* [PATCH 3/6] xfs: repair extended attributes
2023-12-31 19:30 [PATCHSET v29.0 20/28] xfs: online repair of extended attributes Darrick J. Wong
@ 2023-12-31 20:35 ` Darrick J. Wong
0 siblings, 0 replies; 16+ messages in thread
From: Darrick J. Wong @ 2023-12-31 20:35 UTC (permalink / raw
To: djwong; +Cc: linux-xfs
From: Darrick J. Wong <djwong@kernel.org>
If the extended attributes look bad, try to sift through the rubble to
find whatever keys/values we can, stage a new attribute structure in a
temporary file and use the atomic extent swapping mechanism to commit
the results in bulk.
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
fs/xfs/Makefile | 1
fs/xfs/libxfs/xfs_attr.c | 2
fs/xfs/libxfs/xfs_attr.h | 2
fs/xfs/libxfs/xfs_da_format.h | 5
fs/xfs/scrub/attr.c | 20 +
fs/xfs/scrub/attr.h | 7
fs/xfs/scrub/attr_repair.c | 1203 +++++++++++++++++++++++++++++++++++++++++
fs/xfs/scrub/attr_repair.h | 11
fs/xfs/scrub/repair.c | 46 ++
fs/xfs/scrub/repair.h | 6
fs/xfs/scrub/scrub.c | 2
fs/xfs/scrub/trace.h | 83 +++
fs/xfs/scrub/xfarray.c | 17 +
fs/xfs/scrub/xfarray.h | 2
fs/xfs/scrub/xfblob.c | 17 +
fs/xfs/scrub/xfblob.h | 2
fs/xfs/scrub/xfile.h | 12
fs/xfs/xfs_buf.c | 3
fs/xfs/xfs_trace.h | 2
19 files changed, 1439 insertions(+), 4 deletions(-)
create mode 100644 fs/xfs/scrub/attr_repair.c
create mode 100644 fs/xfs/scrub/attr_repair.h
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 72df9890edcf6..9b227be3e28b6 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -194,6 +194,7 @@ ifeq ($(CONFIG_XFS_ONLINE_REPAIR),y)
xfs-y += $(addprefix scrub/, \
agheader_repair.o \
alloc_repair.o \
+ attr_repair.o \
bmap_repair.o \
cow_repair.o \
fscounters_repair.o \
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 1e94e933d7682..b002ddd5f05a2 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -1047,7 +1047,7 @@ xfs_attr_set(
* External routines when attribute list is inside the inode
*========================================================================*/
-static inline int xfs_attr_sf_totsize(struct xfs_inode *dp)
+int xfs_attr_sf_totsize(struct xfs_inode *dp)
{
struct xfs_attr_shortform *sf;
diff --git a/fs/xfs/libxfs/xfs_attr.h b/fs/xfs/libxfs/xfs_attr.h
index 81be9b3e40047..e4f55008552b4 100644
--- a/fs/xfs/libxfs/xfs_attr.h
+++ b/fs/xfs/libxfs/xfs_attr.h
@@ -618,4 +618,6 @@ extern struct kmem_cache *xfs_attr_intent_cache;
int __init xfs_attr_intent_init_cache(void);
void xfs_attr_intent_destroy_cache(void);
+int xfs_attr_sf_totsize(struct xfs_inode *dp);
+
#endif /* __XFS_ATTR_H__ */
diff --git a/fs/xfs/libxfs/xfs_da_format.h b/fs/xfs/libxfs/xfs_da_format.h
index 44748f1640e53..0e1ada44f21ba 100644
--- a/fs/xfs/libxfs/xfs_da_format.h
+++ b/fs/xfs/libxfs/xfs_da_format.h
@@ -716,6 +716,11 @@ struct xfs_attr3_leafblock {
#define XFS_ATTR_INCOMPLETE (1u << XFS_ATTR_INCOMPLETE_BIT)
#define XFS_ATTR_NSP_ONDISK_MASK (XFS_ATTR_ROOT | XFS_ATTR_SECURE)
+#define XFS_ATTR_NAMESPACE_STR \
+ { XFS_ATTR_LOCAL, "local" }, \
+ { XFS_ATTR_ROOT, "root" }, \
+ { XFS_ATTR_SECURE, "secure" }
+
/*
* Alignment for namelist and valuelist entries (since they are mixed
* there can be only one alignment value)
diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c
index 40a59b24c209f..692e1b2837bbb 100644
--- a/fs/xfs/scrub/attr.c
+++ b/fs/xfs/scrub/attr.c
@@ -10,6 +10,7 @@
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_log_format.h"
+#include "xfs_trans.h"
#include "xfs_inode.h"
#include "xfs_da_format.h"
#include "xfs_da_btree.h"
@@ -20,6 +21,7 @@
#include "scrub/common.h"
#include "scrub/dabtree.h"
#include "scrub/attr.h"
+#include "scrub/repair.h"
/* Free the buffers linked from the xattr buffer. */
static void
@@ -35,6 +37,8 @@ xchk_xattr_buf_cleanup(
kvfree(ab->value);
ab->value = NULL;
ab->value_sz = 0;
+ kvfree(ab->name);
+ ab->name = NULL;
}
/*
@@ -65,7 +69,7 @@ xchk_xattr_want_freemap(
* reallocating the buffer if necessary. Buffer contents are not preserved
* across a reallocation.
*/
-static int
+int
xchk_setup_xattr_buf(
struct xfs_scrub *sc,
size_t value_size)
@@ -95,6 +99,12 @@ xchk_setup_xattr_buf(
return -ENOMEM;
}
+ if (xchk_could_repair(sc)) {
+ ab->name = kvmalloc(XATTR_NAME_MAX + 1, XCHK_GFP_FLAGS);
+ if (!ab->name)
+ return -ENOMEM;
+ }
+
resize_value:
if (ab->value_sz >= value_size)
return 0;
@@ -121,6 +131,12 @@ xchk_setup_xattr(
{
int error;
+ if (xchk_could_repair(sc)) {
+ error = xrep_setup_xattr(sc);
+ if (error)
+ return error;
+ }
+
/*
* We failed to get memory while checking attrs, so this time try to
* get all the memory we're ever going to need. Allocate the buffer
@@ -247,7 +263,7 @@ xchk_xattr_listent(
* Within a char, the lowest bit of the char represents the byte with
* the smallest address
*/
-STATIC bool
+bool
xchk_xattr_set_map(
struct xfs_scrub *sc,
unsigned long *map,
diff --git a/fs/xfs/scrub/attr.h b/fs/xfs/scrub/attr.h
index 48fd9402c4328..7db58af56646b 100644
--- a/fs/xfs/scrub/attr.h
+++ b/fs/xfs/scrub/attr.h
@@ -16,9 +16,16 @@ struct xchk_xattr_buf {
/* Bitmap of free space in xattr leaf blocks. */
unsigned long *freemap;
+ /* Memory buffer used to hold salvaged xattr names. */
+ unsigned char *name;
+
/* Memory buffer used to extract xattr values. */
void *value;
size_t value_sz;
};
+bool xchk_xattr_set_map(struct xfs_scrub *sc, unsigned long *map,
+ unsigned int start, unsigned int len);
+int xchk_setup_xattr_buf(struct xfs_scrub *sc, size_t value_size);
+
#endif /* __XFS_SCRUB_ATTR_H__ */
diff --git a/fs/xfs/scrub/attr_repair.c b/fs/xfs/scrub/attr_repair.c
new file mode 100644
index 0000000000000..9a88d46392626
--- /dev/null
+++ b/fs/xfs/scrub/attr_repair.c
@@ -0,0 +1,1203 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2018-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_dir2.h"
+#include "xfs_attr.h"
+#include "xfs_attr_leaf.h"
+#include "xfs_attr_sf.h"
+#include "xfs_attr_remote.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_util.h"
+#include "xfs_swapext.h"
+#include "xfs_xchgrange.h"
+#include "xfs_acl.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/tempfile.h"
+#include "scrub/tempswap.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
+#include "scrub/xfblob.h"
+#include "scrub/attr.h"
+#include "scrub/reap.h"
+#include "scrub/attr_repair.h"
+
+/*
+ * Extended Attribute Repair
+ * =========================
+ *
+ * We repair extended attributes by reading the attr leaf blocks looking for
+ * attributes entries that look salvageable (name passes verifiers, value can
+ * be retrieved, etc). Each extended attribute worth salvaging is stashed in
+ * memory, and the stashed entries are periodically replayed into a temporary
+ * file to constrain memory use. Batching the construction of the temporary
+ * extended attribute structure in this fashion reduces lock cycling of the
+ * file being repaired and the temporary file.
+ *
+ * When salvaging completes, the remaining stashed attributes are replayed to
+ * the temporary file. An atomic extent swap is used to commit the new xattr
+ * blocks to the file being repaired. This will disrupt attrmulti cursors.
+ */
+
+struct xrep_xattr_key {
+ /* Cookie for retrieval of the xattr name. */
+ xfblob_cookie name_cookie;
+
+ /* Cookie for retrieval of the xattr value. */
+ xfblob_cookie value_cookie;
+
+ /* XFS_ATTR_* flags */
+ int flags;
+
+ /* Length of the value and name. */
+ uint32_t valuelen;
+ uint16_t namelen;
+};
+
+/*
+ * Stash up to 8 pages of attrs in xattr_records/xattr_blobs before we write
+ * them to the temp file.
+ */
+#define XREP_XATTR_MAX_STASH_BYTES (PAGE_SIZE * 8)
+
+struct xrep_xattr {
+ struct xfs_scrub *sc;
+
+ /* Information for swapping attr forks at the end. */
+ struct xrep_tempswap tx;
+
+ /* xattr keys */
+ struct xfarray *xattr_records;
+
+ /* xattr values */
+ struct xfblob *xattr_blobs;
+
+ /* Number of attributes that we are salvaging. */
+ unsigned long long attrs_found;
+};
+
+/* Set up to recreate the extended attributes. */
+int
+xrep_setup_xattr(
+ struct xfs_scrub *sc)
+{
+ return xrep_tempfile_create(sc, S_IFREG);
+}
+
+/*
+ * Decide if we want to salvage this attribute. We don't bother with
+ * incomplete or oversized keys or values. The @value parameter can be null
+ * for remote attrs.
+ */
+STATIC int
+xrep_xattr_want_salvage(
+ struct xrep_xattr *rx,
+ unsigned int attr_flags,
+ const void *name,
+ int namelen,
+ const void *value,
+ int valuelen)
+{
+ if (attr_flags & XFS_ATTR_INCOMPLETE)
+ return false;
+ if (namelen > XATTR_NAME_MAX || namelen <= 0)
+ return false;
+ if (valuelen > XATTR_SIZE_MAX || valuelen < 0)
+ return false;
+ return true;
+}
+
+/* Allocate an in-core record to hold xattrs while we rebuild the xattr data. */
+STATIC int
+xrep_xattr_salvage_key(
+ struct xrep_xattr *rx,
+ int flags,
+ unsigned char *name,
+ int namelen,
+ unsigned char *value,
+ int valuelen)
+{
+ struct xrep_xattr_key key = {
+ .valuelen = valuelen,
+ .flags = flags & XFS_ATTR_NSP_ONDISK_MASK,
+ };
+ unsigned int i = 0;
+ int error = 0;
+
+ if (xchk_should_terminate(rx->sc, &error))
+ return error;
+
+ /*
+ * Truncate the name to the first character that would trip namecheck.
+ * If we no longer have a name after that, ignore this attribute.
+ */
+ while (i < namelen && name[i] != 0)
+ i++;
+ if (i == 0)
+ return 0;
+ key.namelen = i;
+
+ trace_xrep_xattr_salvage_rec(rx->sc->ip, flags, name, key.namelen,
+ valuelen);
+
+ error = xfblob_store(rx->xattr_blobs, &key.name_cookie, name,
+ key.namelen);
+ if (error)
+ return error;
+
+ error = xfblob_store(rx->xattr_blobs, &key.value_cookie, value,
+ key.valuelen);
+ if (error)
+ return error;
+
+ error = xfarray_append(rx->xattr_records, &key);
+ if (error)
+ return error;
+
+ rx->attrs_found++;
+ return 0;
+}
+
+/*
+ * Record a shortform extended attribute key & value for later reinsertion
+ * into the inode.
+ */
+STATIC int
+xrep_xattr_salvage_sf_attr(
+ struct xrep_xattr *rx,
+ struct xfs_attr_shortform *sf,
+ struct xfs_attr_sf_entry *sfe)
+{
+ struct xfs_scrub *sc = rx->sc;
+ struct xchk_xattr_buf *ab = sc->buf;
+ unsigned char *name = sfe->nameval;
+ unsigned char *value = &sfe->nameval[sfe->namelen];
+
+ if (!xchk_xattr_set_map(sc, ab->usedmap, (char *)name - (char *)sf,
+ sfe->namelen))
+ return 0;
+
+ if (!xchk_xattr_set_map(sc, ab->usedmap, (char *)value - (char *)sf,
+ sfe->valuelen))
+ return 0;
+
+ if (!xrep_xattr_want_salvage(rx, sfe->flags, sfe->nameval,
+ sfe->namelen, value, sfe->valuelen))
+ return 0;
+
+ return xrep_xattr_salvage_key(rx, sfe->flags, sfe->nameval,
+ sfe->namelen, value, sfe->valuelen);
+}
+
+/*
+ * Record a local format extended attribute key & value for later reinsertion
+ * into the inode.
+ */
+STATIC int
+xrep_xattr_salvage_local_attr(
+ struct xrep_xattr *rx,
+ struct xfs_attr_leaf_entry *ent,
+ unsigned int nameidx,
+ const char *buf_end,
+ struct xfs_attr_leaf_name_local *lentry)
+{
+ struct xchk_xattr_buf *ab = rx->sc->buf;
+ unsigned char *value;
+ unsigned int valuelen;
+ unsigned int namesize;
+
+ /*
+ * Decode the leaf local entry format. If something seems wrong, we
+ * junk the attribute.
+ */
+ value = &lentry->nameval[lentry->namelen];
+ valuelen = be16_to_cpu(lentry->valuelen);
+ namesize = xfs_attr_leaf_entsize_local(lentry->namelen, valuelen);
+ if ((char *)lentry + namesize > buf_end)
+ return 0;
+ if (!xrep_xattr_want_salvage(rx, ent->flags, lentry->nameval,
+ lentry->namelen, value, valuelen))
+ return 0;
+ if (!xchk_xattr_set_map(rx->sc, ab->usedmap, nameidx, namesize))
+ return 0;
+
+ /* Try to save this attribute. */
+ return xrep_xattr_salvage_key(rx, ent->flags, lentry->nameval,
+ lentry->namelen, value, valuelen);
+}
+
+/*
+ * Record a remote format extended attribute key & value for later reinsertion
+ * into the inode.
+ */
+STATIC int
+xrep_xattr_salvage_remote_attr(
+ struct xrep_xattr *rx,
+ struct xfs_attr_leaf_entry *ent,
+ unsigned int nameidx,
+ const char *buf_end,
+ struct xfs_attr_leaf_name_remote *rentry,
+ unsigned int ent_idx,
+ struct xfs_buf *leaf_bp)
+{
+ struct xfs_da_args args = {
+ .trans = rx->sc->tp,
+ .dp = rx->sc->ip,
+ .index = ent_idx,
+ .geo = rx->sc->mp->m_attr_geo,
+ .owner = rx->sc->ip->i_ino,
+ };
+ struct xchk_xattr_buf *ab = rx->sc->buf;
+ unsigned int valuelen;
+ unsigned int namesize;
+ int error;
+
+ /*
+ * Decode the leaf remote entry format. If something seems wrong, we
+ * junk the attribute. Note that we should never find a zero-length
+ * remote attribute value.
+ */
+ valuelen = be32_to_cpu(rentry->valuelen);
+ namesize = xfs_attr_leaf_entsize_remote(rentry->namelen);
+ if ((char *)rentry + namesize > buf_end)
+ return 0;
+ if (valuelen == 0 ||
+ !xrep_xattr_want_salvage(rx, ent->flags, rentry->name,
+ rentry->namelen, NULL, valuelen))
+ return 0;
+ if (!xchk_xattr_set_map(rx->sc, ab->usedmap, nameidx, namesize))
+ return 0;
+
+ /*
+ * Enlarge the buffer (if needed) to hold the value that we're trying
+ * to salvage from the old extended attribute data.
+ */
+ error = xchk_setup_xattr_buf(rx->sc, valuelen);
+ if (error == -ENOMEM)
+ error = -EDEADLOCK;
+ if (error)
+ return error;
+
+ /* Look up the remote value and stash it for reconstruction. */
+ args.valuelen = valuelen;
+ args.namelen = rentry->namelen;
+ args.name = rentry->name;
+ args.value = ab->value;
+ error = xfs_attr3_leaf_getvalue(leaf_bp, &args);
+ if (error || args.rmtblkno == 0)
+ goto err_free;
+
+ error = xfs_attr_rmtval_get(&args);
+ if (error)
+ goto err_free;
+
+ /* Try to save this attribute. */
+ error = xrep_xattr_salvage_key(rx, ent->flags, rentry->name,
+ rentry->namelen, ab->value, valuelen);
+err_free:
+ /* remote value was garbage, junk it */
+ if (error == -EFSBADCRC || error == -EFSCORRUPTED)
+ error = 0;
+ return error;
+}
+
+/* Extract every xattr key that we can from this attr fork block. */
+STATIC int
+xrep_xattr_recover_leaf(
+ struct xrep_xattr *rx,
+ struct xfs_buf *bp)
+{
+ struct xfs_attr3_icleaf_hdr leafhdr;
+ struct xfs_scrub *sc = rx->sc;
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_attr_leafblock *leaf;
+ struct xfs_attr_leaf_name_local *lentry;
+ struct xfs_attr_leaf_name_remote *rentry;
+ struct xfs_attr_leaf_entry *ent;
+ struct xfs_attr_leaf_entry *entries;
+ struct xchk_xattr_buf *ab = rx->sc->buf;
+ char *buf_end;
+ size_t off;
+ unsigned int nameidx;
+ unsigned int hdrsize;
+ int i;
+ int error = 0;
+
+ bitmap_zero(ab->usedmap, mp->m_attr_geo->blksize);
+
+ /* Check the leaf header */
+ leaf = bp->b_addr;
+ xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &leafhdr, leaf);
+ hdrsize = xfs_attr3_leaf_hdr_size(leaf);
+ xchk_xattr_set_map(sc, ab->usedmap, 0, hdrsize);
+ entries = xfs_attr3_leaf_entryp(leaf);
+
+ buf_end = (char *)bp->b_addr + mp->m_attr_geo->blksize;
+ for (i = 0, ent = entries; i < leafhdr.count; ent++, i++) {
+ if (xchk_should_terminate(sc, &error))
+ return error;
+
+ /* Skip key if it conflicts with something else? */
+ off = (char *)ent - (char *)leaf;
+ if (!xchk_xattr_set_map(sc, ab->usedmap, off,
+ sizeof(xfs_attr_leaf_entry_t)))
+ continue;
+
+ /* Check the name information. */
+ nameidx = be16_to_cpu(ent->nameidx);
+ if (nameidx < leafhdr.firstused ||
+ nameidx >= mp->m_attr_geo->blksize)
+ continue;
+
+ if (ent->flags & XFS_ATTR_LOCAL) {
+ lentry = xfs_attr3_leaf_name_local(leaf, i);
+ error = xrep_xattr_salvage_local_attr(rx, ent, nameidx,
+ buf_end, lentry);
+ } else {
+ rentry = xfs_attr3_leaf_name_remote(leaf, i);
+ error = xrep_xattr_salvage_remote_attr(rx, ent, nameidx,
+ buf_end, rentry, i, bp);
+ }
+ if (error)
+ return error;
+ }
+
+ return 0;
+}
+
+/* Try to recover shortform attrs. */
+STATIC int
+xrep_xattr_recover_sf(
+ struct xrep_xattr *rx)
+{
+ struct xfs_scrub *sc = rx->sc;
+ struct xchk_xattr_buf *ab = sc->buf;
+ struct xfs_attr_shortform *sf;
+ struct xfs_attr_sf_entry *sfe;
+ struct xfs_attr_sf_entry *next;
+ struct xfs_ifork *ifp;
+ unsigned char *end;
+ int i;
+ int error = 0;
+
+ ifp = xfs_ifork_ptr(rx->sc->ip, XFS_ATTR_FORK);
+
+ bitmap_zero(ab->usedmap, ifp->if_bytes);
+ sf = (struct xfs_attr_shortform *)rx->sc->ip->i_af.if_u1.if_data;
+ end = (unsigned char *)ifp->if_u1.if_data + ifp->if_bytes;
+ xchk_xattr_set_map(sc, ab->usedmap, 0, sizeof(sf->hdr));
+
+ sfe = &sf->list[0];
+ if ((unsigned char *)sfe > end)
+ return 0;
+
+ for (i = 0; i < sf->hdr.count; i++) {
+ if (xchk_should_terminate(sc, &error))
+ return error;
+
+ next = xfs_attr_sf_nextentry(sfe);
+ if ((unsigned char *)next > end)
+ break;
+
+ if (xchk_xattr_set_map(sc, ab->usedmap,
+ (char *)sfe - (char *)sf,
+ sizeof(struct xfs_attr_sf_entry))) {
+ /*
+ * No conflicts with the sf entry; let's save this
+ * attribute.
+ */
+ error = xrep_xattr_salvage_sf_attr(rx, sf, sfe);
+ if (error)
+ return error;
+ }
+
+ sfe = next;
+ }
+
+ return 0;
+}
+
+/*
+ * Try to return a buffer of xattr data for a given physical extent.
+ *
+ * Because the buffer cache get function complains if it finds a buffer
+ * matching the block number but not matching the length, we must be careful to
+ * look for incore buffers (up to the maximum length of a remote value) that
+ * could be hiding anywhere in the physical range. If we find an incore
+ * buffer, we can pass that to the caller. Optionally, read a single block and
+ * pass that back.
+ *
+ * Note the subtlety that remote attr value blocks for which there is no incore
+ * buffer will be passed to the callback one block at a time. These buffers
+ * will not have any ops attached and must be staled to prevent aliasing with
+ * multiblock buffers once we drop the ILOCK.
+ */
+STATIC int
+xrep_xattr_find_buf(
+ struct xfs_mount *mp,
+ xfs_fsblock_t fsbno,
+ xfs_extlen_t max_len,
+ bool can_read,
+ struct xfs_buf **bpp)
+{
+ struct xrep_bufscan scan = {
+ .daddr = XFS_FSB_TO_DADDR(mp, fsbno),
+ .max_sectors = xrep_bufscan_max_sectors(mp, max_len),
+ .daddr_step = XFS_FSB_TO_BB(mp, 1),
+ };
+ struct xfs_buf *bp;
+
+ while ((bp = xrep_bufscan_advance(mp, &scan)) != NULL) {
+ *bpp = bp;
+ return 0;
+ }
+
+ if (!can_read) {
+ *bpp = NULL;
+ return 0;
+ }
+
+ return xfs_buf_read(mp->m_ddev_targp, scan.daddr, XFS_FSB_TO_BB(mp, 1),
+ XBF_TRYLOCK, bpp, NULL);
+}
+
+/*
+ * Deal with a buffer that we found during our walk of the attr fork.
