added. This also satisfies the __must_hold annotation on mctp_i3c_add_device(). Fixes: c8755b29b58e ("mctp i3c: MCTP I3C driver") Signed-off-by: XingWang Xiang Acked-by: Matt Johnston Signed-off-by: David S. Miller --- drivers/net/mctp/mctp-i3c.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/net/mctp/mctp-i3c.c b/drivers/net/mctp/mctp-i3c.c index 88d9e36cd4a2..4e857dd5df64 100644 --- a/drivers/net/mctp/mctp-i3c.c +++ b/drivers/net/mctp/mctp-i3c.c @@ -288,6 +288,7 @@ __must_hold(&busdevs_lock) static int mctp_i3c_probe(struct i3c_device *i3c) { struct mctp_i3c_bus *b = NULL, *mbus = NULL; + int rc; /* Look for a known bus */ mutex_lock(&busdevs_lock); @@ -296,14 +297,16 @@ static int mctp_i3c_probe(struct i3c_device *i3c) mbus = b; break; } - mutex_unlock(&busdevs_lock); if (!mbus) { /* probably no "mctp-controller" property on the i3c bus */ - return -ENODEV; + rc = -ENODEV; + } else { + rc = mctp_i3c_add_device(mbus, i3c); } + mutex_unlock(&busdevs_lock); - return mctp_i3c_add_device(mbus, i3c); + return rc; } static void mctp_i3c_remove_device(struct mctp_i3c_device *mi) From 63a7531ca31f9f097d9cc1cc3fe86ae683cdabdd Mon Sep 17 00:00:00 2001 From: "Mukesh Kumar Chaurasiya (IBM)" Date: Fri, 4 Sep 2026 14:38:58 +0530 Subject: [PATCH 0736/1198] powerpc/entry: Fix irq_soft_mask corruption on replayed interrupt exit When __replay_soft_interrupts() replays a pending interrupt (e.g. PACA_IRQ_DEC -> timer_interrupt), it calls the handler directly with a synthetic pt_regs. The DEFINE_INTERRUPT_HANDLER_ASYNC wrapper around each handler calls arch_interrupt_async_exit_prepare() on the way out, which calls arch_interrupt_exit_prepare() -> local_irq_disable() -> arch_local_irq_disable(), which does: irq_soft_mask_set(IRQS_DISABLED) /* 0x1 */ This unconditionally overwrites irq_soft_mask with IRQS_DISABLED (0x1), stripping the IRQS_PMI_DISABLED (0x2) bit. The result is that irq_soft_mask is 0x1 instead of IRQS_ALL_DISABLED (0x3) when the handler returns to __replay_soft_interrupts(). For a normally-taken interrupt this is harmless: the next interrupt always enters through arch_interrupt_enter_prepare() which unconditionally sets irq_soft_mask to IRQS_ALL_DISABLED. But during replay, next_interrupt() is called directly between replayed handlers without going back through arch_interrupt_enter_prepare(), so the stripped bit is never restored. next_interrupt() then fires a WARNING: WARNING: arch/powerpc/kernel/irq_64.c:75 WARN_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED) The warning was observed early in boot on a POWER10 pseries guest during kmem_cache_init_late(), where a spinlock release triggers interrupt replay that processes a pending timer interrupt. Debugger state confirming the bug: Before timer_interrupt(®s): irq_soft_mask = 0x3 (IRQS_ALL_DISABLED) correct irq_happened = 0x41 (HARD_DIS|REPLAYING) correct After timer_interrupt(®s) returns: irq_soft_mask = 0x1 (IRQS_DISABLED) WRONG - PMI bit stripped irq_happened = 0x41 unchanged The fix is to replace local_irq_disable() with hard_irq_disable(). hard_irq_disable() is the right primitive here for two reasons: 1. On PPC64 (hw_irq.h:301) it calls irq_soft_mask_set_return(IRQS_ALL_DISABLED), setting the soft mask to 0x3 (both IRQS_DISABLED and IRQS_PMI_DISABLED), which preserves the PMI bit and fixes the WARNING. The additional work it does (__hard_irq_disable(), PACA_IRQ_HARD_DIS |=) is redundant but safe since both are already set at this point in the exit path; the trace_hardirqs_off() inside is guarded by if (!arch_irqs_disabled_flags(flags)) so it will not double-fire. 2. On PPC32 (hw_irq.h:467) hard_irq_disable() maps to arch_local_irq_disable() -> __hard_irq_disable(), which clears MSR[EE] in hardware. This is exactly correct: PPC32 has no soft-mask PACA mechanism, so the hardware disable is the right way to satisfy irqentry_exit()'s requirement. This also fixes a build error on PPC32 where irq_soft_mask_set() is only defined under CONFIG_PPC64: arch/powerpc/include/asm/entry-common.h:273: error: implicit declaration of function 'irq_soft_mask_set' Using hard_irq_disable() requires no #ifdef and is consistent with how the rest of the entry code (e.g. entry-common.h:463) handles the same PPC32/PPC64 split. Fixes: 334f3f6d7a16 ("powerpc/entry: Disable interrupts before irqentry_exit") Reported-by: Venkat Rao Bagalkote Closes: https://lore.kernel.org/all/6f9bfb0f-b14c-468e-bb9f-c157d120d0dc@linux.ibm.com/ Tested-by: Venkat Rao Bagalkote Reviewed-by: Shrikanth Hegde Signed-off-by: Mukesh Kumar Chaurasiya (IBM) Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260904090858.128563-1-mkchauras@gmail.com --- arch/powerpc/include/asm/entry-common.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/include/asm/entry-common.h b/arch/powerpc/include/asm/entry-common.h index 94083516df57..80b07750b531 100644 --- a/arch/powerpc/include/asm/entry-common.h +++ b/arch/powerpc/include/asm/entry-common.h @@ -270,7 +270,7 @@ static inline void arch_interrupt_exit_prepare(struct pt_regs *regs) } /* irqentry_exit expects to be called with interrupts disabled */ - local_irq_disable(); + hard_irq_disable(); } static inline void arch_interrupt_async_enter_prepare(struct pt_regs *regs) From 9f2e63f1b2d5fc5b5423424902c091123e220e7e Mon Sep 17 00:00:00 2001 From: Bjoern Doebel Date: Thu, 3 Sep 2026 21:28:58 +0000 Subject: [PATCH 0737/1198] smb: client: avoid leaking refcount in cifs_queue_oplock_break() cifs_queue_oplock_break() unconditionally takes a reference on the target file before queueing cifs_oplock_break(). Only that work item decreases the reference counter again. If another oplock break arrives while that work is still queued, queue_work() will return false and not queue this second work item. As a result, we will never reach the point to drop the file reference again and are leaking this reference. This can be triggered when interacting with a slow-responding server. As a result, later unmount operations for this file system will fail with BUG: Dentry ... still in use (1) [unmount of cifs cifs] VFS: Busy inodes after unmount of cifs (cifs) kernel BUG at fs/super.c:777! Fix this by only incrementing the reference count if the work has been queued successfully. Taking it after queue_work() is safe because all three callers hold tcon->open_file_lock across the call and _cifsFileInfo_put() decrements under that same lock, so a worker that starts the handler in the window cannot drop the reference before it has been taken. Fixes: b98749cac4a69 ("CIFS: keep FileInfo handle live during oplock break") Cc: stable@vger.kernel.org Assisted-by: Kiro:claude-opus-5 Signed-off-by: Bjoern Doebel Reviewed-by: Namjae Jeon Signed-off-by: Paulo Alcantara --- fs/smb/client/misc.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c index d4db3f91a91f..945194fe7a97 100644 --- a/fs/smb/client/misc.c +++ b/fs/smb/client/misc.c @@ -378,10 +378,11 @@ void cifs_queue_oplock_break(struct cifsFileInfo *cfile) * open_file_lock to enforce the validity of it for the oplock * break handler. The matching put is done at the end of the * handler. + * + * Only take a reference if the work is actually queued. */ - cifsFileInfo_get(cfile); - - queue_work(cifsoplockd_wq, &cfile->oplock_break); + if (queue_work(cifsoplockd_wq, &cfile->oplock_break)) + cifsFileInfo_get(cfile); } void cifs_done_oplock_break(struct cifsInodeInfo *cinode) From 23b26f4408ac3f35a482d2e5cf6fc865d4201b71 Mon Sep 17 00:00:00 2001 From: Bjoern Doebel Date: Fri, 4 Sep 2026 10:42:36 +0000 Subject: [PATCH 0738/1198] smb: client: avoid leaking refcount when cifs_sb_tlink() fails cifs_oplock_break() takes over the reference that cifs_queue_oplock_break() acquired when it queued the work, and drops it with _cifsFileInfo_put() once the break has been processed. Only in setups with "-o multiuser", cifs_sb_tlink() may fail, at which point cifs_oplock_break() returns without putting the file reference, mirroring the reference leak we already fixed in the companion patch to cifs_queue_oplock_break(). This would trigger a crash due to busy inodes on the next unmount: BUG: Dentry ... still in use (1) [unmount of cifs cifs] VFS: Busy inodes after unmount of cifs (cifs) Drop the reference on that path as well. Doing so before the out label mirrors the normal path, which also puts the reference before cifs_done_oplock_break(). Found by Sashiko code review. The failure path was not exercised at runtime. Fixes: e8f5f849ffce2 ("cifs: fix potential oops in cifs_oplock_break") Cc: stable@vger.kernel.org Assisted-by: Kiro:claude-opus-5 Signed-off-by: Bjoern Doebel Reviewed-by: Namjae Jeon Signed-off-by: Paulo Alcantara --- fs/smb/client/file.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index d7b0a9512dfa..27b58d907203 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -3348,8 +3348,11 @@ void cifs_oplock_break(struct work_struct *work) TASK_UNINTERRUPTIBLE); tlink = cifs_sb_tlink(cifs_sb); - if (IS_ERR(tlink)) + if (IS_ERR(tlink)) { + /* drop the reference taken when the break was queued */ + _cifsFileInfo_put(cfile, false /* do not wait for ourself */, false); goto out; + } tcon = tlink_tcon(tlink); server = tcon->ses->server; From 5520e89a5a4f834bced64cf2ac927001cc513a40 Mon Sep 17 00:00:00 2001 From: Fan Wu Date: Fri, 4 Sep 2026 13:48:11 +0000 Subject: [PATCH 0739/1198] smb: client: fix cifsFileInfo reference leak in deferred close When cifs_close() defers a close, it hands the cifsFileInfo reference of the closing struct file to the queued work. Each execution of smb2_deferred_work_close() drops one such reference. deferred_close_scheduled can be false while the work is pending: the workqueue clears PENDING when the callback starts to run, before the callback clears the flag under deferred_lock. A close in that interval requeues the running work, and the callback then clears the flag, leaving the requeued work pending with the flag down. A later cifs_open() can reuse the handle and its cifs_close() reaches the same branch: queue_delayed_work() fails because the work is still pending, but cifs_close() returns without dropping the closing file's reference. The cifsFileInfo count stays pinned and its tlink, dentry and server handle are leaked. Check the return value and hand off the reference only when work was actually queued. Otherwise, use the shared _cifsFileInfo_put(), like the mod_delayed_work() branch above: the pending execution already owns its reference. This issue was found by an in-house static analysis tool. Fixes: c3f207ab29f7 ("cifs: Deferred close for files") Cc: stable@vger.kernel.org Assisted-by: Codex:gpt-5.6 Co-developed-by: Song Li Signed-off-by: Song Li Signed-off-by: Fan Wu Signed-off-by: Paulo Alcantara --- fs/smb/client/file.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 27b58d907203..1aa4844f8b8a 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -1515,11 +1515,18 @@ int cifs_close(struct inode *inode, struct file *file) trace_smb3_close_cached(tcon->tid, tcon->ses->Suid, cfile->fid.persistent_fid, cifs_sb->ctx->closetimeo); - queue_delayed_work(deferredclose_wq, - &cfile->deferred, cifs_sb->ctx->closetimeo); - cfile->deferred_close_scheduled = true; - spin_unlock(&cinode->deferred_lock); - return 0; + /* + * Each queued execution owns one reference. + * If nothing was queued, the reference of + * the closing file is dropped below. + */ + if (queue_delayed_work(deferredclose_wq, + &cfile->deferred, + cifs_sb->ctx->closetimeo)) { + cfile->deferred_close_scheduled = true; + spin_unlock(&cinode->deferred_lock); + return 0; + } } spin_unlock(&cinode->deferred_lock); _cifsFileInfo_put(cfile, true, false); From b144dc5a24149ba9a0cb2197001973a74b8c93b2 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Mon, 10 Aug 2026 09:40:00 -0700 Subject: [PATCH 0740/1198] virtio_console: allocate the port_buffer with the caller's gfp put_chars() runs from the hvc console write path with preemption disabled, so it asks alloc_buf() for GFP_ATOMIC. Only the data buffer gets it: the struct port_buffer itself keeps the GFP_KERNEL default, so the allocation can enter direct reclaim and sleep. A write to /dev/kmsg on a CONFIG_DEBUG_ATOMIC_SLEEP kernel splats: BUG: sleeping function called from invalid context at ./include/linux/sched/mm.h:320 in_atomic(): 1, irqs_disabled(): 1, non_block: 0, pid: 1, name: virtme-ng-init preempt_count: 1, expected: 0 Preemption disabled at: [] vprintk_emit+0x17d/0x510 Call Trace: dump_stack_lvl+0x69/0xa0 __might_resched+0x37a/0x4d0 __kmalloc_cache_noprof+0x94/0x5f0 put_chars+0x209/0x3e0 hvc_console_print+0x234/0x640 console_flush_all+0x4fc/0x950 console_unlock+0xbf/0x1b0 vprintk_emit+0x312/0x510 devkmsg_emit+0xba/0x110 devkmsg_write+0x21b/0x2e0 vfs_write+0x4dc/0x9d0 ksys_write+0x108/0x1e0 do_syscall_64+0xfa/0x460 Pass gfp on to that allocation too. Fixes: fc220d6be3c7 ("virtio_console: refactor __send_to_port() buffer ownership") Signed-off-by: Breno Leitao Acked-by: Sungho Bae Tested-by: Florian Westphal Link: https://patch.msgid.link/20260810-serial-v1-1-abbe51602c13@debian.org Signed-off-by: Greg Kroah-Hartman --- drivers/char/virtio_console.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 62eecfa61646..7f6cbe851d1e 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -426,7 +426,7 @@ static struct port_buffer *alloc_buf(struct virtio_device *vdev, size_t buf_size * Allocate buffer and the sg list. The sg list array is allocated * directly after the port_buffer struct. */ - buf = kmalloc_flex(*buf, sg, pages); + buf = kmalloc_flex(*buf, sg, pages, gfp); if (!buf) goto fail; From e6662f2100f8d33b0f4d0047c219efd6bba186ea Mon Sep 17 00:00:00 2001 From: Weiming Shi Date: Wed, 2 Sep 2026 23:52:31 +0800 Subject: [PATCH 0741/1198] net/sched: defer qdisc freeing after failed creation An RTM_NEWQDISC request can make clsact bind a populated shared ingress block during ->init(), publishing an embedded mini_Qdisc to lockless readers. If the same request has an invalid TCA_RATE, estimator setup fails after ->init(); the unwind removes the pointer but synchronously frees its containing qdisc while tc_run() may still hold it. Retire failed qdiscs through the same RCU helper as normal destruction. Inline the synchronous free into the callback now that no direct callers remain. Fixes: 51ab2994c387 ("net: sched: allow ingress and clsact qdiscs to share filter blocks") Reported-by: Xiang Mei Link: https://lore.kernel.org/netdev/20260805102505.740806-1-david.lee@trailofbits.com/ Signed-off-by: Weiming Shi Link: https://patch.msgid.link/20260902155231.2149915-2-bestswngs@gmail.com Signed-off-by: Jakub Kicinski --- include/net/sch_generic.h | 2 +- net/sched/sch_api.c | 2 +- net/sched/sch_generic.c | 24 ++++++++++++------------ 3 files changed, 14 insertions(+), 14 deletions(-) diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index cbc248776511..f35bd06a6bad 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -793,7 +793,7 @@ void qdisc_offload_query_caps(struct net_device *dev, struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, struct netlink_ext_ack *extack); -void qdisc_free(struct Qdisc *qdisc); +void qdisc_free_rcu(struct Qdisc *qdisc); struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, u32 parentid, struct netlink_ext_ack *extack); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 90503e59e6e3..463ededcdcfe 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1385,7 +1385,7 @@ static struct Qdisc *qdisc_create(struct net_device *dev, err_out3: qdisc_lock_uninit(sch, ops); netdev_put(dev, &sch->dev_tracker); - qdisc_free(sch); + qdisc_free_rcu(sch); err_out2: bpf_module_put(ops, ops->owner); err_out: diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 4539dc2c6d38..6f6a6f0d5eb0 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -1086,21 +1086,21 @@ void qdisc_reset(struct Qdisc *qdisc) } EXPORT_SYMBOL(qdisc_reset); -void qdisc_free(struct Qdisc *qdisc) -{ - if (qdisc_is_percpu_stats(qdisc)) { - free_percpu(qdisc->cpu_bstats); - free_percpu(qdisc->cpu_qstats); - } - - kfree(qdisc); -} - static void qdisc_free_cb(struct rcu_head *head) { struct Qdisc *q = container_of(head, struct Qdisc, rcu); - qdisc_free(q); + if (qdisc_is_percpu_stats(q)) { + free_percpu(q->cpu_bstats); + free_percpu(q->cpu_qstats); + } + + kfree(q); +} + +void qdisc_free_rcu(struct Qdisc *qdisc) +{ + call_rcu(&qdisc->rcu, qdisc_free_cb); } static void __qdisc_destroy(struct Qdisc *qdisc) @@ -1127,7 +1127,7 @@ static void __qdisc_destroy(struct Qdisc *qdisc) trace_qdisc_destroy(qdisc); - call_rcu(&qdisc->rcu, qdisc_free_cb); + qdisc_free_rcu(qdisc); } void qdisc_destroy(struct Qdisc *qdisc) From 802eedcc0b25bb3e1b492f0600ab74325274d53b Mon Sep 17 00:00:00 2001 From: Shahar Shitrit Date: Wed, 2 Sep 2026 19:46:32 +0300 Subject: [PATCH 0742/1198] net/mlx5e: Fix missing FEC mode mapping for RS_544_514_INTERLEAVED_QUAD MLX5E_FEC_RS_544_514_INTERLEAVED_QUAD is missing from pplm_fec_2_ethtool_linkmodes[], leaving index 4 zero-initialized. As a result, when this FEC mode is active, find_first_bit() returns index 4, causing __set_bit() to set bit 0 (ETHTOOL_LINK_MODE_10baseT_Half_BIT) instead of ETHTOOL_LINK_MODE_FEC_RS_BIT. Consequently, ethtool reports: Advertised FEC modes: Not reported Add the missing mapping to ETHTOOL_LINK_MODE_FEC_RS_BIT. Fixes: 4e343c11efbb ("net/mlx5e: Support FEC settings for 200G per lane link modes") Signed-off-by: Shahar Shitrit Reviewed-by: Dragos Tatulea Reviewed-by: Yael Chemla Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20260902164634.3657606-2-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 112926d07634..f285ad88b6d5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1013,6 +1013,7 @@ static const u32 pplm_fec_2_ethtool_linkmodes[] = { [MLX5E_FEC_NOFEC] = ETHTOOL_LINK_MODE_FEC_NONE_BIT, [MLX5E_FEC_FIRECODE] = ETHTOOL_LINK_MODE_FEC_BASER_BIT, [MLX5E_FEC_RS_528_514] = ETHTOOL_LINK_MODE_FEC_RS_BIT, + [MLX5E_FEC_RS_544_514_INTERLEAVED_QUAD] = ETHTOOL_LINK_MODE_FEC_RS_BIT, [MLX5E_FEC_RS_544_514] = ETHTOOL_LINK_MODE_FEC_RS_BIT, [MLX5E_FEC_LLRS_272_257_1] = ETHTOOL_LINK_MODE_FEC_LLRS_BIT, }; From b9d755c5a37519fb1354034db1dfeb30e1ba6856 Mon Sep 17 00:00:00 2001 From: Shahar Shitrit Date: Wed, 2 Sep 2026 19:46:33 +0300 Subject: [PATCH 0743/1198] net/mlx5e: Fix setting RS FEC after remapping When a user sets a FEC mode via ethtool, the driver maps the ethtool FEC type to the lowest mlx5 bit of that type. For RS FEC, this is MLX5E_FEC_RS_528_514 (bit 2). The driver then checks whether this bit is supported by at least one link mode by inspecting the fec_override_cap fields via mlx5e_fec_in_caps(), and returns -EOPNOTSUPP if not. This check is incorrect. RS FEC has three supported hardware variants: RS_528_514 (bit 2), RS_544_514_INTERLEAVED_QUAD (bit 4), and RS_544_514 (bit 7). mlx5e_remap_fec_conf_mode() already remaps bit 2 to the appropriate RS variant per link mode when writing the admin fields, but the early capability check is done against the raw unmapped bit. As a result, a device that supports RS_544_514 or RS_544_514_INTERLEAVED_QUAD but not RS_528_514 will incorrectly reject the user's RS FEC request. Remove the early support check from mlx5e_set_fec_mode() and fold it into the existing write loop, checking caps against the remapped policy per link mode. Return -EOPNOTSUPP before the final register write if no link mode accepted the policy. Fixes: 2608a2f831c4 ("net/mlx5e: Fix return status when setting unsupported FEC mode") Signed-off-by: Shahar Shitrit Reviewed-by: Dragos Tatulea Reviewed-by: Yael Chemla Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20260902164634.3657606-3-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en/port.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c index 6049ccf475bc..a4c096a4fed2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c @@ -557,6 +557,7 @@ int mlx5e_set_fec_mode(struct mlx5_core_dev *dev, u16 fec_policy) u32 in[MLX5_ST_SZ_DW(pplm_reg)] = {}; int sz = MLX5_ST_SZ_BYTES(pplm_reg); u16 fec_policy_auto = 0; + bool fec_set = false; int err; int i; @@ -569,9 +570,6 @@ int mlx5e_set_fec_mode(struct mlx5_core_dev *dev, u16 fec_policy) if (fec_policy >= (1 << MLX5E_FEC_LLRS_272_257_1) && !fec_50g_per_lane) return -EOPNOTSUPP; - if (fec_policy && !mlx5e_fec_in_caps(dev, fec_policy)) - return -EOPNOTSUPP; - MLX5_SET(pplm_reg, in, local_port, 1); err = mlx5_core_access_reg(dev, in, sz, out, sz, MLX5_REG_PPLM, 0, 0); if (err) @@ -591,12 +589,17 @@ int mlx5e_set_fec_mode(struct mlx5_core_dev *dev, u16 fec_policy) mlx5e_get_fec_cap_field(out, &fec_caps, i); /* policy supported for link speed */ - if (fec_caps & conf_fec) + if (fec_caps & conf_fec) { mlx5e_fec_admin_field(out, &conf_fec, 1, i); - else - /* set FEC to auto*/ + fec_set = true; + } else { + /* set FEC to auto */ mlx5e_fec_admin_field(out, &fec_policy_auto, 1, i); + } } + if (fec_policy && !fec_set) + return -EOPNOTSUPP; + return mlx5_core_access_reg(dev, out, sz, out, sz, MLX5_REG_PPLM, 0, 1); } From c84ce45a7a3f3f024502c7f53308db9c76e4ae71 Mon Sep 17 00:00:00 2001 From: Shahar Shitrit Date: Wed, 2 Sep 2026 19:46:34 +0300 Subject: [PATCH 0744/1198] net/mlx5e: Fix reporting support for all RS FEC variants get_fec_supported_advertised() populates the FEC modes reported as supported to userspace. The MLX5E_ADVERTISE_SUPPORTED_FEC macro only checked MLX5E_FEC_RS_528_514, causing devices that support only the other RS variants (RS_544_514_INTERLEAVED_QUAD or RS_544_514) to not advertise RS as supported to ethtool at all. Introduce MLX5E_FEC_RS_MASK covering all three RS bit positions, update the macro to accept a bitmask directly rather than a single enum value, and pass MLX5E_FEC_RS_MASK for the RS entry. Fixes: b5ede32d3329 ("net/mlx5e: Add support for FEC modes based on 50G per lane links") Fixes: 4e343c11efbb ("net/mlx5e: Support FEC settings for 200G per lane link modes") Signed-off-by: Shahar Shitrit Reviewed-by: Dragos Tatulea Reviewed-by: Yael Chemla Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20260902164634.3657606-4-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en/port.h | 4 ++++ drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 12 ++++++------ 2 files changed, 10 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h index fa2283dd383b..53dbdf77bcce 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h @@ -66,4 +66,8 @@ enum { MLX5E_FEC_LLRS_272_257_1 = 9, }; +#define MLX5E_FEC_RS_MASK (BIT(MLX5E_FEC_RS_528_514) | \ + BIT(MLX5E_FEC_RS_544_514_INTERLEAVED_QUAD) | \ + BIT(MLX5E_FEC_RS_544_514)) + #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index f285ad88b6d5..3ed59ced0407 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1002,9 +1002,9 @@ static u32 pplm2ethtool_fec(u_long fec_mode, unsigned long size) return 0; } -#define MLX5E_ADVERTISE_SUPPORTED_FEC(mlx5_fec, ethtool_fec) \ +#define MLX5E_ADVERTISE_SUPPORTED_FEC(fec_mask, ethtool_fec) \ do { \ - if (mlx5e_fec_in_caps(dev, 1 << (mlx5_fec))) \ + if (mlx5e_fec_in_caps(dev, fec_mask)) \ __set_bit(ethtool_fec, \ link_ksettings->link_modes.supported);\ } while (0) @@ -1030,13 +1030,13 @@ static int get_fec_supported_advertised(struct mlx5_core_dev *dev, if (err) return (err == -EOPNOTSUPP) ? 0 : err; - MLX5E_ADVERTISE_SUPPORTED_FEC(MLX5E_FEC_NOFEC, + MLX5E_ADVERTISE_SUPPORTED_FEC(BIT(MLX5E_FEC_NOFEC), ETHTOOL_LINK_MODE_FEC_NONE_BIT); - MLX5E_ADVERTISE_SUPPORTED_FEC(MLX5E_FEC_FIRECODE, + MLX5E_ADVERTISE_SUPPORTED_FEC(BIT(MLX5E_FEC_FIRECODE), ETHTOOL_LINK_MODE_FEC_BASER_BIT); - MLX5E_ADVERTISE_SUPPORTED_FEC(MLX5E_FEC_RS_528_514, + MLX5E_ADVERTISE_SUPPORTED_FEC(MLX5E_FEC_RS_MASK, ETHTOOL_LINK_MODE_FEC_RS_BIT); - MLX5E_ADVERTISE_SUPPORTED_FEC(MLX5E_FEC_LLRS_272_257_1, + MLX5E_ADVERTISE_SUPPORTED_FEC(BIT(MLX5E_FEC_LLRS_272_257_1), ETHTOOL_LINK_MODE_FEC_LLRS_BIT); active_fec_long = active_fec; From b3c79dee5038c5e8460c59d7d01cb1450bdf5ecb Mon Sep 17 00:00:00 2001 From: Akiva Goldberger Date: Wed, 2 Sep 2026 22:27:40 +0300 Subject: [PATCH 0745/1198] net/mlx5: LAG, use local tracker to update active ports The CREATE_LAG command is handled asynchronously by queuing a work, which stores a local copy of ldev->tracker. When the work is processed, it is possible that the values of the local copy and ldev->tracker have diverged. A single CREATE_LAG command programs two related fields into the firmware: the v2p (virtual-to-physical) map, which selects the physical egress port for each hash bucket, and the active_port bitmask, which tells the firmware which physical ports are currently up so it can redirect QP/TIS away from inactive ports. For the firmware to steer traffic correctly, both must be derived from the same view of the ports' link state. The v2p map is computed by mlx5_infer_tx_affinity_mapping() from the local tracker snapshot, but lag_active_port_bits() called mlx5_infer_tx_enabled() on the live ldev->tracker instead. If ldev->tracker changed between the snapshot and command execution, the two fields reflect different port states: the v2p map may steer a bucket to a port that the active_port mask marks as inactive (or vice versa). The firmware then receives a self-contradictory configuration and can redirect or drop traffic on a port the mapping still points at, until a later event happens to reconcile the state. Update lag_active_port_bits so that it receives the local version of the tracker from when the work was queued, effectively closing the window for injecting an inconsistency. Fixes: c5c13b456cb8 ("net/mlx5: Lag, set active ports if support bypass port select flow table") Signed-off-by: Akiva Goldberger Reviewed-by: Shay Drori Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20260902192740.3665435-1-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- .../net/ethernet/mellanox/mlx5/core/lag/lag.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index 2285c889c215..c655f6e32e9b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -63,14 +63,15 @@ static int get_port_sel_mode(enum mlx5_lag_mode mode, unsigned long flags) return MLX5_LAG_PORT_SELECT_MODE_QUEUE_AFFINITY; } -static u8 lag_active_port_bits(struct mlx5_lag *ldev) +static u8 lag_active_port_bits(struct mlx5_lag *ldev, + struct lag_tracker *tracker) { u8 enabled_ports[MLX5_MAX_PORTS] = {}; u8 active_port = 0; int num_enabled; int idx; - mlx5_infer_tx_enabled(&ldev->tracker, ldev, enabled_ports, + mlx5_infer_tx_enabled(tracker, ldev, enabled_ports, &num_enabled); for (idx = 0; idx < num_enabled; idx++) active_port |= BIT_MASK(enabled_ports[idx]); @@ -79,7 +80,8 @@ static u8 lag_active_port_bits(struct mlx5_lag *ldev) } static int mlx5_cmd_create_lag(struct mlx5_core_dev *dev, struct mlx5_lag *ldev, - int mode, unsigned long flags) + struct lag_tracker *tracker, int mode, + unsigned long flags) { bool fdb_sel_mode = test_bit(MLX5_LAG_MODE_FLAG_FDB_SEL_MODE_NATIVE, &flags); @@ -108,7 +110,7 @@ static int mlx5_cmd_create_lag(struct mlx5_core_dev *dev, struct mlx5_lag *ldev, break; MLX5_SET(lagc, lag_ctx, active_port, - lag_active_port_bits(mlx5_lag_dev(dev))); + lag_active_port_bits(ldev, tracker)); break; default: break; @@ -787,7 +789,8 @@ static int mlx5_cmd_modify_active_port(struct mlx5_core_dev *dev, u8 ports) return mlx5_cmd_exec_in(dev, modify_lag, in); } -static int _mlx5_modify_lag(struct mlx5_lag *ldev, u8 *ports) +static int _mlx5_modify_lag(struct mlx5_lag *ldev, + struct lag_tracker *tracker, u8 *ports) { int idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); struct mlx5_core_dev *dev0; @@ -804,7 +807,7 @@ static int _mlx5_modify_lag(struct mlx5_lag *ldev, u8 *ports) !MLX5_CAP_PORT_SELECTION(dev0, port_select_flow_table_bypass)) return ret; - active_ports = lag_active_port_bits(ldev); + active_ports = lag_active_port_bits(ldev, tracker); return mlx5_cmd_modify_active_port(dev0, active_ports); } @@ -868,7 +871,7 @@ void mlx5_modify_lag(struct mlx5_lag *ldev, idx = i * ldev->buckets + j; if (ports[idx] == ldev->v2p_map[idx]) continue; - err = _mlx5_modify_lag(ldev, ports); + err = _mlx5_modify_lag(ldev, tracker, ports); if (err) { mlx5_core_err(dev0, "Failed to modify LAG (%d)\n", @@ -976,7 +979,7 @@ static int mlx5_create_lag(struct mlx5_lag *ldev, mlx5_core_info(dev0, "shared_fdb:%d mode:%s\n", shared_fdb, mlx5_get_str_port_sel_mode(mode, flags)); - err = mlx5_cmd_create_lag(dev0, ldev, mode, flags); + err = mlx5_cmd_create_lag(dev0, ldev, tracker, mode, flags); if (err) { mlx5_core_err(dev0, "Failed to create LAG (%d)\n", From e7ee89740800a1cf253713e9249c3ee9203ebe91 Mon Sep 17 00:00:00 2001 From: Carolina Jubran Date: Wed, 2 Sep 2026 22:32:24 +0300 Subject: [PATCH 0746/1198] net/mlx5e: Fix ETS zero BW reporting when one TC holds 100% When ETS TCs with zero bandwidth are configured, the driver programs the firmware using an alternate representation. On get, it needs to recognize that representation so those TCs can be translated back and reported as 0% bandwidth. The existing detection relied on the programmed bandwidth because it was enough to identify this representation. However, when a single ETS TC owns 100% of the bandwidth, its firmware representation becomes the same as a strict-priority TC, causing zero-bandwidth ETS TCs to be reported with non-zero bandwidth values. Use the cached TSA instead to distinguish the ETS and strict-priority cases. Fixes: be0f161ef141 ("net/mlx5e: DCBNL, Implement tc with ets type and zero bandwidth") Signed-off-by: Carolina Jubran Reviewed-by: Alex Lazar Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20260902193224.3668743-1-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 00e706e1ede1..741f75b5bfec 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -148,7 +148,7 @@ static int mlx5e_dcbnl_ieee_getets(struct net_device *netdev, if (err) return err; - if (ets->tc_tx_bw[i] < MLX5E_MAX_BW_ALLOC && + if (priv->dcbx.tc_tsa[i] == IEEE_8021QAZ_TSA_ETS && tc_group[i] == (MLX5E_LOWEST_PRIO_GROUP + 1)) is_zero_bw_ets_tc = true; From af3aef0245abbab5e9f6302e7a7d6407187afb71 Mon Sep 17 00:00:00 2001 From: Carolina Jubran Date: Wed, 2 Sep 2026 22:33:41 +0300 Subject: [PATCH 0747/1198] net/mlx5e: Fix use-after-free race in sample_restore_put() Concurrent teardown of TC sample rules sharing the same restore context may re-read restore->count after dropping restore_lock. At that point another thread may already have completed cleanup and freed the restore object. Use the result of the refcount decrement while holding restore_lock to determine whether cleanup is needed. Fixes: 36a3196256bf ("net/mlx5e: TC, Add sampler restore handle API") Signed-off-by: Carolina Jubran Reviewed-by: Shahar Shitrit Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20260902193341.3668809-1-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c index 89490f687a9c..93c62d3f3e5b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c @@ -311,12 +311,15 @@ sample_restore_get(struct mlx5e_tc_psample *tc_psample, u32 obj_id, static void sample_restore_put(struct mlx5e_tc_psample *tc_psample, struct mlx5e_sample_restore *restore) { + bool last; + mutex_lock(&tc_psample->restore_lock); - if (--restore->count == 0) + last = --restore->count == 0; + if (last) hash_del(&restore->hlist); mutex_unlock(&tc_psample->restore_lock); - if (!restore->count) { + if (last) { mlx5_del_flow_rules(restore->rule); mlx5_modify_header_dealloc(tc_psample->esw->dev, restore->modify_hdr); kfree(restore); From 7ee07f601f8f507c9faf25c68a49396ab8950596 Mon Sep 17 00:00:00 2001 From: Yael Chemla Date: Wed, 2 Sep 2026 22:35:14 +0300 Subject: [PATCH 0748/1198] net/mlx5: E-Switch: fix use-after-free in mlx5_eswitch_termtbl_put In mlx5_eswitch_termtbl_put(), the zero-ref cleanup check reads tt->ref_count after termtbl_mutex has been released. Two concurrent callers on the same mlx5_termtbl_handle race: one decrements ref_count to zero, removes the hash entry, and calls kfree(tt) while the other has already dropped the mutex and is about to evaluate if (!tt->ref_count), producing a use-after-free. Fix this by capturing the result of the decrement into a stack-local last variable before dropping the mutex. The cleanup decision is now made entirely under termtbl_mutex, and tt is not touched after kfree. Fixes: 10caabdaad5a ("net/mlx5e: Use termination table for VLAN push actions") Signed-off-by: Yael Chemla Reviewed-by: Dragos Tatulea Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20260902193514.3668880-1-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- .../ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c index 19f65d4c4def..d43f07360159 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c @@ -163,12 +163,15 @@ void mlx5_eswitch_termtbl_put(struct mlx5_eswitch *esw, struct mlx5_termtbl_handle *tt) { + bool last; + mutex_lock(&esw->offloads.termtbl_mutex); - if (--tt->ref_count == 0) + last = (--tt->ref_count == 0); + if (last) hash_del(&tt->termtbl_hlist); mutex_unlock(&esw->offloads.termtbl_mutex); - if (!tt->ref_count) { + if (last) { mlx5_del_flow_rules(tt->rule); mlx5_destroy_flow_table(tt->termtbl); kfree(tt); From c0c6f4ba8a37688f7b4d4044898d88f0450d44c2 Mon Sep 17 00:00:00 2001 From: Lama Kayal Date: Wed, 2 Sep 2026 22:38:54 +0300 Subject: [PATCH 0749/1198] net/mlx5: E-Switch, prevent mc_list repopulation during vport disable In mlx5_esw_vport_disable(), move esw_apply_vport_rx_mode() ahead of esw_vport_change_handle_locked() so vport->allmulti_rule is NULL before the change handler observes it. During FW-fatal recovery the disable runs while dev->state == INTERNAL_ERROR. The promisc query inside esw_update_vport_rx_mode() fails and returns early, leaving vport->allmulti_rule intact, so esw_update_vport_mc_promisc() runs and adds MLX5_ACTION_ADD entries to vport->mc_list whose flow rules are then installed in the FDB by esw_add_mc_addr(). esw_destroy_legacy_table() tears down the FDB with those refs still held, corrupting the sub-tree and leaving dangling flow_rule pointers in vport->mc_list. Two-stage failure on `echo 1 > /sys/bus/pci/devices//reset`: refcount_t: underflow; use-after-free. tree_put_node+0xef/0x110 [mlx5_core] clean_tree+0x44/0xd0 [mlx5_core] (x5) mlx5_fs_core_cleanup+0x57/0x1c0 [mlx5_core] mlx5_unload+0x65/0xd0 [mlx5_core] ... mlx5_health_try_recover BUG: unable to handle page fault for address: 0000000003000055 down_write+0x1c/0x60 mlx5_del_flow_rules+0x33/0x1f0 [mlx5_core] esw_del_mc_addr+0x7b/0x170 [mlx5_core] esw_apply_vport_addr_list+0x56/0xf0 [mlx5_core] esw_vport_change_handle_locked+0x28b/0x310 [mlx5_core] mlx5_esw_vport_enable+0x270/0x4a0 [mlx5_core] ... mlx5_load ... mlx5_health_try_recover esw_apply_vport_rx_mode(false, false) clears vport->allmulti_rule via its local state machine even when the FW del fails. With the rule NULL the !IS_ERR_OR_NULL(allmulti_rule) gate in the change handler closes, no rules are installed during disable, and the reload starts with a clean mc_list. Fixes: 922f56e9a795 ("net/mlx5: Fix steering rules cleanup") Signed-off-by: Lama Kayal Reviewed-by: Cosmin Ratiu Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20260902193854.3669035-1-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index b6e2c153b4f7..4c7fa4a52b0e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1040,13 +1040,19 @@ void mlx5_esw_vport_disable(struct mlx5_eswitch *esw, struct mlx5_vport *vport) (vport->info.ipsec_crypto_enabled || vport->info.ipsec_packet_enabled)) esw->enabled_ipsec_vf_count--; + /* Clear rx-mode before esw_vport_change_handle_locked(): on + * MLX5_VPORT_PROMISC_CHANGE it calls esw_update_vport_mc_promisc() + * when vport->allmulti_rule is set, repopulating mc_list with FDB + * rules that dangle once the FDB is destroyed. NULL allmulti_rule + * here skips that path. + */ + esw_apply_vport_rx_mode(esw, vport, false, false); /* We don't assume VFs will cleanup after themselves. * Calling vport change handler while vport is disabled will cleanup * the vport resources. */ esw_vport_change_handle_locked(vport); vport->enabled_events = 0; - esw_apply_vport_rx_mode(esw, vport, false, false); esw_vport_cleanup(esw, vport); esw->enabled_vports--; From df99553f840e4c529c1ba4c29bd39396466ca11a Mon Sep 17 00:00:00 2001 From: Carolina Jubran Date: Wed, 2 Sep 2026 22:37:31 +0300 Subject: [PATCH 0750/1198] net/mlx5e: Keep HW timestamp stats monotonic across reconfiguration `mlx5e_stats_ts_get()` currently selects either DMA or port timestamp counters based on `tx_ptp_opened`. This flag is intentionally kept set once the PTP TX queues have been opened so their statistics remain available after queue teardown. As a result, DMA timestamps are no longer reported after switching from port timestamping back to DMA timestamping. The function also reads statistics only from the currently active channels and TCs. Reducing the number of channels or TCs can therefore drop previously accumulated timestamp counters from the reported value. Read the persistent channel statistics instead and always include DMA timestamp counters. Once the PTP TX queues have been opened, also include the port timestamp counters. This also drops state_lock. It previously protected live channel/PTP pointers, the new code only reads persistent channel_stats and ptp_stats via mlx5e_stats_nch_read(), which is already safe for lockless stats access. Fixes: 3579032c08c1 ("net/mlx5e: Implement ethtool hardware timestamping statistics") Signed-off-by: Carolina Jubran Reviewed-by: Shahar Shitrit Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20260902193731.3668958-1-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- .../ethernet/mellanox/mlx5/core/en_stats.c | 51 ++++++++----------- 1 file changed, 20 insertions(+), 31 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index e7e6db7f6bf1..cd94bb44f6ab 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -1199,50 +1199,39 @@ void mlx5e_stats_rmon_get(struct mlx5e_priv *priv, void mlx5e_stats_ts_get(struct mlx5e_priv *priv, struct ethtool_ts_stats *ts_stats) { - int i, j; + u16 nch = mlx5e_stats_nch_read(priv); + int i, tc; - mutex_lock(&priv->state_lock); + ts_stats->pkts = 0; + for (i = 0; i < nch; i++) { + struct mlx5e_channel_stats *channel_stats = + priv->channel_stats[i]; + + for (tc = 0; tc < priv->max_opened_tc; tc++) + ts_stats->pkts += channel_stats->sq[tc].timestamps; + } + + /* Accumulate DMA and port timestamp counters so values stay monotonic + * across channel teardown and mode switches. + */ if (priv->tx_ptp_opened) { - struct mlx5e_ptp *ptp = priv->channels.ptp; - - ts_stats->pkts = 0; + /* Err and Lost stats are only relevant for port timestamping, + * as the DMA layer will always successfully timestamp packets. + */ ts_stats->err = 0; ts_stats->lost = 0; - if (!ptp) - goto out; - - /* Aggregate stats across all TCs */ - for (i = 0; i < ptp->num_tc; i++) { + for (tc = 0; tc < priv->max_opened_tc; tc++) { struct mlx5e_ptp_cq_stats *stats = - ptp->ptpsq[i].cq_stats; + &priv->ptp_stats.cq[tc]; ts_stats->pkts += stats->cqe; ts_stats->err += stats->abort + stats->err_cqe + - stats->late_cqe; + stats->late_cqe; ts_stats->lost += stats->lost_cqe; } - } else { - /* DMA layer will always successfully timestamp packets. Other - * counters do not make sense for this layer. - */ - ts_stats->pkts = 0; - - /* Aggregate stats across all SQs */ - for (j = 0; j < priv->channels.num; j++) { - struct mlx5e_channel *c = priv->channels.c[j]; - - for (i = 0; i < c->num_tc; i++) { - struct mlx5e_sq_stats *stats = c->sq[i].stats; - - ts_stats->pkts += stats->timestamps; - } - } } - -out: - mutex_unlock(&priv->state_lock); } #define PPORT_PHY_LAYER_OFF(c) \ From 094cc07f98dfe70a34e2a1923af17fd29b8cf622 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Tue, 1 Sep 2026 17:39:22 -0400 Subject: [PATCH 0751/1198] net/sched: fq: clamp quantum and initial_quantum in change path MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The fq change path accepts TCA_FQ_QUANTUM in [1, INT_MAX] and TCA_FQ_INITIAL_QUANTUM up to INT_MAX, while fq_init() already clamps to [1, 1<<20]. A user can override the init clamp via tc qdisc change, restoring the small-quantum deficit spin that the init clamp prevents. Narrow iq_range.max to 1<<20 so TCA_FQ_INITIAL_QUANTUM is rejected at parse time. Clamp TCA_FQ_QUANTUM to [256, 1<<20] in fq_change() and fq_init() quantum to [256, 1<<20] for tiny-MTU devices. Conditions to recreate the bug: CONFIG_NET_SCH_FQ=y. Requires CAP_NET_ADMIN (namespace-local via unshare -Urn suffices). tc qdisc add dev dummy0 root fq tc qdisc change dev dummy0 root fq quantum 1 stab data 32768 size_log 15 cell_log 0 Fixes: 709f34f7c28d ("net/sched: fq: add overflow bounds to quantum and initial quantum") Reported-by: Vega Reviewed-by: Toke Høiland-Jørgensen Tested-by: Victor Nogueira Signed-off-by: Jamal Hadi Salim Link: https://patch.msgid.link/QDISC-0CFC.v3.20260901204856@mojatatu.com.2 Signed-off-by: Jakub Kicinski --- net/sched/sch_fq.c | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 6144b5686f13..35f940b2205d 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -980,7 +980,7 @@ static int fq_resize(struct Qdisc *sch, u32 log) } static const struct netlink_range_validation iq_range = { - .max = INT_MAX, + .max = 1 << 20, }; static const struct nla_policy fq_policy[TCA_FQ_MAX + 1] = { @@ -1106,14 +1106,10 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt, nla_get_u32(tb[TCA_FQ_FLOW_PLIMIT])); if (tb[TCA_FQ_QUANTUM]) { - u32 quantum = nla_get_u32(tb[TCA_FQ_QUANTUM]); + u32 quantum = clamp_t(u32, nla_get_u32(tb[TCA_FQ_QUANTUM]), + 256, 1 << 20); - if (quantum > 0 && quantum <= (1 << 20)) { - WRITE_ONCE(q->quantum, quantum); - } else { - NL_SET_ERR_MSG_MOD(extack, "invalid quantum"); - err = -EINVAL; - } + WRITE_ONCE(q->quantum, quantum); } if (tb[TCA_FQ_INITIAL_QUANTUM]) @@ -1232,7 +1228,7 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt, sch->limit = 10000; q->flow_plimit = 100; mtu = clamp_t(u32, psched_mtu(qdisc_dev(sch)), 1, 1 << 20); - q->quantum = min_t(u32, 2 * mtu, 1 << 20); + q->quantum = clamp_t(u32, 2 * mtu, 256, 1 << 20); q->initial_quantum = min_t(u32, 10 * mtu, 1 << 20); q->flow_refill_delay = msecs_to_jiffies(40); q->flow_max_rate = ~0UL; From 4864f58c53eb47257d55e01f47d4a9f355f7f970 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Tue, 1 Sep 2026 17:39:23 -0400 Subject: [PATCH 0752/1198] net/sched: fq_pie: clamp quantum in change path MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit fq_pie_change() accepts any quantum value from userspace, including 1. With a crafted size table qdisc_pkt_len reaches ~2 GiB, so quantum=1 makes the deficit-refill loop spin ~2^31 times under the qdisc lock (a soft lockup / denial of service). Add max(256U, ...) matching fq_codel_change(). Conditions to recreate the bug: CONFIG_NET_SCH_FQ_PIE=y. Requires CAP_NET_ADMIN (namespace-local via unshare -Urn suffices). tc qdisc add dev dummy0 root fq_pie tc qdisc change dev dummy0 root fq_pie quantum 1 stab data 32768 size_log 15 cell_log 0 Fixes: ec97ecf1ebe4 ("net: sched: add Flow Queue PIE packet scheduler") Reported-by: Vega Reviewed-by: Toke Høiland-Jørgensen Tested-by: Victor Nogueira Signed-off-by: Jamal Hadi Salim Link: https://patch.msgid.link/QDISC-0CFC.v3.20260901204856@mojatatu.com.3 Signed-off-by: Jakub Kicinski --- net/sched/sch_fq_pie.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index b27d95418707..5982847df8f8 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -341,7 +341,8 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt, nla_get_u32(tb[TCA_FQ_PIE_BETA])); if (tb[TCA_FQ_PIE_QUANTUM]) - WRITE_ONCE(q->quantum, nla_get_u32(tb[TCA_FQ_PIE_QUANTUM])); + WRITE_ONCE(q->quantum, + max(256U, nla_get_u32(tb[TCA_FQ_PIE_QUANTUM]))); if (tb[TCA_FQ_PIE_MEMORY_LIMIT]) WRITE_ONCE(q->memory_limit, From fb9f88a33c516ea5c0bcd9a22ca288b246b34567 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Tue, 1 Sep 2026 17:39:24 -0400 Subject: [PATCH 0753/1198] net/sched: sfq: clamp quantum in change path MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit sfq_change() accepts any non-negative quantum (only rejects (int)ctl->quantum < 0). With a crafted size table qdisc_pkt_len reaches ~2 GiB, so quantum=1 makes the deficit-refill loop spin ~2^31 times under the qdisc lock (a soft lockup / denial of service). Add max(256U, ...) matching fq_codel_change(). Reject quantum > 1<<20 with -EINVAL, matching fq_codel_change() and the init clamp. Conditions to recreate the bug: CONFIG_NET_SCH_SFQ=y. Requires CAP_NET_ADMIN (namespace-local via unshare -Urn suffices). tc qdisc add dev dummy0 root sfq tc qdisc change dev dummy0 root sfq quantum 1 stab data 32768 size_log 15 cell_log 0 Fixes: e4650d7ae425 ("net_sched: sch_sfq: handle bigger packets") Reported-by: Vega Reviewed-by: Toke Høiland-Jørgensen Tested-by: Victor Nogueira Signed-off-by: Jamal Hadi Salim Link: https://patch.msgid.link/QDISC-0CFC.v3.20260901204856@mojatatu.com.4 Signed-off-by: Jakub Kicinski --- net/sched/sch_sfq.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 187d3ed578f2..8bbcfc9e85d9 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -660,6 +660,11 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt, return -EINVAL; } + if (ctl->quantum > 1 << 20) { + NL_SET_ERR_MSG_MOD(extack, "quantum too large"); + return -EINVAL; + } + if (ctl->perturb_period < 0 || ctl->perturb_period > INT_MAX / HZ) { NL_SET_ERR_MSG_MOD(extack, "invalid perturb period"); @@ -688,7 +693,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt, /* update and validate configuration */ if (ctl->quantum) - quantum = ctl->quantum; + quantum = max(256U, ctl->quantum); if (ctl->flows) maxflows = min_t(u32, ctl->flows, SFQ_MAX_FLOWS); if (ctl->divisor) { From eb56a495f59baf6cad5ed80e3ffb9078098b1346 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Tue, 1 Sep 2026 17:39:25 -0400 Subject: [PATCH 0754/1198] net/sched: hhf: clamp quantum in change and init paths MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit hhf_change() accepts any quantum from userspace, including 1. With a crafted size table qdisc_pkt_len reaches ~2 GiB, so quantum=1 makes the deficit-refill loop spin ~2^31 times under the qdisc lock (a soft lockup / denial of service). Add max(256U, ...) in hhf_change() matching fq_codel_change(). Clamp hhf_init() to [256, 1<<20] matching the siblings, and remove the old fallback that only set quantum=256 on overflow. Conditions to recreate the bug: CONFIG_NET_SCH_HHF=y. Requires CAP_NET_ADMIN (namespace-local via unshare -Urn suffices). tc qdisc add dev dummy0 root hhf tc qdisc change dev dummy0 root hhf quantum 1 stab data 32768 size_log 15 cell_log 0 Fixes: 10239edf86f1 ("net-qdisc-hhf: Heavy-Hitter Filter (HHF) qdisc") Reported-by: Vega Reviewed-by: Toke Høiland-Jørgensen Tested-by: Victor Nogueira Signed-off-by: Jamal Hadi Salim Link: https://patch.msgid.link/QDISC-0CFC.v3.20260901204856@mojatatu.com.5 Signed-off-by: Jakub Kicinski --- net/sched/sch_hhf.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 96acab6a8da0..fc72f825fbd9 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -551,7 +551,7 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt, return err; if (tb[TCA_HHF_QUANTUM]) - new_quantum = nla_get_u32(tb[TCA_HHF_QUANTUM]); + new_quantum = max(256U, nla_get_u32(tb[TCA_HHF_QUANTUM])); if (tb[TCA_HHF_NON_HH_WEIGHT]) new_hhf_non_hh_weight = nla_get_u32(tb[TCA_HHF_NON_HH_WEIGHT]); @@ -613,7 +613,7 @@ static int hhf_init(struct Qdisc *sch, struct nlattr *opt, int i; sch->limit = 1000; - q->quantum = psched_mtu(qdisc_dev(sch)); + q->quantum = clamp_t(u32, psched_mtu(qdisc_dev(sch)), 256, 1 << 20); get_random_bytes(&q->perturbation, sizeof(q->perturbation)); INIT_LIST_HEAD(&q->new_buckets); INIT_LIST_HEAD(&q->old_buckets); @@ -624,10 +624,6 @@ static int hhf_init(struct Qdisc *sch, struct nlattr *opt, q->hhf_evict_timeout = HZ; /* 1 sec */ q->hhf_non_hh_weight = 2; - if ((int)q->quantum <= 0 || - (u64)q->quantum * q->hhf_non_hh_weight > INT_MAX) - q->quantum = 256; - if (opt) { int err = hhf_change(sch, opt, extack); From 3c01f1ca5dfc6d6911b0e5b37f5062b1dc451b94 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Tue, 1 Sep 2026 17:39:26 -0400 Subject: [PATCH 0755/1198] net/sched: dualpi2: clamp psched_mtu at all call sites MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit dualpi2_calculate_c_protection(), must_drop(), and get_memory_limit() call psched_mtu() with no clamp. A huge MTU makes (s32)psched_mtu() overflow in the signed multiply for c_protection_init, and 2 * psched_mtu() wraps in get_memory_limit(). With a crafted size table qdisc_pkt_len reaches ~2 GiB, causing a soft lockup / denial of service. Clamp psched_mtu() to [1, 1<<20] at all three call sites. Conditions to recreate the bug: CONFIG_NET_SCH_DUALPI2=y. Requires CAP_NET_ADMIN (namespace-local via unshare -Urn suffices). tc qdisc add dev dummy0 root dualpi2 tc qdisc change dev dummy0 root dualpi2 stab data 32768 size_log 15 cell_log 0 Fixes: 320d031ad6e4 ("sched: Struct definition and parsing of dualpi2 qdisc") Reported-by: Vega Reviewed-by: Toke Høiland-Jørgensen Tested-by: Victor Nogueira Signed-off-by: Jamal Hadi Salim Link: https://patch.msgid.link/QDISC-0CFC.v3.20260901204856@mojatatu.com.6 Signed-off-by: Jakub Kicinski --- net/sched/sch_dualpi2.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/net/sched/sch_dualpi2.c b/net/sched/sch_dualpi2.c index 4f678d4ff10e..4947def7c49e 100644 --- a/net/sched/sch_dualpi2.c +++ b/net/sched/sch_dualpi2.c @@ -208,9 +208,11 @@ static void dualpi2_reset_c_protection(struct dualpi2_sched_data *q) static void dualpi2_calculate_c_protection(struct Qdisc *sch, struct dualpi2_sched_data *q, u32 wc) { + u32 mtu = clamp_t(u32, psched_mtu(qdisc_dev(sch)), 1, 1 << 20); + q->c_protection_wc = wc; q->c_protection_wl = MAX_WC - wc; - q->c_protection_init = (s32)psched_mtu(qdisc_dev(sch)) * + q->c_protection_init = (s32)mtu * ((int)q->c_protection_wc - (int)q->c_protection_wl); dualpi2_reset_c_protection(q); } @@ -285,8 +287,9 @@ static bool must_drop(struct Qdisc *sch, struct dualpi2_sched_data *q, u64 local_l_prob; bool overload; u32 prob; + u32 mtu = clamp_t(u32, psched_mtu(qdisc_dev(sch)), 1, 1 << 20); - if (sch->qstats.backlog < 2 * psched_mtu(qdisc_dev(sch))) + if (sch->qstats.backlog < 2 * mtu) return false; prob = READ_ONCE(q->pi2_prob); @@ -712,7 +715,8 @@ static u32 get_memory_limit(struct Qdisc *sch, u32 limit) /* Apply rule of thumb, i.e., doubling the packet length, * to further include per packet overhead in memory_limit. */ - u64 memlim = mul_u32_u32(limit, 2 * psched_mtu(qdisc_dev(sch))); + u64 memlim = mul_u32_u32(limit, 2 * clamp_t(u32, psched_mtu(qdisc_dev(sch)), + 1, 1 << 20)); if (upper_32_bits(memlim)) return U32_MAX; From 54370e44c002770ae61fc889f28f699e91616ffc Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Tue, 1 Sep 2026 17:39:27 -0400 Subject: [PATCH 0756/1198] net/sched: pie: clamp psched_mtu in pie_drop_early MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit pie_drop_early() calls psched_mtu() with no clamp. With mtu=0x80000000 the bytemode divide silently zeroes the drop probability, disabling AQM. Clamp to [1, 1<<20]. Conditions to recreate the bug: CONFIG_NET_SCH_PIE=y. Requires CAP_NET_ADMIN (namespace-local via unshare -Urn suffices). tc qdisc add dev dummy0 root pie tc qdisc change dev dummy0 root pie stab data 32768 size_log 15 cell_log 0 Fixes: d4b36210c2e6 ("net: pkt_sched: PIE AQM scheme") Reported-by: Vega Reviewed-by: Toke Høiland-Jørgensen Tested-by: Victor Nogueira Signed-off-by: Jamal Hadi Salim Link: https://patch.msgid.link/QDISC-0CFC.v3.20260901204856@mojatatu.com.7 Signed-off-by: Jakub Kicinski --- net/sched/sch_pie.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index b41f2def2e2c..3b7863ffd284 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -35,7 +35,7 @@ bool pie_drop_early(struct Qdisc *sch, struct pie_params *params, { u64 rnd; u64 local_prob = vars->prob; - u32 mtu = psched_mtu(qdisc_dev(sch)); + u32 mtu = clamp_t(u32, psched_mtu(qdisc_dev(sch)), 1, 1 << 20); /* If there is still burst allowance left skip random early drop */ if (vars->burst_time > 0) From 8382abec0f1568d0a5590d75a3df92f23fcf5196 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Tue, 1 Sep 2026 17:39:28 -0400 Subject: [PATCH 0757/1198] net/sched: drr: clamp quantum in change class MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit drr_change_class() rejects explicit quantum==0 but falls back to psched_mtu() with no floor. With a crafted size table qdisc_pkt_len reaches ~2 GiB, so quantum=1 (or a zero psched_mtu on a headerless device) makes the deficit-refill loop spin under the qdisc lock. Add clamp_t(u32, quantum, 256, 1<<20) after the zero reject and on the fallback path. The explicit-zero reject is preserved. Conditions to recreate the bug: CONFIG_NET_SCH_DRR=y. Requires CAP_NET_ADMIN (namespace-local via unshare -Urn suffices). tc qdisc add dev dummy0 root drr tc class add dev dummy0 parent 1: classid 1:1 drr quantum 1 Fixes: 13d2a1d2b032 ("pkt_sched: add DRR scheduler") Reported-by: Vega Reviewed-by: Toke Høiland-Jørgensen Tested-by: Victor Nogueira Signed-off-by: Jamal Hadi Salim Link: https://patch.msgid.link/QDISC-0CFC.v3.20260901204856@mojatatu.com.8 Signed-off-by: Jakub Kicinski --- net/sched/sch_drr.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 91b1ef824afa..8621d057edd9 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -82,8 +82,9 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, NL_SET_ERR_MSG(extack, "Specified DRR quantum cannot be zero"); return -EINVAL; } + quantum = clamp_t(u32, quantum, 256, 1 << 20); } else - quantum = psched_mtu(qdisc_dev(sch)); + quantum = clamp_t(u32, (u32)psched_mtu(qdisc_dev(sch)), 256, 1 << 20); if (cl != NULL) { if (tca[TCA_RATE]) { From 1c38487f46b243bfeefec0c0c86023a3904f2214 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Tue, 1 Sep 2026 17:39:29 -0400 Subject: [PATCH 0758/1198] net/sched: ets: clamp quantum in parse and fallback paths MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ets_qdisc_change() falls back to psched_mtu() with no floor for bands without an explicit quantum. With a crafted size table qdisc_pkt_len reaches ~2 GiB, so a zero psched_mtu on a headerless device makes the deficit-refill loop spin under the qdisc lock. Move the floor into ets_quantum_parse() so explicitly configured quanta are also clamped to [256, 1<<20], not just the fallback path. Conditions to recreate the bug: CONFIG_NET_SCH_ETS=y. Requires CAP_NET_ADMIN (namespace-local via unshare -Urn suffices). tc qdisc add dev dummy0 root ets bands 3 strict 2 quanta 1 1 Fixes: dcc68b4d8084 ("net: sch_ets: Add a new Qdisc") Reported-by: Vega Reviewed-by: Toke Høiland-Jørgensen Tested-by: Victor Nogueira Signed-off-by: Jamal Hadi Salim Link: https://patch.msgid.link/QDISC-0CFC.v3.20260901204856@mojatatu.com.9 Signed-off-by: Jakub Kicinski --- net/sched/sch_ets.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index 25fcf4079fec..6cc902a03838 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -83,11 +83,7 @@ static int ets_quantum_parse(struct Qdisc *sch, const struct nlattr *attr, unsigned int *quantum, struct netlink_ext_ack *extack) { - *quantum = nla_get_u32(attr); - if (!*quantum) { - NL_SET_ERR_MSG(extack, "ETS quantum cannot be zero"); - return -EINVAL; - } + *quantum = clamp_t(u32, nla_get_u32(attr), 256, 1 << 20); return 0; } @@ -632,11 +628,13 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, return err; } /* If there are more bands than strict + quanta provided, the remaining - * ones are ETS with quantum of MTU. Initialize the missing values here. + * ones are ETS with quantum of max(MTU, 256). Initialize the missing + * values here. */ for (i = nstrict; i < nbands; i++) { if (!quanta[i]) - quanta[i] = psched_mtu(qdisc_dev(sch)); + quanta[i] = clamp_t(u32, (u32)psched_mtu(qdisc_dev(sch)), + 256, 1 << 20); } /* Before commit, make sure we can allocate all new qdiscs */ From 8f0229bef3cba996bd40e40aafc512150016b696 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Tue, 1 Sep 2026 17:39:30 -0400 Subject: [PATCH 0759/1198] selftests: tc-testing: update ETS test 41f5 for clamped quanta Commit "net/sched: ets: clamp quantum in parse and fallback paths" moved the quantum floor into ets_quantum_parse(), so every explicitly configured quantum is now clamped to [256, 1 << 20], not just the psched_mtu() fallback. Test 41f5 passes "quanta 4294967294 1 1" and matches the values back verbatim, so all three bands now differ from what it expects: before: bands 3 quanta 4294967294 1 1 after: bands 3 quanta 1048576 256 256 Update the match pattern accordingly. Signed-off-by: Jamal Hadi Salim Link: https://patch.msgid.link/QDISC-0CFC.v3.20260901204856@mojatatu.com.10 Signed-off-by: Jakub Kicinski --- tools/testing/selftests/tc-testing/tc-tests/qdiscs/ets.json | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ets.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ets.json index ee09e6d6fdf3..d2eab61c099a 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ets.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ets.json @@ -987,7 +987,7 @@ }, { "id": "41f5", - "name": "ETS offload where the sum of quanta wraps u32", + "name": "ETS offload with out-of-range quanta clamped", "category": [ "qdisc", "ets" @@ -1002,7 +1002,7 @@ "cmdUnderTest": "$TC qdisc add dev $ETH root ets quanta 4294967294 1 1", "expExitCode": "0", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc ets .*bands 3 quanta 4294967294 1 1", + "matchPattern": "qdisc ets .*bands 3 quanta 1048576 256 256", "matchCount": "1", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" From 38b6be101006d3e7af972999f45d4f1e8250587a Mon Sep 17 00:00:00 2001 From: Vineeth Karumanchi Date: Wed, 2 Sep 2026 15:58:36 +0530 Subject: [PATCH 0760/1198] net: macb: fix NULL pointer dereference on unbind with fixed-link When the device tree describes a fixed-link and has no "mdio" child node, macb_mii_init() returns early without allocating the MDIO bus, leaving bp->mii_bus as NULL. Two cleanup paths then dereference this NULL bus: 1. On driver unbind, macb_remove() unconditionally calls mdiobus_unregister(bp->mii_bus), which oopses: Unable to handle kernel NULL pointer dereference at virtual address 00000000000004a8 pc : mdiobus_unregister+0x14/0xa4 lr : macb_remove+0x38/0xa4 Call trace: mdiobus_unregister+0x14/0xa4 (P) macb_remove+0x38/0xa4 platform_remove+0x20/0x30 device_release_driver_internal+0x1c8/0x224 unbind_store+0xb4/0xbc 2. On the probe error path in macb_probe(), reached when macb_mii_init() has succeeded but a subsequent step fails, the err_out_unregister_mdio label runs the same unconditional cleanup. mdiobus_unregister() and mdiobus_free() do not guard against a NULL bus, so guard the calls in both macb_remove() and the probe error path. Fixes: d0c3601f2c4e ("net: macb: Avoid 20s boot delay by skipping MDIO bus registration for fixed-link PHY") Signed-off-by: Vineeth Karumanchi Reviewed-by: Xuanqiang Luo Reviewed-by: Nicolai Buchwitz Link: https://patch.msgid.link/20260902102836.2019355-1-vineeth.karumanchi@amd.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/cadence/macb_main.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index b1939da4c95a..8469df0d89c3 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -5976,8 +5976,10 @@ static int macb_probe(struct platform_device *pdev) macb_free_tieoff(bp); err_out_unregister_mdio: - mdiobus_unregister(bp->mii_bus); - mdiobus_free(bp->mii_bus); + if (bp->mii_bus) { + mdiobus_unregister(bp->mii_bus); + mdiobus_free(bp->mii_bus); + } err_out_phy_exit: phy_exit(bp->phy); @@ -6006,8 +6008,10 @@ static void macb_remove(struct platform_device *pdev) unregister_netdev(netdev); macb_free_tieoff(bp); phy_exit(bp->phy); - mdiobus_unregister(bp->mii_bus); - mdiobus_free(bp->mii_bus); + if (bp->mii_bus) { + mdiobus_unregister(bp->mii_bus); + mdiobus_free(bp->mii_bus); + } device_set_wakeup_enable(&bp->pdev->dev, 0); cancel_delayed_work_sync(&bp->tx_lpi_work); From c6709d5e14072d0e3d02f291daee46a199e5dad3 Mon Sep 17 00:00:00 2001 From: Younes Akhouayri Date: Sat, 5 Sep 2026 17:16:51 +0200 Subject: [PATCH 0761/1198] rust: num: seal Integer Bounded relies on Integer implementations to describe primitive integer semantics correctly. In particular, it uses Integer::BITS and Signedness to justify unchecked operations. Integer is currently safe and externally implementable, so an implementation can violate those assumptions and make safe Bounded operations reach undefined behavior. For example, an Integer implementation for a u8 wrapper can report BITS = 16. Safe code can then cast a Bounded containing 256 to that wrapper. Its TryFrom implementation returns Err, and Bounded::cast() calls unwrap_unchecked() on it, causing undefined behavior. Seal Integer so only the primitive implementations provided by the kernel crate can satisfy it. Fixes: 01e345e82ec3 ("rust: num: add Bounded integer wrapping type") Reported-by: Miguel Ojeda Closes: https://lore.kernel.org/rust-for-linux/CANiq72mOfR33s4y+Ueivd5NrC5yre+Pcp57ZOBz0msw9A4AP1Q@mail.gmail.com/ Cc: stable@vger.kernel.org Suggested-by: Miguel Ojeda Signed-off-by: Younes Akhouayri Acked-by: Alexandre Courbot Link: https://patch.msgid.link/20260905-feature-rust-num-seal-integer-v2-1-f1311ffbe6e7@younes.io Signed-off-by: Miguel Ojeda --- rust/kernel/num.rs | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/rust/kernel/num.rs b/rust/kernel/num.rs index dbe848e30efe..de589792a77a 100644 --- a/rust/kernel/num.rs +++ b/rust/kernel/num.rs @@ -15,9 +15,14 @@ pub enum Unsigned {} /// Designates signed primitive types. pub enum Signed {} +mod private { + pub trait Sealed {} +} + /// Describes core properties of integer types. pub trait Integer: - Sized + private::Sealed + + Sized + Copy + Clone + PartialEq @@ -56,6 +61,8 @@ pub trait Integer: macro_rules! impl_integer { ($($type:ty: $signedness:ty), *) => { $( + impl private::Sealed for $type {} + impl Integer for $type { type Signedness = $signedness; From c3fd8e5fd100f122bad503bdc0e9277219533253 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Sat, 5 Sep 2026 03:47:33 +0200 Subject: [PATCH 0762/1198] bpf: Reject non-scalar bpf_loop iteration counts bpf_loop() declares its nr_loops argument as ARG_ANYTHING. Privileged programs may pass pointer values to such arguments, so check_func_arg() lets a pointer-valued R1 reach the helper-specific checks. Since commit bb124da69c47 ("bpf: keep track of max number of bpf_loop callback iterations"), the verifier marks R1 precise and reads its upper bound to limit callback simulation. Precision backtracking only accepts scalar registers, so passing a pointer instead triggers the "backtracking misuse" verifier warning. Kernels with panic_on_warn enabled subsequently panic. Introduce ARG_SCALAR for helper arguments that only accept scalar values and use it for bpf_loop() nr_loops. Generic helper argument validation then rejects pointers before loop inlining and precision processing. Fixes: bb124da69c47 ("bpf: keep track of max number of bpf_loop callback iterations") Reported-by: syzbot+7b47f87674e9a1569110@syzkaller.appspotmail.com Signed-off-by: Kumar Kartikeya Dwivedi Link: https://patch.msgid.link/20260905014735.1452988-2-memxor@gmail.com Closes: https://lore.kernel.org/bpf/6a9ad24c.b5d4176b.238c3e.0001.GAE@google.com/ Signed-off-by: Eduard Zingerman --- include/linux/bpf.h | 1 + kernel/bpf/bpf_iter.c | 2 +- kernel/bpf/verifier.c | 1 + 3 files changed, 3 insertions(+), 1 deletion(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b7dbf3d9b5c0..e57af902560c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -894,6 +894,7 @@ enum bpf_arg_type { ARG_PTR_TO_CTX, /* pointer to context */ ARG_ANYTHING, /* any (initialized) argument is ok */ + ARG_SCALAR, /* scalar argument */ ARG_PTR_TO_SPIN_LOCK, /* pointer to bpf_spin_lock */ ARG_PTR_TO_SOCK_COMMON, /* pointer to sock_common */ ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */ diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index 14a5fdfa0421..b40eb404adab 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -754,7 +754,7 @@ const struct bpf_func_proto bpf_loop_proto = { .func = bpf_loop, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_ANYTHING, + .arg1_type = ARG_SCALAR, .arg2_type = ARG_PTR_TO_FUNC, .arg3_type = ARG_PTR_TO_STACK_OR_NULL, .arg4_type = ARG_ANYTHING, diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1c3039f3fc32..4638a2f85d0f 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8211,6 +8211,7 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = { [ARG_MEM_SIZE] = &scalar_types, [ARG_MEM_SIZE_OR_ZERO] = &scalar_types, [ARG_CONST_ALLOC_SIZE_OR_ZERO] = &scalar_types, + [ARG_SCALAR] = &scalar_types, [ARG_CONST_MAP_PTR] = &const_map_ptr_types, [ARG_PTR_TO_CTX] = &context_types, [ARG_PTR_TO_SOCK_COMMON] = &sock_types, From bde8901ea14244e7195a2d6b6aa2023b28d4233c Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Sat, 5 Sep 2026 03:47:34 +0200 Subject: [PATCH 0763/1198] selftests/bpf: Test pointer bpf_loop iteration count rejection Add a verifier test that leaves the raw tracepoint context pointer in R1 when calling bpf_loop(). This is the smallest trigger for the incorrect precision backtracking: it reuses an existing callback and needs no maps or userspace setup. Expect an ordinary scalar-type rejection. Without the verifier fix, the test instead reaches precision backtracking and reports an internal "backtracking misuse" error. Signed-off-by: Kumar Kartikeya Dwivedi Acked-by: Eduard Zingerman Link: https://patch.msgid.link/20260905014735.1452988-3-memxor@gmail.com Signed-off-by: Eduard Zingerman --- .../bpf/progs/verifier_iterating_callbacks.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c index 75dd922e4e9f..1fbcc5228306 100644 --- a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c +++ b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c @@ -168,6 +168,23 @@ static int iter_limit_cb(__u32 idx, struct num_context *ctx) return 0; } +SEC("?raw_tp") +__failure __msg("R1 type=ctx expected=scalar") +__naked void bpf_loop_reject_pointer(void) +{ + asm volatile ( + "r2 = %[iter_limit_cb];" + "r3 = 0;" + "r4 = 0;" + "call %[bpf_loop];" + "exit;" + : + : __imm_ptr(iter_limit_cb), + __imm(bpf_loop) + : __clobber_common + ); +} + SEC("?raw_tp") __success int bpf_loop_iter_limit_ok(void *unused) From 536b523b407397c8d3967c020ce7aad70a0ea030 Mon Sep 17 00:00:00 2001 From: Chen Pei Date: Wed, 2 Sep 2026 14:14:51 +0800 Subject: [PATCH 0764/1198] bpf, riscv: Make arena support depend on ZACAS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The arena range tree allocates its nodes with kmalloc_nolock() since commit f8c67d8550ee ("bpf: Use kmalloc_nolock() in range tree"). kmalloc_nolock() requires slab caches with cmpxchg128 support (__CMPXCHG_DOUBLE); on riscv cmpxchg128 is provided by the ZACAS extension. On systems without ZACAS every arena map creation fails with a misleading -ENOMEM. Report the missing support instead: make bpf_jit_supports_arena() return system_has_cmpxchg128() where it is defined, so arena map creation fails with -EOPNOTSUPP on systems without ZACAS. The macro is only defined when both CONFIG_RISCV_ISA_ZACAS and CONFIG_TOOLCHAIN_HAS_ZACAS are enabled, so guard it with #ifdef the same way mm/slab.h consumes it, and reject arena otherwise. This matches how arena BPF_CMPXCHG instructions are already gated on ZACAS in bpf_jit_supports_insn(). Fixes: f8c67d8550ee ("bpf: Use kmalloc_nolock() in range tree") Signed-off-by: Chen Pei Acked-by: Pu Lehui Acked-by: Björn Töpel Cc: stable@vger.kernel.org Link: https://lore.kernel.org/bpf/20260902061451.1416-1-cp0613@linux.alibaba.com Signed-off-by: Kumar Kartikeya Dwivedi --- arch/riscv/net/bpf_jit_comp64.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 74efe4b138d2..151031e97a24 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -2128,7 +2128,15 @@ bool bpf_jit_supports_ptr_xchg(void) bool bpf_jit_supports_arena(void) { - return true; + /* + * The arena range tree uses kmalloc_nolock(), which needs + * cmpxchg128, provided by ZACAS on riscv. + */ +#ifdef system_has_cmpxchg128 + return system_has_cmpxchg128(); +#else + return false; +#endif } bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena) From df2908090cda368b01ff43709f51890076c56157 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 6 Sep 2026 15:07:20 -0700 Subject: [PATCH 0765/1198] Linux 7.3-rc2 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 4ad67b737af7..66654fa71655 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 7 PATCHLEVEL = 3 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Baby Opossum Posse # *DOCUMENTATION* From 2ac74c6db40adaa29c50cbb281ae9a6f63de18e1 Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Sun, 6 Sep 2026 14:58:22 -0700 Subject: [PATCH 0766/1198] rust: allow `clippy::as_underscore` in the generated bindings A CLIPPY=1 build emitted about 15000 `as _` conversion warnings, all of them in bindgen's generated output and none in hand-written code. [ The lint messages look like: error: using `as _` conversion --> rust/bindings/bindings_generated.rs:18947:9 | 18947 | self._bitfield_1.get_const::<0usize, 16u8>() as u32 as _ | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^- | | | help: consider giving the type explicitly: `u32` | = help: for further information visit https://rust-lang.github.io/rust-clippy/rust-1.98.0/index.html#as_underscore = note: `-D clippy::as-underscore` implied by `-D warnings` = help: to override `-D warnings` add `#[allow(clippy::as_underscore)]` - Miguel ] bindgen 0.73 returns each bitfield read through a trailing `as _`, and 0.72 returns it through a transmute, which the lint ignores. The bindings and uapi crates allow `clippy::all` over the generated code. That group does not cover `clippy::as_underscore`, a restriction lint. Allow `clippy::as_underscore` by name in the bindings and uapi crates. Assisted-by: LLM Signed-off-by: John Hubbard Link: https://patch.msgid.link/20260906215822.1201022-1-jhubbard@nvidia.com Cc: stable@vger.kernel.org # Needed in 6.12.y and later (Rust is pinned in older LTSs). [ Removed CI sentence. - Miguel ] Signed-off-by: Miguel Ojeda --- rust/bindings/lib.rs | 1 + rust/uapi/lib.rs | 1 + 2 files changed, 2 insertions(+) diff --git a/rust/bindings/lib.rs b/rust/bindings/lib.rs index 812f8e5a08d5..ad24c920b919 100644 --- a/rust/bindings/lib.rs +++ b/rust/bindings/lib.rs @@ -22,6 +22,7 @@ #![feature(cfi_encoding)] #[allow(dead_code)] +#[allow(clippy::as_underscore)] #[allow(clippy::cast_lossless)] #[allow(clippy::ptr_as_ptr)] #[allow(clippy::ref_as_ptr)] diff --git a/rust/uapi/lib.rs b/rust/uapi/lib.rs index 797ead5b5626..2df0340e63d1 100644 --- a/rust/uapi/lib.rs +++ b/rust/uapi/lib.rs @@ -10,6 +10,7 @@ #![no_std] #![allow( clippy::all, + clippy::as_underscore, clippy::cast_lossless, clippy::ptr_as_ptr, clippy::ref_as_ptr, From 5ba79d37403d86082ab4083b0f51ec3008a942cb Mon Sep 17 00:00:00 2001 From: Thorsten Blum Date: Fri, 3 Jul 2026 18:58:35 +0200 Subject: [PATCH 0767/1198] powerpc/ps3: Fix repository.c build failure MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit GCC fails to build ps3_defconfig with the following errors: arch/powerpc/platforms/ps3/repository.c: In function ‘make_first_field.constprop’: arch/powerpc/platforms/ps3/repository.c:78:9: error: ‘strnlen’ specified bound 8 exceeds source size 3 [-Werror=stringop-overread] 78 | memcpy((char *)&n, text, strnlen(text, sizeof(n))); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ arch/powerpc/platforms/ps3/repository.c: In function ‘make_first_field.constprop’: arch/powerpc/platforms/ps3/repository.c:78:9: error: ‘strnlen’ specified bound 8 exceeds source size 4 [-Werror=stringop-overread] 78 | memcpy((char *)&n, text, strnlen(text, sizeof(n))); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ The current use of strnlen(text, sizeof(n)) triggers -Wstringop-overread when text is a short string literal that is smaller than sizeof(n), such as "bi" or "bus". Use strlen(text) instead and clamp the copy length to sizeof(n) before memcpy(). Drop the redundant char * cast while at it. Fixes: f94a84a09148 ("powerpc/ps3: refactor strncpy usage") Cc: stable@vger.kernel.org Signed-off-by: Thorsten Blum Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260703165834.137242-2-thorsten.blum@linux.dev --- arch/powerpc/platforms/ps3/repository.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/platforms/ps3/repository.c b/arch/powerpc/platforms/ps3/repository.c index b8c030eab138..0cc755ac3e7f 100644 --- a/arch/powerpc/platforms/ps3/repository.c +++ b/arch/powerpc/platforms/ps3/repository.c @@ -6,6 +6,8 @@ * Copyright 2006 Sony Corp. */ +#include + #include #include "platform.h" @@ -74,8 +76,9 @@ static void _dump_node(unsigned int lpar_id, u64 n1, u64 n2, u64 n3, u64 n4, static u64 make_first_field(const char *text, u64 index) { u64 n = 0; + size_t len = min(strlen(text), sizeof(n)); - memcpy((char *)&n, text, strnlen(text, sizeof(n))); + memcpy(&n, text, len); return PS3_VENDOR_ID_NONE + (n >> 32) + index; } From f789d291bbdac6bc02d9d77e0141e138626c17a8 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Thu, 20 Aug 2026 20:58:06 -0700 Subject: [PATCH 0768/1198] xfs: fix media verification ioctl for internal rt volumes A media scan of a filesystem containing an internal rt volume produced an error in xfs_scrub phase 6 complaining about a truncated realtime device. The rt device wasn't truncated, but the media scan code thought we were trying to start a scan past the end of m_rtdev_targp. That in turn is an alias for m_ddev_targp, but in xfs_configure_buftarg we set nr_sectors to the size of the data section. We don't account for an internal realtime section, so the kernel doesn't scan any part of it. Oops. Reproducer: # mkfs.xfs -f /dev/sda -r zoned=1 -d rtinherit=1 # mount /dev/sda /mnt # dd if=/dev/zero of=/mnt/a bs=1024k count=100 # sync # xfs_info /mnt meta-data=/dev/sda isize=512 agcount=4, agsize=32768 blks = sectsz=512 attr=2, projid32bit=1 = crc=1 finobt=1, sparse=1, rmapbt=1 = reflink=0 bigtime=1 inobtcount=1 nrext64=1 = exchange=1 metadir=1 data = bsize=4096 blocks=131072, imaxpct=25 = sunit=0 swidth=0 blks naming =version 2 bsize=4096 ascii-ci=0, ftype=1, parent=1 log =internal log bsize=4096 blocks=16384, version=2 = sectsz=512 sunit=0 blks, lazy-count=1 realtime =internal extsz=4096 blocks=1114112, rtextents=1114112 = rgcount=17 rgsize=65536 extents = zoned=1 start=131072 reserved=53248 IOWS: 512M data volume, 3.1G internal rt section. Now let's try some media verification: # xfs_io -c 'verifymedia -d' -c 'verifymedia -r' /mnt verified 536870912/536870912 bytes at offset 0 512 MiB, 1 ops; 0.0496 sec (10.067 GiB/sec and 20.1345 ops/sec) verified 536870912/536870912 bytes at offset 0 512 MiB, 1 ops; 0.0409 sec (12.222 GiB/sec and 24.4439 ops/sec) Notice how xfs_io says we only verified 512M of the rt volume? If you run btrace in the background you'll see that we read the first 512M of the volume (aka the data section) twice and never read anything from the rt section. An earlier fix tried messing with the buftarg geometry, but I've decided on a more targetted fix for the media verification code. All we have to do is calculate the starting and ending daddr for the device that we're verifying, and clamp the user's input values to that range. This leads to some bogosity in the output reporting: # xfs_io -c 'verifymedia -d' -c 'verifymedia -r' /mnt/t verified 536870912/536870912 bytes at offset 0 512 MiB, 1 ops; 0.0606 sec (8.248 GiB/sec and 16.4968 ops/sec) verified 5100273664/5100273664 bytes at offset 0 4.750 GiB, 1 ops; 0.3329 sec (14.267 GiB/sec and 3.0035 ops/sec) Because we don't have a way to report that we didn't really do anything at all for that first 512M of address space of the rt "device". But at least we're no longer ignoring real media. (Note that the fsmap/bmap/fiemap calls all report physical addresses for the internal rt volume as offsets from the start of the data device, and the media verifier call consumes the same. We baked that into the user-visible behavior in 6.15, so we're stuck with that sparse hole at the beginning.) Cc: stable@vger.kernel.org # v6.15 Fixes: bdc03eb5f98f6f ("xfs: allow internal RT devices for zoned mode") Signed-off-by: Darrick J. Wong Reviewed-by: Carlos Maiolino Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_verify_media.c | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-) diff --git a/fs/xfs/xfs_verify_media.c b/fs/xfs/xfs_verify_media.c index 5ead3976d511..b75c81f8fcc0 100644 --- a/fs/xfs/xfs_verify_media.c +++ b/fs/xfs/xfs_verify_media.c @@ -268,6 +268,8 @@ xfs_verify_media( struct xfs_buftarg *btp = NULL; struct bio *bio; struct folio *folio; + xfs_daddr_t dev_start = 0; + xfs_daddr_t dev_end = 0; xfs_daddr_t daddr; uint64_t bbcount; int error = 0; @@ -277,24 +279,33 @@ xfs_verify_media( switch (me->me_dev) { case XFS_DEV_DATA: btp = mp->m_ddev_targp; + dev_end = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks); break; case XFS_DEV_LOG: - if (mp->m_logdev_targp != mp->m_ddev_targp) + if (mp->m_logdev_targp != mp->m_ddev_targp) { btp = mp->m_logdev_targp; + dev_end = XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks); + } break; case XFS_DEV_RT: btp = mp->m_rtdev_targp; + dev_start = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rtstart); + dev_end = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rtstart + + mp->m_sb.sb_rblocks); break; } if (!btp) return -ENODEV; /* - * If the caller told us to verify beyond the end of the disk, tell the - * user exactly where that was. + * If the caller told us to verify before the start or beyond the end + * of the disk volume, tell the user exactly where the volume starts + * and ends. */ - if (me->me_end_daddr > btp->bt_nr_sectors) - me->me_end_daddr = btp->bt_nr_sectors; + if (me->me_end_daddr > dev_end) + me->me_end_daddr = dev_end; + if (me->me_start_daddr < dev_start) + me->me_start_daddr = dev_start; /* start and end have to be aligned to the lba size */ if (!IS_ALIGNED(BBTOB(me->me_start_daddr | me->me_end_daddr), @@ -323,8 +334,7 @@ xfs_verify_media( * verifying. */ daddr = me->me_start_daddr; - bbcount = min_t(sector_t, me->me_end_daddr, btp->bt_nr_sectors) - - me->me_start_daddr; + bbcount = me->me_end_daddr - me->me_start_daddr; folio = xfs_verify_alloc_folio(xfs_verify_iosize(me, btp, bbcount)); if (!folio) From ff99a5f6cbcc9c4810a8dac46fe76473539513f9 Mon Sep 17 00:00:00 2001 From: Hans Holmberg Date: Wed, 26 Aug 2026 14:32:19 +0200 Subject: [PATCH 0769/1198] xfs: prevent race in zoned space reservations xfs_zoned_add_available() checks whether the reservation list is empty before adding blocks to the available-space counter. This check is not serialized against a task adding itself to the reservation list however. This allows the space provider to observe an empty list, after which a reserver can enqueue itself and retry the counter before the new space is added. The provider then adds the space and returns without waking the now-eligible reserver, leaving it asleep until GC or another event provides a wakeup, potentially adding seconds to max write latency. Take the reservation lock before updating the counter and checking the list. Use list_empty() because the list is now inspected under its lock. Taking a per-mount lock when handing back space is far from ideal, but benchmarking with null_blk showed no measurable performance regression. Fixes: 0bb2193056b5 ("xfs: add support for zoned space reservations") Reported-by: Sashiko Closes: https://sashiko.dev/#/patchset/20260609075655.1698743-1-hch@lst.de?part=2 Signed-off-by: Hans Holmberg Reviewed-by: Carlos Maiolino Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_zone_space_resv.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/fs/xfs/xfs_zone_space_resv.c b/fs/xfs/xfs_zone_space_resv.c index 5c6e6ef627e4..7aa3c74fb2e0 100644 --- a/fs/xfs/xfs_zone_space_resv.c +++ b/fs/xfs/xfs_zone_space_resv.c @@ -85,13 +85,13 @@ xfs_zoned_add_available( struct xfs_zone_info *zi = mp->m_zone_info; struct xfs_zone_reservation *reservation; - if (list_empty_careful(&zi->zi_reclaim_reservations)) { - xfs_add_freecounter(mp, XC_FREE_RTAVAILABLE, count_fsb); + spin_lock(&zi->zi_reservation_lock); + xfs_add_freecounter(mp, XC_FREE_RTAVAILABLE, count_fsb); + if (list_empty(&zi->zi_reclaim_reservations)) { + spin_unlock(&zi->zi_reservation_lock); return; } - spin_lock(&zi->zi_reservation_lock); - xfs_add_freecounter(mp, XC_FREE_RTAVAILABLE, count_fsb); count_fsb = xfs_sum_freecounter(mp, XC_FREE_RTAVAILABLE); list_for_each_entry(reservation, &zi->zi_reclaim_reservations, entry) { if (reservation->count_fsb > count_fsb) From a23eca88448e52eb1a81549862df7adce794fafb Mon Sep 17 00:00:00 2001 From: Lin Jiapeng Date: Tue, 28 Jul 2026 15:19:10 +0800 Subject: [PATCH 0770/1198] xfs: fix exchange-range reflink flag clearing issue with INO1_WRITTEN When exchanging two full-file ranges, xmi_can_exchange_reflink_flags() can move the reflink inode flag from the file that currently has it to the other file, as long as exactly one side is marked. This assumes that the file contents, and therefore all shared extents, are exchanged. That assumption is not true when XFS_EXCHMAPS_INO1_WRITTEN is set. xfs_exchmaps_can_skip_mapping() can skip hole and unwritten mappings from file1, so an exchange can complete without moving every mapping that the earlier flag-swap decision accounted for. In that case the post-operation cleanup can clear the reflink flag from an inode that still owns shared written extents. Later writes then take the non-reflink write path and may update blocks that should still have been protected by CoW, which shows up as data corruption between reflink-related files. Fix this by disabling the reflink flag exchange whenever XFS_EXCHMAPS_INO1_WRITTEN is requested. The contents exchange can still proceed; the conservative outcome is that both inodes keep the reflink flag. The regular reflink flag cleanup path can drop the extra flag later once the inode no longer has shared extents. Reported-by: Lin Jiapeng (TencentOS Red Team) Fixes: 966ceafc7a43 ("xfs: create deferred log items for file mapping exchanges") Cc: stable@vger.kernel.org # v6.10 Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Lin Jiapeng Signed-off-by: Carlos Maiolino --- fs/xfs/libxfs/xfs_exchmaps.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/fs/xfs/libxfs/xfs_exchmaps.c b/fs/xfs/libxfs/xfs_exchmaps.c index 3efed37cb98a..49eda8d0994d 100644 --- a/fs/xfs/libxfs/xfs_exchmaps.c +++ b/fs/xfs/libxfs/xfs_exchmaps.c @@ -959,6 +959,16 @@ xmi_can_exchange_reflink_flags( { struct xfs_mount *mp = req->ip1->i_mount; + /* + * The INO1_WRITTEN optimization can skip exchanging hole and + * unwritten mappings, which means we cannot guarantee that all + * shared extents actually moved to the other file. Clearing the + * reflink flag of an inode that still holds shared extents breaks + * the CoW write path, so refuse to exchange the flags in that case. + */ + if (req->flags & XFS_EXCHMAPS_INO1_WRITTEN) + return false; + /* * The INO1_WRITTEN optimization can skip exchanging hole and * unwritten mappings, which means we cannot guarantee that all From cf3a01684f323dd905d83230b7cb705fabdbcb7b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 20 Jul 2026 11:45:38 +0200 Subject: [PATCH 0771/1198] xfs: fix the lock annotation on xfs_iget_cache_hit The newer clang context analysis requires __releases_shared for the RCU pseudo-lock. Signed-off-by: Christoph Hellwig Reviewed-by: Carlos Maiolino Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_icache.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index a857b8aa255c..82dac88e3c4c 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -497,7 +497,8 @@ xfs_iget_cache_hit( struct xfs_inode *ip, xfs_ino_t ino, int flags, - int lock_flags) __releases(RCU) + int lock_flags) + __releases_shared(RCU) { struct inode *inode = VFS_I(ip); struct xfs_mount *mp = ip->i_mount; From 2078c2d6e1748df6c4c2b28f06797cba4ecda85c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 20 Jul 2026 11:45:39 +0200 Subject: [PATCH 0772/1198] xfs: fix the lock annotation in xfs_extent_busy_update_extent Name the correct lock. Signed-off-by: Christoph Hellwig Reviewed-by: Carlos Maiolino Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_extent_busy.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c index 41cf0605ec22..6da8c1f938aa 100644 --- a/fs/xfs/xfs_extent_busy.c +++ b/fs/xfs/xfs_extent_busy.c @@ -161,8 +161,8 @@ xfs_extent_busy_update_extent( xfs_agblock_t fbno, xfs_extlen_t flen, bool userdata) - __releases(&eb->eb_lock) - __acquires(&eb->eb_lock) + __releases(&xg->xg_busy_extents->eb_lock) + __acquires(&xg->xg_busy_extents->eb_lock) { struct xfs_extent_busy_tree *eb = xg->xg_busy_extents; xfs_agblock_t fend = fbno + flen; From b2ae7f243583e795b1eb3f8977cccfd7e37a8dfc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 20 Jul 2026 11:45:40 +0200 Subject: [PATCH 0773/1198] xfs: fix the lock annotation in xfs_mru_cache_lookup Name the actual lock. Unlike sparse, clang wants the annotation to be correct. Signed-off-by: Christoph Hellwig Reviewed-by: Carlos Maiolino Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_mru_cache.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/xfs_mru_cache.c b/fs/xfs/xfs_mru_cache.c index d61ec8cb126d..3f3af2e2e31c 100644 --- a/fs/xfs/xfs_mru_cache.c +++ b/fs/xfs/xfs_mru_cache.c @@ -520,7 +520,7 @@ xfs_mru_cache_lookup( if (elem) { list_del(&elem->list_node); _xfs_mru_cache_list_insert(mru, elem); - __release(mru_lock); /* help sparse not be stupid */ + __release(&mru->lock); } else spin_unlock(&mru->lock); From 64e1f211d97b42f6e12bef8e6decc207f8871a2d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 20 Jul 2026 11:45:41 +0200 Subject: [PATCH 0774/1198] xfs: improve lock annotations in the log code Improve the __acquires and __releases annotations so that the new clang code that is a bit more picky than sparse is happy. This involves passing an explicit struct xlog argument in a few places because alias analysis can't figure out it is the same lock when dereferencing changing iclogs. Signed-off-by: Christoph Hellwig Reviewed-by: Carlos Maiolino Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_log.c | 31 +++++++++++++++++++------------ fs/xfs/xfs_log_cil.c | 2 +- fs/xfs/xfs_log_priv.h | 4 ++-- 3 files changed, 22 insertions(+), 15 deletions(-) diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index f807f8f4f705..0294ac277f35 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -470,6 +470,8 @@ xlog_state_release_iclog( struct xlog *log, struct xlog_in_core *iclog, struct xlog_ticket *ticket) + __releases(&log->l_icloglock) + __acquires(&log->l_icloglock) { bool last_ref; @@ -744,13 +746,16 @@ xfs_log_mount_cancel( */ static inline int xlog_force_iclog( + struct xlog *log, struct xlog_in_core *iclog) + __releases(&log->l_icloglock) + __acquires(&log->l_icloglock) { atomic_inc(&iclog->ic_refcnt); iclog->ic_flags |= XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA; if (iclog->ic_state == XLOG_STATE_ACTIVE) - xlog_state_switch_iclogs(iclog->ic_log, iclog, 0); - return xlog_state_release_iclog(iclog->ic_log, iclog, NULL); + xlog_state_switch_iclogs(log, iclog, 0); + return xlog_state_release_iclog(log, iclog, NULL); } /* @@ -778,11 +783,10 @@ xlog_wait_iclog_completion(struct xlog *log) */ int xlog_wait_on_iclog( + struct xlog *log, struct xlog_in_core *iclog) - __releases(iclog->ic_log->l_icloglock) + __releases(log->l_icloglock) { - struct xlog *log = iclog->ic_log; - trace_xlog_iclog_wait_on(iclog, _RET_IP_); if (!xlog_is_shutdown(log) && iclog->ic_state != XLOG_STATE_ACTIVE && @@ -879,8 +883,8 @@ xlog_unmount_write( spin_lock(&log->l_icloglock); iclog = log->l_iclog; - error = xlog_force_iclog(iclog); - xlog_wait_on_iclog(iclog); + error = xlog_force_iclog(log, iclog); + xlog_wait_on_iclog(log, iclog); if (tic) { trace_xfs_log_umount_write(log, tic); @@ -2741,14 +2745,17 @@ xlog_state_switch_iclogs( */ static int xlog_force_and_check_iclog( + struct xlog *log, struct xlog_in_core *iclog, bool *completed) + __releases(&log->l_icloglock) + __acquires(&log->l_icloglock) { xfs_lsn_t lsn = be64_to_cpu(iclog->ic_header->h_lsn); int error; *completed = false; - error = xlog_force_iclog(iclog); + error = xlog_force_iclog(log, iclog); if (error) return error; @@ -2825,7 +2832,7 @@ xfs_log_force( /* We have exclusive access to this iclog. */ bool completed; - if (xlog_force_and_check_iclog(iclog, &completed)) + if (xlog_force_and_check_iclog(log, iclog, &completed)) goto out_error; if (completed) @@ -2850,7 +2857,7 @@ xfs_log_force( iclog->ic_flags |= XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA; if (flags & XFS_LOG_SYNC) - return xlog_wait_on_iclog(iclog); + return xlog_wait_on_iclog(log, iclog); out_unlock: spin_unlock(&log->l_icloglock); return 0; @@ -2920,7 +2927,7 @@ xlog_force_lsn( &log->l_icloglock); return -EAGAIN; } - if (xlog_force_and_check_iclog(iclog, &completed)) + if (xlog_force_and_check_iclog(log, iclog, &completed)) goto out_error; if (log_flushed) *log_flushed = 1; @@ -2948,7 +2955,7 @@ xlog_force_lsn( } if (flags & XFS_LOG_SYNC) - return xlog_wait_on_iclog(iclog); + return xlog_wait_on_iclog(log, iclog); out_unlock: spin_unlock(&log->l_icloglock); return 0; diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index 639f875a8fb2..ae1ed16aeb2f 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -1556,7 +1556,7 @@ xlog_cil_push_work( * iclogs older than ic_prev. Hence we only need to wait * on the most recent older iclog here. */ - xlog_wait_on_iclog(ctx->commit_iclog->ic_prev); + xlog_wait_on_iclog(log, ctx->commit_iclog->ic_prev); spin_lock(&log->l_icloglock); } diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index cf1e4ce61a8c..6d9673c41cdf 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -605,8 +605,8 @@ xlog_wait( remove_wait_queue(wq, &wait); } -int xlog_wait_on_iclog(struct xlog_in_core *iclog) - __releases(iclog->ic_log->l_icloglock); +int xlog_wait_on_iclog(struct xlog *log, struct xlog_in_core *iclog) + __releases(log->l_icloglock); /* Calculate the distance between two LSNs in bytes */ static inline uint64_t From 912a5b8e344ad1e3cb6aefedf243404d522ad822 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 20 Jul 2026 11:45:42 +0200 Subject: [PATCH 0775/1198] xfs: add lock annotations to xfs_try_open_zone Improve the __acquires and __releases annotations so that the new clang code that is a bit more picky than sparse is happy. Signed-off-by: Christoph Hellwig Reviewed-by: Carlos Maiolino Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_zone_alloc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c index bdbb60cc5d5b..28c1e48909fa 100644 --- a/fs/xfs/xfs_zone_alloc.c +++ b/fs/xfs/xfs_zone_alloc.c @@ -475,6 +475,8 @@ static struct xfs_open_zone * xfs_try_open_zone( struct xfs_mount *mp, enum rw_hint write_hint) + __releases(&mp->m_zone_info->zi_open_zones_lock) + __acquires(&mp->m_zone_info->zi_open_zones_lock) { struct xfs_zone_info *zi = mp->m_zone_info; struct xfs_open_zone *oz; From 2d1b21fcc9f9463f939103d13d6a0bf05a529901 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 20 Jul 2026 11:45:43 +0200 Subject: [PATCH 0776/1198] xfs: add lock annotations to xlog_state_shutdown_callbacks Sparse used to get away without these despite dropping and reacquiring l_icloglock Signed-off-by: Christoph Hellwig Reviewed-by: Carlos Maiolino Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_log.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 0294ac277f35..2a34611d81f6 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -422,6 +422,8 @@ xfs_log_reserve( static void xlog_state_shutdown_callbacks( struct xlog *log) + __releases(&log->l_icloglock) + __acquires(&log->l_icloglock) { struct xlog_in_core *iclog; LIST_HEAD(cb_list); From 166089a856859d5f3e2b85c6ffd70da084238439 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 20 Jul 2026 11:45:44 +0200 Subject: [PATCH 0777/1198] xfs: add a lock annotation to xlog_cil_push_background This is required to make the clang context analysis happy, which is more strict than the old sparse lock context tracking. Signed-off-by: Christoph Hellwig Reviewed-by: Carlos Maiolino Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_log_cil.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index ae1ed16aeb2f..166531018ce4 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -1627,6 +1627,7 @@ xlog_cil_push_work( static void xlog_cil_push_background( struct xlog *log) + __releases_shared(&log->l_cilp->xc_ctx_lock) { struct xfs_cil *cil = log->l_cilp; int space_used = atomic_read(&cil->xc_ctx->space_used); From ed4abd8617ba348802575a0ae8e01e6c0f7eb2cf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 20 Jul 2026 11:45:45 +0200 Subject: [PATCH 0778/1198] xfs: add lock annotations to xfs_ail_delete* Pass up the __must_hold as clang requires it, and also fix the formatting of the __must_hold on xfs_ail_check to match how we do it elsewhere. Signed-off-by: Christoph Hellwig Reviewed-by: Carlos Maiolino Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_trans_ail.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index 99a9bf3762b7..f955479a08fd 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -33,7 +33,7 @@ STATIC void xfs_ail_check( struct xfs_ail *ailp, struct xfs_log_item *lip) - __must_hold(&ailp->ail_lock) + __must_hold(&ailp->ail_lock) { struct xfs_log_item *prev_lip; struct xfs_log_item *next_lip; @@ -321,6 +321,7 @@ static void xfs_ail_delete( struct xfs_ail *ailp, struct xfs_log_item *lip) + __must_hold(&ailp->ail_lock) { xfs_ail_check(ailp, lip); list_del(&lip->li_ail); @@ -899,6 +900,7 @@ xfs_lsn_t xfs_ail_delete_one( struct xfs_ail *ailp, struct xfs_log_item *lip) + __must_hold(&ailp->ail_lock) { struct xfs_log_item *mlip = xfs_ail_min(ailp); xfs_lsn_t lsn = lip->li_lsn; From 6176d21d7bd609632c5b7e87a3adb9be29ec1e72 Mon Sep 17 00:00:00 2001 From: Javier Tia Date: Mon, 10 Aug 2026 17:06:13 -0600 Subject: [PATCH 0779/1198] xfs: initialise error in xfs_defer_finish_one() xfs_defer_finish_one() declares error without an initialiser and only assigns it inside the loop over dfp->dfp_work. When that list is empty the loop body never runs, control falls through to the "Done with the dfp, free it" path, and the function returns an indeterminate value. An item-less pending item reaches this through xfs_defer_add_barrier(), which xfs_reap_ag_blocks() uses on any CONFIG_XFS_ONLINE_REPAIR kernel. xfs_defer_finish_noroll() treats any non-EAGAIN return as fatal, so a non-zero stack value turns a successful barrier into a SHUTDOWN_CORRUPT_INCORE in the middle of a repair. Zero is the correct result: reaching the free path means the item loop drained without a non-zero error. Fixes: 3f3cec031099 ("xfs: force small EFIs for reaping btree extents") Cc: stable@vger.kernel.org Signed-off-by: Javier Tia Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino --- fs/xfs/libxfs/xfs_defer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c index 89501e8bd2f8..843c33304441 100644 --- a/fs/xfs/libxfs/xfs_defer.c +++ b/fs/xfs/libxfs/xfs_defer.c @@ -583,7 +583,7 @@ xfs_defer_finish_one( const struct xfs_defer_op_type *ops = dfp->dfp_ops; struct xfs_btree_cur *state = NULL; struct list_head *li, *n; - int error; + int error = 0; trace_xfs_defer_pending_finish(tp->t_mountp, dfp); From 91c15cee394e9958898ef1ed55d9ced4c26e2800 Mon Sep 17 00:00:00 2001 From: Javier Tia Date: Mon, 10 Aug 2026 17:06:14 -0600 Subject: [PATCH 0780/1198] xfs: give the deferred barrier op type a name xfs_barrier_defer_type is the only xfs_defer_op_type with no .name. Every other one carries a short string used for tracing and reporting: attr, bmap, extent_free, agfl_free, rtextent_free, refcount, rtrefcount, rmap, rtrmap and exchmaps. That has been harmless because nothing dereferences the field, but it leaves a NULL in a table where every other entry is populated, so the first caller to print it gets "(null)" in the kernel and undefined behaviour in the userspace libxfs build of this file, where xfs_alert lands in fprintf. xfs_defer_add() already treats a missing member of this table as worth shutting the filesystem down for, so an unpopulated one is out of step with how the file handles its own ops tables. Signed-off-by: Javier Tia Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino --- fs/xfs/libxfs/xfs_defer.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c index 843c33304441..75f0d37914d5 100644 --- a/fs/xfs/libxfs/xfs_defer.c +++ b/fs/xfs/libxfs/xfs_defer.c @@ -229,6 +229,7 @@ xfs_defer_barrier_cancel_item( } static const struct xfs_defer_op_type xfs_barrier_defer_type = { + .name = "barrier", .max_items = 1, .create_intent = xfs_defer_barrier_create_intent, .abort_intent = xfs_defer_barrier_abort_intent, From d058f24b163a8d63866ac6bbe5f06b41aabe97d7 Mon Sep 17 00:00:00 2001 From: Javier Tia Date: Mon, 10 Aug 2026 17:06:15 -0600 Subject: [PATCH 0781/1198] xfs: report the error that made deferred work shut down the fs When a deferred operation fails and shuts the filesystem down, xfs_defer_finish_noroll() reports neither the errno nor which operation originated it, so the log cannot tell a transient -ENOSPC from real corruption. Report the operation type, errno and remaining reservation. trace_xfs_defer_finish_error() runs after xfs_force_shutdown(), which BUGs under fs.xfs.panic_mask and so never fires for the first failure; move it ahead of the shutdown and mirror it to xfs_alert() for systems without tracing armed. Capture the op name while the item is live (dfp is freed once its work list drains) and suppress the alert once the fs is already down. Signed-off-by: Javier Tia Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino --- fs/xfs/libxfs/xfs_defer.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c index 75f0d37914d5..3152acdc335d 100644 --- a/fs/xfs/libxfs/xfs_defer.c +++ b/fs/xfs/libxfs/xfs_defer.c @@ -656,6 +656,7 @@ xfs_defer_finish_noroll( struct xfs_trans **tp) { struct xfs_defer_pending *dfp = NULL; + const char *what = "chain"; int error = 0; LIST_HEAD(dop_pending); LIST_HEAD(dop_paused); @@ -705,9 +706,17 @@ xfs_defer_finish_noroll( struct xfs_defer_pending, dfp_list); if (!dfp) break; + what = dfp->dfp_ops->name; error = xfs_defer_finish_one(*tp, dfp); if (error && error != -EAGAIN) goto out_shutdown; + /* + * A finished item is no longer a candidate for a later + * failure. An -EAGAIN one is not finished, so it keeps the + * attribution across the roll that completes it. + */ + if (!error) + what = "chain"; } /* Requeue the paused items in the outgoing transaction. */ @@ -719,8 +728,12 @@ xfs_defer_finish_noroll( out_shutdown: list_splice_tail_init(&dop_paused, &dop_pending); xfs_defer_trans_abort(*tp, &dop_pending); - xfs_force_shutdown((*tp)->t_mountp, SHUTDOWN_CORRUPT_INCORE); trace_xfs_defer_finish_error(*tp, error); + if (!xfs_is_shutdown((*tp)->t_mountp)) + xfs_alert((*tp)->t_mountp, + "deferred %s work failed, error %d, %u blocks reserved", + what, error, (*tp)->t_blk_res); + xfs_force_shutdown((*tp)->t_mountp, SHUTDOWN_CORRUPT_INCORE); xfs_defer_cancel_list((*tp)->t_mountp, &dop_pending); xfs_defer_cancel(*tp); return error; From 6c0fc3cb4e879927b338b4fcb6de6a25c0a67608 Mon Sep 17 00:00:00 2001 From: Javier Tia Date: Mon, 10 Aug 2026 17:06:16 -0600 Subject: [PATCH 0782/1198] xfs: correct the parent pointer space reservation comment The comment on xfs_parent_calc_space_res() claims parent pointers are "always the first attr in an attr tree". They are not: a parent pointer is recorded per dirent, so by the Nth hardlink the attr fork is already in leaf or node format. The reservation is still correct, because XFS_DAENTER_SPACE_RES() covers a split at every level of a maximum-depth attr dabtree whatever format the fork is in, but anyone auditing a shortfall here is led by the comment to look for a bug that is not there. Rewrite the comment to state what actually bounds the result, and record why the double split allowance and the extent-add term differ from xfs_attr_calc_size(). Signed-off-by: Javier Tia Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino --- fs/xfs/libxfs/xfs_trans_space.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/fs/xfs/libxfs/xfs_trans_space.c b/fs/xfs/libxfs/xfs_trans_space.c index 9b8f495c9049..c4cd547033e5 100644 --- a/fs/xfs/libxfs/xfs_trans_space.c +++ b/fs/xfs/libxfs/xfs_trans_space.c @@ -22,8 +22,23 @@ xfs_parent_calc_space_res( unsigned int namelen) { /* - * Parent pointers are always the first attr in an attr tree, and never - * larger than a block + * A parent pointer is recorded per dirent, so an inode with N links + * carries N of them and the attr fork can already be in leaf or node + * format when one is added. That does not affect the reservation: + * XFS_DAENTER_SPACE_RES covers a split at every level of a + * maximum-depth attr dabtree, whatever format the fork is in now. + * + * The name is a dirent name and the value is a struct xfs_parent_rec, + * so the leaf entry is always local and never exceeds 272 bytes. + * Parent pointers require V5, hence a 1k minimum block size, so the + * entry always stays under half a block and this needs none of the + * double split allowance that xfs_attr_calc_size() makes. + * + * The second term hands a byte count to a macro whose parameter counts + * mappings, so it asks for more extent-add allowance than the single + * mapping a parent pointer adds - how much more depends on the block + * size. It over-reserves either way, which is why it is left alone: + * correcting the unit would shrink a reservation that is only generous. */ return XFS_DAENTER_SPACE_RES(mp, XFS_ATTR_FORK) + XFS_NEXTENTADD_SPACE_RES(mp, namelen, XFS_ATTR_FORK); From 8e4ebb6afaa34bd2e8ce52da231003d24111c2d6 Mon Sep 17 00:00:00 2001 From: Javier Tia Date: Mon, 10 Aug 2026 17:06:17 -0600 Subject: [PATCH 0783/1198] xfs: initialise args->total for parent pointer updates xfs_parent_da_args_init() builds an xfs_da_args from a zeroed xfs_parent_args (kmem_cache_zalloc), leaving args->total == 0. xfs_da_grow_inode_int() treats that field as a running block reservation and subtracts from it; because it is an xfs_extlen_t (uint32_t), the first attr-fork growth wraps it to ~0U. That defeats the free-space check in xfs_alloc_space_available(), and when it coincides with an AG that has exactly zero available blocks the allocation is clamped to maxlen 0 and returns -ENOSPC, which xfs_defer_finish_noroll() escalates to a filesystem shutdown. Set args->total the way the log recovery path does (xfs_attri_recover_work(), xfs_attr_item.c:706), in the add and replace paths that can grow the fork. Removals and lookups never grow it, so they leave the field alone, matching that switch. Fixes: b7c62d90c12c ("xfs: parent pointer attribute creation") Cc: stable@vger.kernel.org # v6.10 Signed-off-by: Javier Tia Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino --- fs/xfs/libxfs/xfs_parent.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/fs/xfs/libxfs/xfs_parent.c b/fs/xfs/libxfs/xfs_parent.c index 8d111c9b6527..a2f2f5fa640e 100644 --- a/fs/xfs/libxfs/xfs_parent.c +++ b/fs/xfs/libxfs/xfs_parent.c @@ -193,7 +193,7 @@ xfs_parent_addname( const struct xfs_name *parent_name, struct xfs_inode *child) { - int error; + int error, local; error = xfs_parent_iread_extents(tp, child); if (error) @@ -203,6 +203,10 @@ xfs_parent_addname( xfs_parent_da_args_init(&ppargs->args, tp, &ppargs->rec, child, I_INO(child), parent_name); + /* Growing the attr fork needs a real reservation in args->total. */ + ppargs->args.total = xfs_attr_calc_size(&ppargs->args, &local); + ASSERT(local); + return xfs_attr_setname(&ppargs->args, 0); } @@ -239,7 +243,7 @@ xfs_parent_replacename( const struct xfs_name *new_name, struct xfs_inode *child) { - int error; + int error, local; error = xfs_parent_iread_extents(tp, child); if (error) @@ -249,6 +253,10 @@ xfs_parent_replacename( xfs_parent_da_args_init(&ppargs->args, tp, &ppargs->rec, child, I_INO(child), old_name); + /* Growing the attr fork needs a real reservation in args->total. */ + ppargs->args.total = xfs_attr_calc_size(&ppargs->args, &local); + ASSERT(local); + xfs_inode_to_parent_rec(&ppargs->new_rec, new_dp); ppargs->args.new_name = new_name->name; From 0fe77e57588b989450d668f7c978bb0264c5c340 Mon Sep 17 00:00:00 2001 From: Javier Tia Date: Mon, 10 Aug 2026 17:06:18 -0600 Subject: [PATCH 0784/1198] xfs: assert the reservation covers each da fork growth xfs_da_grow_inode_int() subtracts the blocks it just allocated from args->total, the caller's remaining block reservation. The subtraction is unsigned, so a caller that reaches it with too small a total wraps the field instead of failing, and every allocation afterwards runs with a bogus reservation. Assert the remaining reservation still covers the step, so an under-reserved or uninitialised total trips in debug builds instead of silently wrapping. Suggested-by: Darrick J. Wong Signed-off-by: Javier Tia Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino --- fs/xfs/libxfs/xfs_da_btree.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c index 7938d2324e87..8cbdd6574755 100644 --- a/fs/xfs/libxfs/xfs_da_btree.c +++ b/fs/xfs/libxfs/xfs_da_btree.c @@ -2384,6 +2384,7 @@ xfs_da_grow_inode_int( } /* account for newly allocated blocks in reserved blocks total */ + ASSERT(args->total >= dp->i_nblocks - nblks); args->total -= dp->i_nblocks - nblks; out_free_map: From 9f84792b40d0c96833341602144574bf0bd14a6a Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 26 Aug 2026 22:31:10 -0700 Subject: [PATCH 0785/1198] xfs: don't spin forever on zero-length dirents when salvaging them LOLLM noticed that xrep_dir_recover_data can spin forever if it encounters an unused dirent that claims to have length zero. Fix that, and prevent the same thing from happening with a zero-length entry. Cc: stable@vger.kernel.org # v6.10 Fixes: b1991ee3e7cf85 ("xfs: online repair of directories") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/dir_repair.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/xfs/scrub/dir_repair.c b/fs/xfs/scrub/dir_repair.c index 1c088cfba10e..0c1224d05d57 100644 --- a/fs/xfs/scrub/dir_repair.c +++ b/fs/xfs/scrub/dir_repair.c @@ -484,18 +484,24 @@ xrep_dir_recover_data( while (offset < end) { struct xfs_dir2_data_unused *dup = bp->b_addr + offset; struct xfs_dir2_data_entry *dep = bp->b_addr + offset; + unsigned int advance; if (xchk_should_terminate(rd->sc, &error)) return error; /* Skip unused entries. */ if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) { + if (!dup->length) + break; offset += be16_to_cpu(dup->length); continue; } /* Don't walk off the end of the block. */ - offset += xfs_dir2_data_entsize(rd->sc->mp, dep->namelen); + advance = xfs_dir2_data_entsize(rd->sc->mp, dep->namelen); + if (!advance) + break; + offset += advance; if (offset > end) break; From 865b751e75039fc07838b3200f9740256653da9a Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 26 Aug 2026 22:31:25 -0700 Subject: [PATCH 0786/1198] xfs: don't stash removename operations with unknown ftype LOLLM notices that the behavior of xrep_dir_replay_update changes based on the ftype recorded in the stashed removename information. It also notices that the unlink iops sometimes set that ftype to FT_UNKNOWN because the regular directory tree update code paths don't need to know the ftype of the child. Unfortunately, this results in incorrect link counts, which eventually trips link count errors in later phases of xfs_scrub, or in xfs_repair. Fix this by creating a second xfs_name with the type set correctly. Cc: stable@vger.kernel.org # v6.10 Fixes: 8559b21a64d983 ("xfs: implement live updates for directory repairs") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/dir_repair.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/fs/xfs/scrub/dir_repair.c b/fs/xfs/scrub/dir_repair.c index 0c1224d05d57..31a23c5f386a 100644 --- a/fs/xfs/scrub/dir_repair.c +++ b/fs/xfs/scrub/dir_repair.c @@ -1381,9 +1381,24 @@ xrep_dir_live_update( if (p->delta > 0) error = xrep_dir_stash_createname(rd, p->name, I_INO(p->ip)); - else - error = xrep_dir_stash_removename(rd, p->name, + else { + /* + * xfs_dentry_to_name in unlink or rename-exchange can + * pass us names with ftype FT_UNKNOWN, but we really + * must know the ftype of the child that is being + * removed so that we can do nlink updates correctly + * without holding inode references. + */ + struct xfs_name name = { + .name = p->name->name, + .len = p->name->len, + .type = xfs_mode_to_ftype( + VFS_IC(p->ip)->i_mode), + }; + + error = xrep_dir_stash_removename(rd, &name, I_INO(p->ip)); + } mutex_unlock(&rd->pscan.lock); if (error) goto out_abort; From ed799148e0d63ef41ab60ce98963a1dc423090d3 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 26 Aug 2026 22:31:41 -0700 Subject: [PATCH 0787/1198] xfs: log the tempip after we convert it to extents format LOLLM points out that xrep_symlink_swap_prep converts sc->tempip to an extents format file prior to the atomic swap, but incorrectly logs sc->ip immediately afterwards. Fix that, and the other problem that we're supposed to tell xfs_trans_log_inode what to log and don't. Cc: stable@vger.kernel.org # v6.10 Fixes: 2651923d8d8db0 ("xfs: online repair of symbolic links") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/symlink_repair.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/scrub/symlink_repair.c b/fs/xfs/scrub/symlink_repair.c index 91c86ea0e0f1..181961364233 100644 --- a/fs/xfs/scrub/symlink_repair.c +++ b/fs/xfs/scrub/symlink_repair.c @@ -291,7 +291,7 @@ xrep_symlink_swap_prep( if (error) return error; - xfs_trans_log_inode(sc->tp, sc->ip, 0); + xfs_trans_log_inode(sc->tp, sc->tempip, logflags); error = xfs_defer_finish(&sc->tp); if (error) From cdc4a083adf7bf15a0722c5bd292a35e00112006 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 26 Aug 2026 22:31:56 -0700 Subject: [PATCH 0788/1198] xfs: fix parent rec lookup initialization in xrep_metapath_unlink LOLLM notices that xrep_metapath_unlink looks for a parent pointer in the child metafile that it's removing, but initializes the parent handle using the child. This is obviously incorrect, so fix that. Cc: stable@vger.kernel.org # v6.13 Fixes: 0d2c636e489c11 ("xfs: repair metadata directory file path connectivity") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/metapath.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/scrub/metapath.c b/fs/xfs/scrub/metapath.c index ff1ff762b300..9f44c82910ea 100644 --- a/fs/xfs/scrub/metapath.c +++ b/fs/xfs/scrub/metapath.c @@ -397,7 +397,7 @@ xrep_metapath_unlink( /* Figure out if we're removing a parent pointer too. */ if (xfs_has_parent(mp)) { - xfs_inode_to_parent_rec(&rec, ip); + xfs_inode_to_parent_rec(&rec, mpath->dp); error = xfs_parent_lookup(sc->tp, ip, &mpath->xname, &rec, &mpath->pptr_args); switch (error) { From 9dd6cc92a736a7943dd29776b6eb1938c7f9b94c Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 26 Aug 2026 22:32:12 -0700 Subject: [PATCH 0789/1198] xfs: handle reconnecting metadir subdirectories A longstanding weakness of the metapath repair code is that it can only reattach non-directories to the metadata directory tree. Let's fix that by allowing reconnection of subdirectories. Note that with the initial users of metadir (rtgroups and quota), there's no way to mount a filesystem with broken /rtgroups or /quota subdirectories, so this code won't be all that useful until something adds deeper directory trees. But we shouldn't leave a logic bomb for those futures users wherein we get the link count wrong for a subdir. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/metapath.c | 83 ++++++++++++++++++++++++++++++++++++++++- 1 file changed, 82 insertions(+), 1 deletion(-) diff --git a/fs/xfs/scrub/metapath.c b/fs/xfs/scrub/metapath.c index 9f44c82910ea..a760523f40e6 100644 --- a/fs/xfs/scrub/metapath.c +++ b/fs/xfs/scrub/metapath.c @@ -23,6 +23,7 @@ #include "xfs_rtgroup.h" #include "xfs_rtrmap_btree.h" #include "xfs_rtrefcount_btree.h" +#include "xfs_ag.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" @@ -348,12 +349,78 @@ xchk_metapath( } #ifdef CONFIG_XFS_ONLINE_REPAIR +/* + * Given a directory @dp, an existing inode @ip, and a @name, link @ip into @dp + * under the given @name. + */ +static int +xrep_metadir_add_child( + struct xchk_metapath *mpath, + xfs_ino_t old_dotdot) +{ + struct xfs_trans *tp = mpath->sc->tp; + struct xfs_dir_update *du = &mpath->du; + struct xfs_inode *dp = du->dp; + const struct xfs_name *name = du->name; + struct xfs_inode *ip = du->ip; + struct xfs_mount *mp = tp->t_mountp; + const unsigned int resblks = mpath->link_resblks; + int error; + + /* + * The metadata file shouldn't be on the unlinked list, but we'll fix + * it if that is the case. + */ + if (VFS_I(ip)->i_nlink == 0) { + struct xfs_perag *pag; + + pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, I_INO(ip))); + error = xfs_iunlink_remove(tp, pag, ip); + xfs_perag_put(pag); + if (error) + return error; + } + + error = xfs_dir_createname(tp, dp, name, I_INO(ip), resblks); + if (error) + return error; + + xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE); + + xfs_bumplink(tp, ip); + + /* update dotdot entry in child */ + if (S_ISDIR(VFS_I(ip)->i_mode)) { + xfs_bumplink(tp, dp); + + /* Replace the dotdot entry in the child */ + if (old_dotdot != I_INO(dp)) { + error = xfs_dir_replace(tp, ip, &xfs_name_dotdot, + I_INO(dp), resblks); + if (error) + return error; + } + } + + /* Update the child's parent pointer */ + if (du->ppargs) { + error = xfs_parent_addname(tp, du->ppargs, dp, name, ip); + if (error) + return error; + } + + xfs_dir_update_hook(dp, ip, 1, name); + return 0; +} + /* Create the dirent represented by the final component of the path. */ STATIC int xrep_metapath_link( struct xchk_metapath *mpath) { struct xfs_scrub *sc = mpath->sc; + xfs_ino_t old_dotdot = NULLFSINO; + int error; mpath->du.dp = mpath->dp; mpath->du.name = &mpath->xname; @@ -366,7 +433,21 @@ xrep_metapath_link( trace_xrep_metapath_link(sc, mpath->path, mpath->dp, I_INO(sc->ip)); - return xfs_dir_add_child(sc->tp, mpath->link_resblks, &mpath->du); + if (S_ISDIR(VFS_I(sc->ip)->i_mode)) { + error = xchk_dir_lookup(sc, sc->ip, &xfs_name_dotdot, + &old_dotdot); + if (error && error != -ENOENT) + return error; + + /* + * subdir didn't give us a dotdot entry, so we just give up + * and let the repair get marked as failed. + */ + if (old_dotdot == NULLFSINO) + return 0; + } + + return xrep_metadir_add_child(mpath, old_dotdot); } /* Remove the dirent at the final component of the path. */ From 7538ba528cfd6f176076186c1b1678fdca1c197b Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 26 Aug 2026 22:32:28 -0700 Subject: [PATCH 0790/1198] xfs: lock the healthmon when inserting unmount event LOLLM complains that xfs_healthmon_unmount does an unlocked insert of the unmount event into the health monitor's event list. Fix that. Cc: stable@vger.kernel.org # v7.0 Fixes: 25ca57fa3624ca ("xfs: convey filesystem unmount events to the health monitor") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_healthmon.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/xfs/xfs_healthmon.c b/fs/xfs/xfs_healthmon.c index 4521ffdab9f1..3ae5f4496ad1 100644 --- a/fs/xfs/xfs_healthmon.c +++ b/fs/xfs/xfs_healthmon.c @@ -272,6 +272,8 @@ __xfs_healthmon_insert( { struct timespec64 now; + lockdep_assert_held(&hm->lock); + ktime_get_coarse_real_ts64(&now); event->time_ns = (now.tv_sec * NSEC_PER_SEC) + now.tv_nsec; @@ -294,6 +296,8 @@ __xfs_healthmon_push( { struct timespec64 now; + lockdep_assert_held(&hm->lock); + ktime_get_coarse_real_ts64(&now); event->time_ns = (now.tv_sec * NSEC_PER_SEC) + now.tv_nsec; @@ -415,8 +419,10 @@ xfs_healthmon_unmount( * There's nothing actionable for userspace after an unmount. Once * we've inserted the unmount event, hm no longer owns that event. */ + mutex_lock(&hm->lock); __xfs_healthmon_insert(hm, hm->unmount_event); hm->unmount_event = NULL; + mutex_unlock(&hm->lock); xfs_healthmon_detach(hm); xfs_healthmon_put(hm); From 4164b1e3d728c7cc05e0c1171068aa046542ecc3 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Fri, 21 Aug 2026 17:03:37 -0500 Subject: [PATCH 0791/1198] xfs: fix reclaimed page accounting in xfs_buf_free To obtain nr. of pages in "size" bytes, we need howmany(size, PAGE_SIZE) not howmany(size, PAGE_SHIFT). This over-reports reclaim by orders of magnitude, up to 4096x on a 64k page system. Fixes: e2874632a621 ("xfs: use vmalloc instead of vm_map_area for buffer backing memory") Cc: stable@vger.kernel.org # v6.15+ Signed-off-by: Eric Sandeen Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_buf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index ee7c2e9c0340..836515e8feee 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -139,7 +139,7 @@ xfs_buf_free( ASSERT(list_empty(&bp->b_lru)); if (!xfs_buftarg_is_mem(bp->b_target) && size >= PAGE_SIZE) - mm_account_reclaimed_pages(howmany(size, PAGE_SHIFT)); + mm_account_reclaimed_pages(howmany(size, PAGE_SIZE)); if (is_vmalloc_addr(bp->b_addr)) vfree(bp->b_addr); From 5344402f2c65984cee01a053fd1fa92c44b6aa7d Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Fri, 21 Aug 2026 17:26:39 -0500 Subject: [PATCH 0792/1198] xfs: mark slab-allocated xfs_buf backing memory as __GFP_RECLAIMABLE xfs_bufs have a shrinker and are therefore reclaimable, as is the memory backing them. Mark slab-allocated backing memory as __GFP_RECLAIMABLE in the kmalloc path so that it is accounted properly. Signed-off-by: Eric Sandeen Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_buf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 836515e8feee..8256c1d13ce2 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -176,7 +176,7 @@ xfs_buf_alloc_kmem( ASSERT(is_power_of_2(size)); ASSERT(size < PAGE_SIZE); - bp->b_addr = kmalloc(size, gfp_mask); + bp->b_addr = kmalloc(size, gfp_mask | __GFP_RECLAIMABLE); if (!bp->b_addr) return -ENOMEM; From 48d2b8351bae6d40b44f544fe5540868a55872b2 Mon Sep 17 00:00:00 2001 From: Anuj Gupta Date: Tue, 1 Sep 2026 11:13:48 +0530 Subject: [PATCH 0793/1198] xfs: release alleged child inode on metapath unlink error If xchk_metapath_ilock_parent_and_child() fails after xchk_iget() succeeds, release the inode reference before returning. Fixes: 0d2c636e489c ("xfs: repair metadata directory file path connectivity") Cc: stable@vger.kernel.org # v6.13 Signed-off-by: Anuj Gupta Reviewed-by: Darrick J. Wong Reviewed-by: Carlos Maiolino Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/metapath.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/xfs/scrub/metapath.c b/fs/xfs/scrub/metapath.c index a760523f40e6..e0ee7d9b903f 100644 --- a/fs/xfs/scrub/metapath.c +++ b/fs/xfs/scrub/metapath.c @@ -637,6 +637,8 @@ xrep_metapath_try_unlink( error = xchk_metapath_ilock_parent_and_child(mpath, ip); if (error) { xchk_trans_cancel(sc); + if (ip) + xchk_irele(sc, ip); return error; } xfs_trans_ijoin(sc->tp, mpath->dp, 0); From 05cff7c2b79f76c7cfe90613a60e16aaaa051ef7 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 1 Sep 2026 22:41:59 -0700 Subject: [PATCH 0794/1198] xfs: fix unit conversions in per_binval computation LOLLM noticed that we're doing the unit conversion in the per_binval computation backwards -- xfs_buf_inval_log_space's second parameter is supposed to be in bytes, but max_binval is in units of fsblocks. Hence the conversion should be FSB -> B, not the other way around. Cc: stable@vger.kernel.org # v6.18 Fixes: b2311ec6778fcd ("xfs: compute per-AG extent reap limits dynamically") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/reap.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/xfs/scrub/reap.c b/fs/xfs/scrub/reap.c index fcd14c1703ea..496c6eab555e 100644 --- a/fs/xfs/scrub/reap.c +++ b/fs/xfs/scrub/reap.c @@ -601,7 +601,7 @@ xreap_configure_agextent_limits( /* Maximum overhead of invalidating one buffer. */ const unsigned int per_binval = - xfs_buf_inval_log_space(1, XFS_B_TO_FSBT(mp, max_binval)); + xfs_buf_inval_log_space(1, XFS_FSB_TO_B(mp, max_binval)); /* * For each transaction in a reap chain, we can delete some number of @@ -680,7 +680,7 @@ xreap_configure_agcow_limits( /* Overhead of invalidating one buffer */ const unsigned int per_binval = - xfs_buf_inval_log_space(1, XFS_B_TO_FSBT(mp, max_binval)); + xfs_buf_inval_log_space(1, XFS_FSB_TO_B(mp, max_binval)); /* * For each transaction in a reap chain, we can delete some number of From eacb8479507756c3305994e87fb2fb1183827e98 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 1 Sep 2026 22:42:15 -0700 Subject: [PATCH 0795/1198] xfs: fix short ifork reaping computation in xreap_bmapi_binval LOLLM got really confused about the update to imap->br_blockcount in xreap_bmapi_binval if xreap_inc_binval returns false. The intent of this code is that we shorten the imap to whatever length of space we invalidated so that the next iteration through the loop will start wherever we left off. Unfortunately, the calculation sets br_blockcount to the amount of *unfinished* work, which means that we pointlessly re-scan blocks that we already reaped. This is benign, but we should fix the computation anyway. Cc: stable@vger.kernel.org # v6.10 Fixes: 5befb047b9f4de ("xfs: add the ability to reap entire inode forks") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/reap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/scrub/reap.c b/fs/xfs/scrub/reap.c index 496c6eab555e..f698b9be3dd1 100644 --- a/fs/xfs/scrub/reap.c +++ b/fs/xfs/scrub/reap.c @@ -1399,7 +1399,7 @@ xreap_bmapi_binval( * far we've gotten. */ if (!xreap_inc_binval(rs)) { - imap->br_blockcount = agbno_next - bno; + imap->br_blockcount = bno - agbno; goto out; } } From 72d0a3e4405c1353869bfbbc67c7b8a29df7afd0 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 1 Sep 2026 22:42:31 -0700 Subject: [PATCH 0796/1198] xfs: fix name string recording in slowpath pptr tracepoints LOLLM observes that we memcpy from the xfs_name object, not the name string pointed to by the xfs_name. Fix that. Cc: stable@vger.kernel.org # v6.10 Fixes: b961c8bf1fc3d0 ("xfs: deferred scrub of dirents") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/trace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h index 14aa0ec1f09e..362c6d39e9f5 100644 --- a/fs/xfs/scrub/trace.h +++ b/fs/xfs/scrub/trace.h @@ -1640,7 +1640,7 @@ DECLARE_EVENT_CLASS(xchk_pptr_class, __entry->dev = ip->i_mount->m_super->s_dev; __entry->ino = I_INO(ip); __entry->namelen = name->len; - memcpy(__get_str(name), name, name->len); + memcpy(__get_str(name), name->name, name->len); __entry->far_ino = far_ino; ), TP_printk("dev %d:%d ino 0x%llx name '%.*s' far_ino 0x%llx", From 2eac8d01d2c776fc26b0ac74aebdf91bc4490891 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 1 Sep 2026 22:42:47 -0700 Subject: [PATCH 0797/1198] xfs: don't leak dqacct if rhashtable insertion fails LOLLM observes that xqcheck_mod_live_ino_dqtrx doesn't free the newly allocated dqa object if rhashtable insertion fails. Fix this leak. Cc: stable@vger.kernel.org # v6.9 Fixes: 200491875ce144 ("xfs: track quota updates during live quotacheck") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/quotacheck.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/xfs/scrub/quotacheck.c b/fs/xfs/scrub/quotacheck.c index c199d128538e..c32030a05440 100644 --- a/fs/xfs/scrub/quotacheck.c +++ b/fs/xfs/scrub/quotacheck.c @@ -263,8 +263,10 @@ xqcheck_mod_live_ino_dqtrx( dqa->tx_id = p->tx_id; error = rhashtable_insert_fast(&xqc->shadow_dquot_acct, &dqa->hash, xqcheck_dqacct_hash_params); - if (error) + if (error) { + kfree(dqa); goto out_abort; + } } /* Find the shadow dqtrx (or an empty slot) here. */ From aa301322f72f82f26e4ba0826018d41388ab9896 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 1 Sep 2026 22:43:02 -0700 Subject: [PATCH 0798/1198] xfs: fix the rtrmap and rtrefcount _maxlevels_ondisk functions The _maxlevels_ondisk functions are used to compute the size of in-memory btree cursors for each btree type. Unfortunately, LOLLM noticed that the rtrmap and rtrefcount versions of these functions forget to account for the inode root, which means that we could access beyond the end of the cursor given a sufficiently large btree. Fix this. Cc: stable@vger.kernel.org # v6.14 Fixes: 9abe03a0e4f978 ("xfs: introduce realtime refcount btree ondisk definitions") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/libxfs/xfs_rtrefcount_btree.c | 7 +++++-- fs/xfs/libxfs/xfs_rtrmap_btree.c | 4 +++- 2 files changed, 8 insertions(+), 3 deletions(-) diff --git a/fs/xfs/libxfs/xfs_rtrefcount_btree.c b/fs/xfs/libxfs/xfs_rtrefcount_btree.c index 22acc1411aac..e2950dbe2068 100644 --- a/fs/xfs/libxfs/xfs_rtrefcount_btree.c +++ b/fs/xfs/libxfs/xfs_rtrefcount_btree.c @@ -489,8 +489,11 @@ xfs_rtrefcountbt_maxlevels_ondisk(void) minrecs[0] = xfs_rtrefcountbt_block_maxrecs(blocklen, true) / 2; minrecs[1] = xfs_rtrefcountbt_block_maxrecs(blocklen, false) / 2; - /* We need at most one record for every block in an rt group. */ - return xfs_btree_compute_maxlevels(minrecs, XFS_MAX_RGBLOCKS); + /* + * We need at most one record for every block in an rt group, and + * one extra level for the inode root. + */ + return xfs_btree_compute_maxlevels(minrecs, XFS_MAX_RGBLOCKS) + 1; } int __init diff --git a/fs/xfs/libxfs/xfs_rtrmap_btree.c b/fs/xfs/libxfs/xfs_rtrmap_btree.c index c264bc5651c0..0cb2113d5b40 100644 --- a/fs/xfs/libxfs/xfs_rtrmap_btree.c +++ b/fs/xfs/libxfs/xfs_rtrmap_btree.c @@ -716,10 +716,12 @@ xfs_rtrmapbt_maxlevels_ondisk(void) * happens, which means that we must compute the max height based on * what the btree will look like if it consumes almost all the blocks * in the data device due to maximal sharing factor. + * + * Add one extra level for the inode root. */ max_dblocks = -1U; /* max ag count */ max_dblocks *= XFS_MAX_CRC_AG_BLOCKS; - return xfs_btree_space_to_height(minrecs, max_dblocks); + return xfs_btree_space_to_height(minrecs, max_dblocks) + 1; } int __init From 022d5f5fce7f0b6125d404eb74044e6238aef369 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 1 Sep 2026 22:43:34 -0700 Subject: [PATCH 0799/1198] xfs: fix xfs_rtrmapbt_mem_cursor for non-rmap filesystems It's possible to construct an in-memory rtrmap btree for filesystems that don't have the rmap feature enabled. The kernel doesn't do this, but xfs_repair will, if asked to reindex a filesystem that has rtreflink enabled but not rtrmap. Therefore, we must create the cursor with enough levels to handle a maximally sized btree possible. Note that the rtrmapbt btree cursor slab creates objects large enough to handle xfs_rtrmap_maxlevels_ondisk() levels, so setting bc_nlevels to the same value isn't costing us any extra memory. Cc: stable@vger.kernel.org # v6.14 Fixes: 4a61f12eb11958 ("xfs: create a shadow rmap btree during realtime rmap repair") Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/libxfs/xfs_rtrmap_btree.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/libxfs/xfs_rtrmap_btree.c b/fs/xfs/libxfs/xfs_rtrmap_btree.c index 0cb2113d5b40..a15e460a1ec7 100644 --- a/fs/xfs/libxfs/xfs_rtrmap_btree.c +++ b/fs/xfs/libxfs/xfs_rtrmap_btree.c @@ -618,7 +618,7 @@ xfs_rtrmapbt_mem_cursor( struct xfs_btree_cur *cur; cur = xfs_btree_alloc_cursor(mp, tp, &xfs_rtrmapbt_mem_ops, - mp->m_rtrmap_maxlevels, xfs_rtrmapbt_cur_cache); + xfs_rtrmapbt_maxlevels_ondisk(), xfs_rtrmapbt_cur_cache); cur->bc_mem.xfbtree = xfbt; cur->bc_nlevels = xfbt->nlevels; cur->bc_group = xfs_group_hold(rtg_group(rtg)); From 5287e56cba3be4a64bff9f73bce5964fda2590dc Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 1 Sep 2026 22:43:50 -0700 Subject: [PATCH 0800/1198] xfs: preserve owner on in-memory btree creation LOLLM points out a minor bug where a higher level function creating an in-memory btree is required to pass in an owner number, but the creation function erases that. In-memory btrees are ephemeral so this really doesn't matter except for debugging. But let's fix this papercut. Cc: stable@vger.kernel.org # v6.9 Fixes: a095686a238352 ("xfs: support in-memory btrees") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/libxfs/xfs_btree_mem.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/xfs/libxfs/xfs_btree_mem.c b/fs/xfs/libxfs/xfs_btree_mem.c index 37136a70e56d..1d83a4251cee 100644 --- a/fs/xfs/libxfs/xfs_btree_mem.c +++ b/fs/xfs/libxfs/xfs_btree_mem.c @@ -117,6 +117,7 @@ xfbtree_init( struct xfs_buftarg *btp, const struct xfs_btree_ops *ops) { + unsigned long long owner = xfbt->owner; unsigned int blocklen = xfbtree_rec_bytes(mp, ops); unsigned int keyptr_len; int error; @@ -133,6 +134,7 @@ xfbtree_init( memset(xfbt, 0, sizeof(*xfbt)); xfbt->target = btp; + xfbt->owner = owner; /* Set up min/maxrecs for this btree. */ keyptr_len = ops->key_len + sizeof(__be64); From f1930bc578095409c2dcfca6e4e898b24f0f0de6 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 1 Sep 2026 22:44:05 -0700 Subject: [PATCH 0801/1198] xfs: don't leak new_bp if xfs_btree_bload_drop_buf fails LOLLM observes that in xfs_btree_bload_prep_block, xfs_btree_bload_drop_buf can hit an IO error if writing the delwri buffer list to disk fails. In this case, we fail to release new_bp, which means we lose a locked buffer. Fix that. Cc: stable@vger.kernel.org # v6.8 Fixes: e069d549705e49 ("xfs: constrain dirty buffers while formatting a staged btree") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/libxfs/xfs_btree_staging.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/xfs/libxfs/xfs_btree_staging.c b/fs/xfs/libxfs/xfs_btree_staging.c index 7314dab4bcfb..561fd2c2e950 100644 --- a/fs/xfs/libxfs/xfs_btree_staging.c +++ b/fs/xfs/libxfs/xfs_btree_staging.c @@ -336,8 +336,10 @@ xfs_btree_bload_prep_block( xfs_btree_set_sibling(cur, *blockp, &new_ptr, XFS_BB_RIGHTSIB); ret = xfs_btree_bload_drop_buf(bbl, buffers_list, bpp); - if (ret) + if (ret) { + xfs_buf_relse(new_bp); return ret; + } /* Initialize the new btree block. */ xfs_btree_init_block_cur(cur, new_bp, level, nr_this_block); From b71ae66863e4320a3b7313b53bb4d65f1718d58b Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 1 Sep 2026 22:44:21 -0700 Subject: [PATCH 0802/1198] xfs: actually recover intended file sizes in xfs_xmi_item_recover_intent LOLLM points out that xfs_xmi_item_recover_intent doesn't actually restore the isize1 and isize2 fields that were recovered from an unfinished exchmaps log intent item. Instead, xfs_exchmaps_init_intent sets the wrong isize values from the recovered inodes, with the result that the file sizes are not set correctly when item recovery finishes. Fix this by restoring isize[12] from the log item. Cc: stable@vger.kernel.org # v6.10 Fixes: 966ceafc7a4371 ("xfs: create deferred log items for file mapping exchanges") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_exchmaps_item.c | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/fs/xfs/xfs_exchmaps_item.c b/fs/xfs/xfs_exchmaps_item.c index c3745d33e54e..dd5d92ca1010 100644 --- a/fs/xfs/xfs_exchmaps_item.c +++ b/fs/xfs/xfs_exchmaps_item.c @@ -344,7 +344,17 @@ xfs_xmi_validate( if (!xfs_verify_fileext(mp, xlf->xmi_startoff1, xlf->xmi_blockcount)) return false; - return xfs_verify_fileext(mp, xlf->xmi_startoff2, xlf->xmi_blockcount); + if (!xfs_verify_fileext(mp, xlf->xmi_startoff2, xlf->xmi_blockcount)) + return false; + + if (xlf->xmi_flags & XFS_EXCHMAPS_SET_SIZES) { + if ((int64_t)xlf->xmi_isize1 < 0) + return false; + if ((int64_t)xlf->xmi_isize2 < 0) + return false; + } + + return true; } /* @@ -403,6 +413,13 @@ xfs_xmi_item_recover_intent( *ipp1 = ip1; *ipp2 = ip2; xmi = xfs_exchmaps_init_intent(req); + + /* Restore intended file sizes from recovered logged item */ + if (req->flags & XFS_EXCHMAPS_SET_SIZES) { + xmi->xmi_isize1 = xlf->xmi_isize1; + xmi->xmi_isize2 = xlf->xmi_isize2; + } + xfs_defer_add_item(dfp, &xmi->xmi_list); return xmi; From 365fe37e10ea75840165f13322aa8481ea11dfef Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 1 Sep 2026 22:44:37 -0700 Subject: [PATCH 0803/1198] xfs: don't modify file attributes or poke fsnotify for dry runs I noticed that we shouldn't be removing file privileges when doing a dry run of an exchange-range operation. LOLLM also points out that a dry run shouldn't poke fsnotify because we don't actually change the files. Fix both by gating them on !DRY_RUN. Cc: stable@vger.kernel.org # v6.10 Fixes: 42672471f938cd ("xfs: bind together the front and back ends of the file range exchange code") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_exchrange.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/fs/xfs/xfs_exchrange.c b/fs/xfs/xfs_exchrange.c index 94965a6c2187..c69ecd6a19de 100644 --- a/fs/xfs/xfs_exchrange.c +++ b/fs/xfs/xfs_exchrange.c @@ -504,6 +504,9 @@ xfs_exchange_range_finish( { int error; + if (fxr->flags & XFS_EXCHANGE_RANGE_DRY_RUN) + return 0; + error = file_remove_privs(fxr->file1); if (error) return error; @@ -783,9 +786,12 @@ xfs_exchange_range( if (ret) return ret; - fsnotify_modify(fxr->file1); - if (fxr->file2 != fxr->file1) - fsnotify_modify(fxr->file2); + if (!(fxr->flags & XFS_EXCHANGE_RANGE_DRY_RUN)) { + fsnotify_modify(fxr->file1); + if (fxr->file2 != fxr->file1) + fsnotify_modify(fxr->file2); + } + return 0; } From c83d1ef97ee3b0b92797d4b4932a3a813ba05b86 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 1 Sep 2026 22:44:52 -0700 Subject: [PATCH 0804/1198] xfs: fix bnobt repair space reservation disposal failure LOLLM complains that we don't bubble failures from xrep_abt_dispose_one upwards in the callstack. A failure to clean up the space used (or reserved but not used) by the new bnobt/cntbt should be reported. Cc: stable@vger.kernel.org # v6.8 Fixes: 4bdfd7d15747b1 ("xfs: repair free space btrees") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/alloc_repair.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/fs/xfs/scrub/alloc_repair.c b/fs/xfs/scrub/alloc_repair.c index dce6ab0429dc..95e318e4f3a6 100644 --- a/fs/xfs/scrub/alloc_repair.c +++ b/fs/xfs/scrub/alloc_repair.c @@ -571,7 +571,7 @@ xrep_abt_dispose_one( * allocation, and blocks that didn't get used can be freed via the usual * (deferred) means. */ -STATIC void +STATIC int xrep_abt_dispose_reservations( struct xrep_abt *ra, int error) @@ -582,9 +582,13 @@ xrep_abt_dispose_reservations( goto junkit; list_for_each_entry_safe(resv, n, &ra->new_bnobt.resv_list, list) { - error = xrep_abt_dispose_one(ra, resv); - if (error) + int error2 = xrep_abt_dispose_one(ra, resv); + + if (error2) { + if (!error) + error = error2; goto junkit; + } } junkit: @@ -596,6 +600,7 @@ xrep_abt_dispose_reservations( xrep_newbt_cancel(&ra->new_bnobt); xrep_newbt_cancel(&ra->new_cntbt); + return error; } /* Retrieve free space data for bulk load. */ @@ -801,7 +806,9 @@ xrep_abt_build_new_trees( goto err_newbt; /* Dispose of any unused blocks and the accounting information. */ - xrep_abt_dispose_reservations(ra, error); + error = xrep_abt_dispose_reservations(ra, error); + if (error) + return error; return xrep_roll_ag_trans(sc); @@ -812,8 +819,7 @@ xrep_abt_build_new_trees( xfs_btree_del_cursor(cnt_cur, error); xfs_btree_del_cursor(bno_cur, error); err_newbt: - xrep_abt_dispose_reservations(ra, error); - return error; + return xrep_abt_dispose_reservations(ra, error); } /* From 58a0c7578b25b578c16dea7db2493cfa3a08ecc2 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 1 Sep 2026 22:46:41 -0700 Subject: [PATCH 0805/1198] xfs: always set xfs_healthmon::first_event when inserting at front of list LOLLM complains that while __xfs_healthmon_insert is supposed to insert an event at the head of the list, it doesn't do that correctly if the list isn't empty. In that case it *should* make our new event point to the current head, and then make the head point to the new event, but it doesn't actually update the head so we never see the new event. Fix this by always reassigning first_event. A subsequent patch will clean this up to use a standard list_head, but I felt it important to call out the bug fix first. Cc: stable@vger.kernel.org # v7.0 Fixes: b3a289a2a9397b ("xfs: create event queuing, formatting, and discovery infrastructure") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Reviewed-by: Anuj Gupta Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_healthmon.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/xfs/xfs_healthmon.c b/fs/xfs/xfs_healthmon.c index 3ae5f4496ad1..a4efc084a8fc 100644 --- a/fs/xfs/xfs_healthmon.c +++ b/fs/xfs/xfs_healthmon.c @@ -278,8 +278,7 @@ __xfs_healthmon_insert( event->time_ns = (now.tv_sec * NSEC_PER_SEC) + now.tv_nsec; event->next = hm->first_event; - if (!hm->first_event) - hm->first_event = event; + hm->first_event = event; if (!hm->last_event) hm->last_event = event; xfs_healthmon_bump_events(hm); From 10b1d5fd7189986a0cdd90dde181089b4b2fe40e Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 1 Sep 2026 22:46:56 -0700 Subject: [PATCH 0806/1198] xfs: move healthmon event merge tracepoint Move the tracepoint into the predicate function so that the list conversion in the next patch is easier. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_healthmon.c | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) diff --git a/fs/xfs/xfs_healthmon.c b/fs/xfs/xfs_healthmon.c index a4efc084a8fc..acd41a2b3a1c 100644 --- a/fs/xfs/xfs_healthmon.c +++ b/fs/xfs/xfs_healthmon.c @@ -192,7 +192,7 @@ xfs_healthmon_merge_events( case XFS_HEALTHMON_LOST: existing->lostcount += new->lostcount; - return true; + goto out_merge; case XFS_HEALTHMON_SICK: case XFS_HEALTHMON_CORRUPT: @@ -200,19 +200,19 @@ xfs_healthmon_merge_events( switch (existing->domain) { case XFS_HEALTHMON_FS: existing->fsmask |= new->fsmask; - return true; + goto out_merge; case XFS_HEALTHMON_AG: case XFS_HEALTHMON_RTGROUP: if (existing->group == new->group){ existing->grpmask |= new->grpmask; - return true; + goto out_merge; } return false; case XFS_HEALTHMON_INODE: if (existing->ino == new->ino && existing->gen == new->gen) { existing->imask |= new->imask; - return true; + goto out_merge; } return false; default: @@ -224,18 +224,18 @@ xfs_healthmon_merge_events( case XFS_HEALTHMON_SHUTDOWN: /* yes, we can race to shutdown */ existing->flags |= new->flags; - return true; + goto out_merge; case XFS_HEALTHMON_MEDIA_ERROR: /* physically adjacent errors can merge */ if (existing->daddr + existing->bbcount == new->daddr) { existing->bbcount += new->bbcount; - return true; + goto out_merge; } if (new->daddr + new->bbcount == existing->daddr) { existing->daddr = new->daddr; existing->bbcount += new->bbcount; - return true; + goto out_merge; } return false; @@ -250,18 +250,22 @@ xfs_healthmon_merge_events( if (existing->fpos + existing->flen == new->fpos) { existing->flen += new->flen; - return true; + goto out_merge; } if (new->fpos + new->flen == existing->fpos) { existing->fpos = new->fpos; existing->flen += new->flen; - return true; + goto out_merge; } return false; } return false; + +out_merge: + trace_xfs_healthmon_merge(hm, existing); + return true; } /* Insert an event onto the start of the queue. */ @@ -325,7 +329,6 @@ xfs_healthmon_clear_lost_prev( struct xfs_healthmon_event *event = NULL; if (xfs_healthmon_merge_events(hm->last_event, &lost_event)) { - trace_xfs_healthmon_merge(hm, hm->last_event); wake_up(&hm->wait); goto cleared; } @@ -373,7 +376,6 @@ xfs_healthmon_push( /* Try to merge with the newest event */ if (xfs_healthmon_merge_events(hm->last_event, template)) { - trace_xfs_healthmon_merge(hm, hm->last_event); wake_up(&hm->wait); goto out_unlock; } From 9097f5c03f038cea83d174b6d322d7b2678a3c99 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 1 Sep 2026 22:47:12 -0700 Subject: [PATCH 0807/1198] xfs: port healthmon event list to list_head Simplify the healthmon codebase by porting the single-link event list to a standard list_head. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_healthmon.c | 36 +++++++++++++++--------------------- fs/xfs/xfs_healthmon.h | 5 ++--- 2 files changed, 17 insertions(+), 24 deletions(-) diff --git a/fs/xfs/xfs_healthmon.c b/fs/xfs/xfs_healthmon.c index acd41a2b3a1c..073b74e490df 100644 --- a/fs/xfs/xfs_healthmon.c +++ b/fs/xfs/xfs_healthmon.c @@ -87,12 +87,10 @@ xfs_healthmon_put( struct xfs_healthmon *hm) { if (refcount_dec_and_test(&hm->ref)) { - struct xfs_healthmon_event *event; - struct xfs_healthmon_event *next = hm->first_event; + struct xfs_healthmon_event *event, *s; - while ((event = next) != NULL) { + list_for_each_entry_safe(event, s, &hm->event_list, entry) { trace_xfs_healthmon_drop(hm, event); - next = event->next; kfree(event); } @@ -173,9 +171,13 @@ static inline void xfs_healthmon_bump_lost(struct xfs_healthmon *hm) */ static bool xfs_healthmon_merge_events( - struct xfs_healthmon_event *existing, + struct xfs_healthmon *hm, const struct xfs_healthmon_event *new) { + struct xfs_healthmon_event *existing = + list_last_entry_or_null(&hm->event_list, struct + xfs_healthmon_event, entry); + if (!existing) return false; @@ -281,10 +283,7 @@ __xfs_healthmon_insert( ktime_get_coarse_real_ts64(&now); event->time_ns = (now.tv_sec * NSEC_PER_SEC) + now.tv_nsec; - event->next = hm->first_event; - hm->first_event = event; - if (!hm->last_event) - hm->last_event = event; + list_add(&event->entry, &hm->event_list); xfs_healthmon_bump_events(hm); wake_up(&hm->wait); @@ -304,12 +303,7 @@ __xfs_healthmon_push( ktime_get_coarse_real_ts64(&now); event->time_ns = (now.tv_sec * NSEC_PER_SEC) + now.tv_nsec; - if (!hm->first_event) - hm->first_event = event; - if (hm->last_event) - hm->last_event->next = event; - hm->last_event = event; - event->next = NULL; + list_add_tail(&event->entry, &hm->event_list); xfs_healthmon_bump_events(hm); wake_up(&hm->wait); @@ -328,7 +322,7 @@ xfs_healthmon_clear_lost_prev( }; struct xfs_healthmon_event *event = NULL; - if (xfs_healthmon_merge_events(hm->last_event, &lost_event)) { + if (xfs_healthmon_merge_events(hm, &lost_event)) { wake_up(&hm->wait); goto cleared; } @@ -375,7 +369,7 @@ xfs_healthmon_push( } /* Try to merge with the newest event */ - if (xfs_healthmon_merge_events(hm->last_event, template)) { + if (xfs_healthmon_merge_events(hm, template)) { wake_up(&hm->wait); goto out_unlock; } @@ -901,11 +895,10 @@ xfs_healthmon_format_pop( return NULL; mutex_lock(&hm->lock); - event = hm->first_event; + event = list_first_entry_or_null(&hm->event_list, + struct xfs_healthmon_event, entry); if (event) { - if (hm->last_event == event) - hm->last_event = NULL; - hm->first_event = event->next; + list_del_init(&event->entry); hm->events--; trace_xfs_healthmon_pop(hm, event); @@ -1205,6 +1198,7 @@ xfs_ioc_health_monitor( return -ENOMEM; hm->dev = mp->m_super->s_dev; refcount_set(&hm->ref, 1); + INIT_LIST_HEAD(&hm->event_list); mutex_init(&hm->lock); init_waitqueue_head(&hm->wait); diff --git a/fs/xfs/xfs_healthmon.h b/fs/xfs/xfs_healthmon.h index 0e936507037f..fa3deb187a2b 100644 --- a/fs/xfs/xfs_healthmon.h +++ b/fs/xfs/xfs_healthmon.h @@ -31,8 +31,7 @@ struct xfs_healthmon { struct mutex lock; /* list of event objects */ - struct xfs_healthmon_event *first_event; - struct xfs_healthmon_event *last_event; + struct list_head event_list; /* preallocated event for unmount */ struct xfs_healthmon_event *unmount_event; @@ -110,7 +109,7 @@ enum xfs_healthmon_domain { }; struct xfs_healthmon_event { - struct xfs_healthmon_event *next; + struct list_head entry; enum xfs_healthmon_type type; enum xfs_healthmon_domain domain; From 4c98464e12fcfe3a71646f8efa5d3f7f1b5e2bed Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 1 Sep 2026 22:47:28 -0700 Subject: [PATCH 0808/1198] xfs: merge healthmon insert/push helpers These functions are basically the same except for where in the queue the new event is added. Refactor them as a single function that takes an action verb to tell us where; and rename the tracepoints to describe directly what happens. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_healthmon.c | 52 +++++++++++++++++++----------------------- fs/xfs/xfs_trace.h | 4 ++-- 2 files changed, 26 insertions(+), 30 deletions(-) diff --git a/fs/xfs/xfs_healthmon.c b/fs/xfs/xfs_healthmon.c index 073b74e490df..e012c7545da0 100644 --- a/fs/xfs/xfs_healthmon.c +++ b/fs/xfs/xfs_healthmon.c @@ -270,10 +270,16 @@ xfs_healthmon_merge_events( return true; } -/* Insert an event onto the start of the queue. */ +enum insert_where { + INSERT_HEAD, + INSERT_TAIL, +}; + +/* Add an event onto the start or the end of the queue. */ static inline void __xfs_healthmon_insert( struct xfs_healthmon *hm, + enum insert_where where, struct xfs_healthmon_event *event) { struct timespec64 now; @@ -283,31 +289,21 @@ __xfs_healthmon_insert( ktime_get_coarse_real_ts64(&now); event->time_ns = (now.tv_sec * NSEC_PER_SEC) + now.tv_nsec; - list_add(&event->entry, &hm->event_list); + switch (where) { + case INSERT_HEAD: + trace_xfs_healthmon_insert_head(hm, event); + + list_add(&event->entry, &hm->event_list); + break; + case INSERT_TAIL: + trace_xfs_healthmon_insert_tail(hm, event); + + list_add_tail(&event->entry, &hm->event_list); + break; + } + xfs_healthmon_bump_events(hm); wake_up(&hm->wait); - - trace_xfs_healthmon_insert(hm, event); -} - -/* Push an event onto the end of the queue. */ -static inline void -__xfs_healthmon_push( - struct xfs_healthmon *hm, - struct xfs_healthmon_event *event) -{ - struct timespec64 now; - - lockdep_assert_held(&hm->lock); - - ktime_get_coarse_real_ts64(&now); - event->time_ns = (now.tv_sec * NSEC_PER_SEC) + now.tv_nsec; - - list_add_tail(&event->entry, &hm->event_list); - xfs_healthmon_bump_events(hm); - wake_up(&hm->wait); - - trace_xfs_healthmon_push(hm, event); } /* Deal with any previously lost events */ @@ -333,7 +329,7 @@ xfs_healthmon_clear_lost_prev( if (!event) return -ENOMEM; - __xfs_healthmon_push(hm, event); + __xfs_healthmon_insert(hm, INSERT_TAIL, event); cleared: hm->lost_prev_event = 0; return 0; @@ -386,7 +382,7 @@ xfs_healthmon_push( goto out_unlock; } - __xfs_healthmon_push(hm, event); + __xfs_healthmon_insert(hm, INSERT_TAIL, event); out_unlock: mutex_unlock(&hm->lock); @@ -415,7 +411,7 @@ xfs_healthmon_unmount( * we've inserted the unmount event, hm no longer owns that event. */ mutex_lock(&hm->lock); - __xfs_healthmon_insert(hm, hm->unmount_event); + __xfs_healthmon_insert(hm, INSERT_HEAD, hm->unmount_event); hm->unmount_event = NULL; mutex_unlock(&hm->lock); @@ -1214,7 +1210,7 @@ xfs_ioc_health_monitor( } running_event->type = XFS_HEALTHMON_RUNNING; running_event->domain = XFS_HEALTHMON_MOUNT; - __xfs_healthmon_insert(hm, running_event); + __xfs_healthmon_insert(hm, INSERT_HEAD, running_event); /* * Preallocate the unmount event so that we can't fail to notify the diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index f333c938fbd9..6aa379c2cf0c 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -6139,8 +6139,8 @@ DEFINE_EVENT(xfs_healthmon_event_class, name, \ TP_PROTO(const struct xfs_healthmon *hm, \ const struct xfs_healthmon_event *event), \ TP_ARGS(hm, event)) -DEFINE_HEALTHMONEVENT_EVENT(xfs_healthmon_insert); -DEFINE_HEALTHMONEVENT_EVENT(xfs_healthmon_push); +DEFINE_HEALTHMONEVENT_EVENT(xfs_healthmon_insert_head); +DEFINE_HEALTHMONEVENT_EVENT(xfs_healthmon_insert_tail); DEFINE_HEALTHMONEVENT_EVENT(xfs_healthmon_pop); DEFINE_HEALTHMONEVENT_EVENT(xfs_healthmon_format); DEFINE_HEALTHMONEVENT_EVENT(xfs_healthmon_format_overflow); From 74eeb68a628dbc4a8f976351ad2f1ef5463513ee Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 1 Sep 2026 22:47:43 -0700 Subject: [PATCH 0809/1198] xfs: check healthmon outbuffer space correctly LOLLM notices that the outbuf space check in xfs_healthmon_format_pop isn't quite correct -- it checks that there's enough space to write a xfs_healthmon_event object, but the outbuffer is supposed to contain xfs_health_monitor_event objects. Fix this by adding a helper, and refactoring all three outbuf size checks to use it. Cc: stable@vger.kernel.org # v7.0 Fixes: b3a289a2a9397b ("xfs: create event queuing, formatting, and discovery infrastructure") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_healthmon.