diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 000000000000..89c411b5ce6b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,2 @@ +*.c diff=cpp +*.h diff=cpp diff --git a/.mailmap b/.mailmap index 967f88210b12..2408e56e241b 100644 --- a/.mailmap +++ b/.mailmap @@ -75,6 +75,8 @@ Jean Tourrilhes Jeff Garzik Jens Axboe Jens Osterkamp +Johan Hovold +Johan Hovold John Paul Adrian Glaubitz John Stultz diff --git a/CREDITS b/CREDITS index df0a50eb3f64..513aaa3546bf 100644 --- a/CREDITS +++ b/CREDITS @@ -2296,11 +2296,11 @@ D: Initial implementation of VC's, pty's and select() N: Pavel Machek E: pavel@ucw.cz -D: Softcursor for vga, hypertech cdrom support, vcsa bugfix, nbd +P: 4096R/92DFCE96 4FA7 9EEF FCD4 C44F C585 B8C7 C060 2241 92DF CE96 +D: Softcursor for vga, hypertech cdrom support, vcsa bugfix, nbd, D: sun4/330 port, capabilities for elf, speedup for rm on ext2, USB, -D: work on suspend-to-ram/disk, killing duplicates from ioctl32 -S: Volkova 1131 -S: 198 00 Praha 9 +D: work on suspend-to-ram/disk, killing duplicates from ioctl32, +D: Altera SoCFPGA and Nokia N900 support. S: Czech Republic N: Paul Mackerras diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index fcc1ac094282..219ffd41a911 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -515,6 +515,18 @@ be vanished or the reverse -- new added. This file is only present if the CONFIG_MMU kernel configuration option is enabled. +Note: reading /proc/PID/maps or /proc/PID/smaps is inherently racy (consistent +output can be achieved only in the single read call). +This typically manifests when doing partial reads of these files while the +memory map is being modified. Despite the races, we do provide the following +guarantees: + +1) The mapped addresses never go backwards, which implies no two + regions will ever overlap. +2) If there is something at a given vaddr during the entirety of the + life of the smaps/maps walk, there will be some output for it. + + The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG bits on both physical and virtual pages associated with a process, and the soft-dirty bit on pte (see Documentation/vm/soft-dirty.txt for details). diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index 7f312d80b43b..0e49d39ea74a 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -15,7 +15,6 @@ config ALPHA select GENERIC_IRQ_SHOW select ARCH_WANT_IPC_PARSE_VERSION select ARCH_HAVE_NMI_SAFE_CMPXCHG - select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select AUDIT_ARCH select GENERIC_CLOCKEVENTS select GENERIC_SMP_IDLE_THREAD diff --git a/arch/alpha/kernel/vmlinux.lds.S b/arch/alpha/kernel/vmlinux.lds.S index 647b84c15382..cebecfb76fbf 100644 --- a/arch/alpha/kernel/vmlinux.lds.S +++ b/arch/alpha/kernel/vmlinux.lds.S @@ -22,6 +22,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) *(.gnu.warning) diff --git a/arch/arc/kernel/vmlinux.lds.S b/arch/arc/kernel/vmlinux.lds.S index 36611072305f..f35ed578e007 100644 --- a/arch/arc/kernel/vmlinux.lds.S +++ b/arch/arc/kernel/vmlinux.lds.S @@ -89,6 +89,7 @@ SECTIONS _text = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT *(.fixup) diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 125657b602a4..b5d529fdffab 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -2,7 +2,6 @@ config ARM bool default y select ARCH_CLOCKSOURCE_DATA - select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h index 1bd9510de1b9..e53638c8ed8a 100644 --- a/arch/arm/include/asm/irq.h +++ b/arch/arm/include/asm/irq.h @@ -36,8 +36,9 @@ extern void set_handle_irq(void (*handle_irq)(struct pt_regs *)); #endif #ifdef CONFIG_SMP -extern void arch_trigger_all_cpu_backtrace(bool); -#define arch_trigger_all_cpu_backtrace(x) arch_trigger_all_cpu_backtrace(x) +extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask, + bool exclude_self); +#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace #endif static inline int nr_legacy_irqs(void) diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 937c8920d741..7dd14e8395e6 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -748,19 +748,10 @@ core_initcall(register_cpufreq_notifier); static void raise_nmi(cpumask_t *mask) { - /* - * Generate the backtrace directly if we are running in a calling - * context that is not preemptible by the backtrace IPI. Note - * that nmi_cpu_backtrace() automatically removes the current cpu - * from mask. - */ - if (cpumask_test_cpu(smp_processor_id(), mask) && irqs_disabled()) - nmi_cpu_backtrace(NULL); - smp_cross_call(mask, IPI_CPU_BACKTRACE); } -void arch_trigger_all_cpu_backtrace(bool include_self) +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) { - nmi_trigger_all_cpu_backtrace(include_self, raise_nmi); + nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_nmi); } diff --git a/arch/arm/kernel/vmlinux-xip.lds.S b/arch/arm/kernel/vmlinux-xip.lds.S index cba1ec899a69..7fa487ef7e2f 100644 --- a/arch/arm/kernel/vmlinux-xip.lds.S +++ b/arch/arm/kernel/vmlinux-xip.lds.S @@ -98,6 +98,7 @@ SECTIONS IRQENTRY_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT *(.gnu.warning) diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index d24e5dd2aa7a..f7f55df0bf7b 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -111,6 +111,7 @@ SECTIONS SOFTIRQENTRY_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT HYPERVISOR_TEXT KPROBES_TEXT diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 01600401a53e..30398dbc940a 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -8,9 +8,9 @@ config ARM64 select ARCH_CLOCKSOURCE_DATA select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI - select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_GCOV_PROFILE_ALL + select ARCH_HAS_GIGANTIC_PAGE select ARCH_HAS_KCOV select ARCH_HAS_SG_CHAIN select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 5ce9b2929e0d..1105aab1e6d6 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -122,6 +122,7 @@ SECTIONS ENTRY_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT HYPERVISOR_TEXT diff --git a/arch/avr32/kernel/vmlinux.lds.S b/arch/avr32/kernel/vmlinux.lds.S index a4589176bed5..17f2730eb497 100644 --- a/arch/avr32/kernel/vmlinux.lds.S +++ b/arch/avr32/kernel/vmlinux.lds.S @@ -52,6 +52,7 @@ SECTIONS KPROBES_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) *(.gnu.warning) diff --git a/arch/blackfin/kernel/vmlinux.lds.S b/arch/blackfin/kernel/vmlinux.lds.S index d920b959ff3a..68069a120055 100644 --- a/arch/blackfin/kernel/vmlinux.lds.S +++ b/arch/blackfin/kernel/vmlinux.lds.S @@ -33,6 +33,7 @@ SECTIONS #ifndef CONFIG_SCHEDULE_L1 SCHED_TEXT #endif + CPUIDLE_TEXT LOCK_TEXT IRQENTRY_TEXT SOFTIRQENTRY_TEXT diff --git a/arch/c6x/kernel/vmlinux.lds.S b/arch/c6x/kernel/vmlinux.lds.S index 50bc10f97bcb..a1a5c166bc9b 100644 --- a/arch/c6x/kernel/vmlinux.lds.S +++ b/arch/c6x/kernel/vmlinux.lds.S @@ -70,6 +70,7 @@ SECTIONS _stext = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT IRQENTRY_TEXT SOFTIRQENTRY_TEXT diff --git a/arch/cris/kernel/vmlinux.lds.S b/arch/cris/kernel/vmlinux.lds.S index 7552c2557506..979586261520 100644 --- a/arch/cris/kernel/vmlinux.lds.S +++ b/arch/cris/kernel/vmlinux.lds.S @@ -43,6 +43,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) *(.text.__*) diff --git a/arch/frv/kernel/vmlinux.lds.S b/arch/frv/kernel/vmlinux.lds.S index 7e958d829ec9..aa6e573d57da 100644 --- a/arch/frv/kernel/vmlinux.lds.S +++ b/arch/frv/kernel/vmlinux.lds.S @@ -63,6 +63,7 @@ SECTIONS *(.text..tlbmiss) TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT #ifdef CONFIG_DEBUG_INFO INIT_TEXT diff --git a/arch/h8300/kernel/vmlinux.lds.S b/arch/h8300/kernel/vmlinux.lds.S index cb5dfb02c88d..7f11da1b895e 100644 --- a/arch/h8300/kernel/vmlinux.lds.S +++ b/arch/h8300/kernel/vmlinux.lds.S @@ -29,6 +29,7 @@ SECTIONS _stext = . ; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT #if defined(CONFIG_ROMKERNEL) *(.int_redirect) diff --git a/arch/hexagon/kernel/vmlinux.lds.S b/arch/hexagon/kernel/vmlinux.lds.S index 5f268c1071b3..ec87e67feb19 100644 --- a/arch/hexagon/kernel/vmlinux.lds.S +++ b/arch/hexagon/kernel/vmlinux.lds.S @@ -50,6 +50,7 @@ SECTIONS _text = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT *(.fixup) diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h index f565ad376142..65d4bb2b6685 100644 --- a/arch/ia64/include/asm/atomic.h +++ b/arch/ia64/include/asm/atomic.h @@ -269,6 +269,22 @@ static __inline__ long atomic64_add_unless(atomic64_t *v, long a, long u) #define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) +static __inline__ long atomic64_dec_if_positive(atomic64_t *v) +{ + long c, old, dec; + c = atomic64_read(v); + for (;;) { + dec = c - 1; + if (unlikely(dec < 0)) + break; + old = atomic64_cmpxchg((v), c, dec); + if (likely(old == c)) + break; + c = old; + } + return dec; +} + /* * Atomically add I to V and return TRUE if the resulting value is * negative. diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S index dc506b05ffbd..f89d20c97412 100644 --- a/arch/ia64/kernel/vmlinux.lds.S +++ b/arch/ia64/kernel/vmlinux.lds.S @@ -46,6 +46,7 @@ SECTIONS { __end_ivt_text = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT *(.gnu.linkonce.t*) diff --git a/arch/m32r/kernel/vmlinux.lds.S b/arch/m32r/kernel/vmlinux.lds.S index 018e4a711d79..ad1fe56455aa 100644 --- a/arch/m32r/kernel/vmlinux.lds.S +++ b/arch/m32r/kernel/vmlinux.lds.S @@ -31,6 +31,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) *(.gnu.warning) diff --git a/arch/m68k/kernel/vmlinux-nommu.lds b/arch/m68k/kernel/vmlinux-nommu.lds index 06a763f49fd3..d2c8abf1c8c4 100644 --- a/arch/m68k/kernel/vmlinux-nommu.lds +++ b/arch/m68k/kernel/vmlinux-nommu.lds @@ -45,6 +45,7 @@ SECTIONS { HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) . = ALIGN(16); diff --git a/arch/m68k/kernel/vmlinux-std.lds b/arch/m68k/kernel/vmlinux-std.lds index d0993594f558..5b5ce1e4d1ed 100644 --- a/arch/m68k/kernel/vmlinux-std.lds +++ b/arch/m68k/kernel/vmlinux-std.lds @@ -16,6 +16,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) *(.gnu.warning) diff --git a/arch/m68k/kernel/vmlinux-sun3.lds b/arch/m68k/kernel/vmlinux-sun3.lds index 8080469ee6c1..fe5ea1974b16 100644 --- a/arch/m68k/kernel/vmlinux-sun3.lds +++ b/arch/m68k/kernel/vmlinux-sun3.lds @@ -16,6 +16,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) *(.gnu.warning) diff --git a/arch/metag/kernel/vmlinux.lds.S b/arch/metag/kernel/vmlinux.lds.S index 150ace92c7ad..e6c700eaf207 100644 --- a/arch/metag/kernel/vmlinux.lds.S +++ b/arch/metag/kernel/vmlinux.lds.S @@ -21,6 +21,7 @@ SECTIONS .text : { TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/microblaze/kernel/vmlinux.lds.S b/arch/microblaze/kernel/vmlinux.lds.S index 0a47f0410554..289d0e7f3e3a 100644 --- a/arch/microblaze/kernel/vmlinux.lds.S +++ b/arch/microblaze/kernel/vmlinux.lds.S @@ -33,6 +33,7 @@ SECTIONS { EXIT_TEXT EXIT_CALL SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 212ff92920d2..1a322c807f22 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -30,7 +30,6 @@ config MIPS select HAVE_ARCH_TRANSPARENT_HUGEPAGE if CPU_SUPPORTS_HUGEPAGES && 64BIT select RTC_LIB if !MACH_LOONGSON64 select GENERIC_ATOMIC64 if !64BIT - select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select HAVE_DMA_CONTIGUOUS select HAVE_DMA_API_DEBUG select GENERIC_IRQ_PROBE diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h index 15e0fecbc300..6bf10e796553 100644 --- a/arch/mips/include/asm/irq.h +++ b/arch/mips/include/asm/irq.h @@ -51,7 +51,8 @@ extern int cp0_fdc_irq; extern int get_c0_fdc_int(void); -void arch_trigger_all_cpu_backtrace(bool); -#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace +void arch_trigger_cpumask_backtrace(const struct cpumask *mask, + bool exclude_self); +#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace #endif /* _ASM_IRQ_H */ diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index 70128d3f770a..9e9e94415d08 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -673,8 +673,6 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, struct file; pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot); -int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, - unsigned long size, pgprot_t *vma_prot); #endif /* diff --git a/arch/mips/include/asm/uprobes.h b/arch/mips/include/asm/uprobes.h index 70a4a2f173ff..b86d1ae07125 100644 --- a/arch/mips/include/asm/uprobes.h +++ b/arch/mips/include/asm/uprobes.h @@ -42,16 +42,4 @@ struct arch_uprobe_task { unsigned long saved_trap_nr; }; -extern int arch_uprobe_analyze_insn(struct arch_uprobe *aup, - struct mm_struct *mm, unsigned long addr); -extern int arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs); -extern int arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs); -extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk); -extern int arch_uprobe_exception_notify(struct notifier_block *self, - unsigned long val, void *data); -extern void arch_uprobe_abort_xol(struct arch_uprobe *aup, - struct pt_regs *regs); -extern unsigned long arch_uretprobe_hijack_return_addr( - unsigned long trampoline_vaddr, struct pt_regs *regs); - #endif /* __ASM_UPROBES_H */ diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index d2d061520a23..9514e5f2209f 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -569,9 +569,16 @@ static void arch_dump_stack(void *info) dump_stack(); } -void arch_trigger_all_cpu_backtrace(bool include_self) +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) { - smp_call_function(arch_dump_stack, NULL, 1); + long this_cpu = get_cpu(); + + if (cpumask_test_cpu(this_cpu, mask) && !exclude_self) + dump_stack(); + + smp_call_function_many(mask, arch_dump_stack, NULL, 1); + + put_cpu(); } int mips_get_process_fp_mode(struct task_struct *task) diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S index a82c178d0bb9..d5de67591735 100644 --- a/arch/mips/kernel/vmlinux.lds.S +++ b/arch/mips/kernel/vmlinux.lds.S @@ -55,6 +55,7 @@ SECTIONS .text : { TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/mn10300/kernel/vmlinux.lds.S b/arch/mn10300/kernel/vmlinux.lds.S index 13c4814c29f8..2d5f1c3f1afb 100644 --- a/arch/mn10300/kernel/vmlinux.lds.S +++ b/arch/mn10300/kernel/vmlinux.lds.S @@ -30,6 +30,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT *(.fixup) diff --git a/arch/nios2/kernel/vmlinux.lds.S b/arch/nios2/kernel/vmlinux.lds.S index e23e89539967..6a8045bb1a77 100644 --- a/arch/nios2/kernel/vmlinux.lds.S +++ b/arch/nios2/kernel/vmlinux.lds.S @@ -37,6 +37,7 @@ SECTIONS .text : { TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT IRQENTRY_TEXT SOFTIRQENTRY_TEXT diff --git a/arch/openrisc/kernel/vmlinux.lds.S b/arch/openrisc/kernel/vmlinux.lds.S index d936de4c07ca..d68b9ede8423 100644 --- a/arch/openrisc/kernel/vmlinux.lds.S +++ b/arch/openrisc/kernel/vmlinux.lds.S @@ -47,6 +47,7 @@ SECTIONS _stext = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 2a0339a68894..71c4a3aa3752 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -16,7 +16,6 @@ config PARISC select BUILDTIME_EXTABLE_SORT select HAVE_PERF_EVENTS select GENERIC_ATOMIC64 if !64BIT - select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select GENERIC_IRQ_PROBE select GENERIC_PCI_IOMAP select ARCH_HAVE_NMI_SAFE_CMPXCHG diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S index 5b8fae8d4d12..b37787dbe775 100644 --- a/arch/parisc/kernel/vmlinux.lds.S +++ b/arch/parisc/kernel/vmlinux.lds.S @@ -69,6 +69,7 @@ SECTIONS .text ALIGN(PAGE_SIZE) : { TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 569b4f9271a4..65fba4c34cd7 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -108,7 +108,6 @@ config PPC select HAVE_DEBUG_KMEMLEAK select ARCH_HAS_SG_CHAIN select GENERIC_ATOMIC64 if PPC32 - select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select HAVE_PERF_EVENTS select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h index 7b589178be46..4d52ccfc2366 100644 --- a/arch/powerpc/include/asm/mmzone.h +++ b/arch/powerpc/include/asm/mmzone.h @@ -41,6 +41,9 @@ u64 memory_hotplug_max(void); #else #define memory_hotplug_max() memblock_end_of_DRAM() #endif /* CONFIG_NEED_MULTIPLE_NODES */ +#ifdef CONFIG_FA_DUMP +#define __HAVE_ARCH_RESERVED_KERNEL_PAGES +#endif #endif /* __KERNEL__ */ #endif /* _ASM_MMZONE_H_ */ diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 963918e0974a..8f0c7c5d93f2 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -333,6 +333,11 @@ int __init fadump_reserve_mem(void) return 1; } +unsigned long __init arch_reserved_kernel_pages(void) +{ + return memblock_reserved_size() / PAGE_SIZE; +} + /* Look for fadump= cmdline option. */ static int __init early_fadump_param(char *p) { diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 2d1cfafd1404..8295f51c1a5f 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -99,6 +99,7 @@ SECTIONS /* careful! __ftr_alt_* sections need to be close to .text */ *(.text .fixup __ftr_alt_* .ref.text) SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index deeadfa291ba..426481d4cc86 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -67,10 +67,10 @@ config DEBUG_RODATA config S390 def_bool y - select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_GCOV_PROFILE_ALL + select ARCH_HAS_GIGANTIC_PAGE select ARCH_HAS_KCOV select ARCH_HAS_SG_CHAIN select ARCH_HAS_UBSAN_SANITIZE_ALL diff --git a/arch/s390/include/asm/uprobes.h b/arch/s390/include/asm/uprobes.h index 1411dff7fea7..658393c65d7e 100644 --- a/arch/s390/include/asm/uprobes.h +++ b/arch/s390/include/asm/uprobes.h @@ -29,14 +29,4 @@ struct arch_uprobe { struct arch_uprobe_task { }; -int arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm, - unsigned long addr); -int arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs); -int arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs); -bool arch_uprobe_xol_was_trapped(struct task_struct *tsk); -int arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, - void *data); -void arch_uprobe_abort_xol(struct arch_uprobe *ap, struct pt_regs *regs); -unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline, - struct pt_regs *regs); #endif /* _ASM_UPROBES_H */ diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 437e61159279..0f9cd90c11af 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -189,7 +189,7 @@ static int groups16_to_user(u16 __user *grouplist, struct group_info *group_info kgid_t kgid; for (i = 0; i < group_info->ngroups; i++) { - kgid = GROUP_AT(group_info, i); + kgid = group_info->gid[i]; group = (u16)from_kgid_munged(user_ns, kgid); if (put_user(group, grouplist+i)) return -EFAULT; @@ -213,7 +213,7 @@ static int groups16_from_user(struct group_info *group_info, u16 __user *groupli if (!gid_valid(kgid)) return -EINVAL; - GROUP_AT(group_info, i) = kgid; + group_info->gid[i] = kgid; } return 0; diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 429bfd111961..000e6e91f6a0 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -35,6 +35,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/score/kernel/vmlinux.lds.S b/arch/score/kernel/vmlinux.lds.S index 7274b5c4287e..4117890b1db1 100644 --- a/arch/score/kernel/vmlinux.lds.S +++ b/arch/score/kernel/vmlinux.lds.S @@ -40,6 +40,7 @@ SECTIONS _text = .; /* Text and read-only data */ TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT *(.text.*) diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S index 235a4101999f..5b9a3cc90c58 100644 --- a/arch/sh/kernel/vmlinux.lds.S +++ b/arch/sh/kernel/vmlinux.lds.S @@ -36,6 +36,7 @@ SECTIONS TEXT_TEXT EXTRA_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index f5d60f14a0bc..b23c76b42d6e 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -22,7 +22,6 @@ config SPARC select HAVE_ARCH_TRACEHOOK select HAVE_EXIT_THREAD select SYSCTL_EXCEPTION_TRACE - select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select RTC_CLASS select RTC_DRV_M48T59 select RTC_SYSTOHC diff --git a/arch/sparc/include/asm/irq_64.h b/arch/sparc/include/asm/irq_64.h index 3f70f900e834..1d51a11fb261 100644 --- a/arch/sparc/include/asm/irq_64.h +++ b/arch/sparc/include/asm/irq_64.h @@ -86,8 +86,9 @@ static inline unsigned long get_softint(void) return retval; } -void arch_trigger_all_cpu_backtrace(bool); -#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace +void arch_trigger_cpumask_backtrace(const struct cpumask *mask, + bool exclude_self); +#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace extern void *hardirq_stack[NR_CPUS]; extern void *softirq_stack[NR_CPUS]; diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index fa14402b33f9..47ff5588e521 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -239,7 +239,7 @@ static void __global_reg_poll(struct global_reg_snapshot *gp) } } -void arch_trigger_all_cpu_backtrace(bool include_self) +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) { struct thread_info *tp = current_thread_info(); struct pt_regs *regs = get_irq_regs(); @@ -255,15 +255,15 @@ void arch_trigger_all_cpu_backtrace(bool include_self) memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot)); - if (include_self) + if (cpumask_test_cpu(this_cpu, mask) && !exclude_self) __global_reg_self(tp, regs, this_cpu); smp_fetch_global_regs(); - for_each_online_cpu(cpu) { + for_each_cpu(cpu, mask) { struct global_reg_snapshot *gp; - if (!include_self && cpu == this_cpu) + if (exclude_self && cpu == this_cpu) continue; gp = &global_cpu_snapshot[cpu].reg; @@ -300,7 +300,7 @@ void arch_trigger_all_cpu_backtrace(bool include_self) static void sysrq_handle_globreg(int key) { - arch_trigger_all_cpu_backtrace(true); + trigger_all_cpu_backtrace(); } static struct sysrq_key_op sparc_globalreg_op = { diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S index d79b3b734245..572db686f845 100644 --- a/arch/sparc/kernel/vmlinux.lds.S +++ b/arch/sparc/kernel/vmlinux.lds.S @@ -49,6 +49,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig index 78da75b670bc..4583c0320059 100644 --- a/arch/tile/Kconfig +++ b/arch/tile/Kconfig @@ -3,7 +3,6 @@ config TILE def_bool y - select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_WANT_FRAME_POINTERS diff --git a/arch/tile/include/asm/irq.h b/arch/tile/include/asm/irq.h index 84a924034bdb..1fa1f2544ff9 100644 --- a/arch/tile/include/asm/irq.h +++ b/arch/tile/include/asm/irq.h @@ -79,8 +79,9 @@ void tile_irq_activate(unsigned int irq, int tile_irq_type); void setup_irq_regs(void); #ifdef __tilegx__ -void arch_trigger_all_cpu_backtrace(bool self); -#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace +void arch_trigger_cpumask_backtrace(const struct cpumask *mask, + bool exclude_self); +#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace #endif #endif /* _ASM_TILE_IRQ_H */ diff --git a/arch/tile/kernel/entry.S b/arch/tile/kernel/entry.S index 670a3569450f..101de132e363 100644 --- a/arch/tile/kernel/entry.S +++ b/arch/tile/kernel/entry.S @@ -50,7 +50,7 @@ STD_ENTRY(smp_nap) * When interrupted at _cpu_idle_nap, we bump the PC forward 8, and * as a result return to the function that called _cpu_idle(). */ -STD_ENTRY(_cpu_idle) +STD_ENTRY_SECTION(_cpu_idle, .cpuidle.text) movei r1, 1 IRQ_ENABLE_LOAD(r2, r3) mtspr INTERRUPT_CRITICAL_SECTION, r1 diff --git a/arch/tile/kernel/pmc.c b/arch/tile/kernel/pmc.c index db62cc34b955..81cf8743a3f3 100644 --- a/arch/tile/kernel/pmc.c +++ b/arch/tile/kernel/pmc.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include @@ -29,9 +28,7 @@ int handle_perf_interrupt(struct pt_regs *regs, int fault) if (!perf_irq) panic("Unexpected PERF_COUNT interrupt %d\n", fault); - nmi_enter(); retval = perf_irq(regs, fault); - nmi_exit(); return retval; } diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c index a465d8372edd..9f37106ef93a 100644 --- a/arch/tile/kernel/process.c +++ b/arch/tile/kernel/process.c @@ -22,7 +22,7 @@ #include #include #include -#include +#include #include #include #include @@ -594,66 +594,18 @@ void show_regs(struct pt_regs *regs) tile_show_stack(&kbt); } -/* To ensure stack dump on tiles occurs one by one. */ -static DEFINE_SPINLOCK(backtrace_lock); -/* To ensure no backtrace occurs before all of the stack dump are done. */ -static atomic_t backtrace_cpus; -/* The cpu mask to avoid reentrance. */ -static struct cpumask backtrace_mask; - -void do_nmi_dump_stack(struct pt_regs *regs) -{ - int is_idle = is_idle_task(current) && !in_interrupt(); - int cpu; - - nmi_enter(); - cpu = smp_processor_id(); - if (WARN_ON_ONCE(!cpumask_test_and_clear_cpu(cpu, &backtrace_mask))) - goto done; - - spin_lock(&backtrace_lock); - if (is_idle) - pr_info("CPU: %d idle\n", cpu); - else - show_regs(regs); - spin_unlock(&backtrace_lock); - atomic_dec(&backtrace_cpus); -done: - nmi_exit(); -} - #ifdef __tilegx__ -void arch_trigger_all_cpu_backtrace(bool self) +void nmi_raise_cpu_backtrace(struct cpumask *in_mask) { struct cpumask mask; HV_Coord tile; unsigned int timeout; int cpu; - int ongoing; HV_NMI_Info info[NR_CPUS]; - ongoing = atomic_cmpxchg(&backtrace_cpus, 0, num_online_cpus() - 1); - if (ongoing != 0) { - pr_err("Trying to do all-cpu backtrace.\n"); - pr_err("But another all-cpu backtrace is ongoing (%d cpus left)\n", - ongoing); - if (self) { - pr_err("Reporting the stack on this cpu only.\n"); - dump_stack(); - } - return; - } - - cpumask_copy(&mask, cpu_online_mask); - cpumask_clear_cpu(smp_processor_id(), &mask); - cpumask_copy(&backtrace_mask, &mask); - - /* Backtrace for myself first. */ - if (self) - dump_stack(); - /* Tentatively dump stack on remote tiles via NMI. */ timeout = 100; + cpumask_copy(&mask, in_mask); while (!cpumask_empty(&mask) && timeout) { for_each_cpu(cpu, &mask) { tile.x = cpu_x(cpu); @@ -664,12 +616,17 @@ void arch_trigger_all_cpu_backtrace(bool self) } mdelay(10); + touch_softlockup_watchdog(); timeout--; } - /* Warn about cpus stuck in ICS and decrement their counts here. */ + /* Warn about cpus stuck in ICS. */ if (!cpumask_empty(&mask)) { for_each_cpu(cpu, &mask) { + + /* Clear the bit as if nmi_cpu_backtrace() ran. */ + cpumask_clear_cpu(cpu, in_mask); + switch (info[cpu].result) { case HV_NMI_RESULT_FAIL_ICS: pr_warn("Skipping stack dump of cpu %d in ICS at pc %#llx\n", @@ -680,16 +637,20 @@ void arch_trigger_all_cpu_backtrace(bool self) cpu); break; case HV_ENOSYS: - pr_warn("Hypervisor too old to allow remote stack dumps.\n"); - goto skip_for_each; + WARN_ONCE(1, "Hypervisor too old to allow remote stack dumps.\n"); + break; default: /* should not happen */ pr_warn("Skipping stack dump of cpu %d [%d,%#llx]\n", cpu, info[cpu].result, info[cpu].pc); break; } } -skip_for_each: - atomic_sub(cpumask_weight(&mask), &backtrace_cpus); } } + +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) +{ + nmi_trigger_cpumask_backtrace(mask, exclude_self, + nmi_raise_cpu_backtrace); +} #endif /* __tilegx_ */ diff --git a/arch/tile/kernel/traps.c b/arch/tile/kernel/traps.c index 4d9651c5b1ad..39f427bb0de2 100644 --- a/arch/tile/kernel/traps.c +++ b/arch/tile/kernel/traps.c @@ -20,6 +20,8 @@ #include #include #include +#include +#include #include #include #include @@ -392,14 +394,17 @@ void __kprobes do_trap(struct pt_regs *regs, int fault_num, void do_nmi(struct pt_regs *regs, int fault_num, unsigned long reason) { + nmi_enter(); switch (reason) { +#ifdef arch_trigger_cpumask_backtrace case TILE_NMI_DUMP_STACK: - do_nmi_dump_stack(regs); + nmi_cpu_backtrace(regs); break; +#endif default: panic("Unexpected do_nmi type %ld", reason); - return; } + nmi_exit(); } /* Deprecated function currently only used here. */ diff --git a/arch/tile/kernel/vmlinux.lds.S b/arch/tile/kernel/vmlinux.lds.S index 9d449caf8910..e1baf094fba4 100644 --- a/arch/tile/kernel/vmlinux.lds.S +++ b/arch/tile/kernel/vmlinux.lds.S @@ -42,6 +42,7 @@ SECTIONS .text : AT (ADDR(.text) - LOAD_OFFSET) { HEAD_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/um/kernel/dyn.lds.S b/arch/um/kernel/dyn.lds.S index adde088aeeff..4fdbcf958cd5 100644 --- a/arch/um/kernel/dyn.lds.S +++ b/arch/um/kernel/dyn.lds.S @@ -68,6 +68,7 @@ SECTIONS _stext = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) *(.stub .text.* .gnu.linkonce.t.*) diff --git a/arch/um/kernel/uml.lds.S b/arch/um/kernel/uml.lds.S index 6899195602b7..1840f55ed042 100644 --- a/arch/um/kernel/uml.lds.S +++ b/arch/um/kernel/uml.lds.S @@ -28,6 +28,7 @@ SECTIONS _stext = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) /* .gnu.warning sections are handled specially by elf32.em. */ diff --git a/arch/unicore32/kernel/vmlinux.lds.S b/arch/unicore32/kernel/vmlinux.lds.S index 77e407e49a63..56e788e8ee83 100644 --- a/arch/unicore32/kernel/vmlinux.lds.S +++ b/arch/unicore32/kernel/vmlinux.lds.S @@ -37,6 +37,7 @@ SECTIONS .text : { /* Real text segment */ TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 58bec8f9641a..bada636d1065 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -23,11 +23,11 @@ config X86 select ARCH_CLOCKSOURCE_DATA select ARCH_DISCARD_MEMBLOCK select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI - select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FAST_MULTIPLIER select ARCH_HAS_GCOV_PROFILE_ALL + select ARCH_HAS_GIGANTIC_PAGE if X86_64 select ARCH_HAS_KCOV if X86_64 select ARCH_HAS_PMEM_API if X86_64 select ARCH_HAS_MMIO_FLUSH diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index e7de5c9a4fbd..16d3fa211962 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -50,8 +50,9 @@ extern int vector_used_by_percpu_irq(unsigned int vector); extern void init_ISA_irqs(void); #ifdef CONFIG_X86_LOCAL_APIC -void arch_trigger_all_cpu_backtrace(bool); -#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace +void arch_trigger_cpumask_backtrace(const struct cpumask *mask, + bool exclude_self); +#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace #endif #endif /* _ASM_X86_IRQ_H */ diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index b77f5edb03b0..ac7692dcfa2e 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -4,6 +4,10 @@ #include #ifndef __ASSEMBLY__ + +/* Provide __cpuidle; we can't safely include */ +#define __cpuidle __attribute__((__section__(".cpuidle.text"))) + /* * Interrupt control: */ @@ -44,12 +48,12 @@ static inline void native_irq_enable(void) asm volatile("sti": : :"memory"); } -static inline void native_safe_halt(void) +static inline __cpuidle void native_safe_halt(void) { asm volatile("sti; hlt": : :"memory"); } -static inline void native_halt(void) +static inline __cpuidle void native_halt(void) { asm volatile("hlt": : :"memory"); } @@ -86,7 +90,7 @@ static inline notrace void arch_local_irq_enable(void) * Used in the idle loop; sti takes one instruction cycle * to complete: */ -static inline void arch_safe_halt(void) +static inline __cpuidle void arch_safe_halt(void) { native_safe_halt(); } @@ -95,7 +99,7 @@ static inline void arch_safe_halt(void) * Used when interrupts are already enabled or to * shutdown the processor: */ -static inline void halt(void) +static inline __cpuidle void halt(void) { native_halt(); } diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index f1218f512f62..8b4de22d6429 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -439,8 +439,6 @@ extern pgprot_t pgprot_writethrough(pgprot_t prot); struct file; pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot); -int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, - unsigned long size, pgprot_t *vma_prot); /* Install a pte for a particular vaddr in kernel space. */ void set_pte_vaddr(unsigned long vaddr, pte_t pte); diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index bdfad642123f..af15f4444330 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -152,7 +152,7 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu, } EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe); -void acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cx) +void __cpuidle acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cx) { unsigned int cpu = smp_processor_id(); struct cstate_entry *percpu_entry; diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index f29501e1a5c1..c73c9fb281e1 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -26,32 +26,32 @@ u64 hw_nmi_get_sample_period(int watchdog_thresh) } #endif -#ifdef arch_trigger_all_cpu_backtrace +#ifdef arch_trigger_cpumask_backtrace static void nmi_raise_cpu_backtrace(cpumask_t *mask) { apic->send_IPI_mask(mask, NMI_VECTOR); } -void arch_trigger_all_cpu_backtrace(bool include_self) +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) { - nmi_trigger_all_cpu_backtrace(include_self, nmi_raise_cpu_backtrace); + nmi_trigger_cpumask_backtrace(mask, exclude_self, + nmi_raise_cpu_backtrace); } -static int -arch_trigger_all_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs) +static int nmi_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs) { if (nmi_cpu_backtrace(regs)) return NMI_HANDLED; return NMI_DONE; } -NOKPROBE_SYMBOL(arch_trigger_all_cpu_backtrace_handler); +NOKPROBE_SYMBOL(nmi_cpu_backtrace_handler); -static int __init register_trigger_all_cpu_backtrace(void) +static int __init register_nmi_cpu_backtrace_handler(void) { - register_nmi_handler(NMI_LOCAL, arch_trigger_all_cpu_backtrace_handler, + register_nmi_handler(NMI_LOCAL, nmi_cpu_backtrace_handler, 0, "arch_bt"); return 0; } -early_initcall(register_trigger_all_cpu_backtrace); +early_initcall(register_nmi_cpu_backtrace_handler); #endif diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 4002b475171c..28cea7802ecb 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -302,7 +302,7 @@ void arch_cpu_idle(void) /* * We use this if we don't have any better idle routine.. */ -void default_idle(void) +void __cpuidle default_idle(void) { trace_cpu_idle_rcuidle(1, smp_processor_id()); safe_halt(); @@ -417,7 +417,7 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c) * with interrupts enabled and no flags, which is backwards compatible with the * original MWAIT implementation. */ -static void mwait_idle(void) +static __cpuidle void mwait_idle(void) { if (!current_set_polling_and_test()) { trace_cpu_idle_rcuidle(1, smp_processor_id()); diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 9297a002d8e5..dbf67f64d5ec 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -97,6 +97,7 @@ SECTIONS _stext = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT ENTRY_TEXT diff --git a/arch/xtensa/kernel/vmlinux.lds.S b/arch/xtensa/kernel/vmlinux.lds.S index 72cfe3587dd8..31411fc82662 100644 --- a/arch/xtensa/kernel/vmlinux.lds.S +++ b/arch/xtensa/kernel/vmlinux.lds.S @@ -89,6 +89,9 @@ SECTIONS VMLINUX_SYMBOL(__sched_text_start) = .; *(.sched.literal .sched.text) VMLINUX_SYMBOL(__sched_text_end) = .; + VMLINUX_SYMBOL(__cpuidle_text_start) = .; + *(.cpuidle.literal .cpuidle.text) + VMLINUX_SYMBOL(__cpuidle_text_end) = .; VMLINUX_SYMBOL(__lock_text_start) = .; *(.spinlock.literal .spinlock.text) VMLINUX_SYMBOL(__lock_text_end) = .; diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index cea52528aa18..2237d3f24f0e 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -31,6 +31,7 @@ #include /* need_resched() */ #include #include +#include #include /* @@ -115,7 +116,7 @@ static const struct dmi_system_id processor_power_dmi_table[] = { * Callers should disable interrupts before the call and enable * interrupts after return. */ -static void acpi_safe_halt(void) +static void __cpuidle acpi_safe_halt(void) { if (!tif_need_resched()) { safe_halt(); @@ -645,7 +646,7 @@ static int acpi_idle_bm_check(void) * * Caller disables interrupt before call and enables interrupt after return. */ -static void acpi_idle_do_entry(struct acpi_processor_cx *cx) +static void __cpuidle acpi_idle_do_entry(struct acpi_processor_cx *cx) { if (cx->entry_method == ACPI_CSTATE_FFH) { /* Call into architectural FFH based C-state */ diff --git a/drivers/base/memory.c b/drivers/base/memory.c index dc75de9059cd..62c63c0c5c22 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -361,8 +361,11 @@ store_mem_state(struct device *dev, err: unlock_device_hotplug(); - if (ret) + if (ret < 0) return ret; + if (ret) + return -EINVAL; + return count; } diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c index 389ade4572be..ab264d393233 100644 --- a/drivers/cpuidle/driver.c +++ b/drivers/cpuidle/driver.c @@ -14,6 +14,7 @@ #include #include #include +#include #include "cpuidle.h" @@ -178,8 +179,8 @@ static void __cpuidle_driver_init(struct cpuidle_driver *drv) } #ifdef CONFIG_ARCH_HAS_CPU_RELAX -static int poll_idle(struct cpuidle_device *dev, - struct cpuidle_driver *drv, int index) +static int __cpuidle poll_idle(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) { local_irq_enable(); if (!current_set_polling_and_test()) { diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 67ec58f9ef99..4466a2f969d7 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -863,8 +863,8 @@ static struct cpuidle_state dnv_cstates[] = { * * Must be called under local_irq_disable(). */ -static int intel_idle(struct cpuidle_device *dev, - struct cpuidle_driver *drv, int index) +static __cpuidle int intel_idle(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) { unsigned long ecx = 1; /* break on interrupt flag */ struct cpuidle_state *state = &drv->states[index]; diff --git a/drivers/of/base.c b/drivers/of/base.c index a0bccb54a9bd..d687e6de24a0 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -2077,6 +2077,8 @@ void of_alias_scan(void * (*dt_alloc)(u64 size, u64 align)) name = of_get_property(of_aliases, "stdout", NULL); if (name) of_stdout = of_find_node_opts_by_path(name, &of_stdout_options); + if (of_stdout) + console_set_by_of(); } if (!of_aliases) diff --git a/drivers/staging/lustre/lustre/ptlrpc/sec.c b/drivers/staging/lustre/lustre/ptlrpc/sec.c index 5d3995d5c69a..a7416cd9ac71 100644 --- a/drivers/staging/lustre/lustre/ptlrpc/sec.c +++ b/drivers/staging/lustre/lustre/ptlrpc/sec.c @@ -2220,7 +2220,7 @@ int sptlrpc_pack_user_desc(struct lustre_msg *msg, int offset) task_lock(current); if (pud->pud_ngroups > current_ngroups) pud->pud_ngroups = current_ngroups; - memcpy(pud->pud_groups, current_cred()->group_info->blocks[0], + memcpy(pud->pud_groups, current_cred()->group_info->gid, pud->pud_ngroups * sizeof(__u32)); task_unlock(current); diff --git a/fs/Kconfig b/fs/Kconfig index 3ef62bad8f2b..4bd03a2b0518 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -200,6 +200,9 @@ config HUGETLBFS config HUGETLB_PAGE def_bool HUGETLBFS +config ARCH_HAS_GIGANTIC_PAGE + bool + source "fs/configfs/Kconfig" source "fs/efivarfs/Kconfig" diff --git a/fs/dax.c b/fs/dax.c index cc025f82ef07..014defd2e744 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -1036,7 +1036,7 @@ int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, if (!write && !buffer_mapped(&bh)) { spinlock_t *ptl; pmd_t entry; - struct page *zero_page = get_huge_zero_page(); + struct page *zero_page = mm_get_huge_zero_page(vma->vm_mm); if (unlikely(!zero_page)) { dax_pmd_dbg(&bh, address, "no zero page"); diff --git a/fs/ext2/file.c b/fs/ext2/file.c index 423cc01c9d41..0ca363d1341c 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -234,6 +234,7 @@ const struct file_operations ext2_file_operations = { .open = dquot_file_open, .release = ext2_release_file, .fsync = ext2_fsync, + .get_unmapped_area = thp_get_unmapped_area, .