Merge tag 'v4.5-rc3' into patchwork

Linux 4.5-rc3

* tag 'v4.5-rc3': (644 commits)
  Linux 4.5-rc3
  epoll: restrict EPOLLEXCLUSIVE to POLLIN and POLLOUT
  radix-tree: fix oops after radix_tree_iter_retry
  MAINTAINERS: trim the file triggers for ABI/API
  dax: dirty inode only if required
  thp: make deferred_split_scan() work again
  mm: replace vma_lock_anon_vma with anon_vma_lock_read/write
  ocfs2/dlm: clear refmap bit of recovery lock while doing local recovery cleanup
  um: asm/page.h: remove the pte_high member from struct pte_t
  mm, hugetlb: don't require CMA for runtime gigantic pages
  mm/hugetlb: fix gigantic page initialization/allocation
  mm: downgrade VM_BUG in isolate_lru_page() to warning
  mempolicy: do not try to queue pages from !vma_migratable()
  mm, vmstat: fix wrong WQ sleep when memory reclaim doesn't make any progress
  vmstat: make vmstat_update deferrable
  mm, vmstat: make quiet_vmstat lighter
  mm/Kconfig: correct description of DEFERRED_STRUCT_PAGE_INIT
  memblock: don't mark memblock_phys_mem_size() as __init
  dump_stack: avoid potential deadlocks
  mm: validate_mm browse_rb SMP race condition
  ...

25 files changed, 856 insertions, 775 deletions

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index b0799bced518..89ebbc4d1164 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -291,10 +291,13 @@ static void *perf_event_fd_array_get_ptr(struct bpf_map *map, int fd)
 {
 	struct perf_event *event;
 	const struct perf_event_attr *attr;
+	struct file *file;
 
-	event = perf_event_get(fd);
-	if (IS_ERR(event))
-		return event;
+	file = perf_event_get(fd);
+	if (IS_ERR(file))
+		return file;
+
+	event = file->private_data;
 
 	attr = perf_event_attrs(event);
 	if (IS_ERR(attr))
@@ -304,24 +307,22 @@ static void *perf_event_fd_array_get_ptr(struct bpf_map *map, int fd)
 		goto err;
 
 	if (attr->type == PERF_TYPE_RAW)
-		return event;
+		return file;
 
 	if (attr->type == PERF_TYPE_HARDWARE)
-		return event;
+		return file;
 
 	if (attr->type == PERF_TYPE_SOFTWARE &&
 	    attr->config == PERF_COUNT_SW_BPF_OUTPUT)
-		return event;
+		return file;
 err:
-	perf_event_release_kernel(event);
+	fput(file);
 	return ERR_PTR(-EINVAL);
 }
 
 static void perf_event_fd_array_put_ptr(void *ptr)
 {
-	struct perf_event *event = ptr;
-
-	perf_event_release_kernel(event);
+	fput((struct file *)ptr);
 }
 
 static const struct bpf_map_ops perf_event_array_ops = {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 06ae52e99ac2..5946460b2425 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -49,8 +49,6 @@
 
 #include <asm/irq_regs.h>
 
-static struct workqueue_struct *perf_wq;
-
 typedef int (*remote_function_f)(void *);
 
 struct remote_function_call {
@@ -126,44 +124,181 @@ static int cpu_function_call(int cpu, remote_function_f func, void *info)
 	return data.ret;
 }
 
-static void event_function_call(struct perf_event *event,
-				int (*active)(void *),
-				void (*inactive)(void *),
-				void *data)
+static inline struct perf_cpu_context *
+__get_cpu_context(struct perf_event_context *ctx)
+{
+	return this_cpu_ptr(ctx->pmu->pmu_cpu_context);
+}
+
+static void perf_ctx_lock(struct perf_cpu_context *cpuctx,
+			  struct perf_event_context *ctx)
+{
+	raw_spin_lock(&cpuctx->ctx.lock);
+	if (ctx)
+		raw_spin_lock(&ctx->lock);
+}
+
+static void perf_ctx_unlock(struct perf_cpu_context *cpuctx,
+			    struct perf_event_context *ctx)
+{
+	if (ctx)
+		raw_spin_unlock(&ctx->lock);
+	raw_spin_unlock(&cpuctx->ctx.lock);
+}
+
+#define TASK_TOMBSTONE ((void *)-1L)
+
+static bool is_kernel_event(struct perf_event *event)
+{
+	return READ_ONCE(event->owner) == TASK_TOMBSTONE;
+}
+
+/*
+ * On task ctx scheduling...
+ *
+ * When !ctx->nr_events a task context will not be scheduled. This means
+ * we can disable the scheduler hooks (for performance) without leaving
+ * pending task ctx state.
+ *
+ * This however results in two special cases:
+ *
+ *  - removing the last event from a task ctx; this is relatively straight
+ *    forward and is done in __perf_remove_from_context.
+ *
+ *  - adding the first event to a task ctx; this is tricky because we cannot
+ *    rely on ctx->is_active and therefore cannot use event_function_call().
+ *    See perf_install_in_context().
+ *
+ * This is because we need a ctx->lock serialized variable (ctx->is_active)
+ * to reliably determine if a particular task/context is scheduled in. The
+ * task_curr() use in task_function_call() is racy in that a remote context
+ * switch is not a single atomic operation.
+ *
+ * As is, the situation is 'safe' because we set rq->curr before we do the
+ * actual context switch. This means that task_curr() will fail early, but
+ * we'll continue spinning on ctx->is_active until we've passed
+ * perf_event_task_sched_out().
+ *
+ * Without this ctx->lock serialized variable we could have race where we find
+ * the task (and hence the context) would not be active while in fact they are.
+ *
+ * If ctx->nr_events, then ctx->is_active and cpuctx->task_ctx are set.
+ */
+
+typedef void (*event_f)(struct perf_event *, struct perf_cpu_context *,
+			struct perf_event_context *, void *);
+
+struct event_function_struct {
+	struct perf_event *event;
+	event_f func;
+	void *data;
+};
+
+static int event_function(void *info)
+{
+	struct event_function_struct *efs = info;
+	struct perf_event *event = efs->event;
+	struct perf_event_context *ctx = event->ctx;
+	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
+	struct perf_event_context *task_ctx = cpuctx->task_ctx;
+	int ret = 0;
+
+	WARN_ON_ONCE(!irqs_disabled());
+
+	perf_ctx_lock(cpuctx, task_ctx);
+	/*
+	 * Since we do the IPI call without holding ctx->lock things can have
+	 * changed, double check we hit the task we set out to hit.
+	 */
+	if (ctx->task) {
+		if (ctx->task != current) {
+			ret = -EAGAIN;
+			goto unlock;
+		}
+
+		/*
+		 * We only use event_function_call() on established contexts,
+		 * and event_function() is only ever called when active (or
+		 * rather, we'll have bailed in task_function_call() or the
+		 * above ctx->task != current test), therefore we must have
+		 * ctx->is_active here.
+		 */
+		WARN_ON_ONCE(!ctx->is_active);
+		/*
+		 * And since we have ctx->is_active, cpuctx->task_ctx must
+		 * match.
+		 */
+		WARN_ON_ONCE(task_ctx != ctx);
+	} else {
+		WARN_ON_ONCE(&cpuctx->ctx != ctx);
+	}
+
+	efs->func(event, cpuctx, ctx, efs->data);
+unlock:
+	perf_ctx_unlock(cpuctx, task_ctx);
+
+	return ret;
+}
+
+static void event_function_local(struct perf_event *event, event_f func, void *data)
+{
+	struct event_function_struct efs = {
+		.event = event,
+		.func = func,
+		.data = data,
+	};
+
+	int ret = event_function(&efs);
+	WARN_ON_ONCE(ret);
+}
+
+static void event_function_call(struct perf_event *event, event_f func, void *data)
 {
 	struct perf_event_context *ctx = event->ctx;
-	struct task_struct *task = ctx->task;
+	struct task_struct *task = READ_ONCE(ctx->task); /* verified in event_function */
+	struct event_function_struct efs = {
+		.event = event,
+		.func = func,
+		.data = data,
+	};
+
+	if (!event->parent) {
+		/*
+		 * If this is a !child event, we must hold ctx::mutex to
+		 * stabilize the the event->ctx relation. See
+		 * perf_event_ctx_lock().
+		 */
+		lockdep_assert_held(&ctx->mutex);
+	}
 
 	if (!task) {
-		cpu_function_call(event->cpu, active, data);
+		cpu_function_call(event->cpu, event_function, &efs);
 		return;
 	}
 
 again:
-	if (!task_function_call(task, active, data))
+	if (task == TASK_TOMBSTONE)
+		return;
+
+	if (!task_function_call(task, event_function, &efs))
 		return;
 
 	raw_spin_lock_irq(&ctx->lock);
-	if (ctx->is_active) {
-		/*
-		 * Reload the task pointer, it might have been changed by
-		 * a concurrent perf_event_context_sched_out().
-		 */
-		task = ctx->task;
-		raw_spin_unlock_irq(&ctx->lock);
-		goto again;
+	/*
+	 * Reload the task pointer, it might have been changed by
+	 * a concurrent perf_event_context_sched_out().
+	 */
+	task = ctx->task;
+	if (task != TASK_TOMBSTONE) {
+		if (ctx->is_active) {
+			raw_spin_unlock_irq(&ctx->lock);
+			goto again;
+		}
+		func(event, NULL, ctx, data);
 	}
-	inactive(data);
 	raw_spin_unlock_irq(&ctx->lock);
 }
 
-#define EVENT_OWNER_KERNEL ((void *) -1)
-
-static bool is_kernel_event(struct perf_event *event)
-{
-	return event->owner == EVENT_OWNER_KERNEL;
-}
-
 #define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\
 		       PERF_FLAG_FD_OUTPUT  |\
 		       PERF_FLAG_PID_CGROUP |\
@@ -368,28 +503,6 @@ static inline u64 perf_event_clock(struct perf_event *event)
 	return event->clock();
 }
 
-static inline struct perf_cpu_context *
-__get_cpu_context(struct perf_event_context *ctx)
-{
-	return this_cpu_ptr(ctx->pmu->pmu_cpu_context);
-}
-
-static void perf_ctx_lock(struct perf_cpu_context *cpuctx,
-			  struct perf_event_context *ctx)
-{
-	raw_spin_lock(&cpuctx->ctx.lock);
-	if (ctx)
-		raw_spin_lock(&ctx->lock);
-}
-
-static void perf_ctx_unlock(struct perf_cpu_context *cpuctx,
-			    struct perf_event_context *ctx)
-{
-	if (ctx)
-		raw_spin_unlock(&ctx->lock);
-	raw_spin_unlock(&cpuctx->ctx.lock);
-}
-
 #ifdef CONFIG_CGROUP_PERF
 
 static inline bool
@@ -579,13 +692,7 @@ static inline void perf_cgroup_sched_out(struct task_struct *task,
 	 * we are holding the rcu lock
 	 */
 	cgrp1 = perf_cgroup_from_task(task, NULL);
-
-	/*
-	 * next is NULL when called from perf_event_enable_on_exec()
-	 * that will systematically cause a cgroup_switch()
-	 */
-	if (next)
-		cgrp2 = perf_cgroup_from_task(next, NULL);
+	cgrp2 = perf_cgroup_from_task(next, NULL);
 
 	/*
 	 * only schedule out current cgroup events if we know
@@ -611,8 +718,6 @@ static inline void perf_cgroup_sched_in(struct task_struct *prev,
 	 * we are holding the rcu lock
 	 */
 	cgrp1 = perf_cgroup_from_task(task, NULL);
-
-	/* prev can never be NULL */
 	cgrp2 = perf_cgroup_from_task(prev, NULL);
 
 	/*
@@ -917,7 +1022,7 @@ static void put_ctx(struct perf_event_context *ctx)
 	if (atomic_dec_and_test(&ctx->refcount)) {
 		if (ctx->parent_ctx)
 			put_ctx(ctx->parent_ctx);
-		if (ctx->task)
+		if (ctx->task && ctx->task != TASK_TOMBSTONE)
 			put_task_struct(ctx->task);
 		call_rcu(&ctx->rcu_head, free_ctx);
 	}
@@ -934,9 +1039,8 @@ static void put_ctx(struct perf_event_context *ctx)
  * 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_exit_event()
+ *        put_event()			[ parent, 1 ]
  *
  *  - perf_event_init_context()		[ parent, 0 ]
  *      inherit_task_group()
@@ -979,8 +1083,8 @@ static void put_ctx(struct perf_event_context *ctx)
  * Lock order:
  *	task_struct::perf_event_mutex
  *	  perf_event_context::mutex
- *	    perf_event_context::lock
  *	    perf_event::child_mutex;
+ *	      perf_event_context::lock
  *	    perf_event::mmap_mutex
  *	    mmap_sem
  */
@@ -1078,6 +1182,7 @@ static u64 primary_event_id(struct perf_event *event)
 
 /*
  * Get the perf_event_context for a task and lock it.
+ *
  * This has to cope with with the fact that until it is locked,
  * the context could get moved to another task.
  */
@@ -1118,9 +1223,12 @@ retry:
 			goto retry;
 		}
 
-		if (!atomic_inc_not_zero(&ctx->refcount)) {
+		if (ctx->task == TASK_TOMBSTONE ||
+		    !atomic_inc_not_zero(&ctx->refcount)) {
 			raw_spin_unlock(&ctx->lock);
 			ctx = NULL;
+		} else {
+			WARN_ON_ONCE(ctx->task != task);
 		}
 	}
 	rcu_read_unlock();
@@ -1246,6 +1354,8 @@ ctx_group_list(struct perf_event *event, struct perf_event_context *ctx)
 static void
 list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 {
+	lockdep_assert_held(&ctx->lock);
+
 	WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT);
 	event->attach_state |= PERF_ATTACH_CONTEXT;
 