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) diff --git a/fs/xfs/xfs_healthmon.c b/fs/xfs/xfs_healthmon.c index e012c7545da0..78c87761ac89 100644 --- a/fs/xfs/xfs_healthmon.c +++ b/fs/xfs/xfs_healthmon.c @@ -735,6 +735,13 @@ static const unsigned int type_map[] = { [XFS_HEALTHMON_DATALOST] = XFS_HEALTH_MONITOR_TYPE_DATALOST, }; +static inline bool +xfs_healthmon_check_outbuffer_space(const struct xfs_healthmon *hm) +{ + return hm->bufhead + sizeof(struct xfs_health_monitor_event) <= + hm->bufsize; +} + /* Render event as a V0 structure */ STATIC int xfs_healthmon_format_v0( @@ -801,10 +808,10 @@ xfs_healthmon_format_v0( break; } - ASSERT(hm->bufhead + sizeof(hme) <= hm->bufsize); + ASSERT(xfs_healthmon_check_outbuffer_space(hm)); /* copy formatted object to the outbuf */ - if (hm->bufhead + sizeof(hme) <= hm->bufsize) { + if (xfs_healthmon_check_outbuffer_space(hm)) { memcpy(hm->buffer + hm->bufhead, &hme, sizeof(hme)); hm->bufhead += sizeof(hme); } @@ -887,7 +894,11 @@ xfs_healthmon_format_pop( { struct xfs_healthmon_event *event; - if (hm->bufhead + sizeof(*event) > hm->bufsize) + /* + * Don't bother if there's not enough space to format even one event in + * the outbuffer. + */ + if (!xfs_healthmon_check_outbuffer_space(hm)) return NULL; mutex_lock(&hm->lock); From 295f2cfd3e2c814c2ecd2c1d522bc31c5288e414 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 1 Sep 2026 22:47:59 -0700 Subject: [PATCH 0810/1198] xfs: bump lost_prev_errors if we lose even the healthmon lost event LOLLM observes that we don't bump xfs_healthmon::lost_prev_event even if we can't allocate or queue a LOST event, which means that events can disappear silently when things are going very wrong. Bump the counter to avoid this problem. Cc: stable@vger.kernel.org # v7.0 Fixes: b3a289a2a9397b ("xfs: create event queuing, formatting, and discovery infrastructure") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_healthmon.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/xfs/xfs_healthmon.c b/fs/xfs/xfs_healthmon.c index 78c87761ac89..b57fa033cec4 100644 --- a/fs/xfs/xfs_healthmon.c +++ b/fs/xfs/xfs_healthmon.c @@ -326,8 +326,10 @@ xfs_healthmon_clear_lost_prev( if (hm->events < XFS_HEALTHMON_MAX_EVENTS) event = kmemdup(&lost_event, sizeof(struct xfs_healthmon_event), GFP_NOFS); - if (!event) + if (!event) { + xfs_healthmon_bump_lost(hm); return -ENOMEM; + } __xfs_healthmon_insert(hm, INSERT_TAIL, event); cleared: From 014c1aff607a839b8ddc732da919b94560ae58c2 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 1 Sep 2026 22:48:14 -0700 Subject: [PATCH 0811/1198] xfs: report nonexistent parents as a filesystem corruption LOLLM noticed that when the directory tree scrubber tries to walk up a parent pointer but the parent inumber doesn't point to an allocated inode, we allow the EINVAL/ENOENT error code to bubble up to userspace. That's not right, we should be reporting that as a cross-referencing error so that someone runs the parent pointer checker. Also add a termination check to xchk_dirpath_step_up because it's a loop body function. Cc: stable@vger.kernel.org # v6.10 Fixes: 928b721a11789a ("xfs: teach online scrub to find directory tree structure problems") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/dirtree.c | 30 ++++++++++++++++++++++++++++-- fs/xfs/scrub/trace.h | 33 +++++++++++++++++++++++++++++++++ 2 files changed, 61 insertions(+), 2 deletions(-) diff --git a/fs/xfs/scrub/dirtree.c b/fs/xfs/scrub/dirtree.c index b2cf6e5439d9..717cbac29562 100644 --- a/fs/xfs/scrub/dirtree.c +++ b/fs/xfs/scrub/dirtree.c @@ -368,12 +368,38 @@ xchk_dirpath_step_up( struct xfs_inode *dp; xfs_ino_t parent_ino = be64_to_cpu(dl->pptr_rec.p_ino); unsigned int lock_mode; - int error; + int error = 0; + + if (xchk_should_terminate(sc, &error)) + return error; /* Grab and lock the parent directory. */ error = xchk_iget(sc, parent_ino, &dp); - if (error) + switch (error) { + case -EINVAL: + case -ENOENT: + mutex_lock(&dl->lock); + + if (dl->stale) { + /* live update detected a change in this path */ + error = -ESTALE; + } else { + /* inode doesn't exist, path invalid */ + error = -EFSCORRUPTED; + + trace_xchk_dirpath_badino(dl->sc, path->path_nr, + path->nr_steps, &dl->xname, + &dl->pptr_rec); + } + + mutex_unlock(&dl->lock); return error; + case 0: + /* keep going */ + break; + default: + return error; + } lock_mode = xfs_ilock_attr_map_shared(dp); mutex_lock(&dl->lock); diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h index 362c6d39e9f5..0f5adc293962 100644 --- a/fs/xfs/scrub/trace.h +++ b/fs/xfs/scrub/trace.h @@ -1706,6 +1706,39 @@ DEFINE_EVENT(xchk_dirtree_class, name, \ DEFINE_XCHK_DIRTREE_EVENT(xchk_dirtree_create_path); DEFINE_XCHK_DIRTREE_EVENT(xchk_dirpath_walk_upwards); +TRACE_EVENT(xchk_dirpath_badino, + TP_PROTO(struct xfs_scrub *sc, unsigned int path_nr, + unsigned int step_nr, const struct xfs_name *name, + const struct xfs_parent_rec *pptr), + TP_ARGS(sc, path_nr, step_nr, name, pptr), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(unsigned int, path_nr) + __field(unsigned int, step_nr) + __field(xfs_ino_t, parent_ino) + __field(unsigned int, parent_gen) + __field(unsigned int, namelen) + __dynamic_array(char, name, name->len) + ), + TP_fast_assign( + __entry->dev = sc->mp->m_super->s_dev; + __entry->path_nr = path_nr; + __entry->step_nr = step_nr; + __entry->parent_ino = be64_to_cpu(pptr->p_ino); + __entry->parent_gen = be32_to_cpu(pptr->p_gen); + __entry->namelen = name->len; + memcpy(__get_str(name), name->name, name->len); + ), + TP_printk("dev %d:%d path %u step %u parent_ino 0x%llx parent_gen 0x%x name '%.*s'", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->path_nr, + __entry->step_nr, + __entry->parent_ino, + __entry->parent_gen, + __entry->namelen, + __get_str(name)) +); + DECLARE_EVENT_CLASS(xchk_dirpath_class, TP_PROTO(struct xfs_scrub *sc, struct xfs_inode *ip, unsigned int path_nr, unsigned int step_nr, From 1a441c6842da75c5b862cc1c9f7969d6a93b54b9 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 1 Sep 2026 22:48:30 -0700 Subject: [PATCH 0812/1198] xfs: destroy seen inode bitmap when we fail to add a dirpath LOLLM observes a memory leak in xchk_dirtree_create_path if we create the directory path object but appending the name to the path fails. When this happens, we don't tear down the (empty) seen inode bitmap. This is a pretty trivial error, but let's not leave logic bombs. Do the same for a similar bug in xrep_dirtree_create_adoption_path. Cc: stable@vger.kernel.org # v6.10 Fixes: 928b721a11789a ("xfs: teach online scrub to find directory tree structure problems") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/dirtree.c | 1 + fs/xfs/scrub/dirtree_repair.c | 1 + 2 files changed, 2 insertions(+) diff --git a/fs/xfs/scrub/dirtree.c b/fs/xfs/scrub/dirtree.c index 717cbac29562..9b0ab2316612 100644 --- a/fs/xfs/scrub/dirtree.c +++ b/fs/xfs/scrub/dirtree.c @@ -259,6 +259,7 @@ xchk_dirtree_create_path( dl->nr_paths++; return 0; out_path: + xino_bitmap_destroy(&path->seen_inodes); kfree(path); return error; } diff --git a/fs/xfs/scrub/dirtree_repair.c b/fs/xfs/scrub/dirtree_repair.c index bbf6acf6fd40..8acd55b8c769 100644 --- a/fs/xfs/scrub/dirtree_repair.c +++ b/fs/xfs/scrub/dirtree_repair.c @@ -618,6 +618,7 @@ xrep_dirtree_create_adoption_path( return 0; out_path: + xino_bitmap_destroy(&path->seen_inodes); kfree(path); return error; } From 8c71ad4d4f3e20c30b663bd292526fcbc4d3913f Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 1 Sep 2026 22:48:45 -0700 Subject: [PATCH 0813/1198] xfs: signal inode btree xref error if get_rec returns an error LOLLM points out that xchk_finobt_xref_inobt and xchk_inobt_xref_finobt both ignore errors being returned from the xfs_btree_get_rec function and proceed with a (possibly stale) "true" value for has_record. If the *simple* btree record checks fail during cross-referencing, we can immediately conclude that there's a cross-referncing error in the other btree. On those grounds, we can bubble up the returned error instead of wasting time cross-referencing with garbage. Cc: stable@vger.kernel.org # v6.4 Fixes: bc0f3b55467e1b ("xfs: directly cross-reference the inode btrees with each other") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/ialloc.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c index 19c0b1b2a787..9270ad075fe0 100644 --- a/fs/xfs/scrub/ialloc.c +++ b/fs/xfs/scrub/ialloc.c @@ -85,6 +85,8 @@ xchk_inobt_xref_finobt( goto no_record; error = xfs_inobt_get_rec(cur, &frec, &has_record); + if (error) + return error; if (!has_record) return -EFSCORRUPTED; @@ -188,6 +190,8 @@ xchk_finobt_xref_inobt( goto no_record; error = xfs_inobt_get_rec(cur, &irec, &has_record); + if (error) + return error; if (!has_record) return -EFSCORRUPTED; From 0fc67528f54bb91dac22093749b425207c0fc245 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 1 Sep 2026 22:49:01 -0700 Subject: [PATCH 0814/1198] xfs: truncate quota file correctly when repairing quota file LOLLM noticed that xrep_quota_data_fork screws up the unit handling when it computes the offset at which to start truncating the quota file. max_dquid_off is the file block offset containing the highest possible dquot, and xfs_bunmapi_range takes the starting file block offset. Therefore, it makes no sense to multiply max_dquid_off by the blocksize; all we need to do is start truncating at the next block. Cc: stable@vger.kernel.org # v6.8 Fixes: a5b91555403e3a ("xfs: repair quotas") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/quota_repair.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/xfs/scrub/quota_repair.c b/fs/xfs/scrub/quota_repair.c index 487bd4f68ebb..ca3ac6728339 100644 --- a/fs/xfs/scrub/quota_repair.c +++ b/fs/xfs/scrub/quota_repair.c @@ -455,8 +455,7 @@ xrep_quota_data_fork( if (truncate) { /* Erase everything after the block containing the max dquot */ - error = xfs_bunmapi_range(&sc->tp, sc->ip, 0, - max_dqid_off * sc->mp->m_sb.sb_blocksize, + error = xfs_bunmapi_range(&sc->tp, sc->ip, 0, max_dqid_off + 1, XFS_MAX_FILEOFF); if (error) goto out; From de20f7014917d661afc03d9a1c157d0ae2775b49 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 2 Sep 2026 22:49:52 -0700 Subject: [PATCH 0815/1198] xfs: compute dquot checksum after resetting dd_lsn in repair LOLLM complains that xrep_quota_block updates dd_lsn after calculating the crc of the ondisk dquot. That's clearly broken, so fix that. Cc: stable@vger.kernel.org # v6.8 Fixes: a5b91555403e3a ("xfs: repair quotas") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/quota_repair.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/fs/xfs/scrub/quota_repair.c b/fs/xfs/scrub/quota_repair.c index ca3ac6728339..5c22bb6ccffa 100644 --- a/fs/xfs/scrub/quota_repair.c +++ b/fs/xfs/scrub/quota_repair.c @@ -363,11 +363,18 @@ xrep_quota_block( ddq->d_rtbcount, &ddq->d_rtbtimer, defq->rtb.time); + /* + * This transaction operates on raw disk buffers, so we don't + * have a dquot log item to assign the LSN for us. Instead, + * set it to zero so that log recovery will always replay any + * logged dquot item atop this buffer. + */ + dqblk->dd_lsn = 0; + /* We only support v5 filesystems so always set these. */ uuid_copy(&dqblk->dd_uuid, &sc->mp->m_sb.sb_meta_uuid); xfs_update_cksum((char *)dqblk, sizeof(struct xfs_dqblk), XFS_DQUOT_CRC_OFF); - dqblk->dd_lsn = 0; } switch (dqtype) { case XFS_DQTYPE_USER: From d7f97be48cbe3751e44a45373c0e91e93b976f98 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 1 Sep 2026 22:49:32 -0700 Subject: [PATCH 0816/1198] xfs: fix backwards skipping logic in xrep_quota_block LOLLM complains about the logic in xrep_quota_block that skips reinitializing the ondisk dquot if there aren't any problems that would impede a dqiterate walk later. I got the type checking logic backwards, which is the source of the problem. Fix that. Cc: stable@vger.kernel.org # v6.8 Fixes: a5b91555403e3a ("xfs: repair quotas") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/quota_repair.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/scrub/quota_repair.c b/fs/xfs/scrub/quota_repair.c index 5c22bb6ccffa..59302e8afc7e 100644 --- a/fs/xfs/scrub/quota_repair.c +++ b/fs/xfs/scrub/quota_repair.c @@ -325,7 +325,7 @@ xrep_quota_block( * If there's nothing that would impede a dqiterate, we're * done. */ - if ((ddq->d_type & XFS_DQTYPE_REC_MASK) != dqtype || + if ((ddq->d_type & XFS_DQTYPE_REC_MASK) == dqtype && id == be32_to_cpu(ddq->d_id)) { xfs_trans_brelse(sc->tp, bp); return 0; From e8b01aaafffe6b852325debdf1ef4b13ccea1cd7 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 1 Sep 2026 22:49:47 -0700 Subject: [PATCH 0817/1198] xfs: fix backwards mergeability logic in refcount scrubber When we start the refcount or rtrefcount btree scanners, prev_rec is initialized to all zeroes. This is done so that the record mergeability checks skip the first record because you must have two records to compare. Unfortunately, I got the logic backwards, so scrub has never complained about mergeable refcountbt records. Fix this bug that LOLLM noticed. Cc: stable@vger.kernel.org # v6.4 Fixes: db0502b39c21d1 ("xfs: flag refcount btree records that could be merged") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/refcount.c | 2 +- fs/xfs/scrub/rtrefcount.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index 4e1bf23e5b89..f2addaf13c58 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -410,7 +410,7 @@ xchk_refcount_mergeable( const struct xfs_refcount_irec *r1 = &rrc->prev_rec; /* Ignore if prev_rec is not yet initialized. */ - if (r1->rc_blockcount > 0) + if (r1->rc_blockcount == 0) return false; if (r1->rc_domain != r2->rc_domain) diff --git a/fs/xfs/scrub/rtrefcount.c b/fs/xfs/scrub/rtrefcount.c index 4e7c540c8d23..de100178f41c 100644 --- a/fs/xfs/scrub/rtrefcount.c +++ b/fs/xfs/scrub/rtrefcount.c @@ -375,7 +375,7 @@ xchk_rtrefcount_mergeable( const struct xfs_refcount_irec *r1 = &rrc->prev_rec; /* Ignore if prev_rec is not yet initialized. */ - if (r1->rc_blockcount > 0) + if (r1->rc_blockcount == 0) return false; if (r1->rc_startblock + r1->rc_blockcount != r2->rc_startblock) From 79ab1af2034b2ad10c5f18910937b938d2ad2219 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 2 Sep 2026 22:51:05 -0700 Subject: [PATCH 0818/1198] xfs: cross-reference the rtgroup superblock extent, not block LOLLM noticed that when libxfs creates a realtime superblock, it will create an rtrmapbt record covering the entire rtextent in which the superblock lives. However, the cross-referencing checks only look for the first block, which means that we can miss a corrupt rtrmap record. That will get picked up by the rtrmap scrubber, but we should make the rgsuper scrubber more robust anyway. Cc: stable@vger.kernel.org # v6.13 Fixes: 3f1bdf50ab1b9c ("xfs: scrub the realtime group superblock") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/rgsuper.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/xfs/scrub/rgsuper.c b/fs/xfs/scrub/rgsuper.c index 2bd2c0351b35..6e2abe5dc27c 100644 --- a/fs/xfs/scrub/rgsuper.c +++ b/fs/xfs/scrub/rgsuper.c @@ -36,8 +36,10 @@ xchk_rgsuperblock_xref( if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) return; - xchk_xref_is_used_rt_space(sc, xfs_rgbno_to_rtb(sc->sr.rtg, 0), 1); - xchk_xref_is_only_rt_owned_by(sc, 0, 1, &XFS_RMAP_OINFO_FS); + xchk_xref_is_used_rt_space(sc, xfs_rgbno_to_rtb(sc->sr.rtg, 0), + sc->mp->m_sb.sb_rextsize); + xchk_xref_is_only_rt_owned_by(sc, 0, sc->mp->m_sb.sb_rextsize, + &XFS_RMAP_OINFO_FS); } int From c3085f6c7cca7c162248519ce8d763047cdd8acd Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 2 Sep 2026 22:51:21 -0700 Subject: [PATCH 0819/1198] xfs: use the rtgroup extent count to find rtrefcount gaps LOLLM noticed an anachronism from the early days of rtrefcount where the refcount btree would handle 64-bit block numbers -- we pass rtblocks into the gap finder, but rtrefcount btrees are sharded by rtgroup now. This isn't really a problem for us since we're only looking for overlapping rtrmap records to flag, but let's fix this sillyness. Also fix some stale comments. Cc: stable@vger.kernel.org # v6.14 Fixes: 30f47950dc2eba ("xfs: check reference counts of gaps between rt refcount records") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/rtrefcount.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/xfs/scrub/rtrefcount.c b/fs/xfs/scrub/rtrefcount.c index de100178f41c..a024d50cf9d2 100644 --- a/fs/xfs/scrub/rtrefcount.c +++ b/fs/xfs/scrub/rtrefcount.c @@ -428,7 +428,7 @@ static inline void xchk_rtrefcountbt_xref_gaps( struct xfs_scrub *sc, struct xchk_rtrefcbt_records *rrc, - xfs_rtblock_t bno) + xfs_rgblock_t bno) { struct xfs_rmap_irec low; struct xfs_rmap_irec high; @@ -538,7 +538,7 @@ xchk_refcount_xref_rmap( xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0); } -/* Scrub the refcount btree for some AG. */ +/* Scrub the refcount btree for some rtgroup. */ int xchk_rtrefcountbt( struct xfs_scrub *sc) @@ -564,10 +564,10 @@ xchk_rtrefcountbt( /* * Check that all blocks between the last refcount > 1 record and the - * end of the rt volume have at most one reverse mapping. + * end of the rtgroup have at most one reverse mapping. */ - xchk_rtrefcountbt_xref_gaps(sc, &rrc, sc->mp->m_sb.sb_rblocks); - + xchk_rtrefcountbt_xref_gaps(sc, &rrc, + xfs_rtx_to_rgbno(sc->sr.rtg, sc->mp->m_sb.sb_rgextents)); xchk_refcount_xref_rmap(sc, &btree_oinfo, rrc.cow_blocks); return 0; From 0d43368844a75ad13561a1198a3b027940730756 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 2 Sep 2026 22:51:36 -0700 Subject: [PATCH 0820/1198] xfs: strengthen the "is cow staging" helpers in scrub LOLLM pointed out a bug in both of the refcount scrub predicates that determine if a range of blocks is marked as CoW staging in the btree. While it compares blockcount < len, this isn't enough to determine that the CoW staging record is at least as large as the range passed into the helper. Fix both of them. Cc: stable@vger.kernel.org # v4.16 Fixes: f6d5fc21fdc713 ("xfs: cross-reference refcount btree during scrub") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/refcount.c | 6 +++++- fs/xfs/scrub/rtrefcount.c | 6 +++++- 2 files changed, 10 insertions(+), 2 deletions(-) diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index f2addaf13c58..f8c51d8fbb3d 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -581,8 +581,12 @@ xchk_xref_is_cow_staging( if (rc.rc_domain != XFS_REFC_DOMAIN_COW) xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0); + /* Can't start after bno */ + if (rc.rc_startblock > agbno) + xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0); + /* Must be at least as long as what was passed in */ - if (rc.rc_blockcount < len) + if (rc.rc_startblock + rc.rc_blockcount < agbno + len) xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0); } diff --git a/fs/xfs/scrub/rtrefcount.c b/fs/xfs/scrub/rtrefcount.c index a024d50cf9d2..652d6b78b7a0 100644 --- a/fs/xfs/scrub/rtrefcount.c +++ b/fs/xfs/scrub/rtrefcount.c @@ -609,8 +609,12 @@ xchk_xref_is_rt_cow_staging( if (rc.rc_domain != XFS_REFC_DOMAIN_COW) xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0); + /* Can't start after bno */ + if (rc.rc_startblock > bno) + xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0); + /* Must be at least as long as what was passed in */ - if (rc.rc_blockcount < len) + if (rc.rc_startblock + rc.rc_blockcount < bno + len) xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0); } From 3f9fd694fa429e89fe6de51b22b0ed5fb8b2daf4 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 2 Sep 2026 22:51:52 -0700 Subject: [PATCH 0821/1198] xfs: fix rtrefcount btree block counting in scrub LOLLM started on a long tangent about how xchk_refcount_xref_rmap shouldn't nope out if sc->sa.rmap_cur isn't set, because nothing ever sets that field. It's right about the condition, but misses the bigger problem, which is that to count the rtrefcount btree blocks, we have to walk all rmap records in each AG in the data section. That was papered over by the incorrect !sc->sa.rmap_cur test. In other words, we need a perag iteration loop here. Restructure the code to do that, and now it'll all work properly. Fix the confusing function name prefix. Cc: stable@vger.kernel.org # v6.14 Fixes: c27929670de144 ("xfs: scrub the realtime refcount btree") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/rtrefcount.c | 64 +++++++++++++++++++++++++++++++++------ 1 file changed, 55 insertions(+), 9 deletions(-) diff --git a/fs/xfs/scrub/rtrefcount.c b/fs/xfs/scrub/rtrefcount.c index 652d6b78b7a0..3d916d71a135 100644 --- a/fs/xfs/scrub/rtrefcount.c +++ b/fs/xfs/scrub/rtrefcount.c @@ -20,6 +20,7 @@ #include "xfs_metafile.h" #include "xfs_rtrefcount_btree.h" #include "xfs_rtalloc.h" +#include "xfs_ag.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/btree.h" @@ -504,30 +505,75 @@ xchk_rtrefcountbt_rec( return 0; } +/* Count the number of blocks used by the rtrefcount btree file in this AG. */ +static int +xchk_rtrefcount_count_agblocks( + struct xfs_scrub *sc, + xfs_agnumber_t agno, + const struct xfs_owner_info *btree_oinfo, + xfs_filblks_t *blocks) +{ + xfs_filblks_t agblocks = 0; + int error; + + error = xchk_ag_init_existing(sc, agno, &sc->sa); + if (error) + goto out_free; + + /* + * If we don't have an rmap cursor, we can't complete the cross + * referencing, so return EFSCORRUPTED to end the loop and trigger the + * XFAIL flag. + */ + if (!sc->sa.rmap_cur) { + error = -EFSCORRUPTED; + goto out_free; + } + + error = xchk_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, btree_oinfo, + &agblocks); + if (error) + goto out_free; + + *blocks += agblocks; +out_free: + xchk_ag_free(sc, &sc->sa); + return error; +} + /* Make sure we have as many refc blocks as the rmap says. */ STATIC void -xchk_refcount_xref_rmap( +xchk_rtrefcount_xref_rmap( struct xfs_scrub *sc, const struct xfs_owner_info *btree_oinfo, xfs_extlen_t cow_blocks) { xfs_filblks_t refcbt_blocks = 0; - xfs_filblks_t blocks; - int error; + xfs_filblks_t blocks = 1; /* one for the iroot */ + xfs_agnumber_t agno; + int error = 0; - if (!sc->sr.rmap_cur || !sc->sa.rmap_cur || xchk_skip_xref(sc->sm)) + if (!xfs_has_rmapbt(sc->mp) || xchk_skip_xref(sc->sm)) return; /* Check that we saw as many refcbt blocks as the rmap knows about. */ error = xfs_btree_count_blocks(sc->sr.refc_cur, &refcbt_blocks); if (!xchk_btree_process_error(sc, sc->sr.refc_cur, 0, &error)) return; - error = xchk_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, btree_oinfo, - &blocks); - if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur)) + + for (agno = 0; agno < sc->mp->m_sb.sb_agcount; agno++) { + error = xchk_rtrefcount_count_agblocks(sc, agno, btree_oinfo, + &blocks); + if (error) + break; + } + if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error)) return; if (blocks != refcbt_blocks) - xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0); + xchk_fblock_xref_set_corrupt(sc, XFS_DATA_FORK, 0); + + if (!sc->sr.rmap_cur || xchk_skip_xref(sc->sm)) + return; /* Check that we saw as many cow blocks as the rmap knows about. */ error = xchk_count_rmap_ownedby_ag(sc, sc->sr.rmap_cur, @@ -568,7 +614,7 @@ xchk_rtrefcountbt( */ xchk_rtrefcountbt_xref_gaps(sc, &rrc, xfs_rtx_to_rgbno(sc->sr.rtg, sc->mp->m_sb.sb_rgextents)); - xchk_refcount_xref_rmap(sc, &btree_oinfo, rrc.cow_blocks); + xchk_rtrefcount_xref_rmap(sc, &btree_oinfo, rrc.cow_blocks); return 0; } From 6b760b3232b3efc8bcc7c165e76300bc1c9140c5 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 2 Sep 2026 22:52:07 -0700 Subject: [PATCH 0822/1198] xfs: make the rtsummary repair fix the file size too LOLLM noticed that the rtsummary repair code will create a new rtsummary with the correct file size, but it won't force the new file size to be set on the existing rtsummary file, leaving the rtsummary corrupt. Fix this by setting up the tempfile mapping-exchange to run to the end of both files, which is the magic offset needed to reset the file size. Cc: stable@vger.kernel.org # v6.10 Fixes: abf039e2e4afde ("xfs: online repair of realtime summaries") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/rtsummary_repair.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/xfs/scrub/rtsummary_repair.c b/fs/xfs/scrub/rtsummary_repair.c index f065c3e51ce2..ed763290aec1 100644 --- a/fs/xfs/scrub/rtsummary_repair.c +++ b/fs/xfs/scrub/rtsummary_repair.c @@ -164,9 +164,10 @@ xrep_rtsummary( /* * Now exchange the contents. Nothing in repair uses the temporary * buffer, so we can reuse it for the tempfile exchrange information. + * Use XFS_MAX_FILEOFF here so that we correct the rtsummary file size. */ error = xrep_tempexch_trans_reserve(sc, XFS_DATA_FORK, 0, - rts->rsumblocks, &rts->tempexch); + XFS_MAX_FILEOFF, &rts->tempexch); if (error) return error; From 4d0624679ae29b469016f1ce4714be58582ed06a Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 2 Sep 2026 22:52:23 -0700 Subject: [PATCH 0823/1198] xfs: count escaped corruption errors in scrub stats The main scrub code will quietly turn bubbled-up EFSCORRUPTED and EFSBADCRC errors into corruption errors. These aren't recorded in the scrub stats code (says LOLLM) so do that now. Cc: stable@vger.kernel.org # v6.6 Fixes: d7a74cad8f4513 ("xfs: track usage statistics of online fsck") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/scrub.c | 3 +-- fs/xfs/scrub/stats.c | 28 +++++++++++++++++++--------- fs/xfs/scrub/stats.h | 4 ++-- 3 files changed, 22 insertions(+), 13 deletions(-) diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index 8742445c86f4..12c228b7f477 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -765,8 +765,7 @@ xfs_scrub_metadata( out_teardown: error = xchk_teardown(sc, error); out_sc: - if (error != -ENOENT) - xchk_stats_merge(mp, sm, &run); + xchk_stats_merge(mp, sm, error, &run); kfree(sc); out: trace_xchk_done(XFS_I(file_inode(file)), sm, error); diff --git a/fs/xfs/scrub/stats.c b/fs/xfs/scrub/stats.c index ef3f6abdb706..76f2515188d1 100644 --- a/fs/xfs/scrub/stats.c +++ b/fs/xfs/scrub/stats.c @@ -188,31 +188,37 @@ STATIC void xchk_stats_merge_one( struct xchk_stats *cs, const struct xfs_scrub_metadata *sm, + int error, const struct xchk_stats_run *run) { struct xchk_scrub_stats *css; + unsigned int sm_flags = sm->sm_flags; if (sm->sm_type >= XFS_SCRUB_TYPE_NR) { ASSERT(sm->sm_type < XFS_SCRUB_TYPE_NR); return; } + /* caller applies this same transformation after we return */ + if (error == -EFSCORRUPTED || error == -EFSBADCRC) + sm_flags |= XFS_SCRUB_OFLAG_CORRUPT; + css = &cs->cs_stats[sm->sm_type]; spin_lock(&css->css_lock); css->invocations++; - if (!(sm->sm_flags & XFS_SCRUB_OFLAG_UNCLEAN)) + if (!(sm_flags & XFS_SCRUB_OFLAG_UNCLEAN)) css->clean++; - if (sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + if (sm_flags & XFS_SCRUB_OFLAG_CORRUPT) css->corrupt++; - if (sm->sm_flags & XFS_SCRUB_OFLAG_PREEN) + if (sm_flags & XFS_SCRUB_OFLAG_PREEN) css->preen++; - if (sm->sm_flags & XFS_SCRUB_OFLAG_XFAIL) + if (sm_flags & XFS_SCRUB_OFLAG_XFAIL) css->xfail++; - if (sm->sm_flags & XFS_SCRUB_OFLAG_XCORRUPT) + if (sm_flags & XFS_SCRUB_OFLAG_XCORRUPT) css->xcorrupt++; - if (sm->sm_flags & XFS_SCRUB_OFLAG_INCOMPLETE) + if (sm_flags & XFS_SCRUB_OFLAG_INCOMPLETE) css->incomplete++; - if (sm->sm_flags & XFS_SCRUB_OFLAG_WARNING) + if (sm_flags & XFS_SCRUB_OFLAG_WARNING) css->warning++; css->retries += run->retries; css->checktime_us += howmany_64(run->scrub_ns, NSEC_PER_USEC); @@ -230,10 +236,14 @@ void xchk_stats_merge( struct xfs_mount *mp, const struct xfs_scrub_metadata *sm, + int error, const struct xchk_stats_run *run) { - xchk_stats_merge_one(&global_stats, sm, run); - xchk_stats_merge_one(mp->m_scrub_stats, sm, run); + if (error == -ENOENT) + return; + + xchk_stats_merge_one(&global_stats, sm, error, run); + xchk_stats_merge_one(mp->m_scrub_stats, sm, error, run); } /* debugfs boilerplate */ diff --git a/fs/xfs/scrub/stats.h b/fs/xfs/scrub/stats.h index b358ad8d8b90..221052b95dd0 100644 --- a/fs/xfs/scrub/stats.h +++ b/fs/xfs/scrub/stats.h @@ -27,7 +27,7 @@ void xchk_stats_register(struct xchk_stats *cs, struct dentry *parent); void xchk_stats_unregister(struct xchk_stats *cs); void xchk_stats_merge(struct xfs_mount *mp, const struct xfs_scrub_metadata *sm, - const struct xchk_stats_run *run); + int error, const struct xchk_stats_run *run); static inline u64 xchk_stats_now(void) { return ktime_get_ns(); } static inline u64 xchk_stats_elapsed_ns(u64 since) @@ -53,7 +53,7 @@ static inline u64 xchk_stats_elapsed_ns(u64 since) # define xchk_stats_unregister(cs) ((void)0) # define xchk_stats_now() (0) # define xchk_stats_elapsed_ns(x) (0 * (x)) -# define xchk_stats_merge(mp, sm, run) ((void)0) +# define xchk_stats_merge(mp, sm, error, run) ((void)0) #endif /* CONFIG_XFS_ONLINE_SCRUB_STATS */ #endif /* __XFS_SCRUB_STATS_H__ */ From 3837c3f29fbc3b8c12bebf5c62741e2befe3482a Mon Sep 17 00:00:00 2001 From: Magdalena Schulfer Date: Tue, 1 Sep 2026 14:57:47 +0200 Subject: [PATCH 0824/1198] accel/ivpu: Validate full buffer range in ivpu_to_cpu_addr Add a size parameter to ivpu_to_cpu_addr() and validate that the whole [vpu_addr, vpu_addr + size) range stays within the BO. Cc: stable@vger.kernel.org Fixes: 647371a6609d ("accel/ivpu: Add GEM buffer object management") Signed-off-by: Magdalena Schulfer Signed-off-by: Dawid Osuchowski Reviewed-by: Karol Wachowski Signed-off-by: Karol Wachowski Link: https://patch.msgid.link/20260901125749.404338-2-dawid.osuchowski@linux.intel.com --- drivers/accel/ivpu/ivpu_gem.h | 14 +++++++++++--- drivers/accel/ivpu/ivpu_ipc.c | 7 ++++--- 2 files changed, 15 insertions(+), 6 deletions(-) diff --git a/drivers/accel/ivpu/ivpu_gem.h b/drivers/accel/ivpu/ivpu_gem.h index 0c3350f22b55..b1ae020a4fc2 100644 --- a/drivers/accel/ivpu/ivpu_gem.h +++ b/drivers/accel/ivpu/ivpu_gem.h @@ -87,15 +87,23 @@ static inline bool ivpu_bo_is_resident(struct ivpu_bo *bo) return !!bo->base.pages; } -static inline void *ivpu_to_cpu_addr(struct ivpu_bo *bo, u32 vpu_addr) +static inline void *ivpu_to_cpu_addr(struct ivpu_bo *bo, u64 vpu_addr, u64 size) { + u64 bo_size = ivpu_bo_size(bo); + u64 offset; + if (vpu_addr < bo->vpu_addr) return NULL; - if (vpu_addr >= (bo->vpu_addr + ivpu_bo_size(bo))) + if (size > bo_size) return NULL; - return ivpu_bo_vaddr(bo) + (vpu_addr - bo->vpu_addr); + offset = vpu_addr - bo->vpu_addr; + + if (offset > bo_size - size) + return NULL; + + return ivpu_bo_vaddr(bo) + offset; } static inline u32 cpu_to_vpu_addr(struct ivpu_bo *bo, void *cpu_addr) diff --git a/drivers/accel/ivpu/ivpu_ipc.c b/drivers/accel/ivpu/ivpu_ipc.c index 62607ec8ca8f..8e960293b77a 100644 --- a/drivers/accel/ivpu/ivpu_ipc.c +++ b/drivers/accel/ivpu/ivpu_ipc.c @@ -79,7 +79,7 @@ ivpu_ipc_tx_prepare(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons, return -ENOMEM; } - tx_buf = ivpu_to_cpu_addr(ipc->mem_tx, tx_buf_vpu_addr); + tx_buf = ivpu_to_cpu_addr(ipc->mem_tx, tx_buf_vpu_addr, sizeof(*tx_buf)); if (drm_WARN_ON(&vdev->drm, !tx_buf)) { gen_pool_free(ipc->mm_tx, tx_buf_vpu_addr, sizeof(*tx_buf)); return -EIO; @@ -420,7 +420,7 @@ void ivpu_ipc_irq_handler(struct ivpu_device *vdev) return; } - ipc_hdr = ivpu_to_cpu_addr(ipc->mem_rx, vpu_addr); + ipc_hdr = ivpu_to_cpu_addr(ipc->mem_rx, vpu_addr, sizeof(*ipc_hdr)); if (!ipc_hdr) { ivpu_warn_ratelimited(vdev, "IPC msg 0x%x out of range\n", vpu_addr); continue; @@ -429,7 +429,8 @@ void ivpu_ipc_irq_handler(struct ivpu_device *vdev) jsm_msg = NULL; if (ipc_hdr->channel != IVPU_IPC_CHAN_BOOT_MSG) { - jsm_msg = ivpu_to_cpu_addr(ipc->mem_rx, ipc_hdr->data_addr); + jsm_msg = ivpu_to_cpu_addr(ipc->mem_rx, ipc_hdr->data_addr, + sizeof(*jsm_msg)); if (!jsm_msg) { ivpu_warn_ratelimited(vdev, "JSM msg 0x%x out of range\n", ipc_hdr->data_addr); From 0724afc55c77c36c7feb9a7264b02aa7593c5c2d Mon Sep 17 00:00:00 2001 From: Magdalena Schulfer Date: Tue, 1 Sep 2026 14:57:48 +0200 Subject: [PATCH 0825/1198] accel/ivpu: Validate firmware log buffer metadata The tracing log headers parsed by fw_log_print_buffer() reside in DMA-shared BOs that the NPU firmware can write to. fw_log_from_bo() validated log->header_size and log->size, but fw_log_print_buffer() re-read those same fields from shared memory afterwards, allowing a TOCTOU where firmware changes them between the check and the use, and making the host dereference out-of-bounds addresses while printing logs. Snapshot the validated values once with READ_ONCE() and pass them down explicitly in a new struct ivpu_fw_log_desc instead of re-reading them from the shared struct. Cc: stable@vger.kernel.org Fixes: d4e4257afa6e ("accel/ivpu: Add firmware tracing support") Signed-off-by: Magdalena Schulfer Signed-off-by: Dawid Osuchowski Reviewed-by: Karol Wachowski Signed-off-by: Karol Wachowski Link: https://patch.msgid.link/20260901125749.404338-3-dawid.osuchowski@linux.intel.com --- drivers/accel/ivpu/ivpu_fw_log.c | 76 +++++++++++++++++++------------- 1 file changed, 45 insertions(+), 31 deletions(-) diff --git a/drivers/accel/ivpu/ivpu_fw_log.c b/drivers/accel/ivpu/ivpu_fw_log.c index 716467aa3156..4f9055aa9d33 100644 --- a/drivers/accel/ivpu/ivpu_fw_log.c +++ b/drivers/accel/ivpu/ivpu_fw_log.c @@ -26,10 +26,17 @@ MODULE_PARM_DESC(fw_log_level, " error=" __stringify(IVPU_FW_LOG_ERROR) " fatal=" __stringify(IVPU_FW_LOG_FATAL)); +struct ivpu_fw_log_desc { + struct vpu_tracing_buffer_header *log; + u32 header_size; + u32 size; +}; + static int fw_log_from_bo(struct ivpu_device *vdev, struct ivpu_bo *bo, u32 *offset, - struct vpu_tracing_buffer_header **out_log) + struct ivpu_fw_log_desc *desc) { struct vpu_tracing_buffer_header *log; + u32 header_size, size; if ((*offset + sizeof(*log)) > ivpu_bo_size(bo)) return -EINVAL; @@ -39,26 +46,32 @@ static int fw_log_from_bo(struct ivpu_device *vdev, struct ivpu_bo *bo, u32 *off if (log->vpu_canary_start != VPU_TRACING_BUFFER_CANARY) return -EINVAL; - if (log->header_size < sizeof(*log) || log->header_size > 1024) { - ivpu_dbg(vdev, FW_BOOT, "Invalid header size 0x%x\n", log->header_size); + header_size = READ_ONCE(log->header_size); + size = READ_ONCE(log->size); + + if (header_size < sizeof(*log) || header_size > 1024) { + ivpu_dbg(vdev, FW_BOOT, "Invalid header size 0x%x\n", header_size); return -EINVAL; } - if (log->size < log->header_size) { - ivpu_dbg(vdev, FW_BOOT, "Invalid log size 0x%x\n", log->size); + if ((char *)log + size > (char *)ivpu_bo_vaddr(bo) + ivpu_bo_size(bo)) { + ivpu_dbg(vdev, FW_BOOT, "Invalid log size 0x%x\n", size); return -EINVAL; } - if ((char *)log + log->size > (char *)ivpu_bo_vaddr(bo) + ivpu_bo_size(bo)) { - ivpu_dbg(vdev, FW_BOOT, "Invalid log size 0x%x\n", log->size); + if (size < header_size) { + ivpu_dbg(vdev, FW_BOOT, "Invalid log size 0x%x < header size 0x%x\n", + size, header_size); return -EINVAL; } - *out_log = log; - *offset += log->size; + desc->log = log; + desc->header_size = header_size; + desc->size = size; + *offset += size; ivpu_dbg(vdev, FW_BOOT, "FW log name \"%s\", write offset 0x%x size 0x%x, wrap count %d, hdr version %d size %d format %d, alignment %d", - log->name, log->write_index, log->size, log->wrap_count, log->header_version, - log->header_size, log->format, log->alignment); + log->name, log->write_index, size, log->wrap_count, log->header_version, + header_size, log->format, log->alignment); return 0; } @@ -94,11 +107,12 @@ static void fw_log_print_lines(char *buffer, u32 size, struct drm_printer *p) drm_printf(p, "%s", line); } -static void fw_log_print_buffer(struct vpu_tracing_buffer_header *log, const char *prefix, +static void fw_log_print_buffer(struct ivpu_fw_log_desc *desc, const char *prefix, bool only_new_msgs, struct drm_printer *p) { - char *log_data = (void *)log + log->header_size; - u32 data_size = log->size - log->header_size; + struct vpu_tracing_buffer_header *log = desc->log; + char *log_data = (void *)log + desc->header_size; + u32 data_size = desc->size - desc->header_size; u32 log_start = only_new_msgs ? READ_ONCE(log->read_index) : 0; u32 log_end = READ_ONCE(log->write_index); @@ -134,11 +148,11 @@ static void fw_log_print_all_in_bo(struct ivpu_device *vdev, const char *name, struct ivpu_bo *bo, bool only_new_msgs, struct drm_printer *p) { - struct vpu_tracing_buffer_header *log; + struct ivpu_fw_log_desc desc; u32 next = 0; - while (fw_log_from_bo(vdev, bo, &next, &log) == 0) - fw_log_print_buffer(log, name, only_new_msgs, p); + while (fw_log_from_bo(vdev, bo, &next, &desc) == 0) + fw_log_print_buffer(&desc, name, only_new_msgs, p); } void ivpu_fw_log_print(struct ivpu_device *vdev, bool only_new_msgs, struct drm_printer *p) @@ -149,36 +163,36 @@ void ivpu_fw_log_print(struct ivpu_device *vdev, bool only_new_msgs, struct drm_ void ivpu_fw_log_mark_read(struct ivpu_device *vdev) { - struct vpu_tracing_buffer_header *log; + struct ivpu_fw_log_desc desc; u32 next; next = 0; - while (fw_log_from_bo(vdev, vdev->fw->mem_log_crit, &next, &log) == 0) { - log->read_index = READ_ONCE(log->write_index); - log->read_wrap_count = READ_ONCE(log->wrap_count); + while (fw_log_from_bo(vdev, vdev->fw->mem_log_crit, &next, &desc) == 0) { + desc.log->read_index = READ_ONCE(desc.log->write_index); + desc.log->read_wrap_count = READ_ONCE(desc.log->wrap_count); } next = 0; - while (fw_log_from_bo(vdev, vdev->fw->mem_log_verb, &next, &log) == 0) { - log->read_index = READ_ONCE(log->write_index); - log->read_wrap_count = READ_ONCE(log->wrap_count); + while (fw_log_from_bo(vdev, vdev->fw->mem_log_verb, &next, &desc) == 0) { + desc.log->read_index = READ_ONCE(desc.log->write_index); + desc.log->read_wrap_count = READ_ONCE(desc.log->wrap_count); } } void ivpu_fw_log_reset(struct ivpu_device *vdev) { - struct vpu_tracing_buffer_header *log; + struct ivpu_fw_log_desc desc; u32 next; next = 0; - while (fw_log_from_bo(vdev, vdev->fw->mem_log_crit, &next, &log) == 0) { - log->read_index = 0; - log->read_wrap_count = 0; + while (fw_log_from_bo(vdev, vdev->fw->mem_log_crit, &next, &desc) == 0) { + desc.log->read_index = 0; + desc.log->read_wrap_count = 0; } next = 0; - while (fw_log_from_bo(vdev, vdev->fw->mem_log_verb, &next, &log) == 0) { - log->read_index = 0; - log->read_wrap_count = 0; + while (fw_log_from_bo(vdev, vdev->fw->mem_log_verb, &next, &desc) == 0) { + desc.log->read_index = 0; + desc.log->read_wrap_count = 0; } } From 95bf070f3225dc7175725438c916ad321d42fe45 Mon Sep 17 00:00:00 2001 From: Dawid Osuchowski Date: Tue, 1 Sep 2026 14:57:49 +0200 Subject: [PATCH 0826/1198] accel/ivpu: Limit firmware log name prints to field size The name in struct vpu_tracing_buffer_header is a fixed-size array populated by the NPU firmware. It is expected to be NUL-terminated, but nothing on the host side enforces this, so printing it with an unbounded string conversion would read past the field if the terminator is ever missing and expose adjacent bytes of the shared tracing BO through dmesg and the debugfs FW log output. Print at most as many characters as the name field holds, so the output never runs past it even if the string is not NUL-terminated. Cc: stable@vger.kernel.org Reported-by: sashiko-bot Closes: https://sashiko.dev/#/patchset/20260827102339.281799-1-dawid.osuchowski@linux.intel.com?part=2 Fixes: d4e4257afa6e ("accel/ivpu: Add firmware tracing support") Signed-off-by: Dawid Osuchowski Reviewed-by: Karol Wachowski Signed-off-by: Karol Wachowski Link: https://patch.msgid.link/20260901125749.404338-4-dawid.osuchowski@linux.intel.com --- drivers/accel/ivpu/ivpu_fw_log.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/accel/ivpu/ivpu_fw_log.c b/drivers/accel/ivpu/ivpu_fw_log.c index 4f9055aa9d33..9eafc42120b6 100644 --- a/drivers/accel/ivpu/ivpu_fw_log.c +++ b/drivers/accel/ivpu/ivpu_fw_log.c @@ -69,9 +69,9 @@ static int fw_log_from_bo(struct ivpu_device *vdev, struct ivpu_bo *bo, u32 *off *offset += size; ivpu_dbg(vdev, FW_BOOT, - "FW log name \"%s\", write offset 0x%x size 0x%x, wrap count %d, hdr version %d size %d format %d, alignment %d", - log->name, log->write_index, size, log->wrap_count, log->header_version, - header_size, log->format, log->alignment); + "FW log name \"%.*s\", write offset 0x%x size 0x%x, wrap count %d, hdr version %d size %d format %d, alignment %d", + (int)ARRAY_SIZE(log->name), log->name, log->write_index, size, log->wrap_count, + log->header_version, header_size, log->format, log->alignment); return 0; } @@ -123,7 +123,8 @@ static void fw_log_print_buffer(struct ivpu_fw_log_desc *desc, const char *prefi if (log->wrap_count == log->read_wrap_count) { if (log_end <= log_start) { - drm_printf(p, "==== %s \"%s\" log empty ====\n", prefix, log->name); + drm_printf(p, "==== %s \"%.*s\" log empty ====\n", prefix, + (int)ARRAY_SIZE(log->name), log->name); return; } } else if (log->wrap_count == log->read_wrap_count + 1) { @@ -133,7 +134,8 @@ static void fw_log_print_buffer(struct ivpu_fw_log_desc *desc, const char *prefi log_start = log_end; } - drm_printf(p, "==== %s \"%s\" log start ====\n", prefix, log->name); + drm_printf(p, "==== %s \"%.*s\" log start ====\n", prefix, (int)ARRAY_SIZE(log->name), + log->name); if (log_end > log_start) { fw_log_print_lines(log_data + log_start, log_end - log_start, p); } else { @@ -141,7 +143,8 @@ static void fw_log_print_buffer(struct ivpu_fw_log_desc *desc, const char *prefi fw_log_print_lines(log_data, log_end, p); } drm_printf(p, "\n\x1b[0m"); /* add new line and clear formatting */ - drm_printf(p, "==== %s \"%s\" log end ====\n", prefix, log->name); + drm_printf(p, "==== %s \"%.*s\" log end ====\n", prefix, (int)ARRAY_SIZE(log->name), + log->name); } static void From 157dcb8230a4e882e099ec4d1cb1957b0b2c9b26 Mon Sep 17 00:00:00 2001 From: Zizhi Wo Date: Sat, 5 Sep 2026 09:03:54 +0800 Subject: [PATCH 0827/1198] xfs: remove several unused and never-implemented declarations Over time a number of function declarations in various headers have become stale: either their implementations were removed when their last callers went away, or they were never implemented in the first place. None of them refer to anything anymore. Remove the following dead declarations and the unused stub: - xlog_assign_tail_lsn() and xlog_assign_tail_lsn_locked() - xfs_iext_realloc() - xfs_buf_iodone() - xfs_scrub_tester() and xfs_scrub_setup_inode_bmap_data() (never implemented placeholders) - the !CONFIG_XFS_ONLINE_REPAIR stub of xrep_tempfile_iolock_both() Signed-off-by: Zizhi Wo Reviewed-by: Carlos Maiolino Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/common.h | 1 - fs/xfs/scrub/scrub.h | 1 - fs/xfs/scrub/tempfile.h | 4 ---- fs/xfs/xfs_buf_item.h | 1 - fs/xfs/xfs_inode.h | 1 - fs/xfs/xfs_log.h | 2 -- 6 files changed, 10 deletions(-) diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h index 9d627fd50687..f0f073a93413 100644 --- a/fs/xfs/scrub/common.h +++ b/fs/xfs/scrub/common.h @@ -74,7 +74,6 @@ int xchk_setup_ag_rmapbt(struct xfs_scrub *sc); int xchk_setup_ag_refcountbt(struct xfs_scrub *sc); int xchk_setup_inode(struct xfs_scrub *sc); int xchk_setup_inode_bmap(struct xfs_scrub *sc); -int xchk_setup_inode_bmap_data(struct xfs_scrub *sc); int xchk_setup_directory(struct xfs_scrub *sc); int xchk_setup_xattr(struct xfs_scrub *sc); int xchk_setup_symlink(struct xfs_scrub *sc); diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h index 6d7d3523b71f..737a5d6db15f 100644 --- a/fs/xfs/scrub/scrub.h +++ b/fs/xfs/scrub/scrub.h @@ -261,7 +261,6 @@ static inline int xchk_nothing(struct xfs_scrub *sc) } /* Metadata scrubbers */ -int xchk_tester(struct xfs_scrub *sc); int xchk_superblock(struct xfs_scrub *sc); int xchk_agf(struct xfs_scrub *sc); int xchk_agfl(struct xfs_scrub *sc); diff --git a/fs/xfs/scrub/tempfile.h b/fs/xfs/scrub/tempfile.h index 71c1b54599c3..d44ed43bafe0 100644 --- a/fs/xfs/scrub/tempfile.h +++ b/fs/xfs/scrub/tempfile.h @@ -39,10 +39,6 @@ int xrep_tempfile_roll_trans(struct xfs_scrub *sc); void xrep_tempfile_copyout_local(struct xfs_scrub *sc, int whichfork); bool xrep_is_tempfile(const struct xfs_inode *ip); #else -static inline void xrep_tempfile_iolock_both(struct xfs_scrub *sc) -{ - xchk_ilock(sc, XFS_IOLOCK_EXCL); -} # define xrep_is_tempfile(ip) (false) # define xrep_tempfile_adjust_directory_tree(sc) (0) # define xrep_tempfile_rele(sc) diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h index 3159325dd17b..28c79989d725 100644 --- a/fs/xfs/xfs_buf_item.h +++ b/fs/xfs/xfs_buf_item.h @@ -60,7 +60,6 @@ static inline void xfs_buf_dquot_iodone(struct xfs_buf *bp) { } #endif /* CONFIG_XFS_QUOTA */ -void xfs_buf_iodone(struct xfs_buf *); bool xfs_buf_log_check_iovec(struct kvec *iovec); unsigned int xfs_buf_inval_log_space(unsigned int map_count, diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 34c1038ebfcd..1602027cd0aa 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -585,7 +585,6 @@ uint xfs_ilock_attr_map_shared(struct xfs_inode *); int xfs_ifree(struct xfs_trans *, struct xfs_inode *); int xfs_itruncate_extents_flags(struct xfs_trans **, struct xfs_inode *, int, xfs_fsize_t, int); -void xfs_iext_realloc(xfs_inode_t *, int, int); int xfs_log_force_inode(struct xfs_inode *ip); void xfs_iunpin_wait(xfs_inode_t *); diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h index ca66429bf6c9..f715695e8fcb 100644 --- a/fs/xfs/xfs_log.h +++ b/fs/xfs/xfs_log.h @@ -105,8 +105,6 @@ int xfs_log_mount(struct xfs_mount *mp, int num_bblocks); int xfs_log_mount_finish(struct xfs_mount *mp); void xfs_log_mount_cancel(struct xfs_mount *); -xfs_lsn_t xlog_assign_tail_lsn(struct xfs_mount *mp); -xfs_lsn_t xlog_assign_tail_lsn_locked(struct xfs_mount *mp); void xfs_log_space_wake(struct xfs_mount *mp); int xfs_log_reserve(struct xfs_mount *mp, int length, int count, struct xlog_ticket **ticket, bool permanent); From 45a5f7285f835adb3b74c9344c09a7bd2c4fb664 Mon Sep 17 00:00:00 2001 From: Madhavan Srinivasan Date: Tue, 18 Aug 2026 09:20:37 +0530 Subject: [PATCH 0828/1198] MAINTAINERS: powerpc: Add Ritesh and Shrikanth Ritesh and Shrikanth has been helping in the powerpc mailing list patch reviews, adding them as reviewers. Acked-by: Shrikanth Hegde Acked-by: Ritesh Harjani (IBM) Acked-by: Christophe Leroy (CS GROUP) Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260818035037.613186-1-maddy@linux.ibm.com --- MAINTAINERS | 2 ++ 1 file changed, 2 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 3a19da74d00c..342cc5400fb4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15027,6 +15027,8 @@ M: Madhavan Srinivasan R: Michael Ellerman R: Nicholas Piggin R: Christophe Leroy (CS GROUP) +R: Ritesh Harjani (IBM) +R: Shrikanth Hegde L: linuxppc-dev@lists.ozlabs.org S: Supported W: https://github.com/linuxppc/wiki/wiki From 10e59fbdef13597836bd6459095caa02c80af3d7 Mon Sep 17 00:00:00 2001 From: Haotian Zhang Date: Tue, 1 Sep 2026 10:23:09 +0800 Subject: [PATCH 0829/1198] media: v4l2-h264: Fix memcmp() size in B1 reference list comparison In v4l2_h264_build_b_ref_lists(), the B0/B1 list equality check passes the entry count builder->num_valid to memcmp() instead of a byte size. Since struct v4l2_h264_reference is two bytes (fields and index), only half of each list is compared, so distinct lists can be wrongly treated as equal and trigger an incorrect swap(b1_reflist[0], b1_reflist[1]). Change the memcmp() size argument to sizeof(b1_reflist[0]) * builder->num_valid so that the full byte length of both reference lists is compared. Fixes: 624922a2739b ("media: v4l2-core: Add helpers to build the H264 P/B0/B1 reflists") Suggested-by: Nicolas Dufresne Cc: stable@vger.kernel.org Signed-off-by: Haotian Zhang Reviewed-by: Nicolas Dufresne Signed-off-by: Hans Verkuil --- drivers/media/v4l2-core/v4l2-h264.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/media/v4l2-core/v4l2-h264.c b/drivers/media/v4l2-core/v4l2-h264.c index c00197d095e7..2323f559c6a3 100644 --- a/drivers/media/v4l2-core/v4l2-h264.c +++ b/drivers/media/v4l2-core/v4l2-h264.c @@ -440,7 +440,8 @@ v4l2_h264_build_b_ref_lists(const struct v4l2_h264_reflist_builder *builder, } if (builder->num_valid > 1 && - !memcmp(b1_reflist, b0_reflist, builder->num_valid)) + !memcmp(b1_reflist, b0_reflist, + sizeof(b1_reflist[0]) * builder->num_valid)) swap(b1_reflist[0], b1_reflist[1]); print_ref_list_b(builder, b0_reflist, 0); From dc694a9929f7cb9c88ef91e45eb982b7bbe5a477 Mon Sep 17 00:00:00 2001 From: Michael Bommarito Date: Tue, 16 Jun 2026 22:18:58 -0400 Subject: [PATCH 0830/1198] media: v4l2-ctrls: validate HEVC tile counts The stateless HEVC decoders read num_tile_columns_minus1 + 1 entries from column_width_minus1[] and num_tile_rows_minus1 + 1 from row_height_minus1[] and use them as tile-loop bounds, but std_validate_compound() does not bound these u8 counts. Reject a V4L2_CTRL_TYPE_HEVC_PPS with tiling enabled whose tile counts exceed the uAPI array capacity, mirroring the existing compound-control range checks. Fixes: 256fa3920874 ("media: v4l: Add definitions for HEVC stateless decoding") Assisted-by: Claude:claude-opus-4-8 Cc: stable@vger.kernel.org Signed-off-by: Michael Bommarito Reviewed-by: Benjamin Gaignard Signed-off-by: Hans Verkuil --- drivers/media/v4l2-core/v4l2-ctrls-core.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/media/v4l2-core/v4l2-ctrls-core.c b/drivers/media/v4l2-core/v4l2-ctrls-core.c index 5b8a594fb9e2..9b6121a3a2d2 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls-core.c +++ b/drivers/media/v4l2-core/v4l2-ctrls-core.c @@ -1253,6 +1253,18 @@ static int std_validate_compound(const struct v4l2_ctrl *ctrl, u32 idx, p_hevc_pps->flags &= ~V4L2_HEVC_PPS_FLAG_LOOP_FILTER_ACROSS_TILES_ENABLED; + } else { + /* + * These count the entries the stateless HEVC drivers + * read from column_width_minus1[] / row_height_minus1[] + * and use as tile-loop bounds. + */ + if (p_hevc_pps->num_tile_columns_minus1 >= + ARRAY_SIZE(p_hevc_pps->column_width_minus1)) + return -EINVAL; + if (p_hevc_pps->num_tile_rows_minus1 >= + ARRAY_SIZE(p_hevc_pps->row_height_minus1)) + return -EINVAL; } if (p_hevc_pps->flags & From 439058ced617fbb3febc017b9e93bb7387f309e0 Mon Sep 17 00:00:00 2001 From: Michael Bommarito Date: Tue, 16 Jun 2026 22:18:59 -0400 Subject: [PATCH 0831/1198] media: v4l2-ctrls: validate AV1 tile counts The stateless AV1 decoders use tile_info.tile_cols and tile_rows as loop bounds and as indices into the mi_*_starts[] and *_in_sbs_minus_1[] arrays, as the divisor for context_update_tile_id, and their product bounds the per-tile descriptor buffers, but std_validate_compound() does not bound these u8 fields. Reject a V4L2_CTRL_TYPE_AV1_FRAME whose tile_cols or tile_rows exceeds V4L2_AV1_MAX_TILE_COLS / _ROWS, or whose product exceeds V4L2_AV1_MAX_TILE_COUNT. A zero tile count is left to the consuming driver so the zero-initialised control that existing userspace submits is still accepted. Fixes: 9de30f579980 ("media: Add AV1 uAPI") Assisted-by: Claude:claude-opus-4-8 Cc: stable@vger.kernel.org Signed-off-by: Michael Bommarito Reviewed-by: Benjamin Gaignard Signed-off-by: Hans Verkuil --- drivers/media/v4l2-core/v4l2-ctrls-core.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/drivers/media/v4l2-core/v4l2-ctrls-core.c b/drivers/media/v4l2-core/v4l2-ctrls-core.c index 9b6121a3a2d2..648b88c868bc 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls-core.c +++ b/drivers/media/v4l2-core/v4l2-ctrls-core.c @@ -793,10 +793,30 @@ static int validate_av1_film_grain(struct v4l2_ctrl_av1_film_grain *fg) return 0; } +static int validate_av1_tile_info(struct v4l2_av1_tile_info *t) +{ + /* + * tile_cols and tile_rows index the per-tile descriptor arrays and + * bound the tile loops in the stateless AV1 drivers; the product + * bounds the total tile descriptor count. + */ + if (t->tile_cols > V4L2_AV1_MAX_TILE_COLS || + t->tile_rows > V4L2_AV1_MAX_TILE_ROWS) + return -EINVAL; + + if ((u32)t->tile_cols * t->tile_rows > V4L2_AV1_MAX_TILE_COUNT) + return -EINVAL; + + return 0; +} + static int validate_av1_frame(struct v4l2_ctrl_av1_frame *f) { int ret = 0; + ret = validate_av1_tile_info(&f->tile_info); + if (ret) + return ret; ret = validate_av1_quantization(&f->quantization); if (ret) return ret; From 592dd4f8442a13bed6e946d73d3164ba38b33bbd Mon Sep 17 00:00:00 2001 From: Michael Bommarito Date: Tue, 16 Jun 2026 22:19:00 -0400 Subject: [PATCH 0832/1198] media: hevc: add bounded tile-count helpers The stateless HEVC decoders compute the number of tile columns and rows from num_tile_columns_minus1 / num_tile_rows_minus1 and clamp it to the column_width_minus1[] / row_height_minus1[] capacity before using it as a loop bound. Add shared helpers in a new so the rkvdec and hantro drivers do not each open-code the min_t() clamp. Signed-off-by: Michael Bommarito Assisted-by: Claude:claude-opus-4-8 Fixes: 256fa3920874 ("media: v4l: Add definitions for HEVC stateless decoding") Cc: stable@vger.kernel.org Reviewed-by: Benjamin Gaignard Signed-off-by: Hans Verkuil --- include/media/v4l2-hevc.h | 41 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) create mode 100644 include/media/v4l2-hevc.h diff --git a/include/media/v4l2-hevc.h b/include/media/v4l2-hevc.h new file mode 100644 index 000000000000..973c96be16be --- /dev/null +++ b/include/media/v4l2-hevc.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Helper functions for HEVC stateless codecs. + */ + +#ifndef _MEDIA_V4L2_HEVC_H +#define _MEDIA_V4L2_HEVC_H + +#include +#include + +/** + * v4l2_hevc_pps_num_tile_columns - number of HEVC tile columns, bounded + * @pps: the V4L2 HEVC PPS control + * + * Return the number of tile columns (num_tile_columns_minus1 + 1) clamped to + * the capacity of column_width_minus1[]. The control validation already + * rejects out-of-range counts; this keeps the consuming drivers bounded too. + */ +static inline unsigned int +v4l2_hevc_pps_num_tile_columns(const struct v4l2_ctrl_hevc_pps *pps) +{ + return min_t(unsigned int, pps->num_tile_columns_minus1 + 1, + ARRAY_SIZE(pps->column_width_minus1)); +} + +/** + * v4l2_hevc_pps_num_tile_rows - number of HEVC tile rows, bounded + * @pps: the V4L2 HEVC PPS control + * + * Return the number of tile rows (num_tile_rows_minus1 + 1) clamped to the + * capacity of row_height_minus1[]. + */ +static inline unsigned int +v4l2_hevc_pps_num_tile_rows(const struct v4l2_ctrl_hevc_pps *pps) +{ + return min_t(unsigned int, pps->num_tile_rows_minus1 + 1, + ARRAY_SIZE(pps->row_height_minus1)); +} + +#endif /* _MEDIA_V4L2_HEVC_H */ From 81ad46bb33d8fd279aaa33af5296c648814c964b Mon Sep 17 00:00:00 2001 From: Michael Bommarito Date: Tue, 16 Jun 2026 22:19:01 -0400 Subject: [PATCH 0833/1198] media: rkvdec: bound HEVC tile loops and PPS id to the array capacity compute_tiles_uniform() and compute_tiles_non_uniform() loop over num_tile_columns_minus1 + 1 / num_tile_rows_minus1 + 1 entries, and assemble_hw_pps() writes one COLUMN_WIDTH / ROW_HEIGHT register per tile and indexes priv_tbl->param_set[] by pic_parameter_set_id, all taken from the untrusted PPS. Use the bounded v4l2_hevc_pps_num_tile_columns() / v4l2_hevc_pps_num_tile_rows() helpers for the tile loops, and bail out of assemble_hw_pps() before indexing priv_tbl->param_set[] with an out-of-range pic_parameter_set_id, so the writes stay within the hardware tables. Fixes: 3595375c2301 ("media: rkvdec: Add HEVC backend") Fixes: c9a59dc2acc7 ("media: rkvdec: Add HEVC support for the VDPU381 variant") Assisted-by: Claude:claude-opus-4-8 Cc: stable@vger.kernel.org Signed-off-by: Michael Bommarito Signed-off-by: Hans Verkuil --- .../platform/rockchip/rkvdec/rkvdec-hevc-common.c | 14 ++++++++++---- .../media/platform/rockchip/rkvdec/rkvdec-hevc.c | 7 +++++-- .../platform/rockchip/rkvdec/rkvdec-vdpu381-hevc.c | 2 ++ 3 files changed, 17 insertions(+), 6 deletions(-) diff --git a/drivers/media/platform/rockchip/rkvdec/rkvdec-hevc-common.c b/drivers/media/platform/rockchip/rkvdec/rkvdec-hevc-common.c index 9c4a6093af32..2b8e04dd1572 100644 --- a/drivers/media/platform/rockchip/rkvdec/rkvdec-hevc-common.c +++ b/drivers/media/platform/rockchip/rkvdec/rkvdec-hevc-common.c @@ -16,6 +16,7 @@ */ #include +#include #include #include "rkvdec.h" @@ -37,15 +38,17 @@ void compute_tiles_uniform(struct rkvdec_hevc_run *run, u16 log2_min_cb_size, s32 pic_in_cts_height, u16 *column_width, u16 *row_height) { const struct v4l2_ctrl_hevc_pps *pps = run->pps; + unsigned int num_cols = v4l2_hevc_pps_num_tile_columns(pps); + unsigned int num_rows = v4l2_hevc_pps_num_tile_rows(pps); int i; - for (i = 0; i < pps->num_tile_columns_minus1 + 1; i++) + for (i = 0; i < num_cols; i++) column_width[i] = ((i + 1) * pic_in_cts_width) / (pps->num_tile_columns_minus1 + 1) - (i * pic_in_cts_width) / (pps->num_tile_columns_minus1 + 1); - for (i = 0; i < pps->num_tile_rows_minus1 + 1; i++) + for (i = 0; i < num_rows; i++) row_height[i] = ((i + 1) * pic_in_cts_height) / (pps->num_tile_rows_minus1 + 1) - (i * pic_in_cts_height) / @@ -57,17 +60,20 @@ void compute_tiles_non_uniform(struct rkvdec_hevc_run *run, u16 log2_min_cb_size s32 pic_in_cts_height, u16 *column_width, u16 *row_height) { const struct v4l2_ctrl_hevc_pps *pps = run->pps; + unsigned int num_cols = v4l2_hevc_pps_num_tile_columns(pps); + unsigned int num_rows = v4l2_hevc_pps_num_tile_rows(pps); s32 sum = 0; int i; - for (i = 0; i < pps->num_tile_columns_minus1; i++) { + /* The last tile entry is written after the loop, so iterate one less. */ + for (i = 0; i < num_cols - 1; i++) { column_width[i] = pps->column_width_minus1[i] + 1; sum += column_width[i]; } column_width[i] = pic_in_cts_width - sum; sum = 0; - for (i = 0; i < pps->num_tile_rows_minus1; i++) { + for (i = 0; i < num_rows - 1; i++) { row_height[i] = pps->row_height_minus1[i] + 1; sum += row_height[i]; } diff --git a/drivers/media/platform/rockchip/rkvdec/rkvdec-hevc.c b/drivers/media/platform/rockchip/rkvdec/rkvdec-hevc.c index ff3942f91c5d..88e90c438eb9 100644 --- a/drivers/media/platform/rockchip/rkvdec/rkvdec-hevc.c +++ b/drivers/media/platform/rockchip/rkvdec/rkvdec-hevc.c @@ -12,6 +12,7 @@ * Jeffy Chen */ +#include #include #include "rkvdec.h" @@ -135,6 +136,8 @@ static void assemble_hw_pps(struct rkvdec_ctx *ctx, * packet unit). so the driver copy SPS/PPS information to the exact PPS * packet unit for HW accessing. */ + if (pps->pic_parameter_set_id >= ARRAY_SIZE(priv_tbl->param_set)) + return; hw_ps = &priv_tbl->param_set[pps->pic_parameter_set_id]; memset(hw_ps, 0, sizeof(*hw_ps)); @@ -253,9 +256,9 @@ static void assemble_hw_pps(struct rkvdec_ctx *ctx, if (pps->flags & V4L2_HEVC_PPS_FLAG_TILES_ENABLED) { /* Userspace also provide column width and row height for uniform spacing */ - for (i = 0; i <= pps->num_tile_columns_minus1; i++) + for (i = 0; i < v4l2_hevc_pps_num_tile_columns(pps); i++) WRITE_PPS(pps->column_width_minus1[i], COLUMN_WIDTH(i)); - for (i = 0; i <= pps->num_tile_rows_minus1; i++) + for (i = 0; i < v4l2_hevc_pps_num_tile_rows(pps); i++) WRITE_PPS(pps->row_height_minus1[i], ROW_HEIGHT(i)); } else { WRITE_PPS(DIV_ROUND_UP(sps->pic_width_in_luma_samples, ctb_size_y) - 1, diff --git a/drivers/media/platform/rockchip/rkvdec/rkvdec-vdpu381-hevc.c b/drivers/media/platform/rockchip/rkvdec/rkvdec-vdpu381-hevc.c index d07c74679552..e1936e87f45b 100644 --- a/drivers/media/platform/rockchip/rkvdec/rkvdec-vdpu381-hevc.c +++ b/drivers/media/platform/rockchip/rkvdec/rkvdec-vdpu381-hevc.c @@ -145,6 +145,8 @@ static void assemble_hw_pps(struct rkvdec_ctx *ctx, * packet unit). so the driver copy SPS/PPS information to the exact PPS * packet unit for HW accessing. */ + if (pps->pic_parameter_set_id >= ARRAY_SIZE(priv_tbl->param_set)) + return; hw_ps = &priv_tbl->param_set[pps->pic_parameter_set_id]; memset(hw_ps, 0, sizeof(*hw_ps)); From 06236b094c899c22c12ac5097935eb6719293de8 Mon Sep 17 00:00:00 2001 From: Michael Bommarito Date: Tue, 16 Jun 2026 22:19:02 -0400 Subject: [PATCH 0834/1198] media: verisilicon: hantro: bound G2 HEVC tile loop to the buffer capacity prepare_tile_info_buffer() writes one entry per tile into the tile_sizes DMA buffer, sized for a grid equal to the PPS uAPI array capacity. Use the bounded v4l2_hevc_pps_num_tile_columns() / v4l2_hevc_pps_num_tile_rows() helpers so the loops stay inside the buffer. Fixes: cb5dd5a0fa51 ("media: hantro: Introduce G2/HEVC decoder") Assisted-by: Claude:claude-opus-4-8 Cc: stable@vger.kernel.org Signed-off-by: Michael Bommarito Reviewed-by: Benjamin Gaignard Signed-off-by: Hans Verkuil --- drivers/media/platform/verisilicon/hantro_g2_hevc_dec.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/media/platform/verisilicon/hantro_g2_hevc_dec.c b/drivers/media/platform/verisilicon/hantro_g2_hevc_dec.c index e8c2e83379de..e7a7c7a42467 100644 --- a/drivers/media/platform/verisilicon/hantro_g2_hevc_dec.c +++ b/drivers/media/platform/verisilicon/hantro_g2_hevc_dec.c @@ -5,6 +5,8 @@ * Copyright (C) 2020 Safran Passenger Innovations LLC */ +#include + #include "hantro_hw.h" #include "hantro_g2_regs.h" @@ -15,8 +17,8 @@ static void prepare_tile_info_buffer(struct hantro_ctx *ctx) const struct v4l2_ctrl_hevc_pps *pps = ctrls->pps; const struct v4l2_ctrl_hevc_sps *sps = ctrls->sps; u16 *p = (u16 *)((u8 *)ctx->hevc_dec.tile_sizes.cpu); - unsigned int num_tile_rows = pps->num_tile_rows_minus1 + 1; - unsigned int num_tile_cols = pps->num_tile_columns_minus1 + 1; + unsigned int num_tile_rows = v4l2_hevc_pps_num_tile_rows(pps); + unsigned int num_tile_cols = v4l2_hevc_pps_num_tile_columns(pps); unsigned int pic_width_in_ctbs, pic_height_in_ctbs; unsigned int max_log2_ctb_size, ctb_size; bool tiles_enabled, uniform_spacing; From b84f6533a8ed2fd7b282fc7ab4b8efadc745a89c Mon Sep 17 00:00:00 2001 From: Michael Bommarito Date: Tue, 16 Jun 2026 22:19:03 -0400 Subject: [PATCH 0835/1198] media: verisilicon: rockchip: guard VPU981 AV1 divisor and tile buffer rockchip_vpu981_av1_dec_set_tile_info() divides context_update_tile_id by tile_info->tile_cols and writes one descriptor per tile into the tile_info DMA buffer, which holds AV1_MAX_TILES entries; tile_cols and tile_rows come from the bitstream. Guard the division against a zero tile_cols by initialising the context-update values to zero and computing them only when tile_cols is non-zero, and stop the descriptor writes once the tile_info buffer is full. The tile geometry written to the hardware registers is left unmodified; the per-dimension and total tile bounds are enforced by the control validation. Fixes: 727a400686a2 ("media: verisilicon: Add Rockchip AV1 decoder") Assisted-by: Claude:claude-opus-4-8 Cc: stable@vger.kernel.org Signed-off-by: Michael Bommarito Reviewed-by: Benjamin Gaignard Signed-off-by: Hans Verkuil --- .../verisilicon/rockchip_vpu981_hw_av1_dec.c | 32 +++++++++++++++---- 1 file changed, 26 insertions(+), 6 deletions(-) diff --git a/drivers/media/platform/verisilicon/rockchip_vpu981_hw_av1_dec.c b/drivers/media/platform/verisilicon/rockchip_vpu981_hw_av1_dec.c index e4e21ad37323..fd00dbd79fe4 100644 --- a/drivers/media/platform/verisilicon/rockchip_vpu981_hw_av1_dec.c +++ b/drivers/media/platform/verisilicon/rockchip_vpu981_hw_av1_dec.c @@ -578,16 +578,30 @@ static void rockchip_vpu981_av1_dec_set_tile_info(struct hantro_ctx *ctx) const struct v4l2_av1_tile_info *tile_info = &ctrls->frame->tile_info; const struct v4l2_ctrl_av1_tile_group_entry *group_entry = ctrls->tile_group_entry; - int context_update_y = - tile_info->context_update_tile_id / tile_info->tile_cols; - int context_update_x = - tile_info->context_update_tile_id % tile_info->tile_cols; - int context_update_tile_id = - context_update_x * tile_info->tile_rows + context_update_y; + int context_update_y = 0; + int context_update_x = 0; + int context_update_tile_id = 0; u8 *dst = av1_dec->tile_info.cpu; + u8 *dst_end = dst + av1_dec->tile_info.size; struct hantro_dev *vpu = ctx->dev; int tile0, tile1; + /* + * tile_cols and tile_rows are bounded by the V4L2 control validation + * (V4L2_AV1_MAX_TILE_{COLS,ROWS} and V4L2_AV1_MAX_TILE_COUNT). Guard + * the divisor here, and keep the descriptor writes within the + * AV1_MAX_TILES tile_info buffer below; the register values use the + * unmodified tile geometry. + */ + if (tile_info->tile_cols) { + context_update_y = + tile_info->context_update_tile_id / tile_info->tile_cols; + context_update_x = + tile_info->context_update_tile_id % tile_info->tile_cols; + context_update_tile_id = + context_update_x * tile_info->tile_rows + context_update_y; + } + memset(dst, 0, av1_dec->tile_info.size); for (tile0 = 0; tile0 < tile_info->tile_cols; tile0++) { @@ -598,6 +612,10 @@ static void rockchip_vpu981_av1_dec_set_tile_info(struct hantro_ctx *ctx) tile_info->height_in_sbs_minus_1[tile1] + 1; u32 x0 = tile_info->width_in_sbs_minus_1[tile0] + 1; + /* Stop once the tile_info descriptor buffer is full. */ + if (dst + 16 > dst_end) + break; + /* tile size in SB units (width,height) */ *dst++ = x0; *dst++ = 0; @@ -622,6 +640,8 @@ static void rockchip_vpu981_av1_dec_set_tile_info(struct hantro_ctx *ctx) *dst++ = (end >> 16) & 255; *dst++ = (end >> 24) & 255; } + if (dst + 16 > dst_end) + break; } hantro_reg_write(vpu, &av1_multicore_expect_context_update, !!(context_update_x == 0)); From 367db8b23c26a913d76ed70457bbcd781c422b49 Mon Sep 17 00:00:00 2001 From: Michael Bommarito Date: Tue, 16 Jun 2026 22:19:04 -0400 Subject: [PATCH 0836/1198] media: verisilicon: rockchip: reject AV1 frames exceeding the tile capacity rockchip_vpu981_av1_dec_set_tile_info() indexes the tile group entry array by tile1 * tile_cols + tile0, reading up to tile_cols * tile_rows entries, lays out one descriptor per tile in the AV1_MAX_TILES tile_info buffer, and programs the real tile_cols / tile_rows into the hardware. The tile group entry control is a dynamic array sized to the number of entries userspace submitted, independent of tile_cols / tile_rows, so a frame that claims more tiles than entries reads past the array. A frame that claims more than AV1_MAX_TILES tiles also leaves the hardware programmed for more tiles than the descriptor buffer holds. Reject both in prepare_run(): tile_cols * tile_rows must not exceed the submitted entry count or AV1_MAX_TILES. The entry count is read via v4l2_ctrl_find() (ctrl->elems). This mirrors the bound the mediatek AV1 decoder already enforces. Fixes: 727a400686a2 ("media: verisilicon: Add Rockchip AV1 decoder") Assisted-by: Claude:claude-opus-4-8 Cc: stable@vger.kernel.org Signed-off-by: Michael Bommarito Reviewed-by: Benjamin Gaignard Signed-off-by: Hans Verkuil --- .../verisilicon/rockchip_vpu981_hw_av1_dec.c | 25 ++++++++++++++++--- 1 file changed, 22 insertions(+), 3 deletions(-) diff --git a/drivers/media/platform/verisilicon/rockchip_vpu981_hw_av1_dec.c b/drivers/media/platform/verisilicon/rockchip_vpu981_hw_av1_dec.c index fd00dbd79fe4..00aa566a4ccd 100644 --- a/drivers/media/platform/verisilicon/rockchip_vpu981_hw_av1_dec.c +++ b/drivers/media/platform/verisilicon/rockchip_vpu981_hw_av1_dec.c @@ -431,20 +431,39 @@ static int rockchip_vpu981_av1_dec_prepare_run(struct hantro_ctx *ctx) { struct hantro_av1_dec_hw_ctx *av1_dec = &ctx->av1_dec; struct hantro_av1_dec_ctrls *ctrls = &av1_dec->ctrls; + const struct v4l2_av1_tile_info *tile_info; + struct v4l2_ctrl *tge; + u32 num_tiles; ctrls->sequence = hantro_get_ctrl(ctx, V4L2_CID_STATELESS_AV1_SEQUENCE); if (WARN_ON(!ctrls->sequence)) return -EINVAL; - ctrls->tile_group_entry = - hantro_get_ctrl(ctx, V4L2_CID_STATELESS_AV1_TILE_GROUP_ENTRY); - if (WARN_ON(!ctrls->tile_group_entry)) + tge = v4l2_ctrl_find(&ctx->ctrl_handler, + V4L2_CID_STATELESS_AV1_TILE_GROUP_ENTRY); + if (WARN_ON(!tge)) return -EINVAL; + ctrls->tile_group_entry = tge->p_cur.p; ctrls->frame = hantro_get_ctrl(ctx, V4L2_CID_STATELESS_AV1_FRAME); if (WARN_ON(!ctrls->frame)) return -EINVAL; + /* + * rockchip_vpu981_av1_dec_set_tile_info() indexes the tile group + * entry array by tile1 * tile_cols + tile0, so it reads up to + * tile_cols * tile_rows entries, and lays out one descriptor per tile + * in the AV1_MAX_TILES tile_info buffer while programming the real + * tile geometry into the hardware. Reject a frame that claims more + * tiles than userspace submitted, or more than the hardware tile + * buffer holds, so the read stays in bounds and the programmed + * geometry matches the descriptors written. + */ + tile_info = &ctrls->frame->tile_info; + num_tiles = (u32)tile_info->tile_cols * tile_info->tile_rows; + if (num_tiles > tge->elems || num_tiles > AV1_MAX_TILES) + return -EINVAL; + ctrls->film_grain = hantro_get_ctrl(ctx, V4L2_CID_STATELESS_AV1_FILM_GRAIN); From 37bef2170d4c88fc3d708eecf3ef0f4032bc1372 Mon Sep 17 00:00:00 2001 From: Michael Bommarito Date: Tue, 16 Jun 2026 22:19:05 -0400 Subject: [PATCH 0837/1198] media: mediatek: vcodec: bound AV1 tile-start copy to the array capacity vdec_av1_slice_setup_tile() copies tile_cols + 1 / tile_rows + 1 entries into mi_col_starts[] / mi_row_starts[] from the bitstream tile_info. Bound the copy to the array capacity. Fixes: 0934d3759615 ("media: mediatek: vcodec: separate decoder and encoder") Assisted-by: Claude:claude-opus-4-8 Cc: stable@vger.kernel.org Signed-off-by: Michael Bommarito Signed-off-by: Hans Verkuil --- .../mediatek/vcodec/decoder/vdec/vdec_av1_req_lat_if.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_av1_req_lat_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_av1_req_lat_if.c index 2d622e85f827..49d9b4a72387 100644 --- a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_av1_req_lat_if.c +++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_av1_req_lat_if.c @@ -1299,11 +1299,12 @@ static void vdec_av1_slice_setup_tile(struct vdec_av1_slice_frame *frame, tile->uniform_tile_spacing_flag = BIT_FLAG(ctrl_tile, V4L2_AV1_TILE_INFO_FLAG_UNIFORM_TILE_SPACING); - for (i = 0; i < tile->tile_cols + 1; i++) + /* Bound the copy to the mi_col_starts[]/mi_row_starts[] capacity. */ + for (i = 0; i < tile->tile_cols + 1 && i < V4L2_AV1_MAX_TILE_COLS + 1; i++) tile->mi_col_starts[i] = ALIGN(ctrl_tile->mi_col_starts[i], BIT(mib_size_log2)) >> mib_size_log2; - for (i = 0; i < tile->tile_rows + 1; i++) + for (i = 0; i < tile->tile_rows + 1 && i < V4L2_AV1_MAX_TILE_ROWS + 1; i++) tile->mi_row_starts[i] = ALIGN(ctrl_tile->mi_row_starts[i], BIT(mib_size_log2)) >> mib_size_log2; } From 113a9796effe3376d2ec5aabcca1fef4fef4cd62 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 12 Aug 2024 16:19:48 +0200 Subject: [PATCH 0838/1198] tick/broadcast: Plug clockevents replacement race MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 朱恺乾 reported and decoded the following race condition when a broadcast device is replaced: CPUA CPUB __tick_broadcast_oneshot_control() bc = tick_broadcast_device.evtdev; tick_install_broadcast_device(dev) clockevents_exchange_device(cur, dev) shutdown(cur); detach(cur); cur->handler = noop; tick_broadcast_device.evtdev = dev; tick_broadcast_set_event(bc, next_event); <- FAIL: arms a detached device. If the original broadcast device has a restricted interrupt affinity mask and the last CPU in that mask goes offline then the BUG() in tick_cleanup_dead_cpu() triggers because the clockevent device is not in detached state. The reason for this is that tick_install_broadcast_device() is not serialized vs. tick broadcast operations. The obvious cure is to serialize tick_install_broadcast_device() with tick_broadcast_lock against a concurrent tick broadcast operation. That requires to split clockevents_exchange_device() into two parts, one which does the exchange, shutdown and detach operation and the other which drops the module reference count. This is required because the module reference cannot be dropped while holding tick_broadcast_lock. Let clockevents_exchange_device() do both operations as before, but let the broadcast device code take the two step approach and do the device exchange under tick_broadcast_lock and drop the module reference count after releasing it. Fixes: f8381cba04ba ("[PATCH] tick-management: broadcast functionality") Reported-by: 朱恺乾 Signed-off-by: Thomas Gleixner Signed-off-by: Thomas Gleixner Reviewed-by: Bradley Morgan Tested-by: 刘术高 Cc: stable@vger.kernel.org Link: https://patch.msgid.link/87cymdsu0r.ffs@tglx --- kernel/time/clockevents.c | 35 +++++++++++++++++++++-------------- kernel/time/tick-broadcast.c | 36 ++++++++++++++++++++++-------------- kernel/time/tick-internal.h | 2 ++ 3 files changed, 45 insertions(+), 28 deletions(-) diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 0014d163f989..62ad7c000386 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -615,6 +615,24 @@ void clockevents_handle_noop(struct clock_event_device *dev) { } +void __clockevents_exchange_device(struct clock_event_device *old, + struct clock_event_device *new) +{ + /* + * Caller releases a clock event device. We queue it into the + * released list and do a notify add later. + */ + if (old) { + clockevents_switch_state(old, CLOCK_EVT_STATE_DETACHED); + list_move(&old->list, &clockevents_released); + } + + if (new) { + WARN_ON(!clockevent_state_detached(new)); + clockevents_shutdown(new); + } +} + /** * clockevents_exchange_device - release and request clock devices * @old: device to release (can be NULL) @@ -626,20 +644,9 @@ void clockevents_handle_noop(struct clock_event_device *dev) void clockevents_exchange_device(struct clock_event_device *old, struct clock_event_device *new) { - /* - * Caller releases a clock event device. We queue it into the - * released list and do a notify add later. - */ - if (old) { + __clockevents_exchange_device(old, new); + if (old) module_put(old->owner); - clockevents_switch_state(old, CLOCK_EVT_STATE_DETACHED); - list_move(&old->list, &clockevents_released); - } - - if (new) { - BUG_ON(!clockevent_state_detached(new)); - clockevents_shutdown(new); - } } /** @@ -699,7 +706,7 @@ void tick_offline_cpu(unsigned int cpu) if (cpumask_test_cpu(cpu, dev->cpumask) && cpumask_weight(dev->cpumask) == 1 && !tick_is_broadcast_device(dev)) { - BUG_ON(!clockevent_state_detached(dev)); + WARN_ON(!clockevent_state_detached(dev)); list_del(&dev->list); } } diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 115e0bf01276..bda3d2391a60 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -165,23 +165,31 @@ static bool tick_set_oneshot_wakeup_device(struct clock_event_device *newdev, */ void tick_install_broadcast_device(struct clock_event_device *dev, int cpu) { - struct clock_event_device *cur = tick_broadcast_device.evtdev; + struct clock_event_device *cur; - if (tick_set_oneshot_wakeup_device(dev, cpu)) - return; + scoped_guard(raw_spinlock_irqsave, &tick_broadcast_lock) { - if (!tick_check_broadcast_device(cur, dev)) - return; + if (tick_set_oneshot_wakeup_device(dev, cpu)) + return; - if (!try_module_get(dev->owner)) - return; + cur = tick_broadcast_device.evtdev; + if (!tick_check_broadcast_device(cur, dev)) + return; - clockevents_exchange_device(cur, dev); + if (!try_module_get(dev->owner)) + return; + + __clockevents_exchange_device(cur, dev); + if (cur) + cur->event_handler = clockevents_handle_noop; + WRITE_ONCE(tick_broadcast_device.evtdev, dev); + if (!cpumask_empty(tick_broadcast_mask)) + tick_broadcast_start_periodic(dev); + } + + /* Module release must be outside of the lock */ if (cur) - cur->event_handler = clockevents_handle_noop; - tick_broadcast_device.evtdev = dev; - if (!cpumask_empty(tick_broadcast_mask)) - tick_broadcast_start_periodic(dev); + module_put(cur->owner); if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT)) return; @@ -1218,7 +1226,7 @@ int tick_broadcast_oneshot_active(void) */ bool tick_broadcast_oneshot_available(void) { - struct clock_event_device *bc = tick_broadcast_device.evtdev; + struct clock_event_device *bc = READ_ONCE(tick_broadcast_device.evtdev); return bc ? bc->features & CLOCK_EVT_FEAT_ONESHOT : false; } @@ -1226,7 +1234,7 @@ bool tick_broadcast_oneshot_available(void) #else int __tick_broadcast_oneshot_control(enum tick_broadcast_state state) { - struct clock_event_device *bc = tick_broadcast_device.evtdev; + struct clock_event_device *bc = READ_ONCE(tick_broadcast_device.evtdev); if (!bc || (bc->features & CLOCK_EVT_FEAT_HRTIMER)) return -EBUSY; diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 182974c4f21b..65680db95053 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -55,6 +55,8 @@ static inline void clockevent_set_state(struct clock_event_device *dev, } extern void clockevents_shutdown(struct clock_event_device *dev); +extern void __clockevents_exchange_device(struct clock_event_device *old, + struct clock_event_device *new); extern void clockevents_exchange_device(struct clock_event_device *old, struct clock_event_device *new); extern void clockevents_switch_state(struct clock_event_device *dev, From 954f7a48fa2ae7310c67729fb556caf726783436 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 5 Sep 2026 10:43:57 +0200 Subject: [PATCH 0839/1198] entry: Guard syscall_enter_audit() invocation with CONFIG_AUDITSYSCALL A bunch of older cross compilers notably RISCV64 and S390 fail to eliminate the dead code when CONFIG_AUDITSYSCALL=n. The code in question is: if (unlikely(audit_context()) syscall_enter_audit(regs); and in case of CONFIG_AUDITSYSCALL=n: static inline struct audit_context *audit_context(void) { return NULL; } which should make the compiler eliminate the syscall_enter_audit() call. But a RISV64 GCC12 cross compiler translates that into: if (unlikely(audit_context())) 1c34: 00000097 auipc ra,0x0 1c38: 000080e7 jalr ra # 1c34 <.L785> 1c3c: c511 beqz a0,1c48 <.L787> syscall_enter_audit(regs); 1c3e: 8526 mv a0,s1 1c40: 00000097 auipc ra,0x0 1c44: 000080e7 jalr ra # 1c40 <.L785+0xc> and then claims in the failing link: include/asm-generic/preempt.h:54:(.noinstr.text+0x1a20): undefined reference to 'syscall_enter_audit' which is obviously hallucination. Add an explicit IS_ENABLED(CONFIG_AUDITSYSCALL) check into the condition to cure this compiler madness. Fixes: 6f25517010dd ("entry: Rework syscall_audit_enter()") Reported-by: kernel test robot Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://patch.msgid.link/87tso45bqq.ffs@fw13 Closes: https://lore.kernel.org/oe-kbuild-all/202609031938.ZvZZaRQy-lkp@intel.com/ --- include/linux/entry-common.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index 6574b7183c01..fa2854fed1f2 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -102,7 +102,14 @@ static __always_inline long syscall_trace_enter(struct pt_regs *regs, unsigned l if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT)) trace_syscall_enter(regs); - if (unlikely(audit_context())) + /* + * The config check works around broken compilers which fail to + * eliminate the dead code in case of CONFIG_AUDITSYSCALL=n as they + * insist on creating a always false runtime condition based on + * audit_context() which returns NULL in that case. The explicit + * IS_ENABLED() check makes that madness go away. + */ + if (IS_ENABLED(CONFIG_AUDITSYSCALL) && unlikely(audit_context())) syscall_enter_audit(regs); return true; From 2c6dc792538260a8087ac5b22c31b3b8e47c85d6 Mon Sep 17 00:00:00 2001 From: Norbert Szetei Date: Sat, 22 Aug 2026 14:29:00 +0200 Subject: [PATCH 0840/1198] landlock: Fix use-after-free of the source's parent directory MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit current_check_refer_path() reads old_dentry->d_parent without holding a reference nor a lock on it, and then dereferences it in collect_domain_accesses() and in the audit record. A reference on a child does not pin its parent: __d_move() reassigns dentry->d_parent and drops the reference the child held on its former parent. hook_path_rename() is not affected because the rename path calls lock_rename() before the hook, so the source cannot be reparented under it. hook_path_link() has no such protection: filename_linkat() holds a reference on the source dentry but neither locks nor references its parent, so a concurrent rename(2) can reparent the source while security_path_link() runs, and the former parent can then be removed and freed while the hook walks it. A process can trigger this after entering a Landlock domain that handles at least one filesystem access right. The process can then race a linkat(2) loop against rename(2) and rmdir(2): BUG: KASAN: slab-use-after-free in collect_domain_accesses+0x278/0x290 Read of size 4 at addr ffff888160bd53f4 by task llrepro2/549 collect_domain_accesses+0x278/0x290 current_check_refer_path+0x952/0x1120 security_path_link+0x1be/0x320 filename_linkat+0x342/0x6d0 __x64_sys_linkat+0xfa/0x150 Freed by task 562: kmem_cache_free+0x139/0x4c0 i_callback+0x4b/0x80 rcu_core+0x7dc/0x10a0 Take a reference on the dentry selected as the source parent, using dget() for the common-mount-root case and dget_parent() otherwise. Release it after the hierarchy walk and synchronous audit logging. Cc: stable@vger.kernel.org Fixes: b91c3e4ea756 ("landlock: Add support for file reparenting with LANDLOCK_ACCESS_FS_REFER") Signed-off-by: Norbert Szetei Reviewed-by: Günther Noack Tested-by: Günther Noack Link: https://patch.msgid.link/E9CDD9E6-E960-4DE2-B1AC-5667D52ABB3E@doyensec.com [mic: Clarify the caller, reachability, and reference handling] Signed-off-by: Mickaël Salaün --- security/landlock/fs.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/security/landlock/fs.c b/security/landlock/fs.c index 30aa6ce13590..330a1871bf94 100644 --- a/security/landlock/fs.c +++ b/security/landlock/fs.c @@ -1298,11 +1298,12 @@ static int current_check_refer_path(struct dentry *const old_dentry, /* * old_dentry may be the root of the common mount point and * !IS_ROOT(old_dentry) at the same time (e.g. with open_tree() and - * OPEN_TREE_CLONE). We do not need to call dget(old_parent) because - * we keep a reference to old_dentry. + * OPEN_TREE_CLONE). Pin the dentry used as old_parent in either case. + * Otherwise, dget_parent() safely fetches and pins the current parent + * against a concurrent rename(2). */ - old_parent = (old_dentry == mnt_dir.dentry) ? old_dentry : - old_dentry->d_parent; + old_parent = (old_dentry == mnt_dir.dentry) ? dget(old_dentry) : + dget_parent(old_dentry); /* new_dir->dentry is equal to new_dentry->d_parent */ allow_parent1 = collect_domain_accesses(subject->domain, mnt_dir.dentry, @@ -1311,8 +1312,10 @@ static int current_check_refer_path(struct dentry *const old_dentry, allow_parent2 = collect_domain_accesses(subject->domain, mnt_dir.dentry, new_dir->dentry, &layer_masks_parent2); - if (allow_parent1 && allow_parent2) + if (allow_parent1 && allow_parent2) { + dput(old_parent); return 0; + } /* * To be able to compare source and destination domain access rights, @@ -1324,8 +1327,10 @@ static int current_check_refer_path(struct dentry *const old_dentry, subject->domain, &mnt_dir, access_request_parent1, &layer_masks_parent1, &request1, old_dentry, access_request_parent2, &layer_masks_parent2, &request2, - exchange ? new_dentry : NULL)) + exchange ? new_dentry : NULL)) { + dput(old_parent); return 0; + } if (request1.access) { request1.audit.u.path.dentry = old_parent; @@ -1335,6 +1340,7 @@ static int current_check_refer_path(struct dentry *const old_dentry, request2.audit.u.path.dentry = new_dir->dentry; landlock_log_denial(subject, &request2); } + dput(old_parent); /* * This prioritizes EACCES over EXDEV for all actions, including From 96bf9831fbf423b8104f7948cd8fe7007ecfb46c Mon Sep 17 00:00:00 2001 From: Chengyu Zhu Date: Mon, 7 Sep 2026 16:33:19 +0800 Subject: [PATCH 0841/1198] erofs: delimit inode_share cache key components Previously, inode_share keys were encoded as follows: fingerprint || domain_id It would be better to have a separator between the fingerprint and domain ID so that the fingerprint won't be parsed as part of a domain ID. Change the key encoding as follows: domain_id || '\0' || fingerprint Since domain_id is a NUL-terminated string, this makes the in-memory key indices unambiguous. Signed-off-by: Chengyu Zhu Reviewed-by: Gao Xiang Fixes: e0bf7d1c074d ("erofs: support user-defined fingerprint name") Signed-off-by: Gao Xiang --- fs/erofs/xattr.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c index df7ea019526d..57cfb7520782 100644 --- a/fs/erofs/xattr.c +++ b/fs/erofs/xattr.c @@ -620,8 +620,8 @@ int erofs_xattr_fill_inode_fingerprint(struct erofs_inode_fingerprint *fp, { struct erofs_sb_info *sbi = EROFS_SB(inode->i_sb); struct erofs_xattr_prefix_item *prefix; + int domainlen, valuelen, base_index; const char *infix; - int valuelen, base_index; if (!test_opt(&sbi->opt, INODE_SHARE)) return -EOPNOTSUPP; @@ -633,17 +633,18 @@ int erofs_xattr_fill_inode_fingerprint(struct erofs_inode_fingerprint *fp, valuelen = erofs_getxattr(inode, base_index, infix, NULL, 0); if (valuelen <= 0 || valuelen > (1 << sbi->blkszbits)) return -EFSCORRUPTED; - fp->size = valuelen + (domain_id ? strlen(domain_id) : 0); + domainlen = strlen(domain_id); + fp->size = domainlen + 1 + valuelen; fp->opaque = kmalloc(fp->size, GFP_KERNEL); if (!fp->opaque) return -ENOMEM; + memcpy(fp->opaque, domain_id, domainlen + 1); if (valuelen != erofs_getxattr(inode, base_index, infix, - fp->opaque, valuelen)) { + fp->opaque + domainlen + 1, valuelen)) { kfree(fp->opaque); fp->opaque = NULL; return -EFSCORRUPTED; } - memcpy(fp->opaque + valuelen, domain_id, fp->size - valuelen); return 0; } #endif From e7557b9ef7a87570cbd0873a163de05bde80c39b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micka=C3=ABl=20Sala=C3=BCn?= Date: Mon, 7 Sep 2026 12:35:01 +0200 Subject: [PATCH 0842/1198] selftests/landlock: Test abstract socket trace name limits MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The landlock_deny_scope_abstract_unix_socket event captures binary socket names with __string_len(), whose dynamic field reserves an extra byte for the NUL terminator. The printer subtracts this byte before escaping the content. Exercise the minimum accepted address length, which has no name content, and the maximum sockaddr_un length, which has 107 content bytes. Check the exact trace output at both boundaries. The existing stream and datagram variants share this event, so the boundary variants only need the stream path. Because these boundary names are fixed, run the fixture in a private network namespace. Abstract UNIX socket names are scoped by network namespace, preventing concurrent bind() calls from colliding. The lower-bound test confirms that the subtraction recovers zero instead of underflowing. Cc: Günther Noack Link: https://patch.msgid.link/CAL4aGcVcT0VWVFmGi_vLqxxZ9KdOHfGXYZtKjBdvoUyFjbu5=A@mail.gmail.com Link: https://patch.msgid.link/20260907103503.109461-1-mic@digikod.net Signed-off-by: Mickaël Salaün --- .../landlock/scoped_abstract_unix_test.c | 76 +++++++++++++------ 1 file changed, 54 insertions(+), 22 deletions(-) diff --git a/tools/testing/selftests/landlock/scoped_abstract_unix_test.c b/tools/testing/selftests/landlock/scoped_abstract_unix_test.c index 6dbe863ea571..5dc0debacb2a 100644 --- a/tools/testing/selftests/landlock/scoped_abstract_unix_test.c +++ b/tools/testing/selftests/landlock/scoped_abstract_unix_test.c @@ -1222,7 +1222,7 @@ FIXTURE_SETUP(trace_unix) int ret; set_cap(_metadata, CAP_SYS_ADMIN); - ASSERT_EQ(0, unshare(CLONE_NEWNS)); + ASSERT_EQ(0, unshare(CLONE_NEWNS | CLONE_NEWNET)); ASSERT_EQ(0, mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, NULL)); ret = tracefs_fixture_setup(); @@ -1252,6 +1252,11 @@ FIXTURE_TEARDOWN(trace_unix) clear_cap(_metadata, CAP_SYS_ADMIN); } +static const char + trace_unix_max_name[sizeof(((struct sockaddr_un *)0)->sun_path)] = { + [0 ... sizeof(trace_unix_max_name) - 2] = 'x', + }; + /* clang-format off */ FIXTURE_VARIANT(trace_unix) { /* clang-format on */ @@ -1259,6 +1264,8 @@ FIXTURE_VARIANT(trace_unix) { bool sandbox; bool sandbox_target; /* Peer owned by a domain: peer_domain != 0. */ int expect_denied; + const char *name; /* NULL generates a PID-based binary name. */ + size_t name_len; }; /* clang-format off */ @@ -1281,6 +1288,26 @@ FIXTURE_VARIANT_ADD(trace_unix, stream_allowed) { .sandbox_target = false, .expect_denied = 0, }; +/* Stream: lower abstract-name length boundary. */ +FIXTURE_VARIANT_ADD(trace_unix, stream_denied_empty_name) { + .sock_type = SOCK_STREAM, + .sandbox = true, + .sandbox_target = false, + .expect_denied = 1, + .name = "", + .name_len = 0, +}; + +/* Stream: upper abstract-name length boundary. */ +FIXTURE_VARIANT_ADD(trace_unix, stream_denied_max_name) { + .sock_type = SOCK_STREAM, + .sandbox = true, + .sandbox_target = false, + .expect_denied = 1, + .name = trace_unix_max_name, + .name_len = sizeof(trace_unix_max_name) - 1, +}; + /* Datagram: sandboxed client sendto() an unsandboxed peer (peer_domain=0). */ FIXTURE_VARIANT_ADD(trace_unix, dgram_denied) { .sock_type = SOCK_DGRAM, .sandbox = true, @@ -1304,12 +1331,11 @@ FIXTURE_VARIANT_ADD(trace_unix, dgram_allowed) { /* * A sandboxed thread reaching an abstract unix socket peer through connect(2) * (stream) or sendto(2) (datagram) is denied and emits - * landlock_deny_scope_abstract_unix_socket. The abstract name is crafted with - * a space and an embedded NUL followed by an "END" marker to check the - * tracepoint escaping and its length handling (a raw space would break the - * sun_path field regex; strlen() would truncate at the NUL and drop "END"). - * peer_pid is only meaningful for a stream peer (a datagram peer has no - * SO_PEERCRED), so it is asserted only there. + * landlock_deny_scope_abstract_unix_socket. The default abstract name has a + * space and an embedded NUL followed by an "END" marker to check escaping and + * binary length handling. Additional stream variants cover the minimum and + * maximum abstract-name lengths. peer_pid is only meaningful for a stream peer + * (a datagram peer has no SO_PEERCRED), so it is asserted only there. */ TEST_F(trace_unix, deny_scope_unix) { @@ -1336,12 +1362,19 @@ TEST_F(trace_unix, deny_scope_unix) ASSERT_LE(0, server_fd); addr.sun_path[0] = '\0'; - name_len = snprintf(addr.sun_path + 1, sizeof(addr.sun_path) - 1, - "landlock_trace_test_%d ", getpid()); - addr.sun_path[1 + name_len] = '\0'; - memcpy(addr.sun_path + 1 + name_len + 1, "END", 3); - addr_len = - offsetof(struct sockaddr_un, sun_path) + 1 + name_len + 1 + 3; + if (variant->name) { + ASSERT_LE(variant->name_len, sizeof(addr.sun_path) - 1); + memcpy(addr.sun_path + 1, variant->name, variant->name_len); + name_len = variant->name_len; + } else { + name_len = snprintf(addr.sun_path + 1, + sizeof(addr.sun_path) - 1, + "landlock_trace_test_%d ", getpid()); + addr.sun_path[1 + name_len] = '\0'; + memcpy(addr.sun_path + 1 + name_len + 1, "END", 3); + name_len += 1 + 3; + } + addr_len = offsetof(struct sockaddr_un, sun_path) + 1 + name_len; ASSERT_EQ(0, bind(server_fd, (struct sockaddr *)&addr, addr_len)); if (variant->sock_type == SOCK_STREAM) @@ -1430,19 +1463,18 @@ TEST_F(trace_unix, deny_scope_unix) count, buf); } - /* - * sun_path is escaped: a raw space would break this field's [^ ]*$ - * regex, so a successful extract proves the space was escaped, and its - * full length is honored: the "END" marker after the embedded NUL must - * survive (strlen() would truncate it at the NUL). - */ ASSERT_EQ(0, tracefs_extract_field( buf, REGEX_DENY_SCOPE_ABSTRACT_UNIX_SOCKET(TRACE_TASK), "sun_path", field, sizeof(field))); - EXPECT_NE(NULL, strstr(field, "END")) - { - TH_LOG("sun_path truncated or unescaped: %s", field); + if (variant->name) { + EXPECT_STREQ(variant->name, field); + } else { + /* An embedded NUL must not truncate the following marker. */ + EXPECT_NE(NULL, strstr(field, "END")) + { + TH_LOG("sun_path truncated or unescaped: %s", field); + } } /* peer_pid is the parent's PID for a stream peer (0 for datagram). */ From 353a95f1cd8da8a5436a3f070be07d2f484486cd Mon Sep 17 00:00:00 2001 From: Karl Mehltretter Date: Sat, 22 Aug 2026 09:23:25 +0200 Subject: [PATCH 0843/1198] syscall_user_dispatch: Use CONFIG_SYSCTL for sysctl guard Commit 8d75c338f0bc ("sysctl: remove CONFIG_PROC_SYSCTL, it just mirrors CONFIG_SYSCTL") removed CONFIG_PROC_SYSCTL, but the sysctl added by commit 5b6e32ba7b59 ("syscall_user_dispatch: Add kernel.syscall_user_dispatch sysctl") is still guarded by it. Now that both commits are merged, kernel.syscall_user_dispatch is no longer registered. syscall_user_dispatch_allowed defaults to true. SUD therefore remains available, but administrators cannot disable new activations. Use CONFIG_SYSCTL for the guard and documentation. Fixes: 5b6e32ba7b59 ("syscall_user_dispatch: Add kernel.syscall_user_dispatch sysctl") Assisted-by: Codex:gpt-5.6-sol Acked-by: Oleg Nesterov Reviewed-by: Joel Granados Signed-off-by: Karl Mehltretter Acked-by: Randy Dunlap Reviewed-by: Bradley Morgan Signed-off-by: Joel Granados --- Documentation/admin-guide/sysctl/kernel.rst | 2 +- kernel/entry/syscall_user_dispatch.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst index b6328cd0f43e..ffea61d448eb 100644 --- a/Documentation/admin-guide/sysctl/kernel.rst +++ b/Documentation/admin-guide/sysctl/kernel.rst @@ -1416,7 +1416,7 @@ Controls whether userspace may arm Syscall User Dispatch via == =================================================================== Only present when the kernel is built with ``CONFIG_SYSCALL_USER_DISPATCH`` -and ``CONFIG_PROC_SYSCTL``. +and ``CONFIG_SYSCTL``. sysctl_writes_strict diff --git a/kernel/entry/syscall_user_dispatch.c b/kernel/entry/syscall_user_dispatch.c index 2002c7aae435..59c861866941 100644 --- a/kernel/entry/syscall_user_dispatch.c +++ b/kernel/entry/syscall_user_dispatch.c @@ -178,7 +178,7 @@ int syscall_user_dispatch_set_config(struct task_struct *task, unsigned long siz (char __user *)(uintptr_t)cfg.selector); } -#ifdef CONFIG_PROC_SYSCTL +#ifdef CONFIG_SYSCTL static const struct ctl_table syscall_user_dispatch_sysctls[] = { { .procname = "syscall_user_dispatch", @@ -195,4 +195,4 @@ static int __init syscall_user_dispatch_sysctl_init(void) return 0; } late_initcall(syscall_user_dispatch_sysctl_init); -#endif /* CONFIG_PROC_SYSCTL */ +#endif /* CONFIG_SYSCTL */ From d5bcf9ccaa357396089bbfa47fc82b093f109b1e Mon Sep 17 00:00:00 2001 From: Fangyu Yu Date: Tue, 1 Sep 2026 21:39:18 +0800 Subject: [PATCH 0844/1198] iommu/riscv: Add command queue lock Add a raw spinlock to the RISC-V IOMMU queue state so command queue publishing can be serialized by a later change. Fixes: 856c0cfe5c5f ("iommu/riscv: Command and fault queue support") Signed-off-by: Fangyu Yu Reviewed-by: Nutty Liu Signed-off-by: Joerg Roedel --- drivers/iommu/riscv/iommu.c | 1 + drivers/iommu/riscv/iommu.h | 2 ++ 2 files changed, 3 insertions(+) diff --git a/drivers/iommu/riscv/iommu.c b/drivers/iommu/riscv/iommu.c index cec3ddd7ab10..2c0dcc90cf85 100644 --- a/drivers/iommu/riscv/iommu.c +++ b/drivers/iommu/riscv/iommu.c @@ -1560,6 +1560,7 @@ int riscv_iommu_init(struct riscv_iommu_device *iommu) int rc; RISCV_IOMMU_QUEUE_INIT(&iommu->cmdq, CQ); + raw_spin_lock_init(&iommu->cmdq.lock); RISCV_IOMMU_QUEUE_INIT(&iommu->fltq, FQ); rc = riscv_iommu_init_check(iommu); diff --git a/drivers/iommu/riscv/iommu.h b/drivers/iommu/riscv/iommu.h index 46df79dd5495..5676001548cc 100644 --- a/drivers/iommu/riscv/iommu.h +++ b/drivers/iommu/riscv/iommu.h @@ -12,6 +12,7 @@ #define _RISCV_IOMMU_H_ #include +#include #include #include @@ -23,6 +24,7 @@ struct riscv_iommu_queue { atomic_t prod; /* unbounded producer allocation index */ atomic_t head; /* unbounded shadow ring buffer consumer index */ atomic_t tail; /* unbounded shadow ring buffer producer index */ + raw_spinlock_t lock; /* serialize queue publishing */ unsigned int mask; /* index mask, queue length - 1 */ unsigned int irq; /* allocated interrupt number */ struct riscv_iommu_device *iommu; /* iommu device handling the queue when active */ From ca58afa40946acd252a50fa4d4a86f15847a3d7d Mon Sep 17 00:00:00 2001 From: Fangyu Yu Date: Tue, 1 Sep 2026 21:39:19 +0800 Subject: [PATCH 0845/1198] iommu/riscv: Serialize command queue publishing Serialize command queue publishing so software producer state advances only after a command is written and the hardware tail is updated. Wait for hardware consumption outside the queue lock when the command queue is full so other CPUs are not blocked behind a long poll. Fixes: 856c0cfe5c5f ("iommu/riscv: Command and fault queue support") Signed-off-by: Fangyu Yu Signed-off-by: Joerg Roedel --- drivers/iommu/riscv/iommu.c | 102 +++++++++++++++++++++--------------- 1 file changed, 59 insertions(+), 43 deletions(-) diff --git a/drivers/iommu/riscv/iommu.c b/drivers/iommu/riscv/iommu.c index 2c0dcc90cf85..e335beb70e42 100644 --- a/drivers/iommu/riscv/iommu.c +++ b/drivers/iommu/riscv/iommu.c @@ -382,77 +382,93 @@ static int riscv_iommu_queue_wait(struct riscv_iommu_queue *queue, (int)(cons - index) > 0, 0, timeout_us); } -/* Enqueue an entry and wait to be processed if timeout_us > 0 - * - * Error handling for IOMMU hardware not responding in reasonable time - * will be added as separate patch series along with other RAS features. - * For now, only report hardware failure and continue. - */ +static int riscv_iommu_queue_wait_for_space(struct riscv_iommu_queue *queue, + unsigned int last) +{ + unsigned int head; + unsigned int tail; + unsigned int hw_head; + unsigned long flags; + int ret; + + ret = riscv_iommu_readl_timeout(queue->iommu, Q_HEAD(queue), hw_head, + !(hw_head & ~queue->mask) && hw_head != last, + 0, RISCV_IOMMU_QUEUE_TIMEOUT); + if (ret) + return ret; + + raw_spin_lock_irqsave(&queue->lock, flags); + head = atomic_read(&queue->head); + tail = atomic_read(&queue->tail); + if ((tail - head) >= queue->mask) { + last = Q_ITEM(queue, head); + /* + * Re-read hw_head under the lock so that it is consistent with + * the freshly computed 'last'. Using the pre-lock snapshot + * could produce a stale value that wraps around relative to the + * new 'last', advancing the shadow head past entries that have + * not yet been consumed by the hardware. + */ + hw_head = riscv_iommu_readl(queue->iommu, Q_HEAD(queue)); + if (!(hw_head & ~queue->mask) && hw_head != last) + atomic_add((hw_head - last) & queue->mask, &queue->head); + } + raw_spin_unlock_irqrestore(&queue->lock, flags); + + return 0; +} + +/* Enqueue an entry and publish it to the hardware queue. */ static unsigned int riscv_iommu_queue_send(struct riscv_iommu_queue *queue, void *entry, size_t entry_size) { unsigned int prod; unsigned int head; - unsigned int tail; unsigned long flags; + int ret; - /* Do not preempt submission flow. */ - local_irq_save(flags); + /* 1. Wait for space availability and reserve the next slot. */ + for (;;) { + raw_spin_lock_irqsave(&queue->lock, flags); - /* 1. Allocate some space in the queue */ - prod = atomic_inc_return(&queue->prod) - 1; - head = atomic_read(&queue->head); + prod = atomic_read(&queue->tail); + head = atomic_read(&queue->head); - /* 2. Wait for space availability. */ - if ((prod - head) > queue->mask) { - if (readx_poll_timeout(atomic_read, &queue->head, - head, (prod - head) < queue->mask, - 0, RISCV_IOMMU_QUEUE_TIMEOUT)) + if ((prod - head) < queue->mask) + break; + + head = Q_ITEM(queue, head); + raw_spin_unlock_irqrestore(&queue->lock, flags); + + ret = riscv_iommu_queue_wait_for_space(queue, head); + if (ret) goto err_busy; - } else if ((prod - head) == queue->mask) { - const unsigned int last = Q_ITEM(queue, head); - - if (riscv_iommu_readl_timeout(queue->iommu, Q_HEAD(queue), head, - !(head & ~queue->mask) && head != last, - 0, RISCV_IOMMU_QUEUE_TIMEOUT)) - goto err_busy; - atomic_add((head - last) & queue->mask, &queue->head); } - /* 3. Store entry in the ring buffer */ + /* 2. Store entry in the ring buffer. */ memcpy(queue->base + Q_ITEM(queue, prod) * entry_size, entry, entry_size); - /* 4. Wait for all previous entries to be ready */ - if (readx_poll_timeout(atomic_read, &queue->tail, tail, prod == tail, - 0, RISCV_IOMMU_QUEUE_TIMEOUT)) - goto err_busy; - - /* - * 5. Make sure the ring buffer update (whether in normal or I/O memory) is - * completed and visible before signaling the tail doorbell to fetch - * the next command. 'fence ow, ow' - */ + /* 3. Make sure the entry is visible before updating the queue tail. */ dma_wmb(); riscv_iommu_writel(queue->iommu, Q_TAIL(queue), Q_ITEM(queue, prod + 1)); /* - * 6. Make sure the doorbell write to the device has finished before updating - * the shadow tail index in normal memory. 'fence o, w' + * 4. Make sure the doorbell write to the device has finished before + * updating the shadow tail index in normal memory. 'fence o, w' */ #ifdef CONFIG_MMIOWB mmiowb(); #endif - atomic_inc(&queue->tail); + atomic_set(&queue->tail, prod + 1); + atomic_set(&queue->prod, prod + 1); - /* 7. Complete submission and restore local interrupts */ - local_irq_restore(flags); + raw_spin_unlock_irqrestore(&queue->lock, flags); return prod; err_busy: - local_irq_restore(flags); + /* Report the failure and continue; full RAS recovery is not implemented. */ dev_err_once(queue->iommu->dev, "Hardware error: command enqueue failed\n"); - return prod; } From 4c50bec3d54288230aafb7fe3d2930d42beb14fd Mon Sep 17 00:00:00 2001 From: Fangyu Yu Date: Tue, 1 Sep 2026 21:39:20 +0800 Subject: [PATCH 0846/1198] iommu/riscv: Avoid waiting on failed command enqueue Do not wait for IOFENCE.C completion when the command failed to enter the queue. The command was not published to hardware, so waiting for its producer index can only report a misleading execution timeout. Fixes: 856c0cfe5c5f ("iommu/riscv: Command and fault queue support") Signed-off-by: Fangyu Yu Signed-off-by: Joerg Roedel --- drivers/iommu/riscv/iommu.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/drivers/iommu/riscv/iommu.c b/drivers/iommu/riscv/iommu.c index e335beb70e42..fe8e6d0f8a23 100644 --- a/drivers/iommu/riscv/iommu.c +++ b/drivers/iommu/riscv/iommu.c @@ -419,8 +419,9 @@ static int riscv_iommu_queue_wait_for_space(struct riscv_iommu_queue *queue, } /* Enqueue an entry and publish it to the hardware queue. */ -static unsigned int riscv_iommu_queue_send(struct riscv_iommu_queue *queue, - void *entry, size_t entry_size) +static int riscv_iommu_queue_send(struct riscv_iommu_queue *queue, + void *entry, size_t entry_size, + unsigned int *out_prod) { unsigned int prod; unsigned int head; @@ -462,14 +463,16 @@ static unsigned int riscv_iommu_queue_send(struct riscv_iommu_queue *queue, atomic_set(&queue->tail, prod + 1); atomic_set(&queue->prod, prod + 1); - raw_spin_unlock_irqrestore(&queue->lock, flags); + if (out_prod) + *out_prod = prod; - return prod; + raw_spin_unlock_irqrestore(&queue->lock, flags); + return 0; err_busy: /* Report the failure and continue; full RAS recovery is not implemented. */ dev_err_once(queue->iommu->dev, "Hardware error: command enqueue failed\n"); - return prod; + return ret; } /* @@ -508,7 +511,7 @@ static irqreturn_t riscv_iommu_cmdq_process(int irq, void *data) static void riscv_iommu_cmd_send(struct riscv_iommu_device *iommu, struct riscv_iommu_command *cmd) { - riscv_iommu_queue_send(&iommu->cmdq, cmd, sizeof(*cmd)); + riscv_iommu_queue_send(&iommu->cmdq, cmd, sizeof(*cmd), NULL); } /* Send IOFENCE.C command and wait for all scheduled commands to complete. */ @@ -517,9 +520,12 @@ static void riscv_iommu_cmd_sync(struct riscv_iommu_device *iommu, { struct riscv_iommu_command cmd; unsigned int prod; + int ret; riscv_iommu_cmd_iofence(&cmd); - prod = riscv_iommu_queue_send(&iommu->cmdq, &cmd, sizeof(cmd)); + ret = riscv_iommu_queue_send(&iommu->cmdq, &cmd, sizeof(cmd), &prod); + if (ret) + return; if (!timeout_us) return; From 20db6573301e66cd65ebf6c130b6563c69374d9d Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Tue, 18 Aug 2026 21:13:17 +0200 Subject: [PATCH 0847/1198] iommu/s390: Fix NULL dereference in iova_to_phys() with ZPCI_TABLE_TYPE_RFX When using a 5-level translation table via ZPCI_TABLE_TYPE_RFX get_rso_from_iova() returns NULL when the region-first entry is invalid. Yet in get_rto_from_iova() the region-second origin rso is not checked to be non-NULL before accessing rso[rsx] leading to a NULL pointer dereference instead of a NULL return when iova_to_phys() is called on a unmapped IOVA. Fix this by adding the missing NULL check. Cc: stable@vger.kernel.org Fixes: 81244074b518 ("iommu/s390: allow larger region tables") Signed-off-by: Niklas Schnelle Reviewed-by: Benjamin Block Reviewed-by: Matthew Rosato Reviewed-by: Farhan Ali Signed-off-by: Joerg Roedel --- drivers/iommu/s390-iommu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c index f148f559ac56..58ca7727b7f2 100644 --- a/drivers/iommu/s390-iommu.c +++ b/drivers/iommu/s390-iommu.c @@ -974,6 +974,8 @@ static unsigned long *get_rto_from_iova(struct s390_domain *domain, case ZPCI_TABLE_TYPE_RFX: case ZPCI_TABLE_TYPE_RSX: rso = get_rso_from_iova(domain, iova); + if (!rso) + return NULL; rsx = calc_rsx(iova); rse = READ_ONCE(rso[rsx]); if (!reg_entry_isvalid(rse)) From 00a7dd64888d6dd72110b40e2824a088cf7b7386 Mon Sep 17 00:00:00 2001 From: Karl Mehltretter Date: Wed, 19 Aug 2026 05:23:49 +0200 Subject: [PATCH 0848/1198] iommu/amd: Do not reallocate GA log buffers on resume Commit c5e1a1eb9279 ("iommu/amd: Simplify and Consolidate Virtual APIC (AVIC) Enablement") moved the GA log allocation from iommu_init_pci() to enable_iommus_vapic(), which is called on every resume. iommu_init_ga_log() assigns iommu->ga_log and iommu->ga_log_tail unconditionally. Each resume therefore replaces the boot-time pointers and leaks both old allocations. The function also uses GFP_KERNEL from a syscore resume callback, where interrupts are disabled and the non-boot CPUs are offline. Return early if both buffers are already allocated. Clear the pointers in free_ga_log() so a partial allocation failure cannot leave ga_log dangling. Fixes: c5e1a1eb9279 ("iommu/amd: Simplify and Consolidate Virtual APIC (AVIC) Enablement") Assisted-by: Claude:claude-opus-5 Signed-off-by: Karl Mehltretter Reviewed-by: Vasant Hegde Reviewed-by: Ankit Soni Signed-off-by: Joerg Roedel --- drivers/iommu/amd/init.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 40726dfef273..c6b106d5921e 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -909,7 +909,9 @@ static void free_ga_log(struct amd_iommu *iommu) { #ifdef CONFIG_IRQ_REMAP iommu_free_pages(iommu->ga_log); + iommu->ga_log = NULL; iommu_free_pages(iommu->ga_log_tail); + iommu->ga_log_tail = NULL; #endif } @@ -956,6 +958,9 @@ static int iommu_init_ga_log(struct amd_iommu *iommu) if (WARN_ON_ONCE(!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir))) return -EINVAL; + if (iommu->ga_log && iommu->ga_log_tail) + return 0; + iommu->ga_log = iommu_alloc_pages_node_sz(nid, GFP_KERNEL, GA_LOG_SIZE); if (!iommu->ga_log) goto err_out; From eb29b7bbc8ba28bbb0b9fdd655e931e1d1fa625c Mon Sep 17 00:00:00 2001 From: Vasant Hegde Date: Mon, 24 Aug 2026 06:29:07 +0000 Subject: [PATCH 0849/1198] iommu/amd: Fix premature break in init_iommu_one() again Commit 283d245468a2 ("iommu/amd: Fix premature break in init_iommu_one()") unintentionally broke older platforms - such as the ASRockRack B550D4-4L - where the BIOS advertises incorrect IOMMU features. Move the HATDis check ahead of the GASup check, and re-introduce the break inside the GASup check to restore correct behavior on affected platforms. This is a short-term fix to resolve the regression. Longer term, we should rework how EFRs are tracked and prioritize the MMIO-advertised EFR over the one reported via IVRS. That requires more extensive changes and will be addressed separately. Fixes: 283d245468a2 ("iommu/amd: Fix premature break in init_iommu_one()") Reported-by: Andreas Juch Closes: https://lore.kernel.org/linux-iommu/07b2d390-f7a0-47e2-bc2c-eb0853acf52e@juch.cc/ Tested-by: Andreas Juch Signed-off-by: Vasant Hegde Signed-off-by: Joerg Roedel --- drivers/iommu/amd/init.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index c6b106d5921e..edcc187b8f14 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -1922,19 +1922,20 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h, else iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET; - /* XT and GAM require GA mode. */ - if ((h->efr_reg & (0x1 << IOMMU_EFR_GASUP_SHIFT)) == 0) { - amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY; - } else { - if (h->efr_reg & BIT(IOMMU_EFR_XTSUP_SHIFT)) - amd_iommu_xt_mode = IRQ_REMAP_X2APIC_MODE; - } - if (h->efr_attr & BIT(IOMMU_IVHD_ATTR_HATDIS_SHIFT)) { pr_warn_once("Host Address Translation is not supported.\n"); amd_iommu_hatdis = true; } + /* XT and GAM require GA mode. */ + if ((h->efr_reg & (0x1 << IOMMU_EFR_GASUP_SHIFT)) == 0) { + amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY; + break; + } else { + if (h->efr_reg & BIT(IOMMU_EFR_XTSUP_SHIFT)) + amd_iommu_xt_mode = IRQ_REMAP_X2APIC_MODE; + } + early_iommu_features_init(iommu, h); break; From fa5c0827f0b7bac6d0a188f10118151769ae68fd Mon Sep 17 00:00:00 2001 From: Hemanth Selam Date: Tue, 25 Aug 2026 15:35:54 +0530 Subject: [PATCH 0850/1198] iommu/amd: Fix ineffective error check in nested domain allocation amd_iommu_pdom_id_alloc() returns an int: a domain ID on success, or the negative errno from ida_alloc_range() when the ID space is exhausted or memory is short. amd_iommu_alloc_domain_nested() stores that return value in gdom_info->hdom_id, which is a u32, and only then tests it: gdom_info->hdom_id = amd_iommu_pdom_id_alloc(); if (gdom_info->hdom_id <= 0) { The assignment discards the sign, so -ENOSPC becomes 0xffffffe4 and the test never fires. The nested domain is then set up with a host domain ID that was never allocated, instead of the allocation failing with -ENOSPC. Keep the value in an int, test it there, and store it only once it is known to be valid, which is what the other amd_iommu_pdom_id_alloc() callers already do. Fixes: 757d2b1fdf5b ("iommu/amd: Introduce gDomID-to-hDomID Mapping and handle parent domain invalidation") Signed-off-by: Hemanth Selam Reviewed-by: Vasant Hegde Signed-off-by: Joerg Roedel --- drivers/iommu/amd/nested.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/amd/nested.c b/drivers/iommu/amd/nested.c index 63b53b29e029..f1c7987fc585 100644 --- a/drivers/iommu/amd/nested.c +++ b/drivers/iommu/amd/nested.c @@ -96,7 +96,7 @@ struct iommu_domain * amd_iommu_alloc_domain_nested(struct iommufd_viommu *viommu, u32 flags, const struct iommu_user_data *user_data) { - int ret; + int ret, hdom_id; unsigned long irqflags; struct nested_domain *ndom; struct guest_domain_mapping_info *gdom_info; @@ -161,8 +161,8 @@ amd_iommu_alloc_domain_nested(struct iommufd_viommu *viommu, u32 flags, } /* The gDomID does not exist. We allocate new hdom_id */ - gdom_info->hdom_id = amd_iommu_pdom_id_alloc(); - if (gdom_info->hdom_id <= 0) { + hdom_id = amd_iommu_pdom_id_alloc(); + if (hdom_id <= 0) { __xa_cmpxchg(&aviommu->gdomid_array, ndom->gdom_id, gdom_info, NULL, GFP_ATOMIC); xa_unlock_irqrestore(&aviommu->gdomid_array, irqflags); @@ -170,6 +170,7 @@ amd_iommu_alloc_domain_nested(struct iommufd_viommu *viommu, u32 flags, goto out_err_gdom_info; } + gdom_info->hdom_id = hdom_id; ndom->gdom_info = gdom_info; refcount_set(&gdom_info->users, 1); From adbd8a08208dc64bb1381f51b4f11ffdce1343fa Mon Sep 17 00:00:00 2001 From: Daasaradhi Mannava Date: Sat, 5 Sep 2026 15:49:00 +0000 Subject: [PATCH 0851/1198] MAINTAINERS: Drop the nonexistent vsi-iommu.h file entry Commit 917ace84b770 ("iommu: Add verisilicon IOMMU driver") added the VERISILICON IOMMU DRIVER section, including a file entry for include/linux/vsi-iommu.h. That header is not present in the tree and no file includes it; the driver in drivers/iommu/vsi-iommu.c is self-contained. scripts/get_maintainer.pl --self-test=patterns reports the pattern as matching no file. Drop the stale entry so the section only lists files that exist. Assisted-by: LLM Signed-off-by: Daasaradhi Mannava Reviewed-by: Benjamin Gaignard Signed-off-by: Joerg Roedel --- MAINTAINERS | 1 - 1 file changed, 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 6215fcb07770..0c4ef770807f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -28607,7 +28607,6 @@ L: iommu@lists.linux.dev S: Maintained F: Documentation/devicetree/bindings/iommu/verisilicon,iommu.yaml F: drivers/iommu/vsi-iommu.c -F: include/linux/vsi-iommu.h VF610 NAND DRIVER M: Stefan Agner From e317326d1755ea054b98e7a4833b929157461c35 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 19 Aug 2026 21:05:17 +0200 Subject: [PATCH 0852/1198] hwmon: (ltc4282) Make sure clk_init_data is fully initialized The clk_init_data structure contains several mutually-exclusive members for different methods to specify the possible parents of a clock, prompting drivers to initialize only the members they need. However, not initializing all members may cause subtle issues, which are only exposed when CONFIG_INIT_STACK_ALL_PATTERN or CONFIG_INIT_STACK_NONE is enabled. ltc428_clk_provider_setup() does not fill in any parent clocks, and assumes that init.num_parents is NULL. However, the latter in uninitialized, and thus may cause a crash. Make sure all members are fully initialized, to fix such bugs, and to avoid future breakage when converting drivers to a different method for specifying the parents. Fixes: cbc29538dbf7d740 ("hwmon: Add driver for LTC4282") Signed-off-by: Geert Uytterhoeven Link: https://patch.msgid.link/8ec3c5cbd2df675a938f090470f5da5f22008517.1787165329.git.geert+renesas@glider.be Reviewed-by: Brian Masney Signed-off-by: Guenter Roeck --- drivers/hwmon/ltc4282.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hwmon/ltc4282.c b/drivers/hwmon/ltc4282.c index b1675dc5b3c7..54ba4b8542e9 100644 --- a/drivers/hwmon/ltc4282.c +++ b/drivers/hwmon/ltc4282.c @@ -1106,7 +1106,7 @@ static const struct clk_ops ltc4282_ops = { static int ltc428_clk_provider_setup(struct ltc4282_state *st, struct device *dev) { - struct clk_init_data init; + struct clk_init_data init = {}; int ret; if (!IS_ENABLED(CONFIG_COMMON_CLK)) From 9607c245ca6674955e5e43e3606db410ae9e0b90 Mon Sep 17 00:00:00 2001 From: Nikhil Gurudasani Date: Wed, 19 Aug 2026 23:37:01 +0530 Subject: [PATCH 0853/1198] hwmon: (mcp9982) Propagate one-shot polling errors When a device is in standby, the driver starts a one-shot conversion and polls the BUSY flag before reading temperature, alarm, or fault data. The poll result is currently ignored. Therefore, a timeout or a status-register read failure can be hidden by a later successful read, causing stale data to be returned as valid. Return the polling error before reading the requested attribute. Fixes: e2fe950f34e5 ("hwmon: add support for MCP998X") Cc: stable@vger.kernel.org Signed-off-by: Nikhil Gurudasani Link: https://patch.msgid.link/20260819180701.34797-1-nikhilgurudasani314@gmail.com Signed-off-by: Guenter Roeck --- drivers/hwmon/mcp9982.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/hwmon/mcp9982.c b/drivers/hwmon/mcp9982.c index 9e19e2697e25..3918dc36c946 100644 --- a/drivers/hwmon/mcp9982.c +++ b/drivers/hwmon/mcp9982.c @@ -395,6 +395,8 @@ static int mcp9982_read(struct device *dev, enum hwmon_sensor_types type, u32 at reg_status, !(reg_status & MCP9982_STATUS_BUSY), MCP9982_WAKE_UP_TIME_US, MCP9982_WAKE_UP_TIME_US * 10); + if (ret) + return ret; break; } break; From a2471ed17b0e6ff7bfb6b2ea8e6e5b04c309d293 Mon Sep 17 00:00:00 2001 From: Fan Wu Date: Wed, 19 Aug 2026 03:33:17 +0000 Subject: [PATCH 0854/1198] hwmon: (gpio-fan) Fix use-after-free in alarm work fan_alarm_irq_handler() queues fan_data->alarm_work, but nothing cancels it. fan_alarm_notify() dereferences fan_data and its hwmon device. On unbind, devres frees the interrupt, which only waits for the handler itself, and then releases the hwmon device and fan_data, so a pending fan_alarm_notify() can run after those frees. Replace INIT_WORK() with devm_work_autocancel(), registered before devm_request_irq(). The devres cleanup then frees the interrupt first, so no new work can be queued, and cancels the work while fan_data and the hwmon device are still alive. This issue was found by an in-house static analysis tool. Fixes: d6fe1360f42e ("hwmon: add generic GPIO fan driver") Cc: stable@vger.kernel.org Assisted-by: Codex:gpt-5.6 Signed-off-by: Fan Wu Link: https://patch.msgid.link/20260819033317.446191-1-fanwu01@zju.edu.cn Signed-off-by: Guenter Roeck --- drivers/hwmon/gpio-fan.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c index 084828e1e281..7f36e5f6f223 100644 --- a/drivers/hwmon/gpio-fan.c +++ b/drivers/hwmon/gpio-fan.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -84,6 +85,7 @@ static DEVICE_ATTR_RO(fan1_alarm); static int fan_alarm_init(struct gpio_fan_data *fan_data) { int alarm_irq; + int err; struct device *dev = fan_data->dev; /* @@ -94,7 +96,11 @@ static int fan_alarm_init(struct gpio_fan_data *fan_data) if (alarm_irq <= 0) return 0; - INIT_WORK(&fan_data->alarm_work, fan_alarm_notify); + err = devm_work_autocancel(dev, &fan_data->alarm_work, + fan_alarm_notify); + if (err) + return err; + irq_set_irq_type(alarm_irq, IRQ_TYPE_EDGE_BOTH); return devm_request_irq(dev, alarm_irq, fan_alarm_irq_handler, IRQF_SHARED, "GPIO fan alarm", fan_data); From b4fffa75c1d6f87e6dc6191dec900f2b5bd23a1c Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Thu, 20 Aug 2026 21:40:48 -0700 Subject: [PATCH 0855/1198] Documentation/hwmon: Document hwmon_notify_event() The hwmon core provides hwmon_notify_event() for drivers to report events such as alarm or fault conditions to userspace via sysfs notifications and uevents, as well as to the thermal subsystem for temperature sensors. However, this function is not documented in the hwmon kernel API guide. Add the function prototype and description of hwmon_notify_event() to Documentation/hwmon/hwmon-kernel-api.rst. Cc: Kalesh AP Reviewed-by: Kalesh AP Fixes: 1597b374af222 ("hwmon: Add notification support") Signed-off-by: Guenter Roeck --- Documentation/hwmon/hwmon-kernel-api.rst | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/Documentation/hwmon/hwmon-kernel-api.rst b/Documentation/hwmon/hwmon-kernel-api.rst index 9fcde32a140d..c3eb433a78f6 100644 --- a/Documentation/hwmon/hwmon-kernel-api.rst +++ b/Documentation/hwmon/hwmon-kernel-api.rst @@ -42,6 +42,9 @@ register/unregister functions:: char *devm_hwmon_sanitize_name(struct device *dev, const char *name); + int hwmon_notify_event(struct device *dev, enum hwmon_sensor_types type, + u32 attr, int channel); + void hwmon_lock(struct device *dev); void hwmon_unlock(struct device *dev); @@ -90,6 +93,18 @@ implemented in the driver, or debugfs functions, hwmon_lock() and hwmon_unlock() can be used to ensure that calls to those functions are serialized. Those functions also support guard() and scoped_guard() variants. +Drivers can call hwmon_notify_event() to notify userspace and the thermal +subsystem when a hardware monitoring event (such as an alarm or a fault +condition) occurs or clears. The parameters are the hwmon device, the sensor +type, the attribute identifier associated with the event (such as +hwmon_temp_max_alarm or hwmon_fan_fault), and the sensor channel number. +hwmon_notify_event() generates a sysfs event (calling sysfs_notify()) and a +udev event with the attribute name passed in the NAME environment property +(e.g., "NAME=temp1_max_alarm"). If the event is for a temperature sensor and +the sensor is attached to a thermal zone, it also notifies the thermal +subsystem to update the thermal zone. hwmon_notify_event() returns 0 on +success or a negative error code on failure. + Using devm_hwmon_device_register_with_info() -------------------------------------------- From 354ccc99b2dc8ba0cf6d4de34e520bcf6ecca5c2 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Thu, 20 Aug 2026 10:51:50 -0700 Subject: [PATCH 0856/1198] hwmon: Fix potential UAF in pec_store Sashiko reports: In pec_store(), a guard(mutex)(&hwdev->lock) is taken. If the chip write operation returns an error other than -EOPNOTSUPP, the code jumps to the put label, which calls put_device(hdev). If this drops the final reference, the device is freed. When the function then returns, the guard cleanup function runs and attempts to unlock the freed mutex. Use scoped_guard() instead of guard() to avoid the problem. Fixes: 3ad2a7b9b15d5 ("hwmon: Serialize accesses in hwmon core") Signed-off-by: Guenter Roeck --- drivers/hwmon/hwmon.c | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c index 41755910a25a..3e65fc6d25eb 100644 --- a/drivers/hwmon/hwmon.c +++ b/drivers/hwmon/hwmon.c @@ -371,18 +371,17 @@ static ssize_t pec_store(struct device *dev, const struct device_attribute *deva * handling is not required. */ hwdev = to_hwmon_device(hdev); - guard(mutex)(&hwdev->lock); - if (hwdev->chip->ops->write) { - err = hwdev->chip->ops->write(hdev, hwmon_chip, hwmon_chip_pec, 0, val); - if (err && err != -EOPNOTSUPP) - goto put; + scoped_guard(mutex, &hwdev->lock) { + if (hwdev->chip->ops->write) { + err = hwdev->chip->ops->write(hdev, hwmon_chip, hwmon_chip_pec, 0, val); + if (err && err != -EOPNOTSUPP) + goto put; + } + if (!val) + client->flags &= ~I2C_CLIENT_PEC; + else + client->flags |= I2C_CLIENT_PEC; } - - if (!val) - client->flags &= ~I2C_CLIENT_PEC; - else - client->flags |= I2C_CLIENT_PEC; - err = count; put: put_device(hdev); From 8afc94bfb0ffdfc4a168081785820aa4818d1d23 Mon Sep 17 00:00:00 2001 From: Jared Kangas Date: Thu, 20 Aug 2026 06:09:21 -0700 Subject: [PATCH 0857/1198] hwmon: (ina2xx) Acquire hwmon_lock in shunt_resistor_show() shunt_resistor_store() currently acquires hwmon_lock to set data->rshunt, but the corresponding access in shunt_resistor_show() is unprotected. Acquire the lock in shunt_resistor_show() as well to ensure proper synchronization. Fixes: 3ad867001c91 ("hwmon: (ina2xx) fix sysfs shunt resistor read access") Reported-by: Sashiko Closes: https://lore.kernel.org/all/20260729162836.89BDF1F00A3A@smtp.kernel.org/ Signed-off-by: Jared Kangas Link: https://patch.msgid.link/20260820-upstream-ina2xx-in0-curr1-alarms-v2-1-fdce35abc41e@redhat.com Signed-off-by: Guenter Roeck --- drivers/hwmon/ina2xx.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/hwmon/ina2xx.c b/drivers/hwmon/ina2xx.c index 5c6dc2c370d8..f1f988d099a5 100644 --- a/drivers/hwmon/ina2xx.c +++ b/drivers/hwmon/ina2xx.c @@ -883,8 +883,12 @@ static ssize_t shunt_resistor_show(struct device *dev, struct device_attribute *da, char *buf) { struct ina2xx_data *data = dev_get_drvdata(dev); + long rshunt; - return sysfs_emit(buf, "%li\n", data->rshunt); + scoped_guard(hwmon_lock, dev) { + rshunt = data->rshunt; + } + return sysfs_emit(buf, "%li\n", rshunt); } static ssize_t shunt_resistor_store(struct device *dev, From 2bf98a6af10388215398a30d723ff1f6ff5ce4f7 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Thu, 20 Aug 2026 22:19:13 -0700 Subject: [PATCH 0858/1198] hwmon: Ensure that 'dev' passed to hwmon_notify_event() is a hwmon device The device parameter of hwmon_notify_event() must be a hardware monitoring device. Since this is easy to get wrong, and since passing a non-hwmon device may result in a crash, generate a warning traceback and abort if a wrong device class is passed as parameter. Signed-off-by: Guenter Roeck --- drivers/hwmon/hwmon.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c index 3e65fc6d25eb..10d2df3efdfa 100644 --- a/drivers/hwmon/hwmon.c +++ b/drivers/hwmon/hwmon.c @@ -318,6 +318,11 @@ static int hwmon_attr_base(enum hwmon_sensor_types type) return 1; } +static bool is_hwmon_device(struct device *dev) +{ + return dev->class == &hwmon_class; +} + #if IS_REACHABLE(CONFIG_I2C) /* @@ -338,7 +343,7 @@ static int hwmon_attr_base(enum hwmon_sensor_types type) static int hwmon_match_device(struct device *dev, const void *data) { - return dev->class == &hwmon_class; + return is_hwmon_device(dev); } static ssize_t pec_show(struct device *dev, const struct device_attribute *dummy, @@ -781,6 +786,9 @@ int hwmon_notify_event(struct device *dev, enum hwmon_sensor_types type, const char *template; int base; + if (WARN(!is_hwmon_device(dev), "%s is not a hardware monitoring device\n", + dev_name(dev))) + return -EINVAL; if (type >= ARRAY_SIZE(__templates)) return -EINVAL; if (attr >= __templates_size[type]) From 3d44ab826e0244a8b9eaf0f1f604f4cb8b890325 Mon Sep 17 00:00:00 2001 From: Jared Kangas Date: Thu, 20 Aug 2026 06:09:22 -0700 Subject: [PATCH 0859/1198] hwmon: (ina2xx) Parameterize ina2xx_data in ina226_alert_read() Mirror ina226_alert_limit_read/write and use struct ina2xx_data instead of struct regmap in ina226_alert_read's parameters. Signed-off-by: Jared Kangas Link: https://patch.msgid.link/20260820-upstream-ina2xx-in0-curr1-alarms-v2-2-fdce35abc41e@redhat.com Signed-off-by: Guenter Roeck --- drivers/hwmon/ina2xx.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/hwmon/ina2xx.c b/drivers/hwmon/ina2xx.c index f1f988d099a5..0fd17a6d4f90 100644 --- a/drivers/hwmon/ina2xx.c +++ b/drivers/hwmon/ina2xx.c @@ -498,12 +498,12 @@ static int ina2xx_chip_read(struct device *dev, u32 attr, long *val) return 0; } -static int ina226_alert_read(struct regmap *regmap, u32 mask, long *val) +static int ina226_alert_read(struct ina2xx_data *data, u32 mask, long *val) { unsigned int regval; int ret; - ret = regmap_read_bypassed(regmap, INA226_MASK_ENABLE, ®val); + ret = regmap_read_bypassed(data->regmap, INA226_MASK_ENABLE, ®val); if (ret) return ret; @@ -538,9 +538,9 @@ static int ina2xx_in_read(struct device *dev, u32 attr, int channel, long *val) return ina226_alert_limit_read(data, over_voltage_mask, voltage_reg, val); case hwmon_in_lcrit_alarm: - return ina226_alert_read(regmap, under_voltage_mask, val); + return ina226_alert_read(data, under_voltage_mask, val); case hwmon_in_crit_alarm: - return ina226_alert_read(regmap, over_voltage_mask, val); + return ina226_alert_read(data, over_voltage_mask, val); default: return -EOPNOTSUPP; } @@ -597,7 +597,7 @@ static int ina2xx_power_read(struct device *dev, u32 attr, long *val) return ina226_alert_limit_read(data, INA226_POWER_OVER_LIMIT_MASK, INA2XX_POWER, val); case hwmon_power_crit_alarm: - return ina226_alert_read(data->regmap, INA226_POWER_OVER_LIMIT_MASK, val); + return ina226_alert_read(data, INA226_POWER_OVER_LIMIT_MASK, val); default: return -EOPNOTSUPP; } @@ -639,9 +639,9 @@ static int ina2xx_curr_read(struct device *dev, u32 attr, long *val) return ina226_alert_limit_read(data, INA226_SHUNT_OVER_VOLTAGE_MASK, INA2XX_CURRENT, val); case hwmon_curr_lcrit_alarm: - return ina226_alert_read(regmap, INA226_SHUNT_UNDER_VOLTAGE_MASK, val); + return ina226_alert_read(data, INA226_SHUNT_UNDER_VOLTAGE_MASK, val); case hwmon_curr_crit_alarm: - return ina226_alert_read(regmap, INA226_SHUNT_OVER_VOLTAGE_MASK, val); + return ina226_alert_read(data, INA226_SHUNT_OVER_VOLTAGE_MASK, val); default: return -EOPNOTSUPP; } From e92b9208415a90e9cc1d923c5d8c058dde77be68 Mon Sep 17 00:00:00 2001 From: Jared Kangas Date: Thu, 20 Aug 2026 06:09:23 -0700 Subject: [PATCH 0860/1198] hwmon: (ina2xx) Replace masks with enum in alert functions Instead of passing an explicit mask to alert/limit functions like ina226_alert_read(), introduce an enum ina2xx_alert_type that can be converted to a mask internally. This semantically separates current from shunt voltage in helpers that use function masks, which previously saw the same mask for the two functions. Signed-off-by: Jared Kangas Link: https://patch.msgid.link/20260820-upstream-ina2xx-in0-curr1-alarms-v2-3-fdce35abc41e@redhat.com Signed-off-by: Guenter Roeck --- drivers/hwmon/ina2xx.c | 90 +++++++++++++++++++++++++++++++----------- 1 file changed, 67 insertions(+), 23 deletions(-) diff --git a/drivers/hwmon/ina2xx.c b/drivers/hwmon/ina2xx.c index 0fd17a6d4f90..75e97e30bdcd 100644 --- a/drivers/hwmon/ina2xx.c +++ b/drivers/hwmon/ina2xx.c @@ -129,6 +129,17 @@ enum ina2xx_ids { sy24655 }; +enum ina2xx_alert_type { + INA2XX_ALERT_NONE, + INA2XX_ALERT_CURRENT_LOW, + INA2XX_ALERT_CURRENT_HIGH, + INA2XX_ALERT_POWER_HIGH, + INA2XX_ALERT_BUS_VOLTAGE_LOW, + INA2XX_ALERT_BUS_VOLTAGE_HIGH, + INA2XX_ALERT_SHUNT_VOLTAGE_LOW, + INA2XX_ALERT_SHUNT_VOLTAGE_HIGH, +}; + struct ina2xx_config { u16 config_default; bool has_alerts; /* chip supports alerts and limits */ @@ -428,16 +439,43 @@ static u16 ina226_alert_to_reg(struct ina2xx_data *data, int reg, long val) } } -static int ina226_alert_limit_read(struct ina2xx_data *data, u32 mask, int reg, long *val) +static u32 ina2xx_alert_type_to_mask(enum ina2xx_alert_type alert) +{ + switch (alert) { + case INA2XX_ALERT_CURRENT_LOW: + case INA2XX_ALERT_SHUNT_VOLTAGE_LOW: + return INA226_SHUNT_UNDER_VOLTAGE_MASK; + case INA2XX_ALERT_CURRENT_HIGH: + case INA2XX_ALERT_SHUNT_VOLTAGE_HIGH: + return INA226_SHUNT_OVER_VOLTAGE_MASK; + case INA2XX_ALERT_BUS_VOLTAGE_LOW: + return INA226_BUS_UNDER_VOLTAGE_MASK; + case INA2XX_ALERT_BUS_VOLTAGE_HIGH: + return INA226_BUS_OVER_VOLTAGE_MASK; + case INA2XX_ALERT_POWER_HIGH: + return INA226_POWER_OVER_LIMIT_MASK; + case INA2XX_ALERT_NONE: + return 0; + default: + /* programmer error */ + WARN_ON_ONCE(1); + return 0; + } +} + +static int ina226_alert_limit_read(struct ina2xx_data *data, enum ina2xx_alert_type alert, + int reg, long *val) { struct regmap *regmap = data->regmap; int regval; + u32 mask; int ret; ret = regmap_read(regmap, INA226_MASK_ENABLE, ®val); if (ret) return ret; + mask = ina2xx_alert_type_to_mask(alert); if (regval & mask) { ret = regmap_read(regmap, INA226_ALERT_LIMIT, ®val); if (ret) @@ -449,9 +487,11 @@ static int ina226_alert_limit_read(struct ina2xx_data *data, u32 mask, int reg, return 0; } -static int ina226_alert_limit_write(struct ina2xx_data *data, u32 mask, int reg, long val) +static int ina226_alert_limit_write(struct ina2xx_data *data, enum ina2xx_alert_type alert, + int reg, long val) { struct regmap *regmap = data->regmap; + u32 mask; int ret; if (val < 0) @@ -472,9 +512,11 @@ static int ina226_alert_limit_write(struct ina2xx_data *data, u32 mask, int reg, if (ret < 0) return ret; - if (val) + if (val) { + mask = ina2xx_alert_type_to_mask(alert); return regmap_update_bits(regmap, INA226_MASK_ENABLE, INA226_ALERT_CONFIG_MASK, mask); + } return 0; } @@ -498,15 +540,17 @@ static int ina2xx_chip_read(struct device *dev, u32 attr, long *val) return 0; } -static int ina226_alert_read(struct ina2xx_data *data, u32 mask, long *val) +static int ina226_alert_read(struct ina2xx_data *data, enum ina2xx_alert_type alert, long *val) { unsigned int regval; + u32 mask; int ret; ret = regmap_read_bypassed(data->regmap, INA226_MASK_ENABLE, ®val); if (ret) return ret; + mask = ina2xx_alert_type_to_mask(alert); *val = (regval & mask) && (regval & INA226_ALERT_FUNCTION_FLAG); return 0; @@ -515,10 +559,10 @@ static int ina226_alert_read(struct ina2xx_data *data, u32 mask, long *val) static int ina2xx_in_read(struct device *dev, u32 attr, int channel, long *val) { int voltage_reg = channel ? INA2XX_BUS_VOLTAGE : INA2XX_SHUNT_VOLTAGE; - u32 under_voltage_mask = channel ? INA226_BUS_UNDER_VOLTAGE_MASK - : INA226_SHUNT_UNDER_VOLTAGE_MASK; - u32 over_voltage_mask = channel ? INA226_BUS_OVER_VOLTAGE_MASK - : INA226_SHUNT_OVER_VOLTAGE_MASK; + enum ina2xx_alert_type under_voltage_alert = channel ? INA2XX_ALERT_BUS_VOLTAGE_LOW + : INA2XX_ALERT_SHUNT_VOLTAGE_LOW; + enum ina2xx_alert_type over_voltage_alert = channel ? INA2XX_ALERT_BUS_VOLTAGE_HIGH + : INA2XX_ALERT_SHUNT_VOLTAGE_HIGH; struct ina2xx_data *data = dev_get_drvdata(dev); struct regmap *regmap = data->regmap; unsigned int regval; @@ -532,15 +576,15 @@ static int ina2xx_in_read(struct device *dev, u32 attr, int channel, long *val) *val = ina2xx_get_value(data, voltage_reg, regval); break; case hwmon_in_lcrit: - return ina226_alert_limit_read(data, under_voltage_mask, + return ina226_alert_limit_read(data, under_voltage_alert, voltage_reg, val); case hwmon_in_crit: - return ina226_alert_limit_read(data, over_voltage_mask, + return ina226_alert_limit_read(data, over_voltage_alert, voltage_reg, val); case hwmon_in_lcrit_alarm: - return ina226_alert_read(data, under_voltage_mask, val); + return ina226_alert_read(data, under_voltage_alert, val); case hwmon_in_crit_alarm: - return ina226_alert_read(data, over_voltage_mask, val); + return ina226_alert_read(data, over_voltage_alert, val); default: return -EOPNOTSUPP; } @@ -594,10 +638,10 @@ static int ina2xx_power_read(struct device *dev, u32 attr, long *val) case hwmon_power_average: return sy24655_average_power_read(data, SY24655_EIN, val); case hwmon_power_crit: - return ina226_alert_limit_read(data, INA226_POWER_OVER_LIMIT_MASK, + return ina226_alert_limit_read(data, INA2XX_ALERT_POWER_HIGH, INA2XX_POWER, val); case hwmon_power_crit_alarm: - return ina226_alert_read(data, INA226_POWER_OVER_LIMIT_MASK, val); + return ina226_alert_read(data, INA2XX_ALERT_POWER_HIGH, val); default: return -EOPNOTSUPP; } @@ -633,15 +677,15 @@ static int ina2xx_curr_read(struct device *dev, u32 attr, long *val) *val = ina2xx_get_value(data, INA2XX_CURRENT, regval); return 0; case hwmon_curr_lcrit: - return ina226_alert_limit_read(data, INA226_SHUNT_UNDER_VOLTAGE_MASK, + return ina226_alert_limit_read(data, INA2XX_ALERT_CURRENT_LOW, INA2XX_CURRENT, val); case hwmon_curr_crit: - return ina226_alert_limit_read(data, INA226_SHUNT_OVER_VOLTAGE_MASK, + return ina226_alert_limit_read(data, INA2XX_ALERT_CURRENT_HIGH, INA2XX_CURRENT, val); case hwmon_curr_lcrit_alarm: - return ina226_alert_read(data, INA226_SHUNT_UNDER_VOLTAGE_MASK, val); + return ina226_alert_read(data, INA2XX_ALERT_CURRENT_LOW, val); case hwmon_curr_crit_alarm: - return ina226_alert_read(data, INA226_SHUNT_OVER_VOLTAGE_MASK, val); + return ina226_alert_read(data, INA2XX_ALERT_CURRENT_HIGH, val); default: return -EOPNOTSUPP; } @@ -685,12 +729,12 @@ static int ina2xx_in_write(struct device *dev, u32 attr, int channel, long val) switch (attr) { case hwmon_in_lcrit: return ina226_alert_limit_write(data, - channel ? INA226_BUS_UNDER_VOLTAGE_MASK : INA226_SHUNT_UNDER_VOLTAGE_MASK, + channel ? INA2XX_ALERT_BUS_VOLTAGE_LOW : INA2XX_ALERT_SHUNT_VOLTAGE_LOW, channel ? INA2XX_BUS_VOLTAGE : INA2XX_SHUNT_VOLTAGE, val); case hwmon_in_crit: return ina226_alert_limit_write(data, - channel ? INA226_BUS_OVER_VOLTAGE_MASK : INA226_SHUNT_OVER_VOLTAGE_MASK, + channel ? INA2XX_ALERT_BUS_VOLTAGE_HIGH : INA2XX_ALERT_SHUNT_VOLTAGE_HIGH, channel ? INA2XX_BUS_VOLTAGE : INA2XX_SHUNT_VOLTAGE, val); default: @@ -705,7 +749,7 @@ static int ina2xx_power_write(struct device *dev, u32 attr, long val) switch (attr) { case hwmon_power_crit: - return ina226_alert_limit_write(data, INA226_POWER_OVER_LIMIT_MASK, + return ina226_alert_limit_write(data, INA2XX_ALERT_POWER_HIGH, INA2XX_POWER, val); default: return -EOPNOTSUPP; @@ -719,10 +763,10 @@ static int ina2xx_curr_write(struct device *dev, u32 attr, long val) switch (attr) { case hwmon_curr_lcrit: - return ina226_alert_limit_write(data, INA226_SHUNT_UNDER_VOLTAGE_MASK, + return ina226_alert_limit_write(data, INA2XX_ALERT_CURRENT_LOW, INA2XX_CURRENT, val); case hwmon_curr_crit: - return ina226_alert_limit_write(data, INA226_SHUNT_OVER_VOLTAGE_MASK, + return ina226_alert_limit_write(data, INA2XX_ALERT_CURRENT_HIGH, INA2XX_CURRENT, val); default: return -EOPNOTSUPP; From 35760f5efd7bfa7a44a3831f47e19fe9cbafc905 Mon Sep 17 00:00:00 2001 From: Jared Kangas Date: Thu, 20 Aug 2026 06:09:24 -0700 Subject: [PATCH 0861/1198] hwmon: (ina2xx) Decouple in0 and curr1 alarms INA2XX current limits are converted into shunt voltage limits internally using the shunt resistor value. Once a current limit's corresponding voltage limit is written to the hardware, shunt voltage and current alarms are indistinguishable from each other. This causes two issues: 1. in0/curr1 alarms may be unintentionally cleared by reading from the opposite input's alarm. 2. When a limit for either in0 (shunt voltage) or curr1 (current) is set, both of their alarms are triggered, and both of their limits read nonzero. An example of this behavior on an INA231: # cd /sys/class/hwmon/hwmon0 # head {curr1,in0}_input ==> curr1_input <== 1713 ==> in0_input <== 2 # echo 1800 >curr1_lcrit # head {curr1,in0}_lcrit_alarm ==> curr1_lcrit_alarm <== 1 ==> in0_lcrit_alarm <== 0 # head {in0,curr1}_lcrit_alarm ==> in0_lcrit_alarm <== 1 ==> curr1_lcrit_alarm <== 0 # head {in0,curr1}_lcrit_alarm ==> in0_lcrit_alarm <== 1 ==> curr1_lcrit_alarm <== 1 This is because curr1 uses the same underlying masks (INA226_SHUNT_*_VOLTAGE_MASK) as in0 on the hardware. As a result, ina2xx_{curr,in}_read() both read the shunt voltage alarms/limits without considering whether the voltage or current is currently set. To fix this, track the active alarm type in ina2xx_data and guard alarm/limit reads with a check that returns zero if the active alarm is for a different type. The new field is initialized based on the MASK_ENABLE register's set function, assuming voltage instead of current when the shunt voltage mask is set. After this fix, the alarms only read back 1 if their corresponding limit is set: # echo 0 >curr1_lcrit # head {curr1,in0}_lcrit_alarm ==> curr1_lcrit_alarm <== 0 ==> in0_lcrit_alarm <== 0 # echo 9999 >curr1_lcrit # head {curr1,in0}_lcrit_alarm ==> curr1_lcrit_alarm <== 1 ==> in0_lcrit_alarm <== 0 # echo 9999 >in0_lcrit # head {curr1,in0}_lcrit_alarm ==> curr1_lcrit_alarm <== 0 ==> in0_lcrit_alarm <== 1 Fixes: 4d5c2d986757 ("hwmon: (ina2xx) Add support for current limits") Signed-off-by: Jared Kangas Link: https://patch.msgid.link/20260820-upstream-ina2xx-in0-curr1-alarms-v2-4-fdce35abc41e@redhat.com Signed-off-by: Guenter Roeck --- drivers/hwmon/ina2xx.c | 65 ++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 63 insertions(+), 2 deletions(-) diff --git a/drivers/hwmon/ina2xx.c b/drivers/hwmon/ina2xx.c index 75e97e30bdcd..19b35f3bf3a3 100644 --- a/drivers/hwmon/ina2xx.c +++ b/drivers/hwmon/ina2xx.c @@ -8,6 +8,7 @@ */ #include +#include #include #include #include @@ -159,6 +160,7 @@ struct ina2xx_data { const struct ina2xx_config *config; enum ina2xx_ids chip; + enum ina2xx_alert_type active_alert; long rshunt; long current_lsb_uA; long power_lsb_uW; @@ -463,6 +465,35 @@ static u32 ina2xx_alert_type_to_mask(enum ina2xx_alert_type alert) } } +static enum ina2xx_alert_type ina2xx_mask_to_alert_type(u32 mask) +{ + int top_bit = fls(mask & INA226_ALERT_CONFIG_MASK); + + if (!top_bit) + return INA2XX_ALERT_NONE; + + /* + * Multiple bits may be set, with the highest-set function taking + * precedence according to the datasheet. Shunt voltage masks are + * assumed to map to voltage monitoring rather than current monitoring, + * since the latter isn't directly implemented in the hardware. + */ + switch (BIT(top_bit - 1)) { + case INA226_SHUNT_OVER_VOLTAGE_MASK: + return INA2XX_ALERT_SHUNT_VOLTAGE_HIGH; + case INA226_SHUNT_UNDER_VOLTAGE_MASK: + return INA2XX_ALERT_SHUNT_VOLTAGE_LOW; + case INA226_BUS_OVER_VOLTAGE_MASK: + return INA2XX_ALERT_BUS_VOLTAGE_HIGH; + case INA226_BUS_UNDER_VOLTAGE_MASK: + return INA2XX_ALERT_BUS_VOLTAGE_LOW; + case INA226_POWER_OVER_LIMIT_MASK: + return INA2XX_ALERT_POWER_HIGH; + default: + return INA2XX_ALERT_NONE; + } +} + static int ina226_alert_limit_read(struct ina2xx_data *data, enum ina2xx_alert_type alert, int reg, long *val) { @@ -471,6 +502,12 @@ static int ina226_alert_limit_read(struct ina2xx_data *data, enum ina2xx_alert_t u32 mask; int ret; + /* Avoid nonzero reads from inactive alerts caused by shared limit register */ + if (data->active_alert != alert) { + *val = 0; + return 0; + } + ret = regmap_read(regmap, INA226_MASK_ENABLE, ®val); if (ret) return ret; @@ -506,6 +543,7 @@ static int ina226_alert_limit_write(struct ina2xx_data *data, enum ina2xx_alert_ INA226_ALERT_CONFIG_MASK, 0); if (ret < 0) return ret; + data->active_alert = INA2XX_ALERT_NONE; ret = regmap_write(regmap, INA226_ALERT_LIMIT, ina226_alert_to_reg(data, reg, val)); @@ -514,9 +552,13 @@ static int ina226_alert_limit_write(struct ina2xx_data *data, enum ina2xx_alert_ if (val) { mask = ina2xx_alert_type_to_mask(alert); - return regmap_update_bits(regmap, INA226_MASK_ENABLE, - INA226_ALERT_CONFIG_MASK, mask); + ret = regmap_update_bits(regmap, INA226_MASK_ENABLE, + INA226_ALERT_CONFIG_MASK, mask); + if (ret < 0) + return ret; + data->active_alert = alert; } + return 0; } @@ -546,6 +588,15 @@ static int ina226_alert_read(struct ina2xx_data *data, enum ina2xx_alert_type al u32 mask; int ret; + /* + * With alert latching, reading alerts from hardware also clears the + * alert, so return early if the alert is inactive. + */ + if (data->active_alert != alert) { + *val = 0; + return 0; + } + ret = regmap_read_bypassed(data->regmap, INA226_MASK_ENABLE, ®val); if (ret) return ret; @@ -988,6 +1039,16 @@ static int ina2xx_init(struct device *dev, struct ina2xx_data *data) if (data->config->has_alerts) { bool active_high = device_property_read_bool(dev, "ti,alert-polarity-active-high"); + unsigned int mask_enable; + + /* + * Infer active alert from MASK_ENABLE in case it's already + * configured (e.g., by a past probe or firmware) + */ + ret = regmap_read(regmap, INA226_MASK_ENABLE, &mask_enable); + if (ret < 0) + return ret; + data->active_alert = ina2xx_mask_to_alert_type(mask_enable); regmap_update_bits(regmap, INA226_MASK_ENABLE, INA226_ALERT_LATCH_ENABLE | INA226_ALERT_POLARITY, From 013c5a93e8062014177d68af799e8867cf03958d Mon Sep 17 00:00:00 2001 From: Antonin Godard Date: Tue, 18 Aug 2026 10:08:40 +0200 Subject: [PATCH 0862/1198] Documentation: hwmon: replace full-width colon by a standard ASCII colon MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It prevented the pdfdocs target to complete, prompting the following error: Latexmk: ====Problematic refs and citations with line #s in .tex file: Missing character: There is no ： (U+FF1A) in font DejaVu Serif/OT:script=latn;l Fixes: 69001f21ded78 ("hwmon: document: add gpd-fan") Signed-off-by: Antonin Godard Link: https://patch.msgid.link/20260818-doc-hwmon-remove-confusable-v2-1-c1dff1ec01cd@bootlin.com Signed-off-by: Guenter Roeck --- Documentation/hwmon/gpd-fan.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/hwmon/gpd-fan.rst b/Documentation/hwmon/gpd-fan.rst index 29527a77fe88..b27657d33056 100644 --- a/Documentation/hwmon/gpd-fan.rst +++ b/Documentation/hwmon/gpd-fan.rst @@ -67,7 +67,7 @@ pwm1_enable at full speed. Write "1" to set to manual, write "2" to let the EC control decide fan speed. Read this attribute to see current status. - NB：In consideration of the safety of the device, when setting to manual mode, + NB: In consideration of the safety of the device, when setting to manual mode, the pwm speed will be set to the maximum value (255) by default. You can set a different value by writing pwm1 later. From 100eb7c7d0b28c52ad1b25d51c316fdc46c27c71 Mon Sep 17 00:00:00 2001 From: hanzhijian Date: Fri, 21 Aug 2026 19:57:20 +0800 Subject: [PATCH 0863/1198] hwmon: (yogafan) fix non-kernel-doc comment The file description comment starts with "/**" which is reserved for kernel-doc comments, triggering a kernel-doc checker warning. Change it to a plain "/*" comment since it does not document any function or struct. Fixes: c67c248ca406a ("hwmon: (yogafan) Add support for Lenovo Yoga/Legion fan monitoring") Signed-off-by: hanzhijian Link: https://patch.msgid.link/20260821115720.2017516-1-hanzhijian1991@gmail.com Signed-off-by: Guenter Roeck --- drivers/hwmon/yogafan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hwmon/yogafan.c b/drivers/hwmon/yogafan.c index 48fa5148d9e2..278cb089b0fd 100644 --- a/drivers/hwmon/yogafan.c +++ b/drivers/hwmon/yogafan.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * yoga_fan.c - Lenovo Yoga/Legion Fan Hardware Monitoring Driver * * Provides fan speed monitoring for Lenovo Yoga, Legion, and IdeaPad From 06b7cf395b1fb652a50db39674a759658fbfba0d Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Fri, 21 Aug 2026 07:49:15 -0700 Subject: [PATCH 0864/1198] hwmon: (sht4x) Add missing locks Sashiko reports: Heater sysfs callbacks (heater_enable_store, heater_power_store, and heater_time_store) are exposed to data races without the hwmon lock. If a user-space process reads hwmon data while another process enables the heater, heater_enable_store() executes without holding hwmon_lock(dev). This can interleave I2C commands and mutate shared state (data->heating_complete and data->data_pending) concurrently with sht4x_read_values(), leading to corrupted I2C sequences. Fixes: 53dfa12299c1 ("hwmon: (sht4x) Rely on subsystem locking") Cc: Alessandro Zini Signed-off-by: Guenter Roeck Link: https://patch.msgid.link/20260821144916.2889031-1-linux@roeck-us.net --- drivers/hwmon/sht4x.