io_uring/io-wq: limit retrying worker initialisation
commit0453aad676
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@vger.kernel.org Fixes:3146cba99a
("io-wq: make worker creation resilient against signals") Reported-by: Julian Orth <ju.orth@gmail.com> Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Link: https://lore.kernel.org/r/8280436925db88448c7c85c6656edee1a43029ea.1720634146.git.asml.silence@gmail.com Signed-off-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This commit is contained in:
parent
e71327a647
commit
fc7c4b8ec9
1 changed files with 7 additions and 3 deletions
|
@ -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 */
|
||||
|
@ -58,6 +59,7 @@ struct io_worker {
|
|||
|
||||
unsigned long create_state;
|
||||
struct callback_head create_work;
|
||||
int init_retries;
|
||||
|
||||
union {
|
||||
struct rcu_head rcu;
|
||||
|
@ -744,7 +746,7 @@ 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
|
||||
|
@ -752,6 +754,8 @@ 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:
|
||||
|
@ -778,7 +782,7 @@ static void create_worker_cont(struct callback_head *cb)
|
|||
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);
|
||||
|
@ -845,7 +849,7 @@ 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 {
|
||||
|
|
Loading…
Reference in a new issue