From d407bd25a204bd66b7346dde24bd3d37ef0e0b05 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 18 Jan 2017 15:14:17 +0100 Subject: bpf: don't trigger OOM killer under pressure with map alloc This patch adds two helpers, bpf_map_area_alloc() and bpf_map_area_free(), that are to be used for map allocations. Using kmalloc() for very large allocations can cause excessive work within the page allocator, so i) fall back earlier to vmalloc() when the attempt is considered costly anyway, and even more importantly ii) don't trigger OOM killer with any of the allocators. Since this is based on a user space request, for example, when creating maps with element pre-allocation, we really want such requests to fail instead of killing other user space processes. Also, don't spam the kernel log with warnings should any of the allocations fail under pressure. Given that, we can make backend selection in bpf_map_area_alloc() generic, and convert all maps over to use this API for spots with potentially large allocation requests. Note, replacing the one kmalloc_array() is fine as overflow checks happen earlier in htab_map_alloc(), since it must also protect the multiplication for vmalloc() should kmalloc_array() fail. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/bpf/arraymap.c | 18 +++++++----------- kernel/bpf/hashtab.c | 22 +++++++++------------- kernel/bpf/stackmap.c | 20 ++++++++------------ kernel/bpf/syscall.c | 26 ++++++++++++++++++++++++++ 4 files changed, 50 insertions(+), 36 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 229a5d5df977..3d55d95dcf49 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -11,7 +11,6 @@ */ #include #include -#include #include #include #include @@ -74,14 +73,10 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) if (array_size >= U32_MAX - PAGE_SIZE) return ERR_PTR(-ENOMEM); - /* allocate all map elements and zero-initialize them */ - array = kzalloc(array_size, GFP_USER | __GFP_NOWARN); - if (!array) { - array = vzalloc(array_size); - if (!array) - return ERR_PTR(-ENOMEM); - } + array = bpf_map_area_alloc(array_size); + if (!array) + return ERR_PTR(-ENOMEM); /* copy mandatory map attributes */ array->map.map_type = attr->map_type; @@ -97,7 +92,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) if (array_size >= U32_MAX - PAGE_SIZE || elem_size > PCPU_MIN_UNIT_SIZE || bpf_array_alloc_percpu(array)) { - kvfree(array); + bpf_map_area_free(array); return ERR_PTR(-ENOMEM); } out: @@ -262,7 +257,7 @@ static void array_map_free(struct bpf_map *map) if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) bpf_array_free_percpu(array); - kvfree(array); + bpf_map_area_free(array); } static const struct bpf_map_ops array_ops = { @@ -319,7 +314,8 @@ static void fd_array_map_free(struct bpf_map *map) /* make sure it's empty */ for (i = 0; i < array->map.max_entries; i++) BUG_ON(array->ptrs[i] != NULL); - kvfree(array); + + bpf_map_area_free(array); } static void *fd_array_map_lookup_elem(struct bpf_map *map, void *key) diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 3f2bb58952d8..a753bbe7df0a 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -13,7 +13,6 @@ #include #include #include -#include #include "percpu_freelist.h" #include "bpf_lru_list.h" @@ -103,7 +102,7 @@ static void htab_free_elems(struct bpf_htab *htab) free_percpu(pptr); } free_elems: - vfree(htab->elems); + bpf_map_area_free(htab->elems); } static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key, @@ -125,7 +124,8 @@ static int prealloc_init(struct bpf_htab *htab) { int err = -ENOMEM, i; - htab->elems = vzalloc(htab->elem_size * htab->map.max_entries); + htab->elems = bpf_map_area_alloc(htab->elem_size * + htab->map.max_entries); if (!htab->elems) return -ENOMEM; @@ -320,14 +320,10 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) goto free_htab; err = -ENOMEM; - htab->buckets = kmalloc_array(htab->n_buckets, sizeof(struct bucket), - GFP_USER | __GFP_NOWARN); - - if (!htab->buckets) { - htab->buckets = vmalloc(htab->n_buckets * sizeof(struct bucket)); - if (!htab->buckets) - goto free_htab; - } + htab->buckets = bpf_map_area_alloc(htab->n_buckets * + sizeof(struct bucket)); + if (!htab->buckets) + goto free_htab; for (i = 0; i < htab->n_buckets; i++) { INIT_HLIST_HEAD(&htab->buckets[i].head); @@ -354,7 +350,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) free_extra_elems: free_percpu(htab->extra_elems); free_buckets: - kvfree(htab->buckets); + bpf_map_area_free(htab->buckets); free_htab: kfree(htab); return ERR_PTR(err); @@ -1014,7 +1010,7 @@ static void htab_map_free(struct bpf_map *map) prealloc_destroy(htab); free_percpu(htab->extra_elems); - kvfree(htab->buckets); + bpf_map_area_free(htab->buckets); kfree(htab); } diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 732ae16d12b7..be8519148c25 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -7,7 +7,6 @@ #include #include #include -#include #include #include #include "percpu_freelist.h" @@ -32,7 +31,7 @@ static int prealloc_elems_and_freelist(struct bpf_stack_map *smap) u32 elem_size = sizeof(struct stack_map_bucket) + smap->map.value_size; int err; - smap->elems = vzalloc(elem_size * smap->map.max_entries); + smap->elems = bpf_map_area_alloc(elem_size * smap->map.max_entries); if (!smap->elems) return -ENOMEM; @@ -45,7 +44,7 @@ static int prealloc_elems_and_freelist(struct bpf_stack_map *smap) return 0; free_elems: - vfree(smap->elems); + bpf_map_area_free(smap->elems); return err; } @@ -76,12 +75,9 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) if (cost >= U32_MAX - PAGE_SIZE) return ERR_PTR(-E2BIG); - smap = kzalloc(cost, GFP_USER | __GFP_NOWARN); - if (!smap) { - smap = vzalloc(cost); - if (!smap) - return ERR_PTR(-ENOMEM); - } + smap = bpf_map_area_alloc(cost); + if (!smap) + return ERR_PTR(-ENOMEM); err = -E2BIG; cost += n_buckets * (value_size + sizeof(struct stack_map_bucket)); @@ -112,7 +108,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) put_buffers: put_callchain_buffers(); free_smap: - kvfree(smap); + bpf_map_area_free(smap); return ERR_PTR(err); } @@ -262,9 +258,9 @@ static void stack_map_free(struct bpf_map *map) /* wait for bpf programs to complete before freeing stack map */ synchronize_rcu(); - vfree(smap->elems); + bpf_map_area_free(smap->elems); pcpu_freelist_destroy(&smap->freelist); - kvfree(smap); + bpf_map_area_free(smap); put_callchain_buffers(); } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 1d6b29e4e2c3..19b6129eab23 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -12,6 +12,8 @@ #include #include #include +#include +#include #include #include #include @@ -49,6 +51,30 @@ void bpf_register_map_type(struct bpf_map_type_list *tl) list_add(&tl->list_node, &bpf_map_types); } +void *bpf_map_area_alloc(size_t size) +{ + /* We definitely need __GFP_NORETRY, so OOM killer doesn't + * trigger under memory pressure as we really just want to + * fail instead. + */ + const gfp_t flags = __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO; + void *area; + + if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { + area = kmalloc(size, GFP_USER | flags); + if (area != NULL) + return area; + } + + return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | flags, + PAGE_KERNEL); +} + +void bpf_map_area_free(void *area) +{ + kvfree(area); +} + int bpf_map_precharge_memlock(u32 pages) { struct user_struct *user = get_current_user(); -- cgit v1.2.3 