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

4 files changed, 92 insertions, 48 deletions

diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 7f3f60641344..8cdb2b28a104 100644
--- a/fs/nfs/delegation.c
+++ b/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;
 }
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 5194933ed419..a3bb22ab68c5 100644
--- a/fs/nfs/nfs4state.c
+++ b/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;
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 2b5e769beb16..29c7f33c9cf1 100644
--- a/fs/nfs/pagelist.c
+++ b/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;
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index af3af685a9e3..4ae66f416eb9 100644
--- a/fs/nfs/write.c
+++ b/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 @@ out:
 	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 @@ out:
  */
 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;
 }
 
 /*