Merge tag 'trace-v4.5' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:
 "Not much new with tracing for this release.  Mostly just clean ups and
  minor fixes.

  Here's what else is new:

   - A new TRACE_EVENT_FN_COND macro, combining both _FN and _COND for
     those that want both.

   - New selftest to test the instance create and delete

   - Better debug output when ftrace fails"

* tag 'trace-v4.5' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (24 commits)
  ftrace: Fix the race between ftrace and insmod
  ftrace: Add infrastructure for delayed enabling of module functions
  x86: ftrace: Fix the comments for ftrace_modify_code_direct()
  tracing: Fix comment to use tracing_on over tracing_enable
  metag: ftrace: Fix the comments for ftrace_modify_code
  sh: ftrace: Fix the comments for ftrace_modify_code()
  ia64: ftrace: Fix the comments for ftrace_modify_code()
  ftrace: Clean up ftrace_module_init() code
  ftrace: Join functions ftrace_module_init() and ftrace_init_module()
  tracing: Introduce TRACE_EVENT_FN_COND macro
  tracing: Use seq_buf_used() in seq_buf_to_user() instead of len
  bpf: Constify bpf_verifier_ops structure
  ftrace: Have ftrace_ops_get_func() handle RCU and PER_CPU flags too
  ftrace: Remove use of control list and ops
  ftrace: Fix output of enabled_functions for showing tramp
  ftrace: Fix a typo in comment
  ftrace: Show all tramps registered to a record on ftrace_bug()
  ftrace: Add variable ftrace_expected for archs to show expected code
  ftrace: Add new type to distinguish what kind of ftrace_bug()
  tracing: Update cond flag when enabling or disabling a trigger
  ...

1 files changed, 26 insertions, 31 deletions

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 9c6045a27ba3..95181e36891a 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1001,17 +1001,13 @@ static int rb_head_page_replace(struct buffer_page *old,
 
 /*
  * rb_tail_page_update - move the tail page forward
- *
- * Returns 1 if moved tail page, 0 if someone else did.
  */
-static int rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer,
+static void rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer,
 			       struct buffer_page *tail_page,
 			       struct buffer_page *next_page)
 {
-	struct buffer_page *old_tail;
 	unsigned long old_entries;
 	unsigned long old_write;
-	int ret = 0;
 
 	/*
 	 * The tail page now needs to be moved forward.
@@ -1036,7 +1032,7 @@ static int rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer,
 	 * it is, then it is up to us to update the tail
 	 * pointer.
 	 */
-	if (tail_page == cpu_buffer->tail_page) {
+	if (tail_page == READ_ONCE(cpu_buffer->tail_page)) {
 		/* Zero the write counter */
 		unsigned long val = old_write & ~RB_WRITE_MASK;
 		unsigned long eval = old_entries & ~RB_WRITE_MASK;
@@ -1061,14 +1057,9 @@ static int rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer,
 		 */
 		local_set(&next_page->page->commit, 0);
 
-		old_tail = cmpxchg(&cpu_buffer->tail_page,
-				   tail_page, next_page);
-
-		if (old_tail == tail_page)
-			ret = 1;
+		/* Again, either we update tail_page or an interrupt does */
+		(void)cmpxchg(&cpu_buffer->tail_page, tail_page, next_page);
 	}
-
-	return ret;
 }
 
 static int rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer,
@@ -2036,12 +2027,15 @@ rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer,
 	 * the tail page would have moved.
 	 */
 	if (ret == RB_PAGE_NORMAL) {
+		struct buffer_page *buffer_tail_page;
+
+		buffer_tail_page = READ_ONCE(cpu_buffer->tail_page);
 		/*
 		 * If the tail had moved passed next, then we need
 		 * to reset the pointer.
 		 */
-		if (cpu_buffer->tail_page != tail_page &&
-		    cpu_buffer->tail_page != next_page)
+		if (buffer_tail_page != tail_page &&
+		    buffer_tail_page != next_page)
 			rb_head_page_set_normal(cpu_buffer, new_head,
 						next_page,
 						RB_PAGE_HEAD);
@@ -2135,6 +2129,8 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	local_sub(length, &tail_page->write);
 }
 
+static inline void rb_end_commit(struct ring_buffer_per_cpu *cpu_buffer);
+
 /*
  * This is the slow path, force gcc not to inline it.
  */
@@ -2147,7 +2143,6 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	struct ring_buffer *buffer = cpu_buffer->buffer;
 	struct buffer_page *next_page;
 	int ret;
-	u64 ts;
 
 	next_page = tail_page;
 
@@ -2221,20 +2216,17 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
 		}
 	}
 
-	ret = rb_tail_page_update(cpu_buffer, tail_page, next_page);
-	if (ret) {
-		/*
-		 * Nested commits always have zero deltas, so
-		 * just reread the time stamp
-		 */
-		ts = rb_time_stamp(buffer);
-		next_page->page->time_stamp = ts;
-	}
+	rb_tail_page_update(cpu_buffer, tail_page, next_page);
 
  out_again:
 
 	rb_reset_tail(cpu_buffer, tail, info);
 
+	/* Commit what we have for now. */
+	rb_end_commit(cpu_buffer);
+	/* rb_end_commit() decs committing */
+	local_inc(&cpu_buffer->committing);
+
 	/* fail and let the caller try again */
 	return ERR_PTR(-EAGAIN);
 
@@ -2362,7 +2354,7 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 	addr = (unsigned long)event;
 	addr &= PAGE_MASK;
 
-	bpage = cpu_buffer->tail_page;
+	bpage = READ_ONCE(cpu_buffer->tail_page);
 
 	if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) {
 		unsigned long write_mask =
@@ -2410,7 +2402,7 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
  again:
 	max_count = cpu_buffer->nr_pages * 100;
 
-	while (cpu_buffer->commit_page != cpu_buffer->tail_page) {
+	while (cpu_buffer->commit_page != READ_ONCE(cpu_buffer->tail_page)) {
 		if (RB_WARN_ON(cpu_buffer, !(--max_count)))
 			return;
 		if (RB_WARN_ON(cpu_buffer,
@@ -2419,8 +2411,10 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
 		local_set(&cpu_buffer->commit_page->page->commit,
 			  rb_page_write(cpu_buffer->commit_page));
 		rb_inc_page(cpu_buffer, &cpu_buffer->commit_page);
-		cpu_buffer->write_stamp =
-			cpu_buffer->commit_page->page->time_stamp;
+		/* Only update the write stamp if the page has an event */
+		if (rb_page_write(cpu_buffer->commit_page))
+			cpu_buffer->write_stamp =
+				cpu_buffer->commit_page->page->time_stamp;
 		/* add barrier to keep gcc from optimizing too much */
 		barrier();
 	}
@@ -2443,7 +2437,7 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
 	 * and pushed the tail page forward, we will be left with
 	 * a dangling commit that will never go forward.
 	 */
-	if (unlikely(cpu_buffer->commit_page != cpu_buffer->tail_page))
+	if (unlikely(cpu_buffer->commit_page != READ_ONCE(cpu_buffer->tail_page)))
 		goto again;
 }
 
@@ -2699,7 +2693,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	if (unlikely(info->add_timestamp))
 		info->length += RB_LEN_TIME_EXTEND;
 
-	tail_page = info->tail_page = cpu_buffer->tail_page;
+	/* Don't let the compiler play games with cpu_buffer->tail_page */
+	tail_page = info->tail_page = READ_ONCE(cpu_buffer->tail_page);
 	write = local_add_return(info->length, &tail_page->write);
 
 	/* set write to only the index of the write */