1 files changed, 99 insertions, 107 deletions

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index c06129cffba9..2bfbcf28b1bd 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -598,22 +598,6 @@ xfs_lock_two_inodes(
 	}
 }
 
-void
-__xfs_iflock(
-	struct xfs_inode	*ip)
-{
-	wait_queue_head_t *wq = bit_waitqueue(&ip->i_flags, __XFS_IFLOCK_BIT);
-	DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_IFLOCK_BIT);
-
-	do {
-		prepare_to_wait_exclusive(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
-		if (xfs_isiflocked(ip))
-			io_schedule();
-	} while (!xfs_iflock_nowait(ip));
-
-	finish_wait(wq, &wait.wq_entry);
-}
-
 STATIC uint
 _xfs_dic2xflags(
 	uint16_t		di_flags,
@@ -714,6 +698,68 @@ out_unlock:
 	return error;
 }
 
+/* Propagate di_flags from a parent inode to a child inode. */
+static void
+xfs_inode_inherit_flags(
+	struct xfs_inode	*ip,
+	const struct xfs_inode	*pip)
+{
+	unsigned int		di_flags = 0;
+	umode_t			mode = VFS_I(ip)->i_mode;
+
+	if (S_ISDIR(mode)) {
+		if (pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT)
+			di_flags |= XFS_DIFLAG_RTINHERIT;
+		if (pip->i_d.di_flags & XFS_DIFLAG_EXTSZINHERIT) {
+			di_flags |= XFS_DIFLAG_EXTSZINHERIT;
+			ip->i_d.di_extsize = pip->i_d.di_extsize;
+		}
+		if (pip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)
+			di_flags |= XFS_DIFLAG_PROJINHERIT;
+	} else if (S_ISREG(mode)) {
+		if ((pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT) &&
+		    xfs_sb_version_hasrealtime(&ip->i_mount->m_sb))
+			di_flags |= XFS_DIFLAG_REALTIME;
+		if (pip->i_d.di_flags & XFS_DIFLAG_EXTSZINHERIT) {
+			di_flags |= XFS_DIFLAG_EXTSIZE;
+			ip->i_d.di_extsize = pip->i_d.di_extsize;
+		}
+	}
+	if ((pip->i_d.di_flags & XFS_DIFLAG_NOATIME) &&
+	    xfs_inherit_noatime)
+		di_flags |= XFS_DIFLAG_NOATIME;
+	if ((pip->i_d.di_flags & XFS_DIFLAG_NODUMP) &&
+	    xfs_inherit_nodump)
+		di_flags |= XFS_DIFLAG_NODUMP;
+	if ((pip->i_d.di_flags & XFS_DIFLAG_SYNC) &&
+	    xfs_inherit_sync)
+		di_flags |= XFS_DIFLAG_SYNC;
+	if ((pip->i_d.di_flags & XFS_DIFLAG_NOSYMLINKS) &&
+	    xfs_inherit_nosymlinks)
+		di_flags |= XFS_DIFLAG_NOSYMLINKS;
+	if ((pip->i_d.di_flags & XFS_DIFLAG_NODEFRAG) &&
+	    xfs_inherit_nodefrag)
+		di_flags |= XFS_DIFLAG_NODEFRAG;
+	if (pip->i_d.di_flags & XFS_DIFLAG_FILESTREAM)
+		di_flags |= XFS_DIFLAG_FILESTREAM;
+
+	ip->i_d.di_flags |= di_flags;
+}
+
+/* Propagate di_flags2 from a parent inode to a child inode. */
+static void
+xfs_inode_inherit_flags2(
+	struct xfs_inode	*ip,
+	const struct xfs_inode	*pip)
+{
+	if (pip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) {
+		ip->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
+		ip->i_d.di_cowextsize = pip->i_d.di_cowextsize;
+	}
+	if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX)
+		ip->i_d.di_flags2 |= XFS_DIFLAG2_DAX;
+}
+
 /*
  * Allocate an inode on disk and return a copy of its in-core version.
  * The in-core inode is locked exclusively.  Set mode, nlink, and rdev
@@ -840,7 +886,7 @@ xfs_ialloc(
 
