* [PATCH v4 19/25] xfs: remove unwritten extents after preallocations in fsverity metadata
From: Andrey Albershteyn @ 2026-03-09 19:23 UTC (permalink / raw)
To: linux-xfs, fsverity, linux-fsdevel, ebiggers
Cc: Andrey Albershteyn, hch, linux-ext4, linux-f2fs-devel,
linux-btrfs, djwong
In-Reply-To: <20260309192355.176980-1-aalbersh@kernel.org>
XFS preallocates spaces during writes. In normal I/O this space, if
unused, is removed by truncate. For files with fsverity, XFS does not
use truncate as fsverity metadata is stored past EOF.
After we're done with writing fsverity metadata iterate over extents in
that region and remove any unwritten ones. These would be preallocation
leftovers in the merkle tree holes and past fsverity descriptor.
Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
---
fs/xfs/xfs_fsverity.c | 62 +++++++++++++++++++++++++++++++++++++++++++
1 file changed, 62 insertions(+)
diff --git a/fs/xfs/xfs_fsverity.c b/fs/xfs/xfs_fsverity.c
index e5cd17ec15b6..f78e5f0c2fd0 100644
--- a/fs/xfs/xfs_fsverity.c
+++ b/fs/xfs/xfs_fsverity.c
@@ -21,6 +21,8 @@
#include "xfs_iomap.h"
#include "xfs_error.h"
#include "xfs_health.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_util.h"
#include <linux/fsverity.h>
#include <linux/iomap.h>
#include <linux/pagemap.h>
@@ -189,6 +191,58 @@ xfs_fsverity_delete_metadata(
return error;
}
+static int
+xfs_fsverity_cancel_unwritten(
+ struct xfs_inode *ip,
+ xfs_fileoff_t start,
+ xfs_fileoff_t end)
+{
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_trans *tp;
+ xfs_fileoff_t offset_fsb = XFS_B_TO_FSB(mp, start);
+ xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, end);
+ struct xfs_bmbt_irec imap;
+ int nimaps;
+ int error = 0;
+ int done;
+
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, 0, 0, 0, &tp);
+ if (error)
+ return error;
+
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ xfs_trans_ijoin(tp, ip, 0);
+
+ while (offset_fsb < end_fsb) {
+ nimaps = 1;
+
+ error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb,
+ &imap, &nimaps, 0);
+ if (error)
+ goto out_cancel;
+
+ if (nimaps == 0)
+ break;
+
+ if (imap.br_state == XFS_EXT_UNWRITTEN) {
+ error = xfs_bunmapi(tp, ip, imap.br_startoff,
+ imap.br_blockcount, 0, 1, &done);
+ if (error)
+ goto out_cancel;
+ }
+
+ offset_fsb = imap.br_startoff + imap.br_blockcount;
+ }
+
+ error = xfs_trans_commit(tp);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ return error;
+out_cancel:
+ xfs_trans_cancel(tp);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ return error;
+}
+
/*
* Prepare to enable fsverity by clearing old metadata.
@@ -264,6 +318,14 @@ xfs_fsverity_end_enable(
if (error)
goto out;
+ /*
+ * Remove unwritten extents left by preallocations in the merkle tree
+ * holes and past descriptor
+ */
+ error = xfs_fsverity_cancel_unwritten(ip, range_start, LLONG_MAX);
+ if (error)
+ goto out;
+
/*
* Set fsverity inode flag
*/
--
2.51.2
^ permalink raw reply related
* [PATCH v4 18/25] xfs: add fs-verity support
From: Andrey Albershteyn @ 2026-03-09 19:23 UTC (permalink / raw)
To: linux-xfs, fsverity, linux-fsdevel, ebiggers
Cc: Andrey Albershteyn, hch, linux-ext4, linux-f2fs-devel,
linux-btrfs, djwong
In-Reply-To: <20260309192355.176980-1-aalbersh@kernel.org>
Add integration with fs-verity. XFS stores fs-verity descriptor and
Merkle tree in the inode data fork at first block aligned to 64k past
EOF.
The Merkle tree reading/writing is done through iomap interface. The
data itself is read to the inode's page cache. When XFS reads from this
region iomap doesn't call into fsverity to verify it against Merkle
tree. For data, verification is done at ioend completion in a workqueue.
When fs-verity is enabled on an inode, the XFS_IVERITY_CONSTRUCTION
flag is set meaning that the Merkle tree is being build. The
initialization ends with storing of verity descriptor and setting
inode on-disk flag (XFS_DIFLAG2_VERITY). Lastly, the
XFS_IVERITY_CONSTRUCTION is dropped and I_VERITY is set on inode.
The descriptor is stored in a new block aligned to 64k after the last
Merkle tree block. The size of the descriptor is stored at the end of
the last descriptor block (descriptor can be multiple blocks).
Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
---
fs/xfs/xfs_bmap_util.c | 8 +
fs/xfs/xfs_fsverity.c | 342 ++++++++++++++++++++++++++++++++++++++++-
fs/xfs/xfs_fsverity.h | 2 +
fs/xfs/xfs_message.c | 4 +
fs/xfs/xfs_message.h | 1 +
fs/xfs/xfs_mount.h | 2 +
fs/xfs/xfs_super.c | 7 +
7 files changed, 365 insertions(+), 1 deletion(-)
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 0ab00615f1ad..18348f4fd2aa 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -31,6 +31,7 @@
#include "xfs_rtbitmap.h"
#include "xfs_rtgroup.h"
#include "xfs_zone_alloc.h"
+#include <linux/fsverity.h>
/* Kernel only BMAP related definitions and functions */
@@ -553,6 +554,13 @@ xfs_can_free_eofblocks(
if (last_fsb <= end_fsb)
return false;
+ /*
+ * Nothing to clean on fsverity inodes as they don't use prealloc and
+ * there no delalloc as only written data is fsverity metadata
+ */
+ if (IS_VERITY(VFS_I(ip)))
+ return false;
+
/*
* Check if there is an post-EOF extent to free. If there are any
* delalloc blocks attached to the inode (data fork delalloc
diff --git a/fs/xfs/xfs_fsverity.c b/fs/xfs/xfs_fsverity.c
index dc66ffb7d132..e5cd17ec15b6 100644
--- a/fs/xfs/xfs_fsverity.c
+++ b/fs/xfs/xfs_fsverity.c
@@ -4,14 +4,26 @@
*/
#include "xfs_platform.h"
#include "xfs_format.h"
-#include "xfs_inode.h"
#include "xfs_shared.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_fsverity.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_inode.h"
+#include "xfs_log_format.h"
+#include "xfs_bmap_util.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_trace.h"
+#include "xfs_quota.h"
#include "xfs_fsverity.h"
+#include "xfs_iomap.h"
+#include "xfs_error.h"
+#include "xfs_health.h"
#include <linux/fsverity.h>
#include <linux/iomap.h>
+#include <linux/pagemap.h>
/*
* At maximum of 8 levels with 128 hashes per block (32 bytes SHA-256) maximum
@@ -43,3 +55,331 @@ xfs_fsverity_is_file_data(
return fsverity_active(inode) &&
offset < xfs_fsverity_metadata_offset(ip);
}
+
+/*
+ * Retrieve the verity descriptor.
+ */
+static int
+xfs_fsverity_get_descriptor(
+ struct inode *inode,
+ void *buf,
+ size_t buf_size)
+{
+ struct xfs_inode *ip = XFS_I(inode);
+ struct xfs_mount *mp = ip->i_mount;
+ __be32 d_desc_size;
+ u32 desc_size;
+ u64 desc_size_pos;
+ int error;
+ u64 desc_pos;
+ struct xfs_bmbt_irec rec;
+ int is_empty;
+ uint32_t blocksize = i_blocksize(VFS_I(ip));
+ xfs_fileoff_t last_block_offset;
+
+ ASSERT(inode->i_flags & S_VERITY);
+ error = xfs_bmap_last_extent(NULL, ip, XFS_DATA_FORK, &rec, &is_empty);
+ if (error)
+ return error;
+
+ if (is_empty)
+ return -ENODATA;
+
+ last_block_offset =
+ XFS_FSB_TO_B(mp, rec.br_startoff + rec.br_blockcount);
+ if (last_block_offset < xfs_fsverity_metadata_offset(ip))
+ return -ENODATA;
+
+ desc_size_pos = last_block_offset - sizeof(__be32);
+ error = fsverity_pagecache_read(inode, (char *)&d_desc_size,
+ sizeof(d_desc_size), desc_size_pos);
+ if (error)
+ return error;
+
+ desc_size = be32_to_cpu(d_desc_size);
+ if (XFS_IS_CORRUPT(mp, desc_size > FS_VERITY_MAX_DESCRIPTOR_SIZE))
+ return -ERANGE;
+ if (XFS_IS_CORRUPT(mp, desc_size > desc_size_pos))
+ return -ERANGE;
+
+ if (!buf_size)
+ return desc_size;
+
+ if (XFS_IS_CORRUPT(mp, desc_size > buf_size))
+ return -ERANGE;
+
+ desc_pos = round_down(desc_size_pos - desc_size, blocksize);
+ error = fsverity_pagecache_read(inode, buf, desc_size, desc_pos);
+ if (error)
+ return error;
+
+ return desc_size;
+}
+
+static int
+xfs_fsverity_write_descriptor(
+ struct file *file,
+ const void *desc,
+ u32 desc_size,
+ u64 merkle_tree_size)
+{
+ int error;
+ struct inode *inode = file_inode(file);
+ struct xfs_inode *ip = XFS_I(inode);
+ unsigned int blksize = ip->i_mount->m_attr_geo->blksize;
+ u64 tree_last_block =
+ xfs_fsverity_metadata_offset(ip) + merkle_tree_size;
+ u64 desc_pos = round_up(tree_last_block, 65536);
+ u64 desc_end = desc_pos + desc_size;
+ __be32 desc_size_disk = cpu_to_be32(desc_size);
+ u64 desc_size_pos =
+ round_up(desc_end + sizeof(desc_size_disk), blksize) -
+ sizeof(desc_size_disk);
+
+ error = iomap_fsverity_write(file, desc_size_pos, sizeof(__be32),
+ (const void *)&desc_size_disk,
+ &xfs_buffered_write_iomap_ops,
+ &xfs_iomap_write_ops);
+ if (error)
+ return error;
+
+ error = iomap_fsverity_write(file, desc_pos, desc_size, desc,
+ &xfs_buffered_write_iomap_ops,
+ &xfs_iomap_write_ops);
+
+ return error;
+}
+
+/*
+ * Try to remove all the fsverity metadata after a failed enablement.
+ */
+static int
+xfs_fsverity_delete_metadata(
+ struct xfs_inode *ip)
+{
+ struct xfs_trans *tp;
+ struct xfs_mount *mp = ip->i_mount;
+ int error;
+
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
+ if (error)
+ return error;
+
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ xfs_trans_ijoin(tp, ip, 0);
+
+ /*
+ * We removing post EOF data, no need to update i_size as fsverity
+ * didn't move i_size in the first place
+ */
+ error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, XFS_ISIZE(ip));
+ if (error)
+ goto err_cancel;
+
+ error = xfs_trans_commit(tp);
+ if (error)
+ goto err_cancel;
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+ return error;
+
+err_cancel:
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ xfs_trans_cancel(tp);
+ return error;
+}
+
+
+/*
+ * Prepare to enable fsverity by clearing old metadata.
+ */
+static int
+xfs_fsverity_begin_enable(
+ struct file *filp)
+{
+ struct inode *inode = file_inode(filp);
+ struct xfs_inode *ip = XFS_I(inode);
+ int error;
+
+ xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL);
+
+ if (IS_DAX(inode))
+ return -EINVAL;
+
+ if (inode->i_size > XFS_FSVERITY_LARGEST_FILE)
+ return -EFBIG;
+
+ /*
+ * Flush pagecache before building Merkle tree. Inode is locked and no
+ * further writes will happen to the file except fsverity metadata
+ */
+ error = filemap_write_and_wait(inode->i_mapping);
+ if (error)
+ return error;
+
+ if (xfs_iflags_test_and_set(ip, XFS_VERITY_CONSTRUCTION))
+ return -EBUSY;
+
+ error = xfs_qm_dqattach(ip);
+ if (error)
+ return error;
+
+ return xfs_fsverity_delete_metadata(ip);
+}
+
+/*
+ * Complete (or fail) the process of enabling fsverity.
+ */
+static int
+xfs_fsverity_end_enable(
+ struct file *file,
+ const void *desc,
+ size_t desc_size,
+ u64 merkle_tree_size)
+{
+ struct inode *inode = file_inode(file);
+ struct xfs_inode *ip = XFS_I(inode);
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_trans *tp;
+ int error = 0;
+ loff_t range_start = xfs_fsverity_metadata_offset(ip);
+
+ xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL);
+
+ /* fs-verity failed, just cleanup */
+ if (desc == NULL)
+ goto out;
+
+ error = xfs_fsverity_write_descriptor(file, desc, desc_size,
+ merkle_tree_size);
+ if (error)
+ goto out;
+
+ /*
+ * Wait for Merkle tree get written to disk before setting on-disk inode
+ * flag and clearing XFS_VERITY_CONSTRUCTION
+ */
+ error = filemap_write_and_wait_range(inode->i_mapping, range_start,
+ LLONG_MAX);
+ if (error)
+ goto out;
+
+ /*
+ * Set fsverity inode flag
+ */
+ error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_ichange,
+ 0, 0, false, &tp);
+ if (error)
+ goto out;
+
+ /*
+ * Ensure that we've persisted the verity information before we enable
+ * it on the inode and tell the caller we have sealed the inode.
