Kernel/linux-next
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git synced 2024-12-29 09:12:07 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

New xfs code for 6.13

Browse Source 
* convert perag to use xarrays
 * create a new generic allocation group structure
 * Add metadata inode dir trees
 * Create in-core rt allocation groups
 * Shard the RT section into allocation groups
 * Persist quota options with the enw metadata dir tree
 * Enable quota for RT volumes
 * Enable metadata directory trees
 * Some bugfixes
 
 Signed-off-by: Carlos Maiolino <cem@kernel.org>
 -----BEGIN PGP SIGNATURE-----
 
 iJUEABMJAB0WIQQMHYkcUKcy4GgPe2RGdaER5QtfpgUCZzyNwAAKCRBGdaER5Qtf
 psV3AYCncK/pVhFfKQSFbnCvgPSoAe7N9n0Wt5gmjy0Ill2mbQXVl9ADXkH6a015
 gcGM3t4BgIHLJQndL/Uz+3a0L5IriEb9QkAfzmx8t3vjiRBzBe3WfywEx9Yt7kZe
 xbxEJ2HQpA==
 =3ngC
 -----END PGP SIGNATURE-----

Merge tag 'xfs-6.13-merge-1' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs updates from Carlos Maiolino:
 "The bulk of this pull request is a major rework that Darrick and
  Christoph have been doing on XFS's real-time volume, coupled with a
  few features to support this rework. It does also includes some bug
  fixes.

   - convert perag to use xarrays

   - create a new generic allocation group structure

   - add metadata inode dir trees

   - create in-core rt allocation groups

   - shard the RT section into allocation groups

   - persist quota options with the enw metadata dir tree

   - enable quota for RT volumes

   - enable metadata directory trees

   - some bugfixes"

* tag 'xfs-6.13-merge-1' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (146 commits)
  xfs: port ondisk structure checks from xfs/122 to the kernel
  xfs: separate space btree structures in xfs_ondisk.h
  xfs: convert struct typedefs in xfs_ondisk.h
  xfs: enable metadata directory feature
  xfs: enable realtime quota again
  xfs: update sb field checks when metadir is turned on
  xfs: reserve quota for realtime files correctly
  xfs: create quota preallocation watermarks for realtime quota
  xfs: report realtime block quota limits on realtime directories
  xfs: persist quota flags with metadir
  xfs: advertise realtime quota support in the xqm stat files
  xfs: scrub quota file metapaths
  xfs: fix chown with rt quota
  xfs: use metadir for quota inodes
  xfs: refactor xfs_qm_destroy_quotainos
  xfs: use rtgroup busy extent list for FITRIM
  xfs: implement busy extent tracking for rtgroups
  xfs: port the perag discard code to handle generic groups
  xfs: move the min and max group block numbers to xfs_group
  xfs: adjust min_block usage in xfs_verify_agbno
  ...
This commit is contained in:
Linus Torvalds 2024-11-21 09:20:07 -08:00
commit 2edc8f933d
156 changed files with 9596 additions and 2970 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
fs/iomap/buffered-io.c
View File

@ -1601,6 +1601,8 @@ iomap_ioend_can_merge(struct iomap_ioend *ioend, struct iomap_ioend *next)
{
if (ioend->io_bio.bi_status != next->io_bio.bi_status)
return false;
if (next->io_flags & IOMAP_F_BOUNDARY)
return false;
if ((ioend->io_flags & IOMAP_F_SHARED) ^
(next->io_flags & IOMAP_F_SHARED))
return false;
@ -1720,6 +1722,8 @@ static struct iomap_ioend *iomap_alloc_ioend(struct iomap_writepage_ctx *wpc,
INIT_LIST_HEAD(&ioend->io_list);
ioend->io_type = wpc->iomap.type;
ioend->io_flags = wpc->iomap.flags;
if (pos > wpc->iomap.offset)
wpc->iomap.flags &= ~IOMAP_F_BOUNDARY;
ioend->io_inode = inode;
ioend->io_size = 0;
ioend->io_offset = pos;
@ -1731,6 +1735,8 @@ static struct iomap_ioend *iomap_alloc_ioend(struct iomap_writepage_ctx *wpc,
static bool iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t pos)
{
if (wpc->iomap.offset == pos && (wpc->iomap.flags & IOMAP_F_BOUNDARY))
return false;
if ((wpc->iomap.flags & IOMAP_F_SHARED) !=
(wpc->ioend->io_flags & IOMAP_F_SHARED))
return false;

8
fs/xfs/Makefile
View File

@ -14,7 +14,9 @@ xfs-y += xfs_trace.o
# build the libxfs code first
xfs-y += $(addprefix libxfs/, \
xfs_group.o \
xfs_ag.o \
xfs_ag_resv.o \
xfs_alloc.o \
xfs_alloc_btree.o \
xfs_attr.o \
@ -42,7 +44,8 @@ xfs-y += $(addprefix libxfs/, \
xfs_inode_buf.o \
xfs_inode_util.o \
xfs_log_rlimit.o \
xfs_ag_resv.o \
xfs_metadir.o \
xfs_metafile.o \
xfs_parent.o \
xfs_rmap.o \
xfs_rmap_btree.o \
@ -58,6 +61,7 @@ xfs-y += $(addprefix libxfs/, \
# xfs_rtbitmap is shared with libxfs
xfs-$(CONFIG_XFS_RT) += $(addprefix libxfs/, \
xfs_rtbitmap.o \
xfs_rtgroup.o \
)
# highlevel code
@ -171,6 +175,7 @@ xfs-y += $(addprefix scrub/, \
inode.o \
iscan.o \
listxattr.o \
metapath.o \
nlinks.o \
parent.o \
readdir.o \
@ -186,6 +191,7 @@ xfs-y += $(addprefix scrub/, \
xfs-$(CONFIG_XFS_ONLINE_SCRUB_STATS) += scrub/stats.o
xfs-$(CONFIG_XFS_RT) += $(addprefix scrub/, \
rgsuper.o \
rtbitmap.o \
rtsummary.o \
)

232
fs/xfs/libxfs/xfs_ag.c
View File

@ -30,86 +30,7 @@
#include "xfs_trace.h"
#include "xfs_inode.h"
#include "xfs_icache.h"
/*
* Passive reference counting access wrappers to the perag structures. If the
* per-ag structure is to be freed, the freeing code is responsible for cleaning
* up objects with passive references before freeing the structure. This is
* things like cached buffers.
*/
struct xfs_perag *
xfs_perag_get(
struct xfs_mount *mp,
xfs_agnumber_t agno)
{
struct xfs_perag *pag;
rcu_read_lock();
pag = xa_load(&mp->m_perags, agno);
if (pag) {
trace_xfs_perag_get(pag, _RET_IP_);
ASSERT(atomic_read(&pag->pag_ref) >= 0);
atomic_inc(&pag->pag_ref);
}
rcu_read_unlock();
return pag;
}
/* Get a passive reference to the given perag. */
struct xfs_perag *
xfs_perag_hold(
struct xfs_perag *pag)
{
ASSERT(atomic_read(&pag->pag_ref) > 0 ||
atomic_read(&pag->pag_active_ref) > 0);
trace_xfs_perag_hold(pag, _RET_IP_);
atomic_inc(&pag->pag_ref);
return pag;
}
void
xfs_perag_put(
struct xfs_perag *pag)
{
trace_xfs_perag_put(pag, _RET_IP_);
ASSERT(atomic_read(&pag->pag_ref) > 0);
atomic_dec(&pag->pag_ref);
}
/*
* Active references for perag structures. This is for short term access to the
* per ag structures for walking trees or accessing state. If an AG is being
* shrunk or is offline, then this will fail to find that AG and return NULL
* instead.
*/
struct xfs_perag *
xfs_perag_grab(
struct xfs_mount *mp,
xfs_agnumber_t agno)
{
struct xfs_perag *pag;
rcu_read_lock();
pag = xa_load(&mp->m_perags, agno);
if (pag) {
trace_xfs_perag_grab(pag, _RET_IP_);
if (!atomic_inc_not_zero(&pag->pag_active_ref))
pag = NULL;
}
rcu_read_unlock();
return pag;
}
void
xfs_perag_rele(
struct xfs_perag *pag)
{
trace_xfs_perag_rele(pag, _RET_IP_);
if (atomic_dec_and_test(&pag->pag_active_ref))
wake_up(&pag->pag_active_wq);
}
#include "xfs_group.h"
/*
* xfs_initialize_perag_data
@ -184,6 +105,18 @@ xfs_initialize_perag_data(
return error;
}
static void
xfs_perag_uninit(
struct xfs_group *xg)
{
#ifdef __KERNEL__
struct xfs_perag *pag = to_perag(xg);
cancel_delayed_work_sync(&pag->pag_blockgc_work);
xfs_buf_cache_destroy(&pag->pag_bcache);
#endif
}
/*
* Free up the per-ag resources within the specified AG range.
*/
@ -196,22 +129,8 @@ xfs_free_perag_range(
{
xfs_agnumber_t agno;
for (agno = first_agno; agno < end_agno; agno++) {
struct xfs_perag *pag = xa_erase(&mp->m_perags, agno);
ASSERT(pag);
XFS_IS_CORRUPT(pag->pag_mount, atomic_read(&pag->pag_ref) != 0);
xfs_defer_drain_free(&pag->pag_intents_drain);
cancel_delayed_work_sync(&pag->pag_blockgc_work);
xfs_buf_cache_destroy(&pag->pag_bcache);
/* drop the mount's active reference */
xfs_perag_rele(pag);
XFS_IS_CORRUPT(pag->pag_mount,
atomic_read(&pag->pag_active_ref) != 0);
kfree_rcu_mightsleep(pag);
}
for (agno = first_agno; agno < end_agno; agno++)
xfs_group_free(mp, agno, XG_TYPE_AG, xfs_perag_uninit);
}
/* Find the size of the AG, in blocks. */
@ -273,6 +192,10 @@ xfs_agino_range(
return __xfs_agino_range(mp, xfs_ag_block_count(mp, agno), first, last);
}
/*
* Update the perag of the previous tail AG if it has been changed during
* recovery (i.e. recovery of a growfs).
*/
int
xfs_update_last_ag_size(
struct xfs_mount *mp,
@ -282,88 +205,88 @@ xfs_update_last_ag_size(
if (!pag)
return -EFSCORRUPTED;
pag->block_count = __xfs_ag_block_count(mp, prev_agcount - 1,
mp->m_sb.sb_agcount, mp->m_sb.sb_dblocks);
__xfs_agino_range(mp, pag->block_count, &pag->agino_min,
pag_group(pag)->xg_block_count = __xfs_ag_block_count(mp,
prev_agcount - 1, mp->m_sb.sb_agcount,
mp->m_sb.sb_dblocks);
__xfs_agino_range(mp, pag_group(pag)->xg_block_count, &pag->agino_min,
&pag->agino_max);
xfs_perag_rele(pag);
return 0;
}
int
xfs_initialize_perag(
static int
xfs_perag_alloc(
struct xfs_mount *mp,
xfs_agnumber_t old_agcount,
xfs_agnumber_t new_agcount,
xfs_rfsblock_t dblocks,
xfs_agnumber_t *maxagi)
xfs_agnumber_t index,
xfs_agnumber_t agcount,
xfs_rfsblock_t dblocks)
{
struct xfs_perag *pag;
xfs_agnumber_t index;
int error;
for (index = old_agcount; index < new_agcount; index++) {
pag = kzalloc(sizeof(*pag), GFP_KERNEL);
if (!pag) {
error = -ENOMEM;
goto out_unwind_new_pags;
}
pag->pag_agno = index;
pag->pag_mount = mp;
error = xa_insert(&mp->m_perags, index, pag, GFP_KERNEL);
if (error) {
WARN_ON_ONCE(error == -EBUSY);
goto out_free_pag;
}
if (!pag)
return -ENOMEM;
#ifdef __KERNEL__
/* Place kernel structure only init below this point. */
spin_lock_init(&pag->pag_ici_lock);
spin_lock_init(&pag->pagb_lock);
spin_lock_init(&pag->pag_state_lock);
INIT_DELAYED_WORK(&pag->pag_blockgc_work, xfs_blockgc_worker);
INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC);
xfs_defer_drain_init(&pag->pag_intents_drain);
init_waitqueue_head(&pag->pagb_wait);
init_waitqueue_head(&pag->pag_active_wq);
pag->pagb_count = 0;
pag->pagb_tree = RB_ROOT;
xfs_hooks_init(&pag->pag_rmap_update_hooks);
#endif /* __KERNEL__ */
error = xfs_buf_cache_init(&pag->pag_bcache);
if (error)
goto out_remove_pag;
/* Active ref owned by mount indicates AG is online. */
atomic_set(&pag->pag_active_ref, 1);
goto out_free_perag;
/*
* Pre-calculated geometry
*/
pag->block_count = __xfs_ag_block_count(mp, index, new_agcount,
pag_group(pag)->xg_block_count = __xfs_ag_block_count(mp, index, agcount,
dblocks);
pag->min_block = XFS_AGFL_BLOCK(mp);
__xfs_agino_range(mp, pag->block_count, &pag->agino_min,
pag_group(pag)->xg_min_gbno = XFS_AGFL_BLOCK(mp) + 1;
__xfs_agino_range(mp, pag_group(pag)->xg_block_count, &pag->agino_min,
&pag->agino_max);
error = xfs_group_insert(mp, pag_group(pag), index, XG_TYPE_AG);
if (error)
goto out_buf_cache_destroy;
return 0;
out_buf_cache_destroy:
xfs_buf_cache_destroy(&pag->pag_bcache);
out_free_perag:
kfree(pag);
return error;
}
int
xfs_initialize_perag(
struct xfs_mount *mp,
xfs_agnumber_t orig_agcount,
xfs_agnumber_t new_agcount,
xfs_rfsblock_t dblocks,
xfs_agnumber_t *maxagi)
{
xfs_agnumber_t index;
int error;
if (orig_agcount >= new_agcount)
return 0;
for (index = orig_agcount; index < new_agcount; index++) {
error = xfs_perag_alloc(mp, index, new_agcount, dblocks);
if (error)
goto out_unwind_new_pags;
}
index = xfs_set_inode_alloc(mp, new_agcount);
if (maxagi)
*maxagi = index;
*maxagi = xfs_set_inode_alloc(mp, new_agcount);
mp->m_ag_prealloc_blocks = xfs_prealloc_blocks(mp);
return 0;
out_remove_pag:
xfs_defer_drain_free(&pag->pag_intents_drain);
pag = xa_erase(&mp->m_perags, index);
out_free_pag:
kfree(pag);
out_unwind_new_pags:
xfs_free_perag_range(mp, old_agcount, index);
xfs_free_perag_range(mp, orig_agcount, index);
return error;
}
@ -818,7 +741,7 @@ xfs_ag_shrink_space(
struct xfs_trans **tpp,
xfs_extlen_t delta)
{
struct xfs_mount *mp = pag->pag_mount;
struct xfs_mount *mp = pag_mount(pag);
struct xfs_alloc_arg args = {
.tp = *tpp,
.mp = mp,
@ -835,7 +758,7 @@ xfs_ag_shrink_space(
xfs_agblock_t aglen;
int error, err2;
ASSERT(pag->pag_agno == mp->m_sb.sb_agcount - 1);
ASSERT(pag_agno(pag) == mp->m_sb.sb_agcount - 1);
error = xfs_ialloc_read_agi(pag, *tpp, 0, &agibp);
if (error)
return error;
@ -872,7 +795,7 @@ xfs_ag_shrink_space(
/* internal log shouldn't also show up in the free space btrees */
error = xfs_alloc_vextent_exact_bno(&args,
XFS_AGB_TO_FSB(mp, pag->pag_agno, aglen - delta));
xfs_agbno_to_fsb(pag, aglen - delta));
if (!error && args.agbno == NULLAGBLOCK)
error = -ENOSPC;
@ -931,8 +854,8 @@ xfs_ag_shrink_space(
}
/* Update perag geometry */
pag->block_count -= delta;
__xfs_agino_range(pag->pag_mount, pag->block_count, &pag->agino_min,
pag_group(pag)->xg_block_count -= delta;
__xfs_agino_range(mp, pag_group(pag)->xg_block_count, &pag->agino_min,
&pag->agino_max);
xfs_ialloc_log_agi(*tpp, agibp, XFS_AGI_LENGTH);
@ -958,12 +881,13 @@ xfs_ag_extend_space(
struct xfs_trans *tp,
xfs_extlen_t len)
{
struct xfs_mount *mp = pag_mount(pag);
struct xfs_buf *bp;
struct xfs_agi *agi;
struct xfs_agf *agf;
int error;
ASSERT(pag->pag_agno == pag->pag_mount->m_sb.sb_agcount - 1);
ASSERT(pag_agno(pag) == mp->m_sb.sb_agcount - 1);
error = xfs_ialloc_read_agi(pag, tp, 0, &bp);
if (error)
@ -1002,8 +926,8 @@ xfs_ag_extend_space(
return error;
/* Update perag geometry */
pag->block_count = be32_to_cpu(agf->agf_length);
__xfs_agino_range(pag->pag_mount, pag->block_count, &pag->agino_min,
pag_group(pag)->xg_block_count = be32_to_cpu(agf->agf_length);
__xfs_agino_range(mp, pag_group(pag)->xg_block_count, &pag->agino_min,
&pag->agino_max);
return 0;
}
@ -1031,7 +955,7 @@ xfs_ag_get_geometry(
/* Fill out form. */
memset(ageo, 0, sizeof(*ageo));
ageo->ag_number = pag->pag_agno;
ageo->ag_number = pag_agno(pag);
agi = agi_bp->b_addr;
ageo->ag_icount = be32_to_cpu(agi->agi_count);

205
fs/xfs/libxfs/xfs_ag.h
View File

@ -7,6 +7,8 @@
#ifndef __LIBXFS_AG_H
#define __LIBXFS_AG_H 1
#include "xfs_group.h"
struct xfs_mount;
struct xfs_trans;
struct xfs_perag;
@ -30,11 +32,7 @@ struct xfs_ag_resv {
* performance of allocation group selection.
*/
struct xfs_perag {
struct xfs_mount *pag_mount; /* owner filesystem */
xfs_agnumber_t pag_agno; /* AG this structure belongs to */
atomic_t pag_ref; /* passive reference count */
atomic_t pag_active_ref; /* active reference count */
wait_queue_head_t pag_active_wq;/* woken active_ref falls to zero */
struct xfs_group pag_group;
unsigned long pag_opstate;
uint8_t pagf_bno_level; /* # of levels in bno btree */
uint8_t pagf_cnt_level; /* # of levels in cnt btree */
@ -55,7 +53,6 @@ struct xfs_perag {
xfs_agino_t pagl_leftrec;
xfs_agino_t pagl_rightrec;
int pagb_count; /* pagb slots in use */
uint8_t pagf_refcount_level; /* recount btree height */
/* Blocks reserved for all kinds of metadata. */
@ -64,21 +61,12 @@ struct xfs_perag {
struct xfs_ag_resv pag_rmapbt_resv;
/* Precalculated geometry info */
xfs_agblock_t block_count;
xfs_agblock_t min_block;
xfs_agino_t agino_min;
xfs_agino_t agino_max;
#ifdef __KERNEL__
/* -- kernel only structures below this line -- */
/*
* Bitsets of per-ag metadata that have been checked and/or are sick.
* Callers should hold pag_state_lock before accessing this field.
*/
uint16_t pag_checked;
uint16_t pag_sick;
#ifdef CONFIG_XFS_ONLINE_REPAIR
/*
* Alternate btree heights so that online repair won't trip the write
@ -90,13 +78,6 @@ struct xfs_perag {
uint8_t pagf_repair_rmap_level;
#endif
spinlock_t pag_state_lock;
spinlock_t pagb_lock; /* lock for pagb_tree */
struct rb_root pagb_tree; /* ordered tree of busy extents */
unsigned int pagb_gen; /* generation count for pagb_tree */
wait_queue_head_t pagb_wait; /* woken when pagb_gen changes */
atomic_t pagf_fstrms; /* # of filestreams active in this AG */
spinlock_t pag_ici_lock; /* incore inode cache lock */
@ -108,21 +89,29 @@ struct xfs_perag {
/* background prealloc block trimming */
struct delayed_work pag_blockgc_work;
/*
* We use xfs_drain to track the number of deferred log intent items
* that have been queued (but not yet processed) so that waiters (e.g.
* scrub) will not lock resources when other threads are in the middle
* of processing a chain of intent items only to find momentary
* inconsistencies.
*/
struct xfs_defer_drain pag_intents_drain;
/* Hook to feed rmapbt updates to an active online repair. */
struct xfs_hooks pag_rmap_update_hooks;
#endif /* __KERNEL__ */
};
static inline struct xfs_perag *to_perag(struct xfs_group *xg)
{
return container_of(xg, struct xfs_perag, pag_group);
}
static inline struct xfs_group *pag_group(struct xfs_perag *pag)
{
return &pag->pag_group;
}
static inline struct xfs_mount *pag_mount(const struct xfs_perag *pag)
{
return pag->pag_group.xg_mount;
}
static inline xfs_agnumber_t pag_agno(const struct xfs_perag *pag)
{
return pag->pag_group.xg_gno;
}
/*
* Per-AG operational state. These are atomic flag bits.
*/
@ -144,8 +133,8 @@ __XFS_AG_OPSTATE(prefers_metadata, PREFERS_METADATA)
__XFS_AG_OPSTATE(allows_inodes, ALLOWS_INODES)
__XFS_AG_OPSTATE(agfl_needs_reset, AGFL_NEEDS_RESET)
int xfs_initialize_perag(struct xfs_mount *mp, xfs_agnumber_t old_agcount,
xfs_agnumber_t agcount, xfs_rfsblock_t dcount,
int xfs_initialize_perag(struct xfs_mount *mp, xfs_agnumber_t orig_agcount,
xfs_agnumber_t new_agcount, xfs_rfsblock_t dcount,
xfs_agnumber_t *maxagi);
void xfs_free_perag_range(struct xfs_mount *mp, xfs_agnumber_t first_agno,
xfs_agnumber_t end_agno);
@ -153,13 +142,71 @@ int xfs_initialize_perag_data(struct xfs_mount *mp, xfs_agnumber_t agno);
int xfs_update_last_ag_size(struct xfs_mount *mp, xfs_agnumber_t prev_agcount);
/* Passive AG references */
struct xfs_perag *xfs_perag_get(struct xfs_mount *mp, xfs_agnumber_t agno);
struct xfs_perag *xfs_perag_hold(struct xfs_perag *pag);
void xfs_perag_put(struct xfs_perag *pag);
static inline struct xfs_perag *
xfs_perag_get(
struct xfs_mount *mp,
xfs_agnumber_t agno)
{
return to_perag(xfs_group_get(mp, agno, XG_TYPE_AG));
}
static inline struct xfs_perag *
xfs_perag_hold(
struct xfs_perag *pag)
{
return to_perag(xfs_group_hold(pag_group(pag)));
}
static inline void
xfs_perag_put(
struct xfs_perag *pag)
{
xfs_group_put(pag_group(pag));
}
/* Active AG references */
struct xfs_perag *xfs_perag_grab(struct xfs_mount *, xfs_agnumber_t);
void xfs_perag_rele(struct xfs_perag *pag);
static inline struct xfs_perag *
xfs_perag_grab(
struct xfs_mount *mp,
xfs_agnumber_t agno)
{
return to_perag(xfs_group_grab(mp, agno, XG_TYPE_AG));
}
static inline void
xfs_perag_rele(
struct xfs_perag *pag)
{
xfs_group_rele(pag_group(pag));
}
static inline struct xfs_perag *
xfs_perag_next_range(
struct xfs_mount *mp,
struct xfs_perag *pag,
xfs_agnumber_t start_agno,
xfs_agnumber_t end_agno)
{
return to_perag(xfs_group_next_range(mp, pag ? pag_group(pag) : NULL,
start_agno, end_agno, XG_TYPE_AG));
}
static inline struct xfs_perag *
xfs_perag_next_from(
struct xfs_mount *mp,
struct xfs_perag *pag,
xfs_agnumber_t start_agno)
{
return xfs_perag_next_range(mp, pag, start_agno, mp->m_sb.sb_agcount - 1);
}
static inline struct xfs_perag *
xfs_perag_next(
struct xfs_mount *mp,
struct xfs_perag *pag)
{
return xfs_perag_next_from(mp, pag, 0);
}
/*
* Per-ag geometry infomation and validation
@ -171,11 +218,7 @@ void xfs_agino_range(struct xfs_mount *mp, xfs_agnumber_t agno,
static inline bool
xfs_verify_agbno(struct xfs_perag *pag, xfs_agblock_t agbno)
{
if (agbno >= pag->block_count)
return false;
if (agbno <= pag->min_block)
return false;
return true;
return xfs_verify_gbno(pag_group(pag), agbno);
}
static inline bool
@ -184,13 +227,7 @@ xfs_verify_agbext(
xfs_agblock_t agbno,
xfs_agblock_t len)
{
if (agbno + len <= agbno)
return false;
if (!xfs_verify_agbno(pag, agbno))
return false;
return xfs_verify_agbno(pag, agbno + len - 1);
return xfs_verify_gbext(pag_group(pag), agbno, len);
}
/*
@ -226,40 +263,6 @@ xfs_ag_contains_log(struct xfs_mount *mp, xfs_agnumber_t agno)
agno == XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart);
}
/*
* Perag iteration APIs
*/
static inline struct xfs_perag *
xfs_perag_next(
struct xfs_perag *pag,
xfs_agnumber_t *agno,
xfs_agnumber_t end_agno)
{
struct xfs_mount *mp = pag->pag_mount;
*agno = pag->pag_agno + 1;
xfs_perag_rele(pag);
while (*agno <= end_agno) {
pag = xfs_perag_grab(mp, *agno);
if (pag)
return pag;
(*agno)++;
}
return NULL;
}
#define for_each_perag_range(mp, agno, end_agno, pag) \
for ((pag) = xfs_perag_grab((mp), (agno)); \
(pag) != NULL; \
(pag) = xfs_perag_next((pag), &(agno), (end_agno)))
#define for_each_perag_from(mp, agno, pag) \
for_each_perag_range((mp), (agno), (mp)->m_sb.sb_agcount - 1, (pag))
#define for_each_perag(mp, agno, pag) \
(agno) = 0; \
for_each_perag_from((mp), (agno), (pag))
static inline struct xfs_perag *
xfs_perag_next_wrap(
struct xfs_perag *pag,
@ -268,9 +271,9 @@ xfs_perag_next_wrap(
xfs_agnumber_t restart_agno,
xfs_agnumber_t wrap_agno)
{
struct xfs_mount *mp = pag->pag_mount;
struct xfs_mount *mp = pag_mount(pag);
*agno = pag->pag_agno + 1;
*agno = pag_agno(pag) + 1;
xfs_perag_rele(pag);
while (*agno != stop_agno) {
if (*agno >= wrap_agno) {
@ -332,4 +335,28 @@ int xfs_ag_extend_space(struct xfs_perag *pag, struct xfs_trans *tp,
xfs_extlen_t len);
int xfs_ag_get_geometry(struct xfs_perag *pag, struct xfs_ag_geometry *ageo);
static inline xfs_fsblock_t
xfs_agbno_to_fsb(
struct xfs_perag *pag,
xfs_agblock_t agbno)
{
return XFS_AGB_TO_FSB(pag_mount(pag), pag_agno(pag), agbno);
}
static inline xfs_daddr_t
xfs_agbno_to_daddr(
struct xfs_perag *pag,
xfs_agblock_t agbno)
{
return XFS_AGB_TO_DADDR(pag_mount(pag), pag_agno(pag), agbno);
}
static inline xfs_ino_t
xfs_agino_to_ino(
struct xfs_perag *pag,
xfs_agino_t agino)
{
return XFS_AGINO_TO_INO(pag_mount(pag), pag_agno(pag), agino);
}
#endif /* __LIBXFS_AG_H */

22
fs/xfs/libxfs/xfs_ag_resv.c
View File

@ -70,6 +70,7 @@ xfs_ag_resv_critical(
struct xfs_perag *pag,
enum xfs_ag_resv_type type)
{
struct xfs_mount *mp = pag_mount(pag);
xfs_extlen_t avail;
xfs_extlen_t orig;
@ -92,8 +93,8 @@ xfs_ag_resv_critical(
/* Critically low if less than 10% or max btree height remains. */
return XFS_TEST_ERROR(avail < orig / 10 ||
avail < pag->pag_mount->m_agbtree_maxlevels,
pag->pag_mount, XFS_ERRTAG_AG_RESV_CRITICAL);
avail < mp->m_agbtree_maxlevels,
mp, XFS_ERRTAG_AG_RESV_CRITICAL);
}
/*
@ -137,8 +138,8 @@ __xfs_ag_resv_free(
trace_xfs_ag_resv_free(pag, type, 0);
resv = xfs_perag_resv(pag, type);
if (pag->pag_agno == 0)
pag->pag_mount->m_ag_max_usable += resv->ar_asked;
if (pag_agno(pag) == 0)
pag_mount(pag)->m_ag_max_usable += resv->ar_asked;
/*
* RMAPBT blocks come from the AGFL and AGFL blocks are always
* considered "free", so whatever was reserved at mount time must be
@ -148,7 +149,7 @@ __xfs_ag_resv_free(
oldresv = resv->ar_orig_reserved;
else
oldresv = resv->ar_reserved;
xfs_add_fdblocks(pag->pag_mount, oldresv);
xfs_add_fdblocks(pag_mount(pag), oldresv);
resv->ar_reserved = 0;
resv->ar_asked = 0;
resv->ar_orig_reserved = 0;
@ -170,7 +171,7 @@ __xfs_ag_resv_init(
xfs_extlen_t ask,
xfs_extlen_t used)
{
struct xfs_mount *mp = pag->pag_mount;
struct xfs_mount *mp = pag_mount(pag);
struct xfs_ag_resv *resv;
int error;
xfs_extlen_t hidden_space;
@ -206,11 +207,10 @@ __xfs_ag_resv_init(
else
error = xfs_dec_fdblocks(mp, hidden_space, true);
if (error) {
trace_xfs_ag_resv_init_error(pag->pag_mount, pag->pag_agno,
error, _RET_IP_);
trace_xfs_ag_resv_init_error(pag, error, _RET_IP_);
xfs_warn(mp,
"Per-AG reservation for AG %u failed. Filesystem may run out of space.",
pag->pag_agno);
pag_agno(pag));
return error;
}
@ -220,7 +220,7 @@ __xfs_ag_resv_init(
* counter, we only make the adjustment for AG 0. This assumes that
* there aren't any AGs hungrier for per-AG reservation than AG 0.
*/
if (pag->pag_agno == 0)
if (pag_agno(pag) == 0)
mp->m_ag_max_usable -= ask;
resv = xfs_perag_resv(pag, type);
@ -238,7 +238,7 @@ xfs_ag_resv_init(
struct xfs_perag *pag,
struct xfs_trans *tp)
{
struct xfs_mount *mp = pag->pag_mount;
struct xfs_mount *mp = pag_mount(pag);
xfs_extlen_t ask;
xfs_extlen_t used;
int error = 0, error2;

115
fs/xfs/libxfs/xfs_alloc.c
View File

@ -275,7 +275,7 @@ xfs_alloc_complain_bad_rec(
xfs_warn(mp,
"%sbt record corruption in AG %d detected at %pS!",
cur->bc_ops->name, cur->bc_ag.pag->pag_agno, fa);
cur->bc_ops->name, cur->bc_group->xg_gno, fa);
xfs_warn(mp,
"start block 0x%x block count 0x%x", irec->ar_startblock,
irec->ar_blockcount);
@ -303,7 +303,7 @@ xfs_alloc_get_rec(
return error;
xfs_alloc_btrec_to_irec(rec, &irec);
fa = xfs_alloc_check_irec(cur->bc_ag.pag, &irec);
fa = xfs_alloc_check_irec(to_perag(cur->bc_group), &irec);
if (fa)
return xfs_alloc_complain_bad_rec(cur, fa, &irec);
@ -331,7 +331,8 @@ xfs_alloc_compute_aligned(
bool busy;
/* Trim busy sections out of found extent */
busy = xfs_extent_busy_trim(args, &bno, &len, busy_gen);
busy = xfs_extent_busy_trim(pag_group(args->pag), args->minlen,
args->maxlen, &bno, &len, busy_gen);
/*
* If we have a largish extent that happens to start before min_agbno,
@ -539,7 +540,7 @@ static int
xfs_alloc_fixup_longest(
struct xfs_btree_cur *cnt_cur)
{
struct xfs_perag *pag = cnt_cur->bc_ag.pag;
struct xfs_perag *pag = to_perag(cnt_cur->bc_group);
struct xfs_buf *bp = cnt_cur->bc_ag.agbp;
struct xfs_agf *agf = bp->b_addr;
xfs_extlen_t longest = 0;
@ -799,7 +800,7 @@ xfs_agfl_verify(
* 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(agfl->agfl_seqno) != bp->b_pag->pag_agno)
if (bp->b_pag && be32_to_cpu(agfl->agfl_seqno) != pag_agno((bp->b_pag)))
return __this_address;
for (i = 0; i < xfs_agfl_size(mp); i++) {
@ -879,13 +880,12 @@ xfs_alloc_read_agfl(
struct xfs_trans *tp,
struct xfs_buf **bpp)
{
struct xfs_mount *mp = pag->pag_mount;
struct xfs_mount *mp = pag_mount(pag);
struct xfs_buf *bp;
int error;
error = xfs_trans_read_buf(
mp, tp, mp->m_ddev_targp,
XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGFL_DADDR(mp)),
error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
XFS_AG_DADDR(mp, pag_agno(pag), XFS_AGFL_DADDR(mp)),
XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_agfl_buf_ops);
if (xfs_metadata_is_sick(error))
xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL);
@ -1252,14 +1252,14 @@ xfs_alloc_ag_vextent_small(
if (fbno == NULLAGBLOCK)
goto out;
xfs_extent_busy_reuse(args->mp, args->pag, fbno, 1,
xfs_extent_busy_reuse(pag_group(args->pag), fbno, 1,
(args->datatype & XFS_ALLOC_NOBUSY));
if (args->datatype & XFS_ALLOC_USERDATA) {
struct xfs_buf *bp;
error = xfs_trans_get_buf(args->tp, args->mp->m_ddev_targp,
XFS_AGB_TO_DADDR(args->mp, args->agno, fbno),
xfs_agbno_to_daddr(args->pag, fbno),
args->mp->m_bsize, 0, &bp);
if (error)
goto error;
@ -1365,7 +1365,8 @@ xfs_alloc_ag_vextent_exact(
*/
tbno = fbno;
tlen = flen;
xfs_extent_busy_trim(args, &tbno, &tlen, &busy_gen);
xfs_extent_busy_trim(pag_group(args->pag), args->minlen, args->maxlen,
&tbno, &tlen, &busy_gen);
/*
* Give up if the start of the extent is busy, or the freespace isn't
@ -1758,8 +1759,9 @@ xfs_alloc_ag_vextent_near(
* the allocation can be retried.
*/
trace_xfs_alloc_near_busy(args);
error = xfs_extent_busy_flush(args->tp, args->pag,
acur.busy_gen, alloc_flags);
error = xfs_extent_busy_flush(args->tp,
pag_group(args->pag), acur.busy_gen,
alloc_flags);
if (error)
goto out;
@ -1874,8 +1876,9 @@ xfs_alloc_ag_vextent_size(
* the allocation can be retried.
*/
trace_xfs_alloc_size_busy(args);
error = xfs_extent_busy_flush(args->tp, args->pag,
busy_gen, alloc_flags);
error = xfs_extent_busy_flush(args->tp,
pag_group(args->pag), busy_gen,
alloc_flags);
if (error)
goto error0;
@ -1973,8 +1976,9 @@ xfs_alloc_ag_vextent_size(
* the allocation can be retried.
*/
trace_xfs_alloc_size_busy(args);
error = xfs_extent_busy_flush(args->tp, args->pag,
busy_gen, alloc_flags);
error = xfs_extent_busy_flush(args->tp,
pag_group(args->pag), busy_gen,
alloc_flags);
if (error)
goto error0;
@ -2037,7 +2041,6 @@ int
xfs_free_ag_extent(
struct xfs_trans *tp,
struct xfs_buf *agbp,
xfs_agnumber_t agno,
xfs_agblock_t bno,
xfs_extlen_t len,
const struct xfs_owner_info *oinfo,
@ -2358,19 +2361,19 @@ xfs_free_ag_extent(
* Update the freespace totals in the ag and superblock.
*/
error = xfs_alloc_update_counters(tp, agbp, len);
xfs_ag_resv_free_extent(agbp->b_pag, type, tp, len);
xfs_ag_resv_free_extent(pag, type, tp, len);
if (error)
goto error0;
XFS_STATS_INC(mp, xs_freex);
XFS_STATS_ADD(mp, xs_freeb, len);
trace_xfs_free_extent(mp, agno, bno, len, type, haveleft, haveright);
trace_xfs_free_extent(pag, bno, len, type, haveleft, haveright);
return 0;
error0:
trace_xfs_free_extent(mp, agno, bno, len, type, -1, -1);
trace_xfs_free_extent(pag, bno, len, type, -1, -1);
if (bno_cur)
xfs_btree_del_cursor(bno_cur, XFS_BTREE_ERROR);
if (cnt_cur)
@ -2429,7 +2432,7 @@ xfs_alloc_longest_free_extent(
* reservations and AGFL rules in place, we can return this extent.
*/
if (pag->pagf_longest > delta)
return min_t(xfs_extlen_t, pag->pag_mount->m_ag_max_usable,
return min_t(xfs_extlen_t, pag_mount(pag)->m_ag_max_usable,
pag->pagf_longest - delta);
/* Otherwise, let the caller try for 1 block if there's space. */
@ -2612,7 +2615,7 @@ xfs_agfl_reset(
xfs_warn(mp,
"WARNING: Reset corrupted AGFL on AG %u. %d blocks leaked. "
"Please unmount and run xfs_repair.",
pag->pag_agno, pag->pagf_flcount);
pag_agno(pag), pag->pagf_flcount);
agf->agf_flfirst = 0;
agf->agf_fllast = cpu_to_be32(xfs_agfl_size(mp) - 1);
@ -2645,8 +2648,17 @@ xfs_defer_extent_free(
ASSERT(!isnullstartblock(bno));
ASSERT(!(free_flags & ~XFS_FREE_EXTENT_ALL_FLAGS));
if (free_flags & XFS_FREE_EXTENT_REALTIME) {
if (type != XFS_AG_RESV_NONE) {
ASSERT(type == XFS_AG_RESV_NONE);
return -EFSCORRUPTED;
}
if (XFS_IS_CORRUPT(mp, !xfs_verify_rtbext(mp, bno, len)))
return -EFSCORRUPTED;
} else {
if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbext(mp, bno, len)))
return -EFSCORRUPTED;
}
xefi = kmem_cache_zalloc(xfs_extfree_item_cache,
GFP_KERNEL | __GFP_NOFAIL);
@ -2655,6 +2667,8 @@ xfs_defer_extent_free(
xefi->xefi_agresv = type;
if (free_flags & XFS_FREE_EXTENT_SKIP_DISCARD)
xefi->xefi_flags |= XFS_EFI_SKIP_DISCARD;
if (free_flags & XFS_FREE_EXTENT_REALTIME)
xefi->xefi_flags |= XFS_EFI_REALTIME;
if (oinfo) {
ASSERT(oinfo->oi_offset == 0);
@ -2934,9 +2948,8 @@ xfs_alloc_fix_freelist(
* Deferring the free disconnects freeing up the AGFL slot from
* freeing the block.
*/
error = xfs_free_extent_later(tp,
XFS_AGB_TO_FSB(mp, args->agno, bno), 1,
&targs.oinfo, XFS_AG_RESV_AGFL, 0);
error = xfs_free_extent_later(tp, xfs_agbno_to_fsb(pag, bno),
1, &targs.oinfo, XFS_AG_RESV_AGFL, 0);
if (error)
goto out_agbp_relse;
}
@ -3156,8 +3169,6 @@ xfs_alloc_put_freelist(
logflags |= XFS_AGF_BTREEBLKS;
}
xfs_alloc_log_agf(tp, agbp, logflags);
ASSERT(be32_to_cpu(agf->agf_flcount) <= xfs_agfl_size(mp));
agfl_bno = xfs_buf_to_agfl_bno(agflbp);
@ -3190,7 +3201,7 @@ xfs_validate_ag_length(
* 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)
if (bp->b_pag && seqno != pag_agno(bp->b_pag))
return __this_address;
/*
@ -3359,13 +3370,13 @@ xfs_read_agf(
int flags,
struct xfs_buf **agfbpp)
{
struct xfs_mount *mp = pag->pag_mount;
struct xfs_mount *mp = pag_mount(pag);
int error;
trace_xfs_read_agf(pag->pag_mount, pag->pag_agno);
trace_xfs_read_agf(pag);
error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGF_DADDR(mp)),
XFS_AG_DADDR(mp, pag_agno(pag), XFS_AGF_DADDR(mp)),
XFS_FSS_TO_BB(mp, 1), flags, agfbpp, &xfs_agf_buf_ops);
if (xfs_metadata_is_sick(error))
xfs_ag_mark_sick(pag, XFS_SICK_AG_AGF);
@ -3388,12 +3399,13 @@ xfs_alloc_read_agf(
int flags,
struct xfs_buf **agfbpp)
{
struct xfs_mount *mp = pag_mount(pag);
struct xfs_buf *agfbp;
struct xfs_agf *agf;
int error;
int allocbt_blks;
trace_xfs_alloc_read_agf(pag->pag_mount, pag->pag_agno);
trace_xfs_alloc_read_agf(pag);
/* We don't support trylock when freeing. */
ASSERT((flags & (XFS_ALLOC_FLAG_FREEING | XFS_ALLOC_FLAG_TRYLOCK)) !=
@ -3414,7 +3426,7 @@ xfs_alloc_read_agf(
pag->pagf_cnt_level = be32_to_cpu(agf->agf_cnt_level);
pag->pagf_rmap_level = be32_to_cpu(agf->agf_rmap_level);
pag->pagf_refcount_level = be32_to_cpu(agf->agf_refcount_level);
if (xfs_agfl_needs_reset(pag->pag_mount, agf))
if (xfs_agfl_needs_reset(mp, agf))
set_bit(XFS_AGSTATE_AGFL_NEEDS_RESET, &pag->pag_opstate);
else
clear_bit(XFS_AGSTATE_AGFL_NEEDS_RESET, &pag->pag_opstate);
@ -3427,16 +3439,15 @@ xfs_alloc_read_agf(
* counter only tracks non-root blocks.
*/
allocbt_blks = pag->pagf_btreeblks;
if (xfs_has_rmapbt(pag->pag_mount))
if (xfs_has_rmapbt(mp))
allocbt_blks -= be32_to_cpu(agf->agf_rmap_blocks) - 1;
if (allocbt_blks > 0)
atomic64_add(allocbt_blks,
&pag->pag_mount->m_allocbt_blks);
atomic64_add(allocbt_blks, &mp->m_allocbt_blks);
set_bit(XFS_AGSTATE_AGF_INIT, &pag->pag_opstate);
}
#ifdef DEBUG
else if (!xfs_is_shutdown(pag->pag_mount)) {
else if (!xfs_is_shutdown(mp)) {
ASSERT(pag->pagf_freeblks == be32_to_cpu(agf->agf_freeblks));
ASSERT(pag->pagf_btreeblks == be32_to_cpu(agf->agf_btreeblks));
ASSERT(pag->pagf_flcount == be32_to_cpu(agf->agf_flcount));
@ -3597,7 +3608,7 @@ xfs_alloc_vextent_finish(
goto out_drop_perag;
}
args->fsbno = XFS_AGB_TO_FSB(mp, args->agno, args->agbno);
args->fsbno = xfs_agbno_to_fsb(args->pag, args->agbno);
ASSERT(args->len >= args->minlen);
ASSERT(args->len <= args->maxlen);
@ -3618,8 +3629,8 @@ xfs_alloc_vextent_finish(
if (error)
goto out_drop_perag;
ASSERT(!xfs_extent_busy_search(mp, args->pag, args->agbno,
args->len));
ASSERT(!xfs_extent_busy_search(pag_group(args->pag),
args->agbno, args->len));
}
xfs_ag_resv_alloc_extent(args->pag, args->resv, args);
@ -3649,21 +3660,20 @@ xfs_alloc_vextent_this_ag(
struct xfs_alloc_arg *args,
xfs_agnumber_t agno)
{
struct xfs_mount *mp = args->mp;
xfs_agnumber_t minimum_agno;
uint32_t alloc_flags = 0;
int error;
ASSERT(args->pag != NULL);
ASSERT(args->pag->pag_agno == agno);
ASSERT(pag_agno(args->pag) == agno);
args->agno = agno;
args->agbno = 0;
trace_xfs_alloc_vextent_this_ag(args);
error = xfs_alloc_vextent_check_args(args, XFS_AGB_TO_FSB(mp, agno, 0),
&minimum_agno);
error = xfs_alloc_vextent_check_args(args,
xfs_agbno_to_fsb(args->pag, 0), &minimum_agno);
if (error) {
if (error == -ENOSPC)
return 0;
@ -3868,7 +3878,7 @@ xfs_alloc_vextent_exact_bno(
int error;
ASSERT(args->pag != NULL);
ASSERT(args->pag->pag_agno == XFS_FSB_TO_AGNO(mp, target));
ASSERT(pag_agno(args->pag) == XFS_FSB_TO_AGNO(mp, target));
args->agno = XFS_FSB_TO_AGNO(mp, target);
args->agbno = XFS_FSB_TO_AGBNO(mp, target);
@ -3907,7 +3917,7 @@ xfs_alloc_vextent_near_bno(
int error;
if (!needs_perag)
ASSERT(args->pag->pag_agno == XFS_FSB_TO_AGNO(mp, target));
ASSERT(pag_agno(args->pag) == XFS_FSB_TO_AGNO(mp, target));
args->agno = XFS_FSB_TO_AGNO(mp, target);
args->agbno = XFS_FSB_TO_AGBNO(mp, target);
@ -3944,7 +3954,7 @@ xfs_free_extent_fix_freelist(
memset(&args, 0, sizeof(struct xfs_alloc_arg));
args.tp = tp;
args.mp = tp->t_mountp;
args.agno = pag->pag_agno;
args.agno = pag_agno(pag);
args.pag = pag;
/*
@ -4012,14 +4022,13 @@ __xfs_free_extent(
goto err_release;
}
error = xfs_free_ag_extent(tp, agbp, pag->pag_agno, agbno, len, oinfo,
type);
error = xfs_free_ag_extent(tp, agbp, agbno, len, oinfo, type);
if (error)
goto err_release;
if (skip_discard)
busy_flags |= XFS_EXTENT_BUSY_SKIP_DISCARD;
xfs_extent_busy_insert(tp, pag, agbno, len, busy_flags);
xfs_extent_busy_insert(tp, pag_group(pag), agbno, len, busy_flags);
return 0;
err_release:
@ -4044,7 +4053,7 @@ xfs_alloc_query_range_helper(
xfs_failaddr_t fa;
xfs_alloc_btrec_to_irec(rec, &irec);
fa = xfs_alloc_check_irec(cur->bc_ag.pag, &irec);
fa = xfs_alloc_check_irec(to_perag(cur->bc_group), &irec);
if (fa)
return xfs_alloc_complain_bad_rec(cur, fa, &irec);

