Merge tag 'ceph-for-5.17-rc2' of git://github.com/ceph/ceph-client

Pull ceph fixes from Ilya Dryomov:
 "A ZERO_SIZE_PTR dereference fix from Xiubo and two fixes for async
  creates interacting with pool namespace-constrained OSD permissions
  from Jeff (marked for stable)"

* tag 'ceph-for-5.17-rc2' of git://github.com/ceph/ceph-client:
  ceph: set pool_ns in new inode layout for async creates
  ceph: properly put ceph_string reference after async create attempt
  ceph: put the requests/sessions when it fails to alloc memory

Author: torvalds

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;
 }
 

fs/ceph/file.c

@@ -583,6 +583,7 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry,
 	struct ceph_inode_info *ci = ceph_inode(dir);
 	struct inode *inode;
 	struct timespec64 now;
+	struct ceph_string *pool_ns;
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb);
 	struct ceph_vino vino = { .ino = req->r_deleg_ino,
 				  .snap = CEPH_NOSNAP };
@@ -632,6 +633,12 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry,
 	in.max_size = cpu_to_le64(lo->stripe_unit);
 
 	ceph_file_layout_to_legacy(lo, &in.layout);
+	/* lo is private, so pool_ns can't change */
+	pool_ns = rcu_dereference_raw(lo->pool_ns);
+	if (pool_ns) {
+		iinfo.pool_ns_len = pool_ns->len;
+		iinfo.pool_ns_data = pool_ns->str;
+	}
 
 	down_read(&mdsc->snap_rwsem);
 	ret = ceph_fill_inode(inode, NULL, &iinfo, NULL, req->r_session,
@@ -750,8 +757,10 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 				restore_deleg_ino(dir, req->r_deleg_ino);
 				ceph_mdsc_put_request(req);
 				try_async = false;
+				ceph_put_string(rcu_dereference_raw(lo.pool_ns));
 				goto retry;
 			}
+			ceph_put_string(rcu_dereference_raw(lo.pool_ns));
 			goto out_req;
 		}
 	}