@@ -164,6 +164,7 @@ xfs-$(CONFIG_XFS_QUOTA) += scrub/quota.o
ifeq ($(CONFIG_XFS_ONLINE_REPAIR),y)
xfs-y += $(addprefix scrub/, \
agheader_repair.o \
+ attr_repair.o \
alloc_repair.o \
bitmap.o \
bmap_repair.o \
@@ -125,7 +125,7 @@ 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,
new file mode 100644
@@ -0,0 +1,611 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2018 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ */
+#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 "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+
+/*
+ * Extended Attribute Repair
+ * =========================
+ *
+ * We repair extended attributes by reading the attribute fork blocks looking
+ * for keys and values, then truncate the entire attr fork and reinsert all
+ * the attributes. Unfortunately, there's no secondary copy of most extended
+ * attribute data, which means that if we blow up midway through there's
+ * little we can do.
+ */
+
+struct xrep_xattr_key {
+ struct list_head list;
+ unsigned char *value;
+ int valuelen;
+ int flags;
+ int namelen;
+ unsigned char name[0];
+};
+
+#define XREP_XATTR_KEY_LEN(namelen) \
+ (sizeof(struct xrep_xattr_key) + (namelen) + 1)
+
+struct xrep_xattr {
+ struct list_head *attrlist;
+ struct xfs_scrub *sc;
+};
+
+/*
+ * Iterate each block in an attr fork extent. The m_attr_geo fsbcount is
+ * always 1 for now, but code defensively in case this ever changes.
+ */
+#define for_each_xfs_attr_block(mp, irec, dabno) \
+ for ((dabno) = roundup((xfs_dablk_t)(irec)->br_startoff, \
+ (mp)->m_attr_geo->fsbcount); \
+ (dabno) < (irec)->br_startoff + (irec)->br_blockcount; \
+ (dabno) += (mp)->m_attr_geo->fsbcount)
+
+/*
+ * Decide if we want to salvage this attribute. We don't bother with
+ * incomplete or oversized keys or values.
+ */
+STATIC int
+xrep_xattr_want_salvage(
+ int flags,
+ int namelen,
+ int valuelen)
+{
+ if (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 struct xrep_xattr_key *
+xrep_xattr_salvage_key(
+ int flags,
+ unsigned char *name,
+ int namelen,
+ int valuelen)
+{
+ struct xrep_xattr_key *key;
+
+ /* Store attr key. */
+ key = kmem_alloc(XREP_XATTR_KEY_LEN(namelen), KM_MAYFAIL);
+ if (!key)
+ return NULL;
+ INIT_LIST_HEAD(&key->list);
+ key->valuelen = valuelen;
+ key->flags = flags & (ATTR_ROOT | ATTR_SECURE);
+ key->namelen = namelen;
+ key->name[namelen] = 0;
+ memcpy(key->name, name, namelen);
+ key->value = NULL;
+ if (valuelen) {
+ key->value = kmem_alloc_large(valuelen, KM_MAYFAIL);
+ if (!key->value) {
+ kmem_free(key);
+ return NULL;
+ }
+ }
+ return key;
+}
+
+/*
+ * 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_entry *sfe)
+{
+ unsigned char *value = &sfe->nameval[sfe->namelen];
+ struct xrep_xattr_key *key;
+
+ if (!xrep_xattr_want_salvage(sfe->flags, sfe->namelen, sfe->valuelen))
+ return 0;
+ key = xrep_xattr_salvage_key(sfe->flags, sfe->nameval, sfe->namelen,
+ sfe->valuelen);
+ if (!key)
+ return -ENOMEM;
+ if (sfe->valuelen)
+ memcpy(key->value, value, sfe->valuelen);
+ list_add_tail(&key->list, rx->attrlist);
+ return 0;
+}
+
+/*
+ * 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 xrep_xattr_key *key;
+ unsigned long *usedmap = rx->sc->buf;
+ unsigned int valuelen;
+ unsigned int namesize;
+
+ /*
+ * Decode the leaf local entry format. If something seems wrong, we
+ * junk the attribute.
