aboutsummaryrefslogtreecommitdiffstats
path: root/fs/xfs/xfs_log_recover.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/xfs/xfs_log_recover.c')
-rw-r--r--fs/xfs/xfs_log_recover.c253
1 files changed, 156 insertions, 97 deletions
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index c1a514ffff55..d9b906d75dfa 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -471,7 +471,7 @@ xlog_find_verify_log_record(
xfs_warn(log->l_mp,
"Log inconsistent (didn't find previous header)");
ASSERT(0);
- error = -EIO;
+ error = -EFSCORRUPTED;
goto out;
}
@@ -1347,10 +1347,11 @@ xlog_find_tail(
error = xlog_rseek_logrec_hdr(log, *head_blk, *head_blk, 1, buffer,
&rhead_blk, &rhead, &wrapped);
if (error < 0)
- return error;
+ goto done;
if (!error) {
xfs_warn(log->l_mp, "%s: couldn't find sync record", __func__);
- return -EIO;
+ error = -EFSCORRUPTED;
+ goto done;
}
*tail_blk = BLOCK_LSN(be64_to_cpu(rhead->h_tail_lsn));
@@ -2205,6 +2206,8 @@ xlog_recover_get_buf_lsn(
case XFS_ABTC_MAGIC:
case XFS_RMAP_CRC_MAGIC:
case XFS_REFC_CRC_MAGIC:
+ case XFS_FIBT_CRC_MAGIC:
+ case XFS_FIBT_MAGIC:
case XFS_IBT_CRC_MAGIC:
case XFS_IBT_MAGIC: {
struct xfs_btree_block *btb = blk;
@@ -2576,6 +2579,7 @@ xlog_recover_do_reg_buffer(
int bit;
int nbits;
xfs_failaddr_t fa;
+ const size_t size_disk_dquot = sizeof(struct xfs_disk_dquot);
trace_xfs_log_recover_buf_reg_buf(mp->m_log, buf_f);
@@ -2618,7 +2622,7 @@ xlog_recover_do_reg_buffer(
"XFS: NULL dquot in %s.", __func__);
goto next;
}
- if (item->ri_buf[i].i_len < sizeof(xfs_disk_dquot_t)) {
+ if (item->ri_buf[i].i_len < size_disk_dquot) {
xfs_alert(mp,
"XFS: dquot too small (%d) in %s.",
item->ri_buf[i].i_len, __func__);
@@ -2779,6 +2783,16 @@ xlog_recover_buffer_pass2(
if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) >= 0) {
trace_xfs_log_recover_buf_skip(log, buf_f);
xlog_recover_validate_buf_type(mp, bp, buf_f, NULLCOMMITLSN);
+
+ /*
+ * We're skipping replay of this buffer log item due to the log
+ * item LSN being behind the ondisk buffer. Verify the buffer
+ * contents since we aren't going to run the write verifier.
+ */
+ if (bp->b_ops) {
+ bp->b_ops->verify_read(bp);
+ error = bp->b_error;
+ }
goto out_release;
}
@@ -2875,8 +2889,8 @@ xfs_recover_inode_owner_change(
return -ENOMEM;
/* instantiate the inode */
+ ASSERT(dip->di_version >= 3);
xfs_inode_from_disk(ip, dip);
- ASSERT(ip->i_d.di_version >= 3);
error = xfs_iformat_fork(ip, dip);
if (error)
@@ -3014,7 +3028,7 @@ xlog_recover_inode_pass2(
* superblock flag to determine whether we need to look at di_flushiter
* to skip replay when the on disk inode is newer than the log one
*/
- if (!xfs_sb_version_hascrc(&mp->m_sb) &&
+ if (!xfs_sb_version_has_v3inode(&mp->m_sb) &&
ldip->di_flushiter < be16_to_cpu(dip->di_flushiter)) {
/*
* Deal with the wrap case, DI_MAX_FLUSH is less
@@ -3085,7 +3099,7 @@ xlog_recover_inode_pass2(
error = -EFSCORRUPTED;
goto out_release;
}
- isize = xfs_log_dinode_size(ldip->di_version);
+ isize = xfs_log_dinode_size(mp);
if (unlikely(item->ri_buf[1].i_len > isize)) {
XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(7)",
XFS_ERRLEVEL_LOW, mp, ldip,
@@ -3166,7 +3180,7 @@ xlog_recover_inode_pass2(
default:
xfs_warn(log->l_mp, "%s: Invalid flag", __func__);
ASSERT(0);
- error = -EIO;
+ error = -EFSCORRUPTED;
goto out_release;
}
}
@@ -3247,12 +3261,12 @@ xlog_recover_dquot_pass2(
recddq = item->ri_buf[1].i_addr;
if (recddq == NULL) {
xfs_alert(log->l_mp, "NULL dquot in %s.", __func__);
