locks: protect most of the file_lock handling with i_lock

Having a global lock that protects all of this code is a clear
scalability problem. Instead of doing that, move most of the code to be
protected by the i_lock instead. The exceptions are the global lists
that the ->fl_link sits on, and the ->fl_block list.

->fl_link is what connects these structures to the
global lists, so we must ensure that we hold those locks when iterating
over or updating these lists.

Furthermore, sound deadlock detection requires that we hold the
blocked_list state steady while checking for loops. We also must ensure
that the search and update to the list are atomic.

For the checking and insertion side of the blocked_list, push the
acquisition of the global lock into __posix_lock_file and ensure that
checking and update of the  blocked_list is done without dropping the
lock in between.

On the removal side, when waking up blocked lock waiters, take the
global lock before walking the blocked list and dequeue the waiters from
the global list prior to removal from the fl_block list.

With this, deadlock detection should be race free while we minimize
excessive file_lock_lock thrashing.

Finally, in order to avoid a lock inversion problem when handling
/proc/locks output we must ensure that manipulations of the fl_block
list are also protected by the file_lock_lock.

Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

2 files changed, 9 insertions, 9 deletions

diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 57db3244f4d..7ec4814e298 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -73,20 +73,20 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_
 	if (inode->i_flock == NULL)
 		goto out;
 
-	/* Protect inode->i_flock using the file locks lock */
-	lock_flocks();
+	/* Protect inode->i_flock using the i_lock */
+	spin_lock(&inode->i_lock);
 	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
 		if (!(fl->fl_flags & (FL_POSIX|FL_FLOCK)))
 			continue;
 		if (nfs_file_open_context(fl->fl_file) != ctx)
 			continue;
-		unlock_flocks();
+		spin_unlock(&inode->i_lock);
 		status = nfs4_lock_delegation_recall(fl, state, stateid);
 		if (status < 0)
 			goto out;
-		lock_flocks();
+		spin_lock(&inode->i_lock);
 	}
-	unlock_flocks();
+	spin_unlock(&inode->i_lock);
 out:
 	return status;
 }
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 1fab140764c..ff10b4aa534 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1373,13 +1373,13 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_
 	/* Guard against delegation returns and new lock/unlock calls */
 	down_write(&nfsi->rwsem);
 	/* Protect inode->i_flock using the BKL */
-	lock_flocks();
+	spin_lock(&inode->i_lock);
 	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
 		if (!(fl->fl_flags & (FL_POSIX|FL_FLOCK)))
 			continue;
 		if (nfs_file_open_context(fl->fl_file)->state != state)
 			continue;
-		unlock_flocks();
+		spin_unlock(&inode->i_lock);
 		status = ops->recover_lock(state, fl);
 		switch (status) {
 			case 0:
@@ -1406,9 +1406,9 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_
 				/* kill_proc(fl->fl_pid, SIGLOST, 1); */
 				status = 0;
 		}
-		lock_flocks();
+		spin_lock(&inode->i_lock);
 	}
-	unlock_flocks();
+	spin_unlock(&inode->i_lock);
 out:
 	up_write(&nfsi->rwsem);
 	return status;