* [PATCH v9 04/22] fsverity: generate and store zero-block hash
From: Andrey Albershteyn @ 2026-04-28 8:33 UTC (permalink / raw)
To: linux-xfs, fsverity, linux-fsdevel, ebiggers
Cc: Andrey Albershteyn, hch, linux-ext4, linux-f2fs-devel,
linux-btrfs, linux-unionfs, djwong
In-Reply-To: <20260428083332.768693-1-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 131 data block and whose
merkle tree looks roughly like this:
root
+--leaf0
| +--data0
| +--data1
| +--...
| `--data128
`--leaf1
+--data129
+--data130
`--data131
If data[0-128] 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.
Note that this works only on the first-level (data holes). fsverity
doesn't store/generate zero_digest for any higher levels.
Add a 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: Darrick J. Wong <djwong@kernel.org>
Acked-by: Eric Biggers <ebiggers@kernel.org>
Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
---
fs/verity/fsverity_private.h | 3 +++
fs/verity/measure.c | 4 ++--
fs/verity/open.c | 3 +++
fs/verity/pagecache.c | 22 ++++++++++++++++++++++
include/linux/fsverity.h | 8 ++++++++
5 files changed, 38 insertions(+), 2 deletions(-)
diff --git a/fs/verity/fsverity_private.h b/fs/verity/fsverity_private.h
index 6e6854c19078..881d46f25e08 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 an all-zeroes block */
+ 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/measure.c b/fs/verity/measure.c
index 6a35623ebdf0..818083507885 100644
--- a/fs/verity/measure.c
+++ b/fs/verity/measure.c
@@ -68,8 +68,8 @@ EXPORT_SYMBOL_GPL(fsverity_ioctl_measure);
* @alg: (out) the digest's algorithm, as a FS_VERITY_HASH_ALG_* value
* @halg: (out) the digest's algorithm, as a HASH_ALGO_* value
*
- * Retrieves the fsverity digest of the given file. The file must have been
- * opened at least once since the inode was last loaded into the inode cache;
+ * Retrieves the fsverity digest of the given file. The
+ * fsverity_ensure_verity_info() must be called on the inode beforehand;
* otherwise this function will not recognize when fsverity is enabled.
*
* The file's fsverity digest consists of @raw_digest in combination with either
diff --git a/fs/verity/open.c b/fs/verity/open.c
index d32d0899df25..875e8850ccba 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;
diff --git a/fs/verity/pagecache.c b/fs/verity/pagecache.c
index 1819314ecaa3..99f5f53eea98 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_fill_zerohash() - fill folio with hashes of zero data block
+ * @folio: folio to fill
+ * @offset: offset in the folio to start
+ * @len: length of the range to fill with hashes
+ * @vi: fsverity info
+ */
+void fsverity_fill_zerohash(struct folio *folio, size_t offset, size_t len,
+ struct fsverity_info *vi)
+{
+ size_t off = offset;
+
+ WARN_ON_ONCE(!IS_ALIGNED(offset, vi->tree_params.digest_size));
+ WARN_ON_ONCE(!IS_ALIGNED(len, vi->tree_params.digest_size));
+
+ for (; off < (offset + len); off += vi->tree_params.digest_size)
+ memcpy_to_folio(folio, off, vi->tree_params.zero_digest,
+ vi->tree_params.digest_size);
+}
+EXPORT_SYMBOL_GPL(fsverity_fill_zerohash);
diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h
index 5562271bd628..3c3250f6f272 100644
--- a/include/linux/fsverity.h
+++ b/include/linux/fsverity.h
@@ -201,6 +201,8 @@ bool fsverity_verify_blocks(struct fsverity_info *vi, struct folio *folio,
size_t len, size_t offset);
void fsverity_verify_bio(struct fsverity_info *vi, struct bio *bio);
void fsverity_enqueue_verify_work(struct work_struct *work);
+void fsverity_fill_zerohash(struct folio *folio, size_t offset, size_t len,
+ struct fsverity_info *vi);
#else /* !CONFIG_FS_VERITY */
@@ -281,6 +283,12 @@ static inline void fsverity_enqueue_verify_work(struct work_struct *work)
WARN_ON_ONCE(1);
}
+static inline void fsverity_fill_zerohash(struct folio *folio, size_t offset,
+ size_t len, struct fsverity_info *vi)
+{
+ WARN_ON_ONCE(1);
+}
+
#endif /* !CONFIG_FS_VERITY */
static inline bool fsverity_verify_folio(struct fsverity_info *vi,
--
2.51.2
^ permalink raw reply related
* [PATCH v9 03/22] ovl: use core fsverity ensure info interface
From: Andrey Albershteyn @ 2026-04-28 8:33 UTC (permalink / raw)
To: linux-xfs, fsverity, linux-fsdevel, ebiggers
Cc: Andrey Albershteyn, hch, linux-ext4, linux-f2fs-devel,
linux-btrfs, linux-unionfs, djwong, Amir Goldstein
In-Reply-To: <20260428083332.768693-1-aalbersh@kernel.org>
fsverity now exposes fsverity_ensure_verity_info() which could be used
instead of opening file to ensure that fsverity info is loaded and
attached to inode.
Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
Acked-by: Amir Goldstein <amir73il@gmail.com>
---
fs/overlayfs/util.c | 14 +++-----------
1 file changed, 3 insertions(+), 11 deletions(-)
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index 2ea769f311c3..dd2e81022e4f 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -16,6 +16,7 @@
#include <linux/namei.h>
#include <linux/ratelimit.h>
#include <linux/overflow.h>
+#include <linux/fsverity.h>
#include "overlayfs.h"
/* Get write access to upper mnt - may fail if upper sb was remounted ro */
@@ -1377,18 +1378,9 @@ char *ovl_get_redirect_xattr(struct ovl_fs *ofs, const struct path *path, int pa
int ovl_ensure_verity_loaded(const struct path *datapath)
{
struct inode *inode = d_inode(datapath->dentry);
- struct file *filp;
- if (!fsverity_active(inode) && IS_VERITY(inode)) {
- /*
- * If this inode was not yet opened, the verity info hasn't been
- * loaded yet, so we need to do that here to force it into memory.
- */
- filp = kernel_file_open(datapath, O_RDONLY, current_cred());
- if (IS_ERR(filp))
- return PTR_ERR(filp);
- fput(filp);
- }
+ if (fsverity_active(inode))
+ return fsverity_ensure_verity_info(inode);
return 0;
}
--
2.51.2
^ permalink raw reply related
* [PATCH v9 02/22] fsverity: expose ensure_fsverity_info()
From: Andrey Albershteyn @ 2026-04-28 8:33 UTC (permalink / raw)
To: linux-xfs, fsverity, linux-fsdevel, ebiggers
Cc: Andrey Albershteyn, hch, linux-ext4, linux-f2fs-devel,
linux-btrfs, linux-unionfs, djwong
In-Reply-To: <20260428083332.768693-1-aalbersh@kernel.org>
This function will be used by XFS's scrub to force fsverity activation,
therefore, to read fsverity context.
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Acked-by: Eric Biggers <ebiggers@kernel.org>
Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
fs/verity/open.c | 22 ++++++++++++++++++++--
include/linux/fsverity.h | 2 ++
2 files changed, 22 insertions(+), 2 deletions(-)
diff --git a/fs/verity/open.c b/fs/verity/open.c
index dfa0d1afe0fe..d32d0899df25 100644
--- a/fs/verity/open.c
+++ b/fs/verity/open.c
@@ -344,7 +344,24 @@ int fsverity_get_descriptor(struct inode *inode,
return 0;
}
-static int ensure_verity_info(struct inode *inode)
+/**
+ * fsverity_ensure_verity_info() - cache verity info if it's not already cached
+ * @inode: the inode for which verity info should be cached
+ *
+ * Ensure this inode has verity info attached to it, it's assumed the inode
+ * already has fsverity enabled. Read fsverity descriptor and creates verity
+ * based on that.
+ *
+ * This needs to be called at least once before any of the inode's data
+ * can be verified (and thus read at all) or the inode's fsverity digest
+ * retrieved. fsverity_file_open() calls this already, which handles
+ * normal file accesses. If a filesystem does any internal (i.e. not
+ * associated with a file descriptor) reads of the file's data or
+ * fsverity digest, it must call this explicitly before doing so.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int fsverity_ensure_verity_info(struct inode *inode)
{
struct fsverity_info *vi = fsverity_get_info(inode), *found;
struct fsverity_descriptor *desc;
@@ -380,12 +397,13 @@ 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..5562271bd628 100644
--- a/include/linux/fsverity.h
+++ b/include/linux/fsverity.h
@@ -309,6 +309,8 @@ static inline int fsverity_file_open(struct inode *inode, struct file *filp)
return 0;
}
+int fsverity_ensure_verity_info(struct inode *inode);
+
void fsverity_cleanup_inode(struct inode *inode);
struct page *generic_read_merkle_tree_page(struct inode *inode, pgoff_t index);
--
2.51.2
^ permalink raw reply related
* [PATCH v9 01/22] fsverity: report validation errors through fserror to fsnotify
From: Andrey Albershteyn @ 2026-04-28 8:33 UTC (permalink / raw)
To: linux-xfs, fsverity, linux-fsdevel, ebiggers
Cc: Andrey Albershteyn, hch, linux-ext4, linux-f2fs-devel,
linux-btrfs, linux-unionfs, djwong
In-Reply-To: <20260428083332.768693-1-aalbersh@kernel.org>
Reported verification errors to fsnotify through recently added fserror
interface.
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Eric Biggers <ebiggers@kernel.org>
Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
---
fs/verity/verify.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/fs/verity/verify.c b/fs/verity/verify.c
index 4004a1d42875..db8c350234bb 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
@@ -205,6 +206,8 @@ static bool verify_data_block(struct fsverity_info *vi,
if (memchr_inv(dblock->data, 0, params->block_size)) {
fsverity_err(inode,
"FILE CORRUPTED! Data past EOF is not zeroed");
+ fserror_report_data_lost(inode, data_pos,
+ params->block_size, GFP_NOFS);
return false;
}
return true;
@@ -312,6 +315,7 @@ 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 v9 00/22] fs-verity support for XFS with post EOF merkle tree
From: Andrey Albershteyn @ 2026-04-28 8:33 UTC (permalink / raw)
To: linux-xfs, fsverity, linux-fsdevel, ebiggers
Cc: Andrey Albershteyn, hch, linux-ext4, linux-f2fs-devel,
linux-btrfs, linux-unionfs, 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
on 4k and 64k page size systems. Tested -g quick for enabled/disabled
fsverity. Also, overlay/080 overlay/089 with XFS as base.
This series based on v7.0 with Christoph's read ioends patchset [1].
Darrick, Christoph, I left your Reviewed-by tags on the commits which
have fixes for issues found by sashiko.dev. I've attached diff of
the v8 vs v9 below. Let me know if this a problem or you have more
comments for these changes.