- return -EIO;
+ return -EFSCORRUPTED;
}
- if (item->ri_buf[1].i_len < sizeof(xfs_disk_dquot_t)) {
+ if (item->ri_buf[1].i_len < sizeof(struct xfs_disk_dquot)) {
xfs_alert(log->l_mp, "dquot too small (%d) in %s.",
item->ri_buf[1].i_len, __func__);
- return -EIO;
+ return -EFSCORRUPTED;
}
/*
@@ -3279,7 +3293,7 @@ xlog_recover_dquot_pass2(
if (fa) {
xfs_alert(mp, "corrupt dquot ID 0x%x in log at %pS",
dq_f->qlf_id, fa);
- return -EIO;
+ return -EFSCORRUPTED;
}
ASSERT(dq_f->qlf_len == 1);
@@ -3382,7 +3396,7 @@ xlog_recover_efd_pass2(
struct xlog_recover_item *item)
{
xfs_efd_log_format_t *efd_formatp;
- xfs_efi_log_item_t *efip = NULL;
+ struct xfs_efi_log_item *efip = NULL;
struct xfs_log_item *lip;
uint64_t efi_id;
struct xfs_ail_cursor cur;
@@ -3403,7 +3417,7 @@ xlog_recover_efd_pass2(
lip = xfs_trans_ail_cursor_first(ailp, &cur, 0);
while (lip != NULL) {
if (lip->li_type == XFS_LI_EFI) {
- efip = (xfs_efi_log_item_t *)lip;
+ efip = (struct xfs_efi_log_item *)lip;
if (efip->efi_format.efi_id == efi_id) {
/*
* Drop the EFD reference to the EFI. This
@@ -3537,6 +3551,7 @@ xfs_cui_copy_format(
memcpy(dst_cui_fmt, src_cui_fmt, len);
return 0;
}
+ XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL);
return -EFSCORRUPTED;
}
@@ -3601,8 +3616,10 @@ xlog_recover_cud_pass2(
struct xfs_ail *ailp = log->l_ailp;
cud_formatp = item->ri_buf[0].i_addr;
- if (item->ri_buf[0].i_len != sizeof(struct xfs_cud_log_format))
+ if (item->ri_buf[0].i_len != sizeof(struct xfs_cud_log_format)) {
+ XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp);
return -EFSCORRUPTED;
+ }
cui_id = cud_formatp->cud_cui_id;
/*
@@ -3654,6 +3671,7 @@ xfs_bui_copy_format(
memcpy(dst_bui_fmt, src_bui_fmt, len);
return 0;
}
+ XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL);
return -EFSCORRUPTED;
}
@@ -3677,8 +3695,10 @@ xlog_recover_bui_pass2(
bui_formatp = item->ri_buf[0].i_addr;
- if (bui_formatp->bui_nextents != XFS_BUI_MAX_FAST_EXTENTS)
+ if (bui_formatp->bui_nextents != XFS_BUI_MAX_FAST_EXTENTS) {
+ XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp);
return -EFSCORRUPTED;
+ }
buip = xfs_bui_init(mp);
error = xfs_bui_copy_format(&item->ri_buf[0], &buip->bui_format);
if (error) {
@@ -3720,8 +3740,10 @@ xlog_recover_bud_pass2(
struct xfs_ail *ailp = log->l_ailp;
bud_formatp = item->ri_buf[0].i_addr;
- if (item->ri_buf[0].i_len != sizeof(struct xfs_bud_log_format))
+ if (item->ri_buf[0].i_len != sizeof(struct xfs_bud_log_format)) {
+ XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp);
return -EFSCORRUPTED;
+ }
bui_id = bud_formatp->bud_bui_id;
/*
@@ -4018,7 +4040,7 @@ xlog_recover_commit_pass1(
xfs_warn(log->l_mp, "%s: invalid item type (%d)",
__func__, ITEM_TYPE(item));
ASSERT(0);
- return -EIO;
+ return -EFSCORRUPTED;
}
}
@@ -4066,7 +4088,7 @@ xlog_recover_commit_pass2(
xfs_warn(log->l_mp, "%s: invalid item type (%d)",
__func__, ITEM_TYPE(item));
ASSERT(0);
- return -EIO;
+ return -EFSCORRUPTED;
}
}
@@ -4187,7 +4209,7 @@ xlog_recover_add_to_cont_trans(
ASSERT(len <= sizeof(struct xfs_trans_header));
if (len > sizeof(struct xfs_trans_header)) {
xfs_warn(log->l_mp, "%s: bad header length", __func__);
- return -EIO;
+ return -EFSCORRUPTED;
}
xlog_recover_add_item(&trans->r_itemq);
@@ -4243,13 +4265,13 @@ xlog_recover_add_to_trans(
xfs_warn(log->l_mp, "%s: bad header magic number",
__func__);
ASSERT(0);
- return -EIO;
+ return -EFSCORRUPTED;
}
if (len > sizeof(struct xfs_trans_header)) {
xfs_warn(log->l_mp, "%s: bad header length", __func__);
