goto resv_err;
err2 = __xfs_free_extent_later(*tpp, args.fsbno, delta, NULL,
- true);
+ XFS_AG_RESV_NONE, true);
if (err2)
goto resv_err;
*/
STATIC int
xfs_alloc_ag_vextent_near(
- struct xfs_alloc_arg *args)
+ struct xfs_alloc_arg *args,
+ uint32_t alloc_flags)
{
struct xfs_alloc_cur acur = {};
int error; /* error code */
if (args->agbno > args->max_agbno)
args->agbno = args->max_agbno;
+ /* Retry once quickly if we find busy extents before blocking. */
+ alloc_flags |= XFS_ALLOC_FLAG_TRYFLUSH;
restart:
len = 0;
*/
if (!acur.len) {
if (acur.busy) {
+ /*
+ * Our only valid extents must have been busy. Flush and
+ * retry the allocation again. If we get an -EAGAIN
+ * error, we're being told that a deadlock was avoided
+ * and the current transaction needs committing before
+ * the allocation can be retried.
+ */
trace_xfs_alloc_near_busy(args);
- xfs_extent_busy_flush(args->mp, args->pag,
- acur.busy_gen);
+ error = xfs_extent_busy_flush(args->tp, args->pag,
+ acur.busy_gen, alloc_flags);
+ if (error)
+ goto out;
+
+ alloc_flags &= ~XFS_ALLOC_FLAG_TRYFLUSH;
goto restart;
}
trace_xfs_alloc_size_neither(args);
* and of the form k * prod + mod unless there's nothing that large.
* Return the starting a.g. block, or NULLAGBLOCK if we can't do it.
*/
-STATIC int /* error */
+static int
xfs_alloc_ag_vextent_size(
- xfs_alloc_arg_t *args) /* allocation argument structure */
+ struct xfs_alloc_arg *args,
+ uint32_t alloc_flags)
{
- struct xfs_agf *agf = args->agbp->b_addr;
- struct xfs_btree_cur *bno_cur; /* cursor for bno btree */
- struct xfs_btree_cur *cnt_cur; /* cursor for cnt btree */
- int error; /* error result */
- xfs_agblock_t fbno; /* start of found freespace */
- xfs_extlen_t flen; /* length of found freespace */
- int i; /* temp status variable */
- xfs_agblock_t rbno; /* returned block number */
- xfs_extlen_t rlen; /* length of returned extent */
- bool busy;
- unsigned busy_gen;
+ struct xfs_agf *agf = args->agbp->b_addr;
+ struct xfs_btree_cur *bno_cur;
+ struct xfs_btree_cur *cnt_cur;
+ xfs_agblock_t fbno; /* start of found freespace */
+ xfs_extlen_t flen; /* length of found freespace */
+ xfs_agblock_t rbno; /* returned block number */
+ xfs_extlen_t rlen; /* length of returned extent */
+ bool busy;
+ unsigned busy_gen;
+ int error;
+ int i;
+ /* Retry once quickly if we find busy extents before blocking. */
+ alloc_flags |= XFS_ALLOC_FLAG_TRYFLUSH;
restart:
/*
* Allocate and initialize a cursor for the by-size btree.
error = xfs_btree_increment(cnt_cur, 0, &i);
if (error)
goto error0;
- if (i == 0) {
- /*
- * Our only valid extents must have been busy.
- * Make it unbusy by forcing the log out and
- * retrying.
- */
- xfs_btree_del_cursor(cnt_cur,
- XFS_BTREE_NOERROR);
- trace_xfs_alloc_size_busy(args);
- xfs_extent_busy_flush(args->mp,
- args->pag, busy_gen);
- goto restart;
- }
+ if (i)
+ continue;
+
+ /*
+ * Our only valid extents must have been busy. Flush and
+ * retry the allocation again. If we get an -EAGAIN
+ * error, we're being told that a deadlock was avoided
+ * and the current transaction needs committing before
+ * the allocation can be retried.
+ */
+ trace_xfs_alloc_size_busy(args);
+ error = xfs_extent_busy_flush(args->tp, args->pag,
+ busy_gen, alloc_flags);
+ if (error)
+ goto error0;
+
+ alloc_flags &= ~XFS_ALLOC_FLAG_TRYFLUSH;
+ xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
+ goto restart;
}
}
args->len = rlen;
if (rlen < args->minlen) {
if (busy) {
- xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
+ /*
+ * Our only valid extents must have been busy. Flush and
+ * retry the allocation again. If we get an -EAGAIN
+ * error, we're being told that a deadlock was avoided
+ * and the current transaction needs committing before
+ * the allocation can be retried.
+ */
trace_xfs_alloc_size_busy(args);
- xfs_extent_busy_flush(args->mp, args->pag, busy_gen);
+ error = xfs_extent_busy_flush(args->tp, args->pag,
+ busy_gen, alloc_flags);
+ if (error)
+ goto error0;
+
+ alloc_flags &= ~XFS_ALLOC_FLAG_TRYFLUSH;
+ xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
goto restart;
}
goto out_nominleft;
xfs_defer_agfl_block(
struct xfs_trans *tp,
xfs_agnumber_t agno,
- xfs_fsblock_t agbno,
+ xfs_agblock_t agbno,
struct xfs_owner_info *oinfo)
{
struct xfs_mount *mp = tp->t_mountp;
struct xfs_extent_free_item *xefi;
+ xfs_fsblock_t fsbno = XFS_AGB_TO_FSB(mp, agno, agbno);
ASSERT(xfs_extfree_item_cache != NULL);
ASSERT(oinfo != NULL);
+ if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbno(mp, fsbno)))
+ return -EFSCORRUPTED;
+
xefi = kmem_cache_zalloc(xfs_extfree_item_cache,
GFP_KERNEL | __GFP_NOFAIL);
- xefi->xefi_startblock = XFS_AGB_TO_FSB(mp, agno, agbno);
+ xefi->xefi_startblock = fsbno;
xefi->xefi_blockcount = 1;
xefi->xefi_owner = oinfo->oi_owner;
-
- if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbno(mp, xefi->xefi_startblock)))
- return -EFSCORRUPTED;
+ xefi->xefi_agresv = XFS_AG_RESV_AGFL;
trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1);
xfs_fsblock_t bno,
xfs_filblks_t len,
const struct xfs_owner_info *oinfo,
+ enum xfs_ag_resv_type type,
bool skip_discard)
{
struct xfs_extent_free_item *xefi;
ASSERT(agbno + len <= mp->m_sb.sb_agblocks);
#endif
ASSERT(xfs_extfree_item_cache != NULL);
+ ASSERT(type != XFS_AG_RESV_AGFL);
if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbext(mp, bno, len)))
return -EFSCORRUPTED;
GFP_KERNEL | __GFP_NOFAIL);
xefi->xefi_startblock = bno;
xefi->xefi_blockcount = (xfs_extlen_t)len;
+ xefi->xefi_agresv = type;
if (skip_discard)
xefi->xefi_flags |= XFS_EFI_SKIP_DISCARD;
if (oinfo) {
int /* error */
xfs_alloc_fix_freelist(
struct xfs_alloc_arg *args, /* allocation argument structure */
- int flags) /* XFS_ALLOC_FLAG_... */
+ uint32_t alloc_flags)
{
struct xfs_mount *mp = args->mp;
struct xfs_perag *pag = args->pag;
ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
if (!xfs_perag_initialised_agf(pag)) {
- error = xfs_alloc_read_agf(pag, tp, flags, &agbp);
+ error = xfs_alloc_read_agf(pag, tp, alloc_flags, &agbp);
if (error) {
/* Couldn't lock the AGF so skip this AG. */
if (error == -EAGAIN)
*/
if (xfs_perag_prefers_metadata(pag) &&
(args->datatype & XFS_ALLOC_USERDATA) &&
- (flags & XFS_ALLOC_FLAG_TRYLOCK)) {
- ASSERT(!(flags & XFS_ALLOC_FLAG_FREEING));
+ (alloc_flags & XFS_ALLOC_FLAG_TRYLOCK)) {
+ ASSERT(!(alloc_flags & XFS_ALLOC_FLAG_FREEING));
goto out_agbp_relse;
}
need = xfs_alloc_min_freelist(mp, pag);
- if (!xfs_alloc_space_available(args, need, flags |
+ if (!xfs_alloc_space_available(args, need, alloc_flags |
XFS_ALLOC_FLAG_CHECK))
goto out_agbp_relse;
* Can fail if we're not blocking on locks, and it's held.