+ */
+ 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(ent->flags, lentry->namelen, valuelen))
+ return 0;
+ if (!xchk_xattr_set_map(rx->sc, usedmap, nameidx, namesize))
+ return 0;
+
+ /* Try to save this attribute. */
+ key = xrep_xattr_salvage_key(ent->flags, lentry->nameval,
+ lentry->namelen, valuelen);
+ if (!key)
+ return -ENOMEM;
+ if (valuelen)
+ memcpy(key->value, &lentry->nameval[lentry->namelen], valuelen);
+ list_add_tail(&key->list, rx->attrlist);
+ return 0;
+}
+
+/*
+ * 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,
+ };
+ struct xrep_xattr_key *key;
+ unsigned long *usedmap = 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(ent->flags, rentry->namelen, valuelen))
+ return 0;
+ if (!xchk_xattr_set_map(rx->sc, usedmap, nameidx, namesize))
+ return 0;
+
+ /* Try to save this attribute. */
+ key = xrep_xattr_salvage_key(ent->flags, rentry->name, rentry->namelen,
+ valuelen);
+ if (!key)
+ return -ENOMEM;
+
+ /* Look up the remote value and stash it for reconstruction. */
+ args.valuelen = valuelen;
+ args.namelen = rentry->namelen;
+ args.name = key->name;
+ args.value = key->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 == 0) {
+ /* Got the value, add the attr and get out. */
+ list_add_tail(&key->list, rx->attrlist);
+ return 0;
+ }
+
+err_free:
+ /* remote value was garbage, junk it */
+ if (error == -EFSBADCRC || error == -EFSCORRUPTED)
+ error = 0;
+ kmem_free(key->value);
+ kmem_free(key);
+ 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;
+ unsigned long *usedmap = sc->buf;
+ 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;
+ char *buf_end;
+ size_t off;
+ unsigned int nameidx;
+ unsigned int hdrsize;
+ int i;
+ int error = 0;
+
+ bitmap_zero(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, 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++) {
+ /* Skip key if it conflicts with something else? */
+ off = (char *)ent - (char *)leaf;
+ if (!xchk_xattr_set_map(sc, 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)
+ break;
+ }
+
+ return error;
+}
+
+/* Try to recover shortform attrs. */
+STATIC int
+xrep_xattr_recover_sf(
+ struct xrep_xattr *rx)
+{
+ 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;
+
+ ifp = XFS_IFORK_PTR(rx->sc->ip, XFS_ATTR_FORK);
+ sf = (struct xfs_attr_shortform *)rx->sc->ip->i_afp->if_u1.if_data;
+ end = (unsigned char *)ifp->if_u1.if_data + ifp->if_bytes;
+
+ for (i = 0, sfe = &sf->list[0]; i < sf->hdr.count; i++) {
+ next = XFS_ATTR_SF_NEXTENTRY(sfe);
+ if ((unsigned char *)next > end)
+ break;
+
+ /* Ok, let's save this key/value. */
+ error = xrep_xattr_salvage_sf_attr(rx, sfe);
+ if (error)
+ return error;
+
+ sfe = next;
+ }
+
+ return 0;
+}
+
+/* Extract as many attribute keys and values as we can. */
+STATIC int
+xrep_xattr_recover(
+ struct xrep_xattr *rx)
+{
+ struct xfs_iext_cursor icur;
+ struct xfs_bmbt_irec got;
+ struct xfs_scrub *sc = rx->sc;
+ struct xfs_ifork *ifp;
+ struct xfs_da_blkinfo *info;
+ struct xfs_buf *bp;
+ xfs_dablk_t dabno;
+ int error = 0;
+
+ if (sc->ip->i_d.di_aformat == XFS_DINODE_FMT_LOCAL)
+ return xrep_xattr_recover_sf(rx);
+
+ /* Iterate each attr block in the attr fork. */
+ ifp = XFS_IFORK_PTR(sc->ip, XFS_ATTR_FORK);
+ for_each_xfs_iext(ifp, &icur, &got) {
+ for_each_xfs_attr_block(sc->mp, &got, dabno) {
+ /*
+ * Try to read buffer. We invalidate them in the next
+ * step so we don't bother to set a buffer type or
+ * ops.