@@ -1448,11 +1558,14 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 
 	if (is_cgroup_event(event)) {
 		ctx->nr_cgroups--;
+		/*
+		 * Because cgroup events are always per-cpu events, this will
+		 * always be called from the right CPU.
+		 */
 		cpuctx = __get_cpu_context(ctx);
 		/*
-		 * if there are no more cgroup events
-		 * then cler cgrp to avoid stale pointer
-		 * in update_cgrp_time_from_cpuctx()
+		 * If there are no more cgroup events then clear cgrp to avoid
+		 * stale pointer in update_cgrp_time_from_cpuctx().
 		 */
 		if (!ctx->nr_cgroups)
 			cpuctx->cgrp = NULL;
@@ -1530,45 +1643,11 @@ out:
 		perf_event__header_size(tmp);
 }
 
-/*
- * User event without the task.
- */
 static bool is_orphaned_event(struct perf_event *event)
 {
-	return event && !is_kernel_event(event) && !event->owner;
+	return event->state == PERF_EVENT_STATE_EXIT;
 }
 
-/*
- * Event has a parent but parent's task finished and it's
- * alive only because of children holding refference.
- */
-static bool is_orphaned_child(struct perf_event *event)
-{
-	return is_orphaned_event(event->parent);
-}
-
-static void orphans_remove_work(struct work_struct *work);
-
-static void schedule_orphans_remove(struct perf_event_context *ctx)
-{
-	if (!ctx->task || ctx->orphans_remove_sched || !perf_wq)
-		return;
-
-	if (queue_delayed_work(perf_wq, &ctx->orphans_remove, 1)) {
-		get_ctx(ctx);
-		ctx->orphans_remove_sched = true;
-	}
-}
-
-static int __init perf_workqueue_init(void)
-{
-	perf_wq = create_singlethread_workqueue("perf");
-	WARN(!perf_wq, "failed to create perf workqueue\n");
-	return perf_wq ? 0 : -1;
-}
-
-core_initcall(perf_workqueue_init);
-
 static inline int pmu_filter_match(struct perf_event *event)
 {
 	struct pmu *pmu = event->pmu;
@@ -1629,9 +1708,6 @@ event_sched_out(struct perf_event *event,
 	if (event->attr.exclusive || !cpuctx->active_oncpu)
 		cpuctx->exclusive = 0;
 
-	if (is_orphaned_child(event))
-		schedule_orphans_remove(ctx);
-
 	perf_pmu_enable(event->pmu);
 }
 
@@ -1655,21 +1731,8 @@ group_sched_out(struct perf_event *group_event,
 		cpuctx->exclusive = 0;
 }
 
-struct remove_event {
-	struct perf_event *event;
-	bool detach_group;
-};
-
-static void ___perf_remove_from_context(void *info)
-{
-	struct remove_event *re = info;
-	struct perf_event *event = re->event;
-	struct perf_event_context *ctx = event->ctx;
-
-	if (re->detach_group)
-		perf_group_detach(event);
-	list_del_event(event, ctx);
-}
+#define DETACH_GROUP	0x01UL
+#define DETACH_STATE	0x02UL
 
 /*
  * Cross CPU call to remove a performance event
@@ -1677,33 +1740,33 @@ static void ___perf_remove_from_context(void *info)
  * We disable the event on the hardware level first. After that we
  * remove it from the context list.
  */
-static int __perf_remove_from_context(void *info)
+static void
+__perf_remove_from_context(struct perf_event *event,
+			   struct perf_cpu_context *cpuctx,
+			   struct perf_event_context *ctx,
+			   void *info)
 {
-	struct remove_event *re = info;
-	struct perf_event *event = re->event;
-	struct perf_event_context *ctx = event->ctx;
-	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
+	unsigned long flags = (unsigned long)info;
 
-	raw_spin_lock(&ctx->lock);
 	event_sched_out(event, cpuctx, ctx);
-	if (re->detach_group)
+	if (flags & DETACH_GROUP)
 		perf_group_detach(event);
 	list_del_event(event, ctx);
-	if (!ctx->nr_events && cpuctx->task_ctx == ctx) {
+	if (flags & DETACH_STATE)
+		event->state = PERF_EVENT_STATE_EXIT;
+
+	if (!ctx->nr_events && ctx->is_active) {
 		ctx->is_active = 0;
-		cpuctx->task_ctx = NULL;
+		if (ctx->task) {
+			WARN_ON_ONCE(cpuctx->task_ctx != ctx);
+			cpuctx->task_ctx = NULL;
+		}
 	}
-	raw_spin_unlock(&ctx->lock);
-
-	return 0;
 }
 
 /*
  * Remove the event from a task's (or a CPU's) list of events.
  *
- * CPU events are removed with a smp call. For task events we only
- * call when the task is on a CPU.
- *
  * If event->ctx is a cloned context, callers must make sure that
  * every task struct that event->ctx->task could possibly point to
  * remains valid.  This is OK when called from perf_release since
@@ -1711,73 +1774,32 @@ static int __perf_remove_from_context(void *info)
  * When called from perf_event_exit_task, it's OK because the
  * context has been detached from its task.
  */
-static void perf_remove_from_context(struct perf_event *event, bool detach_group)
+static void perf_remove_from_context(struct perf_event *event, unsigned long flags)
 {
-	struct perf_event_context *ctx = event->ctx;
-	struct remove_event re = {
-		.event = event,
-		.detach_group = detach_group,
-	};
+	lockdep_assert_held(&event->ctx->mutex);
 
-	lockdep_assert_held(&ctx->mutex);
-
-	event_function_call(event, __perf_remove_from_context,
-			    ___perf_remove_from_context, &re);
+	event_function_call(event, __perf_remove_from_context, (void *)flags);
 }
 
 /*
  * Cross CPU call to disable a performance event
  */
-int __perf_event_disable(void *info)
-{
-	struct perf_event *event = info;
-	struct perf_event_context *ctx = event->ctx;
-	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
-
-	/*
-	 * If this is a per-task event, need to check whether this
-	 * event's task is the current task on this cpu.
-	 *
-	 * Can trigger due to concurrent perf_event_context_sched_out()
-	 * flipping contexts around.
-	 */
-	if (ctx->task && cpuctx->task_ctx != ctx)
-		return -EINVAL;
-
-	raw_spin_lock(&ctx->lock);
-
-	/*
-	 * If the event is on, turn it off.
-	 * If it is in error state, leave it in error state.
-	 */
-	if (event->state >= PERF_EVENT_STATE_INACTIVE) {
-		update_context_time(ctx);
-		update_cgrp_time_from_event(event);
-		update_group_times(event);
-		if (event == event->group_leader)
-			group_sched_out(event, cpuctx, ctx);
-		else
-			event_sched_out(event, cpuctx, ctx);
-		event->state = PERF_EVENT_STATE_OFF;
-	}
-
-	raw_spin_unlock(&ctx->lock);
-
-	return 0;
-}
-
-void ___perf_event_disable(void *info)
+static void __perf_event_disable(struct perf_event *event,
+				 struct perf_cpu_context *cpuctx,
+				 struct perf_event_context *ctx,
+				 void *info)
 {
-	struct perf_event *event = info;
+	if (event->state < PERF_EVENT_STATE_INACTIVE)
+		return;
 
-	/*
-	 * Since we have the lock this context can't be scheduled
-	 * in, so we can change the state safely.
-	 */
-	if (event->state == PERF_EVENT_STATE_INACTIVE) {
-		update_group_times(event);
-		event->state = PERF_EVENT_STATE_OFF;
-	}
+	update_context_time(ctx);
+	update_cgrp_time_from_event(event);
+	update_group_times(event);
+	if (event == event->group_leader)
+		group_sched_out(event, cpuctx, ctx);
+	else
+		event_sched_out(event, cpuctx, ctx);
+	event->state = PERF_EVENT_STATE_OFF;
 }
 
 /*
@@ -1788,7 +1810,8 @@ void ___perf_event_disable(void *info)
  * remains valid.  This condition is satisifed when called through
  * perf_event_for_each_child or perf_event_for_each because they
  * hold the top-level event's child_mutex, so any descendant that
- * goes to exit will block in sync_child_event.
+ * goes to exit will block in perf_event_exit_event().
+ *
  * When called from perf_pending_event it's OK because event->ctx
  * is the current context on this CPU and preemption is disabled,
  * hence we can't get into perf_event_task_sched_out for this context.
@@ -1804,8 +1827,12 @@ static void _perf_event_disable(struct perf_event *event)
 	}
 	raw_spin_unlock_irq(&ctx->lock);
 
-	event_function_call(event, __perf_event_disable,
-			    ___perf_event_disable, event);
+	event_function_call(event, __perf_event_disable, NULL);
+}
+
+void perf_event_disable_local(struct perf_event *event)
+{
+	event_function_local(event, __perf_event_disable, NULL);
 }
 
 /*
@@ -1918,9 +1945,6 @@ event_sched_in(struct perf_event *event,
 	if (event->attr.exclusive)
 		cpuctx->exclusive = 1;
 
-	if (is_orphaned_child(event))
-		schedule_orphans_remove(ctx);
-
 out:
 	perf_pmu_enable(event->pmu);
 
@@ -2039,7 +2063,8 @@ static void add_event_to_ctx(struct perf_event *event,
 	event->tstamp_stopped = tstamp;
 }
 
-static void task_ctx_sched_out(struct perf_event_context *ctx);
+static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
+			       struct perf_event_context *ctx);
 static void
 ctx_sched_in(struct perf_event_context *ctx,
 	     struct perf_cpu_context *cpuctx,
@@ -2058,16 +2083,15 @@ static void perf_event_sched_in(struct perf_cpu_context *cpuctx,
 		ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task);
 }
 
-static void ___perf_install_in_context(void *info)
+static void ctx_resched(struct perf_cpu_context *cpuctx,
+			struct perf_event_context *task_ctx)
 {
-	struct perf_event *event = info;
-	struct perf_event_context *ctx = event->ctx;
-
-	/*
-	 * Since the task isn't running, its safe to add the event, us holding
-	 * the ctx->lock ensures the task won't get scheduled in.
-	 */
-	add_event_to_ctx(event, ctx);
+	perf_pmu_disable(cpuctx->ctx.pmu);
+	if (task_ctx)
+		task_ctx_sched_out(cpuctx, task_ctx);
+	cpu_ctx_sched_out(cpuctx, EVENT_ALL);
+	perf_event_sched_in(cpuctx, task_ctx, current);
+	perf_pmu_enable(cpuctx->ctx.pmu);
 }
 
 /*
@@ -2077,55 +2101,31 @@ static void ___perf_install_in_context(void *info)
  */
 static int  __perf_install_in_context(void *info)
 {
-	struct perf_event *event = info;
-	struct perf_event_context *ctx = event->ctx;
+	struct perf_event_context *ctx = info;
 	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 	struct perf_event_context *task_ctx = cpuctx->task_ctx;
-	struct task_struct *task = current;
-
-	perf_ctx_lock(cpuctx, task_ctx);
-	perf_pmu_disable(cpuctx->ctx.pmu);
-
-	/*
-	 * If there was an active task_ctx schedule it out.
-	 */
-	if (task_ctx)
-		task_ctx_sched_out(task_ctx);
 
-	/*
-	 * If the context we're installing events in is not the
-	 * active task_ctx, flip them.
-	 */
-	if (ctx->task && task_ctx != ctx) {
-		if (task_ctx)
-			raw_spin_unlock(&task_ctx->lock);
+	raw_spin_lock(&cpuctx->ctx.lock);
+	if (ctx->task) {
 		raw_spin_lock(&ctx->lock);
+		/*
+		 * If we hit the 'wrong' task, we've since scheduled and
+		 * everything should be sorted, nothing to do!
+		 */
 		task_ctx = ctx;
-	}
+		if (ctx->task != current)
+			goto unlock;
 
-	if (task_ctx) {
-		cpuctx->task_ctx = task_ctx;
-		task = task_ctx->task;
+		/*
+		 * If task_ctx is set, it had better be to us.
+		 */
+		WARN_ON_ONCE(cpuctx->task_ctx != ctx && cpuctx->task_ctx);
+	} else if (task_ctx) {
+		raw_spin_lock(&task_ctx->lock);
 	}
 
-	cpu_ctx_sched_out(cpuctx, EVENT_ALL);
-
-	update_context_time(ctx);
-	/*
-	 * update cgrp time only if current cgrp
-	 * matches event->cgrp. Must be done before
-	 * calling add_event_to_ctx()
-	 */
-	update_cgrp_time_from_event(event);
-
-	add_event_to_ctx(event, ctx);
-
-	/*
-	 * Schedule everything back in
-	 */
-	perf_event_sched_in(cpuctx, task_ctx, task);
-
-	perf_pmu_enable(cpuctx->ctx.pmu);
+	ctx_resched(cpuctx, task_ctx);
+unlock:
 	perf_ctx_unlock(cpuctx, task_ctx);
 
 	return 0;
@@ -2133,27 +2133,54 @@ static int  __perf_install_in_context(void *info)
 