*/
if (!agbp) {
- error = xfs_alloc_read_agf(pag, tp, flags, &agbp);
+ error = xfs_alloc_read_agf(pag, tp, alloc_flags, &agbp);
if (error) {
/* Couldn't lock the AGF so skip this AG. */
if (error == -EAGAIN)
/* If there isn't enough total space or single-extent, reject it. */
need = xfs_alloc_min_freelist(mp, pag);
- if (!xfs_alloc_space_available(args, need, flags))
+ if (!xfs_alloc_space_available(args, need, alloc_flags))
goto out_agbp_relse;
#ifdef DEBUG
*/
memset(&targs, 0, sizeof(targs));
/* struct copy below */
- if (flags & XFS_ALLOC_FLAG_NORMAP)
+ if (alloc_flags & XFS_ALLOC_FLAG_NORMAP)
targs.oinfo = XFS_RMAP_OINFO_SKIP_UPDATE;
else
targs.oinfo = XFS_RMAP_OINFO_AG;
- while (!(flags & XFS_ALLOC_FLAG_NOSHRINK) && pag->pagf_flcount > need) {
+ while (!(alloc_flags & XFS_ALLOC_FLAG_NOSHRINK) &&
+ pag->pagf_flcount > need) {
error = xfs_alloc_get_freelist(pag, tp, agbp, &bno, 0);
if (error)
goto out_agbp_relse;
targs.resv = XFS_AG_RESV_AGFL;
/* Allocate as many blocks as possible at once. */
- error = xfs_alloc_ag_vextent_size(&targs);
+ error = xfs_alloc_ag_vextent_size(&targs, alloc_flags);
if (error)
goto out_agflbp_relse;
* on a completely full ag.
*/
if (targs.agbno == NULLAGBLOCK) {
- if (flags & XFS_ALLOC_FLAG_FREEING)
+ if (alloc_flags & XFS_ALLOC_FLAG_FREEING)
break;
goto out_agflbp_relse;
}
}
/*
+ * Check that this AGF/AGI header's sequence number and length matches the AG
+ * number and size in fsblocks.
+ */
+xfs_failaddr_t
+xfs_validate_ag_length(
+ struct xfs_buf *bp,
+ uint32_t seqno,
+ uint32_t length)
+{
+ struct xfs_mount *mp = bp->b_mount;
+ /*
+ * During growfs operations, the perag is not fully initialised,
+ * so we can't use it for any useful checking. growfs ensures we can't
+ * use it by using uncached buffers that don't have the perag attached
+ * so we can detect and avoid this problem.
+ */
+ if (bp->b_pag && seqno != bp->b_pag->pag_agno)
+ return __this_address;
+
+ /*
+ * Only the last AG in the filesystem is allowed to be shorter
+ * than the AG size recorded in the superblock.
+ */
+ if (length != mp->m_sb.sb_agblocks) {
+ /*
+ * During growfs, the new last AG can get here before we
+ * have updated the superblock. Give it a pass on the seqno
+ * check.
+ */
+ if (bp->b_pag && seqno != mp->m_sb.sb_agcount - 1)
+ return __this_address;
+ if (length < XFS_MIN_AG_BLOCKS)
+ return __this_address;
+ if (length > mp->m_sb.sb_agblocks)
+ return __this_address;
+ }
+
+ return NULL;
+}
+
+/*
* Verify the AGF is consistent.
*
* We do not verify the AGFL indexes in the AGF are fully consistent here
{
struct xfs_mount *mp = bp->b_mount;
struct xfs_agf *agf = bp->b_addr;
+ xfs_failaddr_t fa;
+ uint32_t agf_seqno = be32_to_cpu(agf->agf_seqno);
+ uint32_t agf_length = be32_to_cpu(agf->agf_length);
if (xfs_has_crc(mp)) {
if (!uuid_equal(&agf->agf_uuid, &mp->m_sb.sb_meta_uuid))
if (!xfs_verify_magic(bp, agf->agf_magicnum))
return __this_address;
- if (!(XFS_AGF_GOOD_VERSION(be32_to_cpu(agf->agf_versionnum)) &&
- be32_to_cpu(agf->agf_freeblks) <= be32_to_cpu(agf->agf_length) &&
- be32_to_cpu(agf->agf_flfirst) < xfs_agfl_size(mp) &&
- be32_to_cpu(agf->agf_fllast) < xfs_agfl_size(mp) &&
- be32_to_cpu(agf->agf_flcount) <= xfs_agfl_size(mp)))
+ if (!XFS_AGF_GOOD_VERSION(be32_to_cpu(agf->agf_versionnum)))
return __this_address;
- if (be32_to_cpu(agf->agf_length) > mp->m_sb.sb_dblocks)
+ /*
+ * Both agf_seqno and agf_length need to validated before anything else
+ * block number related in the AGF or AGFL can be checked.
+ */
+ fa = xfs_validate_ag_length(bp, agf_seqno, agf_length);
+ if (fa)
+ return fa;
+
+ if (be32_to_cpu(agf->agf_flfirst) >= xfs_agfl_size(mp))
+ return __this_address;
+ if (be32_to_cpu(agf->agf_fllast) >= xfs_agfl_size(mp))
+ return __this_address;
+ if (be32_to_cpu(agf->agf_flcount) > xfs_agfl_size(mp))
return __this_address;
if (be32_to_cpu(agf->agf_freeblks) < be32_to_cpu(agf->agf_longest) ||
- be32_to_cpu(agf->agf_freeblks) > be32_to_cpu(agf->agf_length))
+ be32_to_cpu(agf->agf_freeblks) > agf_length)
return __this_address;
if (be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) < 1 ||
mp->m_alloc_maxlevels)
return __this_address;
- if (xfs_has_rmapbt(mp) &&
- (be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) < 1 ||
- be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) >
- mp->m_rmap_maxlevels))
- return __this_address;
-
- if (xfs_has_rmapbt(mp) &&
- be32_to_cpu(agf->agf_rmap_blocks) > be32_to_cpu(agf->agf_length))
+ if (xfs_has_lazysbcount(mp) &&
+ be32_to_cpu(agf->agf_btreeblks) > agf_length)
return __this_address;
- /*
- * during growfs operations, the perag is not fully initialised,
- * so we can't use it for any useful checking. growfs ensures we can't
- * use it by using uncached buffers that don't have the perag attached
- * so we can detect and avoid this problem.
- */
- if (bp->b_pag && be32_to_cpu(agf->agf_seqno) != bp->b_pag->pag_agno)
- return __this_address;
+ if (xfs_has_rmapbt(mp)) {
+ if (be32_to_cpu(agf->agf_rmap_blocks) > agf_length)
+ return __this_address;
- if (xfs_has_lazysbcount(mp) &&
- be32_to_cpu(agf->agf_btreeblks) > be32_to_cpu(agf->agf_length))
- return __this_address;
+ if (be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) < 1 ||
+ be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) >
+ mp->m_rmap_maxlevels)
+ return __this_address;
+ }
- if (xfs_has_reflink(mp) &&
- be32_to_cpu(agf->agf_refcount_blocks) >
- be32_to_cpu(agf->agf_length))
- return __this_address;
+ if (xfs_has_reflink(mp)) {
+ if (be32_to_cpu(agf->agf_refcount_blocks) > agf_length)
+ return __this_address;
- if (xfs_has_reflink(mp) &&
- (be32_to_cpu(agf->agf_refcount_level) < 1 ||
- be32_to_cpu(agf->agf_refcount_level) > mp->m_refc_maxlevels))
- return __this_address;
+ if (be32_to_cpu(agf->agf_refcount_level) < 1 ||
+ be32_to_cpu(agf->agf_refcount_level) > mp->m_refc_maxlevels)
+ return __this_address;
+ }
return NULL;
}
static int
xfs_alloc_vextent_prepare_ag(
struct xfs_alloc_arg *args,
- uint32_t flags)
+ uint32_t alloc_flags)
{
bool need_pag = !args->pag;
int error;
args->pag = xfs_perag_get(args->mp, args->agno);
args->agbp = NULL;
- error = xfs_alloc_fix_freelist(args, flags);
+ error = xfs_alloc_fix_freelist(args, alloc_flags);
if (error) {
trace_xfs_alloc_vextent_nofix(args);
if (need_pag)
{
struct xfs_mount *mp = args->mp;
xfs_agnumber_t minimum_agno;
+ uint32_t alloc_flags = 0;
int error;
ASSERT(args->pag != NULL);
return error;
}
- error = xfs_alloc_vextent_prepare_ag(args, 0);
+ error = xfs_alloc_vextent_prepare_ag(args, alloc_flags);
if (!error && args->agbp)
- error = xfs_alloc_ag_vextent_size(args);
+ error = xfs_alloc_ag_vextent_size(args, alloc_flags);
return xfs_alloc_vextent_finish(args, minimum_agno, error, false);
}
xfs_agnumber_t minimum_agno,
xfs_agnumber_t start_agno,
xfs_agblock_t target_agbno,
- uint32_t flags)
+ uint32_t alloc_flags)
{
struct xfs_mount *mp = args->mp;
xfs_agnumber_t restart_agno = minimum_agno;
xfs_agnumber_t agno;
int error = 0;
- if (flags & XFS_ALLOC_FLAG_TRYLOCK)
+ if (alloc_flags & XFS_ALLOC_FLAG_TRYLOCK)
restart_agno = 0;
restart:
for_each_perag_wrap_range(mp, start_agno, restart_agno,
mp->m_sb.sb_agcount, agno, args->pag) {
args->agno = agno;
- error = xfs_alloc_vextent_prepare_ag(args, flags);
+ error = xfs_alloc_vextent_prepare_ag(args, alloc_flags);
if (error)
break;
if (!args->agbp) {
*/
if (args->agno == start_agno && target_agbno) {
args->agbno = target_agbno;
- error = xfs_alloc_ag_vextent_near(args);
+ error = xfs_alloc_ag_vextent_near(args, alloc_flags);
} else {
args->agbno = 0;
- error = xfs_alloc_ag_vextent_size(args);
+ error = xfs_alloc_ag_vextent_size(args, alloc_flags);
}
break;
}
* constraining flags by the caller, drop them and retry the allocation
* without any constraints being set.
*/
- if (flags) {
- flags = 0;
+ if (alloc_flags & XFS_ALLOC_FLAG_TRYLOCK) {
+ alloc_flags &= ~XFS_ALLOC_FLAG_TRYLOCK;
restart_agno = minimum_agno;
goto restart;
}
xfs_agnumber_t start_agno;
xfs_agnumber_t rotorstep = xfs_rotorstep;
bool bump_rotor = false;
+ uint32_t alloc_flags = XFS_ALLOC_FLAG_TRYLOCK;
int error;
ASSERT(args->pag == NULL);
start_agno = max(minimum_agno, XFS_FSB_TO_AGNO(mp, target));
error = xfs_alloc_vextent_iterate_ags(args, minimum_agno, start_agno,
- XFS_FSB_TO_AGBNO(mp, target), XFS_ALLOC_FLAG_TRYLOCK);
+ XFS_FSB_TO_AGBNO(mp, target), alloc_flags);
if (bump_rotor) {
if (args->agno == start_agno)
struct xfs_mount *mp = args->mp;
xfs_agnumber_t minimum_agno;
xfs_agnumber_t start_agno;
+ uint32_t alloc_flags = XFS_ALLOC_FLAG_TRYLOCK;
int error;
ASSERT(args->pag == NULL);
start_agno = max(minimum_agno, XFS_FSB_TO_AGNO(mp, target));
error = xfs_alloc_vextent_iterate_ags(args, minimum_agno, start_agno,
- XFS_FSB_TO_AGBNO(mp, target), 0);
+ XFS_FSB_TO_AGBNO(mp, target), alloc_flags);
return xfs_alloc_vextent_finish(args, minimum_agno, error, true);
}
struct xfs_mount *mp = args->mp;
xfs_agnumber_t minimum_agno;
bool needs_perag = args->pag == NULL;
+ uint32_t alloc_flags = 0;
int error;
if (!needs_perag)
if (needs_perag)
args->pag = xfs_perag_grab(mp, args->agno);
- error = xfs_alloc_vextent_prepare_ag(args, 0);
+ error = xfs_alloc_vextent_prepare_ag(args, alloc_flags);
if (!error && args->agbp)
- error = xfs_alloc_ag_vextent_near(args);
+ error = xfs_alloc_ag_vextent_near(args, alloc_flags);
return xfs_alloc_vextent_finish(args, minimum_agno, error, needs_perag);
}
xfs_alloc_query_range_fn fn,
void *priv)
{
- union xfs_btree_irec low_brec;
- union xfs_btree_irec high_brec;
- struct xfs_alloc_query_range_info query;
+ union xfs_btree_irec low_brec = { .a = *low_rec };
+ union xfs_btree_irec high_brec = { .a = *high_rec };
+ struct xfs_alloc_query_range_info query = { .priv = priv, .fn = fn };
ASSERT(cur->bc_btnum == XFS_BTNUM_BNO);
- low_brec.a = *low_rec;
- high_brec.a = *high_rec;
- query.priv = priv;
- query.fn = fn;
return xfs_btree_query_range(cur, &low_brec, &high_brec,
xfs_alloc_query_range_helper, &query);
}
/*
* Flags for xfs_alloc_fix_freelist.
*/
-#define XFS_ALLOC_FLAG_TRYLOCK 0x00000001 /* use trylock for buffer locking */
-#define XFS_ALLOC_FLAG_FREEING 0x00000002 /* indicate caller is freeing extents*/
-#define XFS_ALLOC_FLAG_NORMAP 0x00000004 /* don't modify the rmapbt */
-#define XFS_ALLOC_FLAG_NOSHRINK 0x00000008 /* don't shrink the freelist */
-#define XFS_ALLOC_FLAG_CHECK 0x00000010 /* test only, don't modify args */
+#define XFS_ALLOC_FLAG_TRYLOCK (1U << 0) /* use trylock for buffer locking */
+#define XFS_ALLOC_FLAG_FREEING (1U << 1) /* indicate caller is freeing extents*/
+#define XFS_ALLOC_FLAG_NORMAP (1U << 2) /* don't modify the rmapbt */
+#define XFS_ALLOC_FLAG_NOSHRINK (1U << 3) /* don't shrink the freelist */
+#define XFS_ALLOC_FLAG_CHECK (1U << 4) /* test only, don't modify args */
+#define XFS_ALLOC_FLAG_TRYFLUSH (1U << 5) /* don't wait in busy extent flush */
/*
* Argument structure for xfs_alloc routines.
struct xfs_buf **bpp);
int xfs_free_agfl_block(struct xfs_trans *, xfs_agnumber_t, xfs_agblock_t,
struct xfs_buf *, struct xfs_owner_info *);
-int xfs_alloc_fix_freelist(struct xfs_alloc_arg *args, int flags);
+int xfs_alloc_fix_freelist(struct xfs_alloc_arg *args, uint32_t alloc_flags);
int xfs_free_extent_fix_freelist(struct xfs_trans *tp, struct xfs_perag *pag,
struct xfs_buf **agbp);
int __xfs_free_extent_later(struct xfs_trans *tp, xfs_fsblock_t bno,
xfs_filblks_t len, const struct xfs_owner_info *oinfo,
- bool skip_discard);
+ enum xfs_ag_resv_type type, bool skip_discard);
/*
* List of extents to be free "later".
