forked from Qortal/Brooklyn
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
964 lines
28 KiB
964 lines
28 KiB
// SPDX-License-Identifier: GPL-2.0+ |
|
/* |
|
* Copyright (C) 2018 Oracle. All Rights Reserved. |
|
* Author: Darrick J. Wong <[email protected]> |
|
*/ |
|
#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_btree.h" |
|
#include "xfs_log_format.h" |
|
#include "xfs_trans.h" |
|
#include "xfs_sb.h" |
|
#include "xfs_inode.h" |
|
#include "xfs_alloc.h" |
|
#include "xfs_alloc_btree.h" |
|
#include "xfs_ialloc.h" |
|
#include "xfs_ialloc_btree.h" |
|
#include "xfs_rmap.h" |
|
#include "xfs_rmap_btree.h" |
|
#include "xfs_refcount_btree.h" |
|
#include "xfs_extent_busy.h" |
|
#include "xfs_ag.h" |
|
#include "xfs_ag_resv.h" |
|
#include "xfs_quota.h" |
|
#include "xfs_qm.h" |
|
#include "scrub/scrub.h" |
|
#include "scrub/common.h" |
|
#include "scrub/trace.h" |
|
#include "scrub/repair.h" |
|
#include "scrub/bitmap.h" |
|
|
|
/* |
|
* Attempt to repair some metadata, if the metadata is corrupt and userspace |
|
* told us to fix it. This function returns -EAGAIN to mean "re-run scrub", |
|
* and will set *fixed to true if it thinks it repaired anything. |
|
*/ |
|
int |
|
xrep_attempt( |
|
struct xfs_scrub *sc) |
|
{ |
|
int error = 0; |
|
|
|
trace_xrep_attempt(XFS_I(file_inode(sc->file)), sc->sm, error); |
|
|
|
xchk_ag_btcur_free(&sc->sa); |
|
|
|
/* Repair whatever's broken. */ |
|
ASSERT(sc->ops->repair); |
|
error = sc->ops->repair(sc); |
|
trace_xrep_done(XFS_I(file_inode(sc->file)), sc->sm, error); |
|
switch (error) { |
|
case 0: |
|
/* |
|
* Repair succeeded. Commit the fixes and perform a second |
|
* scrub so that we can tell userspace if we fixed the problem. |
|
*/ |
|
sc->sm->sm_flags &= ~XFS_SCRUB_FLAGS_OUT; |
|
sc->flags |= XREP_ALREADY_FIXED; |
|
return -EAGAIN; |
|
case -EDEADLOCK: |
|
case -EAGAIN: |
|
/* Tell the caller to try again having grabbed all the locks. */ |
|
if (!(sc->flags & XCHK_TRY_HARDER)) { |
|
sc->flags |= XCHK_TRY_HARDER; |
|
return -EAGAIN; |
|
} |
|
/* |
|
* We tried harder but still couldn't grab all the resources |
|
* we needed to fix it. The corruption has not been fixed, |
|
* so report back to userspace. |
|
*/ |
|
return -EFSCORRUPTED; |
|
default: |
|
return error; |
|
} |
|
} |
|
|
|
/* |
|
* Complain about unfixable problems in the filesystem. We don't log |
|
* corruptions when IFLAG_REPAIR wasn't set on the assumption that the driver |
|
* program is xfs_scrub, which will call back with IFLAG_REPAIR set if the |
|
* administrator isn't running xfs_scrub in no-repairs mode. |
|
* |
|
* Use this helper function because _ratelimited silently declares a static |
|
* structure to track rate limiting information. |
|
*/ |
|
void |
|
xrep_failure( |
|
struct xfs_mount *mp) |
|
{ |
|
xfs_alert_ratelimited(mp, |
|
"Corruption not fixed during online repair. Unmount and run xfs_repair."); |
|
} |
|
|
|
/* |
|
* Repair probe -- userspace uses this to probe if we're willing to repair a |
|
* given mountpoint. |
|
*/ |
|
int |
|
xrep_probe( |
|
struct xfs_scrub *sc) |
|
{ |
|
int error = 0; |
|
|
|
if (xchk_should_terminate(sc, &error)) |
|
return error; |
|
|
|
return 0; |
|
} |
|
|
|
/* |
|
* Roll a transaction, keeping the AG headers locked and reinitializing |
|
* the btree cursors. |
|
*/ |
|
int |
|
xrep_roll_ag_trans( |
|
struct xfs_scrub *sc) |
|
{ |
|
int error; |
|
|
|
/* Keep the AG header buffers locked so we can keep going. */ |
|
if (sc->sa.agi_bp) |
|
xfs_trans_bhold(sc->tp, sc->sa.agi_bp); |
|
if (sc->sa.agf_bp) |
|
xfs_trans_bhold(sc->tp, sc->sa.agf_bp); |
|
if (sc->sa.agfl_bp) |
|
xfs_trans_bhold(sc->tp, sc->sa.agfl_bp); |
|
|
|
/* |
|
* Roll the transaction. We still own the buffer and the buffer lock |
|
* regardless of whether or not the roll succeeds. If the roll fails, |
|
* the buffers will be released during teardown on our way out of the |
