On 10/11/2022 21:48, Ilya Dryomov wrote:

On Thu, Nov 10, 2022 at 2:02 PM xiubli@redhat.com wrote:

...

From: Xiubo Li xiubli@redhat.com

The request's r_session maybe changed when it was forwarded or resent. Both the forwarding and resending cases the requests will be protected by the mdsc->mutex.

Cc: stable@vger.kernel.org URL: https://bugzilla.redhat.com/show_bug.cgi?id=2137955 Signed-off-by: Xiubo Li xiubli@redhat.com

---

Changed in V5:

• simplify the code by removing the "unlikely(s->s_mds >= max_sessions)" check.

Changed in V4:

• move mdsc->mutex acquisition and max_sessions assignment into "if (req1 || req2)" branch

  fs/ceph/caps.c | 48 ++++++++++++------------------------------------ 1 file changed, 12 insertions(+), 36 deletions(-)

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 894adfb4a092..065e9311b607 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2297,7 +2297,6 @@ static int flush_mdlog_and_wait_inode_unsafe_requests(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);
  

@@ -2315,28 +2314,24 @@ static int flush_mdlog_and_wait_inode_unsafe_requests(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) && likely(max_sessions)) {
  

•           struct ceph_mds_session **sessions = NULL;
  

•           struct ceph_mds_session *s;
  

•   if (req1 || req2) {
             struct ceph_mds_request *req;
  

•           struct ceph_mds_session **sessions;
  

•           struct ceph_mds_session *s;
  

•           unsigned int max_sessions;
             int i;
  
  

•           mutex_lock(&mdsc->mutex);
  

•           max_sessions = mdsc->max_sessions;
  

•            sessions = kcalloc(max_sessions, sizeof(s), GFP_KERNEL);
             if (!sessions) {
  

•                   mutex_unlock(&mdsc->mutex);
                     err = -ENOMEM;
                     goto out;
             }
  

@@ -2348,16 +2343,6 @@ static int flush_mdlog_and_wait_inode_unsafe_requests(struct inode *inode) s = req->r_session; if (!s) continue;

•                           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]) {
                                     s = ceph_get_mds_session(s);
                                     sessions[s->s_mds] = s;
  

@@ -2370,16 +2355,6 @@ static int flush_mdlog_and_wait_inode_unsafe_requests(struct inode *inode) s = req->r_session; if (!s) continue;

•                           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]) {
                                     s = ceph_get_mds_session(s);
                                     sessions[s->s_mds] = s;
  

@@ -2391,11 +2366,12 @@ static int flush_mdlog_and_wait_inode_unsafe_requests(struct inode *inode) /* the auth MDS */ spin_lock(&ci->i_ceph_lock); if (ci->i_auth_cap) {

•                 s = ci->i_auth_cap->session;
  

•                 if (!sessions[s->s_mds])
  

•                         sessions[s->s_mds] = ceph_get_mds_session(s);
  

•                   s = ci->i_auth_cap->session;
  

•                   if (!sessions[s->s_mds])
  

•                           sessions[s->s_mds] = ceph_get_mds_session(s);
             }
             spin_unlock(&ci->i_ceph_lock);
  

•           mutex_unlock(&mdsc->mutex);
  
             /* send flush mdlog request to MDSes */
             for (i = 0; i < max_sessions; i++) {
  

-- 2.31.1

Reviewed-by: Ilya Dryomov idryomov@gmail.com

Thanks Ilya!

- Xiubo

Thanks,

             Ilya