6 files changed, 73 insertions, 16 deletions

diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 90e72a0c3047..e3a26188b95e 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -437,7 +437,7 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 		       struct block_device *bdev,
 		       struct blk_user_trace_setup *buts)
 {
-	struct blk_trace *old_bt, *bt = NULL;
+	struct blk_trace *bt = NULL;
 	struct dentry *dir = NULL;
 	int ret;
 
@@ -519,11 +519,8 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	bt->trace_state = Blktrace_setup;
 
 	ret = -EBUSY;
-	old_bt = xchg(&q->blk_trace, bt);
-	if (old_bt) {
-		(void) xchg(&q->blk_trace, old_bt);
+	if (cmpxchg(&q->blk_trace, NULL, bt))
 		goto err;
-	}
 
 	if (atomic_inc_return(&blk_probes_ref) == 1)
 		blk_register_tracepoints();
@@ -1481,7 +1478,7 @@ static int blk_trace_remove_queue(struct request_queue *q)
 static int blk_trace_setup_queue(struct request_queue *q,
 				 struct block_device *bdev)
 {
-	struct blk_trace *old_bt, *bt = NULL;
+	struct blk_trace *bt = NULL;
 	int ret = -ENOMEM;
 
 	bt = kzalloc(sizeof(*bt), GFP_KERNEL);
@@ -1497,12 +1494,9 @@ static int blk_trace_setup_queue(struct request_queue *q,
 
 	blk_trace_setup_lba(bt, bdev);
 
-	old_bt = xchg(&q->blk_trace, bt);
-	if (old_bt != NULL) {
-		(void)xchg(&q->blk_trace, old_bt);
-		ret = -EBUSY;
+	ret = -EBUSY;
+	if (cmpxchg(&q->blk_trace, NULL, bt))
 		goto free_bt;
-	}
 
 	if (atomic_inc_return(&blk_probes_ref) == 1)
 		blk_register_tracepoints();
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 0fe96c7c8803..4228fd3682c3 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -199,6 +199,11 @@ static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5)
 	if (!event)
 		return -ENOENT;
 
+	/* make sure event is local and doesn't have pmu::count */
+	if (event->oncpu != smp_processor_id() ||
+	    event->pmu->count)
+		return -EINVAL;
+
 	/*
 	 * we don't know if the function is run successfully by the
 	 * return value. It can be judged in other places, such as
@@ -207,14 +212,58 @@ static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5)
 	return perf_event_read_local(event);
 }
 
-const struct bpf_func_proto bpf_perf_event_read_proto = {
+static const struct bpf_func_proto bpf_perf_event_read_proto = {
 	.func		= bpf_perf_event_read,
-	.gpl_only	= false,
+	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_CONST_MAP_PTR,
 	.arg2_type	= ARG_ANYTHING,
 };
 
+static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 index, u64 r4, u64 size)
+{
+	struct pt_regs *regs = (struct pt_regs *) (long) r1;
+	struct bpf_map *map = (struct bpf_map *) (long) r2;
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	void *data = (void *) (long) r4;
+	struct perf_sample_data sample_data;
+	struct perf_event *event;
+	struct perf_raw_record raw = {
+		.size = size,
+		.data = data,
+	};
+
+	if (unlikely(index >= array->map.max_entries))
+		return -E2BIG;
+
+	event = (struct perf_event *)array->ptrs[index];
+	if (unlikely(!event))
+		return -ENOENT;
+
+	if (unlikely(event->attr.type != PERF_TYPE_SOFTWARE ||
+		     event->attr.config != PERF_COUNT_SW_BPF_OUTPUT))
+		return -EINVAL;
+
+	if (unlikely(event->oncpu != smp_processor_id()))
+		return -EOPNOTSUPP;
+
+	perf_sample_data_init(&sample_data, 0, 0);
+	sample_data.raw = &raw;
+	perf_event_output(event, &sample_data, regs);
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_perf_event_output_proto = {
+	.func		= bpf_perf_event_output,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_CONST_MAP_PTR,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_PTR_TO_STACK,
+	.arg5_type	= ARG_CONST_STACK_SIZE,
+};
+
 static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func_id)
 {
 	switch (func_id) {
@@ -242,6 +291,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func
 		return &bpf_get_smp_processor_id_proto;
 	case BPF_FUNC_perf_event_read:
 		return &bpf_perf_event_read_proto;
+	case BPF_FUNC_perf_event_output:
+		return &bpf_perf_event_output_proto;
 	default:
 		return NULL;
 	}
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index b0623ac785a2..00611e95a8ee 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -5697,7 +5697,7 @@ free:
 }
 
 static void
-ftrace_graph_probe_sched_switch(void *ignore,
+ftrace_graph_probe_sched_switch(void *ignore, bool preempt,
 			struct task_struct *prev, struct task_struct *next)
 {
 	unsigned long long timestamp;
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index f270088e9929..4c896a0101bd 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -16,7 +16,8 @@ static int			sched_ref;
 static DEFINE_MUTEX(sched_register_mutex);
 
 static void
-probe_sched_switch(void *ignore, struct task_struct *prev, struct task_struct *next)
+probe_sched_switch(void *ignore, bool preempt,
+		   struct task_struct *prev, struct task_struct *next)
 {
 	if (unlikely(!sched_ref))
 		return;
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 12cbe77b4136..4bcfbac289ff 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -420,7 +420,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 }
 
 static void notrace
-probe_wakeup_sched_switch(void *ignore,
+probe_wakeup_sched_switch(void *ignore, bool preempt,
 			  struct task_struct *prev, struct task_struct *next)
 {
 	struct trace_array_cpu *data;
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index b746399ab59c..8abf1ba18085 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -85,9 +85,19 @@ check_stack(unsigned long ip, unsigned long *stack)
 	if (!object_is_on_stack(stack))
 		return;
 
+	/* Can't do this from NMI context (can cause deadlocks) */
+	if (in_nmi())
+		return;
+
 	local_irq_save(flags);
 	arch_spin_lock(&max_stack_lock);
 
+	/*
+	 * RCU may not be watching, make it see us.
+	 * The stack trace code uses rcu_sched.
+	 */
+	rcu_irq_enter();
+
 	/* In case another CPU set the tracer_frame on us */
 	if (unlikely(!frame_size))
 		this_size -= tracer_frame;
@@ -169,6 +179,7 @@ check_stack(unsigned long ip, unsigned long *stack)
 	}
 
  out:
+	rcu_irq_exit();
 	arch_spin_unlock(&max_stack_lock);
 	local_irq_restore(flags);
 }