|
* kernel. If it succeeds, we join them to the new transaction and |
|
* move on. |
|
*/ |
|
error = xfs_trans_roll(&sc->tp); |
|
if (error) |
|
return error; |
|
|
|
/* Join AG headers to the new transaction. */ |
|
if (sc->sa.agi_bp) |
|
xfs_trans_bjoin(sc->tp, sc->sa.agi_bp); |
|
if (sc->sa.agf_bp) |
|
xfs_trans_bjoin(sc->tp, sc->sa.agf_bp); |
|
if (sc->sa.agfl_bp) |
|
xfs_trans_bjoin(sc->tp, sc->sa.agfl_bp); |
|
|
|
return 0; |
|
} |
|
|
|
/* |
|
* Does the given AG have enough space to rebuild a btree? Neither AG |
|
* reservation can be critical, and we must have enough space (factoring |
|
* in AG reservations) to construct a whole btree. |
|
*/ |
|
bool |
|
xrep_ag_has_space( |
|
struct xfs_perag *pag, |
|
xfs_extlen_t nr_blocks, |
|
enum xfs_ag_resv_type type) |
|
{ |
|
return !xfs_ag_resv_critical(pag, XFS_AG_RESV_RMAPBT) && |
|
!xfs_ag_resv_critical(pag, XFS_AG_RESV_METADATA) && |
|
pag->pagf_freeblks > xfs_ag_resv_needed(pag, type) + nr_blocks; |
|
} |
|
|
|
/* |
|
* Figure out how many blocks to reserve for an AG repair. We calculate the |
|
* worst case estimate for the number of blocks we'd need to rebuild one of |
|
* any type of per-AG btree. |
|
*/ |
|
xfs_extlen_t |
|
xrep_calc_ag_resblks( |
|
struct xfs_scrub *sc) |
|
{ |
|
struct xfs_mount *mp = sc->mp; |
|
struct xfs_scrub_metadata *sm = sc->sm; |
|
struct xfs_perag *pag; |
|
struct xfs_buf *bp; |
|
xfs_agino_t icount = NULLAGINO; |
|
xfs_extlen_t aglen = NULLAGBLOCK; |
|
xfs_extlen_t usedlen; |
|
xfs_extlen_t freelen; |
|
xfs_extlen_t bnobt_sz; |
|
xfs_extlen_t inobt_sz; |
|
xfs_extlen_t rmapbt_sz; |
|
xfs_extlen_t refcbt_sz; |
|
int error; |
|
|
|
if (!(sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR)) |
|
return 0; |
|
|
|
pag = xfs_perag_get(mp, sm->sm_agno); |
|
if (pag->pagi_init) { |
|
/* Use in-core icount if possible. */ |
|
icount = pag->pagi_count; |
|
} else { |
|
/* Try to get the actual counters from disk. */ |
|
error = xfs_ialloc_read_agi(mp, NULL, sm->sm_agno, &bp); |
|
if (!error) { |
|
icount = pag->pagi_count; |
|
xfs_buf_relse(bp); |
|
} |
|
} |
|
|
|
/* Now grab the block counters from the AGF. */ |
|
error = xfs_alloc_read_agf(mp, NULL, sm->sm_agno, 0, &bp); |
|
if (error) { |
|
aglen = xfs_ag_block_count(mp, sm->sm_agno); |
|
freelen = aglen; |
|
usedlen = aglen; |
|
} else { |
|
struct xfs_agf *agf = bp->b_addr; |
|
|
|
aglen = be32_to_cpu(agf->agf_length); |
|
freelen = be32_to_cpu(agf->agf_freeblks); |
|
usedlen = aglen - freelen; |
|
xfs_buf_relse(bp); |
|
} |
|
xfs_perag_put(pag); |
|
|
|
/* If the icount is impossible, make some worst-case assumptions. */ |
|
if (icount == NULLAGINO || |
|
!xfs_verify_agino(mp, sm->sm_agno, icount)) { |
|
xfs_agino_t first, last; |
|
|
|
xfs_agino_range(mp, sm->sm_agno, &first, &last); |
|
icount = last - first + 1; |
|
} |
|
|
|
/* If the block counts are impossible, make worst-case assumptions. */ |
|
if (aglen == NULLAGBLOCK || |
|
aglen != xfs_ag_block_count(mp, sm->sm_agno) || |
|
freelen >= aglen) { |
|
aglen = xfs_ag_block_count(mp, sm->sm_agno); |
|
freelen = aglen; |
|
usedlen = aglen; |
|
} |
|
|
|
trace_xrep_calc_ag_resblks(mp, sm->sm_agno, icount, aglen, |
|
freelen, usedlen); |
|
|
|
/* |
|
* Figure out how many blocks we'd need worst case to rebuild |
|
* each type of btree. Note that we can only rebuild the |
|
* bnobt/cntbt or inobt/finobt as pairs. |
|
*/ |
|
bnobt_sz = 2 * xfs_allocbt_calc_size(mp, freelen); |
|
if (xfs_has_sparseinodes(mp)) |
|
inobt_sz = xfs_iallocbt_calc_size(mp, icount / |
|
XFS_INODES_PER_HOLEMASK_BIT); |
|
else |
|
inobt_sz = xfs_iallocbt_calc_size(mp, icount / |
|
XFS_INODES_PER_CHUNK); |
|
if (xfs_has_finobt(mp)) |
|
inobt_sz *= 2; |
|
if (xfs_has_reflink(mp)) |
|
refcbt_sz = xfs_refcountbt_calc_size(mp, usedlen); |
|
else |
|
refcbt_sz = 0; |
|
if (xfs_has_rmapbt(mp)) { |
|
