diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 7bcfb38498c6..dc254a3cb956 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -976,6 +976,29 @@ All cgroup core files are prefixed with "cgroup." killing cgroups is a process directed operation, i.e. it affects the whole thread-group. + cgroup.pressure + A read-write single value file that allowed values are "0" and "1". + The default is "1". + + Writing "0" to the file will disable the cgroup PSI accounting. + Writing "1" to the file will re-enable the cgroup PSI accounting. + + This control attribute is not hierarchical, so disable or enable PSI + accounting in a cgroup does not affect PSI accounting in descendants + and doesn't need pass enablement via ancestors from root. + + The reason this control attribute exists is that PSI accounts stalls for + each cgroup separately and aggregates it at each level of the hierarchy. + This may cause non-negligible overhead for some workloads when under + deep level of the hierarchy, in which case this control attribute can + be used to disable PSI accounting in the non-leaf cgroups. + + irq.pressure + A read-write nested-keyed file. + + Shows pressure stall information for IRQ/SOFTIRQ. See + :ref:`Documentation/accounting/psi.rst ` for details. + Controllers =========== diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 17d9fc5d14fb..808ade4cc008 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -76,6 +76,8 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A55 | #1530923 | ARM64_ERRATUM_1530923 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A55 | #2441007 | ARM64_ERRATUM_2441007 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A57 | #832075 | ARM64_ERRATUM_832075 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A57 | #852523 | N/A | diff --git a/Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml b/Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml index 92e0f8c3eff2..99e01f4d0a69 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml @@ -66,6 +66,11 @@ properties: - enum: - allwinner,sun20i-d1-plic - const: thead,c900-plic + - items: + - const: sifive,plic-1.0.0 + - const: riscv,plic0 + deprecated: true + description: For the QEMU virt machine only reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/leds/common.yaml b/Documentation/devicetree/bindings/leds/common.yaml index 328952d7acbb..3c14a98430e1 100644 --- a/Documentation/devicetree/bindings/leds/common.yaml +++ b/Documentation/devicetree/bindings/leds/common.yaml @@ -79,24 +79,27 @@ properties: the LED. $ref: /schemas/types.yaml#/definitions/string - enum: - # LED will act as a back-light, controlled by the framebuffer system - - backlight - # LED will turn on (but for leds-gpio see "default-state" property in - # Documentation/devicetree/bindings/leds/leds-gpio.yaml) - - default-on - # LED "double" flashes at a load average based rate - - heartbeat - # LED indicates disk activity - - disk-activity - # LED indicates IDE disk activity (deprecated), in new implementations - # use "disk-activity" - - ide-disk - # LED flashes at a fixed, configurable rate - - timer - # LED alters the brightness for the specified duration with one software - # timer (requires "led-pattern" property) - - pattern + oneOf: + - enum: + # LED will act as a back-light, controlled by the framebuffer system + - backlight + # LED will turn on (but for leds-gpio see "default-state" property in + # Documentation/devicetree/bindings/leds/leds-gpio.yaml) + - default-on + # LED "double" flashes at a load average based rate + - heartbeat + # LED indicates disk activity + - disk-activity + # LED indicates IDE disk activity (deprecated), in new implementations + # use "disk-activity" + - ide-disk + # LED flashes at a fixed, configurable rate + - timer + # LED alters the brightness for the specified duration with one software + # timer (requires "led-pattern" property) + - pattern + # LED is triggered by SD/MMC activity + - pattern: "^mmc[0-9]+$" led-pattern: description: | diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml index 873dd12f6e89..90a7cabf58fe 100644 --- a/Documentation/devicetree/bindings/riscv/cpus.yaml +++ b/Documentation/devicetree/bindings/riscv/cpus.yaml @@ -9,6 +9,7 @@ title: RISC-V bindings for 'cpus' DT nodes maintainers: - Paul Walmsley - Palmer Dabbelt + - Conor Dooley description: | This document uses some terminology common to the RISC-V community @@ -79,9 +80,7 @@ properties: insensitive, letters in the riscv,isa string must be all lowercase to simplify parsing. $ref: "/schemas/types.yaml#/definitions/string" - enum: - - rv64imac - - rv64imafdc + pattern: ^rv(?:64|32)imaf?d?q?c?b?v?k?h?(?:_[hsxz](?:[a-z])+)*$ # RISC-V requires 'timebase-frequency' in /cpus, so disallow it here timebase-frequency: false diff --git a/Documentation/devicetree/bindings/riscv/microchip.yaml b/Documentation/devicetree/bindings/riscv/microchip.yaml index 37f97ee4fe46..714d0fcab399 100644 --- a/Documentation/devicetree/bindings/riscv/microchip.yaml +++ b/Documentation/devicetree/bindings/riscv/microchip.yaml @@ -7,8 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Microchip PolarFire SoC-based boards maintainers: - - Cyril Jean - - Lewis Hanly + - Conor Dooley + - Daire McNamara description: Microchip PolarFire SoC-based boards @@ -17,12 +17,20 @@ properties: $nodename: const: '/' compatible: - items: - - enum: - - microchip,mpfs-icicle-kit - - microchip,mpfs-icicle-reference-rtlv2203 - - sundance,polarberry - - const: microchip,mpfs + oneOf: + - items: + - enum: + - microchip,mpfs-icicle-reference-rtlv2203 + - microchip,mpfs-icicle-reference-rtlv2210 + - const: microchip,mpfs-icicle-kit + - const: microchip,mpfs + + - items: + - enum: + - aries,m100pfsevp + - microchip,mpfs-sev-kit + - sundance,polarberry + - const: microchip,mpfs additionalProperties: true diff --git a/Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml b/Documentation/devicetree/bindings/riscv/sifive,ccache0.yaml similarity index 83% rename from Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml rename to Documentation/devicetree/bindings/riscv/sifive,ccache0.yaml index ca3b9be58058..bf3f07421f7e 100644 --- a/Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml +++ b/Documentation/devicetree/bindings/riscv/sifive,ccache0.yaml @@ -2,18 +2,18 @@ # Copyright (C) 2020 SiFive, Inc. %YAML 1.2 --- -$id: http://devicetree.org/schemas/riscv/sifive-l2-cache.yaml# +$id: http://devicetree.org/schemas/riscv/sifive,ccache0.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# -title: SiFive L2 Cache Controller +title: SiFive Composable Cache Controller maintainers: - Sagar Kadam - Paul Walmsley description: - The SiFive Level 2 Cache Controller is used to provide access to fast copies - of memory for masters in a Core Complex. The Level 2 Cache Controller also + The SiFive Composable Cache Controller is used to provide access to fast copies + of memory for masters in a Core Complex. The Composable Cache Controller also acts as directory-based coherency manager. All the properties in ePAPR/DeviceTree specification applies for this platform. @@ -22,6 +22,7 @@ select: compatible: contains: enum: + - sifive,ccache0 - sifive,fu540-c000-ccache - sifive,fu740-c000-ccache @@ -33,6 +34,7 @@ properties: oneOf: - items: - enum: + - sifive,ccache0 - sifive,fu540-c000-ccache - sifive,fu740-c000-ccache - const: cache @@ -45,7 +47,7 @@ properties: const: 64 cache-level: - const: 2 + enum: [2, 3] cache-sets: enum: [1024, 2048] @@ -115,6 +117,22 @@ allOf: cache-sets: const: 1024 + - if: + properties: + compatible: + contains: + const: sifive,ccache0 + + then: + properties: + cache-level: + enum: [2, 3] + + else: + properties: + cache-level: + const: 2 + additionalProperties: false required: diff --git a/Documentation/devicetree/bindings/timer/sifive,clint.yaml b/Documentation/devicetree/bindings/timer/sifive,clint.yaml index e64f46339079..bbad24165837 100644 --- a/Documentation/devicetree/bindings/timer/sifive,clint.yaml +++ b/Documentation/devicetree/bindings/timer/sifive,clint.yaml @@ -22,12 +22,18 @@ description: properties: compatible: - items: - - enum: - - sifive,fu540-c000-clint - - starfive,jh7100-clint - - canaan,k210-clint - - const: sifive,clint0 + oneOf: + - items: + - enum: + - sifive,fu540-c000-clint + - starfive,jh7100-clint + - canaan,k210-clint + - const: sifive,clint0 + - items: + - const: sifive,clint0 + - const: riscv,clint0 + deprecated: true + description: For the QEMU virt machine only description: Should be ",-clint" and "sifive,clint". diff --git a/Documentation/riscv/index.rst b/Documentation/riscv/index.rst index e23b876ad6eb..2e5b18fbb145 100644 --- a/Documentation/riscv/index.rst +++ b/Documentation/riscv/index.rst @@ -8,6 +8,7 @@ RISC-V architecture boot-image-header vm-layout patch-acceptance + uabi features diff --git a/Documentation/riscv/uabi.rst b/Documentation/riscv/uabi.rst new file mode 100644 index 000000000000..21a82cfb6c4d --- /dev/null +++ b/Documentation/riscv/uabi.rst @@ -0,0 +1,6 @@ +.. SPDX-License-Identifier: GPL-2.0 + +RISC-V Linux User ABI +===================== + +Misaligned accesses are supported in userspace, but they may perform poorly. diff --git a/MAINTAINERS b/MAINTAINERS index 15fe1e7731b5..5a51bde5d201 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -752,7 +752,7 @@ ALIBABA PMU DRIVER M: Shuai Xue S: Supported F: Documentation/admin-guide/perf/alibaba_pmu.rst -F: drivers/perf/alibaba_uncore_dwr_pmu.c +F: drivers/perf/alibaba_uncore_drw_pmu.c ALIENWARE WMI DRIVER L: Dell.Client.Kernel@dell.com @@ -17709,6 +17709,7 @@ M: Palmer Dabbelt M: Albert Ou L: linux-riscv@lists.infradead.org S: Supported +Q: https://patchwork.kernel.org/project/linux-riscv/list/ P: Documentation/riscv/patch-acceptance.rst T: git git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux.git F: arch/riscv/ @@ -17720,12 +17721,13 @@ M: Conor Dooley M: Daire McNamara L: linux-riscv@lists.infradead.org S: Supported -F: Documentation/devicetree/bindings/clock/microchip,mpfs.yaml +F: Documentation/devicetree/bindings/clock/microchip,mpfs*.yaml F: Documentation/devicetree/bindings/gpio/microchip,mpfs-gpio.yaml F: Documentation/devicetree/bindings/i2c/microchip,corei2c.yaml F: Documentation/devicetree/bindings/mailbox/microchip,mpfs-mailbox.yaml F: Documentation/devicetree/bindings/net/can/microchip,mpfs-can.yaml F: Documentation/devicetree/bindings/pwm/microchip,corepwm.yaml +F: Documentation/devicetree/bindings/riscv/microchip.yaml F: Documentation/devicetree/bindings/soc/microchip/microchip,mpfs-sys-controller.yaml F: Documentation/devicetree/bindings/spi/microchip,mpfs-spi.yaml F: Documentation/devicetree/bindings/usb/microchip,mpfs-musb.yaml diff --git a/arch/arm/mach-mmp/devices.c b/arch/arm/mach-mmp/devices.c index 79f4a2aa5475..9968239d8041 100644 --- a/arch/arm/mach-mmp/devices.c +++ b/arch/arm/mach-mmp/devices.c @@ -238,7 +238,7 @@ void pxa_usb_phy_deinit(void __iomem *phy_reg) static u64 __maybe_unused usb_dma_mask = ~(u32)0; #if IS_ENABLED(CONFIG_PHY_PXA_USB) -struct resource pxa168_usb_phy_resources[] = { +static struct resource pxa168_usb_phy_resources[] = { [0] = { .start = PXA168_U2O_PHYBASE, .end = PXA168_U2O_PHYBASE + USB_PHY_RANGE, @@ -259,7 +259,7 @@ struct platform_device pxa168_device_usb_phy = { #endif /* CONFIG_PHY_PXA_USB */ #if IS_ENABLED(CONFIG_USB_MV_UDC) -struct resource pxa168_u2o_resources[] = { +static struct resource pxa168_u2o_resources[] = { /* regbase */ [0] = { .start = PXA168_U2O_REGBASE + U2x_CAPREGS_OFFSET, @@ -294,7 +294,7 @@ struct platform_device pxa168_device_u2o = { #endif /* CONFIG_USB_MV_UDC */ #if IS_ENABLED(CONFIG_USB_EHCI_MV_U2O) -struct resource pxa168_u2oehci_resources[] = { +static struct resource pxa168_u2oehci_resources[] = { [0] = { .start = PXA168_U2O_REGBASE, .end = PXA168_U2O_REGBASE + USB_REG_RANGE, @@ -321,7 +321,7 @@ struct platform_device pxa168_device_u2oehci = { #endif #if IS_ENABLED(CONFIG_USB_MV_OTG) -struct resource pxa168_u2ootg_resources[] = { +static struct resource pxa168_u2ootg_resources[] = { /* regbase */ [0] = { .start = PXA168_U2O_REGBASE + U2x_CAPREGS_OFFSET, diff --git a/arch/arm/mach-spear/generic.h b/arch/arm/mach-spear/generic.h index 43b7996ab754..9e36920d4cfd 100644 --- a/arch/arm/mach-spear/generic.h +++ b/arch/arm/mach-spear/generic.h @@ -25,11 +25,8 @@ extern struct pl022_ssp_controller pl022_plat_data; extern struct pl08x_platform_data pl080_plat_data; void __init spear_setup_of_timer(void); -void __init spear3xx_clk_init(void __iomem *misc_base, - void __iomem *soc_config_base); void __init spear3xx_map_io(void); void __init spear3xx_dt_init_irq(void); -void __init spear6xx_clk_init(void __iomem *misc_base); void __init spear13xx_map_io(void); void __init spear13xx_l2x0_init(void); diff --git a/arch/arm/mach-spear/spear3xx.c b/arch/arm/mach-spear/spear3xx.c index 2ba406e92c41..7ef9670d3029 100644 --- a/arch/arm/mach-spear/spear3xx.c +++ b/arch/arm/mach-spear/spear3xx.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include "pl080.h" diff --git a/arch/arm/mach-spear/spear6xx.c b/arch/arm/mach-spear/spear6xx.c index 58183493e06d..f0a1e704cceb 100644 --- a/arch/arm/mach-spear/spear6xx.c +++ b/arch/arm/mach-spear/spear6xx.c @@ -12,6 +12,7 @@ #include #include +#include #include #include #include @@ -339,7 +340,7 @@ static struct pl08x_platform_data spear6xx_pl080_plat_data = { * 0xD0000000 0xFD000000 * 0xFC000000 0xFC000000 */ -struct map_desc spear6xx_io_desc[] __initdata = { +static struct map_desc spear6xx_io_desc[] __initdata = { { .virtual = (unsigned long)VA_SPEAR6XX_ML_CPU_BASE, .pfn = __phys_to_pfn(SPEAR_ICM3_ML1_2_BASE), @@ -359,12 +360,12 @@ struct map_desc spear6xx_io_desc[] __initdata = { }; /* This will create static memory mapping for selected devices */ -void __init spear6xx_map_io(void) +static void __init spear6xx_map_io(void) { iotable_init(spear6xx_io_desc, ARRAY_SIZE(spear6xx_io_desc)); } -void __init spear6xx_timer_init(void) +static void __init spear6xx_timer_init(void) { char pclk_name[] = "pll3_clk"; struct clk *gpt_clk, *pclk; @@ -394,7 +395,7 @@ void __init spear6xx_timer_init(void) } /* Add auxdata to pass platform data */ -struct of_dev_auxdata spear6xx_auxdata_lookup[] __initdata = { +static struct of_dev_auxdata spear6xx_auxdata_lookup[] __initdata = { OF_DEV_AUXDATA("arm,pl080", SPEAR_ICM3_DMA_BASE, NULL, &spear6xx_pl080_plat_data), {} diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index f6737d2f37b2..505c8a1ccbe0 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -632,6 +632,23 @@ config ARM64_ERRATUM_1530923 config ARM64_WORKAROUND_REPEAT_TLBI bool +config ARM64_ERRATUM_2441007 + bool "Cortex-A55: Completion of affected memory accesses might not be guaranteed by completion of a TLBI" + default y + select ARM64_WORKAROUND_REPEAT_TLBI + help + This option adds a workaround for ARM Cortex-A55 erratum #2441007. + + Under very rare circumstances, affected Cortex-A55 CPUs + may not handle a race between a break-before-make sequence on one + CPU, and another CPU accessing the same page. This could allow a + store to a page that has been unmapped. + + Work around this by adding the affected CPUs to the list that needs + TLB sequences to be done twice. + + If unsure, say Y. + config ARM64_ERRATUM_1286807 bool "Cortex-A76: Modification of the translation table for a virtual address might lead to read-after-read ordering violation" default y diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 8aa0d276a636..abc418650fec 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -60,6 +60,7 @@ #define ARM_CPU_IMP_FUJITSU 0x46 #define ARM_CPU_IMP_HISI 0x48 #define ARM_CPU_IMP_APPLE 0x61 +#define ARM_CPU_IMP_AMPERE 0xC0 #define ARM_CPU_PART_AEM_V8 0xD0F #define ARM_CPU_PART_FOUNDATION 0xD00 @@ -123,6 +124,8 @@ #define APPLE_CPU_PART_M1_ICESTORM_MAX 0x028 #define APPLE_CPU_PART_M1_FIRESTORM_MAX 0x029 +#define AMPERE_CPU_PART_AMPERE1 0xAC3 + #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) #define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72) @@ -172,6 +175,7 @@ #define MIDR_APPLE_M1_FIRESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_PRO) #define MIDR_APPLE_M1_ICESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_MAX) #define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX) +#define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ #define MIDR_FUJITSU_ERRATUM_010001 MIDR_FUJITSU_A64FX diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 58ca4f6b25d6..89ac00084f38 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -230,6 +230,11 @@ static const struct arm64_cpu_capabilities arm64_repeat_tlbi_list[] = { ERRATA_MIDR_RANGE(MIDR_QCOM_KRYO_4XX_GOLD, 0xc, 0xe, 0xf, 0xe), }, #endif +#ifdef CONFIG_ARM64_ERRATUM_2441007 + { + ERRATA_MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), + }, +#endif #ifdef CONFIG_ARM64_ERRATUM_2441009 { /* Cortex-A510 r0p0 -> r1p1. Fixed in r1p2 */ diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index aca88470fb69..7467217c1eaf 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -48,7 +48,12 @@ static void mte_sync_page_tags(struct page *page, pte_t old_pte, if (!pte_is_tagged) return; - mte_clear_page_tags(page_address(page)); + /* + * Test PG_mte_tagged again in case it was racing with another + * set_pte_at(). + */ + if (!test_and_set_bit(PG_mte_tagged, &page->flags)) + mte_clear_page_tags(page_address(page)); } void mte_sync_tags(pte_t old_pte, pte_t pte) @@ -64,7 +69,7 @@ void mte_sync_tags(pte_t old_pte, pte_t pte) /* if PG_mte_tagged is set, tags have already been initialised */ for (i = 0; i < nr_pages; i++, page++) { - if (!test_and_set_bit(PG_mte_tagged, &page->flags)) + if (!test_bit(PG_mte_tagged, &page->flags)) mte_sync_page_tags(page, old_pte, check_swap, pte_is_tagged); } diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index a8ea1637b137..bfce41c2a53b 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -868,6 +868,10 @@ u8 spectre_bhb_loop_affected(int scope) MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1), {}, }; + static const struct midr_range spectre_bhb_k11_list[] = { + MIDR_ALL_VERSIONS(MIDR_AMPERE1), + {}, + }; static const struct midr_range spectre_bhb_k8_list[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A72), MIDR_ALL_VERSIONS(MIDR_CORTEX_A57), @@ -878,6 +882,8 @@ u8 spectre_bhb_loop_affected(int scope) k = 32; else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k24_list)) k = 24; + else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k11_list)) + k = 11; else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k8_list)) k = 8; diff --git a/arch/arm64/mm/mteswap.c b/arch/arm64/mm/mteswap.c index 4334dec93bd4..bed803d8e158 100644 --- a/arch/arm64/mm/mteswap.c +++ b/arch/arm64/mm/mteswap.c @@ -53,7 +53,12 @@ bool mte_restore_tags(swp_entry_t entry, struct page *page) if (!tags) return false; - mte_restore_page_tags(page_address(page), tags); + /* + * Test PG_mte_tagged again in case it was racing with another + * set_pte_at(). + */ + if (!test_and_set_bit(PG_mte_tagged, &page->flags)) + mte_restore_page_tags(page_address(page), tags); return true; } diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index 7f1fb36f208c..384757a7eda9 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -732,7 +732,7 @@ EndSysreg Sysreg SCTLR_EL1 3 0 1 0 0 Field 63 TIDCP -Field 62 SPINMASK +Field 62 SPINTMASK Field 61 NMI Field 60 EnTP2 Res0 59:58 diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h index 8ea57e2f0e04..946704bee599 100644 --- a/arch/loongarch/include/asm/pgtable.h +++ b/arch/loongarch/include/asm/pgtable.h @@ -412,6 +412,9 @@ static inline void update_mmu_cache(struct vm_area_struct *vma, __update_tlb(vma, address, ptep); } +#define __HAVE_ARCH_UPDATE_MMU_TLB +#define update_mmu_tlb update_mmu_cache + static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { diff --git a/arch/parisc/include/asm/alternative.h b/arch/parisc/include/asm/alternative.h index 0ec54f43d6d2..1ed45fd085d3 100644 --- a/arch/parisc/include/asm/alternative.h +++ b/arch/parisc/include/asm/alternative.h @@ -22,10 +22,10 @@ struct alt_instr { s32 orig_offset; /* offset to original instructions */ - s32 len; /* end of original instructions */ - u32 cond; /* see ALT_COND_XXX */ + s16 len; /* end of original instructions */ + u16 cond; /* see ALT_COND_XXX */ u32 replacement; /* replacement instruction or code */ -}; +} __packed; void set_kernel_text_rw(int enable_read_write); void apply_alternatives_all(void); @@ -35,8 +35,9 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end, /* Alternative SMP implementation. */ #define ALTERNATIVE(cond, replacement) "!0:" \ ".section .altinstructions, \"aw\" !" \ - ".word (0b-4-.), 1, " __stringify(cond) "," \ - __stringify(replacement) " !" \ + ".word (0b-4-.) !" \ + ".hword 1, " __stringify(cond) " !" \ + ".word " __stringify(replacement) " !" \ ".previous" #else @@ -44,15 +45,17 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end, /* to replace one single instructions by a new instruction */ #define ALTERNATIVE(from, to, cond, replacement)\ .section .altinstructions, "aw" ! \ - .word (from - .), (to - from)/4 ! \ - .word cond, replacement ! \ + .word (from - .) ! \ + .hword (to - from)/4, cond ! \ + .word replacement ! \ .previous /* to replace multiple instructions by new code */ #define ALTERNATIVE_CODE(from, num_instructions, cond, new_instr_ptr)\ .section .altinstructions, "aw" ! \ - .word (from - .), -num_instructions ! \ - .word cond, (new_instr_ptr - .) ! \ + .word (from - .) ! \ + .hword -num_instructions, cond ! \ + .word (new_instr_ptr - .) ! \ .previous #endif /* __ASSEMBLY__ */ diff --git a/arch/parisc/include/asm/pdc.h b/arch/parisc/include/asm/pdc.h index b643092d4b98..fcbcf9a96c11 100644 --- a/arch/parisc/include/asm/pdc.h +++ b/arch/parisc/include/asm/pdc.h @@ -19,9 +19,6 @@ extern unsigned long parisc_pat_pdc_cap; /* PDC capabilities (PAT) */ #define PDC_TYPE_SYSTEM_MAP 1 /* 32-bit, but supports PDC_SYSTEM_MAP */ #define PDC_TYPE_SNAKE 2 /* Doesn't support SYSTEM_MAP */ -void pdc_console_init(void); /* in pdc_console.c */ -void pdc_console_restart(void); - void setup_pdc(void); /* in inventory.c */ /* wrapper-functions from pdc.c */ diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index df7b931865d2..ecd028854469 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -192,6 +192,11 @@ extern void __update_cache(pte_t pte); #define _PAGE_PRESENT_BIT 22 /* (0x200) Software: translation valid */ #define _PAGE_HPAGE_BIT 21 /* (0x400) Software: Huge Page */ #define _PAGE_USER_BIT 20 /* (0x800) Software: User accessible page */ +#ifdef CONFIG_HUGETLB_PAGE +#define _PAGE_SPECIAL_BIT _PAGE_DMB_BIT /* DMB feature is currently unused */ +#else +#define _PAGE_SPECIAL_BIT _PAGE_HPAGE_BIT /* use unused HUGE PAGE bit */ +#endif /* N.B. The bits are defined in terms of a 32 bit word above, so the */ /* following macro is ok for both 32 and 64 bit. */ @@ -219,7 +224,7 @@ extern void __update_cache(pte_t pte); #define _PAGE_PRESENT (1 << xlate_pabit(_PAGE_PRESENT_BIT)) #define _PAGE_HUGE (1 << xlate_pabit(_PAGE_HPAGE_BIT)) #define _PAGE_USER (1 << xlate_pabit(_PAGE_USER_BIT)) -#define _PAGE_SPECIAL (_PAGE_DMB) +#define _PAGE_SPECIAL (1 << xlate_pabit(_PAGE_SPECIAL_BIT)) #define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | _PAGE_DIRTY | _PAGE_ACCESSED) #define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_SPECIAL) diff --git a/arch/parisc/kernel/alternative.c b/arch/parisc/kernel/alternative.c index daa1e9047275..66f5672c70bd 100644 --- a/arch/parisc/kernel/alternative.c +++ b/arch/parisc/kernel/alternative.c @@ -26,7 +26,7 @@ void __init_or_module apply_alternatives(struct alt_instr *start, struct alt_instr *entry; int index = 0, applied = 0; int num_cpus = num_online_cpus(); - u32 cond_check; + u16 cond_check; cond_check = ALT_COND_ALWAYS | ((num_cpus == 1) ? ALT_COND_NO_SMP : 0) | @@ -45,8 +45,9 @@ void __init_or_module apply_alternatives(struct alt_instr *start, for (entry = start; entry < end; entry++, index++) { - u32 *from, cond, replacement; - s32 len; + u32 *from, replacement; + u16 cond; + s16 len; from = (u32 *)((ulong)&entry->orig_offset + entry->orig_offset); len = entry->len; diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index df8102fb435f..0e5ebfe8d9d2 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -499,6 +499,10 @@ * Finally, _PAGE_READ goes in the top bit of PL1 (so we * trigger an access rights trap in user space if the user * tries to read an unreadable page */ +#if _PAGE_SPECIAL_BIT == _PAGE_DMB_BIT + /* need to drop DMB bit, as it's used as SPECIAL flag */ + depi 0,_PAGE_SPECIAL_BIT,1,\pte +#endif depd \pte,8,7,\prot /* PAGE_USER indicates the page can be read with user privileges, @@ -529,6 +533,10 @@ * makes the tlb entry for the differently formatted pa11 * insertion instructions */ .macro make_insert_tlb_11 spc,pte,prot +#if _PAGE_SPECIAL_BIT == _PAGE_DMB_BIT + /* need to drop DMB bit, as it's used as SPECIAL flag */ + depi 0,_PAGE_SPECIAL_BIT,1,\pte +#endif zdep \spc,30,15,\prot dep \pte,8,7,\prot extru,= \pte,_PAGE_NO_CACHE_BIT,1,%r0 diff --git a/arch/parisc/kernel/pdc_cons.c b/arch/parisc/kernel/pdc_cons.c index 2661cdd256ae..7d0989f523d0 100644 --- a/arch/parisc/kernel/pdc_cons.c +++ b/arch/parisc/kernel/pdc_cons.c @@ -1,46 +1,18 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * PDC Console support - ie use firmware to dump text via boot console + * PDC early console support - use PDC firmware to dump text via boot console * - * Copyright (C) 1999-2003 Matthew Wilcox - * Copyright (C) 2000 Martin K Petersen - * Copyright (C) 2000 John Marvin - * Copyright (C) 2000-2003 Paul Bame - * Copyright (C) 2000 Philipp Rumpf - * Copyright (C) 2000 Michael Ang - * Copyright (C) 2000 Grant Grundler - * Copyright (C) 2001-2002 Ryan Bradetich - * Copyright (C) 2001 Helge Deller - * Copyright (C) 2001 Thomas Bogendoerfer - * Copyright (C) 2002 Randolph Chung - * Copyright (C) 2010 Guy Martin + * Copyright (C) 2001-2022 Helge Deller */ -/* - * The PDC console is a simple console, which can be used for debugging - * boot related problems on HP PA-RISC machines. It is also useful when no - * other console works. - * - * This code uses the ROM (=PDC) based functions to read and write characters - * from and to PDC's boot path. - */ - -/* Define EARLY_BOOTUP_DEBUG to debug kernel related boot problems. - * On production kernels EARLY_BOOTUP_DEBUG should be undefined. */ -#define EARLY_BOOTUP_DEBUG - - -#include #include -#include #include -#include -#include +#include +#include #include /* for PAGE0 */ #include /* for iodc_call() proto and friends */ static DEFINE_SPINLOCK(pdc_console_lock); -static struct console pdc_cons; static void pdc_console_write(struct console *co, const char *s, unsigned count) { @@ -54,7 +26,8 @@ static void pdc_console_write(struct console *co, const char *s, unsigned count) spin_unlock_irqrestore(&pdc_console_lock, flags); } -int pdc_console_poll_key(struct console *co) +#ifdef CONFIG_KGDB +static int kgdb_pdc_read_char(void) { int c; unsigned long flags; @@ -63,201 +36,40 @@ int pdc_console_poll_key(struct console *co) c = pdc_iodc_getc(); spin_unlock_irqrestore(&pdc_console_lock, flags); - return c; + return (c <= 0) ? NO_POLL_CHAR : c; } -static int pdc_console_setup(struct console *co, char *options) +static void kgdb_pdc_write_char(u8 chr) { - return 0; + if (PAGE0->mem_cons.cl_class != CL_DUPLEX) + pdc_console_write(NULL, &chr, 1); } -#if defined(CONFIG_PDC_CONSOLE) -#include -#include - -#define PDC_CONS_POLL_DELAY (30 * HZ / 1000) - -static void pdc_console_poll(struct timer_list *unused); -static DEFINE_TIMER(pdc_console_timer, pdc_console_poll); -static struct tty_port tty_port; - -static int pdc_console_tty_open(struct tty_struct *tty, struct file *filp) -{ - tty_port_tty_set(&tty_port, tty); - mod_timer(&pdc_console_timer, jiffies + PDC_CONS_POLL_DELAY); - - return 0; -} - -static void pdc_console_tty_close(struct tty_struct *tty, struct file *filp) -{ - if (tty->count == 1) { - del_timer_sync(&pdc_console_timer); - tty_port_tty_set(&tty_port, NULL); - } -} - -static int pdc_console_tty_write(struct tty_struct *tty, const unsigned char *buf, int count) -{ - pdc_console_write(NULL, buf, count); - return count; -} - -static unsigned int pdc_console_tty_write_room(struct tty_struct *tty) -{ - return 32768; /* no limit, no buffer used */ -} - -static const struct tty_operations pdc_console_tty_ops = { - .open = pdc_console_tty_open, - .close = pdc_console_tty_close, - .write = pdc_console_tty_write, - .write_room = pdc_console_tty_write_room, +static struct kgdb_io kgdb_pdc_io_ops = { + .name = "kgdb_pdc", + .read_char = kgdb_pdc_read_char, + .write_char = kgdb_pdc_write_char, }; - -static void pdc_console_poll(struct timer_list *unused) -{ - int data, count = 0; - - while (1) { - data = pdc_console_poll_key(NULL); - if (data == -1) - break; - tty_insert_flip_char(&tty_port, data & 0xFF, TTY_NORMAL); - count ++; - } - - if (count) - tty_flip_buffer_push(&tty_port); - - if (pdc_cons.flags & CON_ENABLED) - mod_timer(&pdc_console_timer, jiffies + PDC_CONS_POLL_DELAY); -} - -static struct tty_driver *pdc_console_tty_driver; - -static int __init pdc_console_tty_driver_init(void) -{ - struct tty_driver *driver; - int err; - - /* Check if the console driver is still registered. - * It is unregistered if the pdc console was not selected as the - * primary console. */ - - struct console *tmp; - - console_lock(); - for_each_console(tmp) - if (tmp == &pdc_cons) - break; - console_unlock(); - - if (!tmp) { - printk(KERN_INFO "PDC console driver not registered anymore, not creating %s\n", pdc_cons.name); - return -ENODEV; - } - - printk(KERN_INFO "The PDC console driver is still registered, removing CON_BOOT flag\n"); - pdc_cons.flags &= ~CON_BOOT; - - driver = tty_alloc_driver(1, TTY_DRIVER_REAL_RAW | - TTY_DRIVER_RESET_TERMIOS); - if (IS_ERR(driver)) - return PTR_ERR(driver); - - tty_port_init(&tty_port); - - driver->driver_name = "pdc_cons"; - driver->name = "ttyB"; - driver->major = MUX_MAJOR; - driver->minor_start = 0; - driver->type = TTY_DRIVER_TYPE_SYSTEM; - driver->init_termios = tty_std_termios; - tty_set_operations(driver, &pdc_console_tty_ops); - tty_port_link_device(&tty_port, driver, 0); - - err = tty_register_driver(driver); - if (err) { - printk(KERN_ERR "Unable to register the PDC console TTY driver\n"); - tty_port_destroy(&tty_port); - tty_driver_kref_put(driver); - return err; - } - - pdc_console_tty_driver = driver; - - return 0; -} -device_initcall(pdc_console_tty_driver_init); - -static struct tty_driver * pdc_console_device (struct console *c, int *index) -{ - *index = c->index; - return pdc_console_tty_driver; -} -#else -#define pdc_console_device NULL #endif -static struct console pdc_cons = { - .name = "ttyB", - .write = pdc_console_write, - .device = pdc_console_device, - .setup = pdc_console_setup, - .flags = CON_BOOT | CON_PRINTBUFFER, - .index = -1, -}; - -static int pdc_console_initialized; - -static void pdc_console_init_force(void) +static int __init pdc_earlycon_setup(struct earlycon_device *device, + const char *opt) { - if (pdc_console_initialized) - return; - ++pdc_console_initialized; - + struct console *earlycon_console; + /* If the console is duplex then copy the COUT parameters to CIN. */ if (PAGE0->mem_cons.cl_class == CL_DUPLEX) memcpy(&PAGE0->mem_kbd, &PAGE0->mem_cons, sizeof(PAGE0->mem_cons)); - /* register the pdc console */ - register_console(&pdc_cons); -} + earlycon_console = device->con; + earlycon_console->write = pdc_console_write; + device->port.iotype = UPIO_MEM32BE; -void __init pdc_console_init(void) -{ -#if defined(EARLY_BOOTUP_DEBUG) || defined(CONFIG_PDC_CONSOLE) - pdc_console_init_force(); -#endif -#ifdef EARLY_BOOTUP_DEBUG - printk(KERN_INFO "Initialized PDC Console for debugging.