Merge branch 'linus' into perf/core, to pick up fixes

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

21 files changed, 215 insertions, 71 deletions

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index befe570be5ba..c57bd10340ed 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -1459,7 +1459,8 @@ static int btf_modifier_resolve(struct btf_verifier_env *env,
 
 		/* "typedef void new_void", "const void"...etc */
 		if (!btf_type_is_void(next_type) &&
-		    !btf_type_is_fwd(next_type)) {
+		    !btf_type_is_fwd(next_type) &&
+		    !btf_type_is_func_proto(next_type)) {
 			btf_verifier_log_type(env, v->t, "Invalid type_id");
 			return -EINVAL;
 		}
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index ab612fe9862f..d17d05570a3f 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -572,7 +572,7 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk,
 	bpf_compute_and_save_data_end(skb, &saved_data_end);
 
 	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], skb,
-				 bpf_prog_run_save_cb);
+				 __bpf_prog_run_save_cb);
 	bpf_restore_data_end(skb, saved_data_end);
 	__skb_pull(skb, offset);
 	skb->sk = save_sk;
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 4b7c76765d9d..f9274114c88d 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -686,7 +686,7 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
 	}
 
 	if (htab_is_prealloc(htab)) {
-		pcpu_freelist_push(&htab->freelist, &l->fnode);
+		__pcpu_freelist_push(&htab->freelist, &l->fnode);
 	} else {
 		atomic_dec(&htab->count);
 		l->htab = htab;
@@ -748,7 +748,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 		} else {
 			struct pcpu_freelist_node *l;
 
-			l = pcpu_freelist_pop(&htab->freelist);
+			l = __pcpu_freelist_pop(&htab->freelist);
 			if (!l)
 				return ERR_PTR(-E2BIG);
 			l_new = container_of(l, struct htab_elem, fnode);
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index abf1002080df..93a5cbbde421 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -471,6 +471,7 @@ static int trie_delete_elem(struct bpf_map *map, void *_key)
 	}
 
 	if (!node || node->prefixlen != key->prefixlen ||
+	    node->prefixlen != matchlen ||
 	    (node->flags & LPM_TREE_NODE_FLAG_IM)) {
 		ret = -ENOENT;
 		goto out;
diff --git a/kernel/bpf/percpu_freelist.c b/kernel/bpf/percpu_freelist.c
index 673fa6fe2d73..0c1b4ba9e90e 100644
--- a/kernel/bpf/percpu_freelist.c
+++ b/kernel/bpf/percpu_freelist.c
@@ -28,8 +28,8 @@ void pcpu_freelist_destroy(struct pcpu_freelist *s)
 	free_percpu(s->freelist);
 }
 
-static inline void __pcpu_freelist_push(struct pcpu_freelist_head *head,
-					struct pcpu_freelist_node *node)
+static inline void ___pcpu_freelist_push(struct pcpu_freelist_head *head,
+					 struct pcpu_freelist_node *node)
 {
 	raw_spin_lock(&head->lock);
 	node->next = head->first;
@@ -37,12 +37,22 @@ static inline void __pcpu_freelist_push(struct pcpu_freelist_head *head,
 	raw_spin_unlock(&head->lock);
 }
 
-void pcpu_freelist_push(struct pcpu_freelist *s,
+void __pcpu_freelist_push(struct pcpu_freelist *s,
 			struct pcpu_freelist_node *node)
 {
 	struct pcpu_freelist_head *head = this_cpu_ptr(s->freelist);
 
-	__pcpu_freelist_push(head, node);
+	___pcpu_freelist_push(head, node);
+}
+
+void pcpu_freelist_push(struct pcpu_freelist *s,
+			struct pcpu_freelist_node *node)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__pcpu_freelist_push(s, node);
+	local_irq_restore(flags);
 }
 
 void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size,
@@ -63,7 +73,7 @@ void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size,
 	for_each_possible_cpu(cpu) {
 again:
 		head = per_cpu_ptr(s->freelist, cpu);
-		__pcpu_freelist_push(head, buf);
+		___pcpu_freelist_push(head, buf);
 		i++;
 		buf += elem_size;
 		if (i == nr_elems)
@@ -74,14 +84,12 @@ again:
 	local_irq_restore(flags);
 }
 
-struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s)
+struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *s)
 {
 	struct pcpu_freelist_head *head;
 	struct pcpu_freelist_node *node;
-	unsigned long flags;
 	int orig_cpu, cpu;
 
