Merge tag 'v3.12' into core/locking to pick up mutex upates

Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/audit.c

@@ -1117,9 +1117,10 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
 
 			sleep_time = timeout_start + audit_backlog_wait_time -
 					jiffies;
-			if ((long)sleep_time > 0)
+			if ((long)sleep_time > 0) {
 				wait_for_auditd(sleep_time);
-			continue;
+				continue;
+			}
 		}
 		if (audit_rate_check() && printk_ratelimit())
 			printk(KERN_WARNING

kernel/cgroup.c

@@ -2039,7 +2039,7 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk,
 
 		/* @tsk either already exited or can't exit until the end */
 		if (tsk->flags & PF_EXITING)
-			continue;
+			goto next;
 
 		/* as per above, nr_threads may decrease, but not increase. */
 		BUG_ON(i >= group_size);
@@ -2047,7 +2047,7 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk,
 		ent.cgrp = task_cgroup_from_root(tsk, root);
 		/* nothing to do if this task is already in the cgroup */
 		if (ent.cgrp == cgrp)
-			continue;
+			goto next;
 		/*
 		 * saying GFP_ATOMIC has no effect here because we did prealloc
 		 * earlier, but it's good form to communicate our expectations.
@@ -2055,7 +2055,7 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk,
 		retval = flex_array_put(group, i, &ent, GFP_ATOMIC);
 		BUG_ON(retval != 0);
 		i++;
-
+	next:
 		if (!threadgroup)
 			break;
 	} while_each_thread(leader, tsk);
@@ -3188,11 +3188,9 @@ css_next_descendant_post(struct cgroup_subsys_state *pos,
 
 	WARN_ON_ONCE(!rcu_read_lock_held());
 
-	/* if first iteration, visit the leftmost descendant */
-	if (!pos) {
-		next = css_leftmost_descendant(root);
-		return next != root ? next : NULL;
-	}
+	/* if first iteration, visit leftmost descendant which may be @root */
+	if (!pos)
+		return css_leftmost_descendant(root);
 
 	/* if we visited @root, we're done */
 	if (pos == root)

kernel/context_tracking.c

@@ -50,6 +50,15 @@ void context_tracking_user_enter(void)
 {
 	unsigned long flags;
 
+	/*
+	 * Repeat the user_enter() check here because some archs may be calling
+	 * this from asm and if no CPU needs context tracking, they shouldn't
+	 * go further. Repeat the check here until they support the static key
+	 * check.
+	 */
+	if (!static_key_false(&context_tracking_enabled))
+		return;
+
 	/*
 	 * Some contexts may involve an exception occuring in an irq,
 	 * leading to that nesting:
@@ -151,6 +160,9 @@ void context_tracking_user_exit(void)
 {
 	unsigned long flags;
 
+	if (!static_key_false(&context_tracking_enabled))
+		return;
+
 	if (in_interrupt())
 		return;
 

kernel/events/core.c

@@ -3660,6 +3660,26 @@ static void calc_timer_values(struct perf_event *event,
 	*running = ctx_time - event->tstamp_running;
 }
 
+static void perf_event_init_userpage(struct perf_event *event)
+{
+	struct perf_event_mmap_page *userpg;
+	struct ring_buffer *rb;
+
+	rcu_read_lock();
+	rb = rcu_dereference(event->rb);
+	if (!rb)
+		goto unlock;
+
+	userpg = rb->user_page;
+
+	/* Allow new userspace to detect that bit 0 is deprecated */
+	userpg->cap_bit0_is_deprecated = 1;
+	userpg->size = offsetof(struct perf_event_mmap_page, __reserved);
+
+unlock:
+	rcu_read_unlock();
+}
+
 void __weak arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
 {
 }
@@ -4044,6 +4064,7 @@ again:
 	ring_buffer_attach(event, rb);
 	rcu_assign_pointer(event->rb, rb);
 
+	perf_event_init_userpage(event);
 	perf_event_update_userpage(event);
 
 unlock:
@@ -6746,6 +6767,10 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 	if (ret)
 		return -EFAULT;
 
+	/* disabled for now */
+	if (attr->mmap2)
+		return -EINVAL;
+
 	if (attr->__reserved_1)
 		return -EINVAL;
 