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, }; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 25f763f2201a..36d49cfbf2dc 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -697,6 +697,7 @@ const struct file_operations ext4_file_operations = { .open = ext4_file_open, .release = ext4_release_file, .fsync = ext4_sync_file, + .get_unmapped_area = thp_get_unmapped_area, .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, .fallocate = ext4_fallocate, diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 4ea71eba40a5..7337cac29e9e 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -416,7 +416,6 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, for (i = 0; i < pagevec_count(&pvec); ++i) { struct page *page = pvec.pages[i]; - bool rsv_on_error; u32 hash; /* @@ -458,18 +457,17 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, * cache (remove_huge_page) BEFORE removing the * region/reserve map (hugetlb_unreserve_pages). In * rare out of memory conditions, removal of the - * region/reserve map could fail. Before free'ing - * the page, note PagePrivate which is used in case - * of error. + * region/reserve map could fail. Correspondingly, + * the subpool and global reserve usage count can need + * to be adjusted. */ - rsv_on_error = !PagePrivate(page); + VM_BUG_ON(PagePrivate(page)); remove_huge_page(page); freed++; if (!truncate_op) { if (unlikely(hugetlb_unreserve_pages(inode, next, next + 1, 1))) - hugetlb_fix_reserve_counts(inode, - rsv_on_error); + hugetlb_fix_reserve_counts(inode); } unlock_page(page); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index d7b062bdc504..4b308a1487a5 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -679,11 +679,11 @@ unsigned int nfs_page_length(struct page *page) loff_t i_size = i_size_read(page_file_mapping(page)->host); if (i_size > 0) { - pgoff_t page_index = page_file_index(page); + pgoff_t index = page_index(page); pgoff_t end_index = (i_size - 1) >> PAGE_SHIFT; - if (page_index < end_index) + if (index < end_index) return PAGE_SIZE; - if (page_index == end_index) + if (index == end_index) return ((i_size - 1) & ~PAGE_MASK) + 1; } return 0; diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 174dd4cf5747..965db474f4b0 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -342,7 +342,7 @@ nfs_create_request(struct nfs_open_context *ctx, struct page *page, * update_nfs_request below if the region is not locked. */ req->wb_page = page; if (page) { - req->wb_index = page_file_index(page); + req->wb_index = page_index(page); get_page(page); } req->wb_offset = offset; diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 572e5b3b06f1..defc9233e985 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -295,7 +295,7 @@ int nfs_readpage(struct file *file, struct page *page) int error; dprintk("NFS: nfs_readpage (%p %ld@%lu)\n", - page, PAGE_SIZE, page_file_index(page)); + page, PAGE_SIZE, page_index(page)); nfs_inc_stats(inode, NFSIOS_VFSREADPAGE); nfs_add_stats(inode, NFSIOS_READPAGES, 1); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 3a6724c6eb5f..53211838f72a 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -151,7 +151,7 @@ static void nfs_grow_file(struct page *page, unsigned int offset, unsigned int c spin_lock(&inode->i_lock); i_size = i_size_read(inode); end_index = (i_size - 1) >> PAGE_SHIFT; - if (i_size > 0 && page_file_index(page) < end_index) + if (i_size > 0 && page_index(page) < end_index) goto out; end = page_file_offset(page) + ((loff_t)offset+count); if (i_size >= end) @@ -603,7 +603,7 @@ static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, { int ret; - nfs_pageio_cond_complete(pgio, page_file_index(page)); + nfs_pageio_cond_complete(pgio, page_index(page)); ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE, launder); if (ret == -EAGAIN) { diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c index 9d46a0bdd9f9..62469c60be23 100644 --- a/fs/nfsd/auth.c +++ b/fs/nfsd/auth.c @@ -55,10 +55,10 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp) goto oom; for (i = 0; i < rqgi->ngroups; i++) { - if (gid_eq(GLOBAL_ROOT_GID, GROUP_AT(rqgi, i))) - GROUP_AT(gi, i) = exp->ex_anon_gid; + if (gid_eq(GLOBAL_ROOT_GID, rqgi->gid[i])) + gi->gid[i] = exp->ex_anon_gid; else - GROUP_AT(gi, i) = GROUP_AT(rqgi, i); + gi->gid[i] = rqgi->gid[i]; } } else { gi = get_group_info(rqgi); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index a204d7e109d4..39bfaba9c99c 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1903,7 +1903,7 @@ static bool groups_equal(struct group_info *g1, struct group_info *g2) if (g1->ngroups != g2->ngroups) return false; for (i=0; ingroups; i++) - if (!gid_eq(GROUP_AT(g1, i), GROUP_AT(g2, i))) + if (!gid_eq(g1->gid[i], g2->gid[i])) return false; return true; } diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index a64313868d3a..7ebfca6a1427 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -49,12 +49,12 @@ struct kmem_cache *fanotify_perm_event_cachep __read_mostly; * enough to fit in "count". Return an error pointer if the count * is not large enough. * - * Called with the group->notification_mutex held. + * Called with the group->notification_lock held. */ static struct fsnotify_event *get_one_event(struct fsnotify_group *group, size_t count) { - BUG_ON(!mutex_is_locked(&group->notification_mutex)); + assert_spin_locked(&group->notification_lock); pr_debug("%s: group=%p count=%zd\n", __func__, group, count); @@ -64,7 +64,7 @@ static struct fsnotify_event *get_one_event(struct fsnotify_group *group, if (FAN_EVENT_METADATA_LEN > count) return ERR_PTR(-EINVAL); - /* held the notification_mutex the whole time, so this is the + /* held the notification_lock the whole time, so this is the * same event we peeked above */ return fsnotify_remove_first_event(group); } @@ -147,7 +147,7 @@ static struct fanotify_perm_event_info *dequeue_event( { struct fanotify_perm_event_info *event, *return_e = NULL; - spin_lock(&group->fanotify_data.access_lock); + spin_lock(&group->notification_lock); list_for_each_entry(event, &group->fanotify_data.access_list, fae.fse.list) { if (event->fd != fd) @@ -157,7 +157,7 @@ static struct fanotify_perm_event_info *dequeue_event( return_e = event; break; } - spin_unlock(&group->fanotify_data.access_lock); + spin_unlock(&group->notification_lock); pr_debug("%s: found return_re=%p\n", __func__, return_e); @@ -244,10 +244,10 @@ static unsigned int fanotify_poll(struct file *file, poll_table *wait) int ret = 0; poll_wait(file, &group->notification_waitq, wait); - mutex_lock(&group->notification_mutex); + spin_lock(&group->notification_lock); if (!fsnotify_notify_queue_is_empty(group)) ret = POLLIN | POLLRDNORM; - mutex_unlock(&group->notification_mutex); + spin_unlock(&group->notification_lock); return ret; } @@ -268,9 +268,9 @@ static ssize_t fanotify_read(struct file *file, char __user *buf, add_wait_queue(&group->notification_waitq, &wait); while (1) { - mutex_lock(&group->notification_mutex); + spin_lock(&group->notification_lock); kevent = get_one_event(group, count); - mutex_unlock(&group->notification_mutex); + spin_unlock(&group->notification_lock); if (IS_ERR(kevent)) { ret = PTR_ERR(kevent); @@ -309,10 +309,10 @@ static ssize_t fanotify_read(struct file *file, char __user *buf, wake_up(&group->fanotify_data.access_waitq); break; } - spin_lock(&group->fanotify_data.access_lock); + spin_lock(&group->notification_lock); list_add_tail(&kevent->list, &group->fanotify_data.access_list); - spin_unlock(&group->fanotify_data.access_lock); + spin_unlock(&group->notification_lock); #endif } buf += ret; @@ -371,7 +371,7 @@ static int fanotify_release(struct inode *ignored, struct file *file) * Process all permission events on access_list and notification queue * and simulate reply from userspace. */ - spin_lock(&group->fanotify_data.access_lock); + spin_lock(&group->notification_lock); list_for_each_entry_safe(event, next, &group->fanotify_data.access_list, fae.fse.list) { pr_debug("%s: found group=%p event=%p\n", __func__, group, @@ -380,22 +380,22 @@ static int fanotify_release(struct inode *ignored, struct file *file) list_del_init(&event->fae.fse.list); event->response = FAN_ALLOW; } - spin_unlock(&group->fanotify_data.access_lock); /* * Destroy all non-permission events. For permission events just * dequeue them and set the response. They will be freed once the * response is consumed and fanotify_get_response() returns. */ - mutex_lock(&group->notification_mutex); while (!fsnotify_notify_queue_is_empty(group)) { fsn_event = fsnotify_remove_first_event(group); - if (!(fsn_event->mask & FAN_ALL_PERM_EVENTS)) + if (!(fsn_event->mask & FAN_ALL_PERM_EVENTS)) { + spin_unlock(&group->notification_lock); fsnotify_destroy_event(group, fsn_event); - else + spin_lock(&group->notification_lock); + } else FANOTIFY_PE(fsn_event)->response = FAN_ALLOW; } - mutex_unlock(&group->notification_mutex); + spin_unlock(&group->notification_lock); /* Response for all permission events it set, wakeup waiters */ wake_up(&group->fanotify_data.access_waitq); @@ -421,10 +421,10 @@ static long fanotify_ioctl(struct file *file, unsigned int cmd, unsigned long ar switch (cmd) { case FIONREAD: - mutex_lock(&group->notification_mutex); + spin_lock(&group->notification_lock); list_for_each_entry(fsn_event, &group->notification_list, list) send_len += FAN_EVENT_METADATA_LEN; - mutex_unlock(&group->notification_mutex); + spin_unlock(&group->notification_lock); ret = put_user(send_len, (int __user *) p); break; } @@ -765,7 +765,6 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) event_f_flags |= O_LARGEFILE; group->fanotify_data.f_flags = event_f_flags; #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS - spin_lock_init(&group->fanotify_data.access_lock); init_waitqueue_head(&group->fanotify_data.access_waitq); INIT_LIST_HEAD(&group->fanotify_data.access_list); #endif diff --git a/fs/notify/group.c b/fs/notify/group.c index b47f7cfdcaa4..fbe3cbebec16 100644 --- a/fs/notify/group.c +++ b/fs/notify/group.c @@ -45,9 +45,9 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group) */ void fsnotify_group_stop_queueing(struct fsnotify_group *group) { - mutex_lock(&group->notification_mutex); + spin_lock(&group->notification_lock); group->shutdown = true; - mutex_unlock(&group->notification_mutex); + spin_unlock(&group->notification_lock); } /* @@ -125,7 +125,7 @@ struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops) atomic_set(&group->refcnt, 1); atomic_set(&group->num_marks, 0); - mutex_init(&group->notification_mutex); + spin_lock_init(&group->notification_lock); INIT_LIST_HEAD(&group->notification_list); init_waitqueue_head(&group->notification_waitq); group->max_events = UINT_MAX; diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index b8d08d0d0a4d..69d1ea3d292a 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -115,10 +115,10 @@ static unsigned int inotify_poll(struct file *file, poll_table *wait) int ret = 0; poll_wait(file, &group->notification_waitq, wait); - mutex_lock(&group->notification_mutex); + spin_lock(&group->notification_lock); if (!fsnotify_notify_queue_is_empty(group)) ret = POLLIN | POLLRDNORM; - mutex_unlock(&group->notification_mutex); + spin_unlock(&group->notification_lock); return ret; } @@ -138,7 +138,7 @@ static int round_event_name_len(struct fsnotify_event *fsn_event) * enough to fit in "count". Return an error pointer if * not large enough. * - * Called with the group->notification_mutex held. + * Called with the group->notification_lock held. */ static struct fsnotify_event *get_one_event(struct fsnotify_group *group, size_t count) @@ -157,7 +157,7 @@ static struct fsnotify_event *get_one_event(struct fsnotify_group *group, if (event_size > count) return ERR_PTR(-EINVAL); - /* held the notification_mutex the whole time, so this is the + /* held the notification_lock the whole time, so this is the * same event we peeked above */ fsnotify_remove_first_event(group); @@ -234,9 +234,9 @@ static ssize_t inotify_read(struct file *file, char __user *buf, add_wait_queue(&group->notification_waitq, &wait); while (1) { - mutex_lock(&group->notification_mutex); + spin_lock(&group->notification_lock); kevent = get_one_event(group, count); - mutex_unlock(&group->notification_mutex); + spin_unlock(&group->notification_lock); pr_debug("%s: group=%p kevent=%p\n", __func__, group, kevent); @@ -300,13 +300,13 @@ static long inotify_ioctl(struct file *file, unsigned int cmd, switch (cmd) { case FIONREAD: - mutex_lock(&group->notification_mutex); + spin_lock(&group->notification_lock); list_for_each_entry(fsn_event, &group->notification_list, list) { send_len += sizeof(struct inotify_event); send_len += round_event_name_len(fsn_event); } - mutex_unlock(&group->notification_mutex); + spin_unlock(&group->notification_lock); ret = put_user(send_len, (int __user *) p); break; } diff --git a/fs/notify/notification.c b/fs/notify/notification.c index e455e83ceeeb..66f85c651c52 100644 --- a/fs/notify/notification.c +++ b/fs/notify/notification.c @@ -63,7 +63,7 @@ EXPORT_SYMBOL_GPL(fsnotify_get_cookie); /* return true if the notify queue is empty, false otherwise */ bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group) { - BUG_ON(!mutex_is_locked(&group->notification_mutex)); + assert_spin_locked(&group->notification_lock); return list_empty(&group->notification_list) ? true : false; } @@ -73,8 +73,17 @@ void fsnotify_destroy_event(struct fsnotify_group *group, /* Overflow events are per-group and we don't want to free them */ if (!event || event->mask == FS_Q_OVERFLOW) return; - /* If the event is still queued, we have a problem... */ - WARN_ON(!list_empty(&event->list)); + /* + * If the event is still queued, we have a problem... Do an unreliable + * lockless check first to avoid locking in the common case. The + * locking may be necessary for permission events which got removed + * from the list by a different CPU than the one freeing the event. + */ + if (!list_empty(&event->list)) { + spin_lock(&group->notification_lock); + WARN_ON(!list_empty(&event->list)); + spin_unlock(&group->notification_lock); + } group->ops->free_event(event); } @@ -95,10 +104,10 @@ int fsnotify_add_event(struct fsnotify_group *group, pr_debug("%s: group=%p event=%p\n", __func__, group, event); - mutex_lock(&group->notification_mutex); + spin_lock(&group->notification_lock); if (group->shutdown) { - mutex_unlock(&group->notification_mutex); + spin_unlock(&group->notification_lock); return 2; } @@ -106,7 +115,7 @@ int fsnotify_add_event(struct fsnotify_group *group, ret = 2; /* Queue overflow event only if it isn't already queued */ if (!list_empty(&group->overflow_event->list)) { - mutex_unlock(&group->notification_mutex); + spin_unlock(&group->notification_lock); return ret; } event = group->overflow_event; @@ -116,7 +125,7 @@ int fsnotify_add_event(struct fsnotify_group *group, if (!list_empty(list) && merge) { ret = merge(list, event); if (ret) { - mutex_unlock(&group->notification_mutex); + spin_unlock(&group->notification_lock); return ret; } } @@ -124,7 +133,7 @@ int fsnotify_add_event(struct fsnotify_group *group, queue: group->q_len++; list_add_tail(&event->list, list); - mutex_unlock(&group->notification_mutex); + spin_unlock(&group->notification_lock); wake_up(&group->notification_waitq); kill_fasync(&group->fsn_fa, SIGIO, POLL_IN); @@ -139,7 +148,7 @@ struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group *group) { struct fsnotify_event *event; - BUG_ON(!mutex_is_locked(&group->notification_mutex)); + assert_spin_locked(&group->notification_lock); pr_debug("%s: group=%p\n", __func__, group); @@ -161,7 +170,7 @@ struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group *group) */ struct fsnotify_event *fsnotify_peek_first_event(struct fsnotify_group *group) { - BUG_ON(!mutex_is_locked(&group->notification_mutex)); + assert_spin_locked(&group->notification_lock); return list_first_entry(&group->notification_list, struct fsnotify_event, list); @@ -175,12 +184,14 @@ void fsnotify_flush_notify(struct fsnotify_group *group) { struct fsnotify_event *event; - mutex_lock(&group->notification_mutex); + spin_lock(&group->notification_lock); while (!fsnotify_notify_queue_is_empty(group)) { event = fsnotify_remove_first_event(group); + spin_unlock(&group->notification_lock); fsnotify_destroy_event(group, event); + spin_lock(&group->notification_lock); } - mutex_unlock(&group->notification_mutex); + spin_unlock(&group->notification_lock); } /* diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index 1d67fcbf7160..8abab16b4602 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -2104,7 +2104,7 @@ int o2net_start_listening(struct o2nm_node *node) BUG_ON(o2net_listen_sock != NULL); mlog(ML_KTHREAD, "starting o2net thread...\n"); - o2net_wq = create_singlethread_workqueue("o2net"); + o2net_wq = alloc_ordered_workqueue("o2net", WQ_MEM_RECLAIM); if (o2net_wq == NULL) { mlog(ML_ERROR, "unable to launch o2net thread\n"); return -ENOMEM; /* ? */ diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index 533bd524e41e..733e4e79c8e2 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -1904,7 +1904,7 @@ static int dlm_join_domain(struct dlm_ctxt *dlm) } snprintf(wq_name, O2NM_MAX_NAME_LEN, "dlm_wq-%s", dlm->name); - dlm->dlm_worker = create_singlethread_workqueue(wq_name); + dlm->dlm_worker = alloc_workqueue(wq_name, WQ_MEM_RECLAIM, 0); if (!dlm->dlm_worker) { status = -ENOMEM; mlog_errno(status); diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index ef474cdd6404..354cdf9714aa 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -646,7 +646,7 @@ static int __init init_dlmfs_fs(void) } cleanup_inode = 1; - user_dlm_worker = create_singlethread_workqueue("user_dlm"); + user_dlm_worker = alloc_workqueue("user_dlm", WQ_MEM_RECLAIM, 0); if (!user_dlm_worker) { status = -ENOMEM; goto bail; diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h index 50cc55047443..5af68fcdf9d3 100644 --- a/fs/ocfs2/inode.h +++ b/fs/ocfs2/inode.h @@ -123,8 +123,6 @@ static inline struct ocfs2_inode_info *OCFS2_I(struct inode *inode) #define INODE_JOURNAL(i) (OCFS2_I(i)->ip_flags & OCFS2_INODE_JOURNAL) #define SET_INODE_JOURNAL(i) (OCFS2_I(i)->ip_flags |= OCFS2_INODE_JOURNAL) -extern struct kmem_cache *ocfs2_inode_cache; - extern const struct address_space_operations ocfs2_aops; extern const struct ocfs2_caching_operations ocfs2_inode_caching_ops; diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 603b28d6f008..f56fe39fab04 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -2329,7 +2329,7 @@ static int ocfs2_initialize_super(struct super_block *sb, } cleancache_init_shared_fs(sb); - osb->ocfs2_wq = create_singlethread_workqueue("ocfs2_wq"); + osb->ocfs2_wq = alloc_ordered_workqueue("ocfs2_wq", WQ_MEM_RECLAIM); if (!osb->ocfs2_wq) { status = -ENOMEM; mlog_errno(status); diff --git a/fs/proc/array.c b/fs/proc/array.c index 88c7de12197b..89600fd5963d 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -186,51 +186,45 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns, task_unlock(p); rcu_read_unlock(); - seq_printf(m, - "State:\t%s\n" - "Tgid:\t%d\n" - "Ngid:\t%d\n" - "Pid:\t%d\n" - "PPid:\t%d\n" - "TracerPid:\t%d\n" - "Uid:\t%d\t%d\t%d\t%d\n" - "Gid:\t%d\t%d\t%d\t%d\n" - "FDSize:\t%d\nGroups:\t", - get_task_state(p), - tgid, ngid, pid_nr_ns(pid, ns), ppid, tpid, - from_kuid_munged(user_ns, cred->uid), - from_kuid_munged(user_ns, cred->euid), - from_kuid_munged(user_ns, cred->suid), - from_kuid_munged(user_ns, cred->fsuid), - from_kgid_munged(user_ns, cred->gid), - from_kgid_munged(user_ns, cred->egid), - from_kgid_munged(user_ns, cred->sgid), - from_kgid_munged(user_ns, cred->fsgid), - max_fds); + seq_printf(m, "State:\t%s", get_task_state(p)); + seq_put_decimal_ull(m, "\nTgid:\t", tgid); + seq_put_decimal_ull(m, "\nNgid:\t", ngid); + seq_put_decimal_ull(m, "\nPid:\t", pid_nr_ns(pid, ns)); + seq_put_decimal_ull(m, "\nPPid:\t", ppid); + seq_put_decimal_ull(m, "\nTracerPid:\t", tpid); + seq_put_decimal_ull(m, "\nUid:\t", from_kuid_munged(user_ns, cred->uid)); + seq_put_decimal_ull(m, "\t", from_kuid_munged(user_ns, cred->euid)); + seq_put_decimal_ull(m, "\t", from_kuid_munged(user_ns, cred->suid)); + seq_put_decimal_ull(m, "\t", from_kuid_munged(user_ns, cred->fsuid)); + seq_put_decimal_ull(m, "\nGid:\t", from_kgid_munged(user_ns, cred->gid)); + seq_put_decimal_ull(m, "\t", from_kgid_munged(user_ns, cred->egid)); + seq_put_decimal_ull(m, "\t", from_kgid_munged(user_ns, cred->sgid)); + seq_put_decimal_ull(m, "\t", from_kgid_munged(user_ns, cred->fsgid)); + seq_put_decimal_ull(m, "\nFDSize:\t", max_fds); + + seq_puts(m, "\nGroups:\t"); group_info = cred->group_info; for (g = 0; g < group_info->ngroups; g++) - seq_printf(m, "%d ", - from_kgid_munged(user_ns, GROUP_AT(group_info, g))); + seq_put_decimal_ull(m, g ? " " : "", + from_kgid_munged(user_ns, group_info->gid[g])); put_cred(cred); + /* Trailing space shouldn't have been added in the first place. */ + seq_putc(m, ' '); #ifdef CONFIG_PID_NS seq_puts(m, "\nNStgid:"); for (g = ns->level; g <= pid->level; g++) - seq_printf(m, "\t%d", - task_tgid_nr_ns(p, pid->numbers[g].ns)); + seq_put_decimal_ull(m, "\t", task_tgid_nr_ns(p, pid->numbers[g].ns)); seq_puts(m, "\nNSpid:"); for (g = ns->level; g <= pid->level; g++) - seq_printf(m, "\t%d", - task_pid_nr_ns(p, pid->numbers[g].ns)); + seq_put_decimal_ull(m, "\t", task_pid_nr_ns(p, pid->numbers[g].ns)); seq_puts(m, "\nNSpgid:"); for (g = ns->level; g <= pid->level; g++) - seq_printf(m, "\t%d", - task_pgrp_nr_ns(p, pid->numbers[g].ns)); + seq_put_decimal_ull(m, "\t", task_pgrp_nr_ns(p, pid->numbers[g].ns)); seq_puts(m, "\nNSsid:"); for (g = ns->level; g <= pid->level; g++) - seq_printf(m, "\t%d", - task_session_nr_ns(p, pid->numbers[g].ns)); + seq_put_decimal_ull(m, "\t", task_session_nr_ns(p, pid->numbers[g].ns)); #endif seq_putc(m, '\n'); } @@ -299,11 +293,12 @@ static inline void task_sig(struct seq_file *m, struct task_struct *p) unlock_task_sighand(p, &flags); } - seq_printf(m, "Threads:\t%d\n", num_threads); - seq_printf(m, "SigQ:\t%lu/%lu\n", qsize, qlim); + seq_put_decimal_ull(m, "Threads:\t", num_threads); + seq_put_decimal_ull(m, "\nSigQ:\t", qsize); + seq_put_decimal_ull(m, "/", qlim); /* render them all */ - render_sigset_t(m, "SigPnd:\t", &pending); + render_sigset_t(m, "\nSigPnd:\t", &pending); render_sigset_t(m, "ShdPnd:\t", &shpending); render_sigset_t(m, "SigBlk:\t", &blocked); render_sigset_t(m, "SigIgn:\t", &ignored); @@ -348,17 +343,17 @@ static inline void task_cap(struct seq_file *m, struct task_struct *p) static inline void task_seccomp(struct seq_file *m, struct task_struct *p) { #ifdef CONFIG_SECCOMP - seq_printf(m, "Seccomp:\t%d\n", p->seccomp.mode); + seq_put_decimal_ull(m, "Seccomp:\t", p->seccomp.mode); + seq_putc(m, '\n'); #endif } static inline void task_context_switch_counts(struct seq_file *m, struct task_struct *p) { - seq_printf(m, "voluntary_ctxt_switches:\t%lu\n" - "nonvoluntary_ctxt_switches:\t%lu\n", - p->nvcsw, - p->nivcsw); + seq_put_decimal_ull(m, "voluntary_ctxt_switches:\t", p->nvcsw); + seq_put_decimal_ull(m, "\nnonvoluntary_ctxt_switches:\t", p->nivcsw); + seq_putc(m, '\n'); } static void task_cpus_allowed(struct seq_file *m, struct task_struct *task) @@ -490,41 +485,41 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, start_time = nsec_to_clock_t(task->real_start_time); seq_printf(m, "%d (%s) %c", pid_nr_ns(pid, ns), tcomm, state); - seq_put_decimal_ll(m, ' ', ppid); - seq_put_decimal_ll(m, ' ', pgid); - seq_put_decimal_ll(m, ' ', sid); - seq_put_decimal_ll(m, ' ', tty_nr); - seq_put_decimal_ll(m, ' ', tty_pgrp); - seq_put_decimal_ull(m, ' ', task->flags); - seq_put_decimal_ull(m, ' ', min_flt); - seq_put_decimal_ull(m, ' ', cmin_flt); - seq_put_decimal_ull(m, ' ', maj_flt); - seq_put_decimal_ull(m, ' ', cmaj_flt); - seq_put_decimal_ull(m, ' ', cputime_to_clock_t(utime)); - seq_put_decimal_ull(m, ' ', cputime_to_clock_t(stime)); - seq_put_decimal_ll(m, ' ', cputime_to_clock_t(cutime)); - seq_put_decimal_ll(m, ' ', cputime_to_clock_t(cstime)); - seq_put_decimal_ll(m, ' ', priority); - seq_put_decimal_ll(m, ' ', nice); - seq_put_decimal_ll(m, ' ', num_threads); - seq_put_decimal_ull(m, ' ', 0); - seq_put_decimal_ull(m, ' ', start_time); - seq_put_decimal_ull(m, ' ', vsize); - seq_put_decimal_ull(m, ' ', mm ? get_mm_rss(mm) : 0); - seq_put_decimal_ull(m, ' ', rsslim); - seq_put_decimal_ull(m, ' ', mm ? (permitted ? mm->start_code : 1) : 0); - seq_put_decimal_ull(m, ' ', mm ? (permitted ? mm->end_code : 1) : 0); - seq_put_decimal_ull(m, ' ', (permitted && mm) ? mm->start_stack : 0); - seq_put_decimal_ull(m, ' ', esp); - seq_put_decimal_ull(m, ' ', eip); + seq_put_decimal_ll(m, " ", ppid); + seq_put_decimal_ll(m, " ", pgid); + seq_put_decimal_ll(m, " ", sid); + seq_put_decimal_ll(m, " ", tty_nr); + seq_put_decimal_ll(m, " ", tty_pgrp); + seq_put_decimal_ull(m, " ", task->flags); + seq_put_decimal_ull(m, " ", min_flt); + seq_put_decimal_ull(m, " ", cmin_flt); + seq_put_decimal_ull(m, " ", maj_flt); + seq_put_decimal_ull(m, " ", cmaj_flt); + seq_put_decimal_ull(m, " ", cputime_to_clock_t(utime)); + seq_put_decimal_ull(m, " ", cputime_to_clock_t(stime)); + seq_put_decimal_ll(m, " ", cputime_to_clock_t(cutime)); + seq_put_decimal_ll(m, " ", cputime_to_clock_t(cstime)); + seq_put_decimal_ll(m, " ", priority); + seq_put_decimal_ll(m, " ", nice); + seq_put_decimal_ll(m, " ", num_threads); + seq_put_decimal_ull(m, " ", 0); + seq_put_decimal_ull(m, " ", start_time); + seq_put_decimal_ull(m, " ", vsize); + seq_put_decimal_ull(m, " ", mm ? get_mm_rss(mm) : 0); + seq_put_decimal_ull(m, " ", rsslim); + seq_put_decimal_ull(m, " ", mm ? (permitted ? mm->start_code : 1) : 0); + seq_put_decimal_ull(m, " ", mm ? (permitted ? mm->end_code : 1) : 0); + seq_put_decimal_ull(m, " ", (permitted && mm) ? mm->start_stack : 0); + seq_put_decimal_ull(m, " ", esp); + seq_put_decimal_ull(m, " ", eip); /* The signal information here is obsolete. * It must be decimal for Linux 2.0 compatibility. * Use /proc/#/status for real-time signals. */ - seq_put_decimal_ull(m, ' ', task->pending.signal.sig[0] & 0x7fffffffUL); - seq_put_decimal_ull(m, ' ', task->blocked.sig[0] & 0x7fffffffUL); - seq_put_decimal_ull(m, ' ', sigign.sig[0] & 0x7fffffffUL); - seq_put_decimal_ull(m, ' ', sigcatch.sig[0] & 0x7fffffffUL); + seq_put_decimal_ull(m, " ", task->pending.signal.sig[0] & 0x7fffffffUL); + seq_put_decimal_ull(m, " ", task->blocked.sig[0] & 0x7fffffffUL); + seq_put_decimal_ull(m, " ", sigign.sig[0] & 0x7fffffffUL); + seq_put_decimal_ull(m, " ", sigcatch.sig[0] & 0x7fffffffUL); /* * We used to output the absolute kernel address, but that's an @@ -538,31 +533,31 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, else seq_puts(m, " 0"); - seq_put_decimal_ull(m, ' ', 0); - seq_put_decimal_ull(m, ' ', 0); - seq_put_decimal_ll(m, ' ', task->exit_signal); - seq_put_decimal_ll(m, ' ', task_cpu(task)); - seq_put_decimal_ull(m, ' ', task->rt_priority); - seq_put_decimal_ull(m, ' ', task->policy); - seq_put_decimal_ull(m, ' ', delayacct_blkio_ticks(task)); - seq_put_decimal_ull(m, ' ', cputime_to_clock_t(gtime)); - seq_put_decimal_ll(m, ' ', cputime_to_clock_t(cgtime)); + seq_put_decimal_ull(m, " ", 0); + seq_put_decimal_ull(m, " ", 0); + seq_put_decimal_ll(m, " ", task->exit_signal); + seq_put_decimal_ll(m, " ", task_cpu(task)); + seq_put_decimal_ull(m, " ", task->rt_priority); + seq_put_decimal_ull(m, " ", task->policy); + seq_put_decimal_ull(m, " ", delayacct_blkio_ticks(task)); + seq_put_decimal_ull(m, " ", cputime_to_clock_t(gtime)); + seq_put_decimal_ll(m, " ", cputime_to_clock_t(cgtime)); if (mm && permitted) { - seq_put_decimal_ull(m, ' ', mm->start_data); - seq_put_decimal_ull(m, ' ', mm->end_data); - seq_put_decimal_ull(m, ' ', mm->start_brk); - seq_put_decimal_ull(m, ' ', mm->arg_start); - seq_put_decimal_ull(m, ' ', mm->arg_end); - seq_put_decimal_ull(m, ' ', mm->env_start); - seq_put_decimal_ull(m, ' ', mm->env_end); + seq_put_decimal_ull(m, " ", mm->start_data); + seq_put_decimal_ull(m, " ", mm->end_data); + seq_put_decimal_ull(m, " ", mm->start_brk); + seq_put_decimal_ull(m, " ", mm->arg_start); + seq_put_decimal_ull(m, " ", mm->arg_end); + seq_put_decimal_ull(m, " ", mm->env_start); + seq_put_decimal_ull(m, " ", mm->env_end); } else - seq_printf(m, " 0 0 0 0 0 0 0"); + seq_puts(m, " 0 0 0 0 0 0 0"); if (permitted) - seq_put_decimal_ll(m, ' ', task->exit_code); + seq_put_decimal_ll(m, " ", task->exit_code); else - seq_put_decimal_ll(m, ' ', 0); + seq_puts(m, " 0"); seq_putc(m, '\n'); if (mm) @@ -598,13 +593,13 @@ int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns, * seq_printf(m, "%lu %lu %lu %lu 0 %lu 0\n", * size, resident, shared, text, data); */ - seq_put_decimal_ull(m, 0, size); - seq_put_decimal_ull(m, ' ', resident); - seq_put_decimal_ull(m, ' ', shared); - seq_put_decimal_ull(m, ' ', text); - seq_put_decimal_ull(m, ' ', 0); - seq_put_decimal_ull(m, ' ', data); - seq_put_decimal_ull(m, ' ', 0); + seq_put_decimal_ull(m, "", size); + seq_put_decimal_ull(m, " ", resident); + seq_put_decimal_ull(m, " ", shared); + seq_put_decimal_ull(m, " ", text); + seq_put_decimal_ull(m, " ", 0); + seq_put_decimal_ull(m, " ", data); + seq_put_decimal_ull(m, " ", 0); seq_putc(m, '\n'); return 0; diff --git a/fs/proc/base.c b/fs/proc/base.c index 3b792ab3c0dc..dc7fe5f3a53c 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2280,16 +2280,27 @@ static ssize_t timerslack_ns_write(struct file *file, const char __user *buf, if (!p) return -ESRCH; - if (ptrace_may_access(p, PTRACE_MODE_ATTACH_FSCREDS)) { - task_lock(p); - if (slack_ns == 0) - p->timer_slack_ns = p->default_timer_slack_ns; - else - p->timer_slack_ns = slack_ns; - task_unlock(p); - } else - count = -EPERM; + if (p != current) { + if (!capable(CAP_SYS_NICE)) { + count = -EPERM; + goto out; + } + err = security_task_setscheduler(p); + if (err) { + count = err; + goto out; + } + } + + task_lock(p); + if (slack_ns == 0) + p->timer_slack_ns = p->default_timer_slack_ns; + else + p->timer_slack_ns = slack_ns; + task_unlock(p); + +out: put_task_struct(p); return count; @@ -2299,19 +2310,28 @@ static int timerslack_ns_show(struct seq_file *m, void *v) { struct inode *inode = m->private; struct task_struct *p; - int err = 0; + int err = 0; p = get_proc_task(inode); if (!p) return -ESRCH; - if (ptrace_may_access(p, PTRACE_MODE_ATTACH_FSCREDS)) { - task_lock(p); - seq_printf(m, "%llu\n", p->timer_slack_ns); - task_unlock(p); - } else - err = -EPERM; + if (p != current) { + if (!capable(CAP_SYS_NICE)) { + err = -EPERM; + goto out; + } + err = security_task_getscheduler(p); + if (err) + goto out; + } + + task_lock(p); + seq_printf(m, "%llu\n", p->timer_slack_ns); + task_unlock(p); + +out: put_task_struct(p); return err; diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index b9a8c813e5e6..8a428498d6b2 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -23,6 +23,25 @@ void __attribute__((weak)) arch_report_meminfo(struct seq_file *m) { } +static void show_val_kb(struct seq_file *m, const char *s, unsigned long num) +{ + char v[32]; + static const char blanks[7] = {' ', ' ', ' ', ' ',' ', ' ', ' '}; + int len; + + len = num_to_str(v, sizeof(v), num << (PAGE_SHIFT - 10)); + + seq_write(m, s, 16); + + if (len > 0) { + if (len < 8) + seq_write(m, blanks, 8 - len); + + seq_write(m, v, len); + } + seq_write(m, " kB\n", 4); +} + static int meminfo_proc_show(struct seq_file *m, void *v) { struct sysinfo i; @@ -32,10 +51,6 @@ static int meminfo_proc_show(struct seq_file *m, void *v) unsigned long pages[NR_LRU_LISTS]; int lru; -/* - * display in kilobytes. - */ -#define K(x) ((x) << (PAGE_SHIFT - 10)) si_meminfo(&i); si_swapinfo(&i); committed = percpu_counter_read_positive(&vm_committed_as); @@ -50,136 +65,100 @@ static int meminfo_proc_show(struct seq_file *m, void *v) available = si_mem_available(); - /* - * Tagged format, for easy grepping and expansion. - */ - seq_printf(m, - "MemTotal: %8lu kB\n" - "MemFree: %8lu kB\n" - "MemAvailable: %8lu kB\n" - "Buffers: %8lu kB\n" - "Cached: %8lu kB\n" - "SwapCached: %8lu kB\n" - "Active: %8lu kB\n" - "Inactive: %8lu kB\n" - "Active(anon): %8lu kB\n" - "Inactive(anon): %8lu kB\n" - "Active(file): %8lu kB\n" - "Inactive(file): %8lu kB\n" - "Unevictable: %8lu kB\n" - "Mlocked: %8lu kB\n" + show_val_kb(m, "MemTotal: ", i.totalram); + show_val_kb(m, "MemFree: ", i.freeram); + show_val_kb(m, "MemAvailable: ", available); + show_val_kb(m, "Buffers: ", i.bufferram); + show_val_kb(m, "Cached: ", cached); + show_val_kb(m, "SwapCached: ", total_swapcache_pages()); + show_val_kb(m, "Active: ", pages[LRU_ACTIVE_ANON] + + pages[LRU_ACTIVE_FILE]); + show_val_kb(m, "Inactive: ", pages[LRU_INACTIVE_ANON] + + pages[LRU_INACTIVE_FILE]); + show_val_kb(m, "Active(anon): ", pages[LRU_ACTIVE_ANON]); + show_val_kb(m, "Inactive(anon): ", pages[LRU_INACTIVE_ANON]); + show_val_kb(m, "Active(file): ", pages[LRU_ACTIVE_FILE]); + show_val_kb(m, "Inactive(file): ", pages[LRU_INACTIVE_FILE]); + show_val_kb(m, "Unevictable: ", pages[LRU_UNEVICTABLE]); + show_val_kb(m, "Mlocked: ", global_page_state(NR_MLOCK)); + #ifdef CONFIG_HIGHMEM - "HighTotal: %8lu kB\n" - "HighFree: %8lu kB\n" - "LowTotal: %8lu kB\n" - "LowFree: %8lu kB\n" + show_val_kb(m, "HighTotal: ", i.totalhigh); + show_val_kb(m, "HighFree: ", i.freehigh); + show_val_kb(m, "LowTotal: ", i.totalram - i.totalhigh); + show_val_kb(m, "LowFree: ", i.freeram - i.freehigh); #endif + #ifndef CONFIG_MMU - "MmapCopy: %8lu kB\n" + show_val_kb(m, "MmapCopy: ", + (unsigned long)atomic_long_read(&mmap_pages_allocated)); #endif - "SwapTotal: %8lu kB\n" - "SwapFree: %8lu kB\n" - "Dirty: %8lu kB\n" - "Writeback: %8lu kB\n" - "AnonPages: %8lu kB\n" - "Mapped: %8lu kB\n" - "Shmem: %8lu kB\n" - "Slab: %8lu kB\n" - "SReclaimable: %8lu kB\n" - "SUnreclaim: %8lu kB\n" - "KernelStack: %8lu kB\n" - "PageTables: %8lu kB\n" + + show_val_kb(m, "SwapTotal: ", i.totalswap); + show_val_kb(m, "SwapFree: ", i.freeswap); + show_val_kb(m, "Dirty: ", + global_node_page_state(NR_FILE_DIRTY)); + show_val_kb(m, "Writeback: ", + global_node_page_state(NR_WRITEBACK)); + show_val_kb(m, "AnonPages: ", + global_node_page_state(NR_ANON_MAPPED)); + show_val_kb(m, "Mapped: ", + global_node_page_state(NR_FILE_MAPPED)); + show_val_kb(m, "Shmem: ", i.sharedram); + show_val_kb(m, "Slab: ", + global_page_state(NR_SLAB_RECLAIMABLE) + + global_page_state(NR_SLAB_UNRECLAIMABLE)); + + show_val_kb(m, "SReclaimable: ", + global_page_state(NR_SLAB_RECLAIMABLE)); + show_val_kb(m, "SUnreclaim: ", + global_page_state(NR_SLAB_UNRECLAIMABLE)); + seq_printf(m, "KernelStack: %8lu kB\n", + global_page_state(NR_KERNEL_STACK_KB)); + show_val_kb(m, "PageTables: ", + global_page_state(NR_PAGETABLE)); #ifdef CONFIG_QUICKLIST - "Quicklists: %8lu kB\n" + show_val_kb(m, "Quicklists: ", quicklist_total_size()); #endif - "NFS_Unstable: %8lu kB\n" - "Bounce: %8lu kB\n" - "WritebackTmp: %8lu kB\n" - "CommitLimit: %8lu kB\n" - "Committed_AS: %8lu kB\n" - "VmallocTotal: %8lu kB\n" - "VmallocUsed: %8lu kB\n" - "VmallocChunk: %8lu kB\n" + + show_val_kb(m, "NFS_Unstable: ", + global_node_page_state(NR_UNSTABLE_NFS)); + show_val_kb(m, "Bounce: ", + global_page_state(NR_BOUNCE)); + show_val_kb(m, "WritebackTmp: ", + global_node_page_state(NR_WRITEBACK_TEMP)); + show_val_kb(m, "CommitLimit: ", vm_commit_limit()); + show_val_kb(m, "Committed_AS: ", committed); + seq_printf(m, "VmallocTotal: %8lu kB\n", + (unsigned long)VMALLOC_TOTAL >> 10); + show_val_kb(m, "VmallocUsed: ", 0ul); + show_val_kb(m, "VmallocChunk: ", 0ul); + #ifdef CONFIG_MEMORY_FAILURE - "HardwareCorrupted: %5lu kB\n" + seq_printf(m, "HardwareCorrupted: %5lu kB\n", + atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10)); #endif + #ifdef CONFIG_TRANSPARENT_HUGEPAGE - "AnonHugePages: %8lu kB\n" - "ShmemHugePages: %8lu kB\n" - "ShmemPmdMapped: %8lu kB\n" + show_val_kb(m, "AnonHugePages: ", + global_node_page_state(NR_ANON_THPS) * HPAGE_PMD_NR); + show_val_kb(m, "ShmemHugePages: ", + global_node_page_state(NR_SHMEM_THPS) * HPAGE_PMD_NR); + show_val_kb(m, "ShmemPmdMapped: ", + global_node_page_state(NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR); #endif + #ifdef CONFIG_CMA - "CmaTotal: %8lu kB\n" - "CmaFree: %8lu kB\n" + show_val_kb(m, "CmaTotal: ", totalcma_pages); + show_val_kb(m, "CmaFree: ", + global_page_state(NR_FREE_CMA_PAGES)); #endif - , - K(i.totalram), - K(i.freeram), - K(available), - K(i.bufferram), - K(cached), - K(total_swapcache_pages()), - K(pages[LRU_ACTIVE_ANON] + pages[LRU_ACTIVE_FILE]), - K(pages[LRU_INACTIVE_ANON] + pages[LRU_INACTIVE_FILE]), - K(pages[LRU_ACTIVE_ANON]), - K(pages[LRU_INACTIVE_ANON]), - K(pages[LRU_ACTIVE_FILE]), - K(pages[LRU_INACTIVE_FILE]), - K(pages[LRU_UNEVICTABLE]), - K(global_page_state(NR_MLOCK)), -#ifdef CONFIG_HIGHMEM - K(i.totalhigh), - K(i.freehigh), - K(i.totalram-i.totalhigh), - K(i.freeram-i.freehigh), -#endif -#ifndef CONFIG_MMU - K((unsigned long) atomic_long_read(&mmap_pages_allocated)), -#endif - K(i.totalswap), - K(i.freeswap), - K(global_node_page_state(NR_FILE_DIRTY)), - K(global_node_page_state(NR_WRITEBACK)), - K(global_node_page_state(NR_ANON_MAPPED)), - K(global_node_page_state(NR_FILE_MAPPED)), - K(i.sharedram), - K(global_page_state(NR_SLAB_RECLAIMABLE) + - global_page_state(NR_SLAB_UNRECLAIMABLE)), - K(global_page_state(NR_SLAB_RECLAIMABLE)), - K(global_page_state(NR_SLAB_UNRECLAIMABLE)), - global_page_state(NR_KERNEL_STACK_KB), - K(global_page_state(NR_PAGETABLE)), -#ifdef CONFIG_QUICKLIST - K(quicklist_total_size()), -#endif - K(global_node_page_state(NR_UNSTABLE_NFS)), - K(global_page_state(NR_BOUNCE)), - K(global_node_page_state(NR_WRITEBACK_TEMP)), - K(vm_commit_limit()), - K(committed), - (unsigned long)VMALLOC_TOTAL >> 10, - 0ul, // used to be vmalloc 'used' - 0ul // used to be vmalloc 'largest_chunk' -#ifdef CONFIG_MEMORY_FAILURE - , atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10) -#endif -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - , K(global_node_page_state(NR_ANON_THPS) * HPAGE_PMD_NR) - , K(global_node_page_state(NR_SHMEM_THPS) * HPAGE_PMD_NR) - , K(global_node_page_state(NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR) -#endif -#ifdef CONFIG_CMA - , K(totalcma_pages) - , K(global_page_state(NR_FREE_CMA_PAGES)) -#endif - ); hugetlb_report_meminfo(m); arch_report_meminfo(m); return 0; -#undef K } static int meminfo_proc_open(struct inode *inode, struct file *file) diff --git a/fs/proc/stat.c b/fs/proc/stat.c index 7907e456ac4f..d700c42b3572 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -115,17 +115,16 @@ static int show_stat(struct seq_file *p, void *v) } sum += arch_irq_stat(); - seq_puts(p, "cpu "); - seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(user)); - seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(nice)); - seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(system)); - seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(idle)); - seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(iowait)); - seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(irq)); - seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(softirq)); - seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(steal)); - seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest)); - seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest_nice)); + seq_put_decimal_ull(p, "cpu ", cputime64_to_clock_t(user)); + seq_put_decimal_ull(p, " ", cputime64_to_clock_t(nice)); + seq_put_decimal_ull(p, " ", cputime64_to_clock_t(system)); + seq_put_decimal_ull(p, " ", cputime64_to_clock_t(idle)); + seq_put_decimal_ull(p, " ", cputime64_to_clock_t(iowait)); + seq_put_decimal_ull(p, " ", cputime64_to_clock_t(irq)); + seq_put_decimal_ull(p, " ", cputime64_to_clock_t(softirq)); + seq_put_decimal_ull(p, " ", cputime64_to_clock_t(steal)); + seq_put_decimal_ull(p, " ", cputime64_to_clock_t(guest)); + seq_put_decimal_ull(p, " ", cputime64_to_clock_t(guest_nice)); seq_putc(p, '\n'); for_each_online_cpu(i) { @@ -141,23 +140,23 @@ static int show_stat(struct seq_file *p, void *v) guest = kcpustat_cpu(i).cpustat[CPUTIME_GUEST]; guest_nice = kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE]; seq_printf(p, "cpu%d", i); - seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(user)); - seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(nice)); - seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(system)); - seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(idle)); - seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(iowait)); - seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(irq)); - seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(softirq)); - seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(steal)); - seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest)); - seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest_nice)); + seq_put_decimal_ull(p, " ", cputime64_to_clock_t(user)); + seq_put_decimal_ull(p, " ", cputime64_to_clock_t(nice)); + seq_put_decimal_ull(p, " ", cputime64_to_clock_t(system)); + seq_put_decimal_ull(p, " ", cputime64_to_clock_t(idle)); + seq_put_decimal_ull(p, " ", cputime64_to_clock_t(iowait)); + seq_put_decimal_ull(p, " ", cputime64_to_clock_t(irq)); + seq_put_decimal_ull(p, " ", cputime64_to_clock_t(softirq)); + seq_put_decimal_ull(p, " ", cputime64_to_clock_t(steal)); + seq_put_decimal_ull(p, " ", cputime64_to_clock_t(guest)); + seq_put_decimal_ull(p, " ", cputime64_to_clock_t(guest_nice)); seq_putc(p, '\n'); } - seq_printf(p, "intr %llu", (unsigned long long)sum); + seq_put_decimal_ull(p, "intr ", (unsigned long long)sum); /* sum again ? it could be updated? */ for_each_irq_nr(j) - seq_put_decimal_ull(p, ' ', kstat_irqs_usr(j)); + seq_put_decimal_ull(p, " ", kstat_irqs_usr(j)); seq_printf(p, "\nctxt %llu\n" @@ -171,10 +170,10 @@ static int show_stat(struct seq_file *p, void *v) nr_running(), nr_iowait()); - seq_printf(p, "softirq %llu", (unsigned long long)sum_softirq); + seq_put_decimal_ull(p, "softirq ", (unsigned long long)sum_softirq); for (i = 0; i < NR_SOFTIRQS; i++) - seq_put_decimal_ull(p, ' ', per_softirq_sums[i]); + seq_put_decimal_ull(p, " ", per_softirq_sums[i]); seq_putc(p, '\n'); return 0; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index f6fa99eca515..6909582ce5e5 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -147,7 +147,7 @@ m_next_vma(struct proc_maps_private *priv, struct vm_area_struct *vma) static void m_cache_vma(struct seq_file *m, struct vm_area_struct *vma) { if (m->count < m->size) /* vma is copied successfully */ - m->version = m_next_vma(m->private, vma) ? vma->vm_start : -1UL; + m->version = m_next_vma(m->private, vma) ? vma->vm_end : -1UL; } static void *m_start(struct seq_file *m, loff_t *ppos) @@ -175,8 +175,10 @@ static void *m_start(struct seq_file *m, loff_t *ppos) priv->tail_vma = get_gate_vma(mm); if (last_addr) { - vma = find_vma(mm, last_addr); - if (vma && (vma = m_next_vma(priv, vma))) + vma = find_vma(mm, last_addr - 1); + if (vma && vma->vm_start <= last_addr) + vma = m_next_vma(priv, vma); + if (vma) return vma; } @@ -1070,7 +1072,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, } mmu_notifier_invalidate_range_start(mm, 0, -1); } - walk_page_range(0, ~0UL, &clear_refs_walk); + walk_page_range(0, mm->highest_vm_end, &clear_refs_walk); if (type == CLEAR_REFS_SOFT_DIRTY) mmu_notifier_invalidate_range_end(mm, 0, -1); flush_tlb_mm(mm); diff --git a/fs/seq_file.c b/fs/seq_file.c index 6dc4296eed62..368bfb92b115 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -679,11 +679,11 @@ EXPORT_SYMBOL(seq_puts); /* * A helper routine for putting decimal numbers without rich format of printf(). * only 'unsigned long long' is supported. - * This routine will put one byte delimiter + number into seq_file. + * This routine will put strlen(delimiter) + number into seq_file. * This routine is very quick when you show lots of numbers. * In usual cases, it will be better to use seq_printf(). It's easier to read. */ -void seq_put_decimal_ull(struct seq_file *m, char delimiter, +void seq_put_decimal_ull(struct seq_file *m, const char *delimiter, unsigned long long num) { int len; @@ -691,8 +691,15 @@ void seq_put_decimal_ull(struct seq_file *m, char delimiter, if (m->count + 2 >= m->size) /* we'll write 2 bytes at least */ goto overflow; - if (delimiter) - m->buf[m->count++] = delimiter; + len = strlen(delimiter); + if (m->count + len >= m->size) + goto overflow; + + memcpy(m->buf + m->count, delimiter, len); + m->count += len; + + if (m->count + 1 >= m->size) + goto overflow; if (num < 10) { m->buf[m->count++] = num + '0'; @@ -702,6 +709,7 @@ void seq_put_decimal_ull(struct seq_file *m, char delimiter, len = num_to_str(m->buf + m->count, m->size - m->count, num); if (!len) goto overflow; + m->count += len; return; @@ -710,19 +718,42 @@ overflow: } EXPORT_SYMBOL(seq_put_decimal_ull); -void seq_put_decimal_ll(struct seq_file *m, char delimiter, long long num) +void seq_put_decimal_ll(struct seq_file *m, const char *delimiter, long long num) { + int len; + + if (m->count + 3 >= m->size) /* we'll write 2 bytes at least */ + goto overflow; + + len = strlen(delimiter); + if (m->count + len >= m->size) + goto overflow; + + memcpy(m->buf + m->count, delimiter, len); + m->count += len; + + if (m->count + 2 >= m->size) + goto overflow; + if (num < 0) { - if (m->count + 3 >= m->size) { - seq_set_overflow(m); - return; - } - if (delimiter) - m->buf[m->count++] = delimiter; + m->buf[m->count++] = '-'; num = -num; - delimiter = '-'; } - seq_put_decimal_ull(m, delimiter, num); + + if (num < 10) { + m->buf[m->count++] = num + '0'; + return; + } + + len = num_to_str(m->buf + m->count, m->size - m->count, num); + if (!len) + goto overflow; + + m->count += len; + return; + +overflow: + seq_set_overflow(m); } EXPORT_SYMBOL(seq_put_decimal_ll); diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index f46b2929c64d..26acfbb331ae 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1579,6 +1579,7 @@ const struct file_operations xfs_file_operations = { .open = xfs_file_open, .release = xfs_file_release, .fsync = xfs_file_fsync, + .get_unmapped_area = thp_get_unmapped_area, .fallocate = xfs_file_fallocate, }; diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index d4458b6dbfb4..c4f8fd2fd384 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -800,6 +800,9 @@ static inline int pmd_clear_huge(pmd_t *pmd) #endif #endif +struct file; +int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t *vma_prot); #endif /* !__ASSEMBLY__ */ #ifndef io_remap_pfn_range diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 24563970ff7b..3e42bcdd014b 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -454,6 +454,12 @@ *(.spinlock.text) \ VMLINUX_SYMBOL(__lock_text_end) = .; +#define CPUIDLE_TEXT \ + ALIGN_FUNCTION(); \ + VMLINUX_SYMBOL(__cpuidle_text_start) = .; \ + *(.cpuidle.text) \ + VMLINUX_SYMBOL(__cpuidle_text_end) = .; + #define KPROBES_TEXT \ ALIGN_FUNCTION(); \ VMLINUX_SYMBOL(__kprobes_text_start) = .; \ diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 299e76b59fe9..a83c822c35c2 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -65,16 +65,6 @@ static inline int get_bitmask_order(unsigned int count) return order; /* We could be slightly more clever with -1 here... */ } -static inline int get_count_order(unsigned int count) -{ - int order; - - order = fls(count) - 1; - if (count & (count - 1)) - order++; - return order; -} - static __always_inline unsigned long hweight_long(unsigned long w) { return sizeof(w) == 4 ? hweight32(w) : hweight64(w); @@ -191,6 +181,32 @@ static inline unsigned fls_long(unsigned long l) return fls64(l); } +static inline int get_count_order(unsigned int count) +{ + int order; + + order = fls(count) - 1; + if (count & (count - 1)) + order++; + return order; +} + +/** + * get_count_order_long - get order after rounding @l up to power of 2 + * @l: parameter + * + * it is same as get_count_order() but with long type parameter + */ +static inline int get_count_order_long(unsigned long l) +{ + if (l == 0UL) + return -1; + else if (l & (l - 1UL)) + return (int)fls_long(l); + else + return (int)fls_long(l) - 1; +} + /** * __ffs64 - find first set bit in a 64 bit word * @word: The 64 bit word diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index f9be32691718..962164d36506 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -7,6 +7,7 @@ #include #include #include +#include /* * simple boot-time physical memory area allocator. @@ -119,6 +120,10 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, #define BOOTMEM_LOW_LIMIT __pa(MAX_DMA_ADDRESS) #endif +#ifndef ARCH_LOW_ADDRESS_LIMIT +#define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL +#endif + #define alloc_bootmem(x) \ __alloc_bootmem(x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT) #define alloc_bootmem_align(x, align) \ @@ -180,10 +185,6 @@ static inline void * __init memblock_virt_alloc_nopanic( NUMA_NO_NODE); } -#ifndef ARCH_LOW_ADDRESS_LIMIT -#define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL -#endif - static inline void * __init memblock_virt_alloc_low( phys_addr_t size, phys_addr_t align) { diff --git a/include/linux/compaction.h b/include/linux/compaction.h index d4e106b5dc27..0d8415820fc3 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -6,8 +6,10 @@ * Lower value means higher priority, analogically to reclaim priority. */ enum compact_priority { + COMPACT_PRIO_SYNC_FULL, + MIN_COMPACT_PRIORITY = COMPACT_PRIO_SYNC_FULL, COMPACT_PRIO_SYNC_LIGHT, - MIN_COMPACT_PRIORITY = COMPACT_PRIO_SYNC_LIGHT, + MIN_COMPACT_COSTLY_PRIORITY = COMPACT_PRIO_SYNC_LIGHT, DEF_COMPACT_PRIORITY = COMPACT_PRIO_SYNC_LIGHT, COMPACT_PRIO_ASYNC, INIT_COMPACT_PRIORITY = COMPACT_PRIO_ASYNC @@ -49,14 +51,37 @@ enum compact_result { COMPACT_CONTENDED, /* - * direct compaction partially compacted a zone and there might be - * suitable pages + * direct compaction terminated after concluding that the allocation + * should now succeed */ - COMPACT_PARTIAL, + COMPACT_SUCCESS, }; struct alloc_context; /* in mm/internal.h */ +/* + * Number of free order-0 pages that should be available above given watermark + * to make sure compaction has reasonable chance of not running out of free + * pages that it needs to isolate as migration target during its work. + */ +static inline unsigned long compact_gap(unsigned int order) +{ + /* + * Although all the isolations for migration are temporary, compaction + * free scanner may have up to 1 << order pages on its list and then + * try to split an (order - 1) free page. At that point, a gap of + * 1 << order might not be enough, so it's safer to require twice that + * amount. Note that the number of pages on the list is also + * effectively limited by COMPACT_CLUSTER_MAX, as that's the maximum + * that the migrate scanner can have isolated on migrate list, and free + * scanner is only invoked when the number of isolated free pages is + * lower than that. But it's not worth to complicate the formula here + * as a bigger gap for higher orders than strictly necessary can also + * improve chances of compaction success. + */ + return 2UL << order; +} + #ifdef CONFIG_COMPACTION extern int sysctl_compact_memory; extern int sysctl_compaction_handler(struct ctl_table *table, int write, @@ -70,7 +95,6 @@ extern int fragmentation_index(struct zone *zone, unsigned int order); extern enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, unsigned int alloc_flags, const struct alloc_context *ac, enum compact_priority prio); -extern void compact_pgdat(pg_data_t *pgdat, int order); extern void reset_isolation_suitable(pg_data_t *pgdat); extern enum compact_result compaction_suitable(struct zone *zone, int order, unsigned int alloc_flags, int classzone_idx); @@ -89,7 +113,7 @@ static inline bool compaction_made_progress(enum compact_result result) * that the compaction successfully isolated and migrated some * pageblocks. */ - if (result == COMPACT_PARTIAL) + if (result == COMPACT_SUCCESS) return true; return false; @@ -154,10 +178,6 @@ extern void kcompactd_stop(int nid); extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx); #else -static inline void compact_pgdat(pg_data_t *pgdat, int order) -{ -} - static inline void reset_isolation_suitable(pg_data_t *pgdat) { } diff --git a/include/linux/console.h b/include/linux/console.h index d530c4627e54..3672809234a7 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -173,6 +173,12 @@ static inline void console_sysfs_notify(void) #endif extern bool console_suspend_enabled; +#ifdef CONFIG_OF +extern void console_set_by_of(void); +#else +static inline void console_set_by_of(void) {} +#endif + /* Suspend and resume console messages over PM events */ extern void suspend_console(void); extern void resume_console(void); diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 7572d9e9dced..b886dc17f2f3 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -231,6 +231,11 @@ void cpu_startup_entry(enum cpuhp_state state); void cpu_idle_poll_ctrl(bool enable); +/* Attach to any functions which should be considered cpuidle. */ +#define __cpuidle __attribute__((__section__(".cpuidle.text"))) + +bool cpu_in_idle(unsigned long pc); + void arch_cpu_idle(void); void arch_cpu_idle_prepare(void); void arch_cpu_idle_enter(void); diff --git a/include/linux/cred.h b/include/linux/cred.h index 257db64562e5..f0e70a1bb3ac 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -26,15 +26,10 @@ struct inode; /* * COW Supplementary groups list */ -#define NGROUPS_SMALL 32 -#define NGROUPS_PER_BLOCK ((unsigned int)(PAGE_SIZE / sizeof(kgid_t))) - struct group_info { atomic_t usage; int ngroups; - int nblocks; - kgid_t small_block[NGROUPS_SMALL]; - kgid_t *blocks[0]; + kgid_t gid[0]; }; /** @@ -88,10 +83,6 @@ extern void set_groups(struct cred *, struct group_info *); extern int groups_search(const struct group_info *, kgid_t); extern bool may_setgroups(void); -/* access the groups "array" with this macro */ -#define GROUP_AT(gi, i) \ - ((gi)->blocks[(i) / NGROUPS_PER_BLOCK][(i) % NGROUPS_PER_BLOCK]) - /* * The security context of a task * diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 7268ed076be8..79467b239fcf 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -135,7 +135,7 @@ struct fsnotify_group { const struct fsnotify_ops *ops; /* how this group handles things */ /* needed to send notification to userspace */ - struct mutex notification_mutex; /* protect the notification_list */ + spinlock_t notification_lock; /* protect the notification_list */ struct list_head notification_list; /* list of event_holder this group needs to send to userspace */ wait_queue_head_t notification_waitq; /* read() on the notification file blocks on this waitq */ unsigned int q_len; /* events on the queue */ @@ -177,7 +177,6 @@ struct fsnotify_group { struct fanotify_group_private_data { #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS /* allows a group to block waiting for a userspace response */ - spinlock_t access_lock; struct list_head access_list; wait_queue_head_t access_waitq; #endif /* CONFIG_FANOTIFY_ACCESS_PERMISSIONS */ diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 6f14de45b5ce..9b9f65d99873 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -87,6 +87,10 @@ extern bool is_vma_temporary_stack(struct vm_area_struct *vma); extern unsigned long transparent_hugepage_flags; +extern unsigned long thp_get_unmapped_area(struct file *filp, + unsigned long addr, unsigned long len, unsigned long pgoff, + unsigned long flags); + extern void prep_transhuge_page(struct page *page); extern void free_transhuge_page(struct page *page); @@ -152,8 +156,8 @@ static inline bool is_huge_zero_pmd(pmd_t pmd) return is_huge_zero_page(pmd_page(pmd)); } -struct page *get_huge_zero_page(void); -void put_huge_zero_page(void); +struct page *mm_get_huge_zero_page(struct mm_struct *mm); +void mm_put_huge_zero_page(struct mm_struct *mm); #define mk_huge_pmd(page, prot) pmd_mkhuge(mk_pmd(page, prot)) @@ -169,6 +173,9 @@ void put_huge_zero_page(void); static inline void prep_transhuge_page(struct page *page) {} #define transparent_hugepage_flags 0UL + +#define thp_get_unmapped_area NULL + static inline int split_huge_page_to_list(struct page *page, struct list_head *list) { @@ -213,9 +220,9 @@ static inline bool is_huge_zero_page(struct page *page) return false; } -static inline void put_huge_zero_page(void) +static inline void mm_put_huge_zero_page(struct mm_struct *mm) { - BUILD_BUG(); + return; } static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma, diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index c26d4638f665..48c76d612d40 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -90,7 +90,7 @@ int dequeue_hwpoisoned_huge_page(struct page *page); bool isolate_huge_page(struct page *page, struct list_head *list); void putback_active_hugepage(struct page *page); void free_huge_page(struct page *page); -void hugetlb_fix_reserve_counts(struct inode *inode, bool restore_reserve); +void hugetlb_fix_reserve_counts(struct inode *inode); extern struct mutex *hugetlb_fault_mutex_table; u32 hugetlb_fault_mutex_hash(struct hstate *h, struct mm_struct *mm, struct vm_area_struct *vma, @@ -450,8 +450,8 @@ static inline pgoff_t basepage_index(struct page *page) return __basepage_index(page); } -extern void dissolve_free_huge_pages(unsigned long start_pfn, - unsigned long end_pfn); +extern int dissolve_free_huge_pages(unsigned long start_pfn, + unsigned long end_pfn); static inline bool hugepage_migration_supported(struct hstate *h) { #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION @@ -518,7 +518,7 @@ static inline pgoff_t basepage_index(struct page *page) { return page->index; } -#define dissolve_free_huge_pages(s, e) do {} while (0) +#define dissolve_free_huge_pages(s, e) 0 #define hugepage_migration_supported(h) false static inline spinlock_t *huge_pte_lockptr(struct hstate *h, diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 5fdc55312334..589d14e970ad 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -150,15 +150,19 @@ static inline u64 get_jiffies_64(void) /* time_is_before_jiffies(a) return true if a is before jiffies */ #define time_is_before_jiffies(a) time_after(jiffies, a) +#define time_is_before_jiffies64(a) time_after64(get_jiffies_64(), a) /* time_is_after_jiffies(a) return true if a is after jiffies */ #define time_is_after_jiffies(a) time_before(jiffies, a) +#define time_is_after_jiffies64(a) time_before64(get_jiffies_64(), a) /* time_is_before_eq_jiffies(a) return true if a is before or equal to jiffies*/ #define time_is_before_eq_jiffies(a) time_after_eq(jiffies, a) +#define time_is_before_eq_jiffies64(a) time_after_eq64(get_jiffies_64(), a) /* time_is_after_eq_jiffies(a) return true if a is after or equal to jiffies*/ #define time_is_after_eq_jiffies(a) time_before_eq(jiffies, a) +#define time_is_after_eq_jiffies64(a) time_before_eq64(get_jiffies_64(), a) /* * Have the 32 bit jiffies value wrap 5 minutes after boot diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 74fd6f05bc5b..bc6ed52a39b9 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -733,17 +733,25 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } * strict type-checking.. See the * "unnecessary" pointer comparison. */ -#define min(x, y) ({ \ - typeof(x) _min1 = (x); \ - typeof(y) _min2 = (y); \ - (void) (&_min1 == &_min2); \ - _min1 < _min2 ? _min1 : _min2; }) +#define __min(t1, t2, min1, min2, x, y) ({ \ + t1 min1 = (x); \ + t2 min2 = (y); \ + (void) (&min1 == &min2); \ + min1 < min2 ? min1 : min2; }) +#define min(x, y) \ + __min(typeof(x), typeof(y), \ + __UNIQUE_ID(min1_), __UNIQUE_ID(min2_), \ + x, y) -#define max(x, y) ({ \ - typeof(x) _max1 = (x); \ - typeof(y) _max2 = (y); \ - (void) (&_max1 == &_max2); \ - _max1 > _max2 ? _max1 : _max2; }) +#define __max(t1, t2, max1, max2, x, y) ({ \ + t1 max1 = (x); \ + t2 max2 = (y); \ + (void) (&max1 == &max2); \ + max1 > max2 ? max1 : max2; }) +#define max(x, y) \ + __max(typeof(x), typeof(y), \ + __UNIQUE_ID(max1_), __UNIQUE_ID(max2_), \ + x, y) #define min3(x, y, z) min((typeof(x))min(x, y), z) #define max3(x, y, z) max((typeof(x))max(x, y), z) @@ -775,15 +783,15 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } * * Or not use min/max/clamp at all, of course. */ -#define min_t(type, x, y) ({ \ - type __min1 = (x); \ - type __min2 = (y); \ - __min1 < __min2 ? __min1: __min2; }) +#define min_t(type, x, y) \ + __min(type, type, \ + __UNIQUE_ID(min1_), __UNIQUE_ID(min2_), \ + x, y) -#define max_t(type, x, y) ({ \ - type __max1 = (x); \ - type __max2 = (y); \ - __max1 > __max2 ? __max1: __max2; }) +#define max_t(type, x, y) \ + __max(type, type, \ + __UNIQUE_ID(min1_), __UNIQUE_ID(min2_), \ + x, y) /** * clamp_t - return a value clamped to a given range using a given type diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 2925da23505d..5b759c9acf97 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -328,6 +328,7 @@ phys_addr_t memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t __memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr); phys_addr_t memblock_phys_mem_size(void); +phys_addr_t memblock_reserved_size(void); phys_addr_t memblock_mem_size(unsigned long limit_pfn); phys_addr_t memblock_start_of_DRAM(void); phys_addr_t memblock_end_of_DRAM(void); diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 5d8ca6e02e39..61d20c17f3b7 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -366,6 +366,8 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, struct mem_cgroup *, struct mem_cgroup_reclaim_cookie *); void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); +int mem_cgroup_scan_tasks(struct mem_cgroup *, + int (*)(struct task_struct *, void *), void *); static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) { @@ -446,6 +448,8 @@ unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) void mem_cgroup_handle_over_high(void); +unsigned long mem_cgroup_get_limit(struct mem_cgroup *memcg); + void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p); @@ -639,6 +643,12 @@ static inline void mem_cgroup_iter_break(struct mem_cgroup *root, { } +static inline int mem_cgroup_scan_tasks(struct mem_cgroup *memcg, + int (*fn)(struct task_struct *, void *), void *arg) +{ + return 0; +} + static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) { return 0; @@ -669,6 +679,11 @@ mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, return 0; } +static inline unsigned long mem_cgroup_get_limit(struct mem_cgroup *memcg) +{ + return 0; +} + static inline void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) { @@ -758,13 +773,13 @@ static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb, #endif /* CONFIG_CGROUP_WRITEBACK */ struct sock; -void sock_update_memcg(struct sock *sk); -void sock_release_memcg(struct sock *sk); bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); #ifdef CONFIG_MEMCG extern struct static_key_false memcg_sockets_enabled_key; #define mem_cgroup_sockets_enabled static_branch_unlikely(&memcg_sockets_enabled_key) +void mem_cgroup_sk_alloc(struct sock *sk); +void mem_cgroup_sk_free(struct sock *sk); static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_pressure) @@ -777,6 +792,8 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) } #else #define mem_cgroup_sockets_enabled 0 +static inline void mem_cgroup_sk_alloc(struct sock *sk) { }; +static inline void mem_cgroup_sk_free(struct sock *sk) { }; static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { return false; diff --git a/include/linux/mm.h b/include/linux/mm.h index 5f14534f0c90..e9caec6a51e9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -126,7 +126,7 @@ extern int overcommit_kbytes_handler(struct ctl_table *, int, void __user *, #define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE) /* test whether an address (unsigned long or pointer) is aligned to PAGE_SIZE */ -#define PAGE_ALIGNED(addr) IS_ALIGNED((unsigned long)addr, PAGE_SIZE) +#define PAGE_ALIGNED(addr) IS_ALIGNED((unsigned long)(addr), PAGE_SIZE) /* * Linux kernel virtual memory manager primitives. @@ -1048,28 +1048,16 @@ struct address_space *page_file_mapping(struct page *page) return page->mapping; } +extern pgoff_t __page_file_index(struct page *page); + /* * Return the pagecache index of the passed page. Regular pagecache pages - * use ->index whereas swapcache pages use ->private + * use ->index whereas swapcache pages use swp_offset(->private) */ static inline pgoff_t page_index(struct page *page) -{ - if (unlikely(PageSwapCache(page))) - return page_private(page); - return page->index; -} - -extern pgoff_t __page_file_index(struct page *page); - -/* - * Return the file index of the page. Regular pagecache pages use ->index - * whereas swapcache pages use swp_offset(->private) - */ -static inline pgoff_t page_file_index(struct page *page) { if (unlikely(PageSwapCache(page))) return __page_file_index(page); - return page->index; } @@ -1197,10 +1185,10 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, * @pte_hole: if set, called for each hole at all levels * @hugetlb_entry: if set, called for each hugetlb entry * @test_walk: caller specific callback function to determine whether - * we walk over the current vma or not. A positive returned + * we walk over the current vma or not. Returning 0 * value means "do page table walk over the current vma," * and a negative one means "abort current page table walk - * right now." 0 means "skip the current vma." + * right now." 1 means "skip the current vma." * @mm: mm_struct representing the target process of page table walk * @vma: vma currently walked (NULL if walking outside vmas) * @private: private data for callbacks' usage @@ -1529,7 +1517,7 @@ static inline int pte_devmap(pte_t pte) } #endif -int vma_wants_writenotify(struct vm_area_struct *vma); +int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot); extern pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl); @@ -1924,10 +1912,12 @@ extern void show_mem(unsigned int flags); extern long si_mem_available(void); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); +#ifdef __HAVE_ARCH_RESERVED_KERNEL_PAGES +extern unsigned long arch_reserved_kernel_pages(void); +#endif -extern __printf(3, 4) -void warn_alloc_failed(gfp_t gfp_mask, unsigned int order, - const char *fmt, ...); +extern __printf(2, 3) +void warn_alloc(gfp_t gfp_mask, const char *fmt, ...); extern void setup_per_cpu_pageset(void); @@ -1977,8 +1967,14 @@ void anon_vma_interval_tree_verify(struct anon_vma_chain *node); /* mmap.c */ extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin); -extern int vma_adjust(struct vm_area_struct *vma, unsigned long start, - unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert); +extern int __vma_adjust(struct vm_area_struct *vma, unsigned long start, + unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert, + struct vm_area_struct *expand); +static inline int vma_adjust(struct vm_area_struct *vma, unsigned long start, + unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert) +{ + return __vma_adjust(vma, start, end, pgoff, insert, NULL); +} extern struct vm_area_struct *vma_merge(struct mm_struct *, struct vm_area_struct *prev, unsigned long addr, unsigned long end, unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 903200f4ec41..4a8acedf4b7d 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -515,9 +515,7 @@ struct mm_struct { #ifdef CONFIG_HUGETLB_PAGE atomic_long_t hugetlb_usage; #endif -#ifdef CONFIG_MMU struct work_struct async_put_work; -#endif }; static inline void mm_init_cpumask(struct mm_struct *mm) diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 4630eeae18e0..a78c35cff1ae 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -35,21 +35,34 @@ static inline void hardlockup_detector_disable(void) {} * base function. Return whether such support was available, * to allow calling code to fall back to some other mechanism: */ -#ifdef arch_trigger_all_cpu_backtrace +#ifdef arch_trigger_cpumask_backtrace static inline bool trigger_all_cpu_backtrace(void) { - arch_trigger_all_cpu_backtrace(true); - + arch_trigger_cpumask_backtrace(cpu_online_mask, false); return true; } + static inline bool trigger_allbutself_cpu_backtrace(void) { - arch_trigger_all_cpu_backtrace(false); + arch_trigger_cpumask_backtrace(cpu_online_mask, true); + return true; +} + +static inline bool trigger_cpumask_backtrace(struct cpumask *mask) +{ + arch_trigger_cpumask_backtrace(mask, false); + return true; +} + +static inline bool trigger_single_cpu_backtrace(int cpu) +{ + arch_trigger_cpumask_backtrace(cpumask_of(cpu), false); return true; } /* generic implementation */ -void nmi_trigger_all_cpu_backtrace(bool include_self, +void nmi_trigger_cpumask_backtrace(const cpumask_t *mask, + bool exclude_self, void (*raise)(cpumask_t *mask)); bool nmi_cpu_backtrace(struct pt_regs *regs); @@ -62,6 +75,14 @@ static inline bool trigger_allbutself_cpu_backtrace(void) { return false; } +static inline bool trigger_cpumask_backtrace(struct cpumask *mask) +{ + return false; +} +static inline bool trigger_single_cpu_backtrace(int cpu) +{ + return false; +} #endif #ifdef CONFIG_LOCKUP_DETECTOR diff --git a/include/linux/oom.h b/include/linux/oom.h index 5bc0457ee3a8..b4e36e92bc87 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -34,23 +34,11 @@ struct oom_control { * for display purposes. */ const int order; -}; -/* - * Types of limitations to the nodes from which allocations may occur - */ -enum oom_constraint { - CONSTRAINT_NONE, - CONSTRAINT_CPUSET, - CONSTRAINT_MEMORY_POLICY, - CONSTRAINT_MEMCG, -}; - -enum oom_scan_t { - OOM_SCAN_OK, /* scan thread and find its badness */ - OOM_SCAN_CONTINUE, /* do not consider thread for oom kill */ - OOM_SCAN_ABORT, /* abort the iteration and return */ - OOM_SCAN_SELECT, /* always select this thread first */ + /* Used by oom implementation, do not set */ + unsigned long totalpages; + struct task_struct *chosen; + unsigned long chosen_points; }; extern struct mutex oom_lock; @@ -70,45 +58,27 @@ static inline bool oom_task_origin(const struct task_struct *p) return p->signal->oom_flag_origin; } -extern void mark_oom_victim(struct task_struct *tsk); - -#ifdef CONFIG_MMU -extern void wake_oom_reaper(struct task_struct *tsk); -#else -static inline void wake_oom_reaper(struct task_struct *tsk) +static inline bool tsk_is_oom_victim(struct task_struct * tsk) { + return tsk->signal->oom_mm; } -#endif extern unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, const nodemask_t *nodemask, unsigned long totalpages); -extern void oom_kill_process(struct oom_control *oc, struct task_struct *p, - unsigned int points, unsigned long totalpages, - const char *message); - -extern void check_panic_on_oom(struct oom_control *oc, - enum oom_constraint constraint); - -extern enum oom_scan_t oom_scan_process_thread(struct oom_control *oc, - struct task_struct *task); - extern bool out_of_memory(struct oom_control *oc); -extern void exit_oom_victim(struct task_struct *tsk); +extern void exit_oom_victim(void); extern int register_oom_notifier(struct notifier_block *nb); extern int unregister_oom_notifier(struct notifier_block *nb); -extern bool oom_killer_disabled; -extern bool oom_killer_disable(void); +extern bool oom_killer_disable(signed long timeout); extern void oom_killer_enable(void); extern struct task_struct *find_lock_task_mm(struct task_struct *p); -bool task_will_free_mem(struct task_struct *task); - /* sysctls */ extern int sysctl_oom_dump_tasks; extern int sysctl_oom_kill_allocating_task; diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index 03f2a3e7d76d..9298c393ddaa 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -7,6 +7,8 @@ struct pglist_data; struct page_ext_operations { + size_t offset; + size_t size; bool (*need)(void); void (*init)(void); }; @@ -42,12 +44,6 @@ enum page_ext_flags { */ struct page_ext { unsigned long flags; -#ifdef CONFIG_PAGE_OWNER - unsigned int order; - gfp_t gfp_mask; - int last_migrate_reason; - depot_stack_handle_t handle; -#endif }; extern void pgdat_page_ext_init(struct pglist_data *pgdat); diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h index 30583ab0ffb1..2be728d156b5 100644 --- a/include/linux/page_owner.h +++ b/include/linux/page_owner.h @@ -14,6 +14,8 @@ extern void __split_page_owner(struct page *page, unsigned int order); extern void __copy_page_owner(struct page *oldpage, struct page *newpage); extern void __set_page_owner_migrate_reason(struct page *page, int reason); extern void __dump_page_owner(struct page *page); +extern void pagetypeinfo_showmixedcount_print(struct seq_file *m, + pg_data_t *pgdat, struct zone *zone); static inline void reset_page_owner(struct page *page, unsigned int order) { diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 01e84436cddf..794dbcb91084 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -25,6 +25,8 @@ enum mapping_flags { AS_MM_ALL_LOCKS = __GFP_BITS_SHIFT + 2, /* under mm_take_all_locks() */ AS_UNEVICTABLE = __GFP_BITS_SHIFT + 3, /* e.g., ramdisk, SHM_LOCK */ AS_EXITING = __GFP_BITS_SHIFT + 4, /* final truncate in progress */ + /* writeback related tags are not used */ + AS_NO_WRITEBACK_TAGS = __GFP_BITS_SHIFT + 5, }; static inline void mapping_set_error(struct address_space *mapping, int error) @@ -64,6 +66,16 @@ static inline int mapping_exiting(struct address_space *mapping) return test_bit(AS_EXITING, &mapping->flags); } +static inline void mapping_set_no_writeback_tags(struct address_space *mapping) +{ + set_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags); +} + +static inline int mapping_use_writeback_tags(struct address_space *mapping) +{ + return !test_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags); +} + static inline gfp_t mapping_gfp_mask(struct address_space * mapping) { return (__force gfp_t)mapping->flags & __GFP_BITS_MASK; @@ -396,7 +408,7 @@ static inline loff_t page_offset(struct page *page) static inline loff_t page_file_offset(struct page *page) { - return ((loff_t)page_file_index(page)) << PAGE_SHIFT; + return ((loff_t)page_index(page)) << PAGE_SHIFT; } extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma, diff --git a/include/linux/sched.h b/include/linux/sched.h index 7543a476178b..348f51b0ec92 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -524,8 +524,9 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_HAS_UPROBES 19 /* has uprobes */ #define MMF_RECALC_UPROBES 20 /* MMF_HAS_UPROBES can be wrong */ -#define MMF_OOM_REAPED 21 /* mm has been already reaped */ -#define MMF_OOM_NOT_REAPABLE 22 /* mm couldn't be reaped */ +#define MMF_OOM_SKIP 21 /* mm is of no interest for the OOM killer */ +#define MMF_UNSTABLE 22 /* mm is unstable for copy_from_user */ +#define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK) @@ -673,7 +674,6 @@ struct signal_struct { atomic_t sigcnt; atomic_t live; int nr_threads; - atomic_t oom_victims; /* # of TIF_MEDIE threads in this thread group */ struct list_head thread_head; wait_queue_head_t wait_chldexit; /* for wait4() */ @@ -806,6 +806,8 @@ struct signal_struct { short oom_score_adj; /* OOM kill score adjustment */ short oom_score_adj_min; /* OOM kill score adjustment min value. * Only settable by CAP_SYS_RESOURCE. */ + struct mm_struct *oom_mm; /* recorded mm when the thread group got + * killed by the oom killer */ struct mutex cred_guard_mutex; /* guard against foreign influences on * credential calculations @@ -2876,6 +2878,20 @@ static inline void mmdrop(struct mm_struct *mm) __mmdrop(mm); } +static inline void mmdrop_async_fn(struct work_struct *work) +{ + struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work); + __mmdrop(mm); +} + +static inline void mmdrop_async(struct mm_struct *mm) +{ + if (unlikely(atomic_dec_and_test(&mm->mm_count))) { + INIT_WORK(&mm->async_put_work, mmdrop_async_fn); + schedule_work(&mm->async_put_work); + } +} + static inline bool mmget_not_zero(struct mm_struct *mm) { return atomic_inc_not_zero(&mm->mm_users); diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index f3d45dd42695..e305b66a9fb9 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -117,9 +117,9 @@ __printf(2, 3) void seq_printf(struct seq_file *m, const char *fmt, ...); void seq_putc(struct seq_file *m, char c); void seq_puts(struct seq_file *m, const char *s); -void seq_put_decimal_ull(struct seq_file *m, char delimiter, +void seq_put_decimal_ull(struct seq_file *m, const char *delimiter, unsigned long long num); -void seq_put_decimal_ll(struct seq_file *m, char delimiter, long long num); +void seq_put_decimal_ll(struct seq_file *m, const char *delimiter, long long num); void seq_escape(struct seq_file *m, const char *s, const char *esc); void seq_hex_dump(struct seq_file *m, const char *prefix_str, int prefix_type, diff --git a/include/linux/swap.h b/include/linux/swap.h index e1d761463243..a56523cefb9b 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -191,6 +191,11 @@ struct percpu_cluster { unsigned int next; /* Likely next allocation offset */ }; +struct swap_cluster_list { + struct swap_cluster_info head; + struct swap_cluster_info tail; +}; + /* * The in-memory structure used to track swap areas. */ @@ -203,8 +208,7 @@ struct swap_info_struct { unsigned int max; /* extent of the swap_map */ unsigned char *swap_map; /* vmalloc'ed array of usage counts */ struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */ - struct swap_cluster_info free_cluster_head; /* free cluster list head */ - struct swap_cluster_info free_cluster_tail; /* free cluster list tail */ + struct swap_cluster_list free_clusters; /* free clusters list */ unsigned int lowest_bit; /* index of first free in swap_map */ unsigned int highest_bit; /* index of last free in swap_map */ unsigned int pages; /* total of usable pages of swap */ @@ -235,8 +239,7 @@ struct swap_info_struct { * first. */ struct work_struct discard_work; /* discard worker */ - struct swap_cluster_info discard_cluster_head; /* list head of discard clusters */ - struct swap_cluster_info discard_cluster_tail; /* list tail of discard clusters */ + struct swap_cluster_list discard_clusters; /* discard clusters list */ }; /* linux/mm/workingset.c */ diff --git a/include/linux/writeback.h b/include/linux/writeback.h index fc1e16c25a29..797100e10010 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -319,7 +319,6 @@ void laptop_mode_timer_fn(unsigned long data); #else static inline void laptop_sync_completion(void) { } #endif -void throttle_vm_writeout(gfp_t gfp_mask); bool node_dirty_ok(struct pglist_data *pgdat); int wb_domain_init(struct wb_domain *dom, gfp_t gfp); #ifdef CONFIG_CGROUP_WRITEBACK diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h index c2ba402ab256..cbdb90b6b308 100644 --- a/include/trace/events/compaction.h +++ b/include/trace/events/compaction.h @@ -13,7 +13,7 @@ EM( COMPACT_SKIPPED, "skipped") \ EM( COMPACT_DEFERRED, "deferred") \ EM( COMPACT_CONTINUE, "continue") \ - EM( COMPACT_PARTIAL, "partial") \ + EM( COMPACT_SUCCESS, "success") \ EM( COMPACT_PARTIAL_SKIPPED, "partial_skipped") \ EM( COMPACT_COMPLETE, "complete") \ EM( COMPACT_NO_SUITABLE_PAGE, "no_suitable_page") \ diff --git a/kernel/exit.c b/kernel/exit.c index 1e1d913914c0..9d68c45ebbe3 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -511,7 +511,7 @@ static void exit_mm(struct task_struct *tsk) mm_update_next_owner(mm); mmput(mm); if (test_thread_flag(TIF_MEMDIE)) - exit_oom_victim(tsk); + exit_oom_victim(); } static struct task_struct *find_alive_thread(struct task_struct *p) diff --git a/kernel/fork.c b/kernel/fork.c index 9a05bd93f8e7..6d42242485cb 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -359,6 +359,12 @@ static inline void free_signal_struct(struct signal_struct *sig) { taskstats_tgid_free(sig); sched_autogroup_exit(sig); + /* + * __mmdrop is not safe to call from softirq context on x86 due to + * pgd_dtor so postpone it to the async context + */ + if (sig->oom_mm) + mmdrop_async(sig->oom_mm); kmem_cache_free(signal_cachep, sig); } @@ -848,6 +854,7 @@ static inline void __mmput(struct mm_struct *mm) ksm_exit(mm); khugepaged_exit(mm); /* must run before exit_mmap */ exit_mmap(mm); + mm_put_huge_zero_page(mm); set_mm_exe_file(mm, NULL); if (!list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); @@ -856,6 +863,7 @@ static inline void __mmput(struct mm_struct *mm) } if (mm->binfmt) module_put(mm->binfmt->module); + set_bit(MMF_OOM_SKIP, &mm->flags); mmdrop(mm); } diff --git a/kernel/groups.c b/kernel/groups.c index 74d431d25251..2fcadd66a8fd 100644 --- a/kernel/groups.c +++ b/kernel/groups.c @@ -7,55 +7,31 @@ #include #include #include +#include #include struct group_info *groups_alloc(int gidsetsize) { - struct group_info *group_info; - int nblocks; - int i; + struct group_info *gi; + unsigned int len; - nblocks = (gidsetsize + NGROUPS_PER_BLOCK - 1) / NGROUPS_PER_BLOCK; - /* Make sure we always allocate at least one indirect block pointer */ - nblocks = nblocks ? : 1; - group_info = kmalloc(sizeof(*group_info) + nblocks*sizeof(gid_t *), GFP_USER); - if (!group_info) + len = sizeof(struct group_info) + sizeof(kgid_t) * gidsetsize; + gi = kmalloc(len, GFP_KERNEL_ACCOUNT|__GFP_NOWARN|__GFP_NORETRY); + if (!gi) + gi = __vmalloc(len, GFP_KERNEL_ACCOUNT|__GFP_HIGHMEM, PAGE_KERNEL); + if (!gi) return NULL; - group_info->ngroups = gidsetsize; - group_info->nblocks = nblocks; - atomic_set(&group_info->usage, 1); - if (gidsetsize <= NGROUPS_SMALL) - group_info->blocks[0] = group_info->small_block; - else { - for (i = 0; i < nblocks; i++) { - kgid_t *b; - b = (void *)__get_free_page(GFP_USER); - if (!b) - goto out_undo_partial_alloc; - group_info->blocks[i] = b; - } - } - return group_info; - -out_undo_partial_alloc: - while (--i >= 0) { - free_page((unsigned long)group_info->blocks[i]); - } - kfree(group_info); - return NULL; + atomic_set(&gi->usage, 1); + gi->ngroups = gidsetsize; + return gi; } EXPORT_SYMBOL(groups_alloc); void groups_free(struct group_info *group_info) { - if (group_info->blocks[0] != group_info->small_block) { - int i; - for (i = 0; i < group_info->nblocks; i++) - free_page((unsigned long)group_info->blocks[i]); - } - kfree(group_info); + kvfree(group_info); } EXPORT_SYMBOL(groups_free); @@ -70,7 +46,7 @@ static int groups_to_user(gid_t __user *grouplist, for (i = 0; i < count; i++) { gid_t gid; - gid = from_kgid_munged(user_ns, GROUP_AT(group_info, i)); + gid = from_kgid_munged(user_ns, group_info->gid[i]); if (put_user(gid, grouplist+i)) return -EFAULT; } @@ -95,7 +71,7 @@ static int groups_from_user(struct group_info *group_info, if (!gid_valid(kgid)) return -EINVAL; - GROUP_AT(group_info, i) = kgid; + group_info->gid[i] = kgid; } return 0; } @@ -115,15 +91,14 @@ static void groups_sort(struct group_info *group_info) for (base = 0; base < max; base++) { int left = base; int right = left + stride; - kgid_t tmp = GROUP_AT(group_info, right); + kgid_t tmp = group_info->gid[right]; - while (left >= 0 && gid_gt(GROUP_AT(group_info, left), tmp)) { - GROUP_AT(group_info, right) = - GROUP_AT(group_info, left); + while (left >= 0 && gid_gt(group_info->gid[left], tmp)) { + group_info->gid[right] = group_info->gid[left]; right = left; left -= stride; } - GROUP_AT(group_info, right) = tmp; + group_info->gid[right] = tmp; } stride /= 3; } @@ -141,9 +116,9 @@ int groups_search(const struct group_info *group_info, kgid_t grp) right = group_info->ngroups; while (left < right) { unsigned int mid = (left+right)/2; - if (gid_gt(grp, GROUP_AT(group_info, mid))) + if (gid_gt(grp, group_info->gid[mid])) left = mid + 1; - else if (gid_lt(grp, GROUP_AT(group_info, mid))) + else if (gid_lt(grp, group_info->gid[mid])) right = mid; else return 1; diff --git a/kernel/power/process.c b/kernel/power/process.c index 8f27d5a8adf6..2fba066e125f 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -144,23 +144,12 @@ int freeze_processes(void) /* * Now that the whole userspace is frozen we need to disbale * the OOM killer to disallow any further interference with - * killable tasks. + * killable tasks. There is no guarantee oom victims will + * ever reach a point they go away we have to wait with a timeout. */ - if (!error && !oom_killer_disable()) + if (!error && !oom_killer_disable(msecs_to_jiffies(freeze_timeout_msecs))) error = -EBUSY; - /* - * There is a hard to fix race between oom_reaper kernel thread - * and oom_killer_disable. oom_reaper calls exit_oom_victim - * before the victim reaches exit_mm so try to freeze all the tasks - * again and catch such a left over task. - */ - if (!error) { - pr_info("Double checking all user space processes after OOM killer disable... "); - error = try_to_freeze_tasks(true); - pr_cont("\n"); - } - if (error) thaw_processes(); return error; diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index eea6dbc2d8cf..8019cc0d3a73 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -253,6 +253,17 @@ static int preferred_console = -1; int console_set_on_cmdline; EXPORT_SYMBOL(console_set_on_cmdline); +#ifdef CONFIG_OF +static bool of_specified_console; + +void console_set_by_of(void) +{ + of_specified_console = true; +} +#else +# define of_specified_console false +#endif + /* Flag: console code may call schedule() */ static int console_may_schedule; @@ -2647,7 +2658,7 @@ void register_console(struct console *newcon) * didn't select a console we take the first one * that registers here. */ - if (preferred_console < 0) { + if (preferred_console < 0 && !of_specified_console) { if (newcon->index < 0) newcon->index = 0; if (newcon->setup == NULL || diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 9fb873cfc75c..1d8718d5300d 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -16,6 +16,9 @@ #include "sched.h" +/* Linker adds these: start and end of __cpuidle functions */ +extern char __cpuidle_text_start[], __cpuidle_text_end[]; + /** * sched_idle_set_state - Record idle state for the current CPU. * @idle_state: State to record. @@ -53,7 +56,7 @@ static int __init cpu_idle_nopoll_setup(char *__unused) __setup("hlt", cpu_idle_nopoll_setup); #endif -static inline int cpu_idle_poll(void) +static noinline int __cpuidle cpu_idle_poll(void) { rcu_idle_enter(); trace_cpu_idle_rcuidle(0, smp_processor_id()); @@ -84,7 +87,7 @@ void __weak arch_cpu_idle(void) * * To use when the cpuidle framework cannot be used. */ -void default_idle_call(void) +void __cpuidle default_idle_call(void) { if (current_clr_polling_and_test()) { local_irq_enable(); @@ -271,6 +274,12 @@ static void cpu_idle_loop(void) } } +bool cpu_in_idle(unsigned long pc) +{ + return pc >= (unsigned long)__cpuidle_text_start && + pc < (unsigned long)__cpuidle_text_end; +} + void cpu_startup_entry(enum cpuhp_state state) { /* diff --git a/kernel/uid16.c b/kernel/uid16.c index d58cc4d8f0d1..cc40793464e3 100644 --- a/kernel/uid16.c +++ b/kernel/uid16.c @@ -117,7 +117,7 @@ static int groups16_to_user(old_gid_t __user *grouplist, kgid_t kgid; for (i = 0; i < group_info->ngroups; i++) { - kgid = GROUP_AT(group_info, i); + kgid = group_info->gid[i]; group = high2lowgid(from_kgid_munged(user_ns, kgid)); if (put_user(group, grouplist+i)) return -EFAULT; @@ -142,7 +142,7 @@ static int groups16_from_user(struct group_info *group_info, if (!gid_valid(kgid)) return -EINVAL; - GROUP_AT(group_info, i) = kgid; + group_info->gid[i] = kgid; } return 0; diff --git a/lib/Kconfig b/lib/Kconfig index 942fb8091a86..260a80e313b9 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -457,9 +457,6 @@ config NLATTR config GENERIC_ATOMIC64 bool -config ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE - def_bool y if GENERIC_ATOMIC64 - config LRU_CACHE tristate diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c index dbb369145dda..46042901130f 100644 --- a/lib/atomic64_test.c +++ b/lib/atomic64_test.c @@ -213,7 +213,6 @@ static __init void test_atomic64(void) r += one; BUG_ON(v.counter != r); -#ifdef CONFIG_ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE INIT(onestwos); BUG_ON(atomic64_dec_if_positive(&v) != (onestwos - 1)); r -= one; @@ -226,9 +225,6 @@ static __init void test_atomic64(void) INIT(-one); BUG_ON(atomic64_dec_if_positive(&v) != (-one - one)); BUG_ON(v.counter != r); -#else -#warning Please implement atomic64_dec_if_positive for your architecture and select the above Kconfig symbol -#endif INIT(onestwos); BUG_ON(!atomic64_inc_not_zero(&v)); diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c index 26caf51cc238..75554754eadf 100644 --- a/lib/nmi_backtrace.c +++ b/lib/nmi_backtrace.c @@ -16,21 +16,23 @@ #include #include #include +#include -#ifdef arch_trigger_all_cpu_backtrace +#ifdef arch_trigger_cpumask_backtrace /* For reliability, we're prepared to waste bits here. */ static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly; -/* "in progress" flag of arch_trigger_all_cpu_backtrace */ +/* "in progress" flag of arch_trigger_cpumask_backtrace */ static unsigned long backtrace_flag; /* - * When raise() is called it will be is passed a pointer to the + * When raise() is called it will be passed a pointer to the * backtrace_mask. Architectures that call nmi_cpu_backtrace() * directly from their raise() functions may rely on the mask * they are passed being updated as a side effect of this call. */ -void nmi_trigger_all_cpu_backtrace(bool include_self, +void nmi_trigger_cpumask_backtrace(const cpumask_t *mask, + bool exclude_self, void (*raise)(cpumask_t *mask)) { int i, this_cpu = get_cpu(); @@ -44,13 +46,22 @@ void nmi_trigger_all_cpu_backtrace(bool include_self, return; } - cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask); - if (!include_self) + cpumask_copy(to_cpumask(backtrace_mask), mask); + if (exclude_self) cpumask_clear_cpu(this_cpu, to_cpumask(backtrace_mask)); + /* + * Don't try to send an NMI to this cpu; it may work on some + * architectures, but on others it may not, and we'll get + * information at least as useful just by doing a dump_stack() here. + * Note that nmi_cpu_backtrace(NULL) will clear the cpu bit. + */ + if (cpumask_test_cpu(this_cpu, to_cpumask(backtrace_mask))) + nmi_cpu_backtrace(NULL); + if (!cpumask_empty(to_cpumask(backtrace_mask))) { - pr_info("Sending NMI to %s CPUs:\n", - (include_self ? "all" : "other")); + pr_info("Sending NMI from CPU %d to CPUs %*pbl:\n", + this_cpu, nr_cpumask_bits, to_cpumask(backtrace_mask)); raise(to_cpumask(backtrace_mask)); } @@ -77,11 +88,16 @@ bool nmi_cpu_backtrace(struct pt_regs *regs) int cpu = smp_processor_id(); if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) { - pr_warn("NMI backtrace for cpu %d\n", cpu); - if (regs) - show_regs(regs); - else - dump_stack(); + if (regs && cpu_in_idle(instruction_pointer(regs))) { + pr_warn("NMI backtrace for cpu %d skipped: idling at pc %#lx\n", + cpu, instruction_pointer(regs)); + } else { + pr_warn("NMI backtrace for cpu %d\n", cpu); + if (regs) + show_regs(regs); + else + dump_stack(); + } cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask)); return true; } diff --git a/mm/bootmem.c b/mm/bootmem.c index 0aa7dda52402..a869f84f44d3 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -11,15 +11,12 @@ #include #include #include -#include #include #include #include -#include #include #include - -#include +#include #include "internal.h" @@ -712,7 +709,7 @@ void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat, void *ptr; if (WARN_ON_ONCE(slab_is_available())) - return kzalloc(size, GFP_NOWAIT); + return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); again: /* do not panic in alloc_bootmem_bdata() */ @@ -738,9 +735,6 @@ again: void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal) { - if (WARN_ON_ONCE(slab_is_available())) - return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); - return ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, 0); } @@ -812,10 +806,6 @@ void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size, } -#ifndef ARCH_LOW_ADDRESS_LIMIT -#define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL -#endif - /** * __alloc_bootmem_low - allocate low boot memory * @size: size of the request in bytes diff --git a/mm/compaction.c b/mm/compaction.c index 9affb2908304..0409a4ad6ea1 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -997,8 +997,12 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn, #ifdef CONFIG_COMPACTION /* Returns true if the page is within a block suitable for migration to */ -static bool suitable_migration_target(struct page *page) +static bool suitable_migration_target(struct compact_control *cc, + struct page *page) { + if (cc->ignore_block_suitable) + return true; + /* If the page is a large free page, then disallow migration */ if (PageBuddy(page)) { /* @@ -1083,7 +1087,7 @@ static void isolate_freepages(struct compact_control *cc) continue; /* Check the block is suitable for migration */ - if (!suitable_migration_target(page)) + if (!suitable_migration_target(cc, page)) continue; /* If isolation recently failed, do not retry */ @@ -1316,7 +1320,7 @@ static enum compact_result __compact_finished(struct zone *zone, struct compact_ return COMPACT_CONTINUE; /* Compaction run is not finished if the watermark is not met */ - watermark = low_wmark_pages(zone); + watermark = zone->watermark[cc->alloc_flags & ALLOC_WMARK_MASK]; if (!zone_watermark_ok(zone, cc->order, watermark, cc->classzone_idx, cc->alloc_flags)) @@ -1329,13 +1333,13 @@ static enum compact_result __compact_finished(struct zone *zone, struct compact_ /* Job done if page is free of the right migratetype */ if (!list_empty(&area->free_list[migratetype])) - return COMPACT_PARTIAL; + return COMPACT_SUCCESS; #ifdef CONFIG_CMA /* MIGRATE_MOVABLE can fallback on MIGRATE_CMA */ if (migratetype == MIGRATE_MOVABLE && !list_empty(&area->free_list[MIGRATE_CMA])) - return COMPACT_PARTIAL; + return COMPACT_SUCCESS; #endif /* * Job done if allocation would steal freepages from @@ -1343,7 +1347,7 @@ static enum compact_result __compact_finished(struct zone *zone, struct compact_ */ if (find_suitable_fallback(area, order, migratetype, true, &can_steal) != -1) - return COMPACT_PARTIAL; + return COMPACT_SUCCESS; } return COMPACT_NO_SUITABLE_PAGE; @@ -1367,7 +1371,7 @@ static enum compact_result compact_finished(struct zone *zone, * compaction_suitable: Is this suitable to run compaction on this zone now? * Returns * COMPACT_SKIPPED - If there are too few free pages for compaction - * COMPACT_PARTIAL - If the allocation would succeed without compaction + * COMPACT_SUCCESS - If the allocation would succeed without compaction * COMPACT_CONTINUE - If compaction should run now */ static enum compact_result __compaction_suitable(struct zone *zone, int order, @@ -1375,46 +1379,41 @@ static enum compact_result __compaction_suitable(struct zone *zone, int order, int classzone_idx, unsigned long wmark_target) { - int fragindex; unsigned long watermark; if (is_via_compact_memory(order)) return COMPACT_CONTINUE; - watermark = low_wmark_pages(zone); + watermark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK]; /* * If watermarks for high-order allocation are already met, there * should be no need for compaction at all. */ if (zone_watermark_ok(zone, order, watermark, classzone_idx, alloc_flags)) - return COMPACT_PARTIAL; + return COMPACT_SUCCESS; /* - * Watermarks for order-0 must be met for compaction. Note the 2UL. - * This is because during migration, copies of pages need to be - * allocated and for a short time, the footprint is higher + * Watermarks for order-0 must be met for compaction to be able to + * isolate free pages for migration targets. This means that the + * watermark and alloc_flags have to match, or be more pessimistic than + * the check in __isolate_free_page(). We don't use the direct + * compactor's alloc_flags, as they are not relevant for freepage + * isolation. We however do use the direct compactor's classzone_idx to + * skip over zones where lowmem reserves would prevent allocation even + * if compaction succeeds. + * For costly orders, we require low watermark instead of min for + * compaction to proceed to increase its chances. + * ALLOC_CMA is used, as pages in CMA pageblocks are considered + * suitable migration targets */ - watermark += (2UL << order); + watermark = (order > PAGE_ALLOC_COSTLY_ORDER) ? + low_wmark_pages(zone) : min_wmark_pages(zone); + watermark += compact_gap(order); if (!__zone_watermark_ok(zone, 0, watermark, classzone_idx, - alloc_flags, wmark_target)) + ALLOC_CMA, wmark_target)) return COMPACT_SKIPPED; - /* - * fragmentation index determines if allocation failures are due to - * low memory or external fragmentation - * - * index of -1000 would imply allocations might succeed depending on - * watermarks, but we already failed the high-order watermark check - * index towards 0 implies failure is due to lack of memory - * index towards 1000 implies failure is due to fragmentation - * - * Only compact if a failure would be due to fragmentation. - */ - fragindex = fragmentation_index(zone, order); - if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold) - return COMPACT_NOT_SUITABLE_ZONE; - return COMPACT_CONTINUE; } @@ -1423,9 +1422,32 @@ enum compact_result compaction_suitable(struct zone *zone, int order, int classzone_idx) { enum compact_result ret; + int fragindex; ret = __compaction_suitable(zone, order, alloc_flags, classzone_idx, zone_page_state(zone, NR_FREE_PAGES)); + /* + * fragmentation index determines if allocation failures are due to + * low memory or external fragmentation + * + * index of -1000 would imply allocations might succeed depending on + * watermarks, but we already failed the high-order watermark check + * index towards 0 implies failure is due to lack of memory + * index towards 1000 implies failure is due to fragmentation + * + * Only compact if a failure would be due to fragmentation. Also + * ignore fragindex for non-costly orders where the alternative to + * a successful reclaim/compaction is OOM. Fragindex and the + * vm.extfrag_threshold sysctl is meant as a heuristic to prevent + * excessive compaction for costly orders, but it should not be at the + * expense of system stability. + */ + if (ret == COMPACT_CONTINUE && (order > PAGE_ALLOC_COSTLY_ORDER)) { + fragindex = fragmentation_index(zone, order); + if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold) + ret = COMPACT_NOT_SUITABLE_ZONE; + } + trace_mm_compaction_suitable(zone, order, ret); if (ret == COMPACT_NOT_SUITABLE_ZONE) ret = COMPACT_SKIPPED; @@ -1458,8 +1480,7 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order, available += zone_page_state_snapshot(zone, NR_FREE_PAGES); compact_result = __compaction_suitable(zone, order, alloc_flags, ac_classzone_idx(ac), available); - if (compact_result != COMPACT_SKIPPED && - compact_result != COMPACT_NOT_SUITABLE_ZONE) + if (compact_result != COMPACT_SKIPPED) return true; } @@ -1477,7 +1498,7 @@ static enum compact_result compact_zone(struct zone *zone, struct compact_contro ret = compaction_suitable(zone, cc->order, cc->alloc_flags, cc->classzone_idx); /* Compaction is likely to fail */ - if (ret == COMPACT_PARTIAL || ret == COMPACT_SKIPPED) + if (ret == COMPACT_SUCCESS || ret == COMPACT_SKIPPED) return ret; /* huh, compaction_suitable is returning something unexpected */ @@ -1492,23 +1513,29 @@ static enum compact_result compact_zone(struct zone *zone, struct compact_contro /* * Setup to move all movable pages to the end of the zone. Used cached - * information on where the scanners should start but check that it - * is initialised by ensuring the values are within zone boundaries. + * information on where the scanners should start (unless we explicitly + * want to compact the whole zone), but check that it is initialised + * by ensuring the values are within zone boundaries. */ - cc->migrate_pfn = zone->compact_cached_migrate_pfn[sync]; - cc->free_pfn = zone->compact_cached_free_pfn; - if (cc->free_pfn < start_pfn || cc->free_pfn >= end_pfn) { - cc->free_pfn = pageblock_start_pfn(end_pfn - 1); - zone->compact_cached_free_pfn = cc->free_pfn; - } - if (cc->migrate_pfn < start_pfn || cc->migrate_pfn >= end_pfn) { + if (cc->whole_zone) { cc->migrate_pfn = start_pfn; - zone->compact_cached_migrate_pfn[0] = cc->migrate_pfn; - zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn; - } + cc->free_pfn = pageblock_start_pfn(end_pfn - 1); + } else { + cc->migrate_pfn = zone->compact_cached_migrate_pfn[sync]; + cc->free_pfn = zone->compact_cached_free_pfn; + if (cc->free_pfn < start_pfn || cc->free_pfn >= end_pfn) { + cc->free_pfn = pageblock_start_pfn(end_pfn - 1); + zone->compact_cached_free_pfn = cc->free_pfn; + } + if (cc->migrate_pfn < start_pfn || cc->migrate_pfn >= end_pfn) { + cc->migrate_pfn = start_pfn; + zone->compact_cached_migrate_pfn[0] = cc->migrate_pfn; + zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn; + } - if (cc->migrate_pfn == start_pfn) - cc->whole_zone = true; + if (cc->migrate_pfn == start_pfn) + cc->whole_zone = true; + } cc->last_migrated_pfn = 0; @@ -1638,6 +1665,9 @@ static enum compact_result compact_zone_order(struct zone *zone, int order, .alloc_flags = alloc_flags, .classzone_idx = classzone_idx, .direct_compaction = true, + .whole_zone = (prio == MIN_COMPACT_PRIORITY), + .ignore_skip_hint = (prio == MIN_COMPACT_PRIORITY), + .ignore_block_suitable = (prio == MIN_COMPACT_PRIORITY) }; INIT_LIST_HEAD(&cc.freepages); INIT_LIST_HEAD(&cc.migratepages); @@ -1683,7 +1713,8 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, ac->nodemask) { enum compact_result status; - if (compaction_deferred(zone, order)) { + if (prio > MIN_COMPACT_PRIORITY + && compaction_deferred(zone, order)) { rc = max_t(enum compact_result, COMPACT_DEFERRED, rc); continue; } @@ -1692,9 +1723,8 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, alloc_flags, ac_classzone_idx(ac)); rc = max(status, rc); - /* If a normal allocation would succeed, stop compacting */ - if (zone_watermark_ok(zone, order, low_wmark_pages(zone), - ac_classzone_idx(ac), alloc_flags)) { + /* The allocation should succeed, stop compacting */ + if (status == COMPACT_SUCCESS) { /* * We think the allocation will succeed in this zone, * but it is not certain, hence the false. The caller @@ -1730,10 +1760,18 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, /* Compact all zones within a node */ -static void __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc) +static void compact_node(int nid) { + pg_data_t *pgdat = NODE_DATA(nid); int zoneid; struct zone *zone; + struct compact_control cc = { + .order = -1, + .mode = MIGRATE_SYNC, + .ignore_skip_hint = true, + .whole_zone = true, + }; + for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) { @@ -1741,60 +1779,19 @@ static void __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc) if (!populated_zone(zone)) continue; - cc->nr_freepages = 0; - cc->nr_migratepages = 0; - cc->zone = zone; - INIT_LIST_HEAD(&cc->freepages); - INIT_LIST_HEAD(&cc->migratepages); + cc.nr_freepages = 0; + cc.nr_migratepages = 0; + cc.zone = zone; + INIT_LIST_HEAD(&cc.freepages); + INIT_LIST_HEAD(&cc.migratepages); - /* - * When called via /proc/sys/vm/compact_memory - * this makes sure we compact the whole zone regardless of - * cached scanner positions. - */ - if (is_via_compact_memory(cc->order)) - __reset_isolation_suitable(zone); + compact_zone(zone, &cc); - if (is_via_compact_memory(cc->order) || - !compaction_deferred(zone, cc->order)) - compact_zone(zone, cc); - - VM_BUG_ON(!list_empty(&cc->freepages)); - VM_BUG_ON(!list_empty(&cc->migratepages)); - - if (is_via_compact_memory(cc->order)) - continue; - - if (zone_watermark_ok(zone, cc->order, - low_wmark_pages(zone), 0, 0)) - compaction_defer_reset(zone, cc->order, false); + VM_BUG_ON(!list_empty(&cc.freepages)); + VM_BUG_ON(!list_empty(&cc.migratepages)); } } -void compact_pgdat(pg_data_t *pgdat, int order) -{ - struct compact_control cc = { - .order = order, - .mode = MIGRATE_ASYNC, - }; - - if (!order) - return; - - __compact_pgdat(pgdat, &cc); -} - -static void compact_node(int nid) -{ - struct compact_control cc = { - .order = -1, - .mode = MIGRATE_SYNC, - .ignore_skip_hint = true, - }; - - __compact_pgdat(NODE_DATA(nid), &cc); -} - /* Compact all nodes in the system */ static void compact_nodes(void) { @@ -1900,8 +1897,6 @@ static void kcompactd_do_work(pg_data_t *pgdat) .ignore_skip_hint = true, }; - bool success = false; - trace_mm_compaction_kcompactd_wake(pgdat->node_id, cc.order, cc.classzone_idx); count_vm_event(KCOMPACTD_WAKE); @@ -1930,9 +1925,7 @@ static void kcompactd_do_work(pg_data_t *pgdat) return; status = compact_zone(zone, &cc); - if (zone_watermark_ok(zone, cc.order, low_wmark_pages(zone), - cc.classzone_idx, 0)) { - success = true; + if (status == COMPACT_SUCCESS) { compaction_defer_reset(zone, cc.order, false); } else if (status == COMPACT_PARTIAL_SKIPPED || status == COMPACT_COMPLETE) { /* diff --git a/mm/debug.c b/mm/debug.c index 74c7cae4f683..9feb699c5d25 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -42,6 +42,11 @@ const struct trace_print_flags vmaflag_names[] = { void __dump_page(struct page *page, const char *reason) { + /* + * Avoid VM_BUG_ON() in page_mapcount(). + * page->_mapcount space in struct page is used by sl[aou]b pages to + * encode own info. + */ int mapcount = PageSlab(page) ? 0 : page_mapcount(page); pr_emerg("page:%p count:%d mapcount:%d mapping:%p index:%#lx", diff --git a/mm/filemap.c b/mm/filemap.c index 68f1813fbdc3..2f7b7783bd6b 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1687,6 +1687,10 @@ static ssize_t do_generic_file_read(struct file *filp, loff_t *ppos, unsigned int prev_offset; int error = 0; + if (unlikely(*ppos >= inode->i_sb->s_maxbytes)) + return -EINVAL; + iov_iter_truncate(iter, inode->i_sb->s_maxbytes); + index = *ppos >> PAGE_SHIFT; prev_index = ra->prev_pos >> PAGE_SHIFT; prev_offset = ra->prev_pos & (PAGE_SIZE-1); @@ -1721,7 +1725,9 @@ find_page: * wait_on_page_locked is used to avoid unnecessarily * serialisations and why it's safe. */ - wait_on_page_locked_killable(page); + error = wait_on_page_locked_killable(page); + if (unlikely(error)) + goto readpage_error; if (PageUptodate(page)) goto page_ok; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 283583fcb1e7..cdcd25cb30fe 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -59,7 +59,7 @@ static struct shrinker deferred_split_shrinker; static atomic_t huge_zero_refcount; struct page *huge_zero_page __read_mostly; -struct page *get_huge_zero_page(void) +static struct page *get_huge_zero_page(void) { struct page *zero_page; retry: @@ -86,7 +86,7 @@ retry: return READ_ONCE(huge_zero_page); } -void put_huge_zero_page(void) +static void put_huge_zero_page(void) { /* * Counter should never go to zero here. Only shrinker can put @@ -95,6 +95,26 @@ void put_huge_zero_page(void) BUG_ON(atomic_dec_and_test(&huge_zero_refcount)); } +struct page *mm_get_huge_zero_page(struct mm_struct *mm) +{ + if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags)) + return READ_ONCE(huge_zero_page); + + if (!get_huge_zero_page()) + return NULL; + + if (test_and_set_bit(MMF_HUGE_ZERO_PAGE, &mm->flags)) + put_huge_zero_page(); + + return READ_ONCE(huge_zero_page); +} + +void mm_put_huge_zero_page(struct mm_struct *mm) +{ + if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags)) + put_huge_zero_page(); +} + static unsigned long shrink_huge_zero_page_count(struct shrinker *shrink, struct shrink_control *sc) { @@ -469,6 +489,49 @@ void prep_transhuge_page(struct page *page) set_compound_page_dtor(page, TRANSHUGE_PAGE_DTOR); } +unsigned long __thp_get_unmapped_area(struct file *filp, unsigned long len, + loff_t off, unsigned long flags, unsigned long size) +{ + unsigned long addr; + loff_t off_end = off + len; + loff_t off_align = round_up(off, size); + unsigned long len_pad; + + if (off_end <= off_align || (off_end - off_align) < size) + return 0; + + len_pad = len + size; + if (len_pad < len || (off + len_pad) < off) + return 0; + + addr = current->mm->get_unmapped_area(filp, 0, len_pad, + off >> PAGE_SHIFT, flags); + if (IS_ERR_VALUE(addr)) + return 0; + + addr += (off - addr) & (size - 1); + return addr; +} + +unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags) +{ + loff_t off = (loff_t)pgoff << PAGE_SHIFT; + + if (addr) + goto out; + if (!IS_DAX(filp->f_mapping->host) || !IS_ENABLED(CONFIG_FS_DAX_PMD)) + goto out; + + addr = __thp_get_unmapped_area(filp, len, off, flags, PMD_SIZE); + if (addr) + return addr; + + out: + return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags); +} +EXPORT_SYMBOL_GPL(thp_get_unmapped_area); + static int __do_huge_pmd_anonymous_page(struct fault_env *fe, struct page *page, gfp_t gfp) { @@ -601,7 +664,7 @@ int do_huge_pmd_anonymous_page(struct fault_env *fe) pgtable = pte_alloc_one(vma->vm_mm, haddr); if (unlikely(!pgtable)) return VM_FAULT_OOM; - zero_page = get_huge_zero_page(); + zero_page = mm_get_huge_zero_page(vma->vm_mm); if (unlikely(!zero_page)) { pte_free(vma->vm_mm, pgtable); count_vm_event(THP_FAULT_FALLBACK); @@ -623,10 +686,8 @@ int do_huge_pmd_anonymous_page(struct fault_env *fe) } } else spin_unlock(fe->ptl); - if (!set) { + if (!set) pte_free(vma->vm_mm, pgtable); - put_huge_zero_page(); - } return ret; } gfp = alloc_hugepage_direct_gfpmask(vma); @@ -780,7 +841,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, * since we already have a zero page to copy. It just takes a * reference. */ - zero_page = get_huge_zero_page(); + zero_page = mm_get_huge_zero_page(dst_mm); set_huge_zero_page(pgtable, dst_mm, vma, addr, dst_pmd, zero_page); ret = 0; @@ -1038,7 +1099,6 @@ alloc: update_mmu_cache_pmd(vma, fe->address, fe->pmd); if (!page) { add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR); - put_huge_zero_page(); } else { VM_BUG_ON_PAGE(!PageHead(page), page); page_remove_rmap(page, true); @@ -1499,7 +1559,6 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, } smp_wmb(); /* make pte visible before pmd */ pmd_populate(mm, pmd, pgtable); - put_huge_zero_page(); } static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, @@ -1522,8 +1581,6 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, if (!vma_is_anonymous(vma)) { _pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd); - if (is_huge_zero_pmd(_pmd)) - put_huge_zero_page(); if (vma_is_dax(vma)) return; page = pmd_page(_pmd); @@ -1563,7 +1620,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, if (soft_dirty) entry = pte_swp_mksoft_dirty(entry); } else { - entry = mk_pte(page + i, vma->vm_page_prot); + entry = mk_pte(page + i, READ_ONCE(vma->vm_page_prot)); entry = maybe_mkwrite(entry, vma); if (!write) entry = pte_wrprotect(entry); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 87e11d8ad536..ec49d9ef1eef 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -567,13 +567,13 @@ retry: * appear as a "reserved" entry instead of simply dangling with incorrect * counts. */ -void hugetlb_fix_reserve_counts(struct inode *inode, bool restore_reserve) +void hugetlb_fix_reserve_counts(struct inode *inode) { struct hugepage_subpool *spool = subpool_inode(inode); long rsv_adjust; rsv_adjust = hugepage_subpool_get_pages(spool, 1); - if (restore_reserve && rsv_adjust) { + if (rsv_adjust) { struct hstate *h = hstate_inode(inode); hugetlb_acct_memory(h, 1); @@ -1022,7 +1022,7 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) ((node = hstate_next_node_to_free(hs, mask)) || 1); \ nr_nodes--) -#if (defined(CONFIG_X86_64) || defined(CONFIG_S390)) && \ +#if defined(CONFIG_ARCH_HAS_GIGANTIC_PAGE) && \ ((defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || \ defined(CONFIG_CMA)) static void destroy_compound_gigantic_page(struct page *page, @@ -1437,38 +1437,61 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, /* * Dissolve a given free hugepage into free buddy pages. This function does - * nothing for in-use (including surplus) hugepages. + * nothing for in-use (including surplus) hugepages. Returns -EBUSY if the + * number of free hugepages would be reduced below the number of reserved + * hugepages. */ -static void dissolve_free_huge_page(struct page *page) +static int dissolve_free_huge_page(struct page *page) { + int rc = 0; + spin_lock(&hugetlb_lock); if (PageHuge(page) && !page_count(page)) { - struct hstate *h = page_hstate(page); - int nid = page_to_nid(page); - list_del(&page->lru); + struct page *head = compound_head(page); + struct hstate *h = page_hstate(head); + int nid = page_to_nid(head); + if (h->free_huge_pages - h->resv_huge_pages == 0) { + rc = -EBUSY; + goto out; + } + list_del(&head->lru); h->free_huge_pages--; h->free_huge_pages_node[nid]--; h->max_huge_pages--; - update_and_free_page(h, page); + update_and_free_page(h, head); } +out: spin_unlock(&hugetlb_lock); + return rc; } /* * Dissolve free hugepages in a given pfn range. Used by memory hotplug to * make specified memory blocks removable from the system. - * Note that start_pfn should aligned with (minimum) hugepage size. + * Note that this will dissolve a free gigantic hugepage completely, if any + * part of it lies within the given range. + * Also note that if dissolve_free_huge_page() returns with an error, all + * free hugepages that were dissolved before that error are lost. */ -void dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn) +int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn) { unsigned long pfn; + struct page *page; + int rc = 0; if (!hugepages_supported()) - return; + return rc; - VM_BUG_ON(!IS_ALIGNED(start_pfn, 1 << minimum_order)); - for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << minimum_order) - dissolve_free_huge_page(pfn_to_page(pfn)); + for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << minimum_order) { + page = pfn_to_page(pfn); + if (PageHuge(page) && !page_count(page)) { + rc = dissolve_free_huge_page(page); + if (rc) + break; + } + } + + return rc; } /* diff --git a/mm/internal.h b/mm/internal.h index 1501304f87a4..537ac9951f5f 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -178,8 +178,9 @@ struct compact_control { unsigned long last_migrated_pfn;/* Not yet flushed page being freed */ enum migrate_mode mode; /* Async or sync migration mode */ bool ignore_skip_hint; /* Scan blocks even if marked skip */ + bool ignore_block_suitable; /* Scan blocks considered unsuitable */ bool direct_compaction; /* False from kcompactd or /proc/... */ - bool whole_zone; /* Whole zone has been scanned */ + bool whole_zone; /* Whole zone should/has been scanned */ int order; /* order a direct compactor needs */ const gfp_t gfp_mask; /* gfp mask of a direct compactor */ const unsigned int alloc_flags; /* alloc flags of a direct compactor */ diff --git a/mm/ksm.c b/mm/ksm.c index 5048083b60f2..9ae6011a41f8 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -299,7 +299,12 @@ static inline void free_rmap_item(struct rmap_item *rmap_item) static inline struct stable_node *alloc_stable_node(void) { - return kmem_cache_alloc(stable_node_cache, GFP_KERNEL); + /* + * The allocation can take too long with GFP_KERNEL when memory is under + * pressure, which may lead to hung task warnings. Adding __GFP_HIGH + * grants access to memory reserves, helping to avoid this problem. + */ + return kmem_cache_alloc(stable_node_cache, GFP_KERNEL | __GFP_HIGH); } static inline void free_stable_node(struct stable_node *stable_node) diff --git a/mm/memblock.c b/mm/memblock.c index 483197ef613f..c8dfa430342b 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1438,6 +1438,11 @@ phys_addr_t __init_memblock memblock_phys_mem_size(void) return memblock.memory.total_size; } +phys_addr_t __init_memblock memblock_reserved_size(void) +{ + return memblock.reserved.total_size; +} + phys_addr_t __init memblock_mem_size(unsigned long limit_pfn) { unsigned long pages = 0; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 4be518d4e68a..ae052b5e3315 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -920,6 +920,43 @@ static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg) iter != NULL; \ iter = mem_cgroup_iter(NULL, iter, NULL)) +/** + * mem_cgroup_scan_tasks - iterate over tasks of a memory cgroup hierarchy + * @memcg: hierarchy root + * @fn: function to call for each task + * @arg: argument passed to @fn + * + * This function iterates over tasks attached to @memcg or to any of its + * descendants and calls @fn for each task. If @fn returns a non-zero + * value, the function breaks the iteration loop and returns the value. + * Otherwise, it will iterate over all tasks and return 0. + * + * This function must not be called for the root memory cgroup. + */ +int mem_cgroup_scan_tasks(struct mem_cgroup *memcg, + int (*fn)(struct task_struct *, void *), void *arg) +{ + struct mem_cgroup *iter; + int ret = 0; + + BUG_ON(memcg == root_mem_cgroup); + + for_each_mem_cgroup_tree(iter, memcg) { + struct css_task_iter it; + struct task_struct *task; + + css_task_iter_start(&iter->css, &it); + while (!ret && (task = css_task_iter_next(&it))) + ret = fn(task, arg); + css_task_iter_end(&it); + if (ret) { + mem_cgroup_iter_break(memcg, iter); + break; + } + } + return ret; +} + /** * mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page * @page: the page @@ -1178,7 +1215,7 @@ static int mem_cgroup_count_children(struct mem_cgroup *memcg) /* * Return the memory (and swap, if configured) limit for a memcg. */ -static unsigned long mem_cgroup_get_limit(struct mem_cgroup *memcg) +unsigned long mem_cgroup_get_limit(struct mem_cgroup *memcg) { unsigned long limit; @@ -1205,79 +1242,12 @@ static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, .gfp_mask = gfp_mask, .order = order, }; - struct mem_cgroup *iter; - unsigned long chosen_points = 0; - unsigned long totalpages; - unsigned int points = 0; - struct task_struct *chosen = NULL; + bool ret; mutex_lock(&oom_lock); - - /* - * If current has a pending SIGKILL or is exiting, then automatically - * select it. The goal is to allow it to allocate so that it may - * quickly exit and free its memory. - */ - if (task_will_free_mem(current)) { - mark_oom_victim(current); - wake_oom_reaper(current); - goto unlock; - } - - check_panic_on_oom(&oc, CONSTRAINT_MEMCG); - totalpages = mem_cgroup_get_limit(memcg) ? : 1; - for_each_mem_cgroup_tree(iter, memcg) { - struct css_task_iter it; - struct task_struct *task; - - css_task_iter_start(&iter->css, &it); - while ((task = css_task_iter_next(&it))) { - switch (oom_scan_process_thread(&oc, task)) { - case OOM_SCAN_SELECT: - if (chosen) - put_task_struct(chosen); - chosen = task; - chosen_points = ULONG_MAX; - get_task_struct(chosen); - /* fall through */ - case OOM_SCAN_CONTINUE: - continue; - case OOM_SCAN_ABORT: - css_task_iter_end(&it); - mem_cgroup_iter_break(memcg, iter); - if (chosen) - put_task_struct(chosen); - /* Set a dummy value to return "true". */ - chosen = (void *) 1; - goto unlock; - case OOM_SCAN_OK: - break; - }; - points = oom_badness(task, memcg, NULL, totalpages); - if (!points || points < chosen_points) - continue; - /* Prefer thread group leaders for display purposes */ - if (points == chosen_points && - thread_group_leader(chosen)) - continue; - - if (chosen) - put_task_struct(chosen); - chosen = task; - chosen_points = points; - get_task_struct(chosen); - } - css_task_iter_end(&it); - } - - if (chosen) { - points = chosen_points * 1000 / totalpages; - oom_kill_process(&oc, chosen, points, totalpages, - "Memory cgroup out of memory"); - } -unlock: + ret = out_of_memory(&oc); mutex_unlock(&oom_lock); - return chosen; + return ret; } #if MAX_NUMNODES > 1 @@ -1600,7 +1570,7 @@ bool mem_cgroup_oom_synchronize(bool handle) if (!memcg) return false; - if (!handle || oom_killer_disabled) + if (!handle) goto cleanup; owait.memcg = memcg; @@ -2969,16 +2939,16 @@ static int memcg_update_tcp_limit(struct mem_cgroup *memcg, unsigned long limit) /* * The active flag needs to be written after the static_key * update. This is what guarantees that the socket activation - * function is the last one to run. See sock_update_memcg() for - * details, and note that we don't mark any socket as belonging - * to this memcg until that flag is up. + * function is the last one to run. See mem_cgroup_sk_alloc() + * for details, and note that we don't mark any socket as + * belonging to this memcg until that flag is up. * * We need to do this, because static_keys will span multiple * sites, but we can't control their order. If we mark a socket * as accounted, but the accounting functions are not patched in * yet, we'll lose accounting. * - * We never race with the readers in sock_update_memcg(), + * We never race with the readers in mem_cgroup_sk_alloc(), * because when this value change, the code to process it is not * patched in yet. */ @@ -4092,11 +4062,13 @@ static DEFINE_IDR(mem_cgroup_idr); static void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n) { + VM_BUG_ON(atomic_read(&memcg->id.ref) <= 0); atomic_add(n, &memcg->id.ref); } static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n) { + VM_BUG_ON(atomic_read(&memcg->id.ref) < n); if (atomic_sub_and_test(n, &memcg->id.ref)) { idr_remove(&mem_cgroup_idr, memcg->id.id); memcg->id.id = 0; @@ -4285,8 +4257,10 @@ fail: static int mem_cgroup_css_online(struct cgroup_subsys_state *css) { + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + /* Online state pins memcg ID, memcg ID pins CSS */ - mem_cgroup_id_get(mem_cgroup_from_css(css)); + atomic_set(&memcg->id.ref, 1); css_get(css); return 0; } @@ -4434,7 +4408,7 @@ static struct page *mc_handle_swap_pte(struct vm_area_struct *vma, * Because lookup_swap_cache() updates some statistics counter, * we call find_get_page() with swapper_space directly. */ - page = find_get_page(swap_address_space(ent), ent.val); + page = find_get_page(swap_address_space(ent), swp_offset(ent)); if (do_memsw_account()) entry->val = ent.val; @@ -4472,7 +4446,8 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma, swp_entry_t swp = radix_to_swp_entry(page); if (do_memsw_account()) *entry = swp; - page = find_get_page(swap_address_space(swp), swp.val); + page = find_get_page(swap_address_space(swp), + swp_offset(swp)); } } else page = find_get_page(mapping, pgoff); @@ -4707,7 +4682,8 @@ static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm) .mm = mm, }; down_read(&mm->mmap_sem); - walk_page_range(0, ~0UL, &mem_cgroup_count_precharge_walk); + walk_page_range(0, mm->highest_vm_end, + &mem_cgroup_count_precharge_walk); up_read(&mm->mmap_sem); precharge = mc.precharge; @@ -4995,7 +4971,8 @@ retry: * When we have consumed all precharges and failed in doing * additional charge, the page walk just aborts. */ - walk_page_range(0, ~0UL, &mem_cgroup_move_charge_walk); + walk_page_range(0, mc.mm->highest_vm_end, &mem_cgroup_move_charge_walk); + up_read(&mc.mm->mmap_sem); atomic_dec(&mc.from->moving_account); } @@ -5674,11 +5651,15 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) DEFINE_STATIC_KEY_FALSE(memcg_sockets_enabled_key); EXPORT_SYMBOL(memcg_sockets_enabled_key); -void sock_update_memcg(struct sock *sk) +void mem_cgroup_sk_alloc(struct sock *sk) { struct mem_cgroup *memcg; - /* Socket cloning can throw us here with sk_cgrp already + if (!mem_cgroup_sockets_enabled) + return; + + /* + * Socket cloning can throw us here with sk_memcg already * filled. It won't however, necessarily happen from * process context. So the test for root memcg given * the current task's memcg won't help us in this case. @@ -5703,12 +5684,11 @@ void sock_update_memcg(struct sock *sk) out: rcu_read_unlock(); } -EXPORT_SYMBOL(sock_update_memcg); -void sock_release_memcg(struct sock *sk) +void mem_cgroup_sk_free(struct sock *sk) { - WARN_ON(!sk->sk_memcg); - css_put(&sk->sk_memcg->css); + if (sk->sk_memcg) + css_put(&sk->sk_memcg->css); } /** diff --git a/mm/memory.c b/mm/memory.c index f1a68049edff..fc1987dfd8cc 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1649,10 +1649,14 @@ EXPORT_SYMBOL(vm_insert_pfn_prot); int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn) { + pgprot_t pgprot = vma->vm_page_prot; + BUG_ON(!(vma->vm_flags & VM_MIXEDMAP)); if (addr < vma->vm_start || addr >= vma->vm_end) return -EFAULT; + if (track_pfn_insert(vma, &pgprot, pfn)) + return -EINVAL; /* * If we don't have pte special, then we have to use the pfn_valid() @@ -1670,9 +1674,9 @@ int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, * result in pfn_t_has_page() == false. */ page = pfn_to_page(pfn_t_to_pfn(pfn)); - return insert_page(vma, addr, page, vma->vm_page_prot); + return insert_page(vma, addr, page, pgprot); } - return insert_pfn(vma, addr, pfn, vma->vm_page_prot); + return insert_pfn(vma, addr, pfn, pgprot); } EXPORT_SYMBOL(vm_insert_mixed); @@ -3658,6 +3662,19 @@ int handle_mm_fault(struct vm_area_struct *vma, unsigned long address, mem_cgroup_oom_synchronize(false); } + /* + * This mm has been already reaped by the oom reaper and so the + * refault cannot be trusted in general. Anonymous refaults would + * lose data and give a zero page instead e.g. This is especially + * problem for use_mm() because regular tasks will just die and + * the corrupted data will not be visible anywhere while kthread + * will outlive the oom victim and potentially propagate the date + * further. + */ + if (unlikely((current->flags & PF_KTHREAD) && !(ret & VM_FAULT_ERROR) + && test_bit(MMF_UNSTABLE, &vma->vm_mm->flags))) + ret = VM_FAULT_SIGBUS; + return ret; } EXPORT_SYMBOL_GPL(handle_mm_fault); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 9d29ba0f7192..962927309b6e 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1945,7 +1945,9 @@ repeat: * dissolve free hugepages in the memory block before doing offlining * actually in order to make hugetlbfs's object counting consistent. */ - dissolve_free_huge_pages(start_pfn, end_pfn); + ret = dissolve_free_huge_pages(start_pfn, end_pfn); + if (ret) + goto failed_removal; /* check again */ offlined_pages = check_pages_isolated(start_pfn, end_pfn); if (offlined_pages < 0) { diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 2da72a5b6ecc..ad1c96ac313c 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1749,7 +1749,7 @@ unsigned int mempolicy_slab_node(void) */ struct zonelist *zonelist; enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL); - zonelist = &NODE_DATA(node)->node_zonelists[0]; + zonelist = &NODE_DATA(node)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, highest_zoneidx, &policy->v.nodes); return z->zone ? z->zone->node : node; diff --git a/mm/migrate.c b/mm/migrate.c index f7ee04a5ae27..99250aee1ac1 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -234,7 +234,7 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma, goto unlock; get_page(new); - pte = pte_mkold(mk_pte(new, vma->vm_page_prot)); + pte = pte_mkold(mk_pte(new, READ_ONCE(vma->vm_page_prot))); if (pte_swp_soft_dirty(*ptep)) pte = pte_mksoft_dirty(pte); diff --git a/mm/mincore.c b/mm/mincore.c index c0b5ba965200..bfb866435478 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -66,7 +66,8 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff) */ if (radix_tree_exceptional_entry(page)) { swp_entry_t swp = radix_to_swp_entry(page); - page = find_get_page(swap_address_space(swp), swp.val); + page = find_get_page(swap_address_space(swp), + swp_offset(swp)); } } else page = find_get_page(mapping, pgoff); @@ -150,7 +151,7 @@ static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, } else { #ifdef CONFIG_SWAP *vec = mincore_page(swap_address_space(entry), - entry.val); + swp_offset(entry)); #else WARN_ON(1); *vec = 1; diff --git a/mm/mlock.c b/mm/mlock.c index 14645be06e30..145a4258ddbc 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -516,6 +516,7 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev, int nr_pages; int ret = 0; int lock = !!(newflags & VM_LOCKED); + vm_flags_t old_flags = vma->vm_flags; if (newflags == vma->vm_flags || (vma->vm_flags & VM_SPECIAL) || is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm)) @@ -550,6 +551,8 @@ success: nr_pages = (end - start) >> PAGE_SHIFT; if (!lock) nr_pages = -nr_pages; + else if (old_flags & VM_LOCKED) + nr_pages = 0; mm->locked_vm += nr_pages; /* @@ -617,6 +620,45 @@ static int apply_vma_lock_flags(unsigned long start, size_t len, return error; } +/* + * Go through vma areas and sum size of mlocked + * vma pages, as return value. + * Note deferred memory locking case(mlock2(,,MLOCK_ONFAULT) + * is also counted. + * Return value: previously mlocked page counts + */ +static int count_mm_mlocked_page_nr(struct mm_struct *mm, + unsigned long start, size_t len) +{ + struct vm_area_struct *vma; + int count = 0; + + if (mm == NULL) + mm = current->mm; + + vma = find_vma(mm, start); + if (vma == NULL) + vma = mm->mmap; + + for (; vma ; vma = vma->vm_next) { + if (start >= vma->vm_end) + continue; + if (start + len <= vma->vm_start) + break; + if (vma->vm_flags & VM_LOCKED) { + if (start > vma->vm_start) + count -= (start - vma->vm_start); + if (start + len < vma->vm_end) { + count += start + len - vma->vm_start; + break; + } + count += vma->vm_end - vma->vm_start; + } + } + + return count >> PAGE_SHIFT; +} + static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t flags) { unsigned long locked; @@ -639,6 +681,16 @@ static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t fla return -EINTR; locked += current->mm->locked_vm; + if ((locked > lock_limit) && (!capable(CAP_IPC_LOCK))) { + /* + * It is possible that the regions requested intersect with + * previously mlocked areas, that part area in "mm->locked_vm" + * should not be counted to new mlock increment count. So check + * and adjust locked count if necessary. + */ + locked -= count_mm_mlocked_page_nr(current->mm, + start, len); + } /* check against resource limits */ if ((locked <= lock_limit) || capable(CAP_IPC_LOCK)) diff --git a/mm/mmap.c b/mm/mmap.c index 7a0707a48047..1af87c14183d 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -116,13 +116,15 @@ static pgprot_t vm_pgprot_modify(pgprot_t oldprot, unsigned long vm_flags) void vma_set_page_prot(struct vm_area_struct *vma) { unsigned long vm_flags = vma->vm_flags; + pgprot_t vm_page_prot; - vma->vm_page_prot = vm_pgprot_modify(vma->vm_page_prot, vm_flags); - if (vma_wants_writenotify(vma)) { + vm_page_prot = vm_pgprot_modify(vma->vm_page_prot, vm_flags); + if (vma_wants_writenotify(vma, vm_page_prot)) { vm_flags &= ~VM_SHARED; - vma->vm_page_prot = vm_pgprot_modify(vma->vm_page_prot, - vm_flags); + vm_page_prot = vm_pgprot_modify(vm_page_prot, vm_flags); } + /* remove_protection_ptes reads vma->vm_page_prot without mmap_sem */ + WRITE_ONCE(vma->vm_page_prot, vm_page_prot); } /* @@ -400,7 +402,32 @@ static inline void vma_rb_insert(struct vm_area_struct *vma, rb_insert_augmented(&vma->vm_rb, root, &vma_gap_callbacks); } -static void vma_rb_erase(struct vm_area_struct *vma, struct rb_root *root) +static void __vma_rb_erase(struct vm_area_struct *vma, struct rb_root *root) +{ + /* + * Note rb_erase_augmented is a fairly large inline function, + * so make sure we instantiate it only once with our desired + * augmented rbtree callbacks. + */ + rb_erase_augmented(&vma->vm_rb, root, &vma_gap_callbacks); +} + +static __always_inline void vma_rb_erase_ignore(struct vm_area_struct *vma, + struct rb_root *root, + struct vm_area_struct *ignore) +{ + /* + * All rb_subtree_gap values must be consistent prior to erase, + * with the possible exception of the "next" vma being erased if + * next->vm_start was reduced. + */ + validate_mm_rb(root, ignore); + + __vma_rb_erase(vma, root); +} + +static __always_inline void vma_rb_erase(struct vm_area_struct *vma, + struct rb_root *root) { /* * All rb_subtree_gap values must be consistent prior to erase, @@ -408,12 +435,7 @@ static void vma_rb_erase(struct vm_area_struct *vma, struct rb_root *root) */ validate_mm_rb(root, vma); - /* - * Note rb_erase_augmented is a fairly large inline function, - * so make sure we instantiate it only once with our desired - * augmented rbtree callbacks. - */ - rb_erase_augmented(&vma->vm_rb, root, &vma_gap_callbacks); + __vma_rb_erase(vma, root); } /* @@ -599,14 +621,25 @@ static void __insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma) mm->map_count++; } -static inline void -__vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma, - struct vm_area_struct *prev) +static __always_inline void __vma_unlink_common(struct mm_struct *mm, + struct vm_area_struct *vma, + struct vm_area_struct *prev, + bool has_prev, + struct vm_area_struct *ignore) { struct vm_area_struct *next; - vma_rb_erase(vma, &mm->mm_rb); - prev->vm_next = next = vma->vm_next; + vma_rb_erase_ignore(vma, &mm->mm_rb, ignore); + next = vma->vm_next; + if (has_prev) + prev->vm_next = next; + else { + prev = vma->vm_prev; + if (prev) + prev->vm_next = next; + else + mm->mmap = next; + } if (next) next->vm_prev = prev; @@ -614,6 +647,13 @@ __vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma, vmacache_invalidate(mm); } +static inline void __vma_unlink_prev(struct mm_struct *mm, + struct vm_area_struct *vma, + struct vm_area_struct *prev) +{ + __vma_unlink_common(mm, vma, prev, true, vma); +} + /* * We cannot adjust vm_start, vm_end, vm_pgoff fields of a vma that * is already present in an i_mmap tree without adjusting the tree. @@ -621,11 +661,12 @@ __vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma, * are necessary. The "insert" vma (if any) is to be inserted * before we drop the necessary locks. */ -int vma_adjust(struct vm_area_struct *vma, unsigned long start, - unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert) +int __vma_adjust(struct vm_area_struct *vma, unsigned long start, + unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert, + struct vm_area_struct *expand) { struct mm_struct *mm = vma->vm_mm; - struct vm_area_struct *next = vma->vm_next; + struct vm_area_struct *next = vma->vm_next, *orig_vma = vma; struct address_space *mapping = NULL; struct rb_root *root = NULL; struct anon_vma *anon_vma = NULL; @@ -641,9 +682,38 @@ int vma_adjust(struct vm_area_struct *vma, unsigned long start, /* * vma expands, overlapping all the next, and * perhaps the one after too (mprotect case 6). + * The only other cases that gets here are + * case 1, case 7 and case 8. */ - remove_next = 1 + (end > next->vm_end); - end = next->vm_end; + if (next == expand) { + /* + * The only case where we don't expand "vma" + * and we expand "next" instead is case 8. + */ + VM_WARN_ON(end != next->vm_end); + /* + * remove_next == 3 means we're + * removing "vma" and that to do so we + * swapped "vma" and "next". + */ + remove_next = 3; + VM_WARN_ON(file != next->vm_file); + swap(vma, next); + } else { + VM_WARN_ON(expand != vma); + /* + * case 1, 6, 7, remove_next == 2 is case 6, + * remove_next == 1 is case 1 or 7. + */ + remove_next = 1 + (end > next->vm_end); + VM_WARN_ON(remove_next == 2 && + end != next->vm_next->vm_end); + VM_WARN_ON(remove_next == 1 && + end != next->vm_end); + /* trim end to next, for case 6 first pass */ + end = next->vm_end; + } + exporter = next; importer = vma; @@ -651,7 +721,7 @@ int vma_adjust(struct vm_area_struct *vma, unsigned long start, * If next doesn't have anon_vma, import from vma after * next, if the vma overlaps with it. */ - if (remove_next == 2 && next && !next->anon_vma) + if (remove_next == 2 && !next->anon_vma) exporter = next->vm_next; } else if (end > next->vm_start) { @@ -662,6 +732,7 @@ int vma_adjust(struct vm_area_struct *vma, unsigned long start, adjust_next = (end - next->vm_start) >> PAGE_SHIFT; exporter = next; importer = vma; + VM_WARN_ON(expand != importer); } else if (end < vma->vm_end) { /* * vma shrinks, and !insert tells it's not @@ -671,6 +742,7 @@ int vma_adjust(struct vm_area_struct *vma, unsigned long start, adjust_next = -((vma->vm_end - end) >> PAGE_SHIFT); exporter = vma; importer = next; + VM_WARN_ON(expand != importer); } /* @@ -688,7 +760,7 @@ int vma_adjust(struct vm_area_struct *vma, unsigned long start, } } again: - vma_adjust_trans_huge(vma, start, end, adjust_next); + vma_adjust_trans_huge(orig_vma, start, end, adjust_next); if (file) { mapping = file->f_mapping; @@ -714,8 +786,8 @@ again: if (!anon_vma && adjust_next) anon_vma = next->anon_vma; if (anon_vma) { - VM_BUG_ON_VMA(adjust_next && next->anon_vma && - anon_vma != next->anon_vma, next); + VM_WARN_ON(adjust_next && next->anon_vma && + anon_vma != next->anon_vma); anon_vma_lock_write(anon_vma); anon_vma_interval_tree_pre_update_vma(vma); if (adjust_next) @@ -755,7 +827,19 @@ again: * vma_merge has merged next into vma, and needs * us to remove next before dropping the locks. */ - __vma_unlink(mm, next, vma); + if (remove_next != 3) + __vma_unlink_prev(mm, next, vma); + else + /* + * vma is not before next if they've been + * swapped. + * + * pre-swap() next->vm_start was reduced so + * tell validate_mm_rb to ignore pre-swap() + * "next" (which is stored in post-swap() + * "vma"). + */ + __vma_unlink_common(mm, next, NULL, false, vma); if (file) __remove_shared_vm_struct(next, file, mapping); } else if (insert) { @@ -807,7 +891,27 @@ again: * we must remove another next too. It would clutter * up the code too much to do both in one go. */ - next = vma->vm_next; + if (remove_next != 3) { + /* + * If "next" was removed and vma->vm_end was + * expanded (up) over it, in turn + * "next->vm_prev->vm_end" changed and the + * "vma->vm_next" gap must be updated. + */ + next = vma->vm_next; + } else { + /* + * For the scope of the comment "next" and + * "vma" considered pre-swap(): if "vma" was + * removed, next->vm_start was expanded (down) + * over it and the "next" gap must be updated. + * Because of the swap() the post-swap() "vma" + * actually points to pre-swap() "next" + * (post-swap() "next" as opposed is now a + * dangling pointer). + */ + next = vma; + } if (remove_next == 2) { remove_next = 1; end = next->vm_end; @@ -815,8 +919,28 @@ again: } else if (next) vma_gap_update(next); - else - mm->highest_vm_end = end; + else { + /* + * If remove_next == 2 we obviously can't + * reach this path. + * + * If remove_next == 3 we can't reach this + * path because pre-swap() next is always not + * NULL. pre-swap() "next" is not being + * removed and its next->vm_end is not altered + * (and furthermore "end" already matches + * next->vm_end in remove_next == 3). + * + * We reach this only in the remove_next == 1 + * case if the "next" vma that was removed was + * the highest vma of the mm. However in such + * case next->vm_end == "end" and the extended + * "vma" has vma->vm_end == next->vm_end so + * mm->highest_vm_end doesn't need any update + * in remove_next == 1 case. + */ + VM_WARN_ON(mm->highest_vm_end != end); + } } if (insert && file) uprobe_mmap(insert); @@ -936,13 +1060,24 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, * cannot merge might become might become might become * PPNNNNNNNNNN PPPPPPPPPPNN PPPPPPPPPPPP 6 or * mmap, brk or case 4 below case 5 below PPPPPPPPXXXX 7 or - * mremap move: PPPPNNNNNNNN 8 + * mremap move: PPPPXXXXXXXX 8 * AAAA * PPPP NNNN PPPPPPPPPPPP PPPPPPPPNNNN PPPPNNNNNNNN * might become case 1 below case 2 below case 3 below * - * Odd one out? Case 8, because it extends NNNN but needs flags of XXXX: - * mprotect_fixup updates vm_flags & vm_page_prot on successful return. + * It is important for case 8 that the the vma NNNN overlapping the + * region AAAA is never going to extended over XXXX. Instead XXXX must + * be extended in region AAAA and NNNN must be removed. This way in + * all cases where vma_merge succeeds, the moment vma_adjust drops the + * rmap_locks, the properties of the merged vma will be already + * correct for the whole merged range. Some of those properties like + * vm_page_prot/vm_flags may be accessed by rmap_walks and they must + * be correct for the whole merged range immediately after the + * rmap_locks are released. Otherwise if XXXX would be removed and + * NNNN would be extended over the XXXX range, remove_migration_ptes + * or other rmap walkers (if working on addresses beyond the "end" + * parameter) may establish ptes with the wrong permissions of NNNN + * instead of the right permissions of XXXX. */ struct vm_area_struct *vma_merge(struct mm_struct *mm, struct vm_area_struct *prev, unsigned long addr, @@ -967,9 +1102,14 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, else next = mm->mmap; area = next; - if (next && next->vm_end == end) /* cases 6, 7, 8 */ + if (area && area->vm_end == end) /* cases 6, 7, 8 */ next = next->vm_next; + /* verify some invariant that must be enforced by the caller */ + VM_WARN_ON(prev && addr <= prev->vm_start); + VM_WARN_ON(area && end > area->vm_end); + VM_WARN_ON(addr >= end); + /* * Can it merge with the predecessor? */ @@ -990,11 +1130,12 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, is_mergeable_anon_vma(prev->anon_vma, next->anon_vma, NULL)) { /* cases 1, 6 */ - err = vma_adjust(prev, prev->vm_start, - next->vm_end, prev->vm_pgoff, NULL); + err = __vma_adjust(prev, prev->vm_start, + next->vm_end, prev->vm_pgoff, NULL, + prev); } else /* cases 2, 5, 7 */ - err = vma_adjust(prev, prev->vm_start, - end, prev->vm_pgoff, NULL); + err = __vma_adjust(prev, prev->vm_start, + end, prev->vm_pgoff, NULL, prev); if (err) return NULL; khugepaged_enter_vma_merge(prev, vm_flags); @@ -1010,11 +1151,18 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, anon_vma, file, pgoff+pglen, vm_userfaultfd_ctx)) { if (prev && addr < prev->vm_end) /* case 4 */ - err = vma_adjust(prev, prev->vm_start, - addr, prev->vm_pgoff, NULL); - else /* cases 3, 8 */ - err = vma_adjust(area, addr, next->vm_end, - next->vm_pgoff - pglen, NULL); + err = __vma_adjust(prev, prev->vm_start, + addr, prev->vm_pgoff, NULL, next); + else { /* cases 3, 8 */ + err = __vma_adjust(area, addr, next->vm_end, + next->vm_pgoff - pglen, NULL, next); + /* + * In case 3 area is already equal to next and + * this is a noop, but in case 8 "area" has + * been removed and next was expanded over it. + */ + area = next; + } if (err) return NULL; khugepaged_enter_vma_merge(area, vm_flags); @@ -1386,7 +1534,7 @@ SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg) * to the private version (using protection_map[] without the * VM_SHARED bit). */ -int vma_wants_writenotify(struct vm_area_struct *vma) +int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot) { vm_flags_t vm_flags = vma->vm_flags; const struct vm_operations_struct *vm_ops = vma->vm_ops; @@ -1401,8 +1549,8 @@ int vma_wants_writenotify(struct vm_area_struct *vma) /* The open routine did something to the protections that pgprot_modify * won't preserve? */ - if (pgprot_val(vma->vm_page_prot) != - pgprot_val(vm_pgprot_modify(vma->vm_page_prot, vm_flags))) + if (pgprot_val(vm_page_prot) != + pgprot_val(vm_pgprot_modify(vm_page_prot, vm_flags))) return 0; /* Do we need to track softdirty? */ diff --git a/mm/mprotect.c b/mm/mprotect.c index a4830f0325fe..ec91dfd3f900 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -304,6 +304,7 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, vma->vm_userfaultfd_ctx); if (*pprev) { vma = *pprev; + VM_WARN_ON((vma->vm_flags ^ newflags) & ~VM_SOFTDIRTY); goto success; } @@ -327,7 +328,7 @@ success: * held in write mode. */ vma->vm_flags = newflags; - dirty_accountable = vma_wants_writenotify(vma); + dirty_accountable = vma_wants_writenotify(vma, vma->vm_page_prot); vma_set_page_prot(vma); change_protection(vma, start, end, vma->vm_page_prot, diff --git a/mm/nobootmem.c b/mm/nobootmem.c index bd05a70f44b9..ba609b684d7a 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -11,18 +11,21 @@ #include #include #include -#include #include #include #include #include +#include #include #include -#include #include "internal.h" +#ifndef CONFIG_HAVE_MEMBLOCK +#error CONFIG_HAVE_MEMBLOCK not defined +#endif + #ifndef CONFIG_NEED_MULTIPLE_NODES struct pglist_data __refdata contig_page_data; EXPORT_SYMBOL(contig_page_data); @@ -134,6 +137,11 @@ static unsigned long __init free_low_memory_core_early(void) for_each_reserved_mem_region(i, &start, &end) reserve_bootmem_region(start, end); + /* + * We need to use NUMA_NO_NODE instead of NODE_DATA(0)->node_id + * because in some case like Node0 doesn't have RAM installed + * low ram will be on Node1 + */ for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, NULL) count += __free_memory_core(start, end); @@ -191,11 +199,6 @@ unsigned long __init free_all_bootmem(void) reset_all_zones_managed_pages(); - /* - * We need to use NUMA_NO_NODE instead of NODE_DATA(0)->node_id - * because in some case like Node0 doesn't have RAM installed - * low ram will be on Node1 - */ pages = free_low_memory_core_early(); totalram_pages += pages; @@ -395,9 +398,6 @@ void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size, return __alloc_bootmem_node(pgdat, size, align, goal); } -#ifndef ARCH_LOW_ADDRESS_LIMIT -#define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL -#endif /** * __alloc_bootmem_low - allocate low boot memory diff --git a/mm/oom_kill.c b/mm/oom_kill.c index d53a9aa00977..ec9f11d4f094 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -132,6 +132,11 @@ static inline bool is_sysrq_oom(struct oom_control *oc) return oc->order == -1; } +static inline bool is_memcg_oom(struct oom_control *oc) +{ + return oc->memcg != NULL; +} + /* return true if the task is not adequate as candidate victim task. */ static bool oom_unkillable_task(struct task_struct *p, struct mem_cgroup *memcg, const nodemask_t *nodemask) @@ -181,7 +186,7 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, */ adj = (long)p->signal->oom_score_adj; if (adj == OOM_SCORE_ADJ_MIN || - test_bit(MMF_OOM_REAPED, &p->mm->flags) || + test_bit(MMF_OOM_SKIP, &p->mm->flags) || in_vfork(p)) { task_unlock(p); return 0; @@ -213,12 +218,17 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, return points > 0 ? points : 1; } +enum oom_constraint { + CONSTRAINT_NONE, + CONSTRAINT_CPUSET, + CONSTRAINT_MEMORY_POLICY, + CONSTRAINT_MEMCG, +}; + /* * Determine the type of allocation constraint. */ -#ifdef CONFIG_NUMA -static enum oom_constraint constrained_alloc(struct oom_control *oc, - unsigned long *totalpages) +static enum oom_constraint constrained_alloc(struct oom_control *oc) { struct zone *zone; struct zoneref *z; @@ -226,8 +236,16 @@ static enum oom_constraint constrained_alloc(struct oom_control *oc, bool cpuset_limited = false; int nid; + if (is_memcg_oom(oc)) { + oc->totalpages = mem_cgroup_get_limit(oc->memcg) ?: 1; + return CONSTRAINT_MEMCG; + } + /* Default to all available memory */ - *totalpages = totalram_pages + total_swap_pages; + oc->totalpages = totalram_pages + total_swap_pages; + + if (!IS_ENABLED(CONFIG_NUMA)) + return CONSTRAINT_NONE; if (!oc->zonelist) return CONSTRAINT_NONE; @@ -246,9 +264,9 @@ static enum oom_constraint constrained_alloc(struct oom_control *oc, */ if (oc->nodemask && !nodes_subset(node_states[N_MEMORY], *oc->nodemask)) { - *totalpages = total_swap_pages; + oc->totalpages = total_swap_pages; for_each_node_mask(nid, *oc->nodemask) - *totalpages += node_spanned_pages(nid); + oc->totalpages += node_spanned_pages(nid); return CONSTRAINT_MEMORY_POLICY; } @@ -259,98 +277,84 @@ static enum oom_constraint constrained_alloc(struct oom_control *oc, cpuset_limited = true; if (cpuset_limited) { - *totalpages = total_swap_pages; + oc->totalpages = total_swap_pages; for_each_node_mask(nid, cpuset_current_mems_allowed) - *totalpages += node_spanned_pages(nid); + oc->totalpages += node_spanned_pages(nid); return CONSTRAINT_CPUSET; } return CONSTRAINT_NONE; } -#else -static enum oom_constraint constrained_alloc(struct oom_control *oc, - unsigned long *totalpages) -{ - *totalpages = totalram_pages + total_swap_pages; - return CONSTRAINT_NONE; -} -#endif -enum oom_scan_t oom_scan_process_thread(struct oom_control *oc, - struct task_struct *task) +static int oom_evaluate_task(struct task_struct *task, void *arg) { + struct oom_control *oc = arg; + unsigned long points; + if (oom_unkillable_task(task, NULL, oc->nodemask)) - return OOM_SCAN_CONTINUE; + goto next; /* * This task already has access to memory reserves and is being killed. * Don't allow any other task to have access to the reserves unless - * the task has MMF_OOM_REAPED because chances that it would release + * the task has MMF_OOM_SKIP because chances that it would release * any memory is quite low. */ - if (!is_sysrq_oom(oc) && atomic_read(&task->signal->oom_victims)) { - struct task_struct *p = find_lock_task_mm(task); - enum oom_scan_t ret = OOM_SCAN_ABORT; - - if (p) { - if (test_bit(MMF_OOM_REAPED, &p->mm->flags)) - ret = OOM_SCAN_CONTINUE; - task_unlock(p); - } - - return ret; + if (!is_sysrq_oom(oc) && tsk_is_oom_victim(task)) { + if (test_bit(MMF_OOM_SKIP, &task->signal->oom_mm->flags)) + goto next; + goto abort; } /* * If task is allocating a lot of memory and has been marked to be * killed first if it triggers an oom, then select it. */ - if (oom_task_origin(task)) - return OOM_SCAN_SELECT; + if (oom_task_origin(task)) { + points = ULONG_MAX; + goto select; + } - return OOM_SCAN_OK; + points = oom_badness(task, NULL, oc->nodemask, oc->totalpages); + if (!points || points < oc->chosen_points) + goto next; + + /* Prefer thread group leaders for display purposes */ + if (points == oc->chosen_points && thread_group_leader(oc->chosen)) + goto next; +select: + if (oc->chosen) + put_task_struct(oc->chosen); + get_task_struct(task); + oc->chosen = task; + oc->chosen_points = points; +next: + return 0; +abort: + if (oc->chosen) + put_task_struct(oc->chosen); + oc->chosen = (void *)-1UL; + return 1; } /* - * Simple selection loop. We chose the process with the highest - * number of 'points'. Returns -1 on scan abort. + * Simple selection loop. We choose the process with the highest number of + * 'points'. In case scan was aborted, oc->chosen is set to -1. */ -static struct task_struct *select_bad_process(struct oom_control *oc, - unsigned int *ppoints, unsigned long totalpages) +static void select_bad_process(struct oom_control *oc) { - struct task_struct *p; - struct task_struct *chosen = NULL; - unsigned long chosen_points = 0; + if (is_memcg_oom(oc)) + mem_cgroup_scan_tasks(oc->memcg, oom_evaluate_task, oc); + else { + struct task_struct *p; - rcu_read_lock(); - for_each_process(p) { - unsigned int points; - - switch (oom_scan_process_thread(oc, p)) { - case OOM_SCAN_SELECT: - chosen = p; - chosen_points = ULONG_MAX; - /* fall through */ - case OOM_SCAN_CONTINUE: - continue; - case OOM_SCAN_ABORT: - rcu_read_unlock(); - return (struct task_struct *)(-1UL); - case OOM_SCAN_OK: - break; - }; - points = oom_badness(p, NULL, oc->nodemask, totalpages); - if (!points || points < chosen_points) - continue; - - chosen = p; - chosen_points = points; + rcu_read_lock(); + for_each_process(p) + if (oom_evaluate_task(p, oc)) + break; + rcu_read_unlock(); } - if (chosen) - get_task_struct(chosen); - rcu_read_unlock(); - *ppoints = chosen_points * 1000 / totalpages; - return chosen; + oc->chosen_points = oc->chosen_points * 1000 / oc->totalpages; } /** @@ -399,9 +403,14 @@ static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask) static void dump_header(struct oom_control *oc, struct task_struct *p) { - pr_warn("%s invoked oom-killer: gfp_mask=%#x(%pGg), order=%d, oom_score_adj=%hd\n", - current->comm, oc->gfp_mask, &oc->gfp_mask, oc->order, + nodemask_t *nm = (oc->nodemask) ? oc->nodemask : &cpuset_current_mems_allowed; + + pr_warn("%s invoked oom-killer: gfp_mask=%#x(%pGg), nodemask=%*pbl, order=%d, oom_score_adj=%hd\n", + current->comm, oc->gfp_mask, &oc->gfp_mask, + nodemask_pr_args(nm), oc->order, current->signal->oom_score_adj); + if (!IS_ENABLED(CONFIG_COMPACTION) && oc->order) + pr_warn("COMPACTION is disabled!!!\n"); cpuset_print_current_mems_allowed(); dump_stack(); @@ -419,7 +428,7 @@ static void dump_header(struct oom_control *oc, struct task_struct *p) static atomic_t oom_victims = ATOMIC_INIT(0); static DECLARE_WAIT_QUEUE_HEAD(oom_victims_wait); -bool oom_killer_disabled __read_mostly; +static bool oom_killer_disabled __read_mostly; #define K(x) ((x) << (PAGE_SHIFT-10)) @@ -452,12 +461,10 @@ static DECLARE_WAIT_QUEUE_HEAD(oom_reaper_wait); static struct task_struct *oom_reaper_list; static DEFINE_SPINLOCK(oom_reaper_lock); -static bool __oom_reap_task(struct task_struct *tsk) +static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm) { struct mmu_gather tlb; struct vm_area_struct *vma; - struct mm_struct *mm = NULL; - struct task_struct *p; struct zap_details details = {.check_swap_entries = true, .ignore_dirty = true}; bool ret = true; @@ -465,7 +472,7 @@ static bool __oom_reap_task(struct task_struct *tsk) /* * We have to make sure to not race with the victim exit path * and cause premature new oom victim selection: - * __oom_reap_task exit_mm + * __oom_reap_task_mm exit_mm * mmget_not_zero * mmput * atomic_dec_and_test @@ -478,22 +485,9 @@ static bool __oom_reap_task(struct task_struct *tsk) */ mutex_lock(&oom_lock); - /* - * Make sure we find the associated mm_struct even when the particular - * thread has already terminated and cleared its mm. - * We might have race with exit path so consider our work done if there - * is no mm. - */ - p = find_lock_task_mm(tsk); - if (!p) - goto unlock_oom; - mm = p->mm; - atomic_inc(&mm->mm_count); - task_unlock(p); - if (!down_read_trylock(&mm->mmap_sem)) { ret = false; - goto mm_drop; + goto unlock_oom; } /* @@ -503,9 +497,17 @@ static bool __oom_reap_task(struct task_struct *tsk) */ if (!mmget_not_zero(mm)) { up_read(&mm->mmap_sem); - goto mm_drop; + goto unlock_oom; } + /* + * Tell all users of get_user/copy_from_user etc... that the content + * is no longer stable. No barriers really needed because unmapping + * should imply barriers already and the reader would hit a page fault + * if it stumbled over a reaped memory. + */ + set_bit(MMF_UNSTABLE, &mm->flags); + tlb_gather_mmu(&tlb, mm, 0, -1); for (vma = mm->mmap ; vma; vma = vma->vm_next) { if (is_vm_hugetlb_page(vma)) @@ -540,19 +542,12 @@ static bool __oom_reap_task(struct task_struct *tsk) K(get_mm_counter(mm, MM_SHMEMPAGES))); up_read(&mm->mmap_sem); - /* - * This task can be safely ignored because we cannot do much more - * to release its memory. - */ - set_bit(MMF_OOM_REAPED, &mm->flags); /* * Drop our reference but make sure the mmput slow path is called from a * different context because we shouldn't risk we get stuck there and * put the oom_reaper out of the way. */ mmput_async(mm); -mm_drop: - mmdrop(mm); unlock_oom: mutex_unlock(&oom_lock); return ret; @@ -562,44 +557,28 @@ unlock_oom: static void oom_reap_task(struct task_struct *tsk) { int attempts = 0; + struct mm_struct *mm = tsk->signal->oom_mm; /* Retry the down_read_trylock(mmap_sem) a few times */ - while (attempts++ < MAX_OOM_REAP_RETRIES && !__oom_reap_task(tsk)) + while (attempts++ < MAX_OOM_REAP_RETRIES && !__oom_reap_task_mm(tsk, mm)) schedule_timeout_idle(HZ/10); - if (attempts > MAX_OOM_REAP_RETRIES) { - struct task_struct *p; + if (attempts <= MAX_OOM_REAP_RETRIES) + goto done; - pr_info("oom_reaper: unable to reap pid:%d (%s)\n", - task_pid_nr(tsk), tsk->comm); - /* - * If we've already tried to reap this task in the past and - * failed it probably doesn't make much sense to try yet again - * so hide the mm from the oom killer so that it can move on - * to another task with a different mm struct. - */ - p = find_lock_task_mm(tsk); - if (p) { - if (test_and_set_bit(MMF_OOM_NOT_REAPABLE, &p->mm->flags)) { - pr_info("oom_reaper: giving up pid:%d (%s)\n", - task_pid_nr(tsk), tsk->comm); - set_bit(MMF_OOM_REAPED, &p->mm->flags); - } - task_unlock(p); - } + pr_info("oom_reaper: unable to reap pid:%d (%s)\n", + task_pid_nr(tsk), tsk->comm); + debug_show_all_locks(); - debug_show_all_locks(); - } +done: + tsk->oom_reaper_list = NULL; /* - * Clear TIF_MEMDIE because the task shouldn't be sitting on a - * reasonably reclaimable memory anymore or it is not a good candidate - * for the oom victim right now because it cannot release its memory - * itself nor by the oom reaper. + * Hide this mm from OOM killer because it has been either reaped or + * somebody can't call up_write(mmap_sem). */ - tsk->oom_reaper_list = NULL; - exit_oom_victim(tsk); + set_bit(MMF_OOM_SKIP, &mm->flags); /* Drop a reference taken by wake_oom_reaper */ put_task_struct(tsk); @@ -607,8 +586,6 @@ static void oom_reap_task(struct task_struct *tsk) static int oom_reaper(void *unused) { - set_freezable(); - while (true) { struct task_struct *tsk = NULL; @@ -627,7 +604,7 @@ static int oom_reaper(void *unused) return 0; } -void wake_oom_reaper(struct task_struct *tsk) +static void wake_oom_reaper(struct task_struct *tsk) { if (!oom_reaper_th) return; @@ -656,7 +633,11 @@ static int __init oom_init(void) return 0; } subsys_initcall(oom_init) -#endif +#else +static inline void wake_oom_reaper(struct task_struct *tsk) +{ +} +#endif /* CONFIG_MMU */ /** * mark_oom_victim - mark the given task as OOM victim @@ -664,14 +645,23 @@ subsys_initcall(oom_init) * * Has to be called with oom_lock held and never after * oom has been disabled already. + * + * tsk->mm has to be non NULL and caller has to guarantee it is stable (either + * under task_lock or operate on the current). */ -void mark_oom_victim(struct task_struct *tsk) +static void mark_oom_victim(struct task_struct *tsk) { + struct mm_struct *mm = tsk->mm; + WARN_ON(oom_killer_disabled); /* OOM killer might race with memcg OOM */ if (test_and_set_tsk_thread_flag(tsk, TIF_MEMDIE)) return; - atomic_inc(&tsk->signal->oom_victims); + + /* oom_mm is bound to the signal struct life time. */ + if (!cmpxchg(&tsk->signal->oom_mm, NULL, mm)) + atomic_inc(&tsk->signal->oom_mm->mm_count); + /* * Make sure that the task is woken up from uninterruptible sleep * if it is frozen because OOM killer wouldn't be able to free @@ -685,21 +675,29 @@ void mark_oom_victim(struct task_struct *tsk) /** * exit_oom_victim - note the exit of an OOM victim */ -void exit_oom_victim(struct task_struct *tsk) +void exit_oom_victim(void) { - if (!test_and_clear_tsk_thread_flag(tsk, TIF_MEMDIE)) - return; - atomic_dec(&tsk->signal->oom_victims); + clear_thread_flag(TIF_MEMDIE); if (!atomic_dec_return(&oom_victims)) wake_up_all(&oom_victims_wait); } +/** + * oom_killer_enable - enable OOM killer + */ +void oom_killer_enable(void) +{ + oom_killer_disabled = false; +} + /** * oom_killer_disable - disable OOM killer + * @timeout: maximum timeout to wait for oom victims in jiffies * * Forces all page allocations to fail rather than trigger OOM killer. - * Will block and wait until all OOM victims are killed. + * Will block and wait until all OOM victims are killed or the given + * timeout expires. * * The function cannot be called when there are runnable user tasks because * the userspace would see unexpected allocation failures as a result. Any @@ -708,8 +706,10 @@ void exit_oom_victim(struct task_struct *tsk) * Returns true if successful and false if the OOM killer cannot be * disabled. */ -bool oom_killer_disable(void) +bool oom_killer_disable(signed long timeout) { + signed long ret; + /* * Make sure to not race with an ongoing OOM killer. Check that the * current is not killed (possibly due to sharing the victim's memory). @@ -719,19 +719,16 @@ bool oom_killer_disable(void) oom_killer_disabled = true; mutex_unlock(&oom_lock); - wait_event(oom_victims_wait, !atomic_read(&oom_victims)); + ret = wait_event_interruptible_timeout(oom_victims_wait, + !atomic_read(&oom_victims), timeout); + if (ret <= 0) { + oom_killer_enable(); + return false; + } return true; } -/** - * oom_killer_enable - enable OOM killer - */ -void oom_killer_enable(void) -{ - oom_killer_disabled = false; -} - static inline bool __task_will_free_mem(struct task_struct *task) { struct signal_struct *sig = task->signal; @@ -760,7 +757,7 @@ static inline bool __task_will_free_mem(struct task_struct *task) * Caller has to make sure that task->mm is stable (hold task_lock or * it operates on the current). */ -bool task_will_free_mem(struct task_struct *task) +static bool task_will_free_mem(struct task_struct *task) { struct mm_struct *mm = task->mm; struct task_struct *p; @@ -781,15 +778,16 @@ bool task_will_free_mem(struct task_struct *task) * This task has already been drained by the oom reaper so there are * only small chances it will free some more */ - if (test_bit(MMF_OOM_REAPED, &mm->flags)) + if (test_bit(MMF_OOM_SKIP, &mm->flags)) return false; if (atomic_read(&mm->mm_users) <= 1) return true; /* - * This is really pessimistic but we do not have any reliable way - * to check that external processes share with our mm + * Make sure that all tasks which share the mm with the given tasks + * are dying as well to make sure that a) nobody pins its mm and + * b) the task is also reapable by the oom reaper. */ rcu_read_lock(); for_each_process(p) { @@ -806,14 +804,10 @@ bool task_will_free_mem(struct task_struct *task) return ret; } -/* - * Must be called while holding a reference to p, which will be released upon - * returning. - */ -void oom_kill_process(struct oom_control *oc, struct task_struct *p, - unsigned int points, unsigned long totalpages, - const char *message) +static void oom_kill_process(struct oom_control *oc, const char *message) { + struct task_struct *p = oc->chosen; + unsigned int points = oc->chosen_points; struct task_struct *victim = p; struct task_struct *child; struct task_struct *t; @@ -860,7 +854,7 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p, * oom_badness() returns 0 if the thread is unkillable */ child_points = oom_badness(child, - oc->memcg, oc->nodemask, totalpages); + oc->memcg, oc->nodemask, oc->totalpages); if (child_points > victim_points) { put_task_struct(victim); victim = child; @@ -913,20 +907,20 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p, continue; if (same_thread_group(p, victim)) continue; - if (unlikely(p->flags & PF_KTHREAD) || is_global_init(p)) { - /* - * We cannot use oom_reaper for the mm shared by this - * process because it wouldn't get killed and so the - * memory might be still used. Hide the mm from the oom - * killer to guarantee OOM forward progress. - */ + if (is_global_init(p)) { can_oom_reap = false; - set_bit(MMF_OOM_REAPED, &mm->flags); + set_bit(MMF_OOM_SKIP, &mm->flags); pr_info("oom killer %d (%s) has mm pinned by %d (%s)\n", task_pid_nr(victim), victim->comm, task_pid_nr(p), p->comm); continue; } + /* + * No use_mm() user needs to read from the userspace so we are + * ok to reap it. + */ + if (unlikely(p->flags & PF_KTHREAD)) + continue; do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, true); } rcu_read_unlock(); @@ -942,7 +936,8 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p, /* * Determines whether the kernel must panic because of the panic_on_oom sysctl. */ -void check_panic_on_oom(struct oom_control *oc, enum oom_constraint constraint) +static void check_panic_on_oom(struct oom_control *oc, + enum oom_constraint constraint) { if (likely(!sysctl_panic_on_oom)) return; @@ -988,19 +983,18 @@ EXPORT_SYMBOL_GPL(unregister_oom_notifier); */ bool out_of_memory(struct oom_control *oc) { - struct task_struct *p; - unsigned long totalpages; unsigned long freed = 0; - unsigned int uninitialized_var(points); enum oom_constraint constraint = CONSTRAINT_NONE; if (oom_killer_disabled) return false; - blocking_notifier_call_chain(&oom_notify_list, 0, &freed); - if (freed > 0) - /* Got some memory back in the last second. */ - return true; + if (!is_memcg_oom(oc)) { + blocking_notifier_call_chain(&oom_notify_list, 0, &freed); + if (freed > 0) + /* Got some memory back in the last second. */ + return true; + } /* * If current has a pending SIGKILL or is exiting, then automatically @@ -1024,37 +1018,38 @@ bool out_of_memory(struct oom_control *oc) /* * Check if there were limitations on the allocation (only relevant for - * NUMA) that may require different handling. + * NUMA and memcg) that may require different handling. */ - constraint = constrained_alloc(oc, &totalpages); + constraint = constrained_alloc(oc); if (constraint != CONSTRAINT_MEMORY_POLICY) oc->nodemask = NULL; check_panic_on_oom(oc, constraint); - if (sysctl_oom_kill_allocating_task && current->mm && - !oom_unkillable_task(current, NULL, oc->nodemask) && + if (!is_memcg_oom(oc) && sysctl_oom_kill_allocating_task && + current->mm && !oom_unkillable_task(current, NULL, oc->nodemask) && current->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) { get_task_struct(current); - oom_kill_process(oc, current, 0, totalpages, - "Out of memory (oom_kill_allocating_task)"); + oc->chosen = current; + oom_kill_process(oc, "Out of memory (oom_kill_allocating_task)"); return true; } - p = select_bad_process(oc, &points, totalpages); + select_bad_process(oc); /* Found nothing?!?! Either we hang forever, or we panic. */ - if (!p && !is_sysrq_oom(oc)) { + if (!oc->chosen && !is_sysrq_oom(oc) && !is_memcg_oom(oc)) { dump_header(oc, NULL); panic("Out of memory and no killable processes...\n"); } - if (p && p != (void *)-1UL) { - oom_kill_process(oc, p, points, totalpages, "Out of memory"); + if (oc->chosen && oc->chosen != (void *)-1UL) { + oom_kill_process(oc, !is_memcg_oom(oc) ? "Out of memory" : + "Memory cgroup out of memory"); /* * Give the killed process a good chance to exit before trying * to allocate memory again. */ schedule_timeout_killable(1); } - return true; + return !!oc->chosen; } /* @@ -1077,16 +1072,6 @@ void pagefault_out_of_memory(void) if (!mutex_trylock(&oom_lock)) return; - - if (!out_of_memory(&oc)) { - /* - * There shouldn't be any user tasks runnable while the - * OOM killer is disabled, so the current task has to - * be a racing OOM victim for which oom_killer_disable() - * is waiting for. - */ - WARN_ON(test_thread_flag(TIF_MEMDIE)); - } - + out_of_memory(&oc); mutex_unlock(&oom_lock); } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 28d6f36a2d79..439cc63ad903 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1965,36 +1965,6 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb) return false; } -void throttle_vm_writeout(gfp_t gfp_mask) -{ - unsigned long background_thresh; - unsigned long dirty_thresh; - - for ( ; ; ) { - global_dirty_limits(&background_thresh, &dirty_thresh); - dirty_thresh = hard_dirty_limit(&global_wb_domain, dirty_thresh); - - /* - * Boost the allowable dirty threshold a bit for page - * allocators so they don't get DoS'ed by heavy writers - */ - dirty_thresh += dirty_thresh / 10; /* wheeee... */ - - if (global_node_page_state(NR_UNSTABLE_NFS) + - global_node_page_state(NR_WRITEBACK) <= dirty_thresh) - break; - congestion_wait(BLK_RW_ASYNC, HZ/10); - - /* - * The caller might hold locks which can prevent IO completion - * or progress in the filesystem. So we cannot just sit here - * waiting for IO to complete. - */ - if ((gfp_mask & (__GFP_FS|__GFP_IO)) != (__GFP_FS|__GFP_IO)) - break; - } -} - /* * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs */ @@ -2746,7 +2716,7 @@ int test_clear_page_writeback(struct page *page) int ret; lock_page_memcg(page); - if (mapping) { + if (mapping && mapping_use_writeback_tags(mapping)) { struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; @@ -2789,7 +2759,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write) int ret; lock_page_memcg(page); - if (mapping) { + if (mapping && mapping_use_writeback_tags(mapping)) { struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index a2214c64ed3c..ca423cc20b59 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -607,6 +607,9 @@ static bool need_debug_guardpage(void) if (!debug_pagealloc_enabled()) return false; + if (!debug_guardpage_minorder()) + return false; + return true; } @@ -615,6 +618,9 @@ static void init_debug_guardpage(void) if (!debug_pagealloc_enabled()) return; + if (!debug_guardpage_minorder()) + return; + _debug_guardpage_enabled = true; } @@ -635,19 +641,22 @@ static int __init debug_guardpage_minorder_setup(char *buf) pr_info("Setting debug_guardpage_minorder to %lu\n", res); return 0; } -__setup("debug_guardpage_minorder=", debug_guardpage_minorder_setup); +early_param("debug_guardpage_minorder", debug_guardpage_minorder_setup); -static inline void set_page_guard(struct zone *zone, struct page *page, +static inline bool set_page_guard(struct zone *zone, struct page *page, unsigned int order, int migratetype) { struct page_ext *page_ext; if (!debug_guardpage_enabled()) - return; + return false; + + if (order >= debug_guardpage_minorder()) + return false; page_ext = lookup_page_ext(page); if (unlikely(!page_ext)) - return; + return false; __set_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags); @@ -655,6 +664,8 @@ static inline void set_page_guard(struct zone *zone, struct page *page, set_page_private(page, order); /* Guard pages are not available for any usage */ __mod_zone_freepage_state(zone, -(1 << order), migratetype); + + return true; } static inline void clear_page_guard(struct zone *zone, struct page *page, @@ -676,9 +687,9 @@ static inline void clear_page_guard(struct zone *zone, struct page *page, __mod_zone_freepage_state(zone, (1 << order), migratetype); } #else -struct page_ext_operations debug_guardpage_ops = { NULL, }; -static inline void set_page_guard(struct zone *zone, struct page *page, - unsigned int order, int migratetype) {} +struct page_ext_operations debug_guardpage_ops; +static inline bool set_page_guard(struct zone *zone, struct page *page, + unsigned int order, int migratetype) { return false; } static inline void clear_page_guard(struct zone *zone, struct page *page, unsigned int order, int migratetype) {} #endif @@ -1393,15 +1404,18 @@ static void __init deferred_free_range(struct page *page, return; /* Free a large naturally-aligned chunk if possible */ - if (nr_pages == MAX_ORDER_NR_PAGES && - (pfn & (MAX_ORDER_NR_PAGES-1)) == 0) { + if (nr_pages == pageblock_nr_pages && + (pfn & (pageblock_nr_pages - 1)) == 0) { set_pageblock_migratetype(page, MIGRATE_MOVABLE); - __free_pages_boot_core(page, MAX_ORDER-1); + __free_pages_boot_core(page, pageblock_order); return; } - for (i = 0; i < nr_pages; i++, page++) + for (i = 0; i < nr_pages; i++, page++, pfn++) { + if ((pfn & (pageblock_nr_pages - 1)) == 0) + set_pageblock_migratetype(page, MIGRATE_MOVABLE); __free_pages_boot_core(page, 0); + } } /* Completion tracking for deferred_init_memmap() threads */ @@ -1469,9 +1483,9 @@ static int __init deferred_init_memmap(void *data) /* * Ensure pfn_valid is checked every - * MAX_ORDER_NR_PAGES for memory holes + * pageblock_nr_pages for memory holes */ - if ((pfn & (MAX_ORDER_NR_PAGES - 1)) == 0) { + if ((pfn & (pageblock_nr_pages - 1)) == 0) { if (!pfn_valid(pfn)) { page = NULL; goto free_range; @@ -1484,7 +1498,7 @@ static int __init deferred_init_memmap(void *data) } /* Minimise pfn page lookups and scheduler checks */ - if (page && (pfn & (MAX_ORDER_NR_PAGES - 1)) != 0) { + if (page && (pfn & (pageblock_nr_pages - 1)) != 0) { page++; } else { nr_pages += nr_to_free; @@ -1520,6 +1534,9 @@ free_range: free_base_page = NULL; free_base_pfn = nr_to_free = 0; } + /* Free the last block of pages to allocator */ + nr_pages += nr_to_free; + deferred_free_range(free_base_page, free_base_pfn, nr_to_free); first_init_pfn = max(end_pfn, first_init_pfn); } @@ -1616,18 +1633,15 @@ static inline void expand(struct zone *zone, struct page *page, size >>= 1; VM_BUG_ON_PAGE(bad_range(zone, &page[size]), &page[size]); - if (IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) && - debug_guardpage_enabled() && - high < debug_guardpage_minorder()) { - /* - * Mark as guard pages (or page), that will allow to - * merge back to allocator when buddy will be freed. - * Corresponding page table entries will not be touched, - * pages will stay not present in virtual address space - */ - set_page_guard(zone, &page[size], high, migratetype); + /* + * Mark as guard pages (or page), that will allow to + * merge back to allocator when buddy will be freed. + * Corresponding page table entries will not be touched, + * pages will stay not present in virtual address space + */ + if (set_page_guard(zone, &page[size], high, migratetype)) continue; - } + list_add(&page[size].lru, &area->free_list[migratetype]); area->nr_free++; set_page_order(&page[size], high); @@ -2489,9 +2503,14 @@ int __isolate_free_page(struct page *page, unsigned int order) mt = get_pageblock_migratetype(page); if (!is_migrate_isolate(mt)) { - /* Obey watermarks as if the page was being allocated */ - watermark = low_wmark_pages(zone) + (1 << order); - if (!zone_watermark_ok(zone, 0, watermark, 0, 0)) + /* + * Obey watermarks as if the page was being allocated. We can + * emulate a high-order watermark check with a raised order-0 + * watermark, because we already know our high-order page + * exists. + */ + watermark = min_wmark_pages(zone) + (1UL << order); + if (!zone_watermark_ok(zone, 0, watermark, 0, ALLOC_CMA)) return 0; __mod_zone_freepage_state(zone, -(1UL << order), mt); @@ -2960,9 +2979,11 @@ static DEFINE_RATELIMIT_STATE(nopage_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); -void warn_alloc_failed(gfp_t gfp_mask, unsigned int order, const char *fmt, ...) +void warn_alloc(gfp_t gfp_mask, const char *fmt, ...) { unsigned int filter = SHOW_MEM_FILTER_NODES; + struct va_format vaf; + va_list args; if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs) || debug_guardpage_minorder() > 0) @@ -2980,22 +3001,16 @@ void warn_alloc_failed(gfp_t gfp_mask, unsigned int order, const char *fmt, ...) if (in_interrupt() || !(gfp_mask & __GFP_DIRECT_RECLAIM)) filter &= ~SHOW_MEM_FILTER_NODES; - if (fmt) { - struct va_format vaf; - va_list args; + pr_warn("%s: ", current->comm); - va_start(args, fmt); + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + pr_cont("%pV", &vaf); + va_end(args); - vaf.fmt = fmt; - vaf.va = &args; + pr_cont(", mode:%#x(%pGg)\n", gfp_mask, &gfp_mask); - pr_warn("%pV", &vaf); - - va_end(args); - } - - pr_warn("%s: page allocation failure: order:%u, mode:%#x(%pGg)\n", - current->comm, order, gfp_mask, &gfp_mask); dump_stack(); if (!should_suppress_show_mem()) show_mem(filter); @@ -3137,6 +3152,65 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, return NULL; } +static inline bool +should_compact_retry(struct alloc_context *ac, int order, int alloc_flags, + enum compact_result compact_result, + enum compact_priority *compact_priority, + int *compaction_retries) +{ + int max_retries = MAX_COMPACT_RETRIES; + int min_priority; + + if (!order) + return false; + + if (compaction_made_progress(compact_result)) + (*compaction_retries)++; + + /* + * compaction considers all the zone as desperately out of memory + * so it doesn't really make much sense to retry except when the + * failure could be caused by insufficient priority + */ + if (compaction_failed(compact_result)) + goto check_priority; + + /* + * make sure the compaction wasn't deferred or didn't bail out early + * due to locks contention before we declare that we should give up. + * But do not retry if the given zonelist is not suitable for + * compaction. + */ + if (compaction_withdrawn(compact_result)) + return compaction_zonelist_suitable(ac, order, alloc_flags); + + /* + * !costly requests are much more important than __GFP_REPEAT + * costly ones because they are de facto nofail and invoke OOM + * killer to move on while costly can fail and users are ready + * to cope with that. 1/4 retries is rather arbitrary but we + * would need much more detailed feedback from compaction to + * make a better decision. + */ + if (order > PAGE_ALLOC_COSTLY_ORDER) + max_retries /= 4; + if (*compaction_retries <= max_retries) + return true; + + /* + * Make sure there are attempts at the highest priority if we exhausted + * all retries or failed at the lower priorities. + */ +check_priority: + min_priority = (order > PAGE_ALLOC_COSTLY_ORDER) ? + MIN_COMPACT_COSTLY_PRIORITY : MIN_COMPACT_PRIORITY; + if (*compact_priority > min_priority) { + (*compact_priority)--; + *compaction_retries = 0; + return true; + } + return false; +} #else static inline struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, @@ -3147,13 +3221,11 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, return NULL; } -#endif /* CONFIG_COMPACTION */ - static inline bool should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_flags, enum compact_result compact_result, enum compact_priority *compact_priority, - int compaction_retries) + int *compaction_retries) { struct zone *zone; struct zoneref *z; @@ -3175,6 +3247,7 @@ should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_fla } return false; } +#endif /* CONFIG_COMPACTION */ /* Perform direct synchronous page reclaim */ static int @@ -3325,16 +3398,26 @@ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask) static inline bool should_reclaim_retry(gfp_t gfp_mask, unsigned order, struct alloc_context *ac, int alloc_flags, - bool did_some_progress, int no_progress_loops) + bool did_some_progress, int *no_progress_loops) { struct zone *zone; struct zoneref *z; + /* + * Costly allocations might have made a progress but this doesn't mean + * their order will become available due to high fragmentation so + * always increment the no progress counter for them + */ + if (did_some_progress && order <= PAGE_ALLOC_COSTLY_ORDER) + *no_progress_loops = 0; + else + (*no_progress_loops)++; + /* * Make sure we converge to OOM if we cannot make any progress * several times in the row. */ - if (no_progress_loops > MAX_RECLAIM_RETRIES) + if (*no_progress_loops > MAX_RECLAIM_RETRIES) return false; /* @@ -3349,7 +3432,7 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order, unsigned long reclaimable; available = reclaimable = zone_reclaimable_pages(zone); - available -= DIV_ROUND_UP(no_progress_loops * available, + available -= DIV_ROUND_UP((*no_progress_loops) * available, MAX_RECLAIM_RETRIES); available += zone_page_state_snapshot(zone, NR_FREE_PAGES); @@ -3410,6 +3493,8 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, enum compact_result compact_result; int compaction_retries = 0; int no_progress_loops = 0; + unsigned long alloc_start = jiffies; + unsigned int stall_timeout = 10 * HZ; /* * In the slowpath, we sanity check order to avoid ever trying to @@ -3554,9 +3639,6 @@ retry: if (page) goto got_pg; - if (order && compaction_made_progress(compact_result)) - compaction_retries++; - /* Do not loop if specifically requested */ if (gfp_mask & __GFP_NORETRY) goto nopage; @@ -3568,18 +3650,16 @@ retry: if (order > PAGE_ALLOC_COSTLY_ORDER && !(gfp_mask & __GFP_REPEAT)) goto nopage; - /* - * Costly allocations might have made a progress but this doesn't mean - * their order will become available due to high fragmentation so - * always increment the no progress counter for them - */ - if (did_some_progress && order <= PAGE_ALLOC_COSTLY_ORDER) - no_progress_loops = 0; - else - no_progress_loops++; + /* Make sure we know about allocations which stall for too long */ + if (time_after(jiffies, alloc_start + stall_timeout)) { + warn_alloc(gfp_mask, + "page alloction stalls for %ums, order:%u\n", + jiffies_to_msecs(jiffies-alloc_start), order); + stall_timeout += 10 * HZ; + } if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags, - did_some_progress > 0, no_progress_loops)) + did_some_progress > 0, &no_progress_loops)) goto retry; /* @@ -3591,7 +3671,7 @@ retry: if (did_some_progress > 0 && should_compact_retry(ac, order, alloc_flags, compact_result, &compact_priority, - compaction_retries)) + &compaction_retries)) goto retry; /* Reclaim has failed us, start killing things */ @@ -3606,7 +3686,8 @@ retry: } nopage: - warn_alloc_failed(gfp_mask, order, NULL); + warn_alloc(gfp_mask, + "page allocation failure: order:%u", order); got_pg: return page; } @@ -4555,7 +4636,7 @@ static void build_zonelists_in_node_order(pg_data_t *pgdat, int node) int j; struct zonelist *zonelist; - zonelist = &pgdat->node_zonelists[0]; + zonelist = &pgdat->node_zonelists[ZONELIST_FALLBACK]; for (j = 0; zonelist->_zonerefs[j].zone != NULL; j++) ; j = build_zonelists_node(NODE_DATA(node), zonelist, j); @@ -4571,7 +4652,7 @@ static void build_thisnode_zonelists(pg_data_t *pgdat) int j; struct zonelist *zonelist; - zonelist = &pgdat->node_zonelists[1]; + zonelist = &pgdat->node_zonelists[ZONELIST_NOFALLBACK]; j = build_zonelists_node(pgdat, zonelist, 0); zonelist->_zonerefs[j].zone = NULL; zonelist->_zonerefs[j].zone_idx = 0; @@ -4592,7 +4673,7 @@ static void build_zonelists_in_zone_order(pg_data_t *pgdat, int nr_nodes) struct zone *z; struct zonelist *zonelist; - zonelist = &pgdat->node_zonelists[0]; + zonelist = &pgdat->node_zonelists[ZONELIST_FALLBACK]; pos = 0; for (zone_type = MAX_NR_ZONES - 1; zone_type >= 0; zone_type--) { for (j = 0; j < nr_nodes; j++) { @@ -4727,7 +4808,7 @@ static void build_zonelists(pg_data_t *pgdat) local_node = pgdat->node_id; - zonelist = &pgdat->node_zonelists[0]; + zonelist = &pgdat->node_zonelists[ZONELIST_FALLBACK]; j = build_zonelists_node(pgdat, zonelist, 0); /* @@ -4999,15 +5080,6 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, break; #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP - /* - * If not mirrored_kernelcore and ZONE_MOVABLE exists, range - * from zone_movable_pfn[nid] to end of each node should be - * ZONE_MOVABLE not ZONE_NORMAL. skip it. - */ - if (!mirrored_kernelcore && zone_movable_pfn[nid]) - if (zone == ZONE_NORMAL && pfn >= zone_movable_pfn[nid]) - continue; - /* * Check given memblock attribute by firmware which can affect * kernel memory layout. If zone==ZONE_MOVABLE but memory is @@ -5451,6 +5523,12 @@ static void __meminit adjust_zone_range_for_zone_movable(int nid, *zone_end_pfn = min(node_end_pfn, arch_zone_highest_possible_pfn[movable_zone]); + /* Adjust for ZONE_MOVABLE starting within this range */ + } else if (!mirrored_kernelcore && + *zone_start_pfn < zone_movable_pfn[nid] && + *zone_end_pfn > zone_movable_pfn[nid]) { + *zone_end_pfn = zone_movable_pfn[nid]; + /* Check if this whole range is within ZONE_MOVABLE */ } else if (*zone_start_pfn >= zone_movable_pfn[nid]) *zone_start_pfn = *zone_end_pfn; @@ -5554,28 +5632,23 @@ static unsigned long __meminit zone_absent_pages_in_node(int nid, * Treat pages to be ZONE_MOVABLE in ZONE_NORMAL as absent pages * and vice versa. */ - if (zone_movable_pfn[nid]) { - if (mirrored_kernelcore) { - unsigned long start_pfn, end_pfn; - struct memblock_region *r; + if (mirrored_kernelcore && zone_movable_pfn[nid]) { + unsigned long start_pfn, end_pfn; + struct memblock_region *r; - for_each_memblock(memory, r) { - start_pfn = clamp(memblock_region_memory_base_pfn(r), - zone_start_pfn, zone_end_pfn); - end_pfn = clamp(memblock_region_memory_end_pfn(r), - zone_start_pfn, zone_end_pfn); + for_each_memblock(memory, r) { + start_pfn = clamp(memblock_region_memory_base_pfn(r), + zone_start_pfn, zone_end_pfn); + end_pfn = clamp(memblock_region_memory_end_pfn(r), + zone_start_pfn, zone_end_pfn); - if (zone_type == ZONE_MOVABLE && - memblock_is_mirror(r)) - nr_absent += end_pfn - start_pfn; + if (zone_type == ZONE_MOVABLE && + memblock_is_mirror(r)) + nr_absent += end_pfn - start_pfn; - if (zone_type == ZONE_NORMAL && - !memblock_is_mirror(r)) - nr_absent += end_pfn - start_pfn; - } - } else { - if (zone_type == ZONE_NORMAL) - nr_absent += node_end_pfn - zone_movable_pfn[nid]; + if (zone_type == ZONE_NORMAL && + !memblock_is_mirror(r)) + nr_absent += end_pfn - start_pfn; } } @@ -6929,6 +7002,17 @@ static int __init set_hashdist(char *str) __setup("hashdist=", set_hashdist); #endif +#ifndef __HAVE_ARCH_RESERVED_KERNEL_PAGES +/* + * Returns the number of pages that arch has reserved but + * is not known to alloc_large_system_hash(). + */ +static unsigned long __init arch_reserved_kernel_pages(void) +{ + return 0; +} +#endif + /* * allocate a large system hash table from bootmem * - it is assumed that the hash table must contain an exact power-of-2 @@ -6953,6 +7037,7 @@ void *__init alloc_large_system_hash(const char *tablename, if (!numentries) { /* round applicable memory size up to nearest megabyte */ numentries = nr_kernel_pages; + numentries -= arch_reserved_kernel_pages(); /* It isn't necessary when PAGE_SIZE >= 1MB */ if (PAGE_SHIFT < 20) diff --git a/mm/page_ext.c b/mm/page_ext.c index 44a4c029c8e7..121dcffc4ec1 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -42,6 +42,11 @@ * and page extension core can skip to allocate memory. As result, * none of memory is wasted. * + * When need callback returns true, page_ext checks if there is a request for + * extra memory through size in struct page_ext_operations. If it is non-zero, + * extra space is allocated for each page_ext entry and offset is returned to + * user through offset in struct page_ext_operations. + * * The init callback is used to do proper initialization after page extension * is completely initialized. In sparse memory system, extra memory is * allocated some time later than memmap is allocated. In other words, lifetime @@ -66,18 +71,24 @@ static struct page_ext_operations *page_ext_ops[] = { }; static unsigned long total_usage; +static unsigned long extra_mem; static bool __init invoke_need_callbacks(void) { int i; int entries = ARRAY_SIZE(page_ext_ops); + bool need = false; for (i = 0; i < entries; i++) { - if (page_ext_ops[i]->need && page_ext_ops[i]->need()) - return true; + if (page_ext_ops[i]->need && page_ext_ops[i]->need()) { + page_ext_ops[i]->offset = sizeof(struct page_ext) + + extra_mem; + extra_mem += page_ext_ops[i]->size; + need = true; + } } - return false; + return need; } static void __init invoke_init_callbacks(void) @@ -91,6 +102,16 @@ static void __init invoke_init_callbacks(void) } } +static unsigned long get_entry_size(void) +{ + return sizeof(struct page_ext) + extra_mem; +} + +static inline struct page_ext *get_entry(void *base, unsigned long index) +{ + return base + get_entry_size() * index; +} + #if !defined(CONFIG_SPARSEMEM) @@ -102,7 +123,7 @@ void __meminit pgdat_page_ext_init(struct pglist_data *pgdat) struct page_ext *lookup_page_ext(struct page *page) { unsigned long pfn = page_to_pfn(page); - unsigned long offset; + unsigned long index; struct page_ext *base; base = NODE_DATA(page_to_nid(page))->node_page_ext; @@ -119,9 +140,9 @@ struct page_ext *lookup_page_ext(struct page *page) if (unlikely(!base)) return NULL; #endif - offset = pfn - round_down(node_start_pfn(page_to_nid(page)), + index = pfn - round_down(node_start_pfn(page_to_nid(page)), MAX_ORDER_NR_PAGES); - return base + offset; + return get_entry(base, index); } static int __init alloc_node_page_ext(int nid) @@ -143,7 +164,7 @@ static int __init alloc_node_page_ext(int nid) !IS_ALIGNED(node_end_pfn(nid), MAX_ORDER_NR_PAGES)) nr_pages += MAX_ORDER_NR_PAGES; - table_size = sizeof(struct page_ext) * nr_pages; + table_size = get_entry_size() * nr_pages; base = memblock_virt_alloc_try_nid_nopanic( table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), @@ -196,7 +217,7 @@ struct page_ext *lookup_page_ext(struct page *page) if (!section->page_ext) return NULL; #endif - return section->page_ext + pfn; + return get_entry(section->page_ext, pfn); } static void *__meminit alloc_page_ext(size_t size, int nid) @@ -229,7 +250,7 @@ static int __meminit init_section_page_ext(unsigned long pfn, int nid) if (section->page_ext) return 0; - table_size = sizeof(struct page_ext) * PAGES_PER_SECTION; + table_size = get_entry_size() * PAGES_PER_SECTION; base = alloc_page_ext(table_size, nid); /* @@ -249,7 +270,7 @@ static int __meminit init_section_page_ext(unsigned long pfn, int nid) * we need to apply a mask. */ pfn &= PAGE_SECTION_MASK; - section->page_ext = base - pfn; + section->page_ext = (void *)base - get_entry_size() * pfn; total_usage += table_size; return 0; } @@ -262,7 +283,7 @@ static void free_page_ext(void *addr) struct page *page = virt_to_page(addr); size_t table_size; - table_size = sizeof(struct page_ext) * PAGES_PER_SECTION; + table_size = get_entry_size() * PAGES_PER_SECTION; BUG_ON(PageReserved(page)); free_pages_exact(addr, table_size); @@ -277,7 +298,7 @@ static void __free_page_ext(unsigned long pfn) ms = __pfn_to_section(pfn); if (!ms || !ms->page_ext) return; - base = ms->page_ext + pfn; + base = get_entry(ms->page_ext, pfn); free_page_ext(base); ms->page_ext = NULL; } diff --git a/mm/page_io.c b/mm/page_io.c index eafe5ddc2b54..a2651f58c86a 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -264,7 +264,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, int ret; struct swap_info_struct *sis = page_swap_info(page); - BUG_ON(!PageSwapCache(page)); + VM_BUG_ON_PAGE(!PageSwapCache(page), page); if (sis->flags & SWP_FILE) { struct kiocb kiocb; struct file *swap_file = sis->swap_file; @@ -338,7 +338,7 @@ int swap_readpage(struct page *page) int ret = 0; struct swap_info_struct *sis = page_swap_info(page); - BUG_ON(!PageSwapCache(page)); + VM_BUG_ON_PAGE(!PageSwapCache(page), page); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageUptodate(page), page); if (frontswap_load(page) == 0) { @@ -388,7 +388,8 @@ int swap_set_page_dirty(struct page *page) if (sis->flags & SWP_FILE) { struct address_space *mapping = sis->swap_file->f_mapping; - BUG_ON(!PageSwapCache(page)); + + VM_BUG_ON_PAGE(!PageSwapCache(page), page); return mapping->a_ops->set_page_dirty(page); } else { return __set_page_dirty_no_writeback(page); diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 064b7fb6e0b5..a5594bfcc5ed 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -55,7 +55,7 @@ static int set_migratetype_isolate(struct page *page, ret = 0; /* - * immobile means "not-on-lru" paes. If immobile is larger than + * immobile means "not-on-lru" pages. If immobile is larger than * removable-by-driver pages reported by notifier, we'll fail. */ diff --git a/mm/page_owner.c b/mm/page_owner.c index ec6dc1886f71..60634dc53a88 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -8,6 +8,7 @@ #include #include #include +#include #include "internal.h" @@ -17,6 +18,13 @@ */ #define PAGE_OWNER_STACK_DEPTH (16) +struct page_owner { + unsigned int order; + gfp_t gfp_mask; + int last_migrate_reason; + depot_stack_handle_t handle; +}; + static bool page_owner_disabled = true; DEFINE_STATIC_KEY_FALSE(page_owner_inited); @@ -85,10 +93,16 @@ static void init_page_owner(void) } struct page_ext_operations page_owner_ops = { + .size = sizeof(struct page_owner), .need = need_page_owner, .init = init_page_owner, }; +static inline struct page_owner *get_page_owner(struct page_ext *page_ext) +{ + return (void *)page_ext + page_owner_ops.offset; +} + void __reset_page_owner(struct page *page, unsigned int order) { int i; @@ -155,14 +169,16 @@ noinline void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask) { struct page_ext *page_ext = lookup_page_ext(page); + struct page_owner *page_owner; if (unlikely(!page_ext)) return; - page_ext->handle = save_stack(gfp_mask); - page_ext->order = order; - page_ext->gfp_mask = gfp_mask; - page_ext->last_migrate_reason = -1; + page_owner = get_page_owner(page_ext); + page_owner->handle = save_stack(gfp_mask); + page_owner->order = order; + page_owner->gfp_mask = gfp_mask; + page_owner->last_migrate_reason = -1; __set_bit(PAGE_EXT_OWNER, &page_ext->flags); } @@ -170,21 +186,26 @@ noinline void __set_page_owner(struct page *page, unsigned int order, void __set_page_owner_migrate_reason(struct page *page, int reason) { struct page_ext *page_ext = lookup_page_ext(page); + struct page_owner *page_owner; + if (unlikely(!page_ext)) return; - page_ext->last_migrate_reason = reason; + page_owner = get_page_owner(page_ext); + page_owner->last_migrate_reason = reason; } void __split_page_owner(struct page *page, unsigned int order) { int i; struct page_ext *page_ext = lookup_page_ext(page); + struct page_owner *page_owner; if (unlikely(!page_ext)) return; - page_ext->order = 0; + page_owner = get_page_owner(page_ext); + page_owner->order = 0; for (i = 1; i < (1 << order); i++) __copy_page_owner(page, page + i); } @@ -193,14 +214,18 @@ void __copy_page_owner(struct page *oldpage, struct page *newpage) { struct page_ext *old_ext = lookup_page_ext(oldpage); struct page_ext *new_ext = lookup_page_ext(newpage); + struct page_owner *old_page_owner, *new_page_owner; if (unlikely(!old_ext || !new_ext)) return; - new_ext->order = old_ext->order; - new_ext->gfp_mask = old_ext->gfp_mask; - new_ext->last_migrate_reason = old_ext->last_migrate_reason; - new_ext->handle = old_ext->handle; + old_page_owner = get_page_owner(old_ext); + new_page_owner = get_page_owner(new_ext); + new_page_owner->order = old_page_owner->order; + new_page_owner->gfp_mask = old_page_owner->gfp_mask; + new_page_owner->last_migrate_reason = + old_page_owner->last_migrate_reason; + new_page_owner->handle = old_page_owner->handle; /* * We don't clear the bit on the oldpage as it's going to be freed @@ -214,9 +239,88 @@ void __copy_page_owner(struct page *oldpage, struct page *newpage) __set_bit(PAGE_EXT_OWNER, &new_ext->flags); } +void pagetypeinfo_showmixedcount_print(struct seq_file *m, + pg_data_t *pgdat, struct zone *zone) +{ + struct page *page; + struct page_ext *page_ext; + struct page_owner *page_owner; + unsigned long pfn = zone->zone_start_pfn, block_end_pfn; + unsigned long end_pfn = pfn + zone->spanned_pages; + unsigned long count[MIGRATE_TYPES] = { 0, }; + int pageblock_mt, page_mt; + int i; + + /* Scan block by block. First and last block may be incomplete */ + pfn = zone->zone_start_pfn; + + /* + * Walk the zone in pageblock_nr_pages steps. If a page block spans + * a zone boundary, it will be double counted between zones. This does + * not matter as the mixed block count will still be correct + */ + for (; pfn < end_pfn; ) { + if (!pfn_valid(pfn)) { + pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES); + continue; + } + + block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); + block_end_pfn = min(block_end_pfn, end_pfn); + + page = pfn_to_page(pfn); + pageblock_mt = get_pageblock_migratetype(page); + + for (; pfn < block_end_pfn; pfn++) { + if (!pfn_valid_within(pfn)) + continue; + + page = pfn_to_page(pfn); + + if (page_zone(page) != zone) + continue; + + if (PageBuddy(page)) { + pfn += (1UL << page_order(page)) - 1; + continue; + } + + if (PageReserved(page)) + continue; + + page_ext = lookup_page_ext(page); + if (unlikely(!page_ext)) + continue; + + if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) + continue; + + page_owner = get_page_owner(page_ext); + page_mt = gfpflags_to_migratetype( + page_owner->gfp_mask); + if (pageblock_mt != page_mt) { + if (is_migrate_cma(pageblock_mt)) + count[MIGRATE_MOVABLE]++; + else + count[pageblock_mt]++; + + pfn = block_end_pfn; + break; + } + pfn += (1UL << page_owner->order) - 1; + } + } + + /* Print counts */ + seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name); + for (i = 0; i < MIGRATE_TYPES; i++) + seq_printf(m, "%12lu ", count[i]); + seq_putc(m, '\n'); +} + static ssize_t print_page_owner(char __user *buf, size_t count, unsigned long pfn, - struct page *page, struct page_ext *page_ext, + struct page *page, struct page_owner *page_owner, depot_stack_handle_t handle) { int ret; @@ -236,15 +340,15 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn, ret = snprintf(kbuf, count, "Page allocated via order %u, mask %#x(%pGg)\n", - page_ext->order, page_ext->gfp_mask, - &page_ext->gfp_mask); + page_owner->order, page_owner->gfp_mask, + &page_owner->gfp_mask); if (ret >= count) goto err; /* Print information relevant to grouping pages by mobility */ pageblock_mt = get_pageblock_migratetype(page); - page_mt = gfpflags_to_migratetype(page_ext->gfp_mask); + page_mt = gfpflags_to_migratetype(page_owner->gfp_mask); ret += snprintf(kbuf + ret, count - ret, "PFN %lu type %s Block %lu type %s Flags %#lx(%pGp)\n", pfn, @@ -261,10 +365,10 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn, if (ret >= count) goto err; - if (page_ext->last_migrate_reason != -1) { + if (page_owner->last_migrate_reason != -1) { ret += snprintf(kbuf + ret, count - ret, "Page has been migrated, last migrate reason: %s\n", - migrate_reason_names[page_ext->last_migrate_reason]); + migrate_reason_names[page_owner->last_migrate_reason]); if (ret >= count) goto err; } @@ -287,6 +391,7 @@ err: void __dump_page_owner(struct page *page) { struct page_ext *page_ext = lookup_page_ext(page); + struct page_owner *page_owner; unsigned long entries[PAGE_OWNER_STACK_DEPTH]; struct stack_trace trace = { .nr_entries = 0, @@ -302,7 +407,9 @@ void __dump_page_owner(struct page *page) pr_alert("There is not page extension available.\n"); return; } - gfp_mask = page_ext->gfp_mask; + + page_owner = get_page_owner(page_ext); + gfp_mask = page_owner->gfp_mask; mt = gfpflags_to_migratetype(gfp_mask); if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) { @@ -310,7 +417,7 @@ void __dump_page_owner(struct page *page) return; } - handle = READ_ONCE(page_ext->handle); + handle = READ_ONCE(page_owner->handle); if (!handle) { pr_alert("page_owner info is not active (free page?)\n"); return; @@ -318,12 +425,12 @@ void __dump_page_owner(struct page *page) depot_fetch_stack(handle, &trace); pr_alert("page allocated via order %u, migratetype %s, gfp_mask %#x(%pGg)\n", - page_ext->order, migratetype_names[mt], gfp_mask, &gfp_mask); + page_owner->order, migratetype_names[mt], gfp_mask, &gfp_mask); print_stack_trace(&trace, 0); - if (page_ext->last_migrate_reason != -1) + if (page_owner->last_migrate_reason != -1) pr_alert("page has been migrated, last migrate reason: %s\n", - migrate_reason_names[page_ext->last_migrate_reason]); + migrate_reason_names[page_owner->last_migrate_reason]); } static ssize_t @@ -332,6 +439,7 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos) unsigned long pfn; struct page *page; struct page_ext *page_ext; + struct page_owner *page_owner; depot_stack_handle_t handle; if (!static_branch_unlikely(&page_owner_inited)) @@ -381,11 +489,13 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos) if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) continue; + page_owner = get_page_owner(page_ext); + /* * Access to page_ext->handle isn't synchronous so we should * be careful to access it. */ - handle = READ_ONCE(page_ext->handle); + handle = READ_ONCE(page_owner->handle); if (!handle) continue; @@ -393,7 +503,7 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos) *ppos = (pfn - min_low_pfn) + 1; return print_page_owner(buf, count, pfn, page, - page_ext, handle); + page_owner, handle); } return 0; diff --git a/mm/shmem.c b/mm/shmem.c index d86b5e455fef..0e9901e69d24 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -3965,7 +3965,7 @@ EXPORT_SYMBOL_GPL(shmem_truncate_range); /* common code */ -static struct dentry_operations anon_ops = { +static const struct dentry_operations anon_ops = { .d_dname = simple_dname }; diff --git a/mm/swap.c b/mm/swap.c index 75c63bb2a1da..4dcf852e1e6d 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -748,10 +748,8 @@ void release_pages(struct page **pages, int nr, bool cold) locked_pgdat = NULL; } - if (is_huge_zero_page(page)) { - put_huge_zero_page(); + if (is_huge_zero_page(page)) continue; - } page = compound_head(page); if (!put_page_testzero(page)) diff --git a/mm/swap_state.c b/mm/swap_state.c index c8310a37be3a..35d7e0ee1c77 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -37,6 +37,8 @@ struct address_space swapper_spaces[MAX_SWAPFILES] = { .page_tree = RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN), .i_mmap_writable = ATOMIC_INIT(0), .a_ops = &swap_aops, + /* swap cache doesn't use writeback related tags */ + .flags = 1 << AS_NO_WRITEBACK_TAGS, } }; @@ -92,7 +94,7 @@ int __add_to_swap_cache(struct page *page, swp_entry_t entry) address_space = swap_address_space(entry); spin_lock_irq(&address_space->tree_lock); error = radix_tree_insert(&address_space->page_tree, - entry.val, page); + swp_offset(entry), page); if (likely(!error)) { address_space->nrpages++; __inc_node_page_state(page, NR_FILE_PAGES); @@ -143,7 +145,7 @@ void __delete_from_swap_cache(struct page *page) entry.val = page_private(page); address_space = swap_address_space(entry); - radix_tree_delete(&address_space->page_tree, page_private(page)); + radix_tree_delete(&address_space->page_tree, swp_offset(entry)); set_page_private(page, 0); ClearPageSwapCache(page); address_space->nrpages--; @@ -252,9 +254,7 @@ static inline void free_swap_cache(struct page *page) void free_page_and_swap_cache(struct page *page) { free_swap_cache(page); - if (is_huge_zero_page(page)) - put_huge_zero_page(); - else + if (!is_huge_zero_page(page)) put_page(page); } @@ -283,7 +283,7 @@ struct page * lookup_swap_cache(swp_entry_t entry) { struct page *page; - page = find_get_page(swap_address_space(entry), entry.val); + page = find_get_page(swap_address_space(entry), swp_offset(entry)); if (page) { INC_CACHE_INFO(find_success); @@ -310,7 +310,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, * called after lookup_swap_cache() failed, re-calling * that would confuse statistics. */ - found_page = find_get_page(swapper_space, entry.val); + found_page = find_get_page(swapper_space, swp_offset(entry)); if (found_page) break; diff --git a/mm/swapfile.c b/mm/swapfile.c index 2657accc6e2b..2210de290b54 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -105,7 +105,7 @@ __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset) struct page *page; int ret = 0; - page = find_get_page(swap_address_space(entry), entry.val); + page = find_get_page(swap_address_space(entry), swp_offset(entry)); if (!page) return 0; /* @@ -257,6 +257,53 @@ static inline void cluster_set_null(struct swap_cluster_info *info) info->data = 0; } +static inline bool cluster_list_empty(struct swap_cluster_list *list) +{ + return cluster_is_null(&list->head); +} + +static inline unsigned int cluster_list_first(struct swap_cluster_list *list) +{ + return cluster_next(&list->head); +} + +static void cluster_list_init(struct swap_cluster_list *list) +{ + cluster_set_null(&list->head); + cluster_set_null(&list->tail); +} + +static void cluster_list_add_tail(struct swap_cluster_list *list, + struct swap_cluster_info *ci, + unsigned int idx) +{ + if (cluster_list_empty(list)) { + cluster_set_next_flag(&list->head, idx, 0); + cluster_set_next_flag(&list->tail, idx, 0); + } else { + unsigned int tail = cluster_next(&list->tail); + + cluster_set_next(&ci[tail], idx); + cluster_set_next_flag(&list->tail, idx, 0); + } +} + +static unsigned int cluster_list_del_first(struct swap_cluster_list *list, + struct swap_cluster_info *ci) +{ + unsigned int idx; + + idx = cluster_next(&list->head); + if (cluster_next(&list->tail) == idx) { + cluster_set_null(&list->head); + cluster_set_null(&list->tail); + } else + cluster_set_next_flag(&list->head, + cluster_next(&ci[idx]), 0); + + return idx; +} + /* Add a cluster to discard list and schedule it to do discard */ static void swap_cluster_schedule_discard(struct swap_info_struct *si, unsigned int idx) @@ -270,17 +317,7 @@ static void swap_cluster_schedule_discard(struct swap_info_struct *si, memset(si->swap_map + idx * SWAPFILE_CLUSTER, SWAP_MAP_BAD, SWAPFILE_CLUSTER); - if (cluster_is_null(&si->discard_cluster_head)) { - cluster_set_next_flag(&si->discard_cluster_head, - idx, 0); - cluster_set_next_flag(&si->discard_cluster_tail, - idx, 0); - } else { - unsigned int tail = cluster_next(&si->discard_cluster_tail); - cluster_set_next(&si->cluster_info[tail], idx); - cluster_set_next_flag(&si->discard_cluster_tail, - idx, 0); - } + cluster_list_add_tail(&si->discard_clusters, si->cluster_info, idx); schedule_work(&si->discard_work); } @@ -296,15 +333,8 @@ static void swap_do_scheduled_discard(struct swap_info_struct *si) info = si->cluster_info; - while (!cluster_is_null(&si->discard_cluster_head)) { - idx = cluster_next(&si->discard_cluster_head); - - cluster_set_next_flag(&si->discard_cluster_head, - cluster_next(&info[idx]), 0); - if (cluster_next(&si->discard_cluster_tail) == idx) { - cluster_set_null(&si->discard_cluster_head); - cluster_set_null(&si->discard_cluster_tail); - } + while (!cluster_list_empty(&si->discard_clusters)) { + idx = cluster_list_del_first(&si->discard_clusters, info); spin_unlock(&si->lock); discard_swap_cluster(si, idx * SWAPFILE_CLUSTER, @@ -312,19 +342,7 @@ static void swap_do_scheduled_discard(struct swap_info_struct *si) spin_lock(&si->lock); cluster_set_flag(&info[idx], CLUSTER_FLAG_FREE); - if (cluster_is_null(&si->free_cluster_head)) { - cluster_set_next_flag(&si->free_cluster_head, - idx, 0); - cluster_set_next_flag(&si->free_cluster_tail, - idx, 0); - } else { - unsigned int tail; - - tail = cluster_next(&si->free_cluster_tail); - cluster_set_next(&info[tail], idx); - cluster_set_next_flag(&si->free_cluster_tail, - idx, 0); - } + cluster_list_add_tail(&si->free_clusters, info, idx); memset(si->swap_map + idx * SWAPFILE_CLUSTER, 0, SWAPFILE_CLUSTER); } @@ -353,13 +371,8 @@ static void inc_cluster_info_page(struct swap_info_struct *p, if (!cluster_info) return; if (cluster_is_free(&cluster_info[idx])) { - VM_BUG_ON(cluster_next(&p->free_cluster_head) != idx); - cluster_set_next_flag(&p->free_cluster_head, - cluster_next(&cluster_info[idx]), 0); - if (cluster_next(&p->free_cluster_tail) == idx) { - cluster_set_null(&p->free_cluster_tail); - cluster_set_null(&p->free_cluster_head); - } + VM_BUG_ON(cluster_list_first(&p->free_clusters) != idx); + cluster_list_del_first(&p->free_clusters, cluster_info); cluster_set_count_flag(&cluster_info[idx], 0, 0); } @@ -398,14 +411,7 @@ static void dec_cluster_info_page(struct swap_info_struct *p, } cluster_set_flag(&cluster_info[idx], CLUSTER_FLAG_FREE); - if (cluster_is_null(&p->free_cluster_head)) { - cluster_set_next_flag(&p->free_cluster_head, idx, 0); - cluster_set_next_flag(&p->free_cluster_tail, idx, 0); - } else { - unsigned int tail = cluster_next(&p->free_cluster_tail); - cluster_set_next(&cluster_info[tail], idx); - cluster_set_next_flag(&p->free_cluster_tail, idx, 0); - } + cluster_list_add_tail(&p->free_clusters, cluster_info, idx); } } @@ -421,8 +427,8 @@ scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si, bool conflict; offset /= SWAPFILE_CLUSTER; - conflict = !cluster_is_null(&si->free_cluster_head) && - offset != cluster_next(&si->free_cluster_head) && + conflict = !cluster_list_empty(&si->free_clusters) && + offset != cluster_list_first(&si->free_clusters) && cluster_is_free(&si->cluster_info[offset]); if (!conflict) @@ -447,11 +453,11 @@ static void scan_swap_map_try_ssd_cluster(struct swap_info_struct *si, new_cluster: cluster = this_cpu_ptr(si->percpu_cluster); if (cluster_is_null(&cluster->index)) { - if (!cluster_is_null(&si->free_cluster_head)) { - cluster->index = si->free_cluster_head; + if (!cluster_list_empty(&si->free_clusters)) { + cluster->index = si->free_clusters.head; cluster->next = cluster_next(&cluster->index) * SWAPFILE_CLUSTER; - } else if (!cluster_is_null(&si->discard_cluster_head)) { + } else if (!cluster_list_empty(&si->discard_clusters)) { /* * we don't have free cluster but have some clusters in * discarding, do discard now and reclaim them @@ -999,7 +1005,7 @@ int free_swap_and_cache(swp_entry_t entry) if (p) { if (swap_entry_free(p, entry, 1) == SWAP_HAS_CACHE) { page = find_get_page(swap_address_space(entry), - entry.val); + swp_offset(entry)); if (page && !trylock_page(page)) { put_page(page); page = NULL; @@ -2292,10 +2298,8 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p, nr_good_pages = maxpages - 1; /* omit header page */ - cluster_set_null(&p->free_cluster_head); - cluster_set_null(&p->free_cluster_tail); - cluster_set_null(&p->discard_cluster_head); - cluster_set_null(&p->discard_cluster_tail); + cluster_list_init(&p->free_clusters); + cluster_list_init(&p->discard_clusters); for (i = 0; i < swap_header->info.nr_badpages; i++) { unsigned int page_nr = swap_header->info.badpages[i]; @@ -2341,19 +2345,8 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p, for (i = 0; i < nr_clusters; i++) { if (!cluster_count(&cluster_info[idx])) { cluster_set_flag(&cluster_info[idx], CLUSTER_FLAG_FREE); - if (cluster_is_null(&p->free_cluster_head)) { - cluster_set_next_flag(&p->free_cluster_head, - idx, 0); - cluster_set_next_flag(&p->free_cluster_tail, - idx, 0); - } else { - unsigned int tail; - - tail = cluster_next(&p->free_cluster_tail); - cluster_set_next(&cluster_info[tail], idx); - cluster_set_next_flag(&p->free_cluster_tail, - idx, 0); - } + cluster_list_add_tail(&p->free_clusters, cluster_info, + idx); } idx++; if (idx == nr_clusters) diff --git a/mm/vmacache.c b/mm/vmacache.c index fd09dc9c6812..035fdeb35b43 100644 --- a/mm/vmacache.c +++ b/mm/vmacache.c @@ -87,11 +87,11 @@ struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr) { int i; + count_vm_vmacache_event(VMACACHE_FIND_CALLS); + if (!vmacache_valid(mm)) return NULL; - count_vm_vmacache_event(VMACACHE_FIND_CALLS); - for (i = 0; i < VMACACHE_SIZE; i++) { struct vm_area_struct *vma = current->vmacache[i]; @@ -115,11 +115,11 @@ struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, { int i; + count_vm_vmacache_event(VMACACHE_FIND_CALLS); + if (!vmacache_valid(mm)) return NULL; - count_vm_vmacache_event(VMACACHE_FIND_CALLS); - for (i = 0; i < VMACACHE_SIZE; i++) { struct vm_area_struct *vma = current->vmacache[i]; diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 91f44e78c516..f2481cb4e6b2 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1359,14 +1359,14 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, struct vm_struct *area; BUG_ON(in_interrupt()); - if (flags & VM_IOREMAP) - align = 1ul << clamp_t(int, fls_long(size), - PAGE_SHIFT, IOREMAP_MAX_ORDER); - size = PAGE_ALIGN(size); if (unlikely(!size)) return NULL; + if (flags & VM_IOREMAP) + align = 1ul << clamp_t(int, get_count_order_long(size), + PAGE_SHIFT, IOREMAP_MAX_ORDER); + area = kzalloc_node(sizeof(*area), gfp_mask & GFP_RECLAIM_MASK, node); if (unlikely(!area)) return NULL; @@ -1601,7 +1601,6 @@ static void *__vmalloc_node(unsigned long size, unsigned long align, static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot, int node) { - const int order = 0; struct page **pages; unsigned int nr_pages, array_size, i; const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO; @@ -1629,9 +1628,9 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, struct page *page; if (node == NUMA_NO_NODE) - page = alloc_pages(alloc_mask, order); + page = alloc_page(alloc_mask); else - page = alloc_pages_node(node, alloc_mask, order); + page = alloc_pages_node(node, alloc_mask, 0); if (unlikely(!page)) { /* Successfully allocated i pages, free them in __vunmap() */ @@ -1648,8 +1647,8 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, return area->addr; fail: - warn_alloc_failed(gfp_mask, order, - "vmalloc: allocation failure, allocated %ld of %ld bytes\n", + warn_alloc(gfp_mask, + "vmalloc: allocation failure, allocated %ld of %ld bytes", (area->nr_pages*PAGE_SIZE), area->size); vfree(area->addr); return NULL; @@ -1710,9 +1709,8 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, return addr; fail: - warn_alloc_failed(gfp_mask, 0, - "vmalloc: allocation failure: %lu bytes\n", - real_size); + warn_alloc(gfp_mask, + "vmalloc: allocation failure: %lu bytes", real_size); return NULL; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 0fe8b7113868..744f926af442 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2418,8 +2418,6 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc if (inactive_list_is_low(lruvec, false, sc)) shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); - - throttle_vm_writeout(sc->gfp_mask); } /* Use reclaim/compaction for costly allocs or under memory pressure */ @@ -2480,7 +2478,7 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat, * If we have not reclaimed enough pages for compaction and the * inactive lists are large enough, continue reclaiming */ - pages_for_compaction = (2UL << sc->order); + pages_for_compaction = compact_gap(sc->order); inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE); if (get_nr_swap_pages() > 0) inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON); @@ -2495,7 +2493,7 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat, continue; switch (compaction_suitable(zone, sc->order, 0, sc->reclaim_idx)) { - case COMPACT_PARTIAL: + case COMPACT_SUCCESS: case COMPACT_CONTINUE: return false; default: @@ -2598,38 +2596,35 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc) } /* - * Returns true if compaction should go ahead for a high-order request, or - * the high-order allocation would succeed without compaction. + * Returns true if compaction should go ahead for a costly-order request, or + * the allocation would already succeed without compaction. Return false if we + * should reclaim first. */ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) { unsigned long watermark; - bool watermark_ok; + enum compact_result suitable; - /* - * Compaction takes time to run and there are potentially other - * callers using the pages just freed. Continue reclaiming until - * there is a buffer of free pages available to give compaction - * a reasonable chance of completing and allocating the page - */ - watermark = high_wmark_pages(zone) + (2UL << sc->order); - watermark_ok = zone_watermark_ok_safe(zone, 0, watermark, sc->reclaim_idx); - - /* - * If compaction is deferred, reclaim up to a point where - * compaction will have a chance of success when re-enabled - */ - if (compaction_deferred(zone, sc->order)) - return watermark_ok; - - /* - * If compaction is not ready to start and allocation is not likely - * to succeed without it, then keep reclaiming. - */ - if (compaction_suitable(zone, sc->order, 0, sc->reclaim_idx) == COMPACT_SKIPPED) + suitable = compaction_suitable(zone, sc->order, 0, sc->reclaim_idx); + if (suitable == COMPACT_SUCCESS) + /* Allocation should succeed already. Don't reclaim. */ + return true; + if (suitable == COMPACT_SKIPPED) + /* Compaction cannot yet proceed. Do reclaim. */ return false; - return watermark_ok; + /* + * Compaction is already possible, but it takes time to run and there + * are potentially other callers using the pages just freed. So proceed + * with reclaim to make a buffer of free pages available to give + * compaction a reasonable chance of completing and allocating the page. + * Note that we won't actually reclaim the whole buffer in one attempt + * as the target watermark in should_continue_reclaim() is lower. But if + * we are already above the high+gap watermark, don't reclaim at all. + */ + watermark = high_wmark_pages(zone) + compact_gap(sc->order); + + return zone_watermark_ok_safe(zone, 0, watermark, sc->reclaim_idx); } /* @@ -3041,7 +3036,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, */ nid = mem_cgroup_select_victim_node(memcg); - zonelist = NODE_DATA(nid)->node_zonelists; + zonelist = &NODE_DATA(nid)->node_zonelists[ZONELIST_FALLBACK]; trace_mm_vmscan_memcg_reclaim_begin(0, sc.may_writepage, @@ -3169,7 +3164,7 @@ static bool kswapd_shrink_node(pg_data_t *pgdat, * excessive reclaim. Assume that a process requested a high-order * can direct reclaim/compact. */ - if (sc->order && sc->nr_reclaimed >= 2UL << sc->order) + if (sc->order && sc->nr_reclaimed >= compact_gap(sc->order)) sc->order = 0; return sc->nr_scanned >= sc->nr_to_reclaim; diff --git a/mm/vmstat.c b/mm/vmstat.c index 89cec42d19ff..604f26a4f696 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1254,85 +1254,6 @@ static int pagetypeinfo_showblockcount(struct seq_file *m, void *arg) return 0; } -#ifdef CONFIG_PAGE_OWNER -static void pagetypeinfo_showmixedcount_print(struct seq_file *m, - pg_data_t *pgdat, - struct zone *zone) -{ - struct page *page; - struct page_ext *page_ext; - unsigned long pfn = zone->zone_start_pfn, block_end_pfn; - unsigned long end_pfn = pfn + zone->spanned_pages; - unsigned long count[MIGRATE_TYPES] = { 0, }; - int pageblock_mt, page_mt; - int i; - - /* Scan block by block. First and last block may be incomplete */ - pfn = zone->zone_start_pfn; - - /* - * Walk the zone in pageblock_nr_pages steps. If a page block spans - * a zone boundary, it will be double counted between zones. This does - * not matter as the mixed block count will still be correct - */ - for (; pfn < end_pfn; ) { - if (!pfn_valid(pfn)) { - pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES); - continue; - } - - block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); - block_end_pfn = min(block_end_pfn, end_pfn); - - page = pfn_to_page(pfn); - pageblock_mt = get_pageblock_migratetype(page); - - for (; pfn < block_end_pfn; pfn++) { - if (!pfn_valid_within(pfn)) - continue; - - page = pfn_to_page(pfn); - - if (page_zone(page) != zone) - continue; - - if (PageBuddy(page)) { - pfn += (1UL << page_order(page)) - 1; - continue; - } - - if (PageReserved(page)) - continue; - - page_ext = lookup_page_ext(page); - if (unlikely(!page_ext)) - continue; - - if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) - continue; - - page_mt = gfpflags_to_migratetype(page_ext->gfp_mask); - if (pageblock_mt != page_mt) { - if (is_migrate_cma(pageblock_mt)) - count[MIGRATE_MOVABLE]++; - else - count[pageblock_mt]++; - - pfn = block_end_pfn; - break; - } - pfn += (1UL << page_ext->order) - 1; - } - } - - /* Print counts */ - seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name); - for (i = 0; i < MIGRATE_TYPES; i++) - seq_printf(m, "%12lu ", count[i]); - seq_putc(m, '\n'); -} -#endif /* CONFIG_PAGE_OWNER */ - /* * Print out the number of pageblocks for each migratetype that contain pages * of other types. This gives an indication of how well fallbacks are being @@ -1592,7 +1513,10 @@ static int vmstat_show(struct seq_file *m, void *arg) { unsigned long *l = arg; unsigned long off = l - (unsigned long *)m->private; - seq_printf(m, "%s %lu\n", vmstat_text[off], *l); + + seq_puts(m, vmstat_text[off]); + seq_put_decimal_ull(m, " ", *l); + seq_putc(m, '\n'); return 0; } @@ -1794,6 +1718,16 @@ static void __init start_shepherd_timer(void) round_jiffies_relative(sysctl_stat_interval)); } +static void __init init_cpu_node_state(void) +{ + int cpu; + + get_online_cpus(); + for_each_online_cpu(cpu) + node_set_state(cpu_to_node(cpu), N_CPU); + put_online_cpus(); +} + static void vmstat_cpu_dead(int node) { int cpu; @@ -1851,6 +1785,7 @@ static int __init setup_vmstat(void) #ifdef CONFIG_SMP cpu_notifier_register_begin(); __register_cpu_notifier(&vmstat_notifier); + init_cpu_node_state(); start_shepherd_timer(); cpu_notifier_register_done(); diff --git a/net/core/sock.c b/net/core/sock.c index 038e660ef844..c73e28fc9c2a 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1363,6 +1363,7 @@ static void sk_prot_free(struct proto *prot, struct sock *sk) slab = prot->slab; cgroup_sk_free(&sk->sk_cgrp_data); + mem_cgroup_sk_free(sk); security_sk_free(sk); if (slab != NULL) kmem_cache_free(slab, sk); @@ -1399,6 +1400,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, sock_net_set(sk, net); atomic_set(&sk->sk_wmem_alloc, 1); + mem_cgroup_sk_alloc(sk); cgroup_sk_alloc(&sk->sk_cgrp_data); sock_update_classid(&sk->sk_cgrp_data); sock_update_netprioidx(&sk->sk_cgrp_data); @@ -1545,6 +1547,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) newsk->sk_incoming_cpu = raw_smp_processor_id(); atomic64_set(&newsk->sk_cookie, 0); + mem_cgroup_sk_alloc(newsk); cgroup_sk_alloc(&newsk->sk_cgrp_data); /* @@ -1569,9 +1572,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) sk_set_socket(newsk, NULL); newsk->sk_wq = NULL; - if (mem_cgroup_sockets_enabled && sk->sk_memcg) - sock_update_memcg(newsk); - if (newsk->sk_prot->sockets_allocated) sk_sockets_allocated_inc(newsk); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 66ddcb60519a..7cf7d6e380c2 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -258,7 +258,7 @@ int ping_init_sock(struct sock *sk) struct net *net = sock_net(sk); kgid_t group = current_egid(); struct group_info *group_info; - int i, j, count; + int i; kgid_t low, high; int ret = 0; @@ -270,16 +270,11 @@ int ping_init_sock(struct sock *sk) return 0; group_info = get_current_groups(); - count = group_info->ngroups; - for (i = 0; i < group_info->nblocks; i++) { - int cp_count = min_t(int, NGROUPS_PER_BLOCK, count); - for (j = 0; j < cp_count; j++) { - kgid_t gid = group_info->blocks[i][j]; - if (gid_lte(low, gid) && gid_lte(gid, high)) - goto out_release_group; - } + for (i = 0; i < group_info->ngroups; i++) { + kgid_t gid = group_info->gid[i]; - count -= cp_count; + if (gid_lte(low, gid) && gid_lte(gid, high)) + goto out_release_group; } ret = -EACCES; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2414b7c80b87..3251fe71f39f 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -424,8 +424,6 @@ void tcp_init_sock(struct sock *sk) sk->sk_rcvbuf = sysctl_tcp_rmem[1]; local_bh_disable(); - if (mem_cgroup_sockets_enabled) - sock_update_memcg(sk); sk_sockets_allocated_inc(sk); local_bh_enable(); } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 7ac37c314312..bd5e8d10893f 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1871,9 +1871,6 @@ void tcp_v4_destroy_sock(struct sock *sk) local_bh_disable(); sk_sockets_allocated_dec(sk); local_bh_enable(); - - if (mem_cgroup_sockets_enabled && sk->sk_memcg) - sock_release_memcg(sk); } EXPORT_SYMBOL(tcp_v4_destroy_sock); diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c index 168219535a34..83dffeadf20a 100644 --- a/net/sunrpc/auth_generic.c +++ b/net/sunrpc/auth_generic.c @@ -176,8 +176,8 @@ generic_match(struct auth_cred *acred, struct rpc_cred *cred, int flags) if (gcred->acred.group_info->ngroups != acred->group_info->ngroups) goto out_nomatch; for (i = 0; i < gcred->acred.group_info->ngroups; i++) { - if (!gid_eq(GROUP_AT(gcred->acred.group_info, i), - GROUP_AT(acred->group_info, i))) + if (!gid_eq(gcred->acred.group_info->gid[i], + acred->group_info->gid[i])) goto out_nomatch; } out_match: diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c index eeeba5adee6d..dc6fb79a361f 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.c +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c @@ -229,7 +229,7 @@ static int gssx_dec_linux_creds(struct xdr_stream *xdr, kgid = make_kgid(&init_user_ns, tmp); if (!gid_valid(kgid)) goto out_free_groups; - GROUP_AT(creds->cr_group_info, i) = kgid; + creds->cr_group_info->gid[i] = kgid; } return 0; diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index d8582028b346..d67f7e1bc82d 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -479,7 +479,7 @@ static int rsc_parse(struct cache_detail *cd, kgid = make_kgid(&init_user_ns, id); if (!gid_valid(kgid)) goto out; - GROUP_AT(rsci.cred.cr_group_info, i) = kgid; + rsci.cred.cr_group_info->gid[i] = kgid; } /* mech name */ diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c index a99278c984e8..a1d768a973f5 100644 --- a/net/sunrpc/auth_unix.c +++ b/net/sunrpc/auth_unix.c @@ -79,7 +79,7 @@ unx_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags, gfp_t cred->uc_gid = acred->gid; for (i = 0; i < groups; i++) - cred->uc_gids[i] = GROUP_AT(acred->group_info, i); + cred->uc_gids[i] = acred->group_info->gid[i]; if (i < NFS_NGROUPS) cred->uc_gids[i] = INVALID_GID; @@ -127,7 +127,7 @@ unx_match(struct auth_cred *acred, struct rpc_cred *rcred, int flags) if (groups > NFS_NGROUPS) groups = NFS_NGROUPS; for (i = 0; i < groups ; i++) - if (!gid_eq(cred->uc_gids[i], GROUP_AT(acred->group_info, i))) + if (!gid_eq(cred->uc_gids[i], acred->group_info->gid[i])) return 0; if (groups < NFS_NGROUPS && gid_valid(cred->uc_gids[groups])) return 0; diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index dfacdc95b3f5..64af4f034de6 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -517,7 +517,7 @@ static int unix_gid_parse(struct cache_detail *cd, kgid = make_kgid(&init_user_ns, gid); if (!gid_valid(kgid)) goto out; - GROUP_AT(ug.gi, i) = kgid; + ug.gi->gid[i] = kgid; } ugp = unix_gid_lookup(cd, uid); @@ -564,7 +564,7 @@ static int unix_gid_show(struct seq_file *m, seq_printf(m, "%u %d:", from_kuid_munged(user_ns, ug->uid), glen); for (i = 0; i < glen; i++) - seq_printf(m, " %d", from_kgid_munged(user_ns, GROUP_AT(ug->gi, i))); + seq_printf(m, " %d", from_kgid_munged(user_ns, ug->gi->gid[i])); seq_printf(m, "\n"); return 0; } @@ -817,7 +817,7 @@ svcauth_unix_accept(struct svc_rqst *rqstp, __be32 *authp) return SVC_CLOSE; for (i = 0; i < slen; i++) { kgid_t kgid = make_kgid(&init_user_ns, svc_getnl(argv)); - GROUP_AT(cred->cr_group_info, i) = kgid; + cred->cr_group_info->gid[i] = kgid; } if (svc_getu32(argv) != htonl(RPC_AUTH_NULL) || svc_getu32(argv) != 0) { *authp = rpc_autherr_badverf; diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 48958d3cec9e..bd8349759095 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -888,7 +888,7 @@ static void check_section(const char *modname, struct elf_info *elf, #define DATA_SECTIONS ".data", ".data.rel" #define TEXT_SECTIONS ".text", ".text.unlikely", ".sched.text", \ - ".kprobes.text" + ".kprobes.text", ".cpuidle.text" #define OTHER_TEXT_SECTIONS ".ref.text", ".head.text", ".spinlock.text", \ ".fixup", ".entry.text", ".exception.text", ".text.*", \ ".coldtext" diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c index a68f03133df9..5423a58d1b06 100644 --- a/scripts/recordmcount.c +++ b/scripts/recordmcount.c @@ -365,6 +365,7 @@ is_mcounted_section_name(char const *const txtname) strcmp(".irqentry.text", txtname) == 0 || strcmp(".softirqentry.text", txtname) == 0 || strcmp(".kprobes.text", txtname) == 0 || + strcmp(".cpuidle.text", txtname) == 0 || strcmp(".text.unlikely", txtname) == 0; } diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl index 2d48011bc362..faac4b10d8ea 100755 --- a/scripts/recordmcount.pl +++ b/scripts/recordmcount.pl @@ -136,6 +136,7 @@ my %text_sections = ( ".irqentry.text" => 1, ".softirqentry.text" => 1, ".kprobes.text" => 1, + ".cpuidle.text" => 1, ".text.unlikely" => 1, ); diff --git a/scripts/spelling.txt b/scripts/spelling.txt index fa79c6d2a5b8..163c720d3f2b 100644 --- a/scripts/spelling.txt +++ b/scripts/spelling.txt @@ -629,7 +629,6 @@ mispelt||misspelt miximum||maximum mmnemonic||mnemonic mnay||many -modeled||modelled modulues||modules monochorome||monochrome monochromo||monochrome diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore index a937a9d26b60..142c565bb351 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/vm/.gitignore @@ -7,3 +7,4 @@ mlock2-tests on-fault-limit transhuge-stress userfaultfd +mlock-intersect-test diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index e4bb1de1d526..bbab7f4664ac 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -10,6 +10,7 @@ BINARIES += on-fault-limit BINARIES += thuge-gen BINARIES += transhuge-stress BINARIES += userfaultfd +BINARIES += mlock-random-test all: $(BINARIES) %: %.c @@ -17,6 +18,9 @@ all: $(BINARIES) userfaultfd: userfaultfd.c ../../../../usr/include/linux/kernel.h $(CC) $(CFLAGS) -O2 -o $@ $< -lpthread +mlock-random-test: mlock-random-test.c + $(CC) $(CFLAGS) -o $@ $< -lcap + ../../../../usr/include/linux/kernel.h: make -C ../../../.. headers_install diff --git a/tools/testing/selftests/vm/mlock-random-test.c b/tools/testing/selftests/vm/mlock-random-test.c new file mode 100644 index 000000000000..83de4f58d262 --- /dev/null +++ b/tools/testing/selftests/vm/mlock-random-test.c @@ -0,0 +1,293 @@ +/* + * It tests the mlock/mlock2() when they are invoked + * on randomly memory region. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "mlock2.h" + +#define CHUNK_UNIT (128 * 1024) +#define MLOCK_RLIMIT_SIZE (CHUNK_UNIT * 2) +#define MLOCK_WITHIN_LIMIT_SIZE CHUNK_UNIT +#define MLOCK_OUTOF_LIMIT_SIZE (CHUNK_UNIT * 3) + +#define TEST_LOOP 100 +#define PAGE_ALIGN(size, ps) (((size) + ((ps) - 1)) & ~((ps) - 1)) + +int set_cap_limits(rlim_t max) +{ + struct rlimit new; + cap_t cap = cap_init(); + + new.rlim_cur = max; + new.rlim_max = max; + if (setrlimit(RLIMIT_MEMLOCK, &new)) { + perror("setrlimit() returns error\n"); + return -1; + } + + /* drop capabilities including CAP_IPC_LOCK */ + if (cap_set_proc(cap)) { + perror("cap_set_proc() returns error\n"); + return -2; + } + + return 0; +} + +int get_proc_locked_vm_size(void) +{ + FILE *f; + int ret = -1; + char line[1024] = {0}; + unsigned long lock_size = 0; + + f = fopen("/proc/self/status", "r"); + if (!f) { + perror("fopen"); + return -1; + } + + while (fgets(line, 1024, f)) { + if (strstr(line, "VmLck")) { + ret = sscanf(line, "VmLck:\t%8lu kB", &lock_size); + if (ret <= 0) { + printf("sscanf() on VmLck error: %s: %d\n", + line, ret); + fclose(f); + return -1; + } + fclose(f); + return (int)(lock_size << 10); + } + } + + perror("cann't parse VmLck in /proc/self/status\n"); + fclose(f); + return -1; +} + +/* + * Get the MMUPageSize of the memory region including input + * address from proc file. + * + * return value: on error case, 0 will be returned. + * Otherwise the page size(in bytes) is returned. + */ +int get_proc_page_size(unsigned long addr) +{ + FILE *smaps; + char *line; + unsigned long mmupage_size = 0; + size_t size; + + smaps = seek_to_smaps_entry(addr); + if (!smaps) { + printf("Unable to parse /proc/self/smaps\n"); + return 0; + } + + while (getline(&line, &size, smaps) > 0) { + if (!strstr(line, "MMUPageSize")) { + free(line); + line = NULL; + size = 0; + continue; + } + + /* found the MMUPageSize of this section */ + if (sscanf(line, "MMUPageSize: %8lu kB", + &mmupage_size) < 1) { + printf("Unable to parse smaps entry for Size:%s\n", + line); + break; + } + + } + free(line); + if (smaps) + fclose(smaps); + return mmupage_size << 10; +} + +/* + * Test mlock/mlock2() on provided memory chunk. + * It expects the mlock/mlock2() to be successful (within rlimit) + * + * With allocated memory chunk [p, p + alloc_size), this + * test will choose start/len randomly to perform mlock/mlock2 + * [start, start + len] memory range. The range is within range + * of the allocated chunk. + * + * The memory region size alloc_size is within the rlimit. + * So we always expect a success of mlock/mlock2. + * + * VmLck is assumed to be 0 before this test. + * + * return value: 0 - success + * else: failure + */ +int test_mlock_within_limit(char *p, int alloc_size) +{ + int i; + int ret = 0; + int locked_vm_size = 0; + struct rlimit cur; + int page_size = 0; + + getrlimit(RLIMIT_MEMLOCK, &cur); + if (cur.rlim_cur < alloc_size) { + printf("alloc_size[%d] < %u rlimit,lead to mlock failure\n", + alloc_size, (unsigned int)cur.rlim_cur); + return -1; + } + + srand(time(NULL)); + for (i = 0; i < TEST_LOOP; i++) { + /* + * - choose mlock/mlock2 randomly + * - choose lock_size randomly but lock_size < alloc_size + * - choose start_offset randomly but p+start_offset+lock_size + * < p+alloc_size + */ + int is_mlock = !!(rand() % 2); + int lock_size = rand() % alloc_size; + int start_offset = rand() % (alloc_size - lock_size); + + if (is_mlock) + ret = mlock(p + start_offset, lock_size); + else + ret = mlock2_(p + start_offset, lock_size, + MLOCK_ONFAULT); + + if (ret) { + printf("%s() failure at |%p(%d)| mlock:|%p(%d)|\n", + is_mlock ? "mlock" : "mlock2", + p, alloc_size, + p + start_offset, lock_size); + return ret; + } + } + + /* + * Check VmLck left by the tests. + */ + locked_vm_size = get_proc_locked_vm_size(); + page_size = get_proc_page_size((unsigned long)p); + if (page_size == 0) { + printf("cannot get proc MMUPageSize\n"); + return -1; + } + + if (locked_vm_size > PAGE_ALIGN(alloc_size, page_size) + page_size) { + printf("test_mlock_within_limit() left VmLck:%d on %d chunk\n", + locked_vm_size, alloc_size); + return -1; + } + + return 0; +} + + +/* + * We expect the mlock/mlock2() to be fail (outof limitation) + * + * With allocated memory chunk [p, p + alloc_size), this + * test will randomly choose start/len and perform mlock/mlock2 + * on [start, start+len] range. + * + * The memory region size alloc_size is above the rlimit. + * And the len to be locked is higher than rlimit. + * So we always expect a failure of mlock/mlock2. + * No locked page number should be increased as a side effect. + * + * return value: 0 - success + * else: failure + */ +int test_mlock_outof_limit(char *p, int alloc_size) +{ + int i; + int ret = 0; + int locked_vm_size = 0, old_locked_vm_size = 0; + struct rlimit cur; + + getrlimit(RLIMIT_MEMLOCK, &cur); + if (cur.rlim_cur >= alloc_size) { + printf("alloc_size[%d] >%u rlimit, violates test condition\n", + alloc_size, (unsigned int)cur.rlim_cur); + return -1; + } + + old_locked_vm_size = get_proc_locked_vm_size(); + srand(time(NULL)); + for (i = 0; i < TEST_LOOP; i++) { + int is_mlock = !!(rand() % 2); + int lock_size = (rand() % (alloc_size - cur.rlim_cur)) + + cur.rlim_cur; + int start_offset = rand() % (alloc_size - lock_size); + + if (is_mlock) + ret = mlock(p + start_offset, lock_size); + else + ret = mlock2_(p + start_offset, lock_size, + MLOCK_ONFAULT); + if (ret == 0) { + printf("%s() succeeds? on %p(%d) mlock%p(%d)\n", + is_mlock ? "mlock" : "mlock2", + p, alloc_size, + p + start_offset, lock_size); + return -1; + } + } + + locked_vm_size = get_proc_locked_vm_size(); + if (locked_vm_size != old_locked_vm_size) { + printf("tests leads to new mlocked page: old[%d], new[%d]\n", + old_locked_vm_size, + locked_vm_size); + return -1; + } + + return 0; +} + +int main(int argc, char **argv) +{ + char *p = NULL; + int ret = 0; + + if (set_cap_limits(MLOCK_RLIMIT_SIZE)) + return -1; + + p = malloc(MLOCK_WITHIN_LIMIT_SIZE); + if (p == NULL) { + perror("malloc() failure\n"); + return -1; + } + ret = test_mlock_within_limit(p, MLOCK_WITHIN_LIMIT_SIZE); + if (ret) + return ret; + munlock(p, MLOCK_WITHIN_LIMIT_SIZE); + free(p); + + + p = malloc(MLOCK_OUTOF_LIMIT_SIZE); + if (p == NULL) { + perror("malloc() failure\n"); + return -1; + } + ret = test_mlock_outof_limit(p, MLOCK_OUTOF_LIMIT_SIZE); + if (ret) + return ret; + munlock(p, MLOCK_OUTOF_LIMIT_SIZE); + free(p); + + return 0; +} diff --git a/tools/testing/selftests/vm/mlock2-tests.c b/tools/testing/selftests/vm/mlock2-tests.c index 02ca5e0177c5..ff0cda2b19c9 100644 --- a/tools/testing/selftests/vm/mlock2-tests.c +++ b/tools/testing/selftests/vm/mlock2-tests.c @@ -1,33 +1,12 @@ #define _GNU_SOURCE #include #include -#include -#include #include #include #include #include -#include -#include #include - -#ifndef MLOCK_ONFAULT -#define MLOCK_ONFAULT 1 -#endif - -#ifndef MCL_ONFAULT -#define MCL_ONFAULT (MCL_FUTURE << 1) -#endif - -static int mlock2_(void *start, size_t len, int flags) -{ -#ifdef __NR_mlock2 - return syscall(__NR_mlock2, start, len, flags); -#else - errno = ENOSYS; - return -1; -#endif -} +#include "mlock2.h" struct vm_boundaries { unsigned long start; @@ -138,46 +117,6 @@ static uint64_t get_kpageflags(unsigned long pfn) return flags; } -static FILE *seek_to_smaps_entry(unsigned long addr) -{ - FILE *file; - char *line = NULL; - size_t size = 0; - unsigned long start, end; - char perms[5]; - unsigned long offset; - char dev[32]; - unsigned long inode; - char path[BUFSIZ]; - - file = fopen("/proc/self/smaps", "r"); - if (!file) { - perror("fopen smaps"); - _exit(1); - } - - while (getline(&line, &size, file) > 0) { - if (sscanf(line, "%lx-%lx %s %lx %s %lu %s\n", - &start, &end, perms, &offset, dev, &inode, path) < 6) - goto next; - - if (start <= addr && addr < end) - goto out; - -next: - free(line); - line = NULL; - size = 0; - } - - fclose(file); - file = NULL; - -out: - free(line); - return file; -} - #define VMFLAGS "VmFlags:" static bool is_vmflag_set(unsigned long addr, const char *vmflag) diff --git a/tools/testing/selftests/vm/mlock2.h b/tools/testing/selftests/vm/mlock2.h new file mode 100644 index 000000000000..7ee062929d3e --- /dev/null +++ b/tools/testing/selftests/vm/mlock2.h @@ -0,0 +1,62 @@ +#include +#include +#include +#include + +#ifndef MLOCK_ONFAULT +#define MLOCK_ONFAULT 1 +#endif + +#ifndef MCL_ONFAULT +#define MCL_ONFAULT (MCL_FUTURE << 1) +#endif + +static int mlock2_(void *start, size_t len, int flags) +{ +#ifdef __NR_mlock2 + return syscall(__NR_mlock2, start, len, flags); +#else + errno = ENOSYS; + return -1; +#endif +} + +static FILE *seek_to_smaps_entry(unsigned long addr) +{ + FILE *file; + char *line = NULL; + size_t size = 0; + unsigned long start, end; + char perms[5]; + unsigned long offset; + char dev[32]; + unsigned long inode; + char path[BUFSIZ]; + + file = fopen("/proc/self/smaps", "r"); + if (!file) { + perror("fopen smaps"); + _exit(1); + } + + while (getline(&line, &size, file) > 0) { + if (sscanf(line, "%lx-%lx %s %lx %s %lu %s\n", + &start, &end, perms, &offset, dev, &inode, path) < 6) + goto next; + + if (start <= addr && addr < end) + goto out; + +next: + free(line); + line = NULL; + size = 0; + } + + fclose(file); + file = NULL; + +out: + free(line); + return file; +}