Merge branch 'fortglx/4.12/time' of https://git.linaro.org/people/john.stultz/linux into timers/core

Pull timekeeping changes from John Stultz:

 Main changes are the initial steps of Nicoli's work to make the clockevent
 timers be corrected for NTP adjustments. Then a few smaller fixes that
 I've queued, and adding Stephen Boyd to the maintainers list for
 timekeeping.

15 files changed, 256 insertions, 104 deletions

diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 3ea87fb19a94..afe5bab376c9 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -13,11 +13,12 @@
 #include <linux/bpf.h>
 #include <linux/jhash.h>
 #include <linux/filter.h>
+#include <linux/rculist_nulls.h>
 #include "percpu_freelist.h"
 #include "bpf_lru_list.h"
 
 struct bucket {
-	struct hlist_head head;
+	struct hlist_nulls_head head;
 	raw_spinlock_t lock;
 };
 
@@ -44,9 +45,14 @@ enum extra_elem_state {
 /* each htab element is struct htab_elem + key + value */
 struct htab_elem {
 	union {
-		struct hlist_node hash_node;
-		struct bpf_htab *htab;
-		struct pcpu_freelist_node fnode;
+		struct hlist_nulls_node hash_node;
+		struct {
+			void *padding;
+			union {
+				struct bpf_htab *htab;
+				struct pcpu_freelist_node fnode;
+			};
+		};
 	};
 	union {
 		struct rcu_head rcu;
@@ -162,7 +168,8 @@ skip_percpu_elems:
 				 offsetof(struct htab_elem, lru_node),
 				 htab->elem_size, htab->map.max_entries);
 	else
-		pcpu_freelist_populate(&htab->freelist, htab->elems,
+		pcpu_freelist_populate(&htab->freelist,
+				       htab->elems + offsetof(struct htab_elem, fnode),
 				       htab->elem_size, htab->map.max_entries);
 
 	return 0;
@@ -217,6 +224,11 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 	int err, i;
 	u64 cost;
 
+	BUILD_BUG_ON(offsetof(struct htab_elem, htab) !=
+		     offsetof(struct htab_elem, hash_node.pprev));
+	BUILD_BUG_ON(offsetof(struct htab_elem, fnode.next) !=
+		     offsetof(struct htab_elem, hash_node.pprev));
+
 	if (lru && !capable(CAP_SYS_ADMIN))
 		/* LRU implementation is much complicated than other
 		 * maps.  Hence, limit to CAP_SYS_ADMIN for now.
@@ -326,7 +338,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 		goto free_htab;
 
 	for (i = 0; i < htab->n_buckets; i++) {
-		INIT_HLIST_HEAD(&htab->buckets[i].head);
+		INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i);
 		raw_spin_lock_init(&htab->buckets[i].lock);
 	}
 
@@ -366,20 +378,44 @@ static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash)
 	return &htab->buckets[hash & (htab->n_buckets - 1)];
 }
 
-static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)
+static inline struct hlist_nulls_head *select_bucket(struct bpf_htab *htab, u32 hash)
 {
 	return &__select_bucket(htab, hash)->head;
 }
 
-static struct htab_elem *lookup_elem_raw(struct hlist_head *head, u32 hash,
+/* this lookup function can only be called with bucket lock taken */
+static struct htab_elem *lookup_elem_raw(struct hlist_nulls_head *head, u32 hash,
 					 void *key, u32 key_size)
 {
+	struct hlist_nulls_node *n;
+	struct htab_elem *l;
+
+	hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
+		if (l->hash == hash && !memcmp(&l->key, key, key_size))
+			return l;
+
+	return NULL;
+}
+
+/* can be called without bucket lock. it will repeat the loop in
+ * the unlikely event when elements moved from one bucket into another
+ * while link list is being walked
+ */
+static struct htab_elem *lookup_nulls_elem_raw(struct hlist_nulls_head *head,
+					       u32 hash, void *key,
+					       u32 key_size, u32 n_buckets)
+{
+	struct hlist_nulls_node *n;
 	struct htab_elem *l;
 
-	hlist_for_each_entry_rcu(l, head, hash_node)
+again:
+	hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
 		if (l->hash == hash && !memcmp(&l->key, key, key_size))
 			return l;
 
+	if (unlikely(get_nulls_value(n) != (hash & (n_buckets - 1))))
+		goto again;
+
 	return NULL;
 }
 
@@ -387,7 +423,7 @@ static struct htab_elem *lookup_elem_raw(struct hlist_head *head, u32 hash,
 static void *__htab_map_lookup_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
-	struct hlist_head *head;
+	struct hlist_nulls_head *head;
 	struct htab_elem *l;
 	u32 hash, key_size;
 
@@ -400,7 +436,7 @@ static void *__htab_map_lookup_elem(struct bpf_map *map, void *key)
 
 	head = select_bucket(htab, hash);
 