+ */
+ ip->i_diflags2 |= XFS_DIFLAG2_VERITY;
+
+ xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+ xfs_trans_set_sync(tp);
+
+ error = xfs_trans_commit(tp);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+ if (!error)
+ inode->i_flags |= S_VERITY;
+
+out:
+ if (error) {
+ int error2;
+
+ error2 = xfs_fsverity_delete_metadata(ip);
+ if (error2)
+ xfs_alert(ip->i_mount,
+"ino 0x%llx failed to clean up new fsverity metadata, err %d",
+ ip->i_ino, error2);
+ }
+
+ xfs_iflags_clear(ip, XFS_VERITY_CONSTRUCTION);
+ return error;
+}
+
+/*
+ * Retrieve a merkle tree block.
+ */
+static struct page *
+xfs_fsverity_read_merkle(
+ struct inode *inode,
+ pgoff_t index)
+{
+ index += xfs_fsverity_metadata_offset(XFS_I(inode)) >> PAGE_SHIFT;
+
+ return generic_read_merkle_tree_page(inode, index);
+}
+
+/*
+ * Retrieve a merkle tree block.
+ */
+static void
+xfs_fsverity_readahead_merkle_tree(
+ struct inode *inode,
+ pgoff_t index,
+ unsigned long nr_pages)
+{
+ index += xfs_fsverity_metadata_offset(XFS_I(inode)) >> PAGE_SHIFT;
+
+ generic_readahead_merkle_tree(inode, index, nr_pages);
+}
+
+/*
+ * Write a merkle tree block.
+ */
+static int
+xfs_fsverity_write_merkle(
+ struct file *file,
+ const void *buf,
+ u64 pos,
+ unsigned int size,
+ const u8 *zero_digest,
+ unsigned int digest_size)
+{
+ struct inode *inode = file_inode(file);
+ struct xfs_inode *ip = XFS_I(inode);
+ loff_t position = pos +
+ xfs_fsverity_metadata_offset(ip);
+ const char *p;
+ unsigned int i;
+
+ if (position + size > inode->i_sb->s_maxbytes)
+ return -EFBIG;
+
+ /*
+ * If this is a block full of hashes of zeroed blocks, don't bother
+ * storing the block. We can synthesize them later.
+ *
+ * However, do this only in case Merkle tree block == fs block size.
+ * Iomap synthesizes these blocks based on holes in the merkle tree. We
+ * won't be able to tell if something need to be synthesizes for the
+ * range in the fs block. For example, for 4k filesystem block
+ *
+ * [ 1k | zero hashes | zero hashes | 1k ]
+ *
+ * Iomap won't know about these empty blocks.
+ */
+ for (i = 0, p = buf; i < size; i += digest_size, p += digest_size)
+ if (memcmp(p, zero_digest, digest_size))
+ break;
+ if (i == size && size == ip->i_mount->m_sb.sb_blocksize)
+ return 0;
+
+ return iomap_fsverity_write(file, position, size, buf,
+ &xfs_buffered_write_iomap_ops,
+ &xfs_iomap_write_ops);
+}
+
+const struct fsverity_operations xfs_fsverity_ops = {
+ .begin_enable_verity = xfs_fsverity_begin_enable,
+ .end_enable_verity = xfs_fsverity_end_enable,
+ .get_verity_descriptor = xfs_fsverity_get_descriptor,
+ .read_merkle_tree_page = xfs_fsverity_read_merkle,
+ .readahead_merkle_tree = xfs_fsverity_readahead_merkle_tree,
+ .write_merkle_tree_block = xfs_fsverity_write_merkle,
+};
diff --git a/fs/xfs/xfs_fsverity.h b/fs/xfs/xfs_fsverity.h
index ec77ba571106..6a981e20a75b 100644
--- a/fs/xfs/xfs_fsverity.h
+++ b/fs/xfs/xfs_fsverity.h
@@ -6,8 +6,10 @@
#define __XFS_FSVERITY_H__
#include "xfs_platform.h"
+#include <linux/fsverity.h>
#ifdef CONFIG_FS_VERITY
+extern const struct fsverity_operations xfs_fsverity_ops;
loff_t xfs_fsverity_metadata_offset(const struct xfs_inode *ip);
bool xfs_fsverity_is_file_data(const struct xfs_inode *ip, loff_t offset);
#else
diff --git a/fs/xfs/xfs_message.c b/fs/xfs/xfs_message.c
index fd297082aeb8..9818d8f8f239 100644
--- a/fs/xfs/xfs_message.c
+++ b/fs/xfs/xfs_message.c
@@ -153,6 +153,10 @@ xfs_warn_experimental(
.opstate = XFS_OPSTATE_WARNED_ZONED,
.name = "zoned RT device",
},
+ [XFS_EXPERIMENTAL_FSVERITY] = {
+ .opstate = XFS_OPSTATE_WARNED_FSVERITY,
+ .name = "fsverity",
+ },
};
ASSERT(feat >= 0 && feat < XFS_EXPERIMENTAL_MAX);
BUILD_BUG_ON(ARRAY_SIZE(features) != XFS_EXPERIMENTAL_MAX);
diff --git a/fs/xfs/xfs_message.h b/fs/xfs/xfs_message.h
index 49b0ef40d299..083403944f11 100644
--- a/fs/xfs/xfs_message.h
+++ b/fs/xfs/xfs_message.h
@@ -94,6 +94,7 @@ enum xfs_experimental_feat {
XFS_EXPERIMENTAL_SHRINK,
XFS_EXPERIMENTAL_LARP,
XFS_EXPERIMENTAL_ZONED,
+ XFS_EXPERIMENTAL_FSVERITY,
XFS_EXPERIMENTAL_MAX,
};
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index c746bc90cf3e..a4885fe7aa3b 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -583,6 +583,8 @@ __XFS_HAS_FEAT(nouuid, NOUUID)
#define XFS_OPSTATE_WARNED_ZONED 19
/* (Zoned) GC is in progress */
#define XFS_OPSTATE_ZONEGC_RUNNING 20
+/* Kernel has logged a warning about fsverity support */
+#define XFS_OPSTATE_WARNED_FSVERITY 21
#define __XFS_IS_OPSTATE(name, NAME) \
static inline bool xfs_is_ ## name (struct xfs_mount *mp) \
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index abc45f860a73..b7a16dc8de52 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -30,6 +30,7 @@
#include "xfs_filestream.h"
#include "xfs_quota.h"
#include "xfs_sysfs.h"
+#include "xfs_fsverity.h"
#include "xfs_ondisk.h"
#include "xfs_rmap_item.h"
#include "xfs_refcount_item.h"
@@ -1686,6 +1687,9 @@ xfs_fs_fill_super(
sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ;
#endif
sb->s_op = &xfs_super_operations;
+#ifdef CONFIG_FS_VERITY
+ sb->s_vop = &xfs_fsverity_ops;
+#endif
/*
* Delay mount work if the debug hook is set. This is debug
@@ -1939,6 +1943,9 @@ xfs_fs_fill_super(
if (error)
goto out_filestream_unmount;
+ if (xfs_has_verity(mp))
+ xfs_warn_experimental(mp, XFS_EXPERIMENTAL_FSVERITY);
+
root = igrab(VFS_I(mp->m_rootip));
if (!root) {
error = -ENOENT;
--
2.51.2
^ permalink raw reply related
* [PATCH v4 17/25] xfs: use read ioend for fsverity data verification
From: Andrey Albershteyn @ 2026-03-09 19:23 UTC (permalink / raw)
To: linux-xfs, fsverity, linux-fsdevel, ebiggers
Cc: Andrey Albershteyn, hch, linux-ext4, linux-f2fs-devel,
linux-btrfs, djwong
In-Reply-To: <20260309192355.176980-1-aalbersh@kernel.org>
Use read ioends for fsverity verification. Do not issues fsverity
metadata I/O through the same workqueue due to risk of a deadlock by a
filled workqueue.
Pass fsverity_info from iomap context down to the ioend as hashtable
lookups are expensive.
Add a simple helper to check that this is not fsverity metadata but file
data that needs verification.
Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
---
fs/xfs/xfs_aops.c | 32 ++++++++++++++++++++++++--------
fs/xfs/xfs_fsverity.c | 11 +++++++++++
fs/xfs/xfs_fsverity.h | 6 ++++++
3 files changed, 41 insertions(+), 8 deletions(-)
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 9503252a0fa4..4e3dcc4a321d 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -24,6 +24,7 @@
#include "xfs_rtgroup.h"
#include "xfs_fsverity.h"
#include <linux/bio-integrity.h>
+#include <linux/fsverity.h>
struct xfs_writepage_ctx {
struct iomap_writepage_ctx ctx;
@@ -204,11 +205,15 @@ xfs_end_io(
io_list))) {
list_del_init(&ioend->io_list);
iomap_ioend_try_merge(ioend, &tmp);
- if (bio_op(&ioend->io_bio) == REQ_OP_READ)
+ if (bio_op(&ioend->io_bio) == REQ_OP_READ) {
+ if (xfs_fsverity_is_file_data(ip, ioend->io_offset))
+ fsverity_verify_bio(ioend->io_vi,
+ &ioend->io_bio);
iomap_finish_ioends(ioend,
blk_status_to_errno(ioend->io_bio.bi_status));
- else
+ } else {
xfs_end_ioend_write(ioend);
+ }
cond_resched();
}
}
@@ -232,9 +237,14 @@ xfs_end_bio(
}
spin_lock_irqsave(&ip->i_ioend_lock, flags);
- if (list_empty(&ip->i_ioend_list))
- WARN_ON_ONCE(!queue_work(mp->m_unwritten_workqueue,
+ if (list_empty(&ip->i_ioend_list)) {
+ if (IS_ENABLED(CONFIG_FS_VERITY) && ioend->io_vi &&
+ ioend->io_offset < xfs_fsverity_metadata_offset(ip))
+ fsverity_enqueue_verify_work(&ip->i_ioend_work);
+ else
+ WARN_ON_ONCE(!queue_work(mp->m_unwritten_workqueue,
&ip->i_ioend_work));
+ }
list_add_tail(&ioend->io_list, &ip->i_ioend_list);
spin_unlock_irqrestore(&ip->i_ioend_lock, flags);
}
@@ -764,9 +774,12 @@ xfs_bio_submit_read(
struct iomap_read_folio_ctx *ctx)
{
struct bio *bio = ctx->read_ctx;
+ struct iomap_ioend *ioend;
/* defer read completions to the ioend workqueue */
- iomap_init_ioend(iter->inode, bio, ctx->read_ctx_file_offset, 0);
+ ioend = iomap_init_ioend(iter->inode, bio, ctx->read_ctx_file_offset, 0);
+ ioend->io_vi = ctx->vi;
+
bio->bi_end_io = xfs_end_bio;
submit_bio(bio);
}
@@ -779,12 +792,15 @@ static const struct iomap_read_ops xfs_iomap_read_ops = {
static inline const struct iomap_read_ops *
xfs_get_iomap_read_ops(
- const struct address_space *mapping)
+ const struct address_space *mapping,
+ loff_t position)
{
struct xfs_inode *ip = XFS_I(mapping->host);
if (bdev_has_integrity_csum(xfs_inode_buftarg(ip)->bt_bdev))
return &xfs_iomap_read_ops;
+ if (xfs_fsverity_is_file_data(ip, position))
+ return &xfs_iomap_read_ops;
return &iomap_bio_read_ops;
}
@@ -795,7 +811,7 @@ xfs_vm_read_folio(
{
struct iomap_read_folio_ctx ctx = { .cur_folio = folio };
- ctx.ops = xfs_get_iomap_read_ops(folio->mapping);
+ ctx.ops = xfs_get_iomap_read_ops(folio->mapping, folio_pos(folio));
iomap_read_folio(&xfs_read_iomap_ops, &ctx, NULL);
return 0;
}
@@ -806,7 +822,7 @@ xfs_vm_readahead(
{
struct iomap_read_folio_ctx ctx = { .rac = rac };
- ctx.ops = xfs_get_iomap_read_ops(rac->mapping),
+ ctx.ops = xfs_get_iomap_read_ops(rac->mapping, readahead_pos(rac));
iomap_readahead(&xfs_read_iomap_ops, &ctx, NULL);
}
diff --git a/fs/xfs/xfs_fsverity.c b/fs/xfs/xfs_fsverity.c
index bc6020cc6e41..dc66ffb7d132 100644
--- a/fs/xfs/xfs_fsverity.c
+++ b/fs/xfs/xfs_fsverity.c
@@ -32,3 +32,14 @@ xfs_fsverity_metadata_offset(
{
return round_up(i_size_read(VFS_IC(ip)), 65536);
}
+
+bool
+xfs_fsverity_is_file_data(
+ const struct xfs_inode *ip,
+ loff_t offset)
+{
+ const struct inode *inode = VFS_IC(ip);
+
+ return fsverity_active(inode) &&
+ offset < xfs_fsverity_metadata_offset(ip);
+}
diff --git a/fs/xfs/xfs_fsverity.h b/fs/xfs/xfs_fsverity.h
index 5771db2cd797..ec77ba571106 100644
--- a/fs/xfs/xfs_fsverity.h
+++ b/fs/xfs/xfs_fsverity.h
@@ -9,12 +9,18 @@
#ifdef CONFIG_FS_VERITY
loff_t xfs_fsverity_metadata_offset(const struct xfs_inode *ip);
+bool xfs_fsverity_is_file_data(const struct xfs_inode *ip, loff_t offset);
#else
static inline loff_t xfs_fsverity_metadata_offset(const struct xfs_inode *ip)
{
WARN_ON_ONCE(1);
return ULLONG_MAX;
}
+static inline bool xfs_fsverity_is_file_data(const struct xfs_inode *ip,
+ loff_t offset)
+{
+ return false;
+}
#endif /* CONFIG_FS_VERITY */
#endif /* __XFS_FSVERITY_H__ */
--
2.51.2
^ permalink raw reply related
* [PATCH v4 16/25] xfs: handle fsverity I/O in write/read path
From: Andrey Albershteyn @ 2026-03-09 19:23 UTC (permalink / raw)
To: linux-xfs, fsverity, linux-fsdevel, ebiggers
Cc: Andrey Albershteyn, hch, linux-ext4, linux-f2fs-devel,
linux-btrfs, djwong
In-Reply-To: <20260309192355.176980-1-aalbersh@kernel.org>
For write/writeback set IOMAP_F_FSVERITY flag telling iomap to not
update inode size and to not skip folios beyond EOF.