19
fs/xfs/libxfs/xfs_alloc.h
View File

@ -79,9 +79,8 @@ int xfs_alloc_put_freelist(struct xfs_perag *pag, struct xfs_trans *tp,
struct xfs_buf *agfbp, struct xfs_buf *agflbp,
xfs_agblock_t bno, int btreeblk);
int xfs_free_ag_extent(struct xfs_trans *tp, struct xfs_buf *agbp,
xfs_agnumber_t agno, xfs_agblock_t bno,
xfs_extlen_t len, const struct xfs_owner_info *oinfo,
enum xfs_ag_resv_type type);
xfs_agblock_t bno, xfs_extlen_t len,
const struct xfs_owner_info *oinfo, enum xfs_ag_resv_type type);
/*
* Compute and fill in value of m_alloc_maxlevels.
@ -238,7 +237,11 @@ int xfs_free_extent_later(struct xfs_trans *tp, xfs_fsblock_t bno,
/* Don't issue a discard for the blocks freed. */
#define XFS_FREE_EXTENT_SKIP_DISCARD (1U << 0)
#define XFS_FREE_EXTENT_ALL_FLAGS (XFS_FREE_EXTENT_SKIP_DISCARD)
/* Free blocks on the realtime device. */
#define XFS_FREE_EXTENT_REALTIME (1U << 1)
#define XFS_FREE_EXTENT_ALL_FLAGS (XFS_FREE_EXTENT_SKIP_DISCARD | \
XFS_FREE_EXTENT_REALTIME)
/*
* List of extents to be free "later".
@ -249,7 +252,7 @@ struct xfs_extent_free_item {
uint64_t xefi_owner;
xfs_fsblock_t xefi_startblock;/* starting fs block number */
xfs_extlen_t xefi_blockcount;/* number of blocks in extent */
struct xfs_perag *xefi_pag;
struct xfs_group *xefi_group;
unsigned int xefi_flags;
enum xfs_ag_resv_type xefi_agresv;
};
@ -258,6 +261,12 @@ struct xfs_extent_free_item {
#define XFS_EFI_ATTR_FORK (1U << 1) /* freeing attr fork block */
#define XFS_EFI_BMBT_BLOCK (1U << 2) /* freeing bmap btree block */
#define XFS_EFI_CANCELLED (1U << 3) /* dont actually free the space */
#define XFS_EFI_REALTIME (1U << 4) /* freeing realtime extent */
static inline bool xfs_efi_is_realtime(const struct xfs_extent_free_item *xefi)
{
return xefi->xefi_flags & XFS_EFI_REALTIME;
}
struct xfs_alloc_autoreap {
struct xfs_defer_pending *dfp;

26
fs/xfs/libxfs/xfs_alloc_btree.c
View File

@ -28,7 +28,7 @@ xfs_bnobt_dup_cursor(
struct xfs_btree_cur *cur)
{
return xfs_bnobt_init_cursor(cur->bc_mp, cur->bc_tp, cur->bc_ag.agbp,
cur->bc_ag.pag);
to_perag(cur->bc_group));
}
STATIC struct xfs_btree_cur *
@ -36,16 +36,16 @@ xfs_cntbt_dup_cursor(
struct xfs_btree_cur *cur)
{
return xfs_cntbt_init_cursor(cur->bc_mp, cur->bc_tp, cur->bc_ag.agbp,
cur->bc_ag.pag);
to_perag(cur->bc_group));
}
STATIC void
xfs_allocbt_set_root(
struct xfs_btree_cur *cur,
const union xfs_btree_ptr *ptr,
int inc)
{
struct xfs_perag *pag = to_perag(cur->bc_group);
struct xfs_buf *agbp = cur->bc_ag.agbp;
struct xfs_agf *agf = agbp->b_addr;
@ -54,11 +54,11 @@ xfs_allocbt_set_root(
if (xfs_btree_is_bno(cur->bc_ops)) {
agf->agf_bno_root = ptr->s;
be32_add_cpu(&agf->agf_bno_level, inc);
cur->bc_ag.pag->pagf_bno_level += inc;
pag->pagf_bno_level += inc;
} else {
agf->agf_cnt_root = ptr->s;
be32_add_cpu(&agf->agf_cnt_level, inc);
cur->bc_ag.pag->pagf_cnt_level += inc;
pag->pagf_cnt_level += inc;
}
xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_ROOTS | XFS_AGF_LEVELS);
@ -75,7 +75,7 @@ xfs_allocbt_alloc_block(
xfs_agblock_t bno;
/* Allocate the new block from the freelist. If we can't, give up. */
error = xfs_alloc_get_freelist(cur->bc_ag.pag, cur->bc_tp,
error = xfs_alloc_get_freelist(to_perag(cur->bc_group), cur->bc_tp,
cur->bc_ag.agbp, &bno, 1);
if (error)
return error;
@ -86,7 +86,7 @@ xfs_allocbt_alloc_block(
}
atomic64_inc(&cur->bc_mp->m_allocbt_blks);
xfs_extent_busy_reuse(cur->bc_mp, cur->bc_ag.pag, bno, 1, false);
xfs_extent_busy_reuse(cur->bc_group, bno, 1, false);
new->s = cpu_to_be32(bno);
@ -104,13 +104,13 @@ xfs_allocbt_free_block(
int error;
bno = xfs_daddr_to_agbno(cur->bc_mp, xfs_buf_daddr(bp));
error = xfs_alloc_put_freelist(cur->bc_ag.pag, cur->bc_tp, agbp, NULL,
bno, 1);
error = xfs_alloc_put_freelist(to_perag(cur->bc_group), cur->bc_tp,
agbp, NULL, bno, 1);
if (error)
return error;
atomic64_dec(&cur->bc_mp->m_allocbt_blks);
xfs_extent_busy_insert(cur->bc_tp, agbp->b_pag, bno, 1,
xfs_extent_busy_insert(cur->bc_tp, pag_group(agbp->b_pag), bno, 1,
XFS_EXTENT_BUSY_SKIP_DISCARD);
return 0;
}
@ -178,7 +178,7 @@ xfs_allocbt_init_ptr_from_cur(
{
struct xfs_agf *agf = cur->bc_ag.agbp->b_addr;
ASSERT(cur->bc_ag.pag->pag_agno == be32_to_cpu(agf->agf_seqno));
ASSERT(cur->bc_group->xg_gno == be32_to_cpu(agf->agf_seqno));
if (xfs_btree_is_bno(cur->bc_ops))
ptr->s = agf->agf_bno_root;
@ -492,7 +492,7 @@ xfs_bnobt_init_cursor(
cur = xfs_btree_alloc_cursor(mp, tp, &xfs_bnobt_ops,
mp->m_alloc_maxlevels, xfs_allocbt_cur_cache);
cur->bc_ag.pag = xfs_perag_hold(pag);
cur->bc_group = xfs_group_hold(pag_group(pag));
cur->bc_ag.agbp = agbp;
if (agbp) {
struct xfs_agf *agf = agbp->b_addr;
@ -518,7 +518,7 @@ xfs_cntbt_init_cursor(
cur = xfs_btree_alloc_cursor(mp, tp, &xfs_cntbt_ops,
mp->m_alloc_maxlevels, xfs_allocbt_cur_cache);
cur->bc_ag.pag = xfs_perag_hold(pag);
cur->bc_group = xfs_group_hold(pag_group(pag));
cur->bc_ag.agbp = agbp;
if (agbp) {
struct xfs_agf *agf = agbp->b_addr;

3
fs/xfs/libxfs/xfs_attr.c
View File

@ -1004,6 +1004,9 @@ xfs_attr_add_fork(
unsigned int blks; /* space reservation */
int error; /* error return value */
if (xfs_is_metadir_inode(ip))
ASSERT(XFS_IS_DQDETACHED(ip));
else
ASSERT(!XFS_NOT_DQATTACHED(mp, ip));
blks = XFS_ADDAFORK_SPACE_RES(mp);

133
fs/xfs/libxfs/xfs_bmap.c
View File

@ -40,6 +40,7 @@
#include "xfs_bmap_item.h"
#include "xfs_symlink_remote.h"
#include "xfs_inode_util.h"
#include "xfs_rtgroup.h"
struct kmem_cache *xfs_bmap_intent_cache;
@ -1042,6 +1043,9 @@ xfs_bmap_add_attrfork(
int error; /* error return value */
xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
if (xfs_is_metadir_inode(ip))
ASSERT(XFS_IS_DQDETACHED(ip));
else
ASSERT(!XFS_NOT_DQATTACHED(mp, ip));
ASSERT(!xfs_inode_has_attr_fork(ip));
@ -1423,6 +1427,24 @@ xfs_bmap_last_offset(
* Extent tree manipulation functions used during allocation.
*/
static inline bool
xfs_bmap_same_rtgroup(
struct xfs_inode *ip,
int whichfork,
struct xfs_bmbt_irec *left,
struct xfs_bmbt_irec *right)
{
struct xfs_mount *mp = ip->i_mount;
if (xfs_ifork_is_realtime(ip, whichfork) && xfs_has_rtgroups(mp)) {
if (xfs_rtb_to_rgno(mp, left->br_startblock) !=
xfs_rtb_to_rgno(mp, right->br_startblock))
return false;
}
return true;
}
/*
* Convert a delayed allocation to a real allocation.
*/
@ -1492,7 +1514,8 @@ xfs_bmap_add_extent_delay_real(
LEFT.br_startoff + LEFT.br_blockcount == new->br_startoff &&
LEFT.br_startblock + LEFT.br_blockcount == new->br_startblock &&
LEFT.br_state == new->br_state &&
LEFT.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN)
LEFT.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN &&
xfs_bmap_same_rtgroup(bma->ip, whichfork, &LEFT, new))
state |= BMAP_LEFT_CONTIG;
/*
@ -1516,7 +1539,8 @@ xfs_bmap_add_extent_delay_real(
(BMAP_LEFT_CONTIG | BMAP_LEFT_FILLING |
BMAP_RIGHT_FILLING) ||
LEFT.br_blockcount + new->br_blockcount + RIGHT.br_blockcount
<= XFS_MAX_BMBT_EXTLEN))
<= XFS_MAX_BMBT_EXTLEN) &&
xfs_bmap_same_rtgroup(bma->ip, whichfork, new, &RIGHT))
state |= BMAP_RIGHT_CONTIG;
error = 0;
@ -2061,7 +2085,8 @@ xfs_bmap_add_extent_unwritten_real(
LEFT.br_startoff + LEFT.br_blockcount == new->br_startoff &&
LEFT.br_startblock + LEFT.br_blockcount == new->br_startblock &&
LEFT.br_state == new->br_state &&
LEFT.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN)
LEFT.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN &&
xfs_bmap_same_rtgroup(ip, whichfork, &LEFT, new))
state |= BMAP_LEFT_CONTIG;
/*
@ -2085,7 +2110,8 @@ xfs_bmap_add_extent_unwritten_real(
(BMAP_LEFT_CONTIG | BMAP_LEFT_FILLING |
BMAP_RIGHT_FILLING) ||
LEFT.br_blockcount + new->br_blockcount + RIGHT.br_blockcount
<= XFS_MAX_BMBT_EXTLEN))
<= XFS_MAX_BMBT_EXTLEN) &&
xfs_bmap_same_rtgroup(ip, whichfork, new, &RIGHT))
state |= BMAP_RIGHT_CONTIG;
/*
@ -2594,7 +2620,8 @@ xfs_bmap_add_extent_hole_delay(
*/
if ((state & BMAP_LEFT_VALID) && (state & BMAP_LEFT_DELAY) &&
left.br_startoff + left.br_blockcount == new->br_startoff &&
left.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN)
left.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN &&
xfs_bmap_same_rtgroup(ip, whichfork, &left, new))
state |= BMAP_LEFT_CONTIG;
if ((state & BMAP_RIGHT_VALID) && (state & BMAP_RIGHT_DELAY) &&
@ -2602,7 +2629,8 @@ xfs_bmap_add_extent_hole_delay(
new->br_blockcount + right.br_blockcount <= XFS_MAX_BMBT_EXTLEN &&
(!(state & BMAP_LEFT_CONTIG) ||
(left.br_blockcount + new->br_blockcount +
right.br_blockcount <= XFS_MAX_BMBT_EXTLEN)))
right.br_blockcount <= XFS_MAX_BMBT_EXTLEN)) &&
xfs_bmap_same_rtgroup(ip, whichfork, new, &right))
state |= BMAP_RIGHT_CONTIG;
/*
@ -2745,7 +2773,8 @@ xfs_bmap_add_extent_hole_real(
left.br_startoff + left.br_blockcount == new->br_startoff &&
left.br_startblock + left.br_blockcount == new->br_startblock &&
left.br_state == new->br_state &&
left.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN)
left.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN &&
xfs_bmap_same_rtgroup(ip, whichfork, &left, new))
state |= BMAP_LEFT_CONTIG;
if ((state & BMAP_RIGHT_VALID) && !(state & BMAP_RIGHT_DELAY) &&
@ -2755,7 +2784,8 @@ xfs_bmap_add_extent_hole_real(
new->br_blockcount + right.br_blockcount <= XFS_MAX_BMBT_EXTLEN &&
(!(state & BMAP_LEFT_CONTIG) ||
left.br_blockcount + new->br_blockcount +
right.br_blockcount <= XFS_MAX_BMBT_EXTLEN))
right.br_blockcount <= XFS_MAX_BMBT_EXTLEN) &&
xfs_bmap_same_rtgroup(ip, whichfork, new, &right))
state |= BMAP_RIGHT_CONTIG;
error = 0;
@ -3121,9 +3151,16 @@ xfs_bmap_adjacent_valid(
struct xfs_mount *mp = ap->ip->i_mount;
if (XFS_IS_REALTIME_INODE(ap->ip) &&
(ap->datatype & XFS_ALLOC_USERDATA))
(ap->datatype & XFS_ALLOC_USERDATA)) {
if (!xfs_has_rtgroups(mp))
return x < mp->m_sb.sb_rblocks;
return xfs_rtb_to_rgno(mp, x) == xfs_rtb_to_rgno(mp, y) &&
xfs_rtb_to_rgno(mp, x) < mp->m_sb.sb_rgcount &&
xfs_rtb_to_rtx(mp, x) < mp->m_sb.sb_rgextents;
}
return XFS_FSB_TO_AGNO(mp, x) == XFS_FSB_TO_AGNO(mp, y) &&
XFS_FSB_TO_AGNO(mp, x) < mp->m_sb.sb_agcount &&
XFS_FSB_TO_AGBNO(mp, x) < mp->m_sb.sb_agblocks;
@ -3280,7 +3317,7 @@ xfs_bmap_longest_free_extent(
}
longest = xfs_alloc_longest_free_extent(pag,
xfs_alloc_min_freelist(pag->pag_mount, pag),
xfs_alloc_min_freelist(pag_mount(pag), pag),
xfs_ag_resv_needed(pag, XFS_AG_RESV_NONE));
if (*blen < longest)
*blen = longest;
@ -4091,7 +4128,7 @@ xfs_bmapi_reserve_delalloc(
fdblocks = indlen;
if (XFS_IS_REALTIME_INODE(ip)) {
error = xfs_dec_frextents(mp, xfs_rtb_to_rtx(mp, alen));
error = xfs_dec_frextents(mp, xfs_blen_to_rtbxlen(mp, alen));
if (error)
goto out_unreserve_quota;
} else {
@ -4126,7 +4163,7 @@ xfs_bmapi_reserve_delalloc(
out_unreserve_frextents:
if (XFS_IS_REALTIME_INODE(ip))
xfs_add_frextents(mp, xfs_rtb_to_rtx(mp, alen));
xfs_add_frextents(mp, xfs_blen_to_rtbxlen(mp, alen));
out_unreserve_quota:
if (XFS_IS_QUOTA_ON(mp))
xfs_quota_unreserve_blkres(ip, alen);
@ -5034,7 +5071,7 @@ xfs_bmap_del_extent_delay(
fdblocks = da_diff;
if (isrt)
xfs_add_frextents(mp, xfs_rtb_to_rtx(mp, del->br_blockcount));
xfs_add_frextents(mp, xfs_blen_to_rtbxlen(mp, del->br_blockcount));
else
fdblocks += del->br_blockcount;
@ -5113,6 +5150,34 @@ xfs_bmap_del_extent_cow(
ip->i_delayed_blks -= del->br_blockcount;
}
static int
xfs_bmap_free_rtblocks(
struct xfs_trans *tp,
struct xfs_bmbt_irec *del)
{
struct xfs_rtgroup *rtg;
int error;
rtg = xfs_rtgroup_grab(tp->t_mountp, 0);
if (!rtg)
return -EIO;
/*
* Ensure the bitmap and summary inodes are locked and joined to the
* transaction before modifying them.
*/
if (!(tp->t_flags & XFS_TRANS_RTBITMAP_LOCKED)) {
tp->t_flags |= XFS_TRANS_RTBITMAP_LOCKED;
xfs_rtgroup_lock(rtg, XFS_RTGLOCK_BITMAP);
xfs_rtgroup_trans_join(tp, rtg, XFS_RTGLOCK_BITMAP);
}
error = xfs_rtfree_blocks(tp, rtg, del->br_startblock,
del->br_blockcount);
xfs_rtgroup_rele(rtg);
return error;
}
/*
* Called by xfs_bmapi to update file extent records and the btree
* after removing space.
@ -5325,20 +5390,12 @@ xfs_bmap_del_extent_real(
* If we need to, add to list of extents to delete.
*/
if (!(bflags & XFS_BMAPI_REMAP)) {
bool isrt = xfs_ifork_is_realtime(ip, whichfork);
if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) {
xfs_refcount_decrease_extent(tp, del);
} else if (xfs_ifork_is_realtime(ip, whichfork)) {
/*
* Ensure the bitmap and summary inodes are locked
* and joined to the transaction before modifying them.
*/
if (!(tp->t_flags & XFS_TRANS_RTBITMAP_LOCKED)) {
tp->t_flags |= XFS_TRANS_RTBITMAP_LOCKED;
xfs_rtbitmap_lock(mp);
xfs_rtbitmap_trans_join(tp);
}
error = xfs_rtfree_blocks(tp, del->br_startblock,
del->br_blockcount);
} else if (isrt && !xfs_has_rtgroups(mp)) {
error = xfs_bmap_free_rtblocks(tp, del);
} else {
unsigned int efi_flags = 0;
@ -5346,6 +5403,19 @@ xfs_bmap_del_extent_real(
del->br_state == XFS_EXT_UNWRITTEN)
efi_flags |= XFS_FREE_EXTENT_SKIP_DISCARD;
/*
* Historically, we did not use EFIs to free realtime
* extents. However, when reverse mapping is enabled,
* we must maintain the same order of operations as the
* data device, which is: Remove the file mapping,
* remove the reverse mapping, and then free the
* blocks. Reflink for realtime volumes requires the
* same sort of ordering. Both features rely on
* rtgroups, so let's gate rt EFI usage on rtgroups.
*/
if (isrt)
efi_flags |= XFS_FREE_EXTENT_REALTIME;
error = xfs_free_extent_later(tp, del->br_startblock,
del->br_blockcount, NULL,
XFS_AG_RESV_NONE, efi_flags);
@ -5694,6 +5764,8 @@ xfs_bunmapi(
*/
STATIC bool
xfs_bmse_can_merge(
struct xfs_inode *ip,
int whichfork,
struct xfs_bmbt_irec *left, /* preceding extent */
struct xfs_bmbt_irec *got, /* current extent to shift */
xfs_fileoff_t shift) /* shift fsb */
@ -5709,7 +5781,8 @@ xfs_bmse_can_merge(
if ((left->br_startoff + left->br_blockcount != startoff) ||
(left->br_startblock + left->br_blockcount != got->br_startblock) ||
(left->br_state != got->br_state) ||
(left->br_blockcount + got->br_blockcount > XFS_MAX_BMBT_EXTLEN))
(left->br_blockcount + got->br_blockcount > XFS_MAX_BMBT_EXTLEN) ||
!xfs_bmap_same_rtgroup(ip, whichfork, left, got))
return false;
return true;
@ -5745,7 +5818,7 @@ xfs_bmse_merge(
blockcount = left->br_blockcount + got->br_blockcount;
xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL);
ASSERT(xfs_bmse_can_merge(left, got, shift));
ASSERT(xfs_bmse_can_merge(ip, whichfork, left, got, shift));
new = *left;
new.br_blockcount = blockcount;
@ -5907,7 +5980,8 @@ xfs_bmap_collapse_extents(
goto del_cursor;
}
if (xfs_bmse_can_merge(&prev, &got, offset_shift_fsb)) {
if (xfs_bmse_can_merge(ip, whichfork, &prev, &got,
offset_shift_fsb)) {
error = xfs_bmse_merge(tp, ip, whichfork,
offset_shift_fsb, &icur, &got, &prev,
cur, &logflags);
@ -6043,7 +6117,8 @@ xfs_bmap_insert_extents(
* never find mergeable extents in this scenario. Check anyways
* and warn if we encounter two extents that could be one.
*/
if (xfs_bmse_can_merge(&got, &next, offset_shift_fsb))
if (xfs_bmse_can_merge(ip, whichfork, &got, &next,
offset_shift_fsb))
WARN_ON_ONCE(1);
}

2
fs/xfs/libxfs/xfs_bmap.h
View File

@ -248,7 +248,7 @@ struct xfs_bmap_intent {
enum xfs_bmap_intent_type bi_type;
int bi_whichfork;
struct xfs_inode *bi_owner;
struct xfs_perag *bi_pag;
struct xfs_group *bi_group;
struct xfs_bmbt_irec bi_bmap;
};

38
fs/xfs/libxfs/xfs_btree.c
View File

@ -225,7 +225,7 @@ __xfs_btree_check_agblock(
struct xfs_buf *bp)
{
struct xfs_mount *mp = cur->bc_mp;
struct xfs_perag *pag = cur->bc_ag.pag;
struct xfs_perag *pag = to_perag(cur->bc_group);
xfs_failaddr_t fa;
xfs_agblock_t agbno;
@ -331,7 +331,7 @@ __xfs_btree_check_ptr(
return -EFSCORRUPTED;
break;
case XFS_BTREE_TYPE_AG:
if (!xfs_verify_agbno(cur->bc_ag.pag,
if (!xfs_verify_agbno(to_perag(cur->bc_group),
be32_to_cpu((&ptr->s)[index])))
return -EFSCORRUPTED;
break;
@ -372,7 +372,7 @@ xfs_btree_check_ptr(
case XFS_BTREE_TYPE_AG:
xfs_err(cur->bc_mp,
"AG %u: Corrupt %sbt pointer at level %d index %d.",
cur->bc_ag.pag->pag_agno, cur->bc_ops->name,
cur->bc_group->xg_gno, cur->bc_ops->name,
level, index);
break;
}
@ -523,20 +523,8 @@ xfs_btree_del_cursor(
ASSERT(!xfs_btree_is_bmap(cur->bc_ops) || cur->bc_bmap.allocated == 0 ||
xfs_is_shutdown(cur->bc_mp) || error != 0);
switch (cur->bc_ops->type) {
case XFS_BTREE_TYPE_AG:
if (cur->bc_ag.pag)
xfs_perag_put(cur->bc_ag.pag);
break;
case XFS_BTREE_TYPE_INODE:
/* nothing to do */
break;
case XFS_BTREE_TYPE_MEM:
if (cur->bc_mem.pag)
xfs_perag_put(cur->bc_mem.pag);
break;
}
if (cur->bc_group)
xfs_group_put(cur->bc_group);
kmem_cache_free(cur->bc_cache, cur);
}
@ -1017,22 +1005,22 @@ xfs_btree_readahead_agblock(
struct xfs_btree_block *block)
{
struct xfs_mount *mp = cur->bc_mp;
xfs_agnumber_t agno = cur->bc_ag.pag->pag_agno;
struct xfs_perag *pag = to_perag(cur->bc_group);
xfs_agblock_t left = be32_to_cpu(block->bb_u.s.bb_leftsib);
xfs_agblock_t right = be32_to_cpu(block->bb_u.s.bb_rightsib);
int rval = 0;
if ((lr & XFS_BTCUR_LEFTRA) && left != NULLAGBLOCK) {
xfs_buf_readahead(mp->m_ddev_targp,
XFS_AGB_TO_DADDR(mp, agno, left),
mp->m_bsize, cur->bc_ops->buf_ops);
xfs_agbno_to_daddr(pag, left), mp->m_bsize,
cur->bc_ops->buf_ops);
rval++;
}
if ((lr & XFS_BTCUR_RIGHTRA) && right != NULLAGBLOCK) {
xfs_buf_readahead(mp->m_ddev_targp,
XFS_AGB_TO_DADDR(mp, agno, right),
mp->m_bsize, cur->bc_ops->buf_ops);
xfs_agbno_to_daddr(pag, right), mp->m_bsize,
cur->bc_ops->buf_ops);
rval++;
}
@ -1091,7 +1079,7 @@ xfs_btree_ptr_to_daddr(
switch (cur->bc_ops->type) {
case XFS_BTREE_TYPE_AG:
*daddr = XFS_AGB_TO_DADDR(cur->bc_mp, cur->bc_ag.pag->pag_agno,
*daddr = xfs_agbno_to_daddr(to_perag(cur->bc_group),
be32_to_cpu(ptr->s));
break;
case XFS_BTREE_TYPE_INODE:
@ -1313,7 +1301,7 @@ xfs_btree_owner(
case XFS_BTREE_TYPE_INODE:
return cur->bc_ino.ip->i_ino;
case XFS_BTREE_TYPE_AG:
return cur->bc_ag.pag->pag_agno;
return cur->bc_group->xg_gno;
default:
ASSERT(0);
return 0;
@ -4745,7 +4733,7 @@ xfs_btree_agblock_v5hdr_verify(
return __this_address;
if (block->bb_u.s.bb_blkno != cpu_to_be64(xfs_buf_daddr(bp)))
return __this_address;
if (pag && be32_to_cpu(block->bb_u.s.bb_owner) != pag->pag_agno)
if (pag && be32_to_cpu(block->bb_u.s.bb_owner) != pag_agno(pag))
return __this_address;
return NULL;
}

3
fs/xfs/libxfs/xfs_btree.h
View File

@ -254,6 +254,7 @@ struct xfs_btree_cur
union xfs_btree_irec bc_rec; /* current insert/search record value */
uint8_t bc_nlevels; /* number of levels in the tree */
uint8_t bc_maxlevels; /* maximum levels for this btree type */
struct xfs_group *bc_group;
/* per-type information */
union {
@ -264,13 +265,11 @@ struct xfs_btree_cur
struct xbtree_ifakeroot *ifake; /* for staging cursor */
} bc_ino;
struct {
struct xfs_perag *pag;
struct xfs_buf *agbp;
struct xbtree_afakeroot *afake; /* for staging cursor */
} bc_ag;
struct {
struct xfbtree *xfbtree;
struct xfs_perag *pag;
} bc_mem;
};

6
fs/xfs/libxfs/xfs_btree_mem.c
View File

@ -57,10 +57,8 @@ xfbtree_dup_cursor(
ncur->bc_flags = cur->bc_flags;
ncur->bc_nlevels = cur->bc_nlevels;
ncur->bc_mem.xfbtree = cur->bc_mem.xfbtree;
if (cur->bc_mem.pag)
ncur->bc_mem.pag = xfs_perag_hold(cur->bc_mem.pag);
if (cur->bc_group)
ncur->bc_group = xfs_group_hold(cur->bc_group);
return ncur;
}

6
fs/xfs/libxfs/xfs_defer.c
View File

@ -846,6 +846,12 @@ xfs_defer_add(
ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
if (!ops->finish_item) {
ASSERT(ops->finish_item != NULL);
xfs_force_shutdown(tp->t_mountp, SHUTDOWN_CORRUPT_INCORE);
return NULL;
}
dfp = xfs_defer_find_last(tp, ops);
if (!dfp || !xfs_defer_can_append(dfp, ops))
dfp = xfs_defer_alloc(&tp->t_dfops, ops);

1
fs/xfs/libxfs/xfs_defer.h
View File

@ -71,6 +71,7 @@ extern const struct xfs_defer_op_type xfs_refcount_update_defer_type;
extern const struct xfs_defer_op_type xfs_rmap_update_defer_type;
extern const struct xfs_defer_op_type xfs_extent_free_defer_type;
extern const struct xfs_defer_op_type xfs_agfl_free_defer_type;
extern const struct xfs_defer_op_type xfs_rtextent_free_defer_type;
extern const struct xfs_defer_op_type xfs_attr_defer_type;
extern const struct xfs_defer_op_type xfs_exchmaps_defer_type;

190
fs/xfs/libxfs/xfs_dquot_buf.c
View File

@ -16,6 +16,9 @@
#include "xfs_trans.h"
#include "xfs_qm.h"
#include "xfs_error.h"
#include "xfs_health.h"
#include "xfs_metadir.h"
#include "xfs_metafile.h"
int
xfs_calc_dquots_per_chunk(
@ -323,3 +326,190 @@ xfs_dquot_to_disk_ts(
return cpu_to_be32(t);
}
inline unsigned int
xfs_dqinode_sick_mask(xfs_dqtype_t type)
{
switch (type) {
case XFS_DQTYPE_USER:
return XFS_SICK_FS_UQUOTA;
case XFS_DQTYPE_GROUP:
return XFS_SICK_FS_GQUOTA;
case XFS_DQTYPE_PROJ:
return XFS_SICK_FS_PQUOTA;
}
ASSERT(0);
return 0;
}
/*
* Load the inode for a given type of quota, assuming that the sb fields have
* been sorted out. This is not true when switching quota types on a V4
* filesystem, so do not use this function for that. If metadir is enabled,
* @dp must be the /quota metadir.
*
* Returns -ENOENT if the quota inode field is NULLFSINO; 0 and an inode on
* success; or a negative errno.
*/
int
xfs_dqinode_load(
struct xfs_trans *tp,
struct xfs_inode *dp,
xfs_dqtype_t type,
struct xfs_inode **ipp)
{
struct xfs_mount *mp = tp->t_mountp;
struct xfs_inode *ip;
enum xfs_metafile_type metafile_type = xfs_dqinode_metafile_type(type);
int error;
if (!xfs_has_metadir(mp)) {
xfs_ino_t ino;
switch (type) {
case XFS_DQTYPE_USER:
ino = mp->m_sb.sb_uquotino;
break;
case XFS_DQTYPE_GROUP:
ino = mp->m_sb.sb_gquotino;
break;
case XFS_DQTYPE_PROJ:
ino = mp->m_sb.sb_pquotino;
break;
default:
ASSERT(0);
return -EFSCORRUPTED;
}
/* Should have set 0 to NULLFSINO when loading superblock */
if (ino == NULLFSINO)
return -ENOENT;
error = xfs_trans_metafile_iget(tp, ino, metafile_type, &ip);
} else {
error = xfs_metadir_load(tp, dp, xfs_dqinode_path(type),
metafile_type, &ip);
if (error == -ENOENT)
return error;
}
if (error) {
if (xfs_metadata_is_sick(error))
xfs_fs_mark_sick(mp, xfs_dqinode_sick_mask(type));
return error;
}
if (XFS_IS_CORRUPT(mp, ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS &&
ip->i_df.if_format != XFS_DINODE_FMT_BTREE)) {
xfs_irele(ip);
xfs_fs_mark_sick(mp, xfs_dqinode_sick_mask(type));
return -EFSCORRUPTED;
}
if (XFS_IS_CORRUPT(mp, ip->i_projid != 0)) {
xfs_irele(ip);
xfs_fs_mark_sick(mp, xfs_dqinode_sick_mask(type));
return -EFSCORRUPTED;
}
*ipp = ip;
return 0;
}
/* Create a metadata directory quota inode. */
int
xfs_dqinode_metadir_create(
struct xfs_inode *dp,
xfs_dqtype_t type,
struct xfs_inode **ipp)
{
struct xfs_metadir_update upd = {
.dp = dp,
.metafile_type = xfs_dqinode_metafile_type(type),
.path = xfs_dqinode_path(type),
};
int error;
error = xfs_metadir_start_create(&upd);
if (error)
return error;
error = xfs_metadir_create(&upd, S_IFREG);
if (error)
return error;
xfs_trans_log_inode(upd.tp, upd.ip, XFS_ILOG_CORE);
error = xfs_metadir_commit(&upd);
if (error)
return error;
xfs_finish_inode_setup(upd.ip);
*ipp = upd.ip;
return 0;
}
#ifndef __KERNEL__
/* Link a metadata directory quota inode. */
int
xfs_dqinode_metadir_link(
struct xfs_inode *dp,
xfs_dqtype_t type,
struct xfs_inode *ip)
{
struct xfs_metadir_update upd = {
.dp = dp,
.metafile_type = xfs_dqinode_metafile_type(type),
.path = xfs_dqinode_path(type),
.ip = ip,
};
int error;
error = xfs_metadir_start_link(&upd);
if (error)
return error;
error = xfs_metadir_link(&upd);
if (error)
return error;
xfs_trans_log_inode(upd.tp, upd.ip, XFS_ILOG_CORE);
return xfs_metadir_commit(&upd);
}
#endif /* __KERNEL__ */
/* Create the parent directory for all quota inodes and load it. */
int
xfs_dqinode_mkdir_parent(
struct xfs_mount *mp,
struct xfs_inode **dpp)
{
if (!mp->m_metadirip) {
xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR);
return -EFSCORRUPTED;
}
return xfs_metadir_mkdir(mp->m_metadirip, "quota", dpp);
}
/*
* Load the parent directory of all quota inodes. Pass the inode to the caller
* because quota functions (e.g. QUOTARM) can be called on the quota files even
* if quotas are not enabled.
*/
int
xfs_dqinode_load_parent(
struct xfs_trans *tp,
struct xfs_inode **dpp)
{
struct xfs_mount *mp = tp->t_mountp;
if (!mp->m_metadirip) {
xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR);
return -EFSCORRUPTED;
}
return xfs_metadir_load(tp, mp->m_metadirip, "quota", XFS_METAFILE_DIR,
dpp);
}

191
fs/xfs/libxfs/xfs_format.h
View File

@ -174,6 +174,14 @@ typedef struct xfs_sb {
xfs_lsn_t sb_lsn; /* last write sequence */
uuid_t sb_meta_uuid; /* metadata file system unique id */
xfs_ino_t sb_metadirino; /* metadata directory tree root */
xfs_rgnumber_t sb_rgcount; /* number of realtime groups */
xfs_rtxlen_t sb_rgextents; /* size of a realtime group in rtx */
uint8_t sb_rgblklog; /* rt group number shift */
uint8_t sb_pad[7]; /* zeroes */
/* must be padded to 64 bit alignment */
} xfs_sb_t;
@ -259,7 +267,19 @@ struct xfs_dsb {
__be64 sb_lsn; /* last write sequence */
uuid_t sb_meta_uuid; /* metadata file system unique id */
/* must be padded to 64 bit alignment */
__be64 sb_metadirino; /* metadata directory tree root */
__be32 sb_rgcount; /* # of realtime groups */
__be32 sb_rgextents; /* size of rtgroup in rtx */
__u8 sb_rgblklog; /* rt group number shift */
__u8 sb_pad[7]; /* zeroes */
/*
* The size of this structure must be padded to 64 bit alignment.
*
* NOTE: Don't forget to update secondary_sb_whack in xfs_repair when
* adding new fields here.
*/
};
#define XFS_SB_CRC_OFF offsetof(struct xfs_dsb, sb_crc)
@ -278,7 +298,7 @@ struct xfs_dsb {
#define XFS_SB_VERSION_NUM(sbp) ((sbp)->sb_versionnum & XFS_SB_VERSION_NUMBITS)
static inline bool xfs_sb_is_v5(struct xfs_sb *sbp)
static inline bool xfs_sb_is_v5(const struct xfs_sb *sbp)
{
return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5;
}
@ -287,12 +307,12 @@ static inline bool xfs_sb_is_v5(struct xfs_sb *sbp)
* Detect a mismatched features2 field. Older kernels read/wrote
* this into the wrong slot, so to be safe we keep them in sync.
*/
static inline bool xfs_sb_has_mismatched_features2(struct xfs_sb *sbp)
static inline bool xfs_sb_has_mismatched_features2(const struct xfs_sb *sbp)
{
return sbp->sb_bad_features2 != sbp->sb_features2;
}
static inline bool xfs_sb_version_hasmorebits(struct xfs_sb *sbp)
static inline bool xfs_sb_version_hasmorebits(const struct xfs_sb *sbp)
{
return xfs_sb_is_v5(sbp) ||
(sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT);
@ -342,7 +362,7 @@ static inline void xfs_sb_version_addprojid32(struct xfs_sb *sbp)
#define XFS_SB_FEAT_COMPAT_UNKNOWN ~XFS_SB_FEAT_COMPAT_ALL
static inline bool
xfs_sb_has_compat_feature(
struct xfs_sb *sbp,
const struct xfs_sb *sbp,
uint32_t feature)
{
return (sbp->sb_features_compat & feature) != 0;
@ -360,7 +380,7 @@ xfs_sb_has_compat_feature(
#define XFS_SB_FEAT_RO_COMPAT_UNKNOWN ~XFS_SB_FEAT_RO_COMPAT_ALL
static inline bool
xfs_sb_has_ro_compat_feature(
struct xfs_sb *sbp,
const struct xfs_sb *sbp,
uint32_t feature)
{
return (sbp->sb_features_ro_compat & feature) != 0;
@ -374,6 +394,7 @@ xfs_sb_has_ro_compat_feature(
#define XFS_SB_FEAT_INCOMPAT_NREXT64 (1 << 5) /* large extent counters */
#define XFS_SB_FEAT_INCOMPAT_EXCHRANGE (1 << 6) /* exchangerange supported */
#define XFS_SB_FEAT_INCOMPAT_PARENT (1 << 7) /* parent pointers */
#define XFS_SB_FEAT_INCOMPAT_METADIR (1 << 8) /* metadata dir tree */
#define XFS_SB_FEAT_INCOMPAT_ALL \
(XFS_SB_FEAT_INCOMPAT_FTYPE | \
XFS_SB_FEAT_INCOMPAT_SPINODES | \
@ -382,12 +403,13 @@ xfs_sb_has_ro_compat_feature(
XFS_SB_FEAT_INCOMPAT_NEEDSREPAIR | \
XFS_SB_FEAT_INCOMPAT_NREXT64 | \
XFS_SB_FEAT_INCOMPAT_EXCHRANGE | \
XFS_SB_FEAT_INCOMPAT_PARENT)
XFS_SB_FEAT_INCOMPAT_PARENT | \
XFS_SB_FEAT_INCOMPAT_METADIR)
#define XFS_SB_FEAT_INCOMPAT_UNKNOWN ~XFS_SB_FEAT_INCOMPAT_ALL
static inline bool
xfs_sb_has_incompat_feature(
struct xfs_sb *sbp,
const struct xfs_sb *sbp,
uint32_t feature)
{
return (sbp->sb_features_incompat & feature) != 0;
@ -399,7 +421,7 @@ xfs_sb_has_incompat_feature(
#define XFS_SB_FEAT_INCOMPAT_LOG_UNKNOWN ~XFS_SB_FEAT_INCOMPAT_LOG_ALL
static inline bool
xfs_sb_has_incompat_log_feature(
struct xfs_sb *sbp,
const struct xfs_sb *sbp,
uint32_t feature)
{
return (sbp->sb_features_log_incompat & feature) != 0;
@ -420,7 +442,7 @@ xfs_sb_add_incompat_log_features(
sbp->sb_features_log_incompat |= features;
}
static inline bool xfs_sb_version_haslogxattrs(struct xfs_sb *sbp)
static inline bool xfs_sb_version_haslogxattrs(const struct xfs_sb *sbp)
{
return xfs_sb_is_v5(sbp) && (sbp->sb_features_log_incompat &
XFS_SB_FEAT_INCOMPAT_LOG_XATTRS);
@ -694,20 +716,57 @@ struct xfs_agfl {
/*
* Realtime bitmap information is accessed by the word, which is currently
* stored in host-endian format.
* stored in host-endian format. Starting with the realtime groups feature,
* the words are stored in be32 ondisk.
*/
union xfs_rtword_raw {
__u32 old;
__be32 rtg;
};
/*
* Realtime summary counts are accessed by the word, which is currently
* stored in host-endian format.
* stored in host-endian format. Starting with the realtime groups feature,
* the words are stored in be32 ondisk.
*/
union xfs_suminfo_raw {
__u32 old;
__be32 rtg;
};
/*
* Realtime allocation groups break the rt section into multiple pieces that
* could be locked independently. Realtime block group numbers are 32-bit
* quantities. Block numbers within a group are also 32-bit quantities, but
* the upper bit must never be set. rtgroup 0 might have a superblock in it,
* so the minimum size of an rtgroup is 2 rtx.
*/
#define XFS_MAX_RGBLOCKS ((xfs_rgblock_t)(1U << 31) - 1)
#define XFS_MIN_RGEXTENTS ((xfs_rtxlen_t)2)
#define XFS_MAX_RGNUMBER ((xfs_rgnumber_t)(-1U))
#define XFS_RTSB_MAGIC 0x46726F67 /* 'Frog' */
/*
* Realtime superblock - on disk version. Must be padded to 64 bit alignment.
* The first block of the realtime volume contains this superblock.
*/
struct xfs_rtsb {
__be32 rsb_magicnum; /* magic number == XFS_RTSB_MAGIC */
__le32 rsb_crc; /* superblock crc */
__be32 rsb_pad; /* zero */
unsigned char rsb_fname[XFSLABEL_MAX]; /* file system name */
uuid_t rsb_uuid; /* user-visible file system unique id */
uuid_t rsb_meta_uuid; /* metadata file system unique id */
/* must be padded to 64 bit alignment */
};
#define XFS_RTSB_CRC_OFF offsetof(struct xfs_rtsb, rsb_crc)
#define XFS_RTSB_DADDR ((xfs_daddr_t)0) /* daddr in rt section */
/*
* XFS Timestamps
* ==============
@ -790,6 +849,27 @@ static inline time64_t xfs_bigtime_to_unix(uint64_t ondisk_seconds)
return (time64_t)ondisk_seconds - XFS_BIGTIME_EPOCH_OFFSET;
}
enum xfs_metafile_type {
XFS_METAFILE_UNKNOWN, /* unknown */
XFS_METAFILE_DIR, /* metadir directory */
XFS_METAFILE_USRQUOTA, /* user quota */
XFS_METAFILE_GRPQUOTA, /* group quota */
XFS_METAFILE_PRJQUOTA, /* project quota */
XFS_METAFILE_RTBITMAP, /* rt bitmap */
XFS_METAFILE_RTSUMMARY, /* rt summary */
XFS_METAFILE_MAX
} __packed;
#define XFS_METAFILE_TYPE_STR \
{ XFS_METAFILE_UNKNOWN, "unknown" }, \
{ XFS_METAFILE_DIR, "dir" }, \
{ XFS_METAFILE_USRQUOTA, "usrquota" }, \
{ XFS_METAFILE_GRPQUOTA, "grpquota" }, \
{ XFS_METAFILE_PRJQUOTA, "prjquota" }, \
{ XFS_METAFILE_RTBITMAP, "rtbitmap" }, \
{ XFS_METAFILE_RTSUMMARY, "rtsummary" }
/*
* On-disk inode structure.
*
@ -812,7 +892,7 @@ struct xfs_dinode {
__be16 di_mode; /* mode and type of file */
__u8 di_version; /* inode version */
__u8 di_format; /* format of di_c data */
__be16 di_onlink; /* old number of links to file */
__be16 di_metatype; /* XFS_METAFILE_*; was di_onlink */
__be32 di_uid; /* owner's user id */
__be32 di_gid; /* owner's group id */
__be32 di_nlink; /* number of links to file */
@ -1088,21 +1168,60 @@ static inline void xfs_dinode_put_rdev(struct xfs_dinode *dip, xfs_dev_t rdev)
* Values for di_flags2 These start by being exposed to userspace in the upper
* 16 bits of the XFS_XFLAG_s range.
*/
#define XFS_DIFLAG2_DAX_BIT 0 /* use DAX for this inode */
#define XFS_DIFLAG2_REFLINK_BIT 1 /* file's blocks may be shared */
#define XFS_DIFLAG2_COWEXTSIZE_BIT 2 /* copy on write extent size hint */
#define XFS_DIFLAG2_BIGTIME_BIT 3 /* big timestamps */
#define XFS_DIFLAG2_NREXT64_BIT 4 /* large extent counters */
/* use DAX for this inode */
#define XFS_DIFLAG2_DAX_BIT 0
#define XFS_DIFLAG2_DAX (1 << XFS_DIFLAG2_DAX_BIT)
#define XFS_DIFLAG2_REFLINK (1 << XFS_DIFLAG2_REFLINK_BIT)
#define XFS_DIFLAG2_COWEXTSIZE (1 << XFS_DIFLAG2_COWEXTSIZE_BIT)
#define XFS_DIFLAG2_BIGTIME (1 << XFS_DIFLAG2_BIGTIME_BIT)
#define XFS_DIFLAG2_NREXT64 (1 << XFS_DIFLAG2_NREXT64_BIT)
/* file's blocks may be shared */
#define XFS_DIFLAG2_REFLINK_BIT 1
/* copy on write extent size hint */
#define XFS_DIFLAG2_COWEXTSIZE_BIT 2
/* big timestamps */
#define XFS_DIFLAG2_BIGTIME_BIT 3
/* large extent counters */
#define XFS_DIFLAG2_NREXT64_BIT 4
/*
* The inode contains filesystem metadata and can be found through the metadata
* directory tree. Metadata inodes must satisfy the following constraints:
*
* - V5 filesystem (and ftype) are enabled;
* - The only valid modes are regular files and directories;
* - The access bits must be zero;
* - DMAPI event and state masks are zero;
* - The user and group IDs must be zero;
* - The project ID can be used as a u32 annotation;
* - The immutable, sync, noatime, nodump, nodefrag flags must be set.
* - The dax flag must not be set.
* - Directories must have nosymlinks set.
*
* These requirements are chosen defensively to minimize the ability of
* userspace to read or modify the contents, should a metadata file ever
* escape to userspace.
*
* There are further constraints on the directory tree itself:
*
* - Metadata inodes must never be resolvable through the root directory;
* - They must never be accessed by userspace;
* - Metadata directory entries must have correct ftype.
*
* Superblock-rooted metadata files must have the METADATA iflag set even
* though they do not have a parent directory.
*/
#define XFS_DIFLAG2_METADATA_BIT 5
#define XFS_DIFLAG2_DAX (1ULL << XFS_DIFLAG2_DAX_BIT)
#define XFS_DIFLAG2_REFLINK (1ULL << XFS_DIFLAG2_REFLINK_BIT)
#define XFS_DIFLAG2_COWEXTSIZE (1ULL << XFS_DIFLAG2_COWEXTSIZE_BIT)
#define XFS_DIFLAG2_BIGTIME (1ULL << XFS_DIFLAG2_BIGTIME_BIT)
#define XFS_DIFLAG2_NREXT64 (1ULL << XFS_DIFLAG2_NREXT64_BIT)
#define XFS_DIFLAG2_METADATA (1ULL << XFS_DIFLAG2_METADATA_BIT)
#define XFS_DIFLAG2_ANY \
(XFS_DIFLAG2_DAX | XFS_DIFLAG2_REFLINK | XFS_DIFLAG2_COWEXTSIZE | \
XFS_DIFLAG2_BIGTIME | XFS_DIFLAG2_NREXT64)
XFS_DIFLAG2_BIGTIME | XFS_DIFLAG2_NREXT64 | XFS_DIFLAG2_METADATA)
static inline bool xfs_dinode_has_bigtime(const struct xfs_dinode *dip)
{
@ -1117,6 +1236,12 @@ static inline bool xfs_dinode_has_large_extent_counts(
(dip->di_flags2 & cpu_to_be64(XFS_DIFLAG2_NREXT64));
}
static inline bool xfs_dinode_is_metadir(const struct xfs_dinode *dip)
{
return dip->di_version >= 3 &&
(dip->di_flags2 & cpu_to_be64(XFS_DIFLAG2_METADATA));
}
/*
* Inode number format:
* low inopblog bits - offset in block
@ -1164,6 +1289,24 @@ static inline bool xfs_dinode_has_large_extent_counts(
#define XFS_DFL_RTEXTSIZE (64 * 1024) /* 64kB */
#define XFS_MIN_RTEXTSIZE (4 * 1024) /* 4kB */
/*
* RT bit manipulation macros.
*/
#define XFS_RTBITMAP_MAGIC 0x424D505A /* BMPZ */
#define XFS_RTSUMMARY_MAGIC 0x53554D59 /* SUMY */
struct xfs_rtbuf_blkinfo {
__be32 rt_magic; /* validity check on block */
__be32 rt_crc; /* CRC of block */
__be64 rt_owner; /* inode that owns the block */
__be64 rt_blkno; /* first block of the buffer */
__be64 rt_lsn; /* sequence number of last write */
uuid_t rt_uuid; /* filesystem we belong to */
};
#define XFS_RTBUF_CRC_OFF \
offsetof(struct xfs_rtbuf_blkinfo, rt_crc)
/*
* Dquot and dquot block format definitions
*/