 /*
  * Attach a performance event to a context
- *
- * First we add the event to the list with the hardware enable bit
- * in event->hw_config cleared.
- *
- * If the event is attached to a task which is on a CPU we use a smp
- * call to enable it in the task context. The task might have been
- * scheduled away, but we check this in the smp call again.
  */
 static void
 perf_install_in_context(struct perf_event_context *ctx,
 			struct perf_event *event,
 			int cpu)
 {
+	struct task_struct *task = NULL;
+
 	lockdep_assert_held(&ctx->mutex);
 
 	event->ctx = ctx;
 	if (event->cpu != -1)
 		event->cpu = cpu;
 
-	event_function_call(event, __perf_install_in_context,
-			    ___perf_install_in_context, event);
+	/*
+	 * Installing events is tricky because we cannot rely on ctx->is_active
+	 * to be set in case this is the nr_events 0 -> 1 transition.
+	 *
+	 * So what we do is we add the event to the list here, which will allow
+	 * a future context switch to DTRT and then send a racy IPI. If the IPI
+	 * fails to hit the right task, this means a context switch must have
+	 * happened and that will have taken care of business.
+	 */
+	raw_spin_lock_irq(&ctx->lock);
+	task = ctx->task;
+	/*
+	 * Worse, we cannot even rely on the ctx actually existing anymore. If
+	 * between find_get_context() and perf_install_in_context() the task
+	 * went through perf_event_exit_task() its dead and we should not be
+	 * adding new events.
+	 */
+	if (task == TASK_TOMBSTONE) {
+		raw_spin_unlock_irq(&ctx->lock);
+		return;
+	}
+	update_context_time(ctx);
+	/*
+	 * Update cgrp time only if current cgrp matches event->cgrp.
+	 * Must be done before calling add_event_to_ctx().
+	 */
+	update_cgrp_time_from_event(event);
+	add_event_to_ctx(event, ctx);
+	raw_spin_unlock_irq(&ctx->lock);
+
+	if (task)
+		task_function_call(task, __perf_install_in_context, ctx);
+	else
+		cpu_function_call(cpu, __perf_install_in_context, ctx);
 }
 
 /*
@@ -2180,43 +2207,30 @@ static void __perf_event_mark_enabled(struct perf_event *event)
 /*
  * Cross CPU call to enable a performance event
  */
-static int __perf_event_enable(void *info)
+static void __perf_event_enable(struct perf_event *event,
+				struct perf_cpu_context *cpuctx,
+				struct perf_event_context *ctx,
+				void *info)
 {
-	struct perf_event *event = info;
-	struct perf_event_context *ctx = event->ctx;
 	struct perf_event *leader = event->group_leader;
-	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
-	int err;
+	struct perf_event_context *task_ctx;
 
-	/*
-	 * There's a time window between 'ctx->is_active' check
-	 * in perf_event_enable function and this place having:
-	 *   - IRQs on
-	 *   - ctx->lock unlocked
-	 *
-	 * where the task could be killed and 'ctx' deactivated
-	 * by perf_event_exit_task.
-	 */
-	if (!ctx->is_active)
-		return -EINVAL;
+	if (event->state >= PERF_EVENT_STATE_INACTIVE ||
+	    event->state <= PERF_EVENT_STATE_ERROR)
+		return;
 
-	raw_spin_lock(&ctx->lock);
 	update_context_time(ctx);
-
-	if (event->state >= PERF_EVENT_STATE_INACTIVE)
-		goto unlock;
-
-	/*
-	 * set current task's cgroup time reference point
-	 */
-	perf_cgroup_set_timestamp(current, ctx);
-
 	__perf_event_mark_enabled(event);
 
+	if (!ctx->is_active)
+		return;
+
 	if (!event_filter_match(event)) {
-		if (is_cgroup_event(event))
+		if (is_cgroup_event(event)) {
+			perf_cgroup_set_timestamp(current, ctx); // XXX ?
 			perf_cgroup_defer_enabled(event);
-		goto unlock;
+		}
+		return;
 	}
 
 	/*
@@ -2224,41 +2238,13 @@ static int __perf_event_enable(void *info)
 	 * then don't put it on unless the group is on.
 	 */
 	if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE)
-		goto unlock;
-
-	if (!group_can_go_on(event, cpuctx, 1)) {
-		err = -EEXIST;
-	} else {
-		if (event == leader)
-			err = group_sched_in(event, cpuctx, ctx);
-		else
-			err = event_sched_in(event, cpuctx, ctx);
-	}
-
-	if (err) {
-		/*
-		 * If this event can't go on and it's part of a
-		 * group, then the whole group has to come off.
-		 */
-		if (leader != event) {
-			group_sched_out(leader, cpuctx, ctx);
-			perf_mux_hrtimer_restart(cpuctx);
-		}
-		if (leader->attr.pinned) {
-			update_group_times(leader);
-			leader->state = PERF_EVENT_STATE_ERROR;
-		}
-	}
+		return;
 
-unlock:
-	raw_spin_unlock(&ctx->lock);
+	task_ctx = cpuctx->task_ctx;
+	if (ctx->task)
+		WARN_ON_ONCE(task_ctx != ctx);
 
-	return 0;
-}
-
-void ___perf_event_enable(void *info)
-{
-	__perf_event_mark_enabled((struct perf_event *)info);
+	ctx_resched(cpuctx, task_ctx);
 }
 
 /*
@@ -2275,7 +2261,8 @@ static void _perf_event_enable(struct perf_event *event)
 	struct perf_event_context *ctx = event->ctx;
 
 	raw_spin_lock_irq(&ctx->lock);
-	if (event->state >= PERF_EVENT_STATE_INACTIVE) {
+	if (event->state >= PERF_EVENT_STATE_INACTIVE ||
+	    event->state <  PERF_EVENT_STATE_ERROR) {
 		raw_spin_unlock_irq(&ctx->lock);
 		return;
 	}
@@ -2291,8 +2278,7 @@ static void _perf_event_enable(struct perf_event *event)
 		event->state = PERF_EVENT_STATE_OFF;
 	raw_spin_unlock_irq(&ctx->lock);
 
-	event_function_call(event, __perf_event_enable,
-			    ___perf_event_enable, event);
+	event_function_call(event, __perf_event_enable, NULL);
 }
 
 /*
@@ -2342,12 +2328,27 @@ static void ctx_sched_out(struct perf_event_context *ctx,
 			  struct perf_cpu_context *cpuctx,
 			  enum event_type_t event_type)
 {
-	struct perf_event *event;
 	int is_active = ctx->is_active;
+	struct perf_event *event;
 
-	ctx->is_active &= ~event_type;
-	if (likely(!ctx->nr_events))
+	lockdep_assert_held(&ctx->lock);
+
+	if (likely(!ctx->nr_events)) {
+		/*
+		 * See __perf_remove_from_context().
+		 */
+		WARN_ON_ONCE(ctx->is_active);
+		if (ctx->task)
+			WARN_ON_ONCE(cpuctx->task_ctx);
 		return;
+	}
+
+	ctx->is_active &= ~event_type;
+	if (ctx->task) {
+		WARN_ON_ONCE(cpuctx->task_ctx != ctx);
+		if (!ctx->is_active)
+			cpuctx->task_ctx = NULL;
+	}
 
 	update_context_time(ctx);
 	update_cgrp_time_from_cpuctx(cpuctx);
@@ -2518,17 +2519,21 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
 		raw_spin_lock(&ctx->lock);
 		raw_spin_lock_nested(&next_ctx->lock, SINGLE_DEPTH_NESTING);
 		if (context_equiv(ctx, next_ctx)) {
-			/*
-			 * XXX do we need a memory barrier of sorts
-			 * wrt to rcu_dereference() of perf_event_ctxp
-			 */
-			task->perf_event_ctxp[ctxn] = next_ctx;
-			next->perf_event_ctxp[ctxn] = ctx;
-			ctx->task = next;
-			next_ctx->task = task;
+			WRITE_ONCE(ctx->task, next);
+			WRITE_ONCE(next_ctx->task, task);
 
 			swap(ctx->task_ctx_data, next_ctx->task_ctx_data);
 
+			/*
+			 * RCU_INIT_POINTER here is safe because we've not
+			 * modified the ctx and the above modification of
+			 * ctx->task and ctx->task_ctx_data are immaterial
+			 * since those values are always verified under
+			 * ctx->lock which we're now holding.
+			 */
+			RCU_INIT_POINTER(task->perf_event_ctxp[ctxn], next_ctx);
+			RCU_INIT_POINTER(next->perf_event_ctxp[ctxn], ctx);
+
 			do_switch = 0;
 
 			perf_event_sync_stat(ctx, next_ctx);
@@ -2541,8 +2546,7 @@ unlock:
 
 	if (do_switch) {
 		raw_spin_lock(&ctx->lock);
-		ctx_sched_out(ctx, cpuctx, EVENT_ALL);
-		cpuctx->task_ctx = NULL;
+		task_ctx_sched_out(cpuctx, ctx);
 		raw_spin_unlock(&ctx->lock);
 	}
 }
@@ -2637,10 +2641,9 @@ void __perf_event_task_sched_out(struct task_struct *task,
 		perf_cgroup_sched_out(task, next);
 }
 
-static void task_ctx_sched_out(struct perf_event_context *ctx)
+static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
+			       struct perf_event_context *ctx)
 {
-	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
-
 	if (!cpuctx->task_ctx)
 		return;
 
@@ -2648,7 +2651,6 @@ static void task_ctx_sched_out(struct perf_event_context *ctx)
 		return;
 
 	ctx_sched_out(ctx, cpuctx, EVENT_ALL);
-	cpuctx->task_ctx = NULL;
 }
 
 /*
@@ -2725,13 +2727,22 @@ ctx_sched_in(struct perf_event_context *ctx,
 	     enum event_type_t event_type,
 	     struct task_struct *task)
 {
-	u64 now;
 	int is_active = ctx->is_active;
+	u64 now;
+
+	lockdep_assert_held(&ctx->lock);
 
-	ctx->is_active |= event_type;
 	if (likely(!ctx->nr_events))
 		return;
 
+	ctx->is_active |= event_type;
+	if (ctx->task) {
+		if (!is_active)
+			cpuctx->task_ctx = ctx;
+		else
+			WARN_ON_ONCE(cpuctx->task_ctx != ctx);
+	}
+
 	now = perf_clock();
 	ctx->timestamp = now;
 	perf_cgroup_set_timestamp(task, ctx);
@@ -2773,12 +2784,7 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
 	 * cpu flexible, task flexible.
 	 */
 	cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
-
-	if (ctx->nr_events)
-		cpuctx->task_ctx = ctx;
-
-	perf_event_sched_in(cpuctx, cpuctx->task_ctx, task);
-
+	perf_event_sched_in(cpuctx, ctx, task);
 	perf_pmu_enable(ctx->pmu);
 	perf_ctx_unlock(cpuctx, ctx);
 }
@@ -2800,6 +2806,16 @@ void __perf_event_task_sched_in(struct task_struct *prev,
 	struct perf_event_context *ctx;
 	int ctxn;
 
+	/*
+	 * If cgroup events exist on this CPU, then we need to check if we have
+	 * to switch in PMU state; cgroup event are system-wide mode only.
+	 *
+	 * Since cgroup events are CPU events, we must schedule these in before
+	 * we schedule in the task events.
+	 */
+	if (atomic_read(this_cpu_ptr(&perf_cgroup_events)))
+		perf_cgroup_sched_in(prev, task);
+
 	for_each_task_context_nr(ctxn) {
 		ctx = task->perf_event_ctxp[ctxn];
 		if (likely(!ctx))
@@ -2807,13 +2823,6 @@ void __perf_event_task_sched_in(struct task_struct *prev,
 
 		perf_event_context_sched_in(ctx, task);
 	}
-	/*
-	 * if cgroup events exist on this CPU, then we need
-	 * to check if we have to switch in PMU state.
-	 * cgroup event are system-wide mode only
-	 */
-	if (atomic_read(this_cpu_ptr(&perf_cgroup_events)))
-		perf_cgroup_sched_in(prev, task);
 
 	if (atomic_read(&nr_switch_events))
 		perf_event_switch(task, prev, true);
@@ -3099,46 +3108,30 @@ static int event_enable_on_exec(struct perf_event *event,
 static void perf_event_enable_on_exec(int ctxn)
 {
 	struct perf_event_context *ctx, *clone_ctx = NULL;
+	struct perf_cpu_context *cpuctx;
 	struct perf_event *event;
 	unsigned long flags;
 	int enabled = 0;
-	int ret;
 
 	local_irq_save(flags);
 	ctx = current->perf_event_ctxp[ctxn];
 	if (!ctx || !ctx->nr_events)
 		goto out;
 
-	/*
-	 * We must ctxsw out cgroup events to avoid conflict
-	 * when invoking perf_task_event_sched_in() later on
-	 * in this function. Otherwise we end up trying to
-	 * ctxswin cgroup events which are already scheduled
-	 * in.
-	 */
-	perf_cgroup_sched_out(current, NULL);
-
-	raw_spin_lock(&ctx->lock);
-	task_ctx_sched_out(ctx);
-
-	list_for_each_entry(event, &ctx->event_list, event_entry) {
-		ret = event_enable_on_exec(event, ctx);
-		if (ret)
-			enabled = 1;
-	}
+	cpuctx = __get_cpu_context(ctx);
+	perf_ctx_lock(cpuctx, ctx);
+	list_for_each_entry(event, &ctx->event_list, event_entry)
+		enabled |= event_enable_on_exec(event, ctx);
 
 	/*
-	 * Unclone this context if we enabled any event.
+	 * Unclone and reschedule this context if we enabled any event.
 	 */
-	if (enabled)
+	if (enabled) {
 		clone_ctx = unclone_ctx(ctx);
+		ctx_resched(cpuctx, ctx);
+	}
+	perf_ctx_unlock(cpuctx, ctx);
 
-	raw_spin_unlock(&ctx->lock);
-
-	/*
-	 * Also calls ctxswin for cgroup events, if any:
-	 */
-	perf_event_context_sched_in(ctx, ctx->task);
 out:
 	local_irq_restore(flags);
 
@@ -3334,7 +3327,6 @@ static void __perf_event_init_context(struct perf_event_context *ctx)
 	INIT_LIST_HEAD(&ctx->flexible_groups);
 	INIT_LIST_HEAD(&ctx->event_list);
 	atomic_set(&ctx->refcount, 1);
-	INIT_DELAYED_WORK(&ctx->orphans_remove, orphans_remove_work);
 }
 
 static struct perf_event_context *
@@ -3521,11 +3513,13 @@ static void unaccount_event_cpu(struct perf_event *event, int cpu)
 
 static void unaccount_event(struct perf_event *event)
 {
+	bool dec = false;
+
 	if (event->parent)
 		return;
 
 	if (event->attach_state & PERF_ATTACH_TASK)
-		static_key_slow_dec_deferred(&perf_sched_events);
+		dec = true;
 	if (event->attr.mmap || event->attr.mmap_data)
 		atomic_dec(&nr_mmap_events);
 	if (event->attr.comm)
@@ -3535,12 +3529,15 @@ static void unaccount_event(struct perf_event *event)
 	if (event->attr.freq)
 		atomic_dec(&nr_freq_events);
 	if (event->attr.context_switch) {
-		static_key_slow_dec_deferred(&perf_sched_events);
+		dec = true;
 		atomic_dec(&nr_switch_events);
 	}
 	if (is_cgroup_event(event))
-		static_key_slow_dec_deferred(&perf_sched_events);
+		dec = true;
 	if (has_branch_stack(event))
+		dec = true;
+
+	if (dec)
 		static_key_slow_dec_deferred(&perf_sched_events);
 
 	unaccount_event_cpu(event, event->cpu);
@@ -3556,7 +3553,7 @@ static void unaccount_event(struct perf_event *event)
  *  3) two matching events on the same context.
  *
  * The former two cases are handled in the allocation path (perf_event_alloc(),
- * __free_event()), the latter -- before the first perf_install_in_context().
+ * _free_event()), the latter -- before the first perf_install_in_context().
  */
 static int exclusive_event_init(struct perf_event *event)
 {
@@ -3631,29 +3628,6 @@ static bool exclusive_event_installable(struct perf_event *event,
 	return true;
 }
 
-static void __free_event(struct perf_event *event)
-{
-	if (!event->parent) {
-		if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
-			put_callchain_buffers();
-	}
-
-	perf_event_free_bpf_prog(event);
-
-	if (event->destroy)
-		event->destroy(event);
-
-	if (event->ctx)
-		put_ctx(event->ctx);
-
-	if (event->pmu) {
-		exclusive_event_destroy(event);
-		module_put(event->pmu->module);
-	}
-
-	call_rcu(&event->rcu_head, free_event_rcu);
-}
-
 static void _free_event(struct perf_event *event)
 {
 	irq_work_sync(&event->pending);
@@ -3675,7 +3649,25 @@ static void _free_event(struct perf_event *event)
 	if (is_cgroup_event(event))
 		perf_detach_cgroup(event);
 
-	__free_event(event);
+	if (!event->parent) {
+		if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
+			put_callchain_buffers();
+	}
+
+	perf_event_free_bpf_prog(event);
+
+	if (event->destroy)
+		event->destroy(event);
+
+	if (event->ctx)
+		put_ctx(event->ctx);
+
+	if (event->pmu) {
+		exclusive_event_destroy(event);
+		module_put(event->pmu->module);
+	}
+
+	call_rcu(&event->rcu_head, free_event_rcu);
 }
 
 /*
@@ -3702,14 +3694,13 @@ static void perf_remove_from_owner(struct perf_event *event)
 	struct task_struct *owner;
 
 	rcu_read_lock();
-	owner = ACCESS_ONCE(event->owner);
 	/*
-	 * Matches the smp_wmb() in perf_event_exit_task(). If we observe
-	 * !owner it means the list deletion is complete and we can indeed
-	 * free this event, otherwise we need to serialize on
+	 * Matches the smp_store_release() in perf_event_exit_task(). If we
+	 * observe !owner it means the list deletion is complete and we can
+	 * indeed free this event, otherwise we need to serialize on
 	 * owner->perf_event_mutex.
 	 */
-	smp_read_barrier_depends();
+	owner = lockless_dereference(event->owner);
 	if (owner) {
 		/*
 		 * Since delayed_put_task_struct() also drops the last
@@ -3737,8 +3728,10 @@ static void perf_remove_from_owner(struct perf_event *event)
 		 * ensured they're done, and we can proceed with freeing the
 		 * event.
 		 */
-		if (event->owner)
+		if (event->owner) {
 			list_del_init(&event->owner_entry);
+			smp_store_release(&event->owner, NULL);
+		}
 		mutex_unlock(&owner->perf_event_mutex);
 		put_task_struct(owner);
 	}
@@ -3746,36 +3739,98 @@ static void perf_remove_from_owner(struct perf_event *event)
 
 static void put_event(struct perf_event *event)
 {
-	struct perf_event_context *ctx;
-
 	if (!atomic_long_dec_and_test(&event->refcount))
 		return;
 
+	_free_event(event);
+}
+
+/*
+ * Kill an event dead; while event:refcount will preserve the event
+ * object, it will not preserve its functionality. Once the last 'user'
+ * gives up the object, we'll destroy the thing.
+ */
+int perf_event_release_kernel(struct perf_event *event)
+{
+	struct perf_event_context *ctx;
+	struct perf_event *child, *tmp;
+
 	if (!is_kernel_event(event))
 		perf_remove_from_owner(event);
 
+	ctx = perf_event_ctx_lock(event);
+	WARN_ON_ONCE(ctx->parent_ctx);
+	perf_remove_from_context(event, DETACH_GROUP | DETACH_STATE);
+	perf_event_ctx_unlock(event, ctx);
+
 	/*
-	 * There are two ways this annotation is useful:
+	 * At this point we must have event->state == PERF_EVENT_STATE_EXIT,
+	 * either from the above perf_remove_from_context() or through
+	 * perf_event_exit_event().
 	 *
-	 *  1) there is a lock recursion from perf_event_exit_task
-	 *     see the comment there.
+	 * Therefore, anybody acquiring event->child_mutex after the below
+	 * loop _must_ also see this, most importantly inherit_event() which
+	 * will avoid placing more children on the list.
 	 *
-	 *  2) there is a lock-inversion with mmap_sem through
-	 *     perf_read_group(), which takes faults while
-	 *     holding ctx->mutex, however this is called after
-	 *     the last filedesc died, so there is no possibility
-	 *     to trigger the AB-BA case.
+	 * Thus this guarantees that we will in fact observe and kill _ALL_
+	 * child events.
 	 */
-	ctx = perf_event_ctx_lock_nested(event, SINGLE_DEPTH_NESTING);
-	WARN_ON_ONCE(ctx->parent_ctx);
-	perf_remove_from_context(event, true);
-	perf_event_ctx_unlock(event, ctx);
+	WARN_ON_ONCE(event->state != PERF_EVENT_STATE_EXIT);
 
-	_free_event(event);
-}
+again:
+	mutex_lock(&event->child_mutex);
+	list_for_each_entry(child, &event->child_list, child_list) {
 
-int perf_event_release_kernel(struct perf_event *event)
-{
+		/*
+		 * Cannot change, child events are not migrated, see the
+		 * comment with perf_event_ctx_lock_nested().
+		 */
+		ctx = lockless_dereference(child->ctx);
+		/*
+		 * Since child_mutex nests inside ctx::mutex, we must jump
+		 * through hoops. We start by grabbing a reference on the ctx.
+		 *
+		 * Since the event cannot get freed while we hold the
+		 * child_mutex, the context must also exist and have a !0
+		 * reference count.
+		 */
+		get_ctx(ctx);
+
+		/*
+		 * Now that we have a ctx ref, we can drop child_mutex, and
+		 * acquire ctx::mutex without fear of it going away. Then we
+		 * can re-acquire child_mutex.
+		 */
+		mutex_unlock(&event->child_mutex);
+		mutex_lock(&ctx->mutex);
+		mutex_lock(&event->child_mutex);
+
+		/*
+		 * Now that we hold ctx::mutex and child_mutex, revalidate our
+		 * state, if child is still the first entry, it didn't get freed
+		 * and we can continue doing so.
+		 */
+		tmp = list_first_entry_or_null(&event->child_list,
+					       struct perf_event, child_list);
+		if (tmp == child) {
+			perf_remove_from_context(child, DETACH_GROUP);
+			list_del(&child->child_list);
+			free_event(child);
+			/*
+			 * This matches the refcount bump in inherit_event();
+			 * this can't be the last reference.
+			 */
+			put_event(event);
+		}
+
+		mutex_unlock(&event->child_mutex);
+		mutex_unlock(&ctx->mutex);
+		put_ctx(ctx);
+		goto again;
+	}
+	mutex_unlock(&event->child_mutex);
+
+	/* Must be the last reference */
 	put_event(event);
 	return 0;
 }
@@ -3786,46 +3841,10 @@ EXPORT_SYMBOL_GPL(perf_event_release_kernel);
  */
 static int perf_release(struct inode *inode, struct file *file)
 {
-	put_event(file->private_data);
+	perf_event_release_kernel(file->private_data);
 	return 0;
 }
 
-/*
- * Remove all orphanes events from the context.
- */
-static void orphans_remove_work(struct work_struct *work)
-{
-	struct perf_event_context *ctx;
-	struct perf_event *event, *tmp;
-
-	ctx = container_of(work, struct perf_event_context,
-			   orphans_remove.work);
-
-	mutex_lock(&ctx->mutex);
-	list_for_each_entry_safe(event, tmp, &ctx->event_list, event_entry) {
-		struct perf_event *parent_event = event->parent;
-
-		if (!is_orphaned_child(event))
-			continue;
-
-		perf_remove_from_context(event, true);
-
-		mutex_lock(&parent_event->child_mutex);
-		list_del_init(&event->child_list);
-		mutex_unlock(&parent_event->child_mutex);
-
-		free_event(event);
-		put_event(parent_event);
-	}
-
-	raw_spin_lock_irq(&ctx->lock);
-	ctx->orphans_remove_sched = false;
-	raw_spin_unlock_irq(&ctx->lock);
-	mutex_unlock(&ctx->mutex);
-
-	put_ctx(ctx);
-}
-
 u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running)
 {
 	struct perf_event *child;
@@ -4054,7 +4073,7 @@ static void _perf_event_reset(struct perf_event *event)
 /*
  * Holding the top-level event's child_mutex means that any
  * descendant process that has inherited this event will block
- * in sync_child_event if it goes to exit, thus satisfying the
+ * in perf_event_exit_event() if it goes to exit, thus satisfying the
  * task existence requirements of perf_event_enable/disable.
  */
 static void perf_event_for_each_child(struct perf_event *event,
@@ -4086,36 +4105,14 @@ static void perf_event_for_each(struct perf_event *event,
 		perf_event_for_each_child(sibling, func);
 }
 
-struct period_event {
-	struct perf_event *event;
-	u64 value;
-};
-
-static void ___perf_event_period(void *info)
-{
-	struct period_event *pe = info;
-	struct perf_event *event = pe->event;
-	u64 value = pe->value;
-
-	if (event->attr.freq) {
-		event->attr.sample_freq = value;
-	} else {
-		event->attr.sample_period = value;
-		event->hw.sample_period = value;
-	}
-
-	local64_set(&event->hw.period_left, 0);
-}
-
-static int __perf_event_period(void *info)
+static void __perf_event_period(struct perf_event *event,
+				struct perf_cpu_context *cpuctx,
+				struct perf_event_context *ctx,
+				void *info)
 {
-	struct period_event *pe = info;
-	struct perf_event *event = pe->event;
-	struct perf_event_context *ctx = event->ctx;
-	u64 value = pe->value;
+	u64 value = *((u64 *)info);
 	bool active;
 
-	raw_spin_lock(&ctx->lock);
 	if (event->attr.freq) {
 		event->attr.sample_freq = value;
 	} else {
@@ -4135,14 +4132,10 @@ static int __perf_event_period(void *info)
 		event->pmu->start(event, PERF_EF_RELOAD);
 		perf_pmu_enable(ctx->pmu);
 	}
-	raw_spin_unlock(&ctx->lock);
-
-	return 0;
 }
 
 static int perf_event_period(struct perf_event *event, u64 __user *arg)
 {
-	struct period_event pe = { .event = event, };
 	u64 value;
 
 	if (!is_sampling_event(event))
@@ -4157,10 +4150,7 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
 	if (event->attr.freq && value > sysctl_perf_event_sample_rate)
 		return -EINVAL;
 
