Skip to contentSkip to conversation

ceph: fix NULL pointer dereference for req->r_session

PATCH Superseded [email protected] 2 participants 3 messages Nov 10, 2022

Subsystems (2)

v4 of 5 Superseded Latest is v5 →

lore
Share & tools
lore
#0 lore raw

PATCH v4 1/1 ceph: fix NULL pointer dereference for req->r_session

From: Xiubo Li <[email protected]>

The request's r_session maybe changed when it was forwarded or resent.

Cc: [email protected]
URL: https://bugzilla.redhat.com/show_bug.cgi?id=2137955

---

Changed in V4:
- move mdsc->mutex acquisition and max_sessions assignment into "if (req1 || req2)" branch

 fs/ceph/caps.c | 54 +++++++++++++++-----------------------------------
 1 file changed, 16 insertions(+), 38 deletions(-)
fs/ceph/caps.c +16 -38
index 894adfb4a092..1c84be839087 100644
@@ -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;
 		}
@@ -2346,18 +2341,8 @@ static int flush_mdlog_and_wait_inode_unsafe_requests(struct inode *inode)
 			list_for_each_entry(req, &ci->i_unsafe_dirops,
 					    r_unsafe_dir_item) {
 				s = req->r_session;
-				if (!s)
+				if (!s || unlikely(s->s_mds >= max_sessions))
 					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;
@@ -2368,18 +2353,8 @@ static int flush_mdlog_and_wait_inode_unsafe_requests(struct inode *inode)
 			list_for_each_entry(req, &ci->i_unsafe_iops,
 					    r_unsafe_target_item) {
 				s = req->r_session;
-				if (!s)
+				if (!s || unlikely(s->s_mds >= max_sessions))
 					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 +2366,14 @@ 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 (likely(s->s_mds < max_sessions) &&
+			    !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++) {
Signature · 1 line
2.31.1
maintainer
#1 lore raw
Quoted 67 lines · On Thu, Nov 10, 2022 at 3:08 AM <[email protected]> wrote:

From: Xiubo Li <[email protected]>

The request's r_session maybe changed when it was forwarded or resent.

Cc: [email protected]
URL: https://bugzilla.redhat.com/show_bug.cgi?id=2137955

---

Changed in V4:
- move mdsc->mutex acquisition and max_sessions assignment into "if (req1 || req2)" branch

 fs/ceph/caps.c | 54 +++++++++++++++-----------------------------------
 1 file changed, 16 insertions(+), 38 deletions(-)
fs/ceph/caps.c +8 -13
index 894adfb4a092..1c84be839087 100644
@@ -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;
                }

fs/ceph/caps.c static int flush_mdlog_and_wait_inode_unsafe_requests(struct inode *inode) · line 2344

Quoted 5 lines
fs/ceph/caps.c +1 -1
@@ -2346,18 +2341,8 @@ static int flush_mdlog_and_wait_inode_unsafe_requests(struct inode *inode)
                        list_for_each_entry(req, &ci->i_unsafe_dirops,
                                            r_unsafe_dir_item) {
                                s = req->r_session;
-                               if (!s)
+                               if (!s || unlikely(s->s_mds >= max_sessions))

Hi Xiubo,

I would be fine with this patch as is but I'm wondering if it can be simplified further. Now that mdsc->mutex is held while sessions array is populated, is checking s->s_mds against max_sessions actually needed? Is it possible for some req->r_session on one of the unsafe lists to have an "out of bounds" s_mds under mdsc->mutex?

Thanks,

Ilya

author
#2 lore raw
Quoted 74 lines · Ilya Dryomov
Quoted 66 lines · On Thu, Nov 10, 2022 at 3:08 AM <[email protected]> wrote:

From: Xiubo Li <[email protected]>

The request's r_session maybe changed when it was forwarded or resent.

Cc: [email protected]
URL: https://bugzilla.redhat.com/show_bug.cgi?id=2137955

---

Changed in V4:
- move mdsc->mutex acquisition and max_sessions assignment into "if (req1 || req2)" branch

  fs/ceph/caps.c | 54 +++++++++++++++-----------------------------------
  1 file changed, 16 insertions(+), 38 deletions(-)
fs/ceph/caps.c +8 -13
index 894adfb4a092..1c84be839087 100644
@@ -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;
                 }

fs/ceph/caps.c static int flush_mdlog_and_wait_inode_unsafe_requests(struct inode *inode) · line 2344

Quoted 5 lines
fs/ceph/caps.c +1 -1
@@ -2346,18 +2341,8 @@ static int flush_mdlog_and_wait_inode_unsafe_requests(struct inode *inode)
                         list_for_each_entry(req, &ci->i_unsafe_dirops,
                                             r_unsafe_dir_item) {
                                 s = req->r_session;
-                               if (!s)
+                               if (!s || unlikely(s->s_mds >= max_sessions))

Hi Xiubo,

Quoted 5 lines

I would be fine with this patch as is but I'm wondering if it can be simplified further. Now that mdsc->mutex is held while sessions array is populated, is checking s->s_mds against max_sessions actually needed? Is it possible for some req->r_session on one of the unsafe lists to have an "out of bounds" s_mds under mdsc->mutex?

Yeah, this can be simplified.

Let me do that.

Thanks!

- Xiubo

Quoted 5 lines

Thanks,

Ilya