15 files changed, 198 insertions, 77 deletions

diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 44db6db..b9d8a49 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -28,6 +28,37 @@ struct xfs_trans;
 extern kmem_zone_t	*xfs_bmap_free_item_zone;
 
 /*
+ * Argument structure for xfs_bmap_alloc.
+ */
+struct xfs_bmalloca {
+	xfs_fsblock_t		*firstblock; /* i/o first block allocated */
+	struct xfs_bmap_free	*flist;	/* bmap freelist */
+	struct xfs_trans	*tp;	/* transaction pointer */
+	struct xfs_inode	*ip;	/* incore inode pointer */
+	struct xfs_bmbt_irec	prev;	/* extent before the new one */
+	struct xfs_bmbt_irec	got;	/* extent after, or delayed */
+
+	xfs_fileoff_t		offset;	/* offset in file filling in */
+	xfs_extlen_t		length;	/* i/o length asked/allocated */
+	xfs_fsblock_t		blkno;	/* starting block of new extent */
+
+	struct xfs_btree_cur	*cur;	/* btree cursor */
+	xfs_extnum_t		idx;	/* current extent index */
+	int			nallocs;/* number of extents alloc'd */
+	int			logflags;/* flags for transaction logging */
+
+	xfs_extlen_t		total;	/* total blocks needed for xaction */
+	xfs_extlen_t		minlen;	/* minimum allocation size (blocks) */
+	xfs_extlen_t		minleft; /* amount must be left after alloc */
+	bool			eof;	/* set if allocating past last extent */
+	bool			wasdel;	/* replacing a delayed allocation */
+	bool			userdata;/* set if is user data */
+	bool			aeof;	/* allocated space at eof */
+	bool			conv;	/* overwriting unwritten extents */
+	int			flags;
+};
+
+/*
  * List of extents to be free "later".
  * The list is kept sorted on xbf_startblock.
  */
@@ -149,6 +180,8 @@ void	xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork);
 void	xfs_bmap_add_free(xfs_fsblock_t bno, xfs_filblks_t len,
 		struct xfs_bmap_free *flist, struct xfs_mount *mp);
 void	xfs_bmap_cancel(struct xfs_bmap_free *flist);
+int	xfs_bmap_finish(struct xfs_trans **tp, struct xfs_bmap_free *flist,
+			int *committed);
 void	xfs_bmap_compute_maxlevels(struct xfs_mount *mp, int whichfork);
 int	xfs_bmap_first_unused(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_extlen_t len, xfs_fileoff_t *unused, int whichfork);
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 749c861..8eb7189 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -307,8 +307,8 @@ typedef enum {
 #define XFS_SB_ICOUNT		XFS_SB_MVAL(ICOUNT)
 #define XFS_SB_IFREE		XFS_SB_MVAL(IFREE)
 #define XFS_SB_FDBLOCKS		XFS_SB_MVAL(FDBLOCKS)
-#define XFS_SB_FEATURES2	XFS_SB_MVAL(FEATURES2)
-#define XFS_SB_BAD_FEATURES2	XFS_SB_MVAL(BAD_FEATURES2)
+#define XFS_SB_FEATURES2	(XFS_SB_MVAL(FEATURES2) | \
+				 XFS_SB_MVAL(BAD_FEATURES2))
 #define XFS_SB_FEATURES_COMPAT	XFS_SB_MVAL(FEATURES_COMPAT)
 #define XFS_SB_FEATURES_RO_COMPAT XFS_SB_MVAL(FEATURES_RO_COMPAT)
 #define XFS_SB_FEATURES_INCOMPAT XFS_SB_MVAL(FEATURES_INCOMPAT)
@@ -322,9 +322,9 @@ typedef enum {
 	 XFS_SB_VERSIONNUM | XFS_SB_UQUOTINO | XFS_SB_GQUOTINO | \
 	 XFS_SB_QFLAGS | XFS_SB_SHARED_VN | XFS_SB_UNIT | XFS_SB_WIDTH | \
 	 XFS_SB_ICOUNT | XFS_SB_IFREE | XFS_SB_FDBLOCKS | XFS_SB_FEATURES2 | \
-	 XFS_SB_BAD_FEATURES2 | XFS_SB_FEATURES_COMPAT | \
-	 XFS_SB_FEATURES_RO_COMPAT | XFS_SB_FEATURES_INCOMPAT | \
-	 XFS_SB_FEATURES_LOG_INCOMPAT | XFS_SB_PQUOTINO)
+	 XFS_SB_FEATURES_COMPAT | XFS_SB_FEATURES_RO_COMPAT | \
+	 XFS_SB_FEATURES_INCOMPAT | XFS_SB_FEATURES_LOG_INCOMPAT | \
+	 XFS_SB_PQUOTINO)
 