ASSERT(0);
- return -EIO;
+ return -EFSCORRUPTED;
}
/*
@@ -4285,7 +4307,7 @@ xlog_recover_add_to_trans(
in_f->ilf_size);
ASSERT(0);
kmem_free(ptr);
- return -EIO;
+ return -EFSCORRUPTED;
}
item->ri_total = in_f->ilf_size;
@@ -4293,7 +4315,16 @@ xlog_recover_add_to_trans(
kmem_zalloc(item->ri_total * sizeof(xfs_log_iovec_t),
0);
}
- ASSERT(item->ri_total > item->ri_cnt);
+
+ if (item->ri_total <= item->ri_cnt) {
+ xfs_warn(log->l_mp,
+ "log item region count (%d) overflowed size (%d)",
+ item->ri_cnt, item->ri_total);
+ ASSERT(0);
+ kmem_free(ptr);
+ return -EFSCORRUPTED;
+ }
+
/* Description region is ri_buf[0] */
item->ri_buf[item->ri_cnt].i_addr = ptr;
item->ri_buf[item->ri_cnt].i_len = len;
@@ -4380,7 +4411,7 @@ xlog_recovery_process_trans(
default:
xfs_warn(log->l_mp, "%s: bad flag 0x%x", __func__, flags);
ASSERT(0);
- error = -EIO;
+ error = -EFSCORRUPTED;
break;
}
if (error || freeit)
@@ -4460,7 +4491,7 @@ xlog_recover_process_ophdr(
xfs_warn(log->l_mp, "%s: bad clientid 0x%x",
__func__, ohead->oh_clientid);
ASSERT(0);
- return -EIO;
+ return -EFSCORRUPTED;
}
/*
@@ -4470,7 +4501,7 @@ xlog_recover_process_ophdr(
if (dp + len > end) {
xfs_warn(log->l_mp, "%s: bad length 0x%x", __func__, len);
WARN_ON(1);
- return -EIO;
+ return -EFSCORRUPTED;
}
trans = xlog_recover_ophdr_to_trans(rhash, rhead, ohead);
@@ -4566,9 +4597,9 @@ xlog_recover_process_data(
/* Recover the EFI if necessary. */
STATIC int
xlog_recover_process_efi(
- struct xfs_mount *mp,
struct xfs_ail *ailp,
- struct xfs_log_item *lip)
+ struct xfs_log_item *lip,
+ struct list_head *capture_list)
{
struct xfs_efi_log_item *efip;
int error;
@@ -4581,7 +4612,7 @@ xlog_recover_process_efi(
return 0;
spin_unlock(&ailp->ail_lock);
- error = xfs_efi_recover(mp, efip);
+ error = xfs_efi_recover(efip, capture_list);
spin_lock(&ailp->ail_lock);
return error;
@@ -4606,9 +4637,9 @@ xlog_recover_cancel_efi(
/* Recover the RUI if necessary. */
STATIC int
xlog_recover_process_rui(
- struct xfs_mount *mp,
struct xfs_ail *ailp,
- struct xfs_log_item *lip)
+ struct xfs_log_item *lip,
+ struct list_head *capture_list)
{
struct xfs_rui_log_item *ruip;
int error;
@@ -4621,7 +4652,7 @@ xlog_recover_process_rui(
return 0;
spin_unlock(&ailp->ail_lock);
- error = xfs_rui_recover(mp, ruip);
+ error = xfs_rui_recover(ruip, capture_list);
spin_lock(&ailp->ail_lock);
return error;
@@ -4646,9 +4677,9 @@ xlog_recover_cancel_rui(
/* Recover the CUI if necessary. */
STATIC int
xlog_recover_process_cui(
- struct xfs_trans *parent_tp,
struct xfs_ail *ailp,
- struct xfs_log_item *lip)
+ struct xfs_log_item *lip,
+ struct list_head *capture_list)
{
struct xfs_cui_log_item *cuip;
int error;
@@ -4661,7 +4692,7 @@ xlog_recover_process_cui(
return 0;
spin_unlock(&ailp->ail_lock);
- error = xfs_cui_recover(parent_tp, cuip);
+ error = xfs_cui_recover(cuip, capture_list);
spin_lock(&ailp->ail_lock);
return error;
@@ -4686,9 +4717,9 @@ xlog_recover_cancel_cui(
/* Recover the BUI if necessary. */
STATIC int
xlog_recover_process_bui(
- struct xfs_trans *parent_tp,
struct xfs_ail *ailp,
- struct xfs_log_item *lip)
+ struct xfs_log_item *lip,
+ struct list_head *capture_list)
{
struct xfs_bui_log_item *buip;
int error;
@@ -4701,7 +4732,7 @@ xlog_recover_process_bui(
return 0;
spin_unlock(&ailp->ail_lock);
- error = xfs_bui_recover(parent_tp, buip);
+ error = xfs_bui_recover(buip, capture_list);
spin_lock(&ailp->ail_lock);
return error;
@@ -4740,37 +4771,66 @@ static inline bool xlog_item_is_intent(struct xfs_log_item *lip)