53
fs/xfs/libxfs/xfs_fs.h
View File

@ -187,7 +187,9 @@ struct xfs_fsop_geom {
__u32 logsunit; /* log stripe unit, bytes */
uint32_t sick; /* o: unhealthy fs & rt metadata */
uint32_t checked; /* o: checked fs & rt metadata */
__u64 reserved[17]; /* reserved space */
__u32 rgextents; /* rt extents in a realtime group */
__u32 rgcount; /* number of realtime groups */
__u64 reserved[16]; /* reserved space */
};
#define XFS_FSOP_GEOM_SICK_COUNTERS (1 << 0) /* summary counters */
@ -198,6 +200,8 @@ struct xfs_fsop_geom {
#define XFS_FSOP_GEOM_SICK_RT_SUMMARY (1 << 5) /* realtime summary */
#define XFS_FSOP_GEOM_SICK_QUOTACHECK (1 << 6) /* quota counts */
#define XFS_FSOP_GEOM_SICK_NLINKS (1 << 7) /* inode link counts */
#define XFS_FSOP_GEOM_SICK_METADIR (1 << 8) /* metadata directory */
#define XFS_FSOP_GEOM_SICK_METAPATH (1 << 9) /* metadir tree path */
/* Output for XFS_FS_COUNTS */
typedef struct xfs_fsop_counts {
@ -242,6 +246,7 @@ typedef struct xfs_fsop_resblks {
#define XFS_FSOP_GEOM_FLAGS_NREXT64 (1 << 23) /* large extent counters */
#define XFS_FSOP_GEOM_FLAGS_EXCHANGE_RANGE (1 << 24) /* exchange range */
#define XFS_FSOP_GEOM_FLAGS_PARENT (1 << 25) /* linux parent pointers */
#define XFS_FSOP_GEOM_FLAGS_METADIR (1 << 26) /* metadata directories */
/*
* Minimum and maximum sizes need for growth checks.
@ -489,9 +494,17 @@ struct xfs_bulk_ireq {
*/
#define XFS_BULK_IREQ_NREXT64 (1U << 2)
/*
* Allow bulkstat to return information about metadata directories. This
* enables xfs_scrub to find them for scanning, as they are otherwise ordinary
* directories.
*/
#define XFS_BULK_IREQ_METADIR (1U << 3)
#define XFS_BULK_IREQ_FLAGS_ALL (XFS_BULK_IREQ_AGNO | \
XFS_BULK_IREQ_SPECIAL | \
XFS_BULK_IREQ_NREXT64)
XFS_BULK_IREQ_NREXT64 | \
XFS_BULK_IREQ_METADIR)
/* Operate on the root directory inode. */
#define XFS_BULK_IREQ_SPECIAL_ROOT (1)
@ -722,9 +735,11 @@ struct xfs_scrub_metadata {
#define XFS_SCRUB_TYPE_NLINKS 26 /* inode link counts */
#define XFS_SCRUB_TYPE_HEALTHY 27 /* everything checked out ok */
#define XFS_SCRUB_TYPE_DIRTREE 28 /* directory tree structure */
#define XFS_SCRUB_TYPE_METAPATH 29 /* metadata directory tree paths */
#define XFS_SCRUB_TYPE_RGSUPER 30 /* realtime superblock */
/* Number of scrub subcommands. */
#define XFS_SCRUB_TYPE_NR 29
#define XFS_SCRUB_TYPE_NR 31
/*
* This special type code only applies to the vectored scrub implementation.
@ -802,6 +817,22 @@ struct xfs_scrub_vec_head {
#define XFS_SCRUB_VEC_FLAGS_ALL (0)
/*
* i: sm_ino values for XFS_SCRUB_TYPE_METAPATH to select a metadata file for
* path checking.
*/
#define XFS_SCRUB_METAPATH_PROBE (0) /* do we have a metapath scrubber? */
#define XFS_SCRUB_METAPATH_RTDIR (1) /* rtrgroups metadir */
#define XFS_SCRUB_METAPATH_RTBITMAP (2) /* per-rtg bitmap */
#define XFS_SCRUB_METAPATH_RTSUMMARY (3) /* per-rtg summary */
#define XFS_SCRUB_METAPATH_QUOTADIR (4) /* quota metadir */
#define XFS_SCRUB_METAPATH_USRQUOTA (5) /* user quota */
#define XFS_SCRUB_METAPATH_GRPQUOTA (6) /* group quota */
#define XFS_SCRUB_METAPATH_PRJQUOTA (7) /* project quota */
/* Number of metapath sm_ino values */
#define XFS_SCRUB_METAPATH_NR (8)
/*
* ioctl limits
*/
@ -948,6 +979,21 @@ struct xfs_getparents_by_handle {
struct xfs_getparents gph_request;
};
/*
* Output for XFS_IOC_RTGROUP_GEOMETRY
*/
struct xfs_rtgroup_geometry {
__u32 rg_number; /* i/o: rtgroup number */
__u32 rg_length; /* o: length in blocks */
__u32 rg_sick; /* o: sick things in ag */
__u32 rg_checked; /* o: checked metadata in ag */
__u32 rg_flags; /* i/o: flags for this ag */
__u32 rg_reserved[27]; /* o: zero */
};
#define XFS_RTGROUP_GEOM_SICK_SUPER (1U << 0) /* superblock */
#define XFS_RTGROUP_GEOM_SICK_BITMAP (1U << 1) /* rtbitmap */
#define XFS_RTGROUP_GEOM_SICK_SUMMARY (1U << 2) /* rtsummary */
/*
* ioctl commands that are used by Linux filesystems
*/
@ -986,6 +1032,7 @@ struct xfs_getparents_by_handle {
#define XFS_IOC_GETPARENTS _IOWR('X', 62, struct xfs_getparents)
#define XFS_IOC_GETPARENTS_BY_HANDLE _IOWR('X', 63, struct xfs_getparents_by_handle)
#define XFS_IOC_SCRUBV_METADATA _IOWR('X', 64, struct xfs_scrub_vec_head)
#define XFS_IOC_RTGROUP_GEOMETRY _IOWR('X', 65, struct xfs_rtgroup_geometry)
/*
* ioctl commands that replace IRIX syssgi()'s

225
fs/xfs/libxfs/xfs_group.c Normal file
View File

@ -0,0 +1,225 @@
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2018 Red Hat, Inc.
*/
#include "xfs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_error.h"
#include "xfs_trace.h"
#include "xfs_extent_busy.h"
#include "xfs_group.h"
/*
* Groups can have passive and active references.
*
* For passive references the code freeing a group is responsible for cleaning
* up objects that hold the passive references (e.g. cached buffers).
* Routines manipulating passive references are xfs_group_get, xfs_group_hold
* and xfs_group_put.
*
* Active references are for short term access to the group for walking trees or
* accessing state. If a group is being shrunk or offlined, the lookup will fail
* to find that group and return NULL instead.
* Routines manipulating active references are xfs_group_grab and
* xfs_group_rele.
*/
struct xfs_group *
xfs_group_get(
struct xfs_mount *mp,
uint32_t index,
enum xfs_group_type type)
{
struct xfs_group *xg;
rcu_read_lock();
xg = xa_load(&mp->m_groups[type].xa, index);
if (xg) {
trace_xfs_group_get(xg, _RET_IP_);
ASSERT(atomic_read(&xg->xg_ref) >= 0);
atomic_inc(&xg->xg_ref);
}
rcu_read_unlock();
return xg;
}
struct xfs_group *
xfs_group_hold(
struct xfs_group *xg)
{
ASSERT(atomic_read(&xg->xg_ref) > 0 ||
atomic_read(&xg->xg_active_ref) > 0);
trace_xfs_group_hold(xg, _RET_IP_);
atomic_inc(&xg->xg_ref);
return xg;
}
void
xfs_group_put(
struct xfs_group *xg)
{
trace_xfs_group_put(xg, _RET_IP_);
ASSERT(atomic_read(&xg->xg_ref) > 0);
atomic_dec(&xg->xg_ref);
}
struct xfs_group *
xfs_group_grab(
struct xfs_mount *mp,
uint32_t index,
enum xfs_group_type type)
{
struct xfs_group *xg;
rcu_read_lock();
xg = xa_load(&mp->m_groups[type].xa, index);
if (xg) {
trace_xfs_group_grab(xg, _RET_IP_);
if (!atomic_inc_not_zero(&xg->xg_active_ref))
xg = NULL;
}
rcu_read_unlock();
return xg;
}
/*
* Iterate to the next group. To start the iteration at @start_index, a %NULL
* @xg is passed, else the previous group returned from this function. The
* caller should break out of the loop when this returns %NULL. If the caller
* wants to break out of a loop that did not finish it needs to release the
* active reference to @xg using xfs_group_rele() itself.
*/
struct xfs_group *
xfs_group_next_range(
struct xfs_mount *mp,
struct xfs_group *xg,
uint32_t start_index,
uint32_t end_index,
enum xfs_group_type type)
{
uint32_t index = start_index;
if (xg) {
index = xg->xg_gno + 1;
xfs_group_rele(xg);
}
if (index > end_index)
return NULL;
return xfs_group_grab(mp, index, type);
}
/*
* Find the next group after @xg, or the first group if @xg is NULL.
*/
struct xfs_group *
xfs_group_grab_next_mark(
struct xfs_mount *mp,
struct xfs_group *xg,
xa_mark_t mark,
enum xfs_group_type type)
{
unsigned long index = 0;
if (xg) {
index = xg->xg_gno + 1;
xfs_group_rele(xg);
}
rcu_read_lock();
xg = xa_find(&mp->m_groups[type].xa, &index, ULONG_MAX, mark);
if (xg) {
trace_xfs_group_grab_next_tag(xg, _RET_IP_);
if (!atomic_inc_not_zero(&xg->xg_active_ref))
xg = NULL;
}
rcu_read_unlock();
return xg;
}
void
xfs_group_rele(
struct xfs_group *xg)
{
trace_xfs_group_rele(xg, _RET_IP_);
atomic_dec(&xg->xg_active_ref);
}
void
xfs_group_free(
struct xfs_mount *mp,
uint32_t index,
enum xfs_group_type type,
void (*uninit)(struct xfs_group *xg))
{
struct xfs_group *xg = xa_erase(&mp->m_groups[type].xa, index);
XFS_IS_CORRUPT(mp, atomic_read(&xg->xg_ref) != 0);
xfs_defer_drain_free(&xg->xg_intents_drain);
#ifdef __KERNEL__
kfree(xg->xg_busy_extents);
#endif
if (uninit)
uninit(xg);
/* drop the mount's active reference */
xfs_group_rele(xg);
XFS_IS_CORRUPT(mp, atomic_read(&xg->xg_active_ref) != 0);
kfree_rcu_mightsleep(xg);
}
int
xfs_group_insert(
struct xfs_mount *mp,
struct xfs_group *xg,
uint32_t index,
enum xfs_group_type type)
{
int error;
xg->xg_mount = mp;
xg->xg_gno = index;
xg->xg_type = type;
#ifdef __KERNEL__
xg->xg_busy_extents = xfs_extent_busy_alloc();
if (!xg->xg_busy_extents)
return -ENOMEM;
spin_lock_init(&xg->xg_state_lock);
xfs_hooks_init(&xg->xg_rmap_update_hooks);
#endif
xfs_defer_drain_init(&xg->xg_intents_drain);
/* Active ref owned by mount indicates group is online. */
atomic_set(&xg->xg_active_ref, 1);
error = xa_insert(&mp->m_groups[type].xa, index, xg, GFP_KERNEL);
if (error) {
WARN_ON_ONCE(error == -EBUSY);
goto out_drain;
}
return 0;
out_drain:
xfs_defer_drain_free(&xg->xg_intents_drain);
#ifdef __KERNEL__
kfree(xg->xg_busy_extents);
#endif
return error;
}
struct xfs_group *
xfs_group_get_by_fsb(
struct xfs_mount *mp,
xfs_fsblock_t fsbno,
enum xfs_group_type type)
{
return xfs_group_get(mp, xfs_fsb_to_gno(mp, fsbno, type), type);
}

164
fs/xfs/libxfs/xfs_group.h Normal file
View File

@ -0,0 +1,164 @@
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (c) 2018 Red Hat, Inc.
*/
#ifndef __LIBXFS_GROUP_H
#define __LIBXFS_GROUP_H 1
struct xfs_group {
struct xfs_mount *xg_mount;
uint32_t xg_gno;
enum xfs_group_type xg_type;
atomic_t xg_ref; /* passive reference count */
atomic_t xg_active_ref; /* active reference count */
/* Precalculated geometry info */
uint32_t xg_block_count; /* max usable gbno */
uint32_t xg_min_gbno; /* min usable gbno */
#ifdef __KERNEL__
/* -- kernel only structures below this line -- */
/*
* Track freed but not yet committed extents.
*/
struct xfs_extent_busy_tree *xg_busy_extents;
/*
* Bitsets of per-ag metadata that have been checked and/or are sick.
* Callers should hold xg_state_lock before accessing this field.
*/
uint16_t xg_checked;
uint16_t xg_sick;
spinlock_t xg_state_lock;
/*
* We use xfs_drain to track the number of deferred log intent items
* that have been queued (but not yet processed) so that waiters (e.g.
* scrub) will not lock resources when other threads are in the middle
* of processing a chain of intent items only to find momentary
* inconsistencies.
*/
struct xfs_defer_drain xg_intents_drain;
/*
* Hook to feed rmapbt updates to an active online repair.
*/
struct xfs_hooks xg_rmap_update_hooks;
#endif /* __KERNEL__ */
};
struct xfs_group *xfs_group_get(struct xfs_mount *mp, uint32_t index,
enum xfs_group_type type);
struct xfs_group *xfs_group_get_by_fsb(struct xfs_mount *mp,
xfs_fsblock_t fsbno, enum xfs_group_type type);
struct xfs_group *xfs_group_hold(struct xfs_group *xg);
void xfs_group_put(struct xfs_group *xg);
struct xfs_group *xfs_group_grab(struct xfs_mount *mp, uint32_t index,
enum xfs_group_type type);
struct xfs_group *xfs_group_next_range(struct xfs_mount *mp,
struct xfs_group *xg, uint32_t start_index, uint32_t end_index,
enum xfs_group_type type);
struct xfs_group *xfs_group_grab_next_mark(struct xfs_mount *mp,
struct xfs_group *xg, xa_mark_t mark, enum xfs_group_type type);
void xfs_group_rele(struct xfs_group *xg);
void xfs_group_free(struct xfs_mount *mp, uint32_t index,
enum xfs_group_type type, void (*uninit)(struct xfs_group *xg));
int xfs_group_insert(struct xfs_mount *mp, struct xfs_group *xg,
uint32_t index, enum xfs_group_type);
#define xfs_group_set_mark(_xg, _mark) \
xa_set_mark(&(_xg)->xg_mount->m_groups[(_xg)->xg_type].xa, \
(_xg)->xg_gno, (_mark))
#define xfs_group_clear_mark(_xg, _mark) \
xa_clear_mark(&(_xg)->xg_mount->m_groups[(_xg)->xg_type].xa, \
(_xg)->xg_gno, (_mark))
#define xfs_group_marked(_mp, _type, _mark) \
xa_marked(&(_mp)->m_groups[(_type)].xa, (_mark))
static inline xfs_agblock_t
xfs_group_max_blocks(
struct xfs_group *xg)
{
return xg->xg_mount->m_groups[xg->xg_type].blocks;
}
static inline xfs_fsblock_t
xfs_group_start_fsb(
struct xfs_group *xg)
{
return ((xfs_fsblock_t)xg->xg_gno) <<
xg->xg_mount->m_groups[xg->xg_type].blklog;
}
static inline xfs_fsblock_t
xfs_gbno_to_fsb(
struct xfs_group *xg,
xfs_agblock_t gbno)
{
return xfs_group_start_fsb(xg) | gbno;
}
static inline xfs_daddr_t
xfs_gbno_to_daddr(
struct xfs_group *xg,
xfs_agblock_t gbno)
{
struct xfs_mount *mp = xg->xg_mount;
uint32_t blocks = mp->m_groups[xg->xg_type].blocks;
return XFS_FSB_TO_BB(mp, (xfs_fsblock_t)xg->xg_gno * blocks + gbno);
}
static inline uint32_t
xfs_fsb_to_gno(
struct xfs_mount *mp,
xfs_fsblock_t fsbno,
enum xfs_group_type type)
{
if (!mp->m_groups[type].blklog)
return 0;
return fsbno >> mp->m_groups[type].blklog;
}
static inline xfs_agblock_t
xfs_fsb_to_gbno(
struct xfs_mount *mp,
xfs_fsblock_t fsbno,
enum xfs_group_type type)
{
return fsbno & mp->m_groups[type].blkmask;
}
static inline bool
xfs_verify_gbno(
struct xfs_group *xg,
uint32_t gbno)
{
if (gbno >= xg->xg_block_count)
return false;
if (gbno < xg->xg_min_gbno)
return false;
return true;
}
static inline bool
xfs_verify_gbext(
struct xfs_group *xg,
uint32_t gbno,
uint32_t glen)
{
uint32_t end;
if (!xfs_verify_gbno(xg, gbno))
return false;
if (glen == 0 || check_add_overflow(gbno, glen - 1, &end))
return false;
if (!xfs_verify_gbno(xg, end))
return false;
return true;
}
#endif /* __LIBXFS_GROUP_H */

83
fs/xfs/libxfs/xfs_health.h
View File

@ -6,6 +6,8 @@
#ifndef __XFS_HEALTH_H__
#define __XFS_HEALTH_H__
struct xfs_group;
/*
* In-Core Filesystem Health Assessments
* =====================================
@ -52,6 +54,7 @@ struct xfs_inode;
struct xfs_fsop_geom;
struct xfs_btree_cur;
struct xfs_da_args;
struct xfs_rtgroup;
/* Observable health issues for metadata spanning the entire filesystem. */
#define XFS_SICK_FS_COUNTERS (1 << 0) /* summary counters */
@ -60,10 +63,13 @@ struct xfs_da_args;
#define XFS_SICK_FS_PQUOTA (1 << 3) /* project quota */
#define XFS_SICK_FS_QUOTACHECK (1 << 4) /* quota counts */
#define XFS_SICK_FS_NLINKS (1 << 5) /* inode link counts */
#define XFS_SICK_FS_METADIR (1 << 6) /* metadata directory tree */
#define XFS_SICK_FS_METAPATH (1 << 7) /* metadata directory tree path */
/* Observable health issues for realtime volume metadata. */
#define XFS_SICK_RT_BITMAP (1 << 0) /* realtime bitmap */
#define XFS_SICK_RT_SUMMARY (1 << 1) /* realtime summary */
/* Observable health issues for realtime group metadata. */
#define XFS_SICK_RG_SUPER (1 << 0) /* rt group superblock */
#define XFS_SICK_RG_BITMAP (1 << 1) /* rt group bitmap */
#define XFS_SICK_RG_SUMMARY (1 << 2) /* rt groups summary */
/* Observable health issues for AG metadata. */
#define XFS_SICK_AG_SB (1 << 0) /* superblock */
@ -103,10 +109,13 @@ struct xfs_da_args;
XFS_SICK_FS_GQUOTA | \
XFS_SICK_FS_PQUOTA | \
XFS_SICK_FS_QUOTACHECK | \
XFS_SICK_FS_NLINKS)
XFS_SICK_FS_NLINKS | \
XFS_SICK_FS_METADIR | \
XFS_SICK_FS_METAPATH)
#define XFS_SICK_RT_PRIMARY (XFS_SICK_RT_BITMAP | \
XFS_SICK_RT_SUMMARY)
#define XFS_SICK_RG_PRIMARY (XFS_SICK_RG_SUPER | \
XFS_SICK_RG_BITMAP | \
XFS_SICK_RG_SUMMARY)
#define XFS_SICK_AG_PRIMARY (XFS_SICK_AG_SB | \
XFS_SICK_AG_AGF | \
@ -136,13 +145,13 @@ struct xfs_da_args;
/* Secondary state related to (but not primary evidence of) health problems. */
#define XFS_SICK_FS_SECONDARY (0)
#define XFS_SICK_RT_SECONDARY (0)
#define XFS_SICK_RG_SECONDARY (0)
#define XFS_SICK_AG_SECONDARY (0)
#define XFS_SICK_INO_SECONDARY (XFS_SICK_INO_FORGET)
/* Evidence of health problems elsewhere. */
#define XFS_SICK_FS_INDIRECT (0)
#define XFS_SICK_RT_INDIRECT (0)
#define XFS_SICK_RG_INDIRECT (0)
#define XFS_SICK_AG_INDIRECT (XFS_SICK_AG_INODES)
#define XFS_SICK_INO_INDIRECT (0)
@ -151,9 +160,9 @@ struct xfs_da_args;
XFS_SICK_FS_SECONDARY | \
XFS_SICK_FS_INDIRECT)
#define XFS_SICK_RT_ALL (XFS_SICK_RT_PRIMARY | \
XFS_SICK_RT_SECONDARY | \
XFS_SICK_RT_INDIRECT)
#define XFS_SICK_RG_ALL (XFS_SICK_RG_PRIMARY | \
XFS_SICK_RG_SECONDARY | \
XFS_SICK_RG_INDIRECT)
#define XFS_SICK_AG_ALL (XFS_SICK_AG_PRIMARY | \
XFS_SICK_AG_SECONDARY | \
@ -189,18 +198,17 @@ void xfs_fs_mark_healthy(struct xfs_mount *mp, unsigned int mask);
void xfs_fs_measure_sickness(struct xfs_mount *mp, unsigned int *sick,
unsigned int *checked);
void xfs_rt_mark_sick(struct xfs_mount *mp, unsigned int mask);
void xfs_rt_mark_corrupt(struct xfs_mount *mp, unsigned int mask);
void xfs_rt_mark_healthy(struct xfs_mount *mp, unsigned int mask);
void xfs_rt_measure_sickness(struct xfs_mount *mp, unsigned int *sick,
unsigned int *checked);
void xfs_rgno_mark_sick(struct xfs_mount *mp, xfs_rgnumber_t rgno,
unsigned int mask);
void xfs_agno_mark_sick(struct xfs_mount *mp, xfs_agnumber_t agno,
unsigned int mask);
void xfs_ag_mark_sick(struct xfs_perag *pag, unsigned int mask);
void xfs_ag_mark_corrupt(struct xfs_perag *pag, unsigned int mask);
void xfs_ag_mark_healthy(struct xfs_perag *pag, unsigned int mask);
void xfs_ag_measure_sickness(struct xfs_perag *pag, unsigned int *sick,
void xfs_group_mark_sick(struct xfs_group *xg, unsigned int mask);
#define xfs_ag_mark_sick(pag, mask) \
xfs_group_mark_sick(pag_group(pag), (mask))
void xfs_group_mark_corrupt(struct xfs_group *xg, unsigned int mask);
void xfs_group_mark_healthy(struct xfs_group *xg, unsigned int mask);
void xfs_group_measure_sickness(struct xfs_group *xg, unsigned int *sick,
unsigned int *checked);
void xfs_inode_mark_sick(struct xfs_inode *ip, unsigned int mask);
@ -227,22 +235,25 @@ xfs_fs_has_sickness(struct xfs_mount *mp, unsigned int mask)
}
static inline bool
xfs_rt_has_sickness(struct xfs_mount *mp, unsigned int mask)
xfs_group_has_sickness(
struct xfs_group *xg,
unsigned int mask)
{
unsigned int sick, checked;
xfs_rt_measure_sickness(mp, &sick, &checked);
xfs_group_measure_sickness(xg, &sick, &checked);
return sick & mask;
}
static inline bool
xfs_ag_has_sickness(struct xfs_perag *pag, unsigned int mask)
{
unsigned int sick, checked;
#define xfs_ag_has_sickness(pag, mask) \
xfs_group_has_sickness(pag_group(pag), (mask))
#define xfs_ag_is_healthy(pag) \
(!xfs_ag_has_sickness((pag), UINT_MAX))
xfs_ag_measure_sickness(pag, &sick, &checked);
return sick & mask;
}
#define xfs_rtgroup_has_sickness(rtg, mask) \
xfs_group_has_sickness(rtg_group(rtg), (mask))
#define xfs_rtgroup_is_healthy(rtg) \
(!xfs_rtgroup_has_sickness((rtg), UINT_MAX))
static inline bool
xfs_inode_has_sickness(struct xfs_inode *ip, unsigned int mask)
@ -259,18 +270,6 @@ xfs_fs_is_healthy(struct xfs_mount *mp)
return !xfs_fs_has_sickness(mp, -1U);
}
static inline bool
xfs_rt_is_healthy(struct xfs_mount *mp)
{
return !xfs_rt_has_sickness(mp, -1U);
}
static inline bool
xfs_ag_is_healthy(struct xfs_perag *pag)
{
return !xfs_ag_has_sickness(pag, -1U);
}
static inline bool
xfs_inode_is_healthy(struct xfs_inode *ip)
{
@ -279,6 +278,8 @@ xfs_inode_is_healthy(struct xfs_inode *ip)
void xfs_fsop_geom_health(struct xfs_mount *mp, struct xfs_fsop_geom *geo);
void xfs_ag_geom_health(struct xfs_perag *pag, struct xfs_ag_geometry *ageo);
void xfs_rtgroup_geom_health(struct xfs_rtgroup *rtg,
struct xfs_rtgroup_geometry *rgeo);
void xfs_bulkstat_health(struct xfs_inode *ip, struct xfs_bulkstat *bs);
#define xfs_metadata_is_sick(error) \

171
fs/xfs/libxfs/xfs_ialloc.c
View File

@ -142,7 +142,7 @@ xfs_inobt_complain_bad_rec(
xfs_warn(mp,
"%sbt record corruption in AG %d detected at %pS!",
cur->bc_ops->name, cur->bc_ag.pag->pag_agno, fa);
cur->bc_ops->name, cur->bc_group->xg_gno, fa);
xfs_warn(mp,
"start inode 0x%x, count 0x%x, free 0x%x freemask 0x%llx, holemask 0x%x",
irec->ir_startino, irec->ir_count, irec->ir_freecount,
@ -170,7 +170,7 @@ xfs_inobt_get_rec(
return error;
xfs_inobt_btrec_to_irec(mp, rec, irec);
fa = xfs_inobt_check_irec(cur->bc_ag.pag, irec);
fa = xfs_inobt_check_irec(to_perag(cur->bc_group), irec);
if (fa)
return xfs_inobt_complain_bad_rec(cur, fa, irec);
@ -275,8 +275,10 @@ xfs_check_agi_freecount(
}
} while (i == 1);
if (!xfs_is_shutdown(cur->bc_mp))
ASSERT(freecount == cur->bc_ag.pag->pagi_freecount);
if (!xfs_is_shutdown(cur->bc_mp)) {
ASSERT(freecount ==
to_perag(cur->bc_group)->pagi_freecount);
}
}
return 0;
}
@ -551,7 +553,7 @@ xfs_inobt_insert_sprec(
struct xfs_buf *agbp,
struct xfs_inobt_rec_incore *nrec) /* in/out: new/merged rec. */
{
struct xfs_mount *mp = pag->pag_mount;
struct xfs_mount *mp = pag_mount(pag);
struct xfs_btree_cur *cur;
int error;
int i;
@ -606,15 +608,12 @@ xfs_inobt_insert_sprec(
goto error;
}
trace_xfs_irec_merge_pre(mp, pag->pag_agno, rec.ir_startino,
rec.ir_holemask, nrec->ir_startino,
nrec->ir_holemask);
trace_xfs_irec_merge_pre(pag, &rec, nrec);
/* merge to nrec to output the updated record */
__xfs_inobt_rec_merge(nrec, &rec);
trace_xfs_irec_merge_post(mp, pag->pag_agno, nrec->ir_startino,
nrec->ir_holemask);
trace_xfs_irec_merge_post(pag, nrec);
error = xfs_inobt_rec_check_count(mp, nrec);
if (error)
@ -648,7 +647,7 @@ xfs_finobt_insert_sprec(
struct xfs_buf *agbp,
struct xfs_inobt_rec_incore *nrec) /* in/out: new rec. */
{
struct xfs_mount *mp = pag->pag_mount;
struct xfs_mount *mp = pag_mount(pag);
struct xfs_btree_cur *cur;
int error;
int i;
@ -768,8 +767,7 @@ xfs_ialloc_ag_alloc(
/* Allow space for the inode btree to split. */
args.minleft = igeo->inobt_maxlevels;
error = xfs_alloc_vextent_exact_bno(&args,
XFS_AGB_TO_FSB(args.mp, pag->pag_agno,
args.agbno));
xfs_agbno_to_fsb(pag, args.agbno));
if (error)
return error;
@ -811,7 +809,7 @@ xfs_ialloc_ag_alloc(
*/
args.minleft = igeo->inobt_maxlevels;
error = xfs_alloc_vextent_near_bno(&args,
XFS_AGB_TO_FSB(args.mp, pag->pag_agno,
xfs_agbno_to_fsb(pag,
be32_to_cpu(agi->agi_root)));
if (error)
return error;
@ -824,7 +822,7 @@ xfs_ialloc_ag_alloc(
if (isaligned && args.fsbno == NULLFSBLOCK) {
args.alignment = igeo->cluster_align;
error = xfs_alloc_vextent_near_bno(&args,
XFS_AGB_TO_FSB(args.mp, pag->pag_agno,
xfs_agbno_to_fsb(pag,
be32_to_cpu(agi->agi_root)));
if (error)
return error;
@ -860,7 +858,7 @@ xfs_ialloc_ag_alloc(
igeo->ialloc_blks;
error = xfs_alloc_vextent_near_bno(&args,
XFS_AGB_TO_FSB(args.mp, pag->pag_agno,
xfs_agbno_to_fsb(pag,
be32_to_cpu(agi->agi_root)));
if (error)
return error;
@ -884,7 +882,7 @@ xfs_ialloc_ag_alloc(
* rather than a linear progression to prevent the next generation
* number from being easily guessable.
*/
error = xfs_ialloc_inode_init(args.mp, tp, NULL, newlen, pag->pag_agno,
error = xfs_ialloc_inode_init(args.mp, tp, NULL, newlen, pag_agno(pag),
args.agbno, args.len, get_random_u32());
if (error)
@ -915,8 +913,7 @@ xfs_ialloc_ag_alloc(
if (error == -EFSCORRUPTED) {
xfs_alert(args.mp,
"invalid sparse inode record: ino 0x%llx holemask 0x%x count %u",
XFS_AGINO_TO_INO(args.mp, pag->pag_agno,
rec.ir_startino),
xfs_agino_to_ino(pag, rec.ir_startino),
rec.ir_holemask, rec.ir_count);
xfs_force_shutdown(args.mp, SHUTDOWN_CORRUPT_INCORE);
}
@ -1076,7 +1073,7 @@ xfs_dialloc_check_ino(
if (error)
return -EAGAIN;
error = xfs_imap_to_bp(pag->pag_mount, tp, &imap, &bp);
error = xfs_imap_to_bp(pag_mount(pag), tp, &imap, &bp);
if (error)
return -EAGAIN;
@ -1127,7 +1124,7 @@ xfs_dialloc_ag_inobt(
/*
* If in the same AG as the parent, try to get near the parent.
*/
if (pagno == pag->pag_agno) {
if (pagno == pag_agno(pag)) {
int doneleft; /* done, to the left */
int doneright; /* done, to the right */
@ -1335,7 +1332,7 @@ xfs_dialloc_ag_inobt(
ASSERT(offset < XFS_INODES_PER_CHUNK);
ASSERT((XFS_AGINO_TO_OFFSET(mp, rec.ir_startino) %
XFS_INODES_PER_CHUNK) == 0);
ino = XFS_AGINO_TO_INO(mp, pag->pag_agno, rec.ir_startino + offset);
ino = xfs_agino_to_ino(pag, rec.ir_startino + offset);
if (xfs_ag_has_sickness(pag, XFS_SICK_AG_INODES)) {
error = xfs_dialloc_check_ino(pag, tp, ino);
@ -1604,7 +1601,7 @@ xfs_dialloc_ag(
* parent. If so, find the closest available inode to the parent. If
* not, consider the agi hint or find the first free inode in the AG.
*/
if (pag->pag_agno == pagno)
if (pag_agno(pag) == pagno)
error = xfs_dialloc_ag_finobt_near(pagino, &cur, &rec);
else
error = xfs_dialloc_ag_finobt_newino(agi, cur, &rec);
@ -1616,7 +1613,7 @@ xfs_dialloc_ag(
ASSERT(offset < XFS_INODES_PER_CHUNK);
ASSERT((XFS_AGINO_TO_OFFSET(mp, rec.ir_startino) %
XFS_INODES_PER_CHUNK) == 0);
ino = XFS_AGINO_TO_INO(mp, pag->pag_agno, rec.ir_startino + offset);
ino = xfs_agino_to_ino(pag, rec.ir_startino + offset);
if (xfs_ag_has_sickness(pag, XFS_SICK_AG_INODES)) {
error = xfs_dialloc_check_ino(pag, tp, ino);
@ -1844,6 +1841,40 @@ xfs_dialloc_try_ag(
return error;
}
/*
* Pick an AG for the new inode.
*
* Directories, symlinks, and regular files frequently allocate at least one
* block, so factor that potential expansion when we examine whether an AG has
* enough space for file creation. Try to keep metadata files all in the same
* AG.
*/
static inline xfs_agnumber_t
xfs_dialloc_pick_ag(
struct xfs_mount *mp,
struct xfs_inode *dp,
umode_t mode)
{
xfs_agnumber_t start_agno;
if (!dp)
return 0;
if (xfs_is_metadir_inode(dp)) {
if (mp->m_sb.sb_logstart)
return XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart);
return 0;
}
if (S_ISDIR(mode))
return (atomic_inc_return(&mp->m_agirotor) - 1) % mp->m_maxagi;
start_agno = XFS_INO_TO_AGNO(mp, dp->i_ino);
if (start_agno >= mp->m_maxagi)
start_agno = 0;
return start_agno;
}
/*
* Allocate an on-disk inode.
*
@ -1859,31 +1890,19 @@ xfs_dialloc(
xfs_ino_t *new_ino)
{
struct xfs_mount *mp = (*tpp)->t_mountp;
xfs_ino_t parent = args->pip ? args->pip->i_ino : 0;
umode_t mode = args->mode & S_IFMT;
xfs_agnumber_t agno;
int error = 0;
xfs_agnumber_t start_agno;
struct xfs_perag *pag;
struct xfs_ino_geometry *igeo = M_IGEO(mp);
xfs_ino_t ino = NULLFSINO;
xfs_ino_t parent = args->pip ? args->pip->i_ino : 0;
xfs_agnumber_t agno;
xfs_agnumber_t start_agno;
umode_t mode = args->mode & S_IFMT;
bool ok_alloc = true;
bool low_space = false;
int flags;
xfs_ino_t ino = NULLFSINO;
int error = 0;
/*
* Directories, symlinks, and regular files frequently allocate at least
* one block, so factor that potential expansion when we examine whether
* an AG has enough space for file creation.
*/
if (S_ISDIR(mode))
start_agno = (atomic_inc_return(&mp->m_agirotor) - 1) %
mp->m_maxagi;
else {
start_agno = XFS_INO_TO_AGNO(mp, parent);
if (start_agno >= mp->m_maxagi)
start_agno = 0;
}
start_agno = xfs_dialloc_pick_ag(mp, args->pip, mode);
/*
* If we have already hit the ceiling of inode blocks then clear
@ -1974,7 +1993,7 @@ xfs_dialloc(
static int
xfs_difree_inode_chunk(
struct xfs_trans *tp,
xfs_agnumber_t agno,
struct xfs_perag *pag,
struct xfs_inobt_rec_incore *rec)
{
struct xfs_mount *mp = tp->t_mountp;
@ -1988,8 +2007,7 @@ xfs_difree_inode_chunk(
if (!xfs_inobt_issparse(rec->ir_holemask)) {
/* not sparse, calculate extent info directly */
return xfs_free_extent_later(tp,
XFS_AGB_TO_FSB(mp, agno, sagbno),
return xfs_free_extent_later(tp, xfs_agbno_to_fsb(pag, sagbno),
M_IGEO(mp)->ialloc_blks, &XFS_RMAP_OINFO_INODES,
XFS_AG_RESV_NONE, 0);
}
@ -2035,9 +2053,9 @@ xfs_difree_inode_chunk(
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_AG_RESV_NONE, 0);
error = xfs_free_extent_later(tp, xfs_agbno_to_fsb(pag, agbno),
contigblk, &XFS_RMAP_OINFO_INODES,
XFS_AG_RESV_NONE, 0);
if (error)
return error;
@ -2059,7 +2077,7 @@ xfs_difree_inobt(
struct xfs_icluster *xic,
struct xfs_inobt_rec_incore *orec)
{
struct xfs_mount *mp = pag->pag_mount;
struct xfs_mount *mp = pag_mount(pag);
struct xfs_agi *agi = agbp->b_addr;
struct xfs_btree_cur *cur;
struct xfs_inobt_rec_incore rec;
@ -2124,8 +2142,7 @@ xfs_difree_inobt(
if (!xfs_has_ikeep(mp) && rec.ir_free == XFS_INOBT_ALL_FREE &&
mp->m_sb.sb_inopblock <= XFS_INODES_PER_CHUNK) {
xic->deleted = true;
xic->first_ino = XFS_AGINO_TO_INO(mp, pag->pag_agno,
rec.ir_startino);
xic->first_ino = xfs_agino_to_ino(pag, rec.ir_startino);
xic->alloc = xfs_inobt_irec_to_allocmask(&rec);
/*
@ -2148,7 +2165,7 @@ xfs_difree_inobt(
goto error0;
}
error = xfs_difree_inode_chunk(tp, pag->pag_agno, &rec);
error = xfs_difree_inode_chunk(tp, pag, &rec);
if (error)
goto error0;
} else {
@ -2194,7 +2211,7 @@ xfs_difree_finobt(
xfs_agino_t agino,
struct xfs_inobt_rec_incore *ibtrec) /* inobt record */
{
struct xfs_mount *mp = pag->pag_mount;
struct xfs_mount *mp = pag_mount(pag);
struct xfs_btree_cur *cur;
struct xfs_inobt_rec_incore rec;
int offset = agino - ibtrec->ir_startino;
@ -2317,17 +2334,17 @@ xfs_difree(
/*
* Break up inode number into its components.
*/
if (pag->pag_agno != XFS_INO_TO_AGNO(mp, inode)) {
xfs_warn(mp, "%s: agno != pag->pag_agno (%d != %d).",
__func__, XFS_INO_TO_AGNO(mp, inode), pag->pag_agno);
if (pag_agno(pag) != XFS_INO_TO_AGNO(mp, inode)) {
xfs_warn(mp, "%s: agno != pag_agno(pag) (%d != %d).",
__func__, XFS_INO_TO_AGNO(mp, inode), pag_agno(pag));
ASSERT(0);
return -EINVAL;
}
agino = XFS_INO_TO_AGINO(mp, inode);
if (inode != XFS_AGINO_TO_INO(mp, pag->pag_agno, agino)) {
xfs_warn(mp, "%s: inode != XFS_AGINO_TO_INO() (%llu != %llu).",
if (inode != xfs_agino_to_ino(pag, agino)) {
xfs_warn(mp, "%s: inode != xfs_agino_to_ino() (%llu != %llu).",
__func__, (unsigned long long)inode,
(unsigned long long)XFS_AGINO_TO_INO(mp, pag->pag_agno, agino));
(unsigned long long)xfs_agino_to_ino(pag, agino));
ASSERT(0);
return -EINVAL;
}
@ -2380,7 +2397,7 @@ xfs_imap_lookup(
xfs_agblock_t *offset_agbno,
int flags)
{
struct xfs_mount *mp = pag->pag_mount;
struct xfs_mount *mp = pag_mount(pag);
struct xfs_inobt_rec_incore rec;
struct xfs_btree_cur *cur;
struct xfs_buf *agbp;
@ -2391,7 +2408,7 @@ xfs_imap_lookup(
if (error) {
xfs_alert(mp,
"%s: xfs_ialloc_read_agi() returned error %d, agno %d",
__func__, error, pag->pag_agno);
__func__, error, pag_agno(pag));
return error;
}
@ -2441,7 +2458,7 @@ xfs_imap(
struct xfs_imap *imap, /* location map structure */
uint flags) /* flags for inode btree lookup */
{
struct xfs_mount *mp = pag->pag_mount;
struct xfs_mount *mp = pag_mount(pag);
xfs_agblock_t agbno; /* block number of inode in the alloc group */
xfs_agino_t agino; /* inode number within alloc group */
xfs_agblock_t chunk_agbno; /* first block in inode chunk */
@ -2458,7 +2475,7 @@ xfs_imap(
agino = XFS_INO_TO_AGINO(mp, ino);
agbno = XFS_AGINO_TO_AGBNO(mp, agino);
if (agbno >= mp->m_sb.sb_agblocks ||
ino != XFS_AGINO_TO_INO(mp, pag->pag_agno, agino)) {
ino != xfs_agino_to_ino(pag, agino)) {
error = -EINVAL;
#ifdef DEBUG
/*
@ -2473,11 +2490,11 @@ xfs_imap(
__func__, (unsigned long long)agbno,
(unsigned long)mp->m_sb.sb_agblocks);
}
if (ino != XFS_AGINO_TO_INO(mp, pag->pag_agno, agino)) {
if (ino != xfs_agino_to_ino(pag, agino)) {
xfs_alert(mp,
"%s: ino (0x%llx) != XFS_AGINO_TO_INO() (0x%llx)",
"%s: ino (0x%llx) != xfs_agino_to_ino() (0x%llx)",
__func__, ino,
XFS_AGINO_TO_INO(mp, pag->pag_agno, agino));
xfs_agino_to_ino(pag, agino));
}
xfs_stack_trace();
#endif /* DEBUG */
@ -2507,7 +2524,7 @@ xfs_imap(
offset = XFS_INO_TO_OFFSET(mp, ino);
ASSERT(offset < mp->m_sb.sb_inopblock);
imap->im_blkno = XFS_AGB_TO_DADDR(mp, pag->pag_agno, agbno);
imap->im_blkno = xfs_agbno_to_daddr(pag, agbno);
imap->im_len = XFS_FSB_TO_BB(mp, 1);
imap->im_boffset = (unsigned short)(offset <<
mp->m_sb.sb_inodelog);
@ -2537,7 +2554,7 @@ xfs_imap(
offset = ((agbno - cluster_agbno) * mp->m_sb.sb_inopblock) +
XFS_INO_TO_OFFSET(mp, ino);
imap->im_blkno = XFS_AGB_TO_DADDR(mp, pag->pag_agno, cluster_agbno);
imap->im_blkno = xfs_agbno_to_daddr(pag, cluster_agbno);
imap->im_len = XFS_FSB_TO_BB(mp, M_IGEO(mp)->blocks_per_cluster);
imap->im_boffset = (unsigned short)(offset << mp->m_sb.sb_inodelog);
@ -2733,13 +2750,13 @@ xfs_read_agi(
xfs_buf_flags_t flags,
struct xfs_buf **agibpp)
{
struct xfs_mount *mp = pag->pag_mount;
struct xfs_mount *mp = pag_mount(pag);
int error;
trace_xfs_read_agi(pag->pag_mount, pag->pag_agno);
trace_xfs_read_agi(pag);
error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGI_DADDR(mp)),
XFS_AG_DADDR(mp, pag_agno(pag), XFS_AGI_DADDR(mp)),
XFS_FSS_TO_BB(mp, 1), flags, agibpp, &xfs_agi_buf_ops);
if (xfs_metadata_is_sick(error))
xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
@ -2767,7 +2784,7 @@ xfs_ialloc_read_agi(
struct xfs_agi *agi;
int error;
trace_xfs_ialloc_read_agi(pag->pag_mount, pag->pag_agno);
trace_xfs_ialloc_read_agi(pag);
error = xfs_read_agi(pag, tp,
(flags & XFS_IALLOC_FLAG_TRYLOCK) ? XBF_TRYLOCK : 0,
@ -2787,7 +2804,7 @@ xfs_ialloc_read_agi(
* we are in the middle of a forced shutdown.
*/
ASSERT(pag->pagi_freecount == be32_to_cpu(agi->agi_freecount) ||
xfs_is_shutdown(pag->pag_mount));
xfs_is_shutdown(pag_mount(pag)));
if (agibpp)
*agibpp = agibp;
else
@ -2887,7 +2904,7 @@ xfs_ialloc_count_inodes_rec(
xfs_failaddr_t fa;
xfs_inobt_btrec_to_irec(cur->bc_mp, rec, &irec);
fa = xfs_inobt_check_irec(cur->bc_ag.pag, &irec);
fa = xfs_inobt_check_irec(to_perag(cur->bc_group), &irec);
if (fa)
return xfs_inobt_complain_bad_rec(cur, fa, &irec);
@ -3126,13 +3143,13 @@ xfs_ialloc_check_shrink(
int has;
int error;
if (!xfs_has_sparseinodes(pag->pag_mount))
if (!xfs_has_sparseinodes(pag_mount(pag)))
return 0;
cur = xfs_inobt_init_cursor(pag, tp, agibp);
/* Look up the inobt record that would correspond to the new EOFS. */
agino = XFS_AGB_TO_AGINO(pag->pag_mount, new_length);
agino = XFS_AGB_TO_AGINO(pag_mount(pag), new_length);
error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &has);
if (error || !has)
goto out;