-	pe.value = value;
-
-	event_function_call(event, __perf_event_period,
-			    ___perf_event_period, &pe);
+	event_function_call(event, __perf_event_period, &value);
 
 	return 0;
 }
@@ -4932,7 +4922,7 @@ static void perf_pending_event(struct irq_work *entry)
 
 	if (event->pending_disable) {
 		event->pending_disable = 0;
-		__perf_event_disable(event);
+		perf_event_disable_local(event);
 	}
 
 	if (event->pending_wakeup) {
@@ -7753,11 +7743,13 @@ static void account_event_cpu(struct perf_event *event, int cpu)
 
 static void account_event(struct perf_event *event)
 {
+	bool inc = false;
+
 	if (event->parent)
 		return;
 
 	if (event->attach_state & PERF_ATTACH_TASK)
-		static_key_slow_inc(&perf_sched_events.key);
+		inc = true;
 	if (event->attr.mmap || event->attr.mmap_data)
 		atomic_inc(&nr_mmap_events);
 	if (event->attr.comm)
@@ -7770,11 +7762,14 @@ static void account_event(struct perf_event *event)
 	}
 	if (event->attr.context_switch) {
 		atomic_inc(&nr_switch_events);
-		static_key_slow_inc(&perf_sched_events.key);
+		inc = true;
 	}
 	if (has_branch_stack(event))
-		static_key_slow_inc(&perf_sched_events.key);
+		inc = true;
 	if (is_cgroup_event(event))
+		inc = true;
+
+	if (inc)
 		static_key_slow_inc(&perf_sched_events.key);
 
 	account_event_cpu(event, event->cpu);
@@ -8422,11 +8417,11 @@ SYSCALL_DEFINE5(perf_event_open,
 		 * See perf_event_ctx_lock() for comments on the details
 		 * of swizzling perf_event::ctx.
 		 */
-		perf_remove_from_context(group_leader, false);
+		perf_remove_from_context(group_leader, 0);
 
 		list_for_each_entry(sibling, &group_leader->sibling_list,
 				    group_entry) {
-			perf_remove_from_context(sibling, false);
+			perf_remove_from_context(sibling, 0);
 			put_ctx(gctx);
 		}
 
@@ -8479,6 +8474,8 @@ SYSCALL_DEFINE5(perf_event_open,
 	perf_event__header_size(event);
 	perf_event__id_header_size(event);
 
+	event->owner = current;
+
 	perf_install_in_context(ctx, event, event->cpu);
 	perf_unpin_context(ctx);
 
@@ -8488,8 +8485,6 @@ SYSCALL_DEFINE5(perf_event_open,
 
 	put_online_cpus();
 
-	event->owner = current;
-
 	mutex_lock(&current->perf_event_mutex);
 	list_add_tail(&event->owner_entry, &current->perf_event_list);
 	mutex_unlock(&current->perf_event_mutex);
@@ -8556,7 +8551,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 	}
 
 	/* Mark owner so we could distinguish it from user events. */
-	event->owner = EVENT_OWNER_KERNEL;
+	event->owner = TASK_TOMBSTONE;
 
 	account_event(event);
 
@@ -8606,7 +8601,7 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
 	mutex_lock_double(&src_ctx->mutex, &dst_ctx->mutex);
 	list_for_each_entry_safe(event, tmp, &src_ctx->event_list,
 				 event_entry) {
-		perf_remove_from_context(event, false);
+		perf_remove_from_context(event, 0);
 		unaccount_event_cpu(event, src_cpu);
 		put_ctx(src_ctx);
 		list_add(&event->migrate_entry, &events);
@@ -8673,33 +8668,15 @@ static void sync_child_event(struct perf_event *child_event,
 		     &parent_event->child_total_time_enabled);
 	atomic64_add(child_event->total_time_running,
 		     &parent_event->child_total_time_running);
-
-	/*
-	 * Remove this event from the parent's list
-	 */
-	WARN_ON_ONCE(parent_event->ctx->parent_ctx);
-	mutex_lock(&parent_event->child_mutex);
-	list_del_init(&child_event->child_list);
-	mutex_unlock(&parent_event->child_mutex);
-
-	/*
-	 * Make sure user/parent get notified, that we just
-	 * lost one event.
-	 */
-	perf_event_wakeup(parent_event);
-
-	/*
-	 * Release the parent event, if this was the last
-	 * reference to it.
-	 */
-	put_event(parent_event);
 }
 
 static void
-__perf_event_exit_task(struct perf_event *child_event,
-			 struct perf_event_context *child_ctx,
-			 struct task_struct *child)
+perf_event_exit_event(struct perf_event *child_event,
+		      struct perf_event_context *child_ctx,
+		      struct task_struct *child)
 {
+	struct perf_event *parent_event = child_event->parent;
+
 	/*
 	 * Do not destroy the 'original' grouping; because of the context
 	 * switch optimization the original events could've ended up in a
@@ -8712,57 +8689,86 @@ __perf_event_exit_task(struct perf_event *child_event,
 	 * Do destroy all inherited groups, we don't care about those
 	 * and being thorough is better.
 	 */
-	perf_remove_from_context(child_event, !!child_event->parent);
+	raw_spin_lock_irq(&child_ctx->lock);
+	WARN_ON_ONCE(child_ctx->is_active);
+
+	if (parent_event)
+		perf_group_detach(child_event);
+	list_del_event(child_event, child_ctx);
+	child_event->state = PERF_EVENT_STATE_EXIT; /* see perf_event_release_kernel() */
+	raw_spin_unlock_irq(&child_ctx->lock);
 
 	/*
-	 * It can happen that the parent exits first, and has events
-	 * that are still around due to the child reference. These
-	 * events need to be zapped.
+	 * Parent events are governed by their filedesc, retain them.
 	 */
-	if (child_event->parent) {
-		sync_child_event(child_event, child);
-		free_event(child_event);
-	} else {
-		child_event->state = PERF_EVENT_STATE_EXIT;
+	if (!parent_event) {
 		perf_event_wakeup(child_event);
+		return;
 	}
+	/*
+	 * Child events can be cleaned up.
+	 */
+
+	sync_child_event(child_event, child);
+
+	/*
+	 * Remove this event from the parent's list
+	 */
+	WARN_ON_ONCE(parent_event->ctx->parent_ctx);
+	mutex_lock(&parent_event->child_mutex);
+	list_del_init(&child_event->child_list);
+	mutex_unlock(&parent_event->child_mutex);
+
+	/*
+	 * Kick perf_poll() for is_event_hup().
+	 */
+	perf_event_wakeup(parent_event);
+	free_event(child_event);
+	put_event(parent_event);
 }
 
 static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 {
-	struct perf_event *child_event, *next;
 	struct perf_event_context *child_ctx, *clone_ctx = NULL;
-	unsigned long flags;
+	struct perf_event *child_event, *next;
+
+	WARN_ON_ONCE(child != current);
 
-	if (likely(!child->perf_event_ctxp[ctxn]))
+	child_ctx = perf_pin_task_context(child, ctxn);
+	if (!child_ctx)
 		return;
 
-	local_irq_save(flags);
 	/*
-	 * We can't reschedule here because interrupts are disabled,
-	 * and either child is current or it is a task that can't be
-	 * scheduled, so we are now safe from rescheduling changing
-	 * our context.
+	 * In order to reduce the amount of tricky in ctx tear-down, we hold
+	 * ctx::mutex over the entire thing. This serializes against almost
+	 * everything that wants to access the ctx.
+	 *
+	 * The exception is sys_perf_event_open() /
+	 * perf_event_create_kernel_count() which does find_get_context()
+	 * without ctx::mutex (it cannot because of the move_group double mutex
+	 * lock thing). See the comments in perf_install_in_context().
 	 */
-	child_ctx = rcu_dereference_raw(child->perf_event_ctxp[ctxn]);
+	mutex_lock(&child_ctx->mutex);
 
 	/*
-	 * Take the context lock here so that if find_get_context is
-	 * reading child->perf_event_ctxp, we wait until it has
-	 * incremented the context's refcount before we do put_ctx below.
+	 * In a single ctx::lock section, de-schedule the events and detach the
+	 * context from the task such that we cannot ever get it scheduled back
+	 * in.
 	 */
-	raw_spin_lock(&child_ctx->lock);
-	task_ctx_sched_out(child_ctx);
-	child->perf_event_ctxp[ctxn] = NULL;
+	raw_spin_lock_irq(&child_ctx->lock);
+	task_ctx_sched_out(__get_cpu_context(child_ctx), child_ctx);
 
 	/*
-	 * If this context is a clone; unclone it so it can't get
-	 * swapped to another process while we're removing all
-	 * the events from it.
+	 * Now that the context is inactive, destroy the task <-> ctx relation
+	 * and mark the context dead.
 	 */
+	RCU_INIT_POINTER(child->perf_event_ctxp[ctxn], NULL);
+	put_ctx(child_ctx); /* cannot be last */
+	WRITE_ONCE(child_ctx->task, TASK_TOMBSTONE);
+	put_task_struct(current); /* cannot be last */
+
 	clone_ctx = unclone_ctx(child_ctx);
-	update_context_time(child_ctx);
-	raw_spin_unlock_irqrestore(&child_ctx->lock, flags);
+	raw_spin_unlock_irq(&child_ctx->lock);
 
 	if (clone_ctx)
 		put_ctx(clone_ctx);
@@ -8774,20 +8780,8 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 	 */
 	perf_event_task(child, child_ctx, 0);
 
-	/*
-	 * We can recurse on the same lock type through:
-	 *
-	 *   __perf_event_exit_task()
-	 *     sync_child_event()
-	 *       put_event()
-	 *         mutex_lock(&ctx->mutex)
-	 *
-	 * But since its the parent context it won't be the same instance.
-	 */
-	mutex_lock(&child_ctx->mutex);
-
 	list_for_each_entry_safe(child_event, next, &child_ctx->event_list, event_entry)
-		__perf_event_exit_task(child_event, child_ctx, child);
+		perf_event_exit_event(child_event, child_ctx, child);
 
 	mutex_unlock(&child_ctx->mutex);
 
@@ -8812,8 +8806,7 @@ void perf_event_exit_task(struct task_struct *child)
 		 * the owner, closes a race against perf_release() where
 		 * we need to serialize on the owner->perf_event_mutex.
 		 */
-		smp_wmb();
-		event->owner = NULL;
+		smp_store_release(&event->owner, NULL);
 	}
 	mutex_unlock(&child->perf_event_mutex);
 
@@ -8896,21 +8889,20 @@ void perf_event_delayed_put(struct task_struct *task)
 		WARN_ON_ONCE(task->perf_event_ctxp[ctxn]);
 }
 
-struct perf_event *perf_event_get(unsigned int fd)
+struct file *perf_event_get(unsigned int fd)
 {
-	int err;
-	struct fd f;
-	struct perf_event *event;
+	struct file *file;
 
-	err = perf_fget_light(fd, &f);
-	if (err)
-		return ERR_PTR(err);
+	file = fget_raw(fd);
+	if (!file)
+		return ERR_PTR(-EBADF);
 
-	event = f.file->private_data;
-	atomic_long_inc(&event->refcount);
-	fdput(f);
+	if (file->f_op != &perf_fops) {
+		fput(file);
+		return ERR_PTR(-EBADF);
+	}
 
-	return event;
+	return file;
 }
 
 const struct perf_event_attr *perf_event_attrs(struct perf_event *event)
@@ -8953,8 +8945,16 @@ inherit_event(struct perf_event *parent_event,
 	if (IS_ERR(child_event))
 		return child_event;
 
+	/*
+	 * is_orphaned_event() and list_add_tail(&parent_event->child_list)
+	 * must be under the same lock in order to serialize against
+	 * perf_event_release_kernel(), such that either we must observe
+	 * is_orphaned_event() or they will observe us on the child_list.
+	 */
+	mutex_lock(&parent_event->child_mutex);
 	if (is_orphaned_event(parent_event) ||
 	    !atomic_long_inc_not_zero(&parent_event->refcount)) {
+		mutex_unlock(&parent_event->child_mutex);
 		free_event(child_event);
 		return NULL;
 	}
@@ -9002,8 +9002,6 @@ inherit_event(struct perf_event *parent_event,
 	/*
 	 * Link this into the parent event's child list
 	 */
-	WARN_ON_ONCE(parent_event->ctx->parent_ctx);
-	mutex_lock(&parent_event->child_mutex);
 	list_add_tail(&child_event->child_list, &parent_event->child_list);
 	mutex_unlock(&parent_event->child_mutex);
 
@@ -9221,13 +9219,14 @@ static void perf_event_init_cpu(int cpu)
 #if defined CONFIG_HOTPLUG_CPU || defined CONFIG_KEXEC_CORE
 static void __perf_event_exit_context(void *__info)
 {
-	struct remove_event re = { .detach_group = true };
 	struct perf_event_context *ctx = __info;
+	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
+	struct perf_event *event;
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(re.event, &ctx->event_list, event_entry)
-		__perf_remove_from_context(&re);
-	rcu_read_unlock();
+	raw_spin_lock(&ctx->lock);
+	list_for_each_entry(event, &ctx->event_list, event_entry)
+		__perf_remove_from_context(event, cpuctx, ctx, (void *)DETACH_GROUP);
+	raw_spin_unlock(&ctx->lock);
 }
 
 static void perf_event_exit_cpu_context(int cpu)
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 92ce5f4ccc26..3f8cb1e14588 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -444,7 +444,7 @@ int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *att
 	 * current task.
 	 */
 	if (irqs_disabled() && bp->ctx && bp->ctx->task == current)
-		__perf_event_disable(bp);
+		perf_event_disable_local(bp);
 	else
 		perf_event_disable(bp);
 
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index adfdc0536117..1faad2cfdb9e 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -459,6 +459,25 @@ static void rb_free_aux_page(struct ring_buffer *rb, int idx)
 	__free_page(page);
 }
 