xfs_extlen_t xefi_blockcount;/* number of blocks in extent */
struct xfs_perag *xefi_pag;
unsigned int xefi_flags;
+ enum xfs_ag_resv_type xefi_agresv;
};
void xfs_extent_free_get_group(struct xfs_mount *mp,
struct xfs_trans *tp,
xfs_fsblock_t bno,
xfs_filblks_t len,
- const struct xfs_owner_info *oinfo)
+ const struct xfs_owner_info *oinfo,
+ enum xfs_ag_resv_type type)
{
- return __xfs_free_extent_later(tp, bno, len, oinfo, false);
+ return __xfs_free_extent_later(tp, bno, len, oinfo, type, false);
}
int __init xfs_extfree_intent_init_cache(void);
void xfs_extfree_intent_destroy_cache(void);
+xfs_failaddr_t xfs_validate_ag_length(struct xfs_buf *bp, uint32_t seqno,
+ uint32_t length);
+
#endif /* __XFS_ALLOC_H__ */
trace_xfs_attr_leaf_unbalance(state->args);
- drop_leaf = drop_blk->bp->b_addr;
- save_leaf = save_blk->bp->b_addr;
xfs_attr3_leaf_hdr_from_disk(state->args->geo, &drophdr, drop_leaf);
xfs_attr3_leaf_hdr_from_disk(state->args->geo, &savehdr, save_leaf);
entry = xfs_attr3_leaf_entryp(drop_leaf);
return error;
xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork);
- error = xfs_free_extent_later(cur->bc_tp, cbno, 1, &oinfo);
+ error = xfs_free_extent_later(cur->bc_tp, cbno, 1, &oinfo,
+ XFS_AG_RESV_NONE);
if (error)
return error;
} else {
error = __xfs_free_extent_later(tp, del->br_startblock,
del->br_blockcount, NULL,
- (bflags & XFS_BMAPI_NODISCARD) ||
- del->br_state == XFS_EXT_UNWRITTEN);
+ XFS_AG_RESV_NONE,
+ ((bflags & XFS_BMAPI_NODISCARD) ||
+ del->br_state == XFS_EXT_UNWRITTEN));
if (error)
goto done;
}
int error;
xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_ino.whichfork);
- error = xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo);
+ error = xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo,
+ XFS_AG_RESV_NONE);
if (error)
return error;
/* not sparse, calculate extent info directly */
return xfs_free_extent_later(tp,
XFS_AGB_TO_FSB(mp, agno, sagbno),
- M_IGEO(mp)->ialloc_blks,
- &XFS_RMAP_OINFO_INODES);
+ M_IGEO(mp)->ialloc_blks, &XFS_RMAP_OINFO_INODES,
+ XFS_AG_RESV_NONE);
}
/* holemask is only 16-bits (fits in an unsigned long) */
ASSERT(agbno % mp->m_sb.sb_spino_align == 0);
ASSERT(contigblk % mp->m_sb.sb_spino_align == 0);
error = xfs_free_extent_later(tp,
- XFS_AGB_TO_FSB(mp, agno, agbno),
- contigblk, &XFS_RMAP_OINFO_INODES);
+ XFS_AGB_TO_FSB(mp, agno, agbno), contigblk,
+ &XFS_RMAP_OINFO_INODES, XFS_AG_RESV_NONE);
if (error)
return error;
static xfs_failaddr_t
xfs_agi_verify(
- struct xfs_buf *bp)
+ struct xfs_buf *bp)
{
- struct xfs_mount *mp = bp->b_mount;
- struct xfs_agi *agi = bp->b_addr;
- int i;
+ struct xfs_mount *mp = bp->b_mount;
+ struct xfs_agi *agi = bp->b_addr;
+ xfs_failaddr_t fa;
+ uint32_t agi_seqno = be32_to_cpu(agi->agi_seqno);
+ uint32_t agi_length = be32_to_cpu(agi->agi_length);
+ int i;
if (xfs_has_crc(mp)) {
if (!uuid_equal(&agi->agi_uuid, &mp->m_sb.sb_meta_uuid))
if (!XFS_AGI_GOOD_VERSION(be32_to_cpu(agi->agi_versionnum)))
return __this_address;
+ fa = xfs_validate_ag_length(bp, agi_seqno, agi_length);
+ if (fa)
+ return fa;
+
if (be32_to_cpu(agi->agi_level) < 1 ||
be32_to_cpu(agi->agi_level) > M_IGEO(mp)->inobt_maxlevels)
return __this_address;
be32_to_cpu(agi->agi_free_level) > M_IGEO(mp)->inobt_maxlevels))
return __this_address;
- /*
- * during growfs operations, the perag is not fully initialised,
- * so we can't use it for any useful checking. growfs ensures we can't
- * use it by using uncached buffers that don't have the perag attached
- * so we can detect and avoid this problem.
- */
- if (bp->b_pag && be32_to_cpu(agi->agi_seqno) != bp->b_pag->pag_agno)
- return __this_address;
-
for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++) {
if (agi->agi_unlinked[i] == cpu_to_be32(NULLAGINO))
continue;
xfs_inobt_mod_blockcount(cur, -1);
fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, xfs_buf_daddr(bp));
- return xfs_free_extent(cur->bc_tp, cur->bc_ag.pag,
- XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno), 1,
+ return xfs_free_extent_later(cur->bc_tp, fsbno, 1,
&XFS_RMAP_OINFO_INOBT, resv);
}
cur->bc_ag.pag->pag_agno,
tmp.rc_startblock);
error = xfs_free_extent_later(cur->bc_tp, fsbno,
- tmp.rc_blockcount, NULL);
+ tmp.rc_blockcount, NULL,
+ XFS_AG_RESV_NONE);
if (error)
goto out_error;
}
cur->bc_ag.pag->pag_agno,
ext.rc_startblock);
error = xfs_free_extent_later(cur->bc_tp, fsbno,
- ext.rc_blockcount, NULL);
+ ext.rc_blockcount, NULL,
+ XFS_AG_RESV_NONE);
if (error)
goto out_error;
}
struct xfs_buf *agbp;
struct xfs_refcount_recovery *rr, *n;
struct list_head debris;
- union xfs_btree_irec low;
- union xfs_btree_irec high;
+ union xfs_btree_irec low = {
+ .rc.rc_domain = XFS_REFC_DOMAIN_COW,
+ };
+ union xfs_btree_irec high = {
+ .rc.rc_domain = XFS_REFC_DOMAIN_COW,
+ .rc.rc_startblock = -1U,
+ };
xfs_fsblock_t fsb;
int error;
cur = xfs_refcountbt_init_cursor(mp, tp, agbp, pag);
/* Find all the leftover CoW staging extents. */
- memset(&low, 0, sizeof(low));
- memset(&high, 0, sizeof(high));
- low.rc.rc_domain = high.rc.rc_domain = XFS_REFC_DOMAIN_COW;
- high.rc.rc_startblock = -1U;
error = xfs_btree_query_range(cur, &low, &high,
xfs_refcount_recover_extent, &debris);
xfs_btree_del_cursor(cur, error);
/* Free the block. */
error = xfs_free_extent_later(tp, fsb,
- rr->rr_rrec.rc_blockcount, NULL);
+ rr->rr_rrec.rc_blockcount, NULL,
+ XFS_AG_RESV_NONE);
if (error)
goto out_trans;
struct xfs_buf *agbp = cur->bc_ag.agbp;
struct xfs_agf *agf = agbp->b_addr;
xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp));
- int error;
trace_xfs_refcountbt_free_block(cur->bc_mp, cur->bc_ag.pag->pag_agno,
XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno), 1);
be32_add_cpu(&agf->agf_refcount_blocks, -1);
xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_REFCOUNT_BLOCKS);
- error = xfs_free_extent(cur->bc_tp, cur->bc_ag.pag,
- XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno), 1,
+ return xfs_free_extent_later(cur->bc_tp, fsbno, 1,
&XFS_RMAP_OINFO_REFC, XFS_AG_RESV_METADATA);
- if (error)
- return error;
-
- return error;
}
STATIC int
xfs_rmap_query_range_fn fn,
void *priv)
{
- union xfs_btree_irec low_brec;
- union xfs_btree_irec high_brec;
- struct xfs_rmap_query_range_info query;
+ union xfs_btree_irec low_brec = { .r = *low_rec };
+ union xfs_btree_irec high_brec = { .r = *high_rec };
+ struct xfs_rmap_query_range_info query = { .priv = priv, .fn = fn };
- low_brec.r = *low_rec;
- high_brec.r = *high_rec;
- query.priv = priv;
- query.fn = fn;
return xfs_btree_query_range(cur, &low_brec, &high_brec,
xfs_rmap_query_range_helper, &query);
}
sbp->sb_inodelog < XFS_DINODE_MIN_LOG ||
sbp->sb_inodelog > XFS_DINODE_MAX_LOG ||
sbp->sb_inodesize != (1 << sbp->sb_inodelog) ||
- sbp->sb_logsunit > XLOG_MAX_RECORD_BSIZE ||
sbp->sb_inopblock != howmany(sbp->sb_blocksize,sbp->sb_inodesize) ||
XFS_FSB_TO_B(mp, sbp->sb_agblocks) < XFS_MIN_AG_BYTES ||
XFS_FSB_TO_B(mp, sbp->sb_agblocks) > XFS_MAX_AG_BYTES ||
return -EFSCORRUPTED;
}
+ /*
+ * Logs that are too large are not supported at all. Reject them
+ * outright. Logs that are too small are tolerated on v4 filesystems,
+ * but we can only check that when mounting the log. Hence we skip
+ * those checks here.
