From: Dave Chinner <dgc@kernel.org>
To: linux-xfs@vger.kernel.org
Cc: cem@kernel.org
Subject: [PATCH 20/59] xfs: validate operation header length and alignment during recovery
Date: Tue, 17 Nov 2026 10:14:37 +1100 [thread overview]
Message-ID: <20261116231707.3625263-21-dgc@kernel.org> (raw)
In-Reply-To: <20261116231707.3625263-1-dgc@kernel.org>
The operation header length read from the journal was only checked against
the end of the log record, so an implausibly large or misaligned length was
still trusted to drive region assembly and memory allocation.
Bound the length against the largest object that can be logged in a single
region and require it to be 32 bit aligned. Move the in-place ophdr decode
into the validation helper as well, so a misaligned or out-of-bounds header
is rejected before it is dereferenced rather than after.
Assisted-by: LLM
Signed-off-by: Dave Chinner <dgc@kernel.org>
---
fs/xfs/xfs_log_recover.c | 115 +++++++++++++++++++++++++++------------
1 file changed, 81 insertions(+), 34 deletions(-)
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index a5fa7d2676cd..472e0093d589 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -2652,24 +2652,69 @@ xlog_recover_ophdr_to_trans(
}
/*
- * Validate an operation header decoded from the journal before it is used to
- * drive transaction recovery. The ophdr and its data region come straight from
- * the on-disk log and cannot be trusted, so check the fields for known values
- * and obvious corruption here, in one place, before anything acts on them.
+ * Decode and validate an operation header from the journal. dp points at the
+ * ophdr within the log record and end is the end of the record data. The ophdr
+ * and its data region come straight from the on-disk log and cannot be trusted,
+ * so decode the header in place and check its fields for known values and
+ * obvious corruption here, in one place, before anything acts on them.
+ *
+ * Returns the validated ophdr, or an ERR_PTR() on corruption.
*/
-STATIC int
+STATIC struct xlog_op_header *
xlog_recover_validate_ophdr(
struct xlog *log,
- struct xlog_op_header *ohead,
char *dp,
char *end)
{
- unsigned int len = be32_to_cpu(ohead->oh_len);
+ struct xlog_op_header *ohead;
+ unsigned int len;
+
+ /*
+ * All log regions are 32 bit aligned, so the ophdr must be too. A
+ * misaligned ophdr means the walk over the record has lost sync with
+ * the on-disk layout.
+ */
+ if (dp != PTR_ALIGN(dp, sizeof(uint32_t))) {
+ xfs_warn(log->l_mp, "%s: unaligned op header", __func__);
+ return ERR_PTR(-EFSCORRUPTED);
+ }
+
+ /* The ophdr itself must fit within the record. */
+ if (dp + sizeof(*ohead) > end) {
+ xfs_warn(log->l_mp, "%s: op header overrun", __func__);
+ return ERR_PTR(-EFSCORRUPTED);
+ }
+
+ ohead = (struct xlog_op_header *)dp;
+ dp += sizeof(*ohead);
+ len = be32_to_cpu(ohead->oh_len);
/* Check the ophdr contains all the data it is supposed to contain. */
if (dp + len > end) {
xfs_warn(log->l_mp, "%s: bad length 0x%x", __func__, len);
- return -EFSCORRUPTED;
+ return ERR_PTR(-EFSCORRUPTED);
+ }
+
+ /*
+ * All log regions are 32 bit aligned, so the length must be too. A
+ * misaligned length desyncs the walk over the ophdrs in the record.
+ */
+ if (!IS_ALIGNED(len, sizeof(uint32_t))) {
+ xfs_warn(log->l_mp, "%s: unaligned length 0x%x", __func__, len);
+ return ERR_PTR(-EFSCORRUPTED);
+ }
+
+ /*
+ * A single region cannot be larger than the largest object we log in
+ * one region. That is a whole buffer in a buffer log item (up to
+ * XFS_MAX_BLOCKSIZE, e.g. a 64k directory block on a 4k block size
+ * filesystem) or a remote attribute value (up to XFS_XATTR_SIZE_MAX,
+ * logged in its own region); both are 64k.
