diff options
155 files changed, 3222 insertions, 963 deletions
diff --git a/Documentation/DMA-ISA-LPC.txt b/Documentation/DMA-ISA-LPC.txt index c41331398752..7a065ac4a9d1 100644 --- a/Documentation/DMA-ISA-LPC.txt +++ b/Documentation/DMA-ISA-LPC.txt @@ -42,7 +42,7 @@ requirements you pass the flag GFP_DMA to kmalloc. Unfortunately the memory available for ISA DMA is scarce so unless you allocate the memory during boot-up it's a good idea to also pass -__GFP_REPEAT and __GFP_NOWARN to make the allocator try a bit harder. +__GFP_RETRY_MAYFAIL and __GFP_NOWARN to make the allocator try a bit harder. (This scarcity also means that you should allocate the buffer as early as possible and not release it until the driver is unloaded.) diff --git a/Documentation/fault-injection/fault-injection.txt b/Documentation/fault-injection/fault-injection.txt index 415484f3d59a..192d8cbcc5f9 100644 --- a/Documentation/fault-injection/fault-injection.txt +++ b/Documentation/fault-injection/fault-injection.txt @@ -134,6 +134,22 @@ use the boot option: fail_futex= mmc_core.fail_request=<interval>,<probability>,<space>,<times> +o proc entries + +- /proc/self/task/<current-tid>/fail-nth: + + Write to this file of integer N makes N-th call in the current task fail + (N is 0-based). Read from this file returns a single char 'Y' or 'N' + that says if the fault setup with a previous write to this file was + injected or not, and disables the fault if it wasn't yet injected. + Note that this file enables all types of faults (slab, futex, etc). + This setting takes precedence over all other generic debugfs settings + like probability, interval, times, etc. But per-capability settings + (e.g. fail_futex/ignore-private) take precedence over it. + + This feature is intended for systematic testing of faults in a single + system call. See an example below. + How to add new fault injection capability ----------------------------------------- @@ -278,3 +294,65 @@ allocation failure. # env FAILCMD_TYPE=fail_page_alloc \ ./tools/testing/fault-injection/failcmd.sh --times=100 \ -- make -C tools/testing/selftests/ run_tests + +Systematic faults using fail-nth +--------------------------------- + +The following code systematically faults 0-th, 1-st, 2-nd and so on +capabilities in the socketpair() system call. + +#include <sys/types.h> +#include <sys/stat.h> +#include <sys/socket.h> +#include <sys/syscall.h> +#include <fcntl.h> +#include <unistd.h> +#include <string.h> +#include <stdlib.h> +#include <stdio.h> +#include <errno.h> + +int main() +{ + int i, err, res, fail_nth, fds[2]; + char buf[128]; + + system("echo N > /sys/kernel/debug/failslab/ignore-gfp-wait"); + sprintf(buf, "/proc/self/task/%ld/fail-nth", syscall(SYS_gettid)); + fail_nth = open(buf, O_RDWR); + for (i = 0;; i++) { + sprintf(buf, "%d", i); + write(fail_nth, buf, strlen(buf)); + res = socketpair(AF_LOCAL, SOCK_STREAM, 0, fds); + err = errno; + read(fail_nth, buf, 1); + if (res == 0) { + close(fds[0]); + close(fds[1]); + } + printf("%d-th fault %c: res=%d/%d\n", i, buf[0], res, err); + if (buf[0] != 'Y') + break; + } + return 0; +} + +An example output: + +0-th fault Y: res=-1/23 +1-th fault Y: res=-1/23 +2-th fault Y: res=-1/23 +3-th fault Y: res=-1/12 +4-th fault Y: res=-1/12 +5-th fault Y: res=-1/23 +6-th fault Y: res=-1/23 +7-th fault Y: res=-1/23 +8-th fault Y: res=-1/12 +9-th fault Y: res=-1/12 +10-th fault Y: res=-1/12 +11-th fault Y: res=-1/12 +12-th fault Y: res=-1/12 +13-th fault Y: res=-1/12 +14-th fault Y: res=-1/12 +15-th fault Y: res=-1/12 +16-th fault N: res=0/12 diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 4cddbce85ac9..adba21b5ada7 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -1786,12 +1786,16 @@ pair provide additional information particular to the objects they represent. pos: 0 flags: 02 mnt_id: 9 - tfd: 5 events: 1d data: ffffffffffffffff + tfd: 5 events: 1d data: ffffffffffffffff pos:0 ino:61af sdev:7 where 'tfd' is a target file descriptor number in decimal form, 'events' is events mask being watched and the 'data' is data associated with a target [see epoll(7) for more details]. + The 'pos' is current offset of the target file in decimal form + [see lseek(2)], 'ino' and 'sdev' are inode and device numbers + where target file resides, all in hex format. + Fsnotify files ~~~~~~~~~~~~~~ For inotify files the format is the following diff --git a/Documentation/kdump/kdump.txt b/Documentation/kdump/kdump.txt index 615434d81108..51814450a7f8 100644 --- a/Documentation/kdump/kdump.txt +++ b/Documentation/kdump/kdump.txt @@ -112,8 +112,8 @@ There are two possible methods of using Kdump. 2) Or use the system kernel binary itself as dump-capture kernel and there is no need to build a separate dump-capture kernel. This is possible only with the architectures which support a relocatable kernel. As - of today, i386, x86_64, ppc64, ia64 and arm architectures support relocatable - kernel. + of today, i386, x86_64, ppc64, ia64, arm and arm64 architectures support + relocatable kernel. Building a relocatable kernel is advantageous from the point of view that one does not have to build a second kernel for capturing the dump. But @@ -339,7 +339,7 @@ For arm: For arm64: - Use vmlinux or Image -If you are using a uncompressed vmlinux image then use following command +If you are using an uncompressed vmlinux image then use following command to load dump-capture kernel. kexec -p <dump-capture-kernel-vmlinux-image> \ @@ -361,6 +361,12 @@ to load dump-capture kernel. --dtb=<dtb-for-dump-capture-kernel> \ --append="root=<root-dev> <arch-specific-options>" +If you are using an uncompressed Image, then use following command +to load dump-capture kernel. + + kexec -p <dump-capture-kernel-Image> \ + --initrd=<initrd-for-dump-capture-kernel> \ + --append="root=<root-dev> <arch-specific-options>" Please note, that --args-linux does not need to be specified for ia64. It is planned to make this a no-op on that architecture, but for now diff --git a/arch/Kconfig b/arch/Kconfig index cae0958a2298..21d0089117fe 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -198,9 +198,6 @@ config HAVE_KPROBES_ON_FTRACE config HAVE_NMI bool -config HAVE_NMI_WATCHDOG - depends on HAVE_NMI - bool # # An arch should select this if it provides all these things: # @@ -226,6 +223,12 @@ config GENERIC_SMP_IDLE_THREAD config GENERIC_IDLE_POLL_SETUP bool +config ARCH_HAS_FORTIFY_SOURCE + bool + help + An architecture should select this when it can successfully + build and run with CONFIG_FORTIFY_SOURCE. + # Select if arch has all set_memory_ro/rw/x/nx() functions in asm/cacheflush.h config ARCH_HAS_SET_MEMORY bool @@ -288,6 +291,28 @@ config HAVE_PERF_EVENTS_NMI subsystem. Also has support for calculating CPU cycle events to determine how many clock cycles in a given period. +config HAVE_HARDLOCKUP_DETECTOR_PERF + bool + depends on HAVE_PERF_EVENTS_NMI + help + The arch chooses to use the generic perf-NMI-based hardlockup + detector. Must define HAVE_PERF_EVENTS_NMI. + +config HAVE_NMI_WATCHDOG + depends on HAVE_NMI + bool + help + The arch provides a low level NMI watchdog. It provides + asm/nmi.h, and defines its own arch_touch_nmi_watchdog(). + +config HAVE_HARDLOCKUP_DETECTOR_ARCH + bool + select HAVE_NMI_WATCHDOG + help + The arch chooses to provide its own hardlockup detector, which is + a superset of the HAVE_NMI_WATCHDOG. It also conforms to config + interfaces and parameters provided by hardlockup detector subsystem. + config HAVE_PERF_REGS bool help diff --git a/arch/arm/include/asm/kvm_hyp.h b/arch/arm/include/asm/kvm_hyp.h index 58508900c4bb..14b5903f0224 100644 --- a/arch/arm/include/asm/kvm_hyp.h +++ b/arch/arm/include/asm/kvm_hyp.h @@ -110,8 +110,8 @@ void __sysreg_restore_state(struct kvm_cpu_context *ctxt); void __vgic_v3_save_state(struct kvm_vcpu *vcpu); void __vgic_v3_restore_state(struct kvm_vcpu *vcpu); -void asmlinkage __vfp_save_state(struct vfp_hard_struct *vfp); -void asmlinkage __vfp_restore_state(struct vfp_hard_struct *vfp); +asmlinkage void __vfp_save_state(struct vfp_hard_struct *vfp); +asmlinkage void __vfp_restore_state(struct vfp_hard_struct *vfp); static inline bool __vfp_enabled(void) { return !(read_sysreg(HCPTR) & (HCPTR_TCP(11) | HCPTR_TCP(10))); @@ -120,8 +120,8 @@ static inline bool __vfp_enabled(void) void __hyp_text __banked_save_state(struct kvm_cpu_context *ctxt); void __hyp_text __banked_restore_state(struct kvm_cpu_context *ctxt); -int asmlinkage __guest_enter(struct kvm_vcpu *vcpu, +asmlinkage int __guest_enter(struct kvm_vcpu *vcpu, struct kvm_cpu_context *host); -int asmlinkage __hyp_do_panic(const char *, int, u32); +asmlinkage int __hyp_do_panic(const char *, int, u32); #endif /* __ARM_KVM_HYP_H__ */ diff --git a/arch/arm/mach-sa1100/jornada720_ssp.c b/arch/arm/mach-sa1100/jornada720_ssp.c index b143c4659346..7fc11a3c17b4 100644 --- a/arch/arm/mach-sa1100/jornada720_ssp.c +++ b/arch/arm/mach-sa1100/jornada720_ssp.c @@ -33,7 +33,7 @@ static unsigned long jornada_ssp_flags; * we need to reverse all data we receive from the mcu due to its physical location * returns : 01110111 -> 11101110 */ -u8 inline jornada_ssp_reverse(u8 byte) +inline u8 jornada_ssp_reverse(u8 byte) { return ((0x80 & byte) >> 7) | diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 8addb851ab5e..dfd908630631 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -12,6 +12,7 @@ config ARM64 select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_ELF_RANDOMIZE + select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA select ARCH_HAS_KCOV diff --git a/arch/arm64/include/asm/stackprotector.h b/arch/arm64/include/asm/stackprotector.h index fe5e287dc56b..b86a0865ddf1 100644 --- a/arch/arm64/include/asm/stackprotector.h +++ b/arch/arm64/include/asm/stackprotector.h @@ -30,6 +30,7 @@ static __always_inline void boot_init_stack_canary(void) /* Try to get a semi random initial value. */ get_random_bytes(&canary, sizeof(canary)); canary ^= LINUX_VERSION_CODE; + canary &= CANARY_MASK; current->stack_canary = canary; __stack_chk_guard = current->stack_canary; diff --git a/arch/arm64/include/asm/string.h b/arch/arm64/include/asm/string.h index 2eb714c4639f..d0aa42907569 100644 --- a/arch/arm64/include/asm/string.h +++ b/arch/arm64/include/asm/string.h @@ -63,6 +63,11 @@ extern int memcmp(const void *, const void *, size_t); #define memcpy(dst, src, len) __memcpy(dst, src, len) #define memmove(dst, src, len) __memmove(dst, src, len) #define memset(s, c, n) __memset(s, c, n) + +#ifndef __NO_FORTIFY +#define __NO_FORTIFY /* FORTIFY_SOURCE uses __builtin_memcpy, etc. */ +#endif + #endif #endif diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index adc208c2ae9c..decccffb03ca 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -35,7 +35,7 @@ * Leave enough space between the mmap area and the stack to honour ulimit in * the face of randomisation. */ -#define MIN_GAP (SZ_128M + ((STACK_RND_MASK << PAGE_SHIFT) + 1)) +#define MIN_GAP (SZ_128M) #define MAX_GAP (STACK_TOP/6*5) static int mmap_is_legacy(void) @@ -65,6 +65,11 @@ unsigned long arch_mmap_rnd(void) static unsigned long mmap_base(unsigned long rnd) { unsigned long gap = rlimit(RLIMIT_STACK); + unsigned long pad = (STACK_RND_MASK << PAGE_SHIFT) + stack_guard_gap; + + /* Values close to RLIM_INFINITY can overflow. */ + if (gap + pad > gap) + gap += pad; if (gap < MIN_GAP) gap = MIN_GAP; diff --git a/arch/blackfin/include/asm/nmi.h b/arch/blackfin/include/asm/nmi.h index b9caac4fcfd8..107d23705f46 100644 --- a/arch/blackfin/include/asm/nmi.h +++ b/arch/blackfin/include/asm/nmi.h @@ -9,4 +9,6 @@ #include <linux/nmi.h> +extern void arch_touch_nmi_watchdog(void); + #endif diff --git a/arch/blackfin/kernel/nmi.c b/arch/blackfin/kernel/nmi.c index 633c37083e87..1e714329fe8a 100644 --- a/arch/blackfin/kernel/nmi.c +++ b/arch/blackfin/kernel/nmi.c @@ -190,7 +190,7 @@ static int __init init_nmi_wdt(void) } device_initcall(init_nmi_wdt); -void touch_nmi_watchdog(void) +void arch_touch_nmi_watchdog(void) { atomic_set(&nmi_touched[smp_processor_id()], 1); } diff --git a/arch/cris/arch-v10/drivers/gpio.c b/arch/cris/arch-v10/drivers/gpio.c index 64285e0d3481..dfd3b3ba5e4e 100644 --- a/arch/cris/arch-v10/drivers/gpio.c +++ b/arch/cris/arch-v10/drivers/gpio.c @@ -399,7 +399,7 @@ out: /* Main device API. ioctl's to read/set/clear bits, as well as to * set alarms to wait for using a subsequent select(). */ -unsigned long inline setget_input(struct gpio_private *priv, unsigned long arg) +inline unsigned long setget_input(struct gpio_private *priv, unsigned long arg) { /* Set direction 0=unchanged 1=input, * return mask with 1=input */ @@ -450,7 +450,7 @@ unsigned long inline setget_input(struct gpio_private *priv, unsigned long arg) return dir_g_in_bits; } /* setget_input */ -unsigned long inline setget_output(struct gpio_private *priv, unsigned long arg) +inline unsigned long setget_output(struct gpio_private *priv, unsigned long arg) { if (USE_PORTS(priv)) { *priv->dir = *priv->dir_shadow |= diff --git a/arch/frv/include/asm/tlbflush.h b/arch/frv/include/asm/tlbflush.h index 7ac5eafc5d98..75879420f578 100644 --- a/arch/frv/include/asm/tlbflush.h +++ b/arch/frv/include/asm/tlbflush.h @@ -18,10 +18,10 @@ #ifdef CONFIG_MMU #ifndef __ASSEMBLY__ -extern void asmlinkage __flush_tlb_all(void); -extern void asmlinkage __flush_tlb_mm(unsigned long contextid); -extern void asmlinkage __flush_tlb_page(unsigned long contextid, unsigned long start); -extern void asmlinkage __flush_tlb_range(unsigned long contextid, +extern asmlinkage void __flush_tlb_all(void); +extern asmlinkage void __flush_tlb_mm(unsigned long contextid); +extern asmlinkage void __flush_tlb_page(unsigned long contextid, unsigned long start); +extern asmlinkage void __flush_tlb_range(unsigned long contextid, unsigned long start, unsigned long end); #endif /* !__ASSEMBLY__ */ diff --git a/arch/ia64/kernel/machine_kexec.c b/arch/ia64/kernel/machine_kexec.c index 599507bcec91..c14815dca747 100644 --- a/arch/ia64/kernel/machine_kexec.c +++ b/arch/ia64/kernel/machine_kexec.c @@ -163,8 +163,3 @@ void arch_crash_save_vmcoreinfo(void) #endif } -phys_addr_t paddr_vmcoreinfo_note(void) -{ - return ia64_tpa((unsigned long)(char *)&vmcoreinfo_note); -} - diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index 79c7c46d7dc1..555b11180156 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -334,7 +334,7 @@ static void ia64_mlogbuf_dump_from_init(void) ia64_mlogbuf_dump(); } -static void inline +static inline void ia64_mca_spin(const char *func) { if (monarch_cpu == smp_processor_id()) diff --git a/arch/ia64/sn/pci/pcibr/pcibr_ate.c b/arch/ia64/sn/pci/pcibr/pcibr_ate.c index 5bc34eac9e01..b67bb4cb73ff 100644 --- a/arch/ia64/sn/pci/pcibr/pcibr_ate.c +++ b/arch/ia64/sn/pci/pcibr/pcibr_ate.c @@ -140,7 +140,7 @@ static inline u64 __iomem *pcibr_ate_addr(struct pcibus_info *pcibus_info, /* * Update the ate. */ -void inline +inline void ate_write(struct pcibus_info *pcibus_info, int ate_index, int count, volatile u64 ate) { diff --git a/arch/ia64/sn/pci/tioce_provider.c b/arch/ia64/sn/pci/tioce_provider.c index 46d3df4b03a1..3bd9abc35485 100644 --- a/arch/ia64/sn/pci/tioce_provider.c +++ b/arch/ia64/sn/pci/tioce_provider.c @@ -52,7 +52,7 @@ * All registers defined in struct tioce will meet that criteria. */ -static void inline +static inline void tioce_mmr_war_pre(struct tioce_kernel *kern, void __iomem *mmr_addr) { u64 mmr_base; @@ -78,7 +78,7 @@ tioce_mmr_war_pre(struct tioce_kernel *kern, void __iomem *mmr_addr) } } -static void inline +static inline void tioce_mmr_war_post(struct tioce_kernel *kern, void __iomem *mmr_addr) { u64 mmr_base; diff --git a/arch/m68k/coldfire/intc-simr.c b/arch/m68k/coldfire/intc-simr.c index 7cf2c156f72d..15c4b7a6e38f 100644 --- a/arch/m68k/coldfire/intc-simr.c +++ b/arch/m68k/coldfire/intc-simr.c @@ -35,7 +35,7 @@ #define EINT7 67 /* EDGE Port interrupt 7 */ static unsigned int irqebitmap[] = { 0, 1, 4, 7 }; -static unsigned int inline irq2ebit(unsigned int irq) +static inline unsigned int irq2ebit(unsigned int irq) { return irqebitmap[irq - EINT0]; } @@ -51,7 +51,7 @@ static unsigned int inline irq2ebit(unsigned int irq) #define EINT1 65 /* EDGE Port interrupt 1 */ #define EINT7 71 /* EDGE Port interrupt 7 */ -static unsigned int inline irq2ebit(unsigned int irq) +static inline unsigned int irq2ebit(unsigned int irq) { return irq - EINT0; } diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h index a1bdb1ea5234..39b9f311c4ef 100644 --- a/arch/mips/include/asm/pgalloc.h +++ b/arch/mips/include/asm/pgalloc.h @@ -116,7 +116,7 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) { pud_t *pud; - pud = (pud_t *) __get_free_pages(GFP_KERNEL|__GFP_REPEAT, PUD_ORDER); + pud = (pud_t *) __get_free_pages(GFP_KERNEL, PUD_ORDER); if (pud) pud_init((unsigned long)pud, (unsigned long)invalid_pmd_table); return pud; diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h index 98a117a05fbc..bab3d41e5987 100644 --- a/arch/mips/include/asm/smp.h +++ b/arch/mips/include/asm/smp.h @@ -47,7 +47,7 @@ extern int __cpu_logical_map[NR_CPUS]; /* Mask of CPUs which are currently definitely operating coherently */ extern cpumask_t cpu_coherent_mask; -extern void asmlinkage smp_bootstrap(void); +extern asmlinkage void smp_bootstrap(void); extern void calculate_cpu_foreign_map(void); diff --git a/arch/mn10300/include/asm/nmi.h b/arch/mn10300/include/asm/nmi.h index f3671cbbc117..b05627597b1b 100644 --- a/arch/mn10300/include/asm/nmi.h +++ b/arch/mn10300/include/asm/nmi.h @@ -11,4 +11,6 @@ #ifndef _ASM_NMI_H #define _ASM_NMI_H +extern void arch_touch_nmi_watchdog(void); + #endif /* _ASM_NMI_H */ diff --git a/arch/mn10300/kernel/mn10300-watchdog-low.S b/arch/mn10300/kernel/mn10300-watchdog-low.S index f2f5c9cfaabd..34f8773de7d0 100644 --- a/arch/mn10300/kernel/mn10300-watchdog-low.S +++ b/arch/mn10300/kernel/mn10300-watchdog-low.S @@ -50,9 +50,9 @@ watchdog_handler: # we can't inline it) # ############################################################################### - .globl touch_nmi_watchdog - .type touch_nmi_watchdog,@function -touch_nmi_watchdog: + .globl arch_touch_nmi_watchdog + .type arch_touch_nmi_watchdog,@function +arch_touch_nmi_watchdog: clr d0 clr d1 mov watchdog_alert_counter, a0 @@ -63,4 +63,4 @@ touch_nmi_watchdog: lne ret [],0 - .size touch_nmi_watchdog,.-touch_nmi_watchdog + .size arch_touch_nmi_watchdog,.-arch_touch_nmi_watchdog diff --git a/arch/mn10300/kernel/mn10300-watchdog.c b/arch/mn10300/kernel/mn10300-watchdog.c index a2d8e6938d67..0d5641beadf5 100644 --- a/arch/mn10300/kernel/mn10300-watchdog.c +++ b/arch/mn10300/kernel/mn10300-watchdog.c @@ -31,7 +31,7 @@ static unsigned int watchdog; static unsigned int watchdog_hz = 1; unsigned int watchdog_alert_counter[NR_CPUS]; -EXPORT_SYMBOL(touch_nmi_watchdog); +EXPORT_SYMBOL(arch_touch_nmi_watchdog); /* * the best way to detect whether a CPU has a 'hard lockup' problem diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 7177a3f4f418..36f858c37ca7 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -82,7 +82,7 @@ config NR_IRQS config NMI_IPI bool - depends on SMP && (DEBUGGER || KEXEC_CORE) + depends on SMP && (DEBUGGER || KEXEC_CORE || HARDLOCKUP_DETECTOR) default y config STACKTRACE_SUPPORT @@ -125,6 +125,7 @@ config PPC select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_DMA_SET_COHERENT_MASK select ARCH_HAS_ELF_RANDOMIZE + select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE select ARCH_HAS_SG_CHAIN @@ -192,11 +193,13 @@ config PPC select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select HAVE_MOD_ARCH_SPECIFIC - select HAVE_NMI if PERF_EVENTS + select HAVE_NMI if PERF_EVENTS || (PPC64 && PPC_BOOK3S) + select HAVE_HARDLOCKUP_DETECTOR_ARCH if (PPC64 && PPC_BOOK3S) select HAVE_OPROFILE select HAVE_OPTPROBES if PPC64 select HAVE_PERF_EVENTS select HAVE_PERF_EVENTS_NMI if PPC64 + select HAVE_HARDLOCKUP_DETECTOR_PERF if HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP select HAVE_RCU_TABLE_FREE if SMP diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h index 20b1485ff1e8..e2329db9d6f4 100644 --- a/arch/powerpc/include/asm/book3s/64/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h @@ -56,7 +56,7 @@ static inline pgd_t *radix__pgd_alloc(struct mm_struct *mm) return (pgd_t *)__get_free_page(pgtable_gfp_flags(mm, PGALLOC_GFP)); #else struct page *page; - page = alloc_pages(pgtable_gfp_flags(mm, PGALLOC_GFP | __GFP_REPEAT), + page = alloc_pages(pgtable_gfp_flags(mm, PGALLOC_GFP | __GFP_RETRY_MAYFAIL), 4); if (!page) return NULL; diff --git a/arch/powerpc/include/asm/nmi.h b/arch/powerpc/include/asm/nmi.h index ff1ccb375e60..6f8e79cd35d8 100644 --- a/arch/powerpc/include/asm/nmi.h +++ b/arch/powerpc/include/asm/nmi.h @@ -1,4 +1,15 @@ #ifndef _ASM_NMI_H #define _ASM_NMI_H +#ifdef CONFIG_HARDLOCKUP_DETECTOR +extern void arch_touch_nmi_watchdog(void); + +extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask, + bool exclude_self); +#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace + +#else +static inline void arch_touch_nmi_watchdog(void) {} +#endif + #endif /* _ASM_NMI_H */ diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index ebddb2111d87..8ea98504f900 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -55,6 +55,8 @@ struct smp_ops_t { int (*cpu_bootable)(unsigned int nr); }; +extern void smp_flush_nmi_ipi(u64 delay_us); +extern int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us); extern void smp_send_debugger_break(void); extern void start_secondary_resume(void); extern void smp_generic_give_timebase(void); diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 0845eebc5af3..4aa7c147e447 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -38,6 +38,7 @@ obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \ signal_64.o ptrace32.o \ paca.o nvram_64.o firmware.o obj-$(CONFIG_VDSO32) += vdso32/ +obj-$(CONFIG_HARDLOCKUP_DETECTOR) += watchdog.o obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 4c18a5fbb4bb..e6d8354d79ef 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1314,6 +1314,31 @@ EXC_REAL_NONE(0x1800, 0x100) EXC_VIRT_NONE(0x5800, 0x100) #endif +#if defined(CONFIG_HARDLOCKUP_DETECTOR) && defined(CONFIG_HAVE_HARDLOCKUP_DETECTOR_ARCH) + +#define MASKED_DEC_HANDLER_LABEL 3f + +#define MASKED_DEC_HANDLER(_H) \ +3: /* soft-nmi */ \ + std r12,PACA_EXGEN+EX_R12(r13); \ + GET_SCRATCH0(r10); \ + std r10,PACA_EXGEN+EX_R13(r13); \ + EXCEPTION_PROLOG_PSERIES_1(soft_nmi_common, _H) + +EXC_COMMON_BEGIN(soft_nmi_common) + mr r10,r1 + ld r1,PACAEMERGSP(r13) + ld r1,PACA_NMI_EMERG_SP(r13) + subi r1,r1,INT_FRAME_SIZE + EXCEPTION_COMMON_NORET_STACK(PACA_EXGEN, 0x900, + system_reset, soft_nmi_interrupt, + ADD_NVGPRS;ADD_RECONCILE) + b ret_from_except + +#else +#define MASKED_DEC_HANDLER_LABEL 2f /* normal return */ +#define MASKED_DEC_HANDLER(_H) +#endif /* * An interrupt came in while soft-disabled. We set paca->irq_happened, then: @@ -1336,7 +1361,7 @@ masked_##_H##interrupt: \ lis r10,0x7fff; \ ori r10,r10,0xffff; \ mtspr SPRN_DEC,r10; \ - b 2f; \ + b MASKED_DEC_HANDLER_LABEL; \ 1: cmpwi r10,PACA_IRQ_DBELL; \ beq 2f; \ cmpwi r10,PACA_IRQ_HMI; \ @@ -1351,7 +1376,8 @@ masked_##_H##interrupt: \ ld r11,PACA_EXGEN+EX_R11(r13); \ GET_SCRATCH0(r13); \ ##_H##rfid; \ - b . + b .; \ + MASKED_DEC_HANDLER(_H) /* * Real mode exceptions actually use this too, but alternate diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 3079518f2245..dc0c49cfd90a 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -999,8 +999,7 @@ static int fadump_create_elfcore_headers(char *bufp) phdr->p_paddr = fadump_relocate(paddr_vmcoreinfo_note()); phdr->p_offset = phdr->p_paddr; - phdr->p_memsz = vmcoreinfo_max_size; - phdr->p_filesz = vmcoreinfo_max_size; + phdr->p_memsz = phdr->p_filesz = VMCOREINFO_NOTE_SIZE; /* Increment number of program headers. */ (elf->e_phnum)++; diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c index 9ad37f827a97..1086ea37c832 100644 --- a/arch/powerpc/kernel/kvm.c +++ b/arch/powerpc/kernel/kvm.c @@ -25,6 +25,7 @@ #include <linux/kvm_para.h> #include <linux/slab.h> #include <linux/of.h> +#include <linux/nmi.h> /* hardlockup_detector_disable() */ #include <asm/reg.h> #include <asm/sections.h> @@ -718,6 +719,12 @@ static __init void kvm_free_tmp(void) static int __init kvm_guest_init(void) { + /* + * The hardlockup detector is likely to get false positives in + * KVM guests, so disable it by default. + */ + hardlockup_detector_disable(); + if (!kvm_para_available()) goto free_tmp; diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index dd8a04f3053a..613f79f03877 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -15,6 +15,9 @@ #undef DEBUG_PROM +/* we cannot use FORTIFY as it brings in new symbols */ +#define __NO_FORTIFY + #include <stdarg.h> #include <linux/kernel.h> #include <linux/string.h> diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 4640f6d64f8b..af23d4b576ec 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -751,22 +751,3 @@ unsigned long memory_block_size_bytes(void) struct ppc_pci_io ppc_pci_io; EXPORT_SYMBOL(ppc_pci_io); #endif - -#ifdef CONFIG_HARDLOCKUP_DETECTOR -u64 hw_nmi_get_sample_period(int watchdog_thresh) -{ - return ppc_proc_freq * watchdog_thresh; -} - -/* - * The hardlockup detector breaks PMU event based branches and is likely - * to get false positives in KVM guests, so disable it by default. - */ -static int __init disable_hardlockup_detector(void) -{ - hardlockup_detector_disable(); - - return 0; -} -early_initcall(disable_hardlockup_detector); -#endif diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index c6b8bace1766..997c88d54acf 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -435,13 +435,31 @@ static void do_smp_send_nmi_ipi(int cpu) } } +void smp_flush_nmi_ipi(u64 delay_us) +{ + unsigned long flags; + + nmi_ipi_lock_start(&flags); + while (nmi_ipi_busy_count) { + nmi_ipi_unlock_end(&flags); + udelay(1); + if (delay_us) { + delay_us--; + if (!delay_us) + return; + } + nmi_ipi_lock_start(&flags); + } + nmi_ipi_unlock_end(&flags); +} + /* * - cpu is the target CPU (must not be this CPU), or NMI_IPI_ALL_OTHERS. * - fn is the target callback function. * - delay_us > 0 is the delay before giving up waiting for targets to * enter the handler, == 0 specifies indefinite delay. */ -static int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us) +int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us) { unsigned long flags; int me = raw_smp_processor_id(); diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c new file mode 100644 index 000000000000..b67f8b03a32d --- /dev/null +++ b/arch/powerpc/kernel/watchdog.c @@ -0,0 +1,386 @@ +/* + * Watchdog support on powerpc systems. + * + * Copyright 2017, IBM Corporation. + * + * This uses code from arch/sparc/kernel/nmi.c and kernel/watchdog.c + */ +#include <linux/kernel.h> +#include <linux/param.h> +#include <linux/init.h> +#include <linux/percpu.h> +#include <linux/cpu.h> +#include <linux/nmi.h> +#include <linux/module.h> +#include <linux/export.h> +#include <linux/kprobes.h> +#include <linux/hardirq.h> +#include <linux/reboot.h> +#include <linux/slab.h> +#include <linux/kdebug.h> +#include <linux/sched/debug.h> +#include <linux/delay.h> +#include <linux/smp.h> + +#include <asm/paca.h> + +/* + * The watchdog has a simple timer that runs on each CPU, once per timer + * period. This is the heartbeat. + * + * Then there are checks to see if the heartbeat has not triggered on a CPU + * for the panic timeout period. Currently the watchdog only supports an + * SMP check, so the heartbeat only turns on when we have 2 or more CPUs. + * + * This is not an NMI watchdog, but Linux uses that name for a generic + * watchdog in some cases, so NMI gets used in some places. + */ + +static cpumask_t wd_cpus_enabled __read_mostly; + +static u64 wd_panic_timeout_tb __read_mostly; /* timebase ticks until panic */ +static u64 wd_smp_panic_timeout_tb __read_mostly; /* panic other CPUs */ + +static u64 wd_timer_period_ms __read_mostly; /* interval between heartbeat */ + +static DEFINE_PER_CPU(struct timer_list, wd_timer); +static DEFINE_PER_CPU(u64, wd_timer_tb); + +/* + * These are for the SMP checker. CPUs clear their pending bit in their + * heartbeat. If the bitmask becomes empty, the time is noted and the + * bitmask is refilled. + * + * All CPUs clear their bit in the pending mask every timer period. + * Once all have cleared, the time is noted and the bits are reset. + * If the time since all clear was greater than the panic timeout, + * we can panic with the list of stuck CPUs. + * + * This will work best with NMI IPIs for crash code so the stuck CPUs + * can be pulled out to get their backtraces. + */ +static unsigned long __wd_smp_lock; +static cpumask_t wd_smp_cpus_pending; +static cpumask_t wd_smp_cpus_stuck; +static u64 wd_smp_last_reset_tb; + +static inline void wd_smp_lock(unsigned long *flags) +{ + /* + * Avoid locking layers if possible. + * This may be called from low level interrupt handlers at some + * point in future. + */ + local_irq_save(*flags); + while (unlikely(test_and_set_bit_lock(0, &__wd_smp_lock))) + cpu_relax(); +} + +static inline void wd_smp_unlock(unsigned long *flags) +{ + clear_bit_unlock(0, &__wd_smp_lock); + local_irq_restore(*flags); +} + +static void wd_lockup_ipi(struct pt_regs *regs) +{ + pr_emerg("Watchdog CPU:%d Hard LOCKUP\n", raw_smp_processor_id()); + print_modules(); + print_irqtrace_events(current); + if (regs) + show_regs(regs); + else + dump_stack(); + + if (hardlockup_panic) + nmi_panic(regs, "Hard LOCKUP"); +} + +static void set_cpu_stuck(int cpu, u64 tb) +{ + cpumask_set_cpu(cpu, &wd_smp_cpus_stuck); + cpumask_clear_cpu(cpu, &wd_smp_cpus_pending); + if (cpumask_empty(&wd_smp_cpus_pending)) { + wd_smp_last_reset_tb = tb; + cpumask_andnot(&wd_smp_cpus_pending, + &wd_cpus_enabled, + &wd_smp_cpus_stuck); + } +} + +static void watchdog_smp_panic(int cpu, u64 tb) +{ + unsigned long flags; + int c; + + wd_smp_lock(&flags); + /* Double check some things under lock */ + if ((s64)(tb - wd_smp_last_reset_tb) < (s64)wd_smp_panic_timeout_tb) + goto out; + if (cpumask_test_cpu(cpu, &wd_smp_cpus_pending)) + goto out; + if (cpumask_weight(&wd_smp_cpus_pending) == 0) + goto out; + + pr_emerg("Watchdog CPU:%d detected Hard LOCKUP other CPUS:%*pbl\n", + cpu, cpumask_pr_args(&wd_smp_cpus_pending)); + + /* + * Try to trigger the stuck CPUs. + */ + for_each_cpu(c, &wd_smp_cpus_pending) { + if (c == cpu) + continue; + smp_send_nmi_ipi(c, wd_lockup_ipi, 1000000); + } + smp_flush_nmi_ipi(1000000); + + /* Take the stuck CPU out of the watch group */ + for_each_cpu(c, &wd_smp_cpus_pending) + set_cpu_stuck(c, tb); + +out: + wd_smp_unlock(&flags); + + printk_safe_flush(); + /* + * printk_safe_flush() seems to require another print + * before anything actually goes out to console. + */ + if (sysctl_hardlockup_all_cpu_backtrace) + trigger_allbutself_cpu_backtrace(); + + if (hardlockup_panic) + nmi_panic(NULL, "Hard LOCKUP"); +} + +static void wd_smp_clear_cpu_pending(int cpu, u64 tb) +{ + if (!cpumask_test_cpu(cpu, &wd_smp_cpus_pending)) { + if (unlikely(cpumask_test_cpu(cpu, &wd_smp_cpus_stuck))) { + unsigned long flags; + + pr_emerg("Watchdog CPU:%d became unstuck\n", cpu); + wd_smp_lock(&flags); + cpumask_clear_cpu(cpu, &wd_smp_cpus_stuck); + wd_smp_unlock(&flags); + } + return; + } + cpumask_clear_cpu(cpu, &wd_smp_cpus_pending); + if (cpumask_empty(&wd_smp_cpus_pending)) { + unsigned long flags; + + wd_smp_lock(&flags); + if (cpumask_empty(&wd_smp_cpus_pending)) { + wd_smp_last_reset_tb = tb; + cpumask_andnot(&wd_smp_cpus_pending, + &wd_cpus_enabled, + &wd_smp_cpus_stuck); + } + wd_smp_unlock(&flags); + } +} + +static void watchdog_timer_interrupt(int cpu) +{ + u64 tb = get_tb(); + + per_cpu(wd_timer_tb, cpu) = tb; + + wd_smp_clear_cpu_pending(cpu, tb); + + if ((s64)(tb - wd_smp_last_reset_tb) >= (s64)wd_smp_panic_timeout_tb) + watchdog_smp_panic(cpu, tb); +} + +void soft_nmi_interrupt(struct pt_regs *regs) +{ + unsigned long flags; + int cpu = raw_smp_processor_id(); + u64 tb; + + if (!cpumask_test_cpu(cpu, &wd_cpus_enabled)) + return; + + nmi_enter(); + tb = get_tb(); + if (tb - per_cpu(wd_timer_tb, cpu) >= wd_panic_timeout_tb) { + per_cpu(wd_timer_tb, cpu) = tb; + + wd_smp_lock(&flags); + if (cpumask_test_cpu(cpu, &wd_smp_cpus_stuck)) { + wd_smp_unlock(&flags); + goto out; + } + set_cpu_stuck(cpu, tb); + + pr_emerg("Watchdog CPU:%d Hard LOCKUP\n", cpu); + print_modules(); + print_irqtrace_events(current); + if (regs) + show_regs(regs); + else + dump_stack(); + + wd_smp_unlock(&flags); + + if (sysctl_hardlockup_all_cpu_backtrace) + trigger_allbutself_cpu_backtrace(); + + if (hardlockup_panic) + nmi_panic(regs, "Hard LOCKUP"); + } + if (wd_panic_timeout_tb < 0x7fffffff) + mtspr(SPRN_DEC, wd_panic_timeout_tb); + +out: + nmi_exit(); +} + +static void wd_timer_reset(unsigned int cpu, struct timer_list *t) +{ + t->expires = jiffies + msecs_to_jiffies(wd_timer_period_ms); + if (wd_timer_period_ms > 1000) + t->expires = __round_jiffies_up(t->expires, cpu); + add_timer_on(t, cpu); +} + +static void wd_timer_fn(unsigned long data) +{ + struct timer_list *t = this_cpu_ptr(&wd_timer); + int cpu = smp_processor_id(); + + watchdog_timer_interrupt(cpu); + + wd_timer_reset(cpu, t); +} + +void arch_touch_nmi_watchdog(void) +{ + int cpu = smp_processor_id(); + + watchdog_timer_interrupt(cpu); +} +EXPORT_SYMBOL(arch_touch_nmi_watchdog); + +static void start_watchdog_timer_on(unsigned int cpu) +{ + struct timer_list *t = per_cpu_ptr(&wd_timer, cpu); + + per_cpu(wd_timer_tb, cpu) = get_tb(); + + setup_pinned_timer(t, wd_timer_fn, 0); + wd_timer_reset(cpu, t); +} + +static void stop_watchdog_timer_on(unsigned int cpu) +{ + struct timer_list *t = per_cpu_ptr(&wd_timer, cpu); + + del_timer_sync(t); +} + +static int start_wd_on_cpu(unsigned int cpu) +{ + if (cpumask_test_cpu(cpu, &wd_cpus_enabled)) { + WARN_ON(1); + return 0; + } + + if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) + return 0; + + if (watchdog_suspended) + return 0; + + if (!cpumask_test_cpu(cpu, &watchdog_cpumask)) + return 0; + + cpumask_set_cpu(cpu, &wd_cpus_enabled); + if (cpumask_weight(&wd_cpus_enabled) == 1) { + cpumask_set_cpu(cpu, &wd_smp_cpus_pending); + wd_smp_last_reset_tb = get_tb(); + } + smp_wmb(); + start_watchdog_timer_on(cpu); + + return 0; +} + +static int stop_wd_on_cpu(unsigned int cpu) +{ + if (!cpumask_test_cpu(cpu, &wd_cpus_enabled)) + return 0; /* Can happen in CPU unplug case */ + + stop_watchdog_timer_on(cpu); + + cpumask_clear_cpu(cpu, &wd_cpus_enabled); + wd_smp_clear_cpu_pending(cpu, get_tb()); + + return 0; +} + +static void watchdog_calc_timeouts(void) +{ + wd_panic_timeout_tb = watchdog_thresh * ppc_tb_freq; + + /* Have the SMP detector trigger a bit later */ + wd_smp_panic_timeout_tb = wd_panic_timeout_tb * 3 / 2; + + /* 2/5 is the factor that the perf based detector uses */ + wd_timer_period_ms = watchdog_thresh * 1000 * 2 / 5; +} + +void watchdog_nmi_reconfigure(void) +{ + int cpu; + + watchdog_calc_timeouts(); + + for_each_cpu(cpu, &wd_cpus_enabled) + stop_wd_on_cpu(cpu); + + for_each_cpu_and(cpu, cpu_online_mask, &watchdog_cpumask) + start_wd_on_cpu(cpu); +} + +/* + * This runs after lockup_detector_init() which sets up watchdog_cpumask. + */ +static int __init powerpc_watchdog_init(void) +{ + int err; + + watchdog_calc_timeouts(); + + err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "powerpc/watchdog:online", + start_wd_on_cpu, stop_wd_on_cpu); + if (err < 0) + pr_warn("Watchdog could not be initialized"); + + return 0; +} +arch_initcall(powerpc_watchdog_init); + +static void handle_backtrace_ipi(struct pt_regs *regs) +{ + nmi_cpu_backtrace(regs); +} + +static void raise_backtrace_ipi(cpumask_t *mask) +{ + unsigned int cpu; + + for_each_cpu(cpu, mask) { + if (cpu == smp_processor_id()) + handle_backtrace_ipi(NULL); + else + smp_send_nmi_ipi(cpu, handle_backtrace_ipi, 1000000); + } +} + +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) +{ + nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_backtrace_ipi); +} diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 710e491206ed..8cb0190e2a73 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -93,7 +93,7 @@ int kvmppc_allocate_hpt(struct kvm_hpt_info *info, u32 order) } if (!hpt) - hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT + hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_RETRY_MAYFAIL |__GFP_NOWARN, order - PAGE_SHIFT); if (!hpt) diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index f3917705c686..41cf5ae273cf 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -233,192 +233,192 @@ static long calc_offset(struct fixup_entry *entry, unsigned int *p) static void test_basic_patching(void) { - extern unsigned int ftr_fixup_test1; - extern unsigned int end_ftr_fixup_test1; - extern unsigned int ftr_fixup_test1_orig; - extern unsigned int ftr_fixup_test1_expected; - int size = &end_ftr_fixup_test1 - &ftr_fixup_test1; + extern unsigned int ftr_fixup_test1[]; + extern unsigned int end_ftr_fixup_test1[]; + extern unsigned int ftr_fixup_test1_orig[]; + extern unsigned int ftr_fixup_test1_expected[]; + int size = end_ftr_fixup_test1 - ftr_fixup_test1; fixup.value = fixup.mask = 8; - fixup.start_off = calc_offset(&fixup, &ftr_fixup_test1 + 1); - fixup.end_off = calc_offset(&fixup, &ftr_fixup_test1 + 2); + fixup.start_off = calc_offset(&fixup, ftr_fixup_test1 + 1); + fixup.end_off = calc_offset(&fixup, ftr_fixup_test1 + 2); fixup.alt_start_off = fixup.alt_end_off = 0; /* Sanity check */ - check(memcmp(&ftr_fixup_test1, &ftr_fixup_test1_orig, size) == 0); + check(memcmp(ftr_fixup_test1, ftr_fixup_test1_orig, size) == 0); /* Check we don't patch if the value matches */ patch_feature_section(8, &fixup); - check(memcmp(&ftr_fixup_test1, &ftr_fixup_test1_orig, size) == 0); + check(memcmp(ftr_fixup_test1, ftr_fixup_test1_orig, size) == 0); /* Check we do patch if the value doesn't match */ patch_feature_section(0, &fixup); - check(memcmp(&ftr_fixup_test1, &ftr_fixup_test1_expected, size) == 0); + check(memcmp(ftr_fixup_test1, ftr_fixup_test1_expected, size) == 0); /* Check we do patch if the mask doesn't match */ - memcpy(&ftr_fixup_test1, &ftr_fixup_test1_orig, size); - check(memcmp(&ftr_fixup_test1, &ftr_fixup_test1_orig, size) == 0); + memcpy(ftr_fixup_test1, ftr_fixup_test1_orig, size); + check(memcmp(ftr_fixup_test1, ftr_fixup_test1_orig, size) == 0); patch_feature_section(~8, &fixup); - check(memcmp(&ftr_fixup_test1, &ftr_fixup_test1_expected, size) == 0); + check(memcmp(ftr_fixup_test1, ftr_fixup_test1_expected, size) == 0); } static void test_alternative_patching(void) { - extern unsigned int ftr_fixup_test2; - extern unsigned int end_ftr_fixup_test2; - extern unsigned int ftr_fixup_test2_orig; - extern unsigned int ftr_fixup_test2_alt; - extern unsigned int ftr_fixup_test2_expected; - int size = &end_ftr_fixup_test2 - &ftr_fixup_test2; + extern unsigned int ftr_fixup_test2[]; + extern unsigned int end_ftr_fixup_test2[]; + extern unsigned int ftr_fixup_test2_orig[]; + extern unsigned int ftr_fixup_test2_alt[]; + extern unsigned int ftr_fixup_test2_expected[]; + int size = end_ftr_fixup_test2 - ftr_fixup_test2; fixup.value = fixup.mask = 0xF; - fixup.start_off = calc_offset(&fixup, &ftr_fixup_test2 + 1); - fixup.end_off = calc_offset(&fixup, &ftr_fixup_test2 + 2); - fixup.alt_start_off = calc_offset(&fixup, &ftr_fixup_test2_alt); - fixup.alt_end_off = calc_offset(&fixup, &ftr_fixup_test2_alt + 1); + fixup.start_off = calc_offset(&fixup, ftr_fixup_test2 + 1); + fixup.end_off = calc_offset(&fixup, ftr_fixup_test2 + 2); + fixup.alt_start_off = calc_offset(&fixup, ftr_fixup_test2_alt); + fixup.alt_end_off = calc_offset(&fixup, ftr_fixup_test2_alt + 1); /* Sanity check */ - check(memcmp(&ftr_fixup_test2, &ftr_fixup_test2_orig, size) == 0); + check(memcmp(ftr_fixup_test2, ftr_fixup_test2_orig, size) == 0); /* Check we don't patch if the value matches */ patch_feature_section(0xF, &fixup); - check(memcmp(&ftr_fixup_test2, &ftr_fixup_test2_orig, size) == 0); + check(memcmp(ftr_fixup_test2, ftr_fixup_test2_orig, size) == 0); /* Check we do patch if the value doesn't match */ patch_feature_section(0, &fixup); - check(memcmp(&ftr_fixup_test2, &ftr_fixup_test2_expected, size) == 0); + check(memcmp(ftr_fixup_test2, ftr_fixup_test2_expected, size) == 0); /* Check we do patch if the mask doesn't match */ - memcpy(&ftr_fixup_test2, &ftr_fixup_test2_orig, size); - check(memcmp(&ftr_fixup_test2, &ftr_fixup_test2_orig, size) == 0); + memcpy(ftr_fixup_test2, ftr_fixup_test2_orig, size); + check(memcmp(ftr_fixup_test2, ftr_fixup_test2_orig, size) == 0); patch_feature_section(~0xF, &fixup); - check(memcmp(&ftr_fixup_test2, &ftr_fixup_test2_expected, size) == 0); + check(memcmp(ftr_fixup_test2, ftr_fixup_test2_expected, size) == 0); } static void test_alternative_case_too_big(void) { - extern unsigned int ftr_fixup_test3; - extern unsigned int end_ftr_fixup_test3; - extern unsigned int ftr_fixup_test3_orig; - extern unsigned int ftr_fixup_test3_alt; - int size = &end_ftr_fixup_test3 - &ftr_fixup_test3; + extern unsigned int ftr_fixup_test3[]; + extern unsigned int end_ftr_fixup_test3[]; + extern unsigned int ftr_fixup_test3_orig[]; + extern unsigned int ftr_fixup_test3_alt[]; + int size = end_ftr_fixup_test3 - ftr_fixup_test3; fixup.value = fixup.mask = 0xC; - fixup.start_off = calc_offset(&fixup, &ftr_fixup_test3 + 1); - fixup.end_off = calc_offset(&fixup, &ftr_fixup_test3 + 2); - fixup.alt_start_off = calc_offset(&fixup, &ftr_fixup_test3_alt); - fixup.alt_end_off = calc_offset(&fixup, &ftr_fixup_test3_alt + 2); + fixup.start_off = calc_offset(&fixup, ftr_fixup_test3 + 1); + fixup.end_off = calc_offset(&fixup, ftr_fixup_test3 + 2); + fixup.alt_start_off = calc_offset(&fixup, ftr_fixup_test3_alt); + fixup.alt_end_off = calc_offset(&fixup, ftr_fixup_test3_alt + 2); /* Sanity check */ - check(memcmp(&ftr_fixup_test3, &ftr_fixup_test3_orig, size) == 0); + check(memcmp(ftr_fixup_test3, ftr_fixup_test3_orig, size) == 0); /* Expect nothing to be patched, and the error returned to us */ check(patch_feature_section(0xF, &fixup) == 1); - check(memcmp(&ftr_fixup_test3, &ftr_fixup_test3_orig, size) == 0); + check(memcmp(ftr_fixup_test3, ftr_fixup_test3_orig, size) == 0); check(patch_feature_section(0, &fixup) == 1); - check(memcmp(&ftr_fixup_test3, &ftr_fixup_test3_orig, size) == 0); + check(memcmp(ftr_fixup_test3, ftr_fixup_test3_orig, size) == 0); check(patch_feature_section(~0xF, &fixup) == 1); - check(memcmp(&ftr_fixup_test3, &ftr_fixup_test3_orig, size) == 0); + check(memcmp(ftr_fixup_test3, ftr_fixup_test3_orig, size) == 0); } static void test_alternative_case_too_small(void) { - extern unsigned int ftr_fixup_test4; - extern unsigned int end_ftr_fixup_test4; - extern unsigned int ftr_fixup_test4_orig; - extern unsigned int ftr_fixup_test4_alt; - extern unsigned int ftr_fixup_test4_expected; - int size = &end_ftr_fixup_test4 - &ftr_fixup_test4; + extern unsigned int ftr_fixup_test4[]; + extern unsigned int end_ftr_fixup_test4[]; + extern unsigned int ftr_fixup_test4_orig[]; + extern unsigned int ftr_fixup_test4_alt[]; + extern unsigned int ftr_fixup_test4_expected[]; + int size = end_ftr_fixup_test4 - ftr_fixup_test4; unsigned long flag; /* Check a high-bit flag */ flag = 1UL << ((sizeof(unsigned long) - 1) * 8); fixup.value = fixup.mask = flag; - fixup.start_off = calc_offset(&fixup, &ftr_fixup_test4 + 1); - fixup.end_off = calc_offset(&fixup, &ftr_fixup_test4 + 5); - fixup.alt_start_off = calc_offset(&fixup, &ftr_fixup_test4_alt); - fixup.alt_end_off = calc_offset(&fixup, &ftr_fixup_test4_alt + 2); + fixup.start_off = calc_offset(&fixup, ftr_fixup_test4 + 1); + fixup.end_off = calc_offset(&fixup, ftr_fixup_test4 + 5); + fixup.alt_start_off = calc_offset(&fixup, ftr_fixup_test4_alt); + fixup.alt_end_off = calc_offset(&fixup, ftr_fixup_test4_alt + 2); /* Sanity check */ - check(memcmp(&ftr_fixup_test4, &ftr_fixup_test4_orig, size) == 0); + check(memcmp(ftr_fixup_test4, ftr_fixup_test4_orig, size) == 0); /* Check we don't patch if the value matches */ patch_feature_section(flag, &fixup); - check(memcmp(&ftr_fixup_test4, &ftr_fixup_test4_orig, size) == 0); + check(memcmp(ftr_fixup_test4, ftr_fixup_test4_orig, size) == 0); /* Check we do patch if the value doesn't match */ patch_feature_section(0, &fixup); - check(memcmp(&ftr_fixup_test4, &ftr_fixup_test4_expected, size) == 0); + check(memcmp(ftr_fixup_test4, ftr_fixup_test4_expected, size) == 0); /* Check we do patch if the mask doesn't match */ - memcpy(&ftr_fixup_test4, &ftr_fixup_test4_orig, size); - check(memcmp(&ftr_fixup_test4, &ftr_fixup_test4_orig, size) == 0); + memcpy(ftr_fixup_test4, ftr_fixup_test4_orig, size); + check(memcmp(ftr_fixup_test4, ftr_fixup_test4_orig, size) == 0); patch_feature_section(~flag, &fixup); - check(memcmp(&ftr_fixup_test4, &ftr_fixup_test4_expected, size) == 0); + check(memcmp(ftr_fixup_test4, ftr_fixup_test4_expected, size) == 0); } static void test_alternative_case_with_branch(void) { - extern unsigned int ftr_fixup_test5; - extern unsigned int end_ftr_fixup_test5; - extern unsigned int ftr_fixup_test5_expected; - int size = &end_ftr_fixup_test5 - &ftr_fixup_test5; + extern unsigned int ftr_fixup_test5[]; + extern unsigned int end_ftr_fixup_test5[]; + extern unsigned int ftr_fixup_test5_expected[]; + int size = end_ftr_fixup_test5 - ftr_fixup_test5; - check(memcmp(&ftr_fixup_test5, &ftr_fixup_test5_expected, size) == 0); + check(memcmp(ftr_fixup_test5, ftr_fixup_test5_expected, size) == 0); } static void test_alternative_case_with_external_branch(void) { - extern unsigned int ftr_fixup_test6; - extern unsigned int end_ftr_fixup_test6; - extern unsigned int ftr_fixup_test6_expected; - int size = &end_ftr_fixup_test6 - &ftr_fixup_test6; + extern unsigned int ftr_fixup_test6[]; + extern unsigned int end_ftr_fixup_test6[]; + extern unsigned int ftr_fixup_test6_expected[]; + int size = end_ftr_fixup_test6 - ftr_fixup_test6; - check(memcmp(&ftr_fixup_test6, &ftr_fixup_test6_expected, size) == 0); + check(memcmp(ftr_fixup_test6, ftr_fixup_test6_expected, size) == 0); } static void test_cpu_macros(void) { - extern u8 ftr_fixup_test_FTR_macros; - extern u8 ftr_fixup_test_FTR_macros_expected; - unsigned long size = &ftr_fixup_test_FTR_macros_expected - - &ftr_fixup_test_FTR_macros; + extern u8 ftr_fixup_test_FTR_macros[]; + extern u8 ftr_fixup_test_FTR_macros_expected[]; + unsigned long size = ftr_fixup_test_FTR_macros_expected - + ftr_fixup_test_FTR_macros; /* The fixups have already been done for us during boot */ - check(memcmp(&ftr_fixup_test_FTR_macros, - &ftr_fixup_test_FTR_macros_expected, size) == 0); + check(memcmp(ftr_fixup_test_FTR_macros, + ftr_fixup_test_FTR_macros_expected, size) == 0); } static void test_fw_macros(void) { #ifdef CONFIG_PPC64 - extern u8 ftr_fixup_test_FW_FTR_macros; - extern u8 ftr_fixup_test_FW_FTR_macros_expected; - unsigned long size = &ftr_fixup_test_FW_FTR_macros_expected - - &ftr_fixup_test_FW_FTR_macros; + extern u8 ftr_fixup_test_FW_FTR_macros[]; + extern u8 ftr_fixup_test_FW_FTR_macros_expected[]; + unsigned long size = ftr_fixup_test_FW_FTR_macros_expected - + ftr_fixup_test_FW_FTR_macros; /* The fixups have already been done for us during boot */ - check(memcmp(&ftr_fixup_test_FW_FTR_macros, - &ftr_fixup_test_FW_FTR_macros_expected, size) == 0); + check(memcmp(ftr_fixup_test_FW_FTR_macros, + ftr_fixup_test_FW_FTR_macros_expected, size) == 0); #endif } static void test_lwsync_macros(void) { - extern u8 lwsync_fixup_test; - extern u8 end_lwsync_fixup_test; - extern u8 lwsync_fixup_test_expected_LWSYNC; - extern u8 lwsync_fixup_test_expected_SYNC; - unsigned long size = &end_lwsync_fixup_test - - &lwsync_fixup_test; + extern u8 lwsync_fixup_test[]; + extern u8 end_lwsync_fixup_test[]; + extern u8 lwsync_fixup_test_expected_LWSYNC[]; + extern u8 lwsync_fixup_test_expected_SYNC[]; + unsigned long size = end_lwsync_fixup_test - + lwsync_fixup_test; /* The fixups have already been done for us during boot */ if (cur_cpu_spec->cpu_features & CPU_FTR_LWSYNC) { - check(memcmp(&lwsync_fixup_test, - &lwsync_fixup_test_expected_LWSYNC, size) == 0); + check(memcmp(lwsync_fixup_test, + lwsync_fixup_test_expected_LWSYNC, size) == 0); } else { - check(memcmp(&lwsync_fixup_test, - &lwsync_fixup_test_expected_SYNC, size) == 0); + check(memcmp(lwsync_fixup_test, + lwsync_fixup_test_expected_SYNC, size) == 0); } } diff --git a/arch/powerpc/mm/mmap.c b/arch/powerpc/mm/mmap.c index 0ee6be4f1ba4..5d78b193fec4 100644 --- a/arch/powerpc/mm/mmap.c +++ b/arch/powerpc/mm/mmap.c @@ -34,16 +34,9 @@ /* * Top of mmap area (just below the process stack). * - * Leave at least a ~128 MB hole on 32bit applications. - * - * On 64bit applications we randomise the stack by 1GB so we need to - * space our mmap start address by a further 1GB, otherwise there is a - * chance the mmap area will end up closer to the stack than our ulimit - * requires. + * Leave at least a ~128 MB hole. */ -#define MIN_GAP32 (128*1024*1024) -#define MIN_GAP64 ((128 + 1024)*1024*1024UL) -#define MIN_GAP ((is_32bit_task()) ? MIN_GAP32 : MIN_GAP64) +#define MIN_GAP (128*1024*1024) #define MAX_GAP (TASK_SIZE/6*5) static inline int mmap_is_legacy(void) @@ -71,9 +64,26 @@ unsigned long arch_mmap_rnd(void) return rnd << PAGE_SHIFT; } +static inline unsigned long stack_maxrandom_size(void) +{ + if (!