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/hwmon/sht4x.c b/drivers/hwmon/sht4x.c index 9cace0e8acda..7a0dc2ed723d 100644 --- a/drivers/hwmon/sht4x.c +++ b/drivers/hwmon/sht4x.c @@ -277,6 +277,8 @@ static ssize_t heater_enable_store(struct device *dev, heating_time_bound = 1100; } + guard(hwmon_lock)(dev); + if (time_before(jiffies, data->heating_complete)) return -EBUSY; @@ -314,6 +316,8 @@ static ssize_t heater_power_store(struct device *dev, if (power != 20 && power != 110 && power != 200) return -EINVAL; + guard(hwmon_lock)(dev); + data->heater_power = power; return count; @@ -344,6 +348,8 @@ static ssize_t heater_time_store(struct device *dev, if (time != 100 && time != 1000) return -EINVAL; + guard(hwmon_lock)(dev); + data->heater_time = time; return count; From 70c33e211b2b78830f76c908e5236b77ffde63a0 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Fri, 21 Aug 2026 07:49:16 -0700 Subject: [PATCH 0865/1198] hwmon: (sht4x) Fix return value from heater_enable_store() Sashiko reports: The return value in heater_enable_store() causes an unexpected write failure in user-space. When the heater is successfully enabled, the function returns 0 instead of count: drivers/hwmon/sht4x.c:heater_enable_store() { ... data->heating_complete = jiffies + msecs_to_jiffies(heating_time_bound); data->data_pending = true; return 0; } Returning 0 signals to VFS that no bytes were processed. Standard user-space tools will retry the write with the remaining bytes. On the retry, time_before(jiffies, data->heating_complete) evaluates to true, and the function immediately fails with -EBUSY. Return count as expected to fix the problem. Fixes: 0eed6fc3d2b9e ("hwmon: (sht4x): add heater support") Cc: Antoni Pokusinski Cc: Alessandro Zini Signed-off-by: Guenter Roeck Link: https://patch.msgid.link/20260821144916.2889031-2-linux@roeck-us.net --- drivers/hwmon/sht4x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hwmon/sht4x.c b/drivers/hwmon/sht4x.c index 7a0dc2ed723d..a97dda9e92dc 100644 --- a/drivers/hwmon/sht4x.c +++ b/drivers/hwmon/sht4x.c @@ -288,7 +288,7 @@ static ssize_t heater_enable_store(struct device *dev, data->heating_complete = jiffies + msecs_to_jiffies(heating_time_bound); data->data_pending = true; - return 0; + return count; } static ssize_t heater_power_show(struct device *dev, From 5a0aacaa2d593d7582ecfe289529b937b6dc5d3c Mon Sep 17 00:00:00 2001 From: Cong Nguyen Date: Fri, 28 Aug 2026 17:54:13 +0700 Subject: [PATCH 0866/1198] hwmon: (applesmc) fix key backlight workqueue leak on register failure applesmc_create_key_backlight() allocates applesmc_led_wq before calling led_classdev_register(). When register fails, the error is returned to applesmc_init(), which jumps to out_light_sysfs and skips applesmc_release_key_backlight(), leaking the workqueue. Destroy the workqueue on the register failure path. The bug was introduced when the inline init block was refactored into a helper that returns errors directly, dropping the old out_light_wq unwind label. Fixes: 0b0b5dff8967 ("hwmon: (applesmc) Simplify feature sysfs handling") Cc: stable@vger.kernel.org Assisted-by: Claude:claude-opus-4 Signed-off-by: Cong Nguyen Link: https://patch.msgid.link/20260828105413.2401385-1-congnt264@gmail.com Signed-off-by: Guenter Roeck --- drivers/hwmon/applesmc.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c index 00e603b5e401..d0baa10502f7 100644 --- a/drivers/hwmon/applesmc.c +++ b/drivers/hwmon/applesmc.c @@ -1128,12 +1128,17 @@ static void applesmc_release_light_sensor(void) static int applesmc_create_key_backlight(void) { + int ret; + if (!smcreg.has_key_backlight) return 0; applesmc_led_wq = create_singlethread_workqueue("applesmc-led"); if (!applesmc_led_wq) return -ENOMEM; - return led_classdev_register(&pdev->dev, &applesmc_backlight); + ret = led_classdev_register(&pdev->dev, &applesmc_backlight); + if (ret) + destroy_workqueue(applesmc_led_wq); + return ret; } static void applesmc_release_key_backlight(void) From a7c1290eef60711c10289c056ad32ed1f2b47b12 Mon Sep 17 00:00:00 2001 From: Vasileios Almpanis Date: Thu, 30 Jul 2026 11:30:24 +0200 Subject: [PATCH 0867/1198] configfs: pin the symlink target's dirent instead of chasing ->ci_dentry create_link() reads the target's configfs_dirent from item->ci_dentry->d_fsdata, relying on the item reference taken by get_target(). That reference pins the item, not its dentry: the dentry is pinned by DCACHE_PERSISTENT, which configfs_remove_dir() releases via simple_rmdir() while the item is still alive. A symlink racing with rmdir of its target can therefore find ->ci_dentry freed and its dirent released, triggering WARN_ON(!atomic_read(&sd->s_count)) in configfs_get(). Take the dirent in get_target() as well, under ->d_lock and atomically with the item reference, and pass it down to create_link(). A hashed dentry has not been killed yet, so its ->d_fsdata reference keeps the dirent alive there. Cc: stable@vger.kernel.org Fixes: 7063fbf22611 ("[PATCH] configfs: User-driven configuration filesystem") Signed-off-by: Vasileios Almpanis Tested-by: Breno Leitao Reviewed-by: Breno Leitao Link: https://patch.msgid.link/20260730093435.195441-2-vasilisalmpanis@gmail.com Signed-off-by: Breno Leitao --- fs/configfs/symlink.c | 24 ++++++++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-) diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c index 31eb28b27309..3b31c714400f 100644 --- a/fs/configfs/symlink.c +++ b/fs/configfs/symlink.c @@ -76,9 +76,9 @@ static int configfs_get_target_path(struct config_item *item, static int create_link(struct config_item *parent_item, struct config_item *item, + struct configfs_dirent *target_sd, struct dentry *dentry) { - struct configfs_dirent *target_sd = item->ci_dentry->d_fsdata; char *body; int ret; @@ -115,6 +115,7 @@ static int create_link(struct config_item *parent_item, static int get_target(const char *symname, struct config_item **target, + struct configfs_dirent **target_sd, struct super_block *sb) { struct path path __free(path_put) = {}; @@ -125,7 +126,20 @@ static int get_target(const char *symname, struct config_item **target, return ret; if (path.dentry->d_sb != sb) return -EPERM; - *target = configfs_get_config_item(path.dentry); + /* + * A hashed dentry guarantees that neither the item nor the dirent + * have been released yet, as removals unhash before dropping. + * Grab both references here. An item reference alone would not keep + * ->ci_dentry alive. + */ + spin_lock(&path.dentry->d_lock); + if (!d_unhashed(path.dentry)) { + struct configfs_dirent *sd = path.dentry->d_fsdata; + + *target = config_item_get(sd->s_element); + *target_sd = configfs_get(sd); + } + spin_unlock(&path.dentry->d_lock); if (!*target) return -ENOENT; return 0; @@ -139,6 +153,7 @@ int configfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct configfs_dirent *sd; struct config_item *parent_item; struct config_item *target_item = NULL; + struct configfs_dirent *target_sd = NULL; const struct config_item_type *type; sd = dentry->d_parent->d_fsdata; @@ -182,7 +197,7 @@ int configfs_symlink(struct mnt_idmap *idmap, struct inode *dir, * AV, a thoroughly annoyed bastard. */ inode_unlock(dir); - ret = get_target(symname, &target_item, dentry->d_sb); + ret = get_target(symname, &target_item, &target_sd, dentry->d_sb); inode_lock(dir); if (ret) goto out_put; @@ -196,13 +211,14 @@ int configfs_symlink(struct mnt_idmap *idmap, struct inode *dir, ret = type->ct_item_ops->allow_link(parent_item, target_item); if (!ret) { mutex_lock(&configfs_symlink_mutex); - ret = create_link(parent_item, target_item, dentry); + ret = create_link(parent_item, target_item, target_sd, dentry); mutex_unlock(&configfs_symlink_mutex); if (ret && type->ct_item_ops->drop_link) type->ct_item_ops->drop_link(parent_item, target_item); } + configfs_put(target_sd); config_item_put(target_item); out_put: From f06c2d26d1999d37e93299db0ecead04ca7d0b9f Mon Sep 17 00:00:00 2001 From: Vasileios Almpanis Date: Thu, 30 Jul 2026 11:30:25 +0200 Subject: [PATCH 0868/1198] configfs: unhash the dentry before dropping the item in rmdir configfs_get_config_item() treats a hashed dentry as proof that sd->s_element is a live config_item. configfs_rmdir() breaks that: simple_rmdir() leaves the dentry hashed, the last reference to the item is dropped right after, and the dentry is only unhashed by d_delete() once ->rmdir() has returned. configfs_symlink() resolves its target holding no lock on it, so get_target() can land in that window: BUG: KASAN: slab-use-after-free in config_item_get+0x26/0x90 get_target fs/configfs/symlink.c:128 [inline] configfs_symlink+0x4ab/0x1030 fs/configfs/symlink.c:185 Unhash in configfs_remove_dir(), while the item is still guaranteed to be there. A reference obtained just before that stays harmless, as create_link() rechecks CONFIGFS_USET_DROPPING, already set by configfs_detach_prep(). Both configfs_unregister_subsystem() paths d_drop() after detaching, so this only makes rmdir match them. Reported-by: syzbot+6b16e3d085833cbf3e25@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=6b16e3d085833cbf3e25 Fixes: 7063fbf22611 ("[PATCH] configfs: User-driven configuration filesystem") Cc: stable@vger.kernel.org Signed-off-by: Vasileios Almpanis Tested-by: Breno Leitao Reviewed-by: Breno Leitao Link: https://patch.msgid.link/20260730093435.195441-3-vasilisalmpanis@gmail.com Signed-off-by: Breno Leitao --- fs/configfs/dir.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index 3c88f13f1ca2..eda80c2a2d38 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -416,6 +416,15 @@ static void configfs_remove_dir(struct dentry *d) if (d_really_is_positive(d)) { if (unlikely(simple_rmdir(d_inode(parent), d))) pr_warn("remove_dir (%pd): attributes remain", d); + else + /* + * configfs_get_config_item() takes a hashed dentry as + * proof that ->s_element is still alive. Our caller + * is about to drop the last reference to the item and + * the VFS will not unhash until after we return, so + * unhash it here. + */ + d_drop(d); } pr_debug(" o %pd removing done (%d)\n", d, d_count(d)); From 776924b2d9c451fc9dcc40673d17ff255bbc0fef Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Mon, 24 Aug 2026 18:47:58 +0200 Subject: [PATCH 0869/1198] btrfs: set space_info before adding new free space in btrfs_make_block_group() btrfs_make_block_group() calls btrfs_add_new_free_space() before assigning cache->space_info. On a zoned filesystem that ends up in __btrfs_add_free_space_zoned(), which dereferences block_group->space_info and thus hits a NULL pointer dereference when a non-initial free space range is added (e.g. during relocation). Assign cache->space_info before the btrfs_add_new_free_space() call. Reviewed-by: Boris Burkov Signed-off-by: Johannes Thumshirn Signed-off-by: David Sterba --- fs/btrfs/block-group.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 830460a40e86..ee182369254c 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -3074,6 +3074,18 @@ struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *tran return ERR_PTR(ret); } + /* + * Ensure the corresponding space_info object is created and + * assigned to our block group. We want our bg to be added to the rbtree + * with its ->space_info set. + * + * On a zoned filesystem btrfs_add_new_free_space() ends up in + * __btrfs_add_free_space_zoned(), which dereferences + * block_group->space_info, so it has to be set beforehand. + */ + cache->space_info = space_info; + ASSERT(cache->space_info); + ret = btrfs_add_new_free_space(cache, chunk_offset, chunk_offset + size, NULL); btrfs_free_excluded_extents(cache); if (ret) { @@ -3081,14 +3093,6 @@ struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *tran return ERR_PTR(ret); } - /* - * Ensure the corresponding space_info object is created and - * assigned to our block group. We want our bg to be added to the rbtree - * with its ->space_info set. - */ - cache->space_info = space_info; - ASSERT(cache->space_info); - ret = btrfs_add_block_group_cache(cache); if (ret) { btrfs_remove_free_space_cache(cache); From 36f9aafa46f5b9fecf92d9218c5574f1ef6b4907 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 3 Sep 2026 13:15:46 +0100 Subject: [PATCH 0870/1198] btrfs: fix unnecessary transaction commit fallback from btrfs_log_all_parents() When btrfs_log_all_parents() returns without doing any work (because all parent directories were already logged), it returns 1, which is propagated up the fsync call chain up to btrfs_log_dentry_safe(), and that causes btrfs_sync_file() to trigger am unnecessary transaction commit. This all happens because the call to btrfs_search_slot() in btrfs_log_all_parents() always returns 1, as there can not be any inode ref keys with an offset 0 (an invalid inode number), so if the while loop below it does not do any work because all parent directories were already logged, the 'ret' variable remains with a value of 1, which is then returned up the call chain to btrfs_sync_file(). Fix this by setting 'ret' to 0 after the call to btrfs_search_slot(). Fixes: 0f24ea456ae1 ("btrfs: tracepoints: add trace event for btrfs_log_all_parents()") Reviewed-by: Boris Burkov Reviewed-by: Qu Wenruo Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/tree-log.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 7ba7b6098aa5..a00094604e54 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -7286,6 +7286,22 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans, ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto out; + /* + * There can't be an inode ref key with offset 0 because inode numbers + * start at BTRFS_FIRST_FREE_OBJECTID. + */ + if (WARN_ON_ONCE(ret == 0)) { + btrfs_err(trans->fs_info, + "found inode ref key with offset 0 for root %llu inode %llu", + btrfs_root_id(root), ino); + ret = BTRFS_LOG_FORCE_COMMIT; + goto out; + } + /* + * Set to 0 so that in case we don't do any work below, we won't return + * 1 and trigger an unnecessary transaction commit. + */ + ret = 0; while (true) { struct extent_buffer *leaf = path->nodes[0]; From 2a4513ab53361360329b7ad1496d666b7433289e Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 3 Sep 2026 16:16:32 +0100 Subject: [PATCH 0871/1198] btrfs: tree-checker: validate key offset for inode ref keys For a subvolume tree, the offset of an inode ref key corresponds to an inode number, and that must always be within the range: [ BTRFS_FIRST_FREE_OBJECTID (256), BTRFS_LAST_FREE_OBJECTID (-256) ] Add a check for that in check_inode_ref(). Sashiko complained about such check missing in another unrelated patch. Reviewed-by: Boris Burkov Reviewed-by: Qu Wenruo Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/tree-checker.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 0ce91396b517..a4447c57c2a4 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1909,6 +1909,16 @@ static int check_inode_ref(struct extent_buffer *leaf, return -EUCLEAN; } + if (unlikely(btrfs_is_fstree(btrfs_header_owner(leaf)) && + (key->offset < BTRFS_FIRST_FREE_OBJECTID || + key->offset > BTRFS_LAST_FREE_OBJECTID))) { + inode_ref_err(leaf, slot, + "invalid offset for ref key, have %llu expect [%llu, %lld]", + key->offset, BTRFS_FIRST_FREE_OBJECTID, + BTRFS_LAST_FREE_OBJECTID); + return -EUCLEAN; + } + ptr = btrfs_item_ptr_offset(leaf, slot); end = ptr + btrfs_item_size(leaf, slot); while (ptr < end) { From b18f0f8334e6d7e4ed4baf1f404658537659cb57 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 3 Sep 2026 16:24:43 +0100 Subject: [PATCH 0872/1198] btrfs: tree-checker: validate parent field for inode extref items For a subvolume tree, the parent field of an inode extref item corresponds to an inode number, and that must always be within the range: [ BTRFS_FIRST_FREE_OBJECTID (256), BTRFS_LAST_FREE_OBJECTID (-256) ] Add a check for that in check_inode_extref(). Reviewed-by: Boris Burkov Reviewed-by: Qu Wenruo Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/tree-checker.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index a4447c57c2a4..83f7b0aaab21 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1962,12 +1962,14 @@ static int check_inode_extref(struct extent_buffer *leaf, { unsigned long ptr = btrfs_item_ptr_offset(leaf, slot); unsigned long end = ptr + btrfs_item_size(leaf, slot); + const bool is_fstree = btrfs_is_fstree(btrfs_header_owner(leaf)); if (unlikely(!check_prev_ino(leaf, key, slot, prev_key))) return -EUCLEAN; while (ptr < end) { struct btrfs_inode_extref *extref = (struct btrfs_inode_extref *)ptr; + u64 parent; u16 namelen; if (unlikely(ptr + sizeof(*extref) > end)) { @@ -1977,6 +1979,16 @@ static int check_inode_extref(struct extent_buffer *leaf, return -EUCLEAN; } + parent = btrfs_inode_extref_parent(leaf, extref); + if (unlikely(is_fstree && (parent < BTRFS_FIRST_FREE_OBJECTID || + parent > BTRFS_LAST_FREE_OBJECTID))) { + inode_ref_err(leaf, slot, + "invalid parent for extref key, have %llu expect [%llu, %lld]", + parent, BTRFS_FIRST_FREE_OBJECTID, + BTRFS_LAST_FREE_OBJECTID); + return -EUCLEAN; + } + namelen = btrfs_inode_extref_name_len(leaf, extref); if (unlikely(ptr + sizeof(*extref) + namelen > end)) { inode_ref_err(leaf, slot, From 09f1294ee2abee7fe1c2d600671498b7642e0fe0 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 3 Sep 2026 17:24:16 +0100 Subject: [PATCH 0873/1198] btrfs: tree-checker: validate name length for extref items We are validating the name length of inode ref items, but we miss the same validation for extref items. Sashiko pointed this out while reviewing other patch. Add the missing validation, similar to what was done in commit 3dc22abc21f5 ("btrfs: tree-checker: validate INODE_REF's namelen"). Reviewed-by: Boris Burkov Reviewed-by: Qu Wenruo Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/tree-checker.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 83f7b0aaab21..ab5abbb475e2 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1990,6 +1990,13 @@ static int check_inode_extref(struct extent_buffer *leaf, } namelen = btrfs_inode_extref_name_len(leaf, extref); + if (unlikely(namelen == 0 || namelen > BTRFS_NAME_LEN)) { + inode_ref_err(leaf, slot, + "invalid inode extref name length, has %u expect [1, %u]", + namelen, BTRFS_NAME_LEN); + return -EUCLEAN; + } + if (unlikely(ptr + sizeof(*extref) + namelen > end)) { inode_ref_err(leaf, slot, "inode extref overflow, ptr %lu end %lu namelen %u", From 387d744fa7e499d2c3748a4e60e02ebb24e7fb16 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 25 Aug 2026 03:36:03 +0200 Subject: [PATCH 0874/1198] netfilter: nfnetlink_log: cope with concurrent instance destruction Instances are refcounted. However, only memory release happens on the 1 -> 0 transition; the unlink from hashes can occur with any refcount. Uncooperative userspace can force a situation where a queue is pending for destruction from netlink event while a different socket with same portid processes an UNBIND request. With right timing, this will unhash the instance again: Oops: general protection fault, [..] Call Trace: nfulnl_recv_config+0x31a/0xd50 nfnetlink_rcv_msg+0x7c2/0xeb0 Fixes: 0597f2680d66 ("[NETFILTER]: Add new "nfnetlink_log" userspace packet logging facility") Reported-by: Eulgyu Kim Reported-by: Jaeyoung Chung Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink_log.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 9d7fec570abe..d923f2cb1398 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -228,13 +228,18 @@ static void __nfulnl_flush(struct nfulnl_instance *inst); static void __instance_destroy(struct nfulnl_instance *inst) { + spin_lock(&inst->lock); + if (inst->copy_mode == NFULNL_COPY_DISABLED) { + /* attempt to UNBIND a queue already pending + * destruction via netlink close event. Ignore. + */ + spin_unlock(&inst->lock); + return; + } + /* first pull it out of the global list */ hlist_del_rcu(&inst->hlist); - /* then flush all pending packets from skb */ - - spin_lock(&inst->lock); - /* lockless readers wont be able to use us */ inst->copy_mode = NFULNL_COPY_DISABLED; From 0bd7ed1a3263c26cf38fffc035b539a70d88667b Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 25 Aug 2026 12:28:36 +0200 Subject: [PATCH 0875/1198] netfilter: arp_tables: remove the 32bit compat interface This feature is required to use 32bit arptables binary on 64bit kernels. It's already off in many distributions including Debian and Fedora for many years. Zap arptables first, it's the most esoteric of the 4 flavors. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_arp/arp_tables.h | 19 - net/ipv4/netfilter/arp_tables.c | 472 +---------------------- net/netfilter/Kconfig | 2 +- 3 files changed, 4 insertions(+), 489 deletions(-) diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index 05631a25e622..8b8d472eff34 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -56,23 +56,4 @@ void arpt_unregister_table(struct net *net, const char *name); extern unsigned int arpt_do_table(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); -#ifdef CONFIG_NETFILTER_XTABLES_COMPAT -#include - -struct compat_arpt_entry { - struct arpt_arp arp; - __u16 target_offset; - __u16 next_offset; - compat_uint_t comefrom; - struct compat_xt_counters counters; - unsigned char elems[]; -}; - -static inline struct xt_entry_target * -compat_arpt_get_target(struct compat_arpt_entry *e) -{ - return (void *)e + e->target_offset; -} - -#endif /* CONFIG_COMPAT */ #endif /* _ARPTABLES_H */ diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index a87e07e80d0d..db307fa49f3f 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -23,7 +23,6 @@ #include #include #include -#include #include #include @@ -724,80 +723,6 @@ static int copy_entries_to_user(unsigned int total_size, return ret; } -#ifdef CONFIG_NETFILTER_XTABLES_COMPAT -static void compat_standard_from_user(void *dst, const void *src) -{ - int v = *(compat_int_t *)src; - - if (v > 0) - v += xt_compat_calc_jump(NFPROTO_ARP, v); - memcpy(dst, &v, sizeof(v)); -} - -static int compat_standard_to_user(void __user *dst, const void *src) -{ - compat_int_t cv = *(int *)src; - - if (cv > 0) - cv -= xt_compat_calc_jump(NFPROTO_ARP, cv); - return copy_to_user(dst, &cv, sizeof(cv)) ? -EFAULT : 0; -} - -static int compat_calc_entry(const struct arpt_entry *e, - const struct xt_table_info *info, - const void *base, struct xt_table_info *newinfo) -{ - const struct xt_entry_target *t; - unsigned int entry_offset; - int off, i, ret; - - off = sizeof(struct arpt_entry) - sizeof(struct compat_arpt_entry); - entry_offset = (void *)e - base; - - t = arpt_get_target_c(e); - off += xt_compat_target_offset(t->u.kernel.target); - newinfo->size -= off; - ret = xt_compat_add_offset(NFPROTO_ARP, entry_offset, off); - if (ret) - return ret; - - for (i = 0; i < NF_ARP_NUMHOOKS; i++) { - if (info->hook_entry[i] && - (e < (struct arpt_entry *)(base + info->hook_entry[i]))) - newinfo->hook_entry[i] -= off; - if (info->underflow[i] && - (e < (struct arpt_entry *)(base + info->underflow[i]))) - newinfo->underflow[i] -= off; - } - return 0; -} - -static int compat_table_info(const struct xt_table_info *info, - struct xt_table_info *newinfo) -{ - struct arpt_entry *iter; - const void *loc_cpu_entry; - int ret; - - if (!newinfo || !info) - return -EINVAL; - - /* we dont care about newinfo->entries */ - memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); - newinfo->initial_entries = 0; - loc_cpu_entry = info->entries; - ret = xt_compat_init_offsets(NFPROTO_ARP, info->number); - if (ret) - return ret; - xt_entry_foreach(iter, loc_cpu_entry, info->size) { - ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo); - if (ret != 0) - return ret; - } - return 0; -} -#endif - static int get_info(struct net *net, void __user *user, const int *len) { char name[XT_TABLE_MAXNAMELEN]; @@ -811,23 +736,11 @@ static int get_info(struct net *net, void __user *user, const int *len) return -EFAULT; name[XT_TABLE_MAXNAMELEN-1] = '\0'; -#ifdef CONFIG_NETFILTER_XTABLES_COMPAT - if (in_compat_syscall()) - xt_compat_lock(NFPROTO_ARP); -#endif t = xt_request_find_table_lock(net, NFPROTO_ARP, name); if (!IS_ERR(t)) { struct arpt_getinfo info; const struct xt_table_info *private = t->private; -#ifdef CONFIG_NETFILTER_XTABLES_COMPAT - struct xt_table_info tmp; - if (in_compat_syscall()) { - ret = compat_table_info(private, &tmp); - xt_compat_flush_offsets(NFPROTO_ARP); - private = &tmp; - } -#endif memset(&info, 0, sizeof(info)); info.valid_hooks = t->valid_hooks; memcpy(info.hook_entry, private->hook_entry, @@ -846,10 +759,7 @@ static int get_info(struct net *net, void __user *user, const int *len) module_put(t->me); } else ret = PTR_ERR(t); -#ifdef CONFIG_NETFILTER_XTABLES_COMPAT - if (in_compat_syscall()) - xt_compat_unlock(NFPROTO_ARP); -#endif + return ret; } @@ -1059,367 +969,6 @@ static int do_add_counters(struct net *net, sockptr_t arg, unsigned int len) return ret; } -#ifdef CONFIG_NETFILTER_XTABLES_COMPAT -struct compat_arpt_replace { - char name[XT_TABLE_MAXNAMELEN]; - u32 valid_hooks; - u32 num_entries; - u32 size; - u32 hook_entry[NF_ARP_NUMHOOKS]; - u32 underflow[NF_ARP_NUMHOOKS]; - u32 num_counters; - compat_uptr_t counters; - struct compat_arpt_entry entries[]; -}; - -static inline void compat_release_entry(struct compat_arpt_entry *e) -{ - struct xt_entry_target *t; - - t = compat_arpt_get_target(e); - module_put(t->u.kernel.target->me); -} - -static int -check_compat_entry_size_and_hooks(struct compat_arpt_entry *e, - struct xt_table_info *newinfo, - unsigned int *size, - const unsigned char *base, - const unsigned char *limit) -{ - struct xt_entry_target *t; - struct xt_target *target; - unsigned int entry_offset; - int ret, off; - - if ((unsigned long)e % __alignof__(struct compat_arpt_entry) != 0 || - (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit || - (unsigned char *)e + e->next_offset > limit) - return -EINVAL; - - if (e->next_offset < sizeof(struct compat_arpt_entry) + - sizeof(struct compat_xt_entry_target)) - return -EINVAL; - - if (!arp_checkentry(&e->arp)) - return -EINVAL; - - ret = xt_compat_check_entry_offsets(e, e->elems, e->target_offset, - e->next_offset); - if (ret) - return ret; - - off = sizeof(struct arpt_entry) - sizeof(struct compat_arpt_entry); - entry_offset = (void *)e - (void *)base; - - t = compat_arpt_get_target(e); - target = xt_request_find_target(NFPROTO_ARP, t->u.user.name, - t->u.user.revision); - if (IS_ERR(target)) { - ret = PTR_ERR(target); - goto out; - } - t->u.kernel.target = target; - - off += xt_compat_target_offset(target); - *size += off; - ret = xt_compat_add_offset(NFPROTO_ARP, entry_offset, off); - if (ret) - goto release_target; - - return 0; - -release_target: - module_put(t->u.kernel.target->me); -out: - return ret; -} - -static void -compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr, - unsigned int *size, - struct xt_table_info *newinfo, unsigned char *base) -{ - struct xt_entry_target *t; - struct arpt_entry *de; - unsigned int origsize; - int h; - - origsize = *size; - de = *dstptr; - memcpy(de, e, sizeof(struct arpt_entry)); - memcpy(&de->counters, &e->counters, sizeof(e->counters)); - - *dstptr += sizeof(struct arpt_entry); - *size += sizeof(struct arpt_entry) - sizeof(struct compat_arpt_entry); - - de->target_offset = e->target_offset - (origsize - *size); - t = compat_arpt_get_target(e); - xt_compat_target_from_user(t, dstptr, size); - - de->next_offset = e->next_offset - (origsize - *size); - for (h = 0; h < NF_ARP_NUMHOOKS; h++) { - if ((unsigned char *)de - base < newinfo->hook_entry[h]) - newinfo->hook_entry[h] -= origsize - *size; - if ((unsigned char *)de - base < newinfo->underflow[h]) - newinfo->underflow[h] -= origsize - *size; - } -} - -static int translate_compat_table(struct net *net, - struct xt_table_info **pinfo, - void **pentry0, - const struct compat_arpt_replace *compatr) -{ - unsigned int i, j; - struct xt_table_info *newinfo, *info; - void *pos, *entry0, *entry1; - struct compat_arpt_entry *iter0; - struct arpt_replace repl; - unsigned int size; - int ret; - - info = *pinfo; - entry0 = *pentry0; - size = compatr->size; - info->number = compatr->num_entries; - - j = 0; - xt_compat_lock(NFPROTO_ARP); - ret = xt_compat_init_offsets(NFPROTO_ARP, compatr->num_entries); - if (ret) - goto out_unlock; - /* Walk through entries, checking offsets. */ - xt_entry_foreach(iter0, entry0, compatr->size) { - ret = check_compat_entry_size_and_hooks(iter0, info, &size, - entry0, - entry0 + compatr->size); - if (ret != 0) - goto out_unlock; - ++j; - } - - ret = -EINVAL; - if (j != compatr->num_entries) - goto out_unlock; - - ret = -ENOMEM; - newinfo = xt_alloc_table_info(size); - if (!newinfo) - goto out_unlock; - - memset(newinfo->entries, 0, size); - - newinfo->number = compatr->num_entries; - for (i = 0; i < NF_ARP_NUMHOOKS; i++) { - newinfo->hook_entry[i] = compatr->hook_entry[i]; - newinfo->underflow[i] = compatr->underflow[i]; - } - entry1 = newinfo->entries; - pos = entry1; - size = compatr->size; - xt_entry_foreach(iter0, entry0, compatr->size) - compat_copy_entry_from_user(iter0, &pos, &size, - newinfo, entry1); - - /* all module references in entry0 are now gone */ - - xt_compat_flush_offsets(NFPROTO_ARP); - xt_compat_unlock(NFPROTO_ARP); - - memcpy(&repl, compatr, sizeof(*compatr)); - - for (i = 0; i < NF_ARP_NUMHOOKS; i++) { - repl.hook_entry[i] = newinfo->hook_entry[i]; - repl.underflow[i] = newinfo->underflow[i]; - } - - repl.num_counters = 0; - repl.counters = NULL; - repl.size = newinfo->size; - ret = translate_table(net, newinfo, entry1, &repl); - if (ret) - goto free_newinfo; - - *pinfo = newinfo; - *pentry0 = entry1; - xt_free_table_info(info); - return 0; - -free_newinfo: - xt_free_table_info(newinfo); - return ret; -out_unlock: - xt_compat_flush_offsets(NFPROTO_ARP); - xt_compat_unlock(NFPROTO_ARP); - xt_entry_foreach(iter0, entry0, compatr->size) { - if (j-- == 0) - break; - compat_release_entry(iter0); - } - return ret; -} - -static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) -{ - int ret; - struct compat_arpt_replace tmp; - struct xt_table_info *newinfo; - void *loc_cpu_entry; - struct arpt_entry *iter; - - if (len < sizeof(tmp)) - return -EINVAL; - if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) - return -EFAULT; - - /* overflow check */ - if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) - return -ENOMEM; - if (tmp.num_counters == 0) - return -EINVAL; - if ((u64)len < (u64)tmp.size + sizeof(tmp)) - return -EINVAL; - - tmp.name[sizeof(tmp.name)-1] = 0; - - newinfo = xt_alloc_table_info(tmp.size); - if (!newinfo) - return -ENOMEM; - - loc_cpu_entry = newinfo->entries; - if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), - tmp.size) != 0) { - ret = -EFAULT; - goto free_newinfo; - } - - ret = translate_compat_table(net, &newinfo, &loc_cpu_entry, &tmp); - if (ret != 0) - goto free_newinfo; - - ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo, - tmp.num_counters, compat_ptr(tmp.counters)); - if (ret) - goto free_newinfo_untrans; - return 0; - - free_newinfo_untrans: - xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) - cleanup_entry(iter, net); - free_newinfo: - xt_free_table_info(newinfo); - return ret; -} - -static int compat_copy_entry_to_user(struct arpt_entry *e, void __user **dstptr, - compat_uint_t *size, - struct xt_counters *counters, - unsigned int i) -{ - struct xt_entry_target *t; - struct compat_arpt_entry __user *ce; - u_int16_t target_offset, next_offset; - compat_uint_t origsize; - int ret; - - origsize = *size; - ce = *dstptr; - if (copy_to_user(ce, e, offsetof(struct compat_arpt_entry, counters)) || - copy_to_user(&ce->counters, &counters[i], sizeof(counters[i]))) - return -EFAULT; - - *dstptr += sizeof(struct compat_arpt_entry); - *size -= sizeof(struct arpt_entry) - sizeof(struct compat_arpt_entry); - - target_offset = e->target_offset - (origsize - *size); - - t = arpt_get_target(e); - ret = xt_compat_target_to_user(t, dstptr, size); - if (ret) - return ret; - next_offset = e->next_offset - (origsize - *size); - if (put_user(target_offset, &ce->target_offset) != 0 || - put_user(next_offset, &ce->next_offset) != 0) - return -EFAULT; - return 0; -} - -static int compat_copy_entries_to_user(unsigned int total_size, - struct xt_table *table, - void __user *userptr) -{ - struct xt_counters *counters; - const struct xt_table_info *private = table->private; - void __user *pos; - unsigned int size; - int ret = 0; - unsigned int i = 0; - struct arpt_entry *iter; - - counters = alloc_counters(table); - if (IS_ERR(counters)) - return PTR_ERR(counters); - - pos = userptr; - size = total_size; - xt_entry_foreach(iter, private->entries, total_size) { - ret = compat_copy_entry_to_user(iter, &pos, - &size, counters, i++); - if (ret != 0) - break; - } - vfree(counters); - return ret; -} - -struct compat_arpt_get_entries { - char name[XT_TABLE_MAXNAMELEN]; - compat_uint_t size; - struct compat_arpt_entry entrytable[]; -}; - -static int compat_get_entries(struct net *net, - struct compat_arpt_get_entries __user *uptr, - int *len) -{ - int ret; - struct compat_arpt_get_entries get; - struct xt_table *t; - - if (*len < sizeof(get)) - return -EINVAL; - if (copy_from_user(&get, uptr, sizeof(get)) != 0) - return -EFAULT; - if (*len != sizeof(struct compat_arpt_get_entries) + get.size) - return -EINVAL; - - get.name[sizeof(get.name) - 1] = '\0'; - - xt_compat_lock(NFPROTO_ARP); - t = xt_find_table_lock(net, NFPROTO_ARP, get.name); - if (!IS_ERR(t)) { - const struct xt_table_info *private = t->private; - struct xt_table_info info; - - ret = compat_table_info(private, &info); - if (!ret && get.size == info.size) { - ret = compat_copy_entries_to_user(private->size, - t, uptr->entrytable); - } else if (!ret) - ret = -EAGAIN; - - xt_compat_flush_offsets(NFPROTO_ARP); - module_put(t->me); - xt_table_unlock(t); - } else - ret = PTR_ERR(t); - - xt_compat_unlock(NFPROTO_ARP); - return ret; -} -#endif - static int do_arpt_set_ctl(struct sock *sk, int cmd, sockptr_t arg, unsigned int len) { @@ -1432,12 +981,7 @@ static int do_arpt_set_ctl(struct sock *sk, int cmd, sockptr_t arg, switch (cmd) { case ARPT_SO_SET_REPLACE: -#ifdef CONFIG_NETFILTER_XTABLES_COMPAT - if (in_compat_syscall()) - ret = compat_do_replace(sock_net(sk), arg, len); - else -#endif - ret = do_replace(sock_net(sk), arg, len); + ret = do_replace(sock_net(sk), arg, len); break; case ARPT_SO_SET_ADD_COUNTERS: @@ -1466,12 +1010,7 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len break; case ARPT_SO_GET_ENTRIES: -#ifdef CONFIG_NETFILTER_XTABLES_COMPAT - if (in_compat_syscall()) - ret = compat_get_entries(sock_net(sk), user, len); - else -#endif - ret = get_entries(sock_net(sk), user, len); + ret = get_entries(sock_net(sk), user, len); break; case ARPT_SO_GET_REVISION_TARGET: { @@ -1568,11 +1107,6 @@ static struct xt_target arpt_builtin_tg[] __read_mostly = { .name = XT_STANDARD_TARGET, .targetsize = sizeof(int), .family = NFPROTO_ARP, -#ifdef CONFIG_NETFILTER_XTABLES_COMPAT - .compatsize = sizeof(compat_int_t), - .compat_from_user = compat_standard_from_user, - .compat_to_user = compat_standard_to_user, -#endif }, { .name = XT_ERROR_TARGET, diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 4c04cd8d40a2..09874c26fd13 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -739,7 +739,7 @@ config NETFILTER_XTABLES_COMPAT bool "Netfilter Xtables 32bit support" depends on COMPAT help - This option provides a translation layer to run 32bit arp,ip(6),ebtables + This option provides a translation layer to run 32bit ip(6),ebtables binaries on 64bit kernels. If unsure, say N. From da4afc5a956d407443988e97a4d4ca14c2e999c7 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 25 Aug 2026 15:11:24 +0200 Subject: [PATCH 0876/1198] netfilter: ip6_tables: set F_PROTO when proto value is nonzero The ip6tables traverser doesn't search the extension header chain unless userspace did set the IP6T_F_PROTO flag. This also means that userspace that sets the e->ipv6.proto flag can bypass the protocol check for the rule by not setting this flag. That in turn means that all ip6_tables modules and targets that want to reject rules without '-p' flag MUST also check for that flag. Not all do, likely because they got copied from iptables which lacks this flag (no extension headers). Instead of fixing up all the relevant targets, emulate ip6tables behaviour in the kernel (like nft_compat.c) and set the flag if the protocol is set. Reported-by: Zhiling Zou Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/ipv6/netfilter/ip6_tables.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index f42fb96ef64b..313c4aac377a 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -647,6 +647,11 @@ check_entry_size_and_hooks(struct ip6t_entry *e, /* Clear counters and comefrom */ e->counters = ((struct xt_counters) { 0, 0 }); e->comefrom = 0; + + /* set F_PROTO, else ip6_packet_match won't do the right thing. */ + if (e->ipv6.proto) + e->ipv6.flags |= IP6T_F_PROTO; + return 0; } From 7a099b347fef536a84068076e2d384f044e5cfc5 Mon Sep 17 00:00:00 2001 From: Ilya Maximets Date: Tue, 25 Aug 2026 17:27:24 +0200 Subject: [PATCH 0877/1198] netfilter: report NLM_F_DUMP_FILTERED when all is filtered out NLM_F_DUMP_FILTERED is only set on data elements in the conntrack dump. But when everything is filtered out it is confusing for the user space, since the flag is not reported anymore and it looks like the table was empty, which may or may not be the case. 'answer_flags' were introduced precisely for this use case, and the conntrack dump should set the flag in there in case the filtering was applied. This is important, for example, to be able to tell if the filters are supported or not by the kernel without modifying the kernel state. With the proper reporting of NLM_F_DUMP_FILTERED on NLMSG_DONE, an application in user space can just try and dump with an arbitrary filter without worrying that there could be no matching entry. The reported flag will signal that the filtering was applied and therefore supported. Fixes: cb8aa9a3affb ("netfilter: ctnetlink: add kernel side filtering for dump") Cc: stable@vger.kernel.org Signed-off-by: Ilya Maximets Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_netlink.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 9b4e29557ec3..579ada063b1b 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1077,6 +1077,8 @@ static int ctnetlink_start(struct netlink_callback *cb) } cb->data = filter; + if (filter) + cb->answer_flags = NLM_F_DUMP_FILTERED; return 0; } From f3e6ef13e24c9f26dca0d35de57fcdf04f78e378 Mon Sep 17 00:00:00 2001 From: Donggeun Yoo Date: Fri, 4 Sep 2026 19:56:24 +0900 Subject: [PATCH 0878/1198] regulator: pf1550: fix which regulator is notified The interrupt handler distinguishes the rail that reported the fault, but the body ignores it. Every SW interrupt walks the regulator array looking for the name "SW3" and every LDO interrupt looks for "LDO3", so an over-current on SW1 is reported to the consumers of SW3 while the consumers of SW1 hear nothing. The lookup itself is unreliable as well. rdev_get_name() returns the device tree regulator-name property whenever the board supplies one, and only falls back to the name in the driver descriptor when it does not. The binding example for this device sets regulator-name to "sw3" and "ldo3", which strcmp() does not match against the upper case literals used here, so a board that follows the documentation gets no over-current notification at all. A board that names its rails after the schematic does not match either. No other driver in the tree selects a notification target this way. Replace the name lookup with rdev_get_id(), which returns the descriptor id set by the driver and cannot be overridden from the device tree, and take both the id and the event from a table indexed by the interrupt. The die temperature interrupts keep notifying every regulator since they report a chip wide condition. Fixes: 7320d41c29bb ("regulator: pf1550: Add support for regulator") Signed-off-by: Donggeun Yoo Link: https://patch.msgid.link/20260904105624.48577-1-donggeunyoo.kernel@gmail.com Signed-off-by: Mark Brown --- drivers/regulator/pf1550-regulator.c | 82 ++++++++++++++-------------- 1 file changed, 40 insertions(+), 42 deletions(-) diff --git a/drivers/regulator/pf1550-regulator.c b/drivers/regulator/pf1550-regulator.c index 610eac9bb9cb..ceee553a84b2 100644 --- a/drivers/regulator/pf1550-regulator.c +++ b/drivers/regulator/pf1550-regulator.c @@ -283,63 +283,61 @@ static struct pf1550_desc pf1550_regulators[] = { PF_LDO1(PF1550, "ldo3", LDO3, 0x1f, pf1550_ldo13_volts), }; +/* + * The _LS interrupts indicate an over-current event. The _HS + * interrupts, which are more accurate and can detect catastrophic + * faults, issue an error event. The current limit FAULT interrupt is + * similar to the _HS. + */ +static const struct pf1550_regulator_irq { + unsigned int event; + u8 id; +} pf1550_regulator_irqs[] = { + [PF1550_PMIC_IRQ_SW1_LS] = { REGULATOR_EVENT_OVER_CURRENT_WARN, PF1550_SW1 }, + [PF1550_PMIC_IRQ_SW2_LS] = { REGULATOR_EVENT_OVER_CURRENT_WARN, PF1550_SW2 }, + [PF1550_PMIC_IRQ_SW3_LS] = { REGULATOR_EVENT_OVER_CURRENT_WARN, PF1550_SW3 }, + [PF1550_PMIC_IRQ_SW1_HS] = { REGULATOR_EVENT_OVER_CURRENT, PF1550_SW1 }, + [PF1550_PMIC_IRQ_SW2_HS] = { REGULATOR_EVENT_OVER_CURRENT, PF1550_SW2 }, + [PF1550_PMIC_IRQ_SW3_HS] = { REGULATOR_EVENT_OVER_CURRENT, PF1550_SW3 }, + [PF1550_PMIC_IRQ_LDO1_FAULT] = { REGULATOR_EVENT_OVER_CURRENT, PF1550_LDO1 }, + [PF1550_PMIC_IRQ_LDO2_FAULT] = { REGULATOR_EVENT_OVER_CURRENT, PF1550_LDO2 }, + [PF1550_PMIC_IRQ_LDO3_FAULT] = { REGULATOR_EVENT_OVER_CURRENT, PF1550_LDO3 }, +}; + static irqreturn_t pf1550_regulator_irq_handler(int irq, void *data) { + const struct pf1550_regulator_irq *map; struct pf1550_regulator_info *info = data; struct device *dev = info->dev; struct platform_device *pdev = to_platform_device(dev); int i, irq_type = -1; - unsigned int event; for (i = 0; i < PF1550_REGULATOR_IRQ_NR; i++) if (irq == platform_get_irq(pdev, i)) irq_type = i; - switch (irq_type) { - /* The _LS interrupts indicate over-current event. The _HS interrupts - * which are more accurate and can detect catastrophic faults, issue - * an error event. The current limit FAULT interrupt is similar to the - * _HS' - */ - case PF1550_PMIC_IRQ_SW1_LS: - case PF1550_PMIC_IRQ_SW2_LS: - case PF1550_PMIC_IRQ_SW3_LS: - event = REGULATOR_EVENT_OVER_CURRENT_WARN; - for (i = 0; i < PF1550_MAX_REGULATOR; i++) - if (!strcmp(rdev_get_name(info->rdevs[i]), "SW3")) - regulator_notifier_call_chain(info->rdevs[i], - event, NULL); - break; - case PF1550_PMIC_IRQ_SW1_HS: - case PF1550_PMIC_IRQ_SW2_HS: - case PF1550_PMIC_IRQ_SW3_HS: - event = REGULATOR_EVENT_OVER_CURRENT; - for (i = 0; i < PF1550_MAX_REGULATOR; i++) - if (!strcmp(rdev_get_name(info->rdevs[i]), "SW3")) - regulator_notifier_call_chain(info->rdevs[i], - event, NULL); - break; - case PF1550_PMIC_IRQ_LDO1_FAULT: - case PF1550_PMIC_IRQ_LDO2_FAULT: - case PF1550_PMIC_IRQ_LDO3_FAULT: - event = REGULATOR_EVENT_OVER_CURRENT; - for (i = 0; i < PF1550_MAX_REGULATOR; i++) - if (!strcmp(rdev_get_name(info->rdevs[i]), "LDO3")) - regulator_notifier_call_chain(info->rdevs[i], - event, NULL); - break; - case PF1550_PMIC_IRQ_TEMP_110: - case PF1550_PMIC_IRQ_TEMP_125: - event = REGULATOR_EVENT_OVER_TEMP; + /* The die temperature concerns every rail. */ + if (irq_type == PF1550_PMIC_IRQ_TEMP_110 || + irq_type == PF1550_PMIC_IRQ_TEMP_125) { for (i = 0; i < PF1550_MAX_REGULATOR; i++) regulator_notifier_call_chain(info->rdevs[i], - event, NULL); - break; - default: - dev_err(dev, "regulator interrupt: irq %d occurred\n", - irq_type); + REGULATOR_EVENT_OVER_TEMP, + NULL); + return IRQ_HANDLED; } + if (irq_type < 0 || irq_type >= (int)ARRAY_SIZE(pf1550_regulator_irqs)) { + dev_err(dev, "regulator interrupt: irq %d occurred\n", irq_type); + return IRQ_HANDLED; + } + + map = &pf1550_regulator_irqs[irq_type]; + + for (i = 0; i < PF1550_MAX_REGULATOR; i++) + if (rdev_get_id(info->rdevs[i]) == map->id) + regulator_notifier_call_chain(info->rdevs[i], + map->event, NULL); + return IRQ_HANDLED; } From 1017911fcc03584b6854b1b8f0aafeb25f5a8d25 Mon Sep 17 00:00:00 2001 From: Sascha Bischoff Date: Mon, 7 Sep 2026 16:49:50 +0000 Subject: [PATCH 0879/1198] irqchip/gic-v5: Preserve ICC_CR0_EL1 state In addition to EN, ICC_CR0_EL1 contains other fields, such as LINK and LINK_IDLE. The driver only needs to modify EN, and must preserve the values of all other fields when enabling or disabling the CPU interface. Define the missing LINK and LINK_IDLE fields, and use read-modify-write accesses to update EN without affecting the rest of ICC_CR0_EL1. Fixes: 7ec80fb3f025 ("irqchip/gic-v5: Add GICv5 PPI support") Reported-by: Sashiko Signed-off-by: Sascha Bischoff Signed-off-by: Thomas Gleixner Reviewed-by: Marc Zyngier Link: https://patch.msgid.link/20260907164945.714545-1-sascha.bischoff@arm.com Closes: https://lore.kernel.org/r/20260807121703.D4B7A1F00A3A@smtp.kernel.org --- arch/arm64/tools/sysreg | 4 +++- drivers/irqchip/irq-gic-v5.c | 6 ++++-- 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index 94bf065c8ac7..e2d37ee221b8 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -3761,7 +3761,9 @@ Sysreg ICC_CR0_EL1 3 1 12 0 1 Res0 63:39 Field 38 PID Field 37:32 IPPT -Res0 31:1 +Res0 31:3 +Field 2 LINK_IDLE +Field 1 LINK Field 0 EN EndSysreg diff --git a/drivers/irqchip/irq-gic-v5.c b/drivers/irqchip/irq-gic-v5.c index ac2d423b1723..5f2551cf077d 100644 --- a/drivers/irqchip/irq-gic-v5.c +++ b/drivers/irqchip/irq-gic-v5.c @@ -974,7 +974,8 @@ static void gicv5_cpu_disable_interrupts(void) { u64 cr0; - cr0 = FIELD_PREP(ICC_CR0_EL1_EN, 0); + cr0 = read_sysreg_s(SYS_ICC_CR0_EL1); + cr0 &= ~ICC_CR0_EL1_EN_MASK; write_sysreg_s(cr0, SYS_ICC_CR0_EL1); isb(); } @@ -991,7 +992,8 @@ static void gicv5_cpu_enable_interrupts(void) pcr = FIELD_PREP(ICC_PCR_EL1_PRIORITY, GICV5_IRQ_PRI_MI); write_sysreg_s(pcr, SYS_ICC_PCR_EL1); - cr0 = FIELD_PREP(ICC_CR0_EL1_EN, 1); + cr0 = read_sysreg_s(SYS_ICC_CR0_EL1); + cr0 |= ICC_CR0_EL1_EN_MASK; write_sysreg_s(cr0, SYS_ICC_CR0_EL1); } From 75d276e5bb68778b2916f98a2bc30f142ebadc64 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Mon, 17 Aug 2026 22:32:29 +0000 Subject: [PATCH 0880/1198] virtio_ring: fix stale descriptor flags after a failed packed add In a packed ring the AVAIL and USED bits sit in the descriptor itself, so writing them makes that descriptor available. Those bit combinations flip meaning on every round of the ring, tracked by a wrap counter, so invalidating or validating a descriptor means inverting both bits. Commit 1ce9e6055fa0 ("virtio_ring: introduce packed ring support") has virtqueue_add_packed() make every descriptor of a chain available as it maps the chain, and write the head last. The device consumes the ring in order and stops at a head that is not available yet, so it never reaches the rest. When vring_map_one_sg() fails partway, unmap_release unmaps the segments and restores avail_used_flags, but the descriptors it wrote to in the ring stay marked with AVAIL and USED bits. The head is now the only entry that keeps the device from consuming these stale entries. For example, the ring would look like this now. Z - pre-previous command A - previous command B - aborted command C - current command [A1 DONE] [A2 DONE] [B2] [B3] [Z1 DONE] When the driver now attempts to issue the C command, the next add starts at the same head as B. If C spans less descriptors than B, there is no end marker because AVAIL and USED bits were still in place. And that means the device will start interpreting these stale entries (B2/B3) as another command entry, which then blocks the queue. This effect typically happens in swiotlb configurations under memory pressure, because vring_map_one_sg() can then fail with larger I/O requests which then leads to command abortions. There are broadly 2 ways to avoid leaving those flags behind: 1) Defer those flags too until the chain is complete. 2) Rewrite those flags for the previous wrap counter. Implement the second option in both packed add paths. The first option traverses the chain a second time on every successful add. The second option invalidates all added descriptors when any add fails. With this patch applied, a packed virtqueue keeps completing requests after a failed add. Fixes: 1ce9e6055fa0 ("virtio_ring: introduce packed ring support") Fixes: f6a15d854986 ("virtio_ring: add in order support") Assisted-by: Kiro:claude-opus-5 checkpatch sparse Signed-off-by: Alexander Graf Signed-off-by: Michael S. Tsirkin Message-ID: <20260817223229.28954-1-graf@amazon.com> --- drivers/virtio/virtio_ring.c | 38 ++++++++++++++++++++++++++++++++---- 1 file changed, 34 insertions(+), 4 deletions(-) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 5c169fbb418a..db678f5a80e0 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -1670,7 +1670,7 @@ static inline int virtqueue_add_packed(struct vring_virtqueue *vq, struct scatterlist *sg; unsigned int i, n, c, descs_used, err_idx, len; __le16 head_flags, flags; - u16 head, id, prev, curr, avail_used_flags; + u16 head, id, prev, curr, avail_used_flags, unpub_flags; int err; START_USE(vq); @@ -1798,15 +1798,30 @@ static inline int virtqueue_add_packed(struct vring_virtqueue *vq, curr = vq->free_head; vq->packed.avail_used_flags = avail_used_flags; + unpub_flags = avail_used_flags ^ (1 << VRING_PACKED_DESC_F_AVAIL | + 1 << VRING_PACKED_DESC_F_USED); for (n = 0; n < total_sg; n++) { if (i == err_idx) break; + /* + * The mapping loop made every descriptor but the head + * available. Stamp the previous wrap counter's AVAIL and USED + * bits on those, so that a later and shorter chain at this head + * does not leave one of them available beyond its own last + * descriptor. Marking them used instead would hand + * is_used_desc_packed() a completion we never made. + */ + if (i != head) + desc[i].flags = cpu_to_le16(unpub_flags); vring_unmap_extra_packed(vq, &vq->packed.desc_extra[curr]); curr = vq->packed.desc_extra[curr].next; i++; - if (i >= vq->packed.vring.num) + if (i >= vq->packed.vring.num) { i = 0; + unpub_flags ^= 1 << VRING_PACKED_DESC_F_AVAIL | + 1 << VRING_PACKED_DESC_F_USED; + } } END_USE(vq); @@ -1828,7 +1843,7 @@ static inline int virtqueue_add_packed_in_order(struct vring_virtqueue *vq, struct scatterlist *sg; unsigned int i, n, sg_count, err_idx, total_in_len = 0; __le16 head_flags, flags; - u16 head, avail_used_flags; + u16 head, avail_used_flags, unpub_flags; bool avail_wrap_counter; int err; @@ -1955,14 +1970,29 @@ static inline int virtqueue_add_packed_in_order(struct vring_virtqueue *vq, i = head; vq->packed.avail_used_flags = avail_used_flags; vq->packed.avail_wrap_counter = avail_wrap_counter; + unpub_flags = avail_used_flags ^ (1 << VRING_PACKED_DESC_F_AVAIL | + 1 << VRING_PACKED_DESC_F_USED); for (n = 0; n < total_sg; n++) { if (i == err_idx) break; + /* + * The mapping loop made every descriptor but the head + * available. Stamp the previous wrap counter's AVAIL and USED + * bits on those, so that a later and shorter chain at this head + * does not leave one of them available beyond its own last + * descriptor. Marking them used instead would hand + * is_used_desc_packed() a completion we never made. + */ + if (i != head) + desc[i].flags = cpu_to_le16(unpub_flags); vring_unmap_extra_packed(vq, &vq->packed.desc_extra[i]); i++; - if (i >= vq->packed.vring.num) + if (i >= vq->packed.vring.num) { i = 0; + unpub_flags ^= 1 << VRING_PACKED_DESC_F_AVAIL | + 1 << VRING_PACKED_DESC_F_USED; + } } END_USE(vq); From 3f9a0fceb730f5107d52421ead5568eae25a0049 Mon Sep 17 00:00:00 2001 From: Karl Mehltretter Date: Fri, 21 Aug 2026 23:39:53 +0200 Subject: [PATCH 0881/1198] virtio: fix use-after-free in unregister_virtio_device() device_unregister() is device_del() plus put_device(). When the caller holds no extra reference, that drops the last one and runs the release callback, which for several transports frees the memory the embedded struct virtio_device sits in. unregister_virtio_device() then calls virtio_debug_device_exit(), which reads dev->debugfs_dir out of the freed object. Affected transports are the ones whose release callback frees and whose remove path takes no reference: virtio_mmio, virtio_vdpa, virtio_uml, mlxbf-tmfifo and virtio_ccw. virtio_pci is unaffected because virtio_pci_remove() brackets the call with get_device() and put_device(). Remove the debugfs entries before the device can go away. They are only accessed through the protected debugfs interface, so debugfs_remove_recursive() waits for in-progress file operations before returning. Tearing them down while the device is still alive is therefore safe. Reproduced on User-Mode Linux with CONFIG_KASAN and CONFIG_VIRTIO_DEBUG by unbinding a virtio-uml device: BUG: KASAN: slab-use-after-free in virtio_debug_device_exit+0x36/0x4d Read of size 8 at addr 00000000616e0b10 by task init/1 __asan_report_load8_noabort virtio_debug_device_exit+0x36/0x4d unregister_virtio_device+0x48/0x75 virtio_uml_remove platform_remove device_release_driver_internal unbind_store Freed by task 1: kfree virtio_uml_release_dev device_release kobject_put put_device device_unregister With this applied, the report is gone and unbind is clean. Fixes: 96a8326d69ff ("virtio: add debugfs infrastructure to allow to debug virtio features") Assisted-by: Claude:claude-opus-5 Signed-off-by: Karl Mehltretter Signed-off-by: Michael S. Tsirkin Message-ID: <20260821213953.76906-1-kmehltretter@gmail.com> --- drivers/virtio/virtio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 75bb4ffe3b87..b6c9e927bef5 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -604,8 +604,8 @@ void unregister_virtio_device(struct virtio_device *dev) { int index = dev->index; /* save for after device release */ - device_unregister(&dev->dev); virtio_debug_device_exit(dev); + device_unregister(&dev->dev); ida_free(&virtio_index_ida, index); } EXPORT_SYMBOL_GPL(unregister_virtio_device); From 894f98e73983f37354214a89a3a7fd35bf9e3072 Mon Sep 17 00:00:00 2001 From: Jia Jia Date: Wed, 19 Aug 2026 10:12:30 +0800 Subject: [PATCH 0882/1198] virtio_console: do not free control-out buffers on remove __send_control_msg() publishes &portdev->cpkt as the control-out virtqueue cookie. remove_vqs() walks every virtqueue and passes leftover cookies to free_buf(), which treats them as struct port_buffer and reads sgpages. If a control message is still on c_ovq when the device is unbound, free_buf() reads past the ports_device object. KASAN reported slab-out-of-bounds in free_buf(): free_buf remove_vqs virtcons_remove unbind_store The object was the ports_device allocated in virtcons_probe(). Drain c_ovq without freeing. The packet lives in portdev and is released with it. Fixes: a7a69ec0d8e4 ("virtio_console: free buffers after reset") Signed-off-by: Jia Jia Signed-off-by: Michael S. Tsirkin Message-ID: <20260819021230.292696-1-physicalmtea@gmail.com> --- drivers/char/virtio_console.c | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 7f6cbe851d1e..019bcae81af5 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -1964,13 +1964,28 @@ static const struct file_operations portdev_fops = { static void remove_vqs(struct ports_device *portdev) { struct virtqueue *vq; + bool multiport = use_multiport(portdev); virtio_device_for_each_vq(portdev->vdev, vq) { struct port_buffer *buf; + unsigned int len; - flush_bufs(vq, true); - while ((buf = virtqueue_detach_unused_buf(vq))) - free_buf(buf, true); + /* + * c_ovq cookies are &portdev->cpkt, not port_buffer. + * Detach them but do not free_buf(). + */ + if (multiport && vq == portdev->c_ovq) { + spin_lock(&portdev->c_ovq_lock); + while (virtqueue_get_buf(vq, &len)) + ; + while (virtqueue_detach_unused_buf(vq)) + ; + spin_unlock(&portdev->c_ovq_lock); + } else { + flush_bufs(vq, true); + while ((buf = virtqueue_detach_unused_buf(vq))) + free_buf(buf, true); + } cond_resched(); } portdev->vdev->config->del_vqs(portdev->vdev); From ccb1dc7c527f8c925925cf92afc76ae590dac311 Mon Sep 17 00:00:00 2001 From: Jia Jia Date: Mon, 10 Aug 2026 09:03:00 +0800 Subject: [PATCH 0883/1198] vhost/vdpa: reject VRING_NUM larger than device max vhost_vring_set_num() accepts any non-zero power-of-two queue size that fits in 16 bits. vhost-vdpa then passes that value to set_vq_num() without comparing it with get_vq_num_max(). A process with access to /dev/vhost-vdpa-* can therefore configure a queue larger than the device advertises. With vdpa_sim, the worker can walk descriptors beyond the mapped descriptor ring. KASAN reports a 16-byte out-of-bounds read, corresponding to one vring_desc, in the vringh IOTLB path: BUG: KASAN: out-of-bounds in _copy_from_iter Read of size 16 copy_from_iotlb copydesc_iotlb vringh_getdesc_iotlb vdpasim_net_work Cache get_vq_num_max() immediately after reset. Some backends derive it from writable queue-size state, so querying it after SET_NUM may return the current size instead of the device capability. Invalidate the cached value before reset so a failed reset leaves SET_NUM disabled. For VHOST_SET_VRING_NUM, copy the complete vring state once and use the same index and size for validation, vq->num, and set_vq_num(). This ensures that validation and use operate on the same copied values. Fixes: 4c8cf31885f6 ("vhost: introduce vDPA-based backend") Signed-off-by: Jia Jia Signed-off-by: Michael S. Tsirkin Message-ID: <20260810010300.132959-1-physicalmtea@gmail.com> --- drivers/vhost/vdpa.c | 44 +++++++++++++++++++++++++++++++++++++------- 1 file changed, 37 insertions(+), 7 deletions(-) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index c3d913bd7cac..4eb1eb5e5c79 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -58,6 +58,7 @@ struct vhost_vdpa { struct cdev cdev; atomic_t opened; u32 nvqs; + u16 vq_num_max; int virtio_id; int minor; struct eventfd_ctx *config_ctx; @@ -236,7 +237,9 @@ static void vhost_vdpa_unsetup_vq_irq(struct vhost_vdpa *v, u16 qid) static int _compat_vdpa_reset(struct vhost_vdpa *v) { struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; u32 flags = 0; + int ret; v->suspended = false; @@ -246,7 +249,14 @@ static int _compat_vdpa_reset(struct vhost_vdpa *v) VDPA_RESET_F_CLEAN_MAP : 0; } - return vdpa_reset(vdpa, flags); + v->vq_num_max = 0; + ret = vdpa_reset(vdpa, flags); + if (!ret) { + /* Some backends derive the max from mutable queue state. */ + v->vq_num_max = ops->get_vq_num_max(vdpa); + } + + return ret; } static int vhost_vdpa_reset(struct vhost_vdpa *v) @@ -648,9 +658,15 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, u32 idx; long r; - r = get_user(idx, (u32 __user *)argp); - if (r < 0) - return r; + if (cmd == VHOST_SET_VRING_NUM) { + if (copy_from_user(&s, argp, sizeof(s))) + return -EFAULT; + idx = s.index; + } else { + r = get_user(idx, (u32 __user *)argp); + if (r < 0) + return r; + } if (idx >= v->nvqs) return -ENOBUFS; @@ -659,6 +675,23 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, vq = &v->vqs[idx]; switch (cmd) { + case VHOST_SET_VRING_NUM: + mutex_lock(&vq->mutex); + if (vq->private_data) { + r = -EBUSY; + } else if (!s.num || s.num > 0xffff || + s.num > v->vq_num_max || + (s.num & (s.num - 1))) { + r = -EINVAL; + } else { + vq->num = s.num; + r = 0; + } + mutex_unlock(&vq->mutex); + if (r) + return r; + ops->set_vq_num(vdpa, idx, s.num); + return 0; case VHOST_VDPA_SET_VRING_ENABLE: if (copy_from_user(&s, argp, sizeof(s))) return -EFAULT; @@ -772,9 +805,6 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, ops->set_vq_cb(vdpa, idx, &cb); break; - case VHOST_SET_VRING_NUM: - ops->set_vq_num(vdpa, idx, vq->num); - break; } return r; From e74a9fa50749b9940b4fb13199652325e08d3c4a Mon Sep 17 00:00:00 2001 From: Yu Zhang Date: Fri, 7 Aug 2026 20:00:24 +1000 Subject: [PATCH 0884/1198] vhost-vdpa: don't install the eventfd_ctx_fdget() error in config_ctx vhost_vdpa_set_config_call() swaps the eventfd_ctx_fdget() return value into v->config_ctx before checking it, so on failure the field briefly holds an ERR_PTR: ctx = fd == VHOST_FILE_UNBIND ? NULL : eventfd_ctx_fdget(fd); swap(ctx, v->config_ctx); if (!IS_ERR_OR_NULL(ctx)) eventfd_ctx_put(ctx); if (IS_ERR(v->config_ctx)) { long ret = PTR_ERR(v->config_ctx); v->config_ctx = NULL; return ret; } Commit 0bde59c1723a ("vhost-vdpa: set v->config_ctx to NULL if eventfd_ctx_fdget() fails") added that clearing, and spelled out the invariant the rest of the file relies on: "we consider 'v->config_ctx' valid if it is not NULL". The window between the swap and the clearing still breaks it. vhost_vdpa_config_cb() only tests for NULL, so a config interrupt delivered inside the window hands the ERR_PTR to eventfd_signal(). Check the fd before installing it instead. That closes the window and matches how vhost_vring_ioctl() handles the same failure for the vq call fd. It also stops a rejected fd from tearing down a config interrupt that was working: until now the swap replaced the live context and put it, so after an EBADF the device silently stopped delivering config interrupts until userspace installed a new fd. Fixes: 776f395004d8 ("vhost_vdpa: Support config interrupt in vdpa") Signed-off-by: Yu Zhang Signed-off-by: Michael S. Tsirkin Message-ID: <20260807100025.19750-2-yuz08559@gmail.com> --- drivers/vhost/vdpa.c | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 4eb1eb5e5c79..3e5165b7c094 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -546,18 +546,14 @@ static long vhost_vdpa_set_config_call(struct vhost_vdpa *v, u32 __user *argp) return -EFAULT; ctx = fd == VHOST_FILE_UNBIND ? NULL : eventfd_ctx_fdget(fd); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + swap(ctx, v->config_ctx); - if (!IS_ERR_OR_NULL(ctx)) + if (ctx) eventfd_ctx_put(ctx); - if (IS_ERR(v->config_ctx)) { - long ret = PTR_ERR(v->config_ctx); - - v->config_ctx = NULL; - return ret; - } - v->vdpa->config->set_config_cb(v->vdpa, &cb); return 0; From 62be4e3e5f5f947fbf765b914cebdc478f715d12 Mon Sep 17 00:00:00 2001 From: Yu Zhang Date: Fri, 7 Aug 2026 20:00:25 +1000 Subject: [PATCH 0885/1198] vhost-vdpa: protect config_ctx from being freed under the config callback vhost_vdpa_config_cb() loads v->config_ctx and signals it without taking a reference and without holding any lock: struct eventfd_ctx *config_ctx = v->config_ctx; if (config_ctx) eventfd_signal(config_ctx); VHOST_VDPA_SET_CONFIG_CALL replaces that field and drops what is normally the last reference to the old context: swap(ctx, v->config_ctx); if (ctx) eventfd_ctx_put(ctx); eventfd_ctx_put() drops the last kref and frees the context immediately, with no RCU grace period, so a callback that has already loaded the pointer goes on to dereference freed memory. The two sides share no lock: the ioctl runs under vhost_dev.mutex, while the parent invokes the callback from its own interrupt or workqueue context. This is not the reopen refcount underflow fixed by commit f6bbf0010ba0 ("vhost-vdpa: fix use-after-free of v->config_ctx"), which was about vhost_vdpa_config_put() leaving a stale pointer behind. Here the pointer is maintained correctly and it is the read side that is unprotected. With VDUSE as the parent this is reachable from userspace with access to /dev/vduse (root by default). VDUSE_DEV_INJECT_CONFIG_IRQ queues dev->inject, and vduse_dev_irq_inject() runs the callback under VDUSE's own dev->irq_lock, which vhost does not hold. vduse_dev_reset() does flush_work(&dev->inject), but VHOST_VDPA_SET_CONFIG_CALL never goes through reset, so an inject already in flight is not waited for. A process that injects config interrupts on the VDUSE fd while another thread swaps the call fd on the vhost-vdpa fd hits it in seconds: BUG: KASAN: slab-use-after-free in native_queued_spin_lock_slowpath Read of size 4 at addr ffff888107d21808 by task kworker/u17:1/2993 Workqueue: vduse-irq vduse_dev_irq_inject Call Trace: native_queued_spin_lock_slowpath+0x97/0x5b0 _raw_spin_lock_irqsave+0xd4/0xe0 eventfd_signal_mask+0x69/0x120 vhost_vdpa_config_cb+0x34/0x50 vduse_dev_irq_inject+0x46/0x60 process_one_work+0x468/0x950 Allocated by task 2992: do_eventfd+0x50/0x200 __x64_sys_eventfd2+0x2e/0x40 Freed by task 2992: eventfd_ctx_put+0xb9/0xc0 vhost_vdpa_unlocked_ioctl+0x116c/0x2190 Add a spinlock covering every access to config_ctx, so the callback either signals a context that is still alive or observes NULL, and the put happens only once no callback can reach the old value. Clearing the parent's callback before the put would not be enough: of the in-tree set_config_cb() implementations only VDUSE takes a lock, the rest store the pointer unlocked, so that would not order against an in-flight invocation. Fixes: 776f395004d8 ("vhost_vdpa: Support config interrupt in vdpa") Signed-off-by: Yu Zhang Signed-off-by: Michael S. Tsirkin Message-ID: <20260807100025.19750-3-yuz08559@gmail.com> --- drivers/vhost/vdpa.c | 32 +++++++++++++++++++++++++------- 1 file changed, 25 insertions(+), 7 deletions(-) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 3e5165b7c094..a31786796d4c 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -62,6 +62,8 @@ struct vhost_vdpa { int virtio_id; int minor; struct eventfd_ctx *config_ctx; + /* Serialises vhost_vdpa_config_cb() against config_ctx being replaced. */ + spinlock_t config_lock; int in_batch; struct vdpa_iova_range range; u32 batch_asid; @@ -195,10 +197,12 @@ static irqreturn_t vhost_vdpa_virtqueue_cb(void *private) static irqreturn_t vhost_vdpa_config_cb(void *private) { struct vhost_vdpa *v = private; - struct eventfd_ctx *config_ctx = v->config_ctx; + unsigned long flags; - if (config_ctx) - eventfd_signal(config_ctx); + spin_lock_irqsave(&v->config_lock, flags); + if (v->config_ctx) + eventfd_signal(v->config_ctx); + spin_unlock_irqrestore(&v->config_lock, flags); return IRQ_HANDLED; } @@ -528,15 +532,22 @@ static long vhost_vdpa_get_vring_num(struct vhost_vdpa *v, u16 __user *argp) static void vhost_vdpa_config_put(struct vhost_vdpa *v) { - if (v->config_ctx) { - eventfd_ctx_put(v->config_ctx); - v->config_ctx = NULL; - } + struct eventfd_ctx *ctx; + unsigned long flags; + + spin_lock_irqsave(&v->config_lock, flags); + ctx = v->config_ctx; + v->config_ctx = NULL; + spin_unlock_irqrestore(&v->config_lock, flags); + + if (ctx) + eventfd_ctx_put(ctx); } static long vhost_vdpa_set_config_call(struct vhost_vdpa *v, u32 __user *argp) { struct vdpa_callback cb; + unsigned long flags; int fd; struct eventfd_ctx *ctx; @@ -549,8 +560,14 @@ static long vhost_vdpa_set_config_call(struct vhost_vdpa *v, u32 __user *argp) if (IS_ERR(ctx)) return PTR_ERR(ctx); + spin_lock_irqsave(&v->config_lock, flags); swap(ctx, v->config_ctx); + spin_unlock_irqrestore(&v->config_lock, flags); + /* + * The callback can no longer reach the old context, so this is the + * last reference to it. + */ if (ctx) eventfd_ctx_put(ctx); @@ -1639,6 +1656,7 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa) } atomic_set(&v->opened, 0); + spin_lock_init(&v->config_lock); v->minor = minor; v->vdpa = vdpa; v->nvqs = vdpa->nvqs; From d14d693adb055e98ca705822ba6daebc18602d9a Mon Sep 17 00:00:00 2001 From: Xiong Weimin Date: Wed, 5 Aug 2026 11:29:37 +0800 Subject: [PATCH 0886/1198] virtio_mmio: disable IRQ wake before free_irq When the DT node has "wakeup-source", vm_find_vqs() calls enable_irq_wake() on the shared IRQ, but vm_del_vqs() freed that IRQ without a matching disable_irq_wake(). That leaves a wake reference behind and can warn on later free_irq()/request_irq() cycles. Record whether enable_irq_wake() succeeded, and disable it in vm_del_vqs() before free_irq(). Fixes: 02213273f72a ("virtio_mmio: add support to set IRQ of a virtio device as wakeup source") Cc: stable@vger.kernel.org Signed-off-by: Xiong Weimin Signed-off-by: Michael S. Tsirkin Message-ID: <20260805032937.1606737-1-xiongweimin@kylinos.cn> --- drivers/virtio/virtio_mmio.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c index 316f03b97356..faae58e3401a 100644 --- a/drivers/virtio/virtio_mmio.c +++ b/drivers/virtio/virtio_mmio.c @@ -88,6 +88,9 @@ struct virtio_mmio_device { void __iomem *base; unsigned long version; + + /* True if enable_irq_wake() succeeded for the shared IRQ. */ + bool wake_irq_enabled; }; /* Configuration interface */ @@ -336,11 +339,17 @@ static void vm_del_vqs(struct virtio_device *vdev) { struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev); struct virtqueue *vq, *n; + int irq = platform_get_irq(vm_dev->pdev, 0); list_for_each_entry_safe(vq, n, &vdev->vqs, list) vm_del_vq(vq); - free_irq(platform_get_irq(vm_dev->pdev, 0), vm_dev); + if (vm_dev->wake_irq_enabled) { + disable_irq_wake(irq); + vm_dev->wake_irq_enabled = false; + } + + free_irq(irq, vm_dev); } static void vm_synchronize_cbs(struct virtio_device *vdev) @@ -467,8 +476,9 @@ static int vm_find_vqs(struct virtio_device *vdev, unsigned int nvqs, if (err) return err; - if (of_property_read_bool(vm_dev->pdev->dev.of_node, "wakeup-source")) - enable_irq_wake(irq); + if (of_property_read_bool(vm_dev->pdev->dev.of_node, "wakeup-source") && + !enable_irq_wake(irq)) + vm_dev->wake_irq_enabled = true; for (i = 0; i < nvqs; ++i) { struct virtqueue_info *vqi = &vqs_info[i]; From 6601d5a00899e7fa7e6b2d18113cee385ed3801b Mon Sep 17 00:00:00 2001 From: Xiong Weimin Date: Thu, 6 Aug 2026 08:58:09 +0800 Subject: [PATCH 0887/1198] vdpa/pds: check virtqueue notify mapping vp_modern_map_vq_notify() can fail and return NULL. Check the notify mapping while adding a pds vDPA device and use the existing teardown path instead of storing a NULL doorbell pointer in the virtqueue state. Signed-off-by: Xiong Weimin Reviewed-by: Brett Creeley Signed-off-by: Michael S. Tsirkin Message-ID: <20260806005809.1875257-1-xiongweimin@kylinos.cn> --- drivers/vdpa/pds/vdpa_dev.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/vdpa/pds/vdpa_dev.c b/drivers/vdpa/pds/vdpa_dev.c index 43426bd971ac..77d679f6763d 100644 --- a/drivers/vdpa/pds/vdpa_dev.c +++ b/drivers/vdpa/pds/vdpa_dev.c @@ -731,6 +731,12 @@ static int pds_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, notify = vp_modern_map_vq_notify(&pdsv->vdpa_aux->vd_mdev, i, &pdsv->vqs[i].notify_pa); + if (!notify) { + err = -EINVAL; + dev_err(dev, "Fail to map vq notify %d\n", i); + goto err_unmap; + } + pds_vdpa_init_vqs_entry(pdsv, i, notify); } From 9ab9b4f4eb4288588707ec359ac3d5b7ccf07fa6 Mon Sep 17 00:00:00 2001 From: Xiong Weimin Date: Tue, 4 Aug 2026 17:26:07 +0800 Subject: [PATCH 0888/1198] vdpa: alibaba: Keep DRIVER_OK clear if IRQ setup fails If requesting MSI-X interrupts fails while DRIVER_OK is being set, leave the device status unchanged instead of advertising a ready device without working interrupts. Signed-off-by: Xiong Weimin Signed-off-by: Michael S. Tsirkin Message-ID: <20260804092608.1344269-1-xiongweimin@kylinos.cn> --- drivers/vdpa/alibaba/eni_vdpa.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/vdpa/alibaba/eni_vdpa.c b/drivers/vdpa/alibaba/eni_vdpa.c index fd6fdba46094..1288402d3dd8 100644 --- a/drivers/vdpa/alibaba/eni_vdpa.c +++ b/drivers/vdpa/alibaba/eni_vdpa.c @@ -216,7 +216,10 @@ static void eni_vdpa_set_status(struct vdpa_device *vdpa, u8 status) if (status & VIRTIO_CONFIG_S_DRIVER_OK && !(s & VIRTIO_CONFIG_S_DRIVER_OK)) { - eni_vdpa_request_irq(eni_vdpa); + if (eni_vdpa_request_irq(eni_vdpa)) { + WARN_ON(1); + return; + } } vp_legacy_set_status(ldev, status); From e847542ab0545c73354849126150206c29d83929 Mon Sep 17 00:00:00 2001 From: Xiong Weimin Date: Wed, 5 Aug 2026 09:51:53 +0800 Subject: [PATCH 0889/1198] vdpa: solidrun: Free IRQs after request failure Unwind IRQs already requested by snet_request_irqs() before returning a VQ IRQ request error so a later DRIVER_OK retry starts from a clean state. The IRQs are requested and freed while the PCI device remains bound, so the driver cannot wait for devres cleanup at detach time. Fixes: 51a8f9d7f587 ("virtio: vdpa: new SolidNET DPU driver.") Cc: stable@vger.kernel.org # v6.3+ Signed-off-by: Xiong Weimin Signed-off-by: Michael S. Tsirkin Message-ID: <178589471328.1556376.15570536900532373521@kylinos.cn> --- drivers/vdpa/solidrun/snet_main.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/vdpa/solidrun/snet_main.c b/drivers/vdpa/solidrun/snet_main.c index 28d55315df2a..3e2cea1e45f3 100644 --- a/drivers/vdpa/solidrun/snet_main.c +++ b/drivers/vdpa/solidrun/snet_main.c @@ -418,11 +418,15 @@ static int snet_request_irqs(struct pci_dev *pdev, struct snet *snet) snet->vqs[i]->irq_name, snet->vqs[i]); if (ret) { SNET_ERR(pdev, "Failed to request IRQ\n"); - return ret; + goto err_free_irqs; } snet->vqs[i]->irq = irq; } return 0; + +err_free_irqs: + snet_free_irqs(snet); + return ret; } static void snet_set_status(struct vdpa_device *vdev, u8 status) From 4d470be71196ca0ce302e6623454533dc31b465b Mon Sep 17 00:00:00 2001 From: Xiong Weimin Date: Wed, 5 Aug 2026 09:51:52 +0800 Subject: [PATCH 0890/1198] vdpa: ifcvf: Put device on unsupported feature error Route unsupported provisioned features through the common error path after vdpa_alloc_device() so the allocated device and adapter pointer are released consistently. Fixes: 46fc0917bbab ("vDPA/ifcvf: implement features provisioning") Cc: stable@vger.kernel.org # v6.3+ Signed-off-by: Xiong Weimin Signed-off-by: Michael S. Tsirkin Message-ID: <178589471294.1556376.4816776800128323034@kylinos.cn> --- drivers/vdpa/ifcvf/ifcvf_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c index ab6d6ab3b3d8..2af1cec95884 100644 --- a/drivers/vdpa/ifcvf/ifcvf_main.c +++ b/drivers/vdpa/ifcvf/ifcvf_main.c @@ -724,7 +724,8 @@ static int ifcvf_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, if (config->device_features & ~device_features) { IFCVF_ERR(pdev, "The provisioned features 0x%llx are not supported by this device with features 0x%llx\n", config->device_features, device_features); - return -EINVAL; + ret = -EINVAL; + goto err; } device_features &= config->device_features; } From 6519ca235131c3281a83cc9e8b05af709ab98a89 Mon Sep 17 00:00:00 2001 From: Xiong Weimin Date: Tue, 4 Aug 2026 17:26:36 +0800 Subject: [PATCH 0891/1198] vdpa: octeon_ep: Check dev_set_name() in dev add Handle dev_set_name() failures before registering the vDPA device so allocation is unwound through the existing put_device() path. Signed-off-by: Xiong Weimin Signed-off-by: Michael S. Tsirkin Message-ID: <20260804092636.1344431-1-xiongweimin@kylinos.cn> --- drivers/vdpa/octeon_ep/octep_vdpa_main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/vdpa/octeon_ep/octep_vdpa_main.c b/drivers/vdpa/octeon_ep/octep_vdpa_main.c index 23e280a29209..85a3d35ea1e4 100644 --- a/drivers/vdpa/octeon_ep/octep_vdpa_main.c +++ b/drivers/vdpa/octeon_ep/octep_vdpa_main.c @@ -600,6 +600,8 @@ static int octep_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, ret = dev_set_name(&vdpa_dev->dev, "%s", name); else ret = dev_set_name(&vdpa_dev->dev, "vdpa%u", vdpa_dev->index); + if (ret) + goto vdpa_dev_put; ret = _vdpa_register_device(&oct_vdpa->vdpa, oct_hw->nr_vring); if (ret) { From ca2c2165a02e499b591a367224346a7e52664d9c Mon Sep 17 00:00:00 2001 From: Xiong Weimin Date: Tue, 4 Aug 2026 17:26:49 +0800 Subject: [PATCH 0892/1198] virtio-vdpa: Use queue id when setting vq affinity When optional queues are skipped, pass the compressed vDPA queue id to set_vq_affinity() so affinity is applied to the queue that was actually created. Signed-off-by: Xiong Weimin Signed-off-by: Michael S. Tsirkin Message-ID: <20260804092649.1344478-1-xiongweimin@kylinos.cn> --- drivers/virtio/virtio_vdpa.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c index de2af696de6c..6bcf4567a929 100644 --- a/drivers/virtio/virtio_vdpa.c +++ b/drivers/virtio/virtio_vdpa.c @@ -352,7 +352,7 @@ static int virtio_vdpa_find_vqs(struct virtio_device *vdev, unsigned int nvqs, continue; } - vqs[i] = virtio_vdpa_setup_vq(vdev, queue_idx++, vqi->callback, + vqs[i] = virtio_vdpa_setup_vq(vdev, queue_idx, vqi->callback, vqi->name, vqi->ctx); if (IS_ERR(vqs[i])) { err = PTR_ERR(vqs[i]); @@ -360,7 +360,8 @@ static int virtio_vdpa_find_vqs(struct virtio_device *vdev, unsigned int nvqs, } if (has_affinity) - ops->set_vq_affinity(vdpa, i, &masks[i]); + ops->set_vq_affinity(vdpa, queue_idx, &masks[i]); + queue_idx++; } cb.callback = virtio_vdpa_config_cb; From 0a8693f00c408d85f086ad85d29e7030bf1e2055 Mon Sep 17 00:00:00 2001 From: Linfeng Sun Date: Tue, 1 Sep 2026 17:48:00 +0800 Subject: [PATCH 0893/1198] vdpa_sim_blk: reject out-of-range sector starts vdpasim_blk_check_range() logs an invalid start sector but continues validating the request. The subsequent unsigned capacity subtraction can underflow and let an out-of-range buffer offset reach the data path. The invalid offset is used by three request paths. VIRTIO_BLK_T_OUT copies guest data to blk->buffer + offset through vringh_iov_pull_iotlb(), causing an out-of-bounds write in _copy_from_iter() or memcpy(). VIRTIO_BLK_T_IN copies from blk->buffer + offset to the guest through vringh_iov_push_iotlb(), causing an out-of-bounds read in _copy_to_iter(). VIRTIO_BLK_T_WRITE_ZEROES passes blk->buffer + offset to memset(), causing an out-of-bounds write. Reject starts at or beyond the capacity before the subtraction. Treat the capacity boundary as invalid because the IN and OUT paths round byte counts down to sectors for validation but later copy the original byte counts. A sub-sector request at the capacity boundary would otherwise still access past the end of the buffer. I found this bug myself, though the patch was written with AI assistance. Fixes: 7d189f617f83 ("vdpa_sim_blk: implement ramdisk behaviour") Assisted-by: OpenAI-Codex:GPT-5 Signed-off-by: Linfeng Sun Signed-off-by: Michael S. Tsirkin Message-ID: <20260901094800.25475-1-linfeng.sun.dev@gmail.com> --- drivers/vdpa/vdpa_sim/vdpa_sim_blk.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c index f70f454dde8e..76dd5b0828d7 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c @@ -79,10 +79,11 @@ static void vdpasim_blk_buffer_unlock(struct vdpasim_blk *blk) static bool vdpasim_blk_check_range(struct vdpasim *vdpasim, u64 start_sector, u64 num_sectors, u64 max_sectors) { - if (start_sector > VDPASIM_BLK_CAPACITY) { + if (start_sector >= VDPASIM_BLK_CAPACITY) { dev_dbg(&vdpasim->vdpa.dev, "starting sector exceeds the capacity - start: 0x%llx capacity: 0x%x\n", start_sector, VDPASIM_BLK_CAPACITY); + return false; } if (num_sectors > max_sectors) { From 0d195797a80b77f2ec56718cd26d3ee65d0093e8 Mon Sep 17 00:00:00 2001 From: Linfeng Sun Date: Tue, 1 Sep 2026 17:48:42 +0800 Subject: [PATCH 0894/1198] vdpa_sim_net: check TX pull result before RX copy vringh_iov_pull_iotlb() returns a signed byte count. A failed TX pull is currently added to the unsigned byte counter and then passed as a size_t length to receive_filter() and vringh_iov_push_iotlb(). A negative error can therefore become a large length in the RX path. Handle non-positive pull results before every length use. Count the TX error and complete the consumed TX descriptor with zero bytes. I found this bug myself, though the patch was written with AI assistance. Fixes: cfe226892913 ("vdpa_sim: filter destination mac address") Assisted-by: OpenAI-Codex:GPT-5 Signed-off-by: Linfeng Sun Signed-off-by: Michael S. Tsirkin Message-ID: <20260901094842.25875-1-linfeng.sun.dev@gmail.com> --- drivers/vdpa/vdpa_sim/vdpa_sim_net.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c index 29fd14ce5860..a6514b5ccd86 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c @@ -225,10 +225,15 @@ static void vdpasim_net_work(struct vdpasim *vdpasim) break; } - ++tx_pkts; read = vringh_iov_pull_iotlb(&txq->vring, &txq->out_iov, net->buffer, PAGE_SIZE); + if (read <= 0) { + ++tx_errors; + vdpasim_net_complete(txq, 0); + continue; + } + ++tx_pkts; tx_bytes += read; if (!receive_filter(vdpasim, read)) { From 7034e6c8dadaf4a2c95669890095ebafa8d9cee7 Mon Sep 17 00:00:00 2001 From: Laurent Vivier Date: Tue, 18 Aug 2026 15:39:13 +0200 Subject: [PATCH 0895/1198] MAINTAINERS: Add a section for virtio-rng At Michael's request, add a MAINTAINERS entry for the virtio-rng driver and list myself as its maintainer. I already maintain the corresponding QEMU implementation. Cc: Michael S. Tsirkin Signed-off-by: Laurent Vivier Signed-off-by: Michael S. Tsirkin Message-ID: <20260818133913.162471-1-lvivier@redhat.com> --- MAINTAINERS | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 6215fcb07770..35ddf814de94 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -29017,6 +29017,13 @@ S: Maintained F: drivers/nvdimm/nd_virtio.c F: drivers/nvdimm/virtio_pmem.c +VIRTIO RNG DRIVER +M: Laurent Vivier +L: virtualization@lists.linux.dev +S: Maintained +F: drivers/char/hw_random/virtio-rng.c +F: include/uapi/linux/virtio_rng.h + VIRTIO RTC DRIVER M: Peter Hilber L: virtualization@lists.linux.dev From 84cd1f879968ae75da15c25de4cb390428e89e6d Mon Sep 17 00:00:00 2001 From: Linfeng Sun Date: Thu, 3 Sep 2026 12:13:33 +0800 Subject: [PATCH 0896/1198] vhost: limit outstanding IOTLB misses per virtqueue vhost allocates a message node whenever address translation misses. If userspace reads these messages without resolving them, repeated virtqueue kicks can grow the pending message list until the host runs out of memory. Virtqueue processing stops at the first translation miss and cannot make progress until userspace installs a mapping. Keep a pointer to that outstanding message in the virtqueue and suppress additional misses until the node is resolved or discarded. The pointer remains set while the message is queued for reading, copied to userspace, or waiting on the pending list. Clear it under the IOTLB lock when the owning node is freed. This bounds outstanding miss messages by the fixed number of virtqueues without introducing an arbitrary queue limit. Signed-off-by: Linfeng Sun Signed-off-by: Michael S. Tsirkin Message-ID: <20260903-fix-kernel-panic-in-vhost_iotlb_miss_pending_list-v1-1-39b8cd427978@gmail.com> --- drivers/vhost/vhost.c | 38 +++++++++++++++++++++++++++++++++----- drivers/vhost/vhost.h | 3 +++ 2 files changed, 36 insertions(+), 5 deletions(-) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 14637cff0bd4..02588b64b1bb 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -392,6 +392,7 @@ static void vhost_vq_reset(struct vhost_dev *dev, vq->busyloop_timeout = 0; vq->umem = NULL; vq->iotlb = NULL; + vq->iotlb_miss = NULL; rcu_assign_pointer(vq->worker, NULL); vhost_vring_call_reset(&vq->call_ctx); __vhost_vq_meta_reset(vq); @@ -1180,6 +1181,21 @@ void vhost_dev_stop(struct vhost_dev *dev) } EXPORT_SYMBOL_GPL(vhost_dev_stop); +static void vhost_free_msg_locked(struct vhost_msg_node *node) +{ + if (node->vq->iotlb_miss == node) + node->vq->iotlb_miss = NULL; + kfree(node); +} + +static void vhost_free_msg(struct vhost_dev *dev, + struct vhost_msg_node *node) +{ + spin_lock(&dev->iotlb_lock); + vhost_free_msg_locked(node); + spin_unlock(&dev->iotlb_lock); +} + void vhost_clear_msg(struct vhost_dev *dev) { struct vhost_msg_node *node, *n; @@ -1188,12 +1204,12 @@ void vhost_clear_msg(struct vhost_dev *dev) list_for_each_entry_safe(node, n, &dev->read_list, node) { list_del(&node->node); - kfree(node); + vhost_free_msg_locked(node); } list_for_each_entry_safe(node, n, &dev->pending_list, node) { list_del(&node->node); - kfree(node); + vhost_free_msg_locked(node); } spin_unlock(&dev->iotlb_lock); @@ -1602,7 +1618,7 @@ static void vhost_iotlb_notify_vq(struct vhost_dev *d, vq_msg->type == VHOST_IOTLB_MISS) { vhost_poll_queue(&node->vq->poll); list_del(&node->node); - kfree(node); + vhost_free_msg_locked(node); } } @@ -1816,7 +1832,7 @@ ssize_t vhost_chr_read_iter(struct vhost_dev *dev, struct iov_iter *to, ret = copy_to_iter(start, size, to); if (ret != size || msg->type != VHOST_IOTLB_MISS) { - kfree(node); + vhost_free_msg(dev, node); return ret; } vhost_enqueue_msg(dev, &dev->pending_list, node); @@ -1848,7 +1864,19 @@ static int vhost_iotlb_miss(struct vhost_virtqueue *vq, u64 iova, int access) msg->iova = iova; msg->perm = access; - vhost_enqueue_msg(dev, &dev->read_list, node); + spin_lock(&dev->iotlb_lock); + /* VQ processing stops at the first miss until userspace resolves it. */ + if (vq->iotlb_miss) { + spin_unlock(&dev->iotlb_lock); + kfree(node); + return 0; + } + + vq->iotlb_miss = node; + list_add_tail(&node->node, &dev->read_list); + spin_unlock(&dev->iotlb_lock); + + wake_up_interruptible_poll(&dev->wait, EPOLLIN | EPOLLRDNORM); return 0; } diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index 0192ade6e749..fa76b7d44662 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -29,6 +29,7 @@ struct vhost_work { struct vhost_worker; struct vhost_dev; +struct vhost_msg_node; struct vhost_worker_ops { int (*create)(struct vhost_worker *worker, struct vhost_dev *dev, @@ -148,6 +149,8 @@ struct vhost_virtqueue { /* Protected by virtqueue mutex. */ struct vhost_iotlb *umem; struct vhost_iotlb *iotlb; + /* Protected by dev->iotlb_lock. */ + struct vhost_msg_node *iotlb_miss; void *private_data; VIRTIO_DECLARE_FEATURES(acked_features); u64 acked_backend_features; From 8dd505a45de0e63829d8bb4116b1d66db64813be Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= Date: Thu, 3 Sep 2026 10:18:31 +0200 Subject: [PATCH 0897/1198] =?UTF-8?q?virtio:=20add=20Eugenio=20P=C3=A9rez?= =?UTF-8?q?=20as=20Maintainer?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Eugenio Pérez Reviewed-by: Stefano Garzarella Signed-off-by: Michael S. Tsirkin Message-ID: <20260903081831.2129729-1-eperezma@redhat.com> --- MAINTAINERS | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 35ddf814de94..fdbd46fce4b3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -28867,8 +28867,8 @@ F: include/uapi/linux/virtio_console.h VIRTIO CORE M: "Michael S. Tsirkin" M: Jason Wang +M: Eugenio Pérez R: Xuan Zhuo -R: Eugenio Pérez L: virtualization@lists.linux.dev S: Maintained F: Documentation/ABI/testing/sysfs-bus-vdpa @@ -28945,7 +28945,7 @@ F: include/uapi/linux/virtio_gpu.h VIRTIO HOST (VHOST) M: "Michael S. Tsirkin" M: Jason Wang -R: Eugenio Pérez +M: Eugenio Pérez L: kvm@vger.kernel.org L: virtualization@lists.linux.dev L: netdev@vger.kernel.org @@ -29000,8 +29000,8 @@ F: include/uapi/linux/virtio_mem.h VIRTIO NET DRIVER M: "Michael S. Tsirkin" M: Jason Wang +M: Eugenio Pérez R: Xuan Zhuo -R: Eugenio Pérez L: netdev@vger.kernel.org L: virtualization@lists.linux.dev S: Maintained From 93fa09455fb1a9624b73d42ac1f83771f4818e80 Mon Sep 17 00:00:00 2001 From: Andrew Stellman Date: Fri, 4 Sep 2026 10:13:18 -0400 Subject: [PATCH 0898/1198] virtio-pci: return IRQ_HANDLED after non-zero ISR vp_interrupt() reads the ISR before dispatching config-change and vring handling. Reading the ISR also clears it, so once the read returns non-zero the interrupt was from this device and has already been consumed. Currently vp_interrupt() returns the result of vp_vring_interrupt(). For a config-change interrupt with no vring work, that can return IRQ_NONE even though the ISR was non-zero and the interrupt was handled. Call vp_vring_interrupt() for any queue work, but once the ISR is non-zero return IRQ_HANDLED. Tested with QEMU virtio-blk-pci forced to INTx using vectors=0 and pci=nomsi. On an idle device, 200 config-change interrupts were generated using QMP block_resize. Before this change, irq_handler_exit reported ret=unhandled and /proc/irq/11/spurious increased from 0 to 200 unhandled interrupts. After this change, irq_handler_exit reported ret=handled and the unhandled count remained at 0. The issue was found during an LLM-assisted Quality Playbook review. Fixes: 77cf524654a8 ("virtio_pci: split up vp_interrupt") Suggested-by: Michael S. Tsirkin Assisted-by: LLM Signed-off-by: Andrew Stellman Message-ID: <20260904141318.30278-1-astellman@stellman-greene.com> Signed-off-by: Michael S. Tsirkin --- drivers/virtio/virtio_pci_common.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c index 10371ecbc054..b90c174450b2 100644 --- a/drivers/virtio/virtio_pci_common.c +++ b/drivers/virtio/virtio_pci_common.c @@ -120,7 +120,9 @@ static irqreturn_t vp_interrupt(int irq, void *opaque) if (isr & VIRTIO_PCI_ISR_CONFIG) vp_config_changed(irq, opaque); - return vp_vring_interrupt(irq, opaque); + vp_vring_interrupt(irq, opaque); + + return IRQ_HANDLED; } static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors, From c952e607cb4aa3640e5ae07243d3f609dac94424 Mon Sep 17 00:00:00 2001 From: Dongli Zhang Date: Sun, 2 Aug 2026 10:24:55 -0700 Subject: [PATCH 0899/1198] vhost-scsi: use kvzalloc for vq array allocation vhost_scsi_open() allocates one "struct vhost_scsi_virtqueue" for each virtqueue. With large max_io_vqs values, this array can require a high-order contiguous allocation and trigger a page allocator warning. hv# cat /sys/module/vhost_scsi/parameters/max_io_vqs 256 [ 766.075787] ------------[ cut here ]------------ [ 766.077030] WARNING: mm/page_alloc.c:5280 at __alloc_frozen_pages_noprof+0x32c/0x15c0, CPU#23: qemu-system-x86/5964 ... ... [ 766.080351] RIP: 0010:__alloc_frozen_pages_noprof+0x32c/0x15c0 ... ... [ 766.085813] Call Trace: [ 766.085969] [ 766.086098] ? srso_alias_return_thunk+0x5/0xfbef5 [ 766.086365] ? context_struct_compute_av+0x38a/0x4b0 [ 766.086652] alloc_pages_mpol+0x9f/0x170 [ 766.086883] ___kmalloc_large_node+0xb6/0xd0 [ 766.087124] ? srso_alias_return_thunk+0x5/0xfbef5 [ 766.087389] __kmalloc_large_node_noprof+0x18/0xa0 [ 766.087655] __kmalloc_noprof+0x3a0/0x440 [ 766.087877] ? vhost_scsi_open+0xcb/0x2d0 [vhost_scsi] [ 766.088162] vhost_scsi_open+0xcb/0x2d0 [vhost_scsi] [ 766.088449] misc_open+0x123/0x160 [ 766.088679] chrdev_open+0xb1/0x230 [ 766.088885] ? __pfx_chrdev_open+0x10/0x10 [ 766.089157] do_dentry_open+0x11a/0x470 [ 766.089389] vfs_open+0x29/0xf0 [ 766.089596] path_openat+0x7c0/0x1100 [ 766.089821] do_file_open+0xdd/0x190 [ 766.090032] ? srso_alias_return_thunk+0x5/0xfbef5 [ 766.090332] do_sys_openat2+0x7e/0x100 [ 766.090601] __x64_sys_openat+0x51/0xa0 [ 766.090857] do_syscall_64+0xfe/0x590 [ 766.091087] entry_SYSCALL_64_after_hwframe+0x77/0x7f [ 766.091411] RIP: 0033:0x7f9525a11fa6 The array does not require physical contiguity, so allocate it with kvzalloc_objs() and free it with kvfree(). Signed-off-by: Dongli Zhang Reviewed-by: Mike Christie Reviewed-by: Stefan Hajnoczi Signed-off-by: Michael S. Tsirkin Message-ID: <20260802172534.260047-2-dongli.zhang@oracle.com> --- drivers/vhost/scsi.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 7a1f39a327da..223549313ce9 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -2312,7 +2312,7 @@ static int vhost_scsi_open(struct inode *inode, struct file *f) if (!vs->old_inflight) goto err_inflight; - vs->vqs = kmalloc_objs(*vs->vqs, nvqs, GFP_KERNEL | __GFP_ZERO); + vs->vqs = kvzalloc_objs(*vs->vqs, nvqs); if (!vs->vqs) goto err_vqs; @@ -2348,7 +2348,7 @@ static int vhost_scsi_open(struct inode *inode, struct file *f) return 0; err_local_vqs: - kfree(vs->vqs); + kvfree(vs->vqs); err_vqs: kfree(vs->old_inflight); err_inflight: @@ -2369,7 +2369,7 @@ static int vhost_scsi_release(struct inode *inode, struct file *f) vhost_dev_stop(&vs->dev); vhost_dev_cleanup(&vs->dev); kfree(vs->dev.vqs); - kfree(vs->vqs); + kvfree(vs->vqs); kfree(vs->old_inflight); kvfree(vs); return 0; From 4e3ec5b1b427e02082e8b3491731f8c3bcf85c53 Mon Sep 17 00:00:00 2001 From: Dongli Zhang Date: Sun, 2 Aug 2026 10:24:56 -0700 Subject: [PATCH 0900/1198] vhost-scsi: clamp max_io_vqs module parameter max_io_vqs is currently validated only when a vhost-scsi device is opened. This allows sysfs to show values larger than the driver will actually use, e.g. writing 2048 succeeds even though vhost_scsi_open() later clamps it to VHOST_SCSI_MAX_IO_VQ. This makes the sysfs value differ from the value that will actually be used. hv# echo 2048 > /sys/module/vhost_scsi/parameters/max_io_vqs hv# cat /sys/module/vhost_scsi/parameters/max_io_vqs 2048 [ 315.630495] Invalid max_io_vqs of 2048. Using 1024. Keep accepting out-of-range values for compatibility, but clamp them in the module parameter setter and store the effective value. This preserves the existing behavior that invalid values do not make module loading or sysfs writes fail. It also makes reads report the value that will actually be used. With the parameter value kept in range, remove the duplicate validation from vhost_scsi_open(). Signed-off-by: Dongli Zhang Reviewed-by: Mike Christie Reviewed-by: Stefan Hajnoczi Signed-off-by: Michael S. Tsirkin Message-ID: <20260802172534.260047-3-dongli.zhang@oracle.com> --- drivers/vhost/scsi.c | 43 +++++++++++++++++++++++++++++++++---------- 1 file changed, 33 insertions(+), 10 deletions(-) diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 223549313ce9..4f8c0260bc9e 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -210,7 +210,37 @@ static const int vhost_scsi_bits[] = { #define VHOST_SCSI_MAX_EVENT 128 static unsigned vhost_scsi_max_io_vqs = 128; -module_param_named(max_io_vqs, vhost_scsi_max_io_vqs, uint, 0644); + +static int vhost_scsi_set_max_io_vqs(const char *val, + const struct kernel_param *kp) +{ + unsigned int max_io_vqs; + int ret; + + ret = kstrtouint(val, 0, &max_io_vqs); + if (ret) + return ret; + + if (max_io_vqs > VHOST_SCSI_MAX_IO_VQ) { + pr_err("Invalid max_io_vqs of %u. Using %u.\n", + max_io_vqs, VHOST_SCSI_MAX_IO_VQ); + max_io_vqs = VHOST_SCSI_MAX_IO_VQ; + } else if (!max_io_vqs) { + pr_err("Invalid max_io_vqs of 0. Using 1.\n"); + max_io_vqs = 1; + } + + WRITE_ONCE(vhost_scsi_max_io_vqs, max_io_vqs); + return 0; +} + +static const struct kernel_param_ops vhost_scsi_max_io_vqs_op = { + .set = vhost_scsi_set_max_io_vqs, + .get = param_get_uint, +}; + +module_param_cb(max_io_vqs, &vhost_scsi_max_io_vqs_op, + &vhost_scsi_max_io_vqs, 0644); MODULE_PARM_DESC(max_io_vqs, "Set the max number of IO virtqueues a vhost scsi device can support. The default is 128. The max is 1024."); struct vhost_scsi_virtqueue { @@ -2290,21 +2320,14 @@ static int vhost_scsi_open(struct inode *inode, struct file *f) struct vhost_scsi_virtqueue *svq; struct vhost_scsi *vs; struct vhost_virtqueue **vqs; - int r = -ENOMEM, i, nvqs = vhost_scsi_max_io_vqs; + int r = -ENOMEM, i, nvqs; vs = kvzalloc_obj(*vs); if (!vs) goto err_vs; vs->inline_sg_cnt = vhost_scsi_inline_sg_cnt; - if (nvqs > VHOST_SCSI_MAX_IO_VQ) { - pr_err("Invalid max_io_vqs of %d. Using %d.\n", nvqs, - VHOST_SCSI_MAX_IO_VQ); - nvqs = VHOST_SCSI_MAX_IO_VQ; - } else if (nvqs == 0) { - pr_err("Invalid max_io_vqs of %d. Using 1.\n", nvqs); - nvqs = 1; - } + nvqs = READ_ONCE(vhost_scsi_max_io_vqs); nvqs += VHOST_SCSI_VQ_IO; vs->old_inflight = kmalloc_objs(*vs->old_inflight, nvqs, From 7474f3a61043934e9c351febc56f4d85cd5ddc96 Mon Sep 17 00:00:00 2001 From: Nikhil Date: Sun, 30 Aug 2026 04:24:57 +0530 Subject: [PATCH 0901/1198] vduse: do not take dev->rwsem in the virtqueue kick path vduse_vq_kick() runs in the context of the vdpa .kick_vq callback. With the virtio_vdpa bus driver that callback is invoked by virtqueue_notify() from the virtio device driver, which may be an atomic context: virtio-blk kicks from ->queue_rq(), which blk-mq dispatches under rcu_read_lock() (the tag set does not use BLK_MQ_F_BLOCKING), and virtio-net kicks from its xmit path with the tx queue lock held. Commit b282418bc366 ("vduse: Add suspend") made vduse_vq_kick() take dev->rwsem for reading in order to check dev->suspended. down_read() may sleep, so with CONFIG_DEBUG_ATOMIC_SLEEP the first I/O on a VDUSE-backed virtio-blk device bound to virtio_vdpa now triggers: BUG: sleeping function called from invalid context at kernel/locking/rwsem.c:1573 in_atomic(): 0, irqs_disabled(): 0, non_block: 0, pid: 27, name: kworker/1:0H preempt_count: 0, expected: 0 RCU nest depth: 1, expected: 0 3 locks held by kworker/1:0H/27: #0: ((wq_completion)kblockd){+.+.}-{0:0}, at: process_one_work+0xac7/0xcf0 #1: ((work_completion)(&(&hctx->run_work)->work)){+.+.}-{0:0}, at: process_one_work+0x51f/0xcf0 #2: (rcu_read_lock){....}-{1:3}, at: blk_mq_run_work_fn+0x119/0x220 Workqueue: kblockd blk_mq_run_work_fn Call Trace: dump_stack_lvl+0x80/0xa0 __might_resched+0x231/0x370 down_read+0x73/0x330 vduse_vq_kick+0x30/0x120 virtio_vdpa_notify+0x63/0x80 virtqueue_notify+0x45/0x70 virtio_queue_rq+0x19d/0x300 blk_mq_dispatch_rq_list+0x269/0xe20 __blk_mq_sched_dispatch_requests+0x761/0xa60 blk_mq_sched_dispatch_requests+0x6b/0xc0 blk_mq_run_work_fn+0x143/0x220 process_one_work+0x581/0xcf0 worker_thread+0x2fc/0x5a0 kthread+0x1cc/0x210 ret_from_fork+0x3c4/0x540 ret_from_fork_asm+0x1a/0x30 Without CONFIG_DEBUG_ATOMIC_SLEEP, a kick that finds the rwsem write-locked by vduse_dev_reset() or vduse_vdpa_suspend() blocks inside an RCU read-side critical section. The vhost_vdpa path kicks from the vhost worker, i.e. process context, which is why this went unnoticed. Check dev->suspended under vq->kick_lock instead, which the kick path already takes, and have vduse_vdpa_suspend() cycle every virtqueue's kick_lock after setting the flag. A kick that observed suspended == false has thus finished signalling before suspend returns, which is the guarantee the rwsem used to provide. The flag is now also read outside the rwsem, so access it with READ_ONCE()/WRITE_ONCE(). Fixes: b282418bc366 ("vduse: Add suspend") Signed-off-by: Nikhil Signed-off-by: Michael S. Tsirkin Message-ID: <20260829225457.1037867-1-nikhilljatt@gmail.com> --- drivers/vdpa/vdpa_user/vduse_dev.c | 26 +++++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-) diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index 9891cd2cf712..766789a7bbfa 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -506,7 +506,7 @@ static void vduse_dev_reset(struct vduse_dev *dev) } scoped_guard(rwsem_write, &dev->rwsem) { - dev->suspended = false; + WRITE_ONCE(dev->suspended, false); dev->status = 0; dev->driver_features = 0; dev->generation++; @@ -567,11 +567,17 @@ static int vduse_vdpa_set_vq_address(struct vdpa_device *vdpa, u16 idx, static void vduse_vq_kick(struct vduse_virtqueue *vq) { - guard(rwsem_read)(&vq->dev->rwsem); - if (vq->dev->suspended) + /* + * This runs in the context of the vdpa kick_vq op, which may be + * atomic (e.g. virtio-blk kicks from blk-mq dispatch under + * rcu_read_lock()), so dev->rwsem must not be taken here. + * dev->suspended is checked under kick_lock instead and + * vduse_vdpa_suspend() cycles every kick_lock after setting it. + */ + guard(spinlock)(&vq->kick_lock); + if (READ_ONCE(vq->dev->suspended)) return; - guard(spinlock)(&vq->kick_lock); scoped_guard(spinlock_bh, &vq->ready_lock) if (!vq->ready) return; @@ -946,7 +952,17 @@ static int vduse_vdpa_suspend(struct vdpa_device *vdpa) ret = vduse_dev_msg_sync(dev, &msg); if (ret == 0) { scoped_guard(rwsem_write, &dev->rwsem) - dev->suspended = true; + WRITE_ONCE(dev->suspended, true); + + /* + * Kicks check dev->suspended under kick_lock without taking + * the rwsem: cycle each kick_lock so that no kick that has + * already passed the check is still in flight after this. + */ + for (u32 i = 0; i < dev->vq_num; i++) { + spin_lock(&dev->vqs[i]->kick_lock); + spin_unlock(&dev->vqs[i]->kick_lock); + } cancel_work_sync(&dev->inject); for (u32 i = 0; i < dev->vq_num; i++) From fa2c25b4add57888acfa89e398389e267bff3dcf Mon Sep 17 00:00:00 2001 From: Jia Jia Date: Sun, 30 Aug 2026 10:33:54 +0800 Subject: [PATCH 0902/1198] vduse: validate virtqueue alignment vduse_validate_config() only checks the upper bound of vq_align. Invalid values can therefore reach vring_create_virtqueue_map(). The split-ring helpers use align - 1 as a bit mask, so the alignment must be a non-zero power of two. A zero value makes vring_size() drop the descriptor and available-ring part and vring_init() leave the used ring pointer NULL. The VIRTIO spec requires the used ring to start at an address aligned to at least 4 bytes. Reject values below VRING_USED_ALIGN_SIZE as well as non-power-of-two values before they reach the virtio ring helpers. Opening a virtio-net device created with vq_align=0 triggered: BUG: KASAN: null-ptr-deref in virtqueue_kick_prepare_split+0xe3/0x100 Read of size 2 at addr 0000000000000000 by task systemd-network/1062 Call Trace (relevant frames): dump_stack_lvl print_report kasan_report __asan_load2 virtqueue_kick_prepare_split+0xe3/0x100 virtqueue_kick_prepare+0x40/0x60 try_fill_recv+0x857/0x1250 virtnet_open+0x189/0x460 __dev_open+0x225/0x390 __dev_change_flags+0x368/0x3b0 netif_change_flags+0x56/0xc0 do_setlink.isra.0+0x68c/0x1e30 Validate the value before it reaches the virtio ring helpers. Fixes: c8a6153b6c59 ("vduse: Introduce VDUSE - vDPA Device in Userspace") Signed-off-by: Jia Jia Signed-off-by: Michael S. Tsirkin Message-ID: <20260830023354.115333-1-physicalmtea@gmail.com> --- drivers/vdpa/vdpa_user/vduse_dev.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index 766789a7bbfa..4dea4d6a3855 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -2227,7 +2227,9 @@ static bool vduse_validate_config(struct vduse_dev_config *config, return false; } - if (config->vq_align > PAGE_SIZE) + if (config->vq_align < VRING_USED_ALIGN_SIZE || + !is_power_of_2(config->vq_align) || + config->vq_align > PAGE_SIZE) return false; if (config->config_size > PAGE_SIZE) From e4f4761879a230aa59e569102a6ab9851847d833 Mon Sep 17 00:00:00 2001 From: Jia Jia Date: Fri, 28 Aug 2026 16:57:21 +0800 Subject: [PATCH 0903/1198] vhost: invalidate vring access on IOTLB transitions When VIRTIO_F_ACCESS_PLATFORM changes, cached vring pointers and IOTLB metadata are interpreted in a different address space. Keeping them across the transition can leave stale ring mappings in use. Clearing d->iotlb before taking the VQ locks also lets a worker observe a transient NULL d->iotlb and fall back to d->umem while translating a descriptor. Add a common vhost_clear_device_iotlb() helper for vhost-net and vhost-vsock. Take all VQ mutexes in index order before dropping the device-wide IOTLB, invalidate each VQ's cached ring access and metadata, clear pending IOTLB messages, and free the old table after the handoff. This serializes the transition with workers and prevents mixed address space mappings. On the first direct-to-IOTLB transition, invalidate the cached vring addresses. When an existing device IOTLB is replaced, preserve the GIOVA ring addresses and reset only the metadata cache. After clearing ACCESS_PLATFORM, userspace must configure the vring addresses for the new address mode. vhost_vq_invalidate_access() clears desc, avail, and used together. Treat the VQ as invalidated only when all three are NULL, since a single GIOVA address may legitimately be zero. Fixes: 6b1e6cc7855b ("vhost: new device IOTLB API") Fixes: e13a6915a03f ("vhost/vsock: add IOTLB API support") Suggested-by: Michael S. Tsirkin Signed-off-by: Jia Jia Signed-off-by: Michael S. Tsirkin Message-ID: <20260828085721.57816-1-physicalmtea@gmail.com> --- drivers/vhost/net.c | 2 ++ drivers/vhost/vhost.c | 57 ++++++++++++++++++++++++++++++++++++++++++- drivers/vhost/vhost.h | 1 + drivers/vhost/vsock.c | 2 ++ 4 files changed, 61 insertions(+), 1 deletion(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index c25929dd4425..2cc730729e08 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1705,6 +1705,8 @@ static int vhost_net_set_features(struct vhost_net *n, const u64 *features) if (virtio_features_test_bit(features, VIRTIO_F_ACCESS_PLATFORM)) { if (vhost_init_device_iotlb(&n->dev)) goto out_unlock; + } else { + vhost_clear_device_iotlb(&n->dev); } for (i = 0; i < VHOST_NET_VQ_MAX; ++i) { diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 02588b64b1bb..44cac11b68d2 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -344,6 +344,17 @@ static void __vhost_vq_meta_reset(struct vhost_virtqueue *vq) vq->meta_iotlb[j] = NULL; } +/* Caller must hold the virtqueue mutex. */ +static void vhost_vq_invalidate_access(struct vhost_virtqueue *vq) +{ + vq->desc = NULL; + vq->avail = NULL; + vq->used = NULL; + vq->log_used = false; + vq->log_addr = -1ull; + __vhost_vq_meta_reset(vq); +} + static void vhost_vq_meta_reset(struct vhost_dev *d) { int i; @@ -1946,6 +1957,13 @@ int vq_meta_prefetch(struct vhost_virtqueue *vq) { unsigned int num = vq->num; + /* + * vhost_vq_invalidate_access() clears all three addresses together. + * A single zero address may be a valid GIOVA in IOTLB mode. + */ + if (!vq->desc && !vq->avail && !vq->used) + return 0; + if (!vq->iotlb) return 1; @@ -2315,6 +2333,40 @@ long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg } EXPORT_SYMBOL_GPL(vhost_vring_ioctl); +/* Caller must hold the device mutex. */ +void vhost_clear_device_iotlb(struct vhost_dev *d) +{ + struct vhost_iotlb *iotlb; + int i; + + iotlb = d->iotlb; + if (!iotlb) + return; + + vhost_dev_lock_vqs(d); + + /* + * vhost_dev_lock_vqs() takes all VQ mutexes in index order. Drop the + * device-wide view while they are held, then clear each per-VQ view + * and its cached ring access before releasing the locks. Workers + * cannot observe a mixed address-space state during this handoff. + */ + d->iotlb = NULL; + + for (i = 0; i < d->nvqs; ++i) { + struct vhost_virtqueue *vq = d->vqs[i]; + + vq->iotlb = NULL; + vhost_vq_invalidate_access(vq); + } + + vhost_dev_unlock_vqs(d); + vhost_clear_msg(d); + vhost_iotlb_free(iotlb); + wake_up_interruptible_poll(&d->wait, EPOLLIN | EPOLLRDNORM); +} +EXPORT_SYMBOL_GPL(vhost_clear_device_iotlb); + int vhost_init_device_iotlb(struct vhost_dev *d) { struct vhost_iotlb *niotlb, *oiotlb; @@ -2335,7 +2387,10 @@ int vhost_init_device_iotlb(struct vhost_dev *d) mutex_lock(&vq->mutex); vq->iotlb = niotlb; - __vhost_vq_meta_reset(vq); + if (oiotlb) + __vhost_vq_meta_reset(vq); + else + vhost_vq_invalidate_access(vq); mutex_unlock(&vq->mutex); } diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index fa76b7d44662..39e6121f7525 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -280,6 +280,7 @@ ssize_t vhost_chr_read_iter(struct vhost_dev *dev, struct iov_iter *to, int noblock); ssize_t vhost_chr_write_iter(struct vhost_dev *dev, struct iov_iter *from); +void vhost_clear_device_iotlb(struct vhost_dev *d); int vhost_init_device_iotlb(struct vhost_dev *d); void vhost_iotlb_map_free(struct vhost_iotlb *iotlb, diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 9aaab6bb8061..abed1fbcf66c 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -868,6 +868,8 @@ static int vhost_vsock_set_features(struct vhost_vsock *vsock, u64 features) if ((features & (1ULL << VIRTIO_F_ACCESS_PLATFORM))) { if (vhost_init_device_iotlb(&vsock->dev)) goto err; + } else { + vhost_clear_device_iotlb(&vsock->dev); } vsock->seqpacket_allow = features & (1ULL << VIRTIO_VSOCK_F_SEQPACKET); From 81489b32a21c9360f8750d1fb600155d27452e19 Mon Sep 17 00:00:00 2001 From: Xiong Weimin Date: Wed, 5 Aug 2026 11:29:31 +0800 Subject: [PATCH 0904/1198] virtio_input: reset device if input_register_device() fails Probe marks the device DRIVER_OK with virtio_device_ready() before calling input_register_device(). If registration fails, the error path cleared vi->ready and called del_vqs() while the device was still live, so the device could keep DMA to queues that were already torn down. Match remove/freeze: call virtio_reset_device() on that path before tearing down the virtqueues. Fixes: 271c865161c5 ("Add virtio-input driver.") Signed-off-by: Xiong Weimin Signed-off-by: Michael S. Tsirkin Message-ID: <20260805032931.1606652-1-xiongweimin@kylinos.cn> --- drivers/virtio/virtio_input.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/virtio/virtio_input.c b/drivers/virtio/virtio_input.c index deec24e8e682..1a87be4c88cf 100644 --- a/drivers/virtio/virtio_input.c +++ b/drivers/virtio/virtio_input.c @@ -331,6 +331,7 @@ static int virtinput_probe(struct virtio_device *vdev) spin_lock_irqsave(&vi->lock, flags); vi->ready = false; spin_unlock_irqrestore(&vi->lock, flags); + virtio_reset_device(vdev); err_mt_init_slots: input_free_device(vi->idev); err_input_alloc: From d7808b37da0a619cf1fa541c2384e783fecc2480 Mon Sep 17 00:00:00 2001 From: Karl Mehltretter Date: Sat, 5 Sep 2026 17:20:58 +0200 Subject: [PATCH 0905/1198] virtio_input: stop callbacks before unregistering input device virtinput_remove() unregisters the input device before resetting the virtio device. virtinput_recv_events() drops vi->lock around input_event(), so clearing vi->ready does not stop a callback that passed the entry check. It can still use vi->idev, requeue buffers and kick the queue. Reset first, as virtinput_freeze() already does. With the preceding core change, reset waits for callbacks before input_unregister_device() can free vi->idev. Recheck vi->ready after taking the lock again: keep draining completed events so an input packet is not truncated, but stop requeueing buffers and kicking the queue. With evdev attached, input_unregister_handle() currently waits for an RCU grace period, which also waits out IRQ callbacks. This masks the lifetime bug on PCI and MMIO, but does not protect sleepable callbacks on other transports. Fixes: 271c865161c5 ("Add virtio-input driver.") Assisted-by: LLM Signed-off-by: Karl Mehltretter Signed-off-by: Michael S. Tsirkin Message-ID: <20260905152059.89560-3-kmehltretter@gmail.com> --- drivers/virtio/virtio_input.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/virtio/virtio_input.c b/drivers/virtio/virtio_input.c index 1a87be4c88cf..e3bd0b9616f9 100644 --- a/drivers/virtio/virtio_input.c +++ b/drivers/virtio/virtio_input.c @@ -49,9 +49,12 @@ static void virtinput_recv_events(struct virtqueue *vq) le16_to_cpu(event->code), le32_to_cpu(event->value)); spin_lock_irqsave(&vi->lock, flags); + if (!vi->ready) + continue; virtinput_queue_evtbuf(vi, event); } - virtqueue_kick(vq); + if (vi->ready) + virtqueue_kick(vq); } spin_unlock_irqrestore(&vi->lock, flags); } @@ -351,8 +354,9 @@ static void virtinput_remove(struct virtio_device *vdev) vi->ready = false; spin_unlock_irqrestore(&vi->lock, flags); - input_unregister_device(vi->idev); + /* Callbacks use vi->idev. */ virtio_reset_device(vdev); + input_unregister_device(vi->idev); while ((buf = virtqueue_detach_unused_buf(vi->sts)) != NULL) kfree(buf); vdev->config->del_vqs(vdev); From 74f27fc8642b7e8d139796f8c18ee46df393c2b2 Mon Sep 17 00:00:00 2001 From: Nagamani PV Date: Tue, 1 Sep 2026 17:53:44 +0200 Subject: [PATCH 0906/1198] s390/qeth: allow bridgeport queries despite OS_MISMATCH When HiperSockets interfaces on the same VCHID span different OS families, reads of the sysfs attributes bridge_role and bridge_state fail with -EPERM if bridge port ownership belongs to another OS family. As a result, userspace tools such as 'lszdev -ii' cannot retrieve bridge_role and bridge_state, even though firmware returns valid bridge port data for QUERY_BRIDGE_PORTS requests. The firmware reports IPA_RC_SBP_IQD_OS_MISMATCH (0x0010) to indicate that bridge port ownership belongs to a different OS family. For QUERY_BRIDGE_PORTS operations, firmware still returns valid bridge port data (role=none, state=inactive) together with a primary return code of 0x0000 (success). Allow QUERY_BRIDGE_PORTS requests to return the bridge port data provided by the firmware despite OS_MISMATCH. To make the OS family mismatch visible to userspace, represent the firmware-reported role "none" as "none (OS family mismatch)" while preserving the reported bridge_state. The behavior for non-QUERY bridge port commands is unchanged; SET operations continue to return -EPERM when another OS family owns the bridge port. This restores readability of bridge_role and bridge_state. Fixes: 1b05cf6285c1 ("qeth: Include error message for "OS Mismatch"") Cc: stable@vger.kernel.org Suggested-by: Halil Pasic Reviewed-by: Alexandra Winter Signed-off-by: Nagamani PV Link: https://patch.msgid.link/20260901155344.3561483-1-nagamani@linux.ibm.com Signed-off-by: Jakub Kicinski --- drivers/s390/net/qeth_l2.h | 3 ++- drivers/s390/net/qeth_l2_main.c | 26 ++++++++++++++++++++++---- drivers/s390/net/qeth_l2_sys.c | 7 ++++++- 3 files changed, 30 insertions(+), 6 deletions(-) diff --git a/drivers/s390/net/qeth_l2.h b/drivers/s390/net/qeth_l2.h index 7c646e2fed7e..f94975e970ca 100644 --- a/drivers/s390/net/qeth_l2.h +++ b/drivers/s390/net/qeth_l2.h @@ -13,7 +13,8 @@ extern const struct attribute_group *qeth_l2_attr_groups[]; int qeth_bridgeport_query_ports(struct qeth_card *card, enum qeth_sbp_roles *role, - enum qeth_sbp_states *state); + enum qeth_sbp_states *state, + bool *os_mismatch); int qeth_bridgeport_setrole(struct qeth_card *card, enum qeth_sbp_roles role); int qeth_bridgeport_an_set(struct qeth_card *card, int enable); diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index a9e7d1d637a2..2935c2ecc314 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -1158,7 +1158,7 @@ static void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card) qeth_bridgeport_setrole(card, card->options.sbp.role); /* Let the callback function refresh the stored role value. */ qeth_bridgeport_query_ports(card, &card->options.sbp.role, - NULL); + NULL, NULL); } if (card->options.sbp.hostnotification) { if (qeth_bridgeport_an_set(card, 1)) @@ -1545,6 +1545,7 @@ struct _qeth_sbp_cbctl { struct { enum qeth_sbp_roles *role; enum qeth_sbp_states *state; + bool *os_mismatch; } qports; } data; }; @@ -1721,10 +1722,19 @@ static int qeth_bridgeport_query_ports_cb(struct qeth_card *card, struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data; struct _qeth_sbp_cbctl *cbctl = (struct _qeth_sbp_cbctl *)reply->param; struct qeth_sbp_port_data *qports; + u16 sbp_rc; int rc; QETH_CARD_TEXT(card, 2, "brqprtcb"); - rc = qeth_bridgeport_makerc(card, cmd); + sbp_rc = cmd->data.sbp.hdr.return_code; + + /* on OS family mismatch, query still returns valid port data; + * treat as success + */ + if (sbp_rc == IPA_RC_SBP_IQD_OS_MISMATCH && !cmd->hdr.return_code) + rc = 0; + else + rc = qeth_bridgeport_makerc(card, cmd); if (rc) return rc; @@ -1740,6 +1750,9 @@ static int qeth_bridgeport_query_ports_cb(struct qeth_card *card, if (cbctl->data.qports.state) *cbctl->data.qports.state = qports->entry[0].state; } + if (cbctl->data.qports.os_mismatch) + *cbctl->data.qports.os_mismatch = + (sbp_rc == IPA_RC_SBP_IQD_OS_MISMATCH); return 0; } @@ -1748,13 +1761,17 @@ static int qeth_bridgeport_query_ports_cb(struct qeth_card *card, * @card: qeth_card structure pointer. * @role: Role of the port: 0-none, 1-primary, 2-secondary. * @state: State of the port: 0-inactive, 1-standby, 2-active. + * @os_mismatch: if non-NULL, set to true when firmware reports + * OS family mismatch. * * Returns negative errno-compatible error indication or 0 on success. * - * 'role' and 'state' are not updated in case of hardware operation failure. + * 'role', 'state' and 'os_mismatch' are not updated in case of + * hardware operation failure. */ int qeth_bridgeport_query_ports(struct qeth_card *card, - enum qeth_sbp_roles *role, enum qeth_sbp_states *state) + enum qeth_sbp_roles *role, enum qeth_sbp_states *state, + bool *os_mismatch) { struct qeth_cmd_buffer *iob; struct _qeth_sbp_cbctl cbctl = { @@ -1762,6 +1779,7 @@ int qeth_bridgeport_query_ports(struct qeth_card *card, .qports = { .role = role, .state = state, + .os_mismatch = os_mismatch, }, }, }; diff --git a/drivers/s390/net/qeth_l2_sys.c b/drivers/s390/net/qeth_l2_sys.c index 7f592f912517..7101be62eb1d 100644 --- a/drivers/s390/net/qeth_l2_sys.c +++ b/drivers/s390/net/qeth_l2_sys.c @@ -15,6 +15,7 @@ static ssize_t qeth_bridge_port_role_state_show(struct device *dev, { struct qeth_card *card = dev_get_drvdata(dev); enum qeth_sbp_states state = QETH_SBP_STATE_INACTIVE; + bool os_mismatch = false; int rc = 0; char *word; @@ -25,7 +26,7 @@ static ssize_t qeth_bridge_port_role_state_show(struct device *dev, if (qeth_card_hw_is_reachable(card) && card->options.sbp.supported_funcs) rc = qeth_bridgeport_query_ports(card, - &card->options.sbp.role, &state); + &card->options.sbp.role, &state, &os_mismatch); if (!rc) { if (show_state) switch (state) { @@ -52,6 +53,10 @@ static ssize_t qeth_bridge_port_role_state_show(struct device *dev, if (rc) QETH_CARD_TEXT_(card, 2, "SBP%02x:%02x", card->options.sbp.role, state); + else if (!show_state && + card->options.sbp.role == QETH_SBP_ROLE_NONE && + os_mismatch) + rc = sysfs_emit(buf, "%s (OS family mismatch)\n", word); else rc = sysfs_emit(buf, "%s\n", word); } From 94fd4debd2e3a69cf93e766c8b328a810c228119 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 2 Sep 2026 20:21:50 +0000 Subject: [PATCH 0907/1198] af_unix: Update last skb marker in manage_oob(). Fahad Alharbi reported that blocking recv(MSG_PEEK) could hog CPU due to OOB skb. In the following cases, manage_oob() skips OOB skb(s) and returns NULL for the last recv(MSG_PEEK): socketpair(AF_UNIX, SOCK_STREAM, 0, sk); 1) skb -> OOB skb -> NULL send(sk[0], "ab", 2, MSG_OOB); recv(sk[1], buf, 0, MSG_PEEK); 2) skb -> consumed OOB skb -> NULL send(sk[0], "ab", 2, MSG_OOB); recv(sk[1], buf, 1, MSG_OOB); recv(sk[1], buf, 0, MSG_PEEK); 3) consumed OOB skb -> OOB skb -> NULL send(sk[0], "a", 1, MSG_OOB); recv(sk[1], buf, 0, MSG_OOB); send(sk[0], "b", 1, MSG_OOB); recv(sk[1], buf, 1, MSG_PEEK); Then, @copied is 0 in unix_stream_read_generic() (zero-length buffer, or non-OOB skb is not yet consumed), and unix_stream_data_wait() is called. However, it returns immediately because @last is not updated in unix_stream_read_generic(), and the thread busy-waits for a new skb. Let's update @last in manage_oob(). For MSG_PEEK, @last is updated with the skipped OOB, and for the non-peek case, @last matches the returned value (when !copied) because OOB is unlinked. Note that manage_oob() is inlined and no stack canary is added. Fixes: 22dd70eb2c3d ("af_unix: Don't peek OOB data without MSG_OOB.") Reported-by: Fahad Alharbi Signed-off-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20260902202202.892676-2-kuniyu@google.com Signed-off-by: Jakub Kicinski --- net/unix/af_unix.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 13f9926bf205..6861370062df 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2812,8 +2812,8 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state) return 1; } -static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, - int flags, int copied) +static struct sk_buff *manage_oob(struct sk_buff *skb, struct sk_buff **last, + struct sock *sk, int flags, int copied) { struct sk_buff *read_skb = NULL, *unread_skb = NULL; struct unix_sock *u = unix_sk(sk); @@ -2827,11 +2827,13 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, if (copied && (!u->oob_skb || skb == u->oob_skb)) { skb = NULL; } else if (flags & MSG_PEEK) { + *last = skb; skb = skb_peek_next(skb, &sk->sk_receive_queue); } else { read_skb = skb; skb = skb_peek_next(skb, &sk->sk_receive_queue); __skb_unlink(read_skb, &sk->sk_receive_queue); + *last = skb; } if (!skb) @@ -2850,8 +2852,10 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, __skb_unlink(skb, &sk->sk_receive_queue); unread_skb = skb; skb = skb_peek(&sk->sk_receive_queue); + *last = skb; } } else if (!sock_flag(sk, SOCK_URGINLINE)) { + *last = skb; skb = skb_peek_next(skb, &sk->sk_receive_queue); } @@ -2971,7 +2975,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, again: #if IS_ENABLED(CONFIG_AF_UNIX_OOB) if (skb) { - skb = manage_oob(skb, sk, flags, copied); + skb = manage_oob(skb, &last, sk, flags, copied); if (!skb && copied) { unix_state_unlock(sk); break; From 6e5ee08eb5858d175da6768d75d163817b6a9d4a Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 2 Sep 2026 20:21:51 +0000 Subject: [PATCH 0908/1198] af_unix: Return immediately when manage_oob() returns NULL for 0-length buffer. Fahad Alharbi reported that recv(0, MSG_PEEK) triggers busy-wait in unix_stream_read_generic() if recv() is blocking and the last skb in the queue is MSG_OOB skb. In such a situation, TCP returns 0 immediately regardless of blocking or non-blocking. Let's follow the behaviour. Fixes: 314001f0bf92 ("af_unix: Add OOB support") Reported-by: Fahad Alharbi Signed-off-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20260902202202.892676-3-kuniyu@google.com Signed-off-by: Jakub Kicinski --- net/unix/af_unix.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 6861370062df..2da1017f8873 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2976,7 +2976,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, #if IS_ENABLED(CONFIG_AF_UNIX_OOB) if (skb) { skb = manage_oob(skb, &last, sk, flags, copied); - if (!skb && copied) { + if (!skb && (copied || !state->size)) { unix_state_unlock(sk); break; } From ca0b0a86873e8ded39b7fb196dbdc615d9a9a0e4 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 2 Sep 2026 20:21:52 +0000 Subject: [PATCH 0909/1198] selftest: af_unix: Add zero-buffer test for msg_oob.c The previous patches fixed two issues related to zero-length buffer with MSG_PEEK for MSG_OOB skb. Let's add corresponding tests in msg_oob.c. Without this series: # FAILED: 50 / 60 tests passed. # Totals: pass:50 fail:10 xfail:0 xpass:0 skip:0 error:0 With this series: # PASSED: 60 / 60 tests passed. # Totals: pass:60 fail:0 xfail:0 xpass:0 skip:0 error:0 Signed-off-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20260902202202.892676-4-kuniyu@google.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/af_unix/msg_oob.c | 67 +++++++++++++++++++ 1 file changed, 67 insertions(+) diff --git a/tools/testing/selftests/net/af_unix/msg_oob.c b/tools/testing/selftests/net/af_unix/msg_oob.c index 1b499d56656c..f051d79f7a8e 100644 --- a/tools/testing/selftests/net/af_unix/msg_oob.c +++ b/tools/testing/selftests/net/af_unix/msg_oob.c @@ -290,6 +290,25 @@ static void __setinlinepair(struct __test_metadata *_metadata, } } +static void __setblockingpair(struct __test_metadata *_metadata, + FIXTURE_DATA(msg_oob) *self) +{ + int i; + + for (i = 0; i < 2; i++) { + int ret, old_flags, flags; + + old_flags = fcntl(self->fd[i * 2 + 1], F_GETFL, 0); + ASSERT_NE(-1, old_flags); + + ret = fcntl(self->fd[i * 2 + 1], F_SETFL, old_flags & ~O_NONBLOCK); + ASSERT_EQ(0, ret); + + flags = fcntl(self->fd[i * 2 + 1], F_GETFL, 0); + ASSERT_EQ(old_flags & ~O_NONBLOCK, flags); + } +} + static void __siocatmarkpair(struct __test_metadata *_metadata, FIXTURE_DATA(msg_oob) *self, bool oob_head) @@ -347,6 +366,9 @@ static void __resetpair(struct __test_metadata *_metadata, #define setinlinepair() \ __setinlinepair(_metadata, self) +#define setblockingpair() \ + __setblockingpair(_metadata, self) + #define resetpair(reset) \ __resetpair(_metadata, self, variant, reset) @@ -888,4 +910,49 @@ TEST_F(msg_oob, inline_ex_oob_siocatmark) resetpair(true); } +TEST_F(msg_oob, zero_buf_oob) +{ + sendpair("a", 1, MSG_OOB); + recvpair("", 0, 0, 0); +} + +TEST_F(msg_oob, zero_buf_oob_blocking) +{ + sendpair("a", 1, MSG_OOB); + setblockingpair(); + recvpair("", 0, 0, 0); +} + +TEST_F(msg_oob, zero_buf_non_oob_oob) +{ + sendpair("ab", 2, MSG_OOB); + recvpair("", 0, 0, 0); +} + +TEST_F(msg_oob, zero_buf_non_oob_oob_blocking) +{ + sendpair("ab", 2, MSG_OOB); + setblockingpair(); + recvpair("", 0, 0, 0); +} + +TEST_F(msg_oob, zero_buf_ex_oob_oob) +{ + sendpair("a", 1, MSG_OOB); + recvpair("a", 1, 1, MSG_OOB); + + sendpair("b", 1, MSG_OOB); + recvpair("", 0, 0, 0); +} + +TEST_F(msg_oob, zero_buf_ex_oob_oob_blocking) +{ + sendpair("a", 1, MSG_OOB); + recvpair("a", 1, 1, MSG_OOB); + + sendpair("b", 1, MSG_OOB); + setblockingpair(); + recvpair("", 0, 0, 0); +} + TEST_HARNESS_MAIN From b83641e0ab8b20eefcc4cdc5a059f897375291a2 Mon Sep 17 00:00:00 2001 From: Alice Mikityanska Date: Tue, 1 Sep 2026 22:57:11 +0300 Subject: [PATCH 0910/1198] net: ipv4: Fix UDP length overflow with PMTU discover and big MTU This commit bounds cork->base.fragsize to IP_MAX_MTU to avoid a possible overflow of UDP length that triggers a WARN in udp_set_len_short when setsockopt IP_MTU_DISCOVER is set to IP_PMTUDISC_PROBE, and a large packet is sent over a netdev with an unusually large MTU. Steps to reproduce: 1. Set device MTU bigger than IP_MAX_MTU + 20. cork->base.fragsize will be set to that MTU in ip_setup_cork. 2. Set IP_MTU_DISCOVER to IP_PMTUDISC_PROBE. It lets maxnonfragsize be set to device MTU (cork->fragsize) in __ip_append_data, rather than to IP_MAX_MTU. 3. Send 65528 bytes of payload (+8 bytes of UDP header, +20 bytes of IPv4 header). Device MTU allows it (it's only one byte bigger than IP_MAX_MTU + IPv4 header, and the device MTU is bigger than that). 4. The UDP length in the built packet is 65536, which overflows the 16-bit length field and triggers the WARN in udp_set_len_short. Note: IP_PMTUDISC_DO with IPv4 is safe, because ip_dst_mtu_maybe_forward always clamps at IP_MAX_MTU, unlike ip6_dst_mtu_maybe_forward. The Fixes tag points at the first commit where I could reproduce the overflow with IPv4 and IP_PMTUDISC_PROBE. Fixes: daba287b299e ("ipv4: fix DO and PROBE pmtu mode regarding local fragmentation with UFO/CORK") Reported-by: syzbot+ce13c07d96d04716eaa2@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/6a6a966c.86abc875.e5c3d.0054.GAE@google.com/ Signed-off-by: Alice Mikityanska Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20260901195714.673548-2-alice.kernel@fastmail.im Signed-off-by: Jakub Kicinski --- net/ipv4/ip_output.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 74e095b6b7ca..a24cc8ee11d3 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1303,6 +1303,7 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, cork->fragsize = ip_sk_use_pmtu(sk) ? dst4_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu); + cork->fragsize = min(cork->fragsize, IP_MAX_MTU); if (!inetdev_valid_mtu(cork->fragsize)) return -ENETUNREACH; From 0ae10b6be49b425827659b23bcce498f80eb7182 Mon Sep 17 00:00:00 2001 From: Alice Mikityanska Date: Tue, 1 Sep 2026 22:57:12 +0300 Subject: [PATCH 0911/1198] net: ipv6: Fix UDP length overflow with PMTU discover and big MTU This commit bounds cork->base.fragsize to IP6_MAX_MTU for UDP sockets to avoid a possible overflow of UDP length that triggers a WARN in udp_set_len_short when setsockopt IPV6_MTU_DISCOVER is set to IPV6_PMTUDISC_DO or IPV6_PMTUDISC_PROBE, and a large packet is sent over a netdev with an unusually large MTU. Steps to reproduce (included in the new selftest): 1. Set device MTU bigger than IP6_MAX_MTU. cork->base.fragsize will be set to that MTU in ip6_setup_cork. 2. Set IPV6_MTU_DISCOVER to IPV6_PMTUDISC_PROBE or IPV6_PMTUDISC_DO. It lets maxnonfragsize be set to device MTU (cork->fragsize) in __ip6_append_data, rather than to IP6_MAX_MTU. 3. Send 65528 bytes of payload (+8 bytes of UDP header, +40 bytes of IPv6 header). Device MTU allows it (it's only one byte bigger than IP6_MAX_MTU, and the device MTU is bigger than that). 4. The UDP length in the built packet is 65536, which overflows the 16-bit length field and triggers the WARN in udp_set_len_short. To avoid breaking sending UDP jumbograms over raw IPv6 sockets, limit the change to UDP sockets only. The original overflow bug with IPv6 and IPV6_PMTUDISC_DO seems to predate git history (verified reproduction on 2.6.21), was fixed later, and then reappeared in commit 427faee167bc ("net: ipv6: introduce ip6_dst_mtu_maybe_forward"), which is chosen as the Fixes tag here. The overflow with IPV6_PMTUDISC_PROBE reproduces since its introduction in commit 628a5c561890 ("[INET]: Add IP(V6)_PMTUDISC_RPOBE"). Fixes: 427faee167bc ("net: ipv6: introduce ip6_dst_mtu_maybe_forward") Reported-by: syzbot+ce13c07d96d04716eaa2@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/6a6a966c.86abc875.e5c3d.0054.GAE@google.com/ Signed-off-by: Alice Mikityanska Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20260901195714.673548-3-alice.kernel@fastmail.im Signed-off-by: Jakub Kicinski --- net/ipv6/ip6_output.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 8fc4766c8da9..550965058991 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1432,6 +1432,8 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, if (frag_size && frag_size < mtu) mtu = frag_size; + if (sk_is_udp(sk)) + mtu = min(mtu, IP6_MAX_MTU); cork->base.fragsize = mtu; cork->base.gso_size = ipc6->gso_size; cork->base.tx_flags = 0; From 18a9a4342136c5ae954b37d961c374d369615de2 Mon Sep 17 00:00:00 2001 From: Alice Mikityanska Date: Tue, 1 Sep 2026 22:57:13 +0300 Subject: [PATCH 0912/1198] selftests: net: Test UDP length overflow with PMTU discover and big MTU Two previous commits fixed overflow of UDP length when setsockopt IP(V6)_MTU_DISCOVER is set to IPV6_PMTUDISC_DO or IP(V6)_PMTUDISC_PROBE, and a large packet is sent over a netdev with an unusually large MTU. This commit adds the selftests that replicate the described steps to reproduce for IPv6 and IPv4, and also one more test that ensures that sending UDP jumbograms over a raw socket is still possible after the fix. Signed-off-by: Alice Mikityanska Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20260901195714.673548-4-alice.kernel@fastmail.im Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/Makefile | 1 + tools/testing/selftests/net/cork_fragsize.py | 187 +++++++++++++++++++ 2 files changed, 188 insertions(+) create mode 100755 tools/testing/selftests/net/cork_fragsize.py diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 517c09d60bef..3ee3378f8b26 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -25,6 +25,7 @@ TEST_PROGS := \ cmsg_so_mark.sh \ cmsg_so_priority.sh \ cmsg_time.sh \ + cork_fragsize.py \ double_udp_encap.sh \ drop_monitor_tests.sh \ ecmp_rehash.sh \ diff --git a/tools/testing/selftests/net/cork_fragsize.py b/tools/testing/selftests/net/cork_fragsize.py new file mode 100755 index 000000000000..7afd643d07ec --- /dev/null +++ b/tools/testing/selftests/net/cork_fragsize.py @@ -0,0 +1,187 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +'''Test possible UDP length overflow in udp_send_skb/udp_v6_send_skb.''' + +import errno +import gzip +import os +import socket +import struct +import subprocess +from contextlib import contextmanager + +from lib.py import ( + KsftNamedVariant, + KsftSkipEx, + NetNS, + NetNSEnter, + defer, + ip, + ksft_eq, + ksft_exit, + ksft_pr, + ksft_raises, + ksft_run, + ksft_true, + ksft_variants, +) + +IP_MTU_DISCOVER = 10 +IP_PMTUDISC_PROBE = 3 +IPV6_MTU_DISCOVER = 23 +IPV6_PMTUDISC_DO = 2 +IPV6_PMTUDISC_PROBE = 3 +IPV6_TLV_JUMBO = 194 + + +def check_kernel_config(option: str) -> bool | None: + ''' + Check whether the option is enabled in the config of the running kernel. + Returns None if the config is not found; otherwise returns True/False + depending on the option value in the config. + ''' + + for filename, method in [ + ('/proc/config.gz', gzip.open), + (f'/boot/config-{os.uname().release}', open), + ]: + try: + with method(filename, 'rt') as config: + for line in config: + if line.rstrip() == f'{option}=y': + return True + return False + except OSError: + continue + return None + + +def assert_debug_kernel() -> None: + ''' + Skip the test if CONFIG_DEBUG_NET is not set in the kernel config. + ''' + + res = check_kernel_config('CONFIG_DEBUG_NET') + if res is None: + ksft_pr("WARN: Can't read kernel config; assuming debug kernel, and running the test") + elif not res: + raise KsftSkipEx('CONFIG_DEBUG_NET is not set') + + +def check_dmesg_clean(func: str) -> bool: + ''' + Check if the given function produced a WARN in dmesg. + ''' + + with subprocess.Popen(['dmesg'], stdout=subprocess.PIPE) as dmesg: + res = subprocess.run(['grep', '-q', f'WARNING:.*{func}'], stdin=dmesg.stdout, check=False) + return res.returncode != 0 and dmesg.returncode == 0 + + +@contextmanager +def dummy_netdev(ns: NetNS, mtu: int, ipv6: bool) -> None: + ''' + Create a dummy netdev inside the given namespace, and tune it for the test. + ''' + + ip('link add dummy type dummy', ns=ns) + with defer(ip, 'link del dummy', ns=ns): + ip(f'link set dummy mtu {mtu}', ns=ns) + ip('link set dummy up', ns=ns) + flag = '-6' if ipv6 else '' + nodad = 'nodad' if ipv6 else '' + local = 'fd00::1/64' if ipv6 else '10.0.0.1/24' + remote = 'fd00::2' if ipv6 else '10.0.0.2' + ip(f'{flag} addr add {local} dev dummy {nodad}', ns=ns) + ip(f'{flag} neigh add {remote} lladdr 02:00:00:00:00:02 dev dummy nud permanent', ns=ns) + yield + + +@ksft_variants([ + KsftNamedVariant( + 'ipv6', + True, + socket.AF_INET6, + (socket.IPPROTO_IPV6, IPV6_MTU_DISCOVER, IPV6_PMTUDISC_DO), + 'fd00::2', + 'udp_v6_send_skb', + ), + KsftNamedVariant( + 'ipv4', + False, + socket.AF_INET, + (socket.IPPROTO_IP, IP_MTU_DISCOVER, IP_PMTUDISC_PROBE), + '10.0.0.2', + 'udp_send_skb', + ), +]) +def test_udp( + ipv6: bool, + af: socket.AddressFamily, + sockopts: tuple[int, int, int], + destip: str, + func: str +) -> None: + ''' + Test that sending an oversized UDP packet over a UDP socket doesn't overflow + the 16-bit length field in the UDP header, which could happen on older + kernels in udp_send_skb/udp_v6_send_skb. + + IPv4: The packet will be dropped with EMSGSIZE, but the overflow could + happen before it happens. The only way to test this is to check dmesg on + CONFIG_DEBUG_NET=y kernels that have udp_set_len_short with the warning. + + IPv6: The packet will be dropped with EMSGSIZE on fixed kernels, and will be + sent corrupted on older kernels. Test both: sendto must return EMSGSIZE, and + dmesg must be clean of warnings on CONFIG_DEBUG_NET=y kernels. + ''' + + if not ipv6: + assert_debug_kernel() + + with ( + NetNS() as ns, + dummy_netdev(ns, 65556 + 20 * ipv6, ipv6), + NetNSEnter(ns), + socket.socket(af, socket.SOCK_DGRAM) as fd, + ): + fd.setsockopt(*sockopts) + with ksft_raises(OSError) as e: + fd.sendto(b' ' * 65528, (destip, 1234)) + # IPv6: EMSGSIZE happens on kernels with the fix. + # IPv4: EMSGSIZE happens on both fixed and unfixed kernels, after the + # WARN is printed - ignore it and rely on the dmesg check. + if e.exception is not None: + ksft_eq(e.exception.errno, errno.EMSGSIZE) + + ksft_true(check_dmesg_clean(func), 'WARNING detected in dmesg') + + +def test_ipv6_jumbo() -> None: + ''' + Test that sending UDP jumbograms over a raw IPv6 socket works, despite + having the fix for oversized UDP packets. sendto must not raise an OSError + exception (when raised, the test fails automatically). + ''' + + with ( + NetNS() as ns, + dummy_netdev(ns, 65584, True), + NetNSEnter(ns), + socket.socket(socket.AF_INET6, socket.SOCK_RAW, socket.IPPROTO_UDP) as fd, + ): + hopopts = struct.pack('!BBBBI', 0, 0, IPV6_TLV_JUMBO, 4, 65544) + fd.setsockopt(socket.IPPROTO_IPV6, socket.IPV6_HOPOPTS, hopopts) + fd.setsockopt(socket.IPPROTO_IPV6, socket.IPV6_CHECKSUM, 6) + fd.setsockopt(socket.IPPROTO_IPV6, IPV6_MTU_DISCOVER, IPV6_PMTUDISC_PROBE) + udp = struct.pack('!HHHH', 1234, 1234, 0, 0) + b' ' * 65528 + fd.sendto(udp, ('fd00::2', 0)) + + +if __name__ == "__main__": + ksft_run([ + test_udp, + test_ipv6_jumbo, + ]) + ksft_exit() From 199271ebc71c1e0913b2fad988a7bff330a8828a Mon Sep 17 00:00:00 2001 From: Alice Mikityanska Date: Tue, 1 Sep 2026 22:57:14 +0300 Subject: [PATCH 0913/1198] net: ipv6: Clamp to IP6_MAX_MTU in ip6_dst_mtu_maybe_forward Commit 427faee167bc ("net: ipv6: introduce ip6_dst_mtu_maybe_forward") dropped the IP6_MAX_MTU clamp that used to be present in ip6_mtu(). A similar IPv4 commit ac6627a28dbf ("net: ipv4: Consolidate ipv4_mtu and ip_dst_mtu_maybe_forward") preserves the IP_MAX_MTU clamp. Restore the upper bound in the IPv6 flow to avoid potential 16-bit overflows in forwarding paths. Fixes: 427faee167bc ("net: ipv6: introduce ip6_dst_mtu_maybe_forward") Signed-off-by: Alice Mikityanska Suggested-by: Willem de Bruijn Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20260901195714.673548-5-alice.kernel@fastmail.im Signed-off-by: Jakub Kicinski --- include/net/ip6_route.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index c69f1c871922..b9e8d2b759e9 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -384,6 +384,8 @@ static inline unsigned int ip6_dst_mtu_maybe_forward(const struct dst_entry *dst rcu_read_unlock(); out: + mtu = min_t(unsigned int, mtu, IP6_MAX_MTU); + return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } From 4ff75f130d1b84f65a6f35a8a0cbca52130127ef Mon Sep 17 00:00:00 2001 From: Sebastian Sjoholm Date: Thu, 3 Sep 2026 20:00:44 +0200 Subject: [PATCH 0914/1198] net: usb: qmi_wwan: add Quectel RG660QB Add support for the Quectel RG660QB 5G module (USB ID 2c7c:013d). Its QMI interface (interface 4) uses class/subclass/protocol ff/ff/ff like the other recent Quectel modules, so match it the same way. The remaining interfaces are handled by the option driver. Tested with an early sample of the module on a Quectel 5G EVB connected over USB 3 to a Raspberry Pi 5: qmicli talks to the module via /dev/cdc-wdm0. Signed-off-by: Sebastian Sjoholm Link: https://patch.msgid.link/20260903180044.6179-1-sebastian.sjoholm@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/usb/qmi_wwan.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index fdfdcf24ddcf..f51cf9cb9421 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1084,6 +1084,7 @@ static const struct usb_device_id products[] = { }, {QMI_MATCH_FF_FF_FF(0x2c7c, 0x0122)}, /* Quectel RG650V */ {QMI_MATCH_FF_FF_FF(0x2c7c, 0x0125)}, /* Quectel EC25, EC20 R2.0 Mini PCIe */ + {QMI_MATCH_FF_FF_FF(0x2c7c, 0x013d)}, /* Quectel RG660QB */ {QMI_MATCH_FF_FF_FF(0x2c7c, 0x0306)}, /* Quectel EP06/EG06/EM06 */ {QMI_MATCH_FF_FF_FF(0x2c7c, 0x0512)}, /* Quectel EG12/EM12 */ {QMI_MATCH_FF_FF_FF(0x2c7c, 0x0620)}, /* Quectel EM160R-GL */ From 8d6cd188508513503805c156165de38e4e4a8615 Mon Sep 17 00:00:00 2001 From: Zhiling Zou Date: Thu, 3 Sep 2026 14:23:03 +0800 Subject: [PATCH 0915/1198] ipv6: flowlabel: cap duplicate leases per socket ipv6_flowlabel_get() allocates an ipv6_fl_socklist entry for every successful GET. The recheck path for a compatible existing flowlabel links another lease without applying any lease admission check. Repeated GET requests for one shareable label can therefore grow a socket's lease list without bound. Reject a new unprivileged lease once the socket already holds FL_MAX_PER_SOCK leases. Check this on the shared recheck path so reuse of a globally interned label, including the fl_intern() collision path, is covered as well. New-label admission remains under the existing mem_check() policy. Use capable(CAP_NET_ADMIN) rather than ns_capable(), matching mem_check(). An unprivileged user must not bypass the cap by creating a user namespace and a netns where they have CAP_NET_ADMIN, which would still consume host memory. Check the capability only when the socket reaches the limit, so successful unprivileged GET requests below the cap do not generate a capability audit. Do the admission check before updating linger and expires so a rejected GET does not refresh the shared label, matching the existing socket-list allocation failure path. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable@vger.kernel.org Reported-by: Vega Suggested-by: Ido Schimmel Signed-off-by: Zhiling Zou Reviewed-by: Eric Dumazet Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/83f8535972ff6e3741548476a1d50dec24c758be.1788415194.git.zhilinz@nebusec.ai Signed-off-by: Jakub Kicinski --- net/ipv6/ip6_flowlabel.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 1ab5ad0dcf24..006585dc8b5c 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -461,6 +461,21 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq, return NULL; } +static bool fl_sock_at_lease_limit(const struct sock *sk) +{ + const struct ipv6_fl_socklist *sfl; + int count = 0; + + rcu_read_lock(); + for_each_sk_fl_rcu(sk, sfl) { + if (++count >= FL_MAX_PER_SOCK) + break; + } + rcu_read_unlock(); + + return count >= FL_MAX_PER_SOCK; +} + static int mem_check(struct sock *sk) { const int unpriv_total_limit = FL_MAX_SIZE - (FL_MAX_SIZE / 4); @@ -679,6 +694,10 @@ static int ipv6_flowlabel_get(struct sock *sk, struct in6_flowlabel_req *freq, err = -ENOMEM; if (!sfl1) goto release; + err = -ENOBUFS; + if (fl_sock_at_lease_limit(sk) && + !capable(CAP_NET_ADMIN)) + goto release; if (fl->linger > fl1->linger) fl1->linger = fl->linger; if ((long)(fl->expires - fl1->expires) > 0) From 9868f5c077dfe0b606331f2e782484f91a5789a5 Mon Sep 17 00:00:00 2001 From: Dinh Nguyen Date: Wed, 17 Jun 2026 11:43:03 -0500 Subject: [PATCH 0916/1198] EDAC/altera: Use parent device for devres in altr_portb_setup() Anchor the devres group and the devm-managed IRQ requests in altr_portb_setup() to the actual parent device (device->edac->dev) instead of the embedded struct device inside the copied per-port altr_edac_device_dev. This keeps devres_open_group(), devm_request_irq(), devres_remove_group() and devres_release_group() all referring to the same long-lived device so the group and the resources allocated inside it are torn down together. Fixes: 911049845d70 ("EDAC, altera: Add Arria10 SD-MMC EDAC support") Closes: https://sashiko.dev/#/patchset/20260503212558.2811480-1-dbgh9129%40gmail.com Assisted-by: LLM Signed-off-by: Dinh Nguyen Signed-off-by: Borislav Petkov (AMD) Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260617164303.585555-1-dinguyen@kernel.org --- drivers/edac/altera_edac.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c index 1d1e2b5ca14c..68846f583eee 100644 --- a/drivers/edac/altera_edac.c +++ b/drivers/edac/altera_edac.c @@ -1534,7 +1534,7 @@ static int altr_portb_setup(struct altr_edac_device_dev *device) altdev = dci->pvt_info; *altdev = *device; - if (!devres_open_group(&altdev->ddev, altr_portb_setup, GFP_KERNEL)) + if (!devres_open_group(device->edac->dev, altr_portb_setup, GFP_KERNEL)) return -ENOMEM; /* Update PortB specific values */ @@ -1562,7 +1562,7 @@ static int altr_portb_setup(struct altr_edac_device_dev *device) rc = -ENODEV; goto err_release_group_1; } - rc = devm_request_irq(&altdev->ddev, altdev->sb_irq, + rc = devm_request_irq(device->edac->dev, altdev->sb_irq, prv->ecc_irq_handler, IRQF_TRIGGER_HIGH, ecc_name, altdev); if (rc) { @@ -1584,7 +1584,7 @@ static int altr_portb_setup(struct altr_edac_device_dev *device) rc = -ENODEV; goto err_release_group_1; } - rc = devm_request_irq(&altdev->ddev, altdev->db_irq, + rc = devm_request_irq(device->edac->dev, altdev->db_irq, prv->ecc_irq_handler, IRQF_TRIGGER_HIGH, ecc_name, altdev); if (rc) { @@ -1604,13 +1604,13 @@ static int altr_portb_setup(struct altr_edac_device_dev *device) list_add(&altdev->next, &altdev->edac->a10_ecc_devices); - devres_remove_group(&altdev->ddev, altr_portb_setup); + devres_remove_group(device->edac->dev, altr_portb_setup); return 0; err_release_group_1: edac_device_free_ctl_info(dci); - devres_release_group(&altdev->ddev, altr_portb_setup); + devres_release_group(device->edac->dev, altr_portb_setup); edac_printk(KERN_ERR, EDAC_DEVICE, "%s:Error setting up EDAC device: %d\n", ecc_name, rc); return rc; From aefdbd574a362dcf7569bada6d72f64a006b9fb9 Mon Sep 17 00:00:00 2001 From: Jason Andryuk Date: Tue, 25 Aug 2026 17:48:03 -0400 Subject: [PATCH 0917/1198] x86/amd_node: Fix potential NULL pointer dereference amd_smn_read/write() are exported functions around __amd_smn_rw(), so they are always available even if amd_smn_init() fails. In that case, 'amd_roots' is NULL and __amd_smn_rw() will access uninitialized memory. Then, commit: 83518453074d ("x86/amd_node: Add SMN offsets to exclusive region access") added the 'smn_exclusive' flag, which indicated the calls to pci_request_config_region_exclusive() succeeded, to prevent concurrent userspace access. Commit: 0a4b61d9c2e4 ("x86/amd_node: Fix AMD root device caching") re-ordered initialization so pci_request_config_region_exclusive() is called earlier and a failure exits amd_smn_init() before allocating 'amd_roots'. The setting of 'smn_exclusive' moved to the end of amd_smn_init(), after 'amd_roots' is allocated. It became redundant and can be removed. Replace 'smn_exclusive' with directly checking 'amd_roots', to fix a potential NULL pointer dereference and to simplify the logic. [ bp: Reorg commit message, touchup comment. ] [ mingo: Rebase & further touchups. ] Fixes: 77466b798d59 ("x86/amd_node: Remove dependency on AMD_NB") Signed-off-by: Jason Andryuk Signed-off-by: Borislav Petkov (AMD) Signed-off-by: Ingo Molnar Reviewed-by: Yazen Ghannam Reviewed-by: Mario Limonciello (AMD) Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260825214805.39148-3-jason.andryuk@amd.com --- arch/x86/kernel/amd_node.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/arch/x86/kernel/amd_node.c b/arch/x86/kernel/amd_node.c index 408b9fd48349..762585775b5a 100644 --- a/arch/x86/kernel/amd_node.c +++ b/arch/x86/kernel/amd_node.c @@ -38,7 +38,6 @@ static struct pci_dev **amd_roots; /* Protect the PCI config register pairs used for SMN. */ static DEFINE_MUTEX(smn_mutex); -static bool smn_exclusive; #define SMN_INDEX_OFFSET 0x60 #define SMN_DATA_OFFSET 0x64 @@ -91,11 +90,16 @@ static int __amd_smn_rw(u8 i_off, u8 d_off, u16 node, u32 address, u32 *value, b if (node >= amd_num_nodes()) return err; - root = amd_roots[node]; - if (!root) + /* + * Uninitialized amd_roots indicates pci_request_config_region_exclusive() + * didn't run or failed and thus the kernel cannot rely on having + * exclusive access to SMN registers so prevent that. + */ + if (!amd_roots) return err; - if (!smn_exclusive) + root = amd_roots[node]; + if (!root) return err; guard(mutex)(&smn_mutex); @@ -313,8 +317,6 @@ static int __init amd_smn_init(void) debugfs_create_file("value", 0600, debugfs_dir, NULL, &smn_value_fops); } - smn_exclusive = true; - return 0; } From d2929113b15bfc06793b852aeba3d2db6d79fcc9 Mon Sep 17 00:00:00 2001 From: Jasjeet Rangi Date: Wed, 12 Aug 2026 16:15:13 -0600 Subject: [PATCH 0918/1198] x86/MCE/AMD: Fix inverted interrupt enablement during storm handling mce_amd_handle_storm() currently does the opposite of what storm handling needs: it enables thresholding interrupts when a storm is detected and disables them when the storm subsides. Flip the "on" function argument before passing it to threshold_restart_bank() as it should have been done. To clarify: "on" to mce_handle_storm() means, the storm is on now when "on" is true, and off when "on" is false. [ bp: Simplify. ] Fixes: 5c4663ed1eac ("x86/mce: Handle AMD threshold interrupt storms") Signed-off-by: Jasjeet Rangi Signed-off-by: Borislav Petkov (AMD) Signed-off-by: Ingo Molnar Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260812221514.598842-2-jrangi@purestorage.com --- arch/x86/kernel/cpu/mce/amd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index f916fb4c5d13..1cc20b855b7e 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -865,7 +865,7 @@ static void amd_deferred_error_interrupt(void) void mce_amd_handle_storm(unsigned int bank, bool on) { - threshold_restart_bank(bank, on); + threshold_restart_bank(bank, !on); } static void amd_reset_thr_limit(unsigned int bank) From 48a4ee65e677559776349128e6a81a6041986c99 Mon Sep 17 00:00:00 2001 From: Linfeng Sun Date: Tue, 8 Sep 2026 15:31:51 +0800 Subject: [PATCH 0919/1198] vduse: return compat ioctl results directly The compat handler handles VDUSE_IOTLB_GET_FD and VDUSE_VQ_GET_INFO, but then calls the native handler. Their different command sizes make native dispatch return -ENOIOCTLCMD. For GET_FD, this overwrites receive_fd()'s return value after the descriptor is installed, leaking one fd per call. Return handled compat results directly and use native dispatch only for other commands. Fixes: 455a2a1af926 ("vduse: fix compat handling for VDUSE_IOTLB_GET_FD/VDUSE_VQ_GET_INFO") Signed-off-by: Linfeng Sun Signed-off-by: Michael S. Tsirkin Message-ID: <20260908-fix-vduse_dev_compat_ioctl-v1-1-62264d9bfb8d@gmail.com> --- drivers/vdpa/vdpa_user/vduse_dev.