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: linux-unionfs@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 v9:
- Fix fsverity_fill_zerohash() parameter names
- A few fixes found by sashiko.dev:
- Replace ip->i_mount->m_attr_geo->blksize with m_sb.sb_blocksize
- Don't call xfs_trans_cancel() after xfs_trans_commit() in
xfs_fsverity_end_enable()
- Call xfs_fsverity_delete_metadata() if verity enable failed
- Change start/end type from xfs_fileoff_t to loff_t
- Return xfs_trans_commit() error from
xfs_fsverity_cancel_unwritten()
Changes in v8:
- Return fsverity_ensure_verity_info() errors from
ovl_ensure_verity_loaded()
Changes in v7:
- Move kerneldoc to fsverity_ensure_verity_info() definition
- Drop patch adding XFS traces
- Fix overly long line in the comment
- Make order of fserror and fsverity_error consistent
- Add overlay patch converting to fsverity_ensure_verity_info()
Changes in v6:
- Removed stub for fsverity_ensure_verity_info() as it's optimized out
- Rename fsverity_folio_zero_hash() to fsverify_fill_zerohash()
- Merge patches 8 to 10 into one
- Merge patch gerating zero_hash and fsverity_fill_zerohash() into one
- Add kerneldoc to fsverity_ensure_verity_info()
- Add comments to iomap_block_needs_zeroing()
Changes in v5:
- Add fserror_report_data_lost() for data blocks in page spanning EOF
- Issue fsverity metadata readahead in data readahead
- iomap_fsverity_write() return type fix
- Use of S_ISREG(mode)
- Make 65536 #define instead of open-coded
- Use transaction per unwritten extent removal
- Fetch fsverity_info for all fsverity metadata
- Revert fsverity_folio_zero_hash() stub as used in iomap
- Extend cancel_unwritten to whole file range to remove cow leftovers
- Drop delayed allocation on the COW fork on fsverity completion
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
--- >8 ---
ss (cb5e0282a061) fsverity: generate and store zero-block hash
diff --git a/left/include/linux/fsverity.h b/right/include/linux/fsverity.h
index e4503312d114..3c3250f6f272 100644
--- a/left/include/linux/fsverity.h
+++ b/right/include/linux/fsverity.h
@@ -201,8 +201,8 @@ bool fsverity_verify_blocks(struct fsverity_info *vi, struct folio *folio,
size_t len, size_t offset);
void fsverity_verify_bio(struct fsverity_info *vi, struct bio *bio);
void fsverity_enqueue_verify_work(struct work_struct *work);
-void fsverity_fill_zerohash(struct folio *folio, size_t poff, size_t plen,
- struct fsverity_info *vi);
+void fsverity_fill_zerohash(struct folio *folio, size_t offset, size_t len,
+ struct fsverity_info *vi);
#else /* !CONFIG_FS_VERITY */
@@ -283,8 +283,8 @@ static inline void fsverity_enqueue_verify_work(struct work_struct *work)
WARN_ON_ONCE(1);
}
-static inline void fsverity_fill_zerohash(struct folio *folio, size_t poff,
- size_t plen, struct fsverity_info *vi)
+static inline void fsverity_fill_zerohash(struct folio *folio, size_t offset,
+ size_t len, struct fsverity_info *vi)
{
WARN_ON_ONCE(1);
}
wr (aebd19f490d9) xfs: add fs-verity support
diff --git a/left/fs/xfs/xfs_fsverity.c b/right/fs/xfs/xfs_fsverity.c
index 68d9736d19d9..a505616636f9 100644
--- a/left/fs/xfs/xfs_fsverity.c
+++ b/right/fs/xfs/xfs_fsverity.c
@@ -111,7 +111,7 @@ xfs_fsverity_write_descriptor(
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;
+ unsigned int blksize = ip->i_mount->m_bsize;
u64 tree_last_block =
xfs_fsverity_metadata_offset(ip) + merkle_tree_size;
u64 desc_pos =
@@ -161,8 +161,6 @@ xfs_fsverity_delete_metadata(
goto err_cancel;
error = xfs_trans_commit(tp);
- if (error)
- goto err_cancel;
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
@@ -231,8 +229,10 @@ xfs_fsverity_end_enable(
xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL);
/* fs-verity failed, just cleanup */
- if (desc == NULL)
+ if (desc == NULL) {
+ error = xfs_fsverity_delete_metadata(ip);
goto out;
+ }
error = xfs_fsverity_write_descriptor(file, desc, desc_size,
merkle_tree_size);
zv (191b86b3216b) xfs: remove unwritten extents after preallocations in fsverity metadata
diff --git a/left/fs/xfs/xfs_fsverity.c b/right/fs/xfs/xfs_fsverity.c
index 0def83aba712..1a5948d372b6 100644
--- a/left/fs/xfs/xfs_fsverity.c
+++ b/right/fs/xfs/xfs_fsverity.c
@@ -176,8 +176,8 @@ err_cancel:
static int
xfs_fsverity_cancel_unwritten(
struct xfs_inode *ip,
- xfs_fileoff_t start,
- xfs_fileoff_t end)
+ loff_t start,
+ loff_t end)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_trans *tp;
@@ -215,6 +215,8 @@ xfs_fsverity_cancel_unwritten(
goto out_cancel;
error = xfs_trans_commit(tp);
+ if (error)
+ return error;
} else {
xfs_trans_cancel(tp);
}
--- >8 ---
Andrey Albershteyn (20):
fsverity: report validation errors through fserror to fsnotify
fsverity: expose ensure_fsverity_info()
ovl: use core fsverity ensure info interface
fsverity: generate and store zero-block hash
fsverity: pass digest size and hash of the all-zeroes block to ->write
fsverity: hoist pagecache_read from f2fs/ext4 to fsverity
iomap: introduce IOMAP_F_FSVERITY and teach writeback to handle
fsverity
iomap: teach iomap to read files with fsverity
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: 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 | 109 +++++++-
fs/iomap/trace.h | 3 +-
fs/overlayfs/util.c | 14 +-
fs/verity/enable.c | 4 +-
fs/verity/fsverity_private.h | 3 +
fs/verity/measure.c | 4 +-
fs/verity/open.c | 25 +-
fs/verity/pagecache.c | 55 ++++
fs/verity/verify.c | 4 +
fs/xfs/Makefile | 1 +
fs/xfs/libxfs/xfs_bmap.c | 7 +
fs/xfs/libxfs/xfs_format.h | 35 ++-
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 | 62 ++++-
fs/xfs/xfs_bmap_util.c | 8 +
fs/xfs/xfs_file.c | 19 +-
fs/xfs/xfs_fsverity.c | 457 +++++++++++++++++++++++++++++++++
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 +
include/linux/fsverity.h | 18 +-
include/linux/iomap.h | 13 +
41 files changed, 1019 insertions(+), 107 deletions(-)
create mode 100644 fs/xfs/xfs_fsverity.c
create mode 100644 fs/xfs/xfs_fsverity.h
--
2.51.2
^ permalink raw reply related
* Re: [PATCH] ext4: avoid BUG_ON() in ext4_get_inline_entry()
From: Jan Kara @ 2026-04-28 7:38 UTC (permalink / raw)
To: Vineet Agarwal
Cc: linux-ext4, linux-kernel, tytso, adilger.kernel, libaokun1, jack,
ojaswin, ritesh.list, yi.zhang
In-Reply-To: <20260427162020.49723-1-agarwal.vineet2006@gmail.com>
On Mon 27-04-26 21:50:20, Vineet Agarwal wrote:
> Corrupted inline directory metadata can cause offset to exceed
> the inline data size through rec_len processing in
> empty_inline_dir().
>
> This triggers BUG_ON() in ext4_get_inline_entry(), causing a
> kernel panic before ext4_check_dir_entry() can handle the
> corruption gracefully.
>
> Replace BUG_ON() with a NULL return and handle the invalid
> offset in the caller by emitting a warning and exiting safely.
>
> This prevents a kernel panic from corrupted inline directory
> metadata.
>
> Signed-off-by: Vineet Agarwal <agarwal.vineet2006@gmail.com>
I guess this is motivated by some syskaller fuzzing (would be good to
reference). It however doesn't explain how the BUG_ON can trigger when
empty_inline_dir() just did:
inline_len = ext4_get_inline_size(dir);
...
while (offset < inline_len) {
de = ext4_get_inline_entry(dir, &iloc, offset, ...)
I suspect modification of the fs image while being mounted which is not
something we care about.
Honza
> ---
> fs/ext4/inline.c | 9 ++++++++-
> 1 file changed, 8 insertions(+), 1 deletion(-)
>
> diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
> index 8045e4ff270c..bca9936ed6d0 100644
> --- a/fs/ext4/inline.c
> +++ b/fs/ext4/inline.c
> @@ -1718,7 +1718,8 @@ ext4_get_inline_entry(struct inode *inode,
> {
> void *inline_pos;
>
> - BUG_ON(offset > ext4_get_inline_size(inode));
> + if (offset > ext4_get_inline_size(inode))
> + return NULL;
>
> if (offset < EXT4_MIN_INLINE_DATA_SIZE) {
> inline_pos = (void *)ext4_raw_inode(iloc)->i_block;
> @@ -1773,6 +1774,12 @@ bool empty_inline_dir(struct inode *dir, int *has_inline_data)
> while (offset < inline_len) {
> de = ext4_get_inline_entry(dir, &iloc, offset,
> &inline_pos, &inline_size);
> + if (!de) {
> + ext4_warning(dir->i_sb,
> + "bad inline directory (dir #%llu) - invalid offset",
> + dir->i_ino);
> + goto out;
> + }
> if (ext4_check_dir_entry(dir, NULL, de,
> iloc.bh, inline_pos,
> inline_size, offset)) {
> --
> 2.54.0
>
--
Jan Kara <jack@suse.com>
SUSE Labs, CR
^ permalink raw reply
* [PATCH v4 9/9] fstests: btrfs: test UUID consistency for clones with metadata_uuid
From: Anand Jain @ 2026-04-28 6:42 UTC (permalink / raw)
To: fstests
Cc: linux-btrfs, linux-ext4, linux-xfs, linux-f2fs, amir73il, zlang,
hch
In-Reply-To: <cover.1777357320.git.asj@kernel.org>
Btrfs uses the metadata_uuid superblock feature to change the on-disk UUID
without rewriting every block header. This patch adds a sanity check to
ensure UUID consistency when a filesystem with metadata_uuid enabled is
cloned.
Signed-off-by: Anand Jain <asj@kernel.org>
---
tests/btrfs/348 | 92 +++++++++++++++++++++++++++++++++++++++++++++
tests/btrfs/348.out | 19 ++++++++++
2 files changed, 111 insertions(+)
create mode 100644 tests/btrfs/348
create mode 100644 tests/btrfs/348.out
diff --git a/tests/btrfs/348 b/tests/btrfs/348
new file mode 100644
index 000000000000..bb3d451caba5
--- /dev/null
+++ b/tests/btrfs/348
@@ -0,0 +1,92 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2026 Anand Jain <asj@kernel.org>. All Rights Reserved.
+#
+# FS QA Test 348
+#
+# Verify that the cloned filesystem UUID remains consistent, even when the
+# `metadata_uuid` feature is enabled.
+#
+
+. ./common/preamble
+. ./common/filter
+
+_begin_fstest auto quick mount clone
+
+_require_test
+_require_block_device $TEST_DEV
+_require_loop
+
+_cleanup()
+{
+ cd /
+ rm -r -f $tmp.*
+ umount $mnt1 $mnt2 2>/dev/null
+ _loop_image_destroy "${devs[@]}" 2> /dev/null
+}
+
+filter_pool()
+{
+ sed -e "s|${devs[0]}|DEV1|g" -e "s|${mnt1}|MNT1|g" \
+ -e "s|${devs[1]}|DEV2|g" -e "s|${mnt2}|MNT2|g" | _filter_spaces
+}
+
+pre_clone_tune()
+{
+ local temp_mnt=$TEST_DIR/${seq}_mnt
+
+ _require_command "$BTRFS_TUNE_PROG" btrfstune
+ mkdir -p $temp_mnt
+ _mount ${devs[0]} $temp_mnt
+ $BTRFS_UTIL_PROG subvolume create $temp_mnt/sv1 &> /dev/null
+ _unmount $temp_mnt
+ rm -r -f $temp_mnt
+
+ $BTRFS_TUNE_PROG -m ${devs[0]}
+}
+
+print_info()
+{
+ local mntpt=$1
+ local tgt=$(findmnt -no SOURCE $mntpt)
+ local fsuuid=$(blkid -s UUID -o value $tgt)
+
+ echo "mntpt=$mntpt tgt=$tgt fsuuid=$fsuuid" >> $seqres.full
+ echo
+ findmnt -o SOURCE,TARGET,UUID "$tgt" | tail -n +2 | \
+ sed -e "s/${fsuuid}/FSUUID/g" | filter_pool
+ awk -v dev="$tgt" '$1 == dev { print $1, $2 }' /proc/self/mounts | \
+ filter_pool
+ df --all --output=source,target "$tgt" | tail -n +2 | filter_pool
+}
+
+devs=()
+_loop_image_create_clone devs pre_clone_tune
+mkdir -p $TEST_DIR/$seq
+mnt1=$TEST_DIR/$seq/mnt1
+mnt2=$TEST_DIR/$seq/mnt2
+mkdir -p $mnt1
+mkdir -p $mnt2
+
+_mount $(_common_dev_mount_options) $(_clone_mount_option) ${devs[0]} $mnt1 || \
+ _fail "Failed to mount dev1"
+_mount $(_common_dev_mount_options) $(_clone_mount_option) ${devs[1]} $mnt2 || \
+ _fail "Failed to mount dev2"
+
+print_info $mnt1
+print_info $mnt2
+
+echo
+echo "**** mount cycle ****"
+_unmount $mnt1
+_unmount $mnt2
+_mount $(_common_dev_mount_options) $(_clone_mount_option) ${devs[1]} $mnt2 || \
+ _fail "Failed to mount dev2"
+_mount $(_common_dev_mount_options) $(_clone_mount_option) ${devs[0]} $mnt1 || \
+ _fail "Failed to mount dev1"
+
+print_info $mnt1
+print_info $mnt2
+
+status=0
+exit
diff --git a/tests/btrfs/348.out b/tests/btrfs/348.out
new file mode 100644
index 000000000000..4b102e986246
--- /dev/null
+++ b/tests/btrfs/348.out
@@ -0,0 +1,19 @@
+QA output created by 348
+
+DEV1 MNT1 FSUUID
+DEV1 MNT1
+DEV1 MNT1
+
+DEV2 MNT2 FSUUID
+DEV2 MNT2
+DEV2 MNT2
+
+**** mount cycle ****
+
+DEV1 MNT1 FSUUID
+DEV1 MNT1
+DEV1 MNT1
+
+DEV2 MNT2 FSUUID
+DEV2 MNT2
+DEV2 MNT2
--
2.43.0
^ permalink raw reply related
* [PATCH v4 8/9] fstests: verify exportfs file handles on cloned filesystems
From: Anand Jain @ 2026-04-28 6:42 UTC (permalink / raw)
To: fstests
Cc: linux-btrfs, linux-ext4, linux-xfs, linux-f2fs, amir73il, zlang,
hch
In-Reply-To: <cover.1777357320.git.asj@kernel.org>
Ensure that exportfs can correctly decode file handles on a cloned
filesystem across a mount cycle, by file handles generated on a
cloned device remain valid after mount cycle.