@@ -7213,15 +7238,15 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
 		perf_remove_from_context(event);
 		unaccount_event_cpu(event, src_cpu);
 		put_ctx(src_ctx);
-		list_add(&event->event_entry, &events);
+		list_add(&event->migrate_entry, &events);
 	}
 	mutex_unlock(&src_ctx->mutex);
 
 	synchronize_rcu();
 
 	mutex_lock(&dst_ctx->mutex);
-	list_for_each_entry_safe(event, tmp, &events, event_entry) {
-		list_del(&event->event_entry);
+	list_for_each_entry_safe(event, tmp, &events, migrate_entry) {
+		list_del(&event->migrate_entry);
 		if (event->state >= PERF_EVENT_STATE_OFF)
 			event->state = PERF_EVENT_STATE_INACTIVE;
 		account_event_cpu(event, dst_cpu);

kernel/events/ring_buffer.c

@@ -87,10 +87,31 @@ again:
 		goto out;
 
 	/*
-	 * Publish the known good head. Rely on the full barrier implied
-	 * by atomic_dec_and_test() order the rb->head read and this
-	 * write.
+	 * Since the mmap() consumer (userspace) can run on a different CPU:
+	 *
+	 *   kernel				user
+	 *
+	 *   READ ->data_tail			READ ->data_head
+	 *   smp_mb()	(A)			smp_rmb()	(C)
+	 *   WRITE $data			READ $data
+	 *   smp_wmb()	(B)			smp_mb()	(D)
+	 *   STORE ->data_head			WRITE ->data_tail
+	 *
+	 * Where A pairs with D, and B pairs with C.
+	 *
+	 * I don't think A needs to be a full barrier because we won't in fact
+	 * write data until we see the store from userspace. So we simply don't
+	 * issue the data WRITE until we observe it. Be conservative for now.
+	 *
+	 * OTOH, D needs to be a full barrier since it separates the data READ
+	 * from the tail WRITE.
+	 *
+	 * For B a WMB is sufficient since it separates two WRITEs, and for C
+	 * an RMB is sufficient since it separates two READs.
+	 *
+	 * See perf_output_begin().
 	 */
+	smp_wmb();
 	rb->user_page->data_head = head;
 
 	/*
@@ -154,9 +175,11 @@ int perf_output_begin(struct perf_output_handle *handle,
 		 * Userspace could choose to issue a mb() before updating the
 		 * tail pointer. So that all reads will be completed before the
 		 * write is issued.
+		 *
+		 * See perf_output_put_handle().
 		 */
 		tail = ACCESS_ONCE(rb->user_page->data_tail);
-		smp_rmb();
+		smp_mb();
 		offset = head = local_read(&rb->head);
 		head += size;
 		if (unlikely(!perf_output_space(rb, tail, offset, head)))

kernel/kmod.c

@@ -571,6 +571,10 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait)
 	DECLARE_COMPLETION_ONSTACK(done);
 	int retval = 0;
 
+	if (!sub_info->path) {
+		call_usermodehelper_freeinfo(sub_info);
+		return -EINVAL;
+	}
 	helper_lock();
 	if (!khelper_wq || usermodehelper_disabled) {
 		retval = -EBUSY;

kernel/mutex.c

@@ -410,7 +410,7 @@ ww_mutex_set_context_fastpath(struct ww_mutex *lock,
 static __always_inline int __sched
 __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		    struct lockdep_map *nest_lock, unsigned long ip,
-		    struct ww_acquire_ctx *ww_ctx)
+		    struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx)
 {
 	struct task_struct *task = current;
 	struct mutex_waiter waiter;
@@ -450,7 +450,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		struct task_struct *owner;
 		struct mspin_node  node;
 
-		if (!__builtin_constant_p(ww_ctx == NULL) && ww_ctx->acquired > 0) {
+		if (use_ww_ctx && ww_ctx->acquired > 0) {
 			struct ww_mutex *ww;
 
 			ww = container_of(lock, struct ww_mutex, base);
@@ -480,7 +480,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		if ((atomic_read(&lock->count) == 1) &&
 		    (atomic_cmpxchg(&lock->count, 1, 0) == 1)) {
 			lock_acquired(&lock->dep_map, ip);
-			if (!__builtin_constant_p(ww_ctx == NULL)) {
+			if (use_ww_ctx) {
 				struct ww_mutex *ww;
 				ww = container_of(lock, struct ww_mutex, base);
 
@@ -551,7 +551,7 @@ slowpath:
 			goto err;
 		}
 
-		if (!__builtin_constant_p(ww_ctx == NULL) && ww_ctx->acquired > 0) {
+		if (use_ww_ctx && ww_ctx->acquired > 0) {
 			ret = __mutex_lock_check_stamp(lock, ww_ctx);
 			if (ret)
 				goto err;
@@ -575,7 +575,7 @@ skip_wait:
 	lock_acquired(&lock->dep_map, ip);
 	mutex_set_owner(lock);
 
-	if (!__builtin_constant_p(ww_ctx == NULL)) {
+	if (use_ww_ctx) {
 		struct ww_mutex *ww = container_of(lock, struct ww_mutex, base);
 		struct mutex_waiter *cur;
 
@@ -615,7 +615,7 @@ mutex_lock_nested(struct mutex *lock, unsigned int subclass)
 {
 	might_sleep();
 	__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE,
-			    subclass, NULL, _RET_IP_, NULL);
+			    subclass, NULL, _RET_IP_, NULL, 0);
 }
 
 EXPORT_SYMBOL_GPL(mutex_lock_nested);
@@ -625,7 +625,7 @@ _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest)
 {
 	might_sleep();
 	__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE,
-			    0, nest, _RET_IP_, NULL);
+			    0, nest, _RET_IP_, NULL, 0);
 }
 
 EXPORT_SYMBOL_GPL(_mutex_lock_nest_lock);
@@ -635,7 +635,7 @@ mutex_lock_killable_nested(struct mutex *lock, unsigned int subclass)
 {
 	might_sleep();
 	return __mutex_lock_common(lock, TASK_KILLABLE,
-				   subclass, NULL, _RET_IP_, NULL);
+				   subclass, NULL, _RET_IP_, NULL, 0);
 }
 EXPORT_SYMBOL_GPL(mutex_lock_killable_nested);
 
@@ -644,7 +644,7 @@ mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass)
 {
 	might_sleep();
 	return __mutex_lock_common(lock, TASK_INTERRUPTIBLE,
-				   subclass, NULL, _RET_IP_, NULL);
+				   subclass, NULL, _RET_IP_, NULL, 0);
 }
 
 EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested);
@@ -682,7 +682,7 @@ __ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
 
 	might_sleep();
 	ret =  __mutex_lock_common(&lock->base, TASK_UNINTERRUPTIBLE,
-				   0, &ctx->dep_map, _RET_IP_, ctx);
+				   0, &ctx->dep_map, _RET_IP_, ctx, 1);
 	if (!ret && ctx->acquired > 1)
 		return ww_mutex_deadlock_injection(lock, ctx);
 
@@ -697,7 +697,7 @@ __ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
 
 	might_sleep();
 	ret = __mutex_lock_common(&lock->base, TASK_INTERRUPTIBLE,
-				  0, &ctx->dep_map, _RET_IP_, ctx);
+				  0, &ctx->dep_map, _RET_IP_, ctx, 1);
 
 	if (!ret && ctx->acquired > 1)
 		return ww_mutex_deadlock_injection(lock, ctx);
@@ -809,28 +809,28 @@ __mutex_lock_slowpath(atomic_t *lock_count)
 	struct mutex *lock = container_of(lock_count, struct mutex, count);
 
 	__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0,
-			    NULL, _RET_IP_, NULL);
+			    NULL, _RET_IP_, NULL, 0);
 }
 
 static noinline int __sched
 __mutex_lock_killable_slowpath(struct mutex *lock)
 {
 	return __mutex_lock_common(lock, TASK_KILLABLE, 0,
-				   NULL, _RET_IP_, NULL);
+				   NULL, _RET_IP_, NULL, 0);
 }
 
 static noinline int __sched
 __mutex_lock_interruptible_slowpath(struct mutex *lock)
 {
 	return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0,
-				   NULL, _RET_IP_, NULL);
+				   NULL, _RET_IP_, NULL, 0);
 }
 
 static noinline int __sched
 __ww_mutex_lock_slowpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
 {
 	return __mutex_lock_common(&lock->base, TASK_UNINTERRUPTIBLE, 0,
-				   NULL, _RET_IP_, ctx);
+				   NULL, _RET_IP_, ctx, 1);
 }
 
 static noinline int __sched
@@ -838,7 +838,7 @@ __ww_mutex_lock_interruptible_slowpath(struct ww_mutex *lock,
 					    struct ww_acquire_ctx *ctx)
 {
 	return __mutex_lock_common(&lock->base, TASK_INTERRUPTIBLE, 0,
-				   NULL, _RET_IP_, ctx);
+				   NULL, _RET_IP_, ctx, 1);
 }
 