Initiate fsverity writeback with IOMAP_F_FSVERITY set to tell iomap
should not skip folio that is dirty beyond EOF.
In read path let iomap know that we are reading fsverity metadata. So,
treat holes in the tree as request to synthesize tree blocks and hole
after descriptor as end of the fsverity region.
Introduce a new inode flag meaning that merkle tree is being build on
the inode.
Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
---
fs/xfs/Makefile | 1 +
fs/xfs/libxfs/xfs_bmap.c | 7 +++++++
fs/xfs/xfs_aops.c | 16 +++++++++++++++-
fs/xfs/xfs_fsverity.c | 34 ++++++++++++++++++++++++++++++++++
fs/xfs/xfs_fsverity.h | 20 ++++++++++++++++++++
fs/xfs/xfs_inode.h | 6 ++++++
fs/xfs/xfs_iomap.c | 15 +++++++++++++--
7 files changed, 96 insertions(+), 3 deletions(-)
create mode 100644 fs/xfs/xfs_fsverity.c
create mode 100644 fs/xfs/xfs_fsverity.h
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 9f7133e02576..38b7f51e5d84 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -149,6 +149,7 @@ xfs-$(CONFIG_XFS_POSIX_ACL) += xfs_acl.o
xfs-$(CONFIG_SYSCTL) += xfs_sysctl.o
xfs-$(CONFIG_COMPAT) += xfs_ioctl32.o
xfs-$(CONFIG_EXPORTFS_BLOCK_OPS) += xfs_pnfs.o
+xfs-$(CONFIG_FS_VERITY) += xfs_fsverity.o
# notify failure
ifeq ($(CONFIG_MEMORY_FAILURE),y)
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 7a4c8f1aa76c..931d02678d19 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -41,6 +41,8 @@
#include "xfs_inode_util.h"
#include "xfs_rtgroup.h"
#include "xfs_zone_alloc.h"
+#include "xfs_fsverity.h"
+#include <linux/fsverity.h>
struct kmem_cache *xfs_bmap_intent_cache;
@@ -4451,6 +4453,11 @@ xfs_bmapi_convert_one_delalloc(
XFS_STATS_ADD(mp, xs_xstrat_bytes, XFS_FSB_TO_B(mp, bma.length));
XFS_STATS_INC(mp, xs_xstrat_quick);
+ if (xfs_iflags_test(ip, XFS_VERITY_CONSTRUCTION) &&
+ XFS_FSB_TO_B(mp, bma.got.br_startoff) >=
+ xfs_fsverity_metadata_offset(ip))
+ flags |= IOMAP_F_FSVERITY;
+
ASSERT(!isnullstartblock(bma.got.br_startblock));
xfs_bmbt_to_iomap(ip, iomap, &bma.got, 0, flags,
xfs_iomap_inode_sequence(ip, flags));
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index f279055fcea0..9503252a0fa4 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -22,6 +22,7 @@
#include "xfs_icache.h"
#include "xfs_zone_alloc.h"
#include "xfs_rtgroup.h"
+#include "xfs_fsverity.h"
#include <linux/bio-integrity.h>
struct xfs_writepage_ctx {
@@ -339,12 +340,16 @@ xfs_map_blocks(
int retries = 0;
int error = 0;
unsigned int *seq;
+ unsigned int iomap_flags = 0;
if (xfs_is_shutdown(mp))
return -EIO;
XFS_ERRORTAG_DELAY(mp, XFS_ERRTAG_WB_DELAY_MS);
+ if (xfs_iflags_test(ip, XFS_VERITY_CONSTRUCTION))
+ iomap_flags |= IOMAP_F_FSVERITY;
+
/*
* COW fork blocks can overlap data fork blocks even if the blocks
* aren't shared. COW I/O always takes precedent, so we must always
@@ -432,7 +437,8 @@ xfs_map_blocks(
isnullstartblock(imap.br_startblock))
goto allocate_blocks;
- xfs_bmbt_to_iomap(ip, &wpc->iomap, &imap, 0, 0, XFS_WPC(wpc)->data_seq);
+ xfs_bmbt_to_iomap(ip, &wpc->iomap, &imap, 0, iomap_flags,
+ XFS_WPC(wpc)->data_seq);
trace_xfs_map_blocks_found(ip, offset, count, whichfork, &imap);
return 0;
allocate_blocks:
@@ -705,6 +711,14 @@ xfs_vm_writepages(
},
};
+ /*
+ * Writeback does not work for folios past EOF, let it know that
+ * I/O happens for fsverity metadata and this restriction need
+ * to be skipped
+ */
+ if (xfs_iflags_test(ip, XFS_VERITY_CONSTRUCTION))
+ wpc.ctx.iomap.flags |= IOMAP_F_FSVERITY;
+
return iomap_writepages(&wpc.ctx);
}
}
diff --git a/fs/xfs/xfs_fsverity.c b/fs/xfs/xfs_fsverity.c
new file mode 100644
index 000000000000..bc6020cc6e41
--- /dev/null
+++ b/fs/xfs/xfs_fsverity.c
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2026 Red Hat, Inc.
+ */
+#include "xfs_platform.h"
+#include "xfs_format.h"
+#include "xfs_inode.h"
+#include "xfs_shared.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_fsverity.h"
+#include "xfs_fsverity.h"
+#include <linux/fsverity.h>
+#include <linux/iomap.h>
+
+/*
+ * At maximum of 8 levels with 128 hashes per block (32 bytes SHA-256) maximum
+ * tree size is ((128^8 − 1)/(128 − 1)) = 567*10^12 blocks. This should fit in
+ * 53 bits address space.
+ *
+ * At this Merkle tree size we can cover 295EB large file. This is much larger
+ * than the currently supported file size.
+ *
+ * For sha512 the largest file we can cover ends at 1 << 50 offset, this is also
+ * good.
+ */
+#define XFS_FSVERITY_LARGEST_FILE ((loff_t)1ULL << 53)
+
+loff_t
+xfs_fsverity_metadata_offset(
+ const struct xfs_inode *ip)
+{
+ return round_up(i_size_read(VFS_IC(ip)), 65536);
+}
diff --git a/fs/xfs/xfs_fsverity.h b/fs/xfs/xfs_fsverity.h
new file mode 100644
index 000000000000..5771db2cd797
--- /dev/null
+++ b/fs/xfs/xfs_fsverity.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2026 Red Hat, Inc.
+ */
+#ifndef __XFS_FSVERITY_H__
+#define __XFS_FSVERITY_H__
+
+#include "xfs_platform.h"
+
+#ifdef CONFIG_FS_VERITY
+loff_t xfs_fsverity_metadata_offset(const struct xfs_inode *ip);
+#else
+static inline loff_t xfs_fsverity_metadata_offset(const struct xfs_inode *ip)
+{
+ WARN_ON_ONCE(1);
+ return ULLONG_MAX;
+}
+#endif /* CONFIG_FS_VERITY */
+
+#endif /* __XFS_FSVERITY_H__ */
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index bd6d33557194..6df48d68a919 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -415,6 +415,12 @@ static inline bool xfs_inode_can_sw_atomic_write(const struct xfs_inode *ip)
*/
#define XFS_IREMAPPING (1U << 15)
+/*
+ * fs-verity's Merkle tree is under construction. The file is read-only, the
+ * only writes happening are for the fsverity metadata.
+ */
+#define XFS_VERITY_CONSTRUCTION (1U << 16)
+
/* All inode state flags related to inode reclaim. */
#define XFS_ALL_IRECLAIM_FLAGS (XFS_IRECLAIMABLE | \
XFS_IRECLAIM | \
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 9c2f12d5fec9..71ccd4ff5f48 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -32,6 +32,8 @@
#include "xfs_rtbitmap.h"
#include "xfs_icache.h"
#include "xfs_zone_alloc.h"
+#include "xfs_fsverity.h"
+#include <linux/fsverity.h>
#define XFS_ALLOC_ALIGN(mp, off) \
(((off) >> mp->m_allocsize_log) << mp->m_allocsize_log)
@@ -1789,6 +1791,9 @@ xfs_buffered_write_iomap_begin(
return xfs_direct_write_iomap_begin(inode, offset, count,
flags, iomap, srcmap);
+ if (xfs_iflags_test(ip, XFS_VERITY_CONSTRUCTION))
+ iomap_flags |= IOMAP_F_FSVERITY;
+
error = xfs_qm_dqattach(ip);
if (error)
return error;
@@ -2113,12 +2118,17 @@ xfs_read_iomap_begin(
bool shared = false;
unsigned int lockmode = XFS_ILOCK_SHARED;
u64 seq;
+ unsigned int iomap_flags = 0;
ASSERT(!(flags & (IOMAP_WRITE | IOMAP_ZERO)));
if (xfs_is_shutdown(mp))
return -EIO;
+ if (fsverity_active(inode) &&
+ (offset >= xfs_fsverity_metadata_offset(ip)))
+ iomap_flags |= IOMAP_F_FSVERITY;
+
error = xfs_ilock_for_iomap(ip, flags, &lockmode);
if (error)
return error;
@@ -2132,8 +2142,9 @@ xfs_read_iomap_begin(
if (error)
return error;
trace_xfs_iomap_found(ip, offset, length, XFS_DATA_FORK, &imap);
- return xfs_bmbt_to_iomap(ip, iomap, &imap, flags,
- shared ? IOMAP_F_SHARED : 0, seq);
+ iomap_flags |= shared ? IOMAP_F_SHARED : 0;
+
+ return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, iomap_flags, seq);
}
const struct iomap_ops xfs_read_iomap_ops = {
--
2.51.2
^ permalink raw reply related
* [PATCH v4 15/25] xfs: disable direct read path for fs-verity files
From: Andrey Albershteyn @ 2026-03-09 19:23 UTC (permalink / raw)
To: linux-xfs, fsverity, linux-fsdevel, ebiggers
Cc: Andrey Albershteyn, hch, linux-ext4, linux-f2fs-devel,
linux-btrfs, djwong
In-Reply-To: <20260309192355.176980-1-aalbersh@kernel.org>
The direct path is not supported on verity files. Attempts to use direct
I/O path on such files should fall back to buffered I/O path.
Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
[djwong: fix braces]
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
fs/xfs/xfs_file.c | 11 ++++++++++-
1 file changed, 10 insertions(+), 1 deletion(-)
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index a980ac5196a8..6fa9835f9531 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -282,7 +282,8 @@ xfs_file_dax_read(
struct kiocb *iocb,
struct iov_iter *to)
{
- struct xfs_inode *ip = XFS_I(iocb->ki_filp->f_mapping->host);
+ struct inode *inode = iocb->ki_filp->f_mapping->host;
+ struct xfs_inode *ip = XFS_I(inode);
ssize_t ret = 0;
trace_xfs_file_dax_read(iocb, to);
@@ -333,6 +334,14 @@ xfs_file_read_iter(
if (xfs_is_shutdown(mp))
return -EIO;
+ /*
+ * In case fs-verity is enabled, we also fallback to the buffered read
+ * from the direct read path. Therefore, IOCB_DIRECT is set and need to
+ * be cleared (see generic_file_read_iter())
+ */
+ if (fsverity_active(inode))
+ iocb->ki_flags &= ~IOCB_DIRECT;
+
if (IS_DAX(inode))
ret = xfs_file_dax_read(iocb, to);
else if (iocb->ki_flags & IOCB_DIRECT)
--
2.51.2
^ permalink raw reply related
* [PATCH v4 14/25] xfs: don't allow to enable DAX on fs-verity sealed inode
From: Andrey Albershteyn @ 2026-03-09 19:23 UTC (permalink / raw)
To: linux-xfs, fsverity, linux-fsdevel, ebiggers
Cc: Andrey Albershteyn, hch, linux-ext4, linux-f2fs-devel,
linux-btrfs, djwong
In-Reply-To: <20260309192355.176980-1-aalbersh@kernel.org>
fs-verity doesn't support DAX. Forbid filesystem to enable DAX on
inodes which already have fs-verity enabled. The opposite is checked
when fs-verity is enabled, it won't be enabled if DAX is.
Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
[djwong: fix typo in subject]
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
fs/xfs/xfs_iops.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index ca369eb96561..17efc83a86ed 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -1387,6 +1387,8 @@ xfs_inode_should_enable_dax(
return false;
if (!xfs_inode_supports_dax(ip))
return false;
+ if (ip->i_diflags2 & XFS_DIFLAG2_VERITY)
+ return false;
if (xfs_has_dax_always(ip->i_mount))
return true;
if (ip->i_diflags2 & XFS_DIFLAG2_DAX)
--
2.51.2
^ permalink raw reply related
* [PATCH v4 13/25] xfs: initialize fs-verity on file open
From: Andrey Albershteyn @ 2026-03-09 19:23 UTC (permalink / raw)
To: linux-xfs, fsverity, linux-fsdevel, ebiggers
Cc: Andrey Albershteyn, hch, linux-ext4, linux-f2fs-devel,
linux-btrfs, djwong
In-Reply-To: <20260309192355.176980-1-aalbersh@kernel.org>
fs-verity will read and attach metadata (not the tree itself) from
a disk for those inodes which already have fs-verity enabled.
Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
fs/xfs/xfs_file.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 6246f34df9fd..a980ac5196a8 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -37,6 +37,7 @@
#include <linux/fadvise.h>
#include <linux/mount.h>
#include <linux/filelock.h>
+#include <linux/fsverity.h>
static const struct vm_operations_struct xfs_file_vm_ops;
@@ -1640,11 +1641,18 @@ xfs_file_open(
struct inode *inode,
struct file *file)
{
+ int error;
+
if (xfs_is_shutdown(XFS_M(inode->i_sb)))
return -EIO;
file->f_mode |= FMODE_NOWAIT | FMODE_CAN_ODIRECT;
if (xfs_get_atomic_write_min(XFS_I(inode)) > 0)
file->f_mode |= FMODE_CAN_ATOMIC_WRITE;
+
+ error = fsverity_file_open(inode, file);
+ if (error)
+ return error;
+
return generic_file_open(inode, file);
}
--
2.51.2
^ permalink raw reply related
* [PATCH v4 12/25] xfs: introduce fsverity on-disk changes
From: Andrey Albershteyn @ 2026-03-09 19:23 UTC (permalink / raw)
To: linux-xfs, fsverity, linux-fsdevel, ebiggers
Cc: Andrey Albershteyn, hch, linux-ext4, linux-f2fs-devel,
linux-btrfs, djwong
In-Reply-To: <20260309192355.176980-1-aalbersh@kernel.org>
Introduce XFS_DIFLAG2_VERITY for inodes with fsverity. This flag
indicates that inode has fs-verity enabled (i.e. descriptor exist,
tree is built and file is read-only).
Introduce XFS_SB_FEAT_RO_COMPAT_VERITY for filesystems having
fsverity inodes. As on-disk changes applies to fsverity inodes only, let
older kernels read-only access. This will be enabled in the further
patch after full fsverity support.
Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
---
fs/xfs/libxfs/xfs_format.h | 8 +++++++-
fs/xfs/libxfs/xfs_inode_buf.c | 8 ++++++++
fs/xfs/libxfs/xfs_inode_util.c | 2 ++
fs/xfs/libxfs/xfs_sb.c | 2 ++
fs/xfs/xfs_iops.c | 2 ++
fs/xfs/xfs_mount.h | 2 ++
6 files changed, 23 insertions(+), 1 deletion(-)
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 779dac59b1f3..d67b404964fc 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -374,6 +374,7 @@ xfs_sb_has_compat_feature(
#define XFS_SB_FEAT_RO_COMPAT_RMAPBT (1 << 1) /* reverse map btree */
#define XFS_SB_FEAT_RO_COMPAT_REFLINK (1 << 2) /* reflinked files */
#define XFS_SB_FEAT_RO_COMPAT_INOBTCNT (1 << 3) /* inobt block counts */
+#define XFS_SB_FEAT_RO_COMPAT_VERITY (1 << 4) /* fs-verity */
#define XFS_SB_FEAT_RO_COMPAT_ALL \
(XFS_SB_FEAT_RO_COMPAT_FINOBT | \
XFS_SB_FEAT_RO_COMPAT_RMAPBT | \
@@ -1230,16 +1231,21 @@ static inline void xfs_dinode_put_rdev(struct xfs_dinode *dip, xfs_dev_t rdev)
*/
#define XFS_DIFLAG2_METADATA_BIT 5
+/* inodes sealed with fs-verity */
+#define XFS_DIFLAG2_VERITY_BIT 6
+
#define XFS_DIFLAG2_DAX (1ULL << XFS_DIFLAG2_DAX_BIT)
#define XFS_DIFLAG2_REFLINK (1ULL << XFS_DIFLAG2_REFLINK_BIT)
#define XFS_DIFLAG2_COWEXTSIZE (1ULL << XFS_DIFLAG2_COWEXTSIZE_BIT)
#define XFS_DIFLAG2_BIGTIME (1ULL << XFS_DIFLAG2_BIGTIME_BIT)
#define XFS_DIFLAG2_NREXT64 (1ULL << XFS_DIFLAG2_NREXT64_BIT)
#define XFS_DIFLAG2_METADATA (1ULL << XFS_DIFLAG2_METADATA_BIT)
+#define XFS_DIFLAG2_VERITY (1ULL << XFS_DIFLAG2_VERITY_BIT)
#define XFS_DIFLAG2_ANY \
(XFS_DIFLAG2_DAX | XFS_DIFLAG2_REFLINK | XFS_DIFLAG2_COWEXTSIZE | \
- XFS_DIFLAG2_BIGTIME | XFS_DIFLAG2_NREXT64 | XFS_DIFLAG2_METADATA)
+ XFS_DIFLAG2_BIGTIME | XFS_DIFLAG2_NREXT64 | XFS_DIFLAG2_METADATA | \
+ XFS_DIFLAG2_VERITY)
static inline bool xfs_dinode_has_bigtime(const struct xfs_dinode *dip)
{
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index a017016e9075..c5822d938d81 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -756,6 +756,14 @@ xfs_dinode_verify(
!xfs_has_rtreflink(mp))
return __this_address;
+ /* only regular files can have fsverity */
+ if (flags2 & XFS_DIFLAG2_VERITY) {
+ if (!xfs_has_verity(mp))
+ return __this_address;
+ if ((mode & S_IFMT) != S_IFREG)
+ return __this_address;
+ }
+
if (xfs_has_zoned(mp) &&
dip->di_metatype == cpu_to_be16(XFS_METAFILE_RTRMAP)) {
if (be32_to_cpu(dip->di_used_blocks) > mp->m_sb.sb_rgextents)
diff --git a/fs/xfs/libxfs/xfs_inode_util.c b/fs/xfs/libxfs/xfs_inode_util.c
index 551fa51befb6..6b1e20a4bb9b 100644
--- a/fs/xfs/libxfs/xfs_inode_util.c
+++ b/fs/xfs/libxfs/xfs_inode_util.c
@@ -126,6 +126,8 @@ xfs_ip2xflags(
flags |= FS_XFLAG_DAX;
if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE)
flags |= FS_XFLAG_COWEXTSIZE;
+ if (ip->i_diflags2 & XFS_DIFLAG2_VERITY)
+ flags |= FS_XFLAG_VERITY;
}
if (xfs_inode_has_attr_fork(ip))
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 38d16fe1f6d8..4401a5f16344 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -165,6 +165,8 @@ xfs_sb_version_to_features(
features |= XFS_FEAT_REFLINK;
if (sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_INOBTCNT)
features |= XFS_FEAT_INOBTCNT;
+ if (sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_VERITY)
+ features |= XFS_FEAT_VERITY;
if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_FTYPE)
features |= XFS_FEAT_FTYPE;
if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_SPINODES)
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 208543e57eda..ca369eb96561 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -1415,6 +1415,8 @@ xfs_diflags_to_iflags(
flags |= S_NOATIME;
if (init && xfs_inode_should_enable_dax(ip))
flags |= S_DAX;
+ if (xflags & FS_XFLAG_VERITY)
+ flags |= S_VERITY;
/*
* S_DAX can only be set during inode initialization and is never set by
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 61c71128d171..c746bc90cf3e 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -385,6 +385,7 @@ typedef struct xfs_mount {
#define XFS_FEAT_EXCHANGE_RANGE (1ULL << 27) /* exchange range */
#define XFS_FEAT_METADIR (1ULL << 28) /* metadata directory tree */
#define XFS_FEAT_ZONED (1ULL << 29) /* zoned RT device */
+#define XFS_FEAT_VERITY (1ULL << 30) /* fs-verity */
/* Mount features */
#define XFS_FEAT_NOLIFETIME (1ULL << 47) /* disable lifetime hints */
@@ -442,6 +443,7 @@ __XFS_HAS_FEAT(exchange_range, EXCHANGE_RANGE)
__XFS_HAS_FEAT(metadir, METADIR)
__XFS_HAS_FEAT(zoned, ZONED)
__XFS_HAS_FEAT(nolifetime, NOLIFETIME)
+__XFS_HAS_FEAT(verity, VERITY)
static inline bool xfs_has_rtgroups(const struct xfs_mount *mp)
{
--
2.51.2
^ permalink raw reply related
* [PATCH v4 11/25] iomap: introduce iomap_fsverity_write() for writing fsverity metadata
From: Andrey Albershteyn @ 2026-03-09 19:23 UTC (permalink / raw)
To: linux-xfs, fsverity, linux-fsdevel, ebiggers
Cc: Andrey Albershteyn, hch, linux-ext4, linux-f2fs-devel,
linux-btrfs, djwong
In-Reply-To: <20260309192355.176980-1-aalbersh@kernel.org>
This is just a wrapper around iomap_file_buffered_write() to create
necessary iterator over metadata.
Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
---
fs/iomap/buffered-io.c | 25 +++++++++++++++++++++++++
include/linux/iomap.h | 3 +++
2 files changed, 28 insertions(+)
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 31e39ab93a2e..88fe4723bb22 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1259,6 +1259,31 @@ iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *i,
}
EXPORT_SYMBOL_GPL(iomap_file_buffered_write);
+ssize_t iomap_fsverity_write(struct file *file, loff_t pos, size_t length,
+ const void *buf, const struct iomap_ops *ops,
+ const struct iomap_write_ops *write_ops)
+{
+ int ret;
+ struct iov_iter iiter;
+ struct kvec kvec = {
+ .iov_base = (void *)buf,
+ .iov_len = length,
+ };
+ struct kiocb iocb = {
+ .ki_filp = file,
+ .ki_ioprio = get_current_ioprio(),
+ .ki_pos = pos,
+ };
+
+ iov_iter_kvec(&iiter, WRITE, &kvec, 1, length);
+
+ ret = iomap_file_buffered_write(&iocb, &iiter, ops, write_ops, NULL);
+ if (ret < 0)
+ return ret;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(iomap_fsverity_write);
+
static void iomap_write_delalloc_ifs_punch(struct inode *inode,
struct folio *folio, loff_t start_byte, loff_t end_byte,
struct iomap *iomap, iomap_punch_t punch)
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 89e5a7abc012..844fc8414363 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -356,6 +356,9 @@ static inline bool iomap_want_unshare_iter(const struct iomap_iter *iter)
ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
const struct iomap_ops *ops,
const struct iomap_write_ops *write_ops, void *private);
+ssize_t iomap_fsverity_write(struct file *file, loff_t pos, size_t length,
+ const void *buf, const struct iomap_ops *ops,
+ const struct iomap_write_ops *write_ops);
void iomap_read_folio(const struct iomap_ops *ops,
struct iomap_read_folio_ctx *ctx, void *private);
void iomap_readahead(const struct iomap_ops *ops,
--
2.51.2
^ permalink raw reply related
* [PATCH v4 10/25] iomap: teach iomap to handle fsverity holes and verify data holes
From: Andrey Albershteyn @ 2026-03-09 19:23 UTC (permalink / raw)
To: linux-xfs, fsverity, linux-fsdevel, ebiggers
Cc: Andrey Albershteyn, hch, linux-ext4, linux-f2fs-devel,
linux-btrfs, djwong
In-Reply-To: <20260309192355.176980-1-aalbersh@kernel.org>
fsverity metadata has two kinds of holes - ones in merkle tree and one
after fsverity descriptor.
Merkle tree holes are blocks full of hashes of zeroed data blocks. These
are not stored on the disk but synthesized on the fly. This saves a bit
of space for sparse files. Due to this iomap also need to lookup
fsverity_info for folios with fsverity metadata. ->vi has a hash of the
zeroed data block which will be used to fill the merkle tree block. This
patch extends lookup of fsverity_info from just for file data but also
for merkle tree holes.
The hole past descriptor is interpreted as end of metadata region. As we
don't have EOF here we use this hole as an indication that rest of the
folio is empty. This patch marks rest of the folio beyond fsverity
descriptor as uptodate.
For file data, fsverity needs to verify consistency of the whole file
against the root hash, hashes of holes are included in the merkle tree.
Verify them too.
Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
---
fs/iomap/buffered-io.c | 28 ++++++++++++++++++++++++++--
1 file changed, 26 insertions(+), 2 deletions(-)
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 1d9481f00b41..31e39ab93a2e 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -542,9 +542,33 @@ static int iomap_read_folio_iter(struct iomap_iter *iter,
if (plen == 0)
return 0;
- /* zero post-eof blocks as the page may be mapped */
- if (iomap_block_needs_zeroing(iter, pos)) {
+ /*
+ * Handling of fsverity "holes". We hit this for two case:
+ * 1. No need to go further, the hole after fsverity
+ * descriptor is the end of the fsverity metadata.
+ *
+ * 2. This folio contains merkle tree blocks which need to be
+ * synthesized. If we already have fsverity info (ctx->vi)
+ * synthesize these blocks.
+ */
+ if ((iomap->flags & IOMAP_F_FSVERITY) &&
+ iomap->type == IOMAP_HOLE) {
+ /*
+ * Don't cause lookup if we already have fsverity
+ * context from the previous tree hole
+ */
+ if (!ctx->vi)
+ ctx->vi = fsverity_get_info(iter->inode);
+ if (ctx->vi)
+ fsverity_folio_zero_hash(folio, poff, plen,
+ ctx->vi);
+ iomap_set_range_uptodate(folio, poff, plen);
+ } else if (iomap_block_needs_zeroing(iter, pos)) {
+ /* zero post-eof blocks as the page may be mapped */
folio_zero_range(folio, poff, plen);
+ if (ctx->vi &&
+ !fsverity_verify_blocks(ctx->vi, folio, plen, poff))
+ return -EIO;
iomap_set_range_uptodate(folio, poff, plen);
} else {
if (!*bytes_submitted)
--
2.51.2
^ permalink raw reply related
* [PATCH v4 09/25] iomap: issue readahead for fsverity merkle tree
From: Andrey Albershteyn @ 2026-03-09 19:23 UTC (permalink / raw)
To: linux-xfs, fsverity, linux-fsdevel, ebiggers
Cc: Andrey Albershteyn, hch, linux-ext4, linux-f2fs-devel,
linux-btrfs, djwong
In-Reply-To: <20260309192355.176980-1-aalbersh@kernel.org>
Issue reading of fsverity merkle tree on the fsverity inodes. This way
metadata will be available at I/O completion time.
Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
---
fs/iomap/buffered-io.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index a335a18c307f..1d9481f00b41 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -593,6 +593,9 @@ void iomap_read_folio(const struct iomap_ops *ops,
if (iter.pos < i_size_read(iter.inode))
ctx->vi = fsverity_get_info(iter.inode);
+ if (ctx->vi)
+ fsverity_readahead(ctx->vi, folio->index,
+ folio_nr_pages(folio));
while ((ret = iomap_iter(&iter, ops)) > 0)
iter.status = iomap_read_folio_iter(&iter, ctx,
--
2.51.2
^ permalink raw reply related
* [PATCH v4 08/25] iomap: obtain fsverity info for read path
From: Andrey Albershteyn @ 2026-03-09 19:23 UTC (permalink / raw)
To: linux-xfs, fsverity, linux-fsdevel, ebiggers
Cc: Andrey Albershteyn, hch, linux-ext4, linux-f2fs-devel,
linux-btrfs, djwong
In-Reply-To: <20260309192355.176980-1-aalbersh@kernel.org>
Obtain fsverity info for folios with file data. Filesystem can pass vi
down to ioend and then to fsverity for verification. XFS will use it in
further patch for fsverity integration.
Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
---
fs/iomap/buffered-io.c | 7 +++++++
include/linux/iomap.h | 2 ++
2 files changed, 9 insertions(+)
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 530794dcdd91..a335a18c307f 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -9,6 +9,7 @@
#include <linux/swap.h>
#include <linux/migrate.h>
#include <linux/fserror.h>
+#include <linux/fsverity.h>
#include "internal.h"
#include "trace.h"
@@ -590,6 +591,9 @@ void iomap_read_folio(const struct iomap_ops *ops,
trace_iomap_readpage(iter.inode, 1);
+ if (iter.pos < i_size_read(iter.inode))
+ ctx->vi = fsverity_get_info(iter.inode);
+
while ((ret = iomap_iter(&iter, ops)) > 0)
iter.status = iomap_read_folio_iter(&iter, ctx,
&bytes_submitted);
@@ -656,6 +660,9 @@ void iomap_readahead(const struct iomap_ops *ops,
trace_iomap_readahead(rac->mapping->host, readahead_count(rac));
+ if (iter.pos < i_size_read(iter.inode))
+ ctx->vi = fsverity_get_info(iter.inode);
+
while (iomap_iter(&iter, ops) > 0)
iter.status = iomap_readahead_iter(&iter, ctx,
&cur_bytes_submitted);
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index dc39837b0d45..89e5a7abc012 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -432,6 +432,7 @@ struct iomap_ioend {
loff_t io_offset; /* offset in the file */
sector_t io_sector; /* start sector of ioend */
void *io_private; /* file system private data */
+ struct fsverity_info *io_vi; /* fsverity info */
struct bio io_bio; /* MUST BE LAST! */
};
@@ -506,6 +507,7 @@ struct iomap_read_folio_ctx {
struct readahead_control *rac;
void *read_ctx;
loff_t read_ctx_file_offset;
+ struct fsverity_info *vi;
};
struct iomap_read_ops {
--
2.51.2
^ permalink raw reply related
* [PATCH v4 07/25] iomap: introduce IOMAP_F_FSVERITY and teach writeback to handle fsverity
From: Andrey Albershteyn @ 2026-03-09 19:23 UTC (permalink / raw)
To: linux-xfs, fsverity, linux-fsdevel, ebiggers
Cc: Andrey Albershteyn, hch, linux-ext4, linux-f2fs-devel,
linux-btrfs, djwong
In-Reply-To: <20260309192355.176980-1-aalbersh@kernel.org>
This flag indicates that I/O is for fsverity metadata.
In the write path skip i_size check and i_size updates as metadata is
past EOF. In writeback don't update i_size and continue writeback if
even folio is beyond EOF. In read path don't zero fsverity folios, again
they are past EOF.
The iomap_block_needs_zeroing() is also called from write path. For
folios of larger order we don't want to zero out pages in the folio as
these could contain other merkle tree blocks. For fsverity, filesystem
will request to read PAGE_SIZE memory regions. For data folios, iomap
will zero the rest of the folio for anything which is beyond EOF. We
don't want this for fsverity folios.
Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
---
fs/iomap/buffered-io.c | 34 +++++++++++++++++++++++++---------
fs/iomap/trace.h | 3 ++-
include/linux/iomap.h | 5 +++++
3 files changed, 32 insertions(+), 10 deletions(-)
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 51a58a0bfe6c..530794dcdd91 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -344,9 +344,16 @@ static inline bool iomap_block_needs_zeroing(const struct iomap_iter *iter,
{
const struct iomap *srcmap = iomap_iter_srcmap(iter);
- return srcmap->type != IOMAP_MAPPED ||
- (srcmap->flags & IOMAP_F_NEW) ||
- pos >= i_size_read(iter->inode);
+ if (srcmap->type != IOMAP_MAPPED)
+ return true;
+
+ if (srcmap->flags & IOMAP_F_NEW)
+ return true;
+
+ if (srcmap->flags & IOMAP_F_FSVERITY)
+ return false;
+
+ return pos >= i_size_read(iter->inode);
}
/**
@@ -1152,13 +1159,14 @@ static int iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i,
* unlock and release the folio.
*/
old_size = iter->inode->i_size;
- if (pos + written > old_size) {
+ if (pos + written > old_size &&
+ !(iter->iomap.flags & IOMAP_F_FSVERITY)) {
i_size_write(iter->inode, pos + written);
iter->iomap.flags |= IOMAP_F_SIZE_CHANGED;
}
__iomap_put_folio(iter, write_ops, written, folio);
- if (old_size < pos)
+ if (old_size < pos && !(iter->iomap.flags & IOMAP_F_FSVERITY))
pagecache_isize_extended(iter->inode, old_size, pos);
cond_resched();
@@ -1786,13 +1794,21 @@ static int iomap_writeback_range(struct iomap_writepage_ctx *wpc,
* Check interaction of the folio with the file end.
*
* If the folio is entirely beyond i_size, return false. If it straddles
- * i_size, adjust end_pos and zero all data beyond i_size.
+ * i_size, adjust end_pos and zero all data beyond i_size. Don't skip fsverity
+ * folios as those are beyond i_size.
*/
-static bool iomap_writeback_handle_eof(struct folio *folio, struct inode *inode,
- u64 *end_pos)
+static bool iomap_writeback_handle_eof(struct folio *folio,
+ struct iomap_writepage_ctx *wpc,
+ u64 *end_pos)
{
+ struct inode *inode = wpc->inode;
u64 isize = i_size_read(inode);
+ if (wpc->iomap.flags & IOMAP_F_FSVERITY) {
+ WARN_ON_ONCE(folio_pos(folio) < isize);
+ return true;
+ }
+
if (*end_pos > isize) {
size_t poff = offset_in_folio(folio, isize);
pgoff_t end_index = isize >> PAGE_SHIFT;
@@ -1858,7 +1874,7 @@ int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio)
trace_iomap_writeback_folio(inode, pos, folio_size(folio));
- if (!iomap_writeback_handle_eof(folio, inode, &end_pos))
+ if (!iomap_writeback_handle_eof(folio, wpc, &end_pos))
return 0;
WARN_ON_ONCE(end_pos <= pos);
diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h
index 532787277b16..5252051cc137 100644
--- a/fs/iomap/trace.h
+++ b/fs/iomap/trace.h
@@ -118,7 +118,8 @@ DEFINE_RANGE_EVENT(iomap_zero_iter);
{ IOMAP_F_ATOMIC_BIO, "ATOMIC_BIO" }, \
{ IOMAP_F_PRIVATE, "PRIVATE" }, \
{ IOMAP_F_SIZE_CHANGED, "SIZE_CHANGED" }, \
- { IOMAP_F_STALE, "STALE" }
+ { IOMAP_F_STALE, "STALE" }, \
+ { IOMAP_F_FSVERITY, "FSVERITY" }
#define IOMAP_DIO_STRINGS \
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 531f9ebdeeae..dc39837b0d45 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -87,6 +87,11 @@ struct vm_fault;
#define IOMAP_F_INTEGRITY 0
#endif /* CONFIG_BLK_DEV_INTEGRITY */
+/*
+ * IO happens beyond inode EOF, fsverity metadata is stored there
+ */
+#define IOMAP_F_FSVERITY (1U << 10)
+
/*
* Flag reserved for file system specific usage
*/
--
2.51.2
^ permalink raw reply related
* [PATCH v4 06/25] fsverity: hoist pagecache_read from f2fs/ext4 to fsverity
From: Andrey Albershteyn @ 2026-03-09 19:23 UTC (permalink / raw)
To: linux-xfs, fsverity, linux-fsdevel, ebiggers
Cc: Andrey Albershteyn, hch, linux-ext4, linux-f2fs-devel,
linux-btrfs, djwong
In-Reply-To: <20260309192355.176980-1-aalbersh@kernel.org>
This is the same function to read from pageache. XFS will also need
this, so move this to core fsverity.
Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
---
fs/ext4/verity.c | 32 +++-----------------------------
fs/f2fs/verity.c | 30 +-----------------------------
fs/verity/pagecache.c | 33 +++++++++++++++++++++++++++++++++
include/linux/fsverity.h | 2 ++
4 files changed, 39 insertions(+), 58 deletions(-)
diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c
index 347945ac23a4..ac5c133f5529 100644
--- a/fs/ext4/verity.c
+++ b/fs/ext4/verity.c
@@ -34,32 +34,6 @@ static inline loff_t ext4_verity_metadata_pos(const struct inode *inode)
return round_up(inode->i_size, 65536);
}
-/*
- * Read some verity metadata from the inode. __vfs_read() can't be used because
- * we need to read beyond i_size.
- */
-static int pagecache_read(struct inode *inode, void *buf, size_t count,
- loff_t pos)
-{
- while (count) {
- struct folio *folio;
- size_t n;
-
- folio = read_mapping_folio(inode->i_mapping, pos >> PAGE_SHIFT,
- NULL);
- if (IS_ERR(folio))
- return PTR_ERR(folio);
-
- n = memcpy_from_file_folio(buf, folio, pos, count);
- folio_put(folio);
-
- buf += n;
- pos += n;
- count -= n;
- }
- return 0;
-}
-
/*
* Write some verity metadata to the inode for FS_IOC_ENABLE_VERITY.
* kernel_write() can't be used because the file descriptor is readonly.
@@ -311,8 +285,8 @@ static int ext4_get_verity_descriptor_location(struct inode *inode,
goto bad;
desc_size_pos -= sizeof(desc_size_disk);
- err = pagecache_read(inode, &desc_size_disk, sizeof(desc_size_disk),
- desc_size_pos);
+ err = fsverity_pagecache_read(inode, &desc_size_disk,
+ sizeof(desc_size_disk), desc_size_pos);
if (err)
return err;
desc_size = le32_to_cpu(desc_size_disk);
@@ -352,7 +326,7 @@ static int ext4_get_verity_descriptor(struct inode *inode, void *buf,
if (buf_size) {
if (desc_size > buf_size)
return -ERANGE;
- err = pagecache_read(inode, buf, desc_size, desc_pos);
+ err = fsverity_pagecache_read(inode, buf, desc_size, desc_pos);
if (err)
return err;
}
diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c
index b3b3e71604ac..5ea0a9b40443 100644
--- a/fs/f2fs/verity.c
+++ b/fs/f2fs/verity.c
@@ -36,34 +36,6 @@ static inline loff_t f2fs_verity_metadata_pos(const struct inode *inode)
return round_up(inode->i_size, 65536);
}
-/*
- * Read some verity metadata from the inode. __vfs_read() can't be used because
- * we need to read beyond i_size.
- */
-static int pagecache_read(struct inode *inode, void *buf, size_t count,
- loff_t pos)
-{
- while (count) {
- size_t n = min_t(size_t, count,
- PAGE_SIZE - offset_in_page(pos));
- struct page *page;
-
- page = read_mapping_page(inode->i_mapping, pos >> PAGE_SHIFT,
- NULL);
- if (IS_ERR(page))
- return PTR_ERR(page);
-
- memcpy_from_page(buf, page, offset_in_page(pos), n);
-
- put_page(page);
-
- buf += n;
- pos += n;
- count -= n;
- }
- return 0;
-}
-
/*
* Write some verity metadata to the inode for FS_IOC_ENABLE_VERITY.
* kernel_write() can't be used because the file descriptor is readonly.
@@ -248,7 +220,7 @@ static int f2fs_get_verity_descriptor(struct inode *inode, void *buf,
if (buf_size) {
if (size > buf_size)
return -ERANGE;
- res = pagecache_read(inode, buf, size, pos);
+ res = fsverity_pagecache_read(inode, buf, size, pos);
if (res)
return res;
}
diff --git a/fs/verity/pagecache.c b/fs/verity/pagecache.c
index 1d94bf73f38c..ec65f60e657f 100644
--- a/fs/verity/pagecache.c
+++ b/fs/verity/pagecache.c
@@ -78,3 +78,36 @@ void fsverity_folio_zero_hash(struct folio *folio, size_t poff, size_t plen,
vi->tree_params.digest_size);
}
EXPORT_SYMBOL_GPL(fsverity_folio_zero_hash);
+
+/**
+ * fsverity_pagecache_read() - read page and copy data to buffer
+ * @inode: copy from this inode's address space
+ * @buf: buffer to copy to
+ * @count: number of bytes to copy
+ * @pos: position of the folio to copy from
+ *
+ * Read some verity metadata from the inode. __vfs_read() can't be used because
+ * we need to read beyond i_size.
+ */
+int fsverity_pagecache_read(struct inode *inode, void *buf, size_t count,
+ loff_t pos)
+{
+ while (count) {
+ struct folio *folio;
+ size_t n;
+
+ folio = read_mapping_folio(inode->i_mapping, pos >> PAGE_SHIFT,
+ NULL);
+ if (IS_ERR(folio))
+ return PTR_ERR(folio);
+
+ n = memcpy_from_file_folio(buf, folio, pos, count);
+ folio_put(folio);
+
+ buf += n;
+ pos += n;
+ count -= n;
+ }
+ return 0;
+}
+EXPORT_SYMBOL_GPL(fsverity_pagecache_read);
diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h
index 1ca8de129323..53dc161e18c0 100644
--- a/include/linux/fsverity.h
+++ b/include/linux/fsverity.h
@@ -327,5 +327,7 @@ void generic_readahead_merkle_tree(struct inode *inode, pgoff_t index,
unsigned long nr_pages);
void fsverity_folio_zero_hash(struct folio *folio, size_t poff, size_t plen,
struct fsverity_info *vi);
+int fsverity_pagecache_read(struct inode *inode, void *buf, size_t count,
+ loff_t pos);
#endif /* _LINUX_FSVERITY_H */
--
2.51.2
^ permalink raw reply related
* [PATCH v4 05/25] fsverity: pass digest size and hash of the empty block to ->write
From: Andrey Albershteyn @ 2026-03-09 19:23 UTC (permalink / raw)
To: linux-xfs, fsverity, linux-fsdevel, ebiggers
Cc: Andrey Albershteyn, hch, linux-ext4, linux-f2fs-devel,
linux-btrfs, djwong
In-Reply-To: <20260309192355.176980-1-aalbersh@kernel.org>
Let filesystem iterate over hashes in the block and check if these are
hashes of zeroed data blocks. XFS will use this to decide if it want to
store tree block full of these hashes.
Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
---
fs/btrfs/verity.c | 6 +++++-
fs/ext4/verity.c | 4 +++-
fs/f2fs/verity.c | 4 +++-
fs/verity/enable.c | 4 +++-
include/linux/fsverity.h | 6 +++++-
5 files changed, 19 insertions(+), 5 deletions(-)
diff --git a/fs/btrfs/verity.c b/fs/btrfs/verity.c
index 0062b3a55781..6d8d3808d75d 100644
--- a/fs/btrfs/verity.c
+++ b/fs/btrfs/verity.c
@@ -773,11 +773,15 @@ static struct page *btrfs_read_merkle_tree_page(struct inode *inode,
* @buf: Merkle tree block to write
* @pos: the position of the block in the Merkle tree (in bytes)
* @size: the Merkle tree block size (in bytes)
+ * @zero_digest: the hash of a merkle block-sized buffer of zeroes
+ * @digest_size: size of zero_digest, in bytes
*
* Returns 0 on success or negative error code on failure
*/
static int btrfs_write_merkle_tree_block(struct file *file, const void *buf,
- u64 pos, unsigned int size)
+ u64 pos, unsigned int size,
+ const u8 *zero_digest,
+ unsigned int digest_size)
{
struct inode *inode = file_inode(file);
loff_t merkle_pos = merkle_file_pos(inode);
diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c
index ca61da53f313..347945ac23a4 100644
--- a/fs/ext4/verity.c
+++ b/fs/ext4/verity.c
@@ -374,7 +374,9 @@ static void ext4_readahead_merkle_tree(struct inode *inode, pgoff_t index,
}
static int ext4_write_merkle_tree_block(struct file *file, const void *buf,
- u64 pos, unsigned int size)
+ u64 pos, unsigned int size,
+ const u8 *zero_digest,
+ unsigned int digest_size)
{
pos += ext4_verity_metadata_pos(file_inode(file));
diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c
index 92ebcc19cab0..b3b3e71604ac 100644
--- a/fs/f2fs/verity.c
+++ b/fs/f2fs/verity.c
@@ -270,7 +270,9 @@ static void f2fs_readahead_merkle_tree(struct inode *inode, pgoff_t index,
}
static int f2fs_write_merkle_tree_block(struct file *file, const void *buf,
- u64 pos, unsigned int size)
+ u64 pos, unsigned int size,
+ const u8 *zero_digest,
+ unsigned int digest_size)
{
pos += f2fs_verity_metadata_pos(file_inode(file));
diff --git a/fs/verity/enable.c b/fs/verity/enable.c
index 42dfed1ce0ce..ad4ff71d7dd9 100644
--- a/fs/verity/enable.c
+++ b/fs/verity/enable.c
@@ -50,7 +50,9 @@ static int write_merkle_tree_block(struct file *file, const u8 *buf,
int err;
err = inode->i_sb->s_vop->write_merkle_tree_block(file, buf, pos,
- params->block_size);
+ params->block_size,
+ params->zero_digest,
+ params->digest_size);
if (err)
fsverity_err(inode, "Error %d writing Merkle tree block %lu",
err, index);
diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h
index b490b2c8a393..1ca8de129323 100644
--- a/include/linux/fsverity.h
+++ b/include/linux/fsverity.h
@@ -124,6 +124,8 @@ struct fsverity_operations {
* @buf: the Merkle tree block to write
* @pos: the position of the block in the Merkle tree (in bytes)
* @size: the Merkle tree block size (in bytes)
+ * @zero_digest: the hash of a merkle block-sized buffer of zeroes
+ * @digest_size: size of zero_digest, in bytes
*
* This is only called between ->begin_enable_verity() and
* ->end_enable_verity().
@@ -131,7 +133,9 @@ struct fsverity_operations {
* Return: 0 on success, -errno on failure
*/
int (*write_merkle_tree_block)(struct file *file, const void *buf,
- u64 pos, unsigned int size);
+ u64 pos, unsigned int size,
+ const u8 *zero_digest,
+ unsigned int digest_size);
};
#ifdef CONFIG_FS_VERITY
--
2.51.2
^ permalink raw reply related
* [PATCH v4 04/25] fsverity: introduce fsverity_folio_zero_hash()
From: Andrey Albershteyn @ 2026-03-09 19:23 UTC (permalink / raw)
To: linux-xfs, fsverity, linux-fsdevel, ebiggers
Cc: Andrey Albershteyn, hch, linux-ext4, linux-f2fs-devel,
linux-btrfs, djwong
In-Reply-To: <20260309192355.176980-1-aalbersh@kernel.org>
Helper to pre-fill folio with hashes of empty blocks. This will be used
by iomap to synthesize blocks full of zero hashes on the fly.
Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
---
fs/verity/pagecache.c | 22 ++++++++++++++++++++++
include/linux/fsverity.h | 2 ++
2 files changed, 24 insertions(+)
diff --git a/fs/verity/pagecache.c b/fs/verity/pagecache.c
index 1819314ecaa3..1d94bf73f38c 100644
--- a/fs/verity/pagecache.c
+++ b/fs/verity/pagecache.c
@@ -2,6 +2,7 @@
/*
* Copyright 2019 Google LLC
*/
+#include "fsverity_private.h"
#include <linux/export.h>
#include <linux/fsverity.h>
@@ -56,3 +57,24 @@ void generic_readahead_merkle_tree(struct inode *inode, pgoff_t index,
folio_put(folio);
}
EXPORT_SYMBOL_GPL(generic_readahead_merkle_tree);
+
+/**
+ * fsverity_folio_zero_hash() - fill folio with hashes of zero data block
+ * @folio: folio to fill
+ * @poff: offset in the folio to start
+ * @plen: length of the range to fill with hashes
+ * @vi: fsverity info
+ */
+void fsverity_folio_zero_hash(struct folio *folio, size_t poff, size_t plen,
+ struct fsverity_info *vi)
+{
+ size_t offset = poff;
+
+ WARN_ON_ONCE(!IS_ALIGNED(poff, vi->tree_params.digest_size));
+ WARN_ON_ONCE(!IS_ALIGNED(plen, vi->tree_params.digest_size));
+
+ for (; offset < (poff + plen); offset += vi->tree_params.digest_size)
+ memcpy_to_folio(folio, offset, vi->tree_params.zero_digest,
+ vi->tree_params.digest_size);
+}
+EXPORT_SYMBOL_GPL(fsverity_folio_zero_hash);
diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h
index 8ba7806b225e..b490b2c8a393 100644
--- a/include/linux/fsverity.h
+++ b/include/linux/fsverity.h
@@ -321,5 +321,7 @@ void fsverity_cleanup_inode(struct inode *inode);
struct page *generic_read_merkle_tree_page(struct inode *inode, pgoff_t index);
void generic_readahead_merkle_tree(struct inode *inode, pgoff_t index,
unsigned long nr_pages);
+void fsverity_folio_zero_hash(struct folio *folio, size_t poff, size_t plen,
+ struct fsverity_info *vi);
#endif /* _LINUX_FSVERITY_H */
--
2.51.2
^ permalink raw reply related
* [PATCH v4 03/25] fsverity: generate and store zero-block hash
From: Andrey Albershteyn @ 2026-03-09 19:23 UTC (permalink / raw)
To: linux-xfs, fsverity, linux-fsdevel, ebiggers
Cc: Andrey Albershteyn, hch, linux-ext4, linux-f2fs-devel,
linux-btrfs, djwong
In-Reply-To: <20260309192355.176980-1-aalbersh@kernel.org>
Compute the hash of one filesystem block's worth of zeros. A filesystem
implementation can decide to elide merkle tree blocks containing only
this hash and synthesize the contents at read time.
Let's pretend that there's a file containing six data blocks and whose
merkle tree looks roughly like this:
root
+--leaf0
| +--data0
| +--data1
| `--data2
`--leaf1
+--data3
+--data4
`--data5
If data[0-2] are sparse holes, then leaf0 will contain a repeating
sequence of @zero_digest. Therefore, leaf0 need not be written to disk
because its contents can be synthesized.
A subsequent xfs patch will use this to reduce the size of the merkle
tree when dealing with sparse gold master disk images and the like.
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
---
fs/verity/fsverity_private.h | 3 +++
fs/verity/open.c | 3 +++
2 files changed, 6 insertions(+)
diff --git a/fs/verity/fsverity_private.h b/fs/verity/fsverity_private.h
index 6e6854c19078..35636c1e2c41 100644
--- a/fs/verity/fsverity_private.h
+++ b/fs/verity/fsverity_private.h
@@ -53,6 +53,9 @@ struct merkle_tree_params {
u64 tree_size; /* Merkle tree size in bytes */
unsigned long tree_pages; /* Merkle tree size in pages */
+ /* the hash of a merkle block-sized buffer of zeroes */
+ u8 zero_digest[FS_VERITY_MAX_DIGEST_SIZE];
+
/*
* Starting block index for each tree level, ordered from leaf level (0)
* to root level ('num_levels - 1')
diff --git a/fs/verity/open.c b/fs/verity/open.c
index 0483db672526..94407a37aa08 100644
--- a/fs/verity/open.c
+++ b/fs/verity/open.c
@@ -153,6 +153,9 @@ int fsverity_init_merkle_tree_params(struct merkle_tree_params *params,
goto out_err;
}
+ fsverity_hash_block(params, page_address(ZERO_PAGE(0)),
+ params->zero_digest);
+
params->tree_size = offset << log_blocksize;
params->tree_pages = PAGE_ALIGN(params->tree_size) >> PAGE_SHIFT;
return 0;
--
2.51.2
^ permalink raw reply related
* [PATCH v4 02/25] fsverity: expose ensure_fsverity_info()
From: Andrey Albershteyn @ 2026-03-09 19:23 UTC (permalink / raw)
To: linux-xfs, fsverity, linux-fsdevel, ebiggers
Cc: Andrey Albershteyn, hch, linux-ext4, linux-f2fs-devel,
linux-btrfs, djwong
In-Reply-To: <20260309192355.176980-1-aalbersh@kernel.org>
This function will be used by XFS's scrub to force fsverity activation,
therefore, to read fsverity context.
Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
---
fs/verity/open.c | 5 +++--
include/linux/fsverity.h | 7 +++++++
2 files changed, 10 insertions(+), 2 deletions(-)
diff --git a/fs/verity/open.c b/fs/verity/open.c
index dfa0d1afe0fe..0483db672526 100644
--- a/fs/verity/open.c
+++ b/fs/verity/open.c
@@ -344,7 +344,7 @@ int fsverity_get_descriptor(struct inode *inode,
return 0;
}
-static int ensure_verity_info(struct inode *inode)
+int fsverity_ensure_verity_info(struct inode *inode)
{
struct fsverity_info *vi = fsverity_get_info(inode), *found;
struct fsverity_descriptor *desc;
@@ -380,12 +380,13 @@ static int ensure_verity_info(struct inode *inode)
kfree(desc);
return err;
}
+EXPORT_SYMBOL_GPL(fsverity_ensure_verity_info);
int __fsverity_file_open(struct inode *inode, struct file *filp)
{
if (filp->f_mode & FMODE_WRITE)
return -EPERM;
- return ensure_verity_info(inode);
+ return fsverity_ensure_verity_info(inode);
}
EXPORT_SYMBOL_GPL(__fsverity_file_open);
diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h
index a8f9aa75b792..8ba7806b225e 100644
--- a/include/linux/fsverity.h
+++ b/include/linux/fsverity.h
@@ -188,6 +188,7 @@ int fsverity_get_digest(struct inode *inode,
/* open.c */
int __fsverity_file_open(struct inode *inode, struct file *filp);
+int fsverity_ensure_verity_info(struct inode *inode);
/* read_metadata.c */
@@ -281,6 +282,12 @@ static inline void fsverity_enqueue_verify_work(struct work_struct *work)
WARN_ON_ONCE(1);
}
+static inline int fsverity_ensure_verity_info(struct inode *inode)
+{
+ WARN_ON_ONCE(1);
+ return -EOPNOTSUPP;
+}
+
#endif /* !CONFIG_FS_VERITY */
static inline bool fsverity_verify_folio(struct fsverity_info *vi,
--
2.51.2
^ permalink raw reply related
* [PATCH v4 01/25] fsverity: report validation errors through fserror to fsnotify
From: Andrey Albershteyn @ 2026-03-09 19:23 UTC (permalink / raw)
To: linux-xfs, fsverity, linux-fsdevel, ebiggers
Cc: Andrey Albershteyn, hch, linux-ext4, linux-f2fs-devel,
linux-btrfs, djwong
In-Reply-To: <20260309192355.176980-1-aalbersh@kernel.org>
Reported verification errors to fsnotify through recently added fserror
interface.
Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
---
fs/verity/verify.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/fs/verity/verify.c b/fs/verity/verify.c
index 4004a1d42875..99276053d3bb 100644
--- a/fs/verity/verify.c
+++ b/fs/verity/verify.c
@@ -9,6 +9,7 @@
#include <linux/bio.h>
#include <linux/export.h>
+#include <linux/fserror.h>
#define FS_VERITY_MAX_PENDING_BLOCKS 2
@@ -312,6 +313,7 @@ static bool verify_data_block(struct fsverity_info *vi,
data_pos, level - 1, params->hash_alg->name, hsize, want_hash,
params->hash_alg->name, hsize,
level == 0 ? dblock->real_hash : real_hash);
+ fserror_report_data_lost(inode, data_pos, params->block_size, GFP_NOFS);
error:
for (; level > 0; level--) {
kunmap_local(hblocks[level - 1].addr);
--
2.51.2
^ permalink raw reply related
* [PATCH v4 00/25] fs-verity support for XFS with post EOF merkle tree
From: Andrey Albershteyn @ 2026-03-09 19:23 UTC (permalink / raw)
To: linux-xfs, fsverity, linux-fsdevel, ebiggers
Cc: Andrey Albershteyn, hch, linux-ext4, linux-f2fs-devel,
linux-btrfs, djwong, david
Hi all,
This patch series adds fs-verity support for XFS. This version stores
merkle tree beyond end of the file, the same way as ext4 does it. The
difference is that verity descriptor is stored at the next aligned 64k
block after the merkle tree last block. This is done due to sparse
merkle tree which doesn't store hashes of zero data blocks.
The patchset starts with a few fs-verity preparation patches. Then, a
few patches to allow iomap to work in post EOF region. The XFS fs-verity
implementation follows.
The tree is read by iomap into page cache at offset of next largest
folio past end of file. The same offset is used for on-disk.
This patchsets also synthesizes merkle tree block full of hashes of
zeroed data blocks. This merkle blocks are not stored on disk, they are
holes in the tree.
Testing. The -g verity is passing for 1k, 8k and 4k with/without quota,
the tests include different merkle tree block size.
This series based on latest fsverity branch with patchset fs generated
integrity information [1] on top of fsverity/for-current.
kernel:
https://git.kernel.org/pub/scm/linux/kernel/git/aalbersh/xfs-linux.git/log/?h=b4/fsverity
xfsprogs:
https://github.com/alberand/xfsprogs/tree/b4/fsverity
xfstests:
https://github.com/alberand/xfstests/tree/b4/fsverity
Cc: fsverity@lists.linux.dev
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-xfs@vger.kernel.org
Cc: david@fromorbit.com
Cc: djwong@kernel.org
Cc: ebiggers@kernel.org
Cc: hch@lst.de
[1]: https://lore.kernel.org/linux-xfs/20260223132021.292832-1-hch@lst.de/
---
Changes in v4:
- Use fserror interface in fsverity instead of fs callback
- Hoist pagecache_read from f2fs/ext4 to fsverity
- Refactor iomap code
- Fetch fsverity_info only for file data and merkle tree holes
- Do not disable preallocation, remove unwritten extents instead
- Offload fsverity hash I/O to fsverity workqueue in read path
- Store merkle tree at round_up(i_size, 64k)
- Add a spacing between merkle tree and fsverity descriptor as next 64k
aligned block
- Squash helpers into first user commits
- Squash on-disk format changes into single commit
- Drop different offset for pagecache/on-disk
- Don't zero out pages in higher order folios in write path
- Link to v3: https://lore.kernel.org/fsverity/20260217231937.1183679-1-aalbersh@kernel.org/T/#t
Changes in v3:
- Different on-disk and pagecache offset
- Use read path ioends
- Switch to hashtable fsverity info
- Synthesize merkle tree blocks full of zeroes
- Other minor refactors
- Link to v2: https://lore.kernel.org/fsverity/20260114164210.GO15583@frogsfrogsfrogs/T/#t
Changes in v2:
- Move to VFS interface for merkle tree block reading
- Drop patchset for per filesystem workqueues
- Change how offsets of the descriptor and tree metadata is calculated
- Store fs-verity descriptor in data fork side by side with merkle tree
- Simplify iomap changes, remove interface for post eof read/write
- Get rid of extended attribute implementation
- Link to v1: https://lore.kernel.org/r/20250728-fsverity-v1-0-9e5443af0e34@kernel.org
Andrey Albershteyn (23):
fsverity: report validation errors through fserror to fsnotify
fsverity: expose ensure_fsverity_info()
fsverity: generate and store zero-block hash
fsverity: introduce fsverity_folio_zero_hash()
fsverity: pass digest size and hash of the empty block to ->write
fsverity: hoist pagecache_read from f2fs/ext4 to fsverity
iomap: introduce IOMAP_F_FSVERITY and teach writeback to handle
fsverity
iomap: obtain fsverity info for read path
iomap: issue readahead for fsverity merkle tree
iomap: teach iomap to handle fsverity holes and verify data holes
iomap: introduce iomap_fsverity_write() for writing fsverity metadata
xfs: introduce fsverity on-disk changes
xfs: initialize fs-verity on file open
xfs: don't allow to enable DAX on fs-verity sealed inode
xfs: disable direct read path for fs-verity files
xfs: handle fsverity I/O in write/read path
xfs: use read ioend for fsverity data verification
xfs: add fs-verity support
xfs: remove unwritten extents after preallocations in fsverity
metadata
xfs: add fs-verity ioctls
xfs: introduce health state for corrupted fsverity metadata
xfs: add fsverity traces
xfs: enable ro-compat fs-verity flag
Darrick J. Wong (2):
xfs: advertise fs-verity being available on filesystem
xfs: check and repair the verity inode flag state
fs/btrfs/verity.c | 6 +-
fs/ext4/verity.c | 36 +--
fs/f2fs/verity.c | 34 +--
fs/iomap/buffered-io.c | 97 ++++++-
fs/iomap/trace.h | 3 +-
fs/verity/enable.c | 4 +-
fs/verity/fsverity_private.h | 3 +
fs/verity/open.c | 8 +-
fs/verity/pagecache.c | 55 ++++
fs/verity/verify.c | 2 +
fs/xfs/Makefile | 1 +
fs/xfs/libxfs/xfs_bmap.c | 7 +
fs/xfs/libxfs/xfs_format.h | 13 +-
fs/xfs/libxfs/xfs_fs.h | 2 +
fs/xfs/libxfs/xfs_health.h | 4 +-
fs/xfs/libxfs/xfs_inode_buf.c | 8 +
fs/xfs/libxfs/xfs_inode_util.c | 2 +
fs/xfs/libxfs/xfs_sb.c | 4 +
fs/xfs/scrub/attr.c | 7 +
fs/xfs/scrub/common.c | 53 ++++
fs/xfs/scrub/common.h | 2 +
fs/xfs/scrub/inode.c | 7 +
fs/xfs/scrub/inode_repair.c | 36 +++
fs/xfs/xfs_aops.c | 48 +++-
fs/xfs/xfs_bmap_util.c | 8 +
fs/xfs/xfs_file.c | 19 +-
fs/xfs/xfs_fsverity.c | 460 +++++++++++++++++++++++++++++++++
fs/xfs/xfs_fsverity.h | 28 ++
fs/xfs/xfs_health.c | 1 +
fs/xfs/xfs_inode.h | 6 +
fs/xfs/xfs_ioctl.c | 14 +
fs/xfs/xfs_iomap.c | 15 +-
fs/xfs/xfs_iops.c | 4 +
fs/xfs/xfs_message.c | 4 +
fs/xfs/xfs_message.h | 1 +
fs/xfs/xfs_mount.h | 4 +
fs/xfs/xfs_super.c | 7 +
fs/xfs/xfs_trace.h | 45 ++++
include/linux/fsverity.h | 17 +-
include/linux/iomap.h | 10 +
40 files changed, 992 insertions(+), 93 deletions(-)
create mode 100644 fs/xfs/xfs_fsverity.c
create mode 100644 fs/xfs/xfs_fsverity.h
--
2.51.2
^ permalink raw reply
* Re: [PATCH 2/9] fstests: add _mkfs_scratch_clone() helper
From: Zorro Lang @ 2026-03-09 19:13 UTC (permalink / raw)
To: Anand Jain; +Cc: fstests, linux-btrfs, linux-ext4, linux-xfs
In-Reply-To: <254fdd3e212f6618ea33207ef24db2b316d2d8fc.1772095513.git.asj@kernel.org>
On Thu, Feb 26, 2026 at 10:41:43PM +0800, Anand Jain wrote:
> Introduce _mkfs_scratch_clone() to mkfs the scratch device and clone it to
> the next device in SCRATCH_DEV_POOL.
>
> Signed-off-by: Anand Jain <asj@kernel.org>
> ---
> common/rc | 32 ++++++++++++++++++++++++++++++++
> 1 file changed, 32 insertions(+)
>
> diff --git a/common/rc b/common/rc
> index 9db8b3e88996..2253438ef0f6 100644
> --- a/common/rc
> +++ b/common/rc
> @@ -1503,6 +1503,38 @@ _scratch_resvblks()
> esac
> }
>
> +_scratch_mkfs_sized_clone()
> +{
> + local devs=($SCRATCH_DEV_POOL)
> + local scratch_data="$1"
> + local size=$(_small_fs_size_mb 128) # Smallest possible
> +
> + size=$((size * 1024 * 1024))
> +
> + # make sure there are two devices
> + if [ "${#devs[@]}" -ne 2 ]; then
What about if ${#devs[@]} > 2 ?
> + _notrun "Test requires exactly 2 devices"
> + fi
> +
> + case "$FSTYP" in
> + "btrfs")
> + _scratch_mkfs_sized $size
> + _scratch_mount
> + $BTRFS_UTIL_PROG subvolume create $SCRATCH_MNT/sv1
> + _scratch_unmount
> + ;;
> + "xfs"|"ext4")
> + _scratch_mkfs_sized $size
> + ;;
> + *)
> + _notrun "fstests clone op unsupported for FS $FSTYP"
> + ;;
> + esac
> +
> + # clone SCRATCH_DEV devs[0] to devs[1].
> + dd if=$SCRATCH_DEV of=${devs[1]} bs=$size status=none count=1 || \
> + _fail "Clone failed"
I'm wondering if we absolutely need to use SCRATCH_DEV_POOL for this test. Could we clone SCRATCH_DEV
to an image file instead? Or would it be feasible to simply run the test using two image files?
Thanks,
Zorro
> +}
>
> # Repair scratch filesystem. Returns 0 if the FS is good to go (either no
> # errors found or errors were fixed) and nonzero otherwise; also spits out
> --
> 2.43.0
>
>
^ permalink raw reply
* Re: [PATCH v3 00/12] vfs: change inode->i_ino from unsigned long to u64
From: Mimi Zohar @ 2026-03-09 19:00 UTC (permalink / raw)
To: Jeff Layton
Cc: linux-fsdevel, linux-kernel, linux-trace-kernel, nvdimm, fsverity,
linux-mm, netfs, linux-ext4, linux-f2fs-devel, linux-nfs,
linux-cifs, samba-technical, linux-nilfs, v9fs, linux-afs, autofs,
ceph-devel, codalist, ecryptfs, linux-mtd, jfs-discussion, ntfs3,
ocfs2-devel, devel, linux-unionfs, apparmor,
linux-security-module, linux-integrity, selinux, amd-gfx,
dri-devel, linux-media, linaro-mm-sig, netdev, linux-perf-users,
linux-fscrypt, linux-xfs, linux-hams, linux-x25, audit,
linux-bluetooth, linux-can, linux-sctp, bpf
In-Reply-To: <f22758116dabd3c135a833bcb5cfcd2ea4f6ecf4.camel@kernel.org>
On Mon, 2026-03-09 at 13:59 -0400, Jeff Layton wrote:
> On Mon, 2026-03-09 at 13:47 -0400, Mimi Zohar wrote:
> > [ I/O socket time out. Trimming the To list.]
> >
> > On Wed, 2026-03-04 at 10:32 -0500, Jeff Layton wrote:
> > > This version squashes all of the format-string changes and the i_ino
> > > type change into the same patch. This results in a giant 600+ line patch
> > > at the end of the series, but it does remain bisectable. Because the
> > > patchset was reorganized (again) some of the R-b's and A-b's have been
> > > dropped.
> > >
> > > The entire pile is in the "iino-u64" branch of my tree, if anyone is
> > > interested in testing this.
> > >
> > > https://git.kernel.org/pub/scm/linux/kernel/git/jlayton/linux.git/
> > >
> > > Original cover letter follows:
> > >
> > > ----------------------8<-----------------------
> > >
> > > Christian said [1] to "just do it" when I proposed this, so here we are!
> > >
> > > For historical reasons, the inode->i_ino field is an unsigned long,
> > > which means that it's 32 bits on 32 bit architectures. This has caused a
> > > number of filesystems to implement hacks to hash a 64-bit identifier
> > > into a 32-bit field, and deprives us of a universal identifier field for
> > > an inode.
> > >
> > > This patchset changes the inode->i_ino field from an unsigned long to a
> > > u64. This shouldn't make any material difference on 64-bit hosts, but
> > > 32-bit hosts will see struct inode grow by at least 4 bytes. This could
> > > have effects on slabcache sizes and field alignment.
> > >
> > > The bulk of the changes are to format strings and tracepoints, since the
> > > kernel itself doesn't care that much about the i_ino field. The first
> > > patch changes some vfs function arguments, so check that one out
> > > carefully.
> > >
> > > With this change, we may be able to shrink some inode structures. For
> > > instance, struct nfs_inode has a fileid field that holds the 64-bit
> > > inode number. With this set of changes, that field could be eliminated.
> > > I'd rather leave that sort of cleanups for later just to keep this
> > > simple.
> > >
> > > Much of this set was generated by LLM, but I attributed it to myself
> > > since I consider this to be in the "menial tasks" category of LLM usage.
> > >
> > > [1]: https://lore.kernel.org/linux-fsdevel/20260219-portrait-winkt-959070cee42f@brauner/
> > >
> > > Signed-off-by: Jeff Layton <jlayton@kernel.org>
> >
> > Jeff, missing from this patch set is EVM. In hmac_add_misc() EVM copies the
> > i_ino and calculates either an HMAC or file meta-data hash, which is then
> > signed.
> >
> >
>
> Thanks Mimi, good catch.
>
> It looks like we should just be able to change the ino field to a u64
> alongside everything else. Something like this:
>
> diff --git a/security/integrity/evm/evm_crypto.c b/security/integrity/evm/evm_crypto.c
> index c0ca4eedb0fe..77b6c2fa345e 100644
> --- a/security/integrity/evm/evm_crypto.c
> +++ b/security/integrity/evm/evm_crypto.c
> @@ -144,7 +144,7 @@ static void hmac_add_misc(struct shash_desc *desc, struct inode *inode,
> char type, char *digest)
> {
> struct h_misc {
> - unsigned long ino;
> + u64 ino;
> __u32 generation;
> uid_t uid;
> gid_t gid;
>
Agreed.
>
> That should make no material difference on 64-bit hosts. What's the
> effect on 32-bit? Will they just need to remeasure everything or would
> the consequences be more dire? Do we have any clue whether anyone is
> using EVM in 32-bit environments?
All good questions. Unfortunately I don't know the answer to most of them. What
we do know: changing the size of the i_ino field would affect EVM file metadata
verification and would require relabeling the filesystem. Even packages
containing EVM portable signatures, which don't include or verify the i_ino
number, would be affected.
Mimi
^ permalink raw reply
* Re: [PATCH v3 00/12] vfs: change inode->i_ino from unsigned long to u64
From: Jeff Layton @ 2026-03-09 17:59 UTC (permalink / raw)
To: Mimi Zohar
Cc: linux-fsdevel, linux-kernel, linux-trace-kernel, nvdimm, fsverity,
linux-mm, netfs, linux-ext4, linux-f2fs-devel, linux-nfs,
linux-cifs, samba-technical, linux-nilfs, v9fs, linux-afs, autofs,
ceph-devel, codalist, ecryptfs, linux-mtd, jfs-discussion, ntfs3,
ocfs2-devel, devel, linux-unionfs, apparmor,
linux-security-module, linux-integrity, selinux, amd-gfx,
dri-devel, linux-media, linaro-mm-sig, netdev, linux-perf-users,
linux-fscrypt, linux-xfs, linux-hams, linux-x25, audit,
linux-bluetooth, linux-can, linux-sctp, bpf
In-Reply-To: <05b5d55c49b5a1bbc43a5315e3c84872e7e634b3.camel@linux.ibm.com>
On Mon, 2026-03-09 at 13:47 -0400, Mimi Zohar wrote:
> [ I/O socket time out. Trimming the To list.]
>
> On Wed, 2026-03-04 at 10:32 -0500, Jeff Layton wrote:
> > This version squashes all of the format-string changes and the i_ino
> > type change into the same patch. This results in a giant 600+ line patch
> > at the end of the series, but it does remain bisectable. Because the
> > patchset was reorganized (again) some of the R-b's and A-b's have been
> > dropped.
> >
> > The entire pile is in the "iino-u64" branch of my tree, if anyone is
> > interested in testing this.
> >
> > https://git.kernel.org/pub/scm/linux/kernel/git/jlayton/linux.git/
> >
> > Original cover letter follows:
> >
> > ----------------------8<-----------------------
> >
> > Christian said [1] to "just do it" when I proposed this, so here we are!
> >
> > For historical reasons, the inode->i_ino field is an unsigned long,
> > which means that it's 32 bits on 32 bit architectures. This has caused a
> > number of filesystems to implement hacks to hash a 64-bit identifier
> > into a 32-bit field, and deprives us of a universal identifier field for
> > an inode.
> >
> > This patchset changes the inode->i_ino field from an unsigned long to a
> > u64. This shouldn't make any material difference on 64-bit hosts, but
> > 32-bit hosts will see struct inode grow by at least 4 bytes. This could
> > have effects on slabcache sizes and field alignment.
> >
> > The bulk of the changes are to format strings and tracepoints, since the
> > kernel itself doesn't care that much about the i_ino field. The first
> > patch changes some vfs function arguments, so check that one out
> > carefully.
> >
> > With this change, we may be able to shrink some inode structures. For
> > instance, struct nfs_inode has a fileid field that holds the 64-bit
> > inode number. With this set of changes, that field could be eliminated.
> > I'd rather leave that sort of cleanups for later just to keep this
> > simple.
> >
> > Much of this set was generated by LLM, but I attributed it to myself
> > since I consider this to be in the "menial tasks" category of LLM usage.
> >
> > [1]: https://lore.kernel.org/linux-fsdevel/20260219-portrait-winkt-959070cee42f@brauner/
> >
> > Signed-off-by: Jeff Layton <jlayton@kernel.org>
>
> Jeff, missing from this patch set is EVM. In hmac_add_misc() EVM copies the
> i_ino and calculates either an HMAC or file meta-data hash, which is then
> signed.
>
>
Thanks Mimi, good catch.
It looks like we should just be able to change the ino field to a u64
alongside everything else. Something like this:
diff --git a/security/integrity/evm/evm_crypto.c b/security/integrity/evm/evm_crypto.c
index c0ca4eedb0fe..77b6c2fa345e 100644
--- a/security/integrity/evm/evm_crypto.c
+++ b/security/integrity/evm/evm_crypto.c
@@ -144,7 +144,7 @@ static void hmac_add_misc(struct shash_desc *desc, struct inode *inode,
char type, char *digest)
{
struct h_misc {
- unsigned long ino;
+ u64 ino;
__u32 generation;
uid_t uid;
gid_t gid;
That should make no material difference on 64-bit hosts. What's the
effect on 32-bit? Will they just need to remeasure everything or would
the consequences be more dire? Do we have any clue whether anyone is
using EVM in 32-bit environments?
Thanks,
--
Jeff Layton <jlayton@kernel.org>
^ permalink raw reply related
* Re: [PATCH v3 00/12] vfs: change inode->i_ino from unsigned long to u64
From: Mimi Zohar @ 2026-03-09 17:47 UTC (permalink / raw)
To: Jeff Layton
Cc: linux-fsdevel, linux-kernel, linux-trace-kernel, nvdimm, fsverity,
linux-mm, netfs, linux-ext4, linux-f2fs-devel, linux-nfs,
linux-cifs, samba-technical, linux-nilfs, v9fs, linux-afs, autofs,
ceph-devel, codalist, ecryptfs, linux-mtd, jfs-discussion, ntfs3,
ocfs2-devel, devel, linux-unionfs, apparmor,
linux-security-module, linux-integrity, selinux, amd-gfx,
dri-devel, linux-media, linaro-mm-sig, netdev, linux-perf-users,
linux-fscrypt, linux-xfs, linux-hams, linux-x25, audit,
linux-bluetooth, linux-can, linux-sctp, bpf
In-Reply-To: <20260304-iino-u64-v3-0-2257ad83d372@kernel.org>
[ I/O socket time out. Trimming the To list.]
On Wed, 2026-03-04 at 10:32 -0500, Jeff Layton wrote:
> This version squashes all of the format-string changes and the i_ino
> type change into the same patch. This results in a giant 600+ line patch
> at the end of the series, but it does remain bisectable. Because the
> patchset was reorganized (again) some of the R-b's and A-b's have been
> dropped.
>
> The entire pile is in the "iino-u64" branch of my tree, if anyone is
> interested in testing this.
>
> https://git.kernel.org/pub/scm/linux/kernel/git/jlayton/linux.git/
>
> Original cover letter follows:
>
> ----------------------8<-----------------------
>
> Christian said [1] to "just do it" when I proposed this, so here we are!
>
> For historical reasons, the inode->i_ino field is an unsigned long,
> which means that it's 32 bits on 32 bit architectures. This has caused a
> number of filesystems to implement hacks to hash a 64-bit identifier
> into a 32-bit field, and deprives us of a universal identifier field for
> an inode.
>
> This patchset changes the inode->i_ino field from an unsigned long to a
> u64. This shouldn't make any material difference on 64-bit hosts, but
> 32-bit hosts will see struct inode grow by at least 4 bytes. This could
> have effects on slabcache sizes and field alignment.
>
> The bulk of the changes are to format strings and tracepoints, since the
> kernel itself doesn't care that much about the i_ino field. The first
> patch changes some vfs function arguments, so check that one out
> carefully.
>
> With this change, we may be able to shrink some inode structures. For
> instance, struct nfs_inode has a fileid field that holds the 64-bit
> inode number. With this set of changes, that field could be eliminated.
> I'd rather leave that sort of cleanups for later just to keep this
> simple.
>
> Much of this set was generated by LLM, but I attributed it to myself
> since I consider this to be in the "menial tasks" category of LLM usage.
>
> [1]: https://lore.kernel.org/linux-fsdevel/20260219-portrait-winkt-959070cee42f@brauner/
>
> Signed-off-by: Jeff Layton <jlayton@kernel.org>
Jeff, missing from this patch set is EVM. In hmac_add_misc() EVM copies the
i_ino and calculates either an HMAC or file meta-data hash, which is then
signed.
Mimi
^ permalink raw reply
* Re: [PATCH] mm/slab: fix an incorrect check in obj_exts_alloc_size()
From: vbabka @ 2026-03-09 14:00 UTC (permalink / raw)
To: Harry Yoo
Cc: adilger.kernel, akpm, cgroups, hannes, hao.li, linux-ext4,
linux-fsdevel, linux-kernel, linux-mm, shicenci, cl, rientjes,
roman.gushchin, viro, surenb, stable
In-Reply-To: <20260309072219.22653-1-harry.yoo@oracle.com>
On 3/9/26 08:22, Harry Yoo wrote:
> obj_exts_alloc_size() prevents recursive allocation of slabobj_ext
> array from the same cache, to avoid creating slabs that are never freed.
>
> There is one mistake that returns the original size when memory
> allocation profiling is disabled. The assumption was that
> memcg-triggered slabobj_ext allocation is always served from
> KMALLOC_CGROUP type. But this is wrong [1]: when the caller specifies
> both __GFP_RECLAIMABLE and __GFP_ACCOUNT with SLUB_TINY enabled, the
> allocation is served from normal kmalloc. This is because kmalloc_type()
> prioritizes __GFP_RECLAIMABLE over __GFP_ACCOUNT, and SLUB_TINY aliases
> KMALLOC_RECLAIM with KMALLOC_NORMAL.
Hm that's suboptimal (leads to sparsely used obj_exts in normal kmalloc
slabs) and maybe separately from this hotfix we could make sure that with
SLUB_TINY, __GFP_ACCOUNT is preferred going forward?
> As a result, the recursion guard is bypassed and the problematic slabs
> can be created. Fix this by removing the mem_alloc_profiling_enabled()
> check entirely. The remaining is_kmalloc_normal() check is still
> sufficient to detect whether the cache is of KMALLOC_NORMAL type and
> avoid bumping the size if it's not.
>
> Without SLUB_TINY, no functional change intended.
> With SLUB_TINY, allocations with __GFP_ACCOUNT|__GFP_RECLAIMABLE
> now allocate a larger array if the sizes equal.
>
> Reported-by: Zw Tang <shicenci@gmail.com>
> Fixes: 280ea9c3154b ("mm/slab: avoid allocating slabobj_ext array from its own slab")
> Closes: https://lore.kernel.org/linux-mm/CAPHJ_VKuMKSke8b11AZQw1PTSFN4n2C0gFxC6xGOG0ZLHgPmnA@mail.gmail.com [1]
> Cc: stable@vger.kernel.org
> Signed-off-by: Harry Yoo <harry.yoo@oracle.com>
Added to slab/for-next-fixes, thanks!
> ---
>
> Zw Tang, could you please confirm that the warning disappears
> on your test environment, with this patch applied?
>
> mm/slub.c | 7 -------
> 1 file changed, 7 deletions(-)
>
> diff --git a/mm/slub.c b/mm/slub.c
> index 20cb4f3b636d..6371838d2352 100644
> --- a/mm/slub.c
> +++ b/mm/slub.c
> @@ -2119,13 +2119,6 @@ static inline size_t obj_exts_alloc_size(struct kmem_cache *s,
> size_t sz = sizeof(struct slabobj_ext) * slab->objects;
> struct kmem_cache *obj_exts_cache;
>
> - /*
> - * slabobj_ext array for KMALLOC_CGROUP allocations
> - * are served from KMALLOC_NORMAL caches.
> - */
> - if (!mem_alloc_profiling_enabled())
> - return sz;
> -
> if (sz > KMALLOC_MAX_CACHE_SIZE)
> return sz;
>
>
> base-commit: 6432f15c818cb30eec7c4ca378ecdebd9796f741
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox