Merge tag 'locks-v4.21-1' of git://git.kernel.org/pub/scm/linux/kernel/git/jlayton/linux

Pull file locking updates from Jeff Layton:
 "The main change in this set is Neil Brown's work to reduce the
  thundering herd problem when a heavily-contended file lock is
  released.

  Previously we'd always wake up all waiters when this occurred. With
  this set, we'll now we only wake up waiters that were blocked on the
  range being released"

* tag 'locks-v4.21-1' of git://git.kernel.org/pub/scm/linux/kernel/git/jlayton/linux:
  locks: Use inode_is_open_for_write
  fs/locks: remove unnecessary white space.
  fs/locks: merge posix_unblock_lock() and locks_delete_block()
  fs/locks: create a tree of dependent requests.
  fs/locks: change all *_conflict() functions to return bool.
  fs/locks: always delete_block after waiting.
  fs/locks: allow a lock request to block other requests.
  fs/locks: use properly initialized file_lock when unlocking.
  ocfs2: properly initial file_lock used for unlock.
  gfs2: properly initial file_lock used for unlock.
  NFS: use locks_copy_lock() to copy locks.
  fs/locks: split out __locks_wake_up_blocks().
  fs/locks: rename some lists and pointers.

fs/cifs/file.c

@@ -1103,10 +1103,10 @@ cifs_posix_lock_set(struct file *file, struct file_lock *flock)
 	rc = posix_lock_file(file, flock, NULL);
 	up_write(&cinode->lock_sem);
 	if (rc == FILE_LOCK_DEFERRED) {
-		rc = wait_event_interruptible(flock->fl_wait, !flock->fl_next);
+		rc = wait_event_interruptible(flock->fl_wait, !flock->fl_blocker);
 		if (!rc)
 			goto try_again;
-		posix_unblock_lock(flock);
+		locks_delete_block(flock);
 	}
 	return rc;
 }

fs/gfs2/file.c

@@ -1199,13 +1199,13 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl)
 	mutex_lock(&fp->f_fl_mutex);
 
 	if (gfs2_holder_initialized(fl_gh)) {
+		struct file_lock request;
 		if (fl_gh->gh_state == state)
 			goto out;
-		locks_lock_file_wait(file,
-				     &(struct file_lock) {
-					     .fl_type = F_UNLCK,
-					     .fl_flags = FL_FLOCK
-				     });
+		locks_init_lock(&request);
+		request.fl_type = F_UNLCK;
+		request.fl_flags = FL_FLOCK;
+		locks_lock_file_wait(file, &request);
 		gfs2_glock_dq(fl_gh);
 		gfs2_holder_reinit(state, flags, fl_gh);
 	} else {

fs/lockd/svclock.c

@@ -276,7 +276,7 @@ static int nlmsvc_unlink_block(struct nlm_block *block)
 	dprintk("lockd: unlinking block %p...\n", block);
 
 	/* Remove block from list */
-	status = posix_unblock_lock(&block->b_call->a_args.lock.fl);
+	status = locks_delete_block(&block->b_call->a_args.lock.fl);
 	nlmsvc_remove_block(block);
 	return status;
 }

fs/nfs/nfs4proc.c

@@ -6311,7 +6311,8 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl,
 	/* Ensure we don't close file until we're done freeing locks! */
 	p->ctx = get_nfs_open_context(ctx);
 	p->l_ctx = nfs_get_lock_context(ctx);
-	memcpy(&p->fl, fl, sizeof(p->fl));
+	locks_init_lock(&p->fl);
+	locks_copy_lock(&p->fl, fl);
 	p->server = NFS_SERVER(inode);
 	return p;
 }
@@ -6533,7 +6534,8 @@ static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl,
 	p->server = server;
 	refcount_inc(&lsp->ls_count);
 	p->ctx = get_nfs_open_context(ctx);
-	memcpy(&p->fl, fl, sizeof(p->fl));
+	locks_init_lock(&p->fl);
+	locks_copy_lock(&p->fl, fl);
 	return p;
 out_free_seqid:
 	nfs_free_seqid(p->arg.open_seqid);

fs/nfsd/nfs4state.c

@@ -238,7 +238,7 @@ find_blocked_lock(struct nfs4_lockowner *lo, struct knfsd_fh *fh,
 	}
 	spin_unlock(&nn->blocked_locks_lock);
 	if (found)
-		posix_unblock_lock(&found->nbl_lock);
+		locks_delete_block(&found->nbl_lock);
 	return found;
 }
 
@@ -293,7 +293,7 @@ remove_blocked_locks(struct nfs4_lockowner *lo)
 		nbl = list_first_entry(&reaplist, struct nfsd4_blocked_lock,
 					nbl_lru);
 		list_del_init(&nbl->nbl_lru);
-		posix_unblock_lock(&nbl->nbl_lock);
+		locks_delete_block(&nbl->nbl_lock);
 		free_blocked_lock(nbl);
 	}
 }
@@ -4863,7 +4863,7 @@ nfs4_laundromat(struct nfsd_net *nn)
 		nbl = list_first_entry(&reaplist,
 					struct nfsd4_blocked_lock, nbl_lru);
 		list_del_init(&nbl->nbl_lru);
-		posix_unblock_lock(&nbl->nbl_lock);
+		locks_delete_block(&nbl->nbl_lock);
 		free_blocked_lock(nbl);
 	}
 out:

fs/ocfs2/locks.c

@@ -52,6 +52,7 @@ static int ocfs2_do_flock(struct file *file, struct inode *inode,
 	if (lockres->l_flags & OCFS2_LOCK_ATTACHED &&
 	    lockres->l_level > LKM_NLMODE) {
 		int old_level = 0;
+		struct file_lock request;
 
 		if (lockres->l_level == LKM_EXMODE)
 			old_level = 1;
@@ -66,11 +67,10 @@ static int ocfs2_do_flock(struct file *file, struct inode *inode,
 		 * level.
 		 */
 
-		locks_lock_file_wait(file,
-				&(struct file_lock) {
-					.fl_type = F_UNLCK,
-					.fl_flags = FL_FLOCK
-				});
+		locks_init_lock(&request);
+		request.fl_type = F_UNLCK;
+		request.fl_flags = FL_FLOCK;
+		locks_lock_file_wait(file, &request);
 
 		ocfs2_file_unlock(file);
 	}

include/linux/fs.h

@@ -1044,10 +1044,15 @@ bool opens_in_grace(struct net *);
  * 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 file_lock *fl_blocker;	/* The lock, that is blocking us */
 	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 */
+	struct list_head fl_blocked_requests;	/* list of requests with
+						 * ->fl_blocker pointing here
+						 */
+	struct list_head fl_blocked_member;	/* node in
+						 * ->fl_blocker->fl_blocked_requests
+						 */
 	fl_owner_t fl_owner;
 	unsigned int fl_flags;
 	unsigned char fl_type;
@@ -1119,7 +1124,7 @@ extern void locks_remove_file(struct file *);
 extern void locks_release_private(struct file_lock *);
 extern void posix_test_lock(struct file *, struct file_lock *);
 extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *);
-extern int posix_unblock_lock(struct file_lock *);
+extern int locks_delete_block(struct file_lock *);
 extern int vfs_test_lock(struct file *, struct file_lock *);
 extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *);
 extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
@@ -1209,7 +1214,7 @@ static inline int posix_lock_file(struct file *filp, struct file_lock *fl,
 	return -ENOLCK;
 }
 
