8 files changed, 94 insertions, 59 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 81aa3a4ece9f..1a3bf48743ce 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -913,10 +913,30 @@ static void put_ctx(struct perf_event_context *ctx)
  * Those places that change perf_event::ctx will hold both
  * perf_event_ctx::mutex of the 'old' and 'new' ctx value.
  *
- * Lock ordering is by mutex address. There is one other site where
- * perf_event_context::mutex nests and that is put_event(). But remember that
- * that is a parent<->child context relation, and migration does not affect
- * children, therefore these two orderings should not interact.
+ * Lock ordering is by mutex address. There are two other sites where
+ * perf_event_context::mutex nests and those are:
+ *
+ *  - perf_event_exit_task_context()    [ child , 0 ]
+ *      __perf_event_exit_task()
+ *        sync_child_event()
+ *          put_event()                 [ parent, 1 ]
+ *
+ *  - perf_event_init_context()         [ parent, 0 ]
+ *      inherit_task_group()
+ *        inherit_group()
+ *          inherit_event()
+ *            perf_event_alloc()
+ *              perf_init_event()
+ *                perf_try_init_event() [ child , 1 ]
+ *
+ * While it appears there is an obvious deadlock here -- the parent and child
+ * nesting levels are inverted between the two. This is in fact safe because
+ * life-time rules separate them. That is an exiting task cannot fork, and a
+ * spawning task cannot (yet) exit.
+ *
+ * But remember that that these are parent<->child context relations, and
+ * migration does not affect children, therefore these two orderings should not
+ * interact.
  *
  * The change in perf_event::ctx does not affect children (as claimed above)
  * because the sys_perf_event_open() case will install a new event and break
@@ -3657,9 +3677,6 @@ static void perf_remove_from_owner(struct perf_event *event)
         }
 }
 
-/*
- * Called when the last reference to the file is gone.
- */
 static void put_event(struct perf_event *event)
 {
         struct perf_event_context *ctx;
@@ -3697,6 +3714,9 @@ int perf_event_release_kernel(struct perf_event *event)
 }
 EXPORT_SYMBOL_GPL(perf_event_release_kernel);
 
+/*
+ * Called when the last reference to the file is gone.
+ */
 static int perf_release(struct inode *inode, struct file *file)
 {
         put_event(file->private_data);
@@ -7364,7 +7384,12 @@ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event)
                 return -ENODEV;
 
         if (event->group_leader != event) {
-                ctx = perf_event_ctx_lock(event->group_leader);
+                /*
+                 * This ctx->mutex can nest when we're called through
+                 * inheritance. See the perf_event_ctx_lock_nested() comment.
+                 */
+                ctx = perf_event_ctx_lock_nested(event->group_leader,
+                                                 SINGLE_DEPTH_NESTING);
                 BUG_ON(!ctx);
         }
 
diff --git a/kernel/irq/dummychip.c b/kernel/irq/dummychip.c
index 988dc58e8847..2feb6feca0cc 100644
--- a/kernel/irq/dummychip.c
+++ b/kernel/irq/dummychip.c
@@ -57,5 +57,6 @@ struct irq_chip dummy_irq_chip = {
         .irq_ack        = noop,
         .irq_mask       = noop,
         .irq_unmask     = noop,
+        .flags          = IRQCHIP_SKIP_SET_WAKE,
 };
 EXPORT_SYMBOL_GPL(dummy_irq_chip);
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index b73279367087..b025295f4966 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -265,15 +265,17 @@ struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
 }
 
 /*
- * Called by sched_setscheduler() to check whether the priority change
- * is overruled by a possible priority boosting.
+ * Called by sched_setscheduler() to get the priority which will be
+ * effective after the change.
  */
-int rt_mutex_check_prio(struct task_struct *task, int newprio)
+int rt_mutex_get_effective_prio(struct task_struct *task, int newprio)
 {
         if (!task_has_pi_waiters(task))
-                return 0;
+                return newprio;
 
-        return task_top_pi_waiter(task)->task->prio <= newprio;
+        if (task_top_pi_waiter(task)->task->prio <= newprio)
+                return task_top_pi_waiter(task)->task->prio;
+        return newprio;
 }
 
 /*
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 233165da782f..8cf7304b2867 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -162,11 +162,14 @@ static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp);
 static int kthread_prio = CONFIG_RCU_KTHREAD_PRIO;
 module_param(kthread_prio, int, 0644);
 