/* |
|
* Guess how many blocks we need to rebuild the rmapbt. |
|
* For non-reflink filesystems we can't have more records than |
|
* used blocks. However, with reflink it's possible to have |
|
* more than one rmap record per AG block. We don't know how |
|
* many rmaps there could be in the AG, so we start off with |
|
* what we hope is an generous over-estimation. |
|
*/ |
|
if (xfs_has_reflink(mp)) |
|
rmapbt_sz = xfs_rmapbt_calc_size(mp, |
|
(unsigned long long)aglen * 2); |
|
else |
|
rmapbt_sz = xfs_rmapbt_calc_size(mp, usedlen); |
|
} else { |
|
rmapbt_sz = 0; |
|
} |
|
|
|
trace_xrep_calc_ag_resblks_btsize(mp, sm->sm_agno, bnobt_sz, |
|
inobt_sz, rmapbt_sz, refcbt_sz); |
|
|
|
return max(max(bnobt_sz, inobt_sz), max(rmapbt_sz, refcbt_sz)); |
|
} |
|
|
|
/* Allocate a block in an AG. */ |
|
int |
|
xrep_alloc_ag_block( |
|
struct xfs_scrub *sc, |
|
const struct xfs_owner_info *oinfo, |
|
xfs_fsblock_t *fsbno, |
|
enum xfs_ag_resv_type resv) |
|
{ |
|
struct xfs_alloc_arg args = {0}; |
|
xfs_agblock_t bno; |
|
int error; |
|
|
|
switch (resv) { |
|
case XFS_AG_RESV_AGFL: |
|
case XFS_AG_RESV_RMAPBT: |
|
error = xfs_alloc_get_freelist(sc->tp, sc->sa.agf_bp, &bno, 1); |
|
if (error) |
|
return error; |
|
if (bno == NULLAGBLOCK) |
|
return -ENOSPC; |
|
xfs_extent_busy_reuse(sc->mp, sc->sa.pag, bno, |
|
1, false); |
|
*fsbno = XFS_AGB_TO_FSB(sc->mp, sc->sa.pag->pag_agno, bno); |
|
if (resv == XFS_AG_RESV_RMAPBT) |
|
xfs_ag_resv_rmapbt_alloc(sc->mp, sc->sa.pag->pag_agno); |
|
return 0; |
|
default: |
|
break; |
|
} |
|
|
|
args.tp = sc->tp; |
|
args.mp = sc->mp; |
|
args.oinfo = *oinfo; |
|
args.fsbno = XFS_AGB_TO_FSB(args.mp, sc->sa.pag->pag_agno, 0); |
|
args.minlen = 1; |
|
args.maxlen = 1; |
|
args.prod = 1; |
|
args.type = XFS_ALLOCTYPE_THIS_AG; |
|
args.resv = resv; |
|
|
|
error = xfs_alloc_vextent(&args); |
|
if (error) |
|
return error; |
|
if (args.fsbno == NULLFSBLOCK) |
|
return -ENOSPC; |
|
ASSERT(args.len == 1); |
|
*fsbno = args.fsbno; |
|
|
|
return 0; |
|
} |
|
|
|
/* Initialize a new AG btree root block with zero entries. */ |
|
int |
|
xrep_init_btblock( |
|
struct xfs_scrub *sc, |
|
xfs_fsblock_t fsb, |
|
struct xfs_buf **bpp, |
|
xfs_btnum_t btnum, |
|
const struct xfs_buf_ops *ops) |
|
{ |
|
struct xfs_trans *tp = sc->tp; |
|
struct xfs_mount *mp = sc->mp; |
|
struct xfs_buf *bp; |
|
int error; |
|
|
|
trace_xrep_init_btblock(mp, XFS_FSB_TO_AGNO(mp, fsb), |
|
XFS_FSB_TO_AGBNO(mp, fsb), btnum); |
|
|
|
ASSERT(XFS_FSB_TO_AGNO(mp, fsb) == sc->sa.pag->pag_agno); |
|
error = xfs_trans_get_buf(tp, mp->m_ddev_targp, |
|
XFS_FSB_TO_DADDR(mp, fsb), XFS_FSB_TO_BB(mp, 1), 0, |
|
&bp); |
|
if (error) |
|
return error; |
|
xfs_buf_zero(bp, 0, BBTOB(bp->b_length)); |
|
xfs_btree_init_block(mp, bp, btnum, 0, 0, sc->sa.pag->pag_agno); |
|
xfs_trans_buf_set_type(tp, bp, XFS_BLFT_BTREE_BUF); |
|
xfs_trans_log_buf(tp, bp, 0, BBTOB(bp->b_length) - 1); |
|
bp->b_ops = ops; |
|
*bpp = bp; |
|
|
|
return 0; |
|
} |
|
|
|
/* |
|
* Reconstructing per-AG Btrees |
|
* |
|
* When a space btree is corrupt, we don't bother trying to fix it. Instead, |
|
* we scan secondary space metadata to derive the records that should be in |
|
* the damaged btree, initialize a fresh btree root, and insert the records. |
|
* Note that for rebuilding the rmapbt we scan all the primary data to |
|
* generate the new records. |
|
* |
|
* However, that leaves the matter of removing all the metadata describing the |
|
* old broken structure. For primary metadata we use the rmap data to collect |
|
* every extent with a matching rmap owner (bitmap); we then iterate all other |
|
* metadata structures with the same rmap owner to collect the extents that |
|
* cannot be removed (sublist). We then subtract sublist from bitmap to |
|
* derive the blocks that were used by the old btree. These blocks can be |
|
* reaped. |
|
