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

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

9 files changed, 105 insertions, 53 deletions

diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index f2ece3c174a5..8f94ca1860cf 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -31,10 +31,10 @@ static void *bpf_any_get(void *raw, enum bpf_type type)
 {
 	switch (type) {
 	case BPF_TYPE_PROG:
-		atomic_inc(&((struct bpf_prog *)raw)->aux->refcnt);
+		raw = bpf_prog_inc(raw);
 		break;
 	case BPF_TYPE_MAP:
-		bpf_map_inc(raw, true);
+		raw = bpf_map_inc(raw, true);
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -297,7 +297,8 @@ static void *bpf_obj_do_get(const struct filename *pathname,
 		goto out;
 
 	raw = bpf_any_get(inode->i_private, *type);
-	touch_atime(&path);
+	if (!IS_ERR(raw))
+		touch_atime(&path);
 
 	path_put(&path);
 	return raw;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index adc5e4bd74f8..cf5e9f7ad13a 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -218,11 +218,18 @@ struct bpf_map *__bpf_map_get(struct fd f)
 	return f.file->private_data;
 }
 
-void bpf_map_inc(struct bpf_map *map, bool uref)
+/* prog's and map's refcnt limit */
+#define BPF_MAX_REFCNT 32768
+
+struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref)
 {
-	atomic_inc(&map->refcnt);
+	if (atomic_inc_return(&map->refcnt) > BPF_MAX_REFCNT) {
+		atomic_dec(&map->refcnt);
+		return ERR_PTR(-EBUSY);
+	}
 	if (uref)
 		atomic_inc(&map->usercnt);
+	return map;
 }
 
 struct bpf_map *bpf_map_get_with_uref(u32 ufd)
@@ -234,7 +241,7 @@ struct bpf_map *bpf_map_get_with_uref(u32 ufd)
 	if (IS_ERR(map))
 		return map;
 
-	bpf_map_inc(map, true);
+	map = bpf_map_inc(map, true);
 	fdput(f);
 
 	return map;
@@ -658,6 +665,15 @@ static struct bpf_prog *__bpf_prog_get(struct fd f)
 	return f.file->private_data;
 }
 
+struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog)
+{
+	if (atomic_inc_return(&prog->aux->refcnt) > BPF_MAX_REFCNT) {
+		atomic_dec(&prog->aux->refcnt);
+		return ERR_PTR(-EBUSY);
+	}
+	return prog;
+}
+
 /* called by sockets/tracing/seccomp before attaching program to an event
  * pairs with bpf_prog_put()
  */
@@ -670,7 +686,7 @@ struct bpf_prog *bpf_prog_get(u32 ufd)
 	if (IS_ERR(prog))
 		return prog;
 
-	atomic_inc(&prog->aux->refcnt);
+	prog = bpf_prog_inc(prog);
 	fdput(f);
 
 	return prog;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index db2574e7b8b0..c5c17a62f509 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -239,16 +239,6 @@ static const char * const reg_type_str[] = {
 	[CONST_IMM]		= "imm",
 };
 
-static const struct {
-	int map_type;
-	int func_id;
-} func_limit[] = {
-	{BPF_MAP_TYPE_PROG_ARRAY, BPF_FUNC_tail_call},
-	{BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_read},
-	{BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_output},
-	{BPF_MAP_TYPE_STACK_TRACE, BPF_FUNC_get_stackid},
-};
-
 static void print_verifier_state(struct verifier_env *env)
 {
 	enum bpf_reg_type t;
@@ -921,27 +911,52 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
 
 static int check_map_func_compatibility(struct bpf_map *map, int func_id)
 {
-	bool bool_map, bool_func;
-	int i;
-
 	if (!map)
 		return 0;
 
-	for (i = 0; i < ARRAY_SIZE(func_limit); i++) {
-		bool_map = (map->map_type == func_limit[i].map_type);
-		bool_func = (func_id == func_limit[i].func_id);
-		/* only when map & func pair match it can continue.
-		 * don't allow any other map type to be passed into
-		 * the special func;
-		 */
-		if (bool_func && bool_map != bool_func) {
-			verbose("cannot pass map_type %d into func %d\n",
-				map->map_type, func_id);
-			return -EINVAL;
-		}
+	/* We need a two way check, first is from map perspective ... */
+	switch (map->map_type) {
+	case BPF_MAP_TYPE_PROG_ARRAY:
+		if (func_id != BPF_FUNC_tail_call)
+			goto error;
+		break;
+	case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
+		if (func_id != BPF_FUNC_perf_event_read &&
+		    func_id != BPF_FUNC_perf_event_output)
+			goto error;
+		break;
+	case BPF_MAP_TYPE_STACK_TRACE:
+		if (func_id != BPF_FUNC_get_stackid)
+			goto error;
+		break;
+	default:
+		break;
+	}
+
+	/* ... and second from the function itself. */
+	switch (func_id) {
+	case BPF_FUNC_tail_call:
+		if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
+			goto error;
+		break;
+	case BPF_FUNC_perf_event_read:
+	case BPF_FUNC_perf_event_output:
+		if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY)
+			goto error;
+		break;
+	case BPF_FUNC_get_stackid:
+		if (map->map_type != BPF_MAP_TYPE_STACK_TRACE)
+			goto error;
+		break;
+	default:
+		break;
 	}
 
 	return 0;
+error:
+	verbose("cannot pass map_type %d into func %d\n",
+		map->map_type, func_id);
+	return -EINVAL;
 }
 
 static int check_call(struct verifier_env *env, int func_id)
@@ -2049,15 +2064,18 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env)
 				return -E2BIG;
 			}
 
