Merge tag 'locks-v3.20-1' of git://git.samba.org/jlayton/linux

Pull file locking related changes #1 from Jeff Layton:
 "This patchset contains a fairly major overhaul of how file locks are
  tracked within the inode.  Rather than a single list, we now create a
  per-inode "lock context" that contains individual lists for the file
  locks, and a new dedicated spinlock for them.

  There are changes in other trees that are based on top of this set so
  it may be easiest to pull this in early"

* tag 'locks-v3.20-1' of git://git.samba.org/jlayton/linux:
  locks: update comments that refer to inode->i_flock
  locks: consolidate NULL i_flctx checks in locks_remove_file
  locks: keep a count of locks on the flctx lists
  locks: clean up the lm_change prototype
  locks: add a dedicated spinlock to protect i_flctx lists
  locks: remove i_flock field from struct inode
  locks: convert lease handling to file_lock_context
  locks: convert posix locks to file_lock_context
  locks: move flock locks to file_lock_context
  ceph: move spinlocking into ceph_encode_locks_to_buffer and ceph_count_locks
  locks: add a new struct file_locking_context pointer to struct inode
  locks: have locks_release_file use flock_lock_file to release generic flock locks
  locks: add new struct list_head to struct file_lock

fs/ceph/locks.c

@@ -239,23 +239,21 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
 	return err;
 }
 
-/**
- * Must be called with lock_flocks() already held. Fills in the passed
- * counter variables, so you can prepare pagelist metadata before calling
- * ceph_encode_locks.
+/*
+ * Fills in the passed counter variables, so you can prepare pagelist metadata
+ * before calling ceph_encode_locks.
  */
 void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count)
 {
-	struct file_lock *lock;
+	struct file_lock_context *ctx;
 
 	*fcntl_count = 0;
 	*flock_count = 0;
 
-	for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
-		if (lock->fl_flags & FL_POSIX)
-			++(*fcntl_count);
-		else if (lock->fl_flags & FL_FLOCK)
-			++(*flock_count);
+	ctx = inode->i_flctx;
+	if (ctx) {
+		*fcntl_count = ctx->flc_posix_cnt;
+		*flock_count = ctx->flc_flock_cnt;
 	}
 	dout("counted %d flock locks and %d fcntl locks",
 	     *flock_count, *fcntl_count);
@@ -271,6 +269,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode,
 				int num_fcntl_locks, int num_flock_locks)
 {
 	struct file_lock *lock;
+	struct file_lock_context *ctx = inode->i_flctx;
 	int err = 0;
 	int seen_fcntl = 0;
 	int seen_flock = 0;
@@ -279,8 +278,11 @@ int ceph_encode_locks_to_buffer(struct inode *inode,
 	dout("encoding %d flock and %d fcntl locks", num_flock_locks,
 	     num_fcntl_locks);
 
-	for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
-		if (lock->fl_flags & FL_POSIX) {
+	if (!ctx)
+		return 0;
+
+	spin_lock(&ctx->flc_lock);
+	list_for_each_entry(lock, &ctx->flc_flock, fl_list) {
 		++seen_fcntl;
 		if (seen_fcntl > num_fcntl_locks) {
 			err = -ENOSPC;
@@ -291,9 +293,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode,
 			goto fail;
 		++l;
 	}
-	}
-	for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
-		if (lock->fl_flags & FL_FLOCK) {
+	list_for_each_entry(lock, &ctx->flc_flock, fl_list) {
 		++seen_flock;
 		if (seen_flock > num_flock_locks) {
 			err = -ENOSPC;
@@ -304,8 +304,8 @@ int ceph_encode_locks_to_buffer(struct inode *inode,
 			goto fail;
 		++l;
 	}
-	}
 fail:
+	spin_unlock(&ctx->flc_lock);
 	return err;
 }
 

fs/ceph/mds_client.c

@@ -2700,20 +2700,16 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap,
 		struct ceph_filelock *flocks;
 
 encode_again:
-		spin_lock(&inode->i_lock);
 		ceph_count_locks(inode, &num_fcntl_locks, &num_flock_locks);
-		spin_unlock(&inode->i_lock);
 		flocks = kmalloc((num_fcntl_locks+num_flock_locks) *
 				 sizeof(struct ceph_filelock), GFP_NOFS);
 		if (!flocks) {
 			err = -ENOMEM;
 			goto out_free;
 		}
-		spin_lock(&inode->i_lock);
 		err = ceph_encode_locks_to_buffer(inode, flocks,
 						  num_fcntl_locks,
 						  num_flock_locks);
-		spin_unlock(&inode->i_lock);
 		if (err) {
 			kfree(flocks);
 			if (err == -ENOSPC)

fs/cifs/file.c

@@ -1113,11 +1113,6 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile)
 	return rc;
 }
 
-/* copied from fs/locks.c with a name change */
-#define cifs_for_each_lock(inode, lockp) \
-	for (lockp = &inode->i_flock; *lockp != NULL; \
-	     lockp = &(*lockp)->fl_next)
-
 struct lock_to_push {
 	struct list_head llist;
 	__u64 offset;
@@ -1132,8 +1127,9 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
 {
 	struct inode *inode = cfile->dentry->d_inode;
 	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
-	struct file_lock *flock, **before;
-	unsigned int count = 0, i = 0;
+	struct file_lock *flock;
+	struct file_lock_context *flctx = inode->i_flctx;
+	unsigned int i;
 	int rc = 0, xid, type;
 	struct list_head locks_to_send, *el;
 	struct lock_to_push *lck, *tmp;
@@ -1141,21 +1137,17 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
 
 	xid = get_xid();
 
-	spin_lock(&inode->i_lock);
-	cifs_for_each_lock(inode, before) {
-		if ((*before)->fl_flags & FL_POSIX)
-			count++;
-	}
-	spin_unlock(&inode->i_lock);
+	if (!flctx)
+		goto out;
 
 	INIT_LIST_HEAD(&locks_to_send);
 
 	/*
-	 * Allocating count locks is enough because no FL_POSIX locks can be
-	 * added to the list while we are holding cinode->lock_sem that
+	 * Allocating flc_posix_cnt locks is enough because no FL_POSIX locks
+	 * can be added to the list while we are holding cinode->lock_sem that
 	 * protects locking operations of this inode.
 	 */
-	for (; i < count; i++) {
+	for (i = 0; i < flctx->flc_posix_cnt; i++) {
 		lck = kmalloc(sizeof(struct lock_to_push), GFP_KERNEL);
 		if (!lck) {
 			rc = -ENOMEM;
@@ -1165,11 +1157,8 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
 	}
 
 	el = locks_to_send.next;
-	spin_lock(&inode->i_lock);
-	cifs_for_each_lock(inode, before) {
-		flock = *before;
-		if ((flock->fl_flags & FL_POSIX) == 0)
-			continue;
+	spin_lock(&flctx->flc_lock);
+	list_for_each_entry(flock, &flctx->flc_posix, fl_list) {
 		if (el == &locks_to_send) {
 			/*
 			 * The list ended. We don't have enough allocated
@@ -1189,9 +1178,8 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
 		lck->length = length;
 		lck->type = type;
 		lck->offset = flock->fl_start;
-		el = el->next;
 	}
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&flctx->flc_lock);
 
 	list_for_each_entry_safe(lck, tmp, &locks_to_send, llist) {
 		int stored_rc;

fs/inode.c

@@ -194,7 +194,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 #ifdef CONFIG_FSNOTIFY
 	inode->i_fsnotify_mask = 0;
 #endif
-
+	inode->i_flctx = NULL;
 	this_cpu_inc(nr_inodes);
 
 	return 0;
@@ -237,6 +237,7 @@ void __destroy_inode(struct inode *inode)
 	BUG_ON(inode_has_buffers(inode));
 	security_inode_free(inode);
 	fsnotify_inode_delete(inode);
+	locks_free_lock_context(inode->i_flctx);
 	if (!inode->i_nlink) {
 		WARN_ON(atomic_long_read(&inode->i_sb->s_remove_count) == 0);
 		atomic_long_dec(&inode->i_sb->s_remove_count);

fs/lockd/svcsubs.c

@@ -164,12 +164,15 @@ nlm_traverse_locks(struct nlm_host *host, struct nlm_file *file,
 {
 	struct inode	 *inode = nlmsvc_file_inode(file);
 	struct file_lock *fl;
+	struct file_lock_context *flctx = inode->i_flctx;
 	struct nlm_host	 *lockhost;
 