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index 4dea4d6a3855..49a231bdf948 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -1882,11 +1882,11 @@ static long vduse_dev_compat_ioctl(struct file *file, unsigned int cmd, break; } default: - ret = -ENOIOCTLCMD; - break; + return vduse_dev_ioctl(file, cmd, + (unsigned long)compat_ptr(arg)); } - return vduse_dev_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); + return ret; } #else #define vduse_dev_compat_ioctl compat_ptr_ioctl From 4e17b5007b6664559cdad2b2fe270526cf786b5b Mon Sep 17 00:00:00 2001 From: Joe Damato Date: Tue, 1 Sep 2026 18:56:44 -0700 Subject: [PATCH 0920/1198] bnxt_en: Only restore LRO if the device supports TPA With a P5+ device with firmware that reports max_aggs_supported == 0, it is possible to make LRO settable by attaching and detaching an XDP program even though the device does not support TPA. Fix this by testing BNXT_SUPPORTS_TPA before restoring the feature bit. Fixes: f0aa6a37a3db ("eth: bnxt: always recalculate features after XDP clearing, fix null-deref") Reported-by: Sashiko Link: https://netdev-ai.bots.linux.dev/sashiko/#/patchset/20260828190900.1767611-1-joe%40dama.to Cc: stable@vger.kernel.org Signed-off-by: Joe Damato Link: https://patch.msgid.link/20260902015652.2421609-2-joe@dama.to Signed-off-by: Paolo Abeni --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 8c6e2ee6bee4..343d70a98134 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -5026,7 +5026,8 @@ void bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode) bnxt_get_max_rings(bp, &rx, &tx, true); if (rx > 1) { bp->flags &= ~BNXT_FLAG_NO_AGG_RINGS; - bp->dev->hw_features |= NETIF_F_LRO; + if (BNXT_SUPPORTS_TPA(bp)) + bp->dev->hw_features |= NETIF_F_LRO; } } From 5ce7f36c334d723954855ac769ede2fe0e8f89c8 Mon Sep 17 00:00:00 2001 From: Joe Damato Date: Tue, 1 Sep 2026 18:56:45 -0700 Subject: [PATCH 0921/1198] bnxt_en: Don't free the live ring's TPA state on queue restart failure bnxt_queue_mem_alloc() shallow copies the live RX ring into the clone: memcpy(clone, rxr, sizeof(*rxr)); the code currently clears pointers that the clone owns (such as rx_agg_bmap), but rx_tpa and rx_tpa_idx_map are left pointing at memory of the live ring that was cloned. If an allocation failure happens later and the err_free_tpa_info label is taken, the live ring's memory can be freed while still in use. Fix this by initializing the clone's pointers to NULL to prevent live ring state from being freed inadvertently. Fixes: bd649c5cc958 ("bnxt_en: handle tpa_info in queue API implementation") Reported-by: Sashiko Link: https://netdev-ai.bots.linux.dev/sashiko/#/patchset/20260828190900.1767611-1-joe%40dama.to Cc: stable@vger.kernel.org Signed-off-by: Joe Damato Link: https://patch.msgid.link/20260902015652.2421609-3-joe@dama.to Signed-off-by: Paolo Abeni --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 343d70a98134..aaf658976865 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -16357,6 +16357,8 @@ static int bnxt_queue_mem_alloc(struct net_device *dev, clone->need_head_pool = false; clone->rx_page_size = qcfg->rx_page_size; clone->rx_agg_bmap = NULL; + clone->rx_tpa = NULL; + clone->rx_tpa_idx_map = NULL; rc = bnxt_alloc_rx_page_pool(bp, clone, rxr->page_pool->p.nid); if (rc) From b814dfbfeb0a68c9a52073f2caa05a2d5247a329 Mon Sep 17 00:00:00 2001 From: Joe Damato Date: Tue, 1 Sep 2026 18:56:46 -0700 Subject: [PATCH 0922/1198] bnxt_en: Propagate TPA buffer allocation failures in bnxt_queue_mem_alloc() bnxt_alloc_one_tpa_info_data() returns -ENOMEM as soon as one allocation fails. This leaves the remaining rxr->rx_tpa[] entries zeroed. bnxt_queue_mem_alloc() discards that return value, so the partially initialized ring is installed by bnxt_queue_start(). Since the agg_id is picked by the hardware and bnxt_alloc_agg_idx maps it to a SW index in rxr->rx_tpa[], it is possible that an uninitialized slot can be chosen which would hand a zero DMA address to the device. Fix this by checking the return value of bnxt_alloc_one_tpa_info_data and unwinding, freeing the ring buffers. Fixes: bd649c5cc958 ("bnxt_en: handle tpa_info in queue API implementation") Reported-by: Sashiko Link: https://netdev-ai.bots.linux.dev/sashiko/#/patchset/20260828190900.1767611-1-joe%40dama.to Cc: stable@vger.kernel.org Signed-off-by: Joe Damato Link: https://patch.msgid.link/20260902015652.2421609-4-joe@dama.to Signed-off-by: Paolo Abeni --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index aaf658976865..ae7150c7de1f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -16402,11 +16402,16 @@ static int bnxt_queue_mem_alloc(struct net_device *dev, bnxt_alloc_one_rx_ring_skb(bp, clone, idx); if (bp->flags & BNXT_FLAG_AGG_RINGS) bnxt_alloc_one_rx_ring_netmem(bp, clone, idx); - if (bp->flags & BNXT_FLAG_TPA) - bnxt_alloc_one_tpa_info_data(bp, clone); + if (bp->flags & BNXT_FLAG_TPA) { + rc = bnxt_alloc_one_tpa_info_data(bp, clone); + if (rc) + goto err_free_rx_ring_skbs; + } return 0; +err_free_rx_ring_skbs: + bnxt_free_one_rx_ring_skbs(bp, clone); err_free_tpa_info: bnxt_free_one_tpa_info(bp, clone); err_free_rx_agg_ring: From 961e2a17c5e3559b3f8654d2daabdd25a42e770a Mon Sep 17 00:00:00 2001 From: Joe Damato Date: Tue, 1 Sep 2026 18:56:47 -0700 Subject: [PATCH 0923/1198] bnxt_en: Handle buffer allocation failure in bnxt_rx_ring_reset() bnxt_rx_ring_reset() frees the ring buffers and then reallocates them, ignoring the result. bnxt_alloc_one_rx_ring() can fail in bnxt_alloc_one_tpa_info_data(), which returns -ENOMEM on the first failed allocation and leaves the remaining rxr->rx_tpa[] entries zeroed. The error isn't propagated up, so the loop in bnxt_rx_ring_reset continues and at the end the code re-enables TPA with partially unallocated rx_tpa array. This means that when the agg_id from hardware is mapped to a SW index in rxr->rx_tpa[], an uninitialized slot can be chosen which would hand a zero DMA address to the device. Fix this by falling back to a global reset, which is what the existing code already does when other functions fail, but unlike the other failure cases this particular failure has to return because TPA can't be re-enabled since the allocation failed. Fixes: 8fbf58e17dce ("bnxt_en: Implement RX ring reset in response to buffer errors.") Reported-by: Sashiko Link: https://netdev-ai.bots.linux.dev/sashiko/#/patchset/20260828190900.1767611-1-joe%40dama.to Cc: stable@vger.kernel.org Signed-off-by: Joe Damato Link: https://patch.msgid.link/20260902015652.2421609-5-joe@dama.to Signed-off-by: Paolo Abeni --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index ae7150c7de1f..a2283fd9cdfc 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -14628,7 +14628,14 @@ static void bnxt_rx_ring_reset(struct bnxt *bp) rxr->rx_sw_agg_prod = 0; rxr->rx_next_cons = 0; rxr->bnapi->in_reset = false; - bnxt_alloc_one_rx_ring(bp, i); + rc = bnxt_alloc_one_rx_ring(bp, i); + if (rc) { + netdev_warn(bp->dev, "RX ring reset failed to allocate buffers, rc = %d, falling back to global reset\n", + rc); + bnxt_reset_task(bp, true); + bnxt_rtnl_unlock_sp(bp); + return; + } cpr = &rxr->bnapi->cp_ring; cpr->sw_stats->rx.rx_resets++; if (bp->flags & BNXT_FLAG_AGG_RINGS) From 8e6a850c0746bb4be167aedf1ee57469fcda09a9 Mon Sep 17 00:00:00 2001 From: Joe Damato Date: Tue, 1 Sep 2026 18:56:48 -0700 Subject: [PATCH 0924/1198] bnxt_en: Propagate RX ring init failures in bnxt_init_nic() bnxt_init_rx_rings() returns an error when bnxt_alloc_one_rx_ring() fails, but bnxt_init_nic() discards that return value and calls bnxt_init_chip(), which enables TPA. If an allocation fails, this could leave rxr->rx_tpa[] partially zeroed and TPA would be enabled over an array with zeroed entries. This would lead to a zeroed DMA address being handed out if the agg_idx is translated to a SW index at a zeroed entry. Fix this by propagating the error out of bnxt_init_nic(). Both callers already check its return value and unwind with bnxt_free_skbs() and bnxt_free_mem(), which tolerate a partially initialized RX ring. Fixes: c0c050c58d84 ("bnxt_en: New Broadcom ethernet driver.") Reported-by: Sashiko Link: https://netdev-ai.bots.linux.dev/sashiko/#/patchset/20260828190900.1767611-1-joe%40dama.to Cc: stable@vger.kernel.org Signed-off-by: Joe Damato Link: https://patch.msgid.link/20260902015652.2421609-6-joe@dama.to Signed-off-by: Paolo Abeni --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index a2283fd9cdfc..32c59b3d1cbc 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -11363,8 +11363,13 @@ static int bnxt_shutdown_nic(struct bnxt *bp, bool irq_re_init) static int bnxt_init_nic(struct bnxt *bp, bool irq_re_init) { + int rc; + bnxt_init_cp_rings(bp); - bnxt_init_rx_rings(bp); + rc = bnxt_init_rx_rings(bp); + if (rc) + return rc; + bnxt_init_tx_rings(bp); bnxt_init_ring_grps(bp, irq_re_init); bnxt_init_vnics(bp); From c0aceaf65b70b3c000e70dd867f3a673015f24ca Mon Sep 17 00:00:00 2001 From: Joe Damato Date: Tue, 1 Sep 2026 18:56:49 -0700 Subject: [PATCH 0925/1198] bnxt_en: Bound SW TPA IDs to prevent crashes FW supports up to 1024 concurrent TPAs, so the FW TPA ID is in the range 0..1023 (see commit ec4d8e7cf024 ("bnxt_en: Add TPA ID mapping logic for 57500 chips.")). bnxt_alloc_agg_idx is intended to wrap the FW ID down to a software ID which is used to index rxr->rx_tpa, and to generate a mapping between FW IDs and the wrapped software ID. On a 57608 with firmware version 233, the firmware advertises 32 concurrent TPAs. As of the commit under fixes, bp->max_tpa on this NIC is set to 32. If the software ID from bnxt_alloc_agg_idx is above 31, this results in an invalid address being loaded on this line: tpa_info = &rxr->rx_tpa[agg_id]; because rx_tpa is allocated with only bp->max_tpa (32) entries. Writes to tpa_info later in the code are out of bounds. This bug results in a crash at boot: Oops: general protection fault, kernel NULL pointer dereference 0x8: 0000 [#1] SMP NOPTI RIP: 0010:bnxt_rx_pkt+0xc0/0x1560 RSP: 0018:ffffc900009b8c78 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000048 RCX: 0000000206682516 RDX: ffffc900009b8db4 RSI: 0000000000000000 RDI: 01ffffff038fe1c0 RBP: ffffc9006e687480 R08: ffffc9006e687000 R09: 0000000000003048 R10: 0000000000000480 R11: ffff8881c6083900 R12: 0000000006682516 R13: ffff8881c6095400 R14: 0000000000000016 R15: ffff8881c6b66680 FS: 0000000000000000(0000) GS:ffff88fef3c77000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fc8bda40584 CR3: 000000807c812001 CR4: 0000000008772ef0 PKRU: 55555554 Call Trace: ? __netif_receive_skb_list_core+0x1ca/0x250 __bnxt_poll_work+0x152/0x280 bnxt_poll_p5+0x1cd/0x480 __napi_poll+0x30/0x180 net_rx_action+0x20b/0x3b0 ? note_gp_changes+0x53/0xe0 ? tick_setup_sched_timer+0x180/0x180 ? __napi_schedule+0x9a/0xb0 ? bnxt_msix+0x24/0x30 handle_softirqs+0xdd/0x2c0 __irq_exit_rcu.llvm.3171231171502365008+0x47/0xf0 common_interrupt+0x85/0x90 asm_common_interrupt+0x22/0x40 This stack trace is from a crash triggered when an out of bounds rx_tpa is dereferenced. The invalid write mentioned above is silent in this particular crash. Fix this by allocating rx_tpa with bp->max_tpa rounded up to the next power of 2 (bp->max_tpa_roundup_size) entries and masking the FW TPA ID with that size, so the wrapped ID can never index past the end of the array. Fixes: 54c28fab2fa5 ("bnxt_en: Set bp->max_tpa according to what the FW supports") Reported-by: Raphael Cardoso Fernandes Suggested-by: Michael Chan Cc: stable@vger.kernel.org Signed-off-by: Joe Damato Link: https://patch.msgid.link/20260902015652.2421609-7-joe@dama.to Signed-off-by: Paolo Abeni --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 27 ++++++++++++++--------- drivers/net/ethernet/broadcom/bnxt/bnxt.h | 2 +- 2 files changed, 18 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 32c59b3d1cbc..d7728d0c5b6e 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1534,14 +1534,16 @@ static int bnxt_discard_rx(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, return 0; } -static u16 bnxt_alloc_agg_idx(struct bnxt_rx_ring_info *rxr, u16 agg_id) +static u16 bnxt_alloc_agg_idx(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, + u16 agg_id) { struct bnxt_tpa_idx_map *map = rxr->rx_tpa_idx_map; - u16 idx = agg_id & MAX_TPA_P5_MASK; + u16 idx = agg_id & (bp->max_tpa_roundup_size - 1); if (test_bit(idx, map->agg_idx_bmap)) { - idx = find_first_zero_bit(map->agg_idx_bmap, MAX_TPA_P5); - if (idx >= MAX_TPA_P5) + idx = find_first_zero_bit(map->agg_idx_bmap, + bp->max_tpa_roundup_size); + if (idx >= bp->max_tpa_roundup_size) return INVALID_HW_RING_ID; } __set_bit(idx, map->agg_idx_bmap); @@ -1606,7 +1608,7 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) { agg_id = TPA_START_AGG_ID_P5(tpa_start); - agg_id = bnxt_alloc_agg_idx(rxr, agg_id); + agg_id = bnxt_alloc_agg_idx(bp, rxr, agg_id); if (unlikely(agg_id == INVALID_HW_RING_ID)) { netdev_warn(bp->dev, "Unable to allocate agg ID for ring %d, agg 0x%x\n", rxr->bnapi->index, @@ -3604,7 +3606,7 @@ static void bnxt_free_one_tpa_info_data(struct bnxt *bp, { int i; - for (i = 0; i < bp->max_tpa; i++) { + for (i = 0; i < bp->max_tpa_roundup_size; i++) { struct bnxt_tpa_info *tpa_info = &rxr->rx_tpa[i]; u8 *data = tpa_info->data; @@ -3801,7 +3803,7 @@ static void bnxt_free_one_tpa_info(struct bnxt *bp, kfree(rxr->rx_tpa_idx_map); rxr->rx_tpa_idx_map = NULL; if (rxr->rx_tpa) { - for (i = 0; i < bp->max_tpa; i++) { + for (i = 0; i < bp->max_tpa_roundup_size; i++) { kfree(rxr->rx_tpa[i].agg_arr); rxr->rx_tpa[i].agg_arr = NULL; } @@ -3827,13 +3829,14 @@ static int bnxt_alloc_one_tpa_info(struct bnxt *bp, struct rx_agg_cmp *agg; int i; - rxr->rx_tpa = kzalloc_objs(struct bnxt_tpa_info, bp->max_tpa); + rxr->rx_tpa = kzalloc_objs(struct bnxt_tpa_info, + bp->max_tpa_roundup_size); if (!rxr->rx_tpa) return -ENOMEM; if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS)) return 0; - for (i = 0; i < bp->max_tpa; i++) { + for (i = 0; i < bp->max_tpa_roundup_size; i++) { agg = kzalloc_objs(*agg, MAX_SKB_FRAGS); if (!agg) return -ENOMEM; @@ -3852,6 +3855,9 @@ static int bnxt_alloc_tpa_info(struct bnxt *bp) bp->max_tpa = MAX_TPA; if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) { + /* TPA is not supported at all, so there is nothing to + * allocate. + */ if (!bp->max_tpa_v2) return 0; bp->max_tpa = min_t(u16, bp->max_tpa_v2, MAX_TPA_P5); @@ -3859,6 +3865,7 @@ static int bnxt_alloc_tpa_info(struct bnxt *bp) if (bp->max_tpa <= 32 && BNXT_CHIP_P5(bp) && !BNXT_NPAR(bp)) bp->max_tpa = MAX_TPA_P5; } + bp->max_tpa_roundup_size = roundup_pow_of_two(bp->max_tpa); for (i = 0; i < bp->rx_nr_rings; i++) { struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; @@ -4571,7 +4578,7 @@ static int bnxt_alloc_one_tpa_info_data(struct bnxt *bp, u8 *data; int i; - for (i = 0; i < bp->max_tpa; i++) { + for (i = 0; i < bp->max_tpa_roundup_size; i++) { data = __bnxt_alloc_rx_frag(bp, &mapping, rxr, GFP_KERNEL); if (!data) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index dc5a16ec5943..c673b2ce4a0d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -789,7 +789,6 @@ struct nqe_cn { #define MAX_TPA 64 #define MAX_TPA_P5 256 -#define MAX_TPA_P5_MASK (MAX_TPA_P5 - 1) #define MAX_TPA_SEGS_P5 0x3f #if (BNXT_PAGE_SHIFT == 16) @@ -2381,6 +2380,7 @@ struct bnxt { u16 max_tpa_v2; u16 max_tpa; + u16 max_tpa_roundup_size; u32 rx_buf_size; u32 rx_buf_use_size; /* useable size */ u16 rx_offset; From 0523d5c52a450590bf5992bd6925394f3cc403e8 Mon Sep 17 00:00:00 2001 From: Aleksei Sviridkin Date: Thu, 3 Sep 2026 12:36:51 +0000 Subject: [PATCH 0926/1198] net: macb: zero the link settings taprio reads back macb_taprio_setup_replace() calls phylink_ethtool_ksettings_get() with an uninitialised kset, and kset is not only an out-parameter. On a fixed link, or an in-band link with no PHY, phylink writes speed and duplex only if kset->base.rate_matching already reads RATE_MATCH_NONE, a field it never writes itself; in PHY mode before the PHY is attached it writes port and supported and nothing more. Either way the speed read back afterwards can be stack garbage. The ethtool core zeroes the structure on every path into the op, which is why its callers never see this; taprio is the only in-kernel caller passing its own variable. Fixes: 89934dbf169e ("net: macb: Add TAPRIO traffic scheduling support") Assisted-by: LLM Signed-off-by: Aleksei Sviridkin Link: https://patch.msgid.link/20260903123652.23900-2-f@lex.la Signed-off-by: Paolo Abeni --- drivers/net/ethernet/cadence/macb_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 8469df0d89c3..9be28b4fddb8 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -4300,9 +4300,9 @@ static int macb_taprio_setup_replace(struct net_device *netdev, u64 total_on_time = 0, start_time_sec = 0, start_time = conf->base_time; u32 configured_queues = 0, speed = 0, start_time_nsec; struct macb_queue_enst_config *enst_queue; - struct tc_taprio_sched_entry *entry; + struct ethtool_link_ksettings kset = {}; struct macb *bp = netdev_priv(netdev); - struct ethtool_link_ksettings kset; + struct tc_taprio_sched_entry *entry; struct macb_queue *queue; u32 queue_mask; u8 queue_id; From 2b6c0e25a3d713c4032e45f212bdd9e14c50f8a0 Mon Sep 17 00:00:00 2001 From: Aleksei Sviridkin Date: Thu, 3 Sep 2026 12:36:52 +0000 Subject: [PATCH 0927/1198] net: macb: reject an unknown link speed in the taprio setup speed is a u32, so SPEED_UNKNOWN arrives as 0xffffffff and passes the "speed <= 0" check, which only ever catches zero. That is what an autonegotiating link reports while it is down: the limit derived from the speed collapses to a nanosecond at most and the first entry fails with a misleading "exceeds hardware limit". Zero stays covered, it is what an interface that was never opened reports, and enst_max_hw_interval() divides by it. Say which case it was in the error. Fixes: 89934dbf169e ("net: macb: Add TAPRIO traffic scheduling support") Assisted-by: LLM Signed-off-by: Aleksei Sviridkin Link: https://patch.msgid.link/20260903123652.23900-3-f@lex.la Signed-off-by: Paolo Abeni --- drivers/net/ethernet/cadence/macb_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 9be28b4fddb8..0e75339fa206 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -4329,8 +4329,8 @@ static int macb_taprio_setup_replace(struct net_device *netdev, } speed = kset.base.speed; - if (unlikely(speed <= 0)) { - netdev_err(netdev, "Invalid speed: %d\n", speed); + if (unlikely(speed == SPEED_UNKNOWN || !speed)) { + netdev_err(netdev, "Invalid speed %d, link-down?\n", speed); return -EINVAL; } From d3df7ed4683f8c1b35672a40bf20af6a08ef8ca9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micka=C3=ABl=20Sala=C3=BCn?= Date: Mon, 7 Sep 2026 12:36:08 +0200 Subject: [PATCH 0928/1198] landlock: Clean up ruleset validation checks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit landlock_merge_ruleset() checks for a NULL ruleset after dereferencing it in lockdep_assert_held(). Move the assertion after the check so the defensive path remains effective. The mask-validation comment originated in landlock_add_fs_access_mask() to explain that its WARN_ON_ONCE() checked a caller invariant. It became self-referential when this helper and its network and scope counterparts were inlined into landlock_create_ruleset(). Restate the invariant without naming the caller. Keep both as defensive callee checks. Moving the assertion preserves the NULL check's ability to warn and return -EINVAL, while invalid masks remain warned about and masked. Reported-by: Günther Noack Closes: https://patch.msgid.link/aobYhIt3vcs2xN0b@google.com Closes: https://patch.msgid.link/aobasxUDQ8b7GYXl@google.com Reviewed-by: Günther Noack Link: https://patch.msgid.link/20260907103609.113325-1-mic@digikod.net Signed-off-by: Mickaël Salaün --- security/landlock/domain.c | 3 ++- security/landlock/ruleset.c | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/security/landlock/domain.c b/security/landlock/domain.c index 93c7104fd6b2..4031b581be07 100644 --- a/security/landlock/domain.c +++ b/security/landlock/domain.c @@ -439,10 +439,11 @@ landlock_merge_ruleset(struct landlock_domain *const parent, int err; might_sleep(); - lockdep_assert_held(&ruleset->lock); if (WARN_ON_ONCE(!ruleset)) return ERR_PTR(-EINVAL); + lockdep_assert_held(&ruleset->lock); + if (parent) { if (parent->num_layers >= LANDLOCK_MAX_NUM_LAYERS) return ERR_PTR(-E2BIG); diff --git a/security/landlock/ruleset.c b/security/landlock/ruleset.c index 0d07707523cd..a5d135d085cb 100644 --- a/security/landlock/ruleset.c +++ b/security/landlock/ruleset.c @@ -58,7 +58,7 @@ landlock_create_ruleset(const access_mask_t fs_access_mask, new_ruleset->id = landlock_get_id_range(1); #endif /* CONFIG_TRACEPOINTS */ - /* Should already be checked in landlock_create_ruleset(). */ + /* The caller must only pass supported access rights and scopes. */ if (fs_access_mask) { const access_mask_t mask = fs_access_mask & LANDLOCK_MASK_ACCESS_FS; From 3125751cd1de76a01b18daef399d6b88d159bd17 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micka=C3=ABl=20Sala=C3=BCn?= Date: Mon, 7 Sep 2026 17:43:58 +0200 Subject: [PATCH 0929/1198] landlock: Bound escaped trace path output MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Filesystem paths may expand fourfold when trace text escapes spaces and other untrusted bytes. A sufficiently long representation can exhaust the shared scratch sequence. A sibling __print_flags() helper may then return an unterminated one-past pointer because TP_printk() argument ordering is unspecified. Use a fixed budget rather than the scratch space available at call time, so output does not vary with sibling evaluation order. Limit an untrusted string to three quarters of the trace sequence, leaving the rest for sibling helpers and final event metadata. Compute and commit complete escaped output transactionally so an exact fill cannot consume the terminating NUL or poison the scratch sequence. For strings that exceed the limit, retain the largest prefix ending at a complete escape unit, then append a raw UTF-8 ellipsis. Keep the helper's existing octal fallback so complete values remain unchanged. Hex fallback would consume the same four bytes per escaped byte without increasing the prefix or strengthening the marker. ESCAPE_NAP renders every non-ASCII input byte in octal, so legitimate data cannot reproduce the marker without being escaped. Cc: Günther Noack Link: https://patch.msgid.link/20260907154401.124362-1-mic@digikod.net Signed-off-by: Mickaël Salaün --- include/trace/events/landlock.h | 70 +++++++++++++++++++++++++-------- 1 file changed, 53 insertions(+), 17 deletions(-) diff --git a/include/trace/events/landlock.h b/include/trace/events/landlock.h index f82588f6f90e..d05253afaf59 100644 --- a/include/trace/events/landlock.h +++ b/include/trace/events/landlock.h @@ -28,6 +28,16 @@ struct task_struct; #ifdef CREATE_TRACE_POINTS +/* About 6 KiB, leaving about 2 KiB for sibling helpers and fixed fields. */ +#define TRACE_UNTRUSTED_STR_OUTPUT_SIZE \ + (TRACE_SEQ_BUFFER_SIZE - TRACE_SEQ_BUFFER_SIZE / 4) + +/* + * A raw UTF-8 ellipsis (…) marks truncation and cannot collide with escaped + * input: ESCAPE_NAP renders every non-ASCII input byte in octal. + */ +#define TRACE_TRUNCATION_MARKER "\xe2\x80\xa6" + /* * Escapes @len bytes of an untrusted string into the trace sequence @p so it * cannot inject field separators or control characters into the ftrace text @@ -37,33 +47,59 @@ struct task_struct; * NUL-terminated or carries embedded NUL bytes (an abstract socket name) is * escaped in full instead of being truncated at the first NUL. * - * Return: a pointer into @p's buffer, or NULL if @src is NULL or the buffer is - * exhausted (normal when the trace buffer is full). + * Strings that exceed the output limit retain the largest complete escaped + * prefix followed by the truncation marker. + * + * Return: a pointer into @p's buffer, or NULL if @src is NULL or the fixed + * output reservation is unavailable. */ static inline const char * __trace_print_untrusted_str(struct trace_seq *p, const char *src, size_t len) { + const unsigned int escape_flags = ESCAPE_SPACE | ESCAPE_SPECIAL | + ESCAPE_NAP | ESCAPE_APPEND | + ESCAPE_OCTAL; + const size_t marker_len = sizeof(TRACE_TRUNCATION_MARKER) - 1; + size_t buf_size, prefix_len, prefix_size; int escaped_size; char *buf; - size_t buf_size = seq_buf_get_buf(&p->seq, &buf); - const char *ret = trace_seq_buffer_ptr(p); + const char *ret; - /* Buffer exhaustion is normal when the trace buffer is full. */ - if (!src || buf_size == 0) + buf_size = seq_buf_get_buf(&p->seq, &buf); + if (!src || buf_size < TRACE_UNTRUSTED_STR_OUTPUT_SIZE) return NULL; - escaped_size = - string_escape_mem(src, len, buf, buf_size, - ESCAPE_SPACE | ESCAPE_SPECIAL | ESCAPE_NAP | - ESCAPE_APPEND | ESCAPE_OCTAL, - " ='\"\\"); - if (unlikely(escaped_size >= buf_size)) { - /* We need some room for the final '\0'. */ - seq_buf_set_overflow(&p->seq); - p->full = 1; - return NULL; + ret = trace_seq_buffer_ptr(p); + escaped_size = string_escape_mem(src, len, buf, + TRACE_UNTRUSTED_STR_OUTPUT_SIZE, + escape_flags, " ='\"\\"); + if (likely(escaped_size < TRACE_UNTRUSTED_STR_OUTPUT_SIZE)) { + seq_buf_commit(&p->seq, escaped_size); + trace_seq_putc(p, 0); + return ret; } - seq_buf_commit(&p->seq, escaped_size); + + prefix_len = 0; + prefix_size = 0; + while (prefix_len < len) { + const char *const src_char = src + prefix_len; + int char_size; + + char_size = string_escape_mem(src_char, 1, NULL, 0, + escape_flags, " ='\"\\"); + if (char_size > TRACE_UNTRUSTED_STR_OUTPUT_SIZE - marker_len - + 1 - prefix_size) + break; + prefix_size += char_size; + prefix_len++; + } + + escaped_size = string_escape_mem(src, prefix_len, buf, prefix_size, + escape_flags, " ='\"\\"); + if (WARN_ON_ONCE(escaped_size != prefix_size)) + return NULL; + memcpy(buf + prefix_size, TRACE_TRUNCATION_MARKER, marker_len); + seq_buf_commit(&p->seq, prefix_size + marker_len); trace_seq_putc(p, 0); return ret; } From d41d0021a6ea3e9fcd14126a00fead47f981c46e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micka=C3=ABl=20Sala=C3=BCn?= Date: Mon, 7 Sep 2026 17:43:59 +0200 Subject: [PATCH 0930/1198] landlock: Test trace path output boundaries MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use focused KUnit tests to exercise the renderer's internal boundary and composition contracts with synthetic scratch states, including both sibling-helper evaluation orders. Check the exact output and reservation boundaries, including a four-byte octal escape accepted at exact capacity and rejected one byte short. Also verify an unchanged cursor on failure, that bracketed process names and embedded NUL bytes remain data, and that input ellipsis bytes are escaped rather than mistaken for the raw truncation marker. The composition test requires generic trace output helpers. Enable CONFIG_FTRACE and CONFIG_SCHED_TRACER because the latter selects the otherwise-hidden CONFIG_TRACING support required by trace_print_flags_seq(). Use kselftests to exercise the complete tracefs path for both affected filesystem events. A valid path containing 2640 spaces exceeds the scratch output budget. Require its escaped prefix to end in the raw UTF-8 ellipsis while access_rights and blockers remain intact. This division keeps the exact safety contract compiler-independent while proving that real tracepoints preserve their surrounding symbolic fields. The end-to-end assertions fail after a full fix revert with both GCC and Clang, while the composition KUnit test fails if the scratch reserve is removed. Cc: Günther Noack Link: https://patch.msgid.link/20260907154401.124362-2-mic@digikod.net Signed-off-by: Mickaël Salaün --- security/landlock/.kunitconfig | 2 + security/landlock/trace.c | 182 ++++++++++++++++++ .../selftests/landlock/trace_fs_test.c | 160 +++++++++++++++ 3 files changed, 344 insertions(+) diff --git a/security/landlock/.kunitconfig b/security/landlock/.kunitconfig index f9423f01ac5b..fe36228d37ea 100644 --- a/security/landlock/.kunitconfig +++ b/security/landlock/.kunitconfig @@ -1,6 +1,8 @@ CONFIG_AUDIT=y +CONFIG_FTRACE=y CONFIG_KUNIT=y CONFIG_NET=y +CONFIG_SCHED_TRACER=y CONFIG_SECURITY=y CONFIG_SECURITY_LANDLOCK=y CONFIG_SECURITY_LANDLOCK_KUNIT_TEST=y diff --git a/security/landlock/trace.c b/security/landlock/trace.c index 2ea7aac8d75d..8c21e5de6f0d 100644 --- a/security/landlock/trace.c +++ b/security/landlock/trace.c @@ -6,6 +6,7 @@ * Copyright © 2026 Cloudflare, Inc. */ +#include #include #include #include @@ -183,3 +184,184 @@ void landlock_trace_denial( break; } } + +#ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST + +static void test_trace_seq_init(struct trace_seq *const seq, const size_t size) +{ + memset(seq, 0, sizeof(*seq)); + seq_buf_init(&seq->seq, seq->buffer, size); +} + +static void test_untrusted_str_data(struct kunit *const test) +{ + const char binary[] = { 'a', '\0', '<' }; + static const char ellipsis[] = "\xe2\x80\xa6"; + struct trace_seq *const seq = + kunit_kzalloc(test, sizeof(*seq), GFP_KERNEL); + const char *output; + + KUNIT_ASSERT_NOT_NULL(test, seq); + test_trace_seq_init(seq, TRACE_SEQ_BUFFER_SIZE); + output = __trace_print_untrusted_str(seq, "", 10); + KUNIT_ASSERT_NOT_NULL(test, output); + KUNIT_EXPECT_STREQ(test, output, ""); + + test_trace_seq_init(seq, TRACE_SEQ_BUFFER_SIZE); + output = __trace_print_untrusted_str(seq, binary, sizeof(binary)); + KUNIT_ASSERT_NOT_NULL(test, output); + KUNIT_EXPECT_STREQ(test, output, "a\\000<"); + + /* Input ellipsis bytes are escaped and cannot mimic the raw marker. */ + test_trace_seq_init(seq, TRACE_SEQ_BUFFER_SIZE); + output = __trace_print_untrusted_str(seq, ellipsis, + sizeof(ellipsis) - 1); + KUNIT_ASSERT_NOT_NULL(test, output); + KUNIT_EXPECT_STREQ(test, output, "\\342\\200\\246"); +} + +static void test_untrusted_str_boundaries(struct kunit *const test) +{ + static const char escaped_space[] = "\\040"; + const size_t output_size = TRACE_UNTRUSTED_STR_OUTPUT_SIZE; + const size_t marker_len = sizeof(TRACE_TRUNCATION_MARKER) - 1; + const size_t escape_len = sizeof(escaped_space) - 1; + const size_t exact_prefix_len = + output_size - marker_len - 1 - escape_len; + const size_t short_prefix_len = exact_prefix_len + 1; + struct trace_seq *const seq = + kunit_kzalloc(test, sizeof(*seq), GFP_KERNEL); + char *const input = kunit_kmalloc(test, output_size + 1, GFP_KERNEL); + char *const expected = kunit_kmalloc(test, output_size, GFP_KERNEL); + const char *output; + + KUNIT_ASSERT_NOT_NULL(test, seq); + KUNIT_ASSERT_NOT_NULL(test, input); + KUNIT_ASSERT_NOT_NULL(test, expected); + + /* The escaped string and its trailing NUL exactly fit the limit. */ + memset(input, 'a', output_size - 1); + test_trace_seq_init(seq, TRACE_SEQ_BUFFER_SIZE); + output = __trace_print_untrusted_str(seq, input, output_size - 1); + KUNIT_ASSERT_NOT_NULL(test, output); + KUNIT_EXPECT_EQ(test, seq->seq.len, output_size); + KUNIT_EXPECT_EQ(test, memcmp(output, input, output_size - 1), 0); + + /* Stop before a four-byte escape when only three bytes remain. */ + memset(input, 'a', short_prefix_len); + input[short_prefix_len] = ' '; + memset(input + short_prefix_len + 1, 'b', 5); + memset(expected, 'a', short_prefix_len); + memcpy(expected + short_prefix_len, TRACE_TRUNCATION_MARKER, + marker_len + 1); + test_trace_seq_init(seq, TRACE_SEQ_BUFFER_SIZE); + output = __trace_print_untrusted_str(seq, input, short_prefix_len + 6); + KUNIT_ASSERT_NOT_NULL(test, output); + KUNIT_EXPECT_STREQ(test, output, expected); + + /* Include a four-byte escape that exactly fills the prefix capacity. */ + memset(input, 'a', exact_prefix_len); + input[exact_prefix_len] = ' '; + memset(input + exact_prefix_len + 1, 'b', marker_len + 1); + memset(expected, 'a', exact_prefix_len); + memcpy(expected + exact_prefix_len, escaped_space, escape_len); + memcpy(expected + exact_prefix_len + escape_len, + TRACE_TRUNCATION_MARKER, marker_len + 1); + test_trace_seq_init(seq, TRACE_SEQ_BUFFER_SIZE); + output = __trace_print_untrusted_str(seq, input, + exact_prefix_len + marker_len + 2); + KUNIT_ASSERT_NOT_NULL(test, output); + KUNIT_EXPECT_STREQ(test, output, expected); + + /* Literal backslashes remain escaped in complete output. */ + test_trace_seq_init(seq, TRACE_SEQ_BUFFER_SIZE); + output = __trace_print_untrusted_str(seq, "/\\000", 5); + KUNIT_ASSERT_NOT_NULL(test, output); + KUNIT_EXPECT_STREQ(test, output, "/\\\\000"); +} + +static void test_untrusted_str_cursor(struct kunit *const test) +{ + const size_t padding_len = + TRACE_SEQ_BUFFER_SIZE - TRACE_UNTRUSTED_STR_OUTPUT_SIZE + 1; + struct trace_seq *const seq = + kunit_kzalloc(test, sizeof(*seq), GFP_KERNEL); + char *const padding = kunit_kzalloc(test, padding_len, GFP_KERNEL); + const char *output; + + KUNIT_ASSERT_NOT_NULL(test, seq); + KUNIT_ASSERT_NOT_NULL(test, padding); + + /* Accept available space exactly equal to the fixed reservation. */ + test_trace_seq_init(seq, TRACE_SEQ_BUFFER_SIZE); + trace_seq_putmem(seq, padding, padding_len - 1); + output = __trace_print_untrusted_str(seq, "/a", 2); + KUNIT_ASSERT_NOT_NULL(test, output); + KUNIT_EXPECT_STREQ(test, output, "/a"); + KUNIT_EXPECT_EQ(test, seq->seq.len, padding_len - 1 + sizeof("/a")); + + /* Reject one byte less without changing the scratch cursor. */ + test_trace_seq_init(seq, TRACE_SEQ_BUFFER_SIZE); + trace_seq_putmem(seq, padding, padding_len); + output = __trace_print_untrusted_str(seq, "/a", 2); + KUNIT_EXPECT_NULL(test, output); + KUNIT_EXPECT_EQ(test, seq->seq.len, padding_len); +} + +static void test_untrusted_str_composition(struct kunit *const test) +{ + static const struct trace_print_flags flags[] = { + { .mask = 1, .name = "read" }, + }; + const size_t output_size = TRACE_UNTRUSTED_STR_OUTPUT_SIZE; + const size_t prefix_len = output_size - sizeof(TRACE_TRUNCATION_MARKER); + struct trace_seq *const seq = + kunit_kzalloc(test, sizeof(*seq), GFP_KERNEL); + char *const expected = kunit_kmalloc(test, output_size, GFP_KERNEL); + char *const path = kunit_kmalloc(test, output_size, GFP_KERNEL); + const char *flags_output, *path_output; + + KUNIT_ASSERT_NOT_NULL(test, seq); + KUNIT_ASSERT_NOT_NULL(test, expected); + KUNIT_ASSERT_NOT_NULL(test, path); + memset(path, 'a', output_size); + memset(expected, 'a', prefix_len); + memcpy(expected + prefix_len, TRACE_TRUNCATION_MARKER, + sizeof(TRACE_TRUNCATION_MARKER)); + + /* Exercise both legal TP_printk() sibling evaluation orders. */ + test_trace_seq_init(seq, TRACE_SEQ_BUFFER_SIZE); + path_output = __trace_print_untrusted_str(seq, path, output_size); + flags_output = + trace_print_flags_seq(seq, "|", 1, flags, ARRAY_SIZE(flags)); + KUNIT_ASSERT_NOT_NULL(test, path_output); + KUNIT_EXPECT_STREQ(test, path_output, expected); + KUNIT_EXPECT_STREQ(test, flags_output, "read"); + + test_trace_seq_init(seq, TRACE_SEQ_BUFFER_SIZE); + flags_output = + trace_print_flags_seq(seq, "|", 1, flags, ARRAY_SIZE(flags)); + path_output = __trace_print_untrusted_str(seq, path, output_size); + KUNIT_ASSERT_NOT_NULL(test, path_output); + KUNIT_EXPECT_STREQ(test, path_output, expected); + KUNIT_EXPECT_STREQ(test, flags_output, "read"); +} + +static struct kunit_case test_cases[] = { + /* clang-format off */ + KUNIT_CASE(test_untrusted_str_data), + KUNIT_CASE(test_untrusted_str_boundaries), + KUNIT_CASE(test_untrusted_str_cursor), + KUNIT_CASE(test_untrusted_str_composition), + {} + /* clang-format on */ +}; + +static struct kunit_suite test_suite = { + .name = "landlock_trace", + .test_cases = test_cases, +}; + +kunit_test_suite(test_suite); + +#endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */ diff --git a/tools/testing/selftests/landlock/trace_fs_test.c b/tools/testing/selftests/landlock/trace_fs_test.c index 5220f6a4bee1..4543a25c1f55 100644 --- a/tools/testing/selftests/landlock/trace_fs_test.c +++ b/tools/testing/selftests/landlock/trace_fs_test.c @@ -6,8 +6,10 @@ */ #define _GNU_SOURCE +#include #include #include +#include #include #include #include @@ -23,6 +25,63 @@ #define TRACE_TASK "trace_fs_test" +/* Mirrors TRACE_SEQ_SIZE, conservatively larger than the usable buffer. */ +#define TRACE_SEQUENCE_SIZE 8192 +#define OCTAL_ESCAPE_LEN 4 +#define LONG_PATH_COMPONENT_COUNT 11 +#define LONG_PATH_COMPONENT_LEN 240 +#define LONG_PATH_LEN \ + (LONG_PATH_COMPONENT_COUNT * (LONG_PATH_COMPONENT_LEN + 1) + \ + sizeof("/tmp")) +#define LONG_ESCAPED_PATH_LEN \ + (LONG_PATH_COMPONENT_COUNT * LONG_PATH_COMPONENT_LEN * OCTAL_ESCAPE_LEN) + +static_assert(LONG_ESCAPED_PATH_LEN > TRACE_SEQUENCE_SIZE, + "escaped path must exceed the trace sequence"); +static_assert(LONG_PATH_LEN < PATH_MAX, "path must fit in PATH_MAX"); + +static void create_long_path(struct __test_metadata *const _metadata, + char *path) +{ + size_t path_len; + + strcpy(path, "/tmp"); + path_len = strlen(path); + + set_cap(_metadata, CAP_SYS_ADMIN); + ASSERT_EQ(0, mount("tmpfs", "/tmp", "tmpfs", 0, NULL)); + clear_cap(_metadata, CAP_SYS_ADMIN); + + for (int i = 0; i < LONG_PATH_COMPONENT_COUNT; i++) { + path[path_len++] = '/'; + memset(path + path_len, ' ', LONG_PATH_COMPONENT_LEN); + path_len += LONG_PATH_COMPONENT_LEN; + path[path_len] = '\0'; + ASSERT_EQ(0, mkdir(path, 0700)); + } +} + +static void expect_truncated_path(struct __test_metadata *const _metadata, + const char *const trace, + const char *const event_regex) +{ + static const char marker[] = "\xe2\x80\xa6"; + char *path; + size_t path_len; + + path = malloc(TRACE_SEQUENCE_SIZE); + ASSERT_NE(NULL, path); + ASSERT_EQ(0, tracefs_extract_field(trace, event_regex, "path", path, + TRACE_SEQUENCE_SIZE)); + EXPECT_EQ(path, strstr(path, "/tmp/")); + EXPECT_NE(NULL, strstr(path, "\\040")); + + path_len = strlen(path); + ASSERT_LE(sizeof(marker) - 1, path_len); + EXPECT_STREQ(marker, path + path_len - (sizeof(marker) - 1)); + free(path); +} + /* * Like REGEX_DENY_ACCESS_FS(), but pins the logged field to a specific value * ("0" or "1") so a test can tell a suppressed (quiet) denial from a logged @@ -183,6 +242,107 @@ TEST_F(trace_fs, add_rule_fs) free(buf); } +/* + * Verifies that a path whose escaping exceeds the trace scratch sequence does + * not corrupt a sibling symbolic field. + */ +TEST_F(trace_fs, add_rule_fs_escaped_path_overflow) +{ + static const char access_prefix[] = "execute|write_file|read_file|"; + static const char access_suffix[] = "|ioctl_dev|resolve_unix"; + struct landlock_ruleset_attr ruleset_attr = { + .handled_access_fs = LANDLOCK_ACCESS_FS_READ_FILE, + }; + struct landlock_path_beneath_attr path_beneath = { + .allowed_access = LANDLOCK_ACCESS_FS_READ_FILE, + }; + char path[PATH_MAX]; + char *buf, field_buf[256]; + size_t field_len; + int ruleset_fd, count; + + create_long_path(_metadata, path); + + ruleset_fd = + landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0); + ASSERT_LE(0, ruleset_fd); + path_beneath.parent_fd = open(path, O_PATH | O_DIRECTORY | O_CLOEXEC); + ASSERT_LE(0, path_beneath.parent_fd); + + ASSERT_EQ(0, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH, + &path_beneath, 0)); + ASSERT_EQ(0, close(path_beneath.parent_fd)); + ASSERT_EQ(0, close(ruleset_fd)); + + buf = tracefs_read_buf(); + ASSERT_NE(NULL, buf); + + count = tracefs_count_matches(buf, REGEX_ADD_RULE_FS(TRACE_TASK)); + EXPECT_EQ(1, count) + { + TH_LOG("Expected 1 add_rule_fs event, got %d\n%s", count, buf); + } + + /* + * The marker catches a full revert with any compiler. The symbolic + * field also catches scratch-sequence poisoning when the compiler + * evaluates the overflowing path first, as GCC currently does. + */ + ASSERT_EQ(0, tracefs_extract_field(buf, REGEX_ADD_RULE_FS(TRACE_TASK), + "access_rights", field_buf, + sizeof(field_buf))); + EXPECT_EQ(0, + strncmp(field_buf, access_prefix, sizeof(access_prefix) - 1)); + EXPECT_EQ(NULL, strstr(field_buf, "|refer|")); + field_len = strlen(field_buf); + ASSERT_LE(sizeof(access_suffix) - 1, field_len); + EXPECT_STREQ(access_suffix, + field_buf + field_len - (sizeof(access_suffix) - 1)); + expect_truncated_path(_metadata, buf, REGEX_ADD_RULE_FS(TRACE_TASK)); + + free(buf); +} + +/* + * Verifies that an overflowing denied path does not corrupt its sibling + * symbolic blockers field. + */ +TEST_F(trace_fs, deny_access_fs_escaped_path_overflow) +{ + char path[PATH_MAX]; + char *buf, field_buf[64]; + int count, err; + + create_long_path(_metadata, path); + ASSERT_EQ(0, tracefs_clear_buf()); + + sandbox_child_fs_access(_metadata, "/usr", LANDLOCK_ACCESS_FS_READ_DIR, + LANDLOCK_ACCESS_FS_READ_DIR, path); + + buf = tracefs_read_buf(); + ASSERT_NE(NULL, buf); + + count = tracefs_count_matches(buf, REGEX_DENY_ACCESS_FS(TRACE_TASK)); + EXPECT_EQ(1, count) + { + TH_LOG("Expected 1 deny_access_fs event, got %d\n%s", count, + buf); + } + + /* + * The marker catches a full revert with any compiler. The symbolic + * field also catches scratch-sequence poisoning when the compiler + * evaluates the overflowing path first, as GCC currently does. + */ + err = tracefs_extract_field(buf, REGEX_DENY_ACCESS_FS(TRACE_TASK), + "blockers", field_buf, sizeof(field_buf)); + ASSERT_EQ(0, err); + EXPECT_STREQ("read_dir", field_buf); + expect_truncated_path(_metadata, buf, REGEX_DENY_ACCESS_FS(TRACE_TASK)); + + free(buf); +} + /* * Verifies that an allowed access emits check_rule events (rule matched during * pathwalk) but does NOT emit deny_access events (no denial). From a0de06d0da78a3db53de65dfd7452cc6d111f703 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 3 Sep 2026 23:45:29 +0200 Subject: [PATCH 0931/1198] net: ethernet: cortina: Fix budget accounting The gmac_rx() function returns the remaining NAPI budget, but its caller treats the return value as the number of packets received. An idle poll therefore reports a full budget and remains scheduled. Return the number of received packets instead. Preserve the existing free queue refill accounting by adding that count directly; continuing to subtract it from the budget would invert the refill behavior. Fixes: 4d5ae32f5e1e ("net: ethernet: Add a driver for Gemini gigabit ethernet") Link: https://lore.kernel.org/r/20260509-gemini-ethernet-fixes-v1-4-6c5d20ddc35b@kernel.org Link: https://lore.kernel.org/r/20260512131456.189452-1-pabeni@redhat.com Assisted-by: LLM Reviewed-by: Joe Damato Signed-off-by: Linus Walleij Link: https://patch.msgid.link/20260903-gemini-ethernet-fixes-v2-1-2bbbd598ca6e@kernel.org Signed-off-by: Paolo Abeni --- drivers/net/ethernet/cortina/gemini.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 4c762229ce42..1d9824d1716c 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -1450,6 +1450,7 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) unsigned int frame_len, frag_len; struct gmac_rxdesc *rx = NULL; struct gmac_queue_page *gpage; + unsigned int received = 0; union gmac_rxdesc_0 word0; union gmac_rxdesc_1 word1; union gmac_rxdesc_3 word3; @@ -1545,7 +1546,8 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) napi_gro_frags(&port->napi); skb = NULL; frag_nr = 0; - --budget; + budget--; + received++; } continue; @@ -1565,7 +1567,7 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) port->rx_skb = skb; port->rx_frag_nr = frag_nr; writew(r, ptr_reg); - return budget; + return received; } static int gmac_napi_poll(struct napi_struct *napi, int budget) @@ -1586,7 +1588,7 @@ static int gmac_napi_poll(struct napi_struct *napi, int budget) ++port->rx_napi_exits; } - port->freeq_refill += (budget - received); + port->freeq_refill += received; if (port->freeq_refill > freeq_threshold) { port->freeq_refill -= freeq_threshold; geth_fill_freeq(geth, true); From baa26841cb9a2cdc7e0e99d6854a4e3359bf7393 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 3 Sep 2026 23:45:30 +0200 Subject: [PATCH 0932/1198] net: ethernet: cortina: Finish RX updates before NAPI completion napi_complete_done() releases ownership of the NAPI instance, but the Gemini poll keeps the RX statistics writer section open and updates the free queue after calling it. A new poll can therefore start while the old writer is still active. Finish the statistics and free queue updates before releasing ownership. Only re-enable RX interrupts when napi_complete_done() reports successful completion. Fixes: 4d5ae32f5e1e ("net: ethernet: Add a driver for Gemini gigabit ethernet") Suggested-by: Joe Damato Assisted-by: LLM Signed-off-by: Linus Walleij Link: https://patch.msgid.link/20260903-gemini-ethernet-fixes-v2-2-2bbbd598ca6e@kernel.org Signed-off-by: Paolo Abeni --- drivers/net/ethernet/cortina/gemini.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 1d9824d1716c..6502220362cb 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -1581,12 +1581,10 @@ static int gmac_napi_poll(struct napi_struct *napi, int budget) u64_stats_update_begin(&port->rx_stats_syncp); received = gmac_rx(napi->dev, budget); - if (received < budget) { - napi_gro_flush(napi, false); - napi_complete_done(napi, received); - gmac_enable_rx_irq(napi->dev, 1); + if (received < budget) ++port->rx_napi_exits; - } + + u64_stats_update_end(&port->rx_stats_syncp); port->freeq_refill += received; if (port->freeq_refill > freeq_threshold) { @@ -1594,7 +1592,9 @@ static int gmac_napi_poll(struct napi_struct *napi, int budget) geth_fill_freeq(geth, true); } - u64_stats_update_end(&port->rx_stats_syncp); + if (received < budget && napi_complete_done(napi, received)) + gmac_enable_rx_irq(napi->dev, 1); + return received; } From b856c552f556bc0341c1dbe0bf88e630fd1dc4b7 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 3 Sep 2026 23:45:31 +0200 Subject: [PATCH 0933/1198] net: ethernet: cortina: Count dropped frames as NAPI work The RX loop only consumes budget when it successfully delivers a frame. Error paths keep consuming descriptors without reducing the budget, so a stream of bad frames can process the entire receive ring in one poll. Move the budget accounting to a common end-of-frame path. This counts each completed frame as NAPI work whether it was delivered or dropped, matching the behavior of the vendor driver. Fixes: 4d5ae32f5e1e ("net: ethernet: Add a driver for Gemini gigabit ethernet") Assisted-by: LLM Signed-off-by: Linus Walleij Link: https://patch.msgid.link/20260903-gemini-ethernet-fixes-v2-3-2bbbd598ca6e@kernel.org Signed-off-by: Paolo Abeni --- drivers/net/ethernet/cortina/gemini.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 6502220362cb..33e9763b32fe 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -1501,7 +1501,7 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) skb = NULL; frag_nr = 0; } - continue; + goto next_desc; } page = gpage->page; @@ -1523,7 +1523,7 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) } else if (!skb) { put_page(page); - continue; + goto next_desc; } if (word3.bits32 & EOF_BIT) @@ -1546,10 +1546,8 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) napi_gro_frags(&port->napi); skb = NULL; frag_nr = 0; - budget--; - received++; } - continue; + goto next_desc; err_drop: if (skb) { @@ -1562,6 +1560,13 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) put_page(page); port->stats.rx_dropped++; + +next_desc: + /* Final or single-descriptor fragment, advance things */ + if (word3.bits32 & EOF_BIT) { + budget--; + received++; + } } port->rx_skb = skb; From 6520198c430c81bcc367f0dd5e32f2fb740b9d51 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 3 Sep 2026 23:45:32 +0200 Subject: [PATCH 0934/1198] net: ethernet: cortina: Count RX drops once per frame The absence of a partial skb means either that the driver is not assembling a frame or that the current frame was already dropped. Consequently, repeated descriptor errors can increment rx_dropped more than once, while an orphaned descriptor chain can reach EOF without being counted at all. Track the dropping state across NAPI polls. Clear it at frame boundaries and route mapping failures and orphaned continuations through the common drop path so each discarded frame is counted exactly once. Fixes: 4d5ae32f5e1e ("net: ethernet: Add a driver for Gemini gigabit ethernet") Reported-by: Joe Damato Closes: https://lore.kernel.org/netdev/apdK5aMmvYssz35F@devvm20253.cco0.facebook.com/ Assisted-by: LLM Signed-off-by: Linus Walleij Link: https://patch.msgid.link/20260903-gemini-ethernet-fixes-v2-4-2bbbd598ca6e@kernel.org Signed-off-by: Paolo Abeni --- drivers/net/ethernet/cortina/gemini.c | 41 +++++++++++++++------------ 1 file changed, 23 insertions(+), 18 deletions(-) diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 33e9763b32fe..9ba8524fa371 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -124,6 +124,7 @@ struct gemini_ethernet_port { unsigned int rx_coalesce_nsecs; struct sk_buff *rx_skb; unsigned int rx_frag_nr; + bool rx_dropping; unsigned int freeq_refill; struct gmac_txq txq[TX_QUEUE_NUM]; @@ -1451,6 +1452,7 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) struct gmac_rxdesc *rx = NULL; struct gmac_queue_page *gpage; unsigned int received = 0; + bool dropping = port->rx_dropping; union gmac_rxdesc_0 word0; union gmac_rxdesc_1 word1; union gmac_rxdesc_3 word3; @@ -1472,6 +1474,7 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) w = rw.bits.wptr; while (budget && w != r) { + page = NULL; rx = port->rxq_ring + r; word0 = rx->word0; word1 = rx->word1; @@ -1485,6 +1488,16 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) frame_len = word1.bits.byte_count; page_offs = mapping & ~PAGE_MASK; + if (word3.bits32 & SOF_BIT) { + if (skb) { + napi_free_frags(&port->napi); + port->stats.rx_dropped++; + skb = NULL; + frag_nr = 0; + } + dropping = false; + } + if (!mapping) { netdev_err(netdev, "rxq[%u]: HW BUG: zero DMA desc\n", r); @@ -1495,24 +1508,11 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) gpage = gmac_get_queue_page(geth, port, mapping + PAGE_SIZE); if (!gpage) { dev_err(geth->dev, "could not find mapping\n"); - port->stats.rx_dropped++; - if (skb) { - napi_free_frags(&port->napi); - skb = NULL; - frag_nr = 0; - } - goto next_desc; + goto err_drop; } page = gpage->page; if (word3.bits32 & SOF_BIT) { - if (skb) { - napi_free_frags(&port->napi); - port->stats.rx_dropped++; - skb = NULL; - frag_nr = 0; - } - skb = gmac_skb_if_good_frame(port, word0, frame_len); if (!skb) goto err_drop; @@ -1522,8 +1522,7 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) frag_nr = 0; } else if (!skb) { - put_page(page); - goto next_desc; + goto err_drop; } if (word3.bits32 & EOF_BIT) @@ -1556,21 +1555,26 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) frag_nr = 0; } - if (mapping) + if (page) put_page(page); - port->stats.rx_dropped++; + if (!dropping) { + port->stats.rx_dropped++; + dropping = true; + } next_desc: /* Final or single-descriptor fragment, advance things */ if (word3.bits32 & EOF_BIT) { budget--; received++; + dropping = false; } } port->rx_skb = skb; port->rx_frag_nr = frag_nr; + port->rx_dropping = dropping; writew(r, ptr_reg); return received; } @@ -1900,6 +1904,7 @@ static int gmac_stop(struct net_device *netdev) napi_disable(&port->napi); port->rx_skb = NULL; port->rx_frag_nr = 0; + port->rx_dropping = false; gmac_enable_irq(netdev, 0); gmac_cleanup_rxq(netdev); From e89e88ad41d9f31c829c2af39c48313e8e48d5b0 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 3 Sep 2026 23:45:33 +0200 Subject: [PATCH 0935/1198] net: ethernet: cortina: Count RX descriptors for freeq refill The software free queue provides one buffer fragment for every descriptor moved to an RX queue. The refill heuristic instead advances by NAPI work, which counts frames. A fragmented or discarded frame can consume several queue entries while adding only one to the refill count. Count the RX descriptors as they are consumed and report that separately from NAPI work. Use the descriptor count to drive free queue refills. Fixes: 4d5ae32f5e1e ("net: ethernet: Add a driver for Gemini gigabit ethernet") Assisted-by: LLM Reviewed-by: Joe Damato Signed-off-by: Linus Walleij Link: https://patch.msgid.link/20260903-gemini-ethernet-fixes-v2-5-2bbbd598ca6e@kernel.org Signed-off-by: Paolo Abeni --- drivers/net/ethernet/cortina/gemini.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 9ba8524fa371..f08de623e6f7 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -1440,7 +1440,8 @@ static struct sk_buff *gmac_skb_if_good_frame(struct gemini_ethernet_port *port, return skb; } -static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) +static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget, + unsigned int *freeq_consumed) { struct gemini_ethernet_port *port = netdev_priv(netdev); unsigned short m = (1 << port->rxq_order) - 1; @@ -1448,6 +1449,7 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) void __iomem *ptr_reg = port->rxq_rwptr; unsigned int frag_nr = port->rx_frag_nr; struct sk_buff *skb = port->rx_skb; + unsigned int consumed = 0; unsigned int frame_len, frag_len; struct gmac_rxdesc *rx = NULL; struct gmac_queue_page *gpage; @@ -1483,6 +1485,7 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) r++; r &= m; + consumed++; frag_len = word0.bits.buffer_size; frame_len = word1.bits.byte_count; @@ -1575,6 +1578,7 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) port->rx_skb = skb; port->rx_frag_nr = frag_nr; port->rx_dropping = dropping; + *freeq_consumed = consumed; writew(r, ptr_reg); return received; } @@ -1584,18 +1588,19 @@ static int gmac_napi_poll(struct napi_struct *napi, int budget) struct gemini_ethernet_port *port = netdev_priv(napi->dev); struct gemini_ethernet *geth = port->geth; unsigned int freeq_threshold; + unsigned int freeq_consumed; unsigned int received; freeq_threshold = 1 << (geth->freeq_order - 1); u64_stats_update_begin(&port->rx_stats_syncp); - received = gmac_rx(napi->dev, budget); + received = gmac_rx(napi->dev, budget, &freeq_consumed); if (received < budget) ++port->rx_napi_exits; u64_stats_update_end(&port->rx_stats_syncp); - port->freeq_refill += received; + port->freeq_refill += freeq_consumed; if (port->freeq_refill > freeq_threshold) { port->freeq_refill -= freeq_threshold; geth_fill_freeq(geth, true); From 28cc4d5a75bb07d0eb2fa178db355b04483f5aca Mon Sep 17 00:00:00 2001 From: Shixiong Ou Date: Tue, 8 Sep 2026 13:59:41 +0800 Subject: [PATCH 0936/1198] drm/sched: Create a fake device for KUnit tests The DRM scheduler KUnit tests pass NULL for the dev field in drm_sched_init_args, which NULL-pointer dereferences in the drm_sched_job trace event via dev_name() on sched->dev. Give the mock scheduler a device with kunit_device_register(), which is also cleaned up at test exit. A per-function counter keeps the device names unique, since some tests create several mock schedulers. Fixes: 5a99350794fe ("drm/sched: Add scheduler unit testing infrastructure and some basic tests") Cc: stable@vger.kernel.org Signed-off-by: Shixiong Ou Acked-by: Maxime Ripard [phasta: removed static variable init to 0 again] Signed-off-by: Philipp Stanner Link: https://patch.msgid.link/20260908055941.351486-1-oushixiong1025@163.com --- drivers/gpu/drm/scheduler/tests/mock_scheduler.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/gpu/drm/scheduler/tests/mock_scheduler.c b/drivers/gpu/drm/scheduler/tests/mock_scheduler.c index 8e9ae7d980eb..2dfa3efef210 100644 --- a/drivers/gpu/drm/scheduler/tests/mock_scheduler.c +++ b/drivers/gpu/drm/scheduler/tests/mock_scheduler.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2025 Valve Corporation */ +#include + #include "sched_tests.h" /* @@ -288,6 +290,7 @@ static const struct drm_sched_backend_ops drm_mock_scheduler_ops = { */ struct drm_mock_scheduler *drm_mock_sched_new(struct kunit *test, long timeout) { + static unsigned int instance; struct drm_sched_init_args args = { .ops = &drm_mock_scheduler_ops, .num_rqs = DRM_SCHED_PRIORITY_COUNT, @@ -297,11 +300,19 @@ struct drm_mock_scheduler *drm_mock_sched_new(struct kunit *test, long timeout) .name = "drm-mock-scheduler", }; struct drm_mock_scheduler *sched; + struct device *dev; + char name[64]; int ret; sched = kunit_kzalloc(test, sizeof(*sched), GFP_KERNEL); KUNIT_ASSERT_NOT_NULL(test, sched); + snprintf(name, sizeof(name), "%s-%u", args.name, instance++); + dev = kunit_device_register(test, name); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev); + + args.dev = dev; + ret = drm_sched_init(&sched->base, &args); KUNIT_ASSERT_EQ(test, ret, 0); From 313f798f52a5e46b0e419d05f977d40aaeac4106 Mon Sep 17 00:00:00 2001 From: Qinyun Tan Date: Tue, 1 Sep 2026 16:32:31 +0800 Subject: [PATCH 0937/1198] drm/ast: create blend mode property on cursor plane Since commit 860e748bddcc ("drm: ensure blend mode supported if pixel format with alpha exposed"), drm_mode_config_validate() warns when a plane exposes an alpha pixel format but not the "pixel blend mode" property. The ast cursor plane (ARGB4444, ARGB8888) trips this on driver load: [PLANE:37:plane-1] pixel format with alpha exposed but blend mode not setup WARNING: drivers/gpu/drm/drm_mode_config.c:872 at drm_mode_config_validate+0x48f/0x510 [drm] ... Call Trace: drm_dev_register+0x1ce/0x290 [drm] ast_pci_probe+0x19d/0x3f0 [ast] local_pci_probe+0x41/0x90 Per Thomas Zimmermann's review, the ASPEED documentation describes the hardware cursor as blending with straight (non-pre-multiplied) alpha, which corresponds to DRM_MODE_BLEND_COVERAGE. Expose a "pixel blend mode" property advertising only DRM_MODE_BLEND_COVERAGE to make the hardware semantics explicit and silence the warning. Fixes: 860e748bddcc ("drm: ensure blend mode supported if pixel format with alpha exposed") Suggested-by: Thomas Zimmermann Reviewed-by: Thomas Zimmermann Tested-by: Thomas Zimmermann Signed-off-by: Qinyun Tan Signed-off-by: Thomas Zimmermann Link: https://patch.msgid.link/20260901083234.1828755-2-qinyuntan@linux.alibaba.com --- drivers/gpu/drm/ast/ast_cursor.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/ast/ast_cursor.c b/drivers/gpu/drm/ast/ast_cursor.c index fd19c45f2abe..690d4cd1db5e 100644 --- a/drivers/gpu/drm/ast/ast_cursor.c +++ b/drivers/gpu/drm/ast/ast_cursor.c @@ -25,6 +25,7 @@ #include #include +#include #include #include #include @@ -355,6 +356,8 @@ int ast_cursor_plane_init(struct ast_device *ast) } drm_plane_helper_add(cursor_plane, &ast_cursor_plane_helper_funcs); drm_plane_enable_fb_damage_clips(cursor_plane); + drm_plane_create_blend_mode_property(cursor_plane, + BIT(DRM_MODE_BLEND_COVERAGE)); return 0; } From b67f408a0c2427d5d7c682cfbdad87c4ff73265b Mon Sep 17 00:00:00 2001 From: Qinyun Tan Date: Tue, 1 Sep 2026 16:32:32 +0800 Subject: [PATCH 0938/1198] drm/qxl: create blend mode property on primary and cursor planes Since commit 860e748bddcc ("drm: ensure blend mode supported if pixel format with alpha exposed"), drm_mode_config_validate() warns when a plane exposes an alpha pixel format but not the "pixel blend mode" property. Both the qxl primary and cursor planes expose ARGB8888 and trip this on driver load. qxl submits cursors as SPICE_CURSOR_TYPE_ALPHA, which the SPICE protocol explicitly defines as a "pre-multiplied ARGB8888 pixmap" (Spice Protocol, "Cursor channel definition" section [1]). This matches the blend mode userspace has always assumed when the property is not attached. Expose a "pixel blend mode" property advertising only DRM_MODE_BLEND_PREMULTI to make these semantics explicit and silence the warning. The primary plane is the bottom-most plane so its blend mode has no visible effect; advertise the same value there for consistency. No functional change. [1] https://www.spice-space.org/spice-protocol.html Fixes: 860e748bddcc ("drm: ensure blend mode supported if pixel format with alpha exposed") Reviewed-by: Thomas Zimmermann Signed-off-by: Qinyun Tan Signed-off-by: Thomas Zimmermann Link: https://patch.msgid.link/20260901083234.1828755-3-qinyuntan@linux.alibaba.com --- drivers/gpu/drm/qxl/qxl_display.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c index 2fc41fb90aaa..0719fc6a52d5 100644 --- a/drivers/gpu/drm/qxl/qxl_display.c +++ b/drivers/gpu/drm/qxl/qxl_display.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include #include @@ -993,6 +994,9 @@ static struct drm_plane *qxl_create_plane(struct qxl_device *qdev, drm_plane_helper_add(plane, helper_funcs); + drm_plane_create_blend_mode_property(plane, + BIT(DRM_MODE_BLEND_PREMULTI)); + return plane; free_plane: From f2e64f450c1665732505dae8ee34b399da5a5100 Mon Sep 17 00:00:00 2001 From: Qinyun Tan Date: Tue, 1 Sep 2026 16:32:33 +0800 Subject: [PATCH 0939/1198] drm/virtio: create blend mode property on cursor plane Since commit 860e748bddcc ("drm: ensure blend mode supported if pixel format with alpha exposed"), drm_mode_config_validate() warns when a plane exposes an alpha pixel format but not the "pixel blend mode" property. The virtio-gpu cursor plane (HOST_ARGB8888) trips this. The virtio-gpu specification does not define the cursor alpha semantics. The host forwards the cursor pixels verbatim to its display frontends, and the remote cursor protocols among them (SPICE alpha cursors, the VNC "Cursor With Alpha" encoding) both define pre-multiplied alpha, matching what userspace has always assumed when the property is not attached. Expose a "pixel blend mode" property advertising only DRM_MODE_BLEND_PREMULTI to make these semantics explicit and silence the warning. The primary plane only exposes HOST_XRGB8888, so the call is gated to the cursor. No functional change. Fixes: 860e748bddcc ("drm: ensure blend mode supported if pixel format with alpha exposed") Reviewed-by: Thomas Zimmermann Signed-off-by: Qinyun Tan Signed-off-by: Thomas Zimmermann Link: https://patch.msgid.link/20260901083234.1828755-4-qinyuntan@linux.alibaba.com --- drivers/gpu/drm/virtio/virtgpu_plane.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/virtio/virtgpu_plane.c b/drivers/gpu/drm/virtio/virtgpu_plane.c index 1d1b27ece62a..640815af4098 100644 --- a/drivers/gpu/drm/virtio/virtgpu_plane.c +++ b/drivers/gpu/drm/virtio/virtgpu_plane.c @@ -24,6 +24,7 @@ */ #include +#include #include #include #include @@ -609,6 +610,9 @@ struct drm_plane *virtio_gpu_plane_init(struct virtio_gpu_device *vgdev, if (type == DRM_PLANE_TYPE_PRIMARY) drm_plane_enable_fb_damage_clips(plane); + else if (type == DRM_PLANE_TYPE_CURSOR) + drm_plane_create_blend_mode_property(plane, + BIT(DRM_MODE_BLEND_PREMULTI)); return plane; } From 09f7fc4e8e307fcdaa506b3a06cd7b1acffd2584 Mon Sep 17 00:00:00 2001 From: Qinyun Tan Date: Tue, 1 Sep 2026 16:32:34 +0800 Subject: [PATCH 0940/1198] drm/vboxvideo: create blend mode property on planes Since commit 860e748bddcc ("drm: ensure blend mode supported if pixel format with alpha exposed"), drm_mode_config_validate() warns when a plane exposes an alpha pixel format but not the "pixel blend mode" property. Both the vboxvideo primary and cursor planes expose ARGB8888 and trip this on driver load. VirtualBox draws the cursor through the host windowing system, which treats the guest-supplied pointer shape as straight (non-pre-multiplied) alpha: the host frontend loads the pixels verbatim into an unpremultiplied ARGB image before handing them to the host cursor APIs. This corresponds to DRM_MODE_BLEND_COVERAGE. Expose a "pixel blend mode" property advertising only DRM_MODE_BLEND_COVERAGE to make these semantics explicit and silence the warning. The primary plane's alpha channel is ignored by the host (opaque blit) and it is the bottom-most plane anyway; advertise the same value there for consistency. Fixes: 860e748bddcc ("drm: ensure blend mode supported if pixel format with alpha exposed") Acked-by: Thomas Zimmermann Signed-off-by: Qinyun Tan Signed-off-by: Thomas Zimmermann Link: https://patch.msgid.link/20260901083234.1828755-5-qinyuntan@linux.alibaba.com --- drivers/gpu/drm/vboxvideo/vbox_mode.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/vboxvideo/vbox_mode.c b/drivers/gpu/drm/vboxvideo/vbox_mode.c index 8e4e5fc9d3c5..3c41238a8268 100644 --- a/drivers/gpu/drm/vboxvideo/vbox_mode.c +++ b/drivers/gpu/drm/vboxvideo/vbox_mode.c @@ -15,6 +15,7 @@ #include #include +#include #include #include #include @@ -540,6 +541,9 @@ static struct drm_plane *vbox_create_plane(struct vbox_private *vbox, drm_plane_helper_add(plane, helper_funcs); + drm_plane_create_blend_mode_property(plane, + BIT(DRM_MODE_BLEND_COVERAGE)); + return plane; free_plane: From fedf002d7d08bee36693aacd1ade2ba39351ea91 Mon Sep 17 00:00:00 2001 From: Karl Mehltretter Date: Sat, 5 Sep 2026 10:04:26 +0200 Subject: [PATCH 0941/1198] drm/adp: Drop the select of the nonexistent CONFIG_DRM_KMS_DMA_HELPER There is no Kconfig symbol CONFIG_DRM_KMS_DMA_HELPER. The former CONFIG_DRM_KMS_CMA_HELPER was removed by commit 09717af7d13d ("drm: Remove CONFIG_DRM_KMS_CMA_HELPER option") before this driver was added, so the select does nothing. The driver already selects CONFIG_DRM_GEM_DMA_HELPER, which is what it needs. Remove the dead line. Fixes: 332122eba628 ("drm: adp: Add Apple Display Pipe driver") Assisted-by: LLM Signed-off-by: Karl Mehltretter Reviewed-by: Thomas Zimmermann Signed-off-by: Thomas Zimmermann Link: https://patch.msgid.link/20260905080426.34224-1-kmehltretter@gmail.com --- drivers/gpu/drm/adp/Kconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/adp/Kconfig b/drivers/gpu/drm/adp/Kconfig index 9fcc27eb200d..acfa21ee06d2 100644 --- a/drivers/gpu/drm/adp/Kconfig +++ b/drivers/gpu/drm/adp/Kconfig @@ -6,7 +6,6 @@ config DRM_ADP select DRM_KMS_HELPER select DRM_BRIDGE_CONNECTOR select DRM_DISPLAY_HELPER - select DRM_KMS_DMA_HELPER select DRM_GEM_DMA_HELPER select DRM_PANEL_BRIDGE select VIDEOMODE_HELPERS From f97802dd98b27e45c04293f9926f07642578b23f Mon Sep 17 00:00:00 2001 From: Karl Mehltretter Date: Sat, 5 Sep 2026 10:03:44 +0200 Subject: [PATCH 0942/1198] drm/logicvc: Drop the select of the nonexistent CONFIG_DRM_KMS_DMA_HELPER CONFIG_DRM_KMS_CMA_HELPER was removed by commit 09717af7d13d ("drm: Remove CONFIG_DRM_KMS_CMA_HELPER option"). When commit 6bcfe8eaeef0 ("drm/fb: rename FB CMA helpers to FB DMA helpers") later renamed the select in this Kconfig to CONFIG_DRM_KMS_DMA_HELPER, no symbol of that name existed, and git log -S finds no Kconfig file that has defined one since. The select is silently ignored. The driver already selects CONFIG_DRM_GEM_DMA_HELPER, which is what it needs. Remove the dead line. Fixes: 6bcfe8eaeef0 ("drm/fb: rename FB CMA helpers to FB DMA helpers") Assisted-by: LLM Signed-off-by: Karl Mehltretter Reviewed-by: Thomas Zimmermann Signed-off-by: Thomas Zimmermann Link: https://patch.msgid.link/20260905080344.34077-1-kmehltretter@gmail.com --- drivers/gpu/drm/logicvc/Kconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/logicvc/Kconfig b/drivers/gpu/drm/logicvc/Kconfig index 579a358ed5cf..11aae1626199 100644 --- a/drivers/gpu/drm/logicvc/Kconfig +++ b/drivers/gpu/drm/logicvc/Kconfig @@ -4,7 +4,6 @@ config DRM_LOGICVC depends on OF || COMPILE_TEST select DRM_CLIENT_SELECTION select DRM_KMS_HELPER - select DRM_KMS_DMA_HELPER select DRM_GEM_DMA_HELPER select REGMAP select REGMAP_MMIO From 4eef4ab3aa3a32725e5bc79032c722f9f4a90172 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Tue, 1 Sep 2026 14:33:18 +0200 Subject: [PATCH 0943/1198] s390/pai: Use PAI PMU index as parameter replacing event Use PAI PMU index value as function argument instead of pointer to struct perf_event. Only that index value is used inside functions pai_alloc_cpu() and pai_event_destroy_cpu(). No functional change. Signed-off-by: Thomas Richter Reviewed-by: Sumanth Korikkar Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/perf_pai.c | 25 ++++++++++++------------- 1 file changed, 12 insertions(+), 13 deletions(-) diff --git a/arch/s390/kernel/perf_pai.c b/arch/s390/kernel/perf_pai.c index 5c18c8b82ab7..109b15227d8f 100644 --- a/arch/s390/kernel/perf_pai.c +++ b/arch/s390/kernel/perf_pai.c @@ -140,16 +140,14 @@ static void pai_free(struct pai_mapptr *mp) /* Adjust usage counters and remove allocated memory when all users are * gone. */ -static void pai_event_destroy_cpu(struct perf_event *event, int cpu) +static void pai_event_destroy_cpu(int idx, int cpu) { - int idx = PAI_PMU_IDX(event); struct pai_mapptr *mp = per_cpu_ptr(pai_root[idx].mapptr, cpu); struct pai_map *cpump = mp->mapptr; mutex_lock(&pai_reserve_mutex); - debug_sprintf_event(paidbg, 5, "%s event %#llx idx %d cpu %d users %d " - "refcnt %u\n", __func__, event->attr.config, idx, - event->cpu, cpump->active_events, + debug_sprintf_event(paidbg, 5, "%s users %d refcnt %u\n", + __func__, cpump->active_events, refcount_read(&cpump->refcnt)); if (refcount_dec_and_test(&cpump->refcnt)) pai_free(mp); @@ -159,17 +157,17 @@ static void pai_event_destroy_cpu(struct perf_event *event, int cpu) static void pai_event_destroy(struct perf_event *event) { - int cpu; + int cpu = 0, idx = PAI_PMU_IDX(event); free_page(PAI_SAVE_AREA(event)); if (event->cpu == -1) { struct cpumask *mask = PAI_CPU_MASK(event); for_each_cpu(cpu, mask) - pai_event_destroy_cpu(event, cpu); + pai_event_destroy_cpu(idx, cpu); kfree(mask); } else { - pai_event_destroy_cpu(event, event->cpu); + pai_event_destroy_cpu(idx, event->cpu); } } @@ -241,12 +239,12 @@ static u64 paicrypt_getall(struct perf_event *event) * * Allocate the memory for the event. */ -static int pai_alloc_cpu(struct perf_event *event, int cpu) +static int pai_alloc_cpu(int idx, int cpu) { - int rc, idx = PAI_PMU_IDX(event); struct pai_map *cpump = NULL; bool need_paiext_cb = false; struct pai_mapptr *mp; + int rc; mutex_lock(&pai_reserve_mutex); /* Allocate root node */ @@ -318,6 +316,7 @@ static int pai_alloc_cpu(struct perf_event *event, int cpu) static int pai_alloc(struct perf_event *event) { + int idx = PAI_PMU_IDX(event); struct cpumask *maskptr; int cpu, rc = -ENOMEM; @@ -326,10 +325,10 @@ static int pai_alloc(struct perf_event *event) goto out; for_each_online_cpu(cpu) { - rc = pai_alloc_cpu(event, cpu); + rc = pai_alloc_cpu(idx, cpu); if (rc) { for_each_cpu(cpu, maskptr) - pai_event_destroy_cpu(event, cpu); + pai_event_destroy_cpu(idx, cpu); kfree(maskptr); goto out; } @@ -392,7 +391,7 @@ static int pai_event_init(struct perf_event *event, int idx) } if (event->cpu >= 0) - rc = pai_alloc_cpu(event, event->cpu); + rc = pai_alloc_cpu(idx, event->cpu); else rc = pai_alloc(event); if (rc) { From e8df39dacb7d98d2b2aea431ca652d9fadf5efa3 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Tue, 1 Sep 2026 14:33:19 +0200 Subject: [PATCH 0944/1198] s390/pai: Move locking to event init and delete Move mutex locking from per CPU allocation to event allocation. No functional change. Signed-off-by: Thomas Richter Reviewed-by: Sumanth Korikkar Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/perf_pai.c | 25 ++++++++++++------------- 1 file changed, 12 insertions(+), 13 deletions(-) diff --git a/arch/s390/kernel/perf_pai.c b/arch/s390/kernel/perf_pai.c index 109b15227d8f..c333158cc945 100644 --- a/arch/s390/kernel/perf_pai.c +++ b/arch/s390/kernel/perf_pai.c @@ -138,21 +138,19 @@ static void pai_free(struct pai_mapptr *mp) } /* Adjust usage counters and remove allocated memory when all users are - * gone. + * gone. Called under mutex_lock. */ static void pai_event_destroy_cpu(int idx, int cpu) { struct pai_mapptr *mp = per_cpu_ptr(pai_root[idx].mapptr, cpu); struct pai_map *cpump = mp->mapptr; - mutex_lock(&pai_reserve_mutex); debug_sprintf_event(paidbg, 5, "%s users %d refcnt %u\n", __func__, cpump->active_events, refcount_read(&cpump->refcnt)); if (refcount_dec_and_test(&cpump->refcnt)) pai_free(mp); pai_root_free(idx); - mutex_unlock(&pai_reserve_mutex); } static void pai_event_destroy(struct perf_event *event) @@ -160,6 +158,7 @@ static void pai_event_destroy(struct perf_event *event) int cpu = 0, idx = PAI_PMU_IDX(event); free_page(PAI_SAVE_AREA(event)); + mutex_lock(&pai_reserve_mutex); if (event->cpu == -1) { struct cpumask *mask = PAI_CPU_MASK(event); @@ -169,6 +168,7 @@ static void pai_event_destroy(struct perf_event *event) } else { pai_event_destroy_cpu(idx, event->cpu); } + mutex_unlock(&pai_reserve_mutex); } static void paicrypt_event_destroy(struct perf_event *event) @@ -232,12 +232,10 @@ static u64 paicrypt_getall(struct perf_event *event) return sum; } -/* Check concurrent access of counting and sampling for crypto events. - * This function is called in process context and it is save to block. - * When the event initialization functions fails, no other call back will - * be invoked. - * - * Allocate the memory for the event. +/* Allocate all per-CPU data structures. This function is called in + * process context and can block. In case of error all partly allocated + * memory is released and the reference counters adjusted correctly. + * Called under mutex_lock. */ static int pai_alloc_cpu(int idx, int cpu) { @@ -246,11 +244,10 @@ static int pai_alloc_cpu(int idx, int cpu) struct pai_mapptr *mp; int rc; - mutex_lock(&pai_reserve_mutex); /* Allocate root node */ rc = pai_root_alloc(idx); if (rc) - goto unlock; + goto out; /* Allocate node for this event */ mp = per_cpu_ptr(pai_root[idx].mapptr, cpu); @@ -308,12 +305,12 @@ static int pai_alloc_cpu(int idx, int cpu) */ pai_root_free(idx); } -unlock: - mutex_unlock(&pai_reserve_mutex); +out: /* If rc is non-zero, no increment of counter/sampler was done. */ return rc; } +/* Called under mutex_lock */ static int pai_alloc(struct perf_event *event) { int idx = PAI_PMU_IDX(event); @@ -390,10 +387,12 @@ static int pai_event_init(struct perf_event *event, int idx) } } + mutex_lock(&pai_reserve_mutex); if (event->cpu >= 0) rc = pai_alloc_cpu(idx, event->cpu); else rc = pai_alloc(event); + mutex_unlock(&pai_reserve_mutex); if (rc) { free_page(PAI_SAVE_AREA(event)); goto out; From 9ecc4d033879f7761f2df07e20cd2fbec00fd90b Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Tue, 1 Sep 2026 14:33:20 +0200 Subject: [PATCH 0945/1198] s390/pai: Support CPU hotplug for PMU PAI The command 'perf stat -e pai_crypto/CRYPTO_ALL/ -- ' crashes the kernel when CPUs are hotplug added during that run. Root cause is the missing allocation of per-CPU data structures for that new CPU. The allocation is dynamic and the first event that has task context creates such a structure for each online CPU. This is not sufficient. CPUs may be offline during event creation and can be set online during the perf run time. For example commands # echo 0 > /sys/devices/system/cpu/cpu1/online # perf stat -e cycles -i -- stress-ng -t10s --matrix X # sleep 1 # echo 1 > /sys/devices/system/cpu/cpu1/online Currently without a CPU hotplug handler, that new CPU has no per-CPU data infrastructure. The scheduler runs PMU call back function pai_add() to install the PMU support for that CPU before the task is being scheduled on that new CPU. In pai_add() instructions mp = this_cpu_ptr(pai_root[idx].mapptr); cpump = mp->mapptr; return a NULL pointer and the result is a kernel panic as variable cpump is used inside that function. Add CPU hotplug support for CPU add and delete and create the necessary per-CPU data infrastructure during CPU hotplug add processing. Same for CPU hotplug remove. This is done when the CPU is offline to ensure the data structures are available when CPU is made online and tasks are scheduled on it. [hca@linux.ibm.com: fixup error path in pai_init()] Cc: stable@vger.kernel.org # v6.19 Fixes: 582cc1b28e8c ("s390/pai_ext: Enable per-task and system-wide sampling event") Fixes: 9f66572f2889 ("s390/pai_crypto: Enable per-task and system-wide sampling event") Signed-off-by: Thomas Richter Reviewed-by: Jan Polensky Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/pai.h | 1 - arch/s390/kernel/perf_pai.c | 178 ++++++++++++++++++++++++++---------- 2 files changed, 128 insertions(+), 51 deletions(-) diff --git a/arch/s390/include/asm/pai.h b/arch/s390/include/asm/pai.h index 534d0320e2aa..a3456a36aaa7 100644 --- a/arch/s390/include/asm/pai.h +++ b/arch/s390/include/asm/pai.h @@ -76,7 +76,6 @@ static __always_inline void pai_kernel_exit(struct pt_regs *regs) } #define PAI_SAVE_AREA(x) ((x)->hw.event_base) -#define PAI_CPU_MASK(x) ((x)->hw.addr_filters) #define PAI_PMU_IDX(x) ((x)->hw.last_tag) #define PAI_SWLIST(x) (&(x)->hw.tp_list) diff --git a/arch/s390/kernel/perf_pai.c b/arch/s390/kernel/perf_pai.c index c333158cc945..013c3dae21ec 100644 --- a/arch/s390/kernel/perf_pai.c +++ b/arch/s390/kernel/perf_pai.c @@ -67,6 +67,7 @@ struct pai_mapptr { static struct pai_root { /* Anchor to per CPU data */ refcount_t refcnt; /* Overall active events */ + atomic_t tskctx; /* Overall per-task events */ struct pai_mapptr __percpu *mapptr; } pai_root[PAI_PMU_MAX]; @@ -93,14 +94,15 @@ struct pai_pmu { /* Define PAI PMU characteristics */ static struct pai_pmu pai_pmu[]; /* Forward declaration */ /* Free per CPU data when the last event is removed. */ -static void pai_root_free(int idx) +static void pai_root_free(int idx, int tasks) { - if (refcount_dec_and_test(&pai_root[idx].refcnt)) { + if (refcount_sub_and_test(tasks, &pai_root[idx].refcnt)) { free_percpu(pai_root[idx].mapptr); pai_root[idx].mapptr = NULL; } - debug_sprintf_event(paidbg, 5, "%s root[%d].refcount %d\n", __func__, - idx, refcount_read(&pai_root[idx].refcnt)); + debug_sprintf_event(paidbg, 5, "%s root[%d].refcount %d tskctx %d\n", + __func__, idx, refcount_read(&pai_root[idx].refcnt), + atomic_read(&pai_root[idx].tskctx)); } /* @@ -137,20 +139,36 @@ static void pai_free(struct pai_mapptr *mp) mp->mapptr = NULL; } -/* Adjust usage counters and remove allocated memory when all users are - * gone. Called under mutex_lock. - */ -static void pai_event_destroy_cpu(int idx, int cpu) +/* Called under mutex_lock */ +static void pai_event_destroy_cpu(int idx, int cpu, bool hotplug) { - struct pai_mapptr *mp = per_cpu_ptr(pai_root[idx].mapptr, cpu); - struct pai_map *cpump = mp->mapptr; + struct pai_mapptr *mp; + struct pai_map *cpump; + int tasks = 1; - debug_sprintf_event(paidbg, 5, "%s users %d refcnt %u\n", - __func__, cpump->active_events, - refcount_read(&cpump->refcnt)); - if (refcount_dec_and_test(&cpump->refcnt)) + /* Check reference count and return when all gone. + * 1. An event is installed on online CPU X. + * 2. CPU x is offlined and the per-CPU data is removed. + * 3. Event is destroyed via close system call. + */ + if (!refcount_read(&pai_root[idx].refcnt)) + return; /* No events at all */ + mp = per_cpu_ptr(pai_root[idx].mapptr, cpu); + if (!mp || !mp->mapptr) /* No events on that CPU */ + return; + + /* When hotplug is true, invocation is from CPU hotplug callback. + * Delete per-CPU resource and adjust refcnt when per-task events + * are currently active. This can be more than one. + * In this case adjust counters. + */ + if (hotplug) + tasks = atomic_read(&pai_root[idx].tskctx); + + cpump = mp->mapptr; + if (refcount_sub_and_test(tasks, &cpump->refcnt)) pai_free(mp); - pai_root_free(idx); + pai_root_free(idx, tasks); } static void pai_event_destroy(struct perf_event *event) @@ -158,17 +176,17 @@ static void pai_event_destroy(struct perf_event *event) int cpu = 0, idx = PAI_PMU_IDX(event); free_page(PAI_SAVE_AREA(event)); + cpus_read_lock(); mutex_lock(&pai_reserve_mutex); if (event->cpu == -1) { - struct cpumask *mask = PAI_CPU_MASK(event); - - for_each_cpu(cpu, mask) - pai_event_destroy_cpu(idx, cpu); - kfree(mask); + atomic_dec(&pai_root[idx].tskctx); + for_each_online_cpu(cpu) + pai_event_destroy_cpu(idx, cpu, false); } else { - pai_event_destroy_cpu(idx, event->cpu); + pai_event_destroy_cpu(idx, event->cpu, false); } mutex_unlock(&pai_reserve_mutex); + cpus_read_unlock(); } static void paicrypt_event_destroy(struct perf_event *event) @@ -232,17 +250,25 @@ static u64 paicrypt_getall(struct perf_event *event) return sum; } -/* Allocate all per-CPU data structures. This function is called in - * process context and can block. In case of error all partly allocated - * memory is released and the reference counters adjusted correctly. - * Called under mutex_lock. - */ -static int pai_alloc_cpu(int idx, int cpu) +/* Called under mutex_lock */ +static int pai_alloc_cpu(int idx, int cpu, bool hotplug) { struct pai_map *cpump = NULL; bool need_paiext_cb = false; struct pai_mapptr *mp; - int rc; + int tasks = 1, rc = 0; + + /* When hotplug is true, invocation is from CPU hotplug callback. + * Allocate per-CPU resource when per-task events are currently active. + * This can be more than one. In this case adjust all reference + * counters. Otherwise return, this ensures memory is only allocated + * when needed. + */ + if (hotplug) { + tasks = atomic_read(&pai_root[idx].tskctx); + if (!tasks) + goto out; + } /* Allocate root node */ rc = pai_root_alloc(idx); @@ -291,26 +317,42 @@ static int pai_alloc_cpu(int idx, int cpu) goto undo; } INIT_LIST_HEAD(&cpump->syswide_list); - refcount_set(&cpump->refcnt, 1); + refcount_set(&cpump->refcnt, tasks); rc = 0; } else { - refcount_inc(&cpump->refcnt); + refcount_add(tasks, &cpump->refcnt); } + /* If tasks is greater than 1, we are called from CPU hotplug path + * and need to adjust the pai_root[idx].refcnt by the number of + * per-process events. Function pai_root_alloc(idx) already + * incremented by one. Adjust for the rest. + */ + if (tasks > 1) + refcount_add(tasks - 1, &pai_root[idx].refcnt); undo: if (rc) { /* Error in allocation of event, decrement anchor. Since * the event in not created, its destroy() function is never * invoked. Adjust the reference counter for the anchor. + * The failure happened in the case of variable + * cpump == NULL branch above. The pai_root[XXX].refcnt has + * been incremented by one. Then the per-CPU allocation + * failed, so decrement it by one, regardless of tasks. */ - pai_root_free(idx); + pai_root_free(idx, 1); } out: /* If rc is non-zero, no increment of counter/sampler was done. */ return rc; } -/* Called under mutex_lock */ +/* Check concurrent access of counting and sampling for PAI events. + * This function is called in process context and it is safe to block. + * When the event initialization functions fails, no other call back will + * be invoked. + * Called under mutex_lock. + */ static int pai_alloc(struct perf_event *event) { int idx = PAI_PMU_IDX(event); @@ -322,24 +364,20 @@ static int pai_alloc(struct perf_event *event) goto out; for_each_online_cpu(cpu) { - rc = pai_alloc_cpu(idx, cpu); + rc = pai_alloc_cpu(idx, cpu, false); if (rc) { for_each_cpu(cpu, maskptr) - pai_event_destroy_cpu(idx, cpu); - kfree(maskptr); - goto out; + pai_event_destroy_cpu(idx, cpu, false); + goto undo; } cpumask_set_cpu(cpu, maskptr); } - /* - * On error all cpumask are freed and all events have been destroyed. - * Save of which CPUs data structures have been allocated for. - * Release them in pai_event_destroy call back function - * for this event. - */ - PAI_CPU_MASK(event) = maskptr; rc = 0; + /* Trace per-task events for CPU hotplug. */ + atomic_inc(&pai_root[idx].tskctx); +undo: + kfree(maskptr); out: return rc; } @@ -387,12 +425,14 @@ static int pai_event_init(struct perf_event *event, int idx) } } + cpus_read_lock(); mutex_lock(&pai_reserve_mutex); if (event->cpu >= 0) - rc = pai_alloc_cpu(idx, event->cpu); + rc = pai_alloc_cpu(idx, event->cpu, false); else rc = pai_alloc(event); mutex_unlock(&pai_reserve_mutex); + cpus_read_unlock(); if (rc) { free_page(PAI_SAVE_AREA(event)); goto out; @@ -1237,8 +1277,35 @@ static int __init paipmu_setup(void) return install_ok; } +static int pai_online_cpu(unsigned int cpu) +{ + int rc; + + mutex_lock(&pai_reserve_mutex); + rc = pai_alloc_cpu(PAI_PMU_CRYPTO, cpu, true); + if (rc) + goto out; + rc = pai_alloc_cpu(PAI_PMU_EXT, cpu, true); + if (rc) + pai_event_destroy_cpu(PAI_PMU_CRYPTO, cpu, true); +out: + mutex_unlock(&pai_reserve_mutex); + return rc; +} + +static int pai_offline_cpu(unsigned int cpu) +{ + mutex_lock(&pai_reserve_mutex); + pai_event_destroy_cpu(PAI_PMU_CRYPTO, cpu, true); + pai_event_destroy_cpu(PAI_PMU_EXT, cpu, true); + mutex_unlock(&pai_reserve_mutex); + return 0; +} + static int __init pai_init(void) { + int state, rc; + /* Setup s390dbf facility */ paidbg = debug_register("pai", 1, 1, 128); if (!paidbg) { @@ -1247,13 +1314,24 @@ static int __init pai_init(void) } debug_register_view(paidbg, &debug_sprintf_view); - if (!paipmu_setup()) { - /* No PMU registration, no need for debug buffer */ - debug_unregister_view(paidbg, &debug_sprintf_view); - debug_unregister(paidbg); - return -ENODEV; - } + /* CPUHP_BP_PREPARE_DYN --> before CPU is brought online */ + state = cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "perf/pai:prepare", + pai_online_cpu, pai_offline_cpu); + rc = state < 0 ? state : 0; + if (rc < 0) + goto out_debug; + + rc = -ENODEV; + if (!paipmu_setup()) + goto out_cpuhp; return 0; + +out_cpuhp: + cpuhp_remove_state(state); +out_debug: + debug_unregister_view(paidbg, &debug_sprintf_view); + debug_unregister(paidbg); + return rc; } device_initcall(pai_init); From b1eb31d533cdfcae1011ed53850d52f36afe5774 Mon Sep 17 00:00:00 2001 From: Mikhail Zaslonko Date: Thu, 3 Sep 2026 15:07:31 +0200 Subject: [PATCH 0946/1198] s390/debug: Fix NULL pointer dereference in debug_set_level() Commit a2cec6863709 ("s390/debug: Add s390dbf kernel parameter") incorrectly removed a null-id check from debug_set_level(), introducing a possible NULL pointer dereference for debug-API users that put debug_register() results unchecked into debug_set_level(). Fix this by moving the check from the internal _debug_set_level() variant back to the external debug_set_level() wrapper. Fixes: a2cec6863709 ("s390/debug: Add s390dbf kernel parameter") Signed-off-by: Mikhail Zaslonko Reviewed-by: Peter Oberparleiter Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/debug.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index 14d2b58ad093..e06abf1dbc21 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -1074,9 +1074,6 @@ static void _debug_set_level(debug_info_t *id, int new_level) { unsigned long flags; - if (!id) - return; - if (new_level == DEBUG_OFF_LEVEL) { pr_info("%s: switched off\n", id->name); } else if ((new_level > DEBUG_MAX_LEVEL) || (new_level < 0)) { @@ -1101,6 +1098,9 @@ static void _debug_set_level(debug_info_t *id, int new_level) */ void debug_set_level(debug_info_t *id, int new_level) { + if (!id) + return; + /* Level specified via kernel parameter takes precedence */ debug_get_param(id->name, &new_level, NULL); From 22d4210bf988047bd30803cd6ef5177f113e4004 Mon Sep 17 00:00:00 2001 From: Mikhail Zaslonko Date: Thu, 3 Sep 2026 15:07:32 +0200 Subject: [PATCH 0947/1198] s390/debug: Do not repeat parameter override notice on debug_set_level() Commit a2cec6863709 ("s390/debug: Add s390dbf kernel parameter") calls debug_get_param() from both debug_info_create() and debug_set_level(). Since debug_get_param() emits the override notice unconditionally, and drivers typically call debug_set_level() right after debug_register(), the same line is printed twice per debug area: s390dbf: 0.0.1234: override level to 6 s390dbf: 0.0.1234: override level to 6 For areas registered per device this is multiplied by the device count. With 's390dbf=0.0.*:6' a system with many DASDs emits a large number of redundant lines during boot. Add a quiet parameter to debug_get_param() and pass quiet=true from debug_set_level(), where the override has already been announced during registration. The remaining callers keep printing the notice. Signed-off-by: Mikhail Zaslonko Reviewed-by: Peter Oberparleiter Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/debug.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index e06abf1dbc21..cf411f203571 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -182,7 +182,7 @@ static struct debug_param_t { static int debug_param_num; /* functions */ -static void debug_get_param(const char *name, int *level, int *pages) +static void debug_get_param(const char *name, int *level, int *pages, bool quiet) { struct debug_param_t *p; int i; @@ -192,11 +192,13 @@ static void debug_get_param(const char *name, int *level, int *pages) if (!glob_match(p->name, name)) continue; if (level && p->level != PARAM_UNSET) { - pr_info("%s: override level to %d\n", name, p->level); + if (!quiet) + pr_info("%s: override level to %d\n", name, p->level); *level = p->level; } if (pages && p->pages != PARAM_UNSET) { - pr_info("%s: override pages to %d\n", name, p->pages); + if (!quiet) + pr_info("%s: override pages to %d\n", name, p->pages); *pages = p->pages; } } @@ -251,7 +253,7 @@ static int __init s390dbf_parse(char *arg) * regular memory allocations are possible. */ for (i = 0, id = __s390dbf_info; &id[i] < __s390dbf_info_end; i++) - debug_get_param(id[i]->name, &id[i]->level, NULL); + debug_get_param(id[i]->name, &id[i]->level, NULL, false); return rc; } @@ -395,7 +397,7 @@ static debug_info_t *debug_info_create(const char *name, int pages_per_area, int level = DEBUG_DEFAULT_LEVEL; debug_info_t *rc; - debug_get_param(name, &level, &pages_per_area); + debug_get_param(name, &level, &pages_per_area, false); rc = debug_info_alloc(name, pages_per_area, nr_areas, buf_size, level, ALL_AREAS); if (!rc) goto out; @@ -960,7 +962,7 @@ void debug_register_static(debug_info_t *id, int pages_per_area, int nr_areas) return; } - debug_get_param(id->name, &id->level, &pages_per_area); + debug_get_param(id->name, &id->level, &pages_per_area, false); copy = debug_info_alloc("", pages_per_area, nr_areas, id->buf_size, id->level, ALL_AREAS); if (!copy) { @@ -1101,8 +1103,11 @@ void debug_set_level(debug_info_t *id, int new_level) if (!id) return; - /* Level specified via kernel parameter takes precedence */ - debug_get_param(id->name, &new_level, NULL); + /* + * Level specified via kernel parameter takes precedence. The override + * was already announced during registration, so stay quiet here. + */ + debug_get_param(id->name, &new_level, NULL, true); _debug_set_level(id, new_level); } From 0945285e6cd67ee87e9313fb10221aba5bd69c6a Mon Sep 17 00:00:00 2001 From: Mikhail Zaslonko Date: Thu, 3 Sep 2026 15:07:33 +0200 Subject: [PATCH 0948/1198] s390/debug: Fix race between debug area resize and event logging Trace functions check for non-NULL id->areas without lock to minimize overhead. This opens a race window where a NULL pointer dereference occurs if id->areas is set to NULL (e.g. via echo 0 > ../pages) after the check and before id->lock is taken. Fix this by rechecking id->areas under lock. Signed-off-by: Mikhail Zaslonko Reviewed-by: Peter Oberparleiter Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/debug.c | 27 ++++++++++++++++++++------- 1 file changed, 20 insertions(+), 7 deletions(-) diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index cf411f203571..b5bf8284dbfc 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -1283,7 +1283,7 @@ void debug_set_critical(void) debug_entry_t *debug_event_common(debug_info_t *id, int level, const void *buf, int len) { - debug_entry_t *active; + debug_entry_t *active = NULL; unsigned long flags; if (!debug_active || !id->areas) @@ -1294,6 +1294,8 @@ debug_entry_t *debug_event_common(debug_info_t *id, int level, const void *buf, } else { raw_spin_lock_irqsave(&id->lock, flags); } + if (!id->areas) + goto out; do { active = get_active_entry(id); memcpy(DEBUG_DATA(active), buf, min(len, id->buf_size)); @@ -1303,7 +1305,7 @@ debug_entry_t *debug_event_common(debug_info_t *id, int level, const void *buf, len -= id->buf_size; buf += id->buf_size; } while (len > 0); - +out: raw_spin_unlock_irqrestore(&id->lock, flags); return active; } @@ -1316,7 +1318,7 @@ EXPORT_SYMBOL(debug_event_common); debug_entry_t *debug_exception_common(debug_info_t *id, int level, const void *buf, int len) { - debug_entry_t *active; + debug_entry_t *active = NULL; unsigned long flags; if (!debug_active || !id->areas) @@ -1327,6 +1329,8 @@ debug_entry_t *debug_exception_common(debug_info_t *id, int level, } else { raw_spin_lock_irqsave(&id->lock, flags); } + if (!id->areas) + goto out; do { active = get_active_entry(id); memcpy(DEBUG_DATA(active), buf, min(len, id->buf_size)); @@ -1336,7 +1340,7 @@ debug_entry_t *debug_exception_common(debug_info_t *id, int level, len -= id->buf_size; buf += id->buf_size; } while (len > 0); - +out: raw_spin_unlock_irqrestore(&id->lock, flags); return active; } @@ -1362,7 +1366,7 @@ static inline int debug_count_numargs(char *string) debug_entry_t *__debug_sprintf_event(debug_info_t *id, int level, char *string, ...) { debug_sprintf_entry_t *curr_event; - debug_entry_t *active; + debug_entry_t *active = NULL; unsigned long flags; int numargs, idx; va_list ap; @@ -1377,6 +1381,8 @@ debug_entry_t *__debug_sprintf_event(debug_info_t *id, int level, char *string, } else { raw_spin_lock_irqsave(&id->lock, flags); } + if (!id->areas) + goto out; active = get_active_entry(id); curr_event = (debug_sprintf_entry_t *) DEBUG_DATA(active); va_start(ap, string); @@ -1385,6 +1391,7 @@ debug_entry_t *__debug_sprintf_event(debug_info_t *id, int level, char *string, curr_event->args[idx] = va_arg(ap, long); va_end(ap); debug_finish_entry(id, active, level, 0); +out: raw_spin_unlock_irqrestore(&id->lock, flags); return active; @@ -1397,7 +1404,7 @@ EXPORT_SYMBOL(__debug_sprintf_event); debug_entry_t *__debug_sprintf_exception(debug_info_t *id, int level, char *string, ...) { debug_sprintf_entry_t *curr_event; - debug_entry_t *active; + debug_entry_t *active = NULL; unsigned long flags; int numargs, idx; va_list ap; @@ -1413,6 +1420,8 @@ debug_entry_t *__debug_sprintf_exception(debug_info_t *id, int level, char *stri } else { raw_spin_lock_irqsave(&id->lock, flags); } + if (!id->areas) + goto out; active = get_active_entry(id); curr_event = (debug_sprintf_entry_t *)DEBUG_DATA(active); va_start(ap, string); @@ -1421,6 +1430,7 @@ debug_entry_t *__debug_sprintf_exception(debug_info_t *id, int level, char *stri curr_event->args[idx] = va_arg(ap, long); va_end(ap); debug_finish_entry(id, active, level, 1); +out: raw_spin_unlock_irqrestore(&id->lock, flags); return active; @@ -1663,9 +1673,11 @@ static void debug_flush(debug_info_t *id, int area) unsigned long flags; int i, j; - if (!id || !id->areas) + if (!id) return; raw_spin_lock_irqsave(&id->lock, flags); + if (!id->areas) + goto out; if (area == DEBUG_FLUSH_ALL) { id->active_area = 0; memset(id->active_entries, 0, id->nr_areas * sizeof(int)); @@ -1680,6 +1692,7 @@ static void debug_flush(debug_info_t *id, int area) for (i = 0; i < id->pages_per_area; i++) memset(id->areas[area][i], 0, PAGE_SIZE); } +out: raw_spin_unlock_irqrestore(&id->lock, flags); } From 15fa028589c3a2545f0bff355eff06d5844196bf Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Mon, 31 Aug 2026 10:37:33 +0200 Subject: [PATCH 0949/1198] s390/crypto: Fix skcipher_walk return code handling in aes_s390 The return codes from skcipher_walk_virt() were not properly checked before entering the processing loops in ecb_aes_crypt() and ctr_aes_crypt(). If skcipher_walk_virt() fails, the walk structure may be in an undefined state, and attempting to process data could lead to incorrect behavior or accessing uninitialized memory. Add proper return code checking to ensure correct handling of the walk initialization and walk advance and eventually return to the caller with that return code. Fixes: 7988fb2c03c8 ("crypto: s390/aes - convert to skcipher API") Signed-off-by: Harald Freudenberger Reviewed-by: Holger Dengler Cc: stable@vger.kernel.org # 5.5+ Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/crypto/aes_s390.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c index 62edc66d5478..366ce22d3623 100644 --- a/arch/s390/crypto/aes_s390.c +++ b/arch/s390/crypto/aes_s390.c @@ -129,7 +129,7 @@ static int ecb_aes_crypt(struct skcipher_request *req, unsigned long modifier) return fallback_skcipher_crypt(sctx, req, modifier); ret = skcipher_walk_virt(&walk, req, false); - while ((nbytes = walk.nbytes) != 0) { + while (!ret && ((nbytes = walk.nbytes) != 0)) { /* only use complete blocks */ n = nbytes & ~(AES_BLOCK_SIZE - 1); cpacf_km(sctx->fc | modifier, sctx->key, @@ -233,7 +233,7 @@ static int cbc_aes_crypt(struct skcipher_request *req, unsigned long modifier) return ret; memcpy(param.iv, walk.iv, AES_BLOCK_SIZE); memcpy(param.key, sctx->key, sctx->key_len); - while ((nbytes = walk.nbytes) != 0) { + while (!ret && ((nbytes = walk.nbytes) != 0)) { /* only use complete blocks */ n = nbytes & ~(AES_BLOCK_SIZE - 1); cpacf_kmc(sctx->fc | modifier, ¶m, @@ -359,7 +359,7 @@ static int xts_aes_crypt(struct skcipher_request *req, unsigned long modifier) memcpy(xts_param.key + offset, xts_ctx->key, xts_ctx->key_len); memcpy(xts_param.init, pcc_param.xts, 16); - while ((nbytes = walk.nbytes) != 0) { + while (!ret && ((nbytes = walk.nbytes) != 0)) { /* only use complete blocks */ n = nbytes & ~(AES_BLOCK_SIZE - 1); cpacf_km(xts_ctx->fc | modifier, xts_param.key + offset, @@ -487,7 +487,7 @@ static int fullxts_aes_crypt(struct skcipher_request *req, unsigned long modifi memcpy(fxts_param.tweak, req->iv, AES_BLOCK_SIZE); fxts_param.nap[0] = 0x01; /* initial alpha power (1, little-endian) */ - while ((nbytes = walk.nbytes) != 0) { + while (!ret && ((nbytes = walk.nbytes) != 0)) { /* only use complete blocks */ n = nbytes & ~(AES_BLOCK_SIZE - 1); cpacf_km(xts_ctx->fc | modifier, fxts_param.key + offset, @@ -577,7 +577,7 @@ static int ctr_aes_crypt(struct skcipher_request *req) locked = mutex_trylock(&ctrblk_lock); ret = skcipher_walk_virt(&walk, req, false); - while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) { + while (!ret && ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE)) { n = AES_BLOCK_SIZE; if (nbytes >= 2*AES_BLOCK_SIZE && locked) @@ -596,7 +596,7 @@ static int ctr_aes_crypt(struct skcipher_request *req) /* * final block may be < AES_BLOCK_SIZE, copy only nbytes */ - if (nbytes) { + if (!ret && nbytes) { memset(buf, 0, AES_BLOCK_SIZE); memcpy(buf, walk.src.virt.addr, nbytes); cpacf_kmctr(sctx->fc, sctx->key, buf, buf, From 8b7c3b6914f19caf648d05726a86af6326d3c2c6 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Mon, 31 Aug 2026 10:37:34 +0200 Subject: [PATCH 0950/1198] s390/crypto: Fix missing scrub of temp buffers with AES ctr and gcm algorithm In function ctr_aes_crypt() there is a buffer used to process remaining bytes < AES_BLOCK_SIZE. This buffer was not scrubbed and thus could lead to expose of unwanted data. When the buffer is used explicitly scrub it at the end of the code block to avoid exposure of maybe sensitive data. In a similar way the function gcm_aes_crypt() hat an error path where the CPACF param block was not scrubbed. Instead of return early now these error paths go to end of function where explicit scrubbing is done. Similar with the buffers which are part of the gcm_sg_walk structs from the variables gw_in and gw_out. Fixes: d07f951903fa ("crypto: s390/aes - Fix buffer overread in CTR mode") Signed-off-by: Harald Freudenberger Reviewed-by: Holger Dengler Cc: stable@vger.kernel.org # 6.8+ Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/crypto/aes_s390.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c index 366ce22d3623..10561aa687c7 100644 --- a/arch/s390/crypto/aes_s390.c +++ b/arch/s390/crypto/aes_s390.c @@ -604,6 +604,7 @@ static int ctr_aes_crypt(struct skcipher_request *req) memcpy(walk.dst.virt.addr, buf, nbytes); crypto_inc(walk.iv, AES_BLOCK_SIZE); ret = skcipher_walk_done(&walk, 0); + memzero_explicit(buf, sizeof(buf)); } return ret; @@ -895,10 +896,14 @@ static int gcm_aes_crypt(struct aead_request *req, unsigned int flags) gw_in.ptr, aad_bytes); n = aad_bytes + pc_bytes; - if (gcm_in_walk_done(&gw_in, n) != n) - return -ENOMEM; - if (gcm_out_walk_done(&gw_out, n) != n) - return -ENOMEM; + if (gcm_in_walk_done(&gw_in, n) != n) { + ret = -ENOMEM; + goto out; + } + if (gcm_out_walk_done(&gw_out, n) != n) { + ret = -ENOMEM; + goto out; + } aadlen -= aad_bytes; pclen -= pc_bytes; } while (aadlen + pclen > 0); @@ -910,7 +915,10 @@ static int gcm_aes_crypt(struct aead_request *req, unsigned int flags) } else scatterwalk_map_and_copy(param.t, req->dst, len, taglen, 1); +out: memzero_explicit(¶m, sizeof(param)); + memzero_explicit(gw_in.buf, sizeof(gw_in.buf)); + memzero_explicit(gw_out.buf, sizeof(gw_out.buf)); return ret; } From d1c44a7d085473173bb360b7218a43699c3f56c7 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Mon, 31 Aug 2026 10:37:35 +0200 Subject: [PATCH 0951/1198] s390/crypto: Fix use of mutex in atomic context The AES CTR implementation used a mutex to lock one page of exclusive memory for fast CTR processing. Unfortunately a mutex is not save to use in atomic or interrupt context. So use a binary semaphore instead which is save to use in such environments. Furthermore rework the code to get rid of conditional locking. So restructure the AES CRT code by extracting the main loop into a separate function and just give in information about the (locked) page can be used or not (is not locked). Fixes: 7988fb2c03c8 ("crypto: s390/aes - convert to skcipher API") Suggested-by: Heiko Carstens Signed-off-by: Harald Freudenberger Reviewed-by: Holger Dengler Cc: stable@vger.kernel.org # 5.5+ Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/crypto/aes_s390.c | 63 +++++++++++++++++++++++-------------- 1 file changed, 39 insertions(+), 24 deletions(-) diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c index 10561aa687c7..0be6fa779d2c 100644 --- a/arch/s390/crypto/aes_s390.c +++ b/arch/s390/crypto/aes_s390.c @@ -26,14 +26,14 @@ #include #include #include -#include #include +#include #include #include #include static u8 *ctrblk; -static DEFINE_MUTEX(ctrblk_lock); +static DEFINE_SEMAPHORE(ctrblk_sem, 1); static cpacf_mask_t km_functions, kmc_functions, kmctr_functions, kma_functions; @@ -562,46 +562,61 @@ static unsigned int __ctrblk_init(u8 *ctrptr, u8 *iv, unsigned int nbytes) return n; } +static int __ctr_aes_crypt(struct s390_aes_ctx *sctx, + struct skcipher_walk *walk, bool locked) +{ + unsigned int n, nbytes; + int ret = 0; + u8 *ctrptr; + + while (!ret && ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE)) { + n = AES_BLOCK_SIZE; + if (nbytes >= 2 * AES_BLOCK_SIZE && locked) + n = __ctrblk_init(ctrblk, walk->iv, nbytes); + ctrptr = (n > AES_BLOCK_SIZE) ? ctrblk : walk->iv; + cpacf_kmctr(sctx->fc, sctx->key, walk->dst.virt.addr, + walk->src.virt.addr, n, ctrptr); + if (ctrptr == ctrblk) + memcpy(walk->iv, ctrptr + n - AES_BLOCK_SIZE, + AES_BLOCK_SIZE); + crypto_inc(walk->iv, AES_BLOCK_SIZE); + ret = skcipher_walk_done(walk, nbytes - n); + } + + return ret; +} + static int ctr_aes_crypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct s390_aes_ctx *sctx = crypto_skcipher_ctx(tfm); - u8 buf[AES_BLOCK_SIZE], *ctrptr; struct skcipher_walk walk; - unsigned int n, nbytes; - int ret, locked; + u8 buf[AES_BLOCK_SIZE]; + int ret; if (unlikely(!sctx->fc)) return fallback_skcipher_crypt(sctx, req, 0); - locked = mutex_trylock(&ctrblk_lock); - ret = skcipher_walk_virt(&walk, req, false); - while (!ret && ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE)) { - n = AES_BLOCK_SIZE; + if (ret) + return ret; - if (nbytes >= 2*AES_BLOCK_SIZE && locked) - n = __ctrblk_init(ctrblk, walk.iv, nbytes); - ctrptr = (n > AES_BLOCK_SIZE) ? ctrblk : walk.iv; - cpacf_kmctr(sctx->fc, sctx->key, walk.dst.virt.addr, - walk.src.virt.addr, n, ctrptr); - if (ctrptr == ctrblk) - memcpy(walk.iv, ctrptr + n - AES_BLOCK_SIZE, - AES_BLOCK_SIZE); - crypto_inc(walk.iv, AES_BLOCK_SIZE); - ret = skcipher_walk_done(&walk, nbytes - n); + if (down_trylock(&ctrblk_sem) == 0) { + ret = __ctr_aes_crypt(sctx, &walk, true); + up(&ctrblk_sem); + } else { + ret = __ctr_aes_crypt(sctx, &walk, false); } - if (locked) - mutex_unlock(&ctrblk_lock); + /* * final block may be < AES_BLOCK_SIZE, copy only nbytes */ - if (!ret && nbytes) { + if (!ret && walk.nbytes > 0) { memset(buf, 0, AES_BLOCK_SIZE); - memcpy(buf, walk.src.virt.addr, nbytes); + memcpy(buf, walk.src.virt.addr, walk.nbytes); cpacf_kmctr(sctx->fc, sctx->key, buf, buf, AES_BLOCK_SIZE, walk.iv); - memcpy(walk.dst.virt.addr, buf, nbytes); + memcpy(walk.dst.virt.addr, buf, walk.nbytes); crypto_inc(walk.iv, AES_BLOCK_SIZE); ret = skcipher_walk_done(&walk, 0); memzero_explicit(buf, sizeof(buf)); From 403648373816ae8eb76fe4a393836b0d65fa8f85 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Mon, 31 Aug 2026 10:38:30 +0200 Subject: [PATCH 0952/1198] s390/crypto: Fix return code handling at skcipher_walk_done in PAES algorithms All the 4 PAES cipher processing loops were not checking the return value of skcipher_walk_done() immediately after calling it. This could lead to error masking when both the walk operation failed and a subsequent key conversion was needed (k < n condition). Add immediate error checks after skcipher_walk_done() in all main processing loops (ECB, CBC, CTR, XTS modes) to ensure walk errors are properly propagated and not masked by subsequent operations. With that comes a slight rework around the skcipher_walk_done() invocation. It is now necessary to check if the walk has already been finalized (walk->nbytes is then 0) or not to avoid double de-allocation of resources held by the walk. Fixes: 6cd87cb5ef6c ("s390/crypto: Rework protected key AES for true asynch support") Signed-off-by: Harald Freudenberger Reviewed-by: Holger Dengler Cc: stable@vger.kernel.org # 6.16+ Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/crypto/paes_s390.c | 38 +++++++++++++++++++++++++----------- 1 file changed, 27 insertions(+), 11 deletions(-) diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c index 973436592318..89785ab95e6b 100644 --- a/arch/s390/crypto/paes_s390.c +++ b/arch/s390/crypto/paes_s390.c @@ -432,8 +432,11 @@ static int ecb_paes_do_crypt(struct s390_paes_ctx *ctx, n = nbytes & ~(AES_BLOCK_SIZE - 1); k = cpacf_km(ctx->fc | req_ctx->modifier, param, walk->dst.virt.addr, walk->src.virt.addr, n); - if (k) + if (k) { rc = skcipher_walk_done(walk, nbytes - k); + if (rc) + goto out; + } if (k < n) { if (!maysleep) { rc = -EKEYEXPIRED; @@ -495,7 +498,7 @@ static int ecb_paes_crypt(struct skcipher_request *req, unsigned long modifier) atomic_dec(&ctx->via_engine_ctr); } - if (rc != -EINPROGRESS) + if (rc != -EINPROGRESS && walk->nbytes) skcipher_walk_done(walk, rc); out: @@ -549,7 +552,7 @@ static int ecb_paes_do_one_request(struct crypto_engine *engine, void *areq) rc = ecb_paes_do_crypt(ctx, req_ctx, tested, true); if (rc == -EKEYEXPIRED) { return pkey_handle_expired(); - } else if (rc) { + } else if (rc && walk->nbytes) { skcipher_walk_done(walk, rc); } @@ -690,6 +693,8 @@ static int cbc_paes_do_crypt(struct s390_paes_ctx *ctx, if (k) { memcpy(walk->iv, param->iv, AES_BLOCK_SIZE); rc = skcipher_walk_done(walk, nbytes - k); + if (rc) + goto out; } if (k < n) { if (!maysleep) { @@ -752,7 +757,7 @@ static int cbc_paes_crypt(struct skcipher_request *req, unsigned long modifier) atomic_dec(&ctx->via_engine_ctr); } - if (rc != -EINPROGRESS) + if (rc != -EINPROGRESS && walk->nbytes) skcipher_walk_done(walk, rc); out: @@ -806,7 +811,7 @@ static int cbc_paes_do_one_request(struct crypto_engine *engine, void *areq) rc = cbc_paes_do_crypt(ctx, req_ctx, tested, true); if (rc == -EKEYEXPIRED) { return pkey_handle_expired(); - } else if (rc) { + } else if (rc && walk->nbytes) { skcipher_walk_done(walk, rc); } @@ -968,6 +973,11 @@ static int ctr_paes_do_crypt(struct s390_paes_ctx *ctx, AES_BLOCK_SIZE); crypto_inc(walk->iv, AES_BLOCK_SIZE); rc = skcipher_walk_done(walk, nbytes - k); + if (rc) { + if (locked) + mutex_unlock(&ctrblk_lock); + goto out; + } } if (k < n) { if (!maysleep) { @@ -1061,7 +1071,7 @@ static int ctr_paes_crypt(struct skcipher_request *req) atomic_dec(&ctx->via_engine_ctr); } - if (rc != -EINPROGRESS) + if (rc != -EINPROGRESS && walk->nbytes) skcipher_walk_done(walk, rc); out: @@ -1105,7 +1115,7 @@ static int ctr_paes_do_one_request(struct crypto_engine *engine, void *areq) rc = ctr_paes_do_crypt(ctx, req_ctx, tested, true); if (rc == -EKEYEXPIRED) { return pkey_handle_expired(); - } else if (rc) { + } else if (rc && walk->nbytes) { skcipher_walk_done(walk, rc); } @@ -1283,8 +1293,11 @@ static int xts_paes_do_crypt_fullkey(struct s390_pxts_ctx *ctx, n = nbytes & ~(AES_BLOCK_SIZE - 1); k = cpacf_km(ctx->fc | req_ctx->modifier, param->key + offset, walk->dst.virt.addr, walk->src.virt.addr, n); - if (k) + if (k) { rc = skcipher_walk_done(walk, nbytes - k); + if (rc) + goto out; + } if (k < n) { if (!maysleep) { rc = -EKEYEXPIRED; @@ -1377,8 +1390,11 @@ static int xts_paes_do_crypt_2keys(struct s390_pxts_ctx *ctx, n = nbytes & ~(AES_BLOCK_SIZE - 1); k = cpacf_km(ctx->fc | req_ctx->modifier, param->key + offset, walk->dst.virt.addr, walk->src.virt.addr, n); - if (k) + if (k) { rc = skcipher_walk_done(walk, nbytes - k); + if (rc) + goto out; + } if (k < n) { if (!maysleep) { rc = -EKEYEXPIRED; @@ -1485,7 +1501,7 @@ static inline int xts_paes_crypt(struct skcipher_request *req, unsigned long mod atomic_dec(&ctx->via_engine_ctr); } - if (rc != -EINPROGRESS) + if (rc != -EINPROGRESS && walk->nbytes) skcipher_walk_done(walk, rc); out: @@ -1539,7 +1555,7 @@ static int xts_paes_do_one_request(struct crypto_engine *engine, void *areq) rc = xts_paes_do_crypt(ctx, req_ctx, tested, true); if (rc == -EKEYEXPIRED) { return pkey_handle_expired(); - } else if (rc) { + } else if (rc && walk->nbytes) { skcipher_walk_done(walk, rc); } From 19a218b46b2471d370c11fb52040f36ac8d05d23 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Mon, 31 Aug 2026 10:38:31 +0200 Subject: [PATCH 0953/1198] s390/crypto: Fix missing scrub of temp buffers with PAES algorithm In function ctr_paes_do_crypt() there is a buffer used to process remaining bytes < AES_BLOCK_SIZE. This buffer was not scrubbed and thus could lead to expose of unwanted data. Rework the code to explicitly scrub the buffer at the end of the function to avoid exposure of maybe sensitive data. In function __xts_2keys_prep_param() change the existing scrub to clean the whole param block instead of just the key field. Fixes: 6cd87cb5ef6c ("s390/crypto: Rework protected key AES for true asynch support") Signed-off-by: Harald Freudenberger Reviewed-by: Holger Dengler Cc: stable@vger.kernel.org # 6.16+ Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/crypto/paes_s390.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c index 89785ab95e6b..9c8f9e2570f2 100644 --- a/arch/s390/crypto/paes_s390.c +++ b/arch/s390/crypto/paes_s390.c @@ -1026,6 +1026,7 @@ static int ctr_paes_do_crypt(struct s390_paes_ctx *ctx, } out: + memzero_explicit(buf, sizeof(buf)); pr_debug("rc=%d\n", rc); return rc; } @@ -1350,7 +1351,7 @@ static inline int __xts_2keys_prep_param(struct s390_pxts_ctx *ctx, memcpy(param->init, pcc_param.xts, 16); } - memzero_explicit(pcc_param.key, sizeof(pcc_param.key)); + memzero_explicit(&pcc_param, sizeof(pcc_param)); return rc; } From 749990db95d45cc3d96aab999ac7f110259b200c Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Mon, 31 Aug 2026 10:38:32 +0200 Subject: [PATCH 0954/1198] s390/crypto: Fix use of mutex in atomic context in PAES The PAES CTR implementation used a mutex to lock one page of exclusive memory for fast CTR processing. Unfortunately a mutex is not save to use in atomic or interrupt context. So use a binary semaphore instead which is save to use in such environments. Furthermore rework the code to get rid of conditional locking. So restructure the PAES CRT code by extracting the main loop into a separate function and just give in information about the (locked) page can be used or not (is not locked). Fixes: 6cd87cb5ef6c ("s390/crypto: Rework protected key AES for true asynch support") Signed-off-by: Harald Freudenberger Reviewed-by: Holger Dengler Cc: stable@vger.kernel.org # 6.16+ Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/crypto/paes_s390.c | 113 +++++++++++++++++++---------------- 1 file changed, 60 insertions(+), 53 deletions(-) diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c index 9c8f9e2570f2..991a26766d40 100644 --- a/arch/s390/crypto/paes_s390.c +++ b/arch/s390/crypto/paes_s390.c @@ -19,7 +19,7 @@ #include #include #include -#include +#include #include #include #include @@ -45,7 +45,7 @@ module_param_named(clrkey, pkey_clrkey_allowed, bool, 0444); MODULE_PARM_DESC(clrkey, "Allow clear key material (default N)"); static u8 *ctrblk; -static DEFINE_MUTEX(ctrblk_lock); +static DEFINE_SEMAPHORE(ctrblk_sem, 1); static cpacf_mask_t km_functions, kmc_functions, kmctr_functions; @@ -919,15 +919,62 @@ static inline unsigned int __ctrblk_init(u8 *ctrptr, u8 *iv, unsigned int nbytes return n; } +static int __ctr_paes_do_crypt(struct s390_paes_ctx *ctx, + struct ctr_param *param, + struct skcipher_walk *walk, + bool tested, bool maysleep, bool locked) +{ + unsigned int nbytes, n, k; + u8 *ctrptr; + int rc = 0; + + /* + * Note that in case of partial processing or failure the walk + * is NOT unmapped here. So a follow up task may reuse the walk + * or in case of unrecoverable failure needs to unmap it. + */ + while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) { + n = AES_BLOCK_SIZE; + if (nbytes >= 2 * AES_BLOCK_SIZE && locked) + n = __ctrblk_init(ctrblk, walk->iv, nbytes); + ctrptr = (n > AES_BLOCK_SIZE) ? ctrblk : walk->iv; + k = cpacf_kmctr(ctx->fc, param, walk->dst.virt.addr, + walk->src.virt.addr, n, ctrptr); + if (k) { + if (ctrptr == ctrblk) + memcpy(walk->iv, ctrptr + k - AES_BLOCK_SIZE, + AES_BLOCK_SIZE); + crypto_inc(walk->iv, AES_BLOCK_SIZE); + rc = skcipher_walk_done(walk, nbytes - k); + if (rc) + goto out; + } + if (k < n) { + if (!maysleep) { + rc = -EKEYEXPIRED; + goto out; + } + rc = paes_convert_key(ctx, tested); + if (rc) + goto out; + spin_lock_bh(&ctx->pk_lock); + memcpy(param->key, ctx->pk.protkey, sizeof(param->key)); + spin_unlock_bh(&ctx->pk_lock); + } + } + +out: + return rc; +} + static int ctr_paes_do_crypt(struct s390_paes_ctx *ctx, struct s390_pctr_req_ctx *req_ctx, bool tested, bool maysleep) { struct ctr_param *param = &req_ctx->param; struct skcipher_walk *walk = &req_ctx->walk; - u8 buf[AES_BLOCK_SIZE], *ctrptr; - unsigned int nbytes, n, k; - int pk_state, locked, rc = 0; + u8 buf[AES_BLOCK_SIZE]; + int pk_state, rc = 0; if (!req_ctx->param_init_done) { /* fetch and check protected key state */ @@ -953,57 +1000,17 @@ static int ctr_paes_do_crypt(struct s390_paes_ctx *ctx, if (rc) goto out; - locked = mutex_trylock(&ctrblk_lock); - - /* - * Note that in case of partial processing or failure the walk - * is NOT unmapped here. So a follow up task may reuse the walk - * or in case of unrecoverable failure needs to unmap it. - */ - while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) { - n = AES_BLOCK_SIZE; - if (nbytes >= 2 * AES_BLOCK_SIZE && locked) - n = __ctrblk_init(ctrblk, walk->iv, nbytes); - ctrptr = (n > AES_BLOCK_SIZE) ? ctrblk : walk->iv; - k = cpacf_kmctr(ctx->fc, param, walk->dst.virt.addr, - walk->src.virt.addr, n, ctrptr); - if (k) { - if (ctrptr == ctrblk) - memcpy(walk->iv, ctrptr + k - AES_BLOCK_SIZE, - AES_BLOCK_SIZE); - crypto_inc(walk->iv, AES_BLOCK_SIZE); - rc = skcipher_walk_done(walk, nbytes - k); - if (rc) { - if (locked) - mutex_unlock(&ctrblk_lock); - goto out; - } - } - if (k < n) { - if (!maysleep) { - if (locked) - mutex_unlock(&ctrblk_lock); - rc = -EKEYEXPIRED; - goto out; - } - rc = paes_convert_key(ctx, tested); - if (rc) { - if (locked) - mutex_unlock(&ctrblk_lock); - goto out; - } - spin_lock_bh(&ctx->pk_lock); - memcpy(param->key, ctx->pk.protkey, sizeof(param->key)); - spin_unlock_bh(&ctx->pk_lock); - } + if (down_trylock(&ctrblk_sem) == 0) { + rc = __ctr_paes_do_crypt(ctx, param, walk, tested, maysleep, true); + up(&ctrblk_sem); + } else { + rc = __ctr_paes_do_crypt(ctx, param, walk, tested, maysleep, false); } - if (locked) - mutex_unlock(&ctrblk_lock); /* final block may be < AES_BLOCK_SIZE, copy only nbytes */ - if (nbytes) { + if (!rc && walk->nbytes > 0) { memset(buf, 0, AES_BLOCK_SIZE); - memcpy(buf, walk->src.virt.addr, nbytes); + memcpy(buf, walk->src.virt.addr, walk->nbytes); while (1) { if (cpacf_kmctr(ctx->fc, param, buf, buf, AES_BLOCK_SIZE, @@ -1020,7 +1027,7 @@ static int ctr_paes_do_crypt(struct s390_paes_ctx *ctx, memcpy(param->key, ctx->pk.protkey, sizeof(param->key)); spin_unlock_bh(&ctx->pk_lock); } - memcpy(walk->dst.virt.addr, buf, nbytes); + memcpy(walk->dst.virt.addr, buf, walk->nbytes); crypto_inc(walk->iv, AES_BLOCK_SIZE); rc = skcipher_walk_done(walk, 0); } From 5b97b969030c099333d973be420edef0d6452e0f Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Mon, 31 Aug 2026 10:38:33 +0200 Subject: [PATCH 0955/1198] s390/crypto: Fix missing cra_flags in paes_s390 The 4 algorithms implemented in paes_s390 never had any cra_flags set. So add code which sets the cra_flag to CRYPTO_ALG_ASYNC and CRYPTO_ALG_NO_FALLBACK. Fixes: 4ccd065a69df ("crypto: ahash - Add support for drivers with no fallback") Signed-off-by: Harald Freudenberger Reviewed-by: Holger Dengler Cc: stable@vger.kernel.org # 6.17+ Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/crypto/paes_s390.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c index 991a26766d40..5b7664031ea3 100644 --- a/arch/s390/crypto/paes_s390.c +++ b/arch/s390/crypto/paes_s390.c @@ -570,6 +570,7 @@ static struct skcipher_engine_alg ecb_paes_alg = { .base.cra_name = "ecb(paes)", .base.cra_driver_name = "ecb-paes-s390", .base.cra_priority = 401, /* combo: aes + ecb + 1 */ + .base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_NO_FALLBACK, .base.cra_blocksize = AES_BLOCK_SIZE, .base.cra_ctxsize = sizeof(struct s390_paes_ctx), .base.cra_module = THIS_MODULE, @@ -829,6 +830,7 @@ static struct skcipher_engine_alg cbc_paes_alg = { .base.cra_name = "cbc(paes)", .base.cra_driver_name = "cbc-paes-s390", .base.cra_priority = 402, /* cbc-paes-s390 + 1 */ + .base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_NO_FALLBACK, .base.cra_blocksize = AES_BLOCK_SIZE, .base.cra_ctxsize = sizeof(struct s390_paes_ctx), .base.cra_module = THIS_MODULE, @@ -1141,6 +1143,7 @@ static struct skcipher_engine_alg ctr_paes_alg = { .base.cra_name = "ctr(paes)", .base.cra_driver_name = "ctr-paes-s390", .base.cra_priority = 402, /* ecb-paes-s390 + 1 */ + .base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_NO_FALLBACK, .base.cra_blocksize = 1, .base.cra_ctxsize = sizeof(struct s390_paes_ctx), .base.cra_module = THIS_MODULE, @@ -1581,6 +1584,7 @@ static struct skcipher_engine_alg xts_paes_alg = { .base.cra_name = "xts(paes)", .base.cra_driver_name = "xts-paes-s390", .base.cra_priority = 402, /* ecb-paes-s390 + 1 */ + .base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_NO_FALLBACK, .base.cra_blocksize = AES_BLOCK_SIZE, .base.cra_ctxsize = sizeof(struct s390_pxts_ctx), .base.cra_module = THIS_MODULE, From 3fec882c33d9b61983ee31456777f623dccd1a35 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Mon, 31 Aug 2026 10:38:34 +0200 Subject: [PATCH 0956/1198] s390/crypto: Fix handling of EBUSY in PAES when req is pushed to crypto engine When a request is transferred to the engine via crypto_transfer_skcipher_request_to_engine() there are two return codes signaling a successful transfer: EINPROGRESS and EBUSY. However the correct handling of EBUSY was missing and has been added as a return code indicating a successful transfer to the crypto engine. Fixes: 6cd87cb5ef6c ("s390/crypto: Rework protected key AES for true asynch support") Signed-off-by: Harald Freudenberger Reviewed-by: Holger Dengler Cc: stable@vger.kernel.org # 6.16+ Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/crypto/paes_s390.c | 36 ++++++++++++++++++++++++------------ 1 file changed, 24 insertions(+), 12 deletions(-) diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c index 5b7664031ea3..93e0e54ba2e8 100644 --- a/arch/s390/crypto/paes_s390.c +++ b/arch/s390/crypto/paes_s390.c @@ -463,6 +463,7 @@ static int ecb_paes_crypt(struct skcipher_request *req, unsigned long modifier) struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm); struct skcipher_walk *walk = &req_ctx->walk; bool tested = crypto_skcipher_tested(tfm); + bool cleanup = true; int rc; /* @@ -494,15 +495,17 @@ static int ecb_paes_crypt(struct skcipher_request *req, unsigned long modifier) if (rc == 0 || rc == -EKEYEXPIRED) { atomic_inc(&ctx->via_engine_ctr); rc = crypto_transfer_skcipher_request_to_engine(paes_crypto_engine, req); - if (rc != -EINPROGRESS) + if (rc == -EINPROGRESS || rc == -EBUSY) + cleanup = false; + else atomic_dec(&ctx->via_engine_ctr); } - if (rc != -EINPROGRESS && walk->nbytes) + if (cleanup && walk->nbytes) skcipher_walk_done(walk, rc); out: - if (rc != -EINPROGRESS) + if (cleanup) memzero_explicit(&req_ctx->param, sizeof(req_ctx->param)); pr_debug("rc=%d\n", rc); return rc; @@ -723,6 +726,7 @@ static int cbc_paes_crypt(struct skcipher_request *req, unsigned long modifier) struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm); struct skcipher_walk *walk = &req_ctx->walk; bool tested = crypto_skcipher_tested(tfm); + bool cleanup = true; int rc; /* @@ -754,15 +758,17 @@ static int cbc_paes_crypt(struct skcipher_request *req, unsigned long modifier) if (rc == 0 || rc == -EKEYEXPIRED) { atomic_inc(&ctx->via_engine_ctr); rc = crypto_transfer_skcipher_request_to_engine(paes_crypto_engine, req); - if (rc != -EINPROGRESS) + if (rc == -EINPROGRESS || rc == -EBUSY) + cleanup = false; + else atomic_dec(&ctx->via_engine_ctr); } - if (rc != -EINPROGRESS && walk->nbytes) + if (cleanup && walk->nbytes) skcipher_walk_done(walk, rc); out: - if (rc != -EINPROGRESS) + if (cleanup) memzero_explicit(&req_ctx->param, sizeof(req_ctx->param)); pr_debug("rc=%d\n", rc); return rc; @@ -1047,6 +1053,7 @@ static int ctr_paes_crypt(struct skcipher_request *req) struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm); struct skcipher_walk *walk = &req_ctx->walk; bool tested = crypto_skcipher_tested(tfm); + bool cleanup = true; int rc; /* @@ -1077,15 +1084,17 @@ static int ctr_paes_crypt(struct skcipher_request *req) if (rc == 0 || rc == -EKEYEXPIRED) { atomic_inc(&ctx->via_engine_ctr); rc = crypto_transfer_skcipher_request_to_engine(paes_crypto_engine, req); - if (rc != -EINPROGRESS) + if (rc == -EINPROGRESS || rc == -EBUSY) + cleanup = false; + else atomic_dec(&ctx->via_engine_ctr); } - if (rc != -EINPROGRESS && walk->nbytes) + if (cleanup && walk->nbytes) skcipher_walk_done(walk, rc); out: - if (rc != -EINPROGRESS) + if (cleanup) memzero_explicit(&req_ctx->param, sizeof(req_ctx->param)); pr_debug("rc=%d\n", rc); return rc; @@ -1477,6 +1486,7 @@ static inline int xts_paes_crypt(struct skcipher_request *req, unsigned long mod struct s390_pxts_ctx *ctx = crypto_skcipher_ctx(tfm); struct skcipher_walk *walk = &req_ctx->walk; bool tested = crypto_skcipher_tested(tfm); + bool cleanup = true; int rc; /* @@ -1508,15 +1518,17 @@ static inline int xts_paes_crypt(struct skcipher_request *req, unsigned long mod if (rc == 0 || rc == -EKEYEXPIRED) { atomic_inc(&ctx->via_engine_ctr); rc = crypto_transfer_skcipher_request_to_engine(paes_crypto_engine, req); - if (rc != -EINPROGRESS) + if (rc == -EINPROGRESS || rc == -EBUSY) + cleanup = false; + else atomic_dec(&ctx->via_engine_ctr); } - if (rc != -EINPROGRESS && walk->nbytes) + if (cleanup && walk->nbytes) skcipher_walk_done(walk, rc); out: - if (rc != -EINPROGRESS) + if (cleanup) memzero_explicit(&req_ctx->param, sizeof(req_ctx->param)); pr_debug("rc=%d\n", rc); return rc; From 330148371401de474b656eaf521861f12ec1a1ce Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Mon, 31 Aug 2026 10:38:35 +0200 Subject: [PATCH 0957/1198] s390/crypto: Fix handling of EBUSY in PHMAC when req is pushed to crypto engine When a request is transferred to the engine via crypto_transfer_hash_request_to_engine() there are two return codes signaling a successful transfer: EINPROGRESS and EBUSY. However the correct handling of EBUSY was missing and has been added as a return code indicating a successful transfer to the crypto engine. Fixes: cbbc675506cc ("crypto: s390 - New s390 specific protected key hash phmac") Signed-off-by: Harald Freudenberger Reviewed-by: Holger Dengler Cc: stable@vger.kernel.org # 6.17+ Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/crypto/phmac_s390.c | 30 +++++++++++++++++++++--------- 1 file changed, 21 insertions(+), 9 deletions(-) diff --git a/arch/s390/crypto/phmac_s390.c b/arch/s390/crypto/phmac_s390.c index 020a1beb2e22..532fe6c4e89c 100644 --- a/arch/s390/crypto/phmac_s390.c +++ b/arch/s390/crypto/phmac_s390.c @@ -62,8 +62,10 @@ static inline int hwh_prepare(struct ahash_request *req, */ static inline int hwh_advance(struct hash_walk_helper *hwh, int n) { - if (n < 0) + if (n < 0) { + hwh->walkbytes = n; return crypto_hash_walk_done(&hwh->walk, n); + } hwh->walkbytes -= n; hwh->walkaddr += n; @@ -606,6 +608,7 @@ static int phmac_update(struct ahash_request *req) struct phmac_tfm_ctx *tfm_ctx = crypto_ahash_ctx(tfm); struct kmac_sha2_ctx *kmac_ctx = &req_ctx->kmac_ctx; struct hash_walk_helper *hwh = &req_ctx->hwh; + bool cleanup = true; int rc; /* prep the walk in the request context */ @@ -629,12 +632,15 @@ static int phmac_update(struct ahash_request *req) req_ctx->async_op = OP_UPDATE; atomic_inc(&tfm_ctx->via_engine_ctr); rc = crypto_transfer_hash_request_to_engine(phmac_crypto_engine, req); - if (rc != -EINPROGRESS) + if (rc == -EINPROGRESS || rc == -EBUSY) + cleanup = false; + else atomic_dec(&tfm_ctx->via_engine_ctr); } - if (rc != -EINPROGRESS) { - hwh_advance(hwh, rc); + if (cleanup) { + if (hwh->walkbytes > 0) + hwh_advance(hwh, rc); memzero_explicit(kmac_ctx, sizeof(*kmac_ctx)); } @@ -649,6 +655,7 @@ static int phmac_final(struct ahash_request *req) struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); struct phmac_tfm_ctx *tfm_ctx = crypto_ahash_ctx(tfm); struct kmac_sha2_ctx *kmac_ctx = &req_ctx->kmac_ctx; + bool cleanup = true; int rc = 0; /* Try synchronous operation if no active engine usage */ @@ -667,12 +674,14 @@ static int phmac_final(struct ahash_request *req) req_ctx->async_op = OP_FINAL; atomic_inc(&tfm_ctx->via_engine_ctr); rc = crypto_transfer_hash_request_to_engine(phmac_crypto_engine, req); - if (rc != -EINPROGRESS) + if (rc == -EINPROGRESS || rc == -EBUSY) + cleanup = false; + else atomic_dec(&tfm_ctx->via_engine_ctr); } out: - if (rc != -EINPROGRESS) + if (cleanup) memzero_explicit(kmac_ctx, sizeof(*kmac_ctx)); pr_debug("rc=%d\n", rc); return rc; @@ -685,6 +694,7 @@ static int phmac_finup(struct ahash_request *req) struct phmac_tfm_ctx *tfm_ctx = crypto_ahash_ctx(tfm); struct kmac_sha2_ctx *kmac_ctx = &req_ctx->kmac_ctx; struct hash_walk_helper *hwh = &req_ctx->hwh; + bool cleanup = true; int rc; /* prep the walk in the request context */ @@ -716,15 +726,17 @@ static int phmac_finup(struct ahash_request *req) /* req->async_op has been set to either OP_FINUP or OP_FINAL */ atomic_inc(&tfm_ctx->via_engine_ctr); rc = crypto_transfer_hash_request_to_engine(phmac_crypto_engine, req); - if (rc != -EINPROGRESS) + if (rc == -EINPROGRESS || rc == -EBUSY) + cleanup = false; + else atomic_dec(&tfm_ctx->via_engine_ctr); } - if (rc != -EINPROGRESS) + if (cleanup && hwh->walkbytes > 0) hwh_advance(hwh, rc); out: - if (rc != -EINPROGRESS) + if (cleanup) memzero_explicit(kmac_ctx, sizeof(*kmac_ctx)); pr_debug("rc=%d\n", rc); return rc; From ac1481320110b803ab9b79ab4d2ca11a74fc05f2 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Mon, 31 Aug 2026 10:38:36 +0200 Subject: [PATCH 0958/1198] s390/crypto: Fix wrong return code to engine in asynch callbacks When crypto_finalize_hash_request() or crypto_finalize_skcipher_request() explicitly completes a request, the do_one_request callback must return 0 to indicate successful handling. Returning a negative error code causes the crypto engine to assume the driver failed to take ownership and triggers a second completion via crypto_request_complete(), resulting in a double completion. This pattern occurs in paes_s390.c 4 times and once in phmac_s390.c. Fixed in phmac_do_one_request() and all four paes do_one_request callbacks (ecb, cbc, ctr, xts) by returning 0 after explicit finalization instead of propagating the error code. Fixes: 6cd87cb5ef6c ("s390/crypto: Rework protected key AES for true asynch support") Signed-off-by: Harald Freudenberger Reviewed-by: Holger Dengler Cc: stable@vger.kernel.org # 6.16+ Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/crypto/paes_s390.c | 8 ++++---- arch/s390/crypto/phmac_s390.c | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c index 93e0e54ba2e8..a4b972459f52 100644 --- a/arch/s390/crypto/paes_s390.c +++ b/arch/s390/crypto/paes_s390.c @@ -565,7 +565,7 @@ static int ecb_paes_do_one_request(struct crypto_engine *engine, void *areq) atomic_dec(&ctx->via_engine_ctr); crypto_finalize_skcipher_request(engine, req, rc); local_bh_enable(); - return rc; + return 0; } static struct skcipher_engine_alg ecb_paes_alg = { @@ -828,7 +828,7 @@ static int cbc_paes_do_one_request(struct crypto_engine *engine, void *areq) atomic_dec(&ctx->via_engine_ctr); crypto_finalize_skcipher_request(engine, req, rc); local_bh_enable(); - return rc; + return 0; } static struct skcipher_engine_alg cbc_paes_alg = { @@ -1144,7 +1144,7 @@ static int ctr_paes_do_one_request(struct crypto_engine *engine, void *areq) atomic_dec(&ctx->via_engine_ctr); crypto_finalize_skcipher_request(engine, req, rc); local_bh_enable(); - return rc; + return 0; } static struct skcipher_engine_alg ctr_paes_alg = { @@ -1588,7 +1588,7 @@ static int xts_paes_do_one_request(struct crypto_engine *engine, void *areq) atomic_dec(&ctx->via_engine_ctr); crypto_finalize_skcipher_request(engine, req, rc); local_bh_enable(); - return rc; + return 0; } static struct skcipher_engine_alg xts_paes_alg = { diff --git a/arch/s390/crypto/phmac_s390.c b/arch/s390/crypto/phmac_s390.c index 532fe6c4e89c..283a00754a06 100644 --- a/arch/s390/crypto/phmac_s390.c +++ b/arch/s390/crypto/phmac_s390.c @@ -926,7 +926,7 @@ static int phmac_do_one_request(struct crypto_engine *engine, void *areq) atomic_dec(&tfm_ctx->via_engine_ctr); crypto_finalize_hash_request(engine, req, rc); local_bh_enable(); - return rc; + return 0; } #define S390_ASYNC_PHMAC_ALG(x) \ From 7a08507ea5b4d06ad8d269287913573f34467565 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Mon, 31 Aug 2026 10:38:37 +0200 Subject: [PATCH 0959/1198] s390/crypto: Map EBUSY to EIO when key conversion fails repeatedly When hardware persistently returns -EBUSY after exhausting retries, the error propagates to crypto_finalize_*_request(). The crypto API's completion wrapper treats -EBUSY as a queueing status and swallows it, preventing the completion callback from firing. This causes callers using crypto_wait_req() to block indefinitely. Translate persistent -EBUSY to -EIO after retry exhaustion to ensure proper error propagation and callback invocation. Fixes: 6cd87cb5ef6c ("s390/crypto: Rework protected key AES for true asynch support") Signed-off-by: Harald Freudenberger Reviewed-by: Holger Dengler Cc: stable@vger.kernel.org # 6.16+ Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/crypto/paes_s390.c | 4 ++++ arch/s390/crypto/phmac_s390.c | 4 ++++ 2 files changed, 8 insertions(+) diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c index a4b972459f52..f987bcbe8f35 100644 --- a/arch/s390/crypto/paes_s390.c +++ b/arch/s390/crypto/paes_s390.c @@ -220,6 +220,10 @@ static inline int convert_key(const u8 *key, unsigned int keylen, xflags); } + /* But finally map -EBUSY to -EIO to indicate an IO failure */ + if (rc == -EBUSY) + rc = -EIO; + out: pr_debug("rc=%d\n", rc); return rc; diff --git a/arch/s390/crypto/phmac_s390.c b/arch/s390/crypto/phmac_s390.c index 283a00754a06..bbf8a6809ecb 100644 --- a/arch/s390/crypto/phmac_s390.c +++ b/arch/s390/crypto/phmac_s390.c @@ -341,6 +341,10 @@ static inline int convert_key(const u8 *key, unsigned int keylen, xflags); } + /* But finally map -EBUSY to -EIO to indicate an IO failure */ + if (rc == -EBUSY) + rc = -EIO; + out: pr_debug("rc=%d\n", rc); return rc; From dc2136341be9835e70ba7c6b36904cf3683fd029 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 31 Aug 2026 10:38:38 +0200 Subject: [PATCH 0960/1198] s390/crypto: Enable CONTEXT_ANALYSIS Enable CONTEXT_ANALYSIS since s390's crypto code compiles now without warnings. Reviewed-by: Harald Freudenberger Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/crypto/Makefile | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/s390/crypto/Makefile b/arch/s390/crypto/Makefile index 48aeb0c0ffbd..1d6420813935 100644 --- a/arch/s390/crypto/Makefile +++ b/arch/s390/crypto/Makefile @@ -3,6 +3,8 @@ # Cryptographic API # +CONTEXT_ANALYSIS := y + obj-$(CONFIG_CRYPTO_AES_S390) += aes_s390.o obj-$(CONFIG_CRYPTO_PAES_S390) += paes_s390.o obj-$(CONFIG_S390_PRNG) += prng.o From cf4d35896621b7298eef51b7a465e5c0cb22f670 Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Sun, 6 Sep 2026 14:39:44 -0300 Subject: [PATCH 0961/1198] smb: client: fix uid/gid override in getattr with posix extensions When mounting with 'multiuser,posix' options, cifs_getattr() overrides the server-provided uid/gid with the current process's fsuid/fsgid. This is because the condition only checks for unix extensions (tcon->unix_ext) but not posix extensions (tcon->posix_extensions). With SMB3 POSIX extensions, the server provides real uid/gid values just like with unix extensions, so they should be preserved rather than replaced with the caller's credentials. Add a tcon->posix_extensions check to the condition so that uid/gid from the server are properly reported in stat results. Reported-by: Arthur Lesuisse Closes: https://lore.kernel.org/r/DB9P190MB2012266F6B8DECBE5D26A1798DB52@DB9P190MB2012.EURP190.PROD.OUTLOOK.COM Suggested-by: Arthur Lesuisse Reviewed-by: Namjae Jeon Signed-off-by: Paulo Alcantara Cc: Ronnie Sahlberg Cc: Shyam Prasad N Cc: Tom Talpey Cc: Bharath SM Cc: stable@vger.kernel.org --- fs/smb/client/inode.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 12ed8db10e00..49f9993ad567 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -2992,14 +2992,14 @@ int cifs_getattr(struct mnt_idmap *idmap, const struct path *path, stat->attributes |= STATX_ATTR_ENCRYPTED; /* - * If on a multiuser mount without unix extensions or cifsacl being - * enabled, and the admin hasn't overridden them, set the ownership - * to the fsuid/fsgid of the current process. + * If on a multiuser mount without unix extensions, posix extensions + * or cifsacl being enabled, and the admin hasn't overridden them, + * set the ownership to the fsuid/fsgid of the current process. */ sbflags = cifs_sb_flags(cifs_sb); if ((sbflags & CIFS_MOUNT_MULTIUSER) && !(sbflags & CIFS_MOUNT_CIFS_ACL) && - !tcon->unix_ext) { + !tcon->unix_ext && !tcon->posix_extensions) { if (!(sbflags & CIFS_MOUNT_OVERR_UID)) stat->uid = current_fsuid(); if (!(sbflags & CIFS_MOUNT_OVERR_GID)) From 18a72975e9f35aadecc75b031f693f2d1f49308f Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Sun, 6 Sep 2026 14:40:04 -0300 Subject: [PATCH 0962/1198] smb: client: honor forceuid/forcegid when mapping SIDs to uid/gid When the administrator mounts with forceuid or forcegid (uid=/gid= mount options), they expect all files to appear owned by the specified user/group. However, several code paths unconditionally called sid_to_id() to overwrite cf_uid/cf_gid with server-provided values, ignoring the administrator's explicit override: - smb311_posix_info_to_fattr() (stat via POSIX extensions) - cifs_posix_to_fattr() (readdir via POSIX extensions) - parse_sec_desc() (CIFS ACL ownership mapping) This allowed an untrusted server to dictate local file ownership even when the mount was configured to force specific uid/gid values. Fix all three call sites to check CIFS_MOUNT_OVERR_UID and CIFS_MOUNT_OVERR_GID before calling sid_to_id(), following the same pattern already used by cifs_unix_basic_to_fattr() for unix extensions. Closes: https://sashiko.dev/#/patchset/20260906155816.603278-1-pc%40manguebit.org Reviewed-by: Namjae Jeon Signed-off-by: Paulo Alcantara Cc: Ronnie Sahlberg Cc: Shyam Prasad N Cc: Tom Talpey Cc: Bharath SM Cc: stable@vger.kernel.org --- fs/smb/client/cifsacl.c | 29 ++++++++++++++++++----------- fs/smb/client/inode.c | 9 +++++++-- fs/smb/client/readdir.c | 9 +++++++-- 3 files changed, 32 insertions(+), 15 deletions(-) diff --git a/fs/smb/client/cifsacl.c b/fs/smb/client/cifsacl.c index 213a421bf8e9..def8908dd7e9 100644 --- a/fs/smb/client/cifsacl.c +++ b/fs/smb/client/cifsacl.c @@ -1346,6 +1346,7 @@ static int parse_sec_desc(struct cifs_sb_info *cifs_sb, { int rc = 0; struct smb_sid *owner_sid_ptr, *group_sid_ptr; + unsigned int sbflags = cifs_sb_flags(cifs_sb); struct smb_acl *dacl_ptr; /* no need for SACL ptr */ char *end_of_acl; __u32 dacloffset, osidoffset, gsidoffset; @@ -1364,17 +1365,21 @@ static int parse_sec_desc(struct cifs_sb_info *cifs_sb, cifs_dbg(NOISY, "revision %d type 0x%x ooffset 0x%x goffset 0x%x sacloffset 0x%x dacloffset 0x%x\n", pntsd->revision, pntsd->type, osidoffset, gsidoffset, le32_to_cpu(pntsd->sacloffset), dacloffset); -/* cifs_dump_mem("owner_sid: ", owner_sid_ptr, 64); */ + fattr->cf_uid = cifs_sb->ctx->linux_uid; + fattr->cf_gid = cifs_sb->ctx->linux_gid; + rc = sid_from_sd(pntsd, acl_len, osidoffset, &owner_sid_ptr); if (rc) { cifs_dbg(FYI, "%s: Error %d parsing Owner SID\n", __func__, rc); return rc; } - rc = sid_to_id(cifs_sb, owner_sid_ptr, fattr, SIDOWNER); - if (rc) { - cifs_dbg(FYI, "%s: Error %d mapping Owner SID to uid\n", - __func__, rc); - return rc; + if (!(sbflags & CIFS_MOUNT_OVERR_UID)) { + rc = sid_to_id(cifs_sb, owner_sid_ptr, fattr, SIDOWNER); + if (rc) { + cifs_dbg(FYI, "%s: Error %d mapping Owner SID to uid\n", + __func__, rc); + return rc; + } } rc = sid_from_sd(pntsd, acl_len, gsidoffset, &group_sid_ptr); @@ -1383,11 +1388,13 @@ static int parse_sec_desc(struct cifs_sb_info *cifs_sb, __func__, rc); return rc; } - rc = sid_to_id(cifs_sb, group_sid_ptr, fattr, SIDGROUP); - if (rc) { - cifs_dbg(FYI, "%s: Error %d mapping Group SID to gid\n", - __func__, rc); - return rc; + if (!(sbflags & CIFS_MOUNT_OVERR_GID)) { + rc = sid_to_id(cifs_sb, group_sid_ptr, fattr, SIDGROUP); + if (rc) { + cifs_dbg(FYI, "%s: Error %d mapping Group SID to gid\n", + __func__, rc); + return rc; + } } if (dacloffset) { diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 49f9993ad567..1fe0ef0a95db 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -851,6 +851,7 @@ static void smb311_posix_info_to_fattr(struct cifs_fattr *fattr, struct smb311_posix_qinfo *info = &data->posix_fi; struct cifs_sb_info *cifs_sb = CIFS_SB(sb); struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); + unsigned int sbflags = cifs_sb_flags(cifs_sb); memset(fattr, 0, sizeof(*fattr)); @@ -895,8 +896,12 @@ static void smb311_posix_info_to_fattr(struct cifs_fattr *fattr, fattr->cf_symlink_target = data->symlink_target; data->symlink_target = NULL; } - sid_to_id(cifs_sb, &data->posix_owner, fattr, SIDOWNER); - sid_to_id(cifs_sb, &data->posix_group, fattr, SIDGROUP); + fattr->cf_uid = cifs_sb->ctx->linux_uid; + fattr->cf_gid = cifs_sb->ctx->linux_gid; + if (!(sbflags & CIFS_MOUNT_OVERR_UID)) + sid_to_id(cifs_sb, &data->posix_owner, fattr, SIDOWNER); + if (!(sbflags & CIFS_MOUNT_OVERR_GID)) + sid_to_id(cifs_sb, &data->posix_group, fattr, SIDGROUP); cifs_dbg(FYI, "POSIX query info: mode 0x%x uniqueid 0x%llx nlink %d\n", fattr->cf_mode, fattr->cf_uniqueid, fattr->cf_nlink); diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c index 32a75afca8f5..1ea84f4ada39 100644 --- a/fs/smb/client/readdir.c +++ b/fs/smb/client/readdir.c @@ -242,6 +242,7 @@ static void cifs_posix_to_fattr(struct cifs_fattr *fattr, struct smb2_posix_info *info, struct cifs_sb_info *cifs_sb) { + unsigned int sbflags = cifs_sb_flags(cifs_sb); struct smb2_posix_info_parsed parsed; posix_info_parse(info, NULL, &parsed); @@ -281,8 +282,12 @@ cifs_posix_to_fattr(struct cifs_fattr *fattr, struct smb2_posix_info *info, le32_to_cpu(info->ReparseTag), le32_to_cpu(info->Mode)); - sid_to_id(cifs_sb, &parsed.owner, fattr, SIDOWNER); - sid_to_id(cifs_sb, &parsed.group, fattr, SIDGROUP); + fattr->cf_uid = cifs_sb->ctx->linux_uid; + fattr->cf_gid = cifs_sb->ctx->linux_gid; + if (!(sbflags & CIFS_MOUNT_OVERR_UID)) + sid_to_id(cifs_sb, &parsed.owner, fattr, SIDOWNER); + if (!(sbflags & CIFS_MOUNT_OVERR_GID)) + sid_to_id(cifs_sb, &parsed.group, fattr, SIDGROUP); } static void __dir_info_to_fattr(struct cifs_fattr *fattr, const void *info) From cd2b2b57921d4caa7875e83198bb2aa71254328b Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Sun, 6 Sep 2026 14:40:23 -0300 Subject: [PATCH 0963/1198] smb: client: fix WSL reparse point uid/gid override wsl_to_fattr() unconditionally overwrites cf_uid/cf_gid with values from WSL extended attributes ($LXUID/$LXGID), ignoring the forceuid and forcegid mount options. Fix this by initializing cf_uid/cf_gid to the mount defaults and gating the $LXUID/$LXGID EA parsing on forceuid/forcegid. Closes: https://sashiko.dev/#/patchset/20260906190803.667489-1-pc%40manguebit.org Reviewed-by: Namjae Jeon Signed-off-by: Paulo Alcantara Cc: Ronnie Sahlberg Cc: Shyam Prasad N Cc: Tom Talpey Cc: Bharath SM Cc: stable@vger.kernel.org --- fs/smb/client/reparse.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c index 5cc5b0410d48..178da801e775 100644 --- a/fs/smb/client/reparse.c +++ b/fs/smb/client/reparse.c @@ -1137,10 +1137,14 @@ static bool wsl_to_fattr(struct cifs_open_info_data *data, struct cifs_sb_info *cifs_sb, u32 tag, struct cifs_fattr *fattr) { + unsigned int sbflags = cifs_sb_flags(cifs_sb); struct smb2_file_full_ea_info *ea; bool have_xattr_dev = false; u32 next = 0; + fattr->cf_uid = cifs_sb->ctx->linux_uid; + fattr->cf_gid = cifs_sb->ctx->linux_gid; + switch (tag) { case IO_REPARSE_TAG_LX_SYMLINK: fattr->cf_mode |= S_IFLNK; @@ -1177,11 +1181,13 @@ static bool wsl_to_fattr(struct cifs_open_info_data *data, nlen = ea->ea_name_length; v = (void *)((u8 *)ea->ea_data + ea->ea_name_length + 1); - if (!strncmp(name, SMB2_WSL_XATTR_UID, nlen)) - fattr->cf_uid = wsl_make_kuid(cifs_sb, v); - else if (!strncmp(name, SMB2_WSL_XATTR_GID, nlen)) - fattr->cf_gid = wsl_make_kgid(cifs_sb, v); - else if (!strncmp(name, SMB2_WSL_XATTR_MODE, nlen)) { + if (!strncmp(name, SMB2_WSL_XATTR_UID, nlen)) { + if (!(sbflags & CIFS_MOUNT_OVERR_UID)) + fattr->cf_uid = wsl_make_kuid(cifs_sb, v); + } else if (!strncmp(name, SMB2_WSL_XATTR_GID, nlen)) { + if (!(sbflags & CIFS_MOUNT_OVERR_GID)) + fattr->cf_gid = wsl_make_kgid(cifs_sb, v); + } else if (!strncmp(name, SMB2_WSL_XATTR_MODE, nlen)) { /* File type in reparse point tag and in xattr mode must match. */ if (S_DT(fattr->cf_mode) != S_DT(le32_to_cpu(*(__le32 *)v))) return false; From da6e25842431982d5a53cf00d925b98c690f4467 Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Sun, 6 Sep 2026 14:40:39 -0300 Subject: [PATCH 0964/1198] smb: client: avoid using uninitialized SIDs in cifs_posix_to_fattr() cifs_posix_to_fattr() ignores the return value of posix_info_parse(). When a malformed POSIX directory entry is encountered (e.g. invalid SID lengths from an untrusted server), posix_info_parse() returns -1 without populating the 'parsed' struct. The uninitialized stack memory in parsed.owner and parsed.group is then passed to sid_to_id(), which processes the garbage bytes and passes them to request_key() to construct a SID string, potentially leaking kernel stack contents to the userspace idmap daemon. Fix this by checking the return value and skipping the SID-to-id mapping when parsing fails. The remaining fattr fields (timestamps, mode, etc.) are populated directly from the 'info' pointer so they are unaffected. Closes: https://sashiko.dev/#/patchset/20260906172005.627163-1-pc%40manguebit.org Closes: https://sashiko.dev/#/patchset/20260906181540.647469-1-pc%40manguebit.org Reviewed-by: Namjae Jeon Signed-off-by: Paulo Alcantara Cc: Ronnie Sahlberg Cc: Shyam Prasad N Cc: Tom Talpey Cc: Bharath SM Cc: stable@vger.kernel.org --- fs/smb/client/readdir.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c index 1ea84f4ada39..9530e5b01564 100644 --- a/fs/smb/client/readdir.c +++ b/fs/smb/client/readdir.c @@ -244,8 +244,9 @@ cifs_posix_to_fattr(struct cifs_fattr *fattr, struct smb2_posix_info *info, { unsigned int sbflags = cifs_sb_flags(cifs_sb); struct smb2_posix_info_parsed parsed; + int rc; - posix_info_parse(info, NULL, &parsed); + rc = posix_info_parse(info, NULL, &parsed); memset(fattr, 0, sizeof(*fattr)); fattr->cf_uniqueid = le64_to_cpu(info->Inode); @@ -284,10 +285,15 @@ cifs_posix_to_fattr(struct cifs_fattr *fattr, struct smb2_posix_info *info, fattr->cf_uid = cifs_sb->ctx->linux_uid; fattr->cf_gid = cifs_sb->ctx->linux_gid; - if (!(sbflags & CIFS_MOUNT_OVERR_UID)) - sid_to_id(cifs_sb, &parsed.owner, fattr, SIDOWNER); - if (!(sbflags & CIFS_MOUNT_OVERR_GID)) - sid_to_id(cifs_sb, &parsed.group, fattr, SIDGROUP); + if (rc < 0) { + cifs_dbg(VFS, "%s: failed to parse SIDs: %d\n", + __func__, rc); + } else { + if (!(sbflags & CIFS_MOUNT_OVERR_UID)) + sid_to_id(cifs_sb, &parsed.owner, fattr, SIDOWNER); + if (!