/* Take all the collected deferred ops and finish them in order. */
static int
xlog_finish_defer_ops(
- struct xfs_trans *parent_tp)
+ struct xfs_mount *mp,
+ struct list_head *capture_list)
{
- struct xfs_mount *mp = parent_tp->t_mountp;
+ struct xfs_defer_capture *dfc, *next;
struct xfs_trans *tp;
- int64_t freeblks;
- uint resblks;
- int error;
+ struct xfs_inode *ip;
+ int error = 0;
- /*
- * We're finishing the defer_ops that accumulated as a result of
- * recovering unfinished intent items during log recovery. We
- * reserve an itruncate transaction because it is the largest
- * permanent transaction type. Since we're the only user of the fs
- * right now, take 93% (15/16) of the available free blocks. Use
- * weird math to avoid a 64-bit division.
- */
- freeblks = percpu_counter_sum(&mp->m_fdblocks);
- if (freeblks <= 0)
- return -ENOSPC;
- resblks = min_t(int64_t, UINT_MAX, freeblks);
- resblks = (resblks * 15) >> 4;
- error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, resblks,
- 0, XFS_TRANS_RESERVE, &tp);
- if (error)
- return error;
- /* transfer all collected dfops to this transaction */
- xfs_defer_move(tp, parent_tp);
+ list_for_each_entry_safe(dfc, next, capture_list, dfc_list) {
+ struct xfs_trans_res resv;
+
+ /*
+ * Create a new transaction reservation from the captured
+ * information. Set logcount to 1 to force the new transaction
+ * to regrant every roll so that we can make forward progress
+ * in recovery no matter how full the log might be.
+ */
+ resv.tr_logres = dfc->dfc_logres;
+ resv.tr_logcount = 1;
+ resv.tr_logflags = XFS_TRANS_PERM_LOG_RES;
+
+ error = xfs_trans_alloc(mp, &resv, dfc->dfc_blkres,
+ dfc->dfc_rtxres, XFS_TRANS_RESERVE, &tp);
+ if (error)
+ return error;
- return xfs_trans_commit(tp);
+ /*
+ * Transfer to this new transaction all the dfops we captured
+ * from recovering a single intent item.
+ */
+ list_del_init(&dfc->dfc_list);
+ xfs_defer_ops_continue(dfc, tp, &ip);
+
+ error = xfs_trans_commit(tp);
+ if (ip) {
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ xfs_irele(ip);
+ }
+ if (error)
+ return error;
+ }
+
+ ASSERT(list_empty(capture_list));
+ return 0;
}
+/* Release all the captured defer ops and capture structures in this list. */
+static void
+xlog_abort_defer_ops(
+ struct xfs_mount *mp,
+ struct list_head *capture_list)
+{
+ struct xfs_defer_capture *dfc;
+ struct xfs_defer_capture *next;
+
+ list_for_each_entry_safe(dfc, next, capture_list, dfc_list) {
+ list_del_init(&dfc->dfc_list);
+ xfs_defer_ops_release(mp, dfc);
+ }
+}
/*
* When this is called, all of the log intent items which did not have
* corresponding log done items should be in the AIL. What we do now
@@ -4791,35 +4851,23 @@ STATIC int
xlog_recover_process_intents(
struct xlog *log)
{
- struct xfs_trans *parent_tp;
+ LIST_HEAD(capture_list);
struct xfs_ail_cursor cur;
struct xfs_log_item *lip;
struct xfs_ail *ailp;
- int error;
+ int error = 0;
#if defined(DEBUG) || defined(XFS_WARN)
xfs_lsn_t last_lsn;
#endif
- /*
- * The intent recovery handlers commit transactions to complete recovery
- * for individual intents, but any new deferred operations that are
- * queued during that process are held off until the very end. The
- * purpose of this transaction is to serve as a container for deferred
- * operations. Each intent recovery handler must transfer dfops here
- * before its local transaction commits, and we'll finish the entire
- * list below.
- */
- error = xfs_trans_alloc_empty(log->l_mp, &parent_tp);
- if (error)
- return error;
-
ailp = log->l_ailp;
spin_lock(&ailp->ail_lock);
- lip = xfs_trans_ail_cursor_first(ailp, &cur, 0);
#if defined(DEBUG) || defined(XFS_WARN)
last_lsn = xlog_assign_lsn(log->l_curr_cycle, log->l_curr_block);
#endif
- while (lip != NULL) {
+ for (lip = xfs_trans_ail_cursor_first(ailp, &cur, 0);
+ lip != NULL;
+ lip = xfs_trans_ail_cursor_next(ailp, &cur)) {
/*
* We're done when we see something other than an intent.
* There should be no intents left in the AIL now.
@@ -4841,35 +4889,40 @@ xlog_recover_process_intents(
/*
* NOTE: If your intent processing routine can create more
- * deferred ops, you /must/ attach them to the dfops in this
- * routine or else those subsequent intents will get
+ * deferred ops, you /must/ attach them to the capture list in
+ * the recover routine or else those subsequent intents will be
* replayed in the wrong order!
*/
switch (lip->li_type) {
case XFS_LI_EFI:
- error = xlog_recover_process_efi(log->l_mp, ailp, lip);
+ error = xlog_recover_process_efi(ailp, lip, &capture_list);
break;
case XFS_LI_RUI:
- error = xlog_recover_process_rui(log->l_mp, ailp, lip);
+ error = xlog_recover_process_rui(ailp, lip, &capture_list);
break;
case XFS_LI_CUI:
- error = xlog_recover_process_cui(parent_tp, ailp, lip);
+ error = xlog_recover_process_cui(ailp, lip, &capture_list);
break;
case XFS_LI_BUI:
- error = xlog_recover_process_bui(parent_tp, ailp, lip);
+ error = xlog_recover_process_bui(ailp, lip, &capture_list);
break;
}
if (error)
- goto out;
- lip = xfs_trans_ail_cursor_next(ailp, &cur);
+ break;
}
-out:
+
xfs_trans_ail_cursor_done(&cur);
spin_unlock(&ailp->ail_lock);
- if (!error)
- error = xlog_finish_defer_ops(parent_tp);
- xfs_trans_cancel(parent_tp);
+ if (error)
+ goto err;
+
+ error = xlog_finish_defer_ops(log->l_mp, &capture_list);
+ if (error)
+ goto err;
+ return 0;
+err:
+ xlog_abort_defer_ops(log->l_mp, &capture_list);
return error;
}
@@ -5172,8 +5225,10 @@ xlog_recover_process(
* If the filesystem is CRC enabled, this mismatch becomes a
* fatal log corruption failure.
*/
- if (xfs_sb_version_hascrc(&log->l_mp->m_sb))
+ if (xfs_sb_version_hascrc(&log->l_mp->m_sb)) {
+ XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp);
return -EFSCORRUPTED;
+ }
}
xlog_unpack_data(rhead, dp, log);
@@ -5200,7 +5255,7 @@ xlog_valid_rec_header(
(be32_to_cpu(rhead->h_version) & (~XLOG_VERSION_OKBITS))))) {
xfs_warn(log->l_mp, "%s: unrecognised log version (%d).",
__func__, be32_to_cpu(rhead->h_version));
- return -EIO;
+ return -EFSCORRUPTED;
}
/* LR body must have data or it wouldn't have been written */
@@ -5296,8 +5351,12 @@ xlog_do_recovery_pass(
"invalid iclog size (%d bytes), using lsunit (%d bytes)",
h_size, log->l_mp->m_logbsize);
h_size = log->l_mp->m_logbsize;
- } else
- return -EFSCORRUPTED;
+ } else {
+ XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW,
+ log->l_mp);
+ error = -EFSCORRUPTED;
+ goto bread_err1;
+ }
}
if ((be32_to_cpu(rhead->h_version) & XLOG_VERSION_2) &&
generated by cgit 1.2.3-korg (git 2.39.0) at 2024-05-01 07:49:29 +0000