+	if (!flctx || list_empty_careful(&flctx->flc_posix))
+		return 0;
 again:
 	file->f_locks = 0;
-	spin_lock(&inode->i_lock);
-	for (fl = inode->i_flock; fl; fl = fl->fl_next) {
+	spin_lock(&flctx->flc_lock);
+	list_for_each_entry(fl, &flctx->flc_posix, fl_list) {
 		if (fl->fl_lmops != &nlmsvc_lock_operations)
 			continue;
 
@@ -180,7 +183,7 @@ nlm_traverse_locks(struct nlm_host *host, struct nlm_file *file,
 		if (match(lockhost, host)) {
 			struct file_lock lock = *fl;
 
-			spin_unlock(&inode->i_lock);
+			spin_unlock(&flctx->flc_lock);
 			lock.fl_type  = F_UNLCK;
 			lock.fl_start = 0;
 			lock.fl_end   = OFFSET_MAX;
@@ -192,7 +195,7 @@ nlm_traverse_locks(struct nlm_host *host, struct nlm_file *file,
 			goto again;
 		}
 	}
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&flctx->flc_lock);
 
 	return 0;
 }
@@ -223,18 +226,21 @@ nlm_file_inuse(struct nlm_file *file)
 {
 	struct inode	 *inode = nlmsvc_file_inode(file);
 	struct file_lock *fl;
+	struct file_lock_context *flctx = inode->i_flctx;
 
 	if (file->f_count || !list_empty(&file->f_blocks) || file->f_shares)
 		return 1;
 
-	spin_lock(&inode->i_lock);
-	for (fl = inode->i_flock; fl; fl = fl->fl_next) {
+	if (flctx && !list_empty_careful(&flctx->flc_posix)) {
+		spin_lock(&flctx->flc_lock);
+		list_for_each_entry(fl, &flctx->flc_posix, fl_list) {
 			if (fl->fl_lmops == &nlmsvc_lock_operations) {
-			spin_unlock(&inode->i_lock);
+				spin_unlock(&flctx->flc_lock);
 				return 1;
 			}
 		}
-	spin_unlock(&inode->i_lock);
+		spin_unlock(&flctx->flc_lock);
+	}
 	file->f_locks = 0;
 	return 0;
 }

fs/locks.c

@@ -157,14 +157,11 @@ static int target_leasetype(struct file_lock *fl)
 int leases_enable = 1;
 int lease_break_time = 45;
 
-#define for_each_lock(inode, lockp) \
-	for (lockp = &inode->i_flock; *lockp != NULL; lockp = &(*lockp)->fl_next)
-
 /*
  * The global file_lock_list is only used for displaying /proc/locks, so we
  * keep a list on each CPU, with each list protected by its own spinlock via
  * the file_lock_lglock. Note that alterations to the list also require that
- * the relevant i_lock is held.
+ * the relevant flc_lock is held.
  */
 DEFINE_STATIC_LGLOCK(file_lock_lglock);
 static DEFINE_PER_CPU(struct hlist_head, file_lock_list);
@@ -192,21 +189,68 @@ static DEFINE_HASHTABLE(blocked_hash, BLOCKED_HASH_BITS);
  * contrast to those that are acting as records of acquired locks).
  *
  * Note that when we acquire this lock in order to change the above fields,
- * we often hold the i_lock as well. In certain cases, when reading the fields
+ * we often hold the flc_lock as well. In certain cases, when reading the fields
  * protected by this lock, we can skip acquiring it iff we already hold the
- * i_lock.
+ * flc_lock.
  *
  * In particular, adding an entry to the fl_block list requires that you hold
- * both the i_lock and the blocked_lock_lock (acquired in that order). Deleting
- * an entry from the list however only requires the file_lock_lock.
+ * both the flc_lock and the blocked_lock_lock (acquired in that order).
+ * Deleting an entry from the list however only requires the file_lock_lock.
  */
 static DEFINE_SPINLOCK(blocked_lock_lock);
 
+static struct kmem_cache *flctx_cache __read_mostly;
 static struct kmem_cache *filelock_cache __read_mostly;
 
+static struct file_lock_context *
+locks_get_lock_context(struct inode *inode)
+{
+	struct file_lock_context *new;
+
+	if (likely(inode->i_flctx))
+		goto out;
+
+	new = kmem_cache_alloc(flctx_cache, GFP_KERNEL);
+	if (!new)
+		goto out;
+
+	spin_lock_init(&new->flc_lock);
+	INIT_LIST_HEAD(&new->flc_flock);
+	INIT_LIST_HEAD(&new->flc_posix);
+	INIT_LIST_HEAD(&new->flc_lease);
+
+	/*
+	 * Assign the pointer if it's not already assigned. If it is, then
+	 * free the context we just allocated.
+	 */
+	spin_lock(&inode->i_lock);
+	if (likely(!inode->i_flctx)) {
+		inode->i_flctx = new;
+		new = NULL;
+	}
+	spin_unlock(&inode->i_lock);
+
+	if (new)
+		kmem_cache_free(flctx_cache, new);
+out:
+	return inode->i_flctx;
+}
+
+void
+locks_free_lock_context(struct file_lock_context *ctx)
+{
+	if (ctx) {
+		WARN_ON_ONCE(!list_empty(&ctx->flc_flock));
+		WARN_ON_ONCE(!list_empty(&ctx->flc_posix));
+		WARN_ON_ONCE(!list_empty(&ctx->flc_lease));
+		kmem_cache_free(flctx_cache, ctx);
+	}
+}
+
 static void locks_init_lock_heads(struct file_lock *fl)
 {
 	INIT_HLIST_NODE(&fl->fl_link);
+	INIT_LIST_HEAD(&fl->fl_list);
 	INIT_LIST_HEAD(&fl->fl_block);
 	init_waitqueue_head(&fl->fl_wait);
 }
@@ -243,6 +287,7 @@ EXPORT_SYMBOL_GPL(locks_release_private);
 void locks_free_lock(struct file_lock *fl)
 {
 	BUG_ON(waitqueue_active(&fl->fl_wait));
+	BUG_ON(!list_empty(&fl->fl_list));
 	BUG_ON(!list_empty(&fl->fl_block));
 	BUG_ON(!hlist_unhashed(&fl->fl_link));
 
@@ -257,8 +302,8 @@ locks_dispose_list(struct list_head *dispose)
 	struct file_lock *fl;
 
 	while (!list_empty(dispose)) {
-		fl = list_first_entry(dispose, struct file_lock, fl_block);
-		list_del_init(&fl->fl_block);
+		fl = list_first_entry(dispose, struct file_lock, fl_list);
+		list_del_init(&fl->fl_list);
 		locks_free_lock(fl);
 	}
 }
@@ -513,7 +558,7 @@ static int posix_same_owner(struct file_lock *fl1, struct file_lock *fl2)
 	return fl1->fl_owner == fl2->fl_owner;
 }
 
-/* Must be called with the i_lock held! */
+/* Must be called with the flc_lock held! */
 static void locks_insert_global_locks(struct file_lock *fl)
 {
 	lg_local_lock(&file_lock_lglock);
@@ -522,12 +567,12 @@ static void locks_insert_global_locks(struct file_lock *fl)
 	lg_local_unlock(&file_lock_lglock);
 }
 
