Skip to contentSkip to conversation

xfs: add FALLOC_FL_WRITE_ZEROES to XFS code base

PATCH In review [email protected] 4 participants 4 messages Jan 20 – Jan 29 XFS filesystem

lore
Share & tools
lore

[email protected]

author maintainer
#0 lore raw

PATCH v7 1/1 xfs: add FALLOC_FL_WRITE_ZEROES to XFS code base

From: Lukas Herbolt <[email protected]>

Add support for FALLOC_FL_WRITE_ZEROES if the underlying device enable the unmap write zeroes operation.

[cem: rewrite xfs_falloc_zero_range() bits]

---

Christoph, Darrick, could you please review/ack this patch again? I needed to rewrite the xfs_falloc_zero_range() bits, because it conflicted with 66d78a11479c and 8dc15b7a6e59. This version aims mostly to remove one of the if-else nested levels to keep it a bit cleaner.

please let me know if you agree with this version, otherwise I'll ask Lukas to rebase it on top of the new code.

Thanks!

 fs/xfs/xfs_bmap_util.c | 10 ++++++++--
 fs/xfs/xfs_bmap_util.h |  2 +-
 fs/xfs/xfs_file.c      | 38 +++++++++++++++++++++++++++-----------
 3 files changed, 36 insertions(+), 14 deletions(-)
fs/xfs/xfs_bmap_util.c +8 -2
index 0ab00615f1ad..74a7597d0998 100644
@@ -642,11 +642,17 @@ xfs_free_eofblocks(
 	return error;
 }
 
+/*
+ * Callers can specify bmapi_flags, if XFS_BMAPI_ZERO is used there are no
+ * further checks whether the hard ware supports and it can fallback to
+ * software zeroing.
+ */
 int
 xfs_alloc_file_space(
 	struct xfs_inode	*ip,
 	xfs_off_t		offset,
-	xfs_off_t		len)
+	xfs_off_t		len,
+	uint32_t		bmapi_flags)
 {
 	xfs_mount_t		*mp = ip->i_mount;
 	xfs_off_t		count;
@@ -748,7 +754,7 @@ xfs_alloc_file_space(
 		 * will eventually reach the requested range.
 		 */
 		error = xfs_bmapi_write(tp, ip, startoffset_fsb,
-				allocatesize_fsb, XFS_BMAPI_PREALLOC, 0, imapp,
+				allocatesize_fsb, bmapi_flags, 0, imapp,
 				&nimaps);
 		if (error) {
 			if (error != -ENOSR)
fs/xfs/xfs_bmap_util.h +1 -1
index c477b3361630..2895cc97a572 100644
@@ -56,7 +56,7 @@ int	xfs_bmap_last_extent(struct xfs_trans *tp, struct xfs_inode *ip,
 
 /* preallocation and hole punch interface */
 int	xfs_alloc_file_space(struct xfs_inode *ip, xfs_off_t offset,
-		xfs_off_t len);
+		xfs_off_t len, uint32_t bmapi_flags);
 int	xfs_free_file_space(struct xfs_inode *ip, xfs_off_t offset,
 		xfs_off_t len, struct xfs_zone_alloc_ctx *ac);
 int	xfs_collapse_file_space(struct xfs_inode *, xfs_off_t offset,
fs/xfs/xfs_file.c +27 -11
index d36a9aafa8ab..b23f1373116e 100644
@@ -1302,16 +1302,29 @@ xfs_falloc_zero_range(
 
 	if (xfs_falloc_force_zero(ip, ac)) {
 		error = xfs_zero_range(ip, offset, len, ac, NULL);
-	} else {
-		error = xfs_free_file_space(ip, offset, len, ac);
-		if (error)
-			return error;
+		goto out;
+	}
 