+ */
+ error = xfs_da_read_buf(sc->tp, sc->ip, dabno, -1, &bp,
+ XFS_ATTR_FORK, NULL);
+ if (error || !bp)
+ continue;
+
+ /* Screen out non-leaves & other garbage. */
+ info = bp->b_addr;
+ if (info->magic != cpu_to_be16(XFS_ATTR3_LEAF_MAGIC) ||
+ xfs_attr3_leaf_buf_ops.verify_struct(bp) != NULL)
+ continue;
+
+ error = xrep_xattr_recover_leaf(rx, bp);
+ if (error)
+ return error;
+ }
+ }
+
+ return error;
+}
+
+/* Free all the attribute fork blocks and delete the fork. */
+STATIC int
+xrep_xattr_reset_btree(
+ struct xfs_scrub *sc)
+{
+ struct xfs_iext_cursor icur;
+ struct xfs_bmbt_irec got;
+ struct xfs_ifork *ifp;
+ struct xfs_buf *bp;
+ xfs_fileoff_t lblk;
+ int error;
+
+ xfs_trans_ijoin(sc->tp, sc->ip, 0);
+
+ if (sc->ip->i_d.di_aformat == XFS_DINODE_FMT_LOCAL)
+ goto out_fork_remove;
+
+ /* Invalidate each attr block in the attr fork. */
+ ifp = XFS_IFORK_PTR(sc->ip, XFS_ATTR_FORK);
+ for_each_xfs_iext(ifp, &icur, &got) {
+ for_each_xfs_attr_block(sc->mp, &got, lblk) {
+ error = xfs_da_get_buf(sc->tp, sc->ip, lblk, -1, &bp,
+ XFS_ATTR_FORK);
+ if (error || !bp)
+ continue;
+ xfs_trans_binval(sc->tp, bp);
+ error = xfs_trans_roll_inode(&sc->tp, sc->ip);
+ if (error)
+ return error;
+ }
+ }
+
+ /* Now free all the blocks. */
+ error = xfs_itruncate_extents(&sc->tp, sc->ip, XFS_ATTR_FORK, 0);
+ if (error)
+ return error;
+
+out_fork_remove:
+ /* Reset the attribute fork - this also destroys the in-core fork */
+ xfs_attr_fork_remove(sc->ip, sc->tp);
+ return 0;
+}
+
+/*
+ * Compare two xattr keys. ATTR_SECURE keys come before ATTR_ROOT and
+ * ATTR_ROOT keys come before user attrs. Otherwise sort in hash order.
+ */
+static int
+xrep_xattr_key_cmp(
+ void *priv,
+ struct list_head *a,
+ struct list_head *b)
+{
+ struct xrep_xattr_key *ap;
+ struct xrep_xattr_key *bp;
+ uint ahash;
+ uint bhash;
+
+ ap = container_of(a, struct xrep_xattr_key, list);
+ bp = container_of(b, struct xrep_xattr_key, list);
+
+ if (ap->flags > bp->flags)
+ return 1;
+ else if (ap->flags < bp->flags)
+ return -1;
+
+ ahash = xfs_da_hashname(ap->name, ap->namelen);
+ bhash = xfs_da_hashname(bp->name, bp->namelen);
+ if (ahash > bhash)
+ return 1;
+ else if (ahash < bhash)
+ return -1;
+ return 0;
+}
+
+/*
+ * Find all the extended attributes for this inode by scraping them out of the
+ * attribute key blocks by hand. The caller must clean up the lists if
+ * anything goes wrong.
+ */
+STATIC int
+xrep_xattr_find_attributes(
+ struct xfs_scrub *sc,
+ struct list_head *attrlist)
+{
+ struct xrep_xattr rx;
+ struct xfs_ifork *ifp;
+ int error;
+
+ error = xrep_ino_dqattach(sc);
+ if (error)
+ return error;
+
+ /* Extent map should be loaded. */
+ ifp = XFS_IFORK_PTR(sc->ip, XFS_ATTR_FORK);
+ if (XFS_IFORK_FORMAT(sc->ip, XFS_ATTR_FORK) != XFS_DINODE_FMT_LOCAL &&
+ !(ifp->if_flags & XFS_IFEXTENTS)) {
+ error = xfs_iread_extents(sc->tp, sc->ip, XFS_ATTR_FORK);
+ if (error)
+ return error;
+ }
+
+ rx.attrlist = attrlist;
+ rx.sc = sc;
+
+ /* Read every attr key and value and record them in memory. */
+ return xrep_xattr_recover(&rx);
+}
+
+/* Free all the attributes. */
+STATIC void
+xrep_xattr_cancel_attrs(
+ struct list_head *attrlist)
+{
+ struct xrep_xattr_key *key;
+ struct xrep_xattr_key *n;
+
+ list_for_each_entry_safe(key, n, attrlist, list) {
+ list_del(&key->list);
+ kmem_free(key->value);
+ kmem_free(key);
+ }
+}
+
+/*
+ * Insert all the attributes that we collected.
+ *
+ * Commit the repair transaction and drop the ilock because the attribute
+ * setting code needs to be able to allocate special transactions and take the
+ * ilock on its own. Some day we'll have deferred attribute setting, at which
+ * point we'll be able to use that to replace the attributes atomically and
+ * safely.
+ */
+STATIC int
+xrep_xattr_rebuild_tree(
+ struct xfs_scrub *sc,
+ struct list_head *attrlist)
+{
+ struct xrep_xattr_key *key;
+ struct xrep_xattr_key *n;
+ int error;
+
+ error = xfs_trans_commit(sc->tp);
+ sc->tp = NULL;
+ if (error)
+ return error;
+
+ xfs_iunlock(sc->ip, XFS_ILOCK_EXCL);
+ sc->ilock_flags &= ~XFS_ILOCK_EXCL;
+
+ /* Re-add every attr to the file. */
+ list_sort(NULL, attrlist, xrep_xattr_key_cmp);
+ list_for_each_entry_safe(key, n, attrlist, list) {
+ error = xfs_attr_set(sc->ip, key->name, key->value,
+ key->valuelen, key->flags);
+ if (error)
+ return error;
+
+ /*
+ * If the attr value is larger than a single page, free the
+ * key now so that we aren't hogging memory while doing a lot
+ * of metadata updates. Otherwise, we want to spend as little
+ * time reconstructing the attrs as we possibly can.
+ */
+ if (key->valuelen <= PAGE_SIZE)
+ continue;
+ list_del(&key->list);
+ kmem_free(key->value);
+ kmem_free(key);
+ }
+
+ xrep_xattr_cancel_attrs(attrlist);
+ return 0;
+}
+
+/*
+ * 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 list_head attrlist;
+ int error;
+
+ if (!xfs_inode_hasattr(sc->ip))
+ return -ENOENT;
+
+ /* Collect extended attributes by parsing raw blocks. */
+ INIT_LIST_HEAD(&attrlist);
+ error = xrep_xattr_find_attributes(sc, &attrlist);
+ if (error)
+ goto out;
+
+ /*
+ * Invalidate and truncate all attribute fork extents. This is the
+ * point at which we are no longer able to bail out gracefully.
+ * We commit the transaction here because xfs_attr_set allocates its
+ * own transactions.
+ */
+ error = xrep_xattr_reset_btree(sc);
+ if (error)
+ goto out;
+
+ /* Now rebuild the attribute information. */
+ error = xrep_xattr_rebuild_tree(sc, &attrlist);
+out:
+ xrep_xattr_cancel_attrs(&attrlist);
+ return error;
+}
@@ -69,6 +69,7 @@ int xrep_inode(struct xfs_scrub *sc);
int xrep_bmap_data(struct xfs_scrub *sc);
int xrep_bmap_attr(struct xfs_scrub *sc);
int xrep_symlink(struct xfs_scrub *sc);
+int xrep_xattr(struct xfs_scrub *sc);
#else
@@ -110,6 +111,7 @@ xrep_reset_perag_resv(
#define xrep_bmap_data xrep_notsupported
#define xrep_bmap_attr xrep_notsupported
#define xrep_symlink xrep_notsupported
+#define xrep_xattr xrep_notsupported
#endif /* CONFIG_XFS_ONLINE_REPAIR */
@@ -301,7 +301,7 @@ 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,
@@ -139,4 +139,7 @@ void xchk_xref_is_used_rt_space(struct xfs_scrub *sc, xfs_rtblock_t rtbno,
# define xchk_xref_is_used_rt_space(sc, rtbno, len) do { } while (0)
#endif
+bool xchk_xattr_set_map(struct xfs_scrub *sc, unsigned long *map,
+ unsigned int start, unsigned int len);
+
#endif /* __XFS_SCRUB_SCRUB_H__ */