 	if (xfs_sb_version_has_v3inode(&mp->m_sb)) {
 		inode_set_iversion(inode, 1);
-		ip->i_d.di_flags2 = 0;
+		ip->i_d.di_flags2 = mp->m_ino_geo.new_diflags2;
 		ip->i_d.di_cowextsize = 0;
 		ip->i_d.di_crtime = tv;
 	}
@@ -857,54 +903,10 @@ xfs_ialloc(
 		break;
 	case S_IFREG:
 	case S_IFDIR:
-		if (pip && (pip->i_d.di_flags & XFS_DIFLAG_ANY)) {
-			uint		di_flags = 0;
-
-			if (S_ISDIR(mode)) {
-				if (pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT)
-					di_flags |= XFS_DIFLAG_RTINHERIT;
-				if (pip->i_d.di_flags & XFS_DIFLAG_EXTSZINHERIT) {
-					di_flags |= XFS_DIFLAG_EXTSZINHERIT;
-					ip->i_d.di_extsize = pip->i_d.di_extsize;
-				}
-				if (pip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)
-					di_flags |= XFS_DIFLAG_PROJINHERIT;
-			} else if (S_ISREG(mode)) {
-				if (pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT)
-					di_flags |= XFS_DIFLAG_REALTIME;
-				if (pip->i_d.di_flags & XFS_DIFLAG_EXTSZINHERIT) {
-					di_flags |= XFS_DIFLAG_EXTSIZE;
-					ip->i_d.di_extsize = pip->i_d.di_extsize;
-				}
-			}
-			if ((pip->i_d.di_flags & XFS_DIFLAG_NOATIME) &&
-			    xfs_inherit_noatime)
-				di_flags |= XFS_DIFLAG_NOATIME;
-			if ((pip->i_d.di_flags & XFS_DIFLAG_NODUMP) &&
-			    xfs_inherit_nodump)
-				di_flags |= XFS_DIFLAG_NODUMP;
-			if ((pip->i_d.di_flags & XFS_DIFLAG_SYNC) &&
-			    xfs_inherit_sync)
-				di_flags |= XFS_DIFLAG_SYNC;
-			if ((pip->i_d.di_flags & XFS_DIFLAG_NOSYMLINKS) &&
-			    xfs_inherit_nosymlinks)
-				di_flags |= XFS_DIFLAG_NOSYMLINKS;
-			if ((pip->i_d.di_flags & XFS_DIFLAG_NODEFRAG) &&
-			    xfs_inherit_nodefrag)
-				di_flags |= XFS_DIFLAG_NODEFRAG;
-			if (pip->i_d.di_flags & XFS_DIFLAG_FILESTREAM)
-				di_flags |= XFS_DIFLAG_FILESTREAM;
-
-			ip->i_d.di_flags |= di_flags;
-		}
-		if (pip && (pip->i_d.di_flags2 & XFS_DIFLAG2_ANY)) {
-			if (pip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) {
-				ip->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
-				ip->i_d.di_cowextsize = pip->i_d.di_cowextsize;
-			}
-			if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX)
-				ip->i_d.di_flags2 |= XFS_DIFLAG2_DAX;
-		}
+		if (pip && (pip->i_d.di_flags & XFS_DIFLAG_ANY))
+			xfs_inode_inherit_flags(ip, pip);
+		if (pip && (pip->i_d.di_flags2 & XFS_DIFLAG2_ANY))
+			xfs_inode_inherit_flags2(ip, pip);
 		/* FALLTHROUGH */
 	case S_IFLNK:
 		ip->i_df.if_format = XFS_DINODE_FMT_EXTENTS;
@@ -1532,17 +1534,10 @@ xfs_itruncate_extents_flags(
 		if (error)
 			goto out;
 