-	l = lookup_elem_raw(head, hash, key, key_size);
+	l = lookup_nulls_elem_raw(head, hash, key, key_size, htab->n_buckets);
 
 	return l;
 }
@@ -433,8 +469,9 @@ static void *htab_lru_map_lookup_elem(struct bpf_map *map, void *key)
 static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
 {
 	struct bpf_htab *htab = (struct bpf_htab *)arg;
-	struct htab_elem *l, *tgt_l;
-	struct hlist_head *head;
+	struct htab_elem *l = NULL, *tgt_l;
+	struct hlist_nulls_head *head;
+	struct hlist_nulls_node *n;
 	unsigned long flags;
 	struct bucket *b;
 
@@ -444,9 +481,9 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
 
 	raw_spin_lock_irqsave(&b->lock, flags);
 
-	hlist_for_each_entry_rcu(l, head, hash_node)
+	hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
 		if (l == tgt_l) {
-			hlist_del_rcu(&l->hash_node);
+			hlist_nulls_del_rcu(&l->hash_node);
 			break;
 		}
 
@@ -459,7 +496,7 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
 static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
-	struct hlist_head *head;
+	struct hlist_nulls_head *head;
 	struct htab_elem *l, *next_l;
 	u32 hash, key_size;
 	int i;
@@ -473,7 +510,7 @@ static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 	head = select_bucket(htab, hash);
 
 	/* lookup the key */
-	l = lookup_elem_raw(head, hash, key, key_size);
+	l = lookup_nulls_elem_raw(head, hash, key, key_size, htab->n_buckets);
 
 	if (!l) {
 		i = 0;
@@ -481,7 +518,7 @@ static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 	}
 
 	/* key was found, get next key in the same bucket */
-	next_l = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&l->hash_node)),
+	next_l = hlist_nulls_entry_safe(rcu_dereference_raw(hlist_nulls_next_rcu(&l->hash_node)),
 				  struct htab_elem, hash_node);
 
 	if (next_l) {
@@ -500,7 +537,7 @@ find_first_elem:
 		head = select_bucket(htab, i);
 
 		/* pick first element in the bucket */
-		next_l = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),
+		next_l = hlist_nulls_entry_safe(rcu_dereference_raw(hlist_nulls_first_rcu(head)),
 					  struct htab_elem, hash_node);
 		if (next_l) {
 			/* if it's not empty, just return it */
@@ -582,9 +619,13 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 	int err = 0;
 
 	if (prealloc) {
-		l_new = (struct htab_elem *)pcpu_freelist_pop(&htab->freelist);
-		if (!l_new)
+		struct pcpu_freelist_node *l;
+
+		l = pcpu_freelist_pop(&htab->freelist);
+		if (!l)
 			err = -E2BIG;
+		else
+			l_new = container_of(l, struct htab_elem, fnode);
 	} else {
 		if (atomic_inc_return(&htab->count) > htab->map.max_entries) {
 			atomic_dec(&htab->count);
@@ -661,7 +702,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
 	struct htab_elem *l_new = NULL, *l_old;
-	struct hlist_head *head;
+	struct hlist_nulls_head *head;
 	unsigned long flags;
 	struct bucket *b;
 	u32 key_size, hash;
@@ -700,9 +741,9 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 	/* add new element to the head of the list, so that
 	 * concurrent search will find it before old elem
 	 */
-	hlist_add_head_rcu(&l_new->hash_node, head);
+	hlist_nulls_add_head_rcu(&l_new->hash_node, head);
 	if (l_old) {
-		hlist_del_rcu(&l_old->hash_node);
+		hlist_nulls_del_rcu(&l_old->hash_node);
 		free_htab_elem(htab, l_old);
 	}
 	ret = 0;
@@ -716,7 +757,7 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value,
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
 	struct htab_elem *l_new, *l_old = NULL;
-	struct hlist_head *head;
+	struct hlist_nulls_head *head;
 	unsigned long flags;
 	struct bucket *b;
 	u32 key_size, hash;
@@ -757,10 +798,10 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value,
 	/* add new element to the head of the list, so that
 	 * concurrent search will find it before old elem
 	 */
-	hlist_add_head_rcu(&l_new->hash_node, head);
+	hlist_nulls_add_head_rcu(&l_new->hash_node, head);
 	if (l_old) {
 		bpf_lru_node_set_ref(&l_new->lru_node);
-		hlist_del_rcu(&l_old->hash_node);
+		hlist_nulls_del_rcu(&l_old->hash_node);
 	}
 	ret = 0;
 