* |
|
* For rmapbt reconstructions we must use different tactics for extent |
|
* collection. First we iterate all primary metadata (this excludes the old |
|
* rmapbt, obviously) to generate new rmap records. The gaps in the rmap |
|
* records are collected as bitmap. The bnobt records are collected as |
|
* sublist. As with the other btrees we subtract sublist from bitmap, and the |
|
* result (since the rmapbt lives in the free space) are the blocks from the |
|
* old rmapbt. |
|
* |
|
* Disposal of Blocks from Old per-AG Btrees |
|
* |
|
* Now that we've constructed a new btree to replace the damaged one, we want |
|
* to dispose of the blocks that (we think) the old btree was using. |
|
* Previously, we used the rmapbt to collect the extents (bitmap) with the |
|
* rmap owner corresponding to the tree we rebuilt, collected extents for any |
|
* blocks with the same rmap owner that are owned by another data structure |
|
* (sublist), and subtracted sublist from bitmap. In theory the extents |
|
* remaining in bitmap are the old btree's blocks. |
|
* |
|
* Unfortunately, it's possible that the btree was crosslinked with other |
|
* blocks on disk. The rmap data can tell us if there are multiple owners, so |
|
* if the rmapbt says there is an owner of this block other than @oinfo, then |
|
* the block is crosslinked. Remove the reverse mapping and continue. |
|
* |
|
* If there is one rmap record, we can free the block, which removes the |
|
* reverse mapping but doesn't add the block to the free space. Our repair |
|
* strategy is to hope the other metadata objects crosslinked on this block |
|
* will be rebuilt (atop different blocks), thereby removing all the cross |
|
* links. |
|
* |
|
* If there are no rmap records at all, we also free the block. If the btree |
|
* being rebuilt lives in the free space (bnobt/cntbt/rmapbt) then there isn't |
|
* supposed to be a rmap record and everything is ok. For other btrees there |
|
* had to have been an rmap entry for the block to have ended up on @bitmap, |
|
* so if it's gone now there's something wrong and the fs will shut down. |
|
* |
|
* Note: If there are multiple rmap records with only the same rmap owner as |
|
* the btree we're trying to rebuild and the block is indeed owned by another |
|
* data structure with the same rmap owner, then the block will be in sublist |
|
* and therefore doesn't need disposal. If there are multiple rmap records |
|
* with only the same rmap owner but the block is not owned by something with |
|
* the same rmap owner, the block will be freed. |
|
* |
|
* The caller is responsible for locking the AG headers for the entire rebuild |
|
* operation so that nothing else can sneak in and change the AG state while |
|
* we're not looking. We also assume that the caller already invalidated any |
|
* buffers associated with @bitmap. |
|
*/ |
|
|
|
/* |
|
* Invalidate buffers for per-AG btree blocks we're dumping. This function |
|
* is not intended for use with file data repairs; we have bunmapi for that. |
|
*/ |
|
int |
|
xrep_invalidate_blocks( |
|
struct xfs_scrub *sc, |
|
struct xbitmap *bitmap) |
|
{ |
|
struct xbitmap_range *bmr; |
|
struct xbitmap_range *n; |
|
struct xfs_buf *bp; |
|
xfs_fsblock_t fsbno; |
|
|
|
/* |
|
* For each block in each extent, see if there's an incore buffer for |
|
* exactly that block; if so, invalidate it. The buffer cache only |
|
* lets us look for one buffer at a time, so we have to look one block |
|
* at a time. Avoid invalidating AG headers and post-EOFS blocks |
|
* because we never own those; and if we can't TRYLOCK the buffer we |
|
* assume it's owned by someone else. |
|
*/ |
|
for_each_xbitmap_block(fsbno, bmr, n, bitmap) { |
|
/* Skip AG headers and post-EOFS blocks */ |
|
if (!xfs_verify_fsbno(sc->mp, fsbno)) |
|
continue; |
|
bp = xfs_buf_incore(sc->mp->m_ddev_targp, |
