From 63259457a2eea54cc3b3a284b4bc7da52398a19a Mon Sep 17 00:00:00 2001 From: Gao Feng Date: Mon, 8 May 2017 15:54:58 -0700 Subject: proc/sysctl: fix the int overflow for jiffies conversion do_proc_dointvec_jiffies_conv() uses LONG_MAX/HZ as the max value to avoid overflow. But actually the *valp is int type, so it still causes overflow. For example, echo 2147483647 > ./sys/net/ipv4/tcp_keepalive_time Then, cat ./sys/net/ipv4/tcp_keepalive_time The output is "-1", it is not expected. Now use INT_MAX/HZ as the max value instead LONG_MAX/HZ to fix it. Link: http://lkml.kernel.org/r/1490109532-9228-1-git-send-email-fgao@ikuai8.com Signed-off-by: Gao Feng Cc: Arnaldo Carvalho de Melo Cc: Ingo Molnar Cc: Alexey Dobriyan Cc: Eric Dumazet Cc: Josh Poimboeuf Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 21343d110296..4dfba1a76cc3 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2576,7 +2576,7 @@ static int do_proc_dointvec_jiffies_conv(bool *negp, unsigned long *lvalp, int write, void *data) { if (write) { - if (*lvalp > LONG_MAX / HZ) + if (*lvalp > INT_MAX / HZ) return 1; *valp = *negp ? -(*lvalp*HZ) : (*lvalp*HZ); } else { -- cgit v1.2.3 From 780cbcf28781511d2cb235c375127265209796a8 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Mon, 8 May 2017 15:55:11 -0700 Subject: kernel/hung_task.c: defer showing held locks When I was running my testcase which may block hundreds of threads on fs locks, I got lockup due to output from debug_show_all_locks() added by commit b2d4c2edb2e4 ("locking/hung_task: Show all locks"). For example, if 1000 threads were blocked in TASK_UNINTERRUPTIBLE state and 500 out of 1000 threads hold some lock, debug_show_all_locks() from for_each_process_thread() loop will report locks held by 500 threads for 1000 times. This is a too much noise. In order to make sure rcu_lock_break() is called frequently, we should avoid calling debug_show_all_locks() from for_each_process_thread() loop because debug_show_all_locks() effectively calls for_each_process_thread() loop. Let's defer calling debug_show_all_locks() till before panic() or leaving for_each_process_thread() loop. Link: http://lkml.kernel.org/r/1489296834-60436-1-git-send-email-penguin-kernel@I-love.SAKURA.ne.jp Signed-off-by: Tetsuo Handa Reviewed-by: Vegard Nossum Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/hung_task.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/hung_task.c b/kernel/hung_task.c index f0f8e2a8496f..751593ed7c0b 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -43,6 +43,7 @@ unsigned long __read_mostly sysctl_hung_task_timeout_secs = CONFIG_DEFAULT_HUNG_ int __read_mostly sysctl_hung_task_warnings = 10; static int __read_mostly did_panic; +static bool hung_task_show_lock; static struct task_struct *watchdog_task; @@ -120,12 +121,14 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) pr_err("\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\"" " disables this message.\n"); sched_show_task(t); - debug_show_all_locks(); + hung_task_show_lock = true; } touch_nmi_watchdog(); if (sysctl_hung_task_panic) { + if (hung_task_show_lock) + debug_show_all_locks(); trigger_all_cpu_backtrace(); panic("hung_task: blocked tasks"); } @@ -172,6 +175,7 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout) if (test_taint(TAINT_DIE) || did_panic) return; + hung_task_show_lock = false; rcu_read_lock(); for_each_process_thread(g, t) { if (!max_count--) @@ -187,6 +191,8 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout) } unlock: rcu_read_unlock(); + if (hung_task_show_lock) + debug_show_all_locks(); } static long hung_timeout_jiffies(unsigned long last_checked, -- cgit v1.2.3 From 19659c59af52df22d1b85208a2c37b2d46290541 Mon Sep 17 00:00:00 2001 From: Hoeun Ryu Date: Mon, 8 May 2017 15:56:11 -0700 Subject: fork: free vmapped stacks in cache when cpus are offline Using virtually mapped stack, kernel stacks are allocated via vmalloc. In the current implementation, two stacks per cpu can be cached when tasks are freed and the cached stacks are used again in task duplications. But the cached stacks may remain unfreed even when cpu are offline. By adding a cpu hotplug callback to free the cached stacks when a cpu goes offline, the pages of the cached stacks are not wasted. Link: http://lkml.kernel.org/r/1487076043-17802-1-git-send-email-hoeun.ryu@gmail.com Signed-off-by: Hoeun Ryu Reviewed-by: Thomas Gleixner Acked-by: Michal Hocko Cc: Ingo Molnar Cc: Andy Lutomirski Cc: Kees Cook Cc: "Eric W. Biederman" Cc: Oleg Nesterov Cc: Mateusz Guzik Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index dd5a371c392a..55e325f4b457 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -179,6 +179,24 @@ void __weak arch_release_thread_stack(unsigned long *stack) */ #define NR_CACHED_STACKS 2 static DEFINE_PER_CPU(struct vm_struct *, cached_stacks[NR_CACHED_STACKS]); + +static int free_vm_stack_cache(unsigned int cpu) +{ + struct vm_struct **cached_vm_stacks = per_cpu_ptr(cached_stacks, cpu); + int i; + + for (i = 0; i < NR_CACHED_STACKS; i++) { + struct vm_struct *vm_stack = cached_vm_stacks[i]; + + if (!vm_stack) + continue; + + vfree(vm_stack->addr); + cached_vm_stacks[i] = NULL; + } + + return 0; +} #endif static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) @@ -467,6 +485,11 @@ void __init fork_init(void) for (i = 0; i < UCOUNT_COUNTS; i++) { init_user_ns.ucount_max[i] = max_threads/2; } + +#ifdef CONFIG_VMAP_STACK + cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache", + NULL, free_vm_stack_cache); +#endif } int __weak arch_dup_task_struct(struct task_struct *dst, -- cgit v1.2.3 From 692f66f26a4c19d73249736aa973c13a1521b387 Mon Sep 17 00:00:00 2001 From: Hari Bathini Date: Mon, 8 May 2017 15:56:18 -0700 Subject: crash: move crashkernel parsing and vmcore related code under CONFIG_CRASH_CORE Patch series "kexec/fadump: remove dependency with CONFIG_KEXEC and reuse crashkernel parameter for fadump", v4. Traditionally, kdump is used to save vmcore in case of a crash. Some architectures like powerpc can save vmcore using architecture specific support instead of kexec/kdump mechanism. Such architecture specific support also needs to reserve memory, to be used by dump capture kernel. crashkernel parameter can be a reused, for memory reservation, by such architecture specific infrastructure. This patchset removes dependency with CONFIG_KEXEC for crashkernel parameter and vmcoreinfo related code as it can be reused without kexec support. Also, crashkernel parameter is reused instead of fadump_reserve_mem to reserve memory for fadump. The first patch moves crashkernel parameter parsing and vmcoreinfo related code under CONFIG_CRASH_CORE instead of CONFIG_KEXEC_CORE. The second patch reuses the definitions of append_elf_note() & final_note() functions under CONFIG_CRASH_CORE in IA64 arch code. The third patch removes dependency on CONFIG_KEXEC for firmware-assisted dump (fadump) in powerpc. The next patch reuses crashkernel parameter for reserving memory for fadump, instead of the fadump_reserve_mem parameter. This has the advantage of using all syntaxes crashkernel parameter supports, for fadump as well. The last patch updates fadump kernel documentation about use of crashkernel parameter. This patch (of 5): Traditionally, kdump is used to save vmcore in case of a crash. Some architectures like powerpc can save vmcore using architecture specific support instead of kexec/kdump mechanism. Such architecture specific support also needs to reserve memory, to be used by dump capture kernel. crashkernel parameter can be a reused, for memory reservation, by such architecture specific infrastructure. But currently, code related to vmcoreinfo and parsing of crashkernel parameter is built under CONFIG_KEXEC_CORE. This patch introduces CONFIG_CRASH_CORE and moves the above mentioned code under this config, allowing code reuse without dependency on CONFIG_KEXEC. There is no functional change with this patch. Link: http://lkml.kernel.org/r/149035338104.6881.4550894432615189948.stgit@hbathini.in.ibm.com Signed-off-by: Hari Bathini Acked-by: Dave Young Cc: Fenghua Yu Cc: Tony Luck Cc: Eric Biederman Cc: Mahesh Salgaonkar Cc: Vivek Goyal Cc: Michael Ellerman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/Kconfig | 4 + include/linux/crash_core.h | 65 +++++++ include/linux/kexec.h | 57 +----- include/linux/printk.h | 4 +- kernel/Makefile | 1 + kernel/crash_core.c | 445 +++++++++++++++++++++++++++++++++++++++++++++ kernel/kexec_core.c | 403 ---------------------------------------- kernel/ksysfs.c | 8 +- kernel/printk/printk.c | 6 +- 9 files changed, 531 insertions(+), 462 deletions(-) create mode 100644 include/linux/crash_core.h create mode 100644 kernel/crash_core.c (limited to 'kernel') diff --git a/arch/Kconfig b/arch/Kconfig index 640999412d11..dcbd462b68b1 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -2,7 +2,11 @@ # General architecture dependent options # +config CRASH_CORE + bool + config KEXEC_CORE + select CRASH_CORE bool config HAVE_IMA_KEXEC diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h new file mode 