-	local_irq_save(flags);
 	orig_cpu = cpu = raw_smp_processor_id();
 	while (1) {
 		head = per_cpu_ptr(s->freelist, cpu);
@@ -89,16 +97,25 @@ struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s)
 		node = head->first;
 		if (node) {
 			head->first = node->next;
-			raw_spin_unlock_irqrestore(&head->lock, flags);
+			raw_spin_unlock(&head->lock);
 			return node;
 		}
 		raw_spin_unlock(&head->lock);
 		cpu = cpumask_next(cpu, cpu_possible_mask);
 		if (cpu >= nr_cpu_ids)
 			cpu = 0;
-		if (cpu == orig_cpu) {
-			local_irq_restore(flags);
+		if (cpu == orig_cpu)
 			return NULL;
-		}
 	}
 }
+
+struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s)
+{
+	struct pcpu_freelist_node *ret;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	ret = __pcpu_freelist_pop(s);
+	local_irq_restore(flags);
+	return ret;
+}
diff --git a/kernel/bpf/percpu_freelist.h b/kernel/bpf/percpu_freelist.h
index 3049aae8ea1e..c3960118e617 100644
--- a/kernel/bpf/percpu_freelist.h
+++ b/kernel/bpf/percpu_freelist.h
@@ -22,8 +22,12 @@ struct pcpu_freelist_node {
 	struct pcpu_freelist_node *next;
 };
 
+/* pcpu_freelist_* do spin_lock_irqsave. */
 void pcpu_freelist_push(struct pcpu_freelist *, struct pcpu_freelist_node *);
 struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *);
+/* __pcpu_freelist_* do spin_lock only. caller must disable irqs. */
+void __pcpu_freelist_push(struct pcpu_freelist *, struct pcpu_freelist_node *);
+struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *);
 void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size,
 			    u32 nr_elems);
 int pcpu_freelist_init(struct pcpu_freelist *);
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index d43b14535827..950ab2f28922 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -44,7 +44,7 @@ static void do_up_read(struct irq_work *entry)
 	struct stack_map_irq_work *work;
 
 	work = container_of(entry, struct stack_map_irq_work, irq_work);
-	up_read(work->sem);
+	up_read_non_owner(work->sem);
 	work->sem = NULL;
 }
 
@@ -338,6 +338,12 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 	} else {
 		work->sem = &current->mm->mmap_sem;
 		irq_work_queue(&work->irq_work);
+		/*
+		 * The irq_work will release the mmap_sem with
+		 * up_read_non_owner(). The rwsem_release() is called
+		 * here to release the lock from lockdep's perspective.
+		 */
+		rwsem_release(&current->mm->mmap_sem.dep_map, 1, _RET_IP_);
 	}
 }
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 30ebd085790b..d7185c8f77bf 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -713,8 +713,13 @@ static int map_lookup_elem(union bpf_attr *attr)
 
 	if (bpf_map_is_dev_bound(map)) {
 		err = bpf_map_offload_lookup_elem(map, key, value);
-	} else if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
-		   map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
+		goto done;
+	}
+
+	preempt_disable();
+	this_cpu_inc(bpf_prog_active);
+	if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+	    map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
 		err = bpf_percpu_hash_copy(map, key, value);
 	} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
 		err = bpf_percpu_array_copy(map, key, value);
@@ -744,7 +749,10 @@ static int map_lookup_elem(union bpf_attr *attr)
 		}
 		rcu_read_unlock();
 	}
+	this_cpu_dec(bpf_prog_active);
+	preempt_enable();
 
+done:
 	if (err)
 		goto free_value;
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 56674a7c3778..8f295b790297 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1617,12 +1617,13 @@ static int check_flow_keys_access(struct bpf_verifier_env *env, int off,
 	return 0;
 }
 
-static int check_sock_access(struct bpf_verifier_env *env, u32 regno, int off,
-			     int size, enum bpf_access_type t)
+static int check_sock_access(struct bpf_verifier_env *env, int insn_idx,
+			     u32 regno, int off, int size,
+			     enum bpf_access_type t)
 {
 	struct bpf_reg_state *regs = cur_regs(env);
 	struct bpf_reg_state *reg = &regs[regno];
-	struct bpf_insn_access_aux info;
+	struct bpf_insn_access_aux info = {};
 
 	if (reg->smin_value < 0) {
 		verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n",
@@ -1636,6 +1637,8 @@ static int check_sock_access(struct bpf_verifier_env *env, u32 regno, int off,
 		return -EACCES;
 	}
 
+	env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size;
+
 	return 0;
 }
 
@@ -2032,7 +2035,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 			verbose(env, "cannot write into socket\n");
 			return -EACCES;
 		}
-		err = check_sock_access(env, regno, off, size, t);
+		err = check_sock_access(env, insn_idx, regno, off, size, t);
 		if (!err && value_regno >= 0)
 			mark_reg_unknown(env, regs, value_regno);
 	} else {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5aeb4c74fb99..932babd9e86c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4968,6 +4968,11 @@ static void __perf_event_period(struct perf_event *event,
 	}
 }
 
+static int perf_event_check_period(struct perf_event *event, u64 value)
+{
+	return event->pmu->check_period(event, value);
+}
+
 static int perf_event_period(struct perf_event *event, u64 __user *arg)
 {
 	u64 value;
@@ -4984,6 +4989,9 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
 	if (event->attr.freq && value > sysctl_perf_event_sample_rate)
 		return -EINVAL;
 
+	if (perf_event_check_period(event, value))
+		return -EINVAL;
+
 	event_function_call(event, __perf_event_period, &value);
 
 	return 0;
@@ -9600,6 +9608,11 @@ static int perf_pmu_nop_int(struct pmu *pmu)
 	return 0;
 }
 
+static int perf_event_nop_int(struct perf_event *event, u64 value)
+{
+	return 0;
+}
+
 static DEFINE_PER_CPU(unsigned int, nop_txn_flags);
 
 static void perf_pmu_start_txn(struct pmu *pmu, unsigned int flags)
@@ -9900,6 +9913,9 @@ got_cpu_context:
 		pmu->pmu_disable = perf_pmu_nop_void;
 	}
 
+	if (!pmu->check_period)
+		pmu->check_period = perf_event_nop_int;
+
 	if (!pmu->event_idx)
 		pmu->event_idx = perf_event_idx_default;
 
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 70ae2422cbaf..678ccec60d8f 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -733,7 +733,7 @@ struct ring_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags)
 	size = sizeof(struct ring_buffer);
 	size += nr_pages * sizeof(void *);
 
-	if (order_base_2(size) >= MAX_ORDER)
+	if (order_base_2(size) >= PAGE_SHIFT+MAX_ORDER)
 		goto fail;
 
 	rb = kzalloc(size, GFP_KERNEL);
diff --git a/kernel/futex.c b/kernel/futex.c
index fdd312da0992..a0514e01c3eb 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2221,11 +2221,11 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
 	 * decrement the counter at queue_unlock() when some error has
 	 * occurred and we don't end up adding the task to the list.
 	 */
-	hb_waiters_inc(hb);
+	hb_waiters_inc(hb); /* implies smp_mb(); (A) */
 
 	q->lock_ptr = &hb->lock;
 
-	spin_lock(&hb->lock); /* implies smp_mb(); (A) */
+	spin_lock(&hb->lock);
 	return hb;
 }
 
@@ -2861,35 +2861,39 @@ retry_private:
 	 * and BUG when futex_unlock_pi() interleaves with this.
 	 *
 	 * Therefore acquire wait_lock while holding hb->lock, but drop the
-	 * latter before calling rt_mutex_start_proxy_lock(). This still fully
-	 * serializes against futex_unlock_pi() as that does the exact same
-	 * lock handoff sequence.
+	 * latter before calling __rt_mutex_start_proxy_lock(). This
+	 * interleaves with futex_unlock_pi() -- which does a similar lock
+	 * handoff -- such that the latter can observe the futex_q::pi_state
+	 * before __rt_mutex_start_proxy_lock() is done.
 	 */
 	raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock);
 	spin_unlock(q.lock_ptr);
+	/*
+	 * __rt_mutex_start_proxy_lock() unconditionally enqueues the @rt_waiter
+	 * such that futex_unlock_pi() is guaranteed to observe the waiter when
+	 * it sees the futex_q::pi_state.
+	 */
 	ret = __rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current);
 	raw_spin_unlock_irq(&q.pi_state->pi_mutex.wait_lock);
 
 	if (ret) {
 		if (ret == 1)
 			ret = 0;
-
-		spin_lock(q.lock_ptr);
-		goto no_block;
+		goto cleanup;
 	}
 
-
 	if (unlikely(to))
 		hrtimer_start_expires(&to->timer, HRTIMER_MODE_ABS);
 
 	ret = rt_mutex_wait_proxy_lock(&q.pi_state->pi_mutex, to, &rt_waiter);
 
+cleanup:
 	spin_lock(q.lock_ptr);
 	/*
-	 * If we failed to acquire the lock (signal/timeout), we must
+	 * If we failed to acquire the lock (deadlock/signal/timeout), we must
 	 * first acquire the hb->lock before removing the lock from the
-	 * rt_mutex waitqueue, such that we can keep the hb and rt_mutex
-	 * wait lists consistent.
+	 * rt_mutex waitqueue, such that we can keep the hb and rt_mutex wait
+	 * lists consistent.
 	 *
 	 * In particular; it is important that futex_unlock_pi() can not
 	 * observe this inconsistency.
@@ -3013,6 +3017,10 @@ retry:
 		 * there is no point where we hold neither; and therefore
 		 * wake_futex_pi() must observe a state consistent with what we
 		 * observed.
+		 *
+		 * In particular; this forces __rt_mutex_start_proxy() to
+		 * complete such that we're guaranteed to observe the
+		 * rt_waiter. Also see the WARN in wake_futex_pi().
 		 */
 		raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 		spin_unlock(&hb->lock);
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 581edcc63c26..978d63a8261c 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1726,12 +1726,33 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock,
 	rt_mutex_set_owner(lock, NULL);
 }
 
+/**
+ * __rt_mutex_start_proxy_lock() - Start lock acquisition for another task
+ * @lock:		the rt_mutex to take
+ * @waiter:		the pre-initialized rt_mutex_waiter
+ * @task:		the task to prepare
+ *
+ * Starts the rt_mutex acquire; it enqueues the @waiter and does deadlock
+ * detection. It does not wait, see rt_mutex_wait_proxy_lock() for that.
+ *
+ * NOTE: does _NOT_ remove the @waiter on failure; must either call
+ * rt_mutex_wait_proxy_lock() or rt_mutex_cleanup_proxy_lock() after this.
+ *
+ * Returns:
+ *  0 - task blocked on lock
+ *  1 - acquired the lock for task, caller should wake it up
+ * <0 - error
+ *
+ * Special API call for PI-futex support.
+ */
 int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 			      struct rt_mutex_waiter *waiter,
 			      struct task_struct *task)
 {
 	int ret;
 
+	lockdep_assert_held(&lock->wait_lock);
+
 	if (try_to_take_rt_mutex(lock, task, NULL))
 		return 1;
 
@@ -1749,9 +1770,6 @@ int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 		ret = 0;
 	}
 
-	if (unlikely(ret))
-		remove_waiter(lock, waiter);
-
 	debug_rt_mutex_print_deadlock(waiter);
 
 	return ret;
@@ -1763,12 +1781,18 @@ int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
  * @waiter:		the pre-initialized rt_mutex_waiter
  * @task:		the task to prepare
  *
+ * Starts the rt_mutex acquire; it enqueues the @waiter and does deadlock
+ * detection. It does not wait, see rt_mutex_wait_proxy_lock() for that.
+ *
+ * NOTE: unlike __rt_mutex_start_proxy_lock this _DOES_ remove the @waiter
+ * on failure.
+ *
  * Returns:
  *  0 - task blocked on lock
  *  1 - acquired the lock for task, caller should wake it up
  * <0 - error
  *
- * Special API call for FUTEX_REQUEUE_PI support.
+ * Special API call for PI-futex support.
  */
 int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 			      struct rt_mutex_waiter *waiter,
@@ -1778,6 +1802,8 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 
 	raw_spin_lock_irq(&lock->wait_lock);
 	ret = __rt_mutex_start_proxy_lock(lock, waiter, task);
+	if (unlikely(ret))
+		remove_waiter(lock, waiter);
 	raw_spin_unlock_irq(&lock->wait_lock);
 