@@ -781,7 +822,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
 	struct htab_elem *l_new = NULL, *l_old;
-	struct hlist_head *head;
+	struct hlist_nulls_head *head;
 	unsigned long flags;
 	struct bucket *b;
 	u32 key_size, hash;
@@ -820,7 +861,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
 			ret = PTR_ERR(l_new);
 			goto err;
 		}
-		hlist_add_head_rcu(&l_new->hash_node, head);
+		hlist_nulls_add_head_rcu(&l_new->hash_node, head);
 	}
 	ret = 0;
 err:
@@ -834,7 +875,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
 	struct htab_elem *l_new = NULL, *l_old;
-	struct hlist_head *head;
+	struct hlist_nulls_head *head;
 	unsigned long flags;
 	struct bucket *b;
 	u32 key_size, hash;
@@ -882,7 +923,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
 	} else {
 		pcpu_copy_value(htab, htab_elem_get_ptr(l_new, key_size),
 				value, onallcpus);
-		hlist_add_head_rcu(&l_new->hash_node, head);
+		hlist_nulls_add_head_rcu(&l_new->hash_node, head);
 		l_new = NULL;
 	}
 	ret = 0;
@@ -910,7 +951,7 @@ static int htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
 static int htab_map_delete_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
-	struct hlist_head *head;
+	struct hlist_nulls_head *head;
 	struct bucket *b;
 	struct htab_elem *l;
 	unsigned long flags;
@@ -930,7 +971,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key)
 	l = lookup_elem_raw(head, hash, key, key_size);
 
 	if (l) {
-		hlist_del_rcu(&l->hash_node);
+		hlist_nulls_del_rcu(&l->hash_node);
 		free_htab_elem(htab, l);
 		ret = 0;
 	}
@@ -942,7 +983,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key)
 static int htab_lru_map_delete_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
-	struct hlist_head *head;
+	struct hlist_nulls_head *head;
 	struct bucket *b;
 	struct htab_elem *l;
 	unsigned long flags;
@@ -962,7 +1003,7 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key)
 	l = lookup_elem_raw(head, hash, key, key_size);
 
 	if (l) {
-		hlist_del_rcu(&l->hash_node);
+		hlist_nulls_del_rcu(&l->hash_node);
 		ret = 0;
 	}
 
@@ -977,12 +1018,12 @@ static void delete_all_elements(struct bpf_htab *htab)
 	int i;
 
 	for (i = 0; i < htab->n_buckets; i++) {
-		struct hlist_head *head = select_bucket(htab, i);
-		struct hlist_node *n;
+		struct hlist_nulls_head *head = select_bucket(htab, i);
+		struct hlist_nulls_node *n;
 		struct htab_elem *l;
 
-		hlist_for_each_entry_safe(l, n, head, hash_node) {
-			hlist_del_rcu(&l->hash_node);
+		hlist_nulls_for_each_entry_safe(l, n, head, hash_node) {
+			hlist_nulls_del_rcu(&l->hash_node);
 			if (l->state != HTAB_EXTRA_ELEM_USED)
 				htab_elem_free(htab, l);
 		}
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 8bfe0afaee10..b37bd9ab7f57 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -500,9 +500,15 @@ unlock:
 	raw_spin_unlock(&trie->lock);
 }
 
+static int trie_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+	return -ENOTSUPP;
+}
+
 static const struct bpf_map_ops trie_ops = {
 	.map_alloc = trie_alloc,
 	.map_free = trie_free,
+	.map_get_next_key = trie_get_next_key,
 	.map_lookup_elem = trie_lookup_elem,
 	.map_update_elem = trie_update_elem,
 	.map_delete_elem = trie_delete_elem,
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 56eba9caa632..1dc22f6b49f5 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -1329,7 +1329,7 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v)
 		struct task_struct *task;
 		int count = 0;
 
-		seq_printf(seq, "css_set %p\n", cset);
+		seq_printf(seq, "css_set %pK\n", cset);
 
 		list_for_each_entry(task, &cset->tasks, cg_list) {
 			if (count++ > MAX_TASKS_SHOWN_PER_CSS)
diff --git a/kernel/cgroup/pids.c b/kernel/cgroup/pids.c
index e756dae49300..2237201d66d5 100644
--- a/kernel/cgroup/pids.c
+++ b/kernel/cgroup/pids.c
@@ -229,7 +229,7 @@ static int pids_can_fork(struct task_struct *task)
 		/* Only log the first time events_limit is incremented. */
 		if (atomic64_inc_return(&pids->events_limit) == 1) {
 			pr_info("cgroup: fork rejected by pids controller in ");
-			pr_cont_cgroup_path(task_cgroup(current, pids_cgrp_id));
+			pr_cont_cgroup_path(css->cgroup);
 			pr_cont("\n");
 		}
 		cgroup_file_notify(&pids->events_file);
diff --git a/kernel/cpu.c b/kernel/cpu.c
index f7c063239fa5..37b223e4fc05 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1335,26 +1335,21 @@ static int cpuhp_store_callbacks(enum cpuhp_state state, const char *name,
 	struct cpuhp_step *sp;
 	int ret = 0;
 
