Merge branch 'xfs-4.10-misc-fixes-4' into for-next

Documentation/filesystems/xfs.txt

@@ -51,13 +51,6 @@ default behaviour.
 	CRC enabled filesystems always use the attr2 format, and so
 	will reject the noattr2 mount option if it is set.
 
-  barrier (*)
-  nobarrier
-	Enables/disables the use of block layer write barriers for
-	writes into the journal and for data integrity operations.
-	This allows for drive level write caching to be enabled, for
-	devices that support write barriers.
-
   discard
   nodiscard (*)
 	Enable/disable the issuing of commands to let the block
@@ -228,7 +221,10 @@ default behaviour.
 Deprecated Mount Options
 ========================
 
-None at present.
+  Name				Removal Schedule
+  ----				----------------
+  barrier			no earlier than v4.15
+  nobarrier			no earlier than v4.15
 
 
 Removed Mount Options

fs/xfs/libxfs/xfs_alloc_btree.c

@@ -421,7 +421,7 @@ xfs_allocbt_init_cursor(
 
 	ASSERT(btnum == XFS_BTNUM_BNO || btnum == XFS_BTNUM_CNT);
 
-	cur = kmem_zone_zalloc(xfs_btree_cur_zone, KM_SLEEP);
+	cur = kmem_zone_zalloc(xfs_btree_cur_zone, KM_NOFS);
 
 	cur->bc_tp = tp;
 	cur->bc_mp = mp;

fs/xfs/libxfs/xfs_attr_leaf.c

@@ -253,6 +253,7 @@ xfs_attr3_leaf_verify(
 {
 	struct xfs_mount	*mp = bp->b_target->bt_mount;
 	struct xfs_attr_leafblock *leaf = bp->b_addr;
+	struct xfs_perag *pag = bp->b_pag;
 	struct xfs_attr3_icleaf_hdr ichdr;
 
 	xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr, leaf);
@@ -273,7 +274,12 @@ xfs_attr3_leaf_verify(
 		if (ichdr.magic != XFS_ATTR_LEAF_MAGIC)
 			return false;
 	}
-	if (ichdr.count == 0)
+	/*
+	 * In recovery there is a transient state where count == 0 is valid
+	 * because we may have transitioned an empty shortform attr to a leaf
+	 * if the attr didn't fit in shortform.
+	 */
+	if (pag && pag->pagf_init && ichdr.count == 0)
 		return false;
 
 	/* XXX: need to range check rest of attr header values */

fs/xfs/libxfs/xfs_bmap_btree.c

@@ -796,7 +796,7 @@ xfs_bmbt_init_cursor(
 	struct xfs_btree_cur	*cur;
 	ASSERT(whichfork != XFS_COW_FORK);
 
-	cur = kmem_zone_zalloc(xfs_btree_cur_zone, KM_SLEEP);
+	cur = kmem_zone_zalloc(xfs_btree_cur_zone, KM_NOFS);
 
 	cur->bc_tp = tp;
 	cur->bc_mp = mp;

fs/xfs/libxfs/xfs_ialloc_btree.c

@@ -357,7 +357,7 @@ xfs_inobt_init_cursor(
 	struct xfs_agi		*agi = XFS_BUF_TO_AGI(agbp);
 	struct xfs_btree_cur	*cur;
 
-	cur = kmem_zone_zalloc(xfs_btree_cur_zone, KM_SLEEP);
+	cur = kmem_zone_zalloc(xfs_btree_cur_zone, KM_NOFS);
 
 	cur->bc_tp = tp;
 	cur->bc_mp = mp;

fs/xfs/xfs_buf.c

@@ -1737,8 +1737,7 @@ xfs_free_buftarg(
 	percpu_counter_destroy(&btp->bt_io_count);
 	list_lru_destroy(&btp->bt_lru);
 
-	if (mp->m_flags & XFS_MOUNT_BARRIER)
-		xfs_blkdev_issue_flush(btp);
+	xfs_blkdev_issue_flush(btp);
 
 	kmem_free(btp);
 }

fs/xfs/xfs_file.c

@@ -149,19 +149,16 @@ xfs_file_fsync(
 
 	xfs_iflags_clear(ip, XFS_ITRUNCATED);
 