(current->flags & PF_RANDOMIZE)) + return 0; + + /* 8MB for 32bit, 1GB for 64bit */ + if (is_32bit_task()) + return (1<<23); + else + return (1<<30); +} + static inline unsigned long mmap_base(unsigned long rnd) { unsigned long gap = rlimit(RLIMIT_STACK); + unsigned long pad = stack_maxrandom_size() + stack_guard_gap; + + /* Values close to RLIM_INFINITY can overflow. */ + if (gap + pad > gap) + gap += pad; if (gap < MIN_GAP) gap = MIN_GAP; diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index 49a6bd45957b..3d0b14afa232 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -246,6 +246,7 @@ void arch_crash_save_vmcoreinfo(void) VMCOREINFO_SYMBOL(lowcore_ptr); VMCOREINFO_SYMBOL(high_memory); VMCOREINFO_LENGTH(lowcore_ptr, NR_CPUS); + mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note()); } void machine_shutdown(void) diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 3ae756c0db3d..3d1d808ea8a9 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -496,11 +496,6 @@ static void __init setup_memory_end(void) pr_notice("The maximum memory size is %luMB\n", memory_end >> 20); } -static void __init setup_vmcoreinfo(void) -{ - mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note()); -} - #ifdef CONFIG_CRASH_DUMP /* @@ -939,7 +934,6 @@ void __init setup_arch(char **cmdline_p) #endif setup_resources(); - setup_vmcoreinfo(); setup_lowcore(); smp_fill_possible_mask(); cpu_detect_mhz_feature(); diff --git a/arch/sh/include/asm/bug.h b/arch/sh/include/asm/bug.h index 1b77f068be2b..c9828f785ca0 100644 --- a/arch/sh/include/asm/bug.h +++ b/arch/sh/include/asm/bug.h @@ -48,6 +48,7 @@ do { \ "i" (__FILE__), \ "i" (__LINE__), "i" (0), \ "i" (sizeof(struct bug_entry))); \ + unreachable(); \ } while (0) #define __WARN_FLAGS(flags) \ diff --git a/arch/sh/include/asm/stackprotector.h b/arch/sh/include/asm/stackprotector.h index d9df3a76847c..141515a43b78 100644 --- a/arch/sh/include/asm/stackprotector.h +++ b/arch/sh/include/asm/stackprotector.h @@ -19,6 +19,7 @@ static __always_inline void boot_init_stack_canary(void) /* Try to get a semi random initial value. */ get_random_bytes(&canary, sizeof(canary)); canary ^= LINUX_VERSION_CODE; + canary &= CANARY_MASK; current->stack_canary = canary; __stack_chk_guard = current->stack_canary; diff --git a/arch/sh/mm/cache-sh5.c b/arch/sh/mm/cache-sh5.c index d94dadedf74f..445b5e69b73c 100644 --- a/arch/sh/mm/cache-sh5.c +++ b/arch/sh/mm/cache-sh5.c @@ -234,7 +234,7 @@ static void sh64_icache_inv_current_user_range(unsigned long start, unsigned lon #define DUMMY_ALLOCO_AREA_SIZE ((L1_CACHE_BYTES << 10) + (1024 * 4)) static unsigned char dummy_alloco_area[DUMMY_ALLOCO_AREA_SIZE] __cacheline_aligned = { 0, }; -static void inline sh64_dcache_purge_sets(int sets_to_purge_base, int n_sets) +static inline void sh64_dcache_purge_sets(int sets_to_purge_base, int n_sets) { /* Purge all ways in a particular block of sets, specified by the base set number and number of sets. Can handle wrap-around, if that's diff --git a/arch/sparc/include/asm/nmi.h b/arch/sparc/include/asm/nmi.h index 26ad2b2607c6..284eac3ffaf2 100644 --- a/arch/sparc/include/asm/nmi.h +++ b/arch/sparc/include/asm/nmi.h @@ -7,6 +7,7 @@ void nmi_adjust_hz(unsigned int new_hz); extern atomic_t nmi_active; +void arch_touch_nmi_watchdog(void); void start_nmi_watchdog(void *unused); void stop_nmi_watchdog(void *unused); diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c index e4b4e790bf89..fa466ce45bc9 100644 --- a/arch/sparc/kernel/mdesc.c +++ b/arch/sparc/kernel/mdesc.c @@ -205,7 +205,7 @@ static struct mdesc_handle *mdesc_kmalloc(unsigned int mdesc_size) handle_size = (sizeof(struct mdesc_handle) - sizeof(struct mdesc_hdr) + mdesc_size); - base = kmalloc(handle_size + 15, GFP_KERNEL | __GFP_REPEAT); + base = kmalloc(handle_size + 15, GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!base) return NULL; diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c index 95e73c63c99d..048ad783ea3f 100644 --- a/arch/sparc/kernel/nmi.c +++ b/arch/sparc/kernel/nmi.c @@ -51,7 +51,7 @@ static DEFINE_PER_CPU(unsigned int, last_irq_sum); static DEFINE_PER_CPU(long, alert_counter); static DEFINE_PER_CPU(int, nmi_touch); -void touch_nmi_watchdog(void) +void arch_touch_nmi_watchdog(void) { if (atomic_read(&nmi_active)) { int cpu; @@ -61,10 +61,8 @@ void touch_nmi_watchdog(void) per_cpu(nmi_touch, cpu) = 1; } } - - touch_softlockup_watchdog(); } -EXPORT_SYMBOL(touch_nmi_watchdog); +EXPORT_SYMBOL(arch_touch_nmi_watchdog); static void die_nmi(const char *str, struct pt_regs *regs, int do_panic) { diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 94a18681353d..781521b7cf9e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -50,6 +50,7 @@ config X86 select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FAST_MULTIPLIER + select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_KCOV if X86_64 select ARCH_HAS_MMIO_FLUSH @@ -162,6 +163,7 @@ config X86 select HAVE_PCSPKR_PLATFORM select HAVE_PERF_EVENTS select HAVE_PERF_EVENTS_NMI + select HAVE_HARDLOCKUP_DETECTOR_PERF if HAVE_PERF_EVENTS_NMI select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP select HAVE_REGS_AND_STACK_ACCESS_API diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 00241c815524..a0838ab929f2 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -411,3 +411,8 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, debug_putstr("done.\nBooting the kernel.\n"); return output; } + +void fortify_panic(const char *name) +{ + error("detected buffer overflow"); +} diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index d2ff779f347e..796ff6c1aa53 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -33,7 +33,7 @@ #ifdef CONFIG_X86_32 -extern unsigned long asmlinkage efi_call_phys(void *, ...); +extern asmlinkage unsigned long efi_call_phys(void *, ...); #define arch_efi_call_virt_setup() kernel_fpu_begin() #define arch_efi_call_virt_teardown() kernel_fpu_end() @@ -52,7 +52,7 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...); #define EFI_LOADER_SIGNATURE "EL64" -extern u64 asmlinkage efi_call(void *fp, ...); +extern asmlinkage u64 efi_call(void *fp, ...); #define efi_call_phys(f, args...) efi_call((f), args) diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h index dcbd9bcce714..8abedf1d650e 100644 --- a/arch/x86/include/asm/stackprotector.h +++ b/arch/x86/include/asm/stackprotector.h @@ -74,6 +74,7 @@ static __always_inline void boot_init_stack_canary(void) get_random_bytes(&canary, sizeof(canary)); tsc = rdtsc(); canary += tsc + (tsc << 32UL); + canary &= CANARY_MASK; current->stack_canary = canary; #ifdef CONFIG_X86_64 diff --git a/arch/x86/include/asm/string_32.h b/arch/x86/include/asm/string_32.h index 3d3e8353ee5c..e9ee84873de5 100644 --- a/arch/x86/include/asm/string_32.h +++ b/arch/x86/include/asm/string_32.h @@ -142,7 +142,9 @@ static __always_inline void *__constant_memcpy(void *to, const void *from, } #define __HAVE_ARCH_MEMCPY +extern void *memcpy(void *, const void *, size_t); +#ifndef CONFIG_FORTIFY_SOURCE #ifdef CONFIG_X86_USE_3DNOW #include <asm/mmx.h> @@ -195,11 +197,15 @@ static inline void *__memcpy3d(void *to, const void *from, size_t len) #endif #endif +#endif /* !CONFIG_FORTIFY_SOURCE */ #define __HAVE_ARCH_MEMMOVE void *memmove(void *dest, const void *src, size_t n); +extern int memcmp(const void *, const void *, size_t); +#ifndef CONFIG_FORTIFY_SOURCE #define memcmp __builtin_memcmp +#endif #define __HAVE_ARCH_MEMCHR extern void *memchr(const void *cs, int c, size_t count); @@ -321,6 +327,8 @@ void *__constant_c_and_count_memset(void *s, unsigned long pattern, : __memset_generic((s), (c), (count))) #define __HAVE_ARCH_MEMSET +extern void *memset(void *, int, size_t); +#ifndef CONFIG_FORTIFY_SOURCE #if (__GNUC__ >= 4) #define memset(s, c, count) __builtin_memset(s, c, count) #else @@ -330,6 +338,7 @@ void *__constant_c_and_count_memset(void *s, unsigned long pattern, (count)) \ : __memset((s), (c), (count))) #endif +#endif /* !CONFIG_FORTIFY_SOURCE */ /* * find the first occurrence of byte 'c', or 1 past the area if none diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h index 1f22bc277c45..2a8c822de1fc 100644 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -31,6 +31,7 @@ static __always_inline void *__inline_memcpy(void *to, const void *from, size_t extern void *memcpy(void *to, const void *from, size_t len); extern void *__memcpy(void *to, const void *from, size_t len); +#ifndef CONFIG_FORTIFY_SOURCE #ifndef CONFIG_KMEMCHECK #if (__GNUC__ == 4 && __GNUC_MINOR__ < 3) || __GNUC__ < 4 #define memcpy(dst, src, len) \ @@ -51,6 +52,7 @@ extern void *__memcpy(void *to, const void *from, size_t len); */ #define memcpy(dst, src, len) __inline_memcpy((dst), (src), (len)) #endif +#endif /* !CONFIG_FORTIFY_SOURCE */ #define __HAVE_ARCH_MEMSET void *memset(void *s, int c, size_t n); @@ -77,6 +79,11 @@ int strcmp(const char *cs, const char *ct); #define memcpy(dst, src, len) __memcpy(dst, src, len) #define memmove(dst, src, len) __memmove(dst, src, len) #define memset(s, c, n) __memset(s, c, n) + +#ifndef __NO_FORTIFY +#define __NO_FORTIFY /* FORTIFY_SOURCE uses __builtin_memcpy, etc. */ +#endif + #endif #define __HAVE_ARCH_MEMCPY_MCSAFE 1 diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index c73c9fb281e1..d6f387780849 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -19,7 +19,7 @@ #include <linux/init.h> #include <linux/delay.h> -#ifdef CONFIG_HARDLOCKUP_DETECTOR +#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF u64 hw_nmi_get_sample_period(int watchdog_thresh) { return (u64)(cpu_khz) * 1000 * watchdog_thresh; diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 22217ece26c8..44404e2307bb 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -457,7 +457,7 @@ static int prepare_elf64_headers(struct crash_elf_data *ced, bufp += sizeof(Elf64_Phdr); phdr->p_type = PT_NOTE; phdr->p_offset = phdr->p_paddr = paddr_vmcoreinfo_note(); - phdr->p_filesz = phdr->p_memsz = sizeof(vmcoreinfo_note); + phdr->p_filesz = phdr->p_memsz = VMCOREINFO_NOTE_SIZE; (ehdr->e_phnum)++; #ifdef CONFIG_X86_64 diff --git a/arch/x86/lib/memcpy_32.c b/arch/x86/lib/memcpy_32.c index cad12634d6bd..2eab7d0bfedd 100644 --- a/arch/x86/lib/memcpy_32.c +++ b/arch/x86/lib/memcpy_32.c @@ -6,7 +6,7 @@ __visible void *memcpy(void *to, const void *from, size_t n) { -#ifdef CONFIG_X86_USE_3DNOW +#if defined(CONFIG_X86_USE_3DNOW) && !defined(CONFIG_FORTIFY_SOURCE) return __memcpy3d(to, from, n); #else return __memcpy(to, from, n); diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 797295e792b2..229d04a83f85 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -92,13 +92,18 @@ unsigned long arch_mmap_rnd(void) static unsigned long mmap_base(unsigned long rnd, unsigned long task_size) { unsigned long gap = rlimit(RLIMIT_STACK); + unsigned long pad = stack_maxrandom_size(task_size) + stack_guard_gap; unsigned long gap_min, gap_max; + /* Values close to RLIM_INFINITY can overflow. */ + if (gap + pad > gap) + gap += pad; + /* * Top of mmap area (just below the process stack). * Leave an at least ~128 MB hole with possible stack randomization. */ - gap_min = SIZE_128M + stack_maxrandom_size(task_size); + gap_min = SIZE_128M; gap_max = (task_size / 6) * 5; if (gap < gap_min) diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 1d7a7213a310..cab28cf2cffb 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -2693,8 +2693,8 @@ EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region); phys_addr_t paddr_vmcoreinfo_note(void) { if (xen_pv_domain()) - return virt_to_machine(&vmcoreinfo_note).maddr; + return virt_to_machine(vmcoreinfo_note).maddr; else - return __pa_symbol(&vmcoreinfo_note); + return __pa(vmcoreinfo_note); } #endif /* CONFIG_KEXEC_CORE */ diff --git a/drivers/char/random.c b/drivers/char/random.c index 01a260f67437..23cab7a8c1c1 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -987,6 +987,11 @@ void add_device_randomness(const void *buf, unsigned int size) unsigned long time = random_get_entropy() ^ jiffies; unsigned long flags; + if (!crng_ready()) { + crng_fast_load(buf, size); + return; + } + trace_add_device_randomness(size, _RET_IP_); spin_lock_irqsave(&input_pool.lock, flags); _mix_pool_bytes(&input_pool, buf, size); diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index f7425960f6a5..37e24f525162 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -17,6 +17,7 @@ cflags-$(CONFIG_ARM) := $(subst -pg,,$(KBUILD_CFLAGS)) \ cflags-$(CONFIG_EFI_ARMSTUB) += -I$(srctree)/scripts/dtc/libfdt KBUILD_CFLAGS := $(cflags-y) -DDISABLE_BRANCH_PROFILING \ + -D__NO_FORTIFY \ $(call cc-option,-ffreestanding) \ $(call cc-option,-fno-stack-protector) diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 7dcac3bfb771..969bac8404f1 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2434,8 +2434,9 @@ rebuild_st: * again with !__GFP_NORETRY. However, we still * want to fail this allocation rather than * trigger the out-of-memory killer and for - * this we want the future __GFP_MAYFAIL. + * this we want __GFP_RETRY_MAYFAIL. */ + gfp |= __GFP_RETRY_MAYFAIL; } } while (1); diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index 23039768f541..be944d5aa9af 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -995,7 +995,9 @@ static int send_atomic_ack(struct rxe_qp *qp, struct rxe_pkt_info *pkt, free_rd_atomic_resource(qp, res); rxe_advance_resp_resource(qp); - memcpy(SKB_TO_PKT(skb), &ack_pkt, sizeof(skb->cb)); + memcpy(SKB_TO_PKT(skb), &ack_pkt, sizeof(ack_pkt)); + memset((unsigned char *)SKB_TO_PKT(skb) + sizeof(ack_pkt), 0, + sizeof(skb->cb) - sizeof(ack_pkt)); res->type = RXE_ATOMIC_MASK; res->atomic.skb = skb; diff --git a/drivers/mmc/host/wbsd.c b/drivers/mmc/host/wbsd.c index e15a9733fcfd..9668616faf16 100644 --- a/drivers/mmc/host/wbsd.c +++ b/drivers/mmc/host/wbsd.c @@ -1386,7 +1386,7 @@ static void wbsd_request_dma(struct wbsd_host *host, int dma) * order for ISA to be able to DMA to it. */ host->dma_buffer = kmalloc(WBSD_DMA_SIZE, - GFP_NOIO | GFP_DMA | __GFP_REPEAT | __GFP_NOWARN); + GFP_NOIO | GFP_DMA | __GFP_RETRY_MAYFAIL | __GFP_NOWARN); if (!host->dma_buffer) goto free; diff --git a/drivers/s390/char/vmcp.c b/drivers/s390/char/vmcp.c index 65f5a794f26d..98749fa817da 100644 --- a/drivers/s390/char/vmcp.c +++ b/drivers/s390/char/vmcp.c @@ -98,7 +98,7 @@ vmcp_write(struct file *file, const char __user *buff, size_t count, } if (!session->response) session->response = (char *)__get_free_pages(GFP_KERNEL - | __GFP_REPEAT | GFP_DMA, + | __GFP_RETRY_MAYFAIL | GFP_DMA, get_order(session->bufsize)); if (!session->response) { mutex_unlock(&session->mutex); diff --git a/drivers/s390/net/ctcm_main.c b/drivers/s390/net/ctcm_main.c index 1563b1458e44..2ade6131a89f 100644 --- a/drivers/s390/net/ctcm_main.c +++ b/drivers/s390/net/ctcm_main.c @@ -1115,7 +1115,7 @@ static const struct net_device_ops ctcm_mpc_netdev_ops = { .ndo_start_xmit = ctcmpc_tx, }; -void static ctcm_dev_setup(struct net_device *dev) +static void ctcm_dev_setup(struct net_device *dev) { dev->type = ARPHRD_SLIP; dev->tx_queue_len = 100; diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 3062cde33a3d..8975cd321390 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -2408,7 +2408,7 @@ static int qeth_l3_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) return rc; } -int inline qeth_l3_get_cast_type(struct qeth_card *card, struct sk_buff *skb) +inline int qeth_l3_get_cast_type(struct qeth_card *card, struct sk_buff *skb) { int cast_type = RTN_UNSPEC; struct neighbour *n = NULL; diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index f1b3a46bdcaf..1bdc10651bcd 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -252,7 +252,7 @@ int transport_alloc_session_tags(struct se_session *se_sess, int rc; se_sess->sess_cmd_map = kzalloc(tag_num * tag_size, - GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT); + GFP_KERNEL | __GFP_NOWARN | __GFP_RETRY_MAYFAIL); if (!se_sess->sess_cmd_map) { se_sess->sess_cmd_map = vzalloc(tag_num * tag_size); if (!se_sess->sess_cmd_map) { diff --git a/drivers/tty/serial/ioc3_serial.c b/drivers/tty/serial/ioc3_serial.c index 2a61dd6b4009..906ee770ff4a 100644 --- a/drivers/tty/serial/ioc3_serial.c +++ b/drivers/tty/serial/ioc3_serial.c @@ -377,7 +377,7 @@ static struct ioc3_port *get_ioc3_port(struct uart_port *the_port) * called per port from attach... * @port: port to initialize */ -static int inline port_init(struct ioc3_port *port) +static inline int port_init(struct ioc3_port *port) { uint32_t sio_cr; struct port_hooks *hooks = port->ip_hooks; @@ -1430,7 +1430,7 @@ static int receive_chars(struct uart_port *the_port) * @pending: interrupts to handle */ -static int inline +static inline int ioc3uart_intr_one(struct ioc3_submodule *is, struct ioc3_driver_data *idd, unsigned int pending) diff --git a/drivers/tty/serial/ioc4_serial.c b/drivers/tty/serial/ioc4_serial.c index f96bcf9bee25..43d7d32eb150 100644 --- a/drivers/tty/serial/ioc4_serial.c +++ b/drivers/tty/serial/ioc4_serial.c @@ -824,7 +824,7 @@ pending_intrs(struct ioc4_soft *soft, int type) * called per port from attach... * @port: port to initialize */ -static int inline port_init(struct ioc4_port *port) +static inline int port_init(struct ioc4_port *port) { uint32_t sio_cr; struct hooks *hooks = port->ip_hooks; @@ -1048,7 +1048,7 @@ static irqreturn_t ioc4_intr(int irq, void *arg) * IOC4 with serial ports in the system. * @idd: Master module data for this IOC4 */ -static int inline ioc4_attach_local(struct ioc4_driver_data *idd) +static inline int ioc4_attach_local(struct ioc4_driver_data *idd) { struct ioc4_port *port; struct ioc4_port *ports[IOC4_NUM_SERIAL_PORTS]; diff --git a/drivers/usb/serial/safe_serial.c b/drivers/usb/serial/safe_serial.c index 8a069aa154ed..27d7a7016298 100644 --- a/drivers/usb/serial/safe_serial.c +++ b/drivers/usb/serial/safe_serial.c @@ -180,7 +180,7 @@ static const __u16 crc10_table[256] = { * Perform a memcpy and calculate fcs using ppp 10bit CRC algorithm. Return * new 10 bit FCS. */ -static __u16 __inline__ fcs_compute10(unsigned char *sp, int len, __u16 fcs) +static inline __u16 fcs_compute10(unsigned char *sp, int len, __u16 fcs) { for (; len-- > 0; fcs = CRC10_FCS(fcs, *sp++)); return fcs; diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index e3d7ea1288c6..06d044862e58 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -897,7 +897,7 @@ static int vhost_net_open(struct inode *inode, struct file *f) struct sk_buff **queue; int i; - n = kvmalloc(sizeof *n, GFP_KERNEL | __GFP_REPEAT); + n = kvmalloc(sizeof *n, GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!n) return -ENOMEM; vqs = kmalloc(VHOST_NET_VQ_MAX * sizeof(*vqs), GFP_KERNEL); diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index fd6c8b66f06f..ff02a942c4d5 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -1404,7 +1404,7 @@ static int vhost_scsi_open(struct inode *inode, struct file *f) struct vhost_virtqueue **vqs; int r = -ENOMEM, i; - vs = kzalloc(sizeof(*vs), GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT); + vs = kzalloc(sizeof(*vs), GFP_KERNEL | __GFP_NOWARN | __GFP_RETRY_MAYFAIL); if (!vs) { vs = vzalloc(sizeof(*vs)); if (!vs) diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 3f63e03de8e8..c9de9c41aa97 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -508,7 +508,7 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file) /* This struct is large and allocation could fail, fall back to vmalloc * if there is no other way. */ - vsock = kvmalloc(sizeof(*vsock), GFP_KERNEL | __GFP_REPEAT); + vsock = kvmalloc(sizeof(*vsock), GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!vsock) return -ENOMEM; diff --git a/drivers/video/fbdev/intelfb/intelfbdrv.c b/drivers/video/fbdev/intelfb/intelfbdrv.c index 6b444400a86c..ffc391208b27 100644 --- a/drivers/video/fbdev/intelfb/intelfbdrv.c +++ b/drivers/video/fbdev/intelfb/intelfbdrv.c @@ -907,7 +907,7 @@ static void intelfb_pci_unregister(struct pci_dev *pdev) * helper functions * ***************************************************************/ -int __inline__ intelfb_var_to_depth(const struct fb_var_screeninfo *var) +__inline__ int intelfb_var_to_depth(const struct fb_var_screeninfo *var) { DBG_MSG("intelfb_var_to_depth: bpp: %d, green.length is %d\n", var->bits_per_pixel, var->green.length); diff --git a/drivers/video/fbdev/omap/lcdc.c b/drivers/video/fbdev/omap/lcdc.c index e3d9b9ea5498..938cba0d24ae 100644 --- a/drivers/video/fbdev/omap/lcdc.c +++ b/drivers/video/fbdev/omap/lcdc.c @@ -79,12 +79,12 @@ static struct omap_lcd_controller { unsigned long vram_size; } lcdc; -static void inline enable_irqs(int mask) +static inline void enable_irqs(int mask) { lcdc.irq_mask |= mask; } -static void inline disable_irqs(int mask) +static inline void disable_irqs(int mask) { lcdc.irq_mask &= ~mask; } @@ -466,7 +466,7 @@ static void calc_ck_div(int is_tft, int pck, int *pck_div) } } -static void inline setup_regs(void) +static inline void setup_regs(void) { u32 l; struct lcd_panel *panel = lcdc.fbdev->panel; diff --git a/fs/Kconfig b/fs/Kconfig index b0e42b6a96b9..7aee6d699fd6 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -80,7 +80,6 @@ config EXPORTFS_BLOCK_OPS config FILE_LOCKING bool "Enable POSIX file locking API" if EXPERT default y - select PERCPU_RWSEM help This option enables standard file locking support, required for filesystems like NFS and for the flock() system diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index 25e312cb6071..9a69392f1fb3 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -419,7 +419,7 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent) if (i_sblock > info->si_blocks || i_eblock > info->si_blocks || i_sblock > i_eblock || - i_eoff > s_size || + (i_eoff != le32_to_cpu(-1) && i_eoff > s_size) || i_sblock * BFS_BSIZE > i_eoff) { printf("Inode 0x%08x corrupted\n", i); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index a6d194831ed8..e767e4389cb1 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -960,10 +960,14 @@ static void ep_show_fdinfo(struct seq_file *m, struct file *f) mutex_lock(&ep->mtx); for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) { struct epitem *epi = rb_entry(rbp, struct epitem, rbn); + struct inode *inode = file_inode(epi->ffd.file); - seq_printf(m, "tfd: %8d events: %8x data: %16llx\n", + seq_printf(m, "tfd: %8d events: %8x data: %16llx " + " pos:%lli ino:%lx sdev:%x\n", epi->ffd.fd, epi->event.events, - (long long)epi->event.data); + (long long)epi->event.data, + (long long)epi->ffd.file->f_pos, + inode->i_ino, inode->i_sb->s_dev); if (seq_has_overflowed(m)) break; } @@ -1073,6 +1077,50 @@ static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd) return epir; } +#ifdef CONFIG_CHECKPOINT_RESTORE +static struct epitem *ep_find_tfd(struct eventpoll *ep, int tfd, unsigned long toff) +{ + struct rb_node *rbp; + struct epitem *epi; + + for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) { + epi = rb_entry(rbp, struct epitem, rbn); + if (epi->ffd.fd == tfd) { + if (toff == 0) + return epi; + else + toff--; + } + cond_resched(); + } + + return NULL; +} + +struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, + unsigned long toff) +{ + struct file *file_raw; + struct eventpoll *ep; + struct epitem *epi; + + if (!is_file_epoll(file)) + return ERR_PTR(-EINVAL); + + ep = file->private_data; + + mutex_lock(&ep->mtx); + epi = ep_find_tfd(ep, tfd, toff); + if (epi) + file_raw = epi->ffd.file; + else + file_raw = ERR_PTR(-ENOENT); + mutex_unlock(&ep->mtx); + + return file_raw; +} +#endif /* CONFIG_CHECKPOINT_RESTORE */ + /* * This is the callback that is passed to the wait queue wakeup * mechanism. It is called by the stored file descriptors when they diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 8b426f83909f..245c430a2e41 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -380,8 +380,8 @@ static void inode_switch_wbs_work_fn(struct work_struct *work) struct page *page = radix_tree_deref_slot_protected(slot, &mapping->tree_lock); if (likely(page) && PageDirty(page)) { - __dec_wb_stat(old_wb, WB_RECLAIMABLE); - __inc_wb_stat(new_wb, WB_RECLAIMABLE); + dec_wb_stat(old_wb, WB_RECLAIMABLE); + inc_wb_stat(new_wb, WB_RECLAIMABLE); } } @@ -391,8 +391,8 @@ static void inode_switch_wbs_work_fn(struct work_struct *work) &mapping->tree_lock); if (likely(page)) { WARN_ON_ONCE(!PageWriteback(page)); - __dec_wb_stat(old_wb, WB_WRITEBACK); - __inc_wb_stat(new_wb, WB_WRITEBACK); + dec_wb_stat(old_wb, WB_WRITEBACK); + inc_wb_stat(new_wb, WB_WRITEBACK); } } diff --git a/fs/proc/base.c b/fs/proc/base.c index f1e1927ccd48..88b773f318cd 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1355,6 +1355,53 @@ static const struct file_operations proc_fault_inject_operations = { .write = proc_fault_inject_write, .llseek = generic_file_llseek, }; + +static ssize_t proc_fail_nth_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct task_struct *task; + int err, n; + + task = get_proc_task(file_inode(file)); + if (!task) + return -ESRCH; + put_task_struct(task); + if (task != current) + return -EPERM; + err = kstrtoint_from_user(buf, count, 10, &n); + if (err) + return err; + if (n < 0 || n == INT_MAX) + return -EINVAL; + current->fail_nth = n + 1; + return count; +} + +static ssize_t proc_fail_nth_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct task_struct *task; + int err; + + task = get_proc_task(file_inode(file)); + if (!task) + return -ESRCH; + put_task_struct(task); + if (task != current) + return -EPERM; + if (count < 1) + return -EINVAL; + err = put_user((char)(current->fail_nth ? 