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;
@@ -279,33 +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;
 }
 

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 (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;
 }

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

@@ -1366,49 +1366,55 @@ 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:
-				break;
-			case -ESTALE:
-			case -NFS4ERR_ADMIN_REVOKED:
-			case -NFS4ERR_STALE_STATEID:
-			case -NFS4ERR_BAD_STATEID:
-			case -NFS4ERR_EXPIRED:
-			case -NFS4ERR_NO_GRACE:
-			case -NFS4ERR_STALE_CLIENTID:
-			case -NFS4ERR_BADSESSION:
-			case -NFS4ERR_BADSLOT:
-			case -NFS4ERR_BAD_HIGH_SLOT:
-			case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
-				goto out;
-			default:
-				printk(KERN_ERR "NFS: %s: unhandled error %d\n",
-					 __func__, status);
-			case -ENOMEM:
-			case -NFS4ERR_DENIED:
-			case -NFS4ERR_RECLAIM_BAD:
-			case -NFS4ERR_RECLAIM_CONFLICT:
-				/* kill_proc(fl->fl_pid, SIGLOST, 1); */
-				status = 0;
+		case 0:
+			break;
+		case -ESTALE:
+		case -NFS4ERR_ADMIN_REVOKED:
+		case -NFS4ERR_STALE_STATEID:
+		case -NFS4ERR_BAD_STATEID:
+		case -NFS4ERR_EXPIRED:
+		case -NFS4ERR_NO_GRACE:
+		case -NFS4ERR_STALE_CLIENTID:
+		case -NFS4ERR_BADSESSION:
+		case -NFS4ERR_BADSLOT:
+		case -NFS4ERR_BAD_HIGH_SLOT:
+		case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+			goto out;
+		default:
+			pr_err("NFS: %s: unhandled error %d\n",
+					__func__, status);
+		case -ENOMEM:
+		case -NFS4ERR_DENIED:
+		case -NFS4ERR_RECLAIM_BAD:
+		case -NFS4ERR_RECLAIM_CONFLICT:
+			/* 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;
-	return 0;
+	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) {
-			status = true;
-			break;
+	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(&flctx->flc_lock);
 	}
-	spin_unlock(&inode->i_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;
 }