-	if (mp->m_flags & XFS_MOUNT_BARRIER) {
-		/*
-		 * If we have an RT and/or log subvolume we need to make sure
-		 * to flush the write cache the device used for file data
-		 * first.  This is to ensure newly written file data make
-		 * it to disk before logging the new inode size in case of
-		 * an extending write.
-		 */
-		if (XFS_IS_REALTIME_INODE(ip))
-			xfs_blkdev_issue_flush(mp->m_rtdev_targp);
-		else if (mp->m_logdev_targp != mp->m_ddev_targp)
-			xfs_blkdev_issue_flush(mp->m_ddev_targp);
-	}
+	/*
+	 * If we have an RT and/or log subvolume we need to make sure to flush
+	 * the write cache the device used for file data first.  This is to
+	 * ensure newly written file data make it to disk before logging the new
+	 * inode size in case of an extending write.
+	 */
+	if (XFS_IS_REALTIME_INODE(ip))
+		xfs_blkdev_issue_flush(mp->m_rtdev_targp);
+	else if (mp->m_logdev_targp != mp->m_ddev_targp)
+		xfs_blkdev_issue_flush(mp->m_ddev_targp);
 
 	/*
 	 * All metadata updates are logged, which means that we just have to
@@ -196,10 +193,8 @@ xfs_file_fsync(
 	 * an already allocated file and thus do not have any metadata to
 	 * commit.
 	 */
-	if ((mp->m_flags & XFS_MOUNT_BARRIER) &&
-	    mp->m_logdev_targp == mp->m_ddev_targp &&
-	    !XFS_IS_REALTIME_INODE(ip) &&
-	    !log_flushed)
+	if (!log_flushed && !XFS_IS_REALTIME_INODE(ip) &&
+	    mp->m_logdev_targp == mp->m_ddev_targp)
 		xfs_blkdev_issue_flush(mp->m_ddev_targp);
 
 	return error;

fs/xfs/xfs_iops.c

@@ -988,7 +988,7 @@ xfs_vn_setattr(
 			return error;
 
 		xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
-		error = xfs_setattr_size(ip, iattr);
+		error = xfs_vn_setattr_size(dentry, iattr);
 		xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
 	} else {
 		error = xfs_vn_setattr_nonsize(dentry, iattr);

fs/xfs/xfs_log.c

@@ -1862,26 +1862,21 @@ xlog_sync(
 
 	bp->b_io_length = BTOBB(count);
 	bp->b_fspriv = iclog;
-	bp->b_flags &= ~(XBF_FUA | XBF_FLUSH);
-	bp->b_flags |= (XBF_ASYNC | XBF_SYNCIO | XBF_WRITE);
+	bp->b_flags &= ~XBF_FLUSH;
+	bp->b_flags |= (XBF_ASYNC | XBF_SYNCIO | XBF_WRITE | XBF_FUA);
 
-	if (log->l_mp->m_flags & XFS_MOUNT_BARRIER) {
-		bp->b_flags |= XBF_FUA;
-
-		/*
-		 * Flush the data device before flushing the log to make
-		 * sure all meta data written back from the AIL actually made
-		 * it to disk before stamping the new log tail LSN into the
-		 * log buffer.  For an external log we need to issue the
-		 * flush explicitly, and unfortunately synchronously here;
-		 * for an internal log we can simply use the block layer
-		 * state machine for preflushes.
-		 */
-		if (log->l_mp->m_logdev_targp != log->l_mp->m_ddev_targp)
-			xfs_blkdev_issue_flush(log->l_mp->m_ddev_targp);
-		else
-			bp->b_flags |= XBF_FLUSH;
-	}
+	/*
+	 * Flush the data device before flushing the log to make sure all meta
+	 * data written back from the AIL actually made it to disk before
+	 * stamping the new log tail LSN into the log buffer.  For an external
+	 * log we need to issue the flush explicitly, and unfortunately
+	 * synchronously here; for an internal log we can simply use the block
+	 * layer state machine for preflushes.
+	 */
+	if (log->l_mp->m_logdev_targp != log->l_mp->m_ddev_targp)
+		xfs_blkdev_issue_flush(log->l_mp->m_ddev_targp);
+	else
+		bp->b_flags |= XBF_FLUSH;
 