+ */
+ BUILD_BUG_ON(XFS_XATTR_SIZE_MAX > XFS_MAX_BLOCKSIZE);
+ if (len > XFS_MAX_BLOCKSIZE) {
+ xfs_warn(log->l_mp, "%s: length 0x%x too large", __func__, len);
+ return ERR_PTR(-EFSCORRUPTED);
}
/* Do we understand who wrote this op? */
@@ -2677,10 +2722,10 @@ xlog_recover_validate_ophdr(
ohead->oh_clientid != XFS_LOG) {
xfs_warn(log->l_mp, "%s: bad clientid 0x%x",
__func__, ohead->oh_clientid);
- return -EFSCORRUPTED;
+ return ERR_PTR(-EFSCORRUPTED);
}
- return 0;
+ return ohead;
}
STATIC int
@@ -2688,24 +2733,28 @@ xlog_recover_process_ophdr(
struct xlog *log,
struct hlist_head rhash[],
struct xlog_rec_header *rhead,
- struct xlog_op_header *ohead,
char *dp,
char *end,
int pass,
struct list_head *buffer_list)
{
+ struct xlog_op_header *ohead;
struct xlog_recover *trans;
- unsigned int len = be32_to_cpu(ohead->oh_len);
+ unsigned int len;
int error;
- error = xlog_recover_validate_ophdr(log, ohead, dp, end);
- if (error)
- return error;
+ ohead = xlog_recover_validate_ophdr(log, dp, end);
+ if (IS_ERR(ohead))
+ return PTR_ERR(ohead);
+
+ /* the data region follows the ophdr */
+ dp += sizeof(*ohead);
+ len = be32_to_cpu(ohead->oh_len);
trans = xlog_recover_ophdr_to_trans(rhash, rhead, ohead);
if (!trans) {
/* nothing to do, so skip over this ophdr */
- return 0;
+ return sizeof(*ohead) + len;
}
/*
@@ -2739,8 +2788,11 @@ xlog_recover_process_ophdr(
log->l_recovery_lsn = trans->r_lsn;
}
- return xlog_recovery_process_trans(log, trans, dp, len,
- ohead->oh_flags, pass, buffer_list);
+ error = xlog_recovery_process_trans(log, trans, dp, len,
+ ohead->oh_flags, pass, buffer_list);
+ if (error)
+ return error;
+ return sizeof(*ohead) + len;
}
/*
@@ -2761,10 +2813,9 @@ xlog_recover_process_data(
int pass,
struct list_head *buffer_list)
{
- struct xlog_op_header *ohead;
char *end;
int num_logops;
- int error;
+ int consumed;
end = dp + be32_to_cpu(rhead->h_len);
num_logops = be32_to_cpu(rhead->h_num_logops);
@@ -2775,21 +2826,17 @@ xlog_recover_process_data(
trace_xfs_log_recover_record(log, rhead, pass);
while ((dp < end) && num_logops) {
+ /*
+ * Decode, validate and process the next ophdr and its data
+ * region. On success the number of bytes consumed from the
+ * record is returned; errors abort recovery.
+ */
+ consumed = xlog_recover_process_ophdr(log, rhash, rhead, dp,
+ end, pass, buffer_list);
+ if (consumed < 0)
+ return consumed;
- ohead = (struct xlog_op_header *)dp;
- dp += sizeof(*ohead);
- if (dp > end) {
- xfs_warn(log->l_mp, "%s: op header overrun", __func__);
- return -EFSCORRUPTED;
- }
-
- /* errors will abort recovery */
- error = xlog_recover_process_ophdr(log, rhash, rhead, ohead,
- dp, end, pass, buffer_list);
- if (error)
- return error;
-
- dp += be32_to_cpu(ohead->oh_len);
+ dp += consumed;
num_logops--;
}
return 0;
--
2.55.0
next prev parent reply other threads:[~2026-11-16 23:17 UTC|newest]
Thread overview: 60+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-16 23:14 [V2 PATCH 00/59] Validate journal log items during log recovery Dave Chinner
2026-11-16 23:14 ` [PATCH 01/59] xfs: set the unmount record operation header length Dave Chinner
2026-11-16 23:14 ` [PATCH 02/59] xfs: fix the rt rmap btree maximum level checks Dave Chinner
2026-11-16 23:14 ` [PATCH 03/59] xfs: allow an empty rt refcount btree root before the rt volume exists Dave Chinner
2026-11-16 23:14 ` [PATCH 04/59] xfs: recompute the rt btree maxlevels when growfs changes them Dave Chinner
2026-11-16 23:14 ` [PATCH 05/59] xfs: recompute the transaction reservations after growfs Dave Chinner
2026-11-16 23:14 ` [PATCH 06/59] xfs: skip missing groups when freeing them Dave Chinner
2026-11-16 23:14 ` [PATCH 07/59] xfs: update the rt geometry when recovering a superblock change Dave Chinner
2026-11-16 23:14 ` [PATCH 08/59] xfs: reinitialise the filesystem geometry after log recovery Dave Chinner
2026-11-16 23:14 ` [PATCH 09/59] xfs: apply mount superblock updates " Dave Chinner
2026-11-16 23:14 ` [PATCH 10/59] xfs: check the atomic write reservation against the current log size Dave Chinner
2026-11-16 23:14 ` [PATCH 11/59] xfs: fix the bmap btree maximum height calculation Dave Chinner
2026-11-16 23:14 ` [PATCH 12/59] xfs: add log recovery item validation design document Dave Chinner
2026-11-16 23:14 ` [PATCH 13/59] xfs: lift transaction header parsing out of the region assembly Dave Chinner
2026-11-16 23:14 ` [PATCH 14/59] xfs: track transaction header decode state explicitly Dave Chinner
2026-11-16 23:14 ` [PATCH 15/59] xfs: track the log item being rebuilt with an explicit pointer Dave Chinner
2026-11-16 23:14 ` [PATCH 16/59] xfs: complete log items explicitly during recovery Dave Chinner
2026-11-16 23:14 ` [PATCH 17/59] xfs: add log item validation infrastructure to log recovery Dave Chinner
2026-11-16 23:14 ` [PATCH 18/59] xfs: recover the transaction header as a validated item type Dave Chinner
2026-11-16 23:14 ` [PATCH 19/59] xfs: factor out xlog_recover_validate_ophdr() Dave Chinner
2026-11-16 23:14 ` Dave Chinner [this message]
2026-11-16 23:14 ` [PATCH 21/59] xfs: validate the operation header padding during recovery Dave Chinner
2026-11-16 23:14 ` [PATCH 22/59] xfs: validate the operation header flags " Dave Chinner
2026-11-16 23:14 ` [PATCH 23/59] xfs: enforce zero length control records " Dave Chinner
2026-11-16 23:14 ` [PATCH 24/59] xfs: validate the unmount record " Dave Chinner
2026-11-16 23:14 ` [PATCH 25/59] xfs: handle zero length continuation op headers " Dave Chinner
2026-11-16 23:14 ` [PATCH 26/59] xfs: bound the assembled region size " Dave Chinner
2026-11-16 23:14 ` [PATCH 27/59] xfs: dump the corrupt region when log item validation fails Dave Chinner
2026-11-16 23:14 ` [PATCH 28/59] xfs: validate inode create and quota off log items during recovery Dave Chinner
2026-11-16 23:14 ` [PATCH 29/59] xfs: validate extent free " Dave Chinner
2026-11-16 23:14 ` [PATCH 30/59] xfs: validate and convert extent free intents " Dave Chinner
2026-11-16 23:14 ` [PATCH 31/59] xfs: validate and convert extent free done items " Dave Chinner
2026-11-16 23:14 ` [PATCH 32/59] xfs: validate rmap update intents " Dave Chinner
2026-11-16 23:14 ` [PATCH 33/59] xfs: validate rmap update done items " Dave Chinner
2026-11-16 23:14 ` [PATCH 34/59] xfs: validate refcount update intents " Dave Chinner
2026-11-16 23:14 ` [PATCH 35/59] xfs: validate refcount update done items " Dave Chinner
2026-11-16 23:14 ` [PATCH 36/59] xfs: validate bmap update intents " Dave Chinner
2026-11-16 23:14 ` [PATCH 37/59] xfs: validate bmap update done items " Dave Chinner
2026-11-16 23:14 ` [PATCH 38/59] xfs: validate mapping exchange intents " Dave Chinner
2026-11-16 23:14 ` [PATCH 39/59] xfs: validate mapping exchange done items " Dave Chinner
2026-11-16 23:14 ` [PATCH 40/59] xfs: validate dquot " Dave Chinner
2026-11-16 23:14 ` [PATCH 41/59] xfs: validate attr done " Dave Chinner
2026-11-16 23:14 ` [PATCH 42/59] xfs: validate attr intents " Dave Chinner
2026-11-16 23:15 ` [PATCH 43/59] xfs: convert inode items to host format " Dave Chinner
2026-11-16 23:15 ` [PATCH 44/59] xfs: allow xfs_imap() to map without an inode btree lookup Dave Chinner
2026-11-16 23:15 ` [PATCH 45/59] xfs: validate the inode item format header during recovery Dave Chinner
2026-11-16 23:15 ` [PATCH 46/59] xfs: validate the logged inode core " Dave Chinner
2026-11-16 23:15 ` [PATCH 47/59] xfs: validate the logged inode forks " Dave Chinner
2026-11-16 23:15 ` [PATCH 48/59] xfs: validate logged local fork contents " Dave Chinner
2026-11-16 23:15 ` [PATCH 49/59] xfs: validate logged extent " Dave Chinner
2026-11-16 23:15 ` [PATCH 50/59] xfs: allow a long format btree root to be checked without a cursor Dave Chinner
2026-11-16 23:15 ` [PATCH 51/59] xfs: validate logged btree fork roots during recovery Dave Chinner
2026-11-16 23:15 ` [PATCH 52/59] xfs: validate logged metadata " Dave Chinner
2026-11-16 23:15 ` [PATCH 53/59] xfs: check logged btree fork roots fit in the inode fork " Dave Chinner
2026-11-16 23:15 ` [PATCH 54/59] xfs: validate buffer item region count " Dave Chinner
2026-11-16 23:15 ` [PATCH 55/59] xfs: validate buffer item regions " Dave Chinner
2026-11-16 23:15 ` [PATCH 56/59] xfs: validate the whole buffer item " Dave Chinner
2026-11-16 23:15 ` [PATCH 57/59] xfs: remove redundant buffer checks from recovery replay Dave Chinner
2026-11-16 23:15 ` [PATCH 58/59] xfs: fail recovery on a buffer type mismatch Dave Chinner
2026-11-16 23:15 ` [PATCH 59/59] xfs: validate logged dquot buffers during recovery Dave Chinner
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20261116231707.3625263-21-dgc@kernel.org \
--to=dgc@kernel.org \
--cc=cem@kernel.org \
--cc=linux-xfs@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox