Merge tag 'gfs2-4.15.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2

Pull gfs2 updates from Bob Peterson:
"We've got a total of 17 GFS2 patches for this merge window. The
patches are basically in three categories: (1) patches related to
broken xfstest cases, (2) patches related to improving iomap and start
using it in GFS2, and (3) general typos and clarifications.

Please note that one of the iomap patches extends beyond GFS2 and
affects other file systems, but it was publically reviewed by a
variety of file system people in the community.

From Andreas Gruenbacher:

- rename variable 'bsize' to 'factor' to clarify the logic related to
gfs2_block_map.

- correctly set ctime in the setflags ioctl, which fixes broken
xfstests test 277.

- fix broken xfstest 258, due to an atime initialization problem.

- fix broken xfstest 307, in which GFS2 was not setting ctime when
setting acls.

- switch general iomap code from blkno to disk offset for a variety
of file systems.

- add a new IOMAP_F_DATA_INLINE flag for iomap to indicate blocks
that have data mixed with metadata.

- implement SEEK_HOLE and SEEK_DATA via iomap in GFS2.

- fix failing xfstest case 066, which was due to not properly syncing
dirty inodes when changing extended attributes.

- fix a minor typo in a comment.

- partially fix xfstest 424, which involved GET_FLAGS and SET_FLAGS
ioctl. This is also a cleanup and simplification of the translation
of flags from fs flags to gfs2 flags.

- add support for STATX_ATTR_ in statx, which fixed broken xfstest
424.

- fix for failing xfstest 093 which fixes a recursive glock problem
with gfs2_xattr_get and _set

From me:

- make inode height info part of the 'metapath' data structure to
facilitate using iomap in GFS2.

- start using iomap inside GFS2 and switch GFS2's block_map functions
to use iomap under the covers.

- switch GFS2's fiemap implementation from using block_map to using
iomap under the covers.

- fix journaled data pages not being properly synced to media when
writing inodes. This was caught with xfstests.

- fix another failing xfstest case in which switching a file from
ordered_write to journaled data via set_flags caused a deadlock"

* tag 'gfs2-4.15.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2:
gfs2: Allow gfs2_xattr_set to be called with the glock held
gfs2: Add support for statx inode flags
gfs2: Fix and clean up {GET,SET}FLAGS ioctl
gfs2: Fix a harmless typo
gfs2: Fix xattr fsync
GFS2: Take inode off order_write list when setting jdata flag
GFS2: flush the log and all pages for jdata as we do for WB_SYNC_ALL
gfs2: Implement SEEK_HOLE / SEEK_DATA via iomap
GFS2: Switch fiemap implementation to use iomap
GFS2: Implement iomap for block_map
GFS2: Make height info part of metapath
gfs2: Always update inode ctime in set_acl
gfs2: Support negative atimes
gfs2: Update ctime in setflags ioctl
gfs2: Clarify gfs2_block_map

fs/gfs2/Kconfig

···
 	select FS_POSIX_ACL
 	select CRC32
 	select QUOTACTL
+	select FS_IOMAP
 	help
 	  A cluster filesystem.
 

fs/gfs2/acl.c

···
 
 	ret = __gfs2_set_acl(inode, acl, type);
 	if (!ret && mode != inode->i_mode) {
+		inode->i_ctime = current_time(inode);
 		inode->i_mode = mode;
 		mark_inode_dirty(inode);
 	}

fs/gfs2/bmap.c

···
 #include <linux/blkdev.h>
 #include <linux/gfs2_ondisk.h>
 #include <linux/crc32.h>
+#include <linux/iomap.h>
 
 #include "gfs2.h"
 #include "incore.h"
···
 struct metapath {
 	struct buffer_head *mp_bh[GFS2_MAX_META_HEIGHT];
 	__u16 mp_list[GFS2_MAX_META_HEIGHT];
+	int mp_fheight; /* find_metapath height */
+	int mp_aheight; /* actual height (lookup height) */
 };
 
 /**
···
 {
 	unsigned int i;
 
+	mp->mp_fheight = height;
 	for (i = height; i--;)
 		mp->mp_list[i] = do_div(block, sdp->sd_inptrs);
-
 }
 
 static inline unsigned int metapath_branch_start(const struct metapath *mp)
···
 }
 
 /**
- * metaptr1 - Return the first possible metadata pointer in a metaath buffer
+ * metaptr1 - Return the first possible metadata pointer in a metapath buffer
  * @height: The metadata height (0 = dinode)
  * @mp: The metapath
  */
···
 	for (x = 0; x < end_of_metadata; x++) {
 		ret = lookup_mp_height(ip, mp, x);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
-	return ip->i_height;
+	ret = ip->i_height;
+out:
+	mp->mp_aheight = ret;
+	return ret;
 }
 
 /**
···
  * @inode: The GFS2 inode
  * @lblock: The logical starting block of the extent
  * @bh_map: This is used to return the mapping details
- * @mp: The metapath
- * @sheight: The starting height (i.e. whats already mapped)
- * @height: The height to build to
+ * @zero_new: True if newly allocated blocks should be zeroed
+ * @mp: The metapath, with proper height information calculated
  * @maxlen: The max number of data blocks to alloc
+ * @dblock: Pointer to return the resulting new block
+ * @dblks: Pointer to return the number of blocks allocated
  *
  * In this routine we may have to alloc:
  *   i) Indirect blocks to grow the metadata tree height
···
  * Returns: errno on error
  */
 