-/* Must be called with the i_lock held! */
+/* Must be called with the flc_lock held! */
 static void locks_delete_global_locks(struct file_lock *fl)
 {
 	/*
 	 * Avoid taking lock if already unhashed. This is safe since this check
-	 * is done while holding the i_lock, and new insertions into the list
+	 * is done while holding the flc_lock, and new insertions into the list
 	 * also require that it be held.
 	 */
 	if (hlist_unhashed(&fl->fl_link))
@@ -579,10 +624,10 @@ static void locks_delete_block(struct file_lock *waiter)
  * the order they blocked. The documentation doesn't require this but
  * it seems like the reasonable thing to do.
  *
- * Must be called with both the i_lock and blocked_lock_lock held. The fl_block
- * list itself is protected by the blocked_lock_lock, but by ensuring that the
- * i_lock is also held on insertions we can avoid taking the blocked_lock_lock
- * in some cases when we see that the fl_block list is empty.
+ * Must be called with both the flc_lock and blocked_lock_lock held. The
+ * fl_block list itself is protected by the blocked_lock_lock, but by ensuring
+ * that the flc_lock is also held on insertions we can avoid taking the
+ * blocked_lock_lock in some cases when we see that the fl_block list is empty.
  */
 static void __locks_insert_block(struct file_lock *blocker,
 					struct file_lock *waiter)
@@ -594,7 +639,7 @@ static void __locks_insert_block(struct file_lock *blocker,
 		locks_insert_global_blocked(waiter);
 }
 
-/* Must be called with i_lock held. */
+/* Must be called with flc_lock held. */
 static void locks_insert_block(struct file_lock *blocker,
 					struct file_lock *waiter)
 {
@@ -606,15 +651,15 @@ static void locks_insert_block(struct file_lock *blocker,
 /*
  * Wake up processes blocked waiting for blocker.
  *
- * Must be called with the inode->i_lock held!
+ * Must be called with the inode->flc_lock held!
  */
 static void locks_wake_up_blocks(struct file_lock *blocker)
 {
 	/*
 	 * Avoid taking global lock if list is empty. This is safe since new
-	 * blocked requests are only added to the list under the i_lock, and
-	 * the i_lock is always held here. Note that removal from the fl_block
-	 * list does not require the i_lock, so we must recheck list_empty()
+	 * blocked requests are only added to the list under the flc_lock, and
+	 * the flc_lock is always held here. Note that removal from the fl_block
+	 * list does not require the flc_lock, so we must recheck list_empty()
 	 * after acquiring the blocked_lock_lock.
 	 */
 	if (list_empty(&blocker->fl_block))
@@ -635,63 +680,36 @@ static void locks_wake_up_blocks(struct file_lock *blocker)
 	spin_unlock(&blocked_lock_lock);
 }
 
-/* Insert file lock fl into an inode's lock list at the position indicated
- * by pos. At the same time add the lock to the global file lock list.
- *
- * Must be called with the i_lock held!
- */
-static void locks_insert_lock(struct file_lock **pos, struct file_lock *fl)
+static void
+locks_insert_lock_ctx(struct file_lock *fl, int *counter,
+		      struct list_head *before)
 {
 	fl->fl_nspid = get_pid(task_tgid(current));
-
-	/* insert into file's list */
-	fl->fl_next = *pos;
-	*pos = fl;
-
+	list_add_tail(&fl->fl_list, before);
+	++*counter;
 	locks_insert_global_locks(fl);
 }
 
-/**
- * locks_delete_lock - Delete a lock and then free it.
- * @thisfl_p: pointer that points to the fl_next field of the previous
- * 	      inode->i_flock list entry
- *
- * Unlink a lock from all lists and free the namespace reference, but don't
- * free it yet. Wake up processes that are blocked waiting for this lock and
- * notify the FS that the lock has been cleared.
- *
- * Must be called with the i_lock held!
- */
-static void locks_unlink_lock(struct file_lock **thisfl_p)
+static void
+locks_unlink_lock_ctx(struct file_lock *fl, int *counter)
 {
-	struct file_lock *fl = *thisfl_p;
-
 	locks_delete_global_locks(fl);
-
-	*thisfl_p = fl->fl_next;
-	fl->fl_next = NULL;
-
+	list_del_init(&fl->fl_list);
+	--*counter;
 	if (fl->fl_nspid) {
 		put_pid(fl->fl_nspid);
 		fl->fl_nspid = NULL;
 	}
-
 	locks_wake_up_blocks(fl);
 }
 
-/*
- * Unlink a lock from all lists and free it.
- *
- * Must be called with i_lock held!
- */
-static void locks_delete_lock(struct file_lock **thisfl_p,
+static void
+locks_delete_lock_ctx(struct file_lock *fl, int *counter,
 		      struct list_head *dispose)
 {
-	struct file_lock *fl = *thisfl_p;
-
-	locks_unlink_lock(thisfl_p);
+	locks_unlink_lock_ctx(fl, counter);
 	if (dispose)
-		list_add(&fl->fl_block, dispose);
+		list_add(&fl->fl_list, dispose);
 	else
 		locks_free_lock(fl);
 }
@@ -746,22 +764,27 @@ void
 posix_test_lock(struct file *filp, struct file_lock *fl)
 {
 	struct file_lock *cfl;
+	struct file_lock_context *ctx;
 	struct inode *inode = file_inode(filp);
 
-	spin_lock(&inode->i_lock);
-	for (cfl = file_inode(filp)->i_flock; cfl; cfl = cfl->fl_next) {
-		if (!IS_POSIX(cfl))
-			continue;
-		if (posix_locks_conflict(fl, cfl))
-			break;
+	ctx = inode->i_flctx;
+	if (!ctx || list_empty_careful(&ctx->flc_posix)) {
+		fl->fl_type = F_UNLCK;
+		return;
 	}
-	if (cfl) {
+
+	spin_lock(&ctx->flc_lock);
+	list_for_each_entry(cfl, &ctx->flc_posix, fl_list) {
+		if (posix_locks_conflict(fl, cfl)) {
 			locks_copy_conflock(fl, cfl);
 			if (cfl->fl_nspid)
 				fl->fl_pid = pid_vnr(cfl->fl_nspid);
-	} else
+			goto out;
+		}
+	}
 	fl->fl_type = F_UNLCK;
-	spin_unlock(&inode->i_lock);
+out:
+	spin_unlock(&ctx->flc_lock);
 	return;
 }
 EXPORT_SYMBOL(posix_test_lock);
@@ -845,34 +868,34 @@ static int posix_locks_deadlock(struct file_lock *caller_fl,
 static int flock_lock_file(struct file *filp, struct file_lock *request)
 {
 	struct file_lock *new_fl = NULL;
-	struct file_lock **before;
-	struct inode * inode = file_inode(filp);
+	struct file_lock *fl;
+	struct file_lock_context *ctx;
+	struct inode *inode = file_inode(filp);
 	int error = 0;
-	int found = 0;
+	bool found = false;
 	LIST_HEAD(dispose);
 
+	ctx = locks_get_lock_context(inode);
+	if (!ctx)
+		return -ENOMEM;
+
 	if (!(request->fl_flags & FL_ACCESS) && (request->fl_type != F_UNLCK)) {
 		new_fl = locks_alloc_lock();
 		if (!new_fl)
 			return -ENOMEM;
 	}
 
-	spin_lock(&inode->i_lock);
+	spin_lock(&ctx->flc_lock);
 	if (request->fl_flags & FL_ACCESS)
 		goto find_conflict;
 
-	for_each_lock(inode, before) {
-		struct file_lock *fl = *before;
-		if (IS_POSIX(fl))
-			break;
-		if (IS_LEASE(fl))
-			continue;
+	list_for_each_entry(fl, &ctx->flc_flock, fl_list) {
 		if (filp != fl->fl_file)
 			continue;
 		if (request->fl_type == fl->fl_type)
 			goto out;
-		found = 1;
-		locks_delete_lock(before, &dispose);
+		found = true;
+		locks_delete_lock_ctx(fl, &ctx->flc_flock_cnt, &dispose);
 		break;
 	}
 