 
 /*
diff --git a/fs/xfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index 18dc721..18dc721 100644
--- a/fs/xfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
diff --git a/fs/xfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index b79dc66..b79dc66 100644
--- a/fs/xfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h
index 2fdb72d..736429a 100644
--- a/fs/xfs/xfs_bmap_util.h
+++ b/fs/xfs/xfs_bmap_util.h
@@ -26,43 +26,8 @@ struct xfs_ifork;
 struct xfs_inode;
 struct xfs_mount;
 struct xfs_trans;
+struct xfs_bmalloca;
 
-/*
- * Argument structure for xfs_bmap_alloc.
- */
-struct xfs_bmalloca {
-	xfs_fsblock_t		*firstblock; /* i/o first block allocated */
-	struct xfs_bmap_free	*flist;	/* bmap freelist */
-	struct xfs_trans	*tp;	/* transaction pointer */
-	struct xfs_inode	*ip;	/* incore inode pointer */
-	struct xfs_bmbt_irec	prev;	/* extent before the new one */
-	struct xfs_bmbt_irec	got;	/* extent after, or delayed */
-
-	xfs_fileoff_t		offset;	/* offset in file filling in */
-	xfs_extlen_t		length;	/* i/o length asked/allocated */
-	xfs_fsblock_t		blkno;	/* starting block of new extent */
-
-	struct xfs_btree_cur	*cur;	/* btree cursor */
-	xfs_extnum_t		idx;	/* current extent index */
-	int			nallocs;/* number of extents alloc'd */
-	int			logflags;/* flags for transaction logging */
-
-	xfs_extlen_t		total;	/* total blocks needed for xaction */
-	xfs_extlen_t		minlen;	/* minimum allocation size (blocks) */
-	xfs_extlen_t		minleft; /* amount must be left after alloc */
-	bool			eof;	/* set if allocating past last extent */
-	bool			wasdel;	/* replacing a delayed allocation */
-	bool			userdata;/* set if is user data */
-	bool			aeof;	/* allocated space at eof */
-	bool			conv;	/* overwriting unwritten extents */
-	int			flags;
-	struct completion	*done;
-	struct work_struct	work;
-	int			result;
-};
-
-int	xfs_bmap_finish(struct xfs_trans **tp, struct xfs_bmap_free *flist,
-			int *committed);
 int	xfs_bmap_rtalloc(struct xfs_bmalloca *ap);
 int	xfs_bmap_eof(struct xfs_inode *ip, xfs_fileoff_t endoff,
 		     int whichfork, int *eof);
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 3f9bd58..925ead2 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -535,7 +535,7 @@ xfs_buf_item_push(
 	if ((bp->b_flags & XBF_WRITE_FAIL) &&
 	    ___ratelimit(&xfs_buf_write_fail_rl_state, "XFS:")) {
 		xfs_warn(bp->b_target->bt_mount,
-"Detected failing async write on buffer block 0x%llx. Retrying async write.\n",
+"Detected failing async write on buffer block 0x%llx. Retrying async write.",
 			 (long long)bp->b_bn);
 	}
 
diff --git a/fs/xfs/xfs_dquot.h b/fs/xfs/xfs_dquot.h
index c24c67e..2f536f3 100644
--- a/fs/xfs/xfs_dquot.h
+++ b/fs/xfs/xfs_dquot.h
@@ -86,7 +86,7 @@ static inline void xfs_dqflock(xfs_dquot_t *dqp)
 	wait_for_completion(&dqp->q_flush);
 }
 
-static inline int xfs_dqflock_nowait(xfs_dquot_t *dqp)
+static inline bool xfs_dqflock_nowait(xfs_dquot_t *dqp)
 {
 	return try_wait_for_completion(&dqp->q_flush);
 }
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 41f804e..9916aef 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2656,6 +2656,124 @@ xfs_sort_for_rename(
 }
 