31
fs/xfs/libxfs/xfs_ialloc_btree.c
View File

@ -37,7 +37,7 @@ STATIC struct xfs_btree_cur *
xfs_inobt_dup_cursor(
struct xfs_btree_cur *cur)
{
return xfs_inobt_init_cursor(cur->bc_ag.pag, cur->bc_tp,
return xfs_inobt_init_cursor(to_perag(cur->bc_group), cur->bc_tp,
cur->bc_ag.agbp);
}
@ -45,7 +45,7 @@ STATIC struct xfs_btree_cur *
xfs_finobt_dup_cursor(
struct xfs_btree_cur *cur)
{
return xfs_finobt_init_cursor(cur->bc_ag.pag, cur->bc_tp,
return xfs_finobt_init_cursor(to_perag(cur->bc_group), cur->bc_tp,
cur->bc_ag.agbp);
}
@ -112,7 +112,7 @@ __xfs_inobt_alloc_block(
memset(&args, 0, sizeof(args));
args.tp = cur->bc_tp;
args.mp = cur->bc_mp;
args.pag = cur->bc_ag.pag;
args.pag = to_perag(cur->bc_group);
args.oinfo = XFS_RMAP_OINFO_INOBT;
args.minlen = 1;
args.maxlen = 1;
@ -120,7 +120,7 @@ __xfs_inobt_alloc_block(
args.resv = resv;
error = xfs_alloc_vextent_near_bno(&args,
XFS_AGB_TO_FSB(args.mp, args.pag->pag_agno, sbno));
xfs_agbno_to_fsb(args.pag, sbno));
if (error)
return error;
@ -248,7 +248,7 @@ xfs_inobt_init_ptr_from_cur(
{
struct xfs_agi *agi = cur->bc_ag.agbp->b_addr;
ASSERT(cur->bc_ag.pag->pag_agno == be32_to_cpu(agi->agi_seqno));
ASSERT(cur->bc_group->xg_gno == be32_to_cpu(agi->agi_seqno));
ptr->s = agi->agi_root;
}
@ -260,7 +260,8 @@ xfs_finobt_init_ptr_from_cur(
{
struct xfs_agi *agi = cur->bc_ag.agbp->b_addr;
ASSERT(cur->bc_ag.pag->pag_agno == be32_to_cpu(agi->agi_seqno));
ASSERT(cur->bc_group->xg_gno == be32_to_cpu(agi->agi_seqno));
ptr->s = agi->agi_free_root;
}
@ -478,12 +479,12 @@ xfs_inobt_init_cursor(
struct xfs_trans *tp,
struct xfs_buf *agbp)
{
struct xfs_mount *mp = pag->pag_mount;
struct xfs_mount *mp = pag_mount(pag);
struct xfs_btree_cur *cur;
cur = xfs_btree_alloc_cursor(mp, tp, &xfs_inobt_ops,
M_IGEO(mp)->inobt_maxlevels, xfs_inobt_cur_cache);
cur->bc_ag.pag = xfs_perag_hold(pag);
cur->bc_group = xfs_group_hold(pag_group(pag));
cur->bc_ag.agbp = agbp;
if (agbp) {
struct xfs_agi *agi = agbp->b_addr;
@ -504,12 +505,12 @@ xfs_finobt_init_cursor(
struct xfs_trans *tp,
struct xfs_buf *agbp)
{
struct xfs_mount *mp = pag->pag_mount;
struct xfs_mount *mp = pag_mount(pag);
struct xfs_btree_cur *cur;
cur = xfs_btree_alloc_cursor(mp, tp, &xfs_finobt_ops,
M_IGEO(mp)->inobt_maxlevels, xfs_inobt_cur_cache);
cur->bc_ag.pag = xfs_perag_hold(pag);
cur->bc_group = xfs_group_hold(pag_group(pag));
cur->bc_ag.agbp = agbp;
if (agbp) {
struct xfs_agi *agi = agbp->b_addr;
@ -715,8 +716,8 @@ static xfs_extlen_t
xfs_inobt_max_size(
struct xfs_perag *pag)
{
struct xfs_mount *mp = pag->pag_mount;
xfs_agblock_t agblocks = pag->block_count;
struct xfs_mount *mp = pag_mount(pag);
xfs_agblock_t agblocks = pag_group(pag)->xg_block_count;
/* Bail out if we're uninitialized, which can happen in mkfs. */
if (M_IGEO(mp)->inobt_mxr[0] == 0)
@ -727,7 +728,7 @@ xfs_inobt_max_size(
* never be available for the kinds of things that would require btree
* expansion. We therefore can pretend the space isn't there.
*/
if (xfs_ag_contains_log(mp, pag->pag_agno))
if (xfs_ag_contains_log(mp, pag_agno(pag)))
agblocks -= mp->m_sb.sb_logblocks;
return xfs_btree_calc_size(M_IGEO(mp)->inobt_mnr,
@ -791,10 +792,10 @@ xfs_finobt_calc_reserves(
xfs_extlen_t tree_len = 0;
int error;
if (!xfs_has_finobt(pag->pag_mount))
if (!xfs_has_finobt(pag_mount(pag)))
return 0;
if (xfs_has_inobtcounts(pag->pag_mount))
if (xfs_has_inobtcounts(pag_mount(pag)))
error = xfs_finobt_read_blocks(pag, tp, &tree_len);
else
error = xfs_finobt_count_blocks(pag, tp, &tree_len);

90
fs/xfs/libxfs/xfs_inode_buf.c
View File

@ -19,6 +19,7 @@
#include "xfs_ialloc.h"
#include "xfs_dir2.h"
#include "xfs_health.h"
#include "xfs_metafile.h"
#include <linux/iversion.h>
@ -209,12 +210,15 @@ xfs_inode_from_disk(
* They will also be unconditionally written back to disk as v2 inodes.
*/
if (unlikely(from->di_version == 1)) {
set_nlink(inode, be16_to_cpu(from->di_onlink));
/* di_metatype used to be di_onlink */
set_nlink(inode, be16_to_cpu(from->di_metatype));
ip->i_projid = 0;
} else {
set_nlink(inode, be32_to_cpu(from->di_nlink));
ip->i_projid = (prid_t)be16_to_cpu(from->di_projid_hi) << 16 |
be16_to_cpu(from->di_projid_lo);
if (xfs_dinode_is_metadir(from))
ip->i_metatype = be16_to_cpu(from->di_metatype);
}
i_uid_write(inode, be32_to_cpu(from->di_uid));
@ -315,7 +319,10 @@ xfs_inode_to_disk(
struct inode *inode = VFS_I(ip);
to->di_magic = cpu_to_be16(XFS_DINODE_MAGIC);
to->di_onlink = 0;
if (xfs_is_metadir_inode(ip))
to->di_metatype = cpu_to_be16(ip->i_metatype);
else
to->di_metatype = 0;
to->di_format = xfs_ifork_format(&ip->i_df);
to->di_uid = cpu_to_be32(i_uid_read(inode));
@ -483,6 +490,69 @@ xfs_dinode_verify_nrext64(
return NULL;
}
/*
* Validate all the picky requirements we have for a file that claims to be
* filesystem metadata.
*/
xfs_failaddr_t
xfs_dinode_verify_metadir(
struct xfs_mount *mp,
struct xfs_dinode *dip,
uint16_t mode,
uint16_t flags,
uint64_t flags2)
{
if (!xfs_has_metadir(mp))
return __this_address;
/* V5 filesystem only */
if (dip->di_version < 3)
return __this_address;
if (be16_to_cpu(dip->di_metatype) >= XFS_METAFILE_MAX)
return __this_address;
/* V3 inode fields that are always zero */
if ((flags2 & XFS_DIFLAG2_NREXT64) && dip->di_nrext64_pad)
return __this_address;
if (!(flags2 & XFS_DIFLAG2_NREXT64) && dip->di_flushiter)
return __this_address;
/* Metadata files can only be directories or regular files */
if (!S_ISDIR(mode) && !S_ISREG(mode))
return __this_address;
/* They must have zero access permissions */
if (mode & 0777)
return __this_address;
/* DMAPI event and state masks are zero */
if (dip->di_dmevmask || dip->di_dmstate)
return __this_address;
/*
* User and group IDs must be zero. The project ID is used for
* grouping inodes. Metadata inodes are never accounted to quotas.
*/
if (dip->di_uid || dip->di_gid)
return __this_address;
/* Mandatory inode flags must be set */
if (S_ISDIR(mode)) {
if ((flags & XFS_METADIR_DIFLAGS) != XFS_METADIR_DIFLAGS)
return __this_address;
} else {
if ((flags & XFS_METAFILE_DIFLAGS) != XFS_METAFILE_DIFLAGS)
return __this_address;
}
/* dax flags2 must not be set */
if (flags2 & XFS_DIFLAG2_DAX)
return __this_address;
return NULL;
}
xfs_failaddr_t
xfs_dinode_verify(
struct xfs_mount *mp,
@ -523,8 +593,11 @@ xfs_dinode_verify(
* di_nlink==0 on a V1 inode. V2/3 inodes would get written out with
* di_onlink==0, so we can check that.
*/
if (dip->di_version >= 2) {
if (dip->di_onlink)
if (dip->di_version == 2) {
if (dip->di_metatype)
return __this_address;
} else if (dip->di_version >= 3) {
if (!xfs_dinode_is_metadir(dip) && dip->di_metatype)
return __this_address;
}
@ -546,7 +619,8 @@ xfs_dinode_verify(
if (dip->di_nlink)
return __this_address;
} else {
if (dip->di_onlink)
/* di_metatype used to be di_onlink */
if (dip->di_metatype)
return __this_address;
}
}
@ -663,6 +737,12 @@ xfs_dinode_verify(
!xfs_has_bigtime(mp))
return __this_address;
if (flags2 & XFS_DIFLAG2_METADATA) {
fa = xfs_dinode_verify_metadir(mp, dip, mode, flags, flags2);
if (fa)
return fa;
}
return NULL;
}

3
fs/xfs/libxfs/xfs_inode_buf.h
View File

@ -28,6 +28,9 @@ int xfs_inode_from_disk(struct xfs_inode *ip, struct xfs_dinode *from);
xfs_failaddr_t xfs_dinode_verify(struct xfs_mount *mp, xfs_ino_t ino,
struct xfs_dinode *dip);
xfs_failaddr_t xfs_dinode_verify_metadir(struct xfs_mount *mp,
struct xfs_dinode *dip, uint16_t mode, uint16_t flags,
uint64_t flags2);
xfs_failaddr_t xfs_inode_validate_extsize(struct xfs_mount *mp,
uint32_t extsize, uint16_t mode, uint16_t flags);
xfs_failaddr_t xfs_inode_validate_cowextsize(struct xfs_mount *mp,

6
fs/xfs/libxfs/xfs_inode_util.c
View File

@ -224,6 +224,8 @@ xfs_inode_inherit_flags2(
}
if (pip->i_diflags2 & XFS_DIFLAG2_DAX)
ip->i_diflags2 |= XFS_DIFLAG2_DAX;
if (xfs_is_metadir_inode(pip))
ip->i_diflags2 |= XFS_DIFLAG2_METADATA;
/* Don't let invalid cowextsize hints propagate. */
failaddr = xfs_inode_validate_cowextsize(ip->i_mount, ip->i_cowextsize,
@ -442,8 +444,8 @@ xfs_iunlink_update_bucket(
ASSERT(xfs_verify_agino_or_null(pag, new_agino));
old_value = be32_to_cpu(agi->agi_unlinked[bucket_index]);
trace_xfs_iunlink_update_bucket(tp->t_mountp, pag->pag_agno, bucket_index,
old_value, new_agino);
trace_xfs_iunlink_update_bucket(pag, bucket_index, old_value,
new_agino);
/*
* We should never find the head of the list already set to the value

8
fs/xfs/libxfs/xfs_log_format.h
View File

@ -248,6 +248,8 @@ typedef struct xfs_trans_header {
#define XFS_LI_ATTRD 0x1247 /* attr set/remove done */
#define XFS_LI_XMI 0x1248 /* mapping exchange intent */
#define XFS_LI_XMD 0x1249 /* mapping exchange done */
#define XFS_LI_EFI_RT 0x124a /* realtime extent free intent */
#define XFS_LI_EFD_RT 0x124b /* realtime extent free done */
#define XFS_LI_TYPE_DESC \
{ XFS_LI_EFI, "XFS_LI_EFI" }, \
@ -267,7 +269,9 @@ typedef struct xfs_trans_header {
{ XFS_LI_ATTRI, "XFS_LI_ATTRI" }, \
{ XFS_LI_ATTRD, "XFS_LI_ATTRD" }, \
{ XFS_LI_XMI, "XFS_LI_XMI" }, \
{ XFS_LI_XMD, "XFS_LI_XMD" }
{ XFS_LI_XMD, "XFS_LI_XMD" }, \
{ XFS_LI_EFI_RT, "XFS_LI_EFI_RT" }, \
{ XFS_LI_EFD_RT, "XFS_LI_EFD_RT" }
/*
* Inode Log Item Format definitions.
@ -404,7 +408,7 @@ struct xfs_log_dinode {
uint16_t di_mode; /* mode and type of file */
int8_t di_version; /* inode version */
int8_t di_format; /* format of di_c data */
uint8_t di_pad3[2]; /* unused in v2/3 inodes */
uint16_t di_metatype; /* metadata type, if DIFLAG2_METADATA */
uint32_t di_uid; /* owner's user id */
uint32_t di_gid; /* owner's group id */
uint32_t di_nlink; /* number of links to file */

2
fs/xfs/libxfs/xfs_log_recover.h
View File

@ -77,6 +77,8 @@ extern const struct xlog_recover_item_ops xlog_attri_item_ops;
extern const struct xlog_recover_item_ops xlog_attrd_item_ops;
extern const struct xlog_recover_item_ops xlog_xmi_item_ops;
extern const struct xlog_recover_item_ops xlog_xmd_item_ops;
extern const struct xlog_recover_item_ops xlog_rtefi_item_ops;
extern const struct xlog_recover_item_ops xlog_rtefd_item_ops;
/*
* Macros, structures, prototypes for internal log manager use.

481
fs/xfs/libxfs/xfs_metadir.c Normal file
View File

@ -0,0 +1,481 @@
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Copyright (c) 2018-2024 Oracle. All Rights Reserved.
* Author: Darrick J. Wong <djwong@kernel.org>
*/
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_bit.h"
#include "xfs_sb.h"
#include "xfs_mount.h"
#include "xfs_defer.h"
#include "xfs_trans.h"
#include "xfs_metafile.h"
#include "xfs_metadir.h"
#include "xfs_trace.h"
#include "xfs_inode.h"
#include "xfs_quota.h"
#include "xfs_ialloc.h"
#include "xfs_bmap_btree.h"
#include "xfs_da_format.h"
#include "xfs_da_btree.h"
#include "xfs_trans_space.h"
#include "xfs_ag.h"
#include "xfs_dir2.h"
#include "xfs_dir2_priv.h"
#include "xfs_parent.h"
#include "xfs_health.h"
/*
* Metadata Directory Tree
* =======================
*
* These functions provide an abstraction layer for looking up, creating, and
* deleting metadata inodes that live within a special metadata directory tree.
*
* This code does not manage the five existing metadata inodes: real time
* bitmap & summary; and the user, group, and quotas. All other metadata
* inodes must use only the xfs_meta{dir,file}_* functions.
*
* Callers wishing to create or hardlink a metadata inode must create an
* xfs_metadir_update structure, call the appropriate xfs_metadir* function,
* and then call xfs_metadir_commit or xfs_metadir_cancel to commit or cancel
* the update. Files in the metadata directory tree currently cannot be
* unlinked.
*
* When the metadir feature is enabled, all metadata inodes must have the
* "metadata" inode flag set to prevent them from being exposed to the outside
* world.
*
* Callers must take the ILOCK of any inode in the metadata directory tree to
* synchronize access to that inode. It is never necessary to take the IOLOCK
* or the MMAPLOCK since metadata inodes must not be exposed to user space.
*/
static inline void
xfs_metadir_set_xname(
struct xfs_name *xname,
const char *path,
unsigned char ftype)
{
xname->name = (const unsigned char *)path;
xname->len = strlen(path);
xname->type = ftype;
}
/*
* Given a parent directory @dp and a metadata inode path component @xname,
* Look up the inode number in the directory, returning it in @ino.
* @xname.type must match the directory entry's ftype.
*
* Caller must hold ILOCK_EXCL.
*/
static inline int
xfs_metadir_lookup(
struct xfs_trans *tp,
struct xfs_inode *dp,
struct xfs_name *xname,
xfs_ino_t *ino)
{
struct xfs_mount *mp = dp->i_mount;
struct xfs_da_args args = {
.trans = tp,
.dp = dp,
.geo = mp->m_dir_geo,
.name = xname->name,
.namelen = xname->len,
.hashval = xfs_dir2_hashname(mp, xname),
.whichfork = XFS_DATA_FORK,
.op_flags = XFS_DA_OP_OKNOENT,
.owner = dp->i_ino,
};
int error;
if (!S_ISDIR(VFS_I(dp)->i_mode)) {
xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR);
return -EFSCORRUPTED;
}
if (xfs_is_shutdown(mp))
return -EIO;
error = xfs_dir_lookup_args(&args);
if (error)
return error;
if (!xfs_verify_ino(mp, args.inumber)) {
xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR);
return -EFSCORRUPTED;
}
if (xname->type != XFS_DIR3_FT_UNKNOWN && xname->type != args.filetype) {
xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR);
return -EFSCORRUPTED;
}
trace_xfs_metadir_lookup(dp, xname, args.inumber);
*ino = args.inumber;
return 0;
}
/*
* Look up and read a metadata inode from the metadata directory. If the path
* component doesn't exist, return -ENOENT.
*/
int
xfs_metadir_load(
struct xfs_trans *tp,
struct xfs_inode *dp,
const char *path,
enum xfs_metafile_type metafile_type,
struct xfs_inode **ipp)
{
struct xfs_name xname;
xfs_ino_t ino;
int error;
xfs_metadir_set_xname(&xname, path, XFS_DIR3_FT_UNKNOWN);
xfs_ilock(dp, XFS_ILOCK_EXCL);
error = xfs_metadir_lookup(tp, dp, &xname, &ino);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
if (error)
return error;
return xfs_trans_metafile_iget(tp, ino, metafile_type, ipp);
}
/*
* Unlock and release resources after committing (or cancelling) a metadata
* directory tree operation. The caller retains its reference to @upd->ip
* and must release it explicitly.
*/
static inline void
xfs_metadir_teardown(
struct xfs_metadir_update *upd,
int error)
{
trace_xfs_metadir_teardown(upd, error);
if (upd->ppargs) {
xfs_parent_finish(upd->dp->i_mount, upd->ppargs);
upd->ppargs = NULL;
}
if (upd->ip) {
if (upd->ip_locked)
xfs_iunlock(upd->ip, XFS_ILOCK_EXCL);
upd->ip_locked = false;
}
if (upd->dp_locked)
xfs_iunlock(upd->dp, XFS_ILOCK_EXCL);
upd->dp_locked = false;
}
/*
* Begin the process of creating a metadata file by allocating transactions
* and taking whatever resources we're going to need.
*/
int
xfs_metadir_start_create(
struct xfs_metadir_update *upd)
{
struct xfs_mount *mp = upd->dp->i_mount;
int error;
ASSERT(upd->dp != NULL);
ASSERT(upd->ip == NULL);
ASSERT(xfs_has_metadir(mp));
ASSERT(upd->metafile_type != XFS_METAFILE_UNKNOWN);
error = xfs_parent_start(mp, &upd->ppargs);
if (error)
return error;
/*
* If we ever need the ability to create rt metadata files on a
* pre-metadir filesystem, we'll need to dqattach the parent here.
* Currently we assume that mkfs will create the files and quotacheck
* will account for them.
*/
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_create,
xfs_create_space_res(mp, MAXNAMELEN), 0, 0, &upd->tp);
if (error)
goto out_teardown;
/*
* Lock the parent directory if there is one. We can't ijoin it to
* the transaction until after the child file has been created.
*/
xfs_ilock(upd->dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
upd->dp_locked = true;
trace_xfs_metadir_start_create(upd);
return 0;
out_teardown:
xfs_metadir_teardown(upd, error);
return error;
}
/*
* Create a metadata inode with the given @mode, and insert it into the
* metadata directory tree at the given @upd->path. The path up to the final
* component must already exist. The final path component must not exist.
*
* The new metadata inode will be attached to the update structure @upd->ip,
* with the ILOCK held until the caller releases it.
*
* NOTE: This function may return a new inode to the caller even if it returns
* a negative error code. If an inode is passed back, the caller must finish
* setting up the inode before releasing it.
*/
int
xfs_metadir_create(
struct xfs_metadir_update *upd,
umode_t mode)
{
struct xfs_icreate_args args = {
.pip = upd->dp,
.mode = mode,
};
struct xfs_name xname;
struct xfs_dir_update du = {
.dp = upd->dp,
.name = &xname,
.ppargs = upd->ppargs,
};
struct xfs_mount *mp = upd->dp->i_mount;
xfs_ino_t ino;
unsigned int resblks;
int error;
xfs_assert_ilocked(upd->dp, XFS_ILOCK_EXCL);
/* Check that the name does not already exist in the directory. */
xfs_metadir_set_xname(&xname, upd->path, XFS_DIR3_FT_UNKNOWN);
error = xfs_metadir_lookup(upd->tp, upd->dp, &xname, &ino);
switch (error) {
case -ENOENT:
break;
case 0:
error = -EEXIST;
fallthrough;
default:
return error;
}
/*
* A newly created regular or special file just has one directory
* entry pointing to them, but a directory also the "." entry
* pointing to itself.
*/
error = xfs_dialloc(&upd->tp, &args, &ino);
if (error)
return error;
error = xfs_icreate(upd->tp, ino, &args, &upd->ip);
if (error)
return error;
du.ip = upd->ip;
xfs_metafile_set_iflag(upd->tp, upd->ip, upd->metafile_type);
upd->ip_locked = true;
/*
* Join the directory inode to the transaction. We do not do it
* earlier because xfs_dialloc rolls the transaction.
*/
xfs_trans_ijoin(upd->tp, upd->dp, 0);
/* Create the entry. */
if (S_ISDIR(args.mode))
resblks = xfs_mkdir_space_res(mp, xname.len);
else
resblks = xfs_create_space_res(mp, xname.len);
xname.type = xfs_mode_to_ftype(args.mode);
trace_xfs_metadir_try_create(upd);
error = xfs_dir_create_child(upd->tp, resblks, &du);
if (error)
return error;
/* Metadir files are not accounted to quota. */
trace_xfs_metadir_create(upd);
return 0;
}
#ifndef __KERNEL__
/*
* Begin the process of linking a metadata file by allocating transactions
* and locking whatever resources we're going to need.
*/
int
xfs_metadir_start_link(
struct xfs_metadir_update *upd)
{
struct xfs_mount *mp = upd->dp->i_mount;
unsigned int resblks;
int nospace_error = 0;
int error;
ASSERT(upd->dp != NULL);
ASSERT(upd->ip != NULL);
ASSERT(xfs_has_metadir(mp));
error = xfs_parent_start(mp, &upd->ppargs);
if (error)
return error;
resblks = xfs_link_space_res(mp, MAXNAMELEN);
error = xfs_trans_alloc_dir(upd->dp, &M_RES(mp)->tr_link, upd->ip,
&resblks, &upd->tp, &nospace_error);
if (error)
goto out_teardown;
if (!resblks) {
/* We don't allow reservationless updates. */
xfs_trans_cancel(upd->tp);
upd->tp = NULL;
xfs_iunlock(upd->dp, XFS_ILOCK_EXCL);
xfs_iunlock(upd->ip, XFS_ILOCK_EXCL);
error = nospace_error;
goto out_teardown;
}
upd->dp_locked = true;
upd->ip_locked = true;
trace_xfs_metadir_start_link(upd);
return 0;
out_teardown:
xfs_metadir_teardown(upd, error);
return error;
}
/*
* Link the metadata directory given by @path to the inode @upd->ip.
* The path (up to the final component) must already exist, but the final
* component must not already exist.
*/
int
xfs_metadir_link(
struct xfs_metadir_update *upd)
{
struct xfs_name xname;
struct xfs_dir_update du = {
.dp = upd->dp,
.name = &xname,
.ip = upd->ip,
.ppargs = upd->ppargs,
};
struct xfs_mount *mp = upd->dp->i_mount;
xfs_ino_t ino;
unsigned int resblks;
int error;
xfs_assert_ilocked(upd->dp, XFS_ILOCK_EXCL);
xfs_assert_ilocked(upd->ip, XFS_ILOCK_EXCL);
/* Look up the name in the current directory. */
xfs_metadir_set_xname(&xname, upd->path,
xfs_mode_to_ftype(VFS_I(upd->ip)->i_mode));
error = xfs_metadir_lookup(upd->tp, upd->dp, &xname, &ino);
switch (error) {
case -ENOENT:
break;
case 0:
error = -EEXIST;
fallthrough;
default:
return error;
}
resblks = xfs_link_space_res(mp, xname.len);
error = xfs_dir_add_child(upd->tp, resblks, &du);
if (error)
return error;
trace_xfs_metadir_link(upd);
return 0;
}
#endif /* ! __KERNEL__ */
/* Commit a metadir update and unlock/drop all resources. */
int
xfs_metadir_commit(
struct xfs_metadir_update *upd)
{
int error;
trace_xfs_metadir_commit(upd);
error = xfs_trans_commit(upd->tp);
upd->tp = NULL;
xfs_metadir_teardown(upd, error);
return error;
}
/* Cancel a metadir update and unlock/drop all resources. */
void
xfs_metadir_cancel(
struct xfs_metadir_update *upd,
int error)
{
trace_xfs_metadir_cancel(upd);
xfs_trans_cancel(upd->tp);
upd->tp = NULL;
xfs_metadir_teardown(upd, error);
}
/* Create a metadata for the last component of the path. */
int
xfs_metadir_mkdir(
struct xfs_inode *dp,
const char *path,
struct xfs_inode **ipp)
{
struct xfs_metadir_update upd = {
.dp = dp,
.path = path,
.metafile_type = XFS_METAFILE_DIR,
};
int error;
if (xfs_is_shutdown(dp->i_mount))
return -EIO;
/* Allocate a transaction to create the last directory. */
error = xfs_metadir_start_create(&upd);
if (error)
return error;
/* Create the subdirectory and take our reference. */
error = xfs_metadir_create(&upd, S_IFDIR);
if (error)
goto out_cancel;
error = xfs_metadir_commit(&upd);
if (error)
goto out_irele;
xfs_finish_inode_setup(upd.ip);
*ipp = upd.ip;
return 0;
out_cancel:
xfs_metadir_cancel(&upd, error);
out_irele:
/* Have to finish setting up the inode to ensure it's deleted. */
if (upd.ip) {
xfs_finish_inode_setup(upd.ip);
xfs_irele(upd.ip);
}
return error;
}

47
fs/xfs/libxfs/xfs_metadir.h Normal file
View File

@ -0,0 +1,47 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* Copyright (c) 2018-2024 Oracle. All Rights Reserved.
* Author: Darrick J. Wong <djwong@kernel.org>
*/
#ifndef __XFS_METADIR_H__
#define __XFS_METADIR_H__
/* Cleanup widget for metadata inode creation and deletion. */
struct xfs_metadir_update {
/* Parent directory */
struct xfs_inode *dp;
/* Path to metadata file */
const char *path;
/* Parent pointer update context */
struct xfs_parent_args *ppargs;
/* Child metadata file */
struct xfs_inode *ip;
struct xfs_trans *tp;
enum xfs_metafile_type metafile_type;
unsigned int dp_locked:1;
unsigned int ip_locked:1;
};
int xfs_metadir_load(struct xfs_trans *tp, struct xfs_inode *dp,
const char *path, enum xfs_metafile_type metafile_type,
struct xfs_inode **ipp);
int xfs_metadir_start_create(struct xfs_metadir_update *upd);
int xfs_metadir_create(struct xfs_metadir_update *upd, umode_t mode);
int xfs_metadir_start_link(struct xfs_metadir_update *upd);
int xfs_metadir_link(struct xfs_metadir_update *upd);
int xfs_metadir_commit(struct xfs_metadir_update *upd);
void xfs_metadir_cancel(struct xfs_metadir_update *upd, int error);
int xfs_metadir_mkdir(struct xfs_inode *dp, const char *path,
struct xfs_inode **ipp);
#endif /* __XFS_METADIR_H__ */

52
fs/xfs/libxfs/xfs_metafile.c Normal file
View File

@ -0,0 +1,52 @@
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Copyright (c) 2018-2024 Oracle. All Rights Reserved.
* Author: Darrick J. Wong <djwong@kernel.org>
*/
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_bit.h"
#include "xfs_sb.h"
#include "xfs_mount.h"
#include "xfs_defer.h"
#include "xfs_trans.h"
#include "xfs_metafile.h"
#include "xfs_trace.h"
#include "xfs_inode.h"
/* Set up an inode to be recognized as a metadata directory inode. */
void
xfs_metafile_set_iflag(
struct xfs_trans *tp,
struct xfs_inode *ip,
enum xfs_metafile_type metafile_type)
{
VFS_I(ip)->i_mode &= ~0777;
VFS_I(ip)->i_uid = GLOBAL_ROOT_UID;
VFS_I(ip)->i_gid = GLOBAL_ROOT_GID;
if (S_ISDIR(VFS_I(ip)->i_mode))
ip->i_diflags |= XFS_METADIR_DIFLAGS;
else
ip->i_diflags |= XFS_METAFILE_DIFLAGS;
ip->i_diflags2 &= ~XFS_DIFLAG2_DAX;
ip->i_diflags2 |= XFS_DIFLAG2_METADATA;
ip->i_metatype = metafile_type;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
}
/* Clear the metadata directory inode flag. */
void
xfs_metafile_clear_iflag(
struct xfs_trans *tp,
struct xfs_inode *ip)
{
ASSERT(xfs_is_metadir_inode(ip));
ASSERT(VFS_I(ip)->i_nlink == 0);
ip->i_diflags2 &= ~XFS_DIFLAG2_METADATA;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
}

31
fs/xfs/libxfs/xfs_metafile.h Normal file
View File

@ -0,0 +1,31 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* Copyright (c) 2018-2024 Oracle. All Rights Reserved.
* Author: Darrick J. Wong <djwong@kernel.org>
*/
#ifndef __XFS_METAFILE_H__
#define __XFS_METAFILE_H__
/* All metadata files must have these flags set. */
#define XFS_METAFILE_DIFLAGS (XFS_DIFLAG_IMMUTABLE | \
XFS_DIFLAG_SYNC | \
XFS_DIFLAG_NOATIME | \
XFS_DIFLAG_NODUMP | \
XFS_DIFLAG_NODEFRAG)
/* All metadata directories must have these flags set. */
#define XFS_METADIR_DIFLAGS (XFS_METAFILE_DIFLAGS | \
XFS_DIFLAG_NOSYMLINKS)
void xfs_metafile_set_iflag(struct xfs_trans *tp, struct xfs_inode *ip,
enum xfs_metafile_type metafile_type);
void xfs_metafile_clear_iflag(struct xfs_trans *tp, struct xfs_inode *ip);
/* Code specific to kernel/userspace; must be provided externally. */
int xfs_trans_metafile_iget(struct xfs_trans *tp, xfs_ino_t ino,
enum xfs_metafile_type metafile_type, struct xfs_inode **ipp);
int xfs_metafile_iget(struct xfs_mount *mp, xfs_ino_t ino,
enum xfs_metafile_type metafile_type, struct xfs_inode **ipp);
#endif /* __XFS_METAFILE_H__ */

186
fs/xfs/libxfs/xfs_ondisk.h
View File

@ -19,40 +19,46 @@
static_assert((value) == (expected), \
"XFS: value of " #value " is wrong, expected " #expected)
#define XFS_CHECK_SB_OFFSET(field, offset) \
XFS_CHECK_OFFSET(struct xfs_dsb, field, offset); \
XFS_CHECK_OFFSET(struct xfs_sb, field, offset);
static inline void __init
xfs_check_ondisk_structs(void)
{
/* ag/file structures */
/* file structures */
XFS_CHECK_STRUCT_SIZE(struct xfs_acl, 4);
XFS_CHECK_STRUCT_SIZE(struct xfs_acl_entry, 12);
XFS_CHECK_STRUCT_SIZE(struct xfs_agf, 224);
XFS_CHECK_STRUCT_SIZE(struct xfs_agfl, 36);
XFS_CHECK_STRUCT_SIZE(struct xfs_agi, 344);
XFS_CHECK_STRUCT_SIZE(struct xfs_bmbt_key, 8);
XFS_CHECK_STRUCT_SIZE(struct xfs_bmbt_rec, 16);
XFS_CHECK_STRUCT_SIZE(struct xfs_bmdr_block, 4);
XFS_CHECK_STRUCT_SIZE(struct xfs_btree_block_shdr, 48);
XFS_CHECK_STRUCT_SIZE(struct xfs_btree_block_lhdr, 64);
XFS_CHECK_STRUCT_SIZE(struct xfs_btree_block, 72);
XFS_CHECK_STRUCT_SIZE(struct xfs_dinode, 176);
XFS_CHECK_STRUCT_SIZE(struct xfs_disk_dquot, 104);
XFS_CHECK_STRUCT_SIZE(struct xfs_dqblk, 136);
XFS_CHECK_STRUCT_SIZE(struct xfs_dsb, 264);
XFS_CHECK_STRUCT_SIZE(struct xfs_dsymlink_hdr, 56);
XFS_CHECK_STRUCT_SIZE(xfs_timestamp_t, 8);
XFS_CHECK_STRUCT_SIZE(struct xfs_legacy_timestamp, 8);
/* space btrees */
XFS_CHECK_STRUCT_SIZE(struct xfs_agf, 224);
XFS_CHECK_STRUCT_SIZE(struct xfs_agfl, 36);
XFS_CHECK_STRUCT_SIZE(struct xfs_agi, 344);
XFS_CHECK_STRUCT_SIZE(struct xfs_alloc_rec, 8);
XFS_CHECK_STRUCT_SIZE(struct xfs_btree_block, 72);
XFS_CHECK_STRUCT_SIZE(struct xfs_btree_block_lhdr, 64);
XFS_CHECK_STRUCT_SIZE(struct xfs_btree_block_shdr, 48);
XFS_CHECK_STRUCT_SIZE(struct xfs_inobt_key, 4);
XFS_CHECK_STRUCT_SIZE(struct xfs_inobt_rec, 16);
XFS_CHECK_STRUCT_SIZE(struct xfs_refcount_key, 4);
XFS_CHECK_STRUCT_SIZE(struct xfs_refcount_rec, 12);
XFS_CHECK_STRUCT_SIZE(struct xfs_rmap_key, 20);
XFS_CHECK_STRUCT_SIZE(struct xfs_rmap_rec, 24);
XFS_CHECK_STRUCT_SIZE(xfs_timestamp_t, 8);
XFS_CHECK_STRUCT_SIZE(struct xfs_legacy_timestamp, 8);
XFS_CHECK_STRUCT_SIZE(xfs_alloc_key_t, 8);
XFS_CHECK_STRUCT_SIZE(xfs_alloc_ptr_t, 4);
XFS_CHECK_STRUCT_SIZE(xfs_alloc_rec_t, 8);
XFS_CHECK_STRUCT_SIZE(xfs_inobt_ptr_t, 4);
XFS_CHECK_STRUCT_SIZE(xfs_refcount_ptr_t, 4);
XFS_CHECK_STRUCT_SIZE(xfs_rmap_ptr_t, 4);
XFS_CHECK_STRUCT_SIZE(xfs_bmdr_key_t, 8);
/* dir/attr trees */
XFS_CHECK_STRUCT_SIZE(struct xfs_attr3_leaf_hdr, 80);
@ -67,33 +73,34 @@ xfs_check_ondisk_structs(void)
XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_free_hdr, 64);
XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_leaf, 64);
XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_leaf_hdr, 64);
XFS_CHECK_STRUCT_SIZE(xfs_attr_leaf_entry_t, 8);
XFS_CHECK_STRUCT_SIZE(xfs_attr_leaf_hdr_t, 32);
XFS_CHECK_STRUCT_SIZE(xfs_attr_leaf_map_t, 4);
XFS_CHECK_STRUCT_SIZE(xfs_attr_leaf_name_local_t, 4);
XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_entry, 8);
XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_hdr, 32);
XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_map, 4);
XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_name_local, 4);
/* realtime structures */
XFS_CHECK_STRUCT_SIZE(struct xfs_rtsb, 56);
XFS_CHECK_STRUCT_SIZE(union xfs_rtword_raw, 4);
XFS_CHECK_STRUCT_SIZE(union xfs_suminfo_raw, 4);
XFS_CHECK_STRUCT_SIZE(struct xfs_rtbuf_blkinfo, 48);
/*
* m68k has problems with xfs_attr_leaf_name_remote_t, but we pad it to
* 4 bytes anyway so it's not obviously a problem. Hence for the moment
* we don't check this structure. This can be re-instated when the attr
* definitions are updated to use c99 VLA definitions.
* m68k has problems with struct xfs_attr_leaf_name_remote, but we pad
* it to 4 bytes anyway so it's not obviously a problem. Hence for the
* moment we don't check this structure. This can be re-instated when
* the attr definitions are updated to use c99 VLA definitions.
*
XFS_CHECK_STRUCT_SIZE(xfs_attr_leaf_name_remote_t, 12);
XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_name_remote, 12);
*/
XFS_CHECK_OFFSET(struct xfs_dsb, sb_crc, 224);
XFS_CHECK_OFFSET(xfs_attr_leaf_name_local_t, valuelen, 0);
XFS_CHECK_OFFSET(xfs_attr_leaf_name_local_t, namelen, 2);
XFS_CHECK_OFFSET(xfs_attr_leaf_name_local_t, nameval, 3);
XFS_CHECK_OFFSET(xfs_attr_leaf_name_remote_t, valueblk, 0);
XFS_CHECK_OFFSET(xfs_attr_leaf_name_remote_t, valuelen, 4);
XFS_CHECK_OFFSET(xfs_attr_leaf_name_remote_t, namelen, 8);
XFS_CHECK_OFFSET(xfs_attr_leaf_name_remote_t, name, 9);
XFS_CHECK_STRUCT_SIZE(xfs_attr_leafblock_t, 32);
XFS_CHECK_OFFSET(struct xfs_attr_leaf_name_local, valuelen, 0);
XFS_CHECK_OFFSET(struct xfs_attr_leaf_name_local, namelen, 2);
XFS_CHECK_OFFSET(struct xfs_attr_leaf_name_local, nameval, 3);
XFS_CHECK_OFFSET(struct xfs_attr_leaf_name_remote, valueblk, 0);
XFS_CHECK_OFFSET(struct xfs_attr_leaf_name_remote, valuelen, 4);
XFS_CHECK_OFFSET(struct xfs_attr_leaf_name_remote, namelen, 8);
XFS_CHECK_OFFSET(struct xfs_attr_leaf_name_remote, name, 9);
XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leafblock, 32);
XFS_CHECK_STRUCT_SIZE(struct xfs_attr_sf_hdr, 4);
XFS_CHECK_OFFSET(struct xfs_attr_sf_hdr, totsize, 0);
XFS_CHECK_OFFSET(struct xfs_attr_sf_hdr, count, 2);
@ -101,27 +108,41 @@ xfs_check_ondisk_structs(void)
XFS_CHECK_OFFSET(struct xfs_attr_sf_entry, valuelen, 1);
XFS_CHECK_OFFSET(struct xfs_attr_sf_entry, flags, 2);
XFS_CHECK_OFFSET(struct xfs_attr_sf_entry, nameval, 3);
XFS_CHECK_STRUCT_SIZE(xfs_da_blkinfo_t, 12);
XFS_CHECK_STRUCT_SIZE(xfs_da_intnode_t, 16);
XFS_CHECK_STRUCT_SIZE(xfs_da_node_entry_t, 8);
XFS_CHECK_STRUCT_SIZE(xfs_da_node_hdr_t, 16);
XFS_CHECK_STRUCT_SIZE(xfs_dir2_data_free_t, 4);
XFS_CHECK_STRUCT_SIZE(xfs_dir2_data_hdr_t, 16);
XFS_CHECK_OFFSET(xfs_dir2_data_unused_t, freetag, 0);
XFS_CHECK_OFFSET(xfs_dir2_data_unused_t, length, 2);
XFS_CHECK_STRUCT_SIZE(xfs_dir2_free_hdr_t, 16);
XFS_CHECK_STRUCT_SIZE(xfs_dir2_free_t, 16);
XFS_CHECK_STRUCT_SIZE(xfs_dir2_leaf_entry_t, 8);
XFS_CHECK_STRUCT_SIZE(xfs_dir2_leaf_hdr_t, 16);
XFS_CHECK_STRUCT_SIZE(xfs_dir2_leaf_t, 16);
XFS_CHECK_STRUCT_SIZE(xfs_dir2_leaf_tail_t, 4);
XFS_CHECK_STRUCT_SIZE(xfs_dir2_sf_entry_t, 3);
XFS_CHECK_OFFSET(xfs_dir2_sf_entry_t, namelen, 0);
XFS_CHECK_OFFSET(xfs_dir2_sf_entry_t, offset, 1);
XFS_CHECK_OFFSET(xfs_dir2_sf_entry_t, name, 3);
XFS_CHECK_STRUCT_SIZE(xfs_dir2_sf_hdr_t, 10);
XFS_CHECK_STRUCT_SIZE(struct xfs_da_blkinfo, 12);
XFS_CHECK_STRUCT_SIZE(struct xfs_da_intnode, 16);
XFS_CHECK_STRUCT_SIZE(struct xfs_da_node_entry, 8);
XFS_CHECK_STRUCT_SIZE(struct xfs_da_node_hdr, 16);
XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_free, 4);
XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_hdr, 16);
XFS_CHECK_OFFSET(struct xfs_dir2_data_unused, freetag, 0);
XFS_CHECK_OFFSET(struct xfs_dir2_data_unused, length, 2);
XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_free_hdr, 16);
XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_free, 16);
XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf_entry, 8);
XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf_hdr, 16);
XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf, 16);
XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf_tail, 4);
XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_sf_entry, 3);
XFS_CHECK_OFFSET(struct xfs_dir2_sf_entry, namelen, 0);
XFS_CHECK_OFFSET(struct xfs_dir2_sf_entry, offset, 1);
XFS_CHECK_OFFSET(struct xfs_dir2_sf_entry, name, 3);
XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_sf_hdr, 10);
XFS_CHECK_STRUCT_SIZE(struct xfs_parent_rec, 12);
/* ondisk dir/attr structures from xfs/122 */
XFS_CHECK_STRUCT_SIZE(struct xfs_attr_sf_entry, 3);
XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_free, 4);
XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_hdr, 16);
XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_unused, 6);
XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_free, 16);
XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_free_hdr, 16);
XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf, 16);
XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf_entry, 8);
XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf_hdr, 16);
XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf_tail, 4);
XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_sf_entry, 3);
XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_sf_hdr, 10);
/* log structures */
XFS_CHECK_STRUCT_SIZE(struct xfs_buf_log_format, 88);
XFS_CHECK_STRUCT_SIZE(struct xfs_dq_logformat, 24);
@ -157,6 +178,11 @@ xfs_check_ondisk_structs(void)
XFS_CHECK_OFFSET(struct xfs_efi_log_format_32, efi_extents, 16);
XFS_CHECK_OFFSET(struct xfs_efi_log_format_64, efi_extents, 16);
/* ondisk log structures from xfs/122 */
XFS_CHECK_STRUCT_SIZE(struct xfs_unmount_log_format, 8);
XFS_CHECK_STRUCT_SIZE(struct xfs_xmd_log_format, 16);
XFS_CHECK_STRUCT_SIZE(struct xfs_xmi_log_format, 88);
/* parent pointer ioctls */
XFS_CHECK_STRUCT_SIZE(struct xfs_getparents_rec, 32);
XFS_CHECK_STRUCT_SIZE(struct xfs_getparents, 40);
@ -201,6 +227,70 @@ xfs_check_ondisk_structs(void)
XFS_CHECK_VALUE(XFS_DQ_BIGTIME_EXPIRY_MIN << XFS_DQ_BIGTIME_SHIFT, 4);
XFS_CHECK_VALUE(XFS_DQ_BIGTIME_EXPIRY_MAX << XFS_DQ_BIGTIME_SHIFT,
16299260424LL);
/* superblock field checks we got from xfs/122 */
XFS_CHECK_STRUCT_SIZE(struct xfs_dsb, 288);
XFS_CHECK_STRUCT_SIZE(struct xfs_sb, 288);
XFS_CHECK_SB_OFFSET(sb_magicnum, 0);
XFS_CHECK_SB_OFFSET(sb_blocksize, 4);
XFS_CHECK_SB_OFFSET(sb_dblocks, 8);
XFS_CHECK_SB_OFFSET(sb_rblocks, 16);
XFS_CHECK_SB_OFFSET(sb_rextents, 24);
XFS_CHECK_SB_OFFSET(sb_uuid, 32);
XFS_CHECK_SB_OFFSET(sb_logstart, 48);
XFS_CHECK_SB_OFFSET(sb_rootino, 56);
XFS_CHECK_SB_OFFSET(sb_rbmino, 64);
XFS_CHECK_SB_OFFSET(sb_rsumino, 72);
XFS_CHECK_SB_OFFSET(sb_rextsize, 80);
XFS_CHECK_SB_OFFSET(sb_agblocks, 84);
XFS_CHECK_SB_OFFSET(sb_agcount, 88);
XFS_CHECK_SB_OFFSET(sb_rbmblocks, 92);
XFS_CHECK_SB_OFFSET(sb_logblocks, 96);
XFS_CHECK_SB_OFFSET(sb_versionnum, 100);
XFS_CHECK_SB_OFFSET(sb_sectsize, 102);
XFS_CHECK_SB_OFFSET(sb_inodesize, 104);
XFS_CHECK_SB_OFFSET(sb_inopblock, 106);
XFS_CHECK_SB_OFFSET(sb_blocklog, 120);
XFS_CHECK_SB_OFFSET(sb_fname[12], 120);
XFS_CHECK_SB_OFFSET(sb_sectlog, 121);
XFS_CHECK_SB_OFFSET(sb_inodelog, 122);
XFS_CHECK_SB_OFFSET(sb_inopblog, 123);
XFS_CHECK_SB_OFFSET(sb_agblklog, 124);
XFS_CHECK_SB_OFFSET(sb_rextslog, 125);
XFS_CHECK_SB_OFFSET(sb_inprogress, 126);
XFS_CHECK_SB_OFFSET(sb_imax_pct, 127);
XFS_CHECK_SB_OFFSET(sb_icount, 128);
XFS_CHECK_SB_OFFSET(sb_ifree, 136);
XFS_CHECK_SB_OFFSET(sb_fdblocks, 144);
XFS_CHECK_SB_OFFSET(sb_frextents, 152);
XFS_CHECK_SB_OFFSET(sb_uquotino, 160);
XFS_CHECK_SB_OFFSET(sb_gquotino, 168);
XFS_CHECK_SB_OFFSET(sb_qflags, 176);
XFS_CHECK_SB_OFFSET(sb_flags, 178);
XFS_CHECK_SB_OFFSET(sb_shared_vn, 179);
XFS_CHECK_SB_OFFSET(sb_inoalignmt, 180);
XFS_CHECK_SB_OFFSET(sb_unit, 184);
XFS_CHECK_SB_OFFSET(sb_width, 188);
XFS_CHECK_SB_OFFSET(sb_dirblklog, 192);
XFS_CHECK_SB_OFFSET(sb_logsectlog, 193);
XFS_CHECK_SB_OFFSET(sb_logsectsize, 194);
XFS_CHECK_SB_OFFSET(sb_logsunit, 196);
XFS_CHECK_SB_OFFSET(sb_features2, 200);
XFS_CHECK_SB_OFFSET(sb_bad_features2, 204);
XFS_CHECK_SB_OFFSET(sb_features_compat, 208);
XFS_CHECK_SB_OFFSET(sb_features_ro_compat, 212);
XFS_CHECK_SB_OFFSET(sb_features_incompat, 216);
XFS_CHECK_SB_OFFSET(sb_features_log_incompat, 220);
XFS_CHECK_SB_OFFSET(sb_crc, 224);
XFS_CHECK_SB_OFFSET(sb_spino_align, 228);
XFS_CHECK_SB_OFFSET(sb_pquotino, 232);
XFS_CHECK_SB_OFFSET(sb_lsn, 240);
XFS_CHECK_SB_OFFSET(sb_meta_uuid, 248);
XFS_CHECK_SB_OFFSET(sb_metadirino, 264);
XFS_CHECK_SB_OFFSET(sb_rgcount, 272);
XFS_CHECK_SB_OFFSET(sb_rgextents, 276);
XFS_CHECK_SB_OFFSET(sb_rgblklog, 280);
XFS_CHECK_SB_OFFSET(sb_pad, 281);
}
#endif /* __XFS_ONDISK_H */

43
fs/xfs/libxfs/xfs_quota_defs.h
View File

@ -143,4 +143,47 @@ time64_t xfs_dquot_from_disk_ts(struct xfs_disk_dquot *ddq,
__be32 dtimer);
__be32 xfs_dquot_to_disk_ts(struct xfs_dquot *ddq, time64_t timer);
static inline const char *
xfs_dqinode_path(xfs_dqtype_t type)
{
switch (type) {
case XFS_DQTYPE_USER:
return "user";
case XFS_DQTYPE_GROUP:
return "group";
case XFS_DQTYPE_PROJ:
return "project";
}
ASSERT(0);
return NULL;
}
static inline enum xfs_metafile_type
xfs_dqinode_metafile_type(xfs_dqtype_t type)
{
switch (type) {
case XFS_DQTYPE_USER:
return XFS_METAFILE_USRQUOTA;
case XFS_DQTYPE_GROUP:
return XFS_METAFILE_GRPQUOTA;
case XFS_DQTYPE_PROJ:
return XFS_METAFILE_PRJQUOTA;
}
ASSERT(0);
return XFS_METAFILE_UNKNOWN;
}
unsigned int xfs_dqinode_sick_mask(xfs_dqtype_t type);
int xfs_dqinode_load(struct xfs_trans *tp, struct xfs_inode *dp,
xfs_dqtype_t type, struct xfs_inode **ipp);
int xfs_dqinode_metadir_create(struct xfs_inode *dp, xfs_dqtype_t type,
struct xfs_inode **ipp);
int xfs_dqinode_metadir_link(struct xfs_inode *dp, xfs_dqtype_t type,
struct xfs_inode *ip);
int xfs_dqinode_mkdir_parent(struct xfs_mount *mp, struct xfs_inode **dpp);
int xfs_dqinode_load_parent(struct xfs_trans *tp, struct xfs_inode **dpp);
#endif /* __XFS_QUOTA_H__ */

33
fs/xfs/libxfs/xfs_refcount.c
View File

@ -154,7 +154,7 @@ xfs_refcount_complain_bad_rec(
xfs_warn(mp,
"Refcount BTree record corruption in AG %d detected at %pS!",
cur->bc_ag.pag->pag_agno, fa);
cur->bc_group->xg_gno, fa);
xfs_warn(mp,
"Start block 0x%x, block count 0x%x, references 0x%x",
irec->rc_startblock, irec->rc_blockcount, irec->rc_refcount);
@ -180,7 +180,7 @@ xfs_refcount_get_rec(
return error;
xfs_refcount_btrec_to_irec(rec, irec);
fa = xfs_refcount_check_irec(cur->bc_ag.pag, irec);
fa = xfs_refcount_check_irec(to_perag(cur->bc_group), irec);
if (fa)
return xfs_refcount_complain_bad_rec(cur, fa, irec);
@ -1154,8 +1154,7 @@ xfs_refcount_adjust_extents(
goto out_error;
}
} else {
fsbno = XFS_AGB_TO_FSB(cur->bc_mp,
cur->bc_ag.pag->pag_agno,
fsbno = xfs_agbno_to_fsb(to_perag(cur->bc_group),
tmp.rc_startblock);
error = xfs_free_extent_later(cur->bc_tp, fsbno,
tmp.rc_blockcount, NULL,
@ -1217,8 +1216,7 @@ xfs_refcount_adjust_extents(
}
goto advloop;
} else {
fsbno = XFS_AGB_TO_FSB(cur->bc_mp,
cur->bc_ag.pag->pag_agno,
fsbno = xfs_agbno_to_fsb(to_perag(cur->bc_group),
ext.rc_startblock);
error = xfs_free_extent_later(cur->bc_tp, fsbno,
ext.rc_blockcount, NULL,
@ -1312,7 +1310,7 @@ xfs_refcount_continue_op(
xfs_agblock_t new_agbno)
{
struct xfs_mount *mp = cur->bc_mp;
struct xfs_perag *pag = cur->bc_ag.pag;
struct xfs_perag *pag = to_perag(cur->bc_group);
if (XFS_IS_CORRUPT(mp, !xfs_verify_agbext(pag, new_agbno,
ri->ri_blockcount))) {
@ -1320,10 +1318,10 @@ xfs_refcount_continue_op(
return -EFSCORRUPTED;
}
ri->ri_startblock = XFS_AGB_TO_FSB(mp, pag->pag_agno, new_agbno);
ri->ri_startblock = xfs_agbno_to_fsb(pag, new_agbno);
ASSERT(xfs_verify_fsbext(mp, ri->ri_startblock, ri->ri_blockcount));
ASSERT(pag->pag_agno == XFS_FSB_TO_AGNO(mp, ri->ri_startblock));
ASSERT(pag_agno(pag) == XFS_FSB_TO_AGNO(mp, ri->ri_startblock));
return 0;
}
@ -1360,7 +1358,7 @@ xfs_refcount_finish_one(
* If we haven't gotten a cursor or the cursor AG doesn't match
* the startblock, get one now.
*/
if (rcur != NULL && rcur->bc_ag.pag != ri->ri_pag) {
if (rcur != NULL && rcur->bc_group != ri->ri_group) {
nr_ops = rcur->bc_refc.nr_ops;
shape_changes = rcur->bc_refc.shape_changes;
xfs_btree_del_cursor(rcur, 0);
@ -1368,13 +1366,14 @@ xfs_refcount_finish_one(
*pcur = NULL;
}
if (rcur == NULL) {
error = xfs_alloc_read_agf(ri->ri_pag, tp,
struct xfs_perag *pag = to_perag(ri->ri_group);
error = xfs_alloc_read_agf(pag, tp,
XFS_ALLOC_FLAG_FREEING, &agbp);
if (error)
return error;
*pcur = rcur = xfs_refcountbt_init_cursor(mp, tp, agbp,
ri->ri_pag);
*pcur = rcur = xfs_refcountbt_init_cursor(mp, tp, agbp, pag);
rcur->bc_refc.nr_ops = nr_ops;
rcur->bc_refc.shape_changes = shape_changes;
}
@ -1880,7 +1879,8 @@ xfs_refcount_recover_extent(
INIT_LIST_HEAD(&rr->rr_list);
xfs_refcount_btrec_to_irec(rec, &rr->rr_rrec);
if (xfs_refcount_check_irec(cur->bc_ag.pag, &rr->rr_rrec) != NULL ||
if (xfs_refcount_check_irec(to_perag(cur->bc_group), &rr->rr_rrec) !=
NULL ||
XFS_IS_CORRUPT(cur->bc_mp,
rr->rr_rrec.rc_domain != XFS_REFC_DOMAIN_COW)) {
xfs_btree_mark_sick(cur);
@ -1956,8 +1956,7 @@ xfs_refcount_recover_cow_leftovers(
goto out_free;
/* Free the orphan record */
fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno,
rr->rr_rrec.rc_startblock);
fsb = xfs_agbno_to_fsb(pag, rr->rr_rrec.rc_startblock);
xfs_refcount_free_cow_extent(tp, fsb,
rr->rr_rrec.rc_blockcount);
@ -2029,7 +2028,7 @@ xfs_refcount_query_range_helper(
xfs_failaddr_t fa;
xfs_refcount_btrec_to_irec(rec, &irec);
fa = xfs_refcount_check_irec(cur->bc_ag.pag, &irec);
fa = xfs_refcount_check_irec(to_perag(cur->bc_group), &irec);
if (fa)
return xfs_refcount_complain_bad_rec(cur, fa, &irec);

2
fs/xfs/libxfs/xfs_refcount.h
View File

@ -56,7 +56,7 @@ enum xfs_refcount_intent_type {
struct xfs_refcount_intent {
struct list_head ri_list;
struct xfs_perag *ri_pag;
struct xfs_group *ri_group;
enum xfs_refcount_intent_type ri_type;
xfs_extlen_t ri_blockcount;
xfs_fsblock_t ri_startblock;

17
fs/xfs/libxfs/xfs_refcount_btree.c
View File

@ -30,7 +30,7 @@ xfs_refcountbt_dup_cursor(
struct xfs_btree_cur *cur)
{
return xfs_refcountbt_init_cursor(cur->bc_mp, cur->bc_tp,
cur->bc_ag.agbp, cur->bc_ag.pag);
cur->bc_ag.agbp, to_perag(cur->bc_group));
}
STATIC void
@ -68,21 +68,20 @@ xfs_refcountbt_alloc_block(
memset(&args, 0, sizeof(args));
args.tp = cur->bc_tp;
args.mp = cur->bc_mp;
args.pag = cur->bc_ag.pag;
args.pag = to_perag(cur->bc_group);
args.oinfo = XFS_RMAP_OINFO_REFC;
args.minlen = args.maxlen = args.prod = 1;
args.resv = XFS_AG_RESV_METADATA;
error = xfs_alloc_vextent_near_bno(&args,
XFS_AGB_TO_FSB(args.mp, args.pag->pag_agno,
xfs_refc_block(args.mp)));
xfs_agbno_to_fsb(args.pag, xfs_refc_block(args.mp)));
if (error)
goto out_error;
if (args.fsbno == NULLFSBLOCK) {
*stat = 0;
return 0;
}
ASSERT(args.agno == cur->bc_ag.pag->pag_agno);
ASSERT(args.agno == cur->bc_group->xg_gno);
ASSERT(args.len == 1);
new->s = cpu_to_be32(args.agbno);
@ -170,7 +169,7 @@ xfs_refcountbt_init_ptr_from_cur(
{
struct xfs_agf *agf = cur->bc_ag.agbp->b_addr;
ASSERT(cur->bc_ag.pag->pag_agno == be32_to_cpu(agf->agf_seqno));
ASSERT(cur->bc_group->xg_gno == be32_to_cpu(agf->agf_seqno));
ptr->s = agf->agf_refcount_root;
}
@ -362,11 +361,11 @@ xfs_refcountbt_init_cursor(
{
struct xfs_btree_cur *cur;
ASSERT(pag->pag_agno < mp->m_sb.sb_agcount);
ASSERT(pag_agno(pag) < mp->m_sb.sb_agcount);
cur = xfs_btree_alloc_cursor(mp, tp, &xfs_refcountbt_ops,
mp->m_refc_maxlevels, xfs_refcountbt_cur_cache);
cur->bc_ag.pag = xfs_perag_hold(pag);
cur->bc_group = xfs_group_hold(pag_group(pag));
cur->bc_refc.nr_ops = 0;
cur->bc_refc.shape_changes = 0;
cur->bc_ag.agbp = agbp;
@ -515,7 +514,7 @@ xfs_refcountbt_calc_reserves(
* never be available for the kinds of things that would require btree
* expansion. We therefore can pretend the space isn't there.
*/
if (xfs_ag_contains_log(mp, pag->pag_agno))
if (xfs_ag_contains_log(mp, pag_agno(pag)))
agblocks -= mp->m_sb.sb_logblocks;
*ask += xfs_refcountbt_max_size(mp, agblocks);

42
fs/xfs/libxfs/xfs_rmap.c
View File

@ -213,7 +213,7 @@ xfs_rmap_check_irec(
struct xfs_perag *pag,
const struct xfs_rmap_irec *irec)
{
struct xfs_mount *mp = pag->pag_mount;
struct xfs_mount *mp = pag_mount(pag);
bool is_inode;
bool is_unwritten;
bool is_bmbt;
@ -269,9 +269,7 @@ xfs_rmap_check_btrec(
struct xfs_btree_cur *cur,
const struct xfs_rmap_irec *irec)
{
if (xfs_btree_is_mem_rmap(cur->bc_ops))
return xfs_rmap_check_irec(cur->bc_mem.pag, irec);
return xfs_rmap_check_irec(cur->bc_ag.pag, irec);
return xfs_rmap_check_irec(to_perag(cur->bc_group), irec);
}
static inline int
@ -288,7 +286,7 @@ xfs_rmap_complain_bad_rec(
else
xfs_warn(mp,
"Reverse Mapping BTree record corruption in AG %d detected at %pS!",
cur->bc_ag.pag->pag_agno, fa);
cur->bc_group->xg_gno, fa);
xfs_warn(mp,
"Owner 0x%llx, flags 0x%x, start block 0x%x block count 0x%x",
irec->rm_owner, irec->rm_flags, irec->rm_startblock,
@ -835,7 +833,7 @@ xfs_rmap_hook_enable(void)
static inline void
xfs_rmap_update_hook(
struct xfs_trans *tp,
struct xfs_perag *pag,
struct xfs_group *xg,
enum xfs_rmap_intent_type op,
xfs_agblock_t startblock,
xfs_extlen_t blockcount,
@ -850,27 +848,27 @@ xfs_rmap_update_hook(
.oinfo = *oinfo, /* struct copy */
};
if (pag)
xfs_hooks_call(&pag->pag_rmap_update_hooks, op, &p);
if (xg)
xfs_hooks_call(&xg->xg_rmap_update_hooks, op, &p);
}
}
/* Call the specified function during a reverse mapping update. */
int
xfs_rmap_hook_add(
struct xfs_perag *pag,
struct xfs_group *xg,
struct xfs_rmap_hook *hook)
{
return xfs_hooks_add(&pag->pag_rmap_update_hooks, &hook->rmap_hook);
return xfs_hooks_add(&xg->xg_rmap_update_hooks, &hook->rmap_hook);
}
/* Stop calling the specified function during a reverse mapping update. */
void
xfs_rmap_hook_del(
struct xfs_perag *pag,
struct xfs_group *xg,
struct xfs_rmap_hook *hook)
{
xfs_hooks_del(&pag->pag_rmap_update_hooks, &hook->rmap_hook);
xfs_hooks_del(&xg->xg_rmap_update_hooks, &hook->rmap_hook);
}
/* Configure rmap update hook functions. */
@ -905,7 +903,8 @@ xfs_rmap_free(
return 0;
cur = xfs_rmapbt_init_cursor(mp, tp, agbp, pag);
xfs_rmap_update_hook(tp, pag, XFS_RMAP_UNMAP, bno, len, false, oinfo);
xfs_rmap_update_hook(tp, pag_group(pag), XFS_RMAP_UNMAP, bno, len,
false, oinfo);
error = xfs_rmap_unmap(cur, bno, len, false, oinfo);
xfs_btree_del_cursor(cur, error);
@ -1149,7 +1148,8 @@ xfs_rmap_alloc(
return 0;
cur = xfs_rmapbt_init_cursor(mp, tp, agbp, pag);
xfs_rmap_update_hook(tp, pag, XFS_RMAP_MAP, bno, len, false, oinfo);
xfs_rmap_update_hook(tp, pag_group(pag), XFS_RMAP_MAP, bno, len, false,
oinfo);
error = xfs_rmap_map(cur, bno, len, false, oinfo);
xfs_btree_del_cursor(cur, error);
@ -2586,28 +2586,30 @@ xfs_rmap_finish_one(
* If we haven't gotten a cursor or the cursor AG doesn't match
* the startblock, get one now.
*/
if (rcur != NULL && rcur->bc_ag.pag != ri->ri_pag) {
if (rcur != NULL && rcur->bc_group != ri->ri_group) {
xfs_btree_del_cursor(rcur, 0);
rcur = NULL;
*pcur = NULL;
}
if (rcur == NULL) {
struct xfs_perag *pag = to_perag(ri->ri_group);
/*
* Refresh the freelist before we start changing the
* rmapbt, because a shape change could cause us to
* allocate blocks.
*/
error = xfs_free_extent_fix_freelist(tp, ri->ri_pag, &agbp);
error = xfs_free_extent_fix_freelist(tp, pag, &agbp);
if (error) {
xfs_ag_mark_sick(ri->ri_pag, XFS_SICK_AG_AGFL);
xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL);
return error;
}
if (XFS_IS_CORRUPT(tp->t_mountp, !agbp)) {
xfs_ag_mark_sick(ri->ri_pag, XFS_SICK_AG_AGFL);
xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL);
return -EFSCORRUPTED;
}
*pcur = rcur = xfs_rmapbt_init_cursor(mp, tp, agbp, ri->ri_pag);
*pcur = rcur = xfs_rmapbt_init_cursor(mp, tp, agbp, pag);
}
xfs_rmap_ino_owner(&oinfo, ri->ri_owner, ri->ri_whichfork,
@ -2620,7 +2622,7 @@ xfs_rmap_finish_one(
if (error)
return error;
xfs_rmap_update_hook(tp, ri->ri_pag, ri->ri_type, bno,
xfs_rmap_update_hook(tp, ri->ri_group, ri->ri_type, bno,
ri->ri_bmap.br_blockcount, unwritten, &oinfo);
return 0;
}

6
fs/xfs/libxfs/xfs_rmap.h
View File

@ -173,7 +173,7 @@ struct xfs_rmap_intent {
int ri_whichfork;
uint64_t ri_owner;
struct xfs_bmbt_irec ri_bmap;
struct xfs_perag *ri_pag;
struct xfs_group *ri_group;
};
/* functions for updating the rmapbt based on bmbt map/unmap operations */
@ -264,8 +264,8 @@ struct xfs_rmap_hook {
void xfs_rmap_hook_disable(void);
void xfs_rmap_hook_enable(void);
int xfs_rmap_hook_add(struct xfs_perag *pag, struct xfs_rmap_hook *hook);
void xfs_rmap_hook_del(struct xfs_perag *pag, struct xfs_rmap_hook *hook);
int xfs_rmap_hook_add(struct xfs_group *xg, struct xfs_rmap_hook *hook);
void xfs_rmap_hook_del(struct xfs_group *xg, struct xfs_rmap_hook *hook);
void xfs_rmap_hook_setup(struct xfs_rmap_hook *hook, notifier_fn_t mod_fn);
#endif

24
fs/xfs/libxfs/xfs_rmap_btree.c
View File

@ -57,7 +57,7 @@ xfs_rmapbt_dup_cursor(
struct xfs_btree_cur *cur)
{
return xfs_rmapbt_init_cursor(cur->bc_mp, cur->bc_tp,
cur->bc_ag.agbp, cur->bc_ag.pag);
cur->bc_ag.agbp, to_perag(cur->bc_group));
}
STATIC void
@ -68,12 +68,13 @@ xfs_rmapbt_set_root(
{
struct xfs_buf *agbp = cur->bc_ag.agbp;
struct xfs_agf *agf = agbp->b_addr;
struct xfs_perag *pag = to_perag(cur->bc_group);
ASSERT(ptr->s != 0);
agf->agf_rmap_root = ptr->s;
be32_add_cpu(&agf->agf_rmap_level, inc);
cur->bc_ag.pag->pagf_rmap_level += inc;
pag->pagf_rmap_level += inc;
xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_ROOTS | XFS_AGF_LEVELS);
}
@ -87,7 +88,7 @@ xfs_rmapbt_alloc_block(
{
struct xfs_buf *agbp = cur->bc_ag.agbp;
struct xfs_agf *agf = agbp->b_addr;
struct xfs_perag *pag = cur->bc_ag.pag;
struct xfs_perag *pag = to_perag(cur->bc_group);
struct xfs_alloc_arg args = { .len = 1 };
int error;
xfs_agblock_t bno;
@ -102,7 +103,7 @@ xfs_rmapbt_alloc_block(
return 0;
}
xfs_extent_busy_reuse(cur->bc_mp, pag, bno, 1, false);
xfs_extent_busy_reuse(pag_group(pag), bno, 1, false);
new->s = cpu_to_be32(bno);
be32_add_cpu(&agf->agf_rmap_blocks, 1);
@ -125,7 +126,7 @@ xfs_rmapbt_free_block(
{
struct xfs_buf *agbp = cur->bc_ag.agbp;
struct xfs_agf *agf = agbp->b_addr;
struct xfs_perag *pag = cur->bc_ag.pag;
struct xfs_perag *pag = to_perag(cur->bc_group);
xfs_agblock_t bno;
int error;
@ -136,7 +137,7 @@ xfs_rmapbt_free_block(
if (error)
return error;
xfs_extent_busy_insert(cur->bc_tp, pag, bno, 1,
xfs_extent_busy_insert(cur->bc_tp, pag_group(pag), bno, 1,
XFS_EXTENT_BUSY_SKIP_DISCARD);
xfs_ag_resv_free_extent(pag, XFS_AG_RESV_RMAPBT, NULL, 1);
@ -227,7 +228,7 @@ xfs_rmapbt_init_ptr_from_cur(
{
struct xfs_agf *agf = cur->bc_ag.agbp->b_addr;
ASSERT(cur->bc_ag.pag->pag_agno == be32_to_cpu(agf->agf_seqno));
ASSERT(cur->bc_group->xg_gno == be32_to_cpu(agf->agf_seqno));
ptr->s = agf->agf_rmap_root;
}
@ -538,7 +539,7 @@ xfs_rmapbt_init_cursor(
cur = xfs_btree_alloc_cursor(mp, tp, &xfs_rmapbt_ops,
mp->m_rmap_maxlevels, xfs_rmapbt_cur_cache);
cur->bc_ag.pag = xfs_perag_hold(pag);
cur->bc_group = xfs_group_hold(pag_group(pag));
cur->bc_ag.agbp = agbp;
if (agbp) {
struct xfs_agf *agf = agbp->b_addr;
@ -647,14 +648,13 @@ xfs_rmapbt_mem_cursor(
struct xfbtree *xfbt)
{
struct xfs_btree_cur *cur;
struct xfs_mount *mp = pag->pag_mount;
cur = xfs_btree_alloc_cursor(mp, tp, &xfs_rmapbt_mem_ops,
cur = xfs_btree_alloc_cursor(pag_mount(pag), tp, &xfs_rmapbt_mem_ops,
xfs_rmapbt_maxlevels_ondisk(), xfs_rmapbt_cur_cache);
cur->bc_mem.xfbtree = xfbt;
cur->bc_nlevels = xfbt->nlevels;
cur->bc_mem.pag = xfs_perag_hold(pag);
cur->bc_group = xfs_group_hold(pag_group(pag));
return cur;
}
@ -863,7 +863,7 @@ xfs_rmapbt_calc_reserves(
* never be available for the kinds of things that would require btree
* expansion. We therefore can pretend the space isn't there.
*/
if (xfs_ag_contains_log(mp, pag->pag_agno))
if (xfs_ag_contains_log(mp, pag_agno(pag)))
agblocks -= mp->m_sb.sb_logblocks;
/* Reserve 1% of the AG or enough for 1 block per record. */

406
fs/xfs/libxfs/xfs_rtbitmap.c
View File

@ -20,28 +20,87 @@
#include "xfs_error.h"
#include "xfs_rtbitmap.h"
#include "xfs_health.h"
#include "xfs_sb.h"
#include "xfs_errortag.h"
#include "xfs_log.h"
#include "xfs_buf_item.h"
#include "xfs_extent_busy.h"
/*
* Realtime allocator bitmap functions shared with userspace.
*/
/*
* Real time buffers need verifiers to avoid runtime warnings during IO.
* We don't have anything to verify, however, so these are just dummy
* operations.
*/
static xfs_failaddr_t
xfs_rtbuf_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_mount;
struct xfs_rtbuf_blkinfo *hdr = bp->b_addr;
if (!xfs_verify_magic(bp, hdr->rt_magic))
return __this_address;
if (!xfs_has_rtgroups(mp))
return __this_address;
if (!xfs_has_crc(mp))
return __this_address;
if (!uuid_equal(&hdr->rt_uuid, &mp->m_sb.sb_meta_uuid))
return __this_address;
if (hdr->rt_blkno != cpu_to_be64(xfs_buf_daddr(bp)))
return __this_address;
return NULL;
}
static void
xfs_rtbuf_verify_read(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_mount;
struct xfs_rtbuf_blkinfo *hdr = bp->b_addr;
xfs_failaddr_t fa;
if (!xfs_has_rtgroups(mp))
return;
if (!xfs_log_check_lsn(mp, be64_to_cpu(hdr->rt_lsn))) {
fa = __this_address;
goto fail;
}
if (!xfs_buf_verify_cksum(bp, XFS_RTBUF_CRC_OFF)) {
fa = __this_address;
goto fail;
}
fa = xfs_rtbuf_verify(bp);
if (fa)
goto fail;
return;
fail:
xfs_verifier_error(bp, -EFSCORRUPTED, fa);
}
static void
xfs_rtbuf_verify_write(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_mount;
struct xfs_rtbuf_blkinfo *hdr = bp->b_addr;
struct xfs_buf_log_item *bip = bp->b_log_item;
xfs_failaddr_t fa;
if (!xfs_has_rtgroups(mp))
return;
fa = xfs_rtbuf_verify(bp);
if (fa) {
xfs_verifier_error(bp, -EFSCORRUPTED, fa);
return;
}
if (bip)
hdr->rt_lsn = cpu_to_be64(bip->bli_item.li_lsn);
xfs_buf_update_cksum(bp, XFS_RTBUF_CRC_OFF);
}
const struct xfs_buf_ops xfs_rtbuf_ops = {
@ -50,6 +109,22 @@ const struct xfs_buf_ops xfs_rtbuf_ops = {
.verify_write = xfs_rtbuf_verify_write,
};
const struct xfs_buf_ops xfs_rtbitmap_buf_ops = {
.name = "xfs_rtbitmap",
.magic = { 0, cpu_to_be32(XFS_RTBITMAP_MAGIC) },
.verify_read = xfs_rtbuf_verify_read,
.verify_write = xfs_rtbuf_verify_write,
.verify_struct = xfs_rtbuf_verify,
};
const struct xfs_buf_ops xfs_rtsummary_buf_ops = {
.name = "xfs_rtsummary",
.magic = { 0, cpu_to_be32(XFS_RTSUMMARY_MAGIC) },
.verify_read = xfs_rtbuf_verify_read,
.verify_write = xfs_rtbuf_verify_write,
.verify_struct = xfs_rtbuf_verify,
};
/* Release cached rt bitmap and summary buffers. */
void
xfs_rtbuf_cache_relse(
@ -75,28 +150,31 @@ static int
xfs_rtbuf_get(
struct xfs_rtalloc_args *args,
xfs_fileoff_t block, /* block number in bitmap or summary */
int issum) /* is summary not bitmap */
enum xfs_rtg_inodes type)
{
struct xfs_inode *ip = args->rtg->rtg_inodes[type];
struct xfs_mount *mp = args->mp;
struct xfs_buf **cbpp; /* cached block buffer */
xfs_fileoff_t *coffp; /* cached block number */
struct xfs_buf *bp; /* block buffer, result */
struct xfs_inode *ip; /* bitmap or summary inode */
struct xfs_bmbt_irec map;
enum xfs_blft type;
enum xfs_blft buf_type;
int nmap = 1;
int error;
if (issum) {
switch (type) {
case XFS_RTGI_SUMMARY:
cbpp = &args->sumbp;
coffp = &args->sumoff;
ip = mp->m_rsumip;
type = XFS_BLFT_RTSUMMARY_BUF;
} else {
buf_type = XFS_BLFT_RTSUMMARY_BUF;
break;
case XFS_RTGI_BITMAP:
cbpp = &args->rbmbp;
coffp = &args->rbmoff;
ip = mp->m_rbmip;
type = XFS_BLFT_RTBITMAP_BUF;
buf_type = XFS_BLFT_RTBITMAP_BUF;
break;
default:
return -EINVAL;
}
/*
@ -119,22 +197,32 @@ xfs_rtbuf_get(
return error;
if (XFS_IS_CORRUPT(mp, nmap == 0 || !xfs_bmap_is_written_extent(&map))) {
xfs_rt_mark_sick(mp, issum ? XFS_SICK_RT_SUMMARY :
XFS_SICK_RT_BITMAP);
xfs_rtginode_mark_sick(args->rtg, type);
return -EFSCORRUPTED;
}
ASSERT(map.br_startblock != NULLFSBLOCK);
error = xfs_trans_read_buf(mp, args->tp, mp->m_ddev_targp,
XFS_FSB_TO_DADDR(mp, map.br_startblock),
mp->m_bsize, 0, &bp, &xfs_rtbuf_ops);
mp->m_bsize, 0, &bp,
xfs_rtblock_ops(mp, type));
if (xfs_metadata_is_sick(error))
xfs_rt_mark_sick(mp, issum ? XFS_SICK_RT_SUMMARY :
XFS_SICK_RT_BITMAP);
xfs_rtginode_mark_sick(args->rtg, type);
if (error)
return error;
xfs_trans_buf_set_type(args->tp, bp, type);
if (xfs_has_rtgroups(mp)) {
struct xfs_rtbuf_blkinfo *hdr = bp->b_addr;
if (hdr->rt_owner != cpu_to_be64(ip->i_ino)) {
xfs_buf_mark_corrupt(bp);
xfs_trans_brelse(args->tp, bp);
xfs_rtginode_mark_sick(args->rtg, type);
return -EFSCORRUPTED;
}
}
xfs_trans_buf_set_type(args->tp, bp, buf_type);
*cbpp = bp;
*coffp = block;
return 0;
@ -148,11 +236,11 @@ xfs_rtbitmap_read_buf(
struct xfs_mount *mp = args->mp;
if (XFS_IS_CORRUPT(mp, block >= mp->m_sb.sb_rbmblocks)) {
xfs_rt_mark_sick(mp, XFS_SICK_RT_BITMAP);
xfs_rtginode_mark_sick(args->rtg, XFS_RTGI_BITMAP);
return -EFSCORRUPTED;
}
return xfs_rtbuf_get(args, block, 0);
return xfs_rtbuf_get(args, block, XFS_RTGI_BITMAP);
}
int
@ -163,10 +251,10 @@ xfs_rtsummary_read_buf(
struct xfs_mount *mp = args->mp;
if (XFS_IS_CORRUPT(mp, block >= mp->m_rsumblocks)) {
xfs_rt_mark_sick(args->mp, XFS_SICK_RT_SUMMARY);
xfs_rtginode_mark_sick(args->rtg, XFS_RTGI_SUMMARY);
return -EFSCORRUPTED;
}
return xfs_rtbuf_get(args, block, 1);
return xfs_rtbuf_get(args, block, XFS_RTGI_SUMMARY);
}
/*
@ -503,6 +591,7 @@ xfs_rtmodify_summary(
{
struct xfs_mount *mp = args->mp;
xfs_rtsumoff_t so = xfs_rtsumoffs(mp, log, bbno);
uint8_t *rsum_cache = args->rtg->rtg_rsum_cache;
unsigned int infoword;
xfs_suminfo_t val;
int error;
@ -514,11 +603,11 @@ xfs_rtmodify_summary(
infoword = xfs_rtsumoffs_to_infoword(mp, so);
val = xfs_suminfo_add(args, infoword, delta);
if (mp->m_rsum_cache) {
if (val == 0 && log + 1 == mp->m_rsum_cache[bbno])
mp->m_rsum_cache[bbno] = log;
if (val != 0 && log >= mp->m_rsum_cache[bbno])
mp->m_rsum_cache[bbno] = log + 1;
if (rsum_cache) {
if (val == 0 && log + 1 == rsum_cache[bbno])
rsum_cache[bbno] = log;
if (val != 0 && log >= rsum_cache[bbno])
rsum_cache[bbno] = log + 1;
}
xfs_trans_log_rtsummary(args, infoword);
@ -737,7 +826,7 @@ xfs_rtfree_range(
/*
* Find the next allocated block (end of allocated extent).
*/
error = xfs_rtfind_forw(args, end, mp->m_sb.sb_rextents - 1,
error = xfs_rtfind_forw(args, end, args->rtg->rtg_extents - 1,
&postblock);
if (error)
return error;
@ -961,19 +1050,25 @@ xfs_rtcheck_alloc_range(
int
xfs_rtfree_extent(
struct xfs_trans *tp, /* transaction pointer */
struct xfs_rtgroup *rtg,
xfs_rtxnum_t start, /* starting rtext number to free */
xfs_rtxlen_t len) /* length of extent freed */
{
struct xfs_mount *mp = tp->t_mountp;
struct xfs_inode *rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP];
struct xfs_rtalloc_args args = {
.mp = mp,
.tp = tp,
.rtg = rtg,
};
int error;
struct timespec64 atime;
ASSERT(mp->m_rbmip->i_itemp != NULL);
xfs_assert_ilocked(mp->m_rbmip, XFS_ILOCK_EXCL);
ASSERT(rbmip->i_itemp != NULL);
xfs_assert_ilocked(rbmip, XFS_ILOCK_EXCL);
if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_FREE_EXTENT))
return -EIO;
error = xfs_rtcheck_alloc_range(&args, start, len);
if (error)
@ -990,19 +1085,21 @@ xfs_rtfree_extent(
* Mark more blocks free in the superblock.
*/
xfs_trans_mod_sb(tp, XFS_TRANS_SB_FREXTENTS, (long)len);
/*
* If we've now freed all the blocks, reset the file sequence
* number to 0.
* number to 0 for pre-RTG file systems.
*/
if (tp->t_frextents_delta + mp->m_sb.sb_frextents ==
if (!xfs_has_rtgroups(mp) &&
tp->t_frextents_delta + mp->m_sb.sb_frextents ==
mp->m_sb.sb_rextents) {
if (!(mp->m_rbmip->i_diflags & XFS_DIFLAG_NEWRTBM))
mp->m_rbmip->i_diflags |= XFS_DIFLAG_NEWRTBM;
if (!(rbmip->i_diflags & XFS_DIFLAG_NEWRTBM))
rbmip->i_diflags |= XFS_DIFLAG_NEWRTBM;
atime = inode_get_atime(VFS_I(mp->m_rbmip));
atime = inode_get_atime(VFS_I(rbmip));
atime.tv_sec = 0;
inode_set_atime_to_ts(VFS_I(mp->m_rbmip), atime);
xfs_trans_log_inode(tp, mp->m_rbmip, XFS_ILOG_CORE);
inode_set_atime_to_ts(VFS_I(rbmip), atime);
xfs_trans_log_inode(tp, rbmip, XFS_ILOG_CORE);
}
error = 0;
out:
@ -1018,15 +1115,17 @@ xfs_rtfree_extent(
int
xfs_rtfree_blocks(
struct xfs_trans *tp,
struct xfs_rtgroup *rtg,
xfs_fsblock_t rtbno,
xfs_filblks_t rtlen)
{
struct xfs_mount *mp = tp->t_mountp;
xfs_extlen_t mod;
int error;
ASSERT(rtlen <= XFS_MAX_BMBT_EXTLEN);
mod = xfs_rtb_to_rtxoff(mp, rtlen);
mod = xfs_blen_to_rtxoff(mp, rtlen);
if (mod) {
ASSERT(mod == 0);
return -EIO;
@ -1038,21 +1137,31 @@ xfs_rtfree_blocks(
return -EIO;
}
return xfs_rtfree_extent(tp, xfs_rtb_to_rtx(mp, rtbno),
xfs_rtb_to_rtx(mp, rtlen));
error = xfs_rtfree_extent(tp, rtg, xfs_rtb_to_rtx(mp, rtbno),
xfs_extlen_to_rtxlen(mp, rtlen));
if (error)
return error;
if (xfs_has_rtgroups(mp))
xfs_extent_busy_insert(tp, rtg_group(rtg),
xfs_rtb_to_rgbno(mp, rtbno), rtlen, 0);
return 0;
}
/* Find all the free records within a given range. */
int
xfs_rtalloc_query_range(
struct xfs_mount *mp,
struct xfs_rtgroup *rtg,
struct xfs_trans *tp,
xfs_rtxnum_t start,
xfs_rtxnum_t end,
xfs_rtalloc_query_range_fn fn,
void *priv)
{
struct xfs_mount *mp = rtg_mount(rtg);
struct xfs_rtalloc_args args = {
.rtg = rtg,
.mp = mp,
.tp = tp,
};
@ -1060,10 +1169,10 @@ xfs_rtalloc_query_range(
if (start > end)
return -EINVAL;
if (start == end || start >= mp->m_sb.sb_rextents)
if (start == end || start >= rtg->rtg_extents)
return 0;
end = min(end, mp->m_sb.sb_rextents - 1);
end = min(end, rtg->rtg_extents - 1);
/* Iterate the bitmap, looking for discrepancies. */
while (start <= end) {
@ -1086,7 +1195,7 @@ xfs_rtalloc_query_range(
rec.ar_startext = start;
rec.ar_extcount = rtend - start + 1;
error = fn(mp, tp, &rec, priv);
error = fn(rtg, tp, &rec, priv);
if (error)
break;
}
@ -1101,26 +1210,27 @@ xfs_rtalloc_query_range(
/* Find all the free records. */
int
xfs_rtalloc_query_all(
struct xfs_mount *mp,
struct xfs_rtgroup *rtg,
struct xfs_trans *tp,
xfs_rtalloc_query_range_fn fn,
void *priv)
{
return xfs_rtalloc_query_range(mp, tp, 0, mp->m_sb.sb_rextents - 1, fn,
return xfs_rtalloc_query_range(rtg, tp, 0, rtg->rtg_extents - 1, fn,
priv);
}
/* Is the given extent all free? */
int
xfs_rtalloc_extent_is_free(
struct xfs_mount *mp,
struct xfs_rtgroup *rtg,
struct xfs_trans *tp,
xfs_rtxnum_t start,
xfs_rtxlen_t len,
bool *is_free)
{
struct xfs_rtalloc_args args = {
.mp = mp,
.mp = rtg_mount(rtg),
.rtg = rtg,
.tp = tp,
};
xfs_rtxnum_t end;
@ -1136,88 +1246,71 @@ xfs_rtalloc_extent_is_free(
return 0;
}
/* Compute the number of rt extents tracked by a single bitmap block. */
xfs_rtxnum_t
xfs_rtbitmap_rtx_per_rbmblock(
struct xfs_mount *mp)
{
unsigned int rbmblock_bytes = mp->m_sb.sb_blocksize;
if (xfs_has_rtgroups(mp))
rbmblock_bytes -= sizeof(struct xfs_rtbuf_blkinfo);
return rbmblock_bytes * NBBY;
}
/*
* Compute the number of rtbitmap blocks needed to track the given number of rt
* extents.
*/
xfs_filblks_t
xfs_rtbitmap_blockcount(
xfs_rtbitmap_blockcount_len(
struct xfs_mount *mp,
xfs_rtbxlen_t rtextents)
{
return howmany_64(rtextents, NBBY * mp->m_sb.sb_blocksize);
return howmany_64(rtextents, xfs_rtbitmap_rtx_per_rbmblock(mp));
}
/* Compute the number of rtsummary blocks needed to track the given rt space. */
/* How many rt extents does each rtbitmap file track? */
static inline xfs_rtbxlen_t
xfs_rtbitmap_bitcount(
struct xfs_mount *mp)
{
if (!mp->m_sb.sb_rextents)
return 0;
/* rtgroup size can be nonzero even if rextents is zero */
if (xfs_has_rtgroups(mp))
return mp->m_sb.sb_rgextents;
return mp->m_sb.sb_rextents;
}
/*
* Compute the number of rtbitmap blocks used for a given file system.
*/
xfs_filblks_t
xfs_rtbitmap_blockcount(
struct xfs_mount *mp)
{
return xfs_rtbitmap_blockcount_len(mp, xfs_rtbitmap_bitcount(mp));
}
/*
* Compute the geometry of the rtsummary file needed to track the given rt
* space.
*/
xfs_filblks_t
xfs_rtsummary_blockcount(
struct xfs_mount *mp,
unsigned int rsumlevels,
xfs_extlen_t rbmblocks)
unsigned int *rsumlevels)
{
xfs_rtbxlen_t rextents = xfs_rtbitmap_bitcount(mp);
unsigned long long rsumwords;
rsumwords = (unsigned long long)rsumlevels * rbmblocks;
return XFS_B_TO_FSB(mp, rsumwords << XFS_WORDLOG);
}
/* Lock both realtime free space metadata inodes for a freespace update. */
void
xfs_rtbitmap_lock(
struct xfs_mount *mp)
{
xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL | XFS_ILOCK_RTBITMAP);
xfs_ilock(mp->m_rsumip, XFS_ILOCK_EXCL | XFS_ILOCK_RTSUM);
}
/*
* Join both realtime free space metadata inodes to the transaction. The
* ILOCKs will be released on transaction commit.
*/
void
xfs_rtbitmap_trans_join(
struct xfs_trans *tp)
{
xfs_trans_ijoin(tp, tp->t_mountp->m_rbmip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, tp->t_mountp->m_rsumip, XFS_ILOCK_EXCL);
}
/* Unlock both realtime free space metadata inodes after a freespace update. */
void
xfs_rtbitmap_unlock(
struct xfs_mount *mp)
{
xfs_iunlock(mp->m_rsumip, XFS_ILOCK_EXCL | XFS_ILOCK_RTSUM);
xfs_iunlock(mp->m_rbmip, XFS_ILOCK_EXCL | XFS_ILOCK_RTBITMAP);
}
/*
* Lock the realtime free space metadata inodes for a freespace scan. Callers
* must walk metadata blocks in order of increasing file offset.
*/
void
xfs_rtbitmap_lock_shared(
struct xfs_mount *mp,
unsigned int rbmlock_flags)
{
if (rbmlock_flags & XFS_RBMLOCK_BITMAP)
xfs_ilock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
if (rbmlock_flags & XFS_RBMLOCK_SUMMARY)
xfs_ilock(mp->m_rsumip, XFS_ILOCK_SHARED | XFS_ILOCK_RTSUM);
}
/* Unlock the realtime free space metadata inodes after a freespace scan. */
void
xfs_rtbitmap_unlock_shared(
struct xfs_mount *mp,
unsigned int rbmlock_flags)
{
if (rbmlock_flags & XFS_RBMLOCK_SUMMARY)
xfs_iunlock(mp->m_rsumip, XFS_ILOCK_SHARED | XFS_ILOCK_RTSUM);
if (rbmlock_flags & XFS_RBMLOCK_BITMAP)
xfs_iunlock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
*rsumlevels = xfs_compute_rextslog(rextents) + 1;
rsumwords = xfs_rtbitmap_blockcount_len(mp, rextents) * (*rsumlevels);
return howmany_64(rsumwords, mp->m_blockwsize);
}
static int
@ -1260,21 +1353,26 @@ xfs_rtfile_alloc_blocks(
/* Get a buffer for the block. */
static int
xfs_rtfile_initialize_block(
struct xfs_inode *ip,
struct xfs_rtgroup *rtg,
enum xfs_rtg_inodes type,
xfs_fsblock_t fsbno,
void *data)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_mount *mp = rtg_mount(rtg);
struct xfs_inode *ip = rtg->rtg_inodes[type];
struct xfs_trans *tp;
struct xfs_buf *bp;
void *bufdata;
const size_t copylen = mp->m_blockwsize << XFS_WORDLOG;
enum xfs_blft buf_type;
int error;
if (ip == mp->m_rsumip)
if (type == XFS_RTGI_BITMAP)
buf_type = XFS_BLFT_RTBITMAP_BUF;
else if (type == XFS_RTGI_SUMMARY)
buf_type = XFS_BLFT_RTSUMMARY_BUF;
else
buf_type = XFS_BLFT_RTBITMAP_BUF;
return -EINVAL;
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growrtzero, 0, 0, 0, &tp);
if (error)
@ -1288,13 +1386,30 @@ xfs_rtfile_initialize_block(
xfs_trans_cancel(tp);
return error;
}
bufdata = bp->b_addr;
xfs_trans_buf_set_type(tp, bp, buf_type);
bp->b_ops = &xfs_rtbuf_ops;
if (data)
memcpy(bp->b_addr, data, copylen);
bp->b_ops = xfs_rtblock_ops(mp, type);
if (xfs_has_rtgroups(mp)) {
struct xfs_rtbuf_blkinfo *hdr = bp->b_addr;
if (type == XFS_RTGI_BITMAP)
hdr->rt_magic = cpu_to_be32(XFS_RTBITMAP_MAGIC);
else
memset(bp->b_addr, 0, copylen);
hdr->rt_magic = cpu_to_be32(XFS_RTSUMMARY_MAGIC);
hdr->rt_owner = cpu_to_be64(ip->i_ino);
hdr->rt_blkno = cpu_to_be64(XFS_FSB_TO_DADDR(mp, fsbno));
hdr->rt_lsn = 0;
uuid_copy(&hdr->rt_uuid, &mp->m_sb.sb_meta_uuid);
bufdata += sizeof(*hdr);
}
if (data)
memcpy(bufdata, data, copylen);
else
memset(bufdata, 0, copylen);
xfs_trans_log_buf(tp, bp, 0, mp->m_sb.sb_blocksize - 1);
return xfs_trans_commit(tp);
}
@ -1306,12 +1421,13 @@ xfs_rtfile_initialize_block(
*/
int
xfs_rtfile_initialize_blocks(
struct xfs_inode *ip, /* inode (bitmap/summary) */
struct xfs_rtgroup *rtg,
enum xfs_rtg_inodes type,
xfs_fileoff_t offset_fsb, /* offset to start from */
xfs_fileoff_t end_fsb, /* offset to allocate to */
void *data) /* data to fill the blocks */
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_mount *mp = rtg_mount(rtg);
const size_t copylen = mp->m_blockwsize << XFS_WORDLOG;
while (offset_fsb < end_fsb) {
@ -1319,8 +1435,8 @@ xfs_rtfile_initialize_blocks(
xfs_filblks_t i;
int error;
error = xfs_rtfile_alloc_blocks(ip, offset_fsb,
end_fsb - offset_fsb, &map);
error = xfs_rtfile_alloc_blocks(rtg->rtg_inodes[type],
offset_fsb, end_fsb - offset_fsb, &map);
if (error)
return error;
@ -1330,7 +1446,7 @@ xfs_rtfile_initialize_blocks(
* Do this one block per transaction, to keep it simple.
*/
for (i = 0; i < map.br_blockcount; i++) {
error = xfs_rtfile_initialize_block(ip,
error = xfs_rtfile_initialize_block(rtg, type,
map.br_startblock + i, data);
if (error)
return error;
@ -1343,3 +1459,35 @@ xfs_rtfile_initialize_blocks(
return 0;
}
int
xfs_rtbitmap_create(
struct xfs_rtgroup *rtg,
struct xfs_inode *ip,
struct xfs_trans *tp,
bool init)
{
struct xfs_mount *mp = rtg_mount(rtg);
ip->i_disk_size = mp->m_sb.sb_rbmblocks * mp->m_sb.sb_blocksize;
if (init && !xfs_has_rtgroups(mp)) {
ip->i_diflags |= XFS_DIFLAG_NEWRTBM;
inode_set_atime(VFS_I(ip), 0, 0);
}
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
return 0;
}
int
xfs_rtsummary_create(
struct xfs_rtgroup *rtg,
struct xfs_inode *ip,
struct xfs_trans *tp,
bool init)
{
struct xfs_mount *mp = rtg_mount(rtg);
ip->i_disk_size = mp->m_rsumblocks * mp->m_sb.sb_blocksize;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
return 0;
}

249
fs/xfs/libxfs/xfs_rtbitmap.h
View File

@ -6,7 +6,10 @@
#ifndef __XFS_RTBITMAP_H__
#define __XFS_RTBITMAP_H__
#include "xfs_rtgroup.h"
struct xfs_rtalloc_args {
struct xfs_rtgroup *rtg;
struct xfs_mount *mp;
struct xfs_trans *tp;
@ -19,13 +22,37 @@ struct xfs_rtalloc_args {
static inline xfs_rtblock_t
xfs_rtx_to_rtb(
struct xfs_mount *mp,
struct xfs_rtgroup *rtg,
xfs_rtxnum_t rtx)
{
if (mp->m_rtxblklog >= 0)
return rtx << mp->m_rtxblklog;
struct xfs_mount *mp = rtg_mount(rtg);
xfs_rtblock_t start = xfs_group_start_fsb(rtg_group(rtg));
return rtx * mp->m_sb.sb_rextsize;
if (mp->m_rtxblklog >= 0)
return start + (rtx << mp->m_rtxblklog);
return start + (rtx * mp->m_sb.sb_rextsize);
}
/* Convert an rgbno into an rt extent number. */
static inline xfs_rtxnum_t
xfs_rgbno_to_rtx(
struct xfs_mount *mp,
xfs_rgblock_t rgbno)
{
if (likely(mp->m_rtxblklog >= 0))
return rgbno >> mp->m_rtxblklog;
return rgbno / mp->m_sb.sb_rextsize;
}
static inline uint64_t
xfs_rtbxlen_to_blen(
struct xfs_mount *mp,
xfs_rtbxlen_t rtbxlen)
{
if (mp->m_rtxblklog >= 0)
return rtbxlen << mp->m_rtxblklog;
return rtbxlen * mp->m_sb.sb_rextsize;
}
static inline xfs_extlen_t
@ -62,15 +89,49 @@ xfs_extlen_to_rtxlen(
return len / mp->m_sb.sb_rextsize;
}
/* Convert an rt block count into an rt extent count. */
static inline xfs_rtbxlen_t
xfs_blen_to_rtbxlen(
struct xfs_mount *mp,
uint64_t blen)
{
if (likely(mp->m_rtxblklog >= 0))
return blen >> mp->m_rtxblklog;
return div_u64(blen, mp->m_sb.sb_rextsize);
}
/* Return the offset of a file block length within an rt extent. */
static inline xfs_extlen_t
xfs_blen_to_rtxoff(
struct xfs_mount *mp,
xfs_filblks_t blen)
{
if (likely(mp->m_rtxblklog >= 0))
return blen & mp->m_rtxblkmask;
return do_div(blen, mp->m_sb.sb_rextsize);
}
/* Round this block count up to the nearest rt extent size. */
static inline xfs_filblks_t
xfs_blen_roundup_rtx(
struct xfs_mount *mp,
xfs_filblks_t blen)
{
return roundup_64(blen, mp->m_sb.sb_rextsize);
}
/* Convert an rt block number into an rt extent number. */
static inline xfs_rtxnum_t
xfs_rtb_to_rtx(
struct xfs_mount *mp,
xfs_rtblock_t rtbno)
{
/* open-coded 64-bit masking operation */
rtbno &= mp->m_groups[XG_TYPE_RTG].blkmask;
if (likely(mp->m_rtxblklog >= 0))
return rtbno >> mp->m_rtxblklog;
return div_u64(rtbno, mp->m_sb.sb_rextsize);
}
@ -80,48 +141,29 @@ xfs_rtb_to_rtxoff(
struct xfs_mount *mp,
xfs_rtblock_t rtbno)
{
/* open-coded 64-bit masking operation */
rtbno &= mp->m_groups[XG_TYPE_RTG].blkmask;
if (likely(mp->m_rtxblklog >= 0))
return rtbno & mp->m_rtxblkmask;
return do_div(rtbno, mp->m_sb.sb_rextsize);
}
/*
* Convert an rt block number into an rt extent number, rounding up to the next
* rt extent if the rt block is not aligned to an rt extent boundary.
*/
static inline xfs_rtxnum_t
xfs_rtb_to_rtxup(
/* Round this file block offset up to the nearest rt extent size. */
static inline xfs_rtblock_t
xfs_fileoff_roundup_rtx(
struct xfs_mount *mp,
xfs_rtblock_t rtbno)
xfs_fileoff_t off)
{
if (likely(mp->m_rtxblklog >= 0)) {
if (rtbno & mp->m_rtxblkmask)
return (rtbno >> mp->m_rtxblklog) + 1;
return rtbno >> mp->m_rtxblklog;
}
if (do_div(rtbno, mp->m_sb.sb_rextsize))
rtbno++;
return rtbno;
return roundup_64(off, mp->m_sb.sb_rextsize);
}
/* Round this rtblock up to the nearest rt extent size. */
/* Round this file block offset down to the nearest rt extent size. */
static inline xfs_rtblock_t
xfs_rtb_roundup_rtx(
xfs_fileoff_rounddown_rtx(
struct xfs_mount *mp,
xfs_rtblock_t rtbno)
xfs_fileoff_t off)
{
return roundup_64(rtbno, mp->m_sb.sb_rextsize);
}
/* Round this rtblock down to the nearest rt extent size. */
static inline xfs_rtblock_t
xfs_rtb_rounddown_rtx(
struct xfs_mount *mp,
xfs_rtblock_t rtbno)
{
return rounddown_64(rtbno, mp->m_sb.sb_rextsize);
return rounddown_64(off, mp->m_sb.sb_rextsize);
}
/* Convert an rt extent number to a file block offset in the rt bitmap file. */
@ -130,6 +172,9 @@ xfs_rtx_to_rbmblock(
struct xfs_mount *mp,
xfs_rtxnum_t rtx)
{
if (xfs_has_rtgroups(mp))
return div_u64(rtx, mp->m_rtx_per_rbmblock);
return rtx >> mp->m_blkbit_log;
}
@ -139,6 +184,13 @@ xfs_rtx_to_rbmword(
struct xfs_mount *mp,
xfs_rtxnum_t rtx)
{
if (xfs_has_rtgroups(mp)) {
unsigned int mod;
div_u64_rem(rtx >> XFS_NBWORDLOG, mp->m_blockwsize, &mod);
return mod;
}
return (rtx >> XFS_NBWORDLOG) & (mp->m_blockwsize - 1);
}
@ -148,6 +200,9 @@ xfs_rbmblock_to_rtx(
struct xfs_mount *mp,
xfs_fileoff_t rbmoff)
{
if (xfs_has_rtgroups(mp))
return rbmoff * mp->m_rtx_per_rbmblock;
return rbmoff << mp->m_blkbit_log;
}
@ -157,7 +212,14 @@ xfs_rbmblock_wordptr(
struct xfs_rtalloc_args *args,
unsigned int index)
{
union xfs_rtword_raw *words = args->rbmbp->b_addr;
struct xfs_mount *mp = args->mp;
union xfs_rtword_raw *words;
struct xfs_rtbuf_blkinfo *hdr = args->rbmbp->b_addr;
if (xfs_has_rtgroups(mp))
words = (union xfs_rtword_raw *)(hdr + 1);
else
words = args->rbmbp->b_addr;
return words + index;
}
@ -170,6 +232,8 @@ xfs_rtbitmap_getword(
{
union xfs_rtword_raw *word = xfs_rbmblock_wordptr(args, index);
if (xfs_has_rtgroups(args->mp))
return be32_to_cpu(word->rtg);
return word->old;
}
@ -182,6 +246,9 @@ xfs_rtbitmap_setword(
{
union xfs_rtword_raw *word = xfs_rbmblock_wordptr(args, index);
if (xfs_has_rtgroups(args->mp))
word->rtg = cpu_to_be32(value);
else
word->old = value;
}
@ -207,6 +274,9 @@ xfs_rtsumoffs_to_block(
struct xfs_mount *mp,
xfs_rtsumoff_t rsumoff)
{
if (xfs_has_rtgroups(mp))
return rsumoff / mp->m_blockwsize;
return XFS_B_TO_FSBT(mp, rsumoff * sizeof(xfs_suminfo_t));
}
@ -221,6 +291,9 @@ xfs_rtsumoffs_to_infoword(
{
unsigned int mask = mp->m_blockmask >> XFS_SUMINFOLOG;
if (xfs_has_rtgroups(mp))
return rsumoff % mp->m_blockwsize;
return rsumoff & mask;
}
@ -230,7 +303,13 @@ xfs_rsumblock_infoptr(
struct xfs_rtalloc_args *args,
unsigned int index)
{
union xfs_suminfo_raw *info = args->sumbp->b_addr;
union xfs_suminfo_raw *info;
struct xfs_rtbuf_blkinfo *hdr = args->sumbp->b_addr;
if (xfs_has_rtgroups(args->mp))
info = (union xfs_suminfo_raw *)(hdr + 1);
else
info = args->sumbp->b_addr;
return info + index;
}
@ -243,6 +322,8 @@ xfs_suminfo_get(
{
union xfs_suminfo_raw *info = xfs_rsumblock_infoptr(args, index);
if (xfs_has_rtgroups(args->mp))
return be32_to_cpu(info->rtg);
return info->old;
}
@ -255,10 +336,28 @@ xfs_suminfo_add(
{
union xfs_suminfo_raw *info = xfs_rsumblock_infoptr(args, index);
if (xfs_has_rtgroups(args->mp)) {
be32_add_cpu(&info->rtg, delta);
return be32_to_cpu(info->rtg);
}
info->old += delta;
return info->old;
}
static inline const struct xfs_buf_ops *
xfs_rtblock_ops(
struct xfs_mount *mp,
enum xfs_rtg_inodes type)
{
if (xfs_has_rtgroups(mp)) {
if (type == XFS_RTGI_SUMMARY)
return &xfs_rtsummary_buf_ops;
return &xfs_rtbitmap_buf_ops;
}
return &xfs_rtbuf_ops;
}
/*
* Functions for walking free space rtextents in the realtime bitmap.
*/
@ -268,7 +367,7 @@ struct xfs_rtalloc_rec {
};
typedef int (*xfs_rtalloc_query_range_fn)(
struct xfs_mount *mp,
struct xfs_rtgroup *rtg,
struct xfs_trans *tp,
const struct xfs_rtalloc_rec *rec,
void *priv);
@ -291,53 +390,43 @@ int xfs_rtmodify_summary(struct xfs_rtalloc_args *args, int log,
xfs_fileoff_t bbno, int delta);
int xfs_rtfree_range(struct xfs_rtalloc_args *args, xfs_rtxnum_t start,
xfs_rtxlen_t len);
int xfs_rtalloc_query_range(struct xfs_mount *mp, struct xfs_trans *tp,
int xfs_rtalloc_query_range(struct xfs_rtgroup *rtg, struct xfs_trans *tp,
xfs_rtxnum_t start, xfs_rtxnum_t end,
xfs_rtalloc_query_range_fn fn, void *priv);
int xfs_rtalloc_query_all(struct xfs_mount *mp, struct xfs_trans *tp,
xfs_rtalloc_query_range_fn fn,
void *priv);
int xfs_rtalloc_extent_is_free(struct xfs_mount *mp, struct xfs_trans *tp,
xfs_rtxnum_t start, xfs_rtxlen_t len,
bool *is_free);
/*
* Free an extent in the realtime subvolume. Length is expressed in
* realtime extents, as is the block number.
*/
int /* error */
xfs_rtfree_extent(
struct xfs_trans *tp, /* transaction pointer */
xfs_rtxnum_t start, /* starting rtext number to free */
xfs_rtxlen_t len); /* length of extent freed */
int xfs_rtalloc_query_all(struct xfs_rtgroup *rtg, struct xfs_trans *tp,
xfs_rtalloc_query_range_fn fn, void *priv);
int xfs_rtalloc_extent_is_free(struct xfs_rtgroup *rtg, struct xfs_trans *tp,
xfs_rtxnum_t start, xfs_rtxlen_t len, bool *is_free);
int xfs_rtfree_extent(struct xfs_trans *tp, struct xfs_rtgroup *rtg,
xfs_rtxnum_t start, xfs_rtxlen_t len);
/* Same as above, but in units of rt blocks. */
int xfs_rtfree_blocks(struct xfs_trans *tp, xfs_fsblock_t rtbno,
xfs_filblks_t rtlen);
int xfs_rtfree_blocks(struct xfs_trans *tp, struct xfs_rtgroup *rtg,
xfs_fsblock_t rtbno, xfs_filblks_t rtlen);
xfs_filblks_t xfs_rtbitmap_blockcount(struct xfs_mount *mp, xfs_rtbxlen_t
rtextents);
xfs_rtxnum_t xfs_rtbitmap_rtx_per_rbmblock(struct xfs_mount *mp);
xfs_filblks_t xfs_rtbitmap_blockcount(struct xfs_mount *mp);
xfs_filblks_t xfs_rtbitmap_blockcount_len(struct xfs_mount *mp,
xfs_rtbxlen_t rtextents);
xfs_filblks_t xfs_rtsummary_blockcount(struct xfs_mount *mp,
unsigned int rsumlevels, xfs_extlen_t rbmblocks);
unsigned int *rsumlevels);
int xfs_rtfile_initialize_blocks(struct xfs_inode *ip,
xfs_fileoff_t offset_fsb, xfs_fileoff_t end_fsb, void *data);
int xfs_rtfile_initialize_blocks(struct xfs_rtgroup *rtg,
enum xfs_rtg_inodes type, xfs_fileoff_t offset_fsb,
xfs_fileoff_t end_fsb, void *data);
int xfs_rtbitmap_create(struct xfs_rtgroup *rtg, struct xfs_inode *ip,
struct xfs_trans *tp, bool init);
int xfs_rtsummary_create(struct xfs_rtgroup *rtg, struct xfs_inode *ip,
struct xfs_trans *tp, bool init);
void xfs_rtbitmap_lock(struct xfs_mount *mp);
void xfs_rtbitmap_unlock(struct xfs_mount *mp);
void xfs_rtbitmap_trans_join(struct xfs_trans *tp);
/* Lock the rt bitmap inode in shared mode */
#define XFS_RBMLOCK_BITMAP (1U << 0)
/* Lock the rt summary inode in shared mode */
#define XFS_RBMLOCK_SUMMARY (1U << 1)
void xfs_rtbitmap_lock_shared(struct xfs_mount *mp,
unsigned int rbmlock_flags);
void xfs_rtbitmap_unlock_shared(struct xfs_mount *mp,
unsigned int rbmlock_flags);
#else /* CONFIG_XFS_RT */
# define xfs_rtfree_extent(t,b,l) (-ENOSYS)
# define xfs_rtfree_blocks(t,rb,rl) (-ENOSYS)
static inline int xfs_rtfree_blocks(struct xfs_trans *tp,
struct xfs_rtgroup *rtg, xfs_fsblock_t rtbno,
xfs_filblks_t rtlen)
{
return -ENOSYS;
}
# define xfs_rtalloc_query_range(m,t,l,h,f,p) (-ENOSYS)
# define xfs_rtalloc_query_all(m,t,f,p) (-ENOSYS)
# define xfs_rtbitmap_read_buf(a,b) (-ENOSYS)
@ -345,17 +434,11 @@ void xfs_rtbitmap_unlock_shared(struct xfs_mount *mp,
# define xfs_rtbuf_cache_relse(a) (0)
# define xfs_rtalloc_extent_is_free(m,t,s,l,i) (-ENOSYS)
static inline xfs_filblks_t
xfs_rtbitmap_blockcount(struct xfs_mount *mp, xfs_rtbxlen_t rtextents)
xfs_rtbitmap_blockcount_len(struct xfs_mount *mp, xfs_rtbxlen_t rtextents)
{
/* shut up gcc */
return 0;
}
# define xfs_rtsummary_blockcount(mp, l, b) (0)
# define xfs_rtbitmap_lock(mp) do { } while (0)
# define xfs_rtbitmap_trans_join(tp) do { } while (0)
# define xfs_rtbitmap_unlock(mp) do { } while (0)
# define xfs_rtbitmap_lock_shared(mp, lf) do { } while (0)
# define xfs_rtbitmap_unlock_shared(mp, lf) do { } while (0)
#endif /* CONFIG_XFS_RT */
#endif /* __XFS_RTBITMAP_H__ */

697
fs/xfs/libxfs/xfs_rtgroup.c Normal file
View File

@ -0,0 +1,697 @@
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Copyright (c) 2022-2024 Oracle. All Rights Reserved.
* Author: Darrick J. Wong <djwong@kernel.org>
*/
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_trans_resv.h"
#include "xfs_bit.h"
#include "xfs_sb.h"
#include "xfs_mount.h"
#include "xfs_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_rmap_btree.h"
#include "xfs_alloc.h"
#include "xfs_ialloc.h"
#include "xfs_rmap.h"
#include "xfs_ag.h"
#include "xfs_ag_resv.h"
#include "xfs_health.h"
#include "xfs_error.h"
#include "xfs_bmap.h"
#include "xfs_defer.h"
#include "xfs_log_format.h"
#include "xfs_trans.h"
#include "xfs_trace.h"
#include "xfs_inode.h"
#include "xfs_icache.h"
#include "xfs_buf_item.h"
#include "xfs_rtgroup.h"
#include "xfs_rtbitmap.h"
#include "xfs_metafile.h"
#include "xfs_metadir.h"
/* Find the first usable fsblock in this rtgroup. */
static inline uint32_t
xfs_rtgroup_min_block(
struct xfs_mount *mp,
xfs_rgnumber_t rgno)
{
if (xfs_has_rtsb(mp) && rgno == 0)
return mp->m_sb.sb_rextsize;
return 0;
}
/* Precompute this group's geometry */
void
xfs_rtgroup_calc_geometry(
struct xfs_mount *mp,
struct xfs_rtgroup *rtg,
xfs_rgnumber_t rgno,
xfs_rgnumber_t rgcount,
xfs_rtbxlen_t rextents)
{
rtg->rtg_extents = __xfs_rtgroup_extents(mp, rgno, rgcount, rextents);
rtg_group(rtg)->xg_block_count = rtg->rtg_extents * mp->m_sb.sb_rextsize;
rtg_group(rtg)->xg_min_gbno = xfs_rtgroup_min_block(mp, rgno);
}
int
xfs_rtgroup_alloc(
struct xfs_mount *mp,
xfs_rgnumber_t rgno,
xfs_rgnumber_t rgcount,
xfs_rtbxlen_t rextents)
{
struct xfs_rtgroup *rtg;
int error;
rtg = kzalloc(sizeof(struct xfs_rtgroup), GFP_KERNEL);
if (!rtg)
return -ENOMEM;
xfs_rtgroup_calc_geometry(mp, rtg, rgno, rgcount, rextents);
error = xfs_group_insert(mp, rtg_group(rtg), rgno, XG_TYPE_RTG);
if (error)
goto out_free_rtg;
return 0;
out_free_rtg:
kfree(rtg);
return error;
}
void
xfs_rtgroup_free(
struct xfs_mount *mp,
xfs_rgnumber_t rgno)
{
xfs_group_free(mp, rgno, XG_TYPE_RTG, NULL);
}
/* Free a range of incore rtgroup objects. */
void
xfs_free_rtgroups(
struct xfs_mount *mp,
xfs_rgnumber_t first_rgno,
xfs_rgnumber_t end_rgno)
{
xfs_rgnumber_t rgno;
for (rgno = first_rgno; rgno < end_rgno; rgno++)
xfs_rtgroup_free(mp, rgno);
}
/* Initialize some range of incore rtgroup objects. */
int
xfs_initialize_rtgroups(
struct xfs_mount *mp,
xfs_rgnumber_t first_rgno,
xfs_rgnumber_t end_rgno,
xfs_rtbxlen_t rextents)
{
xfs_rgnumber_t index;
int error;
if (first_rgno >= end_rgno)
return 0;
for (index = first_rgno; index < end_rgno; index++) {
error = xfs_rtgroup_alloc(mp, index, end_rgno, rextents);
if (error)
goto out_unwind_new_rtgs;
}
return 0;
out_unwind_new_rtgs:
xfs_free_rtgroups(mp, first_rgno, index);
return error;
}
/* Compute the number of rt extents in this realtime group. */
xfs_rtxnum_t
__xfs_rtgroup_extents(
struct xfs_mount *mp,
xfs_rgnumber_t rgno,
xfs_rgnumber_t rgcount,
xfs_rtbxlen_t rextents)
{
ASSERT(rgno < rgcount);
if (rgno == rgcount - 1)
return rextents - ((xfs_rtxnum_t)rgno * mp->m_sb.sb_rgextents);
ASSERT(xfs_has_rtgroups(mp));
return mp->m_sb.sb_rgextents;
}
xfs_rtxnum_t
xfs_rtgroup_extents(
struct xfs_mount *mp,
xfs_rgnumber_t rgno)
{
return __xfs_rtgroup_extents(mp, rgno, mp->m_sb.sb_rgcount,
mp->m_sb.sb_rextents);
}
/*
* Update the rt extent count of the previous tail rtgroup if it changed during
* recovery (i.e. recovery of a growfs).
*/
int
xfs_update_last_rtgroup_size(
struct xfs_mount *mp,
xfs_rgnumber_t prev_rgcount)
{
struct xfs_rtgroup *rtg;
ASSERT(prev_rgcount > 0);
rtg = xfs_rtgroup_grab(mp, prev_rgcount - 1);
if (!rtg)
return -EFSCORRUPTED;
rtg->rtg_extents = __xfs_rtgroup_extents(mp, prev_rgcount - 1,
mp->m_sb.sb_rgcount, mp->m_sb.sb_rextents);
rtg_group(rtg)->xg_block_count = rtg->rtg_extents * mp->m_sb.sb_rextsize;
xfs_rtgroup_rele(rtg);
return 0;
}
/* Lock metadata inodes associated with this rt group. */
void
xfs_rtgroup_lock(
struct xfs_rtgroup *rtg,
unsigned int rtglock_flags)
{
ASSERT(!(rtglock_flags & ~XFS_RTGLOCK_ALL_FLAGS));
ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) ||
!(rtglock_flags & XFS_RTGLOCK_BITMAP));
if (rtglock_flags & XFS_RTGLOCK_BITMAP) {
/*
* Lock both realtime free space metadata inodes for a freespace
* update.
*/
xfs_ilock(rtg->rtg_inodes[XFS_RTGI_BITMAP], XFS_ILOCK_EXCL);
xfs_ilock(rtg->rtg_inodes[XFS_RTGI_SUMMARY], XFS_ILOCK_EXCL);
} else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) {
xfs_ilock(rtg->rtg_inodes[XFS_RTGI_BITMAP], XFS_ILOCK_SHARED);
}
}
/* Unlock metadata inodes associated with this rt group. */
void
xfs_rtgroup_unlock(
struct xfs_rtgroup *rtg,
unsigned int rtglock_flags)
{
ASSERT(!(rtglock_flags & ~XFS_RTGLOCK_ALL_FLAGS));
ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) ||
!(rtglock_flags & XFS_RTGLOCK_BITMAP));
if (rtglock_flags & XFS_RTGLOCK_BITMAP) {
xfs_iunlock(rtg->rtg_inodes[XFS_RTGI_SUMMARY], XFS_ILOCK_EXCL);
xfs_iunlock(rtg->rtg_inodes[XFS_RTGI_BITMAP], XFS_ILOCK_EXCL);
} else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) {
xfs_iunlock(rtg->rtg_inodes[XFS_RTGI_BITMAP], XFS_ILOCK_SHARED);
}
}
/*
* Join realtime group metadata inodes to the transaction. The ILOCKs will be
* released on transaction commit.
*/
void
xfs_rtgroup_trans_join(
struct xfs_trans *tp,
struct xfs_rtgroup *rtg,
unsigned int rtglock_flags)
{
ASSERT(!(rtglock_flags & ~XFS_RTGLOCK_ALL_FLAGS));
ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED));
if (rtglock_flags & XFS_RTGLOCK_BITMAP) {
xfs_trans_ijoin(tp, rtg->rtg_inodes[XFS_RTGI_BITMAP],
XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, rtg->rtg_inodes[XFS_RTGI_SUMMARY],
XFS_ILOCK_EXCL);
}
}
/* Retrieve rt group geometry. */
int
xfs_rtgroup_get_geometry(
struct xfs_rtgroup *rtg,
struct xfs_rtgroup_geometry *rgeo)
{
/* Fill out form. */
memset(rgeo, 0, sizeof(*rgeo));
rgeo->rg_number = rtg_rgno(rtg);
rgeo->rg_length = rtg_group(rtg)->xg_block_count;
xfs_rtgroup_geom_health(rtg, rgeo);
return 0;
}
#ifdef CONFIG_PROVE_LOCKING
static struct lock_class_key xfs_rtginode_lock_class;
static int
xfs_rtginode_ilock_cmp_fn(
const struct lockdep_map *m1,
const struct lockdep_map *m2)
{
const struct xfs_inode *ip1 =
container_of(m1, struct xfs_inode, i_lock.dep_map);
const struct xfs_inode *ip2 =
container_of(m2, struct xfs_inode, i_lock.dep_map);
if (ip1->i_projid < ip2->i_projid)
return -1;
if (ip1->i_projid > ip2->i_projid)
return 1;
return 0;
}
static inline void
xfs_rtginode_ilock_print_fn(
const struct lockdep_map *m)
{
const struct xfs_inode *ip =
container_of(m, struct xfs_inode, i_lock.dep_map);
printk(KERN_CONT " rgno=%u", ip->i_projid);
}
/*
* Most of the time each of the RTG inode locks are only taken one at a time.
* But when committing deferred ops, more than one of a kind can be taken.
* However, deferred rt ops will be committed in rgno order so there is no
* potential for deadlocks. The code here is needed to tell lockdep about this
* order.
*/
static inline void
xfs_rtginode_lockdep_setup(
struct xfs_inode *ip,
xfs_rgnumber_t rgno,
enum xfs_rtg_inodes type)
{
lockdep_set_class_and_subclass(&ip->i_lock, &xfs_rtginode_lock_class,
type);
lock_set_cmp_fn(&ip->i_lock, xfs_rtginode_ilock_cmp_fn,
xfs_rtginode_ilock_print_fn);
}
#else
#define xfs_rtginode_lockdep_setup(ip, rgno, type) do { } while (0)
#endif /* CONFIG_PROVE_LOCKING */
struct xfs_rtginode_ops {
const char *name; /* short name */
enum xfs_metafile_type metafile_type;
unsigned int sick; /* rtgroup sickness flag */
/* Does the fs have this feature? */
bool (*enabled)(struct xfs_mount *mp);
/* Create this rtgroup metadata inode and initialize it. */
int (*create)(struct xfs_rtgroup *rtg,
struct xfs_inode *ip,
struct xfs_trans *tp,
bool init);
};
static const struct xfs_rtginode_ops xfs_rtginode_ops[XFS_RTGI_MAX] = {
[XFS_RTGI_BITMAP] = {
.name = "bitmap",
.metafile_type = XFS_METAFILE_RTBITMAP,
.sick = XFS_SICK_RG_BITMAP,
.create = xfs_rtbitmap_create,
},
[XFS_RTGI_SUMMARY] = {
.name = "summary",
.metafile_type = XFS_METAFILE_RTSUMMARY,
.sick = XFS_SICK_RG_SUMMARY,
.create = xfs_rtsummary_create,
},
};
/* Return the shortname of this rtgroup inode. */
const char *
xfs_rtginode_name(
enum xfs_rtg_inodes type)
{
return xfs_rtginode_ops[type].name;
}
/* Return the metafile type of this rtgroup inode. */
enum xfs_metafile_type
xfs_rtginode_metafile_type(
enum xfs_rtg_inodes type)
{
return xfs_rtginode_ops[type].metafile_type;
}
/* Should this rtgroup inode be present? */
bool
xfs_rtginode_enabled(
struct xfs_rtgroup *rtg,
enum xfs_rtg_inodes type)
{
const struct xfs_rtginode_ops *ops = &xfs_rtginode_ops[type];
if (!ops->enabled)
return true;
return ops->enabled(rtg_mount(rtg));
}
/* Mark an rtgroup inode sick */
void
xfs_rtginode_mark_sick(
struct xfs_rtgroup *rtg,
enum xfs_rtg_inodes type)
{
const struct xfs_rtginode_ops *ops = &xfs_rtginode_ops[type];
xfs_group_mark_sick(rtg_group(rtg), ops->sick);
}
/* Load and existing rtgroup inode into the rtgroup structure. */
int
xfs_rtginode_load(
struct xfs_rtgroup *rtg,
enum xfs_rtg_inodes type,
struct xfs_trans *tp)
{
struct xfs_mount *mp = tp->t_mountp;
struct xfs_inode *ip;
const struct xfs_rtginode_ops *ops = &xfs_rtginode_ops[type];
int error;
if (!xfs_rtginode_enabled(rtg, type))
return 0;
if (!xfs_has_rtgroups(mp)) {
xfs_ino_t ino;
switch (type) {
case XFS_RTGI_BITMAP:
ino = mp->m_sb.sb_rbmino;
break;
case XFS_RTGI_SUMMARY:
ino = mp->m_sb.sb_rsumino;
break;
default:
/* None of the other types exist on !rtgroups */
return 0;
}
error = xfs_trans_metafile_iget(tp, ino, ops->metafile_type,
&ip);
} else {
const char *path;
if (!mp->m_rtdirip) {
xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR);
return -EFSCORRUPTED;
}
path = xfs_rtginode_path(rtg_rgno(rtg), type);
if (!path)
return -ENOMEM;
error = xfs_metadir_load(tp, mp->m_rtdirip, path,
ops->metafile_type, &ip);
kfree(path);
}
if (error) {
if (xfs_metadata_is_sick(error))
xfs_rtginode_mark_sick(rtg, type);
return error;
}
if (XFS_IS_CORRUPT(mp, ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS &&
ip->i_df.if_format != XFS_DINODE_FMT_BTREE)) {
xfs_irele(ip);
xfs_rtginode_mark_sick(rtg, type);
return -EFSCORRUPTED;
}
if (XFS_IS_CORRUPT(mp, ip->i_projid != rtg_rgno(rtg))) {
xfs_irele(ip);
xfs_rtginode_mark_sick(rtg, type);
return -EFSCORRUPTED;
}
xfs_rtginode_lockdep_setup(ip, rtg_rgno(rtg), type);
rtg->rtg_inodes[type] = ip;
return 0;
}
/* Release an rtgroup metadata inode. */
void
xfs_rtginode_irele(
struct xfs_inode **ipp)
{
if (*ipp)
xfs_irele(*ipp);
*ipp = NULL;
}
/* Add a metadata inode for a realtime rmap btree. */
int
xfs_rtginode_create(
struct xfs_rtgroup *rtg,
enum xfs_rtg_inodes type,
bool init)
{
const struct xfs_rtginode_ops *ops = &xfs_rtginode_ops[type];
struct xfs_mount *mp = rtg_mount(rtg);
struct xfs_metadir_update upd = {
.dp = mp->m_rtdirip,
.metafile_type = ops->metafile_type,
};
int error;
if (!xfs_rtginode_enabled(rtg, type))
return 0;
if (!mp->m_rtdirip) {
xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR);
return -EFSCORRUPTED;
}
upd.path = xfs_rtginode_path(rtg_rgno(rtg), type);
if (!upd.path)
return -ENOMEM;
error = xfs_metadir_start_create(&upd);
if (error)
goto out_path;
error = xfs_metadir_create(&upd, S_IFREG);
if (error)
return error;
xfs_rtginode_lockdep_setup(upd.ip, rtg_rgno(rtg), type);
upd.ip->i_projid = rtg_rgno(rtg);
error = ops->create(rtg, upd.ip, upd.tp, init);
if (error)
goto out_cancel;
error = xfs_metadir_commit(&upd);
if (error)
goto out_path;
kfree(upd.path);
xfs_finish_inode_setup(upd.ip);
rtg->rtg_inodes[type] = upd.ip;
return 0;
out_cancel:
xfs_metadir_cancel(&upd, error);
/* Have to finish setting up the inode to ensure it's deleted. */
if (upd.ip) {
xfs_finish_inode_setup(upd.ip);
xfs_irele(upd.ip);
}
out_path:
kfree(upd.path);
return error;
}
/* Create the parent directory for all rtgroup inodes and load it. */
int
xfs_rtginode_mkdir_parent(
struct xfs_mount *mp)
{
if (!mp->m_metadirip) {
xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR);
return -EFSCORRUPTED;
}
return xfs_metadir_mkdir(mp->m_metadirip, "rtgroups", &mp->m_rtdirip);
}
/* Load the parent directory of all rtgroup inodes. */
int
xfs_rtginode_load_parent(
struct xfs_trans *tp)
{
struct xfs_mount *mp = tp->t_mountp;
if (!mp->m_metadirip) {
xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR);
return -EFSCORRUPTED;
}
return xfs_metadir_load(tp, mp->m_metadirip, "rtgroups",
XFS_METAFILE_DIR, &mp->m_rtdirip);
}
/* Check superblock fields for a read or a write. */
static xfs_failaddr_t
xfs_rtsb_verify_common(
struct xfs_buf *bp)
{
struct xfs_rtsb *rsb = bp->b_addr;
if (!xfs_verify_magic(bp, rsb->rsb_magicnum))
return __this_address;
if (rsb->rsb_pad)
return __this_address;
/* Everything to the end of the fs block must be zero */
if (memchr_inv(rsb + 1, 0, BBTOB(bp->b_length) - sizeof(*rsb)))
return __this_address;
return NULL;
}
/* Check superblock fields for a read or revalidation. */
static inline xfs_failaddr_t
xfs_rtsb_verify_all(
struct xfs_buf *bp)
{
struct xfs_rtsb *rsb = bp->b_addr;
struct xfs_mount *mp = bp->b_mount;
xfs_failaddr_t fa;
fa = xfs_rtsb_verify_common(bp);
if (fa)
return fa;
if (memcmp(&rsb->rsb_fname, &mp->m_sb.sb_fname, XFSLABEL_MAX))
return __this_address;
if (!uuid_equal(&rsb->rsb_uuid, &mp->m_sb.sb_uuid))
return __this_address;
if (!uuid_equal(&rsb->rsb_meta_uuid, &mp->m_sb.sb_meta_uuid))
return __this_address;
return NULL;
}
static void
xfs_rtsb_read_verify(
struct xfs_buf *bp)
{
xfs_failaddr_t fa;
if (!xfs_buf_verify_cksum(bp, XFS_RTSB_CRC_OFF)) {
xfs_verifier_error(bp, -EFSBADCRC, __this_address);
return;
}
fa = xfs_rtsb_verify_all(bp);
if (fa)
xfs_verifier_error(bp, -EFSCORRUPTED, fa);
}
static void
xfs_rtsb_write_verify(
struct xfs_buf *bp)
{
xfs_failaddr_t fa;
fa = xfs_rtsb_verify_common(bp);
if (fa) {
xfs_verifier_error(bp, -EFSCORRUPTED, fa);
return;
}
xfs_buf_update_cksum(bp, XFS_RTSB_CRC_OFF);
}
const struct xfs_buf_ops xfs_rtsb_buf_ops = {
.name = "xfs_rtsb",
.magic = { 0, cpu_to_be32(XFS_RTSB_MAGIC) },
.verify_read = xfs_rtsb_read_verify,
.verify_write = xfs_rtsb_write_verify,
.verify_struct = xfs_rtsb_verify_all,
};
/* Update a realtime superblock from the primary fs super */
void
xfs_update_rtsb(
struct xfs_buf *rtsb_bp,
const struct xfs_buf *sb_bp)
{
const struct xfs_dsb *dsb = sb_bp->b_addr;
struct xfs_rtsb *rsb = rtsb_bp->b_addr;
const uuid_t *meta_uuid;
rsb->rsb_magicnum = cpu_to_be32(XFS_RTSB_MAGIC);
rsb->rsb_pad = 0;
memcpy(&rsb->rsb_fname, &dsb->sb_fname, XFSLABEL_MAX);
memcpy(&rsb->rsb_uuid, &dsb->sb_uuid, sizeof(rsb->rsb_uuid));
/*
* The metadata uuid is the fs uuid if the metauuid feature is not
* enabled.
*/
if (dsb->sb_features_incompat &
cpu_to_be32(XFS_SB_FEAT_INCOMPAT_META_UUID))
meta_uuid = &dsb->sb_meta_uuid;
else
meta_uuid = &dsb->sb_uuid;
memcpy(&rsb->rsb_meta_uuid, meta_uuid, sizeof(rsb->rsb_meta_uuid));
}
/*
* Update the realtime superblock from a filesystem superblock and log it to
* the given transaction.
*/
struct xfs_buf *
xfs_log_rtsb(
struct xfs_trans *tp,
const struct xfs_buf *sb_bp)
{
struct xfs_buf *rtsb_bp;
if (!xfs_has_rtsb(tp->t_mountp))
return NULL;
rtsb_bp = xfs_trans_getrtsb(tp);
if (!rtsb_bp) {
/*
* It's possible for the rtgroups feature to be enabled but
* there is no incore rt superblock buffer if the rt geometry
* was specified at mkfs time but the rt section has not yet
* been attached. In this case, rblocks must be zero.
*/
ASSERT(tp->t_mountp->m_sb.sb_rblocks == 0);
return NULL;
}
xfs_update_rtsb(rtsb_bp, sb_bp);
xfs_trans_ordered_buf(tp, rtsb_bp);
return rtsb_bp;
}