-	mutex_lock(&cpuhp_state_mutex);
-
 	if (state == CPUHP_AP_ONLINE_DYN || state == CPUHP_BP_PREPARE_DYN) {
 		ret = cpuhp_reserve_state(state);
 		if (ret < 0)
-			goto out;
+			return ret;
 		state = ret;
 	}
 	sp = cpuhp_get_step(state);
-	if (name && sp->name) {
-		ret = -EBUSY;
-		goto out;
-	}
+	if (name && sp->name)
+		return -EBUSY;
+
 	sp->startup.single = startup;
 	sp->teardown.single = teardown;
 	sp->name = name;
 	sp->multi_instance = multi_instance;
 	INIT_HLIST_HEAD(&sp->list);
-out:
-	mutex_unlock(&cpuhp_state_mutex);
 	return ret;
 }
 
@@ -1428,6 +1423,7 @@ int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node,
 		return -EINVAL;
 
 	get_online_cpus();
+	mutex_lock(&cpuhp_state_mutex);
 
 	if (!invoke || !sp->startup.multi)
 		goto add_node;
@@ -1447,16 +1443,14 @@ int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node,
 		if (ret) {
 			if (sp->teardown.multi)
 				cpuhp_rollback_install(cpu, state, node);
-			goto err;
+			goto unlock;
 		}
 	}
 add_node:
 	ret = 0;
-	mutex_lock(&cpuhp_state_mutex);
 	hlist_add_head(node, &sp->list);
+unlock:
 	mutex_unlock(&cpuhp_state_mutex);
-
-err:
 	put_online_cpus();
 	return ret;
 }
@@ -1491,6 +1485,7 @@ int __cpuhp_setup_state(enum cpuhp_state state,
 		return -EINVAL;
 
 	get_online_cpus();
+	mutex_lock(&cpuhp_state_mutex);
 
 	ret = cpuhp_store_callbacks(state, name, startup, teardown,
 				    multi_instance);
@@ -1524,6 +1519,7 @@ int __cpuhp_setup_state(enum cpuhp_state state,
 		}
 	}
 out:
+	mutex_unlock(&cpuhp_state_mutex);
 	put_online_cpus();
 	/*
 	 * If the requested state is CPUHP_AP_ONLINE_DYN, return the
@@ -1547,6 +1543,8 @@ int __cpuhp_state_remove_instance(enum cpuhp_state state,
 		return -EINVAL;
 
 	get_online_cpus();
+	mutex_lock(&cpuhp_state_mutex);
+
 	if (!invoke || !cpuhp_get_teardown_cb(state))
 		goto remove;
 	/*
@@ -1563,7 +1561,6 @@ int __cpuhp_state_remove_instance(enum cpuhp_state state,
 	}
 
 remove:
-	mutex_lock(&cpuhp_state_mutex);
 	hlist_del(node);
 	mutex_unlock(&cpuhp_state_mutex);
 	put_online_cpus();
@@ -1571,6 +1568,7 @@ remove:
 	return 0;
 }
 EXPORT_SYMBOL_GPL(__cpuhp_state_remove_instance);
+
 /**
  * __cpuhp_remove_state - Remove the callbacks for an hotplug machine state
  * @state:	The state to remove
@@ -1589,6 +1587,7 @@ void __cpuhp_remove_state(enum cpuhp_state state, bool invoke)
 
 	get_online_cpus();
 
+	mutex_lock(&cpuhp_state_mutex);
 	if (sp->multi_instance) {
 		WARN(!hlist_empty(&sp->list),
 		     "Error: Removing state %d which has instances left.\n",
@@ -1613,6 +1612,7 @@ void __cpuhp_remove_state(enum cpuhp_state state, bool invoke)
 	}
 remove:
 	cpuhp_store_callbacks(state, NULL, NULL, NULL, false);
+	mutex_unlock(&cpuhp_state_mutex);
 	put_online_cpus();
 }
 EXPORT_SYMBOL(__cpuhp_remove_state);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index a17ed56c8ce1..ff01cba86f43 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4256,7 +4256,7 @@ int perf_event_release_kernel(struct perf_event *event)
 
 	raw_spin_lock_irq(&ctx->lock);
 	/*
-	 * Mark this even as STATE_DEAD, there is no external reference to it
+	 * Mark this event as STATE_DEAD, there is no external reference to it
 	 * anymore.
 	 *
 	 * Anybody acquiring event->child_mutex after the below loop _must_
@@ -10417,21 +10417,22 @@ void perf_event_free_task(struct task_struct *task)
 			continue;
 
 		mutex_lock(&ctx->mutex);
-again:
-		list_for_each_entry_safe(event, tmp, &ctx->pinned_groups,
-				group_entry)
-			perf_free_event(event, ctx);
+		raw_spin_lock_irq(&ctx->lock);
+		/*
+		 * Destroy the task <-> ctx relation and mark the context dead.
+		 *
+		 * This is important because even though the task hasn't been
+		 * exposed yet the context has been (through child_list).
+		 */
+		RCU_INIT_POINTER(task->perf_event_ctxp[ctxn], NULL);
+		WRITE_ONCE(ctx->task, TASK_TOMBSTONE);
+		put_task_struct(task); /* cannot be last */
+		raw_spin_unlock_irq(&ctx->lock);
 