 #endif

kernel/params.c

@@ -254,11 +254,11 @@ int parse_args(const char *doing,
 
 
 STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", unsigned long, kstrtoul);
-STANDARD_PARAM_DEF(short, short, "%hi", long, kstrtoul);
+STANDARD_PARAM_DEF(short, short, "%hi", long, kstrtol);
 STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", unsigned long, kstrtoul);
-STANDARD_PARAM_DEF(int, int, "%i", long, kstrtoul);
+STANDARD_PARAM_DEF(int, int, "%i", long, kstrtol);
 STANDARD_PARAM_DEF(uint, unsigned int, "%u", unsigned long, kstrtoul);
-STANDARD_PARAM_DEF(long, long, "%li", long, kstrtoul);
+STANDARD_PARAM_DEF(long, long, "%li", long, kstrtol);
 STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", unsigned long, kstrtoul);
 
 int param_set_charp(const char *val, const struct kernel_param *kp)

kernel/pid.c

@@ -273,6 +273,11 @@ void free_pid(struct pid *pid)
 			 */
 			wake_up_process(ns->child_reaper);
 			break;
+		case PIDNS_HASH_ADDING:
+			/* Handle a fork failure of the first process */
+			WARN_ON(ns->child_reaper);
+			ns->nr_hashed = 0;
+			/* fall through */
 		case 0:
 			schedule_work(&ns->proc_work);
 			break;

kernel/power/hibernate.c

@@ -846,7 +846,7 @@ static int software_resume(void)
 	goto Finish;
 }
 
-late_initcall(software_resume);
+late_initcall_sync(software_resume);
 
 
 static const char * const hibernation_modes[] = {

kernel/power/snapshot.c

@@ -743,7 +743,10 @@ int create_basic_memory_bitmaps(void)
 	struct memory_bitmap *bm1, *bm2;
 	int error = 0;
 
-	BUG_ON(forbidden_pages_map || free_pages_map);
+	if (forbidden_pages_map && free_pages_map)
+		return 0;
+	else
+		BUG_ON(forbidden_pages_map || free_pages_map);
 
 	bm1 = kzalloc(sizeof(struct memory_bitmap), GFP_KERNEL);
 	if (!bm1)

kernel/power/user.c

@@ -39,6 +39,7 @@ static struct snapshot_data {
 	char frozen;
 	char ready;
 	char platform_support;
+	bool free_bitmaps;
 } snapshot_state;
 
 atomic_t snapshot_device_available = ATOMIC_INIT(1);
@@ -82,6 +83,10 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 		data->swap = -1;
 		data->mode = O_WRONLY;
 		error = pm_notifier_call_chain(PM_RESTORE_PREPARE);
+		if (!error) {
+			error = create_basic_memory_bitmaps();
+			data->free_bitmaps = !error;
+		}
 		if (error)
 			pm_notifier_call_chain(PM_POST_RESTORE);
 	}
@@ -111,6 +116,8 @@ static int snapshot_release(struct inode *inode, struct file *filp)
 		pm_restore_gfp_mask();
 		free_basic_memory_bitmaps();
 		thaw_processes();
+	} else if (data->free_bitmaps) {
+		free_basic_memory_bitmaps();
 	}
 	pm_notifier_call_chain(data->mode == O_RDONLY ?
 			PM_POST_HIBERNATION : PM_POST_RESTORE);
@@ -231,6 +238,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 			break;
 		pm_restore_gfp_mask();
 		free_basic_memory_bitmaps();
+		data->free_bitmaps = false;
 		thaw_processes();
 		data->frozen = 0;
 		break;

kernel/reboot.c

@@ -32,7 +32,14 @@ EXPORT_SYMBOL(cad_pid);
 #endif
 enum reboot_mode reboot_mode DEFAULT_REBOOT_MODE;
 
-int reboot_default;
+/*
+ * This variable is used privately to keep track of whether or not
+ * reboot_type is still set to its default value (i.e., reboot= hasn't
+ * been set on the command line).  This is needed so that we can
+ * suppress DMI scanning for reboot quirks.  Without it, it's
+ * impossible to override a faulty reboot quirk without recompiling.
+ */
+int reboot_default = 1;
 int reboot_cpu;
 enum reboot_type reboot_type = BOOT_ACPI;
 int reboot_force;

kernel/sched/fair.c

@@ -4242,7 +4242,7 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq)
 	}
 
 	if (!se) {
-		cfs_rq->h_load = rq->avg.load_avg_contrib;
+		cfs_rq->h_load = cfs_rq->runnable_load_avg;
 		cfs_rq->last_h_load_update = now;
 	}
 
@@ -4823,8 +4823,8 @@ void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
 		(busiest->load_per_task * SCHED_POWER_SCALE) /
 		busiest->group_power;
 
-	if (busiest->avg_load - local->avg_load + scaled_busy_load_per_task >=
-	    (scaled_busy_load_per_task * imbn)) {
+	if (busiest->avg_load + scaled_busy_load_per_task >=
+	    local->avg_load + (scaled_busy_load_per_task * imbn)) {
 		env->imbalance = busiest->load_per_task;
 		return;
 	}
@@ -4896,7 +4896,8 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 	 * max load less than avg load(as we skip the groups at or below
 	 * its cpu_power, while calculating max_load..)
 	 */
-	if (busiest->avg_load < sds->avg_load) {
+	if (busiest->avg_load <= sds->avg_load ||
+	    local->avg_load >= sds->avg_load) {
 		env->imbalance = 0;
 		return fix_small_imbalance(env, sds);
 	}

kernel/softirq.c

@@ -328,10 +328,19 @@ void irq_enter(void)
 
 static inline void invoke_softirq(void)
 {
-	if (!force_irqthreads)
-		__do_softirq();
-	else
+	if (!force_irqthreads) {
+		/*
+		 * We can safely execute softirq on the current stack if
+		 * it is the irq stack, because it should be near empty
+		 * at this stage. But we have no way to know if the arch
+		 * calls irq_exit() on the irq stack. So call softirq
+		 * in its own stack to prevent from any overrun on top
+		 * of a potentially deep task stack.
+		 */
+		do_softirq();
+	} else {
 		wakeup_softirqd();
+	}
 }
 
 static inline void tick_irq_exit(void)

kernel/time/clockevents.c

@@ -33,6 +33,54 @@ struct ce_unbind {
 	int res;
 };
 
+static u64 cev_delta2ns(unsigned long latch, struct clock_event_device *evt,
+			bool ismax)
+{
+	u64 clc = (u64) latch << evt->shift;
+	u64 rnd;
+
+	if (unlikely(!evt->mult)) {
+		evt->mult = 1;
+		WARN_ON(1);
+	}
+	rnd = (u64) evt->mult - 1;
+
+	/*
+	 * Upper bound sanity check. If the backwards conversion is
+	 * not equal latch, we know that the above shift overflowed.
+	 */
+	if ((clc >> evt->shift) != (u64)latch)
+		clc = ~0ULL;
+
+	/*
+	 * Scaled math oddities:
+	 *
+	 * For mult <= (1 << shift) we can safely add mult - 1 to
+	 * prevent integer rounding loss. So the backwards conversion
+	 * from nsec to device ticks will be correct.
+	 *
+	 * For mult > (1 << shift), i.e. device frequency is > 1GHz we
+	 * need to be careful. Adding mult - 1 will result in a value
+	 * which when converted back to device ticks can be larger
+	 * than latch by up to (mult - 1) >> shift. For the min_delta
+	 * calculation we still want to apply this in order to stay
+	 * above the minimum device ticks limit. For the upper limit
+	 * we would end up with a latch value larger than the upper
+	 * limit of the device, so we omit the add to stay below the
+	 * device upper boundary.
+	 *
+	 * Also omit the add if it would overflow the u64 boundary.
+	 */
+	if ((~0ULL - clc > rnd) &&
+	    (!ismax || evt->mult <= (1U << evt->shift)))
+		clc += rnd;
+
+	do_div(clc, evt->mult);
+
+	/* Deltas less than 1usec are pointless noise */
+	return clc > 1000 ? clc : 1000;
+}
+
 /**
  * clockevents_delta2ns - Convert a latch value (device ticks) to nanoseconds
  * @latch:	value to convert
@@ -42,20 +90,7 @@ struct ce_unbind {
  */
 u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt)
 {
-	u64 clc = (u64) latch << evt->shift;
-
-	if (unlikely(!evt->mult)) {
-		evt->mult = 1;
-		WARN_ON(1);
-	}
-
-	do_div(clc, evt->mult);
-	if (clc < 1000)
-		clc = 1000;
-	if (clc > KTIME_MAX)
-		clc = KTIME_MAX;
-
-	return clc;
+	return cev_delta2ns(latch, evt, false);
 }
 EXPORT_SYMBOL_GPL(clockevent_delta2ns);
 