+ *
+ * Attribute leaf and node blocks are simple -- they're a single block, so we
+ * can walk them one at a time and we never have to worry about discontiguous
+ * multiblock buffers like we do for directories.
+ *
+ * Unfortunately, remote attr blocks add a lot of complexity here. Each disk
+ * block is totally self contained, in the sense that the v5 header provides no
+ * indication that there could be more data in the next block. The incore
+ * buffers can span multiple blocks, though they never cross extent records.
+ * However, they don't necessarily start or end on an extent record boundary.
+ * Therefore, we need a special buffer find function to walk the buffer cache
+ * for us.
+ *
+ * The caller must hold the ILOCK on the file being repaired. We use
+ * XBF_TRYLOCK here to skip any locked buffer on the assumption that we don't
+ * own the block and don't want to hang the system on a potentially garbage
+ * buffer.
+ */
+STATIC int
+xrep_xattr_recover_block(
+ struct xrep_xattr *rx,
+ xfs_dablk_t dabno,
+ xfs_fsblock_t fsbno,
+ xfs_extlen_t max_len,
+ xfs_extlen_t *actual_len)
+{
+ struct xfs_da_blkinfo *info;
+ struct xfs_buf *bp;
+ int error;
+
+ error = xrep_xattr_find_buf(rx->sc->mp, fsbno, max_len, true, &bp);
+ if (error)
+ return error;
+ info = bp->b_addr;
+ *actual_len = XFS_BB_TO_FSB(rx->sc->mp, bp->b_length);
+
+ trace_xrep_xattr_recover_leafblock(rx->sc->ip, dabno,
+ be16_to_cpu(info->magic));
+
+ /*
+ * If the buffer has the right magic number for an attr leaf block and
+ * passes a structure check (we don't care about checksums), salvage
+ * as much as we can from the block. */
+ if (info->magic == cpu_to_be16(XFS_ATTR3_LEAF_MAGIC) &&
+ xrep_buf_verify_struct(bp, &xfs_attr3_leaf_buf_ops) &&
+ xfs_attr3_leaf_header_check(bp, rx->sc->ip->i_ino) == NULL)
+ error = xrep_xattr_recover_leaf(rx, bp);
+
+ /*
+ * If the buffer didn't already have buffer ops set, it was read in by
+ * the _find_buf function and could very well be /part/ of a multiblock
+ * remote block. Mark it stale so that it doesn't hang around in
+ * memory to cause problems.
+ */
+ if (bp->b_ops == NULL)
+ xfs_buf_stale(bp);
+
+ xfs_buf_relse(bp);
+ return error;
+}
+
+/* Insert one xattr key/value. */
+STATIC int
+xrep_xattr_insert_rec(
+ struct xrep_xattr *rx,
+ const struct xrep_xattr_key *key)
+{
+ struct xfs_da_args args = {
+ .dp = rx->sc->tempip,
+ .attr_filter = key->flags,
+ .attr_flags = XATTR_CREATE,
+ .namelen = key->namelen,
+ .valuelen = key->valuelen,
+ .op_flags = XFS_DA_OP_NOTIME,
+ .owner = rx->sc->ip->i_ino,
+ };
+ struct xchk_xattr_buf *ab = rx->sc->buf;
+ int error;
+
+ /*
+ * Grab pointers to the scrub buffer so that we can use them to insert
+ * attrs into the temp file.
+ */
+ args.name = ab->name;
+ args.value = ab->value;
+
+ /*
+ * The attribute name is stored near the end of the in-core buffer,
+ * though we reserve one more byte to ensure null termination.
+ */
+ ab->name[XATTR_NAME_MAX] = 0;
+
+ error = xfblob_load(rx->xattr_blobs, key->name_cookie, ab->name,
+ key->namelen);
+ if (error)
+ return error;
+
+ error = xfblob_free(rx->xattr_blobs, key->name_cookie);
+ if (error)
+ return error;
+
+ error = xfblob_load(rx->xattr_blobs, key->value_cookie, args.value,
+ key->valuelen);
+ if (error)
+ return error;
+
+ error = xfblob_free(rx->xattr_blobs, key->value_cookie);
+ if (error)
+ return error;
+
+ ab->name[key->namelen] = 0;
+
+ trace_xrep_xattr_insert_rec(rx->sc->tempip, key->flags, ab->name,
+ key->namelen, key->valuelen);
+
+ /*
+ * xfs_attr_set creates and commits its own transaction. If the attr
+ * already exists, we'll just drop it during the rebuild.
+ */
+ error = xfs_attr_set(&args);
+ if (error == -EEXIST)
+ error = 0;
+
+ return error;
+}
+
+/*
+ * Periodically flush salvaged attributes to the temporary file. This is done
+ * to reduce the memory requirements of the xattr rebuild because files can
+ * contain millions of attributes.
+ */
+STATIC int
+xrep_xattr_flush_stashed(
+ struct xrep_xattr *rx)
+{
+ xfarray_idx_t array_cur;
+ int error;
+
+ /*
+ * Entering this function, the scrub context has a reference to the
+ * inode being repaired, the temporary file, and a scrub transaction
+ * that we use during xattr salvaging to avoid livelocking if there
+ * are cycles in the xattr structures. We hold ILOCK_EXCL on both
+ * the inode being repaired, though it is not ijoined to the scrub
+ * transaction.
+ *
+ * To constrain kernel memory use, we occasionally flush salvaged
+ * xattrs from the xfarray and xfblob structures into the temporary
+ * file in preparation for swapping the xattr structures at the end.
+ * Updating the temporary file requires a transaction, so we commit the
+ * scrub transaction and drop the two ILOCKs so that xfs_attr_set can
+ * allocate whatever transaction it wants.
+ *
+ * We still hold IOLOCK_EXCL on the inode being repaired, which
+ * prevents anyone from modifying the damaged xattr data while we
+ * repair it.
+ */
+ error = xrep_trans_commit(rx->sc);
+ if (error)
+ return error;
+ xchk_iunlock(rx->sc, XFS_ILOCK_EXCL);
+
+ /*
+ * Take the IOLOCK of the temporary file while we modify xattrs. This
+ * isn't strictly required because the temporary file is never revealed
+ * to userspace, but we follow the same locking rules. We still hold
+ * sc->ip's IOLOCK.
+ */
+ error = xrep_tempfile_iolock_polled(rx->sc);
+ if (error)
+ return error;
+
+ /* Add all the salvaged attrs to the temporary file. */
+ foreach_xfarray_idx(rx->xattr_records, array_cur) {
+ struct xrep_xattr_key key;
+
+ error = xfarray_load(rx->xattr_records, array_cur, &key);
+ if (error)
+ return error;
+
+ error = xrep_xattr_insert_rec(rx, &key);
+ if (error)
+ return error;
+ }
+
+ /* Empty out both arrays now that we've added the entries. */
+ xfarray_truncate(rx->xattr_records);
+ xfblob_truncate(rx->xattr_blobs);
+
+ xrep_tempfile_iounlock(rx->sc);
+
+ /* Recreate the salvage transaction and relock the inode. */
+ error = xchk_trans_alloc(rx->sc, 0);
+ if (error)
+ return error;
+ xchk_ilock(rx->sc, XFS_ILOCK_EXCL);
+ return 0;
+}
+
+/* Decide if we've stashed too much xattr data in memory. */
+static inline bool
+xrep_xattr_want_flush_stashed(
+ struct xrep_xattr *rx)
+{
+ unsigned long long bytes;
+
+ bytes = xfarray_bytes(rx->xattr_records) +
+ xfblob_bytes(rx->xattr_blobs);
+ return bytes > XREP_XATTR_MAX_STASH_BYTES;
+}
+
+/* Extract as many attribute keys and values as we can. */
+STATIC int
+xrep_xattr_recover(
+ struct xrep_xattr *rx)
+{
+ struct xfs_bmbt_irec got;
+ struct xfs_scrub *sc = rx->sc;
+ struct xfs_da_geometry *geo = sc->mp->m_attr_geo;
+ xfs_fileoff_t offset;
+ xfs_extlen_t len;
+ xfs_dablk_t dabno;
+ int nmap;
+ int error;
+
+ /*
+ * Iterate each xattr leaf block in the attr fork to scan them for any
+ * attributes that we might salvage.
+ */
+ for (offset = 0;
+ offset < XFS_MAX_FILEOFF;
+ offset = got.br_startoff + got.br_blockcount) {
+ nmap = 1;
+ error = xfs_bmapi_read(sc->ip, offset, XFS_MAX_FILEOFF - offset,
+ &got, &nmap, XFS_BMAPI_ATTRFORK);
+ if (error)
+ return error;
+ if (nmap != 1)
+ return -EFSCORRUPTED;
+ if (!xfs_bmap_is_written_extent(&got))
+ continue;
+
+ for (dabno = round_up(got.br_startoff, geo->fsbcount);
+ dabno < got.br_startoff + got.br_blockcount;
+ dabno += len) {
+ xfs_fileoff_t curr_offset = dabno - got.br_startoff;
+ xfs_extlen_t maxlen;
+
+ if (xchk_should_terminate(rx->sc, &error))
+ return error;
+
+ maxlen = min_t(xfs_filblks_t, INT_MAX,
+ got.br_blockcount - curr_offset);
+ error = xrep_xattr_recover_block(rx, dabno,
+ curr_offset + got.br_startblock,
+ maxlen, &len);
+ if (error)
+ return error;
+
+ if (xrep_xattr_want_flush_stashed(rx)) {
+ error = xrep_xattr_flush_stashed(rx);
+ if (error)
+ return error;
+ }
+ }
+ }
+
+ return 0;
+}
+
+/*
+ * Reset the extended attribute fork to a state where we can start re-adding
+ * the salvaged attributes.
+ */
+STATIC int
+xrep_xattr_fork_remove(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip)
+{
+ struct xfs_attr_sf_hdr *hdr;
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_ATTR_FORK);
+
+ /*
+ * If the data fork is in btree format, we can't change di_forkoff
+ * because we could run afoul of the rule that the data fork isn't
+ * supposed to be in btree format if there's enough space in the fork
+ * that it could have used extents format. Instead, reinitialize the
+ * attr fork to have a shortform structure with zero attributes.
+ */
+ if (ip->i_df.if_format == XFS_DINODE_FMT_BTREE) {
+ ifp->if_format = XFS_DINODE_FMT_LOCAL;
+ xfs_idata_realloc(ip, (int)sizeof(*hdr) - ifp->if_bytes,
+ XFS_ATTR_FORK);
+ hdr = (struct xfs_attr_sf_hdr *)ifp->if_u1.if_data;
+ hdr->count = 0;
+ hdr->totsize = cpu_to_be16(sizeof(*hdr));
+ xfs_trans_log_inode(sc->tp, ip,
+ XFS_ILOG_CORE | XFS_ILOG_ADATA);
+ return 0;
+ }
+
+ /* If we still have attr fork extents, something's wrong. */
+ if (ifp->if_nextents != 0) {
+ struct xfs_iext_cursor icur;
+ struct xfs_bmbt_irec irec;
+ unsigned int i = 0;
+
+ xfs_emerg(sc->mp,
+ "inode 0x%llx attr fork still has %llu attr extents, format %d?!",
+ ip->i_ino, ifp->if_nextents, ifp->if_format);
+ for_each_xfs_iext(ifp, &icur, &irec) {
+ xfs_err(sc->mp,
+ "[%u]: startoff %llu startblock %llu blockcount %llu state %u",
+ i++, irec.br_startoff,
+ irec.br_startblock, irec.br_blockcount,
+ irec.br_state);
+ }
+ ASSERT(0);
+ return -EFSCORRUPTED;
+ }
+
+ xfs_attr_fork_remove(ip, sc->tp);
+ return 0;
+}
+
+/*
+ * Free all the attribute fork blocks of the file being repaired and delete the
+ * fork. The caller must ILOCK the scrub file and join it to the transaction.
+ * This function returns with the inode joined to a clean transaction.
+ */
+int
+xrep_xattr_reset_fork(
+ struct xfs_scrub *sc)
+{
+ int error;
+
+ trace_xrep_xattr_reset_fork(sc->ip, sc->ip);
+
+ /* Unmap all the attr blocks. */
+ if (xfs_ifork_has_extents(&sc->ip->i_af)) {
+ error = xrep_reap_ifork(sc, sc->ip, XFS_ATTR_FORK);
+ if (error)
+ return error;
+ }
+
+ error = xrep_xattr_fork_remove(sc, sc->ip);
+ if (error)
+ return error;
+
+ return xfs_trans_roll_inode(&sc->tp, sc->ip);
+}
+
+/*
+ * Free all the attribute fork blocks of the temporary file and delete the attr
+ * fork. The caller must ILOCK the tempfile and join it to the transaction.
+ * This function returns with the inode joined to a clean scrub transaction.
+ */
+STATIC int
+xrep_xattr_reset_tempfile_fork(
+ struct xfs_scrub *sc)
+{
+ int error;
+
+ trace_xrep_xattr_reset_fork(sc->ip, sc->tempip);
+
+ /*
+ * Wipe out the attr fork of the temp file so that regular inode
+ * inactivation won't trip over the corrupt attr fork.
+ */
+ if (xfs_ifork_has_extents(&sc->tempip->i_af)) {
+ error = xrep_reap_ifork(sc, sc->tempip, XFS_ATTR_FORK);
+ if (error)
+ return error;
+ }
+
+ return xrep_xattr_fork_remove(sc, sc->tempip);
+}
+
+/*
+ * Find all the extended attributes for this inode by scraping them out of the
+ * attribute key blocks by hand, and flushing them into the temp file.
+ * When we're done, free the staging memory before swapping the xattr
+ * structures to reduce memory usage.
+ */
+STATIC int
+xrep_xattr_salvage_attributes(
+ struct xrep_xattr *rx)
+{
+ struct xfs_inode *ip = rx->sc->ip;
+ int error;
+
+ /* Short format xattrs are easy! */
+ if (rx->sc->ip->i_af.if_format == XFS_DINODE_FMT_LOCAL) {
+ error = xrep_xattr_recover_sf(rx);
+ if (error)
+ return error;
+
+ return xrep_xattr_flush_stashed(rx);
+ }
+
+ /*
+ * For non-inline xattr structures, the salvage function scans the
+ * buffer cache looking for potential attr leaf blocks. The scan
+ * requires the ability to lock any buffer found and runs independently
+ * of any transaction <-> buffer item <-> buffer linkage. Therefore,
+ * roll the transaction to ensure there are no buffers joined. We hold
+ * the ILOCK independently of the transaction.
+ */
+ error = xfs_trans_roll(&rx->sc->tp);
+ if (error)
+ return error;
+
+ error = xfs_iread_extents(rx->sc->tp, ip, XFS_ATTR_FORK);
+ if (error)
+ return error;
+
+ error = xrep_xattr_recover(rx);
+ if (error)
+ return error;
+
+ return xrep_xattr_flush_stashed(rx);
+}
+
+/*
+ * Prepare both inodes' attribute forks for extent swapping. Promote the
+ * tempfile from short format to leaf format, and if the file being repaired
+ * has a short format attr fork, turn it into an empty extent list.
+ */
+STATIC int
+xrep_xattr_swap_prep(
+ struct xfs_scrub *sc,
+ bool temp_local,
+ bool ip_local)
+{
+ int error;
+
+ /*
+ * If the tempfile's attributes are in shortform format, convert that
+ * to a single leaf extent so that we can use the atomic extent swap.
+ */
+ if (temp_local) {
+ struct xfs_da_args args = {
+ .dp = sc->tempip,
+ .geo = sc->mp->m_attr_geo,
+ .whichfork = XFS_ATTR_FORK,
+ .trans = sc->tp,
+ .total = 1,
+ .owner = sc->ip->i_ino,
+ };
+
+ error = xfs_attr_shortform_to_leaf(&args);
+ if (error)
+ return error;
+
+ /*
+ * Roll the deferred log items to get us back to a clean
+ * transaction.
+ */
+ error = xfs_defer_finish(&sc->tp);
+ if (error)
+ return error;
+ }
+
+ /*
+ * If the file being repaired had a shortform attribute fork, convert
+ * that to an empty extent list in preparation for the atomic extent
+ * swap.
+ */
+ if (ip_local) {
+ struct xfs_ifork *ifp;
+
+ ifp = xfs_ifork_ptr(sc->ip, XFS_ATTR_FORK);
+
+ xfs_idestroy_fork(ifp);
+ ifp->if_format = XFS_DINODE_FMT_EXTENTS;
+ ifp->if_nextents = 0;
+ ifp->if_bytes = 0;
+ ifp->if_u1.if_root = NULL;
+ ifp->if_height = 0;
+
+ xfs_trans_log_inode(sc->tp, sc->ip,
+ XFS_ILOG_CORE | XFS_ILOG_ADATA);
+ }
+
+ return 0;
+}
+
+/* Swap the temporary file's attribute fork with the one being repaired. */
+STATIC int
+xrep_xattr_swap(
+ struct xfs_scrub *sc,
+ struct xrep_tempswap *tx)
+{
+ bool ip_local, temp_local;
+ int error = 0;
+
+ ip_local = sc->ip->i_af.if_format == XFS_DINODE_FMT_LOCAL;
+ temp_local = sc->tempip->i_af.if_format == XFS_DINODE_FMT_LOCAL;
+
+ /*
+ * If the both files have a local format attr fork and the rebuilt
+ * xattr data would fit in the repaired file's attr fork, just copy
+ * the contents from the tempfile and declare ourselves done.
+ */
+ if (ip_local && temp_local) {
+ int forkoff;
+ int newsize;
+
+ newsize = xfs_attr_sf_totsize(sc->tempip);
+ forkoff = xfs_attr_shortform_bytesfit(sc->ip, newsize);
+ if (forkoff > 0) {
+ sc->ip->i_forkoff = forkoff;
+ xrep_tempfile_copyout_local(sc, XFS_ATTR_FORK);
+ return 0;
+ }
+ }
+
+ /* Otherwise, make sure both attr forks are in block-mapping mode. */
+ error = xrep_xattr_swap_prep(sc, temp_local, ip_local);
+ if (error)
+ return error;
+
+ return xrep_tempswap_contents(sc, tx);
+}
+
+/*
+ * Swap the new extended attribute data (which we created in the tempfile) into
+ * the file being repaired.
+ */
+STATIC int
+xrep_xattr_rebuild_tree(
+ struct xrep_xattr *rx)
+{
+ struct xfs_scrub *sc = rx->sc;
+ int error;
+
+ /*
+ * If we didn't find any attributes to salvage, repair the file by
+ * zapping its attr fork.
+ */
+ if (rx->attrs_found == 0) {
+ xfs_trans_ijoin(sc->tp, sc->ip, 0);
+ error = xrep_xattr_reset_fork(sc);
+ if (error)
+ return error;
+
+ goto forget_acls;
+ }
+
+ trace_xrep_xattr_rebuild_tree(sc->ip, sc->tempip);
+
+ /*
+ * Commit the repair transaction and drop the ILOCKs so that we can use
+ * the atomic extent swap helper functions to compute the correct
+ * resource reservations.
+ *
+ * We still hold IOLOCK_EXCL (aka i_rwsem) which will prevent xattr
+ * modifications, but there's nothing to prevent userspace from reading
+ * the attributes until we're ready for the swap operation. Reads will
+ * return -EIO without shutting down the fs, so we're ok with that.
+ */
+ error = xrep_trans_commit(sc);
+ if (error)
+ return error;
+
+ xchk_iunlock(sc, XFS_ILOCK_EXCL);
+
+ /*
+ * Take the IOLOCK on the temporary file so that we can run xattr
+ * operations with the same locks held as we would for a normal file.
+ * We still hold sc->ip's IOLOCK.
+ */
+ error = xrep_tempfile_iolock_polled(rx->sc);
+ if (error)
+ return error;
+
+ /* Allocate swapext transaction and lock both inodes. */
+ error = xrep_tempswap_trans_alloc(rx->sc, XFS_ATTR_FORK, &rx->tx);
+ if (error)
+ return error;
+
+ /*
+ * Exchange the blocks mapped by the tempfile's attr fork with the file
+ * being repaired. The old attr blocks will then be attached to the
+ * tempfile, so reap its attr fork.
+ */
+ error = xrep_xattr_swap(sc, &rx->tx);
+ if (error)
+ return error;
+
+ error = xrep_xattr_reset_tempfile_fork(sc);
+ if (error)
+ return error;
+
+ /*
+ * Roll to get a transaction without any inodes joined to it. Then we
+ * can drop the tempfile's ILOCK and IOLOCK before doing more work on
+ * the scrub target file.
+ */
+ error = xfs_trans_roll(&sc->tp);
+ if (error)
+ return error;
+
+ xrep_tempfile_iunlock(sc);
+ xrep_tempfile_iounlock(sc);
+
+forget_acls:
+ /* Invalidate cached ACLs now that we've reloaded all the xattrs. */
+ xfs_forget_acl(VFS_I(sc->ip), SGI_ACL_FILE);
+ xfs_forget_acl(VFS_I(sc->ip), SGI_ACL_DEFAULT);
+ return 0;
+}
+
+/* Tear down all the incore scan stuff we created. */
+STATIC void
+xrep_xattr_teardown(
+ struct xrep_xattr *rx)
+{
+ xfblob_destroy(rx->xattr_blobs);
+ xfarray_destroy(rx->xattr_records);
+ kfree(rx);
+}
+
+/* Set up the filesystem scan so we can regenerate extended attributes. */
+STATIC int
+xrep_xattr_setup_scan(
+ struct xfs_scrub *sc,
+ struct xrep_xattr **rxp)
+{
+ struct xrep_xattr *rx;
+ char *descr;
+ int max_len;
+ int error;
+
+ rx = kzalloc(sizeof(struct xrep_xattr), XCHK_GFP_FLAGS);
+ if (!rx)
+ return -ENOMEM;
+ rx->sc = sc;
+
+ /*
+ * Allocate enough memory to handle loading local attr values from the
+ * xfblob data while flushing stashed attrs to the temporary file.
+ * We only realloc the buffer when salvaging remote attr values.
+ */
+ max_len = xfs_attr_leaf_entsize_local_max(sc->mp->m_attr_geo->blksize);
+ error = xchk_setup_xattr_buf(rx->sc, max_len);
+ if (error == -ENOMEM)
+ error = -EDEADLOCK;
+ if (error)
+ goto out_rx;
+
+ /* Set up some staging for salvaged attribute keys and values */
+ descr = xchk_xfile_ino_descr(sc, "xattr keys");
+ error = xfarray_create(descr, 0, sizeof(struct xrep_xattr_key),
+ &rx->xattr_records);
+ kfree(descr);
+ if (error)
+ goto out_rx;
+
+ descr = xchk_xfile_ino_descr(sc, "xattr names");
+ error = xfblob_create(descr, &rx->xattr_blobs);
+ kfree(descr);
+ if (error)
+ goto out_keys;
+
+ *rxp = rx;
+ return 0;
+out_keys:
+ xfarray_destroy(rx->xattr_records);
+out_rx:
+ kfree(rx);
+ return error;
+}
+
+/*
+ * Repair the extended attribute metadata.
+ *
+ * XXX: Remote attribute value buffers encompass the entire (up to 64k) buffer.
+ * The buffer cache in XFS can't handle aliased multiblock buffers, so this
+ * might misbehave if the attr fork is crosslinked with other filesystem
+ * metadata.
+ */
+int
+xrep_xattr(
+ struct xfs_scrub *sc)
+{
+ struct xrep_xattr *rx = NULL;
+ int error;
+
+ if (!xfs_inode_hasattr(sc->ip))
+ return -ENOENT;
+
+ /* The rmapbt is required to reap the old attr fork. */
+ if (!xfs_has_rmapbt(sc->mp))
+ return -EOPNOTSUPP;
+
+ error = xrep_xattr_setup_scan(sc, &rx);
+ if (error)
+ return error;
+
+ ASSERT(sc->ilock_flags & XFS_ILOCK_EXCL);
+
+ error = xrep_xattr_salvage_attributes(rx);
+ if (error)
+ goto out_scan;
+
+ /* Last chance to abort before we start committing fixes. */
+ if (xchk_should_terminate(sc, &error))
+ goto out_scan;
+
+ error = xrep_xattr_rebuild_tree(rx);
+ if (error)
+ goto out_scan;
+
+out_scan:
+ xrep_xattr_teardown(rx);
+ return error;
+}
diff --git a/fs/xfs/scrub/attr_repair.h b/fs/xfs/scrub/attr_repair.h
new file mode 100644
index 0000000000000..0a9ffa7cfa906
--- /dev/null
+++ b/fs/xfs/scrub/attr_repair.h
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2018-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_ATTR_REPAIR_H__
+#define __XFS_SCRUB_ATTR_REPAIR_H__
+
+int xrep_xattr_reset_fork(struct xfs_scrub *sc);
+
+#endif /* __XFS_SCRUB_ATTR_REPAIR_H__ */
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 6490f064e091f..83b7aa48dec19 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -32,6 +32,9 @@
#include "xfs_reflink.h"
#include "xfs_health.h"
#include "xfs_buf_xfile.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_attr.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/trace.h"
@@ -39,6 +42,7 @@
#include "scrub/bitmap.h"
#include "scrub/stats.h"
#include "scrub/xfile.h"
+#include "scrub/attr_repair.h"
/*
* Attempt to repair some metadata, if the metadata is corrupt and userspace
@@ -1136,6 +1140,17 @@ xrep_metadata_inode_forks(
return error;
}
+ /* Clear the attr forks since metadata shouldn't have that. */
+ if (xfs_inode_hasattr(sc->ip)) {
+ if (!dirty) {
+ dirty = true;
+ xfs_trans_ijoin(sc->tp, sc->ip, 0);
+ }
+ error = xrep_xattr_reset_fork(sc);
+ if (error)
+ return error;
+ }
+
/*
* If we modified the inode, roll the transaction but don't rejoin the
* inode to the new transaction because xrep_bmap_data can do that.
@@ -1201,3 +1216,34 @@ xrep_trans_cancel_hook_dummy(
current->journal_info = *cookiep;
*cookiep = NULL;
}
+
+/*
+ * See if this buffer can pass the given ->verify_struct() function.
+ *
+ * If the buffer already has ops attached and they're not the ones that were
+ * passed in, we reject the buffer. Otherwise, we perform the structure test
+ * (note that we do not check CRCs) and return the outcome of the test. The
+ * buffer ops and error state are left unchanged.
+ */
+bool
+xrep_buf_verify_struct(
+ struct xfs_buf *bp,
+ const struct xfs_buf_ops *ops)
+{
+ const struct xfs_buf_ops *old_ops = bp->b_ops;
+ xfs_failaddr_t fa;
+ int old_error;
+
+ if (old_ops) {
+ if (old_ops != ops)
+ return false;
+ }
+
+ old_error = bp->b_error;
+ bp->b_ops = ops;
+ fa = bp->b_ops->verify_struct(bp);
+ bp->b_ops = old_ops;
+ bp->b_error = old_error;
+
+ return fa == NULL;
+}
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 06125d0a2c602..2bc5dd18d46f4 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -90,6 +90,7 @@ int xrep_bmap(struct xfs_scrub *sc, int whichfork, bool allow_unwritten);
int xrep_metadata_inode_forks(struct xfs_scrub *sc);
int xrep_setup_ag_rmapbt(struct xfs_scrub *sc);
int xrep_setup_ag_refcountbt(struct xfs_scrub *sc);
+int xrep_setup_xattr(struct xfs_scrub *sc);
/* Repair setup functions */
int xrep_setup_ag_allocbt(struct xfs_scrub *sc);
@@ -123,6 +124,7 @@ int xrep_bmap_attr(struct xfs_scrub *sc);
int xrep_bmap_cow(struct xfs_scrub *sc);
int xrep_nlinks(struct xfs_scrub *sc);
int xrep_fscounters(struct xfs_scrub *sc);
+int xrep_xattr(struct xfs_scrub *sc);
#ifdef CONFIG_XFS_RT
int xrep_rtbitmap(struct xfs_scrub *sc);
@@ -147,6 +149,8 @@ int xrep_trans_alloc_hook_dummy(struct xfs_mount *mp, void **cookiep,
struct xfs_trans **tpp);
void xrep_trans_cancel_hook_dummy(void **cookiep, struct xfs_trans *tp);
+bool xrep_buf_verify_struct(struct xfs_buf *bp, const struct xfs_buf_ops *ops);
+
#else
#define xrep_ino_dqattach(sc) (0)
@@ -190,6 +194,7 @@ xrep_setup_nothing(
#define xrep_setup_ag_allocbt xrep_setup_nothing
#define xrep_setup_ag_rmapbt xrep_setup_nothing
#define xrep_setup_ag_refcountbt xrep_setup_nothing
+#define xrep_setup_xattr xrep_setup_nothing
#define xrep_setup_inode(sc, imap) ((void)0)
@@ -215,6 +220,7 @@ xrep_setup_nothing(
#define xrep_nlinks xrep_notsupported
#define xrep_fscounters xrep_notsupported
#define xrep_rtsummary xrep_notsupported
+#define xrep_xattr xrep_notsupported
#endif /* CONFIG_XFS_ONLINE_REPAIR */
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 9af91874e58b9..0b8fdd62055fe 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -334,7 +334,7 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
.type = ST_INODE,
.setup = xchk_setup_xattr,
.scrub = xchk_xattr,
- .repair = xrep_notsupported,
+ .repair = xrep_xattr,
},
[XFS_SCRUB_TYPE_SYMLINK] = { /* symbolic link */
.type = ST_INODE,
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 1f06c1ace5902..ba75a56b2e2de 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -2497,6 +2497,89 @@ TRACE_EVENT(xreap_bmapi_binval_scan,
__entry->scan_blocks)
);
+TRACE_EVENT(xrep_xattr_recover_leafblock,
+ TP_PROTO(struct xfs_inode *ip, xfs_dablk_t dabno, uint16_t magic),
+ TP_ARGS(ip, dabno, magic),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(xfs_dablk_t, dabno)
+ __field(uint16_t, magic)
+ ),
+ TP_fast_assign(
+ __entry->dev = ip->i_mount->m_super->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->dabno = dabno;
+ __entry->magic = magic;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx dablk 0x%x magic 0x%x",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->dabno,
+ __entry->magic)
+);
+
+DECLARE_EVENT_CLASS(xrep_xattr_salvage_class,
+ TP_PROTO(struct xfs_inode *ip, unsigned int flags, char *name,
+ unsigned int namelen, unsigned int valuelen),
+ TP_ARGS(ip, flags, name, namelen, valuelen),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(unsigned int, flags)
+ __field(unsigned int, namelen)
+ __dynamic_array(char, name, namelen)
+ __field(unsigned int, valuelen)
+ ),
+ TP_fast_assign(
+ __entry->dev = ip->i_mount->m_super->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->flags = flags;
+ __entry->namelen = namelen;
+ memcpy(__get_str(name), name, namelen);
+ __entry->valuelen = valuelen;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx flags %s name '%.*s' valuelen 0x%x",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __print_flags(__entry->flags, "|", XFS_ATTR_NAMESPACE_STR),
+ __entry->namelen,
+ __get_str(name),
+ __entry->valuelen)
+);
+#define DEFINE_XREP_XATTR_SALVAGE_EVENT(name) \
+DEFINE_EVENT(xrep_xattr_salvage_class, name, \
+ TP_PROTO(struct xfs_inode *ip, unsigned int flags, char *name, \
+ unsigned int namelen, unsigned int valuelen), \
+ TP_ARGS(ip, flags, name, namelen, valuelen))
+DEFINE_XREP_XATTR_SALVAGE_EVENT(xrep_xattr_salvage_rec);
+DEFINE_XREP_XATTR_SALVAGE_EVENT(xrep_xattr_insert_rec);
+
+TRACE_EVENT(xrep_xattr_class,
+ TP_PROTO(struct xfs_inode *ip, struct xfs_inode *arg_ip),
+ TP_ARGS(ip, arg_ip),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(xfs_ino_t, src_ino)
+ ),
+ TP_fast_assign(
+ __entry->dev = ip->i_mount->m_super->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->src_ino = arg_ip->i_ino;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx src 0x%llx",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->src_ino)
+)
+#define DEFINE_XREP_XATTR_EVENT(name) \
+DEFINE_EVENT(xrep_xattr_class, name, \
+ TP_PROTO(struct xfs_inode *ip, struct xfs_inode *arg_ip), \
+ TP_ARGS(ip, arg_ip))
+DEFINE_XREP_XATTR_EVENT(xrep_xattr_rebuild_tree);
+DEFINE_XREP_XATTR_EVENT(xrep_xattr_reset_fork);
+
#endif /* IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) */
diff --git a/fs/xfs/scrub/xfarray.c b/fs/xfs/scrub/xfarray.c
index f0f532c10a5ac..1bd690ac5d368 100644
--- a/fs/xfs/scrub/xfarray.c
+++ b/fs/xfs/scrub/xfarray.c
@@ -1081,3 +1081,20 @@ xfarray_sort(
kvfree(si);
return error;
}
+
+/* How many bytes is this array consuming? */
+unsigned long long
+xfarray_bytes(
+ struct xfarray *array)
+{
+ return xfile_bytes(array->xfile);
+}
+
+/* Empty the entire array. */
+void
+xfarray_truncate(
+ struct xfarray *array)
+{
+ xfile_discard(array->xfile, 0, MAX_LFS_FILESIZE);
+ array->nr = 0;
+}
diff --git a/fs/xfs/scrub/xfarray.h b/fs/xfs/scrub/xfarray.h
index 0f1dac3aa1916..f06af7eb484ec 100644
--- a/fs/xfs/scrub/xfarray.h
+++ b/fs/xfs/scrub/xfarray.h
@@ -44,6 +44,8 @@ int xfarray_unset(struct xfarray *array, xfarray_idx_t idx);
int xfarray_store(struct xfarray *array, xfarray_idx_t idx, const void *ptr);
int xfarray_store_anywhere(struct xfarray *array, const void *ptr);
bool xfarray_element_is_null(struct xfarray *array, const void *ptr);
+void xfarray_truncate(struct xfarray *array);
+unsigned long long xfarray_bytes(struct xfarray *array);
/*
* Load an array element, but zero the buffer if there's no data because we
diff --git a/fs/xfs/scrub/xfblob.c b/fs/xfs/scrub/xfblob.c
index 216f9cb2965a7..9c9ec90c69dbc 100644
--- a/fs/xfs/scrub/xfblob.c
+++ b/fs/xfs/scrub/xfblob.c
@@ -149,3 +149,20 @@ xfblob_free(
xfile_discard(blob->xfile, cookie, sizeof(key) + key.xb_size);
return 0;
}
+
+/* How many bytes is this blob storage object consuming? */
+unsigned long long
+xfblob_bytes(
+ struct xfblob *blob)
+{
+ return xfile_bytes(blob->xfile);
+}
+
+/* Drop all the blobs. */
+void
+xfblob_truncate(
+ struct xfblob *blob)
+{
+ xfile_discard(blob->xfile, PAGE_SIZE, MAX_LFS_FILESIZE - PAGE_SIZE);
+ blob->last_offset = PAGE_SIZE;
+}
diff --git a/fs/xfs/scrub/xfblob.h b/fs/xfs/scrub/xfblob.h
index bd98647407f1d..78a67a06408f8 100644
--- a/fs/xfs/scrub/xfblob.h
+++ b/fs/xfs/scrub/xfblob.h
@@ -20,5 +20,7 @@ int xfblob_load(struct xfblob *blob, xfblob_cookie cookie, void *ptr,
int xfblob_store(struct xfblob *blob, xfblob_cookie *cookie, const void *ptr,
uint32_t size);
int xfblob_free(struct xfblob *blob, xfblob_cookie cookie);
+unsigned long long xfblob_bytes(struct xfblob *blob);
+void xfblob_truncate(struct xfblob *blob);
#endif /* __XFS_SCRUB_XFBLOB_H__ */
diff --git a/fs/xfs/scrub/xfile.h b/fs/xfs/scrub/xfile.h
index 36061af2c1352..849f59da6a184 100644
--- a/fs/xfs/scrub/xfile.h
+++ b/fs/xfs/scrub/xfile.h
@@ -86,6 +86,18 @@ static inline loff_t xfile_size(struct xfile *xf)
return i_size_read(file_inode(xf->file));
}
+static inline unsigned long long xfile_bytes(struct xfile *xf)
+{
+ struct xfile_stat xs;
+ int ret;
+
+ ret = xfile_stat(xf, &xs);
+ if (ret)
+ return 0;
+
+ return xs.bytes;
+}
+
/* file block (aka system page size) to basic block conversions. */
typedef unsigned long long xfileoff_t;
#define XFB_BLOCKSIZE (PAGE_SIZE)
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index a61ad61cb9136..b62518968e784 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -481,6 +481,9 @@ _xfs_buf_obj_cmp(
* it stale has not yet committed. i.e. we are
* reallocating a busy extent. Skip this buffer and
* continue searching for an exact match.
+ *
+ * Note: If we're scanning for incore buffers to stale, don't
+ * complain if we find non-stale buffers.
*/
if (!(map->bm_flags & XBM_LIVESCAN))
ASSERT(bp->b_flags & XBF_STALE);
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index ee6f569c2f3d9..2c838b7471191 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -31,6 +31,8 @@
* pos: file offset, in bytes
* bytecount: number of bytes
*
+ * dablk: directory or xattr block offset, in filesystem blocks
+ *
* disize: ondisk file size, in bytes
* isize: incore file size, in bytes
*
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCHSET v29.4 07/13] xfs: online repair of extended attributes
@ 2024-02-27 2:18 Darrick J. Wong
2024-02-27 2:28 ` [PATCH 1/6] xfs: create a blob array data structure Darrick J. Wong
` (5 more replies)
0 siblings, 6 replies; 16+ messages in thread
From: Darrick J. Wong @ 2024-02-27 2:18 UTC (permalink / raw
To: djwong; +Cc: Dave Chinner, linux-xfs, hch
Hi all,
This series employs atomic extent swapping to enable safe reconstruction
of extended attribute data attached to a file. Because xattrs do not
have any redundant information to draw off of, we can at best salvage
as much data as we can and build a new structure.
Rebuilding an extended attribute structure consists of these three
steps:
First, we walk the existing attributes to salvage as many of them as we
can, by adding them as new attributes attached to the repair tempfile.
We need to add a new xfile-based data structure to hold blobs of
arbitrary length to stage the xattr names and values.
Second, we write the salvaged attributes to a temporary file, and use
atomic extent swaps to exchange the entire attribute fork between the
two files.
Finally, we reap the old xattr blocks (which are now in the temporary
file) as carefully as we can.
If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.
This has been running on the djcloud for months with no problems. Enjoy!
Comments and questions are, as always, welcome.
--D
kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=repair-xattrs
xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=repair-xattrs
fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=repair-xattrs
---
Commits in this patchset:
* xfs: create a blob array data structure
* xfs: use atomic extent swapping to fix user file fork data
* xfs: repair extended attributes
* xfs: scrub should set preen if attr leaf has holes
* xfs: flag empty xattr leaf blocks for optimization
* xfs: create an xattr iteration function for scrub
---
fs/xfs/Makefile | 3
fs/xfs/libxfs/xfs_attr.c | 2
fs/xfs/libxfs/xfs_attr.h | 2
fs/xfs/libxfs/xfs_da_format.h | 5
fs/xfs/libxfs/xfs_exchmaps.c | 2
fs/xfs/libxfs/xfs_exchmaps.h | 1
fs/xfs/scrub/attr.c | 158 +++--
fs/xfs/scrub/attr.h | 7
fs/xfs/scrub/attr_repair.c | 1205 +++++++++++++++++++++++++++++++++++++++++
fs/xfs/scrub/attr_repair.h | 11
fs/xfs/scrub/dab_bitmap.h | 37 +
fs/xfs/scrub/dabtree.c | 16 +
fs/xfs/scrub/dabtree.h | 3
fs/xfs/scrub/listxattr.c | 310 +++++++++++
fs/xfs/scrub/listxattr.h | 17 +
fs/xfs/scrub/repair.c | 46 ++
fs/xfs/scrub/repair.h | 6
fs/xfs/scrub/scrub.c | 2
fs/xfs/scrub/tempexch.h | 2
fs/xfs/scrub/tempfile.c | 204 +++++++
fs/xfs/scrub/tempfile.h | 3
fs/xfs/scrub/trace.h | 85 +++
fs/xfs/scrub/xfarray.c | 17 +
fs/xfs/scrub/xfarray.h | 2
fs/xfs/scrub/xfblob.c | 168 ++++++
fs/xfs/scrub/xfblob.h | 26 +
fs/xfs/scrub/xfile.c | 12
fs/xfs/scrub/xfile.h | 6
fs/xfs/xfs_buf.c | 3
fs/xfs/xfs_trace.h | 2
30 files changed, 2280 insertions(+), 83 deletions(-)
create mode 100644 fs/xfs/scrub/attr_repair.c
create mode 100644 fs/xfs/scrub/attr_repair.h
create mode 100644 fs/xfs/scrub/dab_bitmap.h
create mode 100644 fs/xfs/scrub/listxattr.c
create mode 100644 fs/xfs/scrub/listxattr.h
create mode 100644 fs/xfs/scrub/xfblob.c
create mode 100644 fs/xfs/scrub/xfblob.h
^ permalink raw reply [flat|nested] 16+ messages in thread
* [PATCH 1/6] xfs: create a blob array data structure
2024-02-27 2:18 [PATCHSET v29.4 07/13] xfs: online repair of extended attributes Darrick J. Wong
@ 2024-02-27 2:28 ` Darrick J. Wong
2024-02-28 16:00 ` Christoph Hellwig
2024-02-27 2:29 ` [PATCH 2/6] xfs: use atomic extent swapping to fix user file fork data Darrick J. Wong
` (4 subsequent siblings)
5 siblings, 1 reply; 16+ messages in thread
From: Darrick J. Wong @ 2024-02-27 2:28 UTC (permalink / raw
To: djwong; +Cc: linux-xfs, hch
From: Darrick J. Wong <djwong@kernel.org>
Create a simple 'blob array' data structure for storage of arbitrarily
sized metadata objects that will be used to reconstruct metadata. For
the intended usage (temporarily storing extended attribute names and
values) we only have to support storing objects and retrieving them.
Use the xfile abstraction to store the attribute information in memory
that can be swapped out.
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
fs/xfs/Makefile | 1
fs/xfs/scrub/trace.h | 1
fs/xfs/scrub/xfblob.c | 151 +++++++++++++++++++++++++++++++++++++++++++++++++
fs/xfs/scrub/xfblob.h | 24 ++++++++
fs/xfs/scrub/xfile.c | 12 ++++
fs/xfs/scrub/xfile.h | 1
6 files changed, 190 insertions(+)
create mode 100644 fs/xfs/scrub/xfblob.c
create mode 100644 fs/xfs/scrub/xfblob.h
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 66415ac8f5717..91af9b7f418e9 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -209,6 +209,7 @@ xfs-y += $(addprefix scrub/, \
repair.o \
rmap_repair.o \
tempfile.o \
+ xfblob.o \
)
xfs-$(CONFIG_XFS_RT) += $(addprefix scrub/, \
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 5edbabacc31a8..b5fe49a6da534 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -948,6 +948,7 @@ DEFINE_XFILE_EVENT(xfile_store);
DEFINE_XFILE_EVENT(xfile_seek_data);
DEFINE_XFILE_EVENT(xfile_get_folio);
DEFINE_XFILE_EVENT(xfile_put_folio);
+DEFINE_XFILE_EVENT(xfile_discard);
TRACE_EVENT(xfarray_create,
TP_PROTO(struct xfarray *xfa, unsigned long long required_capacity),
diff --git a/fs/xfs/scrub/xfblob.c b/fs/xfs/scrub/xfblob.c
new file mode 100644
index 0000000000000..cec668debce5a
--- /dev/null
+++ b/fs/xfs/scrub/xfblob.c
@@ -0,0 +1,151 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2021-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "scrub/scrub.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
+#include "scrub/xfblob.h"
+
+/*
+ * XFS Blob Storage
+ * ================
+ * Stores and retrieves blobs using an xfile. Objects are appended to the file
+ * and the offset is returned as a magic cookie for retrieval.
+ */
+
+#define XB_KEY_MAGIC 0xABAADDAD
+struct xb_key {
+ uint32_t xb_magic; /* XB_KEY_MAGIC */
+ uint32_t xb_size; /* size of the blob, in bytes */
+ loff_t xb_offset; /* byte offset of this key */
+ /* blob comes after here */
+} __packed;
+
+/* Initialize a blob storage object. */
+int
+xfblob_create(
+ const char *description,
+ struct xfblob **blobp)
+{
+ struct xfblob *blob;
+ struct xfile *xfile;
+ int error;
+
+ error = xfile_create(description, 0, &xfile);
+ if (error)
+ return error;
+
+ blob = kmalloc(sizeof(struct xfblob), XCHK_GFP_FLAGS);
+ if (!blob) {
+ error = -ENOMEM;
+ goto out_xfile;
+ }
+
+ blob->xfile = xfile;
+ blob->last_offset = PAGE_SIZE;
+
+ *blobp = blob;
+ return 0;
+
+out_xfile:
+ xfile_destroy(xfile);
+ return error;
+}
+
+/* Destroy a blob storage object. */
+void
+xfblob_destroy(
+ struct xfblob *blob)
+{
+ xfile_destroy(blob->xfile);
+ kfree(blob);
+}
+
+/* Retrieve a blob. */
+int
+xfblob_load(
+ struct xfblob *blob,
+ xfblob_cookie cookie,
+ void *ptr,
+ uint32_t size)
+{
+ struct xb_key key;
+ int error;
+
+ error = xfile_load(blob->xfile, &key, sizeof(key), cookie);
+ if (error)
+ return error;
+
+ if (key.xb_magic != XB_KEY_MAGIC || key.xb_offset != cookie) {
+ ASSERT(0);
+ return -ENODATA;
+ }
+ if (size < key.xb_size) {
+ ASSERT(0);
+ return -EFBIG;
+ }
+
+ return xfile_load(blob->xfile, ptr, key.xb_size,
+ cookie + sizeof(key));
+}
+
+/* Store a blob. */
+int
+xfblob_store(
+ struct xfblob *blob,
+ xfblob_cookie *cookie,
+ const void *ptr,
+ uint32_t size)
+{
+ struct xb_key key = {
+ .xb_offset = blob->last_offset,
+ .xb_magic = XB_KEY_MAGIC,
+ .xb_size = size,
+ };
+ loff_t pos = blob->last_offset;
+ int error;
+
+ error = xfile_store(blob->xfile, &key, sizeof(key), pos);
+ if (error)
+ return error;
+
+ pos += sizeof(key);
+ error = xfile_store(blob->xfile, ptr, size, pos);
+ if (error)
+ goto out_err;
+
+ *cookie = blob->last_offset;
+ blob->last_offset += sizeof(key) + size;
+ return 0;
+out_err:
+ xfile_discard(blob->xfile, blob->last_offset, sizeof(key));
+ return error;
+}
+
+/* Free a blob. */
+int
+xfblob_free(
+ struct xfblob *blob,
+ xfblob_cookie cookie)
+{
+ struct xb_key key;
+ int error;
+
+ error = xfile_load(blob->xfile, &key, sizeof(key), cookie);
+ if (error)
+ return error;
+
+ if (key.xb_magic != XB_KEY_MAGIC || key.xb_offset != cookie) {
+ ASSERT(0);
+ return -ENODATA;
+ }
+
+ xfile_discard(blob->xfile, cookie, sizeof(key) + key.xb_size);
+ return 0;
+}
diff --git a/fs/xfs/scrub/xfblob.h b/fs/xfs/scrub/xfblob.h
new file mode 100644
index 0000000000000..bd98647407f1d
--- /dev/null
+++ b/fs/xfs/scrub/xfblob.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2021-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_XFBLOB_H__
+#define __XFS_SCRUB_XFBLOB_H__
+
+struct xfblob {
+ struct xfile *xfile;
+ loff_t last_offset;
+};
+
+typedef loff_t xfblob_cookie;
+
+int xfblob_create(const char *descr, struct xfblob **blobp);
+void xfblob_destroy(struct xfblob *blob);
+int xfblob_load(struct xfblob *blob, xfblob_cookie cookie, void *ptr,
+ uint32_t size);
+int xfblob_store(struct xfblob *blob, xfblob_cookie *cookie, const void *ptr,
+ uint32_t size);
+int xfblob_free(struct xfblob *blob, xfblob_cookie cookie);
+
+#endif /* __XFS_SCRUB_XFBLOB_H__ */
diff --git a/fs/xfs/scrub/xfile.c b/fs/xfs/scrub/xfile.c
index 8cdd863db5850..459e513ade464 100644
--- a/fs/xfs/scrub/xfile.c
+++ b/fs/xfs/scrub/xfile.c
@@ -310,3 +310,15 @@ xfile_put_folio(
folio_unlock(folio);
folio_put(folio);
}
+
+/* Discard pages backing a range of the xfile. */
+void
+xfile_discard(
+ struct xfile *xf,
+ loff_t pos,
+ u64 count)
+{
+ trace_xfile_discard(xf, pos, count);
+
+ shmem_truncate_range(file_inode(xf->file), pos, pos + count - 1);
+}
diff --git a/fs/xfs/scrub/xfile.h b/fs/xfs/scrub/xfile.h
index 76d78dba7e347..8dfbae1fe33a5 100644
--- a/fs/xfs/scrub/xfile.h
+++ b/fs/xfs/scrub/xfile.h
@@ -17,6 +17,7 @@ int xfile_load(struct xfile *xf, void *buf, size_t count, loff_t pos);
int xfile_store(struct xfile *xf, const void *buf, size_t count,
loff_t pos);
+void xfile_discard(struct xfile *xf, loff_t pos, u64 count);
loff_t xfile_seek_data(struct xfile *xf, loff_t pos);
#define XFILE_MAX_FOLIO_SIZE (PAGE_SIZE << MAX_PAGECACHE_ORDER)
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH 2/6] xfs: use atomic extent swapping to fix user file fork data
2024-02-27 2:18 [PATCHSET v29.4 07/13] xfs: online repair of extended attributes Darrick J. Wong
2024-02-27 2:28 ` [PATCH 1/6] xfs: create a blob array data structure Darrick J. Wong
@ 2024-02-27 2:29 ` Darrick J. Wong
2024-02-28 16:01 ` Christoph Hellwig
2024-02-27 2:29 ` [PATCH 3/6] xfs: repair extended attributes Darrick J. Wong
` (3 subsequent siblings)
5 siblings, 1 reply; 16+ messages in thread
From: Darrick J. Wong @ 2024-02-27 2:29 UTC (permalink / raw
To: djwong; +Cc: linux-xfs, hch
From: Darrick J. Wong <djwong@kernel.org>
Build on the code that was recently added to the temporary repair file
code so that we can atomically switch the contents of any file fork,
even if the fork is in local format. The upcoming functions to repair
xattrs, directories, and symlinks will need that capability.
Repair can lock out access to these user files by holding IOLOCK_EXCL on
these user files. Therefore, it is safe to drop the ILOCK of both the
file being repaired and the tempfile being used for staging, and cancel
the scrub transaction. We do this so that we can reuse the resource
estimation and transaction allocation functions used by a regular file
exchange operation.
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
fs/xfs/libxfs/xfs_exchmaps.c | 2
fs/xfs/libxfs/xfs_exchmaps.h | 1
fs/xfs/scrub/tempexch.h | 2
fs/xfs/scrub/tempfile.c | 204 ++++++++++++++++++++++++++++++++++++++++++
fs/xfs/scrub/tempfile.h | 3 +
5 files changed, 211 insertions(+), 1 deletion(-)
diff --git a/fs/xfs/libxfs/xfs_exchmaps.c b/fs/xfs/libxfs/xfs_exchmaps.c
index 7502cb872aba2..9caafd98a223f 100644
--- a/fs/xfs/libxfs/xfs_exchmaps.c
+++ b/fs/xfs/libxfs/xfs_exchmaps.c
@@ -674,7 +674,7 @@ xfs_exchmaps_rmapbt_blocks(
}
/* Estimate the bmbt and rmapbt overhead required to exchange mappings. */
-static int
+int
xfs_exchmaps_estimate_overhead(
struct xfs_exchmaps_req *req)
{
diff --git a/fs/xfs/libxfs/xfs_exchmaps.h b/fs/xfs/libxfs/xfs_exchmaps.h
index d8718fca606e5..fa822dff202ad 100644
--- a/fs/xfs/libxfs/xfs_exchmaps.h
+++ b/fs/xfs/libxfs/xfs_exchmaps.h
@@ -97,6 +97,7 @@ xfs_exchmaps_reqfork(const struct xfs_exchmaps_req *req)
return XFS_DATA_FORK;
}
+int xfs_exchmaps_estimate_overhead(struct xfs_exchmaps_req *req);
int xfs_exchmaps_estimate(struct xfs_exchmaps_req *req);
extern struct kmem_cache *xfs_exchmaps_intent_cache;
diff --git a/fs/xfs/scrub/tempexch.h b/fs/xfs/scrub/tempexch.h
index 98222b684b6a0..c1dd4adec4f11 100644
--- a/fs/xfs/scrub/tempexch.h
+++ b/fs/xfs/scrub/tempexch.h
@@ -14,6 +14,8 @@ struct xrep_tempexch {
int xrep_tempexch_enable(struct xfs_scrub *sc);
int xrep_tempexch_trans_reserve(struct xfs_scrub *sc, int whichfork,
struct xrep_tempexch *ti);
+int xrep_tempexch_trans_alloc(struct xfs_scrub *sc, int whichfork,
+ struct xrep_tempexch *ti);
int xrep_tempexch_contents(struct xfs_scrub *sc, struct xrep_tempexch *ti);
#endif /* CONFIG_XFS_ONLINE_REPAIR */
diff --git a/fs/xfs/scrub/tempfile.c b/fs/xfs/scrub/tempfile.c
index 9ed750699809e..37f74486abde3 100644
--- a/fs/xfs/scrub/tempfile.c
+++ b/fs/xfs/scrub/tempfile.c
@@ -239,6 +239,28 @@ xrep_tempfile_iunlock(
sc->temp_ilock_flags &= ~XFS_ILOCK_EXCL;
}
+/*
+ * Begin the process of making changes to both the file being scrubbed and
+ * the temporary file by taking ILOCK_EXCL on both.
+ */
+void
+xrep_tempfile_ilock_both(
+ struct xfs_scrub *sc)
+{
+ xfs_lock_two_inodes(sc->ip, XFS_ILOCK_EXCL, sc->tempip, XFS_ILOCK_EXCL);
+ sc->ilock_flags |= XFS_ILOCK_EXCL;
+ sc->temp_ilock_flags |= XFS_ILOCK_EXCL;
+}
+
+/* Unlock ILOCK_EXCL on both files. */
+void
+xrep_tempfile_iunlock_both(
+ struct xfs_scrub *sc)
+{
+ xrep_tempfile_iunlock(sc);
+ xchk_iunlock(sc, XFS_ILOCK_EXCL);
+}
+
/* Release the temporary file. */
void
xrep_tempfile_rele(
@@ -517,6 +539,89 @@ xrep_tempexch_prep_request(
return 0;
}
+/*
+ * Fill out the mapping exchange resource estimation structures in preparation
+ * for exchanging the contents of a metadata file that we've rebuilt in the
+ * temp file. Caller must hold IOLOCK_EXCL but not ILOCK_EXCL on both files.
+ */
+STATIC int
+xrep_tempexch_estimate(
+ struct xfs_scrub *sc,
+ struct xrep_tempexch *tx)
+{
+ struct xfs_exchmaps_req *req = &tx->req;
+ struct xfs_ifork *ifp;
+ struct xfs_ifork *tifp;
+ int whichfork = xfs_exchmaps_reqfork(req);
+ int state = 0;
+
+ /*
+ * The exchmaps code only knows how to exchange file fork space
+ * mappings. Any fork data in local format must be promoted to a
+ * single block before the exchange can take place.
+ */
+ ifp = xfs_ifork_ptr(sc->ip, whichfork);
+ if (ifp->if_format == XFS_DINODE_FMT_LOCAL)
+ state |= 1;
+
+ tifp = xfs_ifork_ptr(sc->tempip, whichfork);
+ if (tifp->if_format == XFS_DINODE_FMT_LOCAL)
+ state |= 2;
+
+ switch (state) {
+ case 0:
+ /* Both files have mapped extents; use the regular estimate. */
+ return xfs_exchrange_estimate(req);
+ case 1:
+ /*
+ * The file being repaired is in local format, but the temp
+ * file has mapped extents. To perform the exchange, the file
+ * being repaired must have its shorform data converted to an
+ * ondisk block so that the forks will be in extents format.
+ * We need one resblk for the conversion; the number of
+ * exchanges is (worst case) the temporary file's extent count
+ * plus the block we converted.
+ */
+ req->ip1_bcount = sc->tempip->i_nblocks;
+ req->ip2_bcount = 1;
+ req->nr_exchanges = 1 + tifp->if_nextents;
+ req->resblks = 1;
+ break;
+ case 2:
+ /*
+ * The temporary file is in local format, but the file being
+ * repaired has mapped extents. To perform the exchange, the
+ * temp file must have its shortform data converted to an
+ * ondisk block, and the fork changed to extents format. We
+ * need one resblk for the conversion; the number of exchanges
+ * is (worst case) the extent count of the file being repaired
+ * plus the block we converted.
+ */
+ req->ip1_bcount = 1;
+ req->ip2_bcount = sc->ip->i_nblocks;
+ req->nr_exchanges = 1 + ifp->if_nextents;
+ req->resblks = 1;
+ break;
+ case 3:
+ /*
+ * Both forks are in local format. To perform the exchange,
+ * both files must have their shortform data converted to
+ * fsblocks, and both forks must be converted to extents
+ * format. We need two resblks for the two conversions, and
+ * the number of exchanges is 1 since there's only one block at
+ * fileoff 0. Presumably, the caller could not exchange the
+ * two inode fork areas directly.
+ */
+ req->ip1_bcount = 1;
+ req->ip2_bcount = 1;
+ req->nr_exchanges = 1;
+ req->resblks = 2;
+ break;
+ }
+
+ return xfs_exchmaps_estimate_overhead(req);
+}
+
/*
* Obtain a quota reservation to make sure we don't hit EDQUOT. We can skip
* this if quota enforcement is disabled or if both inodes' dquots are the
@@ -607,6 +712,55 @@ xrep_tempexch_trans_reserve(
return xrep_tempexch_reserve_quota(sc, tx);
}
+/*
+ * Create a new transaction for a file contents exchange.
+ *
+ * This function fills out the mapping excahange request and resource
+ * estimation structures in preparation for exchanging the contents of a
+ * metadata file that has been rebuilt in the temp file. Next, it reserves
+ * space, takes ILOCK_EXCL of both inodes, joins them to the transaction and
+ * reserves quota for the transaction.
+ *
+ * The caller is responsible for dropping both ILOCKs when appropriate.
+ */
+int
+xrep_tempexch_trans_alloc(
+ struct xfs_scrub *sc,
+ int whichfork,
+ struct xrep_tempexch *tx)
+{
+ unsigned int flags = 0;
+ int error;
+
+ ASSERT(sc->tp == NULL);
+
+ error = xrep_tempexch_prep_request(sc, whichfork, tx);
+ if (error)
+ return error;
+
+ error = xrep_tempexch_estimate(sc, tx);
+ if (error)
+ return error;
+
+ if (xfs_has_lazysbcount(sc->mp))
+ flags |= XFS_TRANS_RES_FDBLKS;
+
+ error = xrep_tempexch_enable(sc);
+ if (error)
+ return error;
+
+ error = xfs_trans_alloc(sc->mp, &M_RES(sc->mp)->tr_itruncate,
+ tx->req.resblks, 0, flags, &sc->tp);
+ if (error)
+ return error;
+
+ sc->temp_ilock_flags |= XFS_ILOCK_EXCL;
+ sc->ilock_flags |= XFS_ILOCK_EXCL;
+ xfs_exchrange_ilock(sc->tp, sc->ip, sc->tempip);
+
+ return xrep_tempexch_reserve_quota(sc, tx);
+}
+
/*
* Exchange file mappings (and hence file contents) between the file being
* repaired and the temporary file. Returns with both inodes locked and joined
@@ -640,3 +794,53 @@ xrep_tempexch_contents(
return 0;
}
+
+/*
+ * Write local format data from one of the temporary file's forks into the same
+ * fork of file being repaired, and exchange the file sizes, if appropriate.
+ * Caller must ensure that the file being repaired has enough fork space to
+ * hold all the bytes.
+ */
+void
+xrep_tempfile_copyout_local(
+ struct xfs_scrub *sc,
+ int whichfork)
+{
+ struct xfs_ifork *temp_ifp;
+ struct xfs_ifork *ifp;
+ unsigned int ilog_flags = XFS_ILOG_CORE;
+
+ temp_ifp = xfs_ifork_ptr(sc->tempip, whichfork);
+ ifp = xfs_ifork_ptr(sc->ip, whichfork);
+
+ ASSERT(temp_ifp != NULL);
+ ASSERT(ifp != NULL);
+ ASSERT(temp_ifp->if_format == XFS_DINODE_FMT_LOCAL);
+ ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
+
+ switch (whichfork) {
+ case XFS_DATA_FORK:
+ ASSERT(sc->tempip->i_disk_size <=
+ xfs_inode_data_fork_size(sc->ip));
+ break;
+ case XFS_ATTR_FORK:
+ ASSERT(sc->tempip->i_forkoff >= sc->ip->i_forkoff);
+ break;
+ default:
+ ASSERT(0);
+ return;
+ }
+
+ /* Recreate @sc->ip's incore fork (ifp) with data from temp_ifp. */
+ xfs_idestroy_fork(ifp);
+ xfs_init_local_fork(sc->ip, whichfork, temp_ifp->if_data,
+ temp_ifp->if_bytes);
+
+ if (whichfork == XFS_DATA_FORK) {
+ i_size_write(VFS_I(sc->ip), i_size_read(VFS_I(sc->tempip)));
+ sc->ip->i_disk_size = sc->tempip->i_disk_size;
+ }
+
+ ilog_flags |= xfs_ilog_fdata(whichfork);
+ xfs_trans_log_inode(sc->tp, sc->ip, ilog_flags);
+}
diff --git a/fs/xfs/scrub/tempfile.h b/fs/xfs/scrub/tempfile.h
index 7980f9c4de552..d57e4f145a7c8 100644
--- a/fs/xfs/scrub/tempfile.h
+++ b/fs/xfs/scrub/tempfile.h
@@ -17,6 +17,8 @@ void xrep_tempfile_iounlock(struct xfs_scrub *sc);
void xrep_tempfile_ilock(struct xfs_scrub *sc);
bool xrep_tempfile_ilock_nowait(struct xfs_scrub *sc);
void xrep_tempfile_iunlock(struct xfs_scrub *sc);
+void xrep_tempfile_iunlock_both(struct xfs_scrub *sc);
+void xrep_tempfile_ilock_both(struct xfs_scrub *sc);
int xrep_tempfile_prealloc(struct xfs_scrub *sc, xfs_fileoff_t off,
xfs_filblks_t len);
@@ -32,6 +34,7 @@ int xrep_tempfile_copyin(struct xfs_scrub *sc, xfs_fileoff_t off,
int xrep_tempfile_set_isize(struct xfs_scrub *sc, unsigned long long isize);
int xrep_tempfile_roll_trans(struct xfs_scrub *sc);
+void xrep_tempfile_copyout_local(struct xfs_scrub *sc, int whichfork);
#else
static inline void xrep_tempfile_iolock_both(struct xfs_scrub *sc)
{
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH 3/6] xfs: repair extended attributes
2024-02-27 2:18 [PATCHSET v29.4 07/13] xfs: online repair of extended attributes Darrick J. Wong
2024-02-27 2:28 ` [PATCH 1/6] xfs: create a blob array data structure Darrick J. Wong
2024-02-27 2:29 ` [PATCH 2/6] xfs: use atomic extent swapping to fix user file fork data Darrick J. Wong
@ 2024-02-27 2:29 ` Darrick J. Wong
2024-02-28 17:05 ` Christoph Hellwig
2024-02-27 2:29 ` [PATCH 4/6] xfs: scrub should set preen if attr leaf has holes Darrick J. Wong
` (2 subsequent siblings)
5 siblings, 1 reply; 16+ messages in thread
From: Darrick J. Wong @ 2024-02-27 2:29 UTC (permalink / raw
To: djwong; +Cc: linux-xfs, hch
From: Darrick J. Wong <djwong@kernel.org>
If the extended attributes look bad, try to sift through the rubble to
find whatever keys/values we can, stage a new attribute structure in a
temporary file and use the atomic extent swapping mechanism to commit
the results in bulk.
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
fs/xfs/Makefile | 1
fs/xfs/libxfs/xfs_attr.c | 2
fs/xfs/libxfs/xfs_attr.h | 2
fs/xfs/libxfs/xfs_da_format.h | 5
fs/xfs/scrub/attr.c | 20 +
fs/xfs/scrub/attr.h | 7
fs/xfs/scrub/attr_repair.c | 1205 +++++++++++++++++++++++++++++++++++++++++
fs/xfs/scrub/attr_repair.h | 11
fs/xfs/scrub/repair.c | 46 ++
fs/xfs/scrub/repair.h | 6
fs/xfs/scrub/scrub.c | 2
fs/xfs/scrub/trace.h | 83 +++
fs/xfs/scrub/xfarray.c | 17 +
fs/xfs/scrub/xfarray.h | 2
fs/xfs/scrub/xfblob.c | 17 +
fs/xfs/scrub/xfblob.h | 2
fs/xfs/scrub/xfile.h | 5
fs/xfs/xfs_buf.c | 3
fs/xfs/xfs_trace.h | 2
19 files changed, 1434 insertions(+), 4 deletions(-)
create mode 100644 fs/xfs/scrub/attr_repair.c
create mode 100644 fs/xfs/scrub/attr_repair.h
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 91af9b7f418e9..41f9d78ecd39e 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -195,6 +195,7 @@ ifeq ($(CONFIG_XFS_ONLINE_REPAIR),y)
xfs-y += $(addprefix scrub/, \
agheader_repair.o \
alloc_repair.o \
+ attr_repair.o \
bmap_repair.o \
cow_repair.o \
fscounters_repair.o \
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 732e9df4fefc7..d1a36af321c6d 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -1050,7 +1050,7 @@ xfs_attr_set(
* External routines when attribute list is inside the inode
*========================================================================*/
-static inline int xfs_attr_sf_totsize(struct xfs_inode *dp)
+int xfs_attr_sf_totsize(struct xfs_inode *dp)
{
struct xfs_attr_sf_hdr *sf = dp->i_af.if_data;
diff --git a/fs/xfs/libxfs/xfs_attr.h b/fs/xfs/libxfs/xfs_attr.h
index 81be9b3e40047..e4f55008552b4 100644
--- a/fs/xfs/libxfs/xfs_attr.h
+++ b/fs/xfs/libxfs/xfs_attr.h
@@ -618,4 +618,6 @@ extern struct kmem_cache *xfs_attr_intent_cache;
int __init xfs_attr_intent_init_cache(void);
void xfs_attr_intent_destroy_cache(void);
+int xfs_attr_sf_totsize(struct xfs_inode *dp);
+
#endif /* __XFS_ATTR_H__ */
diff --git a/fs/xfs/libxfs/xfs_da_format.h b/fs/xfs/libxfs/xfs_da_format.h
index 060e5c96b70f6..aac3fe0396140 100644
--- a/fs/xfs/libxfs/xfs_da_format.h
+++ b/fs/xfs/libxfs/xfs_da_format.h
@@ -721,6 +721,11 @@ struct xfs_attr3_leafblock {
#define XFS_ATTR_INCOMPLETE (1u << XFS_ATTR_INCOMPLETE_BIT)
#define XFS_ATTR_NSP_ONDISK_MASK (XFS_ATTR_ROOT | XFS_ATTR_SECURE)
+#define XFS_ATTR_NAMESPACE_STR \
+ { XFS_ATTR_LOCAL, "local" }, \
+ { XFS_ATTR_ROOT, "root" }, \
+ { XFS_ATTR_SECURE, "secure" }
+
/*
* Alignment for namelist and valuelist entries (since they are mixed
* there can be only one alignment value)
diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c
index 0c467f4f8e778..7621e548d7301 100644
--- a/fs/xfs/scrub/attr.c
+++ b/fs/xfs/scrub/attr.c
@@ -10,6 +10,7 @@
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_log_format.h"
+#include "xfs_trans.h"
#include "xfs_inode.h"
#include "xfs_da_format.h"
#include "xfs_da_btree.h"
@@ -20,6 +21,7 @@
#include "scrub/common.h"
#include "scrub/dabtree.h"
#include "scrub/attr.h"
+#include "scrub/repair.h"
/* Free the buffers linked from the xattr buffer. */
static void
@@ -35,6 +37,8 @@ xchk_xattr_buf_cleanup(
kvfree(ab->value);
ab->value = NULL;
ab->value_sz = 0;
+ kvfree(ab->name);
+ ab->name = NULL;
}
/*
@@ -65,7 +69,7 @@ xchk_xattr_want_freemap(
* reallocating the buffer if necessary. Buffer contents are not preserved
* across a reallocation.
*/
-static int
+int
xchk_setup_xattr_buf(
struct xfs_scrub *sc,
size_t value_size)
@@ -95,6 +99,12 @@ xchk_setup_xattr_buf(
return -ENOMEM;
}
+ if (xchk_could_repair(sc)) {
+ ab->name = kvmalloc(XATTR_NAME_MAX + 1, XCHK_GFP_FLAGS);
+ if (!ab->name)
+ return -ENOMEM;
+ }
+
resize_value:
if (ab->value_sz >= value_size)
return 0;
@@ -121,6 +131,12 @@ xchk_setup_xattr(
{
int error;
+ if (xchk_could_repair(sc)) {
+ error = xrep_setup_xattr(sc);
+ if (error)
+ return error;
+ }
+
/*
* We failed to get memory while checking attrs, so this time try to
* get all the memory we're ever going to need. Allocate the buffer
@@ -247,7 +263,7 @@ xchk_xattr_listent(
* Within a char, the lowest bit of the char represents the byte with
* the smallest address
*/
-STATIC bool
+bool
xchk_xattr_set_map(
struct xfs_scrub *sc,
unsigned long *map,
diff --git a/fs/xfs/scrub/attr.h b/fs/xfs/scrub/attr.h
index 48fd9402c4328..7db58af56646b 100644
--- a/fs/xfs/scrub/attr.h
+++ b/fs/xfs/scrub/attr.h
@@ -16,9 +16,16 @@ struct xchk_xattr_buf {
/* Bitmap of free space in xattr leaf blocks. */
unsigned long *freemap;
+ /* Memory buffer used to hold salvaged xattr names. */
+ unsigned char *name;
+
/* Memory buffer used to extract xattr values. */
void *value;
size_t value_sz;
};
+bool xchk_xattr_set_map(struct xfs_scrub *sc, unsigned long *map,
+ unsigned int start, unsigned int len);
+int xchk_setup_xattr_buf(struct xfs_scrub *sc, size_t value_size);
+
#endif /* __XFS_SCRUB_ATTR_H__ */
diff --git a/fs/xfs/scrub/attr_repair.c b/fs/xfs/scrub/attr_repair.c
new file mode 100644
index 0000000000000..4c996458ba1c3
--- /dev/null
+++ b/fs/xfs/scrub/attr_repair.c
@@ -0,0 +1,1205 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2018-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_dir2.h"
+#include "xfs_attr.h"
+#include "xfs_attr_leaf.h"
+#include "xfs_attr_sf.h"
+#include "xfs_attr_remote.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_util.h"
+#include "xfs_exchmaps.h"
+#include "xfs_exchrange.h"
+#include "xfs_acl.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/tempfile.h"
+#include "scrub/tempexch.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
+#include "scrub/xfblob.h"
+#include "scrub/attr.h"
+#include "scrub/reap.h"
+#include "scrub/attr_repair.h"
+
+/*
+ * Extended Attribute Repair
+ * =========================
+ *
+ * We repair extended attributes by reading the attr leaf blocks looking for
+ * attributes entries that look salvageable (name passes verifiers, value can
+ * be retrieved, etc). Each extended attribute worth salvaging is stashed in
+ * memory, and the stashed entries are periodically replayed into a temporary
+ * file to constrain memory use. Batching the construction of the temporary
+ * extended attribute structure in this fashion reduces lock cycling of the
+ * file being repaired and the temporary file.
+ *
+ * When salvaging completes, the remaining stashed attributes are replayed to
+ * the temporary file. An atomic file contents exchange is used to commit the
+ * new xattr blocks to the file being repaired. This will disrupt attrmulti
+ * cursors.
+ */
+
+struct xrep_xattr_key {
+ /* Cookie for retrieval of the xattr name. */
+ xfblob_cookie name_cookie;
+
+ /* Cookie for retrieval of the xattr value. */
+ xfblob_cookie value_cookie;
+
+ /* XFS_ATTR_* flags */
+ int flags;
+
+ /* Length of the value and name. */
+ uint32_t valuelen;
+ uint16_t namelen;
+};
+
+/*
+ * Stash up to 8 pages of attrs in xattr_records/xattr_blobs before we write
+ * them to the temp file.
+ */
+#define XREP_XATTR_MAX_STASH_BYTES (PAGE_SIZE * 8)
+
+struct xrep_xattr {
+ struct xfs_scrub *sc;
+
+ /* Information for exchanging attr fork mappings at the end. */
+ struct xrep_tempexch tx;
+
+ /* xattr keys */
+ struct xfarray *xattr_records;
+
+ /* xattr values */
+ struct xfblob *xattr_blobs;
+
+ /* Number of attributes that we are salvaging. */
+ unsigned long long attrs_found;
+};
+
+/* Set up to recreate the extended attributes. */
+int
+xrep_setup_xattr(
+ struct xfs_scrub *sc)
+{
+ return xrep_tempfile_create(sc, S_IFREG);
+}
+
+/*
+ * Decide if we want to salvage this attribute. We don't bother with
+ * incomplete or oversized keys or values. The @value parameter can be null
+ * for remote attrs.
+ */
+STATIC int
+xrep_xattr_want_salvage(
+ struct xrep_xattr *rx,
+ unsigned int attr_flags,
+ const void *name,
+ int namelen,
+ const void *value,
+ int valuelen)
+{
+ if (attr_flags & XFS_ATTR_INCOMPLETE)
+ return false;
+ if (namelen > XATTR_NAME_MAX || namelen <= 0)
+ return false;
+ if (valuelen > XATTR_SIZE_MAX || valuelen < 0)
+ return false;
+ return true;
+}
+
+/* Allocate an in-core record to hold xattrs while we rebuild the xattr data. */
+STATIC int
+xrep_xattr_salvage_key(
+ struct xrep_xattr *rx,
+ int flags,
+ unsigned char *name,
+ int namelen,
+ unsigned char *value,
+ int valuelen)
+{
+ struct xrep_xattr_key key = {
+ .valuelen = valuelen,
+ .flags = flags & XFS_ATTR_NSP_ONDISK_MASK,
+ };
+ unsigned int i = 0;
+ int error = 0;
+
+ if (xchk_should_terminate(rx->sc, &error))
+ return error;
+
+ /*
+ * Truncate the name to the first character that would trip namecheck.
+ * If we no longer have a name after that, ignore this attribute.
+ */
+ while (i < namelen && name[i] != 0)
+ i++;
+ if (i == 0)
+ return 0;
+ key.namelen = i;
+
+ trace_xrep_xattr_salvage_rec(rx->sc->ip, flags, name, key.namelen,
+ valuelen);
+
+ error = xfblob_store(rx->xattr_blobs, &key.name_cookie, name,
+ key.namelen);
+ if (error)
+ return error;
+
+ error = xfblob_store(rx->xattr_blobs, &key.value_cookie, value,
+ key.valuelen);
+ if (error)
+ return error;
+
+ error = xfarray_append(rx->xattr_records, &key);
+ if (error)
+ return error;
+
+ rx->attrs_found++;
+ return 0;
+}
+
+/*
+ * Record a shortform extended attribute key & value for later reinsertion
+ * into the inode.
+ */
+STATIC int
+xrep_xattr_salvage_sf_attr(
+ struct xrep_xattr *rx,
+ struct xfs_attr_sf_hdr *hdr,
+ struct xfs_attr_sf_entry *sfe)
+{
+ struct xfs_scrub *sc = rx->sc;
+ struct xchk_xattr_buf *ab = sc->buf;
+ unsigned char *name = sfe->nameval;
+ unsigned char *value = &sfe->nameval[sfe->namelen];
+
+ if (!xchk_xattr_set_map(sc, ab->usedmap, (char *)name - (char *)hdr,
+ sfe->namelen))
+ return 0;
+
+ if (!xchk_xattr_set_map(sc, ab->usedmap, (char *)value - (char *)hdr,
+ sfe->valuelen))
+ return 0;
+
+ if (!xrep_xattr_want_salvage(rx, sfe->flags, sfe->nameval,
+ sfe->namelen, value, sfe->valuelen))
+ return 0;
+
+ return xrep_xattr_salvage_key(rx, sfe->flags, sfe->nameval,
+ sfe->namelen, value, sfe->valuelen);
+}
+
+/*
+ * Record a local format extended attribute key & value for later reinsertion
+ * into the inode.
+ */
+STATIC int
+xrep_xattr_salvage_local_attr(
+ struct xrep_xattr *rx,
+ struct xfs_attr_leaf_entry *ent,
+ unsigned int nameidx,
+ const char *buf_end,
+ struct xfs_attr_leaf_name_local *lentry)
+{
+ struct xchk_xattr_buf *ab = rx->sc->buf;
+ unsigned char *value;
+ unsigned int valuelen;
+ unsigned int namesize;
+
+ /*
+ * Decode the leaf local entry format. If something seems wrong, we
+ * junk the attribute.
+ */
+ value = &lentry->nameval[lentry->namelen];
+ valuelen = be16_to_cpu(lentry->valuelen);
+ namesize = xfs_attr_leaf_entsize_local(lentry->namelen, valuelen);
+ if ((char *)lentry + namesize > buf_end)
+ return 0;
+ if (!xrep_xattr_want_salvage(rx, ent->flags, lentry->nameval,
+ lentry->namelen, value, valuelen))
+ return 0;
+ if (!xchk_xattr_set_map(rx->sc, ab->usedmap, nameidx, namesize))
+ return 0;
+
+ /* Try to save this attribute. */
+ return xrep_xattr_salvage_key(rx, ent->flags, lentry->nameval,
+ lentry->namelen, value, valuelen);
+}
+
+/*
+ * Record a remote format extended attribute key & value for later reinsertion
+ * into the inode.
+ */
+STATIC int
+xrep_xattr_salvage_remote_attr(
+ struct xrep_xattr *rx,
+ struct xfs_attr_leaf_entry *ent,
+ unsigned int nameidx,
+ const char *buf_end,
+ struct xfs_attr_leaf_name_remote *rentry,
+ unsigned int ent_idx,
+ struct xfs_buf *leaf_bp)
+{
+ struct xfs_da_args args = {
+ .trans = rx->sc->tp,
+ .dp = rx->sc->ip,
+ .index = ent_idx,
+ .geo = rx->sc->mp->m_attr_geo,
+ .owner = rx->sc->ip->i_ino,
+ };
+ struct xchk_xattr_buf *ab = rx->sc->buf;
+ unsigned int valuelen;
+ unsigned int namesize;
+ int error;
+
+ /*
+ * Decode the leaf remote entry format. If something seems wrong, we
+ * junk the attribute. Note that we should never find a zero-length
+ * remote attribute value.
+ */
+ valuelen = be32_to_cpu(rentry->valuelen);
+ namesize = xfs_attr_leaf_entsize_remote(rentry->namelen);
+ if ((char *)rentry + namesize > buf_end)
+ return 0;
+ if (valuelen == 0 ||
+ !xrep_xattr_want_salvage(rx, ent->flags, rentry->name,
+ rentry->namelen, NULL, valuelen))
+ return 0;
+ if (!xchk_xattr_set_map(rx->sc, ab->usedmap, nameidx, namesize))
+ return 0;
+
+ /*
+ * Enlarge the buffer (if needed) to hold the value that we're trying
+ * to salvage from the old extended attribute data.
+ */
+ error = xchk_setup_xattr_buf(rx->sc, valuelen);
+ if (error == -ENOMEM)
+ error = -EDEADLOCK;
+ if (error)
+ return error;
+
+ /* Look up the remote value and stash it for reconstruction. */
+ args.valuelen = valuelen;
+ args.namelen = rentry->namelen;
+ args.name = rentry->name;
+ args.value = ab->value;
+ error = xfs_attr3_leaf_getvalue(leaf_bp, &args);
+ if (error || args.rmtblkno == 0)
+ goto err_free;
+
+ error = xfs_attr_rmtval_get(&args);
+ if (error)
+ goto err_free;
+
+ /* Try to save this attribute. */
+ error = xrep_xattr_salvage_key(rx, ent->flags, rentry->name,
+ rentry->namelen, ab->value, valuelen);
+err_free:
+ /* remote value was garbage, junk it */
+ if (error == -EFSBADCRC || error == -EFSCORRUPTED)
+ error = 0;
+ return error;
+}
+
+/* Extract every xattr key that we can from this attr fork block. */
+STATIC int
+xrep_xattr_recover_leaf(
+ struct xrep_xattr *rx,
+ struct xfs_buf *bp)
+{
+ struct xfs_attr3_icleaf_hdr leafhdr;
+ struct xfs_scrub *sc = rx->sc;
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_attr_leafblock *leaf;
+ struct xfs_attr_leaf_name_local *lentry;
+ struct xfs_attr_leaf_name_remote *rentry;
+ struct xfs_attr_leaf_entry *ent;
+ struct xfs_attr_leaf_entry *entries;
+ struct xchk_xattr_buf *ab = rx->sc->buf;
+ char *buf_end;
+ size_t off;
+ unsigned int nameidx;
+ unsigned int hdrsize;
+ int i;
+ int error = 0;
+
+ bitmap_zero(ab->usedmap, mp->m_attr_geo->blksize);
+
+ /* Check the leaf header */
+ leaf = bp->b_addr;
+ xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &leafhdr, leaf);
+ hdrsize = xfs_attr3_leaf_hdr_size(leaf);
+ xchk_xattr_set_map(sc, ab->usedmap, 0, hdrsize);
+ entries = xfs_attr3_leaf_entryp(leaf);
+
+ buf_end = (char *)bp->b_addr + mp->m_attr_geo->blksize;
+ for (i = 0, ent = entries; i < leafhdr.count; ent++, i++) {
+ if (xchk_should_terminate(sc, &error))
+ return error;
+
+ /* Skip key if it conflicts with something else? */
+ off = (char *)ent - (char *)leaf;
+ if (!xchk_xattr_set_map(sc, ab->usedmap, off,
+ sizeof(xfs_attr_leaf_entry_t)))
+ continue;
+
+ /* Check the name information. */
+ nameidx = be16_to_cpu(ent->nameidx);
+ if (nameidx < leafhdr.firstused ||
+ nameidx >= mp->m_attr_geo->blksize)
+ continue;
+
+ if (ent->flags & XFS_ATTR_LOCAL) {
+ lentry = xfs_attr3_leaf_name_local(leaf, i);
+ error = xrep_xattr_salvage_local_attr(rx, ent, nameidx,
+ buf_end, lentry);
+ } else {
+ rentry = xfs_attr3_leaf_name_remote(leaf, i);
+ error = xrep_xattr_salvage_remote_attr(rx, ent, nameidx,
+ buf_end, rentry, i, bp);
+ }
+ if (error)
+ return error;
+ }
+
+ return 0;
+}
+
+/* Try to recover shortform attrs. */
+STATIC int
+xrep_xattr_recover_sf(
+ struct xrep_xattr *rx)
+{
+ struct xfs_scrub *sc = rx->sc;
+ struct xchk_xattr_buf *ab = sc->buf;
+ struct xfs_attr_sf_hdr *hdr;
+ struct xfs_attr_sf_entry *sfe;
+ struct xfs_attr_sf_entry *next;
+ struct xfs_ifork *ifp;
+ unsigned char *end;
+ int i;
+ int error = 0;
+
+ ifp = xfs_ifork_ptr(rx->sc->ip, XFS_ATTR_FORK);
+ hdr = ifp->if_data;
+
+ bitmap_zero(ab->usedmap, ifp->if_bytes);
+ end = (unsigned char *)ifp->if_data + ifp->if_bytes;
+ xchk_xattr_set_map(sc, ab->usedmap, 0, sizeof(*hdr));
+
+ sfe = xfs_attr_sf_firstentry(hdr);
+ if ((unsigned char *)sfe > end)
+ return 0;
+
+ for (i = 0; i < hdr->count; i++) {
+ if (xchk_should_terminate(sc, &error))
+ return error;
+
+ next = xfs_attr_sf_nextentry(sfe);
+ if ((unsigned char *)next > end)
+ break;
+
+ if (xchk_xattr_set_map(sc, ab->usedmap,
+ (char *)sfe - (char *)hdr,
+ sizeof(struct xfs_attr_sf_entry))) {
+ /*
+ * No conflicts with the sf entry; let's save this
+ * attribute.
+ */
+ error = xrep_xattr_salvage_sf_attr(rx, hdr, sfe);
+ if (error)
+ return error;
+ }
+
+ sfe = next;
+ }
+
+ return 0;
+}
+
+/*
+ * Try to return a buffer of xattr data for a given physical extent.
+ *
+ * Because the buffer cache get function complains if it finds a buffer
+ * matching the block number but not matching the length, we must be careful to
+ * look for incore buffers (up to the maximum length of a remote value) that
+ * could be hiding anywhere in the physical range. If we find an incore
+ * buffer, we can pass that to the caller. Optionally, read a single block and
+ * pass that back.
+ *
+ * Note the subtlety that remote attr value blocks for which there is no incore
+ * buffer will be passed to the callback one block at a time. These buffers
+ * will not have any ops attached and must be staled to prevent aliasing with
+ * multiblock buffers once we drop the ILOCK.
+ */
+STATIC int
+xrep_xattr_find_buf(
+ struct xfs_mount *mp,
+ xfs_fsblock_t fsbno,
+ xfs_extlen_t max_len,
+ bool can_read,
+ struct xfs_buf **bpp)
+{
+ struct xrep_bufscan scan = {
+ .daddr = XFS_FSB_TO_DADDR(mp, fsbno),
+ .max_sectors = xrep_bufscan_max_sectors(mp, max_len),
+ .daddr_step = XFS_FSB_TO_BB(mp, 1),
+ };
+ struct xfs_buf *bp;
+
+ while ((bp = xrep_bufscan_advance(mp, &scan)) != NULL) {
+ *bpp = bp;
+ return 0;
+ }
+
+ if (!can_read) {
+ *bpp = NULL;
+ return 0;
+ }
+
+ return xfs_buf_read(mp->m_ddev_targp, scan.daddr, XFS_FSB_TO_BB(mp, 1),
+ XBF_TRYLOCK, bpp, NULL);
+}
+
+/*
+ * Deal with a buffer that we found during our walk of the attr fork.
+ *
+ * Attribute leaf and node blocks are simple -- they're a single block, so we
+ * can walk them one at a time and we never have to worry about discontiguous
+ * multiblock buffers like we do for directories.
+ *
+ * Unfortunately, remote attr blocks add a lot of complexity here. Each disk
+ * block is totally self contained, in the sense that the v5 header provides no
+ * indication that there could be more data in the next block. The incore
+ * buffers can span multiple blocks, though they never cross extent records.
+ * However, they don't necessarily start or end on an extent record boundary.
+ * Therefore, we need a special buffer find function to walk the buffer cache
+ * for us.
+ *
+ * The caller must hold the ILOCK on the file being repaired. We use
+ * XBF_TRYLOCK here to skip any locked buffer on the assumption that we don't
+ * own the block and don't want to hang the system on a potentially garbage
+ * buffer.
+ */
+STATIC int
+xrep_xattr_recover_block(
+ struct xrep_xattr *rx,
+ xfs_dablk_t dabno,
+ xfs_fsblock_t fsbno,
+ xfs_extlen_t max_len,
+ xfs_extlen_t *actual_len)
+{
+ struct xfs_da_blkinfo *info;
+ struct xfs_buf *bp;
+ int error;
+
+ error = xrep_xattr_find_buf(rx->sc->mp, fsbno, max_len, true, &bp);
+ if (error)
+ return error;
+ info = bp->b_addr;
+ *actual_len = XFS_BB_TO_FSB(rx->sc->mp, bp->b_length);
+
+ trace_xrep_xattr_recover_leafblock(rx->sc->ip, dabno,
+ be16_to_cpu(info->magic));
+
+ /*
+ * If the buffer has the right magic number for an attr leaf block and
+ * passes a structure check (we don't care about checksums), salvage
+ * as much as we can from the block. */
+ if (info->magic == cpu_to_be16(XFS_ATTR3_LEAF_MAGIC) &&
+ xrep_buf_verify_struct(bp, &xfs_attr3_leaf_buf_ops) &&
+ xfs_attr3_leaf_header_check(bp, rx->sc->ip->i_ino) == NULL)
+ error = xrep_xattr_recover_leaf(rx, bp);
+
+ /*
+ * If the buffer didn't already have buffer ops set, it was read in by
+ * the _find_buf function and could very well be /part/ of a multiblock
+ * remote block. Mark it stale so that it doesn't hang around in
+ * memory to cause problems.
+ */
+ if (bp->b_ops == NULL)
+ xfs_buf_stale(bp);
+
+ xfs_buf_relse(bp);
+ return error;
+}
+
+/* Insert one xattr key/value. */
+STATIC int
+xrep_xattr_insert_rec(
+ struct xrep_xattr *rx,
+ const struct xrep_xattr_key *key)
+{
+ struct xfs_da_args args = {
+ .dp = rx->sc->tempip,
+ .attr_filter = key->flags,
+ .attr_flags = XATTR_CREATE,
+ .namelen = key->namelen,
+ .valuelen = key->valuelen,
+ .op_flags = XFS_DA_OP_NOTIME,
+ .owner = rx->sc->ip->i_ino,
+ };
+ struct xchk_xattr_buf *ab = rx->sc->buf;
+ int error;
+
+ /*
+ * Grab pointers to the scrub buffer so that we can use them to insert
+ * attrs into the temp file.
+ */
+ args.name = ab->name;
+ args.value = ab->value;
+
+ /*
+ * The attribute name is stored near the end of the in-core buffer,
+ * though we reserve one more byte to ensure null termination.
+ */
+ ab->name[XATTR_NAME_MAX] = 0;
+
+ error = xfblob_load(rx->xattr_blobs, key->name_cookie, ab->name,
+ key->namelen);
+ if (error)
+ return error;
+
+ error = xfblob_free(rx->xattr_blobs, key->name_cookie);
+ if (error)
+ return error;
+
+ error = xfblob_load(rx->xattr_blobs, key->value_cookie, args.value,
+ key->valuelen);
+ if (error)
+ return error;
+
+ error = xfblob_free(rx->xattr_blobs, key->value_cookie);
+ if (error)
+ return error;
+
+ ab->name[key->namelen] = 0;
+
+ trace_xrep_xattr_insert_rec(rx->sc->tempip, key->flags, ab->name,
+ key->namelen, key->valuelen);
+
+ /*
+ * xfs_attr_set creates and commits its own transaction. If the attr
+ * already exists, we'll just drop it during the rebuild.
+ */
+ error = xfs_attr_set(&args);
+ if (error == -EEXIST)
+ error = 0;
+
+ return error;
+}
+
+/*
+ * Periodically flush salvaged attributes to the temporary file. This is done
+ * to reduce the memory requirements of the xattr rebuild because files can
+ * contain millions of attributes.
+ */
+STATIC int
+xrep_xattr_flush_stashed(
+ struct xrep_xattr *rx)
+{
+ xfarray_idx_t array_cur;
+ int error;
+
+ /*
+ * Entering this function, the scrub context has a reference to the
+ * inode being repaired, the temporary file, and a scrub transaction
+ * that we use during xattr salvaging to avoid livelocking if there
+ * are cycles in the xattr structures. We hold ILOCK_EXCL on both
+ * the inode being repaired, though it is not ijoined to the scrub
+ * transaction.
+ *
+ * To constrain kernel memory use, we occasionally flush salvaged
+ * xattrs from the xfarray and xfblob structures into the temporary
+ * file in preparation for exchanging the xattr structures at the end.
+ * Updating the temporary file requires a transaction, so we commit the
+ * scrub transaction and drop the two ILOCKs so that xfs_attr_set can
+ * allocate whatever transaction it wants.
+ *
+ * We still hold IOLOCK_EXCL on the inode being repaired, which
+ * prevents anyone from modifying the damaged xattr data while we
+ * repair it.
+ */
+ error = xrep_trans_commit(rx->sc);
+ if (error)
+ return error;
+ xchk_iunlock(rx->sc, XFS_ILOCK_EXCL);
+
+ /*
+ * Take the IOLOCK of the temporary file while we modify xattrs. This
+ * isn't strictly required because the temporary file is never revealed
+ * to userspace, but we follow the same locking rules. We still hold
+ * sc->ip's IOLOCK.
+ */
+ error = xrep_tempfile_iolock_polled(rx->sc);
+ if (error)
+ return error;
+
+ /* Add all the salvaged attrs to the temporary file. */
+ foreach_xfarray_idx(rx->xattr_records, array_cur) {
+ struct xrep_xattr_key key;
+
+ error = xfarray_load(rx->xattr_records, array_cur, &key);
+ if (error)
+ return error;
+
+ error = xrep_xattr_insert_rec(rx, &key);
+ if (error)
+ return error;
+ }
+
+ /* Empty out both arrays now that we've added the entries. */
+ xfarray_truncate(rx->xattr_records);
+ xfblob_truncate(rx->xattr_blobs);
+
+ xrep_tempfile_iounlock(rx->sc);
+
+ /* Recreate the salvage transaction and relock the inode. */
+ error = xchk_trans_alloc(rx->sc, 0);
+ if (error)
+ return error;
+ xchk_ilock(rx->sc, XFS_ILOCK_EXCL);
+ return 0;
+}
+
+/* Decide if we've stashed too much xattr data in memory. */
+static inline bool
+xrep_xattr_want_flush_stashed(
+ struct xrep_xattr *rx)
+{
+ unsigned long long bytes;
+
+ bytes = xfarray_bytes(rx->xattr_records) +
+ xfblob_bytes(rx->xattr_blobs);
+ return bytes > XREP_XATTR_MAX_STASH_BYTES;
+}
+
+/* Extract as many attribute keys and values as we can. */
+STATIC int
+xrep_xattr_recover(
+ struct xrep_xattr *rx)
+{
+ struct xfs_bmbt_irec got;
+ struct xfs_scrub *sc = rx->sc;
+ struct xfs_da_geometry *geo = sc->mp->m_attr_geo;
+ xfs_fileoff_t offset;
+ xfs_extlen_t len;
+ xfs_dablk_t dabno;
+ int nmap;
+ int error;
+
+ /*
+ * Iterate each xattr leaf block in the attr fork to scan them for any
+ * attributes that we might salvage.
+ */
+ for (offset = 0;
+ offset < XFS_MAX_FILEOFF;
+ offset = got.br_startoff + got.br_blockcount) {
+ nmap = 1;
+ error = xfs_bmapi_read(sc->ip, offset, XFS_MAX_FILEOFF - offset,
+ &got, &nmap, XFS_BMAPI_ATTRFORK);
+ if (error)
+ return error;
+ if (nmap != 1)
+ return -EFSCORRUPTED;
+ if (!xfs_bmap_is_written_extent(&got))
+ continue;
+
+ for (dabno = round_up(got.br_startoff, geo->fsbcount);
+ dabno < got.br_startoff + got.br_blockcount;
+ dabno += len) {
+ xfs_fileoff_t curr_offset = dabno - got.br_startoff;
+ xfs_extlen_t maxlen;
+
+ if (xchk_should_terminate(rx->sc, &error))
+ return error;
+
+ maxlen = min_t(xfs_filblks_t, INT_MAX,
+ got.br_blockcount - curr_offset);
+ error = xrep_xattr_recover_block(rx, dabno,
+ curr_offset + got.br_startblock,
+ maxlen, &len);
+ if (error)
+ return error;
+
+ if (xrep_xattr_want_flush_stashed(rx)) {
+ error = xrep_xattr_flush_stashed(rx);
+ if (error)
+ return error;
+ }
+ }
+ }
+
+ return 0;
+}
+
+/*
+ * Reset the extended attribute fork to a state where we can start re-adding
+ * the salvaged attributes.
+ */
+STATIC int
+xrep_xattr_fork_remove(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip)
+{
+ struct xfs_attr_sf_hdr *hdr;
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_ATTR_FORK);
+
+ /*
+ * If the data fork is in btree format, we can't change di_forkoff
+ * because we could run afoul of the rule that the data fork isn't
+ * supposed to be in btree format if there's enough space in the fork
+ * that it could have used extents format. Instead, reinitialize the
+ * attr fork to have a shortform structure with zero attributes.
+ */
+ if (ip->i_df.if_format == XFS_DINODE_FMT_BTREE) {
+ ifp->if_format = XFS_DINODE_FMT_LOCAL;
+ hdr = xfs_idata_realloc(ip, (int)sizeof(*hdr) - ifp->if_bytes,
+ XFS_ATTR_FORK);
+ hdr->count = 0;
+ hdr->totsize = cpu_to_be16(sizeof(*hdr));
+ xfs_trans_log_inode(sc->tp, ip,
+ XFS_ILOG_CORE | XFS_ILOG_ADATA);
+ return 0;
+ }
+
+ /* If we still have attr fork extents, something's wrong. */
+ if (ifp->if_nextents != 0) {
+ struct xfs_iext_cursor icur;
+ struct xfs_bmbt_irec irec;
+ unsigned int i = 0;
+
+ xfs_emerg(sc->mp,
+ "inode 0x%llx attr fork still has %llu attr extents, format %d?!",
+ ip->i_ino, ifp->if_nextents, ifp->if_format);
+ for_each_xfs_iext(ifp, &icur, &irec) {
+ xfs_err(sc->mp,
+ "[%u]: startoff %llu startblock %llu blockcount %llu state %u",
+ i++, irec.br_startoff,
+ irec.br_startblock, irec.br_blockcount,
+ irec.br_state);
+ }
+ ASSERT(0);
+ return -EFSCORRUPTED;
+ }
+
+ xfs_attr_fork_remove(ip, sc->tp);
+ return 0;
+}
+
+/*
+ * Free all the attribute fork blocks of the file being repaired and delete the
+ * fork. The caller must ILOCK the scrub file and join it to the transaction.
+ * This function returns with the inode joined to a clean transaction.
+ */
+int
+xrep_xattr_reset_fork(
+ struct xfs_scrub *sc)
+{
+ int error;
+
+ trace_xrep_xattr_reset_fork(sc->ip, sc->ip);
+
+ /* Unmap all the attr blocks. */
+ if (xfs_ifork_has_extents(&sc->ip->i_af)) {
+ error = xrep_reap_ifork(sc, sc->ip, XFS_ATTR_FORK);
+ if (error)
+ return error;
+ }
+
+ error = xrep_xattr_fork_remove(sc, sc->ip);
+ if (error)
+ return error;
+
+ return xfs_trans_roll_inode(&sc->tp, sc->ip);
+}
+
+/*
+ * Free all the attribute fork blocks of the temporary file and delete the attr
+ * fork. The caller must ILOCK the tempfile and join it to the transaction.
+ * This function returns with the inode joined to a clean scrub transaction.
+ */
+STATIC int
+xrep_xattr_reset_tempfile_fork(
+ struct xfs_scrub *sc)
+{
+ int error;
+
+ trace_xrep_xattr_reset_fork(sc->ip, sc->tempip);
+
+ /*
+ * Wipe out the attr fork of the temp file so that regular inode
+ * inactivation won't trip over the corrupt attr fork.
+ */
+ if (xfs_ifork_has_extents(&sc->tempip->i_af)) {
+ error = xrep_reap_ifork(sc, sc->tempip, XFS_ATTR_FORK);
+ if (error)
+ return error;
+ }
+
+ return xrep_xattr_fork_remove(sc, sc->tempip);
+}
+
+/*
+ * Find all the extended attributes for this inode by scraping them out of the
+ * attribute key blocks by hand, and flushing them into the temp file.
+ * When we're done, free the staging memory before exchanging the xattr
+ * structures to reduce memory usage.
+ */
+STATIC int
+xrep_xattr_salvage_attributes(
+ struct xrep_xattr *rx)
+{
+ struct xfs_inode *ip = rx->sc->ip;
+ int error;
+
+ /* Short format xattrs are easy! */
+ if (rx->sc->ip->i_af.if_format == XFS_DINODE_FMT_LOCAL) {
+ error = xrep_xattr_recover_sf(rx);
+ if (error)
+ return error;
+
+ return xrep_xattr_flush_stashed(rx);
+ }
+
+ /*
+ * For non-inline xattr structures, the salvage function scans the
+ * buffer cache looking for potential attr leaf blocks. The scan
+ * requires the ability to lock any buffer found and runs independently
+ * of any transaction <-> buffer item <-> buffer linkage. Therefore,
+ * roll the transaction to ensure there are no buffers joined. We hold
+ * the ILOCK independently of the transaction.
+ */
+ error = xfs_trans_roll(&rx->sc->tp);
+ if (error)
+ return error;
+
+ error = xfs_iread_extents(rx->sc->tp, ip, XFS_ATTR_FORK);
+ if (error)
+ return error;
+
+ error = xrep_xattr_recover(rx);
+ if (error)
+ return error;
+
+ return xrep_xattr_flush_stashed(rx);
+}
+
+/*
+ * Prepare both inodes' attribute forks for an exchange. Promote the tempfile
+ * from short format to leaf format, and if the file being repaired has a short
+ * format attr fork, turn it into an empty extent list.
+ */
+STATIC int
+xrep_xattr_swap_prep(
+ struct xfs_scrub *sc,
+ bool temp_local,
+ bool ip_local)
+{
+ int error;
+
+ /*
+ * If the tempfile's attributes are in shortform format, convert that
+ * to a single leaf extent so that we can use the atomic mapping
+ * exchange.
+ */
+ if (temp_local) {
+ struct xfs_da_args args = {
+ .dp = sc->tempip,
+ .geo = sc->mp->m_attr_geo,
+ .whichfork = XFS_ATTR_FORK,
+ .trans = sc->tp,
+ .total = 1,
+ .owner = sc->ip->i_ino,
+ };
+
+ error = xfs_attr_shortform_to_leaf(&args);
+ if (error)
+ return error;
+
+ /*
+ * Roll the deferred log items to get us back to a clean
+ * transaction.
+ */
+ error = xfs_defer_finish(&sc->tp);
+ if (error)
+ return error;
+ }
+
+ /*
+ * If the file being repaired had a shortform attribute fork, convert
+ * that to an empty extent list in preparation for the atomic mapping
+ * exchange.
+ */
+ if (ip_local) {
+ struct xfs_ifork *ifp;
+
+ ifp = xfs_ifork_ptr(sc->ip, XFS_ATTR_FORK);
+
+ xfs_idestroy_fork(ifp);
+ ifp->if_format = XFS_DINODE_FMT_EXTENTS;
+ ifp->if_nextents = 0;
+ ifp->if_bytes = 0;
+ ifp->if_data = NULL;
+ ifp->if_height = 0;
+
+ xfs_trans_log_inode(sc->tp, sc->ip,
+ XFS_ILOG_CORE | XFS_ILOG_ADATA);
+ }
+
+ return 0;
+}
+
+/* Exchange the temporary file's attribute fork with the one being repaired. */
+STATIC int
+xrep_xattr_swap(
+ struct xfs_scrub *sc,
+ struct xrep_tempexch *tx)
+{
+ bool ip_local, temp_local;
+ int error = 0;
+
+ ip_local = sc->ip->i_af.if_format == XFS_DINODE_FMT_LOCAL;
+ temp_local = sc->tempip->i_af.if_format == XFS_DINODE_FMT_LOCAL;
+
+ /*
+ * If the both files have a local format attr fork and the rebuilt
+ * xattr data would fit in the repaired file's attr fork, just copy
+ * the contents from the tempfile and declare ourselves done.
+ */
+ if (ip_local && temp_local) {
+ int forkoff;
+ int newsize;
+
+ newsize = xfs_attr_sf_totsize(sc->tempip);
+ forkoff = xfs_attr_shortform_bytesfit(sc->ip, newsize);
+ if (forkoff > 0) {
+ sc->ip->i_forkoff = forkoff;
+ xrep_tempfile_copyout_local(sc, XFS_ATTR_FORK);
+ return 0;
+ }
+ }
+
+ /* Otherwise, make sure both attr forks are in block-mapping mode. */
+ error = xrep_xattr_swap_prep(sc, temp_local, ip_local);
+ if (error)
+ return error;
+
+ return xrep_tempexch_contents(sc, tx);
+}
+
+/*
+ * Exchange the new extended attribute data (which we created in the tempfile)
+ * with the file being repaired.
+ */
+STATIC int
+xrep_xattr_rebuild_tree(
+ struct xrep_xattr *rx)
+{
+ struct xfs_scrub *sc = rx->sc;
+ int error;
+
+ /*
+ * If we didn't find any attributes to salvage, repair the file by
+ * zapping its attr fork.
+ */
+ if (rx->attrs_found == 0) {
+ xfs_trans_ijoin(sc->tp, sc->ip, 0);
+ error = xrep_xattr_reset_fork(sc);
+ if (error)
+ return error;
+
+ goto forget_acls;
+ }
+
+ trace_xrep_xattr_rebuild_tree(sc->ip, sc->tempip);
+
+ /*
+ * Commit the repair transaction and drop the ILOCKs so that we can use
+ * the atomic file content exchange helper functions to compute the
+ * correct resource reservations.
+ *
+ * We still hold IOLOCK_EXCL (aka i_rwsem) which will prevent xattr
+ * modifications, but there's nothing to prevent userspace from reading
+ * the attributes until we're ready for the exchange operation. Reads
+ * will return -EIO without shutting down the fs, so we're ok with
+ * that.
+ */
+ error = xrep_trans_commit(sc);
+ if (error)
+ return error;
+
+ xchk_iunlock(sc, XFS_ILOCK_EXCL);
+
+ /*
+ * Take the IOLOCK on the temporary file so that we can run xattr
+ * operations with the same locks held as we would for a normal file.
+ * We still hold sc->ip's IOLOCK.
+ */
+ error = xrep_tempfile_iolock_polled(rx->sc);
+ if (error)
+ return error;
+
+ /* Allocate exchange transaction and lock both inodes. */
+ error = xrep_tempexch_trans_alloc(rx->sc, XFS_ATTR_FORK, &rx->tx);
+ if (error)
+ return error;
+
+ /*
+ * Exchange the blocks mapped by the tempfile's attr fork with the file
+ * being repaired. The old attr blocks will then be attached to the
+ * tempfile, so reap its attr fork.
+ */
+ error = xrep_xattr_swap(sc, &rx->tx);
+ if (error)
+ return error;
+
+ error = xrep_xattr_reset_tempfile_fork(sc);
+ if (error)
+ return error;
+
+ /*
+ * Roll to get a transaction without any inodes joined to it. Then we
+ * can drop the tempfile's ILOCK and IOLOCK before doing more work on
+ * the scrub target file.
+ */
+ error = xfs_trans_roll(&sc->tp);
+ if (error)
+ return error;
+
+ xrep_tempfile_iunlock(sc);
+ xrep_tempfile_iounlock(sc);
+
+forget_acls:
+ /* Invalidate cached ACLs now that we've reloaded all the xattrs. */
+ xfs_forget_acl(VFS_I(sc->ip), SGI_ACL_FILE);
+ xfs_forget_acl(VFS_I(sc->ip), SGI_ACL_DEFAULT);
+ return 0;
+}
+
+/* Tear down all the incore scan stuff we created. */
+STATIC void
+xrep_xattr_teardown(
+ struct xrep_xattr *rx)
+{
+ xfblob_destroy(rx->xattr_blobs);
+ xfarray_destroy(rx->xattr_records);
+ kfree(rx);
+}
+
+/* Set up the filesystem scan so we can regenerate extended attributes. */
+STATIC int
+xrep_xattr_setup_scan(
+ struct xfs_scrub *sc,
+ struct xrep_xattr **rxp)
+{
+ struct xrep_xattr *rx;
+ char *descr;
+ int max_len;
+ int error;
+
+ rx = kzalloc(sizeof(struct xrep_xattr), XCHK_GFP_FLAGS);
+ if (!rx)
+ return -ENOMEM;
+ rx->sc = sc;
+
+ /*
+ * Allocate enough memory to handle loading local attr values from the
+ * xfblob data while flushing stashed attrs to the temporary file.
+ * We only realloc the buffer when salvaging remote attr values.
+ */
+ max_len = xfs_attr_leaf_entsize_local_max(sc->mp->m_attr_geo->blksize);
+ error = xchk_setup_xattr_buf(rx->sc, max_len);
+ if (error == -ENOMEM)
+ error = -EDEADLOCK;
+ if (error)
+ goto out_rx;
+
+ /* Set up some staging for salvaged attribute keys and values */
+ descr = xchk_xfile_ino_descr(sc, "xattr keys");
+ error = xfarray_create(descr, 0, sizeof(struct xrep_xattr_key),
+ &rx->xattr_records);
+ kfree(descr);
+ if (error)
+ goto out_rx;
+
+ descr = xchk_xfile_ino_descr(sc, "xattr names");
+ error = xfblob_create(descr, &rx->xattr_blobs);
+ kfree(descr);
+ if (error)
+ goto out_keys;
+
+ *rxp = rx;
+ return 0;
+out_keys:
+ xfarray_destroy(rx->xattr_records);
+out_rx:
+ kfree(rx);
+ return error;
+}
+
+/*
+ * Repair the extended attribute metadata.
+ *
+ * XXX: Remote attribute value buffers encompass the entire (up to 64k) buffer.
+ * The buffer cache in XFS can't handle aliased multiblock buffers, so this
+ * might misbehave if the attr fork is crosslinked with other filesystem
+ * metadata.
+ */
+int
+xrep_xattr(
+ struct xfs_scrub *sc)
+{
+ struct xrep_xattr *rx = NULL;
+ int error;
+
+ if (!xfs_inode_hasattr(sc->ip))
+ return -ENOENT;
+
+ /* The rmapbt is required to reap the old attr fork. */
+ if (!xfs_has_rmapbt(sc->mp))
+ return -EOPNOTSUPP;
+
+ error = xrep_xattr_setup_scan(sc, &rx);
+ if (error)
+ return error;
+
+ ASSERT(sc->ilock_flags & XFS_ILOCK_EXCL);
+
+ error = xrep_xattr_salvage_attributes(rx);
+ if (error)
+ goto out_scan;
+
+ /* Last chance to abort before we start committing fixes. */
+ if (xchk_should_terminate(sc, &error))
+ goto out_scan;
+
+ error = xrep_xattr_rebuild_tree(rx);
+ if (error)
+ goto out_scan;
+
+out_scan:
+ xrep_xattr_teardown(rx);
+ return error;
+}
diff --git a/fs/xfs/scrub/attr_repair.h b/fs/xfs/scrub/attr_repair.h
new file mode 100644
index 0000000000000..0a9ffa7cfa906
--- /dev/null
+++ b/fs/xfs/scrub/attr_repair.h
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2018-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_ATTR_REPAIR_H__
+#define __XFS_SCRUB_ATTR_REPAIR_H__
+
+int xrep_xattr_reset_fork(struct xfs_scrub *sc);
+
+#endif /* __XFS_SCRUB_ATTR_REPAIR_H__ */
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index f43dce771cdd2..eabc085ff00f8 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -32,6 +32,9 @@
#include "xfs_reflink.h"
#include "xfs_health.h"
#include "xfs_buf_mem.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_attr.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/trace.h"
@@ -39,6 +42,7 @@
#include "scrub/bitmap.h"
#include "scrub/stats.h"
#include "scrub/xfile.h"
+#include "scrub/attr_repair.h"
/*
* Attempt to repair some metadata, if the metadata is corrupt and userspace
@@ -1136,6 +1140,17 @@ xrep_metadata_inode_forks(
return error;
}
+ /* Clear the attr forks since metadata shouldn't have that. */
+ if (xfs_inode_hasattr(sc->ip)) {
+ if (!dirty) {
+ dirty = true;
+ xfs_trans_ijoin(sc->tp, sc->ip, 0);
+ }
+ error = xrep_xattr_reset_fork(sc);
+ if (error)
+ return error;
+ }
+
/*
* If we modified the inode, roll the transaction but don't rejoin the
* inode to the new transaction because xrep_bmap_data can do that.
@@ -1201,3 +1216,34 @@ xrep_trans_cancel_hook_dummy(
current->journal_info = *cookiep;
*cookiep = NULL;
}
+
+/*
+ * See if this buffer can pass the given ->verify_struct() function.
+ *
+ * If the buffer already has ops attached and they're not the ones that were
+ * passed in, we reject the buffer. Otherwise, we perform the structure test
+ * (note that we do not check CRCs) and return the outcome of the test. The
+ * buffer ops and error state are left unchanged.
+ */
+bool
+xrep_buf_verify_struct(
+ struct xfs_buf *bp,
+ const struct xfs_buf_ops *ops)
+{
+ const struct xfs_buf_ops *old_ops = bp->b_ops;
+ xfs_failaddr_t fa;
+ int old_error;
+
+ if (old_ops) {
+ if (old_ops != ops)
+ return false;
+ }
+
+ old_error = bp->b_error;
+ bp->b_ops = ops;
+ fa = bp->b_ops->verify_struct(bp);
+ bp->b_ops = old_ops;
+ bp->b_error = old_error;
+
+ return fa == NULL;
+}
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 0e2b695ab8f66..9cbfd8da5620b 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -90,6 +90,7 @@ int xrep_bmap(struct xfs_scrub *sc, int whichfork, bool allow_unwritten);
int xrep_metadata_inode_forks(struct xfs_scrub *sc);
int xrep_setup_ag_rmapbt(struct xfs_scrub *sc);
int xrep_setup_ag_refcountbt(struct xfs_scrub *sc);
+int xrep_setup_xattr(struct xfs_scrub *sc);
/* Repair setup functions */
int xrep_setup_ag_allocbt(struct xfs_scrub *sc);
@@ -123,6 +124,7 @@ int xrep_bmap_attr(struct xfs_scrub *sc);
int xrep_bmap_cow(struct xfs_scrub *sc);
int xrep_nlinks(struct xfs_scrub *sc);
int xrep_fscounters(struct xfs_scrub *sc);
+int xrep_xattr(struct xfs_scrub *sc);
#ifdef CONFIG_XFS_RT
int xrep_rtbitmap(struct xfs_scrub *sc);
@@ -147,6 +149,8 @@ int xrep_trans_alloc_hook_dummy(struct xfs_mount *mp, void **cookiep,
struct xfs_trans **tpp);
void xrep_trans_cancel_hook_dummy(void **cookiep, struct xfs_trans *tp);
+bool xrep_buf_verify_struct(struct xfs_buf *bp, const struct xfs_buf_ops *ops);
+
#else
#define xrep_ino_dqattach(sc) (0)
@@ -190,6 +194,7 @@ xrep_setup_nothing(
#define xrep_setup_ag_allocbt xrep_setup_nothing
#define xrep_setup_ag_rmapbt xrep_setup_nothing
#define xrep_setup_ag_refcountbt xrep_setup_nothing
+#define xrep_setup_xattr xrep_setup_nothing
#define xrep_setup_inode(sc, imap) ((void)0)
@@ -215,6 +220,7 @@ xrep_setup_nothing(
#define xrep_nlinks xrep_notsupported
#define xrep_fscounters xrep_notsupported
#define xrep_rtsummary xrep_notsupported
+#define xrep_xattr xrep_notsupported
#endif /* CONFIG_XFS_ONLINE_REPAIR */
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 62a064c1a5d34..547189a14b6bf 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -331,7 +331,7 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
.type = ST_INODE,
.setup = xchk_setup_xattr,
.scrub = xchk_xattr,
- .repair = xrep_notsupported,
+ .repair = xrep_xattr,
},
[XFS_SCRUB_TYPE_SYMLINK] = { /* symbolic link */
.type = ST_INODE,
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index b5fe49a6da534..8a467e708a375 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -2410,6 +2410,89 @@ TRACE_EVENT(xreap_bmapi_binval_scan,
__entry->scan_blocks)
);
+TRACE_EVENT(xrep_xattr_recover_leafblock,
+ TP_PROTO(struct xfs_inode *ip, xfs_dablk_t dabno, uint16_t magic),
+ TP_ARGS(ip, dabno, magic),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(xfs_dablk_t, dabno)
+ __field(uint16_t, magic)
+ ),
+ TP_fast_assign(
+ __entry->dev = ip->i_mount->m_super->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->dabno = dabno;
+ __entry->magic = magic;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx dablk 0x%x magic 0x%x",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->dabno,
+ __entry->magic)
+);
+
+DECLARE_EVENT_CLASS(xrep_xattr_salvage_class,
+ TP_PROTO(struct xfs_inode *ip, unsigned int flags, char *name,
+ unsigned int namelen, unsigned int valuelen),
+ TP_ARGS(ip, flags, name, namelen, valuelen),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(unsigned int, flags)
+ __field(unsigned int, namelen)
+ __dynamic_array(char, name, namelen)
+ __field(unsigned int, valuelen)
+ ),
+ TP_fast_assign(
+ __entry->dev = ip->i_mount->m_super->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->flags = flags;
+ __entry->namelen = namelen;
+ memcpy(__get_str(name), name, namelen);
+ __entry->valuelen = valuelen;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx flags %s name '%.*s' valuelen 0x%x",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __print_flags(__entry->flags, "|", XFS_ATTR_NAMESPACE_STR),
+ __entry->namelen,
+ __get_str(name),
+ __entry->valuelen)
+);
+#define DEFINE_XREP_XATTR_SALVAGE_EVENT(name) \
+DEFINE_EVENT(xrep_xattr_salvage_class, name, \
+ TP_PROTO(struct xfs_inode *ip, unsigned int flags, char *name, \
+ unsigned int namelen, unsigned int valuelen), \
+ TP_ARGS(ip, flags, name, namelen, valuelen))
+DEFINE_XREP_XATTR_SALVAGE_EVENT(xrep_xattr_salvage_rec);
+DEFINE_XREP_XATTR_SALVAGE_EVENT(xrep_xattr_insert_rec);
+
+TRACE_EVENT(xrep_xattr_class,
+ TP_PROTO(struct xfs_inode *ip, struct xfs_inode *arg_ip),
+ TP_ARGS(ip, arg_ip),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(xfs_ino_t, src_ino)
+ ),
+ TP_fast_assign(
+ __entry->dev = ip->i_mount->m_super->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->src_ino = arg_ip->i_ino;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx src 0x%llx",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->src_ino)
+)
+#define DEFINE_XREP_XATTR_EVENT(name) \
+DEFINE_EVENT(xrep_xattr_class, name, \
+ TP_PROTO(struct xfs_inode *ip, struct xfs_inode *arg_ip), \
+ TP_ARGS(ip, arg_ip))
+DEFINE_XREP_XATTR_EVENT(xrep_xattr_rebuild_tree);
+DEFINE_XREP_XATTR_EVENT(xrep_xattr_reset_fork);
+
#endif /* IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) */
#endif /* _TRACE_XFS_SCRUB_TRACE_H */
diff --git a/fs/xfs/scrub/xfarray.c b/fs/xfs/scrub/xfarray.c
index 17c982a4821d4..b65cd3fc5ac9b 100644
--- a/fs/xfs/scrub/xfarray.c
+++ b/fs/xfs/scrub/xfarray.c
@@ -1051,3 +1051,20 @@ xfarray_sort(
kvfree(si);
return error;
}
+
+/* How many bytes is this array consuming? */
+unsigned long long
+xfarray_bytes(
+ struct xfarray *array)
+{
+ return xfile_bytes(array->xfile);
+}
+
+/* Empty the entire array. */
+void
+xfarray_truncate(
+ struct xfarray *array)
+{
+ xfile_discard(array->xfile, 0, MAX_LFS_FILESIZE);
+ array->nr = 0;
+}
diff --git a/fs/xfs/scrub/xfarray.h b/fs/xfs/scrub/xfarray.h
index acb2f94c56c13..3b10a58e9f146 100644
--- a/fs/xfs/scrub/xfarray.h
+++ b/fs/xfs/scrub/xfarray.h
@@ -44,6 +44,8 @@ int xfarray_unset(struct xfarray *array, xfarray_idx_t idx);
int xfarray_store(struct xfarray *array, xfarray_idx_t idx, const void *ptr);
int xfarray_store_anywhere(struct xfarray *array, const void *ptr);
bool xfarray_element_is_null(struct xfarray *array, const void *ptr);
+void xfarray_truncate(struct xfarray *array);
+unsigned long long xfarray_bytes(struct xfarray *array);
/*
* Load an array element, but zero the buffer if there's no data because we
diff --git a/fs/xfs/scrub/xfblob.c b/fs/xfs/scrub/xfblob.c
index cec668debce5a..6ef2a9637f162 100644
--- a/fs/xfs/scrub/xfblob.c
+++ b/fs/xfs/scrub/xfblob.c
@@ -149,3 +149,20 @@ xfblob_free(
xfile_discard(blob->xfile, cookie, sizeof(key) + key.xb_size);
return 0;
}
+
+/* How many bytes is this blob storage object consuming? */
+unsigned long long
+xfblob_bytes(
+ struct xfblob *blob)
+{
+ return xfile_bytes(blob->xfile);
+}
+
+/* Drop all the blobs. */
+void
+xfblob_truncate(
+ struct xfblob *blob)
+{
+ xfile_discard(blob->xfile, PAGE_SIZE, MAX_LFS_FILESIZE - PAGE_SIZE);
+ blob->last_offset = PAGE_SIZE;
+}
diff --git a/fs/xfs/scrub/xfblob.h b/fs/xfs/scrub/xfblob.h
index bd98647407f1d..78a67a06408f8 100644
--- a/fs/xfs/scrub/xfblob.h
+++ b/fs/xfs/scrub/xfblob.h
@@ -20,5 +20,7 @@ int xfblob_load(struct xfblob *blob, xfblob_cookie cookie, void *ptr,
int xfblob_store(struct xfblob *blob, xfblob_cookie *cookie, const void *ptr,
uint32_t size);
int xfblob_free(struct xfblob *blob, xfblob_cookie cookie);
+unsigned long long xfblob_bytes(struct xfblob *blob);
+void xfblob_truncate(struct xfblob *blob);
#endif /* __XFS_SCRUB_XFBLOB_H__ */
diff --git a/fs/xfs/scrub/xfile.h b/fs/xfs/scrub/xfile.h
index 8dfbae1fe33a5..cc2cc1714cd4e 100644
--- a/fs/xfs/scrub/xfile.h
+++ b/fs/xfs/scrub/xfile.h
@@ -27,4 +27,9 @@ struct folio *xfile_get_folio(struct xfile *xf, loff_t offset, size_t len,
unsigned int flags);
void xfile_put_folio(struct xfile *xf, struct folio *folio);
+static inline unsigned long long xfile_bytes(struct xfile *xf)
+{
+ return file_inode(xf->file)->i_blocks << SECTOR_SHIFT;
+}
+
#endif /* __XFS_SCRUB_XFILE_H__ */
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 1f681a889d6ed..503ce7aff0c30 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -488,6 +488,9 @@ _xfs_buf_obj_cmp(
* it stale has not yet committed. i.e. we are
* reallocating a busy extent. Skip this buffer and
* continue searching for an exact match.
+ *
+ * Note: If we're scanning for incore buffers to stale, don't
+ * complain if we find non-stale buffers.
*/
if (!(map->bm_flags & XBM_LIVESCAN))
ASSERT(bp->b_flags & XBF_STALE);
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 2d7664a5cabae..7630ab0514f57 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -31,6 +31,8 @@
* pos: file offset, in bytes
* bytecount: number of bytes
*
+ * dablk: directory or xattr block offset, in filesystem blocks
+ *
* disize: ondisk file size, in bytes
* isize: incore file size, in bytes
*
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH 4/6] xfs: scrub should set preen if attr leaf has holes
2024-02-27 2:18 [PATCHSET v29.4 07/13] xfs: online repair of extended attributes Darrick J. Wong
` (2 preceding siblings ...)
2024-02-27 2:29 ` [PATCH 3/6] xfs: repair extended attributes Darrick J. Wong
@ 2024-02-27 2:29 ` Darrick J. Wong
2024-02-28 17:06 ` Christoph Hellwig
2024-02-27 2:29 ` [PATCH 5/6] xfs: flag empty xattr leaf blocks for optimization Darrick J. Wong
2024-02-27 2:30 ` [PATCH 6/6] xfs: create an xattr iteration function for scrub Darrick J. Wong
5 siblings, 1 reply; 16+ messages in thread
From: Darrick J. Wong @ 2024-02-27 2:29 UTC (permalink / raw
To: djwong; +Cc: Dave Chinner, linux-xfs, hch
From: Darrick J. Wong <djwong@kernel.org>
If an attr block indicates that it could use compaction, set the preen
flag to have the attr fork rebuilt, since the attr fork rebuilder can
take care of that for us.
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
---
fs/xfs/scrub/attr.c | 2 ++
fs/xfs/scrub/dabtree.c | 16 ++++++++++++++++
fs/xfs/scrub/dabtree.h | 1 +
fs/xfs/scrub/trace.h | 1 +
4 files changed, 20 insertions(+)
diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c
index 7621e548d7301..ba06be86ac7d4 100644
--- a/fs/xfs/scrub/attr.c
+++ b/fs/xfs/scrub/attr.c
@@ -428,6 +428,8 @@ xchk_xattr_block(
xchk_da_set_corrupt(ds, level);
if (!xchk_xattr_set_map(ds->sc, ab->usedmap, 0, hdrsize))
xchk_da_set_corrupt(ds, level);
+ if (leafhdr.holes)
+ xchk_da_set_preen(ds, level);
if (ds->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
goto out;
diff --git a/fs/xfs/scrub/dabtree.c b/fs/xfs/scrub/dabtree.c
index c71254088dffe..056de4819f866 100644
--- a/fs/xfs/scrub/dabtree.c
+++ b/fs/xfs/scrub/dabtree.c
@@ -78,6 +78,22 @@ xchk_da_set_corrupt(
__return_address);
}
+/* Flag a da btree node in need of optimization. */
+void
+xchk_da_set_preen(
+ struct xchk_da_btree *ds,
+ int level)
+{
+ struct xfs_scrub *sc = ds->sc;
+
+ sc->sm->sm_flags |= XFS_SCRUB_OFLAG_PREEN;
+ trace_xchk_fblock_preen(sc, ds->dargs.whichfork,
+ xfs_dir2_da_to_db(ds->dargs.geo,
+ ds->state->path.blk[level].blkno),
+ __return_address);
+}
+
+/* Find an entry at a certain level in a da btree. */
static struct xfs_da_node_entry *
xchk_da_btree_node_entry(
struct xchk_da_btree *ds,
diff --git a/fs/xfs/scrub/dabtree.h b/fs/xfs/scrub/dabtree.h
index 4f8c2138a1ec6..d654c125feb4d 100644
--- a/fs/xfs/scrub/dabtree.h
+++ b/fs/xfs/scrub/dabtree.h
@@ -35,6 +35,7 @@ bool xchk_da_process_error(struct xchk_da_btree *ds, int level, int *error);
/* Check for da btree corruption. */
void xchk_da_set_corrupt(struct xchk_da_btree *ds, int level);
+void xchk_da_set_preen(struct xchk_da_btree *ds, int level);
int xchk_da_btree_hash(struct xchk_da_btree *ds, int level, __be32 *hashp);
int xchk_da_btree(struct xfs_scrub *sc, int whichfork,
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 8a467e708a375..06d31b9dd0f47 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -365,6 +365,7 @@ DEFINE_EVENT(xchk_fblock_error_class, name, \
DEFINE_SCRUB_FBLOCK_ERROR_EVENT(xchk_fblock_error);
DEFINE_SCRUB_FBLOCK_ERROR_EVENT(xchk_fblock_warning);
+DEFINE_SCRUB_FBLOCK_ERROR_EVENT(xchk_fblock_preen);
#ifdef CONFIG_XFS_QUOTA
DECLARE_EVENT_CLASS(xchk_dqiter_class,
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH 5/6] xfs: flag empty xattr leaf blocks for optimization
2024-02-27 2:18 [PATCHSET v29.4 07/13] xfs: online repair of extended attributes Darrick J. Wong
` (3 preceding siblings ...)
2024-02-27 2:29 ` [PATCH 4/6] xfs: scrub should set preen if attr leaf has holes Darrick J. Wong
@ 2024-02-27 2:29 ` Darrick J. Wong
2024-02-28 17:06 ` Christoph Hellwig
2024-02-27 2:30 ` [PATCH 6/6] xfs: create an xattr iteration function for scrub Darrick J. Wong
5 siblings, 1 reply; 16+ messages in thread
From: Darrick J. Wong @ 2024-02-27 2:29 UTC (permalink / raw
To: djwong; +Cc: linux-xfs, hch
From: Darrick J. Wong <djwong@kernel.org>
Empty xattr leaf blocks at offset zero are a waste of space but
otherwise harmless. If we encounter one, flag it as an opportunity for
optimization.
If we encounter empty attr leaf blocks anywhere else in the attr fork,
that's corruption.
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
fs/xfs/scrub/attr.c | 11 +++++++++++
fs/xfs/scrub/dabtree.h | 2 ++
2 files changed, 13 insertions(+)
diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c
index ba06be86ac7d4..696971204b876 100644
--- a/fs/xfs/scrub/attr.c
+++ b/fs/xfs/scrub/attr.c
@@ -420,6 +420,17 @@ xchk_xattr_block(
xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &leafhdr, leaf);
hdrsize = xfs_attr3_leaf_hdr_size(leaf);
+ /*
+ * Empty xattr leaf blocks mapped at block 0 are probably a byproduct
+ * of a race between setxattr and a log shutdown. Anywhere else in the
+ * attr fork is a corruption.
+ */
+ if (leafhdr.count == 0) {
+ if (blk->blkno == 0)
+ xchk_da_set_preen(ds, level);
+ else
+ xchk_da_set_corrupt(ds, level);
+ }
if (leafhdr.usedbytes > mp->m_attr_geo->blksize)
xchk_da_set_corrupt(ds, level);
if (leafhdr.firstused > mp->m_attr_geo->blksize)
diff --git a/fs/xfs/scrub/dabtree.h b/fs/xfs/scrub/dabtree.h
index d654c125feb4d..de291e3b77dd8 100644
--- a/fs/xfs/scrub/dabtree.h
+++ b/fs/xfs/scrub/dabtree.h
@@ -37,6 +37,8 @@ bool xchk_da_process_error(struct xchk_da_btree *ds, int level, int *error);
void xchk_da_set_corrupt(struct xchk_da_btree *ds, int level);
void xchk_da_set_preen(struct xchk_da_btree *ds, int level);
+void xchk_da_set_preen(struct xchk_da_btree *ds, int level);
+
int xchk_da_btree_hash(struct xchk_da_btree *ds, int level, __be32 *hashp);
int xchk_da_btree(struct xfs_scrub *sc, int whichfork,
xchk_da_btree_rec_fn scrub_fn, void *private);
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH 6/6] xfs: create an xattr iteration function for scrub
2024-02-27 2:18 [PATCHSET v29.4 07/13] xfs: online repair of extended attributes Darrick J. Wong
` (4 preceding siblings ...)
2024-02-27 2:29 ` [PATCH 5/6] xfs: flag empty xattr leaf blocks for optimization Darrick J. Wong
@ 2024-02-27 2:30 ` Darrick J. Wong
2024-02-28 17:11 ` Christoph Hellwig
5 siblings, 1 reply; 16+ messages in thread
From: Darrick J. Wong @ 2024-02-27 2:30 UTC (permalink / raw
To: djwong; +Cc: linux-xfs, hch
From: Darrick J. Wong <djwong@kernel.org>
Create a streamlined function to walk a file's xattrs, without all the
cursor management stuff in the regular listxattr.
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
fs/xfs/Makefile | 1
fs/xfs/scrub/attr.c | 125 +++++++-----------
fs/xfs/scrub/dab_bitmap.h | 37 +++++
fs/xfs/scrub/listxattr.c | 310 +++++++++++++++++++++++++++++++++++++++++++++
fs/xfs/scrub/listxattr.h | 17 ++
5 files changed, 412 insertions(+), 78 deletions(-)
create mode 100644 fs/xfs/scrub/dab_bitmap.h
create mode 100644 fs/xfs/scrub/listxattr.c
create mode 100644 fs/xfs/scrub/listxattr.h
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 41f9d78ecd39e..7c2f4ba3335ec 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -166,6 +166,7 @@ xfs-y += $(addprefix scrub/, \
ialloc.o \
inode.o \
iscan.o \
+ listxattr.o \
nlinks.o \
parent.o \
readdir.o \
diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c
index 696971204b876..8853e4d0eee3d 100644
--- a/fs/xfs/scrub/attr.c
+++ b/fs/xfs/scrub/attr.c
@@ -21,6 +21,7 @@
#include "scrub/common.h"
#include "scrub/dabtree.h"
#include "scrub/attr.h"
+#include "scrub/listxattr.h"
#include "scrub/repair.h"
/* Free the buffers linked from the xattr buffer. */
@@ -153,90 +154,81 @@ xchk_setup_xattr(
/* Extended Attributes */
-struct xchk_xattr {
- struct xfs_attr_list_context context;
- struct xfs_scrub *sc;
-};
-
/*
* Check that an extended attribute key can be looked up by hash.
*
- * We use the XFS attribute list iterator (i.e. xfs_attr_list_ilocked)
- * to call this function for every attribute key in an inode. Once
- * we're here, we load the attribute value to see if any errors happen,
- * or if we get more or less data than we expected.
+ * We use the extended attribute walk helper to call this function for every
+ * attribute key in an inode. Once we're here, we load the attribute value to
+ * see if any errors happen, or if we get more or less data than we expected.
*/
-static void
-xchk_xattr_listent(
- struct xfs_attr_list_context *context,
- int flags,
- unsigned char *name,
- int namelen,
- int valuelen)
+static int
+xchk_xattr_actor(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ unsigned int attr_flags,
+ const unsigned char *name,
+ unsigned int namelen,
+ const void *value,
+ unsigned int valuelen,
+ void *priv)
{
struct xfs_da_args args = {
.op_flags = XFS_DA_OP_NOTIME,
- .attr_filter = flags & XFS_ATTR_NSP_ONDISK_MASK,
- .geo = context->dp->i_mount->m_attr_geo,
+ .attr_filter = attr_flags & XFS_ATTR_NSP_ONDISK_MASK,
+ .geo = sc->mp->m_attr_geo,
.whichfork = XFS_ATTR_FORK,
- .dp = context->dp,
+ .dp = ip,
.name = name,
.namelen = namelen,
.hashval = xfs_da_hashname(name, namelen),
- .trans = context->tp,
+ .trans = sc->tp,
.valuelen = valuelen,
- .owner = context->dp->i_ino,
+ .owner = ip->i_ino,
};
struct xchk_xattr_buf *ab;
- struct xchk_xattr *sx;
int error = 0;
- sx = container_of(context, struct xchk_xattr, context);
- ab = sx->sc->buf;
+ ab = sc->buf;
- if (xchk_should_terminate(sx->sc, &error)) {
- context->seen_enough = error;
- return;
- }
+ if (xchk_should_terminate(sc, &error))
+ return error;
- if (flags & XFS_ATTR_INCOMPLETE) {
+ if (attr_flags & XFS_ATTR_INCOMPLETE) {
/* Incomplete attr key, just mark the inode for preening. */
- xchk_ino_set_preen(sx->sc, context->dp->i_ino);
- return;
+ xchk_ino_set_preen(sc, ip->i_ino);
+ return 0;
}
/* Only one namespace bit allowed. */
- if (hweight32(flags & XFS_ATTR_NSP_ONDISK_MASK) > 1) {
- xchk_fblock_set_corrupt(sx->sc, XFS_ATTR_FORK, args.blkno);
- goto fail_xref;
+ if (hweight32(attr_flags & XFS_ATTR_NSP_ONDISK_MASK) > 1) {
+ xchk_fblock_set_corrupt(sc, XFS_ATTR_FORK, args.blkno);
+ return -ECANCELED;
}
/* Does this name make sense? */
if (!xfs_attr_namecheck(name, namelen)) {
- xchk_fblock_set_corrupt(sx->sc, XFS_ATTR_FORK, args.blkno);
- goto fail_xref;
+ xchk_fblock_set_corrupt(sc, XFS_ATTR_FORK, args.blkno);
+ return -ECANCELED;
}
/*
- * Local xattr values are stored in the attr leaf block, so we don't
- * need to retrieve the value from a remote block to detect corruption
- * problems.
+ * Local and shortform xattr values are stored in the attr leaf block,
+ * so we don't need to retrieve the value from a remote block to detect
+ * corruption problems.
*/
- if (flags & XFS_ATTR_LOCAL)
- goto fail_xref;
+ if (value)
+ return 0;
/*
- * Try to allocate enough memory to extrat the attr value. If that
- * doesn't work, we overload the seen_enough variable to convey
- * the error message back to the main scrub function.
+ * Try to allocate enough memory to extract the attr value. If that
+ * doesn't work, return -EDEADLOCK as a signal to try again with a
+ * maximally sized buffer.