|
XFS_FSB_TO_DADDR(sc->mp, fsbno), |
|
XFS_FSB_TO_BB(sc->mp, 1), XBF_TRYLOCK); |
|
if (bp) { |
|
xfs_trans_bjoin(sc->tp, bp); |
|
xfs_trans_binval(sc->tp, bp); |
|
} |
|
} |
|
|
|
return 0; |
|
} |
|
|
|
/* Ensure the freelist is the correct size. */ |
|
int |
|
xrep_fix_freelist( |
|
struct xfs_scrub *sc, |
|
bool can_shrink) |
|
{ |
|
struct xfs_alloc_arg args = {0}; |
|
|
|
args.mp = sc->mp; |
|
args.tp = sc->tp; |
|
args.agno = sc->sa.pag->pag_agno; |
|
args.alignment = 1; |
|
args.pag = sc->sa.pag; |
|
|
|
return xfs_alloc_fix_freelist(&args, |
|
can_shrink ? 0 : XFS_ALLOC_FLAG_NOSHRINK); |
|
} |
|
|
|
/* |
|
* Put a block back on the AGFL. |
|
*/ |
|
STATIC int |
|
xrep_put_freelist( |
|
struct xfs_scrub *sc, |
|
xfs_agblock_t agbno) |
|
{ |
|
int error; |
|
|
|
/* Make sure there's space on the freelist. */ |
|
error = xrep_fix_freelist(sc, true); |
|
if (error) |
|
return error; |
|
|
|
/* |
|
* Since we're "freeing" a lost block onto the AGFL, we have to |
|
* create an rmap for the block prior to merging it or else other |
|
* parts will break. |
|
*/ |
|
error = xfs_rmap_alloc(sc->tp, sc->sa.agf_bp, sc->sa.pag, agbno, 1, |
|
&XFS_RMAP_OINFO_AG); |
|
if (error) |
|
return error; |
|
|
|
/* Put the block on the AGFL. */ |
|
error = xfs_alloc_put_freelist(sc->tp, sc->sa.agf_bp, sc->sa.agfl_bp, |
|
agbno, 0); |
|
if (error) |
|
return error; |
|
xfs_extent_busy_insert(sc->tp, sc->sa.pag, agbno, 1, |
|
XFS_EXTENT_BUSY_SKIP_DISCARD); |
|
|
|
return 0; |
|
} |
|
|
|
/* Dispose of a single block. */ |
|
STATIC int |
|
xrep_reap_block( |
|
struct xfs_scrub *sc, |
|
xfs_fsblock_t fsbno, |
|
const struct xfs_owner_info *oinfo, |
|
enum xfs_ag_resv_type resv) |
|
{ |
|
struct xfs_btree_cur *cur; |
|
struct xfs_buf *agf_bp = NULL; |
|
xfs_agnumber_t agno; |
|
xfs_agblock_t agbno; |
|
bool has_other_rmap; |
|
int error; |
|
|
|
agno = XFS_FSB_TO_AGNO(sc->mp, fsbno); |
|
agbno = XFS_FSB_TO_AGBNO(sc->mp, fsbno); |
|
|
|
/* |
|
* If we are repairing per-inode metadata, we need to read in the AGF |
|
* buffer. Otherwise, we're repairing a per-AG structure, so reuse |
|
* the AGF buffer that the setup functions already grabbed. |
|
*/ |
|
if (sc->ip) { |
|
error = xfs_alloc_read_agf(sc->mp, sc->tp, agno, 0, &agf_bp); |
|
if (error) |
|
return error; |
|
} else { |
|
agf_bp = sc->sa.agf_bp; |
|
} |
|
cur = xfs_rmapbt_init_cursor(sc->mp, sc->tp, agf_bp, sc->sa.pag); |
|
|
|
/* Can we find any other rmappings? */ |
|
error = xfs_rmap_has_other_keys(cur, agbno, 1, oinfo, &has_other_rmap); |
|
xfs_btree_del_cursor(cur, error); |
|
if (error) |
|
goto out_free; |
|
|
|
/* |
|
* If there are other rmappings, this block is cross linked and must |
|
* not be freed. Remove the reverse mapping and move on. Otherwise, |
|
* we were the only owner of the block, so free the extent, which will |
|
* also remove the rmap. |
|
* |
|
* XXX: XFS doesn't support detecting the case where a single block |
|
* metadata structure is crosslinked with a multi-block structure |
|
* because the buffer cache doesn't detect aliasing problems, so we |
|
* can't fix 100% of crosslinking problems (yet). The verifiers will |
|
* blow on writeout, the filesystem will shut down, and the admin gets |
|
* to run xfs_repair. |
|
*/ |
|
if (has_other_rmap) |
|
error = xfs_rmap_free(sc->tp, agf_bp, sc->sa.pag, agbno, |
|
1, oinfo); |
|
else if (resv == XFS_AG_RESV_AGFL) |
|
error = xrep_put_freelist(sc, agbno); |
|
else |
|
error = xfs_free_extent(sc->tp, fsbno, 1, oinfo, resv); |
|
if (agf_bp != sc->sa.agf_bp) |
|
xfs_trans_brelse(sc->tp, agf_bp); |
|
if (error) |
|
return error; |
|
|
|
if (sc->ip) |
|
return xfs_trans_roll_inode(&sc->tp, sc->ip); |
|
return xrep_roll_ag_trans(sc); |
|
|
|
out_free: |
|
if (agf_bp != sc->sa.agf_bp) |
|
xfs_trans_brelse(sc->tp, agf_bp); |
|
return error; |
|
} |
|
|
|
/* Dispose of every block of every extent in the bitmap. */ |