+static void __rb_free_aux(struct ring_buffer *rb)
+{
+	int pg;
+
+	if (rb->aux_priv) {
+		rb->free_aux(rb->aux_priv);
+		rb->free_aux = NULL;
+		rb->aux_priv = NULL;
+	}
+
+	if (rb->aux_nr_pages) {
+		for (pg = 0; pg < rb->aux_nr_pages; pg++)
+			rb_free_aux_page(rb, pg);
+
+		kfree(rb->aux_pages);
+		rb->aux_nr_pages = 0;
+	}
+}
+
 int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event,
 		 pgoff_t pgoff, int nr_pages, long watermark, int flags)
 {
@@ -547,30 +566,11 @@ out:
 	if (!ret)
 		rb->aux_pgoff = pgoff;
 	else
-		rb_free_aux(rb);
+		__rb_free_aux(rb);
 
 	return ret;
 }
 
-static void __rb_free_aux(struct ring_buffer *rb)
-{
-	int pg;
-
-	if (rb->aux_priv) {
-		rb->free_aux(rb->aux_priv);
-		rb->free_aux = NULL;
-		rb->aux_priv = NULL;
-	}
-
-	if (rb->aux_nr_pages) {
-		for (pg = 0; pg < rb->aux_nr_pages; pg++)
-			rb_free_aux_page(rb, pg);
-
-		kfree(rb->aux_pages);
-		rb->aux_nr_pages = 0;
-	}
-}
-
 void rb_free_aux(struct ring_buffer *rb)
 {
 	if (atomic_dec_and_test(&rb->aux_refcount))
diff --git a/kernel/futex.c b/kernel/futex.c
index 0773f2b23b10..5d6ce6413ef1 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1191,7 +1191,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this,
 	if (pi_state->owner != current)
 		return -EINVAL;
 
-	raw_spin_lock(&pi_state->pi_mutex.wait_lock);
+	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 	new_owner = rt_mutex_next_owner(&pi_state->pi_mutex);
 
 	/*
@@ -1217,22 +1217,22 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this,
 	else if (curval != uval)
 		ret = -EINVAL;
 	if (ret) {
-		raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
+		raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 		return ret;
 	}
 
-	raw_spin_lock_irq(&pi_state->owner->pi_lock);
+	raw_spin_lock(&pi_state->owner->pi_lock);
 	WARN_ON(list_empty(&pi_state->list));
 	list_del_init(&pi_state->list);
-	raw_spin_unlock_irq(&pi_state->owner->pi_lock);
+	raw_spin_unlock(&pi_state->owner->pi_lock);
 
-	raw_spin_lock_irq(&new_owner->pi_lock);
+	raw_spin_lock(&new_owner->pi_lock);
 	WARN_ON(!list_empty(&pi_state->list));
 	list_add(&pi_state->list, &new_owner->pi_state_list);
 	pi_state->owner = new_owner;
-	raw_spin_unlock_irq(&new_owner->pi_lock);
+	raw_spin_unlock(&new_owner->pi_lock);
 
-	raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
+	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 
 	deboost = rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q);
 
@@ -2127,11 +2127,11 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 		 * we returned due to timeout or signal without taking the
 		 * rt_mutex. Too late.
 		 */
-		raw_spin_lock(&q->pi_state->pi_mutex.wait_lock);
+		raw_spin_lock_irq(&q->pi_state->pi_mutex.wait_lock);
 		owner = rt_mutex_owner(&q->pi_state->pi_mutex);
 		if (!owner)
 			owner = rt_mutex_next_owner(&q->pi_state->pi_mutex);
-		raw_spin_unlock(&q->pi_state->pi_mutex.wait_lock);
+		raw_spin_unlock_irq(&q->pi_state->pi_mutex.wait_lock);
 		ret = fixup_pi_state_owner(uaddr, q, owner);
 		goto out;
 	}
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index a302cf9a2126..57bff7857e87 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -138,7 +138,8 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc)
 	unsigned int flags = 0, irq = desc->irq_data.irq;
 	struct irqaction *action = desc->action;
 
-	do {
+	/* action might have become NULL since we dropped the lock */
+	while (action) {
 		irqreturn_t res;
 
 		trace_irq_handler_entry(irq, action);
@@ -173,7 +174,7 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc)
 
 		retval |= res;
 		action = action->next;
-	} while (action);
+	}
 
 	add_interrupt_randomness(irq, flags);
 
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 6e655f7acd3b..3e56d2f03e24 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -575,10 +575,15 @@ unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec)
 	unsigned int type = IRQ_TYPE_NONE;
 	int virq;
 
-	if (fwspec->fwnode)
-		domain = irq_find_matching_fwnode(fwspec->fwnode, DOMAIN_BUS_ANY);
-	else
+	if (fwspec->fwnode) {
+		domain = irq_find_matching_fwnode(fwspec->fwnode,
+						  DOMAIN_BUS_WIRED);
+		if (!domain)
+			domain = irq_find_matching_fwnode(fwspec->fwnode,
+							  DOMAIN_BUS_ANY);
+	} else {
 		domain = irq_default_domain;
+	}
 
 	if (!domain) {
 		pr_warn("no irq domain found for %s !\n",
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 8251e75dd9c0..3e746607abe5 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -99,13 +99,14 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
  * 2) Drop lock->wait_lock
  * 3) Try to unlock the lock with cmpxchg
  */
-static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock)
+static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock,
+					unsigned long flags)
 	__releases(lock->wait_lock)
 {
 	struct task_struct *owner = rt_mutex_owner(lock);
 
 	clear_rt_mutex_waiters(lock);
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 	/*
 	 * If a new waiter comes in between the unlock and the cmpxchg
 	 * we have two situations:
@@ -147,11 +148,12 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
 /*
  * Simple slow path only version: lock->owner is protected by lock->wait_lock.
  */
-static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock)
+static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock,
+					unsigned long flags)
 	__releases(lock->wait_lock)
 {
 	lock->owner = NULL;
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 	return true;
 }
 #endif
@@ -433,7 +435,6 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	int ret = 0, depth = 0;
 	struct rt_mutex *lock;
 	bool detect_deadlock;
-	unsigned long flags;
 	bool requeue = true;
 
 	detect_deadlock = rt_mutex_cond_detect_deadlock(orig_waiter, chwalk);
@@ -476,7 +477,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	/*
 	 * [1] Task cannot go away as we did a get_task() before !
 	 */
-	raw_spin_lock_irqsave(&task->pi_lock, flags);
+	raw_spin_lock_irq(&task->pi_lock);
 
 	/*
 	 * [2] Get the waiter on which @task is blocked on.
@@ -560,7 +561,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	 * operations.
 	 */
 	if (!raw_spin_trylock(&lock->wait_lock)) {
-		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+		raw_spin_unlock_irq(&task->pi_lock);
 		cpu_relax();
 		goto retry;
 	}
@@ -591,7 +592,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		/*
 		 * No requeue[7] here. Just release @task [8]
 		 */
-		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+		raw_spin_unlock(&task->pi_lock);
 		put_task_struct(task);
 
 		/*
@@ -599,14 +600,14 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		 * If there is no owner of the lock, end of chain.
 		 */
 		if (!rt_mutex_owner(lock)) {
-			raw_spin_unlock(&lock->wait_lock);
+			raw_spin_unlock_irq(&lock->wait_lock);
 			return 0;
 		}
 
 		/* [10] Grab the next task, i.e. owner of @lock */
 		task = rt_mutex_owner(lock);
 		get_task_struct(task);
-		raw_spin_lock_irqsave(&task->pi_lock, flags);
+		raw_spin_lock(&task->pi_lock);
 
 		/*
 		 * No requeue [11] here. We just do deadlock detection.
@@ -621,8 +622,8 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		top_waiter = rt_mutex_top_waiter(lock);
 
 		/* [13] Drop locks */
-		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
-		raw_spin_unlock(&lock->wait_lock);
+		raw_spin_unlock(&task->pi_lock);
+		raw_spin_unlock_irq(&lock->wait_lock);
 
 		/* If owner is not blocked, end of chain. */
 		if (!next_lock)
@@ -643,7 +644,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	rt_mutex_enqueue(lock, waiter);
 
 	/* [8] Release the task */
-	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+	raw_spin_unlock(&task->pi_lock);
 	put_task_struct(task);
 
 	/*
@@ -661,14 +662,14 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		 */
 		if (prerequeue_top_waiter != rt_mutex_top_waiter(lock))
 			wake_up_process(rt_mutex_top_waiter(lock)->task);
-		raw_spin_unlock(&lock->wait_lock);
+		raw_spin_unlock_irq(&lock->wait_lock);
 		return 0;
 	}
 
 	/* [10] Grab the next task, i.e. the owner of @lock */
 	task = rt_mutex_owner(lock);
 	get_task_struct(task);
-	raw_spin_lock_irqsave(&task->pi_lock, flags);
+	raw_spin_lock(&task->pi_lock);
 
 	/* [11] requeue the pi waiters if necessary */
 	if (waiter == rt_mutex_top_waiter(lock)) {
@@ -722,8 +723,8 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	top_waiter = rt_mutex_top_waiter(lock);
 
 	/* [13] Drop the locks */
-	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock(&task->pi_lock);
+	raw_spin_unlock_irq(&lock->wait_lock);
 
 	/*
 	 * Make the actual exit decisions [12], based on the stored
@@ -746,7 +747,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	goto again;
 
  out_unlock_pi:
-	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+	raw_spin_unlock_irq(&task->pi_lock);
  out_put_task:
 	put_task_struct(task);
 
@@ -756,7 +757,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 /*
  * Try to take an rt-mutex
  *
- * Must be called with lock->wait_lock held.
+ * Must be called with lock->wait_lock held and interrupts disabled
  *
  * @lock:   The lock to be acquired.
  * @task:   The task which wants to acquire the lock
@@ -766,8 +767,6 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
 				struct rt_mutex_waiter *waiter)
 {
-	unsigned long flags;
-
 	/*
 	 * Before testing whether we can acquire @lock, we set the
 	 * RT_MUTEX_HAS_WAITERS bit in @lock->owner. This forces all
@@ -852,7 +851,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
 	 * case, but conditionals are more expensive than a redundant
 	 * store.
 	 */
-	raw_spin_lock_irqsave(&task->pi_lock, flags);
+	raw_spin_lock(&task->pi_lock);
 	task->pi_blocked_on = NULL;
 	/*
 	 * Finish the lock acquisition. @task is the new owner. If
@@ -861,7 +860,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
 	 */
 	if (rt_mutex_has_waiters(lock))
 		rt_mutex_enqueue_pi(task, rt_mutex_top_waiter(lock));
-	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+	raw_spin_unlock(&task->pi_lock);
 
 takeit:
 	/* We got the lock. */
@@ -883,7 +882,7 @@ takeit:
  *
  * Prepare waiter and propagate pi chain
  *
- * This must be called with lock->wait_lock held.
+ * This must be called with lock->wait_lock held and interrupts disabled
  */
 static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 				   struct rt_mutex_waiter *waiter,
@@ -894,7 +893,6 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	struct rt_mutex_waiter *top_waiter = waiter;
 	struct rt_mutex *next_lock;
 	int chain_walk = 0, res;
-	unsigned long flags;
 
 	/*
 	 * Early deadlock detection. We really don't want the task to
@@ -908,7 +906,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	if (owner == task)
 		return -EDEADLK;
 
-	raw_spin_lock_irqsave(&task->pi_lock, flags);
+	raw_spin_lock(&task->pi_lock);
 	__rt_mutex_adjust_prio(task);
 	waiter->task = task;
 	waiter->lock = lock;
@@ -921,12 +919,12 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 
 	task->pi_blocked_on = waiter;
 
-	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+	raw_spin_unlock(&task->pi_lock);
 
 	if (!owner)
 		return 0;
 
-	raw_spin_lock_irqsave(&owner->pi_lock, flags);
+	raw_spin_lock(&owner->pi_lock);
 	if (waiter == rt_mutex_top_waiter(lock)) {
 		rt_mutex_dequeue_pi(owner, top_waiter);
 		rt_mutex_enqueue_pi(owner, waiter);
@@ -941,7 +939,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	/* Store the lock on which owner is blocked or NULL */
 	next_lock = task_blocked_on_lock(owner);
 
-	raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
+	raw_spin_unlock(&owner->pi_lock);
 	/*
 	 * Even if full deadlock detection is on, if the owner is not
 	 * blocked itself, we can avoid finding this out in the chain
@@ -957,12 +955,12 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	 */
 	get_task_struct(owner);
 
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock_irq(&lock->wait_lock);
 
 	res = rt_mutex_adjust_prio_chain(owner, chwalk, lock,
 					 next_lock, waiter, task);
 
-	raw_spin_lock(&lock->wait_lock);
+	raw_spin_lock_irq(&lock->wait_lock);
 
 	return res;
 }
@@ -971,15 +969,14 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
  * Remove the top waiter from the current tasks pi waiter tree and
  * queue it up.
  *
- * Called with lock->wait_lock held.
+ * Called with lock->wait_lock held and interrupts disabled.
  */
 static void mark_wakeup_next_waiter(struct wake_q_head *wake_q,
 				    struct rt_mutex *lock)
 {
 	struct rt_mutex_waiter *waiter;
-	unsigned long flags;
 
-	raw_spin_lock_irqsave(&current->pi_lock, flags);
+	raw_spin_lock(&current->pi_lock);
 
 	waiter = rt_mutex_top_waiter(lock);
 
@@ -1001,7 +998,7 @@ static void mark_wakeup_next_waiter(struct wake_q_head *wake_q,
 	 */
 	lock->owner = (void *) RT_MUTEX_HAS_WAITERS;
 