Signed-off-by: Anand Jain <asj@kernel.org>
---
tests/generic/805 | 73 +++++++++++++++++++++++++++++++++++++++++++
tests/generic/805.out | 2 ++
2 files changed, 75 insertions(+)
create mode 100644 tests/generic/805
create mode 100644 tests/generic/805.out
diff --git a/tests/generic/805 b/tests/generic/805
new file mode 100644
index 000000000000..98e7172e141f
--- /dev/null
+++ b/tests/generic/805
@@ -0,0 +1,73 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2026 Anand Jain <asj@kernel.org>. All Rights Reserved.
+#
+# FS QA Test No. 805
+
+. ./common/preamble
+
+_begin_fstest auto quick exportfs clone
+
+_require_test
+_require_block_device $TEST_DEV
+_require_exportfs
+_require_loop
+_require_test_program "open_by_handle"
+
+_cleanup()
+{
+ cd /
+ rm -r -f $tmp.*
+ _unmount $mnt1 2>/dev/null
+ _unmount $mnt2 2>/dev/null
+ _loop_image_destroy "${devs[@]}" 2> /dev/null
+}
+
+# Create test dir and test files, encode file handles and store to tmp file
+create_test_files()
+{
+ rm -rf $testdir
+ mkdir -p $testdir
+ $here/src/open_by_handle -cwp -o $tmp.handles_file $testdir $NUMFILES
+}
+
+# Decode file handles loaded from tmp file
+test_file_handles()
+{
+ local opt=$1
+ local when=$2
+
+ echo test_file_handles after $when
+ $here/src/open_by_handle $opt -i $tmp.handles_file $mnt2 $NUMFILES
+}
+
+devs=()
+_loop_image_create_clone devs
+mkdir -p $TEST_DIR/$seq
+mnt1=$TEST_DIR/$seq/mnt1
+mnt2=$TEST_DIR/$seq/mnt2
+mkdir -p $mnt1
+mkdir -p $mnt2
+
+_mount $(_common_dev_mount_options) $(_clone_mount_option) ${devs[0]} $mnt1 || \
+ _fail "Failed to mount dev1"
+_mount $(_common_dev_mount_options) $(_clone_mount_option) ${devs[1]} $mnt2 || \
+ _fail "Failed to mount dev2"
+
+NUMFILES=1
+testdir=$mnt2/testdir
+
+# Decode file handles of files/dir after cycle mount
+create_test_files
+
+_unmount $mnt1
+_unmount $mnt2
+_mount $(_common_dev_mount_options) $(_clone_mount_option) ${devs[1]} $mnt2 || \
+ _fail "Failed to mount dev2"
+_mount $(_common_dev_mount_options) $(_clone_mount_option) ${devs[0]} $mnt1 || \
+ _fail "Failed to mount dev1"
+
+test_file_handles -rp "cycle mount"
+
+status=0
+exit
diff --git a/tests/generic/805.out b/tests/generic/805.out
new file mode 100644
index 000000000000..29b11ec77ffb
--- /dev/null
+++ b/tests/generic/805.out
@@ -0,0 +1,2 @@
+QA output created by 805
+test_file_handles after cycle mount
--
2.43.0
^ permalink raw reply related
* [PATCH v4 7/9] fstests: verify IMA isolation on cloned filesystems
From: Anand Jain @ 2026-04-28 6:42 UTC (permalink / raw)
To: fstests
Cc: linux-btrfs, linux-ext4, linux-xfs, linux-f2fs, amir73il, zlang,
hch
In-Reply-To: <cover.1777357320.git.asj@kernel.org>
Add testcase to verify IMA measurement isolation when multiple devices
share the same FSUUID.
Signed-off-by: Anand Jain <asj@kernel.org>
---
tests/generic/804 | 103 ++++++++++++++++++++++++++++++++++++++++++
tests/generic/804.out | 10 ++++
2 files changed, 113 insertions(+)
create mode 100644 tests/generic/804
create mode 100644 tests/generic/804.out
diff --git a/tests/generic/804 b/tests/generic/804
new file mode 100644
index 000000000000..9f3459015422
--- /dev/null
+++ b/tests/generic/804
@@ -0,0 +1,103 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2026 Anand Jain <asj@kernel.org>. All Rights Reserved.
+#
+# FS QA Test 804
+# Verify IMA isolation on cloned filesystems:
+# . Mount two devices sharing the same FSUUID (cloned).
+# . Apply an IMA policy to measure files based on that FSUUID.
+# . Create unique files on each mount point to trigger measurements.
+# . Confirm the IMA log correctly attributes events to the respective mounts.
+
+. ./common/preamble
+. ./common/filter
+
+_begin_fstest auto quick clone
+
+_require_test
+_require_block_device $TEST_DEV
+_require_loop
+
+[ "$FSTYP" = "btrfs" ] && _fixed_by_kernel_commit xxxxxxxxxxxx \
+ "btrfs: use on-disk uuid for s_uuid in temp_fsid mounts"
+[ "$FSTYP" = "btrfs" ] && _fixed_by_kernel_commit xxxxxxxxxxxx \
+ "btrfs: derive f_fsid from on-disk fsuuid and dev_t"
+
+_cleanup()
+{
+ cd /
+ rm -r -f $tmp.*
+ _unmount $mnt1 2>/dev/null
+ _unmount $mnt2 2>/dev/null
+ _loop_image_destroy "${devs[@]}" 2> /dev/null
+}
+
+filter_pool()
+{
+ sed -e "s|${devs[0]}|DEV1|g" -e "s|$mnt1|MNT1|g" \
+ -e "s|${devs[1]}|DEV2|g" -e "s|$mnt2|MNT2|g" | _filter_spaces
+}
+
+do_ima()
+{
+ local ima_policy="/sys/kernel/security/ima/policy"
+ local ima_log="/sys/kernel/security/ima/ascii_runtime_measurements"
+ local fsuuid
+ local mnt=$1
+ local enable=$2
+
+ # Since the in-memory IMA audit log is only cleared upon reboot,
+ # use unique random filenames to avoid log collisions.
+ local foofile=$(mktemp --dry-run foobar_XXXXX)
+
+ echo $mnt $enable | filter_pool
+
+ [ -w "$ima_policy" ] || _notrun "IMA policy not writable"
+
+ fsuuid=$(blkid -s UUID -o value ${devs[0]})
+
+ # Load IMA policy to measure file access specifically for this
+ # filesystem UUID.
+ if [[ $enable -eq 1 ]]; then
+ echo "measure func=FILE_CHECK fsuuid=$fsuuid" > "$ima_policy" || \
+ _notrun "Policy rejected"
+ fi
+
+ # Create a file to trigger measurement and verify its entry in
+ # the IMA log.
+ echo "test_data" > $mnt/$foofile
+
+ # For $ima_log column entry please ref to
+ grep $foofile "$ima_log" | awk '{ print $5 }' | filter_pool | \
+ sed "s/$foofile/FOOBAR_FILE/"
+
+ echo "dbg: $mnt $fsuuid $foofile" >> $seqres.full
+ cat $ima_log | tail -1 >> $seqres.full
+ echo >> $seqres.full
+}
+
+devs=()
+_loop_image_create_clone devs
+mnt1=$TEST_DIR/$seq/mnt1
+mnt2=$TEST_DIR/$seq/mnt2
+mkdir -p $mnt1
+mkdir -p $mnt2
+
+_mount $(_common_dev_mount_options) $(_clone_mount_option) ${devs[0]} $mnt1 || \
+ _fail "Failed to mount dev1"
+_mount $(_common_dev_mount_options) $(_clone_mount_option) ${devs[1]} $mnt2 || \
+ _fail "Failed to mount dev2"
+
+do_ima $mnt1 1
+do_ima $mnt2 0
+
+# Btrfs uses in-memory dynamic temp_fsid
+echo mount cycle
+_unmount $mnt2
+_mount $mount_opts ${devs[1]} $mnt2 || _fail "Failed to mount dev2"
+
+do_ima $mnt1 0
+do_ima $mnt2 0
+
+status=0
+exit
diff --git a/tests/generic/804.out b/tests/generic/804.out
new file mode 100644
index 000000000000..9804181d6c17
--- /dev/null
+++ b/tests/generic/804.out
@@ -0,0 +1,10 @@
+QA output created by 804
+MNT1 1
+MNT1/FOOBAR_FILE
+MNT2 0
+MNT2/FOOBAR_FILE
+mount cycle
+MNT1 0
+MNT1/FOOBAR_FILE
+MNT2 0
+MNT2/FOOBAR_FILE
--
2.43.0
^ permalink raw reply related
* [PATCH v4 6/9] fstests: verify libblkid resolution of duplicate UUIDs
From: Anand Jain @ 2026-04-28 6:42 UTC (permalink / raw)
To: fstests
Cc: linux-btrfs, linux-ext4, linux-xfs, linux-f2fs, amir73il, zlang,
hch
In-Reply-To: <cover.1777357320.git.asj@kernel.org>
Verify how findmnt, df (libblkid) resolve device paths when multiple
block devices share the same FSUUID.
Signed-off-by: Anand Jain <asj@kernel.org>
---
tests/generic/803 | 76 +++++++++++++++++++++++++++++++++++++++++++
tests/generic/803.out | 19 +++++++++++
2 files changed, 95 insertions(+)
create mode 100644 tests/generic/803
create mode 100644 tests/generic/803.out
diff --git a/tests/generic/803 b/tests/generic/803
new file mode 100644
index 000000000000..36de7887065e
--- /dev/null
+++ b/tests/generic/803
@@ -0,0 +1,76 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2026 Anand Jain <asj@kernel.org>. All Rights Reserved.
+#
+# FS QA Test 803
+# Verify how libblkid resolve devices when multiple devices sharing the
+# same FSUUID.
+
+. ./common/preamble
+. ./common/filter
+
+_begin_fstest auto quick mount clone
+
+_require_test
+_require_block_device $TEST_DEV
+_require_loop
+
+_cleanup()
+{
+ cd /
+ rm -r -f $tmp.*
+ umount $mnt1 $mnt2 2>/dev/null
+ _loop_image_destroy "${devs[@]}" 2> /dev/null
+}
+
+filter_pool()
+{
+ sed -e "s|${devs[0]}|DEV1|g" -e "s|${mnt1}|MNT1|g" \
+ -e "s|${devs[1]}|DEV2|g" -e "s|${mnt2}|MNT2|g" | _filter_spaces
+}
+
+print_info()
+{
+ local mntpt=$1
+ local tgt=$(findmnt -no SOURCE $mntpt)
+ local fsuuid=$(blkid -s UUID -o value $tgt)
+
+ echo "mntpt=$mntpt tgt=$tgt fsuuid=$fsuuid" >> $seqres.full
+ echo
+ findmnt -o SOURCE,TARGET,UUID "$tgt" | tail -n +2 | \
+ sed -e "s/${fsuuid}/FSUUID/g" | filter_pool
+ awk -v dev="$tgt" '$1 == dev { print $1, $2 }' /proc/self/mounts | \
+ filter_pool
+ df --all --output=source,target "$tgt" | tail -n +2 | filter_pool
+}
+
+devs=()
+_loop_image_create_clone devs
+mkdir -p $TEST_DIR/$seq
+mnt1=$TEST_DIR/$seq/mnt1
+mnt2=$TEST_DIR/$seq/mnt2
+mkdir -p $mnt1
+mkdir -p $mnt2
+
+_mount $(_common_dev_mount_options) $(_clone_mount_option) ${devs[0]} $mnt1 || \
+ _fail "Failed to mount dev1"
+_mount $(_common_dev_mount_options) $(_clone_mount_option) ${devs[1]} $mnt2 || \
+ _fail "Failed to mount dev2"
+
+print_info $mnt1
+print_info $mnt2
+
+echo
+echo "**** mount cycle ****"
+_unmount $mnt1
+_unmount $mnt2
+_mount $(_common_dev_mount_options) $(_clone_mount_option) ${devs[1]} $mnt2 || \
+ _fail "Failed to mount dev2"
+_mount $(_common_dev_mount_options) $(_clone_mount_option) ${devs[0]} $mnt1 || \
+ _fail "Failed to mount dev1"
+
+print_info $mnt1
+print_info $mnt2
+
+status=0
+exit
diff --git a/tests/generic/803.out b/tests/generic/803.out
new file mode 100644
index 000000000000..20a1cb36a213
--- /dev/null
+++ b/tests/generic/803.out
@@ -0,0 +1,19 @@
+QA output created by 803
+
+DEV1 MNT1 FSUUID
+DEV1 MNT1
+DEV1 MNT1
+
+DEV2 MNT2 FSUUID
+DEV2 MNT2
+DEV2 MNT2
+
+**** mount cycle ****
+
+DEV1 MNT1 FSUUID
+DEV1 MNT1
+DEV1 MNT1
+
+DEV2 MNT2 FSUUID
+DEV2 MNT2
+DEV2 MNT2
--
2.43.0
^ permalink raw reply related
* [PATCH v4 5/9] fstests: verify f_fsid for cloned filesystems
From: Anand Jain @ 2026-04-28 6:42 UTC (permalink / raw)
To: fstests
Cc: linux-btrfs, linux-ext4, linux-xfs, linux-f2fs, amir73il, zlang,
hch
In-Reply-To: <cover.1777357320.git.asj@kernel.org>
Verify that the cloned filesystem provides an f_fsid that is persistent
across mount cycles, yet unique from the original filesystem's f_fsid.
Signed-off-by: Anand Jain <asj@kernel.org>
---
tests/generic/802 | 62 +++++++++++++++++++++++++++++++++++++++++++
tests/generic/802.out | 7 +++++
2 files changed, 69 insertions(+)
create mode 100644 tests/generic/802
create mode 100644 tests/generic/802.out
diff --git a/tests/generic/802 b/tests/generic/802
new file mode 100644
index 000000000000..31044695f3a8
--- /dev/null
+++ b/tests/generic/802
@@ -0,0 +1,62 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2026 Anand Jain <asj@kernel.org>. All Rights Reserved.
+#
+# FS QA Test 802
+# Verify f_fsid and s_uuid of cloned filesystems across mount cycle.
+
+. ./common/preamble
+
+_begin_fstest auto quick mount clone
+
+_require_test
+_require_block_device $TEST_DEV
+_require_loop
+
+[ "$FSTYP" = "btrfs" ] && _fixed_by_kernel_commit xxxxxxxxxxxx \
+ "btrfs: use on-disk uuid for s_uuid in temp_fsid mounts"
+[ "$FSTYP" = "btrfs" ] && _fixed_by_kernel_commit xxxxxxxxxxxx \
+ "btrfs: derive f_fsid from on-disk fsuuid and dev_t"
+
+_cleanup()
+{
+ cd /
+ rm -r -f $tmp.*
+ umount $mnt1 $mnt2 2>/dev/null
+ _loop_image_destroy "${devs[@]}" 2> /dev/null
+}
+
+devs=()
+_loop_image_create_clone devs
+mkdir -p $TEST_DIR/$seq
+mnt1=$TEST_DIR/$seq/mnt1
+mnt2=$TEST_DIR/$seq/mnt2
+mkdir -p $mnt1
+mkdir -p $mnt2
+
+_mount $(_common_dev_mount_options) $(_clone_mount_option) ${devs[0]} $mnt1 || \
+ _fail "Failed to mount dev1"
+_mount $(_common_dev_mount_options) $(_clone_mount_option) ${devs[1]} $mnt2 || \
+ _fail "Failed to mount dev2"
+
+fsid_scratch=$(stat -f -c "%i" $mnt1)
+fsid_clone=$(stat -f -c "%i" $mnt2)
+
+echo "**** fsid initially ****"
+echo $fsid_scratch | sed -e "s/$fsid_scratch/FSID_SCRATCH/g"
+echo $fsid_clone | sed -e "s/$fsid_clone/FSID_CLONE/g"
+
+# Make sure fsid still match across a mount cycle, also reverse the order.
+echo "**** fsid after mount cycle ****"
+_unmount $mnt1
+_unmount $mnt2
+_mount $(_common_dev_mount_options) $(_clone_mount_option) ${devs[1]} $mnt2 || \
+ _fail "Failed to mount dev2"
+_mount $(_common_dev_mount_options) $(_clone_mount_option) ${devs[0]} $mnt1 || \
+ _fail "Failed to mount dev1"
+
+stat -f -c "%i" $mnt1 | sed -e "s/$fsid_scratch/FSID_SCRATCH/g"
+stat -f -c "%i" $mnt2 | sed -e "s/$fsid_clone/FSID_CLONE/g"
+
+status=0
+exit
diff --git a/tests/generic/802.out b/tests/generic/802.out
new file mode 100644
index 000000000000..d1e008f122bb
--- /dev/null
+++ b/tests/generic/802.out
@@ -0,0 +1,7 @@
+QA output created by 802
+**** fsid initially ****
+FSID_SCRATCH
+FSID_CLONE
+**** fsid after mount cycle ****
+FSID_SCRATCH
+FSID_CLONE
--
2.43.0
^ permalink raw reply related
* [PATCH v4 4/9] fstests: verify fanotify isolation on cloned filesystems
From: Anand Jain @ 2026-04-28 6:42 UTC (permalink / raw)
To: fstests
Cc: linux-btrfs, linux-ext4, linux-xfs, linux-f2fs, amir73il, zlang,
hch
In-Reply-To: <cover.1777357320.git.asj@kernel.org>
Verify that fanotify events are correctly routed to the appropriate
watcher when cloned filesystems are mounted.
Helps verify kernel's event notification distinguishes between devices
sharing the same FSID/UUID.
Signed-off-by: Anand Jain <asj@kernel.org>
---
common/config | 1 +
tests/generic/801 | 113 ++++++++++++++++++++++++++++++++++++++++++
tests/generic/801.out | 7 +++
3 files changed, 121 insertions(+)
create mode 100644 tests/generic/801
create mode 100644 tests/generic/801.out
diff --git a/common/config b/common/config
index 605a57947a40..1588bdcb1aa1 100644
--- a/common/config
+++ b/common/config
@@ -243,6 +243,7 @@ export PARTED_PROG="$(type -P parted)"
export XFS_PROPERTY_PROG="$(type -P xfs_property)"
export FSCRYPTCTL_PROG="$(type -P fscryptctl)"
export INOTIFYWAIT_PROG="$(type -P inotifywait)"
+export FSNOTIFYWAIT_PROG="$(type -P fsnotifywait)"
# udev wait functions.
#
diff --git a/tests/generic/801 b/tests/generic/801
new file mode 100644
index 000000000000..e1282f4e3d71
--- /dev/null
+++ b/tests/generic/801
@@ -0,0 +1,113 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2026 Anand Jain <asj@kernel.org>. All Rights Reserved.
+#
+# FS QA Test 801
+# Verify fanotify FID functionality on cloned filesystems by setting up
+# watchers and making sure notifications are in the correct logs files.
+
+. ./common/preamble
+
+_begin_fstest auto quick mount clone
+
+_require_test
+_require_block_device $TEST_DEV
+_require_loop
+_require_command "$FSNOTIFYWAIT_PROG" fsnotifywait
+
+_cleanup()
+{
+ cd /
+ [[ -n $pid1 ]] && { kill -TERM "$pid1" 2> /dev/null; wait $pid1; }
+ [[ -n $pid2 ]] && { kill -TERM "$pid2" 2> /dev/null; wait $pid2; }
+ umount $mnt1 $mnt2 2>/dev/null
+ _loop_image_destroy "${devs[@]}" 2> /dev/null
+ rm -r -f $tmp.*
+}
+
+monitor_fanotify()
+{
+ local mmnt=$1
+ exec stdbuf -oL $FSNOTIFYWAIT_PROG -m -F -S -e create "$mmnt" 2>&1
+}
+
+fsid_to_fid_parts()
+{
+ local fsid=$1
+ # Pad to 16 hex chars (64-bit), then split into two 32-bit halves
+ local padded=$(printf '%016x' "0x${fsid}")
+ local hi=$(printf '%x' "0x${padded:0:8}") # strips leading zeros
+ local lo=$(printf '%x' "0x${padded:8:8}") # strips leading zeros
+ echo "${hi}.${lo}"
+}
+
+devs=()
+_loop_image_create_clone devs
+mkdir -p $TEST_DIR/$seq
+mnt1=$TEST_DIR/$seq/mnt1
+mnt2=$TEST_DIR/$seq/mnt2
+mkdir -p $mnt1
+mkdir -p $mnt2
+
+_mount $(_common_dev_mount_options) $(_clone_mount_option) ${devs[0]} $mnt1 || \
+ _fail "Failed to mount dev1"
+_mount $(_common_dev_mount_options) $(_clone_mount_option) ${devs[1]} $mnt2 || \
+ _fail "Failed to mount dev2"
+
+fsid1=$(stat -f -c "%i" $mnt1)
+fsid2=$(stat -f -c "%i" $mnt2)
+
+[[ "$fsid1" == "$fsid2" ]] && \
+ _notrun "Require clone filesystem with unique f_fsid"
+
+log1=$tmp.fanotify1
+log2=$tmp.fanotify2
+
+pid1=""
+pid2=""
+echo "Setup FID fanotify watchers on both mnt1 and mnt2"
+( monitor_fanotify "$mnt1" > "$log1" ) &
+pid1=$!
+( monitor_fanotify "$mnt2" > "$log2" ) &
+pid2=$!
+sleep 2
+
+echo "Trigger file creation on mnt1"
+touch $mnt1/file_on_mnt1
+sync
+sleep 1
+
+echo "Trigger file creation on mnt2"
+touch $mnt2/file_on_mnt2
+sync
+sleep 1
+
+echo "Verify fsid in the fanotify"
+kill $pid1 $pid2
+wait $pid1 $pid2 2>/dev/null
+pid1=""
+pid2=""
+
+e_fsid1=$(fsid_to_fid_parts "$fsid1")
+e_fsid2=$(fsid_to_fid_parts "$fsid2")
+
+echo $fsid1 $e_fsid1 $fsid2 $e_fsid2 >> $seqres.full
+cat $log1 >> $seqres.full
+cat $log2 >> $seqres.full
+
+if grep -qF "$e_fsid1" "$log1" && ! grep -qF "$e_fsid2" "$log1"; then
+ echo "SUCCESS: mnt1 events found"
+else
+ [ ! -s "$log1" ] && echo " - mnt1 received no events."
+ grep -qF "$e_fsid2" "$log1" && echo " - mnt1 received event from mnt2."
+fi
+
+if grep -qF "$e_fsid2" "$log2" && ! grep -qF "$e_fsid1" "$log2"; then
+ echo "SUCCESS: mnt2 events found"
+else
+ [ ! -s "$log2" ] && echo " - mnt2 received no events."
+ grep -qF "$e_fsid1" "$log2" && echo " - mnt2 received event from mnt1."
+fi
+
+status=0
+exit
diff --git a/tests/generic/801.out b/tests/generic/801.out
new file mode 100644
index 000000000000..d7b318d9f27c
--- /dev/null
+++ b/tests/generic/801.out
@@ -0,0 +1,7 @@
+QA output created by 801
+Setup FID fanotify watchers on both mnt1 and mnt2
+Trigger file creation on mnt1
+Trigger file creation on mnt2
+Verify fsid in the fanotify
+SUCCESS: mnt1 events found
+SUCCESS: mnt2 events found
--
2.43.0
^ permalink raw reply related
* [PATCH v4 3/9] fstests: add test for inotify isolation on cloned devices
From: Anand Jain @ 2026-04-28 6:42 UTC (permalink / raw)
To: fstests
Cc: linux-btrfs, linux-ext4, linux-xfs, linux-f2fs, amir73il, zlang,
hch
In-Reply-To: <cover.1777357320.git.asj@kernel.org>
Add a new test, to verify that the kernel correctly differentiates between
two block devices sharing the same FSID/UUID.
Signed-off-by: Anand Jain <asj@kernel.org>
---
common/config | 1 +
tests/generic/800 | 89 +++++++++++++++++++++++++++++++++++++++++++
tests/generic/800.out | 7 ++++
3 files changed, 97 insertions(+)
create mode 100644 tests/generic/800
create mode 100644 tests/generic/800.out
diff --git a/common/config b/common/config
index 4fd4c2c8af11..605a57947a40 100644
--- a/common/config
+++ b/common/config
@@ -242,6 +242,7 @@ export BTRFS_MAP_LOGICAL_PROG=$(type -P btrfs-map-logical)
export PARTED_PROG="$(type -P parted)"
export XFS_PROPERTY_PROG="$(type -P xfs_property)"
export FSCRYPTCTL_PROG="$(type -P fscryptctl)"
+export INOTIFYWAIT_PROG="$(type -P inotifywait)"
# udev wait functions.
#
diff --git a/tests/generic/800 b/tests/generic/800
new file mode 100644
index 000000000000..4b9bd3e4f487
--- /dev/null
+++ b/tests/generic/800
@@ -0,0 +1,89 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2026 Anand Jain <asj@kernel.org>. All Rights Reserved.
+#
+# FS QA Test 800
+#
+# Verify if the kernel or userspace becomes confused when two block devices
+# share the same fid/fsid/uuid. Create inotify on both original and cloned
+# filesystem. Monitor the notification in the respective logs.
+
+. ./common/preamble
+
+_begin_fstest auto quick mount clone
+
+_require_test
+_require_block_device $TEST_DEV
+_require_loop
+_require_command "$INOTIFYWAIT_PROG" inotifywait
+
+_cleanup()
+{
+ cd /
+ [[ -n $pid1 ]] && { kill -TERM "$pid1" 2> /dev/null; wait $pid1; }
+ [[ -n $pid2 ]] && { kill -TERM "$pid2" 2> /dev/null; wait $pid2; }
+ rm -r -f $tmp.*
+ _unmount $mnt1 2>/dev/null
+ _unmount $mnt2 2>/dev/null
+ _loop_image_destroy "${devs[@]}" 2> /dev/null
+}
+
+devs=()
+_loop_image_create_clone devs
+mkdir -p $TEST_DIR/$seq
+mnt1=$TEST_DIR/$seq/mnt1
+mnt2=$TEST_DIR/$seq/mnt2
+mkdir -p $mnt1
+mkdir -p $mnt2
+
+_mount $(_common_dev_mount_options) $(_clone_mount_option) ${devs[0]} $mnt1 || \
+ _fail "Failed to mount dev1"
+_mount $(_common_dev_mount_options) $(_clone_mount_option) ${devs[1]} $mnt2 || \
+ _fail "Failed to mount dev2"
+
+log1=$tmp.inotify1
+log2=$tmp.inotify2
+
+pid1=""
+pid2=""
+echo "Setup inotify watchers on both mnt1 and mnt2"
+$INOTIFYWAIT_PROG -m -e create --format '%f' $mnt1 > $log1 2>&1 &
+pid1=$!
+$INOTIFYWAIT_PROG -m -e create --format '%f' $mnt2 > $log2 2>&1 &
+pid2=$!
+sleep 2
+
+echo "Trigger file creation on mnt1"
+touch $mnt1/file_on_mnt1
+sync
+sleep 1
+
+echo "Trigger file creation on mnt2"
+touch $mnt2/file_on_mnt2
+sync
+sleep 1
+
+echo "Verify inotify isolation"
+kill $pid1 $pid2
+wait $pid1 $pid2 2>/dev/null
+pid1=""
+pid2=""
+
+if grep -q "file_on_mnt1" $log1 && ! grep -q "file_on_mnt2" $log1; then
+ echo "SUCCESS: mnt1 events isolated."
+else
+ echo "FAIL: mnt1 inotify confusion!"
+ [ ! -s $log1 ] && echo " - mnt1 received no events."
+ grep -q "file_on_mnt2" $log1 && echo " - mnt1 received event from mnt2."
+fi
+
+if grep -q "file_on_mnt2" $log2 && ! grep -q "file_on_mnt1" $log2; then
+ echo "SUCCESS: mnt2 events isolated."
+else
+ echo "FAIL: mnt2 inotify confusion!"
+ [ ! -s $log2 ] && echo " - mnt2 received no events."
+ grep -q "file_on_mnt1" $log2 && echo " - mnt2 received event from mnt1."
+fi
+
+status=0
+exit
diff --git a/tests/generic/800.out b/tests/generic/800.out
new file mode 100644
index 000000000000..b10842a31210
--- /dev/null
+++ b/tests/generic/800.out
@@ -0,0 +1,7 @@
+QA output created by 800
+Setup inotify watchers on both mnt1 and mnt2
+Trigger file creation on mnt1
+Trigger file creation on mnt2
+Verify inotify isolation
+SUCCESS: mnt1 events isolated.
+SUCCESS: mnt2 events isolated.
--
2.43.0
^ permalink raw reply related
* [PATCH v4 2/9] fstests: add _clone_mount_option() helper
From: Anand Jain @ 2026-04-28 6:42 UTC (permalink / raw)
To: fstests
Cc: linux-btrfs, linux-ext4, linux-xfs, linux-f2fs, amir73il, zlang,
hch
In-Reply-To: <cover.1777357320.git.asj@kernel.org>
Adds _clone_mount_option() helper function to handle filesystem-specific
requirements for mounting cloned devices. Abstract the need for -o nouuid
on XFS.
Signed-off-by: Anand Jain <asj@kernel.org>
---
common/rc | 14 ++++++++++++++
1 file changed, 14 insertions(+)
diff --git a/common/rc b/common/rc
index 754365e80dca..771472d2f8c7 100644
--- a/common/rc
+++ b/common/rc
@@ -397,6 +397,20 @@ _scratch_mount_options()
$SCRATCH_DEV $SCRATCH_MNT
}
+_clone_mount_option()
+{
+ local mount_opts=""
+
+ case "$FSTYP" in
+ xfs)
+ mount_opts="-o nouuid"
+ ;;
+ *)
+ esac
+
+ echo $mount_opts
+}
+
_supports_filetype()
{
local dir=$1
--
2.43.0
^ permalink raw reply related
* [PATCH v4 1/9] fstests: add _loop_image_create_clone() helper
From: Anand Jain @ 2026-04-28 6:42 UTC (permalink / raw)
To: fstests
Cc: linux-btrfs, linux-ext4, linux-xfs, linux-f2fs, amir73il, zlang,
hch
In-Reply-To: <cover.1777357320.git.asj@kernel.org>
Introduce _loop_image_create_clone() and _loop_image_destroy() to mkfs an
image file and clone it to another image file, and attach a loop device to
them. And its destroy part.
Signed-off-by: Anand Jain <asj@kernel.org>
---
common/rc | 47 +++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 47 insertions(+)
diff --git a/common/rc b/common/rc
index 9632b211b58f..754365e80dca 100644
--- a/common/rc
+++ b/common/rc
@@ -1503,6 +1503,53 @@ _scratch_resvblks()
esac
}
+_loop_image_create_clone()
+{
+ local -n _ret=$1
+ local pre_clone_tune_func=$2
+ local img_file=$TEST_DIR/${seq}.img
+ local img_file_clone=$TEST_DIR/${seq}_clone.img
+ local size=$(_small_fs_size_mb 128) # Smallest possible
+ local loop_devs
+
+ _require_fs_space $TEST_DIR $((size * 1024))
+
+ _create_file_sized $((size * 1024 * 1024)) $img_file ||
+ _fail "Failed: Create $img_file $size"
+
+ loop_devs=$(_create_loop_device $img_file)
+ _ret=($loop_devs)
+
+ case $FSTYP in
+ xfs)
+ _mkfs_dev "-s size=4096" ${loop_devs[0]}
+ ;;
+ btrfs)
+ _mkfs_dev ${loop_devs[0]}
+ ;;
+ *)
+ _mkfs_dev ${loop_devs[0]}
+ ;;
+ esac
+
+ ($pre_clone_tune_func)
+
+ sync ${loop_devs[0]}
+ cp $img_file $img_file_clone
+
+ loop_devs="$loop_devs $(_create_loop_device $img_file_clone)"
+
+ _ret=($loop_devs)
+}
+
+_loop_image_destroy()
+{
+ for d in "$@"; do
+ local f=$(losetup --noheadings --output BACK-FILE $d)
+ _destroy_loop_device "$d"
+ [ -n "$f" ] && rm -f "$f"
+ done
+}
# 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 related
* [PATCH v4 0/9] fstests: add test coverage for cloned filesystem ids
From: Anand Jain @ 2026-04-28 6:42 UTC (permalink / raw)
To: fstests
Cc: linux-btrfs, linux-ext4, linux-xfs, linux-f2fs, amir73il, zlang,
hch
v4:
In _loop_image_create_clone() (Patch 1/9):
. Added _require_fs_space $TEST_DIR $((size * 1024)).
. Switched to the _create_file_sized() helper.
. Used the loop device in mkfs instead of the image file directly.
. Added a sync on the loop device before copying to ensure consistency.
For test cases (Patches 3/9 to 9/9):
. Added _require_block_device $TEST_DEV.
For test case (Patch 4/9):
. Removed the ext4 patch reference in _fixed_by_kernel_commit since
that part of the plan was dropped.
v3:
https://lore.kernel.org/fstests/cover.1777281778.git.asj@kernel.org
Anand Jain (9):
fstests: add _loop_image_create_clone() helper
fstests: add _clone_mount_option() helper
fstests: add test for inotify isolation on cloned devices
fstests: verify fanotify isolation on cloned filesystems
fstests: verify f_fsid for cloned filesystems
fstests: verify libblkid resolution of duplicate UUIDs
fstests: verify IMA isolation on cloned filesystems
fstests: verify exportfs file handles on cloned filesystems
fstests: btrfs: test UUID consistency for clones with metadata_uuid
common/config | 2 +
common/rc | 61 +++++++++++++++++++++++
tests/btrfs/348 | 92 ++++++++++++++++++++++++++++++++++
tests/btrfs/348.out | 19 +++++++
tests/generic/800 | 89 +++++++++++++++++++++++++++++++++
tests/generic/800.out | 7 +++
tests/generic/801 | 113 ++++++++++++++++++++++++++++++++++++++++++
tests/generic/801.out | 7 +++
tests/generic/802 | 62 +++++++++++++++++++++++
tests/generic/802.out | 7 +++
tests/generic/803 | 76 ++++++++++++++++++++++++++++
tests/generic/803.out | 19 +++++++
tests/generic/804 | 103 ++++++++++++++++++++++++++++++++++++++
tests/generic/804.out | 10 ++++
tests/generic/805 | 73 +++++++++++++++++++++++++++
tests/generic/805.out | 2 +
16 files changed, 742 insertions(+)
create mode 100644 tests/btrfs/348
create mode 100644 tests/btrfs/348.out
create mode 100644 tests/generic/800
create mode 100644 tests/generic/800.out
create mode 100644 tests/generic/801
create mode 100644 tests/generic/801.out
create mode 100644 tests/generic/802
create mode 100644 tests/generic/802.out
create mode 100644 tests/generic/803
create mode 100644 tests/generic/803.out
create mode 100644 tests/generic/804
create mode 100644 tests/generic/804.out
create mode 100644 tests/generic/805
create mode 100644 tests/generic/805.out
--
2.43.0
^ permalink raw reply
* Re: [PATCH v3 1/9] fstests: add _loop_image_create_clone() helper
From: Anand Jain @ 2026-04-28 6:42 UTC (permalink / raw)
To: Amir Goldstein, Anand Jain
Cc: fstests, linux-btrfs, linux-ext4, linux-xfs, linux-f2fs, zlang,
hch
In-Reply-To: <CAOQ4uxjEcHiqzB+JrnzDExMcBuTbLaPT5qQcEDX0GO0TX7hp=g@mail.gmail.com>
On 28/4/26 02:31, Amir Goldstein wrote:
> On Mon, Apr 27, 2026 at 12:19 PM Anand Jain <asj@kernel.org> wrote:
>>
>> Introduce _loop_image_create_clone() and _loop_image_destroy() to mkfs an
>> image file and clone it to another image file, and attach a loop device to
>> them. And its destroy part.