-/* Delay in jiffies for grace-period initialization delays. */
-static int gp_init_delay = IS_ENABLED(CONFIG_RCU_TORTURE_TEST_SLOW_INIT)
-                                ? CONFIG_RCU_TORTURE_TEST_SLOW_INIT_DELAY
-                                : 0;
+/* Delay in jiffies for grace-period initialization delays, debug only. */
+#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT
+static int gp_init_delay = CONFIG_RCU_TORTURE_TEST_SLOW_INIT_DELAY;
 module_param(gp_init_delay, int, 0644);
+#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */
+static const int gp_init_delay;
+#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */
+#define PER_RCU_NODE_PERIOD 10  /* Number of grace periods between delays. */
 
 /*
  * Track the rcutorture test sequence number and the update version
@@ -1843,9 +1846,8 @@ static int rcu_gp_init(struct rcu_state *rsp)
                 raw_spin_unlock_irq(&rnp->lock);
                 cond_resched_rcu_qs();
                 ACCESS_ONCE(rsp->gp_activity) = jiffies;
-                if (IS_ENABLED(CONFIG_RCU_TORTURE_TEST_SLOW_INIT) &&
-                    gp_init_delay > 0 &&
-                    !(rsp->gpnum % (rcu_num_nodes * 10)))
+                if (gp_init_delay > 0 &&
+                    !(rsp->gpnum % (rcu_num_nodes * PER_RCU_NODE_PERIOD)))
                         schedule_timeout_uninterruptible(gp_init_delay);
         }
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index fe22f7510bce..57bd333bc4ab 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3300,15 +3300,18 @@ static void __setscheduler_params(struct task_struct *p,
 
 /* Actually do priority change: must hold pi & rq lock. */
 static void __setscheduler(struct rq *rq, struct task_struct *p,
-                           const struct sched_attr *attr)
+                           const struct sched_attr *attr, bool keep_boost)
 {
         __setscheduler_params(p, attr);
 
         /*
-         * If we get here, there was no pi waiters boosting the
-         * task. It is safe to use the normal prio.
+         * Keep a potential priority boosting if called from
+         * sched_setscheduler().
          */
-        p->prio = normal_prio(p);
+        if (keep_boost)
+                p->prio = rt_mutex_get_effective_prio(p, normal_prio(p));
+        else
+                p->prio = normal_prio(p);
 
         if (dl_prio(p->prio))
                 p->sched_class = &dl_sched_class;
@@ -3408,7 +3411,7 @@ static int __sched_setscheduler(struct task_struct *p,
         int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 :
                       MAX_RT_PRIO - 1 - attr->sched_priority;
         int retval, oldprio, oldpolicy = -1, queued, running;
-        int policy = attr->sched_policy;
+        int new_effective_prio, policy = attr->sched_policy;
         unsigned long flags;
         const struct sched_class *prev_class;
         struct rq *rq;
@@ -3590,15 +3593,14 @@ change:
         oldprio = p->prio;
 
         /*
-         * Special case for priority boosted tasks.
-         *
-         * If the new priority is lower or equal (user space view)
-         * than the current (boosted) priority, we just store the new
+         * Take priority boosted tasks into account. If the new
+         * effective priority is unchanged, we just store the new
          * normal parameters and do not touch the scheduler class and
          * the runqueue. This will be done when the task deboost
          * itself.
          */
-        if (rt_mutex_check_prio(p, newprio)) {
+        new_effective_prio = rt_mutex_get_effective_prio(p, newprio);
+        if (new_effective_prio == oldprio) {
                 __setscheduler_params(p, attr);
                 task_rq_unlock(rq, p, &flags);
                 return 0;
@@ -3612,7 +3614,7 @@ change:
                 put_prev_task(rq, p);
 
         prev_class = p->sched_class;
-        __setscheduler(rq, p, attr);
+        __setscheduler(rq, p, attr, true);
 
         if (running)
                 p->sched_class->set_curr_task(rq);
@@ -6997,27 +6999,23 @@ static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action,
         unsigned long flags;
         long cpu = (long)hcpu;
         struct dl_bw *dl_b;
+        bool overflow;
+        int cpus;
 
-        switch (action & ~CPU_TASKS_FROZEN) {
+        switch (action) {
         case CPU_DOWN_PREPARE:
-                /* explicitly allow suspend */
-                if (!(action & CPU_TASKS_FROZEN)) {
-                        bool overflow;
-                        int cpus;
-
-                        rcu_read_lock_sched();
-                        dl_b = dl_bw_of(cpu);
+                rcu_read_lock_sched();
+                dl_b = dl_bw_of(cpu);
 