 	ASSERT(XFS_BUF_ADDR(bp) <= log->l_logBBsize-1);
 	ASSERT(XFS_BUF_ADDR(bp) + BTOBB(count) <= log->l_logBBsize);
@@ -1906,10 +1901,8 @@ xlog_sync(
 		xfs_buf_associate_memory(bp,
 				(char *)&iclog->ic_header + count, split);
 		bp->b_fspriv = iclog;
-		bp->b_flags &= ~(XBF_FUA | XBF_FLUSH);
-		bp->b_flags |= (XBF_ASYNC | XBF_SYNCIO | XBF_WRITE);
-		if (log->l_mp->m_flags & XFS_MOUNT_BARRIER)
-			bp->b_flags |= XBF_FUA;
+		bp->b_flags &= ~XBF_FLUSH;
+		bp->b_flags |= (XBF_ASYNC | XBF_SYNCIO | XBF_WRITE | XBF_FUA);
 
 		ASSERT(XFS_BUF_ADDR(bp) <= log->l_logBBsize-1);
 		ASSERT(XFS_BUF_ADDR(bp) + BTOBB(count) <= log->l_logBBsize);

fs/xfs/xfs_super.c

@@ -104,9 +104,6 @@ static const match_table_t tokens = {
 	{Opt_sysvgroups,"sysvgroups"},	/* group-ID from current process */
 	{Opt_allocsize,	"allocsize=%s"},/* preferred allocation size */
 	{Opt_norecovery,"norecovery"},	/* don't run XFS recovery */
-	{Opt_barrier,	"barrier"},	/* use writer barriers for log write and
-					 * unwritten extent conversion */
-	{Opt_nobarrier,	"nobarrier"},	/* .. disable */
 	{Opt_inode64,	"inode64"},	/* inodes can be allocated anywhere */
 	{Opt_inode32,   "inode32"},	/* inode allocation limited to
 					 * XFS_MAXINUMBER_32 */
@@ -134,6 +131,12 @@ static const match_table_t tokens = {
 	{Opt_nodiscard,	"nodiscard"},	/* Do not discard unused blocks */
 
 	{Opt_dax,	"dax"},		/* Enable direct access to bdev pages */
+
+	/* Deprecated mount options scheduled for removal */
+	{Opt_barrier,	"barrier"},	/* use writer barriers for log write and
+					 * unwritten extent conversion */
+	{Opt_nobarrier,	"nobarrier"},	/* .. disable */
+
 	{Opt_err,	NULL},
 };
 
@@ -301,12 +304,6 @@ xfs_parseargs(
 		case Opt_nouuid:
 			mp->m_flags |= XFS_MOUNT_NOUUID;
 			break;
-		case Opt_barrier:
-			mp->m_flags |= XFS_MOUNT_BARRIER;
-			break;
-		case Opt_nobarrier:
-			mp->m_flags &= ~XFS_MOUNT_BARRIER;
-			break;
 		case Opt_ikeep:
 			mp->m_flags |= XFS_MOUNT_IKEEP;
 			break;
@@ -374,6 +371,14 @@ xfs_parseargs(
 			mp->m_flags |= XFS_MOUNT_DAX;
 			break;
 #endif
+		case Opt_barrier:
+			xfs_warn(mp, "%s option is deprecated, ignoring.", p);
+			mp->m_flags |= XFS_MOUNT_BARRIER;
+			break;
+		case Opt_nobarrier:
+			xfs_warn(mp, "%s option is deprecated, ignoring.", p);
+			mp->m_flags &= ~XFS_MOUNT_BARRIER;
+			break;
 		default:
 			xfs_warn(mp, "unknown mount option [%s].", p);
 			return -EINVAL;
@@ -1238,9 +1243,11 @@ xfs_fs_remount(
 		token = match_token(p, tokens, args);
 		switch (token) {
 		case Opt_barrier:
+			xfs_warn(mp, "%s option is deprecated, ignoring.", p);
 			mp->m_flags |= XFS_MOUNT_BARRIER;
 			break;
 		case Opt_nobarrier:
+			xfs_warn(mp, "%s option is deprecated, ignoring.", p);
 			mp->m_flags &= ~XFS_MOUNT_BARRIER;
 			break;
 		case Opt_inode64: