FAILED: patch "[PATCH] io_uring/io-wq: limit retrying worker initialisation" failed to apply to 5.15-stable tree

FAILED: patch "[PATCH] io_uring/io-wq: limit retrying worker initialisation" failed to apply to 5.15-stable tree

[gregkh]

The patch below does not apply to the 5.15-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@vger.kernel.org>.

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-5.15.y
git checkout FETCH_HEAD
git cherry-pick -x 0453aad676ff99787124b9b3af4a5f59fbe808e2
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable@vger.kernel.org>' --in-reply-to '2024072924-robin-manger-e92b@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^..

Possible dependencies:

0453aad676ff ("io_uring/io-wq: limit retrying worker initialisation")
8a565304927f ("io_uring/io-wq: Use set_bit() and test_bit() at worker->flags")
eb47943f2238 ("io-wq: Drop struct io_wqe")
dfd63baf892c ("io-wq: Move wq accounting to io_wq")
da64d6db3bd3 ("io_uring: One wqe per wq")
01e68ce08a30 ("io_uring/io-wq: stop setting PF_NO_SETAFFINITY on io-wq workers")
996d3efeb091 ("io-wq: Fix memory leak in worker creation")
024f15e033a5 ("io_uring: dedup io_run_task_work")
a6b21fbb4ce3 ("io_uring: move list helpers to a separate file")
ab1c84d855cf ("io_uring: make io_uring_types.h public")
48c13d898084 ("io_uring: explain io_wq_work::cancel_seq placement")
e418bbc97bff ("io_uring: move our reference counting into a header")
cd40cae29ef8 ("io_uring: split out open/close operations")
453b329be5ea ("io_uring: separate out file table handling code")
f4c163dd7d4b ("io_uring: split out fadvise/madvise operations")
0d5847274037 ("io_uring: split out fs related sync/fallocate functions")
531113bbd5bf ("io_uring: split out splice related operations")
11aeb71406dd ("io_uring: split out filesystem related operations")
e28683bdfc2f ("io_uring: move nop into its own file")
5e2a18d93fec ("io_uring: move xattr related opcodes to its own file")

thanks,

greg k-h

------------------ original commit in Linus's tree ------------------

From 0453aad676ff99787124b9b3af4a5f59fbe808e2 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Wed, 10 Jul 2024 18:58:17 +0100
Subject: [PATCH] io_uring/io-wq: limit retrying worker initialisation

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: 3146cba99aa28 ("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>

diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c
index 913c92249522..f1e7c670add8 100644
--- 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 */
@@ -58,6 +59,7 @@ struct io_worker {
 
 	unsigned long create_state;
 	struct callback_head create_work;
+	int init_retries;
 
 	union {
 		struct rcu_head rcu;
@@ -745,7 +747,7 @@ 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
@@ -753,6 +755,8 @@ 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:
@@ -779,7 +783,7 @@ 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);
@@ -846,7 +850,7 @@ static bool create_io_worker(struct io_wq *wq, int index)
 	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 {

Re: FAILED: patch "[PATCH] io_uring/io-wq: limit retrying worker initialisation" failed to apply to 5.15-stable tree

[Jens Axboe]

[-- Attachment #1: Type: text/plain, Size: 825 bytes --]

On 7/29/24 1:55 AM, gregkh@linuxfoundation.org wrote:
> 
> The patch below does not apply to the 5.15-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@vger.kernel.org>.
> 
> 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-5.15.y
> git checkout FETCH_HEAD
> git cherry-pick -x 0453aad676ff99787124b9b3af4a5f59fbe808e2
> # <resolve conflicts, build, test, etc.>
> git commit -s
> git send-email --to '<stable@vger.kernel.org>' --in-reply-to '2024072924-robin-manger-e92b@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^..

Here's the 5.10 and 5.15-stable variant of this.

-- 
Jens Axboe


[-- Attachment #2: 0002-io_uring-io-wq-limit-retrying-worker-initialisation.patch --]
[-- Type: text/x-patch, Size: 2997 bytes --]

From e2aa81d4fc08889e47250315fbdb0db1365a849d Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Wed, 10 Jul 2024 18:58:17 +0100
Subject: [PATCH 2/2] 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@vger.kernel.org
Fixes: 3146cba99aa28 ("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>
---
 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 fe8594a0396c..c5d249f5d214 100644
--- a/io_uring/io-wq.c
+++ b/io_uring/io-wq.c
@@ -19,6 +19,7 @@
 #include "io-wq.h"
 
 #define WORKER_IDLE_TIMEOUT	(5 * HZ)
+#define WORKER_INIT_LIMIT	3
 
 enum {
 	IO_WORKER_F_UP		= 1,	/* up and active */
@@ -54,6 +55,7 @@ struct io_worker {
 	unsigned long create_state;
 	struct callback_head create_work;
 	int create_index;
+	int init_retries;
 
 	union {
 		struct rcu_head rcu;
@@ -732,7 +734,7 @@ 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
@@ -740,6 +742,8 @@ 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:
@@ -766,7 +770,7 @@ 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);
@@ -831,7 +835,7 @@ 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 {
-- 
2.43.0

Re: FAILED: patch "[PATCH] io_uring/io-wq: limit retrying worker initialisation" failed to apply to 5.15-stable tree

[Greg KH]

On Mon, Jul 29, 2024 at 12:02:14PM -0600, Jens Axboe wrote:
> On 7/29/24 1:55 AM, gregkh@linuxfoundation.org wrote:
> > 
> > The patch below does not apply to the 5.15-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@vger.kernel.org>.
> > 
> > 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-5.15.y
> > git checkout FETCH_HEAD
> > git cherry-pick -x 0453aad676ff99787124b9b3af4a5f59fbe808e2
> > # <resolve conflicts, build, test, etc.>
> > git commit -s
> > git send-email --to '<stable@vger.kernel.org>' --in-reply-to '2024072924-robin-manger-e92b@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^..
> 
> Here's the 5.10 and 5.15-stable variant of this.
> 

Now queued up,t hanks.

greg k-h