\n"); +#ifdef CONFIG_KGDB + kgdb_register_io_module(&kgdb_pdc_io_ops); #endif + + return 0; } - -/* - * Used for emergencies. Currently only used if an HPMC occurs. If an - * HPMC occurs, it is possible that the current console may not be - * properly initialised after the PDC IO reset. This routine unregisters - * all of the current consoles, reinitializes the pdc console and - * registers it. - */ - -void pdc_console_restart(void) -{ - struct console *console; - - if (pdc_console_initialized) - return; - - /* If we've already seen the output, don't bother to print it again */ - if (console_drivers != NULL) - pdc_cons.flags &= ~CON_PRINTBUFFER; - - while ((console = console_drivers) != NULL) - unregister_console(console_drivers); - - /* force registering the pdc console */ - pdc_console_init_force(); -} +EARLYCON_DECLARE(pdc, pdc_earlycon_setup); diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c index f005ddedb50e..375f38d6e1a4 100644 --- a/arch/parisc/kernel/setup.c +++ b/arch/parisc/kernel/setup.c @@ -70,6 +70,10 @@ void __init setup_cmdline(char **cmdline_p) strlcat(p, "tty0", COMMAND_LINE_SIZE); } + /* default to use early console */ + if (!strstr(p, "earlycon")) + strlcat(p, " earlycon=pdc", COMMAND_LINE_SIZE); + #ifdef CONFIG_BLK_DEV_INITRD if (boot_args[2] != 0) /* did palo pass us a ramdisk? */ { @@ -139,8 +143,6 @@ void __init setup_arch(char **cmdline_p) if (__pa((unsigned long) &_end) >= KERNEL_INITIAL_SIZE) panic("KERNEL_INITIAL_ORDER too small!"); - pdc_console_init(); - #ifdef CONFIG_64BIT if(parisc_narrow_firmware) { printk(KERN_INFO "Kernel is using PDC in 32-bit mode.\n"); diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index b78f1b9d45c1..f9696fbf646c 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -239,13 +239,6 @@ void die_if_kernel(char *str, struct pt_regs *regs, long err) /* unlock the pdc lock if necessary */ pdc_emergency_unlock(); - /* maybe the kernel hasn't booted very far yet and hasn't been able - * to initialize the serial or STI console. In that case we should - * re-enable the pdc console, so that the user will be able to - * identify the problem. */ - if (!console_drivers) - pdc_console_restart(); - if (err) printk(KERN_CRIT "%s (pid %d): %s (code %ld)\n", current->comm, task_pid_nr(current), str, err); @@ -429,10 +422,6 @@ void parisc_terminate(char *msg, struct pt_regs *regs, int code, unsigned long o /* unlock the pdc lock if necessary */ pdc_emergency_unlock(); - /* restart pdc console if necessary */ - if (!console_drivers) - pdc_console_restart(); - /* Not all paths will gutter the processor... */ switch(code){ @@ -482,9 +471,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs) unsigned long fault_space = 0; int si_code; - if (code == 1) - pdc_console_restart(); /* switch back to pdc if HPMC */ - else if (!irqs_disabled_flags(regs->gr[0])) + if (!irqs_disabled_flags(regs->gr[0])) local_irq_enable(); /* Security check: diff --git a/arch/powerpc/include/asm/syscalls.h b/arch/powerpc/include/asm/syscalls.h index 9840d572da55..a1142496cd58 100644 --- a/arch/powerpc/include/asm/syscalls.h +++ b/arch/powerpc/include/asm/syscalls.h @@ -89,6 +89,22 @@ long compat_sys_rt_sigreturn(void); * responsible for combining parameter pairs. */ +#ifdef CONFIG_PPC32 +long sys_ppc_pread64(unsigned int fd, + char __user *ubuf, compat_size_t count, + u32 reg6, u32 pos1, u32 pos2); +long sys_ppc_pwrite64(unsigned int fd, + const char __user *ubuf, compat_size_t count, + u32 reg6, u32 pos1, u32 pos2); +long sys_ppc_readahead(int fd, u32 r4, + u32 offset1, u32 offset2, u32 count); +long sys_ppc_truncate64(const char __user *path, u32 reg4, + unsigned long len1, unsigned long len2); +long sys_ppc_ftruncate64(unsigned int fd, u32 reg4, + unsigned long len1, unsigned long len2); +long sys_ppc32_fadvise64(int fd, u32 unused, u32 offset1, u32 offset2, + size_t len, int advice); +#endif #ifdef CONFIG_COMPAT long compat_sys_mmap2(unsigned long addr, size_t len, unsigned long prot, unsigned long flags, diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index ee2d76cb3187..9b6146056e48 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -73,6 +73,7 @@ obj-y := cputable.o syscalls.o \ obj-y += ptrace/ obj-$(CONFIG_PPC64) += setup_64.o irq_64.o\ paca.o nvram_64.o note.o +obj-$(CONFIG_PPC32) += sys_ppc32.o obj-$(CONFIG_COMPAT) += sys_ppc32.o signal_32.o obj-$(CONFIG_VDSO32) += vdso32_wrapper.o obj-$(CONFIG_PPC_WATCHDOG) += watchdog.o diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S index 904a5608cbe3..978a173eb339 100644 --- a/arch/powerpc/kernel/interrupt_64.S +++ b/arch/powerpc/kernel/interrupt_64.S @@ -538,7 +538,7 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_kernel) beq .Lfast_kernel_interrupt_return_\srr\() // EE already disabled lbz r11,PACAIRQHAPPENED(r13) andi. r10,r11,PACA_IRQ_MUST_HARD_MASK - beq 1f // No HARD_MASK pending + beq .Lfast_kernel_interrupt_return_\srr\() // No HARD_MASK pending /* Must clear MSR_EE from _MSR */ #ifdef CONFIG_PPC_BOOK3S @@ -555,12 +555,23 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_kernel) b .Lfast_kernel_interrupt_return_\srr\() .Linterrupt_return_\srr\()_soft_enabled: + /* + * In the soft-enabled case, need to double-check that we have no + * pending interrupts that might have come in before we reached the + * restart section of code, and restart the exit so those can be + * handled. + * + * If there are none, it is be possible that the interrupt still + * has PACA_IRQ_HARD_DIS set, which needs to be cleared for the + * interrupted context. This clear will not clobber a new pending + * interrupt coming in, because we're in the restart section, so + * such would return to the restart location. + */ #ifdef CONFIG_PPC_BOOK3S lbz r11,PACAIRQHAPPENED(r13) andi. r11,r11,(~PACA_IRQ_HARD_DIS)@l bne- interrupt_return_\srr\()_kernel_restart #endif -1: li r11,0 stb r11,PACAIRQHAPPENED(r13) // clear the possible HARD_DIS diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index dcc3c9fd4cfd..1ab4a4d95aba 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -1,13 +1,23 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * sys_ppc32.c: Conversion between 32bit and 64bit native syscalls. + * sys_ppc32.c: 32-bit system calls with complex calling conventions. * * Copyright (C) 2001 IBM * Copyright (C) 1997,1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz) * Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu) * - * These routines maintain argument size conversion between 32bit and 64bit - * environment. + * 32-bit system calls with 64-bit arguments pass those in register pairs. + * This must be specially dealt with on 64-bit kernels. The compat_arg_u64_dual + * in generic compat syscalls is not always usable because the register + * pairing is constrained depending on preceding arguments. + * + * An analogous problem exists on 32-bit kernels with ARCH_HAS_SYSCALL_WRAPPER, + * the defined system call functions take the pt_regs as an argument, and there + * is a mapping macro which maps registers to arguments + * (SC_POWERPC_REGS_TO_ARGS) which also does not deal with these 64-bit + * arguments. + * + * This file contains these system calls. */ #include @@ -47,7 +57,17 @@ #include #include -COMPAT_SYSCALL_DEFINE6(ppc_pread64, +#ifdef CONFIG_PPC32 +#define PPC32_SYSCALL_DEFINE4 SYSCALL_DEFINE4 +#define PPC32_SYSCALL_DEFINE5 SYSCALL_DEFINE5 +#define PPC32_SYSCALL_DEFINE6 SYSCALL_DEFINE6 +#else +#define PPC32_SYSCALL_DEFINE4 COMPAT_SYSCALL_DEFINE4 +#define PPC32_SYSCALL_DEFINE5 COMPAT_SYSCALL_DEFINE5 +#define PPC32_SYSCALL_DEFINE6 COMPAT_SYSCALL_DEFINE6 +#endif + +PPC32_SYSCALL_DEFINE6(ppc_pread64, unsigned int, fd, char __user *, ubuf, compat_size_t, count, u32, reg6, u32, pos1, u32, pos2) @@ -55,7 +75,7 @@ COMPAT_SYSCALL_DEFINE6(ppc_pread64, return ksys_pread64(fd, ubuf, count, merge_64(pos1, pos2)); } -COMPAT_SYSCALL_DEFINE6(ppc_pwrite64, +PPC32_SYSCALL_DEFINE6(ppc_pwrite64, unsigned int, fd, const char __user *, ubuf, compat_size_t, count, u32, reg6, u32, pos1, u32, pos2) @@ -63,28 +83,28 @@ COMPAT_SYSCALL_DEFINE6(ppc_pwrite64, return ksys_pwrite64(fd, ubuf, count, merge_64(pos1, pos2)); } -COMPAT_SYSCALL_DEFINE5(ppc_readahead, +PPC32_SYSCALL_DEFINE5(ppc_readahead, int, fd, u32, r4, u32, offset1, u32, offset2, u32, count) { return ksys_readahead(fd, merge_64(offset1, offset2), count); } -COMPAT_SYSCALL_DEFINE4(ppc_truncate64, +PPC32_SYSCALL_DEFINE4(ppc_truncate64, const char __user *, path, u32, reg4, unsigned long, len1, unsigned long, len2) { return ksys_truncate(path, merge_64(len1, len2)); } -COMPAT_SYSCALL_DEFINE4(ppc_ftruncate64, +PPC32_SYSCALL_DEFINE4(ppc_ftruncate64, unsigned int, fd, u32, reg4, unsigned long, len1, unsigned long, len2) { return ksys_ftruncate(fd, merge_64(len1, len2)); } -COMPAT_SYSCALL_DEFINE6(ppc32_fadvise64, +PPC32_SYSCALL_DEFINE6(ppc32_fadvise64, int, fd, u32, unused, u32, offset1, u32, offset2, size_t, len, int, advice) { diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 2bca64f96164..e9e0df4f9a61 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -228,8 +228,10 @@ 176 64 rt_sigtimedwait sys_rt_sigtimedwait 177 nospu rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo 178 nospu rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend -179 common pread64 sys_pread64 compat_sys_ppc_pread64 -180 common pwrite64 sys_pwrite64 compat_sys_ppc_pwrite64 +179 32 pread64 sys_ppc_pread64 compat_sys_ppc_pread64 +179 64 pread64 sys_pread64 +180 32 pwrite64 sys_ppc_pwrite64 compat_sys_ppc_pwrite64 +180 64 pwrite64 sys_pwrite64 181 common chown sys_chown 182 common getcwd sys_getcwd 183 common capget sys_capget @@ -242,10 +244,11 @@ 188 common putpmsg sys_ni_syscall 189 nospu vfork sys_vfork 190 common ugetrlimit sys_getrlimit compat_sys_getrlimit -191 common readahead sys_readahead compat_sys_ppc_readahead +191 32 readahead sys_ppc_readahead compat_sys_ppc_readahead +191 64 readahead sys_readahead 192 32 mmap2 sys_mmap2 compat_sys_mmap2 -193 32 truncate64 sys_truncate64 compat_sys_ppc_truncate64 -194 32 ftruncate64 sys_ftruncate64 compat_sys_ppc_ftruncate64 +193 32 truncate64 sys_ppc_truncate64 compat_sys_ppc_truncate64 +194 32 ftruncate64 sys_ppc_ftruncate64 compat_sys_ppc_ftruncate64 195 32 stat64 sys_stat64 196 32 lstat64 sys_lstat64 197 32 fstat64 sys_fstat64 @@ -288,7 +291,8 @@ 230 common io_submit sys_io_submit compat_sys_io_submit 231 common io_cancel sys_io_cancel 232 nospu set_tid_address sys_set_tid_address -233 common fadvise64 sys_fadvise64 compat_sys_ppc32_fadvise64 +233 32 fadvise64 sys_ppc32_fadvise64 compat_sys_ppc32_fadvise64 +233 64 fadvise64 sys_fadvise64 234 nospu exit_group sys_exit_group 235 nospu lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie 236 common epoll_create sys_epoll_create diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c index 598006301620..e2f11f9c3f2a 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -508,10 +508,10 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) static int __kvmppc_svm_page_out(struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long page_shift, - struct kvm *kvm, unsigned long gpa) + struct kvm *kvm, unsigned long gpa, struct page *fault_page) { unsigned long src_pfn, dst_pfn = 0; - struct migrate_vma mig; + struct migrate_vma mig = { 0 }; struct page *dpage, *spage; struct kvmppc_uvmem_page_pvt *pvt; unsigned long pfn; @@ -525,6 +525,7 @@ static int __kvmppc_svm_page_out(struct vm_area_struct *vma, mig.dst = &dst_pfn; mig.pgmap_owner = &kvmppc_uvmem_pgmap; mig.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE; + mig.fault_page = fault_page; /* The requested page is already paged-out, nothing to do */ if (!kvmppc_gfn_is_uvmem_pfn(gpa >> page_shift, kvm, NULL)) @@ -580,12 +581,14 @@ static int __kvmppc_svm_page_out(struct vm_area_struct *vma, static inline int kvmppc_svm_page_out(struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long page_shift, - struct kvm *kvm, unsigned long gpa) + struct kvm *kvm, unsigned long gpa, + struct page *fault_page) { int ret; mutex_lock(&kvm->arch.uvmem_lock); - ret = __kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa); + ret = __kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa, + fault_page); mutex_unlock(&kvm->arch.uvmem_lock); return ret; @@ -634,7 +637,7 @@ void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *slot, pvt->remove_gfn = true; if (__kvmppc_svm_page_out(vma, addr, addr + PAGE_SIZE, - PAGE_SHIFT, kvm, pvt->gpa)) + PAGE_SHIFT, kvm, pvt->gpa, NULL)) pr_err("Can't page out gpa:0x%lx addr:0x%lx\n", pvt->gpa, addr); } else { @@ -715,7 +718,7 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm) dpage = pfn_to_page(uvmem_pfn); dpage->zone_device_data = pvt; - lock_page(dpage); + zone_device_page_init(dpage); return dpage; out_clear: spin_lock(&kvmppc_uvmem_bitmap_lock); @@ -736,7 +739,7 @@ static int kvmppc_svm_page_in(struct vm_area_struct *vma, bool pagein) { unsigned long src_pfn, dst_pfn = 0; - struct migrate_vma mig; + struct migrate_vma mig = { 0 }; struct page *spage; unsigned long pfn; struct page *dpage; @@ -994,7 +997,7 @@ static vm_fault_t kvmppc_uvmem_migrate_to_ram(struct vm_fault *vmf) if (kvmppc_svm_page_out(vmf->vma, vmf->address, vmf->address + PAGE_SIZE, PAGE_SHIFT, - pvt->kvm, pvt->gpa)) + pvt->kvm, pvt->gpa, vmf->page)) return VM_FAULT_SIGBUS; else return 0; @@ -1065,7 +1068,7 @@ kvmppc_h_svm_page_out(struct kvm *kvm, unsigned long gpa, if (!vma || vma->vm_start > start || vma->vm_end < end) goto out; - if (!kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa)) + if (!kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa, NULL)) ret = H_SUCCESS; out: mmap_read_unlock(kvm->mm); diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index 14e143b946a3..92310202bdd7 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -7,7 +7,7 @@ obj-y := lpar.o hvCall.o nvram.o reconfig.o \ setup.o iommu.o event_sources.o ras.o \ firmware.o power.o dlpar.o mobility.o rng.o \ pci.o pci_dlpar.o eeh_pseries.o msi.o \ - papr_platform_attributes.o + papr_platform_attributes.o dtl.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_KEXEC_CORE) += kexec.o obj-$(CONFIG_PSERIES_ENERGY) += pseries_energy.o @@ -19,7 +19,6 @@ obj-$(CONFIG_HVC_CONSOLE) += hvconsole.o obj-$(CONFIG_HVCS) += hvcserver.o obj-$(CONFIG_HCALL_STATS) += hvCall_inst.o obj-$(CONFIG_CMM) += cmm.o -obj-$(CONFIG_DTL) += dtl.o obj-$(CONFIG_IO_EVENT_IRQ) += io_event_irq.o obj-$(CONFIG_LPARCFG) += lparcfg.o obj-$(CONFIG_IBMVIO) += vio.o diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c index 1b1977bc78e7..3f1cdccebc9c 100644 --- a/arch/powerpc/platforms/pseries/dtl.c +++ b/arch/powerpc/platforms/pseries/dtl.c @@ -18,6 +18,7 @@ #include #include +#ifdef CONFIG_DTL struct dtl { struct dtl_entry *buf; int cpu; @@ -57,78 +58,6 @@ static DEFINE_PER_CPU(struct dtl_ring, dtl_rings); static atomic_t dtl_count; -/* - * Scan the dispatch trace log and count up the stolen time. - * Should be called with interrupts disabled. - */ -static notrace u64 scan_dispatch_log(u64 stop_tb) -{ - u64 i = local_paca->dtl_ridx; - struct dtl_entry *dtl = local_paca->dtl_curr; - struct dtl_entry *dtl_end = local_paca->dispatch_log_end; - struct lppaca *vpa = local_paca->lppaca_ptr; - u64 tb_delta; - u64 stolen = 0; - u64 dtb; - - if (!dtl) - return 0; - - if (i == be64_to_cpu(vpa->dtl_idx)) - return 0; - while (i < be64_to_cpu(vpa->dtl_idx)) { - dtb = be64_to_cpu(dtl->timebase); - tb_delta = be32_to_cpu(dtl->enqueue_to_dispatch_time) + - be32_to_cpu(dtl->ready_to_enqueue_time); - barrier(); - if (i + N_DISPATCH_LOG < be64_to_cpu(vpa->dtl_idx)) { - /* buffer has overflowed */ - i = be64_to_cpu(vpa->dtl_idx) - N_DISPATCH_LOG; - dtl = local_paca->dispatch_log + (i % N_DISPATCH_LOG); - continue; - } - if (dtb > stop_tb) - break; - if (dtl_consumer) - dtl_consumer(dtl, i); - stolen += tb_delta; - ++i; - ++dtl; - if (dtl == dtl_end) - dtl = local_paca->dispatch_log; - } - local_paca->dtl_ridx = i; - local_paca->dtl_curr = dtl; - return stolen; -} - -/* - * Accumulate stolen time by scanning the dispatch trace log. - * Called on entry from user mode. - */ -void notrace pseries_accumulate_stolen_time(void) -{ - u64 sst, ust; - struct cpu_accounting_data *acct = &local_paca->accounting; - - sst = scan_dispatch_log(acct->starttime_user); - ust = scan_dispatch_log(acct->starttime); - acct->stime -= sst; - acct->utime -= ust; - acct->steal_time += ust + sst; -} - -u64 pseries_calculate_stolen_time(u64 stop_tb) -{ - if (!firmware_has_feature(FW_FEATURE_SPLPAR)) - return 0; - - if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) - return scan_dispatch_log(stop_tb); - - return 0; -} - /* * The cpu accounting code controls the DTL ring buffer, and we get * given entries as they are processed. @@ -436,3 +365,81 @@ static int dtl_init(void) return 0; } machine_arch_initcall(pseries, dtl_init); +#endif /* CONFIG_DTL */ + +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE +/* + * Scan the dispatch trace log and count up the stolen time. + * Should be called with interrupts disabled. + */ +static notrace u64 scan_dispatch_log(u64 stop_tb) +{ + u64 i = local_paca->dtl_ridx; + struct dtl_entry *dtl = local_paca->dtl_curr; + struct dtl_entry *dtl_end = local_paca->dispatch_log_end; + struct lppaca *vpa = local_paca->lppaca_ptr; + u64 tb_delta; + u64 stolen = 0; + u64 dtb; + + if (!dtl) + return 0; + + if (i == be64_to_cpu(vpa->dtl_idx)) + return 0; + while (i < be64_to_cpu(vpa->dtl_idx)) { + dtb = be64_to_cpu(dtl->timebase); + tb_delta = be32_to_cpu(dtl->enqueue_to_dispatch_time) + + be32_to_cpu(dtl->ready_to_enqueue_time); + barrier(); + if (i + N_DISPATCH_LOG < be64_to_cpu(vpa->dtl_idx)) { + /* buffer has overflowed */ + i = be64_to_cpu(vpa->dtl_idx) - N_DISPATCH_LOG; + dtl = local_paca->dispatch_log + (i % N_DISPATCH_LOG); + continue; + } + if (dtb > stop_tb) + break; +#ifdef CONFIG_DTL + if (dtl_consumer) + dtl_consumer(dtl, i); +#endif + stolen += tb_delta; + ++i; + ++dtl; + if (dtl == dtl_end) + dtl = local_paca->dispatch_log; + } + local_paca->dtl_ridx = i; + local_paca->dtl_curr = dtl; + return stolen; +} + +/* + * Accumulate stolen time by scanning the dispatch trace log. + * Called on entry from user mode. + */ +void notrace pseries_accumulate_stolen_time(void) +{ + u64 sst, ust; + struct cpu_accounting_data *acct = &local_paca->accounting; + + sst = scan_dispatch_log(acct->starttime_user); + ust = scan_dispatch_log(acct->starttime); + acct->stime -= sst; + acct->utime -= ust; + acct->steal_time += ust + sst; +} + +u64 pseries_calculate_stolen_time(u64 stop_tb) +{ + if (!firmware_has_feature(FW_FEATURE_SPLPAR)) + return 0; + + if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) + return scan_dispatch_log(stop_tb); + + return 0; +} + +#endif diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 56976e5674ee..6b48a3ae9843 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -70,6 +70,7 @@ config RISCV select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL if MMU && 64BIT select GENERIC_VDSO_TIME_NS if HAVE_GENERIC_VDSO + select HARDIRQS_SW_RESEND select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL select HAVE_ARCH_JUMP_LABEL_RELATIVE if !XIP_KERNEL diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index e9bd21816ea9..1c8ec656e916 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -37,6 +37,7 @@ else endif ifeq ($(CONFIG_LD_IS_LLD),y) +ifeq ($(shell test $(CONFIG_LLD_VERSION) -lt 150000; echo $$?),0) KBUILD_CFLAGS += -mno-relax KBUILD_AFLAGS += -mno-relax ifndef CONFIG_AS_IS_LLVM @@ -44,6 +45,7 @@ ifndef CONFIG_AS_IS_LLVM KBUILD_AFLAGS += -Wa,-mno-relax endif endif +endif # ISA string setting riscv-march-$(CONFIG_ARCH_RV32I) := rv32ima diff --git a/arch/riscv/boot/dts/microchip/Makefile b/arch/riscv/boot/dts/microchip/Makefile index 39aae7b04f1c..7427a20934f3 100644 --- a/arch/riscv/boot/dts/microchip/Makefile +++ b/arch/riscv/boot/dts/microchip/Makefile @@ -1,4 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 dtb-$(CONFIG_SOC_MICROCHIP_POLARFIRE) += mpfs-icicle-kit.dtb +dtb-$(CONFIG_SOC_MICROCHIP_POLARFIRE) += mpfs-m100pfsevp.dtb dtb-$(CONFIG_SOC_MICROCHIP_POLARFIRE) += mpfs-polarberry.dtb +dtb-$(CONFIG_SOC_MICROCHIP_POLARFIRE) += mpfs-sev-kit.dtb obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .o, $(dtb-y)) diff --git a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi index 0d28858b83f2..24b1cfb9a73e 100644 --- a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi +++ b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi @@ -2,20 +2,21 @@ /* Copyright (c) 2020-2021 Microchip Technology Inc */ / { - compatible = "microchip,mpfs-icicle-reference-rtlv2203", "microchip,mpfs"; + compatible = "microchip,mpfs-icicle-reference-rtlv2210", "microchip,mpfs-icicle-kit", + "microchip,mpfs"; - core_pwm0: pwm@41000000 { + core_pwm0: pwm@40000000 { compatible = "microchip,corepwm-rtl-v4"; - reg = <0x0 0x41000000 0x0 0xF0>; + reg = <0x0 0x40000000 0x0 0xF0>; microchip,sync-update-mask = /bits/ 32 <0>; #pwm-cells = <2>; clocks = <&fabric_clk3>; status = "disabled"; }; - i2c2: i2c@44000000 { + i2c2: i2c@40000200 { compatible = "microchip,corei2c-rtl-v7"; - reg = <0x0 0x44000000 0x0 0x1000>; + reg = <0x0 0x40000200 0x0 0x100>; #address-cells = <1>; #size-cells = <0>; clocks = <&fabric_clk3>; @@ -28,7 +29,7 @@ i2c2: i2c@44000000 { fabric_clk3: fabric-clk3 { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <62500000>; + clock-frequency = <50000000>; }; fabric_clk1: fabric-clk1 { @@ -36,4 +37,34 @@ fabric_clk1: fabric-clk1 { #clock-cells = <0>; clock-frequency = <125000000>; }; + + pcie: pcie@3000000000 { + compatible = "microchip,pcie-host-1.0"; + #address-cells = <0x3>; + #interrupt-cells = <0x1>; + #size-cells = <0x2>; + device_type = "pci"; + reg = <0x30 0x0 0x0 0x8000000>, <0x0 0x43000000 0x0 0x10000>; + reg-names = "cfg", "apb"; + bus-range = <0x0 0x7f>; + interrupt-parent = <&plic>; + interrupts = <119>; + interrupt-map = <0 0 0 1 &pcie_intc 0>, + <0 0 0 2 &pcie_intc 1>, + <0 0 0 3 &pcie_intc 2>, + <0 0 0 4 &pcie_intc 3>; + interrupt-map-mask = <0 0 0 7>; + clocks = <&fabric_clk1>, <&fabric_clk3>; + clock-names = "fic1", "fic3"; + ranges = <0x3000000 0x0 0x8000000 0x30 0x8000000 0x0 0x80000000>; + dma-ranges = <0x02000000 0x0 0x00000000 0x0 0x00000000 0x1 0x00000000>; + msi-parent = <&pcie>; + msi-controller; + status = "disabled"; + pcie_intc: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; }; diff --git a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts index f3f87ed2007f..ec7b7c2a3ce2 100644 --- a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts +++ b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts @@ -11,7 +11,8 @@ / { model = "Microchip PolarFire-SoC Icicle Kit"; - compatible = "microchip,mpfs-icicle-kit", "microchip,mpfs"; + compatible = "microchip,mpfs-icicle-reference-rtlv2210", "microchip,mpfs-icicle-kit", + "microchip,mpfs"; aliases { ethernet0 = &mac1; @@ -32,15 +33,26 @@ cpus { ddrc_cache_lo: memory@80000000 { device_type = "memory"; - reg = <0x0 0x80000000 0x0 0x2e000000>; + reg = <0x0 0x80000000 0x0 0x40000000>; status = "okay"; }; ddrc_cache_hi: memory@1000000000 { device_type = "memory"; - reg = <0x10 0x0 0x0 0x40000000>; + reg = <0x10 0x40000000 0x0 0x40000000>; status = "okay"; }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + hss_payload: region@BFC00000 { + reg = <0x0 0xBFC00000 0x0 0x400000>; + no-map; + }; + }; }; &core_pwm0 { diff --git a/arch/riscv/boot/dts/microchip/mpfs-m100pfs-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-m100pfs-fabric.dtsi new file mode 100644 index 000000000000..7b9ee13b6a3a --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-m100pfs-fabric.dtsi @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2022 Microchip Technology Inc */ + +/ { + fabric_clk3: fabric-clk3 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <62500000>; + }; + + fabric_clk1: fabric-clk1 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <125000000>; + }; + + pcie: pcie@2000000000 { + compatible = "microchip,pcie-host-1.0"; + #address-cells = <0x3>; + #interrupt-cells = <0x1>; + #size-cells = <0x2>; + device_type = "pci"; + reg = <0x20 0x0 0x0 0x8000000>, <0x0 0x43000000 0x0 0x10000>; + reg-names = "cfg", "apb"; + bus-range = <0x0 0x7f>; + interrupt-parent = <&plic>; + interrupts = <119>; + interrupt-map = <0 0 0 1 &pcie_intc 0>, + <0 0 0 2 &pcie_intc 1>, + <0 0 0 3 &pcie_intc 2>, + <0 0 0 4 &pcie_intc 3>; + interrupt-map-mask = <0 0 0 7>; + clocks = <&fabric_clk1>, <&fabric_clk1>, <&fabric_clk3>; + clock-names = "fic0", "fic1", "fic3"; + ranges = <0x3000000 0x0 0x8000000 0x20 0x8000000 0x0 0x80000000>; + msi-parent = <&pcie>; + msi-controller; + status = "disabled"; + pcie_intc: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; +}; diff --git a/arch/riscv/boot/dts/microchip/mpfs-m100pfsevp.dts b/arch/riscv/boot/dts/microchip/mpfs-m100pfsevp.dts new file mode 100644 index 000000000000..184cb36a175e --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-m100pfsevp.dts @@ -0,0 +1,179 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Original all-in-one devicetree: + * Copyright (C) 2021-2022 - Wolfgang Grandegger + * Rewritten to use includes: + * Copyright (C) 2022 - Conor Dooley + */ +/dts-v1/; + +#include "mpfs.dtsi" +#include "mpfs-m100pfs-fabric.dtsi" + +/* Clock frequency (in Hz) of the rtcclk */ +#define MTIMER_FREQ 1000000 + +/ { + model = "Aries Embedded M100PFEVPS"; + compatible = "aries,m100pfsevp", "microchip,mpfs"; + + aliases { + ethernet0 = &mac0; + ethernet1 = &mac1; + serial0 = &mmuart0; + serial1 = &mmuart1; + serial2 = &mmuart2; + serial3 = &mmuart3; + serial4 = &mmuart4; + gpio0 = &gpio0; + gpio1 = &gpio2; + }; + + chosen { + stdout-path = "serial1:115200n8"; + }; + + cpus { + timebase-frequency = ; + }; + + ddrc_cache_lo: memory@80000000 { + device_type = "memory"; + reg = <0x0 0x80000000 0x0 0x40000000>; + }; + ddrc_cache_hi: memory@1040000000 { + device_type = "memory"; + reg = <0x10 0x40000000 0x0 0x40000000>; + }; +}; + +&can0 { + status = "okay"; +}; + +&i2c0 { + status = "okay"; +}; + +&i2c1 { + status = "okay"; +}; + +&gpio0 { + interrupts = <13>, <14>, <15>, <16>, + <17>, <18>, <19>, <20>, + <21>, <22>, <23>, <24>, + <25>, <26>; + ngpios = <14>; + status = "okay"; + + pmic-irq-hog { + gpio-hog; + gpios = <13 0>; + input; + }; + + /* Set to low for eMMC, high for SD-card */ + mmc-sel-hog { + gpio-hog; + gpios = <12 0>; + output-high; + }; +}; + +&gpio2 { + interrupts = <13>, <14>, <15>, <16>, + <17>, <18>, <19>, <20>, + <21>, <22>, <23>, <24>, + <25>, <26>, <27>, <28>, + <29>, <30>, <31>, <32>, + <33>, <34>, <35>, <36>, + <37>, <38>, <39>, <40>, + <41>, <42>, <43>, <44>; + status = "okay"; +}; + +&mac0 { + status = "okay"; + phy-mode = "gmii"; + phy-handle = <&phy0>; + phy0: ethernet-phy@0 { + reg = <0>; + }; +}; + +&mac1 { + status = "okay"; + phy-mode = "gmii"; + phy-handle = <&phy1>; + phy1: ethernet-phy@0 { + reg = <0>; + }; +}; + +&mbox { + status = "okay"; +}; + +&mmc { + max-frequency = <50000000>; + bus-width = <4>; + cap-mmc-highspeed; + cap-sd-highspeed; + no-1-8-v; + sd-uhs-sdr12; + sd-uhs-sdr25; + sd-uhs-sdr50; + sd-uhs-sdr104; + disable-wp; + status = "okay"; +}; + +&mmuart1 { + status = "okay"; +}; + +&mmuart2 { + status = "okay"; +}; + +&mmuart3 { + status = "okay"; +}; + +&mmuart4 { + status = "okay"; +}; + +&pcie { + status = "okay"; +}; + +&qspi { + status = "okay"; +}; + +&refclk { + clock-frequency = <125000000>; +}; + +&rtc { + status = "okay"; +}; + +&spi0 { + status = "okay"; +}; + +&spi1 { + status = "okay"; +}; + +&syscontroller { + status = "okay"; +}; + +&usb { + status = "okay"; + dr_mode = "host"; +}; diff --git a/arch/riscv/boot/dts/microchip/mpfs-polarberry-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-polarberry-fabric.dtsi index 49380c428ec9..67303bc0e451 100644 --- a/arch/riscv/boot/dts/microchip/mpfs-polarberry-fabric.dtsi +++ b/arch/riscv/boot/dts/microchip/mpfs-polarberry-fabric.dtsi @@ -13,4 +13,33 @@ fabric_clk1: fabric-clk1 { #clock-cells = <0>; clock-frequency = <125000000>; }; + + pcie: pcie@2000000000 { + compatible = "microchip,pcie-host-1.0"; + #address-cells = <0x3>; + #interrupt-cells = <0x1>; + #size-cells = <0x2>; + device_type = "pci"; + reg = <0x20 0x0 0x0 0x8000000>, <0x0 0x43000000 0x0 0x10000>; + reg-names = "cfg", "apb"; + bus-range = <0x0 0x7f>; + interrupt-parent = <&plic>; + interrupts = <119>; + interrupt-map = <0 0 0 1 &pcie_intc 0>, + <0 0 0 2 &pcie_intc 1>, + <0 0 0 3 &pcie_intc 2>, + <0 0 0 4 &pcie_intc 3>; + interrupt-map-mask = <0 0 0 7>; + clocks = <&fabric_clk1>, <&fabric_clk1>, <&fabric_clk3>; + clock-names = "fic0", "fic1", "fic3"; + ranges = <0x3000000 0x0 0x8000000 0x20 0x8000000 0x0 0x80000000>; + msi-parent = <&pcie>; + msi-controller; + status = "disabled"; + pcie_intc: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; }; diff --git a/arch/riscv/boot/dts/microchip/mpfs-sev-kit-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-sev-kit-fabric.dtsi new file mode 100644 index 000000000000..8545baf4d129 --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-sev-kit-fabric.dtsi @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2022 Microchip Technology Inc */ + +/ { + fabric_clk3: fabric-clk3 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <0>; + }; + + fabric_clk1: fabric-clk1 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <125000000>; + }; + + pcie: pcie@2000000000 { + compatible = "microchip,pcie-host-1.0"; + #address-cells = <0x3>; + #interrupt-cells = <0x1>; + #size-cells = <0x2>; + device_type = "pci"; + reg = <0x20 0x0 0x0 0x8000000>, <0x0 0x43000000 0x0 0x10000>; + reg-names = "cfg", "apb"; + bus-range = <0x0 0x7f>; + interrupt-parent = <&plic>; + interrupts = <119>; + interrupt-map = <0 0 0 1 &pcie_intc 0>, + <0 0 0 2 &pcie_intc 1>, + <0 0 0 3 &pcie_intc 2>, + <0 0 0 4 &pcie_intc 3>; + interrupt-map-mask = <0 0 0 7>; + clocks = <&fabric_clk1>, <&fabric_clk1>, <&fabric_clk3>; + clock-names = "fic0", "fic1", "fic3"; + ranges = <0x3000000 0x0 0x8000000 0x20 0x8000000 0x0 0x80000000>; + msi-parent = <&pcie>; + msi-controller; + status = "disabled"; + pcie_intc: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; +}; diff --git a/arch/riscv/boot/dts/microchip/mpfs-sev-kit.dts b/arch/riscv/boot/dts/microchip/mpfs-sev-kit.dts new file mode 100644 index 000000000000..013cb666c72d --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-sev-kit.dts @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2022 Microchip Technology Inc */ + +/dts-v1/; + +#include "mpfs.dtsi" +#include "mpfs-sev-kit-fabric.dtsi" + +/* Clock frequency (in Hz) of the rtcclk */ +#define MTIMER_FREQ 1000000 + +/ { + #address-cells = <2>; + #size-cells = <2>; + model = "Microchip PolarFire-SoC SEV Kit"; + compatible = "microchip,mpfs-sev-kit", "microchip,mpfs"; + + aliases { + ethernet0 = &mac1; + serial0 = &mmuart0; + serial1 = &mmuart1; + serial2 = &mmuart2; + serial3 = &mmuart3; + serial4 = &mmuart4; + }; + + chosen { + stdout-path = "serial1:115200n8"; + }; + + cpus { + timebase-frequency = ; + }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + fabricbuf0ddrc: buffer@80000000 { + compatible = "shared-dma-pool"; + reg = <0x0 0x80000000 0x0 0x2000000>; + }; + + fabricbuf1ddrnc: buffer@c4000000 { + compatible = "shared-dma-pool"; + reg = <0x0 0xc4000000 0x0 0x4000000>; + }; + + fabricbuf2ddrncwcb: buffer@d4000000 { + compatible = "shared-dma-pool"; + reg = <0x0 0xd4000000 0x0 0x4000000>; + }; + }; + + ddrc_cache: memory@1000000000 { + device_type = "memory"; + reg = <0x10 0x0 0x0 0x76000000>; + }; +}; + +&i2c0 { + status = "okay"; +}; + +&gpio2 { + interrupts = <53>, <53>, <53>, <53>, + <53>, <53>, <53>, <53>, + <53>, <53>, <53>, <53>, + <53>, <53>, <53>, <53>, + <53>, <53>, <53>, <53>, + <53>, <53>, <53>, <53>, + <53>, <53>, <53>, <53>, + <53>, <53>, <53>, <53>; + status = "okay"; +}; + +&mac0 { + status = "okay"; + phy-mode = "sgmii"; + phy-handle = <&phy0>; + phy1: ethernet-phy@9 { + reg = <9>; + }; + phy0: ethernet-phy@8 { + reg = <8>; + }; +}; + +&mac1 { + status = "okay"; + phy-mode = "sgmii"; + phy-handle = <&phy1>; +}; + +&mbox { + status = "okay"; +}; + +&mmc { + status = "okay"; + bus-width = <4>; + disable-wp; + cap-sd-highspeed; + cap-mmc-highspeed; + mmc-ddr-1_8v; + mmc-hs200-1_8v; + sd-uhs-sdr12; + sd-uhs-sdr25; + sd-uhs-sdr50; + sd-uhs-sdr104; +}; + +&mmuart1 { + status = "okay"; +}; + +&mmuart2 { + status = "okay"; +}; + +&mmuart3 { + status = "okay"; +}; + +&mmuart4 { + status = "okay"; +}; + +&refclk { + clock-frequency = <125000000>; +}; + +&rtc { + status = "okay"; +}; + +&syscontroller { + status = "okay"; +}; + +&usb { + status = "okay"; + dr_mode = "otg"; +}; diff --git a/arch/riscv/boot/dts/microchip/mpfs.dtsi b/arch/riscv/boot/dts/microchip/mpfs.dtsi index 6d9d455fa160..8f463399a568 100644 --- a/arch/riscv/boot/dts/microchip/mpfs.dtsi +++ b/arch/riscv/boot/dts/microchip/mpfs.dtsi @@ -330,7 +330,7 @@ spi1: spi@20109000 { }; qspi: spi@21000000 { - compatible = "microchip,mpfs-qspi"; + compatible = "microchip,mpfs-qspi", "microchip,coreqspi-rtl-v2"; #address-cells = <1>; #size-cells = <0>; reg = <0x0 0x21000000 0x0 0x1000>; @@ -464,35 +464,6 @@ usb: usb@20201000 { status = "disabled"; }; - pcie: pcie@2000000000 { - compatible = "microchip,pcie-host-1.0"; - #address-cells = <0x3>; - #interrupt-cells = <0x1>; - #size-cells = <0x2>; - device_type = "pci"; - reg = <0x20 0x0 0x0 0x8000000>, <0x0 0x43000000 0x0 0x10000>; - reg-names = "cfg", "apb"; - bus-range = <0x0 0x7f>; - interrupt-parent = <&plic>; - interrupts = <119>; - interrupt-map = <0 0 0 1 &pcie_intc 0>, - <0 0 0 2 &pcie_intc 1>, - <0 0 0 3 &pcie_intc 2>, - <0 0 0 4 &pcie_intc 3>; - interrupt-map-mask = <0 0 0 7>; - clocks = <&fabric_clk1>, <&fabric_clk1>, <&fabric_clk3>; - clock-names = "fic0", "fic1", "fic3"; - ranges = <0x3000000 0x0 0x8000000 0x20 0x8000000 0x0 0x80000000>; - msi-parent = <&pcie>; - msi-controller; - status = "disabled"; - pcie_intc: interrupt-controller { - #address-cells = <0>; - #interrupt-cells = <1>; - interrupt-controller; - }; - }; - mbox: mailbox@37020000 { compatible = "microchip,mpfs-mailbox"; reg = <0x0 0x37020000 0x0 0x1000>, <0x0 0x2000318C 0x0 0x40>; diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c index 96648c176f37..21546937db39 100644 --- a/arch/riscv/errata/thead/errata.c +++ b/arch/riscv/errata/thead/errata.c @@ -17,6 +17,9 @@ static bool errata_probe_pbmt(unsigned int stage, unsigned long arch_id, unsigned long impid) { + if (!IS_ENABLED(CONFIG_ERRATA_THEAD_PBMT)) + return false; + if (arch_id != 0 || impid != 0) return false; @@ -30,7 +33,9 @@ static bool errata_probe_pbmt(unsigned int stage, static bool errata_probe_cmo(unsigned int stage, unsigned long arch_id, unsigned long impid) { -#ifdef CONFIG_ERRATA_THEAD_CMO + if (!IS_ENABLED(CONFIG_ERRATA_THEAD_CMO)) + return false; + if (arch_id != 0 || impid != 0) return false; @@ -40,9 +45,6 @@ static bool errata_probe_cmo(unsigned int stage, riscv_cbom_block_size = L1_CACHE_BYTES; riscv_noncoherent_supported(); return true; -#else - return false; -#endif } static u32 thead_errata_probe(unsigned int stage, @@ -51,10 +53,10 @@ static u32 thead_errata_probe(unsigned int stage, u32 cpu_req_errata = 0; if (errata_probe_pbmt(stage, archid, impid)) - cpu_req_errata |= (1U << ERRATA_THEAD_PBMT); + cpu_req_errata |= BIT(ERRATA_THEAD_PBMT); if (errata_probe_cmo(stage, archid, impid)) - cpu_req_errata |= (1U << ERRATA_THEAD_CMO); + cpu_req_errata |= BIT(ERRATA_THEAD_CMO); return cpu_req_errata; } diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h index 273ece6b622f..8a5c246b0a21 100644 --- a/arch/riscv/include/asm/cacheflush.h +++ b/arch/riscv/include/asm/cacheflush.h @@ -55,6 +55,8 @@ static inline void riscv_init_cbom_blocksize(void) { } #ifdef CONFIG_RISCV_DMA_NONCOHERENT void riscv_noncoherent_supported(void); +#else +static inline void riscv_noncoherent_supported(void) {} #endif /* diff --git a/arch/riscv/include/asm/elf.h b/arch/riscv/include/asm/elf.h index 14fc7342490b..e7acffdf21d2 100644 --- a/arch/riscv/include/asm/elf.h +++ b/arch/riscv/include/asm/elf.h @@ -99,6 +99,10 @@ do { \ get_cache_size(2, CACHE_TYPE_UNIFIED)); \ NEW_AUX_ENT(AT_L2_CACHEGEOMETRY, \ get_cache_geometry(2, CACHE_TYPE_UNIFIED)); \ + NEW_AUX_ENT(AT_L3_CACHESIZE, \ + get_cache_size(3, CACHE_TYPE_UNIFIED)); \ + NEW_AUX_ENT(AT_L3_CACHEGEOMETRY, \ + get_cache_geometry(3, CACHE_TYPE_UNIFIED)); \ } while (0) #define ARCH_HAS_SETUP_ADDITIONAL_PAGES struct linux_binprm; diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h index 69605a474270..92080a227937 100644 --- a/arch/riscv/include/asm/io.h +++ b/arch/riscv/include/asm/io.h @@ -101,9 +101,9 @@ __io_reads_ins(reads, u32, l, __io_br(), __io_ar(addr)) __io_reads_ins(ins, u8, b, __io_pbr(), __io_par(addr)) __io_reads_ins(ins, u16, w, __io_pbr(), __io_par(addr)) __io_reads_ins(ins, u32, l, __io_pbr(), __io_par(addr)) -#define insb(addr, buffer, count) __insb((void __iomem *)(long)addr, buffer, count) -#define insw(addr, buffer, count) __insw((void __iomem *)(long)addr, buffer, count) -#define insl(addr, buffer, count) __insl((void __iomem *)(long)addr, buffer, count) +#define insb(addr, buffer, count) __insb(PCI_IOBASE + (addr), buffer, count) +#define insw(addr, buffer, count) __insw(PCI_IOBASE + (addr), buffer, count) +#define insl(addr, buffer, count) __insl(PCI_IOBASE + (addr), buffer, count) __io_writes_outs(writes, u8, b, __io_bw(), __io_aw()) __io_writes_outs(writes, u16, w, __io_bw(), __io_aw()) @@ -115,22 +115,22 @@ __io_writes_outs(writes, u32, l, __io_bw(), __io_aw()) __io_writes_outs(outs, u8, b, __io_pbw(), __io_paw()) __io_writes_outs(outs, u16, w, __io_pbw(), __io_paw()) __io_writes_outs(outs, u32, l, __io_pbw(), __io_paw()) -#define outsb(addr, buffer, count) __outsb((void __iomem *)(long)addr, buffer, count) -#define outsw(addr, buffer, count) __outsw((void __iomem *)(long)addr, buffer, count) -#define outsl(addr, buffer, count) __outsl((void __iomem *)(long)addr, buffer, count) +#define outsb(addr, buffer, count) __outsb(PCI_IOBASE + (addr), buffer, count) +#define outsw(addr, buffer, count) __outsw(PCI_IOBASE + (addr), buffer, count) +#define outsl(addr, buffer, count) __outsl(PCI_IOBASE + (addr), buffer, count) #ifdef CONFIG_64BIT __io_reads_ins(reads, u64, q, __io_br(), __io_ar(addr)) #define readsq(addr, buffer, count) __readsq(addr, buffer, count) __io_reads_ins(ins, u64, q, __io_pbr(), __io_par(addr)) -#define insq(addr, buffer, count) __insq((void __iomem *)addr, buffer, count) +#define insq(addr, buffer, count) __insq(PCI_IOBASE + (addr), buffer, count) __io_writes_outs(writes, u64, q, __io_bw(), __io_aw()) #define writesq(addr, buffer, count) __writesq(addr, buffer, count) __io_writes_outs(outs, u64, q, __io_pbr(), __io_paw()) -#define outsq(addr, buffer, count) __outsq((void __iomem *)addr, buffer, count) +#define outsq(addr, buffer, count) __outsq(PCI_IOBASE + (addr), buffer, count) #endif #include diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h index cedcf8ea3c76..0099dc116168 100644 --- a/arch/riscv/include/asm/mmu.h +++ b/arch/riscv/include/asm/mmu.h @@ -16,7 +16,6 @@ typedef struct { atomic_long_t id; #endif void *vdso; - void *vdso_info; #ifdef CONFIG_SMP /* A local icache flush is needed before user execution can resume. */ cpumask_t icache_stale_mask; diff --git a/arch/riscv/include/uapi/asm/auxvec.h b/arch/riscv/include/uapi/asm/auxvec.h index 32c73ba1d531..fb187a33ce58 100644 --- a/arch/riscv/include/uapi/asm/auxvec.h +++ b/arch/riscv/include/uapi/asm/auxvec.h @@ -30,8 +30,10 @@ #define AT_L1D_CACHEGEOMETRY 43 #define AT_L2_CACHESIZE 44 #define AT_L2_CACHEGEOMETRY 45 +#define AT_L3_CACHESIZE 46 +#define AT_L3_CACHEGEOMETRY 47 /* entries in ARCH_DLINFO */ -#define AT_VECTOR_SIZE_ARCH 7 +#define AT_VECTOR_SIZE_ARCH 9 #endif /* _UAPI_ASM_RISCV_AUXVEC_H */ diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c index 4d0dece5996c..fa427bdcf773 100644 --- a/arch/riscv/kernel/cpu.c +++ b/arch/riscv/kernel/cpu.c @@ -3,10 +3,13 @@ * Copyright (C) 2012 Regents of the University of California */ +#include #include #include #include +#include #include +#include #include #include @@ -68,6 +71,50 @@ int riscv_of_parent_hartid(struct device_node *node, unsigned long *hartid) } #ifdef CONFIG_PROC_FS + +struct riscv_cpuinfo { + unsigned long mvendorid; + unsigned long marchid; + unsigned long mimpid; +}; +static DEFINE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo); + +static int riscv_cpuinfo_starting(unsigned int cpu) +{ + struct riscv_cpuinfo *ci = this_cpu_ptr(&riscv_cpuinfo); + +#if IS_ENABLED(CONFIG_RISCV_SBI) + ci->mvendorid = sbi_spec_is_0_1() ? 0 : sbi_get_mvendorid(); + ci->marchid = sbi_spec_is_0_1() ? 0 : sbi_get_marchid(); + ci->mimpid = sbi_spec_is_0_1() ? 0 : sbi_get_mimpid(); +#elif IS_ENABLED(CONFIG_RISCV_M_MODE) + ci->mvendorid = csr_read(CSR_MVENDORID); + ci->marchid = csr_read(CSR_MARCHID); + ci->mimpid = csr_read(CSR_MIMPID); +#else + ci->mvendorid = 0; + ci->marchid = 0; + ci->mimpid = 0; +#endif + + return 0; +} + +static int __init riscv_cpuinfo_init(void) +{ + int ret; + + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "riscv/cpuinfo:starting", + riscv_cpuinfo_starting, NULL); + if (ret < 0) { + pr_err("cpuinfo: failed to register hotplug callbacks.\n"); + return ret; + } + + return 0; +} +device_initcall(riscv_cpuinfo_init); + #define __RISCV_ISA_EXT_DATA(UPROP, EXTID) \ { \ .uprop = #UPROP, \ @@ -186,6 +233,7 @@ static int c_show(struct seq_file *m, void *v) { unsigned long cpu_id = (unsigned long)v - 1; struct device_node *node = of_get_cpu_node(cpu_id, NULL); + struct riscv_cpuinfo *ci = per_cpu_ptr(&riscv_cpuinfo, cpu_id); const char *compat, *isa; seq_printf(m, "processor\t: %lu\n", cpu_id); @@ -196,6 +244,9 @@ static int c_show(struct seq_file *m, void *v) if (!of_property_read_string(node, "compatible", &compat) && strcmp(compat, "riscv")) seq_printf(m, "uarch\t\t: %s\n", compat); + seq_printf(m, "mvendorid\t: 0x%lx\n", ci->mvendorid); + seq_printf(m, "marchid\t\t: 0x%lx\n", ci->marchid); + seq_printf(m, "mimpid\t\t: 0x%lx\n", ci->mimpid); seq_puts(m, "\n"); of_node_put(node); diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 9774f1271f93..694267d1fe81 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -254,35 +254,28 @@ void __init riscv_fill_hwcap(void) #ifdef CONFIG_RISCV_ALTERNATIVE static bool __init_or_module cpufeature_probe_svpbmt(unsigned int stage) { -#ifdef CONFIG_RISCV_ISA_SVPBMT - switch (stage) { - case RISCV_ALTERNATIVES_EARLY_BOOT: + if (!IS_ENABLED(CONFIG_RISCV_ISA_SVPBMT)) return false; - default: - return riscv_isa_extension_available(NULL, SVPBMT); - } -#endif - return false; + if (stage == RISCV_ALTERNATIVES_EARLY_BOOT) + return false; + + return riscv_isa_extension_available(NULL, SVPBMT); } static bool __init_or_module cpufeature_probe_zicbom(unsigned int stage) { -#ifdef CONFIG_RISCV_ISA_ZICBOM - switch (stage) { - case RISCV_ALTERNATIVES_EARLY_BOOT: + if (!IS_ENABLED(CONFIG_RISCV_ISA_ZICBOM)) return false; - default: - if (riscv_isa_extension_available(NULL, ZICBOM)) { - riscv_noncoherent_supported(); - return true; - } else { - return false; - } - } -#endif - return false; + if (stage == RISCV_ALTERNATIVES_EARLY_BOOT) + return false; + + if (!riscv_isa_extension_available(NULL, ZICBOM)) + return false; + + riscv_noncoherent_supported(); + return true; } /* @@ -297,10 +290,10 @@ static u32 __init_or_module cpufeature_probe(unsigned int stage) u32 cpu_req_feature = 0; if (cpufeature_probe_svpbmt(stage)) - cpu_req_feature |= (1U << CPUFEATURE_SVPBMT); + cpu_req_feature |= BIT(CPUFEATURE_SVPBMT); if (cpufeature_probe_zicbom(stage)) - cpu_req_feature |= (1U << CPUFEATURE_ZICBOM); + cpu_req_feature |= BIT(CPUFEATURE_ZICBOM); return cpu_req_feature; } diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 2dfc463b86bb..ad76bb59b059 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -252,10 +252,10 @@ static void __init parse_dtb(void) pr_info("Machine model: %s\n", name); dump_stack_set_arch_desc("%s (DT)", name); } - return; + } else { + pr_err("No DTB passed to the kernel\n"); } - pr_err("No DTB passed to the kernel\n"); #ifdef CONFIG_CMDLINE_FORCE strscpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE); pr_info("Forcing kernel command line to: %s\n", boot_command_line); diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c index 571556bb9261..5d3f2fbeb33c 100644 --- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -18,9 +18,6 @@ static long riscv_sys_mmap(unsigned long addr, unsigned long len, if (unlikely(offset & (~PAGE_MASK >> page_shift_offset))) return -EINVAL; - if (unlikely((prot & PROT_WRITE) && !(prot & PROT_READ))) - return -EINVAL; - return ksys_mmap_pgoff(addr, len, prot, flags, fd, offset >> (PAGE_SHIFT - page_shift_offset)); } diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 635e6ec26938..f3e96d60a2ff 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -33,6 +33,7 @@ void die(struct pt_regs *regs, const char *str) { static int die_counter; int ret; + long cause; oops_enter(); @@ -42,11 +43,13 @@ void die(struct pt_regs *regs, const char *str) pr_emerg("%s [#%d]\n", str, ++die_counter); print_modules(); - show_regs(regs); + if (regs) + show_regs(regs); - ret = notify_die(DIE_OOPS, str, regs, 0, regs->cause, SIGSEGV); + cause = regs ? regs->cause : -1; + ret = notify_die(DIE_OOPS, str, regs, 0, cause, SIGSEGV); - if (regs && kexec_should_crash(current)) + if (kexec_should_crash(current)) crash_kexec(regs); bust_spinlocks(0); diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index 692e7ae3dcb8..123d05255fcf 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -60,6 +60,11 @@ struct __vdso_info { struct vm_special_mapping *cm; }; +static struct __vdso_info vdso_info; +#ifdef CONFIG_COMPAT +static struct __vdso_info compat_vdso_info; +#endif + static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma) { @@ -115,15 +120,18 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) struct mm_struct *mm = task->mm; struct vm_area_struct *vma; VMA_ITERATOR(vmi, mm, 0); - struct __vdso_info *vdso_info = mm->context.vdso_info; mmap_read_lock(mm); for_each_vma(vmi, vma) { unsigned long size = vma->vm_end - vma->vm_start; - if (vma_is_special_mapping(vma, vdso_info->dm)) + if (vma_is_special_mapping(vma, vdso_info.dm)) zap_page_range(vma, vma->vm_start, size); +#ifdef CONFIG_COMPAT + if (vma_is_special_mapping(vma, compat_vdso_info.dm)) + zap_page_range(vma, vma->vm_start, size); +#endif } mmap_read_unlock(mm); @@ -265,7 +273,6 @@ static int __setup_additional_pages(struct mm_struct *mm, vdso_base += VVAR_SIZE; mm->context.vdso = (void *)vdso_base; - mm->context.vdso_info = (void *)vdso_info; ret = _install_special_mapping(mm, vdso_base, vdso_text_len, diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index f2fbd1400b7c..d86f7cebd4a7 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -184,7 +184,8 @@ static inline bool access_error(unsigned long cause, struct vm_area_struct *vma) } break; case EXC_LOAD_PAGE_FAULT: - if (!(vma->vm_flags & VM_READ)) { + /* Write implies read */ + if (!(vma->vm_flags & (VM_READ | VM_WRITE))) { return true; } break; diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 7c74d8cba44f..966aab902d19 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -52,9 +52,6 @@ static unsigned int num_devices = 1; static size_t huge_class_size; static const struct block_device_operations zram_devops; -#ifdef CONFIG_ZRAM_WRITEBACK -static const struct block_device_operations zram_wb_devops; -#endif static void zram_free_page(struct zram *zram, size_t index); static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, @@ -546,17 +543,6 @@ static ssize_t backing_dev_store(struct device *dev, zram->backing_dev = backing_dev; zram->bitmap = bitmap; zram->nr_pages = nr_pages; - /* - * With writeback feature, zram does asynchronous IO so it's no longer - * synchronous device so let's remove synchronous io flag. Othewise, - * upper layer(e.g., swap) could wait IO completion rather than - * (submit and return), which will cause system sluggish. - * Furthermore, when the IO function returns(e.g., swap_readpage), - * upper layer expects IO was done so it could deallocate the page - * freely but in fact, IO is going on so finally could cause - * use-after-free when the IO is really done. - */ - zram->disk->fops = &zram_wb_devops; up_write(&zram->init_lock); pr_info("setup backing device %s\n", file_name); @@ -1270,6 +1256,9 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index, struct bio_vec bvec; zram_slot_unlock(zram, index); + /* A null bio means rw_page was used, we must fallback to bio */ + if (!bio) + return -EOPNOTSUPP; bvec.bv_page = page; bvec.bv_len = PAGE_SIZE; @@ -1856,15 +1845,6 @@ static const struct block_device_operations zram_devops = { .owner = THIS_MODULE }; -#ifdef CONFIG_ZRAM_WRITEBACK -static const struct block_device_operations zram_wb_devops = { - .open = zram_open, - .submit_bio = zram_submit_bio, - .swap_slot_free_notify = zram_slot_free_notify, - .owner = THIS_MODULE -}; -#endif - static DEVICE_ATTR_WO(compact); static DEVICE_ATTR_RW(disksize); static DEVICE_ATTR_RO(initstate); diff --git a/drivers/clk/spear/spear3xx_clock.c b/drivers/clk/spear/spear3xx_clock.c index 41717ff707f6..ba8791303156 100644 --- a/drivers/clk/spear/spear3xx_clock.c +++ b/drivers/clk/spear/spear3xx_clock.c @@ -8,6 +8,7 @@ #include #include +#include #include #include #include diff --git a/drivers/clk/spear/spear6xx_clock.c b/drivers/clk/spear/spear6xx_clock.c index 490701ac9e93..c192a9141b86 100644 --- a/drivers/clk/spear/spear6xx_clock.c +++ b/drivers/clk/spear/spear6xx_clock.c @@ -7,6 +7,7 @@ */ #include +#include #include #include #include "clk.h" diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index 17562cf1fe97..456602d373b7 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -473,7 +473,7 @@ config EDAC_ALTERA_SDMMC config EDAC_SIFIVE bool "Sifive platform EDAC driver" - depends on EDAC=y && SIFIVE_L2 + depends on EDAC=y && SIFIVE_CCACHE help Support for error detection and correction on the SiFive SoCs. diff --git a/drivers/edac/sifive_edac.c b/drivers/edac/sifive_edac.c index ee800aec7d47..b844e2626fd5 100644 --- a/drivers/edac/sifive_edac.c +++ b/drivers/edac/sifive_edac.c @@ -2,7 +2,7 @@ /* * SiFive Platform EDAC Driver * - * Copyright (C) 2018-2019 SiFive, Inc. + * Copyright (C) 2018-2022 SiFive, Inc. * * This driver is partially based on octeon_edac-pc.c * @@ -10,7 +10,7 @@ #include #include #include "edac_module.h" -#include +#include #define DRVNAME "sifive_edac" @@ -32,9 +32,9 @@ int ecc_err_event(struct notifier_block *this, unsigned long event, void *ptr) p = container_of(this, struct sifive_edac_priv, notifier); - if (event == SIFIVE_L2_ERR_TYPE_UE) + if (event == SIFIVE_CCACHE_ERR_TYPE_UE) edac_device_handle_ue(p->dci, 0, 0, msg); - else if (event == SIFIVE_L2_ERR_TYPE_CE) + else if (event == SIFIVE_CCACHE_ERR_TYPE_CE) edac_device_handle_ce(p->dci, 0, 0, msg); return NOTIFY_OK; @@ -67,7 +67,7 @@ static int ecc_register(struct platform_device *pdev) goto err; } - register_sifive_l2_error_notifier(&p->notifier); + register_sifive_ccache_error_notifier(&p->notifier); return 0; @@ -81,7 +81,7 @@ static int ecc_unregister(struct platform_device *pdev) { struct sifive_edac_priv *p = platform_get_drvdata(pdev); - unregister_sifive_l2_error_notifier(&p->notifier); + unregister_sifive_ccache_error_notifier(&p->notifier); edac_device_del_device(&pdev->dev); edac_device_free_ctl_info(p->dci); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index c70c026c9a93..2797029bd500 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -223,7 +223,7 @@ svm_migrate_get_vram_page(struct svm_range *prange, unsigned long pfn) page = pfn_to_page(pfn); svm_range_bo_ref(prange->svm_bo); page->zone_device_data = prange->svm_bo; - lock_page(page); + zone_device_page_init(page); } static void @@ -410,7 +410,7 @@ svm_migrate_vma_to_vram(struct amdgpu_device *adev, struct svm_range *prange, uint64_t npages = (end - start) >> PAGE_SHIFT; struct kfd_process_device *pdd; struct dma_fence *mfence = NULL; - struct migrate_vma migrate; + struct migrate_vma migrate = { 0 }; unsigned long cpages = 0; dma_addr_t *scratch; void *buf; @@ -666,7 +666,7 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange, static long svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange, struct vm_area_struct *vma, uint64_t start, uint64_t end, - uint32_t trigger) + uint32_t trigger, struct page *fault_page) { struct kfd_process *p = container_of(prange->svms, struct kfd_process, svms); uint64_t npages = (end - start) >> PAGE_SHIFT; @@ -674,7 +674,7 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange, unsigned long cpages = 0; struct kfd_process_device *pdd; struct dma_fence *mfence = NULL; - struct migrate_vma migrate; + struct migrate_vma migrate = { 0 }; dma_addr_t *scratch; void *buf; int r = -ENOMEM; @@ -697,6 +697,7 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange, migrate.src = buf; migrate.dst = migrate.src + npages; + migrate.fault_page = fault_page; scratch = (dma_addr_t *)(migrate.dst + npages); kfd_smi_event_migration_start(adev->kfd.dev, p->lead_thread->pid, @@ -764,7 +765,7 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange, * 0 - OK, otherwise error code */ int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm, - uint32_t trigger) + uint32_t trigger, struct page *fault_page) { struct amdgpu_device *adev; struct vm_area_struct *vma; @@ -805,7 +806,8 @@ int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm, } next = min(vma->vm_end, end); - r = svm_migrate_vma_to_ram(adev, prange, vma, addr, next, trigger); + r = svm_migrate_vma_to_ram(adev, prange, vma, addr, next, trigger, + fault_page); if (r < 0) { pr_debug("failed %ld to migrate prange %p\n", r, prange); break; @@ -849,7 +851,7 @@ svm_migrate_vram_to_vram(struct svm_range *prange, uint32_t best_loc, pr_debug("from gpu 0x%x to gpu 0x%x\n", prange->actual_loc, best_loc); do { - r = svm_migrate_vram_to_ram(prange, mm, trigger); + r = svm_migrate_vram_to_ram(prange, mm, trigger, NULL); if (r) return r; } while (prange->actual_loc && --retries); @@ -950,7 +952,8 @@ static vm_fault_t svm_migrate_to_ram(struct vm_fault *vmf) } r = svm_migrate_vram_to_ram(prange, vmf->vma->vm_mm, - KFD_MIGRATE_TRIGGER_PAGEFAULT_CPU); + KFD_MIGRATE_TRIGGER_PAGEFAULT_CPU, + vmf->page); if (r) pr_debug("failed %d migrate svms 0x%p range 0x%p [0x%lx 0x%lx]\n", r, prange->svms, prange, prange->start, prange->last); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h index b3f0754b32fa..a5d7e6d22264 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h @@ -43,7 +43,7 @@ enum MIGRATION_COPY_DIR { int svm_migrate_to_vram(struct svm_range *prange, uint32_t best_loc, struct mm_struct *mm, uint32_t trigger); int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm, - uint32_t trigger); + uint32_t trigger, struct page *fault_page); unsigned long svm_migrate_addr_to_pfn(struct amdgpu_device *adev, unsigned long addr); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index f5913ba22174..64fdf63093a0 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -2913,13 +2913,15 @@ svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid, */ if (prange->actual_loc) r = svm_migrate_vram_to_ram(prange, mm, - KFD_MIGRATE_TRIGGER_PAGEFAULT_GPU); + KFD_MIGRATE_TRIGGER_PAGEFAULT_GPU, + NULL); else r = 0; } } else { r = svm_migrate_vram_to_ram(prange, mm, - KFD_MIGRATE_TRIGGER_PAGEFAULT_GPU); + KFD_MIGRATE_TRIGGER_PAGEFAULT_GPU, + NULL); } if (r) { pr_debug("failed %d to migrate svms %p [0x%lx 0x%lx]\n", @@ -3278,7 +3280,8 @@ svm_range_trigger_migration(struct mm_struct *mm, struct svm_range *prange, return 0; if (!best_loc) { - r = svm_migrate_vram_to_ram(prange, mm, KFD_MIGRATE_TRIGGER_PREFETCH); + r = svm_migrate_vram_to_ram(prange, mm, + KFD_MIGRATE_TRIGGER_PREFETCH, NULL); *migrated = !r; return r; } @@ -3339,7 +3342,7 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work) mutex_lock(&prange->migrate_mutex); do { r = svm_migrate_vram_to_ram(prange, mm, - KFD_MIGRATE_TRIGGER_TTM_EVICTION); + KFD_MIGRATE_TRIGGER_TTM_EVICTION, NULL); } while (!r && prange->actual_loc && --retries); if (!r && prange->actual_loc) 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 f6a9e8fdd87d..c053cb79cd06 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -8310,8 +8310,8 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) crtc, dm_new_crtc_state, cur_crc_src)) DRM_DEBUG_DRIVER("Failed to configure crc source"); } -#endif } +#endif } for_each_new_crtc_in_state(state, crtc, new_crtc_state, j) diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 16356611b5b9..5fe209107246 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -139,44 +139,24 @@ static void nouveau_dmem_fence_done(struct nouveau_fence **fence) } } -static vm_fault_t nouveau_dmem_fault_copy_one(struct nouveau_drm *drm, - struct vm_fault *vmf, struct migrate_vma *args, - dma_addr_t *dma_addr) +static int nouveau_dmem_copy_one(struct nouveau_drm *drm, struct page *spage, + struct page *dpage, dma_addr_t *dma_addr) { struct device *dev = drm->dev->dev; - struct page *dpage, *spage; - struct nouveau_svmm *svmm; - spage = migrate_pfn_to_page(args->src[0]); - if (!spage || !(args->src[0] & MIGRATE_PFN_MIGRATE)) - return 0; - - dpage = alloc_page_vma(GFP_HIGHUSER, vmf->vma, vmf->address); - if (!dpage) - return VM_FAULT_SIGBUS; lock_page(dpage); *dma_addr = dma_map_page(dev, dpage, 0, PAGE_SIZE, DMA_BIDIRECTIONAL); if (dma_mapping_error(dev, *dma_addr)) - goto error_free_page; + return -EIO; - svmm = spage->zone_device_data; - mutex_lock(&svmm->mutex); - nouveau_svmm_invalidate(svmm, args->start, args->end); if (drm->dmem->migrate.copy_func(drm, 1, NOUVEAU_APER_HOST, *dma_addr, - NOUVEAU_APER_VRAM, nouveau_dmem_page_addr(spage))) - goto error_dma_unmap; - mutex_unlock(&svmm->mutex); + NOUVEAU_APER_VRAM, nouveau_dmem_page_addr(spage))) { + dma_unmap_page(dev, *dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL); + return -EIO; + } - args->dst[0] = migrate_pfn(page_to_pfn(dpage)); return 0; - -error_dma_unmap: - mutex_unlock(&svmm->mutex); - dma_unmap_page(dev, *dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL); -error_free_page: - __free_page(dpage); - return VM_FAULT_SIGBUS; } static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf) @@ -184,9 +164,11 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf) struct nouveau_drm *drm = page_to_drm(vmf->page); struct nouveau_dmem *dmem = drm->dmem; struct nouveau_fence *fence; + struct nouveau_svmm *svmm; + struct page *spage, *dpage; unsigned long src = 0, dst = 0; dma_addr_t dma_addr = 0; - vm_fault_t ret; + vm_fault_t ret = 0; struct migrate_vma args = { .vma = vmf->vma, .start = vmf->address, @@ -207,10 +189,26 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf) if (!args.cpages) return 0; - ret = nouveau_dmem_fault_copy_one(drm, vmf, &args, &dma_addr); - if (ret || dst == 0) + spage = migrate_pfn_to_page(src); + if (!spage || !(src & MIGRATE_PFN_MIGRATE)) goto done; + dpage = alloc_page_vma(GFP_HIGHUSER, vmf->vma, vmf->address); + if (!dpage) + goto done; + + dst = migrate_pfn(page_to_pfn(dpage)); + + svmm = spage->zone_device_data; + mutex_lock(&svmm->mutex); + nouveau_svmm_invalidate(svmm, args.start, args.end); + ret = nouveau_dmem_copy_one(drm, spage, dpage, &dma_addr); + mutex_unlock(&svmm->mutex); + if (ret) { + ret = VM_FAULT_SIGBUS; + goto done; + } + nouveau_fence_new(dmem->migrate.chan, false, &fence); migrate_vma_pages(&args); nouveau_dmem_fence_done(&fence); @@ -326,7 +324,7 @@ nouveau_dmem_page_alloc_locked(struct nouveau_drm *drm) return NULL; } - lock_page(page); + zone_device_page_init(page); return page; } @@ -369,6 +367,52 @@ nouveau_dmem_suspend(struct nouveau_drm *drm) mutex_unlock(&drm->dmem->mutex); } +/* + * Evict all pages mapping a chunk. + */ +static void +nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk) +{ + unsigned long i, npages = range_len(&chunk->pagemap.range) >> PAGE_SHIFT; + unsigned long *src_pfns, *dst_pfns; + dma_addr_t *dma_addrs; + struct nouveau_fence *fence; + + src_pfns = kcalloc(npages, sizeof(*src_pfns), GFP_KERNEL); + dst_pfns = kcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL); + dma_addrs = kcalloc(npages, sizeof(*dma_addrs), GFP_KERNEL); + + migrate_device_range(src_pfns, chunk->pagemap.range.start >> PAGE_SHIFT, + npages); + + for (i = 0; i < npages; i++) { + if (src_pfns[i] & MIGRATE_PFN_MIGRATE) { + struct page *dpage; + + /* + * _GFP_NOFAIL because the GPU is going away and there + * is nothing sensible we can do if we can't copy the + * data back. + */ + dpage = alloc_page(GFP_HIGHUSER | __GFP_NOFAIL); + dst_pfns[i] = migrate_pfn(page_to_pfn(dpage)); + nouveau_dmem_copy_one(chunk->drm, + migrate_pfn_to_page(src_pfns[i]), dpage, + &dma_addrs[i]); + } + } + + nouveau_fence_new(chunk->drm->dmem->migrate.chan, false, &fence); + migrate_device_pages(src_pfns, dst_pfns, npages); + nouveau_dmem_fence_done(&fence); + migrate_device_finalize(src_pfns, dst_pfns, npages); + kfree(src_pfns); + kfree(dst_pfns); + for (i = 0; i < npages; i++) + dma_unmap_page(chunk->drm->dev->dev, dma_addrs[i], PAGE_SIZE, DMA_BIDIRECTIONAL); + kfree(dma_addrs); +} + void nouveau_dmem_fini(struct nouveau_drm *drm) { @@ -380,8 +424,10 @@ nouveau_dmem_fini(struct nouveau_drm *drm) mutex_lock(&drm->dmem->mutex); list_for_each_entry_safe(chunk, tmp, &drm->dmem->chunks, list) { + nouveau_dmem_evict_chunk(chunk); nouveau_bo_unpin(chunk->bo); nouveau_bo_ref(NULL, &chunk->bo); + WARN_ON(chunk->callocated); list_del(&chunk->list); memunmap_pages(&chunk->pagemap); release_mem_region(chunk->pagemap.range.start, diff --git a/drivers/leds/leds-pca963x.c b/drivers/leds/leds-pca963x.c index 00aecd67e348..a7e052c1db53 100644 --- a/drivers/leds/leds-pca963x.c +++ b/drivers/leds/leds-pca963x.c @@ -101,6 +101,7 @@ struct pca963x_led { struct pca963x *chip; struct led_classdev led_cdev; int led_num; /* 0 .. 15 potentially */ + bool blinking; u8 gdc; u8 gfrq; }; @@ -129,12 +130,21 @@ static int pca963x_brightness(struct pca963x_led *led, switch (brightness) { case LED_FULL: - val = (ledout & ~mask) | (PCA963X_LED_ON << shift); + if (led->blinking) { + val = (ledout & ~mask) | (PCA963X_LED_GRP_PWM << shift); + ret = i2c_smbus_write_byte_data(client, + PCA963X_PWM_BASE + + led->led_num, + LED_FULL); + } else { + val = (ledout & ~mask) | (PCA963X_LED_ON << shift); + } ret = i2c_smbus_write_byte_data(client, ledout_addr, val); break; case LED_OFF: val = ledout & ~mask; ret = i2c_smbus_write_byte_data(client, ledout_addr, val); + led->blinking = false; break; default: ret = i2c_smbus_write_byte_data(client, @@ -144,7 +154,11 @@ static int pca963x_brightness(struct pca963x_led *led, if (ret < 0) return ret; - val = (ledout & ~mask) | (PCA963X_LED_PWM << shift); + if (led->blinking) + val = (ledout & ~mask) | (PCA963X_LED_GRP_PWM << shift); + else + val = (ledout & ~mask) | (PCA963X_LED_PWM << shift); + ret = i2c_smbus_write_byte_data(client, ledout_addr, val); break; } @@ -181,6 +195,7 @@ static void pca963x_blink(struct pca963x_led *led) } mutex_unlock(&led->chip->mutex); + led->blinking = true; } static int pca963x_power_state(struct pca963x_led *led) @@ -275,6 +290,8 @@ static int pca963x_blink_set(struct led_classdev *led_cdev, led->gfrq = gfrq; pca963x_blink(led); + led->led_cdev.brightness = LED_FULL; + pca963x_led_set(led_cdev, LED_FULL); *delay_on = time_on; *delay_off = time_off; @@ -337,6 +354,7 @@ static int pca963x_register_leds(struct i2c_client *client, led->led_cdev.brightness_set_blocking = pca963x_led_set; if (hw_blink) led->led_cdev.blink_set = pca963x_blink_set; + led->blinking = false; init_data.fwnode = child; /* for backwards compatibility */ diff --git a/drivers/parisc/eisa_enumerator.c b/drivers/parisc/eisa_enumerator.c index f54a6f450391..f0cb31198a8f 100644 --- a/drivers/parisc/eisa_enumerator.c +++ b/drivers/parisc/eisa_enumerator.c @@ -393,7 +393,7 @@ static int parse_slot_config(int slot, } if (p0 + function_len < pos) { - printk(KERN_ERR "eisa_enumerator: function %d length mis-match " + printk(KERN_ERR "eisa_enumerator: function %d length mismatch " "got %d, expected %d\n", num_func, pos-p0, function_len); res=-1; @@ -407,13 +407,13 @@ static int parse_slot_config(int slot, } if (pos != es->config_data_length) { - printk(KERN_ERR "eisa_enumerator: config data length mis-match got %d, expected %d\n", + printk(KERN_ERR "eisa_enumerator: config data length mismatch got %d, expected %d\n", pos, es->config_data_length); res=-1; } if (num_func != es->num_functions) { - printk(KERN_ERR "eisa_enumerator: number of functions mis-match got %d, expected %d\n", + printk(KERN_ERR "eisa_enumerator: number of functions mismatch got %d, expected %d\n", num_func, es->num_functions); res=-2; } @@ -451,7 +451,7 @@ static int init_slot(int slot, struct eeprom_eisa_slot_info *es) } if (es->eisa_slot_id != id) { print_eisa_id(id_string, id); - printk(KERN_ERR "EISA slot %d id mis-match: got %s", + printk(KERN_ERR "EISA slot %d id mismatch: got %s", slot, id_string); print_eisa_id(id_string, es->eisa_slot_id); diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig index 44c07ea487f4..341010f20b77 100644 --- a/drivers/perf/Kconfig +++ b/drivers/perf/Kconfig @@ -185,7 +185,7 @@ config APPLE_M1_CPU_PMU config ALIBABA_UNCORE_DRW_PMU tristate "Alibaba T-Head Yitian 710 DDR Sub-system Driveway PMU driver" - depends on ARM64 || COMPILE_TEST + depends on (ARM64 && ACPI) || COMPILE_TEST help Support for Driveway PMU events monitoring on Yitian 710 DDR Sub-system. diff --git a/drivers/perf/alibaba_uncore_drw_pmu.c b/drivers/perf/alibaba_uncore_drw_pmu.c index 82729b874f09..a7689fecb49d 100644 --- a/drivers/perf/alibaba_uncore_drw_pmu.c +++ b/drivers/perf/alibaba_uncore_drw_pmu.c @@ -658,8 +658,8 @@ static int ali_drw_pmu_probe(struct platform_device *pdev) res = platform_get_resource(pdev, IORESOURCE_MEM, 0); drw_pmu->cfg_base = devm_ioremap_resource(&pdev->dev, res); - if (!drw_pmu->cfg_base) - return -ENOMEM; + if (IS_ERR(drw_pmu->cfg_base)) + return PTR_ERR(drw_pmu->cfg_base); name = devm_kasprintf(drw_pmu->dev, GFP_KERNEL, "ali_drw_%llx", (u64) (res->start >> ALI_DRW_PMU_PA_SHIFT)); diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 15e5a47be7d5..3852c18362f5 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -652,8 +652,11 @@ static int pmu_sbi_starting_cpu(unsigned int cpu, struct hlist_node *node) struct riscv_pmu *pmu = hlist_entry_safe(node, struct riscv_pmu, node); struct cpu_hw_events *cpu_hw_evt = this_cpu_ptr(pmu->hw_events); - /* Enable the access for TIME csr only from the user mode now */ - csr_write(CSR_SCOUNTEREN, 0x2); + /* + * Enable the access for CYCLE, TIME, and INSTRET CSRs from userspace, + * as is necessary to maintain uABI compatibility. + */ + csr_write(CSR_SCOUNTEREN, 0x7); /* Stop all the counters so that they can be enabled from perf */ pmu_sbi_stop_all(pmu); diff --git a/drivers/s390/char/vmur.c b/drivers/s390/char/vmur.c index 68f49e2e964c..131293f7f152 100644 --- a/drivers/s390/char/vmur.c +++ b/drivers/s390/char/vmur.c @@ -15,12 +15,14 @@ #include #include #include +#include #include #include #include #include #include +#include #include "vmur.h" @@ -78,6 +80,8 @@ static struct ccw_driver ur_driver = { static DEFINE_MUTEX(vmur_mutex); +static void ur_uevent(struct work_struct *ws); + /* * Allocation, freeing, getting and putting of urdev structures * @@ -108,6 +112,7 @@ static struct urdev *urdev_alloc(struct ccw_device *cdev) ccw_device_get_id(cdev, &urd->dev_id); mutex_init(&urd->io_mutex); init_waitqueue_head(&urd->wait); + INIT_WORK(&urd->uevent_work, ur_uevent); spin_lock_init(&urd->open_lock); refcount_set(&urd->ref_count, 1); urd->cdev = cdev; @@ -275,6 +280,18 @@ static int do_ur_io(struct urdev *urd, struct ccw1 *cpa) return rc; } +static void ur_uevent(struct work_struct *ws) +{ + struct urdev *urd = container_of(ws, struct urdev, uevent_work); + char *envp[] = { + "EVENT=unsol_de", /* Unsolicited device-end interrupt */ + NULL + }; + + kobject_uevent_env(&urd->cdev->dev.kobj, KOBJ_CHANGE, envp); + urdev_put(urd); +} + /* * ur interrupt handler, called from the ccw_device layer */ @@ -288,12 +305,21 @@ static void ur_int_handler(struct ccw_device *cdev, unsigned long intparm, intparm, irb->scsw.cmd.cstat, irb->scsw.cmd.dstat, irb->scsw.cmd.count); } + urd = dev_get_drvdata(&cdev->dev); if (!intparm) { TRACE("ur_int_handler: unsolicited interrupt\n"); + + if (scsw_dstat(&irb->scsw) & DEV_STAT_DEV_END) { + /* + * Userspace might be interested in a transition to + * device-ready state. + */ + urdev_get(urd); + schedule_work(&urd->uevent_work); + } + return; } - urd = dev_get_drvdata(&cdev->dev); - BUG_ON(!urd); /* On special conditions irb is an error pointer */ if (IS_ERR(irb)) urd->io_request_rc = PTR_ERR(irb); @@ -809,7 +835,6 @@ static int ur_probe(struct ccw_device *cdev) rc = -ENOMEM; goto fail_urdev_put; } - cdev->handler = ur_int_handler; /* validate virtual unit record device */ urd->class = get_urd_class(urd); @@ -823,6 +848,7 @@ static int ur_probe(struct ccw_device *cdev) } spin_lock_irq(get_ccwdev_lock(cdev)); dev_set_drvdata(&cdev->dev, urd); + cdev->handler = ur_int_handler; spin_unlock_irq(get_ccwdev_lock(cdev)); mutex_unlock(&vmur_mutex); @@ -928,6 +954,10 @@ static int ur_set_offline_force(struct ccw_device *cdev, int force) rc = -EBUSY; goto fail_urdev_put; } + if (cancel_work_sync(&urd->uevent_work)) { + /* Work not run yet - need to release reference here */ + urdev_put(urd); + } device_destroy(vmur_class, urd->char_device->dev); cdev_del(urd->char_device); urd->char_device = NULL; @@ -963,6 +993,7 @@ static void ur_remove(struct ccw_device *cdev) spin_lock_irqsave(get_ccwdev_lock(cdev), flags); urdev_put(dev_get_drvdata(&cdev->dev)); dev_set_drvdata(&cdev->dev, NULL); + cdev->handler = NULL; spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags); mutex_unlock(&vmur_mutex); diff --git a/drivers/s390/char/vmur.h b/drivers/s390/char/vmur.h index 608b0719ce17..92d17d7cb47b 100644 --- a/drivers/s390/char/vmur.h +++ b/drivers/s390/char/vmur.h @@ -13,6 +13,7 @@ #define _VMUR_H_ #include +#include #define DEV_CLASS_UR_I 0x20 /* diag210 unit record input device class */ #define DEV_CLASS_UR_O 0x10 /* diag210 unit record output device class */ @@ -76,6 +77,7 @@ struct urdev { wait_queue_head_t wait; /* wait queue to serialize open */ int open_flag; /* "urdev is open" flag */ spinlock_t open_lock; /* serialize critical sections */ + struct work_struct uevent_work; /* work to send uevent */ }; /* diff --git a/drivers/soc/sifive/Kconfig b/drivers/soc/sifive/Kconfig index 58cf8c40d08d..ed4c571f8771 100644 --- a/drivers/soc/sifive/Kconfig +++ b/drivers/soc/sifive/Kconfig @@ -2,9 +2,9 @@ if SOC_SIFIVE -config SIFIVE_L2 - bool "Sifive L2 Cache controller" +config SIFIVE_CCACHE + bool "Sifive Composable Cache controller" help - Support for the L2 cache controller on SiFive platforms. + Support for the composable cache controller on SiFive platforms. endif diff --git a/drivers/soc/sifive/Makefile b/drivers/soc/sifive/Makefile index b5caff77938f..1f5dc339bf82 100644 --- a/drivers/soc/sifive/Makefile +++ b/drivers/soc/sifive/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_SIFIVE_L2) += sifive_l2_cache.o +obj-$(CONFIG_SIFIVE_CCACHE) += sifive_ccache.o diff --git a/drivers/soc/sifive/sifive_ccache.c b/drivers/soc/sifive/sifive_ccache.c new file mode 100644 index 000000000000..1c171150e878 --- /dev/null +++ b/drivers/soc/sifive/sifive_ccache.c @@ -0,0 +1,255 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * SiFive composable cache controller Driver + * + * Copyright (C) 2018-2022 SiFive, Inc. + * + */ + +#define pr_fmt(fmt) "CCACHE: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include + +#define SIFIVE_CCACHE_DIRECCFIX_LOW 0x100 +#define SIFIVE_CCACHE_DIRECCFIX_HIGH 0x104 +#define SIFIVE_CCACHE_DIRECCFIX_COUNT 0x108 + +#define SIFIVE_CCACHE_DIRECCFAIL_LOW 0x120 +#define SIFIVE_CCACHE_DIRECCFAIL_HIGH 0x124 +#define SIFIVE_CCACHE_DIRECCFAIL_COUNT 0x128 + +#define SIFIVE_CCACHE_DATECCFIX_LOW 0x140 +#define SIFIVE_CCACHE_DATECCFIX_HIGH 0x144 +#define SIFIVE_CCACHE_DATECCFIX_COUNT 0x148 + +#define SIFIVE_CCACHE_DATECCFAIL_LOW 0x160 +#define SIFIVE_CCACHE_DATECCFAIL_HIGH 0x164 +#define SIFIVE_CCACHE_DATECCFAIL_COUNT 0x168 + +#define SIFIVE_CCACHE_CONFIG 0x00 +#define SIFIVE_CCACHE_CONFIG_BANK_MASK GENMASK_ULL(7, 0) +#define SIFIVE_CCACHE_CONFIG_WAYS_MASK GENMASK_ULL(15, 8) +#define SIFIVE_CCACHE_CONFIG_SETS_MASK GENMASK_ULL(23, 16) +#define SIFIVE_CCACHE_CONFIG_BLKS_MASK GENMASK_ULL(31, 24) + +#define SIFIVE_CCACHE_WAYENABLE 0x08 +#define SIFIVE_CCACHE_ECCINJECTERR 0x40 + +#define SIFIVE_CCACHE_MAX_ECCINTR 4 + +static void __iomem *ccache_base; +static int g_irq[SIFIVE_CCACHE_MAX_ECCINTR]; +static struct riscv_cacheinfo_ops ccache_cache_ops; +static int level; + +enum { + DIR_CORR = 0, + DATA_CORR, + DATA_UNCORR, + DIR_UNCORR, +}; + +#ifdef CONFIG_DEBUG_FS +static struct dentry *sifive_test; + +static ssize_t ccache_write(struct file *file, const char __user *data, + size_t count, loff_t *ppos) +{ + unsigned int val; + + if (kstrtouint_from_user(data, count, 0, &val)) + return -EINVAL; + if ((val < 0xFF) || (val >= 0x10000 && val < 0x100FF)) + writel(val, ccache_base + SIFIVE_CCACHE_ECCINJECTERR); + else + return -EINVAL; + return count; +} + +static const struct file_operations ccache_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .write = ccache_write +}; + +static void setup_sifive_debug(void) +{ + sifive_test = debugfs_create_dir("sifive_ccache_cache", NULL); + + debugfs_create_file("sifive_debug_inject_error", 0200, + sifive_test, NULL, &ccache_fops); +} +#endif + +static void ccache_config_read(void) +{ + u32 cfg; + + cfg = readl(ccache_base + SIFIVE_CCACHE_CONFIG); + pr_info("%llu banks, %llu ways, sets/bank=%llu, bytes/block=%llu\n", + FIELD_GET(SIFIVE_CCACHE_CONFIG_BANK_MASK, cfg), + FIELD_GET(SIFIVE_CCACHE_CONFIG_WAYS_MASK, cfg), + BIT_ULL(FIELD_GET(SIFIVE_CCACHE_CONFIG_SETS_MASK, cfg)), + BIT_ULL(FIELD_GET(SIFIVE_CCACHE_CONFIG_BLKS_MASK, cfg))); + + cfg = readl(ccache_base + SIFIVE_CCACHE_WAYENABLE); + pr_info("Index of the largest way enabled: %u\n", cfg); +} + +static const struct of_device_id sifive_ccache_ids[] = { + { .compatible = "sifive,fu540-c000-ccache" }, + { .compatible = "sifive,fu740-c000-ccache" }, + { .compatible = "sifive,ccache0" }, + { /* end of table */ } +}; + +static ATOMIC_NOTIFIER_HEAD(ccache_err_chain); + +int register_sifive_ccache_error_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_register(&ccache_err_chain, nb); +} +EXPORT_SYMBOL_GPL(register_sifive_ccache_error_notifier); + +int unregister_sifive_ccache_error_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&ccache_err_chain, nb); +} +EXPORT_SYMBOL_GPL(unregister_sifive_ccache_error_notifier); + +static int ccache_largest_wayenabled(void) +{ + return readl(ccache_base + SIFIVE_CCACHE_WAYENABLE) & 0xFF; +} + +static ssize_t number_of_ways_enabled_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", ccache_largest_wayenabled()); +} + +static DEVICE_ATTR_RO(number_of_ways_enabled); + +static struct attribute *priv_attrs[] = { + &dev_attr_number_of_ways_enabled.attr, + NULL, +}; + +static const struct attribute_group priv_attr_group = { + .attrs = priv_attrs, +}; + +static const struct attribute_group *ccache_get_priv_group(struct cacheinfo + *this_leaf) +{ + /* We want to use private group for composable cache only */ + if (this_leaf->level == level) + return &priv_attr_group; + else + return NULL; +} + +static irqreturn_t ccache_int_handler(int irq, void *device) +{ + unsigned int add_h, add_l; + + if (irq == g_irq[DIR_CORR]) { + add_h = readl(ccache_base + SIFIVE_CCACHE_DIRECCFIX_HIGH); + add_l = readl(ccache_base + SIFIVE_CCACHE_DIRECCFIX_LOW); + pr_err("DirError @ 0x%08X.%08X\n", add_h, add_l); + /* Reading this register clears the DirError interrupt sig */ + readl(ccache_base + SIFIVE_CCACHE_DIRECCFIX_COUNT); + atomic_notifier_call_chain(&ccache_err_chain, + SIFIVE_CCACHE_ERR_TYPE_CE, + "DirECCFix"); + } + if (irq == g_irq[DIR_UNCORR]) { + add_h = readl(ccache_base + SIFIVE_CCACHE_DIRECCFAIL_HIGH); + add_l = readl(ccache_base + SIFIVE_CCACHE_DIRECCFAIL_LOW); + /* Reading this register clears the DirFail interrupt sig */ + readl(ccache_base + SIFIVE_CCACHE_DIRECCFAIL_COUNT); + atomic_notifier_call_chain(&ccache_err_chain, + SIFIVE_CCACHE_ERR_TYPE_UE, + "DirECCFail"); + panic("CCACHE: DirFail @ 0x%08X.%08X\n", add_h, add_l); + } + if (irq == g_irq[DATA_CORR]) { + add_h = readl(ccache_base + SIFIVE_CCACHE_DATECCFIX_HIGH); + add_l = readl(ccache_base + SIFIVE_CCACHE_DATECCFIX_LOW); + pr_err("DataError @ 0x%08X.%08X\n", add_h, add_l); + /* Reading this register clears the DataError interrupt sig */ + readl(ccache_base + SIFIVE_CCACHE_DATECCFIX_COUNT); + atomic_notifier_call_chain(&ccache_err_chain, + SIFIVE_CCACHE_ERR_TYPE_CE, + "DatECCFix"); + } + if (irq == g_irq[DATA_UNCORR]) { + add_h = readl(ccache_base + SIFIVE_CCACHE_DATECCFAIL_HIGH); + add_l = readl(ccache_base + SIFIVE_CCACHE_DATECCFAIL_LOW); + pr_err("DataFail @ 0x%08X.%08X\n", add_h, add_l); + /* Reading this register clears the DataFail interrupt sig */ + readl(ccache_base + SIFIVE_CCACHE_DATECCFAIL_COUNT); + atomic_notifier_call_chain(&ccache_err_chain, + SIFIVE_CCACHE_ERR_TYPE_UE, + "DatECCFail"); + } + + return IRQ_HANDLED; +} + +static int __init sifive_ccache_init(void) +{ + struct device_node *np; + struct resource res; + int i, rc, intr_num; + + np = of_find_matching_node(NULL, sifive_ccache_ids); + if (!np) + return -ENODEV; + + if (of_address_to_resource(np, 0, &res)) + return -ENODEV; + + ccache_base = ioremap(res.start, resource_size(&res)); + if (!ccache_base) + return -ENOMEM; + + if (of_property_read_u32(np, "cache-level", &level)) + return -ENOENT; + + intr_num = of_property_count_u32_elems(np, "interrupts"); + if (!intr_num) { + pr_err("No interrupts property\n"); + return -ENODEV; + } + + for (i = 0; i < intr_num; i++) { + g_irq[i] = irq_of_parse_and_map(np, i); + rc = request_irq(g_irq[i], ccache_int_handler, 0, "ccache_ecc", + NULL); + if (rc) { + pr_err("Could not request IRQ %d\n", g_irq[i]); + return rc; + } + } + + ccache_config_read(); + + ccache_cache_ops.get_priv_group = ccache_get_priv_group; + riscv_set_cacheinfo_ops(&ccache_cache_ops); + +#ifdef CONFIG_DEBUG_FS + setup_sifive_debug(); +#endif + return 0; +} + +device_initcall(sifive_ccache_init); diff --git a/drivers/soc/sifive/sifive_l2_cache.c b/drivers/soc/sifive/sifive_l2_cache.c deleted file mode 100644 index 59640a1d0b28..000000000000 --- a/drivers/soc/sifive/sifive_l2_cache.c +++ /dev/null @@ -1,237 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * SiFive L2 cache controller Driver - * - * Copyright (C) 2018-2019 SiFive, Inc. - * - */ -#include -#include -#include -#include -#include -#include -#include - -#define SIFIVE_L2_DIRECCFIX_LOW 0x100 -#define SIFIVE_L2_DIRECCFIX_HIGH 0x104 -#define SIFIVE_L2_DIRECCFIX_COUNT 0x108 - -#define SIFIVE_L2_DIRECCFAIL_LOW 0x120 -#define SIFIVE_L2_DIRECCFAIL_HIGH 0x124 -#define SIFIVE_L2_DIRECCFAIL_COUNT 0x128 - -#define SIFIVE_L2_DATECCFIX_LOW 0x140 -#define SIFIVE_L2_DATECCFIX_HIGH 0x144 -#define SIFIVE_L2_DATECCFIX_COUNT 0x148 - -#define SIFIVE_L2_DATECCFAIL_LOW 0x160 -#define SIFIVE_L2_DATECCFAIL_HIGH 0x164 -#define SIFIVE_L2_DATECCFAIL_COUNT 0x168 - -#define SIFIVE_L2_CONFIG 0x00 -#define SIFIVE_L2_WAYENABLE 0x08 -#define SIFIVE_L2_ECCINJECTERR 0x40 - -#define SIFIVE_L2_MAX_ECCINTR 4 - -static void __iomem *l2_base; -static int g_irq[SIFIVE_L2_MAX_ECCINTR]; -static struct riscv_cacheinfo_ops l2_cache_ops; - -enum { - DIR_CORR = 0, - DATA_CORR, - DATA_UNCORR, - DIR_UNCORR, -}; - -#ifdef CONFIG_DEBUG_FS -static struct dentry *sifive_test; - -static ssize_t l2_write(struct file *file, const char __user *data, - size_t count, loff_t *ppos) -{ - unsigned int val; - - if (kstrtouint_from_user(data, count, 0, &val)) - return -EINVAL; - if ((val < 0xFF) || (val >= 0x10000 && val < 0x100FF)) - writel(val, l2_base + SIFIVE_L2_ECCINJECTERR); - else - return -EINVAL; - return count; -} - -static const struct file_operations l2_fops = { - .owner = THIS_MODULE, - .open = simple_open, - .write = l2_write -}; - -static void setup_sifive_debug(void) -{ - sifive_test = debugfs_create_dir("sifive_l2_cache", NULL); - - debugfs_create_file("sifive_debug_inject_error", 0200, - sifive_test, NULL, &l2_fops); -} -#endif - -static void l2_config_read(void) -{ - u32 regval, val; - - regval = readl(l2_base + SIFIVE_L2_CONFIG); - val = regval & 0xFF; - pr_info("L2CACHE: No. of Banks in the cache: %d\n", val); - val = (regval & 0xFF00) >> 8; - pr_info("L2CACHE: No. of ways per bank: %d\n", val); - val = (regval & 0xFF0000) >> 16; - pr_info("L2CACHE: Sets per bank: %llu\n", (uint64_t)1 << val); - val = (regval & 0xFF000000) >> 24; - pr_info("L2CACHE: Bytes per cache block: %llu\n", (uint64_t)1 << val); - - regval = readl(l2_base + SIFIVE_L2_WAYENABLE); - pr_info("L2CACHE: Index of the largest way enabled: %d\n", regval); -} - -static const struct of_device_id sifive_l2_ids[] = { - { .compatible = "sifive,fu540-c000-ccache" }, - { .compatible = "sifive,fu740-c000-ccache" }, - { /* end of table */ }, -}; - -static ATOMIC_NOTIFIER_HEAD(l2_err_chain); - -int register_sifive_l2_error_notifier(struct notifier_block *nb) -{ - return atomic_notifier_chain_register(&l2_err_chain, nb); -} -EXPORT_SYMBOL_GPL(register_sifive_l2_error_notifier); - -int unregister_sifive_l2_error_notifier(struct notifier_block *nb) -{ - return atomic_notifier_chain_unregister(&l2_err_chain, nb); -} -EXPORT_SYMBOL_GPL(unregister_sifive_l2_error_notifier); - -static int l2_largest_wayenabled(void) -{ - return readl(l2_base + SIFIVE_L2_WAYENABLE) & 0xFF; -} - -static ssize_t number_of_ways_enabled_show(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - return sprintf(buf, "%u\n", l2_largest_wayenabled()); -} - -static DEVICE_ATTR_RO(number_of_ways_enabled); - -static struct attribute *priv_attrs[] = { - &dev_attr_number_of_ways_enabled.attr, - NULL, -}; - -static const struct attribute_group priv_attr_group = { - .attrs = priv_attrs, -}; - -static const struct attribute_group *l2_get_priv_group(struct cacheinfo *this_leaf) -{ - /* We want to use private group for L2 cache only */ - if (this_leaf->level == 2) - return &priv_attr_group; - else - return NULL; -} - -static irqreturn_t l2_int_handler(int irq, void *device) -{ - unsigned int add_h, add_l; - - if (irq == g_irq[DIR_CORR]) { - add_h = readl(l2_base + SIFIVE_L2_DIRECCFIX_HIGH); - add_l = readl(l2_base + SIFIVE_L2_DIRECCFIX_LOW); - pr_err("L2CACHE: DirError @ 0x%08X.%08X\n", add_h, add_l); - /* Reading this register clears the DirError interrupt sig */ - readl(l2_base + SIFIVE_L2_DIRECCFIX_COUNT); - atomic_notifier_call_chain(&l2_err_chain, SIFIVE_L2_ERR_TYPE_CE, - "DirECCFix"); - } - if (irq == g_irq[DIR_UNCORR]) { - add_h = readl(l2_base + SIFIVE_L2_DIRECCFAIL_HIGH); - add_l = readl(l2_base + SIFIVE_L2_DIRECCFAIL_LOW); - /* Reading this register clears the DirFail interrupt sig */ - readl(l2_base + SIFIVE_L2_DIRECCFAIL_COUNT); - atomic_notifier_call_chain(&l2_err_chain, SIFIVE_L2_ERR_TYPE_UE, - "DirECCFail"); - panic("L2CACHE: DirFail @ 0x%08X.%08X\n", add_h, add_l); - } - if (irq == g_irq[DATA_CORR]) { - add_h = readl(l2_base + SIFIVE_L2_DATECCFIX_HIGH); - add_l = readl(l2_base + SIFIVE_L2_DATECCFIX_LOW); - pr_err("L2CACHE: DataError @ 0x%08X.%08X\n", add_h, add_l); - /* Reading this register clears the DataError interrupt sig */ - readl(l2_base + SIFIVE_L2_DATECCFIX_COUNT); - atomic_notifier_call_chain(&l2_err_chain, SIFIVE_L2_ERR_TYPE_CE, - "DatECCFix"); - } - if (irq == g_irq[DATA_UNCORR]) { - add_h = readl(l2_base + SIFIVE_L2_DATECCFAIL_HIGH); - add_l = readl(l2_base + SIFIVE_L2_DATECCFAIL_LOW); - pr_err("L2CACHE: DataFail @ 0x%08X.%08X\n", add_h, add_l); - /* Reading this register clears the DataFail interrupt sig */ - readl(l2_base + SIFIVE_L2_DATECCFAIL_COUNT); - atomic_notifier_call_chain(&l2_err_chain, SIFIVE_L2_ERR_TYPE_UE, - "DatECCFail"); - } - - return IRQ_HANDLED; -} - -static int __init sifive_l2_init(void) -{ - struct device_node *np; - struct resource res; - int i, rc, intr_num; - - np = of_find_matching_node(NULL, sifive_l2_ids); - if (!np) - return -ENODEV; - - if (of_address_to_resource(np, 0, &res)) - return -ENODEV; - - l2_base = ioremap(res.start, resource_size(&res)); - if (!l2_base) - return -ENOMEM; - - intr_num = of_property_count_u32_elems(np, "interrupts"); - if (!intr_num) { - pr_err("L2CACHE: no interrupts property\n"); - return -ENODEV; - } - - for (i = 0; i < intr_num; i++) { - g_irq[i] = irq_of_parse_and_map(np, i); - rc = request_irq(g_irq[i], l2_int_handler, 0, "l2_ecc", NULL); - if (rc) { - pr_err("L2CACHE: Could not request IRQ %d\n", g_irq[i]); - return rc; - } - } - - l2_config_read(); - - l2_cache_ops.get_priv_group = l2_get_priv_group; - riscv_set_cacheinfo_ops(&l2_cache_ops); - -#ifdef CONFIG_DEBUG_FS - setup_sifive_debug(); -#endif - return 0; -} -device_initcall(sifive_l2_init); diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index 113aafb5d9c3..a504c0e9b711 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -602,21 +602,6 @@ config SERIAL_MUX_CONSOLE select SERIAL_CORE_CONSOLE default y -config PDC_CONSOLE - bool "PDC software console support" - depends on PARISC && !SERIAL_MUX && VT - help - Saying Y here will enable the software based PDC console to be - used as the system console. This is useful for machines in - which the hardware based console has not been written yet. The - following steps must be completed to use the PDC console: - - 1. create the device entry (mknod /dev/ttyB0 c 11 0) - 2. Edit the /etc/inittab to start a getty listening on /dev/ttyB0 - 3. Add device ttyB0 to /etc/securetty (if you want to log on as - root on this console.) - 4. Change the kernel command console parameter to: console=ttyB0 - config SERIAL_SUNSAB tristate "Sun Siemens SAB82532 serial support" depends on SPARC && PCI diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c index 38a861e22c33..7753e586e65a 100644 --- a/drivers/video/fbdev/stifb.c +++ b/drivers/video/fbdev/stifb.c @@ -1298,7 +1298,7 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) /* limit fbsize to max visible screen size */ if (fix->smem_len > yres*fix->line_length) - fix->smem_len = yres*fix->line_length; + fix->smem_len = ALIGN(yres*fix->line_length, 4*1024*1024); fix->accel = FB_ACCEL_NONE; diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c index 20cadfb740dc..3c640bd7ecae 100644 --- a/fs/ext4/verity.c +++ b/fs/ext4/verity.c @@ -363,13 +363,14 @@ static struct page *ext4_read_merkle_tree_page(struct inode *inode, pgoff_t index, unsigned long num_ra_pages) { - DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, index); struct page *page; index += ext4_verity_metadata_pos(inode) >> PAGE_SHIFT; page = find_get_page_flags(inode->i_mapping, index, FGP_ACCESSED); if (!page || !PageUptodate(page)) { + DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, index); + if (page) put_page(page); else if (num_ra_pages > 1) diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c index f0805e51b3fe..c352fff88a5e 100644 --- a/fs/f2fs/verity.c +++ b/fs/f2fs/verity.c @@ -258,13 +258,14 @@ static struct page *f2fs_read_merkle_tree_page(struct inode *inode, pgoff_t index, unsigned long num_ra_pages) { - DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, index); struct page *page; index += f2fs_verity_metadata_pos(inode) >> PAGE_SHIFT; page = find_get_page_flags(inode->i_mapping, index, FGP_ACCESSED); if (!page || !PageUptodate(page)) { + DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, index); + if (page) put_page(page); else if (num_ra_pages > 1) diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 8f481d1b159a..6e01f10f0d88 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -428,6 +428,9 @@ struct cgroup { struct cgroup_file procs_file; /* handle for "cgroup.procs" */ struct cgroup_file events_file; /* handle for "cgroup.events" */ + /* handles for "{cpu,memory,io,irq}.pressure" */ + struct cgroup_file psi_files[NR_PSI_RESOURCES]; + /* * The bitmask of subsystems enabled on the child cgroups. * ->subtree_control is the one configured through diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 23b102b4349e..f2a9f2274c3b 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -682,11 +682,6 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp) pr_cont_kernfs_path(cgrp->kn); } -static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) -{ - return cgrp->psi; -} - bool cgroup_psi_enabled(void); static inline void cgroup_init_kthreadd(void) diff --git a/include/linux/clk/spear.h b/include/linux/clk/spear.h index a64d034ceddd..eaf95ca656f8 100644 --- a/include/linux/clk/spear.h +++ b/include/linux/clk/spear.h @@ -8,6 +8,20 @@ #ifndef __LINUX_CLK_SPEAR_H #define __LINUX_CLK_SPEAR_H +#ifdef CONFIG_ARCH_SPEAR3XX +void __init spear3xx_clk_init(void __iomem *misc_base, + void __iomem *soc_config_base); +#else +static inline void __init spear3xx_clk_init(void __iomem *misc_base, + void __iomem *soc_config_base) {} +#endif + +#ifdef CONFIG_ARCH_SPEAR6XX +void __init spear6xx_clk_init(void __iomem *misc_base); +#else +static inline void __init spear6xx_clk_init(void __iomem *misc_base) {} +#endif + #ifdef CONFIG_MACH_SPEAR1310 void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base); #else diff --git a/include/linux/damon.h b/include/linux/damon.h index ed5470f50bab..620ada094c3b 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -484,6 +484,12 @@ static inline struct damon_region *damon_first_region(struct damon_target *t) return list_first_entry(&t->regions_list, struct damon_region, list); } +static inline unsigned long damon_sz_region(struct damon_region *r) +{ + return r->ar.end - r->ar.start; +} + + #define damon_for_each_region(r, t) \ list_for_each_entry(r, &t->regions_list, list) diff --git a/include/linux/memremap.h b/include/linux/memremap.h index c3b4cc84877b..7fcaf3180a5b 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -187,6 +187,7 @@ static inline bool folio_is_device_coherent(const struct folio *folio) } #ifdef CONFIG_ZONE_DEVICE +void zone_device_page_init(struct page *page); void *memremap_pages(struct dev_pagemap *pgmap, int nid); void memunmap_pages(struct dev_pagemap *pgmap); void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap); diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 704a04f5a074..3ef77f52a4f0 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -62,6 +62,8 @@ extern const char *migrate_reason_names[MR_TYPES]; #ifdef CONFIG_MIGRATION extern void putback_movable_pages(struct list_head *l); +int migrate_folio_extra(struct address_space *mapping, struct folio *dst, + struct folio *src, enum migrate_mode mode, int extra_count); int migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode); extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, @@ -197,11 +199,24 @@ struct migrate_vma { */ void *pgmap_owner; unsigned long flags; + + /* + * Set to vmf->page if this is being called to migrate a page as part of + * a migrate_to_ram() callback. + */ + struct page *fault_page; }; int migrate_vma_setup(struct migrate_vma *args); void migrate_vma_pages(struct migrate_vma *migrate); void migrate_vma_finalize(struct migrate_vma *migrate); +int migrate_device_range(unsigned long *src_pfns, unsigned long start, + unsigned long npages); +void migrate_device_pages(unsigned long *src_pfns, unsigned long *dst_pfns, + unsigned long npages); +void migrate_device_finalize(unsigned long *src_pfns, + unsigned long *dst_pfns, unsigned long npages); + #endif /* CONFIG_MIGRATION */ #endif /* _LINUX_MIGRATE_H */ diff --git a/include/linux/psi.h b/include/linux/psi.h index dd74411ac21d..b029a847def1 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -7,6 +7,7 @@ #include #include #include +#include struct seq_file; struct css_set; @@ -18,10 +19,6 @@ extern struct psi_group psi_system; void psi_init(void); -void psi_task_change(struct task_struct *task, int clear, int set); -void psi_task_switch(struct task_struct *prev, struct task_struct *next, - bool sleep); - void psi_memstall_enter(unsigned long *flags); void psi_memstall_leave(unsigned long *flags); @@ -34,9 +31,15 @@ __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, poll_table *wait); #ifdef CONFIG_CGROUPS +static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) +{ + return cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi; +} + int psi_cgroup_alloc(struct cgroup *cgrp); void psi_cgroup_free(struct cgroup *cgrp); void cgroup_move_task(struct task_struct *p, struct css_set *to); +void psi_cgroup_restart(struct psi_group *group); #endif #else /* CONFIG_PSI */ @@ -58,6 +61,7 @@ static inline void cgroup_move_task(struct task_struct *p, struct css_set *to) { rcu_assign_pointer(p->cgroups, to); } +static inline void psi_cgroup_restart(struct psi_group *group) {} #endif #endif /* CONFIG_PSI */ diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index c7fe7c089718..6e4372735068 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -15,13 +15,6 @@ enum psi_task_count { NR_IOWAIT, NR_MEMSTALL, NR_RUNNING, - /* - * This can't have values other than 0 or 1 and could be - * implemented as a bit flag. But for now we still have room - * in the first cacheline of psi_group_cpu, and this way we - * don't have to special case any state tracking for it. - */ - NR_ONCPU, /* * For IO and CPU stalls the presence of running/oncpu tasks * in the domain means a partial rather than a full stall. @@ -32,22 +25,27 @@ enum psi_task_count { * threads and memstall ones. */ NR_MEMSTALL_RUNNING, - NR_PSI_TASK_COUNTS = 5, + NR_PSI_TASK_COUNTS = 4, }; /* Task state bitmasks */ #define TSK_IOWAIT (1 << NR_IOWAIT) #define TSK_MEMSTALL (1 << NR_MEMSTALL) #define TSK_RUNNING (1 << NR_RUNNING) -#define TSK_ONCPU (1 << NR_ONCPU) #define TSK_MEMSTALL_RUNNING (1 << NR_MEMSTALL_RUNNING) +/* Only one task can be scheduled, no corresponding task count */ +#define TSK_ONCPU (1 << NR_PSI_TASK_COUNTS) + /* Resources that workloads could be stalled on */ enum psi_res { PSI_IO, PSI_MEM, PSI_CPU, - NR_PSI_RESOURCES = 3, +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + PSI_IRQ, +#endif + NR_PSI_RESOURCES, }; /* @@ -63,11 +61,17 @@ enum psi_states { PSI_MEM_FULL, PSI_CPU_SOME, PSI_CPU_FULL, +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + PSI_IRQ_FULL, +#endif /* Only per-CPU, to weigh the CPU in the global average: */ PSI_NONIDLE, - NR_PSI_STATES = 7, + NR_PSI_STATES, }; +/* Use one bit in the state mask to track TSK_ONCPU */ +#define PSI_ONCPU (1 << NR_PSI_STATES) + enum psi_aggregators { PSI_AVGS = 0, PSI_POLL, @@ -147,6 +151,9 @@ struct psi_trigger { }; struct psi_group { + struct psi_group *parent; + bool enabled; + /* Protects data used by the aggregator */ struct mutex avgs_lock; @@ -188,6 +195,8 @@ struct psi_group { #else /* CONFIG_PSI */ +#define NR_PSI_RESOURCES 0 + struct psi_group { }; #endif /* CONFIG_PSI */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 1577b06b7df5..54a7ce50cbe7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -873,8 +873,6 @@ struct task_struct { struct mm_struct *mm; struct mm_struct *active_mm; - /* Per-thread vma caching: */ - #ifdef SPLIT_RSS_COUNTING struct task_rss_stat rss_stat; #endif diff --git a/include/soc/sifive/sifive_ccache.h b/include/soc/sifive/sifive_ccache.h new file mode 100644 index 000000000000..4d4ed49388a0 --- /dev/null +++ b/include/soc/sifive/sifive_ccache.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * SiFive Composable Cache Controller header file + * + */ + +#ifndef __SOC_SIFIVE_CCACHE_H +#define __SOC_SIFIVE_CCACHE_H + +extern int register_sifive_ccache_error_notifier(struct notifier_block *nb); +extern int unregister_sifive_ccache_error_notifier(struct notifier_block *nb); + +#define SIFIVE_CCACHE_ERR_TYPE_CE 0 +#define SIFIVE_CCACHE_ERR_TYPE_UE 1 + +#endif /* __SOC_SIFIVE_CCACHE_H */ diff --git a/include/soc/sifive/sifive_l2_cache.h b/include/soc/sifive/sifive_l2_cache.h deleted file mode 100644 index 92ade10ed67e..000000000000 --- a/include/soc/sifive/sifive_l2_cache.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * SiFive L2 Cache Controller header file - * - */ - -#ifndef __SOC_SIFIVE_L2_CACHE_H -#define __SOC_SIFIVE_L2_CACHE_H - -extern int register_sifive_l2_error_notifier(struct notifier_block *nb); -extern int unregister_sifive_l2_error_notifier(struct notifier_block *nb); - -#define SIFIVE_L2_ERR_TYPE_CE 0 -#define SIFIVE_L2_ERR_TYPE_UE 1 - -#endif /* __SOC_SIFIVE_L2_CACHE_H */ diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h index ddff03e546e9..35778f953a3f 100644 --- a/include/sound/hdaudio.h +++ b/include/sound/hdaudio.h @@ -592,11 +592,11 @@ int snd_hdac_get_stream_stripe_ctl(struct hdac_bus *bus, #define snd_hdac_stream_readb(dev, reg) \ snd_hdac_reg_readb((dev)->bus, (dev)->sd_addr + AZX_REG_ ## reg) #define snd_hdac_stream_readb_poll(dev, reg, val, cond, delay_us, timeout_us) \ - readb_poll_timeout((dev)->sd_addr + AZX_REG_ ## reg, val, cond, \ - delay_us, timeout_us) + read_poll_timeout_atomic(snd_hdac_reg_readb, val, cond, delay_us, timeout_us, \ + false, (dev)->bus, (dev)->sd_addr + AZX_REG_ ## reg) #define snd_hdac_stream_readl_poll(dev, reg, val, cond, delay_us, timeout_us) \ - readl_poll_timeout((dev)->sd_addr + AZX_REG_ ## reg, val, cond, \ - delay_us, timeout_us) + read_poll_timeout_atomic(snd_hdac_reg_readl, val, cond, delay_us, timeout_us, \ + false, (dev)->bus, (dev)->sd_addr + AZX_REG_ ## reg) /* update a register, pass without AZX_REG_ prefix */ #define snd_hdac_stream_updatel(dev, reg, mask, val) \ diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 27f107b3c9c4..1840f5894761 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3704,27 +3704,27 @@ static int cpu_stat_show(struct seq_file *seq, void *v) static int cgroup_io_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; - struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi; + struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_IO); } static int cgroup_memory_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; - struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi; + struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_MEM); } static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; - struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi; + struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_CPU); } -static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, - size_t nbytes, enum psi_res res) +static ssize_t pressure_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, enum psi_res res) { struct cgroup_file_ctx *ctx = of->priv; struct psi_trigger *new; @@ -3744,7 +3744,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, return -EBUSY; } - psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi; + psi = cgroup_psi(cgrp); new = psi_trigger_create(psi, buf, res); if (IS_ERR(new)) { cgroup_put(cgrp); @@ -3761,21 +3761,86 @@ static ssize_t cgroup_io_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { - return cgroup_pressure_write(of, buf, nbytes, PSI_IO); + return pressure_write(of, buf, nbytes, PSI_IO); } static ssize_t cgroup_memory_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { - return cgroup_pressure_write(of, buf, nbytes, PSI_MEM); + return pressure_write(of, buf, nbytes, PSI_MEM); } static ssize_t cgroup_cpu_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { - return cgroup_pressure_write(of, buf, nbytes, PSI_CPU); + return pressure_write(of, buf, nbytes, PSI_CPU); +} + +#ifdef CONFIG_IRQ_TIME_ACCOUNTING +static int cgroup_irq_pressure_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + struct psi_group *psi = cgroup_psi(cgrp); + + return psi_show(seq, psi, PSI_IRQ); +} + +static ssize_t cgroup_irq_pressure_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) +{ + return pressure_write(of, buf, nbytes, PSI_IRQ); +} +#endif + +static int cgroup_pressure_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + struct psi_group *psi = cgroup_psi(cgrp); + + seq_printf(seq, "%d\n", psi->enabled); + + return 0; +} + +static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) +{ + ssize_t ret; + int enable; + struct cgroup *cgrp; + struct psi_group *psi; + + ret = kstrtoint(strstrip(buf), 0, &enable); + if (ret) + return ret; + + if (enable < 0 || enable > 1) + return -ERANGE; + + cgrp = cgroup_kn_lock_live(of->kn, false); + if (!cgrp) + return -ENOENT; + + psi = cgroup_psi(cgrp); + if (psi->enabled != enable) { + int i; + + /* show or hide {cpu,memory,io,irq}.pressure files */ + for (i = 0; i < NR_PSI_RESOURCES; i++) + cgroup_file_show(&cgrp->psi_files[i], enable); + + psi->enabled = enable; + if (enable) + psi_cgroup_restart(psi); + } + + cgroup_kn_unlock(of->kn); + + return nbytes; } static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of, @@ -3795,6 +3860,9 @@ static void cgroup_pressure_release(struct kernfs_open_file *of) bool cgroup_psi_enabled(void) { + if (static_branch_likely(&psi_disabled)) + return false; + return (cgroup_feature_disable_mask & (1 << OPT_FEATURE_PRESSURE)) == 0; } @@ -5182,6 +5250,7 @@ static struct cftype cgroup_psi_files[] = { #ifdef CONFIG_PSI { .name = "io.pressure", + .file_offset = offsetof(struct cgroup, psi_files[PSI_IO]), .seq_show = cgroup_io_pressure_show, .write = cgroup_io_pressure_write, .poll = cgroup_pressure_poll, @@ -5189,6 +5258,7 @@ static struct cftype cgroup_psi_files[] = { }, { .name = "memory.pressure", + .file_offset = offsetof(struct cgroup, psi_files[PSI_MEM]), .seq_show = cgroup_memory_pressure_show, .write = cgroup_memory_pressure_write, .poll = cgroup_pressure_poll, @@ -5196,11 +5266,27 @@ static struct cftype cgroup_psi_files[] = { }, { .name = "cpu.pressure", + .file_offset = offsetof(struct cgroup, psi_files[PSI_CPU]), .seq_show = cgroup_cpu_pressure_show, .write = cgroup_cpu_pressure_write, .poll = cgroup_pressure_poll, .release = cgroup_pressure_release, }, +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + { + .name = "irq.pressure", + .file_offset = offsetof(struct cgroup, psi_files[PSI_IRQ]), + .seq_show = cgroup_irq_pressure_show, + .write = cgroup_irq_pressure_write, + .poll = cgroup_pressure_poll, + .release = cgroup_pressure_release, + }, +#endif + { + .name = "cgroup.pressure", + .seq_show = cgroup_pressure_show, + .write = cgroup_pressure_write, + }, #endif /* CONFIG_PSI */ { } /* terminate */ }; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 16de2fd98427..70c5ed8e5c2d 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -712,6 +712,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) rq->prev_irq_time += irq_delta; delta -= irq_delta; + psi_account_irqtime(rq->curr, irq_delta); #endif #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING if (static_key_false((¶virt_steal_rq_enabled))) { diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 7f6030091aee..ee2ecc081422 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -181,6 +181,7 @@ static void group_init(struct psi_group *group) { int cpu; + group->enabled = true; for_each_possible_cpu(cpu) seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq); group->avg_last_update = sched_clock(); @@ -201,6 +202,7 @@ void __init psi_init(void) { if (!psi_enable) { static_branch_enable(&psi_disabled); + static_branch_disable(&psi_cgroups_enabled); return; } @@ -211,7 +213,7 @@ void __init psi_init(void) group_init(&psi_system); } -static bool test_state(unsigned int *tasks, enum psi_states state) +static bool test_state(unsigned int *tasks, enum psi_states state, bool oncpu) { switch (state) { case PSI_IO_SOME: @@ -224,9 +226,9 @@ static bool test_state(unsigned int *tasks, enum psi_states state) return unlikely(tasks[NR_MEMSTALL] && tasks[NR_RUNNING] == tasks[NR_MEMSTALL_RUNNING]); case PSI_CPU_SOME: - return unlikely(tasks[NR_RUNNING] > tasks[NR_ONCPU]); + return unlikely(tasks[NR_RUNNING] > oncpu); case PSI_CPU_FULL: - return unlikely(tasks[NR_RUNNING] && !tasks[NR_ONCPU]); + return unlikely(tasks[NR_RUNNING] && !oncpu); case PSI_NONIDLE: return tasks[NR_IOWAIT] || tasks[NR_MEMSTALL] || tasks[NR_RUNNING]; @@ -688,35 +690,53 @@ static void psi_group_change(struct psi_group *group, int cpu, bool wake_clock) { struct psi_group_cpu *groupc; - u32 state_mask = 0; unsigned int t, m; enum psi_states s; + u32 state_mask; groupc = per_cpu_ptr(group->pcpu, cpu); /* - * First we assess the aggregate resource states this CPU's - * tasks have been in since the last change, and account any - * SOME and FULL time these may have resulted in. - * - * Then we update the task counts according to the state + * First we update the task counts according to the state * change requested through the @clear and @set bits. + * + * Then if the cgroup PSI stats accounting enabled, we + * assess the aggregate resource states this CPU's tasks + * have been in since the last change, and account any + * SOME and FULL time these may have resulted in. */ write_seqcount_begin(&groupc->seq); - record_times(groupc, now); + /* + * Start with TSK_ONCPU, which doesn't have a corresponding + * task count - it's just a boolean flag directly encoded in + * the state mask. Clear, set, or carry the current state if + * no changes are requested. + */ + if (unlikely(clear & TSK_ONCPU)) { + state_mask = 0; + clear &= ~TSK_ONCPU; + } else if (unlikely(set & TSK_ONCPU)) { + state_mask = PSI_ONCPU; + set &= ~TSK_ONCPU; + } else { + state_mask = groupc->state_mask & PSI_ONCPU; + } + /* + * The rest of the state mask is calculated based on the task + * counts. Update those first, then construct the mask. + */ for (t = 0, m = clear; m; m &= ~(1 << t), t++) { if (!(m & (1 << t))) continue; if (groupc->tasks[t]) { groupc->tasks[t]--; } else if (!psi_bug) { - printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u %u %u] clear=%x set=%x\n", + printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u %u] clear=%x set=%x\n", cpu, t, groupc->tasks[0], groupc->tasks[1], groupc->tasks[2], - groupc->tasks[3], groupc->tasks[4], - clear, set); + groupc->tasks[3], clear, set); psi_bug = 1; } } @@ -725,9 +745,25 @@ static void psi_group_change(struct psi_group *group, int cpu, if (set & (1 << t)) groupc->tasks[t]++; - /* Calculate state mask representing active states */ + if (!group->enabled) { + /* + * On the first group change after disabling PSI, conclude + * the current state and flush its time. This is unlikely + * to matter to the user, but aggregation (get_recent_times) + * may have already incorporated the live state into times_prev; + * avoid a delta sample underflow when PSI is later re-enabled. + */ + if (unlikely(groupc->state_mask & (1 << PSI_NONIDLE))) + record_times(groupc, now); + + groupc->state_mask = state_mask; + + write_seqcount_end(&groupc->seq); + return; + } + for (s = 0; s < NR_PSI_STATES; s++) { - if (test_state(groupc->tasks, s)) + if (test_state(groupc->tasks, s, state_mask & PSI_ONCPU)) state_mask |= (1 << s); } @@ -739,9 +775,11 @@ static void psi_group_change(struct psi_group *group, int cpu, * task in a cgroup is in_memstall, the corresponding groupc * on that cpu is in PSI_MEM_FULL state. */ - if (unlikely(groupc->tasks[NR_ONCPU] && cpu_curr(cpu)->in_memstall)) + if (unlikely((state_mask & PSI_ONCPU) && cpu_curr(cpu)->in_memstall)) state_mask |= (1 << PSI_MEM_FULL); + record_times(groupc, now); + groupc->state_mask = state_mask; write_seqcount_end(&groupc->seq); @@ -753,27 +791,12 @@ static void psi_group_change(struct psi_group *group, int cpu, schedule_delayed_work(&group->avgs_work, PSI_FREQ); } -static struct psi_group *iterate_groups(struct task_struct *task, void **iter) +static inline struct psi_group *task_psi_group(struct task_struct *task) { - if (*iter == &psi_system) - return NULL; - #ifdef CONFIG_CGROUPS - if (static_branch_likely(&psi_cgroups_enabled)) { - struct cgroup *cgroup = NULL; - - if (!*iter) - cgroup = task->cgroups->dfl_cgrp; - else - cgroup = cgroup_parent(*iter); - - if (cgroup && cgroup_parent(cgroup)) { - *iter = cgroup; - return cgroup_psi(cgroup); - } - } + if (static_branch_likely(&psi_cgroups_enabled)) + return cgroup_psi(task_dfl_cgroup(task)); #endif - *iter = &psi_system; return &psi_system; } @@ -796,8 +819,6 @@ void psi_task_change(struct task_struct *task, int clear, int set) { int cpu = task_cpu(task); struct psi_group *group; - bool wake_clock = true; - void *iter = NULL; u64 now; if (!task->pid) @@ -806,19 +827,11 @@ void psi_task_change(struct task_struct *task, int clear, int set) psi_flags_change(task, clear, set); now = cpu_clock(cpu); - /* - * Periodic aggregation shuts off if there is a period of no - * task changes, so we wake it back up if necessary. However, - * don't do this if the task change is the aggregation worker - * itself going to sleep, or we'll ping-pong forever. - */ - if (unlikely((clear & TSK_RUNNING) && - (task->flags & PF_WQ_WORKER) && - wq_worker_last_func(task) == psi_avgs_work)) - wake_clock = false; - while ((group = iterate_groups(task, &iter))) - psi_group_change(group, cpu, clear, set, now, wake_clock); + group = task_psi_group(task); + do { + psi_group_change(group, cpu, clear, set, now, true); + } while ((group = group->parent)); } void psi_task_switch(struct task_struct *prev, struct task_struct *next, @@ -826,34 +839,30 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, { struct psi_group *group, *common = NULL; int cpu = task_cpu(prev); - void *iter; u64 now = cpu_clock(cpu); if (next->pid) { - bool identical_state; - psi_flags_change(next, 0, TSK_ONCPU); /* - * When switching between tasks that have an identical - * runtime state, the cgroup that contains both tasks - * we reach the first common ancestor. Iterate @next's - * ancestors only until we encounter @prev's ONCPU. + * Set TSK_ONCPU on @next's cgroups. If @next shares any + * ancestors with @prev, those will already have @prev's + * TSK_ONCPU bit set, and we can stop the iteration there. */ - identical_state = prev->psi_flags == next->psi_flags; - iter = NULL; - while ((group = iterate_groups(next, &iter))) { - if (identical_state && - per_cpu_ptr(group->pcpu, cpu)->tasks[NR_ONCPU]) { + group = task_psi_group(next); + do { + if (per_cpu_ptr(group->pcpu, cpu)->state_mask & + PSI_ONCPU) { common = group; break; } psi_group_change(group, cpu, 0, TSK_ONCPU, now, true); - } + } while ((group = group->parent)); } if (prev->pid) { int clear = TSK_ONCPU, set = 0; + bool wake_clock = true; /* * When we're going to sleep, psi_dequeue() lets us @@ -867,26 +876,74 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, clear |= TSK_MEMSTALL_RUNNING; if (prev->in_iowait) set |= TSK_IOWAIT; + + /* + * Periodic aggregation shuts off if there is a period of no + * task changes, so we wake it back up if necessary. However, + * don't do this if the task change is the aggregation worker + * itself going to sleep, or we'll ping-pong forever. + */ + if (unlikely((prev->flags & PF_WQ_WORKER) && + wq_worker_last_func(prev) == psi_avgs_work)) + wake_clock = false; } psi_flags_change(prev, clear, set); - iter = NULL; - while ((group = iterate_groups(prev, &iter)) && group != common) - psi_group_change(group, cpu, clear, set, now, true); + group = task_psi_group(prev); + do { + if (group == common) + break; + psi_group_change(group, cpu, clear, set, now, wake_clock); + } while ((group = group->parent)); /* - * TSK_ONCPU is handled up to the common ancestor. If we're tasked - * with dequeuing too, finish that for the rest of the hierarchy. + * TSK_ONCPU is handled up to the common ancestor. If there are + * any other differences between the two tasks (e.g. prev goes + * to sleep, or only one task is memstall), finish propagating + * those differences all the way up to the root. */ - if (sleep) { + if ((prev->psi_flags ^ next->psi_flags) & ~TSK_ONCPU) { clear &= ~TSK_ONCPU; - for (; group; group = iterate_groups(prev, &iter)) - psi_group_change(group, cpu, clear, set, now, true); + for (; group; group = group->parent) + psi_group_change(group, cpu, clear, set, now, wake_clock); } } } +#ifdef CONFIG_IRQ_TIME_ACCOUNTING +void psi_account_irqtime(struct task_struct *task, u32 delta) +{ + int cpu = task_cpu(task); + struct psi_group *group; + struct psi_group_cpu *groupc; + u64 now; + + if (!task->pid) + return; + + now = cpu_clock(cpu); + + group = task_psi_group(task); + do { + if (!group->enabled) + continue; + + groupc = per_cpu_ptr(group->pcpu, cpu); + + write_seqcount_begin(&groupc->seq); + + record_times(groupc, now); + groupc->times[PSI_IRQ_FULL] += delta; + + write_seqcount_end(&groupc->seq); + + if (group->poll_states & (1 << PSI_IRQ_FULL)) + psi_schedule_poll_work(group, 1); + } while ((group = group->parent)); +} +#endif + /** * psi_memstall_enter - mark the beginning of a memory stall section * @flags: flags to handle nested sections @@ -952,7 +1009,7 @@ EXPORT_SYMBOL_GPL(psi_memstall_leave); #ifdef CONFIG_CGROUPS int psi_cgroup_alloc(struct cgroup *cgroup) { - if (static_branch_likely(&psi_disabled)) + if (!static_branch_likely(&psi_cgroups_enabled)) return 0; cgroup->psi = kzalloc(sizeof(struct psi_group), GFP_KERNEL); @@ -965,12 +1022,13 @@ int psi_cgroup_alloc(struct cgroup *cgroup) return -ENOMEM; } group_init(cgroup->psi); + cgroup->psi->parent = cgroup_psi(cgroup_parent(cgroup)); return 0; } void psi_cgroup_free(struct cgroup *cgroup) { - if (static_branch_likely(&psi_disabled)) + if (!static_branch_likely(&psi_cgroups_enabled)) return; cancel_delayed_work_sync(&cgroup->psi->avgs_work); @@ -998,7 +1056,7 @@ void cgroup_move_task(struct task_struct *task, struct css_set *to) struct rq_flags rf; struct rq *rq; - if (static_branch_likely(&psi_disabled)) { + if (!static_branch_likely(&psi_cgroups_enabled)) { /* * Lame to do this here, but the scheduler cannot be locked * from the outside, so we move cgroups from inside sched/. @@ -1046,10 +1104,45 @@ void cgroup_move_task(struct task_struct *task, struct css_set *to) task_rq_unlock(rq, task, &rf); } + +void psi_cgroup_restart(struct psi_group *group) +{ + int cpu; + + /* + * After we disable psi_group->enabled, we don't actually + * stop percpu tasks accounting in each psi_group_cpu, + * instead only stop test_state() loop, record_times() + * and averaging worker, see psi_group_change() for details. + * + * When disable cgroup PSI, this function has nothing to sync + * since cgroup pressure files are hidden and percpu psi_group_cpu + * would see !psi_group->enabled and only do task accounting. + * + * When re-enable cgroup PSI, this function use psi_group_change() + * to get correct state mask from test_state() loop on tasks[], + * and restart groupc->state_start from now, use .clear = .set = 0 + * here since no task status really changed. + */ + if (!group->enabled) + return; + + for_each_possible_cpu(cpu) { + struct rq *rq = cpu_rq(cpu); + struct rq_flags rf; + u64 now; + + rq_lock_irq(rq, &rf); + now = cpu_clock(cpu); + psi_group_change(group, cpu, 0, 0, now, true); + rq_unlock_irq(rq, &rf); + } +} #endif /* CONFIG_CGROUPS */ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) { + bool only_full = false; int full; u64 now; @@ -1064,7 +1157,11 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) group->avg_next_update = update_averages(group, now); mutex_unlock(&group->avgs_lock); - for (full = 0; full < 2; full++) { +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + only_full = res == PSI_IRQ; +#endif + + for (full = 0; full < 2 - only_full; full++) { unsigned long avg[3] = { 0, }; u64 total = 0; int w; @@ -1078,7 +1175,7 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) } seq_printf(m, "%s avg10=%lu.%02lu avg60=%lu.%02lu avg300=%lu.%02lu total=%llu\n", - full ? "full" : "some", + full || only_full ? "full" : "some", LOAD_INT(avg[0]), LOAD_FRAC(avg[0]), LOAD_INT(avg[1]), LOAD_FRAC(avg[1]), LOAD_INT(avg[2]), LOAD_FRAC(avg[2]), @@ -1106,6 +1203,11 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, else return ERR_PTR(-EINVAL); +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + if (res == PSI_IRQ && --state != PSI_IRQ_FULL) + return ERR_PTR(-EINVAL); +#endif + if (state >= PSI_NONIDLE) return ERR_PTR(-EINVAL); @@ -1390,6 +1492,33 @@ static const struct proc_ops psi_cpu_proc_ops = { .proc_release = psi_fop_release, }; +#ifdef CONFIG_IRQ_TIME_ACCOUNTING +static int psi_irq_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_IRQ); +} + +static int psi_irq_open(struct inode *inode, struct file *file) +{ + return psi_open(file, psi_irq_show); +} + +static ssize_t psi_irq_write(struct file *file, const char __user *user_buf, + size_t nbytes, loff_t *ppos) +{ + return psi_write(file, user_buf, nbytes, PSI_IRQ); +} + +static const struct proc_ops psi_irq_proc_ops = { + .proc_open = psi_irq_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_write = psi_irq_write, + .proc_poll = psi_fop_poll, + .proc_release = psi_fop_release, +}; +#endif + static int __init psi_proc_init(void) { if (psi_enable) { @@ -1397,6 +1526,9 @@ static int __init psi_proc_init(void) proc_create("pressure/io", 0666, NULL, &psi_io_proc_ops); proc_create("pressure/memory", 0666, NULL, &psi_memory_proc_ops); proc_create("pressure/cpu", 0666, NULL, &psi_cpu_proc_ops); +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + proc_create("pressure/irq", 0666, NULL, &psi_irq_proc_ops); +#endif } return 0; } diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index baa839c1ba96..84a188913cc9 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -107,6 +107,11 @@ __schedstats_from_se(struct sched_entity *se) } #ifdef CONFIG_PSI +void psi_task_change(struct task_struct *task, int clear, int set); +void psi_task_switch(struct task_struct *prev, struct task_struct *next, + bool sleep); +void psi_account_irqtime(struct task_struct *task, u32 delta); + /* * PSI tracks state that persists across sleeps, such as iowaits and * memory stalls. As a result, it has to distinguish between sleeps, @@ -201,6 +206,7 @@ static inline void psi_ttwu_dequeue(struct task_struct *p) {} static inline void psi_sched_switch(struct task_struct *prev, struct task_struct *next, bool sleep) {} +static inline void psi_account_irqtime(struct task_struct *task, u32 delta) {} #endif /* CONFIG_PSI */ #ifdef CONFIG_SCHED_INFO diff --git a/lib/Kconfig.kgdb b/lib/Kconfig.kgdb index 05dae05b6cc9..3b9a44008433 100644 --- a/lib/Kconfig.kgdb +++ b/lib/Kconfig.kgdb @@ -121,7 +121,7 @@ config KDB_DEFAULT_ENABLE config KDB_KEYBOARD bool "KGDB_KDB: keyboard as input device" - depends on VT && KGDB_KDB + depends on VT && KGDB_KDB && !PARISC default n help KDB can use a PS/2 type keyboard for an input device diff --git a/lib/test_hmm.c b/lib/test_hmm.c index 6a33f6b1b465..67e6f83fe0f8 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @@ -100,6 +100,7 @@ struct dmirror { struct dmirror_chunk { struct dev_pagemap pagemap; struct dmirror_device *mdevice; + bool remove; }; /* @@ -192,11 +193,15 @@ static int dmirror_fops_release(struct inode *inode, struct file *filp) return 0; } +static struct dmirror_chunk *dmirror_page_to_chunk(struct page *page) +{ + return container_of(page->pgmap, struct dmirror_chunk, pagemap); +} + static struct dmirror_device *dmirror_page_to_device(struct page *page) { - return container_of(page->pgmap, struct dmirror_chunk, - pagemap)->mdevice; + return dmirror_page_to_chunk(page)->mdevice; } static int dmirror_do_fault(struct dmirror *dmirror, struct hmm_range *range) @@ -627,8 +632,8 @@ static struct page *dmirror_devmem_alloc_page(struct dmirror_device *mdevice) goto error; } + zone_device_page_init(dpage); dpage->zone_device_data = rpage; - lock_page(dpage); return dpage; error: @@ -907,7 +912,7 @@ static int dmirror_migrate_to_system(struct dmirror *dmirror, struct vm_area_struct *vma; unsigned long src_pfns[64] = { 0 }; unsigned long dst_pfns[64] = { 0 }; - struct migrate_vma args; + struct migrate_vma args = { 0 }; unsigned long next; int ret; @@ -968,7 +973,7 @@ static int dmirror_migrate_to_device(struct dmirror *dmirror, unsigned long src_pfns[64] = { 0 }; unsigned long dst_pfns[64] = { 0 }; struct dmirror_bounce bounce; - struct migrate_vma args; + struct migrate_vma args = { 0 }; unsigned long next; int ret; @@ -1218,6 +1223,85 @@ static int dmirror_snapshot(struct dmirror *dmirror, return ret; } +static void dmirror_device_evict_chunk(struct dmirror_chunk *chunk) +{ + unsigned long start_pfn = chunk->pagemap.range.start >> PAGE_SHIFT; + unsigned long end_pfn = chunk->pagemap.range.end >> PAGE_SHIFT; + unsigned long npages = end_pfn - start_pfn + 1; + unsigned long i; + unsigned long *src_pfns; + unsigned long *dst_pfns; + + src_pfns = kcalloc(npages, sizeof(*src_pfns), GFP_KERNEL); + dst_pfns = kcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL); + + migrate_device_range(src_pfns, start_pfn, npages); + for (i = 0; i < npages; i++) { + struct page *dpage, *spage; + + spage = migrate_pfn_to_page(src_pfns[i]); + if (!spage || !(src_pfns[i] & MIGRATE_PFN_MIGRATE)) + continue; + + if (WARN_ON(!is_device_private_page(spage) && + !is_device_coherent_page(spage))) + continue; + spage = BACKING_PAGE(spage); + dpage = alloc_page(GFP_HIGHUSER_MOVABLE | __GFP_NOFAIL); + lock_page(dpage); + copy_highpage(dpage, spage); + dst_pfns[i] = migrate_pfn(page_to_pfn(dpage)); + if (src_pfns[i] & MIGRATE_PFN_WRITE) + dst_pfns[i] |= MIGRATE_PFN_WRITE; + } + migrate_device_pages(src_pfns, dst_pfns, npages); + migrate_device_finalize(src_pfns, dst_pfns, npages); + kfree(src_pfns); + kfree(dst_pfns); +} + +/* Removes free pages from the free list so they can't be re-allocated */ +static void dmirror_remove_free_pages(struct dmirror_chunk *devmem) +{ + struct dmirror_device *mdevice = devmem->mdevice; + struct page *page; + + for (page = mdevice->free_pages; page; page = page->zone_device_data) + if (dmirror_page_to_chunk(page) == devmem) + mdevice->free_pages = page->zone_device_data; +} + +static void dmirror_device_remove_chunks(struct dmirror_device *mdevice) +{ + unsigned int i; + + mutex_lock(&mdevice->devmem_lock); + if (mdevice->devmem_chunks) { + for (i = 0; i < mdevice->devmem_count; i++) { + struct dmirror_chunk *devmem = + mdevice->devmem_chunks[i]; + + spin_lock(&mdevice->lock); + devmem->remove = true; + dmirror_remove_free_pages(devmem); + spin_unlock(&mdevice->lock); + + dmirror_device_evict_chunk(devmem); + memunmap_pages(&devmem->pagemap); + if (devmem->pagemap.type == MEMORY_DEVICE_PRIVATE) + release_mem_region(devmem->pagemap.range.start, + range_len(&devmem->pagemap.range)); + kfree(devmem); + } + mdevice->devmem_count = 0; + mdevice->devmem_capacity = 0; + mdevice->free_pages = NULL; + kfree(mdevice->devmem_chunks); + mdevice->devmem_chunks = NULL; + } + mutex_unlock(&mdevice->devmem_lock); +} + static long dmirror_fops_unlocked_ioctl(struct file *filp, unsigned int command, unsigned long arg) @@ -1272,6 +1356,11 @@ static long dmirror_fops_unlocked_ioctl(struct file *filp, ret = dmirror_snapshot(dmirror, &cmd); break; + case HMM_DMIRROR_RELEASE: + dmirror_device_remove_chunks(dmirror->mdevice); + ret = 0; + break; + default: return -EINVAL; } @@ -1326,15 +1415,19 @@ static void dmirror_devmem_free(struct page *page) mdevice = dmirror_page_to_device(page); spin_lock(&mdevice->lock); - mdevice->cfree++; - page->zone_device_data = mdevice->free_pages; - mdevice->free_pages = page; + + /* Return page to our allocator if not freeing the chunk */ + if (!dmirror_page_to_chunk(page)->remove) { + mdevice->cfree++; + page->zone_device_data = mdevice->free_pages; + mdevice->free_pages = page; + } spin_unlock(&mdevice->lock); } static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf) { - struct migrate_vma args; + struct migrate_vma args = { 0 }; unsigned long src_pfns = 0; unsigned long dst_pfns = 0; struct page *rpage; @@ -1357,6 +1450,7 @@ static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf) args.dst = &dst_pfns; args.pgmap_owner = dmirror->mdevice; args.flags = dmirror_select_device(dmirror); + args.fault_page = vmf->page; if (migrate_vma_setup(&args)) return VM_FAULT_SIGBUS; @@ -1407,22 +1501,7 @@ static int dmirror_device_init(struct dmirror_device *mdevice, int id) static void dmirror_device_remove(struct dmirror_device *mdevice) { - unsigned int i; - - if (mdevice->devmem_chunks) { - for (i = 0; i < mdevice->devmem_count; i++) { - struct dmirror_chunk *devmem = - mdevice->devmem_chunks[i]; - - memunmap_pages(&devmem->pagemap); - if (devmem->pagemap.type == MEMORY_DEVICE_PRIVATE) - release_mem_region(devmem->pagemap.range.start, - range_len(&devmem->pagemap.range)); - kfree(devmem); - } - kfree(mdevice->devmem_chunks); - } - + dmirror_device_remove_chunks(mdevice); cdev_device_del(&mdevice->cdevice, &mdevice->device); } diff --git a/lib/test_hmm_uapi.h b/lib/test_hmm_uapi.h index e31d58c9034a..8c818a2cf4f6 100644 --- a/lib/test_hmm_uapi.h +++ b/lib/test_hmm_uapi.h @@ -36,6 +36,7 @@ struct hmm_dmirror_cmd { #define HMM_DMIRROR_SNAPSHOT _IOWR('H', 0x04, struct hmm_dmirror_cmd) #define HMM_DMIRROR_EXCLUSIVE _IOWR('H', 0x05, struct hmm_dmirror_cmd) #define HMM_DMIRROR_CHECK_EXCLUSIVE _IOWR('H', 0x06, struct hmm_dmirror_cmd) +#define HMM_DMIRROR_RELEASE _IOWR('H', 0x07, struct hmm_dmirror_cmd) /* * Values returned in hmm_dmirror_cmd.ptr for HMM_DMIRROR_SNAPSHOT. diff --git a/lib/test_meminit.c b/lib/test_meminit.c index c95db11a6906..60e1984c060f 100644 --- a/lib/test_meminit.c +++ b/lib/test_meminit.c @@ -67,17 +67,24 @@ static int __init do_alloc_pages_order(int order, int *total_failures) size_t size = PAGE_SIZE << order; page = alloc_pages(GFP_KERNEL, order); + if (!page) + goto err; buf = page_address(page); fill_with_garbage(buf, size); __free_pages(page, order); page = alloc_pages(GFP_KERNEL, order); + if (!page) + goto err; buf = page_address(page); if (count_nonzero_bytes(buf, size)) (*total_failures)++; fill_with_garbage(buf, size); __free_pages(page, order); return 1; +err: + (*total_failures)++; + return 1; } /* Test the page allocator by calling alloc_pages with different orders. */ @@ -100,15 +107,22 @@ static int __init do_kmalloc_size(size_t size, int *total_failures) void *buf; buf = kmalloc(size, GFP_KERNEL); + if (!buf) + goto err; fill_with_garbage(buf, size); kfree(buf); buf = kmalloc(size, GFP_KERNEL); + if (!buf) + goto err; if (count_nonzero_bytes(buf, size)) (*total_failures)++; fill_with_garbage(buf, size); kfree(buf); return 1; +err: + (*total_failures)++; + return 1; } /* Test vmalloc() with given parameters. */ @@ -117,15 +131,22 @@ static int __init do_vmalloc_size(size_t size, int *total_failures) void *buf; buf = vmalloc(size); + if (!buf) + goto err; fill_with_garbage(buf, size); vfree(buf); buf = vmalloc(size); + if (!buf) + goto err; if (count_nonzero_bytes(buf, size)) (*total_failures)++; fill_with_garbage(buf, size); vfree(buf); return 1; +err: + (*total_failures)++; + return 1; } /* Test kmalloc()/vmalloc() by allocating objects of different sizes. */ diff --git a/mm/compaction.c b/mm/compaction.c index 2dd02c4683c4..c51f7f545afe 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1847,7 +1847,6 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc) pfn = cc->zone->zone_start_pfn; cc->fast_search_fail = 0; found_block = true; - set_pageblock_skip(freepage); break; } } diff --git a/mm/damon/core.c b/mm/damon/core.c index 8e1ab38d0f1f..36d098d06c55 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -491,7 +491,7 @@ static unsigned long damon_region_sz_limit(struct damon_ctx *ctx) damon_for_each_target(t, ctx) { damon_for_each_region(r, t) - sz += r->ar.end - r->ar.start; + sz += damon_sz_region(r); } if (ctx->attrs.min_nr_regions) @@ -674,7 +674,7 @@ static bool __damos_valid_target(struct damon_region *r, struct damos *s) { unsigned long sz; - sz = r->ar.end - r->ar.start; + sz = damon_sz_region(r); return s->pattern.min_sz_region <= sz && sz <= s->pattern.max_sz_region && s->pattern.min_nr_accesses <= r->nr_accesses && @@ -702,7 +702,7 @@ static void damon_do_apply_schemes(struct damon_ctx *c, damon_for_each_scheme(s, c) { struct damos_quota *quota = &s->quota; - unsigned long sz = r->ar.end - r->ar.start; + unsigned long sz = damon_sz_region(r); struct timespec64 begin, end; unsigned long sz_applied = 0; @@ -731,14 +731,14 @@ static void damon_do_apply_schemes(struct damon_ctx *c, sz = ALIGN_DOWN(quota->charge_addr_from - r->ar.start, DAMON_MIN_REGION); if (!sz) { - if (r->ar.end - r->ar.start <= - DAMON_MIN_REGION) + if (damon_sz_region(r) <= + DAMON_MIN_REGION) continue; sz = DAMON_MIN_REGION; } damon_split_region_at(t, r, sz); r = damon_next_region(r); - sz = r->ar.end - r->ar.start; + sz = damon_sz_region(r); } quota->charge_target_from = NULL; quota->charge_addr_from = 0; @@ -843,8 +843,7 @@ static void kdamond_apply_schemes(struct damon_ctx *c) continue; score = c->ops.get_scheme_score( c, t, r, s); - quota->histogram[score] += - r->ar.end - r->ar.start; + quota->histogram[score] += damon_sz_region(r); if (score > max_score) max_score = score; } @@ -865,18 +864,13 @@ static void kdamond_apply_schemes(struct damon_ctx *c) } } -static inline unsigned long sz_damon_region(struct damon_region *r) -{ - return r->ar.end - r->ar.start; -} - /* * Merge two adjacent regions into one region */ static void damon_merge_two_regions(struct damon_target *t, struct damon_region *l, struct damon_region *r) { - unsigned long sz_l = sz_damon_region(l), sz_r = sz_damon_region(r); + unsigned long sz_l = damon_sz_region(l), sz_r = damon_sz_region(r); l->nr_accesses = (l->nr_accesses * sz_l + r->nr_accesses * sz_r) / (sz_l + sz_r); @@ -905,7 +899,7 @@ static void damon_merge_regions_of(struct damon_target *t, unsigned int thres, if (prev && prev->ar.end == r->ar.start && abs(prev->nr_accesses - r->nr_accesses) <= thres && - sz_damon_region(prev) + sz_damon_region(r) <= sz_limit) + damon_sz_region(prev) + damon_sz_region(r) <= sz_limit) damon_merge_two_regions(t, prev, r); else prev = r; @@ -963,7 +957,7 @@ static void damon_split_regions_of(struct damon_target *t, int nr_subs) int i; damon_for_each_region_safe(r, next, t) { - sz_region = r->ar.end - r->ar.start; + sz_region = damon_sz_region(r); for (i = 0; i < nr_subs - 1 && sz_region > 2 * DAMON_MIN_REGION; i++) { diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index ea94e0b2c311..15f03df66db6 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -72,7 +72,7 @@ static int damon_va_evenly_split_region(struct damon_target *t, return -EINVAL; orig_end = r->ar.end; - sz_orig = r->ar.end - r->ar.start; + sz_orig = damon_sz_region(r); sz_piece = ALIGN_DOWN(sz_orig / nr_pieces, DAMON_MIN_REGION); if (!sz_piece) @@ -618,7 +618,7 @@ static unsigned long damos_madvise(struct damon_target *target, { struct mm_struct *mm; unsigned long start = PAGE_ALIGN(r->ar.start); - unsigned long len = PAGE_ALIGN(r->ar.end - r->ar.start); + unsigned long len = PAGE_ALIGN(damon_sz_region(r)); unsigned long applied; mm = damon_get_mm(target); diff --git a/mm/highmem.c b/mm/highmem.c index c707d7202d5f..db251e77f98f 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -30,6 +30,17 @@ #include #include +#ifdef CONFIG_KMAP_LOCAL +static inline int kmap_local_calc_idx(int idx) +{ + return idx + KM_MAX_IDX * smp_processor_id(); +} + +#ifndef arch_kmap_local_map_idx +#define arch_kmap_local_map_idx(idx, pfn) kmap_local_calc_idx(idx) +#endif +#endif /* CONFIG_KMAP_LOCAL */ + /* * Virtual_count is not a pure "count". * 0 means that it is not mapped, and has not been mapped @@ -142,12 +153,29 @@ pte_t *pkmap_page_table; struct page *__kmap_to_page(void *vaddr) { + unsigned long base = (unsigned long) vaddr & PAGE_MASK; + struct kmap_ctrl *kctrl = ¤t->kmap_ctrl; unsigned long addr = (unsigned long)vaddr; + int i; - if (addr >= PKMAP_ADDR(0) && addr < PKMAP_ADDR(LAST_PKMAP)) { - int i = PKMAP_NR(addr); + /* kmap() mappings */ + if (WARN_ON_ONCE(addr >= PKMAP_ADDR(0) && + addr < PKMAP_ADDR(LAST_PKMAP))) + return pte_page(pkmap_page_table[PKMAP_NR(addr)]); - return pte_page(pkmap_page_table[i]); + /* kmap_local_page() mappings */ + if (WARN_ON_ONCE(base >= __fix_to_virt(FIX_KMAP_END) && + base < __fix_to_virt(FIX_KMAP_BEGIN))) { + for (i = 0; i < kctrl->idx; i++) { + unsigned long base_addr; + int idx; + + idx = arch_kmap_local_map_idx(i, pte_pfn(pteval)); + base_addr = __fix_to_virt(FIX_KMAP_BEGIN + idx); + + if (base_addr == base) + return pte_page(kctrl->pteval[i]); + } } return virt_to_page(vaddr); @@ -462,10 +490,6 @@ static inline void kmap_local_idx_pop(void) # define arch_kmap_local_post_unmap(vaddr) do { } while (0) #endif -#ifndef arch_kmap_local_map_idx -#define arch_kmap_local_map_idx(idx, pfn) kmap_local_calc_idx(idx) -#endif - #ifndef arch_kmap_local_unmap_idx #define arch_kmap_local_unmap_idx(idx, vaddr) kmap_local_calc_idx(idx) #endif @@ -494,11 +518,6 @@ static inline bool kmap_high_unmap_local(unsigned long vaddr) return false; } -static inline int kmap_local_calc_idx(int idx) -{ - return idx + KM_MAX_IDX * smp_processor_id(); -} - static pte_t *__kmap_pte; static pte_t *kmap_get_pte(unsigned long vaddr, int idx) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 57b7b0b5d9eb..b586cdd75930 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5096,6 +5096,7 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct * unmapped and its refcount is dropped, so just clear pte here. */ if (unlikely(!pte_present(pte))) { +#ifdef CONFIG_PTE_MARKER_UFFD_WP /* * If the pte was wr-protected by uffd-wp in any of the * swap forms, meanwhile the caller does not want to @@ -5107,6 +5108,7 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct set_huge_pte_at(mm, address, ptep, make_pte_marker(PTE_MARKER_UFFD_WP)); else +#endif huge_pte_clear(mm, address, ptep, sz); spin_unlock(ptl); continue; @@ -5135,11 +5137,13 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct tlb_remove_huge_tlb_entry(h, tlb, ptep, address); if (huge_pte_dirty(pte)) set_page_dirty(page); +#ifdef CONFIG_PTE_MARKER_UFFD_WP /* Leave a uffd-wp pte marker if needed */ if (huge_pte_uffd_wp(pte) && !