diff --git a/Documentation/ABI/testing/sysfs-class-devlink b/Documentation/ABI/testing/sysfs-class-devlink index b662f747c83e..8a21ce515f61 100644 --- a/Documentation/ABI/testing/sysfs-class-devlink +++ b/Documentation/ABI/testing/sysfs-class-devlink @@ -5,8 +5,8 @@ Description: Provide a place in sysfs for the device link objects in the kernel at any given time. The name of a device link directory, denoted as ... above, is of the form -- - where is the supplier device name and is - the consumer device name. + where is the supplier bus:device name and + is the consumer bus:device name. What: /sys/class/devlink/.../auto_remove_on Date: May 2020 diff --git a/Documentation/ABI/testing/sysfs-devices-consumer b/Documentation/ABI/testing/sysfs-devices-consumer index 1f06d74d1c3c..0809fda092e6 100644 --- a/Documentation/ABI/testing/sysfs-devices-consumer +++ b/Documentation/ABI/testing/sysfs-devices-consumer @@ -4,5 +4,6 @@ Contact: Saravana Kannan Description: The /sys/devices/.../consumer: are symlinks to device links where this device is the supplier. denotes the - name of the consumer in that device link. There can be zero or - more of these symlinks for a given device. + name of the consumer in that device link and is of the form + bus:device name. There can be zero or more of these symlinks + for a given device. diff --git a/Documentation/ABI/testing/sysfs-devices-supplier b/Documentation/ABI/testing/sysfs-devices-supplier index a919e0db5e90..207f5972e98d 100644 --- a/Documentation/ABI/testing/sysfs-devices-supplier +++ b/Documentation/ABI/testing/sysfs-devices-supplier @@ -4,5 +4,6 @@ Contact: Saravana Kannan Description: The /sys/devices/.../supplier: are symlinks to device links where this device is the consumer. denotes the - name of the supplier in that device link. There can be zero or - more of these symlinks for a given device. + name of the supplier in that device link and is of the form + bus:device name. There can be zero or more of these symlinks + for a given device. diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst index 3e4310d0c6bd..40ab01e670db 100644 --- a/Documentation/dev-tools/kasan.rst +++ b/Documentation/dev-tools/kasan.rst @@ -160,29 +160,14 @@ intended for use in production as a security mitigation. Therefore it supports boot parameters that allow to disable KASAN competely or otherwise control particular KASAN features. -The things that can be controlled are: +- ``kasan=off`` or ``=on`` controls whether KASAN is enabled (default: ``on``). -1. Whether KASAN is enabled at all. -2. Whether KASAN collects and saves alloc/free stacks. -3. Whether KASAN panics on a detected bug or not. +- ``kasan.stacktrace=off`` or ``=on`` disables or enables alloc and free stack + traces collection (default: ``on`` for ``CONFIG_DEBUG_KERNEL=y``, otherwise + ``off``). -The ``kasan.mode`` boot parameter allows to choose one of three main modes: - -- ``kasan.mode=off`` - KASAN is disabled, no tag checks are performed -- ``kasan.mode=prod`` - only essential production features are enabled -- ``kasan.mode=full`` - all KASAN features are enabled - -The chosen mode provides default control values for the features mentioned -above. However it's also possible to override the default values by providing: - -- ``kasan.stacktrace=off`` or ``=on`` - enable alloc/free stack collection - (default: ``on`` for ``mode=full``, - otherwise ``off``) -- ``kasan.fault=report`` or ``=panic`` - only print KASAN report or also panic - (default: ``report``) - -If ``kasan.mode`` parameter is not provided, it defaults to ``full`` when -``CONFIG_DEBUG_KERNEL`` is enabled, and to ``prod`` otherwise. +- ``kasan.fault=report`` or ``=panic`` controls whether to only print a KASAN + report or also panic the kernel (default: ``report``). For developers ~~~~~~~~~~~~~~ diff --git a/Documentation/devicetree/bindings/iio/accel/bosch,bma255.yaml b/Documentation/devicetree/bindings/iio/accel/bosch,bma255.yaml index 6eef3480ea8f..c2efbb813ca2 100644 --- a/Documentation/devicetree/bindings/iio/accel/bosch,bma255.yaml +++ b/Documentation/devicetree/bindings/iio/accel/bosch,bma255.yaml @@ -16,8 +16,8 @@ description: properties: compatible: enum: - - bosch,bmc150 - - bosch,bmi055 + - bosch,bmc150_accel + - bosch,bmi055_accel - bosch,bma255 - bosch,bma250e - bosch,bma222 diff --git a/MAINTAINERS b/MAINTAINERS index b6c0feb03563..9347fb3220c6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3879,7 +3879,7 @@ F: Documentation/devicetree/bindings/mtd/cadence-nand-controller.txt F: drivers/mtd/nand/raw/cadence-nand-controller.c CADENCE USB3 DRD IP DRIVER -M: Peter Chen +M: Peter Chen M: Pawel Laszczak R: Roger Quadros R: Aswath Govindraju @@ -4161,7 +4161,7 @@ S: Maintained F: Documentation/translations/zh_CN/ CHIPIDEA USB HIGH SPEED DUAL ROLE CONTROLLER -M: Peter Chen +M: Peter Chen L: linux-usb@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/peter.chen/usb.git @@ -4311,7 +4311,9 @@ W: https://clangbuiltlinux.github.io/ B: https://github.com/ClangBuiltLinux/linux/issues C: irc://chat.freenode.net/clangbuiltlinux F: Documentation/kbuild/llvm.rst +F: include/linux/compiler-clang.h F: scripts/clang-tools/ +F: scripts/clang-version.sh F: scripts/lld-version.sh K: \b(?i:clang|llvm)\b @@ -18433,7 +18435,7 @@ F: Documentation/usb/ohci.rst F: drivers/usb/host/ohci* USB OTG FSM (Finite State Machine) -M: Peter Chen +M: Peter Chen L: linux-usb@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/peter.chen/usb.git diff --git a/Makefile b/Makefile index 10c95030393e..6f6c3d170ff7 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 11 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc5 NAME = Kleptomaniac Octopus # *DOCUMENTATION* diff --git a/arch/mips/include/asm/highmem.h b/arch/mips/include/asm/highmem.h index 19edf8e69971..292d0425717f 100644 --- a/arch/mips/include/asm/highmem.h +++ b/arch/mips/include/asm/highmem.h @@ -51,6 +51,7 @@ extern void kmap_flush_tlb(unsigned long addr); #define flush_cache_kmaps() BUG_ON(cpu_has_dc_aliases) +#define arch_kmap_local_set_pte(mm, vaddr, ptep, ptev) set_pte(ptep, ptev) #define arch_kmap_local_post_map(vaddr, pteval) local_flush_tlb_one(vaddr) #define arch_kmap_local_post_unmap(vaddr) local_flush_tlb_one(vaddr) diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 1d32b174ab6a..c1a8aac01cf9 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -63,6 +63,12 @@ nop; \ nop; +#define SCV_ENTRY_FLUSH_SLOT \ + SCV_ENTRY_FLUSH_FIXUP_SECTION; \ + nop; \ + nop; \ + nop; + /* * r10 must be free to use, r13 must be paca */ @@ -70,6 +76,13 @@ STF_ENTRY_BARRIER_SLOT; \ ENTRY_FLUSH_SLOT +/* + * r10, ctr must be free to use, r13 must be paca + */ +#define SCV_INTERRUPT_TO_KERNEL \ + STF_ENTRY_BARRIER_SLOT; \ + SCV_ENTRY_FLUSH_SLOT + /* * Macros for annotating the expected destination of (h)rfid * diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index f6d2acb57425..ac605fc369c4 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -240,6 +240,14 @@ label##3: \ FTR_ENTRY_OFFSET 957b-958b; \ .popsection; +#define SCV_ENTRY_FLUSH_FIXUP_SECTION \ +957: \ + .pushsection __scv_entry_flush_fixup,"a"; \ + .align 2; \ +958: \ + FTR_ENTRY_OFFSET 957b-958b; \ + .popsection; + #define RFI_FLUSH_FIXUP_SECTION \ 951: \ .pushsection __rfi_flush_fixup,"a"; \ @@ -273,10 +281,12 @@ label##3: \ extern long stf_barrier_fallback; extern long entry_flush_fallback; +extern long scv_entry_flush_fallback; extern long __start___stf_entry_barrier_fixup, __stop___stf_entry_barrier_fixup; extern long __start___stf_exit_barrier_fixup, __stop___stf_exit_barrier_fixup; extern long __start___uaccess_flush_fixup, __stop___uaccess_flush_fixup; extern long __start___entry_flush_fixup, __stop___entry_flush_fixup; +extern long __start___scv_entry_flush_fixup, __stop___scv_entry_flush_fixup; extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup; extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup; extern long __start__btb_flush_fixup, __stop__btb_flush_fixup; diff --git a/arch/powerpc/include/asm/highmem.h b/arch/powerpc/include/asm/highmem.h index 80a5ae771c65..c0fcd1bbdba9 100644 --- a/arch/powerpc/include/asm/highmem.h +++ b/arch/powerpc/include/asm/highmem.h @@ -58,6 +58,8 @@ extern pte_t *pkmap_page_table; #define flush_cache_kmaps() flush_cache_all() +#define arch_kmap_local_set_pte(mm, vaddr, ptep, ptev) \ + __set_pte_at(mm, vaddr, ptep, ptev, 1) #define arch_kmap_local_post_map(vaddr, pteval) \ local_flush_tlb_page(NULL, vaddr) #define arch_kmap_local_post_unmap(vaddr) \ diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index aa1af139d947..33ddfeef4fe9 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -75,7 +75,7 @@ BEGIN_FTR_SECTION bne .Ltabort_syscall END_FTR_SECTION_IFSET(CPU_FTR_TM) #endif - INTERRUPT_TO_KERNEL + SCV_INTERRUPT_TO_KERNEL mr r10,r1 ld r1,PACAKSAVE(r13) std r10,0(r1) diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index e02ad6fefa46..6e53f7638737 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -2993,6 +2993,25 @@ TRAMP_REAL_BEGIN(entry_flush_fallback) ld r11,PACA_EXRFI+EX_R11(r13) blr +/* + * The SCV entry flush happens with interrupts enabled, so it must disable + * to prevent EXRFI being clobbered by NMIs (e.g., soft_nmi_common). r10 + * (containing LR) does not need to be preserved here because scv entry + * puts 0 in the pt_regs, CTR can be clobbered for the same reason. + */ +TRAMP_REAL_BEGIN(scv_entry_flush_fallback) + li r10,0 + mtmsrd r10,1 + lbz r10,PACAIRQHAPPENED(r13) + ori r10,r10,PACA_IRQ_HARD_DIS + stb r10,PACAIRQHAPPENED(r13) + std r11,PACA_EXRFI+EX_R11(r13) + L1D_DISPLACEMENT_FLUSH + ld r11,PACA_EXRFI+EX_R11(r13) + li r10,MSR_RI + mtmsrd r10,1 + blr + TRAMP_REAL_BEGIN(rfi_flush_fallback) SET_SCRATCH0(r13); GET_PACA(r13); diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 83281aee14d2..4a1f494ef03f 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -145,6 +145,13 @@ SECTIONS __stop___entry_flush_fixup = .; } + . = ALIGN(8); + __scv_entry_flush_fixup : AT(ADDR(__scv_entry_flush_fixup) - LOAD_OFFSET) { + __start___scv_entry_flush_fixup = .; + *(__scv_entry_flush_fixup) + __stop___scv_entry_flush_fixup = .; + } + . = ALIGN(8); __stf_exit_barrier_fixup : AT(ADDR(__stf_exit_barrier_fixup) - LOAD_OFFSET) { __start___stf_exit_barrier_fixup = .; diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index 47821055b94c..1fd31b4b0e13 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -290,9 +290,6 @@ void do_entry_flush_fixups(enum l1d_flush_type types) long *start, *end; int i; - start = PTRRELOC(&__start___entry_flush_fixup); - end = PTRRELOC(&__stop___entry_flush_fixup); - instrs[0] = 0x60000000; /* nop */ instrs[1] = 0x60000000; /* nop */ instrs[2] = 0x60000000; /* nop */ @@ -312,6 +309,8 @@ void do_entry_flush_fixups(enum l1d_flush_type types) if (types & L1D_FLUSH_MTTRIG) instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */ + start = PTRRELOC(&__start___entry_flush_fixup); + end = PTRRELOC(&__stop___entry_flush_fixup); for (i = 0; start < end; start++, i++) { dest = (void *)start + *start; @@ -328,6 +327,25 @@ void do_entry_flush_fixups(enum l1d_flush_type types) patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); } + start = PTRRELOC(&__start___scv_entry_flush_fixup); + end = PTRRELOC(&__stop___scv_entry_flush_fixup); + for (; start < end; start++, i++) { + dest = (void *)start + *start; + + pr_devel("patching dest %lx\n", (unsigned long)dest); + + patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); + + if (types == L1D_FLUSH_FALLBACK) + patch_branch((struct ppc_inst *)(dest + 1), (unsigned long)&scv_entry_flush_fallback, + BRANCH_SET_LINK); + else + patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1])); + + patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + } + + printk(KERN_DEBUG "entry-flush: patched %d locations (%s flush)\n", i, (types == L1D_FLUSH_NONE) ? "no" : (types == L1D_FLUSH_FALLBACK) ? "fallback displacement" : diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 5fa580219a86..52646f52f130 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -29,7 +29,6 @@ config SUPERH select HAVE_ARCH_KGDB select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK - select HAVE_COPY_THREAD_TLS select HAVE_DEBUG_BUGVERBOSE select HAVE_DEBUG_KMEMLEAK select HAVE_DYNAMIC_FTRACE diff --git a/arch/sh/boards/mach-sh03/rtc.c b/arch/sh/boards/mach-sh03/rtc.c index 8b23ed7c201c..7fb474844a2d 100644 --- a/arch/sh/boards/mach-sh03/rtc.c +++ b/arch/sh/boards/mach-sh03/rtc.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/sh/configs/landisk_defconfig b/arch/sh/configs/landisk_defconfig index ba6ec042606f..e6c5ddf070c0 100644 --- a/arch/sh/configs/landisk_defconfig +++ b/arch/sh/configs/landisk_defconfig @@ -27,13 +27,12 @@ CONFIG_NETFILTER=y CONFIG_ATALK=m CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y -CONFIG_IDE=y -CONFIG_BLK_DEV_IDECD=y -CONFIG_BLK_DEV_OFFBOARD=y -CONFIG_BLK_DEV_GENERIC=y -CONFIG_BLK_DEV_AEC62XX=y +CONFIG_ATA=y +CONFIG_ATA_GENERIC=y +CONFIG_PATA_ATP867X=y CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y +CONFIG_BLK_DEV_SR=y CONFIG_SCSI_MULTI_LUN=y CONFIG_MD=y CONFIG_BLK_DEV_MD=m diff --git a/arch/sh/configs/microdev_defconfig b/arch/sh/configs/microdev_defconfig index c65667d00313..e9825196dd66 100644 --- a/arch/sh/configs/microdev_defconfig +++ b/arch/sh/configs/microdev_defconfig @@ -20,8 +20,6 @@ CONFIG_IP_PNP=y # CONFIG_IPV6 is not set # CONFIG_FW_LOADER is not set CONFIG_BLK_DEV_RAM=y -CONFIG_IDE=y -CONFIG_BLK_DEV_IDECD=y CONFIG_NETDEVICES=y CONFIG_NET_ETHERNET=y CONFIG_SMC91X=y diff --git a/arch/sh/configs/sdk7780_defconfig b/arch/sh/configs/sdk7780_defconfig index d10a0414123a..d00376eb044f 100644 --- a/arch/sh/configs/sdk7780_defconfig +++ b/arch/sh/configs/sdk7780_defconfig @@ -44,16 +44,14 @@ CONFIG_NET_SCHED=y CONFIG_PARPORT=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y -CONFIG_IDE=y -CONFIG_BLK_DEV_IDECD=y -CONFIG_BLK_DEV_PLATFORM=y -CONFIG_BLK_DEV_GENERIC=y CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_SPI_ATTRS=y CONFIG_SCSI_FC_ATTRS=y CONFIG_ATA=y +CONFIG_ATA_GENERIC=y +CONFIG_PATA_PLATFORM=y CONFIG_MD=y CONFIG_BLK_DEV_DM=y CONFIG_NETDEVICES=y diff --git a/arch/sh/configs/sdk7786_defconfig b/arch/sh/configs/sdk7786_defconfig index 61bec46ebd66..4a44cac640bc 100644 --- a/arch/sh/configs/sdk7786_defconfig +++ b/arch/sh/configs/sdk7786_defconfig @@ -116,9 +116,6 @@ CONFIG_MTD_UBI_GLUEBI=m CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_CRYPTOLOOP=y CONFIG_BLK_DEV_RAM=y -CONFIG_IDE=y -CONFIG_BLK_DEV_IDECD=y -CONFIG_BLK_DEV_PLATFORM=y CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y CONFIG_SCSI_MULTI_LUN=y diff --git a/arch/sh/configs/se7750_defconfig b/arch/sh/configs/se7750_defconfig index 3f1c13799d79..4defc7628a49 100644 --- a/arch/sh/configs/se7750_defconfig +++ b/arch/sh/configs/se7750_defconfig @@ -29,7 +29,6 @@ CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_AMDSTD=y CONFIG_MTD_ROM=y -CONFIG_IDE=y CONFIG_SCSI=y CONFIG_NETDEVICES=y CONFIG_NET_ETHERNET=y diff --git a/arch/sh/configs/sh03_defconfig b/arch/sh/configs/sh03_defconfig index f0073ed39947..48b457d59e79 100644 --- a/arch/sh/configs/sh03_defconfig +++ b/arch/sh/configs/sh03_defconfig @@ -39,9 +39,6 @@ CONFIG_IP_PNP_RARP=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_NBD=y CONFIG_BLK_DEV_RAM=y -CONFIG_IDE=y -CONFIG_BLK_DEV_IDECD=m -CONFIG_BLK_DEV_IDETAPE=m CONFIG_SCSI=m CONFIG_BLK_DEV_SD=m CONFIG_BLK_DEV_SR=m diff --git a/arch/sh/drivers/dma/Kconfig b/arch/sh/drivers/dma/Kconfig index d0de378beefe..7d54f284ce10 100644 --- a/arch/sh/drivers/dma/Kconfig +++ b/arch/sh/drivers/dma/Kconfig @@ -63,8 +63,7 @@ config PVR2_DMA config G2_DMA tristate "G2 Bus DMA support" - depends on SH_DREAMCAST - select SH_DMA_API + depends on SH_DREAMCAST && SH_DMA_API help This enables support for the DMA controller for the Dreamcast's G2 bus. Drivers that want this will generally enable this on diff --git a/arch/sh/include/asm/gpio.h b/arch/sh/include/asm/gpio.h index 351918894e86..d643250f0a0f 100644 --- a/arch/sh/include/asm/gpio.h +++ b/arch/sh/include/asm/gpio.h @@ -16,7 +16,6 @@ #include #endif -#define ARCH_NR_GPIOS 512 #include #ifdef CONFIG_GPIOLIB diff --git a/arch/sh/kernel/cpu/sh3/entry.S b/arch/sh/kernel/cpu/sh3/entry.S index 25eb80905416..e48b3dd996f5 100644 --- a/arch/sh/kernel/cpu/sh3/entry.S +++ b/arch/sh/kernel/cpu/sh3/entry.S @@ -14,7 +14,6 @@ #include #include #include -#include ! NOTE: ! GNU as (as of 2.9.1) changes bf/s into bt/s and bra, when the address diff --git a/arch/sh/mm/Kconfig b/arch/sh/mm/Kconfig index 703d3069997c..77aa2f802d8d 100644 --- a/arch/sh/mm/Kconfig +++ b/arch/sh/mm/Kconfig @@ -105,7 +105,7 @@ config VSYSCALL (the default value) say Y. config NUMA - bool "Non Uniform Memory Access (NUMA) Support" + bool "Non-Uniform Memory Access (NUMA) Support" depends on MMU && SYS_SUPPORTS_NUMA select ARCH_WANT_NUMA_VARIABLE_LOCALITY default n diff --git a/arch/sh/mm/asids-debugfs.c b/arch/sh/mm/asids-debugfs.c index 4c1ca197e9c5..d16d6f5ec774 100644 --- a/arch/sh/mm/asids-debugfs.c +++ b/arch/sh/mm/asids-debugfs.c @@ -26,7 +26,7 @@ #include #include -static int asids_seq_show(struct seq_file *file, void *iter) +static int asids_debugfs_show(struct seq_file *file, void *iter) { struct task_struct *p; @@ -48,18 +48,7 @@ static int asids_seq_show(struct seq_file *file, void *iter) return 0; } -static int asids_debugfs_open(struct inode *inode, struct file *file) -{ - return single_open(file, asids_seq_show, inode->i_private); -} - -static const struct file_operations asids_debugfs_fops = { - .owner = THIS_MODULE, - .open = asids_debugfs_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(asids_debugfs); static int __init asids_debugfs_init(void) { diff --git a/arch/sh/mm/cache-debugfs.c b/arch/sh/mm/cache-debugfs.c index 17d780794497..b0f185169dfa 100644 --- a/arch/sh/mm/cache-debugfs.c +++ b/arch/sh/mm/cache-debugfs.c @@ -22,7 +22,7 @@ enum cache_type { CACHE_TYPE_UNIFIED, }; -static int cache_seq_show(struct seq_file *file, void *iter) +static int cache_debugfs_show(struct seq_file *file, void *iter) { unsigned int cache_type = (unsigned int)file->private; struct cache_info *cache; @@ -94,18 +94,7 @@ static int cache_seq_show(struct seq_file *file, void *iter) return 0; } -static int cache_debugfs_open(struct inode *inode, struct file *file) -{ - return single_open(file, cache_seq_show, inode->i_private); -} - -static const struct file_operations cache_debugfs_fops = { - .owner = THIS_MODULE, - .open = cache_debugfs_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(cache_debugfs); static int __init cache_debugfs_init(void) { diff --git a/arch/sh/mm/pmb.c b/arch/sh/mm/pmb.c index b20aba6e1b37..68eb7cc6e564 100644 --- a/arch/sh/mm/pmb.c +++ b/arch/sh/mm/pmb.c @@ -812,7 +812,7 @@ bool __in_29bit_mode(void) return (__raw_readl(PMB_PASCR) & PASCR_SE) == 0; } -static int pmb_seq_show(struct seq_file *file, void *iter) +static int pmb_debugfs_show(struct seq_file *file, void *iter) { int i; @@ -846,18 +846,7 @@ static int pmb_seq_show(struct seq_file *file, void *iter) return 0; } -static int pmb_debugfs_open(struct inode *inode, struct file *file) -{ - return single_open(file, pmb_seq_show, NULL); -} - -static const struct file_operations pmb_debugfs_fops = { - .owner = THIS_MODULE, - .open = pmb_debugfs_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(pmb_debugfs); static int __init pmb_debugfs_init(void) { diff --git a/arch/sparc/include/asm/highmem.h b/arch/sparc/include/asm/highmem.h index 875116209ec1..c7b2e208328b 100644 --- a/arch/sparc/include/asm/highmem.h +++ b/arch/sparc/include/asm/highmem.h @@ -50,10 +50,11 @@ extern pte_t *pkmap_page_table; #define flush_cache_kmaps() flush_cache_all() -/* FIXME: Use __flush_tlb_one(vaddr) instead of flush_cache_all() -- Anton */ -#define arch_kmap_local_post_map(vaddr, pteval) flush_cache_all() -#define arch_kmap_local_post_unmap(vaddr) flush_cache_all() - +/* FIXME: Use __flush_*_one(vaddr) instead of flush_*_all() -- Anton */ +#define arch_kmap_local_pre_map(vaddr, pteval) flush_cache_all() +#define arch_kmap_local_pre_unmap(vaddr) flush_cache_all() +#define arch_kmap_local_post_map(vaddr, pteval) flush_tlb_all() +#define arch_kmap_local_post_unmap(vaddr) flush_tlb_all() #endif /* __KERNEL__ */ diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 18d8f17f755c..0904f5676e4d 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -73,10 +73,8 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, unsigned int nr) { if (likely(nr < IA32_NR_syscalls)) { - instrumentation_begin(); nr = array_index_nospec(nr, IA32_NR_syscalls); regs->ax = ia32_sys_call_table[nr](regs); - instrumentation_end(); } } @@ -91,8 +89,11 @@ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs) * or may not be necessary, but it matches the old asm behavior. */ nr = (unsigned int)syscall_enter_from_user_mode(regs, nr); + instrumentation_begin(); do_syscall_32_irqs_on(regs, nr); + + instrumentation_end(); syscall_exit_to_user_mode(regs); } @@ -121,11 +122,12 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs) res = get_user(*(u32 *)®s->bp, (u32 __user __force *)(unsigned long)(u32)regs->sp); } - instrumentation_end(); if (res) { /* User code screwed up. */ regs->ax = -EFAULT; + + instrumentation_end(); syscall_exit_to_user_mode(regs); return false; } @@ -135,6 +137,8 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs) /* Now this is just like a normal syscall. */ do_syscall_32_irqs_on(regs, nr); + + instrumentation_end(); syscall_exit_to_user_mode(regs); return true; } diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index a5aba4ab0224..67a4f1cb2aac 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -16,14 +16,25 @@ * Use kernel_fpu_begin/end() if you intend to use FPU in kernel context. It * disables preemption so be careful if you intend to use it for long periods * of time. - * If you intend to use the FPU in softirq you need to check first with + * If you intend to use the FPU in irq/softirq you need to check first with * irq_fpu_usable() if it is possible. */ -extern void kernel_fpu_begin(void); + +/* Kernel FPU states to initialize in kernel_fpu_begin_mask() */ +#define KFPU_387 _BITUL(0) /* 387 state will be initialized */ +#define KFPU_MXCSR _BITUL(1) /* MXCSR will be initialized */ + +extern void kernel_fpu_begin_mask(unsigned int kfpu_mask); extern void kernel_fpu_end(void); extern bool irq_fpu_usable(void); extern void fpregs_mark_activate(void); +/* Code that is unaware of kernel_fpu_begin_mask() can use this */ +static inline void kernel_fpu_begin(void) +{ + kernel_fpu_begin_mask(KFPU_387 | KFPU_MXCSR); +} + /* * Use fpregs_lock() while editing CPU's FPU registers or fpu->state. * A context switch will (and softirq might) save CPU's FPU registers to diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 5e658ba2654a..9abe842dbd84 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -97,6 +97,7 @@ #define INTEL_FAM6_LAKEFIELD 0x8A #define INTEL_FAM6_ALDERLAKE 0x97 +#define INTEL_FAM6_ALDERLAKE_L 0x9A /* "Small Core" Processors (Atom) */ diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 0b4920a7238e..e16cccdd0420 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -86,7 +86,7 @@ static inline void do_trace_rdpmc(unsigned int msr, u64 val, int failed) {} * think of extending them - you will be slapped with a stinking trout or a frozen * shark will reach you, wherever you are! You've been warned. */ -static inline unsigned long long notrace __rdmsr(unsigned int msr) +static __always_inline unsigned long long __rdmsr(unsigned int msr) { DECLARE_ARGS(val, low, high); @@ -98,7 +98,7 @@ static inline unsigned long long notrace __rdmsr(unsigned int msr) return EAX_EDX_VAL(val, low, high); } -static inline void notrace __wrmsr(unsigned int msr, u32 low, u32 high) +static __always_inline void __wrmsr(unsigned int msr, u32 low, u32 high) { asm volatile("1: wrmsr\n" "2:\n" diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 488a8e848754..9239399e5491 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -110,6 +110,8 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu); #define topology_die_id(cpu) (cpu_data(cpu).cpu_die_id) #define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id) +extern unsigned int __max_die_per_package; + #ifdef CONFIG_SMP #define topology_die_cpumask(cpu) (per_cpu(cpu_die_map, cpu)) #define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) @@ -118,8 +120,6 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu); extern unsigned int __max_logical_packages; #define topology_max_packages() (__max_logical_packages) -extern unsigned int __max_die_per_package; - static inline int topology_max_die_per_package(void) { return __max_die_per_package; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index f8ca66f3d861..347a956f71ca 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -542,12 +542,12 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) u32 ecx; ecx = cpuid_ecx(0x8000001e); - nodes_per_socket = ((ecx >> 8) & 7) + 1; + __max_die_per_package = nodes_per_socket = ((ecx >> 8) & 7) + 1; } else if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) { u64 value; rdmsrl(MSR_FAM10H_NODE_ID, value); - nodes_per_socket = ((value >> 3) & 7) + 1; + __max_die_per_package = nodes_per_socket = ((value >> 3) & 7) + 1; } if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) && diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 13d3f1cbda17..e133ce1e562b 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1992,10 +1992,9 @@ static __always_inline void exc_machine_check_kernel(struct pt_regs *regs) * that out because it's an indirect call. Annotate it. */ instrumentation_begin(); - trace_hardirqs_off_finish(); + machine_check_vector(regs); - if (regs->flags & X86_EFLAGS_IF) - trace_hardirqs_on_prepare(); + instrumentation_end(); irqentry_nmi_exit(regs, irq_state); } @@ -2004,7 +2003,9 @@ static __always_inline void exc_machine_check_user(struct pt_regs *regs) { irqentry_enter_from_user_mode(regs); instrumentation_begin(); + machine_check_vector(regs); + instrumentation_end(); irqentry_exit_to_user_mode(regs); } diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index 1068002c8532..8678864ce712 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -25,10 +25,10 @@ #define BITS_SHIFT_NEXT_LEVEL(eax) ((eax) & 0x1f) #define LEVEL_MAX_SIBLINGS(ebx) ((ebx) & 0xffff) -#ifdef CONFIG_SMP unsigned int __max_die_per_package __read_mostly = 1; EXPORT_SYMBOL(__max_die_per_package); +#ifdef CONFIG_SMP /* * Check if given CPUID extended toplogy "leaf" is implemented */ diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index eb86a2b831b1..571220ac8bea 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -121,7 +121,7 @@ int copy_fpregs_to_fpstate(struct fpu *fpu) } EXPORT_SYMBOL(copy_fpregs_to_fpstate); -void kernel_fpu_begin(void) +void kernel_fpu_begin_mask(unsigned int kfpu_mask) { preempt_disable(); @@ -141,13 +141,14 @@ void kernel_fpu_begin(void) } __cpu_invalidate_fpregs_state(); - if (boot_cpu_has(X86_FEATURE_XMM)) + /* Put sane initial values into the control registers. */ + if (likely(kfpu_mask & KFPU_MXCSR) && boot_cpu_has(X86_FEATURE_XMM)) ldmxcsr(MXCSR_DEFAULT); - if (boot_cpu_has(X86_FEATURE_FPU)) + if (unlikely(kfpu_mask & KFPU_387) && boot_cpu_has(X86_FEATURE_FPU)) asm volatile ("fninit"); } -EXPORT_SYMBOL_GPL(kernel_fpu_begin); +EXPORT_SYMBOL_GPL(kernel_fpu_begin_mask); void kernel_fpu_end(void) { diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 740f3bdb3f61..3412c4595efd 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -660,17 +660,6 @@ static void __init trim_platform_memory_ranges(void) static void __init trim_bios_range(void) { - /* - * A special case is the first 4Kb of memory; - * This is a BIOS owned area, not kernel ram, but generally - * not listed as such in the E820 table. - * - * This typically reserves additional memory (64KiB by default) - * since some BIOSes are known to corrupt low memory. See the - * Kconfig help text for X86_RESERVE_LOW. - */ - e820__range_update(0, PAGE_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED); - /* * special case: Some BIOSes report the PC BIOS * area (640Kb -> 1Mb) as RAM even though it is not. @@ -728,6 +717,15 @@ early_param("reservelow", parse_reservelow); static void __init trim_low_memory_range(void) { + /* + * A special case is the first 4Kb of memory; + * This is a BIOS owned area, not kernel ram, but generally + * not listed as such in the E820 table. + * + * This typically reserves additional memory (64KiB by default) + * since some BIOSes are known to corrupt low memory. See the + * Kconfig help text for X86_RESERVE_LOW. + */ memblock_reserve(0, ALIGN(reserve_low, PAGE_SIZE)); } diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 0bd1a0fc587e..84c1821819af 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -225,7 +225,7 @@ static inline u64 sev_es_rd_ghcb_msr(void) return __rdmsr(MSR_AMD64_SEV_ES_GHCB); } -static inline void sev_es_wr_ghcb_msr(u64 val) +static __always_inline void sev_es_wr_ghcb_msr(u64 val) { u32 low, high; @@ -286,6 +286,12 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt, u16 d2; u8 d1; + /* If instruction ran in kernel mode and the I/O buffer is in kernel space */ + if (!user_mode(ctxt->regs) && !access_ok(target, size)) { + memcpy(dst, buf, size); + return ES_OK; + } + switch (size) { case 1: memcpy(&d1, buf, 1); @@ -335,6 +341,12 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, u16 d2; u8 d1; + /* If instruction ran in kernel mode and the I/O buffer is in kernel space */ + if (!user_mode(ctxt->regs) && !access_ok(s, size)) { + memcpy(buf, src, size); + return ES_OK; + } + switch (size) { case 1: if (get_user(d1, s)) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 8ca66af96a54..117e24fbfd8a 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -56,6 +56,7 @@ #include #include #include +#include #include #include @@ -2083,6 +2084,23 @@ static void init_counter_refs(void) this_cpu_write(arch_prev_mperf, mperf); } +#ifdef CONFIG_PM_SLEEP +static struct syscore_ops freq_invariance_syscore_ops = { + .resume = init_counter_refs, +}; + +static void register_freq_invariance_syscore_ops(void) +{ + /* Bail out if registered already. */ + if (freq_invariance_syscore_ops.node.prev) + return; + + register_syscore_ops(&freq_invariance_syscore_ops); +} +#else +static inline void register_freq_invariance_syscore_ops(void) {} +#endif + static void init_freq_invariance(bool secondary, bool cppc_ready) { bool ret = false; @@ -2109,6 +2127,7 @@ static void init_freq_invariance(bool secondary, bool cppc_ready) if (ret) { init_counter_refs(); static_branch_enable(&arch_scale_freq_key); + register_freq_invariance_syscore_ops(); pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio); } else { pr_debug("Couldn't determine max cpu frequency, necessary for scale-invariant accounting.\n"); diff --git a/arch/x86/lib/mmx_32.c b/arch/x86/lib/mmx_32.c index 4321fa02e18d..419365c48b2a 100644 --- a/arch/x86/lib/mmx_32.c +++ b/arch/x86/lib/mmx_32.c @@ -26,6 +26,16 @@ #include #include +/* + * Use KFPU_387. MMX instructions are not affected by MXCSR, + * but both AMD and Intel documentation states that even integer MMX + * operations will result in #MF if an exception is pending in FCW. + * + * EMMS is not needed afterwards because, after calling kernel_fpu_end(), + * any subsequent user of the 387 stack will reinitialize it using + * KFPU_387. + */ + void *_mmx_memcpy(void *to, const void *from, size_t len) { void *p; @@ -37,7 +47,7 @@ void *_mmx_memcpy(void *to, const void *from, size_t len) p = to; i = len >> 6; /* len/64 */ - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); __asm__ __volatile__ ( "1: prefetch (%0)\n" /* This set is 28 bytes */ @@ -127,7 +137,7 @@ static void fast_clear_page(void *page) { int i; - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); __asm__ __volatile__ ( " pxor %%mm0, %%mm0\n" : : @@ -160,7 +170,7 @@ static void fast_copy_page(void *to, void *from) { int i; - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); /* * maybe the prefetch stuff can go before the expensive fnsave... @@ -247,7 +257,7 @@ static void fast_clear_page(void *page) { int i; - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); __asm__ __volatile__ ( " pxor %%mm0, %%mm0\n" : : @@ -282,7 +292,7 @@ static void fast_copy_page(void *to, void *from) { int i; - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); __asm__ __volatile__ ( "1: prefetch (%0)\n" diff --git a/drivers/base/core.c b/drivers/base/core.c index ef051bec51eb..113859cb8565 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -208,6 +208,16 @@ int device_links_read_lock_held(void) #endif #endif /* !CONFIG_SRCU */ +static bool device_is_ancestor(struct device *dev, struct device *target) +{ + while (target->parent) { + target = target->parent; + if (dev == target) + return true; + } + return false; +} + /** * device_is_dependent - Check if one device depends on another one * @dev: Device to check dependencies for. @@ -221,7 +231,12 @@ int device_is_dependent(struct device *dev, void *target) struct device_link *link; int ret; - if (dev == target) + /* + * The "ancestors" check is needed to catch the case when the target + * device has not been completely initialized yet and it is still + * missing from the list of children of its parent device. + */ + if (dev == target || device_is_ancestor(dev, target)) return 1; ret = device_for_each_child(dev, target, device_is_dependent); @@ -456,7 +471,9 @@ static int devlink_add_symlinks(struct device *dev, struct device *con = link->consumer; char *buf; - len = max(strlen(dev_name(sup)), strlen(dev_name(con))); + len = max(strlen(dev_bus_name(sup)) + strlen(dev_name(sup)), + strlen(dev_bus_name(con)) + strlen(dev_name(con))); + len += strlen(":"); len += strlen("supplier:") + 1; buf = kzalloc(len, GFP_KERNEL); if (!buf) @@ -470,12 +487,12 @@ static int devlink_add_symlinks(struct device *dev, if (ret) goto err_con; - snprintf(buf, len, "consumer:%s", dev_name(con)); + snprintf(buf, len, "consumer:%s:%s", dev_bus_name(con), dev_name(con)); ret = sysfs_create_link(&sup->kobj, &link->link_dev.kobj, buf); if (ret) goto err_con_dev; - snprintf(buf, len, "supplier:%s", dev_name(sup)); + snprintf(buf, len, "supplier:%s:%s", dev_bus_name(sup), dev_name(sup)); ret = sysfs_create_link(&con->kobj, &link->link_dev.kobj, buf); if (ret) goto err_sup_dev; @@ -483,7 +500,7 @@ static int devlink_add_symlinks(struct device *dev, goto out; err_sup_dev: - snprintf(buf, len, "consumer:%s", dev_name(con)); + snprintf(buf, len, "consumer:%s:%s", dev_bus_name(con), dev_name(con)); sysfs_remove_link(&sup->kobj, buf); err_con_dev: sysfs_remove_link(&link->link_dev.kobj, "consumer"); @@ -506,7 +523,9 @@ static void devlink_remove_symlinks(struct device *dev, sysfs_remove_link(&link->link_dev.kobj, "consumer"); sysfs_remove_link(&link->link_dev.kobj, "supplier"); - len = max(strlen(dev_name(sup)), strlen(dev_name(con))); + len = max(strlen(dev_bus_name(sup)) + strlen(dev_name(sup)), + strlen(dev_bus_name(con)) + strlen(dev_name(con))); + len += strlen(":"); len += strlen("supplier:") + 1; buf = kzalloc(len, GFP_KERNEL); if (!buf) { @@ -514,9 +533,9 @@ static void devlink_remove_symlinks(struct device *dev, return; } - snprintf(buf, len, "supplier:%s", dev_name(sup)); + snprintf(buf, len, "supplier:%s:%s", dev_bus_name(sup), dev_name(sup)); sysfs_remove_link(&con->kobj, buf); - snprintf(buf, len, "consumer:%s", dev_name(con)); + snprintf(buf, len, "consumer:%s:%s", dev_bus_name(con), dev_name(con)); sysfs_remove_link(&sup->kobj, buf); kfree(buf); } @@ -737,8 +756,9 @@ struct device_link *device_link_add(struct device *consumer, link->link_dev.class = &devlink_class; device_set_pm_not_required(&link->link_dev); - dev_set_name(&link->link_dev, "%s--%s", - dev_name(supplier), dev_name(consumer)); + dev_set_name(&link->link_dev, "%s:%s--%s:%s", + dev_bus_name(supplier), dev_name(supplier), + dev_bus_name(consumer), dev_name(consumer)); if (device_register(&link->link_dev)) { put_device(consumer); put_device(supplier); @@ -1808,9 +1828,7 @@ const char *dev_driver_string(const struct device *dev) * never change once they are set, so they don't need special care. */ drv = READ_ONCE(dev->driver); - return drv ? drv->name : - (dev->bus ? dev->bus->name : - (dev->class ? dev->class->name : "")); + return drv ? drv->name : dev_bus_name(dev); } EXPORT_SYMBOL(dev_driver_string); diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 2f32f38a11ed..9179825ff646 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -370,13 +370,6 @@ static void driver_bound(struct device *dev) device_pm_check_callbacks(dev); - /* - * Reorder successfully probed devices to the end of the device list. - * This ensures that suspend/resume order matches probe order, which - * is usually what drivers rely on. - */ - device_pm_move_to_tail(dev); - /* * Make sure the device is no longer in one of the deferred lists and * kick off retrying all pending devices @@ -619,6 +612,8 @@ static int really_probe(struct device *dev, struct device_driver *drv) else if (drv->remove) drv->remove(dev); probe_failed: + kfree(dev->dma_range_map); + dev->dma_range_map = NULL; if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_DRIVER_NOT_BOUND, dev); diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 95fd1549f87d..8456d8384ac8 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -366,6 +366,8 @@ int devm_platform_get_irqs_affinity(struct platform_device *dev, return -ERANGE; nvec = platform_irq_count(dev); + if (nvec < 0) + return nvec; if (nvec < minvec) return -ENOSPC; diff --git a/drivers/counter/ti-eqep.c b/drivers/counter/ti-eqep.c index a60aee1a1a29..65df9ef5b5bc 100644 --- a/drivers/counter/ti-eqep.c +++ b/drivers/counter/ti-eqep.c @@ -235,36 +235,6 @@ static ssize_t ti_eqep_position_ceiling_write(struct counter_device *counter, return len; } -static ssize_t ti_eqep_position_floor_read(struct counter_device *counter, - struct counter_count *count, - void *ext_priv, char *buf) -{ - struct ti_eqep_cnt *priv = counter->priv; - u32 qposinit; - - regmap_read(priv->regmap32, QPOSINIT, &qposinit); - - return sprintf(buf, "%u\n", qposinit); -} - -static ssize_t ti_eqep_position_floor_write(struct counter_device *counter, - struct counter_count *count, - void *ext_priv, const char *buf, - size_t len) -{ - struct ti_eqep_cnt *priv = counter->priv; - int err; - u32 res; - - err = kstrtouint(buf, 0, &res); - if (err < 0) - return err; - - regmap_write(priv->regmap32, QPOSINIT, res); - - return len; -} - static ssize_t ti_eqep_position_enable_read(struct counter_device *counter, struct counter_count *count, void *ext_priv, char *buf) @@ -301,11 +271,6 @@ static struct counter_count_ext ti_eqep_position_ext[] = { .read = ti_eqep_position_ceiling_read, .write = ti_eqep_position_ceiling_write, }, - { - .name = "floor", - .read = ti_eqep_position_floor_read, - .write = ti_eqep_position_floor_write, - }, { .name = "enable", .read = ti_eqep_position_enable_read, diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c index 52acd77438ed..251e75c9ba9d 100644 --- a/drivers/hwtracing/intel_th/pci.c +++ b/drivers/hwtracing/intel_th/pci.c @@ -268,6 +268,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7aa6), .driver_data = (kernel_ulong_t)&intel_th_2x, }, + { + /* Alder Lake-P */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x51a6), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, { /* Alder Lake CPU */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x466f), diff --git a/drivers/hwtracing/stm/heartbeat.c b/drivers/hwtracing/stm/heartbeat.c index 3e7df1c0477f..81d7b21d31ec 100644 --- a/drivers/hwtracing/stm/heartbeat.c +++ b/drivers/hwtracing/stm/heartbeat.c @@ -64,7 +64,7 @@ static void stm_heartbeat_unlink(struct stm_source_data *data) static int stm_heartbeat_init(void) { - int i, ret = -ENOMEM; + int i, ret; if (nr_devs < 0 || nr_devs > STM_HEARTBEAT_MAX) return -EINVAL; @@ -72,8 +72,10 @@ static int stm_heartbeat_init(void) for (i = 0; i < nr_devs; i++) { stm_heartbeat[i].data.name = kasprintf(GFP_KERNEL, "heartbeat.%d", i); - if (!stm_heartbeat[i].data.name) + if (!stm_heartbeat[i].data.name) { + ret = -ENOMEM; goto fail_unregister; + } stm_heartbeat[i].data.nr_chans = 1; stm_heartbeat[i].data.link = stm_heartbeat_link; diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c index b11c8c47ba2a..e946903b0993 100644 --- a/drivers/iio/adc/ti_am335x_adc.c +++ b/drivers/iio/adc/ti_am335x_adc.c @@ -397,16 +397,12 @@ static int tiadc_iio_buffered_hardware_setup(struct device *dev, ret = devm_request_threaded_irq(dev, irq, pollfunc_th, pollfunc_bh, flags, indio_dev->name, indio_dev); if (ret) - goto error_kfifo_free; + return ret; indio_dev->setup_ops = setup_ops; indio_dev->modes |= INDIO_BUFFER_SOFTWARE; return 0; - -error_kfifo_free: - iio_kfifo_free(indio_dev->buffer); - return ret; } static const char * const chan_name_ain[] = { diff --git a/drivers/iio/common/st_sensors/st_sensors_trigger.c b/drivers/iio/common/st_sensors/st_sensors_trigger.c index 0507283bd4c1..2dbd2646e44e 100644 --- a/drivers/iio/common/st_sensors/st_sensors_trigger.c +++ b/drivers/iio/common/st_sensors/st_sensors_trigger.c @@ -23,35 +23,31 @@ * @sdata: Sensor data. * * returns: - * 0 - no new samples available - * 1 - new samples available - * negative - error or unknown + * false - no new samples available or read error + * true - new samples available */ -static int st_sensors_new_samples_available(struct iio_dev *indio_dev, - struct st_sensor_data *sdata) +static bool st_sensors_new_samples_available(struct iio_dev *indio_dev, + struct st_sensor_data *sdata) { int ret, status; /* How would I know if I can't check it? */ if (!sdata->sensor_settings->drdy_irq.stat_drdy.addr) - return -EINVAL; + return true; /* No scan mask, no interrupt */ if (!indio_dev->active_scan_mask) - return 0; + return false; ret = regmap_read(sdata->regmap, sdata->sensor_settings->drdy_irq.stat_drdy.addr, &status); if (ret < 0) { dev_err(sdata->dev, "error checking samples available\n"); - return ret; + return false; } - if (status & sdata->sensor_settings->drdy_irq.stat_drdy.mask) - return 1; - - return 0; + return !!(status & sdata->sensor_settings->drdy_irq.stat_drdy.mask); } /** @@ -180,9 +176,15 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, /* Tell the interrupt handler that we're dealing with edges */ if (irq_trig == IRQF_TRIGGER_FALLING || - irq_trig == IRQF_TRIGGER_RISING) + irq_trig == IRQF_TRIGGER_RISING) { + if (!sdata->sensor_settings->drdy_irq.stat_drdy.addr) { + dev_err(&indio_dev->dev, + "edge IRQ not supported w/o stat register.\n"); + err = -EOPNOTSUPP; + goto iio_trigger_free; + } sdata->edge_irq = true; - else + } else { /* * If we're not using edges (i.e. level interrupts) we * just mask off the IRQ, handle one interrupt, then @@ -190,6 +192,7 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, * interrupt handler top half again and start over. */ irq_trig |= IRQF_ONESHOT; + } /* * If the interrupt pin is Open Drain, by definition this diff --git a/drivers/iio/dac/ad5504.c b/drivers/iio/dac/ad5504.c index 28921b62e642..e9297c25d4ef 100644 --- a/drivers/iio/dac/ad5504.c +++ b/drivers/iio/dac/ad5504.c @@ -187,9 +187,9 @@ static ssize_t ad5504_write_dac_powerdown(struct iio_dev *indio_dev, return ret; if (pwr_down) - st->pwr_down_mask |= (1 << chan->channel); - else st->pwr_down_mask &= ~(1 << chan->channel); + else + st->pwr_down_mask |= (1 << chan->channel); ret = ad5504_spi_write(st, AD5504_ADDR_CTRL, AD5504_DAC_PWRDWN_MODE(st->pwr_down_mode) | diff --git a/drivers/iio/proximity/sx9310.c b/drivers/iio/proximity/sx9310.c index a2f820997afc..37fd0b65a014 100644 --- a/drivers/iio/proximity/sx9310.c +++ b/drivers/iio/proximity/sx9310.c @@ -601,7 +601,7 @@ static int sx9310_read_thresh(struct sx9310_data *data, return ret; regval = FIELD_GET(SX9310_REG_PROX_CTRL8_9_PTHRESH_MASK, regval); - if (regval > ARRAY_SIZE(sx9310_pthresh_codes)) + if (regval >= ARRAY_SIZE(sx9310_pthresh_codes)) return -EINVAL; *val = sx9310_pthresh_codes[regval]; @@ -1305,7 +1305,8 @@ sx9310_get_default_reg(struct sx9310_data *data, int i, if (ret) break; - pos = min(max(ilog2(pos), 3), 10) - 3; + /* Powers of 2, except for a gap between 16 and 64 */ + pos = clamp(ilog2(pos), 3, 11) - (pos >= 32 ? 4 : 3); reg_def->def &= ~SX9310_REG_PROX_CTRL7_AVGPOSFILT_MASK; reg_def->def |= FIELD_PREP(SX9310_REG_PROX_CTRL7_AVGPOSFILT_MASK, pos); diff --git a/drivers/iio/temperature/mlx90632.c b/drivers/iio/temperature/mlx90632.c index 503fe54a0bb9..608ccb1d8bc8 100644 --- a/drivers/iio/temperature/mlx90632.c +++ b/drivers/iio/temperature/mlx90632.c @@ -248,6 +248,12 @@ static int mlx90632_set_meas_type(struct regmap *regmap, u8 type) if (ret < 0) return ret; + /* + * Give the mlx90632 some time to reset properly before sending a new I2C command + * if this is not done, the following I2C command(s) will not be accepted. + */ + usleep_range(150, 200); + ret = regmap_write_bits(regmap, MLX90632_REG_CONTROL, (MLX90632_CFG_MTYP_MASK | MLX90632_CFG_PWR_MASK), (MLX90632_MTYP_STATUS(type) | MLX90632_PWR_STATUS_HALT)); diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index ae6816df48b8..a8af289f6d09 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -494,8 +494,9 @@ config TI_SCI_INTA_IRQCHIP TI System Controller, say Y here. Otherwise, say N. config TI_PRUSS_INTC - tristate "TI PRU-ICSS Interrupt Controller" - depends on ARCH_DAVINCI || SOC_AM33XX || SOC_AM43XX || SOC_DRA7XX || ARCH_KEYSTONE || ARCH_K3 + tristate + depends on TI_PRUSS + default TI_PRUSS select IRQ_DOMAIN help This enables support for the PRU-ICSS Local Interrupt Controller diff --git a/drivers/irqchip/irq-bcm2836.c b/drivers/irqchip/irq-bcm2836.c index 5f5eb8877c41..25c9a9c06e41 100644 --- a/drivers/irqchip/irq-bcm2836.c +++ b/drivers/irqchip/irq-bcm2836.c @@ -167,7 +167,7 @@ static void bcm2836_arm_irqchip_handle_ipi(struct irq_desc *desc) chained_irq_exit(chip, desc); } -static void bcm2836_arm_irqchip_ipi_eoi(struct irq_data *d) +static void bcm2836_arm_irqchip_ipi_ack(struct irq_data *d) { int cpu = smp_processor_id(); @@ -195,7 +195,7 @@ static struct irq_chip bcm2836_arm_irqchip_ipi = { .name = "IPI", .irq_mask = bcm2836_arm_irqchip_dummy_op, .irq_unmask = bcm2836_arm_irqchip_dummy_op, - .irq_eoi = bcm2836_arm_irqchip_ipi_eoi, + .irq_ack = bcm2836_arm_irqchip_ipi_ack, .ipi_send_mask = bcm2836_arm_irqchip_ipi_send_mask, }; diff --git a/drivers/irqchip/irq-loongson-liointc.c b/drivers/irqchip/irq-loongson-liointc.c index 9ed1bc473663..09b91b81851c 100644 --- a/drivers/irqchip/irq-loongson-liointc.c +++ b/drivers/irqchip/irq-loongson-liointc.c @@ -142,8 +142,8 @@ static void liointc_resume(struct irq_chip_generic *gc) static const char * const parent_names[] = {"int0", "int1", "int2", "int3"}; -int __init liointc_of_init(struct device_node *node, - struct device_node *parent) +static int __init liointc_of_init(struct device_node *node, + struct device_node *parent) { struct irq_chip_generic *gc; struct irq_domain *domain; diff --git a/drivers/irqchip/irq-mips-cpu.c b/drivers/irqchip/irq-mips-cpu.c index 95d4fd8f7a96..0bbb0b2d0dd5 100644 --- a/drivers/irqchip/irq-mips-cpu.c +++ b/drivers/irqchip/irq-mips-cpu.c @@ -197,6 +197,13 @@ static int mips_cpu_ipi_alloc(struct irq_domain *domain, unsigned int virq, if (ret) return ret; + ret = irq_domain_set_hwirq_and_chip(domain->parent, virq + i, hwirq, + &mips_mt_cpu_irq_controller, + NULL); + + if (ret) + return ret; + ret = irq_set_irq_type(virq + i, IRQ_TYPE_LEVEL_HIGH); if (ret) return ret; diff --git a/drivers/irqchip/irq-sl28cpld.c b/drivers/irqchip/irq-sl28cpld.c index 0aa50d025ef6..fbb354413ffa 100644 --- a/drivers/irqchip/irq-sl28cpld.c +++ b/drivers/irqchip/irq-sl28cpld.c @@ -66,7 +66,7 @@ static int sl28cpld_intc_probe(struct platform_device *pdev) irqchip->chip.num_regs = 1; irqchip->chip.status_base = base + INTC_IP; irqchip->chip.mask_base = base + INTC_IE; - irqchip->chip.mask_invert = true, + irqchip->chip.mask_invert = true; irqchip->chip.ack_base = base + INTC_IP; return devm_regmap_add_irq_chip_fwnode(dev, dev_fwnode(dev), diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c index c1bcac71008c..28ddcaa5358b 100644 --- a/drivers/lightnvm/core.c +++ b/drivers/lightnvm/core.c @@ -844,11 +844,10 @@ static int nvm_bb_chunk_sense(struct nvm_dev *dev, struct ppa_addr ppa) rqd.ppa_addr = generic_to_dev_addr(dev, ppa); ret = nvm_submit_io_sync_raw(dev, &rqd); + __free_page(page); if (ret) return ret; - __free_page(page); - return rqd.error; } diff --git a/drivers/md/md.c b/drivers/md/md.c index ca409428b4fc..04384452a7ab 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -639,8 +639,10 @@ static void md_submit_flush_data(struct work_struct *ws) * could wait for this and below md_handle_request could wait for those * bios because of suspend check */ + spin_lock_irq(&mddev->lock); mddev->prev_flush_start = mddev->start_flush; mddev->flush_bio = NULL; + spin_unlock_irq(&mddev->lock); wake_up(&mddev->sb_wait); if (bio->bi_iter.bi_size == 0) { diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c index 2aa6648fa41f..5a491d2cd1ae 100644 --- a/drivers/misc/cardreader/rtsx_pcr.c +++ b/drivers/misc/cardreader/rtsx_pcr.c @@ -1512,6 +1512,7 @@ static int rtsx_pci_probe(struct pci_dev *pcidev, struct pcr_handle *handle; u32 base, len; int ret, i, bar = 0; + u8 val; dev_dbg(&(pcidev->dev), ": Realtek PCI-E Card Reader found at %s [%04x:%04x] (rev %x)\n", @@ -1577,7 +1578,11 @@ static int rtsx_pci_probe(struct pci_dev *pcidev, pcr->host_cmds_addr = pcr->rtsx_resv_buf_addr; pcr->host_sg_tbl_ptr = pcr->rtsx_resv_buf + HOST_CMDS_BUF_LEN; pcr->host_sg_tbl_addr = pcr->rtsx_resv_buf_addr + HOST_CMDS_BUF_LEN; - + rtsx_pci_read_register(pcr, ASPM_FORCE_CTL, &val); + if (val & FORCE_ASPM_CTL0 && val & FORCE_ASPM_CTL1) + pcr->aspm_enabled = false; + else + pcr->aspm_enabled = true; pcr->card_inserted = 0; pcr->card_removed = 0; INIT_DELAYED_WORK(&pcr->carddet_work, rtsx_pci_card_detect); diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c index 1456eabf9601..69d04eca767f 100644 --- a/drivers/misc/habanalabs/common/device.c +++ b/drivers/misc/habanalabs/common/device.c @@ -1037,7 +1037,7 @@ int hl_device_reset(struct hl_device *hdev, bool hard_reset, if (hard_reset) { /* Release kernel context */ - if (hl_ctx_put(hdev->kernel_ctx) == 1) + if (hdev->kernel_ctx && hl_ctx_put(hdev->kernel_ctx) == 1) hdev->kernel_ctx = NULL; hl_vm_fini(hdev); hl_mmu_fini(hdev); @@ -1487,6 +1487,15 @@ void hl_device_fini(struct hl_device *hdev) } } + /* Disable PCI access from device F/W so it won't send us additional + * interrupts. We disable MSI/MSI-X at the halt_engines function and we + * can't have the F/W sending us interrupts after that. We need to + * disable the access here because if the device is marked disable, the + * message won't be send. Also, in case of heartbeat, the device CPU is + * marked as disable so this message won't be sent + */ + hl_fw_send_pci_access_msg(hdev, CPUCP_PACKET_DISABLE_PCI_ACCESS); + /* Mark device as disabled */ hdev->disabled = true; diff --git a/drivers/misc/habanalabs/common/firmware_if.c b/drivers/misc/habanalabs/common/firmware_if.c index 20f77f58edef..c9a12980218a 100644 --- a/drivers/misc/habanalabs/common/firmware_if.c +++ b/drivers/misc/habanalabs/common/firmware_if.c @@ -402,6 +402,10 @@ int hl_fw_cpucp_pci_counters_get(struct hl_device *hdev, } counters->rx_throughput = result; + memset(&pkt, 0, sizeof(pkt)); + pkt.ctl = cpu_to_le32(CPUCP_PACKET_PCIE_THROUGHPUT_GET << + CPUCP_PKT_CTL_OPCODE_SHIFT); + /* Fetch PCI tx counter */ pkt.index = cpu_to_le32(cpucp_pcie_throughput_tx); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), @@ -414,6 +418,7 @@ int hl_fw_cpucp_pci_counters_get(struct hl_device *hdev, counters->tx_throughput = result; /* Fetch PCI replay counter */ + memset(&pkt, 0, sizeof(pkt)); pkt.ctl = cpu_to_le32(CPUCP_PACKET_PCIE_REPLAY_CNT_GET << CPUCP_PKT_CTL_OPCODE_SHIFT); diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h index e0d7f5fbaa5c..60e16dc4bcac 100644 --- a/drivers/misc/habanalabs/common/habanalabs.h +++ b/drivers/misc/habanalabs/common/habanalabs.h @@ -2182,6 +2182,7 @@ void hl_mmu_v1_set_funcs(struct hl_device *hdev, struct hl_mmu_funcs *mmu); int hl_mmu_va_to_pa(struct hl_ctx *ctx, u64 virt_addr, u64 *phys_addr); int hl_mmu_get_tlb_info(struct hl_ctx *ctx, u64 virt_addr, struct hl_mmu_hop_info *hops); +bool hl_is_dram_va(struct hl_device *hdev, u64 virt_addr); int hl_fw_load_fw_to_device(struct hl_device *hdev, const char *fw_name, void __iomem *dst, u32 src_offset, u32 size); diff --git a/drivers/misc/habanalabs/common/habanalabs_ioctl.c b/drivers/misc/habanalabs/common/habanalabs_ioctl.c index 12efbd9d2e3a..d25892d61ec9 100644 --- a/drivers/misc/habanalabs/common/habanalabs_ioctl.c +++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c @@ -133,6 +133,8 @@ static int hw_idle(struct hl_device *hdev, struct hl_info_args *args) hw_idle.is_idle = hdev->asic_funcs->is_device_idle(hdev, &hw_idle.busy_engines_mask_ext, NULL); + hw_idle.busy_engines_mask = + lower_32_bits(hw_idle.busy_engines_mask_ext); return copy_to_user(out, &hw_idle, min((size_t) max_size, sizeof(hw_idle))) ? -EFAULT : 0; diff --git a/drivers/misc/habanalabs/common/memory.c b/drivers/misc/habanalabs/common/memory.c index cbe9da4e0211..5d4fbdcaefe3 100644 --- a/drivers/misc/habanalabs/common/memory.c +++ b/drivers/misc/habanalabs/common/memory.c @@ -886,8 +886,10 @@ static void unmap_phys_pg_pack(struct hl_ctx *ctx, u64 vaddr, { struct hl_device *hdev = ctx->hdev; u64 next_vaddr, i; + bool is_host_addr; u32 page_size; + is_host_addr = !hl_is_dram_va(hdev, vaddr); page_size = phys_pg_pack->page_size; next_vaddr = vaddr; @@ -900,9 +902,13 @@ static void unmap_phys_pg_pack(struct hl_ctx *ctx, u64 vaddr, /* * unmapping on Palladium can be really long, so avoid a CPU * soft lockup bug by sleeping a little between unmapping pages + * + * In addition, when unmapping host memory we pass through + * the Linux kernel to unpin the pages and that takes a long + * time. Therefore, sleep every 32K pages to avoid soft lockup */ - if (hdev->pldm) - usleep_range(500, 1000); + if (hdev->pldm || (is_host_addr && (i & 0x7FFF) == 0)) + usleep_range(50, 200); } } diff --git a/drivers/misc/habanalabs/common/mmu.c b/drivers/misc/habanalabs/common/mmu.c index 33ae953d3a36..28a4638741d8 100644 --- a/drivers/misc/habanalabs/common/mmu.c +++ b/drivers/misc/habanalabs/common/mmu.c @@ -9,7 +9,7 @@ #include "habanalabs.h" -static bool is_dram_va(struct hl_device *hdev, u64 virt_addr) +bool hl_is_dram_va(struct hl_device *hdev, u64 virt_addr) { struct asic_fixed_properties *prop = &hdev->asic_prop; @@ -156,7 +156,7 @@ int hl_mmu_unmap_page(struct hl_ctx *ctx, u64 virt_addr, u32 page_size, if (!hdev->mmu_enable) return 0; - is_dram_addr = is_dram_va(hdev, virt_addr); + is_dram_addr = hl_is_dram_va(hdev, virt_addr); if (is_dram_addr) mmu_prop = &prop->dmmu; @@ -236,7 +236,7 @@ int hl_mmu_map_page(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr, if (!hdev->mmu_enable) return 0; - is_dram_addr = is_dram_va(hdev, virt_addr); + is_dram_addr = hl_is_dram_va(hdev, virt_addr); if (is_dram_addr) mmu_prop = &prop->dmmu; diff --git a/drivers/misc/habanalabs/common/mmu_v1.c b/drivers/misc/habanalabs/common/mmu_v1.c index 2ce6ea89d4fa..06d8a44dd5d4 100644 --- a/drivers/misc/habanalabs/common/mmu_v1.c +++ b/drivers/misc/habanalabs/common/mmu_v1.c @@ -467,8 +467,16 @@ static void hl_mmu_v1_fini(struct hl_device *hdev) { /* MMU H/W fini was already done in device hw_fini() */ - kvfree(hdev->mmu_priv.dr.mmu_shadow_hop0); - gen_pool_destroy(hdev->mmu_priv.dr.mmu_pgt_pool); + if (!ZERO_OR_NULL_PTR(hdev->mmu_priv.hr.mmu_shadow_hop0)) { + kvfree(hdev->mmu_priv.dr.mmu_shadow_hop0); + gen_pool_destroy(hdev->mmu_priv.dr.mmu_pgt_pool); + } + + /* Make sure that if we arrive here again without init was called we + * won't cause kernel panic. This can happen for example if we fail + * during hard reset code at certain points + */ + hdev->mmu_priv.dr.mmu_shadow_hop0 = NULL; } /** diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c index 8c09e4466af8..b328ddaa64ee 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi.c +++ b/drivers/misc/habanalabs/gaudi/gaudi.c @@ -4002,7 +4002,8 @@ static int gaudi_cb_mmap(struct hl_device *hdev, struct vm_area_struct *vma, vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | VM_DONTCOPY | VM_NORESERVE; - rc = dma_mmap_coherent(hdev->dev, vma, cpu_addr, dma_addr, size); + rc = dma_mmap_coherent(hdev->dev, vma, cpu_addr, + (dma_addr - HOST_PHYS_BASE), size); if (rc) dev_err(hdev->dev, "dma_mmap_coherent error %d", rc); diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index b8b4aa636b7c..63679a747d2c 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -2719,7 +2719,8 @@ static int goya_cb_mmap(struct hl_device *hdev, struct vm_area_struct *vma, vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | VM_DONTCOPY | VM_NORESERVE; - rc = dma_mmap_coherent(hdev->dev, vma, cpu_addr, dma_addr, size); + rc = dma_mmap_coherent(hdev->dev, vma, cpu_addr, + (dma_addr - HOST_PHYS_BASE), size); if (rc) dev_err(hdev->dev, "dma_mmap_coherent error %d", rc); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 200bdd672c28..8caf9b34734d 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1543,8 +1543,21 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) } length = (io.nblocks + 1) << ns->lba_shift; - meta_len = (io.nblocks + 1) * ns->ms; - metadata = nvme_to_user_ptr(io.metadata); + + if ((io.control & NVME_RW_PRINFO_PRACT) && + ns->ms == sizeof(struct t10_pi_tuple)) { + /* + * Protection information is stripped/inserted by the + * controller. + */ + if (nvme_to_user_ptr(io.metadata)) + return -EINVAL; + meta_len = 0; + metadata = NULL; + } else { + meta_len = (io.nblocks + 1) * ns->ms; + metadata = nvme_to_user_ptr(io.metadata); + } if (ns->features & NVME_NS_EXT_LBAS) { length += meta_len; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 50d9a20568a2..856aa31931c1 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include @@ -542,50 +543,71 @@ static inline bool nvme_pci_use_sgls(struct nvme_dev *dev, struct request *req) return true; } -static void nvme_unmap_data(struct nvme_dev *dev, struct request *req) +static void nvme_free_prps(struct nvme_dev *dev, struct request *req) { - struct nvme_iod *iod = blk_mq_rq_to_pdu(req); const int last_prp = NVME_CTRL_PAGE_SIZE / sizeof(__le64) - 1; - dma_addr_t dma_addr = iod->first_dma, next_dma_addr; + struct nvme_iod *iod = blk_mq_rq_to_pdu(req); + dma_addr_t dma_addr = iod->first_dma; int i; - if (iod->dma_len) { - dma_unmap_page(dev->dev, dma_addr, iod->dma_len, - rq_dma_dir(req)); - return; + for (i = 0; i < iod->npages; i++) { + __le64 *prp_list = nvme_pci_iod_list(req)[i]; + dma_addr_t next_dma_addr = le64_to_cpu(prp_list[last_prp]); + + dma_pool_free(dev->prp_page_pool, prp_list, dma_addr); + dma_addr = next_dma_addr; } - WARN_ON_ONCE(!iod->nents); +} + +static void nvme_free_sgls(struct nvme_dev *dev, struct request *req) +{ + const int last_sg = SGES_PER_PAGE - 1; + struct nvme_iod *iod = blk_mq_rq_to_pdu(req); + dma_addr_t dma_addr = iod->first_dma; + int i; + + for (i = 0; i < iod->npages; i++) { + struct nvme_sgl_desc *sg_list = nvme_pci_iod_list(req)[i]; + dma_addr_t next_dma_addr = le64_to_cpu((sg_list[last_sg]).addr); + + dma_pool_free(dev->prp_page_pool, sg_list, dma_addr); + dma_addr = next_dma_addr; + } + +} + +static void nvme_unmap_sg(struct nvme_dev *dev, struct request *req) +{ + struct nvme_iod *iod = blk_mq_rq_to_pdu(req); if (is_pci_p2pdma_page(sg_page(iod->sg))) pci_p2pdma_unmap_sg(dev->dev, iod->sg, iod->nents, rq_dma_dir(req)); else dma_unmap_sg(dev->dev, iod->sg, iod->nents, rq_dma_dir(req)); +} +static void nvme_unmap_data(struct nvme_dev *dev, struct request *req) +{ + struct nvme_iod *iod = blk_mq_rq_to_pdu(req); - if (iod->npages == 0) - dma_pool_free(dev->prp_small_pool, nvme_pci_iod_list(req)[0], - dma_addr); - - for (i = 0; i < iod->npages; i++) { - void *addr = nvme_pci_iod_list(req)[i]; - - if (iod->use_sgl) { - struct nvme_sgl_desc *sg_list = addr; - - next_dma_addr = - le64_to_cpu((sg_list[SGES_PER_PAGE - 1]).addr); - } else { - __le64 *prp_list = addr; - - next_dma_addr = le64_to_cpu(prp_list[last_prp]); - } - - dma_pool_free(dev->prp_page_pool, addr, dma_addr); - dma_addr = next_dma_addr; + if (iod->dma_len) { + dma_unmap_page(dev->dev, iod->first_dma, iod->dma_len, + rq_dma_dir(req)); + return; } + WARN_ON_ONCE(!iod->nents); + + nvme_unmap_sg(dev, req); + if (iod->npages == 0) + dma_pool_free(dev->prp_small_pool, nvme_pci_iod_list(req)[0], + iod->first_dma); + else if (iod->use_sgl) + nvme_free_sgls(dev, req); + else + nvme_free_prps(dev, req); mempool_free(iod->sg, dev->iod_mempool); } @@ -661,7 +683,7 @@ static blk_status_t nvme_pci_setup_prps(struct nvme_dev *dev, __le64 *old_prp_list = prp_list; prp_list = dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma); if (!prp_list) - return BLK_STS_RESOURCE; + goto free_prps; list[iod->npages++] = prp_list; prp_list[0] = old_prp_list[i - 1]; old_prp_list[i - 1] = cpu_to_le64(prp_dma); @@ -681,14 +703,14 @@ static blk_status_t nvme_pci_setup_prps(struct nvme_dev *dev, dma_addr = sg_dma_address(sg); dma_len = sg_dma_len(sg); } - done: cmnd->dptr.prp1 = cpu_to_le64(sg_dma_address(iod->sg)); cmnd->dptr.prp2 = cpu_to_le64(iod->first_dma); - return BLK_STS_OK; - - bad_sgl: +free_prps: + nvme_free_prps(dev, req); + return BLK_STS_RESOURCE; +bad_sgl: WARN(DO_ONCE(nvme_print_sgl, iod->sg, iod->nents), "Invalid SGL for payload:%d nents:%d\n", blk_rq_payload_bytes(req), iod->nents); @@ -760,7 +782,7 @@ static blk_status_t nvme_pci_setup_sgls(struct nvme_dev *dev, sg_list = dma_pool_alloc(pool, GFP_ATOMIC, &sgl_dma); if (!sg_list) - return BLK_STS_RESOURCE; + goto free_sgls; i = 0; nvme_pci_iod_list(req)[iod->npages++] = sg_list; @@ -773,6 +795,9 @@ static blk_status_t nvme_pci_setup_sgls(struct nvme_dev *dev, } while (--entries > 0); return BLK_STS_OK; +free_sgls: + nvme_free_sgls(dev, req); + return BLK_STS_RESOURCE; } static blk_status_t nvme_setup_prp_simple(struct nvme_dev *dev, @@ -841,7 +866,7 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req, sg_init_table(iod->sg, blk_rq_nr_phys_segments(req)); iod->nents = blk_rq_map_sg(req->q, req, iod->sg); if (!iod->nents) - goto out; + goto out_free_sg; if (is_pci_p2pdma_page(sg_page(iod->sg))) nr_mapped = pci_p2pdma_map_sg_attrs(dev->dev, iod->sg, @@ -850,16 +875,21 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req, nr_mapped = dma_map_sg_attrs(dev->dev, iod->sg, iod->nents, rq_dma_dir(req), DMA_ATTR_NO_WARN); if (!nr_mapped) - goto out; + goto out_free_sg; iod->use_sgl = nvme_pci_use_sgls(dev, req); if (iod->use_sgl) ret = nvme_pci_setup_sgls(dev, req, &cmnd->rw, nr_mapped); else ret = nvme_pci_setup_prps(dev, req, &cmnd->rw); -out: if (ret != BLK_STS_OK) - nvme_unmap_data(dev, req); + goto out_unmap_sg; + return BLK_STS_OK; + +out_unmap_sg: + nvme_unmap_sg(dev, req); +out_free_sg: + mempool_free(iod->sg, dev->iod_mempool); return ret; } @@ -1795,6 +1825,9 @@ static void nvme_map_cmb(struct nvme_dev *dev) if (dev->cmb_size) return; + if (NVME_CAP_CMBS(dev->ctrl.cap)) + writel(NVME_CMBMSC_CRE, dev->bar + NVME_REG_CMBMSC); + dev->cmbsz = readl(dev->bar + NVME_REG_CMBSZ); if (!dev->cmbsz) return; @@ -1808,6 +1841,16 @@ static void nvme_map_cmb(struct nvme_dev *dev) if (offset > bar_size) return; + /* + * Tell the controller about the host side address mapping the CMB, + * and enable CMB decoding for the NVMe 1.4+ scheme: + */ + if (NVME_CAP_CMBS(dev->ctrl.cap)) { + hi_lo_writeq(NVME_CMBMSC_CRE | NVME_CMBMSC_CMSE | + (pci_bus_address(pdev, bar) + offset), + dev->bar + NVME_REG_CMBMSC); + } + /* * Controllers may support a CMB size larger than their BAR, * for example, due to being behind a bridge. Reduce the CMB to diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index cf6c49d09c82..b7ce4f221d99 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -97,6 +97,7 @@ struct nvme_rdma_queue { struct completion cm_done; bool pi_support; int cq_size; + struct mutex queue_lock; }; struct nvme_rdma_ctrl { @@ -579,6 +580,7 @@ static int nvme_rdma_alloc_queue(struct nvme_rdma_ctrl *ctrl, int ret; queue = &ctrl->queues[idx]; + mutex_init(&queue->queue_lock); queue->ctrl = ctrl; if (idx && ctrl->ctrl.max_integrity_segments) queue->pi_support = true; @@ -598,7 +600,8 @@ static int nvme_rdma_alloc_queue(struct nvme_rdma_ctrl *ctrl, if (IS_ERR(queue->cm_id)) { dev_info(ctrl->ctrl.device, "failed to create CM ID: %ld\n", PTR_ERR(queue->cm_id)); - return PTR_ERR(queue->cm_id); + ret = PTR_ERR(queue->cm_id); + goto out_destroy_mutex; } if (ctrl->ctrl.opts->mask & NVMF_OPT_HOST_TRADDR) @@ -628,6 +631,8 @@ static int nvme_rdma_alloc_queue(struct nvme_rdma_ctrl *ctrl, out_destroy_cm_id: rdma_destroy_id(queue->cm_id); nvme_rdma_destroy_queue_ib(queue); +out_destroy_mutex: + mutex_destroy(&queue->queue_lock); return ret; } @@ -639,9 +644,10 @@ static void __nvme_rdma_stop_queue(struct nvme_rdma_queue *queue) static void nvme_rdma_stop_queue(struct nvme_rdma_queue *queue) { - if (!test_and_clear_bit(NVME_RDMA_Q_LIVE, &queue->flags)) - return; - __nvme_rdma_stop_queue(queue); + mutex_lock(&queue->queue_lock); + if (test_and_clear_bit(NVME_RDMA_Q_LIVE, &queue->flags)) + __nvme_rdma_stop_queue(queue); + mutex_unlock(&queue->queue_lock); } static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue) @@ -651,6 +657,7 @@ static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue) nvme_rdma_destroy_queue_ib(queue); rdma_destroy_id(queue->cm_id); + mutex_destroy(&queue->queue_lock); } static void nvme_rdma_free_io_queues(struct nvme_rdma_ctrl *ctrl) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 216619926563..881d28eb15e9 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -76,6 +76,7 @@ struct nvme_tcp_queue { struct work_struct io_work; int io_cpu; + struct mutex queue_lock; struct mutex send_mutex; struct llist_head req_list; struct list_head send_list; @@ -1219,6 +1220,7 @@ static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid) sock_release(queue->sock); kfree(queue->pdu); + mutex_destroy(&queue->queue_lock); } static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue) @@ -1380,6 +1382,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, struct nvme_tcp_queue *queue = &ctrl->queues[qid]; int ret, rcv_pdu_size; + mutex_init(&queue->queue_lock); queue->ctrl = ctrl; init_llist_head(&queue->req_list); INIT_LIST_HEAD(&queue->send_list); @@ -1398,7 +1401,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, if (ret) { dev_err(nctrl->device, "failed to create socket: %d\n", ret); - return ret; + goto err_destroy_mutex; } /* Single syn retry */ @@ -1507,6 +1510,8 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, err_sock: sock_release(queue->sock); queue->sock = NULL; +err_destroy_mutex: + mutex_destroy(&queue->queue_lock); return ret; } @@ -1534,9 +1539,10 @@ static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid) struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); struct nvme_tcp_queue *queue = &ctrl->queues[qid]; - if (!test_and_clear_bit(NVME_TCP_Q_LIVE, &queue->flags)) - return; - __nvme_tcp_stop_queue(queue); + mutex_lock(&queue->queue_lock); + if (test_and_clear_bit(NVME_TCP_Q_LIVE, &queue->flags)) + __nvme_tcp_stop_queue(queue); + mutex_unlock(&queue->queue_lock); } static int nvme_tcp_start_queue(struct nvme_ctrl *nctrl, int idx) diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 8d90235e4fcc..dc1ea468b182 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -487,8 +487,10 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req) /* return an all zeroed buffer if we can't find an active namespace */ ns = nvmet_find_namespace(ctrl, req->cmd->identify.nsid); - if (!ns) + if (!ns) { + status = NVME_SC_INVALID_NS; goto done; + } nvmet_ns_revalidate(ns); @@ -541,7 +543,9 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req) id->nsattr |= (1 << 0); nvmet_put_namespace(ns); done: - status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id)); + if (!status) + status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id)); + kfree(id); out: nvmet_req_complete(req, status); diff --git a/drivers/phy/ingenic/Makefile b/drivers/phy/ingenic/Makefile index 65d5ea00fc9d..1cb158d7233f 100644 --- a/drivers/phy/ingenic/Makefile +++ b/drivers/phy/ingenic/Makefile @@ -1,2 +1,2 @@ # SPDX-License-Identifier: GPL-2.0 -obj-y += phy-ingenic-usb.o +obj-$(CONFIG_PHY_INGENIC_USB) += phy-ingenic-usb.o diff --git a/drivers/phy/mediatek/Kconfig b/drivers/phy/mediatek/Kconfig index d38def43b1bf..55f8e6c048ab 100644 --- a/drivers/phy/mediatek/Kconfig +++ b/drivers/phy/mediatek/Kconfig @@ -49,7 +49,9 @@ config PHY_MTK_HDMI config PHY_MTK_MIPI_DSI tristate "MediaTek MIPI-DSI Driver" - depends on ARCH_MEDIATEK && OF + depends on ARCH_MEDIATEK || COMPILE_TEST + depends on COMMON_CLK + depends on OF select GENERIC_PHY help Support MIPI DSI for Mediatek SoCs. diff --git a/drivers/phy/motorola/phy-cpcap-usb.c b/drivers/phy/motorola/phy-cpcap-usb.c index 442522ba487f..4728e2bff662 100644 --- a/drivers/phy/motorola/phy-cpcap-usb.c +++ b/drivers/phy/motorola/phy-cpcap-usb.c @@ -662,35 +662,42 @@ static int cpcap_usb_phy_probe(struct platform_device *pdev) generic_phy = devm_phy_create(ddata->dev, NULL, &ops); if (IS_ERR(generic_phy)) { error = PTR_ERR(generic_phy); - return PTR_ERR(generic_phy); + goto out_reg_disable; } phy_set_drvdata(generic_phy, ddata); phy_provider = devm_of_phy_provider_register(ddata->dev, of_phy_simple_xlate); - if (IS_ERR(phy_provider)) - return PTR_ERR(phy_provider); + if (IS_ERR(phy_provider)) { + error = PTR_ERR(phy_provider); + goto out_reg_disable; + } error = cpcap_usb_init_optional_pins(ddata); if (error) - return error; + goto out_reg_disable; cpcap_usb_init_optional_gpios(ddata); error = cpcap_usb_init_iio(ddata); if (error) - return error; + goto out_reg_disable; error = cpcap_usb_init_interrupts(pdev, ddata); if (error) - return error; + goto out_reg_disable; usb_add_phy_dev(&ddata->phy); atomic_set(&ddata->active, 1); schedule_delayed_work(&ddata->detect_work, msecs_to_jiffies(1)); return 0; + +out_reg_disable: + regulator_disable(ddata->vusb); + + return error; } static int cpcap_usb_phy_remove(struct platform_device *pdev) diff --git a/drivers/sh/intc/core.c b/drivers/sh/intc/core.c index f8e070d67fa3..a14684ffe4c1 100644 --- a/drivers/sh/intc/core.c +++ b/drivers/sh/intc/core.c @@ -214,7 +214,7 @@ int __init register_intc_controller(struct intc_desc *desc) d->window[k].phys = res->start; d->window[k].size = resource_size(res); d->window[k].virt = ioremap(res->start, - resource_size(res)); + resource_size(res)); if (!d->window[k].virt) goto err2; } diff --git a/drivers/sh/intc/virq-debugfs.c b/drivers/sh/intc/virq-debugfs.c index 9e62ba9311f0..939915a07d99 100644 --- a/drivers/sh/intc/virq-debugfs.c +++ b/drivers/sh/intc/virq-debugfs.c @@ -16,7 +16,7 @@ #include #include "internals.h" -static int intc_irq_xlate_debug(struct seq_file *m, void *priv) +static int intc_irq_xlate_show(struct seq_file *m, void *priv) { int i; @@ -37,17 +37,7 @@ static int intc_irq_xlate_debug(struct seq_file *m, void *priv) return 0; } -static int intc_irq_xlate_open(struct inode *inode, struct file *file) -{ - return single_open(file, intc_irq_xlate_debug, inode->i_private); -} - -static const struct file_operations intc_irq_xlate_fops = { - .open = intc_irq_xlate_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(intc_irq_xlate); static int __init intc_irq_xlate_init(void) { diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c index 8b7f941a9bb7..b8c4159bc32d 100644 --- a/drivers/thunderbolt/icm.c +++ b/drivers/thunderbolt/icm.c @@ -2316,7 +2316,7 @@ static int icm_usb4_switch_nvm_authenticate_status(struct tb_switch *sw, if (auth && auth->reply.route_hi == sw->config.route_hi && auth->reply.route_lo == sw->config.route_lo) { - tb_dbg(tb, "NVM_AUTH found for %llx flags 0x%#x status %#x\n", + tb_dbg(tb, "NVM_AUTH found for %llx flags %#x status %#x\n", tb_route(sw), auth->reply.hdr.flags, auth->reply.status); if (auth->reply.hdr.flags & ICM_FLAGS_ERROR) ret = -EIO; diff --git a/drivers/tty/serial/mvebu-uart.c b/drivers/tty/serial/mvebu-uart.c index 118b29912289..e0c00a1b0763 100644 --- a/drivers/tty/serial/mvebu-uart.c +++ b/drivers/tty/serial/mvebu-uart.c @@ -648,6 +648,14 @@ static void wait_for_xmitr(struct uart_port *port) (val & STAT_TX_RDY(port)), 1, 10000); } +static void wait_for_xmite(struct uart_port *port) +{ + u32 val; + + readl_poll_timeout_atomic(port->membase + UART_STAT, val, + (val & STAT_TX_EMP), 1, 10000); +} + static void mvebu_uart_console_putchar(struct uart_port *port, int ch) { wait_for_xmitr(port); @@ -675,7 +683,7 @@ static void mvebu_uart_console_write(struct console *co, const char *s, uart_console_write(port, s, count, mvebu_uart_console_putchar); - wait_for_xmitr(port); + wait_for_xmite(port); if (ier) writel(ier, port->membase + UART_CTRL(port)); diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 8034489337d7..4a208a95e921 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -143,9 +143,8 @@ LIST_HEAD(tty_drivers); /* linked list of tty drivers */ DEFINE_MUTEX(tty_mutex); static ssize_t tty_read(struct file *, char __user *, size_t, loff_t *); -static ssize_t tty_write(struct file *, const char __user *, size_t, loff_t *); -ssize_t redirected_tty_write(struct file *, const char __user *, - size_t, loff_t *); +static ssize_t tty_write(struct kiocb *, struct iov_iter *); +ssize_t redirected_tty_write(struct kiocb *, struct iov_iter *); static __poll_t tty_poll(struct file *, poll_table *); static int tty_open(struct inode *, struct file *); long tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg); @@ -438,8 +437,7 @@ static ssize_t hung_up_tty_read(struct file *file, char __user *buf, return 0; } -static ssize_t hung_up_tty_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) +static ssize_t hung_up_tty_write(struct kiocb *iocb, struct iov_iter *from) { return -EIO; } @@ -478,7 +476,8 @@ static void tty_show_fdinfo(struct seq_file *m, struct file *file) static const struct file_operations tty_fops = { .llseek = no_llseek, .read = tty_read, - .write = tty_write, + .write_iter = tty_write, + .splice_write = iter_file_splice_write, .poll = tty_poll, .unlocked_ioctl = tty_ioctl, .compat_ioctl = tty_compat_ioctl, @@ -491,7 +490,8 @@ static const struct file_operations tty_fops = { static const struct file_operations console_fops = { .llseek = no_llseek, .read = tty_read, - .write = redirected_tty_write, + .write_iter = redirected_tty_write, + .splice_write = iter_file_splice_write, .poll = tty_poll, .unlocked_ioctl = tty_ioctl, .compat_ioctl = tty_compat_ioctl, @@ -503,7 +503,7 @@ static const struct file_operations console_fops = { static const struct file_operations hung_up_tty_fops = { .llseek = no_llseek, .read = hung_up_tty_read, - .write = hung_up_tty_write, + .write_iter = hung_up_tty_write, .poll = hung_up_tty_poll, .unlocked_ioctl = hung_up_tty_ioctl, .compat_ioctl = hung_up_tty_compat_ioctl, @@ -606,9 +606,9 @@ static void __tty_hangup(struct tty_struct *tty, int exit_session) /* This breaks for file handles being sent over AF_UNIX sockets ? */ list_for_each_entry(priv, &tty->tty_files, list) { filp = priv->file; - if (filp->f_op->write == redirected_tty_write) + if (filp->f_op->write_iter == redirected_tty_write) cons_filp = filp; - if (filp->f_op->write != tty_write) + if (filp->f_op->write_iter != tty_write) continue; closecount++; __tty_fasync(-1, filp, 0); /* can't block */ @@ -901,9 +901,9 @@ static inline ssize_t do_tty_write( ssize_t (*write)(struct tty_struct *, struct file *, const unsigned char *, size_t), struct tty_struct *tty, struct file *file, - const char __user *buf, - size_t count) + struct iov_iter *from) { + size_t count = iov_iter_count(from); ssize_t ret, written = 0; unsigned int chunk; @@ -955,14 +955,20 @@ static inline ssize_t do_tty_write( size_t size = count; if (size > chunk) size = chunk; + ret = -EFAULT; - if (copy_from_user(tty->write_buf, buf, size)) + if (copy_from_iter(tty->write_buf, size, from) != size) break; + ret = write(tty, file, tty->write_buf, size); if (ret <= 0) break; + + /* FIXME! Have Al check this! */ + if (ret != size) + iov_iter_revert(from, size-ret); + written += ret; - buf += ret; count -= ret; if (!count) break; @@ -1022,9 +1028,9 @@ void tty_write_message(struct tty_struct *tty, char *msg) * write method will not be invoked in parallel for each device. */ -static ssize_t tty_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) +static ssize_t tty_write(struct kiocb *iocb, struct iov_iter *from) { + struct file *file = iocb->ki_filp; struct tty_struct *tty = file_tty(file); struct tty_ldisc *ld; ssize_t ret; @@ -1038,17 +1044,16 @@ static ssize_t tty_write(struct file *file, const char __user *buf, tty_err(tty, "missing write_room method\n"); ld = tty_ldisc_ref_wait(tty); if (!ld) - return hung_up_tty_write(file, buf, count, ppos); + return hung_up_tty_write(iocb, from); if (!ld->ops->write) ret = -EIO; else - ret = do_tty_write(ld->ops->write, tty, file, buf, count); + ret = do_tty_write(ld->ops->write, tty, file, from); tty_ldisc_deref(ld); return ret; } -ssize_t redirected_tty_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) +ssize_t redirected_tty_write(struct kiocb *iocb, struct iov_iter *iter) { struct file *p = NULL; @@ -1059,11 +1064,11 @@ ssize_t redirected_tty_write(struct file *file, const char __user *buf, if (p) { ssize_t res; - res = vfs_write(p, buf, count, &p->f_pos); + res = vfs_iocb_iter_write(p, iocb, iter); fput(p); return res; } - return tty_write(file, buf, count, ppos); + return tty_write(iocb, iter); } /* @@ -2295,7 +2300,7 @@ static int tioccons(struct file *file) { if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (file->f_op->write == redirected_tty_write) { + if (file->f_op->write_iter == redirected_tty_write) { struct file *f; spin_lock(&redirect_lock); f = redirect; diff --git a/drivers/usb/cdns3/cdns3-imx.c b/drivers/usb/cdns3/cdns3-imx.c index 22a56c4dce67..7990fee03fe4 100644 --- a/drivers/usb/cdns3/cdns3-imx.c +++ b/drivers/usb/cdns3/cdns3-imx.c @@ -185,7 +185,11 @@ static int cdns_imx_probe(struct platform_device *pdev) } data->num_clks = ARRAY_SIZE(imx_cdns3_core_clks); - data->clks = (struct clk_bulk_data *)imx_cdns3_core_clks; + data->clks = devm_kmemdup(dev, imx_cdns3_core_clks, + sizeof(imx_cdns3_core_clks), GFP_KERNEL); + if (!data->clks) + return -ENOMEM; + ret = devm_clk_bulk_get(dev, data->num_clks, data->clks); if (ret) return ret; @@ -214,20 +218,16 @@ static int cdns_imx_probe(struct platform_device *pdev) return ret; } -static int cdns_imx_remove_core(struct device *dev, void *data) -{ - struct platform_device *pdev = to_platform_device(dev); - - platform_device_unregister(pdev); - - return 0; -} - static int cdns_imx_remove(struct platform_device *pdev) { struct device *dev = &pdev->dev; + struct cdns_imx *data = dev_get_drvdata(dev); - device_for_each_child(dev, NULL, cdns_imx_remove_core); + pm_runtime_get_sync(dev); + of_platform_depopulate(dev); + clk_bulk_disable_unprepare(data->num_clks, data->clks); + pm_runtime_disable(dev); + pm_runtime_put_noidle(dev); platform_set_drvdata(pdev, NULL); return 0; diff --git a/drivers/usb/gadget/udc/aspeed-vhub/epn.c b/drivers/usb/gadget/udc/aspeed-vhub/epn.c index 0bd6b20435b8..02d8bfae58fb 100644 --- a/drivers/usb/gadget/udc/aspeed-vhub/epn.c +++ b/drivers/usb/gadget/udc/aspeed-vhub/epn.c @@ -420,7 +420,10 @@ static void ast_vhub_stop_active_req(struct ast_vhub_ep *ep, u32 state, reg, loops; /* Stop DMA activity */ - writel(0, ep->epn.regs + AST_VHUB_EP_DMA_CTLSTAT); + if (ep->epn.desc_mode) + writel(VHUB_EP_DMA_CTRL_RESET, ep->epn.regs + AST_VHUB_EP_DMA_CTLSTAT); + else + writel(0, ep->epn.regs + AST_VHUB_EP_DMA_CTLSTAT); /* Wait for it to complete */ for (loops = 0; loops < 1000; loops++) { diff --git a/drivers/usb/gadget/udc/bdc/Kconfig b/drivers/usb/gadget/udc/bdc/Kconfig index 3e88c7670b2e..fb01ff47b64c 100644 --- a/drivers/usb/gadget/udc/bdc/Kconfig +++ b/drivers/usb/gadget/udc/bdc/Kconfig @@ -17,7 +17,7 @@ if USB_BDC_UDC comment "Platform Support" config USB_BDC_PCI tristate "BDC support for PCIe based platforms" - depends on USB_PCI + depends on USB_PCI && BROKEN default USB_BDC_UDC help Enable support for platforms which have BDC connected through PCIe, such as Lego3 FPGA platform. diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index 6a62bbd01324..ea114f922ccf 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -1529,10 +1529,13 @@ static ssize_t soft_connect_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t n) { struct usb_udc *udc = container_of(dev, struct usb_udc, dev); + ssize_t ret; + mutex_lock(&udc_lock); if (!udc->driver) { dev_err(dev, "soft-connect without a gadget driver\n"); - return -EOPNOTSUPP; + ret = -EOPNOTSUPP; + goto out; } if (sysfs_streq(buf, "connect")) { @@ -1543,10 +1546,14 @@ static ssize_t soft_connect_store(struct device *dev, usb_gadget_udc_stop(udc); } else { dev_err(dev, "unsupported command '%s'\n", buf); - return -EINVAL; + ret = -EINVAL; + goto out; } - return n; + ret = n; +out: + mutex_unlock(&udc_lock); + return ret; } static DEVICE_ATTR_WO(soft_connect); diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c index 1a953f44183a..57067763b100 100644 --- a/drivers/usb/gadget/udc/dummy_hcd.c +++ b/drivers/usb/gadget/udc/dummy_hcd.c @@ -2270,17 +2270,20 @@ static int dummy_hub_control( } fallthrough; case USB_PORT_FEAT_RESET: + if (!(dum_hcd->port_status & USB_PORT_STAT_CONNECTION)) + break; /* if it's already enabled, disable */ if (hcd->speed == HCD_USB3) { - dum_hcd->port_status = 0; dum_hcd->port_status = (USB_SS_PORT_STAT_POWER | USB_PORT_STAT_CONNECTION | USB_PORT_STAT_RESET); - } else + } else { dum_hcd->port_status &= ~(USB_PORT_STAT_ENABLE | USB_PORT_STAT_LOW_SPEED | USB_PORT_STAT_HIGH_SPEED); + dum_hcd->port_status |= USB_PORT_STAT_RESET; + } /* * We want to reset device status. All but the * Self powered feature @@ -2292,7 +2295,8 @@ static int dummy_hub_control( * interval? Is it still 50msec as for HS? */ dum_hcd->re_timeout = jiffies + msecs_to_jiffies(50); - fallthrough; + set_link_state(dum_hcd); + break; case USB_PORT_FEAT_C_CONNECTION: case USB_PORT_FEAT_C_RESET: case USB_PORT_FEAT_C_ENABLE: diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c index e358ae17d51e..1926b328b6aa 100644 --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -574,6 +574,7 @@ static int ehci_run (struct usb_hcd *hcd) struct ehci_hcd *ehci = hcd_to_ehci (hcd); u32 temp; u32 hcc_params; + int rc; hcd->uses_new_polling = 1; @@ -629,9 +630,20 @@ static int ehci_run (struct usb_hcd *hcd) down_write(&ehci_cf_port_reset_rwsem); ehci->rh_state = EHCI_RH_RUNNING; ehci_writel(ehci, FLAG_CF, &ehci->regs->configured_flag); + + /* Wait until HC become operational */ ehci_readl(ehci, &ehci->regs->command); /* unblock posted writes */ msleep(5); + rc = ehci_handshake(ehci, &ehci->regs->status, STS_HALT, 0, 100 * 1000); + up_write(&ehci_cf_port_reset_rwsem); + + if (rc) { + ehci_err(ehci, "USB %x.%x, controller refused to start: %d\n", + ((ehci->sbrn & 0xf0)>>4), (ehci->sbrn & 0x0f), rc); + return rc; + } + ehci->last_periodic_enable = ktime_get_real(); temp = HC_VERSION(ehci, ehci_readl(ehci, &ehci->caps->hc_capbase)); diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c index 087402aec5cb..9f9ab5ccea88 100644 --- a/drivers/usb/host/ehci-hub.c +++ b/drivers/usb/host/ehci-hub.c @@ -345,6 +345,9 @@ static int ehci_bus_suspend (struct usb_hcd *hcd) unlink_empty_async_suspended(ehci); + /* Some Synopsys controllers mistakenly leave IAA turned on */ + ehci_writel(ehci, STS_IAA, &ehci->regs->status); + /* Any IAA cycle that started before the suspend is now invalid */ end_iaa_cycle(ehci); ehci_handle_start_intr_unlinks(ehci); diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 5677b81c0915..cf0c93a90200 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -2931,6 +2931,8 @@ static void queue_trb(struct xhci_hcd *xhci, struct xhci_ring *ring, trb->field[0] = cpu_to_le32(field1); trb->field[1] = cpu_to_le32(field2); trb->field[2] = cpu_to_le32(field3); + /* make sure TRB is fully written before giving it to the controller */ + wmb(); trb->field[3] = cpu_to_le32(field4); trace_xhci_queue_trb(ring, trb); diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c index 934be1686352..50bb91b6a4b8 100644 --- a/drivers/usb/host/xhci-tegra.c +++ b/drivers/usb/host/xhci-tegra.c @@ -623,6 +623,13 @@ static void tegra_xusb_mbox_handle(struct tegra_xusb *tegra, enable); if (err < 0) break; + + /* + * wait 500us for LFPS detector to be disabled before + * sending ACK + */ + if (!enable) + usleep_range(500, 1000); } if (err < 0) { diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 5d39129406ea..c8ef24bac94f 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -2195,7 +2195,7 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) if (ses->server->capabilities & SMB2_GLOBAL_CAP_DIRECTORY_LEASING) tcon->nohandlecache = ctx->nohandlecache; else - tcon->nohandlecache = 1; + tcon->nohandlecache = true; tcon->nodelete = ctx->nodelete; tcon->local_lease = ctx->local_lease; INIT_LIST_HEAD(&tcon->pending_opens); @@ -2628,7 +2628,7 @@ void reset_cifs_unix_caps(unsigned int xid, struct cifs_tcon *tcon, } else if (ctx) tcon->unix_ext = 1; /* Unix Extensions supported */ - if (tcon->unix_ext == 0) { + if (!tcon->unix_ext) { cifs_dbg(FYI, "Unix extensions disabled so not set on reconnect\n"); return; } diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index e9abb41aa89b..95ef26b555b9 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -338,7 +338,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, if (ssocket == NULL) return -EAGAIN; - if (signal_pending(current)) { + if (fatal_signal_pending(current)) { cifs_dbg(FYI, "signal pending before send request\n"); return -ERESTARTSYS; } @@ -429,7 +429,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, if (signal_pending(current) && (total_len != send_length)) { cifs_dbg(FYI, "signal is pending after attempt to send\n"); - rc = -EINTR; + rc = -ERESTARTSYS; } /* uncork it */ diff --git a/fs/io_uring.c b/fs/io_uring.c index 985a9e3f976d..c07913ec0cca 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1025,6 +1025,7 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req, static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec, const struct iovec *fast_iov, struct iov_iter *iter, bool force); +static void io_req_drop_files(struct io_kiocb *req); static struct kmem_cache *req_cachep; @@ -1048,8 +1049,7 @@ EXPORT_SYMBOL(io_uring_get_socket); static inline void io_clean_op(struct io_kiocb *req) { - if (req->flags & (REQ_F_NEED_CLEANUP | REQ_F_BUFFER_SELECTED | - REQ_F_INFLIGHT)) + if (req->flags & (REQ_F_NEED_CLEANUP | REQ_F_BUFFER_SELECTED)) __io_clean_op(req); } @@ -1075,8 +1075,11 @@ static bool io_match_task(struct io_kiocb *head, return true; io_for_each_link(req, head) { - if ((req->flags & REQ_F_WORK_INITIALIZED) && - (req->work.flags & IO_WQ_WORK_FILES) && + if (!(req->flags & REQ_F_WORK_INITIALIZED)) + continue; + if (req->file && req->file->f_op == &io_uring_fops) + return true; + if ((req->work.flags & IO_WQ_WORK_FILES) && req->work.identity->files == files) return true; } @@ -1394,6 +1397,8 @@ static void io_req_clean_work(struct io_kiocb *req) free_fs_struct(fs); req->work.flags &= ~IO_WQ_WORK_FS; } + if (req->flags & REQ_F_INFLIGHT) + io_req_drop_files(req); io_put_identity(req->task->io_uring, req); } @@ -1503,11 +1508,14 @@ static bool io_grab_identity(struct io_kiocb *req) return false; atomic_inc(&id->files->count); get_nsproxy(id->nsproxy); - req->flags |= REQ_F_INFLIGHT; - spin_lock_irq(&ctx->inflight_lock); - list_add(&req->inflight_entry, &ctx->inflight_list); - spin_unlock_irq(&ctx->inflight_lock); + if (!(req->flags & REQ_F_INFLIGHT)) { + req->flags |= REQ_F_INFLIGHT; + + spin_lock_irq(&ctx->inflight_lock); + list_add(&req->inflight_entry, &ctx->inflight_list); + spin_unlock_irq(&ctx->inflight_lock); + } req->work.flags |= IO_WQ_WORK_FILES; } if (!(req->work.flags & IO_WQ_WORK_MM) && @@ -2270,6 +2278,8 @@ static void io_req_free_batch_finish(struct io_ring_ctx *ctx, struct io_uring_task *tctx = rb->task->io_uring; percpu_counter_sub(&tctx->inflight, rb->task_refs); + if (atomic_read(&tctx->in_idle)) + wake_up(&tctx->wait); put_task_struct_many(rb->task, rb->task_refs); rb->task = NULL; } @@ -2288,6 +2298,8 @@ static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req) struct io_uring_task *tctx = rb->task->io_uring; percpu_counter_sub(&tctx->inflight, rb->task_refs); + if (atomic_read(&tctx->in_idle)) + wake_up(&tctx->wait); put_task_struct_many(rb->task, rb->task_refs); } rb->task = req->task; @@ -3548,7 +3560,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock, /* read it all, or we did blocking attempt. no retry. */ if (!iov_iter_count(iter) || !force_nonblock || - (req->file->f_flags & O_NONBLOCK)) + (req->file->f_flags & O_NONBLOCK) || !(req->flags & REQ_F_ISREG)) goto done; io_size -= ret; @@ -4468,7 +4480,6 @@ static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) * io_wq_work.flags, so initialize io_wq_work firstly. */ io_req_init_async(req); - req->work.flags |= IO_WQ_WORK_NO_CANCEL; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; @@ -4501,6 +4512,8 @@ static int io_close(struct io_kiocb *req, bool force_nonblock, /* if the file has a flush method, be safe and punt to async */ if (close->put_file->f_op->flush && force_nonblock) { + /* not safe to cancel at this point */ + req->work.flags |= IO_WQ_WORK_NO_CANCEL; /* was never set, but play safe */ req->flags &= ~REQ_F_NOWAIT; /* avoid grabbing files - we don't need the files */ @@ -6157,8 +6170,10 @@ static void io_req_drop_files(struct io_kiocb *req) struct io_uring_task *tctx = req->task->io_uring; unsigned long flags; - put_files_struct(req->work.identity->files); - put_nsproxy(req->work.identity->nsproxy); + if (req->work.flags & IO_WQ_WORK_FILES) { + put_files_struct(req->work.identity->files); + put_nsproxy(req->work.identity->nsproxy); + } spin_lock_irqsave(&ctx->inflight_lock, flags); list_del(&req->inflight_entry); spin_unlock_irqrestore(&ctx->inflight_lock, flags); @@ -6225,9 +6240,6 @@ static void __io_clean_op(struct io_kiocb *req) } req->flags &= ~REQ_F_NEED_CLEANUP; } - - if (req->flags & REQ_F_INFLIGHT) - io_req_drop_files(req); } static int io_issue_sqe(struct io_kiocb *req, bool force_nonblock, @@ -6446,6 +6458,15 @@ static struct file *io_file_get(struct io_submit_state *state, file = __io_file_get(state, fd); } + if (file && file->f_op == &io_uring_fops) { + io_req_init_async(req); + req->flags |= REQ_F_INFLIGHT; + + spin_lock_irq(&ctx->inflight_lock); + list_add(&req->inflight_entry, &ctx->inflight_list); + spin_unlock_irq(&ctx->inflight_lock); + } + return file; } @@ -8856,8 +8877,7 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx, spin_lock_irq(&ctx->inflight_lock); list_for_each_entry(req, &ctx->inflight_list, inflight_entry) { - if (req->task != task || - req->work.identity->files != files) + if (!io_match_task(req, task, files)) continue; found = true; break; @@ -8874,6 +8894,7 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx, io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, &cancel, true); io_poll_remove_all(ctx, task, files); io_kill_timeouts(ctx, task, files); + io_cqring_overflow_flush(ctx, true, task, files); /* cancellations _may_ trigger task work */ io_run_task_work(); schedule(); @@ -8914,8 +8935,6 @@ static void __io_uring_cancel_task_requests(struct io_ring_ctx *ctx, static void io_disable_sqo_submit(struct io_ring_ctx *ctx) { - WARN_ON_ONCE(ctx->sqo_task != current); - mutex_lock(&ctx->uring_lock); ctx->sqo_dead = 1; mutex_unlock(&ctx->uring_lock); @@ -8937,6 +8956,7 @@ static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx, if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) { /* for SQPOLL only sqo_task has task notes */ + WARN_ON_ONCE(ctx->sqo_task != current); io_disable_sqo_submit(ctx); task = ctx->sq_data->thread; atomic_inc(&task->io_uring->in_idle); @@ -9082,6 +9102,10 @@ void __io_uring_task_cancel(void) /* make sure overflow events are dropped */ atomic_inc(&tctx->in_idle); + /* trigger io_disable_sqo_submit() */ + if (tctx->sqpoll) + __io_uring_files_cancel(NULL); + do { /* read completions before cancelations */ inflight = tctx_inflight(tctx); @@ -9128,7 +9152,10 @@ static int io_uring_flush(struct file *file, void *data) if (ctx->flags & IORING_SETUP_SQPOLL) { /* there is only one file note, which is owned by sqo_task */ - WARN_ON_ONCE((ctx->sqo_task == current) == + WARN_ON_ONCE(ctx->sqo_task != current && + xa_load(&tctx->xa, (unsigned long)file)); + /* sqo_dead check is for when this happens after cancellation */ + WARN_ON_ONCE(ctx->sqo_task == current && !ctx->sqo_dead && !xa_load(&tctx->xa, (unsigned long)file)); io_disable_sqo_submit(ctx); diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index f277d023ebcd..c75719312147 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -14,6 +14,7 @@ #include #include #include +#include #include "kernfs-internal.h" @@ -180,11 +181,10 @@ static const struct seq_operations kernfs_seq_ops = { * it difficult to use seq_file. Implement simplistic custom buffering for * bin files. */ -static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of, - char __user *user_buf, size_t count, - loff_t *ppos) +static ssize_t kernfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { - ssize_t len = min_t(size_t, count, PAGE_SIZE); + struct kernfs_open_file *of = kernfs_of(iocb->ki_filp); + ssize_t len = min_t(size_t, iov_iter_count(iter), PAGE_SIZE); const struct kernfs_ops *ops; char *buf; @@ -210,7 +210,7 @@ static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of, of->event = atomic_read(&of->kn->attr.open->event); ops = kernfs_ops(of->kn); if (ops->read) - len = ops->read(of, buf, len, *ppos); + len = ops->read(of, buf, len, iocb->ki_pos); else len = -EINVAL; @@ -220,12 +220,12 @@ static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of, if (len < 0) goto out_free; - if (copy_to_user(user_buf, buf, len)) { + if (copy_to_iter(buf, len, iter) != len) { len = -EFAULT; goto out_free; } - *ppos += len; + iocb->ki_pos += len; out_free: if (buf == of->prealloc_buf) @@ -235,31 +235,14 @@ static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of, return len; } -/** - * kernfs_fop_read - kernfs vfs read callback - * @file: file pointer - * @user_buf: data to write - * @count: number of bytes - * @ppos: starting offset - */ -static ssize_t kernfs_fop_read(struct file *file, char __user *user_buf, - size_t count, loff_t *ppos) +static ssize_t kernfs_fop_read_iter(struct kiocb *iocb, struct iov_iter *iter) { - struct kernfs_open_file *of = kernfs_of(file); - - if (of->kn->flags & KERNFS_HAS_SEQ_SHOW) - return seq_read(file, user_buf, count, ppos); - else - return kernfs_file_direct_read(of, user_buf, count, ppos); + if (kernfs_of(iocb->ki_filp)->kn->flags & KERNFS_HAS_SEQ_SHOW) + return seq_read_iter(iocb, iter); + return kernfs_file_read_iter(iocb, iter); } -/** - * kernfs_fop_write - kernfs vfs write callback - * @file: file pointer - * @user_buf: data to write - * @count: number of bytes - * @ppos: starting offset - * +/* * Copy data in from userland and pass it to the matching kernfs write * operation. * @@ -269,20 +252,18 @@ static ssize_t kernfs_fop_read(struct file *file, char __user *user_buf, * modify only the the value you're changing, then write entire buffer * back. */ -static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf, - size_t count, loff_t *ppos) +static ssize_t kernfs_fop_write_iter(struct kiocb *iocb, struct iov_iter *iter) { - struct kernfs_open_file *of = kernfs_of(file); + struct kernfs_open_file *of = kernfs_of(iocb->ki_filp); + ssize_t len = iov_iter_count(iter); const struct kernfs_ops *ops; - ssize_t len; char *buf; if (of->atomic_write_len) { - len = count; if (len > of->atomic_write_len) return -E2BIG; } else { - len = min_t(size_t, count, PAGE_SIZE); + len = min_t(size_t, len, PAGE_SIZE); } buf = of->prealloc_buf; @@ -293,7 +274,7 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf, if (!buf) return -ENOMEM; - if (copy_from_user(buf, user_buf, len)) { + if (copy_from_iter(buf, len, iter) != len) { len = -EFAULT; goto out_free; } @@ -312,7 +293,7 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf, ops = kernfs_ops(of->kn); if (ops->write) - len = ops->write(of, buf, len, *ppos); + len = ops->write(of, buf, len, iocb->ki_pos); else len = -EINVAL; @@ -320,7 +301,7 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf, mutex_unlock(&of->mutex); if (len > 0) - *ppos += len; + iocb->ki_pos += len; out_free: if (buf == of->prealloc_buf) @@ -673,7 +654,7 @@ static int kernfs_fop_open(struct inode *inode, struct file *file) /* * Write path needs to atomic_write_len outside active reference. - * Cache it in open_file. See kernfs_fop_write() for details. + * Cache it in open_file. See kernfs_fop_write_iter() for details. */ of->atomic_write_len = ops->atomic_write_len; @@ -960,14 +941,16 @@ void kernfs_notify(struct kernfs_node *kn) EXPORT_SYMBOL_GPL(kernfs_notify); const struct file_operations kernfs_file_fops = { - .read = kernfs_fop_read, - .write = kernfs_fop_write, + .read_iter = kernfs_fop_read_iter, + .write_iter = kernfs_fop_write_iter, .llseek = generic_file_llseek, .mmap = kernfs_fop_mmap, .open = kernfs_fop_open, .release = kernfs_fop_release, .poll = kernfs_fop_poll, .fsync = noop_fsync, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, }; /** diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 317899222d7f..d2018f70d1fa 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1770,6 +1770,12 @@ static int process_sysctl_arg(char *param, char *val, return 0; } + if (!val) + return -EINVAL; + len = strlen(val); + if (len == 0) + return -EINVAL; + /* * To set sysctl options, we use a temporary mount of proc, look up the * respective sys/ file and write to it. To avoid mounting it when no @@ -1811,7 +1817,6 @@ static int process_sysctl_arg(char *param, char *val, file, param, val); goto out; } - len = strlen(val); wret = kernel_write(file, val, len, &pos); if (wret < 0) { err = wret; diff --git a/include/linux/device.h b/include/linux/device.h index 89bb8b84173e..1779f90eeb4c 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -609,6 +609,18 @@ static inline const char *dev_name(const struct device *dev) return kobject_name(&dev->kobj); } +/** + * dev_bus_name - Return a device's bus/class name, if at all possible + * @dev: struct device to get the bus/class name of + * + * Will return the name of the bus/class the device is attached to. If it is + * not attached to a bus/class, an empty string will be returned. + */ +static inline const char *dev_bus_name(const struct device *dev) +{ + return dev->bus ? dev->bus->name : (dev->class ? dev->class->name : ""); +} + __printf(2, 3) int dev_set_name(struct device *dev, const char *name, ...); #ifdef CONFIG_NUMA diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 65b81e0c494d..2484ed97e72f 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -33,6 +33,9 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), unsigned int cpu, const char *namefmt); +void kthread_set_per_cpu(struct task_struct *k, int cpu); +bool kthread_is_per_cpu(struct task_struct *k); + /** * kthread_run - create and wake a thread. * @threadfn: the function to run until signal_pending(current). diff --git a/include/linux/ktime.h b/include/linux/ktime.h index a12b5523cc18..73f20deb497d 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -230,6 +230,5 @@ static inline ktime_t ms_to_ktime(u64 ms) } # include -# include #endif diff --git a/include/linux/nvme.h b/include/linux/nvme.h index d92535997687..bfed36e342cc 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -116,6 +116,9 @@ enum { NVME_REG_BPMBL = 0x0048, /* Boot Partition Memory Buffer * Location */ + NVME_REG_CMBMSC = 0x0050, /* Controller Memory Buffer Memory + * Space Control + */ NVME_REG_PMRCAP = 0x0e00, /* Persistent Memory Capabilities */ NVME_REG_PMRCTL = 0x0e04, /* Persistent Memory Region Control */ NVME_REG_PMRSTS = 0x0e08, /* Persistent Memory Region Status */ @@ -135,6 +138,7 @@ enum { #define NVME_CAP_CSS(cap) (((cap) >> 37) & 0xff) #define NVME_CAP_MPSMIN(cap) (((cap) >> 48) & 0xf) #define NVME_CAP_MPSMAX(cap) (((cap) >> 52) & 0xf) +#define NVME_CAP_CMBS(cap) (((cap) >> 57) & 0x1) #define NVME_CMB_BIR(cmbloc) ((cmbloc) & 0x7) #define NVME_CMB_OFST(cmbloc) (((cmbloc) >> 12) & 0xfffff) @@ -192,6 +196,8 @@ enum { NVME_CSTS_SHST_OCCUR = 1 << 2, NVME_CSTS_SHST_CMPLT = 2 << 2, NVME_CSTS_SHST_MASK = 3 << 2, + NVME_CMBMSC_CRE = 1 << 0, + NVME_CMBMSC_CMSE = 1 << 1, }; struct nvme_id_power_state { diff --git a/include/linux/timekeeping32.h b/include/linux/timekeeping32.h deleted file mode 100644 index 266017fc9ee9..000000000000 --- a/include/linux/timekeeping32.h +++ /dev/null @@ -1,14 +0,0 @@ -#ifndef _LINUX_TIMEKEEPING32_H -#define _LINUX_TIMEKEEPING32_H -/* - * These interfaces are all based on the old timespec type - * and should get replaced with the timespec64 based versions - * over time so we can remove the file here. - */ - -static inline unsigned long get_seconds(void) -{ - return ktime_get_real_seconds(); -} - -#endif diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index 27a0a64433ae..483732858e0d 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -366,7 +366,7 @@ TRACE_EVENT(sched_process_wait, ); /* - * Tracepoint for do_fork: + * Tracepoint for kernel_clone: */ TRACE_EVENT(sched_process_fork, diff --git a/kernel/fork.c b/kernel/fork.c index 1a8aeed7fbb4..e3d54415015e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -822,9 +822,8 @@ void __init fork_init(void) init_task.signal->rlim[RLIMIT_SIGPENDING] = init_task.signal->rlim[RLIMIT_NPROC]; - for (i = 0; i < UCOUNT_COUNTS; i++) { + for (i = 0; i < UCOUNT_COUNTS; i++) init_user_ns.ucount_max[i] = max_threads/2; - } #ifdef CONFIG_VMAP_STACK cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache", @@ -1657,9 +1656,8 @@ static inline void init_task_pid_links(struct task_struct *task) { enum pid_type type; - for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) { + for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) INIT_HLIST_NODE(&task->pid_links[type]); - } } static inline void diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 2c0c4d6d0f83..dc0e2d7fbdfd 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -402,7 +402,7 @@ int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, struct msi_domain_ops *ops = info->ops; struct irq_data *irq_data; struct msi_desc *desc; - msi_alloc_info_t arg; + msi_alloc_info_t arg = { }; int i, ret, virq; bool can_reserve; diff --git a/kernel/kthread.c b/kernel/kthread.c index 8e857f100a29..028cff2576ef 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -294,7 +294,7 @@ static int kthread(void *_create) do_exit(ret); } -/* called from do_fork() to get node information for about to be created task */ +/* called from kernel_clone() to get node information for about to be created task */ int tsk_fork_get_node(struct task_struct *tsk) { #ifdef CONFIG_NUMA @@ -494,11 +494,36 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), return p; kthread_bind(p, cpu); /* CPU hotplug need to bind once again when unparking the thread. */ - set_bit(KTHREAD_IS_PER_CPU, &to_kthread(p)->flags); to_kthread(p)->cpu = cpu; return p; } +void kthread_set_per_cpu(struct task_struct *k, int cpu) +{ + struct kthread *kthread = to_kthread(k); + if (!kthread) + return; + + WARN_ON_ONCE(!(k->flags & PF_NO_SETAFFINITY)); + + if (cpu < 0) { + clear_bit(KTHREAD_IS_PER_CPU, &kthread->flags); + return; + } + + kthread->cpu = cpu; + set_bit(KTHREAD_IS_PER_CPU, &kthread->flags); +} + +bool kthread_is_per_cpu(struct task_struct *k) +{ + struct kthread *kthread = to_kthread(k); + if (!kthread) + return false; + + return test_bit(KTHREAD_IS_PER_CPU, &kthread->flags); +} + /** * kthread_unpark - unpark a thread created by kthread_create(). * @k: thread created by kthread_create(). diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index c1418b47f625..bdaf4829098c 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -79,7 +79,7 @@ module_param(lock_stat, int, 0644); DEFINE_PER_CPU(unsigned int, lockdep_recursion); EXPORT_PER_CPU_SYMBOL_GPL(lockdep_recursion); -static inline bool lockdep_enabled(void) +static __always_inline bool lockdep_enabled(void) { if (!debug_locks) return false; @@ -5271,12 +5271,15 @@ static void __lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie cookie /* * Check whether we follow the irq-flags state precisely: */ -static void check_flags(unsigned long flags) +static noinstr void check_flags(unsigned long flags) { #if defined(CONFIG_PROVE_LOCKING) && defined(CONFIG_DEBUG_LOCKDEP) if (!debug_locks) return; + /* Get the warning out.. */ + instrumentation_begin(); + if (irqs_disabled_flags(flags)) { if (DEBUG_LOCKS_WARN_ON(lockdep_hardirqs_enabled())) { printk("possible reason: unannotated irqs-off.\n"); @@ -5304,6 +5307,8 @@ static void check_flags(unsigned long flags) if (!debug_locks) print_irqtrace_events(current); + + instrumentation_end(); #endif } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 06c495196256..b9a19b575ac3 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1815,13 +1815,28 @@ static inline bool rq_has_pinned_tasks(struct rq *rq) */ static inline bool is_cpu_allowed(struct task_struct *p, int cpu) { + /* When not in the task's cpumask, no point in looking further. */ if (!cpumask_test_cpu(cpu, p->cpus_ptr)) return false; - if (is_per_cpu_kthread(p) || is_migration_disabled(p)) + /* migrate_disabled() must be allowed to finish. */ + if (is_migration_disabled(p)) return cpu_online(cpu); - return cpu_active(cpu); + /* Non kernel threads are not allowed during either online or offline. */ + if (!(p->flags & PF_KTHREAD)) + return cpu_active(cpu); + + /* KTHREAD_IS_PER_CPU is always allowed. */ + if (kthread_is_per_cpu(p)) + return cpu_online(cpu); + + /* Regular kernel threads don't get to stay during offline. */ + if (cpu_rq(cpu)->balance_push) + return false; + + /* But are allowed during online. */ + return cpu_online(cpu); } /* @@ -2358,7 +2373,9 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, if (p->flags & PF_KTHREAD || is_migration_disabled(p)) { /* - * Kernel threads are allowed on online && !active CPUs. + * Kernel threads are allowed on online && !active CPUs, + * however, during cpu-hot-unplug, even these might get pushed + * away if not KTHREAD_IS_PER_CPU. * * Specifically, migration_disabled() tasks must not fail the * cpumask_any_and_distribute() pick below, esp. so on @@ -2402,16 +2419,6 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, __do_set_cpus_allowed(p, new_mask, flags); - if (p->flags & PF_KTHREAD) { - /* - * For kernel threads that do indeed end up on online && - * !active we want to ensure they are strict per-CPU threads. - */ - WARN_ON(cpumask_intersects(new_mask, cpu_online_mask) && - !cpumask_intersects(new_mask, cpu_active_mask) && - p->nr_cpus_allowed != 1); - } - return affine_move_task(rq, p, &rf, dest_cpu, flags); out: @@ -3157,6 +3164,13 @@ bool cpus_share_cache(int this_cpu, int that_cpu) static inline bool ttwu_queue_cond(int cpu, int wake_flags) { + /* + * Do not complicate things with the async wake_list while the CPU is + * in hotplug state. + */ + if (!cpu_active(cpu)) + return false; + /* * If the CPU does not share cache, then queue the task on the * remote rqs wakelist to avoid accessing remote data. @@ -7315,8 +7329,14 @@ static void balance_push(struct rq *rq) /* * Both the cpu-hotplug and stop task are in this case and are * required to complete the hotplug process. + * + * XXX: the idle task does not match kthread_is_per_cpu() due to + * histerical raisins. */ - if (is_per_cpu_kthread(push_task) || is_migration_disabled(push_task)) { + if (rq->idle == push_task || + ((push_task->flags & PF_KTHREAD) && kthread_is_per_cpu(push_task)) || + is_migration_disabled(push_task)) { + /* * If this is the idle task on the outgoing CPU try to wake * up the hotplug control thread which might wait for the @@ -7348,7 +7368,7 @@ static void balance_push(struct rq *rq) /* * At this point need_resched() is true and we'll take the loop in * schedule(). The next pick is obviously going to be the stop task - * which is_per_cpu_kthread() and will push this task away. + * which kthread_is_per_cpu() and will push this task away. */ raw_spin_lock(&rq->lock); } @@ -7359,10 +7379,13 @@ static void balance_push_set(int cpu, bool on) struct rq_flags rf; rq_lock_irqsave(rq, &rf); - if (on) + rq->balance_push = on; + if (on) { + WARN_ON_ONCE(rq->balance_callback); rq->balance_callback = &balance_push_callback; - else + } else if (rq->balance_callback == &balance_push_callback) { rq->balance_callback = NULL; + } rq_unlock_irqrestore(rq, &rf); } @@ -7480,6 +7503,10 @@ int sched_cpu_activate(unsigned int cpu) struct rq *rq = cpu_rq(cpu); struct rq_flags rf; + /* + * Make sure that when the hotplug state machine does a roll-back + * we clear balance_push. Ideally that would happen earlier... + */ balance_push_set(cpu, false); #ifdef CONFIG_SCHED_SMT @@ -7522,17 +7549,27 @@ int sched_cpu_deactivate(unsigned int cpu) int ret; set_cpu_active(cpu, false); + /* - * We've cleared cpu_active_mask, wait for all preempt-disabled and RCU - * users of this state to go away such that all new such users will - * observe it. + * From this point forward, this CPU will refuse to run any task that + * is not: migrate_disable() or KTHREAD_IS_PER_CPU, and will actively + * push those tasks away until this gets cleared, see + * sched_cpu_dying(). + */ + balance_push_set(cpu, true); + + /* + * We've cleared cpu_active_mask / set balance_push, wait for all + * preempt-disabled and RCU users of this state to go away such that + * all new such users will observe it. + * + * Specifically, we rely on ttwu to no longer target this CPU, see + * ttwu_queue_cond() and is_cpu_allowed(). * * Do sync before park smpboot threads to take care the rcu boost case. */ synchronize_rcu(); - balance_push_set(cpu, true); - rq_lock_irqsave(rq, &rf); if (rq->rd) { update_rq_clock(rq); @@ -7613,6 +7650,25 @@ static void calc_load_migrate(struct rq *rq) atomic_long_add(delta, &calc_load_tasks); } +static void dump_rq_tasks(struct rq *rq, const char *loglvl) +{ + struct task_struct *g, *p; + int cpu = cpu_of(rq); + + lockdep_assert_held(&rq->lock); + + printk("%sCPU%d enqueued tasks (%u total):\n", loglvl, cpu, rq->nr_running); + for_each_process_thread(g, p) { + if (task_cpu(p) != cpu) + continue; + + if (!task_on_rq_queued(p)) + continue; + + printk("%s\tpid: %d, name: %s\n", loglvl, p->pid, p->comm); + } +} + int sched_cpu_dying(unsigned int cpu) { struct rq *rq = cpu_rq(cpu); @@ -7622,9 +7678,18 @@ int sched_cpu_dying(unsigned int cpu) sched_tick_stop(cpu); rq_lock_irqsave(rq, &rf); - BUG_ON(rq->nr_running != 1 || rq_has_pinned_tasks(rq)); + if (rq->nr_running != 1 || rq_has_pinned_tasks(rq)) { + WARN(true, "Dying CPU not properly vacated!"); + dump_rq_tasks(rq, KERN_WARNING); + } rq_unlock_irqrestore(rq, &rf); + /* + * Now that the CPU is offline, make sure we're welcome + * to new tasks once we come back up. + */ + balance_push_set(cpu, false); + calc_load_migrate(rq); update_max_interval(); nohz_balance_exit_idle(rq); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 8bcaf42b717a..063cec8749d5 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -982,6 +982,7 @@ struct rq { unsigned long cpu_capacity_orig; struct callback_head *balance_callback; + unsigned char balance_push; unsigned char nohz_idle_balance; unsigned char idle_balance; diff --git a/kernel/signal.c b/kernel/signal.c index bc52aa0035f6..2d24e3769301 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -3705,7 +3705,8 @@ static bool access_pidfd_pidns(struct pid *pid) return true; } -static int copy_siginfo_from_user_any(kernel_siginfo_t *kinfo, siginfo_t *info) +static int copy_siginfo_from_user_any(kernel_siginfo_t *kinfo, + siginfo_t __user *info) { #ifdef CONFIG_COMPAT /* diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 2efe1e206167..f25208e8df83 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -188,6 +188,7 @@ __smpboot_create_thread(struct smp_hotplug_thread *ht, unsigned int cpu) kfree(td); return PTR_ERR(tsk); } + kthread_set_per_cpu(tsk, cpu); /* * Park the thread so that it could start right on the CPU * when it is available. diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 7404d3831527..87389b9e21ab 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -498,7 +498,7 @@ int second_overflow(time64_t secs) static void sync_hw_clock(struct work_struct *work); static DECLARE_WORK(sync_work, sync_hw_clock); static struct hrtimer sync_hrtimer; -#define SYNC_PERIOD_NS (11UL * 60 * NSEC_PER_SEC) +#define SYNC_PERIOD_NS (11ULL * 60 * NSEC_PER_SEC) static enum hrtimer_restart sync_timer_callback(struct hrtimer *timer) { @@ -512,7 +512,7 @@ static void sched_sync_hw_clock(unsigned long offset_nsec, bool retry) ktime_t exp = ktime_set(ktime_get_real_seconds(), 0); if (retry) - exp = ktime_add_ns(exp, 2 * NSEC_PER_SEC - offset_nsec); + exp = ktime_add_ns(exp, 2ULL * NSEC_PER_SEC - offset_nsec); else exp = ktime_add_ns(exp, SYNC_PERIOD_NS - offset_nsec); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index a45cedda93a7..6aee5768c86f 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -991,8 +991,7 @@ EXPORT_SYMBOL_GPL(ktime_get_seconds); /** * ktime_get_real_seconds - Get the seconds portion of CLOCK_REALTIME * - * Returns the wall clock seconds since 1970. This replaces the - * get_seconds() interface which is not y2038 safe on 32bit systems. + * Returns the wall clock seconds since 1970. * * For 64bit systems the fast access to tk->xtime_sec is preserved. On * 32bit systems the access must be protected with the sequence diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 7add67d78119..00957eafdf6c 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1852,12 +1852,6 @@ static void worker_attach_to_pool(struct worker *worker, { mutex_lock(&wq_pool_attach_mutex); - /* - * set_cpus_allowed_ptr() will fail if the cpumask doesn't have any - * online CPUs. It'll be re-applied when any of the CPUs come up. - */ - set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask); - /* * The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains * stable across this function. See the comments above the flag @@ -1865,6 +1859,11 @@ static void worker_attach_to_pool(struct worker *worker, */ if (pool->flags & POOL_DISASSOCIATED) worker->flags |= WORKER_UNBOUND; + else + kthread_set_per_cpu(worker->task, pool->cpu); + + if (worker->rescue_wq) + set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask); list_add_tail(&worker->node, &pool->workers); worker->pool = pool; @@ -1887,6 +1886,7 @@ static void worker_detach_from_pool(struct worker *worker) mutex_lock(&wq_pool_attach_mutex); + kthread_set_per_cpu(worker->task, -1); list_del(&worker->node); worker->pool = NULL; @@ -4923,8 +4923,10 @@ static void unbind_workers(int cpu) raw_spin_unlock_irq(&pool->lock); - for_each_pool_worker(worker, pool) - WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_active_mask) < 0); + for_each_pool_worker(worker, pool) { + kthread_set_per_cpu(worker->task, -1); + WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_possible_mask) < 0); + } mutex_unlock(&wq_pool_attach_mutex); @@ -4976,9 +4978,11 @@ static void rebind_workers(struct worker_pool *pool) * of all workers first and then clear UNBOUND. As we're called * from CPU_ONLINE, the following shouldn't fail. */ - for_each_pool_worker(worker, pool) + for_each_pool_worker(worker, pool) { + kthread_set_per_cpu(worker->task, pool->cpu); WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask) < 0); + } raw_spin_lock_irq(&pool->lock); diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan index 14482cd85857..f09d33be44dc 100644 --- a/lib/Kconfig.ubsan +++ b/lib/Kconfig.ubsan @@ -123,6 +123,7 @@ config UBSAN_SIGNED_OVERFLOW config UBSAN_UNSIGNED_OVERFLOW bool "Perform checking for unsigned arithmetic overflow" depends on $(cc-option,-fsanitize=unsigned-integer-overflow) + depends on !X86_32 # avoid excessive stack usage on x86-32/clang help This option enables -fsanitize=unsigned-integer-overflow which checks for overflow of any arithmetic operations with unsigned integers. This diff --git a/mm/highmem.c b/mm/highmem.c index c3a9ea7875ef..874b732b120c 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -473,6 +473,11 @@ static inline void *arch_kmap_local_high_get(struct page *page) } #endif +#ifndef arch_kmap_local_set_pte +#define arch_kmap_local_set_pte(mm, vaddr, ptep, ptev) \ + set_pte_at(mm, vaddr, ptep, ptev) +#endif + /* Unmap a local mapping which was obtained by kmap_high_get() */ static inline bool kmap_high_unmap_local(unsigned long vaddr) { @@ -515,7 +520,7 @@ void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot) vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); BUG_ON(!pte_none(*(kmap_pte - idx))); pteval = pfn_pte(pfn, prot); - set_pte_at(&init_mm, vaddr, kmap_pte - idx, pteval); + arch_kmap_local_set_pte(&init_mm, vaddr, kmap_pte - idx, pteval); arch_kmap_local_post_map(vaddr, pteval); current->kmap_ctrl.pteval[kmap_local_idx()] = pteval; preempt_enable(); diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c index 55bd6f09c70f..e529428e7a11 100644 --- a/mm/kasan/hw_tags.c +++ b/mm/kasan/hw_tags.c @@ -19,11 +19,10 @@ #include "kasan.h" -enum kasan_arg_mode { - KASAN_ARG_MODE_DEFAULT, - KASAN_ARG_MODE_OFF, - KASAN_ARG_MODE_PROD, - KASAN_ARG_MODE_FULL, +enum kasan_arg { + KASAN_ARG_DEFAULT, + KASAN_ARG_OFF, + KASAN_ARG_ON, }; enum kasan_arg_stacktrace { @@ -38,7 +37,7 @@ enum kasan_arg_fault { KASAN_ARG_FAULT_PANIC, }; -static enum kasan_arg_mode kasan_arg_mode __ro_after_init; +static enum kasan_arg kasan_arg __ro_after_init; static enum kasan_arg_stacktrace kasan_arg_stacktrace __ro_after_init; static enum kasan_arg_fault kasan_arg_fault __ro_after_init; @@ -52,26 +51,24 @@ DEFINE_STATIC_KEY_FALSE(kasan_flag_stacktrace); /* Whether panic or disable tag checking on fault. */ bool kasan_flag_panic __ro_after_init; -/* kasan.mode=off/prod/full */ -static int __init early_kasan_mode(char *arg) +/* kasan=off/on */ +static int __init early_kasan_flag(char *arg) { if (!arg) return -EINVAL; if (!strcmp(arg, "off")) - kasan_arg_mode = KASAN_ARG_MODE_OFF; - else if (!strcmp(arg, "prod")) - kasan_arg_mode = KASAN_ARG_MODE_PROD; - else if (!strcmp(arg, "full")) - kasan_arg_mode = KASAN_ARG_MODE_FULL; + kasan_arg = KASAN_ARG_OFF; + else if (!strcmp(arg, "on")) + kasan_arg = KASAN_ARG_ON; else return -EINVAL; return 0; } -early_param("kasan.mode", early_kasan_mode); +early_param("kasan", early_kasan_flag); -/* kasan.stack=off/on */ +/* kasan.stacktrace=off/on */ static int __init early_kasan_flag_stacktrace(char *arg) { if (!arg) @@ -113,8 +110,8 @@ void kasan_init_hw_tags_cpu(void) * as this function is only called for MTE-capable hardware. */ - /* If KASAN is disabled, do nothing. */ - if (kasan_arg_mode == KASAN_ARG_MODE_OFF) + /* If KASAN is disabled via command line, don't initialize it. */ + if (kasan_arg == KASAN_ARG_OFF) return; hw_init_tags(KASAN_TAG_MAX); @@ -124,43 +121,28 @@ void kasan_init_hw_tags_cpu(void) /* kasan_init_hw_tags() is called once on boot CPU. */ void __init kasan_init_hw_tags(void) { - /* If hardware doesn't support MTE, do nothing. */ + /* If hardware doesn't support MTE, don't