-		list_for_each_entry_safe(event, tmp, &ctx->flexible_groups,
-				group_entry)
+		list_for_each_entry_safe(event, tmp, &ctx->event_list, event_entry)
 			perf_free_event(event, ctx);
 
-		if (!list_empty(&ctx->pinned_groups) ||
-				!list_empty(&ctx->flexible_groups))
-			goto again;
-
 		mutex_unlock(&ctx->mutex);
-
 		put_ctx(ctx);
 	}
 }
@@ -10469,7 +10470,12 @@ const struct perf_event_attr *perf_event_attrs(struct perf_event *event)
 }
 
 /*
- * inherit a event from parent task to child task:
+ * Inherit a event from parent task to child task.
+ *
+ * Returns:
+ *  - valid pointer on success
+ *  - NULL for orphaned events
+ *  - IS_ERR() on error
  */
 static struct perf_event *
 inherit_event(struct perf_event *parent_event,
@@ -10563,6 +10569,16 @@ inherit_event(struct perf_event *parent_event,
 	return child_event;
 }
 
+/*
+ * Inherits an event group.
+ *
+ * This will quietly suppress orphaned events; !inherit_event() is not an error.
+ * This matches with perf_event_release_kernel() removing all child events.
+ *
+ * Returns:
+ *  - 0 on success
+ *  - <0 on error
+ */
 static int inherit_group(struct perf_event *parent_event,
 	      struct task_struct *parent,
 	      struct perf_event_context *parent_ctx,
@@ -10577,6 +10593,11 @@ static int inherit_group(struct perf_event *parent_event,
 				 child, NULL, child_ctx);
 	if (IS_ERR(leader))
 		return PTR_ERR(leader);
+	/*
+	 * @leader can be NULL here because of is_orphaned_event(). In this
+	 * case inherit_event() will create individual events, similar to what
+	 * perf_group_detach() would do anyway.
+	 */
 	list_for_each_entry(sub, &parent_event->sibling_list, group_entry) {
 		child_ctr = inherit_event(sub, parent, parent_ctx,
 					    child, leader, child_ctx);
@@ -10586,6 +10607,17 @@ static int inherit_group(struct perf_event *parent_event,
 	return 0;
 }
 
+/*
+ * Creates the child task context and tries to inherit the event-group.
+ *
+ * Clears @inherited_all on !attr.inherited or error. Note that we'll leave
+ * inherited_all set when we 'fail' to inherit an orphaned event; this is
+ * consistent with perf_event_release_kernel() removing all child events.
+ *
+ * Returns:
+ *  - 0 on success
+ *  - <0 on error
+ */
 static int
 inherit_task_group(struct perf_event *event, struct task_struct *parent,
 		   struct perf_event_context *parent_ctx,
@@ -10608,7 +10640,6 @@ inherit_task_group(struct perf_event *event, struct task_struct *parent,
 		 * First allocate and initialize a context for the
 		 * child.
 		 */
-
 		child_ctx = alloc_perf_context(parent_ctx->pmu, child);
 		if (!child_ctx)
 			return -ENOMEM;
@@ -10670,7 +10701,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn)
 		ret = inherit_task_group(event, parent, parent_ctx,
 					 child, ctxn, &inherited_all);
 		if (ret)
-			break;
+			goto out_unlock;
 	}
 
 	/*
@@ -10686,7 +10717,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn)
 		ret = inherit_task_group(event, parent, parent_ctx,
 					 child, ctxn, &inherited_all);
 		if (ret)
-			break;
+			goto out_unlock;
 	}
 
 	raw_spin_lock_irqsave(&parent_ctx->lock, flags);
@@ -10714,6 +10745,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn)
 	}
 
 	raw_spin_unlock_irqrestore(&parent_ctx->lock, flags);
+out_unlock:
 	mutex_unlock(&parent_ctx->mutex);
 