From e326ce013a8e851193eb337aafb1aa396c533a61 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 20 Jan 2017 03:25:34 +0100 Subject: Revert "PM / sleep / ACPI: Use the ACPI_FADT_LOW_POWER_S0 flag" Revert commit 08b98d329165 (PM / sleep / ACPI: Use the ACPI_FADT_LOW_POWER_S0 flag) as it caused system suspend (in the default configuration) to fail on Dell XPS13 (9360) with the Kaby Lake processor. Fixes: 08b98d329165 (PM / sleep / ACPI: Use the ACPI_FADT_LOW_POWER_S0 flag) Reported-by: Paul Menzel Signed-off-by: Rafael J. Wysocki --- kernel/power/suspend.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index f67ceb7768b8..15e6baef5c73 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -46,7 +46,7 @@ static const char * const mem_sleep_labels[] = { const char *mem_sleep_states[PM_SUSPEND_MAX]; suspend_state_t mem_sleep_current = PM_SUSPEND_FREEZE; -suspend_state_t mem_sleep_default = PM_SUSPEND_MAX; +static suspend_state_t mem_sleep_default = PM_SUSPEND_MEM; unsigned int pm_suspend_global_flags; EXPORT_SYMBOL_GPL(pm_suspend_global_flags); @@ -168,7 +168,7 @@ void suspend_set_ops(const struct platform_suspend_ops *ops) } if (valid_state(PM_SUSPEND_MEM)) { mem_sleep_states[PM_SUSPEND_MEM] = mem_sleep_labels[PM_SUSPEND_MEM]; - if (mem_sleep_default >= PM_SUSPEND_MEM) + if (mem_sleep_default == PM_SUSPEND_MEM) mem_sleep_current = PM_SUSPEND_MEM; } -- cgit v1.2.3 From 880a38547ff08715ce4f1daf9a4bb30c87676e68 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Fri, 20 Jan 2017 15:21:35 +0200 Subject: userns: Make ucounts lock irq-safe The ucounts_lock is being used to protect various ucounts lifecycle management functionalities. However, those services can also be invoked when a pidns is being freed in an RCU callback (e.g. softirq context). This can lead to deadlocks. There were already efforts trying to prevent similar deadlocks in add7c65ca426 ("pid: fix lockdep deadlock warning due to ucount_lock"), however they just moved the context from hardirq to softrq. Fix this issue once and for all by explictly making the lock disable irqs altogether. Dmitry Vyukov reported: > I've got the following deadlock report while running syzkaller fuzzer > on eec0d3d065bfcdf9cd5f56dd2a36b94d12d32297 of linux-next (on odroid > device if it matters): > > ================================= > [ INFO: inconsistent lock state ] > 4.10.0-rc3-next-20170112-xc2-dirty #6 Not tainted > --------------------------------- > inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. > swapper/2/0 [HC0[0]:SC1[1]:HE1:SE0] takes: > (ucounts_lock){+.?...}, at: [< inline >] spin_lock > ./include/linux/spinlock.h:302 > (ucounts_lock){+.?...}, at: [] > put_ucounts+0x60/0x138 kernel/ucount.c:162 > {SOFTIRQ-ON-W} state was registered at: > [] mark_lock+0x220/0xb60 kernel/locking/lockdep.c:3054 > [< inline >] mark_irqflags kernel/locking/lockdep.c:2941 > [] __lock_acquire+0x388/0x3260 kernel/locking/lockdep.c:3295 > [] lock_acquire+0xa4/0x138 kernel/locking/lockdep.c:3753 > [< inline >] __raw_spin_lock ./include/linux/spinlock_api_smp.h:144 > [] _raw_spin_lock+0x90/0xd0 kernel/locking/spinlock.c:151 > [< inline >] spin_lock ./include/linux/spinlock.h:302 > [< inline >] get_ucounts kernel/ucount.c:131 > [] inc_ucount+0x80/0x6c8 kernel/ucount.c:189 > [< inline >] inc_mnt_namespaces fs/namespace.c:2818 > [] alloc_mnt_ns+0x78/0x3a8 fs/namespace.c:2849 > [] create_mnt_ns+0x28/0x200 fs/namespace.c:2959 > [< inline >] init_mount_tree fs/namespace.c:3199 > [] mnt_init+0x258/0x384 fs/namespace.c:3251 > [] vfs_caches_init+0x6c/0x80 fs/dcache.c:3626 > [] start_kernel+0x414/0x460 init/main.c:648 > [] __primary_switched+0x6c/0x70 arch/arm64/kernel/head.S:456 > irq event stamp: 2316924 > hardirqs last enabled at (2316924): [< inline >] rcu_do_batch > kernel/rcu/tree.c:2911 > hardirqs last enabled at (2316924): [< inline >] > invoke_rcu_callbacks kernel/rcu/tree.c:3182 > hardirqs last enabled at (2316924): [< inline >] > __rcu_process_callbacks kernel/rcu/tree.c:3149 > hardirqs last enabled at (2316924): [] > rcu_process_callbacks+0x7a4/0xc28 kernel/rcu/tree.c:3166 > hardirqs last disabled at (2316923): [< inline >] rcu_do_batch > kernel/rcu/tree.c:2900 > hardirqs last disabled at (2316923): [< inline >] > invoke_rcu_callbacks kernel/rcu/tree.c:3182 > hardirqs last disabled at (2316923): [< inline >] > __rcu_process_callbacks kernel/rcu/tree.c:3149 > hardirqs last disabled at (2316923): [] > rcu_process_callbacks+0x210/0xc28 kernel/rcu/tree.c:3166 > softirqs last enabled at (2316912): [] > _local_bh_enable+0x4c/0x80 kernel/softirq.c:155 > softirqs last disabled at (2316913): [< inline >] > do_softirq_own_stack ./include/linux/interrupt.h:488 > softirqs last disabled at (2316913): [< inline >] > invoke_softirq kernel/softirq.c:371 > softirqs last disabled at (2316913): [] > irq_exit+0x264/0x308 kernel/softirq.c:405 > > other info that might help us debug this: > Possible unsafe locking scenario: > > CPU0 > ---- > lock(ucounts_lock); > > lock(ucounts_lock); > > *** DEADLOCK *** > > 1 lock held by swapper/2/0: > #0: (rcu_callback){......}, at: [< inline >] __rcu_reclaim > kernel/rcu/rcu.h:108 > #0: (rcu_callback){......}, at: [< inline >] rcu_do_batch > kernel/rcu/tree.c:2919 > #0: (rcu_callback){......}, at: [< inline >] > invoke_rcu_callbacks kernel/rcu/tree.c:3182 > #0: (rcu_callback){......}, at: [< inline >] > __rcu_process_callbacks kernel/rcu/tree.c:3149 > #0: (rcu_callback){......}, at: [] > rcu_process_callbacks+0x720/0xc28 kernel/rcu/tree.c:3166 > > stack backtrace: > CPU: 2 PID: 0 Comm: swapper/2 Not tainted 4.10.0-rc3-next-20170112-xc2-dirty #6 > Hardware name: Hardkernel ODROID-C2 (DT) > Call trace: > [] dump_backtrace+0x0/0x440 arch/arm64/kernel/traps.c:500 > [] show_stack+0x20/0x30 arch/arm64/kernel/traps.c:225 > [] dump_stack+0x110/0x168 > [] print_usage_bug.part.27+0x49c/0x4bc > kernel/locking/lockdep.c:2387 > [< inline >] print_usage_bug kernel/locking/lockdep.c:2357 > [< inline >] valid_state kernel/locking/lockdep.c:2400 > [< inline >] mark_lock_irq kernel/locking/lockdep.c:2617 > [] mark_lock+0x934/0xb60 kernel/locking/lockdep.c:3065 > [< inline >] mark_irqflags kernel/locking/lockdep.c:2923 > [] __lock_acquire+0x640/0x3260 kernel/locking/lockdep.c:3295 > [] lock_acquire+0xa4/0x138 kernel/locking/lockdep.c:3753 > [< inline >] __raw_spin_lock ./include/linux/spinlock_api_smp.h:144 > [] _raw_spin_lock+0x90/0xd0 kernel/locking/spinlock.c:151 > [< inline >] spin_lock ./include/linux/spinlock.h:302 > [] put_ucounts+0x60/0x138 kernel/ucount.c:162 > [] dec_ucount+0xf4/0x158 kernel/ucount.c:214 > [< inline >] dec_pid_namespaces kernel/pid_namespace.c:89 > [] delayed_free_pidns+0x40/0xe0 kernel/pid_namespace.c:156 > [< inline >] __rcu_reclaim kernel/rcu/rcu.h:118 > [< inline >] rcu_do_batch kernel/rcu/tree.c:2919 > [< inline >] invoke_rcu_callbacks kernel/rcu/tree.c:3182 > [< inline >] __rcu_process_callbacks kernel/rcu/tree.c:3149 > [] rcu_process_callbacks+0x768/0xc28 kernel/rcu/tree.c:3166 > [] __do_softirq+0x324/0x6e0 kernel/softirq.c:284 > [< inline >] do_softirq_own_stack ./include/linux/interrupt.h:488 > [< inline >] invoke_softirq kernel/softirq.c:371 > [] irq_exit+0x264/0x308 kernel/softirq.c:405 > [] __handle_domain_irq+0xc0/0x150 kernel/irq/irqdesc.c:636 > [] gic_handle_irq+0x68/0xd8 > Exception stack(0xffff8000648e7dd0 to 0xffff8000648e7f00) > 7dc0: ffff8000648d4b3c 0000000000000007 > 7de0: 0000000000000000 1ffff0000c91a967 1ffff0000c91a967 1ffff0000c91a967 > 7e00: ffff20000a4b6b68 0000000000000001 0000000000000007 0000000000000001 > 7e20: 1fffe4000149ae90 ffff200009d35000 0000000000000000 0000000000000002 > 7e40: 0000000000000000 0000000000000000 0000000002624a1a 0000000000000000 > 7e60: 0000000000000000 ffff200009cbcd88 000060006d2ed000 0000000000000140 > 7e80: ffff200009cff000 ffff200009cb6000 ffff200009cc2020 ffff200009d2159d > 7ea0: 0000000000000000 ffff8000648d4380 0000000000000000 ffff8000648e7f00 > 7ec0: ffff20000820a478 ffff8000648e7f00 ffff20000820a47c 0000000010000145 > 7ee0: 0000000000000140 dfff200000000000 ffffffffffffffff ffff20000820a478 > [] el1_irq+0xb8/0x130 arch/arm64/kernel/entry.S:486 > [< inline >] arch_local_irq_restore > ./arch/arm64/include/asm/irqflags.h:81 > [] rcu_idle_exit+0x64/0xa8 kernel/rcu/tree.c:1030 > [< inline >] cpuidle_idle_call kernel/sched/idle.c:200 > [] do_idle+0x1dc/0x2d0 kernel/sched/idle.c:243 > [] cpu_startup_entry+0x24/0x28 kernel/sched/idle.c:345 > [] secondary_start_kernel+0x2cc/0x358 > arch/arm64/kernel/smp.c:276 > [<000000000279f1a4>] 0x279f1a4 Reported-by: Dmitry Vyukov Tested-by: Dmitry Vyukov Fixes: add7c65ca426 ("pid: fix lockdep deadlock warning due to ucount_lock") Fixes: f333c700c610 ("pidns: Add a limit on the number of pid namespaces") Cc: stable@vger.kernel.org Link: https://www.spinics.net/lists/kernel/msg2426637.html Signed-off-by: Nikolay Borisov Signed-off-by: Eric W. Biederman --- kernel/ucount.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/ucount.c b/kernel/ucount.c index 9d20d5dd298a..4bbd38ec3788 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -128,10 +128,10 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid) struct hlist_head *hashent = ucounts_hashentry(ns, uid); struct ucounts *ucounts, *new; - spin_lock(&ucounts_lock); + spin_lock_irq(&ucounts_lock); ucounts = find_ucounts(ns, uid, hashent); if (!ucounts) { - spin_unlock(&ucounts_lock); + spin_unlock_irq(&ucounts_lock); new = kzalloc(sizeof(*new), GFP_KERNEL); if (!new) @@ -141,7 +141,7 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid) new->uid = uid; atomic_set(&new->count, 0); - spin_lock(&ucounts_lock); + spin_lock_irq(&ucounts_lock); ucounts = find_ucounts(ns, uid, hashent); if (ucounts) { kfree(new); @@ -152,16 +152,18 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid) } if (!atomic_add_unless(&ucounts->count, 1, INT_MAX)) ucounts = NULL; - spin_unlock(&ucounts_lock); + spin_unlock_irq(&ucounts_lock); return ucounts; } static void put_ucounts(struct ucounts *ucounts) { + unsigned long flags; + if (atomic_dec_and_test(&ucounts->count)) { - spin_lock(&ucounts_lock); + spin_lock_irqsave(&ucounts_lock, flags); hlist_del_init(&ucounts->node); - spin_unlock(&ucounts_lock); + spin_unlock_irqrestore(&ucounts_lock, flags); kfree(ucounts); } -- cgit v1.2.3 From b94f51183b0617e7b9b4fb4137d4cf1cab7547c2 Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Tue, 24 Jan 2017 15:17:53 -0800 Subject: kernel/watchdog: prevent false hardlockup on overloaded system On an overloaded system, it is possible that a change in the watchdog threshold can be delayed long enough to trigger a false positive. This can easily be achieved by having a cpu spinning indefinitely on a task, while another cpu updates watchdog threshold. What happens is while trying to park the watchdog threads, the hrtimers on the other cpus trigger and reprogram themselves with the new slower watchdog threshold. Meanwhile, the nmi watchdog is still programmed with the old faster threshold. Because the one cpu is blocked, it prevents the thread parking on the other cpus from completing, which is needed to shutdown the nmi watchdog and reprogram it correctly. As a result, a false positive from the nmi watchdog is reported. Fix this by setting a park_in_progress flag to block all lockups until the parking is complete. Fix provided by Ulrich Obergfell. [akpm@linux-foundation.org: s/park_in_progress/watchdog_park_in_progress/] Link: http://lkml.kernel.org/r/1481041033-192236-1-git-send-email-dzickus@redhat.com Signed-off-by: Don Zickus Reviewed-by: Aaron Tomlin Cc: Ulrich Obergfell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/watchdog.c | 9 +++++++++ kernel/watchdog_hld.c | 3 +++ 2 files changed, 12 insertions(+) (limited to 'kernel') diff --git a/kernel/watchdog.c b/kernel/watchdog.c index d4b0fa01cae3..63177be0159e 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -49,6 +49,8 @@ unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); #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 @@ -260,6 +262,9 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) int duration; int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace; + if (atomic_read(&watchdog_park_in_progress) != 0) + return HRTIMER_NORESTART; + /* kick the hardlockup detector */ watchdog_interrupt_count(); @@ -467,12 +472,16 @@ static int watchdog_park_threads(void) { int cpu, ret = 0; + atomic_set(&watchdog_park_in_progress, 1); + for_each_watchdog_cpu(cpu) { ret = kthread_park(per_cpu(softlockup_watchdog, cpu)); if (ret) break; } + atomic_set(&watchdog_park_in_progress, 0); + return ret; } diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 84016c8aee6b..12b8dd640786 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -84,6 +84,9 @@ static void watchdog_overflow_callback(struct perf_event *event, /* Ensure the watchdog never gets throttled */ event->hw.interrupts = 0; + if (atomic_read(&watchdog_park_in_progress) != 0) + return; + if (__this_cpu_read(watchdog_nmi_touch) == true) { __this_cpu_write(watchdog_nmi_touch, false); return; -- cgit v1.2.3 From ff7a28a074ccbea999dadbb58c46212cf90984c6 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Tue, 24 Jan 2017 15:18:29 -0800 Subject: kernel/panic.c: add missing \n When a system panics, the "Rebooting in X seconds.." message is never printed because it lacks a new line. Fix it. Link: http://lkml.kernel.org/r/20170119114751.2724-1-jslaby@suse.cz Signed-off-by: Jiri Slaby Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/panic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/panic.c b/kernel/panic.c index 901c4fb46002..08aa88dde7de 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -249,7 +249,7 @@ void panic(const char *fmt, ...) * Delay timeout seconds before rebooting the machine. * We can't use the "normal" timers since we just panicked. */ - pr_emerg("Rebooting in %d seconds..", panic_timeout); + pr_emerg("Rebooting in %d seconds..\n", panic_timeout); for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) { touch_nmi_watchdog(); -- cgit v1.2.3 From ff9f8a7cf935468a94d9927c68b00daae701667e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 25 Jan 2017 18:20:55 -0800 Subject: sysctl: fix proc_doulongvec_ms_jiffies_minmax() We perform the conversion between kernel jiffies and ms only when exporting kernel value to user space. We need to do the opposite operation when value is written by user. Only matters when HZ != 1000 Signed-off-by: Eric Dumazet Cc: stable@vger.kernel.org Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 8dbaec0e4f7f..1aea594a54db 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2475,6 +2475,7 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int break; if (neg) continue; + val = convmul * val / convdiv; if ((min && val < *min) || (max && val > *max)) continue; *i = val; -- cgit v1.2.3