-	raw_spin_unlock_irqrestore(&current->pi_lock, flags);
+	raw_spin_unlock(&current->pi_lock);
 
 	wake_q_add(wake_q, waiter->task);
 }
@@ -1009,7 +1006,7 @@ static void mark_wakeup_next_waiter(struct wake_q_head *wake_q,
 /*
  * Remove a waiter from a lock and give up
  *
- * Must be called with lock->wait_lock held and
+ * Must be called with lock->wait_lock held and interrupts disabled. I must
  * have just failed to try_to_take_rt_mutex().
  */
 static void remove_waiter(struct rt_mutex *lock,
@@ -1018,12 +1015,11 @@ static void remove_waiter(struct rt_mutex *lock,
 	bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock));
 	struct task_struct *owner = rt_mutex_owner(lock);
 	struct rt_mutex *next_lock;
-	unsigned long flags;
 
-	raw_spin_lock_irqsave(&current->pi_lock, flags);
+	raw_spin_lock(&current->pi_lock);
 	rt_mutex_dequeue(lock, waiter);
 	current->pi_blocked_on = NULL;
-	raw_spin_unlock_irqrestore(&current->pi_lock, flags);
+	raw_spin_unlock(&current->pi_lock);
 
 	/*
 	 * Only update priority if the waiter was the highest priority
@@ -1032,7 +1028,7 @@ static void remove_waiter(struct rt_mutex *lock,
 	if (!owner || !is_top_waiter)
 		return;
 
-	raw_spin_lock_irqsave(&owner->pi_lock, flags);
+	raw_spin_lock(&owner->pi_lock);
 
 	rt_mutex_dequeue_pi(owner, waiter);
 
@@ -1044,7 +1040,7 @@ static void remove_waiter(struct rt_mutex *lock,
 	/* Store the lock on which owner is blocked or NULL */
 	next_lock = task_blocked_on_lock(owner);
 
-	raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
+	raw_spin_unlock(&owner->pi_lock);
 
 	/*
 	 * Don't walk the chain, if the owner task is not blocked
@@ -1056,12 +1052,12 @@ static void remove_waiter(struct rt_mutex *lock,
 	/* gets dropped in rt_mutex_adjust_prio_chain()! */
 	get_task_struct(owner);
 
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock_irq(&lock->wait_lock);
 
 	rt_mutex_adjust_prio_chain(owner, RT_MUTEX_MIN_CHAINWALK, lock,
 				   next_lock, NULL, current);
 
-	raw_spin_lock(&lock->wait_lock);
+	raw_spin_lock_irq(&lock->wait_lock);
 }
 
 /*
@@ -1097,11 +1093,11 @@ void rt_mutex_adjust_pi(struct task_struct *task)
  * __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop
  * @lock:		 the rt_mutex to take
  * @state:		 the state the task should block in (TASK_INTERRUPTIBLE
- * 			 or TASK_UNINTERRUPTIBLE)
+ *			 or TASK_UNINTERRUPTIBLE)
  * @timeout:		 the pre-initialized and started timer, or NULL for none
  * @waiter:		 the pre-initialized rt_mutex_waiter
  *
- * lock->wait_lock must be held by the caller.
+ * Must be called with lock->wait_lock held and interrupts disabled
  */
 static int __sched
 __rt_mutex_slowlock(struct rt_mutex *lock, int state,
@@ -1129,13 +1125,13 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state,
 				break;
 		}
 
-		raw_spin_unlock(&lock->wait_lock);
+		raw_spin_unlock_irq(&lock->wait_lock);
 
 		debug_rt_mutex_print_deadlock(waiter);
 
 		schedule();
 
-		raw_spin_lock(&lock->wait_lock);
+		raw_spin_lock_irq(&lock->wait_lock);
 		set_current_state(state);
 	}
 
@@ -1172,17 +1168,26 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 		  enum rtmutex_chainwalk chwalk)
 {
 	struct rt_mutex_waiter waiter;
+	unsigned long flags;
 	int ret = 0;
 
 	debug_rt_mutex_init_waiter(&waiter);
 	RB_CLEAR_NODE(&waiter.pi_tree_entry);
 	RB_CLEAR_NODE(&waiter.tree_entry);
 
-	raw_spin_lock(&lock->wait_lock);
+	/*
+	 * Technically we could use raw_spin_[un]lock_irq() here, but this can
+	 * be called in early boot if the cmpxchg() fast path is disabled
+	 * (debug, no architecture support). In this case we will acquire the
+	 * rtmutex with lock->wait_lock held. But we cannot unconditionally
+	 * enable interrupts in that early boot case. So we need to use the
+	 * irqsave/restore variants.
+	 */
+	raw_spin_lock_irqsave(&lock->wait_lock, flags);
 
 	/* Try to acquire the lock again: */
 	if (try_to_take_rt_mutex(lock, current, NULL)) {
-		raw_spin_unlock(&lock->wait_lock);
+		raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 		return 0;
 	}
 
@@ -1211,7 +1216,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	 */
 	fixup_rt_mutex_waiters(lock);
 
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
 	/* Remove pending timer: */
 	if (unlikely(timeout))
@@ -1227,6 +1232,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
  */
 static inline int rt_mutex_slowtrylock(struct rt_mutex *lock)
 {
+	unsigned long flags;
 	int ret;
 
 	/*
@@ -1238,10 +1244,10 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock)
 		return 0;
 
 	/*
-	 * The mutex has currently no owner. Lock the wait lock and
-	 * try to acquire the lock.
+	 * The mutex has currently no owner. Lock the wait lock and try to
+	 * acquire the lock. We use irqsave here to support early boot calls.
 	 */
-	raw_spin_lock(&lock->wait_lock);
+	raw_spin_lock_irqsave(&lock->wait_lock, flags);
 
 	ret = try_to_take_rt_mutex(lock, current, NULL);
 
@@ -1251,7 +1257,7 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock)
 	 */
 	fixup_rt_mutex_waiters(lock);
 
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
 	return ret;
 }
@@ -1263,7 +1269,10 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock)
 static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock,
 					struct wake_q_head *wake_q)
 {
-	raw_spin_lock(&lock->wait_lock);
+	unsigned long flags;
+
+	/* irqsave required to support early boot calls */
+	raw_spin_lock_irqsave(&lock->wait_lock, flags);
 
 	debug_rt_mutex_unlock(lock);
 
@@ -1302,10 +1311,10 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock,
 	 */
 	while (!rt_mutex_has_waiters(lock)) {
 		/* Drops lock->wait_lock ! */
-		if (unlock_rt_mutex_safe(lock) == true)
+		if (unlock_rt_mutex_safe(lock, flags) == true)
 			return false;
 		/* Relock the rtmutex and try again */
-		raw_spin_lock(&lock->wait_lock);
+		raw_spin_lock_irqsave(&lock->wait_lock, flags);
 	}
 
 	/*
@@ -1316,7 +1325,7 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock,
 	 */
 	mark_wakeup_next_waiter(wake_q, lock);
 
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
 	/* check PI boosting */
 	return true;
@@ -1596,10 +1605,10 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 {
 	int ret;
 
-	raw_spin_lock(&lock->wait_lock);
+	raw_spin_lock_irq(&lock->wait_lock);
 
 	if (try_to_take_rt_mutex(lock, task, NULL)) {
-		raw_spin_unlock(&lock->wait_lock);
+		raw_spin_unlock_irq(&lock->wait_lock);
 		return 1;
 	}
 
@@ -1620,7 +1629,7 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 	if (unlikely(ret))
 		remove_waiter(lock, waiter);
 
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock_irq(&lock->wait_lock);
 
 	debug_rt_mutex_print_deadlock(waiter);
 
@@ -1668,7 +1677,7 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
 {
 	int ret;
 
-	raw_spin_lock(&lock->wait_lock);
+	raw_spin_lock_irq(&lock->wait_lock);
 
 	set_current_state(TASK_INTERRUPTIBLE);
 
@@ -1684,7 +1693,7 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
 	 */
 	fixup_rt_mutex_waiters(lock);
 
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock_irq(&lock->wait_lock);
 
 	return ret;
 }
diff --git a/kernel/memremap.c b/kernel/memremap.c
index e517a16cb426..70ee3775de24 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -150,7 +150,7 @@ void devm_memunmap(struct device *dev, void *addr)
 }
 EXPORT_SYMBOL(devm_memunmap);
 
-pfn_t phys_to_pfn_t(dma_addr_t addr, unsigned long flags)
+pfn_t phys_to_pfn_t(phys_addr_t addr, unsigned long flags)
 {
 	return __pfn_to_pfn_t(addr >> PAGE_SHIFT, flags);
 }
@@ -183,7 +183,11 @@ EXPORT_SYMBOL(put_zone_device_page);
 
 static void pgmap_radix_release(struct resource *res)
 {
-	resource_size_t key;
+	resource_size_t key, align_start, align_size, align_end;
+
+	align_start = res->start & ~(SECTION_SIZE - 1);
+	align_size = ALIGN(resource_size(res), SECTION_SIZE);
+	align_end = align_start + align_size - 1;
 
 	mutex_lock(&pgmap_lock);
 	for (key = res->start; key <= res->end; key += SECTION_SIZE)
@@ -226,12 +230,11 @@ static void devm_memremap_pages_release(struct device *dev, void *data)
 		percpu_ref_put(pgmap->ref);
 	}
 
-	pgmap_radix_release(res);
-
 	/* pages are dead and unused, undo the arch mapping */
 	align_start = res->start & ~(SECTION_SIZE - 1);
 	align_size = ALIGN(resource_size(res), SECTION_SIZE);
 	arch_remove_memory(align_start, align_size);
+	pgmap_radix_release(res);
 	dev_WARN_ONCE(dev, pgmap->altmap && pgmap->altmap->alloc,
 			"%s: failed to free all reserved pages\n", __func__);
 }
@@ -267,7 +270,7 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 {
 	int is_ram = region_intersects(res->start, resource_size(res),
 			"System RAM");
-	resource_size_t key, align_start, align_size;
+	resource_size_t key, align_start, align_size, align_end;
 	struct dev_pagemap *pgmap;
 	struct page_map *page_map;
 	unsigned long pfn;
@@ -309,7 +312,10 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 
 	mutex_lock(&pgmap_lock);
 	error = 0;
-	for (key = res->start; key <= res->end; key += SECTION_SIZE) {
+	align_start = res->start & ~(SECTION_SIZE - 1);
+	align_size = ALIGN(resource_size(res), SECTION_SIZE);
+	align_end = align_start + align_size - 1;
+	for (key = align_start; key <= align_end; key += SECTION_SIZE) {
 		struct dev_pagemap *dup;
 
 		rcu_read_lock();
@@ -336,8 +342,6 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 	if (nid < 0)
 		nid = numa_mem_id();
 
-	align_start = res->start & ~(SECTION_SIZE - 1);
-	align_size = ALIGN(resource_size(res), SECTION_SIZE);
 	error = arch_add_memory(nid, align_start, align_size, true);
 	if (error)
 		goto err_add_memory;
diff --git a/kernel/pid.c b/kernel/pid.c
index f4ad91b746f1..4d73a834c7e6 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -588,7 +588,7 @@ void __init pidhash_init(void)
 
 void __init pidmap_init(void)
 {
-	/* Veryify no one has done anything silly */
+	/* Verify no one has done anything silly: */
 	BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_HASH_ADDING);
 
 	/* bump default and minimum pid_max based on number of cpus */
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 02e8dfaa1ce2..68d3ebc12601 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -235,7 +235,7 @@ config PM_TRACE_RTC
 
 config APM_EMULATION
 	tristate "Advanced Power Management Emulation"
-	depends on PM && SYS_SUPPORTS_APM_EMULATION
+	depends on SYS_SUPPORTS_APM_EMULATION
 	help
 	  APM is a BIOS specification for saving power using several different
 	  techniques. This is mostly useful for battery powered laptops with
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 63d3a24e081a..9503d590e5ef 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6840,7 +6840,7 @@ static void sched_init_numa(void)
 
 			sched_domains_numa_masks[i][j] = mask;
 
-			for (k = 0; k < nr_node_ids; k++) {
+			for_each_node(k) {
 				if (node_distance(j, k) > sched_domains_numa_distance[i])
 					continue;
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1926606ece80..56b7d4b83947 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1220,8 +1220,6 @@ static void task_numa_assign(struct task_numa_env *env,
 {
 	if (env->best_task)
 		put_task_struct(env->best_task);
-	if (p)
-		get_task_struct(p);
 
 	env->best_task = p;
 	env->best_imp = imp;
@@ -1289,20 +1287,30 @@ static void task_numa_compare(struct task_numa_env *env,
 	long imp = env->p->numa_group ? groupimp : taskimp;
 	long moveimp = imp;
 	int dist = env->dist;
+	bool assigned = false;
 
 	rcu_read_lock();
 
 	raw_spin_lock_irq(&dst_rq->lock);
 	cur = dst_rq->curr;
 	/*
-	 * No need to move the exiting task, and this ensures that ->curr
-	 * wasn't reaped and thus get_task_struct() in task_numa_assign()
-	 * is safe under RCU read lock.
-	 * Note that rcu_read_lock() itself can't protect from the final
-	 * put_task_struct() after the last schedule().
+	 * No need to move the exiting task or idle task.
 	 */
 	if ((cur->flags & PF_EXITING) || is_idle_task(cur))
 		cur = NULL;
+	else {
+		/*
+		 * The task_struct must be protected here to protect the
+		 * p->numa_faults access in the task_weight since the
+		 * numa_faults could already be freed in the following path:
+		 * finish_task_switch()
+		 *     --> put_task_struct()
+		 *         --> __put_task_struct()
+		 *             --> task_numa_free()
+		 */
+		get_task_struct(cur);
+	}
+
 	raw_spin_unlock_irq(&dst_rq->lock);
 