-static int gfs2_bmap_alloc(struct inode *inode, const sector_t lblock,
-			   struct buffer_head *bh_map, struct metapath *mp,
-			   const unsigned int sheight,
-			   const unsigned int height,
-			   const size_t maxlen)
+static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap,
+			    unsigned flags, struct metapath *mp)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct super_block *sb = sdp->sd_vfs;
 	struct buffer_head *dibh = mp->mp_bh[0];
-	u64 bn, dblock = 0;
+	u64 bn;
 	unsigned n, i, blks, alloced = 0, iblks = 0, branch_start = 0;
 	unsigned dblks = 0;
 	unsigned ptrs_per_blk;
-	const unsigned end_of_metadata = height - 1;
+	const unsigned end_of_metadata = mp->mp_fheight - 1;
 	int ret;
-	int eob = 0;
 	enum alloc_state state;
 	__be64 *ptr;
 	__be64 zero_bn = 0;
+	size_t maxlen = iomap->length >> inode->i_blkbits;
 
-	BUG_ON(sheight < 1);
+	BUG_ON(mp->mp_aheight < 1);
 	BUG_ON(dibh == NULL);
 
 	gfs2_trans_add_meta(ip->i_gl, dibh);
 
-	if (height == sheight) {
+	if (mp->mp_fheight == mp->mp_aheight) {
 		struct buffer_head *bh;
+		int eob;
+
 		/* Bottom indirect block exists, find unalloced extent size */
 		ptr = metapointer(end_of_metadata, mp);
 		bh = mp->mp_bh[end_of_metadata];
-		dblks = gfs2_extent_length(bh->b_data, bh->b_size, ptr, maxlen,
-					   &eob);
+		dblks = gfs2_extent_length(bh->b_data, bh->b_size, ptr,
+					   maxlen, &eob);
 		BUG_ON(dblks < 1);
 		state = ALLOC_DATA;
 	} else {
 		/* Need to allocate indirect blocks */
-		ptrs_per_blk = height > 1 ? sdp->sd_inptrs : sdp->sd_diptrs;
+		ptrs_per_blk = mp->mp_fheight > 1 ? sdp->sd_inptrs :
+			sdp->sd_diptrs;
 		dblks = min(maxlen, (size_t)(ptrs_per_blk -
 					     mp->mp_list[end_of_metadata]));
-		if (height == ip->i_height) {
+		if (mp->mp_fheight == ip->i_height) {
 			/* Writing into existing tree, extend tree down */
-			iblks = height - sheight;
+			iblks = mp->mp_fheight - mp->mp_aheight;
 			state = ALLOC_GROW_DEPTH;
 		} else {
 			/* Building up tree height */
 			state = ALLOC_GROW_HEIGHT;
-			iblks = height - ip->i_height;
+			iblks = mp->mp_fheight - ip->i_height;
 			branch_start = metapath_branch_start(mp);
-			iblks += (height - branch_start);
+			iblks += (mp->mp_fheight - branch_start);
 		}
 	}
 
 	/* start of the second part of the function (state machine) */
 
 	blks = dblks + iblks;
-	i = sheight;
+	i = mp->mp_aheight;
 	do {
 		int error;
 		n = blks - alloced;
···
 						 sizeof(struct gfs2_dinode));
 				zero_bn = *ptr;
 			}
-			for (; i - 1 < height - ip->i_height && n > 0; i++, n--)
+			for (; i - 1 < mp->mp_fheight - ip->i_height && n > 0;
+			     i++, n--)
 				gfs2_indirect_init(mp, ip->i_gl, i, 0, bn++);
-			if (i - 1 == height - ip->i_height) {
+			if (i - 1 == mp->mp_fheight - ip->i_height) {
 				i--;
 				gfs2_buffer_copy_tail(mp->mp_bh[i],
 						sizeof(struct gfs2_meta_header),
···
 					sizeof(struct gfs2_meta_header));
 				*ptr = zero_bn;
 				state = ALLOC_GROW_DEPTH;
-				for(i = branch_start; i < height; i++) {
+				for(i = branch_start; i < mp->mp_fheight; i++) {
 					if (mp->mp_bh[i] == NULL)
 						break;
 					brelse(mp->mp_bh[i]);
···
 				break;
 		/* Branching from existing tree */
 		case ALLOC_GROW_DEPTH:
-			if (i > 1 && i < height)
+			if (i > 1 && i < mp->mp_fheight)
 				gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[i-1]);
-			for (; i < height && n > 0; i++, n--)
+			for (; i < mp->mp_fheight && n > 0; i++, n--)
 				gfs2_indirect_init(mp, ip->i_gl, i,
 						   mp->mp_list[i-1], bn++);
-			if (i == height)
+			if (i == mp->mp_fheight)
 				state = ALLOC_DATA;
 			if (n == 0)
 				break;
···
 			gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[end_of_metadata]);
 			dblks = n;
 			ptr = metapointer(end_of_metadata, mp);
-			dblock = bn;
+			iomap->addr = bn << inode->i_blkbits;
+			iomap->flags |= IOMAP_F_NEW;
 			while (n-- > 0)
 				*ptr++ = cpu_to_be64(bn++);
-			if (buffer_zeronew(bh_map)) {
-				ret = sb_issue_zeroout(sb, dblock, dblks,
-						       GFP_NOFS);
+			if (flags & IOMAP_ZERO) {
+				ret = sb_issue_zeroout(sb, iomap->addr >> inode->i_blkbits,
+						       dblks, GFP_NOFS);
 				if (ret) {
 					fs_err(sdp,
 					       "Failed to zero data buffers\n");
-					clear_buffer_zeronew(bh_map);
+					flags &= ~IOMAP_ZERO;
 				}
 			}
 			break;
 		}
-	} while ((state != ALLOC_DATA) || !dblock);
+	} while (iomap->addr == IOMAP_NULL_ADDR);
 