@@ -887,18 +910,13 @@ static int flock_lock_file(struct file *filp, struct file_lock *request)
 	 * give it the opportunity to lock the file.
 	 */
 	if (found) {
-		spin_unlock(&inode->i_lock);
+		spin_unlock(&ctx->flc_lock);
 		cond_resched();
-		spin_lock(&inode->i_lock);
+		spin_lock(&ctx->flc_lock);
 	}
 
 find_conflict:
-	for_each_lock(inode, before) {
-		struct file_lock *fl = *before;
-		if (IS_POSIX(fl))
-			break;
-		if (IS_LEASE(fl))
-			continue;
+	list_for_each_entry(fl, &ctx->flc_flock, fl_list) {
 		if (!flock_locks_conflict(request, fl))
 			continue;
 		error = -EAGAIN;
@@ -911,12 +929,12 @@ static int flock_lock_file(struct file *filp, struct file_lock *request)
 	if (request->fl_flags & FL_ACCESS)
 		goto out;
 	locks_copy_lock(new_fl, request);
-	locks_insert_lock(before, new_fl);
+	locks_insert_lock_ctx(new_fl, &ctx->flc_flock_cnt, &ctx->flc_flock);
 	new_fl = NULL;
 	error = 0;
 
 out:
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&ctx->flc_lock);
 	if (new_fl)
 		locks_free_lock(new_fl);
 	locks_dispose_list(&dispose);
@@ -925,16 +943,20 @@ static int flock_lock_file(struct file *filp, struct file_lock *request)
 
 static int __posix_lock_file(struct inode *inode, struct file_lock *request, struct file_lock *conflock)
 {
-	struct file_lock *fl;
+	struct file_lock *fl, *tmp;
 	struct file_lock *new_fl = NULL;
 	struct file_lock *new_fl2 = NULL;
 	struct file_lock *left = NULL;
 	struct file_lock *right = NULL;
-	struct file_lock **before;
+	struct file_lock_context *ctx;
 	int error;
 	bool added = false;
 	LIST_HEAD(dispose);
 
+	ctx = locks_get_lock_context(inode);
+	if (!ctx)
+		return -ENOMEM;
+
 	/*
 	 * We may need two file_lock structures for this operation,
 	 * so we get them in advance to avoid races.
@@ -948,15 +970,14 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 		new_fl2 = locks_alloc_lock();
 	}
 
-	spin_lock(&inode->i_lock);
+	spin_lock(&ctx->flc_lock);
 	/*
 	 * New lock request. Walk all POSIX locks and look for conflicts. If
 	 * there are any, either return error or put the request on the
 	 * blocker's list of waiters and the global blocked_hash.
 	 */
 	if (request->fl_type != F_UNLCK) {
-		for_each_lock(inode, before) {
-			fl = *before;
+		list_for_each_entry(fl, &ctx->flc_posix, fl_list) {
 			if (!IS_POSIX(fl))
 				continue;
 			if (!posix_locks_conflict(request, fl))
@@ -986,29 +1007,25 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 	if (request->fl_flags & FL_ACCESS)
 		goto out;
 
-	/*
-	 * Find the first old lock with the same owner as the new lock.
-	 */
-	
-	before = &inode->i_flock;
-
-	/* First skip locks owned by other processes.  */
-	while ((fl = *before) && (!IS_POSIX(fl) ||
-				  !posix_same_owner(request, fl))) {
-		before = &fl->fl_next;
+	/* Find the first old lock with the same owner as the new lock */
+	list_for_each_entry(fl, &ctx->flc_posix, fl_list) {
+		if (posix_same_owner(request, fl))
+			break;
 	}
 
 	/* Process locks with this owner. */
-	while ((fl = *before) && posix_same_owner(request, fl)) {
-		/* Detect adjacent or overlapping regions (if same lock type)
-		 */
+	list_for_each_entry_safe_from(fl, tmp, &ctx->flc_posix, fl_list) {
+		if (!posix_same_owner(request, fl))
+			break;
+
+		/* Detect adjacent or overlapping regions (if same lock type) */
 		if (request->fl_type == fl->fl_type) {
 			/* In all comparisons of start vs end, use
 			 * "start - 1" rather than "end + 1". If end
 			 * is OFFSET_MAX, end + 1 will become negative.
 			 */
 			if (fl->fl_end < request->fl_start - 1)
-				goto next_lock;
+				continue;
 			/* If the next lock in the list has entirely bigger
 			 * addresses than the new one, insert the lock here.
 			 */
@@ -1029,18 +1046,18 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 			else
 				request->fl_end = fl->fl_end;
 			if (added) {
-				locks_delete_lock(before, &dispose);
+				locks_delete_lock_ctx(fl, &ctx->flc_posix_cnt,
+							&dispose);
 				continue;
 			}
 			request = fl;
 			added = true;
-		}
-		else {
+		} else {
 			/* Processing for different lock types is a bit
 			 * more complex.
 			 */
 			if (fl->fl_end < request->fl_start)
-				goto next_lock;
+				continue;
 			if (fl->fl_start > request->fl_end)
 				break;
 			if (request->fl_type == F_UNLCK)
@@ -1059,7 +1076,8 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 				 * one (This may happen several times).
 				 */
 				if (added) {
-					locks_delete_lock(before, &dispose);
+					locks_delete_lock_ctx(fl,
+						&ctx->flc_posix_cnt, &dispose);
 					continue;
 				}
 				/*
@@ -1075,15 +1093,13 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 				locks_copy_lock(new_fl, request);
 				request = new_fl;
 				new_fl = NULL;
-				locks_delete_lock(before, &dispose);
-				locks_insert_lock(before, request);
+				locks_insert_lock_ctx(request,
+					&ctx->flc_posix_cnt, &fl->fl_list);
+				locks_delete_lock_ctx(fl,
+					&ctx->flc_posix_cnt, &dispose);
 				added = true;
 			}
 		}
-		/* Go on to next lock.
-		 */
-	next_lock:
-		before = &fl->fl_next;
 	}
 
 	/*
@@ -1108,7 +1124,8 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 			goto out;
 		}
 		locks_copy_lock(new_fl, request);
-		locks_insert_lock(before, new_fl);
+		locks_insert_lock_ctx(new_fl, &ctx->flc_posix_cnt,
+					&fl->fl_list);
 		new_fl = NULL;
 	}
 	if (right) {
@@ -1119,7 +1136,8 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 			left = new_fl2;
 			new_fl2 = NULL;
 			locks_copy_lock(left, right);
-			locks_insert_lock(before, left);
+			locks_insert_lock_ctx(left, &ctx->flc_posix_cnt,
+						&fl->fl_list);
 		}
 		right->fl_start = request->fl_end + 1;
 		locks_wake_up_blocks(right);
@@ -1129,7 +1147,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 		locks_wake_up_blocks(left);
 	}
  out:
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&ctx->flc_lock);
 	/*
 	 * Free any unused locks.
 	 */
@@ -1199,22 +1217,29 @@ EXPORT_SYMBOL(posix_lock_file_wait);
  */
 int locks_mandatory_locked(struct file *file)
 {
+	int ret;
 	struct inode *inode = file_inode(file);
+	struct file_lock_context *ctx;
 	struct file_lock *fl;
 
+	ctx = inode->i_flctx;
+	if (!ctx || list_empty_careful(&ctx->flc_posix))
+		return 0;
+
 	/*
 	 * Search the lock list for this inode for any POSIX locks.
 	 */
-	spin_lock(&inode->i_lock);
-	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
-		if (!IS_POSIX(fl))
-			continue;
+	spin_lock(&ctx->flc_lock);
+	ret = 0;
+	list_for_each_entry(fl, &ctx->flc_posix, fl_list) {
 		if (fl->fl_owner != current->files &&
-		    fl->fl_owner != file)
+		    fl->fl_owner != file) {
+			ret = -EAGAIN;
 			break;
 		}
-	spin_unlock(&inode->i_lock);
-	return fl ? -EAGAIN : 0;
+	}
+	spin_unlock(&ctx->flc_lock);
+	return ret;
 }
 
 /**
@@ -1294,9 +1319,9 @@ static void lease_clear_pending(struct file_lock *fl, int arg)
 }
 
 /* We already had a lease on this file; just change its type */
-int lease_modify(struct file_lock **before, int arg, struct list_head *dispose)
+int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose)
 {
-	struct file_lock *fl = *before;
+	struct file_lock_context *flctx;
 	int error = assign_type(fl, arg);
 
 	if (error)
@@ -1306,6 +1331,7 @@ int lease_modify(struct file_lock **before, int arg, struct list_head *dispose)
 	if (arg == F_UNLCK) {
 		struct file *filp = fl->fl_file;
 
+		flctx = file_inode(filp)->i_flctx;
 		f_delown(filp);
 		filp->f_owner.signum = 0;
 		fasync_helper(0, fl->fl_file, 0, &fl->fl_fasync);
@@ -1313,7 +1339,7 @@ int lease_modify(struct file_lock **before, int arg, struct list_head *dispose)
 			printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync);
 			fl->fl_fasync = NULL;
 		}
-		locks_delete_lock(before, dispose);
+		locks_delete_lock_ctx(fl, &flctx->flc_lease_cnt, dispose);
 	}
 	return 0;
 }
@@ -1329,20 +1355,17 @@ static bool past_time(unsigned long then)
 
 static void time_out_leases(struct inode *inode, struct list_head *dispose)
 {
-	struct file_lock **before;
-	struct file_lock *fl;
+	struct file_lock_context *ctx = inode->i_flctx;
+	struct file_lock *fl, *tmp;
 
-	lockdep_assert_held(&inode->i_lock);
+	lockdep_assert_held(&ctx->flc_lock);
 
-	before = &inode->i_flock;
-	while ((fl = *before) && IS_LEASE(fl) && lease_breaking(fl)) {
+	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) {
 		trace_time_out_leases(inode, fl);
 		if (past_time(fl->fl_downgrade_time))
-			lease_modify(before, F_RDLCK, dispose);
+			lease_modify(fl, F_RDLCK, dispose);
 		if (past_time(fl->fl_break_time))
-			lease_modify(before, F_UNLCK, dispose);
-		if (fl == *before)	/* lease_modify may have freed fl */
-			before = &fl->fl_next;
+			lease_modify(fl, F_UNLCK, dispose);
 	}
 }
 
@@ -1356,11 +1379,12 @@ static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker)
 static bool
 any_leases_conflict(struct inode *inode, struct file_lock *breaker)
 {
+	struct file_lock_context *ctx = inode->i_flctx;
 	struct file_lock *fl;
 
-	lockdep_assert_held(&inode->i_lock);
+	lockdep_assert_held(&ctx->flc_lock);
 
-	for (fl = inode->i_flock ; fl && IS_LEASE(fl); fl = fl->fl_next) {
+	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
 		if (leases_conflict(fl, breaker))
 			return true;
 	}
@@ -1384,7 +1408,8 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 {
 	int error = 0;
 	struct file_lock *new_fl;
-	struct file_lock *fl, **before;
+	struct file_lock_context *ctx = inode->i_flctx;
+	struct file_lock *fl;
 	unsigned long break_time;
 	int want_write = (mode & O_ACCMODE) != O_RDONLY;
 	LIST_HEAD(dispose);
@@ -1394,7 +1419,13 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 		return PTR_ERR(new_fl);
 	new_fl->fl_flags = type;
 
-	spin_lock(&inode->i_lock);
+	/* typically we will check that ctx is non-NULL before calling */
+	if (!ctx) {
+		WARN_ON_ONCE(1);
+		return error;
+	}
+
+	spin_lock(&ctx->flc_lock);
 
 	time_out_leases(inode, &dispose);
 
@@ -1408,9 +1439,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 			break_time++;	/* so that 0 means no break time */
 	}
 
-	for (before = &inode->i_flock;
-			((fl = *before) != NULL) && IS_LEASE(fl);
-			before = &fl->fl_next) {
+	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
 		if (!leases_conflict(fl, new_fl))
 			continue;
 		if (want_write) {
@@ -1419,17 +1448,17 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 			fl->fl_flags |= FL_UNLOCK_PENDING;
 			fl->fl_break_time = break_time;
 		} else {
-			if (lease_breaking(inode->i_flock))
+			if (lease_breaking(fl))
 				continue;
 			fl->fl_flags |= FL_DOWNGRADE_PENDING;
 			fl->fl_downgrade_time = break_time;
 		}
 		if (fl->fl_lmops->lm_break(fl))
-			locks_delete_lock(before, &dispose);
+			locks_delete_lock_ctx(fl, &ctx->flc_lease_cnt,
+						&dispose);
 	}
 
-	fl = inode->i_flock;
-	if (!fl || !IS_LEASE(fl))
+	if (list_empty(&ctx->flc_lease))
 		goto out;
 
 	if (mode & O_NONBLOCK) {
@@ -1439,18 +1468,19 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 	}
 
 restart:
-	break_time = inode->i_flock->fl_break_time;
+	fl = list_first_entry(&ctx->flc_lease, struct file_lock, fl_list);
+	break_time = fl->fl_break_time;
 	if (break_time != 0)
 		break_time -= jiffies;
 	if (break_time == 0)
 		break_time++;
-	locks_insert_block(inode->i_flock, new_fl);
+	locks_insert_block(fl, new_fl);
 	trace_break_lease_block(inode, new_fl);
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&ctx->flc_lock);
 	locks_dispose_list(&dispose);
 	error = wait_event_interruptible_timeout(new_fl->fl_wait,
 						!new_fl->fl_next, break_time);
-	spin_lock(&inode->i_lock);
+	spin_lock(&ctx->flc_lock);
 	trace_break_lease_unblock(inode, new_fl);
 	locks_delete_block(new_fl);
 	if (error >= 0) {
@@ -1462,12 +1492,10 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 			time_out_leases(inode, &dispose);
 		if (any_leases_conflict(inode, new_fl))
 			goto restart;
-
 		error = 0;
 	}
-
 out:
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&ctx->flc_lock);
 	locks_dispose_list(&dispose);
 	locks_free_lock(new_fl);
 	return error;
@@ -1487,14 +1515,18 @@ EXPORT_SYMBOL(__break_lease);
 void lease_get_mtime(struct inode *inode, struct timespec *time)
 {
 	bool has_lease = false;
-	struct file_lock *flock;
+	struct file_lock_context *ctx = inode->i_flctx;
+	struct file_lock *fl;
 
-	if (inode->i_flock) {
-		spin_lock(&inode->i_lock);
-		flock = inode->i_flock;
-		if (flock && IS_LEASE(flock) && (flock->fl_type == F_WRLCK))
+	if (ctx && !list_empty_careful(&ctx->flc_lease)) {
+		spin_lock(&ctx->flc_lock);
+		if (!list_empty(&ctx->flc_lease)) {
+			fl = list_first_entry(&ctx->flc_lease,
+						struct file_lock, fl_list);
+			if (fl->fl_type == F_WRLCK)
 				has_lease = true;
-		spin_unlock(&inode->i_lock);
+		}
+		spin_unlock(&ctx->flc_lock);
 	}
 
 	if (has_lease)
@@ -1532,20 +1564,22 @@ int fcntl_getlease(struct file *filp)
 {
 	struct file_lock *fl;
 	struct inode *inode = file_inode(filp);
+	struct file_lock_context *ctx = inode->i_flctx;
 	int type = F_UNLCK;
 	LIST_HEAD(dispose);
 
-	spin_lock(&inode->i_lock);
+	if (ctx && !list_empty_careful(&ctx->flc_lease)) {
+		spin_lock(&ctx->flc_lock);
 		time_out_leases(file_inode(filp), &dispose);
-	for (fl = file_inode(filp)->i_flock; fl && IS_LEASE(fl);
-			fl = fl->fl_next) {
-		if (fl->fl_file == filp) {
+		list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
+			if (fl->fl_file != filp)
+				continue;
 			type = target_leasetype(fl);
 			break;
 		}
-	}
-	spin_unlock(&inode->i_lock);
+		spin_unlock(&ctx->flc_lock);
 		locks_dispose_list(&dispose);
+	}
 	return type;
 }
 
@@ -1578,9 +1612,10 @@ check_conflicting_open(const struct dentry *dentry, const long arg)
 static int
 generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **priv)
 {
-	struct file_lock *fl, **before, **my_before = NULL, *lease;
+	struct file_lock *fl, *my_fl = NULL, *lease;
 	struct dentry *dentry = filp->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
+	struct file_lock_context *ctx;
 	bool is_deleg = (*flp)->fl_flags & FL_DELEG;
 	int error;
 	LIST_HEAD(dispose);
@@ -1588,6 +1623,10 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 	lease = *flp;
 	trace_generic_add_lease(inode, lease);
 