*/
- error = xchk_setup_xattr_buf(sx->sc, valuelen);
+ error = xchk_setup_xattr_buf(sc, valuelen);
if (error == -ENOMEM)
error = -EDEADLOCK;
- if (error) {
- context->seen_enough = error;
- return;
- }
+ if (error)
+ return error;
args.value = ab->value;
@@ -244,16 +236,13 @@ xchk_xattr_listent(
/* ENODATA means the hash lookup failed and the attr is bad */
if (error == -ENODATA)
error = -EFSCORRUPTED;
- if (!xchk_fblock_process_error(sx->sc, XFS_ATTR_FORK, args.blkno,
+ if (!xchk_fblock_process_error(sc, XFS_ATTR_FORK, args.blkno,
&error))
- goto fail_xref;
+ return error;
if (args.valuelen != valuelen)
- xchk_fblock_set_corrupt(sx->sc, XFS_ATTR_FORK,
- args.blkno);
-fail_xref:
- if (sx->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
- context->seen_enough = 1;
- return;
+ xchk_fblock_set_corrupt(sc, XFS_ATTR_FORK, args.blkno);
+
+ return 0;
}
/*
@@ -618,16 +607,6 @@ int
xchk_xattr(
struct xfs_scrub *sc)
{
- struct xchk_xattr sx = {
- .sc = sc,
- .context = {
- .dp = sc->ip,
- .tp = sc->tp,
- .resynch = 1,
- .put_listent = xchk_xattr_listent,
- .allow_incomplete = true,
- },
- };
xfs_dablk_t last_checked = -1U;
int error = 0;
@@ -656,12 +635,6 @@ xchk_xattr(
/*
* Look up every xattr in this file by name and hash.
*
- * Use the backend implementation of xfs_attr_list to call
- * xchk_xattr_listent on every attribute key in this inode.
- * In other words, we use the same iterator/callback mechanism
- * that listattr uses to scrub extended attributes, though in our
- * _listent function, we check the value of the attribute.
- *
* The VFS only locks i_rwsem when modifying attrs, so keep all
* three locks held because that's the only way to ensure we're
* the only thread poking into the da btree. We traverse the da
@@ -669,13 +642,9 @@ xchk_xattr(
* iteration, which doesn't really follow the usual buffer
* locking order.
*/
- error = xfs_attr_list_ilocked(&sx.context);
+ error = xchk_xattr_walk(sc, sc->ip, xchk_xattr_actor, NULL);
if (!xchk_fblock_process_error(sc, XFS_ATTR_FORK, 0, &error))
return error;
- /* Did our listent function try to return any errors? */
- if (sx.context.seen_enough < 0)
- return sx.context.seen_enough;
-
return 0;
}
diff --git a/fs/xfs/scrub/dab_bitmap.h b/fs/xfs/scrub/dab_bitmap.h
new file mode 100644
index 0000000000000..0c6e3aad43954
--- /dev/null
+++ b/fs/xfs/scrub/dab_bitmap.h
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2022-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_DAB_BITMAP_H__
+#define __XFS_SCRUB_DAB_BITMAP_H__
+
+/* Bitmaps, but for type-checked for xfs_dablk_t */
+
+struct xdab_bitmap {
+ struct xbitmap32 dabitmap;
+};
+
+static inline void xdab_bitmap_init(struct xdab_bitmap *bitmap)
+{
+ xbitmap32_init(&bitmap->dabitmap);
+}
+
+static inline void xdab_bitmap_destroy(struct xdab_bitmap *bitmap)
+{
+ xbitmap32_destroy(&bitmap->dabitmap);
+}
+
+static inline int xdab_bitmap_set(struct xdab_bitmap *bitmap,
+ xfs_dablk_t dabno, xfs_extlen_t len)
+{
+ return xbitmap32_set(&bitmap->dabitmap, dabno, len);
+}
+
+static inline bool xdab_bitmap_test(struct xdab_bitmap *bitmap,
+ xfs_dablk_t dabno, xfs_extlen_t *len)
+{
+ return xbitmap32_test(&bitmap->dabitmap, dabno, len);
+}
+
+#endif /* __XFS_SCRUB_DAB_BITMAP_H__ */
diff --git a/fs/xfs/scrub/listxattr.c b/fs/xfs/scrub/listxattr.c
new file mode 100644
index 0000000000000..f38d6ea4579ac
--- /dev/null
+++ b/fs/xfs/scrub/listxattr.c
@@ -0,0 +1,310 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2022-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_inode.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_attr.h"
+#include "xfs_attr_leaf.h"
+#include "xfs_attr_sf.h"
+#include "xfs_trans.h"
+#include "scrub/scrub.h"
+#include "scrub/bitmap.h"
+#include "scrub/dab_bitmap.h"
+#include "scrub/listxattr.h"
+
+/* Call a function for every entry in a shortform xattr structure. */
+STATIC int
+xchk_xattr_walk_sf(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ xchk_xattr_fn attr_fn,
+ void *priv)
+{
+ struct xfs_attr_sf_hdr *hdr = ip->i_af.if_data;
+ struct xfs_attr_sf_entry *sfe;
+ unsigned int i;
+ int error;
+
+ sfe = xfs_attr_sf_firstentry(hdr);
+ for (i = 0; i < hdr->count; i++) {
+ error = attr_fn(sc, ip, sfe->flags, sfe->nameval, sfe->namelen,
+ &sfe->nameval[sfe->namelen], sfe->valuelen,
+ priv);
+ if (error)
+ return error;
+
+ sfe = xfs_attr_sf_nextentry(sfe);
+ }
+
+ return 0;
+}
+
+/* Call a function for every entry in this xattr leaf block. */
+STATIC int
+xchk_xattr_walk_leaf_entries(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ xchk_xattr_fn attr_fn,
+ struct xfs_buf *bp,
+ void *priv)
+{
+ struct xfs_attr3_icleaf_hdr ichdr;
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_attr_leafblock *leaf = bp->b_addr;
+ struct xfs_attr_leaf_entry *entry;
+ unsigned int i;
+ int error;
+
+ xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr, leaf);
+ entry = xfs_attr3_leaf_entryp(leaf);
+
+ for (i = 0; i < ichdr.count; entry++, i++) {
+ void *value;
+ unsigned char *name;
+ unsigned int namelen, valuelen;
+
+ if (entry->flags & XFS_ATTR_LOCAL) {
+ struct xfs_attr_leaf_name_local *name_loc;
+
+ name_loc = xfs_attr3_leaf_name_local(leaf, i);
+ name = name_loc->nameval;
+ namelen = name_loc->namelen;
+ value = &name_loc->nameval[name_loc->namelen];
+ valuelen = be16_to_cpu(name_loc->valuelen);
+ } else {
+ struct xfs_attr_leaf_name_remote *name_rmt;
+
+ name_rmt = xfs_attr3_leaf_name_remote(leaf, i);
+ name = name_rmt->name;
+ namelen = name_rmt->namelen;
+ value = NULL;
+ valuelen = be32_to_cpu(name_rmt->valuelen);
+ }
+
+ error = attr_fn(sc, ip, entry->flags, name, namelen, value,
+ valuelen, priv);
+ if (error)
+ return error;
+
+ }
+
+ return 0;
+}
+
+/*
+ * Call a function for every entry in a leaf-format xattr structure. Avoid
+ * memory allocations for the loop detector since there's only one block.
+ */
+STATIC int
+xchk_xattr_walk_leaf(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ xchk_xattr_fn attr_fn,
+ void *priv)
+{
+ struct xfs_buf *leaf_bp;
+ int error;
+
+ error = xfs_attr3_leaf_read(sc->tp, ip, ip->i_ino, 0, &leaf_bp);
+ if (error)
+ return error;
+
+ error = xchk_xattr_walk_leaf_entries(sc, ip, attr_fn, leaf_bp, priv);
+ xfs_trans_brelse(sc->tp, leaf_bp);
+ return error;
+}
+
+/* Find the leftmost leaf in the xattr dabtree. */
+STATIC int
+xchk_xattr_find_leftmost_leaf(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ struct xdab_bitmap *seen_dablks,
+ struct xfs_buf **leaf_bpp)
+{
+ struct xfs_da3_icnode_hdr nodehdr;
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_trans *tp = sc->tp;
+ struct xfs_da_intnode *node;
+ struct xfs_da_node_entry *btree;
+ struct xfs_buf *bp;
+ xfs_failaddr_t fa;
+ xfs_dablk_t blkno = 0;
+ unsigned int expected_level = 0;
+ int error;
+
+ for (;;) {
+ xfs_extlen_t len = 1;
+ uint16_t magic;
+
+ /* Make sure we haven't seen this new block already. */
+ if (xdab_bitmap_test(seen_dablks, blkno, &len))
+ return -EFSCORRUPTED;
+
+ error = xfs_da3_node_read(tp, ip, blkno, &bp, XFS_ATTR_FORK);
+ if (error)
+ return error;
+
+ node = bp->b_addr;
+ magic = be16_to_cpu(node->hdr.info.magic);
+ if (magic == XFS_ATTR_LEAF_MAGIC ||
+ magic == XFS_ATTR3_LEAF_MAGIC)
+ break;
+
+ error = -EFSCORRUPTED;
+ if (magic != XFS_DA_NODE_MAGIC &&
+ magic != XFS_DA3_NODE_MAGIC)
+ goto out_buf;
+
+ fa = xfs_da3_node_header_check(bp, ip->i_ino);
+ if (fa)
+ goto out_buf;
+
+ xfs_da3_node_hdr_from_disk(mp, &nodehdr, node);
+
+ if (nodehdr.count == 0 || nodehdr.level >= XFS_DA_NODE_MAXDEPTH)
+ goto out_buf;
+
+ /* Check the level from the root node. */
+ if (blkno == 0)
+ expected_level = nodehdr.level - 1;
+ else if (expected_level != nodehdr.level)
+ goto out_buf;
+ else
+ expected_level--;
+
+ /* Remember that we've seen this node. */
+ error = xdab_bitmap_set(seen_dablks, blkno, 1);
+ if (error)
+ goto out_buf;
+
+ /* Find the next level towards the leaves of the dabtree. */
+ btree = nodehdr.btree;
+ blkno = be32_to_cpu(btree->before);
+ xfs_trans_brelse(tp, bp);
+ }
+
+ error = -EFSCORRUPTED;
+ fa = xfs_attr3_leaf_header_check(bp, ip->i_ino);
+ if (fa)
+ goto out_buf;
+
+ if (expected_level != 0)
+ goto out_buf;
+
+ /* Remember that we've seen this leaf. */
+ error = xdab_bitmap_set(seen_dablks, blkno, 1);
+ if (error)
+ goto out_buf;
+
+ *leaf_bpp = bp;
+ return 0;
+
+out_buf:
+ xfs_trans_brelse(tp, bp);
+ return error;
+}
+
+/* Call a function for every entry in a node-format xattr structure. */
+STATIC int
+xchk_xattr_walk_node(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ xchk_xattr_fn attr_fn,
+ void *priv)
+{
+ struct xfs_attr3_icleaf_hdr leafhdr;
+ struct xdab_bitmap seen_dablks;
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_attr_leafblock *leaf;
+ struct xfs_buf *leaf_bp;
+ int error;
+
+ xdab_bitmap_init(&seen_dablks);
+
+ error = xchk_xattr_find_leftmost_leaf(sc, ip, &seen_dablks, &leaf_bp);
+ if (error)
+ goto out_bitmap;
+
+ for (;;) {
+ xfs_extlen_t len;
+
+ error = xchk_xattr_walk_leaf_entries(sc, ip, attr_fn, leaf_bp,
+ priv);
+ if (error)
+ goto out_leaf;
+
+ /* Find the right sibling of this leaf block. */
+ leaf = leaf_bp->b_addr;
+ xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &leafhdr, leaf);
+ if (leafhdr.forw == 0)
+ goto out_leaf;
+
+ xfs_trans_brelse(sc->tp, leaf_bp);
+
+ /* Make sure we haven't seen this new leaf already. */
+ len = 1;
+ if (xdab_bitmap_test(&seen_dablks, leafhdr.forw, &len))
+ goto out_bitmap;
+
+ error = xfs_attr3_leaf_read(sc->tp, ip, ip->i_ino,
+ leafhdr.forw, &leaf_bp);
+ if (error)
+ goto out_bitmap;
+
+ /* Remember that we've seen this new leaf. */
+ error = xdab_bitmap_set(&seen_dablks, leafhdr.forw, 1);
+ if (error)
+ goto out_leaf;
+ }
+
+out_leaf:
+ xfs_trans_brelse(sc->tp, leaf_bp);
+out_bitmap:
+ xdab_bitmap_destroy(&seen_dablks);
+ return error;
+}
+
+/*
+ * Call a function for every extended attribute in a file.
+ *
+ * Callers must hold the ILOCK. No validation or cursor restarts allowed.
+ * Returns -EFSCORRUPTED on any problem, including loops in the dabtree.
+ */
+int
+xchk_xattr_walk(
+ struct xfs_scrub *sc,
+ struct xfs_inode *ip,
+ xchk_xattr_fn attr_fn,
+ void *priv)
+{
+ int error;
+
+ ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
+
+ if (!xfs_inode_hasattr(ip))
+ return 0;
+
+ if (ip->i_af.if_format == XFS_DINODE_FMT_LOCAL)
+ return xchk_xattr_walk_sf(sc, ip, attr_fn, priv);
+
+ /* attr functions require that the attr fork is loaded */
+ error = xfs_iread_extents(sc->tp, ip, XFS_ATTR_FORK);
+ if (error)
+ return error;
+
+ if (xfs_attr_is_leaf(ip))
+ return xchk_xattr_walk_leaf(sc, ip, attr_fn, priv);
+
+ return xchk_xattr_walk_node(sc, ip, attr_fn, priv);
+}
diff --git a/fs/xfs/scrub/listxattr.h b/fs/xfs/scrub/listxattr.h
new file mode 100644
index 0000000000000..48fe89d05946b
--- /dev/null
+++ b/fs/xfs/scrub/listxattr.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2022-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_LISTXATTR_H__
+#define __XFS_SCRUB_LISTXATTR_H__
+
+typedef int (*xchk_xattr_fn)(struct xfs_scrub *sc, struct xfs_inode *ip,
+ unsigned int attr_flags, const unsigned char *name,
+ unsigned int namelen, const void *value, unsigned int valuelen,
+ void *priv);
+
+int xchk_xattr_walk(struct xfs_scrub *sc, struct xfs_inode *ip,
+ xchk_xattr_fn attr_fn, void *priv);
+
+#endif /* __XFS_SCRUB_LISTXATTR_H__ */
^ permalink raw reply related [flat|nested] 16+ messages in thread
* Re: [PATCH 1/6] xfs: create a blob array data structure
2024-02-27 2:28 ` [PATCH 1/6] xfs: create a blob array data structure Darrick J. Wong
@ 2024-02-28 16:00 ` Christoph Hellwig
2024-02-28 17:48 ` Darrick J. Wong
0 siblings, 1 reply; 16+ messages in thread
From: Christoph Hellwig @ 2024-02-28 16:00 UTC (permalink / raw
To: Darrick J. Wong; +Cc: linux-xfs, hch
> +/* Discard pages backing a range of the xfile. */
> +void
> +xfile_discard(
> + struct xfile *xf,
> + loff_t pos,
> + u64 count)
> +{
> + trace_xfile_discard(xf, pos, count);
> +
> + shmem_truncate_range(file_inode(xf->file), pos, pos + count - 1);
> +}
Can you split this xfile infrastructure addition into a separate patch
instead of hiding it here?
Otherwise looks good:
Reviewed-by: Christoph Hellwig <hch@lst.de>
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH 2/6] xfs: use atomic extent swapping to fix user file fork data
2024-02-27 2:29 ` [PATCH 2/6] xfs: use atomic extent swapping to fix user file fork data Darrick J. Wong
@ 2024-02-28 16:01 ` Christoph Hellwig
0 siblings, 0 replies; 16+ messages in thread
From: Christoph Hellwig @ 2024-02-28 16:01 UTC (permalink / raw
To: Darrick J. Wong; +Cc: linux-xfs, hch
Looks good:
Reviewed-by: Christoph Hellwig <hch@lst.de>
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH 3/6] xfs: repair extended attributes
2024-02-27 2:29 ` [PATCH 3/6] xfs: repair extended attributes Darrick J. Wong
@ 2024-02-28 17:05 ` Christoph Hellwig
0 siblings, 0 replies; 16+ messages in thread
From: Christoph Hellwig @ 2024-02-28 17:05 UTC (permalink / raw
To: Darrick J. Wong; +Cc: linux-xfs, hch
Looks good:
Reviewed-by: Christoph Hellwig <hch@lst.de>
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH 4/6] xfs: scrub should set preen if attr leaf has holes
2024-02-27 2:29 ` [PATCH 4/6] xfs: scrub should set preen if attr leaf has holes Darrick J. Wong
@ 2024-02-28 17:06 ` Christoph Hellwig
0 siblings, 0 replies; 16+ messages in thread
From: Christoph Hellwig @ 2024-02-28 17:06 UTC (permalink / raw
To: Darrick J. Wong; +Cc: Dave Chinner, linux-xfs, hch
Looks good:
Reviewed-by: Christoph Hellwig <hch@lst.de>
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH 5/6] xfs: flag empty xattr leaf blocks for optimization
2024-02-27 2:29 ` [PATCH 5/6] xfs: flag empty xattr leaf blocks for optimization Darrick J. Wong
@ 2024-02-28 17:06 ` Christoph Hellwig
0 siblings, 0 replies; 16+ messages in thread
From: Christoph Hellwig @ 2024-02-28 17:06 UTC (permalink / raw
To: Darrick J. Wong; +Cc: linux-xfs, hch
Looks good:
Reviewed-by: Christoph Hellwig <hch@lst.de>
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH 6/6] xfs: create an xattr iteration function for scrub
2024-02-27 2:30 ` [PATCH 6/6] xfs: create an xattr iteration function for scrub Darrick J. Wong
@ 2024-02-28 17:11 ` Christoph Hellwig
2024-02-28 18:07 ` Darrick J. Wong
0 siblings, 1 reply; 16+ messages in thread
From: Christoph Hellwig @ 2024-02-28 17:11 UTC (permalink / raw
To: Darrick J. Wong; +Cc: linux-xfs, hch
On Mon, Feb 26, 2024 at 06:30:14PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
>
> Create a streamlined function to walk a file's xattrs, without all the
> cursor management stuff in the regular listxattr.
So given that the Linux xattr interface doesn't have cursors and they
are only around for the XFS listattr by handle interface, why can't
the normal listxattr syscall also use this cursors-less variant,
which probably more efficient? (assuming it is, maybe a little more
explanation on why you've added this variant would be useful).
No need to hold this series for optimizing regular listxattr, just
thinking out loud here.
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH 1/6] xfs: create a blob array data structure
2024-02-28 16:00 ` Christoph Hellwig
@ 2024-02-28 17:48 ` Darrick J. Wong
0 siblings, 0 replies; 16+ messages in thread
From: Darrick J. Wong @ 2024-02-28 17:48 UTC (permalink / raw
To: Christoph Hellwig; +Cc: linux-xfs, hch
On Wed, Feb 28, 2024 at 08:00:50AM -0800, Christoph Hellwig wrote:
> > +/* Discard pages backing a range of the xfile. */
> > +void
> > +xfile_discard(
> > + struct xfile *xf,
> > + loff_t pos,
> > + u64 count)
> > +{
> > + trace_xfile_discard(xf, pos, count);
> > +
> > + shmem_truncate_range(file_inode(xf->file), pos, pos + count - 1);
> > +}
>
> Can you split this xfile infrastructure addition into a separate patch
> instead of hiding it here?
Done.
> Otherwise looks good:
>
> Reviewed-by: Christoph Hellwig <hch@lst.de>
Thanks!
--D
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH 6/6] xfs: create an xattr iteration function for scrub
2024-02-28 17:11 ` Christoph Hellwig
@ 2024-02-28 18:07 ` Darrick J. Wong
0 siblings, 0 replies; 16+ messages in thread
From: Darrick J. Wong @ 2024-02-28 18:07 UTC (permalink / raw
To: Christoph Hellwig; +Cc: linux-xfs, hch
On Wed, Feb 28, 2024 at 09:11:10AM -0800, Christoph Hellwig wrote:
> On Mon, Feb 26, 2024 at 06:30:14PM -0800, Darrick J. Wong wrote:
> > From: Darrick J. Wong <djwong@kernel.org>
> >
> > Create a streamlined function to walk a file's xattrs, without all the
> > cursor management stuff in the regular listxattr.
>
> So given that the Linux xattr interface doesn't have cursors
Which IMO is a deficiency that really ought to be rectified. It's also
totally stupid that it returns E2BIG if the fs returned a list longer
than 64k even if the caller passed in a sufficiently large buffer.
> and they
> are only around for the XFS listattr by handle interface, why can't
> the normal listxattr syscall also use this cursors-less variant,
> which probably more efficient? (assuming it is, maybe a little more
> explanation on why you've added this variant would be useful).
It's slightly more efficient since we don't have to keep the
xfs_attr_list_context updated or pay the initial "resynch" cost. The
context itself is zero-initialized, so it'll pointlessly walk the leaf
entry array after loading the buffer.
The scrub listxattr implementation has the extra overhead of creating a
dabno bitmap while it walks multi-block attr structures so that it can't
get locked in a cycle. xdabitmap_set can allocate memory for bitmap
records, which we might not want for code that userspace calls.
Another difficulty in porting xfs_vn_listxattr to use this is that we'd
have to hoist both this and xdabitmap out of scrub.
> No need to hold this series for optimizing regular listxattr, just
> thinking out loud here.
<nod> I guess we could share, but if I were to spend time on fixing
listxattr I'd rather upgrade the interface to use a cursor and gain the
ability to return more than 64k of names.
--D
^ permalink raw reply [flat|nested] 16+ messages in thread
end of thread, other threads:[~2024-02-28 18:07 UTC | newest]
Thread overview: 16+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2024-02-27 2:18 [PATCHSET v29.4 07/13] xfs: online repair of extended attributes Darrick J. Wong
2024-02-27 2:28 ` [PATCH 1/6] xfs: create a blob array data structure Darrick J. Wong
2024-02-28 16:00 ` Christoph Hellwig
2024-02-28 17:48 ` Darrick J. Wong
2024-02-27 2:29 ` [PATCH 2/6] xfs: use atomic extent swapping to fix user file fork data Darrick J. Wong
2024-02-28 16:01 ` Christoph Hellwig
2024-02-27 2:29 ` [PATCH 3/6] xfs: repair extended attributes Darrick J. Wong
2024-02-28 17:05 ` Christoph Hellwig
2024-02-27 2:29 ` [PATCH 4/6] xfs: scrub should set preen if attr leaf has holes Darrick J. Wong
2024-02-28 17:06 ` Christoph Hellwig
2024-02-27 2:29 ` [PATCH 5/6] xfs: flag empty xattr leaf blocks for optimization Darrick J. Wong
2024-02-28 17:06 ` Christoph Hellwig
2024-02-27 2:30 ` [PATCH 6/6] xfs: create an xattr iteration function for scrub Darrick J. Wong
2024-02-28 17:11 ` Christoph Hellwig
2024-02-28 18:07 ` Darrick J. Wong
-- strict thread matches above, loose matches on Subject: below --
2023-12-31 19:30 [PATCHSET v29.0 20/28] xfs: online repair of extended attributes Darrick J. Wong
2023-12-31 20:35 ` [PATCH 3/6] xfs: repair " Darrick J. Wong
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).