[for-linus][PATCH 2/3] ring-buffer: Fix resetting of shortest_full

[Steven Rostedt]

From: "Steven Rostedt (Google)" <rostedt@xxxxxxxxxxx>

The "shortest_full" variable is used to keep track of the waiter that is
waiting for the smallest amount on the ring buffer before being woken up.
When a tasks waits on the ring buffer, it passes in a "full" value that is
a percentage. 0 means wake up on any data. 1-100 means wake up from 1% to
100% full buffer.

As all waiters are on the same wait queue, the wake up happens for the
waiter with the smallest percentage.

The problem is that the smallest_full on the cpu_buffer that stores the
smallest amount doesn't get reset when all the waiters are woken up. It
does get reset when the ring buffer is reset (echo > /sys/kernel/tracing/trace).

This means that tasks may be woken up more often then when they want to
be. Instead, have the shortest_full field get reset just before waking up
all the tasks. If the tasks wait again, they will update the shortest_full
before sleeping.

Also add locking around setting of shortest_full in the poll logic, and
change "work" to "rbwork" to match the variable name for rb_irq_work
structures that are used in other places.

Link: https://lore.kernel.org/linux-trace-kernel/20240308202431.948914369@xxxxxxxxxxx

Cc: stable@xxxxxxxxxxxxxxx
Cc: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Cc: Mark Rutland <mark.rutland@xxxxxxx>
Cc: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: linke li <lilinke99@xxxxxx>
Cc: Rabin Vincent <rabin@xxxxxx>
Fixes: 2c2b0a78b3739 ("ring-buffer: Add percentage of ring buffer full to wake up reader")
Signed-off-by: Steven Rostedt (Google) <rostedt@xxxxxxxxxxx>
---
 kernel/trace/ring_buffer.c | 30 +++++++++++++++++++++++-------
 1 file changed, 23 insertions(+), 7 deletions(-)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 3400f11286e3..aa332ace108b 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -755,8 +755,19 @@ static void rb_wake_up_waiters(struct irq_work *work)
 
 	wake_up_all(&rbwork->waiters);
 	if (rbwork->full_waiters_pending || rbwork->wakeup_full) {
+		/* Only cpu_buffer sets the above flags */
+		struct ring_buffer_per_cpu *cpu_buffer =
+			container_of(rbwork, struct ring_buffer_per_cpu, irq_work);
+
+		/* Called from interrupt context */
+		raw_spin_lock(&cpu_buffer->reader_lock);
 		rbwork->wakeup_full = false;
 		rbwork->full_waiters_pending = false;
+
+		/* Waking up all waiters, they will reset the shortest full */
+		cpu_buffer->shortest_full = 0;
+		raw_spin_unlock(&cpu_buffer->reader_lock);
+
 		wake_up_all(&rbwork->full_waiters);
 	}
 }
@@ -934,28 +945,33 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu,
 			  struct file *filp, poll_table *poll_table, int full)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
-	struct rb_irq_work *work;
+	struct rb_irq_work *rbwork;
 
 	if (cpu == RING_BUFFER_ALL_CPUS) {
-		work = &buffer->irq_work;
+		rbwork = &buffer->irq_work;
 		full = 0;
 	} else {
 		if (!cpumask_test_cpu(cpu, buffer->cpumask))
 			return EPOLLERR;
 
 		cpu_buffer = buffer->buffers[cpu];
-		work = &cpu_buffer->irq_work;
+		rbwork = &cpu_buffer->irq_work;
 	}
 
 	if (full) {
-		poll_wait(filp, &work->full_waiters, poll_table);
-		work->full_waiters_pending = true;
+		unsigned long flags;
+
+		poll_wait(filp, &rbwork->full_waiters, poll_table);
+
+		raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+		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, &work->waiters, poll_table);
-		work->waiters_pending = true;
+		poll_wait(filp, &rbwork->waiters, poll_table);
+		rbwork->waiters_pending = true;
 	}
 
 	/*
-- 
2.43.0