 	/*
@@ -1386,6 +1394,7 @@ balance:
 		 */
 		if (!load_too_imbalanced(src_load, dst_load, env)) {
 			imp = moveimp - 1;
+			put_task_struct(cur);
 			cur = NULL;
 			goto assign;
 		}
@@ -1411,9 +1420,16 @@ balance:
 		env->dst_cpu = select_idle_sibling(env->p, env->dst_cpu);
 
 assign:
+	assigned = true;
 	task_numa_assign(env, cur, imp);
 unlock:
 	rcu_read_unlock();
+	/*
+	 * The dst_rq->curr isn't assigned. The protection for task_struct is
+	 * finished.
+	 */
+	if (cur && !assigned)
+		put_task_struct(cur);
 }
 
 static void task_numa_find_cpu(struct task_numa_env *env,
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index de0e786b2667..544a7133cbd1 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -162,7 +162,7 @@ static void cpuidle_idle_call(void)
 	 */
 	if (idle_should_freeze()) {
 		entered_state = cpuidle_enter_freeze(drv, dev);
-		if (entered_state >= 0) {
+		if (entered_state > 0) {
 			local_irq_enable();
 			goto exit_idle;
 		}
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 580ac2d4024f..15a1795bbba1 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -316,24 +316,24 @@ static inline void seccomp_sync_threads(void)
 		put_seccomp_filter(thread);
 		smp_store_release(&thread->seccomp.filter,
 				  caller->seccomp.filter);
+
+		/*
+		 * Don't let an unprivileged task work around
+		 * the no_new_privs restriction by creating
+		 * a thread that sets it up, enters seccomp,
+		 * then dies.
+		 */
+		if (task_no_new_privs(caller))
+			task_set_no_new_privs(thread);
+
 		/*
 		 * Opt the other thread into seccomp if needed.
 		 * As threads are considered to be trust-realm
 		 * equivalent (see ptrace_may_access), it is safe to
 		 * allow one thread to transition the other.
 		 */
-		if (thread->seccomp.mode == SECCOMP_MODE_DISABLED) {
-			/*
-			 * Don't let an unprivileged task work around
-			 * the no_new_privs restriction by creating
-			 * a thread that sets it up, enters seccomp,
-			 * then dies.
-			 */
-			if (task_no_new_privs(caller))
-				task_set_no_new_privs(thread);
-
+		if (thread->seccomp.mode == SECCOMP_MODE_DISABLED)
 			seccomp_assign_mode(thread, SECCOMP_MODE_FILTER);
-		}
 	}
 }
 
diff --git a/kernel/signal.c b/kernel/signal.c
index f3f1f7a972fd..0508544c8ced 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -3508,8 +3508,10 @@ static int sigsuspend(sigset_t *set)
 	current->saved_sigmask = current->blocked;
 	set_current_blocked(set);
 
-	__set_current_state(TASK_INTERRUPTIBLE);
-	schedule();
+	while (!signal_pending(current)) {
+		__set_current_state(TASK_INTERRUPTIBLE);
+		schedule();
+	}
 	set_restore_sigmask();
 	return -ERESTARTNOHAND;
 }
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 435b8850dd80..fa909f9fd559 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -897,10 +897,10 @@ static int enqueue_hrtimer(struct hrtimer *timer,
  */
 static void __remove_hrtimer(struct hrtimer *timer,
 			     struct hrtimer_clock_base *base,
-			     unsigned long newstate, int reprogram)
+			     u8 newstate, int reprogram)
 {
 	struct hrtimer_cpu_base *cpu_base = base->cpu_base;
-	unsigned int state = timer->state;
+	u8 state = timer->state;
 
 	timer->state = newstate;
 	if (!(state & HRTIMER_STATE_ENQUEUED))
@@ -930,7 +930,7 @@ static inline int
 remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool restart)
 {
 	if (hrtimer_is_queued(timer)) {
-		unsigned long state = timer->state;
+		u8 state = timer->state;
 		int reprogram;
 
 		/*
@@ -954,6 +954,22 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool rest
 	return 0;
 }
 
+static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim,
+					    const enum hrtimer_mode mode)
+{
+#ifdef CONFIG_TIME_LOW_RES
+	/*
+	 * CONFIG_TIME_LOW_RES indicates that the system has no way to return
+	 * granular time values. For relative timers we add hrtimer_resolution
+	 * (i.e. one jiffie) to prevent short timeouts.
+	 */
+	timer->is_rel = mode & HRTIMER_MODE_REL;
+	if (timer->is_rel)
+		tim = ktime_add_safe(tim, ktime_set(0, hrtimer_resolution));
+#endif
+	return tim;
+}
+
 /**
  * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU
  * @timer:	the timer to be added
@@ -974,19 +990,10 @@ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 	/* Remove an active timer from the queue: */
 	remove_hrtimer(timer, base, true);
 
-	if (mode & HRTIMER_MODE_REL) {
+	if (mode & HRTIMER_MODE_REL)
 		tim = ktime_add_safe(tim, base->get_time());
-		/*
-		 * CONFIG_TIME_LOW_RES is a temporary way for architectures
-		 * to signal that they simply return xtime in
-		 * do_gettimeoffset(). In this case we want to round up by
-		 * resolution when starting a relative timer, to avoid short
-		 * timeouts. This will go away with the GTOD framework.
-		 */
-#ifdef CONFIG_TIME_LOW_RES
-		tim = ktime_add_safe(tim, ktime_set(0, hrtimer_resolution));
-#endif
-	}
+
+	tim = hrtimer_update_lowres(timer, tim, mode);
 
 	hrtimer_set_expires_range_ns(timer, tim, delta_ns);
 
@@ -1074,19 +1081,23 @@ EXPORT_SYMBOL_GPL(hrtimer_cancel);
 /**
  * hrtimer_get_remaining - get remaining time for the timer
  * @timer:	the timer to read
+ * @adjust:	adjust relative timers when CONFIG_TIME_LOW_RES=y
  */
-ktime_t hrtimer_get_remaining(const struct hrtimer *timer)
+ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust)
 {
 	unsigned long flags;
 	ktime_t rem;
 
 	lock_hrtimer_base(timer, &flags);
-	rem = hrtimer_expires_remaining(timer);
+	if (IS_ENABLED(CONFIG_TIME_LOW_RES) && adjust)
+		rem = hrtimer_expires_remaining_adjusted(timer);
+	else
+		rem = hrtimer_expires_remaining(timer);
 	unlock_hrtimer_base(timer, &flags);
 
 	return rem;
 }
-EXPORT_SYMBOL_GPL(hrtimer_get_remaining);
+EXPORT_SYMBOL_GPL(__hrtimer_get_remaining);
 
 #ifdef CONFIG_NO_HZ_COMMON
 /**
@@ -1220,6 +1231,14 @@ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
 	fn = timer->function;
 
 	/*
+	 * Clear the 'is relative' flag for the TIME_LOW_RES case. If the
+	 * timer is restarted with a period then it becomes an absolute
+	 * timer. If its not restarted it does not matter.
+	 */
+	if (IS_ENABLED(CONFIG_TIME_LOW_RES))
+		timer->is_rel = false;
+
+	/*
 	 * Because we run timers from hardirq context, there is no chance
 	 * they get migrated to another cpu, therefore its safe to unlock
 	 * the timer base.
diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c
index 8d262b467573..1d5c7204ddc9 100644
--- a/kernel/time/itimer.c
+++ b/kernel/time/itimer.c
@@ -26,7 +26,7 @@
  */
 static struct timeval itimer_get_remtime(struct hrtimer *timer)
 {
-	ktime_t rem = hrtimer_get_remaining(timer);
+	ktime_t rem = __hrtimer_get_remaining(timer, true);
 
 	/*
 	 * Racy but safe: if the itimer expires after the above
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 36f2ca09aa5e..6df8927c58a5 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -685,8 +685,18 @@ int ntp_validate_timex(struct timex *txc)
 		if (!capable(CAP_SYS_TIME))
 			return -EPERM;
 
-		if (!timeval_inject_offset_valid(&txc->time))
-			return -EINVAL;
+		if (txc->modes & ADJ_NANO) {
+			struct timespec ts;
+
+			ts.tv_sec = txc->time.tv_sec;
+			ts.tv_nsec = txc->time.tv_usec;
+			if (!timespec_inject_offset_valid(&ts))
+				return -EINVAL;
+
+		} else {
+			if (!timeval_inject_offset_valid(&txc->time))
+				return -EINVAL;
+		}
 	}
 
 	/*
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 31d11ac9fa47..f2826c35e918 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -760,7 +760,7 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting)
 	    (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE))
 		timr->it_overrun += (unsigned int) hrtimer_forward(timer, now, iv);
 
-	remaining = ktime_sub(hrtimer_get_expires(timer), now);
+	remaining = __hrtimer_expires_remaining_adjusted(timer, now);
 	/* Return 0 only, when the timer is expired and not pending */
 	if (remaining.tv64 <= 0) {
 		/*
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 9d7a053545f5..0b17424349eb 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -36,16 +36,17 @@
  */
 static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched);
 
-/*
- * The time, when the last jiffy update happened. Protected by jiffies_lock.
- */
-static ktime_t last_jiffies_update;
-
 struct tick_sched *tick_get_tick_sched(int cpu)
 {
 	return &per_cpu(tick_cpu_sched, cpu);
 }
 
+#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS)
+/*
+ * The time, when the last jiffy update happened. Protected by jiffies_lock.
+ */
+static ktime_t last_jiffies_update;
+
 /*
  * Must be called with interrupts disabled !
  */
@@ -151,6 +152,7 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs)
 	update_process_times(user_mode(regs));
 	profile_tick(CPU_PROFILING);
 }
+#endif
 
 #ifdef CONFIG_NO_HZ_FULL
 cpumask_var_t tick_nohz_full_mask;
@@ -993,9 +995,9 @@ static void tick_nohz_switch_to_nohz(void)
 	/* Get the next period */
 	next = tick_init_jiffy_update();
 
-	hrtimer_forward_now(&ts->sched_timer, tick_period);
 	hrtimer_set_expires(&ts->sched_timer, next);
-	tick_program_event(next, 1);
+	hrtimer_forward_now(&ts->sched_timer, tick_period);
+	tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
 	tick_nohz_activate(ts, NOHZ_MODE_LOWRES);
 }
 
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index f75e35b60149..ba7d8b288bb3 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -69,7 +69,7 @@ print_timer(struct seq_file *m, struct hrtimer *taddr, struct hrtimer *timer,
 	print_name_offset(m, taddr);
 	SEQ_printf(m, ", ");
 	print_name_offset(m, timer->function);
-	SEQ_printf(m, ", S:%02lx", timer->state);
+	SEQ_printf(m, ", S:%02x", timer->state);
 #ifdef CONFIG_TIMER_STATS
 	SEQ_printf(m, ", ");
 	print_name_offset(m, timer->start_site);
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 45dd798bcd37..326a75e884db 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -191,14 +191,17 @@ static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5)
 	struct bpf_map *map = (struct bpf_map *) (unsigned long) r1;
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	struct perf_event *event;
+	struct file *file;
 
 	if (unlikely(index >= array->map.max_entries))
 		return -E2BIG;
 
-	event = (struct perf_event *)array->ptrs[index];
-	if (!event)
+	file = (struct file *)array->ptrs[index];
+	if (unlikely(!file))
 		return -ENOENT;
 
+	event = file->private_data;
+
 	/* make sure event is local and doesn't have pmu::count */
 	if (event->oncpu != smp_processor_id() ||
 	    event->pmu->count)
@@ -228,6 +231,7 @@ static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 index, u64 r4, u64 size)
 	void *data = (void *) (long) r4;
 	struct perf_sample_data sample_data;
 	struct perf_event *event;
+	struct file *file;
 	struct perf_raw_record raw = {
 		.size = size,
 		.data = data,
@@ -236,10 +240,12 @@ static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 index, u64 r4, u64 size)
 	if (unlikely(index >= array->map.max_entries))
 		return -E2BIG;
 
-	event = (struct perf_event *)array->ptrs[index];
-	if (unlikely(!event))
+	file = (struct file *)array->ptrs[index];
+	if (unlikely(!file))
 		return -ENOENT;
 
+	event = file->private_data;
+
 	if (unlikely(event->attr.type != PERF_TYPE_SOFTWARE ||
 		     event->attr.config != PERF_COUNT_SW_BPF_OUTPUT))
 		return -EINVAL;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 87fb9801bd9e..d9293402ee68 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1751,7 +1751,7 @@ void trace_buffer_unlock_commit_regs(struct trace_array *tr,
 {
 	__buffer_unlock_commit(buffer, event);
 
-	ftrace_trace_stack(tr, buffer, flags, 6, pc, regs);
+	ftrace_trace_stack(tr, buffer, flags, 0, pc, regs);
 	ftrace_trace_userstack(buffer, flags, pc);
 }
 EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit_regs);
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index dda9e6742950..202df6cffcca 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -126,6 +126,13 @@ check_stack(unsigned long ip, unsigned long *stack)
 	}
 
 	/*
+	 * Some archs may not have the passed in ip in the dump.
+	 * If that happens, we need to show everything.
+	 */
+	if (i == stack_trace_max.nr_entries)
+		i = 0;
+
+	/*
 	 * Now find where in the stack these are.
 	 */
 	x = 0;