-static inline int posix_unblock_lock(struct file_lock *waiter)
+static inline int locks_delete_block(struct file_lock *waiter)
 {
 	return -ENOENT;
 }

include/trace/events/filelock.h

@@ -68,7 +68,7 @@ DECLARE_EVENT_CLASS(filelock_lock,
 		__field(struct file_lock *, fl)
 		__field(unsigned long, i_ino)
 		__field(dev_t, s_dev)
-		__field(struct file_lock *, fl_next)
+		__field(struct file_lock *, fl_blocker)
 		__field(fl_owner_t, fl_owner)
 		__field(unsigned int, fl_pid)
 		__field(unsigned int, fl_flags)
@@ -82,7 +82,7 @@ DECLARE_EVENT_CLASS(filelock_lock,
 		__entry->fl = fl ? fl : NULL;
 		__entry->s_dev = inode->i_sb->s_dev;
 		__entry->i_ino = inode->i_ino;
-		__entry->fl_next = fl ? fl->fl_next : NULL;
+		__entry->fl_blocker = fl ? fl->fl_blocker : NULL;
 		__entry->fl_owner = fl ? fl->fl_owner : NULL;
 		__entry->fl_pid = fl ? fl->fl_pid : 0;
 		__entry->fl_flags = fl ? fl->fl_flags : 0;
@@ -92,9 +92,9 @@ DECLARE_EVENT_CLASS(filelock_lock,
 		__entry->ret = ret;
 	),
 
-	TP_printk("fl=0x%p dev=0x%x:0x%x ino=0x%lx fl_next=0x%p fl_owner=0x%p fl_pid=%u fl_flags=%s fl_type=%s fl_start=%lld fl_end=%lld ret=%d",
+	TP_printk("fl=0x%p dev=0x%x:0x%x ino=0x%lx fl_blocker=0x%p fl_owner=0x%p fl_pid=%u fl_flags=%s fl_type=%s fl_start=%lld fl_end=%lld ret=%d",
 		__entry->fl, MAJOR(__entry->s_dev), MINOR(__entry->s_dev),
-		__entry->i_ino, __entry->fl_next, __entry->fl_owner,
+		__entry->i_ino, __entry->fl_blocker, __entry->fl_owner,
 		__entry->fl_pid, show_fl_flags(__entry->fl_flags),
 		show_fl_type(__entry->fl_type),
 		__entry->fl_start, __entry->fl_end, __entry->ret)
@@ -125,7 +125,7 @@ DECLARE_EVENT_CLASS(filelock_lease,
 		__field(struct file_lock *, fl)
 		__field(unsigned long, i_ino)
 		__field(dev_t, s_dev)
-		__field(struct file_lock *, fl_next)
+		__field(struct file_lock *, fl_blocker)
 		__field(fl_owner_t, fl_owner)
 		__field(unsigned int, fl_flags)
 		__field(unsigned char, fl_type)
@@ -137,7 +137,7 @@ DECLARE_EVENT_CLASS(filelock_lease,
 		__entry->fl = fl ? fl : NULL;
 		__entry->s_dev = inode->i_sb->s_dev;
 		__entry->i_ino = inode->i_ino;
-		__entry->fl_next = fl ? fl->fl_next : NULL;
+		__entry->fl_blocker = fl ? fl->fl_blocker : NULL;
 		__entry->fl_owner = fl ? fl->fl_owner : NULL;
 		__entry->fl_flags = fl ? fl->fl_flags : 0;
 		__entry->fl_type = fl ? fl->fl_type : 0;
@@ -145,9 +145,9 @@ DECLARE_EVENT_CLASS(filelock_lease,
 		__entry->fl_downgrade_time = fl ? fl->fl_downgrade_time : 0;
 	),
 
-	TP_printk("fl=0x%p dev=0x%x:0x%x ino=0x%lx fl_next=0x%p fl_owner=0x%p fl_flags=%s fl_type=%s fl_break_time=%lu fl_downgrade_time=%lu",
+	TP_printk("fl=0x%p dev=0x%x:0x%x ino=0x%lx fl_blocker=0x%p fl_owner=0x%p fl_flags=%s fl_type=%s fl_break_time=%lu fl_downgrade_time=%lu",
 		__entry->fl, MAJOR(__entry->s_dev), MINOR(__entry->s_dev),
-		__entry->i_ino, __entry->fl_next, __entry->fl_owner,
+		__entry->i_ino, __entry->fl_blocker, __entry->fl_owner,
 		show_fl_flags(__entry->fl_flags),
 		show_fl_type(__entry->fl_type),
 		__entry->fl_break_time, __entry->fl_downgrade_time)