-		len = round_up(offset + len, blksize) -
-			round_down(offset, blksize);
-		offset = round_down(offset, blksize);
-		error = xfs_alloc_file_space(ip, offset, len);
+	error = xfs_free_file_space(ip, offset, len, ac);
+	if (error)
+		return error;
+
+	len = round_up(offset + len, blksize) - round_down(offset, blksize);
+	offset = round_down(offset, blksize);
+
+	if (mode & FALLOC_FL_WRITE_ZEROES) {
+		if (xfs_is_always_cow_inode(ip) ||
+		    !bdev_write_zeroes_unmap_sectors(
+				xfs_inode_buftarg(ip)->bt_bdev))
+			return -EOPNOTSUPP;
+		error = xfs_alloc_file_space(ip, offset, len,
+					     XFS_BMAPI_ZERO);
+	} else {
+		error = xfs_alloc_file_space(ip, offset, len,
+					     XFS_BMAPI_PREALLOC);
 	}
+
+out:
 	if (error)
 		return error;
 	return xfs_falloc_setsize(file, new_size);
@@ -1336,7 +1349,8 @@ xfs_falloc_unshare_range(
 	if (error)
 		return error;
 
-	error = xfs_alloc_file_space(XFS_I(inode), offset, len);
+	error = xfs_alloc_file_space(XFS_I(inode), offset, len,
+			XFS_BMAPI_PREALLOC);
 	if (error)
 		return error;
 	return xfs_falloc_setsize(file, new_size);
@@ -1364,7 +1378,8 @@ xfs_falloc_allocate_range(
 	if (error)
 		return error;
 
-	error = xfs_alloc_file_space(XFS_I(inode), offset, len);
+	error = xfs_alloc_file_space(XFS_I(inode), offset, len,
+			XFS_BMAPI_PREALLOC);
 	if (error)
 		return error;
 	return xfs_falloc_setsize(file, new_size);
@@ -1374,7 +1389,7 @@ xfs_falloc_allocate_range(
 		(FALLOC_FL_ALLOCATE_RANGE | FALLOC_FL_KEEP_SIZE |	\
 		 FALLOC_FL_PUNCH_HOLE |	FALLOC_FL_COLLAPSE_RANGE |	\
 		 FALLOC_FL_ZERO_RANGE |	FALLOC_FL_INSERT_RANGE |	\
-		 FALLOC_FL_UNSHARE_RANGE)
+		 FALLOC_FL_UNSHARE_RANGE | FALLOC_FL_WRITE_ZEROES)
 
 STATIC long
 __xfs_file_fallocate(
@@ -1417,6 +1432,7 @@ __xfs_file_fallocate(
 	case FALLOC_FL_INSERT_RANGE:
 		error = xfs_falloc_insert_range(file, offset, len);
 		break;
+	case FALLOC_FL_WRITE_ZEROES:
 	case FALLOC_FL_ZERO_RANGE:
 		error = xfs_falloc_zero_range(file, mode, offset, len, ac);
 		break;
Signature · 1 line
2.52.0
#1 lore raw
Quoted 90 lines · On Tue, Jan 20, 2026 at 02:20:50PM +0100, [email protected] wrote:

From: Lukas Herbolt <[email protected]>

Add support for FALLOC_FL_WRITE_ZEROES if the underlying device enable the unmap write zeroes operation.

[cem: rewrite xfs_falloc_zero_range() bits]

---

Christoph, Darrick, could you please review/ack this patch again? I needed to rewrite the xfs_falloc_zero_range() bits, because it conflicted with 66d78a11479c and 8dc15b7a6e59. This version aims mostly to remove one of the if-else nested levels to keep it a bit cleaner.

please let me know if you agree with this version, otherwise I'll ask Lukas to rebase it on top of the new code.

Thanks!

 fs/xfs/xfs_bmap_util.c | 10 ++++++++--
 fs/xfs/xfs_bmap_util.h |  2 +-
 fs/xfs/xfs_file.c      | 38 +++++++++++++++++++++++++++-----------
 3 files changed, 36 insertions(+), 14 deletions(-)
fs/xfs/xfs_bmap_util.c +8 -2
index 0ab00615f1ad..74a7597d0998 100644
@@ -642,11 +642,17 @@ xfs_free_eofblocks(
 	return error;
 }
 
+/*
+ * Callers can specify bmapi_flags, if XFS_BMAPI_ZERO is used there are no
+ * further checks whether the hard ware supports and it can fallback to
+ * software zeroing.
+ */
 int
 xfs_alloc_file_space(
 	struct xfs_inode	*ip,
 	xfs_off_t		offset,
-	xfs_off_t		len)
+	xfs_off_t		len,
+	uint32_t		bmapi_flags)
 {
 	xfs_mount_t		*mp = ip->i_mount;
 	xfs_off_t		count;
@@ -748,7 +754,7 @@ xfs_alloc_file_space(
 		 * will eventually reach the requested range.
 		 */
 		error = xfs_bmapi_write(tp, ip, startoffset_fsb,
-				allocatesize_fsb, XFS_BMAPI_PREALLOC, 0, imapp,
+				allocatesize_fsb, bmapi_flags, 0, imapp,
 				&nimaps);
 		if (error) {
 			if (error != -ENOSR)
fs/xfs/xfs_bmap_util.h +1 -1
index c477b3361630..2895cc97a572 100644
@@ -56,7 +56,7 @@ int	xfs_bmap_last_extent(struct xfs_trans *tp, struct xfs_inode *ip,
 
 /* preallocation and hole punch interface */
 int	xfs_alloc_file_space(struct xfs_inode *ip, xfs_off_t offset,
-		xfs_off_t len);
+		xfs_off_t len, uint32_t bmapi_flags);
 int	xfs_free_file_space(struct xfs_inode *ip, xfs_off_t offset,
 		xfs_off_t len, struct xfs_zone_alloc_ctx *ac);
 int	xfs_collapse_file_space(struct xfs_inode *, xfs_off_t offset,
fs/xfs/xfs_file.c +4 -8
index d36a9aafa8ab..b23f1373116e 100644
@@ -1302,16 +1302,29 @@ xfs_falloc_zero_range(
 
 	if (xfs_falloc_force_zero(ip, ac)) {
 		error = xfs_zero_range(ip, offset, len, ac, NULL);
-	} else {
-		error = xfs_free_file_space(ip, offset, len, ac);
-		if (error)
-			return error;
+		goto out;
+	}
 
-		len = round_up(offset + len, blksize) -
-			round_down(offset, blksize);
-		offset = round_down(offset, blksize);
-		error = xfs_alloc_file_space(ip, offset, len);
+	error = xfs_free_file_space(ip, offset, len, ac);
+	if (error)

fs/xfs/xfs_file.c xfs_falloc_zero_range( · line 1319

Quoted 10 lines
fs/xfs/xfs_file.c +10 -0
+		return error;
+
+	len = round_up(offset + len, blksize) - round_down(offset, blksize);
+	offset = round_down(offset, blksize);
+
+	if (mode & FALLOC_FL_WRITE_ZEROES) {
+		if (xfs_is_always_cow_inode(ip) ||
+		    !bdev_write_zeroes_unmap_sectors(
+				xfs_inode_buftarg(ip)->bt_bdev))
+			return -EOPNOTSUPP;

Taking a second look -- this code allows ZERO_RANGE|WRITE_ZEROES to punch out the file space but then fail with EOPNOTSUPP. I think if we're going to error out that way, we should do that at the top of the function before any changes are made.

--D

Quoted 52 lines
fs/xfs/xfs_file.c +13 -3
+		error = xfs_alloc_file_space(ip, offset, len,
+					     XFS_BMAPI_ZERO);
+	} else {
+		error = xfs_alloc_file_space(ip, offset, len,
+					     XFS_BMAPI_PREALLOC);
 	}
+
+out:
 	if (error)
 		return error;
 	return xfs_falloc_setsize(file, new_size);
@@ -1336,7 +1349,8 @@ xfs_falloc_unshare_range(
 	if (error)
 		return error;
 
-	error = xfs_alloc_file_space(XFS_I(inode), offset, len);
+	error = xfs_alloc_file_space(XFS_I(inode), offset, len,
+			XFS_BMAPI_PREALLOC);
 	if (error)
 		return error;
 	return xfs_falloc_setsize(file, new_size);
@@ -1364,7 +1378,8 @@ xfs_falloc_allocate_range(
 	if (error)
 		return error;
 
-	error = xfs_alloc_file_space(XFS_I(inode), offset, len);
+	error = xfs_alloc_file_space(XFS_I(inode), offset, len,
+			XFS_BMAPI_PREALLOC);
 	if (error)
 		return error;
 	return xfs_falloc_setsize(file, new_size);
@@ -1374,7 +1389,7 @@ xfs_falloc_allocate_range(
 		(FALLOC_FL_ALLOCATE_RANGE | FALLOC_FL_KEEP_SIZE |	\
 		 FALLOC_FL_PUNCH_HOLE |	FALLOC_FL_COLLAPSE_RANGE |	\
 		 FALLOC_FL_ZERO_RANGE |	FALLOC_FL_INSERT_RANGE |	\
-		 FALLOC_FL_UNSHARE_RANGE)
+		 FALLOC_FL_UNSHARE_RANGE | FALLOC_FL_WRITE_ZEROES)
 
 STATIC long
 __xfs_file_fallocate(
@@ -1417,6 +1432,7 @@ __xfs_file_fallocate(
 	case FALLOC_FL_INSERT_RANGE:
 		error = xfs_falloc_insert_range(file, offset, len);
 		break;
+	case FALLOC_FL_WRITE_ZEROES:
 	case FALLOC_FL_ZERO_RANGE:
 		error = xfs_falloc_zero_range(file, mode, offset, len, ac);
 		break;
Signature · 1 line
2.52.0
#2 lore raw
In reply to [email protected]
Quoted 7 lines · On Tue, Jan 20, 2026 at 02:20:50PM +0100, [email protected] wrote:

From: Lukas Herbolt <[email protected]>

Add support for FALLOC_FL_WRITE_ZEROES if the underlying device enable the unmap write zeroes operation.

[cem: rewrite xfs_falloc_zero_range() bits]

Nit: once you modify something substantially and add your marker you also need to sign off on it.

Quoted 6 lines

---

Christoph, Darrick, could you please review/ack this patch again? I needed to rewrite the xfs_falloc_zero_range() bits, because it conflicted with 66d78a11479c and 8dc15b7a6e59. This version aims mostly to remove one of the if-else nested levels to keep it a bit cleaner.

Maybe mention the "merge conflict" in the above note?

Quoted 14 lines

index d36a9aafa8ab..b23f1373116e 100644

fs/xfs/xfs_file.c +6 -0
@@ -1302,16 +1302,29 @@ xfs_falloc_zero_range(
 
 	if (xfs_falloc_force_zero(ip, ac)) {
 		error = xfs_zero_range(ip, offset, len, ac, NULL);
+		goto out;
+	}
 
+	error = xfs_free_file_space(ip, offset, len, ac);
+	if (error)
+		return error;
+

fs/xfs/xfs_file.c xfs_falloc_zero_range( · line 1321

Quoted 10 lines
fs/xfs/xfs_file.c +10 -0
+	len = round_up(offset + len, blksize) - round_down(offset, blksize);
+	offset = round_down(offset, blksize);
+
+	if (mode & FALLOC_FL_WRITE_ZEROES) {
+		if (xfs_is_always_cow_inode(ip) ||
+		    !bdev_write_zeroes_unmap_sectors(
+				xfs_inode_buftarg(ip)->bt_bdev))
+			return -EOPNOTSUPP;
+		error = xfs_alloc_file_space(ip, offset, len,
+					     XFS_BMAPI_ZERO);

Darrick made a good point that we should check the not supported cases earlier, even if that is an issue in the original version. Also I don't think we should hit the force zero case for FALLOC_FL_WRITE_ZEROES. I.e., this should probably become something like:

	if (mode & FALLOC_FL_WRITE_ZEROES) {
		if (xfs_is_always_cow_inode(ip) ||
		    !bdev_write_zeroes_unmap_sectors(
				xfs_inode_buftarg(ip)->bt_bdev))
			return -EOPNOTSUPP;
		bmapi_flags = XFS_BMAPI_ZERO;
	} else {
	  	if (xfs_falloc_force_zero(ip, ac)) {
	  		error = xfs_zero_range(ip, offset, len, ac, NULL);
			goto set_filesize;
		}
		bmapi_flags = XFS_BMAPI_PREALLOC;
	}

	< free file space, round, etc.. >

	error = xfs_alloc_file_space(ip, offset, len, bmapi_flags);
#3 lore raw
Quoted 60 lines · Christoph Hellwig
Quoted 7 lines · On Tue, Jan 20, 2026 at 02:20:50PM +0100, [email protected] wrote:

From: Lukas Herbolt <[email protected]>

Add support for FALLOC_FL_WRITE_ZEROES if the underlying device enable the unmap write zeroes operation.

[cem: rewrite xfs_falloc_zero_range() bits]

Nit: once you modify something substantially and add your marker you also need to sign off on it.

Quoted 6 lines

---

Christoph, Darrick, could you please review/ack this patch again? I needed to rewrite the xfs_falloc_zero_range() bits, because it conflicted with 66d78a11479c and 8dc15b7a6e59. This version aims mostly to remove one of the if-else nested levels to keep it a bit cleaner.

Maybe mention the "merge conflict" in the above note?

Quoted 14 lines

index d36a9aafa8ab..b23f1373116e 100644

fs/xfs/xfs_file.c +6 -0
@@ -1302,16 +1302,29 @@ xfs_falloc_zero_range(
 
 	if (xfs_falloc_force_zero(ip, ac)) {
 		error = xfs_zero_range(ip, offset, len, ac, NULL);
+		goto out;
+	}
 
+	error = xfs_free_file_space(ip, offset, len, ac);
+	if (error)
+		return error;
+

fs/xfs/xfs_file.c xfs_falloc_zero_range( · line 1321

Quoted 10 lines
fs/xfs/xfs_file.c +10 -0
+	len = round_up(offset + len, blksize) - round_down(offset, blksize);
+	offset = round_down(offset, blksize);
+
+	if (mode & FALLOC_FL_WRITE_ZEROES) {
+		if (xfs_is_always_cow_inode(ip) ||
+		    !bdev_write_zeroes_unmap_sectors(
+				xfs_inode_buftarg(ip)->bt_bdev))
+			return -EOPNOTSUPP;
+		error = xfs_alloc_file_space(ip, offset, len,
+					     XFS_BMAPI_ZERO);

Darrick made a good point that we should check the not supported cases earlier, even if that is an issue in the original version. Also I don't think we should hit the force zero case for FALLOC_FL_WRITE_ZEROES. I.e., this should probably become something like:

	if (mode & FALLOC_FL_WRITE_ZEROES) {
		if (xfs_is_always_cow_inode(ip) ||
		    !bdev_write_zeroes_unmap_sectors(
				xfs_inode_buftarg(ip)->bt_bdev))
			return -EOPNOTSUPP;
		bmapi_flags = XFS_BMAPI_ZERO;
	} else {
	  	if (xfs_falloc_force_zero(ip, ac)) {
	  		error = xfs_zero_range(ip, offset, len, ac, NULL);
Quoted 8 lines
			goto set_filesize;
		}
		bmapi_flags = XFS_BMAPI_PREALLOC;
	}

	< free file space, round, etc.. >

	error = xfs_alloc_file_space(ip, offset, len, bmapi_flags);

ugh I missed this one, I will add the Darrick/Christoph earlier check and rebase to more recent version.