-	ip->i_height = height;
+	iomap->length = (u64)dblks << inode->i_blkbits;
+	ip->i_height = mp->mp_fheight;
 	gfs2_add_inode_blocks(&ip->i_inode, alloced);
 	gfs2_dinode_out(ip, mp->mp_bh[0]->b_data);
-	map_bh(bh_map, inode->i_sb, dblock);
-	bh_map->b_size = dblks << inode->i_blkbits;
-	set_buffer_new(bh_map);
 	return 0;
+}
+
+/**
+ * hole_size - figure out the size of a hole
+ * @inode: The inode
+ * @lblock: The logical starting block number
+ * @mp: The metapath
+ *
+ * Returns: The hole size in bytes
+ *
+ */
+static u64 hole_size(struct inode *inode, sector_t lblock, struct metapath *mp)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct metapath mp_eof;
+	u64 factor = 1;
+	int hgt;
+	u64 holesz = 0;
+	const __be64 *first, *end, *ptr;
+	const struct buffer_head *bh;
+	u64 lblock_stop = (i_size_read(inode) - 1) >> inode->i_blkbits;
+	int zeroptrs;
+	bool done = false;
+
+	/* Get another metapath, to the very last byte */
+	find_metapath(sdp, lblock_stop, &mp_eof, ip->i_height);
+	for (hgt = ip->i_height - 1; hgt >= 0 && !done; hgt--) {
+		bh = mp->mp_bh[hgt];
+		if (bh) {
+			zeroptrs = 0;
+			first = metapointer(hgt, mp);
+			end = (const __be64 *)(bh->b_data + bh->b_size);
+
+			for (ptr = first; ptr < end; ptr++) {
+				if (*ptr) {
+					done = true;
+					break;
+				} else {
+					zeroptrs++;
+				}
+			}
+		} else {
+			zeroptrs = sdp->sd_inptrs;
+		}
+		if (factor * zeroptrs >= lblock_stop - lblock + 1) {
+			holesz = lblock_stop - lblock + 1;
+			break;
+		}
+		holesz += factor * zeroptrs;
+
+		factor *= sdp->sd_inptrs;
+		if (hgt && (mp->mp_list[hgt - 1] < mp_eof.mp_list[hgt - 1]))
+			(mp->mp_list[hgt - 1])++;
+	}
+	return holesz << inode->i_blkbits;
+}
+
+static void gfs2_stuffed_iomap(struct inode *inode, struct iomap *iomap)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+
+	iomap->addr = (ip->i_no_addr << inode->i_blkbits) +
+		      sizeof(struct gfs2_dinode);
+	iomap->offset = 0;
+	iomap->length = i_size_read(inode);
+	iomap->type = IOMAP_MAPPED;
+	iomap->flags = IOMAP_F_DATA_INLINE;
+}
+
+/**
+ * gfs2_iomap_begin - Map blocks from an inode to disk blocks
+ * @inode: The inode
+ * @pos: Starting position in bytes
+ * @length: Length to map, in bytes
+ * @flags: iomap flags
+ * @iomap: The iomap structure
+ *
+ * Returns: errno
+ */
+int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
+		     unsigned flags, struct iomap *iomap)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct metapath mp = { .mp_aheight = 1, };
+	unsigned int factor = sdp->sd_sb.sb_bsize;
+	const u64 *arr = sdp->sd_heightsize;
+	__be64 *ptr;
+	sector_t lblock;
+	sector_t lend;
+	int ret;
+	int eob;
+	unsigned int len;
+	struct buffer_head *bh;
+	u8 height;
+
+	trace_gfs2_iomap_start(ip, pos, length, flags);
+	if (!length) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if ((flags & IOMAP_REPORT) && gfs2_is_stuffed(ip)) {
+		gfs2_stuffed_iomap(inode, iomap);
+		if (pos >= iomap->length)
+			return -ENOENT;
+		ret = 0;
+		goto out;
+	}
+
+	lblock = pos >> inode->i_blkbits;
+	lend = (pos + length + sdp->sd_sb.sb_bsize - 1) >> inode->i_blkbits;
+
+	iomap->offset = lblock << inode->i_blkbits;
+	iomap->addr = IOMAP_NULL_ADDR;
+	iomap->type = IOMAP_HOLE;
+	iomap->length = (u64)(lend - lblock) << inode->i_blkbits;
+	iomap->flags = IOMAP_F_MERGED;
+	bmap_lock(ip, 0);
+
+	/*
+	 * Directory data blocks have a struct gfs2_meta_header header, so the
+	 * remaining size is smaller than the filesystem block size.  Logical
+	 * block numbers for directories are in units of this remaining size!
+	 */
+	if (gfs2_is_dir(ip)) {
+		factor = sdp->sd_jbsize;
+		arr = sdp->sd_jheightsize;
+	}
+
+	ret = gfs2_meta_inode_buffer(ip, &mp.mp_bh[0]);
+	if (ret)
+		goto out_release;
+
+	height = ip->i_height;
+	while ((lblock + 1) * factor > arr[height])
+		height++;
+	find_metapath(sdp, lblock, &mp, height);
+	if (height > ip->i_height || gfs2_is_stuffed(ip))
+		goto do_alloc;
+
+	ret = lookup_metapath(ip, &mp);
+	if (ret < 0)
+		goto out_release;
+
+	if (mp.mp_aheight != ip->i_height)
+		goto do_alloc;
+
+	ptr = metapointer(ip->i_height - 1, &mp);
+	if (*ptr == 0)
+		goto do_alloc;
+
+	iomap->type = IOMAP_MAPPED;
+	iomap->addr = be64_to_cpu(*ptr) << inode->i_blkbits;
+
+	bh = mp.mp_bh[ip->i_height - 1];
+	len = gfs2_extent_length(bh->b_data, bh->b_size, ptr, lend - lblock, &eob);
+	if (eob)
+		iomap->flags |= IOMAP_F_BOUNDARY;
+	iomap->length = (u64)len << inode->i_blkbits;
+
+	ret = 0;
+
+out_release:
+	release_metapath(&mp);
+	bmap_unlock(ip, 0);
+out:
+	trace_gfs2_iomap_end(ip, iomap, ret);
+	return ret;
+
+do_alloc:
+	if (!(flags & IOMAP_WRITE)) {
+		if (pos >= i_size_read(inode)) {
+			ret = -ENOENT;
+			goto out_release;
+		}
+		ret = 0;
+		iomap->length = hole_size(inode, lblock, &mp);
+		goto out_release;
+	}
+
+	ret = gfs2_iomap_alloc(inode, iomap, flags, &mp);
+	goto out_release;
 }
 