 /*
+ * xfs_cross_rename()
+ *
+ * responsible for handling RENAME_EXCHANGE flag in renameat2() sytemcall
+ */
+STATIC int
+xfs_cross_rename(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*dp1,
+	struct xfs_name		*name1,
+	struct xfs_inode	*ip1,
+	struct xfs_inode	*dp2,
+	struct xfs_name		*name2,
+	struct xfs_inode	*ip2,
+	struct xfs_bmap_free	*free_list,
+	xfs_fsblock_t		*first_block,
+	int			spaceres)
+{
+	int		error = 0;
+	int		ip1_flags = 0;
+	int		ip2_flags = 0;
+	int		dp2_flags = 0;
+
+	/* Swap inode number for dirent in first parent */
+	error = xfs_dir_replace(tp, dp1, name1,
+				ip2->i_ino,
+				first_block, free_list, spaceres);
+	if (error)
+		goto out;
+
+	/* Swap inode number for dirent in second parent */
+	error = xfs_dir_replace(tp, dp2, name2,
+				ip1->i_ino,
+				first_block, free_list, spaceres);
+	if (error)
+		goto out;
+
+	/*
+	 * If we're renaming one or more directories across different parents,
+	 * update the respective ".." entries (and link counts) to match the new
+	 * parents.
+	 */
+	if (dp1 != dp2) {
+		dp2_flags = XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
+
+		if (S_ISDIR(ip2->i_d.di_mode)) {
+			error = xfs_dir_replace(tp, ip2, &xfs_name_dotdot,
+						dp1->i_ino, first_block,
+						free_list, spaceres);
+			if (error)
+				goto out;
+
+			/* transfer ip2 ".." reference to dp1 */
+			if (!S_ISDIR(ip1->i_d.di_mode)) {
+				error = xfs_droplink(tp, dp2);
+				if (error)
+					goto out;
+				error = xfs_bumplink(tp, dp1);
+				if (error)
+					goto out;
+			}
+
+			/*
+			 * Although ip1 isn't changed here, userspace needs
+			 * to be warned about the change, so that applications
+			 * relying on it (like backup ones), will properly
+			 * notify the change
+			 */
+			ip1_flags |= XFS_ICHGTIME_CHG;
+			ip2_flags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
+		}
+
+		if (S_ISDIR(ip1->i_d.di_mode)) {
+			error = xfs_dir_replace(tp, ip1, &xfs_name_dotdot,
+						dp2->i_ino, first_block,
+						free_list, spaceres);
+			if (error)
+				goto out;
+
+			/* transfer ip1 ".." reference to dp2 */
+			if (!S_ISDIR(ip2->i_d.di_mode)) {
+				error = xfs_droplink(tp, dp1);
+				if (error)
+					goto out;
+				error = xfs_bumplink(tp, dp2);
+				if (error)
+					goto out;
+			}
+
+			/*
+			 * Although ip2 isn't changed here, userspace needs
+			 * to be warned about the change, so that applications
+			 * relying on it (like backup ones), will properly
+			 * notify the change
+			 */
+			ip1_flags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
+			ip2_flags |= XFS_ICHGTIME_CHG;
+		}
+	}
+
+	if (ip1_flags) {
+		xfs_trans_ichgtime(tp, ip1, ip1_flags);
+		xfs_trans_log_inode(tp, ip1, XFS_ILOG_CORE);
+	}
+	if (ip2_flags) {
+		xfs_trans_ichgtime(tp, ip2, ip2_flags);
+		xfs_trans_log_inode(tp, ip2, XFS_ILOG_CORE);
+	}
+	if (dp2_flags) {
+		xfs_trans_ichgtime(tp, dp2, dp2_flags);
+		xfs_trans_log_inode(tp, dp2, XFS_ILOG_CORE);
+	}
+	xfs_trans_ichgtime(tp, dp1, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+	xfs_trans_log_inode(tp, dp1, XFS_ILOG_CORE);
+out:
+	return error;
+}
+
+/*
  * xfs_rename
  */
 int
@@ -2665,7 +2783,8 @@ xfs_rename(
 	xfs_inode_t	*src_ip,
 	xfs_inode_t	*target_dp,
 	struct xfs_name	*target_name,
-	xfs_inode_t	*target_ip)
+	xfs_inode_t	*target_ip,
+	unsigned int	flags)
 {
 	xfs_trans_t	*tp = NULL;
 	xfs_mount_t	*mp = src_dp->i_mount;
@@ -2743,6 +2862,18 @@ xfs_rename(
 	}
 