-			/* remember this map */
-			env->used_maps[env->used_map_cnt++] = map;
-
 			/* hold the map. If the program is rejected by verifier,
 			 * the map will be released by release_maps() or it
 			 * will be used by the valid program until it's unloaded
 			 * and all maps are released in free_bpf_prog_info()
 			 */
-			bpf_map_inc(map, false);
+			map = bpf_map_inc(map, false);
+			if (IS_ERR(map)) {
+				fdput(f);
+				return PTR_ERR(map);
+			}
+			env->used_maps[env->used_map_cnt++] = map;
+
 			fdput(f);
 next_insn:
 			insn++;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index fc0290f25482..050a290c72c7 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -353,7 +353,7 @@ static struct srcu_struct pmus_srcu;
  *   1 - disallow cpu events for unpriv
  *   2 - disallow kernel profiling for unpriv
  */
-int sysctl_perf_event_paranoid __read_mostly = 1;
+int sysctl_perf_event_paranoid __read_mostly = 2;
 
 /* Minimum for 512 kiB + 1 user control page */
 int sysctl_perf_event_mlock __read_mostly = 512 + (PAGE_SIZE / 1024); /* 'free' kiB per user */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 8b489fcac37b..d1f7149f8704 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -596,17 +596,8 @@ bool sched_can_stop_tick(struct rq *rq)
 		return false;
 
 	/*
-	 * FIFO realtime policy runs the highest priority task (after DEADLINE).
-	 * Other runnable tasks are of a lower priority. The scheduler tick
-	 * isn't needed.
-	 */
-	fifo_nr_running = rq->rt.rt_nr_running - rq->rt.rr_nr_running;
-	if (fifo_nr_running)
-		return true;
-
-	/*
-	 * Round-robin realtime tasks time slice with other tasks at the same
-	 * realtime priority.
+	 * If there are more than one RR tasks, we need the tick to effect the
+	 * actual RR behaviour.
 	 */
 	if (rq->rt.rr_nr_running) {
 		if (rq->rt.rr_nr_running == 1)
@@ -615,8 +606,20 @@ bool sched_can_stop_tick(struct rq *rq)
 			return false;
 	}
 
-	/* Normal multitasking need periodic preemption checks */
-	if (rq->cfs.nr_running > 1)
+	/*
+	 * If there's no RR tasks, but FIFO tasks, we can skip the tick, no
+	 * forced preemption between FIFO tasks.
+	 */
+	fifo_nr_running = rq->rt.rt_nr_running - rq->rt.rr_nr_running;
+	if (fifo_nr_running)
+		return true;
+
+	/*
+	 * If there are no DL,RR/FIFO tasks, there must only be CFS tasks left;
+	 * if there's more than one we need the tick for involuntary
+	 * preemption.
+	 */
+	if (rq->nr_running > 1)
 		return false;
 
 	return true;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index affd97ec9f65..686ec8adf952 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1394,6 +1394,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
 				     !cpumask_test_cpu(later_rq->cpu,
 				                       &task->cpus_allowed) ||
 				     task_running(rq, task) ||
+				     !dl_task(task) ||
 				     !task_on_rq_queued(task))) {
 				double_unlock_balance(rq, later_rq);
 				later_rq = NULL;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0fe30e66aff1..40748dc8ea3e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3030,7 +3030,14 @@ static int idle_balance(struct rq *this_rq);
 
 #else /* CONFIG_SMP */
 
-static inline void update_load_avg(struct sched_entity *se, int update_tg) {}
+static inline void update_load_avg(struct sched_entity *se, int not_used)
+{
+	struct cfs_rq *cfs_rq = cfs_rq_of(se);
+	struct rq *rq = rq_of(cfs_rq);
+
+	cpufreq_trigger_update(rq_clock(rq));
+}
+
 static inline void
 enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
 static inline void
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index c41ea7ac1764..ec4f538d4396 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1729,6 +1729,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 				     !cpumask_test_cpu(lowest_rq->cpu,
 						       tsk_cpus_allowed(task)) ||
 				     task_running(rq, task) ||
+				     !rt_task(task) ||
 				     !task_on_rq_queued(task))) {
 
 				double_unlock_balance(rq, lowest_rq);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 05ddc0820771..6f965864cc02 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2095,8 +2095,13 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file)
 	trace_create_file("filter", 0644, file->dir, file,
 			  &ftrace_event_filter_fops);
 
-	trace_create_file("trigger", 0644, file->dir, file,
-			  &event_trigger_fops);
+	/*
+	 * Only event directories that can be enabled should have
+	 * triggers.
+	 */
+	if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE))
+		trace_create_file("trigger", 0644, file->dir, file,
+				  &event_trigger_fops);
 
 	trace_create_file("format", 0444, file->dir, call,
 			  &ftrace_event_format_fops);