>>
>> Signed-off-by: Anand Jain <asj@kernel.org>
>> ---
>> common/rc | 44 ++++++++++++++++++++++++++++++++++++++++++++
>> 1 file changed, 44 insertions(+)
>>
>> diff --git a/common/rc b/common/rc
>> index 9632b211b58f..0e7b7eb1d98f 100644
>> --- a/common/rc
>> +++ b/common/rc
>> @@ -1503,6 +1503,50 @@ _scratch_resvblks()
>> esac
>> }
>>
>> +_loop_image_create_clone()
>> +{
>> + local -n _ret=$1
>> + local pre_clone_tune_func=$2
>> + local img_file=$TEST_DIR/${seq}.img
>> + local img_file_clone=$TEST_DIR/${seq}_clone.img
>> + local size=$(_small_fs_size_mb 128) # Smallest possible
>> + local loop_devs
>> +
>> + size=$((size * 1024 * 1024))
>> + $XFS_IO_PROG -f -c "truncate $size" $img_file
>> +
>> + loop_devs=$(_create_loop_device $img_file)
>> + _ret=($loop_devs)
>> +
>> + case $FSTYP in
>> + xfs)
>> + _mkfs_dev "-s size=4096" $img_file
>> + ;;
>> + btrfs)
>> + _mkfs_dev $img_file
>> + ;;
>> + *)
>> + _mkfs_dev $img_file
>
> You making a wrong assumption that FSTYP can format the loop devices
>
> You should add _require_block_device $SCRATCH_DEV
> to all your tests or maybe nicer, add:
>
> _require_loop_mountable which requires loop and block dev fs
> and use this requirement instead of just _require_loop in all tests.
>
Thanks. I've fixed this in v4 by adding
_require_block_device $TEST_DEV
Since SCRATCH_DEV is not required.
I didn't create a new _require_loop_mountable() helper.
Both _require_loop() and _require_block_device() are
used both together across other existing tests;
I prefer not to deviate into cleaning that up in this
patch set.
v4 is in the ML for rvb.
Thanks, Anand
> Thanks,
> Amir.
^ permalink raw reply
* Re: [PATCH v11 08/15] xfs: Report case sensitivity in fileattr_get
From: Chuck Lever @ 2026-04-28 1:32 UTC (permalink / raw)
To: Darrick J. Wong
Cc: Alexander Viro, Christian Brauner, Jan Kara, linux-fsdevel,
linux-ext4, linux-xfs, linux-cifs, linux-nfs, linux-api,
linux-f2fs-devel, OGAWA Hirofumi, Namjae Jeon, Sungjong Seo,
Yuezhang Mo, almaz.alexandrovich, Viacheslav Dubeyko,
John Paul Adrian Glaubitz, frank.li, Theodore Tso, adilger.kernel,
Carlos Maiolino, Steve French, Paulo Alcantara, Ronnie Sahlberg,
Shyam Prasad N, Trond Myklebust, Anna Schumaker, Jaegeuk Kim,
Chao Yu, Hans de Goede, senozhatsky, Chuck Lever, Roland Mainz
In-Reply-To: <20260427155636.GC7751@frogsfrogsfrogs>
On Mon, Apr 27, 2026, at 11:56 AM, Darrick J. Wong wrote:
> On Fri, Apr 24, 2026 at 09:53:10PM -0400, Chuck Lever wrote:
>> From: Chuck Lever <chuck.lever@oracle.com>
>>
>> Upper layers such as NFSD need to query whether a filesystem
>> is case-sensitive. Add FS_XFLAG_CASEFOLD to xfs_ip2xflags()
>> when the filesystem is formatted with the ASCIICI feature
>> flag. This serves both FS_IOC_FSGETXATTR (via xfs_fill_fsxattr() in
>> xfs_fileattr_get()) and XFS_IOC_BULKSTAT (which populates bs_xflags
>> directly from xfs_ip2xflags()), so bulkstat consumers and per-inode
>> queries see a consistent view of the filesystem's case-folding
>> behavior.
>>
>> XFS always preserves case. XFS is case-sensitive by default, but
>> supports ASCII case-insensitive lookups when formatted with the
>> ASCIICI feature flag.
>>
>> Reviewed-by: Roland Mainz <roland.mainz@nrubsig.org>
>> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
>> ---
> I don't understand this at all. Yes, FS_XFLAG_CASEFOLD is readonly,
> but how does clearing FS_CASEFOLD_FL from the fileattr_get output
> (without clearing XFLAG_CASEFOLD!) solve anything? This makes the
> reported output inconsistent between fsgetxattr and getflags -- one
> reports case folding, the other reports no casefolding.
The masking is a misplaced reaction to a sashiko review on the
v9 predecessor of this patch [1], which pointed out that v9 set
FS_XFLAG_CASEFOLD in fa->fsx_xflags after xfs_fill_fsxattr() had
already synced fa->flags, leaving the two views inconsistent in
the other direction, and that bulkstat would miss the flag for
the same reason. Moving the injection into xfs_ip2xflags() fixed
both gaps -- but it also surfaced FS_CASEFOLD_FL on the legacy
view, so chattr's RMW through FS_IOC_SETFLAGS hits the EOPNOTSUPP
gate at the top of xfs_fileattr_set(). Hiding it from getflags
was the wrong place to address that.
> If you want to avoid fileattr_set returning EINVAL when setting
> attributes due to the casefold flag, then don't you want to check
> the flag state vs. xfs_has_asciici() in the *fileattr_set* path?
Yep. For v12 I’ll drop the fa->flags mask and add FS_CASEFOLD_FL
to the allowlist in xfs_fileattr_set(), gated on xfs_has_asciici(mp).
xfs_flags2diflags() already has no clause for CASEFOLD, so the
FSSETXATTR path silently no-ops it the same way it does for
FS_XFLAG_HASATTR, and FS_XFLAG_CASEFOLD is in FS_XFLAG_RDONLY_MASK
so FSSETXATTR strips it centrally. Both views then agree, and a
chattr round-trip is accepted as a no-op.
The hfsplus patch in this series carries the same pattern --
FS_XFLAG_CASEFOLD is set after fileattr_fill_flags() so that
FS_CASEFOLD_FL stays out of fa->flags and dodges the EOPNOTSUPP
gate in hfsplus_fileattr_set(). I will fix it the same way.
Thanks for the catch!
[1] https://sashiko.dev/#/patchset/20260422-case-sensitivity-v9-0-be023cc070e2@oracle.com?part=9
--
Chuck Lever
^ permalink raw reply
* Re: [PATCH] ext4: avoid __GFP_NOFAIL in __ext4_get_inode_loc allocation
From: Theodore Tso @ 2026-04-28 1:28 UTC (permalink / raw)
To: Chao Shi
Cc: linux-ext4, adilger.kernel, jack, Sungwoo Kim, Dave Tian,
Weidong Zhu
In-Reply-To: <20260427222300.1284855-1-coshi036@gmail.com>
On Mon, Apr 27, 2026 at 06:23:00PM -0400, Chao Shi wrote:
> When kswapd shrinks the dcache, the last iput() on an ext4 inode can
> trigger ext4_orphan_del(), which calls ext4_reserve_inode_write() and
> ultimately __ext4_get_inode_loc(). That function calls sb_getblk(),
> which wraps __getblk() and carries implicit __GFP_NOFAIL. Because
> kswapd runs with PF_MEMALLOC set, combining NOFAIL with a non-reclaimable
> context trips WARN_ON_ONCE(current->flags & PF_MEMALLOC) inside
> __alloc_pages_slowpath(), producing a spurious splat even though the
> allocation could simply fail and return -ENOMEM to the caller.
NAK. As Sashiko correctly points out:
Sashiko AI review found 1 potential issue(s):
- [Critical] Removing __GFP_NOFAIL from __ext4_get_inode_loc causes transient memory
shortages to trigger a fatal filesystem abort (remount read-only) or severe metadata
corruption, trading a memory reclaim warning for a Denial of Service.
The warning in mm/page_alloc.c is the sort of thing that causes file
system developers to decide to drop __GFP_NOFAIL and replace it with a
retry loop just to shut the mm subsystem the heck up, since some mm
developers seem to view hangs in heavy OOM conditions as the worst
thing, where as fs developers consider data corruption to be far
worse, since users tend to get cranky when they lose their data, and
(a) in practice the OOM killer tends to get triggered first, and (b)
that's what software and hardware watchdogs are for.
In any case, there are *far* worse things than a random splat, and if
you really want to make it go away, my suggestion is to remove the
WARN_ON_ONCE from __alloc_pages_slowpath().
/*
* PF_MEMALLOC request from this context is rather bizarre
* because we cannot reclaim anything and only can loop waiting
* for somebody to do a work for us.
*/
WARN_ON_ONCE(current->flags & PF_MEMALLOC);
I disagrr the premise; it's not bizzare at all.
- Ted
^ permalink raw reply
* [PATCH] ext4: avoid __GFP_NOFAIL in __ext4_get_inode_loc allocation
From: Chao Shi @ 2026-04-27 22:23 UTC (permalink / raw)
To: linux-ext4
Cc: tytso, adilger.kernel, jack, Chao Shi, Sungwoo Kim, Dave Tian,
Weidong Zhu
When kswapd shrinks the dcache, the last iput() on an ext4 inode can
trigger ext4_orphan_del(), which calls ext4_reserve_inode_write() and
ultimately __ext4_get_inode_loc(). That function calls sb_getblk(),
which wraps __getblk() and carries implicit __GFP_NOFAIL. Because
kswapd runs with PF_MEMALLOC set, combining NOFAIL with a non-reclaimable
context trips WARN_ON_ONCE(current->flags & PF_MEMALLOC) inside
__alloc_pages_slowpath(), producing a spurious splat even though the
allocation could simply fail and return -ENOMEM to the caller.
Switch both sb_getblk() call sites in __ext4_get_inode_loc() to
sb_getblk_gfp() with the same flags minus __GFP_NOFAIL
(mapping_gfp_constraint(~__GFP_FS) | __GFP_MOVABLE), computing the gfp
value once and reusing it for the optional bitmap_bh optimisation fetch.
All callers of __ext4_get_inode_loc() -- reached via ext4_get_inode_loc(),
__ext4_get_inode_loc_noinmem(), and ext4_get_fc_inode_loc() -- already
propagate a non-zero return as an error without aborting the filesystem.
Both sb_getblk() call sites in __ext4_get_inode_loc() are converted; the
bitmap_bh fetch already falls back to make_io on NULL, so allowing it to
fail is a no-op there.
Reproduced under syzkaller+FEMU based fuzz tool (FuzzNvme) on x86_64 QEMU,
based on mainline 894009e2ef10:
WARNING: CPU: 0 PID: 55 at mm/page_alloc.c:4722
__alloc_pages_slowpath
Comm: kswapd0 Not tainted 6.19.0+ #14
Call Trace:
__alloc_pages_slowpath
alloc_pages_mpol
folio_alloc_noprof
filemap_alloc_folio_noprof
__filemap_get_folio
grow_dev_folio
grow_buffers
__getblk_slow
bdev_getblk
__ext4_get_inode_loc
ext4_get_inode_loc
ext4_reserve_inode_write
ext4_orphan_del
ext4_evict_inode
evict
iput
dentry_unlink_inode
__dentry_kill
shrink_dentry_list
prune_dcache_sb
super_cache_scan
do_shrink_slab
shrink_slab
shrink_node
balance_pgdat
kswapd
kthread
ret_from_fork
Related: see d8b90e6387a ("ext4: add ext4_sb_bread_nofail() helper
function for ext4_free_branches()") for the same strategy applied to
the read path in ext4_free_branches().
Link: https://lore.kernel.org/all/?q=PF_MEMALLOC+nofail+ext4+iput
Acked-by: Sungwoo Kim <iam@sung-woo.kim>
Acked-by: Dave Tian <daveti@purdue.edu>
Acked-by: Weidong Zhu <weizhu@fiu.edu>
Signed-off-by: Chao Shi <coshi036@gmail.com>
---
fs/ext4/inode.c | 12 ++++++++++--
1 file changed, 10 insertions(+), 2 deletions(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index c2c2d6ac7f3..1b2a7bd59b8 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4859,6 +4859,7 @@ static int __ext4_get_inode_loc(struct super_block *sb, unsigned long ino,
ext4_fsblk_t block;
struct blk_plug plug;
int inodes_per_block, inode_offset;
+ gfp_t gfp;
iloc->bh = NULL;
if (ino < EXT4_ROOT_INO ||
@@ -4887,7 +4888,14 @@ static int __ext4_get_inode_loc(struct super_block *sb, unsigned long ino,
}
block += (inode_offset / inodes_per_block);
- bh = sb_getblk(sb, block);
+ /*
+ * No __GFP_NOFAIL: this can run from reclaim context (kswapd
+ * shrinker -> iput -> ext4_orphan_del path) where NOFAIL trips
+ * WARN_ON_ONCE in __alloc_pages_slowpath().
+ */
+ gfp = mapping_gfp_constraint(sb->s_bdev->bd_mapping, ~__GFP_FS) |
+ __GFP_MOVABLE;
+ bh = sb_getblk_gfp(sb, block, gfp);
if (unlikely(!bh))
return -ENOMEM;
if (ext4_buffer_uptodate(bh))
@@ -4912,7 +4920,7 @@ static int __ext4_get_inode_loc(struct super_block *sb, unsigned long ino,
start = inode_offset & ~(inodes_per_block - 1);
/* Is the inode bitmap in cache? */
- bitmap_bh = sb_getblk(sb, ext4_inode_bitmap(sb, gdp));
+ bitmap_bh = sb_getblk_gfp(sb, ext4_inode_bitmap(sb, gdp), gfp);
if (unlikely(!bitmap_bh))
goto make_io;
--
2.43.0
^ permalink raw reply related
* Re: [PATCH v3 4/9] fstests: verify fanotify isolation on cloned filesystems
From: Amir Goldstein @ 2026-04-27 18:32 UTC (permalink / raw)
To: Anand Jain
Cc: fstests, linux-btrfs, linux-ext4, linux-xfs, linux-f2fs, zlang,
hch
In-Reply-To: <4777ecd14815b92c9e8577ed4d073d0f999e51ef.1777281778.git.asj@kernel.org>
On Mon, Apr 27, 2026 at 12:20 PM Anand Jain <asj@kernel.org> wrote:
>
> Verify that fanotify events are correctly routed to the appropriate
> watcher when cloned filesystems are mounted.
> Helps verify kernel's event notification distinguishes between devices
> sharing the same FSID/UUID.
>
> Signed-off-by: Anand Jain <asj@kernel.org>
> ---
> common/config | 1 +
> tests/generic/801 | 115 ++++++++++++++++++++++++++++++++++++++++++
> tests/generic/801.out | 7 +++
> 3 files changed, 123 insertions(+)
> create mode 100644 tests/generic/801
> create mode 100644 tests/generic/801.out
>
> diff --git a/common/config b/common/config
> index 605a57947a40..1588bdcb1aa1 100644
> --- a/common/config
> +++ b/common/config
> @@ -243,6 +243,7 @@ export PARTED_PROG="$(type -P parted)"
> export XFS_PROPERTY_PROG="$(type -P xfs_property)"
> export FSCRYPTCTL_PROG="$(type -P fscryptctl)"
> export INOTIFYWAIT_PROG="$(type -P inotifywait)"
> +export FSNOTIFYWAIT_PROG="$(type -P fsnotifywait)"
>
> # udev wait functions.
> #
> diff --git a/tests/generic/801 b/tests/generic/801
> new file mode 100644
> index 000000000000..3f64e4de2206
> --- /dev/null
> +++ b/tests/generic/801
> @@ -0,0 +1,115 @@
> +#! /bin/bash
> +# SPDX-License-Identifier: GPL-2.0
> +# Copyright (c) 2026 Anand Jain <asj@kernel.org>. All Rights Reserved.
> +#
> +# FS QA Test 801
> +# Verify fanotify FID functionality on cloned filesystems by setting up
> +# watchers and making sure notifications are in the correct logs files.
> +
> +. ./common/preamble
> +
> +_begin_fstest auto quick mount clone
> +
> +_require_test
> +_require_loop
insufficient check for mounting a blockdev fs
> +_require_command "$FSNOTIFYWAIT_PROG" fsnotifywait
> +
> +[ "$FSTYP" = "ext4" ] && _fixed_by_kernel_commit xxxxxxxxxxxx \
Fix before merging
Other than that it looks ok.
Thanks,
Amir.
> + "ext4: derive f_fsid from block device to avoid collisions"
> +
> +_cleanup()
> +{
> + cd /
> + [[ -n $pid1 ]] && { kill -TERM "$pid1" 2> /dev/null; wait $pid1; }
> + [[ -n $pid2 ]] && { kill -TERM "$pid2" 2> /dev/null; wait $pid2; }
> + umount $mnt1 $mnt2 2>/dev/null
> + _loop_image_destroy "${devs[@]}" 2> /dev/null
> + rm -r -f $tmp.*
> +}
> +
> +monitor_fanotify()
> +{
> + local mmnt=$1
> + exec stdbuf -oL $FSNOTIFYWAIT_PROG -m -F -S -e create "$mmnt" 2>&1
> +}
> +
> +fsid_to_fid_parts()
> +{
> + local fsid=$1
> + # Pad to 16 hex chars (64-bit), then split into two 32-bit halves
> + local padded=$(printf '%016x' "0x${fsid}")
> + local hi=$(printf '%x' "0x${padded:0:8}") # strips leading zeros
> + local lo=$(printf '%x' "0x${padded:8:8}") # strips leading zeros
> + echo "${hi}.${lo}"
> +}
> +
> +devs=()
> +_loop_image_create_clone devs
> +mkdir -p $TEST_DIR/$seq
> +mnt1=$TEST_DIR/$seq/mnt1
> +mnt2=$TEST_DIR/$seq/mnt2
> +mkdir -p $mnt1
> +mkdir -p $mnt2
> +
> +_mount $(_common_dev_mount_options) $(_clone_mount_option) ${devs[0]} $mnt1 || \
> + _fail "Failed to mount dev1"
> +_mount $(_common_dev_mount_options) $(_clone_mount_option) ${devs[1]} $mnt2 || \
> + _fail "Failed to mount dev2"
> +
> +fsid1=$(stat -f -c "%i" $mnt1)
> +fsid2=$(stat -f -c "%i" $mnt2)
> +
> +[[ "$fsid1" == "$fsid2" ]] && \
> + _notrun "Require clone filesystem with unique f_fsid"
> +
> +log1=$tmp.fanotify1
> +log2=$tmp.fanotify2
> +
> +pid1=""
> +pid2=""
> +echo "Setup FID fanotify watchers on both mnt1 and mnt2"
> +( monitor_fanotify "$mnt1" > "$log1" ) &
> +pid1=$!
> +( monitor_fanotify "$mnt2" > "$log2" ) &
> +pid2=$!
> +sleep 2
> +
> +echo "Trigger file creation on mnt1"
> +touch $mnt1/file_on_mnt1
> +sync
> +sleep 1
> +
> +echo "Trigger file creation on mnt2"
> +touch $mnt2/file_on_mnt2
> +sync
> +sleep 1
> +
> +echo "Verify fsid in the fanotify"
> +kill $pid1 $pid2
> +wait $pid1 $pid2 2>/dev/null
> +pid1=""
> +pid2=""
> +
> +e_fsid1=$(fsid_to_fid_parts "$fsid1")
> +e_fsid2=$(fsid_to_fid_parts "$fsid2")
> +
> +echo $fsid1 $e_fsid1 $fsid2 $e_fsid2 >> $seqres.full
> +cat $log1 >> $seqres.full
> +cat $log2 >> $seqres.full
> +
> +if grep -qF "$e_fsid1" "$log1" && ! grep -qF "$e_fsid2" "$log1"; then
> + echo "SUCCESS: mnt1 events found"
> +else
> + [ ! -s "$log1" ] && echo " - mnt1 received no events."
> + grep -qF "$e_fsid2" "$log1" && echo " - mnt1 received event from mnt2."
> +fi
> +
> +if grep -qF "$e_fsid2" "$log2" && ! grep -qF "$e_fsid1" "$log2"; then
> + echo "SUCCESS: mnt2 events found"
> +else
> + [ ! -s "$log2" ] && echo " - mnt2 received no events."
> + grep -qF "$e_fsid1" "$log2" && echo " - mnt2 received event from mnt1."
> +fi
> +
> +status=0
> +exit
> diff --git a/tests/generic/801.out b/tests/generic/801.out
> new file mode 100644
> index 000000000000..d7b318d9f27c
> --- /dev/null
> +++ b/tests/generic/801.out
> @@ -0,0 +1,7 @@
> +QA output created by 801
> +Setup FID fanotify watchers on both mnt1 and mnt2
> +Trigger file creation on mnt1
> +Trigger file creation on mnt2
> +Verify fsid in the fanotify
> +SUCCESS: mnt1 events found
> +SUCCESS: mnt2 events found
> --
> 2.43.0
>
^ permalink raw reply
* Re: [PATCH v3 1/9] fstests: add _loop_image_create_clone() helper
From: Amir Goldstein @ 2026-04-27 18:31 UTC (permalink / raw)
To: Anand Jain
Cc: fstests, linux-btrfs, linux-ext4, linux-xfs, linux-f2fs, zlang,
hch
In-Reply-To: <05ace38b54ea49f462bcd6274c4a2528192e6949.1777281778.git.asj@kernel.org>
On Mon, Apr 27, 2026 at 12:19 PM Anand Jain <asj@kernel.org> wrote:
>
> Introduce _loop_image_create_clone() and _loop_image_destroy() to mkfs an
> image file and clone it to another image file, and attach a loop device to
> them. And its destroy part.
>
> Signed-off-by: Anand Jain <asj@kernel.org>
> ---
> common/rc | 44 ++++++++++++++++++++++++++++++++++++++++++++
> 1 file changed, 44 insertions(+)
>
> diff --git a/common/rc b/common/rc
> index 9632b211b58f..0e7b7eb1d98f 100644
> --- a/common/rc
> +++ b/common/rc
> @@ -1503,6 +1503,50 @@ _scratch_resvblks()
> esac
> }
>
> +_loop_image_create_clone()
> +{
> + local -n _ret=$1
> + local pre_clone_tune_func=$2
> + local img_file=$TEST_DIR/${seq}.img
> + local img_file_clone=$TEST_DIR/${seq}_clone.img
> + local size=$(_small_fs_size_mb 128) # Smallest possible
> + local loop_devs
> +
> + size=$((size * 1024 * 1024))
> + $XFS_IO_PROG -f -c "truncate $size" $img_file
> +
> + loop_devs=$(_create_loop_device $img_file)
> + _ret=($loop_devs)
> +
> + case $FSTYP in
> + xfs)
> + _mkfs_dev "-s size=4096" $img_file
> + ;;
> + btrfs)
> + _mkfs_dev $img_file
> + ;;
> + *)
> + _mkfs_dev $img_file
You making a wrong assumption that FSTYP can format the loop devices
You should add _require_block_device $SCRATCH_DEV
to all your tests or maybe nicer, add:
_require_loop_mountable which requires loop and block dev fs
and use this requirement instead of just _require_loop in all tests.
Thanks,
Amir.
^ permalink raw reply
* Re: [PATCH v3 3/9] fstests: add test for inotify isolation on cloned devices
From: Amir Goldstein @ 2026-04-27 17:15 UTC (permalink / raw)
To: Anand Jain
Cc: fstests, linux-btrfs, linux-ext4, linux-xfs, linux-f2fs, zlang,
hch
In-Reply-To: <d5bff7b1c8f17cffb13c8a8f28bd8ad645306e09.1777281778.git.asj@kernel.org>
On Mon, Apr 27, 2026 at 12:20 PM Anand Jain <asj@kernel.org> wrote:
>
> Add a new test, to verify that the kernel correctly differentiates between
> two block devices sharing the same FSID/UUID.
>
> Signed-off-by: Anand Jain <asj@kernel.org>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
> ---
> common/config | 1 +
> tests/generic/800 | 88 +++++++++++++++++++++++++++++++++++++++++++
> tests/generic/800.out | 7 ++++
> 3 files changed, 96 insertions(+)
> create mode 100644 tests/generic/800
> create mode 100644 tests/generic/800.out
>
> diff --git a/common/config b/common/config
> index 4fd4c2c8af11..605a57947a40 100644
> --- a/common/config
> +++ b/common/config
> @@ -242,6 +242,7 @@ export BTRFS_MAP_LOGICAL_PROG=$(type -P btrfs-map-logical)
> export PARTED_PROG="$(type -P parted)"
> export XFS_PROPERTY_PROG="$(type -P xfs_property)"
> export FSCRYPTCTL_PROG="$(type -P fscryptctl)"
> +export INOTIFYWAIT_PROG="$(type -P inotifywait)"
>
> # udev wait functions.
> #
> diff --git a/tests/generic/800 b/tests/generic/800
> new file mode 100644
> index 000000000000..16bc1159a2e1
> --- /dev/null
> +++ b/tests/generic/800
> @@ -0,0 +1,88 @@
> +#! /bin/bash
> +# SPDX-License-Identifier: GPL-2.0
> +# Copyright (c) 2026 Anand Jain <asj@kernel.org>. All Rights Reserved.
> +#
> +# FS QA Test 800
> +#
> +# Verify if the kernel or userspace becomes confused when two block devices
> +# share the same fid/fsid/uuid. Create inotify on both original and cloned
> +# filesystem. Monitor the notification in the respective logs.
> +
> +. ./common/preamble
> +
> +_begin_fstest auto quick mount clone
> +
> +_require_test
> +_require_loop
> +_require_command "$INOTIFYWAIT_PROG" inotifywait
> +
> +_cleanup()
> +{
> + cd /
> + [[ -n $pid1 ]] && { kill -TERM "$pid1" 2> /dev/null; wait $pid1; }
> + [[ -n $pid2 ]] && { kill -TERM "$pid2" 2> /dev/null; wait $pid2; }
> + rm -r -f $tmp.*
> + _unmount $mnt1 2>/dev/null
> + _unmount $mnt2 2>/dev/null
> + _loop_image_destroy "${devs[@]}" 2> /dev/null
> +}
> +
> +devs=()
> +_loop_image_create_clone devs
> +mkdir -p $TEST_DIR/$seq
> +mnt1=$TEST_DIR/$seq/mnt1
> +mnt2=$TEST_DIR/$seq/mnt2
> +mkdir -p $mnt1
> +mkdir -p $mnt2
> +
> +_mount $(_common_dev_mount_options) $(_clone_mount_option) ${devs[0]} $mnt1 || \
> + _fail "Failed to mount dev1"
> +_mount $(_common_dev_mount_options) $(_clone_mount_option) ${devs[1]} $mnt2 || \
> + _fail "Failed to mount dev2"
> +
> +log1=$tmp.inotify1
> +log2=$tmp.inotify2
> +
> +pid1=""
> +pid2=""
> +echo "Setup inotify watchers on both mnt1 and mnt2"
> +$INOTIFYWAIT_PROG -m -e create --format '%f' $mnt1 > $log1 2>&1 &
> +pid1=$!
> +$INOTIFYWAIT_PROG -m -e create --format '%f' $mnt2 > $log2 2>&1 &
> +pid2=$!
> +sleep 2
> +
> +echo "Trigger file creation on mnt1"
> +touch $mnt1/file_on_mnt1
> +sync
> +sleep 1
> +
> +echo "Trigger file creation on mnt2"
> +touch $mnt2/file_on_mnt2
> +sync
> +sleep 1
> +
> +echo "Verify inotify isolation"
> +kill $pid1 $pid2
> +wait $pid1 $pid2 2>/dev/null
> +pid1=""
> +pid2=""
> +
> +if grep -q "file_on_mnt1" $log1 && ! grep -q "file_on_mnt2" $log1; then
> + echo "SUCCESS: mnt1 events isolated."
> +else
> + echo "FAIL: mnt1 inotify confusion!"
> + [ ! -s $log1 ] && echo " - mnt1 received no events."
> + grep -q "file_on_mnt2" $log1 && echo " - mnt1 received event from mnt2."
> +fi
> +
> +if grep -q "file_on_mnt2" $log2 && ! grep -q "file_on_mnt1" $log2; then
> + echo "SUCCESS: mnt2 events isolated."
> +else
> + echo "FAIL: mnt2 inotify confusion!"
> + [ ! -s $log2 ] && echo " - mnt2 received no events."
> + grep -q "file_on_mnt1" $log2 && echo " - mnt2 received event from mnt1."
> +fi
> +
> +status=0
> +exit
> diff --git a/tests/generic/800.out b/tests/generic/800.out
> new file mode 100644
> index 000000000000..b10842a31210
> --- /dev/null
> +++ b/tests/generic/800.out
> @@ -0,0 +1,7 @@
> +QA output created by 800
> +Setup inotify watchers on both mnt1 and mnt2
> +Trigger file creation on mnt1
> +Trigger file creation on mnt2
> +Verify inotify isolation
> +SUCCESS: mnt1 events isolated.
> +SUCCESS: mnt2 events isolated.
> --
> 2.43.0
>
^ permalink raw reply
* [PATCH] ext4: avoid BUG_ON() in ext4_get_inline_entry()
From: Vineet Agarwal @ 2026-04-27 16:20 UTC (permalink / raw)
To: linux-ext4, linux-kernel
Cc: tytso, adilger.kernel, libaokun1, jack, ojaswin, ritesh.list,
yi.zhang, Vineet Agarwal
Corrupted inline directory metadata can cause offset to exceed
the inline data size through rec_len processing in
empty_inline_dir().
This triggers BUG_ON() in ext4_get_inline_entry(), causing a
kernel panic before ext4_check_dir_entry() can handle the
corruption gracefully.
Replace BUG_ON() with a NULL return and handle the invalid
offset in the caller by emitting a warning and exiting safely.
This prevents a kernel panic from corrupted inline directory
metadata.
Signed-off-by: Vineet Agarwal <agarwal.vineet2006@gmail.com>
---
fs/ext4/inline.c | 9 ++++++++-
1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 8045e4ff270c..bca9936ed6d0 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -1718,7 +1718,8 @@ ext4_get_inline_entry(struct inode *inode,
{
void *inline_pos;
- BUG_ON(offset > ext4_get_inline_size(inode));
+ if (offset > ext4_get_inline_size(inode))
+ return NULL;
if (offset < EXT4_MIN_INLINE_DATA_SIZE) {
inline_pos = (void *)ext4_raw_inode(iloc)->i_block;
@@ -1773,6 +1774,12 @@ bool empty_inline_dir(struct inode *dir, int *has_inline_data)
while (offset < inline_len) {
de = ext4_get_inline_entry(dir, &iloc, offset,
&inline_pos, &inline_size);
+ if (!de) {
+ ext4_warning(dir->i_sb,
+ "bad inline directory (dir #%llu) - invalid offset",
+ dir->i_ino);
+ goto out;
+ }
if (ext4_check_dir_entry(dir, NULL, de,
iloc.bh, inline_pos,
inline_size, offset)) {
--
2.54.0
^ permalink raw reply related
* Re: [PATCH v11 08/15] xfs: Report case sensitivity in fileattr_get
From: Darrick J. Wong @ 2026-04-27 15:56 UTC (permalink / raw)
To: Chuck Lever
Cc: Al Viro, Christian Brauner, Jan Kara, linux-fsdevel, linux-ext4,
linux-xfs, linux-cifs, linux-nfs, linux-api, linux-f2fs-devel,
hirofumi, linkinjeon, sj1557.seo, yuezhang.mo,
almaz.alexandrovich, slava, glaubitz, frank.li, tytso,
adilger.kernel, cem, sfrench, pc, ronniesahlberg, sprasad,
trondmy, anna, jaegeuk, chao, hansg, senozhatsky, Chuck Lever,
Roland Mainz
In-Reply-To: <20260424-case-sensitivity-v11-8-de5619beddaf@oracle.com>
On Fri, Apr 24, 2026 at 09:53:10PM -0400, Chuck Lever wrote:
> From: Chuck Lever <chuck.lever@oracle.com>
>
> Upper layers such as NFSD need to query whether a filesystem
> is case-sensitive. Add FS_XFLAG_CASEFOLD to xfs_ip2xflags()
> when the filesystem is formatted with the ASCIICI feature
> flag. This serves both FS_IOC_FSGETXATTR (via xfs_fill_fsxattr() in
> xfs_fileattr_get()) and XFS_IOC_BULKSTAT (which populates bs_xflags
> directly from xfs_ip2xflags()), so bulkstat consumers and per-inode
> queries see a consistent view of the filesystem's case-folding
> behavior.
>
> XFS always preserves case. XFS is case-sensitive by default, but
> supports ASCII case-insensitive lookups when formatted with the
> ASCIICI feature flag.
>
> Reviewed-by: Roland Mainz <roland.mainz@nrubsig.org>
> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
> ---
> fs/xfs/libxfs/xfs_inode_util.c | 2 ++
> fs/xfs/xfs_ioctl.c | 7 +++++++
> 2 files changed, 9 insertions(+)
>
> diff --git a/fs/xfs/libxfs/xfs_inode_util.c b/fs/xfs/libxfs/xfs_inode_util.c
> index 551fa51befb6..82be54b6f8d3 100644
> --- a/fs/xfs/libxfs/xfs_inode_util.c
> +++ b/fs/xfs/libxfs/xfs_inode_util.c
> @@ -130,6 +130,8 @@ xfs_ip2xflags(
>
> if (xfs_inode_has_attr_fork(ip))
> flags |= FS_XFLAG_HASATTR;
> + if (xfs_has_asciici(ip->i_mount))
> + flags |= FS_XFLAG_CASEFOLD;
> return flags;
> }
>
> diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
> index ed9b4846c05f..5a58fb0bad2b 100644
> --- a/fs/xfs/xfs_ioctl.c
> +++ b/fs/xfs/xfs_ioctl.c
> @@ -472,6 +472,13 @@ xfs_fill_fsxattr(
>
> fileattr_fill_xflags(fa, xfs_ip2xflags(ip));
>
> + /*
> + * FS_XFLAG_CASEFOLD is read-only; hide it from the legacy
> + * flags view so chattr's RMW cycle does not pass it back to
> + * xfs_fileattr_set().
> + */
> + fa->flags &= ~FS_CASEFOLD_FL;
I don't understand this at all. Yes, FS_XFLAG_CASEFOLD is readonly, but
how does clearing FS_CASEFOLD_FL from the fileattr_get output (without
clearing XFLAG_CASEFOLD!) solve anything? This makes the reported
output inconsistent between fsgetxattr and getflags -- one reports case
folding, the other reports no casefolding.
If you want to avoid fileattr_set returning EINVAL when setting
attributes due to the casefold flag, then don't you want to check the
flag state vs. xfs_has_asciici() in the *fileattr_set* path?
--D
> +
> if (ip->i_diflags & XFS_DIFLAG_EXTSIZE) {
> fa->fsx_extsize = XFS_FSB_TO_B(mp, ip->i_extsize);
> } else if (ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) {
>
> --
> 2.53.0
>
>
^ 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