-		/*
-		 * Duplicate the transaction that has the permanent
-		 * reservation and commit the old transaction.
-		 */
+		/* free the just unmapped extents */
 		error = xfs_defer_finish(&tp);
 		if (error)
 			goto out;
-
-		error = xfs_trans_roll_inode(&tp, ip);
-		if (error)
-			goto out;
 	}
 
 	if (whichfork == XFS_DATA_FORK) {
@@ -2531,11 +2526,8 @@ retry:
 	 * valid, the wrong inode or stale.
 	 */
 	spin_lock(&ip->i_flags_lock);
-	if (ip->i_ino != inum || __xfs_iflags_test(ip, XFS_ISTALE)) {
-		spin_unlock(&ip->i_flags_lock);
-		rcu_read_unlock();
-		return;
-	}
+	if (ip->i_ino != inum || __xfs_iflags_test(ip, XFS_ISTALE))
+		goto out_iflags_unlock;
 
 	/*
 	 * Don't try to lock/unlock the current inode, but we _cannot_ skip the
@@ -2552,16 +2544,14 @@ retry:
 		}
 	}
 	ip->i_flags |= XFS_ISTALE;
-	spin_unlock(&ip->i_flags_lock);
-	rcu_read_unlock();
 
 	/*
-	 * If we can't get the flush lock, the inode is already attached.  All
+	 * If the inode is flushing, it is already attached to the buffer.  All
 	 * we needed to do here is mark the inode stale so buffer IO completion
 	 * will remove it from the AIL.
 	 */
 	iip = ip->i_itemp;
-	if (!xfs_iflock_nowait(ip)) {
+	if (__xfs_iflags_test(ip, XFS_IFLUSHING)) {
 		ASSERT(!list_empty(&iip->ili_item.li_bio_list));
 		ASSERT(iip->ili_last_fields);
 		goto out_iunlock;
@@ -2573,10 +2563,12 @@ retry:
 	 * commit as the flock synchronises removal of the inode from the
 	 * cluster buffer against inode reclaim.
 	 */
-	if (!iip || list_empty(&iip->ili_item.li_bio_list)) {
-		xfs_ifunlock(ip);
+	if (!iip || list_empty(&iip->ili_item.li_bio_list))
 		goto out_iunlock;
-	}
+
+	__xfs_iflags_set(ip, XFS_IFLUSHING);
+	spin_unlock(&ip->i_flags_lock);
+	rcu_read_unlock();
 
 	/* we have a dirty inode in memory that has not yet been flushed. */
 	spin_lock(&iip->ili_lock);
@@ -2586,9 +2578,16 @@ retry:
 	spin_unlock(&iip->ili_lock);
 	ASSERT(iip->ili_last_fields);
 
+	if (ip != free_ip)
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	return;
+
 out_iunlock:
 	if (ip != free_ip)
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+out_iflags_unlock:
+	spin_unlock(&ip->i_flags_lock);
+	rcu_read_unlock();
 }
 
 /*
@@ -2631,8 +2630,9 @@ xfs_ifree_cluster(
 
 		/*
 		 * We obtain and lock the backing buffer first in the process
-		 * here, as we have to ensure that any dirty inode that we
-		 * can't get the flush lock on is attached to the buffer.
+		 * here to ensure dirty inodes attached to the buffer remain in
+		 * the flushing state while we mark them stale.
+		 *
 		 * If we scan the in-memory inodes first, then buffer IO can
 		 * complete before we get a lock on it, and hence we may fail
 		 * to mark all the active inodes on the buffer stale.
@@ -2717,7 +2717,7 @@ xfs_ifree(
 
 	VFS_I(ip)->i_mode = 0;		/* mark incore inode as free */
 	ip->i_d.di_flags = 0;
-	ip->i_d.di_flags2 = 0;
+	ip->i_d.di_flags2 = ip->i_mount->m_ino_geo.new_diflags2;
 	ip->i_d.di_dmevmask = 0;
 	ip->i_d.di_forkoff = 0;		/* mark the attr fork not in use */
 	ip->i_df.if_format = XFS_DINODE_FMT_EXTENTS;
@@ -3443,7 +3443,7 @@ xfs_iflush(
 	int			error;
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
-	ASSERT(xfs_isiflocked(ip));
+	ASSERT(xfs_iflags_test(ip, XFS_IFLUSHING));
 	ASSERT(ip->i_df.if_format != XFS_DINODE_FMT_BTREE ||
 	       ip->i_df.if_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK));
 	ASSERT(iip->ili_item.li_buf == bp);
@@ -3553,8 +3553,8 @@ xfs_iflush(
 	 *
 	 * What we do is move the bits to the ili_last_fields field.  When
 	 * logging the inode, these bits are moved back to the ili_fields field.
-	 * In the xfs_iflush_done() routine we clear ili_last_fields, since we
-	 * know that the information those bits represent is permanently on
+	 * In the xfs_buf_inode_iodone() routine we clear ili_last_fields, since
+	 * we know that the information those bits represent is permanently on
 	 * disk.  As long as the flush completes before the inode is logged
 	 * again, then both ili_fields and ili_last_fields will be cleared.
 	 */
@@ -3568,7 +3568,7 @@ flush_out:
 