 /**
···
 		   struct buffer_head *bh_map, int create)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	unsigned int bsize = sdp->sd_sb.sb_bsize;
-	const size_t maxlen = bh_map->b_size >> inode->i_blkbits;
-	const u64 *arr = sdp->sd_heightsize;
-	__be64 *ptr;
-	u64 size;
-	struct metapath mp;
-	int ret;
-	int eob;
-	unsigned int len;
-	struct buffer_head *bh;
-	u8 height;
+	struct iomap iomap;
+	int ret, flags = 0;
 
-	BUG_ON(maxlen == 0);
-
-	memset(&mp, 0, sizeof(mp));
-	bmap_lock(ip, create);
 	clear_buffer_mapped(bh_map);
 	clear_buffer_new(bh_map);
 	clear_buffer_boundary(bh_map);
 	trace_gfs2_bmap(ip, bh_map, lblock, create, 1);
-	if (gfs2_is_dir(ip)) {
-		bsize = sdp->sd_jbsize;
-		arr = sdp->sd_jheightsize;
+
+	if (create)
+		flags |= IOMAP_WRITE;
+	if (buffer_zeronew(bh_map))
+		flags |= IOMAP_ZERO;
+	ret = gfs2_iomap_begin(inode, (loff_t)lblock << inode->i_blkbits,
+			       bh_map->b_size, flags, &iomap);
+	if (ret) {
+		if (!create && ret == -ENOENT) {
+			/* Return unmapped buffer beyond the end of file.  */
+			ret = 0;
+		}
+		goto out;
 	}
 
-	ret = gfs2_meta_inode_buffer(ip, &mp.mp_bh[0]);
-	if (ret)
-		goto out;
-
-	height = ip->i_height;
-	size = (lblock + 1) * bsize;
-	while (size > arr[height])
-		height++;
-	find_metapath(sdp, lblock, &mp, height);
-	ret = 1;
-	if (height > ip->i_height || gfs2_is_stuffed(ip))
-		goto do_alloc;
-	ret = lookup_metapath(ip, &mp);
-	if (ret < 0)
-		goto out;
-	if (ret != ip->i_height)
-		goto do_alloc;
-	ptr = metapointer(ip->i_height - 1, &mp);
-	if (*ptr == 0)
-		goto do_alloc;
-	map_bh(bh_map, inode->i_sb, be64_to_cpu(*ptr));
-	bh = mp.mp_bh[ip->i_height - 1];
-	len = gfs2_extent_length(bh->b_data, bh->b_size, ptr, maxlen, &eob);
-	bh_map->b_size = (len << inode->i_blkbits);
-	if (eob)
+	if (iomap.length > bh_map->b_size) {
+		iomap.length = bh_map->b_size;
+		iomap.flags &= ~IOMAP_F_BOUNDARY;
+	}
+	if (iomap.addr != IOMAP_NULL_ADDR)
+		map_bh(bh_map, inode->i_sb, iomap.addr >> inode->i_blkbits);
+	bh_map->b_size = iomap.length;
+	if (iomap.flags & IOMAP_F_BOUNDARY)
 		set_buffer_boundary(bh_map);
-	ret = 0;
+	if (iomap.flags & IOMAP_F_NEW)
+		set_buffer_new(bh_map);
+
 out:
-	release_metapath(&mp);
 	trace_gfs2_bmap(ip, bh_map, lblock, create, ret);
-	bmap_unlock(ip, create);
 	return ret;
-
-do_alloc:
-	/* All allocations are done here, firstly check create flag */
-	if (!create) {
-		BUG_ON(gfs2_is_stuffed(ip));
-		ret = 0;
-		goto out;
-	}
-
-	/* At this point ret is the tree depth of already allocated blocks */
-	ret = gfs2_bmap_alloc(inode, lblock, bh_map, &mp, ret, height, maxlen);
-	goto out;
 }
 
 /*

fs/gfs2/bmap.h

···
 #ifndef __BMAP_DOT_H__
 #define __BMAP_DOT_H__
 
+#include <linux/iomap.h>
+
 #include "inode.h"
 
 struct inode;
···
 extern int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page);
 extern int gfs2_block_map(struct inode *inode, sector_t lblock,
 			  struct buffer_head *bh, int create);
+extern int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
+			    unsigned flags, struct iomap *iomap);
 extern int gfs2_extent_map(struct inode *inode, u64 lblock, int *new,
 			   u64 *dblock, unsigned *extlen);
 extern int gfs2_setattr_size(struct inode *inode, u64 size);

fs/gfs2/file.c

···
 	loff_t error;
 
 	switch (whence) {
-	case SEEK_END: /* These reference inode->i_size */
-	case SEEK_DATA:
-	case SEEK_HOLE:
+	case SEEK_END:
 		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
 					   &i_gh);
 		if (!error) {
···
 			gfs2_glock_dq_uninit(&i_gh);
 		}
 		break;
+
+	case SEEK_DATA:
+		error = gfs2_seek_data(file, offset);
+		break;
+
+	case SEEK_HOLE:
+		error = gfs2_seek_hole(file, offset);
+		break;
+
 	case SEEK_CUR:
 	case SEEK_SET:
+		/*
+		 * These don't reference inode->i_size and don't depend on the
+		 * block mapping, so we don't need the glock.
+		 */
 		error = generic_file_llseek(file, offset, whence);
 		break;
 	default:
···
 }
 