-                        raw_spin_lock_irqsave(&dl_b->lock, flags);
-                        cpus = dl_bw_cpus(cpu);
-                        overflow = __dl_overflow(dl_b, cpus, 0, 0);
-                        raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+                raw_spin_lock_irqsave(&dl_b->lock, flags);
+                cpus = dl_bw_cpus(cpu);
+                overflow = __dl_overflow(dl_b, cpus, 0, 0);
+                raw_spin_unlock_irqrestore(&dl_b->lock, flags);
 
-                        rcu_read_unlock_sched();
+                rcu_read_unlock_sched();
 
-                        if (overflow)
-                                return notifier_from_errno(-EBUSY);
-                }
+                if (overflow)
+                        return notifier_from_errno(-EBUSY);
                 cpuset_update_active_cpus(false);
                 break;
         case CPU_DOWN_PREPARE_FROZEN:
@@ -7346,7 +7344,7 @@ static void normalize_task(struct rq *rq, struct task_struct *p)
         queued = task_on_rq_queued(p);
         if (queued)
                 dequeue_task(rq, p, 0);
-        __setscheduler(rq, p, &attr);
+        __setscheduler(rq, p, &attr, false);
         if (queued) {
                 enqueue_task(rq, p, 0);
                 resched_curr(rq);
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 11dc22a6983b..637a09461c1d 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -117,11 +117,7 @@ static int __clockevents_set_state(struct clock_event_device *dev,
         /* Transition with new state-specific callbacks */
         switch (state) {
         case CLOCK_EVT_STATE_DETACHED:
-                /*
-                 * This is an internal state, which is guaranteed to go from
-                 * SHUTDOWN to DETACHED. No driver interaction required.
-                 */
-                return 0;
+                /* The clockevent device is getting replaced. Shut it down. */
 
         case CLOCK_EVT_STATE_SHUTDOWN:
                 return dev->set_state_shutdown(dev);
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 692bf7184c8c..25a086bcb700 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -178,12 +178,13 @@ ftrace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int buf_len)
 EXPORT_SYMBOL(ftrace_print_hex_seq);
 
 const char *
-ftrace_print_array_seq(struct trace_seq *p, const void *buf, int buf_len,
+ftrace_print_array_seq(struct trace_seq *p, const void *buf, int count,
                        size_t el_size)
 {
         const char *ret = trace_seq_buffer_ptr(p);
         const char *prefix = "";
         void *ptr = (void *)buf;
+        size_t buf_len = count * el_size;
 
         trace_seq_putc(p, '{');
 
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 2316f50b07a4..506edcc500c4 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -41,6 +41,8 @@
 #define NMI_WATCHDOG_ENABLED      (1 << NMI_WATCHDOG_ENABLED_BIT)
 #define SOFT_WATCHDOG_ENABLED     (1 << SOFT_WATCHDOG_ENABLED_BIT)
 
+static DEFINE_MUTEX(watchdog_proc_mutex);
+
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
 static unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED|NMI_WATCHDOG_ENABLED;
 #else
@@ -608,26 +610,36 @@ void watchdog_nmi_enable_all(void)
 {
         int cpu;
 
-        if (!watchdog_user_enabled)
-                return;
+        mutex_lock(&watchdog_proc_mutex);
+
+        if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
+                goto unlock;
 
         get_online_cpus();
         for_each_online_cpu(cpu)
                 watchdog_nmi_enable(cpu);
         put_online_cpus();
+
+unlock:
+        mutex_lock(&watchdog_proc_mutex);
 }
 
 void watchdog_nmi_disable_all(void)
 {
         int cpu;
 
+        mutex_lock(&watchdog_proc_mutex);
+
         if (!watchdog_running)
-                return;
+                goto unlock;
 
         get_online_cpus();
         for_each_online_cpu(cpu)
                 watchdog_nmi_disable(cpu);
         put_online_cpus();
+
+unlock:
+        mutex_unlock(&watchdog_proc_mutex);
 }
 #else
 static int watchdog_nmi_enable(unsigned int cpu) { return 0; }
@@ -744,8 +756,6 @@ static int proc_watchdog_update(void)
 
 }
 
-static DEFINE_MUTEX(watchdog_proc_mutex);
-
 /*
  * common function for watchdog, nmi_watchdog and soft_watchdog parameter
  *