This is a note to let you know that I've just added the patch titled ceph: put the requests/sessions when it fails to alloc memory to the 5.16-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary The filename of the patch is: ceph-put-the-requests-sessions-when-it-fails-to-allo.patch and it can be found in the queue-5.16 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable@xxxxxxxxxxxxxxx> know about it. commit bf4089cf9195d6ba4e37a8b739ead4b8c2f60d07 Author: Xiubo Li <xiubli@xxxxxxxxxx> Date: Wed Jan 12 12:29:04 2022 +0800 ceph: put the requests/sessions when it fails to alloc memory [ Upstream commit 89d43d0551a848e70e63d9ba11534aaeabc82443 ] When failing to allocate the sessions memory we should make sure the req1 and req2 and the sessions get put. And also in case the max_sessions decreased so when kreallocate the new memory some sessions maybe missed being put. And if the max_sessions is 0 krealloc will return ZERO_SIZE_PTR, which will lead to a distinct access fault. URL: https://tracker.ceph.com/issues/53819 Fixes: e1a4541ec0b9 ("ceph: flush the mdlog before waiting on unsafe reqs") Signed-off-by: Xiubo Li <xiubli@xxxxxxxxxx> Reviewed-by: Venky Shankar <vshankar@xxxxxxxxxx> Reviewed-by: Jeff Layton <jlayton@xxxxxxxxxx> Signed-off-by: Ilya Dryomov <idryomov@xxxxxxxxx> Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx> diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index c447fa2e2d1fe..2f8696f3b925d 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2218,6 +2218,7 @@ static int unsafe_request_wait(struct inode *inode) struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc; struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_mds_request *req1 = NULL, *req2 = NULL; + unsigned int max_sessions; int ret, err = 0; spin_lock(&ci->i_unsafe_lock); @@ -2235,37 +2236,45 @@ static int unsafe_request_wait(struct inode *inode) } spin_unlock(&ci->i_unsafe_lock); + /* + * The mdsc->max_sessions is unlikely to be changed + * mostly, here we will retry it by reallocating the + * sessions array memory to get rid of the mdsc->mutex + * lock. + */ +retry: + max_sessions = mdsc->max_sessions; + /* * Trigger to flush the journal logs in all the relevant MDSes * manually, or in the worst case we must wait at most 5 seconds * to wait the journal logs to be flushed by the MDSes periodically. */ - if (req1 || req2) { + if ((req1 || req2) && likely(max_sessions)) { struct ceph_mds_session **sessions = NULL; struct ceph_mds_session *s; struct ceph_mds_request *req; - unsigned int max; int i; - /* - * The mdsc->max_sessions is unlikely to be changed - * mostly, here we will retry it by reallocating the - * sessions arrary memory to get rid of the mdsc->mutex - * lock. - */ -retry: - max = mdsc->max_sessions; - sessions = krealloc(sessions, max * sizeof(s), __GFP_ZERO); - if (!sessions) - return -ENOMEM; + sessions = kzalloc(max_sessions * sizeof(s), GFP_KERNEL); + if (!sessions) { + err = -ENOMEM; + goto out; + } spin_lock(&ci->i_unsafe_lock); if (req1) { list_for_each_entry(req, &ci->i_unsafe_dirops, r_unsafe_dir_item) { s = req->r_session; - if (unlikely(s->s_mds >= max)) { + if (unlikely(s->s_mds >= max_sessions)) { spin_unlock(&ci->i_unsafe_lock); + for (i = 0; i < max_sessions; i++) { + s = sessions[i]; + if (s) + ceph_put_mds_session(s); + } + kfree(sessions); goto retry; } if (!sessions[s->s_mds]) { @@ -2278,8 +2287,14 @@ static int unsafe_request_wait(struct inode *inode) list_for_each_entry(req, &ci->i_unsafe_iops, r_unsafe_target_item) { s = req->r_session; - if (unlikely(s->s_mds >= max)) { + if (unlikely(s->s_mds >= max_sessions)) { spin_unlock(&ci->i_unsafe_lock); + for (i = 0; i < max_sessions; i++) { + s = sessions[i]; + if (s) + ceph_put_mds_session(s); + } + kfree(sessions); goto retry; } if (!sessions[s->s_mds]) { @@ -2300,7 +2315,7 @@ static int unsafe_request_wait(struct inode *inode) spin_unlock(&ci->i_ceph_lock); /* send flush mdlog request to MDSes */ - for (i = 0; i < max; i++) { + for (i = 0; i < max_sessions; i++) { s = sessions[i]; if (s) { send_flush_mdlog(s); @@ -2317,15 +2332,19 @@ static int unsafe_request_wait(struct inode *inode) ceph_timeout_jiffies(req1->r_timeout)); if (ret) err = -EIO; - ceph_mdsc_put_request(req1); } if (req2) { ret = !wait_for_completion_timeout(&req2->r_safe_completion, ceph_timeout_jiffies(req2->r_timeout)); if (ret) err = -EIO; - ceph_mdsc_put_request(req2); } + +out: + if (req1) + ceph_mdsc_put_request(req1); + if (req2) + ceph_mdsc_put_request(req2); return err; }