1 files changed, 48 insertions, 29 deletions

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index b9460b6fb76f..b472cd066d1c 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1856,7 +1856,7 @@ static int try_nonblocking_invalidate(struct inode *inode)
 	u32 invalidating_gen = ci->i_rdcache_gen;
 
 	spin_unlock(&ci->i_ceph_lock);
-	ceph_fscache_invalidate(inode);
+	ceph_fscache_invalidate(inode, false);
 	invalidate_mapping_pages(&inode->i_data, 0, -1);
 	spin_lock(&ci->i_ceph_lock);
 
@@ -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);
@@ -2236,36 +2237,44 @@ 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 @@ retry:
 			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 @@ retry:
 		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 @@ retry:
 					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;
 }
 
@@ -2388,6 +2407,7 @@ int ceph_write_inode(struct inode *inode, struct writeback_control *wbc)
 	int wait = (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync);
 
 	dout("write_inode %p wait=%d\n", inode, wait);
+	ceph_fscache_unpin_writeback(inode, wbc);
 	if (wait) {
 		dirty = try_flush_caps(inode, &flush_tid);
 		if (dirty)
@@ -3375,8 +3395,7 @@ static void handle_cap_grant(struct inode *inode,
 	if ((newcaps & CEPH_CAP_LINK_SHARED) &&
 	    (extra_info->issued & CEPH_CAP_LINK_EXCL) == 0) {
 		set_nlink(inode, le32_to_cpu(grant->nlink));
-		if (inode->i_nlink == 0 &&
-		    (newcaps & (CEPH_CAP_LINK_SHARED | CEPH_CAP_LINK_EXCL)))
+		if (inode->i_nlink == 0)
 			deleted_inode = true;
 	}
 
@@ -4350,7 +4369,7 @@ void ceph_get_fmode(struct ceph_inode_info *ci, int fmode, int count)
 {
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(ci->vfs_inode.i_sb);
 	int bits = (fmode << 1) | 1;
-	bool is_opened = false;
+	bool already_opened = false;
 	int i;
 
 	if (count == 1)
@@ -4358,19 +4377,19 @@ void ceph_get_fmode(struct ceph_inode_info *ci, int fmode, int count)
 
 	spin_lock(&ci->i_ceph_lock);
 	for (i = 0; i < CEPH_FILE_MODE_BITS; i++) {
-		if (bits & (1 << i))
-			ci->i_nr_by_mode[i] += count;
-
 		/*
-		 * If any of the mode ref is larger than 1,
+		 * If any of the mode ref is larger than 0,
 		 * that means it has been already opened by
 		 * others. Just skip checking the PIN ref.
 		 */
-		if (i && ci->i_nr_by_mode[i] > 1)
-			is_opened = true;
+		if (i && ci->i_nr_by_mode[i])
+			already_opened = true;
+
+		if (bits & (1 << i))
+			ci->i_nr_by_mode[i] += count;
 	}
 
-	if (!is_opened)
+	if (!already_opened)
 		percpu_counter_inc(&mdsc->metric.opened_inodes);
 	spin_unlock(&ci->i_ceph_lock);
 }