'N' : 'Y'), buf); + if (err) + return err; + current->fail_nth = 0; + return 1; +} + +static const struct file_operations proc_fail_nth_operations = { + .read = proc_fail_nth_read, + .write = proc_fail_nth_write, +}; #endif @@ -3311,6 +3358,11 @@ static const struct pid_entry tid_base_stuff[] = { #endif #ifdef CONFIG_FAULT_INJECTION REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations), + /* + * Operations on the file check that the task is current, + * so we create it with 0666 to support testing under unprivileged user. + */ + REG("fail-nth", 0666, proc_fail_nth_operations), #endif #ifdef CONFIG_TASK_IO_ACCOUNTING ONE("io", S_IRUSR, proc_tid_io_accounting), diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 9bf06e2b1284..8f479229b349 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1078,16 +1078,30 @@ static int sysctl_err(const char *path, struct ctl_table *table, char *fmt, ...) return -EINVAL; } +static int sysctl_check_table_array(const char *path, struct ctl_table *table) +{ + int err = 0; + + if ((table->proc_handler == proc_douintvec) || + (table->proc_handler == proc_douintvec_minmax)) { + if (table->maxlen != sizeof(unsigned int)) + err |= sysctl_err(path, table, "array now allowed"); + } + + return err; +} + static int sysctl_check_table(const char *path, struct ctl_table *table) { int err = 0; for (; table->procname; table++) { if (table->child) - err = sysctl_err(path, table, "Not a file"); + err |= sysctl_err(path, table, "Not a file"); if ((table->proc_handler == proc_dostring) || (table->proc_handler == proc_dointvec) || (table->proc_handler == proc_douintvec) || + (table->proc_handler == proc_douintvec_minmax) || (table->proc_handler == proc_dointvec_minmax) || (table->proc_handler == proc_dointvec_jiffies) || (table->proc_handler == proc_dointvec_userhz_jiffies) || @@ -1095,15 +1109,17 @@ static int sysctl_check_table(const char *path, struct ctl_table *table) (table->proc_handler == proc_doulongvec_minmax) || (table->proc_handler == proc_doulongvec_ms_jiffies_minmax)) { if (!table->data) - err = sysctl_err(path, table, "No data"); + err |= sysctl_err(path, table, "No data"); if (!table->maxlen) - err = sysctl_err(path, table, "No maxlen"); + err |= sysctl_err(path, table, "No maxlen"); + else + err |= sysctl_check_table_array(path, table); } if (!table->proc_handler) - err = sysctl_err(path, table, "No proc_handler"); + err |= sysctl_err(path, table, "No proc_handler"); if ((table->mode & (S_IRUGO|S_IWUGO)) != table->mode) - err = sysctl_err(path, table, "bogus .mode 0%o", + err |= sysctl_err(path, table, "bogus .mode 0%o", table->mode); } return err; diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h index d6ea520162b2..4d85992d75b2 100644 --- a/fs/xfs/kmem.h +++ b/fs/xfs/kmem.h @@ -54,6 +54,16 @@ kmem_flags_convert(xfs_km_flags_t flags) lflags &= ~__GFP_FS; } + /* + * Default page/slab allocator behavior is to retry for ever + * for small allocations. We can override this behavior by using + * __GFP_RETRY_MAYFAIL which will tell the allocator to retry as long + * as it is feasible but rather fail than retry forever for all + * request sizes. + */ + if (flags & KM_MAYFAIL) + lflags |= __GFP_RETRY_MAYFAIL; + if (flags & KM_ZERO) lflags |= __GFP_ZERO; diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 334165c911f0..854e1bdd0b2a 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -69,34 +69,14 @@ static inline void __add_wb_stat(struct bdi_writeback *wb, percpu_counter_add_batch(&wb->stat[item], amount, WB_STAT_BATCH); } -static inline void __inc_wb_stat(struct bdi_writeback *wb, - enum wb_stat_item item) -{ - __add_wb_stat(wb, item, 1); -} - static inline void inc_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { - unsigned long flags; - - local_irq_save(flags); - __inc_wb_stat(wb, item); - local_irq_restore(flags); -} - -static inline void __dec_wb_stat(struct bdi_writeback *wb, - enum wb_stat_item item) -{ - __add_wb_stat(wb, item, -1); + __add_wb_stat(wb, item, 1); } static inline void dec_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { - unsigned long flags; - - local_irq_save(flags); - __dec_wb_stat(wb, item); - local_irq_restore(flags); + __add_wb_stat(wb, item, -1); } static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index 4090a42578a8..2df2118fbe13 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -19,7 +19,7 @@ CRASH_CORE_NOTE_NAME_BYTES + \ CRASH_CORE_NOTE_DESC_BYTES) -#define VMCOREINFO_BYTES (4096) +#define VMCOREINFO_BYTES PAGE_SIZE #define VMCOREINFO_NOTE_NAME "VMCOREINFO" #define VMCOREINFO_NOTE_NAME_BYTES ALIGN(sizeof(VMCOREINFO_NOTE_NAME), 4) #define VMCOREINFO_NOTE_SIZE ((CRASH_CORE_NOTE_HEAD_BYTES * 2) + \ @@ -28,6 +28,7 @@ typedef u32 note_buf_t[CRASH_CORE_NOTE_BYTES/4]; +void crash_update_vmcoreinfo_safecopy(void *ptr); void crash_save_vmcoreinfo(void); void arch_crash_save_vmcoreinfo(void); __printf(1, 2) @@ -56,9 +57,7 @@ phys_addr_t paddr_vmcoreinfo_note(void); #define VMCOREINFO_CONFIG(name) \ vmcoreinfo_append_str("CONFIG_%s=y\n", #name) -extern u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4]; -extern size_t vmcoreinfo_size; -extern size_t vmcoreinfo_max_size; +extern u32 *vmcoreinfo_note; Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, void *data, size_t data_len); diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 025727bf6797..c706eaac692e 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -592,8 +592,8 @@ static inline struct inode *d_real_inode(const struct dentry *dentry) } struct name_snapshot { - const char *name; - char inline_name[DNAME_INLINE_LEN]; + const unsigned char *name; + unsigned char inline_name[DNAME_INLINE_LEN]; }; void take_dentry_name_snapshot(struct name_snapshot *, struct dentry *); void release_dentry_name_snapshot(struct name_snapshot *); diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index 6daf6d4971f6..2f14ac73d01d 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -14,6 +14,7 @@ #define _LINUX_EVENTPOLL_H #include <uapi/linux/eventpoll.h> +#include <uapi/linux/kcmp.h> /* Forward declarations to avoid compiler errors */ @@ -22,6 +23,10 @@ struct file; #ifdef CONFIG_EPOLL +#ifdef CONFIG_CHECKPOINT_RESTORE +struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff); +#endif + /* Used to initialize the epoll bits inside the "struct file" */ static inline void eventpoll_init_file(struct file *file) { diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 4c6656f1fee7..bcfb9f7c46f5 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -25,7 +25,7 @@ struct vm_area_struct; #define ___GFP_FS 0x80u #define ___GFP_COLD 0x100u #define ___GFP_NOWARN 0x200u -#define ___GFP_REPEAT 0x400u +#define ___GFP_RETRY_MAYFAIL 0x400u #define ___GFP_NOFAIL 0x800u #define ___GFP_NORETRY 0x1000u #define ___GFP_MEMALLOC 0x2000u @@ -136,26 +136,56 @@ struct vm_area_struct; * * __GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim. * - * __GFP_REPEAT: Try hard to allocate the memory, but the allocation attempt - * _might_ fail. This depends upon the particular VM implementation. + * The default allocator behavior depends on the request size. We have a concept + * of so called costly allocations (with order > PAGE_ALLOC_COSTLY_ORDER). + * !costly allocations are too essential to fail so they are implicitly + * non-failing by default (with some exceptions like OOM victims might fail so + * the caller still has to check for failures) while costly requests try to be + * not disruptive and back off even without invoking the OOM killer. + * The following three modifiers might be used to override some of these + * implicit rules + * + * __GFP_NORETRY: The VM implementation will try only very lightweight + * memory direct reclaim to get some memory under memory pressure (thus + * it can sleep). It will avoid disruptive actions like OOM killer. The + * caller must handle the failure which is quite likely to happen under + * heavy memory pressure. The flag is suitable when failure can easily be + * handled at small cost, such as reduced throughput + * + * __GFP_RETRY_MAYFAIL: The VM implementation will retry memory reclaim + * procedures that have previously failed if there is some indication + * that progress has been made else where. It can wait for other + * tasks to attempt high level approaches to freeing memory such as + * compaction (which removes fragmentation) and page-out. + * There is still a definite limit to the number of retries, but it is + * a larger limit than with __GFP_NORETRY. + * Allocations with this flag may fail, but only when there is + * genuinely little unused memory. While these allocations do not + * directly trigger the OOM killer, their failure indicates that + * the system is likely to need to use the OOM killer soon. The + * caller must handle failure, but can reasonably do so by failing + * a higher-level request, or completing it only in a much less + * efficient manner. + * If the allocation does fail, and the caller is in a position to + * free some non-essential memory, doing so could benefit the system + * as a whole. * * __GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller - * cannot handle allocation failures. New users should be evaluated carefully - * (and the flag should be used only when there is no reasonable failure - * policy) but it is definitely preferable to use the flag rather than - * opencode endless loop around allocator. - * - * __GFP_NORETRY: The VM implementation must not retry indefinitely and will - * return NULL when direct reclaim and memory compaction have failed to allow - * the allocation to succeed. The OOM killer is not called with the current - * implementation. + * cannot handle allocation failures. The allocation could block + * indefinitely but will never return with failure. Testing for + * failure is pointless. + * New users should be evaluated carefully (and the flag should be + * used only when there is no reasonable failure policy) but it is + * definitely preferable to use the flag rather than opencode endless + * loop around allocator. + * Using this flag for costly allocations is _highly_ discouraged. */ #define __GFP_IO ((__force gfp_t)___GFP_IO) #define __GFP_FS ((__force gfp_t)___GFP_FS) #define __GFP_DIRECT_RECLAIM ((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */ #define __GFP_KSWAPD_RECLAIM ((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */ #define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM)) -#define __GFP_REPEAT ((__force gfp_t)___GFP_REPEAT) +#define __GFP_RETRY_MAYFAIL ((__force gfp_t)___GFP_RETRY_MAYFAIL) #define __GFP_NOFAIL ((__force gfp_t)___GFP_NOFAIL) #define __GFP_NORETRY ((__force gfp_t)___GFP_NORETRY) diff --git a/include/linux/ipc.h b/include/linux/ipc.h index 71fd92d81b26..5591f055e13f 100644 --- a/include/linux/ipc.h +++ b/include/linux/ipc.h @@ -20,6 +20,9 @@ struct kern_ipc_perm { umode_t mode; unsigned long seq; void *security; + + struct rcu_head rcu; + atomic_t refcount; } ____cacheline_aligned_in_smp; #endif /* _LINUX_IPC_H */ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 1c91f26e2996..bd6d96cf80b1 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -11,6 +11,7 @@ #include <linux/log2.h> #include <linux/typecheck.h> #include <linux/printk.h> +#include <linux/build_bug.h> #include <asm/byteorder.h> #include <uapi/linux/kernel.h> @@ -854,9 +855,12 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } * @member: the name of the member within the struct. * */ -#define container_of(ptr, type, member) ({ \ - const typeof( ((type *)0)->member ) *__mptr = (ptr); \ - (type *)( (char *)__mptr - offsetof(type,member) );}) +#define container_of(ptr, type, member) ({ \ + void *__mptr = (void *)(ptr); \ + BUILD_BUG_ON_MSG(!__same_type(*(ptr), ((type *)0)->member) && \ + !__same_type(*(ptr), void), \ + "pointer type mismatch in container_of()"); \ + ((type *)(__mptr - offsetof(type, member))); }) /* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */ #ifdef CONFIG_FTRACE_MCOUNT_RECORD diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 65888418fb69..dd056fab9e35 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -172,6 +172,7 @@ struct kimage { unsigned long start; struct page *control_code_page; struct page *swap_page; + void *vmcoreinfo_data_copy; /* locates in the crash memory */ unsigned long nr_segments; struct kexec_segment segment[KEXEC_SEGMENT_MAX]; @@ -241,6 +242,7 @@ extern void crash_kexec(struct pt_regs *); int kexec_should_crash(struct task_struct *); int kexec_crash_loaded(void); void crash_save_cpu(struct pt_regs *regs, int cpu); +extern int kimage_crash_copy_vmcoreinfo(struct kimage *image); extern struct kimage *kexec_image; extern struct kimage *kexec_crash_image; diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 4634da521238..3e0d405dc842 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -34,7 +34,7 @@ extern char *migrate_reason_names[MR_TYPES]; static inline struct page *new_page_nodemask(struct page *page, int preferred_nid, nodemask_t *nodemask) { - gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE; + gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL; if (PageHuge(page)) return alloc_huge_page_nodemask(page_hstate(compound_head(page)), diff --git a/include/linux/nmi.h b/include/linux/nmi.h index aa3cd0878270..8aa01fd859fb 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -6,18 +6,26 @@ #include <linux/sched.h> #include <asm/irq.h> +#if defined(CONFIG_HAVE_NMI_WATCHDOG) +#include <asm/nmi.h> +#endif #ifdef CONFIG_LOCKUP_DETECTOR +void lockup_detector_init(void); +#else +static inline void lockup_detector_init(void) +{ +} +#endif + +#ifdef CONFIG_SOFTLOCKUP_DETECTOR extern void touch_softlockup_watchdog_sched(void); extern void touch_softlockup_watchdog(void); extern void touch_softlockup_watchdog_sync(void); extern void touch_all_softlockup_watchdogs(void); -extern int proc_dowatchdog_thresh(struct ctl_table *table, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos); extern unsigned int softlockup_panic; -extern unsigned int hardlockup_panic; -void lockup_detector_init(void); +extern int soft_watchdog_enabled; +extern atomic_t watchdog_park_in_progress; #else static inline void touch_softlockup_watchdog_sched(void) { @@ -31,9 +39,6 @@ static inline void touch_softlockup_watchdog_sync(void) static inline void touch_all_softlockup_watchdogs(void) { } -static inline void lockup_detector_init(void) -{ -} #endif #ifdef CONFIG_DETECT_HUNG_TASK @@ -61,6 +66,21 @@ static inline void reset_hung_task_detector(void) #define NMI_WATCHDOG_ENABLED (1 << NMI_WATCHDOG_ENABLED_BIT) #define SOFT_WATCHDOG_ENABLED (1 << SOFT_WATCHDOG_ENABLED_BIT) +#if defined(CONFIG_HARDLOCKUP_DETECTOR) +extern void hardlockup_detector_disable(void); +extern unsigned int hardlockup_panic; +#else +static inline void hardlockup_detector_disable(void) {} +#endif + +#if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF) +extern void arch_touch_nmi_watchdog(void); +#else +#if !defined(CONFIG_HAVE_NMI_WATCHDOG) +static inline void arch_touch_nmi_watchdog(void) {} +#endif +#endif + /** * touch_nmi_watchdog - restart NMI watchdog timeout. * @@ -68,21 +88,11 @@ static inline void reset_hung_task_detector(void) * may be used to reset the timeout - for code which intentionally * disables interrupts for a long time. This call is stateless. */ -#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR) -#include <asm/nmi.h> -extern void touch_nmi_watchdog(void); -#else static inline void touch_nmi_watchdog(void) { + arch_touch_nmi_watchdog(); touch_softlockup_watchdog(); } -#endif - -#if defined(CONFIG_HARDLOCKUP_DETECTOR) -extern void hardlockup_detector_disable(void); -#else -static inline void hardlockup_detector_disable(void) {} -#endif /* * Create trigger_all_cpu_backtrace() out of the arch-provided @@ -139,15 +149,18 @@ static inline bool trigger_single_cpu_backtrace(int cpu) } #endif -#ifdef CONFIG_LOCKUP_DETECTOR +#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF u64 hw_nmi_get_sample_period(int watchdog_thresh); +#endif + +#ifdef CONFIG_LOCKUP_DETECTOR extern int nmi_watchdog_enabled; -extern int soft_watchdog_enabled; extern int watchdog_user_enabled; extern int watchdog_thresh; extern unsigned long watchdog_enabled; +extern struct cpumask watchdog_cpumask; extern unsigned long *watchdog_cpumask_bits; -extern atomic_t watchdog_park_in_progress; +extern int __read_mostly watchdog_suspended; #ifdef CONFIG_SMP extern int sysctl_softlockup_all_cpu_backtrace; extern int sysctl_hardlockup_all_cpu_backtrace; diff --git a/include/linux/platform_data/usb-ohci-s3c2410.h b/include/linux/platform_data/usb-ohci-s3c2410.h index 7fa1fbefc3f2..cc7554ae6e8b 100644 --- a/include/linux/platform_data/usb-ohci-s3c2410.h +++ b/include/linux/platform_data/usb-ohci-s3c2410.h @@ -31,7 +31,7 @@ struct s3c2410_hcd_info { void (*report_oc)(struct s3c2410_hcd_info *, int ports); }; -static void inline s3c2410_usb_report_oc(struct s3c2410_hcd_info *info, int ports) +static inline void s3c2410_usb_report_oc(struct s3c2410_hcd_info *info, int ports) { if (info->report_oc != NULL) { (info->report_oc)(info, ports); diff --git a/include/linux/random.h b/include/linux/random.h index ed5c3838780d..1fa0dc880bd7 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -57,6 +57,27 @@ static inline unsigned long get_random_long(void) #endif } +/* + * On 64-bit architectures, protect against non-terminated C string overflows + * by zeroing out the first byte of the canary; this leaves 56 bits of entropy. + */ +#ifdef CONFIG_64BIT +# ifdef __LITTLE_ENDIAN +# define CANARY_MASK 0xffffffffffffff00UL +# else /* big endian, 64 bits: */ +# define CANARY_MASK 0x00ffffffffffffffUL +# endif +#else /* 32 bits: */ +# define CANARY_MASK 0xffffffffUL +#endif + +static inline unsigned long get_random_canary(void) +{ + unsigned long val = get_random_long(); + + return val & CANARY_MASK; +} + unsigned long randomize_page(unsigned long start, unsigned long range); u32 prandom_u32(void); diff --git a/include/linux/sched.h b/include/linux/sched.h index 20814b7d7d70..3822d749fc9e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -974,6 +974,7 @@ struct task_struct { #ifdef CONFIG_FAULT_INJECTION int make_it_fail; + int fail_nth; #endif /* * When (nr_dirtied >= nr_dirtied_pause), it's time to call diff --git a/include/linux/sem.h b/include/linux/sem.h index 9edec926e9d9..be5cf2ea14ad 100644 --- a/include/linux/sem.h +++ b/include/linux/sem.h @@ -8,11 +8,29 @@ struct task_struct; +/* One semaphore structure for each semaphore in the system. */ +struct sem { + int semval; /* current value */ + /* + * PID of the process that last modified the semaphore. For + * Linux, specifically these are: + * - semop + * - semctl, via SETVAL and SETALL. + * - at task exit when performing undo adjustments (see exit_sem). + */ + int sempid; + spinlock_t lock; /* spinlock for fine-grained semtimedop */ + struct list_head pending_alter; /* pending single-sop operations */ + /* that alter the semaphore */ + struct list_head pending_const; /* pending single-sop operations */ + /* that do not alter the semaphore*/ + time_t sem_otime; /* candidate for sem_otime */ +} ____cacheline_aligned_in_smp; + /* One sem_array data structure for each set of semaphores in the system. */ struct sem_array { struct kern_ipc_perm sem_perm; /* permissions .. see ipc.h */ - time_t sem_ctime; /* last change time */ - struct sem *sem_base; /* ptr to first semaphore in array */ + time_t sem_ctime; /* create/last semctl() time */ struct list_head pending_alter; /* pending operations */ /* that alter the array */ struct list_head pending_const; /* pending complex operations */ @@ -21,6 +39,8 @@ struct sem_array { int sem_nsems; /* no. of semaphores in array */ int complex_count; /* pending complex operations */ unsigned int use_global_lock;/* >0: global lock required */ + + struct sem sems[]; }; #ifdef CONFIG_SYSVIPC diff --git a/include/linux/slab.h b/include/linux/slab.h index 04a7f7993e67..41473df6dfb0 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -471,7 +471,8 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags) * * %__GFP_NOWARN - If allocation fails, don't issue any warnings. * - * %__GFP_REPEAT - If allocation fails initially, try once more before failing. + * %__GFP_RETRY_MAYFAIL - Try really hard to succeed the allocation but fail + * eventually. * * There are other flags available as well, but these are not intended * for general use, and so are not documented here. For a full list of diff --git a/include/linux/string.h b/include/linux/string.h index 7439d83eaa33..96f5a5fd0377 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -193,4 +193,204 @@ static inline const char *kbasename(const char *path) return tail ? tail + 1 : path; } +#define __FORTIFY_INLINE extern __always_inline __attribute__((gnu_inline)) +#define __RENAME(x) __asm__(#x) + +void fortify_panic(const char *name) __noreturn __cold; +void __read_overflow(void) __compiletime_error("detected read beyond size of object passed as 1st parameter"); +void __read_overflow2(void) __compiletime_error("detected read beyond size of object passed as 2nd parameter"); +void __write_overflow(void) __compiletime_error("detected write beyond size of object passed as 1st parameter"); + +#if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE) +__FORTIFY_INLINE char *strcpy(char *p, const char *q) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (p_size == (size_t)-1 && q_size == (size_t)-1) + return __builtin_strcpy(p, q); + if (strscpy(p, q, p_size < q_size ? p_size : q_size) < 0) + fortify_panic(__func__); + return p; +} + +__FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __write_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __builtin_strncpy(p, q, size); +} + +__FORTIFY_INLINE char *strcat(char *p, const char *q) +{ + size_t p_size = __builtin_object_size(p, 0); + if (p_size == (size_t)-1) + return __builtin_strcat(p, q); + if (strlcat(p, q, p_size) >= p_size) + fortify_panic(__func__); + return p; +} + +__FORTIFY_INLINE __kernel_size_t strlen(const char *p) +{ + __kernel_size_t ret; + size_t p_size = __builtin_object_size(p, 0); + if (p_size == (size_t)-1) + return __builtin_strlen(p); + ret = strnlen(p, p_size); + if (p_size <= ret) + fortify_panic(__func__); + return ret; +} + +extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen); +__FORTIFY_INLINE __kernel_size_t strnlen(const char *p, __kernel_size_t maxlen) +{ + size_t p_size = __builtin_object_size(p, 0); + __kernel_size_t ret = __real_strnlen(p, maxlen < p_size ? maxlen : p_size); + if (p_size <= ret && maxlen != ret) + fortify_panic(__func__); + return ret; +} + +/* defined after fortified strlen to reuse it */ +extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy); +__FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size) +{ + size_t ret; + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (p_size == (size_t)-1 && q_size == (size_t)-1) + return __real_strlcpy(p, q, size); + ret = strlen(q); + if (size) { + size_t len = (ret >= size) ? size - 1 : ret; + if (__builtin_constant_p(len) && len >= p_size) + __write_overflow(); + if (len >= p_size) + fortify_panic(__func__); + __builtin_memcpy(p, q, len); + p[len] = '\0'; + } + return ret; +} + +/* defined after fortified strlen and strnlen to reuse them */ +__FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count) +{ + size_t p_len, copy_len; + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (p_size == (size_t)-1 && q_size == (size_t)-1) + return __builtin_strncat(p, q, count); + p_len = strlen(p); + copy_len = strnlen(q, count); + if (p_size < p_len + copy_len + 1) + fortify_panic(__func__); + __builtin_memcpy(p + p_len, q, copy_len); + p[p_len + copy_len] = '\0'; + return p; +} + +__FORTIFY_INLINE void *memset(void *p, int c, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __write_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __builtin_memset(p, c, size); +} + +__FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (__builtin_constant_p(size)) { + if (p_size < size) + __write_overflow(); + if (q_size < size) + __read_overflow2(); + } + if (p_size < size || q_size < size) + fortify_panic(__func__); + return __builtin_memcpy(p, q, size); +} + +__FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (__builtin_constant_p(size)) { + if (p_size < size) + __write_overflow(); + if (q_size < size) + __read_overflow2(); + } + if (p_size < size || q_size < size) + fortify_panic(__func__); + return __builtin_memmove(p, q, size); +} + +extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan); +__FORTIFY_INLINE void *memscan(void *p, int c, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __real_memscan(p, c, size); +} + +__FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (__builtin_constant_p(size)) { + if (p_size < size) + __read_overflow(); + if (q_size < size) + __read_overflow2(); + } + if (p_size < size || q_size < size) + fortify_panic(__func__); + return __builtin_memcmp(p, q, size); +} + +__FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __builtin_memchr(p, c, size); +} + +void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv); +__FORTIFY_INLINE void *memchr_inv(const void *p, int c, size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __real_memchr_inv(p, c, size); +} + +extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup); +__FORTIFY_INLINE void *kmemdup(const void *p, size_t size, gfp_t gfp) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __real_kmemdup(p, size, gfp); +} +#endif + #endif /* _LINUX_STRING_H_ */ diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 1c04a26bfd2f..3a89b9ff4cdc 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -47,6 +47,9 @@ extern int proc_douintvec(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int proc_dointvec_minmax(struct ctl_table *, int, void __user *, size_t *, loff_t *); +extern int proc_douintvec_minmax(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos); extern int proc_dointvec_jiffies(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int proc_dointvec_userhz_jiffies(struct ctl_table *, int, diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index 10e3663a75a6..8e50d01c645f 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -34,7 +34,7 @@ {(unsigned long)__GFP_FS, "__GFP_FS"}, \ {(unsigned long)__GFP_COLD, "__GFP_COLD"}, \ {(unsigned long)__GFP_NOWARN, "__GFP_NOWARN"}, \ - {(unsigned long)__GFP_REPEAT, "__GFP_REPEAT"}, \ + {(unsigned long)__GFP_RETRY_MAYFAIL, "__GFP_RETRY_MAYFAIL"}, \ {(unsigned long)__GFP_NOFAIL, "__GFP_NOFAIL"}, \ {(unsigned long)__GFP_NORETRY, "__GFP_NORETRY"}, \ {(unsigned long)__GFP_COMP, "__GFP_COMP"}, \ diff --git a/include/uapi/linux/kcmp.h b/include/uapi/linux/kcmp.h index 84df14b37360..481e103da78e 100644 --- a/include/uapi/linux/kcmp.h +++ b/include/uapi/linux/kcmp.h @@ -1,6 +1,8 @@ #ifndef _UAPI_LINUX_KCMP_H #define _UAPI_LINUX_KCMP_H +#include <linux/types.h> + /* Comparison type */ enum kcmp_type { KCMP_FILE, @@ -10,8 +12,16 @@ enum kcmp_type { KCMP_SIGHAND, KCMP_IO, KCMP_SYSVSEM, + KCMP_EPOLL_TFD, KCMP_TYPES, }; +/* Slot for KCMP_EPOLL_TFD */ +struct kcmp_epoll_slot { + __u32 efd; /* epoll file descriptor */ + __u32 tfd; /* target file number */ + __u32 toff; /* target offset within same numbered sequence */ +}; + #endif /* _UAPI_LINUX_KCMP_H */ diff --git a/include/uapi/linux/sem.h b/include/uapi/linux/sem.h index dd73b908b2f3..67eb90361692 100644 --- a/include/uapi/linux/sem.h +++ b/include/uapi/linux/sem.h @@ -23,7 +23,7 @@ struct semid_ds { struct ipc_perm sem_perm; /* permissions .. see ipc.h */ __kernel_time_t sem_otime; /* last semop time */ - __kernel_time_t sem_ctime; /* last change time */ + __kernel_time_t sem_ctime; /* create/last semctl() time */ struct sem *sem_base; /* ptr to first semaphore in array */ struct sem_queue *sem_pending; /* pending operations to be processed */ struct sem_queue **sem_pending_last; /* last pending operation */ diff --git a/init/main.c b/init/main.c index df58a416dd1d..052481fbe363 100644 --- a/init/main.c +++ b/init/main.c @@ -518,6 +518,7 @@ asmlinkage __visible void __init start_kernel(void) /* * Set up the initial canary ASAP: */ + add_latent_entropy(); boot_init_stack_canary(); cgroup_init_early(); diff --git a/ipc/msg.c b/ipc/msg.c index 104926dc72be..5b25e0755656 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -97,11 +97,11 @@ static inline void msg_rmid(struct ipc_namespace *ns, struct msg_queue *s) static void msg_rcu_free(struct rcu_head *head) { - struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu); - struct msg_queue *msq = ipc_rcu_to_struct(p); + struct kern_ipc_perm *p = container_of(head, struct kern_ipc_perm, rcu); + struct msg_queue *msq = container_of(p, struct msg_queue, q_perm); security_msg_queue_free(msq); - ipc_rcu_free(head); + kvfree(msq); } /** @@ -114,12 +114,12 @@ static void msg_rcu_free(struct rcu_head *head) static int newque(struct ipc_namespace *ns, struct ipc_params *params) { struct msg_queue *msq; - int id, retval; + int retval; key_t key = params->key; int msgflg = params->flg; - msq = ipc_rcu_alloc(sizeof(*msq)); - if (!msq) + msq = kvmalloc(sizeof(*msq), GFP_KERNEL); + if (unlikely(!msq)) return -ENOMEM; msq->q_perm.mode = msgflg & S_IRWXUGO; @@ -128,7 +128,7 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params) msq->q_perm.security = NULL; retval = security_msg_queue_alloc(msq); if (retval) { - ipc_rcu_putref(msq, ipc_rcu_free); + kvfree(msq); return retval; } @@ -142,10 +142,10 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params) INIT_LIST_HEAD(&msq->q_senders); /* ipc_addid() locks msq upon success. */ - id = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni); - if (id < 0) { - ipc_rcu_putref(msq, msg_rcu_free); - return id; + retval = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni); + if (retval < 0) { + call_rcu(&msq->q_perm.rcu, msg_rcu_free); + return retval; } ipc_unlock_object(&msq->q_perm); @@ -249,7 +249,7 @@ static void freeque(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) free_msg(msg); } atomic_sub(msq->q_cbytes, &ns->msg_bytes); - ipc_rcu_putref(msq, msg_rcu_free); + ipc_rcu_putref(&msq->q_perm, msg_rcu_free); } /* @@ -688,7 +688,7 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext, /* enqueue the sender and prepare to block */ ss_add(msq, &s, msgsz); - if (!ipc_rcu_getref(msq)) { + if (!ipc_rcu_getref(&msq->q_perm)) { err = -EIDRM; goto out_unlock0; } @@ -700,7 +700,7 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext, rcu_read_lock(); ipc_lock_object(&msq->q_perm); - ipc_rcu_putref(msq, msg_rcu_free); + ipc_rcu_putref(&msq->q_perm, msg_rcu_free); /* raced with RMID? */ if (!ipc_valid_object(&msq->q_perm)) { err = -EIDRM; diff --git a/ipc/sem.c b/ipc/sem.c index 947dc2348271..9e70cd7a17da 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -87,24 +87,6 @@ #include <linux/uaccess.h> #include "util.h" -/* One semaphore structure for each semaphore in the system. */ -struct sem { - int semval; /* current value */ - /* - * PID of the process that last modified the semaphore. For - * Linux, specifically these are: - * - semop - * - semctl, via SETVAL and SETALL. - * - at task exit when performing undo adjustments (see exit_sem). - */ - int sempid; - spinlock_t lock; /* spinlock for fine-grained semtimedop */ - struct list_head pending_alter; /* pending single-sop operations */ - /* that alter the semaphore */ - struct list_head pending_const; /* pending single-sop operations */ - /* that do not alter the semaphore*/ - time_t sem_otime; /* candidate for sem_otime */ -} ____cacheline_aligned_in_smp; /* One queue for each sleeping process in the system. */ struct sem_queue { @@ -175,7 +157,7 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it); * sem_array.sem_undo * * b) global or semaphore sem_lock() for read/write: - * sem_array.sem_base[i].pending_{const,alter}: + * sem_array.sems[i].pending_{const,alter}: * * c) special: * sem_undo_list.list_proc: @@ -250,7 +232,7 @@ static void unmerge_queues(struct sem_array *sma) */ list_for_each_entry_safe(q, tq, &sma->pending_alter, list) { struct sem *curr; - curr = &sma->sem_base[q->sops[0].sem_num]; + curr = &sma->sems[q->sops[0].sem_num]; list_add_tail(&q->list, &curr->pending_alter); } @@ -270,7 +252,7 @@ static void merge_queues(struct sem_array *sma) { int i; for (i = 0; i < sma->sem_nsems; i++) { - struct sem *sem = sma->sem_base + i; + struct sem *sem = &sma->sems[i]; list_splice_init(&sem->pending_alter, &sma->pending_alter); } @@ -278,11 +260,11 @@ static void merge_queues(struct sem_array *sma) static void sem_rcu_free(struct rcu_head *head) { - struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu); - struct sem_array *sma = ipc_rcu_to_struct(p); + struct kern_ipc_perm *p = container_of(head, struct kern_ipc_perm, rcu); + struct sem_array *sma = container_of(p, struct sem_array, sem_perm); security_sem_free(sma); - ipc_rcu_free(head); + kvfree(sma); } /* @@ -306,7 +288,7 @@ static void complexmode_enter(struct sem_array *sma) sma->use_global_lock = USE_GLOBAL_LOCK_HYSTERESIS; for (i = 0; i < sma->sem_nsems; i++) { - sem = sma->sem_base + i; + sem = &sma->sems[i]; spin_lock(&sem->lock); spin_unlock(&sem->lock); } @@ -366,7 +348,7 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops, * * Both facts are tracked by use_global_mode. */ - sem = sma->sem_base + sops->sem_num; + sem = &sma->sems[sops->sem_num]; /* * Initial check for use_global_lock. Just an optimization, @@ -421,7 +403,7 @@ static inline void sem_unlock(struct sem_array *sma, int locknum) complexmode_tryleave(sma); ipc_unlock_object(&sma->sem_perm); } else { - struct sem *sem = sma->sem_base + locknum; + struct sem *sem = &sma->sems[locknum]; spin_unlock(&sem->lock); } } @@ -456,7 +438,7 @@ static inline struct sem_array *sem_obtain_object_check(struct ipc_namespace *ns static inline void sem_lock_and_putref(struct sem_array *sma) { sem_lock(sma, NULL, -1); - ipc_rcu_putref(sma, sem_rcu_free); + ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); } static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s) @@ -464,6 +446,24 @@ static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s) ipc_rmid(&sem_ids(ns), &s->sem_perm); } +static struct sem_array *sem_alloc(size_t nsems) +{ + struct sem_array *sma; + size_t size; + + if (nsems > (INT_MAX - sizeof(*sma)) / sizeof(sma->sems[0])) + return NULL; + + size = sizeof(*sma) + nsems * sizeof(sma->sems[0]); + sma = kvmalloc(size, GFP_KERNEL); + if (unlikely(!sma)) + return NULL; + + memset(sma, 0, size); + + return sma; +} + /** * newary - Create a new semaphore set * @ns: namespace @@ -473,10 +473,8 @@ static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s) */ static int newary(struct ipc_namespace *ns, struct ipc_params *params) { - int id; int retval; struct sem_array *sma; - int size; key_t key = params->key; int nsems = params->u.nsems; int semflg = params->flg; @@ -487,29 +485,24 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params) if (ns->used_sems + nsems > ns->sc_semmns) return -ENOSPC; - size = sizeof(*sma) + nsems * sizeof(struct sem); - sma = ipc_rcu_alloc(size); + sma = sem_alloc(nsems); if (!sma) return -ENOMEM; - memset(sma, 0, size); - sma->sem_perm.mode = (semflg & S_IRWXUGO); sma->sem_perm.key = key; sma->sem_perm.security = NULL; retval = security_sem_alloc(sma); if (retval) { - ipc_rcu_putref(sma, ipc_rcu_free); + kvfree(sma); return retval; } - sma->sem_base = (struct sem *) &sma[1]; - for (i = 0; i < nsems; i++) { - INIT_LIST_HEAD(&sma->sem_base[i].pending_alter); - INIT_LIST_HEAD(&sma->sem_base[i].pending_const); - spin_lock_init(&sma->sem_base[i].lock); + INIT_LIST_HEAD(&sma->sems[i].pending_alter); + INIT_LIST_HEAD(&sma->sems[i].pending_const); + spin_lock_init(&sma->sems[i].lock); } sma->complex_count = 0; @@ -520,10 +513,10 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params) sma->sem_nsems = nsems; sma->sem_ctime = get_seconds(); - id = ipc_addid(&sem_ids(ns), &sma->sem_perm, ns->sc_semmni); - if (id < 0) { - ipc_rcu_putref(sma, sem_rcu_free); - return id; + retval = ipc_addid(&sem_ids(ns), &sma->sem_perm, ns->sc_semmni); + if (retval < 0) { + call_rcu(&sma->sem_perm.rcu, sem_rcu_free); + return retval; } ns->used_sems += nsems; @@ -612,7 +605,7 @@ static int perform_atomic_semop_slow(struct sem_array *sma, struct sem_queue *q) un = q->undo; for (sop = sops; sop < sops + nsops; sop++) { - curr = sma->sem_base + sop->sem_num; + curr = &sma->sems[sop->sem_num]; sem_op = sop->sem_op; result = curr->semval; @@ -639,7 +632,7 @@ static int perform_atomic_semop_slow(struct sem_array *sma, struct sem_queue *q) sop--; pid = q->pid; while (sop >= sops) { - sma->sem_base[sop->sem_num].sempid = pid; + sma->sems[sop->sem_num].sempid = pid; sop--; } @@ -661,7 +654,7 @@ undo: sop--; while (sop >= sops) { sem_op = sop->sem_op; - sma->sem_base[sop->sem_num].semval -= sem_op; + sma->sems[sop->sem_num].semval -= sem_op; if (sop->sem_flg & SEM_UNDO) un->semadj[sop->sem_num] += sem_op; sop--; @@ -692,7 +685,7 @@ static int perform_atomic_semop(struct sem_array *sma, struct sem_queue *q) * until the operations can go through. */ for (sop = sops; sop < sops + nsops; sop++) { - curr = sma->sem_base + sop->sem_num; + curr = &sma->sems[sop->sem_num]; sem_op = sop->sem_op; result = curr->semval; @@ -716,7 +709,7 @@ static int perform_atomic_semop(struct sem_array *sma, struct sem_queue *q) } for (sop = sops; sop < sops + nsops; sop++) { - curr = sma->sem_base + sop->sem_num; + curr = &sma->sems[sop->sem_num]; sem_op = sop->sem_op; result = curr->semval; @@ -815,7 +808,7 @@ static int wake_const_ops(struct sem_array *sma, int semnum, if (semnum == -1) pending_list = &sma->pending_const; else - pending_list = &sma->sem_base[semnum].pending_const; + pending_list = &sma->sems[semnum].pending_const; list_for_each_entry_safe(q, tmp, pending_list, list) { int error = perform_atomic_semop(sma, q); @@ -856,7 +849,7 @@ static int do_smart_wakeup_zero(struct sem_array *sma, struct sembuf *sops, for (i = 0; i < nsops; i++) { int num = sops[i].sem_num; - if (sma->sem_base[num].semval == 0) { + if (sma->sems[num].semval == 0) { got_zero = 1; semop_completed |= wake_const_ops(sma, num, wake_q); } @@ -867,7 +860,7 @@ static int do_smart_wakeup_zero(struct sem_array *sma, struct sembuf *sops, * Assume all were changed. */ for (i = 0; i < sma->sem_nsems; i++) { - if (sma->sem_base[i].semval == 0) { + if (sma->sems[i].semval == 0) { got_zero = 1; semop_completed |= wake_const_ops(sma, i, wake_q); } @@ -909,7 +902,7 @@ static int update_queue(struct sem_array *sma, int semnum, struct wake_q_head *w if (semnum == -1) pending_list = &sma->pending_alter; else - pending_list = &sma->sem_base[semnum].pending_alter; + pending_list = &sma->sems[semnum].pending_alter; again: list_for_each_entry_safe(q, tmp, pending_list, list) { @@ -922,7 +915,7 @@ again: * be in the per semaphore pending queue, and decrements * cannot be successful if the value is already 0. */ - if (semnum != -1 && sma->sem_base[semnum].semval == 0) + if (semnum != -1 && sma->sems[semnum].semval == 0) break; error = perform_atomic_semop(sma, q); @@ -959,9 +952,9 @@ again: static void set_semotime(struct sem_array *sma, struct sembuf *sops) { if (sops == NULL) { - sma->sem_base[0].sem_otime = get_seconds(); + sma->sems[0].sem_otime = get_seconds(); } else { - sma->sem_base[sops[0].sem_num].sem_otime = + sma->sems[sops[0].sem_num].sem_otime = get_seconds(); } } @@ -1067,9 +1060,9 @@ static int count_semcnt(struct sem_array *sma, ushort semnum, semcnt = 0; /* First: check the simple operations. They are easy to evaluate */ if (count_zero) - l = &sma->sem_base[semnum].pending_const; + l = &sma->sems[semnum].pending_const; else - l = &sma->sem_base[semnum].pending_alter; + l = &sma->sems[semnum].pending_alter; list_for_each_entry(q, l, list) { /* all task on a per-semaphore list sleep on exactly @@ -1124,7 +1117,7 @@ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) wake_up_sem_queue_prepare(q, -EIDRM, &wake_q); } for (i = 0; i < sma->sem_nsems; i++) { - struct sem *sem = sma->sem_base + i; + struct sem *sem = &sma->sems[i]; list_for_each_entry_safe(q, tq, &sem->pending_const, list) { unlink_queue(sma, q); wake_up_sem_queue_prepare(q, -EIDRM, &wake_q); @@ -1142,7 +1135,7 @@ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) wake_up_q(&wake_q); ns->used_sems -= sma->sem_nsems; - ipc_rcu_putref(sma, sem_rcu_free); + ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); } static unsigned long copy_semid_to_user(void __user *buf, struct semid64_ds *in, int version) @@ -1174,9 +1167,9 @@ static time_t get_semotime(struct sem_array *sma) int i; time_t res; - res = sma->sem_base[0].sem_otime; + res = sma->sems[0].sem_otime; for (i = 1; i < sma->sem_nsems; i++) { - time_t to = sma->sem_base[i].sem_otime; + time_t to = sma->sems[i].sem_otime; if (to > res) res = to; @@ -1325,7 +1318,7 @@ static int semctl_setval(struct ipc_namespace *ns, int semid, int semnum, return -EIDRM; } - curr = &sma->sem_base[semnum]; + curr = &sma->sems[semnum]; ipc_assert_locked_object(&sma->sem_perm); list_for_each_entry(un, &sma->list_id, list_id) @@ -1382,15 +1375,16 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, goto out_unlock; } if (nsems > SEMMSL_FAST) { - if (!ipc_rcu_getref(sma)) { + if (!ipc_rcu_getref(&sma->sem_perm)) { err = -EIDRM; goto out_unlock; } sem_unlock(sma, -1); rcu_read_unlock(); - sem_io = ipc_alloc(sizeof(ushort)*nsems); + sem_io = kvmalloc_array(nsems, sizeof(ushort), + GFP_KERNEL); if (sem_io == NULL) { - ipc_rcu_putref(sma, sem_rcu_free); + ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); return -ENOMEM; } @@ -1402,7 +1396,7 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, } } for (i = 0; i < sma->sem_nsems; i++) - sem_io[i] = sma->sem_base[i].semval; + sem_io[i] = sma->sems[i].semval; sem_unlock(sma, -1); rcu_read_unlock(); err = 0; @@ -1415,29 +1409,30 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, int i; struct sem_undo *un; - if (!ipc_rcu_getref(sma)) { + if (!ipc_rcu_getref(&sma->sem_perm)) { err = -EIDRM; goto out_rcu_wakeup; } rcu_read_unlock(); if (nsems > SEMMSL_FAST) { - sem_io = ipc_alloc(sizeof(ushort)*nsems); + sem_io = kvmalloc_array(nsems, sizeof(ushort), + GFP_KERNEL); if (sem_io == NULL) { - ipc_rcu_putref(sma, sem_rcu_free); + ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); return -ENOMEM; } } if (copy_from_user(sem_io, p, nsems*sizeof(ushort))) { - ipc_rcu_putref(sma, sem_rcu_free); + ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); err = -EFAULT; goto out_free; } for (i = 0; i < nsems; i++) { if (sem_io[i] > SEMVMX) { - ipc_rcu_putref(sma, sem_rcu_free); + ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); err = -ERANGE; goto out_free; } @@ -1450,8 +1445,8 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, } for (i = 0; i < nsems; i++) { - sma->sem_base[i].semval = sem_io[i]; - sma->sem_base[i].sempid = task_tgid_vnr(current); + sma->sems[i].semval = sem_io[i]; + sma->sems[i].sempid = task_tgid_vnr(current); } ipc_assert_locked_object(&sma->sem_perm); @@ -1476,7 +1471,7 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, err = -EIDRM; goto out_unlock; } - curr = &sma->sem_base[semnum]; + curr = &sma->sems[semnum]; switch (cmd) { case GETVAL: @@ -1500,7 +1495,7 @@ out_rcu_wakeup: wake_up_q(&wake_q); out_free: if (sem_io != fast_sem_io) - ipc_free(sem_io); + kvfree(sem_io); return err; } @@ -1719,7 +1714,7 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid) } nsems = sma->sem_nsems; - if (!ipc_rcu_getref(sma)) { + if (!ipc_rcu_getref(&sma->sem_perm)) { rcu_read_unlock(); un = ERR_PTR(-EIDRM); goto out; @@ -1729,7 +1724,7 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid) /* step 2: allocate new undo structure */ new = kzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, GFP_KERNEL); if (!new) { - ipc_rcu_putref(sma, sem_rcu_free); + ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); return ERR_PTR(-ENOMEM); } @@ -1932,7 +1927,7 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops, */ if (nsops == 1) { struct sem *curr; - curr = &sma->sem_base[sops->sem_num]; + curr = &sma->sems[sops->sem_num]; if (alter) { if (sma->complex_count) { @@ -2146,7 +2141,7 @@ void exit_sem(struct task_struct *tsk) /* perform adjustments registered in un */ for (i = 0; i < sma->sem_nsems; i++) { - struct sem *semaphore = &sma->sem_base[i]; + struct sem *semaphore = &sma->sems[i]; if (un->semadj[i]) { semaphore->semval += un->semadj[i]; /* diff --git a/ipc/shm.c b/ipc/shm.c index f45c7959b264..28a444861a8f 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -174,11 +174,12 @@ static inline void shm_lock_by_ptr(struct shmid_kernel *ipcp) static void shm_rcu_free(struct rcu_head *head) { - struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu); - struct shmid_kernel *shp = ipc_rcu_to_struct(p); - + struct kern_ipc_perm *ptr = container_of(head, struct kern_ipc_perm, + rcu); + struct shmid_kernel *shp = container_of(ptr, struct shmid_kernel, + shm_perm); security_shm_free(shp); - ipc_rcu_free(head); + kvfree(shp); } static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s) @@ -241,7 +242,7 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp) user_shm_unlock(i_size_read(file_inode(shm_file)), shp->mlock_user); fput(shm_file); - ipc_rcu_putref(shp, shm_rcu_free); + ipc_rcu_putref(&shp->shm_perm, shm_rcu_free); } /* @@ -529,7 +530,6 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) size_t numpages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; struct file *file; char name[13]; - int id; vm_flags_t acctflag = 0; if (size < SHMMIN || size > ns->shm_ctlmax) @@ -542,8 +542,8 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) ns->shm_tot + numpages > ns->shm_ctlall) return -ENOSPC; - shp = ipc_rcu_alloc(sizeof(*shp)); - if (!shp) + shp = kvmalloc(sizeof(*shp), GFP_KERNEL); + if (unlikely(!shp)) return -ENOMEM; shp->shm_perm.key = key; @@ -553,7 +553,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) shp->shm_perm.security = NULL; error = security_shm_alloc(shp); if (error) { - ipc_rcu_putref(shp, ipc_rcu_free); + kvfree(shp); return error; } @@ -598,11 +598,9 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) shp->shm_file = file; shp->shm_creator = current; - id = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni); - if (id < 0) { - error = id; + error = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni); + if (error < 0) goto no_id; - } list_add(&shp->shm_clist, ¤t->sysvshm.shm_clist); @@ -624,7 +622,7 @@ no_id: user_shm_unlock(size, shp->mlock_user); fput(file); no_file: - ipc_rcu_putref(shp, shm_rcu_free); + call_rcu(&shp->shm_perm.rcu, shm_rcu_free); return error; } diff --git a/ipc/util.c b/ipc/util.c index caec7b1bfaa3..1a2cb02467ab 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -232,6 +232,7 @@ int ipc_addid(struct ipc_ids *ids, struct kern_ipc_perm *new, int size) idr_preload(GFP_KERNEL); + atomic_set(&new->refcount, 1); spin_lock_init(&new->lock); new->deleted = false; rcu_read_lock(); @@ -394,70 +395,18 @@ void ipc_rmid(struct ipc_ids *ids, struct kern_ipc_perm *ipcp) ipcp->deleted = true; } -/** - * ipc_alloc - allocate ipc space - * @size: size desired - * - * Allocate memory from the appropriate pools and return a pointer to it. - * NULL is returned if the allocation fails - */ -void *ipc_alloc(int size) -{ - return kvmalloc(size, GFP_KERNEL); -} - -/** - * ipc_free - free ipc space - * @ptr: pointer returned by ipc_alloc - * - * Free a block created with ipc_alloc(). - */ -void ipc_free(void *ptr) +int ipc_rcu_getref(struct kern_ipc_perm *ptr) { - kvfree(ptr); + return atomic_inc_not_zero(&ptr->refcount); } -/** - * ipc_rcu_alloc - allocate ipc and rcu space - * @size: size desired - * - * Allocate memory for the rcu header structure + the object. - * Returns the pointer to the object or NULL upon failure. - */ -void *ipc_rcu_alloc(int size) +void ipc_rcu_putref(struct kern_ipc_perm *ptr, + void (*func)(struct rcu_head *head)) { - /* - * We prepend the allocation with the rcu struct - */ - struct ipc_rcu *out = ipc_alloc(sizeof(struct ipc_rcu) + size); - if (unlikely(!out)) - return NULL; - atomic_set(&out->refcount, 1); - return out + 1; -} - -int ipc_rcu_getref(void *ptr) -{ - struct ipc_rcu *p = ((struct ipc_rcu *)ptr) - 1; - - return atomic_inc_not_zero(&p->refcount); -} - -void ipc_rcu_putref(void *ptr, void (*func)(struct rcu_head *head)) -{ - struct ipc_rcu *p = ((struct ipc_rcu *)ptr) - 1; - - if (!atomic_dec_and_test(&p->refcount)) + if (!atomic_dec_and_test(&ptr->refcount)) return; - call_rcu(&p->rcu, func); -} - -void ipc_rcu_free(struct rcu_head *head) -{ - struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu); - - kvfree(p); + call_rcu(&ptr->rcu, func); } /** diff --git a/ipc/util.h b/ipc/util.h index 60ddccca464d..c692010e6f0a 100644 --- a/ipc/util.h +++ b/ipc/util.h @@ -47,13 +47,6 @@ static inline void msg_exit_ns(struct ipc_namespace *ns) { } static inline void shm_exit_ns(struct ipc_namespace *ns) { } #endif -struct ipc_rcu { - struct rcu_head rcu; - atomic_t refcount; -} ____cacheline_aligned_in_smp; - -#define ipc_rcu_to_struct(p) ((void *)(p+1)) - /* * Structure that holds the parameters needed by the ipc operations * (see after) @@ -114,22 +107,18 @@ void ipc_rmid(struct ipc_ids *, struct kern_ipc_perm *); /* must be called with ipcp locked */ int ipcperms(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp, short flg); -/* for rare, potentially huge allocations. - * both function can sleep - */ -void *ipc_alloc(int size); -void ipc_free(void *ptr); - /* * For allocation that need to be freed by RCU. * Objects are reference counted, they start with reference count 1. * getref increases the refcount, the putref call that reduces the recount * to 0 schedules the rcu destruction. Caller must guarantee locking. + * + * refcount is initialized by ipc_addid(), before that point call_rcu() + * must be used. */ -void *ipc_rcu_alloc(int size); -int ipc_rcu_getref(void *ptr); -void ipc_rcu_putref(void *ptr, void (*func)(struct rcu_head *head)); -void ipc_rcu_free(struct rcu_head *head); +int ipc_rcu_getref(struct kern_ipc_perm *ptr); +void ipc_rcu_putref(struct kern_ipc_perm *ptr, + void (*func)(struct rcu_head *head)); struct kern_ipc_perm *ipc_lock(struct ipc_ids *, int); struct kern_ipc_perm *ipc_obtain_object_idr(struct ipc_ids *ids, int id); diff --git a/kernel/Makefile b/kernel/Makefile index 72aa080f91f0..4cb8e8b23c6e 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -82,7 +82,7 @@ obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_KGDB) += debug/ obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o obj-$(CONFIG_LOCKUP_DETECTOR) += watchdog.o -obj-$(CONFIG_HARDLOCKUP_DETECTOR) += watchdog_hld.o +obj-$(CONFIG_HARDLOCKUP_DETECTOR_PERF) += watchdog_hld.o obj-$(CONFIG_SECCOMP) += seccomp.o obj-$(CONFIG_RELAY) += relay.o obj-$(CONFIG_SYSCTL) += utsname_sysctl.o diff --git a/kernel/crash_core.c b/kernel/crash_core.c index fcbd568f1e95..6db80fc0810b 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -14,10 +14,12 @@ #include <asm/sections.h> /* vmcoreinfo stuff */ -static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES]; -u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4]; -size_t vmcoreinfo_size; -size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data); +static unsigned char *vmcoreinfo_data; +static size_t vmcoreinfo_size; +u32 *vmcoreinfo_note; + +/* trusted vmcoreinfo, e.g. we can make a copy in the crash memory */ +static unsigned char *vmcoreinfo_data_safecopy; /* * parsing the "crashkernel" commandline @@ -324,8 +326,23 @@ static void update_vmcoreinfo_note(void) final_note(buf); } +void crash_update_vmcoreinfo_safecopy(void *ptr) +{ + if (ptr) + memcpy(ptr, vmcoreinfo_data, vmcoreinfo_size); + + vmcoreinfo_data_safecopy = ptr; +} + void crash_save_vmcoreinfo(void) { + if (!vmcoreinfo_note) + return; + + /* Use the safe copy to generate vmcoreinfo note if have */ + if (vmcoreinfo_data_safecopy) + vmcoreinfo_data = vmcoreinfo_data_safecopy; + vmcoreinfo_append_str("CRASHTIME=%ld\n", get_seconds()); update_vmcoreinfo_note(); } @@ -340,7 +357,7 @@ void vmcoreinfo_append_str(const char *fmt, ...) r = vscnprintf(buf, sizeof(buf), fmt, args); va_end(args); - r = min(r, vmcoreinfo_max_size - vmcoreinfo_size); + r = min(r, (size_t)VMCOREINFO_BYTES - vmcoreinfo_size); memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r); @@ -356,11 +373,26 @@ void __weak arch_crash_save_vmcoreinfo(void) phys_addr_t __weak paddr_vmcoreinfo_note(void) { - return __pa_symbol((unsigned long)(char *)&vmcoreinfo_note); + return __pa(vmcoreinfo_note); } static int __init crash_save_vmcoreinfo_init(void) { + vmcoreinfo_data = (unsigned char *)get_zeroed_page(GFP_KERNEL); + if (!vmcoreinfo_data) { + pr_warn("Memory allocation for vmcoreinfo_data failed\n"); + return -ENOMEM; + } + + vmcoreinfo_note = alloc_pages_exact(VMCOREINFO_NOTE_SIZE, + GFP_KERNEL | __GFP_ZERO); + if (!vmcoreinfo_note) { + free_page((unsigned long)vmcoreinfo_data); + vmcoreinfo_data = NULL; + pr_warn("Memory allocation for vmcoreinfo_note failed\n"); + return -ENOMEM; + } + VMCOREINFO_OSRELEASE(init_uts_ns.name.release); VMCOREINFO_PAGESIZE(PAGE_SIZE); diff --git a/kernel/fork.c b/kernel/fork.c index 0f69a3e5281e..17921b0390b4 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -205,19 +205,17 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) void *stack; int i; - local_irq_disable(); for (i = 0; i < NR_CACHED_STACKS; i++) { - struct vm_struct *s = this_cpu_read(cached_stacks[i]); + struct vm_struct *s; + + s = this_cpu_xchg(cached_stacks[i], NULL); if (!s) continue; - this_cpu_write(cached_stacks[i], NULL); tsk->stack_vm_area = s; - local_irq_enable(); return s->addr; } - local_irq_enable(); stack = __vmalloc_node_range(THREAD_SIZE, THREAD_SIZE, VMALLOC_START, VMALLOC_END, @@ -245,19 +243,15 @@ static inline void free_thread_stack(struct task_struct *tsk) { #ifdef CONFIG_VMAP_STACK if (task_stack_vm_area(tsk)) { - unsigned long flags; int i; - local_irq_save(flags); for (i = 0; i < NR_CACHED_STACKS; i++) { - if (this_cpu_read(cached_stacks[i])) + if (this_cpu_cmpxchg(cached_stacks[i], + NULL, tsk->stack_vm_area) != NULL) continue; - this_cpu_write(cached_stacks[i], tsk->stack_vm_area); - local_irq_restore(flags); return; } - local_irq_restore(flags); vfree_atomic(tsk->stack); return; @@ -560,7 +554,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) set_task_stack_end_magic(tsk); #ifdef CONFIG_CC_STACKPROTECTOR - tsk->stack_canary = get_random_long(); + tsk->stack_canary = get_random_canary(); #endif /* @@ -579,6 +573,10 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) kcov_task_init(tsk); +#ifdef CONFIG_FAULT_INJECTION + tsk->fail_nth = 0; +#endif + return tsk; free_stack: diff --git a/kernel/kcmp.c b/kernel/kcmp.c index 3a47fa998fe0..ea34ed8bb952 100644 --- a/kernel/kcmp.c +++ b/kernel/kcmp.c @@ -11,6 +11,10 @@ #include <linux/bug.h> #include <linux/err.h> #include <linux/kcmp.h> +#include <linux/capability.h> +#include <linux/list.h> +#include <linux/eventpoll.h> +#include <linux/file.h> #include <asm/unistd.h> @@ -94,6 +98,56 @@ static int kcmp_lock(struct mutex *m1, struct mutex *m2) return err; } +#ifdef CONFIG_EPOLL +static int kcmp_epoll_target(struct task_struct *task1, + struct task_struct *task2, + unsigned long idx1, + struct kcmp_epoll_slot __user *uslot) +{ + struct file *filp, *filp_epoll, *filp_tgt; + struct kcmp_epoll_slot slot; + struct files_struct *files; + + if (copy_from_user(&slot, uslot, sizeof(slot))) + return -EFAULT; + + filp = get_file_raw_ptr(task1, idx1); + if (!filp) + return -EBADF; + + files = get_files_struct(task2); + if (!files) + return -EBADF; + + spin_lock(&files->file_lock); + filp_epoll = fcheck_files(files, slot.efd); + if (filp_epoll) + get_file(filp_epoll); + else + filp_tgt = ERR_PTR(-EBADF); + spin_unlock(&files->file_lock); + put_files_struct(files); + + if (filp_epoll) { + filp_tgt = get_epoll_tfile_raw_ptr(filp_epoll, slot.tfd, slot.toff); + fput(filp_epoll); + } else + + if (IS_ERR(filp_tgt)) + return PTR_ERR(filp_tgt); + + return kcmp_ptr(filp, filp_tgt, KCMP_FILE); +} +#else +static int kcmp_epoll_target(struct task_struct *task1, + struct task_struct *task2, + unsigned long idx1, + struct kcmp_epoll_slot __user *uslot) +{ + return -EOPNOTSUPP; +} +#endif + SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type, unsigned long, idx1, unsigned long, idx2) { @@ -165,6 +219,9 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type, ret = -EOPNOTSUPP; #endif break; + case KCMP_EPOLL_TFD: + ret = kcmp_epoll_target(task1, task2, idx1, (void *)idx2); + break; default: ret = -EINVAL; break; diff --git a/kernel/kexec.c b/kernel/kexec.c index 980936a90ee6..e62ec4dc6620 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -144,6 +144,14 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments, if (ret) goto out; + /* + * Some architecture(like S390) may touch the crash memory before + * machine_kexec_prepare(), we must copy vmcoreinfo data after it. + */ + ret = kimage_crash_copy_vmcoreinfo(image); + if (ret) + goto out; + for (i = 0; i < nr_segments; i++) { ret = kimage_load_segment(image, &image->segment[i]); if (ret) diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 154ffb489b93..1ae7c41c33c1 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -482,6 +482,40 @@ struct page *kimage_alloc_control_pages(struct kimage *image, return pages; } +int kimage_crash_copy_vmcoreinfo(struct kimage *image) +{ + struct page *vmcoreinfo_page; + void *safecopy; + + if (image->type != KEXEC_TYPE_CRASH) + return 0; + + /* + * For kdump, allocate one vmcoreinfo safe copy from the + * crash memory. as we have arch_kexec_protect_crashkres() + * after kexec syscall, we naturally protect it from write + * (even read) access under kernel direct mapping. But on + * the other hand, we still need to operate it when crash + * happens to generate vmcoreinfo note, hereby we rely on + * vmap for this purpose. + */ + vmcoreinfo_page = kimage_alloc_control_pages(image, 0); + if (!vmcoreinfo_page) { + pr_warn("Could not allocate vmcoreinfo buffer\n"); + return -ENOMEM; + } + safecopy = vmap(&vmcoreinfo_page, 1, VM_MAP, PAGE_KERNEL); + if (!safecopy) { + pr_warn("Could not vmap vmcoreinfo buffer\n"); + return -ENOMEM; + } + + image->vmcoreinfo_data_copy = safecopy; + crash_update_vmcoreinfo_safecopy(safecopy); + + return 0; +} + static int kimage_add_entry(struct kimage *image, kimage_entry_t entry) { if (*image->entry != 0) @@ -569,6 +603,11 @@ void kimage_free(struct kimage *image) if (!image) return; + if (image->vmcoreinfo_data_copy) { + crash_update_vmcoreinfo_safecopy(NULL); + vunmap(image->vmcoreinfo_data_copy); + } + kimage_free_extra_pages(image); for_each_kimage_entry(image, ptr, entry) { if (entry & IND_INDIRECTION) { diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 766e7e4d3ad9..9f48f4412297 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -26,13 +26,6 @@ #include <linux/vmalloc.h> #include "kexec_internal.h" -/* - * Declare these symbols weak so that if architecture provides a purgatory, - * these will be overridden. - */ -char __weak kexec_purgatory[0]; -size_t __weak kexec_purgatory_size = 0; - static int kexec_calculate_store_digests(struct kimage *image); /* Architectures can provide this probe function */ @@ -298,6 +291,14 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, if (ret) goto out; + /* + * Some architecture(like S390) may touch the crash memory before + * machine_kexec_prepare(), we must copy vmcoreinfo data after it. + */ + ret = kimage_crash_copy_vmcoreinfo(image); + if (ret) + goto out; + ret = kexec_calculate_store_digests(image); if (ret) goto out; diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h index 799a8a452187..50dfcb039a41 100644 --- a/kernel/kexec_internal.h +++ b/kernel/kexec_internal.h @@ -17,6 +17,8 @@ extern struct mutex kexec_mutex; #ifdef CONFIG_KEXEC_FILE #include <linux/purgatory.h> void kimage_file_post_load_cleanup(struct kimage *image); +extern char kexec_purgatory[]; +extern size_t kexec_purgatory_size; #else /* CONFIG_KEXEC_FILE */ static inline void kimage_file_post_load_cleanup(struct kimage *image) { } #endif /* CONFIG_KEXEC_FILE */ diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index df1a9aa602a0..46ba853656f6 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -134,7 +134,7 @@ static ssize_t vmcoreinfo_show(struct kobject *kobj, { phys_addr_t vmcore_base = paddr_vmcoreinfo_note(); return sprintf(buf, "%pa %x\n", &vmcore_base, - (unsigned int)sizeof(vmcoreinfo_note)); + (unsigned int)VMCOREINFO_NOTE_SIZE); } KERNEL_ATTR_RO(vmcoreinfo); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 4dfba1a76cc3..6648fbbb8157 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -174,11 +174,32 @@ extern int no_unaligned_warning; #ifdef CONFIG_PROC_SYSCTL -#define SYSCTL_WRITES_LEGACY -1 -#define SYSCTL_WRITES_WARN 0 -#define SYSCTL_WRITES_STRICT 1 +/** + * enum sysctl_writes_mode - supported sysctl write modes + * + * @SYSCTL_WRITES_LEGACY: each write syscall must fully contain the sysctl value + * to be written, and multiple writes on the same sysctl file descriptor + * will rewrite the sysctl value, regardless of file position. No warning + * is issued when the initial position is not 0. + * @SYSCTL_WRITES_WARN: same as above but warn when the initial file position is + * not 0. + * @SYSCTL_WRITES_STRICT: writes to numeric sysctl entries must always be at + * file position 0 and the value must be fully contained in the buffer + * sent to the write syscall. If dealing with strings respect the file + * position, but restrict this to the max length of the buffer, anything + * passed the max lenght will be ignored. Multiple writes will append + * to the buffer. + * + * These write modes control how current file position affects the behavior of + * updating sysctl values through the proc interface on each write. + */ +enum sysctl_writes_mode { + SYSCTL_WRITES_LEGACY = -1, + SYSCTL_WRITES_WARN = 0, + SYSCTL_WRITES_STRICT = 1, +}; -static int sysctl_writes_strict = SYSCTL_WRITES_STRICT; +static enum sysctl_writes_mode sysctl_writes_strict = SYSCTL_WRITES_STRICT; static int proc_do_cad_pid(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); @@ -880,6 +901,14 @@ static struct ctl_table kern_table[] = { #endif }, { + .procname = "watchdog_cpumask", + .data = &watchdog_cpumask_bits, + .maxlen = NR_CPUS, + .mode = 0644, + .proc_handler = proc_watchdog_cpumask, + }, +#ifdef CONFIG_SOFTLOCKUP_DETECTOR + { .procname = "soft_watchdog", .data = &soft_watchdog_enabled, .maxlen = sizeof (int), @@ -889,13 +918,6 @@ static struct ctl_table kern_table[] = { .extra2 = &one, }, { - .procname = "watchdog_cpumask", - .data = &watchdog_cpumask_bits, - .maxlen = NR_CPUS, - .mode = 0644, - .proc_handler = proc_watchdog_cpumask, - }, - { .procname = "softlockup_panic", .data = &softlockup_panic, .maxlen = sizeof(int), @@ -904,27 +926,29 @@ static struct ctl_table kern_table[] = { .extra1 = &zero, .extra2 = &one, }, -#ifdef CONFIG_HARDLOCKUP_DETECTOR +#ifdef CONFIG_SMP { - .procname = "hardlockup_panic", - .data = &hardlockup_panic, + .procname = "softlockup_all_cpu_backtrace", + .data = &sysctl_softlockup_all_cpu_backtrace, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &zero, .extra2 = &one, }, +#endif /* CONFIG_SMP */ #endif -#ifdef CONFIG_SMP +#ifdef CONFIG_HARDLOCKUP_DETECTOR { - .procname = "softlockup_all_cpu_backtrace", - .data = &sysctl_softlockup_all_cpu_backtrace, + .procname = "hardlockup_panic", + .data = &hardlockup_panic, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &zero, .extra2 = &one, }, +#ifdef CONFIG_SMP { .procname = "hardlockup_all_cpu_backtrace", .data = &sysctl_hardlockup_all_cpu_backtrace, @@ -936,6 +960,8 @@ static struct ctl_table kern_table[] = { }, #endif /* CONFIG_SMP */ #endif +#endif + #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) { .procname = "unknown_nmi_panic", @@ -1950,6 +1976,32 @@ static void warn_sysctl_write(struct ctl_table *table) } /** + * proc_first_pos_non_zero_ignore - check if firs position is allowed + * @ppos: file position + * @table: the sysctl table + * + * Returns true if the first position is non-zero and the sysctl_writes_strict + * mode indicates this is not allowed for numeric input types. String proc + * hadlers can ignore the return value. + */ +static bool proc_first_pos_non_zero_ignore(loff_t *ppos, + struct ctl_table *table) +{ + if (!*ppos) + return false; + + switch (sysctl_writes_strict) { + case SYSCTL_WRITES_STRICT: + return true; + case SYSCTL_WRITES_WARN: + warn_sysctl_write(table); + return false; + default: + return false; + } +} + +/** * proc_dostring - read a string sysctl * @table: the sysctl table * @write: %TRUE if this is a write to the sysctl file @@ -1969,8 +2021,8 @@ static void warn_sysctl_write(struct ctl_table *table) int proc_dostring(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - if (write && *ppos && sysctl_writes_strict == SYSCTL_WRITES_WARN) - warn_sysctl_write(table); + if (write) + proc_first_pos_non_zero_ignore(ppos, table); return _proc_do_string((char *)(table->data), table->maxlen, write, (char __user *)buffer, lenp, ppos); @@ -2128,19 +2180,18 @@ static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp, return 0; } -static int do_proc_douintvec_conv(bool *negp, unsigned long *lvalp, - int *valp, - int write, void *data) +static int do_proc_douintvec_conv(unsigned long *lvalp, + unsigned int *valp, + int write, void *data) { if (write) { - if (*negp) + if (*lvalp > UINT_MAX) return -EINVAL; if (*lvalp > UINT_MAX) return -EINVAL; *valp = *lvalp; } else { unsigned int val = *valp; - *negp = false; *lvalp = (unsigned long)val; } return 0; @@ -2172,17 +2223,8 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, conv = do_proc_dointvec_conv; if (write) { - if (*ppos) { - switch (sysctl_writes_strict) { - case SYSCTL_WRITES_STRICT: - goto out; - case SYSCTL_WRITES_WARN: - warn_sysctl_write(table); - break; - default: - break; - } - } + if (proc_first_pos_non_zero_ignore(ppos, table)) + goto out; if (left > PAGE_SIZE - 1) left = PAGE_SIZE - 1; @@ -2249,6 +2291,146 @@ static int do_proc_dointvec(struct ctl_table *table, int write, buffer, lenp, ppos, conv, data); } +static int do_proc_douintvec_w(unsigned int *tbl_data, + struct ctl_table *table, + void __user *buffer, + size_t *lenp, loff_t *ppos, + int (*conv)(unsigned long *lvalp, + unsigned int *valp, + int write, void *data), + void *data) +{ + unsigned long lval; + int err = 0; + size_t left; + bool neg; + char *kbuf = NULL, *p; + + left = *lenp; + + if (proc_first_pos_non_zero_ignore(ppos, table)) + goto bail_early; + + if (left > PAGE_SIZE - 1) + left = PAGE_SIZE - 1; + + p = kbuf = memdup_user_nul(buffer, left); + if (IS_ERR(kbuf)) + return -EINVAL; + + left -= proc_skip_spaces(&p); + if (!left) { + err = -EINVAL; + goto out_free; + } + + err = proc_get_long(&p, &left, &lval, &neg, + proc_wspace_sep, + sizeof(proc_wspace_sep), NULL); + if (err || neg) { + err = -EINVAL; + goto out_free; + } + + if (conv(&lval, tbl_data, 1, data)) { + err = -EINVAL; + goto out_free; + } + + if (!err && left) + left -= proc_skip_spaces(&p); + +out_free: + kfree(kbuf); + if (err) + return -EINVAL; + + return 0; + + /* This is in keeping with old __do_proc_dointvec() */ +bail_early: + *ppos += *lenp; + return err; +} + +static int do_proc_douintvec_r(unsigned int *tbl_data, void __user *buffer, + size_t *lenp, loff_t *ppos, + int (*conv)(unsigned long *lvalp, + unsigned int *valp, + int write, void *data), + void *data) +{ + unsigned long lval; + int err = 0; + size_t left; + + left = *lenp; + + if (conv(&lval, tbl_data, 0, data)) { + err = -EINVAL; + goto out; + } + + err = proc_put_long(&buffer, &left, lval, false); + if (err || !left) + goto out; + + err = proc_put_char(&buffer, &left, '\n'); + +out: + *lenp -= left; + *ppos += *lenp; + + return err; +} + +static int __do_proc_douintvec(void *tbl_data, struct ctl_table *table, + int write, void __user *buffer, + size_t *lenp, loff_t *ppos, + int (*conv)(unsigned long *lvalp, + unsigned int *valp, + int write, void *data), + void *data) +{ + unsigned int *i, vleft; + + if (!tbl_data || !table->maxlen || !*lenp || (*ppos && !write)) { + *lenp = 0; + return 0; + } + + i = (unsigned int *) tbl_data; + vleft = table->maxlen / sizeof(*i); + + /* + * Arrays are not supported, keep this simple. *Do not* add + * support for them. + */ + if (vleft != 1) { + *lenp = 0; + return -EINVAL; + } + + if (!conv) + conv = do_proc_douintvec_conv; + + if (write) + return do_proc_douintvec_w(i, table, buffer, lenp, ppos, + conv, data); + return do_proc_douintvec_r(i, buffer, lenp, ppos, conv, data); +} + +static int do_proc_douintvec(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos, + int (*conv)(unsigned long *lvalp, + unsigned int *valp, + int write, void *data), + void *data) +{ + return __do_proc_douintvec(table->data, table, write, + buffer, lenp, ppos, conv, data); +} + /** * proc_dointvec - read a vector of integers * @table: the sysctl table @@ -2284,8 +2466,8 @@ int proc_dointvec(struct ctl_table *table, int write, int proc_douintvec(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - return do_proc_dointvec(table, write, buffer, lenp, ppos, - do_proc_douintvec_conv, NULL); + return do_proc_douintvec(table, write, buffer, lenp, ppos, + do_proc_douintvec_conv, NULL); } /* @@ -2390,6 +2572,65 @@ int proc_dointvec_minmax(struct ctl_table *table, int write, do_proc_dointvec_minmax_conv, ¶m); } +struct do_proc_douintvec_minmax_conv_param { + unsigned int *min; + unsigned int *max; +}; + +static int do_proc_douintvec_minmax_conv(unsigned long *lvalp, + unsigned int *valp, + int write, void *data) +{ + struct do_proc_douintvec_minmax_conv_param *param = data; + + if (write) { + unsigned int val = *lvalp; + + if ((param->min && *param->min > val) || + (param->max && *param->max < val)) + return -ERANGE; + + if (*lvalp > UINT_MAX) + return -EINVAL; + *valp = val; + } else { + unsigned int val = *valp; + *lvalp = (unsigned long) val; + } + + return 0; +} + +/** + * proc_douintvec_minmax - read a vector of unsigned ints with min/max values + * @table: the sysctl table + * @write: %TRUE if this is a write to the sysctl file + * @buffer: the user buffer + * @lenp: the size of the user buffer + * @ppos: file position + * + * Reads/writes up to table->maxlen/sizeof(unsigned int) unsigned integer + * values from/to the user buffer, treated as an ASCII string. Negative + * strings are not allowed. + * + * This routine will ensure the values are within the range specified by + * table->extra1 (min) and table->extra2 (max). There is a final sanity + * check for UINT_MAX to avoid having to support wrap around uses from + * userspace. + * + * Returns 0 on success. + */ +int proc_douintvec_minmax(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct do_proc_douintvec_minmax_conv_param param = { + .min = (unsigned int *) table->extra1, + .max = (unsigned int *) table->extra2, + }; + return do_proc_douintvec(table, write, buffer, lenp, ppos, + do_proc_douintvec_minmax_conv, ¶m); +} + static void validate_coredump_safety(void) { #ifdef CONFIG_COREDUMP @@ -2447,17 +2688,8 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int left = *lenp; if (write) { - if (*ppos) { - switch (sysctl_writes_strict) { - case SYSCTL_WRITES_STRICT: - goto out; - case SYSCTL_WRITES_WARN: - warn_sysctl_write(table); - break; - default: - break; - } - } + if (proc_first_pos_non_zero_ignore(ppos, table)) + goto out; if (left > PAGE_SIZE - 1) left = PAGE_SIZE - 1; @@ -2898,6 +3130,12 @@ int proc_dointvec_minmax(struct ctl_table *table, int write, return -ENOSYS; } +int proc_douintvec_minmax(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return -ENOSYS; +} + int proc_dointvec_jiffies(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -2940,6 +3178,7 @@ EXPORT_SYMBOL(proc_dointvec); EXPORT_SYMBOL(proc_douintvec); EXPORT_SYMBOL(proc_dointvec_jiffies); EXPORT_SYMBOL(proc_dointvec_minmax); +EXPORT_SYMBOL_GPL(proc_douintvec_minmax); EXPORT_SYMBOL(proc_dointvec_userhz_jiffies); EXPORT_SYMBOL(proc_dointvec_ms_jiffies); EXPORT_SYMBOL(proc_dostring); diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index 939a158eab11..02e1859f2ca8 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -1346,7 +1346,7 @@ static void deprecated_sysctl_warning(const int *name, int nlen) * CTL_KERN/KERN_VERSION is used by older glibc and cannot * ever go away. */ - if (name[0] == CTL_KERN && name[1] == KERN_VERSION) + if (nlen >= 2 && name[0] == CTL_KERN && name[1] == KERN_VERSION) return; if (printk_ratelimit()) { diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 03e0b69bb5bf..cabe3e9fb620 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -29,15 +29,58 @@ #include <linux/kvm_para.h> #include <linux/kthread.h> +/* Watchdog configuration */ static DEFINE_MUTEX(watchdog_proc_mutex); -#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR) -unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED|NMI_WATCHDOG_ENABLED; +int __read_mostly nmi_watchdog_enabled; + +#if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HAVE_NMI_WATCHDOG) +unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED | + NMI_WATCHDOG_ENABLED; #else unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED; #endif -int __read_mostly nmi_watchdog_enabled; + +#ifdef CONFIG_HARDLOCKUP_DETECTOR +/* boot commands */ +/* + * Should we panic when a soft-lockup or hard-lockup occurs: + */ +unsigned int __read_mostly hardlockup_panic = + CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE; +/* + * We may not want to enable hard lockup detection by default in all cases, + * for example when running the kernel as a guest on a hypervisor. In these + * cases this function can be called to disable hard lockup detection. This + * function should only be executed once by the boot processor before the + * kernel command line parameters are parsed, because otherwise it is not + * possible to override this in hardlockup_panic_setup(). + */ +void hardlockup_detector_disable(void) +{ + watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; +} + +static int __init hardlockup_panic_setup(char *str) +{ + if (!strncmp(str, "panic", 5)) + hardlockup_panic = 1; + else if (!strncmp(str, "nopanic", 7)) + hardlockup_panic = 0; + else if (!strncmp(str, "0", 1)) + watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; + else if (!strncmp(str, "1", 1)) + watchdog_enabled |= NMI_WATCHDOG_ENABLED; + return 1; +} +__setup("nmi_watchdog=", hardlockup_panic_setup); + +#endif + +#ifdef CONFIG_SOFTLOCKUP_DETECTOR int __read_mostly soft_watchdog_enabled; +#endif + int __read_mostly watchdog_user_enabled; int __read_mostly watchdog_thresh = 10; @@ -45,15 +88,9 @@ int __read_mostly watchdog_thresh = 10; int __read_mostly sysctl_softlockup_all_cpu_backtrace; int __read_mostly sysctl_hardlockup_all_cpu_backtrace; #endif -static struct cpumask watchdog_cpumask __read_mostly; +struct cpumask watchdog_cpumask __read_mostly; unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); -/* Helper for online, unparked cpus. */ -#define for_each_watchdog_cpu(cpu) \ - for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask) - -atomic_t watchdog_park_in_progress = ATOMIC_INIT(0); - /* * The 'watchdog_running' variable is set to 1 when the watchdog threads * are registered/started and is set to 0 when the watchdog threads are @@ -72,7 +109,47 @@ static int __read_mostly watchdog_running; * of 'watchdog_running' cannot change while the watchdog is deactivated * temporarily (see related code in 'proc' handlers). */ -static int __read_mostly watchdog_suspended; +int __read_mostly watchdog_suspended; + +/* + * These functions can be overridden if an architecture implements its + * own hardlockup detector. + * + * watchdog_nmi_enable/disable can be implemented to start and stop when + * softlockup watchdog threads start and stop. The arch must select the + * SOFTLOCKUP_DETECTOR Kconfig. + */ +int __weak watchdog_nmi_enable(unsigned int cpu) +{ + return 0; +} +void __weak watchdog_nmi_disable(unsigned int cpu) +{ +} + +/* + * watchdog_nmi_reconfigure can be implemented to be notified after any + * watchdog configuration change. The arch hardlockup watchdog should + * respond to the following variables: + * - nmi_watchdog_enabled + * - watchdog_thresh + * - watchdog_cpumask + * - sysctl_hardlockup_all_cpu_backtrace + * - hardlockup_panic + * - watchdog_suspended + */ +void __weak watchdog_nmi_reconfigure(void) +{ +} + + +#ifdef CONFIG_SOFTLOCKUP_DETECTOR + +/* Helper for online, unparked cpus. */ +#define for_each_watchdog_cpu(cpu) \ + for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask) + +atomic_t watchdog_park_in_progress = ATOMIC_INIT(0); static u64 __read_mostly sample_period; @@ -120,6 +197,7 @@ static int __init softlockup_all_cpu_backtrace_setup(char *str) return 1; } __setup("softlockup_all_cpu_backtrace=", softlockup_all_cpu_backtrace_setup); +#ifdef CONFIG_HARDLOCKUP_DETECTOR static int __init hardlockup_all_cpu_backtrace_setup(char *str) { sysctl_hardlockup_all_cpu_backtrace = @@ -128,6 +206,7 @@ static int __init hardlockup_all_cpu_backtrace_setup(char *str) } __setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup); #endif +#endif /* * Hard-lockup warnings should be triggered after just a few seconds. Soft- @@ -213,18 +292,6 @@ void touch_softlockup_watchdog_sync(void) __this_cpu_write(watchdog_touch_ts, 0); } -/* watchdog detector functions */ -bool is_hardlockup(void) -{ - unsigned long hrint = __this_cpu_read(hrtimer_interrupts); - - if (__this_cpu_read(hrtimer_interrupts_saved) == hrint) - return true; - - __this_cpu_write(hrtimer_interrupts_saved, hrint); - return false; -} - static int is_softlockup(unsigned long touch_ts) { unsigned long now = get_timestamp(); @@ -237,21 +304,21 @@ static int is_softlockup(unsigned long touch_ts) return 0; } -static void watchdog_interrupt_count(void) +/* watchdog detector functions */ +bool is_hardlockup(void) { - __this_cpu_inc(hrtimer_interrupts); -} + unsigned long hrint = __this_cpu_read(hrtimer_interrupts); -/* - * These two functions are mostly architecture specific - * defining them as weak here. - */ -int __weak watchdog_nmi_enable(unsigned int cpu) -{ - return 0; + if (__this_cpu_read(hrtimer_interrupts_saved) == hrint) + return true; + + __this_cpu_write(hrtimer_interrupts_saved, hrint); + return false; } -void __weak watchdog_nmi_disable(unsigned int cpu) + +static void watchdog_interrupt_count(void) { + __this_cpu_inc(hrtimer_interrupts); } static int watchdog_enable_all_cpus(void); @@ -502,57 +569,6 @@ static void watchdog_unpark_threads(void) kthread_unpark(per_cpu(softlockup_watchdog, cpu)); } -/* - * Suspend the hard and soft lockup detector by parking the watchdog threads. - */ -int lockup_detector_suspend(void) -{ - int ret = 0; - - get_online_cpus(); - mutex_lock(&watchdog_proc_mutex); - /* - * Multiple suspend requests can be active in parallel (counted by - * the 'watchdog_suspended' variable). If the watchdog threads are - * running, the first caller takes care that they will be parked. - * The state of 'watchdog_running' cannot change while a suspend - * request is active (see related code in 'proc' handlers). - */ - if (watchdog_running && !watchdog_suspended) - ret = watchdog_park_threads(); - - if (ret == 0) - watchdog_suspended++; - else { - watchdog_disable_all_cpus(); - pr_err("Failed to suspend lockup detectors, disabled\n"); - watchdog_enabled = 0; - } - - mutex_unlock(&watchdog_proc_mutex); - - return ret; -} - -/* - * Resume the hard and soft lockup detector by unparking the watchdog threads. - */ -void lockup_detector_resume(void) -{ - mutex_lock(&watchdog_proc_mutex); - - watchdog_suspended--; - /* - * The watchdog threads are unparked if they were previously running - * and if there is no more active suspend request. - */ - if (watchdog_running && !watchdog_suspended) - watchdog_unpark_threads(); - - mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); -} - static int update_watchdog_all_cpus(void) { int ret; @@ -605,6 +621,100 @@ static void watchdog_disable_all_cpus(void) } #ifdef CONFIG_SYSCTL +static int watchdog_update_cpus(void) +{ + return smpboot_update_cpumask_percpu_thread( + &watchdog_threads, &watchdog_cpumask); +} +#endif + +#else /* SOFTLOCKUP */ +static int watchdog_park_threads(void) +{ + return 0; +} + +static void watchdog_unpark_threads(void) +{ +} + +static int watchdog_enable_all_cpus(void) +{ + return 0; +} + +static void watchdog_disable_all_cpus(void) +{ +} + +#ifdef CONFIG_SYSCTL +static int watchdog_update_cpus(void) +{ + return 0; +} +#endif + +static void set_sample_period(void) +{ +} +#endif /* SOFTLOCKUP */ + +/* + * Suspend the hard and soft lockup detector by parking the watchdog threads. + */ +int lockup_detector_suspend(void) +{ + int ret = 0; + + get_online_cpus(); + mutex_lock(&watchdog_proc_mutex); + /* + * Multiple suspend requests can be active in parallel (counted by + * the 'watchdog_suspended' variable). If the watchdog threads are + * running, the first caller takes care that they will be parked. + * The state of 'watchdog_running' cannot change while a suspend + * request is active (see related code in 'proc' handlers). + */ + if (watchdog_running && !watchdog_suspended) + ret = watchdog_park_threads(); + + if (ret == 0) + watchdog_suspended++; + else { + watchdog_disable_all_cpus(); + pr_err("Failed to suspend lockup detectors, disabled\n"); + watchdog_enabled = 0; + } + + watchdog_nmi_reconfigure(); + + mutex_unlock(&watchdog_proc_mutex); + + return ret; +} + +/* + * Resume the hard and soft lockup detector by unparking the watchdog threads. + */ +void lockup_detector_resume(void) +{ + mutex_lock(&watchdog_proc_mutex); + + watchdog_suspended--; + /* + * The watchdog threads are unparked if they were previously running + * and if there is no more active suspend request. + */ + if (watchdog_running && !watchdog_suspended) + watchdog_unpark_threads(); + + watchdog_nmi_reconfigure(); + + mutex_unlock(&watchdog_proc_mutex); + put_online_cpus(); +} + +#ifdef CONFIG_SYSCTL /* * Update the run state of the lockup detectors. @@ -625,6 +735,8 @@ static int proc_watchdog_update(void) else watchdog_disable_all_cpus(); + watchdog_nmi_reconfigure(); + return err; } @@ -810,10 +922,11 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write, * a temporary cpumask, so we are likely not in a * position to do much else to make things better. */ - if (smpboot_update_cpumask_percpu_thread( - &watchdog_threads, &watchdog_cpumask) != 0) + if (watchdog_update_cpus() != 0) pr_err("cpumask update failed\n"); } + + watchdog_nmi_reconfigure(); } out: mutex_unlock(&watchdog_proc_mutex); diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 54a427d1f344..295a0d84934c 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -22,41 +22,9 @@ static DEFINE_PER_CPU(bool, hard_watchdog_warn); static DEFINE_PER_CPU(bool, watchdog_nmi_touch); static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); -/* boot commands */ -/* - * Should we panic when a soft-lockup or hard-lockup occurs: - */ -unsigned int __read_mostly hardlockup_panic = - CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE; static unsigned long hardlockup_allcpu_dumped; -/* - * We may not want to enable hard lockup detection by default in all cases, - * for example when running the kernel as a guest on a hypervisor. In these - * cases this function can be called to disable hard lockup detection. This - * function should only be executed once by the boot processor before the - * kernel command line parameters are parsed, because otherwise it is not - * possible to override this in hardlockup_panic_setup(). - */ -void hardlockup_detector_disable(void) -{ - watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; -} - -static int __init hardlockup_panic_setup(char *str) -{ - if (!strncmp(str, "panic", 5)) - hardlockup_panic = 1; - else if (!strncmp(str, "nopanic", 7)) - hardlockup_panic = 0; - else if (!strncmp(str, "0", 1)) - watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; - else if (!strncmp(str, "1", 1)) - watchdog_enabled |= NMI_WATCHDOG_ENABLED; - return 1; -} -__setup("nmi_watchdog=", hardlockup_panic_setup); -void touch_nmi_watchdog(void) +void arch_touch_nmi_watchdog(void) { /* * Using __raw here because some code paths have @@ -66,9 +34,8 @@ void touch_nmi_watchdog(void) * going off. */ raw_cpu_write(watchdog_nmi_touch, true); - touch_softlockup_watchdog(); } -EXPORT_SYMBOL(touch_nmi_watchdog); +EXPORT_SYMBOL(arch_touch_nmi_watchdog); static struct perf_event_attr wd_hw_attr = { .type = PERF_TYPE_HARDWARE, diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index e20fc079bebd..b0d01c6d4e03 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -778,34 +778,45 @@ config DEBUG_SHIRQ menu "Debug Lockups and Hangs" config LOCKUP_DETECTOR - bool "Detect Hard and Soft Lockups" + bool + +config SOFTLOCKUP_DETECTOR + bool "Detect Soft Lockups" depends on DEBUG_KERNEL && !S390 + select LOCKUP_DETECTOR help Say Y here to enable the kernel to act as a watchdog to detect - hard and soft lockups. + soft lockups. Softlockups are bugs that cause the kernel to loop in kernel mode for more than 20 seconds, without giving other tasks a chance to run. The current stack trace is displayed upon detection and the system will stay locked up. +config HARDLOCKUP_DETECTOR_PERF + bool + select SOFTLOCKUP_DETECTOR + +# +# arch/ can define HAVE_HARDLOCKUP_DETECTOR_ARCH to provide their own hard +# lockup detector rather than the perf based detector. +# +config HARDLOCKUP_DETECTOR + bool "Detect Hard Lockups" + depends on DEBUG_KERNEL && !S390 + depends on HAVE_HARDLOCKUP_DETECTOR_PERF || HAVE_HARDLOCKUP_DETECTOR_ARCH + select LOCKUP_DETECTOR + select HARDLOCKUP_DETECTOR_PERF if HAVE_HARDLOCKUP_DETECTOR_PERF + select HARDLOCKUP_DETECTOR_ARCH if HAVE_HARDLOCKUP_DETECTOR_ARCH + help + Say Y here to enable the kernel to act as a watchdog to detect + hard lockups. + Hardlockups are bugs that cause the CPU to loop in kernel mode for more than 10 seconds, without letting other interrupts have a chance to run. The current stack trace is displayed upon detection and the system will stay locked up. - The overhead should be minimal. A periodic hrtimer runs to - generate interrupts and kick the watchdog task every 4 seconds. - An NMI is generated every 10 seconds or so to check for hardlockups. - - The frequency of hrtimer and NMI events and the soft and hard lockup - thresholds can be controlled through the sysctl watchdog_thresh. - -config HARDLOCKUP_DETECTOR - def_bool y - depends on LOCKUP_DETECTOR && !HAVE_NMI_WATCHDOG - depends on PERF_EVENTS && HAVE_PERF_EVENTS_NMI - config BOOTPARAM_HARDLOCKUP_PANIC bool "Panic (Reboot) On Hard Lockups" depends on HARDLOCKUP_DETECTOR @@ -826,7 +837,7 @@ config BOOTPARAM_HARDLOCKUP_PANIC_VALUE config BOOTPARAM_SOFTLOCKUP_PANIC bool "Panic (Reboot) On Soft Lockups" - depends on LOCKUP_DETECTOR + depends on SOFTLOCKUP_DETECTOR help Say Y here to enable the kernel to panic on "soft lockups", which are bugs that cause the kernel to loop in kernel @@ -843,7 +854,7 @@ config BOOTPARAM_SOFTLOCKUP_PANIC config BOOTPARAM_SOFTLOCKUP_PANIC_VALUE int - depends on LOCKUP_DETECTOR + depends on SOFTLOCKUP_DETECTOR range 0 1 default 0 if !BOOTPARAM_SOFTLOCKUP_PANIC default 1 if BOOTPARAM_SOFTLOCKUP_PANIC @@ -851,7 +862,7 @@ config BOOTPARAM_SOFTLOCKUP_PANIC_VALUE config DETECT_HUNG_TASK bool "Detect Hung Tasks" depends on DEBUG_KERNEL - default LOCKUP_DETECTOR + default SOFTLOCKUP_DETECTOR help Say Y here to enable the kernel to detect "hung tasks", which are bugs that cause the task to be stuck in @@ -1785,6 +1796,17 @@ config TEST_FIRMWARE If unsure, say N. +config TEST_SYSCTL + tristate "sysctl test driver" + default n + depends on PROC_SYSCTL + help + This builds the "test_sysctl" module. This driver enables to test the + proc sysctl interfaces available to drivers safely without affecting + production knobs which might alter system functionality. + + If unsure, say N. + config TEST_UDELAY tristate "udelay test driver" default n diff --git a/lib/Makefile b/lib/Makefile index 5a008329324e..85e91e51a9fe 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -46,6 +46,7 @@ obj-$(CONFIG_TEST_HEXDUMP) += test_hexdump.o obj-y += kstrtox.o obj-$(CONFIG_TEST_BPF) += test_bpf.o obj-$(CONFIG_TEST_FIRMWARE) += test_firmware.o +obj-$(CONFIG_TEST_SYSCTL) += test_sysctl.o obj-$(CONFIG_TEST_HASH) += test_hash.o test_siphash.o obj-$(CONFIG_TEST_KASAN) += test_kasan.o obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o diff --git a/lib/fault-inject.c b/lib/fault-inject.c index 4ff157159a0d..09ac73c177fd 100644 --- a/lib/fault-inject.c +++ b/lib/fault-inject.c @@ -107,6 +107,12 @@ static inline bool fail_stacktrace(struct fault_attr *attr) bool should_fail(struct fault_attr *attr, ssize_t size) { + if (in_task() && current->fail_nth) { + if (--current->fail_nth == 0) + goto fail; + return false; + } + /* No need to check any other properties if the probability is 0 */ if (attr->probability == 0) return false; @@ -134,6 +140,7 @@ bool should_fail(struct fault_attr *attr, ssize_t size) if (!fail_stacktrace(attr)) return false; +fail: fail_dump(attr); if (atomic_read(&attr->times) != -1) diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c index 8ee7e5ec21be..3bf4a9984f4c 100644 --- a/lib/percpu_counter.c +++ b/lib/percpu_counter.c @@ -72,6 +72,13 @@ void percpu_counter_set(struct percpu_counter *fbc, s64 amount) } EXPORT_SYMBOL(percpu_counter_set); +/** + * This function is both preempt and irq safe. The former is due to explicit + * preemption disable. The latter is guaranteed by the fact that the slow path + * is explicitly protected by an irq-safe spinlock whereas the fast patch uses + * this_cpu_add which is irq-safe by definition. Hence there is no need muck + * with irq state before calling this one + */ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { s64 count; diff --git a/lib/string.c b/lib/string.c index 1c1fc9187b05..ebbb99c775bd 100644 --- a/lib/string.c +++ b/lib/string.c @@ -978,3 +978,10 @@ char *strreplace(char *s, char old, char new) return s; } EXPORT_SYMBOL(strreplace); + +void fortify_panic(const char *name) +{ + pr_emerg("detected buffer overflow in %s\n", name); + BUG(); +} +EXPORT_SYMBOL(fortify_panic); diff --git a/lib/test_sysctl.c b/lib/test_sysctl.c new file mode 100644 index 000000000000..3dd801c1c85b --- /dev/null +++ b/lib/test_sysctl.c @@ -0,0 +1,148 @@ +/* + * proc sysctl test driver + * + * Copyright (C) 2017 Luis R. Rodriguez <mcgrof@kernel.org> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or at your option any + * later version; or, when distributed separately from the Linux kernel or + * when incorporated into other software packages, subject to the following + * license: + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of copyleft-next (version 0.3.1 or later) as published + * at http://copyleft-next.org/. + */ + +/* + * This module provides an interface to the the proc sysctl interfaces. This + * driver requires CONFIG_PROC_SYSCTL. It will not normally be loaded by the + * system unless explicitly requested by name. You can also build this driver + * into your kernel. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/init.h> +#include <linux/list.h> +#include <linux/module.h> +#include <linux/printk.h> +#include <linux/fs.h> +#include <linux/miscdevice.h> +#include <linux/slab.h> +#include <linux/uaccess.h> +#include <linux/async.h> +#include <linux/delay.h> +#include <linux/vmalloc.h> + +static int i_zero; +static int i_one_hundred = 100; + +struct test_sysctl_data { + int int_0001; + int int_0002; + int int_0003[4]; + + unsigned int uint_0001; + + char string_0001[65]; +}; + +static struct test_sysctl_data test_data = { + .int_0001 = 60, + .int_0002 = 1, + + .int_0003[0] = 0, + .int_0003[1] = 1, + .int_0003[2] = 2, + .int_0003[3] = 3, + + .uint_0001 = 314, + + .string_0001 = "(none)", +}; + +/* These are all under /proc/sys/debug/test_sysctl/ */ +static struct ctl_table test_table[] = { + { + .procname = "int_0001", + .data = &test_data.int_0001, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }, + { + .procname = "int_0002", + .data = &test_data.int_0002, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "int_0003", + .data = &test_data.int_0003, + .maxlen = sizeof(test_data.int_0003), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "uint_0001", + .data = &test_data.uint_0001, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_douintvec, + }, + { + .procname = "string_0001", + .data = &test_data.string_0001, + .maxlen = sizeof(test_data.string_0001), + .mode = 0644, + .proc_handler = proc_dostring, + }, + { } +}; + +static struct ctl_table test_sysctl_table[] = { + { + .procname = "test_sysctl", + .maxlen = 0, + .mode = 0555, + .child = test_table, + }, + { } +}; + +static struct ctl_table test_sysctl_root_table[] = { + { + .procname = "debug", + .maxlen = 0, + .mode = 0555, + .child = test_sysctl_table, + }, + { } +}; + +static struct ctl_table_header *test_sysctl_header; + +static int __init test_sysctl_init(void) +{ + test_sysctl_header = register_sysctl_table(test_sysctl_root_table); + if (!test_sysctl_header) + return -ENOMEM; + return 0; +} +late_initcall(test_sysctl_init); + +static void __exit test_sysctl_exit(void) +{ + if (test_sysctl_header) + unregister_sysctl_table(test_sysctl_header); +} + +module_exit(test_sysctl_exit); + +MODULE_AUTHOR("Luis R. Rodriguez <mcgrof@kernel.org>"); +MODULE_LICENSE("GPL"); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 1e516520433d..bc48ee783dd9 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1384,7 +1384,7 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) page = __alloc_pages_node(nid, htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE| - __GFP_REPEAT|__GFP_NOWARN, + __GFP_RETRY_MAYFAIL|__GFP_NOWARN, huge_page_order(h)); if (page) { prep_new_huge_page(h, page, nid); @@ -1525,7 +1525,7 @@ static struct page *__hugetlb_alloc_buddy_huge_page(struct hstate *h, { int order = huge_page_order(h); - gfp_mask |= __GFP_COMP|__GFP_REPEAT|__GFP_NOWARN; + gfp_mask |= __GFP_COMP|__GFP_RETRY_MAYFAIL|__GFP_NOWARN; if (nid == NUMA_NO_NODE) nid = numa_mem_id(); return __alloc_pages_nodemask(gfp_mask, order, nid, nmask); diff --git a/mm/internal.h b/mm/internal.h index 0e4f558412fb..24d88f084705 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -23,7 +23,7 @@ * hints such as HIGHMEM usage. */ #define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\ - __GFP_NOWARN|__GFP_REPEAT|__GFP_NOFAIL|\ + __GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_NOFAIL|\ __GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\ __GFP_ATOMIC) diff --git a/mm/memory.c b/mm/memory.c index cbb57194687e..0e517be91a89 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3591,7 +3591,7 @@ out: return 0; } -static int create_huge_pmd(struct vm_fault *vmf) +static inline int create_huge_pmd(struct vm_fault *vmf) { if (vma_is_anonymous(vmf->vma)) return do_huge_pmd_anonymous_page(vmf); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 7d8e56214ac0..d911fa5cb2a7 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1078,7 +1078,8 @@ static struct page *new_page(struct page *page, unsigned long start, int **x) /* * if !vma, alloc_page_vma() will use task or system default policy */ - return alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); + return alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL, + vma, address); } #else diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 0b60cc7ddac2..96e93b214d31 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -601,7 +601,7 @@ static inline void __wb_writeout_inc(struct bdi_writeback *wb) { struct wb_domain *cgdom; - __inc_wb_stat(wb, WB_WRITTEN); + inc_wb_stat(wb, WB_WRITTEN); wb_domain_writeout_inc(&global_wb_domain, &wb->completions, wb->bdi->max_prop_frac); @@ -2435,8 +2435,8 @@ void account_page_dirtied(struct page *page, struct address_space *mapping) __inc_lruvec_page_state(page, NR_FILE_DIRTY); __inc_zone_page_state(page, NR_ZONE_WRITE_PENDING); __inc_node_page_state(page, NR_DIRTIED); - __inc_wb_stat(wb, WB_RECLAIMABLE); - __inc_wb_stat(wb, WB_DIRTIED); + inc_wb_stat(wb, WB_RECLAIMABLE); + inc_wb_stat(wb, WB_DIRTIED); task_io_account_write(PAGE_SIZE); current->nr_dirtied++; this_cpu_inc(bdp_ratelimits); @@ -2741,7 +2741,7 @@ int test_clear_page_writeback(struct page *page) if (bdi_cap_account_writeback(bdi)) { struct bdi_writeback *wb = inode_to_wb(inode); - __dec_wb_stat(wb, WB_WRITEBACK); + dec_wb_stat(wb, WB_WRITEBACK); __wb_writeout_inc(wb); } } @@ -2786,7 +2786,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write) page_index(page), PAGECACHE_TAG_WRITEBACK); if (bdi_cap_account_writeback(bdi)) - __inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK); + inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK); /* * We can come through here when swapping anonymous diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 64b7d82a9b1a..6d30e914afb6 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3284,6 +3284,14 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, /* The OOM killer will not help higher order allocs */ if (order > PAGE_ALLOC_COSTLY_ORDER) goto out; + /* + * We have already exhausted all our reclaim opportunities without any + * success so it is time to admit defeat. We will skip the OOM killer + * because it is very likely that the caller has a more reasonable + * fallback than shooting a random task. + */ + if (gfp_mask & __GFP_RETRY_MAYFAIL) + goto out; /* The OOM killer does not needlessly kill tasks for lowmem */ if (ac->high_zoneidx < ZONE_NORMAL) goto out; @@ -3413,7 +3421,7 @@ should_compact_retry(struct alloc_context *ac, int order, int alloc_flags, } /* - * !costly requests are much more important than __GFP_REPEAT + * !costly requests are much more important than __GFP_RETRY_MAYFAIL * 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 @@ -3920,9 +3928,9 @@ retry: /* * Do not retry costly high order allocations unless they are - * __GFP_REPEAT + * __GFP_RETRY_MAYFAIL */ - if (costly_order && !(gfp_mask & __GFP_REPEAT)) + if (costly_order && !(gfp_mask & __GFP_RETRY_MAYFAIL)) goto nopage; if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags, diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index a56c3989f773..c50b1a14d55e 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -56,11 +56,11 @@ void * __meminit vmemmap_alloc_block(unsigned long size, int node) if (node_state(node, N_HIGH_MEMORY)) page = alloc_pages_node( - node, GFP_KERNEL | __GFP_ZERO | __GFP_REPEAT, + node, GFP_KERNEL | __GFP_ZERO | __GFP_RETRY_MAYFAIL, get_order(size)); else page = alloc_pages( - GFP_KERNEL | __GFP_ZERO | __GFP_REPEAT, + GFP_KERNEL | __GFP_ZERO | __GFP_RETRY_MAYFAIL, get_order(size)); if (page) return page_address(page); diff --git a/mm/util.c b/mm/util.c index 26be6407abd7..ee250e2cde34 100644 --- a/mm/util.c +++ b/mm/util.c @@ -339,9 +339,9 @@ EXPORT_SYMBOL(vm_mmap); * Uses kmalloc to get the memory but if the allocation fails then falls back * to the vmalloc allocator. Use kvfree for freeing the memory. * - * Reclaim modifiers - __GFP_NORETRY and __GFP_NOFAIL are not supported. __GFP_REPEAT - * is supported only for large (>32kB) allocations, and it should be used only if - * kmalloc is preferable to the vmalloc fallback, due to visible performance drawbacks. + * Reclaim modifiers - __GFP_NORETRY and __GFP_NOFAIL are not supported. + * __GFP_RETRY_MAYFAIL is supported, and it should be used only if kmalloc is + * preferable to the vmalloc fallback, due to visible performance drawbacks. * * Any use of gfp flags outside of GFP_KERNEL should be consulted with mm people. */ @@ -366,13 +366,7 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node) if (size > PAGE_SIZE) { kmalloc_flags |= __GFP_NOWARN; - /* - * We have to override __GFP_REPEAT by __GFP_NORETRY for !costly - * requests because there is no other way to tell the allocator - * that we want to fail rather than retry endlessly. - */ - if (!(kmalloc_flags & __GFP_REPEAT) || - (size <= PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) + if (!(kmalloc_flags & __GFP_RETRY_MAYFAIL)) kmalloc_flags |= __GFP_NORETRY; } diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 6016ab079e2b..8698c1c86c4d 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1795,7 +1795,7 @@ fail: * allocator with @gfp_mask flags. Map them into contiguous * kernel virtual space, using a pagetable protection of @prot. * - * Reclaim modifiers in @gfp_mask - __GFP_NORETRY, __GFP_REPEAT + * Reclaim modifiers in @gfp_mask - __GFP_NORETRY, __GFP_RETRY_MAYFAIL * and __GFP_NOFAIL are not supported * * Any use of gfp flags outside of GFP_KERNEL should be consulted diff --git a/mm/vmscan.c b/mm/vmscan.c index e9210f825219..a1af041930a6 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2506,18 +2506,18 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat, return false; /* Consider stopping depending on scan and reclaim activity */ - if (sc->gfp_mask & __GFP_REPEAT) { + if (sc->gfp_mask & __GFP_RETRY_MAYFAIL) { /* - * For __GFP_REPEAT allocations, stop reclaiming if the + * For __GFP_RETRY_MAYFAIL allocations, stop reclaiming if the * full LRU list has been scanned and we are still failing * to reclaim pages. This full LRU scan is potentially - * expensive but a __GFP_REPEAT caller really wants to succeed + * expensive but a __GFP_RETRY_MAYFAIL caller really wants to succeed */ if (!nr_reclaimed && !nr_scanned) return false; } else { /* - * For non-__GFP_REPEAT allocations which can presumably + * For non-__GFP_RETRY_MAYFAIL allocations which can presumably * fail without consequence, stop if we failed to reclaim * any pages from the last SWAP_CLUSTER_MAX number of * pages that were scanned. This will return to the diff --git a/net/core/dev.c b/net/core/dev.c index 02440518dd69..8515f8fe0460 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -7384,7 +7384,7 @@ static int netif_alloc_rx_queues(struct net_device *dev) BUG_ON(count < 1); - rx = kvzalloc(sz, GFP_KERNEL | __GFP_REPEAT); + rx = kvzalloc(sz, GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!rx) return -ENOMEM; @@ -7424,7 +7424,7 @@ static int netif_alloc_netdev_queues(struct net_device *dev) if (count < 1 || count > 0xffff) return -EINVAL; - tx = kvzalloc(sz, GFP_KERNEL | __GFP_REPEAT); + tx = kvzalloc(sz, GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!tx) return -ENOMEM; @@ -7965,7 +7965,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, /* ensure 32-byte alignment of whole construct */ alloc_size += NETDEV_ALIGN - 1; - p = kvzalloc(alloc_size, GFP_KERNEL | __GFP_REPEAT); + p = kvzalloc(alloc_size, GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!p) return NULL; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 8b11341ed69a..f990eb8b30a9 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4747,7 +4747,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len, gfp_head = gfp_mask; if (gfp_head & __GFP_DIRECT_RECLAIM) - gfp_head |= __GFP_REPEAT; + gfp_head |= __GFP_RETRY_MAYFAIL; *errcode = -ENOBUFS; skb = alloc_skb(header_len, gfp_head); diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 1770c1d9b37f..e1648238a9c9 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1003,14 +1003,10 @@ struct xt_table_info *xt_alloc_table_info(unsigned int size) if ((SMP_ALIGN(size) >> PAGE_SHIFT) + 2 > totalram_pages) return NULL; - if (sz <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) - info = kmalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); - if (!info) { - info = __vmalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY, - PAGE_KERNEL); - if (!info) - return NULL; - } + info = kvmalloc(sz, GFP_KERNEL); + if (!info) + return NULL; + memset(info, 0, sizeof(*info)); info->size = size; return info; diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 147fde73a0f5..263d16e3219e 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -648,7 +648,7 @@ static int fq_resize(struct Qdisc *sch, u32 log) return 0; /* If XPS was setup, we can allocate memory on right NUMA node */ - array = kvmalloc_node(sizeof(struct rb_root) << log, GFP_KERNEL | __GFP_REPEAT, + array = kvmalloc_node(sizeof(struct rb_root) << log, GFP_KERNEL | __GFP_RETRY_MAYFAIL, netdev_queue_numa_node_read(sch->dev_queue)); if (!array) return -ENOMEM; diff --git a/samples/kfifo/dma-example.c b/samples/kfifo/dma-example.c index aa243db93f01..be0d4a5fdf53 100644 --- a/samples/kfifo/dma-example.c +++ b/samples/kfifo/dma-example.c @@ -75,8 +75,8 @@ static int __init example_init(void) for (i = 0; i < nents; i++) { printk(KERN_INFO "sg[%d] -> " - "page_link 0x%.8lx offset 0x%.8x length 0x%.8x\n", - i, sg[i].page_link, sg[i].offset, sg[i].length); + "page %p offset 0x%.8x length 0x%.8x\n", + i, sg_page(&sg[i]), sg[i].offset, sg[i].length); if (sg_is_last(&sg[i])) break; @@ -104,8 +104,8 @@ static int __init example_init(void) for (i = 0; i < nents; i++) { printk(KERN_INFO "sg[%d] -> " - "page_link 0x%.8lx offset 0x%.8x length 0x%.8x\n", - i, sg[i].page_link, sg[i].offset, sg[i].length); + "page %p offset 0x%.8x length 0x%.8x\n", + i, sg_page(&sg[i]), sg[i].offset, sg[i].length); if (sg_is_last(&sg[i])) break; diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 8f940c09918f..2287a0bca863 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -5576,10 +5576,18 @@ sub process { "architecture specific defines should be avoided\n" . $herecurr); } +# check that the storage class is not after a type + if ($line =~ /\b($Type)\s+($Storage)\b/) { + WARN("STORAGE_CLASS", + "storage class '$2' should be located before type '$1'\n" . $herecurr); + } # Check that the storage class is at the beginning of a declaration - if ($line =~ /\b$Storage\b/ && $line !~ /^.\s*$Storage\b/) { + if ($line =~ /\b$Storage\b/ && + $line !~ /^.\s*$Storage/ && + $line =~ /^.\s*(.+?)\$Storage\s/ && + $1 !~ /[\,\)]\s*$/) { WARN("STORAGE_CLASS", - "storage class should be at the beginning of the declaration\n" . $herecurr) + "storage class should be at the beginning of the declaration\n" . $herecurr); } # check the location of the inline attribute, that it is between diff --git a/scripts/gdb/linux/constants.py.in b/scripts/gdb/linux/constants.py.in index 7986f4e0da12..7aad82406422 100644 --- a/scripts/gdb/linux/constants.py.in +++ b/scripts/gdb/linux/constants.py.in @@ -14,6 +14,7 @@ #include <linux/fs.h> #include <linux/mount.h> +#include <linux/of_fdt.h> /* We need to stringify expanded macros so that they can be parsed */ @@ -50,3 +51,9 @@ LX_VALUE(MNT_NOEXEC) LX_VALUE(MNT_NOATIME) LX_VALUE(MNT_NODIRATIME) LX_VALUE(MNT_RELATIME) + +/* linux/of_fdt.h> */ +LX_VALUE(OF_DT_HEADER) + +/* Kernel Configs */ +LX_CONFIG(CONFIG_OF) diff --git a/scripts/gdb/linux/dmesg.py b/scripts/gdb/linux/dmesg.py index 5afd1098e33a..6d2e09a2ad2f 100644 --- a/scripts/gdb/linux/dmesg.py +++ b/scripts/gdb/linux/dmesg.py @@ -12,6 +12,7 @@ # import gdb +import sys from linux import utils @@ -24,7 +25,7 @@ class LxDmesg(gdb.Command): def invoke(self, arg, from_tty): log_buf_addr = int(str(gdb.parse_and_eval( - "'printk.c'::log_buf")).split()[0], 16) + "(void *)'printk.c'::log_buf")).split()[0], 16) log_first_idx = int(gdb.parse_and_eval("'printk.c'::log_first_idx")) log_next_idx = int(gdb.parse_and_eval("'printk.c'::log_next_idx")) log_buf_len = int(gdb.parse_and_eval("'printk.c'::log_buf_len")) @@ -52,13 +53,19 @@ class LxDmesg(gdb.Command): continue text_len = utils.read_u16(log_buf[pos + 10:pos + 12]) - text = log_buf[pos + 16:pos + 16 + text_len].decode() + text = log_buf[pos + 16:pos + 16 + text_len].decode( + encoding='utf8', errors='replace') time_stamp = utils.read_u64(log_buf[pos:pos + 8]) for line in text.splitlines(): - gdb.write("[{time:12.6f}] {line}\n".format( + msg = u"[{time:12.6f}] {line}\n".format( time=time_stamp / 1000000000.0, - line=line)) + line=line) + # With python2 gdb.write will attempt to convert unicode to + # ascii and might fail so pass an utf8-encoded str instead. + if sys.hexversion < 0x03000000: + msg = msg.encode(encoding='utf8', errors='replace') + gdb.write(msg) pos += length diff --git a/scripts/gdb/linux/proc.py b/scripts/gdb/linux/proc.py index 38b1f09d1cd9..086d27223c0c 100644 --- a/scripts/gdb/linux/proc.py +++ b/scripts/gdb/linux/proc.py @@ -16,6 +16,7 @@ from linux import constants from linux import utils from linux import tasks from linux import lists +from struct import * class LxCmdLine(gdb.Command): @@ -195,3 +196,75 @@ values of that process namespace""" info_opts(MNT_INFO, m_flags))) LxMounts() + + +class LxFdtDump(gdb.Command): + """Output Flattened Device Tree header and dump FDT blob to the filename + specified as the command argument. Equivalent to + 'cat /proc/fdt > fdtdump.dtb' on a running target""" + + def __init__(self): + super(LxFdtDump, self).__init__("lx-fdtdump", gdb.COMMAND_DATA, + gdb.COMPLETE_FILENAME) + + def fdthdr_to_cpu(self, fdt_header): + + fdt_header_be = ">IIIIIII" + fdt_header_le = "<IIIIIII" + + if utils.get_target_endianness() == 1: + output_fmt = fdt_header_le + else: + output_fmt = fdt_header_be + + return unpack(output_fmt, pack(fdt_header_be, + fdt_header['magic'], + fdt_header['totalsize'], + fdt_header['off_dt_struct'], + fdt_header['off_dt_strings'], + fdt_header['off_mem_rsvmap'], + fdt_header['version'], + fdt_header['last_comp_version'])) + + def invoke(self, arg, from_tty): + + if not constants.LX_CONFIG_OF: + raise gdb.GdbError("Kernel not compiled with CONFIG_OF\n") + + if len(arg) == 0: + filename = "fdtdump.dtb" + else: + filename = arg + + py_fdt_header_ptr = gdb.parse_and_eval( + "(const struct fdt_header *) initial_boot_params") + py_fdt_header = py_fdt_header_ptr.dereference() + + fdt_header = self.fdthdr_to_cpu(py_fdt_header) + + if fdt_header[0] != constants.LX_OF_DT_HEADER: + raise gdb.GdbError("No flattened device tree magic found\n") + + gdb.write("fdt_magic: 0x{:02X}\n".format(fdt_header[0])) + gdb.write("fdt_totalsize: 0x{:02X}\n".format(fdt_header[1])) + gdb.write("off_dt_struct: 0x{:02X}\n".format(fdt_header[2])) + gdb.write("off_dt_strings: 0x{:02X}\n".format(fdt_header[3])) + gdb.write("off_mem_rsvmap: 0x{:02X}\n".format(fdt_header[4])) + gdb.write("version: {}\n".format(fdt_header[5])) + gdb.write("last_comp_version: {}\n".format(fdt_header[6])) + + inf = gdb.inferiors()[0] + fdt_buf = utils.read_memoryview(inf, py_fdt_header_ptr, + fdt_header[1]).tobytes() + + try: + f = open(filename, 'wb') + except: + raise gdb.GdbError("Could not open file to dump fdt") + + f.write(fdt_buf) + f.close() + + gdb.write("Dumped fdt blob to " + filename + "\n") + +LxFdtDump() diff --git a/security/Kconfig b/security/Kconfig index d540bfe73190..e8e449444e65 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -163,6 +163,13 @@ config HARDENED_USERCOPY_PAGESPAN been removed. This config is intended to be used only while trying to find such users. +config FORTIFY_SOURCE + bool "Harden common str/mem functions against buffer overflows" + depends on ARCH_HAS_FORTIFY_SOURCE + help + Detect overflows of buffers in common string and memory functions + where the compiler can determine and validate the buffer sizes. + config STATIC_USERMODEHELPER bool "Force all usermode helper calls through a single binary" help diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 0a8a1c45af87..a1497c516d85 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -643,7 +643,7 @@ static const struct { { "__GFP_FS", "F" }, { "__GFP_COLD", "CO" }, { "__GFP_NOWARN", "NWR" }, - { "__GFP_REPEAT", "R" }, + { "__GFP_RETRY_MAYFAIL", "R" }, { "__GFP_NOFAIL", "NF" }, { "__GFP_NORETRY", "NR" }, { "__GFP_COMP", "C" }, diff --git a/tools/testing/selftests/sysctl/Makefile b/tools/testing/selftests/sysctl/Makefile index b3c33e071f10..95c320b354e8 100644 --- a/tools/testing/selftests/sysctl/Makefile +++ b/tools/testing/selftests/sysctl/Makefile @@ -4,8 +4,7 @@ # No binaries, but make sure arg-less "make" doesn't trigger "run_tests". all: -TEST_PROGS := run_numerictests run_stringtests -TEST_FILES := common_tests +TEST_PROGS := sysctl.sh include ../lib.mk diff --git a/tools/testing/selftests/sysctl/common_tests b/tools/testing/selftests/sysctl/common_tests deleted file mode 100644 index b6862322962f..000000000000 --- a/tools/testing/selftests/sysctl/common_tests +++ /dev/null @@ -1,131 +0,0 @@ -#!/bin/sh - -TEST_FILE=$(mktemp) - -echo "== Testing sysctl behavior against ${TARGET} ==" - -set_orig() -{ - echo "${ORIG}" > "${TARGET}" -} - -set_test() -{ - echo "${TEST_STR}" > "${TARGET}" -} - -verify() -{ - local seen - seen=$(cat "$1") - if [ "${seen}" != "${TEST_STR}" ]; then - return 1 - fi - return 0 -} - -exit_test() -{ - if [ ! -z ${old_strict} ]; then - echo ${old_strict} > ${WRITES_STRICT} - fi - exit $rc -} - -trap 'set_orig; rm -f "${TEST_FILE}"' EXIT - -rc=0 - -echo -n "Writing test file ... " -echo "${TEST_STR}" > "${TEST_FILE}" -if ! verify "${TEST_FILE}"; then - echo "FAIL" >&2 - exit 1 -else - echo "ok" -fi - -echo -n "Checking sysctl is not set to test value ... " -if verify "${TARGET}"; then - echo "FAIL" >&2 - exit 1 -else - echo "ok" -fi - -echo -n "Writing sysctl from shell ... " -set_test -if ! verify "${TARGET}"; then - echo "FAIL" >&2 - exit 1 -else - echo "ok" -fi - -echo -n "Resetting sysctl to original value ... " -set_orig -if verify "${TARGET}"; then - echo "FAIL" >&2 - exit 1 -else - echo "ok" -fi - -echo -n "Checking write strict setting ... " -WRITES_STRICT="${SYSCTL}/kernel/sysctl_writes_strict" -if [ ! -e ${WRITES_STRICT} ]; then - echo "FAIL, but skip in case of old kernel" >&2 -else - old_strict=$(cat ${WRITES_STRICT}) - if [ "$old_strict" = "1" ]; then - echo "ok" - else - echo "FAIL, strict value is 0 but force to 1 to continue" >&2 - echo "1" > ${WRITES_STRICT} - fi -fi - -# Now that we've validated the sanity of "set_test" and "set_orig", -# we can use those functions to set starting states before running -# specific behavioral tests. - -echo -n "Writing entire sysctl in single write ... " -set_orig -dd if="${TEST_FILE}" of="${TARGET}" bs=4096 2>/dev/null -if ! verify "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi - -echo -n "Writing middle of sysctl after synchronized seek ... " -set_test -dd if="${TEST_FILE}" of="${TARGET}" bs=1 seek=1 skip=1 2>/dev/null -if ! verify "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi - -echo -n "Writing beyond end of sysctl ... " -set_orig -dd if="${TEST_FILE}" of="${TARGET}" bs=20 seek=2 2>/dev/null -if verify "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi - -echo -n "Writing sysctl with multiple long writes ... " -set_orig -(perl -e 'print "A" x 50;'; echo "${TEST_STR}") | \ - dd of="${TARGET}" bs=50 2>/dev/null -if verify "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi diff --git a/tools/testing/selftests/sysctl/config b/tools/testing/selftests/sysctl/config new file mode 100644 index 000000000000..6ca14800d755 --- /dev/null +++ b/tools/testing/selftests/sysctl/config @@ -0,0 +1 @@ +CONFIG_TEST_SYSCTL=y diff --git a/tools/testing/selftests/sysctl/run_numerictests b/tools/testing/selftests/sysctl/run_numerictests deleted file mode 100755 index e6e76c93d948..000000000000 --- a/tools/testing/selftests/sysctl/run_numerictests +++ /dev/null @@ -1,10 +0,0 @@ -#!/bin/sh - -SYSCTL="/proc/sys" -TARGET="${SYSCTL}/vm/swappiness" -ORIG=$(cat "${TARGET}") -TEST_STR=$(( $ORIG + 1 )) - -. ./common_tests - -exit_test diff --git a/tools/testing/selftests/sysctl/run_stringtests b/tools/testing/selftests/sysctl/run_stringtests deleted file mode 100755 index 857ec667fb02..000000000000 --- a/tools/testing/selftests/sysctl/run_stringtests +++ /dev/null @@ -1,77 +0,0 @@ -#!/bin/sh - -SYSCTL="/proc/sys" -TARGET="${SYSCTL}/kernel/domainname" -ORIG=$(cat "${TARGET}") -TEST_STR="Testing sysctl" - -. ./common_tests - -# Only string sysctls support seeking/appending. -MAXLEN=65 - -echo -n "Writing entire sysctl in short writes ... " -set_orig -dd if="${TEST_FILE}" of="${TARGET}" bs=1 2>/dev/null -if ! verify "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi - -echo -n "Writing middle of sysctl after unsynchronized seek ... " -set_test -dd if="${TEST_FILE}" of="${TARGET}" bs=1 seek=1 2>/dev/null -if verify "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi - -echo -n "Checking sysctl maxlen is at least $MAXLEN ... " -set_orig -perl -e 'print "A" x ('"${MAXLEN}"'-2), "B";' | \ - dd of="${TARGET}" bs="${MAXLEN}" 2>/dev/null -if ! grep -q B "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi - -echo -n "Checking sysctl keeps original string on overflow append ... " -set_orig -perl -e 'print "A" x ('"${MAXLEN}"'-1), "B";' | \ - dd of="${TARGET}" bs=$(( MAXLEN - 1 )) 2>/dev/null -if grep -q B "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi - -echo -n "Checking sysctl stays NULL terminated on write ... " -set_orig -perl -e 'print "A" x ('"${MAXLEN}"'-1), "B";' | \ - dd of="${TARGET}" bs="${MAXLEN}" 2>/dev/null -if grep -q B "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi - -echo -n "Checking sysctl stays NULL terminated on overwrite ... " -set_orig -perl -e 'print "A" x ('"${MAXLEN}"'-1), "BB";' | \ - dd of="${TARGET}" bs=$(( $MAXLEN + 1 )) 2>/dev/null -if grep -q B "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi - -exit_test diff --git a/tools/testing/selftests/sysctl/sysctl.sh b/tools/testing/selftests/sysctl/sysctl.sh new file mode 100644 index 000000000000..ec232c3cfcaa --- /dev/null +++ b/tools/testing/selftests/sysctl/sysctl.sh @@ -0,0 +1,774 @@ +#!/bin/bash +# Copyright (C) 2017 Luis R. Rodriguez <mcgrof@kernel.org> +# +# This program is free software; you can redistribute it and/or modify it +# under the terms of the GNU General Public License as published by the Free +# Software Foundation; either version 2 of the License, or at your option any +# later version; or, when distributed separately from the Linux kernel or +# when incorporated into other software packages, subject to the following +# license: +# +# This program is free software; you can redistribute it and/or modify it +# under the terms of copyleft-next (version 0.3.1 or later) as published +# at http://copyleft-next.org/. + +# This performs a series tests against the proc sysctl interface. + +TEST_NAME="sysctl" +TEST_DRIVER="test_${TEST_NAME}" +TEST_DIR=$(dirname $0) +TEST_FILE=$(mktemp) + +# This represents +# +# TEST_ID:TEST_COUNT:ENABLED +# +# TEST_ID: is the test id number +# TEST_COUNT: number of times we should run the test +# ENABLED: 1 if enabled, 0 otherwise +# +# Once these are enabled please leave them as-is. Write your own test, +# we have tons of space. +ALL_TESTS="0001:1:1" +ALL_TESTS="$ALL_TESTS 0002:1:1" +ALL_TESTS="$ALL_TESTS 0003:1:1" +ALL_TESTS="$ALL_TESTS 0004:1:1" +ALL_TESTS="$ALL_TESTS 0005:3:1" + +test_modprobe() +{ + if [ ! -d $DIR ]; then + echo "$0: $DIR not present" >&2 + echo "You must have the following enabled in your kernel:" >&2 + cat $TEST_DIR/config >&2 + exit 1 + fi +} + +function allow_user_defaults() +{ + if [ -z $DIR ]; then + DIR="/sys/module/test_sysctl/" + fi + if [ -z $DEFAULT_NUM_TESTS ]; then + DEFAULT_NUM_TESTS=50 + fi + if [ -z $SYSCTL ]; then + SYSCTL="/proc/sys/debug/test_sysctl" + fi + if [ -z $PROD_SYSCTL ]; then + PROD_SYSCTL="/proc/sys" + fi + if [ -z $WRITES_STRICT ]; then + WRITES_STRICT="${PROD_SYSCTL}/kernel/sysctl_writes_strict" + fi +} + +function check_production_sysctl_writes_strict() +{ + echo -n "Checking production write strict setting ... " + if [ ! -e ${WRITES_STRICT} ]; then + echo "FAIL, but skip in case of old kernel" >&2 + else + old_strict=$(cat ${WRITES_STRICT}) + if [ "$old_strict" = "1" ]; then + echo "ok" + else + echo "FAIL, strict value is 0 but force to 1 to continue" >&2 + echo "1" > ${WRITES_STRICT} + fi + fi + + if [ -z $PAGE_SIZE ]; then + PAGE_SIZE=$(getconf PAGESIZE) + fi + if [ -z $MAX_DIGITS ]; then + MAX_DIGITS=$(($PAGE_SIZE/8)) + fi + if [ -z $INT_MAX ]; then + INT_MAX=$(getconf INT_MAX) + fi + if [ -z $UINT_MAX ]; then + UINT_MAX=$(getconf UINT_MAX) + fi +} + +test_reqs() +{ + uid=$(id -u) + if [ $uid -ne 0 ]; then + echo $msg must be run as root >&2 + exit 0 + fi + + if ! which perl 2> /dev/null > /dev/null; then + echo "$0: You need perl installed" + exit 1 + fi + if ! which getconf 2> /dev/null > /dev/null; then + echo "$0: You need getconf installed" + exit 1 + fi + if ! which diff 2> /dev/null > /dev/null; then + echo "$0: You need diff installed" + exit 1 + fi +} + +function load_req_mod() +{ + trap "test_modprobe" EXIT + + if [ ! -d $DIR ]; then + modprobe $TEST_DRIVER + if [ $? -ne 0 ]; then + exit + fi + fi +} + +reset_vals() +{ + VAL="" + TRIGGER=$(basename ${TARGET}) + case "$TRIGGER" in + int_0001) + VAL="60" + ;; + int_0002) + VAL="1" + ;; + uint_0001) + VAL="314" + ;; + string_0001) + VAL="(none)" + ;; + *) + ;; + esac + echo -n $VAL > $TARGET +} + +set_orig() +{ + if [ ! -z $TARGET ]; then + echo "${ORIG}" > "${TARGET}" + fi +} + +set_test() +{ + echo "${TEST_STR}" > "${TARGET}" +} + +verify() +{ + local seen + seen=$(cat "$1") + if [ "${seen}" != "${TEST_STR}" ]; then + return 1 + fi + return 0 +} + +verify_diff_w() +{ + echo "$TEST_STR" | diff -q -w -u - $1 + return $? +} + +test_rc() +{ + if [[ $rc != 0 ]]; then + echo "Failed test, return value: $rc" >&2 + exit $rc + fi +} + +test_finish() +{ + set_orig + rm -f "${TEST_FILE}" + + if [ ! -z ${old_strict} ]; then + echo ${old_strict} > ${WRITES_STRICT} + fi + exit $rc +} + +run_numerictests() +{ + echo "== Testing sysctl behavior against ${TARGET} ==" + + rc=0 + + echo -n "Writing test file ... " + echo "${TEST_STR}" > "${TEST_FILE}" + if ! verify "${TEST_FILE}"; then + echo "FAIL" >&2 + exit 1 + else + echo "ok" + fi + + echo -n "Checking sysctl is not set to test value ... " + if verify "${TARGET}"; then + echo "FAIL" >&2 + exit 1 + else + echo "ok" + fi + + echo -n "Writing sysctl from shell ... " + set_test + if ! verify "${TARGET}"; then + echo "FAIL" >&2 + exit 1 + else + echo "ok" + fi + + echo -n "Resetting sysctl to original value ... " + set_orig + if verify "${TARGET}"; then + echo "FAIL" >&2 + exit 1 + else + echo "ok" + fi + + # Now that we've validated the sanity of "set_test" and "set_orig", + # we can use those functions to set starting states before running + # specific behavioral tests. + + echo -n "Writing entire sysctl in single write ... " + set_orig + dd if="${TEST_FILE}" of="${TARGET}" bs=4096 2>/dev/null + if ! verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + + echo -n "Writing middle of sysctl after synchronized seek ... " + set_test + dd if="${TEST_FILE}" of="${TARGET}" bs=1 seek=1 skip=1 2>/dev/null + if ! verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + + echo -n "Writing beyond end of sysctl ... " + set_orig + dd if="${TEST_FILE}" of="${TARGET}" bs=20 seek=2 2>/dev/null + if verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + + echo -n "Writing sysctl with multiple long writes ... " + set_orig + (perl -e 'print "A" x 50;'; echo "${TEST_STR}") | \ + dd of="${TARGET}" bs=50 2>/dev/null + if verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc +} + +# Your test must accept digits 3 and 4 to use this +run_limit_digit() +{ + echo -n "Checking ignoring spaces up to PAGE_SIZE works on write ..." + reset_vals + + LIMIT=$((MAX_DIGITS -1)) + TEST_STR="3" + (perl -e 'print " " x '$LIMIT';'; echo "${TEST_STR}") | \ + dd of="${TARGET}" 2>/dev/null + + if ! verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc + + echo -n "Checking passing PAGE_SIZE of spaces fails on write ..." + reset_vals + + LIMIT=$((MAX_DIGITS)) + TEST_STR="4" + (perl -e 'print " " x '$LIMIT';'; echo "${TEST_STR}") | \ + dd of="${TARGET}" 2>/dev/null + + if verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc +} + +# You are using an int +run_limit_digit_int() +{ + echo -n "Testing INT_MAX works ..." + reset_vals + TEST_STR="$INT_MAX" + echo -n $TEST_STR > $TARGET + + if ! verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc + + echo -n "Testing INT_MAX + 1 will fail as expected..." + reset_vals + let TEST_STR=$INT_MAX+1 + echo -n $TEST_STR > $TARGET 2> /dev/null + + if verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc + + echo -n "Testing negative values will work as expected..." + reset_vals + TEST_STR="-3" + echo -n $TEST_STR > $TARGET 2> /dev/null + if ! verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc +} + +# You used an int array +run_limit_digit_int_array() +{ + echo -n "Testing array works as expected ... " + TEST_STR="4 3 2 1" + echo -n $TEST_STR > $TARGET + + if ! verify_diff_w "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc + + echo -n "Testing skipping trailing array elements works ... " + # Do not reset_vals, carry on the values from the last test. + # If we only echo in two digits the last two are left intact + TEST_STR="100 101" + echo -n $TEST_STR > $TARGET + # After we echo in, to help diff we need to set on TEST_STR what + # we expect the result to be. + TEST_STR="100 101 2 1" + + if ! verify_diff_w "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc + + echo -n "Testing PAGE_SIZE limit on array works ... " + # Do not reset_vals, carry on the values from the last test. + # Even if you use an int array, you are still restricted to + # MAX_DIGITS, this is a known limitation. Test limit works. + LIMIT=$((MAX_DIGITS -1)) + TEST_STR="9" + (perl -e 'print " " x '$LIMIT';'; echo "${TEST_STR}") | \ + dd of="${TARGET}" 2>/dev/null + + TEST_STR="9 101 2 1" + if ! verify_diff_w "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc + + echo -n "Testing exceeding PAGE_SIZE limit fails as expected ... " + # Do not reset_vals, carry on the values from the last test. + # Now go over limit. + LIMIT=$((MAX_DIGITS)) + TEST_STR="7" + (perl -e 'print " " x '$LIMIT';'; echo "${TEST_STR}") | \ + dd of="${TARGET}" 2>/dev/null + + TEST_STR="7 101 2 1" + if verify_diff_w "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc +} + +# You are using an unsigned int +run_limit_digit_uint() +{ + echo -n "Testing UINT_MAX works ..." + reset_vals + TEST_STR="$UINT_MAX" + echo -n $TEST_STR > $TARGET + + if ! verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc + + echo -n "Testing UINT_MAX + 1 will fail as expected..." + reset_vals + TEST_STR=$(($UINT_MAX+1)) + echo -n $TEST_STR > $TARGET 2> /dev/null + + if verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc + + echo -n "Testing negative values will not work as expected ..." + reset_vals + TEST_STR="-3" + echo -n $TEST_STR > $TARGET 2> /dev/null + + if verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc +} + +run_stringtests() +{ + echo -n "Writing entire sysctl in short writes ... " + set_orig + dd if="${TEST_FILE}" of="${TARGET}" bs=1 2>/dev/null + if ! verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + + echo -n "Writing middle of sysctl after unsynchronized seek ... " + set_test + dd if="${TEST_FILE}" of="${TARGET}" bs=1 seek=1 2>/dev/null + if verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + + echo -n "Checking sysctl maxlen is at least $MAXLEN ... " + set_orig + perl -e 'print "A" x ('"${MAXLEN}"'-2), "B";' | \ + dd of="${TARGET}" bs="${MAXLEN}" 2>/dev/null + if ! grep -q B "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + + echo -n "Checking sysctl keeps original string on overflow append ... " + set_orig + perl -e 'print "A" x ('"${MAXLEN}"'-1), "B";' | \ + dd of="${TARGET}" bs=$(( MAXLEN - 1 )) 2>/dev/null + if grep -q B "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + + echo -n "Checking sysctl stays NULL terminated on write ... " + set_orig + perl -e 'print "A" x ('"${MAXLEN}"'-1), "B";' | \ + dd of="${TARGET}" bs="${MAXLEN}" 2>/dev/null + if grep -q B "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + + echo -n "Checking sysctl stays NULL terminated on overwrite ... " + set_orig + perl -e 'print "A" x ('"${MAXLEN}"'-1), "BB";' | \ + dd of="${TARGET}" bs=$(( $MAXLEN + 1 )) 2>/dev/null + if grep -q B "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + + test_rc +} + +sysctl_test_0001() +{ + TARGET="${SYSCTL}/int_0001" + reset_vals + ORIG=$(cat "${TARGET}") + TEST_STR=$(( $ORIG + 1 )) + + run_numerictests + run_limit_digit +} + +sysctl_test_0002() +{ + TARGET="${SYSCTL}/string_0001" + reset_vals + ORIG=$(cat "${TARGET}") + TEST_STR="Testing sysctl" + # Only string sysctls support seeking/appending. + MAXLEN=65 + + run_numerictests + run_stringtests +} + +sysctl_test_0003() +{ + TARGET="${SYSCTL}/int_0002" + reset_vals + ORIG=$(cat "${TARGET}") + TEST_STR=$(( $ORIG + 1 )) + + run_numerictests + run_limit_digit + run_limit_digit_int +} + +sysctl_test_0004() +{ + TARGET="${SYSCTL}/uint_0001" + reset_vals + ORIG=$(cat "${TARGET}") + TEST_STR=$(( $ORIG + 1 )) + + run_numerictests + run_limit_digit + run_limit_digit_uint +} + +sysctl_test_0005() +{ + TARGET="${SYSCTL}/int_0003" + reset_vals + ORIG=$(cat "${TARGET}") + + run_limit_digit_int_array +} + +list_tests() +{ + echo "Test ID list:" + echo + echo "TEST_ID x NUM_TEST" + echo "TEST_ID: Test ID" + echo "NUM_TESTS: Number of recommended times to run the test" + echo + echo "0001 x $(get_test_count 0001) - tests proc_dointvec_minmax()" + echo "0002 x $(get_test_count 0002) - tests proc_dostring()" + echo "0003 x $(get_test_count 0003) - tests proc_dointvec()" + echo "0004 x $(get_test_count 0004) - tests proc_douintvec()" + echo "0005 x $(get_test_count 0005) - tests proc_douintvec() array" +} + +test_reqs + +usage() +{ + NUM_TESTS=$(grep -o ' ' <<<"$ALL_TESTS" | grep -c .) + let NUM_TESTS=$NUM_TESTS+1 + MAX_TEST=$(printf "%04d\n" $NUM_TESTS) + echo "Usage: $0 [ -t <4-number-digit> ] | [ -w <4-number-digit> ] |" + echo " [ -s <4-number-digit> ] | [ -c <4-number-digit> <test- count>" + echo " [ all ] [ -h | --help ] [ -l ]" + echo "" + echo "Valid tests: 0001-$MAX_TEST" + echo "" + echo " all Runs all tests (default)" + echo " -t Run test ID the number amount of times is recommended" + echo " -w Watch test ID run until it runs into an error" + echo " -c Run test ID once" + echo " -s Run test ID x test-count number of times" + echo " -l List all test ID list" + echo " -h|--help Help" + echo + echo "If an error every occurs execution will immediately terminate." + echo "If you are adding a new test try using -w <test-ID> first to" + echo "make sure the test passes a series of tests." + echo + echo Example uses: + echo + echo "$TEST_NAME.sh -- executes all tests" + echo "$TEST_NAME.sh -t 0002 -- Executes test ID 0002 number of times is recomended" + echo "$TEST_NAME.sh -w 0002 -- Watch test ID 0002 run until an error occurs" + echo "$TEST_NAME.sh -s 0002 -- Run test ID 0002 once" + echo "$TEST_NAME.sh -c 0002 3 -- Run test ID 0002 three times" + echo + list_tests + exit 1 +} + +function test_num() +{ + re='^[0-9]+$' + if ! [[ $1 =~ $re ]]; then + usage + fi +} + +function get_test_count() +{ + test_num $1 + TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$1'}') + LAST_TWO=${TEST_DATA#*:*} + echo ${LAST_TWO%:*} +} + +function get_test_enabled() +{ + test_num $1 + TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$1'}') + echo ${TEST_DATA#*:*:} +} + +function run_all_tests() +{ + for i in $ALL_TESTS ; do + TEST_ID=${i%:*:*} + ENABLED=$(get_test_enabled $TEST_ID) + TEST_COUNT=$(get_test_count $TEST_ID) + if [[ $ENABLED -eq "1" ]]; then + test_case $TEST_ID $TEST_COUNT + fi + done +} + +function watch_log() +{ + if [ $# -ne 3 ]; then + clear + fi + date + echo "Running test: $2 - run #$1" +} + +function watch_case() +{ + i=0 + while [ 1 ]; do + + if [ $# -eq 1 ]; then + test_num $1 + watch_log $i ${TEST_NAME}_test_$1 + ${TEST_NAME}_test_$1 + else + watch_log $i all + run_all_tests + fi + let i=$i+1 + done +} + +function test_case() +{ + NUM_TESTS=$DEFAULT_NUM_TESTS + if [ $# -eq 2 ]; then + NUM_TESTS=$2 + fi + + i=0 + while [ $i -lt $NUM_TESTS ]; do + test_num $1 + watch_log $i ${TEST_NAME}_test_$1 noclear + RUN_TEST=${TEST_NAME}_test_$1 + $RUN_TEST + let i=$i+1 + done +} + +function parse_args() +{ + if [ $# -eq 0 ]; then + run_all_tests + else + if [[ "$1" = "all" ]]; then + run_all_tests + elif [[ "$1" = "-w" ]]; then + shift + watch_case $@ + elif [[ "$1" = "-t" ]]; then + shift + test_num $1 + test_case $1 $(get_test_count $1) + elif [[ "$1" = "-c" ]]; then + shift + test_num $1 + test_num $2 + test_case $1 $2 + elif [[ "$1" = "-s" ]]; then + shift + test_case $1 1 + elif [[ "$1" = "-l" ]]; then + list_tests + elif [[ "$1" = "-h" || "$1" = "--help" ]]; then + usage + else + usage + fi + fi +} + +test_reqs +allow_user_defaults +check_production_sysctl_writes_strict +load_req_mod + +trap "test_finish" EXIT + +parse_args $@ + +exit 0 |