 /**
- * fsflags_cvt
- * @table: A table of 32 u32 flags
- * @val: a 32 bit value to convert
+ * fsflag_gfs2flag
  *
- * This function can be used to convert between fsflags values and
- * GFS2's own flags values.
- *
- * Returns: the converted flags
+ * The FS_JOURNAL_DATA_FL flag maps to GFS2_DIF_INHERIT_JDATA for directories,
+ * and to GFS2_DIF_JDATA for non-directories.
  */
-static u32 fsflags_cvt(const u32 *table, u32 val)
-{
-	u32 res = 0;
-	while(val) {
-		if (val & 1)
-			res |= *table;
-		table++;
-		val >>= 1;
-	}
-	return res;
-}
-
-static const u32 fsflags_to_gfs2[32] = {
-	[3] = GFS2_DIF_SYNC,
-	[4] = GFS2_DIF_IMMUTABLE,
-	[5] = GFS2_DIF_APPENDONLY,
-	[7] = GFS2_DIF_NOATIME,
-	[12] = GFS2_DIF_EXHASH,
-	[14] = GFS2_DIF_INHERIT_JDATA,
-	[17] = GFS2_DIF_TOPDIR,
-};
-
-static const u32 gfs2_to_fsflags[32] = {
-	[gfs2fl_Sync] = FS_SYNC_FL,
-	[gfs2fl_Immutable] = FS_IMMUTABLE_FL,
-	[gfs2fl_AppendOnly] = FS_APPEND_FL,
-	[gfs2fl_NoAtime] = FS_NOATIME_FL,
-	[gfs2fl_ExHash] = FS_INDEX_FL,
-	[gfs2fl_TopLevel] = FS_TOPDIR_FL,
-	[gfs2fl_InheritJdata] = FS_JOURNAL_DATA_FL,
+static struct {
+	u32 fsflag;
+	u32 gfsflag;
+} fsflag_gfs2flag[] = {
+	{FS_SYNC_FL, GFS2_DIF_SYNC},
+	{FS_IMMUTABLE_FL, GFS2_DIF_IMMUTABLE},
+	{FS_APPEND_FL, GFS2_DIF_APPENDONLY},
+	{FS_NOATIME_FL, GFS2_DIF_NOATIME},
+	{FS_INDEX_FL, GFS2_DIF_EXHASH},
+	{FS_TOPDIR_FL, GFS2_DIF_TOPDIR},
+	{FS_JOURNAL_DATA_FL, GFS2_DIF_JDATA | GFS2_DIF_INHERIT_JDATA},
 };
 
 static int gfs2_get_flags(struct file *filp, u32 __user *ptr)
···
 	struct inode *inode = file_inode(filp);
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_holder gh;
-	int error;
-	u32 fsflags;
+	int i, error;
+	u32 gfsflags, fsflags = 0;
 
 	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
 	error = gfs2_glock_nq(&gh);
 	if (error)
 		goto out_uninit;
 
-	fsflags = fsflags_cvt(gfs2_to_fsflags, ip->i_diskflags);
-	if (!S_ISDIR(inode->i_mode) && ip->i_diskflags & GFS2_DIF_JDATA)
-		fsflags |= FS_JOURNAL_DATA_FL;
+	gfsflags = ip->i_diskflags;
+	if (S_ISDIR(inode->i_mode))
+		gfsflags &= ~GFS2_DIF_JDATA;
+	else
+		gfsflags &= ~GFS2_DIF_INHERIT_JDATA;
+	for (i = 0; i < ARRAY_SIZE(fsflag_gfs2flag); i++)
+		if (gfsflags & fsflag_gfs2flag[i].gfsflag)
+			fsflags |= fsflag_gfs2flag[i].fsflag;
+
 	if (put_user(fsflags, ptr))
 		error = -EFAULT;
 
···
 			     GFS2_DIF_APPENDONLY|		\
 			     GFS2_DIF_NOATIME|			\
 			     GFS2_DIF_SYNC|			\
-			     GFS2_DIF_SYSTEM|			\
 			     GFS2_DIF_TOPDIR|			\
 			     GFS2_DIF_INHERIT_JDATA)
 
···
 	if ((new_flags ^ flags) == 0)
 		goto out;
 
-	error = -EINVAL;
-	if ((new_flags ^ flags) & ~GFS2_FLAGS_USER_SET)
-		goto out;
-
 	error = -EPERM;
 	if (IS_IMMUTABLE(inode) && (new_flags & GFS2_DIF_IMMUTABLE))
 		goto out;
···
 			goto out;
 	}
 	if ((flags ^ new_flags) & GFS2_DIF_JDATA) {
-		if (flags & GFS2_DIF_JDATA)
+		if (new_flags & GFS2_DIF_JDATA)
 			gfs2_log_flush(sdp, ip->i_gl, NORMAL_FLUSH);
 		error = filemap_fdatawrite(inode->i_mapping);
 		if (error)
···
 		error = filemap_fdatawait(inode->i_mapping);
 		if (error)
 			goto out;
+		if (new_flags & GFS2_DIF_JDATA)
+			gfs2_ordered_del_inode(ip);
 	}
 	error = gfs2_trans_begin(sdp, RES_DINODE, 0);
 	if (error)
···
 	error = gfs2_meta_inode_buffer(ip, &bh);
 	if (error)
 		goto out_trans_end;
+	inode->i_ctime = current_time(inode);
 	gfs2_trans_add_meta(ip->i_gl, bh);
 	ip->i_diskflags = new_flags;
 	gfs2_dinode_out(ip, bh->b_data);
···
 static int gfs2_set_flags(struct file *filp, u32 __user *ptr)
 {
 	struct inode *inode = file_inode(filp);
-	u32 fsflags, gfsflags;
+	u32 fsflags, gfsflags = 0;
+	u32 mask;
+	int i;
 
 	if (get_user(fsflags, ptr))
 		return -EFAULT;
 
-	gfsflags = fsflags_cvt(fsflags_to_gfs2, fsflags);
-	if (!S_ISDIR(inode->i_mode)) {
-		gfsflags &= ~GFS2_DIF_TOPDIR;
-		if (gfsflags & GFS2_DIF_INHERIT_JDATA)
-			gfsflags ^= (GFS2_DIF_JDATA | GFS2_DIF_INHERIT_JDATA);
-		return do_gfs2_set_flags(filp, gfsflags, ~GFS2_DIF_SYSTEM);
+	for (i = 0; i < ARRAY_SIZE(fsflag_gfs2flag); i++) {
+		if (fsflags & fsflag_gfs2flag[i].fsflag) {
+			fsflags &= ~fsflag_gfs2flag[i].fsflag;
+			gfsflags |= fsflag_gfs2flag[i].gfsflag;
+		}
 	}
-	return do_gfs2_set_flags(filp, gfsflags, ~(GFS2_DIF_SYSTEM | GFS2_DIF_JDATA));
+	if (fsflags || gfsflags & ~GFS2_FLAGS_USER_SET)
+		return -EINVAL;
+
+	mask = GFS2_FLAGS_USER_SET;
+	if (S_ISDIR(inode->i_mode)) {
+		mask &= ~GFS2_DIF_JDATA;
+	} else {
+		/* The GFS2_DIF_TOPDIR flag is only valid for directories. */
+		if (gfsflags & GFS2_DIF_TOPDIR)
+			return -EINVAL;
+		mask &= ~(GFS2_DIF_TOPDIR | GFS2_DIF_INHERIT_JDATA);
+	}
+
+	return do_gfs2_set_flags(filp, gfsflags, mask);
 }
 
 static long gfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)

fs/gfs2/inode.c

···
 #include <linux/posix_acl.h>
 #include <linux/gfs2_ondisk.h>
 #include <linux/crc32.h>
-#include <linux/fiemap.h>
+#include <linux/iomap.h>
 #include <linux/security.h>
 #include <linux/uaccess.h>
 
···
 
 		gfs2_set_iop(inode);
 
-		inode->i_atime.tv_sec = 0;
+		/* Lowest possible timestamp; will be overwritten in gfs2_dinode_in. */
+		inode->i_atime.tv_sec = 1LL << (8 * sizeof(inode->i_atime.tv_sec) - 1);
 		inode->i_atime.tv_nsec = 0;
 
 		unlock_new_inode(inode);
···
 	struct inode *inode = d_inode(path->dentry);
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_holder gh;
+	u32 gfsflags;
 	int error;
 
 	gfs2_holder_mark_uninitialized(&gh);
···
 			return error;
 	}
 
+	gfsflags = ip->i_diskflags;
+	if (gfsflags & GFS2_DIF_APPENDONLY)
+		stat->attributes |= STATX_ATTR_APPEND;
+	if (gfsflags & GFS2_DIF_IMMUTABLE)
+		stat->attributes |= STATX_ATTR_IMMUTABLE;
+
+	stat->attributes_mask |= (STATX_ATTR_APPEND |
+				  STATX_ATTR_COMPRESSED |
+				  STATX_ATTR_ENCRYPTED |
+				  STATX_ATTR_IMMUTABLE |
+				  STATX_ATTR_NODUMP);
+
 	generic_fillattr(inode, stat);
+
 	if (gfs2_holder_initialized(&gh))
 		gfs2_glock_dq_uninit(&gh);
 
 	return 0;
 }
+
+const struct iomap_ops gfs2_iomap_ops = {
+	.iomap_begin = gfs2_iomap_begin,
+};
 
 static int gfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		       u64 start, u64 len)
···
 	struct gfs2_holder gh;
 	int ret;
 
-	ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
-	if (ret)
-		return ret;
-
-	inode_lock(inode);
+	inode_lock_shared(inode);
 
 	ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
 	if (ret)
 		goto out;
 
-	if (gfs2_is_stuffed(ip)) {
-		u64 phys = ip->i_no_addr << inode->i_blkbits;
-		u64 size = i_size_read(inode);
-		u32 flags = FIEMAP_EXTENT_LAST|FIEMAP_EXTENT_NOT_ALIGNED|
-			    FIEMAP_EXTENT_DATA_INLINE;
-		phys += sizeof(struct gfs2_dinode);
-		phys += start;
-		if (start + len > size)
-			len = size - start;
-		if (start < size)
-			ret = fiemap_fill_next_extent(fieinfo, start, phys,
-						      len, flags);
-		if (ret == 1)
-			ret = 0;
-	} else {
-		ret = __generic_block_fiemap(inode, fieinfo, start, len,
-					     gfs2_block_map);
-	}
+	ret = iomap_fiemap(inode, fieinfo, start, len, &gfs2_iomap_ops);
 
 	gfs2_glock_dq_uninit(&gh);
+
 out:
-	inode_unlock(inode);
+	inode_unlock_shared(inode);
 	return ret;
+}
+
+loff_t gfs2_seek_data(struct file *file, loff_t offset)
+{
+	struct inode *inode = file->f_mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder gh;
+	loff_t ret;
+
+	inode_lock_shared(inode);
+	ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+	if (!ret)
+		ret = iomap_seek_data(inode, offset, &gfs2_iomap_ops);
+	gfs2_glock_dq_uninit(&gh);
+	inode_unlock_shared(inode);
+
+	if (ret < 0)
+		return ret;
+	return vfs_setpos(file, ret, inode->i_sb->s_maxbytes);
+}
+
+loff_t gfs2_seek_hole(struct file *file, loff_t offset)
+{
+	struct inode *inode = file->f_mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder gh;
+	loff_t ret;
+
+	inode_lock_shared(inode);
+	ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+	if (!ret)
+		ret = iomap_seek_hole(inode, offset, &gfs2_iomap_ops);
+	gfs2_glock_dq_uninit(&gh);
+	inode_unlock_shared(inode);
+
+	if (ret < 0)
+		return ret;
+	return vfs_setpos(file, ret, inode->i_sb->s_maxbytes);
 }
 
 const struct inode_operations gfs2_file_iops = {

fs/gfs2/inode.h

···
 extern struct inode *gfs2_lookup_simple(struct inode *dip, const char *name);
 extern void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf);
 extern int gfs2_open_common(struct inode *inode, struct file *file);
+extern loff_t gfs2_seek_data(struct file *file, loff_t offset);
+extern loff_t gfs2_seek_hole(struct file *file, loff_t offset);
 
 extern const struct inode_operations gfs2_file_iops;
 extern const struct inode_operations gfs2_dir_iops;

fs/gfs2/super.c

···
 	struct address_space *metamapping = gfs2_glock2aspace(ip->i_gl);
 	struct backing_dev_info *bdi = inode_to_bdi(metamapping->host);
 	int ret = 0;
+	bool flush_all = (wbc->sync_mode == WB_SYNC_ALL || gfs2_is_jdata(ip));
 
-	if (wbc->sync_mode == WB_SYNC_ALL)
+	if (flush_all)
 		gfs2_log_flush(GFS2_SB(inode), ip->i_gl, NORMAL_FLUSH);
 	if (bdi->wb.dirty_exceeded)
 		gfs2_ail1_flush(sdp, wbc);
 	else
 		filemap_fdatawrite(metamapping);
-	if (wbc->sync_mode == WB_SYNC_ALL)
+	if (flush_all)
 		ret = filemap_fdatawait(metamapping);
 	if (ret)
 		mark_inode_dirty_sync(inode);

fs/gfs2/trace_gfs2.h

···
 #include <linux/gfs2_ondisk.h>
 #include <linux/writeback.h>
 #include <linux/ktime.h>
+#include <linux/iomap.h>
 #include "incore.h"
 #include "glock.h"
 #include "rgrp.h"
···
 		  (unsigned long long)__entry->pblock,
 		  __entry->state, __entry->create ? "create " : "nocreate",
 		  __entry->errno)
+);
+
+TRACE_EVENT(gfs2_iomap_start,
+
+	TP_PROTO(const struct gfs2_inode *ip, loff_t pos, ssize_t length,
+		 u16 flags),
+
+	TP_ARGS(ip, pos, length, flags),
+
+	TP_STRUCT__entry(
+		__field(        dev_t,  dev                     )
+		__field(	u64,	inum			)
+		__field(	loff_t, pos			)
+		__field(	ssize_t, length			)
+		__field(	u16,	flags			)
+	),
+
+	TP_fast_assign(
+		__entry->dev            = ip->i_gl->gl_name.ln_sbd->sd_vfs->s_dev;
+		__entry->inum		= ip->i_no_addr;
+		__entry->pos		= pos;
+		__entry->length		= length;
+		__entry->flags		= flags;
+	),
+
+	TP_printk("%u,%u bmap %llu iomap start %llu/%lu flags:%08x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long long)__entry->inum,
+		  (unsigned long long)__entry->pos,
+		  (unsigned long)__entry->length, (u16)__entry->flags)
+);
+
+TRACE_EVENT(gfs2_iomap_end,
+
+	TP_PROTO(const struct gfs2_inode *ip, struct iomap *iomap, int ret),
+
+	TP_ARGS(ip, iomap, ret),
+
+	TP_STRUCT__entry(
+		__field(        dev_t,  dev                     )
+		__field(	u64,	inum			)
+		__field(	loff_t, offset			)
+		__field(	ssize_t, length			)
+		__field(	u16,	flags			)
+		__field(	u16,	type			)
+		__field(	int,	ret			)
+	),
+
+	TP_fast_assign(
+		__entry->dev            = ip->i_gl->gl_name.ln_sbd->sd_vfs->s_dev;
+		__entry->inum		= ip->i_no_addr;
+		__entry->offset		= iomap->offset;
+		__entry->length		= iomap->length;
+		__entry->flags		= iomap->flags;
+		__entry->type		= iomap->type;
+		__entry->ret		= ret;
+	),
+
+	TP_printk("%u,%u bmap %llu iomap end %llu/%lu ty:%d flags:%08x rc:%d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long long)__entry->inum,
+		  (unsigned long long)__entry->offset,
+		  (unsigned long)__entry->length, (u16)__entry->type,
+		  (u16)__entry->flags, __entry->ret)
 );
 
 /* Keep track of blocks as they are allocated/freed */

fs/gfs2/trans.c

···
  *
  * This is used in two distinct cases:
  * i) In ordered write mode
- *    We put the data buffer on a list so that we can ensure that its
+ *    We put the data buffer on a list so that we can ensure that it's
  *    synced to disk at the right time
  * ii) In journaled data mode
  *    We need to journal the data block in the same way as metadata in

fs/gfs2/xattr.c

···
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_rgrpd *rgd;
 	struct gfs2_holder rg_gh;
-	struct buffer_head *dibh;
 	__be64 *dataptrs;
 	u64 bn = 0;
 	u64 bstart = 0;
···
 		ea->ea_num_ptrs = 0;
 	}
 
