Merge tag 'trace-ring-buffer-v6.8-rc7-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull tracing updates from Steven Rostedt:

- Do not update shortest_full in rb_watermark_hit() if the watermark is
hit. The shortest_full field was being updated regardless if the task
was going to wait or not. If the watermark is hit, then the task is
not going to wait, so do not update the shortest_full field (used by
the waker).

- Update shortest_full field before setting the full_waiters_pending
flag

In the poll logic, the full_waiters_pending flag was being set before
the shortest_full field was set. If the full_waiters_pending flag is
set, writers will check the shortest_full field which has the least
percentage of data that the ring buffer needs to be filled before
waking up. The writer will check shortest_full if
full_waiters_pending is set, and if the ring buffer percentage filled
is greater than shortest full, then it will call the irq_work to wake
up the waiters.

The problem was that the poll logic set the full_waiters_pending flag
before updating shortest_full, which when zero will always trigger
the writer to call the irq_work to wake up the waiters. The irq_work
will reset the shortest_full field back to zero as the woken waiters
is suppose to reset it.

- There's some optimized logic in the rb_watermark_hit() that is used
in ring_buffer_wait(). Use that helper function in the poll logic as
well.

- Restructure ring_buffer_wait() to use wait_event_interruptible()

The logic to wake up pending readers when the file descriptor is
closed is racy. Restructure ring_buffer_wait() to allow callers to
pass in conditions besides the ring buffer having enough data in it
by using wait_event_interruptible().

- Update the tracing_wait_on_pipe() to call ring_buffer_wait() with its
own conditions to exit the wait loop.

* tag 'trace-ring-buffer-v6.8-rc7-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
tracing/ring-buffer: Fix wait_on_pipe() race
ring-buffer: Use wait_event_interruptible() in ring_buffer_wait()
ring-buffer: Reuse rb_watermark_hit() for the poll logic
ring-buffer: Fix full_waiters_pending in poll
ring-buffer: Do not set shortest_full when full target is hit

include/linux/ring_buffer.h

···
 	__ring_buffer_alloc((size), (flags), &__key);	\
 })
 
-int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full);
+typedef bool (*ring_buffer_cond_fn)(void *data);
+int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full,
+		     ring_buffer_cond_fn cond, void *data);
 __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu,
 			  struct file *filp, poll_table *poll_table, int full);
 void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu);

include/linux/trace_events.h

···
 	unsigned int		temp_size;
 	char			*fmt;	/* modified format holder */
 	unsigned int		fmt_size;
-	long			wait_index;
+	atomic_t		wait_index;
 
 	/* trace_seq for __print_flags() and __print_symbolic() etc. */
 	struct trace_seq	tmp_seq;
 
 	cpumask_var_t		started;
+
+	/* Set when the file is closed to prevent new waiters */
+	bool			closed;
 
 	/* it's true when current open file is snapshot */
 	bool			snapshot;

kernel/trace/ring_buffer.c

···
 		pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page;
 		ret = !pagebusy && full_hit(buffer, cpu, full);
 
-		if (!cpu_buffer->shortest_full ||
-		    cpu_buffer->shortest_full > full)
-			cpu_buffer->shortest_full = full;
+		if (!ret && (!cpu_buffer->shortest_full ||
+			     cpu_buffer->shortest_full > full)) {
+		    cpu_buffer->shortest_full = full;
+		}
 		raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 	}
 	return ret;
 }
 
-/**
- * ring_buffer_wait - wait for input to the ring buffer
- * @buffer: buffer to wait on
- * @cpu: the cpu buffer to wait on
- * @full: wait until the percentage of pages are available, if @cpu != RING_BUFFER_ALL_CPUS
- *
- * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon
- * as data is added to any of the @buffer's cpu buffers. Otherwise
- * it will wait for data to be added to a specific cpu buffer.
- */
-int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
+static inline bool
+rb_wait_cond(struct rb_irq_work *rbwork, struct trace_buffer *buffer,
+	     int cpu, int full, ring_buffer_cond_fn cond, void *data)
 {
-	struct ring_buffer_per_cpu *cpu_buffer;
-	DEFINE_WAIT(wait);
-	struct rb_irq_work *work;
-	int ret = 0;
+	if (rb_watermark_hit(buffer, cpu, full))
+		return true;
 
-	/*
-	 * Depending on what the caller is waiting for, either any
-	 * data in any cpu buffer, or a specific buffer, put the
-	 * caller on the appropriate wait queue.
-	 */
-	if (cpu == RING_BUFFER_ALL_CPUS) {
-		work = &buffer->irq_work;
-		/* Full only makes sense on per cpu reads */
-		full = 0;
-	} else {
-		if (!cpumask_test_cpu(cpu, buffer->cpumask))
-			return -ENODEV;
-		cpu_buffer = buffer->buffers[cpu];
-		work = &cpu_buffer->irq_work;
-	}
-
-	if (full)
-		prepare_to_wait(&work->full_waiters, &wait, TASK_INTERRUPTIBLE);
-	else
-		prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE);
+	if (cond(data))
+		return true;
 
 	/*
 	 * The events can happen in critical sections where
···
 	 * a task has been queued. It's OK for spurious wake ups.
 	 */
 	if (full)
-		work->full_waiters_pending = true;
+		rbwork->full_waiters_pending = true;
 	else
-		work->waiters_pending = true;
+		rbwork->waiters_pending = true;
 
-	if (rb_watermark_hit(buffer, cpu, full))
-		goto out;
+	return false;
+}
 
-	if (signal_pending(current)) {
-		ret = -EINTR;
-		goto out;
+/*
+ * The default wait condition for ring_buffer_wait() is to just to exit the
+ * wait loop the first time it is woken up.
+ */
+static bool rb_wait_once(void *data)
+{
+	long *once = data;
+
+	/* wait_event() actually calls this twice before scheduling*/
+	if (*once > 1)
+		return true;
+
+	(*once)++;
+	return false;
+}
+
+/**
+ * ring_buffer_wait - wait for input to the ring buffer
+ * @buffer: buffer to wait on
+ * @cpu: the cpu buffer to wait on
+ * @full: wait until the percentage of pages are available, if @cpu != RING_BUFFER_ALL_CPUS
+ * @cond: condition function to break out of wait (NULL to run once)
+ * @data: the data to pass to @cond.
+ *
+ * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon
+ * as data is added to any of the @buffer's cpu buffers. Otherwise
+ * it will wait for data to be added to a specific cpu buffer.
+ */
+int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full,
+		     ring_buffer_cond_fn cond, void *data)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	struct wait_queue_head *waitq;
+	struct rb_irq_work *rbwork;
+	long once = 0;
+	int ret = 0;
+
+	if (!cond) {
+		cond = rb_wait_once;
+		data = &once;
 	}
 
-	schedule();
- out:
-	if (full)
-		finish_wait(&work->full_waiters, &wait);
-	else
-		finish_wait(&work->waiters, &wait);
+	/*
+	 * Depending on what the caller is waiting for, either any
+	 * data in any cpu buffer, or a specific buffer, put the
+	 * caller on the appropriate wait queue.
+	 */
+	if (cpu == RING_BUFFER_ALL_CPUS) {
+		rbwork = &buffer->irq_work;
+		/* Full only makes sense on per cpu reads */
+		full = 0;
+	} else {
+		if (!cpumask_test_cpu(cpu, buffer->cpumask))
+			return -ENODEV;
+		cpu_buffer = buffer->buffers[cpu];
+		rbwork = &cpu_buffer->irq_work;
+	}
 
-	if (!ret && !rb_watermark_hit(buffer, cpu, full) && signal_pending(current))
-		ret = -EINTR;
+	if (full)
+		waitq = &rbwork->full_waiters;
+	else
+		waitq = &rbwork->waiters;
+
+	ret = wait_event_interruptible((*waitq),
+				rb_wait_cond(rbwork, buffer, cpu, full, cond, data));
 
 	return ret;
 }
···
 	}
 
 	if (full) {
-		unsigned long flags;
-
 		poll_wait(filp, &rbwork->full_waiters, poll_table);
 
-		raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+		if (rb_watermark_hit(buffer, cpu, full))
+			return EPOLLIN | EPOLLRDNORM;
+		/*
+		 * Only allow full_waiters_pending update to be seen after
+		 * the shortest_full is set (in rb_watermark_hit). If the
+		 * writer sees the full_waiters_pending flag set, it will
+		 * compare the amount in the ring buffer to shortest_full.
+		 * If the amount in the ring buffer is greater than the
+		 * shortest_full percent, it will call the irq_work handler
+		 * to wake up this list. The irq_handler will reset shortest_full
+		 * back to zero. That's done under the reader_lock, but
+		 * the below smp_mb() makes sure that the update to
+		 * full_waiters_pending doesn't leak up into the above.
+		 */
+		smp_mb();
 		rbwork->full_waiters_pending = true;
-		if (!cpu_buffer->shortest_full ||
-		    cpu_buffer->shortest_full > full)
-			cpu_buffer->shortest_full = full;
-		raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
-	} else {
-		poll_wait(filp, &rbwork->waiters, poll_table);
-		rbwork->waiters_pending = true;
+		return 0;
 	}
+
+	poll_wait(filp, &rbwork->waiters, poll_table);
+	rbwork->waiters_pending = true;
 
 	/*
 	 * There's a tight race between setting the waiters_pending and
···
 	 * will fix it later.
 	 */
 	smp_mb();
-
-	if (full)
-		return full_hit(buffer, cpu, full) ? EPOLLIN | EPOLLRDNORM : 0;
 
 	if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) ||
 	    (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu)))

kernel/trace/trace.c

···
 
 #endif /* CONFIG_TRACER_MAX_TRACE */
 
+struct pipe_wait {
+	struct trace_iterator		*iter;
+	int				wait_index;
+};
+
+static bool wait_pipe_cond(void *data)
+{
+	struct pipe_wait *pwait = data;
+	struct trace_iterator *iter = pwait->iter;
+
+	if (atomic_read_acquire(&iter->wait_index) != pwait->wait_index)
+		return true;
+
+	return iter->closed;
+}
+
 static int wait_on_pipe(struct trace_iterator *iter, int full)
 {
+	struct pipe_wait pwait;
 	int ret;
 
 	/* Iterators are static, they should be filled or empty */
 	if (trace_buffer_iter(iter, iter->cpu_file))
 		return 0;
 
-	ret = ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, full);
+	pwait.wait_index = atomic_read_acquire(&iter->wait_index);
+	pwait.iter = iter;
+
+	ret = ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, full,
+			       wait_pipe_cond, &pwait);
 
 #ifdef CONFIG_TRACER_MAX_TRACE
 	/*
···
 	struct ftrace_buffer_info *info = file->private_data;
 	struct trace_iterator *iter = &info->iter;
 
-	iter->wait_index++;
+	iter->closed = true;
 	/* Make sure the waiters see the new wait_index */
-	smp_wmb();
+	(void)atomic_fetch_inc_release(&iter->wait_index);
 
 	ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file);
 
···
 		.spd_release	= buffer_spd_release,
 	};
 	struct buffer_ref *ref;
+	bool woken = false;
 	int page_size;
 	int entries, i;
 	ssize_t ret = 0;
···
 
 	/* did we read anything? */
 	if (!spd.nr_pages) {
-		long wait_index;
 
 		if (ret)
+			goto out;
+
+		if (woken)
 			goto out;
 
 		ret = -EAGAIN;
 		if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK))
 			goto out;
-
-		wait_index = READ_ONCE(iter->wait_index);
 
 		ret = wait_on_pipe(iter, iter->snapshot ? 0 : iter->tr->buffer_percent);
 		if (ret)
···
 		if (!tracer_tracing_is_on(iter->tr))
 			goto out;
 
-		/* Make sure we see the new wait_index */
-		smp_rmb();
-		if (wait_index != iter->wait_index)
-			goto out;
+		/* Iterate one more time to collect any new data then exit */
+		woken = true;
 
 		goto again;
 	}
···
 
 	mutex_lock(&trace_types_lock);
 
-	iter->wait_index++;
 	/* Make sure the waiters see the new wait_index */
-	smp_wmb();
+	(void)atomic_fetch_inc_release(&iter->wait_index);
 
 	ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file);