|
int |
|
xrep_reap_extents( |
|
struct xfs_scrub *sc, |
|
struct xbitmap *bitmap, |
|
const struct xfs_owner_info *oinfo, |
|
enum xfs_ag_resv_type type) |
|
{ |
|
struct xbitmap_range *bmr; |
|
struct xbitmap_range *n; |
|
xfs_fsblock_t fsbno; |
|
int error = 0; |
|
|
|
ASSERT(xfs_has_rmapbt(sc->mp)); |
|
|
|
for_each_xbitmap_block(fsbno, bmr, n, bitmap) { |
|
ASSERT(sc->ip != NULL || |
|
XFS_FSB_TO_AGNO(sc->mp, fsbno) == sc->sa.pag->pag_agno); |
|
trace_xrep_dispose_btree_extent(sc->mp, |
|
XFS_FSB_TO_AGNO(sc->mp, fsbno), |
|
XFS_FSB_TO_AGBNO(sc->mp, fsbno), 1); |
|
|
|
error = xrep_reap_block(sc, fsbno, oinfo, type); |
|
if (error) |
|
break; |
|
} |
|
|
|
return error; |
|
} |
|
|
|
/* |
|
* Finding per-AG Btree Roots for AGF/AGI Reconstruction |
|
* |
|
* If the AGF or AGI become slightly corrupted, it may be necessary to rebuild |
|
* the AG headers by using the rmap data to rummage through the AG looking for |
|
* btree roots. This is not guaranteed to work if the AG is heavily damaged |
|
* or the rmap data are corrupt. |
|
* |
|
* Callers of xrep_find_ag_btree_roots must lock the AGF and AGFL |
|
* buffers if the AGF is being rebuilt; or the AGF and AGI buffers if the |
|
* AGI is being rebuilt. It must maintain these locks until it's safe for |
|
* other threads to change the btrees' shapes. The caller provides |
|
* information about the btrees to look for by passing in an array of |
|
* xrep_find_ag_btree with the (rmap owner, buf_ops, magic) fields set. |
|
* The (root, height) fields will be set on return if anything is found. The |
|
* last element of the array should have a NULL buf_ops to mark the end of the |
|
* array. |
|
* |
|
* For every rmapbt record matching any of the rmap owners in btree_info, |
|
* read each block referenced by the rmap record. If the block is a btree |
|
* block from this filesystem matching any of the magic numbers and has a |
|
* level higher than what we've already seen, remember the block and the |
|
* height of the tree required to have such a block. When the call completes, |
|
* we return the highest block we've found for each btree description; those |
|
* should be the roots. |
|
*/ |
|
|
|
struct xrep_findroot { |
|
struct xfs_scrub *sc; |
|
struct xfs_buf *agfl_bp; |
|
struct xfs_agf *agf; |
|
struct xrep_find_ag_btree *btree_info; |
|
}; |
|
|
|
/* See if our block is in the AGFL. */ |
|
STATIC int |
|
xrep_findroot_agfl_walk( |
|
struct xfs_mount *mp, |
|
xfs_agblock_t bno, |
|
void *priv) |
|
{ |
|
xfs_agblock_t *agbno = priv; |
|
|
|
return (*agbno == bno) ? -ECANCELED : 0; |
|
} |
|
|
|
/* Does this block match the btree information passed in? */ |
|
STATIC int |
|
xrep_findroot_block( |
|
struct xrep_findroot *ri, |
|
struct xrep_find_ag_btree *fab, |
|
uint64_t owner, |
|
xfs_agblock_t agbno, |
|
bool *done_with_block) |
|
{ |
|
struct xfs_mount *mp = ri->sc->mp; |
|
struct xfs_buf *bp; |
|
struct xfs_btree_block *btblock; |
|
xfs_daddr_t daddr; |
|
int block_level; |
|
int error = 0; |
|
|
|
daddr = XFS_AGB_TO_DADDR(mp, ri->sc->sa.pag->pag_agno, agbno); |
|
|
|
/* |
|
* Blocks in the AGFL have stale contents that might just happen to |
|
* have a matching magic and uuid. We don't want to pull these blocks |
|
* in as part of a tree root, so we have to filter out the AGFL stuff |
|
* here. If the AGFL looks insane we'll just refuse to repair. |
|
*/ |
|
if (owner == XFS_RMAP_OWN_AG) { |
|
error = xfs_agfl_walk(mp, ri->agf, ri->agfl_bp, |
|
xrep_findroot_agfl_walk, &agbno); |
|
if (error == -ECANCELED) |
|
return 0; |
|
if (error) |
|
return error; |
|
} |
|
|
|
/* |
|
* Read the buffer into memory so that we can see if it's a match for |
|
* our btree type. We have no clue if it is beforehand, and we want to |
|
* avoid xfs_trans_read_buf's behavior of dumping the DONE state (which |
|