-	error = gfs2_meta_inode_buffer(ip, &dibh);
-	if (!error) {
-		ip->i_inode.i_ctime = current_time(&ip->i_inode);
-		gfs2_trans_add_meta(ip->i_gl, dibh);
-		gfs2_dinode_out(ip, dibh->b_data);
-		brelse(dibh);
-	}
+	ip->i_inode.i_ctime = current_time(&ip->i_inode);
+	__mark_inode_dirty(&ip->i_inode, I_DIRTY_SYNC | I_DIRTY_DATASYNC);
 
 	gfs2_trans_end(sdp);
 
···
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_holder gh;
-	bool need_unlock = false;
 	int ret;
 
 	/* During lookup, SELinux calls this function with the glock locked. */
···
 		ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &gh);
 		if (ret)
 			return ret;
-		need_unlock = true;
+	} else {
+		gfs2_holder_mark_uninitialized(&gh);
 	}
 	ret = __gfs2_xattr_get(inode, name, buffer, size, handler->flags);
-	if (need_unlock)
+	if (gfs2_holder_initialized(&gh))
 		gfs2_glock_dq_uninit(&gh);
 	return ret;
 }
···
 			     ea_skeleton_call_t skeleton_call, void *private)
 {
 	struct gfs2_alloc_parms ap = { .target = blks };
-	struct buffer_head *dibh;
 	int error;
 
 	error = gfs2_rindex_update(GFS2_SB(&ip->i_inode));
···
 	if (error)
 		goto out_end_trans;
 
-	error = gfs2_meta_inode_buffer(ip, &dibh);
-	if (!error) {
-		ip->i_inode.i_ctime = current_time(&ip->i_inode);
-		gfs2_trans_add_meta(ip->i_gl, dibh);
-		gfs2_dinode_out(ip, dibh->b_data);
-		brelse(dibh);
-	}
+	ip->i_inode.i_ctime = current_time(&ip->i_inode);
+	__mark_inode_dirty(&ip->i_inode, I_DIRTY_SYNC | I_DIRTY_DATASYNC);
 
 out_end_trans:
 	gfs2_trans_end(GFS2_SB(&ip->i_inode));
···
 				 struct gfs2_ea_header *ea, struct ea_set *es)
 {
 	struct gfs2_ea_request *er = es->es_er;
-	struct buffer_head *dibh;
 	int error;
 
 	error = gfs2_trans_begin(GFS2_SB(&ip->i_inode), RES_DINODE + 2 * RES_EATTR, 0);
···
 	if (es->es_el)
 		ea_set_remove_stuffed(ip, es->es_el);
 
-	error = gfs2_meta_inode_buffer(ip, &dibh);
-	if (error)
-		goto out;
 	ip->i_inode.i_ctime = current_time(&ip->i_inode);
-	gfs2_trans_add_meta(ip->i_gl, dibh);
-	gfs2_dinode_out(ip, dibh->b_data);
-	brelse(dibh);
-out:
+	__mark_inode_dirty(&ip->i_inode, I_DIRTY_SYNC | I_DIRTY_DATASYNC);
+
 	gfs2_trans_end(GFS2_SB(&ip->i_inode));
 	return error;
 }
···
 {
 	struct gfs2_ea_header *ea = el->el_ea;
 	struct gfs2_ea_header *prev = el->el_prev;
-	struct buffer_head *dibh;
 	int error;
 
 	error = gfs2_trans_begin(GFS2_SB(&ip->i_inode), RES_DINODE + RES_EATTR, 0);
···
 		ea->ea_type = GFS2_EATYPE_UNUSED;
 	}
 
-	error = gfs2_meta_inode_buffer(ip, &dibh);
-	if (!error) {
-		ip->i_inode.i_ctime = current_time(&ip->i_inode);
-		gfs2_trans_add_meta(ip->i_gl, dibh);
-		gfs2_dinode_out(ip, dibh->b_data);
-		brelse(dibh);
-	}
+	ip->i_inode.i_ctime = current_time(&ip->i_inode);
+	__mark_inode_dirty(&ip->i_inode, I_DIRTY_SYNC | I_DIRTY_DATASYNC);
 
 	gfs2_trans_end(GFS2_SB(&ip->i_inode));
 
···
 	if (ret)
 		return ret;
 
-	ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
-	if (ret)
-		return ret;
+	/* May be called from gfs_setattr with the glock locked. */
+
+	if (!gfs2_glock_is_locked_by_me(ip->i_gl)) {
+		ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+		if (ret)
+			return ret;
+	} else {
+		if (WARN_ON_ONCE(ip->i_gl->gl_state != LM_ST_EXCLUSIVE))
+			return -EIO;
+		gfs2_holder_mark_uninitialized(&gh);
+	}
 	ret = __gfs2_xattr_set(inode, name, value, size, flags, handler->flags);
-	gfs2_glock_dq_uninit(&gh);
+	if (gfs2_holder_initialized(&gh))
+		gfs2_glock_dq_uninit(&gh);
 	return ret;
 }
 

include/linux/iomap.h

···
 /*
  * Flags for all iomap mappings:
  */
-#define IOMAP_F_NEW	0x01	/* blocks have been newly allocated */
+#define IOMAP_F_NEW		0x01	/* blocks have been newly allocated */
+#define IOMAP_F_BOUNDARY	0x02	/* mapping ends at metadata boundary */
 
 /*
  * Flags that only need to be reported for IOMAP_REPORT requests: