On 7/29/24 1:55 AM, gregkh@xxxxxxxxxxxxxxxxxxx wrote:
>
> The patch below does not apply to the 6.1-stable tree.
> If someone wants it applied there, or to any other stable or longterm
> tree, then please email the backport, including the original git commit
> id to <stable@xxxxxxxxxxxxxxx>.
>
> To reproduce the conflict and resubmit, you may use the following commands:
>
> git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y
> git checkout FETCH_HEAD
> git cherry-pick -x 0453aad676ff99787124b9b3af4a5f59fbe808e2
> # <resolve conflicts, build, test, etc.>
> git commit -s
> git send-email --to '<stable@xxxxxxxxxxxxxxx>' --in-reply-to '2024072923-bodacious-claw-442b@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^..
Here's a 6.1 variant.
--
Jens Axboe
From 0453aad676ff99787124b9b3af4a5f59fbe808e2 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@xxxxxxxxx>
Date: Wed, 10 Jul 2024 18:58:17 +0100
Subject: [PATCH] io_uring/io-wq: limit retrying worker initialisation
commit 0453aad676ff99787124b9b3af4a5f59fbe808e2 upstream.
If io-wq worker creation fails, we retry it by queueing up a task_work.
tasK_work is needed because it should be done from the user process
context. The problem is that retries are not limited, and if queueing a
task_work is the reason for the failure, we might get into an infinite
loop.
It doesn't seem to happen now but it would with the following patch
executing task_work in the freezer's loop. For now, arbitrarily limit the
number of attempts to create a worker.
Cc: stable@xxxxxxxxxxxxxxx
Fixes: 3146cba99aa28 ("io-wq: make worker creation resilient against signals")
Reported-by: Julian Orth <ju.orth@xxxxxxxxx>
Signed-off-by: Pavel Begunkov <asml.silence@xxxxxxxxx>
Link: https://lore.kernel.org/r/8280436925db88448c7c85c6656edee1a43029ea.1720634146.git.asml.silence@xxxxxxxxx
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
---
io_uring/io-wq.c | 10 +++++++---
1 file changed, 7 insertions(+), 3 deletions(-)
diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c
index 98ac9dbcec2f..04503118cdc1 100644
--- a/io_uring/io-wq.c
+++ b/io_uring/io-wq.c
@@ -22,6 +22,7 @@
#include "io_uring.h"
#define WORKER_IDLE_TIMEOUT (5 * HZ)
+#define WORKER_INIT_LIMIT 3
enum {
IO_WORKER_F_UP = 1, /* up and active */
@@ -58,6 +59,7 @@ struct io_worker {
unsigned long create_state;
struct callback_head create_work;
int create_index;
+ int init_retries;
union {
struct rcu_head rcu;
@@ -729,7 +731,7 @@ static bool io_wq_work_match_all(struct io_wq_work *work, void *data)
return true;
}
-static inline bool io_should_retry_thread(long err)
+static inline bool io_should_retry_thread(struct io_worker *worker, long err)
{
/*
* Prevent perpetual task_work retry, if the task (or its group) is
@@ -737,6 +739,8 @@ static inline bool io_should_retry_thread(long err)
*/
if (fatal_signal_pending(current))
return false;
+ if (worker->init_retries++ >= WORKER_INIT_LIMIT)
+ return false;
switch (err) {
case -EAGAIN:
@@ -763,7 +767,7 @@ static void create_worker_cont(struct callback_head *cb)
io_init_new_worker(wqe, worker, tsk);
io_worker_release(worker);
return;
- } else if (!io_should_retry_thread(PTR_ERR(tsk))) {
+ } else if (!io_should_retry_thread(worker, PTR_ERR(tsk))) {
struct io_wqe_acct *acct = io_wqe_get_acct(worker);
atomic_dec(&acct->nr_running);
@@ -830,7 +834,7 @@ static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index)
tsk = create_io_thread(io_wqe_worker, worker, wqe->node);
if (!IS_ERR(tsk)) {
io_init_new_worker(wqe, worker, tsk);
- } else if (!io_should_retry_thread(PTR_ERR(tsk))) {
+ } else if (!io_should_retry_thread(worker, PTR_ERR(tsk))) {
kfree(worker);
goto fail;
} else {