 	perf_unpin_context(parent_ctx);
diff --git a/kernel/futex.c b/kernel/futex.c
index 229a744b1781..45858ec73941 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2815,7 +2815,6 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 {
 	struct hrtimer_sleeper timeout, *to = NULL;
 	struct rt_mutex_waiter rt_waiter;
-	struct rt_mutex *pi_mutex = NULL;
 	struct futex_hash_bucket *hb;
 	union futex_key key2 = FUTEX_KEY_INIT;
 	struct futex_q q = futex_q_init;
@@ -2899,6 +2898,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		if (q.pi_state && (q.pi_state->owner != current)) {
 			spin_lock(q.lock_ptr);
 			ret = fixup_pi_state_owner(uaddr2, &q, current);
+			if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current)
+				rt_mutex_unlock(&q.pi_state->pi_mutex);
 			/*
 			 * Drop the reference to the pi state which
 			 * the requeue_pi() code acquired for us.
@@ -2907,6 +2908,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 			spin_unlock(q.lock_ptr);
 		}
 	} else {
+		struct rt_mutex *pi_mutex;
+
 		/*
 		 * We have been woken up by futex_unlock_pi(), a timeout, or a
 		 * signal.  futex_unlock_pi() will not destroy the lock_ptr nor
@@ -2930,18 +2933,19 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		if (res)
 			ret = (res < 0) ? res : 0;
 
+		/*
+		 * If fixup_pi_state_owner() faulted and was unable to handle
+		 * the fault, unlock the rt_mutex and return the fault to
+		 * userspace.
+		 */
+		if (ret && rt_mutex_owner(pi_mutex) == current)
+			rt_mutex_unlock(pi_mutex);
+
 		/* Unqueue and drop the lock. */
 		unqueue_me_pi(&q);
 	}
 
-	/*
-	 * If fixup_pi_state_owner() faulted and was unable to handle the
-	 * fault, unlock the rt_mutex and return the fault to userspace.
-	 */
-	if (ret == -EFAULT) {
-		if (pi_mutex && rt_mutex_owner(pi_mutex) == current)
-			rt_mutex_unlock(pi_mutex);
-	} else if (ret == -EINTR) {
+	if (ret == -EINTR) {
 		/*
 		 * We've already been requeued, but cannot restart by calling
 		 * futex_lock_pi() directly. We could restart this syscall, but
diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c
index 7bc24d477805..c65f7989f850 100644
--- a/kernel/locking/rwsem-spinlock.c
+++ b/kernel/locking/rwsem-spinlock.c
@@ -213,10 +213,9 @@ int __sched __down_write_common(struct rw_semaphore *sem, int state)
 		 */
 		if (sem->count == 0)
 			break;
-		if (signal_pending_state(state, current)) {
-			ret = -EINTR;
-			goto out;
-		}
+		if (signal_pending_state(state, current))
+			goto out_nolock;
+
 		set_current_state(state);
 		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 		schedule();
@@ -224,12 +223,19 @@ int __sched __down_write_common(struct rw_semaphore *sem, int state)
 	}
 	/* got the lock */
 	sem->count = -1;
-out:
 	list_del(&waiter.list);
 
 	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 
 	return ret;
+
+out_nolock:
+	list_del(&waiter.list);
+	if (!list_empty(&sem->wait_list))
+		__rwsem_do_wake(sem, 1);
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+	return -EINTR;
 }
 
 void __sched __down_write(struct rw_semaphore *sem)
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 06123234f118..07e85e5229da 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -247,11 +247,9 @@ static void devm_memremap_pages_release(struct device *dev, void *data)
 	align_start = res->start & ~(SECTION_SIZE - 1);
 	align_size = ALIGN(resource_size(res), SECTION_SIZE);
 
-	lock_device_hotplug();
 	mem_hotplug_begin();
 	arch_remove_memory(align_start, align_size);
 	mem_hotplug_done();
-	unlock_device_hotplug();
 
 	untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
 	pgmap_radix_release(res);
@@ -364,11 +362,9 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 	if (error)
 		goto err_pfn_remap;
 
-	lock_device_hotplug();
 	mem_hotplug_begin();
 	error = arch_add_memory(nid, align_start, align_size, true);
 	mem_hotplug_done();
-	unlock_device_hotplug();
 	if (error)
 		goto err_add_memory;
 
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 99b2c33a9fbc..a2ce59015642 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -445,13 +445,13 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
  *
  * This function returns true if:
  *
- *   runtime / (deadline - t) > dl_runtime / dl_period ,
+ *   runtime / (deadline - t) > dl_runtime / dl_deadline ,
  *
  * IOW we can't recycle current parameters.
  *
- * Notice that the bandwidth check is done against the period. For
+ * Notice that the bandwidth check is done against the deadline. For
  * task with deadline equal to period this is the same of using
- * dl_deadline instead of dl_period in the equation above.
+ * dl_period instead of dl_deadline in the equation above.
  */
 static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
 			       struct sched_dl_entity *pi_se, u64 t)
@@ -476,7 +476,7 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
 	 * of anything below microseconds resolution is actually fiction
 	 * (but still we want to give the user that illusion >;).
 	 */
-	left = (pi_se->dl_period >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
+	left = (pi_se->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
 	right = ((dl_se->deadline - t) >> DL_SCALE) *
 		(pi_se->dl_runtime >> DL_SCALE);
 
@@ -505,10 +505,15 @@ static void update_dl_entity(struct sched_dl_entity *dl_se,
 	}
 }
 
+static inline u64 dl_next_period(struct sched_dl_entity *dl_se)
+{
+	return dl_se->deadline - dl_se->dl_deadline + dl_se->dl_period;
+}
+
 /*
  * If the entity depleted all its runtime, and if we want it to sleep
  * while waiting for some new execution time to become available, we
- * set the bandwidth enforcement timer to the replenishment instant
+ * set the bandwidth replenishment timer to the replenishment instant
  * and try to activate it.
  *
  * Notice that it is important for the caller to know if the timer
@@ -530,7 +535,7 @@ static int start_dl_timer(struct task_struct *p)
 	 * that it is actually coming from rq->clock and not from
 	 * hrtimer's time base reading.
 	 */
-	act = ns_to_ktime(dl_se->deadline);
+	act = ns_to_ktime(dl_next_period(dl_se));
 	now = hrtimer_cb_get_time(timer);
 	delta = ktime_to_ns(now) - rq_clock(rq);
 	act = ktime_add_ns(act, delta);
@@ -638,6 +643,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 		lockdep_unpin_lock(&rq->lock, rf.cookie);
 		rq = dl_task_offline_migration(rq, p);
 		rf.cookie = lockdep_pin_lock(&rq->lock);
+		update_rq_clock(rq);
 
 		/*
 		 * Now that the task has been migrated to the new RQ and we
@@ -689,6 +695,37 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
 	timer->function = dl_task_timer;
 }
 
+/*
+ * During the activation, CBS checks if it can reuse the current task's
+ * runtime and period. If the deadline of the task is in the past, CBS
+ * cannot use the runtime, and so it replenishes the task. This rule
+ * works fine for implicit deadline tasks (deadline == period), and the
+ * CBS was designed for implicit deadline tasks. However, a task with
+ * constrained deadline (deadine < period) might be awakened after the
+ * deadline, but before the next period. In this case, replenishing the
+ * task would allow it to run for runtime / deadline. As in this case
+ * deadline < period, CBS enables a task to run for more than the
+ * runtime / period. In a very loaded system, this can cause a domino
+ * effect, making other tasks miss their deadlines.
+ *
+ * To avoid this problem, in the activation of a constrained deadline
+ * task after the deadline but before the next period, throttle the
+ * task and set the replenishing timer to the begin of the next period,
+ * unless it is boosted.
+ */
+static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se)
+{
+	struct task_struct *p = dl_task_of(dl_se);
+	struct rq *rq = rq_of_dl_rq(dl_rq_of_se(dl_se));
+
+	if (dl_time_before(dl_se->deadline, rq_clock(rq)) &&
+	    dl_time_before(rq_clock(rq), dl_next_period(dl_se))) {
+		if (unlikely(dl_se->dl_boosted || !start_dl_timer(p)))
+			return;
+		dl_se->dl_throttled = 1;
+	}
+}
+
 static
 int dl_runtime_exceeded(struct sched_dl_entity *dl_se)
 {
@@ -922,6 +959,11 @@ static void dequeue_dl_entity(struct sched_dl_entity *dl_se)
 	__dequeue_dl_entity(dl_se);
 }
 
+static inline bool dl_is_constrained(struct sched_dl_entity *dl_se)
+{
+	return dl_se->dl_deadline < dl_se->dl_period;
+}
+
 static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct task_struct *pi_task = rt_mutex_get_top_task(p);
@@ -948,6 +990,15 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 	}
 
 	/*
+	 * Check if a constrained deadline task was activated
+	 * after the deadline but before the next period.
+	 * If that is the case, the task will be throttled and
+	 * the replenishment timer will be set to the next period.
+	 */
+	if (!p->dl.dl_throttled && dl_is_constrained(&p->dl))
+		dl_check_constrained_dl(&p->dl);
+
+	/*
 	 * If p is throttled, we do nothing. In fact, if it exhausted
 	 * its budget it needs a replenishment and, since it now is on
 	 * its rq, the bandwidth timer callback (which clearly has not
diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index 7296b7308eca..f15fb2bdbc0d 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -169,7 +169,7 @@ static inline int calc_load_write_idx(void)
 	 * If the folding window started, make sure we start writing in the
 	 * next idle-delta.
 	 */
-	if (!time_before(jiffies, calc_load_update))
+	if (!time_before(jiffies, READ_ONCE(calc_load_update)))
 		idx++;
 
 	return idx & 1;
@@ -202,8 +202,9 @@ void calc_load_exit_idle(void)
 	struct rq *this_rq = this_rq();
 