 	return ret;
@@ -1845,7 +1871,8 @@ int rt_mutex_wait_proxy_lock(struct rt_mutex *lock,
  * @lock:		the rt_mutex we were woken on
  * @waiter:		the pre-initialized rt_mutex_waiter
  *
- * Attempt to clean up after a failed rt_mutex_wait_proxy_lock().
+ * Attempt to clean up after a failed __rt_mutex_start_proxy_lock() or
+ * rt_mutex_wait_proxy_lock().
  *
  * Unless we acquired the lock; we're still enqueued on the wait-list and can
  * in fact still be granted ownership until we're removed. Therefore we can
diff --git a/kernel/relay.c b/kernel/relay.c
index 04f248644e06..9e0f52375487 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -428,6 +428,8 @@ static struct dentry *relay_create_buf_file(struct rchan *chan,
 	dentry = chan->cb->create_buf_file(tmpname, chan->parent,
 					   S_IRUSR, buf,
 					   &chan->is_global);
+	if (IS_ERR(dentry))
+		dentry = NULL;
 
 	kfree(tmpname);
 
@@ -461,7 +463,7 @@ static struct rchan_buf *relay_open_buf(struct rchan *chan, unsigned int cpu)
 		dentry = chan->cb->create_buf_file(NULL, NULL,
 						   S_IRUSR, buf,
 						   &chan->is_global);
-		if (WARN_ON(dentry))
+		if (IS_ERR_OR_NULL(dentry))
 			goto free_buf;
 	}
 
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index c3484785b179..0e97ca9306ef 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -322,7 +322,7 @@ static bool update_stats(struct psi_group *group)
 	expires = group->next_update;
 	if (now < expires)
 		goto out;
-	if (now - expires > psi_period)
+	if (now - expires >= psi_period)
 		missed_periods = div_u64(now - expires, psi_period);
 
 	/*
diff --git a/kernel/signal.c b/kernel/signal.c
index e1d7ad8e6ab1..57b7771e20d7 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -688,6 +688,48 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, kernel_siginfo_t *in
 }
 EXPORT_SYMBOL_GPL(dequeue_signal);
 
+static int dequeue_synchronous_signal(kernel_siginfo_t *info)
+{
+	struct task_struct *tsk = current;
+	struct sigpending *pending = &tsk->pending;
+	struct sigqueue *q, *sync = NULL;
+
+	/*
+	 * Might a synchronous signal be in the queue?
+	 */
+	if (!((pending->signal.sig[0] & ~tsk->blocked.sig[0]) & SYNCHRONOUS_MASK))
+		return 0;
+
+	/*
+	 * Return the first synchronous signal in the queue.
+	 */
+	list_for_each_entry(q, &pending->list, list) {
+		/* Synchronous signals have a postive si_code */
+		if ((q->info.si_code > SI_USER) &&
+		    (sigmask(q->info.si_signo) & SYNCHRONOUS_MASK)) {
+			sync = q;
+			goto next;
+		}
+	}
+	return 0;
+next:
+	/*
+	 * Check if there is another siginfo for the same signal.
+	 */
+	list_for_each_entry_continue(q, &pending->list, list) {
+		if (q->info.si_signo == sync->info.si_signo)
+			goto still_pending;
+	}
+
+	sigdelset(&pending->signal, sync->info.si_signo);
+	recalc_sigpending();
+still_pending:
+	list_del_init(&sync->list);
+	copy_siginfo(info, &sync->info);
+	__sigqueue_free(sync);
+	return info->si_signo;
+}
+
 /*
  * Tell a process that it has a new active signal..
  *
@@ -1057,10 +1099,9 @@ static int __send_signal(int sig, struct kernel_siginfo *info, struct task_struc
 
 	result = TRACE_SIGNAL_DELIVERED;
 	/*
-	 * Skip useless siginfo allocation for SIGKILL SIGSTOP,
-	 * and kernel threads.
+	 * Skip useless siginfo allocation for SIGKILL and kernel threads.
 	 */
-	if (sig_kernel_only(sig) || (t->flags & PF_KTHREAD))
+	if ((sig == SIGKILL) || (t->flags & PF_KTHREAD))
 		goto out_set;
 
 	/*
@@ -2394,6 +2435,14 @@ relock:
 		goto relock;
 	}
 
+	/* Has this task already been marked for death? */
+	if (signal_group_exit(signal)) {
+		ksig->info.si_signo = signr = SIGKILL;
+		sigdelset(&current->pending.signal, SIGKILL);
+		recalc_sigpending();
+		goto fatal;
+	}
+
 	for (;;) {
 		struct k_sigaction *ka;
 