initialize KASAN. */ if (!system_supports_mte()) return; - /* Choose KASAN mode if kasan boot parameter is not provided. */ - if (kasan_arg_mode == KASAN_ARG_MODE_DEFAULT) { - if (IS_ENABLED(CONFIG_DEBUG_KERNEL)) - kasan_arg_mode = KASAN_ARG_MODE_FULL; - else - kasan_arg_mode = KASAN_ARG_MODE_PROD; - } - - /* Preset parameter values based on the mode. */ - switch (kasan_arg_mode) { - case KASAN_ARG_MODE_DEFAULT: - /* Shouldn't happen as per the check above. */ - WARN_ON(1); + /* If KASAN is disabled via command line, don't initialize it. */ + if (kasan_arg == KASAN_ARG_OFF) return; - case KASAN_ARG_MODE_OFF: - /* If KASAN is disabled, do nothing. */ - return; - case KASAN_ARG_MODE_PROD: - static_branch_enable(&kasan_flag_enabled); - break; - case KASAN_ARG_MODE_FULL: - static_branch_enable(&kasan_flag_enabled); - static_branch_enable(&kasan_flag_stacktrace); - break; - } - /* Now, optionally override the presets. */ + /* Enable KASAN. */ + static_branch_enable(&kasan_flag_enabled); switch (kasan_arg_stacktrace) { case KASAN_ARG_STACKTRACE_DEFAULT: + /* + * Default to enabling stack trace collection for + * debug kernels. + */ + if (IS_ENABLED(CONFIG_DEBUG_KERNEL)) + static_branch_enable(&kasan_flag_stacktrace); break; case KASAN_ARG_STACKTRACE_OFF: - static_branch_disable(&kasan_flag_stacktrace); + /* Do nothing, kasan_flag_stacktrace keeps its default value. */ break; case KASAN_ARG_STACKTRACE_ON: static_branch_enable(&kasan_flag_stacktrace); @@ -169,11 +151,16 @@ void __init kasan_init_hw_tags(void) switch (kasan_arg_fault) { case KASAN_ARG_FAULT_DEFAULT: + /* + * Default to no panic on report. + * Do nothing, kasan_flag_panic keeps its default value. + */ break; case KASAN_ARG_FAULT_REPORT: - kasan_flag_panic = false; + /* Do nothing, kasan_flag_panic keeps its default value. */ break; case KASAN_ARG_FAULT_PANIC: + /* Enable panic on report. */ kasan_flag_panic = true; break; } diff --git a/mm/kasan/init.c b/mm/kasan/init.c index 7ca0b92d5886..c4605ac9837b 100644 --- a/mm/kasan/init.c +++ b/mm/kasan/init.c @@ -373,9 +373,10 @@ static void kasan_remove_pmd_table(pmd_t *pmd, unsigned long addr, if (kasan_pte_table(*pmd)) { if (IS_ALIGNED(addr, PMD_SIZE) && - IS_ALIGNED(next, PMD_SIZE)) + IS_ALIGNED(next, PMD_SIZE)) { pmd_clear(pmd); - continue; + continue; + } } pte = pte_offset_kernel(pmd, addr); kasan_remove_pte_table(pte, addr, next); @@ -398,9 +399,10 @@ static void kasan_remove_pud_table(pud_t *pud, unsigned long addr, if (kasan_pmd_table(*pud)) { if (IS_ALIGNED(addr, PUD_SIZE) && - IS_ALIGNED(next, PUD_SIZE)) + IS_ALIGNED(next, PUD_SIZE)) { pud_clear(pud); - continue; + continue; + } } pmd = pmd_offset(pud, addr); pmd_base = pmd_offset(pud, 0); @@ -424,9 +426,10 @@ static void kasan_remove_p4d_table(p4d_t *p4d, unsigned long addr, if (kasan_pud_table(*p4d)) { if (IS_ALIGNED(addr, P4D_SIZE) && - IS_ALIGNED(next, P4D_SIZE)) + IS_ALIGNED(next, P4D_SIZE)) { p4d_clear(p4d); - continue; + continue; + } } pud = pud_offset(p4d, addr); kasan_remove_pud_table(pud, addr, next); @@ -457,9 +460,10 @@ void kasan_remove_zero_shadow(void *start, unsigned long size) if (kasan_p4d_table(*pgd)) { if (IS_ALIGNED(addr, PGDIR_SIZE) && - IS_ALIGNED(next, PGDIR_SIZE)) + IS_ALIGNED(next, PGDIR_SIZE)) { pgd_clear(pgd); - continue; + continue; + } } p4d = p4d_offset(pgd, addr); @@ -482,7 +486,6 @@ int kasan_add_zero_shadow(void *start, unsigned long size) ret = kasan_populate_early_shadow(shadow_start, shadow_end); if (ret) - kasan_remove_zero_shadow(shadow_start, - size >> KASAN_SHADOW_SCALE_SHIFT); + kasan_remove_zero_shadow(start, size); return ret; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 605f671203ef..e2de77b5bcc2 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3115,9 +3115,7 @@ void __memcg_kmem_uncharge(struct mem_cgroup *memcg, unsigned int nr_pages) if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) page_counter_uncharge(&memcg->kmem, nr_pages); - page_counter_uncharge(&memcg->memory, nr_pages); - if (do_memsw_account()) - page_counter_uncharge(&memcg->memsw, nr_pages); + refill_stock(memcg, nr_pages); } /** diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 04d9f154a130..e9481632fcd1 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1885,6 +1885,12 @@ static int soft_offline_free_page(struct page *page) return rc; } +static void put_ref_page(struct page *page) +{ + if (page) + put_page(page); +} + /** * soft_offline_page - Soft offline a page. * @pfn: pfn to soft-offline @@ -1910,20 +1916,26 @@ static int soft_offline_free_page(struct page *page) int soft_offline_page(unsigned long pfn, int flags) { int ret; - struct page *page; bool try_again = true; + struct page *page, *ref_page = NULL; + + WARN_ON_ONCE(!pfn_valid(pfn) && (flags & MF_COUNT_INCREASED)); if (!pfn_valid(pfn)) return -ENXIO; + if (flags & MF_COUNT_INCREASED) + ref_page = pfn_to_page(pfn); + /* Only online pages can be soft-offlined (esp., not ZONE_DEVICE). */ page = pfn_to_online_page(pfn); - if (!page) + if (!page) { + put_ref_page(ref_page); return -EIO; + } if (PageHWPoison(page)) { pr_info("%s: %#lx page already poisoned\n", __func__, pfn); - if (flags & MF_COUNT_INCREASED) - put_page(page); + put_ref_page(ref_page); return 0; } diff --git a/mm/migrate.c b/mm/migrate.c index ee5e612b4cd8..c0efe921bca5 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -402,6 +402,7 @@ int migrate_page_move_mapping(struct address_space *mapping, struct zone *oldzone, *newzone; int dirty; int expected_count = expected_page_refs(mapping, page) + extra_count; + int nr = thp_nr_pages(page); if (!mapping) { /* Anonymous page without mapping */ @@ -437,7 +438,7 @@ int migrate_page_move_mapping(struct address_space *mapping, */ newpage->index = page->index; newpage->mapping = page->mapping; - page_ref_add(newpage, thp_nr_pages(page)); /* add cache reference */ + page_ref_add(newpage, nr); /* add cache reference */ if (PageSwapBacked(page)) { __SetPageSwapBacked(newpage); if (PageSwapCache(page)) { @@ -459,7 +460,7 @@ int migrate_page_move_mapping(struct address_space *mapping, if (PageTransHuge(page)) { int i; - for (i = 1; i < HPAGE_PMD_NR; i++) { + for (i = 1; i < nr; i++) { xas_next(&xas); xas_store(&xas, newpage); } @@ -470,7 +471,7 @@ int migrate_page_move_mapping(struct address_space *mapping, * to one less reference. * We know this isn't the last reference. */ - page_ref_unfreeze(page, expected_count - thp_nr_pages(page)); + page_ref_unfreeze(page, expected_count - nr); xas_unlock(&xas); /* Leave irq disabled to prevent preemption while updating stats */ @@ -493,17 +494,17 @@ int migrate_page_move_mapping(struct address_space *mapping, old_lruvec = mem_cgroup_lruvec(memcg, oldzone->zone_pgdat); new_lruvec = mem_cgroup_lruvec(memcg, newzone->zone_pgdat); - __dec_lruvec_state(old_lruvec, NR_FILE_PAGES); - __inc_lruvec_state(new_lruvec, NR_FILE_PAGES); + __mod_lruvec_state(old_lruvec, NR_FILE_PAGES, -nr); + __mod_lruvec_state(new_lruvec, NR_FILE_PAGES, nr); if (PageSwapBacked(page) && !PageSwapCache(page)) { - __dec_lruvec_state(old_lruvec, NR_SHMEM); - __inc_lruvec_state(new_lruvec, NR_SHMEM); + __mod_lruvec_state(old_lruvec, NR_SHMEM, -nr); + __mod_lruvec_state(new_lruvec, NR_SHMEM, nr); } if (dirty && mapping_can_writeback(mapping)) { - __dec_node_state(oldzone->zone_pgdat, NR_FILE_DIRTY); - __dec_zone_state(oldzone, NR_ZONE_WRITE_PENDING); - __inc_node_state(newzone->zone_pgdat, NR_FILE_DIRTY); - __inc_zone_state(newzone, NR_ZONE_WRITE_PENDING); + __mod_lruvec_state(old_lruvec, NR_FILE_DIRTY, -nr); + __mod_zone_page_state(oldzone, NR_ZONE_WRITE_PENDING, -nr); + __mod_lruvec_state(new_lruvec, NR_FILE_DIRTY, nr); + __mod_zone_page_state(newzone, NR_ZONE_WRITE_PENDING, nr); } } local_irq_enable(); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 9043009e28c2..95c51ab69fcf 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1219,8 +1219,10 @@ static void kernel_init_free_pages(struct page *page, int numpages) /* s390's use of memset() could override KASAN redzones. */ kasan_disable_current(); for (i = 0; i < numpages; i++) { + u8 tag = page_kasan_tag(page + i); page_kasan_tag_reset(page + i); clear_highpage(page + i); + page_kasan_tag_set(page + i, tag); } kasan_enable_current(); } @@ -7090,23 +7092,26 @@ void __init free_area_init_memoryless_node(int nid) * Initialize all valid struct pages in the range [spfn, epfn) and mark them * PageReserved(). Return the number of struct pages that were initialized. */ -static u64 __init init_unavailable_range(unsigned long spfn, unsigned long epfn) +static u64 __init init_unavailable_range(unsigned long spfn, unsigned long epfn, + int zone, int nid) { - unsigned long pfn; + unsigned long pfn, zone_spfn, zone_epfn; u64 pgcnt = 0; + zone_spfn = arch_zone_lowest_possible_pfn[zone]; + zone_epfn = arch_zone_highest_possible_pfn[zone]; + + spfn = clamp(spfn, zone_spfn, zone_epfn); + epfn = clamp(epfn, zone_spfn, zone_epfn); + for (pfn = spfn; pfn < epfn; pfn++) { if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) { pfn = ALIGN_DOWN(pfn, pageblock_nr_pages) + pageblock_nr_pages - 1; continue; } - /* - * Use a fake node/zone (0) for now. Some of these pages - * (in memblock.reserved but not in memblock.memory) will - * get re-initialized via reserve_bootmem_region() later. - */ - __init_single_page(pfn_to_page(pfn), pfn, 0, 0); + + __init_single_page(pfn_to_page(pfn), pfn, zone, nid); __SetPageReserved(pfn_to_page(pfn)); pgcnt++; } @@ -7115,51 +7120,64 @@ static u64 __init init_unavailable_range(unsigned long spfn, unsigned long epfn) } /* - * Only struct pages that are backed by physical memory are zeroed and - * initialized by going through __init_single_page(). But, there are some - * struct pages which are reserved in memblock allocator and their fields - * may be accessed (for example page_to_pfn() on some configuration accesses - * flags). We must explicitly initialize those struct pages. + * Only struct pages that correspond to ranges defined by memblock.memory + * are zeroed and initialized by going through __init_single_page() during + * memmap_init(). * - * This function also addresses a similar issue where struct pages are left - * uninitialized because the physical address range is not covered by - * memblock.memory or memblock.reserved. That could happen when memblock - * layout is manually configured via memmap=, or when the highest physical - * address (max_pfn) does not end on a section boundary. + * But, there could be struct pages that correspond to holes in + * memblock.memory. This can happen because of the following reasons: + * - phyiscal memory bank size is not necessarily the exact multiple of the + * arbitrary section size + * - early reserved memory may not be listed in memblock.memory + * - memory layouts defined with memmap= kernel parameter may not align + * nicely with memmap sections + * + * Explicitly initialize those struct pages so that: + * - PG_Reserved is set + * - zone link is set accorging to the architecture constrains + * - node is set to node id of the next populated region except for the + * trailing hole where last node id is used */ -static void __init init_unavailable_mem(void) +static void __init init_zone_unavailable_mem(int zone) { - phys_addr_t start, end; - u64 i, pgcnt; - phys_addr_t next = 0; + unsigned long start, end; + int i, nid; + u64 pgcnt; + unsigned long next = 0; /* - * Loop through unavailable ranges not covered by memblock.memory. + * Loop through holes in memblock.memory and initialize struct + * pages corresponding to these holes */ pgcnt = 0; - for_each_mem_range(i, &start, &end) { + for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, &nid) { if (next < start) - pgcnt += init_unavailable_range(PFN_DOWN(next), - PFN_UP(start)); + pgcnt += init_unavailable_range(next, start, zone, nid); next = end; } /* - * Early sections always have a fully populated memmap for the whole - * section - see pfn_valid(). If the last section has holes at the - * end and that section is marked "online", the memmap will be - * considered initialized. Make sure that memmap has a well defined - * state. + * Last section may surpass the actual end of memory (e.g. we can + * have 1Gb section and 512Mb of RAM pouplated). + * Make sure that memmap has a well defined state in this case. */ - pgcnt += init_unavailable_range(PFN_DOWN(next), - round_up(max_pfn, PAGES_PER_SECTION)); + end = round_up(max_pfn, PAGES_PER_SECTION); + pgcnt += init_unavailable_range(next, end, zone, nid); /* * Struct pages that do not have backing memory. This could be because * firmware is using some of this memory, or for some other reasons. */ if (pgcnt) - pr_info("Zeroed struct page in unavailable ranges: %lld pages", pgcnt); + pr_info("Zone %s: zeroed struct page in unavailable ranges: %lld pages", zone_names[zone], pgcnt); +} + +static void __init init_unavailable_mem(void) +{ + int zone; + + for (zone = 0; zone < ZONE_MOVABLE; zone++) + init_zone_unavailable_mem(zone); } #else static inline void __init init_unavailable_mem(void) diff --git a/mm/slub.c b/mm/slub.c index d9e4e10683cc..69742ab9a21d 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2791,7 +2791,8 @@ static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s, void *obj) { if (unlikely(slab_want_init_on_free(s)) && obj) - memset((void *)((char *)obj + s->offset), 0, sizeof(void *)); + memset((void *)((char *)kasan_reset_tag(obj) + s->offset), + 0, sizeof(void *)); } /* @@ -2883,7 +2884,7 @@ static __always_inline void *slab_alloc_node(struct kmem_cache *s, stat(s, ALLOC_FASTPATH); } - maybe_wipe_obj_freeptr(s, kasan_reset_tag(object)); + maybe_wipe_obj_freeptr(s, object); if (unlikely(slab_want_init_on_alloc(gfpflags, s)) && object) memset(kasan_reset_tag(object), 0, s->object_size); @@ -3329,7 +3330,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, int j; for (j = 0; j < i; j++) - memset(p[j], 0, s->object_size); + memset(kasan_reset_tag(p[j]), 0, s->object_size); } /* memcg and kmem_cache debug support */ diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 5f8d3eed78a1..4bd30315eb62 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -2928,14 +2928,10 @@ int check(struct objtool_file *file) warnings += ret; out: - if (ret < 0) { - /* - * Fatal error. The binary is corrupt or otherwise broken in - * some way, or objtool itself is broken. Fail the kernel - * build. - */ - return ret; - } - + /* + * For now, don't fail the kernel build on fatal warnings. These + * errors are still fairly common due to the growing matrix of + * supported toolchains and their recent pace of change. + */ return 0; } diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index be89c741ba9a..d8421e1d06be 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -380,8 +380,11 @@ static int read_symbols(struct elf *elf) symtab = find_section_by_name(elf, ".symtab"); if (!symtab) { - WARN("missing symbol table"); - return -1; + /* + * A missing symbol table is actually possible if it's an empty + * .o file. This can happen for thunk_64.o. + */ + return 0; } symtab_shndx = find_section_by_name(elf, ".symtab_shndx"); @@ -448,6 +451,13 @@ static int read_symbols(struct elf *elf) list_add(&sym->list, entry); elf_hash_add(elf->symbol_hash, &sym->hash, sym->idx); elf_hash_add(elf->symbol_name_hash, &sym->name_hash, str_hash(sym->name)); + + /* + * Don't store empty STT_NOTYPE symbols in the rbtree. They + * can exist within a function, confusing the sorting. + */ + if (!sym->len) + rb_erase(&sym->node, &sym->sec->symbol_tree); } if (stats) diff --git a/tools/testing/selftests/powerpc/alignment/alignment_handler.c b/tools/testing/selftests/powerpc/alignment/alignment_handler.c index cb53a8b777e6..c25cf7cd45e9 100644 --- a/tools/testing/selftests/powerpc/alignment/alignment_handler.c +++ b/tools/testing/selftests/powerpc/alignment/alignment_handler.c @@ -443,7 +443,6 @@ int test_alignment_handler_integer(void) LOAD_DFORM_TEST(ldu); LOAD_XFORM_TEST(ldx); LOAD_XFORM_TEST(ldux); - LOAD_DFORM_TEST(lmw); STORE_DFORM_TEST(stb); STORE_XFORM_TEST(stbx); STORE_DFORM_TEST(stbu); @@ -462,7 +461,11 @@ int test_alignment_handler_integer(void) STORE_XFORM_TEST(stdx); STORE_DFORM_TEST(stdu); STORE_XFORM_TEST(stdux); + +#ifdef __BIG_ENDIAN__ + LOAD_DFORM_TEST(lmw); STORE_DFORM_TEST(stmw); +#endif return rc; } diff --git a/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c b/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c index 9e5c7f3f498a..0af4f02669a1 100644 --- a/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c +++ b/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c @@ -290,5 +290,5 @@ static int test(void) int main(void) { - test_harness(test, "pkey_exec_prot"); + return test_harness(test, "pkey_exec_prot"); } diff --git a/tools/testing/selftests/powerpc/mm/pkey_siginfo.c b/tools/testing/selftests/powerpc/mm/pkey_siginfo.c index 4f815d7c1214..2db76e56d4cb 100644 --- a/tools/testing/selftests/powerpc/mm/pkey_siginfo.c +++ b/tools/testing/selftests/powerpc/mm/pkey_siginfo.c @@ -329,5 +329,5 @@ static int test(void) int main(void) { - test_harness(test, "pkey_siginfo"); + return test_harness(test, "pkey_siginfo"); }