100644 index 000000000000..18d0f946fda3 --- /dev/null +++ b/include/linux/crash_core.h @@ -0,0 +1,65 @@ +#ifndef LINUX_CRASH_CORE_H +#define LINUX_CRASH_CORE_H + +#include +#include +#include + +#define CRASH_CORE_NOTE_NAME "CORE" +#define CRASH_CORE_NOTE_HEAD_BYTES ALIGN(sizeof(struct elf_note), 4) +#define CRASH_CORE_NOTE_NAME_BYTES ALIGN(sizeof(CRASH_CORE_NOTE_NAME), 4) +#define CRASH_CORE_NOTE_DESC_BYTES ALIGN(sizeof(struct elf_prstatus), 4) + +#define CRASH_CORE_NOTE_BYTES ((CRASH_CORE_NOTE_HEAD_BYTES * 2) + \ + CRASH_CORE_NOTE_NAME_BYTES + \ + CRASH_CORE_NOTE_DESC_BYTES) + +#define VMCOREINFO_BYTES (4096) +#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) + \ + VMCOREINFO_NOTE_NAME_BYTES + \ + VMCOREINFO_BYTES) + +typedef u32 note_buf_t[CRASH_CORE_NOTE_BYTES/4]; + +void crash_save_vmcoreinfo(void); +void arch_crash_save_vmcoreinfo(void); +__printf(1, 2) +void vmcoreinfo_append_str(const char *fmt, ...); +phys_addr_t paddr_vmcoreinfo_note(void); + +#define VMCOREINFO_OSRELEASE(value) \ + vmcoreinfo_append_str("OSRELEASE=%s\n", value) +#define VMCOREINFO_PAGESIZE(value) \ + vmcoreinfo_append_str("PAGESIZE=%ld\n", value) +#define VMCOREINFO_SYMBOL(name) \ + vmcoreinfo_append_str("SYMBOL(%s)=%lx\n", #name, (unsigned long)&name) +#define VMCOREINFO_SIZE(name) \ + vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \ + (unsigned long)sizeof(name)) +#define VMCOREINFO_STRUCT_SIZE(name) \ + vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \ + (unsigned long)sizeof(struct name)) +#define VMCOREINFO_OFFSET(name, field) \ + vmcoreinfo_append_str("OFFSET(%s.%s)=%lu\n", #name, #field, \ + (unsigned long)offsetof(struct name, field)) +#define VMCOREINFO_LENGTH(name, value) \ + vmcoreinfo_append_str("LENGTH(%s)=%lu\n", #name, (unsigned long)value) +#define VMCOREINFO_NUMBER(name) \ + vmcoreinfo_append_str("NUMBER(%s)=%ld\n", #name, (long)name) +#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; + +int __init parse_crashkernel(char *cmdline, unsigned long long system_ram, + unsigned long long *crash_size, unsigned long long *crash_base); +int parse_crashkernel_high(char *cmdline, unsigned long long system_ram, + unsigned long long *crash_size, unsigned long long *crash_base); +int parse_crashkernel_low(char *cmdline, unsigned long long system_ram, + unsigned long long *crash_size, unsigned long long *crash_base); + +#endif /* LINUX_CRASH_CORE_H */ diff --git a/include/linux/kexec.h b/include/linux/kexec.h index d419d0e51fe5..c9481ebcbc0c 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -14,17 +14,15 @@ #if !defined(__ASSEMBLY__) +#include #include #include #ifdef CONFIG_KEXEC_CORE #include -#include #include #include -#include -#include #include #include @@ -62,19 +60,15 @@ #define KEXEC_CRASH_MEM_ALIGN PAGE_SIZE #endif -#define KEXEC_NOTE_HEAD_BYTES ALIGN(sizeof(struct elf_note), 4) -#define KEXEC_CORE_NOTE_NAME "CORE" -#define KEXEC_CORE_NOTE_NAME_BYTES ALIGN(sizeof(KEXEC_CORE_NOTE_NAME), 4) -#define KEXEC_CORE_NOTE_DESC_BYTES ALIGN(sizeof(struct elf_prstatus), 4) +#define KEXEC_CORE_NOTE_NAME CRASH_CORE_NOTE_NAME + /* * The per-cpu notes area is a list of notes terminated by a "NULL" * note header. For kdump, the code in vmcore.c runs in the context * of the second kernel to combine them into one note. */ #ifndef KEXEC_NOTE_BYTES -#define KEXEC_NOTE_BYTES ( (KEXEC_NOTE_HEAD_BYTES * 2) + \ - KEXEC_CORE_NOTE_NAME_BYTES + \ - KEXEC_CORE_NOTE_DESC_BYTES ) +#define KEXEC_NOTE_BYTES CRASH_CORE_NOTE_BYTES #endif /* @@ -256,33 +250,6 @@ 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); -void crash_save_vmcoreinfo(void); -void arch_crash_save_vmcoreinfo(void); -__printf(1, 2) -void vmcoreinfo_append_str(const char *fmt, ...); -phys_addr_t paddr_vmcoreinfo_note(void); - -#define VMCOREINFO_OSRELEASE(value) \ - vmcoreinfo_append_str("OSRELEASE=%s\n", value) -#define VMCOREINFO_PAGESIZE(value) \ - vmcoreinfo_append_str("PAGESIZE=%ld\n", value) -#define VMCOREINFO_SYMBOL(name) \ - vmcoreinfo_append_str("SYMBOL(%s)=%lx\n", #name, (unsigned long)&name) -#define VMCOREINFO_SIZE(name) \ - vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \ - (unsigned long)sizeof(name)) -#define VMCOREINFO_STRUCT_SIZE(name) \ - vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \ - (unsigned long)sizeof(struct name)) -#define VMCOREINFO_OFFSET(name, field) \ - vmcoreinfo_append_str("OFFSET(%s.%s)=%lu\n", #name, #field, \ - (unsigned long)offsetof(struct name, field)) -#define VMCOREINFO_LENGTH(name, value) \ - vmcoreinfo_append_str("LENGTH(%s)=%lu\n", #name, (unsigned long)value) -#define VMCOREINFO_NUMBER(name) \ - vmcoreinfo_append_str("NUMBER(%s)=%ld\n", #name, (long)name) -#define VMCOREINFO_CONFIG(name) \ - vmcoreinfo_append_str("CONFIG_%s=y\n", #name) extern struct kimage *kexec_image; extern struct kimage *kexec_crash_image; @@ -303,31 +270,15 @@ extern int kexec_load_disabled; #define KEXEC_FILE_FLAGS (KEXEC_FILE_UNLOAD | KEXEC_FILE_ON_CRASH | \ KEXEC_FILE_NO_INITRAMFS) -#define VMCOREINFO_BYTES (4096) -#define VMCOREINFO_NOTE_NAME "VMCOREINFO" -#define VMCOREINFO_NOTE_NAME_BYTES ALIGN(sizeof(VMCOREINFO_NOTE_NAME), 4) -#define VMCOREINFO_NOTE_SIZE (KEXEC_NOTE_HEAD_BYTES*2 + VMCOREINFO_BYTES \ - + VMCOREINFO_NOTE_NAME_BYTES) - /* Location of a reserved region to hold the crash kernel. */ extern struct resource crashk_res; extern struct resource crashk_low_res; -typedef u32 note_buf_t[KEXEC_NOTE_BYTES/4]; extern note_buf_t __percpu *crash_notes; -extern u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4]; -extern size_t vmcoreinfo_size; -extern size_t vmcoreinfo_max_size; /* flag to track if kexec reboot is in progress */ extern bool kexec_in_progress; -int __init parse_crashkernel(char *cmdline, unsigned long long system_ram, - unsigned long long *crash_size, unsigned long long *crash_base); -int parse_crashkernel_high(char *cmdline, unsigned long long system_ram, - unsigned long long *crash_size, unsigned long long *crash_base); -int parse_crashkernel_low(char *cmdline, unsigned long long system_ram, - unsigned long long *crash_size, unsigned long long *crash_base); int crash_shrink_memory(unsigned long new_size); size_t crash_get_memory_size(void); void crash_free_reserved_phys_range(unsigned long begin, unsigned long end); diff --git a/include/linux/printk.h b/include/linux/printk.h index 571257e0f53d..e10f27468322 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -198,7 +198,7 @@ extern void wake_up_klogd(void); char *log_buf_addr_get(void); u32 log_buf_len_get(void); -void log_buf_kexec_setup(void); +void log_buf_vmcoreinfo_setup(void); void __init setup_log_buf(int early); __printf(1, 2) void dump_stack_set_arch_desc(const char *fmt, ...); void dump_stack_print_info(const char *log_lvl); @@ -246,7 +246,7 @@ static inline u32 log_buf_len_get(void) return 0; } -static inline void log_buf_kexec_setup(void) +static inline void log_buf_vmcoreinfo_setup(void) { } diff --git a/kernel/Makefile b/kernel/Makefile index b302b4731d16..72aa080f91f0 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -59,6 +59,7 @@ obj-$(CONFIG_MODULES) += module.o obj-$(CONFIG_MODULE_SIG) += module_signing.o obj-$(CONFIG_KALLSYMS) += kallsyms.o obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o +obj-$(CONFIG_CRASH_CORE) += crash_core.o obj-$(CONFIG_KEXEC_CORE) += kexec_core.o obj-$(CONFIG_KEXEC) += kexec.o obj-$(CONFIG_KEXEC_FILE) += kexec_file.o diff --git a/kernel/crash_core.c b/kernel/crash_core.c new file mode 100644 index 000000000000..4261587a34d2 --- /dev/null +++ b/kernel/crash_core.c @@ -0,0 +1,445 @@ +/* + * crash.c - kernel crash support code. + * Copyright (C) 2002-2004 Eric Biederman + * + * This source code is licensed under the GNU General Public License, + * Version 2. See the file COPYING for more details. + */ + +#include +#include +#include + +#include +#include + +/* 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); + +/* + * parsing the "crashkernel" commandline + * + * this code is intended to be called from architecture specific code + */ + + +/* + * This function parses command lines in the format + * + * crashkernel=ramsize-range:size[,...][@offset] + * + * The function returns 0 on success and -EINVAL on failure. + */ +static int __init parse_crashkernel_mem(char *cmdline, + unsigned long long system_ram, + unsigned long long *crash_size, + unsigned long long *crash_base) +{ + char *cur = cmdline, *tmp; + + /* for each entry of the comma-separated list */ + do { + unsigned long long start, end = ULLONG_MAX, size; + + /* get the start of the range */ + start = memparse(cur, &tmp); + if (cur == tmp) { + pr_warn("crashkernel: Memory value expected\n"); + return -EINVAL; + } + cur = tmp; + if (*cur != '-') { + pr_warn("crashkernel: '-' expected\n"); + return -EINVAL; + } + cur++; + + /* if no ':' is here, than we read the end */ + if (*cur != ':') { + end = memparse(cur, &tmp); + if (cur == tmp) { + pr_warn("crashkernel: Memory value expected\n"); + return -EINVAL; + } + cur = tmp; + if (end <= start) { + pr_warn("crashkernel: end <= start\n"); + return -EINVAL; + } + } + + if (*cur != ':') { + pr_warn("crashkernel: ':' expected\n"); + return -EINVAL; + } + cur++; + + size = memparse(cur, &tmp); + if (cur == tmp) { + pr_warn("Memory value expected\n"); + return -EINVAL; + } + cur = tmp; + if (size >= system_ram) { + pr_warn("crashkernel: invalid size\n"); + return -EINVAL; + } + + /* match ? */ + if (system_ram >= start && system_ram < end) { + *crash_size = size; + break; + } + } while (*cur++ == ','); + + if (*crash_size > 0) { + while (*cur && *cur != ' ' && *cur != '@') + cur++; + if (*cur == '@') { + cur++; + *crash_base = memparse(cur, &tmp); + if (cur == tmp) { + pr_warn("Memory value expected after '@'\n"); + return -EINVAL; + } + } + } + + return 0; +} + +/* + * That function parses "simple" (old) crashkernel command lines like + * + * crashkernel=size[@offset] + * + * It returns 0 on success and -EINVAL on failure. + */ +static int __init parse_crashkernel_simple(char *cmdline, + unsigned long long *crash_size, + unsigned long long *crash_base) +{ + char *cur = cmdline; + + *crash_size = memparse(cmdline, &cur); + if (cmdline == cur) { + pr_warn("crashkernel: memory value expected\n"); + return -EINVAL; + } + + if (*cur == '@') + *crash_base = memparse(cur+1, &cur); + else if (*cur != ' ' && *cur != '\0') { + pr_warn("crashkernel: unrecognized char: %c\n", *cur); + return -EINVAL; + } + + return 0; +} + +#define SUFFIX_HIGH 0 +#define SUFFIX_LOW 1 +#define SUFFIX_NULL 2 +static __initdata char *suffix_tbl[] = { + [SUFFIX_HIGH] = ",high", + [SUFFIX_LOW] = ",low", + [SUFFIX_NULL] = NULL, +}; + +/* + * That function parses "suffix" crashkernel command lines like + * + * crashkernel=size,[high|low] + * + * It returns 0 on success and -EINVAL on failure. + */ +static int __init parse_crashkernel_suffix(char *cmdline, + unsigned long long *crash_size, + const char *suffix) +{ + char *cur = cmdline; + + *crash_size = memparse(cmdline, &cur); + if (cmdline == cur) { + pr_warn("crashkernel: memory value expected\n"); + return -EINVAL; + } + + /* check with suffix */ + if (strncmp(cur, suffix, strlen(suffix))) { + pr_warn("crashkernel: unrecognized char: %c\n", *cur); + return -EINVAL; + } + cur += strlen(suffix); + if (*cur != ' ' && *cur != '\0') { + pr_warn("crashkernel: unrecognized char: %c\n", *cur); + return -EINVAL; + } + + return 0; +} + +static __init char *get_last_crashkernel(char *cmdline, + const char *name, + const char *suffix) +{ + char *p = cmdline, *ck_cmdline = NULL; + + /* find crashkernel and use the last one if there are more */ + p = strstr(p, name); + while (p) { + char *end_p = strchr(p, ' '); + char *q; + + if (!end_p) + end_p = p + strlen(p); + + if (!suffix) { + int i; + + /* skip the one with any known suffix */ + for (i = 0; suffix_tbl[i]; i++) { + q = end_p - strlen(suffix_tbl[i]); + if (!strncmp(q, suffix_tbl[i], + strlen(suffix_tbl[i]))) + goto next; + } + ck_cmdline = p; + } else { + q = end_p - strlen(suffix); + if (!strncmp(q, suffix, strlen(suffix))) + ck_cmdline = p; + } +next: + p = strstr(p+1, name); + } + + if (!ck_cmdline) + return NULL; + + return ck_cmdline; +} + +static int __init __parse_crashkernel(char *cmdline, + unsigned long long system_ram, + unsigned long long *crash_size, + unsigned long long *crash_base, + const char *name, + const char *suffix) +{ + char *first_colon, *first_space; + char *ck_cmdline; + + BUG_ON(!crash_size || !crash_base); + *crash_size = 0; + *crash_base = 0; + + ck_cmdline = get_last_crashkernel(cmdline, name, suffix); + + if (!ck_cmdline) + return -EINVAL; + + ck_cmdline += strlen(name); + + if (suffix) + return parse_crashkernel_suffix(ck_cmdline, crash_size, + suffix); + /* + * if the commandline contains a ':', then that's the extended + * syntax -- if not, it must be the classic syntax + */ + first_colon = strchr(ck_cmdline, ':'); + first_space = strchr(ck_cmdline, ' '); + if (first_colon && (!first_space || first_colon < first_space)) + return parse_crashkernel_mem(ck_cmdline, system_ram, + crash_size, crash_base); + + return parse_crashkernel_simple(ck_cmdline, crash_size, crash_base); +} + +/* + * That function is the entry point for command line parsing and should be + * called from the arch-specific code. + */ +int __init parse_crashkernel(char *cmdline, + unsigned long long system_ram, + unsigned long long *crash_size, + unsigned long long *crash_base) +{ + return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base, + "crashkernel=", NULL); +} + +int __init parse_crashkernel_high(char *cmdline, + unsigned long long system_ram, + unsigned long long *crash_size, + unsigned long long *crash_base) +{ + return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base, + "crashkernel=", suffix_tbl[SUFFIX_HIGH]); +} + +int __init parse_crashkernel_low(char *cmdline, + unsigned long long system_ram, + unsigned long long *crash_size, + unsigned long long *crash_base) +{ + return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base, + "crashkernel=", suffix_tbl[SUFFIX_LOW]); +} + +static u32 *append_elf_note(u32 *buf, char *name, unsigned int type, + void *data, size_t data_len) +{ + struct elf_note note; + + note.n_namesz = strlen(name) + 1; + note.n_descsz = data_len; + note.n_type = type; + memcpy(buf, ¬e, sizeof(note)); + buf += (sizeof(note) + 3)/4; + memcpy(buf, name, note.n_namesz); + buf += (note.n_namesz + 3)/4; + memcpy(buf, data, note.n_descsz); + buf += (note.n_descsz + 3)/4; + + return buf; +} + +static void final_note(u32 *buf) +{ + struct elf_note note; + + note.n_namesz = 0; + note.n_descsz = 0; + note.n_type = 0; + memcpy(buf, ¬e, sizeof(note)); +} + +static void update_vmcoreinfo_note(void) +{ + u32 *buf = vmcoreinfo_note; + + if (!vmcoreinfo_size) + return; + buf = append_elf_note(buf, VMCOREINFO_NOTE_NAME, 0, vmcoreinfo_data, + vmcoreinfo_size); + final_note(buf); +} + +void crash_save_vmcoreinfo(void) +{ + vmcoreinfo_append_str("CRASHTIME=%ld\n", get_seconds()); + update_vmcoreinfo_note(); +} + +void vmcoreinfo_append_str(const char *fmt, ...) +{ + va_list args; + char buf[0x50]; + size_t r; + + va_start(args, fmt); + r = vscnprintf(buf, sizeof(buf), fmt, args); + va_end(args); + + r = min(r, vmcoreinfo_max_size - vmcoreinfo_size); + + memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r); + + vmcoreinfo_size += r; +} + +/* + * provide an empty default implementation here -- architecture + * code may override this + */ +void __weak arch_crash_save_vmcoreinfo(void) +{} + +phys_addr_t __weak paddr_vmcoreinfo_note(void) +{ + return __pa_symbol((unsigned long)(char *)&vmcoreinfo_note); +} + +static int __init crash_save_vmcoreinfo_init(void) +{ + VMCOREINFO_OSRELEASE(init_uts_ns.name.release); + VMCOREINFO_PAGESIZE(PAGE_SIZE); + + VMCOREINFO_SYMBOL(init_uts_ns); + VMCOREINFO_SYMBOL(node_online_map); +#ifdef CONFIG_MMU + VMCOREINFO_SYMBOL(swapper_pg_dir); +#endif + VMCOREINFO_SYMBOL(_stext); + VMCOREINFO_SYMBOL(vmap_area_list); + +#ifndef CONFIG_NEED_MULTIPLE_NODES + VMCOREINFO_SYMBOL(mem_map); + VMCOREINFO_SYMBOL(contig_page_data); +#endif +#ifdef CONFIG_SPARSEMEM + VMCOREINFO_SYMBOL(mem_section); + VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS); + VMCOREINFO_STRUCT_SIZE(mem_section); + VMCOREINFO_OFFSET(mem_section, section_mem_map); +#endif + VMCOREINFO_STRUCT_SIZE(page); + VMCOREINFO_STRUCT_SIZE(pglist_data); + VMCOREINFO_STRUCT_SIZE(zone); + VMCOREINFO_STRUCT_SIZE(free_area); + VMCOREINFO_STRUCT_SIZE(list_head); + VMCOREINFO_SIZE(nodemask_t); + VMCOREINFO_OFFSET(page, flags); + VMCOREINFO_OFFSET(page, _refcount); + VMCOREINFO_OFFSET(page, mapping); + VMCOREINFO_OFFSET(page, lru); + VMCOREINFO_OFFSET(page, _mapcount); + VMCOREINFO_OFFSET(page, private); + VMCOREINFO_OFFSET(page, compound_dtor); + VMCOREINFO_OFFSET(page, compound_order); + VMCOREINFO_OFFSET(page, compound_head); + VMCOREINFO_OFFSET(pglist_data, node_zones); + VMCOREINFO_OFFSET(pglist_data, nr_zones); +#ifdef CONFIG_FLAT_NODE_MEM_MAP + VMCOREINFO_OFFSET(pglist_data, node_mem_map); +#endif + VMCOREINFO_OFFSET(pglist_data, node_start_pfn); + VMCOREINFO_OFFSET(pglist_data, node_spanned_pages); + VMCOREINFO_OFFSET(pglist_data, node_id); + VMCOREINFO_OFFSET(zone, free_area); + VMCOREINFO_OFFSET(zone, vm_stat); + VMCOREINFO_OFFSET(zone, spanned_pages); + VMCOREINFO_OFFSET(free_area, free_list); + VMCOREINFO_OFFSET(list_head, next); + VMCOREINFO_OFFSET(list_head, prev); + VMCOREINFO_OFFSET(vmap_area, va_start); + VMCOREINFO_OFFSET(vmap_area, list); + VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER); + log_buf_vmcoreinfo_setup(); + VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES); + VMCOREINFO_NUMBER(NR_FREE_PAGES); + VMCOREINFO_NUMBER(PG_lru); + VMCOREINFO_NUMBER(PG_private); + VMCOREINFO_NUMBER(PG_swapcache); + VMCOREINFO_NUMBER(PG_slab); +#ifdef CONFIG_MEMORY_FAILURE + VMCOREINFO_NUMBER(PG_hwpoison); +#endif + VMCOREINFO_NUMBER(PG_head_mask); + VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE); +#ifdef CONFIG_HUGETLB_PAGE + VMCOREINFO_NUMBER(HUGETLB_PAGE_DTOR); +#endif + + arch_crash_save_vmcoreinfo(); + update_vmcoreinfo_note(); + + return 0; +} + +subsys_initcall(crash_save_vmcoreinfo_init); diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index bfe62d5b3872..9dd722912850 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -51,12 +51,6 @@ DEFINE_MUTEX(kexec_mutex); /* Per cpu memory for storing cpu states in case of system crash. */ note_buf_t __percpu *crash_notes; -/* 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); - /* Flag to indicate we are going to kexec a new kernel */ bool kexec_in_progress = false; @@ -1084,403 +1078,6 @@ static int __init crash_notes_memory_init(void) subsys_initcall(crash_notes_memory_init); -/* - * parsing the "crashkernel" commandline - * - * this code is intended to be called from architecture specific code - */ - - -/* - * This function parses command lines in the format - * - * crashkernel=ramsize-range:size[,...][@offset] - * - * The function returns 0 on success and -EINVAL on failure. - */ -static int __init parse_crashkernel_mem(char *cmdline, - unsigned long long system_ram, - unsigned long long *crash_size, - unsigned long long *crash_base) -{ - char *cur = cmdline, *tmp; - - /* for each entry of the comma-separated list */ - do { - unsigned long long start, end = ULLONG_MAX, size; - - /* get the start of the range */ - start = memparse(cur, &tmp); - if (cur == tmp) { - pr_warn("crashkernel: Memory value expected\n"); - return -EINVAL; - } - cur = tmp; - if (*cur != '-') { - pr_warn("crashkernel: '-' expected\n"); - return -EINVAL; - } - cur++; - - /* if no ':' is here, than we read the end */ - if (*cur != ':') { - end = memparse(cur, &tmp); - if (cur == tmp) { - pr_warn("crashkernel: Memory value expected\n"); - return -EINVAL; - } - cur = tmp; - if (end <= start) { - pr_warn("crashkernel: end <= start\n"); - return -EINVAL; - } - } - - if (*cur != ':') { - pr_warn("crashkernel: ':' expected\n"); - return -EINVAL; - } - cur++; - - size = memparse(cur, &tmp); - if (cur == tmp) { - pr_warn("Memory value expected\n"); - return -EINVAL; - } - cur = tmp; - if (size >= system_ram) { - pr_warn("crashkernel: invalid size\n"); - return -EINVAL; - } - - /* match ? */ - if (system_ram >= start && system_ram < end) { - *crash_size = size; - break; - } - } while (*cur++ == ','); - - if (*crash_size > 0) { - while (*cur && *cur != ' ' && *cur != '@') - cur++; - if (*cur == '@') { - cur++; - *crash_base = memparse(cur, &tmp); - if (cur == tmp) { - pr_warn("Memory value expected after '@'\n"); - return -EINVAL; - } - } - } - - return 0; -} - -/* - * That function parses "simple" (old) crashkernel command lines like - * - * crashkernel=size[@offset] - * - * It returns 0 on success and -EINVAL on failure. - */ -static int __init parse_crashkernel_simple(char *cmdline, - unsigned long long *crash_size, - unsigned long long *crash_base) -{ - char *cur = cmdline; - - *crash_size = memparse(cmdline, &cur); - if (cmdline == cur) { - pr_warn("crashkernel: memory value expected\n"); - return -EINVAL; - } - - if (*cur == '@') - *crash_base = memparse(cur+1, &cur); - else if (*cur != ' ' && *cur != '\0') { - pr_warn("crashkernel: unrecognized char: %c\n", *cur); - return -EINVAL; - } - - return 0; -} - -#define SUFFIX_HIGH 0 -#define SUFFIX_LOW 1 -#define SUFFIX_NULL 2 -static __initdata char *suffix_tbl[] = { - [SUFFIX_HIGH] = ",high", - [SUFFIX_LOW] = ",low", - [SUFFIX_NULL] = NULL, -}; - -/* - * That function parses "suffix" crashkernel command lines like - * - * crashkernel=size,[high|low] - * - * It returns 0 on success and -EINVAL on failure. - */ -static int __init parse_crashkernel_suffix(char *cmdline, - unsigned long long *crash_size, - const char *suffix) -{ - char *cur = cmdline; - - *crash_size = memparse(cmdline, &cur); - if (cmdline == cur) { - pr_warn("crashkernel: memory value expected\n"); - return -EINVAL; - } - - /* check with suffix */ - if (strncmp(cur, suffix, strlen(suffix))) { - pr_warn("crashkernel: unrecognized char: %c\n", *cur); - return -EINVAL; - } - cur += strlen(suffix); - if (*cur != ' ' && *cur != '\0') { - pr_warn("crashkernel: unrecognized char: %c\n", *cur); - return -EINVAL; - } - - return 0; -} - -static __init char *get_last_crashkernel(char *cmdline, - const char *name, - const char *suffix) -{ - char *p = cmdline, *ck_cmdline = NULL; - - /* find crashkernel and use the last one if there are more */ - p = strstr(p, name); - while (p) { - char *end_p = strchr(p, ' '); - char *q; - - if (!end_p) - end_p = p + strlen(p); - - if (!suffix) { - int i; - - /* skip the one with any known suffix */ - for (i = 0; suffix_tbl[i]; i++) { - q = end_p - strlen(suffix_tbl[i]); - if (!strncmp(q, suffix_tbl[i], - strlen(suffix_tbl[i]))) - goto next; - } - ck_cmdline = p; - } else { - q = end_p - strlen(suffix); - if (!strncmp(q, suffix, strlen(suffix))) - ck_cmdline = p; - } -next: - p = strstr(p+1, name); - } - - if (!ck_cmdline) - return NULL; - - return ck_cmdline; -} - -static int __init __parse_crashkernel(char *cmdline, - unsigned long long system_ram, - unsigned long long *crash_size, - unsigned long long *crash_base, - const char *name, - const char *suffix) -{ - char *first_colon, *first_space; - char *ck_cmdline; - - BUG_ON(!crash_size || !crash_base); - *crash_size = 0; - *crash_base = 0; - - ck_cmdline = get_last_crashkernel(cmdline, name, suffix); - - if (!ck_cmdline) - return -EINVAL; - - ck_cmdline += strlen(name); - - if (suffix) - return parse_crashkernel_suffix(ck_cmdline, crash_size, - suffix); - /* - * if the commandline contains a ':', then that's the extended - * syntax -- if not, it must be the classic syntax - */ - first_colon = strchr(ck_cmdline, ':'); - first_space = strchr(ck_cmdline, ' '); - if (first_colon && (!first_space || first_colon < first_space)) - return parse_crashkernel_mem(ck_cmdline, system_ram, - crash_size, crash_base); - - return parse_crashkernel_simple(ck_cmdline, crash_size, crash_base); -} - -/* - * That function is the entry point for command line parsing and should be - * called from the arch-specific code. - */ -int __init parse_crashkernel(char *cmdline, - unsigned long long system_ram, - unsigned long long *crash_size, - unsigned long long *crash_base) -{ - return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base, - "crashkernel=", NULL); -} - -int __init parse_crashkernel_high(char *cmdline, - unsigned long long system_ram, - unsigned long long *crash_size, - unsigned long long *crash_base) -{ - return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base, - "crashkernel=", suffix_tbl[SUFFIX_HIGH]); -} - -int __init parse_crashkernel_low(char *cmdline, - unsigned long long system_ram, - unsigned long long *crash_size, - unsigned long long *crash_base) -{ - return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base, - "crashkernel=", suffix_tbl[SUFFIX_LOW]); -} - -static void update_vmcoreinfo_note(void) -{ - u32 *buf = vmcoreinfo_note; - - if (!vmcoreinfo_size) - return; - buf = append_elf_note(buf, VMCOREINFO_NOTE_NAME, 0, vmcoreinfo_data, - vmcoreinfo_size); - final_note(buf); -} - -void crash_save_vmcoreinfo(void) -{ - vmcoreinfo_append_str("CRASHTIME=%ld\n", get_seconds()); - update_vmcoreinfo_note(); -} - -void vmcoreinfo_append_str(const char *fmt, ...) -{ - va_list args; - char buf[0x50]; - size_t r; - - va_start(args, fmt); - r = vscnprintf(buf, sizeof(buf), fmt, args); - va_end(args); - - r = min(r, vmcoreinfo_max_size - vmcoreinfo_size); - - memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r); - - vmcoreinfo_size += r; -} - -/* - * provide an empty default implementation here -- architecture - * code may override this - */ -void __weak arch_crash_save_vmcoreinfo(void) -{} - -phys_addr_t __weak paddr_vmcoreinfo_note(void) -{ - return __pa_symbol((unsigned long)(char *)&vmcoreinfo_note); -} - -static int __init crash_save_vmcoreinfo_init(void) -{ - VMCOREINFO_OSRELEASE(init_uts_ns.name.release); - VMCOREINFO_PAGESIZE(PAGE_SIZE); - - VMCOREINFO_SYMBOL(init_uts_ns); - VMCOREINFO_SYMBOL(node_online_map); -#ifdef CONFIG_MMU - VMCOREINFO_SYMBOL(swapper_pg_dir); -#endif - VMCOREINFO_SYMBOL(_stext); - VMCOREINFO_SYMBOL(vmap_area_list); - -#ifndef CONFIG_NEED_MULTIPLE_NODES - VMCOREINFO_SYMBOL(mem_map); - VMCOREINFO_SYMBOL(contig_page_data); -#endif -#ifdef CONFIG_SPARSEMEM - VMCOREINFO_SYMBOL(mem_section); - VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS); - VMCOREINFO_STRUCT_SIZE(mem_section); - VMCOREINFO_OFFSET(mem_section, section_mem_map); -#endif - VMCOREINFO_STRUCT_SIZE(page); - VMCOREINFO_STRUCT_SIZE(pglist_data); - VMCOREINFO_STRUCT_SIZE(zone); - VMCOREINFO_STRUCT_SIZE(free_area); - VMCOREINFO_STRUCT_SIZE(list_head); - VMCOREINFO_SIZE(nodemask_t); - VMCOREINFO_OFFSET(page, flags); - VMCOREINFO_OFFSET(page, _refcount); - VMCOREINFO_OFFSET(page, mapping); - VMCOREINFO_OFFSET(page, lru); - VMCOREINFO_OFFSET(page, _mapcount); - VMCOREINFO_OFFSET(page, private); - VMCOREINFO_OFFSET(page, compound_dtor); - VMCOREINFO_OFFSET(page, compound_order); - VMCOREINFO_OFFSET(page, compound_head); - VMCOREINFO_OFFSET(pglist_data, node_zones); - VMCOREINFO_OFFSET(pglist_data, nr_zones); -#ifdef CONFIG_FLAT_NODE_MEM_MAP - VMCOREINFO_OFFSET(pglist_data, node_mem_map); -#endif - VMCOREINFO_OFFSET(pglist_data, node_start_pfn); - VMCOREINFO_OFFSET(pglist_data, node_spanned_pages); - VMCOREINFO_OFFSET(pglist_data, node_id); - VMCOREINFO_OFFSET(zone, free_area); - VMCOREINFO_OFFSET(zone, vm_stat); - VMCOREINFO_OFFSET(zone, spanned_pages); - VMCOREINFO_OFFSET(free_area, free_list); - VMCOREINFO_OFFSET(list_head, next); - VMCOREINFO_OFFSET(list_head, prev); - VMCOREINFO_OFFSET(vmap_area, va_start); - VMCOREINFO_OFFSET(vmap_area, list); - VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER); - log_buf_kexec_setup(); - VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES); - VMCOREINFO_NUMBER(NR_FREE_PAGES); - VMCOREINFO_NUMBER(PG_lru); - VMCOREINFO_NUMBER(PG_private); - VMCOREINFO_NUMBER(PG_swapcache); - VMCOREINFO_NUMBER(PG_slab); -#ifdef CONFIG_MEMORY_FAILURE - VMCOREINFO_NUMBER(PG_hwpoison); -#endif - VMCOREINFO_NUMBER(PG_head_mask); - VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE); -#ifdef CONFIG_HUGETLB_PAGE - VMCOREINFO_NUMBER(HUGETLB_PAGE_DTOR); -#endif - - arch_crash_save_vmcoreinfo(); - update_vmcoreinfo_note(); - - return 0; -} - -subsys_initcall(crash_save_vmcoreinfo_init); - /* * Move into place and start executing a preloaded standalone * executable. If nothing was preloaded return an error. diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index 0999679d6f26..23cd70651238 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -125,6 +125,10 @@ static ssize_t kexec_crash_size_store(struct kobject *kobj, } KERNEL_ATTR_RW(kexec_crash_size); +#endif /* CONFIG_KEXEC_CORE */ + +#ifdef CONFIG_CRASH_CORE + static ssize_t vmcoreinfo_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { @@ -134,7 +138,7 @@ static ssize_t vmcoreinfo_show(struct kobject *kobj, } KERNEL_ATTR_RO(vmcoreinfo); -#endif /* CONFIG_KEXEC_CORE */ +#endif /* CONFIG_CRASH_CORE */ /* whether file capabilities are enabled */ static ssize_t fscaps_show(struct kobject *kobj, @@ -219,6 +223,8 @@ static struct attribute * kernel_attrs[] = { &kexec_loaded_attr.attr, &kexec_crash_loaded_attr.attr, &kexec_crash_size_attr.attr, +#endif +#ifdef CONFIG_CRASH_CORE &vmcoreinfo_attr.attr, #endif #ifndef CONFIG_TINY_RCU diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 779479ac9f57..fb2d1591f671 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -32,7 +32,7 @@ #include #include #include -#include +#include #include #include #include @@ -1002,7 +1002,7 @@ const struct file_operations kmsg_fops = { .release = devkmsg_release, }; -#ifdef CONFIG_KEXEC_CORE +#ifdef CONFIG_CRASH_CORE /* * This appends the listed symbols to /proc/vmcore * @@ -1011,7 +1011,7 @@ const struct file_operations kmsg_fops = { * symbols are specifically used so that utilities can access and extract the * dmesg log from a vmcore file after a crash. */ -void log_buf_kexec_setup(void) +void log_buf_vmcoreinfo_setup(void) { VMCOREINFO_SYMBOL(log_buf); VMCOREINFO_SYMBOL(log_buf_len); -- cgit v1.2.3 From 51dbd92520d4344fef78481b1bcbc3a7de32b69b Mon Sep 17 00:00:00 2001 From: Hari Bathini Date: Mon, 8 May 2017 15:56:21 -0700 Subject: ia64: reuse append_elf_note() and final_note() functions Get rid of multiple definitions of append_elf_note() & final_note() functions. Reuse these functions compiled under CONFIG_CRASH_CORE Also, define Elf_Word and use it instead of generic u32 or the more specific Elf64_Word. Link: http://lkml.kernel.org/r/149035342324.6881.11667840929850361402.stgit@hbathini.in.ibm.com Signed-off-by: Hari Bathini Acked-by: Dave Young Acked-by: Tony Luck Cc: Fenghua Yu Cc: Eric Biederman Cc: Mahesh Salgaonkar Cc: Vivek Goyal Cc: Michael Ellerman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/kernel/crash.c | 22 ---------------------- include/linux/crash_core.h | 4 ++++ include/linux/elf.h | 2 ++ kernel/crash_core.c | 34 ++++++++++++++-------------------- kernel/kexec_core.c | 28 ---------------------------- 5 files changed, 20 insertions(+), 70 deletions(-) (limited to 'kernel') diff --git a/arch/ia64/kernel/crash.c b/arch/ia64/kernel/crash.c index 2955f359e2a7..75859a07d75b 100644 --- a/arch/ia64/kernel/crash.c +++ b/arch/ia64/kernel/crash.c @@ -27,28 +27,6 @@ static int kdump_freeze_monarch; static int kdump_on_init = 1; static int kdump_on_fatal_mca = 1; -static inline Elf64_Word -*append_elf_note(Elf64_Word *buf, char *name, unsigned type, void *data, - size_t data_len) -{ - struct elf_note *note = (struct elf_note *)buf; - note->n_namesz = strlen(name) + 1; - note->n_descsz = data_len; - note->n_type = type; - buf += (sizeof(*note) + 3)/4; - memcpy(buf, name, note->n_namesz); - buf += (note->n_namesz + 3)/4; - memcpy(buf, data, data_len); - buf += (data_len + 3)/4; - return buf; -} - -static void -final_note(void *buf) -{ - memset(buf, 0, sizeof(struct elf_note)); -} - extern void ia64_dump_cpu_regs(void *); static DEFINE_PER_CPU(struct elf_prstatus, elf_prstatus); diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index 18d0f946fda3..541a197ba4a2 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -55,6 +55,10 @@ extern u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4]; extern size_t vmcoreinfo_size; extern size_t vmcoreinfo_max_size; +Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, + void *data, size_t data_len); +void final_note(Elf_Word *buf); + int __init parse_crashkernel(char *cmdline, unsigned long long system_ram, unsigned long long *crash_size, unsigned long long *crash_base); int parse_crashkernel_high(char *cmdline, unsigned long long system_ram, diff --git a/include/linux/elf.h b/include/linux/elf.h index 20fa8d8ae313..ba069e8f4f78 100644 --- a/include/linux/elf.h +++ b/include/linux/elf.h @@ -29,6 +29,7 @@ extern Elf32_Dyn _DYNAMIC []; #define elf_note elf32_note #define elf_addr_t Elf32_Off #define Elf_Half Elf32_Half +#define Elf_Word Elf32_Word #else @@ -39,6 +40,7 @@ extern Elf64_Dyn _DYNAMIC []; #define elf_note elf64_note #define elf_addr_t Elf64_Off #define Elf_Half Elf64_Half +#define Elf_Word Elf64_Word #endif diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 4261587a34d2..fcbd568f1e95 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -291,32 +291,26 @@ int __init parse_crashkernel_low(char *cmdline, "crashkernel=", suffix_tbl[SUFFIX_LOW]); } -static u32 *append_elf_note(u32 *buf, char *name, unsigned int type, - void *data, size_t data_len) +Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, + void *data, size_t data_len) { - struct elf_note note; - - note.n_namesz = strlen(name) + 1; - note.n_descsz = data_len; - note.n_type = type; - memcpy(buf, ¬e, sizeof(note)); - buf += (sizeof(note) + 3)/4; - memcpy(buf, name, note.n_namesz); - buf += (note.n_namesz + 3)/4; - memcpy(buf, data, note.n_descsz); - buf += (note.n_descsz + 3)/4; + struct elf_note *note = (struct elf_note *)buf; + + note->n_namesz = strlen(name) + 1; + note->n_descsz = data_len; + note->n_type = type; + buf += DIV_ROUND_UP(sizeof(*note), sizeof(Elf_Word)); + memcpy(buf, name, note->n_namesz); + buf += DIV_ROUND_UP(note->n_namesz, sizeof(Elf_Word)); + memcpy(buf, data, data_len); + buf += DIV_ROUND_UP(data_len, sizeof(Elf_Word)); return buf; } -static void final_note(u32 *buf) +void final_note(Elf_Word *buf) { - struct elf_note note; - - note.n_namesz = 0; - note.n_descsz = 0; - note.n_type = 0; - memcpy(buf, ¬e, sizeof(note)); + memset(buf, 0, sizeof(struct elf_note)); } static void update_vmcoreinfo_note(void) diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 9dd722912850..ae1a3ba24df5 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -990,34 +990,6 @@ unlock: return ret; } -static u32 *append_elf_note(u32 *buf, char *name, unsigned type, void *data, - size_t data_len) -{ - struct elf_note note; - - note.n_namesz = strlen(name) + 1; - note.n_descsz = data_len; - note.n_type = type; - memcpy(buf, ¬e, sizeof(note)); - buf += (sizeof(note) + 3)/4; - memcpy(buf, name, note.n_namesz); - buf += (note.n_namesz + 3)/4; - memcpy(buf, data, note.n_descsz); - buf += (note.n_descsz + 3)/4; - - return buf; -} - -static void final_note(u32 *buf) -{ - struct elf_note note; - - note.n_namesz = 0; - note.n_descsz = 0; - note.n_type = 0; - memcpy(buf, ¬e, sizeof(note)); -} - void crash_save_cpu(struct pt_regs *regs, int cpu) { struct elf_prstatus prstatus; -- cgit v1.2.3 From 8896c23d2ef803f1883fea73117a435925c2b4c4 Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Mon, 8 May 2017 15:56:34 -0700 Subject: pidns: disable pid allocation if pid_ns_prepare_proc() is failed in alloc_pid() alloc_pidmap() advances pid_namespace::last_pid. When first pid allocation fails, then next created process will have pid 2 and pid_ns_prepare_proc() won't be called. So, pid_namespace::proc_mnt will never be initialized (not to mention that there won't be a child reaper). I saw crash stack of such case on kernel 3.10: BUG: unable to handle kernel NULL pointer dereference at (null) IP: proc_flush_task+0x8f/0x1b0 Call Trace: release_task+0x3f/0x490 wait_consider_task.part.10+0x7ff/0xb00 do_wait+0x11f/0x280 SyS_wait4+0x7d/0x110 We may fix this by restore of last_pid in 0 or by prohibiting of futher allocations. Since there was a similar issue in Oleg Nesterov's commit 314a8ad0f18a ("pidns: fix free_pid() to handle the first fork failure"). and it was fixed via prohibiting allocation, let's follow this way, and do the same. Link: http://lkml.kernel.org/r/149201021004.4863.6762095011554287922.stgit@localhost.localdomain Signed-off-by: Kirill Tkhai Acked-by: Cyrill Gorcunov Cc: Andrei Vagin Cc: Andreas Gruenbacher Cc: Kees Cook Cc: Michael Kerrisk Cc: Al Viro Cc: Oleg Nesterov Cc: Paul Moore Cc: Eric Biederman Cc: Andy Lutomirski Cc: Ingo Molnar Cc: Serge Hallyn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/pid.