 	/*
-	 * If we're still before the sample window, we're done.
+	 * If we're still before the pending sample window, we're done.
 	 */
+	this_rq->calc_load_update = READ_ONCE(calc_load_update);
 	if (time_before(jiffies, this_rq->calc_load_update))
 		return;
 
@@ -212,7 +213,6 @@ void calc_load_exit_idle(void)
 	 * accounted through the nohz accounting, so skip the entire deal and
 	 * sync up for the next window.
 	 */
-	this_rq->calc_load_update = calc_load_update;
 	if (time_before(jiffies, this_rq->calc_load_update + 10))
 		this_rq->calc_load_update += LOAD_FREQ;
 }
@@ -308,13 +308,15 @@ calc_load_n(unsigned long load, unsigned long exp,
  */
 static void calc_global_nohz(void)
 {
+	unsigned long sample_window;
 	long delta, active, n;
 
-	if (!time_before(jiffies, calc_load_update + 10)) {
+	sample_window = READ_ONCE(calc_load_update);
+	if (!time_before(jiffies, sample_window + 10)) {
 		/*
 		 * Catch-up, fold however many we are behind still
 		 */
-		delta = jiffies - calc_load_update - 10;
+		delta = jiffies - sample_window - 10;
 		n = 1 + (delta / LOAD_FREQ);
 
 		active = atomic_long_read(&calc_load_tasks);
@@ -324,7 +326,7 @@ static void calc_global_nohz(void)
 		avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
 		avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
 
-		calc_load_update += n * LOAD_FREQ;
+		WRITE_ONCE(calc_load_update, sample_window + n * LOAD_FREQ);
 	}
 
 	/*
@@ -352,9 +354,11 @@ static inline void calc_global_nohz(void) { }
  */
 void calc_global_load(unsigned long ticks)
 {
+	unsigned long sample_window;
 	long active, delta;
 
-	if (time_before(jiffies, calc_load_update + 10))
+	sample_window = READ_ONCE(calc_load_update);
+	if (time_before(jiffies, sample_window + 10))
 		return;
 
 	/*
@@ -371,7 +375,7 @@ void calc_global_load(unsigned long ticks)
 	avenrun[1] = calc_load(avenrun[1], EXP_5, active);
 	avenrun[2] = calc_load(avenrun[2], EXP_15, active);
 
-	calc_load_update += LOAD_FREQ;
+	WRITE_ONCE(calc_load_update, sample_window + LOAD_FREQ);
 
 	/*
 	 * In case we idled for multiple LOAD_FREQ intervals, catch up in bulk.
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 97ac0951f164..4237e0744e26 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -468,7 +468,7 @@ void clockevents_register_device(struct clock_event_device *dev)
 }
 EXPORT_SYMBOL_GPL(clockevents_register_device);
 
-void clockevents_config(struct clock_event_device *dev, u32 freq)
+static void clockevents_config(struct clock_event_device *dev, u32 freq)
 {
 	u64 sec;
 
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index ea6b610c4c57..2d8f05aad442 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -206,6 +206,11 @@ sched_clock_register(u64 (*read)(void), int bits, unsigned long rate)
 
 	update_clock_read_data(&rd);
 
+	if (sched_clock_timer.function != NULL) {
+		/* update timeout for clock wrap */
+		hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL);
+	}
+
 	r = rate;
 	if (r >= 4000000) {
 		r /= 1000000;
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index ff8d5c13d04b..0e7f5428a148 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -16,6 +16,7 @@
 #include <linux/sched.h>
 #include <linux/seq_file.h>
 #include <linux/kallsyms.h>
+#include <linux/nmi.h>
 
 #include <linux/uaccess.h>
 
@@ -86,6 +87,9 @@ print_active_timers(struct seq_file *m, struct hrtimer_clock_base *base,
 
 next_one:
 	i = 0;
+
+	touch_nmi_watchdog();
+
 	raw_spin_lock_irqsave(&base->cpu_base->lock, flags);
 
 	curr = timerqueue_getnext(&base->active);
@@ -197,6 +201,8 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu)
 {
 	struct clock_event_device *dev = td->evtdev;
 
+	touch_nmi_watchdog();
+
 	SEQ_printf(m, "Tick Device: mode:     %d\n", td->mode);
 	if (cpu < 0)
 		SEQ_printf(m, "Broadcast device\n");
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 072cbc9b175d..c0168b7da1ea 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1507,6 +1507,7 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq,
 	struct timer_list *timer = &dwork->timer;
 	struct work_struct *work = &dwork->work;
 
+	WARN_ON_ONCE(!wq);
 	WARN_ON_ONCE(timer->function != delayed_work_timer_fn ||
 		     timer->data != (unsigned long)dwork);
 	WARN_ON_ONCE(timer_pending(timer));