(sbflags & CIFS_MOUNT_OVERR_GID)) + sid_to_id(cifs_sb, &parsed.group, fattr, SIDGROUP); + } } static void __dir_info_to_fattr(struct cifs_fattr *fattr, const void *info) From fa7a2cfcf1e6117fc478cae6809c66c518740969 Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Sun, 6 Sep 2026 16:01:04 -0300 Subject: [PATCH 0965/1198] smb: client: fix file type corruption in wsl_to_fattr() Setting the file type in cf_mode without clearing the existing S_IFMT bits first is wrong as it corrupts the file type when cf_mode already has type bits set (e.g. S_IFREG | S_IFCHR == S_IFLNK). Clear S_IFMT before the switch statement. Closes: https://sashiko.dev/#/patchset/20260906172005.627163-1-pc%40manguebit.org Reviewed-by: Namjae Jeon Signed-off-by: Paulo Alcantara Cc: Ronnie Sahlberg Cc: Shyam Prasad N Cc: Tom Talpey Cc: Bharath SM Cc: stable@vger.kernel.org --- fs/smb/client/reparse.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c index 178da801e775..8a19dee564b8 100644 --- a/fs/smb/client/reparse.c +++ b/fs/smb/client/reparse.c @@ -1145,6 +1145,7 @@ static bool wsl_to_fattr(struct cifs_open_info_data *data, fattr->cf_uid = cifs_sb->ctx->linux_uid; fattr->cf_gid = cifs_sb->ctx->linux_gid; + fattr->cf_mode &= ~S_IFMT; switch (tag) { case IO_REPARSE_TAG_LX_SYMLINK: fattr->cf_mode |= S_IFLNK; From 65d5dbdc089be42fc48a6f77bc6b648307f34b17 Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Sun, 6 Sep 2026 16:01:16 -0300 Subject: [PATCH 0966/1198] smb: client: fix file type corruption in posix_reparse_to_fattr() Setting the file type in cf_mode without clearing the existing S_IFMT bits first is wrong as it corrupts the file type when cf_mode already has type bits set (e.g. S_IFREG | S_IFCHR == S_IFLNK). Use a local ftype variable to collect the new file type and apply it after validation succeeds, clearing S_IFMT and setting the new type in a single assignment. This avoids stripping cf_mode on malformed reparse points where the function returns false early. Closes: https://sashiko.dev/#/patchset/20260906172005.627163-1-pc%40manguebit.org Reviewed-by: Namjae Jeon Signed-off-by: Paulo Alcantara Cc: Ronnie Sahlberg Cc: Shyam Prasad N Cc: Tom Talpey Cc: Bharath SM Cc: stable@vger.kernel.org --- fs/smb/client/reparse.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c index 8a19dee564b8..616ca2dbfac4 100644 --- a/fs/smb/client/reparse.c +++ b/fs/smb/client/reparse.c @@ -1212,6 +1212,7 @@ static bool posix_reparse_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_open_info_data *data) { struct reparse_nfs_data_buffer *buf = (struct reparse_nfs_data_buffer *)data->reparse.buf; + umode_t ftype; if (buf == NULL) return true; @@ -1227,7 +1228,7 @@ static bool posix_reparse_to_fattr(struct cifs_sb_info *cifs_sb, WARN_ON_ONCE(1); return false; } - fattr->cf_mode |= S_IFCHR; + ftype = S_IFCHR; fattr->cf_rdev = reparse_mkdev(buf->DataBuffer); break; case NFS_SPECFILE_BLK: @@ -1235,22 +1236,23 @@ static bool posix_reparse_to_fattr(struct cifs_sb_info *cifs_sb, WARN_ON_ONCE(1); return false; } - fattr->cf_mode |= S_IFBLK; + ftype = S_IFBLK; fattr->cf_rdev = reparse_mkdev(buf->DataBuffer); break; case NFS_SPECFILE_FIFO: - fattr->cf_mode |= S_IFIFO; + ftype = S_IFIFO; break; case NFS_SPECFILE_SOCK: - fattr->cf_mode |= S_IFSOCK; + ftype = S_IFSOCK; break; case NFS_SPECFILE_LNK: - fattr->cf_mode |= S_IFLNK; + ftype = S_IFLNK; break; default: WARN_ON_ONCE(1); return false; } + fattr->cf_mode = (fattr->cf_mode & ~S_IFMT) | ftype; return true; } From 6bd360447941357e959414a525aa62576a448116 Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Sun, 6 Sep 2026 16:01:24 -0300 Subject: [PATCH 0967/1198] smb: client: fix file type corruption in cifs_reparse_point_to_fattr() Setting the file type in cf_mode without clearing the existing S_IFMT bits first is wrong as it corrupts the file type when cf_mode already has type bits set (e.g. S_IFREG | S_IFLNK == S_IFDIR | S_IFREG). Clear S_IFMT before setting S_IFLNK for native and SMB1 symlinks. Closes: https://sashiko.dev/#/patchset/20260906181540.647469-1-pc%40manguebit.org Reviewed-by: Namjae Jeon Signed-off-by: Paulo Alcantara Cc: Ronnie Sahlberg Cc: Shyam Prasad N Cc: Tom Talpey Cc: Bharath SM Cc: stable@vger.kernel.org --- fs/smb/client/reparse.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c index 616ca2dbfac4..b6bded042e78 100644 --- a/fs/smb/client/reparse.c +++ b/fs/smb/client/reparse.c @@ -1280,6 +1280,7 @@ bool cifs_reparse_point_to_fattr(struct cifs_sb_info *cifs_sb, break; case 0: /* SMB1 symlink */ case IO_REPARSE_TAG_SYMLINK: + fattr->cf_mode &= ~S_IFMT; fattr->cf_mode |= S_IFLNK; break; default: From f77de4c33f0edbb33411f92a35d7196965597e6d Mon Sep 17 00:00:00 2001 From: Jia Wang Date: Mon, 7 Sep 2026 17:54:44 +0800 Subject: [PATCH 0968/1198] spi: dt-bindings: snps,dw-apb-ssi: Add compatible for UltraRISC DP1000 SoC Add the SoC-specific compatible string and use the generic one as fallback for the UltraRISC DP1000 SPI controller. The DP1000 integrates two SPI controllers. SPI0 supports standard, dual and quad transfers with three native chip-select signals. SPI1 supports standard transfers with four native chip-select signals. Both controllers have one register range and separate reference and APB interface clocks. Signed-off-by: Jia Wang Acked-by: Conor Dooley Link: https://patch.msgid.link/20260907-ultrarisc-dts-v2-5-5eb4c97477c5@ultrarisc.com Signed-off-by: Mark Brown --- .../devicetree/bindings/spi/snps,dw-apb-ssi.yaml | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml index 1e70c6804d5d..e8d6d5d858b6 100644 --- a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml +++ b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml @@ -44,6 +44,21 @@ allOf: else: properties: starfive,sfc-filter-syscon: false + - if: + properties: + compatible: + contains: + const: ultrarisc,dp1000-spi + then: + properties: + reg: + maxItems: 1 + clocks: + minItems: 2 + clock-names: + minItems: 2 + required: + - clock-names properties: compatible: @@ -63,6 +78,7 @@ properties: - mscc,jaguar2-spi - sophgo,sg2042-spi - thead,th1520-spi + - ultrarisc,dp1000-spi - const: snps,dw-apb-ssi - description: Vendor controllers compatible with v1.01a items: From 159720704d9d652b64390c11fb971e15b0a78d23 Mon Sep 17 00:00:00 2001 From: Sunil Khatri Date: Tue, 8 Sep 2026 14:47:29 +0530 Subject: [PATCH 0969/1198] drm/drm_exec: fix up contended obj when num_objects is 0 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit drm_exec_prepare_array() silently returns success without calling drm_exec_lock_contended() when num_objects is zero. This breaks the invariant upheld by drm_exec_lock_obj(), where every entry point into the locking sequence must first attempt to lock any previously contended object before proceeding. Drivers that chain multiple drm_exec_prepare_array() calls per drm_exec_until_all_locked() iteration (e.g. amdgpu's userq signal/wait ioctls, which prepare separate read and write BO arrays) can pass an empty array for one of the two calls. If contention is hit while preparing the non-empty array, exec->contended is set and the loop retries; on retry, the empty-array call preceding it is a no-op that never clears exec->contended, so drm_exec_retry_on_contention() immediately jumps back to the top of the loop without ever reaching the call that would resolve the contention. This spins forever. Fix it by having drm_exec_prepare_array() call drm_exec_lock_contended() directly when num_objects is zero, so a pending contended object dont loop infinitely. Fixes: 09593216bff1 ("drm: execution context for GEM buffers v7") CC: stable@vger.kernel.org # v6.6+ Signed-off-by: Sunil Khatri Link: https://lore.kernel.org/r/20260908091729.2749399-1-sunil.khatri@amd.com Reviewed-by: Christian König Signed-off-by: Christian König --- drivers/gpu/drm/drm_exec.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/gpu/drm/drm_exec.c b/drivers/gpu/drm/drm_exec.c index 41034a5996ff..2453ec41360f 100644 --- a/drivers/gpu/drm/drm_exec.c +++ b/drivers/gpu/drm/drm_exec.c @@ -322,6 +322,19 @@ int drm_exec_prepare_array(struct drm_exec *exec, { int ret; + /* + * Make sure to lock a contended object even when no objects are + * given, otherwise drm_exec_retry_on_contention() would loop + * forever on patterns like: + * + * ret = drm_exec_prepare_array(exec, objs, num_objects, ...); + * drm_exec_retry_on_contention(exec); + * + * with num_objects == 0. + */ + if (!num_objects) + return drm_exec_lock_contended(exec); + for (unsigned int i = 0; i < num_objects; ++i) { ret = drm_exec_prepare_obj(exec, objects[i], num_fences); if (unlikely(ret)) From dd519eb8f66eaa205bbbdcb753588138a1d18414 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 8 Sep 2026 20:55:17 +0200 Subject: [PATCH 0970/1198] platform/x86: x86-android-tablets: fix gpio_secondary_fwnode_init() not working MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit acpi_bus_find_device_by_name() call returns a pointer to the device object on the ACPI bus, aka the ACPI companion device. gpio_secondary_fwnode_init() then continues with setting the secondary fwnode on this device. But this is not the actual physical device for the GPIO controller (e.g. the GPIO controller platform bus device). This mismatch is causing GPIO lookups by secondary fwnode to not work. Modify gpio_secondary_fwnode_init() to instead set the secondary fwnode of the first physical device associated with the ACPI companion device. This fixes the GPIO lookups not working. Fixes: 1448c2d2ca5c ("platform/x86: x86-android-tablets: enable fwnode matching of GPIO chips") Reviewed-by: Dmitry Torokhov Signed-off-by: Hans de Goede Link: https://patch.msgid.link/20260908185517.49047-1-johannes.goede@oss.qualcomm.com Signed-off-by: Ilpo Järvinen --- drivers/platform/x86/x86-android-tablets/core.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/platform/x86/x86-android-tablets/core.c b/drivers/platform/x86/x86-android-tablets/core.c index b028af1c9942..cfff7f5eac5d 100644 --- a/drivers/platform/x86/x86-android-tablets/core.c +++ b/drivers/platform/x86/x86-android-tablets/core.c @@ -390,6 +390,7 @@ static int gpio_secondary_fwnode_init(struct device *parent, { const struct software_node *const *swnode; struct fwnode_handle *fwnode; + struct device *phys_dev; int ret; if (!node_group) @@ -417,9 +418,15 @@ static int gpio_secondary_fwnode_init(struct device *parent, if (WARN_ON(!fwnode)) return -ENOENT; - set_secondary_fwnode(dev, fwnode); + phys_dev = acpi_get_first_physical_node(to_acpi_device(dev)); + if (!phys_dev) + return dev_err_probe(parent, -ENODEV, + "No physical device for ACPI GPIO dev: %pfwP\n", + fwnode); - ret = devm_add_action_or_reset(parent, gpio_secondary_unset, get_device(dev)); + set_secondary_fwnode(phys_dev, fwnode); + + ret = devm_add_action_or_reset(parent, gpio_secondary_unset, get_device(phys_dev)); if (ret) return ret; } From 7dd4c829bac2916be98a3e34b41daaba7f42b4c4 Mon Sep 17 00:00:00 2001 From: Myeonghun Pak Date: Mon, 20 Jul 2026 22:58:46 +0900 Subject: [PATCH 0971/1198] idpf: disable DIM work before freeing q_vectors idpf never drains the Tx/Rx DIM works before freeing the memory they live in. tx_dim and rx_dim are embedded in struct idpf_q_vector, they are queued from the NAPI poll via net_dim(), and idpf_vport_intr_rel() ends with kfree(rsrc->q_vectors). Nothing in the driver cancels them. idpf_tx_dim_work() and idpf_rx_dim_work() then run on freed memory: idpf_vport_intr_write_itr() writes the ITR register through q_vector->intr_reg.tx_itr / rx_itr, void __iomem pointers loaded out of the freed q_vector. No configuration is needed to get there -- IDPF_ITR_IS_DYNAMIC() is defined as (itr_mode) and idpf_vport_alloc() initialises both modes to IDPF_ITR_DYNAMIC. Draining after idpf_vport_intr_napi_dis_all() is not enough on its own. idpf_net_dim() is called from inside the "if (napi_complete_done(napi, work_done))" branch of the poll, and napi_complete_done() has already cleared NAPIF_STATE_SCHED by then. napi_disable_locked() waits only while (val & (NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC)), so napi_disable() can return while the poll tail is still queueing the work, and a plain cancel_work_sync() would be re-armed behind the drain. Use disable_work_sync(): schedule_work() on a work with a non-zero disable count is dropped by clear_pending_if_disabled() before __queue_work() is reached. Move idpf_init_dim() to idpf_vport_intr_alloc() so the works are initialised on every path that can reach the drain -- the three "goto intr_deinit" sites between idpf_vport_intr_init() and idpf_vport_intr_ena() get there without the enable side having run. Nothing re-enables them: rsrc->q_vectors is freed on every exit from idpf_vport_open() and on every idpf_vport_stop(), so the count dies with the object. It is a race, not a deterministic failure -- net_dim() only schedules once DIM_NEVENTS events have accumulated and the profile index changes. A KASAN ifup/ifdown loop under load is the way to see it. Fixes: c2d548cad150 ("idpf: add TX splitq napi poll support") Fixes: 3a8845af66ed ("idpf: add RX splitq napi poll support") Cc: # see patch description, needs adjustments for <= 6.9 Co-developed-by: Ijae Kim Signed-off-by: Ijae Kim Signed-off-by: Myeonghun Pak Tested-by: Samuel Salin Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/idpf/idpf_txrx.c | 24 ++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 24b91be25676..9ba9c2952d78 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -4145,6 +4145,26 @@ static void idpf_vport_intr_ena_irq_all(struct idpf_vport *vport, writel(rsrc->noirq_dyn_ctl_ena, rsrc->noirq_dyn_ctl); } +/** + * idpf_vport_intr_dis_dim_all - Disable DIM work for all q_vectors + * @rsrc: pointer to queue and vector resources + * + * The DIM works are embedded in the q_vector array that + * idpf_vport_intr_rel() frees, and the poll arms them after + * napi_complete_done() has already cleared NAPI_STATE_SCHED. Disable + * rather than just cancel, so that a poll tail still running past + * napi_disable() cannot queue them again behind the drain. + */ +static void idpf_vport_intr_dis_dim_all(struct idpf_q_vec_rsrc *rsrc) +{ + for (u16 v_idx = 0; v_idx < rsrc->num_q_vectors; v_idx++) { + struct idpf_q_vector *q_vector = &rsrc->q_vectors[v_idx]; + + disable_work_sync(&q_vector->tx_dim.work); + disable_work_sync(&q_vector->rx_dim.work); + } +} + /** * idpf_vport_intr_deinit - Release all vector associations for the vport * @vport: main vport structure @@ -4155,6 +4175,7 @@ void idpf_vport_intr_deinit(struct idpf_vport *vport, { idpf_vport_intr_dis_irq_all(rsrc); idpf_vport_intr_napi_dis_all(rsrc); + idpf_vport_intr_dis_dim_all(rsrc); idpf_vport_intr_napi_del_all(rsrc); idpf_vport_intr_rel_irq(vport, rsrc); } @@ -4235,7 +4256,6 @@ static void idpf_vport_intr_napi_ena_all(struct idpf_q_vec_rsrc *rsrc) for (u16 q_idx = 0; q_idx < rsrc->num_q_vectors; q_idx++) { struct idpf_q_vector *q_vector = &rsrc->q_vectors[q_idx]; - idpf_init_dim(q_vector); napi_enable(&q_vector->napi); } } @@ -4578,6 +4598,8 @@ int idpf_vport_intr_alloc(struct idpf_vport *vport, q_coal = &user_config->q_coalesce[v_idx]; q_vector->vport = vport; + idpf_init_dim(q_vector); + q_vector->tx_itr_value = q_coal->tx_coalesce_usecs; q_vector->tx_intr_mode = q_coal->tx_intr_mode; q_vector->tx_itr_idx = VIRTCHNL2_ITR_IDX_1; From 650f197d8ea6ebbc9ce1c9fb0358258b65e74291 Mon Sep 17 00:00:00 2001 From: Myeonghun Pak Date: Mon, 20 Jul 2026 23:35:10 +0900 Subject: [PATCH 0972/1198] idpf: disable PTM on probe failure and on remove idpf_probe() enables PCIe Precision Time Measurement with pci_enable_ptm(), which takes a reference on the device and on every PTM-capable device up the path to the PTM Root. Neither the probe error path nor idpf_remove() drops that reference, so the PTM enable counts of this device and of its upstream path stay elevated with no bound driver, and the device's PTM control bits remain set. pcim_enable_device() only arranges for pci_disable_device() and does not undo the PTM enable. Add the matching pci_disable_ptm() to the common unwind path. pci_enable_ptm() failure is not fatal here, so guard the call with pcie_ptm_enabled(): pci_disable_ptm() decrements dev->ptm_enable_cnt unconditionally and then recurses upstream, so calling it after a failed enable would drive this device's count negative and wrongly decrement parents shared with other endpoints. This issue was identified during our ongoing static-analysis research while reviewing kernel code. Fixes: 8d5e12c5921c ("idpf: add initial PTP support") Co-developed-by: Ijae Kim Signed-off-by: Ijae Kim Signed-off-by: Myeonghun Pak Reviewed-by: Aleksandr Loktionov Tested-by: Samuel Salin [TN moved call due to commit 6b284aa2ddf3 ("idpf: refactor idpf to use libie_pci APIs")] Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/idpf/idpf_main.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/intel/idpf/idpf_main.c b/drivers/net/ethernet/intel/idpf/idpf_main.c index 9840580fbe51..129bccaa6baa 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_main.c +++ b/drivers/net/ethernet/intel/idpf/idpf_main.c @@ -106,6 +106,11 @@ static int idpf_dev_init(struct idpf_adapter *adapter, */ static void idpf_decfg_device(struct idpf_adapter *adapter) { + struct pci_dev *pdev = adapter->pdev; + + if (pcie_ptm_enabled(pdev)) + pci_disable_ptm(pdev); + libie_pci_unmap_all_mmio_regions(&adapter->ctlq_ctx.mmio_info); } From cc6d60ef92278a31ffc2e94966a0921b9646af18 Mon Sep 17 00:00:00 2001 From: Joshua Hay Date: Mon, 27 Jul 2026 16:08:48 -0700 Subject: [PATCH 0973/1198] idpf: account for VLAN header when parsing RSC packet header While parsing the header of a Receive Side Coalesced (RSC) packet, check if a VLAN tag is present and adjust the header parsing accordingly. Otherwise, Rx TCP traffic is completely broken for any VLAN interface whose underlying interface has RSC (rx-gro-hw) enabled. We only need to worry about one VLAN header since Rx packets with multiple VLAN headers are not candidates for RSC. Fixes: 3a8845af66edb ("idpf: add RX splitq napi poll support") Signed-off-by: Joshua Hay Reviewed-by: Emil Tantilov Reviewed-by: Aleksandr Loktionov Tested-by: Samuel Salin Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/idpf/idpf_txrx.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 9ba9c2952d78..4311ffa30bb1 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -3299,6 +3299,7 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb, struct libeth_rx_pt decoded) { u16 rsc_segments, rsc_seg_len; + u16 l3_start = 0; bool ipv4, ipv6; int len; @@ -3321,7 +3322,10 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb, NAPI_GRO_CB(skb)->count = rsc_segments; skb_shinfo(skb)->gso_size = rsc_seg_len; - skb_reset_network_header(skb); + if (unlikely(eth_type_vlan(skb->protocol))) + l3_start = VLAN_HLEN; + + skb_set_network_header(skb, l3_start); if (ipv4) { struct iphdr *ipv4h = ip_hdr(skb); @@ -3329,7 +3333,7 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb, skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; /* Reset and set transport header offset in skb */ - skb_set_transport_header(skb, sizeof(struct iphdr)); + skb_set_transport_header(skb, l3_start + sizeof(struct iphdr)); len = skb->len - skb_transport_offset(skb); /* Compute the TCP pseudo header checksum*/ @@ -3339,7 +3343,7 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb, struct ipv6hdr *ipv6h = ipv6_hdr(skb); skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; - skb_set_transport_header(skb, sizeof(struct ipv6hdr)); + skb_set_transport_header(skb, l3_start + sizeof(struct ipv6hdr)); len = skb->len - skb_transport_offset(skb); tcp_hdr(skb)->check = ~tcp_v6_check(len, &ipv6h->saddr, &ipv6h->daddr, 0); From 53432c4c3e869076350aef319534431af8ba99c1 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 6 Jul 2026 16:31:17 -0700 Subject: [PATCH 0974/1198] ice: add missing xa_destroy for sched_node_ids Commit 16dfa49406bc ("ice: Introduce new parameters in ice_sched_node") added a sched_node_ids xarray to the port info structure, but never called xa_destroy on it. Since xarrays can allocate internal memory, this can result in a memory leak even if every element in the xarray has been removed. The xarray is currently embedded in the port_info structure. This appears to have been done because its use is within functions that take the port_info as a primary argument. However, this complicates managing the lifecycle of the field. The port_info structure is allocated in ice_init_hw() using devm, and it is not released until the devm cleanup when the driver is unloaded. The ice_init_hw() function is called in many places, including devlink reload, and possibly during DDP load after updating the Tx scheduler layout. Adding a call of xa_destroy to the ice_deinit_hw() causes Sashiko to raise multiple concerns due to potential ordering issues and possible ways that port_info could be a dangling reference. To handle this, move the sched_node_ids out of port_info and into the hw structure. All users of the array already have a pointer to hw anyways, and there is only one sched_node_ids per adapter. While here, remove the overly verbose comment explaining the nature of the sched_node_ids xarray. Add the missing xa_destroy to the cleanup path and to ice_deinit_hw(), ensuring that we properly release the xarray memory. This was caught by Sashiko during development of unrelated code. Fixes: 16dfa49406bc ("ice: Introduce new parameters in ice_sched_node") Signed-off-by: Jacob Keller Reviewed-by: Aleksandr Loktionov Tested-by: Rinitha S (A Contingent worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_common.c | 9 ++++++--- drivers/net/ethernet/intel/ice/ice_sched.c | 4 ++-- drivers/net/ethernet/intel/ice/ice_type.h | 2 +- 3 files changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index ef1ce106f81b..04633103e3e6 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -1051,14 +1051,13 @@ int ice_init_hw(struct ice_hw *hw) hw->evb_veb = true; - /* init xarray for identifying scheduling nodes uniquely */ - xa_init_flags(&hw->port_info->sched_node_ids, XA_FLAGS_ALLOC); + xa_init_flags(&hw->sched_node_ids, XA_FLAGS_ALLOC); /* Query the allocated resources for Tx scheduler */ status = ice_sched_query_res_alloc(hw); if (status) { ice_debug(hw, ICE_DBG_SCHED, "Failed to get scheduler allocated resources\n"); - goto err_unroll_alloc; + goto err_unroll_xarray; } ice_sched_get_psm_clk_freq(hw); @@ -1146,6 +1145,8 @@ int ice_init_hw(struct ice_hw *hw) ice_cleanup_fltr_mgmt_struct(hw); err_unroll_sched: ice_sched_cleanup_all(hw); +err_unroll_xarray: + xa_destroy(&hw->sched_node_ids); err_unroll_alloc: devm_kfree(ice_hw_to_dev(hw), hw->port_info); err_unroll_cqinit: @@ -1186,6 +1187,8 @@ void ice_deinit_hw(struct ice_hw *hw) /* Clear VSI contexts if not already cleared */ ice_clear_all_vsi_ctx(hw); + + xa_destroy(&hw->sched_node_ids); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index fff0c1afdb41..ffa18d86729a 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -371,7 +371,7 @@ void ice_free_sched_node(struct ice_port_info *pi, struct ice_sched_node *node) devm_kfree(ice_hw_to_dev(hw), node->children); kfree(node->name); - xa_erase(&pi->sched_node_ids, node->id); + xa_erase(&hw->sched_node_ids, node->id); devm_kfree(ice_hw_to_dev(hw), node); } @@ -977,7 +977,7 @@ ice_sched_add_elems(struct ice_port_info *pi, struct ice_sched_node *tc_node, if (!new_node->name) return -ENOMEM; - status = xa_alloc(&pi->sched_node_ids, &new_node->id, NULL, XA_LIMIT(0, UINT_MAX), + status = xa_alloc(&hw->sched_node_ids, &new_node->id, NULL, XA_LIMIT(0, UINT_MAX), GFP_KERNEL); if (status) { ice_debug(hw, ICE_DBG_SCHED, "xa_alloc failed for sched node status =%d\n", diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index d9a5c1aae7c2..cf147a212707 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -765,7 +765,6 @@ struct ice_port_info { /* List contain profile ID(s) and other params per layer */ struct list_head rl_prof_list[ICE_AQC_TOPO_MAX_LEVEL_NUM]; struct ice_qos_cfg qos_cfg; - struct xarray sched_node_ids; u8 is_vf:1; u8 is_custom_tx_enabled:1; }; @@ -930,6 +929,7 @@ struct ice_hw { u8 sw_entry_point_layer; u16 max_children[ICE_AQC_TOPO_MAX_LEVEL_NUM]; struct list_head agg_list; /* lists all aggregator */ + struct xarray sched_node_ids; struct ice_vsi_ctx *vsi_ctx[ICE_MAX_VSI]; u8 evb_veb; /* true for VEB, false for VEPA */ From b8bf9bfda5f62e11444e483c2b4aaff90c5cfc6b Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 20 Aug 2026 19:02:01 -0700 Subject: [PATCH 0975/1198] eth: ice: don't dereference pointers from TP_printk() After forwarding net-next during the v7.3 merge window we started seeing: TRACE EVENT ERROR: Event ice_tx_dim_work has double dereference in TP_printk: REC->q_vector->tx.tx_ring->q_index WARNING: kernel/trace/trace_events.c:420 at test_double_dereference.cold+0x39/0x4b this is due to extra checks added in tracing subsystem in commit b5cc230af5e5 ("tracing: Warn when an event dereferences a pointer in TP_printk()"). Printing happens long after the event was recorded, by which point the pointers may be invalid (the ring or the dim instance). Copy the eight scalars into the event instead. Fixes: 3089cf6d3caa ("ice: add tracepoints") Signed-off-by: Jakub Kicinski Tested-by: Alexander Nowlin Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_trace.h | 64 ++++++++++++++-------- 1 file changed, 42 insertions(+), 22 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_trace.h b/drivers/net/ethernet/intel/ice/ice_trace.h index 4f35ef8d6b29..7568c917cdbe 100644 --- a/drivers/net/ethernet/intel/ice/ice_trace.h +++ b/drivers/net/ethernet/intel/ice/ice_trace.h @@ -63,23 +63,33 @@ DECLARE_EVENT_CLASS(ice_rx_dim_template, TP_PROTO(struct ice_q_vector *q_vector, struct dim *dim), TP_ARGS(q_vector, dim), - TP_STRUCT__entry(__field(struct ice_q_vector *, q_vector) - __field(struct dim *, dim) + TP_STRUCT__entry(__field(u16, q_index) + __field(u8, state) + __field(u8, profile_ix) + __field(u8, tune_state) + __field(u8, steps_right) + __field(u8, steps_left) + __field(u8, tired) __string(devname, q_vector->rx.rx_ring->netdev->name)), - TP_fast_assign(__entry->q_vector = q_vector; - __entry->dim = dim; + TP_fast_assign(__entry->q_index = q_vector->rx.rx_ring->q_index; + __entry->state = dim->state; + __entry->profile_ix = dim->profile_ix; + __entry->tune_state = dim->tune_state; + __entry->steps_right = dim->steps_right; + __entry->steps_left = dim->steps_left; + __entry->tired = dim->tired; __assign_str(devname);), TP_printk("netdev: %s Rx-Q: %d dim-state: %d dim-profile: %d dim-tune: %d dim-st-right: %d dim-st-left: %d dim-tired: %d", __get_str(devname), - __entry->q_vector->rx.rx_ring->q_index, - __entry->dim->state, - __entry->dim->profile_ix, - __entry->dim->tune_state, - __entry->dim->steps_right, - __entry->dim->steps_left, - __entry->dim->tired) + __entry->q_index, + __entry->state, + __entry->profile_ix, + __entry->tune_state, + __entry->steps_right, + __entry->steps_left, + __entry->tired) ); DEFINE_EVENT(ice_rx_dim_template, ice_rx_dim_work, @@ -90,23 +100,33 @@ DEFINE_EVENT(ice_rx_dim_template, ice_rx_dim_work, DECLARE_EVENT_CLASS(ice_tx_dim_template, TP_PROTO(struct ice_q_vector *q_vector, struct dim *dim), TP_ARGS(q_vector, dim), - TP_STRUCT__entry(__field(struct ice_q_vector *, q_vector) - __field(struct dim *, dim) + TP_STRUCT__entry(__field(u16, q_index) + __field(u8, state) + __field(u8, profile_ix) + __field(u8, tune_state) + __field(u8, steps_right) + __field(u8, steps_left) + __field(u8, tired) __string(devname, q_vector->tx.tx_ring->netdev->name)), - TP_fast_assign(__entry->q_vector = q_vector; - __entry->dim = dim; + TP_fast_assign(__entry->q_index = q_vector->tx.tx_ring->q_index; + __entry->state = dim->state; + __entry->profile_ix = dim->profile_ix; + __entry->tune_state = dim->tune_state; + __entry->steps_right = dim->steps_right; + __entry->steps_left = dim->steps_left; + __entry->tired = dim->tired; __assign_str(devname);), TP_printk("netdev: %s Tx-Q: %d dim-state: %d dim-profile: %d dim-tune: %d dim-st-right: %d dim-st-left: %d dim-tired: %d", __get_str(devname), - __entry->q_vector->tx.tx_ring->q_index, - __entry->dim->state, - __entry->dim->profile_ix, - __entry->dim->tune_state, - __entry->dim->steps_right, - __entry->dim->steps_left, - __entry->dim->tired) + __entry->q_index, + __entry->state, + __entry->profile_ix, + __entry->tune_state, + __entry->steps_right, + __entry->steps_left, + __entry->tired) ); DEFINE_EVENT(ice_tx_dim_template, ice_tx_dim_work, From dcaf83ead130d3067862599089b0999b3da140a4 Mon Sep 17 00:00:00 2001 From: Rong Zhang Date: Wed, 2 Sep 2026 02:19:18 +0800 Subject: [PATCH 0976/1198] Bluetooth: Properly disable remote wakeup for MT7922/MT7925 on Ryzen platform It is reported that a remote wakeup could cause MT7922/MT7925's btusb interface completely unresponsive. Resetting the xHCI root hub doesn't help at all, and recovering from such a state needs a power cycle. All reports seen to be relevant to Ryzen-based laptops. These NICs are usually used as OEM components thanks to some sort of reference designs. Their popularity on other platforms is unclear. While there is still a chance that the quirk may exist on other platforms, be cautious and only apply the quirk to direct children of Ryzen platforms's root hubs for the time being. In most cases the root hub is on the SoC or PCH, which needs the quirk. Unfortunately, this can't distinguish root hubs on PCIe add-in cards. Such roughness should be acceptable, as PCIe USB controller add-in cards are less commonly used nowadays. On the other hand, applying the quirk doesn't hurt any functionalities either, as the device can still be used as a wakeup source if desired. Theoretically, we could retrieve the root hub's PCI vendor ID with some hierarchy magic, but that's too intrusive... Meanwhile, though device_set_wakeup_capable(false) is the correct fix for other NICs with fake remote wakeup capabilities, doing so for MT7922/MT7925 effectively prevents it from being used as wakeup sources as per userspace requests. Hence, return -EBUSY on runtime suspend to prevent the interface from being autosuspended while it's still opened, which has the same effect as device_set_wakeup_capable(false), since disabling remote wakeup simply causes the USB core to gate runtime autosuspend as well due to needs_remote_wakeup == 1. The interface can be safely autosuspended as long as remote wakeup is disabled, i.e., after closing the HCI device. Specifically, the interface may still take the advantage of remote wakeup in order to wake up the system from sleep if userspace has enabled it as a wakeup source. Fixes: e31d761628ad ("Bluetooth: btmtk: Disable remote wakeup for MT7922/MT7925") Tested-by: Rafael Passos Signed-off-by: Rong Zhang Signed-off-by: Luiz Augusto von Dentz --- drivers/bluetooth/btmtk.c | 10 ------ drivers/bluetooth/btusb.c | 73 ++++++++++++++++++++++++++++++++++++--- 2 files changed, 69 insertions(+), 14 deletions(-) diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c index c0ed51567ed4..9589caff925d 100644 --- a/drivers/bluetooth/btmtk.c +++ b/drivers/bluetooth/btmtk.c @@ -1374,16 +1374,6 @@ int btmtk_usb_setup(struct hci_dev *hdev) break; case 0x7922: case 0x7925: - /* - * A remote wakeup could cause the device completely unresponsive, and - * recovering from such a state needs a power cycle. - * - * Since the remote wakeup capability is super broken, just disable it - * to get rid of the troubles. The device can still be autosuspended - * when the bluetooth interface is closed. - */ - device_set_wakeup_capable(&btmtk_data->udev->dev, false); - fallthrough; case 0x7961: case 0x7902: case 0x6639: diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index d70a3e7a13f5..95f4640c60e4 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -6,6 +6,7 @@ * Copyright (C) 2005-2008 Marcel Holtmann */ +#include #include #include #include @@ -980,6 +981,7 @@ struct btqca_data { #define BTUSB_USE_ALT3_FOR_WBS 15 #define BTUSB_ALT6_CONTINUOUS_TX 16 #define BTUSB_HW_SSR_ACTIVE 17 +#define BTUSB_WAKEUP_BROKEN 18 struct btusb_data { struct hci_dev *hdev; @@ -2969,10 +2971,25 @@ static int btusb_send_frame_mtk(struct hci_dev *hdev, struct sk_buff *skb) } } +static inline bool platform_is_ryzen(void) +{ +#ifdef CONFIG_X86 + return boot_cpu_has(X86_FEATURE_ZEN); +#else + return false; +#endif +} + +static inline bool is_direct_child_of_root_hub(struct usb_device *udev) +{ + return udev->parent == udev->bus->root_hub; +} + static int btusb_mtk_setup(struct hci_dev *hdev) { struct btusb_data *data = hci_get_drvdata(hdev); struct btmtk_data *btmtk_data = hci_get_priv(hdev); + int err; /* MediaTek WMT vendor cmd requiring below USB resources to * complete the handshake. @@ -2989,7 +3006,40 @@ static int btusb_mtk_setup(struct hci_dev *hdev) btusb_mtk_claim_iso_intf(data); } - return btmtk_usb_setup(hdev); + err = btmtk_usb_setup(hdev); + if (err) + return err; + + switch (btmtk_data->dev_id) { + case 0x7922: + case 0x7925: + /* + * All reports seen to be relevant to Ryzen-based laptops. These + * NICs are usually used as OEM components thanks to some sort + * of reference designs. + * + * Their popularity on other platforms is unclear. While there + * is still a chance that the quirk may exist on other + * platforms, be cautious and only apply the quirk to direct + * children of Ryzen platforms's root hubs for the time being. + * + * In most cases the root hub is on the SoC or PCH, which needs + * the quirk. Unfortunately, this can't distinguish root hubs on + * PCIe add-in cards. Such roughness should be acceptable, as + * PCIe USB controller add-in cards are less commonly used + * nowadays. On the other hand, applying the quirk doesn't hurt + * any functionalities either, as the device can still be used + * as a wakeup source if desired. + * + * Theoretically, we could retrieve the root hub's PCI vendor ID + * with some hierarchy magic, but that's too intrusive... + */ + if (platform_is_ryzen() && is_direct_child_of_root_hub(data->udev)) + set_bit(BTUSB_WAKEUP_BROKEN, &data->flags); + break; + } + + return 0; } static int btusb_mtk_shutdown(struct hci_dev *hdev) @@ -4565,11 +4615,26 @@ static int btusb_suspend(struct usb_interface *intf, pm_message_t message) BT_DBG("intf %p", intf); - /* Don't auto-suspend if there are connections or discovery in - * progress; external suspend calls shall never fail. + /* + * It is reported that remote wakeup events could sometimes cause some + * adapters completely unresponsive. Resetting the xHCI root hub doesn't + * help at all, and recovering from such a state needs a power cycle. + * Since disabling remote wakeup simply causes the USB core to gate + * runtime autosuspend as well due to needs_remote_wakeup == 1, let's do + * this ourselves to make our life easier. The interface can be safely + * autosuspended as long as remote wakeup is disabled, i.e., after + * closing the HCI device. + * + * Don't auto-suspend if there are connections or discovery in progress. + * + * External suspend calls shall never fail. Specifically, a device with + * broken remote wakeup may still take the advantage of remote wakeup in + * order to wake up the system from sleep if userspace has enabled it as + * a wakeup source. */ if (PMSG_IS_AUTO(message) && - (hci_conn_count(data->hdev) || hci_discovery_active(data->hdev))) + ((test_bit(BTUSB_WAKEUP_BROKEN, &data->flags) && data->intf->needs_remote_wakeup) || + hci_conn_count(data->hdev) || hci_discovery_active(data->hdev))) return -EBUSY; if (data->suspend_count++) From 1c12c3117639e78940959d956519c758c57d0849 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Mon, 31 Aug 2026 12:13:10 -0400 Subject: [PATCH 0977/1198] Bluetooth: btusb: Fix UAF of btusb_data by rx_work btusb_close() and btusb_flush() cancel data->rx_work with the asynchronous cancel_delayed_work(), so if btusb_rx_work() is already running on another CPU it keeps running after the cancel returns. btusb_disconnect() calls hci_unregister_dev(), which invokes btusb_close(), and then frees the btusb_data. A still running btusb_rx_work() then dereferences the freed data: while ((skb = skb_dequeue(&data->acl_q))) data->recv_acl(data->hdev, skb); Use cancel_delayed_work_sync() instead. In btusb_close() the cancel also has to happen after btusb_stop_traffic(), otherwise an URB completion racing with the cancel can requeue the work right after it has been waited for. Fixes: 800fe5ec302e ("Bluetooth: btusb: Add support for queuing during polling interval") Signed-off-by: Luiz Augusto von Dentz --- drivers/bluetooth/btusb.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 95f4640c60e4..ddc44ca28722 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -2094,18 +2094,24 @@ static int btusb_close(struct hci_dev *hdev) BT_DBG("%s", hdev->name); - cancel_delayed_work(&data->rx_work); cancel_work_sync(&data->work); cancel_work_sync(&data->waker); - skb_queue_purge(&data->acl_q); - clear_bit(BTUSB_ISOC_RUNNING, &data->flags); clear_bit(BTUSB_BULK_RUNNING, &data->flags); clear_bit(BTUSB_INTR_RUNNING, &data->flags); clear_bit(BTUSB_DIAG_RUNNING, &data->flags); btusb_stop_traffic(data); + + /* rx_work must only be canceled once the URBs that can rearm it are + * gone, and it must be canceled synchronously since btusb_disconnect() + * frees the btusb_data it dereferences right after hci_unregister_dev(). + */ + cancel_delayed_work_sync(&data->rx_work); + + skb_queue_purge(&data->acl_q); + btusb_free_frags(data); err = usb_autopm_get_interface(data->intf); @@ -2131,7 +2137,7 @@ static int btusb_flush(struct hci_dev *hdev) BT_DBG("%s", hdev->name); - cancel_delayed_work(&data->rx_work); + cancel_delayed_work_sync(&data->rx_work); skb_queue_purge(&data->acl_q); From 83e3e515fd261600ed8491fb0a8bcdfb115c904e Mon Sep 17 00:00:00 2001 From: Rong Zhang Date: Thu, 3 Sep 2026 03:18:59 +0800 Subject: [PATCH 0978/1198] Bluetooth: btrtl: Don't leak return code when parsing firmware format v2 When key_id from chip is zero, rtlbt_parse_firmware_v2() intentionally ignores all security headers. However, the implementation simply breaks from a switch statement and leaks uninitialized return code `rc' (if the first section is a security one) or the previous section's `rc'. Fix it by really skipping a loop with `continue'. For consistency and readability, also do the same for the default case. Fixes: 9a24ce5e29b1 ("Bluetooth: btrtl: Firmware format v2 support") Cc: stable@vger.kernel.org Signed-off-by: Rong Zhang Signed-off-by: Luiz Augusto von Dentz --- drivers/bluetooth/btrtl.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index 03fa9409e3ee..d29813331603 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -591,7 +591,7 @@ static int rtlbt_parse_firmware_v2(struct hci_dev *hdev, * headers. */ if (!key_id) - break; + continue; rc = btrtl_parse_section(hdev, btrtl_dev, opcode, ptr, section_len); break; @@ -600,8 +600,7 @@ static int rtlbt_parse_firmware_v2(struct hci_dev *hdev, ptr, section_len); break; default: - rc = 0; - break; + continue; } if (rc < 0) { rtl_dev_err(hdev, "RTL: Parse section (%u) err %d", From 6436e1b5331b1aebf905c13e0880a37032719b75 Mon Sep 17 00:00:00 2001 From: Kiran K Date: Thu, 3 Sep 2026 20:21:01 +0530 Subject: [PATCH 0979/1198] Bluetooth: btintel_pcie: validate packet_len before skb_put_data btintel_pcie_submit_rx_work() reads packet_len from rfh_hdr without checking if it exceeds the RX buffer size. An oversized packet_len can lead to an out-of-bounds read in skb_put_data(). Validate packet_len to ensure it is non-zero and does not exceed BTINTEL_PCIE_BUFFER_SIZE - sizeof(*rfh_hdr), logging an error when invalid. This issue was reported by Claude Mythos. It can be simulated either by using customized firmware configured to return an invalid packet_len or by modifying rfh_hdr->packet_len in the driver before calling btintel_pcie_submit_rx_work(). Fixes: c2b636b3f788 ("Bluetooth: btintel_pcie: Add support for PCIe transport") Signed-off-by: Kiran K Signed-off-by: Luiz Augusto von Dentz --- drivers/bluetooth/btintel_pcie.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c index eec95e5f3dbb..968608932fb7 100644 --- a/drivers/bluetooth/btintel_pcie.c +++ b/drivers/bluetooth/btintel_pcie.c @@ -1599,7 +1599,9 @@ static int btintel_pcie_submit_rx_work(struct btintel_pcie_data *data, u8 status rfh_hdr = buf; len = rfh_hdr->packet_len; - if (len <= 0) { + if (len == 0 || len > BTINTEL_PCIE_BUFFER_SIZE - sizeof(*rfh_hdr)) { + bt_dev_err(data->hdev, "Invalid packet_len %d (max %zu)", len, + BTINTEL_PCIE_BUFFER_SIZE - sizeof(*rfh_hdr)); ret = -EINVAL; goto resubmit; } From 3dd1b41f96aad08444be1b7626c89de2b9f2abd4 Mon Sep 17 00:00:00 2001 From: Kiran K Date: Thu, 3 Sep 2026 20:21:02 +0530 Subject: [PATCH 0980/1198] Bluetooth: btintel_pcie: fix tx_handle bounds off-by-one Valid indices into txq->urbd0s/tfds/bufs are 0..txq->count-1, so tfd_index == txq->count is already out of range. Change the guard in btintel_pcie_msix_tx_handle() from '> txq->count' to '>= txq->count'. This issue was reported by Claude Mythos. Fixes: c2b636b3f788 ("Bluetooth: btintel_pcie: Add support for PCIe transport") Signed-off-by: Kiran K Signed-off-by: Luiz Augusto von Dentz --- drivers/bluetooth/btintel_pcie.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c index 968608932fb7..6d9649776ae7 100644 --- a/drivers/bluetooth/btintel_pcie.c +++ b/drivers/bluetooth/btintel_pcie.c @@ -1099,7 +1099,7 @@ static void btintel_pcie_msix_tx_handle(struct btintel_pcie_data *data) urbd0 = &txq->urbd0s[cr_tia]; - if (urbd0->tfd_index > txq->count) + if (urbd0->tfd_index >= txq->count) return; cr_tia = (cr_tia + 1) % txq->count; From 3621f78d43b0a9563d5ade68370434c532eea259 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Wed, 2 Sep 2026 13:16:26 -0400 Subject: [PATCH 0981/1198] Bluetooth: hci_sync: Fix not setting CE length properly Both hci_le_set_def_rate_sync() and hci_le_conn_rate_request_sync() were leaving Min_CE_Length and Max_CE_Length set to 0x0000, but the connection event length recommended in requests by a Peripheral has a valid range of 0x0001 to 0x7CFF (Time = N * 125 us, Time Range: 0.125 ms to 3.999875 s), so 0x0000 cannot be used. Set both to the minimum valid value, which is safe since the Controller is not required to use these values: BLUETOOTH CORE SPECIFICATION Version 6.2 | Vol 4, Part E 7.8.157. LE Connection Rate Request command 7.8.158. LE Set Default Rate Parameters command The Min_CE_Length and Max_CE_Length parameters provide the Controller with the expected minimum and maximum length of the connection events. The Controller is not required to use these values. Fixes: 2f8784cfe8a9 ("Bluetooth: Add support for Shorter Connection Interval (SCI) feature") Signed-off-by: Luiz Augusto von Dentz --- net/bluetooth/hci_sync.c | 38 ++++++++++++++++++++++++++++++++++++-- 1 file changed, 36 insertions(+), 2 deletions(-) diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index ffd7b37e7401..3ab5fa3dce96 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -4797,6 +4797,24 @@ static int hci_le_set_def_rate_sync(struct hci_dev *hdev) cp.cont_num = cpu_to_le16(0x0001); cp.supv_timeout = cpu_to_le16(0x000c); /* 120 ms */ + /* The connection event length recommended in requests by a Peripheral + * uses units of 125 us with a valid range of 0x0001 to 0x7CFF + * (0.125 ms to 3.999875 s), so 0x0000 cannot be used. Also note that + * the Controller is not required to use these values: + * + * BLUETOOTH CORE SPECIFICATION Version 6.2 | Vol 4, Part E + * 7.8.158. LE Set Default Rate Parameters command + * + * The Min_CE_Length and Max_CE_Length parameters provide the + * Controller with the expected minimum and maximum length of the + * connection events. The Controller is not required to use these + * values. + * + * So it is safe to just use the minimum. + */ + cp.min_ce_len = cpu_to_le16(0x0001); + cp.max_ce_len = cpu_to_le16(0x0001); + return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_DEF_RATE, sizeof(cp), &cp, HCI_CMD_TIMEOUT); } @@ -7467,8 +7485,24 @@ static int hci_le_conn_rate_request_sync(struct hci_dev *hdev, void *data) cp.max_latency = cpu_to_le16(params->max_latency); cp.cont_num = cpu_to_le16(params->cont_num); cp.supv_timeout = cpu_to_le16(params->rate_supv_timeout); - cp.min_ce_len = cpu_to_le16(0x0000); - cp.max_ce_len = cpu_to_le16(0x0000); + + /* The connection event length recommended in requests by a Peripheral + * uses units of 125 us with a valid range of 0x0001 to 0x7CFF + * (0.125 ms to 3.999875 s), so 0x0000 cannot be used. Also note that + * the Controller is not required to use these values: + * + * BLUETOOTH CORE SPECIFICATION Version 6.2 | Vol 4, Part E + * 7.8.157. LE Connection Rate Request command + * + * The Min_CE_Length and Max_CE_Length parameters provide the + * Controller with the expected minimum and maximum length of the + * connection events. The Controller is not required to use these + * values. + * + * So it is safe to just use the minimum. + */ + cp.min_ce_len = cpu_to_le16(0x0001); + cp.max_ce_len = cpu_to_le16(0x0001); hci_dev_unlock(hdev); From 3d8a8e81ea8ad8813d4c82a12ba53ecb597b217d Mon Sep 17 00:00:00 2001 From: Ivan Hu Date: Fri, 4 Sep 2026 13:30:07 +0800 Subject: [PATCH 0982/1198] Bluetooth: btmtk: Declare MT7920 (MT7961 1a) Bluetooth firmware btmtk_fw_get_filename() constructs the firmware name at runtime, so for the MT7920 variant (dev_id 0x7961 with fw_flavor set) it requests "mediatek/BT_RAM_CODE_MT7961_1a_2_hdr.bin" without ever declaring it via MODULE_FIRMWARE(). Tools that select firmware from module metadata (e.g. "modinfo -F firmware") therefore omit this blob, so request_firmware() fails and Bluetooth does not initialise on MT7920, even though the file is present in linux-firmware. Declare it with MODULE_FIRMWARE(), as the mt76 driver already does for the corresponding MT7920 wifi firmware. Fixes: 1cb63d80fff6 ("Bluetooth: btusb: Add support Mediatek MT7920") Signed-off-by: Ivan Hu Signed-off-by: Luiz Augusto von Dentz --- drivers/bluetooth/btmtk.c | 1 + drivers/bluetooth/btmtk.h | 1 + 2 files changed, 2 insertions(+) diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c index 9589caff925d..26d525acd659 100644 --- a/drivers/bluetooth/btmtk.c +++ b/drivers/bluetooth/btmtk.c @@ -1577,5 +1577,6 @@ MODULE_FIRMWARE(FIRMWARE_MT7663); MODULE_FIRMWARE(FIRMWARE_MT7668); MODULE_FIRMWARE(FIRMWARE_MT7922); MODULE_FIRMWARE(FIRMWARE_MT7961); +MODULE_FIRMWARE(FIRMWARE_MT7920); MODULE_FIRMWARE(FIRMWARE_MT7925); MODULE_FIRMWARE(FIRMWARE_MT7927); diff --git a/drivers/bluetooth/btmtk.h b/drivers/bluetooth/btmtk.h index c83c24897c95..bc26148ec544 100644 --- a/drivers/bluetooth/btmtk.h +++ b/drivers/bluetooth/btmtk.h @@ -7,6 +7,7 @@ #define FIRMWARE_MT7922 "mediatek/BT_RAM_CODE_MT7922_1_1_hdr.bin" #define FIRMWARE_MT7902 "mediatek/BT_RAM_CODE_MT7902_1_1_hdr.bin" #define FIRMWARE_MT7961 "mediatek/BT_RAM_CODE_MT7961_1_2_hdr.bin" +#define FIRMWARE_MT7920 "mediatek/BT_RAM_CODE_MT7961_1a_2_hdr.bin" #define FIRMWARE_MT7925 "mediatek/mt7925/BT_RAM_CODE_MT7925_1_1_hdr.bin" #define FIRMWARE_MT7927 "mediatek/mt7927/BT_RAM_CODE_MT6639_2_1_hdr.bin" From 9b851b09b392da68bd715601f10a5adb2d8d19b8 Mon Sep 17 00:00:00 2001 From: Krystian Kaniewski Date: Fri, 4 Sep 2026 12:24:22 +0000 Subject: [PATCH 0983/1198] Bluetooth: hci_sysfs: Fix NULL pointer dereference in device_del() A NULL pointer dereference in klist_put() occurs when a child device (such as a BNEP network device in bnep_session) is concurrently being unregistered while hci_conn_del_sysfs() reparents child devices. This is caused by a race condition between hci_conn_del_sysfs() and concurrent child device unregistration (e.g. bnep_session calling unregister_netdev()). During device unregistration, device_del() snapshots a non-NULL parent pointer. Concurrently, hci_conn_del_sysfs() finds the child device using device_find_any_child() and calls device_move() to reparent it to NULL, which removes the node from its parent's klist and clears knode_parent. Subsequently, device_del() calls klist_del(&dev->p->knode_parent) using the stale parent snapshot, causing klist_put() to dereference knode_klist(n)->put on an already removed node, resulting in a NULL pointer dereference. This race was introduced by commit 27aabf27fd01 ("Bluetooth: fix use-after-free in device_for_each_child()"), which replaced device_find_child(..., __match_tty) with device_find_any_child() in hci_conn_del_sysfs(). That change was intended to avoid a use-after-free where conn->dev outlived its parent hdev->dev when child devices held references to conn->dev, because conn->dev only held a reference to hdev->dev while registered in sysfs. Fix the issue properly by taking an explicit reference to the parent device with get_device(&hdev->dev) in hci_conn_init_sysfs() and dropping it with put_device(parent) in bt_link_release() when the conn device is freed. This ensures that hdev->dev remains valid for the entire lifecycle of conn->dev, resolving the underlying use-after-free. With the parent reference held properly, restore the __match_tty filter in hci_conn_del_sysfs() so that device_move() is only invoked on persistent RFCOMM TTY devices as originally intended, eliminating the race condition with unregistering network devices. Fixes: 27aabf27fd01 ("Bluetooth: fix use-after-free in device_for_each_child()") Assisted-by: Gemini:gemini-3.7-flash syzbot Reported-by: syzbot+6df45dd3d03e1a9aca96@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=6df45dd3d03e1a9aca96 Link: https://syzkaller.appspot.com/ai_job?id=f1c0e740-db21-40af-a9ff-84db0fd8b8bd Signed-off-by: Krystian Kaniewski Signed-off-by: Luiz Augusto von Dentz --- net/bluetooth/hci_sysfs.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index 8957ce7c21b7..c2065abf753e 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -13,7 +13,10 @@ static const struct class bt_class = { static void bt_link_release(struct device *dev) { struct hci_conn *conn = to_hci_conn(dev); + struct device *parent = dev->parent; + kfree(conn); + put_device(parent); } static const struct device_type bt_link = { @@ -21,6 +24,16 @@ static const struct device_type bt_link = { .release = bt_link_release, }; +/* + * The rfcomm tty device will possibly retain even when conn + * is down, and sysfs doesn't support move zombie device, + * so we should move the device before conn device is destroyed. + */ +static int __match_tty(struct device *dev, const void *data) +{ + return !strncmp(dev_name(dev), "rfcomm", 6); +} + void hci_conn_init_sysfs(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; @@ -29,7 +42,7 @@ void hci_conn_init_sysfs(struct hci_conn *conn) conn->dev.type = &bt_link; conn->dev.class = &bt_class; - conn->dev.parent = &hdev->dev; + conn->dev.parent = get_device(&hdev->dev); device_initialize(&conn->dev); } @@ -69,7 +82,7 @@ void hci_conn_del_sysfs(struct hci_conn *conn) while (1) { struct device *dev; - dev = device_find_any_child(&conn->dev); + dev = device_find_child(&conn->dev, NULL, __match_tty); if (!dev) break; device_move(dev, NULL, DPM_ORDER_DEV_LAST); From f5a427b16e45210dee656b0860728f3d496dee85 Mon Sep 17 00:00:00 2001 From: Xu Rao Date: Fri, 4 Sep 2026 10:54:57 +0800 Subject: [PATCH 0984/1198] Bluetooth: btqcomsmd: destroy RPMsg endpoints before freeing hci_dev The command and ACL RPMsg endpoints store struct btqcomsmd as their callback private data. The receive callbacks dereference btq->hdev without taking an hci_dev reference. The current teardown order frees the hci_dev before destroying the RPMsg endpoints in both the hci_register_dev() error path and the driver remove path. If WCNSS delivers data in that window, the endpoint callback can run with an already freed hci_dev and pass it to the Bluetooth core. For qcom_smd endpoints, rpmsg_destroy_ept() closes the channel and clears the callback under the channel recv_lock. The receive path holds the same lock while invoking the callback, so destroying the endpoints first both prevents new callbacks and serializes with any callback already running. Destroy the command and ACL endpoints before hci_free_dev(). Keep hci_unregister_dev() first during remove so the HCI core stops issuing operations before the transport endpoints are shut down. In the full registration-error cleanup path, return directly after freeing the hci_dev to avoid falling through to the partial-construction labels and destroying the endpoints twice. Fixes: 5052de8deff5 ("soc: qcom: smd: Transition client drivers from smd to rpmsg") Fixes: 9a39a927be01 ("Bluetooth: btqcomsmd: Fix a resource leak in error handling paths in the probe function") Cc: stable@vger.kernel.org Acked-by: Bartosz Golaszewski Reviewed-by: Dmitry Baryshkov Signed-off-by: Xu Rao Signed-off-by: Luiz Augusto von Dentz --- drivers/bluetooth/btqcomsmd.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/bluetooth/btqcomsmd.c b/drivers/bluetooth/btqcomsmd.c index d2e13fcb6bab..d669ea4eb3eb 100644 --- a/drivers/bluetooth/btqcomsmd.c +++ b/drivers/bluetooth/btqcomsmd.c @@ -188,7 +188,10 @@ static int btqcomsmd_probe(struct platform_device *pdev) return 0; hci_free_dev: + rpmsg_destroy_ept(btq->cmd_channel); + rpmsg_destroy_ept(btq->acl_channel); hci_free_dev(hdev); + return ret; destroy_cmd_channel: rpmsg_destroy_ept(btq->cmd_channel); destroy_acl_channel: @@ -202,10 +205,11 @@ static void btqcomsmd_remove(struct platform_device *pdev) struct btqcomsmd *btq = platform_get_drvdata(pdev); hci_unregister_dev(btq->hdev); - hci_free_dev(btq->hdev); rpmsg_destroy_ept(btq->cmd_channel); rpmsg_destroy_ept(btq->acl_channel); + + hci_free_dev(btq->hdev); } static const struct of_device_id btqcomsmd_of_match[] = { From e486a891c412d9d82ee865987f4eead6196e1f96 Mon Sep 17 00:00:00 2001 From: Jiajia Liu Date: Fri, 4 Sep 2026 16:03:50 +0800 Subject: [PATCH 0985/1198] Bluetooth: btusb: mediatek: Fix leaked runtime PM reference in reset MT7925 on HP Pro Mini 260 sometimes timed out during reloading driver and reset usb device. btusb_suspend is not called again after closing bluetooth interface. usbcore: registered new interface driver btusb Bluetooth: hci0: HW/SW Version: 0x00000000, Build Time: 20260605184935 Bluetooth: hci0: Execution of wmt command timed out Bluetooth: hci0: Failed to send wmt patch dwnld (-110) Bluetooth: hci0: Failed to set up firmware (-110) usb 3-10: reset high-speed USB device number 4 using xhci_hcd Bluetooth: hci0: HW/SW Version: 0x00000000, Build Time: 20260605184935 Bluetooth: hci0: Device setup in 1856545 usecs Bluetooth: hci0: AOSP extensions version v1.00 Bluetooth: hci0: AOSP quality report is supported Bluetooth: MGMT ver 1.23 btusb_mtk_reset calls usb_autopm_get_interface to resume the device before driving the hardware reset, but never calls the matching usb_autopm_put_interface. Every hardware reset therefore leaks a PM usage reference of the interface, preventing the device from being runtime suspended again until it is unbound. Add the BTUSB_RESET flag. It is set before usb_queue_reset_device and is cleared in btusb_disconnect, which drops the reference as well. If the flag is already set when a new reset is requested, drop one reference. Also clear BTMTK_HW_RESET_ACTIVE if usb_autopm_get_interface fails, otherwise no further reset could ever be attempted. Fixes: 25b6d7593a3a ("Bluetooth: btmtk: introduce btmtk reset work") Assisted-by: Claude:qwen3.8-max Signed-off-by: Jiajia Liu Signed-off-by: Luiz Augusto von Dentz --- drivers/bluetooth/btusb.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index ddc44ca28722..9372fb521575 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -982,6 +982,7 @@ struct btqca_data { #define BTUSB_ALT6_CONTINUOUS_TX 16 #define BTUSB_HW_SSR_ACTIVE 17 #define BTUSB_WAKEUP_BROKEN 18 +#define BTUSB_RESET 19 struct btusb_data { struct hci_dev *hdev; @@ -2931,8 +2932,11 @@ static int btusb_mtk_reset(struct hci_dev *hdev, void *rst_data) } err = usb_autopm_get_interface(data->intf); - if (err < 0) + if (err < 0) { + bt_dev_err(hdev, "Failed usb_autopm_get_interface: %d", err); + clear_bit(BTMTK_HW_RESET_ACTIVE, &btmtk_data->flags); return err; + } /* Release MediaTek ISO data interface */ btusb_mtk_release_iso_intf(hdev); @@ -2954,6 +2958,11 @@ static int btusb_mtk_reset(struct hci_dev *hdev, void *rst_data) err = btmtk_usb_subsys_reset(hdev, btmtk_data->dev_id); + if (test_and_set_bit(BTUSB_RESET, &data->flags)) { + bt_dev_err(hdev, "last usb reset failed? Resetting again"); + usb_autopm_put_interface_no_suspend(data->intf); + } + usb_queue_reset_device(data->intf); clear_bit(BTMTK_HW_RESET_ACTIVE, &btmtk_data->flags); @@ -4596,6 +4605,9 @@ static void btusb_disconnect(struct usb_interface *intf) if (data->reset_gpio) gpiod_put(data->reset_gpio); + if (test_and_clear_bit(BTUSB_RESET, &data->flags)) + usb_autopm_put_interface_no_suspend(data->intf); + if (intf == data->intf) { if (data->isoc) usb_driver_release_interface(&btusb_driver, data->isoc); From c93922dd316b7273a8667d29084632066fa8a2d3 Mon Sep 17 00:00:00 2001 From: Jiajia Liu Date: Fri, 4 Sep 2026 16:03:51 +0800 Subject: [PATCH 0986/1198] Bluetooth: btusb: Fix leaked runtime PM reference in btusb_reset btusb_reset calls usb_autopm_get_interface to resume the device before queuing a reset of it, but never calls the matching usb_autopm_put_interface. usb_queue_reset_device ends up in usb_reset_device(), and since btusb provides no pre_reset/post_reset callbacks the interface is merely unbound and rebound: the interface device object survives this cycle, and so does its PM usage count, which is not cleared when the driver is unbound. As a result every reset permanently leaks a PM usage reference, preventing the interface from being runtime suspended again until it is unbound. Set BTUSB_RESET flag before usb_queue_reset_device so that btusb_disconnect drops the reference. If the flag is already set, drop one reference. Fixes: c9209b269afd ("Bluetooth: btusb: Introduce generic USB reset") Assisted-by: Claude:qwen3.8-max Signed-off-by: Jiajia Liu Signed-off-by: Luiz Augusto von Dentz --- drivers/bluetooth/btusb.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 9372fb521575..002b9f975710 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -1057,13 +1057,15 @@ static void btusb_reset(struct hci_dev *hdev) int err; data = hci_get_drvdata(hdev); - /* This is not an unbalanced PM reference since the device will reset */ err = usb_autopm_get_interface(data->intf); if (err) { bt_dev_err(hdev, "Failed usb_autopm_get_interface: %d", err); return; } + if (test_and_set_bit(BTUSB_RESET, &data->flags)) + usb_autopm_put_interface_no_suspend(data->intf); + bt_dev_err(hdev, "Resetting usb device."); usb_queue_reset_device(data->intf); } From f4c3e38111fd84c2c7ae5785755f4a4d476e1cba Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Tue, 8 Sep 2026 19:05:39 +0200 Subject: [PATCH 0987/1198] rust: allow `unknown_lints` in generated bindings for Rust < 1.88 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Starting with bindgen 0.73.2 [1], `#[allow(unnecessary_transmutes)]` are used, even when `--rust-target 1.85` is passed. However, the lint was introduced in Rust 1.88.0. Thus building with older Rust versions warns like: error: unknown lint: `unnecessary_transmutes` --> rust/uapi/uapi_generated.rs:26294:13 | 26294 | #[allow(unnecessary_transmutes)] | ^^^^^^^^^^^^^^^^^^^^^^ | = note: `-D unknown-lints` implied by `-D warnings` = help: to override `-D warnings` add `#[allow(unknown_lints)]` Thus allow `unknown_lints` in the generated bindings -- only when building with older Rust versions. I have asked upstream if this is intentional [1], i.e. if we are supposed to always allow unknown lints in case `bindgen` uses such attributes, or whether it is an oversight. [ Emilio said it wasn't intentional -- we will work around it for now on the kernel side. - Miguel ] Cc: stable@vger.kernel.org # Needed in 6.12.y and later (Rust is pinned in older LTSs). Cc: Emilio Cobos Álvarez Link: https://github.com/rust-lang/rust-bindgen/pull/3455#issuecomment-5588526559 [1] Assisted-by: LLM Link: https://patch.msgid.link/20260908170539.345207-1-ojeda@kernel.org [ Removed the `cfg` for `allow(unnecessary_transmutes)` as suggested by Gary. - Miguel ] Signed-off-by: Miguel Ojeda --- rust/bindings/lib.rs | 3 ++- rust/uapi/lib.rs | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/rust/bindings/lib.rs b/rust/bindings/lib.rs index ad24c920b919..439ab88a5da1 100644 --- a/rust/bindings/lib.rs +++ b/rust/bindings/lib.rs @@ -27,7 +27,8 @@ #[allow(clippy::ptr_as_ptr)] #[allow(clippy::ref_as_ptr)] #[allow(clippy::undocumented_unsafe_blocks)] -#[cfg_attr(CONFIG_RUSTC_HAS_UNNECESSARY_TRANSMUTES, allow(unnecessary_transmutes))] +#[cfg_attr(not(CONFIG_RUSTC_HAS_UNNECESSARY_TRANSMUTES), allow(unknown_lints))] +#[allow(unnecessary_transmutes)] #[cfg_attr( CONFIG_RUSTC_HAS_SUSPICIOUS_RUNTIME_SYMBOL_DEFINITIONS, allow(suspicious_runtime_symbol_definitions) diff --git a/rust/uapi/lib.rs b/rust/uapi/lib.rs index 2df0340e63d1..003e6d4f7c4b 100644 --- a/rust/uapi/lib.rs +++ b/rust/uapi/lib.rs @@ -24,7 +24,8 @@ unreachable_pub, unsafe_op_in_unsafe_fn )] -#![cfg_attr(CONFIG_RUSTC_HAS_UNNECESSARY_TRANSMUTES, allow(unnecessary_transmutes))] +#![cfg_attr(not(CONFIG_RUSTC_HAS_UNNECESSARY_TRANSMUTES), allow(unknown_lints))] +#![allow(unnecessary_transmutes)] #![cfg_attr( CONFIG_RUSTC_HAS_SUSPICIOUS_RUNTIME_SYMBOL_DEFINITIONS, allow(suspicious_runtime_symbol_definitions) From f6d61fe4c19cf448e5cba6d8767b4e6966f58606 Mon Sep 17 00:00:00 2001 From: Long Li Date: Wed, 2 Sep 2026 10:51:53 -0700 Subject: [PATCH 0988/1198] net: mana: Clear RDMA teardown and suspend state in mana_rdma_probe() mana_rdma_remove() sets gd->rdma_teardown to stop mana_rdma_service_handle() from acting on servicing events, but nothing ever clears it. A hardware service reset (GDMA_EQE_HWC_RESET_REQUEST) goes through mana_gd_suspend() -> mana_rdma_remove() and mana_gd_resume() -> mana_rdma_probe(), so from the first reset onwards every GDMA_EQE_HWC_SOC_SERVICE event returns early and RDMA suspend/resume servicing is silently dropped for the life of the device. gd->is_suspended has the same problem: it is set when servicing removes the adev and is cleared only by a matching resume. A reset while RDMA is suspended re-adds the adev but leaves is_suspended set, so a later resume event calls add_adev() on top of a live gd->adev and leaks it. This is currently masked by the rdma_teardown bug. Clear both in mana_rdma_probe(). On the reset path mana_rdma_remove() has closed the gate and drained the service workqueue, so clear is_suspended first and re-open the gate with smp_store_release(), paired with smp_load_acquire() in the handler, so the handler cannot observe an open gate with a stale is_suspended. On the initial probe path the gate was never closed and both flags are already clear. This does not order gd->adev, which add_adev() publishes afterwards. A servicing event arriving in that window is still dropped, as it is in mainline today on the initial probe path; closing it needs probe and the handler to be serialized and is left to a separate change. Fixes: 505cc26bcae0 ("net: mana: Add support for auxiliary device servicing events") Signed-off-by: Long Li Link: https://patch.msgid.link/20260902175153.3410560-1-longli@microsoft.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/microsoft/mana/mana_en.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 45a7520491a6..591fb4191d90 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -3987,7 +3987,8 @@ static void mana_rdma_service_handle(struct work_struct *work) struct device *dev = gd->gdma_context->dev; int ret; - if (READ_ONCE(gd->rdma_teardown)) + /* Pairs with the smp_store_release() in mana_rdma_probe(). */ + if (smp_load_acquire(&gd->rdma_teardown)) goto out; switch (serv_work->event) { @@ -4283,6 +4284,21 @@ int mana_rdma_probe(struct gdma_dev *gd) if (err) return err; + /* Clear the state left by a previous mana_rdma_remove() so servicing + * events are handled again after a reset cycle. + */ + gd->is_suspended = false; + + /* Publish is_suspended before re-opening the gate, so the handler + * cannot observe an open gate with a stale is_suspended. Pairs + * with the smp_load_acquire() in mana_rdma_service_handle(). This + * matters on the reset path, where mana_rdma_remove() closed the + * gate and drained the workqueue; on the initial probe path the + * gate was never closed and both flags are already clear. It does + * not order gd->adev, which add_adev() publishes below. + */ + smp_store_release(&gd->rdma_teardown, false); + err = add_adev(gd, "rdma"); if (err) mana_gd_deregister_device(gd); From 8dc5d98a16fa23c00999aecf10018c9f69fa5bf4 Mon Sep 17 00:00:00 2001 From: Vlatko Kosturjak Date: Thu, 3 Sep 2026 08:21:29 +0200 Subject: [PATCH 0989/1198] ppp_async: drop the errored frame instead of resetting its headroom ppp_receive_nonmp_frame() prepends a two-byte direction tag before running the pass/active BPF filters: *(__be16 *)skb_push(skb, 2) = htons(PPP_FILTER_INBOUND_TAG); Nothing on the receive path guarantees those two bytes of headroom. The frame-error path in ppp_async's process_input_packet() resets a reused skb's headroom to zero while claiming to restore it to a freshly allocated state - but a fresh skb from dev_alloc_skb() carries NET_SKB_PAD: err: if (skb) { /* make skb appear as freshly allocated */ skb_trim(skb, 0); skb_reserve(skb, - skb_headroom(skb)); } ap->rpkt still points at that skb, so the next frame is reassembled into it with no headroom at all. A peer that sends a bad-FCS frame followed by one beginning ff 03 then leaves a single byte of headroom by the time the filter tag is pushed, which lands one byte below skb->head: skbuff: skb_under_panic: len:49 put:2 head:ffff888003c10000 data:ffff888003c0ffff tail:0x30 end:0x640 dev: kernel BUG at net/core/skbuff.c:214! RIP: 0010:skb_panic+0x13e/0x230 Call Trace: skb_push+0xbd/0x100 ppp_receive_nonmp_frame+0x48a/0x1d10 ppp_input+0x4e9/0x2f80 ppp_async_process+0x2a/0xe0 tasklet_action_common+0x20f/0x8a0 handle_softirqs+0x18e/0x590 Kernel panic - not syncing: Fatal exception in interrupt Zeroing the headroom violates the NET_SKB_PAD guarantee that dev_alloc_skb() gives the rest of the receive path. Besides the filter panic above, when CCP compression is enabled ppp_decompress_frame() hands skb->data - 2 to ->decompress()/->incomp(), which then reads out of bounds before skb->head for the same reason. Rather than restore the headroom, drop the errored frame - as ppp_synctty already does on its error path - and clear ap->rpkt so the next frame is reassembled into a fresh skb with proper headroom. This is simpler and fixes both the filter under-panic and the CCP out-of-bounds read. The original V1 of this patch made room in ppp_receive_nonmp_frame() with skb_cow_head(); Eric pointed out that fixing the root cause in the transport is the right approach. Found by fuzzing the PPP receive path with a mutating peer on a pty; it is an interesting (remote) DoS: root configures PPP, the peer supplies two crashing frames. The reproducer (repro-ppp-skb.c, unchanged from v1) panics in about a second, and returns cleanly with this applied. Fixes: 6722e78c9005 ("[PPP]: handle misaligned accesses") Suggested-by: Eric Dumazet Signed-off-by: Vlatko Kosturjak Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/apkR6ZU+tqP2C3Fl@griffin.linux.hr Signed-off-by: Jakub Kicinski --- drivers/net/ppp/ppp_async.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c index ea7fe9608ffd..6e6e2b944128 100644 --- a/drivers/net/ppp/ppp_async.c +++ b/drivers/net/ppp/ppp_async.c @@ -742,11 +742,8 @@ process_input_packet(struct asyncppp *ap) err: /* frame had an error, remember that, reset SC_TOSS & SC_ESCAPE */ ap->state = SC_PREV_ERROR; - if (skb) { - /* make skb appear as freshly allocated */ - skb_trim(skb, 0); - skb_reserve(skb, - skb_headroom(skb)); - } + kfree_skb(skb); + ap->rpkt = NULL; } /* Called when the tty driver has data for us. Runs parallel with the From e24279bffec6c9aa3fef7e3c64bd4000aca9d698 Mon Sep 17 00:00:00 2001 From: Karl Mehltretter Date: Sat, 5 Sep 2026 12:06:08 +0200 Subject: [PATCH 0990/1198] MAINTAINERS: Update the so_txtime selftest path in SOCKET TIMESTAMPING Commit 5c6baef3885c ("selftests: drv-net: convert so_txtime to drv-net") moved the test to tools/testing/selftests/drivers/net/, but the SOCKET TIMESTAMPING entry still lists the old path and scripts/get_maintainer.pl --self-test=patterns reports it as matching nothing. Point the pattern at the new location. Signed-off-by: Karl Mehltretter Reviewed-by: Jason Xing Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20260905100608.42539-1-kmehltretter@gmail.com Signed-off-by: Jakub Kicinski --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index fc320b373656..6f2c8cb67c7d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -25335,8 +25335,8 @@ F: Documentation/networking/timestamping.rst F: include/linux/net_tstamp.h F: include/uapi/linux/net_tstamp.h F: tools/testing/selftests/bpf/*/net_timestamping* +F: tools/testing/selftests/drivers/net/so_txtime.* F: tools/testing/selftests/net/*timestamp* -F: tools/testing/selftests/net/so_txtime.c SOEKRIS NET48XX LED SUPPORT M: Chris Boot From cdca92eddc025fdb90071be97738f7d55a65f8dd Mon Sep 17 00:00:00 2001 From: Naman Gulati Date: Fri, 4 Sep 2026 18:06:44 +0000 Subject: [PATCH 0991/1198] ipv6: null-check fib6_node before accessing in __ip6_del_rt_siblings() syzbot reported a null-ptr-deref in __ip6_del_rt_siblings() [0]. The stack trace hinted towards a null dereference of rt->fib6_node when fn->leaf is accessed in __ip6_del_rt_siblings(). With RTNL_FLAG_DOIT_UNLOCKED set, inet6_rtm_delroute() operations run concurrently without acquiring the RTNL lock. In ip6_route_del(), the route lookup happens under rcu_read_lock() without acquiring table->tb6_lock. Between ip6_route_del() looking up the route and __ip6_del_rt_siblings() acquiring table->tb6_lock, another thread can modify the routing table. For example, when an ECMP route is replaced via RTM_NEWROUTE with NLM_F_REPLACE, fib6_add_rt2node() unlinks all old siblings and sets iter->fib6_node = NULL. A reproducer was found that triggers this [1]. Add a check to ensure rt->fib6_node is non-null before accessing it. [0] KASAN: null-ptr-deref in range [0x0000000000000020-0x0000000000000027] RIP: 0010:__ip6_del_rt_siblings+0x31e/0x7c0 net/ipv6/route.c:4056 Call Trace: ip6_route_del+0x1054/0x1110 net/ipv6/route.c:4232 inet6_rtm_delroute+0x5d7/0x6d0 net/ipv6/route.c:5669 rtnetlink_rcv_msg+0x802/0xc00 net/core/rtnetlink.c:7132 netlink_rcv_skb+0x226/0x4a0 net/netlink/af_netlink.c:2556 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] netlink_unicast+0x7f5/0x990 net/netlink/af_netlink.c:1345 netlink_sendmsg+0x813/0xb40 net/netlink/af_netlink.c:1900 sock_sendmsg_nosec+0x13a/0x180 net/socket.c:800 __sock_sendmsg net/socket.c:815 [inline] ____sys_sendmsg+0x565/0x870 net/socket.c:2713 ___sys_sendmsg+0x2a5/0x360 net/socket.c:2767 __sys_sendmsg net/socket.c:2799 [inline] __do_sys_sendmsg net/socket.c:2804 [inline] __se_sys_sendmsg net/socket.c:2802 [inline] __x64_sys_sendmsg+0x1b7/0x290 net/socket.c:2802 do_syscall_x64 arch/x86/entry/syscall_64.c:61 [inline] do_syscall_64+0x166/0x520 arch/x86/entry/syscall_64.c:84 entry_SYSCALL_64_after_hwframe+0x77/0x7f [1] https://gist.github.com/NamanGulati/0766a1159b6ca61928faaf87425ff899 Fixes: bd11ff421d36 ("ipv6: Get rid of RTNL for SIOCDELRT and RTM_DELROUTE.") Reported-by: syzbot+a73e5ee0fd534fed75bd@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/6a9b03f9.04649fcc.10325f.0003.GAE@google.com Signed-off-by: Naman Gulati Reviewed-by: Kuniyuki Iwashima Reviewed-by: Ido Schimmel Reviewed-by: Fernando Fernandez Mancera Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20260904180645.706425-1-namangulati@google.com Signed-off-by: Jakub Kicinski --- net/ipv6/route.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 9658939511e0..08bd68f1b5bb 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -4019,6 +4019,7 @@ static int __ip6_del_rt_siblings(struct fib6_info *rt, struct fib6_config *cfg) struct net *net = info->nl_net; struct sk_buff *skb = NULL; struct fib6_table *table; + struct fib6_node *fn; int err = -ENOENT; if (rt == net->ipv6.fib6_null_entry) @@ -4026,9 +4027,13 @@ static int __ip6_del_rt_siblings(struct fib6_info *rt, struct fib6_config *cfg) table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); + fn = rcu_dereference_protected(rt->fib6_node, + lockdep_is_held(&table->tb6_lock)); + if (!fn) + goto out_unlock; + if (rt->fib6_nsiblings && cfg->fc_delete_all_nh) { struct fib6_info *sibling, *next_sibling; - struct fib6_node *fn; /* prefer to send a single notification with all hops */ skb = nlmsg_new(rt6_nlmsg_size(rt), GFP_ATOMIC); @@ -4051,8 +4056,6 @@ static int __ip6_del_rt_siblings(struct fib6_info *rt, struct fib6_config *cfg) * and emit a replace or delete notification, respectively. */ info->skip_notify_kernel = 1; - fn = rcu_dereference_protected(rt->fib6_node, - lockdep_is_held(&table->tb6_lock)); if (rcu_access_pointer(fn->leaf) == rt) { struct fib6_info *last_sibling, *replace_rt; From ba4ba11ed6eb8972c69070417fc27b48deb002e8 Mon Sep 17 00:00:00 2001 From: Norbert Szetei Date: Sun, 6 Sep 2026 10:21:09 +0200 Subject: [PATCH 0992/1198] net: openvswitch: fix use-after-free of the flow table mask array tbl_mask_array_realloc() retires the old mask_array before it stops being reachable: old = ovsl_dereference(tbl->mask_array); if (old) { ... call_rcu(&old->rcu, mask_array_rcu_cb); } rcu_assign_pointer(tbl->mask_array, new); call_rcu() only waits for read-side critical sections already in flight. tbl->mask_array still points at old between the call_rcu() and the rcu_assign_pointer(), so a reader entering ovs_flow_tbl_lookup_stats() in that window picks up old in a fresh critical section that the pending grace period does not cover. tbl_mask_array_realloc() runs in process context under ovs_mutex, so the window is preemptible and can outlast the grace period. Then mask_array_rcu_cb() frees old before the swap runs: BUG: KASAN: slab-use-after-free in flow_lookup.constprop.0+0x2bf/0x2f0 Read of size 8 at addr ffff888020b3e018 by task poc/741 flow_lookup.constprop.0+0x2bf/0x2f0 ovs_flow_tbl_lookup_stats+0x4a3/0x5c0 ovs_dp_process_packet+0x19c/0x710 ovs_vport_receive+0x243/0x390 internal_dev_xmit+0x81/0x170 Freed by task 728: kfree+0x16a/0x4e0 rcu_core+0x853/0x1030 Publish the new array before retiring the old one. The kfree_rcu() that call_rcu() replaced ran after the swap. Fixes: eac87c413bf9 ("net: openvswitch: reorder masks array based on usage") Cc: stable@vger.kernel.org Signed-off-by: Norbert Szetei Reviewed-by: Ilya Maximets Acked-by: Eelco Chaudron echaudro@redhat.com Link: https://patch.msgid.link/DE115F9C-2545-423E-A702-986FC952FD62@doyensec.com Signed-off-by: Jakub Kicinski --- net/openvswitch/flow_table.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index 67d5b8c0fe79..1e0f9d193eb0 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -257,11 +257,13 @@ static int tbl_mask_array_realloc(struct flow_table *tbl, int size) if (ovsl_dereference(old->masks[i])) new->masks[new->count++] = old->masks[i]; } - call_rcu(&old->rcu, mask_array_rcu_cb); } rcu_assign_pointer(tbl->mask_array, new); + if (old) + call_rcu(&old->rcu, mask_array_rcu_cb); + return 0; } From 7a49e6b16f36b8e085521699adbca3e321b6dd0c Mon Sep 17 00:00:00 2001 From: Zhiling Zou Date: Thu, 3 Sep 2026 14:56:14 +0800 Subject: [PATCH 0993/1198] net: bridge: use option bits for CFM/MRP frame handlers CFM and MRP register a global br_frame_type whose hlist_node is linked into the per-bridge frame_type_list when the first MEP/MRP instance is created. Enabling the protocol on multiple bridges therefore inserts the same node into multiple lists. Unregistering it on one bridge then corrupts list state belonging to another. These handlers can only be installed once per bridge, and they are uncommon. Track their per-bridge enable state with net_bridge option bits, which already live on the Rx hot cache line, and dispatch the matching handler directly from the receive path. Check both bits together first as an unlikely case. Remove the generic frame_type_list and br_frame_type helpers, which have had no other users since CFM and MRP were added. That shrinks struct net_bridge by 8 bytes and drops the list walk from the fast path. When neither protocol is compiled in, BR_CFM_MRP_OPTS is 0 and the compiler prunes the branch. Fixes: 90c628dd47ff ("net: bridge: extend the process of special frames") Fixes: dc32cbb3dbd7 ("bridge: cfm: Kernel space implementation of CFM. CCM frame RX added.") Cc: stable@vger.kernel.org Reported-by: Vega Suggested-by: Nikolay Aleksandrov Co-developed-by: Yilin Zhu Signed-off-by: Yilin Zhu Signed-off-by: Zhiling Zou Acked-by: Nikolay Aleksandrov Link: https://patch.msgid.link/0345b9d5aa60ba416f6738ff1b87140f0a749cb8.1788417901.git.zhilinz@nebusec.ai Signed-off-by: Jakub Kicinski --- net/bridge/br_cfm.c | 11 +++-------- net/bridge/br_device.c | 1 - net/bridge/br_input.c | 35 ++++++++++++++--------------------- net/bridge/br_mrp.c | 13 +++---------- net/bridge/br_private.h | 26 +++++++++++++++----------- 5 files changed, 35 insertions(+), 51 deletions(-) diff --git a/net/bridge/br_cfm.c b/net/bridge/br_cfm.c index dea56fffa1c1..9dcc97d63a6f 100644 --- a/net/bridge/br_cfm.c +++ b/net/bridge/br_cfm.c @@ -367,7 +367,7 @@ static u32 ccm_tlv_extract(struct sk_buff *skb, u32 index, } /* note: already called with rcu_read_lock */ -static int br_cfm_frame_rx(struct net_bridge_port *port, struct sk_buff *skb) +int br_cfm_frame_rx(struct net_bridge_port *port, struct sk_buff *skb) { u32 mdlevel, interval, size, index, max; const struct br_cfm_common_hdr *hdr; @@ -489,11 +489,6 @@ static int br_cfm_frame_rx(struct net_bridge_port *port, struct sk_buff *skb) return 1; } -static struct br_frame_type cfm_frame_type __read_mostly = { - .type = cpu_to_be16(ETH_P_CFM), - .frame_handler = br_cfm_frame_rx, -}; - int br_cfm_mep_create(struct net_bridge *br, const u32 instance, struct br_cfm_mep_create *const create, @@ -559,7 +554,7 @@ int br_cfm_mep_create(struct net_bridge *br, INIT_DELAYED_WORK(&mep->ccm_tx_dwork, ccm_tx_work_expired); if (hlist_empty(&br->mep_list)) - br_add_frame(br, &cfm_frame_type); + br_opt_toggle(br, BROPT_CFM_ENABLED, true); hlist_add_tail_rcu(&mep->head, &br->mep_list); @@ -588,7 +583,7 @@ static void mep_delete_implementation(struct net_bridge *br, kfree_rcu(mep, rcu); if (hlist_empty(&br->mep_list)) - br_del_frame(br, &cfm_frame_type); + br_opt_toggle(br, BROPT_CFM_ENABLED, false); } int br_cfm_mep_delete(struct net_bridge *br, diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index ff55dab73632..e01c44a90d84 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -503,7 +503,6 @@ void br_dev_setup(struct net_device *dev) spin_lock_init(&br->lock); INIT_LIST_HEAD(&br->port_list); INIT_HLIST_HEAD(&br->fdb_list); - INIT_HLIST_HEAD(&br->frame_type_list); #if IS_ENABLED(CONFIG_BRIDGE_MRP) INIT_HLIST_HEAD(&br->mrp_list); #endif diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index d87a5f9fa92b..8bed72baf161 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -317,17 +317,25 @@ static int nf_hook_bridge_pre(struct sk_buff *skb, struct sk_buff **pskb) return RX_HANDLER_CONSUMED; } +#define BR_CFM_MRP_OPTS \ + ((IS_ENABLED(CONFIG_BRIDGE_CFM) ? BIT(BROPT_CFM_ENABLED) : 0UL) | \ + (IS_ENABLED(CONFIG_BRIDGE_MRP) ? BIT(BROPT_MRP_ENABLED) : 0UL)) + /* Return 0 if the frame was not processed otherwise 1 * note: already called with rcu_read_lock */ static int br_process_frame_type(struct net_bridge_port *p, struct sk_buff *skb) { - struct br_frame_type *tmp; + struct net_bridge *br = p->br; - hlist_for_each_entry_rcu(tmp, &p->br->frame_type_list, list) - if (unlikely(tmp->type == skb->protocol)) - return tmp->frame_handler(p, skb); + if (skb->protocol == htons(ETH_P_CFM) && + br_opt_get(br, BROPT_CFM_ENABLED)) + return br_cfm_frame_rx(p, skb); + + if (skb->protocol == htons(ETH_P_MRP) && + br_opt_get(br, BROPT_MRP_ENABLED)) + return br_mrp_process(p, skb); return 0; } @@ -425,7 +433,8 @@ static rx_handler_result_t br_handle_frame(struct sk_buff **pskb) } } - if (unlikely(br_process_frame_type(p, skb))) + if (unlikely((READ_ONCE(p->br->options) & BR_CFM_MRP_OPTS) && + br_process_frame_type(p, skb))) return RX_HANDLER_PASS; forward: @@ -467,19 +476,3 @@ rx_handler_func_t *br_get_rx_handler(const struct net_device *dev) return br_handle_frame; } - -void br_add_frame(struct net_bridge *br, struct br_frame_type *ft) -{ - hlist_add_head_rcu(&ft->list, &br->frame_type_list); -} - -void br_del_frame(struct net_bridge *br, struct br_frame_type *ft) -{ - struct br_frame_type *tmp; - - hlist_for_each_entry(tmp, &br->frame_type_list, list) - if (ft == tmp) { - hlist_del_rcu(&ft->list); - return; - } -} diff --git a/net/bridge/br_mrp.c b/net/bridge/br_mrp.c index ef16d0703924..dce6efa96c4c 100644 --- a/net/bridge/br_mrp.c +++ b/net/bridge/br_mrp.c @@ -6,13 +6,6 @@ static const u8 mrp_test_dmac[ETH_ALEN] = { 0x1, 0x15, 0x4e, 0x0, 0x0, 0x1 }; static const u8 mrp_in_test_dmac[ETH_ALEN] = { 0x1, 0x15, 0x4e, 0x0, 0x0, 0x3 }; -static int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb); - -static struct br_frame_type mrp_frame_type __read_mostly = { - .type = cpu_to_be16(ETH_P_MRP), - .frame_handler = br_mrp_process, -}; - static bool br_mrp_is_ring_port(struct net_bridge_port *p_port, struct net_bridge_port *s_port, struct net_bridge_port *port) @@ -486,7 +479,7 @@ static void br_mrp_del_impl(struct net_bridge *br, struct br_mrp *mrp) kfree_rcu(mrp, rcu); if (hlist_empty(&br->mrp_list)) - br_del_frame(br, &mrp_frame_type); + br_opt_toggle(br, BROPT_MRP_ENABLED, false); } /* Adds a new MRP instance. @@ -536,7 +529,7 @@ int br_mrp_add(struct net_bridge *br, struct br_mrp_instance *instance) rcu_assign_pointer(mrp->s_port, p); if (hlist_empty(&br->mrp_list)) - br_add_frame(br, &mrp_frame_type); + br_opt_toggle(br, BROPT_MRP_ENABLED, true); INIT_DELAYED_WORK(&mrp->test_work, br_mrp_test_work_expired); INIT_DELAYED_WORK(&mrp->in_test_work, br_mrp_in_test_work_expired); @@ -1241,7 +1234,7 @@ static int br_mrp_rcv(struct net_bridge_port *p, * normal forwarding. * note: already called with rcu_read_lock */ -static int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb) +int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb) { /* If there is no MRP instance do normal forwarding */ if (likely(!test_bit(BR_MRP_AWARE_BIT, &p->flags))) diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index d337b1cfb980..b01997ea9508 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -495,12 +495,13 @@ enum net_bridge_opts { BROPT_MST_ENABLED, BROPT_MDB_OFFLOAD_FAIL_NOTIFICATION, BROPT_FDB_LOCAL_VLAN_0, + BROPT_CFM_ENABLED, + BROPT_MRP_ENABLED, }; struct net_bridge { spinlock_t lock; spinlock_t hash_lock; - struct hlist_head frame_type_list; struct net_device *dev; unsigned long options; /* These fields are accessed on each packet */ @@ -932,16 +933,6 @@ int nbp_backup_change(struct net_bridge_port *p, struct net_device *backup_dev); int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb); rx_handler_func_t *br_get_rx_handler(const struct net_device *dev); -struct br_frame_type { - __be16 type; - int (*frame_handler)(struct net_bridge_port *port, - struct sk_buff *skb); - struct hlist_node list; -}; - -void br_add_frame(struct net_bridge *br, struct br_frame_type *ft); -void br_del_frame(struct net_bridge *br, struct br_frame_type *ft); - static inline bool br_rx_handler_check_rcu(const struct net_device *dev) { return rcu_dereference(dev->rx_handler) == br_get_rx_handler(dev); @@ -2080,6 +2071,7 @@ int br_mrp_parse(struct net_bridge *br, struct net_bridge_port *p, bool br_mrp_enabled(struct net_bridge *br); void br_mrp_port_del(struct net_bridge *br, struct net_bridge_port *p); int br_mrp_fill_info(struct sk_buff *skb, struct net_bridge *br); +int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb); #else static inline int br_mrp_parse(struct net_bridge *br, struct net_bridge_port *p, struct nlattr *attr, int cmd, @@ -2103,6 +2095,11 @@ static inline int br_mrp_fill_info(struct sk_buff *skb, struct net_bridge *br) return 0; } +static inline int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb) +{ + return 0; +} + #endif /* br_cfm.c */ @@ -2111,6 +2108,7 @@ int br_cfm_parse(struct net_bridge *br, struct net_bridge_port *p, struct nlattr *attr, int cmd, struct netlink_ext_ack *extack); bool br_cfm_created(struct net_bridge *br); void br_cfm_port_del(struct net_bridge *br, struct net_bridge_port *p); +int br_cfm_frame_rx(struct net_bridge_port *port, struct sk_buff *skb); int br_cfm_config_fill_info(struct sk_buff *skb, struct net_bridge *br); int br_cfm_status_fill_info(struct sk_buff *skb, struct net_bridge *br, @@ -2135,6 +2133,12 @@ static inline void br_cfm_port_del(struct net_bridge *br, { } +static inline int br_cfm_frame_rx(struct net_bridge_port *port, + struct sk_buff *skb) +{ + return 0; +} + static inline int br_cfm_config_fill_info(struct sk_buff *skb, struct net_bridge *br) { return -EOPNOTSUPP; From 7d059f390750152b9bd69df934198651b94fc26d Mon Sep 17 00:00:00 2001 From: Nicolai Buchwitz Date: Mon, 7 Sep 2026 23:08:55 +0200 Subject: [PATCH 0994/1198] net: macb: destroy the phylink instance on the probe error path macb_mii_init() creates a phylink instance on both of its success paths, but the probe unwind frees the netdev without destroying it, so a failing macb_alloc_tieoff() or register_netdev() leaks the instance. Destroy it at err_out_unregister_mdio, which is only reachable once macb_mii_init() has succeeded, so bp->phylink is valid there. Fixes: 7897b071ac3b ("net: macb: convert to phylink") Signed-off-by: Nicolai Buchwitz Link: https://patch.msgid.link/20260907210856.1673589-2-nb@tipi-net.de Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/cadence/macb_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 0e75339fa206..50ecfa80c660 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -5980,6 +5980,7 @@ static int macb_probe(struct platform_device *pdev) mdiobus_unregister(bp->mii_bus); mdiobus_free(bp->mii_bus); } + phylink_destroy(bp->phylink); err_out_phy_exit: phy_exit(bp->phy); From 382a373d9ea7a6ac4de9c022385b6217f65ae3cc Mon Sep 17 00:00:00 2001 From: Nicolai Buchwitz Date: Mon, 7 Sep 2026 23:08:56 +0200 Subject: [PATCH 0995/1198] net: macb: put the "mdio" child node reference on success macb_mii_init() holds the reference returned by of_get_child_by_name() for macb_mdiobus_register() and drops it only on the error paths, so every successful probe leaks a node reference. On a CM5, overlay removal after four bind cycles reports OF: ERROR: memory leak, expected refcount 1 instead of 5 Drop the reference after registration, where __mdiobus_register() has already taken its own for the lifetime of the bus. Fixes: 8a6631f1cece ("net: macb: avoid redundant lookup for "mdio" child node in MDIO setup") Signed-off-by: Nicolai Buchwitz Link: https://patch.msgid.link/20260907210856.1673589-3-nb@tipi-net.de Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/cadence/macb_main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 50ecfa80c660..77dec2d6e3fb 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1164,6 +1164,8 @@ static int macb_mii_init(struct macb *bp) if (err) goto err_out_unregister_bus; + of_node_put(mdio_np); + return 0; err_out_unregister_bus: From 796aa0547557e63338657ed1c487906f9fac4c73 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 8 Sep 2026 17:53:20 -0600 Subject: [PATCH 0996/1198] io_uring/rw: end write accounting from ->ki_complete Commit b000145e9907 moved both the fsnotify calls and the write accounting out of the kiocb completion handler and into the io_req_rw_complete() task_work. However, only the fsnotify part actually needed to move as it may sleep. Ending the write accounting is just a percpu_up_read() on the superblock writers sem. Deferring it is a problem, because it makes dropping SB_FREEZE_WRITE protection depend on the ring owner getting to running task_work. But the task may be blocked in freeze_super(), causing it to never get to that: task io-wq worker -------------------------------------------------------------- io_write() io_kiocb_start_write() (takes sb_writers, hidden from lockdep by __sb_writers_release) write_iter() -> -EIOCBQUEUED ioctl(FS_IOC_SHUTDOWN) bdev_freeze() freeze_super() percpu_down_write() <- waits for the reader above io_write() kiocb_start_write() percpu_down_read() <- queued behind the writer io_complete_rw() queues io_req_rw_complete() <- never runs, task is in D state End the write from io_complete_rw() instead, and leave only the fsnotify calls in task_work. Reported-by: syzbot+2eb3d983669d3e49d4fa@syzkaller.appspotmail.com Cc: stable@vger.kernel.org Fixes: b000145e9907 ("io_uring/rw: defer fsnotify calls to task context") Signed-off-by: Jens Axboe --- io_uring/rw.c | 29 +++++++++++++++++++---------- 1 file changed, 19 insertions(+), 10 deletions(-) diff --git a/io_uring/rw.c b/io_uring/rw.c index 95106dd1d7eb..3e22f294bdf2 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -517,20 +517,25 @@ static void io_req_end_write(struct io_kiocb *req) } } -/* - * Trigger the notifications after having done some IO, and finish the write - * accounting, if any. - */ +/* Trigger the notifications after having done some IO. */ +static void io_req_io_notify(struct io_kiocb *req) +{ + struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw); + + if (rw->kiocb.ki_flags & IOCB_WRITE) + fsnotify_modify(req->file); + else + fsnotify_access(req->file); +} + +/* Finish write accounting and notify, for inline completions only. */ static void io_req_io_end(struct io_kiocb *req) { struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw); - if (rw->kiocb.ki_flags & IOCB_WRITE) { + if (rw->kiocb.ki_flags & IOCB_WRITE) io_req_end_write(req); - fsnotify_modify(req->file); - } else { - fsnotify_access(req->file); - } + io_req_io_notify(req); } static void __io_complete_rw_common(struct io_kiocb *req, long res) @@ -563,7 +568,7 @@ void io_req_rw_complete(struct io_tw_req tw_req, io_tw_token_t tw) { struct io_kiocb *req = tw_req.req; - io_req_io_end(req); + io_req_io_notify(req); if (req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)) req->cqe.flags |= io_put_kbuf(req, max(req->cqe.res, 0), NULL); @@ -577,6 +582,10 @@ static void io_complete_rw(struct kiocb *kiocb, long res) struct io_rw *rw = container_of(kiocb, struct io_rw, kiocb); struct io_kiocb *req = cmd_to_io_kiocb(rw); + /* ring owner may block in freeze_super() before task_work runs */ + if (kiocb->ki_flags & IOCB_WRITE) + io_req_end_write(req); + __io_complete_rw_common(req, res); io_req_set_res(req, io_fixup_rw_res(req, res), 0); req->io_task_work.func = io_req_rw_complete; From dcbd1c054848848a1937ca0768ce2bdbc31ae621 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Wed, 2 Sep 2026 20:00:40 -0300 Subject: [PATCH 0997/1198] io_uring/net: let io_recv_buf_select return the length of the buffer region In preparation to using this field as an upper limit to truncation, return the size of the allocated region. Fixes: ae98dbf43d75 ("io_uring/kbuf: add support for incremental buffer consumption") Cc: stable@vger.kernel.org Signed-off-by: Gabriel Krisman Bertazi Link: https://patch.msgid.link/20260902230041.1320658-2-krisman@suse.de Signed-off-by: Jens Axboe --- io_uring/net.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/io_uring/net.c b/io_uring/net.c index fbe719d86c46..647156c9331a 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -1108,6 +1108,7 @@ static int io_recv_buf_select(struct io_kiocb *req, struct io_async_msghdr *kmsg struct io_br_sel *sel, unsigned int issue_flags) { struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); + size_t len; int ret; /* @@ -1153,13 +1154,14 @@ static int io_recv_buf_select(struct io_kiocb *req, struct io_async_msghdr *kmsg /* special case 1 vec, can be a fast path */ if (ret == 1) { sr->buf = arg.iovs[0].iov_base; - sr->len = arg.iovs[0].iov_len; + len = sr->len = arg.iovs[0].iov_len; goto map_ubuf; } iov_iter_init(&kmsg->msg.msg_iter, ITER_DEST, arg.iovs, ret, - arg.out_len); + arg.out_len); + len = arg.out_len; } else { - size_t len = sel->val; + len = sel->val; *sel = io_buffer_select(req, &len, sr->buf_group, issue_flags); if (!sel->addr) @@ -1173,7 +1175,7 @@ static int io_recv_buf_select(struct io_kiocb *req, struct io_async_msghdr *kmsg return ret; } - return 0; + return len; } int io_recv(struct io_kiocb *req, unsigned int issue_flags) From 1f6de65e3314519ce462bfd3a1d29e918f97e4e5 Mon Sep 17 00:00:00 2001 From: Peter Griffin Date: Tue, 8 Sep 2026 12:37:27 +0000 Subject: [PATCH 0998/1198] opp: fix use after free in _update_opp_table_clk() dev_pm_opp_put_opp_table() frees the opp_table which is subsquently used by dev_err_probe(). This causes an Oops during boot on gs101-oriole. cpu cpu0: error 000000006b6b6b6b: Couldn't find clock Unable to handle kernel paging request at virtual address 006b6b6b6b6b6cd3 ... Hardware name: Oriole (DT) pstate: 00400005 (nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : _of_add_table_indexed+0x80/0xbb0 lr : _of_add_table_indexed+0x6c/0xbb0 ... Call trace: _of_add_table_indexed+0x80/0xbb0 (P) dev_pm_opp_of_cpumask_add_table+0x70/0x120 dt_cpufreq_probe+0x23c/0x480 platform_probe+0x64/0xb8 Fixes: 84f05af0975c9 ("opp: Use clk_get_optional() to avoid leaving opp_table->clk as an error pointer") Signed-off-by: Peter Griffin Reviewed-by: Tudor Ambarus [ Viresh: use return value of dev_err_probe() ] Signed-off-by: Viresh Kumar --- drivers/opp/core.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/opp/core.c b/drivers/opp/core.c index 1e3b80a1f88e..1da7d86241ae 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -1581,6 +1581,8 @@ static struct opp_table *_update_opp_table_clk(struct device *dev, struct opp_table *opp_table, bool getclk) { + int ret; + /* * Return early if we don't need to get clk or we have already done it * earlier. @@ -1607,9 +1609,9 @@ static struct opp_table *_update_opp_table_clk(struct device *dev, opp_table->clk = clk_get_optional(dev, NULL); if (IS_ERR(opp_table->clk)) { + ret = dev_err_probe(dev, PTR_ERR(opp_table->clk), "Couldn't find clock\n"); dev_pm_opp_put_opp_table(opp_table); - dev_err_probe(dev, PTR_ERR(opp_table->clk), "Couldn't find clock\n"); - return ERR_CAST(opp_table->clk); + return ERR_PTR(ret); } if (opp_table->clk) From e780259b54e618ceb4763fbc21314acf3565e813 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Mon, 7 Sep 2026 23:26:32 +0200 Subject: [PATCH 0999/1198] exec: do_close_on_exec() before taking exec_update_lock do_close_on_exec() currently happens while holding the exec_update_lock, which is used in a lot of places that access process state to synchronize access checks. I recently added another such use of exec_update_lock, causing a regression. do_close_on_exec() can block waiting for a reply from a filesystem. That means a hung filesystem can block codepaths that use exec_update_lock; and it also means that a FUSE filesystem which attempts to inspect the calling process can deadlock. To avoid such problems, move do_close_on_exec() before the exec_update_lock is taken, but after the FD table has been copied if necessary. I have looked through all the calls between the old and new position of the do_close_on_exec() call; there seems to be no file descriptor table access in between. Reported-by: Benjamin Peterson Closes: https://lore.kernel.org/r/f5e8166a-88be-46c5-8939-1e5227ffe4c2@app.fastmail.com Fixes: 6650527444da ("proc: protect ptrace_may_access() with exec_update_lock (part 1)") Cc: stable@vger.kernel.org Signed-off-by: Jann Horn Link: https://patch.msgid.link/20260907-cloexec-before-exec-update-lock-v1-1-8018c201a7df@google.com Tested-by: Benjamin Peterson Reviewed-by: Jan Kara Signed-off-by: Christian Brauner (Amutable) --- fs/exec.c | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) diff --git a/fs/exec.c b/fs/exec.c index 263b1f67f1f8..f419a512de63 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1161,6 +1161,20 @@ int begin_new_exec(struct linux_binprm * bprm) if (retval) goto out; + /* + * We have to apply CLOEXEC before we change whether the process is + * dumpable (in setup_new_exec) to avoid a race with a process in userspace + * trying to access the should-be-closed file descriptors of a process + * undergoing exec(2). + * + * This can block on filesystem ->flush() handlers, including waiting + * for FUSE daemons, so do it before exec_mmap takes the + * exec_update_lock. + * This must happen after the point of no return, and after unsharing + * the FD table. + */ + do_close_on_exec(me->files); + /* * Must be called _before_ exec_mmap() as bprm->mm is * not visible until then. Doing it here also ensures @@ -1211,14 +1225,6 @@ int begin_new_exec(struct linux_binprm * bprm) clear_syscall_work_syscall_user_dispatch(me); - /* - * We have to apply CLOEXEC before we change whether the process is - * dumpable (in setup_new_exec) to avoid a race with a process in userspace - * trying to access the should-be-closed file descriptors of a process - * undergoing exec(2). - */ - do_close_on_exec(me->files); - if (bprm->secureexec) { /* Make sure parent cannot signal privileged process. */ me->pdeath_signal = 0; From 56ea4e86832d8abe8930394473566c194d189f85 Mon Sep 17 00:00:00 2001 From: Norbert Szetei Date: Mon, 7 Sep 2026 16:22:17 +0200 Subject: [PATCH 1000/1198] nstree: check listing permission before taking a namespace reference legitimize_ns() takes a reference on the candidate namespace before may_list_ns() has decided whether the caller may see it. The __free(ns_put) cleanup on the denied path can drop the last reference to a mount namespace while we still hold the rcu read lock, and put_mnt_ns() may sleep there. This is the same problem commit 2ec2aff3c8e2 ("ns: make sure reference are dropped outside of rcu lock") fixed for the put_user() path. Neither ns_requested() nor may_list_ns() needs a reference, both only look at the namespace type and at the caller's own namespaces, so do the checks first and take the reference last. Splat: Voluntary context switch within RCU read-side critical section! WARNING: kernel/rcu/tree_plugin.h:332 at rcu_note_context_switch+0x238/0x2a0, CPU#5: a/3442 CPU: 5 UID: 1000 PID: 3442 Comm: a Not tainted 7.0.0-30-generic #30-Ubuntu PREEMPT(lazy) RIP: 0010:rcu_note_context_switch+0x238/0x2a0 Call Trace: __schedule+0xcf/0x650 schedule+0x27/0x90 schedule_preempt_disabled+0x15/0x30 __mutex_lock.constprop.0+0x550/0xaf0 __mutex_lock_slowpath+0x13/0x20 mutex_lock+0x3b/0x50 exp_funnel_lock+0xb2/0x260 synchronize_rcu_expedited+0xe7/0x220 namespace_unlock+0x26a/0x320 put_mnt_ns+0xd3/0x120 mntns_put+0xe/0x20 do_listns+0x13e/0x560 __do_sys_listns+0x126/0x2d0 __x64_sys_listns+0x20/0x30 x64_sys_call+0x2366/0x2390 do_syscall_64+0x105/0x5a0 entry_SYSCALL_64_after_hwframe+0x76/0x7e Fixes: 76b6f5dfb3fd ("nstree: add listns()") Signed-off-by: Norbert Szetei Link: https://patch.msgid.link/ABA32239-733B-438C-B95A-B13ED69FF0F3@doyensec.com Reviewed-by: Bradley Morgan Signed-off-by: Christian Brauner (Amutable) --- kernel/nstree.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/kernel/nstree.c b/kernel/nstree.c index 6d12e5900ac0..831f279d174a 100644 --- a/kernel/nstree.c +++ b/kernel/nstree.c @@ -533,19 +533,13 @@ DEFINE_FREE(ns_put, struct ns_common *, if (!IS_ERR_OR_NULL(_T)) ns_put(_T)) static inline struct ns_common *__must_check legitimize_ns(const struct klistns *kls, struct ns_common *candidate) { - struct ns_common *ns __free(ns_put) = NULL; - if (!ns_requested(kls, candidate)) return NULL; - ns = ns_get_unless_inactive(candidate); - if (!ns) + if (!may_list_ns(kls, candidate)) return NULL; - if (!may_list_ns(kls, ns)) - return NULL; - - return no_free_ptr(ns); + return ns_get_unless_inactive(candidate); } static ssize_t do_listns_userns(struct klistns *kls) From ed761e0693950fcb4f6b0f60387a3961b972adf3 Mon Sep 17 00:00:00 2001 From: Leonardo Costa Date: Mon, 6 Jul 2026 10:24:17 -0300 Subject: [PATCH 1001/1198] drm/bridge: tc358768: Enforce input bus flags via atomic_check The tc358768 declares static bridge timings requiring pixel data to be sampled on the positive clock edge. However, the DRM core default propagation simply copies the output-side bus flags, coming from the next bridge, connector or panel, to the input side. If the propagated flags are incompatible with the bridge ones, the data is wrongly sampled, typically resulting in visual artifacts on the panel. Implement the atomic_check hook, replacing the mutually exclusive mode_fixup, and set the bridge state input bus flags to the ones required by the tc358768. The sync polarity defaulting previously done in mode_fixup is carried over into atomic_check unchanged. Fixes: ff1ca6397b1d ("drm/bridge: Add tc358768 driver") Cc: stable@vger.kernel.org Signed-off-by: Leonardo Costa Reviewed-by: Francesco Dolcini Reviewed-by: Swamil Jain Reviewed-by: Luca Ceresoli Link: https://patch.msgid.link/20260706132440.1594239-1-leoreis.costa@gmail.com Signed-off-by: Luca Ceresoli --- drivers/gpu/drm/bridge/tc358768.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/bridge/tc358768.c b/drivers/gpu/drm/bridge/tc358768.c index d1fc6af37cc5..19b43efcf93f 100644 --- a/drivers/gpu/drm/bridge/tc358768.c +++ b/drivers/gpu/drm/bridge/tc358768.c @@ -1263,10 +1263,13 @@ tc358768_atomic_get_input_bus_fmts(struct drm_bridge *bridge, return input_fmts; } -static bool tc358768_mode_fixup(struct drm_bridge *bridge, - const struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode) +static int tc358768_bridge_atomic_check(struct drm_bridge *bridge, + struct drm_bridge_state *bridge_state, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state) { + struct drm_display_mode *adjusted_mode = &crtc_state->adjusted_mode; + /* Default to positive sync */ if (!(adjusted_mode->flags & @@ -1277,13 +1280,15 @@ static bool tc358768_mode_fixup(struct drm_bridge *bridge, (DRM_MODE_FLAG_PVSYNC | DRM_MODE_FLAG_NVSYNC))) adjusted_mode->flags |= DRM_MODE_FLAG_PVSYNC; - return true; + bridge_state->input_bus_cfg.flags = bridge->timings->input_bus_flags; + + return 0; } static const struct drm_bridge_funcs tc358768_bridge_funcs = { .attach = tc358768_bridge_attach, .mode_valid = tc358768_bridge_mode_valid, - .mode_fixup = tc358768_mode_fixup, + .atomic_check = tc358768_bridge_atomic_check, .atomic_pre_enable = tc358768_bridge_atomic_pre_enable, .atomic_enable = tc358768_bridge_atomic_enable, .atomic_disable = tc358768_bridge_atomic_disable, From d144a494d81fcf2d1c5cf58b01c655bb8bafc701 Mon Sep 17 00:00:00 2001 From: Gabriel Windlin Date: Tue, 8 Sep 2026 22:34:11 +0200 Subject: [PATCH 1002/1198] MAINTAINERS: fix sysfs-platform-ayaneo-ec documentation path MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The documentation file for the AYANEO platform EC driver was added as Documentation/ABI/testing/sysfs-platform-ayaneo-ec, but MAINTAINERS references it without the '-ec' suffix, causing 'make refcheckdocs' to report a broken reference. Update the file entry to point to the correct file name. Signed-off-by: Gabriel Windlin Link: https://patch.msgid.link/20260908203412.608606-1-gawindlin@gmail.com Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 3a19da74d00c..0a0dbb9cb126 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4512,7 +4512,7 @@ AYANEO PLATFORM EC DRIVER M: Antheas Kapenekakis L: platform-driver-x86@vger.kernel.org S: Maintained -F: Documentation/ABI/testing/sysfs-platform-ayaneo +F: Documentation/ABI/testing/sysfs-platform-ayaneo-ec F: drivers/platform/x86/ayaneo-ec.c AZ6007 DVB DRIVER From 0ee150794c75bcd0be0e24ff3394f433cbae18cc Mon Sep 17 00:00:00 2001 From: Bjoern Doebel Date: Tue, 8 Sep 2026 16:10:00 +0000 Subject: [PATCH 1003/1198] smb: client: fix heap overflow in DACL owner/group rewrite When id_mode_to_cifs_acl rewrites an existing DACL, it allocates a buffer sized according to the on-disk DACL length reported by dacl_ptr->size. However, replace_sids_and_copy_aces may rewrite each ACE with a new owner/group SID obtained from the cifs.idmap upcall. Those SIDs can have up to SID_MAX_SUB_AUTHORITIES (15) sub-authorities, making each ACE up to 76 bytes (sizeof(struct smb_ace)). If the original DACL contains short SIDs (e.g., 1 sub-authority) while the replacement SIDs are long, the rewritten ACEs overflow the allocation. Fix this by always budgeting for worst-case SID expansion: allocate sizeof(struct smb_acl) plus num_aces * sizeof(struct smb_ace), which covers the smb_acl header and room for every ACE at maximum SID size. This replaces the previous split logic that used dacl_ptr->size for cifsacl mounts but num_aces * sizeof(struct smb_ace) for mode_from_sid mounts: both paths can trigger the same rewrite and need the same headroom. KASAN reports this as: BUG: KASAN: slab-out-of-bounds in build_sec_desc+0x1e8a/0x2680 [cifs] Write of size 4 at addr ffff8881a5e25374 by task chown/5298 ... The buggy address is located 0 bytes to the right of allocated 884-byte region [ffff8881a5e25000, ffff8881a5e25374) Cc: stable@vger.kernel.org Fixes: bc3e9dd9d104 ("cifs: Change SIDs in ACEs while transferring file ownership.") Assisted-by: Kiro:claude-opus-4.6 Signed-off-by: Bjoern Doebel Reviewed-by: Namjae Jeon Fixes: 5c3564852c58 ("cifs: Minimize the number of cifs_acl memory allocations") Signed-off-by: Paulo Alcantara --- fs/smb/client/cifsacl.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/fs/smb/client/cifsacl.c b/fs/smb/client/cifsacl.c index def8908dd7e9..3e96e151df35 100644 --- a/fs/smb/client/cifsacl.c +++ b/fs/smb/client/cifsacl.c @@ -1837,11 +1837,13 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode, cifs_put_tlink(tlink); return rc; } - if (mode_from_sid) - nsecdesclen += - le16_to_cpu(dacl_ptr->num_aces) * sizeof(struct smb_ace); - else /* cifsacl */ - nsecdesclen += le16_to_cpu(dacl_ptr->size); + /* + * Worst case: every ACE is rewritten with a new SID of + * SID_MAX_SUB_AUTHORITIES sub-auths -> sizeof(smb_ace) each, + * plus the smb_acl header replace_sids_and_copy_aces() emits. + */ + nsecdesclen += sizeof(struct smb_acl) + + le16_to_cpu(dacl_ptr->num_aces) * sizeof(struct smb_ace); } } From d05045177a855386bca5e1909e08d06290e6e3b3 Mon Sep 17 00:00:00 2001 From: Bjoern Doebel Date: Tue, 8 Sep 2026 16:10:01 +0000 Subject: [PATCH 1004/1198] smb: client: fail DACL rewrite when the new DACL exceeds 64K replace_sids_and_copy_aces() and set_chmod_dacl() accumulate the size of the DACL they build in a u16. That accumulator can wrap. validate_dacl() caps num_aces at (dacl_size - sizeof(struct smb_acl)) / 20, i.e. 3276 for a maximally sized DACL, while each rewritten ACE can grow to sizeof(struct smb_ace) (76 bytes) once its SID is replaced with one carrying SID_MAX_SUB_AUTHORITIES sub-authorities. The worst case is therefore sizeof(struct smb_acl) + 3276 * 76 = 248984 bytes, far beyond what a u16 can hold. A wraparound is reached with 863 ACEs. After the wraparound, ndacl_ptr->size becomes meaningless and the offset will point anywhere in the ACE array. As a result, we will see corruption of the DACL, which then gets sent to the server. This is not an out-of-bounds write as the allocation now covers the worst-case expansion, so writes will always go into the buffer. Adjust the code to use a u32 internally and return -EOVERFLOW in the overflow case. The operation must be refused, because a DACL can only hold 2^16-1 bytes on the wire and larger DACLs cannot be represented. set_chmod_dacl() carries the same pattern and is fixed the same way. It only wraps once the source DACL comes within roughly 380 bytes of the 64K ceiling, but the failure mode is identical. Suggested-by: Namjae Jeon Cc: stable@vger.kernel.org Fixes: f5065508897a ("cifs: Retain old ACEs when converting between mode bits and ACL.") Assisted-by: Kiro:claude-opus-5 Signed-off-by: Bjoern Doebel Reviewed-by: Namjae Jeon Signed-off-by: Paulo Alcantara --- fs/smb/client/cifsacl.c | 39 ++++++++++++++++++++++++++------------- 1 file changed, 26 insertions(+), 13 deletions(-) diff --git a/fs/smb/client/cifsacl.c b/fs/smb/client/cifsacl.c index 3e96e151df35..c5e47a835f99 100644 --- a/fs/smb/client/cifsacl.c +++ b/fs/smb/client/cifsacl.c @@ -1096,13 +1096,13 @@ unsigned int setup_special_user_owner_ACE(struct smb_ace *pntace) static void populate_new_aces(char *nacl_base, struct smb_sid *pownersid, struct smb_sid *pgrpsid, - __u64 *pnmode, u16 *pnum_aces, u16 *pnsize, + __u64 *pnmode, u16 *pnum_aces, u32 *pnsize, bool modefromsid, bool posix) { __u64 nmode; u16 num_aces = 0; - u16 nsize = 0; + u32 nsize = 0; __u64 user_mode; __u64 group_mode; __u64 other_mode; @@ -1201,17 +1201,17 @@ static void populate_new_aces(char *nacl_base, *pnsize = nsize; } -static __u16 replace_sids_and_copy_aces(struct smb_acl *pdacl, struct smb_acl *pndacl, - struct smb_sid *pownersid, struct smb_sid *pgrpsid, - struct smb_sid *pnownersid, struct smb_sid *pngrpsid, - int *aclflag) +static int replace_sids_and_copy_aces(struct smb_acl *pdacl, struct smb_acl *pndacl, + struct smb_sid *pownersid, struct smb_sid *pgrpsid, + struct smb_sid *pnownersid, struct smb_sid *pngrpsid, + int *aclflag, u16 *pnsize) { int i; u16 size = 0; struct smb_ace *pntace = NULL; char *acl_base = NULL; u16 src_num_aces = 0; - u16 nsize = 0; + u32 nsize = 0; struct smb_ace *pnntace = NULL; char *nacl_base = NULL; u16 ace_size = 0; @@ -1240,9 +1240,12 @@ static __u16 replace_sids_and_copy_aces(struct smb_acl *pdacl, struct smb_acl *p size += le16_to_cpu(pntace->size); nsize += ace_size; + if (nsize > U16_MAX) + return -EOVERFLOW; } - return nsize; + *pnsize = nsize; + return 0; } static int set_chmod_dacl(struct smb_acl *pdacl, struct smb_acl *pndacl, @@ -1254,7 +1257,7 @@ static int set_chmod_dacl(struct smb_acl *pdacl, struct smb_acl *pndacl, struct smb_ace *pntace = NULL; char *acl_base = NULL; u16 src_num_aces = 0; - u16 nsize = 0; + u32 nsize = 0; struct smb_ace *pnntace = NULL; char *nacl_base = NULL; u16 num_aces = 0; @@ -1305,6 +1308,8 @@ static int set_chmod_dacl(struct smb_acl *pdacl, struct smb_acl *pndacl, nsize += cifs_copy_ace(pnntace, pntace, NULL); num_aces++; + if (nsize > U16_MAX) + return -EOVERFLOW; next_ace: size += le16_to_cpu(pntace->size); @@ -1321,6 +1326,10 @@ static int set_chmod_dacl(struct smb_acl *pdacl, struct smb_acl *pndacl, } finalize_dacl: + /* The DACL size field is 16-bit on the wire, see MS-DTYP 2.4.5 */ + if (nsize > U16_MAX) + return -EOVERFLOW; + pndacl->num_aces = cpu_to_le16(num_aces); pndacl->size = cpu_to_le16(nsize); @@ -1473,6 +1482,8 @@ static int build_sec_desc(struct smb_ntsd *pntsd, struct smb_ntsd *pnntsd, rc = set_chmod_dacl(dacl_ptr, ndacl_ptr, owner_sid_ptr, group_sid_ptr, pnmode, mode_from_sid, posix); + if (rc) + return rc; sidsoffset = ndacloffset + le16_to_cpu(ndacl_ptr->size); /* copy the non-dacl portion of secdesc */ @@ -1548,10 +1559,12 @@ static int build_sec_desc(struct smb_ntsd *pntsd, struct smb_ntsd *pnntsd, if (dacloffset) { /* Replace ACEs for old owner with new one */ - size = replace_sids_and_copy_aces(dacl_ptr, ndacl_ptr, - owner_sid_ptr, group_sid_ptr, - nowner_sid_ptr, ngroup_sid_ptr, - aclflag); + rc = replace_sids_and_copy_aces(dacl_ptr, ndacl_ptr, + owner_sid_ptr, group_sid_ptr, + nowner_sid_ptr, ngroup_sid_ptr, + aclflag, &size); + if (rc) + goto chown_chgrp_exit; ndacl_ptr->size = cpu_to_le16(size); } From 4600b4d1a9ee730d03ddac5ce409cd2730ce8c0c Mon Sep 17 00:00:00 2001 From: Esben Haabendal Date: Mon, 31 Aug 2026 14:21:32 +0200 Subject: [PATCH 1005/1198] drm/bridge: ti-sn65dsi83: Fix error handling in sn65dsi83_reset_work() The error handling of sn65dsi83_reset_pipe() in sn65dsi83_reset_work() has seen a couple of changes that seems to cause a bit of confusion. While sn65dsi83_reset_work() has implemented an early exit if sn65dsi83_reset_pipe() fails since it was added, when a commit from Maxime Ripard switched to use drm_bridge_helper_reset_crtc() [1] the sn65dsi83_reset_pipe() function would no longer return an error code, so the early exit was then a no-op, and even on sn65dsi83_reset_pipe() failure, enable_irq() has been called. When drm_bridge_enter()/drm_bridge_exit() resource protection was added, the drm_bridge_exit() incidentally was always called, which is the correct approach. But only because the early exit in sn65dsi83_reset_pipe() was never hit because sn65dsi83_reset_pipe() always returns 0. In order get back to a situation where enable_irq() is not called on sn65dsi83_reset_pipe() failure, which should help protect against irq storms, we need to reintroduce a non-zero return value from sn65dsi83_reset_pipe() on error, and fix sn65dsi83_reset_work() so that we always exit the DRM bridge critical section with drm_bridge_exit(). [1] commit e17fadff7ab9 ("drm/bridge: ti-sn65dsi83: Switch to drm_bridge_helper_reset_crtc") [2] commit d2e8d1bc840b ("drm/bridge: ti-sn65dsi83: protect device resources on unplug") Fixes: e17fadff7ab9 ("drm/bridge: ti-sn65dsi83: Switch to drm_bridge_helper_reset_crtc") Cc: stable@vger.kernel.org Signed-off-by: Esben Haabendal Reviewed-by: Herve Codina Reviewed-by: Luca Ceresoli Tested-by: Luca Ceresoli Link: https://patch.msgid.link/20260831-ti-sn65dsi83-fixes-v5-1-e712765d6c4f@geanix.com Signed-off-by: Luca Ceresoli --- drivers/gpu/drm/bridge/ti-sn65dsi83.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi83.c b/drivers/gpu/drm/bridge/ti-sn65dsi83.c index f9fdbf48c6b3..526826ba4524 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi83.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi83.c @@ -403,7 +403,7 @@ static int sn65dsi83_reset_pipe(struct sn65dsi83 *sn65dsi83) drm_modeset_drop_locks(&ctx); drm_modeset_acquire_fini(&ctx); - return 0; + return err; } static void sn65dsi83_reset_work(struct work_struct *ws) @@ -419,11 +419,13 @@ static void sn65dsi83_reset_work(struct work_struct *ws) ret = sn65dsi83_reset_pipe(ctx); if (ret) { dev_err(ctx->dev, "reset pipe failed %pe\n", ERR_PTR(ret)); - return; + goto bridge_exit; } + if (ctx->irq) enable_irq(ctx->irq); +bridge_exit: drm_bridge_exit(idx); } From 20fce5b34b21a995839743b4917a1edd2fd503ba Mon Sep 17 00:00:00 2001 From: Varun Gupta Date: Mon, 7 Sep 2026 10:30:12 +0530 Subject: [PATCH 1006/1198] drm/xe: Guard page-fault worker with runtime PM check MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit During VM teardown, the VM's runtime PM reference is dropped asynchronously, allowing the device to autosuspend while stale page faults belonging to the now-dead VM are still queued. When the page-fault worker later tries to ack one of these, it calls into guc_ct_send_locked() on an already-suspended device, tripping:   Assertion `!xe_pm_runtime_suspended(xe)` failed!   WARNING at xe_device.c:1267 xe_device_assert_mem_access+0x11c/0x140 [xe] A live VM/exec queue always holds a PM reference while it has outstanding work, so if the device is suspended at ack time, the owning context is already gone and the fault is stale. Take a runtime PM reference across the entire pagefault queue worker to safely deliver acks for torn-down VMs. v3: - Move PM ref to the generic xe_pagefault_queue_work using guard(xe_pm_runtime)(xe) instead of tracking it in the GuC backend(Matt Brost). v2: - Hold PM ref across the entire batch (begin/end) instead of per-ack. This prevents the device from autosuspending mid-batch, which would leave write_only acks written but the end flush skipped, and skip counter++, desyncing the cadence check.(Himal) - Add a comment explaining stale faults.(Himal) Fixes: f289f7807119 ("drm/xe: Add xe_guc_pagefault layer") Signed-off-by: Varun Gupta Reviewed-by: Matthew Brost Reviewed-by: Tejas Upadhyay Link: https://patch.msgid.link/20260907050011.497181-2-varun.gupta@intel.com Signed-off-by: Tejas Upadhyay (cherry picked from commit fcc2431d2213dc4d04250c4f1ae87d9c3ae0d455) Signed-off-by: Rodrigo Vivi [Rodrigo: Added xe_device struct for compatibility while cherry-picking] --- drivers/gpu/drm/xe/xe_pagefault.c | 10 ++++++++++ drivers/gpu/drm/xe/xe_pagefault_types.h | 3 +++ 2 files changed, 13 insertions(+) diff --git a/drivers/gpu/drm/xe/xe_pagefault.c b/drivers/gpu/drm/xe/xe_pagefault.c index dbf8f71d3328..a4986df8328d 100644 --- a/drivers/gpu/drm/xe/xe_pagefault.c +++ b/drivers/gpu/drm/xe/xe_pagefault.c @@ -16,6 +16,7 @@ #include "xe_hw_engine.h" #include "xe_pagefault.h" #include "xe_pagefault_types.h" +#include "xe_pm.h" #include "xe_svm.h" #include "xe_trace_bo.h" #include "xe_vm.h" @@ -292,9 +293,17 @@ static void xe_pagefault_queue_work(struct work_struct *w) { struct xe_pagefault_queue *pf_queue = container_of(w, typeof(*pf_queue), worker); + struct xe_device *xe = pf_queue->xe; struct xe_pagefault pf; unsigned long threshold; + /* + * A live VM holds a PM reference, but a torn-down VM does not. + * Guard the entire worker loop to safely drain stale faults and + * prevent autosuspends from desyncing batched CT flushes. + */ + guard(xe_pm_runtime)(xe); + #define USM_QUEUE_MAX_RUNTIME_MS 20 threshold = jiffies + msecs_to_jiffies(USM_QUEUE_MAX_RUNTIME_MS); @@ -365,6 +374,7 @@ static int xe_pagefault_queue_init(struct xe_device *xe, drm_dbg(&xe->drm, "xe_pagefault_entry_size=%d, total_num_eus=%d, pf_queue->size=%u", xe_pagefault_entry_size(), total_num_eus, pf_queue->size); + pf_queue->xe = xe; spin_lock_init(&pf_queue->lock); INIT_WORK(&pf_queue->worker, xe_pagefault_queue_work); diff --git a/drivers/gpu/drm/xe/xe_pagefault_types.h b/drivers/gpu/drm/xe/xe_pagefault_types.h index c4ee625b93dd..f63a12aa0d4f 100644 --- a/drivers/gpu/drm/xe/xe_pagefault_types.h +++ b/drivers/gpu/drm/xe/xe_pagefault_types.h @@ -8,6 +8,7 @@ #include +struct xe_device; struct xe_gt; struct xe_pagefault; @@ -118,6 +119,8 @@ struct xe_pagefault { * queue to absorb the device’s worst-case number of outstanding faults. */ struct xe_pagefault_queue { + /** @xe: Back-pointer to the Xe device */ + struct xe_device *xe; /** * @data: Data in queue containing struct xe_pagefault, protected by * @lock From f5fcf7e638b904397ec0f66d3ea6766ef0cfe25b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= Date: Thu, 3 Sep 2026 13:45:52 +0200 Subject: [PATCH 1007/1198] drm/xe: Flush LSC untyped L1 dataport cache after rcs/ccs batches MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit emit_render_cache_flush() sets PIPE_CONTROL0_HDC_PIPELINE_FLUSH to flush the L2/HDC data cache before fence signalling, but it never requests a flush of the LSC untyped L1 data cache via the 'Untyped Data-Port Cache Flush Enable' bit in PIPE_CONTROL DWord0[11]. Per the Bspec, in 3D pipeline mode HDC Pipeline Flush is documented to also flush/invalidate the untyped L1 cache, but only depending on how HDC_CHICKEN0[13:11] is programmed. Starting with MTL, this coupling between HDC Pipeline Flush and the untyped L1 cache flush no longer holds in practice, regardless of how HDC_CHICKEN0 is programmed, so relying on it is not safe on newer platforms such as BMG. Mesa's Vulkan driver (anv) has been assuming the kernel flushes both caches between submissions, and hit user-visible corruption in apps such as Llama.cpp because of this gap; it now works around it by flushing both caches again from userspace at the end of every command buffer. Correctness between submissions on the same queue is userspace's responsibility and belongs in Mesa, not the kernel. However, for security we must ensure stale data can't leak through the untyped L1 dataport cache once memory is reclaimed or evicted, which requires the KMD to flush it before releasing memory for reuse. Prior to MTL, HDC_CHICKEN0 could be programmed (as already done for DG2 via Wa_22010960976/Wa_14013347512) to reliably keep HDC Pipeline Flush coupled to the untyped L1 cache flush, so those platforms are unaffected. Mesa's own anv driver found that on MTL the HW disconnected the two independently of how HDC_CHICKEN0 is programmed, and could not bring the old behavior back even by writing the register by hand; see Mesa commit 7c2ff46a4fc3 ("anv: don't prevent L1 untyped cache flush in 3D mode"). The kernel can't reliably request the flush from the CS on MTL either, so restrict the new PIPE_CONTROL bit to GRAPHICS_VERx100 >= 2000 (Xe2 and later), where it can be relied on. Explicitly set PIPE_CONTROL0_UNTYPED_DATAPORT_CACHE_FLUSH together with PIPE_CONTROL0_HDC_PIPELINE_FLUSH in emit_render_cache_flush() on Xe2 and later, so the L1 data cache is known clean before memory is released for reuse, without depending on undocumented platform-specific HDC_CHICKEN0 behavior. Bspec: 56551 Link: https://gitlab.freedesktop.org/mesa/mesa/-/commit/7c2ff46a4fc3e537573ac9503057e0cd29b6fff3 Fixes: 9f8f93bee3ef ("drm/xe: Emit a render cache flush after each rcs/ccs batch") Reported-by: Lionel Landwerlin Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/8909 Cc: José Roberto de Souza Cc: intel-xe@lists.freedesktop.org Cc: # v6.8+ Assisted-by: GitHub_Copilot:claude-sonnet-5 Signed-off-by: Thomas Hellström Reviewed-by: Matthew Auld Link: https://patch.msgid.link/20260903114552.48634-1-thomas.hellstrom@linux.intel.com (cherry picked from commit 434514b6fe731e873808297c268fc52cdf4a1ce6) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/xe/instructions/xe_gpu_commands.h | 1 + drivers/gpu/drm/xe/xe_ring_ops.c | 11 +++++++++++ 2 files changed, 12 insertions(+) diff --git a/drivers/gpu/drm/xe/instructions/xe_gpu_commands.h b/drivers/gpu/drm/xe/instructions/xe_gpu_commands.h index 18d0fde8c98f..faf8d7e2c5c1 100644 --- a/drivers/gpu/drm/xe/instructions/xe_gpu_commands.h +++ b/drivers/gpu/drm/xe/instructions/xe_gpu_commands.h @@ -46,6 +46,7 @@ #define GFX_OP_PIPE_CONTROL(len) ((0x3<<29)|(0x3<<27)|(0x2<<24)|((len)-2)) #define PIPE_CONTROL0_QUEUE_DRAIN_MODE BIT(12) +#define PIPE_CONTROL0_UNTYPED_DATAPORT_CACHE_FLUSH BIT(11) /* gen12 */ #define PIPE_CONTROL0_L3_READ_ONLY_CACHE_INVALIDATE BIT(10) /* gen12 */ #define PIPE_CONTROL0_HDC_PIPELINE_FLUSH BIT(9) /* gen12 */ diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c index 39a670e91ba7..08b4a4283e96 100644 --- a/drivers/gpu/drm/xe/xe_ring_ops.c +++ b/drivers/gpu/drm/xe/xe_ring_ops.c @@ -212,6 +212,7 @@ static int emit_render_cache_flush(struct xe_sched_job *job, u32 *dw, int i) { struct xe_exec_queue *q = job->q; struct xe_gt *gt = q->gt; + struct xe_device *xe = gt_to_xe(gt); bool lacks_render = !(gt->info.engine_mask & XE_HW_ENGINE_RCS_MASK); u32 flags0, flags1; @@ -220,6 +221,16 @@ static int emit_render_cache_flush(struct xe_sched_job *job, u32 *dw, int i) LRC_PPHWSP_FLUSH_INVAL_SCRATCH_ADDR, 0); flags0 = PIPE_CONTROL0_HDC_PIPELINE_FLUSH; + /* + * Prior to MTL, HDC Pipeline Flush reliably also flushes the LSC + * untyped L1 dataport cache, provided HDC_CHICKEN0 is programmed + * correctly. Starting with MTL that coupling no longer holds + * regardless of how HDC_CHICKEN0 is programmed, but explicitly + * requesting the flush via PIPE_CONTROL is itself only reliable + * from Xe2 onward, so only gate it in on Xe2+. + */ + if (GRAPHICS_VERx100(xe) >= 2000) + flags0 |= PIPE_CONTROL0_UNTYPED_DATAPORT_CACHE_FLUSH; flags1 = (PIPE_CONTROL_TILE_CACHE_FLUSH | PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH | PIPE_CONTROL_DEPTH_CACHE_FLUSH | From 6028b543884f8735e057ec9eea4908cd61cab230 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Wed, 2 Sep 2026 20:00:41 -0300 Subject: [PATCH 1008/1198] io_uring/net: don't overconsume buffers when using MSG_TRUNC When a recv/recvmsg is issued with MSG_TRUNC and the incoming packet is larger than the provided buffer, the net layer returns the full length of the packet rather than the number of bytes actually copied into the buffer. As a result, io_uring advances more of the provided buffer ring than was actually filled. Use the actual filled region size to consume the buffer, but still return the full size to preserve MSG_TRUNC semantics. Take care with multishot, because that seems to already truncate the consumption based on the available payload size. This was reported in https://github.com/axboe/liburing/issues/1619. Fixes: ae98dbf43d75 ("io_uring/kbuf: add support for incremental buffer consumption") Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260728191454.1850326-1-krisman@suse.de Signed-off-by: Gabriel Krisman Bertazi Link: https://patch.msgid.link/20260902230041.1320658-3-krisman@suse.de [axboe: fold in size_t unsigned fix] Signed-off-by: Jens Axboe --- io_uring/net.c | 41 +++++++++++++++++++++++++++++++++-------- 1 file changed, 33 insertions(+), 8 deletions(-) diff --git a/io_uring/net.c b/io_uring/net.c index 647156c9331a..050ed274170a 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -853,7 +853,7 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) static inline bool io_recv_finish(struct io_kiocb *req, struct io_async_msghdr *kmsg, struct io_br_sel *sel, bool mshot_finished, - unsigned issue_flags) + unsigned issue_flags, int consumed) { struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); unsigned int cflags = 0; @@ -877,7 +877,7 @@ static inline bool io_recv_finish(struct io_kiocb *req, if (sr->flags & IORING_RECVSEND_BUNDLE) { size_t this_ret = sel->val - sr->done_io; - cflags |= io_put_kbufs(req, this_ret, sel->buf_list, io_bundle_nbufs(kmsg, this_ret)); + cflags |= io_put_kbufs(req, consumed, sel->buf_list, io_bundle_nbufs(kmsg, consumed)); if (sr->flags & IORING_RECV_RETRY) cflags = req->cqe.flags | (cflags & CQE_F_MASK); if (sr->mshot_len && sel->val >= sr->mshot_len) @@ -899,7 +899,7 @@ static inline bool io_recv_finish(struct io_kiocb *req, return false; } } else { - cflags |= io_put_kbuf(req, sel->val, sel->buf_list); + cflags |= io_put_kbuf(req, consumed, sel->buf_list); } /* @@ -1027,6 +1027,8 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) int ret, min_ret = 0; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; bool mshot_finished = true; + int consumed = 0; + size_t len; sock = sock_from_file(req->file); if (unlikely(!sock)) @@ -1042,9 +1044,8 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) retry_multishot: sel.buf_list = NULL; + len = sr->len; if (io_do_buffer_select(req)) { - size_t len = sr->len; - sel = io_buffer_select(req, &len, sr->buf_group, issue_flags); if (!sel.addr) return -ENOBUFS; @@ -1065,6 +1066,7 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) if (req->flags & REQ_F_APOLL_MULTISHOT) { ret = io_recvmsg_multishot(sock, sr, kmsg, flags, &mshot_finished); + consumed = ret; } else { /* disable partial retry for recvmsg with cmsg attached */ if (flags & MSG_WAITALL && !kmsg->msg.msg_controllen) @@ -1072,6 +1074,15 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) ret = __sys_recvmsg_sock(sock, &kmsg->msg, sr->umsg, kmsg->uaddr, flags); + /* + * With MSG_TRUNC, the net layer will return the full size of + * the packet, even if we only filled part of it in the buffers. + * Adjust the returned size to consume only the real part of the + * buffer. + */ + consumed = ret; + if (ret > 0) + consumed = min_t(size_t, ret, len); } if (ret < min_ret) { @@ -1098,7 +1109,7 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) io_kbuf_recycle(req, sel.buf_list, issue_flags); sel.val = ret; - if (!io_recv_finish(req, kmsg, &sel, mshot_finished, issue_flags)) + if (!io_recv_finish(req, kmsg, &sel, mshot_finished, issue_flags, consumed)) goto retry_multishot; return sel.val; @@ -1185,9 +1196,10 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags) struct io_br_sel sel; struct socket *sock; unsigned flags; - int ret, min_ret = 0; + int ret, min_ret = 0, consumed = 0; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; bool mshot_finished; + size_t len = 0; sock = sock_from_file(req->file); if (unlikely(!sock)) @@ -1215,6 +1227,7 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags) retry_multishot: sel.buf_list = NULL; + len = sr->len; if (io_do_buffer_select(req)) { sel.val = sr->len; ret = io_recv_buf_select(req, kmsg, &sel, issue_flags); @@ -1222,6 +1235,7 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags) kmsg->msg.msg_inq = -1; goto out_free; } + len = ret; sr->buf = NULL; } @@ -1252,6 +1266,17 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags) } mshot_finished = ret <= 0; + + /* + * With MSG_TRUNC, the net layer will return the full size of + * the packet, even if we only filled part of it in the buffers. + * Adjust the returned size to consume only the real part of the + * buffer. + */ + consumed = ret; + if (ret > 0) + consumed = min_t(size_t, ret, len); + if (ret > 0) ret += sr->done_io; else if (sr->done_io) @@ -1260,7 +1285,7 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags) io_kbuf_recycle(req, sel.buf_list, issue_flags); sel.val = ret; - if (!io_recv_finish(req, kmsg, &sel, mshot_finished, issue_flags)) + if (!io_recv_finish(req, kmsg, &sel, mshot_finished, issue_flags, consumed)) goto retry_multishot; return sel.val; From 47ccc3f1c615a46c25cbf7f3ae60df30b40eb2e6 Mon Sep 17 00:00:00 2001 From: Caleb Sander Mateos Date: Wed, 2 Sep 2026 15:01:59 -0600 Subject: [PATCH 1009/1198] io_uring/rw: keep CQE flags on iopoll requests when adding kbuf flags io_do_iopoll() assigns the result of io_put_kbuf() to the request's CQE flags upon completion. This overwrites any CQE flags that may have been set by the opcode-specific layer. (For example, if __io_uring_cmd_done() had set IORING_CQE_F_32, it would be cleared.) Switch the = to an |= so the kbuf flags are added to the existing CQE flags rather than replacing them. io_req_rw_complete() does the same with the io_put_kbuf() result. Fixes: e26dca67fde1 ("io_uring: add support for IORING_SETUP_CQE_MIXED") Reported-by: sashiko-bot@kernel.org Link: https://sashiko.dev/#/message/20260827191705.D53C91F000E9%40smtp.kernel.org Signed-off-by: Caleb Sander Mateos Reviewed-by: Anuj Gupta Link: https://patch.msgid.link/20260902210200.2336720-1-csander@purestorage.com Signed-off-by: Jens Axboe --- io_uring/rw.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/io_uring/rw.c b/io_uring/rw.c index 3e22f294bdf2..432820f86251 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -880,6 +880,7 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode, int rw_type) kiocb->private = NULL; kiocb->ki_flags |= IOCB_HIPRI; req->iopoll_completed = 0; + req->cqe.flags = 0; if (ctx->flags & IORING_SETUP_HYBRID_IOPOLL) { /* make sure every req only blocks once*/ req->flags &= ~REQ_F_IOPOLL_STATE; @@ -1382,7 +1383,7 @@ int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin) list_del(&req->iopoll_node); wq_list_add_tail(&req->comp_list, &ctx->submit_state.compl_reqs); nr_events++; - req->cqe.flags = io_put_kbuf(req, max(req->cqe.res, 0), NULL); + req->cqe.flags |= io_put_kbuf(req, max(req->cqe.res, 0), NULL); if (!io_is_uring_cmd(req)) io_req_rw_cleanup(req, 0); } From 5be081b83abd3f17d908953b4bb77279f5a149e3 Mon Sep 17 00:00:00 2001 From: Weiming Shi Date: Wed, 9 Sep 2026 00:50:47 +0800 Subject: [PATCH 1010/1198] net: dsa: tag_brcm: legacy FCS: request needed tailroom The legacy FCS tagger calculates the CRC over skb->len bytes starting at skb->data. When a nonlinear skb reaches the tagger, this reads past the linear head into unrelated slab memory. The tagger appends an Ethernet FCS but does not declare that tailroom. As a result, DSA leaves NETIF_F_SG and NETIF_F_FRAGLIST enabled on the user port, and nonlinear skbs can reach the CRC calculation. Declare the required tailroom. DSA will then clear those features and the networking core will linearize skbs before the tagger runs. A KASAN-enabled dsa_loop test using this tagger reports: BUG: KASAN: slab-out-of-bounds in crc32_le Read of size 1 at addr ffff8880397086c0 by task exp/135 Call Trace: crc32_le (lib/crc/crc32-main.c:38) brcm_leg_fcs_tag_xmit (net/dsa/tag_brcm.c:343) dsa_user_xmit (net/dsa/user.c:942) dev_hard_start_xmit (net/core/dev.c:3937) __dev_queue_xmit (net/core/dev.c:4926) packet_sendmsg (net/packet/af_packet.c:3110) __sys_sendto (net/socket.c:2281) The buggy address belongs to the object at ffff888039708400 which belongs to the cache skbuff_small_head of size 704 The buggy address is located 0 bytes to the right of allocated 704-byte region [ffff888039708400, ffff8880397086c0) Fixes: ef07df397a62 ("net: dsa: tag_brcm: add support for legacy FCS tags") Cc: stable@vger.kernel.org Reported-by: co+28eef7d8af9428e6@bugs.sh Closes: https://lore.kernel.org/all/jH6u350kaBRuqklDjd3k3BW4nWzp0tYRjq3p%40bugs.sh/ Signed-off-by: Weiming Shi Reviewed-by: Florian Fainelli Link: https://patch.msgid.link/20260908165047.2786340-1-bestswngs@gmail.com Signed-off-by: Jakub Kicinski --- net/dsa/tag_brcm.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index 411e3b57d16a..b7c49822ca88 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -373,6 +373,7 @@ static const struct dsa_device_ops brcm_legacy_fcs_netdev_ops = { .xmit = brcm_leg_fcs_tag_xmit, .rcv = brcm_leg_tag_rcv, .needed_headroom = BRCM_LEG_TAG_LEN, + .needed_tailroom = ETH_FCS_LEN, }; DSA_TAG_DRIVER(brcm_legacy_fcs_netdev_ops); From e2ab913f68c7d11e2561b8a8ad0b87ffefcad667 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 8 Sep 2026 16:07:06 +0200 Subject: [PATCH 1011/1198] mptcp: do not reschedule the RTX timer for fallback sockets On fallback socket the retrans timer is a quite convoluted no-op, but currently nothing prevents the MPTCP core to keep rescheduling it. Additionally gate RTX timer reset to the msk not being fallen back to TCP yet. To avoid adding multiple tests in fast-path, use a new flags bit for such condition. The RTX enable bit is clear at close time and set before the msk could start retransmitting, with a couple of caveats: - passive sockets inherit the bit from the listener msk; set the bit on such socket to avoid flipping it in the fast-path, even if the listener will obviously never retransmit. - while fastopening (MPTFO), mptcp_sendmsg_fastopen still ends-up calling mptcp_connect via tcp_sendmsg_fastopen -> __inet_stream_connect(ssk->sk_socket), and the first subflow's sk_socket points to the msk one. Fixes: b51f9b80c032 ("mptcp: introduce MPTCP retransmission timer") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260908-net-mptcp-misc-fixes-7-3-rc1-v2-1-df1de70348b6@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 13 ++++++++++--- net/mptcp/protocol.h | 1 + 2 files changed, 11 insertions(+), 3 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index e1f08f71cdb1..be59651e708e 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -95,6 +95,7 @@ bool __mptcp_try_fallback(struct mptcp_sock *msk, int fb_mib) msk->allow_subflows = false; set_bit(MPTCP_FALLBACK_DONE, &msk->flags); + clear_bit(MPTCP_RTX_ENABLED, &msk->flags); __MPTCP_INC_STATS(net, fb_mib); spin_unlock_bh(&msk->fallback_lock); return true; @@ -1084,13 +1085,14 @@ static bool mptcp_rtx_timer_pending(struct sock *sk) static void mptcp_reset_rtx_timer(struct sock *sk) { + struct mptcp_sock *msk = mptcp_sk(sk); unsigned long tout; - /* prevent rescheduling on close */ - if (unlikely(inet_sk_state_load(sk) == TCP_CLOSE)) + /* Prevent rescheduling on close and in case of fallback. */ + if (!test_bit(MPTCP_RTX_ENABLED, &msk->flags)) return; - tout = mptcp_sk(sk)->timer_ival; + tout = msk->timer_ival; sk_reset_timer(sk, &sk->mptcp_retransmit_timer, jiffies + tout); } @@ -3323,6 +3325,9 @@ void mptcp_set_state(struct sock *sk, int state) * transition from TCP_SYN_RECV to TCP_CLOSE_WAIT. */ break; + case TCP_CLOSE: + clear_bit(MPTCP_RTX_ENABLED, &mptcp_sk(sk)->flags); + fallthrough; default: if (oldstate == TCP_ESTABLISHED || oldstate == TCP_CLOSE_WAIT) MPTCP_DEC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB); @@ -4141,6 +4146,7 @@ static int mptcp_connect(struct sock *sk, struct sockaddr_unsized *uaddr, if (IS_ERR(ssk)) return PTR_ERR(ssk); + set_bit(MPTCP_RTX_ENABLED, &msk->flags); mptcp_set_state(sk, TCP_SYN_SENT); subflow = mptcp_subflow_ctx(ssk); #ifdef CONFIG_TCP_MD5SIG @@ -4288,6 +4294,7 @@ static int mptcp_listen(struct socket *sock, int backlog) goto unlock; } + set_bit(MPTCP_RTX_ENABLED, &msk->flags); mptcp_set_state(sk, TCP_LISTEN); sock_set_flag(sk, SOCK_RCU_FREE); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 87ccb84e9927..2b4c27426477 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -116,6 +116,7 @@ #define MPTCP_WORK_RTX 1 #define MPTCP_FALLBACK_DONE 2 #define MPTCP_WORK_CLOSE_SUBFLOW 3 +#define MPTCP_RTX_ENABLED 4 /* MPTCP socket release cb flags */ #define MPTCP_PUSH_PENDING 1 From 29f641951be0d91036d77edf677807f1447dbe65 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Tue, 8 Sep 2026 16:07:07 +0200 Subject: [PATCH 1012/1198] mptcp: subflow: no need to copy thmac during ulp_clone 'thmac' is not used after that point. Indeed, subflow_ulp_clone() is called when the request on the passive side is over, so when the truncated HMAC is no longer needed. Note that in case of SYN cookies, thmac will not be initialised. So better to remove it to avoid a warning from debug tools like KMSAN for reading uninitialised data. Fixes: f296234c98a8 ("mptcp: Add handling of incoming MP_JOIN requests") Cc: stable@vger.kernel.org Reviewed-by: Geliang Tang Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260908-net-mptcp-misc-fixes-7-3-rc1-v2-2-df1de70348b6@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/subflow.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index af81ad5e699d..01db7edce18a 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -2084,7 +2084,6 @@ static void subflow_ulp_clone(const struct request_sock *req, new_ctx->request_bkup = subflow_req->request_bkup; WRITE_ONCE(new_ctx->remote_id, subflow_req->remote_id); new_ctx->token = subflow_req->token; - new_ctx->thmac = subflow_req->thmac; /* the subflow req id is valid, fetched via subflow_check_req() * and subflow_token_join_request() From b76c0e28b392620dfbaf92cdeedbf115820b44cb Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Tue, 8 Sep 2026 16:07:08 +0200 Subject: [PATCH 1013/1198] mptcp: syncookies: remember the request backup flag Instead of using an uninitialised bit when copying the info in subflow_ulp_clone(). To fix this, no need to extend the join_entry structure: backup is coming from struct mptcp_subflow_request_sock, only one bit. Do the same here by using one bit for both. Fixes: efd340bf3d77 ("mptcp: distinguish rcv vs sent backup flag in requests") Cc: stable@vger.kernel.org Reviewed-by: Geliang Tang Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260908-net-mptcp-misc-fixes-7-3-rc1-v2-3-df1de70348b6@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/syncookies.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/mptcp/syncookies.c b/net/mptcp/syncookies.c index b5cac5701122..9474706641c1 100644 --- a/net/mptcp/syncookies.c +++ b/net/mptcp/syncookies.c @@ -26,7 +26,8 @@ struct join_entry { u32 local_nonce; u8 join_id; u8 local_id; - u8 backup; + u8 backup:1, + request_bkup:1; u8 valid; }; @@ -63,6 +64,7 @@ static void mptcp_join_store_state(struct join_entry *entry, entry->remote_nonce = subflow_req->remote_nonce; entry->local_nonce = subflow_req->local_nonce; entry->backup = subflow_req->backup; + entry->request_bkup = subflow_req->request_bkup; entry->join_id = subflow_req->remote_id; entry->local_id = subflow_req->local_id; entry->valid = 1; @@ -117,6 +119,7 @@ bool mptcp_token_join_cookie_init_state(struct mptcp_subflow_request_sock *subfl subflow_req->remote_nonce = e->remote_nonce; subflow_req->local_nonce = e->local_nonce; subflow_req->backup = e->backup; + subflow_req->request_bkup = e->request_bkup; subflow_req->remote_id = e->join_id; subflow_req->local_id = e->local_id; subflow_req->token = e->token; From 2ac7d6e620764f1fc79eb4edd3610a7a661981ca Mon Sep 17 00:00:00 2001 From: Kalpan Jani Date: Tue, 8 Sep 2026 16:07:09 +0200 Subject: [PATCH 1014/1198] mptcp: pm: kernel: drop pending ADD_ADDR when removing ID0 The in-kernel MPTCP path manager can leave a stale ADD_ADDR announcement entry alive when removing the id 0 endpoint. This happens because the id 0 removal path does not tear down pending announcements, unlike the non-zero id path. When the PM later reselects id 0 after adding another signal endpoint, it finds the stale anno_list entry and hits WARN_ON_ONCE(mptcp_pm_is_kernel()) in mptcp_pm_announced_alloc(). Root cause: asymmetry between removal paths. - Non-zero id path: mptcp_nl_remove_subflow_and_signal_addr() calls mptcp_pm_remove_announced() to clean up. - Id 0 path: mptcp_nl_remove_id_zero_address() skips cleanup entirely. Fix by making the id 0 path symmetric: call mptcp_pm_announced_remove() and decrement add_addr_signaled before queuing the RM_ADDR. Subtle detail: signal endpoints are stored in anno_list with port 0, but msk_local carries the connection's local port. In other words, entries linked to ID0 paths should have port == 0. A follow-up patch will ensure that. mptcp_pm_announced_remove() uses use_port=true for comparison. So clear the port before the lookup. Fixes: 740d798e8767 ("mptcp: remove id 0 address") Cc: stable@vger.kernel.org Reported-by: syzbot+55c2a5c871441261ed14@syzkaller.appspotmail.com Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/620 Suggested-by: Tao Cui Signed-off-by: Kalpan Jani Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260908-net-mptcp-misc-fixes-7-3-rc1-v2-4-df1de70348b6@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_kernel.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c index 424f1a7f9248..1a7750813235 100644 --- a/net/mptcp/pm_kernel.c +++ b/net/mptcp/pm_kernel.c @@ -1137,6 +1137,8 @@ static int mptcp_nl_remove_id_zero_address(struct net *net, while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) { struct sock *sk = (struct sock *)msk; struct mptcp_addr_info msk_local; + struct mptcp_addr_info anno_addr; + bool announced; if (list_empty(&msk->conn_list) || mptcp_pm_is_userspace(msk)) goto next; @@ -1146,7 +1148,13 @@ static int mptcp_nl_remove_id_zero_address(struct net *net, goto next; lock_sock(sk); + /* Drop a possibly pending ADD_ADDR for this address. */ + anno_addr = msk_local; + anno_addr.port = 0; + announced = mptcp_pm_announced_remove(msk, &anno_addr); spin_lock_bh(&msk->pm.lock); + if (announced) + msk->pm.add_addr_signaled--; mptcp_pm_remove_addr(msk, &list); mptcp_pm_rm_subflow(msk, &list); __mark_subflow_endp_available(msk, 0); From ab36b1a80942c78ddb04d006ff38aa7ed3ec0e5e Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Tue, 8 Sep 2026 16:07:10 +0200 Subject: [PATCH 1015/1198] mptcp: options: handle MPC data + csum reqd + no csum Before this modification, a remote peer could send an MP_CAPABLE with data, with the checksum flag set, but without adding the actual 2 bytes of checksum. As a result, uninitialised bytes could be used for the 'csum' field. That was not a critical issue, because this 'csum' field is only used to compare with the expected one, if previously negotiated in the 3WHS. Worst case, the checksum is likely wrong, a fallback is done without a reject if the negotiation was done earlier. That's OK. Yet, better to take the expected path with this case: only look at the checksum flag for MP_CAPABLEs not carrying a data-len. Such packet can be seen as a 3rd or 4th ACK. The RFC8684 mentions [1] that the 3rd packet should have the checksum flag set. When an MPC + ACK contains data, the checksum flag is redundant with the checksum field. It is not clear what should be done for the 4th ACK, nor if the flag has to be set if the checksum field is set. Therefore, it seems fine to only look at the presence of the checksum field, not to break the interaction with stacks that were not setting both. Note that linked to this checksum flag on the 3rd ACK, with the current implementation, we can have a situation where the SYN packets have no checksum flag, but the 3rd ACK has one, and this is the one that will be taken into account. First, that's clearly not directly linked to this patch, but Clashiko forced us to look at that. At the end, that seems fine to act like that: yes that's not how the negotiation should work, but being flexible without introducing side effects is also fine: fixing this would mean increasing the complexity, and that's not worth it. Fixes: 208e8f66926c ("mptcp: receive checksum for MP_CAPABLE with data") Cc: stable@vger.kernel.org Link: https://datatracker.ietf.org/doc/html/rfc8684#section-3.1-23 [1] Closes: https://netdev-ai.bots.linux.dev/sashiko/#/patchset/20260803-net-mptcp-misc-fixes-7-2-rc6-v2-0-b8f496d71664%40kernel.org?part=1 Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260908-net-mptcp-misc-fixes-7-3-rc1-v2-5-df1de70348b6@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/options.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/mptcp/options.c b/net/mptcp/options.c index b8318e030138..92f27b9e087a 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -93,7 +93,8 @@ static void mptcp_parse_option(const struct sk_buff *skb, * In other words, the only way for checksums not to be used * is if both hosts in their SYNs set A=0." */ - if (flags & MPTCP_CAP_CHECKSUM_REQD) + if ((flags & MPTCP_CAP_CHECKSUM_REQD) && + opsize < TCPOLEN_MPTCP_MPC_ACK_DATA) mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD; mp_opt->deny_join_id0 = !!