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/pid.c b/kernel/pid.c index 0143ac0ddceb..fd1cde1e4576 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -321,8 +321,10 @@ struct pid *alloc_pid(struct pid_namespace *ns) } if (unlikely(is_child_reaper(pid))) { - if (pid_ns_prepare_proc(ns)) + if (pid_ns_prepare_proc(ns)) { + disable_pid_allocation(ns); goto out_free; + } } get_pid_ns(ns); -- cgit v1.2.3 From eaa0d190bfe1ed891b814a52712dcd852554cb08 Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Mon, 8 May 2017 15:56:41 -0700 Subject: pidns: expose task pid_ns_for_children to userspace pid_ns_for_children set by a task is known only to the task itself, and it's impossible to identify it from outside. It's a big problem for checkpoint/restore software like CRIU, because it can't correctly handle tasks, that do setns(CLONE_NEWPID) in proccess of their work. This patch solves the problem, and it exposes pid_ns_for_children to ns directory in standard way with the name "pid_for_children": ~# ls /proc/5531/ns -l | grep pid lrwxrwxrwx 1 root root 0 Jan 14 16:38 pid -> pid:[4026531836] lrwxrwxrwx 1 root root 0 Jan 14 16:38 pid_for_children -> pid:[4026532286] Link: http://lkml.kernel.org/r/149201123914.6007.2187327078064239572.stgit@localhost.localdomain Signed-off-by: Kirill Tkhai Cc: Andrei Vagin Cc: Andreas Gruenbacher Cc: Kees Cook Cc: Michael Kerrisk Cc: Al Viro Cc: Oleg Nesterov Cc: Paul Moore Cc: Eric Biederman Cc: Andy Lutomirski Cc: Ingo Molnar Cc: Serge Hallyn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/namespaces.c | 1 + include/linux/proc_ns.h | 1 + kernel/pid_namespace.c | 34 ++++++++++++++++++++++++++++++++++ 3 files changed, 36 insertions(+) (limited to 'kernel') diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c index 766f0c637ad1..3803b24ca220 100644 --- a/fs/proc/namespaces.c +++ b/fs/proc/namespaces.c @@ -23,6 +23,7 @@ static const struct proc_ns_operations *ns_entries[] = { #endif #ifdef CONFIG_PID_NS &pidns_operations, + &pidns_for_children_operations, #endif #ifdef CONFIG_USER_NS &userns_operations, diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index 88dba3b53375..58ab28d81fc2 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -27,6 +27,7 @@ extern const struct proc_ns_operations netns_operations; extern const struct proc_ns_operations utsns_operations; extern const struct proc_ns_operations ipcns_operations; extern const struct proc_ns_operations pidns_operations; +extern const struct proc_ns_operations pidns_for_children_operations; extern const struct proc_ns_operations userns_operations; extern const struct proc_ns_operations mntns_operations; extern const struct proc_ns_operations cgroupns_operations; diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index de461aa0bf9a..d1f3e9f558b8 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -374,6 +374,29 @@ static struct ns_common *pidns_get(struct task_struct *task) return ns ? &ns->ns : NULL; } +static struct ns_common *pidns_for_children_get(struct task_struct *task) +{ + struct pid_namespace *ns = NULL; + + task_lock(task); + if (task->nsproxy) { + ns = task->nsproxy->pid_ns_for_children; + get_pid_ns(ns); + } + task_unlock(task); + + if (ns) { + read_lock(&tasklist_lock); + if (!ns->child_reaper) { + put_pid_ns(ns); + ns = NULL; + } + read_unlock(&tasklist_lock); + } + + return ns ? &ns->ns : NULL; +} + static void pidns_put(struct ns_common *ns) { put_pid_ns(to_pid_ns(ns)); @@ -443,6 +466,17 @@ const struct proc_ns_operations pidns_operations = { .get_parent = pidns_get_parent, }; +const struct proc_ns_operations pidns_for_children_operations = { + .name = "pid_for_children", + .real_ns_name = "pid", + .type = CLONE_NEWPID, + .get = pidns_for_children_get, + .put = pidns_put, + .install = pidns_install, + .owner = pidns_owner, + .get_parent = pidns_get_parent, +}; + static __init int pid_namespaces_init(void) { pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC); -- cgit v1.2.3 From 8c733420bdd5a6cc2d8540fb5aa32d1fbf3cb3ff Mon Sep 17 00:00:00 2001 From: Zhang Xiao Date: Mon, 8 May 2017 15:56:45 -0700 Subject: taskstats: add e/u/stime for TGID command The elapsed time, user CPU time and system CPU time for the thread group status request are presently left at zero. Fill these in. [akpm@linux-foundation.org: run ktime_get_ns() a single time] [akpm@linux-foundation.org: include linux/sched/cputime.h for task_cputime()] Link: http://lkml.kernel.org/r/1488508424-12322-1-git-send-email-xiao.zhang@windriver.com Signed-off-by: Zhang Xiao Cc: Balbir Singh Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/taskstats.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'kernel') diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 8a5e44236f78..4559e914452b 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -30,6 +30,7 @@ #include #include #include +#include /* * Maximum length of a cpumask that can be specified in @@ -210,6 +211,8 @@ static int fill_stats_for_tgid(pid_t tgid, struct taskstats *stats) struct task_struct *tsk, *first; unsigned long flags; int rc = -ESRCH; + u64 delta, utime, stime; + u64 start_time; /* * Add additional stats from live tasks except zombie thread group @@ -227,6 +230,7 @@ static int fill_stats_for_tgid(pid_t tgid, struct taskstats *stats) memset(stats, 0, sizeof(*stats)); tsk = first; + start_time = ktime_get_ns(); do { if (tsk->exit_state) continue; @@ -238,6 +242,16 @@ static int fill_stats_for_tgid(pid_t tgid, struct taskstats *stats) */ delayacct_add_tsk(stats, tsk); + /* calculate task elapsed time in nsec */ + delta = start_time - tsk->start_time; + /* Convert to micro seconds */ + do_div(delta, NSEC_PER_USEC); + stats->ac_etime += delta; + + task_cputime(tsk, &utime, &stime); + stats->ac_utime += div_u64(utime, NSEC_PER_USEC); + stats->ac_stime += div_u64(stime, NSEC_PER_USEC); + stats->nvcsw += tsk->nvcsw; stats->nivcsw += tsk->nivcsw; } while_each_thread(first, tsk); -- cgit v1.2.3 From f61e869d519c0c11a8d80a503cfdfb4897df855a Mon Sep 17 00:00:00 2001 From: Dmitry Vyukov Date: Mon, 8 May 2017 15:56:48 -0700 Subject: kcov: simplify interrupt check in_interrupt() semantics are confusing and wrong for most users as it also returns true when bh is disabled. Thus we open coded a proper check for interrupts in __sanitizer_cov_trace_pc() with a lengthy explanatory comment. Use the new in_task() predicate instead. Link: http://lkml.kernel.org/r/20170321091026.139655-1-dvyukov@google.com Signed-off-by: Dmitry Vyukov Cc: Kefeng Wang Cc: James Morse Cc: Alexander Popov Cc: Andrey Konovalov Cc: Hillf Danton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/kcov.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) (limited to 'kernel') diff --git a/kernel/kcov.c b/kernel/kcov.c index 85e5546cd791..cd771993f96f 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -60,15 +60,8 @@ void notrace __sanitizer_cov_trace_pc(void) /* * We are interested in code coverage as a function of a syscall inputs, * so we ignore code executed in interrupts. - * The checks for whether we are in an interrupt are open-coded, because - * 1. We can't use in_interrupt() here, since it also returns true - * when we are inside local_bh_disable() section. - * 2. We don't want to use (in_irq() | in_serving_softirq() | in_nmi()), - * since that leads to slower generated code (three separate tests, - * one for each of the flags). */ - if (!t || (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_OFFSET - | NMI_MASK))) + if (!t || !in_task()) return; mode = READ_ONCE(t->kcov_mode); if (mode == KCOV_MODE_TRACE) { -- cgit v1.2.3 From 19809c2da28aee5860ad9a2eff760730a0710df0 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Mon, 8 May 2017 15:57:44 -0700 Subject: mm, vmalloc: use __GFP_HIGHMEM implicitly __vmalloc* allows users to provide gfp flags for the underlying allocation. This API is quite popular $ git grep "=[[:space:]]__vmalloc\|return[[:space:]]*__vmalloc" | wc -l 77 The only problem is that many people are not aware that they really want to give __GFP_HIGHMEM along with other flags because there is really no reason to consume precious lowmemory on CONFIG_HIGHMEM systems for pages which are mapped to the kernel vmalloc space. About half of users don't use this flag, though. This signals that we make the API unnecessarily too complex. This patch simply uses __GFP_HIGHMEM implicitly when allocating pages to be mapped to the vmalloc space. Current users which add __GFP_HIGHMEM are simplified and drop the flag. Link: http://lkml.kernel.org/r/20170307141020.29107-1-mhocko@kernel.org Signed-off-by: Michal Hocko Reviewed-by: Matthew Wilcox Cc: Al Viro Cc: Vlastimil Babka Cc: David Rientjes Cc: Cristopher Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/parisc/kernel/module.c | 2 +- arch/x86/kernel/module.c | 2 +- drivers/block/drbd/drbd_bitmap.c | 2 +- drivers/gpu/drm/etnaviv/etnaviv_dump.c | 4 ++-- drivers/md/dm-bufio.c | 2 +- fs/btrfs/free-space-tree.c | 3 +-- fs/file.c | 2 +- fs/xfs/kmem.c | 2 +- include/drm/drm_mem_util.h | 9 +++------ kernel/bpf/core.c | 9 +++------ kernel/bpf/syscall.c | 3 +-- kernel/fork.c | 2 +- kernel/groups.c | 2 +- kernel/module.c | 2 +- mm/kasan/kasan.c | 2 +- mm/nommu.c | 3 +-- mm/util.c | 2 +- mm/vmalloc.c | 14 +++++++------- net/ceph/ceph_common.c | 2 +- net/netfilter/x_tables.c | 3 +-- 20 files changed, 31 insertions(+), 41 deletions(-) (limited to 'kernel') diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c index c66c943d9322..f1a76935a314 100644 --- a/arch/parisc/kernel/module.c +++ b/arch/parisc/kernel/module.c @@ -218,7 +218,7 @@ void *module_alloc(unsigned long size) * easier than trying to map the text, data, init_text and * init_data correctly */ return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END, - GFP_KERNEL | __GFP_HIGHMEM, + GFP_KERNEL, PAGE_KERNEL_RWX, 0, NUMA_NO_NODE, __builtin_return_address(0)); } diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 477ae806c2fa..f67bd3205df7 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -85,7 +85,7 @@ void *module_alloc(unsigned long size) p = __vmalloc_node_range(size, MODULE_ALIGN, MODULES_VADDR + get_module_load_offset(), - MODULES_END, GFP_KERNEL | __GFP_HIGHMEM, + MODULES_END, GFP_KERNEL, PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE, __builtin_return_address(0)); if (p && (kasan_module_alloc(p, size) < 0)) { diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c index dece26f119d4..a804a4107fbc 100644 --- a/drivers/block/drbd/drbd_bitmap.c +++ b/drivers/block/drbd/drbd_bitmap.c @@ -409,7 +409,7 @@ static struct page **bm_realloc_pages(struct drbd_bitmap *b, unsigned long want) new_pages = kzalloc(bytes, GFP_NOIO | __GFP_NOWARN); if (!new_pages) { new_pages = __vmalloc(bytes, - GFP_NOIO | __GFP_HIGHMEM | __GFP_ZERO, + GFP_NOIO | __GFP_ZERO, PAGE_KERNEL); if (!new_pages) return NULL; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_dump.c b/drivers/gpu/drm/etnaviv/etnaviv_dump.c index d019b5e311cc..2d955d7d7b6d 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_dump.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_dump.c @@ -161,8 +161,8 @@ void etnaviv_core_dump(struct etnaviv_gpu *gpu) file_size += sizeof(*iter.hdr) * n_obj; /* Allocate the file in vmalloc memory, it's likely to be big */ - iter.start = __vmalloc(file_size, GFP_KERNEL | __GFP_HIGHMEM | - __GFP_NOWARN | __GFP_NORETRY, PAGE_KERNEL); + iter.start = __vmalloc(file_size, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY, + PAGE_KERNEL); if (!iter.start) { dev_warn(gpu->dev, "failed to allocate devcoredump file\n"); return; diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index c92c31b23e54..5db11a405129 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -406,7 +406,7 @@ static void *alloc_buffer_data(struct dm_bufio_client *c, gfp_t gfp_mask, if (gfp_mask & __GFP_NORETRY) noio_flag = memalloc_noio_save(); - ptr = __vmalloc(c->block_size, gfp_mask | __GFP_HIGHMEM, PAGE_KERNEL); + ptr = __vmalloc(c->block_size, gfp_mask, PAGE_KERNEL); if (gfp_mask & __GFP_NORETRY) memalloc_noio_restore(noio_flag); diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index dd7fb22a955a..fc0bd8406758 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -167,8 +167,7 @@ static u8 *alloc_bitmap(u32 bitmap_size) if (mem) return mem; - return __vmalloc(bitmap_size, GFP_NOFS | __GFP_HIGHMEM | __GFP_ZERO, - PAGE_KERNEL); + return __vmalloc(bitmap_size, GFP_NOFS | __GFP_ZERO, PAGE_KERNEL); } int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans, diff --git a/fs/file.c b/fs/file.c index ad6f094f2eff..1c2972e3a405 100644 --- a/fs/file.c +++ b/fs/file.c @@ -42,7 +42,7 @@ static void *alloc_fdmem(size_t size) if (data != NULL) return data; } - return __vmalloc(size, GFP_KERNEL_ACCOUNT | __GFP_HIGHMEM, PAGE_KERNEL); + return __vmalloc(size, GFP_KERNEL_ACCOUNT, PAGE_KERNEL); } static void __free_fdtable(struct fdtable *fdt) diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c index 780fc8986dab..393b6849aeb3 100644 --- a/fs/xfs/kmem.c +++ b/fs/xfs/kmem.c @@ -67,7 +67,7 @@ kmem_zalloc_large(size_t size, xfs_km_flags_t flags) nofs_flag = memalloc_nofs_save(); lflags = kmem_flags_convert(flags); - ptr = __vmalloc(size, lflags | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL); + ptr = __vmalloc(size, lflags | __GFP_ZERO, PAGE_KERNEL); if (flags & KM_NOFS) memalloc_nofs_restore(nofs_flag); diff --git a/include/drm/drm_mem_util.h b/include/drm/drm_mem_util.h index 70d4e221a3ad..d0f6cf2e5324 100644 --- a/include/drm/drm_mem_util.h +++ b/include/drm/drm_mem_util.h @@ -37,8 +37,7 @@ static __inline__ void *drm_calloc_large(size_t nmemb, size_t size) if (size * nmemb <= PAGE_SIZE) return kcalloc(nmemb, size, GFP_KERNEL); - return __vmalloc(size * nmemb, - GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL); + return vzalloc(size * nmemb); } /* Modeled after cairo's malloc_ab, it's like calloc but without the zeroing. */ @@ -50,8 +49,7 @@ static __inline__ void *drm_malloc_ab(size_t nmemb, size_t size) if (size * nmemb <= PAGE_SIZE) return kmalloc(nmemb * size, GFP_KERNEL); - return __vmalloc(size * nmemb, - GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL); + return vmalloc(size * nmemb); } static __inline__ void *drm_malloc_gfp(size_t nmemb, size_t size, gfp_t gfp) @@ -69,8 +67,7 @@ static __inline__ void *drm_malloc_gfp(size_t nmemb, size_t size, gfp_t gfp) return ptr; } - return __vmalloc(size * nmemb, - gfp | __GFP_HIGHMEM, PAGE_KERNEL); + return __vmalloc(size * nmemb, gfp, PAGE_KERNEL); } static __inline void drm_free_large(void *ptr) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 6f81e0f5a0fa..dedf367f59bb 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -76,8 +76,7 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags) { - gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO | - gfp_extra_flags; + gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags; struct bpf_prog_aux *aux; struct bpf_prog *fp; @@ -107,8 +106,7 @@ EXPORT_SYMBOL_GPL(bpf_prog_alloc); struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, gfp_t gfp_extra_flags) { - gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO | - gfp_extra_flags; + gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags; struct bpf_prog *fp; u32 pages, delta; int ret; @@ -655,8 +653,7 @@ out: static struct bpf_prog *bpf_prog_clone_create(struct bpf_prog *fp_other, gfp_t gfp_extra_flags) { - gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO | - gfp_extra_flags; + gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags; struct bpf_prog *fp; fp = __vmalloc(fp_other->pages * PAGE_SIZE, gfp_flags, PAGE_KERNEL); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 13642c73dca0..fd2411fd6914 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -67,8 +67,7 @@ void *bpf_map_area_alloc(size_t size) return area; } - return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | flags, - PAGE_KERNEL); + return __vmalloc(size, GFP_KERNEL | flags, PAGE_KERNEL); } void bpf_map_area_free(void *area) diff --git a/kernel/fork.c b/kernel/fork.c index 55e325f4b457..08ba696aa561 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -221,7 +221,7 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) stack = __vmalloc_node_range(THREAD_SIZE, THREAD_SIZE, VMALLOC_START, VMALLOC_END, - THREADINFO_GFP | __GFP_HIGHMEM, + THREADINFO_GFP, PAGE_KERNEL, 0, node, __builtin_return_address(0)); diff --git a/kernel/groups.c b/kernel/groups.c index 8dd7a61b7115..d09727692a2a 100644 --- a/kernel/groups.c +++ b/kernel/groups.c @@ -18,7 +18,7 @@ struct group_info *groups_alloc(int gidsetsize) len = sizeof(struct group_info) + sizeof(kgid_t) * gidsetsize; gi = kmalloc(len, GFP_KERNEL_ACCOUNT|__GFP_NOWARN|__GFP_NORETRY); if (!gi) - gi = __vmalloc(len, GFP_KERNEL_ACCOUNT|__GFP_HIGHMEM, PAGE_KERNEL); + gi = __vmalloc(len, GFP_KERNEL_ACCOUNT, PAGE_KERNEL); if (!gi) return NULL; diff --git a/kernel/module.c b/kernel/module.c index f37308b733d8..2b316b954828 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2864,7 +2864,7 @@ static int copy_module_from_user(const void __user *umod, unsigned long len, /* Suck in entire file: we'll want most of it. */ info->hdr = __vmalloc(info->len, - GFP_KERNEL | __GFP_HIGHMEM | __GFP_NOWARN, PAGE_KERNEL); + GFP_KERNEL | __GFP_NOWARN, PAGE_KERNEL); if (!info->hdr) return -ENOMEM; diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c index 9348d27088c1..b10da59cf765 100644 --- a/mm/kasan/kasan.c +++ b/mm/kasan/kasan.c @@ -691,7 +691,7 @@ int kasan_module_alloc(void *addr, size_t size) ret = __vmalloc_node_range(shadow_size, 1, shadow_start, shadow_start + shadow_size, - GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, + GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL, VM_NO_GUARD, NUMA_NO_NODE, __builtin_return_address(0)); diff --git a/mm/nommu.c b/mm/nommu.c index a80411d258fc..fc184f597d59 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -246,8 +246,7 @@ void *vmalloc_user(unsigned long size) { void *ret; - ret = __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, - PAGE_KERNEL); + ret = __vmalloc(size, GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL); if (ret) { struct vm_area_struct *vma; diff --git a/mm/util.c b/mm/util.c index f4e590b2c0da..718154debc87 100644 --- a/mm/util.c +++ b/mm/util.c @@ -382,7 +382,7 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node) if (ret || size <= PAGE_SIZE) return ret; - return __vmalloc_node_flags(size, node, flags | __GFP_HIGHMEM); + return __vmalloc_node_flags(size, node, flags); } EXPORT_SYMBOL(kvmalloc_node); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 717b1e8b942c..1dda6d8a200a 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1655,7 +1655,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, struct page **pages; unsigned int nr_pages, array_size, i; const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO; - const gfp_t alloc_mask = gfp_mask | __GFP_NOWARN; + const gfp_t alloc_mask = gfp_mask | __GFP_HIGHMEM | __GFP_NOWARN; nr_pages = get_vm_area_size(area) >> PAGE_SHIFT; array_size = (nr_pages * sizeof(struct page *)); @@ -1818,7 +1818,7 @@ EXPORT_SYMBOL(__vmalloc); void *vmalloc(unsigned long size) { return __vmalloc_node_flags(size, NUMA_NO_NODE, - GFP_KERNEL | __GFP_HIGHMEM); + GFP_KERNEL); } EXPORT_SYMBOL(vmalloc); @@ -1835,7 +1835,7 @@ EXPORT_SYMBOL(vmalloc); void *vzalloc(unsigned long size) { return __vmalloc_node_flags(size, NUMA_NO_NODE, - GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO); + GFP_KERNEL | __GFP_ZERO); } EXPORT_SYMBOL(vzalloc); @@ -1852,7 +1852,7 @@ void *vmalloc_user(unsigned long size) void *ret; ret = __vmalloc_node(size, SHMLBA, - GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, + GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL, NUMA_NO_NODE, __builtin_return_address(0)); if (ret) { @@ -1876,7 +1876,7 @@ EXPORT_SYMBOL(vmalloc_user); */ void *vmalloc_node(unsigned long size, int node) { - return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL, + return __vmalloc_node(size, 1, GFP_KERNEL, PAGE_KERNEL, node, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_node); @@ -1896,7 +1896,7 @@ EXPORT_SYMBOL(vmalloc_node); void *vzalloc_node(unsigned long size, int node) { return __vmalloc_node_flags(size, node, - GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO); + GFP_KERNEL | __GFP_ZERO); } EXPORT_SYMBOL(vzalloc_node); @@ -1918,7 +1918,7 @@ EXPORT_SYMBOL(vzalloc_node); void *vmalloc_exec(unsigned long size) { - return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC, + return __vmalloc_node(size, 1, GFP_KERNEL, PAGE_KERNEL_EXEC, NUMA_NO_NODE, __builtin_return_address(0)); } diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 108533859a53..4eb773ccce11 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -187,7 +187,7 @@ void *ceph_kvmalloc(size_t size, gfp_t flags) return ptr; } - return __vmalloc(size, flags | __GFP_HIGHMEM, PAGE_KERNEL); + return __vmalloc(size, flags, PAGE_KERNEL); } diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 3d0584665b5d..8876b7da6884 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -998,8 +998,7 @@ struct xt_table_info *xt_alloc_table_info(unsigned int size) 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 | __GFP_HIGHMEM, + info = __vmalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY, PAGE_KERNEL); if (!info) return NULL; -- cgit v1.2.3 From bbca07c307166a753155e79a874d07023f4edd20 Mon Sep 17 00:00:00 2001 From: Laura Abbott Date: Mon, 8 May 2017 15:58:29 -0700 Subject: kernel/module.c: use set_memory.h header set_memory_* functions have moved to set_memory.h. Switch to this explicitly. Link: http://lkml.kernel.org/r/1488920133-27229-12-git-send-email-labbott@redhat.com Signed-off-by: Laura Abbott Acked-by: Jessica Yu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/module.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel') diff --git a/kernel/module.c b/kernel/module.c index 2b316b954828..4a3665f8f837 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -49,6 +49,9 @@ #include #include #include +#ifdef CONFIG_STRICT_MODULE_RWX +#include +#endif #include #include #include -- cgit v1.2.3 From 50327ddfbc926e68da1958e4fac51f1106f5e730 Mon Sep 17 00:00:00 2001 From: Laura Abbott Date: Mon, 8 May 2017 15:58:32 -0700 Subject: kernel/power/snapshot.c: use set_memory.h header set_memory_* functions have moved to set_memory.h. Switch to this explicitly. Link: http://lkml.kernel.org/r/1488920133-27229-13-git-send-email-labbott@redhat.com Signed-off-by: Laura Abbott Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/power/snapshot.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel') diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index d79a38de425a..3b1e0f3ad07f 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -36,6 +36,9 @@ #include #include #include +#ifdef CONFIG_STRICT_KERNEL_RWX +#include +#endif #include "power.h" -- cgit v1.2.3 From 51aad0aee5b70e26347e4d891d568518909f3452 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Mon, 8 May 2017 15:59:13 -0700 Subject: trace: make trace_hwlat timestamp y2038 safe struct timespec is not y2038 safe on 32 bit machines and needs to be replaced by struct timespec64 in order to represent times beyond year 2038 on such machines. Fix all the timestamp representation in struct trace_hwlat and all the corresponding implementations. Link: http://lkml.kernel.org/r/1491613030-11599-3-git-send-email-deepa.kernel@gmail.com Signed-off-by: Deepa Dinamani Acked-by: Steven Rostedt (VMware) Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/trace/trace_entries.h | 6 +++--- kernel/trace/trace_hwlat.c | 14 +++++++------- kernel/trace/trace_output.c | 9 ++++----- 3 files changed, 14 insertions(+), 15 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index c203ac4df791..adcdbbeae010 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -348,14 +348,14 @@ FTRACE_ENTRY(hwlat, hwlat_entry, __field( u64, duration ) __field( u64, outer_duration ) __field( u64, nmi_total_ts ) - __field_struct( struct timespec, timestamp ) - __field_desc( long, timestamp, tv_sec ) + __field_struct( struct timespec64, timestamp ) + __field_desc( s64, timestamp, tv_sec ) __field_desc( long, timestamp, tv_nsec ) __field( unsigned int, nmi_count ) __field( unsigned int, seqnum ) ), - F_printk("cnt:%u\tts:%010lu.%010lu\tinner:%llu\touter:%llunmi-ts:%llu\tnmi-count:%u\n", + F_printk("cnt:%u\tts:%010llu.%010lu\tinner:%llu\touter:%llunmi-ts:%llu\tnmi-count:%u\n", __entry->seqnum, __entry->tv_sec, __entry->tv_nsec, diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c index 21ea6ae77d93..d7c8e4ec3d9d 100644 --- a/kernel/trace/trace_hwlat.c +++ b/kernel/trace/trace_hwlat.c @@ -79,12 +79,12 @@ static u64 last_tracing_thresh = DEFAULT_LAT_THRESHOLD * NSEC_PER_USEC; /* Individual latency samples are stored here when detected. */ struct hwlat_sample { - u64 seqnum; /* unique sequence */ - u64 duration; /* delta */ - u64 outer_duration; /* delta (outer loop) */ - u64 nmi_total_ts; /* Total time spent in NMIs */ - struct timespec timestamp; /* wall time */ - int nmi_count; /* # NMIs during this sample */ + u64 seqnum; /* unique sequence */ + u64 duration; /* delta */ + u64 outer_duration; /* delta (outer loop) */ + u64 nmi_total_ts; /* Total time spent in NMIs */ + struct timespec64 timestamp; /* wall time */ + int nmi_count; /* # NMIs during this sample */ }; /* keep the global state somewhere. */ @@ -250,7 +250,7 @@ static int get_sample(void) s.seqnum = hwlat_data.count; s.duration = sample; s.outer_duration = outer_sample; - s.timestamp = CURRENT_TIME; + ktime_get_real_ts64(&s.timestamp); s.nmi_total_ts = nmi_total_ts; s.nmi_count = nmi_count; trace_hwlat_sample(&s); diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 02a4aeb22c47..08f9bab8089e 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -4,7 +4,6 @@ * Copyright (C) 2008 Red Hat Inc, Steven Rostedt * */ - #include #include #include @@ -1161,11 +1160,11 @@ trace_hwlat_print(struct trace_iterator *iter, int flags, trace_assign_type(field, entry); - trace_seq_printf(s, "#%-5u inner/outer(us): %4llu/%-5llu ts:%ld.%09ld", + trace_seq_printf(s, "#%-5u inner/outer(us): %4llu/%-5llu ts:%lld.%09ld", field->seqnum, field->duration, field->outer_duration, - field->timestamp.tv_sec, + (long long)field->timestamp.tv_sec, field->timestamp.tv_nsec); if (field->nmi_count) { @@ -1195,10 +1194,10 @@ trace_hwlat_raw(struct trace_iterator *iter, int flags, trace_assign_type(field, iter->ent); - trace_seq_printf(s, "%llu %lld %ld %09ld %u\n", + trace_seq_printf(s, "%llu %lld %lld %09ld %u\n", field->duration, field->outer_duration, - field->timestamp.tv_sec, + (long long)field->timestamp.tv_sec, field->timestamp.tv_nsec, field->seqnum); -- cgit v1.2.3