 	/*
+	 * Handle RENAME_EXCHANGE flags
+	 */
+	if (flags & RENAME_EXCHANGE) {
+		error = xfs_cross_rename(tp, src_dp, src_name, src_ip,
+					 target_dp, target_name, target_ip,
+					 &free_list, &first_block, spaceres);
+		if (error)
+			goto abort_return;
+		goto finish_rename;
+	}
+
+	/*
 	 * Set up the target.
 	 */
 	if (target_ip == NULL) {
@@ -2881,6 +3012,7 @@ xfs_rename(
 	if (new_parent)
 		xfs_trans_log_inode(tp, target_dp, XFS_ILOG_CORE);
 
+finish_rename:
 	/*
 	 * If this is a synchronous mount, make sure that the
 	 * rename transaction goes to disk before returning to
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 4ed2ba9..f772296 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -338,7 +338,7 @@ int		xfs_link(struct xfs_inode *tdp, struct xfs_inode *sip,
 int		xfs_rename(struct xfs_inode *src_dp, struct xfs_name *src_name,
 			   struct xfs_inode *src_ip, struct xfs_inode *target_dp,
 			   struct xfs_name *target_name,
-			   struct xfs_inode *target_ip);
+			   struct xfs_inode *target_ip, unsigned int flags);
 
 void		xfs_ilock(xfs_inode_t *, uint);
 int		xfs_ilock_nowait(xfs_inode_t *, uint);
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index c980e2a..ccb1dd0 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -802,7 +802,7 @@ int
 xfs_iomap_write_unwritten(
 	xfs_inode_t	*ip,
 	xfs_off_t	offset,
-	size_t		count)
+	xfs_off_t	count)
 {
 	xfs_mount_t	*mp = ip->i_mount;
 	xfs_fileoff_t	offset_fsb;
diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index 411fbb8..8688e66 100644
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -27,6 +27,6 @@ int xfs_iomap_write_delay(struct xfs_inode *, xfs_off_t, size_t,
 			struct xfs_bmbt_irec *);
 int xfs_iomap_write_allocate(struct xfs_inode *, xfs_off_t,
 			struct xfs_bmbt_irec *);
-int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, size_t);
+int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t);
 
 #endif /* __XFS_IOMAP_H__*/
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index c50311c..ce80eeb 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -380,18 +380,27 @@ xfs_vn_rename(
 	struct inode	*odir,
 	struct dentry	*odentry,
 	struct inode	*ndir,
-	struct dentry	*ndentry)
+	struct dentry	*ndentry,
+	unsigned int	flags)
 {
 	struct inode	*new_inode = ndentry->d_inode;
+	int		omode = 0;
 	struct xfs_name	oname;
 	struct xfs_name	nname;
 
-	xfs_dentry_to_name(&oname, odentry, 0);
+	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE))
+		return -EINVAL;
+
+	/* if we are exchanging files, we need to set i_mode of both files */
+	if (flags & RENAME_EXCHANGE)
+		omode = ndentry->d_inode->i_mode;
+
+	xfs_dentry_to_name(&oname, odentry, omode);
 	xfs_dentry_to_name(&nname, ndentry, odentry->d_inode->i_mode);
 
 	return xfs_rename(XFS_I(odir), &oname, XFS_I(odentry->d_inode),
-			  XFS_I(ndir), &nname, new_inode ?
-						XFS_I(new_inode) : NULL);
+			  XFS_I(ndir), &nname,
+			  new_inode ? XFS_I(new_inode) : NULL, flags);
 }
 
 /*
@@ -1144,7 +1153,7 @@ static const struct inode_operations xfs_dir_inode_operations = {
 	 */
 	.rmdir			= xfs_vn_unlink,
 	.mknod			= xfs_vn_mknod,
-	.rename			= xfs_vn_rename,
+	.rename2		= xfs_vn_rename,
 	.get_acl		= xfs_get_acl,
 	.set_acl		= xfs_set_acl,
 	.getattr		= xfs_vn_getattr,
@@ -1172,7 +1181,7 @@ static const struct inode_operations xfs_dir_ci_inode_operations = {
 	 */
 	.rmdir			= xfs_vn_unlink,
 	.mknod			= xfs_vn_mknod,
-	.rename			= xfs_vn_rename,
+	.rename2		= xfs_vn_rename,
 	.get_acl		= xfs_get_acl,
 	.set_acl		= xfs_set_acl,
 	.getattr		= xfs_vn_getattr,
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 2b8dcf2..bcc7cfa 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1407,6 +1407,8 @@ xlog_alloc_log(
 	ASSERT(xfs_buf_islocked(bp));
 	xfs_buf_unlock(bp);
 
+	/* use high priority wq for log I/O completion */
+	bp->b_ioend_wq = mp->m_log_workqueue;
 	bp->b_iodone = xlog_iodone;
 	log->l_xbuf = bp;
 
@@ -1439,6 +1441,8 @@ xlog_alloc_log(
 		ASSERT(xfs_buf_islocked(bp));
 		xfs_buf_unlock(bp);
 
+		/* use high priority wq for log I/O completion */
+		bp->b_ioend_wq = mp->m_log_workqueue;
 		bp->b_iodone = xlog_iodone;
 		iclog->ic_bp = bp;
 		iclog->ic_data = bp->b_addr;
@@ -1818,8 +1822,6 @@ xlog_sync(
 	XFS_BUF_ZEROFLAGS(bp);
 	XFS_BUF_ASYNC(bp);
 	bp->b_flags |= XBF_SYNCIO;
-	/* use high priority completion wq */
-	bp->b_ioend_wq = log->l_mp->m_log_workqueue;
 
 	if (log->l_mp->m_flags & XFS_MOUNT_BARRIER) {
 		bp->b_flags |= XBF_FUA;
@@ -1868,8 +1870,6 @@ xlog_sync(
 		bp->b_flags |= XBF_SYNCIO;
 		if (log->l_mp->m_flags & XFS_MOUNT_BARRIER)
 			bp->b_flags |= XBF_FUA;
-		/* use high priority completion wq */
-		bp->b_ioend_wq = log->l_mp->m_log_workqueue;
 
 		ASSERT(XFS_BUF_ADDR(bp) <= log->l_logBBsize-1);
 		ASSERT(XFS_BUF_ADDR(bp) + BTOBB(count) <= log->l_logBBsize);
@@ -2039,7 +2039,7 @@ xlog_print_tic_res(
 		"  total reg   = %u bytes (o/flow = %u bytes)\n"
 		"  ophdrs      = %u (ophdr space = %u bytes)\n"
 		"  ophdr + reg = %u bytes\n"
-		"  num regions = %u\n",
+		"  num regions = %u",
 		((ticket->t_trans_type <= 0 ||
 		  ticket->t_trans_type > XFS_TRANS_TYPE_MAX) ?
 		  "bad-trans-type" : trans_type_str[ticket->t_trans_type-1]),
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index a3b791b..5ce76d0 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -685,7 +685,7 @@ xfs_blkdev_get(
 				    mp);
 	if (IS_ERR(*bdevp)) {
 		error = PTR_ERR(*bdevp);
-		xfs_warn(mp, "Invalid device [%s], error=%d\n", name, error);
+		xfs_warn(mp, "Invalid device [%s], error=%d", name, error);
 	}
 
 	return error;
diff --git a/fs/xfs/xfs_sysctl.c b/fs/xfs/xfs_sysctl.c
index 1743b9f..a0c8067 100644
--- a/fs/xfs/xfs_sysctl.c
+++ b/fs/xfs/xfs_sysctl.c
@@ -149,24 +149,6 @@ static struct ctl_table xfs_table[] = {
 		.extra2		= &xfs_params.inherit_noatim.max
 	},
 	{
-		.procname	= "xfsbufd_centisecs",
-		.data		= &xfs_params.xfs_buf_timer.val,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &xfs_params.xfs_buf_timer.min,
-		.extra2		= &xfs_params.xfs_buf_timer.max
-	},
-	{
-		.procname	= "age_buffer_centisecs",
-		.data		= &xfs_params.xfs_buf_age.val,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &xfs_params.xfs_buf_age.min,
-		.extra2		= &xfs_params.xfs_buf_age.max
-	},
-	{
 		.procname	= "inherit_nosymlinks",
 		.data		= &xfs_params.inherit_nosym.val,
 		.maxlen		= sizeof(int),