6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Pavel Begunkov <asml.silence@xxxxxxxxx>
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>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
io_uring/io-wq.c | 10 +++++++---
1 file changed, 7 insertions(+), 3 deletions(-)
--- a/io_uring/io-wq.c
+++ b/io_uring/io-wq.c
@@ -23,6 +23,7 @@
#include "io_uring.h"
#define WORKER_IDLE_TIMEOUT (5 * HZ)
+#define WORKER_INIT_LIMIT 3
enum {
IO_WORKER_F_UP = 0, /* up and active */
@@ -59,6 +60,7 @@ struct io_worker {
unsigned long create_state;
struct callback_head create_work;
+ int init_retries;
union {
struct rcu_head rcu;
@@ -746,7 +748,7 @@ static bool io_wq_work_match_all(struct
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
@@ -754,6 +756,8 @@ static inline bool io_should_retry_threa
*/
if (fatal_signal_pending(current))
return false;
+ if (worker->init_retries++ >= WORKER_INIT_LIMIT)
+ return false;
switch (err) {
case -EAGAIN:
@@ -780,7 +784,7 @@ static void create_worker_cont(struct ca
io_init_new_worker(wq, 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_wq_acct *acct = io_wq_get_acct(worker);
atomic_dec(&acct->nr_running);
@@ -847,7 +851,7 @@ fail:
tsk = create_io_thread(io_wq_worker, worker, NUMA_NO_NODE);
if (!IS_ERR(tsk)) {
io_init_new_worker(wq, 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 {