284
fs/xfs/libxfs/xfs_rtgroup.h Normal file
View File

@ -0,0 +1,284 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* Copyright (c) 2022-2024 Oracle. All Rights Reserved.
* Author: Darrick J. Wong <djwong@kernel.org>
*/
#ifndef __LIBXFS_RTGROUP_H
#define __LIBXFS_RTGROUP_H 1
#include "xfs_group.h"
struct xfs_mount;
struct xfs_trans;
enum xfs_rtg_inodes {
XFS_RTGI_BITMAP, /* allocation bitmap */
XFS_RTGI_SUMMARY, /* allocation summary */
XFS_RTGI_MAX,
};
#ifdef MAX_LOCKDEP_SUBCLASSES
static_assert(XFS_RTGI_MAX <= MAX_LOCKDEP_SUBCLASSES);
#endif
/*
* Realtime group incore structure, similar to the per-AG structure.
*/
struct xfs_rtgroup {
struct xfs_group rtg_group;
/* per-rtgroup metadata inodes */
struct xfs_inode *rtg_inodes[XFS_RTGI_MAX];
/* Number of blocks in this group */
xfs_rtxnum_t rtg_extents;
/*
* Cache of rt summary level per bitmap block with the invariant that
* rtg_rsum_cache[bbno] > the maximum i for which rsum[i][bbno] != 0,
* or 0 if rsum[i][bbno] == 0 for all i.
*
* Reads and writes are serialized by the rsumip inode lock.
*/
uint8_t *rtg_rsum_cache;
};
static inline struct xfs_rtgroup *to_rtg(struct xfs_group *xg)
{
return container_of(xg, struct xfs_rtgroup, rtg_group);
}
static inline struct xfs_group *rtg_group(struct xfs_rtgroup *rtg)
{
return &rtg->rtg_group;
}
static inline struct xfs_mount *rtg_mount(const struct xfs_rtgroup *rtg)
{
return rtg->rtg_group.xg_mount;
}
static inline xfs_rgnumber_t rtg_rgno(const struct xfs_rtgroup *rtg)
{
return rtg->rtg_group.xg_gno;
}
/* Passive rtgroup references */
static inline struct xfs_rtgroup *
xfs_rtgroup_get(
struct xfs_mount *mp,
xfs_rgnumber_t rgno)
{
return to_rtg(xfs_group_get(mp, rgno, XG_TYPE_RTG));
}
static inline struct xfs_rtgroup *
xfs_rtgroup_hold(
struct xfs_rtgroup *rtg)
{
return to_rtg(xfs_group_hold(rtg_group(rtg)));
}
static inline void
xfs_rtgroup_put(
struct xfs_rtgroup *rtg)
{
xfs_group_put(rtg_group(rtg));
}
/* Active rtgroup references */
static inline struct xfs_rtgroup *
xfs_rtgroup_grab(
struct xfs_mount *mp,
xfs_rgnumber_t rgno)
{
return to_rtg(xfs_group_grab(mp, rgno, XG_TYPE_RTG));
}
static inline void
xfs_rtgroup_rele(
struct xfs_rtgroup *rtg)
{
xfs_group_rele(rtg_group(rtg));
}
static inline struct xfs_rtgroup *
xfs_rtgroup_next_range(
struct xfs_mount *mp,
struct xfs_rtgroup *rtg,
xfs_rgnumber_t start_rgno,
xfs_rgnumber_t end_rgno)
{
return to_rtg(xfs_group_next_range(mp, rtg ? rtg_group(rtg) : NULL,
start_rgno, end_rgno, XG_TYPE_RTG));
}
static inline struct xfs_rtgroup *
xfs_rtgroup_next(
struct xfs_mount *mp,
struct xfs_rtgroup *rtg)
{
return xfs_rtgroup_next_range(mp, rtg, 0, mp->m_sb.sb_rgcount - 1);
}
static inline xfs_rtblock_t
xfs_rgbno_to_rtb(
struct xfs_rtgroup *rtg,
xfs_rgblock_t rgbno)
{
return xfs_gbno_to_fsb(rtg_group(rtg), rgbno);
}
static inline xfs_rgnumber_t
xfs_rtb_to_rgno(
struct xfs_mount *mp,
xfs_rtblock_t rtbno)
{
return xfs_fsb_to_gno(mp, rtbno, XG_TYPE_RTG);
}
static inline xfs_rgblock_t
xfs_rtb_to_rgbno(
struct xfs_mount *mp,
xfs_rtblock_t rtbno)
{
return xfs_fsb_to_gbno(mp, rtbno, XG_TYPE_RTG);
}
/* Is rtbno the start of a RT group? */
static inline bool
xfs_rtbno_is_group_start(
struct xfs_mount *mp,
xfs_rtblock_t rtbno)
{
return (rtbno & mp->m_groups[XG_TYPE_RTG].blkmask) == 0;
}
/* Convert an rtgroups rt extent number into an rgbno. */
static inline xfs_rgblock_t
xfs_rtx_to_rgbno(
struct xfs_rtgroup *rtg,
xfs_rtxnum_t rtx)
{
struct xfs_mount *mp = rtg_mount(rtg);
if (likely(mp->m_rtxblklog >= 0))
return rtx << mp->m_rtxblklog;
return rtx * mp->m_sb.sb_rextsize;
}
static inline xfs_daddr_t
xfs_rtb_to_daddr(
struct xfs_mount *mp,
xfs_rtblock_t rtbno)
{
struct xfs_groups *g = &mp->m_groups[XG_TYPE_RTG];
xfs_rgnumber_t rgno = xfs_rtb_to_rgno(mp, rtbno);
uint64_t start_bno = (xfs_rtblock_t)rgno * g->blocks;
return XFS_FSB_TO_BB(mp, start_bno + (rtbno & g->blkmask));
}
static inline xfs_rtblock_t
xfs_daddr_to_rtb(
struct xfs_mount *mp,
xfs_daddr_t daddr)
{
xfs_rfsblock_t bno = XFS_BB_TO_FSBT(mp, daddr);
if (xfs_has_rtgroups(mp)) {
struct xfs_groups *g = &mp->m_groups[XG_TYPE_RTG];
xfs_rgnumber_t rgno;
uint32_t rgbno;
rgno = div_u64_rem(bno, g->blocks, &rgbno);
return ((xfs_rtblock_t)rgno << g->blklog) + rgbno;
}
return bno;
}
#ifdef CONFIG_XFS_RT
int xfs_rtgroup_alloc(struct xfs_mount *mp, xfs_rgnumber_t rgno,
xfs_rgnumber_t rgcount, xfs_rtbxlen_t rextents);
void xfs_rtgroup_free(struct xfs_mount *mp, xfs_rgnumber_t rgno);
void xfs_free_rtgroups(struct xfs_mount *mp, xfs_rgnumber_t first_rgno,
xfs_rgnumber_t end_rgno);
int xfs_initialize_rtgroups(struct xfs_mount *mp, xfs_rgnumber_t first_rgno,
xfs_rgnumber_t end_rgno, xfs_rtbxlen_t rextents);
xfs_rtxnum_t __xfs_rtgroup_extents(struct xfs_mount *mp, xfs_rgnumber_t rgno,
xfs_rgnumber_t rgcount, xfs_rtbxlen_t rextents);
xfs_rtxnum_t xfs_rtgroup_extents(struct xfs_mount *mp, xfs_rgnumber_t rgno);
void xfs_rtgroup_calc_geometry(struct xfs_mount *mp, struct xfs_rtgroup *rtg,
xfs_rgnumber_t rgno, xfs_rgnumber_t rgcount,
xfs_rtbxlen_t rextents);
int xfs_update_last_rtgroup_size(struct xfs_mount *mp,
xfs_rgnumber_t prev_rgcount);
/* Lock the rt bitmap inode in exclusive mode */
#define XFS_RTGLOCK_BITMAP (1U << 0)
/* Lock the rt bitmap inode in shared mode */
#define XFS_RTGLOCK_BITMAP_SHARED (1U << 1)
#define XFS_RTGLOCK_ALL_FLAGS (XFS_RTGLOCK_BITMAP | \
XFS_RTGLOCK_BITMAP_SHARED)
void xfs_rtgroup_lock(struct xfs_rtgroup *rtg, unsigned int rtglock_flags);
void xfs_rtgroup_unlock(struct xfs_rtgroup *rtg, unsigned int rtglock_flags);
void xfs_rtgroup_trans_join(struct xfs_trans *tp, struct xfs_rtgroup *rtg,
unsigned int rtglock_flags);
int xfs_rtgroup_get_geometry(struct xfs_rtgroup *rtg,
struct xfs_rtgroup_geometry *rgeo);
int xfs_rtginode_mkdir_parent(struct xfs_mount *mp);
int xfs_rtginode_load_parent(struct xfs_trans *tp);
const char *xfs_rtginode_name(enum xfs_rtg_inodes type);
enum xfs_metafile_type xfs_rtginode_metafile_type(enum xfs_rtg_inodes type);
bool xfs_rtginode_enabled(struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type);
void xfs_rtginode_mark_sick(struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type);
int xfs_rtginode_load(struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type,
struct xfs_trans *tp);
int xfs_rtginode_create(struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type,
bool init);
void xfs_rtginode_irele(struct xfs_inode **ipp);
static inline const char *xfs_rtginode_path(xfs_rgnumber_t rgno,
enum xfs_rtg_inodes type)
{
return kasprintf(GFP_KERNEL, "%u.%s", rgno, xfs_rtginode_name(type));
}
void xfs_update_rtsb(struct xfs_buf *rtsb_bp,
const struct xfs_buf *sb_bp);
struct xfs_buf *xfs_log_rtsb(struct xfs_trans *tp,
const struct xfs_buf *sb_bp);
#else
static inline void xfs_free_rtgroups(struct xfs_mount *mp,
xfs_rgnumber_t first_rgno, xfs_rgnumber_t end_rgno)
{
}
static inline int xfs_initialize_rtgroups(struct xfs_mount *mp,
xfs_rgnumber_t first_rgno, xfs_rgnumber_t end_rgno,
xfs_rtbxlen_t rextents)
{
return 0;
}
# define xfs_rtgroup_extents(mp, rgno) (0)
# define xfs_update_last_rtgroup_size(mp, rgno) (-EOPNOTSUPP)
# define xfs_rtgroup_lock(rtg, gf) ((void)0)
# define xfs_rtgroup_unlock(rtg, gf) ((void)0)
# define xfs_rtgroup_trans_join(tp, rtg, gf) ((void)0)
# define xfs_update_rtsb(bp, sb_bp) ((void)0)
# define xfs_log_rtsb(tp, sb_bp) (NULL)
# define xfs_rtgroup_get_geometry(rtg, rgeo) (-EOPNOTSUPP)
#endif /* CONFIG_XFS_RT */
#endif /* __LIBXFS_RTGROUP_H */

278
fs/xfs/libxfs/xfs_sb.c
View File

@ -27,6 +27,7 @@
#include "xfs_ag.h"
#include "xfs_rtbitmap.h"
#include "xfs_exchrange.h"
#include "xfs_rtgroup.h"
/*
* Physical superblock buffer manipulations. Shared with libxfs in userspace.
@ -180,6 +181,8 @@ xfs_sb_version_to_features(
features |= XFS_FEAT_EXCHANGE_RANGE;
if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_PARENT)
features |= XFS_FEAT_PARENT;
if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)
features |= XFS_FEAT_METADIR;
return features;
}
@ -232,11 +235,37 @@ xfs_validate_sb_read(
return 0;
}
static uint64_t
xfs_sb_calc_rbmblocks(
/* Return the number of extents covered by a single rt bitmap file */
static xfs_rtbxlen_t
xfs_extents_per_rbm(
struct xfs_sb *sbp)
{
return howmany_64(sbp->sb_rextents, NBBY * sbp->sb_blocksize);
if (xfs_sb_is_v5(sbp) &&
(sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR))
return sbp->sb_rgextents;
return sbp->sb_rextents;
}
/*
* Return the payload size of a single rt bitmap block (without the metadata
* header if any).
*/
static inline unsigned int
xfs_rtbmblock_size(
struct xfs_sb *sbp)
{
if (xfs_sb_is_v5(sbp) &&
(sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR))
return sbp->sb_blocksize - sizeof(struct xfs_rtbuf_blkinfo);
return sbp->sb_blocksize;
}
static uint64_t
xfs_expected_rbmblocks(
struct xfs_sb *sbp)
{
return howmany_64(xfs_extents_per_rbm(sbp),
NBBY * xfs_rtbmblock_size(sbp));
}
/* Validate the realtime geometry */
@ -258,7 +287,7 @@ xfs_validate_rt_geometry(
if (sbp->sb_rextents == 0 ||
sbp->sb_rextents != div_u64(sbp->sb_rblocks, sbp->sb_rextsize) ||
sbp->sb_rextslog != xfs_compute_rextslog(sbp->sb_rextents) ||
sbp->sb_rbmblocks != xfs_sb_calc_rbmblocks(sbp))
sbp->sb_rbmblocks != xfs_expected_rbmblocks(sbp))
return false;
return true;
@ -339,6 +368,78 @@ xfs_validate_sb_write(
return 0;
}
int
xfs_compute_rgblklog(
xfs_rtxlen_t rgextents,
xfs_rgblock_t rextsize)
{
uint64_t rgblocks = (uint64_t)rgextents * rextsize;
return xfs_highbit64(rgblocks - 1) + 1;
}
static int
xfs_validate_sb_rtgroups(
struct xfs_mount *mp,
struct xfs_sb *sbp)
{
uint64_t groups;
int rgblklog;
if (sbp->sb_rextsize == 0) {
xfs_warn(mp,
"Realtime extent size must not be zero.");
return -EINVAL;
}
if (sbp->sb_rgextents > XFS_MAX_RGBLOCKS / sbp->sb_rextsize) {
xfs_warn(mp,
"Realtime group size (%u) must be less than %u rt extents.",
sbp->sb_rgextents,
XFS_MAX_RGBLOCKS / sbp->sb_rextsize);
return -EINVAL;
}
if (sbp->sb_rgextents < XFS_MIN_RGEXTENTS) {
xfs_warn(mp,
"Realtime group size (%u) must be at least %u rt extents.",
sbp->sb_rgextents, XFS_MIN_RGEXTENTS);
return -EINVAL;
}
if (sbp->sb_rgcount > XFS_MAX_RGNUMBER) {
xfs_warn(mp,
"Realtime groups (%u) must be less than %u.",
sbp->sb_rgcount, XFS_MAX_RGNUMBER);
return -EINVAL;
}
groups = howmany_64(sbp->sb_rextents, sbp->sb_rgextents);
if (groups != sbp->sb_rgcount) {
xfs_warn(mp,
"Realtime groups (%u) do not cover the entire rt section; need (%llu) groups.",
sbp->sb_rgcount, groups);
return -EINVAL;
}
/* Exchange-range is required for fsr to work on realtime files */
if (!(sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_EXCHRANGE)) {
xfs_warn(mp,
"Realtime groups feature requires exchange-range support.");
return -EINVAL;
}
rgblklog = xfs_compute_rgblklog(sbp->sb_rgextents, sbp->sb_rextsize);
if (sbp->sb_rgblklog != rgblklog) {
xfs_warn(mp,
"Realtime group log (%d) does not match expected value (%d).",
sbp->sb_rgblklog, rgblklog);
return -EINVAL;
}
return 0;
}
/* Check the validity of the SB. */
STATIC int
xfs_validate_sb_common(
@ -350,6 +451,7 @@ xfs_validate_sb_common(
uint32_t agcount = 0;
uint32_t rem;
bool has_dalign;
int error;
if (!xfs_verify_magic(bp, dsb->sb_magicnum)) {
xfs_warn(mp,
@ -398,6 +500,32 @@ xfs_validate_sb_common(
sbp->sb_inoalignmt, align);
return -EINVAL;
}
if (!sbp->sb_spino_align ||
sbp->sb_spino_align > sbp->sb_inoalignmt ||
(sbp->sb_inoalignmt % sbp->sb_spino_align) != 0) {
xfs_warn(mp,
"Sparse inode alignment (%u) is invalid.",
sbp->sb_spino_align);
return -EINVAL;
}
} else if (sbp->sb_spino_align) {
xfs_warn(mp,
"Sparse inode alignment (%u) should be zero.",
sbp->sb_spino_align);
return -EINVAL;
}
if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) {
if (memchr_inv(sbp->sb_pad, 0, sizeof(sbp->sb_pad))) {
xfs_warn(mp,
"Metadir superblock padding fields must be zero.");
return -EINVAL;
}
error = xfs_validate_sb_rtgroups(mp, sbp);
if (error)
return error;
}
} else if (sbp->sb_qflags & (XFS_PQUOTA_ENFD | XFS_GQUOTA_ENFD |
XFS_PQUOTA_CHKD | XFS_GQUOTA_CHKD)) {
@ -566,6 +694,14 @@ xfs_validate_sb_common(
void
xfs_sb_quota_from_disk(struct xfs_sb *sbp)
{
if (xfs_sb_is_v5(sbp) &&
(sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) {
sbp->sb_uquotino = NULLFSINO;
sbp->sb_gquotino = NULLFSINO;
sbp->sb_pquotino = NULLFSINO;
return;
}
/*
* older mkfs doesn't initialize quota inodes to NULLFSINO. This
* leads to in-core values having two different values for a quota
@ -689,6 +825,20 @@ __xfs_sb_from_disk(
/* Convert on-disk flags to in-memory flags? */
if (convert_xquota)
xfs_sb_quota_from_disk(to);
if (to->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) {
to->sb_metadirino = be64_to_cpu(from->sb_metadirino);
to->sb_rgblklog = from->sb_rgblklog;
memcpy(to->sb_pad, from->sb_pad, sizeof(to->sb_pad));
to->sb_rgcount = be32_to_cpu(from->sb_rgcount);
to->sb_rgextents = be32_to_cpu(from->sb_rgextents);
to->sb_rbmino = NULLFSINO;
to->sb_rsumino = NULLFSINO;
} else {
to->sb_metadirino = NULLFSINO;
to->sb_rgcount = 1;
to->sb_rgextents = 0;
}
}
void
@ -706,6 +856,15 @@ xfs_sb_quota_to_disk(
{
uint16_t qflags = from->sb_qflags;
if (xfs_sb_is_v5(from) &&
(from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) {
to->sb_qflags = cpu_to_be16(from->sb_qflags);
to->sb_uquotino = cpu_to_be64(0);
to->sb_gquotino = cpu_to_be64(0);
to->sb_pquotino = cpu_to_be64(0);
return;
}
to->sb_uquotino = cpu_to_be64(from->sb_uquotino);
/*
@ -836,6 +995,16 @@ xfs_sb_to_disk(
to->sb_lsn = cpu_to_be64(from->sb_lsn);
if (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_META_UUID)
uuid_copy(&to->sb_meta_uuid, &from->sb_meta_uuid);
if (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) {
to->sb_metadirino = cpu_to_be64(from->sb_metadirino);
to->sb_rgblklog = from->sb_rgblklog;
memset(to->sb_pad, 0, sizeof(to->sb_pad));
to->sb_rgcount = cpu_to_be32(from->sb_rgcount);
to->sb_rgextents = cpu_to_be32(from->sb_rgextents);
to->sb_rbmino = cpu_to_be64(0);
to->sb_rsumino = cpu_to_be64(0);
}
}
/*
@ -965,13 +1134,43 @@ const struct xfs_buf_ops xfs_sb_quiet_buf_ops = {
.verify_write = xfs_sb_write_verify,
};
/* Compute cached rt geometry from the incore sb. */
void
xfs_mount_sb_set_rextsize(
xfs_sb_mount_rextsize(
struct xfs_mount *mp,
struct xfs_sb *sbp)
{
struct xfs_groups *rgs = &mp->m_groups[XG_TYPE_RTG];
mp->m_rtxblklog = log2_if_power2(sbp->sb_rextsize);
mp->m_rtxblkmask = mask64_if_power2(sbp->sb_rextsize);
if (xfs_sb_is_v5(sbp) &&
(sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) {
rgs->blocks = sbp->sb_rgextents * sbp->sb_rextsize;
rgs->blklog = mp->m_sb.sb_rgblklog;
rgs->blkmask = xfs_mask32lo(mp->m_sb.sb_rgblklog);
} else {
rgs->blocks = 0;
rgs->blklog = 0;
rgs->blkmask = (uint64_t)-1;
}
}
/* Update incore sb rt extent size, then recompute the cached rt geometry. */
void
xfs_mount_sb_set_rextsize(
struct xfs_mount *mp,
struct xfs_sb *sbp,
xfs_agblock_t rextsize)
{
sbp->sb_rextsize = rextsize;
if (xfs_sb_is_v5(sbp) &&
(sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR))
sbp->sb_rgblklog = xfs_compute_rgblklog(sbp->sb_rgextents,
rextsize);
xfs_sb_mount_rextsize(mp, sbp);
}
/*
@ -988,6 +1187,8 @@ xfs_sb_mount_common(
struct xfs_mount *mp,
struct xfs_sb *sbp)
{
struct xfs_groups *ags = &mp->m_groups[XG_TYPE_AG];
mp->m_agfrotor = 0;
atomic_set(&mp->m_agirotor, 0);
mp->m_maxagi = mp->m_sb.sb_agcount;
@ -996,9 +1197,14 @@ xfs_sb_mount_common(
mp->m_sectbb_log = sbp->sb_sectlog - BBSHIFT;
mp->m_agno_log = xfs_highbit32(sbp->sb_agcount - 1) + 1;
mp->m_blockmask = sbp->sb_blocksize - 1;
mp->m_blockwsize = sbp->sb_blocksize >> XFS_WORDLOG;
mp->m_blockwmask = mp->m_blockwsize - 1;
xfs_mount_sb_set_rextsize(mp, sbp);
mp->m_blockwsize = xfs_rtbmblock_size(sbp) >> XFS_WORDLOG;
mp->m_rtx_per_rbmblock = mp->m_blockwsize << XFS_NBWORDLOG;
ags->blocks = mp->m_sb.sb_agblocks;
ags->blklog = mp->m_sb.sb_agblklog;
ags->blkmask = xfs_mask32lo(mp->m_sb.sb_agblklog);
xfs_sb_mount_rextsize(mp, sbp);
mp->m_alloc_mxr[0] = xfs_allocbt_maxrecs(mp, sbp->sb_blocksize, true);
mp->m_alloc_mxr[1] = xfs_allocbt_maxrecs(mp, sbp->sb_blocksize, false);
@ -1045,11 +1251,6 @@ xfs_log_sb(
* reservations that have been taken out percpu counters. If we have an
* unclean shutdown, this will be corrected by log recovery rebuilding
* the counters from the AGF block counts.
*
* Do not update sb_frextents here because it is not part of the lazy
* sb counters, despite having a percpu counter. It is always kept
* consistent with the ondisk rtbitmap by xfs_trans_apply_sb_deltas()
* and hence we don't need have to update it here.
*/
if (xfs_has_lazysbcount(mp)) {
mp->m_sb.sb_icount = percpu_counter_sum_positive(&mp->m_icount);
@ -1060,6 +1261,16 @@ xfs_log_sb(
percpu_counter_sum_positive(&mp->m_fdblocks);
}
/*
* sb_frextents was added to the lazy sb counters when the rt groups
* feature was introduced. This counter can go negative due to the way
* we handle nearly-lockless reservations, so we must use the _positive
* variant here to avoid writing out nonsense frextents.
*/
if (xfs_has_rtgroups(mp))
mp->m_sb.sb_frextents =
percpu_counter_sum_positive(&mp->m_frextents);
xfs_sb_to_disk(bp->b_addr, &mp->m_sb);
xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF);
xfs_trans_log_buf(tp, bp, 0, sizeof(struct xfs_dsb) - 1);
@ -1109,18 +1320,17 @@ int
xfs_update_secondary_sbs(
struct xfs_mount *mp)
{
struct xfs_perag *pag;
xfs_agnumber_t agno = 1;
struct xfs_perag *pag = NULL;
int saved_error = 0;
int error = 0;
LIST_HEAD (buffer_list);
/* update secondary superblocks. */
for_each_perag_from(mp, agno, pag) {
while ((pag = xfs_perag_next_from(mp, pag, 1))) {
struct xfs_buf *bp;
error = xfs_buf_get(mp->m_ddev_targp,
XFS_AG_DADDR(mp, pag->pag_agno, XFS_SB_DADDR),
XFS_AG_DADDR(mp, pag_agno(pag), XFS_SB_DADDR),
XFS_FSS_TO_BB(mp, 1), &bp);
/*
* If we get an error reading or writing alternate superblocks,
@ -1132,7 +1342,7 @@ xfs_update_secondary_sbs(
if (error) {
xfs_warn(mp,
"error allocating secondary superblock for ag %d",
pag->pag_agno);
pag_agno(pag));
if (!saved_error)
saved_error = error;
continue;
@ -1146,26 +1356,22 @@ xfs_update_secondary_sbs(
xfs_buf_relse(bp);
/* don't hold too many buffers at once */
if (agno % 16)
if (pag_agno(pag) % 16)
continue;
error = xfs_buf_delwri_submit(&buffer_list);
if (error) {
xfs_warn(mp,
"write error %d updating a secondary superblock near ag %d",
error, pag->pag_agno);
error, pag_agno(pag));
if (!saved_error)
saved_error = error;
continue;
}
}
error = xfs_buf_delwri_submit(&buffer_list);
if (error) {
xfs_warn(mp,
"write error %d updating a secondary superblock near ag %d",
error, agno);
}
if (error)
xfs_warn(mp, "error %d writing secondary superblocks", error);
return saved_error ? saved_error : error;
}
@ -1175,10 +1381,12 @@ xfs_update_secondary_sbs(
*/
int
xfs_sync_sb_buf(
struct xfs_mount *mp)
struct xfs_mount *mp,
bool update_rtsb)
{
struct xfs_trans *tp;
struct xfs_buf *bp;
struct xfs_buf *rtsb_bp = NULL;
int error;
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_sb, 0, 0, 0, &tp);
@ -1188,6 +1396,11 @@ xfs_sync_sb_buf(
bp = xfs_trans_getsb(tp);
xfs_log_sb(tp);
xfs_trans_bhold(tp, bp);
if (update_rtsb) {
rtsb_bp = xfs_log_rtsb(tp, bp);
if (rtsb_bp)
xfs_trans_bhold(tp, rtsb_bp);
}
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp);
if (error)
@ -1196,7 +1409,11 @@ xfs_sync_sb_buf(
* write out the sb buffer to get the changes to disk
*/
error = xfs_bwrite(bp);
if (!error && rtsb_bp)
error = xfs_bwrite(rtsb_bp);
out:
if (rtsb_bp)
xfs_buf_relse(rtsb_bp);
xfs_buf_relse(bp);
return error;
}
@ -1283,6 +1500,8 @@ xfs_fs_geometry(
geo->flags |= XFS_FSOP_GEOM_FLAGS_NREXT64;
if (xfs_has_exchange_range(mp))
geo->flags |= XFS_FSOP_GEOM_FLAGS_EXCHANGE_RANGE;
if (xfs_has_metadir(mp))
geo->flags |= XFS_FSOP_GEOM_FLAGS_METADIR;
geo->rtsectsize = sbp->sb_blocksize;
geo->dirblocksize = xfs_dir2_dirblock_bytes(sbp);
@ -1298,6 +1517,11 @@ xfs_fs_geometry(
return;
geo->version = XFS_FSOP_GEOM_VERSION_V5;
if (xfs_has_rtgroups(mp)) {
geo->rgcount = sbp->sb_rgcount;
geo->rgextents = sbp->sb_rgextents;
}
}
/* Read a secondary superblock. */

6
fs/xfs/libxfs/xfs_sb.h
View File

@ -15,10 +15,11 @@ struct xfs_perag;
extern void xfs_log_sb(struct xfs_trans *tp);
extern int xfs_sync_sb(struct xfs_mount *mp, bool wait);
extern int xfs_sync_sb_buf(struct xfs_mount *mp);
extern int xfs_sync_sb_buf(struct xfs_mount *mp, bool update_rtsb);
extern void xfs_sb_mount_common(struct xfs_mount *mp, struct xfs_sb *sbp);
void xfs_sb_mount_rextsize(struct xfs_mount *mp, struct xfs_sb *sbp);
void xfs_mount_sb_set_rextsize(struct xfs_mount *mp,
struct xfs_sb *sbp);
struct xfs_sb *sbp, xfs_agblock_t rextsize);
extern void xfs_sb_from_disk(struct xfs_sb *to, struct xfs_dsb *from);
extern void xfs_sb_to_disk(struct xfs_dsb *to, struct xfs_sb *from);
extern void xfs_sb_quota_from_disk(struct xfs_sb *sbp);
@ -43,5 +44,6 @@ bool xfs_validate_stripe_geometry(struct xfs_mount *mp,
bool xfs_validate_rt_geometry(struct xfs_sb *sbp);
uint8_t xfs_compute_rextslog(xfs_rtbxlen_t rtextents);
int xfs_compute_rgblklog(xfs_rtxlen_t rgextents, xfs_rgblock_t rextsize);
#endif /* __XFS_SB_H__ */

4
fs/xfs/libxfs/xfs_shared.h
View File

@ -38,7 +38,10 @@ extern const struct xfs_buf_ops xfs_inode_buf_ops;
extern const struct xfs_buf_ops xfs_inode_buf_ra_ops;
extern const struct xfs_buf_ops xfs_refcountbt_buf_ops;
extern const struct xfs_buf_ops xfs_rmapbt_buf_ops;
extern const struct xfs_buf_ops xfs_rtbitmap_buf_ops;
extern const struct xfs_buf_ops xfs_rtsummary_buf_ops;
extern const struct xfs_buf_ops xfs_rtbuf_ops;
extern const struct xfs_buf_ops xfs_rtsb_buf_ops;
extern const struct xfs_buf_ops xfs_sb_buf_ops;
extern const struct xfs_buf_ops xfs_sb_quiet_buf_ops;
extern const struct xfs_buf_ops xfs_symlink_buf_ops;
@ -157,6 +160,7 @@ void xfs_log_get_max_trans_res(struct xfs_mount *mp,
#define XFS_TRANS_SB_RBLOCKS 0x00000800
#define XFS_TRANS_SB_REXTENTS 0x00001000
#define XFS_TRANS_SB_REXTSLOG 0x00002000
#define XFS_TRANS_SB_RGCOUNT 0x00004000
/*
* Here we centralize the specification of XFS meta-data buffer reference count

2
fs/xfs/libxfs/xfs_trans_resv.c
View File

@ -224,7 +224,7 @@ xfs_rtalloc_block_count(
xfs_rtxlen_t rtxlen;
rtxlen = xfs_extlen_to_rtxlen(mp, XFS_MAX_BMBT_EXTLEN);
rtbmp_blocks = xfs_rtbitmap_blockcount(mp, rtxlen);
rtbmp_blocks = xfs_rtbitmap_blockcount_len(mp, rtxlen);
return (rtbmp_blocks + 1) * num_ops;
}

44
fs/xfs/libxfs/xfs_types.c
View File

@ -12,6 +12,8 @@
#include "xfs_bit.h"
#include "xfs_mount.h"
#include "xfs_ag.h"
#include "xfs_rtbitmap.h"
#include "xfs_rtgroup.h"
/*
@ -111,7 +113,7 @@ xfs_verify_ino(
/* Is this an internal inode number? */
inline bool
xfs_internal_inum(
xfs_is_sb_inum(
struct xfs_mount *mp,
xfs_ino_t ino)
{
@ -129,24 +131,42 @@ xfs_verify_dir_ino(
struct xfs_mount *mp,
xfs_ino_t ino)
{
if (xfs_internal_inum(mp, ino))
if (xfs_is_sb_inum(mp, ino))
return false;
return xfs_verify_ino(mp, ino);
}
/*
* Verify that an realtime block number pointer doesn't point off the
* end of the realtime device.
* Verify that a realtime block number pointer neither points outside the
* allocatable areas of the rtgroup nor off the end of the realtime
* device.
*/
inline bool
xfs_verify_rtbno(
struct xfs_mount *mp,
xfs_rtblock_t rtbno)
{
if (xfs_has_rtgroups(mp)) {
xfs_rgnumber_t rgno = xfs_rtb_to_rgno(mp, rtbno);
xfs_rtxnum_t rtx = xfs_rtb_to_rtx(mp, rtbno);
if (rgno >= mp->m_sb.sb_rgcount)
return false;
if (rtx >= xfs_rtgroup_extents(mp, rgno))
return false;
if (xfs_has_rtsb(mp) && rgno == 0 && rtx == 0)
return false;
return true;
}
return rtbno < mp->m_sb.sb_rblocks;
}
/* Verify that a realtime device extent is fully contained inside the volume. */
/*
* Verify that an allocated realtime device extent neither points outside
* allocatable areas of the rtgroup, across an rtgroup boundary, nor off the
* end of the realtime device.
*/
bool
xfs_verify_rtbext(
struct xfs_mount *mp,
@ -159,7 +179,14 @@ xfs_verify_rtbext(
if (!xfs_verify_rtbno(mp, rtbno))
return false;
return xfs_verify_rtbno(mp, rtbno + len - 1);
if (!xfs_verify_rtbno(mp, rtbno + len - 1))
return false;
if (xfs_has_rtgroups(mp) &&
xfs_rtb_to_rgno(mp, rtbno) != xfs_rtb_to_rgno(mp, rtbno + len - 1))
return false;
return true;
}
/* Calculate the range of valid icount values. */
@ -170,13 +197,12 @@ xfs_icount_range(
unsigned long long *max)
{
unsigned long long nr_inos = 0;
struct xfs_perag *pag;
xfs_agnumber_t agno;
struct xfs_perag *pag = NULL;
/* root, rtbitmap, rtsum all live in the first chunk */
*min = XFS_INODES_PER_CHUNK;
for_each_perag(mp, agno, pag)
while ((pag = xfs_perag_next(mp, pag)))
nr_inos += pag->agino_max - pag->agino_min + 1;
*max = nr_inos;
}

16
fs/xfs/libxfs/xfs_types.h
View File

@ -9,10 +9,12 @@
typedef uint32_t prid_t; /* project ID */
typedef uint32_t xfs_agblock_t; /* blockno in alloc. group */
typedef uint32_t xfs_rgblock_t; /* blockno in realtime group */
typedef uint32_t xfs_agino_t; /* inode # within allocation grp */
typedef uint32_t xfs_extlen_t; /* extent length in blocks */
typedef uint32_t xfs_rtxlen_t; /* file extent length in rtextents */
typedef uint32_t xfs_agnumber_t; /* allocation group number */
typedef uint32_t xfs_rgnumber_t; /* realtime group number */
typedef uint64_t xfs_extnum_t; /* # of extents in a file */
typedef uint32_t xfs_aextnum_t; /* # extents in an attribute fork */
typedef int64_t xfs_fsize_t; /* bytes in a file */
@ -53,7 +55,9 @@ typedef void * xfs_failaddr_t;
#define NULLFILEOFF ((xfs_fileoff_t)-1)
#define NULLAGBLOCK ((xfs_agblock_t)-1)
#define NULLRGBLOCK ((xfs_rgblock_t)-1)
#define NULLAGNUMBER ((xfs_agnumber_t)-1)
#define NULLRGNUMBER ((xfs_rgnumber_t)-1)
#define NULLCOMMITLSN ((xfs_lsn_t)-1)
@ -212,6 +216,16 @@ enum xbtree_recpacking {
XBTREE_RECPACKING_FULL,
};
enum xfs_group_type {
XG_TYPE_AG,
XG_TYPE_RTG,
XG_TYPE_MAX,
} __packed;
#define XG_TYPE_STRINGS \
{ XG_TYPE_AG, "ag" }, \
{ XG_TYPE_RTG, "rtg" }
/*
* Type verifier functions
*/
@ -222,7 +236,7 @@ bool xfs_verify_fsbext(struct xfs_mount *mp, xfs_fsblock_t fsbno,
xfs_fsblock_t len);
bool xfs_verify_ino(struct xfs_mount *mp, xfs_ino_t ino);
bool xfs_internal_inum(struct xfs_mount *mp, xfs_ino_t ino);
bool xfs_is_sb_inum(struct xfs_mount *mp, xfs_ino_t ino);
bool xfs_verify_dir_ino(struct xfs_mount *mp, xfs_ino_t ino);
bool xfs_verify_rtbno(struct xfs_mount *mp, xfs_rtblock_t rtbno);
bool xfs_verify_rtbext(struct xfs_mount *mp, xfs_rtblock_t rtbno,

28
fs/xfs/scrub/agheader.c
View File

@ -144,11 +144,16 @@ xchk_superblock(
if (sb->sb_rootino != cpu_to_be64(mp->m_sb.sb_rootino))
xchk_block_set_preen(sc, bp);
if (xfs_has_metadir(sc->mp)) {
if (sb->sb_metadirino != cpu_to_be64(mp->m_sb.sb_metadirino))
xchk_block_set_preen(sc, bp);
} else {
if (sb->sb_rbmino != cpu_to_be64(mp->m_sb.sb_rbmino))
xchk_block_set_preen(sc, bp);
if (sb->sb_rsumino != cpu_to_be64(mp->m_sb.sb_rsumino))
xchk_block_set_preen(sc, bp);
}
if (sb->sb_rextsize != cpu_to_be32(mp->m_sb.sb_rextsize))
xchk_block_set_corrupt(sc, bp);
@ -224,11 +229,13 @@ xchk_superblock(
* sb_icount, sb_ifree, sb_fdblocks, sb_frexents
*/
if (!xfs_has_metadir(mp)) {
if (sb->sb_uquotino != cpu_to_be64(mp->m_sb.sb_uquotino))
xchk_block_set_preen(sc, bp);
if (sb->sb_gquotino != cpu_to_be64(mp->m_sb.sb_gquotino))
xchk_block_set_preen(sc, bp);
}
/*
* Skip the quota flags since repair will force quotacheck.
@ -274,9 +281,16 @@ xchk_superblock(
if (!!(sb->sb_features2 & cpu_to_be32(~v2_ok)))
xchk_block_set_corrupt(sc, bp);
if (xfs_has_metadir(mp)) {
if (sb->sb_rgblklog != mp->m_sb.sb_rgblklog)
xchk_block_set_corrupt(sc, bp);
if (memchr_inv(sb->sb_pad, 0, sizeof(sb->sb_pad)))
xchk_block_set_preen(sc, bp);
} else {
if (sb->sb_features2 != sb->sb_bad_features2)
xchk_block_set_preen(sc, bp);
}
}
/* Check sb_features2 flags that are set at mkfs time. */
features_mask = cpu_to_be32(XFS_SB_VERSION2_LAZYSBCOUNTBIT |
@ -337,8 +351,10 @@ xchk_superblock(
if (sb->sb_spino_align != cpu_to_be32(mp->m_sb.sb_spino_align))
xchk_block_set_corrupt(sc, bp);
if (!xfs_has_metadir(mp)) {
if (sb->sb_pquotino != cpu_to_be64(mp->m_sb.sb_pquotino))
xchk_block_set_preen(sc, bp);
}
/* Don't care about sb_lsn */
}
@ -349,6 +365,14 @@ xchk_superblock(
xchk_block_set_corrupt(sc, bp);
}
if (xfs_has_metadir(mp)) {
if (sb->sb_rgcount != cpu_to_be32(mp->m_sb.sb_rgcount))
xchk_block_set_corrupt(sc, bp);
if (sb->sb_rgextents != cpu_to_be32(mp->m_sb.sb_rgextents))
xchk_block_set_corrupt(sc, bp);
}
/* Everything else must be zero. */
if (memchr_inv(sb + 1, 0,
BBTOB(bp->b_length) - sizeof(struct xfs_dsb)))
@ -552,7 +576,7 @@ xchk_agf(
/* Check the AG length */
eoag = be32_to_cpu(agf->agf_length);
if (eoag != pag->block_count)
if (eoag != pag_group(pag)->xg_block_count)
xchk_block_set_corrupt(sc, sc->sa.agf_bp);
/* Check the AGF btree roots and levels */
@ -932,7 +956,7 @@ xchk_agi(
/* Check the AG length */
eoag = be32_to_cpu(agi->agi_length);
if (eoag != pag->block_count)
if (eoag != pag_group(pag)->xg_block_count)
xchk_block_set_corrupt(sc, sc->sa.agi_bp);
/* Check btree roots and levels */

