diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-01-20 10:41:01 +0200 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-01-20 10:41:01 +0200 |
commit | f4484d138b31e8fa1ba410363b5b9664f68974af (patch) | |
tree | 6d776b1212604d3b16df499ae6e455e4a20544db | |
parent | 1d1df41c5a33359a00e919d54eaebfb789711fdc (diff) | |
parent | b1e78ef3be2533973953a35a56739fda7325875c (diff) | |
download | linux-stable-f4484d138b31e8fa1ba410363b5b9664f68974af.tar.gz linux-stable-f4484d138b31e8fa1ba410363b5b9664f68974af.tar.bz2 linux-stable-f4484d138b31e8fa1ba410363b5b9664f68974af.zip |
Merge branch 'akpm' (patches from Andrew)
Merge more updates from Andrew Morton:
"55 patches.
Subsystems affected by this patch series: percpu, procfs, sysctl,
misc, core-kernel, get_maintainer, lib, checkpatch, binfmt, nilfs2,
hfs, fat, adfs, panic, delayacct, kconfig, kcov, and ubsan"
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (55 commits)
lib: remove redundant assignment to variable ret
ubsan: remove CONFIG_UBSAN_OBJECT_SIZE
kcov: fix generic Kconfig dependencies if ARCH_WANTS_NO_INSTR
lib/Kconfig.debug: make TEST_KMOD depend on PAGE_SIZE_LESS_THAN_256KB
btrfs: use generic Kconfig option for 256kB page size limit
arch/Kconfig: split PAGE_SIZE_LESS_THAN_256KB from PAGE_SIZE_LESS_THAN_64KB
configs: introduce debug.config for CI-like setup
delayacct: track delays from memory compact
Documentation/accounting/delay-accounting.rst: add thrashing page cache and direct compact
delayacct: cleanup flags in struct task_delay_info and functions use it
delayacct: fix incomplete disable operation when switch enable to disable
delayacct: support swapin delay accounting for swapping without blkio
panic: remove oops_id
panic: use error_report_end tracepoint on warnings
fs/adfs: remove unneeded variable make code cleaner
FAT: use io_schedule_timeout() instead of congestion_wait()
hfsplus: use struct_group_attr() for memcpy() region
nilfs2: remove redundant pointer sbufs
fs/binfmt_elf: use PT_LOAD p_align values for static PIE
const_structs.checkpatch: add frequently used ops structs
...
77 files changed, 826 insertions, 873 deletions
diff --git a/Documentation/accounting/delay-accounting.rst b/Documentation/accounting/delay-accounting.rst index 1b8b46deeb29..197fe319cbec 100644 --- a/Documentation/accounting/delay-accounting.rst +++ b/Documentation/accounting/delay-accounting.rst @@ -13,6 +13,8 @@ a) waiting for a CPU (while being runnable) b) completion of synchronous block I/O initiated by the task c) swapping in pages d) memory reclaim +e) thrashing page cache +f) direct compact and makes these statistics available to userspace through the taskstats interface. @@ -41,11 +43,12 @@ generic data structure to userspace corresponding to per-pid and per-tgid statistics. The delay accounting functionality populates specific fields of this structure. See - include/linux/taskstats.h + include/uapi/linux/taskstats.h for a description of the fields pertaining to delay accounting. It will generally be in the form of counters returning the cumulative -delay seen for cpu, sync block I/O, swapin, memory reclaim etc. +delay seen for cpu, sync block I/O, swapin, memory reclaim, thrash page +cache, direct compact etc. Taking the difference of two successive readings of a given counter (say cpu_delay_total) for a task will give the delay @@ -88,41 +91,37 @@ seen. General format of the getdelays command:: - getdelays [-t tgid] [-p pid] [-c cmd...] - + getdelays [-dilv] [-t tgid] [-p pid] Get delays, since system boot, for pid 10:: - # ./getdelays -p 10 + # ./getdelays -d -p 10 (output similar to next case) Get sum of delays, since system boot, for all pids with tgid 5:: - # ./getdelays -t 5 - - - CPU count real total virtual total delay total - 7876 92005750 100000000 24001500 - IO count delay total - 0 0 - SWAP count delay total - 0 0 - RECLAIM count delay total - 0 0 + # ./getdelays -d -t 5 + print delayacct stats ON + TGID 5 -Get delays seen in executing a given simple command:: - # ./getdelays -c ls / + CPU count real total virtual total delay total delay average + 8 7000000 6872122 3382277 0.423ms + IO count delay total delay average + 0 0 0ms + SWAP count delay total delay average + 0 0 0ms + RECLAIM count delay total delay average + 0 0 0ms + THRASHING count delay total delay average + 0 0 0ms + COMPACT count delay total delay average + 0 0 0ms - bin data1 data3 data5 dev home media opt root srv sys usr - boot data2 data4 data6 etc lib mnt proc sbin subdomain tmp var +Get IO accounting for pid 1, it works only with -p:: + # ./getdelays -i -p 1 + printing IO accounting + linuxrc: read=65536, write=0, cancelled_write=0 - CPU count real total virtual total delay total - 6 4000250 4000000 0 - IO count delay total - 0 0 - SWAP count delay total - 0 0 - RECLAIM count delay total - 0 0 +The above command can be used with -v to get more debug information. diff --git a/arch/Kconfig b/arch/Kconfig index 874c65d9e963..678a80713b21 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -997,6 +997,10 @@ config PAGE_SIZE_LESS_THAN_64KB depends on !PAGE_SIZE_64KB depends on !PARISC_PAGE_SIZE_64KB depends on !PPC_64K_PAGES + depends on PAGE_SIZE_LESS_THAN_256KB + +config PAGE_SIZE_LESS_THAN_256KB + def_bool y depends on !PPC_256K_PAGES depends on !PAGE_SIZE_256KB diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index f6e333b59314..dc10d26cb432 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1136,6 +1136,10 @@ config NUMA select GENERIC_ARCH_NUMA select ACPI_NUMA if ACPI select OF_NUMA + select HAVE_SETUP_PER_CPU_AREA + select NEED_PER_CPU_EMBED_FIRST_CHUNK + select NEED_PER_CPU_PAGE_FIRST_CHUNK + select USE_PERCPU_NUMA_NODE_ID help Enable NUMA (Non-Uniform Memory Access) support. @@ -1152,22 +1156,6 @@ config NODES_SHIFT Specify the maximum number of NUMA Nodes available on the target system. Increases memory reserved to accommodate various tables. -config USE_PERCPU_NUMA_NODE_ID - def_bool y - depends on NUMA - -config HAVE_SETUP_PER_CPU_AREA - def_bool y - depends on NUMA - -config NEED_PER_CPU_EMBED_FIRST_CHUNK - def_bool y - depends on NUMA - -config NEED_PER_CPU_PAGE_FIRST_CHUNK - def_bool y - depends on NUMA - source "kernel/Kconfig.hz" config ARCH_SPARSEMEM_ENABLE diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 1e33666fa679..703952819e10 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -32,6 +32,7 @@ config IA64 select HAVE_FTRACE_MCOUNT_RECORD select HAVE_DYNAMIC_FTRACE if (!ITANIUM) select HAVE_FUNCTION_TRACER + select HAVE_SETUP_PER_CPU_AREA select TTY select HAVE_ARCH_TRACEHOOK select HAVE_VIRT_CPU_ACCOUNTING @@ -88,9 +89,6 @@ config GENERIC_CALIBRATE_DELAY bool default y -config HAVE_SETUP_PER_CPU_AREA - def_bool y - config DMI bool default y @@ -292,6 +290,7 @@ config NUMA bool "NUMA support" depends on !FLATMEM select SMP + select USE_PERCPU_NUMA_NODE_ID help Say Y to compile the kernel to support NUMA (Non-Uniform Memory Access). This option is for configuring high-end multiprocessor @@ -311,10 +310,6 @@ config HAVE_ARCH_NODEDATA_EXTENSION def_bool y depends on NUMA -config USE_PERCPU_NUMA_NODE_ID - def_bool y - depends on NUMA - config HAVE_MEMORYLESS_NODES def_bool NUMA diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 3dd8c4618293..edf6c1577449 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -2674,6 +2674,8 @@ config NUMA bool "NUMA Support" depends on SYS_SUPPORTS_NUMA select SMP + select HAVE_SETUP_PER_CPU_AREA + select NEED_PER_CPU_EMBED_FIRST_CHUNK help Say Y to compile the kernel to support NUMA (Non-Uniform Memory Access). This option improves performance on systems with more @@ -2684,14 +2686,6 @@ config NUMA config SYS_SUPPORTS_NUMA bool -config HAVE_SETUP_PER_CPU_AREA - def_bool y - depends on NUMA - -config NEED_PER_CPU_EMBED_FIRST_CHUNK - def_bool y - depends on NUMA - config RELOCATABLE bool "Relocatable kernel" depends on SYS_SUPPORTS_RELOCATABLE diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 325e1552cbea..5a8002839550 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -519,17 +519,9 @@ static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) return node_distance(cpu_to_node(from), cpu_to_node(to)); } -static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, - size_t align) +static int __init pcpu_cpu_to_node(int cpu) { - return memblock_alloc_try_nid(size, align, __pa(MAX_DMA_ADDRESS), - MEMBLOCK_ALLOC_ACCESSIBLE, - cpu_to_node(cpu)); -} - -static void __init pcpu_fc_free(void *ptr, size_t size) -{ - memblock_free(ptr, size); + return cpu_to_node(cpu); } void __init setup_per_cpu_areas(void) @@ -545,7 +537,7 @@ void __init setup_per_cpu_areas(void) rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, pcpu_cpu_distance, - pcpu_fc_alloc, pcpu_fc_free); + pcpu_cpu_to_node); if (rc < 0) panic("Failed to initialize percpu areas."); diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 0631c9241af3..b779603978e1 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -55,15 +55,6 @@ config ARCH_MMAP_RND_COMPAT_BITS_MIN default 9 if PPC_16K_PAGES # 9 = 23 (8MB) - 14 (16K) default 11 # 11 = 23 (8MB) - 12 (4K) -config HAVE_SETUP_PER_CPU_AREA - def_bool PPC64 - -config NEED_PER_CPU_EMBED_FIRST_CHUNK - def_bool y if PPC64 - -config NEED_PER_CPU_PAGE_FIRST_CHUNK - def_bool y if PPC64 - config NR_IRQS int "Number of virtual interrupt numbers" range 32 1048576 @@ -241,6 +232,7 @@ config PPC select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RELIABLE_STACKTRACE select HAVE_RSEQ + select HAVE_SETUP_PER_CPU_AREA if PPC64 select HAVE_SOFTIRQ_ON_OWN_STACK select HAVE_STACKPROTECTOR if PPC32 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r2) select HAVE_STACKPROTECTOR if PPC64 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r13) @@ -255,6 +247,8 @@ config PPC select MMU_GATHER_RCU_TABLE_FREE select MODULES_USE_ELF_RELA select NEED_DMA_MAP_STATE if PPC64 || NOT_COHERENT_CACHE + select NEED_PER_CPU_EMBED_FIRST_CHUNK if PPC64 + select NEED_PER_CPU_PAGE_FIRST_CHUNK if PPC64 select NEED_SG_DMA_LENGTH select OF select OF_DMA_DEFAULT_COHERENT if !NOT_COHERENT_CACHE @@ -660,6 +654,7 @@ config NUMA bool "NUMA Memory Allocation and Scheduler Support" depends on PPC64 && SMP default y if PPC_PSERIES || PPC_POWERNV + select USE_PERCPU_NUMA_NODE_ID help Enable NUMA (Non-Uniform Memory Access) support. @@ -673,10 +668,6 @@ config NODES_SHIFT default "4" depends on NUMA -config USE_PERCPU_NUMA_NODE_ID - def_bool y - depends on NUMA - config HAVE_MEMORYLESS_NODES def_bool y depends on NUMA diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index d87f7c1103ce..be8577ac9397 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -771,50 +771,6 @@ void __init emergency_stack_init(void) } #ifdef CONFIG_SMP -/** - * pcpu_alloc_bootmem - NUMA friendly alloc_bootmem wrapper for percpu - * @cpu: cpu to allocate for - * @size: size allocation in bytes - * @align: alignment - * - * Allocate @size bytes aligned at @align for cpu @cpu. This wrapper - * does the right thing for NUMA regardless of the current - * configuration. - * - * RETURNS: - * Pointer to the allocated area on success, NULL on failure. - */ -static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size, - size_t align) -{ - const unsigned long goal = __pa(MAX_DMA_ADDRESS); -#ifdef CONFIG_NUMA - int node = early_cpu_to_node(cpu); - void *ptr; - - if (!node_online(node) || !NODE_DATA(node)) { - ptr = memblock_alloc_from(size, align, goal); - pr_info("cpu %d has no node %d or node-local memory\n", - cpu, node); - pr_debug("per cpu data for cpu%d %lu bytes at %016lx\n", - cpu, size, __pa(ptr)); - } else { - ptr = memblock_alloc_try_nid(size, align, goal, - MEMBLOCK_ALLOC_ACCESSIBLE, node); - pr_debug("per cpu data for cpu%d %lu bytes on node%d at " - "%016lx\n", cpu, size, node, __pa(ptr)); - } - return ptr; -#else - return memblock_alloc_from(size, align, goal); -#endif -} - -static void __init pcpu_free_bootmem(void *ptr, size_t size) -{ - memblock_free(ptr, size); -} - static int pcpu_cpu_distance(unsigned int from, unsigned int to) { if (early_cpu_to_node(from) == early_cpu_to_node(to)) @@ -823,53 +779,13 @@ static int pcpu_cpu_distance(unsigned int from, unsigned int to) return REMOTE_DISTANCE; } -unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; -EXPORT_SYMBOL(__per_cpu_offset); - -static void __init pcpu_populate_pte(unsigned long addr) +static __init int pcpu_cpu_to_node(int cpu) { - pgd_t *pgd = pgd_offset_k(addr); - p4d_t *p4d; - pud_t *pud; - pmd_t *pmd; - - p4d = p4d_offset(pgd, addr); - if (p4d_none(*p4d)) { - pud_t *new; - - new = memblock_alloc(PUD_TABLE_SIZE, PUD_TABLE_SIZE); - if (!new) - goto err_alloc; - p4d_populate(&init_mm, p4d, new); - } - - pud = pud_offset(p4d, addr); - if (pud_none(*pud)) { - pmd_t *new; - - new = memblock_alloc(PMD_TABLE_SIZE, PMD_TABLE_SIZE); - if (!new) - goto err_alloc; - pud_populate(&init_mm, pud, new); - } - - pmd = pmd_offset(pud, addr); - if (!pmd_present(*pmd)) { - pte_t *new; - - new = memblock_alloc(PTE_TABLE_SIZE, PTE_TABLE_SIZE); - if (!new) - goto err_alloc; - pmd_populate_kernel(&init_mm, pmd, new); - } - - return; - -err_alloc: - panic("%s: Failed to allocate %lu bytes align=%lx from=%lx\n", - __func__, PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); + return early_cpu_to_node(cpu); } +unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; +EXPORT_SYMBOL(__per_cpu_offset); void __init setup_per_cpu_areas(void) { @@ -900,7 +816,7 @@ void __init setup_per_cpu_areas(void) if (pcpu_chosen_fc != PCPU_FC_PAGE) { rc = pcpu_embed_first_chunk(0, dyn_size, atom_size, pcpu_cpu_distance, - pcpu_alloc_bootmem, pcpu_free_bootmem); + pcpu_cpu_to_node); if (rc) pr_warn("PERCPU: %s allocator failed (%d), " "falling back to page size\n", @@ -908,8 +824,7 @@ void __init setup_per_cpu_areas(void) } if (rc < 0) - rc = pcpu_page_first_chunk(0, pcpu_alloc_bootmem, pcpu_free_bootmem, - pcpu_populate_pte); + rc = pcpu_page_first_chunk(0, pcpu_cpu_to_node); if (rc < 0) panic("cannot initialize percpu area (err=%d)", rc); diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 4602cfe92a20..171ecc6d1792 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -335,6 +335,8 @@ config NUMA select GENERIC_ARCH_NUMA select OF_NUMA select ARCH_SUPPORTS_NUMA_BALANCING + select USE_PERCPU_NUMA_NODE_ID + select NEED_PER_CPU_EMBED_FIRST_CHUNK help Enable NUMA (Non-Uniform Memory Access) support. @@ -350,14 +352,6 @@ config NODES_SHIFT Specify the maximum number of NUMA Nodes available on the target system. Increases memory reserved to accommodate various tables. -config USE_PERCPU_NUMA_NODE_ID - def_bool y - depends on NUMA - -config NEED_PER_CPU_EMBED_FIRST_CHUNK - def_bool y - depends on NUMA - config RISCV_ISA_C bool "Emit compressed instructions when building Linux" default y diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 66fc08646be5..1cab1b284f1a 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -97,6 +97,9 @@ config SPARC64 select PCI_DOMAINS if PCI select ARCH_HAS_GIGANTIC_PAGE select HAVE_SOFTIRQ_ON_OWN_STACK + select HAVE_SETUP_PER_CPU_AREA + select NEED_PER_CPU_EMBED_FIRST_CHUNK + select NEED_PER_CPU_PAGE_FIRST_CHUNK config ARCH_PROC_KCORE_TEXT def_bool y @@ -123,15 +126,6 @@ config AUDIT_ARCH bool default y -config HAVE_SETUP_PER_CPU_AREA - def_bool y if SPARC64 - -config NEED_PER_CPU_EMBED_FIRST_CHUNK - def_bool y if SPARC64 - -config NEED_PER_CPU_PAGE_FIRST_CHUNK - def_bool y if SPARC64 - config MMU bool default y diff --git a/arch/sparc/kernel/led.c b/arch/sparc/kernel/led.c index 3a66e62eb2a0..ab657b359789 100644 --- a/arch/sparc/kernel/led.c +++ b/arch/sparc/kernel/led.c @@ -114,18 +114,16 @@ static const struct proc_ops led_proc_ops = { }; #endif -static struct proc_dir_entry *led; - #define LED_VERSION "0.1" static int __init led_init(void) { timer_setup(&led_blink_timer, led_blink, 0); - led = proc_create("led", 0, NULL, &led_proc_ops); - if (!led) +#ifdef CONFIG_PROC_FS + if (!proc_create("led", 0, NULL, &led_proc_ops)) return -ENOMEM; - +#endif printk(KERN_INFO "led: version %s, Lars Kotthoff <metalhead@metalhead.ws>\n", LED_VERSION); diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index b98a7bbe6728..a1f78e9ddaf3 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1526,50 +1526,6 @@ void smp_send_stop(void) smp_call_function(stop_this_cpu, NULL, 0); } -/** - * pcpu_alloc_bootmem - NUMA friendly alloc_bootmem wrapper for percpu - * @cpu: cpu to allocate for - * @size: size allocation in bytes - * @align: alignment - * - * Allocate @size bytes aligned at @align for cpu @cpu. This wrapper - * does the right thing for NUMA regardless of the current - * configuration. - * - * RETURNS: - * Pointer to the allocated area on success, NULL on failure. - */ -static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size, - size_t align) -{ - const unsigned long goal = __pa(MAX_DMA_ADDRESS); -#ifdef CONFIG_NUMA - int node = cpu_to_node(cpu); - void *ptr; - - if (!node_online(node) || !NODE_DATA(node)) { - ptr = memblock_alloc_from(size, align, goal); - pr_info("cpu %d has no node %d or node-local memory\n", - cpu, node); - pr_debug("per cpu data for cpu%d %lu bytes at %016lx\n", - cpu, size, __pa(ptr)); - } else { - ptr = memblock_alloc_try_nid(size, align, goal, - MEMBLOCK_ALLOC_ACCESSIBLE, node); - pr_debug("per cpu data for cpu%d %lu bytes on node%d at " - "%016lx\n", cpu, size, node, __pa(ptr)); - } - return ptr; -#else - return memblock_alloc_from(size, align, goal); -#endif -} - -static void __init pcpu_free_bootmem(void *ptr, size_t size) -{ - memblock_free(ptr, size); -} - static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) { if (cpu_to_node(from) == cpu_to_node(to)) @@ -1578,57 +1534,9 @@ static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) return REMOTE_DISTANCE; } -static void __init pcpu_populate_pte(unsigned long addr) +static int __init pcpu_cpu_to_node(int cpu) { - pgd_t *pgd = pgd_offset_k(addr); - p4d_t *p4d; - pud_t *pud; - pmd_t *pmd; - - if (pgd_none(*pgd)) { - pud_t *new; - - new = memblock_alloc_from(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); - if (!new) - goto err_alloc; - pgd_populate(&init_mm, pgd, new); - } - - p4d = p4d_offset(pgd, addr); - if (p4d_none(*p4d)) { - pud_t *new; - - new = memblock_alloc_from(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); - if (!new) - goto err_alloc; - p4d_populate(&init_mm, p4d, new); - } - - pud = pud_offset(p4d, addr); - if (pud_none(*pud)) { - pmd_t *new; - - new = memblock_alloc_from(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); - if (!new) - goto err_alloc; - pud_populate(&init_mm, pud, new); - } - - pmd = pmd_offset(pud, addr); - if (!pmd_present(*pmd)) { - pte_t *new; - - new = memblock_alloc_from(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); - if (!new) - goto err_alloc; - pmd_populate_kernel(&init_mm, pmd, new); - } - - return; - -err_alloc: - panic("%s: Failed to allocate %lu bytes align=%lx from=%lx\n", - __func__, PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); + return cpu_to_node(cpu); } void __init setup_per_cpu_areas(void) @@ -1641,8 +1549,7 @@ void __init setup_per_cpu_areas(void) rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, PERCPU_DYNAMIC_RESERVE, 4 << 20, pcpu_cpu_distance, - pcpu_alloc_bootmem, - pcpu_free_bootmem); + pcpu_cpu_to_node); if (rc) pr_warn("PERCPU: %s allocator failed (%d), " "falling back to page size\n", @@ -1650,9 +1557,7 @@ void __init setup_per_cpu_areas(void) } if (rc < 0) rc = pcpu_page_first_chunk(PERCPU_MODULE_RESERVE, - pcpu_alloc_bootmem, - pcpu_free_bootmem, - pcpu_populate_pte); + pcpu_cpu_to_node); if (rc < 0) panic("cannot initialize percpu area (err=%d)", rc); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 407533c835fe..6fddb63271d9 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -78,7 +78,7 @@ config X86 select ARCH_HAS_FILTER_PGPROT select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL - select ARCH_HAS_KCOV if X86_64 && STACK_VALIDATION + select ARCH_HAS_KCOV if X86_64 select ARCH_HAS_MEM_ENCRYPT select ARCH_HAS_MEMBARRIER_SYNC_CORE select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE @@ -240,6 +240,7 @@ config X86 select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RELIABLE_STACKTRACE if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION select HAVE_FUNCTION_ARG_ACCESS_API + select HAVE_SETUP_PER_CPU_AREA select HAVE_SOFTIRQ_ON_OWN_STACK select HAVE_STACKPROTECTOR if CC_HAS_SANE_STACKPROTECTOR select HAVE_STACK_VALIDATION if X86_64 @@ -253,6 +254,8 @@ config X86 select HAVE_GENERIC_VDSO select HOTPLUG_SMT if SMP select IRQ_FORCED_THREADING + select NEED_PER_CPU_EMBED_FIRST_CHUNK + select NEED_PER_CPU_PAGE_FIRST_CHUNK select NEED_SG_DMA_LENGTH select PCI_DOMAINS if PCI select PCI_LOCKLESS_CONFIG if PCI @@ -333,15 +336,6 @@ config ARCH_HAS_CPU_RELAX config ARCH_HAS_FILTER_PGPROT def_bool y -config HAVE_SETUP_PER_CPU_AREA - def_bool y - -config NEED_PER_CPU_EMBED_FIRST_CHUNK - def_bool y - -config NEED_PER_CPU_PAGE_FIRST_CHUNK - def_bool y - config ARCH_HIBERNATION_POSSIBLE def_bool y @@ -1575,6 +1569,7 @@ config NUMA depends on SMP depends on X86_64 || (X86_32 && HIGHMEM64G && X86_BIGSMP) default y if X86_BIGSMP + select USE_PERCPU_NUMA_NODE_ID help Enable NUMA (Non-Uniform Memory Access) support. @@ -2450,10 +2445,6 @@ config ARCH_HAS_ADD_PAGES config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE def_bool y -config USE_PERCPU_NUMA_NODE_ID - def_bool y - depends on NUMA - menu "Power management and ACPI options" config ARCH_HIBERNATION_HEADER diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 7b65275544b2..49325caa7307 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -84,60 +84,6 @@ static bool __init pcpu_need_numa(void) } #endif -/** - * pcpu_alloc_bootmem - NUMA friendly alloc_bootmem wrapper for percpu - * @cpu: cpu to allocate for - * @size: size allocation in bytes - * @align: alignment - * - * Allocate @size bytes aligned at @align for cpu @cpu. This wrapper - * does the right thing for NUMA regardless of the current - * configuration. - * - * RETURNS: - * Pointer to the allocated area on success, NULL on failure. - */ -static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size, - unsigned long align) -{ - const unsigned long goal = __pa(MAX_DMA_ADDRESS); -#ifdef CONFIG_NUMA - int node = early_cpu_to_node(cpu); - void *ptr; - - if (!node_online(node) || !NODE_DATA(node)) { - ptr = memblock_alloc_from(size, align, goal); - pr_info("cpu %d has no node %d or node-local memory\n", - cpu, node); - pr_debug("per cpu data for cpu%d %lu bytes at %016lx\n", - cpu, size, __pa(ptr)); - } else { - ptr = memblock_alloc_try_nid(size, align, goal, - MEMBLOCK_ALLOC_ACCESSIBLE, - node); - - pr_debug("per cpu data for cpu%d %lu bytes on node%d at %016lx\n", - cpu, size, node, __pa(ptr)); - } - return ptr; -#else - return memblock_alloc_from(size, align, goal); -#endif -} - -/* - * Helpers for first chunk memory allocation - */ -static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align) -{ - return pcpu_alloc_bootmem(cpu, size, align); -} - -static void __init pcpu_fc_free(void *ptr, size_t size) -{ - memblock_free(ptr, size); -} - static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) { #ifdef CONFIG_NUMA @@ -150,7 +96,12 @@ static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) #endif } -static void __init pcpup_populate_pte(unsigned long addr) +static int __init pcpu_cpu_to_node(int cpu) +{ + return early_cpu_to_node(cpu); +} + +void __init pcpu_populate_pte(unsigned long addr) { populate_extra_pte(addr); } @@ -205,15 +156,14 @@ void __init setup_per_cpu_areas(void) rc = pcpu_embed_first_chunk(PERCPU_FIRST_CHUNK_RESERVE, dyn_size, atom_size, pcpu_cpu_distance, - pcpu_fc_alloc, pcpu_fc_free); + pcpu_cpu_to_node); if (rc < 0) pr_warn("%s allocator failed (%d), falling back to page size\n", pcpu_fc_names[pcpu_chosen_fc], rc); } if (rc < 0) rc = pcpu_page_first_chunk(PERCPU_FIRST_CHUNK_RESERVE, - pcpu_fc_alloc, pcpu_fc_free, - pcpup_populate_pte); + pcpu_cpu_to_node); if (rc < 0) panic("cannot initialize percpu area (err=%d)", rc); diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c index bc1876915457..eaa31e567d1e 100644 --- a/drivers/base/arch_numa.c +++ b/drivers/base/arch_numa.c @@ -14,7 +14,6 @@ #include <linux/of.h> #include <asm/sections.h> -#include <asm/pgalloc.h> struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; EXPORT_SYMBOL(node_data); @@ -155,66 +154,6 @@ static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) return node_distance(early_cpu_to_node(from), early_cpu_to_node(to)); } -static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, - size_t align) -{ - int nid = early_cpu_to_node(cpu); - - return memblock_alloc_try_nid(size, align, - __pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid); -} - -static void __init pcpu_fc_free(void *ptr, size_t size) -{ - memblock_free(ptr, size); -} - -#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK -static void __init pcpu_populate_pte(unsigned long addr) -{ - pgd_t *pgd = pgd_offset_k(addr); - p4d_t *p4d; - pud_t *pud; - pmd_t *pmd; - - p4d = p4d_offset(pgd, addr); - if (p4d_none(*p4d)) { - pud_t *new; - - new = memblock_alloc(PAGE_SIZE, PAGE_SIZE); - if (!new) - goto err_alloc; - p4d_populate(&init_mm, p4d, new); - } - - pud = pud_offset(p4d, addr); - if (pud_none(*pud)) { - pmd_t *new; - - new = memblock_alloc(PAGE_SIZE, PAGE_SIZE); - if (!new) - goto err_alloc; - pud_populate(&init_mm, pud, new); - } - - pmd = pmd_offset(pud, addr); - if (!pmd_present(*pmd)) { - pte_t *new; - - new = memblock_alloc(PAGE_SIZE, PAGE_SIZE); - if (!new) - goto err_alloc; - pmd_populate_kernel(&init_mm, pmd, new); - } - - return; - -err_alloc: - panic("%s: Failed to allocate %lu bytes align=%lx from=%lx\n", - __func__, PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); -} -#endif - void __init setup_per_cpu_areas(void) { unsigned long delta; @@ -229,7 +168,7 @@ void __init setup_per_cpu_areas(void) rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, pcpu_cpu_distance, - pcpu_fc_alloc, pcpu_fc_free); + early_cpu_to_node); #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK if (rc < 0) pr_warn("PERCPU: %s allocator failed (%d), falling back to page size\n", @@ -239,10 +178,7 @@ void __init setup_per_cpu_areas(void) #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK if (rc < 0) - rc = pcpu_page_first_chunk(PERCPU_MODULE_RESERVE, - pcpu_fc_alloc, - pcpu_fc_free, - pcpu_populate_pte); + rc = pcpu_page_first_chunk(PERCPU_MODULE_RESERVE, early_cpu_to_node); #endif if (rc < 0) panic("Failed to initialize percpu areas (err=%d).", rc); diff --git a/drivers/infiniband/hw/qib/qib.h b/drivers/infiniband/hw/qib/qib.h index 9363bccfc6e7..a8e1c30c370f 100644 --- a/drivers/infiniband/hw/qib/qib.h +++ b/drivers/infiniband/hw/qib/qib.h @@ -196,7 +196,7 @@ struct qib_ctxtdata { pid_t pid; pid_t subpid[QLOGIC_IB_MAX_SUBCTXT]; /* same size as task_struct .comm[], command that opened context */ - char comm[16]; + char comm[TASK_COMM_LEN]; /* pkeys set by this use of this ctxt */ u16 pkeys[4]; /* so file ops can get at unit */ diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c index 63854f4b6524..aa290928cf96 100644 --- a/drivers/infiniband/hw/qib/qib_file_ops.c +++ b/drivers/infiniband/hw/qib/qib_file_ops.c @@ -1321,7 +1321,7 @@ static int setup_ctxt(struct qib_pportdata *ppd, int ctxt, rcd->tid_pg_list = ptmp; rcd->pid = current->pid; init_waitqueue_head(&dd->rcd[ctxt]->wait); - strlcpy(rcd->comm, current->comm, sizeof(rcd->comm)); + get_task_comm(rcd->comm, current); ctxt_fp(fp) = rcd; qib_stats.sps_ctxts++; dd->freectxts--; diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index afe11f475b8c..5018b9387694 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -217,8 +217,7 @@ static int rxe_qp_init_req(struct rxe_dev *rxe, struct rxe_qp *qp, * the port number must be in the Dynamic Ports range * (0xc000 - 0xffff). */ - qp->src_port = RXE_ROCE_V2_SPORT + - (hash_32_generic(qp_num(qp), 14) & 0x3fff); + qp->src_port = RXE_ROCE_V2_SPORT + (hash_32(qp_num(qp), 14) & 0x3fff); qp->sq.max_wr = init->cap.max_send_wr; /* These caps are limited by rxe_qp_chk_cap() done by the caller */ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/xtlv.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/xtlv.c index 2f3c451148db..2f8908074303 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/xtlv.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/xtlv.c @@ -4,6 +4,8 @@ */ #include <asm/unaligned.h> + +#include <linux/math.h> #include <linux/string.h> #include <linux/bug.h> diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c index adbb3a1edcbf..5156821bfe6a 100644 --- a/fs/adfs/inode.c +++ b/fs/adfs/inode.c @@ -355,7 +355,6 @@ int adfs_write_inode(struct inode *inode, struct writeback_control *wbc) { struct super_block *sb = inode->i_sb; struct object_info obj; - int ret; obj.indaddr = ADFS_I(inode)->indaddr; obj.name_len = 0; @@ -365,6 +364,5 @@ int adfs_write_inode(struct inode *inode, struct writeback_control *wbc) obj.attr = ADFS_I(inode)->attr; obj.size = inode->i_size; - ret = adfs_dir_update(sb, &obj, wbc->sync_mode == WB_SYNC_ALL); - return ret; + return adfs_dir_update(sb, &obj, wbc->sync_mode == WB_SYNC_ALL); } diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index f8c7f26f1fbb..605017eb9349 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1116,11 +1116,11 @@ out_free_interp: * independently randomized mmap region (0 load_bias * without MAP_FIXED nor MAP_FIXED_NOREPLACE). */ - if (interpreter) { + alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum); + if (alignment > ELF_MIN_ALIGN) { load_bias = ELF_ET_DYN_BASE; if (current->flags & PF_RANDOMIZE) load_bias += arch_mmap_rnd(); - alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum); if (alignment) load_bias &= ~(alignment - 1); elf_flags |= MAP_FIXED_NOREPLACE; @@ -1585,7 +1585,7 @@ static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p, SET_UID(psinfo->pr_uid, from_kuid_munged(cred->user_ns, cred->uid)); SET_GID(psinfo->pr_gid, from_kgid_munged(cred->user_ns, cred->gid)); rcu_read_unlock(); - strncpy(psinfo->pr_fname, p->comm, sizeof(psinfo->pr_fname)); + get_task_comm(psinfo->pr_fname, p); return 0; } diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig index 520a0f6a7d9e..183e5c4aed34 100644 --- a/fs/btrfs/Kconfig +++ b/fs/btrfs/Kconfig @@ -18,8 +18,7 @@ config BTRFS_FS select RAID6_PQ select XOR_BLOCKS select SRCU - depends on !PPC_256K_PAGES # powerpc - depends on !PAGE_SIZE_256KB # hexagon + depends on PAGE_SIZE_LESS_THAN_256KB help Btrfs is a general purpose copy-on-write filesystem with extents, diff --git a/fs/exec.c b/fs/exec.c index 82db656ca709..3c3c366a9bcf 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1207,7 +1207,8 @@ static int unshare_sighand(struct task_struct *me) char *__get_task_comm(char *buf, size_t buf_size, struct task_struct *tsk) { task_lock(tsk); - strncpy(buf, tsk->comm, buf_size); + /* Always NUL terminated and zero-padded */ + strscpy_pad(buf, tsk->comm, buf_size); task_unlock(tsk); return buf; } @@ -1222,7 +1223,7 @@ void __set_task_comm(struct task_struct *tsk, const char *buf, bool exec) { task_lock(tsk); trace_task_rename(tsk, buf); - strlcpy(tsk->comm, buf, sizeof(tsk->comm)); + strscpy_pad(tsk->comm, buf, sizeof(tsk->comm)); task_unlock(tsk); perf_event_comm(tsk, exec); } diff --git a/fs/fat/file.c b/fs/fat/file.c index 13855ba49cd9..a5a309fcc7fa 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -175,9 +175,10 @@ long fat_generic_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) static int fat_file_release(struct inode *inode, struct file *filp) { if ((filp->f_mode & FMODE_WRITE) && - MSDOS_SB(inode->i_sb)->options.flush) { + MSDOS_SB(inode->i_sb)->options.flush) { fat_flush_inodes(inode->i_sb, inode, NULL); - congestion_wait(BLK_RW_ASYNC, HZ/10); + set_current_state(TASK_UNINTERRUPTIBLE); + io_schedule_timeout(HZ/10); } return 0; } diff --git a/fs/hfsplus/hfsplus_raw.h b/fs/hfsplus/hfsplus_raw.h index 456e87aec7fd..68b4240c6191 100644 --- a/fs/hfsplus/hfsplus_raw.h +++ b/fs/hfsplus/hfsplus_raw.h @@ -260,8 +260,10 @@ struct hfsplus_cat_folder { __be32 access_date; __be32 backup_date; struct hfsplus_perm permissions; - struct DInfo user_info; - struct DXInfo finder_info; + struct_group_attr(info, __packed, + struct DInfo user_info; + struct DXInfo finder_info; + ); __be32 text_encoding; __be32 subfolders; /* Subfolder count in HFSX. Reserved in HFS+. */ } __packed; @@ -294,8 +296,10 @@ struct hfsplus_cat_file { __be32 access_date; __be32 backup_date; struct hfsplus_perm permissions; - struct FInfo user_info; - struct FXInfo finder_info; + struct_group_attr(info, __packed, + struct FInfo user_info; + struct FXInfo finder_info; + ); __be32 text_encoding; u32 reserved2; diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c index e2855ceefd39..49891b12c415 100644 --- a/fs/hfsplus/xattr.c +++ b/fs/hfsplus/xattr.c @@ -296,7 +296,7 @@ int __hfsplus_setxattr(struct inode *inode, const char *name, sizeof(hfsplus_cat_entry)); if (be16_to_cpu(entry.type) == HFSPLUS_FOLDER) { if (size == folder_finderinfo_len) { - memcpy(&entry.folder.user_info, value, + memcpy(&entry.folder.info, value, folder_finderinfo_len); hfs_bnode_write(cat_fd.bnode, &entry, cat_fd.entryoffset, @@ -309,7 +309,7 @@ int __hfsplus_setxattr(struct inode *inode, const char *name, } } else if (be16_to_cpu(entry.type) == HFSPLUS_FILE) { if (size == file_finderinfo_len) { - memcpy(&entry.file.user_info, value, + memcpy(&entry.file.info, value, file_finderinfo_len); hfs_bnode_write(cat_fd.bnode, &entry, cat_fd.entryoffset, diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index bc3e2cd4117f..063dd16d75b5 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -195,12 +195,12 @@ void nilfs_page_bug(struct page *page) */ static void nilfs_copy_page(struct page *dst, struct page *src, int copy_dirty) { - struct buffer_head *dbh, *dbufs, *sbh, *sbufs; + struct buffer_head *dbh, *dbufs, *sbh; unsigned long mask = NILFS_BUFFER_INHERENT_BITS; BUG_ON(PageWriteback(dst)); - sbh = sbufs = page_buffers(src); + sbh = page_buffers(src); if (!page_has_buffers(dst)) create_empty_buffers(dst, sbh->b_size, 0); diff --git a/fs/proc/array.c b/fs/proc/array.c index 43a7abde9e42..fd8b0c12b2cb 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -92,6 +92,7 @@ #include <linux/string_helpers.h> #include <linux/user_namespace.h> #include <linux/fs_struct.h> +#include <linux/kthread.h> #include <asm/processor.h> #include "internal.h" @@ -102,6 +103,8 @@ void proc_task_name(struct seq_file *m, struct task_struct *p, bool escape) if (p->flags & PF_WQ_WORKER) wq_worker_comm(tcomm, sizeof(tcomm), p); + else if (p->flags & PF_KTHREAD) + get_kthread_comm(tcomm, sizeof(tcomm), p); else __get_task_comm(tcomm, sizeof(tcomm), p); diff --git a/fs/proc/base.c b/fs/proc/base.c index 13eda8de2998..d654ce7150fd 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -670,10 +670,10 @@ static int proc_pid_syscall(struct seq_file *m, struct pid_namespace *ns, /************************************************************************/ /* permission checks */ -static int proc_fd_access_allowed(struct inode *inode) +static bool proc_fd_access_allowed(struct inode *inode) { struct task_struct *task; - int allowed = 0; + bool allowed = false; /* Allow access to a task's file descriptors if it is us or we * may use ptrace attach to the process and find out that * information. diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 5d66faecd4ef..389e1e42e7d9 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -163,7 +163,7 @@ static int insert_entry(struct ctl_table_header *head, struct ctl_table *entry) else { pr_err("sysctl duplicate entry: "); sysctl_print_dir(head->parent); - pr_cont("/%s\n", entry->procname); + pr_cont("%s\n", entry->procname); return -EEXIST; } } @@ -1020,8 +1020,8 @@ failed: if (IS_ERR(subdir)) { pr_err("sysctl could not get directory: "); sysctl_print_dir(dir); - pr_cont("/%*.*s %ld\n", - namelen, namelen, name, PTR_ERR(subdir)); + pr_cont("%*.*s %ld\n", namelen, namelen, name, + PTR_ERR(subdir)); } drop_sysctl_table(&dir->header); if (new) @@ -1053,7 +1053,6 @@ static int sysctl_follow_link(struct ctl_table_header **phead, struct ctl_dir *dir; int ret; - ret = 0; spin_lock(&sysctl_lock); root = (*pentry)->data; set = lookup_header_set(root); @@ -1626,7 +1625,7 @@ static void put_links(struct ctl_table_header *header) else { pr_err("sysctl link missing during unregister: "); sysctl_print_dir(parent); - pr_cont("/%s\n", name); + pr_cont("%s\n", name); } } } diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 509f85148fee..702754dd1daf 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -65,8 +65,6 @@ static size_t vmcoredd_orig_sz; static DECLARE_RWSEM(vmcore_cb_rwsem); /* List of registered vmcore callbacks. */ static LIST_HEAD(vmcore_cb_list); -/* Whether we had a surprise unregistration of a callback. */ -static bool vmcore_cb_unstable; /* Whether the vmcore has been opened once. */ static bool vmcore_opened; @@ -94,10 +92,8 @@ void unregister_vmcore_cb(struct vmcore_cb *cb) * very unusual (e.g., forced driver removal), but we cannot stop * unregistering. */ - if (vmcore_opened) { + if (vmcore_opened) pr_warn_once("Unexpected vmcore callback unregistration\n"); - vmcore_cb_unstable = true; - } up_write(&vmcore_cb_rwsem); } EXPORT_SYMBOL_GPL(unregister_vmcore_cb); @@ -108,8 +104,6 @@ static bool pfn_is_ram(unsigned long pfn) bool ret = true; lockdep_assert_held_read(&vmcore_cb_rwsem); - if (unlikely(vmcore_cb_unstable)) - return false; list_for_each_entry(cb, &vmcore_cb_list, next) { if (unlikely(!cb->pfn_is_ram)) @@ -581,7 +575,7 @@ static int vmcore_remap_oldmem_pfn(struct vm_area_struct *vma, * looping over all pages without a reason. */ down_read(&vmcore_cb_rwsem); - if (!list_empty(&vmcore_cb_list) || vmcore_cb_unstable) + if (!list_empty(&vmcore_cb_list)) ret = remap_oldmem_pfn_checked(vma, from, pfn, size, prot); else ret = remap_oldmem_pfn_range(vma, from, pfn, size, prot); diff --git a/include/kunit/assert.h b/include/kunit/assert.h index ad889b539ab3..ccbc36c0b02f 100644 --- a/include/kunit/assert.h +++ b/include/kunit/assert.h @@ -10,7 +10,7 @@ #define _KUNIT_ASSERT_H #include <linux/err.h> -#include <linux/kernel.h> +#include <linux/printk.h> struct kunit; struct string_stream; diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index af7e6eb50283..3e03d010bd2e 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -9,18 +9,9 @@ #include <uapi/linux/taskstats.h> -/* - * Per-task flags relevant to delay accounting - * maintained privately to avoid exhausting similar flags in sched.h:PF_* - * Used to set current->delays->flags - */ -#define DELAYACCT_PF_SWAPIN 0x00000001 /* I am doing a swapin */ -#define DELAYACCT_PF_BLKIO 0x00000002 /* I am waiting on IO */ - #ifdef CONFIG_TASK_DELAY_ACCT struct task_delay_info { raw_spinlock_t lock; - unsigned int flags; /* Private per-task flags */ /* For each stat XXX, add following, aligned appropriately * @@ -37,13 +28,13 @@ struct task_delay_info { * associated with the operation is added to XXX_delay. * XXX_delay contains the accumulated delay time in nanoseconds. */ - u64 blkio_start; /* Shared by blkio, swapin */ + u64 blkio_start; u64 blkio_delay; /* wait for sync block io completion */ - u64 swapin_delay; /* wait for swapin block io completion */ + u64 swapin_start; + u64 swapin_delay; /* wait for swapin */ u32 blkio_count; /* total count of the number of sync block */ /* io operations performed */ - u32 swapin_count; /* total count of the number of swapin block */ - /* io operations performed */ + u32 swapin_count; /* total count of swapin */ u64 freepages_start; u64 freepages_delay; /* wait for memory reclaim */ @@ -51,8 +42,12 @@ struct task_delay_info { u64 thrashing_start; u64 thrashing_delay; /* wait for thrashing page */ + u64 compact_start; + u64 compact_delay; /* wait for memory compact */ + u32 freepages_count; /* total count of memory reclaim */ u32 thrashing_count; /* total count of thrash waits */ + u32 compact_count; /* total count of memory compact */ }; #endif @@ -79,26 +74,10 @@ extern void __delayacct_freepages_start(void); extern void __delayacct_freepages_end(void); extern void __delayacct_thrashing_start(void); extern void __delayacct_thrashing_end(void); - -static inline int delayacct_is_task_waiting_on_io(struct task_struct *p) -{ - if (p->delays) - return (p->delays->flags & DELAYACCT_PF_BLKIO); - else - return 0; -} - -static inline void delayacct_set_flag(struct task_struct *p, int flag) -{ - if (p->delays) - p->delays->flags |= flag; -} - -static inline void delayacct_clear_flag(struct task_struct *p, int flag) -{ - if (p->delays) - p->delays->flags &= ~flag; -} +extern void __delayacct_swapin_start(void); +extern void __delayacct_swapin_end(void); +extern void __delayacct_compact_start(void); +extern void __delayacct_compact_end(void); static inline void delayacct_tsk_init(struct task_struct *tsk) { @@ -123,7 +102,6 @@ static inline void delayacct_blkio_start(void) if (!static_branch_unlikely(&delayacct_key)) return; - delayacct_set_flag(current, DELAYACCT_PF_BLKIO); if (current->delays) __delayacct_blkio_start(); } @@ -135,7 +113,6 @@ static inline void delayacct_blkio_end(struct task_struct *p) if (p->delays) __delayacct_blkio_end(p); - delayacct_clear_flag(p, DELAYACCT_PF_BLKIO); } static inline __u64 delayacct_blkio_ticks(struct task_struct *tsk) @@ -147,33 +124,77 @@ static inline __u64 delayacct_blkio_ticks(struct task_struct *tsk) static inline void delayacct_freepages_start(void) { + if (!static_branch_unlikely(&delayacct_key)) + return; + if (current->delays) __delayacct_freepages_start(); } static inline void delayacct_freepages_end(void) { + if (!static_branch_unlikely(&delayacct_key)) + return; + if (current->delays) __delayacct_freepages_end(); } static inline void delayacct_thrashing_start(void) { + if (!static_branch_unlikely(&delayacct_key)) + return; + if (current->delays) __delayacct_thrashing_start(); } static inline void delayacct_thrashing_end(void) { + if (!static_branch_unlikely(&delayacct_key)) + return; + if (current->delays) __delayacct_thrashing_end(); } +static inline void delayacct_swapin_start(void) +{ + if (!static_branch_unlikely(&delayacct_key)) + return; + + if (current->delays) + __delayacct_swapin_start(); +} + +static inline void delayacct_swapin_end(void) +{ + if (!static_branch_unlikely(&delayacct_key)) + return; + + if (current->delays) + __delayacct_swapin_end(); +} + +static inline void delayacct_compact_start(void) +{ + if (!static_branch_unlikely(&delayacct_key)) + return; + + if (current->delays) + __delayacct_compact_start(); +} + +static inline void delayacct_compact_end(void) +{ + if (!static_branch_unlikely(&delayacct_key)) + return; + + if (current->delays) + __delayacct_compact_end(); +} + #else -static inline void delayacct_set_flag(struct task_struct *p, int flag) -{} -static inline void delayacct_clear_flag(struct task_struct *p, int flag) -{} static inline void delayacct_init(void) {} static inline void delayacct_tsk_init(struct task_struct *tsk) @@ -199,6 +220,14 @@ static inline void delayacct_thrashing_start(void) {} static inline void delayacct_thrashing_end(void) {} +static inline void delayacct_swapin_start(void) +{} +static inline void delayacct_swapin_end(void) +{} +static inline void delayacct_compact_start(void) +{} +static inline void delayacct_compact_end(void) +{} #endif /* CONFIG_TASK_DELAY_ACCT */ diff --git a/include/linux/elfcore-compat.h b/include/linux/elfcore-compat.h index e272c3d452ce..54feb64e9b5d 100644 --- a/include/linux/elfcore-compat.h +++ b/include/linux/elfcore-compat.h @@ -43,6 +43,11 @@ struct compat_elf_prpsinfo __compat_uid_t pr_uid; __compat_gid_t pr_gid; compat_pid_t pr_pid, pr_ppid, pr_pgrp, pr_sid; + /* + * The hard-coded 16 is derived from TASK_COMM_LEN, but it can't be + * changed as it is exposed to userspace. We'd better make it hard-coded + * here. + */ char pr_fname[16]; char pr_psargs[ELF_PRARGSZ]; }; diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h index 957ebec35aad..746e081879a5 100644 --- a/include/linux/elfcore.h +++ b/include/linux/elfcore.h @@ -65,6 +65,11 @@ struct elf_prpsinfo __kernel_gid_t pr_gid; pid_t pr_pid, pr_ppid, pr_pgrp, pr_sid; /* Lots missing */ + /* + * The hard-coded 16 is derived from TASK_COMM_LEN, but it can't be + * changed as it is exposed to userspace. We'd better make it hard-coded + * here. + */ char pr_fname[16]; /* filename of executable */ char pr_psargs[ELF_PRARGSZ]; /* initial part of arg list */ }; diff --git a/include/linux/hash.h b/include/linux/hash.h index ad6fa21d977b..38edaa08f862 100644 --- a/include/linux/hash.h +++ b/include/linux/hash.h @@ -62,10 +62,7 @@ static inline u32 __hash_32_generic(u32 val) return val * GOLDEN_RATIO_32; } -#ifndef HAVE_ARCH_HASH_32 -#define hash_32 hash_32_generic -#endif -static inline u32 hash_32_generic(u32 val, unsigned int bits) +static inline u32 hash_32(u32 val, unsigned int bits) { /* High bits are more random, so use them. */ return __hash_32(val) >> (32 - bits); diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 055eb203c00e..33f47a996513 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -1,4 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ +/* + * NOTE: + * + * This header has combined a lot of unrelated to each other stuff. + * The process of splitting its content is in progress while keeping + * backward compatibility. That's why it's highly recommended NOT to + * include this header inside another header file, especially under + * generic or architectural include/ directory. + */ #ifndef _LINUX_KERNEL_H #define _LINUX_KERNEL_H diff --git a/include/linux/kthread.h b/include/linux/kthread.h index b6c8aafa8db5..3df4ea04716f 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -33,6 +33,7 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), unsigned int cpu, const char *namefmt); +void get_kthread_comm(char *buf, size_t buf_size, struct task_struct *tsk); bool set_kthread_struct(struct task_struct *p); void kthread_set_per_cpu(struct task_struct *k, int cpu); diff --git a/include/linux/list.h b/include/linux/list.h index 6636fc07f918..dd6c2041d09c 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -258,8 +258,7 @@ static inline void list_bulk_move_tail(struct list_head *head, * @list: the entry to test * @head: the head of the list */ -static inline int list_is_first(const struct list_head *list, - const struct list_head *head) +static inline int list_is_first(const struct list_head *list, const struct list_head *head) { return list->prev == head; } @@ -269,13 +268,22 @@ static inline int list_is_first(const struct list_head *list, * @list: the entry to test * @head: the head of the list */ -static inline int list_is_last(const struct list_head *list, - const struct list_head *head) +static inline int list_is_last(const struct list_head *list, const struct list_head *head) { return list->next == head; } /** + * list_is_head - tests whether @list is the list @head + * @list: the entry to test + * @head: the head of the list + */ +static inline int list_is_head(const struct list_head *list, const struct list_head *head) +{ + return list == head; +} + +/** * list_empty - tests whether a list is empty * @head: the list to test. */ @@ -318,7 +326,7 @@ static inline void list_del_init_careful(struct list_head *entry) static inline int list_empty_careful(const struct list_head *head) { struct list_head *next = smp_load_acquire(&head->next); - return (next == head) && (next == head->prev); + return list_is_head(next, head) && (next == head->prev); } /** @@ -393,10 +401,9 @@ static inline void list_cut_position(struct list_head *list, { if (list_empty(head)) return; - if (list_is_singular(head) && - (head->next != entry && head != entry)) + if (list_is_singular(head) && !list_is_head(entry, head) && (entry != head->next)) return; - if (entry == head) + if (list_is_head(entry, head)) INIT_LIST_HEAD(list); else __list_cut_position(list, head, entry); @@ -570,7 +577,7 @@ static inline void list_splice_tail_init(struct list_head *list, * @head: the head for your list. */ #define list_for_each(pos, head) \ - for (pos = (head)->next; pos != (head); pos = pos->next) + for (pos = (head)->next; !list_is_head(pos, (head)); pos = pos->next) /** * list_for_each_continue - continue iteration over a list @@ -580,7 +587,7 @@ static inline void list_splice_tail_init(struct list_head *list, * Continue to iterate over a list, continuing after the current position. */ #define list_for_each_continue(pos, head) \ - for (pos = pos->next; pos != (head); pos = pos->next) + for (pos = pos->next; !list_is_head(pos, (head)); pos = pos->next) /** * list_for_each_prev - iterate over a list backwards @@ -588,7 +595,7 @@ static inline void list_splice_tail_init(struct list_head *list, * @head: the head for your list. */ #define list_for_each_prev(pos, head) \ - for (pos = (head)->prev; pos != (head); pos = pos->prev) + for (pos = (head)->prev; !list_is_head(pos, (head)); pos = pos->prev) /** * list_for_each_safe - iterate over a list safe against removal of list entry @@ -597,8 +604,9 @@ static inline void list_splice_tail_init(struct list_head *list, * @head: the head for your list. */ #define list_for_each_safe(pos, n, head) \ - for (pos = (head)->next, n = pos->next; pos != (head); \ - pos = n, n = pos->next) + for (pos = (head)->next, n = pos->next; \ + !list_is_head(pos, (head)); \ + pos = n, n = pos->next) /** * list_for_each_prev_safe - iterate over a list backwards safe against removal of list entry @@ -608,7 +616,7 @@ static inline void list_splice_tail_init(struct list_head *list, */ #define list_for_each_prev_safe(pos, n, head) \ for (pos = (head)->prev, n = pos->prev; \ - pos != (head); \ + !list_is_head(pos, (head)); \ pos = n, n = pos->prev) /** diff --git a/include/linux/percpu.h b/include/linux/percpu.h index ae4004e7957e..f1ec5ad1351c 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -94,10 +94,7 @@ extern const char * const pcpu_fc_names[PCPU_FC_NR]; extern enum pcpu_fc pcpu_chosen_fc; -typedef void * (*pcpu_fc_alloc_fn_t)(unsigned int cpu, size_t size, - size_t align); -typedef void (*pcpu_fc_free_fn_t)(void *ptr, size_t size); -typedef void (*pcpu_fc_populate_pte_fn_t)(unsigned long addr); +typedef int (pcpu_fc_cpu_to_node_fn_t)(int cpu); typedef int (pcpu_fc_cpu_distance_fn_t)(unsigned int from, unsigned int to); extern struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, @@ -111,15 +108,13 @@ extern void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, extern int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn, - pcpu_fc_alloc_fn_t alloc_fn, - pcpu_fc_free_fn_t free_fn); + pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn); #endif #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK +void __init pcpu_populate_pte(unsigned long addr); extern int __init pcpu_page_first_chunk(size_t reserved_size, - pcpu_fc_alloc_fn_t alloc_fn, - pcpu_fc_free_fn_t free_fn, - pcpu_fc_populate_pte_fn_t populate_pte_fn); + pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn); #endif extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align) __alloc_size(1); diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 069c7fd95396..01b9268451a8 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -178,8 +178,16 @@ static inline struct proc_dir_entry *proc_mkdir_mode(const char *name, #define proc_create_seq(name, mode, parent, ops) ({NULL;}) #define proc_create_single(name, mode, parent, show) ({NULL;}) #define proc_create_single_data(name, mode, parent, show, data) ({NULL;}) -#define proc_create(name, mode, parent, proc_ops) ({NULL;}) -#define proc_create_data(name, mode, parent, proc_ops, data) ({NULL;}) + +static inline struct proc_dir_entry * +proc_create(const char *name, umode_t mode, struct proc_dir_entry *parent, + const struct proc_ops *proc_ops) +{ return NULL; } + +static inline struct proc_dir_entry * +proc_create_data(const char *name, umode_t mode, struct proc_dir_entry *parent, + const struct proc_ops *proc_ops, void *data) +{ return NULL; } static inline void proc_set_size(struct proc_dir_entry *de, loff_t size) {} static inline void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid) {} diff --git a/include/linux/sched.h b/include/linux/sched.h index a6a2db5f85ac..508b91d57470 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -274,8 +274,13 @@ struct task_group; #define get_current_state() READ_ONCE(current->__state) -/* Task command name length: */ -#define TASK_COMM_LEN 16 +/* + * Define the task command name length as enum, then it can be visible to + * BPF programs. + */ +enum { + TASK_COMM_LEN = 16, +}; extern void scheduler_tick(void); diff --git a/include/linux/unaligned/packed_struct.h b/include/linux/unaligned/packed_struct.h index c0d817de4df2..f4c8eaf4d012 100644 --- a/include/linux/unaligned/packed_struct.h +++ b/include/linux/unaligned/packed_struct.h @@ -1,7 +1,7 @@ #ifndef _LINUX_UNALIGNED_PACKED_STRUCT_H #define _LINUX_UNALIGNED_PACKED_STRUCT_H -#include <linux/kernel.h> +#include <linux/types.h> struct __una_u16 { u16 x; } __packed; struct __una_u32 { u32 x; } __packed; diff --git a/include/trace/events/error_report.h b/include/trace/events/error_report.h index 96f64bf218b2..a1922a800e6f 100644 --- a/include/trace/events/error_report.h +++ b/include/trace/events/error_report.h @@ -17,14 +17,16 @@ enum error_detector { ERROR_DETECTOR_KFENCE, - ERROR_DETECTOR_KASAN + ERROR_DETECTOR_KASAN, + ERROR_DETECTOR_WARN, }; #endif /* __ERROR_REPORT_DECLARE_TRACE_ENUMS_ONCE_ONLY */ -#define error_detector_list \ +#define error_detector_list \ EM(ERROR_DETECTOR_KFENCE, "kfence") \ - EMe(ERROR_DETECTOR_KASAN, "kasan") + EM(ERROR_DETECTOR_KASAN, "kasan") \ + EMe(ERROR_DETECTOR_WARN, "warning") /* Always end the list with an EMe. */ #undef EM diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h index ccbd08709321..12327d32378f 100644 --- a/include/uapi/linux/taskstats.h +++ b/include/uapi/linux/taskstats.h @@ -34,7 +34,7 @@ */ -#define TASKSTATS_VERSION 10 +#define TASKSTATS_VERSION 11 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -172,6 +172,10 @@ struct taskstats { /* v10: 64-bit btime to avoid overflow */ __u64 ac_btime64; /* 64-bit begin time */ + + /* Delay waiting for memory compact */ + __u64 compact_count; + __u64 compact_delay_total; }; diff --git a/include/uapi/linux/uuid.h b/include/uapi/linux/uuid.h index e5a7eecef7c3..c0f4bd9b040e 100644 --- a/include/uapi/linux/uuid.h +++ b/include/uapi/linux/uuid.h @@ -1,18 +1,10 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* DO NOT USE in new code! This is solely for MEI due to legacy reasons */ /* * UUID/GUID definition * * Copyright (C) 2010, Intel Corp. * Huang Ying <ying.huang@intel.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation; - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #ifndef _UAPI_LINUX_UUID_H_ diff --git a/kernel/configs/debug.config b/kernel/configs/debug.config new file mode 100644 index 000000000000..e9ffb0cc1eec --- /dev/null +++ b/kernel/configs/debug.config @@ -0,0 +1,105 @@ +# The config is based on running daily CI for enterprise Linux distros to +# seek regressions on linux-next builds on different bare-metal and virtual +# platforms. It can be used for example, +# +# $ make ARCH=arm64 defconfig debug.config +# +# Keep alphabetically sorted inside each section. +# +# printk and dmesg options +# +CONFIG_DEBUG_BUGVERBOSE=y +CONFIG_DYNAMIC_DEBUG=y +CONFIG_PRINTK_CALLER=y +CONFIG_PRINTK_TIME=y +CONFIG_SYMBOLIC_ERRNAME=y +# +# Compile-time checks and compiler options +# +CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_SECTION_MISMATCH=y +CONFIG_FRAME_WARN=2048 +CONFIG_SECTION_MISMATCH_WARN_ONLY=y +# +# Generic Kernel Debugging Instruments +# +# CONFIG_UBSAN_ALIGNMENT is not set +# CONFIG_UBSAN_DIV_ZERO is not set +# CONFIG_UBSAN_TRAP is not set +# CONFIG_WARN_ALL_UNSEEDED_RANDOM is not set +CONFIG_DEBUG_FS=y +CONFIG_DEBUG_FS_ALLOW_ALL=y +CONFIG_DEBUG_IRQFLAGS=y +CONFIG_UBSAN=y +CONFIG_UBSAN_BOOL=y +CONFIG_UBSAN_BOUNDS=y +CONFIG_UBSAN_ENUM=y +CONFIG_UBSAN_SHIFT=y +CONFIG_UBSAN_UNREACHABLE=y +# +# Memory Debugging +# +# CONFIG_DEBUG_PAGEALLOC is not set +# CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF is not set +# CONFIG_DEBUG_RODATA_TEST is not set +# CONFIG_DEBUG_WX is not set +# CONFIG_KFENCE is not set +# CONFIG_PAGE_POISONING is not set +# CONFIG_SLUB_STATS is not set +CONFIG_PAGE_EXTENSION=y +CONFIG_PAGE_OWNER=y +CONFIG_DEBUG_KMEMLEAK=y +CONFIG_DEBUG_KMEMLEAK_AUTO_SCAN=y +CONFIG_DEBUG_OBJECTS=y +CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT=1 +CONFIG_DEBUG_OBJECTS_FREE=y +CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER=y +CONFIG_DEBUG_OBJECTS_RCU_HEAD=y +CONFIG_DEBUG_OBJECTS_TIMERS=y +CONFIG_DEBUG_OBJECTS_WORK=y +CONFIG_DEBUG_PER_CPU_MAPS=y +CONFIG_DEBUG_STACK_USAGE=y +CONFIG_DEBUG_VIRTUAL=y +CONFIG_DEBUG_VM=y +CONFIG_DEBUG_VM_PGFLAGS=y +CONFIG_DEBUG_VM_RB=y +CONFIG_DEBUG_VM_VMACACHE=y +CONFIG_GENERIC_PTDUMP=y +CONFIG_KASAN=y +CONFIG_KASAN_GENERIC=y +CONFIG_KASAN_INLINE=y +CONFIG_KASAN_VMALLOC=y +CONFIG_PTDUMP_DEBUGFS=y +CONFIG_SCHED_STACK_END_CHECK=y +CONFIG_SLUB_DEBUG_ON=y +# +# Debug Oops, Lockups and Hangs +# +# CONFIG_BOOTPARAM_HUNG_TASK_PANIC is not set +# CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set +CONFIG_DEBUG_ATOMIC_SLEEP=y +CONFIG_DETECT_HUNG_TASK=y +CONFIG_PANIC_ON_OOPS=y +CONFIG_PANIC_TIMEOUT=0 +CONFIG_SOFTLOCKUP_DETECTOR=y +# +# Lock Debugging (spinlocks, mutexes, etc...) +# +# CONFIG_PROVE_RAW_LOCK_NESTING is not set +CONFIG_PROVE_LOCKING=y +# +# Debug kernel data structures +# +CONFIG_BUG_ON_DATA_CORRUPTION=y +# +# RCU Debugging +# +CONFIG_PROVE_RCU=y +CONFIG_PROVE_RCU_LIST=y +# +# Tracers +# +CONFIG_BRANCH_PROFILE_NONE=y +CONFIG_DYNAMIC_FTRACE=y +CONFIG_FTRACE=y +CONFIG_FUNCTION_TRACER=y diff --git a/kernel/delayacct.c b/kernel/delayacct.c index 51530d5b15a8..c5e8cea9e05f 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -100,19 +100,10 @@ void __delayacct_blkio_start(void) */ void __delayacct_blkio_end(struct task_struct *p) { - struct task_delay_info *delays = p->delays; - u64 *total; - u32 *count; - - if (p->delays->flags & DELAYACCT_PF_SWAPIN) { - total = &delays->swapin_delay; - count = &delays->swapin_count; - } else { - total = &delays->blkio_delay; - count = &delays->blkio_count; - } - - delayacct_end(&delays->lock, &delays->blkio_start, total, count); + delayacct_end(&p->delays->lock, + &p->delays->blkio_start, + &p->delays->blkio_delay, + &p->delays->blkio_count); } int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) @@ -164,10 +155,13 @@ int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) d->freepages_delay_total = (tmp < d->freepages_delay_total) ? 0 : tmp; tmp = d->thrashing_delay_total + tsk->delays->thrashing_delay; d->thrashing_delay_total = (tmp < d->thrashing_delay_total) ? 0 : tmp; + tmp = d->compact_delay_total + tsk->delays->compact_delay; + d->compact_delay_total = (tmp < d->compact_delay_total) ? 0 : tmp; d->blkio_count += tsk->delays->blkio_count; d->swapin_count += tsk->delays->swapin_count; d->freepages_count += tsk->delays->freepages_count; d->thrashing_count += tsk->delays->thrashing_count; + d->compact_count += tsk->delays->compact_count; raw_spin_unlock_irqrestore(&tsk->delays->lock, flags); return 0; @@ -179,8 +173,7 @@ __u64 __delayacct_blkio_ticks(struct task_struct *tsk) unsigned long flags; raw_spin_lock_irqsave(&tsk->delays->lock, flags); - ret = nsec_to_clock_t(tsk->delays->blkio_delay + - tsk->delays->swapin_delay); + ret = nsec_to_clock_t(tsk->delays->blkio_delay); raw_spin_unlock_irqrestore(&tsk->delays->lock, flags); return ret; } @@ -210,3 +203,29 @@ void __delayacct_thrashing_end(void) ¤t->delays->thrashing_delay, ¤t->delays->thrashing_count); } + +void __delayacct_swapin_start(void) +{ + current->delays->swapin_start = local_clock(); +} + +void __delayacct_swapin_end(void) +{ + delayacct_end(¤t->delays->lock, + ¤t->delays->swapin_start, + ¤t->delays->swapin_delay, + ¤t->delays->swapin_count); +} + +void __delayacct_compact_start(void) +{ + current->delays->compact_start = local_clock(); +} + +void __delayacct_compact_end(void) +{ + delayacct_end(¤t->delays->lock, + ¤t->delays->compact_start, + ¤t->delays->compact_delay, + ¤t->delays->compact_count); +} diff --git a/kernel/kthread.c b/kernel/kthread.c index a2c156ee8275..38c6dd822da8 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -61,6 +61,8 @@ struct kthread { #ifdef CONFIG_BLK_CGROUP struct cgroup_subsys_state *blkcg_css; #endif + /* To store the full name if task comm is truncated. */ + char *full_name; }; enum KTHREAD_BITS { @@ -94,6 +96,18 @@ static inline struct kthread *__to_kthread(struct task_struct *p) return kthread; } +void get_kthread_comm(char *buf, size_t buf_size, struct task_struct *tsk) +{ + struct kthread *kthread = to_kthread(tsk); + + if (!kthread || !kthread->full_name) { + __get_task_comm(buf, buf_size, tsk); + return; + } + + strscpy_pad(buf, kthread->full_name, buf_size); +} + bool set_kthread_struct(struct task_struct *p) { struct kthread *kthread; @@ -121,10 +135,14 @@ void free_kthread_struct(struct task_struct *k) * Can be NULL if kmalloc() in set_kthread_struct() failed. */ kthread = to_kthread(k); + if (!kthread) + return; + #ifdef CONFIG_BLK_CGROUP - WARN_ON_ONCE(kthread && kthread->blkcg_css); + WARN_ON_ONCE(kthread->blkcg_css); #endif k->worker_private = NULL; + kfree(kthread->full_name); kfree(kthread); } @@ -438,12 +456,22 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data), task = create->result; if (!IS_ERR(task)) { char name[TASK_COMM_LEN]; + va_list aq; + int len; /* * task is already visible to other tasks, so updating * COMM must be protected. */ - vsnprintf(name, sizeof(name), namefmt, args); + va_copy(aq, args); + len = vsnprintf(name, sizeof(name), namefmt, aq); + va_end(aq); + if (len >= TASK_COMM_LEN) { + struct kthread *kthread = to_kthread(task); + + /* leave it truncated when out of memory. */ + kthread->full_name = kvasprintf(GFP_KERNEL, namefmt, args); + } set_task_comm(task, name); } kfree(create); diff --git a/kernel/panic.c b/kernel/panic.c index cefd7d82366f..55b50e052ec3 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -32,6 +32,7 @@ #include <linux/bug.h> #include <linux/ratelimit.h> #include <linux/debugfs.h> +#include <trace/events/error_report.h> #include <asm/sections.h> #define PANIC_TIMER_STEP 100 @@ -533,26 +534,9 @@ void oops_enter(void) trigger_all_cpu_backtrace(); } -/* - * 64-bit random ID for oopses: - */ -static u64 oops_id; - -static int init_oops_id(void) -{ - if (!oops_id) - get_random_bytes(&oops_id, sizeof(oops_id)); - else - oops_id++; - - return 0; -} -late_initcall(init_oops_id); - static void print_oops_end_marker(void) { - init_oops_id(); - pr_warn("---[ end trace %016llx ]---\n", (unsigned long long)oops_id); + pr_warn("---[ end trace %016llx ]---\n", 0ULL); } /* @@ -609,6 +593,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint, print_irqtrace_events(current); print_oops_end_marker(); + trace_error_report_end(ERROR_DETECTOR_WARN, (unsigned long)caller); /* Just a warning, don't kill lockdep. */ add_taint(taint, LOCKDEP_STILL_OK); diff --git a/kernel/sys.c b/kernel/sys.c index 2450a9f33cb0..ecc4cf019242 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -220,7 +220,6 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval) niceval = MAX_NICE; rcu_read_lock(); - read_lock(&tasklist_lock); switch (which) { case PRIO_PROCESS: if (who) @@ -235,9 +234,11 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval) pgrp = find_vpid(who); else pgrp = task_pgrp(current); + read_lock(&tasklist_lock); do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { error = set_one_prio(p, niceval, error); } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); + read_unlock(&tasklist_lock); break; case PRIO_USER: uid = make_kuid(cred->user_ns, who); @@ -249,16 +250,15 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval) if (!user) goto out_unlock; /* No processes for this user */ } - do_each_thread(g, p) { + for_each_process_thread(g, p) { if (uid_eq(task_uid(p), uid) && task_pid_vnr(p)) error = set_one_prio(p, niceval, error); - } while_each_thread(g, p); + } if (!uid_eq(uid, cred->uid)) free_uid(user); /* For find_user() */ break; } out_unlock: - read_unlock(&tasklist_lock); rcu_read_unlock(); out: return error; @@ -283,7 +283,6 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who) return -EINVAL; rcu_read_lock(); - read_lock(&tasklist_lock); switch (which) { case PRIO_PROCESS: if (who) @@ -301,11 +300,13 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who) pgrp = find_vpid(who); else pgrp = task_pgrp(current); + read_lock(&tasklist_lock); do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { niceval = nice_to_rlimit(task_nice(p)); if (niceval > retval) retval = niceval; } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); + read_unlock(&tasklist_lock); break; case PRIO_USER: uid = make_kuid(cred->user_ns, who); @@ -317,19 +318,18 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who) if (!user) goto out_unlock; /* No processes for this user */ } - do_each_thread(g, p) { + for_each_process_thread(g, p) { if (uid_eq(task_uid(p), uid) && task_pid_vnr(p)) { niceval = nice_to_rlimit(task_nice(p)); if (niceval > retval) retval = niceval; } - } while_each_thread(g, p); + } if (!uid_eq(uid, cred->uid)) free_uid(user); /* for find_user() */ break; } out_unlock: - read_unlock(&tasklist_lock); rcu_read_unlock(); return retval; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index c77fe36bb3d8..14b89aa37c5c 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1984,6 +1984,8 @@ config KCOV bool "Code coverage for fuzzing" depends on ARCH_HAS_KCOV depends on CC_HAS_SANCOV_TRACE_PC || GCC_PLUGINS + depends on !ARCH_WANTS_NO_INSTR || STACK_VALIDATION || \ + GCC_VERSION >= 120000 || CLANG_VERSION >= 130000 select DEBUG_FS select GCC_PLUGIN_SANCOV if !CC_HAS_SANCOV_TRACE_PC help @@ -2222,12 +2224,11 @@ config TEST_RHASHTABLE If unsure, say N. -config TEST_HASH - tristate "Perform selftest on hash functions" +config TEST_SIPHASH + tristate "Perform selftest on siphash functions" help - Enable this option to test the kernel's integer (<linux/hash.h>), - string (<linux/stringhash.h>), and siphash (<linux/siphash.h>) - hash functions on boot (or module load). + Enable this option to test the kernel's siphash (<linux/siphash.h>) hash + functions on boot (or module load). This is intended to help people writing architecture-specific optimized versions. If unsure, say N. @@ -2371,6 +2372,25 @@ config BITFIELD_KUNIT If unsure, say N. +config HASH_KUNIT_TEST + tristate "KUnit Test for integer hash functions" if !KUNIT_ALL_TESTS + depends on KUNIT + default KUNIT_ALL_TESTS + help + Enable this option to test the kernel's string (<linux/stringhash.h>), and + integer (<linux/hash.h>) hash functions on boot. + + KUnit tests run during boot and output the results to the debug log + in TAP format (https://testanything.org/). Only useful for kernel devs + running the KUnit test harness, and not intended for inclusion into a + production build. + + For more information on KUnit and unit tests in general please refer + to the KUnit documentation in Documentation/dev-tools/kunit/. + + This is intended to help people writing architecture-specific + optimized versions. If unsure, say N. + config RESOURCE_KUNIT_TEST tristate "KUnit test for resource API" depends on KUNIT @@ -2502,6 +2522,7 @@ config TEST_KMOD depends on m depends on NETDEVICES && NET_CORE && INET # for TUN depends on BLOCK + depends on PAGE_SIZE_LESS_THAN_256KB # for BTRFS select TEST_LKM select XFS_FS select TUN diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan index e5372a13511d..236c5cefc4cc 100644 --- a/lib/Kconfig.ubsan +++ b/lib/Kconfig.ubsan @@ -112,19 +112,6 @@ config UBSAN_UNREACHABLE This option enables -fsanitize=unreachable which checks for control flow reaching an expected-to-be-unreachable position. -config UBSAN_OBJECT_SIZE - bool "Perform checking for accesses beyond the end of objects" - default UBSAN - # gcc hugely expands stack usage with -fsanitize=object-size - # https://lore.kernel.org/lkml/CAHk-=wjPasyJrDuwDnpHJS2TuQfExwe=px-SzLeN8GFMAQJPmQ@mail.gmail.com/ - depends on !CC_IS_GCC - depends on $(cc-option,-fsanitize=object-size) - help - This option enables -fsanitize=object-size which checks for accesses - beyond the end of objects where the optimizer can determine both the - object being operated on and its size, usually seen with bad downcasts, - or access to struct members from NULL pointers. - config UBSAN_BOOL bool "Perform checking for non-boolean values used as boolean" default UBSAN diff --git a/lib/Makefile b/lib/Makefile index b213a7bbf3fd..300f569c626b 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -61,7 +61,8 @@ obj-$(CONFIG_TEST_FIRMWARE) += test_firmware.o obj-$(CONFIG_TEST_BITOPS) += test_bitops.o CFLAGS_test_bitops.o += -Werror obj-$(CONFIG_TEST_SYSCTL) += test_sysctl.o -obj-$(CONFIG_TEST_HASH) += test_hash.o test_siphash.o +obj-$(CONFIG_TEST_SIPHASH) += test_siphash.o +obj-$(CONFIG_HASH_KUNIT_TEST) += test_hash.o obj-$(CONFIG_TEST_IDA) += test_ida.o obj-$(CONFIG_KASAN_KUNIT_TEST) += test_kasan.o CFLAGS_test_kasan.o += -fno-builtin diff --git a/lib/kstrtox.c b/lib/kstrtox.c index 059b8b00dc53..886510d248e5 100644 --- a/lib/kstrtox.c +++ b/lib/kstrtox.c @@ -22,6 +22,7 @@ #include "kstrtox.h" +noinline const char *_parse_integer_fixup_radix(const char *s, unsigned int *base) { if (*base == 0) { @@ -47,6 +48,7 @@ const char *_parse_integer_fixup_radix(const char *s, unsigned int *base) * * Don't you dare use this function. */ +noinline unsigned int _parse_integer_limit(const char *s, unsigned int base, unsigned long long *p, size_t max_chars) { @@ -85,6 +87,7 @@ unsigned int _parse_integer_limit(const char *s, unsigned int base, unsigned lon return rv; } +noinline unsigned int _parse_integer(const char *s, unsigned int base, unsigned long long *p) { return _parse_integer_limit(s, base, p, INT_MAX); @@ -125,6 +128,7 @@ static int _kstrtoull(const char *s, unsigned int base, unsigned long long *res) * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. * Preferred over simple_strtoull(). Return code must be checked. */ +noinline int kstrtoull(const char *s, unsigned int base, unsigned long long *res) { if (s[0] == '+') @@ -148,6 +152,7 @@ EXPORT_SYMBOL(kstrtoull); * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. * Preferred over simple_strtoll(). Return code must be checked. */ +noinline int kstrtoll(const char *s, unsigned int base, long long *res) { unsigned long long tmp; @@ -219,6 +224,7 @@ EXPORT_SYMBOL(_kstrtol); * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. * Preferred over simple_strtoul(). Return code must be checked. */ +noinline int kstrtouint(const char *s, unsigned int base, unsigned int *res) { unsigned long long tmp; @@ -249,6 +255,7 @@ EXPORT_SYMBOL(kstrtouint); * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. * Preferred over simple_strtol(). Return code must be checked. */ +noinline int kstrtoint(const char *s, unsigned int base, int *res) { long long tmp; @@ -264,6 +271,7 @@ int kstrtoint(const char *s, unsigned int base, int *res) } EXPORT_SYMBOL(kstrtoint); +noinline int kstrtou16(const char *s, unsigned int base, u16 *res) { unsigned long long tmp; @@ -279,6 +287,7 @@ int kstrtou16(const char *s, unsigned int base, u16 *res) } EXPORT_SYMBOL(kstrtou16); +noinline int kstrtos16(const char *s, unsigned int base, s16 *res) { long long tmp; @@ -294,6 +303,7 @@ int kstrtos16(const char *s, unsigned int base, s16 *res) } EXPORT_SYMBOL(kstrtos16); +noinline int kstrtou8(const char *s, unsigned int base, u8 *res) { unsigned long long tmp; @@ -309,6 +319,7 @@ int kstrtou8(const char *s, unsigned int base, u8 *res) } EXPORT_SYMBOL(kstrtou8); +noinline int kstrtos8(const char *s, unsigned int base, s8 *res) { long long tmp; @@ -333,6 +344,7 @@ EXPORT_SYMBOL(kstrtos8); * [oO][NnFf] for "on" and "off". Otherwise it will return -EINVAL. Value * pointed to by res is updated upon finding a match. */ +noinline int kstrtobool(const char *s, bool *res) { if (!s) diff --git a/lib/list_debug.c b/lib/list_debug.c index 5d5424b51b74..9daa3fb9d1cd 100644 --- a/lib/list_debug.c +++ b/lib/list_debug.c @@ -49,11 +49,11 @@ bool __list_del_entry_valid(struct list_head *entry) "list_del corruption, %px->prev is LIST_POISON2 (%px)\n", entry, LIST_POISON2) || CHECK_DATA_CORRUPTION(prev->next != entry, - "list_del corruption. prev->next should be %px, but was %px\n", - entry, prev->next) || + "list_del corruption. prev->next should be %px, but was %px. (prev=%px)\n", + entry, prev->next, prev) || CHECK_DATA_CORRUPTION(next->prev != entry, - "list_del corruption. next->prev should be %px, but was %px\n", - entry, next->prev)) + "list_del corruption. next->prev should be %px, but was %px. (next=%px)\n", + entry, next->prev, next)) return false; return true; diff --git a/lib/lz4/lz4defs.h b/lib/lz4/lz4defs.h index 673bd206aa98..330aa539b46e 100644 --- a/lib/lz4/lz4defs.h +++ b/lib/lz4/lz4defs.h @@ -36,6 +36,8 @@ */ #include <asm/unaligned.h> + +#include <linux/bitops.h> #include <linux/string.h> /* memset, memcpy */ #define FORCE_INLINE __always_inline diff --git a/lib/test_hash.c b/lib/test_hash.c index 0ee40b4a56dd..bb25fda34794 100644 --- a/lib/test_hash.c +++ b/lib/test_hash.c @@ -14,17 +14,15 @@ * and hash_64(). */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt "\n" - #include <linux/compiler.h> #include <linux/types.h> #include <linux/module.h> #include <linux/hash.h> #include <linux/stringhash.h> -#include <linux/printk.h> +#include <kunit/test.h> /* 32-bit XORSHIFT generator. Seed must not be zero. */ -static u32 __init __attribute_const__ +static u32 __attribute_const__ xorshift(u32 seed) { seed ^= seed << 13; @@ -34,7 +32,7 @@ xorshift(u32 seed) } /* Given a non-zero x, returns a non-zero byte. */ -static u8 __init __attribute_const__ +static u8 __attribute_const__ mod255(u32 x) { x = (x & 0xffff) + (x >> 16); /* 1 <= x <= 0x1fffe */ @@ -45,8 +43,7 @@ mod255(u32 x) } /* Fill the buffer with non-zero bytes. */ -static void __init -fill_buf(char *buf, size_t len, u32 seed) +static void fill_buf(char *buf, size_t len, u32 seed) { size_t i; @@ -56,6 +53,50 @@ fill_buf(char *buf, size_t len, u32 seed) } } +/* Holds most testing variables for the int test. */ +struct test_hash_params { + /* Pointer to integer to be hashed. */ + unsigned long long *h64; + /* Low 32-bits of integer to be hashed. */ + u32 h0; + /* Arch-specific hash result. */ + u32 h1; + /* Generic hash result. */ + u32 h2; + /* ORed hashes of given size (in bits). */ + u32 (*hash_or)[33]; +}; + +#ifdef HAVE_ARCH__HASH_32 +static void +test_int__hash_32(struct kunit *test, struct test_hash_params *params) +{ + params->hash_or[1][0] |= params->h2 = __hash_32_generic(params->h0); +#if HAVE_ARCH__HASH_32 == 1 + KUNIT_EXPECT_EQ_MSG(test, params->h1, params->h2, + "__hash_32(%#x) = %#x != __hash_32_generic() = %#x", + params->h0, params->h1, params->h2); +#endif +} +#endif + +#ifdef HAVE_ARCH_HASH_64 +static void +test_int_hash_64(struct kunit *test, struct test_hash_params *params, u32 const *m, int *k) +{ + params->h2 = hash_64_generic(*params->h64, *k); +#if HAVE_ARCH_HASH_64 == 1 + KUNIT_EXPECT_EQ_MSG(test, params->h1, params->h2, + "hash_64(%#llx, %d) = %#x != hash_64_generic() = %#x", + *params->h64, *k, params->h1, params->h2); +#else + KUNIT_EXPECT_LE_MSG(test, params->h1, params->h2, + "hash_64_generic(%#llx, %d) = %#x > %#x", + *params->h64, *k, params->h1, *m); +#endif +} +#endif + /* * Test the various integer hash functions. h64 (or its low-order bits) * is the integer to hash. hash_or accumulates the OR of the hash values, @@ -65,23 +106,16 @@ fill_buf(char *buf, size_t len, u32 seed) * inline, the code being tested is actually in the module, and you can * recompile and re-test the module without rebooting. */ -static bool __init -test_int_hash(unsigned long long h64, u32 hash_or[2][33]) +static void +test_int_hash(struct kunit *test, unsigned long long h64, u32 hash_or[2][33]) { int k; - u32 h0 = (u32)h64, h1, h2; + struct test_hash_params params = { &h64, (u32)h64, 0, 0, hash_or }; /* Test __hash32 */ - hash_or[0][0] |= h1 = __hash_32(h0); + hash_or[0][0] |= params.h1 = __hash_32(params.h0); #ifdef HAVE_ARCH__HASH_32 - hash_or[1][0] |= h2 = __hash_32_generic(h0); -#if HAVE_ARCH__HASH_32 == 1 - if (h1 != h2) { - pr_err("__hash_32(%#x) = %#x != __hash_32_generic() = %#x", - h0, h1, h2); - return false; - } -#endif + test_int__hash_32(test, ¶ms); #endif /* Test k = 1..32 bits */ @@ -89,63 +123,53 @@ test_int_hash(unsigned long long h64, u32 hash_or[2][33]) u32 const m = ((u32)2 << (k-1)) - 1; /* Low k bits set */ /* Test hash_32 */ - hash_or[0][k] |= h1 = hash_32(h0, k); - if (h1 > m) { - pr_err("hash_32(%#x, %d) = %#x > %#x", h0, k, h1, m); - return false; - } -#ifdef HAVE_ARCH_HASH_32 - h2 = hash_32_generic(h0, k); -#if HAVE_ARCH_HASH_32 == 1 - if (h1 != h2) { - pr_err("hash_32(%#x, %d) = %#x != hash_32_generic() " - " = %#x", h0, k, h1, h2); - return false; - } -#else - if (h2 > m) { - pr_err("hash_32_generic(%#x, %d) = %#x > %#x", - h0, k, h1, m); - return false; - } -#endif -#endif + hash_or[0][k] |= params.h1 = hash_32(params.h0, k); + KUNIT_EXPECT_LE_MSG(test, params.h1, m, + "hash_32(%#x, %d) = %#x > %#x", + params.h0, k, params.h1, m); + /* Test hash_64 */ - hash_or[1][k] |= h1 = hash_64(h64, k); - if (h1 > m) { - pr_err("hash_64(%#llx, %d) = %#x > %#x", h64, k, h1, m); - return false; - } + hash_or[1][k] |= params.h1 = hash_64(h64, k); + KUNIT_EXPECT_LE_MSG(test, params.h1, m, + "hash_64(%#llx, %d) = %#x > %#x", + h64, k, params.h1, m); #ifdef HAVE_ARCH_HASH_64 - h2 = hash_64_generic(h64, k); -#if HAVE_ARCH_HASH_64 == 1 - if (h1 != h2) { - pr_err("hash_64(%#llx, %d) = %#x != hash_64_generic() " - "= %#x", h64, k, h1, h2); - return false; - } -#else - if (h2 > m) { - pr_err("hash_64_generic(%#llx, %d) = %#x > %#x", - h64, k, h1, m); - return false; - } -#endif + test_int_hash_64(test, ¶ms, &m, &k); #endif } - - (void)h2; /* Suppress unused variable warning */ - return true; } #define SIZE 256 /* Run time is cubic in SIZE */ -static int __init -test_hash_init(void) +static void test_string_or(struct kunit *test) { char buf[SIZE+1]; - u32 string_or = 0, hash_or[2][33] = { { 0, } }; - unsigned tests = 0; + u32 string_or = 0; + int i, j; + + fill_buf(buf, SIZE, 1); + + /* Test every possible non-empty substring in the buffer. */ + for (j = SIZE; j > 0; --j) { + buf[j] = '\0'; + + for (i = 0; i <= j; i++) { + u32 h0 = full_name_hash(buf+i, buf+i, j-i); + + string_or |= h0; + } /* i */ + } /* j */ + + /* The OR of all the hash values should cover all the bits */ + KUNIT_EXPECT_EQ_MSG(test, string_or, -1u, + "OR of all string hash results = %#x != %#x", + string_or, -1u); +} + +static void test_hash_or(struct kunit *test) +{ + char buf[SIZE+1]; + u32 hash_or[2][33] = { { 0, } }; unsigned long long h64 = 0; int i, j; @@ -160,46 +184,27 @@ test_hash_init(void) u32 h0 = full_name_hash(buf+i, buf+i, j-i); /* Check that hashlen_string gets the length right */ - if (hashlen_len(hashlen) != j-i) { - pr_err("hashlen_string(%d..%d) returned length" - " %u, expected %d", - i, j, hashlen_len(hashlen), j-i); - return -EINVAL; - } + KUNIT_EXPECT_EQ_MSG(test, hashlen_len(hashlen), j-i, + "hashlen_string(%d..%d) returned length %u, expected %d", + i, j, hashlen_len(hashlen), j-i); /* Check that the hashes match */ - if (hashlen_hash(hashlen) != h0) { - pr_err("hashlen_string(%d..%d) = %08x != " - "full_name_hash() = %08x", - i, j, hashlen_hash(hashlen), h0); - return -EINVAL; - } + KUNIT_EXPECT_EQ_MSG(test, hashlen_hash(hashlen), h0, + "hashlen_string(%d..%d) = %08x != full_name_hash() = %08x", + i, j, hashlen_hash(hashlen), h0); - string_or |= h0; h64 = h64 << 32 | h0; /* For use with hash_64 */ - if (!test_int_hash(h64, hash_or)) - return -EINVAL; - tests++; + test_int_hash(test, h64, hash_or); } /* i */ } /* j */ - /* The OR of all the hash values should cover all the bits */ - if (~string_or) { - pr_err("OR of all string hash results = %#x != %#x", - string_or, -1u); - return -EINVAL; - } - if (~hash_or[0][0]) { - pr_err("OR of all __hash_32 results = %#x != %#x", - hash_or[0][0], -1u); - return -EINVAL; - } + KUNIT_EXPECT_EQ_MSG(test, hash_or[0][0], -1u, + "OR of all __hash_32 results = %#x != %#x", + hash_or[0][0], -1u); #ifdef HAVE_ARCH__HASH_32 #if HAVE_ARCH__HASH_32 != 1 /* Test is pointless if results match */ - if (~hash_or[1][0]) { - pr_err("OR of all __hash_32_generic results = %#x != %#x", - hash_or[1][0], -1u); - return -EINVAL; - } + KUNIT_EXPECT_EQ_MSG(test, hash_or[1][0], -1u, + "OR of all __hash_32_generic results = %#x != %#x", + hash_or[1][0], -1u); #endif #endif @@ -207,51 +212,27 @@ test_hash_init(void) for (i = 1; i <= 32; i++) { u32 const m = ((u32)2 << (i-1)) - 1; /* Low i bits set */ - if (hash_or[0][i] != m) { - pr_err("OR of all hash_32(%d) results = %#x " - "(%#x expected)", i, hash_or[0][i], m); - return -EINVAL; - } - if (hash_or[1][i] != m) { - pr_err("OR of all hash_64(%d) results = %#x " - "(%#x expected)", i, hash_or[1][i], m); - return -EINVAL; - } + KUNIT_EXPECT_EQ_MSG(test, hash_or[0][i], m, + "OR of all hash_32(%d) results = %#x (%#x expected)", + i, hash_or[0][i], m); + KUNIT_EXPECT_EQ_MSG(test, hash_or[1][i], m, + "OR of all hash_64(%d) results = %#x (%#x expected)", + i, hash_or[1][i], m); } +} - /* Issue notices about skipped tests. */ -#ifdef HAVE_ARCH__HASH_32 -#if HAVE_ARCH__HASH_32 != 1 - pr_info("__hash_32() is arch-specific; not compared to generic."); -#endif -#else - pr_info("__hash_32() has no arch implementation to test."); -#endif -#ifdef HAVE_ARCH_HASH_32 -#if HAVE_ARCH_HASH_32 != 1 - pr_info("hash_32() is arch-specific; not compared to generic."); -#endif -#else - pr_info("hash_32() has no arch implementation to test."); -#endif -#ifdef HAVE_ARCH_HASH_64 -#if HAVE_ARCH_HASH_64 != 1 - pr_info("hash_64() is arch-specific; not compared to generic."); -#endif -#else - pr_info("hash_64() has no arch implementation to test."); -#endif - - pr_notice("%u tests passed.", tests); +static struct kunit_case hash_test_cases[] __refdata = { + KUNIT_CASE(test_string_or), + KUNIT_CASE(test_hash_or), + {} +}; - return 0; -} +static struct kunit_suite hash_test_suite = { + .name = "hash", + .test_cases = hash_test_cases, +}; -static void __exit test_hash_exit(void) -{ -} -module_init(test_hash_init); /* Does everything */ -module_exit(test_hash_exit); /* Does nothing */ +kunit_test_suite(hash_test_suite); MODULE_LICENSE("GPL"); diff --git a/lib/test_meminit.c b/lib/test_meminit.c index e4f706a404b3..3ca717f11397 100644 --- a/lib/test_meminit.c +++ b/lib/test_meminit.c @@ -337,6 +337,7 @@ static int __init do_kmem_cache_size_bulk(int size, int *total_failures) if (num) kmem_cache_free_bulk(c, num, objects); } + kmem_cache_destroy(c); *total_failures += fail; return 1; } diff --git a/lib/test_ubsan.c b/lib/test_ubsan.c index 7e7bbd0f3fd2..2062be1f2e80 100644 --- a/lib/test_ubsan.c +++ b/lib/test_ubsan.c @@ -79,15 +79,6 @@ static void test_ubsan_load_invalid_value(void) eval2 = eval; } -static void test_ubsan_null_ptr_deref(void) -{ - volatile int *ptr = NULL; - int val; - - UBSAN_TEST(CONFIG_UBSAN_OBJECT_SIZE); - val = *ptr; -} - static void test_ubsan_misaligned_access(void) { volatile char arr[5] __aligned(4) = {1, 2, 3, 4, 5}; @@ -98,29 +89,16 @@ static void test_ubsan_misaligned_access(void) *ptr = val; } -static void test_ubsan_object_size_mismatch(void) -{ - /* "((aligned(8)))" helps this not into be misaligned for ptr-access. */ - volatile int val __aligned(8) = 4; - volatile long long *ptr, val2; - - UBSAN_TEST(CONFIG_UBSAN_OBJECT_SIZE); - ptr = (long long *)&val; - val2 = *ptr; -} - static const test_ubsan_fp test_ubsan_array[] = { test_ubsan_shift_out_of_bounds, test_ubsan_out_of_bounds, test_ubsan_load_invalid_value, test_ubsan_misaligned_access, - test_ubsan_object_size_mismatch, }; /* Excluded because they Oops the module. */ static const test_ubsan_fp skip_ubsan_array[] = { test_ubsan_divrem_overflow, - test_ubsan_null_ptr_deref, }; static int __init test_ubsan_init(void) diff --git a/mm/Kconfig b/mm/Kconfig index 53d7485fc38f..a99bd499ef51 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -432,6 +432,18 @@ config NEED_PER_CPU_KM bool default y +config NEED_PER_CPU_EMBED_FIRST_CHUNK + bool + +config NEED_PER_CPU_PAGE_FIRST_CHUNK + bool + +config USE_PERCPU_NUMA_NODE_ID + bool + +config HAVE_SETUP_PER_CPU_AREA + bool + config CLEANCACHE bool "Enable cleancache driver to cache clean pages if tmem is present" help diff --git a/mm/memory.c b/mm/memory.c index f306e698a1e3..c125c4969913 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3529,7 +3529,6 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (unlikely(!si)) goto out; - delayacct_set_flag(current, DELAYACCT_PF_SWAPIN); page = lookup_swap_cache(entry, vma, vmf->address); swapcache = page; @@ -3577,7 +3576,6 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) vmf->address, &vmf->ptl); if (likely(pte_same(*vmf->pte, vmf->orig_pte))) ret = VM_FAULT_OOM; - delayacct_clear_flag(current, DELAYACCT_PF_SWAPIN); goto unlock; } @@ -3591,13 +3589,11 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) * owner processes (which may be unknown at hwpoison time) */ ret = VM_FAULT_HWPOISON; - delayacct_clear_flag(current, DELAYACCT_PF_SWAPIN); goto out_release; } locked = lock_page_or_retry(page, vma->vm_mm, vmf->flags); - delayacct_clear_flag(current, DELAYACCT_PF_SWAPIN); if (!locked) { ret |= VM_FAULT_RETRY; goto out_release; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d4205e5e41d1..3589febc6d31 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -74,6 +74,7 @@ #include <linux/padata.h> #include <linux/khugepaged.h> #include <linux/buffer_head.h> +#include <linux/delayacct.h> #include <asm/sections.h> #include <asm/tlbflush.h> #include <asm/div64.h> @@ -4365,6 +4366,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, return NULL; psi_memstall_enter(&pflags); + delayacct_compact_start(); noreclaim_flag = memalloc_noreclaim_save(); *compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac, @@ -4372,6 +4374,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, memalloc_noreclaim_restore(noreclaim_flag); psi_memstall_leave(&pflags); + delayacct_compact_end(); if (*compact_result == COMPACT_SKIPPED) return NULL; diff --git a/mm/page_io.c b/mm/page_io.c index 9725c7e1eeea..0bf8e40f4e57 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -25,6 +25,7 @@ #include <linux/psi.h> #include <linux/uio.h> #include <linux/sched/task.h> +#include <linux/delayacct.h> void end_swap_bio_write(struct bio *bio) { @@ -370,6 +371,7 @@ int swap_readpage(struct page *page, bool synchronous) * significant part of overall IO time. */ psi_memstall_enter(&pflags); + delayacct_swapin_start(); if (frontswap_load(page) == 0) { SetPageUptodate(page); @@ -432,6 +434,7 @@ int swap_readpage(struct page *page, bool synchronous) out: psi_memstall_leave(&pflags); + delayacct_swapin_end(); return ret; } diff --git a/mm/percpu.c b/mm/percpu.c index 4199a0604c32..a188ac9a267d 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -2992,6 +2992,42 @@ static struct pcpu_alloc_info * __init __flatten pcpu_build_alloc_info( return ai; } + +static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align, + pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) +{ + const unsigned long goal = __pa(MAX_DMA_ADDRESS); +#ifdef CONFIG_NUMA + int node = NUMA_NO_NODE; + void *ptr; + + if (cpu_to_nd_fn) + node = cpu_to_nd_fn(cpu); + + if (node == NUMA_NO_NODE || !node_online(node) || !NODE_DATA(node)) { + ptr = memblock_alloc_from(size, align, goal); + pr_info("cpu %d has no node %d or node-local memory\n", + cpu, node); + pr_debug("per cpu data for cpu%d %zu bytes at 0x%llx\n", + cpu, size, (u64)__pa(ptr)); + } else { + ptr = memblock_alloc_try_nid(size, align, goal, + MEMBLOCK_ALLOC_ACCESSIBLE, + node); + + pr_debug("per cpu data for cpu%d %zu bytes on node%d at 0x%llx\n", + cpu, size, node, (u64)__pa(ptr)); + } + return ptr; +#else + return memblock_alloc_from(size, align, goal); +#endif +} + +static void __init pcpu_fc_free(void *ptr, size_t size) +{ + memblock_free(ptr, size); +} #endif /* BUILD_EMBED_FIRST_CHUNK || BUILD_PAGE_FIRST_CHUNK */ #if defined(BUILD_EMBED_FIRST_CHUNK) @@ -3001,14 +3037,13 @@ static struct pcpu_alloc_info * __init __flatten pcpu_build_alloc_info( * @dyn_size: minimum free size for dynamic allocation in bytes * @atom_size: allocation atom size * @cpu_distance_fn: callback to determine distance between cpus, optional - * @alloc_fn: function to allocate percpu page - * @free_fn: function to free percpu page + * @cpu_to_nd_fn: callback to convert cpu to it's node, optional * * This is a helper to ease setting up embedded first percpu chunk and * can be called where pcpu_setup_first_chunk() is expected. * * If this function is used to setup the first chunk, it is allocated - * by calling @alloc_fn and used as-is without being mapped into + * by calling pcpu_fc_alloc and used as-is without being mapped into * vmalloc area. Allocations are always whole multiples of @atom_size * aligned to @atom_size. * @@ -3022,7 +3057,7 @@ static struct pcpu_alloc_info * __init __flatten pcpu_build_alloc_info( * @dyn_size specifies the minimum dynamic area size. * * If the needed size is smaller than the minimum or specified unit - * size, the leftover is returned using @free_fn. + * size, the leftover is returned using pcpu_fc_free. * * RETURNS: * 0 on success, -errno on failure. @@ -3030,8 +3065,7 @@ static struct pcpu_alloc_info * __init __flatten pcpu_build_alloc_info( int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn, - pcpu_fc_alloc_fn_t alloc_fn, - pcpu_fc_free_fn_t free_fn) + pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { void *base = (void *)ULONG_MAX; void **areas = NULL; @@ -3066,7 +3100,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, BUG_ON(cpu == NR_CPUS); /* allocate space for the whole group */ - ptr = alloc_fn(cpu, gi->nr_units * ai->unit_size, atom_size); + ptr = pcpu_fc_alloc(cpu, gi->nr_units * ai->unit_size, atom_size, cpu_to_nd_fn); if (!ptr) { rc = -ENOMEM; goto out_free_areas; @@ -3105,12 +3139,12 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, for (i = 0; i < gi->nr_units; i++, ptr += ai->unit_size) { if (gi->cpu_map[i] == NR_CPUS) { /* unused unit, free whole */ - free_fn(ptr, ai->unit_size); + pcpu_fc_free(ptr, ai->unit_size); continue; } /* copy and return the unused part */ memcpy(ptr, __per_cpu_load, ai->static_size); - free_fn(ptr + size_sum, ai->unit_size - size_sum); + pcpu_fc_free(ptr + size_sum, ai->unit_size - size_sum); } } @@ -3129,7 +3163,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, out_free_areas: for (group = 0; group < ai->nr_groups; group++) if (areas[group]) - free_fn(areas[group], + pcpu_fc_free(areas[group], ai->groups[group].nr_units * ai->unit_size); out_free: pcpu_free_alloc_info(ai); @@ -3140,12 +3174,79 @@ out_free: #endif /* BUILD_EMBED_FIRST_CHUNK */ #ifdef BUILD_PAGE_FIRST_CHUNK +#include <asm/pgalloc.h> + +#ifndef P4D_TABLE_SIZE +#define P4D_TABLE_SIZE PAGE_SIZE +#endif + +#ifndef PUD_TABLE_SIZE +#define PUD_TABLE_SIZE PAGE_SIZE +#endif + +#ifndef PMD_TABLE_SIZE +#define PMD_TABLE_SIZE PAGE_SIZE +#endif + +#ifndef PTE_TABLE_SIZE +#define PTE_TABLE_SIZE PAGE_SIZE +#endif +void __init __weak pcpu_populate_pte(unsigned long addr) +{ + pgd_t *pgd = pgd_offset_k(addr); + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + if (pgd_none(*pgd)) { + p4d_t *new; + + new = memblock_alloc(P4D_TABLE_SIZE, P4D_TABLE_SIZE); + if (!new) + goto err_alloc; + pgd_populate(&init_mm, pgd, new); + } + + p4d = p4d_offset(pgd, addr); + if (p4d_none(*p4d)) { + pud_t *new; + + new = memblock_alloc(PUD_TABLE_SIZE, PUD_TABLE_SIZE); + if (!new) + goto err_alloc; + p4d_populate(&init_mm, p4d, new); + } + + pud = pud_offset(p4d, addr); + if (pud_none(*pud)) { + pmd_t *new; + + new = memblock_alloc(PMD_TABLE_SIZE, PMD_TABLE_SIZE); + if (!new) + goto err_alloc; + pud_populate(&init_mm, pud, new); + } + + pmd = pmd_offset(pud, addr); + if (!pmd_present(*pmd)) { + pte_t *new; + + new = memblock_alloc(PTE_TABLE_SIZE, PTE_TABLE_SIZE); + if (!new) + goto err_alloc; + pmd_populate_kernel(&init_mm, pmd, new); + } + + return; + +err_alloc: + panic("%s: Failed to allocate memory\n", __func__); +} + /** * pcpu_page_first_chunk - map the first chunk using PAGE_SIZE pages * @reserved_size: the size of reserved percpu area in bytes - * @alloc_fn: function to allocate percpu page, always called with PAGE_SIZE - * @free_fn: function to free percpu page, always called with PAGE_SIZE - * @populate_pte_fn: function to populate pte + * @cpu_to_nd_fn: callback to convert cpu to it's node, optional * * This is a helper to ease setting up page-remapped first percpu * chunk and can be called where pcpu_setup_first_chunk() is expected. @@ -3156,10 +3257,7 @@ out_free: * RETURNS: * 0 on success, -errno on failure. */ -int __init pcpu_page_first_chunk(size_t reserved_size, - pcpu_fc_alloc_fn_t alloc_fn, - pcpu_fc_free_fn_t free_fn, - pcpu_fc_populate_pte_fn_t populate_pte_fn) +int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { static struct vm_struct vm; struct pcpu_alloc_info *ai; @@ -3201,7 +3299,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, for (i = 0; i < unit_pages; i++) { void *ptr; - ptr = alloc_fn(cpu, PAGE_SIZE, PAGE_SIZE); + ptr = pcpu_fc_alloc(cpu, PAGE_SIZE, PAGE_SIZE, cpu_to_nd_fn); if (!ptr) { pr_warn("failed to allocate %s page for cpu%u\n", psize_str, cpu); @@ -3223,7 +3321,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, (unsigned long)vm.addr + unit * ai->unit_size; for (i = 0; i < unit_pages; i++) - populate_pte_fn(unit_addr + (i << PAGE_SHIFT)); + pcpu_populate_pte(unit_addr + (i << PAGE_SHIFT)); /* pte already populated, the following shouldn't fail */ rc = __pcpu_map_pages(unit_addr, &pages[unit * unit_pages], @@ -3253,7 +3351,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, enomem: while (--j >= 0) - free_fn(page_address(pages[j]), PAGE_SIZE); + pcpu_fc_free(page_address(pages[j]), PAGE_SIZE); rc = -ENOMEM; out_free_ar: memblock_free(pages, pages_size); @@ -3278,17 +3376,6 @@ out_free_ar: unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; EXPORT_SYMBOL(__per_cpu_offset); -static void * __init pcpu_dfl_fc_alloc(unsigned int cpu, size_t size, - size_t align) -{ - return memblock_alloc_from(size, align, __pa(MAX_DMA_ADDRESS)); -} - -static void __init pcpu_dfl_fc_free(void *ptr, size_t size) -{ - memblock_free(ptr, size); -} - void __init setup_per_cpu_areas(void) { unsigned long delta; @@ -3299,9 +3386,8 @@ void __init setup_per_cpu_areas(void) * Always reserve area for module percpu variables. That's * what the legacy allocator did. */ - rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, - PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, NULL, - pcpu_dfl_fc_alloc, pcpu_dfl_fc_free); + rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, PERCPU_DYNAMIC_RESERVE, + PAGE_SIZE, NULL, NULL); if (rc < 0) panic("Failed to initialize percpu areas."); diff --git a/samples/bpf/offwaketime_kern.c b/samples/bpf/offwaketime_kern.c index 4866afd054da..eb4d94742e6b 100644 --- a/samples/bpf/offwaketime_kern.c +++ b/samples/bpf/offwaketime_kern.c @@ -113,11 +113,11 @@ static inline int update_counts(void *ctx, u32 pid, u64 delta) /* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */ struct sched_switch_args { unsigned long long pad; - char prev_comm[16]; + char prev_comm[TASK_COMM_LEN]; int prev_pid; int prev_prio; long long prev_state; - char next_comm[16]; + char next_comm[TASK_COMM_LEN]; int next_pid; int next_prio; }; diff --git a/samples/bpf/test_overhead_kprobe_kern.c b/samples/bpf/test_overhead_kprobe_kern.c index f6d593e47037..8fdd2c9c56b2 100644 --- a/samples/bpf/test_overhead_kprobe_kern.c +++ b/samples/bpf/test_overhead_kprobe_kern.c @@ -6,6 +6,7 @@ */ #include <linux/version.h> #include <linux/ptrace.h> +#include <linux/sched.h> #include <uapi/linux/bpf.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> @@ -22,17 +23,17 @@ int prog(struct pt_regs *ctx) { struct signal_struct *signal; struct task_struct *tsk; - char oldcomm[16] = {}; - char newcomm[16] = {}; + char oldcomm[TASK_COMM_LEN] = {}; + char newcomm[TASK_COMM_LEN] = {}; u16 oom_score_adj; u32 pid; tsk = (void *)PT_REGS_PARM1(ctx); pid = _(tsk->pid); - bpf_probe_read_kernel(oldcomm, sizeof(oldcomm), &tsk->comm); - bpf_probe_read_kernel(newcomm, sizeof(newcomm), - (void *)PT_REGS_PARM2(ctx)); + bpf_probe_read_kernel_str(oldcomm, sizeof(oldcomm), &tsk->comm); + bpf_probe_read_kernel_str(newcomm, sizeof(newcomm), + (void *)PT_REGS_PARM2(ctx)); signal = _(tsk->signal); oom_score_adj = _(signal->oom_score_adj); return 0; diff --git a/samples/bpf/test_overhead_tp_kern.c b/samples/bpf/test_overhead_tp_kern.c index eaa32693f8fc..80edadacb692 100644 --- a/samples/bpf/test_overhead_tp_kern.c +++ b/samples/bpf/test_overhead_tp_kern.c @@ -4,6 +4,7 @@ * modify it under the terms of version 2 of the GNU General Public * License as published by the Free Software Foundation. */ +#include <linux/sched.h> #include <uapi/linux/bpf.h> #include <bpf/bpf_helpers.h> @@ -11,8 +12,8 @@ struct task_rename { __u64 pad; __u32 pid; - char oldcomm[16]; - char newcomm[16]; + char oldcomm[TASK_COMM_LEN]; + char newcomm[TASK_COMM_LEN]; __u16 oom_score_adj; }; SEC("tracepoint/task/task_rename") diff --git a/scripts/Makefile.ubsan b/scripts/Makefile.ubsan index 9e2092fd5206..7099c603ff0a 100644 --- a/scripts/Makefile.ubsan +++ b/scripts/Makefile.ubsan @@ -8,7 +8,6 @@ ubsan-cflags-$(CONFIG_UBSAN_LOCAL_BOUNDS) += -fsanitize=local-bounds ubsan-cflags-$(CONFIG_UBSAN_SHIFT) += -fsanitize=shift ubsan-cflags-$(CONFIG_UBSAN_DIV_ZERO) += -fsanitize=integer-divide-by-zero ubsan-cflags-$(CONFIG_UBSAN_UNREACHABLE) += -fsanitize=unreachable -ubsan-cflags-$(CONFIG_UBSAN_OBJECT_SIZE) += -fsanitize=object-size ubsan-cflags-$(CONFIG_UBSAN_BOOL) += -fsanitize=bool ubsan-cflags-$(CONFIG_UBSAN_ENUM) += -fsanitize=enum ubsan-cflags-$(CONFIG_UBSAN_TRAP) += -fsanitize-undefined-trap-on-error diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 1784921c645d..b01c36a15d9d 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -3172,7 +3172,7 @@ sub process { length($line) > 75 && !($line =~ /^\s*[a-zA-Z0-9_\/\.]+\s+\|\s+\d+/ || # file delta changes - $line =~ /^\s*(?:[\w\.\-]+\/)++[\w\.\-]+:/ || + $line =~ /^\s*(?:[\w\.\-\+]*\/)++[\w\.\-\+]+:/ || # filename then : $line =~ /^\s*(?:Fixes:|Link:|$signature_tags)/i || # A Fixes: or Link: line or signature tag line @@ -3479,47 +3479,47 @@ sub process { # Kconfig supports named choices), so use a word boundary # (\b) rather than a whitespace character (\s) $line =~ /^\+\s*(?:config|menuconfig|choice)\b/) { - my $length = 0; - my $cnt = $realcnt; - my $ln = $linenr + 1; - my $f; - my $is_start = 0; - my $is_end = 0; - for (; $cnt > 0 && defined $lines[$ln - 1]; $ln++) { - $f = $lines[$ln - 1]; - $cnt-- if ($lines[$ln - 1] !~ /^-/); - $is_end = $lines[$ln - 1] =~ /^\+/; + my $ln = $linenr; + my $needs_help = 0; + my $has_help = 0; + my $help_length = 0; + while (defined $lines[$ln]) { + my $f = $lines[$ln++]; next if ($f =~ /^-/); - last if (!$file && $f =~ /^\@\@/); + last if ($f !~ /^[\+ ]/); # !patch context - if ($lines[$ln - 1] =~ /^\+\s*(?:bool|tristate|prompt)\s*["']/) { - $is_start = 1; - } elsif ($lines[$ln - 1] =~ /^\+\s*(?:---)?help(?:---)?$/) { - $length = -1; + if ($f =~ /^\+\s*(?:bool|tristate|prompt)\s*["']/) { + $needs_help = 1; + next; + } + if ($f =~ /^\+\s*help\s*$/) { + $has_help = 1; + next; } - $f =~ s/^.//; - $f =~ s/#.*//; - $f =~ s/^\s+//; - next if ($f =~ /^$/); + $f =~ s/^.//; # strip patch context [+ ] + $f =~ s/#.*//; # strip # directives + $f =~ s/^\s+//; # strip leading blanks + next if ($f =~ /^$/); # skip blank lines + # At the end of this Kconfig block: # This only checks context lines in the patch # and so hopefully shouldn't trigger false # positives, even though some of these are # common words in help texts - if ($f =~ /^\s*(?:config|menuconfig|choice|endchoice| - if|endif|menu|endmenu|source)\b/x) { - $is_end = 1; + if ($f =~ /^(?:config|menuconfig|choice|endchoice| + if|endif|menu|endmenu|source)\b/x) { last; } - $length++; + $help_length++ if ($has_help); } - if ($is_start && $is_end && $length < $min_conf_desc_length) { + if ($needs_help && + $help_length < $min_conf_desc_length) { + my $stat_real = get_stat_real($linenr, $ln - 1); WARN("CONFIG_DESCRIPTION", - "please write a paragraph that describes the config symbol fully\n" . $herecurr); + "please write a help paragraph that fully describes the config symbol\n" . "$here\n$stat_real\n"); } - #print "is_start<$is_start> is_end<$is_end> length<$length>\n"; } # check MAINTAINERS entries diff --git a/scripts/const_structs.checkpatch b/scripts/const_structs.checkpatch index 3980985205a0..1eeb7b42c5b9 100644 --- a/scripts/const_structs.checkpatch +++ b/scripts/const_structs.checkpatch @@ -12,19 +12,27 @@ driver_info drm_connector_funcs drm_encoder_funcs drm_encoder_helper_funcs +dvb_frontend_ops +dvb_tuner_ops ethtool_ops extent_io_ops +fb_ops file_lock_operations file_operations hv_ops +hwmon_ops +ib_device_ops ide_dma_ops ide_port_ops +ieee80211_ops +iio_buffer_setup_ops inode_operations intel_dvo_dev_ops irq_domain_ops item_operations iwl_cfg iwl_ops +kernel_param_ops kgdb_arch kgdb_io kset_uevent_ops @@ -32,25 +40,33 @@ lock_manager_operations machine_desc microcode_ops mlxsw_reg_info +mtd_ooblayout_ops mtrr_ops +nand_controller_ops neigh_ops net_device_ops +nft_expr_ops nlmsvc_binding nvkm_device_chip of_device_id pci_raw_ops phy_ops +pinconf_ops pinctrl_ops pinmux_ops pipe_buf_operations platform_hibernation_ops platform_suspend_ops +proc_ops proto_ops +pwm_ops regmap_access_table regulator_ops +reset_control_ops rpc_pipe_ops rtc_class_ops sd_desc +sdhci_ops seq_operations sirfsoc_padmux snd_ac97_build_ops @@ -67,6 +83,13 @@ uart_ops usb_mon_operations v4l2_ctrl_ops v4l2_ioctl_ops +v4l2_subdev_core_ops +v4l2_subdev_internal_ops +v4l2_subdev_ops +v4l2_subdev_pad_ops +v4l2_subdev_video_ops +vb2_ops vm_operations_struct wacom_features +watchdog_ops wd_ops diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 2075db0c08b8..6bd5221d37b8 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -1718,7 +1718,7 @@ sub vcs_exists { %VCS_cmds = %VCS_cmds_hg; return 2 if eval $VCS_cmds{"available"}; %VCS_cmds = (); - if (!$printed_novcs) { + if (!$printed_novcs && $email_git) { warn("$P: No supported VCS found. Add --nogit to options?\n"); warn("Using a git repository produces better results.\n"); warn("Try Linus Torvalds' latest git repository using:\n"); diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c index 5ef1c15e88ad..11e86739456d 100644 --- a/tools/accounting/getdelays.c +++ b/tools/accounting/getdelays.c @@ -205,6 +205,8 @@ static void print_delayacct(struct taskstats *t) "RECLAIM %12s%15s%15s\n" " %15llu%15llu%15llums\n" "THRASHING%12s%15s%15s\n" + " %15llu%15llu%15llums\n" + "COMPACT %12s%15s%15s\n" " %15llu%15llu%15llums\n", "count", "real total", "virtual total", "delay total", "delay average", @@ -228,7 +230,11 @@ static void print_delayacct(struct taskstats *t) "count", "delay total", "delay average", (unsigned long long)t->thrashing_count, (unsigned long long)t->thrashing_delay_total, - average_ms(t->thrashing_delay_total, t->thrashing_count)); + average_ms(t->thrashing_delay_total, t->thrashing_count), + "count", "delay total", "delay average", + (unsigned long long)t->compact_count, + (unsigned long long)t->compact_delay_total, + average_ms(t->compact_delay_total, t->compact_count)); } static void task_context_switch_counts(struct taskstats *t) diff --git a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c index d9b420972934..f70702fcb224 100644 --- a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c +++ b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c @@ -71,8 +71,8 @@ int iter(struct bpf_iter__task_file *ctx) e.pid = task->tgid; e.id = get_obj_id(file->private_data, obj_type); - bpf_probe_read_kernel(&e.comm, sizeof(e.comm), - task->group_leader->comm); + bpf_probe_read_kernel_str(&e.comm, sizeof(e.comm), + task->group_leader->comm); bpf_seq_write(ctx->meta->seq, &e, sizeof(e)); return 0; diff --git a/tools/include/linux/hash.h b/tools/include/linux/hash.h index ad6fa21d977b..38edaa08f862 100644 --- a/tools/include/linux/hash.h +++ b/tools/include/linux/hash.h @@ -62,10 +62,7 @@ static inline u32 __hash_32_generic(u32 val) return val * GOLDEN_RATIO_32; } -#ifndef HAVE_ARCH_HASH_32 -#define hash_32 hash_32_generic -#endif -static inline u32 hash_32_generic(u32 val, unsigned int bits) +static inline u32 hash_32(u32 val, unsigned int bits) { /* High bits are more random, so use them. */ return __hash_32(val) >> (32 - bits); diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c index a8233e7f173b..728dbd39eff0 100644 --- a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c +++ b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2018 Facebook -#include <linux/bpf.h> +#include <vmlinux.h> #include <bpf/bpf_helpers.h> #ifndef PERF_MAX_STACK_DEPTH @@ -41,11 +41,11 @@ struct { /* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */ struct sched_switch_args { unsigned long long pad; - char prev_comm[16]; + char prev_comm[TASK_COMM_LEN]; int prev_pid; int prev_prio; long long prev_state; - char next_comm[16]; + char next_comm[TASK_COMM_LEN]; int next_pid; int next_prio; }; diff --git a/tools/testing/selftests/bpf/progs/test_tracepoint.c b/tools/testing/selftests/bpf/progs/test_tracepoint.c index ce6974016f53..43bd7a20cc50 100644 --- a/tools/testing/selftests/bpf/progs/test_tracepoint.c +++ b/tools/testing/selftests/bpf/progs/test_tracepoint.c @@ -1,17 +1,17 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2017 Facebook -#include <linux/bpf.h> +#include <vmlinux.h> #include <bpf/bpf_helpers.h> /* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */ struct sched_switch_args { unsigned long long pad; - char prev_comm[16]; + char prev_comm[TASK_COMM_LEN]; int prev_pid; int prev_prio; long long prev_state; - char next_comm[16]; + char next_comm[TASK_COMM_LEN]; int next_pid; int next_prio; }; |