@@ -2407,7 +2456,15 @@ relock:
 			goto relock;
 		}
 
-		signr = dequeue_signal(current, &current->blocked, &ksig->info);
+		/*
+		 * Signals generated by the execution of an instruction
+		 * need to be delivered before any other pending signals
+		 * so that the instruction pointer in the signal stack
+		 * frame points to the faulting instruction.
+		 */
+		signr = dequeue_synchronous_signal(&ksig->info);
+		if (!signr)
+			signr = dequeue_signal(current, &current->blocked, &ksig->info);
 
 		if (!signr)
 			break; /* will return 0 */
@@ -2489,6 +2546,7 @@ relock:
 			continue;
 		}
 
+	fatal:
 		spin_unlock_irq(&sighand->siglock);
 
 		/*
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 088c2032ceaf..d64c00afceb5 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1203,22 +1203,12 @@ static int __bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *
 
 int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog)
 {
-	int err;
-
-	mutex_lock(&bpf_event_mutex);
-	err = __bpf_probe_register(btp, prog);
-	mutex_unlock(&bpf_event_mutex);
-	return err;
+	return __bpf_probe_register(btp, prog);
 }
 
 int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog)
 {
-	int err;
-
-	mutex_lock(&bpf_event_mutex);
-	err = tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, prog);
-	mutex_unlock(&bpf_event_mutex);
-	return err;
+	return tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, prog);
 }
 
 int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index c521b7347482..c4238b441624 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3384,6 +3384,8 @@ static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file
 	const char tgid_space[] = "          ";
 	const char space[] = "  ";
 
+	print_event_info(buf, m);
+
 	seq_printf(m, "#                          %s  _-----=> irqs-off\n",
 		   tgid ? tgid_space : space);
 	seq_printf(m, "#                          %s / _----=> need-resched\n",
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index d5fb09ebba8b..9eaf07f99212 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -861,22 +861,14 @@ static const struct file_operations kprobe_profile_ops = {
 static nokprobe_inline int
 fetch_store_strlen(unsigned long addr)
 {
-	mm_segment_t old_fs;
 	int ret, len = 0;
 	u8 c;
 
-	old_fs = get_fs();
-	set_fs(KERNEL_DS);
-	pagefault_disable();
-
 	do {
-		ret = __copy_from_user_inatomic(&c, (u8 *)addr + len, 1);
+		ret = probe_mem_read(&c, (u8 *)addr + len, 1);
 		len++;
 	} while (c && ret == 0 && len < MAX_STRING_SIZE);
 
-	pagefault_enable();
-	set_fs(old_fs);
-
 	return (ret < 0) ? ret : len;
 }
 
diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h
index 5c56afc17cf8..4737bb8c07a3 100644
--- a/kernel/trace/trace_probe_tmpl.h
+++ b/kernel/trace/trace_probe_tmpl.h
@@ -180,10 +180,12 @@ store_trace_args(void *data, struct trace_probe *tp, struct pt_regs *regs,
 		if (unlikely(arg->dynamic))
 			*dl = make_data_loc(maxlen, dyndata - base);
 		ret = process_fetch_insn(arg->code, regs, dl, base);
-		if (unlikely(ret < 0 && arg->dynamic))
+		if (unlikely(ret < 0 && arg->dynamic)) {
 			*dl = make_data_loc(0, dyndata - base);
-		else
+		} else {
 			dyndata += ret;
+			maxlen -= ret;
+		}
 	}
 }
 
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index e335576b9411..9bde07c06362 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -5,7 +5,7 @@
  * Copyright (C) IBM Corporation, 2010-2012
  * Author:	Srikar Dronamraju <srikar@linux.vnet.ibm.com>
  */
-#define pr_fmt(fmt)	"trace_kprobe: " fmt
+#define pr_fmt(fmt)	"trace_uprobe: " fmt
 
 #include <linux/ctype.h>
 #include <linux/module.h>
@@ -160,6 +160,13 @@ fetch_store_string(unsigned long addr, void *dest, void *base)
 	if (ret >= 0) {
 		if (ret == maxlen)
 			dst[ret - 1] = '\0';
+		else
+			/*
+			 * Include the terminating null byte. In this case it
+			 * was copied by strncpy_from_user but not accounted
+			 * for in ret.
+			 */
+			ret++;
 		*(u32 *)dest = make_data_loc(ret, (void *)dst - base);
 	}