* will cause needless disk reads in subsequent calls to this function) |
|
* and logging metadata verifier failures. |
|
* |
|
* Therefore, pass in NULL buffer ops. If the buffer was already in |
|
* memory from some other caller it will already have b_ops assigned. |
|
* If it was in memory from a previous unsuccessful findroot_block |
|
* call, the buffer won't have b_ops but it should be clean and ready |
|
* for us to try to verify if the read call succeeds. The same applies |
|
* if the buffer wasn't in memory at all. |
|
* |
|
* Note: If we never match a btree type with this buffer, it will be |
|
* left in memory with NULL b_ops. This shouldn't be a problem unless |
|
* the buffer gets written. |
|
*/ |
|
error = xfs_trans_read_buf(mp, ri->sc->tp, mp->m_ddev_targp, daddr, |
|
mp->m_bsize, 0, &bp, NULL); |
|
if (error) |
|
return error; |
|
|
|
/* Ensure the block magic matches the btree type we're looking for. */ |
|
btblock = XFS_BUF_TO_BLOCK(bp); |
|
ASSERT(fab->buf_ops->magic[1] != 0); |
|
if (btblock->bb_magic != fab->buf_ops->magic[1]) |
|
goto out; |
|
|
|
/* |
|
* If the buffer already has ops applied and they're not the ones for |
|
* this btree type, we know this block doesn't match the btree and we |
|
* can bail out. |
|
* |
|
* If the buffer ops match ours, someone else has already validated |
|
* the block for us, so we can move on to checking if this is a root |
|
* block candidate. |
|
* |
|
* If the buffer does not have ops, nobody has successfully validated |
|
* the contents and the buffer cannot be dirty. If the magic, uuid, |
|
* and structure match this btree type then we'll move on to checking |
|
* if it's a root block candidate. If there is no match, bail out. |
|
*/ |
|
if (bp->b_ops) { |
|
if (bp->b_ops != fab->buf_ops) |
|
goto out; |
|
} else { |
|
ASSERT(!xfs_trans_buf_is_dirty(bp)); |
|
if (!uuid_equal(&btblock->bb_u.s.bb_uuid, |
|
&mp->m_sb.sb_meta_uuid)) |
|
goto out; |
|
/* |
|
* Read verifiers can reference b_ops, so we set the pointer |
|
* here. If the verifier fails we'll reset the buffer state |
|
* to what it was before we touched the buffer. |
|
*/ |
|
bp->b_ops = fab->buf_ops; |
|
fab->buf_ops->verify_read(bp); |
|
if (bp->b_error) { |
|
bp->b_ops = NULL; |
|
bp->b_error = 0; |
|
goto out; |
|
} |
|
|
|
/* |
|
* Some read verifiers will (re)set b_ops, so we must be |
|
* careful not to change b_ops after running the verifier. |
|
*/ |
|
} |
|
|
|
/* |
|
* This block passes the magic/uuid and verifier tests for this btree |
|
* type. We don't need the caller to try the other tree types. |
|
*/ |
|
*done_with_block = true; |
|
|
|
/* |
|
* Compare this btree block's level to the height of the current |
|
* candidate root block. |
|
* |
|
* If the level matches the root we found previously, throw away both |
|
* blocks because there can't be two candidate roots. |
|
* |
|
* If level is lower in the tree than the root we found previously, |
|
* ignore this block. |
|
*/ |
|
block_level = xfs_btree_get_level(btblock); |
|
if (block_level + 1 == fab->height) { |
|
fab->root = NULLAGBLOCK; |
|
goto out; |
|
} else if (block_level < fab->height) { |
|
goto out; |
|
} |
|
|
|
/* |
|
* This is the highest block in the tree that we've found so far. |
|
* Update the btree height to reflect what we've learned from this |
|
* block. |
|
*/ |
|
fab->height = block_level + 1; |
|
|
|
/* |
|
* If this block doesn't have sibling pointers, then it's the new root |
|
* block candidate. Otherwise, the root will be found farther up the |
|
* tree. |
|
*/ |
|
if (btblock->bb_u.s.bb_leftsib == cpu_to_be32(NULLAGBLOCK) && |
|
btblock->bb_u.s.bb_rightsib == cpu_to_be32(NULLAGBLOCK)) |
|
fab->root = agbno; |
|
else |
|
fab->root = NULLAGBLOCK; |
|
|
|
trace_xrep_findroot_block(mp, ri->sc->sa.pag->pag_agno, agbno, |
|
be32_to_cpu(btblock->bb_magic), fab->height - 1); |
|
out: |
|
xfs_trans_brelse(ri->sc->tp, bp); |
|
return error; |
|
} |
|
|
|
/* |
|
* Do any of the blocks in this rmap record match one of the btrees we're |
|
* looking for? |
|
*/ |
|
STATIC int |
|
xrep_findroot_rmap( |
|
struct xfs_btree_cur *cur, |
|
const struct xfs_rmap_irec *rec, |
|
void *priv) |
|
{ |
|
struct xrep_findroot *ri = priv; |
|
struct xrep_find_ag_btree *fab; |
|
xfs_agblock_t b; |
|
bool done; |
|
int error = 0; |
|
|
|
/* Ignore anything that isn't AG metadata. */ |
|
if (!XFS_RMAP_NON_INODE_OWNER(rec->rm_owner)) |
|
return 0; |
|
|
|
/* Otherwise scan each block + btree type. */ |
|
for (b = 0; b < rec->rm_blockcount; b++) { |
|
done = false; |
|
for (fab = ri->btree_info; fab->buf_ops; fab++) { |
|
if (rec->rm_owner != fab->rmap_owner) |
|
continue; |
|
error = xrep_findroot_block(ri, fab, |
|
rec->rm_owner, rec->rm_startblock + b, |
|
&done); |
|
if (error) |
|
return error; |
|
if (done) |
|
break; |
|
} |
|
} |
|
|
|
return 0; |
|
} |
|
|
|
/* Find the roots of the per-AG btrees described in btree_info. */ |
|
int |
|
xrep_find_ag_btree_roots( |
|
struct xfs_scrub *sc, |
|
struct xfs_buf *agf_bp, |
|
struct xrep_find_ag_btree *btree_info, |
|
struct xfs_buf *agfl_bp) |
|
{ |
|
struct xfs_mount *mp = sc->mp; |
|
struct xrep_findroot ri; |
|
struct xrep_find_ag_btree *fab; |
|
struct xfs_btree_cur *cur; |
|
int error; |
|
|
|
ASSERT(xfs_buf_islocked(agf_bp)); |
|
ASSERT(agfl_bp == NULL || xfs_buf_islocked(agfl_bp)); |
|
|
|
ri.sc = sc; |
|
ri.btree_info = btree_info; |
|
ri.agf = agf_bp->b_addr; |
|
ri.agfl_bp = agfl_bp; |
|
for (fab = btree_info; fab->buf_ops; fab++) { |
|
ASSERT(agfl_bp || fab->rmap_owner != XFS_RMAP_OWN_AG); |
|
ASSERT(XFS_RMAP_NON_INODE_OWNER(fab->rmap_owner)); |
|
fab->root = NULLAGBLOCK; |
|
fab->height = 0; |
|
} |
|
|
|
cur = xfs_rmapbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.pag); |
|
error = xfs_rmap_query_all(cur, xrep_findroot_rmap, &ri); |
|
xfs_btree_del_cursor(cur, error); |
|
|
|
return error; |
|
} |
|
|
|
/* Force a quotacheck the next time we mount. */ |
|
void |
|
xrep_force_quotacheck( |
|
struct xfs_scrub *sc, |
|
xfs_dqtype_t type) |
|
{ |
|
uint flag; |
|
|
|
flag = xfs_quota_chkd_flag(type); |
|
if (!(flag & sc->mp->m_qflags)) |
|
return; |
|
|
|
mutex_lock(&sc->mp->m_quotainfo->qi_quotaofflock); |
|
sc->mp->m_qflags &= ~flag; |
|
spin_lock(&sc->mp->m_sb_lock); |
|
sc->mp->m_sb.sb_qflags &= ~flag; |
|
spin_unlock(&sc->mp->m_sb_lock); |
|
xfs_log_sb(sc->tp); |
|
mutex_unlock(&sc->mp->m_quotainfo->qi_quotaofflock); |
|
} |
|
|
|
/* |
|
* Attach dquots to this inode, or schedule quotacheck to fix them. |
|
* |
|
* This function ensures that the appropriate dquots are attached to an inode. |
|
* We cannot allow the dquot code to allocate an on-disk dquot block here |
|
* because we're already in transaction context with the inode locked. The |
|
* on-disk dquot should already exist anyway. If the quota code signals |
|
* corruption or missing quota information, schedule quotacheck, which will |
|
* repair corruptions in the quota metadata. |
|
*/ |
|
int |
|
xrep_ino_dqattach( |
|
struct xfs_scrub *sc) |
|
{ |
|
int error; |
|
|
|
error = xfs_qm_dqattach_locked(sc->ip, false); |
|
switch (error) { |
|
case -EFSBADCRC: |
|
case -EFSCORRUPTED: |
|
case -ENOENT: |
|
xfs_err_ratelimited(sc->mp, |
|
"inode %llu repair encountered quota error %d, quotacheck forced.", |
|
(unsigned long long)sc->ip->i_ino, error); |
|
if (XFS_IS_UQUOTA_ON(sc->mp) && !sc->ip->i_udquot) |
|
xrep_force_quotacheck(sc, XFS_DQTYPE_USER); |
|
if (XFS_IS_GQUOTA_ON(sc->mp) && !sc->ip->i_gdquot) |
|
xrep_force_quotacheck(sc, XFS_DQTYPE_GROUP); |
|
if (XFS_IS_PQUOTA_ON(sc->mp) && !sc->ip->i_pdquot) |
|
xrep_force_quotacheck(sc, XFS_DQTYPE_PROJ); |
|
fallthrough; |
|
case -ESRCH: |
|
error = 0; |
|
break; |
|
default: |
|
break; |
|
} |
|
|
|
return error; |
|
}
|
|
|