(flags & MPTCP_CAP_DENY_JOIN_ID0); From 85c580b0d8590520ae00a15c29e9fb9c99427a3e Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 8 Sep 2026 16:07:11 +0200 Subject: [PATCH 1016/1198] mptcp: prevent race between disconnect() and rtx Sashiko noted that the two event can race, leading to inconsistent status. Prevent the race using the synchronous timer stop operation. Cc: stable@vger.kernel.org Fixes: b29fcfb54cd7 ("mptcp: full disconnect implementation") Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260908-net-mptcp-misc-fixes-7-3-rc1-v2-6-df1de70348b6@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index be59651e708e..d611af2eb74f 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3588,6 +3588,7 @@ static void mptcp_destroy_common(struct mptcp_sock *msk) static int mptcp_disconnect(struct sock *sk, int flags) { + struct inet_connection_sock *icsk = inet_csk(sk); struct mptcp_sock *msk = mptcp_sk(sk); /* We are on the fastopen error path. We can't call straight into the @@ -3600,8 +3601,13 @@ static int mptcp_disconnect(struct sock *sk, int flags) mptcp_check_listen_stop(sk); mptcp_set_state(sk, TCP_CLOSE); - mptcp_stop_rtx_timer(sk); - mptcp_stop_tout_timer(sk); + /* The later subflow close can not kick again the tout timer, + * as the msk is already in closed status. + */ + msk->timer_ival = icsk->icsk_rto_min; + sk_stop_timer_sync(sk, &sk->mptcp_retransmit_timer); + icsk->icsk_mtup.probe_timestamp = 0; + sk_stop_timer_sync(sk, &icsk->mptcp_tout_timer); mptcp_pm_connection_closed(msk); From 730444f094b12052916ebd7e14fe57bc3d47bf38 Mon Sep 17 00:00:00 2001 From: Gang Yan Date: Tue, 8 Sep 2026 16:07:12 +0200 Subject: [PATCH 1017/1198] selftests: mptcp: fix an UAF in mptcp_connect.c At the end of 'sock_connect_mptcp()', it calls 'freeaddrinfo(addr)', the 'peer' pointer (which points into 'addr') remains. Later, the main loop uses this peer pointer for reconnection attempts. If the memory has been freed and reused, the address data could be overwritten, resulting in an invalid remote address. This patch keeps the addrinfo list allocated for the whole process lifetime so "peer" remains valid across reconnects; the memory will be released at exit() time. Fixes: 05be5e273c84 ("selftests: mptcp: add disconnect tests") Cc: stable@vger.kernel.org Suggested-by: Paolo Abeni Signed-off-by: Gang Yan Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260908-net-mptcp-misc-fixes-7-3-rc1-v2-7-df1de70348b6@kernel.org Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/mptcp/mptcp_connect.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index ea4cb6c1bd5e..178d98d91fea 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -381,6 +381,9 @@ static int sock_connect_mptcp(const char * const remoteaddr, hints.ai_family = pf; + /* Keep the resolved address alive for the whole execution: it is + * used again when reconnecting, and will be released at exit time. + */ xgetaddrinfo(remoteaddr, port, &hints, &addr); for (a = addr; a; a = a->ai_next) { sock = socket(a->ai_family, a->ai_socktype, proto); @@ -421,7 +424,6 @@ static int sock_connect_mptcp(const char * const remoteaddr, sock = -1; } - freeaddrinfo(addr); if (sock != -1) SOCK_TEST_TCPULP(sock, proto); return sock; From f9f0068e8813d8c10d016b030fc3a320d0b6767c Mon Sep 17 00:00:00 2001 From: Qing Luo Date: Tue, 8 Sep 2026 16:07:13 +0200 Subject: [PATCH 1018/1198] mptcp: pm: userspace: fix address ID overflow When all MPTCP address IDs (1-255) are exhausted in the userspace PM, find_next_zero_bit() returns MPTCP_PM_MAX_ADDR_ID + 1 (256). This value overflows when stored in the u8 field e->addr.id, resulting in ID 0 being stored and the entry being incorrectly added to the list. ID 0 is reserved for the initial connection in MPTCP, so this overflow can cause address conflicts. Note: the in-kernel PM already has an 'endpoints == MPTCP_PM_MAX_ADDR_ID' check in mptcp_pm_nl_append_new_local_addr() that returns -ERANGE before reaching find_next_zero_bit(), preventing this overflow. So this fix only addresses the userspace PM path. Check the find_next_zero_bit() result against MPTCP_PM_MAX_ADDR_ID and return -ENOSPC if all IDs are truly exhausted. Move the ID allocation check before the memory allocation so that the error path does not need to free the allocated entry. Fixes: 4638de5aefe5 ("mptcp: handle local addrs announced by userspace PMs") Cc: stable@vger.kernel.org Signed-off-by: Qing Luo Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260908-net-mptcp-misc-fixes-7-3-rc1-v2-8-df1de70348b6@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_userspace.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index b94fbb483bf9..fab16d953dbf 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -69,6 +69,19 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, } if (!addr_match && !id_match) { + unsigned int id; + + if (!entry->addr.id && needs_id) { + id = find_next_zero_bit(id_bitmap, + MPTCP_PM_MAX_ADDR_ID + 1, 1); + if (id > MPTCP_PM_MAX_ADDR_ID) { + ret = -ENOSPC; + goto append_err; + } + } else { + id = entry->addr.id; + } + /* Memory for the entry is allocated from the * sock option buffer. */ @@ -78,10 +91,7 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, goto append_err; } - if (!e->addr.id && needs_id) - e->addr.id = find_next_zero_bit(id_bitmap, - MPTCP_PM_MAX_ADDR_ID + 1, - 1); + e->addr.id = id; list_add_tail_rcu(&e->list, &msk->pm.userspace_pm_local_addr_list); msk->pm.local_addr_used++; ret = e->addr.id; From f968190c0b42ea2004dc1426359a53ec365a7a37 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Tue, 8 Sep 2026 16:07:14 +0200 Subject: [PATCH 1019/1198] mptcp: pm: reset retrans_time when ADD_ADDR entry is reused When an ADD_ADDR entry is reused, the timer is re-armed, because the goal is to re-announce an ADD_ADDR, and eventually retransmit it if needed. In this case, the retransmission counter should be reset as well, so the re-announced address gets its retransmissions back instead of relying on what was left before, and possibly not being able to retransmit it. Fixes: 304ab97f4c7c ("mptcp: allow ADD_ADDR reissuance by userspace PMs") Cc: stable@vger.kernel.org Link: https://netdev-ai.bots.linux.dev/sashiko/#/patchset/20260803-net-mptcp-misc-fixes-7-2-rc6-v2-0-b8f496d71664%40kernel.org?part=4 Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260908-net-mptcp-misc-fixes-7-3-rc1-v2-9-df1de70348b6@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 8b68868255c5..b0b71adefb8f 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -462,10 +462,10 @@ bool mptcp_pm_announced_alloc(struct mptcp_sock *msk, add_entry->addr = *addr; add_entry->sock = msk; - add_entry->retrans_times = 0; timer_setup(&add_entry->timer, mptcp_pm_add_addr_timer, 0); reset_timer: + add_entry->retrans_times = 0; add_entry->timer_done = false; timeout = mptcp_adjust_add_addr_timeout(msk); if (timeout) From caa4a79f74f32084ce28aee8653bc04df745970d Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 8 Sep 2026 16:07:15 +0200 Subject: [PATCH 1020/1198] mptcp: remove unneeded READ_ONCE() annotation The subflow->fully_established flag is always written under the subflow socket lock. Reading such value under the same lock does not require any ONCE annotation. Fixes: 581c8cbfa934 ("mptcp: annotate data-races around subflow->fully_established") Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260908-net-mptcp-misc-fixes-7-3-rc1-v2-10-df1de70348b6@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/options.c | 4 ++-- net/mptcp/protocol.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 92f27b9e087a..196a46e7467d 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -530,7 +530,7 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, return false; /* MPC/MPJ needed only on 3rd ack packet, DATA_FIN and TCP shutdown take precedence */ - if (READ_ONCE(subflow->fully_established) || snd_data_fin_enable || + if (subflow->fully_established || snd_data_fin_enable || subflow->snd_isn != TCP_SKB_CB(skb)->seq || sk->sk_state != TCP_ESTABLISHED) return false; @@ -981,7 +981,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, /* here we can process OoO, in-window pkts, only in-sequence 4th ack * will make the subflow fully established */ - if (likely(READ_ONCE(subflow->fully_established))) { + if (likely(subflow->fully_established)) { /* on passive sockets, check for 3rd ack retransmission * note that msk is always set by subflow_syn_recv_sock() * for mp_join subflows diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index d611af2eb74f..302936ff456a 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3886,7 +3886,7 @@ static void schedule_3rdack_retransmission(struct sock *ssk) struct tcp_sock *tp = tcp_sk(ssk); unsigned long timeout; - if (READ_ONCE(mptcp_subflow_ctx(ssk)->fully_established)) + if (mptcp_subflow_ctx(ssk)->fully_established) return; /* reschedule with a timeout above RTT, as we must look only for drop */ From e1a56368eac18b3b4b956b794526e8713c48a0ec Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Tue, 8 Sep 2026 16:07:16 +0200 Subject: [PATCH 1021/1198] selftests: mptcp: lib: dump nstat for the right test In case of errors, mptcp_lib_pr_nstat is called to dump the nstat counters, but for some tests, it was dumping the counters for all subtests, not just the current one. That's an issue for tests that don't recreate the netns for each subtest, e.g. mptcp_connect.sh. In this case, 'nstat -a' will look at the absolute counters since the creation of the netns, making debugging harder. Instead, it should dump the counters for the current test, by using the history recorded in /tmp/.nstat if available, and not using '-a' which was dumping the absolute values instead of calculating increments. While at it, rename the previous 'hist' variable to 'cache' as it was used to look at the cache, not the nstat history. Fixes: 658e53141780 ("selftests: mptcp: join: dump stats from history") Cc: stable@vger.kernel.org Reviewed-by: Geliang Tang Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260908-net-mptcp-misc-fixes-7-3-rc1-v2-11-df1de70348b6@kernel.org Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/mptcp/mptcp_lib.sh | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index 5ef6033775c8..da1da414c30f 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -108,12 +108,14 @@ mptcp_lib_pr_info() { mptcp_lib_pr_nstat() { local ns="${1}" - local hist="/tmp/${ns}.out" + local cache="/tmp/${ns}.out" + local hist="/tmp/${ns}.nstat" - if [ -f "${hist}" ]; then - awk '$2 != 0 { print " "$0 }' "${hist}" + if [ -f "${cache}" ]; then + awk '$2 != 0 { print " "$0 }' "${cache}" else - ip netns exec "${ns}" nstat -as | grep Tcp + NSTAT_HISTORY="${hist}" ip netns exec "${ns}" nstat -s | + grep Tcp fi } From d23c41366e85f149b48323d66adc36c4a9f18cbd Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Tue, 8 Sep 2026 16:07:17 +0200 Subject: [PATCH 1022/1198] selftests: mptcp: lib: get counters for the right test When the value for a MIB counter is required, mptcp_lib_get_counter is called. It tries to use the cache, if available. If not it falls back to calling 'nstat' directly by looking at the absolute counters. That's an issue for tests that don't recreate the netns for each subtest. In this case, 'nstat -a' will look at the counters for the netns. Instead, it should look at the increment for the current test, by using the history recorded in /tmp/.nstat, if available, and not using '-a' which was dumping the absolute values. While at it, rename the previous 'hist' variable to 'cache' as it was used to look at the cache, not the nstat history. Fixes: 71388a9f331d ("selftests: mptcp: lib: get counters from nstat history") Cc: stable@vger.kernel.org Reviewed-by: Geliang Tang Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260908-net-mptcp-misc-fixes-7-3-rc1-v2-12-df1de70348b6@kernel.org Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/mptcp/mptcp_lib.sh | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index da1da414c30f..b9d14647f401 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -416,19 +416,21 @@ mptcp_lib_nstat_get() { } # $1: ns, $2: MIB counter -# Get the counter from the history (mptcp_lib_nstat_{init,get}()) if available. -# If not, get the counter from nstat ignoring any history. +# Get the counter from the cache (mptcp_lib_nstat_{init,get}()) if available. +# If not, get the counter from nstat ignoring any cache, but using the history. mptcp_lib_get_counter() { local ns="${1}" local counter="${2}" - local hist="/tmp/${ns}.out" + local cache="/tmp/${ns}.out" + local hist="/tmp/${ns}.nstat" local count - if [[ -s "${hist}" && "${counter}" == *"Tcp"* ]]; then - count=$(awk "/^${counter} / {print \$2; exit}" "${hist}") + if [[ -s "${cache}" && "${counter}" == *"Tcp"* ]]; then + count=$(awk "/^${counter} / {print \$2; exit}" "${cache}") else - count=$(ip netns exec "${ns}" nstat -asz "${counter}" | - awk 'NR==1 {next} {print $2}') + count=$(NSTAT_HISTORY="${hist}" ip netns exec "${ns}" \ + nstat -sz "${counter}" | + awk 'NR==1 {next} {print $2}') fi if [ -z "${count}" ]; then mptcp_lib_fail_if_expected_feature "${counter} counter" From b110f1dd6cb6a9930503354a01a315e0a821eaa7 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Tue, 8 Sep 2026 16:07:18 +0200 Subject: [PATCH 1023/1198] mptcp: options: fix uninit-value in mptcp_write_data_fin When sending a DATA_FIN without data, and because the DATA_FIN occupies 1 octet of the connection-level sequence space [1], it is then required to add a DSS mapping with specific values. If the checksum has been negotiated, it also needs to be computed, and included in the outgoing packet, and thus the initial csum data needs to be reset to 0 as well. This is no longer the case since commit cfcceb7a39fc ("tcp: shrink per-packet memset in __tcp_transmit_skb()"), because the whole ext_copy structure is no longer zeroed by default. This seems to be the only case where use_map is changed and set afterwards, so initialising the csum field only in this case, along with other fields for this specific case. Fixes: cfcceb7a39fc ("tcp: shrink per-packet memset in __tcp_transmit_skb()") Cc: stable@vger.kernel.org Link: https://datatracker.ietf.org/doc/html/rfc8684#section-3.3.3 [1] Link: https://sashiko.dev/#/patchset/20260812-net-next-mptcp-misc-feat-7-3-v1-0-1905a818f6cb%40kernel.org?part=2 Reviewed-by: Geliang Tang Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260908-net-mptcp-misc-fixes-7-3-rc1-v2-13-df1de70348b6@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/options.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 196a46e7467d..ce0de02f5a3a 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -612,6 +612,7 @@ static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow, ext->data_seq = data_fin_tx_seq; ext->subflow_seq = 0; ext->data_len = 1; + ext->csum = 0; } else if (ext->data_seq + ext->data_len == data_fin_tx_seq) { /* If there's an existing DSS mapping and it is the * final mapping, DATA_FIN consumes 1 additional byte of From a4257a91af7a77a8347d33413ec9e54106f7ff48 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 8 Sep 2026 16:07:19 +0200 Subject: [PATCH 1024/1198] mptcp: being below memory limit is a likely() condition The current compiler hint annotation is wrong, due to inverted logic in the previous revision of the relevant code. Fixes: e468d371180d ("mptcp: implemented OoO queue pruning") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260908-net-mptcp-misc-fixes-7-3-rc1-v2-14-df1de70348b6@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 302936ff456a..4309fca6b119 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -289,8 +289,8 @@ static void mptcp_prune_ofo_queue(struct sock *sk, */ static bool mptcp_can_ingest(const struct sock *sk) { - return unlikely(sk_rmem_alloc_get(sk) <= READ_ONCE(sk->sk_rcvbuf)) || - __mptcp_check_fallback(mptcp_sk(sk)); + return likely(sk_rmem_alloc_get(sk) <= READ_ONCE(sk->sk_rcvbuf)) || + __mptcp_check_fallback(mptcp_sk(sk)); } static bool mptcp_try_rmem_schedule(struct sock *sk, const struct sk_buff *skb) From f01b8275745efe611284f6c3628099a81a421f0d Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 8 Sep 2026 16:07:20 +0200 Subject: [PATCH 1025/1198] mptcp: avoid pruning for OoW data Pruning is expansive and destructive, do it only when we expect to accept the skb triggering the cleanup. Fixes: e468d371180d ("mptcp: implemented OoO queue pruning") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260908-net-mptcp-misc-fixes-7-3-rc1-v2-15-df1de70348b6@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 4309fca6b119..0098e2830931 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -313,12 +313,6 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb) u64 seq, end_seq, max_seq; struct sk_buff *skb1; - if (!mptcp_try_rmem_schedule(sk, skb)) { - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED); - mptcp_drop(sk, skb); - return; - } - seq = MPTCP_SKB_CB(skb)->map_seq; end_seq = MPTCP_SKB_CB(skb)->end_seq; max_seq = atomic64_read(&msk->rcv_wnd_sent); @@ -335,6 +329,12 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb) return; } + if (!mptcp_try_rmem_schedule(sk, skb)) { + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED); + mptcp_drop(sk, skb); + return; + } + p = &msk->out_of_order_queue.rb_node; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOQUEUE); if (RB_EMPTY_ROOT(&msk->out_of_order_queue)) { From 0fa37512eb747e4ffdcf367274f9e72845f1bca4 Mon Sep 17 00:00:00 2001 From: David Arcari Date: Thu, 3 Sep 2026 14:20:29 -0400 Subject: [PATCH 1026/1198] watchdog: fix hrtimer start when pretimeout is zero Per the watchdog API, a pretimeout value of 0 disables the feature. However, watchdog_hrtimer_pretimeout_start() fails to verify if the pretimeout is non-zero before arming the timer. This omission inadvertently starts the software pretimeout timer, which could result in the pretimeout handler executing incorrectly when the watchdog timeout is reached. Fix this by adding a check for wdd->pretimeout before calling hrtimer_start(), ensuring the disabled state is respected. Fixes: 7b7d2fdc8c3e ("watchdog: Add hrtimer-based pretimeout feature") Signed-off-by: David Arcari Link: https://patch.msgid.link/20260903182029.936030-1-darcari@redhat.com Signed-off-by: Guenter Roeck --- drivers/watchdog/watchdog_hrtimer_pretimeout.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/watchdog/watchdog_hrtimer_pretimeout.c b/drivers/watchdog/watchdog_hrtimer_pretimeout.c index fbc7eecd8b20..49a05ea60c97 100644 --- a/drivers/watchdog/watchdog_hrtimer_pretimeout.c +++ b/drivers/watchdog/watchdog_hrtimer_pretimeout.c @@ -30,6 +30,7 @@ void watchdog_hrtimer_pretimeout_init(struct watchdog_device *wdd) void watchdog_hrtimer_pretimeout_start(struct watchdog_device *wdd) { if (!(wdd->info->options & WDIOF_PRETIMEOUT) && + wdd->pretimeout && !watchdog_pretimeout_invalid(wdd, wdd->pretimeout)) hrtimer_start(&wdd->wd_data->pretimeout_timer, ktime_set(wdd->timeout - wdd->pretimeout, 0), From 3c73a37f5e40972ce26d8eeb98e8b938d719b069 Mon Sep 17 00:00:00 2001 From: Tzung-Bi Shih Date: Sat, 29 Aug 2026 00:13:41 +0800 Subject: [PATCH 1027/1198] watchdog: msc313e: Avoid division by zero clk_get_rate() could return 0. Avoid a division by zero panic. Fixes: e9800b799464 ("watchdog: Add Mstar MSC313e WDT driver") Signed-off-by: Tzung-Bi Shih Link: https://patch.msgid.link/20260828161348.13212-3-tzungbi@kernel.org Signed-off-by: Guenter Roeck --- drivers/watchdog/msc313e_wdt.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/watchdog/msc313e_wdt.c b/drivers/watchdog/msc313e_wdt.c index f69d66971c41..c3018b970164 100644 --- a/drivers/watchdog/msc313e_wdt.c +++ b/drivers/watchdog/msc313e_wdt.c @@ -97,6 +97,7 @@ static int msc313e_wdt_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct msc313e_wdt_priv *priv; + unsigned long rate; priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); if (!priv) @@ -116,7 +117,10 @@ static int msc313e_wdt_probe(struct platform_device *pdev) priv->wdev.ops = &msc313e_wdt_ops, priv->wdev.parent = dev; priv->wdev.min_timeout = MSC313E_WDT_MIN_TIMEOUT; - priv->wdev.max_timeout = U32_MAX / clk_get_rate(priv->clk); + rate = clk_get_rate(priv->clk); + if (!rate) + return -EINVAL; + priv->wdev.max_timeout = U32_MAX / rate; priv->wdev.timeout = MSC313E_WDT_DEFAULT_TIMEOUT; /* If the period is non-zero the WDT is running */ From 3db30f315935c2fb0d95f46b7a593b5b4d3ec3d0 Mon Sep 17 00:00:00 2001 From: Tzung-Bi Shih Date: Sat, 29 Aug 2026 00:13:42 +0800 Subject: [PATCH 1028/1198] watchdog: msc313e: Fix clock leak and spurious timer in settimeout() msc313e_wdt_settimeout() unconditionally calls msc313e_wdt_start() which introduces two severe bugs: 1. If the watchdog is already active, calling start() again will increase the reference count of the clock again. However stop() is only called once, the reference count is unbalance. 2. If the watchdog is stopped, calling settimeout() will start the hardware timer accidentally. Factor out the register-writing logic into a helper function. Only call it in settimeout() if the watchdog is running. Otherwise, simply update `wdev->timeout`. Fixes: e9800b799464 ("watchdog: Add Mstar MSC313e WDT driver") Signed-off-by: Tzung-Bi Shih Link: https://patch.msgid.link/20260828161348.13212-4-tzungbi@kernel.org Signed-off-by: Guenter Roeck --- drivers/watchdog/msc313e_wdt.c | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) diff --git a/drivers/watchdog/msc313e_wdt.c b/drivers/watchdog/msc313e_wdt.c index c3018b970164..8ce24df8e338 100644 --- a/drivers/watchdog/msc313e_wdt.c +++ b/drivers/watchdog/msc313e_wdt.c @@ -31,20 +31,26 @@ struct msc313e_wdt_priv { struct clk *clk; }; +static void msc313e_wdt_set_hw_timeout(struct msc313e_wdt_priv *priv, + unsigned int timeout) +{ + u32 t = timeout * clk_get_rate(priv->clk); + + writew(t & 0xffff, priv->base + REG_WDT_MAX_PRD_L); + writew((t >> 16) & 0xffff, priv->base + REG_WDT_MAX_PRD_H); + writew(1, priv->base + REG_WDT_CLR); +} + static int msc313e_wdt_start(struct watchdog_device *wdev) { struct msc313e_wdt_priv *priv = watchdog_get_drvdata(wdev); - u32 timeout; int err; err = clk_prepare_enable(priv->clk); if (err) return err; - timeout = wdev->timeout * clk_get_rate(priv->clk); - writew(timeout & 0xffff, priv->base + REG_WDT_MAX_PRD_L); - writew((timeout >> 16) & 0xffff, priv->base + REG_WDT_MAX_PRD_H); - writew(1, priv->base + REG_WDT_CLR); + msc313e_wdt_set_hw_timeout(priv, wdev->timeout); return 0; } @@ -69,9 +75,13 @@ static int msc313e_wdt_stop(struct watchdog_device *wdev) static int msc313e_wdt_settimeout(struct watchdog_device *wdev, unsigned int new_time) { + struct msc313e_wdt_priv *priv = watchdog_get_drvdata(wdev); + wdev->timeout = new_time; - return msc313e_wdt_start(wdev); + if (watchdog_hw_running(wdev) || watchdog_active(wdev)) + msc313e_wdt_set_hw_timeout(priv, wdev->timeout); + return 0; } static const struct watchdog_info msc313e_wdt_ident = { From 3db2df24e7f11fb117718f6abe326628d91bc500 Mon Sep 17 00:00:00 2001 From: Tzung-Bi Shih Date: Sat, 29 Aug 2026 00:13:43 +0800 Subject: [PATCH 1029/1198] watchdog: msc313e: Enable clock before accessing hardware registers msc313e_wdt_probe() reads from hardware registers without ensuring the required clock is enabled. Furthermore, if the bootloader leaves the watchdog running, msc313e_wdt_probe() sets WDOG_HW_RUNNING without increasing the clock's reference count. While the clock is currently supplied as a fixed clock by the device tree (`xtal_div2` in arch/arm/boot/dts/sigmastar/mstar-v7.dtsi) which masks the physical issue, this still violates the API usage. Call clk_prepare_enable() before reading WDT registers. If the WDT is running, leave the clock enabled so the CCF reference counter is balanced. Fixes: ffd264bd152c ("watchdog: msc313e: Check if the WDT was running at boot") Signed-off-by: Tzung-Bi Shih Link: https://patch.msgid.link/20260828161348.13212-5-tzungbi@kernel.org Signed-off-by: Guenter Roeck --- drivers/watchdog/msc313e_wdt.c | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) diff --git a/drivers/watchdog/msc313e_wdt.c b/drivers/watchdog/msc313e_wdt.c index 8ce24df8e338..7c4593566781 100644 --- a/drivers/watchdog/msc313e_wdt.c +++ b/drivers/watchdog/msc313e_wdt.c @@ -108,6 +108,7 @@ static int msc313e_wdt_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct msc313e_wdt_priv *priv; unsigned long rate; + int ret; priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); if (!priv) @@ -133,9 +134,21 @@ static int msc313e_wdt_probe(struct platform_device *pdev) priv->wdev.max_timeout = U32_MAX / rate; priv->wdev.timeout = MSC313E_WDT_DEFAULT_TIMEOUT; + ret = clk_prepare_enable(priv->clk); + if (ret) + return ret; + /* If the period is non-zero the WDT is running */ - if (readw(priv->base + REG_WDT_MAX_PRD_L) | (readw(priv->base + REG_WDT_MAX_PRD_H) << 16)) + if (readw(priv->base + REG_WDT_MAX_PRD_L) | (readw(priv->base + REG_WDT_MAX_PRD_H) << 16)) { set_bit(WDOG_HW_RUNNING, &priv->wdev.status); + /* + * Keep the clock enabled. The watchdog core will skip the next + * start() and a future stop() will balance the CCF reference + * count. + */ + } else { + clk_disable_unprepare(priv->clk); + } watchdog_set_drvdata(&priv->wdev, priv); platform_set_drvdata(pdev, priv); @@ -144,7 +157,13 @@ static int msc313e_wdt_probe(struct platform_device *pdev) watchdog_stop_on_reboot(&priv->wdev); watchdog_stop_on_unregister(&priv->wdev); - return devm_watchdog_register_device(dev, &priv->wdev); + ret = devm_watchdog_register_device(dev, &priv->wdev); + + /* If the WDT is running and anything goes wrong, disable the clock. */ + if (ret && test_bit(WDOG_HW_RUNNING, &priv->wdev.status)) + clk_disable_unprepare(priv->clk); + + return ret; } static int __maybe_unused msc313e_wdt_suspend(struct device *dev) From 4f6817c9eff4aa1078e16652d82e4b7ef4ffae3e Mon Sep 17 00:00:00 2001 From: Tzung-Bi Shih Date: Sat, 29 Aug 2026 00:13:44 +0800 Subject: [PATCH 1030/1198] watchdog: msc313e: Fix spurious reset on suspend If the hardware watchdog was started by the bootloader and the device is suspended before userspace opens it, the ping worker (from watchdog core) is frozen and the active hardware timer continues running. This leads to a spurious system reset. Check both watchdog_active() and watchdog_hw_running() when deciding whether to start or stop the watchdog during suspend and resume. Additionally, call watchdog_stop_ping_on_suspend() to ensure the ping worker be correctly paused and restarted during suspend and resume. Fixes: ffd264bd152c ("watchdog: msc313e: Check if the WDT was running at boot") Signed-off-by: Tzung-Bi Shih Link: https://patch.msgid.link/20260828161348.13212-6-tzungbi@kernel.org Signed-off-by: Guenter Roeck --- drivers/watchdog/msc313e_wdt.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/watchdog/msc313e_wdt.c b/drivers/watchdog/msc313e_wdt.c index 7c4593566781..c7d558fefc86 100644 --- a/drivers/watchdog/msc313e_wdt.c +++ b/drivers/watchdog/msc313e_wdt.c @@ -156,6 +156,7 @@ static int msc313e_wdt_probe(struct platform_device *pdev) watchdog_init_timeout(&priv->wdev, timeout, dev); watchdog_stop_on_reboot(&priv->wdev); watchdog_stop_on_unregister(&priv->wdev); + watchdog_stop_ping_on_suspend(&priv->wdev); ret = devm_watchdog_register_device(dev, &priv->wdev); @@ -170,7 +171,7 @@ static int __maybe_unused msc313e_wdt_suspend(struct device *dev) { struct msc313e_wdt_priv *priv = dev_get_drvdata(dev); - if (watchdog_active(&priv->wdev)) + if (watchdog_active(&priv->wdev) || watchdog_hw_running(&priv->wdev)) msc313e_wdt_stop(&priv->wdev); return 0; @@ -180,7 +181,7 @@ static int __maybe_unused msc313e_wdt_resume(struct device *dev) { struct msc313e_wdt_priv *priv = dev_get_drvdata(dev); - if (watchdog_active(&priv->wdev)) + if (watchdog_active(&priv->wdev) || watchdog_hw_running(&priv->wdev)) msc313e_wdt_start(&priv->wdev); return 0; From ab390021b2a3bb4cc875f28a6f76d13de90d7457 Mon Sep 17 00:00:00 2001 From: Tzung-Bi Shih Date: Sat, 29 Aug 2026 00:13:45 +0800 Subject: [PATCH 1031/1198] watchdog: msc313e: Fix undefined behavior readw() returns a u16. Left shifting a u16 by 16 bits yields undefined behavior. Cast to u32 explicitly before the shift. Fixes: ffd264bd152c ("watchdog: msc313e: Check if the WDT was running at boot") Signed-off-by: Tzung-Bi Shih Link: https://patch.msgid.link/20260828161348.13212-7-tzungbi@kernel.org Signed-off-by: Guenter Roeck --- drivers/watchdog/msc313e_wdt.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/watchdog/msc313e_wdt.c b/drivers/watchdog/msc313e_wdt.c index c7d558fefc86..e28261c7a8d4 100644 --- a/drivers/watchdog/msc313e_wdt.c +++ b/drivers/watchdog/msc313e_wdt.c @@ -31,6 +31,16 @@ struct msc313e_wdt_priv { struct clk *clk; }; +static u32 msc313e_wdt_get_hw_timeout(struct msc313e_wdt_priv *priv) +{ + u16 low, high; + + low = readw(priv->base + REG_WDT_MAX_PRD_L); + high = readw(priv->base + REG_WDT_MAX_PRD_H); + + return ((u32)high << 16) | low; +} + static void msc313e_wdt_set_hw_timeout(struct msc313e_wdt_priv *priv, unsigned int timeout) { @@ -139,7 +149,7 @@ static int msc313e_wdt_probe(struct platform_device *pdev) return ret; /* If the period is non-zero the WDT is running */ - if (readw(priv->base + REG_WDT_MAX_PRD_L) | (readw(priv->base + REG_WDT_MAX_PRD_H) << 16)) { + if (msc313e_wdt_get_hw_timeout(priv)) { set_bit(WDOG_HW_RUNNING, &priv->wdev.status); /* * Keep the clock enabled. The watchdog core will skip the next From 01504d14e47b34779911250dd308a03f6ef681c2 Mon Sep 17 00:00:00 2001 From: Tzung-Bi Shih Date: Sat, 29 Aug 2026 00:13:46 +0800 Subject: [PATCH 1032/1198] watchdog: msc313e: Sync timeout value if WDT was running at boot If WDT was running at boot, the hardware timeout might be set to values other than the final software timeout. To be consistent, set the hardware timeout to match the final software timeout (i.e., after watchdog_init_timeout()) if WDT was running. Fixes: ffd264bd152c ("watchdog: msc313e: Check if the WDT was running at boot") Signed-off-by: Tzung-Bi Shih Link: https://patch.msgid.link/20260828161348.13212-8-tzungbi@kernel.org Signed-off-by: Guenter Roeck --- drivers/watchdog/msc313e_wdt.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/drivers/watchdog/msc313e_wdt.c b/drivers/watchdog/msc313e_wdt.c index e28261c7a8d4..4a5cce2a16b1 100644 --- a/drivers/watchdog/msc313e_wdt.c +++ b/drivers/watchdog/msc313e_wdt.c @@ -144,12 +144,21 @@ static int msc313e_wdt_probe(struct platform_device *pdev) priv->wdev.max_timeout = U32_MAX / rate; priv->wdev.timeout = MSC313E_WDT_DEFAULT_TIMEOUT; + watchdog_set_drvdata(&priv->wdev, priv); + platform_set_drvdata(pdev, priv); + + watchdog_init_timeout(&priv->wdev, timeout, dev); + watchdog_stop_on_reboot(&priv->wdev); + watchdog_stop_on_unregister(&priv->wdev); + watchdog_stop_ping_on_suspend(&priv->wdev); + ret = clk_prepare_enable(priv->clk); if (ret) return ret; /* If the period is non-zero the WDT is running */ if (msc313e_wdt_get_hw_timeout(priv)) { + msc313e_wdt_set_hw_timeout(priv, priv->wdev.timeout); set_bit(WDOG_HW_RUNNING, &priv->wdev.status); /* * Keep the clock enabled. The watchdog core will skip the next @@ -160,14 +169,6 @@ static int msc313e_wdt_probe(struct platform_device *pdev) clk_disable_unprepare(priv->clk); } - watchdog_set_drvdata(&priv->wdev, priv); - platform_set_drvdata(pdev, priv); - - watchdog_init_timeout(&priv->wdev, timeout, dev); - watchdog_stop_on_reboot(&priv->wdev); - watchdog_stop_on_unregister(&priv->wdev); - watchdog_stop_ping_on_suspend(&priv->wdev); - ret = devm_watchdog_register_device(dev, &priv->wdev); /* If the WDT is running and anything goes wrong, disable the clock. */ From b824476c56a153934c67c9e0f873e1fd967743d6 Mon Sep 17 00:00:00 2001 From: Yilin Zhang Date: Sat, 5 Sep 2026 00:28:00 +0800 Subject: [PATCH 1033/1198] inet: frags: invalidate queues before flushing them fqdir_pre_exit() flushes the skbs from incomplete queues without changing their completion state. A fragment which found a queue before high_thresh was cleared can then acquire the queue lock and reuse stale reassembly metadata. A queue concurrently killed after fqdir->dead is set can instead become INET_FRAG_COMPLETE|INET_FRAG_HASH_DEAD while still holding its old skbs; skipping it because it is complete leaves those references behind until asynchronous fqdir teardown. For IPv6, stale metadata can make ip6_frag_reasm() use the old nhoffset with a new skb and access memory out of bounds. The resulting heap corruption can be leveraged for local privilege escalation when unprivileged network namespaces are available. Unflushed fragments can also keep conntrack references alive after the conntrack per-net cleanup point. Kill each incomplete queue, then flush every queue still owned by the dying rhashtable. HASH_DEAD identifies that ownership, while complete queues without it are already owned by another destroy path and must be left alone. Releasing a timer reference removed by inet_frag_kill() is deferred to inet_frag_putn(), after the queue lock is dropped. KASAN report: BUG: KASAN: slab-out-of-bounds in ipv6_frag_rcv (net/ipv6/reassembly.c:289 (discriminator 2) net/ipv6/reassembly.c:229 (discriminator 2) net/ipv6/reassembly.c:391 (discriminator 2)) Write of size 1 at addr ff110001039c6e00 by task poc/771 Call Trace: ? ipv6_frag_rcv (net/ipv6/reassembly.c:289 (discriminator 2) net/ipv6/reassembly.c:229 (discriminator 2) net/ipv6/reassembly.c:391 (discriminator 2)) ipv6_frag_rcv (net/ipv6/reassembly.c:289 (discriminator 2) net/ipv6/reassembly.c:229 (discriminator 2) net/ipv6/reassembly.c:391 (discriminator 2)) ip6_protocol_deliver_rcu (net/ipv6/ip6_input.c:479 (discriminator 5)) ip6_input_finish (net/ipv6/ip6_input.c:534) ipv6_rcv (include/net/dst.h:480 (discriminator 3) net/ipv6/ip6_input.c:119 (discriminator 3) net/ipv6/ip6_input.c:109 (discriminator 3) include/linux/netfilter.h:325 (discriminator 3) include/linux/netfilter.h:319 (discriminator 3) net/ipv6/ip6_input.c:351 (discriminator 3)) packet_sendmsg (net/packet/af_packet.c:3110 net/packet/af_packet.c:3142) __x64_sys_sendmmsg (net/socket.c:2883 net/socket.c:2880 net/socket.c:2880) The buggy address belongs to the object at ff110001039c6b40 which belongs to the cache skbuff_small_head of size 704 The buggy address is located 0 bytes to the right of allocated 704-byte region [ff110001039c6b40, ff110001039c6e00) BUG: KASAN: slab-out-of-bounds in ip6_protocol_deliver_rcu (net/ipv6/ip6_input.c:423 (discriminator 1)) Read of size 1 at addr ff110001039c6e08 by task poc/771 Call Trace: ? ip6_protocol_deliver_rcu (net/ipv6/ip6_input.c:423 (discriminator 1)) ip6_protocol_deliver_rcu (net/ipv6/ip6_input.c:423 (discriminator 1)) ip6_input_finish (net/ipv6/ip6_input.c:534) ipv6_rcv (include/net/dst.h:480 (discriminator 3) net/ipv6/ip6_input.c:119 (discriminator 3) net/ipv6/ip6_input.c:109 (discriminator 3) include/linux/netfilter.h:325 (discriminator 3) include/linux/netfilter.h:319 (discriminator 3) net/ipv6/ip6_input.c:351 (discriminator 3)) packet_sendmsg (net/packet/af_packet.c:3110 net/packet/af_packet.c:3142) __x64_sys_sendmmsg (net/socket.c:2883 net/socket.c:2880 net/socket.c:2880) packet_sendmsg (net/packet/af_packet.c:2959 net/packet/af_packet.c:3053 net/packet/af_packet.c:3142) __x64_sys_sendmmsg (net/socket.c:2883 net/socket.c:2880 net/socket.c:2880) The buggy address belongs to the object at ff110001039c6b40 which belongs to the cache skbuff_small_head of size 704 The buggy address is located 8 bytes to the right of allocated 704-byte region [ff110001039c6b40, ff110001039c6e00) Fixes: 006a5035b495 ("inet: frags: flush pending skbs in fqdir_pre_exit()") Cc: stable@vger.kernel.org Reported-by: Kimi Security Team Tested-by: Weiming Shi Reviewed-by: Eric Dumazet Signed-off-by: Yilin Zhang Link: https://patch.msgid.link/20260904162800.1095662-1-yilinzhang@moonshot.ai Signed-off-by: Jakub Kicinski --- net/ipv4/inet_fragment.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index c17e57ec7d5c..b286ee429da8 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -235,6 +235,8 @@ void fqdir_pre_exit(struct fqdir *fqdir) rhashtable_walk_start(&hti); while ((fq = rhashtable_walk_next(&hti))) { + int refs = 0; + if (IS_ERR(fq)) { if (PTR_ERR(fq) != -EAGAIN) break; @@ -242,8 +244,12 @@ void fqdir_pre_exit(struct fqdir *fqdir) } spin_lock_bh(&fq->lock); if (!(fq->flags & INET_FRAG_COMPLETE)) + inet_frag_kill(fq, &refs); + + if (fq->flags & INET_FRAG_HASH_DEAD) inet_frag_queue_flush(fq, 0); spin_unlock_bh(&fq->lock); + inet_frag_putn(fq, refs); } rhashtable_walk_stop(&hti); From 59fb389ad6bf50916189e56dafcd225ab977f874 Mon Sep 17 00:00:00 2001 From: "Jan Havran (Advantech Czech)" Date: Mon, 7 Sep 2026 15:48:18 +0200 Subject: [PATCH 1034/1198] net: dsa: lantiq_gswip: fix GSWIP_MDIO_PHY_FCONTX_EN value Per the GSW145 data sheet, the FCONTX (bits 8:7) and FCONRX (bits 6:5) flow-control fields of the PHY_ADDR_n register both encode 00 = AUTO, 01 = EN, 10 = reserved, 11 = DIS. GSWIP_MDIO_PHY_FCONTX_EN was 0x0100, i.e. field value 10 (the reserved encoding), instead of 0x0080 (01 = EN); FCONRX_EN is already 0x0020 (01). Enabling tx flow control therefore wrote the reserved value. Set FCONTX_EN to 0x0080. The register is shared by all supported parts. Fixes: 14fceff4771e ("net: dsa: Add Lantiq / Intel DSA driver for vrx200") Signed-off-by: Jan Havran (Advantech Czech) Reviewed-by: Daniel Golle Reviewed-by: Maxime Chevallier Link: https://patch.msgid.link/20260907134818.16670-4-havran.jan@email.cz Signed-off-by: Jakub Kicinski --- drivers/net/dsa/lantiq/lantiq_gswip.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/dsa/lantiq/lantiq_gswip.h b/drivers/net/dsa/lantiq/lantiq_gswip.h index bc3686faad0d..0b75be14dc10 100644 --- a/drivers/net/dsa/lantiq/lantiq_gswip.h +++ b/drivers/net/dsa/lantiq/lantiq_gswip.h @@ -42,7 +42,7 @@ #define GSWIP_MDIO_PHY_FDUP_DIS 0x0600 #define GSWIP_MDIO_PHY_FCONTX_MASK 0x0180 #define GSWIP_MDIO_PHY_FCONTX_AUTO 0x0000 -#define GSWIP_MDIO_PHY_FCONTX_EN 0x0100 +#define GSWIP_MDIO_PHY_FCONTX_EN 0x0080 #define GSWIP_MDIO_PHY_FCONTX_DIS 0x0180 #define GSWIP_MDIO_PHY_FCONRX_MASK 0x0060 #define GSWIP_MDIO_PHY_FCONRX_AUTO 0x0000 From 66ef5adb75446627f8b6c26cd04f2adc86d4de56 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sat, 5 Sep 2026 15:02:32 +0200 Subject: [PATCH 1035/1198] net: ks8851: Fix receiver error in 100BASE-TX mode following software power-down KSZ8851 errata sheet DS80000716D-page 4 Module 3 [1] states that, when issuing a software power-down (PMECR[1:0] = 10) followed by a power-on (PMECR[1:0] = 00), the receiver circuit can fail to start properly preventing communication. The Transmitter will still send data, but no data will be received. The errata sheet also includes a workaround, which states that, it is recommended that the software power-down feature not be used. Implement that workaround and drop the entry into software power-down mode. The ks8851_write_mac_addr() calls entry into normal power-on mode at the very beginning of the function, therefore dropping the second call to enter software power-down mode is sufficient here. The ks8851_net_stop() can only be called after ks8851_net_start() was already called, and ks8851_net_start() also makes the MAC enter normal power-on mode, therefore it is also fine to drop the call to enter software power-down mode from ks8851_net_stop(). This will lead to a slight increase in power consumption, but it also fixes a sporadic reliability problem on at least KSZ8851-16MLL, which is where the problem was reported and this fix was tested. [1] https://ww1.microchip.com/downloads/en/DeviceDoc/80000716D.pdf Fixes: 3ba81f3ece3c ("net: Micrel KS8851 SPI network driver") Reviewed-by: Sebastian Andrzej Siewior Signed-off-by: Marek Vasut Link: https://patch.msgid.link/20260905130327.203851-1-marex@nabladev.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/micrel/ks8851_common.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/drivers/net/ethernet/micrel/ks8851_common.c b/drivers/net/ethernet/micrel/ks8851_common.c index 4afbb40bc0e4..d49f281c7867 100644 --- a/drivers/net/ethernet/micrel/ks8851_common.c +++ b/drivers/net/ethernet/micrel/ks8851_common.c @@ -143,9 +143,6 @@ static int ks8851_write_mac_addr(struct net_device *dev) ks8851_wrreg16(ks, KS_MAR(i), val); } - if (!netif_running(dev)) - ks8851_set_powermode(ks, PMECR_PM_SOFTDOWN); - ks8851_unlock(ks); return 0; @@ -478,8 +475,7 @@ static int ks8851_net_open(struct net_device *dev) * @dev: The device being closed. * * Called to close down a network device which has been active. Cancel any - * work, shutdown the RX and TX process and then place the chip into a low - * power state whilst it is not being used. + * work and shutdown the RX and TX process. */ static int ks8851_net_stop(struct net_device *dev) { @@ -506,8 +502,6 @@ static int ks8851_net_stop(struct net_device *dev) /* shutdown TX process */ ks8851_wrreg16(ks, KS_TXCR, 0x0000); - /* set powermode to soft power down to save power */ - ks8851_set_powermode(ks, PMECR_PM_SOFTDOWN); ks8851_unlock(ks); /* ensure any queued tx buffers are dumped */ From cb26524ef4ac28fcfa554c0656e8dc412c38a8ff Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Wed, 9 Sep 2026 17:02:40 -0300 Subject: [PATCH 1036/1198] smb: client: fix one-byte OOB read in smb2_parse_native_symlink() When parsing a share-root relative native symlink, memcpy copies smb_target+1 (skipping the leading separator) but uses strlen(smb_target)+1 as the length, reading one byte past the allocated buffer. This fixes the following KASAN splat when accessing an SMB symlink with a target of '\a\b': BUG: KASAN: slab-out-of-bounds in smb2_parse_native_symlink+0x4f5/0xca0 Read of size 5 at addr ffff88800878fe21 by task netfsfuzz-execu/1 CPU: 1 UID: 0 PID: 1 Comm: netfsfuzz-execu Tainted: G N 7.2.0-11943-g2709dd5ae32f-dirty #1 PREEMPT(lazy) Hardware name: QEMU Ubuntu 24.04 PC v2 (i440FX + PIIX, arch_caps fix, 1996) Call Trace: dump_stack_lvl+0x7b/0xa0 print_report+0xd0/0x630 kasan_report+0xe5/0x120 kasan_check_range+0x105/0x1b0 __asan_memcpy+0x23/0x60 smb2_parse_native_symlink+0x4f5/0xca0 parse_reparse_point+0x68a/0x1530 reparse_info_to_fattr+0x752/0xa20 cifs_get_fattr+0x873/0x15b0 cifs_get_inode_info+0xc0/0x310 cifs_lookup+0x308/0xa70 __lookup_slow+0x122/0x2b0 lookup_slow+0x50/0x70 path_lookupat+0x525/0xaf0 filename_lookup+0x1f2/0x550 vfs_statx+0xd1/0x1a0 vfs_fstatat+0x65/0xc0 __do_sys_newfstatat+0x9a/0x120 do_syscall_64+0xdd/0x4a0 entry_SYSCALL_64_after_hwframe+0x77/0x7f Reported-by: Yuanfu Xie Fixes: 723f4ef90452 ("cifs: Fix parsing native symlinks relative to the export") Suggested-by: Pali Rohar Reviewed-by: Pali Rohar Reviewed-by: Namjae Jeon Signed-off-by: Paulo Alcantara Cc: Ronnie Sahlberg Cc: Shyam Prasad N Cc: Tom Talpey Cc: Bharath SM Cc: stable@vger.kernel.org --- fs/smb/client/reparse.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c index b6bded042e78..8a1b9e8be5ba 100644 --- a/fs/smb/client/reparse.c +++ b/fs/smb/client/reparse.c @@ -971,7 +971,8 @@ int smb2_parse_native_symlink(char **target, const char *buf, unsigned int len, linux_target[i*3 + 1] = '.'; linux_target[i*3 + 2] = sep; } - memcpy(linux_target + levels*3, smb_target+1, smb_target_len); /* +1 to skip leading sep */ + /* +1 to skip leading sep */ + memcpy(linux_target + levels*3, smb_target+1, smb_target_len-1); } else { /* * This is either an absolute symlink in POSIX-style format From 286b175bb03893949f24621f356abd9d20368b0a Mon Sep 17 00:00:00 2001 From: Javier Carrasco Date: Sun, 23 Aug 2026 19:59:01 +0200 Subject: [PATCH 1037/1198] hwmon: (chipcap2) fix channels in humidity alarm notifications hwmon_notify_event() expects the channel number as its last argument, taken into account with the type parameter that it is a humidity sensor type. Given that this device only provides one humidity channel, 0 must be passed. The custom construct to enumerate the channels makes wrong assumptions by listing all types together (temperature and humidity). Remove the custom channel enumeration and pass the right channel to hwmon_notify_event() for hwmon_humidity_min_alarm and hwmon_humidity_max_alarm. Fixes: 3af350929e75 ("hwmon: Add support for Amphenol ChipCap 2") Cc: stable@vger.kernel.org Signed-off-by: Javier Carrasco Link: https://patch.msgid.link/20260823-chipcap2_locks-v2-1-6a26c8e9e2fc@gmail.com Signed-off-by: Guenter Roeck --- drivers/hwmon/chipcap2.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/drivers/hwmon/chipcap2.c b/drivers/hwmon/chipcap2.c index 086571d556b7..9bef767b589e 100644 --- a/drivers/hwmon/chipcap2.c +++ b/drivers/hwmon/chipcap2.c @@ -92,11 +92,6 @@ struct cc2_data { bool process_irqs; }; -enum cc2_chan_addr { - CC2_CHAN_TEMP = 0, - CC2_CHAN_HUMIDITY, -}; - /* %RH as a per cent mille from a register value */ static long cc2_rh_convert(u16 data) { @@ -499,7 +494,7 @@ static irqreturn_t cc2_low_interrupt(int irq, void *data) if (cc2->process_irqs) { hwmon_notify_event(cc2->hwmon, hwmon_humidity, - hwmon_humidity_min_alarm, CC2_CHAN_HUMIDITY); + hwmon_humidity_min_alarm, 0); cc2->rh_alarm.low_alarm = true; } @@ -512,7 +507,7 @@ static irqreturn_t cc2_high_interrupt(int irq, void *data) if (cc2->process_irqs) { hwmon_notify_event(cc2->hwmon, hwmon_humidity, - hwmon_humidity_max_alarm, CC2_CHAN_HUMIDITY); + hwmon_humidity_max_alarm, 0); cc2->rh_alarm.high_alarm = true; } From 6d760f8b41aed74de4402440e4db663d261478bd Mon Sep 17 00:00:00 2001 From: Vishnu Razdan Date: Mon, 24 Aug 2026 23:58:00 -0700 Subject: [PATCH 1038/1198] hwmon: (pmbus) Clear generic status alarms with CLEAR_FAULTS Some hwmon alarms fall back to STATUS_WORD summary bits when no individual limit alarm is available. On PMBus 1.2 and newer devices, pmbus_get_boolean() acknowledges these alarms with the same byte-data write used for detailed status registers. For example, PB_STATUS_INPUT is 0x2000, so it is truncated to zero when passed to _pmbus_write_byte_data(). The resulting write cannot acknowledge the input alarm. PMBus 1.3 Part II, sections 10.2.4 and 10.2.5, excludes ordinary STATUS_BYTE and STATUS_WORD summary bits from individual clearing. Their summary bits clear when the underlying status bits clear, so changing this to a word-data write would not fix the generic input alarm either. Use the existing page CLEAR_FAULTS path for generic STATUS_WORD alarms, including devices whose status accessor uses STATUS_BYTE. Keep individual byte writes for detailed status registers on PMBus 1.2 and newer devices. As with the existing older-device fallback, CLEAR_FAULTS can clear other latched status; an active condition can reassert its status. Fixes: 35f165f08950 ("hwmon: (pmbus) Clear pmbus fault/warning bits after read") Cc: stable@vger.kernel.org Assisted-by: LLM Signed-off-by: Vishnu Razdan Link: https://patch.msgid.link/20260824-vrazdan-pmbus-status-word-b4-v1-1-2606ecd0c029@openai.com Signed-off-by: Guenter Roeck --- drivers/hwmon/pmbus/pmbus_core.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/hwmon/pmbus/pmbus_core.c b/drivers/hwmon/pmbus/pmbus_core.c index 806c9a4913bb..5f69c1420b4e 100644 --- a/drivers/hwmon/pmbus/pmbus_core.c +++ b/drivers/hwmon/pmbus/pmbus_core.c @@ -1275,7 +1275,9 @@ static int pmbus_get_boolean(struct i2c_client *client, struct pmbus_boolean *b, regval = status & mask; if (regval) { - if (data->revision >= PMBUS_REV_12) { + /* Generic STATUS_WORD alarms are not individually clearable. */ + if (data->revision >= PMBUS_REV_12 && + reg != PMBUS_STATUS_WORD) { ret = _pmbus_write_byte_data(client, page, reg, regval); if (ret) return ret; From 508baf1713f32f287bfb4f85d759403ec8ba35a3 Mon Sep 17 00:00:00 2001 From: Linmao Li Date: Mon, 31 Aug 2026 09:45:09 +0800 Subject: [PATCH 1039/1198] hwmon: (corsair-cpro) Create debugfs entries after hwmon registration ccp_debugfs_init() registers debugfs files whose private data is the devm allocated ccp. It runs before hwmon_device_register_with_info(), so when that registration fails, ccp_probe() returns with the files still in place. The HID core then frees ccp, and ccp_remove() is not called for a failed probe, so nothing removes them later either. Reading one of the files dereferences the freed pointer. Create the debugfs entries only after the hwmon device has been registered, so no failing path can leave them behind. The two version queries stay where they are. They send USB commands without holding ccp->mutex, which is only safe as long as nothing else can call send_usb_cmd(); once the hwmon device is registered its callbacks can do so concurrently. Only the debugfs creation moves, and it is told which queries succeeded. Reported-by: Sashiko Closes: https://lore.kernel.org/linux-hwmon/20260708031612.BD7E61F000E9@smtp.kernel.org/ Suggested-by: Guenter Roeck Fixes: 5997eb60f896 ("hwmon: (corsair-cpro) Add firmware and bootloader information") Signed-off-by: Linmao Li Link: https://patch.msgid.link/20260831014509.3352442-1-lilinmao@kylinos.cn Signed-off-by: Guenter Roeck --- drivers/hwmon/corsair-cpro.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/drivers/hwmon/corsair-cpro.c b/drivers/hwmon/corsair-cpro.c index 8354a002f4c5..56de0fe0f544 100644 --- a/drivers/hwmon/corsair-cpro.c +++ b/drivers/hwmon/corsair-cpro.c @@ -566,21 +566,18 @@ static int bootloader_show(struct seq_file *seqf, void *unused) } DEFINE_SHOW_ATTRIBUTE(bootloader); -static void ccp_debugfs_init(struct ccp_device *ccp) +static void ccp_debugfs_init(struct ccp_device *ccp, bool fw_valid, bool bl_valid) { char name[32]; - int ret; scnprintf(name, sizeof(name), "corsaircpro-%s", dev_name(&ccp->hdev->dev)); ccp->debugfs = debugfs_create_dir(name, NULL); - ret = get_fw_version(ccp); - if (!ret) + if (fw_valid) debugfs_create_file("firmware_version", 0444, ccp->debugfs, ccp, &firmware_fops); - ret = get_bl_version(ccp); - if (!ret) + if (bl_valid) debugfs_create_file("bootloader_version", 0444, ccp->debugfs, ccp, &bootloader_fops); } @@ -588,6 +585,7 @@ static void ccp_debugfs_init(struct ccp_device *ccp) static int ccp_probe(struct hid_device *hdev, const struct hid_device_id *id) { struct ccp_device *ccp; + bool fw_valid, bl_valid; int ret; ccp = devm_kzalloc(&hdev->dev, sizeof(*ccp), GFP_KERNEL); @@ -632,7 +630,13 @@ static int ccp_probe(struct hid_device *hdev, const struct hid_device_id *id) if (ret) goto out_hw_close; - ccp_debugfs_init(ccp); + /* + * Query the versions before registering the hwmon device: they send + * USB commands without holding ccp->mutex, which is only safe while + * nothing else can call send_usb_cmd(). + */ + fw_valid = !get_fw_version(ccp); + bl_valid = !get_bl_version(ccp); ccp->hwmon_dev = hwmon_device_register_with_info(&hdev->dev, "corsaircpro", ccp, &ccp_chip_info, NULL); @@ -641,6 +645,8 @@ static int ccp_probe(struct hid_device *hdev, const struct hid_device_id *id) goto out_hw_close; } + ccp_debugfs_init(ccp, fw_valid, bl_valid); + return 0; out_hw_close: From bb2424c3502cc72292eedade46960c331d5f28fb Mon Sep 17 00:00:00 2001 From: Cong Nguyen Date: Tue, 1 Sep 2026 22:54:04 +0700 Subject: [PATCH 1040/1198] hwmon: (gpio-fan) take fan_data->lock in gpio_fan_shutdown() set_fan_speed() writes the control GPIOs one bit at a time. Every other caller locks around it; gpio_fan_shutdown() doesn't. If it races a locked caller, the GPIO writes can interleave and leave the fan at a speed neither caller asked for. Fixes: b95579cd8795 ("hwmon: (gpio-fan) Add a shutdown handler to poweroff the fans") Reported-by: Sashiko AI review Link: https://lore.kernel.org/r/20260830152150.27F5F1F000E9@smtp.kernel.org Assisted-by: Claude:claude-opus-4 Signed-off-by: Cong Nguyen Link: https://patch.msgid.link/20260901155404.1532092-1-congnt264@gmail.com Signed-off-by: Guenter Roeck --- drivers/hwmon/gpio-fan.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c index 7f36e5f6f223..df8bd9707605 100644 --- a/drivers/hwmon/gpio-fan.c +++ b/drivers/hwmon/gpio-fan.c @@ -612,8 +612,11 @@ static void gpio_fan_shutdown(struct platform_device *pdev) { struct gpio_fan_data *fan_data = platform_get_drvdata(pdev); - if (fan_data->gpios) + if (fan_data->gpios) { + mutex_lock(&fan_data->lock); set_fan_speed(fan_data, 0); + mutex_unlock(&fan_data->lock); + } } static int gpio_fan_runtime_suspend(struct device *dev) From 09a9e1746a87845d7d8e2b4e23bb613306effdff Mon Sep 17 00:00:00 2001 From: Pengpeng Hou Date: Sun, 30 Aug 2026 20:50:44 +0800 Subject: [PATCH 1041/1198] hwmon: (aspeed-pwm-tacho) Propagate reset deassert errors aspeed_pwm_tacho_probe() installs its reset cleanup action and configures the controller after an unchecked reset deassertion. Stop probing when the reset controller rejects the transition, before the hwmon device becomes visible. Fixes: 18c514cc0e02 ("hwmon: (aspeed-pwm-tacho) Deassert reset in probe") Signed-off-by: Pengpeng Hou Link: https://patch.msgid.link/20260830125044.97718-1-pengpeng@iscas.ac.cn Signed-off-by: Guenter Roeck --- drivers/hwmon/aspeed-pwm-tacho.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/hwmon/aspeed-pwm-tacho.c b/drivers/hwmon/aspeed-pwm-tacho.c index 1c5945d4ba37..bfce589c3fb1 100644 --- a/drivers/hwmon/aspeed-pwm-tacho.c +++ b/drivers/hwmon/aspeed-pwm-tacho.c @@ -934,7 +934,9 @@ static int aspeed_pwm_tacho_probe(struct platform_device *pdev) "missing or invalid reset controller device tree entry"); return PTR_ERR(priv->rst); } - reset_control_deassert(priv->rst); + ret = reset_control_deassert(priv->rst); + if (ret) + return ret; ret = devm_add_action_or_reset(dev, aspeed_pwm_tacho_remove, priv); if (ret) From 4ee875c423c66c45d7ef7bbff403cd0e3971e0a2 Mon Sep 17 00:00:00 2001 From: Linmao Li Date: Fri, 28 Aug 2026 14:19:49 +0800 Subject: [PATCH 1042/1198] hwmon: (corsair-cpro) Remove debugfs entries when probe fails ccp_debugfs_init() registers debugfs files whose private data is the devm allocated ccp. If hwmon_device_register_with_info() fails right after it, ccp_probe() returns without removing them: the HID core then frees ccp, and ccp_remove() is not called for a failed probe, so the files stay behind. Reading one of them dereferences the freed pointer. Remove the debugfs entries on that error path. debugfs_remove_recursive() waits for readers already inside the show callbacks, so ccp is no longer reachable through debugfs by the time probe returns. Reported-by: Sashiko Closes: https://lore.kernel.org/linux-hwmon/20260708031612.BD7E61F000E9@smtp.kernel.org/ Fixes: 5997eb60f896 ("hwmon: (corsair-cpro) Add firmware and bootloader information") Signed-off-by: Linmao Li Link: https://patch.msgid.link/20260828061949.3151191-1-lilinmao@kylinos.cn Signed-off-by: Guenter Roeck --- drivers/hwmon/corsair-cpro.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/hwmon/corsair-cpro.c b/drivers/hwmon/corsair-cpro.c index 56de0fe0f544..c09645152613 100644 --- a/drivers/hwmon/corsair-cpro.c +++ b/drivers/hwmon/corsair-cpro.c @@ -642,13 +642,15 @@ static int ccp_probe(struct hid_device *hdev, const struct hid_device_id *id) ccp, &ccp_chip_info, NULL); if (IS_ERR(ccp->hwmon_dev)) { ret = PTR_ERR(ccp->hwmon_dev); - goto out_hw_close; + goto out_debugfs_remove; } ccp_debugfs_init(ccp, fw_valid, bl_valid); return 0; +out_debugfs_remove: + debugfs_remove_recursive(ccp->debugfs); out_hw_close: hid_hw_close(hdev); hid_device_io_stop(hdev); From 8042312e73c50de82634ce63eae7cf219464b481 Mon Sep 17 00:00:00 2001 From: Arie Miller Date: Thu, 3 Sep 2026 22:21:28 -0400 Subject: [PATCH 1043/1198] hwmon: (asus_rog_ryujin) Validate HID report lengths rog_ryujin_raw_event() parses response headers and payload fields without first checking that they are present in the received report. A short report can therefore make the driver consume uninitialized bytes from the HID transport buffer and expose them as sensor values through sysfs. Validate the response header and the fields used by each response type before parsing them. Fixes: ed3e03790c5c ("hwmon: Add driver for ASUS ROG RYUJIN II 360 AIO cooler") Reported-by: Sashiko Closes: https://lore.kernel.org/linux-hwmon/20260812104617.858D01F000E9@smtp.kernel.org/ Cc: stable@vger.kernel.org Assisted-by: Codex:gpt-5.6-sol sparse Signed-off-by: Arie Miller Link: https://patch.msgid.link/20260904022129.97896-2-renari@arimil.com Signed-off-by: Guenter Roeck --- drivers/hwmon/asus_rog_ryujin.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/drivers/hwmon/asus_rog_ryujin.c b/drivers/hwmon/asus_rog_ryujin.c index 702edb831394..f4d99c510369 100644 --- a/drivers/hwmon/asus_rog_ryujin.c +++ b/drivers/hwmon/asus_rog_ryujin.c @@ -422,10 +422,15 @@ static int rog_ryujin_raw_event(struct hid_device *hdev, struct hid_report *repo { struct rog_ryujin_data *priv = hid_get_drvdata(hdev); - if (data[0] != RYUJIN_CMD_PREFIX) + if (size < 2 || data[0] != RYUJIN_CMD_PREFIX) return 0; if (data[1] == RYUJIN_GET_COOLER_STATUS_CMD_RESPONSE) { + if (size <= priv->info->temp_offset + 1 || + size <= priv->info->pump_speed_offset + 1 || + size <= priv->info->fan_speed_offset + 1) + return 0; + /* Received coolant temp and speeds of pump and internal fan */ priv->temp_input[0] = data[priv->info->temp_offset] * 1000 + data[priv->info->temp_offset + 1] * 100; @@ -437,6 +442,9 @@ static int rog_ryujin_raw_event(struct hid_device *hdev, struct hid_report *repo if (!completion_done(&priv->cooler_status_received)) complete_all(&priv->cooler_status_received); } else if (data[1] == RYUJIN_GET_CONTROLLER_SPEED_CMD_RESPONSE) { + if (size <= RYUJIN_CONTROLLER_SPEED_3 + 1) + return 0; + /* Received speeds of four fans attached to the controller */ priv->speed_input[2] = get_unaligned_le16(data + RYUJIN_CONTROLLER_SPEED_1); priv->speed_input[3] = get_unaligned_le16(data + RYUJIN_CONTROLLER_SPEED_2); @@ -446,6 +454,9 @@ static int rog_ryujin_raw_event(struct hid_device *hdev, struct hid_report *repo if (!completion_done(&priv->controller_status_received)) complete_all(&priv->controller_status_received); } else if (data[1] == RYUJIN_GET_COOLER_DUTY_CMD_RESPONSE) { + if (size <= RYUJIN_INTERNAL_FAN_DUTY) + return 0; + /* Received report for pump and internal fan duties (in %) */ if (data[RYUJIN_PUMP_DUTY] == 0 && data[RYUJIN_INTERNAL_FAN_DUTY] == 0) { /* @@ -472,6 +483,9 @@ static int rog_ryujin_raw_event(struct hid_device *hdev, struct hid_report *repo if (!completion_done(&priv->cooler_duty_received)) complete_all(&priv->cooler_duty_received); } else if (data[1] == RYUJIN_GET_CONTROLLER_DUTY_CMD_RESPONSE) { + if (size <= RYUJIN_CONTROLLER_DUTY) + return 0; + /* Received report for controller duty for fans (in PWM) */ if (data[RYUJIN_CONTROLLER_DUTY] == 0) { /* From 06d48355bf41028c1321acda6a4391cd70098be8 Mon Sep 17 00:00:00 2001 From: Arie Miller Date: Thu, 3 Sep 2026 22:21:29 -0400 Subject: [PATCH 1044/1198] hwmon: (asus_rog_ryujin) Synchronize HID command and report handling rog_ryujin_execute_cmd() holds status_report_request_lock while reinitializing a completion, intending to exclude raw-event handling. However, rog_ryujin_raw_event() does not acquire the lock when it updates the completion. A response can therefore race with reinit_completion() and be lost, leaving the command to time out. Hold the lock while parsing reports and updating their completions. Use the irqsave variants in both paths because raw-event handling may run in interrupt context. Fixes: ed3e03790c5c ("hwmon: Add driver for ASUS ROG RYUJIN II 360 AIO cooler") Reported-by: Sashiko Closes: https://lore.kernel.org/linux-hwmon/20260812104617.858D01F000E9@smtp.kernel.org/ Cc: stable@vger.kernel.org Assisted-by: Codex:gpt-5.6-sol sparse Signed-off-by: Arie Miller Link: https://patch.msgid.link/20260904022129.97896-3-renari@arimil.com Signed-off-by: Guenter Roeck --- drivers/hwmon/asus_rog_ryujin.c | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) diff --git a/drivers/hwmon/asus_rog_ryujin.c b/drivers/hwmon/asus_rog_ryujin.c index f4d99c510369..e297557ca346 100644 --- a/drivers/hwmon/asus_rog_ryujin.c +++ b/drivers/hwmon/asus_rog_ryujin.c @@ -184,6 +184,7 @@ static int rog_ryujin_write_expanded(struct rog_ryujin_data *priv, const u8 *cmd static int rog_ryujin_execute_cmd(struct rog_ryujin_data *priv, const u8 *cmd, int cmd_length, struct completion *status_completion) { + unsigned long flags; int ret; /* @@ -191,9 +192,9 @@ static int rog_ryujin_execute_cmd(struct rog_ryujin_data *priv, const u8 *cmd, i * completion. Reinit is done because hidraw could have triggered * the raw event parsing and marked the passed in completion as done. */ - spin_lock_bh(&priv->status_report_request_lock); + spin_lock_irqsave(&priv->status_report_request_lock, flags); reinit_completion(status_completion); - spin_unlock_bh(&priv->status_report_request_lock); + spin_unlock_irqrestore(&priv->status_report_request_lock, flags); /* Send command for getting data */ ret = rog_ryujin_write_expanded(priv, cmd, cmd_length); @@ -421,15 +422,18 @@ static int rog_ryujin_raw_event(struct hid_device *hdev, struct hid_report *repo int size) { struct rog_ryujin_data *priv = hid_get_drvdata(hdev); + unsigned long flags; if (size < 2 || data[0] != RYUJIN_CMD_PREFIX) return 0; + spin_lock_irqsave(&priv->status_report_request_lock, flags); + if (data[1] == RYUJIN_GET_COOLER_STATUS_CMD_RESPONSE) { if (size <= priv->info->temp_offset + 1 || size <= priv->info->pump_speed_offset + 1 || size <= priv->info->fan_speed_offset + 1) - return 0; + goto unlock; /* Received coolant temp and speeds of pump and internal fan */ priv->temp_input[0] = data[priv->info->temp_offset] * 1000 + @@ -443,7 +447,7 @@ static int rog_ryujin_raw_event(struct hid_device *hdev, struct hid_report *repo complete_all(&priv->cooler_status_received); } else if (data[1] == RYUJIN_GET_CONTROLLER_SPEED_CMD_RESPONSE) { if (size <= RYUJIN_CONTROLLER_SPEED_3 + 1) - return 0; + goto unlock; /* Received speeds of four fans attached to the controller */ priv->speed_input[2] = get_unaligned_le16(data + RYUJIN_CONTROLLER_SPEED_1); @@ -455,7 +459,7 @@ static int rog_ryujin_raw_event(struct hid_device *hdev, struct hid_report *repo complete_all(&priv->controller_status_received); } else if (data[1] == RYUJIN_GET_COOLER_DUTY_CMD_RESPONSE) { if (size <= RYUJIN_INTERNAL_FAN_DUTY) - return 0; + goto unlock; /* Received report for pump and internal fan duties (in %) */ if (data[RYUJIN_PUMP_DUTY] == 0 && data[RYUJIN_INTERNAL_FAN_DUTY] == 0) { @@ -474,7 +478,7 @@ static int rog_ryujin_raw_event(struct hid_device *hdev, struct hid_report *repo * We're expecting a report, so parse it. */ goto read_cooler_duty; - return 0; + goto unlock; } read_cooler_duty: priv->duty_input[0] = rog_ryujin_percent_to_pwm(data[RYUJIN_PUMP_DUTY]); @@ -484,7 +488,7 @@ static int rog_ryujin_raw_event(struct hid_device *hdev, struct hid_report *repo complete_all(&priv->cooler_duty_received); } else if (data[1] == RYUJIN_GET_CONTROLLER_DUTY_CMD_RESPONSE) { if (size <= RYUJIN_CONTROLLER_DUTY) - return 0; + goto unlock; /* Received report for controller duty for fans (in PWM) */ if (data[RYUJIN_CONTROLLER_DUTY] == 0) { @@ -503,7 +507,7 @@ static int rog_ryujin_raw_event(struct hid_device *hdev, struct hid_report *repo * We're expecting a report, so parse it. */ goto read_controller_duty; - return 0; + goto unlock; } read_controller_duty: priv->duty_input[2] = data[RYUJIN_CONTROLLER_DUTY]; @@ -512,6 +516,8 @@ static int rog_ryujin_raw_event(struct hid_device *hdev, struct hid_report *repo complete_all(&priv->controller_duty_received); } +unlock: + spin_unlock_irqrestore(&priv->status_report_request_lock, flags); return 0; } From c88a6338ae485e4d6210cc74cdb7664d6476c925 Mon Sep 17 00:00:00 2001 From: Ali Ahmet Memis Date: Mon, 3 Aug 2026 10:21:48 +0000 Subject: [PATCH 1045/1198] hwmon: (nct6694) do not expose enable on DTIN temperature channels The driver registers 26 temperature channels, all advertising HWMON_T_ENABLE, and indexes the enable bitmap with the raw channel: data->hwmon_en.tin_en[channel / 8] |= BIT(channel % 8); tin_en is two bytes and only covers the 5 THR and 5 TDP channels (index 0-9). The 16 DTIN channels (index 10-25) are enabled by the firmware and were never meant to carry an enable bit. Because the control structure is packed, writing temp17_enable and above indexes past tin_en into the fin_en bytes that follow it, so it toggles fan enable state instead; nct6694_hwmon_init() then sends the whole structure back to the device, and reads report fan state as temperature state. It stays within the structure, so this is not a memory safety problem, but on a board that uses the fan channels it is not harmless. Give the DTIN channels a temperature config without HWMON_T_ENABLE so the core never creates their enable attribute. The enable path is then reachable only for the first 10 channels, which stay within tin_en, and fin_en is left alone. The DTIN input and limit attributes are unchanged. Fixes: 197e779d29d8 ("hwmon: Add Nuvoton NCT6694 HWMON support") Suggested-by: Ming Yu Link: https://lore.kernel.org/all/20260802124730.20387-1-ali@iusegentoo.com/ Signed-off-by: Ali Ahmet Memis Link: https://patch.msgid.link/20260803102148.14196-1-ali@iusegentoo.com Signed-off-by: Guenter Roeck --- drivers/hwmon/nct6694-hwmon.c | 35 +++++++++++++++++++---------------- 1 file changed, 19 insertions(+), 16 deletions(-) diff --git a/drivers/hwmon/nct6694-hwmon.c b/drivers/hwmon/nct6694-hwmon.c index 6dcf22ca5018..9a9a4db434c4 100644 --- a/drivers/hwmon/nct6694-hwmon.c +++ b/drivers/hwmon/nct6694-hwmon.c @@ -159,6 +159,9 @@ static inline s8 temp_to_reg(long val) #define NCT6694_HWMON_TEMP_CONFIG (HWMON_T_INPUT | HWMON_T_ENABLE | \ HWMON_T_MAX | HWMON_T_MAX_HYST | \ HWMON_T_MAX_ALARM) +#define NCT6694_HWMON_DTIN_CONFIG (HWMON_T_INPUT | \ + HWMON_T_MAX | HWMON_T_MAX_HYST | \ + HWMON_T_MAX_ALARM) #define NCT6694_HWMON_FAN_CONFIG (HWMON_F_INPUT | HWMON_F_ENABLE | \ HWMON_F_MIN | HWMON_F_MIN_ALARM) #define NCT6694_HWMON_PWM_CONFIG (HWMON_PWM_INPUT | HWMON_PWM_ENABLE | \ @@ -193,22 +196,22 @@ static const struct hwmon_channel_info *nct6694_info[] = { NCT6694_HWMON_TEMP_CONFIG, /* TDP2 */ NCT6694_HWMON_TEMP_CONFIG, /* TDP3 */ NCT6694_HWMON_TEMP_CONFIG, /* TDP4 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN0 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN1 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN2 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN3 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN4 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN5 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN6 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN7 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN8 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN9 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN10 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN11 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN12 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN13 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN14 */ - NCT6694_HWMON_TEMP_CONFIG), /* DTIN15 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN0 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN1 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN2 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN3 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN4 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN5 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN6 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN7 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN8 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN9 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN10 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN11 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN12 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN13 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN14 */ + NCT6694_HWMON_DTIN_CONFIG), /* DTIN15 */ HWMON_CHANNEL_INFO(fan, NCT6694_HWMON_FAN_CONFIG, /* FIN0 */ From ef39fca8508597fa565cf2be72a884a712fb98af Mon Sep 17 00:00:00 2001 From: Ratheesh Kannoth Date: Thu, 3 Sep 2026 07:35:33 +0530 Subject: [PATCH 1046/1198] octeontx2-pf: reset HTB scheduler topology before freeing queues HTB offload programs NIX_AF_TLxX_TOPOLOGY on QoS-allocated scheduler queues via otx2_qos_txschq_set_parent_topology(), but teardown freed those queues without clearing TOPOLOGY. The AF only restores PARENT and SCHEDULE on free, so PRIO_ANCHOR/RR_PRIO settings can survive in the shared scheduler pool and affect later allocations. Add otx2_qos_reset_schq_topology() and otx2_qos_free_hw_schq() to zero TL4 through TL2 TOPOLOGY before each schq is returned to the AF during hierarchy teardown and cfg rollback. Skip the aggregation level (TL1): it is a per-tx-link queue shared by the PF, default Tx hierarchy and VFs, and is not freed back to the AF by nix_txschq_free_one(). Fixes: 5e6808b4c68d ("octeontx2-pf: Add support for HTB offload") Signed-off-by: Ratheesh Kannoth Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260903020533.3068041-1-rkannoth@marvell.com Signed-off-by: Jakub Kicinski --- .../net/ethernet/marvell/octeontx2/nic/qos.c | 60 +++++++++++++++++-- 1 file changed, 55 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c index 69c0911e28e9..f160b1618efa 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c @@ -235,13 +235,63 @@ static int otx2_qos_txschq_set_parent_topology(struct otx2_nic *pfvf, return rc; } +static int otx2_qos_reset_schq_topology(struct otx2_nic *pfvf, u16 lvl, + u16 schq) +{ + struct mbox *mbox = &pfvf->mbox; + struct nix_txschq_config *cfg; + int rc; + + if (lvl < NIX_TXSCH_LVL_TL4 || lvl >= NIX_TXSCH_LVL_TL1) + return 0; + + mutex_lock(&mbox->lock); + + cfg = otx2_mbox_alloc_msg_nix_txschq_cfg(mbox); + if (!cfg) { + mutex_unlock(&mbox->lock); + return -ENOMEM; + } + + cfg->lvl = lvl; + cfg->num_regs = 1; + + if (lvl == NIX_TXSCH_LVL_TL4) + cfg->reg[0] = NIX_AF_TL4X_TOPOLOGY(schq); + else if (lvl == NIX_TXSCH_LVL_TL3) + cfg->reg[0] = NIX_AF_TL3X_TOPOLOGY(schq); + else if (lvl == NIX_TXSCH_LVL_TL2) + cfg->reg[0] = NIX_AF_TL2X_TOPOLOGY(schq); + + cfg->regval[0] = 0; + + rc = otx2_sync_mbox_msg(mbox); + + mutex_unlock(&mbox->lock); + + return rc; +} + +static void otx2_qos_free_hw_schq(struct otx2_nic *pfvf, u16 lvl, u16 schq) +{ + int err; + + err = otx2_qos_reset_schq_topology(pfvf, lvl, schq); + if (err) + netdev_warn(pfvf->netdev, + "QoS: failed to reset topology for schq %u at level %u: %d\n", + schq, lvl, err); + + otx2_txschq_free_one(pfvf, lvl, schq); +} + static void otx2_qos_free_hw_node_schq(struct otx2_nic *pfvf, struct otx2_qos_node *parent) { struct otx2_qos_node *node; list_for_each_entry_reverse(node, &parent->child_schq_list, list) - otx2_txschq_free_one(pfvf, node->level, node->schq); + otx2_qos_free_hw_schq(pfvf, node->level, node->schq); } static void otx2_qos_free_hw_node(struct otx2_nic *pfvf, @@ -252,7 +302,7 @@ static void otx2_qos_free_hw_node(struct otx2_nic *pfvf, list_for_each_entry_safe(node, tmp, &parent->child_list, list) { otx2_qos_free_hw_node(pfvf, node); otx2_qos_free_hw_node_schq(pfvf, node); - otx2_txschq_free_one(pfvf, node->level, node->schq); + otx2_qos_free_hw_schq(pfvf, node->level, node->schq); } } @@ -266,7 +316,7 @@ static void otx2_qos_free_hw_cfg(struct otx2_nic *pfvf, otx2_qos_free_hw_node_schq(pfvf, node); /* free node hw mappings */ - otx2_txschq_free_one(pfvf, node->level, node->schq); + otx2_qos_free_hw_schq(pfvf, node->level, node->schq); mutex_unlock(&pfvf->qos.qos_lock); } @@ -913,7 +963,7 @@ static void otx2_qos_free_cfg(struct otx2_nic *pfvf, struct otx2_qos_cfg *cfg) for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) { for (idx = 0; idx < cfg->schq[lvl]; idx++) { schq = cfg->schq_list[lvl][idx]; - otx2_txschq_free_one(pfvf, lvl, schq); + otx2_qos_free_hw_schq(pfvf, lvl, schq); } } @@ -921,7 +971,7 @@ static void otx2_qos_free_cfg(struct otx2_nic *pfvf, struct otx2_qos_cfg *cfg) for (idx = 0; idx < cfg->schq_contig[lvl]; idx++) { if (cfg->schq_index_used[lvl][idx]) { schq = cfg->schq_contig_list[lvl][idx]; - otx2_txschq_free_one(pfvf, lvl, schq); + otx2_qos_free_hw_schq(pfvf, lvl, schq); } } } From be83178bfc44588f6e3adb827ed874c683193466 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 6 Sep 2026 18:01:04 +0000 Subject: [PATCH 1047/1198] vxlan: initialize _md in vxlan_xmit_one() If a VXLAN device is configured with both VXLAN_F_COLLECT_METADATA and VXLAN_F_GBP, and a packet is transmitted through it using an external ip_tunnel_info that lacks the IP_TUNNEL_VXLAN_OPT_BIT flag, md is left pointing to the uninitialized _md stack variable: if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags)) { if (info->options_len < sizeof(*md)) goto drop; md = ip_tunnel_info_opts(info); } Because IP_TUNNEL_VXLAN_OPT_BIT is not set, md is not updated and remains pointing to _md. Later, vxlan_build_skb() is called with md, which eventually calls vxlan_build_gbp_hdr(): if (vxflags & VXLAN_F_GBP) vxlan_build_gbp_hdr(vxh, md); Inside vxlan_build_gbp_hdr(), md->gbp is read: if (!md->gbp) return; gbp = (struct vxlanhdr_gbp *)vxh; ... if (md->gbp & VXLAN_GBP_DONT_LEARN) gbp->dont_learn = 1; If the stack contains garbage, this causes: 1) VXLAN_HF_GBP flag to be spuriously set in the VXLAN header. 2) gbp->dont_learn and gbp->policy_applied to be set from stack bits. 3) gbp->policy_id to receive 16 bits of uninitialized kernel stack data, leaking it onto the wire. Fix this by zero-initializing _md. If IP_TUNNEL_VXLAN_OPT_BIT is not present, md->gbp remains 0, and vxlan_build_gbp_hdr() returns early without modifying the VXLAN header. Fixes: ee122c79d422 ("vxlan: Flow based tunneling") Signed-off-by: Eric Dumazet Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20260906180111.1973188-2-edumazet@google.com Signed-off-by: Jakub Kicinski --- drivers/net/vxlan/vxlan_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index be95af64a1f5..c1d54339fa2b 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -2373,7 +2373,7 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, struct ip_tunnel_key key; struct vxlan_dev *vxlan = netdev_priv(dev); const struct iphdr *old_iph; - struct vxlan_metadata _md; + struct vxlan_metadata _md = {}; struct vxlan_metadata *md = &_md; unsigned int pkt_len = skb->len; __be16 src_port = 0, dst_port; From 8aaeb56aff2a557a88f83ae866da2c91ad247e59 Mon Sep 17 00:00:00 2001 From: Qingfang Deng Date: Tue, 8 Sep 2026 15:21:31 +0800 Subject: [PATCH 1048/1198] ppp_synctty: ensure a writeable skb header ppp_sync_txmunge() checks headroom before prepending the address and control bytes, but does not ensure that the skb header is writable. A received skb can reach this function through PPP channel bridging without passing through ppp_start_xmit(), which calls skb_cow_head(). For example, a PPPoE frame may share its buffer with a clone queued to an AF_PACKET socket. If it is bridged to a synchronous tty channel, the address/control bytes can overwrite data still visible to that socket. Use skb_cow_head() to ensure both sufficient headroom and a writable header. Fixes: 4cf476ced45d ("ppp: add PPPIOCBRIDGECHAN and PPPIOCUNBRIDGECHAN ioctls") Signed-off-by: Qingfang Deng Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20260908072135.877364-1-qingfang.deng@linux.dev Signed-off-by: Jakub Kicinski --- drivers/net/ppp/ppp_synctty.c | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-) diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c index f87d43faeeab..ebd62a7ab54b 100644 --- a/drivers/net/ppp/ppp_synctty.c +++ b/drivers/net/ppp/ppp_synctty.c @@ -455,17 +455,9 @@ ppp_sync_txmunge(struct syncppp *ap, struct sk_buff *skb) /* prepend address/control fields if necessary */ if ((ap->flags & SC_COMP_AC) == 0 || islcp) { - if (skb_headroom(skb) < 2) { - struct sk_buff *npkt = dev_alloc_skb(skb->len + 2); - if (npkt == NULL) { - kfree_skb(skb); - return NULL; - } - skb_reserve(npkt,2); - skb_copy_from_linear_data(skb, - skb_put(npkt, skb->len), skb->len); - consume_skb(skb); - skb = npkt; + if (skb_cow_head(skb, 2)) { + kfree_skb(skb); + return NULL; } skb_push(skb,2); skb->data[0] = PPP_ALLSTATIONS; From 113998aa372f4869bf62cfc75c28a2849e8487be Mon Sep 17 00:00:00 2001 From: Aleksei Sviridkin Date: Fri, 4 Sep 2026 18:55:40 +0000 Subject: [PATCH 1049/1198] net: phylink: initialise link_state before a forced major config phylink_resolve() leaves link_state on the stack unpopulated on its disable and link-failed branches, which set only link_state.link. phylink_apply_manual_flow() then reads the struct's advertising on every mode but MLO_AN_FIXED, and has done so since long before force_major_config existed. force_major_config turns that into a write to the hardware. It is the only trigger for the major-config block that does not require mac_config, so phylink_major_config() programs the MAC for whatever the stack held, a zeroed interface is PHY_INTERFACE_MODE_NA, and the write-back stores it in pl->link_config.interface. phylink_replay_link_end() is the only in-tree setter, and sja1105_static_config_reload() calls it for every port that has a phylink instance, regardless of admin state. On a stopped port phylink_run_resolve() no-ops, so the flag outlives the call. The next resolve consumes it whatever branch it takes; an unpopulated branch is where that does damage. Found while developing a series that attaches a late PHY from a delayed work item and sets this flag there, so the PHY attached after its port was already up. The link stayed down until the port was cycled 29 minutes later. With this patch on the same board the same attach programs the MAC for 2500base-x rather than unknown, and the PHY's interrupt fires without a port bounce where it had stayed at zero throughout the failure. Fixes: 96969b132bf1 ("net: phylink: introduce helpers for replaying link callbacks") Signed-off-by: Aleksei Sviridkin Link: https://patch.msgid.link/20260904185540.2844261-1-f@lex.la Signed-off-by: Jakub Kicinski --- drivers/net/phy/phylink.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 3ec3bb439109..a1458da8111b 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -1630,8 +1630,10 @@ static void phylink_resolve(struct work_struct *w) if (pl->phylink_disable_state) { pl->link_failed = false; + link_state = pl->link_config; link_state.link = false; } else if (pl->link_failed) { + link_state = pl->link_config; link_state.link = false; retrigger = true; } else if (pl->act_link_an_mode == MLO_AN_FIXED) { From 0338c68e22abd2ee509ec2e32508a50896618c32 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 4 Sep 2026 12:32:55 +0200 Subject: [PATCH 1050/1198] net: stmmac: initialize ptp_lock at probe time priv->ptp_lock is only initialized in stmmac_ptp_register(), which runs during __stmmac_open(). However, the lock is also used while the interface is down and has never been opened: tc_taprio_configure() invokes the PTP gettime64() callback to compute the EST base time when offloading a TAPRIO schedule, and stmmac_get_time() takes priv->ptp_lock. Using an uninitialized rwlock is undefined behaviour. Move the rwlock_init() to __stmmac_dvr_probe(), together with the other private locks, so that ptp_lock is always valid regardless of the interface state. Fixes: b60189e0392f ("net: stmmac: Integrate EST with TAPRIO scheduler API") Signed-off-by: Lorenzo Bianconi Reviewed-by: Maxime Chevallier Link: https://patch.msgid.link/20260904-stmmac-fix-ptp-clock-init-v1-1-df70eb1eb04d@oss.qualcomm.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 1 + drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c | 1 - 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 24656b35350b..5fe7e95fdd34 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -8025,6 +8025,7 @@ static int __stmmac_dvr_probe(struct device *device, stmmac_napi_add(ndev); mutex_init(&priv->lock); + rwlock_init(&priv->ptp_lock); stmmac_fpe_init(priv); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index 960249960004..3bfcc9760dce 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -365,7 +365,6 @@ void stmmac_ptp_register(struct stmmac_priv *priv) if (priv->plat->crosststamp) priv->ptp_clock_ops.getcrosststamp = stmmac_getcrosststamp; - rwlock_init(&priv->ptp_lock); mutex_init(&priv->aux_ts_lock); priv->ptp_clock = ptp_clock_register(&priv->ptp_clock_ops, From 7f26a5e8040b4957ef4dbdfcde6cc7ba2db53937 Mon Sep 17 00:00:00 2001 From: Carolina Jubran Date: Sun, 6 Sep 2026 12:07:00 +0300 Subject: [PATCH 1051/1198] net/mlx5e: Move representor vnic reporter to eswitch devlink port The representor vnic devlink health reporter is created and destroyed along the representor netdev (un)load path, which is not serialized by the devlink instance lock. Destroying the reporter from there triggers a devl_assert_locked() splat on driver unbind: WARNING: net/devlink/core.c:259 at devl_assert_locked+0x54/0x70, CPU#2: bash/3758 Modules linked in: mlx5_vdpa vringh vdpa mlx5_ib mlx5_fwctl mlx5_core ... CPU: 2 UID: 0 PID: 3758 Comm: bash Tainted: G W 6.19.0+ #1 PREEMPT Tainted: [W]=WARN Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), ... RIP: 0010:devl_assert_locked+0x54/0x70 Call Trace: devl_health_reporter_destroy+0x3a/0x1b0 mlx5e_vport_rep_unload+0x12d/0x2b0 [mlx5_core] mlx5_eswitch_unregister_vport_reps+0x1b8/0x220 [mlx5_core] ? __esw_offloads_unload_rep+0x190/0x190 [mlx5_core] ? kernfs_remove_by_name_ns+0xc3/0xf0 device_release_driver_internal+0x3b2/0x560 unbind_store+0xce/0xf0 Move the reporter's lifecycle to the eswitch devlink port (un)register paths, which are already serialized by the devlink instance lock, and store the handle on mlx5_devlink_port. Use the port's mlx5_vport as the reporter priv since the diagnose callback only needs a device handle and a vport number, and mlx5_vport carries both and is initialized before any representor driver probes. Fixes: cf14af140a5a ("net/mlx5e: Add vnic devlink health reporter to representors") Signed-off-by: Carolina Jubran Reviewed-by: Cosmin Ratiu Signed-off-by: Tariq Toukan Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260906090700.3761260-1-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- .../net/ethernet/mellanox/mlx5/core/en_rep.c | 52 +------------------ .../net/ethernet/mellanox/mlx5/core/en_rep.h | 1 - .../mellanox/mlx5/core/esw/devlink_port.c | 37 +++++++++++++ .../net/ethernet/mellanox/mlx5/core/eswitch.h | 1 + 4 files changed, 39 insertions(+), 52 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index ce765692fd19..88a170e40bd9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -56,7 +56,6 @@ #include "lib/vxlan.h" #define CREATE_TRACE_POINTS #include "diag/en_rep_tracepoint.h" -#include "diag/reporter_vnic.h" #include "en_accel/ipsec.h" #include "en/tc/int_port.h" #include "en/ptp.h" @@ -1439,51 +1438,6 @@ static unsigned int mlx5e_ul_rep_stats_grps_num(struct mlx5e_priv *priv) return ARRAY_SIZE(mlx5e_ul_rep_stats_grps); } -static int -mlx5e_rep_vnic_reporter_diagnose(struct devlink_health_reporter *reporter, - struct devlink_fmsg *fmsg, - struct netlink_ext_ack *extack) -{ - struct mlx5e_rep_priv *rpriv = devlink_health_reporter_priv(reporter); - struct mlx5_eswitch_rep *rep = rpriv->rep; - - mlx5_reporter_vnic_diagnose_counters(rep->esw->dev, fmsg, rep->vport, - true); - return 0; -} - -static const struct devlink_health_reporter_ops mlx5_rep_vnic_reporter_ops = { - .name = "vnic", - .diagnose = mlx5e_rep_vnic_reporter_diagnose, -}; - -static void mlx5e_rep_vnic_reporter_create(struct mlx5e_priv *priv, - struct devlink_port *dl_port) -{ - struct mlx5e_rep_priv *rpriv = priv->ppriv; - struct devlink_health_reporter *reporter; - - reporter = devl_port_health_reporter_create(dl_port, - &mlx5_rep_vnic_reporter_ops, - rpriv); - if (IS_ERR(reporter)) { - mlx5_core_err(priv->mdev, - "Failed to create representor vnic reporter, err = %pe\n", - reporter); - return; - } - - rpriv->rep_vnic_reporter = reporter; -} - -static void mlx5e_rep_vnic_reporter_destroy(struct mlx5e_priv *priv) -{ - struct mlx5e_rep_priv *rpriv = priv->ppriv; - - if (!IS_ERR_OR_NULL(rpriv->rep_vnic_reporter)) - devl_health_reporter_destroy(rpriv->rep_vnic_reporter); -} - static const struct mlx5e_profile mlx5e_rep_profile = { .init = mlx5e_init_rep, .cleanup = mlx5e_cleanup_rep, @@ -1607,10 +1561,8 @@ mlx5e_vport_vf_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) dl_port = mlx5_esw_offloads_devlink_port(dev->priv.eswitch, rpriv->rep->vport); - if (!IS_ERR(dl_port)) { + if (!IS_ERR(dl_port)) SET_NETDEV_DEVLINK_PORT(netdev, dl_port); - mlx5e_rep_vnic_reporter_create(priv, dl_port); - } err = register_netdev(netdev); if (err) { @@ -1623,7 +1575,6 @@ mlx5e_vport_vf_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) return 0; err_detach_netdev: - mlx5e_rep_vnic_reporter_destroy(priv); mlx5e_detach_netdev(netdev_priv(netdev)); err_cleanup_profile: priv->profile->cleanup(priv); @@ -1681,7 +1632,6 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep) } unregister_netdev(netdev); - mlx5e_rep_vnic_reporter_destroy(priv); mlx5e_detach_netdev(priv); priv->profile->cleanup(priv); mlx5e_destroy_netdev(netdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index 70640fa1ad7b..bcd7b4e814d0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -118,7 +118,6 @@ struct mlx5e_rep_priv { struct rtnl_link_stats64 prev_vf_vport_stats; struct mlx5_flow_handle *send_to_vport_meta_rule; struct rhashtable tc_ht; - struct devlink_health_reporter *rep_vnic_reporter; }; static inline diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c index 36b00a856bc2..fdc960ea5331 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c @@ -4,6 +4,26 @@ #include #include "eswitch.h" #include "devlink.h" +#include "diag/reporter_vnic.h" + +static int +mlx5_esw_rep_vnic_reporter_diagnose(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg, + struct netlink_ext_ack *extack) +{ + struct mlx5_vport *vport = devlink_health_reporter_priv(reporter); + + mlx5_reporter_vnic_diagnose_counters(vport->dev, fmsg, vport->vport, + true); + + return 0; +} + +static const +struct devlink_health_reporter_ops mlx5_esw_rep_vnic_reporter_ops = { + .name = "vnic", + .diagnose = mlx5_esw_rep_vnic_reporter_diagnose, +}; static void mlx5_esw_get_port_parent_id(struct mlx5_core_dev *dev, struct netdev_phys_item_id *ppid) @@ -220,6 +240,7 @@ static void mlx5_esw_devlink_port_res_unregister(struct devlink_port *dl_port) int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, struct mlx5_vport *vport) { + struct devlink_health_reporter *reporter; struct mlx5_core_dev *dev = esw->dev; const struct devlink_port_ops *ops; struct mlx5_devlink_port *dl_port; @@ -255,6 +276,16 @@ int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, struct mlx mlx5_core_dbg(dev, "Failed to register port resources: %d\n", err); + reporter = devl_port_health_reporter_create( + &dl_port->dl_port, &mlx5_esw_rep_vnic_reporter_ops, + vport); + if (IS_ERR(reporter)) + mlx5_core_err(dev, + "Failed to create vnic health reporter for vport %d: %pe\n", + vport_num, reporter); + else + dl_port->vnic_reporter = reporter; + return 0; rate_err: @@ -269,6 +300,12 @@ void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_vport *vport) if (!vport->dl_port) return; dl_port = vport->dl_port; + + if (dl_port->vnic_reporter) { + devl_health_reporter_destroy(dl_port->vnic_reporter); + dl_port->vnic_reporter = NULL; + } + mlx5_esw_devlink_port_res_unregister(&dl_port->dl_port); devl_rate_leaf_destroy(&dl_port->dl_port); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index c655f6e8da1c..8b1f93b13ea9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -189,6 +189,7 @@ struct mlx5_vport; struct mlx5_devlink_port { struct devlink_port dl_port; struct mlx5_vport *vport; + struct devlink_health_reporter *vnic_reporter; }; static inline void mlx5_devlink_port_init(struct mlx5_devlink_port *dl_port, From 11ae2e1dc58304a48816fc8ca4afa8f2ef9d1bdf Mon Sep 17 00:00:00 2001 From: Aboorva Devarajan Date: Fri, 4 Sep 2026 08:28:30 +0530 Subject: [PATCH 1052/1198] powerpc/entry: Fix double accounting of user time on interrupt entry Since the switch to generic entry, an interrupt from user mode accounts user time twice: once in arch_interrupt_enter_prepare() and again in arch_enter_from_user_mode(), which irqentry_enter() invokes for the same interrupt: arch_interrupt_enter_prepare() account_cpu_user_entry() /* first */ irqentry_enter() arch_enter_from_user_mode() account_cpu_user_entry() /* second */ The second call charges the same interval again, because account_cpu_user_entry() accumulates the time spent in user mode since the last return to user space. The two calls come from the GENERIC_ENTRY preparation series, where each step was a no-op on its own. Commit 09a9d3a8499d ("powerpc: introduce arch_enter_from_user_mode") added the hook with the user-time accounting in it, but nothing called it yet. Commit 893082ac769b ("powerpc: Prepare for IRQ entry exit") copied interrupt_enter_prepare() verbatim into entry-common.h as arch_interrupt_enter_prepare(); that copy was equally unused, as handlers still called interrupt_enter_prepare(). Commit bee25f97ad24 ("powerpc: Enable GENERIC_ENTRY feature") made both live. On the syscall side it did the full conversion: system_call_exception() now accounts once through the hook via syscall_enter_from_user_mode(), rather than calling account_cpu_user_entry() directly. On the interrupt side it switched the handler macros to arch_interrupt_enter_prepare() followed by irqentry_enter(), which also runs the hook, but the accounting in arch_interrupt_enter_prepare() was not removed to match. The double accounting starts with that commit. With CONFIG_VIRT_CPU_ACCOUNTING_NATIVE=y this roughly doubles the reported user time of any workload that takes interrupts. The other accounting modes compile account_cpu_user_entry() to an empty stub, so they are not affected. Remove the accounting from arch_interrupt_enter_prepare() and rely on arch_enter_from_user_mode(), which already runs for both syscalls and interrupts. The duplicate account_stolen_time() call is removed the same way. On a pseries LPAR a busy loop reports 6s user time in 3s elapsed (~210% CPU) before the fix, and 3s (~105% CPU) after it: $ python3 -c 'while True: pass' & $ sleep 3; ps -p $! -o etime,time,pcpu ELAPSED TIME %CPU Before 00:03 00:00:06 210 After 00:03 00:00:03 105 A 50% load reports ~70% usr / 30% idle before the fix, and ~49% usr / 51% idle after it: $ taskset -c 6 stress-ng --cpu 1 --cpu-load 50 & $ mpstat -P 6 1 CPU %usr %idle Before 6 69.74 30.26 After 6 48.51 50.50 Fixes: bee25f97ad24 ("powerpc: Enable GENERIC_ENTRY feature") Reviewed-by: Mukesh Kumar Chaurasiya (IBM) Signed-off-by: Aboorva Devarajan Tested-by: Venkat Rao Bagalkote Reviewed-by: Amit Machhiwal Reviewed-by: Ritesh Harjani (IBM) Reviewed-by: Christophe Leroy (CS GROUP) Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260904025831.3439809-1-aboorvad@linux.ibm.com --- arch/powerpc/include/asm/entry-common.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/powerpc/include/asm/entry-common.h b/arch/powerpc/include/asm/entry-common.h index 80b07750b531..8e91489fdf2b 100644 --- a/arch/powerpc/include/asm/entry-common.h +++ b/arch/powerpc/include/asm/entry-common.h @@ -222,8 +222,6 @@ static inline void arch_interrupt_enter_prepare(struct pt_regs *regs) if (user_mode(regs)) { kuap_lock(); - account_cpu_user_entry(); - account_stolen_time(); } else { kuap_save_and_lock(regs); /* From ef17515a8ef88c246c342a6c532aa10f9ecdcfaf Mon Sep 17 00:00:00 2001 From: Athira Rajeev Date: Thu, 3 Sep 2026 13:10:36 +0530 Subject: [PATCH 1053/1198] selftests/powerpc/pmu/ebb: fix lost_exception_test hang with sched yield change commit 79104becf42b ("sched/fair: Forfeit vruntime on yield") changed yield_task_fair() to only bump the deadline when the entity is eligible (vruntime <= avg_vruntime). When the entity is ineligible the yield becomes a complete no-op from scheduling perspective. lost_exception_test calls sched_yield() 100,000 times per iteration to race the EBB exception delivery with a context switch to the eat_cpu companion process. After enough iterations the test process's vruntime races ahead of avg_vruntime (each eligible yield bumps vruntime to deadline, then advances deadline by one slice). Once ineligible, yield_task_fair() does nothing: so the scheduler won't pick the eat_cpu child. No context switch occurs, the PMAO race is never triggered, and ebb_count stays at 0 forever causing the test to hang until timeout. Fix by replacing sched_yield() with nanosleep(0, 1ns). nanosleep() goes through hrtimer_nanosleep() -> do_nanosleep(), which puts the task into TASK_INTERRUPTIBLE and removes it from the run queue entirely. This guarantees the scheduler picks the eat_cpu child, restoring the context-switch guarantee the test requires. The 1ns duration is enough to engage the hrtimer path while keeping the sleep effectively instantaneous; the same race window between PMU overflow and context switch is preserved. Reported-by: Venkat Rao Bagalkote Signed-off-by: Athira Rajeev Tested-by: Venkat Rao Bagalkote Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260903074036.63309-1-atrajeev@linux.ibm.com --- .../selftests/powerpc/pmu/ebb/lost_exception_test.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c b/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c index ba2681a12cc7..9be5945f3b1f 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c +++ b/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c @@ -8,6 +8,7 @@ #include #include #include +#include #include "ebb.h" @@ -22,6 +23,7 @@ static int test_body(void) { int i, orig_period, max_period; struct event event; + struct timespec ts = { .tv_sec = 0, .tv_nsec = 1 }; SKIP_IF(!ebb_is_supported()); @@ -57,10 +59,15 @@ static int test_body(void) * kernel to decide our timeslice is up and context switch to * the other thread. When we come back our EBB will have been * lost and we'll spin in this while loop forever. + * + * Use nanosleep(0) instead of sched_yield() to guarantee a + * context switch to the eat_cpu child regardless of the + * eligibility state. sched_yield() via yield_task_fair() may + * become a no-op when the task is ineligible (vruntime ahead + * of avg_vruntime), preventing the required context switch. */ - for (i = 0; i < 100000; i++) - sched_yield(); + nanosleep(&ts, NULL); /* Change the sample period slightly to try and hit the race */ if (sample_period >= (orig_period + 200)) From ed28b16eab705071d28edaace47189c2eb3aa108 Mon Sep 17 00:00:00 2001 From: Thibault Ferrante Date: Mon, 7 Sep 2026 23:54:20 +0200 Subject: [PATCH 1054/1198] selftests/powerpc/tm: Fix tcheck() reading uninitialised CR value tcheck() is used to check the current transaction state (active, suspended, doomed) via the "tcheck" instruction, which writes its result into CR field 0. The inline asm declared a GPR output operand for this result but never actually moved the CR into it. Every caller (tcheck_doomed(), tcheck_active(), tcheck_suspended(), tcheck_transactional()) has effectively been testing bits of an unrelated, arbitrary register value since this helper was introduced. The "& 4" mask discards the TDOOMED and TS_lsb (suspended) bits before they ever reach the callers, so tcheck_doomed() and tcheck_suspended() can never return true, and tcheck_transactional() degrades to being equivalent to tcheck_active(). Fix tcheck() to actually move CR into the output register with mfcr, and widen the mask from "& 4" to "& 0xf" so the full CR0 nibble (TDOOMED | TS_msb | TS_lsb | reserved) is preserved for the callers. This bug has been present since tcheck() was introduced. Link: https://bugs.launchpad.net/bugs/2107442 Fixes: 8e03bd4e70b6 ("selftests/powerpc: Add TM tcheck helpers in C") Signed-off-by: Thibault Ferrante Reported-by: Venkat Rao Bagalkote Tested-by: Venkat Rao Bagalkote Closes: https://lore.kernel.org/all/364996ce-aba2-4213-8d20-7dd481b43fe6@linux.ibm.com/ Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260907215420.1258678-1-thibault.ferrante@canonical.com --- tools/testing/selftests/powerpc/tm/tm.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/powerpc/tm/tm.h b/tools/testing/selftests/powerpc/tm/tm.h index c03c6e778876..6024ce4ba6ff 100644 --- a/tools/testing/selftests/powerpc/tm/tm.h +++ b/tools/testing/selftests/powerpc/tm/tm.h @@ -105,8 +105,12 @@ static inline bool failure_is_nesting(void) static inline int tcheck(void) { long cr; - asm volatile ("tcheck 0" : "=r"(cr) : : "cr0"); - return (cr >> 28) & 4; + asm volatile("tcheck 0;" + "mfcr %0;" + : "=r"(cr) + : + : "cr0"); + return (cr >> 28) & 0xf; } static inline bool tcheck_doomed(void) From 10557fe7fc9e09d273f8575274be2bbbe255dbf0 Mon Sep 17 00:00:00 2001 From: Michail Tatas Date: Tue, 4 Aug 2026 22:55:23 +0300 Subject: [PATCH 1055/1198] powerpc/pseries/htmdump: Fix leak in htmdump_init_debugfs If any allocation fails during init all previous allocations are leaked and the debugfs directory is left. Fix by freeing the allocations that have already happened and also remove the directory that has been created. Signed-off-by: Michail Tatas Reviewed-by: Athira Rajeev Reviewed-by: Ritesh Harjani (IBM) Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/anJDq-JckR6j-6EJ@michalis-linux --- arch/powerpc/platforms/pseries/htmdump.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/platforms/pseries/htmdump.c b/arch/powerpc/platforms/pseries/htmdump.c index 489a80e87082..f33941b80ada 100644 --- a/arch/powerpc/platforms/pseries/htmdump.c +++ b/arch/powerpc/platforms/pseries/htmdump.c @@ -527,28 +527,28 @@ static int htmdump_init_debugfs(void) htm_status_buf = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!htm_status_buf) { pr_err("Failed to allocate htmstatus buf\n"); - return -ENOMEM; + goto htm_status_buf_err; } /* Debugfs interface file to present System Processor Configuration */ htm_info_buf = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!htm_info_buf) { pr_err("Failed to allocate htm info buf\n"); - return -ENOMEM; + goto htm_info_buf_err; } /* Debugfs interface file to present HTM capabilities */ htm_caps_buf = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!htm_caps_buf) { pr_err("Failed to allocate htm caps buf\n"); - return -ENOMEM; + goto htm_caps_buf_err; } /* Memory to present HTM system memory configuration */ htm_mem_buf = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!htm_mem_buf) { pr_err("Failed to allocate htm mem buf\n"); - return -ENOMEM; + goto htm_mem_buf_err; } debugfs_create_file("htmstatus", 0400, htmdump_debugfs_dir, htm_status_buf, &htmstatus_fops); @@ -557,6 +557,17 @@ static int htmdump_init_debugfs(void) debugfs_create_file("htmsystem_mem", 0400, htmdump_debugfs_dir, htm_mem_buf, &htmsystem_mem_fops); return 0; + +htm_mem_buf_err: + kfree(htm_caps_buf); +htm_caps_buf_err: + kfree(htm_info_buf); +htm_info_buf_err: + kfree(htm_status_buf); +htm_status_buf_err: + debugfs_remove_recursive(htmdump_debugfs_dir); + kfree(htm_buf); + return -ENOMEM; } static int __init htmdump_init(void) From 1144454ea22290d7c6998a2af6239e5995476afc Mon Sep 17 00:00:00 2001 From: leixiang Date: Thu, 9 Jul 2026 13:57:52 +0800 Subject: [PATCH 1056/1198] KVM: PPC: Book3S HV: Set irqfd->producer only on success Set irqfd->producer only after kvmppc_set_passthru_irq() succeeds to avoid leaving a dangling pointer on failure. The bypass manager does not register a failed producer, so the pointer is never cleared. Fixes: c57875f5f9be ("KVM: PPC: Book3S HV: Enable IRQ bypass") Suggested-by: Sean Christopherson Cc: stable@vger.kernel.org Signed-off-by: leixiang Reviewed-by: Amit Machhiwal Reviewed-by: Vaibhav Jain Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260709055755.31297-1-leixiang@kylinos.cn --- arch/powerpc/kvm/book3s_hv.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 0409ac9e7b31..dbac3573b2c8 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -6140,12 +6140,12 @@ static int kvmppc_irq_bypass_add_producer_hv(struct irq_bypass_consumer *cons, struct kvm_kernel_irqfd *irqfd = container_of(cons, struct kvm_kernel_irqfd, consumer); - irqfd->producer = prod; - ret = kvmppc_set_passthru_irq(irqfd->kvm, prod->irq, irqfd->gsi); if (ret) pr_info("kvmppc_set_passthru_irq (irq %d, gsi %d) fails: %d\n", prod->irq, irqfd->gsi, ret); + else + irqfd->producer = prod; return ret; } From e58b9d90973e09f1908d2cd00ca2336a8232b9f8 Mon Sep 17 00:00:00 2001 From: Sourabh Jain Date: Fri, 25 Jul 2025 18:14:38 +0530 Subject: [PATCH 1057/1198] powerpc/kexec_file: print configured kernel command line Kexec with the -d option prints extra logs about the kexec/kdump kernel that help debug kexec and kdump. For example, it shows what kexec segments are loaded, their locations, and sizes. One key piece of information still missing is the kernel command line configured for the kexec/kdump kernel. With this patch included, the kernel will print the kernel command line configured for the kexec/kdump kernel as shown below: kexec --initrd=./initrd ./kernel -lspd --command-line="test1 test2" Loaded elf core header at 0x22e30000, bufsz=0x2000 memsz=0x80000 kexec_elf: Command line: elfcorehdr=0x22e30000 test1 test2 <--- New kexec_elf: Loaded initrd at 0x22eb0000 Signed-off-by: Sourabh Jain Tested-by: Mukesh Kumar Chaurasiya (IBM) Reviewed-by: Mukesh Kumar Chaurasiya (IBM) Reviewed-by: Ritesh Harjani (IBM) Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20250725124438.327593-1-sourabhjain@linux.ibm.com --- arch/powerpc/kexec/elf_64.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/powerpc/kexec/elf_64.c b/arch/powerpc/kexec/elf_64.c index ea50a072debf..d9a466cd602e 100644 --- a/arch/powerpc/kexec/elf_64.c +++ b/arch/powerpc/kexec/elf_64.c @@ -94,6 +94,8 @@ static void *elf64_load(struct kimage *image, char *kernel_buf, cmdline = modified_cmdline; } + kexec_dprintk("Command line: %s", cmdline ? cmdline : ""); + if (initrd != NULL) { kbuf.buffer = initrd; kbuf.bufsz = kbuf.memsz = initrd_len; From bf1d8287816194457c1a936056ad2d1e1e478944 Mon Sep 17 00:00:00 2001 From: longlong yan Date: Wed, 22 Jul 2026 10:34:28 +0800 Subject: [PATCH 1058/1198] selftests/powerpc: use MAP_FAILED instead of (void *)-1 in tm-signal-context-force-tm mmap() is documented to return MAP_FAILED on error, but tm-signal-context-force-tm.c compares the return value against (void *)-1. Replace these with the standard MAP_FAILED macro for better readability and type safety. Signed-off-by: longlong yan Tested-by: Venkat Rao Bagalkote Reviewed-by: Amit Machhiwal Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260722023428.932-1-yanlonglong@kylinos.cn --- .../testing/selftests/powerpc/tm/tm-signal-context-force-tm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/powerpc/tm/tm-signal-context-force-tm.c b/tools/testing/selftests/powerpc/tm/tm-signal-context-force-tm.c index 0a4bc479ae39..5dc0f12f467d 100644 --- a/tools/testing/selftests/powerpc/tm/tm-signal-context-force-tm.c +++ b/tools/testing/selftests/powerpc/tm/tm-signal-context-force-tm.c @@ -60,7 +60,7 @@ void usr_signal_handler(int signo, siginfo_t *si, void *uc) ucp->uc_link = mmap(NULL, sizeof(ucontext_t), PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, 0, 0); - if (ucp->uc_link == (void *)-1) { + if (ucp->uc_link == MAP_FAILED) { perror("Mmap failed"); exit(-1); } @@ -129,7 +129,7 @@ void tm_trap_test(void) ss.ss_size = SIGSTKSZ; ss.ss_flags = 0; - if (ss.ss_sp == (void *)-1) { + if (ss.ss_sp == MAP_FAILED) { perror("mmap error\n"); exit(-1); } From 15f3ce3aa218f6d4cece9101f1af4332e8712e39 Mon Sep 17 00:00:00 2001 From: Sourabh Jain Date: Sat, 18 Apr 2026 14:42:50 +0530 Subject: [PATCH 1059/1198] powerpc/prom: Remove redundant early_init_dt_scan_root() call Commit 554b66233623 ("of/fdt: Scan the root node properties earlier") moved the invocation of early_init_dt_scan_root() into early_init_dt_verify(). early_init_devtree() already calls early_init_dt_verify(), so the root node properties are parsed before reaching the explicit call in this function. Keeping the call here results in scanning the root node twice. Remove the redundant call and rely on the invocation from early_init_dt_verify(). This change keeps the behavior the same and removes an unnecessary duplicate call. Signed-off-by: Sourabh Jain Tested-by: Shivang Upadhyay Reviewed-by: Ritesh Harjani (IBM) Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260418091250.134111-1-sourabhjain@linux.ibm.com --- arch/powerpc/kernel/prom.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 9ed9dde7d231..d218c8cc1f73 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -824,7 +824,6 @@ void __init early_init_devtree(void *params) fadump_append_bootargs(); /* Scan memory nodes and rebuild MEMBLOCKs */ - early_init_dt_scan_root(); early_init_dt_scan_memory_ppc(); /* From 9e5c53d75c560a058abef0e4338c5e3e52cb432a Mon Sep 17 00:00:00 2001 From: Kunwu Chan Date: Wed, 17 Jan 2024 17:17:06 +0800 Subject: [PATCH 1060/1198] powerpc/pasemi: Add a null pointer check to the pas_setup_mce_regs kasprintf() returns a pointer to dynamically allocated memory which can be NULL upon failure. Ensure the allocation was successful by checking the pointer validity. Signed-off-by: Kunwu Chan Reviewed-by: Christophe Leroy Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20240117091706.153431-1-chentao@kylinos.cn --- arch/powerpc/platforms/pasemi/setup.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/powerpc/platforms/pasemi/setup.c b/arch/powerpc/platforms/pasemi/setup.c index d03b41336901..45792ecd5dfd 100644 --- a/arch/powerpc/platforms/pasemi/setup.c +++ b/arch/powerpc/platforms/pasemi/setup.c @@ -165,6 +165,8 @@ static int __init pas_setup_mce_regs(void) while (dev && reg < MAX_MCE_REGS) { mce_regs[reg].name = kasprintf(GFP_KERNEL, "mc%d_mcdebug_errsta", reg); + if (!mce_regs[reg].name) + return -ENOMEM; mce_regs[reg].addr = pasemi_pci_getcfgaddr(dev, 0x730); dev = pci_get_device(PCI_VENDOR_ID_PASEMI, 0xa00a, dev); reg++; From a894f97318366d12102c15937aa6b63c21aa82b5 Mon Sep 17 00:00:00 2001 From: Mitul Golani Date: Tue, 25 Aug 2026 13:02:04 +0530 Subject: [PATCH 1061/1198] drm/i915/dp: Gate UHBR SST SDP splitting on sink capability SDP splitting for 128b/132b (UHBR) SST audio must only be enabled when the sink advertises support for it. Previously sdp_split_enable was set for every UHBR SST stream carrying audio, regardless of sink capability. In MST mode SDP splitting is inherently supported, so the sink capability check (DP_SST_SPLIT_SDP_CAP) is applied only to the SST path. Fixes: 8853750dbad8 ("drm/i915: Enable SDP split for DP2.0") Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Mitul Golani Reviewed-by: Suraj Kandpal Signed-off-by: Suraj Kandpal Link: https://patch.msgid.link/20260825073204.872441-1-mitulkumar.ajitkumar.golani@intel.com (cherry picked from commit b37921c9f533ca936c5b5a484c1299680c570a7e) Signed-off-by: Jani Nikula --- .../drm/i915/display/intel_display_types.h | 2 + drivers/gpu/drm/i915/display/intel_dp.c | 44 ++++++++++++++++--- 2 files changed, 40 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h index b7cc361fd955..43d53a98dae7 100644 --- a/drivers/gpu/drm/i915/display/intel_display_types.h +++ b/drivers/gpu/drm/i915/display/intel_display_types.h @@ -1946,6 +1946,8 @@ struct intel_dp { bool colorimetry_support; + bool sst_split_sdp_support; + struct { enum transcoder transcoder; struct mutex lock; diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 113d767e62e9..3152122e6aef 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -3409,12 +3409,22 @@ intel_dp_audio_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config, struct drm_connector_state *conn_state) { + struct intel_dp *intel_dp = enc_to_intel_dp(encoder); + pipe_config->has_audio = intel_dp_has_audio(encoder, conn_state) && intel_audio_compute_config(encoder, pipe_config, conn_state); pipe_config->sdp_split_enable = pipe_config->has_audio && intel_dp_is_uhbr(pipe_config); + + /* + * SDP splitting for UHBR audio requires explicit sink capability in + * SST mode, whereas in MST mode it is inherently supported. + */ + if (pipe_config->sdp_split_enable && + !intel_crtc_has_type(pipe_config, INTEL_OUTPUT_DP_MST)) + pipe_config->sdp_split_enable = intel_dp->sst_split_sdp_support; } void @@ -4462,16 +4472,25 @@ void intel_dp_configure_protocol_converter(struct intel_dp *intel_dp, str_enable_disable(tmp)); } -static bool intel_dp_get_colorimetry_status(struct intel_dp *intel_dp) +static u8 intel_dp_read_dprx_feature_enum(struct intel_dp *intel_dp) { u8 dprx = 0; - if (drm_dp_dpcd_readb(&intel_dp->aux, DP_DPRX_FEATURE_ENUMERATION_LIST, - &dprx) != 1) - return false; + drm_dp_dpcd_read_data(&intel_dp->aux, DP_DPRX_FEATURE_ENUMERATION_LIST, + &dprx, sizeof(dprx)); + return dprx; +} + +static bool intel_dp_get_colorimetry_status(u8 dprx) +{ return dprx & DP_VSC_SDP_EXT_FOR_COLORIMETRY_SUPPORTED; } +static bool intel_dp_get_sst_split_sdp_status(u8 dprx) +{ + return dprx & DP_SST_SPLIT_SDP_CAP; +} + static int intel_dp_read_dsc_dpcd(struct drm_dp_aux *aux, u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE]) { @@ -4771,6 +4790,7 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp, struct intel_connector *connector { struct intel_display *display = to_intel_display(intel_dp); int ret; + u8 dprx; /* this function is meant to be called only once */ drm_WARN_ON(display->drm, intel_dp->dpcd[DP_DPCD_REV] != 0); @@ -4782,8 +4802,13 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp, struct intel_connector *connector drm_dp_is_branch(intel_dp->dpcd)); intel_init_dpcd_quirks(intel_dp, &intel_dp->desc.ident); + dprx = intel_dp_read_dprx_feature_enum(intel_dp); + intel_dp->colorimetry_support = - intel_dp_get_colorimetry_status(intel_dp); + intel_dp_get_colorimetry_status(dprx); + + intel_dp->sst_split_sdp_support = + intel_dp_get_sst_split_sdp_status(dprx); /* * Read the eDP display control registers. @@ -4874,13 +4899,20 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp) * the OUI/ID since we know it won't change. */ if (!intel_dp_is_edp(intel_dp)) { + u8 dprx; + drm_dp_read_desc(&intel_dp->aux, &intel_dp->desc, drm_dp_is_branch(intel_dp->dpcd)); intel_init_dpcd_quirks(intel_dp, &intel_dp->desc.ident); + dprx = intel_dp_read_dprx_feature_enum(intel_dp); + intel_dp->colorimetry_support = - intel_dp_get_colorimetry_status(intel_dp); + intel_dp_get_colorimetry_status(dprx); + + intel_dp->sst_split_sdp_support = + intel_dp_get_sst_split_sdp_status(dprx); intel_dp_update_sink_caps(intel_dp); } From cbd3dafc2003db679ccd2f6c6a2551db79657049 Mon Sep 17 00:00:00 2001 From: Thorsten Blum Date: Sun, 23 Aug 2026 22:50:28 +0200 Subject: [PATCH 1062/1198] drm/i915: Fix memory leak in query_perf_config_list() When krealloc() fails, free the original oa_config_ids before returning to avoid a memory leak. Fixes: 4f6ccc74a85c ("drm/i915: add support for perf configuration queries") Signed-off-by: Thorsten Blum Cc: # v5.5+ Reviewed-by: Andi Shyti Signed-off-by: Andi Shyti Link: https://patch.msgid.link/20260823205028.178597-2-thorsten.blum@linux.dev (cherry picked from commit 9977e9d84f46d4f12ad35fbbc0ec4638554bce87) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_query.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c index 0c55fb6e9727..11157fb14db3 100644 --- a/drivers/gpu/drm/i915/i915_query.c +++ b/drivers/gpu/drm/i915/i915_query.c @@ -403,8 +403,10 @@ static int query_perf_config_list(struct drm_i915_private *i915, ids = krealloc(oa_config_ids, n_configs * sizeof(*oa_config_ids), GFP_KERNEL); - if (!ids) + if (!ids) { + kfree(oa_config_ids); return -ENOMEM; + } alloc = fetch_and_zero(&n_configs); From 59e63416f5153e7d58652c616fbdcb7d5e01fff7 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Tue, 8 Sep 2026 12:56:37 +0200 Subject: [PATCH 1063/1198] perf/core: Allow list_del during perf_event_overflow() A PMU might use perf_sched_cb_inc() and perf_sched_cb_dec() interface to get the PMU call back function pmu::sched_task invoked at schedule in and schedule out. This is achieved by walking along the list anchored by sched_cb_list. The following scenario might lead to a list corruption. perf_pmu_sched_task() for_each_list_entry(..., &sched_cb_list) +--> __perf_pmu_sched_task() +--> event->pmu->sched_task()) +--> PMU_push_sample() +--> perf_event_overflow() +--> __perf_event_overflow() +--> pmu->stop() +--> perf_sched_cb_dec() remove entry from sched_cb_list while list node in use. This happens when ioctl(fd, PERF_EVENT_IOC_REFRESH, xxx) has been invoked and perf_event::event_limit hits zero. Prevent the list corruption and convert for_each_list_entry() to for_each_list_entry_safe(). Fixes: bd2756811766 ("perf: Rewrite core context handling") Signed-off-by: Thomas Richter Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20260908105637.627004-1-tmricht@linux.ibm.com --- kernel/events/core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 33210aff3ee6..fe33fe15689d 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3925,13 +3925,13 @@ static void perf_pmu_sched_task(struct task_struct *prev, bool sched_in) { struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context); - struct perf_cpu_pmu_context *cpc; + struct perf_cpu_pmu_context *cpc, *cpc2; /* cpuctx->task_ctx will be handled in perf_event_context_sched_in/out */ if (prev == next || cpuctx->task_ctx) return; - list_for_each_entry(cpc, this_cpu_ptr(&sched_cb_list), sched_cb_entry) + list_for_each_entry_safe(cpc, cpc2, this_cpu_ptr(&sched_cb_list), sched_cb_entry) __perf_pmu_sched_task(cpc, sched_in ? next : prev, sched_in); } From 88aa1223bfffb1a0a98c639e9e1f71058f0d9178 Mon Sep 17 00:00:00 2001 From: Dapeng Mi Date: Tue, 8 Sep 2026 15:51:01 +0800 Subject: [PATCH 1064/1198] perf/x86/intel: Correct pt_regs->flags update for PEBS path pt_regs->flags holds the saved CPU FLAGS register. In the PEBS path, it was incorrectly set to PERF_EFLAGS_EXACT instead of being populated from the PEBS flags snapshot. Update pt_regs->flags from PEBS GPR flags if GPRs group is present. Fixes: c22497f5838c ("perf/x86/intel: Support adaptive PEBS v4") Signed-off-by: Dapeng Mi Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20260908075102.540715-1-dapeng1.mi@linux.intel.com --- arch/x86/events/intel/ds.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 8940f0292229..d0bb767a0fef 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -2432,7 +2432,7 @@ static inline void __setup_pebs_basic_group(struct perf_event *event, { /* The ip in basic is EventingIP */ set_linear_ip(regs, ip); - regs->flags = PERF_EFLAGS_EXACT; + regs->flags |= PERF_EFLAGS_EXACT; setup_pebs_time(event, data, tsc); if (sample_type & PERF_SAMPLE_WEIGHT_STRUCT) @@ -2444,9 +2444,17 @@ static inline void __setup_pebs_gpr_group(struct perf_event *event, struct pebs_gprs *gprs, u64 sample_type) { + /* + * Update flags with PEBS data. PERF_EFLAGS_EXACT must be set + * in previous basic group handling. + */ + regs->flags = gprs->flags | PERF_EFLAGS_EXACT; + if (event->attr.precise_ip < 2) { set_linear_ip(regs, gprs->ip); regs->flags &= ~PERF_EFLAGS_EXACT; + } else if (regs->flags & X86_VM_MASK) { + regs->flags ^= (PERF_EFLAGS_VM | X86_VM_MASK); } if (sample_type & (PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER)) From a56c03a397e2cd0c4cf8da96dcd6214f7d0e7d8c Mon Sep 17 00:00:00 2001 From: Dapeng Mi Date: Thu, 13 Aug 2026 14:43:46 +0800 Subject: [PATCH 1065/1198] perf/x86/intel: Prevent drain_pebs() reentry The PEBS buffer is shared by all events on a CPU, so drain_pebs() must not be reentered. If so, one instance may observe stale buffer state and potentially access out-of-bound memory. Most invocations happen in NMI context, which naturally prevents reentry. However, drain_pebs() is also reachable from process context via intel_pmu_drain_pebs_buffer(). In those paths, the PMU is often already disabled, but not guaranteed. For example, __intel_pmu_pebs_disable() only disables the target counter, so other active counters can still raise a PMI and interrupt an in-flight drain_pebs(). Here is an example, __perf_addr_filters_adjust() perf_event_stop() __perf_event_stop() x86_pmu_stop() (event->pmu->stop) intel_pmu_disable_event() intel_pmu_pebs_disable() __intel_pmu_pebs_disable() intel_pmu_drain_large_pebs() intel_pmu_drain_pebs_buffer() Introduce __intel_pmu_quiesce() and __intel_pmu_resume() helpers and use them in intel_pmu_drain_large_pebs() to disable the full PMU around the intel_pmu_drain_pebs_buffer() call, preventing reentry. Also add a warning in intel_pmu_drain_pebs_buffer() when the full PMU is not disabled. Fixes: b752ea0c28e3 ("perf/x86/intel/ds: Flush PEBS DS when changing PEBS_DATA_CFG") Signed-off-by: Dapeng Mi Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20260813064346.335458-1-dapeng1.mi@linux.intel.com --- arch/x86/events/intel/core.c | 33 ++++++++++++++++++++++++--------- arch/x86/events/intel/ds.c | 8 +++++++- arch/x86/events/perf_event.h | 3 +++ 3 files changed, 34 insertions(+), 10 deletions(-) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index cc13164d948f..1ac2ca35db53 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3125,6 +3125,27 @@ static void intel_pmu_del_event(struct perf_event *event) this_cpu_ptr(&cpu_hw_events)->n_late_setup--; } +int __intel_pmu_quiesce(void) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + int pmu_enabled = cpuc->enabled; + + cpuc->enabled = 0; + if (pmu_enabled) + intel_pmu_disable_all(); + + return pmu_enabled; +} + +void __intel_pmu_resume(int pmu_enabled) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + cpuc->enabled = pmu_enabled; + if (pmu_enabled) + intel_pmu_enable_all(0); +} + static int icl_set_topdown_event_period(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; @@ -3316,16 +3337,13 @@ static void intel_pmu_read_event(struct perf_event *event) if (event->hw.flags & (PERF_X86_EVENT_AUTO_RELOAD | PERF_X86_EVENT_TOPDOWN) || is_pebs_counter_event_group(event)) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - bool pmu_enabled = cpuc->enabled; + int pmu_enabled; /* Only need to call update_topdown_event() once for group read. */ if (is_metric_event(event) && (cpuc->txn_flags & PERF_PMU_TXN_READ)) return; - cpuc->enabled = 0; - if (pmu_enabled) - intel_pmu_disable_all(); - + pmu_enabled = __intel_pmu_quiesce(); /* * If the PEBS counters snapshotting is enabled, * the topdown event is available in PEBS records. @@ -3334,10 +3352,7 @@ static void intel_pmu_read_event(struct perf_event *event) static_call(intel_pmu_update_topdown_event)(event, NULL); else intel_pmu_drain_pebs_buffer(); - - cpuc->enabled = pmu_enabled; - if (pmu_enabled) - intel_pmu_enable_all(0); + __intel_pmu_resume(pmu_enabled); return; } diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index d0bb767a0fef..b98029b44052 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1242,8 +1242,11 @@ int intel_pmu_drain_bts_buffer(void) void intel_pmu_drain_pebs_buffer(void) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct perf_sample_data data; + WARN_ON_ONCE(cpuc->enabled); + static_call(x86_pmu_drain_pebs)(NULL, &data); } @@ -1864,8 +1867,11 @@ static void intel_pmu_pebs_via_pt_enable(struct perf_event *event) static inline void intel_pmu_drain_large_pebs(struct cpu_hw_events *cpuc) { if (cpuc->n_pebs == cpuc->n_large_pebs && - cpuc->n_pebs != cpuc->n_pebs_via_pt) + cpuc->n_pebs != cpuc->n_pebs_via_pt) { + int enabled = __intel_pmu_quiesce(); intel_pmu_drain_pebs_buffer(); + __intel_pmu_resume(enabled); + } } static void __intel_pmu_pebs_enable(struct perf_event *event) diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 71ed5b2acea2..4680cba91340 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -1638,6 +1638,9 @@ static __always_inline void __intel_pmu_lbr_disable(void) wrmsrq(MSR_IA32_DEBUGCTLMSR, debugctl); } +extern int __intel_pmu_quiesce(void); +extern void __intel_pmu_resume(int pmu_enabled); + int intel_pmu_save_and_restart(struct perf_event *event); struct event_constraint * From 9a8bc9bb4c3fb3218b4f151f98a722fbeb5b5c34 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Mon, 7 Sep 2026 14:38:55 +0200 Subject: [PATCH 1066/1198] sched/eevdf: Fix augmented max_slice Similarly to se->min_slice, init se->max_slice with se->slice before enqueueing the entity so the augmented callback computes it correctly at parent level. Fixes: 6e3c0a4e1ad1 ("sched/fair: Fix lag clamp") Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: K Prateek Nayak Link: https://patch.msgid.link/20260907123855.1297976-1-vincent.guittot@linaro.org --- kernel/sched/fair.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index ade1eceb39b8..5b944f9a8a00 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1073,6 +1073,8 @@ static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) sum_w_vruntime_add(cfs_rq, se); se->min_vruntime = se->vruntime; se->min_slice = se->slice; + se->max_slice = se->slice; + rb_add_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline, __entity_less, &min_vruntime_cb); } From 51b0e68cfa0ac69e3c3ea9d6753af7e15dfaab22 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Wed, 9 Sep 2026 17:05:22 +0200 Subject: [PATCH 1067/1198] sched/eevdf: Fix rb augmented with multi fields The eevdf rb tree maintains 3 augmented fields but only one is currently copied when balancing the tree. Add a more generic define that can be used when there are several augmented fields. In this case, we provide a function that takes care of copying all fields. Fixes: aef6987d8954 ("sched/eevdf: Propagate min_slice up the cgroup hierarchy") Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: K Prateek Nayak Tested-by: K Prateek Nayak Link: https://patch.msgid.link/20260909150522.858312-1-vincent.guittot@linaro.org --- include/linux/rbtree_augmented.h | 35 +++++++++++++++++++++++++------- kernel/sched/fair.c | 12 +++++++++-- 2 files changed, 38 insertions(+), 9 deletions(-) diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h index 6dbc5a1bf6a8..d2fa1c41bfd2 100644 --- a/include/linux/rbtree_augmented.h +++ b/include/linux/rbtree_augmented.h @@ -87,18 +87,18 @@ rb_add_augmented_cached(struct rb_node *node, struct rb_root_cached *tree, } /* - * Template for declaring augmented rbtree callbacks (generic case) + * Template for declaring augmented rbtree callbacks (generic multi fields) * * RBSTATIC: 'static' or empty * RBNAME: name of the rb_augment_callbacks structure * RBSTRUCT: struct type of the tree nodes * RBFIELD: name of struct rb_node field within RBSTRUCT - * RBAUGMENTED: name of field within RBSTRUCT holding data for subtree - * RBCOMPUTE: name of function that recomputes the RBAUGMENTED data + * RBCOPY: name of function that copies the RBAUGMENTED datas + * RBCOMPUTE: name of function that recomputes the RBAUGMENTED datas */ -#define RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ - RBSTRUCT, RBFIELD, RBAUGMENTED, RBCOMPUTE) \ +#define RB_DECLARE_CALLBACKS_MULTI(RBSTATIC, RBNAME, \ + RBSTRUCT, RBFIELD, RBCOPY, RBCOMPUTE) \ static inline void \ RBNAME ## _propagate(struct rb_node *rb, struct rb_node *stop) \ { \ @@ -114,14 +114,14 @@ RBNAME ## _copy(struct rb_node *rb_old, struct rb_node *rb_new) \ { \ RBSTRUCT *old = rb_entry(rb_old, RBSTRUCT, RBFIELD); \ RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD); \ - new->RBAUGMENTED = old->RBAUGMENTED; \ + RBCOPY(new, old); \ } \ static void \ RBNAME ## _rotate(struct rb_node *rb_old, struct rb_node *rb_new) \ { \ RBSTRUCT *old = rb_entry(rb_old, RBSTRUCT, RBFIELD); \ RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD); \ - new->RBAUGMENTED = old->RBAUGMENTED; \ + RBCOPY(new, old); \ RBCOMPUTE(old, false); \ } \ RBSTATIC const struct rb_augment_callbacks RBNAME = { \ @@ -130,6 +130,27 @@ RBSTATIC const struct rb_augment_callbacks RBNAME = { \ .rotate = RBNAME ## _rotate \ }; +/* + * Template for declaring augmented rbtree callbacks (generic single field) + * + * RBSTATIC: 'static' or empty + * RBNAME: name of the rb_augment_callbacks structure + * RBSTRUCT: struct type of the tree nodes + * RBFIELD: name of struct rb_node field within RBSTRUCT + * RBAUGMENTED: name of field within RBSTRUCT holding data for subtree + * RBCOMPUTE: name of function that recomputes the RBAUGMENTED data + */ + +#define RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ + RBSTRUCT, RBFIELD, RBAUGMENTED, RBCOMPUTE) \ +static inline void \ +RBNAME ## _copy_single(RBSTRUCT *new, RBSTRUCT *old) \ +{ \ + new->RBAUGMENTED = old->RBAUGMENTED; \ +} \ +RB_DECLARE_CALLBACKS_MULTI(RBSTATIC, RBNAME, \ + RBSTRUCT, RBFIELD, RBNAME ## _copy_single, RBCOMPUTE) + /* * Template for declaring augmented rbtree callbacks, * computing RBAUGMENTED scalar as max(RBCOMPUTE(node)) for all subtree nodes. diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 5b944f9a8a00..944833e8056f 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1032,6 +1032,13 @@ static inline void __max_slice_update(struct sched_entity *se, struct rb_node *n } } +static inline void min_vruntime_copy(struct sched_entity *new, struct sched_entity *old) +{ + new->min_vruntime = old->min_vruntime; + new->min_slice = old->min_slice; + new->max_slice = old->max_slice; +} + /* * se->min_vruntime = min(se->vruntime, {left,right}->min_vruntime) */ @@ -1059,8 +1066,9 @@ static inline bool min_vruntime_update(struct sched_entity *se, bool exit) se->max_slice == old_max_slice; } -RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity, - run_node, min_vruntime, min_vruntime_update); + +RB_DECLARE_CALLBACKS_MULTI(static, min_vruntime_cb, struct sched_entity, + run_node, min_vruntime_copy, min_vruntime_update); /* * Enqueue an entity into the rb-tree: From c23810313bdf6b02f39a1f2a1464c4b18bd39e31 Mon Sep 17 00:00:00 2001 From: Hui Su Date: Fri, 4 Sep 2026 11:47:07 +0800 Subject: [PATCH 1068/1198] sched: Account cgroup CPU time to the execution context Proxy execution separates the scheduling context from the execution context. Commit aa4f74dfd42b ("sched: Fix runtime accounting w/ split exec & sched contexts") made per-task and thread-group runtime accounting follow the task that actually executes, while cgroup CPU usage is charged to the donor. When the donor and execution task belong to different cgroups, this makes a task's execution time count against a different cgroup from the one the task belongs to. Cgroup CPU usage should follow the execution context, matching the per-task, thread-group, and cgroup user/system accounting. Keep scheduling state associated with the donor, but charge cgroup CPU usage to rq->curr. A reproducer with the donor and execution task in separate cgroups showed the execution task accumulating runtime while cgroup CPU usage was charged to the donor's cgroup. With this change, the execution task's cgroup accumulates the CPU usage instead. The same behavior was verified with an RT donor and with legacy cpuacct accounting. Fixes: aa4f74dfd42b ("sched: Fix runtime accounting w/ split exec & sched contexts") Suggested-by: Tejun Heo Signed-off-by: Hui Su Signed-off-by: Peter Zijlstra (Intel) Acked-by: Tejun Heo Acked-by: John Stultz Link: https://patch.msgid.link/20260904034707.268416-1-sh_def@163.com --- kernel/sched/fair.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 944833e8056f..7455a83a6a99 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1414,7 +1414,6 @@ static s64 update_se(struct rq *rq, struct sched_entity *se) se->exec_start = now; if (entity_is_task(se)) { - struct task_struct *donor = task_of(se); struct task_struct *running = rq->curr; /* * If se is a task, we account the time against the running @@ -1427,8 +1426,7 @@ static s64 update_se(struct rq *rq, struct sched_entity *se) account_group_exec_runtime(running, delta_exec); account_mm_sched(rq, running, delta_exec); - /* cgroup time is always accounted against the donor */ - cgroup_account_cputime(donor, delta_exec); + cgroup_account_cputime(running, delta_exec); } else { /* If not task, account the time against donor se */ se->sum_exec_runtime += delta_exec; From f5741d2b34519d387edf6e9798fc7030c20a35f3 Mon Sep 17 00:00:00 2001 From: Hui Su Date: Wed, 2 Sep 2026 23:02:09 +0800 Subject: [PATCH 1069/1198] sched/core: Call wq_worker_tick() for the execution context wq_worker_tick() accounts CPU time and detects CPU-intensive work for the kworker that is actually running. With proxy execution, rq->donor is the scheduling context while rq->curr is the execution context. Calling the hook with rq->donor can skip workqueue accounting when a kworker is executing on behalf of a donor task. It can also account a blocked kworker when the donor is a worker but rq->curr is the task actually executing. The former can delay WORKER_CPU_INTENSIVE handling and pool concurrency management, which can delay pending kernel work and userspace operations depending on it. Use rq->curr for the workqueue tick hook while retaining rq->donor for scheduler accounting. Fixes: af0c8b2bf67b ("sched: Split scheduler and execution contexts") Signed-off-by: Hui Su Signed-off-by: Peter Zijlstra (Intel) Acked-by: Tejun Heo Link: https://patch.msgid.link/20260902150208.1209922-2-sh_def@163.com --- kernel/sched/core.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b998ef6b87af..7885ff76e69f 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5776,8 +5776,8 @@ void sched_tick(void) { int cpu = smp_processor_id(); struct rq *rq = cpu_rq(cpu); - /* accounting goes to the donor task */ - struct task_struct *donor; + /* scheduler accounting goes to the donor task */ + struct task_struct *curr, *donor; struct rq_flags rf; unsigned long hw_pressure; u64 resched_latency; @@ -5788,6 +5788,7 @@ void sched_tick(void) sched_clock_tick(); rq_lock(rq, &rf); + curr = rq->curr; donor = rq->donor; psi_account_irqtime(rq, donor, NULL); @@ -5813,8 +5814,8 @@ void sched_tick(void) perf_event_task_tick(); - if (donor->flags & PF_WQ_WORKER) - wq_worker_tick(donor); + if (curr->flags & PF_WQ_WORKER) + wq_worker_tick(curr); if (!scx_switched_all()) { rq->idle_balance = idle_cpu(cpu); From 00f9fbc12320253bfc576fb7539d860029c82d0f Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 7 Sep 2026 08:52:35 +0200 Subject: [PATCH 1070/1198] net: hso: fix TIOCMIWAIT race The task state must be updated before checking the wakeup condition to avoid missing a racing modem status update. Fixes: 542f54823614 ("tty: Modem functions for the HSO driver") Cc: stable@vger.kernel.org # 2.6.29 Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260907065235.100848-1-johan@kernel.org Signed-off-by: Paolo Abeni --- drivers/net/usb/hso.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index c1aec67688ae..71caa3764b23 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -1547,10 +1547,10 @@ hso_wait_modem_status(struct hso_serial *serial, unsigned long arg) spin_unlock_irq(&serial->serial_lock); add_wait_queue(&tiocmget->waitq, &wait); for (;;) { + set_current_state(TASK_INTERRUPTIBLE); spin_lock_irq(&serial->serial_lock); memcpy(&cnow, &tiocmget->icount, sizeof(struct uart_icount)); spin_unlock_irq(&serial->serial_lock); - set_current_state(TASK_INTERRUPTIBLE); if (((arg & TIOCM_RNG) && (cnow.rng != cprev.rng)) || ((arg & TIOCM_DSR) && (cnow.dsr != cprev.dsr)) || ((arg & TIOCM_CD) && (cnow.dcd != cprev.dcd))) { From 1853f30cf5c84971f99788a76207c6f745380896 Mon Sep 17 00:00:00 2001 From: Victor Nogueira Date: Mon, 7 Sep 2026 16:21:30 -0300 Subject: [PATCH 1071/1198] net/sched: cls_route: free emptied bucket on filter move route4_change can move an existing filter to a different top-level bucket: route4_set_parms recomputes the handle from TCA_ROUTE4_TO/ FROM/IIF, and the handle-mismatch check is gated on the 'new' flag, so for an existing filter the new handle may differ from the old one and land in a different bucket. When this happens, the filter is unlinked from the old bucket, but the bucket itself is never freed once it goes empty. The stale empty bucket remains in head->table[], causing route4_delete to report *last=false even after the last live filter is gone. That pins the empty tcf_proto and causes a leak. Fix this by refcounting the filters linked to a bucket and freeing the bucket when the count drops to zero. The existing scan in route4_delete goes away with it. The count is updated at all sites that link or unlink a filter during add, change and delete, and the bucket is dropped from head->table[] as soon as it reaches zero. Conditions to recreate the bug: CONFIG_NET_CLS_ROUTE4=y, CONFIG_NET_SCH_INGRESS=y, CONFIG_NET_CLS_ACT=y. tc qdisc replace dev lo clsact tc filter add dev lo ingress protocol ip pref 100 route from 1 to 1 tc filter change dev lo ingress protocol ip pref 100 handle 0x10001 \ route from 1 to 2 tc filter del dev lo ingress protocol ip pref 100 handle 0x10002 \ route from 1 to 2 tc filter show dev lo ingress | grep -c 'pref 100 route chain 0 ' Fixes: 1e052be69d04 ("net_sched: destroy proto tp when all filters are gone") Reported-by: Vega Acked-by: Jamal Hadi Salim Signed-off-by: Victor Nogueira Link: https://patch.msgid.link/20260907192133.2639067-2-victor@mojatatu.com Signed-off-by: Paolo Abeni --- net/sched/cls_route.c | 45 +++++++++++++++++++++---------------------- 1 file changed, 22 insertions(+), 23 deletions(-) diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 0d1324c90583..17b0ebb76662 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -41,6 +42,7 @@ struct route4_head { struct route4_bucket { /* 16 FROM buckets + 16 IIF buckets + 1 wildcard bucket */ struct route4_filter __rcu *ht[16 + 16 + 1]; + refcount_t filters_ref; struct rcu_head rcu; }; @@ -336,7 +338,7 @@ static int route4_delete(struct tcf_proto *tp, void *arg, bool *last, struct route4_filter *nf; struct route4_bucket *b; unsigned int h = 0; - int i, h1; + int h1; if (!head || !f) return -EINVAL; @@ -362,23 +364,14 @@ static int route4_delete(struct tcf_proto *tp, void *arg, bool *last, tcf_exts_get_net(&f->exts); tcf_queue_work(&f->rwork, route4_delete_filter_work); - /* Strip RTNL protected tree */ - for (i = 0; i <= 32; i++) { - struct route4_filter *rt; - - rt = rtnl_dereference(b->ht[i]); - if (rt) - goto out; + if (refcount_dec_and_test(&b->filters_ref)) { + RCU_INIT_POINTER(head->table[to_hash(h)], NULL); + kfree_rcu(b, rcu); } - - /* OK, session has no flows */ - RCU_INIT_POINTER(head->table[to_hash(h)], NULL); - kfree_rcu(b, rcu); break; } } -out: *last = true; for (h1 = 0; h1 <= 256; h1++) { if (rcu_access_pointer(head->table[h1])) { @@ -459,6 +452,7 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, if (b == NULL) return -ENOBUFS; + refcount_set(&b->filters_ref, 1); rcu_assign_pointer(head->table[h1], b); } else { unsigned int h2 = from_hash(nhandle >> 16); @@ -468,6 +462,8 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, fp = rtnl_dereference(fp->next)) if (fp->handle == f->handle) return -EEXIST; + + refcount_inc(&b->filters_ref); } if (tb[TCA_ROUTE4_TO]) @@ -500,7 +496,7 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, struct route4_filter *fold, *f1, *pfp, *f = NULL; struct route4_bucket *b; struct nlattr *tb[TCA_ROUTE4_MAX + 1]; - unsigned int h, th; + unsigned int h; int err; bool new = true; @@ -560,17 +556,20 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, rcu_assign_pointer(*fp, f); if (fold) { - th = to_hash(fold->handle); + b = fold->bkt; h = from_hash(fold->handle >> 16); - b = rtnl_dereference(head->table[th]); - if (b) { - fp = &b->ht[h]; - for (pfp = rtnl_dereference(*fp); pfp; - fp = &pfp->next, pfp = rtnl_dereference(*fp)) { - if (pfp == fold) { - rcu_assign_pointer(*fp, fold->next); - break; + fp = &b->ht[h]; + for (pfp = rtnl_dereference(*fp); pfp; + fp = &pfp->next, pfp = rtnl_dereference(*fp)) { + if (pfp == fold) { + rcu_assign_pointer(*fp, fold->next); + if (refcount_dec_and_test(&b->filters_ref)) { + unsigned int th = to_hash(fold->handle); + + RCU_INIT_POINTER(head->table[th], NULL); + kfree_rcu(b, rcu); } + break; } } } From b74a8455a2f271f54695b6a8ec1f113824a46c0e Mon Sep 17 00:00:00 2001 From: Victor Nogueira Date: Mon, 7 Sep 2026 16:21:31 -0300 Subject: [PATCH 1072/1198] net/sched: cls_route: Reject handle aliasing route4_set_parms() rejects a duplicate by scanning the destination chain for f->handle, but f->handle is the handle the filter has before the update, not the one it is about to be linked under. The comparison and the insertion therefore use different handles, which causes breakage. When a change moves the filter to a chain that already holds nhandle, the scan looks for the old handle instead, misses the collision and links a second filter with the same handle: tc filter add dev lo ingress protocol ip pref 100 \ route from 1 to 1 classid 1:1 action ok tc filter add dev lo ingress protocol ip pref 100 \ route from 2 to 2 classid 1:2 action drop tc filter change dev lo ingress protocol ip pref 100 handle 0x10001 \ route from 2 to 2 classid 1:1 action ok tc filter show dev lo ingress ... fh 0x00020002 flowid 1:2 to 2 from 2 ... fh 0x00020002 flowid 1:1 to 2 from 2 The newcomer is appended after the incumbent, and both end up with the same f->id. route4_get() returns the first match, so the second filter can no longer be addressed by handle, and route4_classify() stops at the first filter whose f->id matches. The second filter is dumped but is effectively dead. Fix this by comparing against nhandle. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Sashiko Closes: https://netdev-ai.bots.linux.dev/sashiko/#/patchset/20260829205422.854785-1-victor%40mojatatu.com Acked-by: Jamal Hadi Salim Signed-off-by: Victor Nogueira Link: https://patch.msgid.link/20260907192133.2639067-3-victor@mojatatu.com Signed-off-by: Paolo Abeni --- net/sched/cls_route.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 17b0ebb76662..9710b77d379c 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -460,8 +460,12 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, for (fp = rtnl_dereference(b->ht[h2]); fp; fp = rtnl_dereference(fp->next)) - if (fp->handle == f->handle) + if (fp->handle == nhandle) { + NL_SET_ERR_MSG_FMT(extack, + "Handle %x is already in use", + nhandle); return -EEXIST; + } refcount_inc(&b->filters_ref); } From 41e85e54e5649a1617698438b0ce64c6f9d83d69 Mon Sep 17 00:00:00 2001 From: Victor Nogueira Date: Mon, 7 Sep 2026 16:21:32 -0300 Subject: [PATCH 1073/1198] net/sched: cls_route: Fix in-place replace Building on the previous patch, route4_set_parms rejects a duplicate by scanning the destination chain for nhandle, but the scan doesn't exclude the older version it is replacing, so an in-place replace will match the older version's handle and fail. Fix this by passing the older filter as a parameter to route4_set_parms (replacing "new") and skipping it in the scan. Excluding the older version is not enough on its own. nhandle is built out of TCA_ROUTE4_TO, TCA_ROUTE4_FROM and TCA_ROUTE4_IIF alone, while the 0x7F00 bits, which only tell apart filters sharing one key, are folded in on the create path. Letting the replace through would therefore rename the filter it replaces: replacing handle 0x10101 stored it back as 0x10001, and a sibling at 0x10201 could then no longer be replaced at all, since its own nhandle collided with the renamed filter. tc filter add ... handle 0x10101 route from 1 to 1 classid 1:1 tc filter add ... handle 0x10201 route from 1 to 1 classid 1:2 tc filter replace ... handle 0x10101 route from 1 to 1 classid 1:9 ... fh 0x00010001 flowid 1:9 to 1 from 1 ... fh 0x00010201 flowid 1:2 to 1 from 1 tc filter replace ... handle 0x10201 route from 1 to 1 classid 1:8 Error: Handle 10001 is already in use. So carry those bits over when the key the request builds is the key the older filter already has. An in-place replace then keeps the handle userspace named the filter by, while a request that does change the key still renames it, as it did before. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Sashiko Closes: https://netdev-ai.bots.linux.dev/sashiko/#/patchset/20260829205422.854785-1-victor%40mojatatu.com Acked-by: Jamal Hadi Salim Signed-off-by: Victor Nogueira Link: https://patch.msgid.link/20260907192133.2639067-4-victor@mojatatu.com Signed-off-by: Paolo Abeni --- net/sched/cls_route.c | 27 +++++++++++++-------------- 1 file changed, 13 insertions(+), 14 deletions(-) diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 9710b77d379c..0f211f030fd9 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -393,8 +393,9 @@ static const struct nla_policy route4_policy[TCA_ROUTE4_MAX + 1] = { static int route4_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, struct route4_filter *f, u32 handle, struct route4_head *head, - struct nlattr **tb, struct nlattr *est, int new, - u32 flags, struct netlink_ext_ack *extack) + struct nlattr **tb, struct nlattr *est, + struct route4_filter *fold, u32 flags, + struct netlink_ext_ack *extack) { u32 id = 0, to = 0, nhandle = 0x8000; struct route4_filter *fp; @@ -407,7 +408,7 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, return err; if (tb[TCA_ROUTE4_TO]) { - if (new && handle & 0x8000) { + if (!fold && handle & 0x8000) { NL_SET_ERR_MSG(extack, "Invalid handle"); return -EINVAL; } @@ -430,14 +431,14 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, } else nhandle |= 0xFFFF << 16; - if (handle && new) { + if (handle && (!fold || nhandle == (handle & ~0x7F00))) nhandle |= handle & 0x7F00; - if (nhandle != handle) { - NL_SET_ERR_MSG_FMT(extack, - "Handle mismatch constructed: %x (expected: %x)", - handle, nhandle); - return -EINVAL; - } + + if (handle && !fold && nhandle != handle) { + NL_SET_ERR_MSG_FMT(extack, + "Handle mismatch constructed: %x (expected: %x)", + handle, nhandle); + return -EINVAL; } if (!nhandle) { @@ -460,7 +461,7 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, for (fp = rtnl_dereference(b->ht[h2]); fp; fp = rtnl_dereference(fp->next)) - if (fp->handle == nhandle) { + if (fp != fold && fp->handle == nhandle) { NL_SET_ERR_MSG_FMT(extack, "Handle %x is already in use", nhandle); @@ -502,7 +503,6 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, struct nlattr *tb[TCA_ROUTE4_MAX + 1]; unsigned int h; int err; - bool new = true; if (!handle) { NL_SET_ERR_MSG(extack, "Creating with handle of 0 is invalid"); @@ -539,11 +539,10 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, f->tp = fold->tp; f->bkt = fold->bkt; - new = false; } err = route4_set_parms(net, tp, base, f, handle, head, tb, - tca[TCA_RATE], new, flags, extack); + tca[TCA_RATE], fold, flags, extack); if (err < 0) goto errout; From e190a7aabbea4fbfec0e74de134144cb4d040738 Mon Sep 17 00:00:00 2001 From: Victor Nogueira Date: Mon, 7 Sep 2026 16:21:33 -0300 Subject: [PATCH 1074/1198] selftests/tc-testing: Add cls_route bucket move and change tests Add 4 tdc tests for the cls_route bugs fixed earlier in this series: - Delete a route filter that was moved to another bucket (a7d2): Validates that deleting a filter, and making a bucket empty, does not leave a dangling empty bucket - Try to change a route filter onto an already used handle (c05a): Validates that attempting to change an existing filter's handle to an already taken one fails - Replace a route filter that shares its key with another filter (3f21): Validates that an in-place replace keeps the handle userspace named the filter by, rather than dropping the 0x7F00 bits from it - Replace both route filters sharing a key (9d0e): Validates that replacing one of the two does not make the other one unreplaceable Acked-by: Jamal Hadi Salim Signed-off-by: Victor Nogueira Link: https://patch.msgid.link/20260907192133.2639067-5-victor@mojatatu.com Signed-off-by: Paolo Abeni --- .../tc-testing/tc-tests/filters/route.json | 210 ++++++++++++++++++ 1 file changed, 210 insertions(+) diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/route.json b/tools/testing/selftests/tc-testing/tc-tests/filters/route.json index 05cedca67cca..2d5843aebd72 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/route.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/route.json @@ -202,5 +202,215 @@ "teardown": [ "$TC qdisc del dev $DEV1 parent root drr" ] + }, + { + "id": "a7d2", + "name": "Delete a route filter that was moved to another bucket", + "category": [ + "filter", + "route" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress", + "$TC filter add dev $DEV1 parent ffff: protocol ip prio 100 route from 1 to 1 classid 1:1", + "$TC filter change dev $DEV1 parent ffff: protocol ip prio 100 handle 0x10001 route from 1 to 2 classid 1:1", + "$TC filter add dev $DEV1 parent ffff: protocol ip prio 200 route from 5 to 5 classid 1:5" + ], + "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff: protocol ip prio 100 handle 0x10002 route from 1 to 2", + "expExitCode": "0", + "verifyCmd": "$TC -j filter show dev $DEV1 parent ffff:", + "matchJSON": [ + { + "protocol": "ip", + "pref": 200, + "kind": "route", + "chain": 0 + }, + { + "protocol": "ip", + "pref": 200, + "kind": "route", + "chain": 0, + "options": { + "fh": "0x50005", + "flowid": "1:5" + } + } + ], + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "c05a", + "name": "Try to change a route filter onto an already used handle", + "category": [ + "filter", + "route" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress", + "$TC filter add dev $DEV1 parent ffff: protocol ip prio 100 route from 1 to 1 classid 1:1 action ok", + "$TC filter add dev $DEV1 parent ffff: protocol ip prio 100 route from 2 to 2 classid 1:2 action drop" + ], + "cmdUnderTest": "$TC filter change dev $DEV1 parent ffff: protocol ip prio 100 handle 0x10001 route from 2 to 2 classid 1:1 action ok", + "expExitCode": "2", + "verifyCmd": "$TC -j filter show dev $DEV1 parent ffff:", + "matchJSON": [ + { + "protocol": "ip", + "pref": 100, + "kind": "route", + "chain": 0 + }, + { + "protocol": "ip", + "pref": 100, + "kind": "route", + "chain": 0, + "options": { + "fh": "0x10001", + "flowid": "1:1", + "actions": [ + { + "order": 1, + "kind": "gact", + "control_action": { + "type": "pass" + } + } + ] + } + }, + { + "protocol": "ip", + "pref": 100, + "kind": "route", + "chain": 0, + "options": { + "fh": "0x20002", + "flowid": "1:2", + "actions": [ + { + "order": 1, + "kind": "gact", + "control_action": { + "type": "drop" + } + } + ] + } + } + ], + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "3f21", + "name": "Replace a route filter that shares its key with another filter", + "category": [ + "filter", + "route" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress", + "$TC filter add dev $DEV1 parent ffff: protocol ip prio 100 handle 0x10101 route from 1 to 1 classid 1:1", + "$TC filter add dev $DEV1 parent ffff: protocol ip prio 100 handle 0x10201 route from 1 to 1 classid 1:2" + ], + "cmdUnderTest": "$TC filter replace dev $DEV1 parent ffff: protocol ip prio 100 handle 0x10101 route from 1 to 1 classid 1:9", + "expExitCode": "0", + "verifyCmd": "$TC -j filter show dev $DEV1 parent ffff:", + "matchJSON": [ + { + "protocol": "ip", + "pref": 100, + "kind": "route", + "chain": 0 + }, + { + "protocol": "ip", + "pref": 100, + "kind": "route", + "chain": 0, + "options": { + "fh": "0x10101", + "flowid": "1:9" + } + }, + { + "protocol": "ip", + "pref": 100, + "kind": "route", + "chain": 0, + "options": { + "fh": "0x10201", + "flowid": "1:2" + } + } + ], + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "9d0e", + "name": "Replace both route filters sharing a key", + "category": [ + "filter", + "route" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress", + "$TC filter add dev $DEV1 parent ffff: protocol ip prio 100 handle 0x10101 route from 1 to 1 classid 1:1", + "$TC filter add dev $DEV1 parent ffff: protocol ip prio 100 handle 0x10201 route from 1 to 1 classid 1:2", + "$TC filter replace dev $DEV1 parent ffff: protocol ip prio 100 handle 0x10101 route from 1 to 1 classid 1:9" + ], + "cmdUnderTest": "$TC filter replace dev $DEV1 parent ffff: protocol ip prio 100 handle 0x10201 route from 1 to 1 classid 1:8", + "expExitCode": "0", + "verifyCmd": "$TC -j filter show dev $DEV1 parent ffff:", + "matchJSON": [ + { + "protocol": "ip", + "pref": 100, + "kind": "route", + "chain": 0 + }, + { + "protocol": "ip", + "pref": 100, + "kind": "route", + "chain": 0, + "options": { + "fh": "0x10101", + "flowid": "1:9" + } + }, + { + "protocol": "ip", + "pref": 100, + "kind": "route", + "chain": 0, + "options": { + "fh": "0x10201", + "flowid": "1:8" + } + } + ], + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] } ] From dff39930ad5e53d202bfdfb14687d1d2fd753b4d Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Tue, 8 Sep 2026 20:55:25 +0000 Subject: [PATCH 1075/1198] net/sched: cls_api: Don't replay RTM_GETCHAIN in tc_ctl_chain(). If a netlink socket sends RTM_GETCHAIN requests repeatedly without recv()ing the responses, tc_ctl_chain() hogs CPU and triggers Hung Task splat. [0] As caught in the stack trace, netlink_attachskb() could confuse tc_ctl_chain() by returning -EAGAIN when the userspace netlink socket's receive buffer is full. The replay: label exists since commit 32a4f5ecd738 ("net: sched: introduce chain object to uapi") but was not used initially. Since commit 9f407f1768d3 ("net: sched: introduce chain templates"), the label is needed for RTM_NEWCHAIN because tcf_proto_lookup_ops() may release RTNL to call request_module(). However, the replay logic is unnecessary for RTM_GETCHAIN. Let's apply the replay logic only for RTM_NEWCHAIN. [0]: INFO: task repro:1018 is blocked on a mutex likely owned by task repro:1022. task:repro state:R running task stack:14096 pid:1022 tgid:1014 ppid:961 task_flags:0x400040 flags:0x00080000 Call Trace: ? clockevents_program_event (kernel/time/clockevents.c:372) ? pskb_expand_head (net/core/skbuff.c:615) ? skb_release_data (net/core/skbuff.c:1122) ? netlink_attachskb (./include/linux/skbuff.h:1323 ./include/linux/skbuff.h:1332 net/netlink/af_netlink.c:1232) ? __netlink_lookup (./include/linux/rcupdate.h:882 ./include/linux/rhashtable.h:711 net/netlink/af_netlink.c:499) ? tc_chain_notify (net/sched/cls_api.c:3045) ? tc_chain_notify (./include/linux/skbuff.h:1384 net/sched/cls_api.c:3041) ? netlink_unicast (net/netlink/af_netlink.c:1335) ? rtnl_unicast (./include/net/netlink.h:1198 net/core/rtnetlink.c:985) ? tc_ctl_chain (net/sched/cls_api.c:3242) ? rtnetlink_rcv_msg (net/core/rtnetlink.c:7146) ? netlink_unicast (net/netlink/af_netlink.c:1354) ? __pfx_rtnetlink_rcv_msg (net/core/rtnetlink.c:7177) ? netlink_rcv_skb (net/netlink/af_netlink.c:2556) ? netlink_unicast (net/netlink/af_netlink.c:1319) ? netlink_sendmsg (net/netlink/af_netlink.c:1900) ? __sock_sendmsg (net/socket.c:800) ? __sys_sendto (net/socket.c:2281) ? __x64_sys_sendto (net/socket.c:2288 net/socket.c:2284 net/socket.c:2284) ? do_syscall_64 (arch/x86/entry/syscall_64.c:61 arch/x86/entry/syscall_64.c:84) ? entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:121) Fixes: 2ed9db3074fc ("net: sched: cls_api: fix dead code in switch") Reported-by: Taras Madan Signed-off-by: Kuniyuki Iwashima Reviewed-by: Jamal Hadi Salim Tested-by: hybris@mojatatu.ai Link: https://patch.msgid.link/20260908205537.863484-1-kuniyu@google.com Signed-off-by: Paolo Abeni --- net/sched/cls_api.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 9966766661d5..c47d2ee13641 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -3254,7 +3254,7 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n, tcf_chain_put(chain); errout_block: tcf_block_release(q, block, true); - if (err == -EAGAIN) + if (err == -EAGAIN && n->nlmsg_type == RTM_NEWCHAIN) /* Replay the request. */ goto replay; return err; From af406abfecad2f48d8f1fc646d3994f0982bac62 Mon Sep 17 00:00:00 2001 From: Li Youhong Date: Fri, 4 Sep 2026 16:07:58 +0800 Subject: [PATCH 1076/1198] net: sun4i-emac: fix missing of_node_put() for phy_node of_parse_phandle() returns a node pointer with an elevated refcount. Add the missing of_node_put() on the probe error path after register_netdev() fails and in emac_remove(). Fixes: 492205050d77 ("net: Add EMAC ethernet driver found on Allwinner A10 SoC's") Signed-off-by: Li Youhong Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260904080758.2432748-1-dayou5941@163.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/allwinner/sun4i-emac.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c index 942454e29488..0ba67a55705d 100644 --- a/drivers/net/ethernet/allwinner/sun4i-emac.c +++ b/drivers/net/ethernet/allwinner/sun4i-emac.c @@ -1067,6 +1067,7 @@ static int emac_probe(struct platform_device *pdev) return 0; out_release_sram: + of_node_put(db->phy_node); sunxi_sram_release(&pdev->dev); out_clk_disable_unprepare: clk_disable_unprepare(db->clk); @@ -1094,6 +1095,7 @@ static void emac_remove(struct platform_device *pdev) } unregister_netdev(ndev); + of_node_put(db->phy_node); sunxi_sram_release(&pdev->dev); clk_disable_unprepare(db->clk); irq_dispose_mapping(ndev->irq); From 5d4d985957434867bbe85e4fa5e638f3e48ad522 Mon Sep 17 00:00:00 2001 From: Aamir Ahmed Date: Mon, 7 Sep 2026 02:42:34 +0000 Subject: [PATCH 1077/1198] net: hinic: fix mailbox segment buffer overflow check_mbox_seq_id_and_seg_len() validates that seq_id does not exceed SEQ_ID_MAX_VAL (42) and seg_len does not exceed MBOX_SEG_LEN (48). However, this allows the last segment (seq_id=42) to carry a full 48-byte payload, writing to offset 42*48=2016 for 48 bytes (ending at byte 2064). The receive buffer is only MBOX_MAX_BUF_SZ (2048) bytes, resulting in a 16-byte heap buffer overflow. The hinic3 driver already handles this correctly by defining MBOX_LAST_SEG_MAX_LEN and rejecting the last segment when it exceeds the remaining buffer space. Apply the same fix to the hinic driver. Fixes: a425b6e1c69b ("hinic: add mailbox function support") Signed-off-by: Aamir Ahmed Link: https://patch.msgid.link/AS8P251MB0001AE870B09020B46B5D7DBC8B22@AS8P251MB0001.EURP251.PROD.OUTLOOK.COM Signed-off-by: Paolo Abeni --- drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c index 2784127327e6..6e67a6c9578e 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c @@ -128,6 +128,7 @@ enum hinic_mbox_tx_status { #define SEQ_ID_START_VAL 0 #define SEQ_ID_MAX_VAL 42 +#define MBOX_LAST_SEG_MAX_LEN (MBOX_MAX_BUF_SZ - SEQ_ID_MAX_VAL * MBOX_SEG_LEN) #define NO_DMA_ATTRIBUTE_VAL 0 @@ -372,7 +373,8 @@ recv_pf_from_vf_mbox_handler(struct hinic_mbox_func_to_func *func_to_func, static bool check_mbox_seq_id_and_seg_len(struct hinic_recv_mbox *recv_mbox, u8 seq_id, u8 seg_len) { - if (seq_id > SEQ_ID_MAX_VAL || seg_len > MBOX_SEG_LEN) + if (seq_id > SEQ_ID_MAX_VAL || seg_len > MBOX_SEG_LEN || + (seq_id == SEQ_ID_MAX_VAL && seg_len > MBOX_LAST_SEG_MAX_LEN)) return false; if (seq_id == 0) { From 3c18e3c9a54e1239b72849502ca4737604bfbb46 Mon Sep 17 00:00:00 2001 From: Aleksei Sviridkin Date: Thu, 3 Sep 2026 12:36:43 +0000 Subject: [PATCH 1078/1198] net: dsa: mt7530: populate lpi_interfaces to fix EEE support phylink_create() decides once and for all that a MAC supports managed EEE, and it requires the tx_lpi ops plus non-empty lpi_capabilities and lpi_interfaces. mt753x_phylink_get_caps() leaves lpi_interfaces empty. So ever since the conversion to phylink managed EEE, ethtool has answered "Not supported" on every mt753x port, and phy_disable_eee() has locked userspace out of turning EEE on. That undoes what commit 06dfcd4098cf ("net: dsa: mt7530: fix enabling EEE on MT7531 switch on all boards") arranged: EEE off by default, but reachable with ethtool. Leave the speeds above 1 Gbps out of both bitmaps. PMCR folds SPEED_2500 and SPEED_10000 onto PMCR_FORCE_SPEED_1000, so PMCR_FORCE_EEE1G would govern LPI on such a link, and that is unvalidated rather than known unsupported: MediaTek's SDK driver sets the EEE force bits for 100 Mbps and 1 Gbps only, and the unit of the wakeup timers is undocumented with the port clock at 2.5 times the rate. LPI stays off until userspace enables it, but the EEE advertisement of a PHY that advertises it out of reset comes back, since phylink stops force-clearing it. Fixes: 9cf21773f535 ("net: dsa: mt7530: convert to phylink managed EEE") Signed-off-by: Aleksei Sviridkin Link: https://patch.msgid.link/20260903123644.23800-2-f@lex.la Signed-off-by: Paolo Abeni --- drivers/net/dsa/mt7530.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 2b7be091c056..3e61eb3c2b1e 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -3172,23 +3172,31 @@ static void mt753x_phylink_get_caps(struct dsa_switch *ds, int port, config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE; + priv->info->mac_port_get_caps(ds, port, config); + /* The EN7528 GPHYs report EEE capability, but negotiating EEE with * common link partners (e.g. Realtek GbE NICs) results in an unstable * link with dropped frames. Leave the LPI capabilities empty so that * phylink disables EEE on these PHYs and refuses to enable it from * userspace. */ - if (priv->id != ID_EN7528) { + if (priv->id != ID_EN7528 && + config->mac_capabilities & (MAC_100FD | MAC_1000FD)) { u32 eeecr = mt7530_read(priv, MT753X_PMEEECR_P(port)); - config->lpi_capabilities = MAC_100FD | MAC_1000FD | MAC_2500FD; + /* LPI above 1 Gbps is not supported */ + config->lpi_capabilities = config->mac_capabilities & + (MAC_100FD | MAC_1000FD); + phy_interface_copy(config->lpi_interfaces, + config->supported_interfaces); + __clear_bit(PHY_INTERFACE_MODE_2500BASEX, + config->lpi_interfaces); + /* tx_lpi_timer should be in microseconds. The time units for * LPI threshold are unspecified. */ config->lpi_timer_default = FIELD_GET(LPI_THRESH_MASK, eeecr); } - - priv->info->mac_port_get_caps(ds, port, config); } static int mt753x_pcs_validate(struct phylink_pcs *pcs, From d876c9cb2d16ed259449fe9da08c37a5cb81d724 Mon Sep 17 00:00:00 2001 From: Aleksei Sviridkin Date: Thu, 3 Sep 2026 12:36:44 +0000 Subject: [PATCH 1079/1198] net: ethernet: mtk_eth_soc: populate lpi_interfaces to fix EEE support phylink_create() decides once and for all that a MAC supports managed EEE, and it requires the tx_lpi ops plus non-empty lpi_capabilities and lpi_interfaces. mtk_add_mac() leaves lpi_interfaces empty. So ever since EEE support was added, ethtool has answered "Not supported" on every MAC that uses mtk_phylink_ops, and phy_disable_eee() has locked userspace out of turning EEE on. MT7628 is unaffected, as rt5350_phylink_ops has no tx_lpi methods. Leave 2.5 Gbps out of both bitmaps, and the xGMII modes that mtk_mac_enable_tx_lpi() already refuses. MAC_MCR folds SPEED_2500 onto MAC_MCR_SPEED_1000, so MAC_MCR_EEE1G would govern LPI on such a link, and that is unvalidated rather than known unsupported: MediaTek's SDK driver sets the EEE force bits for 100 Mbps and 1 Gbps only, and the unit of the wakeup timers is undocumented with the port clock at 2.5 times the rate. mtk_mac_enable_tx_lpi() programs wake-up times taken from MT7531's reset values, and the SoC's own field has no reset value to fall back on. Only MT7981 has been seen to exit LPI cleanly with them, so the LPI interfaces sit behind a new MTK_GMAC_EEE capability that only MT7981 sets; every other SoC keeps the current behaviour until it has been confirmed. LPI stays off until userspace enables it, but the EEE advertisement of a PHY that advertises it out of reset comes back, since phylink stops force-clearing it. Fixes: 952d7325362f ("net: ethernet: mediatek: add EEE support") Signed-off-by: Aleksei Sviridkin Link: https://patch.msgid.link/20260903123644.23800-3-f@lex.la Signed-off-by: Paolo Abeni --- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 18 +++++++++++++++--- drivers/net/ethernet/mediatek/mtk_eth_soc.h | 4 +++- 2 files changed, 18 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index be3bd025c41a..fd7a49ae88d0 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -4828,7 +4828,7 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) phy_interface_t phy_mode; struct phylink *phylink; struct mtk_mac *mac; - int id, err; + int id, err, i; int txqs = 1; u32 val; @@ -4907,8 +4907,8 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) mac->phylink_config.type = PHYLINK_NETDEV; mac->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | MAC_10 | MAC_100 | MAC_1000 | MAC_2500FD; - mac->phylink_config.lpi_capabilities = MAC_100FD | MAC_1000FD | - MAC_2500FD; + /* LPI above 1 Gbps is not supported */ + mac->phylink_config.lpi_capabilities = MAC_100FD | MAC_1000FD; mac->phylink_config.lpi_timer_default = 1000; /* MT7623 gmac0 is now missing its speed-specific PLL configuration @@ -4966,6 +4966,18 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) __set_bit(PHY_INTERFACE_MODE_INTERNAL, mac->phylink_config.supported_interfaces); + /* LPI wake-up timing is only verified on MTK_GMAC_EEE SoCs */ + if (MTK_HAS_CAPS(eth->soc->caps, MTK_GMAC_EEE)) { + phy_interface_copy(mac->phylink_config.lpi_interfaces, + mac->phylink_config.supported_interfaces); + __clear_bit(PHY_INTERFACE_MODE_2500BASEX, + mac->phylink_config.lpi_interfaces); + for (i = 0; i < PHY_INTERFACE_MODE_MAX; i++) + if (mtk_interface_mode_is_xgmii(eth, i)) + __clear_bit(i, + mac->phylink_config.lpi_interfaces); + } + phylink = phylink_create(&mac->phylink_config, of_fwnode_handle(mac->of_node), phy_mode, mac_ops); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index 0168e2fbc619..88a9b3b23bea 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -994,6 +994,7 @@ enum mkt_eth_capabilities { MTK_U3_COPHY_V2_BIT, MTK_SRAM_BIT, MTK_36BIT_DMA_BIT, + MTK_GMAC_EEE_BIT, /* MUX BITS*/ MTK_ETH_MUX_GDM1_TO_GMAC1_ESW_BIT, @@ -1034,6 +1035,7 @@ enum mkt_eth_capabilities { #define MTK_U3_COPHY_V2 BIT_ULL(MTK_U3_COPHY_V2_BIT) #define MTK_SRAM BIT_ULL(MTK_SRAM_BIT) #define MTK_36BIT_DMA BIT_ULL(MTK_36BIT_DMA_BIT) +#define MTK_GMAC_EEE BIT_ULL(MTK_GMAC_EEE_BIT) #define MTK_ETH_MUX_GDM1_TO_GMAC1_ESW \ BIT_ULL(MTK_ETH_MUX_GDM1_TO_GMAC1_ESW_BIT) @@ -1117,7 +1119,7 @@ enum mkt_eth_capabilities { #define MT7981_CAPS (MTK_GMAC1_SGMII | MTK_GMAC2_SGMII | MTK_GMAC2_GEPHY | \ MTK_MUX_GMAC12_TO_GEPHY_SGMII | MTK_QDMA | \ MTK_MUX_U3_GMAC2_TO_QPHY | MTK_U3_COPHY_V2 | \ - MTK_RSTCTRL_PPE1 | MTK_SRAM) + MTK_RSTCTRL_PPE1 | MTK_SRAM | MTK_GMAC_EEE) #define MT7986_CAPS (MTK_GMAC1_SGMII | MTK_GMAC2_SGMII | \ MTK_MUX_GMAC12_TO_GEPHY_SGMII | MTK_QDMA | \ From 125755776bc6d4dd53eaf551c87e3d460625d638 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Fri, 4 Sep 2026 14:43:07 +0100 Subject: [PATCH 1080/1198] tcp: reject non zerocopy devmem tx Devmem tcp tx doesn't work without zero-copy, however it's not currently enforced if NETIF_F_SG isn't present. In this case, tcp_sendmsg_locked() will try the copy path and try to copy data from an iovec which consists of offsets into the dma-buf and would normally fail. Moreover, d9c56501c72fd ("net: tcp: block mixing readable and unreadable frags") relies on that and assumes that the devmem binding is present IFF we're using the zero-copy path, which can be used to mix net-iov and pages in a single skb, and break invariants. Let's reject devmem tx without zero-copy. Note, the parameter check the patch is modifying is too loose, we can create an io_uring request with dmabuf_id and all ZC flags, but which won't have the binding. We replace it with stricter validation. Fixes: bd61848900bff ("net: devmem: Implement TX path") Fixes: d9c56501c72fd ("net: tcp: block mixing readable and unreadable frags") Signed-off-by: Pavel Begunkov Reviewed-by: Mina Almasry Link: https://patch.msgid.link/fdc2478d8f21268d7078556409887d8e6ba0ad32.1788529053.git.asml.silence@gmail.com Signed-off-by: Paolo Abeni --- net/ipv4/tcp.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 1c867a302444..562752352afe 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1169,8 +1169,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) zc = MSG_SPLICE_PAGES; } - if (!sockc_err && sockc.dmabuf_id && - (!(flags & MSG_ZEROCOPY) || !sock_flag(sk, SOCK_ZEROCOPY))) { + if (!sockc_err && sockc.dmabuf_id && (zc != MSG_ZEROCOPY || !binding)) { err = -EINVAL; goto out_err; } From ccbe7540e4aad0d1c3acc249697350b93ccb8025 Mon Sep 17 00:00:00 2001 From: Vladislav Karmanov Date: Tue, 8 Sep 2026 17:52:13 +0300 Subject: [PATCH 1081/1198] net: phy: mediatek-ge: disable EEE on the MT7530 PHY The MT7530 internal GE PHY advertises EEE by hardware default, but its EEE support is defective: with EEE advertised, some link partners fail to establish a stable link. On a 2-pair (4-wire) cable where both ends advertise gigabit, 1000BASE-T training cannot succeed, and instead of falling back to 100 Mbps the port loops, so no link or DHCP lease is ever obtained. MediaTek confirms the hardware is the root cause (Landen Chao, 2021): "EEE of the 10-year-old MT7530 internal gephy has many IOT problems, so it is recommended to disable its EEE." mtk_gephy_config_init() used to clear the EEE advertisement early, but commit af3b4b0e59de ("net: phy: mediatek-ge: do not disable EEE advertisement") removed that on the rationale that the DSA subdriver already performs an early disable. That holds for MT7531, whose mt7531_setup() clears MDIO_AN_EEE_ADV on each switch PHY, but not for the MT7530 PHY: neither the MT7621 integrated switch nor the dedicated MT7530 IC ever had such a loop, so removing it left those boards without any working early EEE disable and the link flapping came back. Since the broken hardware is the PHY, fix it in the PHY driver so it covers all users of this PHY, integrated in a switch or standalone: - clear MDIO_AN_EEE_ADV in probe(), as early as possible, before anything can negotiate EEE with the link partner; - clear it again in config_init() and call phy_disable_eee() there. config_init() is what phy_init_hw() replays after a PHY reset, when the register is back at its EEE-advertising hardware default, and it runs after of_set_phy_eee_broken() in phy_probe(), so the eee_disabled_modes mask survives and neither phylib nor userspace can re-enable EEE. dp83867 disables broken EEE from config_init() the same way. Auto-negotiation then falls back to a stable 100 Mbps link instead of looping at gigabit. Tested on ASUS RT-AX53U (MT7621): with a 2-pair cable on the WAN port, a single clean 100 Mbps link comes up and a DHCP lease is obtained, where the unpatched driver loops. Fixes: af3b4b0e59de ("net: phy: mediatek-ge: do not disable EEE advertisement") Suggested-by: Andrew Lunn Signed-off-by: Vladislav Karmanov Link: https://patch.msgid.link/20260908145213.3976508-1-vladislav.karmanov.dev@gmail.com Signed-off-by: Paolo Abeni --- drivers/net/phy/mediatek/mtk-ge.c | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/drivers/net/phy/mediatek/mtk-ge.c b/drivers/net/phy/mediatek/mtk-ge.c index 73d9b72f9d9e..96d8ac5154e5 100644 --- a/drivers/net/phy/mediatek/mtk-ge.c +++ b/drivers/net/phy/mediatek/mtk-ge.c @@ -62,10 +62,38 @@ static void mtk_gephy_config_init(struct phy_device *phydev) FIELD_PREP(MTK_MCC_NEARECHO_OFFSET_MASK, 0x3)); } +static int mt7530_phy_probe(struct phy_device *phydev) +{ + /* The MT7530 internal GE PHY has broken EEE: with EEE advertised, + * some link partners fail to establish a stable link (on a 2-pair + * cable, 1000BASE-T training fails and the port loops instead of + * falling back). MediaTek recommends disabling EEE on this PHY. + * Clear the advertisement as early as possible, before anything + * can negotiate EEE with the link partner. + */ + return phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, 0); +} + static int mt7530_phy_config_init(struct phy_device *phydev) { + int ret; + mtk_gephy_config_init(phydev); + /* The probe() clear alone is not durable: phy_init_hw() replays only + * ->config_init after a PHY reset, with the register back at its + * EEE-advertising hardware default, and phy_probe() zeroes + * eee_disabled_modes (of_set_phy_eee_broken()) after ->probe already + * ran. Clear the advertisement again and mark EEE disabled, so that + * neither phylib nor userspace can re-enable it; dp83867 disables + * broken EEE from config_init() the same way. + */ + ret = phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, 0); + if (ret) + return ret; + + phy_disable_eee(phydev); + /* Increase post_update_timer */ phy_write_paged(phydev, MTK_PHY_PAGE_EXTENDED_3, MTK_PHY_RG_LPI_PCS_DSP_CTRL_REG11, 0x4b); @@ -100,6 +128,7 @@ static struct phy_driver mtk_gephy_driver[] = { { PHY_ID_MATCH_EXACT(MTK_GPHY_ID_MT7530), .name = "MediaTek MT7530 PHY", + .probe = mt7530_phy_probe, .config_init = mt7530_phy_config_init, /* Interrupts are handled by the switch, not the PHY * itself. From 985a663bf00799c1daf1c5789efa6406958780c8 Mon Sep 17 00:00:00 2001 From: Faicker Mo Date: Tue, 8 Sep 2026 12:06:29 +0800 Subject: [PATCH 1082/1198] net: net_failover: Fix the deadlock in net_failover_slave_name_change() This is a sibling fix of commit b84c5632c7b3 ("net: net_failover: Fix the deadlock in slave register"). There is netdev_lock_ops() in the upper callers, so using netif_open() instead of dev_open(). Call Trace: __schedule+0x2bb/0x650 schedule+0x27/0xb0 schedule_preempt_disabled+0x15/0x30 __mutex_lock.constprop.0+0x550/0xaf0 __mutex_lock_slowpath+0x13/0x20 mutex_lock+0x3b/0x50 dev_open+0x3b/0xe0 net_failover_slave_name_change+0x22/0x40 failover_event+0xd4/0x1e0 notifier_call_chain+0x62/0xf0 raw_notifier_call_chain+0x16/0x30 call_netdevice_notifiers_info+0x50/0x80 netif_change_name+0x200/0x330 do_setlink.isra.0+0xb12/0xdf0 ? security_capable+0x9a/0x1e0 ? ns_capable+0x31/0x60 rtnl_setlink+0x302/0x670 ? netlink_recvmsg+0x296/0x340 ? security_capable+0x9a/0x1e0 ? __pfx_rtnl_setlink+0x10/0x10 rtnetlink_rcv_msg+0x384/0x460 ? __pfx_rtnetlink_rcv_msg+0x10/0x10 netlink_rcv_skb+0x61/0x120 rtnetlink_rcv+0x15/0x30 netlink_unicast+0x28f/0x3c0 netlink_sendmsg+0x216/0x450 __sys_sendto+0x222/0x230 __x64_sys_sendto+0x24/0x40 x64_sys_call+0x1d5d/0x2390 do_syscall_64+0x105/0x5a0 ? do_syscall_64+0x140/0x5a0 ? exc_page_fault+0x94/0x1e0 entry_SYSCALL_64_after_hwframe+0x76/0x7e Fixes: 7e4d784f5810 ("net: hold netdev instance lock during rtnetlink operations") Signed-off-by: Faicker Mo Reviewed-by: Hangbin Liu Link: https://patch.msgid.link/20260908040708.3972058-1-faicker.mo@gmail.com Signed-off-by: Paolo Abeni --- drivers/net/net_failover.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c index 3f7d31033bae..1b5213e87070 100644 --- a/drivers/net/net_failover.c +++ b/drivers/net/net_failover.c @@ -675,7 +675,7 @@ static int net_failover_slave_name_change(struct net_device *slave_dev, /* We need to bring up the slave after the rename by udev in case * open failed with EBUSY when it was registered. */ - dev_open(slave_dev, NULL); + netif_open(slave_dev, NULL); return 0; } From 568a1588b906780dc3e9be56a61217afb4f7800e Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 8 Sep 2026 23:03:02 -0700 Subject: [PATCH 1083/1198] xfs: snapshot scrub stats when rendering them LOLLM complains about concurrency problems in the scrub stats code because xchk_stats_format doesn't synchronize in any way with updates. These stats are only reported through debugfs so I don't think it really matters, but I guess I exist to make bots happy now. Note: We snapshot the entire stats object with a spinlock so that we don't have to worry about users seeing slightly weird numbers (e.g. invocations has incremented but none of the outcomes have been yet) if we race with xchk_stats_merge_one. This isn't a hot path. Cc: stable@vger.kernel.org # v6.6 Fixes: d7a74cad8f4513 ("xfs: track usage statistics of online fsck") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Carlos Maiolino Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/stats.c | 32 +++++++++++++++++++------------- 1 file changed, 19 insertions(+), 13 deletions(-) diff --git a/fs/xfs/scrub/stats.c b/fs/xfs/scrub/stats.c index 76f2515188d1..f3f1fbfb6d99 100644 --- a/fs/xfs/scrub/stats.c +++ b/fs/xfs/scrub/stats.c @@ -99,25 +99,31 @@ xchk_stats_format( int ret = 0; for (i = 0; i < XFS_SCRUB_TYPE_NR; i++, css++) { + struct xchk_scrub_stats fss; + if (!name_map[i]) continue; + spin_lock(&css->css_lock); + memcpy(&fss, css, offsetof(struct xchk_scrub_stats, css_lock)); + spin_unlock(&css->css_lock); + ret = scnprintf(buf, remaining, "%s %u %u %u %u %u %u %u %u %u %llu %u %u %llu\n", name_map[i], - (unsigned int)css->invocations, - (unsigned int)css->clean, - (unsigned int)css->corrupt, - (unsigned int)css->preen, - (unsigned int)css->xfail, - (unsigned int)css->xcorrupt, - (unsigned int)css->incomplete, - (unsigned int)css->warning, - (unsigned int)css->retries, - (unsigned long long)css->checktime_us, - (unsigned int)css->repair_invocations, - (unsigned int)css->repair_success, - (unsigned long long)css->repairtime_us); + (unsigned int)fss.invocations, + (unsigned int)fss.clean, + (unsigned int)fss.corrupt, + (unsigned int)fss.preen, + (unsigned int)fss.xfail, + (unsigned int)fss.xcorrupt, + (unsigned int)fss.incomplete, + (unsigned int)fss.warning, + (unsigned int)fss.retries, + (unsigned long long)fss.checktime_us, + (unsigned int)fss.repair_invocations, + (unsigned int)fss.repair_success, + (unsigned long long)fss.repairtime_us); if (ret <= 0) break; From 0ae61c331ec552ad0c278c5c48a1c4ccb90b4bab Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 8 Sep 2026 23:03:17 -0700 Subject: [PATCH 1084/1198] xfs: report healthy filesystem events in scrub stats LOLLM also notices that I forgot to expose the "clean bill of health" scrub stats. Fix that. Cc: stable@vger.kernel.org # v6.9 Fixes: a1f3e0cca41036 ("xfs: update health status if we get a clean bill of health") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Carlos Maiolino Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/stats.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/xfs/scrub/stats.c b/fs/xfs/scrub/stats.c index f3f1fbfb6d99..da0c05ffe5cd 100644 --- a/fs/xfs/scrub/stats.c +++ b/fs/xfs/scrub/stats.c @@ -84,6 +84,7 @@ static const char *name_map[XFS_SCRUB_TYPE_NR] = { [XFS_SCRUB_TYPE_RGSUPER] = "rgsuper", [XFS_SCRUB_TYPE_RTRMAPBT] = "rtrmapbt", [XFS_SCRUB_TYPE_RTREFCBT] = "rtrefcountbt", + [XFS_SCRUB_TYPE_HEALTHY] = "healthy", }; /* Format the scrub stats into a text buffer, similar to pcp style. */ From d3dc979a49df6d48f8e137034d19d9b35afd07d8 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 8 Sep 2026 23:03:33 -0700 Subject: [PATCH 1085/1198] xfs: report runtime failures in scrub Add a new counter so that we can track the number of runtime failures encountered during scrubs. Signed-off-by: Darrick J. Wong Reviewed-by: Carlos Maiolino Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/stats.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/fs/xfs/scrub/stats.c b/fs/xfs/scrub/stats.c index da0c05ffe5cd..3339cae4b39d 100644 --- a/fs/xfs/scrub/stats.c +++ b/fs/xfs/scrub/stats.c @@ -29,6 +29,7 @@ struct xchk_scrub_stats { uint32_t incomplete; uint32_t warning; uint32_t retries; + uint32_t runtime_errors; /* repair stats */ uint32_t repair_invocations; @@ -110,7 +111,7 @@ xchk_stats_format( spin_unlock(&css->css_lock); ret = scnprintf(buf, remaining, - "%s %u %u %u %u %u %u %u %u %u %llu %u %u %llu\n", + "%s %u %u %u %u %u %u %u %u %u %llu %u %u %llu %u\n", name_map[i], (unsigned int)fss.invocations, (unsigned int)fss.clean, @@ -124,7 +125,8 @@ xchk_stats_format( (unsigned long long)fss.checktime_us, (unsigned int)fss.repair_invocations, (unsigned int)fss.repair_success, - (unsigned long long)fss.repairtime_us); + (unsigned long long)fss.repairtime_us, + (unsigned int)fss.runtime_errors); if (ret <= 0) break; @@ -207,13 +209,17 @@ xchk_stats_merge_one( } /* caller applies this same transformation after we return */ - if (error == -EFSCORRUPTED || error == -EFSBADCRC) + if (error == -EFSCORRUPTED || error == -EFSBADCRC) { sm_flags |= XFS_SCRUB_OFLAG_CORRUPT; + error = 0; + } css = &cs->cs_stats[sm->sm_type]; spin_lock(&css->css_lock); css->invocations++; - if (!(sm_flags & XFS_SCRUB_OFLAG_UNCLEAN)) + if (error) + css->runtime_errors++; + else if (!(sm_flags & XFS_SCRUB_OFLAG_UNCLEAN)) css->clean++; if (sm_flags & XFS_SCRUB_OFLAG_CORRUPT) css->corrupt++; From 341f03865d0793e7df22c4661e04047c092e5ac2 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 8 Sep 2026 23:03:48 -0700 Subject: [PATCH 1086/1198] xfs: remove redundant function declaration Remove this useless code. Signed-off-by: Darrick J. Wong Reviewed-by: Carlos Maiolino Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/dabtree.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/fs/xfs/scrub/dabtree.h b/fs/xfs/scrub/dabtree.h index de291e3b77dd..d654c125feb4 100644 --- a/fs/xfs/scrub/dabtree.h +++ b/fs/xfs/scrub/dabtree.h @@ -37,8 +37,6 @@ bool xchk_da_process_error(struct xchk_da_btree *ds, int level, int *error); void xchk_da_set_corrupt(struct xchk_da_btree *ds, int level); void xchk_da_set_preen(struct xchk_da_btree *ds, int level); -void xchk_da_set_preen(struct xchk_da_btree *ds, int level); - int xchk_da_btree_hash(struct xchk_da_btree *ds, int level, __be32 *hashp); int xchk_da_btree(struct xfs_scrub *sc, int whichfork, xchk_da_btree_rec_fn scrub_fn, void *private); From 3466dfef0a20f842363958deea55be9f1d26818a Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 8 Sep 2026 23:04:04 -0700 Subject: [PATCH 1087/1198] xfs: snapshot old AGFL before rewriting it LOLLM complains that we can't undo an attempt at fixing the AGFL if anything goes wrong during the rewrite, so take a snapshot of the whole buffer so that we can restore it. Move the xrep_agfl_update_agf call so that we only update the AGF if the AGFL update is 100% successful. While we're at it, fix leaking the used_extents bitmap if the disunion operation fails. Cc: stable@vger.kernel.org # v4.19 Fixes: 0e93d3f43ec7d3 ("xfs: repair the AGFL") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Carlos Maiolino Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/agheader_repair.c | 35 ++++++++++++++++++++++++---------- 1 file changed, 25 insertions(+), 10 deletions(-) diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c index 2104512f1ee1..46c95354ca64 100644 --- a/fs/xfs/scrub/agheader_repair.c +++ b/fs/xfs/scrub/agheader_repair.c @@ -668,14 +668,16 @@ xrep_agfl_init_header( struct xfs_scrub *sc, struct xfs_buf *agfl_bp, struct xagb_bitmap *agfl_extents, - xfs_agblock_t flcount) + xfs_agblock_t flcount, + struct xfs_agfl *old_agfl) { struct xrep_agfl_fill af = { .sc = sc, .flcount = flcount, }; struct xfs_mount *mp = sc->mp; - struct xfs_agfl *agfl; + struct xfs_agfl *agfl = XFS_BUF_TO_AGFL(agfl_bp); + const size_t agfl_sz = BBTOB(agfl_bp->b_length); int error; ASSERT(flcount <= xfs_agfl_size(mp)); @@ -684,8 +686,8 @@ xrep_agfl_init_header( * Start rewriting the header by setting the bno[] array to * NULLAGBLOCK, then setting AGFL header fields. */ - agfl = XFS_BUF_TO_AGFL(agfl_bp); - memset(agfl, 0xFF, BBTOB(agfl_bp->b_length)); + memcpy(old_agfl, agfl, agfl_sz); + memset(agfl, 0xFF, agfl_sz); agfl->agfl_magicnum = cpu_to_be32(XFS_AGFL_MAGIC); agfl->agfl_seqno = cpu_to_be32(pag_agno(sc->sa.pag)); uuid_copy(&agfl->agfl_uuid, &mp->m_sb.sb_meta_uuid); @@ -700,13 +702,18 @@ xrep_agfl_init_header( xagb_bitmap_walk(agfl_extents, xrep_agfl_fill, &af); error = xagb_bitmap_disunion(agfl_extents, &af.used_extents); if (error) - return error; + goto err_undo; /* Write new AGFL to disk. */ xfs_trans_buf_set_type(sc->tp, agfl_bp, XFS_BLFT_AGFL_BUF); - xfs_trans_log_buf(sc->tp, agfl_bp, 0, BBTOB(agfl_bp->b_length) - 1); + xfs_trans_log_buf(sc->tp, agfl_bp, 0, agfl_sz - 1); xagb_bitmap_destroy(&af.used_extents); return 0; + +err_undo: + xagb_bitmap_destroy(&af.used_extents); + memcpy(agfl, old_agfl, agfl_sz); + return error; } /* Repair the AGFL. */ @@ -718,6 +725,7 @@ xrep_agfl( struct xfs_mount *mp = sc->mp; struct xfs_buf *agf_bp; struct xfs_buf *agfl_bp; + struct xfs_agfl *old_agfl; xfs_agblock_t flcount; int error; @@ -725,6 +733,10 @@ xrep_agfl( if (!xfs_has_rmapbt(mp)) return -EOPNOTSUPP; + old_agfl = kzalloc(BBTOB(XFS_FSS_TO_BB(mp, 1)), XCHK_GFP_FLAGS); + if (!old_agfl) + return -ENOMEM; + xagb_bitmap_init(&agfl_extents); /* @@ -734,7 +746,7 @@ xrep_agfl( */ error = xfs_alloc_read_agf(sc->sa.pag, sc->tp, 0, &agf_bp); if (error) - return error; + goto err_old_agfl; /* * Make sure we have the AGFL buffer, as scrub might have decided it @@ -745,7 +757,7 @@ xrep_agfl( XFS_AGFL_DADDR(mp)), XFS_FSS_TO_BB(mp, 1), 0, &agfl_bp, NULL); if (error) - return error; + goto err_old_agfl; agfl_bp->b_ops = &xfs_agfl_buf_ops; /* Gather all the extents we're going to put on the new AGFL. */ @@ -762,10 +774,11 @@ xrep_agfl( * we adjust the AGF flcount (which can fail) so avoid updating any * buffers until we know that part works. */ - xrep_agfl_update_agf(sc, agf_bp, flcount); - error = xrep_agfl_init_header(sc, agfl_bp, &agfl_extents, flcount); + error = xrep_agfl_init_header(sc, agfl_bp, &agfl_extents, flcount, + old_agfl); if (error) goto err; + xrep_agfl_update_agf(sc, agf_bp, flcount); /* * Ok, the AGFL should be ready to go now. Roll the transaction to @@ -785,6 +798,8 @@ xrep_agfl( err: xagb_bitmap_destroy(&agfl_extents); +err_old_agfl: + kfree(old_agfl); return error; } From eaf580538eb1be3d162400d04c4b7dc4c627296b Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 8 Sep 2026 23:04:19 -0700 Subject: [PATCH 1088/1198] xfs: bail out on bitmap errors in xrep_agfl_fill LOLLM also points out that the xagb_bitmap_set call in xrep_agfl_fill can fail, but we don't check the result of xagb_bitmap_walk, so we silently drop the error and proceed with inconsistent incore data. That shouldn't be allowed. Cc: stable@vger.kernel.org # v6.6 Fixes: 014ad53732d2ba ("xfs: use per-AG bitmaps to reap unused AG metadata blocks during repair") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Christoph Hellwig Reviewed-by: Carlos Maiolino Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/agheader_repair.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c index 46c95354ca64..a66b611588c4 100644 --- a/fs/xfs/scrub/agheader_repair.c +++ b/fs/xfs/scrub/agheader_repair.c @@ -699,7 +699,9 @@ xrep_agfl_init_header( */ xagb_bitmap_init(&af.used_extents); af.agfl_bno = xfs_buf_to_agfl_bno(agfl_bp); - xagb_bitmap_walk(agfl_extents, xrep_agfl_fill, &af); + error = xagb_bitmap_walk(agfl_extents, xrep_agfl_fill, &af); + if (error && error != -ECANCELED) + goto err_undo; error = xagb_bitmap_disunion(agfl_extents, &af.used_extents); if (error) goto err_undo; From ad0033e2dbd3ecc063dfe613060da5cbab9a4970 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 7 Sep 2026 10:33:07 +0300 Subject: [PATCH 1089/1198] xfs: also flush the RT device cache in xlog_write_iclog The cache flush before writing the CIL start record no only needs to ensure any metadata covered by the overwritten part of the log is on stable storage, but also that any data pointed to by metadata logged is on stable storage, as otherwise log recovery could created allocated blocks that point to stale data. Fortunately the code already handles this right for the data device, but it also needs to flush the RT device for this to work for data on the RT device. Also update the comments to explicitly mention this case. This omission goes back to the first days of cache control in XFS. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Reviewed-by: Carlos Maiolino Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_log.c | 45 ++++++++++++++++++++++++++++++-------------- fs/xfs/xfs_log_cil.c | 7 ++++--- 2 files changed, 35 insertions(+), 17 deletions(-) diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 2a34611d81f6..f4f81d893e8c 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -1544,6 +1544,35 @@ xlog_bio_end_io( &iclog->ic_end_io_work); } +/* + * When using multiple devices, we also need to flush the data and RT device + * caches first to ensure that all metadata writeback covered by the LSN in + * this iclog is on stable storage. This is slow, but it *must* complete + * before we issue the external log IO. + * + * If the flush fails, we cannot conclude that past metadata writeback from + * the log succeeded. Repeating the flush is not possible, hence we must + * shut down with log IO error to avoid shutdown re-entering this path and + * erroring out again. + */ +static int +xlog_flush_data_caches( + struct xlog *log) +{ + struct xfs_mount *mp = log->l_mp; + + if (log->l_targ != mp->m_ddev_targp) { + if (blkdev_issue_flush(mp->m_ddev_targp->bt_bdev)) + return -EIO; + } + if (mp->m_rtdev_targp && mp->m_rtdev_targp != mp->m_ddev_targp) { + if (blkdev_issue_flush(mp->m_rtdev_targp->bt_bdev)) + return -EIO; + } + + return 0; +} + STATIC void xlog_write_iclog( struct xlog *log, @@ -1588,21 +1617,9 @@ xlog_write_iclog( iclog->ic_bio.bi_private = iclog; if (iclog->ic_flags & XLOG_ICL_NEED_FLUSH) { - iclog->ic_bio.bi_opf |= REQ_PREFLUSH; - /* - * For external log devices, we also need to flush the data - * device cache first to ensure all metadata writeback covered - * by the LSN in this iclog is on stable storage. This is slow, - * but it *must* complete before we issue the external log IO. - * - * If the flush fails, we cannot conclude that past metadata - * writeback from the log succeeded. Repeating the flush is - * not possible, hence we must shut down with log IO error to - * avoid shutdown re-entering this path and erroring out again. - */ - if (log->l_targ != log->l_mp->m_ddev_targp && - blkdev_issue_flush(log->l_mp->m_ddev_targp->bt_bdev)) + if (xlog_flush_data_caches(log)) goto shutdown; + iclog->ic_bio.bi_opf |= REQ_PREFLUSH; } if (iclog->ic_flags & XLOG_ICL_NEED_FUA) iclog->ic_bio.bi_opf |= REQ_FUA; diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index 166531018ce4..f9e07a32f60f 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -1055,9 +1055,10 @@ xlog_cil_set_ctx_write_state( spin_unlock(&cil->xc_push_lock); /* - * Make sure the metadata we are about to overwrite in the log - * has been flushed to stable storage before this iclog is - * issued. + * Flush the write cache before writing the start record so that + * the metadata we are about to overwrite in the log and the + * data that new allocations in this context refer to are + * persisted to stable storage before this iclog is written. */ spin_lock(&cil->xc_log->l_icloglock); iclog->ic_flags |= XLOG_ICL_NEED_FLUSH; From c84455c683eb0b0397b0f5c5f5ce5cd82572a23f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 7 Sep 2026 10:33:08 +0300 Subject: [PATCH 1090/1198] xfs: don't continue on error in xfs_fsync As soon as we get an error from cache flushing or log forcing, there is no point in continuing as the data integrity is already impacted. Return the error instead of continuing to do more work. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Reviewed-by: Carlos Maiolino Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_file.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 426a67b813a7..0d31fea67a2c 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -130,8 +130,8 @@ xfs_file_fsync( { struct xfs_inode *ip = XFS_I(file->f_mapping->host); struct xfs_mount *mp = ip->i_mount; - int error, err2; int log_flushed = 0; + int error; trace_xfs_file_fsync(ip); @@ -154,15 +154,17 @@ xfs_file_fsync( error = blkdev_issue_flush(mp->m_rtdev_targp->bt_bdev); else if (mp->m_logdev_targp != mp->m_ddev_targp) error = blkdev_issue_flush(mp->m_ddev_targp->bt_bdev); + if (error) + return error; /* * If the inode has a inode log item attached, it may need the journal * flushed to persist any changes the log item might be tracking. */ if (ip->i_itemp) { - err2 = xfs_fsync_flush_log(ip, datasync, &log_flushed); - if (err2 && !error) - error = err2; + error = xfs_fsync_flush_log(ip, datasync, &log_flushed); + if (error) + return error; } /* @@ -178,14 +180,11 @@ xfs_file_fsync( if (!log_flushed) { struct xfs_buftarg *file_targp = xfs_inode_buftarg(ip); - if (mp->m_logdev_targp == file_targp) { - err2 = blkdev_issue_flush(file_targp->bt_bdev); - if (err2 && !error) - error = err2; - } + if (mp->m_logdev_targp == file_targp) + return blkdev_issue_flush(file_targp->bt_bdev); } - return error; + return 0; } static int From 761e015e5a54851043c3b5bb7cfb6f539b01a35e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 7 Sep 2026 10:33:09 +0300 Subject: [PATCH 1091/1198] xfs: avoid extra cache flushes for multi-device file systems in xfs_fsync When xlog_force_lsn sets log_flushed, it has just called xlog_force_iclog through xlog_force_and_check_iclog, which sets XLOG_ICL_NEED_FLUSH before writing out the head iclog. This means that we already flushed the log, data, and (with the recent fix) RT devices before writing out the iclog start record and no extra cache flushed is required. This optimizes the external log case, and fixes a performance regression due to double RT dev flushes with "xfs: also flush the RT device cache in xlog_write_iclog". The explicit flush of the data that the device resides on when no iclog was written out is still required. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Reviewed-by: Carlos Maiolino Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_file.c | 36 +++++++++--------------------------- 1 file changed, 9 insertions(+), 27 deletions(-) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 0d31fea67a2c..d8202da15aca 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -129,7 +129,6 @@ xfs_file_fsync( int datasync) { struct xfs_inode *ip = XFS_I(file->f_mapping->host); - struct xfs_mount *mp = ip->i_mount; int log_flushed = 0; int error; @@ -139,27 +138,17 @@ xfs_file_fsync( if (error) return error; - if (xfs_is_shutdown(mp)) + if (xfs_is_shutdown(ip->i_mount)) return -EIO; xfs_iflags_clear(ip, XFS_ITRUNCATED); /* - * If we have an RT and/or log subvolume we need to make sure to flush - * the write cache the device used for file data first. This is to - * ensure newly written file data make it to disk before logging the new - * inode size in case of an extending write. - */ - if (XFS_IS_REALTIME_INODE(ip) && mp->m_rtdev_targp != mp->m_ddev_targp) - error = blkdev_issue_flush(mp->m_rtdev_targp->bt_bdev); - else if (mp->m_logdev_targp != mp->m_ddev_targp) - error = blkdev_issue_flush(mp->m_ddev_targp->bt_bdev); - if (error) - return error; - - /* - * If the inode has a inode log item attached, it may need the journal - * flushed to persist any changes the log item might be tracking. + * If the inode has a log item attached, we must force the log up to the + * last LSN in which the inode was modified to ensure all metadata is + * persisted. The log force will flush the caches for all devices + * before writing the log records unless it is a no-op because there are + * no modifications to this inode that need to be pushed out. */ if (ip->i_itemp) { error = xfs_fsync_flush_log(ip, datasync, &log_flushed); @@ -173,17 +162,10 @@ xfs_file_fsync( * when no metadata needed to be committed. * * Use the inode's actual file data target rather than assuming the - * main data device. Realtime inodes with a separate realtime device - * are flushed before the log force, so this fallback only applies - * when the file data target is the same as the log target. + * main data device. */ - if (!log_flushed) { - struct xfs_buftarg *file_targp = xfs_inode_buftarg(ip); - - if (mp->m_logdev_targp == file_targp) - return blkdev_issue_flush(file_targp->bt_bdev); - } - + if (!log_flushed) + return blkdev_issue_flush(xfs_inode_buftarg(ip)->bt_bdev); return 0; } From 50ba24ccb9a94f61c707209442ca23d98c815052 Mon Sep 17 00:00:00 2001 From: Anuj Gupta Date: Mon, 7 Sep 2026 10:27:39 +0300 Subject: [PATCH 1092/1198] xfs: set IOMAP_F_INTEGRITY for zoned writes on integrity devices xfs_iomap_set_anon_write does not set IOMAP_F_INTEGRITY based on bdev_has_integrity_csum(), so file system PI generation is silently skipped for zoned writes on integrity-enabled devices, and left to the block layer PI generation. Fixes: 6bbb4d96f797 ("xfs: support T10 protection information") Signed-off-by: Anuj Gupta [hch: ported to the recently introduced xfs_iomap_set_anon_write()] Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_iomap.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index c906c62d46f3..f2520a9b3a13 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -41,6 +41,8 @@ xfs_iomap_set_anon_write( iomap->offset = offset; iomap->length = length; iomap->flags = IOMAP_F_ANON_WRITE | IOMAP_F_DIRTY; + if (bdev_has_integrity_csum(iomap->bdev)) + iomap->flags |= IOMAP_F_INTEGRITY; } static inline xfs_filblks_t From e240919ca727776f16a468d3d90686dc82cfe9cb Mon Sep 17 00:00:00 2001 From: Deepanshu Kartikey Date: Sun, 6 Sep 2026 20:16:29 +0530 Subject: [PATCH 1093/1198] xfs: take hm->lock in xfs_ioc_health_monitor() before insert __xfs_healthmon_insert() asserts that hm->lock is held (lockdep_assert_held), but xfs_ioc_health_monitor() called it right after allocating hm, before ever taking the lock, triggering a lockdep warning. Take hm->lock around the call. Fixes: b3a289a2a9397 ("xfs: create event queuing, formatting, and discovery infrastructure") Reported-by: syzbot+ccdf3469f5f653bff7ac@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=ccdf3469f5f653bff7ac Signed-off-by: Deepanshu Kartikey Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_healthmon.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/xfs/xfs_healthmon.c b/fs/xfs/xfs_healthmon.c index b57fa033cec4..c3749675ef19 100644 --- a/fs/xfs/xfs_healthmon.c +++ b/fs/xfs/xfs_healthmon.c @@ -1223,7 +1223,9 @@ xfs_ioc_health_monitor( } running_event->type = XFS_HEALTHMON_RUNNING; running_event->domain = XFS_HEALTHMON_MOUNT; + mutex_lock(&hm->lock); __xfs_healthmon_insert(hm, INSERT_HEAD, running_event); + mutex_unlock(&hm->lock); /* * Preallocate the unmount event so that we can't fail to notify the From 4f4b743c2d2bbc336cb164d9d3d2ed6956ad8437 Mon Sep 17 00:00:00 2001 From: Ratheesh Kannoth Date: Fri, 4 Sep 2026 14:21:13 +0530 Subject: [PATCH 1094/1198] octeontx2-af: fix PF/CGX debugfs PCI bus lookup rvu_dbg_rvu_pf_cgx_map_display() locates each RVU PF PCI device via pci_get_domain_bus_and_slot() when printing the PF-to-CGX map. It assumed PF0 always sits on PCI bus 1 and derived other PF bus numbers as pf + 1, but the AF device can be enumerated on a different bus. Use rvu->pdev->bus->number as the base bus instead, so each PF lookup uses pf + start on systems where RVU functions are on contiguous buses but do not start at bus 1. Fixes: e2fb373038654 ("octeontx2-af: Display CGX, NIX and PF map in debugfs.") Signed-off-by: Subbaraya Sundeep Signed-off-by: Ratheesh Kannoth Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260904085114.3385530-1-rkannoth@marvell.com Signed-off-by: Jakub Kicinski --- .../net/ethernet/marvell/octeontx2/af/rvu_debugfs.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index 22ee99676879..904374baae6f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -829,19 +829,25 @@ static int rvu_dbg_rvu_pf_cgx_map_display(struct seq_file *filp, void *unused) int pf, domain, blkid; u8 cgx_id, lmac_id; u16 pcifunc; + u8 start; - domain = 2; + domain = pci_domain_nr(rvu->pdev->bus); mac_ops = get_mac_ops(rvu_first_cgx_pdata(rvu)); /* There can be no CGX devices at all */ if (!mac_ops) return 0; seq_printf(filp, "PCI dev\t\tRVU PF Func\tNIX block\t%s\tLMAC\tCHAN\n", mac_ops->name); + + /* All the PF devices are on contiguous PCI bus numbers, but the PF0(AF) + * may not start from 1 always. Hence get domain and bus from PCI device. + */ + start = rvu->pdev->bus->number; for (pf = 0; pf < rvu->hw->total_pfs; pf++) { if (!is_pf_cgxmapped(rvu, pf)) continue; - pdev = pci_get_domain_bus_and_slot(domain, pf + 1, 0); + pdev = pci_get_domain_bus_and_slot(domain, pf + start, 0); if (!pdev) continue; From 36a45facedd5c8e73bfb2403f8b0dbff05124c9c Mon Sep 17 00:00:00 2001 From: Donggeun Yoo Date: Thu, 3 Sep 2026 11:28:38 +0900 Subject: [PATCH 1095/1198] net: phy: dp83867: handle the active-high LED polarity mode Commit a274465cc3be ("net: phy: support 'active-high' property for PHY LEDs") added PHY_LED_ACTIVE_HIGH and made of_phy_led() set the matching bit in the modes mask when a LED node carries the 'active-high' property. dp83867 was not part of that series. dp83867_led_polarity_set() only recognizes PHY_LED_ACTIVE_LOW, so PHY_LED_ACTIVE_HIGH falls through to the default case and returns -EINVAL. of_phy_led() propagates the error, of_phy_leds() drops the LEDs registered so far and passes it on, and phy_probe() fails. A device tree marking a DP83867 LED as 'active-high', which leds/common.yaml allows and ethernet-phy.yaml references for led@N nodes, thus stops the PHY from probing. Active high is what the function programs when no polarity mode is requested at all, so the initial value of polarity already satisfies the request and only the case label is missing. The same series updated mxl-gpy in commit eb89c79c1b8f ("net: phy: mxl-gpy: correctly describe LED polarity") and aquantia in commit 9d55e68b19f2 ("net: phy: aquantia: correctly describe LED polarity override"). Fixes: a274465cc3be ("net: phy: support 'active-high' property for PHY LEDs") Signed-off-by: Donggeun Yoo Link: https://patch.msgid.link/20260903022839.4006614-1-donggeunyoo.kernel@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/phy/dp83867.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index 88255e92b4cd..61a941aa02d9 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -1150,6 +1150,9 @@ static int dp83867_led_polarity_set(struct phy_device *phydev, int index, case PHY_LED_ACTIVE_LOW: polarity = 0; break; + case PHY_LED_ACTIVE_HIGH: + polarity = DP83867_LED_POLARITY(index); + break; default: return -EINVAL; } From 4c46beb807efcc93f5899ebe1f5958248eb296c6 Mon Sep 17 00:00:00 2001 From: Long Li Date: Fri, 4 Sep 2026 13:26:40 -0700 Subject: [PATCH 1096/1198] net: mana: restore the XDP program pointer when pre-allocation fails mana_xdp_set() publishes the new program into apc->bpf_prog before it allocates anything, because mana_pre_alloc_rxbufs() sizes the buffers from it via mana_get_rxbuf_cfg(). When that allocation fails the function returns the error directly, skipping the err_dealloc_rxbuffs label which is the only place that restores the previous pointer. The attach is reported as failed, so the BPF core drops the reference it held for the caller and the program can be freed, while apc->bpf_prog still points at it. The next consumer of mana_xdp_get() - typically mana_chn_setxdp() from mana_alloc_queues() on the following ifup, or after a TX timeout reset - then calls bpf_prog_add() on freed memory. This is reachable from an ordinary "ip link set dev ethX xdp obj ..." whenever the per-queue RX buffer pre-allocation cannot be satisfied. Restore the previous program on that error path. Fixes: 730ff06d3f5c ("net: mana: Use page pool fragments for RX buffers instead of full pages to improve memory efficiency.") Signed-off-by: Long Li Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260904202640.3900685-1-longli@microsoft.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/microsoft/mana/mana_bpf.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/microsoft/mana/mana_bpf.c b/drivers/net/ethernet/microsoft/mana/mana_bpf.c index 53308e139cbe..5c9961ee9747 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_bpf.c +++ b/drivers/net/ethernet/microsoft/mana/mana_bpf.c @@ -208,6 +208,7 @@ static int mana_xdp_set(struct net_device *ndev, struct bpf_prog *prog, if (err) { NL_SET_ERR_MSG_MOD(extack, "XDP: Insufficient memory for tx/rx re-config"); + apc->bpf_prog = old_prog; return err; } From 2ac09b5353fe6858411fdc8c6efa60d832e20f13 Mon Sep 17 00:00:00 2001 From: Greg Marsden Date: Sat, 5 Sep 2026 10:00:41 -0700 Subject: [PATCH 1097/1198] net/rds: fix tcp stream corruption with large pages rds_message_map_pages() assigns PAGE_SIZE bytes to every scatterlist entry, even when total_len ends in a partial page. The RDS congestion map is defined as 8192 bytes, so on systems with PAGE_SIZE greater than 8192 the scatterlist maps bytes beyond the end of the congestion map. RDS-TCP transmits the SG contents according to those lengths, so the extra bytes become part of the TCP RDS stream and are interpreted as subsequent RDS message headers, corrupting the stream. Limit the final scatterlist mapping to the number of bytes remaining. This has no effect on systems with a 4K page size and allows RDS-TCP to be used on systems with 16K and larger page sizes. The RDS selftest, which previously hung on 16K pages, now passes. Fixes: 7875e18e0996 ("RDS: Message parsing") Signed-off-by: Greg Marsden Reviewed-by: Allison Henderson Link: https://patch.msgid.link/apxJjxvStibPI0AS@oracle.com Signed-off-by: Jakub Kicinski --- net/rds/message.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/rds/message.c b/net/rds/message.c index f25f2592586f..47d5e9ab9b10 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -431,7 +431,9 @@ struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned in for (i = 0; i < rm->data.op_nents; ++i) { sg_set_page(&rm->data.op_sg[i], virt_to_page((void *)page_addrs[i]), - PAGE_SIZE, 0); + i == rm->data.op_nents - 1 + ? total_len - (i * PAGE_SIZE) + : PAGE_SIZE, 0); } return rm; From 5e38d732ec67a5b1f9a56e6c73add480c4b6030a Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Mon, 7 Sep 2026 23:46:45 +0200 Subject: [PATCH 1098/1198] net: stmmac: fix TX descriptor availability check for TSO traffic stmmac_tso_xmit() estimates the number of free TX descriptors required by a TSO skb as: (skb->len - proto_hdr_len) / TSO_MAX_BUFF_SIZE + 1 which assumes the payload is split into TSO_MAX_BUFF_SIZE chunks. This underestimates the descriptors actually consumed by stmmac_tso_allocator(), since each fragment is mapped individually and so it needs at least one descriptor regardless of its size. Moreover, one descriptor is used for the L2/L3/L4 headers and, when the MSS changes, one more is consumed for the MSS context descriptor. For a highly fragmented TSO skb the check can therefore pass even when the ring has too few free slots. stmmac_tso_allocator() then writes past the available descriptors, overwriting descriptors still owned by the DMA engine, corrupting the TX ring. Add stmmac_tso_get_num_desc() to compute the exact number of descriptors needed for the header, the linear payload and each fragment, plus the MSS context descriptor when required, and use it in the availability check. Fixes: f748be531d70 ("stmmac: support new GMAC4") Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20260907-stmmac-fix-tso-nfrags-check-v1-1-328459906cdb@oss.qualcomm.com Signed-off-by: Jakub Kicinski --- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 31 +++++++++++++++---- 1 file changed, 25 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 5fe7e95fdd34..62c3441911e7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -4454,6 +4454,26 @@ static bool stmmac_tso_valid_packet(struct sk_buff *skb) header_len + gso_size < 16383; } +static int stmmac_tso_get_num_desc(struct stmmac_tx_queue *tx_q, + struct sk_buff *skb, u32 pay_len) +{ + int i, ndesc = 1; + + /* head payload */ + ndesc += DIV_ROUND_UP(pay_len, TSO_MAX_BUFF_SIZE); + /* frag payload */ + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + + ndesc += DIV_ROUND_UP(skb_frag_size(frag), + TSO_MAX_BUFF_SIZE); + } + /* MSS update requires a new descriptor */ + ndesc += !!(skb_shinfo(skb)->gso_size != tx_q->mss); + + return ndesc; +} + /** * stmmac_tso_xmit - Tx entry point of the driver for oversized frames (TSO) * @skb : the socket buffer @@ -4497,10 +4517,10 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) struct stmmac_priv *priv = netdev_priv(dev); unsigned int first_entry, entry, tx_packets; struct stmmac_txq_stats *txq_stats; + int i, first_tx, nfrags, ndesc; struct stmmac_tx_queue *tx_q; bool set_ic, is_last_segment; u32 pay_len, mss, queue; - int i, first_tx, nfrags; u8 proto_hdr_len, hdr; dma_addr_t des; @@ -4513,14 +4533,15 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) /* Compute header lengths */ proto_hdr_len = stmmac_tso_header_size(skb); + pay_len = skb_headlen(skb) - proto_hdr_len; /* no frags */ + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) hdr = sizeof(struct udphdr); else hdr = tcp_hdrlen(skb); - /* Desc availability based on threshold should be enough safe */ - if (unlikely(stmmac_tx_avail(priv, queue) < - (((skb->len - proto_hdr_len) / TSO_MAX_BUFF_SIZE + 1)))) { + ndesc = stmmac_tso_get_num_desc(tx_q, skb, pay_len); + if (unlikely(stmmac_tx_avail(priv, queue) < ndesc)) { if (!netif_tx_queue_stopped(netdev_get_tx_queue(dev, queue))) { netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue)); @@ -4532,8 +4553,6 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_BUSY; } - pay_len = skb_headlen(skb) - proto_hdr_len; /* no frags */ - mss = skb_shinfo(skb)->gso_size; /* set new MSS value if needed */ From 19b4ed644d68098cc62ab612727f40d30f43476c Mon Sep 17 00:00:00 2001 From: Zihan Xi Date: Tue, 8 Sep 2026 07:42:56 +0000 Subject: [PATCH 1099/1198] ipv6: fix fib6 walker UAF on seq stop ipv6_route_iter_active() treats a walker in FWS_U at the table root as already unlinked. fib6_del_route() can move a still-linked walker into that same state when the current leaf is the last route at the root, so ipv6_route_native_seq_stop() skips fib6_walker_unlink(). The seq private object can then be freed while it remains on net->ipv6.fib6_walkers. A later route deletion walks the dangling list and uses the freed walker. Use the list head as membership state and reinitialize it when unlinking. Keep the existing w->node check so a never-started iterator with a zeroed private object is not treated as linked. The same stop helper is used by /proc/net/ipv6_route and by the BPF ipv6_route iterator. The BPF show path only widens the race. Fixes: 8d2ca1d7b5c3 ("ipv6: avoid high order memory allocations for /proc/net/ipv6_route") Cc: stable@vger.kernel.org Reported-by: Vega Co-developed-by: Luxing Yin Signed-off-by: Luxing Yin Signed-off-by: Zihan Xi Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/89699735763f6c297584d7c2ff106239cc1e8ce0.1788837093.git.zihanx@nebusec.ai Signed-off-by: Jakub Kicinski --- net/ipv6/ip6_fib.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 3e382ba1573e..9ea75703b38d 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -85,7 +85,7 @@ static void fib6_walker_link(struct net *net, struct fib6_walker *w) static void fib6_walker_unlink(struct net *net, struct fib6_walker *w) { write_lock_bh(&net->ipv6.fib6_walker_lock); - list_del(&w->lh); + list_del_init(&w->lh); write_unlock_bh(&net->ipv6.fib6_walker_lock); } @@ -2760,7 +2760,7 @@ static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos) static bool ipv6_route_iter_active(struct ipv6_route_iter *iter) { struct fib6_walker *w = &iter->w; - return w->node && !(w->state == FWS_U && w->node == w->root); + return w->node && !list_empty(&w->lh); } static void ipv6_route_native_seq_stop(struct seq_file *seq, void *v) From a2dc179481d18f6df7274522571b64dd50f31e81 Mon Sep 17 00:00:00 2001 From: MD Danish Anwar Date: Tue, 8 Sep 2026 14:38:56 +0530 Subject: [PATCH 1100/1198] net: hsr: enable promiscuous mode on interlink port with fwd offload hsr_portdev_setup() skips promiscuous mode on non-master ports when hsr->fwd_offloaded is set. fwd_offloaded is derived only from the ring slaves' NETIF_F_HW_HSR_FWD bit, so this also skips it for the interlink port, which never gets forwarding offload. Without promiscuous mode, the interlink NIC drops unicast frames addressed to hsr_dev's MAC (e.g. SAN traffic to the RedBox), breaking RedBox whenever the ring is HW-offloaded. Fixes: 5055cccfc2d1 ("net: hsr: Provide RedBox support (HSR-SAN)") Signed-off-by: MD Danish Anwar Reviewed-by: Simon Horman Reviewed-by: Fernando Fernandez Mancera Link: https://patch.msgid.link/20260908090856.2876114-1-danishanwar@ti.com Signed-off-by: Jakub Kicinski --- net/hsr/hsr_slave.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c index 01c73b4b50dd..a546f70f9cc8 100644 --- a/net/hsr/hsr_slave.c +++ b/net/hsr/hsr_slave.c @@ -149,9 +149,12 @@ static int hsr_portdev_setup(struct hsr_priv *hsr, struct net_device *dev, int res; /* Don't use promiscuous mode for offload since L2 frame forward - * happens at the offloaded hardware. + * happens at the offloaded hardware. The interlink port never + * gets forwarding offload (RedBox forwarding to/from it is done + * by this driver), so it still needs promiscuous mode to receive + * frames addressed to hsr_dev's MAC rather than its own. */ - if (!port->hsr->fwd_offloaded) { + if (!port->hsr->fwd_offloaded || port->type == HSR_PT_INTERLINK) { res = dev_set_promiscuity(dev, 1); if (res) return res; @@ -176,7 +179,7 @@ static int hsr_portdev_setup(struct hsr_priv *hsr, struct net_device *dev, fail_rx_handler: netdev_upper_dev_unlink(dev, hsr_dev); fail_upper_dev_link: - if (!port->hsr->fwd_offloaded) + if (!port->hsr->fwd_offloaded || port->type == HSR_PT_INTERLINK) dev_set_promiscuity(dev, -1); return res; @@ -240,7 +243,7 @@ void hsr_del_port(struct hsr_port *port) netdev_update_features(master->dev); dev_set_mtu(master->dev, hsr_get_max_mtu(hsr)); netdev_rx_handler_unregister(port->dev); - if (!port->hsr->fwd_offloaded) + if (!port->hsr->fwd_offloaded || port->type == HSR_PT_INTERLINK) dev_set_promiscuity(port->dev, -1); if (port->type == HSR_PT_SLAVE_A || port->type == HSR_PT_SLAVE_B) vlan_vids_del_by_dev(port->dev, master->dev); From e1406330d70e56dd44fa6fbafc86e77e5c80c122 Mon Sep 17 00:00:00 2001 From: Runyu Xiao Date: Tue, 8 Sep 2026 18:39:24 +0800 Subject: [PATCH 1101/1198] net: macb: initialize PTP state before registering clock MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit gem_ptp_init() registers the PTP clock before initializing bp->tsu_clk_lock and the TSU hardware. Since ptp_clock_register() publishes the PTP character device, userspace may invoke PTP callbacks before the lock and hardware are ready. In addition, gem_ptp_init() is called from both the interface open and resume paths. Reinitializing tsu_clk_lock there can reset the lock while timestamp processing is using it. This race is theoretical and has not been observed in practice. Initialize tsu_clk_lock once during probe and initialize the TSU before registering the PTP clock. Fixes: ab91f0a9b5f4 ("net: macb: Add hardware PTP support") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/netdev/20260904030439.3994047-1-runyu.xiao@seu.edu.cn/ Reviewed-by: Théo Lebrun Reviewed-by: Vadim Fedorenko Signed-off-by: Runyu Xiao Link: https://patch.msgid.link/20260908103924.607033-1-runyu.xiao@seu.edu.cn Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/cadence/macb_main.c | 1 + drivers/net/ethernet/cadence/macb_ptp.c | 5 +---- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 77dec2d6e3fb..4cb5d7088d43 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -5883,6 +5883,7 @@ static int macb_probe(struct platform_device *pdev) } spin_lock_init(&bp->lock); spin_lock_init(&bp->stats_lock); + spin_lock_init(&bp->tsu_clk_lock); /* setup capabilities */ macb_configure_caps(bp, macb_config); diff --git a/drivers/net/ethernet/cadence/macb_ptp.c b/drivers/net/ethernet/cadence/macb_ptp.c index e5195d7dac1d..6d9166389988 100644 --- a/drivers/net/ethernet/cadence/macb_ptp.c +++ b/drivers/net/ethernet/cadence/macb_ptp.c @@ -334,6 +334,7 @@ void gem_ptp_init(struct net_device *netdev) bp->tsu_rate = bp->ptp_info->get_tsu_rate(bp); bp->ptp_clock_info.max_adj = bp->ptp_info->get_ptp_max_adj(); gem_ptp_init_timer(bp); + gem_ptp_init_tsu(bp); bp->ptp_clock = ptp_clock_register(&bp->ptp_clock_info, &netdev->dev); if (IS_ERR(bp->ptp_clock)) { pr_err("ptp clock register failed: %ld\n", @@ -345,10 +346,6 @@ void gem_ptp_init(struct net_device *netdev) return; } - spin_lock_init(&bp->tsu_clk_lock); - - gem_ptp_init_tsu(bp); - dev_info(&bp->pdev->dev, "%s ptp clock registered.\n", GEM_PTP_TIMER_NAME); } From 6ca81bbc31cdc964e4b74d17b86215d4a810a56f Mon Sep 17 00:00:00 2001 From: Donggeun Yoo Date: Tue, 8 Sep 2026 19:59:58 +0900 Subject: [PATCH 1102/1198] net: phy: dp83td510: handle the active-high LED polarity mode dp83td510_led_polarity_set() only recognizes PHY_LED_ACTIVE_LOW, so PHY_LED_ACTIVE_HIGH falls through to the default case and returns -EINVAL. of_phy_led() propagates the error, of_phy_leds() drops the LEDs registered so far and passes it on, and phy_probe() returns it. A device tree marking a DP83TD510 LED as 'active-high', which leds/common.yaml allows and ethernet-phy.yaml references for led@N nodes, thus leaves the mdio device unbound, so phy_attach_direct() falls back to the genphy driver, which cannot drive this 10BASE-T1L single-mode PHY, so the interface has no usable link. The callback initializes polarity to DP83TD510E_LED_POLARITY(index), which is the active-high setting, so the request is already satisfied and only the case label is missing. Cc: stable@vger.kernel.org Fixes: 5b281fe7e396 ("net: phy: dp83td510: introduce LED framework support") Signed-off-by: Donggeun Yoo Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20260908105959.70453-3-donggeunyoo.kernel@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/phy/dp83td510.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/phy/dp83td510.c b/drivers/net/phy/dp83td510.c index d75dae6071ad..9e9a41bf6457 100644 --- a/drivers/net/phy/dp83td510.c +++ b/drivers/net/phy/dp83td510.c @@ -439,6 +439,9 @@ static int dp83td510_led_polarity_set(struct phy_device *phydev, int index, case PHY_LED_ACTIVE_LOW: polarity = 0; break; + case PHY_LED_ACTIVE_HIGH: + polarity = DP83TD510E_LED_POLARITY(index); + break; default: return -EINVAL; } From b7ee18725f2292ab554aa96a101ae42d45f008bd Mon Sep 17 00:00:00 2001 From: Zihan Xi Date: Tue, 8 Sep 2026 11:58:39 +0000 Subject: [PATCH 1103/1198] ipmr: account multicast table and route memory A netadmin in a user+net namespace can create many IPv4 and IPv6 multicast routing tables with MRT_TABLE and MRT6_TABLE. Each unseen id allocates an mr_table via the shared mr_table_alloc(), links it into the per-net list, and leaves it until netns teardown. Those objects were not charged to memcg, so the host unreclaimable slab grows with the table count. Account mr_table allocations with GFP_KERNEL_ACCOUNT and mark the IPv4/IPv6 MFC caches SLAB_ACCOUNT. This matches the established handling of IP addresses, routes and alternate interface names. Unresolved MFC entries are still allocated from softIRQ with GFP_ATOMIC and are not charged. They expire after 10 seconds and are bounded by the socket receive queue; see commit 0079ad8e8dc3 ("ipmr: remove hard code cache_resolve_queue_len limit"). Fixes: f0ad0860d01e ("ipv4: ipmr: support multiple tables") Fixes: d1db275dd3f6 ("ipv6: ip6mr: support multiple tables") Cc: stable@vger.kernel.org Reported-by: Vega Signed-off-by: Zihan Xi Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/050b58f7fc6b45da0fb12768ebb62d18fa46133d.1788784801.git.zihanx@nebusec.ai Signed-off-by: Jakub Kicinski --- net/ipv4/ipmr.c | 3 ++- net/ipv4/ipmr_base.c | 2 +- net/ipv6/ip6mr.c | 2 +- 3 files changed, 4 insertions(+), 3 deletions(-) diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index e5f2b1c6150d..b9c544d48c45 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -3376,7 +3376,8 @@ int __init ip_mr_init(void) { int err; - mrt_cachep = KMEM_CACHE(mfc_cache, SLAB_HWCACHE_ALIGN | SLAB_PANIC); + mrt_cachep = KMEM_CACHE(mfc_cache, + SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT); err = register_pernet_subsys(&ipmr_net_ops); if (err) diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c index 867b24beded1..a0ec6d19a237 100644 --- a/net/ipv4/ipmr_base.c +++ b/net/ipv4/ipmr_base.c @@ -52,7 +52,7 @@ mr_table_alloc(struct net *net, u32 id, struct mr_table *mrt; int err; - mrt = kzalloc_obj(*mrt); + mrt = kzalloc_obj(*mrt, GFP_KERNEL_ACCOUNT); if (!mrt) return ERR_PTR(-ENOMEM); mrt->id = id; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 3f2ed9b77deb..9d8116b5edb1 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1427,7 +1427,7 @@ int __init ip6_mr_init(void) { int err; - mrt_cachep = KMEM_CACHE(mfc6_cache, SLAB_HWCACHE_ALIGN); + mrt_cachep = KMEM_CACHE(mfc6_cache, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT); if (!mrt_cachep) return -ENOMEM; From e184a4a6f423550a25adce867036cdb1ff471745 Mon Sep 17 00:00:00 2001 From: Eelco Chaudron Date: Tue, 8 Sep 2026 16:15:17 +0200 Subject: [PATCH 1104/1198] openvswitch: fix wrong flag value in get_ipv6_ext_hdrs() The ESP and AH cases in get_ipv6_ext_hdrs() used IPPROTO_FRAGMENT instead of OFPIEH12_FRAG when checking for out-of-order extension headers, causing the fragment header to not be recognised as a valid predecessor. The original code used IPPROTO_FRAGMENT (44) as a bitmask constant where OFPIEH12_FRAG (1 << 4 = 16) was intended. IPPROTO_FRAGMENT encodes bits 2, 3 and 5 (OFPIEH12_AUTH | OFPIEH12_DEST | OFPIEH12_ROUTER), but not bit 4 (OFPIEH12_FRAG). This caused incorrect OFPIEH12_UNSEQ verdicts in both the ESP and AH arms: the ESP arm failed to whitelist OFPIEH12_FRAG, while the AH arm accidentally whitelisted OFPIEH12_AUTH. With the fix, a packet with two AH headers now also gets OFPIEH12_UNSEQ in addition to OFPIEH12_UNREP, matching the ESP arm which already sets UNSEQ on a repeat, which is the intended behavior. Fixes: 28a3f0601727 ("net: openvswitch: IPv6: Add IPv6 extension header support") Reported-by: Paolo Abeni Reviewed-by: Aaron Conole Reviewed-by: Ilya Maximets Signed-off-by: Eelco Chaudron Link: https://patch.msgid.link/1b1582eb07550d71f3cbe210e5cb31eeb8d0ad86.1788876917.git.echaudro@redhat.com Signed-off-by: Jakub Kicinski --- net/openvswitch/flow.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 46c1d66aad8c..868d9fdf3afd 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -288,7 +288,7 @@ static void get_ipv6_ext_hdrs(struct sk_buff *skb, struct ipv6hdr *nh, if (*ext_hdrs & OFPIEH12_ESP) *ext_hdrs |= OFPIEH12_UNREP; if ((*ext_hdrs & ~(OFPIEH12_HOP | OFPIEH12_DEST | - OFPIEH12_ROUTER | IPPROTO_FRAGMENT | + OFPIEH12_ROUTER | OFPIEH12_FRAG | OFPIEH12_AUTH | OFPIEH12_UNREP)) || dest_options_header_count >= 2) { *ext_hdrs |= OFPIEH12_UNSEQ; @@ -301,7 +301,7 @@ static void get_ipv6_ext_hdrs(struct sk_buff *skb, struct ipv6hdr *nh, *ext_hdrs |= OFPIEH12_UNREP; if ((*ext_hdrs & ~(OFPIEH12_HOP | OFPIEH12_DEST | OFPIEH12_ROUTER | - IPPROTO_FRAGMENT | OFPIEH12_UNREP)) || + OFPIEH12_FRAG | OFPIEH12_UNREP)) || dest_options_header_count >= 2) { *ext_hdrs |= OFPIEH12_UNSEQ; } From 478eb5abb51931a152abab068f8a717b7ff480fd Mon Sep 17 00:00:00 2001 From: Xuanqiang Luo Date: Wed, 9 Sep 2026 15:03:35 +0800 Subject: [PATCH 1105/1198] net/sched: act_api: release all action references on NEWACTION failure When a batched RTM_NEWACTION request replaces an existing action, tcf_idr_check_alloc() takes a temporary reference on it. If a later action fails to initialize, tcf_action_destroy() uses strict release semantics to clean up the actions initialized so far. For an action bound to a filter, the strict check returns -EPERM without dropping the temporary reference. This error also makes tcf_action_destroy() return before releasing subsequent entries. Any new action initialized between the bound action and the failing entry is leaked together with its reserved IDR slot, preventing reuse of its index. Use tcf_idr_release() to drop each reference held by the batch without rejecting bound actions. This allows cleanup to continue through all initialized entries and preserves the module reference release when an action is destroyed. Explicit action deletion and flushing retain their separate bind-count checks. Fixes: 55334a5db5cd ("net_sched: act: refuse to remove bound action outside") Cc: stable@vger.kernel.org Signed-off-by: Xuanqiang Luo Reviewed-by: Jamal Hadi Salim Link: https://patch.msgid.link/20260909070336.32979-2-xuanqiang.luo@linux.dev Signed-off-by: Jakub Kicinski --- net/sched/act_api.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 37eced84dfa5..19501dc99464 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -1200,18 +1200,13 @@ EXPORT_SYMBOL(tcf_action_exec); int tcf_action_destroy(struct tc_action *actions[], int bind) { - const struct tc_action_ops *ops; struct tc_action *a; int ret = 0, i; tcf_act_for_each_action(i, a, actions) { actions[i] = NULL; - ops = a->ops; - ret = __tcf_idr_release(a, bind, true); - if (ret == ACT_P_DELETED) - module_put(ops->owner); - else if (ret < 0) - return ret; + /* Drop our reference even if the action is still bound to a filter. */ + ret = tcf_idr_release(a, bind); } return ret; } From 2a86bbed9f60702e97a8194e40f90f4db22d7795 Mon Sep 17 00:00:00 2001 From: Xuanqiang Luo Date: Wed, 9 Sep 2026 15:03:36 +0800 Subject: [PATCH 1106/1198] selftests: tc-testing: test action batch failure cleanup Add tests for cleanup after a batched RTM_NEWACTION request fails. Replace an existing gact action bound to a filter, then fail a later entry by requesting goto chain without a classifier context. Check that the bound action's reference count returns to its original value. Also cover a successfully initialized new action between the bound action and the failing entry, verifying that its reserved index can be reused. Repeat the bound action in another batch to check that each temporary reference to the same action is released. Signed-off-by: Xuanqiang Luo Reviewed-by: Jamal Hadi Salim Link: https://patch.msgid.link/20260909070336.32979-3-xuanqiang.luo@linux.dev Signed-off-by: Jakub Kicinski --- .../tc-tests/actions/gact-rollback.json | 78 +++++++++++++++++++ 1 file changed, 78 insertions(+) create mode 100644 tools/testing/selftests/tc-testing/tc-tests/actions/gact-rollback.json diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/gact-rollback.json b/tools/testing/selftests/tc-testing/tc-tests/actions/gact-rollback.json new file mode 100644 index 000000000000..e92a4180db68 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/gact-rollback.json @@ -0,0 +1,78 @@ +[ + { + "id": "e3b1", + "name": "Failed action batch releases a bound action reference", + "category": [ + "actions", + "gact" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress", + "$TC actions add action pass index 1", + "$TC filter add dev $DEV1 protocol all ingress prio 1 matchall action gact index 1" + ], + "cmdUnderTest": "$TC actions replace action pass index 1 action goto chain 42 index 3", + "expExitCode": "255", + "verifyCmd": "$TC actions ls action gact", + "matchPattern": "total acts 1.*index 1 ref 2 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "e3b2", + "name": "Failed action batch releases entries after a bound action", + "category": [ + "actions", + "gact" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress", + "$TC actions add action pass index 1", + "$TC filter add dev $DEV1 protocol all ingress prio 1 matchall action gact index 1", + [ + "$TC actions replace action pass index 1 action pass index 2 action goto chain 42 index 3", + 255 + ] + ], + "cmdUnderTest": "$TC actions add action pass index 2", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action gact", + "matchPattern": "total acts 2.*index 1 ref 2 bind 1.*index 2 ref 1 bind 0", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "e3b3", + "name": "Failed action batch releases repeated references to a bound action", + "category": [ + "actions", + "gact" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress", + "$TC actions add action pass index 1", + "$TC filter add dev $DEV1 protocol all ingress prio 1 matchall action gact index 1" + ], + "cmdUnderTest": "$TC actions replace action pass index 1 action pass index 1 action goto chain 42 index 3", + "expExitCode": "255", + "verifyCmd": "$TC actions ls action gact", + "matchPattern": "total acts 1.*index 1 ref 2 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + } +] From cfdcf5571c3107bf636002fc0c16ce93c19bd671 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Michel=20D=C3=A4nzer?= Date: Mon, 18 May 2026 17:48:09 +0200 Subject: [PATCH 1107/1198] drm/amd/display: Consult MCCS FreeSync cap only if requested & supported MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When the do_mccs parameter is false, we don't call dm_helpers_read_mccs_caps, so sink->mccs_caps.freesync_supported is unlikely to be true. Fixes: 6f71d5dd3206 ("drm/amd/display: Read sink freesync support via mccs") Bug: https://gitlab.freedesktop.org/drm/amd/-/work_items/5286 Signed-off-by: Michel Dänzer Reviewed-by: Alex Hung Signed-off-by: Alex Deucher (cherry picked from commit ac3aea794fb4156467b4b3b92c3155d95bf435c9) Cc: stable@vger.kernel.org --- .../amd/display/amdgpu_dm/amdgpu_dm_connector.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_connector.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_connector.c index c8a1ab8c3b16..d03773887214 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_connector.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_connector.c @@ -3937,17 +3937,15 @@ void amdgpu_dm_update_freesync_caps(struct drm_connector *connector, } /* Handle MCCS */ - if (do_mccs) + if (do_mccs) { dm_helpers_read_mccs_caps(adev->dm.dc->ctx, amdgpu_dm_connector->dc_link, sink); - if ((sink->sink_signal == SIGNAL_TYPE_HDMI_TYPE_A || - as_type == FREESYNC_TYPE_PCON_IN_WHITELIST) && - (!sink->edid_caps.freesync_vcp_code || - (sink->edid_caps.freesync_vcp_code && !sink->mccs_caps.freesync_supported))) - freesync_capable = false; + if (sink->edid_caps.freesync_vcp_code && !sink->mccs_caps.freesync_supported) + freesync_capable = false; - if (do_mccs && sink->mccs_caps.freesync_supported && freesync_capable) - dm_helpers_mccs_vcp_set(adev->dm.dc->ctx, amdgpu_dm_connector->dc_link, sink); + if (sink->mccs_caps.freesync_supported && freesync_capable) + dm_helpers_mccs_vcp_set(adev->dm.dc->ctx, amdgpu_dm_connector->dc_link, sink); + } update: if (dm_con_state) From 87ceb8cba73d0b3c4025ff42495bccd8164acaed Mon Sep 17 00:00:00 2001 From: Arunpravin Paneer Selvam Date: Wed, 2 Sep 2026 18:33:48 +0530 Subject: [PATCH 1108/1198] drm/amdgpu: skip the VMID 0 flush for VRAM MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Clear-on-release only runs on VRAM, which amdgpu_ttm_map_buffer() reaches via its direct MC address without programming a GART window, yet the wipe still forces a VMID 0 flush. On GFX11 (e.g. Navi33) that spurious SDMA flush can wedge the engine; only flush when a GART window is actually used. v2: Let amdgpu_ttm_map_buffer() return whether the VMID 0 flush is needed, and drive the clear and copy paths from that. (Christian) v3: Make the vm_needs_flush output parameter mandatory instead of allowing NULL. (Christian) Fixes: a68c7eaa7a8f ("drm/amdgpu: Enable clear page functionality") Closes: https://gitlab.freedesktop.org/drm/amd/-/work_items/5413 Cc: Christian König Signed-off-by: Arunpravin Paneer Selvam Reviewed-by: Christian König Reviewed-by: Timur Kristóf Signed-off-by: Alex Deucher (cherry picked from commit a306e406e570b74318ff7d80e5b07b540ca1d3a9) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 05abf4c31dce..016957cac1f2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -191,6 +191,8 @@ amdgpu_ttm_job_submit(struct amdgpu_device *adev, struct amdgpu_ttm_buffer_entit * @tmz: if we should setup a TMZ enabled mapping * @size: in number of bytes to map, out number of bytes mapped * @addr: resulting address inside the MC address space + * @vm_needs_flush: out, set true if a GART window was programmed (VMID 0 flush + * needed) or false for a direct address * * Setup one of the GART windows to access a specific piece of memory or return * the physical address for local memory. @@ -200,7 +202,8 @@ static int amdgpu_ttm_map_buffer(struct amdgpu_ttm_buffer_entity *entity, struct ttm_resource *mem, struct amdgpu_res_cursor *mm_cur, unsigned int window, - bool tmz, uint64_t *size, uint64_t *addr) + bool tmz, uint64_t *size, uint64_t *addr, + bool *vm_needs_flush) { struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev); unsigned int offset, num_pages, num_dw, num_bytes; @@ -221,9 +224,12 @@ static int amdgpu_ttm_map_buffer(struct amdgpu_ttm_buffer_entity *entity, if (!tmz && mem->start != AMDGPU_BO_INVALID_OFFSET) { *addr = amdgpu_ttm_domain_start(adev, mem->mem_type) + mm_cur->start; + *vm_needs_flush = false; return 0; } + /* A GART window is programmed below, so its VMID 0 TLB needs a flush */ + *vm_needs_flush = true; /* * If start begins at an offset inside the page, then adjust the size @@ -324,6 +330,7 @@ static int amdgpu_ttm_copy_mem_to_mem(struct amdgpu_device *adev, while (src_mm.remaining) { uint64_t from, to, cur_size, tiling_flags; uint32_t num_type, data_format, max_com, write_compress_disable; + bool src_vm_flush, dst_vm_flush; struct dma_fence *next; /* Never copy more than 256MiB at once to avoid a timeout */ @@ -331,12 +338,12 @@ static int amdgpu_ttm_copy_mem_to_mem(struct amdgpu_device *adev, /* Map src to window 0 and dst to window 1. */ r = amdgpu_ttm_map_buffer(entity, src->bo, src->mem, &src_mm, - 0, tmz, &cur_size, &from); + 0, tmz, &cur_size, &from, &src_vm_flush); if (r) goto error; r = amdgpu_ttm_map_buffer(entity, dst->bo, dst->mem, &dst_mm, - 1, tmz, &cur_size, &to); + 1, tmz, &cur_size, &to, &dst_vm_flush); if (r) goto error; @@ -364,7 +371,7 @@ static int amdgpu_ttm_copy_mem_to_mem(struct amdgpu_device *adev, } r = amdgpu_copy_buffer(adev, entity, from, to, cur_size, resv, - &next, true, copy_flags); + &next, src_vm_flush || dst_vm_flush, copy_flags); if (r) goto error; @@ -2624,6 +2631,7 @@ int amdgpu_ttm_clear_buffer(struct amdgpu_ttm_buffer_entity *entity, struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); struct dma_fence *fence = NULL; struct amdgpu_res_cursor dst; + bool vm_needs_flush = false; int r; if (!entity) @@ -2645,13 +2653,13 @@ int amdgpu_ttm_clear_buffer(struct amdgpu_ttm_buffer_entity *entity, cur_size = min(dst.size, 256ULL << 20); r = amdgpu_ttm_map_buffer(entity, &bo->tbo, bo->tbo.resource, &dst, - 0, false, &cur_size, &to); + 0, false, &cur_size, &to, &vm_needs_flush); if (r) goto error; r = amdgpu_ttm_fill_mem(adev, entity, 0, to, cur_size, resv, - &next, true, k_job_id); + &next, vm_needs_flush, k_job_id); if (r) goto error; From 622b4e8505aa7453a53d17fa3a288871f270fc8b Mon Sep 17 00:00:00 2001 From: Harry Wentland Date: Tue, 16 Jun 2026 13:39:21 -0400 Subject: [PATCH 1109/1198] dm/amdgpu: fix malformed link_settings debugfs output [Why] dp_link_settings_read() passed strlen() of each format string as the size argument to snprintf() and then advanced rd_buf_ptr by that same fixed amount. The format-string length has no relation to the formatted output length, so snprintf() truncated each field at a NUL it wrote inside the buffer while the pointer was advanced past it. The result is a buffer peppered with embedded NUL bytes and fields that are silently cut short, so the data read back from the debugfs node does not reflect the actual link settings. [How] Use scnprintf() with the real remaining buffer size (rd_buf_size - (rd_buf_ptr - rd_buf)) and advance rd_buf_ptr by its return value, which is the number of characters actually written. This both bounds each write to the space left in rd_buf and keeps the output a single, properly terminated string. The now-unused str_len local is removed. Fixes: 41db5f1931ec ("drm/amd/display: set-read link rate and lane count through debugfs") Assisted-by: Copilot:claude-opus-4.8 Signed-off-by: Harry Wentland Reviewed-by: Alex Hung Signed-off-by: Alex Deucher (cherry picked from commit 43b9f0f18693c7f7b75613f3aeae25fa2b4e2f76) Cc: stable@vger.kernel.org --- .../amd/display/amdgpu_dm/amdgpu_dm_debugfs.c | 20 ++++++++----------- 1 file changed, 8 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c index c4b2fc690fd7..2a6b48e24869 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c @@ -196,7 +196,6 @@ static ssize_t dp_link_settings_read(struct file *f, char __user *buf, char *rd_buf_ptr = NULL; const uint32_t rd_buf_size = 100; uint32_t result = 0; - uint8_t str_len = 0; int r; if (*pos & 3 || size & 3) @@ -208,29 +207,26 @@ static ssize_t dp_link_settings_read(struct file *f, char __user *buf, rd_buf_ptr = rd_buf; - str_len = strlen("Current: %d 0x%x %d "); - snprintf(rd_buf_ptr, str_len, "Current: %d 0x%x %d ", + rd_buf_ptr += scnprintf(rd_buf_ptr, rd_buf_size - (rd_buf_ptr - rd_buf), + "Current: %d 0x%x %d ", link->cur_link_settings.lane_count, link->cur_link_settings.link_rate, link->cur_link_settings.link_spread); - rd_buf_ptr += str_len; - str_len = strlen("Verified: %d 0x%x %d "); - snprintf(rd_buf_ptr, str_len, "Verified: %d 0x%x %d ", + rd_buf_ptr += scnprintf(rd_buf_ptr, rd_buf_size - (rd_buf_ptr - rd_buf), + "Verified: %d 0x%x %d ", link->verified_link_cap.lane_count, link->verified_link_cap.link_rate, link->verified_link_cap.link_spread); - rd_buf_ptr += str_len; - str_len = strlen("Reported: %d 0x%x %d "); - snprintf(rd_buf_ptr, str_len, "Reported: %d 0x%x %d ", + rd_buf_ptr += scnprintf(rd_buf_ptr, rd_buf_size - (rd_buf_ptr - rd_buf), + "Reported: %d 0x%x %d ", link->reported_link_cap.lane_count, link->reported_link_cap.link_rate, link->reported_link_cap.link_spread); - rd_buf_ptr += str_len; - str_len = strlen("Preferred: %d 0x%x %d "); - snprintf(rd_buf_ptr, str_len, "Preferred: %d 0x%x %d\n", + rd_buf_ptr += scnprintf(rd_buf_ptr, rd_buf_size - (rd_buf_ptr - rd_buf), + "Preferred: %d 0x%x %d\n", link->preferred_link_setting.lane_count, link->preferred_link_setting.link_rate, link->preferred_link_setting.link_spread); From 2e8ff3ac79eb09dccbd8f00ee5da1b61e53246be Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Thu, 18 Jun 2026 09:52:14 -0700 Subject: [PATCH 1110/1198] drm/amd/display: Shorten hdmi_frl_status_polling_workqueue There is a warning when creating the hdmi_frl_status_polling_wq workqueue because "hdmi_frl_status_polling_workqueue" excceds WQ_NAME_LEN: workqueue: name exceeds WQ_NAME_LEN. Truncating to: hdmi_frl_status_polling_workque Shorten the workqueue name to "hdmi_frl_status_polling_wq" like the structure member to avoid the warning. Fixes: 5c9b8b27a883 ("drm/amd/display: Tie FRL support into amdgpu_dm") Reviewed-by: Alex Hung Signed-off-by: Nathan Chancellor Reviewed-by: Tvrtko Ursulin Link: https://patch.msgid.link/20260618-amdgpu-fix-wq_name_len-warning-v2-1-ef0e2e6f5be7@kernel.org Signed-off-by: Mario Limonciello Signed-off-by: Alex Deucher (cherry picked from commit 767ae341b68193fda5fdbc510b2d77e3e8938039) --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 2fe934036e36..a95243656f54 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -747,9 +747,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) } if (adev->dm.dc->caps.max_links > 0) { adev->dm.hdmi_frl_status_polling_wq = - create_singlethread_workqueue("hdmi_frl_status_polling_workqueue"); + create_singlethread_workqueue("hdmi_frl_status_polling_wq"); if (!adev->dm.hdmi_frl_status_polling_wq) - drm_err(adev_to_drm(adev), "failed to initialize hdmi_frl_status_polling_workqueue\n"); + drm_err(adev_to_drm(adev), "failed to initialize hdmi_frl_status_polling_wq\n"); } if (dc_is_dmub_outbox_supported(adev->dm.dc)) { init_completion(&adev->dm.dmub_aux_transfer_done); From 3001d2073d6542a9e51fa5bca3a39a078094d3c6 Mon Sep 17 00:00:00 2001 From: Fangzhi Zuo Date: Thu, 27 Aug 2026 13:12:46 -0400 Subject: [PATCH 1111/1198] drm/amd/display: Exit IPS before connector detection on resume [Why & How] On resume, dm_resume() walks the connector list and, for each connector, calls dc_link_detect_connection_type() at the top of the loop iteration before the per-connector dc_exit_ips_for_hw_access() that sits in the detection branch. There is no dc_exit_ips_for_hw_access() before the loop, so the very first HW access relies on an earlier connector having already taken the display out of IPS. Commit d1d51519bc3b ("drm/amd/display: Skip eDP detection when no sink") skips the eDP connector when no panel is present. On a DCN3.5 APU whose eDP link has no sink, the eDP iteration - which used to bring the HW out of IPS first - is now skipped, so a downstream DP connector becomes the first one processed. Its initial DDC/AUX access then runs while the HW is still idle, the AUX transfers time out (-ETIMEDOUT), and the EDID read fails: [drm:dm_helpers_read_local_edid [amdgpu]] *ERROR* EDID err: 2, on connector: DP-1 amdgpu: [drm] *ERROR* No EDID read. Take the display out of IPS once before the detection loop so the first connector processed no longer touches the AUX/DDC engine while the HW is still in idle power state. This keeps the eDP-skip boot/resume optimization while fixing the DP EDID read failure. Fixes: d1d51519bc3b ("drm/amd/display: Skip eDP detection when no sink") Reviewed-by: Roman Li Signed-off-by: Fangzhi Zuo Signed-off-by: Ray Wu Tested-by: Dan Wheeler Signed-off-by: Alex Deucher (cherry picked from commit 86420fe3093161971b4064e05be11ffff1df76aa) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index a95243656f54..08b8605029ab 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1972,6 +1972,10 @@ static int dm_resume(struct amdgpu_ip_block *ip_block) /* On resume we need to rewrite the MSTM control bits to enable MST*/ s3_handle_mst(ddev, false); + /* Exit IPS before the detection loop's first AUX/DDC access. */ + scoped_guard(mutex, &dm->dc_lock) + dc_exit_ips_for_hw_access(dm->dc); + /* Do detection*/ drm_connector_list_iter_begin(ddev, &iter); drm_for_each_connector_iter(connector, &iter) { From 5d7e0cc4afda0cb25c0829dc7c1bb4bedd7886a5 Mon Sep 17 00:00:00 2001 From: Fangzhi Zuo Date: Wed, 26 Aug 2026 17:47:41 -0400 Subject: [PATCH 1112/1198] drm/amd/display: Fix HF-VSDB DSC bpc detection to be cumulative [Why & How] The HDMI Forum VSDB reports the maximum DSC color depth a sink supports. This maximum is cumulative: a sink that reports 12 bpc also supports 10 and 8 bpc. The previous code used exact "== 10" and "== 12" comparisons chained with else-if, so a 12 bpc sink only set frl_dsc_12bpc and never set frl_dsc_10bpc, incorrectly narrowing the DSC bpc range usable with that sink. Use ">= 10" and a separate ">= 12" check so a sink advertising a higher maximum also enables the lower DSC bit depths it supports. Reviewed-by: Alex Hung Signed-off-by: Fangzhi Zuo Signed-off-by: Ray Wu Tested-by: Dan Wheeler Signed-off-by: Alex Deucher (cherry picked from commit 4523adbf4dca157aea96a6f28b4e7b7ebd4d5eda) --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c | 5 +++-- .../drm/amd/display/amdgpu_dm/tests/amdgpu_dm_helpers_test.c | 2 +- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index d451082552e8..249e0cd995c6 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -1202,9 +1202,10 @@ void populate_hdmi_info_from_connector(bool enable_frl, struct drm_hdmi_info *hd edid_caps->max_frl_rate = get_max_frl_rate(hdmi->max_lanes, hdmi->max_frl_rate_per_lane); edid_caps->frl_dsc_support = hdmi->dsc_cap.v_1p2; if (edid_caps->frl_dsc_support) { - if (hdmi->dsc_cap.bpc_supported == 10) + /* HF-VSDB DSC max bpc is cumulative: >=12 implies 10 and 8. */ + if (hdmi->dsc_cap.bpc_supported >= 10) edid_caps->frl_dsc_10bpc = true; - else if (hdmi->dsc_cap.bpc_supported == 12) + if (hdmi->dsc_cap.bpc_supported >= 12) edid_caps->frl_dsc_12bpc = true; edid_caps->frl_dsc_all_bpp = hdmi->dsc_cap.all_bpp; edid_caps->frl_dsc_native_420 = hdmi->dsc_cap.native_420; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_helpers_test.c b/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_helpers_test.c index 058e1ad15dfe..0c4517fb9d75 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_helpers_test.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_helpers_test.c @@ -909,7 +909,7 @@ static void dm_test_populate_hdmi_frl_dsc_12bpc(struct kunit *test) KUNIT_EXPECT_EQ(test, caps->max_frl_rate, 2); KUNIT_EXPECT_TRUE(test, caps->frl_dsc_support); - KUNIT_EXPECT_FALSE(test, caps->frl_dsc_10bpc); + KUNIT_EXPECT_TRUE(test, caps->frl_dsc_10bpc); KUNIT_EXPECT_TRUE(test, caps->frl_dsc_12bpc); KUNIT_EXPECT_EQ(test, caps->frl_dsc_max_slices, 7); KUNIT_EXPECT_EQ(test, caps->frl_dsc_max_frl_rate, 1); From 1f1d43418d61c8511779e0f63a954a78b9433b43 Mon Sep 17 00:00:00 2001 From: Prike Liang Date: Mon, 31 Aug 2026 10:51:04 +0800 Subject: [PATCH 1113/1198] drm/amdgpu: skip gfx switch_power_profile during GPU reset During resume from GPU reset, the gfx idle work may invoke switch_power_profile before the reset completes. This causes the following assert error because the register access occurs without first releasing the GPU reset semaphore: [ 1576.768935] CR2: 0000559ea133ead0 CR3: 00000002e6c42000 CR4: 0000000000350ef0 [ 1576.768940] Call Trace: [ 1576.768944] [ 1576.768953] amdgpu_device_rreg+0x21/0x50 [amdgpu] [ 1576.769158] smu_msg_v1_send_msg+0x1a4/0x6e0 [amdgpu] [ 1576.769437] smu_cmn_send_smc_msg_with_params_ext+0xba/0x120 [amdgpu] [ 1576.769721] smu_cmn_send_smc_msg_with_param+0x33/0x40 [amdgpu] [ 1576.769993] smu_v13_0_0_set_power_profile_mode+0x192/0x2b0 [amdgpu] [ 1576.770267] smu_bump_power_profile_mode+0x5d/0x80 [amdgpu] [ 1576.770538] smu_switch_power_profile+0xa4/0xf0 [amdgpu] [ 1576.770839] amdgpu_dpm_switch_power_profile+0x6f/0x90 [amdgpu] [ 1576.771210] amdgpu_gfx_profile_idle_work_handler+0xe9/0x130 [amdgpu] [ 1576.771460] process_one_work+0x23e/0x6f0 [ 1576.771491] worker_thread+0x1c4/0x380 [ 1576.771506] kthread+0x10c/0x150 [ 1576.771512] ? __pfx_worker_thread+0x10/0x10 [ 1576.771518] ? __pfx_kthread+0x10/0x10 [ 1576.771530] ret_from_fork+0x314/0x390 [ 1576.771537] ? __pfx_kthread+0x10/0x10 [ 1576.771546] ret_from_fork_asm+0x1a/0x30 Signed-off-by: Prike Liang Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher (cherry picked from commit d93b1ff538ce9750c01e0dd0aa62575579c0fc08) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/pm/amdgpu_dpm.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c index ce526db4d24a..808be6c425bf 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c @@ -348,7 +348,8 @@ int amdgpu_dpm_switch_power_profile(struct amdgpu_device *adev, const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; int ret = 0; - if (amdgpu_sriov_vf(adev)) + if (amdgpu_sriov_vf(adev) || + amdgpu_in_reset(adev)) return 0; if (pp_funcs && pp_funcs->switch_power_profile) { @@ -367,7 +368,8 @@ int amdgpu_dpm_pause_power_profile(struct amdgpu_device *adev, const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; int ret = 0; - if (amdgpu_sriov_vf(adev)) + if (amdgpu_sriov_vf(adev) || + amdgpu_in_reset(adev)) return 0; if (pp_funcs && pp_funcs->pause_power_profile) { From 829157e762ed043e28ecb2e9f3c7d22b54e5989e Mon Sep 17 00:00:00 2001 From: Thadeu Lima de Souza Cascardo Date: Tue, 8 Sep 2026 16:59:51 -0300 Subject: [PATCH 1114/1198] Revert "drm/amdgpu: debugfs: avoid extra EOLs in amdgpu_gem_info" This reverts commit c119d05a36a884482decc67e55944648f8cba97e. It removes the newline even when there are no fences attached to a struct dma_resv, leading to multiple BOs being output on the same line, making the debug file less readable, not more as the commit intended. Signed-off-by: Thadeu Lima de Souza Cascardo Signed-off-by: Alex Deucher (cherry picked from commit a2aafaeb2be13ed3c893e6a44a3a5d26b251ae6a) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 5d9d137209b6..1b6c32a177fb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -1701,9 +1701,8 @@ u64 amdgpu_bo_print_info(int id, struct amdgpu_bo *bo, struct seq_file *m) if (dma_resv_trylock(bo->tbo.base.resv)) { dma_resv_describe(bo->tbo.base.resv, m); dma_resv_unlock(bo->tbo.base.resv); - } else { - seq_puts(m, "\n"); } + seq_puts(m, "\n"); return size; } From bdcd0411d7d186225a52458fd42bb70d54ca917a Mon Sep 17 00:00:00 2001 From: Satyajit Roy Date: Sun, 30 Aug 2026 03:51:58 +0000 Subject: [PATCH 1115/1198] drm/amd/display: Propagate HDMI RGB quantization selectability DC uses dc_edid_caps.qs_bit when constructing the HDMI AVI InfoFrame quantization-range field. Although DRM parses the sink capability into drm_display_info, DM never copies it into the DC EDID capabilities. The field therefore remains zero and the AVI quantization range stays at its default value. Copy rgb_quant_range_selectable for HDMI sinks and extend the existing EDID-capability KUnit test to cover it. Fixes: 6eb4c13a3845 ("drm/amd/display: Support "Broadcast RGB" drm property") Signed-off-by: Satyajit Roy Reviewed-by: Alex Hung Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher (cherry picked from commit 892659399f64642e33072562a11ec1b2e7bd2263) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c | 1 + .../drm/amd/display/amdgpu_dm/tests/amdgpu_dm_helpers_test.c | 2 ++ 2 files changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index 249e0cd995c6..298de7b75ca8 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -200,6 +200,7 @@ enum dc_edid_status dm_helpers_parse_edid_caps( edid_caps->edid_hdmi = connector->display_info.is_hdmi; if (edid_caps->edid_hdmi) { + edid_caps->qs_bit = connector->display_info.rgb_quant_range_selectable; populate_hdmi_info_from_connector(link->dc->config.enable_frl, &connector->display_info.hdmi, edid_caps); drm_dbg_driver(connector->dev, "%s: HDMI_FRL [%s] max_frl_rate %d\n", __func__, connector->name, edid_caps->max_frl_rate); if (edid_caps->frl_dsc_support) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_helpers_test.c b/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_helpers_test.c index 0c4517fb9d75..82e0c984693c 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_helpers_test.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_helpers_test.c @@ -358,12 +358,14 @@ static void dm_test_parse_edid_caps_hdmi_frl(struct kunit *test) /* Drive the HDMI/FRL branch */ connector->display_info.is_hdmi = true; + connector->display_info.rgb_quant_range_selectable = true; connector->display_info.hdmi.scdc.supported = true; connector->display_info.hdmi.max_lanes = 4; connector->display_info.hdmi.max_frl_rate_per_lane = 12; KUNIT_EXPECT_EQ(test, dm_helpers_parse_edid_caps(link, dc_edid, edid_caps), EDID_OK); KUNIT_EXPECT_TRUE(test, edid_caps->edid_hdmi); + KUNIT_EXPECT_EQ(test, edid_caps->qs_bit, 1); KUNIT_EXPECT_TRUE(test, edid_caps->scdc_present); /* max_lanes 4 + max_frl_rate_per_lane 12 -> rate index 6 */ KUNIT_EXPECT_EQ(test, edid_caps->max_frl_rate, 6); From 7fca7acd60a228b62b4e9efa5f184738041e9564 Mon Sep 17 00:00:00 2001 From: Satyajit Roy Date: Sun, 30 Aug 2026 03:52:06 +0000 Subject: [PATCH 1116/1198] drm/amd/display: Honor Broadcast RGB for BT.2020 RGB output amdgpu_dm_get_output_color_space() applies the Broadcast RGB connector property to default RGB output, but always selects full-range output for BT.2020 RGB. Consequently, explicitly selecting Limited has no effect on the output CSC or AVI InfoFrame when HDR uses BT.2020 RGB. Select COLOR_SPACE_2020_RGB_LIMITEDRANGE when the output encoding is RGB and Broadcast RGB is Limited. Keep Automatic and Full at full range, and leave YCbCr output unchanged. Add KUnit coverage for limited-range RGB output through both BT.2020 connector colorspace values. Fixes: 6eb4c13a3845 ("drm/amd/display: Support "Broadcast RGB" drm property") Signed-off-by: Satyajit Roy Reviewed-by: Alex Hung Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher (cherry picked from commit 022236eaa63bbf65761aa8aec43f661451a94654) Cc: stable@vger.kernel.org --- .../display/amdgpu_dm/amdgpu_dm_connector.c | 10 +++-- .../tests/amdgpu_dm_connector_test.c | 37 +++++++++++++++++++ 2 files changed, 44 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_connector.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_connector.c index d03773887214..154e1f35dcb1 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_connector.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_connector.c @@ -756,10 +756,14 @@ amdgpu_dm_get_output_color_space(const struct dc_crtc_timing *dc_crtc_timing, break; case DRM_MODE_COLORIMETRY_BT2020_RGB: case DRM_MODE_COLORIMETRY_BT2020_YCC: - if (dc_crtc_timing->pixel_encoding == PIXEL_ENCODING_RGB) - color_space = COLOR_SPACE_2020_RGB_FULLRANGE; - else + if (dc_crtc_timing->pixel_encoding == PIXEL_ENCODING_RGB) { + if (connector_state->hdmi.broadcast_rgb == DRM_HDMI_BROADCAST_RGB_LIMITED) + color_space = COLOR_SPACE_2020_RGB_LIMITEDRANGE; + else + color_space = COLOR_SPACE_2020_RGB_FULLRANGE; + } else { color_space = COLOR_SPACE_2020_YCBCR_LIMITED; + } break; case DRM_MODE_COLORIMETRY_DEFAULT: /* ITU601 */ default: diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_connector_test.c b/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_connector_test.c index 0d2f9dbce0a9..212a7536e65b 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_connector_test.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_connector_test.c @@ -567,6 +567,23 @@ static void dm_test_output_color_space_bt2020_rgb(struct kunit *test) (int)COLOR_SPACE_2020_RGB_FULLRANGE); } +/** + * dm_test_output_color_space_bt2020_rgb_limited - Test limited BT.2020 RGB + * @test: The KUnit test context + */ +static void dm_test_output_color_space_bt2020_rgb_limited(struct kunit *test) +{ + struct dc_crtc_timing timing = {}; + struct drm_connector_state state = {}; + + timing.pixel_encoding = PIXEL_ENCODING_RGB; + state.colorspace = DRM_MODE_COLORIMETRY_BT2020_RGB; + state.hdmi.broadcast_rgb = DRM_HDMI_BROADCAST_RGB_LIMITED; + + KUNIT_EXPECT_EQ(test, (int)amdgpu_dm_get_output_color_space(&timing, &state), + (int)COLOR_SPACE_2020_RGB_LIMITEDRANGE); +} + /** * dm_test_output_color_space_bt2020_ycc - Test Output color space bt2020 ycc * @test: The KUnit test context @@ -638,6 +655,24 @@ static void dm_test_output_color_space_bt2020_ycc_rgb_encoding(struct kunit *tes (int)COLOR_SPACE_2020_RGB_FULLRANGE); } +/** + * dm_test_output_color_space_bt2020_ycc_rgb_encoding_limited - Test limited + * BT.2020 RGB output selected through the BT.2020 YCC connector colorspace + * @test: The KUnit test context + */ +static void dm_test_output_color_space_bt2020_ycc_rgb_encoding_limited(struct kunit *test) +{ + struct dc_crtc_timing timing = {}; + struct drm_connector_state state = {}; + + timing.pixel_encoding = PIXEL_ENCODING_RGB; + state.colorspace = DRM_MODE_COLORIMETRY_BT2020_YCC; + state.hdmi.broadcast_rgb = DRM_HDMI_BROADCAST_RGB_LIMITED; + + KUNIT_EXPECT_EQ(test, (int)amdgpu_dm_get_output_color_space(&timing, &state), + (int)COLOR_SPACE_2020_RGB_LIMITEDRANGE); +} + /** * dm_test_output_color_space_bt2020_rgb_ycc_encoding - Test Output color space * bt2020 rgb with non-rgb pixel encoding falls back to limited ycbcr @@ -5422,10 +5457,12 @@ static struct kunit_case amdgpu_dm_connector_tests[] = { KUNIT_CASE(dm_test_output_color_space_bt709_y_only), KUNIT_CASE(dm_test_output_color_space_oprgb), KUNIT_CASE(dm_test_output_color_space_bt2020_rgb), + KUNIT_CASE(dm_test_output_color_space_bt2020_rgb_limited), KUNIT_CASE(dm_test_output_color_space_bt2020_ycc), KUNIT_CASE(dm_test_output_color_space_default_ycbcr709_y_only), KUNIT_CASE(dm_test_output_color_space_default_ycbcr601), KUNIT_CASE(dm_test_output_color_space_bt2020_ycc_rgb_encoding), + KUNIT_CASE(dm_test_output_color_space_bt2020_ycc_rgb_encoding_limited), KUNIT_CASE(dm_test_output_color_space_bt2020_rgb_ycc_encoding), /* Tests for amdgpu_dm_convert_dc_color_depth_into_bpc */ KUNIT_CASE(dm_test_convert_color_depth_bpc_mappings), From 8cfd9e22eb5c04b15b82985ff913944f84673d4f Mon Sep 17 00:00:00 2001 From: Satyajit Roy Date: Sun, 30 Aug 2026 03:52:13 +0000 Subject: [PATCH 1117/1198] drm/amd/display: Rebuild InfoFrames on output color space changes resource_build_info_frame() derives colorimetry and RGB quantization from stream->output_color_space. A Broadcast RGB-only atomic commit updates that field and reprograms the output CSC, but none of the InfoFrame update predicates include output_color_space. The sink can therefore retain the previous AVI InfoFrame range while the source starts transmitting a different pixel range. Treat an output color space change as an InfoFrame change in update classification and in both stream programming paths. Hardware testing on an HDMI 2.1 television confirmed that its automatic black-level selection follows Full to Limited and Limited to Full transitions in SDR, HDR, and HDR with VRR active, without a modeset or visible link blank. Fixes: 6eb4c13a3845 ("drm/amd/display: Support "Broadcast RGB" drm property") Signed-off-by: Satyajit Roy Reviewed-by: Alex Hung Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher (cherry picked from commit d6faca79f5720893843e649e70aeb19147ee0578) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/display/dc/core/dc.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index a98ed4617a03..519ac878ada1 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -3198,6 +3198,7 @@ static struct dc_update_descriptor check_update_surfaces_for_stream( } if ((stream_update->hdr_static_metadata && !stream_update->stream->use_dynamic_meta) || + stream_update->output_color_space || stream_update->vrr_infopacket || stream_update->vsc_infopacket || stream_update->vsp_infopacket || @@ -4188,6 +4189,7 @@ static void commit_planes_do_stream_update_sequence(struct dc *dc, hwss_add_setup_periodic_interrupt(&seq_state, dc, pipe_ctx); if ((stream_update->hdr_static_metadata && !stream->use_dynamic_meta) || + stream_update->output_color_space || stream_update->vrr_infopacket || stream_update->vsc_infopacket || stream_update->vsp_infopacket || @@ -4370,6 +4372,7 @@ static void commit_planes_do_stream_update(struct dc *dc, dc->hwss.setup_periodic_interrupt(dc, pipe_ctx); if ((stream_update->hdr_static_metadata && !stream->use_dynamic_meta) || + stream_update->output_color_space || stream_update->vrr_infopacket || stream_update->vsc_infopacket || stream_update->vsp_infopacket || From 13ddcc7acb9adbed7627e952a61d1d62cd9546fc Mon Sep 17 00:00:00 2001 From: Kevin Wang Date: Wed, 26 Aug 2026 09:51:55 +0800 Subject: [PATCH 1118/1198] drm/amd/pm: fix gpu metrics energy accumulator for smu 13.0.0/13.0.7 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit GPU metrics v1.3 defines energy_accumulator as a 64‑bit field. The unsupported‑firmware code path assigns UINT_MAX, which is neither the full‑width invalid value for this field nor its default value. Fixes: 8de9edb35976 ("drm/amd/pm: remove invalid gpu_metrics.energy_accumulator on smu v13.0.x") Signed-off-by: Kevin Wang Reviewed-by: Kenneth Feng Signed-off-by: Alex Deucher (cherry picked from commit c2b948c4fe16eb13d98ff5d1371956cb2f55cdc6) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c | 2 -- drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c | 4 ++-- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 6e741ec4a71e..87b80b6f83b5 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -2095,8 +2095,6 @@ static ssize_t smu_v13_0_0_get_gpu_metrics(struct smu_context *smu, if ((mp1_ver == IP_VERSION(13, 0, 0) && smu->smc_fw_version <= 0x004e1e00) || (mp1_ver == IP_VERSION(13, 0, 10) && smu->smc_fw_version <= 0x00500800)) gpu_metrics->energy_accumulator = metrics->EnergyAccumulator; - else - gpu_metrics->energy_accumulator = UINT_MAX; if (metrics->AverageGfxActivity <= SMU_13_0_0_BUSY_THRESHOLD) gpu_metrics->average_gfxclk_frequency = metrics->AverageGfxclkFrequencyPostDs; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index b94ae43586df..5fe409a23772 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -2097,8 +2097,8 @@ static ssize_t smu_v13_0_7_get_gpu_metrics(struct smu_context *smu, metrics->Vcn1ActivityPercentage); gpu_metrics->average_socket_power = metrics->AverageSocketPower; - gpu_metrics->energy_accumulator = smu->smc_fw_version <= 0x00521400 ? - metrics->EnergyAccumulator : UINT_MAX; + if (smu->smc_fw_version <= 0x00521400) + gpu_metrics->energy_accumulator = metrics->EnergyAccumulator; if (metrics->AverageGfxActivity <= SMU_13_0_7_BUSY_THRESHOLD) gpu_metrics->average_gfxclk_frequency = metrics->AverageGfxclkFrequencyPostDs; From f3c6a8ae601abf2d8476d3f899283cc9a1001f7d Mon Sep 17 00:00:00 2001 From: Kevin Wang Date: Tue, 8 Sep 2026 18:15:41 +0800 Subject: [PATCH 1119/1198] drm/amd/pm: report energy accumulator for smu 13.0.0 add energy accumulator on pmfw 0x004e8600 and above version. Signed-off-by: Kevin Wang Reviewed-by: Kenneth Feng Signed-off-by: Alex Deucher (cherry picked from commit 3a804a5b15c22e4d7a3906ff09035e539785813e) --- drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 87b80b6f83b5..a29e76b03476 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -2092,8 +2092,10 @@ static ssize_t smu_v13_0_0_get_gpu_metrics(struct smu_context *smu, gpu_metrics->average_socket_power = metrics->AverageSocketPower; - if ((mp1_ver == IP_VERSION(13, 0, 0) && smu->smc_fw_version <= 0x004e1e00) || - (mp1_ver == IP_VERSION(13, 0, 10) && smu->smc_fw_version <= 0x00500800)) + if ((mp1_ver == IP_VERSION(13, 0, 0) && + (smu->smc_fw_version <= 0x004e1e00 || smu->smc_fw_version >= 0x004e8600)) || + (mp1_ver == IP_VERSION(13, 0, 10) && + smu->smc_fw_version <= 0x00500800)) gpu_metrics->energy_accumulator = metrics->EnergyAccumulator; if (metrics->AverageGfxActivity <= SMU_13_0_0_BUSY_THRESHOLD) From a19d4f9b8befdcfcd5a87bab91312fe64af3bbb8 Mon Sep 17 00:00:00 2001 From: Ethan Nelson-Moore Date: Sat, 6 Jun 2026 23:40:49 -0700 Subject: [PATCH 1120/1198] ata: pata_legacy: remove documentation for removed module parameters Commit 3c4d783f6922 ("ata: pata_legacy: remove VLB support") removed several module parameters from the pata_legacy driver, but neglected to remove their documentation. Remove it. Fixes: 3c4d783f6922 ("ata: pata_legacy: remove VLB support") Cc: stable@vger.kernel.org # 7.0+ Signed-off-by: Ethan Nelson-Moore Reviewed-by: Karl Mehltretter Reviewed-by: Damien Le Moal Reviewed-by: Randy Dunlap Link: https://lore.kernel.org/r/20260607064053.195166-1-enelsonmoore@gmail.com Signed-off-by: Niklas Cassel --- .../admin-guide/kernel-parameters.txt | 37 ------------------- 1 file changed, 37 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 68647ff4bdd2..33cd30996e47 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -4987,18 +4987,6 @@ Kernel parameters Set to non-zero if a chip is present that snoops speed changes. Disabled by default. - pata_legacy.ht6560a= [HW,LIBATA] - Format: - Set to 1, 2, or 3 for HT 6560A on the primary channel, - the secondary channel, or both channels respectively. - Disabled by default. - - pata_legacy.ht6560b= [HW,LIBATA] - Format: - Set to 1, 2, or 3 for HT 6560B on the primary channel, - the secondary channel, or both channels respectively. - Disabled by default. - pata_legacy.iordy_mask= [HW,LIBATA] Format: IORDY enable mask. Set individual bits to allow IORDY @@ -5011,18 +4999,6 @@ Kernel parameters with the sequence. By default IORDY is allowed across all channels. - pata_legacy.opti82c46x= [HW,LIBATA] - Format: - Set to 1, 2, or 3 for Opti 82c611A on the primary - channel, the secondary channel, or both channels - respectively. Disabled by default. - - pata_legacy.opti82c611a= [HW,LIBATA] - Format: - Set to 1, 2, or 3 for Opti 82c465MV on the primary - channel, the secondary channel, or both channels - respectively. Disabled by default. - pata_legacy.pio_mask= [HW,LIBATA] Format: PIO mode mask for autospeed devices. Set individual @@ -5046,19 +5022,6 @@ Kernel parameters the first port in the list above (0x1f0), and so on. By default all supported ports are probed. - pata_legacy.qdi= [HW,LIBATA] - Format: - Set to non-zero to probe QDI controllers. By default - set to 1 if CONFIG_PATA_QDI_MODULE, 0 otherwise. - - pata_legacy.winbond= [HW,LIBATA] - Format: - Set to non-zero to probe Winbond controllers. Use - the standard I/O port (0x130) if 1, otherwise the - value given is the I/O port to use (typically 0x1b0). - By default set to 1 if CONFIG_PATA_WINBOND_VLB_MODULE, - 0 otherwise. - pata_platform.pio_mask= [HW,LIBATA] Format: Supported PIO mode mask. Set individual bits to allow From 3fb13d29cf8eb4502837bff06b2873c5435f6ffd Mon Sep 17 00:00:00 2001 From: Yang Zi <2959243019@qq.com> Date: Tue, 25 Aug 2026 16:58:15 +0800 Subject: [PATCH 1121/1198] fbdev: ssd1307fb: fix NULL pointer dereference on missing match data device_get_match_data() can return NULL, e.g. when the device is matched through the I2C device ID table rather than the OF match table. The returned value is stored in par->device_info and later dereferenced when initializing par->vcomh, causing a NULL pointer dereference. Check the return value right after the assignment and bail out with -ENODEV (releasing the already allocated framebuffer) before any dereference. Signed-off-by: Yang Zi <2959243019@qq.com> Signed-off-by: Helge Deller --- drivers/video/fbdev/ssd1307fb.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/video/fbdev/ssd1307fb.c b/drivers/video/fbdev/ssd1307fb.c index c4fdecafd856..4d185c754284 100644 --- a/drivers/video/fbdev/ssd1307fb.c +++ b/drivers/video/fbdev/ssd1307fb.c @@ -665,6 +665,10 @@ static int ssd1307fb_probe(struct i2c_client *client) spin_lock_init(&par->damage_lock); par->device_info = device_get_match_data(dev); + if (!par->device_info) { + ret = -ENODEV; + goto fb_alloc_error; + } par->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW); if (IS_ERR(par->reset)) { From 3934185ba63feca6e80cc8b90f7d7f01cde78223 Mon Sep 17 00:00:00 2001 From: Linmao Li Date: Thu, 27 Aug 2026 17:39:48 +0800 Subject: [PATCH 1122/1198] fbdev: atafb: Restrict SuperBlitter to supported formats MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The SuperBlitter operations derive an integer byte count per pixel. The accelerated fill path handles only one-, two- and four-byte pixels. However, the operations are currently installed for every external framebuffer in SuperVidel RAM, including planar 1/2/4/8-bpp and 24-bpp truecolor modes accepted by the external video parser. For 1/2/4-bpp modes, the byte count becomes zero, so accelerated copies do nothing and fills fall through to 32-bit stores. Planar 8-bpp uses an incompatible memory layout. For 24-bpp modes, fills also use 32-bit stores despite advancing addresses by three bytes per pixel. These cases can corrupt the framebuffer beyond the requested rectangle. Enable the SuperBlitter operations only for the layouts they implement: 8-bpp packed pixels and 16/32-bpp truecolor. Keep the existing software operations for all other external formats. Fixes: d463633d63e6 ("fbdev: atafb: Add support for SuperVidel's SuperBlitter") Signed-off-by: Linmao Li Tested-by: Miro Kropáček Reviewed-by: Michael Schmitz Signed-off-by: Helge Deller --- drivers/video/fbdev/atafb.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/video/fbdev/atafb.c b/drivers/video/fbdev/atafb.c index 5bca34c45cef..c3011b61a94b 100644 --- a/drivers/video/fbdev/atafb.c +++ b/drivers/video/fbdev/atafb.c @@ -3360,7 +3360,11 @@ static int __init atafb_probe(struct platform_device *pdev) memset (screen_base, 0, external_len); /* framebuffer in SV RAM: enable the SuperBlitter */ - if (external_addr >= 0xa0000000) { + if (external_addr >= 0xa0000000 && + ((external_pmode == FB_TYPE_PACKED_PIXELS && + external_depth == 8) || + (external_pmode == -1 && + (external_depth == 16 || external_depth == 32)))) { svblit_regs = ioremap(SVBLIT_REGS_PHYS, 0x100); if (svblit_regs) { svblit_fw = svblit_rd(SVBLIT_VERSION) & 0x1ff; From c4fa55f85c47cd5d54d717fb8170746edb10292e Mon Sep 17 00:00:00 2001 From: Mahmoud Nagy Adam Date: Wed, 9 Sep 2026 15:26:03 +0200 Subject: [PATCH 1123/1198] selftests: ublk: install test_common.sh and trace/ scripts Every ublk test script sources test_common.sh from its own directory: . "$(cd "$(dirname "$0")" && pwd)"/test_common.sh and test_generic_02/12 additionally run bpftrace against the scripts in trace/. Neither test_common.sh nor trace/ is listed in TEST_FILES, so "make install" does not copy them into the install directory and every ublk test fails when run from there: ./test_generic_02.sh: line 4: .../kselftest_install/ublk/test_common.sh: No such file or directory ./test_generic_02.sh: line 8: _have_program: command not found The bpftrace tests are affected even when bpftrace is installed: the missing trace/*.bt makes bpftrace exit immediately, and the tests then report a skip rather than a failure, which hides the problem. Add both to TEST_FILES, matching how other selftests ship their sourced helpers (see kexec/kexec_common_lib.sh and zram/zram_lib.sh). Fixes: 6aecda00b7d1e1 ("selftests: ublk: add kernel selftests for ublk") Fixes: 723977cab4c0fd ("selftests: ublk: add generic_01 for verifying sequential IO order") Cc: stable@vger.kernel.org # v6.15+ Assisted-by: Kiro:claude-opus-5 Signed-off-by: Mahmoud Nagy Adam Reviewed-by: Ming Lei Link: https://patch.msgid.link/20260909132602.68852-2-mngyadam@amazon.de Signed-off-by: Jens Axboe --- tools/testing/selftests/ublk/Makefile | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/selftests/ublk/Makefile b/tools/testing/selftests/ublk/Makefile index 5daf36c6c36c..37883e9d50ec 100644 --- a/tools/testing/selftests/ublk/Makefile +++ b/tools/testing/selftests/ublk/Makefile @@ -73,6 +73,8 @@ TEST_PROGS += test_stress_08.sh TEST_PROGS += test_stress_09.sh TEST_FILES := settings +TEST_FILES += test_common.sh +TEST_FILES += trace TEST_GEN_PROGS_EXTENDED = kublk metadata_size STANDALONE_UTILS := metadata_size.c From b0d8d56b7c93ed767eb4f2be9988e7b9dc023566 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 9 Sep 2026 09:06:31 +0100 Subject: [PATCH 1124/1198] block: Fix start and length check added to iov_iter_extract_bvecs() Commit 14b007e17881 added an address check using iter_iov_addr() and a length check using iter_iov_len() to iov_iter_extract_bvecs(), but these cannot be used so and are unsafe in this circumstance as the functions have hardwired assumptions about the iterator type. They should only be used with ITER_UBUF or ITER_IOVEC-type iterators; they shouldn't be used with ITER_BVEC, ITER_KVEC, ITER_FOLIOQ, ITER_XARRAY or ITER_DISCARD iterators. This proves to be a problem for cachefiles as an iterator of type ITER_FOLIOQ is passed and iter_iov_addr() and iter_iov_len() both malfunction because iter->__iov in iter_iov() is not pointing to an iovec array. Fix this by using iov_iter_alignment() instead. Fixes: 14b007e17881 ("block: validate user space vectors during extraction") Signed-off-by: David Howells Reviewed-by: Keith Busch cc: Hannes Reinecke cc: Christoph Hellwig cc: Jens Axboe cc: Alexander Viro cc: Paulo Alcantara cc: netfs@lists.linux.dev cc: linux-block@vger.kernel.org cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Link: https://patch.msgid.link/1667275.1788941191@warthog.procyon.org.uk Signed-off-by: Jens Axboe --- lib/iov_iter.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 6665372ecf71..2072c04e99d0 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1921,15 +1921,29 @@ ssize_t iov_iter_extract_bvecs(struct iov_iter *iter, struct bio_vec *bv, unsigned short max_vecs, unsigned mem_align_mask, iov_iter_extraction_t extraction_flags) { - unsigned long start = (unsigned long)iter_iov_addr(iter); unsigned short entries_left = max_vecs - *nr_vecs; unsigned short nr_pages, i = 0; size_t left, offset, len; struct page **pages; ssize_t size; - if ((start | iter_iov_len(iter)) & mem_align_mask) + /* + * DMA engines typically have both memory address and length alignment + * requirements, so check these against the alignment mask. For UBUF, + * IOVEC and KVEC, only the current segment will be extracted from; for + * everything else we might extract from multiple segments, so we need + * to check those too. + */ + if (likely(iter_is_ubuf(iter) || + iter_is_iovec(iter) || + iov_iter_is_kvec(iter))) { + unsigned long start = (unsigned long)iter_iov_addr(iter); + + if ((start | iter_iov_len(iter)) & mem_align_mask) + return -EINVAL; + } else if (iov_iter_alignment(iter) & mem_align_mask) { return -EINVAL; + } /* * Move page array up in the allocated memory for the bio vecs as far as From 0c6da21fa35e03fc74f09895433ccd6d4a9c3530 Mon Sep 17 00:00:00 2001 From: Stian Halseth Date: Tue, 1 Sep 2026 19:39:45 +0200 Subject: [PATCH 1125/1198] sunvdc: unmap LDC cookies when the descriptor send fails __send_request() maps the request's pages into the LDC channel's map table (ldc_map_sg()), fills in the descriptor and marks it VIO_DESC_READY before ringing the doorbell via __vdc_tx_trigger(). When the trigger fails, the error path only prints a message: the descriptor stays READY and the cookies are never unmapped. The mapping is normally released in vdc_end_one() when the peer completes the descriptor - but a descriptor whose doorbell was never sent will never complete, and since dr->prod is not advanced on failure, the reset path (vdc_requeue_inflight(), which walks [cons, prod)) never visits it either. The map table entries are leaked permanently. Since commit a11f6ca9aef9 ("sunvdc: Do not spin in an infinite loop when vio_ldc_send() returns EAGAIN") trigger failures occur in practice under load, so every resulting I/O error also leaks one request's worth of entries from the fixed-size (8192 entries per channel) map table. Because the allocator hands out contiguous ranges, fragmentation makes large multi-segment requests fail first as the table drains, until ldc_map_sg() fails permanently and the disk is dead until reboot. It also makes any retry-based recovery unusable: requeuing the request on -EAGAIN remaps the pages on every attempt, overwriting desc->cookies and orphaning the previous mapping, so the table drains at the retry rate. This is the memory exhaustion observed when the requeue approach was first tested in October 2025. Roll back on failure: unmap the cookies, mark the descriptor FREE again and clear the request entry. If the trigger failed with -ENOTCONN, __vdc_tx_trigger() has already reset the port, which tears down and reallocates both the dring and the LDC channel including its map table - nothing to roll back, and the stale descriptor must not be touched. Fixes: a11f6ca9aef9 ("sunvdc: Do not spin in an infinite loop when vio_ldc_send() returns EAGAIN") Reported-by: John Paul Adrian Glaubitz Link: https://github.com/sparclinux/issues/issues/2 Signed-off-by: Stian Halseth Link: https://patch.msgid.link/20260901173947.3292110-2-stian@itx.no Signed-off-by: Jens Axboe --- drivers/block/sunvdc.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c index 020bd9f1a7b6..24ad56536ed6 100644 --- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -525,6 +525,23 @@ static int __send_request(struct request *req) err = __vdc_tx_trigger(port); if (err < 0) { printk(KERN_ERR PFX "vdc_tx_trigger() failure, err=%d\n", err); + /* + * If the port was reset (-ENOTCONN), the dring and the + * LDC channel including all of its mappings are already + * torn down and reallocated - there is nothing to undo + * and @desc must not be touched. + * + * For any other failure the descriptor was never handed + * to the peer: unmap the cookies and free the descriptor + * again, so that a later retry of the request does not + * leak LDC map table entries. + */ + if (err != -ENOTCONN) { + ldc_unmap(port->vio.lp, desc->cookies, + desc->ncookies); + desc->hdr.state = VIO_DESC_FREE; + rqe->req = NULL; + } } else { port->req_id++; dr->prod = vio_dring_next(dr, dr->prod); From 5067d4ba713961d8ccea1e06cd4c453793f3121e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 1 Sep 2026 19:39:46 +0200 Subject: [PATCH 1126/1198] sunvdc: fix -EIO issue due to lack of retries John reports that since commit: a11f6ca9aef9 ("sunvdc: Do not spin in an infinite loop when vio_ldc_send() returns EAGAIN") users of Linux inside Solaris ldom see occasional -EIO errors because the request send loop now times out. The current loop does 10 retries, and inside vio_ldc_send() a further 1000 1usec retries are done as well. Even with 10.5 msec of busy loop retries that's apparently not enough to always succeed. Rather than introduce continued busy looping, requeue the request and have the delayed queue kicking retry the request after another 10ms. This obviously isn't ideal, but there's seemingly no way to wait for this type of event. And if 10ms of busy looping was not enough to make progress, then presumably this is an edge condition and we just need to guarantee to make forward progress at some later point in time. That's more suitably done through letting the CPU tend to other work, rather than sitting in a tight loop retrying. [stian: rebased on top of the cookie-unmap fix, without which every requeued attempt leaks LDC map table entries; tested on an UltraSPARC T4 LDOM where the vdc_tx_trigger failure condition was reproduced and absorbed by the requeue with no I/O error] Reported-by: John Paul Adrian Glaubitz Link: https://lore.kernel.org/all/20251006100226.4246-2-glaubitz@physik.fu-berlin.de/ Link: https://lore.kernel.org/all/418310b3-2b77-4534-b2fd-27dcc11e333c@kernel.dk/ Signed-off-by: Stian Halseth Link: https://patch.msgid.link/20260901173947.3292110-3-stian@itx.no Signed-off-by: Jens Axboe --- drivers/block/sunvdc.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c index 24ad56536ed6..2be8231dcd5b 100644 --- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -556,6 +556,7 @@ static blk_status_t vdc_queue_rq(struct blk_mq_hw_ctx *hctx, struct vdc_port *port = hctx->queue->queuedata; struct vio_dring_state *dr; unsigned long flags; + int ret; dr = &port->vio.drings[VIO_DRIVER_TX_RING]; @@ -577,7 +578,13 @@ static blk_status_t vdc_queue_rq(struct blk_mq_hw_ctx *hctx, return BLK_STS_DEV_RESOURCE; } - if (__send_request(bd->rq) < 0) { + ret = __send_request(bd->rq); + if (ret == -EAGAIN) { + spin_unlock_irqrestore(&port->vio.lock, flags); + /* already spun for 10msec, defer 10msec and retry */ + blk_mq_delay_kick_requeue_list(hctx->queue, 10); + return BLK_STS_DEV_RESOURCE; + } else if (ret < 0) { spin_unlock_irqrestore(&port->vio.lock, flags); return BLK_STS_IOERR; } From a0a34a40ed299c9c7cff6af163a5b883ee9d6d73 Mon Sep 17 00:00:00 2001 From: Weiming Shi Date: Thu, 10 Sep 2026 03:10:23 +0800 Subject: [PATCH 1127/1198] fbdev: vfb: defer cleanup until the last reference FBIOGETCMAP takes a shallow snapshot of info->cmap and performs the usercopy after dropping info->lock. vfb_remove() frees the colormap immediately after unregistering the framebuffer, even when an open file still holds a reference to fb_info. A concurrent driver unbind can therefore free the colormap while the ioctl copies it to userspace. KASAN reports: BUG: KASAN: slab-use-after-free in _copy_to_user Read of size 512 by task poc/125 _copy_to_user (./include/linux/instrumented.h:129 ./include/linux/uaccess.h:201 lib/usercopy.c:24) fb_cmap_to_user (./include/linux/uaccess.h:230 drivers/video/fbdev/core/fbcmap.c:211) do_fb_ioctl (drivers/video/fbdev/core/fb_chrdev.c:114) Allocated by task 1: fb_alloc_cmap_gfp (./include/linux/slab.h:973 ./include/linux/slab.h:1290 drivers/video/fbdev/core/fbcmap.c:108) vfb_probe (drivers/video/fbdev/vfb.c:459) Freed by task 124: fb_dealloc_cmap (drivers/video/fbdev/core/fbcmap.c:151) vfb_remove (drivers/video/fbdev/vfb.c:489) unregister_framebuffer() drops the registration reference, and fbdev calls fb_destroy after the last put_fb_info(). Move the registered framebuffer's cleanup into an fb_destroy callback so its colormap and screen buffer stay alive until all file references have been released. Fixes: 5e266e2e0e19 ("vfb: fix memory leaks in removal path") Reported-by: co+c25629c98ba36ebe@bugs.sh Cc: stable@kernel.org Closes: https://lore.kernel.org/linux-fbdev/f2Kf9GYn1lKR5S1dbvGVtykMxK1RlgP5z8sW@bugs.sh/ Assisted-by: Codex:gpt-5 Signed-off-by: Weiming Shi Link: https://lore.kernel.org/linux-fbdev/f2Kf9GYn1lKR5S1dbvGVtykMxK1RlgP5z8sW@bugs.sh/ Signed-off-by: Helge Deller --- drivers/video/fbdev/vfb.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/video/fbdev/vfb.c b/drivers/video/fbdev/vfb.c index 5b7965f36c5e..de137b2bdaed 100644 --- a/drivers/video/fbdev/vfb.c +++ b/drivers/video/fbdev/vfb.c @@ -78,6 +78,13 @@ static int vfb_pan_display(struct fb_var_screeninfo *var, static int vfb_mmap(struct fb_info *info, struct vm_area_struct *vma); +static void vfb_destroy(struct fb_info *info) +{ + vfree(info->screen_buffer); + fb_dealloc_cmap(&info->cmap); + framebuffer_release(info); +} + static const struct fb_ops vfb_ops = { .owner = THIS_MODULE, __FB_DEFAULT_SYSMEM_OPS_RDWR, @@ -87,6 +94,7 @@ static const struct fb_ops vfb_ops = { .fb_pan_display = vfb_pan_display, __FB_DEFAULT_SYSMEM_OPS_DRAW, .fb_mmap = vfb_mmap, + .fb_destroy = vfb_destroy, }; /* @@ -485,9 +493,6 @@ static void vfb_remove(struct platform_device *dev) if (info) { unregister_framebuffer(info); - vfree(videomemory); - fb_dealloc_cmap(&info->cmap); - framebuffer_release(info); } } From 8a14be55bdc6d5a25cd7b0ac5d4d884fcc727b49 Mon Sep 17 00:00:00 2001 From: Yang Xiuwei Date: Fri, 21 Aug 2026 18:30:46 +0800 Subject: [PATCH 1128/1198] ublk: clear force_abort in ublk_queue_reset_io_flags() Quiesce sets ubq->force_abort for batch I/O. Recovery never clears it, so batch fetch keeps failing with -ENODEV and the device stays QUIESCED. Fixes: a4d883755399 ("ublk: add UBLK_U_IO_FETCH_IO_CMDS for batch I/O processing") Signed-off-by: Yang Xiuwei Reviewed-by: Ming Lei Link: https://patch.msgid.link/20260821103047.369522-2-yangxiuwei@kylinos.cn Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index e5ba07d8d281..44d10cb36bf1 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -3030,6 +3030,7 @@ static void ublk_queue_reset_io_flags(struct ublk_queue *ubq) ubq->canceling = false; spin_unlock(&ubq->cancel_lock); ubq->fail_io = false; + ubq->force_abort = false; } /* device can only be started after all IOs are ready */ From 94b1a3ca9b8db3151f1416263704c159a9470da5 Mon Sep 17 00:00:00 2001 From: Yang Xiuwei Date: Fri, 21 Aug 2026 18:30:47 +0800 Subject: [PATCH 1129/1198] selftests: ublk: add batch IO cases to recover_03 Add -b coverage for quiesce recover. Signed-off-by: Yang Xiuwei Reviewed-by: Ming Lei Link: https://patch.msgid.link/20260821103047.369522-3-yangxiuwei@kylinos.cn Signed-off-by: Jens Axboe --- tools/testing/selftests/ublk/test_recover_03.sh | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/tools/testing/selftests/ublk/test_recover_03.sh b/tools/testing/selftests/ublk/test_recover_03.sh index 2554805e5b02..92f4012178f0 100755 --- a/tools/testing/selftests/ublk/test_recover_03.sh +++ b/tools/testing/selftests/ublk/test_recover_03.sh @@ -29,6 +29,11 @@ _create_backfile 0 256M _create_backfile 1 128M _create_backfile 2 128M +ublk_run_quiesce_recover -t null -q 2 -r 1 -b & +ublk_run_quiesce_recover -t loop -q 2 -r 1 -b "${UBLK_BACKFILES[0]}" & +ublk_run_quiesce_recover -t stripe -q 2 -r 1 -b "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & +wait + ublk_run_quiesce_recover -t null -q 2 -r 1 & ublk_run_quiesce_recover -t loop -q 2 -r 1 "${UBLK_BACKFILES[0]}" & ublk_run_quiesce_recover -t stripe -q 2 -r 1 "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & From 135d84c66f85426299db01a09d93a79a87af18ba Mon Sep 17 00:00:00 2001 From: Binglei Wang Date: Fri, 11 Sep 2026 12:11:33 +0800 Subject: [PATCH 1130/1198] erofs: add missing buf->off in erofs_bread() erofs_bread() locates the target folio with index = (buf->off + offset) >> PAGE_SHIFT; but computes the in-folio offset without taking buf->off into account: return buf->base + (offset & ~PAGE_MASK); If buf->off is not page-aligned, the returned pointer misses the in-page component of buf->off, so callers end up fetching data from a wrong offset. buf->off is set to sbi->dif0.fsoff in erofs_init_metabuf(), and fsoff can be specified via the "fsoffset=" mount option, which only requires block-size alignment. Therefore, on an image with a sub-page block size (e.g. 512 bytes), a non-page-aligned fsoff (e.g. 512) triggers the issue, since 512 is a multiple of the block size but not of PAGE_SIZE. It can be reproduced by mounting an image that is placed at a non-page-aligned offset: mkfs.erofs -b512 -zlz4hc sub.erofs src/ # prepend 512 bytes of padding to the image mount -t erofs -o loop,fsoffset=512 padded.erofs /mnt which fails with erofs (device loop0): cannot find valid erofs superblock because the on-disk superblock (at offset 1024 within the image, i.e. 1536 within the padded file) is read from a wrong in-folio offset. With this fixed, the very same image mounts successfully and its file contents match those read from the unpadded image. Fix it by including buf->off in the in-folio offset calculation, so that it is consistent with the folio index calculation. Fixes: c36ec00d7f67 ("erofs: add 'fsoffset' mount option to specify filesystem offset") Signed-off-by: Binglei Wang Reviewed-by: Gao Xiang Signed-off-by: Gao Xiang --- fs/erofs/data.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/erofs/data.c b/fs/erofs/data.c index 0885b1f2fc92..be63b89f0862 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -48,7 +48,7 @@ void *erofs_bread(struct erofs_buf *buf, erofs_off_t offset, bool need_kmap) return NULL; if (!buf->base) buf->base = kmap_local_page(buf->page); - return buf->base + (offset & ~PAGE_MASK); + return buf->base + ((buf->off + offset) & ~PAGE_MASK); } int erofs_init_metabuf(struct erofs_buf *buf, struct super_block *sb, From 4d3c07591534517c633945c8d8e6526f10e3fabc Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Thu, 10 Sep 2026 21:42:28 -0700 Subject: [PATCH 1131/1198] xfs: fix under-reservation of blocks when repairing sf directories Whilst running QA on XFS for-next as of 7.3-rc2 with MKFS_OPTIONS="-n size=8192", I observed the following (trimmed) dmesg splat: XFS: Assertion failed: args->total >= dp->i_nblocks - nblks, file: fs/xfs/libxfs/xfs_da_btree.c, line: 2387 WARNING: fs/xfs/xfs_message.c:104 at assfail+0x46/0x4a [xfs], CPU#0: xfs_scrub/1426511 CPU: 0 UID: 0 PID: 1426511 Comm: xfs_scrub Tainted: G W 7.3.0-rc2-djwx #rc2 PREEMPT(lazy) 6e418570b606a39783b0e7e7b30dc407b965f9e8 Tainted: [W]=WARN RIP: 0010:assfail+0x46/0x4a [xfs] RSP: 0018:ffffc900010d7890 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 00000000ffffffd1 RDX: 0000000000000000 RSI: 0000000000000021 RDI: ffffffffa059fd38 RBP: 0000000000000002 R08: 0000000000000000 R09: 0000000000000000 R10: 000000000000000a R11: 000000007fffffff R12: ffffc900010d7940 R13: ffff888368d8f980 R14: ffffc900010d7a48 R15: ffffc900010d78d0 FS: 00007f445c5ce680(0000) GS:ffff8884a97ea000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f443803b9a8 CR3: 0000000107a4b000 CR4: 00000000003506f0 Call Trace: xfs_da_grow_inode_int+0x2e0/0x300 [xfs 5de2257e14108c136f11317e6bbb8ac77efd392c] xfs_dir2_grow_inode+0x6e/0x150 [xfs 5de2257e14108c136f11317e6bbb8ac77efd392c] xfs_dir2_sf_to_block+0x149/0x870 [xfs 5de2257e14108c136f11317e6bbb8ac77efd392c] xrep_dir_swap_prep+0xe2/0x110 [xfs 5de2257e14108c136f11317e6bbb8ac77efd392c] xrep_dir_swap+0xfb/0x2f0 [xfs 5de2257e14108c136f11317e6bbb8ac77efd392c] xrep_dir_rebuild_tree+0x99/0x100 [xfs 5de2257e14108c136f11317e6bbb8ac77efd392c] xrep_directory+0x83/0x1c0 [xfs 5de2257e14108c136f11317e6bbb8ac77efd392c] xrep_attempt+0x4f/0x1e0 [xfs 5de2257e14108c136f11317e6bbb8ac77efd392c] xfs_scrub_metadata+0x393/0x5b0 [xfs 5de2257e14108c136f11317e6bbb8ac77efd392c] xfs_ioc_scrubv_metadata+0x306/0x570 [xfs 5de2257e14108c136f11317e6bbb8ac77efd392c] xfs_file_ioctl+0xa4f/0x1150 [xfs 5de2257e14108c136f11317e6bbb8ac77efd392c] __x64_sys_ioctl+0x76/0xc0 do_syscall_64+0x7a/0x3b0 entry_SYSCALL_64_after_hwframe+0x4b/0x53 This is a consequence of commit 0fe77e57588b98, which added the following assertion to xfs_da_grow_inode_int: ASSERT(args->total >= dp->i_nblocks - nblks); Tracing this back to xrep_dir_swap_prep, I noticed that the xfs_da_args object that's passed to xfs_dir2_sf_to_block sets args->total to 1. This is incorrect because mkfs set the directory block size to 8k and the filesystem block size to 4k. In other words, args->total should be 2 here, not 1. Dave Chinner tripped over the same problem with the same branch through a different channel -- his test setup set the fs block size to 1k, in which case the directory block size is still set to 4k. Here, args->total should be 4. Changing the assignment of args->total to sc->mp->m_dir_geo->fsbcount makes the assertion go away, but that isn't a complete fix. In xrep_tempexch_estimate, we also incorrectly assume that a shortform conversion requires 1 fsblock when it should be m_dir_geo->fsbcount. Without that, we can under-reserve space in the transaction and cause a filesystem shutdown. Note that the xfs_dabuf_nfsb helper will compute the correct value for directories and xattr, so we use that instead of open-coding the logic. Also fix xrep_xattr_swap_prep to assign args->total via xfs_dabuf_nfsb to avoid one logic bomb if we ever support multi-fsblock attrs. Cc: stable@vger.kernel.org # v6.10 Cc: floss@jetm.me Reported-by: dgc@kernel.org Fixes: 629fdaf5f5b1b7 ("xfs: use atomic extent swapping to fix user file fork data") Tripped-by: 0fe77e57588b98 ("xfs: assert the reservation covers each da fork growth") Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Reviewed-by: Carlos Maiolino Signed-off-by: Carlos Maiolino --- fs/xfs/libxfs/xfs_da_btree.c | 2 +- fs/xfs/libxfs/xfs_da_btree.h | 2 ++ fs/xfs/scrub/attr_repair.c | 2 +- fs/xfs/scrub/dir_repair.c | 2 +- fs/xfs/scrub/tempfile.c | 29 ++++++++++++++++++++++------- 5 files changed, 27 insertions(+), 10 deletions(-) diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c index 8cbdd6574755..3d02a0d7ba44 100644 --- a/fs/xfs/libxfs/xfs_da_btree.c +++ b/fs/xfs/libxfs/xfs_da_btree.c @@ -130,7 +130,7 @@ xfs_da_state_reset( state->mp = state->args->dp->i_mount; } -static inline int xfs_dabuf_nfsb(struct xfs_mount *mp, int whichfork) +inline int xfs_dabuf_nfsb(struct xfs_mount *mp, int whichfork) { if (whichfork == XFS_DATA_FORK) return mp->m_dir_geo->fsbcount; diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h index afcf2d3c7a21..a718b1ceb0aa 100644 --- a/fs/xfs/libxfs/xfs_da_btree.h +++ b/fs/xfs/libxfs/xfs_da_btree.h @@ -244,4 +244,6 @@ xfs_failaddr_t xfs_da3_node_header_check(struct xfs_buf *bp, xfs_ino_t owner); extern struct kmem_cache *xfs_da_state_cache; +int xfs_dabuf_nfsb(struct xfs_mount *mp, int whichfork); + #endif /* __XFS_DA_BTREE_H__ */ diff --git a/fs/xfs/scrub/attr_repair.c b/fs/xfs/scrub/attr_repair.c index 6e6af142f1fb..28f92e9ba72b 100644 --- a/fs/xfs/scrub/attr_repair.c +++ b/fs/xfs/scrub/attr_repair.c @@ -1294,7 +1294,7 @@ xrep_xattr_swap_prep( .geo = sc->mp->m_attr_geo, .whichfork = XFS_ATTR_FORK, .trans = sc->tp, - .total = 1, + .total = xfs_dabuf_nfsb(sc->mp, XFS_ATTR_FORK), .owner = I_INO(sc->ip), }; diff --git a/fs/xfs/scrub/dir_repair.c b/fs/xfs/scrub/dir_repair.c index 31a23c5f386a..d9d6b7e2abda 100644 --- a/fs/xfs/scrub/dir_repair.c +++ b/fs/xfs/scrub/dir_repair.c @@ -1488,7 +1488,7 @@ xrep_dir_swap_prep( .geo = sc->mp->m_dir_geo, .whichfork = XFS_DATA_FORK, .trans = sc->tp, - .total = 1, + .total = xfs_dabuf_nfsb(sc->mp, XFS_DATA_FORK), .owner = I_INO(sc->ip), }; diff --git a/fs/xfs/scrub/tempfile.c b/fs/xfs/scrub/tempfile.c index 98820003b929..59a9213a3c7d 100644 --- a/fs/xfs/scrub/tempfile.c +++ b/fs/xfs/scrub/tempfile.c @@ -649,6 +649,19 @@ xrep_tempexch_prep_request( return 0; } +static inline unsigned int +xrep_tempexch_estimate_sf_resblks( + struct xfs_scrub *sc, + int whichfork) +{ + /* repairing a symlink target */ + if (S_ISLNK(VFS_I(sc->ip)->i_mode) && whichfork == XFS_DATA_FORK) + return 1; + + /* everything else is a directory or an xattr structure */ + return xfs_dabuf_nfsb(sc->mp, whichfork); +} + /* * Fill out the mapping exchange resource estimation structures in preparation * for exchanging the contents of a metadata file that we've rebuilt in the @@ -663,6 +676,8 @@ xrep_tempexch_estimate( struct xfs_ifork *ifp; struct xfs_ifork *tifp; int whichfork = xfs_exchmaps_reqfork(req); + unsigned int sf_resblks = + xrep_tempexch_estimate_sf_resblks(sc, whichfork); int state = 0; /* @@ -693,9 +708,9 @@ xrep_tempexch_estimate( * plus the block we converted. */ req->ip1_bcount = sc->tempip->i_nblocks; - req->ip2_bcount = 1; + req->ip2_bcount = sf_resblks; req->nr_exchanges = 1 + tifp->if_nextents; - req->resblks = 1; + req->resblks = sf_resblks; break; case 2: /* @@ -707,10 +722,10 @@ xrep_tempexch_estimate( * is (worst case) the extent count of the file being repaired * plus the block we converted. */ - req->ip1_bcount = 1; + req->ip1_bcount = sf_resblks; req->ip2_bcount = sc->ip->i_nblocks; req->nr_exchanges = 1 + ifp->if_nextents; - req->resblks = 1; + req->resblks = sf_resblks; break; case 3: /* @@ -722,10 +737,10 @@ xrep_tempexch_estimate( * fileoff 0. Presumably, the caller could not exchange the * two inode fork areas directly. */ - req->ip1_bcount = 1; - req->ip2_bcount = 1; + req->ip1_bcount = sf_resblks; + req->ip2_bcount = sf_resblks; req->nr_exchanges = 1; - req->resblks = 2; + req->resblks = 2 * sf_resblks; break; } From 1ee2ce797c360785a3813fef62c90f427f3aed34 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 8 Sep 2026 23:04:50 -0700 Subject: [PATCH 1132/1198] xfs: actually check internal-rtdev fields in the superblock LOLLM points out that the superblock scrubber doesn't check the new fields that were added for internal realtime volumes when we added zoned device support. Cc: stable@vger.kernel.org # v6.15 Fixes: 2167eaabe2fadd ("xfs: define the zoned on-disk format") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Carlos Maiolino Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/agheader.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c index 1fa66aa68e16..fa5d32ec020a 100644 --- a/fs/xfs/scrub/agheader.c +++ b/fs/xfs/scrub/agheader.c @@ -418,6 +418,13 @@ xchk_superblock( xchk_block_set_corrupt(sc, bp); } + if (xfs_has_zoned(mp)) { + if (sb->sb_rtstart != cpu_to_be64(mp->m_sb.sb_rtstart)) + xchk_block_set_corrupt(sc, bp); + if (sb->sb_rtreserved != cpu_to_be64(mp->m_sb.sb_rtreserved)) + xchk_block_set_corrupt(sc, bp); + } + /* Everything else must be zero. */ sblen = xchk_superblock_ondisk_size(mp); if (memchr_inv((char *)sb + sblen, 0, BBTOB(bp->b_length) - sblen)) From 3bdbf472a608aeb7e8e4dc70ee86738ad5256356 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 8 Sep 2026 23:05:06 -0700 Subject: [PATCH 1133/1198] xfs: fix rtrmap cross-referencing elision logic LOLLM points out that xchk_bmap_xref_rmap_cow skips the cross-reference if the data-section rmapbt cursor is not present. However, this is broken for realtime file data fork scanning, because they will have an rtrmapbt cursor and not an rmapbt cursor. Fix the behavior by removing the cursor checks because xchk_bmap_get_rmap already accounts for that. Cc: stable@vger.kernel.org # v6.14 Fixes: 037a44d8277adf ("xfs: cross-reference the realtime rmapbt") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Carlos Maiolino Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/bmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index 401c278725d2..3b0f1dbd9147 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -274,7 +274,7 @@ xchk_bmap_xref_rmap_cow( unsigned long long rmap_end; uint64_t owner = XFS_RMAP_OWN_COW; - if (!info->sc->sa.rmap_cur || xchk_skip_xref(info->sc->sm)) + if (xchk_skip_xref(info->sc->sm)) return; /* Find the rmap record for this irec. */ From d3a6a35a220615c4f4578aedf3b1626b91d3acae Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 8 Sep 2026 23:05:21 -0700 Subject: [PATCH 1134/1198] xfs: fix termination logic in xchk_bmap xchk_should_terminate can turn its @error argument into -EINTR if the user is sitting on ^C. Unfortunately, this code here turns that into a 0 return, which isn't quite correct. LOLLM complains about this, though I think it's a very minor matter because the only way -EINTR happens is if there's a fatal signal. Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Carlos Maiolino Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/bmap.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index 3b0f1dbd9147..4f3c7f681bd9 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -1103,8 +1103,9 @@ xchk_bmap( * the rmap must match the combined mapping exactly. */ while (xchk_bmap_iext_iter(&info, &irec)) { - if (xchk_should_terminate(sc, &error) || - (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) + if (xchk_should_terminate(sc, &error)) + return error; + if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) return 0; if (irec.br_startoff >= endoff) { From e854f9a28b1fa08dfa5bf18ee4184fae90106180 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 8 Sep 2026 23:05:37 -0700 Subject: [PATCH 1135/1198] xfs: fix replaying dirent removals into the temporary directory xrep_dir_replay_removename is the function that replays a directory entry removal from sc->ip into the temporary directory so that when we swap the contents of sc->tempip and sc->ip, the directory is correct. LOLLM noticed that we were passing the wrong inode pointer into xrep_dir_init_args. It doesn't make sense to set rd->args.dp to rd->args.dp so let's fix this. Cc: stable@vger.kernel.org # v6.10 Fixes: 8559b21a64d983 ("xfs: implement live updates for directory repairs") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Carlos Maiolino Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/dir_repair.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/scrub/dir_repair.c b/fs/xfs/scrub/dir_repair.c index d9d6b7e2abda..2cfcf1c35679 100644 --- a/fs/xfs/scrub/dir_repair.c +++ b/fs/xfs/scrub/dir_repair.c @@ -727,7 +727,7 @@ xrep_dir_replay_removename( const struct xfs_name *name, xfs_extlen_t total) { - struct xfs_inode *dp = rd->args.dp; + struct xfs_inode *dp = rd->sc->tempip; ASSERT(S_ISDIR(VFS_I(dp)->i_mode)); From 69e10c2b4a51b4ff3c88a70e90f5180ad58c758f Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 8 Sep 2026 23:05:52 -0700 Subject: [PATCH 1136/1198] xfs: reset parent pointer args before each dir tree unlink repair LOLLM noticed that xfs_parent_removename only partially initializes the passed-in parent pointer arguments object. In the directory tree repair code, we could decide to remove multiple links to a file, so we don't want state from one call to bleed into the next one. Zero the whole thing explicitly. Cc: stable@vger.kernel.org # v6.10 Fixes: 3f31406aef493b ("xfs: fix corruptions in the directory tree") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Carlos Maiolino Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/dirtree_repair.