@@ -380,8 +415,8 @@ void clockevents_config(struct clock_event_device *dev, u32 freq)
 		sec = 600;
 
 	clockevents_calc_mult_shift(dev, freq, sec);
-	dev->min_delta_ns = clockevent_delta2ns(dev->min_delta_ticks, dev);
-	dev->max_delta_ns = clockevent_delta2ns(dev->max_delta_ticks, dev);
+	dev->min_delta_ns = cev_delta2ns(dev->min_delta_ticks, dev, false);
+	dev->max_delta_ns = cev_delta2ns(dev->max_delta_ticks, dev, true);
 }
 
 /**

kernel/watchdog.c

@@ -486,7 +486,52 @@ static struct smp_hotplug_thread watchdog_threads = {
 	.unpark			= watchdog_enable,
 };
 
-static int watchdog_enable_all_cpus(void)
+static void restart_watchdog_hrtimer(void *info)
+{
+	struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer);
+	int ret;
+
+	/*
+	 * No need to cancel and restart hrtimer if it is currently executing
+	 * because it will reprogram itself with the new period now.
+	 * We should never see it unqueued here because we are running per-cpu
+	 * with interrupts disabled.
+	 */
+	ret = hrtimer_try_to_cancel(hrtimer);
+	if (ret == 1)
+		hrtimer_start(hrtimer, ns_to_ktime(sample_period),
+				HRTIMER_MODE_REL_PINNED);
+}
+
+static void update_timers(int cpu)
+{
+	struct call_single_data data = {.func = restart_watchdog_hrtimer};
+	/*
+	 * Make sure that perf event counter will adopt to a new
+	 * sampling period. Updating the sampling period directly would
+	 * be much nicer but we do not have an API for that now so
+	 * let's use a big hammer.
+	 * Hrtimer will adopt the new period on the next tick but this
+	 * might be late already so we have to restart the timer as well.
+	 */
+	watchdog_nmi_disable(cpu);
+	__smp_call_function_single(cpu, &data, 1);
+	watchdog_nmi_enable(cpu);
+}
+
+static void update_timers_all_cpus(void)
+{
+	int cpu;
+
+	get_online_cpus();
+	preempt_disable();
+	for_each_online_cpu(cpu)
+		update_timers(cpu);
+	preempt_enable();
+	put_online_cpus();
+}
+
+static int watchdog_enable_all_cpus(bool sample_period_changed)
 {
 	int err = 0;
 
@@ -496,6 +541,8 @@ static int watchdog_enable_all_cpus(void)
 			pr_err("Failed to create watchdog threads, disabled\n");
 		else
 			watchdog_running = 1;
+	} else if (sample_period_changed) {
+		update_timers_all_cpus();
 	}
 
 	return err;
@@ -520,13 +567,15 @@ int proc_dowatchdog(struct ctl_table *table, int write,
 		    void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	int err, old_thresh, old_enabled;
+	static DEFINE_MUTEX(watchdog_proc_mutex);
 
+	mutex_lock(&watchdog_proc_mutex);
 	old_thresh = ACCESS_ONCE(watchdog_thresh);
 	old_enabled = ACCESS_ONCE(watchdog_user_enabled);
 
 	err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	if (err || !write)
-		return err;
+		goto out;
 
 	set_sample_period();
 	/*
@@ -535,7 +584,7 @@ int proc_dowatchdog(struct ctl_table *table, int write,
 	 * watchdog_*_all_cpus() function takes care of this.
 	 */
 	if (watchdog_user_enabled && watchdog_thresh)
-		err = watchdog_enable_all_cpus();
+		err = watchdog_enable_all_cpus(old_thresh != watchdog_thresh);
 	else
 		watchdog_disable_all_cpus();
 
@@ -544,7 +593,8 @@ int proc_dowatchdog(struct ctl_table *table, int write,
 		watchdog_thresh = old_thresh;
 		watchdog_user_enabled = old_enabled;
 	}
-
+out:
+	mutex_unlock(&watchdog_proc_mutex);
 	return err;
 }
 #endif /* CONFIG_SYSCTL */
@@ -554,5 +604,5 @@ void __init lockup_detector_init(void)
 	set_sample_period();
 
 	if (watchdog_user_enabled)
-		watchdog_enable_all_cpus();
+		watchdog_enable_all_cpus(false);
 }