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

12 files changed, 474 insertions, 389 deletions

diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index c35c5c614e38..06ea5cd05cd9 100644
--- a/fs/ceph/locks.c
+++ b/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;
@@ -279,33 +278,34 @@ 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) {
-			++seen_fcntl;
-			if (seen_fcntl > num_fcntl_locks) {
-				err = -ENOSPC;
-				goto fail;
-			}
-			err = lock_to_ceph_filelock(lock, &flocks[l]);
-			if (err)
-				goto fail;
-			++l;
+	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;
+			goto fail;
 		}
+		err = lock_to_ceph_filelock(lock, &flocks[l]);
+		if (err)
+			goto fail;
+		++l;
 	}
-	for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
-		if (lock->fl_flags & FL_FLOCK) {
-			++seen_flock;
-			if (seen_flock > num_flock_locks) {
-				err = -ENOSPC;
-				goto fail;
-			}
-			err = lock_to_ceph_filelock(lock, &flocks[l]);
-			if (err)
-				goto fail;
-			++l;
+	list_for_each_entry(lock, &ctx->flc_flock, fl_list) {
+		++seen_flock;
+		if (seen_flock > num_flock_locks) {
+			err = -ENOSPC;
+			goto fail;
 		}
+		err = lock_to_ceph_filelock(lock, &flocks[l]);
+		if (err)
+			goto fail;
+		++l;
 	}
 fail:
+	spin_unlock(&ctx->flc_lock);
 	return err;
 }
 
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index d2171f4a6980..5f62fb7a5d0a 100644
--- a/fs/ceph/mds_client.c
+++ b/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)
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 74f12877493a..c1a86764bbf7 100644
--- a/fs/cifs/file.c
+++ b/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;
diff --git a/fs/inode.c b/fs/inode.c
index aa149e7262ac..f30872ade6d7 100644
--- a/fs/inode.c
+++ b/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);
diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c
index d12ff4e2dbe7..665ef5a05183 100644
--- a/fs/lockd/svcsubs.c
+++ b/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 @@ again:
 		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 @@ again:
 			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 (fl->fl_lmops == &nlmsvc_lock_operations) {
-			spin_unlock(&inode->i_lock);
-			return 1;
+	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(&flctx->flc_lock);
+				return 1;
+			}
 		}
+		spin_unlock(&flctx->flc_lock);
 	}
-	spin_unlock(&inode->i_lock);
 	file->f_locks = 0;
 	return 0;
 }
diff --git a/fs/locks.c b/fs/locks.c
index 59e2f905e4ff..4d0d41163a50 100644
--- a/fs/locks.c
+++ b/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,
-			      struct list_head *dispose)
+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;
-	}
-	if (cfl) {
-		locks_copy_conflock(fl, cfl);
-		if (cfl->fl_nspid)
-			fl->fl_pid = pid_vnr(cfl->fl_nspid);
-	} else
+	ctx = inode->i_flctx;
+	if (!ctx || list_empty_careful(&ctx->flc_posix)) {
 		fl->fl_type = F_UNLCK;
-	spin_unlock(&inode->i_lock);
+		return;
+	}
+
+	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);
+			goto out;
+		}
+	}
+	fl->fl_type = F_UNLCK;
+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 @@ find_conflict:
 	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 @@ out:
 
 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