+	ctx = locks_get_lock_context(inode);
+	if (!ctx)
+		return -ENOMEM;
+
 	/*
 	 * In the delegation case we need mutual exclusion with
 	 * a number of operations that take the i_mutex.  We trylock
@@ -1606,7 +1645,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 		return -EINVAL;
 	}
 
-	spin_lock(&inode->i_lock);
+	spin_lock(&ctx->flc_lock);
 	time_out_leases(inode, &dispose);
 	error = check_conflicting_open(dentry, arg);
 	if (error)
@@ -1621,13 +1660,12 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 	 * except for this filp.
 	 */
 	error = -EAGAIN;
-	for (before = &inode->i_flock;
-			((fl = *before) != NULL) && IS_LEASE(fl);
-			before = &fl->fl_next) {
+	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
 		if (fl->fl_file == filp) {
-			my_before = before;
+			my_fl = fl;
 			continue;
 		}
+
 		/*
 		 * No exclusive leases if someone else has a lease on
 		 * this file:
@@ -1642,9 +1680,8 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 			goto out;
 	}
 
-	if (my_before != NULL) {
-		lease = *my_before;
-		error = lease->fl_lmops->lm_change(my_before, arg, &dispose);
+	if (my_fl != NULL) {
+		error = lease->fl_lmops->lm_change(my_fl, arg, &dispose);
 		if (error)
 			goto out;
 		goto out_setup;
@@ -1654,7 +1691,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 	if (!leases_enable)
 		goto out;
 
-	locks_insert_lock(before, lease);
+	locks_insert_lock_ctx(lease, &ctx->flc_lease_cnt, &ctx->flc_lease);
 	/*
 	 * The check in break_lease() is lockless. It's possible for another
 	 * open to race in after we did the earlier check for a conflicting
@@ -1666,45 +1703,49 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 	 */
 	smp_mb();
 	error = check_conflicting_open(dentry, arg);
-	if (error)
-		goto out_unlink;
+	if (error) {
+		locks_unlink_lock_ctx(lease, &ctx->flc_lease_cnt);
+		goto out;
+	}
 
 out_setup:
 	if (lease->fl_lmops->lm_setup)
 		lease->fl_lmops->lm_setup(lease, priv);
 out:
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&ctx->flc_lock);
 	locks_dispose_list(&dispose);
 	if (is_deleg)
 		mutex_unlock(&inode->i_mutex);
-	if (!error && !my_before)
+	if (!error && !my_fl)
 		*flp = NULL;
 	return error;
-out_unlink:
-	locks_unlink_lock(before);
-	goto out;
 }
 
 static int generic_delete_lease(struct file *filp)
 {
 	int error = -EAGAIN;
-	struct file_lock *fl, **before;
+	struct file_lock *fl, *victim = NULL;
 	struct dentry *dentry = filp->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
+	struct file_lock_context *ctx = inode->i_flctx;
 	LIST_HEAD(dispose);
 
-	spin_lock(&inode->i_lock);
-	time_out_leases(inode, &dispose);
-	for (before = &inode->i_flock;
-			((fl = *before) != NULL) && IS_LEASE(fl);
-			before = &fl->fl_next) {
-		if (fl->fl_file == filp)
+	if (!ctx) {
+		trace_generic_delete_lease(inode, NULL);
+		return error;
+	}
+
+	spin_lock(&ctx->flc_lock);
+	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
+		if (fl->fl_file == filp) {
+			victim = fl;
 			break;
 		}
+	}
 	trace_generic_delete_lease(inode, fl);
-	if (fl && IS_LEASE(fl))
-		error = fl->fl_lmops->lm_change(before, F_UNLCK, &dispose);
-	spin_unlock(&inode->i_lock);
+	if (victim)
+		error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose);
+	spin_unlock(&ctx->flc_lock);
 	locks_dispose_list(&dispose);
 	return error;
 }
@@ -2171,7 +2212,7 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
 	 */
 	/*
 	 * we need that spin_lock here - it prevents reordering between
-	 * update of inode->i_flock and check for it done in close().
+	 * update of i_flctx->flc_posix and check for it done in close().
 	 * rcu_read_lock() wouldn't do.
 	 */
 	spin_lock(&current->files->file_lock);
@@ -2331,13 +2372,14 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd,
 void locks_remove_posix(struct file *filp, fl_owner_t owner)
 {
 	struct file_lock lock;
+	struct file_lock_context *ctx = file_inode(filp)->i_flctx;
 
 	/*
 	 * If there are no locks held on this file, we don't need to call
 	 * posix_lock_file().  Another process could be setting a lock on this
 	 * file at the same time, but we wouldn't remove that lock anyway.
 	 */
-	if (!file_inode(filp)->i_flock)
+	if (!ctx || list_empty(&ctx->flc_posix))
 		return;
 
 	lock.fl_type = F_UNLCK;
@@ -2358,22 +2400,10 @@ void locks_remove_posix(struct file *filp, fl_owner_t owner)
 
 EXPORT_SYMBOL(locks_remove_posix);
 
-/*
- * This function is called on the last close of an open file.
- */
-void locks_remove_file(struct file *filp)
+/* The i_flctx must be valid when calling into here */
+static void
+locks_remove_flock(struct file *filp)
 {
-	struct inode * inode = file_inode(filp);
-	struct file_lock *fl;
-	struct file_lock **before;
-	LIST_HEAD(dispose);
-
-	if (!inode->i_flock)
-		return;
-
-	locks_remove_posix(filp, filp);
-
-	if (filp->f_op->flock) {
 	struct file_lock fl = {
 		.fl_owner = filp,
 		.fl_pid = current->tgid,
@@ -2382,45 +2412,57 @@ void locks_remove_file(struct file *filp)
 		.fl_type = F_UNLCK,
 		.fl_end = OFFSET_MAX,
 	};
+	struct file_lock_context *flctx = file_inode(filp)->i_flctx;
+
+	if (list_empty(&flctx->flc_flock))
+		return;
+
+	if (filp->f_op->flock)
 		filp->f_op->flock(filp, F_SETLKW, &fl);
+	else
+		flock_lock_file(filp, &fl);
+
 	if (fl.fl_ops && fl.fl_ops->fl_release_private)
 		fl.fl_ops->fl_release_private(&fl);
-	}
-
-	spin_lock(&inode->i_lock);
-	before = &inode->i_flock;
+}
 
-	while ((fl = *before) != NULL) {
-		if (fl->fl_file == filp) {
-			if (IS_LEASE(fl)) {
-				lease_modify(before, F_UNLCK, &dispose);
-				continue;
-			}
+/* The i_flctx must be valid when calling into here */
+static void
+locks_remove_lease(struct file *filp)
+{
+	struct inode *inode = file_inode(filp);
+	struct file_lock_context *ctx = inode->i_flctx;
+	struct file_lock *fl, *tmp;
+	LIST_HEAD(dispose);
 
-			/*
-			 * There's a leftover lock on the list of a type that
-			 * we didn't expect to see. Most likely a classic
-			 * POSIX lock that ended up not getting released
-			 * properly, or that raced onto the list somehow. Log
-			 * some info about it and then just remove it from
-			 * the list.
-			 */
-			WARN(!IS_FLOCK(fl),
-				"leftover lock: dev=%u:%u ino=%lu type=%hhd flags=0x%x start=%lld end=%lld\n",
-				MAJOR(inode->i_sb->s_dev),
-				MINOR(inode->i_sb->s_dev), inode->i_ino,
-				fl->fl_type, fl->fl_flags,
-				fl->fl_start, fl->fl_end);
+	if (list_empty(&ctx->flc_lease))
+		return;
 
-			locks_delete_lock(before, &dispose);
-			continue;
- 		}
-		before = &fl->fl_next;
-	}
-	spin_unlock(&inode->i_lock);
+	spin_lock(&ctx->flc_lock);
+	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list)
+		lease_modify(fl, F_UNLCK, &dispose);
+	spin_unlock(&ctx->flc_lock);
 	locks_dispose_list(&dispose);
 }
 
+/*
+ * This function is called on the last close of an open file.
+ */
+void locks_remove_file(struct file *filp)
+{
+	if (!file_inode(filp)->i_flctx)
+		return;
+
+	/* remove any OFD locks */
+	locks_remove_posix(filp, filp);
+
+	/* remove flock locks */
+	locks_remove_flock(filp);
+
+	/* remove any leases */
+	locks_remove_lease(filp);
+}
+
 /**
  *	posix_unblock_lock - stop waiting for a file lock
  *	@waiter: the lock which was waiting
@@ -2621,6 +2663,9 @@ static int __init filelock_init(void)
 {
 	int i;
 
+	flctx_cache = kmem_cache_create("file_lock_ctx",
+			sizeof(struct file_lock_context), 0, SLAB_PANIC, NULL);
+
 	filelock_cache = kmem_cache_create("file_lock_cache",
 			sizeof(struct file_lock), 0, SLAB_PANIC, NULL);
 

fs/nfs/delegation.c

@@ -85,25 +85,30 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_
 {
 	struct inode *inode = state->inode;
 	struct file_lock *fl;
+	struct file_lock_context *flctx = inode->i_flctx;
+	struct list_head *list;
 	int status = 0;
 
-	if (inode->i_flock == NULL)
+	if (flctx == NULL)
 		goto out;
 
-	/* 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;
+	list = &flctx->flc_posix;
+	spin_lock(&flctx->flc_lock);
+restart:
+	list_for_each_entry(fl, list, fl_list) {
 		if (nfs_file_open_context(fl->fl_file) != ctx)
 			continue;
-		spin_unlock(&inode->i_lock);
+		spin_unlock(&flctx->flc_lock);
 		status = nfs4_lock_delegation_recall(fl, state, stateid);
 		if (status < 0)
 			goto out;
-		spin_lock(&inode->i_lock);
+		spin_lock(&flctx->flc_lock);
 	}
-	spin_unlock(&inode->i_lock);
+	if (list == &flctx->flc_posix) {
+		list = &flctx->flc_flock;
+		goto restart;
+	}
+	spin_unlock(&flctx->flc_lock);
 out:
 	return status;
 }

fs/nfs/nfs4state.c

@@ -1366,20 +1366,22 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct file_lock *fl;
 	int status = 0;
+	struct file_lock_context *flctx = inode->i_flctx;
+	struct list_head *list;
 
-	if (inode->i_flock == NULL)
+	if (flctx == NULL)
 		return 0;
 
+	list = &flctx->flc_posix;
+
 	/* Guard against delegation returns and new lock/unlock calls */
 	down_write(&nfsi->rwsem);
-	/* Protect inode->i_flock using the BKL */
-	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;
+	spin_lock(&flctx->flc_lock);
+restart:
+	list_for_each_entry(fl, list, fl_list) {
 		if (nfs_file_open_context(fl->fl_file)->state != state)
 			continue;
-		spin_unlock(&inode->i_lock);
+		spin_unlock(&flctx->flc_lock);
 		status = ops->recover_lock(state, fl);
 		switch (status) {
 		case 0:
@@ -1397,7 +1399,7 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_
 		case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
 			goto out;
 		default:
-				printk(KERN_ERR "NFS: %s: unhandled error %d\n",
+			pr_err("NFS: %s: unhandled error %d\n",
 					__func__, status);
 		case -ENOMEM:
 		case -NFS4ERR_DENIED:
@@ -1406,9 +1408,13 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_
 			/* kill_proc(fl->fl_pid, SIGLOST, 1); */
 			status = 0;
 		}
-		spin_lock(&inode->i_lock);
+		spin_lock(&flctx->flc_lock);
 	}
-	spin_unlock(&inode->i_lock);
+	if (list == &flctx->flc_posix) {
+		list = &flctx->flc_flock;
+		goto restart;
+	}
+	spin_unlock(&flctx->flc_lock);
 out:
 	up_write(&nfsi->rwsem);
 	return status;

fs/nfs/pagelist.c

@@ -826,11 +826,15 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev,
 				      struct nfs_pageio_descriptor *pgio)
 {
 	size_t size;
+	struct file_lock_context *flctx;
 
 	if (prev) {
 		if (!nfs_match_open_context(req->wb_context, prev->wb_context))
 			return false;
-		if (req->wb_context->dentry->d_inode->i_flock != NULL &&
+		flctx = req->wb_context->dentry->d_inode->i_flctx;
+		if (flctx != NULL &&
+		    !(list_empty_careful(&flctx->flc_posix) &&
+		      list_empty_careful(&flctx->flc_flock)) &&
 		    !nfs_match_lock_context(req->wb_lock_context,
 					    prev->wb_lock_context))
 			return false;

fs/nfs/write.c

@@ -1091,6 +1091,7 @@ int nfs_flush_incompatible(struct file *file, struct page *page)
 {
 	struct nfs_open_context *ctx = nfs_file_open_context(file);
 	struct nfs_lock_context *l_ctx;
+	struct file_lock_context *flctx = file_inode(file)->i_flctx;
 	struct nfs_page	*req;
 	int do_flush, status;
 	/*
@@ -1109,7 +1110,9 @@ int nfs_flush_incompatible(struct file *file, struct page *page)
 		do_flush = req->wb_page != page || req->wb_context != ctx;
 		/* for now, flush if more than 1 request in page_group */
 		do_flush |= req->wb_this_page != req;
-		if (l_ctx && ctx->dentry->d_inode->i_flock != NULL) {
+		if (l_ctx && flctx &&
+		    !(list_empty_careful(&flctx->flc_posix) &&
+		      list_empty_careful(&flctx->flc_flock))) {
 			do_flush |= l_ctx->lockowner.l_owner != current->files
 				|| l_ctx->lockowner.l_pid != current->tgid;
 		}
@@ -1170,6 +1173,13 @@ static bool nfs_write_pageuptodate(struct page *page, struct inode *inode)
 	return PageUptodate(page) != 0;
 }
 
+static bool
+is_whole_file_wrlock(struct file_lock *fl)
+{
+	return fl->fl_start == 0 && fl->fl_end == OFFSET_MAX &&
+			fl->fl_type == F_WRLCK;
+}
+
 /* If we know the page is up to date, and we're not using byte range locks (or
  * if we have the whole file locked for writing), it may be more efficient to
  * extend the write to cover the entire page in order to avoid fragmentation
@@ -1180,17 +1190,36 @@ static bool nfs_write_pageuptodate(struct page *page, struct inode *inode)
  */
 static int nfs_can_extend_write(struct file *file, struct page *page, struct inode *inode)
 {
+	int ret;
+	struct file_lock_context *flctx = inode->i_flctx;
+	struct file_lock *fl;
+
 	if (file->f_flags & O_DSYNC)
 		return 0;
 	if (!nfs_write_pageuptodate(page, inode))
 		return 0;
 	if (NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE))
 		return 1;
-	if (inode->i_flock == NULL || (inode->i_flock->fl_start == 0 &&
-			inode->i_flock->fl_end == OFFSET_MAX &&
-			inode->i_flock->fl_type != F_RDLCK))
-		return 1;
+	if (!flctx || (list_empty_careful(&flctx->flc_flock) &&
+		       list_empty_careful(&flctx->flc_posix)))
 		return 0;
+
+	/* Check to see if there are whole file write locks */
+	ret = 0;
+	spin_lock(&flctx->flc_lock);
+	if (!list_empty(&flctx->flc_posix)) {
+		fl = list_first_entry(&flctx->flc_posix, struct file_lock,
+					fl_list);
+		if (is_whole_file_wrlock(fl))
+			ret = 1;
+	} else if (!list_empty(&flctx->flc_flock)) {
+		fl = list_first_entry(&flctx->flc_flock, struct file_lock,
+					fl_list);
+		if (fl->fl_type == F_WRLCK)
+			ret = 1;
+	}
+	spin_unlock(&flctx->flc_lock);
+	return ret;
 }
 