+ */
+ if (sbp->sb_logblocks > XFS_MAX_LOG_BLOCKS) {
+ xfs_notice(mp,
+ "Log size 0x%x blocks too large, maximum size is 0x%llx blocks",
+ sbp->sb_logblocks, XFS_MAX_LOG_BLOCKS);
+ return -EFSCORRUPTED;
+ }
+
+ if (XFS_FSB_TO_B(mp, sbp->sb_logblocks) > XFS_MAX_LOG_BYTES) {
+ xfs_warn(mp,
+ "log size 0x%llx bytes too large, maximum size is 0x%llx bytes",
+ XFS_FSB_TO_B(mp, sbp->sb_logblocks),
+ XFS_MAX_LOG_BYTES);
+ return -EFSCORRUPTED;
+ }
+
+ /*
+ * Do not allow filesystems with corrupted log sector or stripe units to
+ * be mounted. We cannot safely size the iclogs or write to the log if
+ * the log stripe unit is not valid.
+ */
+ if (sbp->sb_versionnum & XFS_SB_VERSION_SECTORBIT) {
+ if (sbp->sb_logsectsize != (1U << sbp->sb_logsectlog)) {
+ xfs_notice(mp,
+ "log sector size in bytes/log2 (0x%x/0x%x) must match",
+ sbp->sb_logsectsize, 1U << sbp->sb_logsectlog);
+ return -EFSCORRUPTED;
+ }
+ } else if (sbp->sb_logsectsize || sbp->sb_logsectlog) {
+ xfs_notice(mp,
+ "log sector size in bytes/log2 (0x%x/0x%x) are not zero",
+ sbp->sb_logsectsize, sbp->sb_logsectlog);
+ return -EFSCORRUPTED;
+ }
+
+ if (sbp->sb_logsunit > 1) {
+ if (sbp->sb_logsunit % sbp->sb_blocksize) {
+ xfs_notice(mp,
+ "log stripe unit 0x%x bytes must be a multiple of block size",
+ sbp->sb_logsunit);
+ return -EFSCORRUPTED;
+ }
+ if (sbp->sb_logsunit > XLOG_MAX_RECORD_BSIZE) {
+ xfs_notice(mp,
+ "log stripe unit 0x%x bytes over maximum size (0x%x bytes)",
+ sbp->sb_logsunit, XLOG_MAX_RECORD_BSIZE);
+ return -EFSCORRUPTED;
+ }
+ }
+
/* Validate the realtime geometry; stolen from xfs_repair */
if (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE ||
sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE) {
/*
* Flush out all busy extents for this AG.
+ *
+ * If the current transaction is holding busy extents, the caller may not want
+ * to wait for committed busy extents to resolve. If we are being told just to
+ * try a flush or progress has been made since we last skipped a busy extent,
+ * return immediately to allow the caller to try again.
+ *
+ * If we are freeing extents, we might actually be holding the only free extents
+ * in the transaction busy list and the log force won't resolve that situation.
+ * In this case, we must return -EAGAIN to avoid a deadlock by informing the
+ * caller it needs to commit the busy extents it holds before retrying the
+ * extent free operation.
*/
-void
+int
xfs_extent_busy_flush(
- struct xfs_mount *mp,
+ struct xfs_trans *tp,
struct xfs_perag *pag,
- unsigned busy_gen)
+ unsigned busy_gen,
+ uint32_t alloc_flags)
{
DEFINE_WAIT (wait);
int error;
- error = xfs_log_force(mp, XFS_LOG_SYNC);
+ error = xfs_log_force(tp->t_mountp, XFS_LOG_SYNC);
if (error)
- return;
+ return error;
+
+ /* Avoid deadlocks on uncommitted busy extents. */
+ if (!list_empty(&tp->t_busy)) {
+ if (alloc_flags & XFS_ALLOC_FLAG_TRYFLUSH)
+ return 0;
+
+ if (busy_gen != READ_ONCE(pag->pagb_gen))
+ return 0;
+
+ if (alloc_flags & XFS_ALLOC_FLAG_FREEING)
+ return -EAGAIN;
+ }
+ /* Wait for committed busy extents to resolve. */
do {
prepare_to_wait(&pag->pagb_wait, &wait, TASK_KILLABLE);
if (busy_gen != READ_ONCE(pag->pagb_gen))
} while (1);
finish_wait(&pag->pagb_wait, &wait);
+ return 0;
}
void
xfs_extent_busy_trim(struct xfs_alloc_arg *args, xfs_agblock_t *bno,
xfs_extlen_t *len, unsigned *busy_gen);
-void
-xfs_extent_busy_flush(struct xfs_mount *mp, struct xfs_perag *pag,
- unsigned busy_gen);
+int
+xfs_extent_busy_flush(struct xfs_trans *tp, struct xfs_perag *pag,
+ unsigned busy_gen, uint32_t alloc_flags);
void
xfs_extent_busy_wait_all(struct xfs_mount *mp);
}
/*
+ * Fill the EFD with all extents from the EFI when we need to roll the
+ * transaction and continue with a new EFI.
+ *
+ * This simply copies all the extents in the EFI to the EFD rather than make
+ * assumptions about which extents in the EFI have already been processed. We
+ * currently keep the xefi list in the same order as the EFI extent list, but
+ * that may not always be the case. Copying everything avoids leaving a landmine
+ * were we fail to cancel all the extents in an EFI if the xefi list is
+ * processed in a different order to the extents in the EFI.
+ */
+static void
+xfs_efd_from_efi(
+ struct xfs_efd_log_item *efdp)
+{
+ struct xfs_efi_log_item *efip = efdp->efd_efip;
+ uint i;
+
+ ASSERT(efip->efi_format.efi_nextents > 0);
+ ASSERT(efdp->efd_next_extent < efip->efi_format.efi_nextents);
+
+ for (i = 0; i < efip->efi_format.efi_nextents; i++) {
+ efdp->efd_format.efd_extents[i] =
+ efip->efi_format.efi_extents[i];
+ }
+ efdp->efd_next_extent = efip->efi_format.efi_nextents;
+}
+
+/*
* Free an extent and log it to the EFD. Note that the transaction is marked
* dirty regardless of whether the extent free succeeds or fails to support the
* EFI/EFD lifecycle rules.
agbno, xefi->xefi_blockcount);
error = __xfs_free_extent(tp, xefi->xefi_pag, agbno,
- xefi->xefi_blockcount, &oinfo, XFS_AG_RESV_NONE,
+ xefi->xefi_blockcount, &oinfo, xefi->xefi_agresv,
xefi->xefi_flags & XFS_EFI_SKIP_DISCARD);
/*
tp->t_flags |= XFS_TRANS_DIRTY | XFS_TRANS_HAS_INTENT_DONE;
set_bit(XFS_LI_DIRTY, &efdp->efd_item.li_flags);
+ /*
+ * If we need a new transaction to make progress, the caller will log a
+ * new EFI with the current contents. It will also log an EFD to cancel
+ * the existing EFI, and so we need to copy all the unprocessed extents
+ * in this EFI to the EFD so this works correctly.
+ */
+ if (error == -EAGAIN) {
+ xfs_efd_from_efi(efdp);
+ return error;
+ }
+
next_extent = efdp->efd_next_extent;
ASSERT(next_extent < efdp->efd_format.efd_nextents);
extp = &(efdp->efd_format.efd_extents[next_extent]);
error = xfs_trans_free_extent(tp, EFD_ITEM(done), xefi);
+ /*
+ * Don't free the XEFI if we need a new transaction to complete
+ * processing of it.
+ */
+ if (error == -EAGAIN)
+ return error;
+
xfs_extent_free_put_group(xefi);
kmem_cache_free(xfs_extfree_item_cache, xefi);
return error;
struct xfs_trans *tp;
int i;
int error = 0;
+ bool requeue_only = false;
/*
* First check the validity of the extents described by the
for (i = 0; i < efip->efi_format.efi_nextents; i++) {
struct xfs_extent_free_item fake = {
.xefi_owner = XFS_RMAP_OWN_UNKNOWN,
+ .xefi_agresv = XFS_AG_RESV_NONE,
};
struct xfs_extent *extp;
fake.xefi_startblock = extp->ext_start;
fake.xefi_blockcount = extp->ext_len;
- xfs_extent_free_get_group(mp, &fake);
- error = xfs_trans_free_extent(tp, efdp, &fake);
- xfs_extent_free_put_group(&fake);
+ if (!requeue_only) {
+ xfs_extent_free_get_group(mp, &fake);
+ error = xfs_trans_free_extent(tp, efdp, &fake);
+ xfs_extent_free_put_group(&fake);
+ }
+
+ /*
+ * If we can't free the extent without potentially deadlocking,
+ * requeue the rest of the extents to a new so that they get
+ * run again later with a new transaction context.
+ */
+ if (error == -EAGAIN || requeue_only) {
+ error = xfs_free_extent_later(tp, fake.xefi_startblock,
+ fake.xefi_blockcount,
+ &XFS_RMAP_OINFO_ANY_OWNER,
+ fake.xefi_agresv);
+ if (!error) {
+ requeue_only = true;
+ continue;
+ }
+ }
+
if (error == -EFSCORRUPTED)
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
extp, sizeof(*extp));
struct xfs_buf *agf_bp; /* AGF, for refcount queries */
struct xfs_perag *pag; /* AG info, if applicable */
xfs_daddr_t next_daddr; /* next daddr we expect */
+ /* daddr of low fsmap key when we're using the rtbitmap */
+ xfs_daddr_t low_daddr;
u64 missing_owner; /* owner of holes */
u32 dev; /* device id */
- struct xfs_rmap_irec low; /* low rmap key */
+ /*
+ * Low rmap key for the query. If low.rm_blockcount is nonzero, this
+ * is the second (or later) call to retrieve the recordset in pieces.
+ * xfs_getfsmap_rec_before_start will compare all records retrieved
+ * by the rmapbt query to filter out any records that start before
+ * the last record.
+ */
+ struct xfs_rmap_irec low;
struct xfs_rmap_irec high; /* high rmap key */
bool last; /* last extent? */
};
xfs_fsmap_from_internal(rec, xfm);
}
+static inline bool
+xfs_getfsmap_rec_before_start(
+ struct xfs_getfsmap_info *info,
+ const struct xfs_rmap_irec *rec,
+ xfs_daddr_t rec_daddr)
+{
+ if (info->low_daddr != -1ULL)
+ return rec_daddr < info->low_daddr;
+ if (info->low.rm_blockcount)
+ return xfs_rmap_compare(rec, &info->low) < 0;
+ return false;
+}
+
/*
* Format a reverse mapping for getfsmap, having translated rm_startblock
- * into the appropriate daddr units.
+ * into the appropriate daddr units. Pass in a nonzero @len_daddr if the
+ * length could be larger than rm_blockcount in struct xfs_rmap_irec.
*/
STATIC int
xfs_getfsmap_helper(
struct xfs_trans *tp,
struct xfs_getfsmap_info *info,
const struct xfs_rmap_irec *rec,
- xfs_daddr_t rec_daddr)
+ xfs_daddr_t rec_daddr,
+ xfs_daddr_t len_daddr)
{
struct xfs_fsmap fmr;
struct xfs_mount *mp = tp->t_mountp;
if (fatal_signal_pending(current))
return -EINTR;
+ if (len_daddr == 0)
+ len_daddr = XFS_FSB_TO_BB(mp, rec->rm_blockcount);
+
/*
* Filter out records that start before our startpoint, if the
* caller requested that.
*/
- if (xfs_rmap_compare(rec, &info->low) < 0) {
- rec_daddr += XFS_FSB_TO_BB(mp, rec->rm_blockcount);
+ if (xfs_getfsmap_rec_before_start(info, rec, rec_daddr)) {
+ rec_daddr += len_daddr;
if (info->next_daddr < rec_daddr)
info->next_daddr = rec_daddr;
return 0;
info->head->fmh_entries++;
- rec_daddr += XFS_FSB_TO_BB(mp, rec->rm_blockcount);
+ rec_daddr += len_daddr;
if (info->next_daddr < rec_daddr)
info->next_daddr = rec_daddr;
return 0;
if (error)
return error;
fmr.fmr_offset = XFS_FSB_TO_BB(mp, rec->rm_offset);
- fmr.fmr_length = XFS_FSB_TO_BB(mp, rec->rm_blockcount);
+ fmr.fmr_length = len_daddr;
if (rec->rm_flags & XFS_RMAP_UNWRITTEN)
fmr.fmr_flags |= FMR_OF_PREALLOC;
if (rec->rm_flags & XFS_RMAP_ATTR_FORK)
xfs_getfsmap_format(mp, &fmr, info);
out:
- rec_daddr += XFS_FSB_TO_BB(mp, rec->rm_blockcount);
+ rec_daddr += len_daddr;
if (info->next_daddr < rec_daddr)
info->next_daddr = rec_daddr;
return 0;
fsb = XFS_AGB_TO_FSB(mp, cur->bc_ag.pag->pag_agno, rec->rm_startblock);
rec_daddr = XFS_FSB_TO_DADDR(mp, fsb);
- return xfs_getfsmap_helper(cur->bc_tp, info, rec, rec_daddr);
+ return xfs_getfsmap_helper(cur->bc_tp, info, rec, rec_daddr, 0);
}
/* Transform a bnobt irec into a fsmap */
irec.rm_offset = 0;
irec.rm_flags = 0;
- return xfs_getfsmap_helper(cur->bc_tp, info, &irec, rec_daddr);
+ return xfs_getfsmap_helper(cur->bc_tp, info, &irec, rec_daddr, 0);
}
/* Set rmap flags based on the getfsmap flags */
{
struct xfs_mount *mp = tp->t_mountp;
struct xfs_rmap_irec rmap;
- int error;
+ xfs_daddr_t rec_daddr, len_daddr;
+ xfs_fsblock_t start_fsb, end_fsb;
+ uint64_t eofs;
- /* Set up search keys */
- info->low.rm_startblock = XFS_BB_TO_FSBT(mp, keys[0].fmr_physical);
- info->low.rm_offset = XFS_BB_TO_FSBT(mp, keys[0].fmr_offset);
- error = xfs_fsmap_owner_to_rmap(&info->low, keys);
- if (error)
- return error;
- info->low.rm_blockcount = 0;
- xfs_getfsmap_set_irec_flags(&info->low, &keys[0]);
+ eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks);
+ if (keys[0].fmr_physical >= eofs)
+ return 0;
+ start_fsb = XFS_BB_TO_FSBT(mp,
+ keys[0].fmr_physical + keys[0].fmr_length);
+ end_fsb = XFS_BB_TO_FSB(mp, min(eofs - 1, keys[1].fmr_physical));
- error = xfs_fsmap_owner_to_rmap(&info->high, keys + 1);
- if (error)
- return error;
- info->high.rm_startblock = -1U;
- info->high.rm_owner = ULLONG_MAX;
- info->high.rm_offset = ULLONG_MAX;
- info->high.rm_blockcount = 0;
- info->high.rm_flags = XFS_RMAP_KEY_FLAGS | XFS_RMAP_REC_FLAGS;
- info->missing_owner = XFS_FMR_OWN_FREE;
+ /* Adjust the low key if we are continuing from where we left off. */
+ if (keys[0].fmr_length > 0)
+ info->low_daddr = XFS_FSB_TO_BB(mp, start_fsb);
- trace_xfs_fsmap_low_key(mp, info->dev, NULLAGNUMBER, &info->low);
- trace_xfs_fsmap_high_key(mp, info->dev, NULLAGNUMBER, &info->high);
+ trace_xfs_fsmap_low_key_linear(mp, info->dev, start_fsb);
+ trace_xfs_fsmap_high_key_linear(mp, info->dev, end_fsb);
- if (keys[0].fmr_physical > 0)
+ if (start_fsb > 0)
return 0;
/* Fabricate an rmap entry for the external log device. */
rmap.rm_offset = 0;
rmap.rm_flags = 0;
- return xfs_getfsmap_helper(tp, info, &rmap, 0);
+ rec_daddr = XFS_FSB_TO_BB(mp, rmap.rm_startblock);
+ len_daddr = XFS_FSB_TO_BB(mp, rmap.rm_blockcount);
+ return xfs_getfsmap_helper(tp, info, &rmap, rec_daddr, len_daddr);
}
#ifdef CONFIG_XFS_RT
{
struct xfs_getfsmap_info *info = priv;
struct xfs_rmap_irec irec;
- xfs_daddr_t rec_daddr;
+ xfs_rtblock_t rtbno;
+ xfs_daddr_t rec_daddr, len_daddr;
+
+ rtbno = rec->ar_startext * mp->m_sb.sb_rextsize;
+ rec_daddr = XFS_FSB_TO_BB(mp, rtbno);
+ irec.rm_startblock = rtbno;
+
+ rtbno = rec->ar_extcount * mp->m_sb.sb_rextsize;
+ len_daddr = XFS_FSB_TO_BB(mp, rtbno);
+ irec.rm_blockcount = rtbno;
- irec.rm_startblock = rec->ar_startext * mp->m_sb.sb_rextsize;
- rec_daddr = XFS_FSB_TO_BB(mp, irec.rm_startblock);
- irec.rm_blockcount = rec->ar_extcount * mp->m_sb.sb_rextsize;
irec.rm_owner = XFS_RMAP_OWN_NULL; /* "free" */
irec.rm_offset = 0;
irec.rm_flags = 0;
- return xfs_getfsmap_helper(tp, info, &irec, rec_daddr);
+ return xfs_getfsmap_helper(tp, info, &irec, rec_daddr, len_daddr);
}
-/* Execute a getfsmap query against the realtime device. */
+/* Execute a getfsmap query against the realtime device rtbitmap. */
STATIC int
-__xfs_getfsmap_rtdev(
+xfs_getfsmap_rtdev_rtbitmap(
struct xfs_trans *tp,
const struct xfs_fsmap *keys,
- int (*query_fn)(struct xfs_trans *,
- struct xfs_getfsmap_info *),
struct xfs_getfsmap_info *info)
{
+
+ struct xfs_rtalloc_rec alow = { 0 };
+ struct xfs_rtalloc_rec ahigh = { 0 };
struct xfs_mount *mp = tp->t_mountp;
- xfs_fsblock_t start_fsb;
- xfs_fsblock_t end_fsb;
+ xfs_rtblock_t start_rtb;
+ xfs_rtblock_t end_rtb;
uint64_t eofs;
- int error = 0;
+ int error;
- eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rblocks);
+ eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rextents * mp->m_sb.sb_rextsize);
if (keys[0].fmr_physical >= eofs)
return 0;
- start_fsb = XFS_BB_TO_FSBT(mp, keys[0].fmr_physical);
- end_fsb = XFS_BB_TO_FSB(mp, min(eofs - 1, keys[1].fmr_physical));
+ start_rtb = XFS_BB_TO_FSBT(mp,
+ keys[0].fmr_physical + keys[0].fmr_length);
+ end_rtb = XFS_BB_TO_FSB(mp, min(eofs - 1, keys[1].fmr_physical));
- /* Set up search keys */
- info->low.rm_startblock = start_fsb;
- error = xfs_fsmap_owner_to_rmap(&info->low, &keys[0]);
- if (error)
- return error;
- info->low.rm_offset = XFS_BB_TO_FSBT(mp, keys[0].fmr_offset);
- info->low.rm_blockcount = 0;
- xfs_getfsmap_set_irec_flags(&info->low, &keys[0]);
-
- info->high.rm_startblock = end_fsb;
- error = xfs_fsmap_owner_to_rmap(&info->high, &keys[1]);
- if (error)
- return error;
- info->high.rm_offset = XFS_BB_TO_FSBT(mp, keys[1].fmr_offset);
- info->high.rm_blockcount = 0;
- xfs_getfsmap_set_irec_flags(&info->high, &keys[1]);
-
- trace_xfs_fsmap_low_key(mp, info->dev, NULLAGNUMBER, &info->low);
- trace_xfs_fsmap_high_key(mp, info->dev, NULLAGNUMBER, &info->high);
+ info->missing_owner = XFS_FMR_OWN_UNKNOWN;
- return query_fn(tp, info);
-}
+ /* Adjust the low key if we are continuing from where we left off. */
+ if (keys[0].fmr_length > 0) {
+ info->low_daddr = XFS_FSB_TO_BB(mp, start_rtb);
+ if (info->low_daddr >= eofs)
+ return 0;
+ }
-/* Actually query the realtime bitmap. */
-STATIC int
-xfs_getfsmap_rtdev_rtbitmap_query(
- struct xfs_trans *tp,
- struct xfs_getfsmap_info *info)
-{
- struct xfs_rtalloc_rec alow = { 0 };
- struct xfs_rtalloc_rec ahigh = { 0 };
- struct xfs_mount *mp = tp->t_mountp;
- int error;
+ trace_xfs_fsmap_low_key_linear(mp, info->dev, start_rtb);
+ trace_xfs_fsmap_high_key_linear(mp, info->dev, end_rtb);
xfs_ilock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
* Set up query parameters to return free rtextents covering the range
* we want.
*/
- alow.ar_startext = info->low.rm_startblock;
- ahigh.ar_startext = info->high.rm_startblock;
+ alow.ar_startext = start_rtb;
+ ahigh.ar_startext = end_rtb;
do_div(alow.ar_startext, mp->m_sb.sb_rextsize);
if (do_div(ahigh.ar_startext, mp->m_sb.sb_rextsize))
ahigh.ar_startext++;
xfs_iunlock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
return error;
}
-
-/* Execute a getfsmap query against the realtime device rtbitmap. */
-STATIC int
-xfs_getfsmap_rtdev_rtbitmap(
- struct xfs_trans *tp,
- const struct xfs_fsmap *keys,
- struct xfs_getfsmap_info *info)
-{
- info->missing_owner = XFS_FMR_OWN_UNKNOWN;
- return __xfs_getfsmap_rtdev(tp, keys, xfs_getfsmap_rtdev_rtbitmap_query,
- info);
-}
#endif /* CONFIG_XFS_RT */
/* Execute a getfsmap query against the regular data device. */
error = xfs_fsmap_owner_to_rmap(&info->low, &keys[0]);
if (error)
return error;
- info->low.rm_blockcount = 0;
+ info->low.rm_blockcount = XFS_BB_TO_FSBT(mp, keys[0].fmr_length);
xfs_getfsmap_set_irec_flags(&info->low, &keys[0]);
+ /* Adjust the low key if we are continuing from where we left off. */
+ if (info->low.rm_blockcount == 0) {
+ /* empty */
+ } else if (XFS_RMAP_NON_INODE_OWNER(info->low.rm_owner) ||
+ (info->low.rm_flags & (XFS_RMAP_ATTR_FORK |
+ XFS_RMAP_BMBT_BLOCK |
+ XFS_RMAP_UNWRITTEN))) {
+ info->low.rm_startblock += info->low.rm_blockcount;
+ info->low.rm_owner = 0;
+ info->low.rm_offset = 0;
+
+ start_fsb += info->low.rm_blockcount;
+ if (XFS_FSB_TO_DADDR(mp, start_fsb) >= eofs)
+ return 0;
+ } else {
+ info->low.rm_offset += info->low.rm_blockcount;
+ }
+
info->high.rm_startblock = -1U;
info->high.rm_owner = ULLONG_MAX;
info->high.rm_offset = ULLONG_MAX;
* Set the AG low key to the start of the AG prior to
* moving on to the next AG.
*/
- if (pag->pag_agno == start_ag) {
- info->low.rm_startblock = 0;
- info->low.rm_owner = 0;
- info->low.rm_offset = 0;
- info->low.rm_flags = 0;
- }
+ if (pag->pag_agno == start_ag)
+ memset(&info->low, 0, sizeof(info->low));
/*
* If this is the last AG, report any gap at the end of it
struct xfs_fsmap *low_key,
struct xfs_fsmap *high_key)
{
+ if (low_key->fmr_flags & (FMR_OF_SPECIAL_OWNER | FMR_OF_EXTENT_MAP)) {
+ if (low_key->fmr_offset)
+ return false;
+ }
+ if (high_key->fmr_flags != -1U &&
+ (high_key->fmr_flags & (FMR_OF_SPECIAL_OWNER |
+ FMR_OF_EXTENT_MAP))) {
+ if (high_key->fmr_offset && high_key->fmr_offset != -1ULL)
+ return false;
+ }
+ if (high_key->fmr_length && high_key->fmr_length != -1ULL)
+ return false;
+
if (low_key->fmr_device > high_key->fmr_device)
return false;
if (low_key->fmr_device < high_key->fmr_device)
* ----------------
* There are multiple levels of keys and counters at work here:
* xfs_fsmap_head.fmh_keys -- low and high fsmap keys passed in;
- * these reflect fs-wide sector addrs.
+ * these reflect fs-wide sector addrs.
* dkeys -- fmh_keys used to query each device;
- * these are fmh_keys but w/ the low key
- * bumped up by fmr_length.
+ * these are fmh_keys but w/ the low key
+ * bumped up by fmr_length.
* xfs_getfsmap_info.next_daddr -- next disk addr we expect to see; this
* is how we detect gaps in the fsmap
records and report them.
* xfs_getfsmap_info.low/high -- per-AG low/high keys computed from
- * dkeys; used to query the metadata.
+ * dkeys; used to query the metadata.
*/
int
xfs_getfsmap(
if (!xfs_getfsmap_is_valid_device(mp, &head->fmh_keys[0]) ||
!xfs_getfsmap_is_valid_device(mp, &head->fmh_keys[1]))
return -EINVAL;
+ if (!xfs_getfsmap_check_keys(&head->fmh_keys[0], &head->fmh_keys[1]))
+ return -EINVAL;
use_rmap = xfs_has_rmapbt(mp) &&
has_capability_noaudit(current, CAP_SYS_ADMIN);
* blocks could be mapped to several other files/offsets.
* According to rmapbt record ordering, the minimal next
* possible record for the block range is the next starting
- * offset in the same inode. Therefore, bump the file offset to
- * continue the search appropriately. For all other low key
- * mapping types (attr blocks, metadata), bump the physical
- * offset as there can be no other mapping for the same physical
- * block range.
+ * offset in the same inode. Therefore, each fsmap backend bumps
+ * the file offset to continue the search appropriately. For
+ * all other low key mapping types (attr blocks, metadata), each
+ * fsmap backend bumps the physical offset as there can be no
+ * other mapping for the same physical block range.
*/
dkeys[0] = head->fmh_keys[0];
- if (dkeys[0].fmr_flags & (FMR_OF_SPECIAL_OWNER | FMR_OF_EXTENT_MAP)) {
- dkeys[0].fmr_physical += dkeys[0].fmr_length;
- dkeys[0].fmr_owner = 0;
- if (dkeys[0].fmr_offset)
- return -EINVAL;
- } else
- dkeys[0].fmr_offset += dkeys[0].fmr_length;
- dkeys[0].fmr_length = 0;
memset(&dkeys[1], 0xFF, sizeof(struct xfs_fsmap));
- if (!xfs_getfsmap_check_keys(dkeys, &head->fmh_keys[1]))
- return -EINVAL;
-
info.next_daddr = head->fmh_keys[0].fmr_physical +
head->fmh_keys[0].fmr_length;
info.fsmap_recs = fsmap_recs;
info.dev = handlers[i].dev;
info.last = false;
info.pag = NULL;
+ info.low_daddr = -1ULL;
+ info.low.rm_blockcount = 0;
error = handlers[i].fn(tp, dkeys, &info);
if (error)
break;
int num_bblks)
{
struct xlog *log;
- bool fatal = xfs_has_crc(mp);
int error = 0;
int min_logfsbs;
mp->m_log = log;
/*
- * Validate the given log space and drop a critical message via syslog
- * if the log size is too small that would lead to some unexpected
- * situations in transaction log space reservation stage.
+ * Now that we have set up the log and it's internal geometry
+ * parameters, we can validate the given log space and drop a critical
+ * message via syslog if the log size is too small. A log that is too
+ * small can lead to unexpected situations in transaction log space
+ * reservation stage. The superblock verifier has already validated all
+ * the other log geometry constraints, so we don't have to check those
+ * here.
*
- * Note: we can't just reject the mount if the validation fails. This
- * would mean that people would have to downgrade their kernel just to
- * remedy the situation as there is no way to grow the log (short of
- * black magic surgery with xfs_db).
+ * Note: For v4 filesystems, we can't just reject the mount if the
+ * validation fails. This would mean that people would have to
+ * downgrade their kernel just to remedy the situation as there is no
+ * way to grow the log (short of black magic surgery with xfs_db).
*
- * We can, however, reject mounts for CRC format filesystems, as the
+ * We can, however, reject mounts for V5 format filesystems, as the
* mkfs binary being used to make the filesystem should never create a
* filesystem with a log that is too small.
*/
min_logfsbs = xfs_log_calc_minimum_size(mp);
-
if (mp->m_sb.sb_logblocks < min_logfsbs) {
xfs_warn(mp,
"Log size %d blocks too small, minimum size is %d blocks",
mp->m_sb.sb_logblocks, min_logfsbs);
- error = -EINVAL;
- } else if (mp->m_sb.sb_logblocks > XFS_MAX_LOG_BLOCKS) {
- xfs_warn(mp,
- "Log size %d blocks too large, maximum size is %lld blocks",
- mp->m_sb.sb_logblocks, XFS_MAX_LOG_BLOCKS);
- error = -EINVAL;
- } else if (XFS_FSB_TO_B(mp, mp->m_sb.sb_logblocks) > XFS_MAX_LOG_BYTES) {
- xfs_warn(mp,
- "log size %lld bytes too large, maximum size is %lld bytes",
- XFS_FSB_TO_B(mp, mp->m_sb.sb_logblocks),
- XFS_MAX_LOG_BYTES);
- error = -EINVAL;
- } else if (mp->m_sb.sb_logsunit > 1 &&
- mp->m_sb.sb_logsunit % mp->m_sb.sb_blocksize) {
- xfs_warn(mp,
- "log stripe unit %u bytes must be a multiple of block size",
- mp->m_sb.sb_logsunit);
- error = -EINVAL;
- fatal = true;
- }
- if (error) {
+
/*
* Log check errors are always fatal on v5; or whenever bad
* metadata leads to a crash.
*/
- if (fatal) {
+ if (xfs_has_crc(mp)) {
xfs_crit(mp, "AAIEEE! Log failed size checks. Abort!");
ASSERT(0);
+ error = -EINVAL;
goto out_free_log;
}
xfs_crit(mp, "Log size out of supported range.");
int error = 0;
xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, daddr);
xfs_agnumber_t agno = XFS_FSB_TO_AGNO(mp, fsbno);
- xfs_fsblock_t end_fsbno = XFS_DADDR_TO_FSB(mp, daddr + bblen);
+ xfs_fsblock_t end_fsbno = XFS_DADDR_TO_FSB(mp,
+ daddr + bblen - 1);
xfs_agnumber_t end_agno = XFS_FSB_TO_AGNO(mp, end_fsbno);
error = xfs_trans_alloc_empty(mp, &tp);
ddev_end = ddev_start + bdev_nr_bytes(mp->m_ddev_targp->bt_bdev) - 1;
/* Ignore the range out of filesystem area */
- if (offset + len < ddev_start)
+ if (offset + len - 1 < ddev_start)
return -ENXIO;
if (offset > ddev_end)
return -ENXIO;
len -= ddev_start - offset;
offset = 0;
}
- if (offset + len > ddev_end)
- len -= ddev_end - offset;
+ if (offset + len - 1 > ddev_end)
+ len = ddev_end - offset + 1;
return xfs_dax_notify_ddev_failure(mp, BTOBB(offset), BTOBB(len),
mf_flags);
del.br_blockcount);
error = xfs_free_extent_later(*tpp, del.br_startblock,
- del.br_blockcount, NULL);
+ del.br_blockcount, NULL,
+ XFS_AG_RESV_NONE);
if (error)
break;
DEFINE_FSMAP_EVENT(xfs_fsmap_high_key);
DEFINE_FSMAP_EVENT(xfs_fsmap_mapping);
+DECLARE_EVENT_CLASS(xfs_fsmap_linear_class,
+ TP_PROTO(struct xfs_mount *mp, u32 keydev, uint64_t bno),
+ TP_ARGS(mp, keydev, bno),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(dev_t, keydev)
+ __field(xfs_fsblock_t, bno)
+ ),
+ TP_fast_assign(
+ __entry->dev = mp->m_super->s_dev;
+ __entry->keydev = new_decode_dev(keydev);
+ __entry->bno = bno;
+ ),
+ TP_printk("dev %d:%d keydev %d:%d bno 0x%llx",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ MAJOR(__entry->keydev), MINOR(__entry->keydev),
+ __entry->bno)
+)
+#define DEFINE_FSMAP_LINEAR_EVENT(name) \
+DEFINE_EVENT(xfs_fsmap_linear_class, name, \
+ TP_PROTO(struct xfs_mount *mp, u32 keydev, uint64_t bno), \
+ TP_ARGS(mp, keydev, bno))
+DEFINE_FSMAP_LINEAR_EVENT(xfs_fsmap_low_key_linear);
+DEFINE_FSMAP_LINEAR_EVENT(xfs_fsmap_high_key_linear);
+
DECLARE_EVENT_CLASS(xfs_getfsmap_class,
TP_PROTO(struct xfs_mount *mp, struct xfs_fsmap *fsmap),
TP_ARGS(mp, fsmap),
trace_xfs_ail_insert(lip, 0, lsn);
}
lip->li_lsn = lsn;
- list_add(&lip->li_ail, &tmp);
+ list_add_tail(&lip->li_ail, &tmp);
}
if (!list_empty(&tmp))
projects / platform / kernel / linux-starfive.git / commitdiff