 	/*
 	 * Store the current LSN of the inode so that we can tell whether the
-	 * item has moved in the AIL from xfs_iflush_done().
+	 * item has moved in the AIL from xfs_buf_inode_iodone().
 	 */
 	xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn,
 				&iip->ili_item.li_lsn);
@@ -3613,7 +3613,7 @@ xfs_iflush_cluster(
 		/*
 		 * Quick and dirty check to avoid locks if possible.
 		 */
-		if (__xfs_iflags_test(ip, XFS_IRECLAIM | XFS_IFLOCK))
+		if (__xfs_iflags_test(ip, XFS_IRECLAIM | XFS_IFLUSHING))
 			continue;
 		if (xfs_ipincount(ip))
 			continue;
@@ -3627,7 +3627,7 @@ xfs_iflush_cluster(
 		 */
 		spin_lock(&ip->i_flags_lock);
 		ASSERT(!__xfs_iflags_test(ip, XFS_ISTALE));
-		if (__xfs_iflags_test(ip, XFS_IRECLAIM | XFS_IFLOCK)) {
+		if (__xfs_iflags_test(ip, XFS_IRECLAIM | XFS_IFLUSHING)) {
 			spin_unlock(&ip->i_flags_lock);
 			continue;
 		}
@@ -3635,24 +3635,17 @@ xfs_iflush_cluster(
 		/*
 		 * ILOCK will pin the inode against reclaim and prevent
 		 * concurrent transactions modifying the inode while we are
-		 * flushing the inode.
+		 * flushing the inode. If we get the lock, set the flushing
+		 * state before we drop the i_flags_lock.
 		 */
 		if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) {
 			spin_unlock(&ip->i_flags_lock);
 			continue;
 		}
+		__xfs_iflags_set(ip, XFS_IFLUSHING);
 		spin_unlock(&ip->i_flags_lock);
 
 		/*
-		 * Skip inodes that are already flush locked as they have
-		 * already been written to the buffer.
-		 */
-		if (!xfs_iflock_nowait(ip)) {
-			xfs_iunlock(ip, XFS_ILOCK_SHARED);
-			continue;
-		}
-
-		/*
 		 * Abort flushing this inode if we are shut down because the
 		 * inode may not currently be in the AIL. This can occur when
 		 * log I/O failure unpins the inode without inserting into the
@@ -3661,7 +3654,6 @@ xfs_iflush_cluster(
 		 */
 		if (XFS_FORCED_SHUTDOWN(mp)) {
 			xfs_iunpin_wait(ip);
-			/* xfs_iflush_abort() drops the flush lock */
 			xfs_iflush_abort(ip);
 			xfs_iunlock(ip, XFS_ILOCK_SHARED);
 			error = -EIO;
@@ -3670,7 +3662,7 @@ xfs_iflush_cluster(
 
 		/* don't block waiting on a log force to unpin dirty inodes */
 		if (xfs_ipincount(ip)) {
-			xfs_ifunlock(ip);
+			xfs_iflags_clear(ip, XFS_IFLUSHING);
 			xfs_iunlock(ip, XFS_ILOCK_SHARED);
 			continue;
 		}
@@ -3678,7 +3670,7 @@ xfs_iflush_cluster(
 		if (!xfs_inode_clean(ip))
 			error = xfs_iflush(ip, bp);
 		else
-			xfs_ifunlock(ip);
+			xfs_iflags_clear(ip, XFS_IFLUSHING);
 		xfs_iunlock(ip, XFS_ILOCK_SHARED);
 		if (error)
 			break;