 /*

fs/nfsd/nfs4state.c

@@ -3477,7 +3477,8 @@ nfsd_break_deleg_cb(struct file_lock *fl)
 }
 
 static int
-nfsd_change_deleg_cb(struct file_lock **onlist, int arg, struct list_head *dispose)
+nfsd_change_deleg_cb(struct file_lock *onlist, int arg,
+		     struct list_head *dispose)
 {
 	if (arg & F_UNLCK)
 		return lease_modify(onlist, arg, dispose);
@@ -5556,10 +5557,11 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 static bool
 check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner)
 {
-	struct file_lock **flpp;
+	struct file_lock *fl;
 	int status = false;
 	struct file *filp = find_any_file(fp);
 	struct inode *inode;
+	struct file_lock_context *flctx;
 
 	if (!filp) {
 		/* Any valid lock stateid should have some sort of access */
@@ -5568,15 +5570,18 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner)
 	}
 
 	inode = file_inode(filp);
+	flctx = inode->i_flctx;
 
-	spin_lock(&inode->i_lock);
-	for (flpp = &inode->i_flock; *flpp != NULL; flpp = &(*flpp)->fl_next) {
-		if ((*flpp)->fl_owner == (fl_owner_t)lowner) {
+	if (flctx && !list_empty_careful(&flctx->flc_posix)) {
+		spin_lock(&flctx->flc_lock);
+		list_for_each_entry(fl, &flctx->flc_posix, fl_list) {
+			if (fl->fl_owner == (fl_owner_t)lowner) {
 				status = true;
 				break;
 			}
 		}
-	spin_unlock(&inode->i_lock);
+		spin_unlock(&flctx->flc_lock);
+	}
 	fput(filp);
 	return status;
 }

fs/read_write.c

@@ -358,7 +358,7 @@ int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t
 			return retval;
 	}
 
-	if (unlikely(inode->i_flock && mandatory_lock(inode))) {
+	if (unlikely(inode->i_flctx && mandatory_lock(inode))) {
 		retval = locks_mandatory_area(
 			read_write == READ ? FLOCK_VERIFY_READ : FLOCK_VERIFY_WRITE,
 			inode, file, pos, count);

include/linux/fs.h

@@ -625,7 +625,7 @@ struct inode {
 	atomic_t		i_readcount; /* struct files open RO */
 #endif
 	const struct file_operations	*i_fop;	/* former ->i_op->default_file_ops */
-	struct file_lock	*i_flock;
+	struct file_lock_context	*i_flctx;
 	struct address_space	i_data;
 	struct list_head	i_devices;
 	union {
@@ -885,6 +885,8 @@ static inline struct file *get_file(struct file *f)
 /* legacy typedef, should eventually be removed */
 typedef void *fl_owner_t;
 
+struct file_lock;
+
 struct file_lock_operations {
 	void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
 	void (*fl_release_private)(struct file_lock *);
@@ -898,7 +900,7 @@ struct lock_manager_operations {
 	void (*lm_notify)(struct file_lock *);	/* unblock callback */
 	int (*lm_grant)(struct file_lock *, int);
 	bool (*lm_break)(struct file_lock *);
-	int (*lm_change)(struct file_lock **, int, struct list_head *);
+	int (*lm_change)(struct file_lock *, int, struct list_head *);
 	void (*lm_setup)(struct file_lock *, void **);
 };
 
@@ -923,17 +925,17 @@ int locks_in_grace(struct net *);
  * FIXME: should we create a separate "struct lock_request" to help distinguish
  * these two uses?
  *
- * The i_flock list is ordered by:
+ * The varous i_flctx lists are ordered by:
  *
- * 1) lock type -- FL_LEASEs first, then FL_FLOCK, and finally FL_POSIX
- * 2) lock owner
- * 3) lock range start
- * 4) lock range end
+ * 1) lock owner
+ * 2) lock range start
+ * 3) lock range end
  *
  * Obviously, the last two criteria only matter for POSIX locks.
  */
 struct file_lock {
 	struct file_lock *fl_next;	/* singly linked list for this inode  */
+	struct list_head fl_list;	/* link into file_lock_context */
 	struct hlist_node fl_link;	/* node in global lists */
 	struct list_head fl_block;	/* circular list of blocked processes */
 	fl_owner_t fl_owner;
@@ -964,6 +966,16 @@ struct file_lock {
 	} fl_u;
 };
 
+struct file_lock_context {
+	spinlock_t		flc_lock;
+	struct list_head	flc_flock;
+	struct list_head	flc_posix;
+	struct list_head	flc_lease;
+	int			flc_flock_cnt;
+	int			flc_posix_cnt;
+	int			flc_lease_cnt;
+};
+
 /* The following constant reflects the upper bound of the file/locking space */
 #ifndef OFFSET_MAX
 #define INT_LIMIT(x)	(~((x)1 << (sizeof(x)*8 - 1)))
@@ -990,6 +1002,7 @@ extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg);
 extern int fcntl_getlease(struct file *filp);
 
 /* fs/locks.c */
+void locks_free_lock_context(struct file_lock_context *ctx);
 void locks_free_lock(struct file_lock *fl);
 extern void locks_init_lock(struct file_lock *);
 extern struct file_lock * locks_alloc_lock(void);
@@ -1010,7 +1023,7 @@ extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int t
 extern void lease_get_mtime(struct inode *, struct timespec *time);
 extern int generic_setlease(struct file *, long, struct file_lock **, void **priv);
 extern int vfs_setlease(struct file *, long, struct file_lock **, void **);
-extern int lease_modify(struct file_lock **, int, struct list_head *);
+extern int lease_modify(struct file_lock *, int, struct list_head *);
 #else /* !CONFIG_FILE_LOCKING */
 static inline int fcntl_getlk(struct file *file, unsigned int cmd,
 			      struct flock __user *user)
@@ -1047,6 +1060,11 @@ static inline int fcntl_getlease(struct file *filp)
 	return F_UNLCK;
 }
 
+static inline void
+locks_free_lock_context(struct file_lock_context *ctx)
+{
+}
+
 static inline void locks_init_lock(struct file_lock *fl)
 {
 	return;
@@ -1137,7 +1155,7 @@ static inline int vfs_setlease(struct file *filp, long arg,
 	return -EINVAL;
 }
 
-static inline int lease_modify(struct file_lock **before, int arg,
+static inline int lease_modify(struct file_lock *fl, int arg,
 			       struct list_head *dispose)
 {
 	return -EINVAL;
@@ -1959,7 +1977,7 @@ static inline int locks_verify_truncate(struct inode *inode,
 				    struct file *filp,
 				    loff_t size)
 {
-	if (inode->i_flock && mandatory_lock(inode))
+	if (inode->i_flctx && mandatory_lock(inode))
 		return locks_mandatory_area(
 			FLOCK_VERIFY_WRITE, inode, filp,
 			size < inode->i_size ? size : inode->i_size,
@@ -1973,11 +1991,12 @@ static inline int break_lease(struct inode *inode, unsigned int mode)
 {
 	/*
 	 * Since this check is lockless, we must ensure that any refcounts
-	 * taken are done before checking inode->i_flock. Otherwise, we could
-	 * end up racing with tasks trying to set a new lease on this file.
+	 * taken are done before checking i_flctx->flc_lease. Otherwise, we
+	 * could end up racing with tasks trying to set a new lease on this
+	 * file.
 	 */
 	smp_mb();
-	if (inode->i_flock)
+	if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
 		return __break_lease(inode, mode, FL_LEASE);
 	return 0;
 }
@@ -1986,11 +2005,12 @@ static inline int break_deleg(struct inode *inode, unsigned int mode)
 {
 	/*
 	 * Since this check is lockless, we must ensure that any refcounts
-	 * taken are done before checking inode->i_flock. Otherwise, we could
-	 * end up racing with tasks trying to set a new lease on this file.
+	 * taken are done before checking i_flctx->flc_lease. Otherwise, we
+	 * could end up racing with tasks trying to set a new lease on this
+	 * file.
 	 */
 	smp_mb();
-	if (inode->i_flock)
+	if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
 		return __break_lease(inode, mode, FL_DELEG);
 	return 0;
 }