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/xfs/scrub/dirtree_repair.c b/fs/xfs/scrub/dirtree_repair.c index 8acd55b8c769..1d1eafcf6eb5 100644 --- a/fs/xfs/scrub/dirtree_repair.c +++ b/fs/xfs/scrub/dirtree_repair.c @@ -479,6 +479,7 @@ xrep_dirtree_unlink( } if (xfs_has_parent(sc->mp)) { + memset(&dl->ppargs, 0, sizeof(dl->ppargs)); error = xfs_parent_removename(sc->tp, &dl->ppargs, dp, &dl->xname, sc->ip); if (error) From ad4497a92caba4630f75c80d49cb947026213280 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 8 Sep 2026 23:06:08 -0700 Subject: [PATCH 1137/1198] xfs: advance the findparent inode scan cursor while holding ILOCK LOLLM pointed out a race condition in xrep_findparent_scan -- the directory live update hook holds the directory ILOCK when it calls the xchk_iscan_want_live_update predicate to figure out if it needs to remember the live update, but xrep_findparent_scan drops the directory ILOCK before advancing the cursor. Therefore, it's possible for a live update to check the scan cursor after the scan drops the ILOCK but before the scan updates its cursor. If this happens, we'll fail to record the live update. Fix this by moving the cursor update logic inside xrep_findparent_walk_directory. Note that for non-directories it's ok to advance the cursor without holding any ILOCK because the findparent scan only cares about directory parents, not the children. Cc: stable@vger.kernel.org # v6.10 Fixes: a07b45576264e7 ("xfs: scan the filesystem to repair a directory dotdot entry") Signed-off-by: Darrick J. Wong Assisted-by: LOLLM # finding obvious bugs Reviewed-by: Carlos Maiolino Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/scrub/findparent.c | 56 ++++++++++++++++++++++++++------------- 1 file changed, 37 insertions(+), 19 deletions(-) diff --git a/fs/xfs/scrub/findparent.c b/fs/xfs/scrub/findparent.c index 04b6b96b0a30..eab3ac2704be 100644 --- a/fs/xfs/scrub/findparent.c +++ b/fs/xfs/scrub/findparent.c @@ -139,12 +139,40 @@ xrep_findparent_dirent( return 0; } +static inline bool +xrep_findparent_want_scan_file( + const struct xrep_findparent_info *fpi) +{ + const struct xfs_scrub *sc = fpi->sc; + const struct xfs_inode *dp = fpi->dp; + + /* Only directories can be parents */ + if (!S_ISDIR(VFS_IC(dp)->i_mode)) + return false; + + /* + * The inode being scanned cannot be its own parent, nor can any + * temporary directory we created to stage this repair. + */ + if (dp == sc->ip || dp == sc->tempip) + return false; + + /* + * Similarly, temporary files created to stage a repair cannot be the + * parent of this inode. + */ + if (xrep_is_tempfile(dp)) + return false; + + return true; +} + /* * If this is a directory, walk the dirents looking for any that point to the * scrub target inode. */ STATIC int -xrep_findparent_walk_directory( +xrep_findparent_walk_file( struct xrep_findparent_info *fpi) { struct xfs_scrub *sc = fpi->sc; @@ -152,19 +180,11 @@ xrep_findparent_walk_directory( unsigned int lock_mode; int error = 0; - /* - * The inode being scanned cannot be its own parent, nor can any - * temporary directory we created to stage this repair. - */ - if (dp == sc->ip || dp == sc->tempip) - return 0; - - /* - * Similarly, temporary files created to stage a repair cannot be the - * parent of this inode. - */ - if (xrep_is_tempfile(dp)) + if (!xrep_findparent_want_scan_file(fpi)) { + if (fpi->parent_scan) + xchk_iscan_mark_visited(&fpi->parent_scan->iscan, dp); return 0; + } /* * Scan the directory to see if there it contains an entry pointing to @@ -201,6 +221,8 @@ xrep_findparent_walk_directory( goto out_unlock; out_unlock: + if (fpi->parent_scan) + xchk_iscan_mark_visited(&fpi->parent_scan->iscan, dp); xfs_iunlock(dp, lock_mode); return error; } @@ -308,11 +330,7 @@ xrep_findparent_scan( ASSERT(S_ISDIR(VFS_IC(sc->ip)->i_mode)); while ((ret = xchk_iscan_iter(&pscan->iscan, &fpi.dp)) == 1) { - if (S_ISDIR(VFS_I(fpi.dp)->i_mode)) - ret = xrep_findparent_walk_directory(&fpi); - else - ret = 0; - xchk_iscan_mark_visited(&pscan->iscan, fpi.dp); + ret = xrep_findparent_walk_file(&fpi); xchk_irele(sc, fpi.dp); if (ret) break; @@ -401,7 +419,7 @@ xrep_findparent_confirm( goto out_rele; } - error = xrep_findparent_walk_directory(&fpi); + error = xrep_findparent_walk_file(&fpi); if (error) goto out_rele; From c5dcb3aadc18d7b82ba64790721b005d18193d35 Mon Sep 17 00:00:00 2001 From: Andrea Parri Date: Thu, 10 Sep 2026 16:34:42 +0200 Subject: [PATCH 1138/1198] hrtimer: Use hard expiry when updating timers on the same base Rearming a queued timer with nonzero slack can leave the timerqueue out of order. remove_and_enqueue_same_base() checks the new soft expiry against its neighbours' hard expiries, then stores the new hard expiry in the node without requeueing it. For example, with A at 10 and B at 20, rearming A at 11 with slack 30 passes the neighbour check but leaves A's hard expiry of 41 before B's 20. The same function also caches the soft expiry in base->expires_next when updating or inserting the first timer, giving next-event selection an earlier deadline than the queue head's hard expiry. Set the timer expiry before handling the queue. Use its stored hard expiry for the in-place ordering check and both updates to base->expires_next. The early update is safe because remove_and_enqueue_same_base() runs with base->cpu_base->lock held. The lock keeps the queue stable while hrtimer_can_update_in_place() checks the new expiry against both neighbours. If the check fails, timerqueue_linked_del() removes the node without comparing expiry values before it is reinserted. Fixes: eddffab8282e3 ("hrtimer: Keep track of first expiring timer per clock base") Fixes: 343f2f4dc5425 ("hrtimer: Try to modify timers in place") Signed-off-by: Andrea Parri Signed-off-by: Thomas Gleixner Assisted-by: LLM Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260910143442.2018-1-parri.andrea@gmail.com --- kernel/time/hrtimer.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 530d61257b9a..cbf1693c86b3 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1263,13 +1263,23 @@ remove_and_enqueue_same_base(struct hrtimer *timer, struct hrtimer_clock_base *b { bool was_first = false; + /* + * Updating the sort key while @timer is queued can temporarily + * make the tree inconsistent. This is safe under cpu_base->lock: + * no other queue operation can observe that state. + * hrtimer_can_update_in_place() either confirms that the new expiry + * fits between the neighbours or timerqueue_linked_del() removes the + * timer without consulting the expiry. + */ + hrtimer_set_expires_range_ns(timer, expires, delta_ns); + expires = hrtimer_get_expires(timer); + /* Remove it from the timer queue if active */ if (timer->is_queued) { was_first = !timerqueue_linked_prev(&timer->node); /* Try to update in place to avoid the de/enqueue dance */ if (hrtimer_can_update_in_place(timer, base, expires)) { - hrtimer_set_expires_range_ns(timer, expires, delta_ns); trace_hrtimer_start(timer, mode, true); if (was_first) base->expires_next = expires; @@ -1280,9 +1290,6 @@ remove_and_enqueue_same_base(struct hrtimer *timer, struct hrtimer_clock_base *b timerqueue_linked_del(&base->active, &timer->node); } - /* Set the new expiry time */ - hrtimer_set_expires_range_ns(timer, expires, delta_ns); - debug_activate(timer, mode, timer->is_queued); base->cpu_base->active_bases |= 1 << base->index; From 462d0b066b613103f579793031429db2ca23abc0 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Fri, 11 Sep 2026 00:15:24 +0900 Subject: [PATCH 1139/1198] tools/bootconfig: Fix integer overflow and truncation in size checks Sashiko reported that on 32-bit systems, if an attacker crafts size in the bootconfig footer such that adding BOOTCONFIG_FOOTER_SIZE wraps around (for instance, if size is 0xFFFFFFFF), the size check in load_xbc_from_initrd() can be bypassed: if (stat.st_size < size + BOOTCONFIG_FOOTER_SIZE) { pr_err("bootconfig size is too big\n"); return -E2BIG; } Furthermore, on 64-bit systems with an initrd > 4.29 GB, comparing a corrupted 32-bit size (e.g. 0xFFFFFFFF) against stat.st_size - BOOTCONFIG_FOOTER_SIZE can also bypass the check if size is not bounded. Similarly, load_xbc_file() passes 64-bit stat.st_size directly into the 32-bit int size parameter of load_xbc_fd(), truncating large standalone files (>= 2GB). In both cases, passing 0xFFFFFFFF to load_xbc_fd() truncates to -1, resulting in malloc(0), an integer overflow in read(), and an out-of-bounds null-byte write. Fix this by: 1. Rejecting size > XBC_DATA_MAX or size > stat.st_size - BOOTCONFIG_FOOTER_SIZE in load_xbc_from_initrd(). 2. Rejecting stat.st_size > XBC_DATA_MAX in load_xbc_file() before passing it to load_xbc_fd(). 3. Checking size < 0 || size > XBC_DATA_MAX defensively in load_xbc_fd(). Link: https://lore.kernel.org/all/178905332413.213925.3179977110281463499.stgit@devnote2/ Fixes: 950313ebf79c ("tools: bootconfig: Add bootconfig command") Cc: stable@vger.kernel.org Reported-by: Sashiko Closes: https://lore.kernel.org/all/20260909161113.16C691F00A3A@smtp.kernel.org/ Closes: https://lore.kernel.org/all/20260910010137.EE0431F000FF@smtp.kernel.org/ Assisted-by: Antigravity:gemini-3.8-flash Signed-off-by: Masami Hiramatsu (Google) Reviewed-by: Sang-Heon Jeon --- tools/bootconfig/main.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index 7dc9fff9b637..17d971d47f87 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -140,6 +140,9 @@ static int load_xbc_fd(int fd, char **buf, int size) { int ret; + if (size < 0 || size > XBC_DATA_MAX) + return -EINVAL; + *buf = malloc(size + 1); if (!*buf) return -ENOMEM; @@ -168,6 +171,13 @@ static int load_xbc_file(const char *path, char **buf) return ret; } + if (stat.st_size > XBC_DATA_MAX) { + pr_err("%s size is too big\n", path); + ret = -E2BIG; + close(fd); + return ret; + } + ret = load_xbc_fd(fd, buf, stat.st_size); close(fd); @@ -218,7 +228,8 @@ static int load_xbc_from_initrd(int fd, char **buf) csum = le32toh(csum); /* Wrong size error */ - if (stat.st_size < size + BOOTCONFIG_FOOTER_SIZE) { + if (size > XBC_DATA_MAX || + size > stat.st_size - BOOTCONFIG_FOOTER_SIZE) { pr_err("bootconfig size is too big\n"); return -E2BIG; } From 7812d6dab0698001e50e8c2f901e17da3eb6f429 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Fri, 11 Sep 2026 00:15:34 +0900 Subject: [PATCH 1140/1198] bootconfig: Fix integer overflow in initrd size check Sashiko reported that in get_boot_config_from_initrd(), a crafted initrd with a huge bootconfig size (such as 0xFFFFFFFF) can cause the pointer arithmetic: data = ((void *)hdr) - size; to wrap around on 32-bit systems (or when pointer subtraction overflows). Because data wraps around, the subsequent bounds check: if ((unsigned long)data < initrd_start) evaluates to false, bypassing the check. The kernel then calls xbc_calc_checksum(data, size), which attempts to read 4GB of memory, hitting unmapped pages and triggering a fatal kernel page fault during early boot. Furthermore, on 64-bit systems with an initrd > 4.29 GB, an unbounded 32-bit size can similarly bypass the initrd_start check. Fix this by: 1. Ensuring the initrd is at least large enough to contain the bootconfig footer and verifying hdr is within the initrd bounds. 2. Checking that size does not exceed XBC_DATA_MAX and does not exceed the available space between initrd_start and hdr before performing pointer subtraction. Link: https://lore.kernel.org/all/178905333479.213925.1358412668943562406.stgit@devnote2/ Fixes: de462e5f1071 ("bootconfig: Fix to remove bootconfig data from initrd while boot") Cc: stable@vger.kernel.org Reported-by: Sashiko Closes: https://lore.kernel.org/all/20260910010137.EE0431F000FF@smtp.kernel.org/ Assisted-by: Antigravity:gemini-3.8-flash Signed-off-by: Masami Hiramatsu (Google) Reviewed-by: Sang-Heon Jeon --- init/main.c | 25 +++++++++++++++---------- 1 file changed, 15 insertions(+), 10 deletions(-) diff --git a/init/main.c b/init/main.c index 2613d3f9b3ce..16749bb7a219 100644 --- a/init/main.c +++ b/init/main.c @@ -277,7 +277,8 @@ static void * __init get_boot_config_from_initrd(size_t *_size) u8 *hdr; int i; - if (!initrd_end) + if (!initrd_end || initrd_end < initrd_start || + initrd_end - initrd_start < BOOTCONFIG_MAGIC_LEN + 8) return NULL; data = (char *)initrd_end - BOOTCONFIG_MAGIC_LEN; @@ -294,16 +295,26 @@ static void * __init get_boot_config_from_initrd(size_t *_size) found: hdr = (u8 *)(data - 8); + if ((unsigned long)hdr < initrd_start) + return NULL; + size = get_unaligned_le32(hdr); csum = get_unaligned_le32(hdr + 4); - data = ((void *)hdr) - size; - if ((unsigned long)data < initrd_start) { - pr_err("bootconfig size %d is greater than initrd size %ld\n", + if (size > XBC_DATA_MAX) { + pr_err("bootconfig size %u is greater than max size %d\n", + size, XBC_DATA_MAX); + return NULL; + } + + if (size > ((unsigned long)hdr - initrd_start)) { + pr_err("bootconfig size %u is greater than initrd size %lu\n", size, initrd_end - initrd_start); return NULL; } + data = ((void *)hdr) - size; + if (xbc_calc_checksum(data, size) != csum) { pr_err("bootconfig checksum failed\n"); return NULL; @@ -394,12 +405,6 @@ static void __init setup_boot_config(void) return; } - if (size >= XBC_DATA_MAX) { - pr_err("bootconfig size %ld greater than max size %d\n", - (long)size, XBC_DATA_MAX); - return; - } - ret = xbc_init(data, size, &msg, &pos); if (ret < 0) { if (pos < 0) From 798514a25544d6978d0bd7fe7071c9bdb5503076 Mon Sep 17 00:00:00 2001 From: Vasant Hegde Date: Fri, 11 Sep 2026 08:33:50 +0000 Subject: [PATCH 1141/1198] iommu/amd: Make iommu_sva_set_dev_pasid as static Its used inside pasid.c only. No functional changes. Signed-off-by: Vasant Hegde Signed-off-by: Joerg Roedel --- drivers/iommu/amd/amd_iommu.h | 3 --- drivers/iommu/amd/pasid.c | 6 +++--- 2 files changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h index a2fe804b038b..71113e860859 100644 --- a/drivers/iommu/amd/amd_iommu.h +++ b/drivers/iommu/amd/amd_iommu.h @@ -54,9 +54,6 @@ struct protection_domain *protection_domain_alloc(void); struct iommu_domain *amd_iommu_domain_alloc_sva(struct device *dev, struct mm_struct *mm); void amd_iommu_domain_free(struct iommu_domain *dom); -int iommu_sva_set_dev_pasid(struct iommu_domain *domain, - struct device *dev, ioasid_t pasid, - struct iommu_domain *old); void amd_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid, struct iommu_domain *domain); diff --git a/drivers/iommu/amd/pasid.c b/drivers/iommu/amd/pasid.c index d708c6532480..40be5902087c 100644 --- a/drivers/iommu/amd/pasid.c +++ b/drivers/iommu/amd/pasid.c @@ -99,9 +99,9 @@ static const struct mmu_notifier_ops sva_mn = { .release = sva_mn_release, }; -int iommu_sva_set_dev_pasid(struct iommu_domain *domain, - struct device *dev, ioasid_t pasid, - struct iommu_domain *old) +static int iommu_sva_set_dev_pasid(struct iommu_domain *domain, + struct device *dev, ioasid_t pasid, + struct iommu_domain *old) { struct pdom_dev_data *pdom_dev_data; struct protection_domain *sva_pdom = to_pdomain(domain); From 5e1afd4ea1d6a9bbaecf3e28707dac9c8b56bd45 Mon Sep 17 00:00:00 2001 From: Vasant Hegde Date: Fri, 11 Sep 2026 08:33:51 +0000 Subject: [PATCH 1142/1198] iommu/amd: Remove redundant check in irq_remapping_select() The amd_iommu_irq_remap flag is already validated during irq remapping domain creation (before calling amd_iommu_create_irq_domain()). The duplicate check in irq_remapping_select() is unnecessary and can be removed. Additionally, mark amd_iommu_irq_remap as static. No functional changes. Signed-off-by: Vasant Hegde Signed-off-by: Joerg Roedel --- drivers/iommu/amd/amd_iommu_types.h | 3 --- drivers/iommu/amd/init.c | 2 +- drivers/iommu/amd/iommu.c | 3 --- 3 files changed, 1 insertion(+), 7 deletions(-) diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index 3dbe20023456..bce5027388b9 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -434,9 +434,6 @@ struct irq_remap_table { u32 *table; }; -/* Interrupt remapping feature used? */ -extern bool amd_iommu_irq_remap; - extern const struct iommu_ops amd_iommu_ops; /* IVRS indicates that pre-boot remapping was enabled */ diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index edcc187b8f14..8a410d4aa370 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -152,7 +152,7 @@ struct ivmd_header { } __attribute__((packed)); bool amd_iommu_dump; -bool amd_iommu_irq_remap __read_mostly; +static bool amd_iommu_irq_remap __read_mostly; enum protection_domain_mode amd_iommu_pgtable = PD_MODE_V1; /* Virtual address size */ diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 4dc306a4b5c6..67a86b9e1eca 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -3976,9 +3976,6 @@ static int irq_remapping_select(struct irq_domain *d, struct irq_fwspec *fwspec, struct amd_iommu *iommu; int devid = -1; - if (!amd_iommu_irq_remap) - return 0; - if (x86_fwspec_is_ioapic(fwspec)) devid = get_ioapic_devid(fwspec->param[0]); else if (x86_fwspec_is_hpet(fwspec)) From 80a4e3ad8daba66915a9bdf0fcae5831cc8dbd5f Mon Sep 17 00:00:00 2001 From: Vasant Hegde Date: Fri, 11 Sep 2026 08:33:52 +0000 Subject: [PATCH 1143/1198] iommu/amd: Remove redundant checks from interrupt handler path PPR and GAlog interrupt is enabled only if buffer is allocated. (See amd_iommu_enable_ppr_log() and iommu_ga_log_enable()). The duplicate check in interrupt hanlder path is unnecessary and can be removed. No functional changes. Signed-off-by: Vasant Hegde Signed-off-by: Joerg Roedel --- drivers/iommu/amd/iommu.c | 3 --- drivers/iommu/amd/ppr.c | 3 --- 2 files changed, 6 deletions(-) diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 67a86b9e1eca..56262f6b1f70 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -1076,9 +1076,6 @@ static void iommu_poll_ga_log(struct amd_iommu *iommu) { u32 head, tail; - if (iommu->ga_log == NULL) - return; - head = readl(iommu->mmio_base + MMIO_GA_HEAD_OFFSET); tail = readl(iommu->mmio_base + MMIO_GA_TAIL_OFFSET); diff --git a/drivers/iommu/amd/ppr.c b/drivers/iommu/amd/ppr.c index 76296079bb8b..2039a9dd71ac 100644 --- a/drivers/iommu/amd/ppr.c +++ b/drivers/iommu/amd/ppr.c @@ -165,9 +165,6 @@ void amd_iommu_poll_ppr_log(struct amd_iommu *iommu) { u32 head, tail; - if (iommu->ppr_log == NULL) - return; - head = readl(iommu->mmio_base + MMIO_PPR_HEAD_OFFSET); tail = readl(iommu->mmio_base + MMIO_PPR_TAIL_OFFSET); From b63c3c26726576e2a87baeee80bc202a5a43c9e5 Mon Sep 17 00:00:00 2001 From: Vasant Hegde Date: Fri, 11 Sep 2026 08:33:53 +0000 Subject: [PATCH 1144/1198] iommu/amd: Remove unused macro Remove unsed device range capability related macros. No functional changes. Signed-off-by: Vasant Hegde Signed-off-by: Joerg Roedel --- drivers/iommu/amd/amd_iommu_types.h | 13 ------------- 1 file changed, 13 deletions(-) diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index bce5027388b9..8241ef922519 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -39,18 +39,6 @@ #define MMIO_RANGE_OFFSET 0x0c #define MMIO_MISC_OFFSET 0x10 -/* Masks, shifts and macros to parse the device range capability */ -#define MMIO_RANGE_LD_MASK 0xff000000 -#define MMIO_RANGE_FD_MASK 0x00ff0000 -#define MMIO_RANGE_BUS_MASK 0x0000ff00 -#define MMIO_RANGE_LD_SHIFT 24 -#define MMIO_RANGE_FD_SHIFT 16 -#define MMIO_RANGE_BUS_SHIFT 8 -#define MMIO_GET_LD(x) (((x) & MMIO_RANGE_LD_MASK) >> MMIO_RANGE_LD_SHIFT) -#define MMIO_GET_FD(x) (((x) & MMIO_RANGE_FD_MASK) >> MMIO_RANGE_FD_SHIFT) -#define MMIO_GET_BUS(x) (((x) & MMIO_RANGE_BUS_MASK) >> MMIO_RANGE_BUS_SHIFT) -#define MMIO_MSI_NUM(x) ((x) & 0x1f) - /* Used offsets into the MMIO space */ #define MMIO_DEV_TABLE_OFFSET 0x0000 #define MMIO_CMD_BUF_OFFSET 0x0008 @@ -247,7 +235,6 @@ /* constants to configure the command buffer */ #define CMD_BUFFER_SIZE 8192 -#define CMD_BUFFER_UNINITIALIZED 1 #define CMD_BUFFER_ENTRIES 512 #define MMIO_CMD_SIZE_SHIFT 56 #define MMIO_CMD_SIZE_512 (0x9ULL << MMIO_CMD_SIZE_SHIFT) From 2deb753127d7b7035e893955c5e91875e767d1f8 Mon Sep 17 00:00:00 2001 From: Henry Martin Date: Fri, 4 Sep 2026 19:52:23 +0800 Subject: [PATCH 1145/1198] tracing/user_events: Don't destroy fields when event removal fails destroy_user_event() destroys the event's fields before attempting to remove the trace event call. If user_event_set_call_visible() fails, e.g. because the event is still enabled and trace_remove_event_call() returns -EBUSY, the event is left registered with an irreversibly destroyed field list. Any subsequent interaction with the event then operates on an empty field list while it is still fully visible in tracefs. Move the field destruction after the call removal, and splice the field list back onto the event when the removal fails so the event remains in a consistent state. Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260904115223.2976446-1-bsdhenrymartin@gmail.com Fixes: 7f5a08c79df35 ("user_events: Add minimal support for trace_event into ftrace") Signed-off-by: Henry Martin Reviewed-by: Beau Belgrave Signed-off-by: Steven Rostedt --- kernel/trace/trace_events_user.c | 26 ++++++++++++++++++++------ 1 file changed, 20 insertions(+), 6 deletions(-) diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 93cda2f6f269..f658c3a77aa7 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -1122,10 +1122,9 @@ static void user_event_destroy_validators(struct user_event *user) } } -static void user_event_destroy_fields(struct user_event *user) +static void user_event_destroy_fields(struct list_head *head) { struct ftrace_event_field *field, *next; - struct list_head *head = &user->fields; list_for_each_entry_safe(field, next, head, link) { list_del(&field->link); @@ -1502,17 +1501,32 @@ static int user_event_set_call_visible(struct user_event *user, bool visible) static int destroy_user_event(struct user_event *user) { + LIST_HEAD(fields); int ret = 0; lockdep_assert_held(&event_mutex); - /* Must destroy fields before call removal */ - user_event_destroy_fields(user); + /* + * Detach the fields before removing the call. Removing the event + * frees the field list memory (trace_destroy_fields() is run on + * successful removal and kmem_cache_free()s the fields), but the + * fields here are allocated and owned by user_events. Destroy + * them separately once removal has succeeded. + */ + list_splice_init(&user->fields, &fields); ret = user_event_set_call_visible(user, false); - if (ret) + if (ret) { + /* + * Removal failed and the event stays registered, recover + * the fields so it is left in a consistent state. + */ + list_splice(&fields, &user->fields); return ret; + } + + user_event_destroy_fields(&fields); dyn_event_remove(&user->devent); hash_del(&user->node); @@ -2212,7 +2226,7 @@ static int user_event_parse(struct user_event_group *group, char *name, put_user_lock: mutex_unlock(&event_mutex); put_user: - user_event_destroy_fields(user); + user_event_destroy_fields(&user->fields); user_event_destroy_validators(user); kfree(user->call.print_fmt); From 08cacffeef8f64f1a222c93467ca84f24a46c953 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=A9my=20Jean?= Date: Sat, 22 Aug 2026 19:53:22 +0000 Subject: [PATCH 1146/1198] ftrace: fork: Initialize function graph state before copy_exec_state() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit dup_task_struct() copies the parent's task_struct, including ret_stack. ftrace_graph_init_task() clears the copied function graph state, but it currently runs after copy_exec_state(). For non-CLONE_VM forks, copy_exec_state() allocates a new task_exec_state. If that allocation fails, copy_process() reaches bad_fork_free and free_task() calls ftrace_graph_exit_task(). Since the child still carries the parent's ret_stack pointer, the unwind frees the parent's active function graph return stack. The parent subsequently accesses freed memory from function_graph_enter_regs(). KASAN reports: [ 22.190920] ================================================================== [ 22.195899] BUG: KASAN: slab-use-after-free in function_graph_enter_regs+0xa76/0xb90 [ 22.200747] Write of size 8 at addr ff110000054dc0a8 by task repro/1 [ 22.205134] [ 22.210770] CPU: 0 UID: 0 PID: 1 Comm: repro Not tainted 7.2.0-07732-g9328b3b03bdc-dirty #3 PREEMPT(lazy) [ 22.212576] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 [ 22.213750] Call Trace: [ 22.215271] [ 22.216242] ? ftrace_stub_direct_tramp+0x10/0x10 [ 22.217774] dump_stack_lvl+0x4e/0x70 [ 22.220531] print_report+0x157/0x4b4 [ 22.223202] ? fixup_red_left+0x9/0x30 [ 22.224407] ? complete_report_info+0x83/0x110 [ 22.226679] ? function_graph_enter_regs+0xa76/0xb90 [ 22.228084] kasan_report+0xce/0x100 [ 22.230109] ? function_graph_enter_regs+0xa76/0xb90 [ 22.232860] ? stack_trace_save+0x4/0xd0 [ 22.234156] function_graph_enter_regs+0xa76/0xb90 [ 22.236090] ? kasan_save_stack+0x30/0x50 [ 22.237752] ? __pfx_function_graph_enter_regs+0x10/0x10 [ 22.238694] ? ring_buffer_lock_reserve+0x345/0xf80 [ 22.239628] ? stack_trace_save+0x4/0xd0 [ 22.242121] ? stack_trace_save+0x4/0xd0 [ 22.243588] ftrace_graph_func+0xda/0x160 [ 22.245362] ? ftrace_stub_direct_tramp+0x10/0x10 [ 22.246520] 0xffffffffa0000095 [ 22.250528] ? stack_trace_save+0x9/0xd0 [ 22.251757] ? ring_buffer_unlock_commit+0x11d/0x5c0 [ 22.253152] stack_trace_save+0x9/0xd0 [ 22.254264] kasan_save_stack+0x30/0x50 [ 22.273631] kasan_save_track+0x14/0x30 [ 22.276763] kasan_save_free_info+0x3b/0x70 [ 22.278296] __kasan_slab_free+0x43/0x70 [ 22.280157] kmem_cache_free+0xbf/0x3b0 [ 22.282963] ? ftrace_stub_direct_tramp+0x10/0x10 [ 22.284001] free_task+0xa2/0x160 [ 22.285699] ? ftrace_stub_direct_tramp+0x10/0x10 [ 22.286752] copy_process+0x2aae/0x7bc0 Initialize the child function graph state immediately after dup_task_struct(), before the first fallible operation. Cc: stable@vger.kernel.org Fixes: 6b1c66c9cca9 ("exec_state: relocate dumpable information") Reviewed-by: Bradley Morgan Link: https://patch.msgid.link/20260822195321.962383-2-Jeremy.Jean@oss.cyber.gouv.fr Assisted-by: Codex:gpt-5 Signed-off-by: Jérémy Jean Signed-off-by: Steven Rostedt --- kernel/fork.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/kernel/fork.c b/kernel/fork.c index 416758c8a3d4..a5934a317634 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2133,6 +2133,11 @@ __latent_entropy struct task_struct *copy_process( p = dup_task_struct(current, node); if (!p) goto fork_out; + /* + * Must run before the first fallible op, so error paths never + * free the parent's ret_stack. + */ + ftrace_graph_init_task(p); retval = copy_exec_state(clone_flags, p); if (retval) goto bad_fork_free; @@ -2159,8 +2164,6 @@ __latent_entropy struct task_struct *copy_process( */ p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? args->child_tid : NULL; - ftrace_graph_init_task(p); - rt_mutex_init_task(p); raw_spin_lock_init(&p->blocked_lock); From b22845487096247f5370c412376a472304627847 Mon Sep 17 00:00:00 2001 From: Donggeun Yoo Date: Sun, 6 Sep 2026 06:19:22 +0900 Subject: [PATCH 1147/1198] fgraph: Remove unused FGRAPH_MAX_INDEX FGRAPH_MAX_INDEX has no user, and it expands to FGRAPH_INDEX_SIZE and FGRAPH_RET_INDEX, neither of which is defined anywhere in the tree. It was added in that form by commit 91c46b0aa917 ("function_graph: Implement fgraph_reserve_data() and fgraph_retrieve_data()"), which introduced the current data word layout under new names, so anything referencing it would have failed to build ever since. Remove it. Link: https://patch.msgid.link/20260905211922.1196366-1-donggeunyoo.kernel@gmail.com Signed-off-by: Donggeun Yoo Acked-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt --- kernel/trace/fgraph.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 40d373d65f9b..ed455b53513b 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -143,9 +143,6 @@ enum { #define FGRAPH_DATA_INDEX_MASK GENMASK(FGRAPH_DATA_INDEX_BITS - 1, 0) #define FGRAPH_DATA_INDEX_SHIFT (FGRAPH_DATA_SHIFT + FGRAPH_DATA_BITS) -#define FGRAPH_MAX_INDEX \ - ((FGRAPH_INDEX_SIZE << FGRAPH_DATA_BITS) + FGRAPH_RET_INDEX) - #define FGRAPH_ARRAY_SIZE FGRAPH_INDEX_BITS /* From 0701995aaf8fc2281154db829ca85e231951e51d Mon Sep 17 00:00:00 2001 From: Donggeun Yoo Date: Sun, 6 Sep 2026 12:44:06 +0900 Subject: [PATCH 1148/1198] function_graph: Use the saved entry's size when reprinting it When a graph entry does not fit in the trace_seq, print_graph_entry() saves it in the iterator's fgraph_data and reprints it on the next read. The entry has already been consumed from the ring buffer by then, so the copy is all that is left of it. The copy is sized with iter->ent_size, which no longer describes the saved entry but whatever entry the iterator has moved on to. The argument count is derived from the same field, so a 72 byte entry saved and then reprinted ahead of a 48 byte return entry loses its arguments. Record the size next to the failure flag, so that the two are always set together, and restore it before reprinting. Cc: stable@vger.kernel.org Fixes: ff5c9c576e75 ("ftrace: Add support for function argument to graph tracer") Link: https://patch.msgid.link/20260906034406.1335316-1-donggeunyoo.kernel@gmail.com Signed-off-by: Donggeun Yoo Signed-off-by: Steven Rostedt --- kernel/trace/trace_functions_graph.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index ff7cb1a76b95..c5befd0c5b9a 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -52,6 +52,7 @@ struct fgraph_data { }; struct ftrace_graph_ret_entry ret; int failed; + int ent_size; int cpu; }; @@ -1274,6 +1275,7 @@ print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s, if (s->full) { data->failed = 1; data->cpu = cpu; + data->ent_size = iter->ent_size; } else data->failed = 0; } @@ -1457,6 +1459,7 @@ print_graph_function_flags(struct trace_iterator *iter, u32 flags) if (data && data->failed) { field = &data->ent.ent; iter->cpu = data->cpu; + iter->ent_size = data->ent_size; ret = print_graph_entry(field, s, iter, flags); if (ret == TRACE_TYPE_HANDLED && iter->cpu != cpu) { per_cpu_ptr(data->cpu_data, iter->cpu)->ignore = 1; From 4bddcb346a6cf4615ca77f69a589623b877ca267 Mon Sep 17 00:00:00 2001 From: Donggeun Yoo Date: Sun, 6 Sep 2026 21:40:25 +0900 Subject: [PATCH 1149/1198] tracing: Free histogram var refs regardless of how often they are referenced Using the same variable three or more times in one hist trigger leaks the variable reference and its strings when the trigger is removed. commit 656fe2ba85e8 ("tracing: Use hist trigger's var_ref array to destroy var_refs") made a trigger's var_refs[] array the only owner of a var ref: destroy_hist_field() returns early for HIST_FIELD_FL_VAR_REF, so the field expressions never destroy one. One entry, freed once, no count needed. commit 8bcebc77e85f ("tracing: Fix histogram code when expression has same var as value") then made repeated references share one object and added a count of them. Only the increment side exists, since those expressions still return early and never drop a reference, so __destroy_hist_field() sees how many references were created rather than how many are left. It frees when the decremented count is 0 or 1, so two references work and three or more leak. Sharing kept one array entry per object, and create_var_ref() searches and appends within a single trigger, so nothing outside it holds the object. Removing a trigger whose variables are still referenced is already refused by check_var_refs() with -EBUSY. Drop the count and free unconditionally. Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260906124025.3550596-1-donggeunyoo.kernel@gmail.com Fixes: 8bcebc77e85f ("tracing: Fix histogram code when expression has same var as value") Signed-off-by: Donggeun Yoo Signed-off-by: Steven Rostedt --- kernel/trace/trace_events_hist.c | 16 +--------------- 1 file changed, 1 insertion(+), 15 deletions(-) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 963e0d6b61fd..f90680b33a37 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -169,7 +169,6 @@ struct hist_field { struct hist_field *operands[HIST_FIELD_OPERANDS_MAX]; struct hist_trigger_data *hist_data; enum hist_field_fn fn_num; - unsigned int ref; unsigned int size; unsigned int offset; unsigned int is_signed; @@ -1913,16 +1912,8 @@ static int contains_operator(char *str, char **sep) return field_op; } -static void get_hist_field(struct hist_field *hist_field) -{ - hist_field->ref++; -} - static void __destroy_hist_field(struct hist_field *hist_field) { - if (--hist_field->ref > 1) - return; - kfree(hist_field->var.name); kfree(hist_field->name); @@ -1969,8 +1960,6 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, if (!hist_field) return NULL; - hist_field->ref = 1; - hist_field->hist_data = hist_data; if (flags & HIST_FIELD_FL_EXPR || flags & HIST_FIELD_FL_ALIAS) @@ -2223,10 +2212,8 @@ static struct hist_field *create_var_ref(struct hist_trigger_data *hist_data, for (i = 0; i < hist_data->n_var_refs; i++) { ref_field = hist_data->var_refs[i]; if (ref_field->var.idx == var_field->var.idx && - ref_field->var.hist_data == var_field->hist_data) { - get_hist_field(ref_field); + ref_field->var.hist_data == var_field->hist_data) return ref_field; - } } /* Sanity check to avoid out-of-bound write on 'hist_data->var_refs' */ if (hist_data->n_var_refs >= TRACING_MAP_VARS_MAX) @@ -3276,7 +3263,6 @@ static struct hist_field *create_var(struct hist_trigger_data *hist_data, goto out; } - var->ref = 1; var->flags = HIST_FIELD_FL_VAR; var->var.idx = idx; var->var.hist_data = var->hist_data = hist_data; From 516001d53e6b2ea95a251ee2ef54a1a689a3fd58 Mon Sep 17 00:00:00 2001 From: Donggeun Yoo Date: Sun, 6 Sep 2026 22:33:52 +0900 Subject: [PATCH 1150/1198] tracing: Free histogram the var ref when its initialization fails create_var_ref() allocates a VAR_REF hist_field and then calls init_var_ref() to fill it in. When that fails the field is leaked. commit 656fe2ba85e8 ("tracing: Use hist trigger's var_ref array to destroy var_refs") made destroy_hist_field() return early for HIST_FIELD_FL_VAR_REF, since var refs are freed by walking the trigger's var_refs[] array instead. create_var_ref() adds the field to that array only after init_var_ref() has succeeded, so on this path the field is in neither place and nothing frees it. The call was correct when it was written, before var refs were taken out of destroy_hist_field(). init_var_ref() cannot free it either. The caller owns the field, so init_var_ref() undoes only its own string allocations and leaves the field alone. Freeing it there would leave create_var_ref() passing freed memory to destroy_hist_field(), which reads its flags. Call __destroy_hist_field(), which frees the field without consulting the flag. Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260906133352.3815019-1-donggeunyoo.kernel@gmail.com Fixes: 656fe2ba85e8 ("tracing: Use hist trigger's var_ref array to destroy var_refs") Signed-off-by: Donggeun Yoo Signed-off-by: Steven Rostedt --- kernel/trace/trace_events_hist.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index f90680b33a37..bbdd56208eff 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -2221,7 +2221,7 @@ static struct hist_field *create_var_ref(struct hist_trigger_data *hist_data, ref_field = create_hist_field(var_field->hist_data, NULL, flags, NULL); if (ref_field) { if (init_var_ref(ref_field, var_field, system, event_name)) { - destroy_hist_field(ref_field, 0); + __destroy_hist_field(ref_field); return NULL; } From 230234d12ce42ab04132a32c3a848f07a5d27a71 Mon Sep 17 00:00:00 2001 From: Donggeun Yoo Date: Mon, 7 Sep 2026 12:49:48 +0900 Subject: [PATCH 1151/1198] tracing: Free histogram the field rejected for a bad modifier Writing a hist trigger whose value or variable carries a modifier that is not allowed there leaks the fields that were built for it. __create_val_field() takes the field from parse_expr() and stores it in hist_data->fields[] only after the modifier checks have run: hist_field = parse_expr(hist_data, file, field_str, flags, var_name, &n_subexprs); ... if (hist_field->flags & HIST_FIELD_FL_VAR) { if (hist_field->flags & (...)) goto err; } else { if (hist_field->flags & (...)) goto err; } hist_data->fields[val_idx] = hist_field; Both checks jump past that store, and the err label returns without freeing anything. The error unwinds to create_hist_data(), which calls destroy_hist_data() -> destroy_hist_fields(), and that reaches a field only by walking fields[]. A field that never got there is unreachable. commit e0213434fe3e ("tracing: Do not let histogram values have some modifiers") set ret to -EINVAL and fell through to the store, which left the field owned by fields[] and freed along with the rest of hist_data. Splitting the check into a value case and a variable case replaced that fall-through with a goto that skips it. With CONFIG_DEBUG_KMEMLEAK, 200 writes of # echo 'hist:keys=prev_pid:vals=next_pid.log2' > \ events/sched/sched_switch/trigger each correctly rejected with -EINVAL, leave 332 unreferenced objects (63744 bytes) reported at create_hist_field(); 200 install and remove cycles of a valid trigger leave none. A '.log2' field is two allocations, since create_hist_field() puts the plain field in operands[0] of the log2 field, and both are reported. Use destroy_hist_field() rather than __destroy_hist_field() so that operands[0] is freed as well. It returns early for HIST_FIELD_FL_VAR_REF, which is what an operand owned by hist_data->var_refs[] needs; the rejected field itself is never a var ref, because a var ref never carries a modifier flag. Cc: stable@vger.kernel.org Fixes: e30fbc618e97 ("tracing/histograms: Allow variables to have some modifiers") Link: https://patch.msgid.link/20260907034948.240387-1-donggeunyoo.kernel@gmail.com Signed-off-by: Donggeun Yoo Signed-off-by: Steven Rostedt --- kernel/trace/trace_events_hist.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index bbdd56208eff..8cad99a8d01e 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -4317,6 +4317,7 @@ static int __create_val_field(struct hist_trigger_data *hist_data, return ret; err: hist_err(file->tr, HIST_ERR_BAD_FIELD_MODIFIER, errpos(field_str)); + destroy_hist_field(hist_field, 0); return -EINVAL; } From 06f5634ec5584954177f9a22e36b3bfb398a971b Mon Sep 17 00:00:00 2001 From: Donggeun Yoo Date: Mon, 7 Sep 2026 15:03:23 +0900 Subject: [PATCH 1152/1198] tracing: Keep the entry count when the histogram stats allocation fails print_entries() uses n_entries both as the number of sort entries and as its own return value, so the -ENOMEM it stores when the stats allocation fails overwrites the count that the cleanup still needs: n_entries = tracing_map_sort_entries(map, ...); if (n_entries < 0) return n_entries; ... if (!stats) { n_entries = -ENOMEM; goto out; } ... out: tracing_map_destroy_sort_entries(sort_entries, n_entries); tracing_map_destroy_sort_entries() takes an unsigned int and loops up to it, so -ENOMEM arrives as 4294967284. It walks an array of at most map->max_elts pointers and calls destroy_sort_entry(), which dereferences and frees, on whatever lies past the end. Reading the hist file of a trigger with a .percent value, with that allocation forced to fail: BUG: KASAN: vmalloc-out-of-bounds in tracing_map_destroy_sort_entries+0xa0/0xb0 Read of size 8 at addr ffffc90000045000 by task init/1 tracing_map_destroy_sort_entries+0xa0/0xb0 hist_show+0x6f7/0x1df0 seq_read_iter+0x2b8/0x1190 vfs_read+0x176/0xa40 The buggy address belongs to a 4-page vmalloc region starting at ffffc90000041000 allocated at tracing_map_sort_entries+0x5c/0xd50 A few pages further the fault is fatal. The registers at the oops confirm the bound: the loop's end pointer less the array start, over the pointer size, is 4294967284. Return the error in a separate variable and leave n_entries holding the count, the way tracing_map_sort_entries() does on its own error path. The stats block is only entered for a value carrying .percent or .graph, which __create_val_field() has rejected since v6.3, so this cannot be reached in mainline as it stands. It becomes reachable again with "tracing: hist: let values keep the percent and graph modifiers", so it should be applied first. Cc: stable@vger.kernel.org Fixes: abaa5258ce5e ("tracing: Add .percent suffix option to histogram values") Link: https://patch.msgid.link/20260907060323.480728-1-donggeunyoo.kernel@gmail.com Reported-by: sashiko-bot@kernel.org Closes: https://lore.kernel.org/all/20260907053113.1CED91F00A3A@smtp.kernel.org/ Signed-off-by: Donggeun Yoo Acked-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt --- kernel/trace/trace_events_hist.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 8cad99a8d01e..8d80562fb502 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -5677,7 +5677,7 @@ static int print_entries(struct seq_file *m, { struct tracing_map_sort_entry **sort_entries = NULL; struct tracing_map *map = hist_data->map; - int i, j, n_entries; + int i, j, n_entries, ret; struct hist_val_stat *stats = NULL; u64 val; @@ -5687,6 +5687,8 @@ static int print_entries(struct seq_file *m, if (n_entries < 0) return n_entries; + ret = n_entries; + /* Calculate the max and the total for each field if needed. */ for (j = 0; j < hist_data->n_vals; j++) { if (!(hist_data->fields[j]->flags & @@ -5695,7 +5697,7 @@ static int print_entries(struct seq_file *m, if (!stats) { stats = kzalloc_objs(*stats, hist_data->n_vals); if (!stats) { - n_entries = -ENOMEM; + ret = -ENOMEM; goto out; } } @@ -5716,7 +5718,7 @@ static int print_entries(struct seq_file *m, out: tracing_map_destroy_sort_entries(sort_entries, n_entries); - return n_entries; + return ret; } static void hist_trigger_show(struct seq_file *m, From 3d617bfd79330ae3acf94862c18bb3ccf5f5a0f9 Mon Sep 17 00:00:00 2001 From: Donggeun Yoo Date: Mon, 7 Sep 2026 14:21:13 +0900 Subject: [PATCH 1153/1198] tracing: Let histogram values keep the percent and graph modifiers The .percent and .graph modifiers exist only for histogram values, but a value carrying either of them has been rejected since v6.3. The example in Documentation/trace/histogram.rst, # echo 'hist:keys=prev_comm:vals=hitcount.percent:nohitcount' > \ events/sched/sched_switch/trigger returns -EINVAL. parse_field() sets the two flags only when the field is neither a key nor a variable, that is, only on a value: } else if (strncmp(modifier, "percent", 7) == 0) { if (*flags & (HIST_FIELD_FL_VAR | HIST_FIELD_FL_KEY)) goto error; *flags |= HIST_FIELD_FL_PERCENT; __create_val_field() then rejects a value for carrying them, so no field can reach hist_trigger_print_val(), where both are implemented. commit e0213434fe3e ("tracing: Do not let histogram values have some modifiers") added the check after a value with .buckets oopsed in hist_field_name(). That happens because .buckets and .log2 make create_hist_field() build a nested field in operands[0] which hist_field_name() then walks into. The percent and graph flags do not create an operand and are not read by hist_field_name(); they are only used when printing a value. Stop rejecting the two flags on a value. The check for variables is left alone, where they are unreachable anyway because parse_field() rejects a variable carrying them first. With the two flags removed, the trigger above installs and prints as documented: { prev_comm: rcu_preempt } hitcount (%): 0.00 { prev_comm: init } hitcount (%): 99.98 Totals: Hits: 237896 Cc: stable@vger.kernel.org Fixes: e0213434fe3e ("tracing: Do not let histogram values have some modifiers") Link: https://patch.msgid.link/20260907052113.430818-1-donggeunyoo.kernel@gmail.com Signed-off-by: Donggeun Yoo Signed-off-by: Steven Rostedt --- kernel/trace/trace_events_hist.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 8d80562fb502..5e00da2d5b1a 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -4299,8 +4299,7 @@ static int __create_val_field(struct hist_trigger_data *hist_data, goto err; } else { /* Value */ - if (hist_field->flags & (HIST_FIELD_FL_GRAPH | HIST_FIELD_FL_PERCENT | - HIST_FIELD_FL_BUCKET | HIST_FIELD_FL_LOG2 | + if (hist_field->flags & (HIST_FIELD_FL_BUCKET | HIST_FIELD_FL_LOG2 | HIST_FIELD_FL_SYM | HIST_FIELD_FL_SYM_OFFSET | HIST_FIELD_FL_SYSCALL | HIST_FIELD_FL_STACKTRACE)) goto err; From 89b000ba0796593aa61f6eec24d369337594588b Mon Sep 17 00:00:00 2001 From: Hemanth Selam Date: Mon, 7 Sep 2026 11:56:08 +0530 Subject: [PATCH 1154/1198] tracing: Fix typo "availabe" in comment Correct "availabe" to "available", reported by scripts/checkpatch.pl using the misspelling list in scripts/spelling.txt. Only touches comments, no code changes. Link: https://patch.msgid.link/20260907062608.13924-1-hemanth.selam@gmail.com Assisted-by: Cursor:claude-opus-5 Signed-off-by: Hemanth Selam Signed-off-by: Steven Rostedt --- kernel/trace/rethook.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c index 5a8bdf88999a..87a27f3aa4a6 100644 --- a/kernel/trace/rethook.c +++ b/kernel/trace/rethook.c @@ -171,7 +171,7 @@ struct rethook_node *rethook_try_get(struct rethook *rh) * This expects the caller will set up a rethook on a function entry. * When the function returns, the rethook will eventually be reclaimed * or released in the rethook_recycle() with call_rcu(). - * This means the caller must be run in the RCU-availabe context. + * This means the caller must be run in the RCU-available context. */ if (unlikely(!rcu_is_watching())) return NULL; From 0999d3e16d13b6299fd7cc7a7fb2825c18e90dd0 Mon Sep 17 00:00:00 2001 From: Hemanth Selam Date: Mon, 7 Sep 2026 12:26:07 +0530 Subject: [PATCH 1155/1198] tracing: Fix typo "preceeded" in comment Correct "preceeded" to "Preceded", reported by scripts/checkpatch.pl using the misspelling list in scripts/spelling.txt. Only touches comments, no code changes. Link: https://patch.msgid.link/20260907065607.36615-1-hemanth.selam@gmail.com Assisted-by: Cursor:claude-opus-5 Signed-off-by: Hemanth Selam Signed-off-by: Steven Rostedt --- include/trace/events/timer.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h index ca82fd62dc30..3aa0608c6361 100644 --- a/include/trace/events/timer.h +++ b/include/trace/events/timer.h @@ -302,7 +302,7 @@ DECLARE_EVENT_CLASS(hrtimer_class, * hrtimer_start_expired - Invoked when a expired timer was started * @hrtimer: pointer to struct hrtimer * - * Preceeded by a hrtimer_start tracepoint. + * Preceded by a hrtimer_start tracepoint. */ DEFINE_EVENT(hrtimer_class, hrtimer_start_expired, From 6ede78d0563a2a3ae3e46f9c07cedb5d79645429 Mon Sep 17 00:00:00 2001 From: Donggeun Yoo Date: Mon, 7 Sep 2026 18:14:15 +0900 Subject: [PATCH 1156/1198] tracing: Set the trace clock before registering the histogram trigger hist_register_trigger() puts the trigger on the global named_triggers list in cmd_ops->init(), and only then sets the trace clock: if (data->cmd_ops->init) { ret = data->cmd_ops->init(data); if (ret < 0) goto out; } if (hist_data->enable_timestamps) { ret = tracing_set_clock(file->tr, hist_data->attrs->clock); if (ret) { hist_err(tr, HIST_ERR_SET_CLOCK_FAIL, errpos(clock)); goto out; } The clock string is not checked anywhere before that call, so a named trigger using common_timestamp with an unknown clock fails after it has already become findable. event_hist_trigger_parse() then frees it without taking it off the list, and the next lookup by name reads the freed object: ~# cd /sys/kernel/tracing/events/sched/sched_switch ~# echo 'hist:name=foo:keys=common_pid:ts=common_timestamp:clock=bogus' > trigger bash: echo: write error: Invalid argument ~# echo 'hist:name=foo:keys=common_pid' > trigger BUG: KASAN: slab-use-after-free in find_named_trigger+0xac/0xc0 Read of size 8 at addr ffff88800915d760 by task init/1 find_named_trigger+0xac/0xc0 hist_register_trigger+0xc1/0x900 event_hist_trigger_parse+0x3146/0x6af0 event_trigger_write+0xce/0x160 Freed by task 63: kfree+0x154/0x420 trigger_kthread_fn+0xfd/0x160 Set the clock before the trigger is registered, so that nothing which can fail runs after it is published, the way commit 6f86bdeab633 ("tracing: Fix bad hist from corrupting named_triggers list") moved the registration below the rest of the setup. tracing_set_filter_buffering() is reference counted, so the init failure path has to drop the reference that the clock block now takes first. Cc: stable@vger.kernel.org Fixes: a4072fe85ba3 ("tracing: Add a clock attribute for hist triggers") Link: https://patch.msgid.link/20260907091415.554535-1-donggeunyoo.kernel@gmail.com Signed-off-by: Donggeun Yoo Signed-off-by: Steven Rostedt --- kernel/trace/trace_events_hist.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 5e00da2d5b1a..1889e310b73c 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -6631,12 +6631,6 @@ static int hist_register_trigger(char *glob, data->cmd_ops = cmd_ops; } - if (data->cmd_ops->init) { - ret = data->cmd_ops->init(data); - if (ret < 0) - goto out; - } - if (hist_data->enable_timestamps) { char *clock = hist_data->attrs->clock; @@ -6649,6 +6643,15 @@ static int hist_register_trigger(char *glob, tracing_set_filter_buffering(file->tr, true); } + if (data->cmd_ops->init) { + ret = data->cmd_ops->init(data); + if (ret < 0) { + if (hist_data->enable_timestamps) + tracing_set_filter_buffering(file->tr, false); + goto out; + } + } + if (named_data) { remove_hist_vars(hist_data); destroy_hist_data(hist_data); From 0fe23b8eaba0d3372c66b7b31204408da0715edc Mon Sep 17 00:00:00 2001 From: Donggeun Yoo Date: Mon, 7 Sep 2026 21:44:19 +0900 Subject: [PATCH 1157/1198] tracing: Take the reference before publishing the named histogram trigger event_hist_trigger_named_init() puts the trigger on the global named_triggers list and only then takes the reference on the trigger it shares its histogram with: data->ref++; save_named_trigger(data->named_data->name, data); ret = event_hist_trigger_init(data->named_data); if (ret < 0) { kfree(data->cmd_ops); data->cmd_ops = &trigger_hist_cmd; } return ret; event_hist_trigger_init() fails when alloc_hist_pad() cannot allocate, and nothing takes the trigger back off the list on the way out. event_hist_trigger_parse() frees it, and the next lookup by name reads the freed object: BUG: KASAN: slab-use-after-free in find_named_trigger+0xac/0xc0 Read of size 8 at addr ffff888009346860 by task init/1 find_named_trigger+0xac/0xc0 hist_register_trigger+0xc1/0xa00 event_hist_trigger_parse+0x3146/0x6af0 event_trigger_write+0xce/0x160 Freed by task 67: kfree+0x154/0x420 trigger_kthread_fn+0xfd/0x160 Do the reference first and publish once it has succeeded, so that nothing which can fail runs after the trigger becomes findable. Cc: stable@vger.kernel.org Fixes: 7ab0fc61ce73 ("tracing: Move histogram trigger variables from stack to per CPU structure") Reported-by: Sashiko AI Closes: https://lore.kernel.org/linux-trace-kernel/20260907092944.3950E1F00A3D@smtp.kernel.org/ Link: https://patch.msgid.link/20260907124420.607097-2-donggeunyoo.kernel@gmail.com Signed-off-by: Donggeun Yoo Acked-by: Tom Zanussi Signed-off-by: Steven Rostedt --- kernel/trace/trace_events_hist.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 1889e310b73c..54c95f9bd0a3 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -6371,17 +6371,18 @@ static int event_hist_trigger_named_init(struct event_trigger_data *data) { int ret; - data->ref++; - - save_named_trigger(data->named_data->name, data); - ret = event_hist_trigger_init(data->named_data); if (ret < 0) { kfree(data->cmd_ops); data->cmd_ops = &trigger_hist_cmd; + return ret; } - return ret; + data->ref++; + + save_named_trigger(data->named_data->name, data); + + return 0; } static void event_hist_trigger_named_free(struct event_trigger_data *data) From 92383cef66791a0c63a2f27755cadbdb2fbf270b Mon Sep 17 00:00:00 2001 From: Donggeun Yoo Date: Mon, 7 Sep 2026 21:44:20 +0900 Subject: [PATCH 1158/1198] tracing: Undo the registration when enabling the histogram trigger fails Commit 6f86bdeab633 ("tracing: Fix bad hist from corrupting named_triggers list") described how a trigger that is registered but not on file->triggers ends up freed while still on the global named_triggers list, and moved the registration down so that hist_trigger_enable() follows it immediately. One path still gets there. hist_trigger_enable() adds the trigger and takes it straight back out when the event cannot be enabled: list_add_tail_rcu(&data->list, &file->triggers); update_cond_flag(file); if (trace_event_trigger_enable_disable(file, 1) < 0) { list_del_rcu(&data->list); update_cond_flag(file); ret--; } so the list walk in hist_unregister_trigger() matches nothing, test stays NULL, and the ->free() that would call del_named_trigger() is skipped. out_unreg falls through to out_free, which frees the trigger anyway: BUG: KASAN: slab-use-after-free in find_named_trigger+0xac/0xc0 Read of size 8 at addr ffff8880091d3160 by task init/1 find_named_trigger+0xac/0xc0 hist_register_trigger+0xc1/0xa00 event_hist_trigger_parse+0x3146/0x6af0 event_trigger_write+0xce/0x160 Freed by task 69: kfree+0x154/0x420 trigger_kthread_fn+0xfd/0x160 Leave the trigger where hist_unregister_trigger() can find it and let that undo the registration, which is the only code that knows all of what cmd_ops->init() took: the named list entry, the hist_pad reference, the reference on the trigger a named histogram is shared with, and the copied cmd_ops. It also pairs the failed trace_event_trigger_enable_disable(), whose sm_ref and buffered event reference are otherwise left behind. Since ->free() releases trigger_data and, for a trigger that does not share its histogram, hist_data with it, out_unreg can no longer fall through to out_free. For a trigger that does share, hist_register_trigger() has already destroyed the caller's hist_data, so the fall-through was reading freed memory there as well. Move the enable_timestamps check in hist_unregister_trigger() above the ->free() call for the same reason: hist_data does not outlive it once the trigger being removed is the one that owns it. Cc: stable@vger.kernel.org Fixes: 067fe038e70f ("tracing: Add variable reference handling to hist triggers") Reported-by: Sashiko AI Closes: https://lore.kernel.org/linux-trace-kernel/20260907092944.3950E1F00A3D@smtp.kernel.org/ Link: https://patch.msgid.link/20260907124420.607097-3-donggeunyoo.kernel@gmail.com Signed-off-by: Donggeun Yoo Signed-off-by: Steven Rostedt --- kernel/trace/trace_events_hist.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 54c95f9bd0a3..53100287466f 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -6670,11 +6670,12 @@ static int hist_trigger_enable(struct event_trigger_data *data, update_cond_flag(file); - if (trace_event_trigger_enable_disable(file, 1) < 0) { - list_del_rcu(&data->list); - update_cond_flag(file); + /* + * On failure the caller undoes the registration, and + * hist_unregister_trigger() can only find the trigger here. + */ + if (trace_event_trigger_enable_disable(file, 1) < 0) ret--; - } return ret; } @@ -6752,13 +6753,13 @@ static void hist_unregister_trigger(char *glob, } } - if (test && test->cmd_ops->free) - test->cmd_ops->free(test); - if (hist_data->enable_timestamps) { if (!hist_data->remove || test) tracing_set_filter_buffering(file->tr, false); } + + if (test && test->cmd_ops->free) + test->cmd_ops->free(test); } static bool hist_file_check_refs(struct trace_event_file *file) @@ -6963,6 +6964,8 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops, return ret; out_unreg: event_trigger_unregister(cmd_ops, file, glob+1, trigger_data); + /* The unregister frees trigger_data, skip out_free */ + goto out; out_free: remove_hist_vars(hist_data); From a5e70ba87ca8ebc79b4e63de302d03b0625fe153 Mon Sep 17 00:00:00 2001 From: Donggeun Yoo Date: Tue, 8 Sep 2026 00:50:44 +0900 Subject: [PATCH 1159/1198] tracing: Fix memory corruption from the histogram stacktrace modifier parse_field() sets HIST_FIELD_FL_STACKTRACE from the ".stacktrace" modifier before it looks the field name up, and nothing afterwards checks that the name resolved to a field which holds a stacktrace. create_hist_field() picks HIST_FIELD_FN_STACK on the strength of the field pointer alone, which reads a __data_loc word from the record and follows its low 16 bits as an offset into the same record. event_hist_trigger() takes the first word there as an entry count and copies that many longs into a 31 entry array: n_entries = *stack; memcpy(entries, ++stack, n_entries * sizeof(unsigned long)); Neither end of that copy is bounded, and the count is whatever the event holds at the offset, so any field will do: # cd /sys/kernel/tracing/events/sched/sched_process_fork # echo 'hist:keys=parent_pid.stacktrace' > trigger # (true) BUG: kernel NULL pointer dereference, address: 0000000000000008 RIP: 0010:rb_insert_color+0x18/0x130 timerqueue_linked_add+0x7e/0xd0 enqueue_hrtimer+0x39/0xb0 __hrtimer_run_queues+0x10f/0x1f0 RIP: 0010:memcpy+0xc/0x30 event_hist_trigger+0x165/0x690 The timer interrupt landed on the rbtree the copy had already run over. No debug options are needed for this; KASAN reports the same write as an out-of-bounds read of 13835058055416381440 bytes. Documentation/trace/histogram.rst already states the rule, "must be a long[] type", so enforce it once the name has been resolved. Names which resolve to no field at all, "hitcount.stacktrace" and the common_* pseudo-fields, are refused for the same reason: they hold no stacktrace to read. Cc: stable@vger.kernel.org Fixes: cc5fc8bfc961 ("tracing/histogram: Add stacktrace type") Link: https://patch.msgid.link/20260907155045.692664-2-donggeunyoo.kernel@gmail.com Signed-off-by: Donggeun Yoo Signed-off-by: Steven Rostedt --- kernel/trace/trace_events_hist.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 53100287466f..9bc829c1e876 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -2317,6 +2317,7 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, struct ftrace_event_field *field = NULL; char *field_name, *modifier, *str; struct trace_array *tr = file->tr; + bool stack_modifier = false; modifier = str = kstrdup(field_str, GFP_KERNEL); if (!modifier) @@ -2339,9 +2340,10 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, *flags |= HIST_FIELD_FL_EXECNAME; else if (strcmp(modifier, "syscall") == 0) *flags |= HIST_FIELD_FL_SYSCALL; - else if (strcmp(modifier, "stacktrace") == 0) + else if (strcmp(modifier, "stacktrace") == 0) { *flags |= HIST_FIELD_FL_STACKTRACE; - else if (strcmp(modifier, "log2") == 0) + stack_modifier = true; + } else if (strcmp(modifier, "log2") == 0) *flags |= HIST_FIELD_FL_LOG2; else if (strcmp(modifier, "usecs") == 0) *flags |= HIST_FIELD_FL_TIMESTAMP_USECS; @@ -2412,6 +2414,12 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, } } } + + if (stack_modifier && + (!field || field->filter_type != FILTER_STACKTRACE)) { + hist_err(tr, HIST_ERR_BAD_FIELD_MODIFIER, errpos(field_str)); + field = ERR_PTR(-EINVAL); + } out: kfree(str); From 7f711e62355bb3123a2ca2f97a2facbfebc678c6 Mon Sep 17 00:00:00 2001 From: Donggeun Yoo Date: Tue, 8 Sep 2026 00:50:45 +0900 Subject: [PATCH 1160/1198] tracing: Fix memory corruption from a "STACKTRACE" histogram key "cpu", "CPU", "stacktrace" and "STACKTRACE" are generic fields, defined with an offset and a size of zero so that the filter code can match them by name. parse_field() maps them onto their common_* equivalents for backward compatibility, but unlike the common_* names it hands the placeholder back to the caller instead of NULL. create_hist_field() takes a non-NULL field as a promise that the record carries a stacktrace and picks HIST_FIELD_FN_STACK, so the __data_loc word is read from offset 0, that is from common_type, and its low 16 bits are followed as an offset into the record. What is found there becomes the length of an unbounded memcpy. Pick an event whose id is small enough that the offset stays inside its own record and the length is a kernel text address: # cd /sys/kernel/tracing # echo 'hist:keys=STACKTRACE' > events/ftrace/print/trigger # echo hello > trace_marker Oops: general protection fault, probably for non-canonical address RIP: 0010:rb_next+0x23/0x60 RIP: 0010:memcpy+0xc/0x30 event_hist_trigger+0x2e7/0x12c0 Kernel panic - not syncing: Fatal exception in interrupt Leave the field NULL, which is what the comment above the branch says the code does and what common_stacktrace already does. FILTER_CPU and FILTER_COMM are left alone, their create_hist_field() branches never look at the field. Cc: stable@vger.kernel.org Fixes: 4b512860bdbd ("tracing: Rename stacktrace field to common_stacktrace") Link: https://patch.msgid.link/20260907155045.692664-3-donggeunyoo.kernel@gmail.com Signed-off-by: Donggeun Yoo Signed-off-by: Steven Rostedt --- kernel/trace/trace_events_hist.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 9bc829c1e876..8af97fd4ee2d 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -2404,6 +2404,7 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, *flags |= HIST_FIELD_FL_CPU; } else if (field && field->filter_type == FILTER_STACKTRACE) { *flags |= HIST_FIELD_FL_STACKTRACE; + field = NULL; } else if (field && field->filter_type == FILTER_COMM) { *flags |= HIST_FIELD_FL_COMM | HIST_FIELD_FL_STRING; } else { From 911002e99e15f640f1fdc6d276206beaef59e790 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Tue, 8 Sep 2026 08:22:15 +0200 Subject: [PATCH 1161/1198] tracing: Restore :mod: trailer after parsing in ftrace_set_clr_event() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit While ftrace_set_clr_event() modifies its input buffer during parsing, before returning to the caller the buffer is supposed to be restored to its original state. This works correctly for the colon between the subsystem and event but not the colon at the beginning of :mod:. Restore the colon, so the :mod: trailer is not stripped after ftrace_set_clr_event(). Cc: stable@vger.kernel.org Fixes: 4c86bc531e60 ("tracing: Add :mod: command to enabled module events") Link: https://patch.msgid.link/20260908-tracing-cli-event-filter-v2-1-05396a3fb663@linutronix.de Signed-off-by: Thomas Weißschuh Signed-off-by: Steven Rostedt --- kernel/trace/trace_events.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 9dbc2441763b..30c0ddf90887 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1489,6 +1489,8 @@ int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set) /* Put back the colon to allow this to be called again */ if (buf) *(buf - 1) = ':'; + if (mod) + *(mod - 5) = ':'; return ret; } From 7e645147dfba67edb3ed3090a1ed1d89df77fc27 Mon Sep 17 00:00:00 2001 From: Karl Mehltretter Date: Wed, 9 Sep 2026 08:29:17 +0200 Subject: [PATCH 1162/1198] tracing: Fix ring_buffer_read_page_size() kernel-doc ring_buffer_read_page_size() takes a parameter named rpage, but its kernel-doc describes page. As a result, kernel-doc reports rpage as undescribed and page as an excess parameter description. Rename the documentation entry to match the function. Link: https://patch.msgid.link/20260909062917.89482-1-kmehltretter@gmail.com Fixes: dae8dda341d2 ("tracing: Fix subbuf resize races with trace_pipe_raw readers") Assisted-by: LLM Signed-off-by: Karl Mehltretter Reviewed-by: Vincent Donnefort Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 9c03a555a6ba..0e30c7bd6045 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -7384,7 +7384,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_read_page_data); /** * ring_buffer_read_page_size - get size of the read page. - * @page: the page to get the size from + * @rpage: the page to get the size from * * Returns size of the page in bytes. */ From ed0aff60f83a9bdc2f6556376ac79c96b3ce7e80 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 10 Sep 2026 22:12:09 -0400 Subject: [PATCH 1163/1198] tracing: Take trace_array reference when opening a tracer options file When a tracer option file is opened, it is passed a descriptor that points to an element on the trace_array's topts array. This element has information to find the trace array and other information. It uses this element to take a reference of the trace_array so that the trace_array does not get removed while this file is opened. Unfortunately, there's a race condition where the element itself could be freed by the removal of the instance the trace_array represents causing a use-after-free as this element that is used to find the trace_array to increment its reference counter is also freed when the instance is removed. To solve this, add a trace_array_tracer_options_get() helper function that will take the address of the element that is passed to the open function by the inode->i_private pointer and search all the trace_arrays under a lock to find the one that the element's address is in the range of the trace_arrays topts array elements. When a match happens, that trace_array's reference would be increased. Note, there's a race where if an admin was deleting and creating trace instances at the same time and the memory of the old trace_array's array matched the memory of the new trace_array that it could in theory open the option from the wrong trace array. But we do not care because it would be stupid to perform that kind of action. As long as the only thing that can happen is that the option from the wrong trace array is used and doesn't crash the kernel it will only make the user confused. But if they are doing something stupid like this, they are already confused, so no harm done. Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260910221209.62dad8d3@robin Fixes: 7e2cfbd2d3c86 ("tracing: Have option files inc the trace array ref count") Reported-by: sashiko-bot@kernel.org Closes: https://lore.kernel.org/linux-trace-kernel/20260902121918.5a9e9d1b@gandalf.local.home/ Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 46 +++++++++++++++++++++++++++++++++++++++++++- kernel/trace/trace.h | 1 + 2 files changed, 46 insertions(+), 1 deletion(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 8658cad53cb5..e4a490d3d08c 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -7717,12 +7717,55 @@ trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt, return cnt; } +static bool tr_option_match(struct trace_array *tr, void *topt) +{ + for (int i = 0; i < tr->nr_topts; i++) { + struct trace_options *tr_topts = &tr->topts[i]; + + if (topt >= (void *)&tr_topts->topts[0] && + topt < (void *)&tr_topts->topts[tr_topts->nr_topts]) + return true; + } + return false; +} + +/* + * The topt is the address of a trace_array->topts[] element that holds the + * the tracer options descriptor. But since the trace_array reference has not + * been taken yet, it cannot be dereferenced as it could have been freed by + * a rmdir of the instance the trace_array represents. + * + * Search the list of trace_arrays and compare the topt to the address of + * the entire trace_array topts array for each trace_array in the list. + * If one is matched, then take the reference and return it. If not, the + * trace_array no longer exits. + */ +static int trace_array_tracer_options_get(void *topt) +{ + struct trace_array *tr; + int ret; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + + if (tracing_disabled) + return -ENODEV; + + guard(mutex)(&trace_types_lock); + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + if (tr_option_match(tr, topt)) + return __trace_array_get(tr); + } + return -ENODEV; +} + static int tracing_open_options(struct inode *inode, struct file *filp) { struct trace_option_dentry *topt = inode->i_private; int ret; - ret = tracing_check_open_get_tr(topt->tr); + ret = trace_array_tracer_options_get(topt); if (ret) return ret; @@ -7984,6 +8027,7 @@ create_trace_option_files(struct trace_array *tr, struct tracer *tracer, tr->topts = tr_topts; tr->topts[tr->nr_topts].tracer = tracer; tr->topts[tr->nr_topts].topts = topts; + tr->topts[tr->nr_topts].nr_topts = cnt; tr->nr_topts++; for (cnt = 0; opts[cnt].name; cnt++) { diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 5e76f94e7a80..bd3c8f80300f 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -227,6 +227,7 @@ struct array_buffer { struct trace_options { struct tracer *tracer; struct trace_option_dentry *topts; + int nr_topts; }; struct trace_pid_list *trace_pid_list_alloc(void); From 815e07c8fe885a87751c2496a30ae0dcd4118210 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 11 Sep 2026 12:21:52 +0200 Subject: [PATCH 1164/1198] ring-buffer: Acquire the lock with irqsave in rb_wake_up_waiters() rb_wake_up_waiters() is a irq_work callback which is initialized with init_irq_work(). As such it will be invoked in thread context on PREEMPT_RT. Invoking the callback in IRQ context on PREEMPT_RT is not an option due its usage of wake_up_all(). Since this callback may run in thread context, it needs to acquire ring_buffer_per_cpu::reader_lock with disabling interrupts and may not assume that they are disabled. Use raw_spinlock_irqsave() to acquire ring_buffer_per_cpu::reader_lock. Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260911102152.YEtwkBj9@linutronix.de Fixes: 68282dd930ea3 ("ring-buffer: Fix resetting of shortest_full") Reviewed-by: Vincent Donnefort Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 0e30c7bd6045..9bc8ce8c5676 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -904,14 +904,13 @@ static void rb_wake_up_waiters(struct irq_work *work) struct ring_buffer_per_cpu *cpu_buffer = container_of(rbwork, struct ring_buffer_per_cpu, irq_work); - /* Called from interrupt context */ - raw_spin_lock(&cpu_buffer->reader_lock); - rbwork->wakeup_full = false; - rbwork->full_waiters_pending = false; + scoped_guard(raw_spinlock_irqsave, &cpu_buffer->reader_lock) { + rbwork->wakeup_full = false; + rbwork->full_waiters_pending = false; - /* Waking up all waiters, they will reset the shortest full */ - cpu_buffer->shortest_full = 0; - raw_spin_unlock(&cpu_buffer->reader_lock); + /* Waking up all waiters, they will reset the shortest full */ + cpu_buffer->shortest_full = 0; + } wake_up_all(&rbwork->full_waiters); } From 5225b8eec4c9bb21aecff6295fab6346a3c3738e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 11 Sep 2026 15:45:37 -0600 Subject: [PATCH 1165/1198] mailmap: update entry for Jens Axboe I recently changed jobs, let's update the .mailmap entry so that patches are attributed to the right (current) company. Signed-off-by: Jens Axboe Signed-off-by: Linus Torvalds --- .mailmap | 1 + 1 file changed, 1 insertion(+) diff --git a/.mailmap b/.mailmap index 7c02242d4ed7..29c556cf597b 100644 --- a/.mailmap +++ b/.mailmap @@ -421,6 +421,7 @@ Jens Axboe Jens Axboe Jens Axboe Jens Axboe +Jens Axboe Jens Osterkamp Jens Wiklander Jernej Skrabec From b4dcc18b97913888e8d009624e07c8014ce41b84 Mon Sep 17 00:00:00 2001 From: Leon Hwang Date: Fri, 11 Sep 2026 22:25:12 +0800 Subject: [PATCH 1166/1198] ftrace: Use rcu_assign_pointer() for tmp_ops filter hash tmp_ops.func_hash->filter_hash is annotated __rcu, but update_ftrace_direct_mod() assigns hash to it directly. Sparse reports an address-space mismatch. Use rcu_assign_pointer() for the assignment. Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260911142512.19344-1-leon.hwang@linux.dev Fixes: 50b35c9e50a8 ("ftrace: Use hash argument for tmp_ops in update_ftrace_direct_mod") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202609110704.Q3M5vCDV-lkp@intel.com/ Signed-off-by: Leon Hwang Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 53d5db60bfa5..673a54fdf392 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -6675,7 +6675,7 @@ int update_ftrace_direct_mod(struct ftrace_ops *ops, struct ftrace_hash *hash, b /* Enable the tmp_ops to have the same functions as the hash object. */ ftrace_ops_init(&tmp_ops); - tmp_ops.func_hash->filter_hash = hash; + rcu_assign_pointer(tmp_ops.func_hash->filter_hash, hash); err = register_ftrace_function_nolock(&tmp_ops); if (err) From bcfe2816e6ec46c3f4c58aa4264476665ddb3f69 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ali=20Ahmet=20Memi=C5=9F?= Date: Fri, 11 Sep 2026 18:56:47 +0300 Subject: [PATCH 1167/1198] tracing: Don't dereference trace_event_file in deferred trigger free MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The enable_event trigger defers trace_event_put_ref() to the trigger free kthread, but the trace_event_file can already be freed when the instance is removed. Keep the trace_event_call directly in enable_trigger_data so the deferred free does not access the freed trace_event_file. Cc: stable@vger.kernel.org Fixes: e091351b3881 ("tracing: Delay module ref count for "enable_event" trigger") Reported-by: Alexander Gordeev Closes: https://lore.kernel.org/all/20260828134340.2501683A24-agordeev@linux.ibm.com/ Link: https://patch.msgid.link/20260911155650.354844-1-aliamemis@disroot.org Signed-off-by: Ali Ahmet Memiş Signed-off-by: Steven Rostedt --- kernel/trace/trace.h | 1 + kernel/trace/trace_events_trigger.c | 4 +++- 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index bd3c8f80300f..3749485a7d85 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1953,6 +1953,7 @@ struct event_trigger_data { struct enable_trigger_data { struct trace_event_file *file; + struct trace_event_call *call; bool enable; bool hist; }; diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 149300cc5e8a..4d2fde996c0f 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -1728,7 +1728,8 @@ static void enable_trigger_private_data_free(struct event_trigger_data *data) { struct enable_trigger_data *enable_data = data->private_data; - trace_event_put_ref(enable_data->file->event_call); + /* The file may already be freed here, only the call is kept alive */ + trace_event_put_ref(enable_data->call); kfree(enable_data); } @@ -1801,6 +1802,7 @@ int event_enable_trigger_parse(struct event_command *cmd_ops, enable_data->hist = hist; enable_data->enable = enable; enable_data->file = event_enable_file; + enable_data->call = event_enable_file->event_call; trigger_data = trigger_data_alloc(cmd_ops, cmd, param, enable_data); if (!trigger_data) From 06bb43d8c79762fa3452f292cd080e54bef5d431 Mon Sep 17 00:00:00 2001 From: Vlad Poenaru Date: Wed, 2 Sep 2026 09:13:47 -0700 Subject: [PATCH 1168/1198] kbuild: don't delete in-flight filechk temporaries in asm-headers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 2d69b891e646 ("kbuild: Support generated asm-headers in subdirectories") switched the stale-wrapper sweep in scripts/Makefile.asm-headers from $(wildcard $(obj)/*.h) to a find(1) invocation, so that generated headers in subdirectories are considered. The two do not match the same set of files. Make's $(wildcard) uses glob semantics, where a leading '.' has to be matched explicitly, whereas find's -name uses fnmatch() without FNM_PERIOD, so '*.h' matches dotfiles as well. filechk writes its output to $(dir $@).tmp_$(notdir $@) before renaming it into place, so such a scratch file, if it happens to exist in $(obj) when the sub-make is parsed, is now picked up in old-headers. It appears in neither generic-y, generated-y nor syscall-y, is therefore classified as unwanted, and cmd_remove deletes it. On x86 this races with archprepare, which lists both asm-generic and arch/x86/include/generated/asm/cpufeaturemasks.h as prerequisites. Under -j they run concurrently against the same directory, and the build fails intermittently: mv: cannot stat 'arch/x86/include/generated/asm/.tmp_cpufeaturemasks.h': No such file or directory make[1]: *** [arch/x86/Makefile:269: arch/x86/include/generated/asm/cpufeaturemasks.h] Error 1 The same commit also converted the generic wrapper rule to filechk, so those wrappers now create .tmp_*.h in $(obj) too and can race among themselves. Restore the previous behaviour by excluding dotfiles from the sweep. Subdirectories, which is what the find(1) conversion was for, keep being descended into. While at it, quote the -name argument: it is currently expanded by the shell against the build directory before find sees it. Fixes: 2d69b891e646 ("kbuild: Support generated asm-headers in subdirectories") Signed-off-by: Vlad Poenaru Reviewed-by: Nathan Chancellor Reviewed-by: Thomas Weißschuh Reviewed-by: Nicolas Schier Link: https://patch.msgid.link/20260902161347.4163577-1-vlad.wing@gmail.com Signed-off-by: Nicolas Schier --- scripts/Makefile.asm-headers | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/Makefile.asm-headers b/scripts/Makefile.asm-headers index b38931314ad7..f1c3d287c14b 100644 --- a/scripts/Makefile.asm-headers +++ b/scripts/Makefile.asm-headers @@ -48,7 +48,7 @@ syscall-y := $(addprefix $(obj)/, $(syscall-y)) generated-y := $(addprefix $(obj)/, $(generated-y)) # Remove stale wrappers when the corresponding files are removed from generic-y -old-headers := $(shell test -d $(obj) && find $(obj) -name *.h) +old-headers := $(shell test -d $(obj) && find $(obj) -name '*.h' ! -name '.*') unwanted := $(filter-out $(generic-y) $(generated-y) $(syscall-y),$(old-headers)) filechk_wrap = echo "\#include " From 4f73462856576797b8f3c55564a9be99f76dc67b Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Mon, 31 Aug 2026 18:46:31 -0700 Subject: [PATCH 1169/1198] scripts/sorttable: Mark long_size as __maybe_unused When building in a kernel tree prior to commit b055f4c431e3 ("sorttable: Move ELF parsing into scripts/elf-parse.[ch]") with clang-23 or newer, which implements a new warning under -Wunused-but-set-variable for static global variable, there is a warning from sorttable because long_size is unused when MCOUNT_SORT_ENABLED is not set: scripts/sorttable.c:452:12: error: variable 'long_size' set but not used [-Werror,-Wunused-but-set-global] 452 | static int long_size; | ^ Mark long_size as __maybe_unused to avoid inserting more ugly #ifdef directives while insuring the warning does not reappear, as the aforementioned change does not alter the uses of long_size, so it appears to be coincidence that the warning disappears after this refactoring. Cc: stable@vger.kernel.org Signed-off-by: Nathan Chancellor Tested-by: Nicolas Schier Link: https://patch.msgid.link/20260831-sorttable-long_size-unused-but-set-global-v1-1-8a96b88697e5@kernel.org Signed-off-by: Nicolas Schier --- scripts/sorttable.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/sorttable.c b/scripts/sorttable.c index d8dc2a1b7c31..d7b50581c732 100644 --- a/scripts/sorttable.c +++ b/scripts/sorttable.c @@ -116,7 +116,7 @@ static inline void *get_index(void *start, int entsize, int index) } static int extable_ent_size; -static int long_size; +static int long_size __maybe_unused; #define ERRSTR_MAXSZ 256 From 281b61d408d4c39544583e393c6707af0ef5ee50 Mon Sep 17 00:00:00 2001 From: "Lorenzo Stoakes (ARM)" Date: Tue, 8 Sep 2026 21:55:01 +0100 Subject: [PATCH 1170/1198] scripts/mksysmap: drop the MODULE_INFO() symbols from kallsyms Commit 3e86e4d74c04 ("kbuild: keep .modinfo section in vmlinux.unstripped") keeps .modinfo symbols out of System.map and kallsyms, which assumes unique IDs have a format like '__UNIQUE_ID_modinfo123'. However, commit afb026b6d35c ("compiler: Tweak __UNIQUE_ID() naming"), sent in the same cycle, changes this to '__UNIQUE_ID_modinfo_123'. As a result this regexp has never matched and every kernel since v6.18 has carried one kallsyms entries for every MODULE_INFO() declaration in the kernel whether the modules are compiled or not. That's 5,810 entries for an x86 defconfig build and 15,200 for arm64. On x86 defconfig that is 113 KiB of kallsyms tables and 32 KiB of bzImage, and every lookup walks past them. Fix the pattern. Fixes: 3e86e4d74c04 ("kbuild: keep .modinfo section in vmlinux.unstripped") Assisted-by: LLM Signed-off-by: Lorenzo Stoakes (ARM) Reviewed-by: Nicolas Schier Reviewed-by: Nathan Chancellor Link: https://patch.msgid.link/20260908-build-speedup-v1-1-5dc1ac01672d@kernel.org Signed-off-by: Nicolas Schier --- scripts/mksysmap | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/mksysmap b/scripts/mksysmap index c4531eacde20..56a8b8bbdb37 100755 --- a/scripts/mksysmap +++ b/scripts/mksysmap @@ -83,7 +83,7 @@ / _SDA2_BASE_$/d # MODULE_INFO() -/ __UNIQUE_ID_modinfo[0-9]*$/d +/ __UNIQUE_ID_modinfo_[0-9]*$/d # --------------------------------------------------------------------------- # Ignored patterns From 59351365ac271b5e0eb180f211c531476a36221f Mon Sep 17 00:00:00 2001 From: "Lorenzo Stoakes (ARM)" Date: Tue, 8 Sep 2026 21:55:02 +0100 Subject: [PATCH 1171/1198] scripts/mksysmap: fix escape of '$' in the __pi_ pattern Commit b18b047002b7 ("kbuild: change scripts/mksysmap into sed script") converted scripts/mksysmap from a shell script to a sed script. However an error was made - escaping of '$' required \\ escaping in shell but only \ in a sed script. This was mostly corrected in commit 7a6c355b55c0 ("scripts/mksysmap: Fix escape chars '$'"), but this fix missed arm64 PIE namespace local symbols like __pi_$x and __pi_$d which appear in System.map and /proc/kallsyms: $ grep __pi_\\$ /proc/kallsyms | sort -u 0000000000000000 d __pi_$d 0000000000000000 t __pi_$x Fix the escaping properly. Fixes: b18b047002b7 ("kbuild: change scripts/mksysmap into sed script") Assisted-by: LLM Signed-off-by: Lorenzo Stoakes (ARM) Reviewed-by: Nathan Chancellor Reviewed-by: Nicolas Schier Link: https://patch.msgid.link/20260908-build-speedup-v1-2-5dc1ac01672d@kernel.org Signed-off-by: Nicolas Schier --- scripts/mksysmap | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/mksysmap b/scripts/mksysmap index 56a8b8bbdb37..856b26ba2ac0 100755 --- a/scripts/mksysmap +++ b/scripts/mksysmap @@ -35,7 +35,7 @@ / __efistub_/d # arm64 local symbols in PIE namespace -/ __pi_\\$/d +/ __pi_\$/d / __pi_\.L/d # arm64 local symbols in non-VHE KVM namespace From 442ffa742daa65a0e8fe003abe9fbe472366e4de Mon Sep 17 00:00:00 2001 From: Vincent Donnefort Date: Fri, 11 Sep 2026 20:39:35 +0100 Subject: [PATCH 1172/1198] tracing/remotes: Account for ring buffer page header in size calculation trace_buffer_desc_size() and trace_remote_alloc_buffer() undercount the required pages because every ring buffer page contains a header (BUF_PAGE_HDR_SIZE). Account for that header to ensure allocated remote ring buffers aren't smaller than requested by the user. The newly introduced helper __calc_nr_pages_ring_buffer_desc() can return a value that overflows the descriptor nr_pages field (32 bits). Link: https://patch.msgid.link/20260911193937.602202-2-vdonnefort@google.com Fixes: 2e67fabd8b77 ("ring-buffer: Introduce ring-buffer remotes") Signed-off-by: Vincent Donnefort Signed-off-by: Steven Rostedt --- include/linux/ring_buffer.h | 15 +++++++++++++-- kernel/trace/trace_remote.c | 2 +- 2 files changed, 14 insertions(+), 3 deletions(-) diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index afc7daa6ee7d..11bffb6a142d 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -3,8 +3,9 @@ #define _LINUX_RING_BUFFER_H #include -#include #include +#include +#include #include @@ -279,9 +280,19 @@ static inline struct ring_buffer_desc *__first_ring_buffer_desc(struct trace_buf return (struct ring_buffer_desc *)(&desc->__data[0]); } +/* + * Returns the number of pages for a ring_buffer_desc. The caller must ensure it + * does not overflow ring_buffer_desc::nr_page_va. + */ +static inline unsigned long __calc_nr_pages_ring_buffer_desc(size_t size) +{ + /* Takes into account the reader page */ + return max(DIV_ROUND_UP(size, PAGE_SIZE - BUF_PAGE_HDR_SIZE), 2UL) + 1; +} + static inline size_t trace_buffer_desc_size(size_t buffer_size, unsigned int nr_cpus) { - unsigned int nr_pages = max(DIV_ROUND_UP(buffer_size, PAGE_SIZE), 2UL) + 1; + unsigned long nr_pages = __calc_nr_pages_ring_buffer_desc(buffer_size); struct ring_buffer_desc *rbdesc; return size_add(offsetof(struct trace_buffer_desc, __data), diff --git a/kernel/trace/trace_remote.c b/kernel/trace/trace_remote.c index 75fa1ffc4c96..c17902e42ef1 100644 --- a/kernel/trace/trace_remote.c +++ b/kernel/trace/trace_remote.c @@ -980,7 +980,7 @@ int trace_remote_alloc_buffer(struct trace_buffer_desc *desc, size_t desc_size, const struct cpumask *cpumask) { size_t min_desc_size = trace_buffer_desc_size(buffer_size, cpumask_weight(cpumask)); - unsigned int nr_pages = max(DIV_ROUND_UP(buffer_size, PAGE_SIZE), 2UL) + 1; + unsigned int nr_pages = __calc_nr_pages_ring_buffer_desc(buffer_size); struct ring_buffer_desc *rb_desc; int cpu, ret = -ENOMEM; From d059d8bf2c9b5d563d15e7552d73e17d7535013a Mon Sep 17 00:00:00 2001 From: Vincent Donnefort Date: Fri, 11 Sep 2026 20:39:36 +0100 Subject: [PATCH 1173/1198] tracing/remotes: Catch nr_page_va overflow in ring_buffer_desc sizing The number of pages per remote ring buffer is capped by ring_buffer_desc::nr_page_va (32 bits). A buffer_size large enough to overflow that field would silently allocate a descriptor smaller than what was asked for. Return SIZE_MAX from trace_buffer_desc_size() on nr_page_va overflow. Link: https://patch.msgid.link/20260911193937.602202-3-vdonnefort@google.com Fixes: 2e67fabd8b77 ("ring-buffer: Introduce ring-buffer remotes") Signed-off-by: Vincent Donnefort Signed-off-by: Steven Rostedt --- include/linux/ring_buffer.h | 4 ++++ kernel/trace/trace_remote.c | 6 +++++- 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 11bffb6a142d..eac3e9080c3c 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -295,6 +295,10 @@ static inline size_t trace_buffer_desc_size(size_t buffer_size, unsigned int nr_ unsigned long nr_pages = __calc_nr_pages_ring_buffer_desc(buffer_size); struct ring_buffer_desc *rbdesc; + /* Capped by ring_buffer_desc::nr_page_va */ + if (nr_pages > UINT_MAX) + return SIZE_MAX; + return size_add(offsetof(struct trace_buffer_desc, __data), size_mul(nr_cpus, struct_size(rbdesc, page_va, nr_pages))); } diff --git a/kernel/trace/trace_remote.c b/kernel/trace/trace_remote.c index c17902e42ef1..2d5bc423efca 100644 --- a/kernel/trace/trace_remote.c +++ b/kernel/trace/trace_remote.c @@ -980,9 +980,12 @@ int trace_remote_alloc_buffer(struct trace_buffer_desc *desc, size_t desc_size, const struct cpumask *cpumask) { size_t min_desc_size = trace_buffer_desc_size(buffer_size, cpumask_weight(cpumask)); - unsigned int nr_pages = __calc_nr_pages_ring_buffer_desc(buffer_size); struct ring_buffer_desc *rb_desc; int cpu, ret = -ENOMEM; + unsigned int nr_pages; + + if (min_desc_size == SIZE_MAX) + return -E2BIG; if (desc_size < min_desc_size) return -EINVAL; @@ -991,6 +994,7 @@ int trace_remote_alloc_buffer(struct trace_buffer_desc *desc, size_t desc_size, desc->struct_len = min_desc_size; rb_desc = __first_ring_buffer_desc(desc); + nr_pages = __calc_nr_pages_ring_buffer_desc(buffer_size); for_each_cpu(cpu, cpumask) { unsigned int id; From d860c67c051685abb0460b593b193f0f45f4fa92 Mon Sep 17 00:00:00 2001 From: David Carlier Date: Sat, 12 Sep 2026 11:39:38 +0100 Subject: [PATCH 1174/1198] ring-buffer: Check resize_disabled before publishing the new subbuf order ring_buffer_subbuf_order_set() stores the new order and only then walks the CPUs, returning -EBUSY if any of them has resizing disabled. A user mapped buffer has resizing disabled, and __rb_map_vma() reads buffer->subbuf_order without buffer->mutex, so an mmap of an already mapped CPU racing the failing order change sizes the mapping with the new order and inserts pages past the sub-buffer into the VMA. Check the CPUs before storing the new order. Cc: stable@vger.kernel.org Fixes: 117c39200d9d ("ring-buffer: Introducing ring-buffer mapping functions") Link: https://patch.msgid.link/20260912103938.1127021-1-devnexen@gmail.com Signed-off-by: David Carlier Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 9bc8ce8c5676..04bb94c29f58 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -7473,6 +7473,14 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order) old_capacity = rb_subbuf_capacity(buffer); + /* The mmap fast path reads subbuf_order without buffer->mutex. */ + for_each_buffer_cpu(buffer, cpu) { + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + continue; + if (atomic_read(&buffer->buffers[cpu]->resize_disabled)) + return -EBUSY; + } + atomic_inc(&buffer->record_disabled); /* Make sure all commits have finished */ From 1a296bfd3e775e515233f746218824fc7dd5ff16 Mon Sep 17 00:00:00 2001 From: Laxman Acharya Padhya Date: Sun, 16 Aug 2026 23:33:40 +0545 Subject: [PATCH 1175/1198] wifi: mt76: mt7921: skip unknown CLC firmware records Treat an out-of-range CLC index as newer firmware rather than a malformed image. linux-firmware 20260810 ships MT7922 records with idx 3, and rejecting them made mt7921e fail to probe. Keep the record-length checks, and report those as errors so a truncated table is visible instead of a silent retry loop. Fixes: 9417c5818a01 ("wifi: mt76: mt7921: validate CLC firmware records") Reported-by: Mikhail Gavrilov Signed-off-by: Laxman Acharya Padhya Reviewed-by: Junjie Cao Tested-by: Mikhail Gavrilov Signed-off-by: Linus Torvalds --- drivers/net/wireless/mediatek/mt76/mt7921/mcu.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c index a118a301564c..40546005c743 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c @@ -477,18 +477,23 @@ static int mt7921_load_clc(struct mt792x_dev *dev, const char *fw_name) for (offset = 0; offset < len; offset += clc_len) { if (len - offset < sizeof(*clc)) { + dev_err(mdev->dev, "Invalid CLC record\n"); ret = -EINVAL; goto out; } clc = (const struct mt7921_clc *)(clc_base + offset); clc_len = le32_to_cpu(clc->len); - if (clc_len < sizeof(*clc) || clc_len > len - offset || - clc->idx >= ARRAY_SIZE(phy->clc)) { + if (clc_len < sizeof(*clc) || clc_len > len - offset) { + dev_err(mdev->dev, "Invalid CLC record\n"); ret = -EINVAL; goto out; } + /* Newer firmware may add records this driver does not use yet */ + if (clc->idx >= ARRAY_SIZE(phy->clc)) + continue; + /* do not init buf again if chip reset triggered */ if (phy->clc[clc->idx]) continue; From 7825de3f75d184612d77655669a04ea0da252c17 Mon Sep 17 00:00:00 2001 From: Devin Wittmayer Date: Tue, 25 Aug 2026 11:17:12 -0700 Subject: [PATCH 1176/1198] wifi: mt76: mt792x: fix NULL dereference in ACPI SAR init during probe Some laptops carry a MediaTek power table in their firmware, and the driver reads it to set a transmit limit for each frequency range. It only fills in the ranges themselves when it registers the device. The startup step that does this existed already, but it never programmed anything. Two recent commits made it run a regulatory update instead, which sets the limits on the way through, long before registration. As a result, on a machine that has the table the driver reads through an empty pointer and the interface never appears: BUG: kernel NULL pointer dereference, address: 0000000000000004 RIP: 0010:mt792x_init_acpi_sar_power Call Trace: mt7921_set_tx_sar_pwr mt7921_mcu_regd_update mt7921_regd_update mt7921_run_firmware mt7921e_mcu_init mt7921_init_work Skip it when the ranges are missing. They are applied again once the device is up, which is where they came from before. Reported-by: Klara Modin Closes: https://lore.kernel.org/linux-wireless/aoyxqHYvSuaBeubf@soda.int.kasm.eu/ Fixes: 9b80bd9cab40 ("wifi: mt76: mt7921: add regulatory wiphy self manager support") Fixes: e9f3f1cc133f ("wifi: mt76: mt7925: add regulatory wiphy self manager support") Signed-off-by: Devin Wittmayer Tested-by: David Gow Tested-by: Klara Modin Signed-off-by: Linus Torvalds --- drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.c b/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.c index 946dd7956e4a..b468051fbe68 100644 --- a/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.c +++ b/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.c @@ -323,7 +323,8 @@ int mt792x_init_acpi_sar_power(struct mt792x_phy *phy, bool set_default) const struct cfg80211_sar_capa *capa = phy->mt76->hw->wiphy->sar_capa; int i; - if (!phy->acpisar || !((struct mt792x_acpi_sar *)phy->acpisar)->dyn) + if (!capa || !phy->acpisar || + !((struct mt792x_acpi_sar *)phy->acpisar)->dyn) return 0; /* When ACPI SAR enabled in HW, we should apply rules for .frp From 856c562c94964a74f63c6d5f38a1509a59a2357d Mon Sep 17 00:00:00 2001 From: Sergey Zagursky Date: Wed, 2 Sep 2026 22:15:24 +0100 Subject: [PATCH 1177/1198] media: ipu-bridge: do not use the CVS device lookup for IVSC Since commit c6b1b34b5090 ("media: pci: intel: Add CVS support for IPU bridge driver") the internal camera no longer works on laptops where the sensor sits behind an IVSC, for example a Dell XPS 16 9640 (IPU6, INTC10CF, ov02c10): intel-ipu6 0000:00:05.0: Found supported sensor OVTI02C1:00 intel-ipu6 0000:00:05.0: Connected 1 cameras ivsc_csi intel_vsc-92335fcf-3203-4472-af93-7b4453ac29da: mei-csi probed without device fwnode! No sensor subdevice is registered, the media graph has no sensor entity and userspace finds no camera at all. ipu_bridge_get_ivsc_csi_dev() first looks for the platform device named "intel_vsc" and returns its mei-csi child. That device is created by mei_vsc, which on this machine only appears once the LJCA USB bridge and its SPI controller have probed, about a second after the IPU6 probe that runs the bridge: 07:59:29.297 platform INTC10CF:00 created (ACPI scan) 07:59:41 intel-ipu6 probe -> ipu_bridge_init() 07:59:42.391 platform intel_vsc created (mei_vsc) The commit above added two fallbacks for CVS which match on the ACPI companion alone. They are reached for every entry of ivsc_acpi_ids[], IVSC IDs included. The IVSC ACPI device has two physical nodes: INTC10CF:00/physical_node -> platform/INTC10CF:00 (no driver bound) INTC10CF:00/physical_node1 -> platform/intel_vsc (mei_vsc) so bus_find_device_by_acpi_dev(&platform_bus_type, adev) returns the bare platform device. ipu_bridge_instantiate_ivsc() then attaches the IVSC software node to that device instead of to the mei-csi client, the bridge reports success, and the probe is never retried. mei_csi later probes without a fwnode, the CSI-2 link is never described, and the sensor ACPI device, which has an honoured _DEP on the IVSC device, is never enumerated. Before those fallbacks existed the lookup returned NULL here, the bridge failed with -ENODEV and the probe was retried once the IVSC device had shown up. Skip those fallbacks for IVSC devices, keying on the IVSC IDs rather than the CVS ones: new CVS IDs keep being added, whereas the IVSC list is complete. CVS binds a driver to the ACPI device itself, so matching on the companion stays unambiguous there. Fixes: c6b1b34b5090 ("media: pci: intel: Add CVS support for IPU bridge driver") Link: https://lore.kernel.org/linux-media/20260901194526.6369-1-gvozdoder@gmail.com/ Cc: stable@vger.kernel.org Assisted-by: Claude Code:claude-opus-5 Signed-off-by: Sergey Zagursky Signed-off-by: Linus Torvalds --- drivers/media/pci/intel/ipu-bridge.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/drivers/media/pci/intel/ipu-bridge.c b/drivers/media/pci/intel/ipu-bridge.c index 1bb3a3e98d6b..bd64c0400c0d 100644 --- a/drivers/media/pci/intel/ipu-bridge.c +++ b/drivers/media/pci/intel/ipu-bridge.c @@ -232,6 +232,19 @@ static const struct acpi_device_id ivsc_acpi_ids[] = { { "INTC10FA" }, /* NVL */ }; +/* + * The subset of ivsc_acpi_ids[] which are IVSC, rather than CVS, devices. The + * CVS IDs are deliberately not listed here: new ones keep being added, whereas + * this list is complete. + */ +static const struct acpi_device_id ivsc_only_acpi_ids[] = { + { "INTC1059" }, + { "INTC1095" }, + { "INTC100A" }, + { "INTC10CF" }, + { } +}; + static struct acpi_device *ipu_bridge_get_ivsc_acpi_dev(struct acpi_device *adev) { unsigned int i; @@ -283,6 +296,17 @@ static struct device *ipu_bridge_get_ivsc_csi_dev(struct acpi_device *adev) return csi_dev; } + /* + * The lookups below match on the ACPI companion alone. That is fine for + * CVS, which binds a driver to that very device, but not for IVSC: there + * the ACPI device also has a driverless platform device, which would be + * returned instead of the mei-csi client. Return NULL for IVSC so that + * the caller fails and the probe is retried once the IVSC device shows + * up. + */ + if (!acpi_match_device_ids(adev, ivsc_only_acpi_ids)) + return NULL; + /* Try to locate CVS device on the I2C bus */ csi_dev = bus_find_device_by_acpi_dev(&i2c_bus_type, adev); if (csi_dev) From fd73f4a6659897191fa0d40695fe370925dd3780 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 13 Sep 2026 14:38:02 -0700 Subject: [PATCH 1178/1198] Linux 7.3-rc3 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 66654fa71655..0f1b80100b47 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 7 PATCHLEVEL = 3 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc3 NAME = Baby Opossum Posse # *DOCUMENTATION* From 88c4aff39452d7f0ab59f13730182a43bc7257c6 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Thu, 10 Sep 2026 13:10:46 +0100 Subject: [PATCH 1179/1198] ASoC: wm_adsp: Firmware search progress log should not look like an error In wm_adsp_request_firmware_file() only log the "Failed to request FILENAME" message when there is a real error (not when the file is missing). Add a new debug message to log the sequence of filenames tried during the file search. People have enabled debug messages, seen the "Failed to request" messages that are only logging the normal file search sequence, and reported them as errors. Signed-off-by: Richard Fitzgerald Link: https://patch.msgid.link/20260910121047.1592541-1-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- sound/soc/codecs/wm_adsp.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index 90c24c4b318e..b8f3035af3ba 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -775,9 +775,12 @@ static int wm_adsp_request_firmware_file(struct wm_adsp *dsp, s++; } + adsp_dbg(dsp, "Try '%s'\n", fw->filename); ret = wm_adsp_firmware_request(&fw->firmware, fw->filename, cs_dsp->dev); if (ret < 0) { - adsp_dbg(dsp, "Failed to request '%s': %d\n", fw->filename, ret); + if (ret != -ENOENT) + adsp_dbg(dsp, "Failed to request '%s': %d\n", fw->filename, ret); + kfree(fw->filename); fw->filename = NULL; if (ret != -ENOENT) From d56fe35c1bce1f547eb600695f60c139a508ff6e Mon Sep 17 00:00:00 2001 From: Jack Yu Date: Wed, 9 Sep 2026 16:54:49 +0800 Subject: [PATCH 1180/1198] ASoC: rt712-sdca: reconfigure PLL2 to fix calibration time-out Add pll2 reconfiguration sequence in order to fix calibration time-out issue and to support 24.576MHz MCLK on specific platforms. Signed-off-by: Jack Yu Link: https://patch.msgid.link/20260909085449.862350-1-jack.yu@realtek.com Signed-off-by: Mark Brown --- sound/soc/codecs/rt712-sdca-sdw.c | 8 +++ sound/soc/codecs/rt712-sdca.c | 86 +++++++++++++++++++++++++++++-- sound/soc/codecs/rt712-sdca.h | 18 +++++++ 3 files changed, 109 insertions(+), 3 deletions(-) diff --git a/sound/soc/codecs/rt712-sdca-sdw.c b/sound/soc/codecs/rt712-sdca-sdw.c index c50e74e20a88..edba0367d9ce 100644 --- a/sound/soc/codecs/rt712-sdca-sdw.c +++ b/sound/soc/codecs/rt712-sdca-sdw.c @@ -18,12 +18,16 @@ static bool rt712_sdca_readable_register(struct device *dev, unsigned int reg) { switch (reg) { + case 0x004d: case 0x201a ... 0x201f: case 0x2029 ... 0x202a: case 0x202d ... 0x2034: case 0x2230 ... 0x2232: case 0x2f01 ... 0x2f0a: case 0x2f35 ... 0x2f36: + case 0x2f3a: + case 0x2f3d: + case 0x2f41: case 0x2f50: case 0x2f54: case 0x2f58 ... 0x2f5d: @@ -48,6 +52,7 @@ static bool rt712_sdca_readable_register(struct device *dev, unsigned int reg) static bool rt712_sdca_volatile_register(struct device *dev, unsigned int reg) { switch (reg) { + case 0x004d: case 0x201b: case 0x201c: case 0x201d: @@ -56,6 +61,9 @@ static bool rt712_sdca_volatile_register(struct device *dev, unsigned int reg) case 0x2230: case 0x2f01: case 0x2f35: + case 0x2f3a: + case 0x2f3d: + case 0x2f41: case 0x320c: case SDW_SDCA_CTL(FUNC_NUM_JACK_CODEC, RT712_SDCA_ENT_GE49, RT712_SDCA_CTL_DETECTED_MODE, 0): case SDW_SDCA_CTL(FUNC_NUM_HID, RT712_SDCA_ENT_HID01, RT712_SDCA_CTL_HIDTX_CURRENT_OWNER, 0) ... diff --git a/sound/soc/codecs/rt712-sdca.c b/sound/soc/codecs/rt712-sdca.c index eda87eb9ab66..38052cb19790 100644 --- a/sound/soc/codecs/rt712-sdca.c +++ b/sound/soc/codecs/rt712-sdca.c @@ -73,14 +73,57 @@ static int rt712_sdca_index_update_bits(struct rt712_sdca_priv *rt712, return rt712_sdca_index_write(rt712, nid, reg, tmp); } +static void rt712_sdca_clk_patch(struct rt712_sdca_priv *rt712) +{ + rt712_sdca_index_write(rt712, RT712_VENDOR_REG, 0x65, 0x0000); + regmap_write(rt712->regmap, RT712_SDW_ROOT_CLK, 0x03); + usleep_range(1000, 1100); + regmap_write(rt712->regmap, RT712_SDW_ROOT_CLK, 0x02); + usleep_range(1000, 1100); + regmap_update_bits(rt712->regmap, RT712_PLL2_CONF2, 0x0080, 0x0000); + regmap_update_bits(rt712->regmap, RT712_PLL2_CONF2, 0x001f, 0x0017); + regmap_update_bits(rt712->regmap, RT712_PLL2_CONF3, 0x0010, 0x0000); + regmap_update_bits(rt712->regmap, RT712_PLL2_CONF1, 0x0081, 0x0001); + regmap_write(rt712->regmap, RT712_SDW_ROOT_CLK, 0x03); + usleep_range(1000, 1100); + regmap_update_bits(rt712->regmap, RT712_PLL2_CONF1, 0x0081, 0x0081); + regmap_update_bits(rt712->regmap, RT712_PLL2_CONF2, 0x0080, 0x0080); + regmap_update_bits(rt712->regmap, RT712_PLL2_CONF2, 0x001f, 0x0000); + regmap_update_bits(rt712->regmap, RT712_PLL2_CONF3, 0x0010, 0x0010); + usleep_range(1000, 1100); + rt712_sdca_index_write(rt712, RT712_VENDOR_REG, 0x65, 0x0081); +} + +static void rt712_sdca_clk_patch2(struct rt712_sdca_priv *rt712) +{ + rt712_sdca_index_update_bits(rt712, RT712_VENDOR_REG, 0x49, 0x0800, + 0x0000); + rt712_sdca_index_update_bits(rt712, RT712_VENDOR_REG, 0x49, 0xf000, + 0x0000); + rt712_sdca_index_write(rt712, RT712_VENDOR_REG, 0x65, 0x0000); + rt712_sdca_index_update_bits(rt712, RT712_VENDOR_ANALOG_CTL, 0x0c, 0xc000, + 0xc000); + rt712_sdca_index_update_bits(rt712, RT712_VENDOR_ANALOG_CTL, 0x00, 0xc000, + 0xc000); + rt712_sdca_index_write(rt712, RT712_VENDOR_REG, 0x65, 0x0081); + regmap_write(rt712->regmap, RT712_SDW_ROOT_CLK, 0x02); + usleep_range(1000, 1100); + regmap_write(rt712->regmap, RT712_SDW_ROOT_CLK, 0x03); + usleep_range(1000, 1100); + rt712_sdca_index_write(rt712, RT712_VENDOR_REG, 0x65, 0x0000); +} + static int rt712_sdca_calibration(struct rt712_sdca_priv *rt712) { unsigned int val, loop_rc = 0, loop_dc = 0; struct device *dev; struct regmap *regmap = rt712->regmap; + unsigned int clk_base; int chk_cnt = 100; int ret = 0; + regmap_read(rt712->regmap, RT712_SDW_ROOT_CLK, &clk_base); + mutex_lock(&rt712->calibrate_mutex); dev = regmap_get_device(regmap); @@ -109,8 +152,35 @@ static int rt712_sdca_calibration(struct rt712_sdca_priv *rt712) if (ret < 0) goto _cali_fail_; } - if (loop_dc == chk_cnt) - dev_err(dev, "%s, calibration time-out!\n", __func__); + + if (loop_dc == chk_cnt) { + if (clk_base == RT712_CLK_FREQ_24_576MHZ) { + rt712_sdca_clk_patch(rt712); + rt712_sdca_clk_patch2(rt712); + } + rt712_sdca_index_write(rt712, RT712_VENDOR_REG, RT712_FSM_CTL, 0x4100); + rt712_sdca_index_write(rt712, RT712_VENDOR_CALI, + RT712_DAC_DC_CALI_CTL1, 0x7883); + rt712_sdca_index_write(rt712, RT712_VENDOR_CALI, + RT712_DAC_DC_CALI_CTL1, 0xf893); + rt712_sdca_index_read(rt712, RT712_VENDOR_CALI, + RT712_DAC_DC_CALI_CTL1, &val); + + for (loop_dc = 0; loop_dc < chk_cnt && + (val & RT712_DAC_DC_CALI_TRIGGER); loop_dc++) { + usleep_range(10000, 11000); + ret = rt712_sdca_index_read(rt712, RT712_VENDOR_CALI, + RT712_DAC_DC_CALI_CTL1, &val); + + if (ret < 0) + goto _cali_fail_; + } + + if (loop_dc == chk_cnt) + dev_err(dev, "%s, calibration time-out!\n", __func__); + else + dev_dbg(dev, "%s, calibration success!\n", __func__); + } if (loop_dc == chk_cnt || loop_rc == chk_cnt) ret = -ETIMEDOUT; @@ -1759,9 +1829,13 @@ static void rt712_sdca_va_io_init(struct rt712_sdca_priv *rt712) static void rt712_sdca_vb_io_init(struct rt712_sdca_priv *rt712) { - int ret = 0; unsigned int jack_func_status, mic_func_status, amp_func_status; struct device *dev = &rt712->slave->dev; + unsigned int clk_base; + int ret = 0; + + regmap_read(rt712->regmap, RT712_SDW_ROOT_CLK, &clk_base); + dev_dbg(dev, "%s clk_base=%x", __func__, clk_base); regmap_read(rt712->regmap, SDW_SDCA_CTL(FUNC_NUM_JACK_CODEC, RT712_SDCA_ENT0, RT712_SDCA_CTL_FUNC_STATUS, 0), &jack_func_status); @@ -1773,6 +1847,12 @@ static void rt712_sdca_vb_io_init(struct rt712_sdca_priv *rt712) __func__, jack_func_status, mic_func_status, amp_func_status); rt712_sdca_index_write(rt712, RT712_VENDOR_REG, RT712_JD_CTL3, 0x7778); + + if (clk_base == RT712_CLK_FREQ_24_576MHZ) { + rt712_sdca_clk_patch(rt712); + rt712_sdca_clk_patch2(rt712); + } + /* DMIC */ if ((mic_func_status & FUNCTION_NEEDS_INITIALIZATION) || (!rt712->first_hw_init)) { rt712_sdca_index_write(rt712, RT712_VENDOR_HDA_CTL, RT712_DMIC2_FU_IT_FLOAT_CTL, 0x1526); diff --git a/sound/soc/codecs/rt712-sdca.h b/sound/soc/codecs/rt712-sdca.h index 46740281a5c1..6229fe341bb5 100644 --- a/sound/soc/codecs/rt712-sdca.h +++ b/sound/soc/codecs/rt712-sdca.h @@ -162,6 +162,16 @@ struct rt712_dmic_kctrl_priv { #define RT712_EAPD_HIGH 0x2 #define RT712_EAPD_LOW 0x0 +/* SDW clock root frequency */ +#define RT712_SDW_ROOT_CLK 0x004d +#define RT712_SDW_SCALE_CLK0 0x0062 +#define RT712_SDW_SCALE_CLK1 0x0072 + +/* PLL2 config */ +#define RT712_PLL2_CONF1 0x2f3a +#define RT712_PLL2_CONF2 0x2f3d +#define RT712_PLL2_CONF3 0x2f41 + /* RC Calibration register */ #define RT712_RC_CAL 0x3201 @@ -254,6 +264,14 @@ enum rt712_sdca_version { RT712_VB, }; +enum { + RT712_CLK_FREQ_19_2_MHZ = 1, + RT712_CLK_FREQ_24MHZ = 2, + RT712_CLK_FREQ_24_576MHZ = 3, + RT712_CLK_FREQ_22_5792MHZ = 4, +}; + + int rt712_sdca_io_init(struct device *dev, struct sdw_slave *slave); int rt712_sdca_init(struct device *dev, struct regmap *regmap, struct regmap *mbq_regmap, struct sdw_slave *slave); From 4d855d747521505b54457c96bc73577bf74b2374 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Thu, 10 Sep 2026 12:44:56 +0100 Subject: [PATCH 1181/1198] ASoC: Rename snd_soc_dai_link_ch_map.ch_mask to cpu_ch_mask Rename the ch_mask member of snd_soc_dai_link_ch_map to cpu_ch_mask, as that is what it is used for. The CPU and codec channel masks are not necessarily the same, and are quite likely different. SoundWire and I2S/TDM both support assigning different sample slots to each codec, so for example channel 0 on each codec could map to different channels at the CPU. So it's quite normal that the channel mask at the CPU end is different for each codec, but the codec channel masks are the same for each codec. Signed-off-by: Richard Fitzgerald Link: https://patch.msgid.link/20260910114500.1586637-2-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- include/sound/soc.h | 2 +- sound/soc/sdw_utils/soc_sdw_utils.c | 2 +- sound/soc/soc-pcm.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/include/sound/soc.h b/include/sound/soc.h index f46b2bc2a022..94c9b75e27e3 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -699,7 +699,7 @@ struct snd_soc_dai_link_component { struct snd_soc_dai_link_ch_map { unsigned int cpu; unsigned int codec; - unsigned int ch_mask; + unsigned int cpu_ch_mask; }; struct snd_soc_dai_link { diff --git a/sound/soc/sdw_utils/soc_sdw_utils.c b/sound/soc/sdw_utils/soc_sdw_utils.c index a66dcc02fb59..f0cebcbf6288 100644 --- a/sound/soc/sdw_utils/soc_sdw_utils.c +++ b/sound/soc/sdw_utils/soc_sdw_utils.c @@ -1596,7 +1596,7 @@ int asoc_sdw_hw_params(struct snd_pcm_substream *substream, * ASoC will set the corresponding channel numbers for each cpu dai. */ for_each_link_ch_maps(rtd->dai_link, i, ch_maps) - ch_maps->ch_mask = ch_mask << (i * step); + ch_maps->cpu_ch_mask = ch_mask << (i * step); return 0; } diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 0e49290a8c90..cb64ced21149 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -1264,7 +1264,7 @@ static int __soc_pcm_hw_params(struct snd_pcm_substream *substream, */ for_each_rtd_ch_maps(rtd, j, ch_maps) if (ch_maps->cpu == i) - ch_mask |= ch_maps->ch_mask; + ch_mask |= ch_maps->cpu_ch_mask; /* fixup cpu channel number */ if (ch_mask) From 88b14c0d0bab5c0f3e7c641f274e3c70210c0e36 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Thu, 10 Sep 2026 12:44:57 +0100 Subject: [PATCH 1182/1198] ASoC: Add codec_ch_mask to snd_soc_dai_link_ch_map Add a codec_ch_mask member to snd_soc_dai_link_ch_map. The CPU and codec channel masks are not necessarily the same, and are quite likely different. SoundWire and I2S/TDM both support assigning different sample slots to each codec, so for example channel 0 on each codec could map to different channels at the CPU. It is also possible for one TX channel to map to multiple RX channels. So it isn't _always_ safe to assume that the total number of set bits in the CPU ch_mask is the same as the total number of enabled channels on the codec. For example consider this mapping on a capture stream: CPU0 CODEC0 cpu_ch_mask = 0x03 CPU1 CODEC0 cpu_ch_mask = 0x03 This could be either four TX channels on the codec split across two receiving CPUs, or two TX channels on the codec duplicated to two CPUs. Signed-off-by: Richard Fitzgerald Link: https://patch.msgid.link/20260910114500.1586637-3-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- include/sound/soc.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/sound/soc.h b/include/sound/soc.h index 94c9b75e27e3..5afc34b147b5 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -700,6 +700,7 @@ struct snd_soc_dai_link_ch_map { unsigned int cpu; unsigned int codec; unsigned int cpu_ch_mask; + unsigned int codec_ch_mask; }; struct snd_soc_dai_link { From 6b382bdfe26a2232091bf743e454e6794295783e Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Thu, 10 Sep 2026 12:44:58 +0100 Subject: [PATCH 1183/1198] ASoC: soc-pcm: Apply snd_soc_dai_link_ch_map.codec_ch_mask to codec params In __soc_pcm_hw_params() if there is a snd_soc_dai_link_ch_map with non-zero codec_ch_mask, use that channel mask to restrict which channels are enabled on the codec. But only if there isn't a TDM mask. It is possible that a snd_soc_dai_link_ch_map could include the same codec multiple times on different CPUs so the for_each_rtd_ch_maps() loop accumulates the channel masks for all entries of that codec. If a TDM mask was also set, it takes priority and is used instead of any possible snd_soc_dai_link_ch_map entries. (They cannot be ANDed together because the bit positions are indicating different things: TDM is a bit for each TDM slot, codec_ch_mask is a bit for each codec channel.) This fixes a problem of incorrect TX channels enabled on the codec when multiple codecs are aggregated on a single capture link. For example: - Two CPUs with six 4-channel codecs. - The machine driver chooses to assign one channel from each codec to one channel on the CPU - But the codec hw_params() would be passed a channel count of 6, which (a) is more channels than the codec has and (b) allows enabling channels that should not be driving the audio bus. Fixes: ac950278b087 ("ASoC: add N cpus to M codecs dai link support") Signed-off-by: Richard Fitzgerald Link: https://patch.msgid.link/20260910114500.1586637-4-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- sound/soc/soc-pcm.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index cb64ced21149..3137c091bdb8 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -1206,7 +1206,9 @@ static int __soc_pcm_hw_params(struct snd_pcm_substream *substream, goto out; for_each_rtd_codec_dais(rtd, i, codec_dai) { - unsigned int tdm_mask = snd_soc_dai_tdm_mask_get(codec_dai, substream->stream); + unsigned int ch_mask = snd_soc_dai_tdm_mask_get(codec_dai, substream->stream); + struct snd_soc_dai_link_ch_map *ch_maps; + int j; /* * Skip CODECs which don't support the current stream type, @@ -1228,9 +1230,15 @@ static int __soc_pcm_hw_params(struct snd_pcm_substream *substream, /* copy params for each codec */ tmp_params = *params; - /* fixup params based on TDM slot masks */ - if (tdm_mask) - soc_pcm_codec_params_fixup(&tmp_params, tdm_mask); + /* fixup params based on TDM or ch_map masks */ + if (!ch_mask) { + for_each_rtd_ch_maps(rtd, j, ch_maps) + if (ch_maps->codec == i) + ch_mask |= ch_maps->codec_ch_mask; + } + + if (ch_mask) + soc_pcm_codec_params_fixup(&tmp_params, ch_mask); ret = snd_soc_dai_hw_params(codec_dai, substream, &tmp_params); From 290845e151cd4e307cc1f25319583aaceb4eeb30 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Thu, 10 Sep 2026 12:44:59 +0100 Subject: [PATCH 1184/1198] ASoC: sdw_utils: Set snd_soc_dai_link_ch_map.codec_ch_mask for capture In asoc_sdw_hw_params() set the codec_ch_mask member of struct snd_soc_dai_link_ch_map for capture streams. ASoC will then pass the correct number of channels to each codec hw_params(). This prevents trying to enable more channels on the codec DP than have been allocated bitslots in the SoundWire frame, which would cause bus clash errors. In theory codec_ch_mask could also be set for playback streams, but for those the CPU is the only sender so there is no risk of bus clash. For playback streams codec_ch_mask is set to 0 to preserve the existing behavior and avoid introducing bugs. Signed-off-by: Richard Fitzgerald Link: https://patch.msgid.link/20260910114500.1586637-5-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- sound/soc/sdw_utils/soc_sdw_utils.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/sound/soc/sdw_utils/soc_sdw_utils.c b/sound/soc/sdw_utils/soc_sdw_utils.c index f0cebcbf6288..293574a6ccca 100644 --- a/sound/soc/sdw_utils/soc_sdw_utils.c +++ b/sound/soc/sdw_utils/soc_sdw_utils.c @@ -1565,7 +1565,7 @@ int asoc_sdw_hw_params(struct snd_pcm_substream *substream, struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); struct snd_soc_dai_link_ch_map *ch_maps; int ch = params_channels(params); - unsigned int ch_mask; + unsigned int cpu_ch_mask, codec_ch_mask; int num_codecs; int step; int i; @@ -1575,8 +1575,9 @@ int asoc_sdw_hw_params(struct snd_pcm_substream *substream, /* Identical data will be sent to all codecs in playback */ if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { - ch_mask = GENMASK(ch - 1, 0); + cpu_ch_mask = GENMASK(ch - 1, 0); step = 0; + codec_ch_mask = 0; } else { num_codecs = rtd->dai_link->num_codecs; @@ -1586,17 +1587,24 @@ int asoc_sdw_hw_params(struct snd_pcm_substream *substream, return -EINVAL; } - ch_mask = GENMASK(ch / num_codecs - 1, 0); - step = hweight_long(ch_mask); + cpu_ch_mask = GENMASK(ch / num_codecs - 1, 0); + step = hweight_long(cpu_ch_mask); + codec_ch_mask = cpu_ch_mask; } /* * The captured data will be combined from each cpu DAI if the dai * link has more than one codec DAIs. Set codec channel mask and * ASoC will set the corresponding channel numbers for each cpu dai. + * + * sdw_stream_add_slave() assigns different payload offsets to each + * codec in a capture stream, so that the same channels on each + * codec map to different channels on the CPU. */ - for_each_link_ch_maps(rtd->dai_link, i, ch_maps) - ch_maps->cpu_ch_mask = ch_mask << (i * step); + for_each_link_ch_maps(rtd->dai_link, i, ch_maps) { + ch_maps->cpu_ch_mask = cpu_ch_mask << (i * step); + ch_maps->codec_ch_mask = codec_ch_mask; + } return 0; } From b5b00a57868b1eabdf90a29a51f0eb732c609f3a Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Thu, 10 Sep 2026 12:45:00 +0100 Subject: [PATCH 1185/1198] ASoC: sdw_utils: cs_amp: Delete bogus and incorrect capture channel fixup Delete the asoc_sdw_cs_spk_feedback_rtd_init(). This is not needed now that the ASoC bug it was working around has been fixed. And it was broken anyway because it didn't match the way the core SoundWire code mapped codec channels to frame bitslots. This code was added to avoid a problem where multiple codec DP outputs were mapped to the same SoundWire frame bit slot. This would allow a user to break the SoundWire bus just by enabling mixer outputs using ALSA controls. As no production system has used the capture stream, this workaround was of little consequence and the problem of conflicting DP mappings was not investigated. The ASoC bug that enabled too many channels on each codec has now been fixed. So this workaround can be completely deleted. Signed-off-by: Richard Fitzgerald Link: https://patch.msgid.link/20260910114500.1586637-6-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- include/sound/soc_sdw_utils.h | 2 -- sound/soc/sdw_utils/soc_sdw_cs_amp.c | 46 ---------------------------- sound/soc/sdw_utils/soc_sdw_utils.c | 4 --- 3 files changed, 52 deletions(-) diff --git a/include/sound/soc_sdw_utils.h b/include/sound/soc_sdw_utils.h index 9b28e9aef4f1..9fbb69b9052d 100644 --- a/include/sound/soc_sdw_utils.h +++ b/include/sound/soc_sdw_utils.h @@ -250,8 +250,6 @@ int asoc_sdw_cs_amp_init(struct snd_soc_card *card, struct snd_soc_dai_link *dai_links, struct asoc_sdw_codec_info *info, bool playback); -int asoc_sdw_cs_spk_feedback_rtd_init(struct snd_soc_pcm_runtime *rtd, - struct snd_soc_dai *dai); int asoc_sdw_cs35l56_volume_limit(struct snd_soc_card *card, const char *name_prefix); /* MAXIM codec support */ diff --git a/sound/soc/sdw_utils/soc_sdw_cs_amp.c b/sound/soc/sdw_utils/soc_sdw_cs_amp.c index 325ab7230481..6e21ef8f87e2 100644 --- a/sound/soc/sdw_utils/soc_sdw_cs_amp.c +++ b/sound/soc/sdw_utils/soc_sdw_cs_amp.c @@ -14,7 +14,6 @@ #include #include -#define CS_AMP_CHANNELS_PER_AMP 4 #define CS35L56_SPK_VOLUME_0DB 400 /* 0dB Max */ int asoc_sdw_cs35l56_volume_limit(struct snd_soc_card *card, const char *name_prefix) @@ -64,51 +63,6 @@ int asoc_sdw_cs_spk_rtd_init(struct snd_soc_pcm_runtime *rtd, struct snd_soc_dai } EXPORT_SYMBOL_NS(asoc_sdw_cs_spk_rtd_init, "SND_SOC_SDW_UTILS"); -int asoc_sdw_cs_spk_feedback_rtd_init(struct snd_soc_pcm_runtime *rtd, struct snd_soc_dai *dai) -{ - const struct snd_soc_dai_link *dai_link = rtd->dai_link; - const struct snd_soc_dai_link_ch_map *ch_map; - const struct snd_soc_dai_link_component *codec_dlc; - struct snd_soc_dai *codec_dai; - u8 ch_slot[8] = {}; - unsigned int amps_per_bus, ch_per_amp, mask; - int i, ret; - - WARN_ON(dai_link->num_cpus > ARRAY_SIZE(ch_slot)); - - /* - * CS35L56 has 4 TX channels. When the capture is aggregated the - * same bus slots will be allocated to all the amps on a bus. Only - * one amp on that bus can be transmitting in each slot so divide - * the available 4 slots between all the amps on a bus. - */ - amps_per_bus = dai_link->num_codecs / dai_link->num_cpus; - if ((amps_per_bus == 0) || (amps_per_bus > CS_AMP_CHANNELS_PER_AMP)) { - dev_err(rtd->card->dev, "Illegal num_codecs:%u / num_cpus:%u\n", - dai_link->num_codecs, dai_link->num_cpus); - return -EINVAL; - } - - ch_per_amp = CS_AMP_CHANNELS_PER_AMP / amps_per_bus; - - for_each_rtd_ch_maps(rtd, i, ch_map) { - codec_dlc = snd_soc_link_to_codec(rtd->dai_link, i); - codec_dai = snd_soc_find_dai(codec_dlc); - mask = GENMASK(ch_per_amp - 1, 0) << ch_slot[ch_map->cpu]; - - ret = snd_soc_dai_set_tdm_slot(codec_dai, 0, mask, 4, 32); - if (ret < 0) { - dev_err(rtd->card->dev, "Failed to set TDM slot:%d\n", ret); - return ret; - } - - ch_slot[ch_map->cpu] += ch_per_amp; - } - - return 0; -} -EXPORT_SYMBOL_NS(asoc_sdw_cs_spk_feedback_rtd_init, "SND_SOC_SDW_UTILS"); - int asoc_sdw_cs_amp_init(struct snd_soc_card *card, struct snd_soc_dai_link *dai_links, struct asoc_sdw_codec_info *info, diff --git a/sound/soc/sdw_utils/soc_sdw_utils.c b/sound/soc/sdw_utils/soc_sdw_utils.c index 293574a6ccca..d2eeef4931c6 100644 --- a/sound/soc/sdw_utils/soc_sdw_utils.c +++ b/sound/soc/sdw_utils/soc_sdw_utils.c @@ -811,7 +811,6 @@ struct asoc_sdw_codec_info codec_info_list[] = { .dai_name = "cs35l56-sdw1c", .dai_type = SOC_SDW_DAI_TYPE_AMP, .dailink = {SOC_SDW_UNUSED_DAI_ID, SOC_SDW_AMP_IN_DAI_ID}, - .rtd_init = asoc_sdw_cs_spk_feedback_rtd_init, }, }, .dai_num = 2, @@ -840,7 +839,6 @@ struct asoc_sdw_codec_info codec_info_list[] = { .dai_name = "cs35l56-sdw1c", .dai_type = SOC_SDW_DAI_TYPE_AMP, .dailink = {SOC_SDW_UNUSED_DAI_ID, SOC_SDW_AMP_IN_DAI_ID}, - .rtd_init = asoc_sdw_cs_spk_feedback_rtd_init, }, }, .dai_num = 2, @@ -869,7 +867,6 @@ struct asoc_sdw_codec_info codec_info_list[] = { .dai_name = "cs35l56-sdw1c", .dai_type = SOC_SDW_DAI_TYPE_AMP, .dailink = {SOC_SDW_UNUSED_DAI_ID, SOC_SDW_AMP_IN_DAI_ID}, - .rtd_init = asoc_sdw_cs_spk_feedback_rtd_init, }, }, .dai_num = 2, @@ -898,7 +895,6 @@ struct asoc_sdw_codec_info codec_info_list[] = { .dai_name = "cs35l56-sdw1c", .dai_type = SOC_SDW_DAI_TYPE_AMP, .dailink = {SOC_SDW_UNUSED_DAI_ID, SOC_SDW_AMP_IN_DAI_ID}, - .rtd_init = asoc_sdw_cs_spk_feedback_rtd_init, }, }, .dai_num = 2, From 576725ded009f09a28da19852f7edf62dbc5f94c Mon Sep 17 00:00:00 2001 From: Ai Chao Date: Fri, 11 Sep 2026 16:19:32 +0800 Subject: [PATCH 1186/1198] ASoC: Intel: sof_es8336: Add a quirk for Huawei Matebook B3-420 Add DMI entry for Huawei Matebook B3-420 (BDZ-WXX9) with HEADPHONE_GPIO and HEADSET_MIC1 quirks. Similar to Huawei Matebook D (BOD-WXX9). On the same machine,audio routing between speakers and headphones works correctly when running Windows with the Huawei audio driver. However, after reinstalling Linux, both the speakers and headphones output sound simultaneously,indicating that the amplifier enable GPIOs are not being toggled correctly to separate the two outputs. Signed-off-by: Ai Chao Link: https://patch.msgid.link/20260911081932.2605407-1-aichao@kylinos.cn Signed-off-by: Mark Brown --- sound/soc/intel/boards/sof_es8336.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/sound/soc/intel/boards/sof_es8336.c b/sound/soc/intel/boards/sof_es8336.c index 9b016136c639..f1e62c2e79fe 100644 --- a/sound/soc/intel/boards/sof_es8336.c +++ b/sound/soc/intel/boards/sof_es8336.c @@ -360,6 +360,15 @@ static const struct dmi_system_id sof_es8336_quirk_table[] = { .driver_data = (void *)(SOF_ES8336_HEADPHONE_GPIO | SOC_ES8336_HEADSET_MIC1) }, + { + .callback = sof_es8336_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "HUAWEI"), + DMI_MATCH(DMI_PRODUCT_NAME, "NDZ-WXX9"), + }, + .driver_data = (void *)(SOF_ES8336_HEADPHONE_GPIO | + SOC_ES8336_HEADSET_MIC1) + }, {} }; From a5e22cba3549b3b9ca592a6bc62329c9b85ce285 Mon Sep 17 00:00:00 2001 From: Oder Chiou Date: Wed, 16 Sep 2026 18:18:03 +0800 Subject: [PATCH 1187/1198] ASoC: rt721: Reset codec to fix abnormal sound The audio output may become abnormal after a warm reboot from Windows. Reset the codec once during hardware initialization to restore it to a known state and prevent the issue. Signed-off-by: Oder Chiou Link: https://patch.msgid.link/20260916101803.2301508-1-oder_chiou@realtek.com Signed-off-by: Mark Brown --- sound/soc/codecs/rt721-sdca-sdw.c | 3 +++ sound/soc/codecs/rt721-sdca.c | 17 +++++++++++++++++ 2 files changed, 20 insertions(+) diff --git a/sound/soc/codecs/rt721-sdca-sdw.c b/sound/soc/codecs/rt721-sdca-sdw.c index eae7d662efae..910583162d3e 100644 --- a/sound/soc/codecs/rt721-sdca-sdw.c +++ b/sound/soc/codecs/rt721-sdca-sdw.c @@ -70,6 +70,7 @@ static bool rt721_sdca_mbq_readable_register(struct device *dev, unsigned int re case 0x0310100: case 0x2000000 ... 0x2000003: case 0x2000013: + case 0x2000026: case 0x200002c: case 0x200003c: case 0x2000046: @@ -142,6 +143,7 @@ static bool rt721_sdca_mbq_volatile_register(struct device *dev, unsigned int re case 0x200000d: case 0x2000019: case 0x2000020: + case 0x2000026: case 0x200002c: case 0x2000030: case 0x2000046: @@ -155,6 +157,7 @@ static bool rt721_sdca_mbq_volatile_register(struct device *dev, unsigned int re case 0x5810039: case 0x5b10018: case 0x5b10019: + case 0x6100006: return true; default: return false; diff --git a/sound/soc/codecs/rt721-sdca.c b/sound/soc/codecs/rt721-sdca.c index a9479d0e4941..738644018fb9 100644 --- a/sound/soc/codecs/rt721-sdca.c +++ b/sound/soc/codecs/rt721-sdca.c @@ -1497,6 +1497,15 @@ int rt721_sdca_init(struct device *dev, struct regmap *regmap, &soc_sdca_dev_rt721, rt721_sdca_dai, ARRAY_SIZE(rt721_sdca_dai)); } +static void rt721_sdca_reset(struct rt721_sdca_priv *rt721) +{ + rt_sdca_index_update_bits(rt721->mbq_regmap, RT721_VENDOR_REG, + RT721_VD_HIDDEN_CTRL, RT721_HIDDEN_REG_SW_RESET, + RT721_HIDDEN_REG_SW_RESET); + rt_sdca_index_update_bits(rt721->mbq_regmap, RT721_HDA_SDCA_FLOAT, + RT721_HDA_LEGACY_RESET_CTL, 0x1, 0x1); +} + int rt721_sdca_io_init(struct device *dev, struct sdw_slave *slave) { struct rt721_sdca_priv *rt721 = dev_get_drvdata(dev); @@ -1530,9 +1539,17 @@ int rt721_sdca_io_init(struct device *dev, struct sdw_slave *slave) } pm_runtime_get_noresume(&slave->dev); + + if (!rt721->first_hw_init) + rt721_sdca_reset(rt721); + rt721_sdca_dmic_preset(rt721); rt721_sdca_amp_preset(rt721); rt721_sdca_jack_preset(rt721); + + if (rt721->hs_jack && (!rt721->first_hw_init)) + rt721_sdca_jack_init(rt721); + if (rt721->first_hw_init) { regcache_cache_bypass(rt721->regmap, false); regcache_mark_dirty(rt721->regmap); From 11fc0048a6930f4fca44fe3bd16a0023e78846a2 Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Sun, 13 Sep 2026 13:31:32 -0400 Subject: [PATCH 1188/1198] ASoC: ux500: Parenthesize MSP_{RX,TX}_CLKPOL_BIT() arguments arm allmodconfig fails to build with gcc: In file included from sound/soc/ux500/ux500_msp_i2s.c:20: sound/soc/ux500/ux500_msp_i2s.h:151:38: error: suggest parentheses around arithmetic in operand of '^' [-Werror=parentheses] sound/soc/ux500/ux500_msp_i2s.c:204:21: note: in expansion of macro 'MSP_TX_CLKPOL_BIT' cc1: all warnings being treated as errors The macros never parenthesized their argument: #define MSP_TX_CLKPOL_BIT(n) ((n & TCKPOL_MASK) << TCKPOL_SHIFT) That went unnoticed while every caller passed a plain variable, but configure_protocol() now passes an XOR expression, which binds as "a ^ (b & MASK)" rather than "(a ^ b) & MASK", and gcc rightly complains. No functional change: tx_clk_pol and rx_clk_pol only ever hold MSP_FALLING_EDGE (0) or MSP_RISING_EDGE (1), and bclk_inverted is a bool, so masking before or after the XOR gives the same 0/1 result. Parenthesize the argument anyway - it fixes the build and stops the macros from silently mis-evaluating a future composite argument. Fixes: 9ccbacf5a012 ("ASoC: ux500: Validate MSP DAI configuration") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202609051547.G9SJp8UQ-lkp@intel.com/ Assisted-by: LLM Signed-off-by: Sasha Levin Reviewed-by: Linus Walleij Link: https://patch.msgid.link/20260913173132.1172003-1-sashal@kernel.org Signed-off-by: Mark Brown --- sound/soc/ux500/ux500_msp_i2s.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/soc/ux500/ux500_msp_i2s.h b/sound/soc/ux500/ux500_msp_i2s.h index 2bf2699bdc49..c66ef455e138 100644 --- a/sound/soc/ux500/ux500_msp_i2s.h +++ b/sound/soc/ux500/ux500_msp_i2s.h @@ -147,8 +147,8 @@ enum msp_direction { #define RCKPOL_MASK BIT(0) #define TCKPOL_MASK BIT(0) #define SPICKM_MASK (BIT(1) | BIT(0)) -#define MSP_RX_CLKPOL_BIT(n) ((n & RCKPOL_MASK) << RCKPOL_SHIFT) -#define MSP_TX_CLKPOL_BIT(n) ((n & TCKPOL_MASK) << TCKPOL_SHIFT) +#define MSP_RX_CLKPOL_BIT(n) (((n) & RCKPOL_MASK) << RCKPOL_SHIFT) +#define MSP_TX_CLKPOL_BIT(n) (((n) & TCKPOL_MASK) << TCKPOL_SHIFT) #define P1ELEN_SHIFT 0 #define P1FLEN_SHIFT 3 From c17ae8c26eac16ad244daef44044d714f68a2ddc Mon Sep 17 00:00:00 2001 From: HyeongJun An Date: Tue, 15 Sep 2026 18:25:15 +0900 Subject: [PATCH 1189/1198] ASoC: hdmi-codec: Report a change when the channel status moves The put() callback of "IEC958 Playback Default" stores all 24 channel status bytes and then returns 0. The core notifies userspace only on a positive return, so a write that changes what the get() callback hands back is never announced, and a mixer holding the control open keeps showing the old value. Compare the stored bytes and return 1 when they move, the way snd_hda_spdif_default_put() does. The same shape is in img-spdif-out and uniperif_player. No board with this codec was to hand. The change is a comparison of driver state with no hardware behaviour in it, and mixer-test counts the missing notification as event_missing. Fixes: 7a8e1d44211e ("ASoC: hdmi-codec: Add iec958 controls") Signed-off-by: HyeongJun An Assisted-by: Claude:claude-opus-5 Link: https://patch.msgid.link/20260915092515.2638542-1-sammiee5311@gmail.com Signed-off-by: Mark Brown --- sound/soc/codecs/hdmi-codec.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c index bc2c22436ba6..7aa50c5bd3df 100644 --- a/sound/soc/codecs/hdmi-codec.c +++ b/sound/soc/codecs/hdmi-codec.c @@ -426,10 +426,14 @@ static int hdmi_codec_iec958_default_put(struct snd_kcontrol *kcontrol, struct snd_soc_component *component = snd_kcontrol_chip(kcontrol); struct hdmi_codec_priv *hcp = snd_soc_component_get_drvdata(component); + if (!memcmp(hcp->iec_status, ucontrol->value.iec958.status, + sizeof(hcp->iec_status))) + return 0; + memcpy(hcp->iec_status, ucontrol->value.iec958.status, sizeof(hcp->iec_status)); - return 0; + return 1; } static int hdmi_codec_iec958_mask_get(struct snd_kcontrol *kcontrol, From 03a5699a0a04309c597683967aaaf25d1e555ea2 Mon Sep 17 00:00:00 2001 From: Jiangshan Yi Date: Mon, 14 Sep 2026 18:47:12 +0800 Subject: [PATCH 1190/1198] ASoC: codecs: rt712-sdca-dmic: fix uninitialized stream_config->type stream_config is not initialized before being passed to sdw_stream_add_slave(). The type field may contain garbage and is later copied to stream->type by sdw_config_stream(). Zero-initialize stream_config so type defaults to SDW_STREAM_PCM. While at it, use snd_sdw_params_to_config() helper instead of open-coding the same logic. Fixes: 63a511284c9e ("ASoC: rt712-sdca: Add RT712 SDCA driver for Mic topology") Cc: stable@vger.kernel.org Signed-off-by: Jiangshan Yi Reviewed-by: Pierre-Louis Bossart Link: https://patch.msgid.link/20260914104712.379574-1-yijiangshan@kylinos.cn Signed-off-by: Mark Brown --- sound/soc/codecs/rt712-sdca-dmic.c | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) diff --git a/sound/soc/codecs/rt712-sdca-dmic.c b/sound/soc/codecs/rt712-sdca-dmic.c index 8860d81134e7..a9f3aa4e143a 100644 --- a/sound/soc/codecs/rt712-sdca-dmic.c +++ b/sound/soc/codecs/rt712-sdca-dmic.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include "rt712-sdca.h" #include "rt712-sdca-dmic.h" @@ -632,10 +633,10 @@ static int rt712_sdca_dmic_hw_params(struct snd_pcm_substream *substream, { struct snd_soc_component *component = dai->component; struct rt712_sdca_dmic_priv *rt712 = snd_soc_component_get_drvdata(component); - struct sdw_stream_config stream_config; + struct sdw_stream_config stream_config = {0}; struct sdw_port_config port_config; struct sdw_stream_runtime *sdw_stream; - int retval, num_channels; + int retval; unsigned int sampling_rate; dev_dbg(dai->dev, "%s %s", __func__, dai->name); @@ -647,13 +648,8 @@ static int rt712_sdca_dmic_hw_params(struct snd_pcm_substream *substream, if (!rt712->slave) return -EINVAL; - stream_config.frame_rate = params_rate(params); - stream_config.ch_count = params_channels(params); - stream_config.bps = snd_pcm_format_width(params_format(params)); - stream_config.direction = SDW_DATA_DIR_TX; - - num_channels = params_channels(params); - port_config.ch_mask = GENMASK(num_channels - 1, 0); + /* SoundWire specific configuration */ + snd_sdw_params_to_config(substream, params, &stream_config, &port_config); port_config.num = 2; retval = sdw_stream_add_slave(rt712->slave, &stream_config, From 3482062c786ce4233f8ed3224d824184f53ec154 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Mon, 14 Sep 2026 13:26:11 +0100 Subject: [PATCH 1191/1198] ASoC: cs-amp-lib: Prevent NULL pointer if efi variable is zero length In cs_amp_alloc_get_efi_variable() the first call to cs_amp_get_efi_variable() might return EFI_SUCCESS if the variable exists with zero length. Trap this and return -ENOENT to prevent returning an unexpected NULL pointer. The first cs_amp_get_efi_variable() call was assumed to return EFI_BUFFER_TOO_SMALL if the variable existed, but if instead it returned EFI_SUCCESS this would be converted to 0 by cs_amp_convert_efi_status() and then be returned as a NULL pointer. Fixes: 00fd40bc7acec ("ASoC: cs-amp-lib: Support Dell SSIDExV2 UEFI variable") Signed-off-by: Richard Fitzgerald Link: https://patch.msgid.link/20260914122611.2783563-1-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- sound/soc/codecs/cs-amp-lib.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/soc/codecs/cs-amp-lib.c b/sound/soc/codecs/cs-amp-lib.c index 41a9a5b005c6..9bc19d2e1639 100644 --- a/sound/soc/codecs/cs-amp-lib.c +++ b/sound/soc/codecs/cs-amp-lib.c @@ -317,6 +317,8 @@ static void *cs_amp_alloc_get_efi_variable(efi_char16_t *name, unsigned long size = 0; status = cs_amp_get_efi_variable(name, guid, NULL, &size, NULL); + if (status == EFI_SUCCESS) + return ERR_PTR(-ENOENT); if (status != EFI_BUFFER_TOO_SMALL) return ERR_PTR(cs_amp_convert_efi_status(status)); From 29218a4d11a31a8157389bc2b9e62dd768d7ea42 Mon Sep 17 00:00:00 2001 From: Vijendar Mukunda Date: Thu, 10 Sep 2026 21:46:46 +0530 Subject: [PATCH 1192/1198] ASoC: amd: acp: bounds-check SoundWire link ID in machine drivers Add a bounds check in create_sdw_dailink() to validate that the SoundWire link ID derived from link_mask does not exceed the maximum supported by the platform. If the link ID is out of range or link_mask is zero, log an error and return -EINVAL to prevent accessing invalid CPU pin ID tables. Applied to both acp-sdw-sof-mach.c and acp-sdw-legacy-mach.c. Fixes: 6d8348ddc56e ("ASoC: amd: acp: refactor SoundWire machine driver code") Signed-off-by: Vijendar Mukunda Reviewed-by: Mario Limonciello (AMD) Link: https://patch.msgid.link/20260910161728.1452808-2-Vijendar.Mukunda@amd.com Signed-off-by: Mark Brown --- sound/soc/amd/acp/acp-sdw-legacy-mach.c | 10 ++++++++++ sound/soc/amd/acp/acp-sdw-sof-mach.c | 9 +++++++++ 2 files changed, 19 insertions(+) diff --git a/sound/soc/amd/acp/acp-sdw-legacy-mach.c b/sound/soc/amd/acp/acp-sdw-legacy-mach.c index 6eac42bac855..2ea226a195c3 100644 --- a/sound/soc/amd/acp/acp-sdw-legacy-mach.c +++ b/sound/soc/amd/acp/acp-sdw-legacy-mach.c @@ -205,6 +205,16 @@ static int create_sdw_dailink(struct snd_soc_card *card, return -EINVAL; } + if (!soc_end->link_mask) { + dev_err(dev, "invalid zero link_mask\n"); + return -EINVAL; + } + if ((ffs(soc_end->link_mask) - 1) >= amd_ctx->max_sdw_links) { + dev_err(dev, "link_id %d exceeds max_sdw_links %d\n", + ffs(soc_end->link_mask) - 1, amd_ctx->max_sdw_links); + return -EINVAL; + } + switch (amd_ctx->acp_rev) { case ACP63_PCI_REV: ret = get_acp63_cpu_pin_id(ffs(soc_end->link_mask - 1), diff --git a/sound/soc/amd/acp/acp-sdw-sof-mach.c b/sound/soc/amd/acp/acp-sdw-sof-mach.c index a9cd1f335167..6c74e67b134f 100644 --- a/sound/soc/amd/acp/acp-sdw-sof-mach.c +++ b/sound/soc/amd/acp/acp-sdw-sof-mach.c @@ -121,6 +121,15 @@ static int create_sdw_dailink(struct snd_soc_card *card, return -EINVAL; } + if (!sof_end->link_mask) { + dev_err(dev, "invalid zero link_mask\n"); + return -EINVAL; + } + if ((ffs(sof_end->link_mask) - 1) >= amd_ctx->max_sdw_links) { + dev_err(dev, "link_id %d exceeds max_sdw_links %d\n", + ffs(sof_end->link_mask) - 1, amd_ctx->max_sdw_links); + return -EINVAL; + } switch (amd_ctx->acp_rev) { case ACP63_PCI_REV: ret = get_acp63_cpu_pin_id(ffs(sof_end->link_mask - 1), From 0b7d55d3a91200f2b1ed710f525a944b0a7d6369 Mon Sep 17 00:00:00 2001 From: Vijendar Mukunda Date: Thu, 10 Sep 2026 21:46:47 +0530 Subject: [PATCH 1193/1198] ASoC: amd: acp: refactor codec config count in SOF SoundWire machine driver num_devs was used both as the endpoint count and as the output for asoc_sdw_parse_sdw_endpoints(), which overwrites it with the codec configuration count. Introduce a separate num_confs variable to hold the codec conf count so the two values remain distinct across codec_conf allocation and card->num_configs assignment. Fixes: 6d8348ddc56e ("ASoC: amd: acp: refactor SoundWire machine driver code") Signed-off-by: Vijendar Mukunda Reviewed-by: Mario Limonciello (AMD) Link: https://patch.msgid.link/20260910161728.1452808-3-Vijendar.Mukunda@amd.com Signed-off-by: Mark Brown --- sound/soc/amd/acp/acp-sdw-sof-mach.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/sound/soc/amd/acp/acp-sdw-sof-mach.c b/sound/soc/amd/acp/acp-sdw-sof-mach.c index 6c74e67b134f..b7926967593f 100644 --- a/sound/soc/amd/acp/acp-sdw-sof-mach.c +++ b/sound/soc/amd/acp/acp-sdw-sof-mach.c @@ -286,6 +286,7 @@ static int sof_card_dai_links_create(struct snd_soc_card *card) int num_devs = 0; int num_ends = 0; int num_aux = 0; + int num_confs; int num_links; int be_id = 0; int ret; @@ -296,6 +297,7 @@ static int sof_card_dai_links_create(struct snd_soc_card *card) return ret; } + num_confs = num_ends; /* One per DAI link, worst case is a DAI link for every endpoint */ struct asoc_sdw_dailink *sof_dais __free(kfree) = kzalloc_objs(*sof_dais, num_ends); @@ -312,7 +314,7 @@ static int sof_card_dai_links_create(struct snd_soc_card *card) if (!sof_aux) return -ENOMEM; - ret = asoc_sdw_parse_sdw_endpoints(dev, ctx, sof_aux, sof_dais, sof_ends, &num_devs); + ret = asoc_sdw_parse_sdw_endpoints(dev, ctx, sof_aux, sof_dais, sof_ends, &num_confs); if (ret < 0) return ret; @@ -324,7 +326,7 @@ static int sof_card_dai_links_create(struct snd_soc_card *card) dev_dbg(dev, "sdw %d, dmic %d", sdw_be_num, dmic_num); - codec_conf = devm_kcalloc(dev, num_devs, sizeof(*codec_conf), GFP_KERNEL); + codec_conf = devm_kcalloc(dev, num_confs, sizeof(*codec_conf), GFP_KERNEL); if (!codec_conf) return -ENOMEM; @@ -335,7 +337,7 @@ static int sof_card_dai_links_create(struct snd_soc_card *card) return -ENOMEM; card->codec_conf = codec_conf; - card->num_configs = num_devs; + card->num_configs = num_confs; card->dai_link = dai_links; card->num_links = num_links; card->aux_dev = sof_aux; From 27098aaf28b96ab4e6891709062c343566d4882b Mon Sep 17 00:00:00 2001 From: Vijendar Mukunda Date: Thu, 10 Sep 2026 21:46:48 +0530 Subject: [PATCH 1194/1198] ASoC: amd: acp: fix ffs() operator precedence for SoundWire link ID ffs(link_mask - 1) computes ffs on (link_mask - 1) instead of subtracting 1 from the result of ffs(link_mask). For a typical power-of-2 link_mask this returns the wrong link ID, causing cpu_pin_id lookup to select the incorrect SoundWire manager. Fix the operator precedence to ffs(link_mask) - 1 in both acp-sdw-sof-mach.c and acp-sdw-legacy-mach.c. Fixes: 6d8348ddc56e ("ASoC: amd: acp: refactor SoundWire machine driver code") Signed-off-by: Vijendar Mukunda Reviewed-by: Mario Limonciello (AMD) Link: https://patch.msgid.link/20260910161728.1452808-4-Vijendar.Mukunda@amd.com Signed-off-by: Mark Brown --- sound/soc/amd/acp/acp-sdw-legacy-mach.c | 4 ++-- sound/soc/amd/acp/acp-sdw-sof-mach.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/sound/soc/amd/acp/acp-sdw-legacy-mach.c b/sound/soc/amd/acp/acp-sdw-legacy-mach.c index 2ea226a195c3..1a05d4288a46 100644 --- a/sound/soc/amd/acp/acp-sdw-legacy-mach.c +++ b/sound/soc/amd/acp/acp-sdw-legacy-mach.c @@ -217,7 +217,7 @@ static int create_sdw_dailink(struct snd_soc_card *card, switch (amd_ctx->acp_rev) { case ACP63_PCI_REV: - ret = get_acp63_cpu_pin_id(ffs(soc_end->link_mask - 1), + ret = get_acp63_cpu_pin_id(ffs(soc_end->link_mask) - 1, *be_id, &cpu_pin_id, dev); if (ret) return ret; @@ -225,7 +225,7 @@ static int create_sdw_dailink(struct snd_soc_card *card, case ACP70_PCI_REV: case ACP71_PCI_REV: case ACP72_PCI_REV: - ret = get_acp70_cpu_pin_id(ffs(soc_end->link_mask - 1), + ret = get_acp70_cpu_pin_id(ffs(soc_end->link_mask) - 1, *be_id, &cpu_pin_id, dev); if (ret) return ret; diff --git a/sound/soc/amd/acp/acp-sdw-sof-mach.c b/sound/soc/amd/acp/acp-sdw-sof-mach.c index b7926967593f..e6d545fd665e 100644 --- a/sound/soc/amd/acp/acp-sdw-sof-mach.c +++ b/sound/soc/amd/acp/acp-sdw-sof-mach.c @@ -132,7 +132,7 @@ static int create_sdw_dailink(struct snd_soc_card *card, } switch (amd_ctx->acp_rev) { case ACP63_PCI_REV: - ret = get_acp63_cpu_pin_id(ffs(sof_end->link_mask - 1), + ret = get_acp63_cpu_pin_id(ffs(sof_end->link_mask) - 1, *be_id, &cpu_pin_id, dev); if (ret) return ret; @@ -140,7 +140,7 @@ static int create_sdw_dailink(struct snd_soc_card *card, case ACP70_PCI_REV: case ACP71_PCI_REV: case ACP72_PCI_REV: - ret = get_acp70_cpu_pin_id(ffs(sof_end->link_mask - 1), + ret = get_acp70_cpu_pin_id(ffs(sof_end->link_mask) - 1, *be_id, &cpu_pin_id, dev); if (ret) return ret; From d57616f8be5601d210bbb0f677b9cb88a5186c3c Mon Sep 17 00:00:00 2001 From: Vijendar Mukunda Date: Thu, 10 Sep 2026 21:46:49 +0530 Subject: [PATCH 1195/1198] ASoC: amd: acp: fix card name length warning in SOF SoundWire machine driver The ALSA snd_card driver[] field is 16 bytes (including the NUL terminator), leaving 15 usable characters. The SOF framework prepends a "sof-" prefix when registering the card, so card->name = "amd-soundwire" becomes driver name "sof-amd-soundwire" which is 17 characters and overflows the driver[16] buffer, triggering a kernel warning. Fix by shortening the card name to "amd-sdw"; the resulting driver name "sof-amd-sdw" fits within the 15-character limit. Signed-off-by: Vijendar Mukunda Reviewed-by: Mario Limonciello (AMD) Link: https://patch.msgid.link/20260910161728.1452808-5-Vijendar.Mukunda@amd.com Signed-off-by: Mark Brown --- sound/soc/amd/acp/acp-sdw-sof-mach.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/amd/acp/acp-sdw-sof-mach.c b/sound/soc/amd/acp/acp-sdw-sof-mach.c index e6d545fd665e..ec3e1f5f1052 100644 --- a/sound/soc/amd/acp/acp-sdw-sof-mach.c +++ b/sound/soc/amd/acp/acp-sdw-sof-mach.c @@ -390,7 +390,7 @@ static int mc_probe(struct platform_device *pdev) ctx->private = amd_ctx; card = &ctx->card; card->dev = &pdev->dev; - card->name = "amd-soundwire"; + card->name = "amd-sdw"; card->owner = THIS_MODULE; card->late_probe = asoc_sdw_card_late_probe; From 0030f62683d5061d43b80577b7ab27196f1adb4c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Alvin=20=C5=A0ipraga?= Date: Mon, 14 Sep 2026 12:12:35 +0200 Subject: [PATCH 1196/1198] ASoC: adau1977: make the Kconfig symbols user selectable MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit SND_SOC_ADAU1977_{SPI,I2C} are missing Kconfig text, so they don't show up in menuconfig and can't be selected by a user - only by another symbol such as a machine driver. Add the text to make these symbols selectable and usable with generic machine drivers like the simple audio card. Signed-off-by: Alvin Šipraga Reviewed-by: Nuno Sá Link: https://patch.msgid.link/20260914-asoc-adau1977-fixes-v1-1-aa2f0cabd728@analog.com Signed-off-by: Mark Brown --- sound/soc/codecs/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig index f9a47e262a77..d88593c2bac8 100644 --- a/sound/soc/codecs/Kconfig +++ b/sound/soc/codecs/Kconfig @@ -524,13 +524,13 @@ config SND_SOC_ADAU1977 tristate config SND_SOC_ADAU1977_SPI - tristate + tristate "Analog Devices ADAU1977/ADAU1978/ADAU1979 CODEC - SPI" depends on SPI_MASTER select SND_SOC_ADAU1977 select REGMAP_SPI config SND_SOC_ADAU1977_I2C - tristate + tristate "Analog Devices ADAU1977/ADAU1978/ADAU1979 CODEC - I2C" depends on I2C select SND_SOC_ADAU1977 select REGMAP_I2C From 528a0da3e55b24d1113b3658e94cf432e0020913 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Alvin=20=C5=A0ipraga?= Date: Mon, 14 Sep 2026 12:12:36 +0200 Subject: [PATCH 1197/1198] ASoC: adau1977-spi: drop __maybe_unused and of_match_ptr() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since commit 5ab23c7923a1 ("modpost: Create modalias for builtin modules") MODULE_DEVICE_TABLE() is enough to reference a match table and the data isn't discarded by the linker even when the driver is built-in and CONFIG_OF is disabled. Drop the of_match_ptr() wrapping so that OF matching keeps working regardless of CONFIG_OF. This also means we can drop __maybe_unused since it's always used. The entries in adau1977_spi_of_match were also erroneously indented with spaces - replace the indentation with tabs to conform with coding style. Signed-off-by: Alvin Šipraga Reviewed-by: Nuno Sá Link: https://patch.msgid.link/20260914-asoc-adau1977-fixes-v1-2-aa2f0cabd728@analog.com Signed-off-by: Mark Brown --- sound/soc/codecs/adau1977-spi.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/sound/soc/codecs/adau1977-spi.c b/sound/soc/codecs/adau1977-spi.c index 878cde9d1014..c98da5ba9e9e 100644 --- a/sound/soc/codecs/adau1977-spi.c +++ b/sound/soc/codecs/adau1977-spi.c @@ -53,18 +53,18 @@ static const struct spi_device_id adau1977_spi_ids[] = { }; MODULE_DEVICE_TABLE(spi, adau1977_spi_ids); -static const struct of_device_id adau1977_spi_of_match[] __maybe_unused = { - { .compatible = "adi,adau1977" }, - { .compatible = "adi,adau1978" }, - { .compatible = "adi,adau1979" }, - { }, +static const struct of_device_id adau1977_spi_of_match[] = { + { .compatible = "adi,adau1977" }, + { .compatible = "adi,adau1978" }, + { .compatible = "adi,adau1979" }, + { }, }; MODULE_DEVICE_TABLE(of, adau1977_spi_of_match); static struct spi_driver adau1977_spi_driver = { .driver = { .name = "adau1977", - .of_match_table = of_match_ptr(adau1977_spi_of_match), + .of_match_table = adau1977_spi_of_match, }, .probe = adau1977_spi_probe, .id_table = adau1977_spi_ids, From 76a8fe25b97881223976363044924d5cf0511749 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Alvin=20=C5=A0ipraga?= Date: Mon, 14 Sep 2026 12:12:37 +0200 Subject: [PATCH 1198/1198] ASoC: adau1977-i2c: add OF match table for I2C MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Like for SPI, the I2C driver needs an OF match table for the kernel to be able to automatically load the driver when built as a module. Add one. Signed-off-by: Alvin Šipraga Reviewed-by: Nuno Sá Link: https://patch.msgid.link/20260914-asoc-adau1977-fixes-v1-3-aa2f0cabd728@analog.com Signed-off-by: Mark Brown --- sound/soc/codecs/adau1977-i2c.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/sound/soc/codecs/adau1977-i2c.c b/sound/soc/codecs/adau1977-i2c.c index d1c6c4ddf506..5a11cafdff36 100644 --- a/sound/soc/codecs/adau1977-i2c.c +++ b/sound/soc/codecs/adau1977-i2c.c @@ -34,9 +34,18 @@ static const struct i2c_device_id adau1977_i2c_ids[] = { }; MODULE_DEVICE_TABLE(i2c, adau1977_i2c_ids); +static const struct of_device_id adau1977_i2c_of_match[] = { + { .compatible = "adi,adau1977" }, + { .compatible = "adi,adau1978" }, + { .compatible = "adi,adau1979" }, + { }, +}; +MODULE_DEVICE_TABLE(of, adau1977_i2c_of_match); + static struct i2c_driver adau1977_i2c_driver = { .driver = { .name = "adau1977", + .of_match_table = adau1977_i2c_of_match, }, .probe = adau1977_i2c_probe, .id_table = adau1977_i2c_ids,