tracing/ring-buffer: Fix wait_on_pipe() race

When the trace_pipe_raw file is closed, there should be no new readers on
the file descriptor. This is mostly handled with the waking and wait_index
fields of the iterator. But there's still a slight race.

     CPU 0                              CPU 1
     -----                              -----
                                   wait_index++;
   index = wait_index;
                                   ring_buffer_wake_waiters();
   wait_on_pipe()
     ring_buffer_wait();

The ring_buffer_wait() will miss the wakeup from CPU 1. The problem is
that the ring_buffer_wait() needs the logic of:

        prepare_to_wait();
        if (!condition)
                schedule();

Where the missing condition check is the iter->wait_index update.

Have the ring_buffer_wait() take a conditional callback function and a
data parameter that can be used within the wait_event_interruptible() of
the ring_buffer_wait() function.

In wait_on_pipe(), pass a condition function that will check if the
wait_index has been updated, if it has, it will return true to break out
of the wait_event_interruptible() loop.

Create a new field "closed" in the trace_iterator and set it in the
.flush() callback before calling ring_buffer_wake_waiters().
This will keep any new readers from waiting on a closed file descriptor.

Have the wait_on_pipe() condition callback also check the closed field.

Change the wait_index field of the trace_iterator to atomic_t. There's no
reason it needs to be 'long' and making it atomic and using
atomic_read_acquire() and atomic_fetch_inc_release() will provide the
necessary memory barriers.

Add a "woken" flag to tracing_buffers_splice_read() to exit the loop after
one more try to fetch data. That is, if it waited for data and something
woke it up, it should try to collect any new data and then exit back to
user space.

Link: https://lore.kernel.org/linux-trace-kernel/CAHk-=wgsNgewHFxZAJiAQznwPMqEtQmi1waeS2O1v6L4c_Um5A@mail.gmail.com/
Link: https://lore.kernel.org/linux-trace-kernel/20240312121703.557950713@goodmis.org

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linke li <lilinke99@qq.com>
Cc: Rabin Vincent <rabin@rab.in>
Fixes: f3ddb74ad0790 ("tracing: Wake up ring buffer waiters on closing of the file")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

1 files changed, 31 insertions, 12 deletions

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index c9c898307348..d390fea3a6a5 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1955,15 +1955,36 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 
 #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
 	/*
@@ -8398,9 +8419,9 @@ static int tracing_buffers_flush(struct file *file, fl_owner_t id)
 	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);
 
@@ -8500,6 +8521,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		.spd_release	= buffer_spd_release,
 	};
 	struct buffer_ref *ref;
+	bool woken = false;
 	int page_size;
 	int entries, i;
 	ssize_t ret = 0;
@@ -8573,17 +8595,17 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 
 	/* 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)
 			goto out;
@@ -8592,10 +8614,8 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		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;
 	}
@@ -8618,9 +8638,8 @@ static long tracing_buffers_ioctl(struct file *file, unsigned int cmd, unsigned
 
 	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);