(zap_flags & ZAP_FLAG_DROP_MARKER)) set_huge_pte_at(mm, address, ptep, make_pte_marker(PTE_MARKER_UFFD_WP)); +#endif hugetlb_count_sub(pages_per_huge_page(h), mm); page_remove_rmap(page, vma, true); @@ -5531,6 +5535,23 @@ static inline vm_fault_t hugetlb_handle_userfault(struct vm_area_struct *vma, return handle_userfault(&vmf, reason); } +/* + * Recheck pte with pgtable lock. Returns true if pte didn't change, or + * false if pte changed or is changing. + */ +static bool hugetlb_pte_stable(struct hstate *h, struct mm_struct *mm, + pte_t *ptep, pte_t old_pte) +{ + spinlock_t *ptl; + bool same; + + ptl = huge_pte_lock(h, mm, ptep); + same = pte_same(huge_ptep_get(ptep), old_pte); + spin_unlock(ptl); + + return same; +} + static vm_fault_t hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, struct address_space *mapping, pgoff_t idx, @@ -5571,10 +5592,33 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, if (idx >= size) goto out; /* Check for page in userfault range */ - if (userfaultfd_missing(vma)) - return hugetlb_handle_userfault(vma, mapping, idx, - flags, haddr, address, - VM_UFFD_MISSING); + if (userfaultfd_missing(vma)) { + /* + * Since hugetlb_no_page() was examining pte + * without pgtable lock, we need to re-test under + * lock because the pte may not be stable and could + * have changed from under us. Try to detect + * either changed or during-changing ptes and retry + * properly when needed. + * + * Note that userfaultfd is actually fine with + * false positives (e.g. caused by pte changed), + * but not wrong logical events (e.g. caused by + * reading a pte during changing). The latter can + * confuse the userspace, so the strictness is very + * much preferred. E.g., MISSING event should + * never happen on the page after UFFDIO_COPY has + * correctly installed the page and returned. + */ + if (!hugetlb_pte_stable(h, mm, ptep, old_pte)) { + ret = 0; + goto out; + } + + return hugetlb_handle_userfault(vma, mapping, idx, flags, + haddr, address, + VM_UFFD_MISSING); + } page = alloc_huge_page(vma, haddr, 0); if (IS_ERR(page)) { @@ -5590,11 +5634,10 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, * here. Before returning error, get ptl and make * sure there really is no pte entry. */ - ptl = huge_pte_lock(h, mm, ptep); - ret = 0; - if (huge_pte_none(huge_ptep_get(ptep))) + if (hugetlb_pte_stable(h, mm, ptep, old_pte)) ret = vmf_error(PTR_ERR(page)); - spin_unlock(ptl); + else + ret = 0; goto out; } clear_huge_page(page, address, pages_per_huge_page(h)); @@ -5640,9 +5683,14 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, if (userfaultfd_minor(vma)) { unlock_page(page); put_page(page); - return hugetlb_handle_userfault(vma, mapping, idx, - flags, haddr, address, - VM_UFFD_MINOR); + /* See comment in userfaultfd_missing() block above */ + if (!hugetlb_pte_stable(h, mm, ptep, old_pte)) { + ret = 0; + goto out; + } + return hugetlb_handle_userfault(vma, mapping, idx, flags, + haddr, address, + VM_UFFD_MINOR); } } @@ -6804,7 +6852,7 @@ void hugetlb_vma_lock_release(struct kref *kref) kfree(vma_lock); } -void __hugetlb_vma_unlock_write_put(struct hugetlb_vma_lock *vma_lock) +static void __hugetlb_vma_unlock_write_put(struct hugetlb_vma_lock *vma_lock) { struct vm_area_struct *vma = vma_lock->vma; diff --git a/mm/kasan/kasan_test.c b/mm/kasan/kasan_test.c index f25692def781..57e4c72aa8bd 100644 --- a/mm/kasan/kasan_test.c +++ b/mm/kasan/kasan_test.c @@ -295,6 +295,9 @@ static void krealloc_more_oob_helper(struct kunit *test, ptr2 = krealloc(ptr1, size2, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr2); + /* Suppress -Warray-bounds warnings. */ + OPTIMIZER_HIDE_VAR(ptr2); + /* All offsets up to size2 must be accessible. */ ptr2[size1 - 1] = 'x'; ptr2[size1] = 'x'; @@ -327,6 +330,9 @@ static void krealloc_less_oob_helper(struct kunit *test, ptr2 = krealloc(ptr1, size2, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr2); + /* Suppress -Warray-bounds warnings. */ + OPTIMIZER_HIDE_VAR(ptr2); + /* Must be accessible for all modes. */ ptr2[size2 - 1] = 'x'; @@ -540,13 +546,14 @@ static void kmalloc_memmove_invalid_size(struct kunit *test) { char *ptr; size_t size = 64; - volatile size_t invalid_size = size; + size_t invalid_size = size; ptr = kmalloc(size, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); memset((char *)ptr, 0, 64); OPTIMIZER_HIDE_VAR(ptr); + OPTIMIZER_HIDE_VAR(invalid_size); KUNIT_EXPECT_KASAN_FAIL(test, memmove((char *)ptr, (char *)ptr + 4, invalid_size)); kfree(ptr); diff --git a/mm/memory.c b/mm/memory.c index 032d0b5a7eca..84854e3b6177 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1394,10 +1394,12 @@ zap_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, pte_t *pte, struct zap_details *details, pte_t pteval) { +#ifdef CONFIG_PTE_MARKER_UFFD_WP if (zap_drop_file_uffd_wp(details)) return; pte_install_uffd_wp_if_needed(vma, addr, pte, pteval); +#endif } static unsigned long zap_pte_range(struct mmu_gather *tlb, @@ -3749,7 +3751,21 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) ret = remove_device_exclusive_entry(vmf); } else if (is_device_private_entry(entry)) { vmf->page = pfn_swap_entry_to_page(entry); - ret = vmf->page->pgmap->ops->migrate_to_ram(vmf); + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, + vmf->address, &vmf->ptl); + if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) { + spin_unlock(vmf->ptl); + goto out; + } + + /* + * Get a page reference while we know the page can't be + * freed. + */ + get_page(vmf->page); + pte_unmap_unlock(vmf->pte, vmf->ptl); + vmf->page->pgmap->ops->migrate_to_ram(vmf); + put_page(vmf->page); } else if (is_hwpoison_entry(entry)) { ret = VM_FAULT_HWPOISON; } else if (is_swapin_error_entry(entry)) { @@ -4119,7 +4135,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (!pte_none(*vmf->pte)) { - update_mmu_cache(vma, vmf->address, vmf->pte); + update_mmu_tlb(vma, vmf->address, vmf->pte); goto release; } diff --git a/mm/memremap.c b/mm/memremap.c index 25029a474d30..421bec3a29ee 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -138,8 +138,11 @@ void memunmap_pages(struct dev_pagemap *pgmap) int i; percpu_ref_kill(&pgmap->ref); - for (i = 0; i < pgmap->nr_range; i++) - percpu_ref_put_many(&pgmap->ref, pfn_len(pgmap, i)); + if (pgmap->type != MEMORY_DEVICE_PRIVATE && + pgmap->type != MEMORY_DEVICE_COHERENT) + for (i = 0; i < pgmap->nr_range; i++) + percpu_ref_put_many(&pgmap->ref, pfn_len(pgmap, i)); + wait_for_completion(&pgmap->done); for (i = 0; i < pgmap->nr_range; i++) @@ -264,7 +267,9 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params, memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE], PHYS_PFN(range->start), PHYS_PFN(range_len(range)), pgmap); - percpu_ref_get_many(&pgmap->ref, pfn_len(pgmap, range_id)); + if (pgmap->type != MEMORY_DEVICE_PRIVATE && + pgmap->type != MEMORY_DEVICE_COHERENT) + percpu_ref_get_many(&pgmap->ref, pfn_len(pgmap, range_id)); return 0; err_add_memory: @@ -502,12 +507,29 @@ void free_zone_device_page(struct page *page) page->mapping = NULL; page->pgmap->ops->page_free(page); - /* - * Reset the page count to 1 to prepare for handing out the page again. - */ - set_page_count(page, 1); + if (page->pgmap->type != MEMORY_DEVICE_PRIVATE && + page->pgmap->type != MEMORY_DEVICE_COHERENT) + /* + * Reset the page count to 1 to prepare for handing out the page + * again. + */ + set_page_count(page, 1); + else + put_dev_pagemap(page->pgmap); } +void zone_device_page_init(struct page *page) +{ + /* + * Drivers shouldn't be allocating pages after calling + * memunmap_pages(). + */ + WARN_ON_ONCE(!percpu_ref_tryget_live(&page->pgmap->ref)); + set_page_count(page, 1); + lock_page(page); +} +EXPORT_SYMBOL_GPL(zone_device_page_init); + #ifdef CONFIG_FS_DAX bool __put_devmap_managed_page_refs(struct page *page, int refs) { diff --git a/mm/migrate.c b/mm/migrate.c index c228afba0963..1379e1912772 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -625,6 +625,25 @@ EXPORT_SYMBOL(folio_migrate_copy); * Migration functions ***********************************************************/ +int migrate_folio_extra(struct address_space *mapping, struct folio *dst, + struct folio *src, enum migrate_mode mode, int extra_count) +{ + int rc; + + BUG_ON(folio_test_writeback(src)); /* Writeback must be complete */ + + rc = folio_migrate_mapping(mapping, dst, src, extra_count); + + if (rc != MIGRATEPAGE_SUCCESS) + return rc; + + if (mode != MIGRATE_SYNC_NO_COPY) + folio_migrate_copy(dst, src); + else + folio_migrate_flags(dst, src); + return MIGRATEPAGE_SUCCESS; +} + /** * migrate_folio() - Simple folio migration. * @mapping: The address_space containing the folio. @@ -640,20 +659,7 @@ EXPORT_SYMBOL(folio_migrate_copy); int migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode) { - int rc; - - BUG_ON(folio_test_writeback(src)); /* Writeback must be complete */ - - rc = folio_migrate_mapping(mapping, dst, src, 0); - - if (rc != MIGRATEPAGE_SUCCESS) - return rc; - - if (mode != MIGRATE_SYNC_NO_COPY) - folio_migrate_copy(dst, src); - else - folio_migrate_flags(dst, src); - return MIGRATEPAGE_SUCCESS; + return migrate_folio_extra(mapping, dst, src, mode, 0); } EXPORT_SYMBOL(migrate_folio); diff --git a/mm/migrate_device.c b/mm/migrate_device.c index 5ab6ab9d2ed8..6fa682eef7a0 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -325,14 +325,14 @@ static void migrate_vma_collect(struct migrate_vma *migrate) * folio_migrate_mapping(), except that here we allow migration of a * ZONE_DEVICE page. */ -static bool migrate_vma_check_page(struct page *page) +static bool migrate_vma_check_page(struct page *page, struct page *fault_page) { /* * One extra ref because caller holds an extra reference, either from * isolate_lru_page() for a regular page, or migrate_vma_collect() for * a device page. */ - int extra = 1; + int extra = 1 + (page == fault_page); /* * FIXME support THP (transparent huge page), it is bit more complex to @@ -357,26 +357,20 @@ static bool migrate_vma_check_page(struct page *page) } /* - * migrate_vma_unmap() - replace page mapping with special migration pte entry - * @migrate: migrate struct containing all migration information - * - * Isolate pages from the LRU and replace mappings (CPU page table pte) with a - * special migration pte entry and check if it has been pinned. Pinned pages are - * restored because we cannot migrate them. - * - * This is the last step before we call the device driver callback to allocate - * destination memory and copy contents of original page over to new page. + * Unmaps pages for migration. Returns number of unmapped pages. */ -static void migrate_vma_unmap(struct migrate_vma *migrate) +static unsigned long migrate_device_unmap(unsigned long *src_pfns, + unsigned long npages, + struct page *fault_page) { - const unsigned long npages = migrate->npages; unsigned long i, restore = 0; bool allow_drain = true; + unsigned long unmapped = 0; lru_add_drain(); for (i = 0; i < npages; i++) { - struct page *page = migrate_pfn_to_page(migrate->src[i]); + struct page *page = migrate_pfn_to_page(src_pfns[i]); struct folio *folio; if (!page) @@ -391,8 +385,7 @@ static void migrate_vma_unmap(struct migrate_vma *migrate) } if (isolate_lru_page(page)) { - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; - migrate->cpages--; + src_pfns[i] &= ~MIGRATE_PFN_MIGRATE; restore++; continue; } @@ -405,34 +398,55 @@ static void migrate_vma_unmap(struct migrate_vma *migrate) if (folio_mapped(folio)) try_to_migrate(folio, 0); - if (page_mapped(page) || !migrate_vma_check_page(page)) { + if (page_mapped(page) || + !migrate_vma_check_page(page, fault_page)) { if (!is_zone_device_page(page)) { get_page(page); putback_lru_page(page); } - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; - migrate->cpages--; + src_pfns[i] &= ~MIGRATE_PFN_MIGRATE; restore++; continue; } + + unmapped++; } for (i = 0; i < npages && restore; i++) { - struct page *page = migrate_pfn_to_page(migrate->src[i]); + struct page *page = migrate_pfn_to_page(src_pfns[i]); struct folio *folio; - if (!page || (migrate->src[i] & MIGRATE_PFN_MIGRATE)) + if (!page || (src_pfns[i] & MIGRATE_PFN_MIGRATE)) continue; folio = page_folio(page); remove_migration_ptes(folio, folio, false); - migrate->src[i] = 0; + src_pfns[i] = 0; folio_unlock(folio); folio_put(folio); restore--; } + + return unmapped; +} + +/* + * migrate_vma_unmap() - replace page mapping with special migration pte entry + * @migrate: migrate struct containing all migration information + * + * Isolate pages from the LRU and replace mappings (CPU page table pte) with a + * special migration pte entry and check if it has been pinned. Pinned pages are + * restored because we cannot migrate them. + * + * This is the last step before we call the device driver callback to allocate + * destination memory and copy contents of original page over to new page. + */ +static void migrate_vma_unmap(struct migrate_vma *migrate) +{ + migrate->cpages = migrate_device_unmap(migrate->src, migrate->npages, + migrate->fault_page); } /** @@ -517,6 +531,8 @@ int migrate_vma_setup(struct migrate_vma *args) return -EINVAL; if (!args->src || !args->dst) return -EINVAL; + if (args->fault_page && !is_device_private_page(args->fault_page)) + return -EINVAL; memset(args->src, 0, sizeof(*args->src) * nr_pages); args->cpages = 0; @@ -677,42 +693,38 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, *src &= ~MIGRATE_PFN_MIGRATE; } -/** - * migrate_vma_pages() - migrate meta-data from src page to dst page - * @migrate: migrate struct containing all migration information - * - * This migrates struct page meta-data from source struct page to destination - * struct page. This effectively finishes the migration from source page to the - * destination page. - */ -void migrate_vma_pages(struct migrate_vma *migrate) +static void __migrate_device_pages(unsigned long *src_pfns, + unsigned long *dst_pfns, unsigned long npages, + struct migrate_vma *migrate) { - const unsigned long npages = migrate->npages; - const unsigned long start = migrate->start; struct mmu_notifier_range range; - unsigned long addr, i; + unsigned long i; bool notified = false; - for (i = 0, addr = start; i < npages; addr += PAGE_SIZE, i++) { - struct page *newpage = migrate_pfn_to_page(migrate->dst[i]); - struct page *page = migrate_pfn_to_page(migrate->src[i]); + for (i = 0; i < npages; i++) { + struct page *newpage = migrate_pfn_to_page(dst_pfns[i]); + struct page *page = migrate_pfn_to_page(src_pfns[i]); struct address_space *mapping; int r; if (!newpage) { - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; + src_pfns[i] &= ~MIGRATE_PFN_MIGRATE; continue; } if (!page) { + unsigned long addr; + + if (!(src_pfns[i] & MIGRATE_PFN_MIGRATE)) + continue; + /* * The only time there is no vma is when called from * migrate_device_coherent_page(). However this isn't * called if the page could not be unmapped. */ - VM_BUG_ON(!migrate->vma); - if (!(migrate->src[i] & MIGRATE_PFN_MIGRATE)) - continue; + VM_BUG_ON(!migrate); + addr = migrate->start + i*PAGE_SIZE; if (!notified) { notified = true; @@ -723,7 +735,7 @@ void migrate_vma_pages(struct migrate_vma *migrate) mmu_notifier_invalidate_range_start(&range); } migrate_vma_insert_page(migrate, addr, newpage, - &migrate->src[i]); + &src_pfns[i]); continue; } @@ -736,21 +748,26 @@ void migrate_vma_pages(struct migrate_vma *migrate) * device private or coherent memory. */ if (mapping) { - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; + src_pfns[i] &= ~MIGRATE_PFN_MIGRATE; continue; } } else if (is_zone_device_page(newpage)) { /* * Other types of ZONE_DEVICE page are not supported. */ - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; + src_pfns[i] &= ~MIGRATE_PFN_MIGRATE; continue; } - r = migrate_folio(mapping, page_folio(newpage), - page_folio(page), MIGRATE_SYNC_NO_COPY); + if (migrate && migrate->fault_page == page) + r = migrate_folio_extra(mapping, page_folio(newpage), + page_folio(page), + MIGRATE_SYNC_NO_COPY, 1); + else + r = migrate_folio(mapping, page_folio(newpage), + page_folio(page), MIGRATE_SYNC_NO_COPY); if (r != MIGRATEPAGE_SUCCESS) - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; + src_pfns[i] &= ~MIGRATE_PFN_MIGRATE; } /* @@ -761,28 +778,56 @@ void migrate_vma_pages(struct migrate_vma *migrate) if (notified) mmu_notifier_invalidate_range_only_end(&range); } -EXPORT_SYMBOL(migrate_vma_pages); /** - * migrate_vma_finalize() - restore CPU page table entry + * migrate_device_pages() - migrate meta-data from src page to dst page + * @src_pfns: src_pfns returned from migrate_device_range() + * @dst_pfns: array of pfns allocated by the driver to migrate memory to + * @npages: number of pages in the range + * + * Equivalent to migrate_vma_pages(). This is called to migrate struct page + * meta-data from source struct page to destination. + */ +void migrate_device_pages(unsigned long *src_pfns, unsigned long *dst_pfns, + unsigned long npages) +{ + __migrate_device_pages(src_pfns, dst_pfns, npages, NULL); +} +EXPORT_SYMBOL(migrate_device_pages); + +/** + * migrate_vma_pages() - migrate meta-data from src page to dst page * @migrate: migrate struct containing all migration information * - * This replaces the special migration pte entry with either a mapping to the - * new page if migration was successful for that page, or to the original page - * otherwise. - * - * This also unlocks the pages and puts them back on the lru, or drops the extra - * refcount, for device pages. + * This migrates struct page meta-data from source struct page to destination + * struct page. This effectively finishes the migration from source page to the + * destination page. */ -void migrate_vma_finalize(struct migrate_vma *migrate) +void migrate_vma_pages(struct migrate_vma *migrate) +{ + __migrate_device_pages(migrate->src, migrate->dst, migrate->npages, migrate); +} +EXPORT_SYMBOL(migrate_vma_pages); + +/* + * migrate_device_finalize() - complete page migration + * @src_pfns: src_pfns returned from migrate_device_range() + * @dst_pfns: array of pfns allocated by the driver to migrate memory to + * @npages: number of pages in the range + * + * Completes migration of the page by removing special migration entries. + * Drivers must ensure copying of page data is complete and visible to the CPU + * before calling this. + */ +void migrate_device_finalize(unsigned long *src_pfns, + unsigned long *dst_pfns, unsigned long npages) { - const unsigned long npages = migrate->npages; unsigned long i; for (i = 0; i < npages; i++) { struct folio *dst, *src; - struct page *newpage = migrate_pfn_to_page(migrate->dst[i]); - struct page *page = migrate_pfn_to_page(migrate->src[i]); + struct page *newpage = migrate_pfn_to_page(dst_pfns[i]); + struct page *page = migrate_pfn_to_page(src_pfns[i]); if (!page) { if (newpage) { @@ -792,7 +837,7 @@ void migrate_vma_finalize(struct migrate_vma *migrate) continue; } - if (!(migrate->src[i] & MIGRATE_PFN_MIGRATE) || !newpage) { + if (!(src_pfns[i] & MIGRATE_PFN_MIGRATE) || !newpage) { if (newpage) { unlock_page(newpage); put_page(newpage); @@ -819,8 +864,72 @@ void migrate_vma_finalize(struct migrate_vma *migrate) } } } +EXPORT_SYMBOL(migrate_device_finalize); + +/** + * migrate_vma_finalize() - restore CPU page table entry + * @migrate: migrate struct containing all migration information + * + * This replaces the special migration pte entry with either a mapping to the + * new page if migration was successful for that page, or to the original page + * otherwise. + * + * This also unlocks the pages and puts them back on the lru, or drops the extra + * refcount, for device pages. + */ +void migrate_vma_finalize(struct migrate_vma *migrate) +{ + migrate_device_finalize(migrate->src, migrate->dst, migrate->npages); +} EXPORT_SYMBOL(migrate_vma_finalize); +/** + * migrate_device_range() - migrate device private pfns to normal memory. + * @src_pfns: array large enough to hold migrating source device private pfns. + * @start: starting pfn in the range to migrate. + * @npages: number of pages to migrate. + * + * migrate_vma_setup() is similar in concept to migrate_vma_setup() except that + * instead of looking up pages based on virtual address mappings a range of + * device pfns that should be migrated to system memory is used instead. + * + * This is useful when a driver needs to free device memory but doesn't know the + * virtual mappings of every page that may be in device memory. For example this + * is often the case when a driver is being unloaded or unbound from a device. + * + * Like migrate_vma_setup() this function will take a reference and lock any + * migrating pages that aren't free before unmapping them. Drivers may then + * allocate destination pages and start copying data from the device to CPU + * memory before calling migrate_device_pages(). + */ +int migrate_device_range(unsigned long *src_pfns, unsigned long start, + unsigned long npages) +{ + unsigned long i, pfn; + + for (pfn = start, i = 0; i < npages; pfn++, i++) { + struct page *page = pfn_to_page(pfn); + + if (!get_page_unless_zero(page)) { + src_pfns[i] = 0; + continue; + } + + if (!trylock_page(page)) { + src_pfns[i] = 0; + put_page(page); + continue; + } + + src_pfns[i] = migrate_pfn(pfn) | MIGRATE_PFN_MIGRATE; + } + + migrate_device_unmap(src_pfns, npages, NULL); + + return 0; +} +EXPORT_SYMBOL(migrate_device_range); + /* * Migrate a device coherent page back to normal memory. The caller should have * a reference on page which will be copied to the new page if migration is @@ -829,25 +938,19 @@ EXPORT_SYMBOL(migrate_vma_finalize); int migrate_device_coherent_page(struct page *page) { unsigned long src_pfn, dst_pfn = 0; - struct migrate_vma args; struct page *dpage; WARN_ON_ONCE(PageCompound(page)); lock_page(page); src_pfn = migrate_pfn(page_to_pfn(page)) | MIGRATE_PFN_MIGRATE; - args.src = &src_pfn; - args.dst = &dst_pfn; - args.cpages = 1; - args.npages = 1; - args.vma = NULL; /* * We don't have a VMA and don't need to walk the page tables to find * the source page. So call migrate_vma_unmap() directly to unmap the * page as migrate_vma_setup() will fail if args.vma == NULL. */ - migrate_vma_unmap(&args); + migrate_device_unmap(&src_pfn, 1, NULL); if (!(src_pfn & MIGRATE_PFN_MIGRATE)) return -EBUSY; @@ -857,10 +960,10 @@ int migrate_device_coherent_page(struct page *page) dst_pfn = migrate_pfn(page_to_pfn(dpage)); } - migrate_vma_pages(&args); + migrate_device_pages(&src_pfn, &dst_pfn, 1); if (src_pfn & MIGRATE_PFN_MIGRATE) copy_highpage(dpage, page); - migrate_vma_finalize(&args); + migrate_device_finalize(&src_pfn, &dst_pfn, 1); if (src_pfn & MIGRATE_PFN_MIGRATE) return 0; diff --git a/mm/mmap.c b/mm/mmap.c index 439af6d192a0..b5d09c63bef2 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2674,7 +2674,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, if (!arch_validate_flags(vma->vm_flags)) { error = -EINVAL; if (file) - goto unmap_and_free_vma; + goto close_and_free_vma; else goto free_vma; } @@ -2743,6 +2743,9 @@ unsigned long mmap_region(struct file *file, unsigned long addr, validate_mm(mm); return addr; +close_and_free_vma: + if (vma->vm_ops && vma->vm_ops->close) + vma->vm_ops->close(vma); unmap_and_free_vma: fput(vma->vm_file); vma->vm_file = NULL; @@ -2943,17 +2946,18 @@ static int do_brk_flags(struct ma_state *mas, struct vm_area_struct *vma, if (vma && (!vma->anon_vma || list_is_singular(&vma->anon_vma_chain)) && ((vma->vm_flags & ~VM_SOFTDIRTY) == flags)) { - mas->index = vma->vm_start; - mas->last = addr + len - 1; - vma_adjust_trans_huge(vma, addr, addr + len, 0); + mas_set_range(mas, vma->vm_start, addr + len - 1); + if (mas_preallocate(mas, vma, GFP_KERNEL)) + return -ENOMEM; + + vma_adjust_trans_huge(vma, vma->vm_start, addr + len, 0); if (vma->anon_vma) { anon_vma_lock_write(vma->anon_vma); anon_vma_interval_tree_pre_update_vma(vma); } vma->vm_end = addr + len; vma->vm_flags |= VM_SOFTDIRTY; - if (mas_store_gfp(mas, vma, GFP_KERNEL)) - goto mas_expand_failed; + mas_store_prealloc(mas, vma); if (vma->anon_vma) { anon_vma_interval_tree_post_update_vma(vma); @@ -2994,13 +2998,6 @@ static int do_brk_flags(struct ma_state *mas, struct vm_area_struct *vma, vma_alloc_fail: vm_unacct_memory(len >> PAGE_SHIFT); return -ENOMEM; - -mas_expand_failed: - if (vma->anon_vma) { - anon_vma_interval_tree_post_update_vma(vma); - anon_vma_unlock_write(vma->anon_vma); - } - return -ENOMEM; } int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags) @@ -3241,6 +3238,11 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, out_vma_link: if (new_vma->vm_ops && new_vma->vm_ops->close) new_vma->vm_ops->close(new_vma); + + if (new_vma->vm_file) + fput(new_vma->vm_file); + + unlink_anon_vmas(new_vma); out_free_mempol: mpol_put(vma_policy(new_vma)); out_free_vma: diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index a71924bd38c0..add4244e5790 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -1,6 +1,7 @@ #include #include #include +#include #include #include #include @@ -265,6 +266,15 @@ void tlb_flush_mmu(struct mmu_gather *tlb) static void __tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm) { + /* + * struct mmu_gather contains 7 1-bit fields packed into a 32-bit + * unsigned int value. The remaining 25 bits remain uninitialized + * and are never used, but KMSAN updates the origin for them in + * zap_pXX_range() in mm/memory.c, thus creating very long origin + * chains. This is technically correct, but consumes too much memory. + * Unpoisoning the whole structure will prevent creating such chains. + */ + kmsan_unpoison_memory(tlb, sizeof(*tlb)); tlb->mm = mm; tlb->fullmm = fullmm; diff --git a/mm/mprotect.c b/mm/mprotect.c index 461dcbd4f21a..668bfaa6ed2a 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -267,6 +267,7 @@ static unsigned long change_pte_range(struct mmu_gather *tlb, } else { /* It must be an none page, or what else?.. */ WARN_ON_ONCE(!pte_none(oldpte)); +#ifdef CONFIG_PTE_MARKER_UFFD_WP if (unlikely(uffd_wp && !vma_is_anonymous(vma))) { /* * For file-backed mem, we need to be able to @@ -278,6 +279,7 @@ static unsigned long change_pte_range(struct mmu_gather *tlb, make_pte_marker(PTE_MARKER_UFFD_WP)); pages++; } +#endif } } while (pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ac2c9f12a7b2..e20ade858e71 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3446,7 +3446,7 @@ static void free_unref_page_commit(struct zone *zone, struct per_cpu_pages *pcp, int pindex; bool free_high; - __count_vm_event(PGFREE); + __count_vm_events(PGFREE, 1 << order); pindex = order_to_pindex(migratetype, order); list_add(&page->pcp_list, &pcp->lists[pindex]); pcp->count += 1 << order; @@ -3803,7 +3803,7 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone, pcp_spin_unlock_irqrestore(pcp, flags); pcp_trylock_finish(UP_flags); if (page) { - __count_zid_vm_events(PGALLOC, page_zonenum(page), 1); + __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); zone_statistics(preferred_zone, zone, 1); } return page; @@ -6823,6 +6823,14 @@ static void __ref __init_zone_device_page(struct page *page, unsigned long pfn, set_pageblock_migratetype(page, MIGRATE_MOVABLE); cond_resched(); } + + /* + * ZONE_DEVICE pages are released directly to the driver page allocator + * which will set the page count to 1 when allocating the page. + */ + if (pgmap->type == MEMORY_DEVICE_PRIVATE || + pgmap->type == MEMORY_DEVICE_COHERENT) + set_page_count(page, 0); } /* diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index 6963d5a487b3..d8edb6055072 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -1899,10 +1899,8 @@ static int snd_rawmidi_free(struct snd_rawmidi *rmidi) snd_info_free_entry(rmidi->proc_entry); rmidi->proc_entry = NULL; - mutex_lock(®ister_mutex); if (rmidi->ops && rmidi->ops->dev_unregister) rmidi->ops->dev_unregister(rmidi); - mutex_unlock(®ister_mutex); snd_rawmidi_free_substreams(&rmidi->streams[SNDRV_RAWMIDI_STREAM_INPUT]); snd_rawmidi_free_substreams(&rmidi->streams[SNDRV_RAWMIDI_STREAM_OUTPUT]); diff --git a/sound/core/sound_oss.c b/sound/core/sound_oss.c index 7ed0a2a91035..2751bf2ff61b 100644 --- a/sound/core/sound_oss.c +++ b/sound/core/sound_oss.c @@ -162,7 +162,6 @@ int snd_unregister_oss_device(int type, struct snd_card *card, int dev) mutex_unlock(&sound_oss_mutex); return -ENOENT; } - unregister_sound_special(minor); switch (SNDRV_MINOR_OSS_DEVICE(minor)) { case SNDRV_MINOR_OSS_PCM: track2 = SNDRV_MINOR_OSS(cidx, SNDRV_MINOR_OSS_AUDIO); @@ -174,12 +173,18 @@ int snd_unregister_oss_device(int type, struct snd_card *card, int dev) track2 = SNDRV_MINOR_OSS(cidx, SNDRV_MINOR_OSS_DMMIDI1); break; } - if (track2 >= 0) { - unregister_sound_special(track2); + if (track2 >= 0) snd_oss_minors[track2] = NULL; - } snd_oss_minors[minor] = NULL; mutex_unlock(&sound_oss_mutex); + + /* call unregister_sound_special() outside sound_oss_mutex; + * otherwise may deadlock, as it can trigger the release of a card + */ + unregister_sound_special(minor); + if (track2 >= 0) + unregister_sound_special(track2); + kfree(mptr); return 0; } diff --git a/sound/pci/hda/cs35l41_hda.c b/sound/pci/hda/cs35l41_hda.c index 3952f2853703..e5f0549bf06d 100644 --- a/sound/pci/hda/cs35l41_hda.c +++ b/sound/pci/hda/cs35l41_hda.c @@ -91,20 +91,18 @@ static const struct reg_sequence cs35l41_hda_mute[] = { { CS35L41_AMP_DIG_VOL_CTRL, 0x0000A678 }, // AMP_VOL_PCM Mute }; -static int cs35l41_control_add(struct cs_dsp_coeff_ctl *cs_ctl) +static void cs35l41_add_controls(struct cs35l41_hda *cs35l41) { - struct cs35l41_hda *cs35l41 = container_of(cs_ctl->dsp, struct cs35l41_hda, cs_dsp); struct hda_cs_dsp_ctl_info info; info.device_name = cs35l41->amp_name; info.fw_type = cs35l41->firmware_type; info.card = cs35l41->codec->card; - return hda_cs_dsp_control_add(cs_ctl, &info); + hda_cs_dsp_add_controls(&cs35l41->cs_dsp, &info); } static const struct cs_dsp_client_ops client_ops = { - .control_add = cs35l41_control_add, .control_remove = hda_cs_dsp_control_remove, }; @@ -435,6 +433,8 @@ static int cs35l41_init_dsp(struct cs35l41_hda *cs35l41) if (ret) goto err_release; + cs35l41_add_controls(cs35l41); + ret = cs35l41_save_calibration(cs35l41); err_release: @@ -461,9 +461,12 @@ static void cs35l41_remove_dsp(struct cs35l41_hda *cs35l41) struct cs_dsp *dsp = &cs35l41->cs_dsp; cancel_work_sync(&cs35l41->fw_load_work); + + mutex_lock(&cs35l41->fw_mutex); cs35l41_shutdown_dsp(cs35l41); cs_dsp_remove(dsp); cs35l41->halo_initialized = false; + mutex_unlock(&cs35l41->fw_mutex); } /* Protection release cycle to get the speaker out of Safe-Mode */ @@ -487,10 +490,10 @@ static void cs35l41_hda_playback_hook(struct device *dev, int action) struct regmap *reg = cs35l41->regmap; int ret = 0; - mutex_lock(&cs35l41->fw_mutex); - switch (action) { case HDA_GEN_PCM_ACT_OPEN: + pm_runtime_get_sync(dev); + mutex_lock(&cs35l41->fw_mutex); cs35l41->playback_started = true; if (cs35l41->firmware_running) { regmap_multi_reg_write(reg, cs35l41_hda_config_dsp, @@ -508,15 +511,21 @@ static void cs35l41_hda_playback_hook(struct device *dev, int action) CS35L41_AMP_EN_MASK, 1 << CS35L41_AMP_EN_SHIFT); if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST) regmap_write(reg, CS35L41_GPIO1_CTRL1, 0x00008001); + mutex_unlock(&cs35l41->fw_mutex); break; case HDA_GEN_PCM_ACT_PREPARE: + mutex_lock(&cs35l41->fw_mutex); ret = cs35l41_global_enable(reg, cs35l41->hw_cfg.bst_type, 1); + mutex_unlock(&cs35l41->fw_mutex); break; case HDA_GEN_PCM_ACT_CLEANUP: + mutex_lock(&cs35l41->fw_mutex); regmap_multi_reg_write(reg, cs35l41_hda_mute, ARRAY_SIZE(cs35l41_hda_mute)); ret = cs35l41_global_enable(reg, cs35l41->hw_cfg.bst_type, 0); + mutex_unlock(&cs35l41->fw_mutex); break; case HDA_GEN_PCM_ACT_CLOSE: + mutex_lock(&cs35l41->fw_mutex); ret = regmap_update_bits(reg, CS35L41_PWR_CTRL2, CS35L41_AMP_EN_MASK, 0 << CS35L41_AMP_EN_SHIFT); if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST) @@ -530,14 +539,16 @@ static void cs35l41_hda_playback_hook(struct device *dev, int action) } cs35l41_irq_release(cs35l41); cs35l41->playback_started = false; + mutex_unlock(&cs35l41->fw_mutex); + + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); break; default: dev_warn(cs35l41->dev, "Playback action not supported: %d\n", action); break; } - mutex_unlock(&cs35l41->fw_mutex); - if (ret) dev_err(cs35l41->dev, "Regmap access fail: %d\n", ret); } @@ -562,45 +573,148 @@ static int cs35l41_hda_channel_map(struct device *dev, unsigned int tx_num, unsi rx_slot); } +static void cs35l41_ready_for_reset(struct cs35l41_hda *cs35l41) +{ + mutex_lock(&cs35l41->fw_mutex); + if (cs35l41->firmware_running) { + + regcache_cache_only(cs35l41->regmap, false); + + cs35l41_exit_hibernate(cs35l41->dev, cs35l41->regmap); + cs35l41_shutdown_dsp(cs35l41); + cs35l41_safe_reset(cs35l41->regmap, cs35l41->hw_cfg.bst_type); + + regcache_cache_only(cs35l41->regmap, true); + regcache_mark_dirty(cs35l41->regmap); + } + mutex_unlock(&cs35l41->fw_mutex); +} + +static int cs35l41_system_suspend(struct device *dev) +{ + struct cs35l41_hda *cs35l41 = dev_get_drvdata(dev); + int ret; + + dev_dbg(cs35l41->dev, "System Suspend\n"); + + if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST_NO_VSPK_SWITCH) { + dev_err(cs35l41->dev, "System Suspend not supported\n"); + return -EINVAL; + } + + ret = pm_runtime_force_suspend(dev); + if (ret) + return ret; + + /* Shutdown DSP before system suspend */ + cs35l41_ready_for_reset(cs35l41); + + /* + * Reset GPIO may be shared, so cannot reset here. + * However beyond this point, amps may be powered down. + */ + return 0; +} + +static int cs35l41_system_resume(struct device *dev) +{ + struct cs35l41_hda *cs35l41 = dev_get_drvdata(dev); + int ret; + + dev_dbg(cs35l41->dev, "System Resume\n"); + + if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST_NO_VSPK_SWITCH) { + dev_err(cs35l41->dev, "System Resume not supported\n"); + return -EINVAL; + } + + if (cs35l41->reset_gpio) { + usleep_range(2000, 2100); + gpiod_set_value_cansleep(cs35l41->reset_gpio, 1); + } + + usleep_range(2000, 2100); + + ret = pm_runtime_force_resume(dev); + + mutex_lock(&cs35l41->fw_mutex); + if (!ret && cs35l41->request_fw_load && !cs35l41->fw_request_ongoing) { + cs35l41->fw_request_ongoing = true; + schedule_work(&cs35l41->fw_load_work); + } + mutex_unlock(&cs35l41->fw_mutex); + + return ret; +} + static int cs35l41_runtime_suspend(struct device *dev) { struct cs35l41_hda *cs35l41 = dev_get_drvdata(dev); + int ret = 0; - dev_dbg(cs35l41->dev, "Suspend\n"); + dev_dbg(cs35l41->dev, "Runtime Suspend\n"); - if (!cs35l41->firmware_running) + if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST_NO_VSPK_SWITCH) { + dev_dbg(cs35l41->dev, "Runtime Suspend not supported\n"); return 0; + } - if (cs35l41_enter_hibernate(cs35l41->dev, cs35l41->regmap, cs35l41->hw_cfg.bst_type) < 0) - return 0; + mutex_lock(&cs35l41->fw_mutex); + + if (cs35l41->playback_started) { + regmap_multi_reg_write(cs35l41->regmap, cs35l41_hda_mute, + ARRAY_SIZE(cs35l41_hda_mute)); + cs35l41_global_enable(cs35l41->regmap, cs35l41->hw_cfg.bst_type, 0); + regmap_update_bits(cs35l41->regmap, CS35L41_PWR_CTRL2, + CS35L41_AMP_EN_MASK, 0 << CS35L41_AMP_EN_SHIFT); + if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST) + regmap_write(cs35l41->regmap, CS35L41_GPIO1_CTRL1, 0x00000001); + regmap_update_bits(cs35l41->regmap, CS35L41_PWR_CTRL2, + CS35L41_VMON_EN_MASK | CS35L41_IMON_EN_MASK, + 0 << CS35L41_VMON_EN_SHIFT | 0 << CS35L41_IMON_EN_SHIFT); + cs35l41->playback_started = false; + } + + if (cs35l41->firmware_running) { + ret = cs35l41_enter_hibernate(cs35l41->dev, cs35l41->regmap, + cs35l41->hw_cfg.bst_type); + if (ret) + goto err; + } else { + cs35l41_safe_reset(cs35l41->regmap, cs35l41->hw_cfg.bst_type); + } regcache_cache_only(cs35l41->regmap, true); regcache_mark_dirty(cs35l41->regmap); - return 0; +err: + mutex_unlock(&cs35l41->fw_mutex); + + return ret; } static int cs35l41_runtime_resume(struct device *dev) { struct cs35l41_hda *cs35l41 = dev_get_drvdata(dev); - int ret; + int ret = 0; - dev_dbg(cs35l41->dev, "Resume.\n"); + dev_dbg(cs35l41->dev, "Runtime Resume\n"); if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST_NO_VSPK_SWITCH) { - dev_dbg(cs35l41->dev, "System does not support Resume\n"); + dev_dbg(cs35l41->dev, "Runtime Resume not supported\n"); return 0; } - if (!cs35l41->firmware_running) - return 0; + mutex_lock(&cs35l41->fw_mutex); regcache_cache_only(cs35l41->regmap, false); - ret = cs35l41_exit_hibernate(cs35l41->dev, cs35l41->regmap); - if (ret) { - regcache_cache_only(cs35l41->regmap, true); - return ret; + if (cs35l41->firmware_running) { + ret = cs35l41_exit_hibernate(cs35l41->dev, cs35l41->regmap); + if (ret) { + dev_warn(cs35l41->dev, "Unable to exit Hibernate."); + goto err; + } } /* Test key needs to be unlocked to allow the OTP settings to re-apply */ @@ -609,26 +723,16 @@ static int cs35l41_runtime_resume(struct device *dev) cs35l41_test_key_lock(cs35l41->dev, cs35l41->regmap); if (ret) { dev_err(cs35l41->dev, "Failed to restore register cache: %d\n", ret); - return ret; + goto err; } if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST) cs35l41_init_boost(cs35l41->dev, cs35l41->regmap, &cs35l41->hw_cfg); - return 0; -} +err: + mutex_unlock(&cs35l41->fw_mutex); -static int cs35l41_hda_suspend_hook(struct device *dev) -{ - dev_dbg(dev, "Request Suspend\n"); - pm_runtime_mark_last_busy(dev); - return pm_runtime_put_autosuspend(dev); -} - -static int cs35l41_hda_resume_hook(struct device *dev) -{ - dev_dbg(dev, "Request Resume\n"); - return pm_runtime_get_sync(dev); + return ret; } static int cs35l41_smart_amp(struct cs35l41_hda *cs35l41) @@ -678,8 +782,6 @@ static int cs35l41_smart_amp(struct cs35l41_hda *cs35l41) static void cs35l41_load_firmware(struct cs35l41_hda *cs35l41, bool load) { - pm_runtime_get_sync(cs35l41->dev); - if (cs35l41->firmware_running && !load) { dev_dbg(cs35l41->dev, "Unloading Firmware\n"); cs35l41_shutdown_dsp(cs35l41); @@ -689,9 +791,6 @@ static void cs35l41_load_firmware(struct cs35l41_hda *cs35l41, bool load) } else { dev_dbg(cs35l41->dev, "Unable to Load firmware.\n"); } - - pm_runtime_mark_last_busy(cs35l41->dev); - pm_runtime_put_autosuspend(cs35l41->dev); } static int cs35l41_fw_load_ctl_get(struct snd_kcontrol *kcontrol, @@ -707,16 +806,21 @@ static void cs35l41_fw_load_work(struct work_struct *work) { struct cs35l41_hda *cs35l41 = container_of(work, struct cs35l41_hda, fw_load_work); + pm_runtime_get_sync(cs35l41->dev); + mutex_lock(&cs35l41->fw_mutex); /* Recheck if playback is ongoing, mutex will block playback during firmware loading */ if (cs35l41->playback_started) - dev_err(cs35l41->dev, "Cannot Load/Unload firmware during Playback\n"); + dev_err(cs35l41->dev, "Cannot Load/Unload firmware during Playback. Retrying...\n"); else cs35l41_load_firmware(cs35l41, cs35l41->request_fw_load); cs35l41->fw_request_ongoing = false; mutex_unlock(&cs35l41->fw_mutex); + + pm_runtime_mark_last_busy(cs35l41->dev); + pm_runtime_put_autosuspend(cs35l41->dev); } static int cs35l41_fw_load_ctl_put(struct snd_kcontrol *kcontrol, @@ -840,6 +944,8 @@ static int cs35l41_hda_bind(struct device *dev, struct device *master, void *mas pm_runtime_get_sync(dev); + mutex_lock(&cs35l41->fw_mutex); + comps->dev = dev; if (!cs35l41->acpi_subsystem_id) cs35l41->acpi_subsystem_id = kasprintf(GFP_KERNEL, "%.8x", @@ -852,10 +958,8 @@ static int cs35l41_hda_bind(struct device *dev, struct device *master, void *mas if (firmware_autostart) { dev_dbg(cs35l41->dev, "Firmware Autostart.\n"); cs35l41->request_fw_load = true; - mutex_lock(&cs35l41->fw_mutex); if (cs35l41_smart_amp(cs35l41) < 0) dev_warn(cs35l41->dev, "Cannot Run Firmware, reverting to dsp bypass...\n"); - mutex_unlock(&cs35l41->fw_mutex); } else { dev_dbg(cs35l41->dev, "Firmware Autostart is disabled.\n"); } @@ -863,8 +967,8 @@ static int cs35l41_hda_bind(struct device *dev, struct device *master, void *mas ret = cs35l41_create_controls(cs35l41); comps->playback_hook = cs35l41_hda_playback_hook; - comps->suspend_hook = cs35l41_hda_suspend_hook; - comps->resume_hook = cs35l41_hda_resume_hook; + + mutex_unlock(&cs35l41->fw_mutex); pm_runtime_mark_last_busy(dev); pm_runtime_put_autosuspend(dev); @@ -1433,6 +1537,7 @@ EXPORT_SYMBOL_NS_GPL(cs35l41_hda_remove, SND_HDA_SCODEC_CS35L41); const struct dev_pm_ops cs35l41_hda_pm_ops = { RUNTIME_PM_OPS(cs35l41_runtime_suspend, cs35l41_runtime_resume, NULL) + SYSTEM_SLEEP_PM_OPS(cs35l41_system_suspend, cs35l41_system_resume) }; EXPORT_SYMBOL_NS_GPL(cs35l41_hda_pm_ops, SND_HDA_SCODEC_CS35L41); diff --git a/sound/pci/hda/hda_component.h b/sound/pci/hda/hda_component.h index 1223621bd62c..534e845b9cd1 100644 --- a/sound/pci/hda/hda_component.h +++ b/sound/pci/hda/hda_component.h @@ -16,6 +16,4 @@ struct hda_component { char name[HDA_MAX_NAME_SIZE]; struct hda_codec *codec; void (*playback_hook)(struct device *dev, int action); - int (*suspend_hook)(struct device *dev); - int (*resume_hook)(struct device *dev); }; diff --git a/sound/pci/hda/hda_cs_dsp_ctl.c b/sound/pci/hda/hda_cs_dsp_ctl.c index 89ee549cb7d5..1622a22f96f6 100644 --- a/sound/pci/hda/hda_cs_dsp_ctl.c +++ b/sound/pci/hda/hda_cs_dsp_ctl.c @@ -97,7 +97,7 @@ static unsigned int wmfw_convert_flags(unsigned int in) return out; } -static int hda_cs_dsp_add_kcontrol(struct hda_cs_dsp_coeff_ctl *ctl, const char *name) +static void hda_cs_dsp_add_kcontrol(struct hda_cs_dsp_coeff_ctl *ctl, const char *name) { struct cs_dsp_coeff_ctl *cs_ctl = ctl->cs_ctl; struct snd_kcontrol_new kcontrol = {0}; @@ -107,7 +107,7 @@ static int hda_cs_dsp_add_kcontrol(struct hda_cs_dsp_coeff_ctl *ctl, const char if (cs_ctl->len > ADSP_MAX_STD_CTRL_SIZE) { dev_err(cs_ctl->dsp->dev, "KControl %s: length %zu exceeds maximum %d\n", name, cs_ctl->len, ADSP_MAX_STD_CTRL_SIZE); - return -EINVAL; + return; } kcontrol.name = name; @@ -120,24 +120,21 @@ static int hda_cs_dsp_add_kcontrol(struct hda_cs_dsp_coeff_ctl *ctl, const char /* Save ctl inside private_data, ctl is owned by cs_dsp, * and will be freed when cs_dsp removes the control */ kctl = snd_ctl_new1(&kcontrol, (void *)ctl); - if (!kctl) { - ret = -ENOMEM; - return ret; - } + if (!kctl) + return; ret = snd_ctl_add(ctl->card, kctl); if (ret) { dev_err(cs_ctl->dsp->dev, "Failed to add KControl %s = %d\n", kcontrol.name, ret); - return ret; + return; } dev_dbg(cs_ctl->dsp->dev, "Added KControl: %s\n", kcontrol.name); ctl->kctl = kctl; - - return 0; } -int hda_cs_dsp_control_add(struct cs_dsp_coeff_ctl *cs_ctl, struct hda_cs_dsp_ctl_info *info) +static void hda_cs_dsp_control_add(struct cs_dsp_coeff_ctl *cs_ctl, + const struct hda_cs_dsp_ctl_info *info) { struct cs_dsp *cs_dsp = cs_ctl->dsp; char name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN]; @@ -145,13 +142,10 @@ int hda_cs_dsp_control_add(struct cs_dsp_coeff_ctl *cs_ctl, struct hda_cs_dsp_ct const char *region_name; int ret; - if (cs_ctl->flags & WMFW_CTL_FLAG_SYS) - return 0; - region_name = cs_dsp_mem_region_name(cs_ctl->alg_region.type); if (!region_name) { - dev_err(cs_dsp->dev, "Unknown region type: %d\n", cs_ctl->alg_region.type); - return -EINVAL; + dev_warn(cs_dsp->dev, "Unknown region type: %d\n", cs_ctl->alg_region.type); + return; } ret = scnprintf(name, SNDRV_CTL_ELEM_ID_NAME_MAXLEN, "%s %s %.12s %x", info->device_name, @@ -171,22 +165,39 @@ int hda_cs_dsp_control_add(struct cs_dsp_coeff_ctl *cs_ctl, struct hda_cs_dsp_ct ctl = kzalloc(sizeof(*ctl), GFP_KERNEL); if (!ctl) - return -ENOMEM; + return; ctl->cs_ctl = cs_ctl; ctl->card = info->card; cs_ctl->priv = ctl; - ret = hda_cs_dsp_add_kcontrol(ctl, name); - if (ret) { - dev_err(cs_dsp->dev, "Error (%d) adding control %s\n", ret, name); - kfree(ctl); - return ret; - } - - return 0; + hda_cs_dsp_add_kcontrol(ctl, name); } -EXPORT_SYMBOL_NS_GPL(hda_cs_dsp_control_add, SND_HDA_CS_DSP_CONTROLS); + +void hda_cs_dsp_add_controls(struct cs_dsp *dsp, const struct hda_cs_dsp_ctl_info *info) +{ + struct cs_dsp_coeff_ctl *cs_ctl; + + /* + * pwr_lock would cause mutex inversion with ALSA control lock compared + * to the get/put functions. + * It is safe to walk the list without holding a mutex because entries + * are persistent and only cs_dsp_power_up() or cs_dsp_remove() can + * change the list. + */ + lockdep_assert_not_held(&dsp->pwr_lock); + + list_for_each_entry(cs_ctl, &dsp->ctl_list, list) { + if (cs_ctl->flags & WMFW_CTL_FLAG_SYS) + continue; + + if (cs_ctl->priv) + continue; + + hda_cs_dsp_control_add(cs_ctl, info); + } +} +EXPORT_SYMBOL_NS_GPL(hda_cs_dsp_add_controls, SND_HDA_CS_DSP_CONTROLS); void hda_cs_dsp_control_remove(struct cs_dsp_coeff_ctl *cs_ctl) { @@ -203,19 +214,18 @@ int hda_cs_dsp_write_ctl(struct cs_dsp *dsp, const char *name, int type, struct hda_cs_dsp_coeff_ctl *ctl; int ret; + mutex_lock(&dsp->pwr_lock); cs_ctl = cs_dsp_get_ctl(dsp, name, type, alg); - if (!cs_ctl) - return -EINVAL; - - ctl = cs_ctl->priv; - ret = cs_dsp_coeff_write_ctrl(cs_ctl, 0, buf, len); + mutex_unlock(&dsp->pwr_lock); if (ret) return ret; if (cs_ctl->flags & WMFW_CTL_FLAG_SYS) return 0; + ctl = cs_ctl->priv; + snd_ctl_notify(ctl->card, SNDRV_CTL_EVENT_MASK_VALUE, &ctl->kctl->id); return 0; @@ -225,13 +235,14 @@ EXPORT_SYMBOL_NS_GPL(hda_cs_dsp_write_ctl, SND_HDA_CS_DSP_CONTROLS); int hda_cs_dsp_read_ctl(struct cs_dsp *dsp, const char *name, int type, unsigned int alg, void *buf, size_t len) { - struct cs_dsp_coeff_ctl *cs_ctl; + int ret; - cs_ctl = cs_dsp_get_ctl(dsp, name, type, alg); - if (!cs_ctl) - return -EINVAL; + mutex_lock(&dsp->pwr_lock); + ret = cs_dsp_coeff_read_ctrl(cs_dsp_get_ctl(dsp, name, type, alg), 0, buf, len); + mutex_unlock(&dsp->pwr_lock); + + return ret; - return cs_dsp_coeff_read_ctrl(cs_ctl, 0, buf, len); } EXPORT_SYMBOL_NS_GPL(hda_cs_dsp_read_ctl, SND_HDA_CS_DSP_CONTROLS); diff --git a/sound/pci/hda/hda_cs_dsp_ctl.h b/sound/pci/hda/hda_cs_dsp_ctl.h index 4babc69cf2f0..2cf93359c4f2 100644 --- a/sound/pci/hda/hda_cs_dsp_ctl.h +++ b/sound/pci/hda/hda_cs_dsp_ctl.h @@ -29,7 +29,7 @@ struct hda_cs_dsp_ctl_info { extern const char * const hda_cs_dsp_fw_ids[HDA_CS_DSP_NUM_FW]; -int hda_cs_dsp_control_add(struct cs_dsp_coeff_ctl *cs_ctl, struct hda_cs_dsp_ctl_info *info); +void hda_cs_dsp_add_controls(struct cs_dsp *dsp, const struct hda_cs_dsp_ctl_info *info); void hda_cs_dsp_control_remove(struct cs_dsp_coeff_ctl *cs_ctl); int hda_cs_dsp_write_ctl(struct cs_dsp *dsp, const char *name, int type, unsigned int alg, const void *buf, size_t len); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index bce82b834cec..e6c4bb5fa041 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -4022,22 +4022,16 @@ static void alc5505_dsp_init(struct hda_codec *codec) static int alc269_suspend(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - int i; if (spec->has_alc5505_dsp) alc5505_dsp_suspend(codec); - for (i = 0; i < HDA_MAX_COMPONENTS; i++) - if (spec->comps[i].suspend_hook) - spec->comps[i].suspend_hook(spec->comps[i].dev); - return alc_suspend(codec); } static int alc269_resume(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - int i; if (spec->codec_variant == ALC269_TYPE_ALC269VB) alc269vb_toggle_power_output(codec, 0); @@ -4068,10 +4062,6 @@ static int alc269_resume(struct hda_codec *codec) if (spec->has_alc5505_dsp) alc5505_dsp_resume(codec); - for (i = 0; i < HDA_MAX_COMPONENTS; i++) - if (spec->comps[i].resume_hook) - spec->comps[i].resume_hook(spec->comps[i].dev); - return 0; } #endif /* CONFIG_PM */ @@ -6664,19 +6654,12 @@ static int comp_bind(struct device *dev) { struct hda_codec *cdc = dev_to_hda_codec(dev); struct alc_spec *spec = cdc->spec; - int ret, i; + int ret; ret = component_bind_all(dev, spec->comps); if (ret) return ret; - if (snd_hdac_is_power_on(&cdc->core)) { - codec_dbg(cdc, "Resuming after bind.\n"); - for (i = 0; i < HDA_MAX_COMPONENTS; i++) - if (spec->comps[i].resume_hook) - spec->comps[i].resume_hook(spec->comps[i].dev); - } - return 0; } @@ -8449,11 +8432,13 @@ static const struct hda_fixup alc269_fixups[] = { [ALC285_FIXUP_ASUS_G533Z_PINS] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { - { 0x14, 0x90170120 }, + { 0x14, 0x90170152 }, /* Speaker Surround Playback Switch */ + { 0x19, 0x03a19020 }, /* Mic Boost Volume */ + { 0x1a, 0x03a11c30 }, /* Mic Boost Volume */ + { 0x1e, 0x90170151 }, /* Rear jack, IN OUT EAPD Detect */ + { 0x21, 0x03211420 }, { } }, - .chained = true, - .chain_id = ALC294_FIXUP_ASUS_G513_PINS, }, [ALC294_FIXUP_ASUS_COEF_1B] = { .type = HDA_FIXUP_VERBS, @@ -9198,7 +9183,6 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0871, "Dell Precision 3630", ALC255_FIXUP_DELL_HEADSET_MIC), SND_PCI_QUIRK(0x1028, 0x0872, "Dell Precision 3630", ALC255_FIXUP_DELL_HEADSET_MIC), SND_PCI_QUIRK(0x1028, 0x0873, "Dell Precision 3930", ALC255_FIXUP_DUMMY_LINEOUT_VERB), - SND_PCI_QUIRK(0x1028, 0x087d, "Dell Precision 5530", ALC289_FIXUP_DUAL_SPK), SND_PCI_QUIRK(0x1028, 0x08ad, "Dell WYSE AIO", ALC225_FIXUP_DELL_WYSE_AIO_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x08ae, "Dell WYSE NB", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0935, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB), @@ -9422,6 +9406,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1e8e, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1c52, "ASUS Zephyrus G15 2022", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401), + SND_PCI_QUIRK(0x1043, 0x1f92, "ASUS ROG Flow X16", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2), SND_PCI_QUIRK(0x1043, 0x831a, "ASUS P901", ALC269_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x1043, 0x834a, "ASUS S101", ALC269_FIXUP_STEREO_DMIC), @@ -9443,6 +9428,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x10ec, 0x10f2, "Intel Reference board", ALC700_FIXUP_INTEL_REFERENCE), SND_PCI_QUIRK(0x10ec, 0x118c, "Medion EE4254 MD62100", ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE), SND_PCI_QUIRK(0x10ec, 0x1230, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), + SND_PCI_QUIRK(0x10ec, 0x124c, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10ec, 0x1252, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10ec, 0x1254, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE), diff --git a/sound/usb/card.h b/sound/usb/card.h index ca75f2206170..40061550105a 100644 --- a/sound/usb/card.h +++ b/sound/usb/card.h @@ -129,7 +129,8 @@ struct snd_usb_endpoint { in a stream */ bool implicit_fb_sync; /* syncs with implicit feedback */ bool lowlatency_playback; /* low-latency playback mode */ - bool need_setup; /* (re-)need for configure? */ + bool need_setup; /* (re-)need for hw_params? */ + bool need_prepare; /* (re-)need for prepare? */ /* for hw constraints */ const struct audioformat *cur_audiofmt; diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c index 48a3843a08f1..d0b8d61d1d22 100644 --- a/sound/usb/endpoint.c +++ b/sound/usb/endpoint.c @@ -32,6 +32,7 @@ struct snd_usb_iface_ref { unsigned char iface; bool need_setup; int opened; + int altset; struct list_head list; }; @@ -823,6 +824,7 @@ snd_usb_endpoint_open(struct snd_usb_audio *chip, ep->implicit_fb_sync = fp->implicit_fb; ep->need_setup = true; + ep->need_prepare = true; usb_audio_dbg(chip, " channels=%d, rate=%d, format=%s, period_bytes=%d, periods=%d, implicit_fb=%d\n", ep->cur_channels, ep->cur_rate, @@ -899,6 +901,9 @@ static int endpoint_set_interface(struct snd_usb_audio *chip, int altset = set ? ep->altsetting : 0; int err; + if (ep->iface_ref->altset == altset) + return 0; + usb_audio_dbg(chip, "Setting usb interface %d:%d for EP 0x%x\n", ep->iface, altset, ep->ep_num); err = usb_set_interface(chip->dev, ep->iface, altset); @@ -910,6 +915,7 @@ static int endpoint_set_interface(struct snd_usb_audio *chip, if (chip->quirk_flags & QUIRK_FLAG_IFACE_DELAY) msleep(50); + ep->iface_ref->altset = altset; return 0; } @@ -947,7 +953,7 @@ void snd_usb_endpoint_close(struct snd_usb_audio *chip, /* Prepare for suspening EP, called from the main suspend handler */ void snd_usb_endpoint_suspend(struct snd_usb_endpoint *ep) { - ep->need_setup = true; + ep->need_prepare = true; if (ep->iface_ref) ep->iface_ref->need_setup = true; if (ep->clock_ref) @@ -1330,12 +1336,16 @@ int snd_usb_endpoint_set_params(struct snd_usb_audio *chip, struct snd_usb_endpoint *ep) { const struct audioformat *fmt = ep->cur_audiofmt; - int err; + int err = 0; + + mutex_lock(&chip->mutex); + if (!ep->need_setup) + goto unlock; /* release old buffers, if any */ err = release_urbs(ep, false); if (err < 0) - return err; + goto unlock; ep->datainterval = fmt->datainterval; ep->maxpacksize = fmt->maxpacksize; @@ -1373,13 +1383,21 @@ int snd_usb_endpoint_set_params(struct snd_usb_audio *chip, usb_audio_dbg(chip, "Set up %d URBS, ret=%d\n", ep->nurbs, err); if (err < 0) - return err; + goto unlock; /* some unit conversions in runtime */ ep->maxframesize = ep->maxpacksize / ep->cur_frame_bytes; ep->curframesize = ep->curpacksize / ep->cur_frame_bytes; - return update_clock_ref_rate(chip, ep); + err = update_clock_ref_rate(chip, ep); + if (err >= 0) { + ep->need_setup = false; + err = 0; + } + + unlock: + mutex_unlock(&chip->mutex); + return err; } static int init_sample_rate(struct snd_usb_audio *chip, @@ -1426,7 +1444,7 @@ int snd_usb_endpoint_prepare(struct snd_usb_audio *chip, mutex_lock(&chip->mutex); if (WARN_ON(!ep->iface_ref)) goto unlock; - if (!ep->need_setup) + if (!ep->need_prepare) goto unlock; /* If the interface has been already set up, just set EP parameters */ @@ -1480,7 +1498,7 @@ int snd_usb_endpoint_prepare(struct snd_usb_audio *chip, ep->iface_ref->need_setup = false; done: - ep->need_setup = false; + ep->need_prepare = false; err = 1; unlock: diff --git a/tools/testing/selftests/vm/hmm-tests.c b/tools/testing/selftests/vm/hmm-tests.c index 7d722265dcd7..4adaad1b822f 100644 --- a/tools/testing/selftests/vm/hmm-tests.c +++ b/tools/testing/selftests/vm/hmm-tests.c @@ -1054,6 +1054,55 @@ TEST_F(hmm, migrate_fault) hmm_buffer_free(buffer); } +TEST_F(hmm, migrate_release) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + unsigned long i; + int *ptr; + int ret; + + npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift; + ASSERT_NE(npages, 0); + size = npages << self->page_shift; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = -1; + buffer->size = size; + buffer->mirror = malloc(size); + ASSERT_NE(buffer->mirror, NULL); + + buffer->ptr = mmap(NULL, size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, buffer->fd, 0); + ASSERT_NE(buffer->ptr, MAP_FAILED); + + /* Initialize buffer in system memory. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Migrate memory to device. */ + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i); + + /* Release device memory. */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_RELEASE, buffer, npages); + ASSERT_EQ(ret, 0); + + /* Fault pages back to system memory and check them. */ + for (i = 0, ptr = buffer->ptr; i < size / (2 * sizeof(*ptr)); ++i) + ASSERT_EQ(ptr[i], i); + + hmm_buffer_free(buffer); +} + /* * Migrate anonymous shared memory to device private memory. */ diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index 74babdbc02e5..297f250c1d95 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -774,7 +774,27 @@ static void uffd_handle_page_fault(struct uffd_msg *msg, continue_range(uffd, msg->arg.pagefault.address, page_size); stats->minor_faults++; } else { - /* Missing page faults */ + /* + * Missing page faults. + * + * Here we force a write check for each of the missing mode + * faults. It's guaranteed because the only threads that + * will trigger uffd faults are the locking threads, and + * their first instruction to touch the missing page will + * always be pthread_mutex_lock(). + * + * Note that here we relied on an NPTL glibc impl detail to + * always read the lock type at the entry of the lock op + * (pthread_mutex_t.__data.__type, offset 0x10) before + * doing any locking operations to guarantee that. It's + * actually not good to rely on this impl detail because + * logically a pthread-compatible lib can implement the + * locks without types and we can fail when linking with + * them. However since we used to find bugs with this + * strict check we still keep it around. Hopefully this + * could be a good hint when it fails again. If one day + * it'll break on some other impl of glibc we'll revisit. + */ if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE) err("unexpected write fault");