42
fs/xfs/scrub/agheader_repair.c
View File

@ -208,8 +208,8 @@ xrep_agf_init_header(
memset(agf, 0, BBTOB(agf_bp->b_length));
agf->agf_magicnum = cpu_to_be32(XFS_AGF_MAGIC);
agf->agf_versionnum = cpu_to_be32(XFS_AGF_VERSION);
agf->agf_seqno = cpu_to_be32(pag->pag_agno);
agf->agf_length = cpu_to_be32(pag->block_count);
agf->agf_seqno = cpu_to_be32(pag_agno(pag));
agf->agf_length = cpu_to_be32(pag_group(pag)->xg_block_count);
agf->agf_flfirst = old_agf->agf_flfirst;
agf->agf_fllast = old_agf->agf_fllast;
agf->agf_flcount = old_agf->agf_flcount;
@ -384,7 +384,7 @@ xrep_agf(
* was corrupt after xfs_alloc_read_agf failed with -EFSCORRUPTED.
*/
error = xfs_trans_read_buf(mp, sc->tp, mp->m_ddev_targp,
XFS_AG_DADDR(mp, sc->sa.pag->pag_agno,
XFS_AG_DADDR(mp, pag_agno(sc->sa.pag),
XFS_AGF_DADDR(mp)),
XFS_FSS_TO_BB(mp, 1), 0, &agf_bp, NULL);
if (error)
@ -687,7 +687,7 @@ xrep_agfl_init_header(
agfl = XFS_BUF_TO_AGFL(agfl_bp);
memset(agfl, 0xFF, BBTOB(agfl_bp->b_length));
agfl->agfl_magicnum = cpu_to_be32(XFS_AGFL_MAGIC);
agfl->agfl_seqno = cpu_to_be32(sc->sa.pag->pag_agno);
agfl->agfl_seqno = cpu_to_be32(pag_agno(sc->sa.pag));
uuid_copy(&agfl->agfl_uuid, &mp->m_sb.sb_meta_uuid);
/*
@ -741,7 +741,7 @@ xrep_agfl(
* was corrupt after xfs_alloc_read_agfl failed with -EFSCORRUPTED.
*/
error = xfs_trans_read_buf(mp, sc->tp, mp->m_ddev_targp,
XFS_AG_DADDR(mp, sc->sa.pag->pag_agno,
XFS_AG_DADDR(mp, pag_agno(sc->sa.pag),
XFS_AGFL_DADDR(mp)),
XFS_FSS_TO_BB(mp, 1), 0, &agfl_bp, NULL);
if (error)
@ -897,8 +897,8 @@ xrep_agi_init_header(
memset(agi, 0, BBTOB(agi_bp->b_length));
agi->agi_magicnum = cpu_to_be32(XFS_AGI_MAGIC);
agi->agi_versionnum = cpu_to_be32(XFS_AGI_VERSION);
agi->agi_seqno = cpu_to_be32(pag->pag_agno);
agi->agi_length = cpu_to_be32(pag->block_count);
agi->agi_seqno = cpu_to_be32(pag_agno(pag));
agi->agi_length = cpu_to_be32(pag_group(pag)->xg_block_count);
agi->agi_newino = cpu_to_be32(NULLAGINO);
agi->agi_dirino = cpu_to_be32(NULLAGINO);
if (xfs_has_crc(mp))
@ -1038,12 +1038,10 @@ xrep_iunlink_reload_next(
{
struct xfs_scrub *sc = ragi->sc;
struct xfs_inode *ip;
xfs_ino_t ino;
xfs_agino_t ret = NULLAGINO;
int error;
ino = XFS_AGINO_TO_INO(sc->mp, sc->sa.pag->pag_agno, agino);
error = xchk_iget(ragi->sc, ino, &ip);
error = xchk_iget(ragi->sc, xfs_agino_to_ino(sc->sa.pag, agino), &ip);
if (error)
return ret;
@ -1114,9 +1112,9 @@ xrep_iunlink_igrab(
struct xfs_perag *pag,
struct xfs_inode *ip)
{
struct xfs_mount *mp = pag->pag_mount;
struct xfs_mount *mp = pag_mount(pag);
if (XFS_INO_TO_AGNO(mp, ip->i_ino) != pag->pag_agno)
if (XFS_INO_TO_AGNO(mp, ip->i_ino) != pag_agno(pag))
return false;
if (!xfs_inode_on_unlinked_list(ip))
@ -1140,7 +1138,7 @@ xrep_iunlink_visit(
unsigned int bucket;
int error;
ASSERT(XFS_INO_TO_AGNO(mp, ip->i_ino) == ragi->sc->sa.pag->pag_agno);
ASSERT(XFS_INO_TO_AGNO(mp, ip->i_ino) == pag_agno(ragi->sc->sa.pag));
ASSERT(xfs_inode_on_unlinked_list(ip));
agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
@ -1171,7 +1169,7 @@ xrep_iunlink_mark_incore(
struct xrep_agi *ragi)
{
struct xfs_perag *pag = ragi->sc->sa.pag;
struct xfs_mount *mp = pag->pag_mount;
struct xfs_mount *mp = pag_mount(pag);
uint32_t first_index = 0;
bool done = false;
unsigned int nr_found = 0;
@ -1211,7 +1209,7 @@ xrep_iunlink_mark_incore(
* us to see this inode, so another lookup from the
* same index will not find it again.
*/
if (XFS_INO_TO_AGNO(mp, ip->i_ino) != pag->pag_agno)
if (XFS_INO_TO_AGNO(mp, ip->i_ino) != pag_agno(pag))
continue;
first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
if (first_index < XFS_INO_TO_AGINO(mp, ip->i_ino))
@ -1278,9 +1276,7 @@ xrep_iunlink_mark_ondisk_rec(
* on because we haven't actually scrubbed the inobt or the
* inodes yet.
*/
error = xchk_iget(ragi->sc,
XFS_AGINO_TO_INO(mp, sc->sa.pag->pag_agno,
agino),
error = xchk_iget(ragi->sc, xfs_agino_to_ino(sc->sa.pag, agino),
&ip);
if (error)
continue;
@ -1539,15 +1535,13 @@ xrep_iunlink_relink_next(
ip = xfs_iunlink_lookup(pag, agino);
if (!ip) {
xfs_ino_t ino;
xfs_agino_t prev_agino;
/*
* No inode exists in cache. Load it off the disk so that we
* can reinsert it into the incore unlinked list.
*/
ino = XFS_AGINO_TO_INO(sc->mp, pag->pag_agno, agino);
error = xchk_iget(sc, ino, &ip);
error = xchk_iget(sc, xfs_agino_to_ino(pag, agino), &ip);
if (error)
return -EFSCORRUPTED;
@ -1601,15 +1595,13 @@ xrep_iunlink_relink_prev(
ip = xfs_iunlink_lookup(pag, agino);
if (!ip) {
xfs_ino_t ino;
xfs_agino_t next_agino;
/*
* No inode exists in cache. Load it off the disk so that we
* can reinsert it into the incore unlinked list.
*/
ino = XFS_AGINO_TO_INO(sc->mp, pag->pag_agno, agino);
error = xchk_iget(sc, ino, &ip);
error = xchk_iget(sc, xfs_agino_to_ino(pag, agino), &ip);
if (error)
return -EFSCORRUPTED;
@ -1769,7 +1761,7 @@ xrep_agi(
* was corrupt after xfs_ialloc_read_agi failed with -EFSCORRUPTED.
*/
error = xfs_trans_read_buf(mp, sc->tp, mp->m_ddev_targp,
XFS_AG_DADDR(mp, sc->sa.pag->pag_agno,
XFS_AG_DADDR(mp, pag_agno(sc->sa.pag),
XFS_AGI_DADDR(mp)),
XFS_FSS_TO_BB(mp, 1), 0, &ragi->agi_bp, NULL);
if (error)

2
fs/xfs/scrub/alloc.c
View File

@ -139,7 +139,7 @@ xchk_allocbt_rec(
struct xchk_alloc *ca = bs->private;
xfs_alloc_btrec_to_irec(rec, &irec);
if (xfs_alloc_check_irec(bs->cur->bc_ag.pag, &irec) != NULL) {
if (xfs_alloc_check_irec(to_perag(bs->cur->bc_group), &irec) != NULL) {
xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
return 0;
}

22
fs/xfs/scrub/alloc_repair.c
View File

@ -132,17 +132,16 @@ int
xrep_setup_ag_allocbt(
struct xfs_scrub *sc)
{
struct xfs_group *xg = pag_group(sc->sa.pag);
unsigned int busy_gen;
/*
* Make sure the busy extent list is clear because we can't put extents
* on there twice.
*/
busy_gen = READ_ONCE(sc->sa.pag->pagb_gen);
if (xfs_extent_busy_list_empty(sc->sa.pag))
if (xfs_extent_busy_list_empty(xg, &busy_gen))
return 0;
return xfs_extent_busy_flush(sc->tp, sc->sa.pag, busy_gen, 0);
return xfs_extent_busy_flush(sc->tp, xg, busy_gen, 0);
}
/* Check for any obvious conflicts in the free extent. */
@ -210,7 +209,7 @@ xrep_abt_stash(
if (error)
return error;
trace_xrep_abt_found(sc->mp, sc->sa.pag->pag_agno, &arec);
trace_xrep_abt_found(sc->sa.pag, &arec);
error = xfarray_append(ra->free_records, &arec);
if (error)
@ -484,8 +483,8 @@ xrep_abt_reserve_space(
ASSERT(arec.ar_blockcount <= UINT_MAX);
len = min_t(unsigned int, arec.ar_blockcount, desired);
trace_xrep_newbt_alloc_ag_blocks(sc->mp, sc->sa.pag->pag_agno,
arec.ar_startblock, len, XFS_RMAP_OWN_AG);
trace_xrep_newbt_alloc_ag_blocks(sc->sa.pag, arec.ar_startblock,
len, XFS_RMAP_OWN_AG);
error = xrep_newbt_add_extent(&ra->new_bnobt, sc->sa.pag,
arec.ar_startblock, len);
@ -543,7 +542,7 @@ xrep_abt_dispose_one(
/* Add a deferred rmap for each extent we used. */
if (resv->used > 0)
xfs_rmap_alloc_extent(sc->tp, pag->pag_agno, resv->agbno,
xfs_rmap_alloc_extent(sc->tp, pag_agno(pag), resv->agbno,
resv->used, XFS_RMAP_OWN_AG);
/*
@ -554,8 +553,8 @@ xrep_abt_dispose_one(
if (free_aglen == 0)
return 0;
trace_xrep_newbt_free_blocks(sc->mp, resv->pag->pag_agno, free_agbno,
free_aglen, ra->new_bnobt.oinfo.oi_owner);
trace_xrep_newbt_free_blocks(resv->pag, free_agbno, free_aglen,
ra->new_bnobt.oinfo.oi_owner);
error = __xfs_free_extent(sc->tp, resv->pag, free_agbno, free_aglen,
&ra->new_bnobt.oinfo, XFS_AG_RESV_IGNORE, true);
@ -849,6 +848,7 @@ xrep_allocbt(
{
struct xrep_abt *ra;
struct xfs_mount *mp = sc->mp;
unsigned int busy_gen;
char *descr;
int error;
@ -869,7 +869,7 @@ xrep_allocbt(
* on there twice. In theory we cleared this before we started, but
* let's not risk the filesystem.
*/
if (!xfs_extent_busy_list_empty(sc->sa.pag)) {
if (!xfs_extent_busy_list_empty(pag_group(sc->sa.pag), &busy_gen)) {
error = -EDEADLOCK;
goto out_ra;
}

38
fs/xfs/scrub/bmap.c
View File

@ -19,6 +19,7 @@
#include "xfs_bmap_btree.h"
#include "xfs_rmap.h"
#include "xfs_rmap_btree.h"
#include "xfs_rtgroup.h"
#include "xfs_health.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
@ -314,8 +315,20 @@ xchk_bmap_rt_iextent_xref(
struct xchk_bmap_info *info,
struct xfs_bmbt_irec *irec)
{
int error;
error = xchk_rtgroup_init_existing(info->sc,
xfs_rtb_to_rgno(ip->i_mount, irec->br_startblock),
&info->sc->sr);
if (!xchk_fblock_process_error(info->sc, info->whichfork,
irec->br_startoff, &error))
return;
xchk_rtgroup_lock(&info->sc->sr, XCHK_RTGLOCK_ALL);
xchk_xref_is_used_rt_space(info->sc, irec->br_startblock,
irec->br_blockcount);
xchk_rtgroup_free(info->sc, &info->sc->sr);
}
/* Cross-reference a single datadev extent record. */
@ -600,8 +613,8 @@ xchk_bmap_check_rmap(
if (irec.br_startoff != check_rec.rm_offset)
xchk_fblock_set_corrupt(sc, sbcri->whichfork,
check_rec.rm_offset);
if (irec.br_startblock != XFS_AGB_TO_FSB(sc->mp,
cur->bc_ag.pag->pag_agno,
if (irec.br_startblock !=
xfs_agbno_to_fsb(to_perag(cur->bc_group),
check_rec.rm_startblock))
xchk_fblock_set_corrupt(sc, sbcri->whichfork,
check_rec.rm_offset);
@ -761,11 +774,10 @@ xchk_bmap_check_rmaps(
struct xfs_scrub *sc,
int whichfork)
{
struct xfs_perag *pag;
xfs_agnumber_t agno;
struct xfs_perag *pag = NULL;
int error;
for_each_perag(sc->mp, agno, pag) {
while ((pag = xfs_perag_next(sc->mp, pag))) {
error = xchk_bmap_check_ag_rmaps(sc, whichfork, pag);
if (error ||
(sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) {
@ -822,9 +834,12 @@ xchk_bmap_iext_mapping(
/* Are these two mappings contiguous with each other? */
static inline bool
xchk_are_bmaps_contiguous(
const struct xchk_bmap_info *info,
const struct xfs_bmbt_irec *b1,
const struct xfs_bmbt_irec *b2)
{
struct xfs_mount *mp = info->sc->mp;
/* Don't try to combine unallocated mappings. */
if (!xfs_bmap_is_real_extent(b1))
return false;
@ -838,6 +853,17 @@ xchk_are_bmaps_contiguous(
return false;
if (b1->br_state != b2->br_state)
return false;
/*
* Don't combine bmaps that would cross rtgroup boundaries. This is a
* valid state, but if combined they will fail rtb extent checks.
*/
if (info->is_rt && xfs_has_rtgroups(mp)) {
if (xfs_rtb_to_rgno(mp, b1->br_startblock) !=
xfs_rtb_to_rgno(mp, b2->br_startblock))
return false;
}
return true;
}
@ -875,7 +901,7 @@ xchk_bmap_iext_iter(
* that we just read, if possible.
*/
while (xfs_iext_peek_next_extent(ifp, &info->icur, &got)) {
if (!xchk_are_bmaps_contiguous(irec, &got))
if (!xchk_are_bmaps_contiguous(info, irec, &got))
break;
if (!xchk_bmap_iext_mapping(info, &got)) {

11
fs/xfs/scrub/bmap_repair.c
View File

@ -196,7 +196,7 @@ xrep_bmap_check_fork_rmap(
return -EFSCORRUPTED;
/* Check that this is within the AG. */
if (!xfs_verify_agbext(cur->bc_ag.pag, rec->rm_startblock,
if (!xfs_verify_agbext(to_perag(cur->bc_group), rec->rm_startblock,
rec->rm_blockcount))
return -EFSCORRUPTED;
@ -237,7 +237,6 @@ xrep_bmap_walk_rmap(
void *priv)
{
struct xrep_bmap *rb = priv;
struct xfs_mount *mp = cur->bc_mp;
xfs_fsblock_t fsbno;
int error = 0;
@ -269,8 +268,7 @@ xrep_bmap_walk_rmap(
if ((rec->rm_flags & XFS_RMAP_UNWRITTEN) && !rb->allow_unwritten)
return -EFSCORRUPTED;
fsbno = XFS_AGB_TO_FSB(mp, cur->bc_ag.pag->pag_agno,
rec->rm_startblock);
fsbno = xfs_agbno_to_fsb(to_perag(cur->bc_group), rec->rm_startblock);
if (rec->rm_flags & XFS_RMAP_BMBT_BLOCK) {
rb->old_bmbt_block_count += rec->rm_blockcount;
@ -409,12 +407,11 @@ xrep_bmap_find_mappings(
struct xrep_bmap *rb)
{
struct xfs_scrub *sc = rb->sc;
struct xfs_perag *pag;
xfs_agnumber_t agno;
struct xfs_perag *pag = NULL;
int error = 0;
/* Iterate the rmaps for extents. */
for_each_perag(sc->mp, agno, pag) {
while ((pag = xfs_perag_next(sc->mp, pag))) {
error = xrep_bmap_scan_ag(rb, pag);
if (error) {
xfs_perag_rele(pag);

149
fs/xfs/scrub/common.c
View File

@ -34,11 +34,13 @@
#include "xfs_quota.h"
#include "xfs_exchmaps.h"
#include "xfs_rtbitmap.h"
#include "xfs_rtgroup.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/trace.h"
#include "scrub/repair.h"
#include "scrub/health.h"
#include "scrub/tempfile.h"
/* Common code for the metadata scrubbers. */
@ -120,6 +122,17 @@ xchk_process_error(
XFS_SCRUB_OFLAG_CORRUPT, __return_address);
}
bool
xchk_process_rt_error(
struct xfs_scrub *sc,
xfs_rgnumber_t rgno,
xfs_rgblock_t rgbno,
int *error)
{
return __xchk_process_error(sc, rgno, rgbno, error,
XFS_SCRUB_OFLAG_CORRUPT, __return_address);
}
bool
xchk_xref_process_error(
struct xfs_scrub *sc,
@ -513,7 +526,7 @@ xchk_perag_drain_and_lock(
* Obviously, this should be slanted against scrub and in favor
* of runtime threads.
*/
if (!xfs_perag_intent_busy(sa->pag))
if (!xfs_group_intent_busy(pag_group(sa->pag)))
return 0;
if (sa->agf_bp) {
@ -528,7 +541,7 @@ xchk_perag_drain_and_lock(
if (!(sc->flags & XCHK_FSGATES_DRAIN))
return -ECHRNG;
error = xfs_perag_intent_drain(sa->pag);
error = xfs_group_intent_drain(pag_group(sa->pag));
if (error == -ERESTARTSYS)
error = -EINTR;
} while (!error);
@ -683,6 +696,72 @@ xchk_ag_init(
return 0;
}
#ifdef CONFIG_XFS_RT
/*
* For scrubbing a realtime group, grab all the in-core resources we'll need to
* check the metadata, which means taking the ILOCK of the realtime group's
* metadata inodes. Callers must not join these inodes to the transaction with
* non-zero lockflags or concurrency problems will result. The @rtglock_flags
* argument takes XFS_RTGLOCK_* flags.
*/
int
xchk_rtgroup_init(
struct xfs_scrub *sc,
xfs_rgnumber_t rgno,
struct xchk_rt *sr)
{
ASSERT(sr->rtg == NULL);
ASSERT(sr->rtlock_flags == 0);
sr->rtg = xfs_rtgroup_get(sc->mp, rgno);
if (!sr->rtg)
return -ENOENT;
return 0;
}
void
xchk_rtgroup_lock(
struct xchk_rt *sr,
unsigned int rtglock_flags)
{
xfs_rtgroup_lock(sr->rtg, rtglock_flags);
sr->rtlock_flags = rtglock_flags;
}
/*
* Unlock the realtime group. This must be done /after/ committing (or
* cancelling) the scrub transaction.
*/
static void
xchk_rtgroup_unlock(
struct xchk_rt *sr)
{
ASSERT(sr->rtg != NULL);
if (sr->rtlock_flags) {
xfs_rtgroup_unlock(sr->rtg, sr->rtlock_flags);
sr->rtlock_flags = 0;
}
}
/*
* Unlock the realtime group and release its resources. This must be done
* /after/ committing (or cancelling) the scrub transaction.
*/
void
xchk_rtgroup_free(
struct xfs_scrub *sc,
struct xchk_rt *sr)
{
ASSERT(sr->rtg != NULL);
xchk_rtgroup_unlock(sr);
xfs_rtgroup_put(sr->rtg);
sr->rtg = NULL;
}
#endif /* CONFIG_XFS_RT */
/* Per-scrubber setup functions */
void
@ -947,9 +1026,15 @@ xchk_iget_for_scrubbing(
if (sc->sm->sm_ino == 0 || sc->sm->sm_ino == ip_in->i_ino)
return xchk_install_live_inode(sc, ip_in);
/* Reject internal metadata files and obviously bad inode numbers. */
if (xfs_internal_inum(mp, sc->sm->sm_ino))
/*
* On pre-metadir filesystems, reject internal metadata files. For
* metadir filesystems, limited scrubbing of any file in the metadata
* directory tree by handle is allowed, because that is the only way to
* validate the lack of parent pointers in the sb-root metadata inodes.
*/
if (!xfs_has_metadir(mp) && xfs_is_sb_inum(mp, sc->sm->sm_ino))
return -ENOENT;
/* Reject obviously bad inode numbers. */
if (!xfs_verify_ino(sc->mp, sc->sm->sm_ino))
return -ENOENT;
@ -1084,6 +1169,10 @@ xchk_setup_inode_contents(
if (error)
return error;
error = xrep_tempfile_adjust_directory_tree(sc);
if (error)
return error;
/* Lock the inode so the VFS cannot touch this file. */
xchk_ilock(sc, XFS_IOLOCK_EXCL);
@ -1239,12 +1328,6 @@ xchk_metadata_inode_forks(
return 0;
}
/* They also should never have extended attributes. */
if (xfs_inode_hasattr(sc->ip)) {
xchk_ino_set_corrupt(sc, sc->ip->i_ino);
return 0;
}
/* Invoke the data fork scrubber. */
error = xchk_metadata_inode_subtype(sc, XFS_SCRUB_TYPE_BMBTD);
if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
@ -1261,6 +1344,21 @@ xchk_metadata_inode_forks(
xchk_ino_set_corrupt(sc, sc->ip->i_ino);
}
/*
* Metadata files can only have extended attributes on metadir
* filesystems, either for parent pointers or for actual xattr data.
*/
if (xfs_inode_hasattr(sc->ip)) {
if (!xfs_has_metadir(sc->mp)) {
xchk_ino_set_corrupt(sc, sc->ip->i_ino);
return 0;
}
error = xchk_metadata_inode_subtype(sc, XFS_SCRUB_TYPE_BMBTA);
if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
return error;
}
return 0;
}
@ -1336,7 +1434,7 @@ xchk_inode_is_allocated(
}
/* reject inode numbers outside existing AGs */
ino = XFS_AGINO_TO_INO(sc->mp, pag->pag_agno, agino);
ino = xfs_agino_to_ino(pag, agino);
if (!xfs_verify_ino(mp, ino))
return -EINVAL;
@ -1446,3 +1544,32 @@ xchk_inode_is_allocated(
rcu_read_unlock();
return error;
}
/* Is this inode a root directory for either tree? */
bool
xchk_inode_is_dirtree_root(const struct xfs_inode *ip)
{
struct xfs_mount *mp = ip->i_mount;
return ip == mp->m_rootip ||
(xfs_has_metadir(mp) && ip == mp->m_metadirip);
}
/* Does the superblock point down to this inode? */
bool
xchk_inode_is_sb_rooted(const struct xfs_inode *ip)
{
return xchk_inode_is_dirtree_root(ip) ||
xfs_is_sb_inum(ip->i_mount, ip->i_ino);
}
/* What is the root directory inumber for this inode? */
xfs_ino_t
xchk_inode_rootdir_inum(const struct xfs_inode *ip)
{
struct xfs_mount *mp = ip->i_mount;
if (xfs_is_metadir_inode(ip))
return mp->m_metadirip->i_ino;
return mp->m_rootip->i_ino;
}

40
fs/xfs/scrub/common.h
View File

@ -12,6 +12,8 @@ void xchk_trans_cancel(struct xfs_scrub *sc);
bool xchk_process_error(struct xfs_scrub *sc, xfs_agnumber_t agno,
xfs_agblock_t bno, int *error);
bool xchk_process_rt_error(struct xfs_scrub *sc, xfs_rgnumber_t rgno,
xfs_rgblock_t rgbno, int *error);
bool xchk_fblock_process_error(struct xfs_scrub *sc, int whichfork,
xfs_fileoff_t offset, int *error);
@ -73,12 +75,15 @@ int xchk_setup_xattr(struct xfs_scrub *sc);
int xchk_setup_symlink(struct xfs_scrub *sc);
int xchk_setup_parent(struct xfs_scrub *sc);
int xchk_setup_dirtree(struct xfs_scrub *sc);
int xchk_setup_metapath(struct xfs_scrub *sc);
#ifdef CONFIG_XFS_RT
int xchk_setup_rtbitmap(struct xfs_scrub *sc);
int xchk_setup_rtsummary(struct xfs_scrub *sc);
int xchk_setup_rgsuperblock(struct xfs_scrub *sc);
#else
# define xchk_setup_rtbitmap xchk_setup_nothing
# define xchk_setup_rtsummary xchk_setup_nothing
# define xchk_setup_rgsuperblock xchk_setup_nothing
#endif
#ifdef CONFIG_XFS_QUOTA
int xchk_ino_dqattach(struct xfs_scrub *sc);
@ -117,6 +122,34 @@ xchk_ag_init_existing(
return error == -ENOENT ? -EFSCORRUPTED : error;
}
#ifdef CONFIG_XFS_RT
/* All the locks we need to check an rtgroup. */
#define XCHK_RTGLOCK_ALL (XFS_RTGLOCK_BITMAP)
int xchk_rtgroup_init(struct xfs_scrub *sc, xfs_rgnumber_t rgno,
struct xchk_rt *sr);
static inline int
xchk_rtgroup_init_existing(
struct xfs_scrub *sc,
xfs_rgnumber_t rgno,
struct xchk_rt *sr)
{
int error = xchk_rtgroup_init(sc, rgno, sr);
return error == -ENOENT ? -EFSCORRUPTED : error;
}
void xchk_rtgroup_lock(struct xchk_rt *sr, unsigned int rtglock_flags);
void xchk_rtgroup_free(struct xfs_scrub *sc, struct xchk_rt *sr);
#else
# define xchk_rtgroup_init(sc, rgno, sr) (-EFSCORRUPTED)
# define xchk_rtgroup_init_existing(sc, rgno, sr) (-EFSCORRUPTED)
# define xchk_rtgroup_lock(sc, lockflags) do { } while (0)
# define xchk_rtgroup_free(sc, sr) do { } while (0)
#endif /* CONFIG_XFS_RT */
int xchk_ag_read_headers(struct xfs_scrub *sc, xfs_agnumber_t agno,
struct xchk_ag *sa);
void xchk_ag_btcur_free(struct xchk_ag *sa);
@ -216,7 +249,8 @@ int xchk_metadata_inode_forks(struct xfs_scrub *sc);
#define xchk_xfile_ag_descr(sc, fmt, ...) \
kasprintf(XCHK_GFP_FLAGS, "XFS (%s): AG 0x%x " fmt, \
(sc)->mp->m_super->s_id, \
(sc)->sa.pag ? (sc)->sa.pag->pag_agno : (sc)->sm->sm_agno, \
(sc)->sa.pag ? \
pag_agno((sc)->sa.pag) : (sc)->sm->sm_agno, \
##__VA_ARGS__)
#define xchk_xfile_ino_descr(sc, fmt, ...) \
kasprintf(XCHK_GFP_FLAGS, "XFS (%s): inode 0x%llx " fmt, \
@ -241,4 +275,8 @@ void xchk_fsgates_enable(struct xfs_scrub *sc, unsigned int scrub_fshooks);
int xchk_inode_is_allocated(struct xfs_scrub *sc, xfs_agino_t agino,
bool *inuse);
bool xchk_inode_is_dirtree_root(const struct xfs_inode *ip);
bool xchk_inode_is_sb_rooted(const struct xfs_inode *ip);
xfs_ino_t xchk_inode_rootdir_inum(const struct xfs_inode *ip);
#endif /* __XFS_SCRUB_COMMON_H__ */

21
fs/xfs/scrub/cow_repair.c
View File

@ -137,7 +137,6 @@ xrep_cow_mark_shared_staging(
{
struct xrep_cow *xc = priv;
struct xfs_refcount_irec rrec;
xfs_fsblock_t fsbno;
if (!xfs_refcount_check_domain(rec) ||
rec->rc_domain != XFS_REFC_DOMAIN_SHARED)
@ -145,9 +144,10 @@ xrep_cow_mark_shared_staging(
xrep_cow_trim_refcount(xc, &rrec, rec);
fsbno = XFS_AGB_TO_FSB(xc->sc->mp, cur->bc_ag.pag->pag_agno,
rrec.rc_startblock);
return xrep_cow_mark_file_range(xc, fsbno, rrec.rc_blockcount);
return xrep_cow_mark_file_range(xc,
xfs_agbno_to_fsb(to_perag(cur->bc_group),
rrec.rc_startblock),
rrec.rc_blockcount);
}
/*
@ -177,9 +177,9 @@ xrep_cow_mark_missing_staging(
if (xc->next_bno >= rrec.rc_startblock)
goto next;
error = xrep_cow_mark_file_range(xc,
XFS_AGB_TO_FSB(xc->sc->mp, cur->bc_ag.pag->pag_agno,
xc->next_bno),
xfs_agbno_to_fsb(to_perag(cur->bc_group), xc->next_bno),
rrec.rc_startblock - xc->next_bno);
if (error)
return error;
@ -200,7 +200,6 @@ xrep_cow_mark_missing_staging_rmap(
void *priv)
{
struct xrep_cow *xc = priv;
xfs_fsblock_t fsbno;
xfs_agblock_t rec_bno;
xfs_extlen_t rec_len;
unsigned int adj;
@ -222,8 +221,9 @@ xrep_cow_mark_missing_staging_rmap(
rec_len -= adj;
}
fsbno = XFS_AGB_TO_FSB(xc->sc->mp, cur->bc_ag.pag->pag_agno, rec_bno);
return xrep_cow_mark_file_range(xc, fsbno, rec_len);
return xrep_cow_mark_file_range(xc,
xfs_agbno_to_fsb(to_perag(cur->bc_group), rec_bno),
rec_len);
}
/*
@ -275,8 +275,7 @@ xrep_cow_find_bad(
if (xc->next_bno < xc->irec_startbno + xc->irec.br_blockcount) {
error = xrep_cow_mark_file_range(xc,
XFS_AGB_TO_FSB(sc->mp, pag->pag_agno,
xc->next_bno),
xfs_agbno_to_fsb(pag, xc->next_bno),
xc->irec_startbno + xc->irec.br_blockcount -
xc->next_bno);
if (error)

10
fs/xfs/scrub/dir.c
View File

@ -100,6 +100,14 @@ xchk_dir_check_ftype(
if (xfs_mode_to_ftype(VFS_I(ip)->i_mode) != ftype)
xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
/*
* Metadata and regular inodes cannot cross trees. This property
* cannot change without a full inode free and realloc cycle, so it's
* safe to check this without holding locks.
*/
if (xfs_is_metadir_inode(ip) != xfs_is_metadir_inode(sc->ip))
xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
}
/*
@ -253,7 +261,7 @@ xchk_dir_actor(
* If this is ".." in the root inode, check that the inum
* matches this dir.
*/
if (dp->i_ino == mp->m_sb.sb_rootino && ino != dp->i_ino)
if (xchk_inode_is_dirtree_root(dp) && ino != dp->i_ino)
xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
}

20
fs/xfs/scrub/dir_repair.c
View File

@ -415,6 +415,12 @@ xrep_dir_salvage_entry(
if (error)
return 0;
/* Don't mix metadata and regular directory trees. */
if (xfs_is_metadir_inode(ip) != xfs_is_metadir_inode(rd->sc->ip)) {
xchk_irele(sc, ip);
return 0;
}
xname.type = xfs_mode_to_ftype(VFS_I(ip)->i_mode);
xchk_irele(sc, ip);
@ -1270,7 +1276,7 @@ xrep_dir_scan_dirtree(
int error;
/* Roots of directory trees are their own parents. */
if (sc->ip == sc->mp->m_rootip)
if (xchk_inode_is_dirtree_root(sc->ip))
xrep_findparent_scan_found(&rd->pscan, sc->ip->i_ino);
/*
@ -1632,6 +1638,7 @@ xrep_dir_swap(
struct xrep_dir *rd)
{
struct xfs_scrub *sc = rd->sc;
xfs_ino_t ino;
bool ip_local, temp_local;
int error = 0;
@ -1649,14 +1656,17 @@ xrep_dir_swap(
/*
* Reset the temporary directory's '..' entry to point to the parent
* that we found. The temporary directory was created with the root
* directory as the parent, so we can skip this if repairing a
* subdirectory of the root.
* that we found. The dirent replace code asserts if the dirent
* already points at the new inumber, so we look it up here.
*
* It's also possible that this replacement could also expand a sf
* tempdir into block format.
*/
if (rd->pscan.parent_ino != sc->mp->m_rootip->i_ino) {
error = xchk_dir_lookup(sc, rd->sc->tempip, &xfs_name_dotdot, &ino);
if (error)
return error;
if (rd->pscan.parent_ino != ino) {
error = xrep_dir_replace(rd, rd->sc->tempip, &xfs_name_dotdot,
rd->pscan.parent_ino, rd->tx.req.resblks);
if (error)

32
fs/xfs/scrub/dirtree.c
View File

@ -362,7 +362,8 @@ xchk_dirpath_set_outcome(
STATIC int
xchk_dirpath_step_up(
struct xchk_dirtree *dl,
struct xchk_dirpath *path)
struct xchk_dirpath *path,
bool is_metadir)
{
struct xfs_scrub *sc = dl->sc;
struct xfs_inode *dp;
@ -435,6 +436,14 @@ xchk_dirpath_step_up(
goto out_scanlock;
}
/* Parent must be in the same directory tree. */
if (is_metadir != xfs_is_metadir_inode(dp)) {
trace_xchk_dirpath_crosses_tree(dl->sc, dp, path->path_nr,
path->nr_steps, &dl->xname, &dl->pptr_rec);
error = -EFSCORRUPTED;
goto out_scanlock;
}
/*
* If the extended attributes look as though they has been zapped by
* the inode record repair code, we cannot scan for parent pointers.
@ -508,6 +517,7 @@ xchk_dirpath_walk_upwards(
struct xchk_dirpath *path)
{
struct xfs_scrub *sc = dl->sc;
bool is_metadir;
int error;
ASSERT(sc->ilock_flags & XFS_ILOCK_EXCL);
@ -538,6 +548,7 @@ xchk_dirpath_walk_upwards(
* ILOCK state is no longer tracked in the scrub context. Hence we
* must drop @sc->ip's ILOCK during the walk.
*/
is_metadir = xfs_is_metadir_inode(sc->ip);
mutex_unlock(&dl->lock);
xchk_iunlock(sc, XFS_ILOCK_EXCL);
@ -547,7 +558,7 @@ xchk_dirpath_walk_upwards(
* If we see any kind of error here (including corruptions), the parent
* pointer of @sc->ip is corrupt. Stop the whole scan.
*/
error = xchk_dirpath_step_up(dl, path);
error = xchk_dirpath_step_up(dl, path, is_metadir);
if (error) {
xchk_ilock(sc, XFS_ILOCK_EXCL);
mutex_lock(&dl->lock);
@ -560,7 +571,7 @@ xchk_dirpath_walk_upwards(
* *somewhere* in the path, but we don't need to stop scanning.
*/
while (!error && path->outcome == XCHK_DIRPATH_SCANNING)
error = xchk_dirpath_step_up(dl, path);
error = xchk_dirpath_step_up(dl, path, is_metadir);
/* Retake the locks we had, mark paths, etc. */
xchk_ilock(sc, XFS_ILOCK_EXCL);
@ -917,7 +928,7 @@ xchk_dirtree(
* scan, because the hook doesn't detach until after sc->ip gets
* released during teardown.
*/
dl->root_ino = sc->mp->m_rootip->i_ino;
dl->root_ino = xchk_inode_rootdir_inum(sc->ip);
dl->scan_ino = sc->ip->i_ino;
trace_xchk_dirtree_start(sc->ip, sc->sm, 0);
@ -983,3 +994,16 @@ xchk_dirtree(
trace_xchk_dirtree_done(sc->ip, sc->sm, error);
return error;
}
/* Does the directory targetted by this scrub have no parents? */
bool
xchk_dirtree_parentless(const struct xchk_dirtree *dl)
{
struct xfs_scrub *sc = dl->sc;
if (xchk_inode_is_dirtree_root(sc->ip))
return true;
if (VFS_I(sc->ip)->i_nlink == 0)
return true;
return false;
}

12
fs/xfs/scrub/dirtree.h
View File

@ -156,17 +156,7 @@ struct xchk_dirtree {
#define xchk_dirtree_for_each_path(dl, path) \
list_for_each_entry((path), &(dl)->path_list, list)
static inline bool
xchk_dirtree_parentless(const struct xchk_dirtree *dl)
{
struct xfs_scrub *sc = dl->sc;
if (sc->ip == sc->mp->m_rootip)
return true;
if (VFS_I(sc->ip)->i_nlink == 0)
return true;
return false;
}
bool xchk_dirtree_parentless(const struct xchk_dirtree *dl);
int xchk_dirtree_find_paths_to_root(struct xchk_dirtree *dl);
int xchk_dirpath_append(struct xchk_dirtree *dl, struct xfs_inode *ip,

28
fs/xfs/scrub/findparent.c
View File

@ -172,6 +172,10 @@ xrep_findparent_walk_directory(
*/
lock_mode = xfs_ilock_data_map_shared(dp);
/* Don't mix metadata and regular directory trees. */
if (xfs_is_metadir_inode(dp) != xfs_is_metadir_inode(sc->ip))
goto out_unlock;
/*
* If this directory is known to be sick, we cannot scan it reliably
* and must abort.
@ -362,15 +366,24 @@ xrep_findparent_confirm(
};
int error;
/*
* The root directory always points to itself. Unlinked dirs can point
* anywhere, so we point them at the root dir too.
*/
if (sc->ip == sc->mp->m_rootip || VFS_I(sc->ip)->i_nlink == 0) {
/* The root directory always points to itself. */
if (sc->ip == sc->mp->m_rootip) {
*parent_ino = sc->mp->m_sb.sb_rootino;
return 0;
}
/* The metadata root directory always points to itself. */
if (sc->ip == sc->mp->m_metadirip) {
*parent_ino = sc->mp->m_sb.sb_metadirino;
return 0;
}
/* Unlinked dirs can point anywhere; point them up to the root dir. */
if (VFS_I(sc->ip)->i_nlink == 0) {
*parent_ino = xchk_inode_rootdir_inum(sc->ip);
return 0;
}
/* Reject garbage parent inode numbers and self-referential parents. */
if (*parent_ino == NULLFSINO)
return 0;
@ -412,8 +425,11 @@ xrep_findparent_self_reference(
if (sc->ip->i_ino == sc->mp->m_sb.sb_rootino)
return sc->mp->m_sb.sb_rootino;
if (sc->ip->i_ino == sc->mp->m_sb.sb_metadirino)
return sc->mp->m_sb.sb_metadirino;
if (VFS_I(sc->ip)->i_nlink == 0)
return sc->mp->m_sb.sb_rootino;
return xchk_inode_rootdir_inum(sc->ip);
return NULLFSINO;
}

29
fs/xfs/scrub/fscounters.c
View File

@ -19,6 +19,7 @@
#include "xfs_rtbitmap.h"
#include "xfs_inode.h"
#include "xfs_icache.h"
#include "xfs_rtgroup.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/trace.h"
@ -74,10 +75,9 @@ xchk_fscount_warmup(
struct xfs_buf *agi_bp = NULL;
struct xfs_buf *agf_bp = NULL;
struct xfs_perag *pag = NULL;
xfs_agnumber_t agno;
int error = 0;
for_each_perag(mp, agno, pag) {
while ((pag = xfs_perag_next(mp, pag))) {
if (xchk_should_terminate(sc, &error))
break;
if (xfs_perag_initialised_agi(pag) &&
@ -295,9 +295,8 @@ xchk_fscount_aggregate_agcounts(
struct xchk_fscounters *fsc)
{
struct xfs_mount *mp = sc->mp;
struct xfs_perag *pag;
struct xfs_perag *pag = NULL;
uint64_t delayed;
xfs_agnumber_t agno;
int tries = 8;
int error = 0;
@ -306,7 +305,7 @@ xchk_fscount_aggregate_agcounts(
fsc->ifree = 0;
fsc->fdblocks = 0;
for_each_perag(mp, agno, pag) {
while ((pag = xfs_perag_next(mp, pag))) {
if (xchk_should_terminate(sc, &error))
break;
@ -327,7 +326,7 @@ xchk_fscount_aggregate_agcounts(
if (xfs_has_lazysbcount(sc->mp)) {
fsc->fdblocks += pag->pagf_btreeblks;
} else {
error = xchk_fscount_btreeblks(sc, fsc, agno);
error = xchk_fscount_btreeblks(sc, fsc, pag_agno(pag));
if (error)
break;
}
@ -388,7 +387,7 @@ xchk_fscount_aggregate_agcounts(
#ifdef CONFIG_XFS_RT
STATIC int
xchk_fscount_add_frextent(
struct xfs_mount *mp,
struct xfs_rtgroup *rtg,
struct xfs_trans *tp,
const struct xfs_rtalloc_rec *rec,
void *priv)
@ -409,6 +408,7 @@ xchk_fscount_count_frextents(
struct xchk_fscounters *fsc)
{
struct xfs_mount *mp = sc->mp;
struct xfs_rtgroup *rtg = NULL;
int error;
fsc->frextents = 0;
@ -416,19 +416,20 @@ xchk_fscount_count_frextents(
if (!xfs_has_realtime(mp))
return 0;
xfs_rtbitmap_lock_shared(sc->mp, XFS_RBMLOCK_BITMAP);
error = xfs_rtalloc_query_all(sc->mp, sc->tp,
while ((rtg = xfs_rtgroup_next(mp, rtg))) {
xfs_rtgroup_lock(rtg, XFS_RTGLOCK_BITMAP_SHARED);
error = xfs_rtalloc_query_all(rtg, sc->tp,
xchk_fscount_add_frextent, fsc);
xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_BITMAP_SHARED);
if (error) {
xchk_set_incomplete(sc);
goto out_unlock;
xfs_rtgroup_rele(rtg);
return error;
}
}
fsc->frextents_delayed = percpu_counter_sum(&mp->m_delalloc_rtextents);
out_unlock:
xfs_rtbitmap_unlock_shared(sc->mp, XFS_RBMLOCK_BITMAP);
return error;
return 0;
}
#else
STATIC int

7
fs/xfs/scrub/fscounters_repair.c
View File

@ -68,14 +68,15 @@ xrep_fscounters(
/*
* Online repair is only supported on v5 file systems, which require
* lazy sb counters and thus no update of sb_fdblocks here. But as of
* now we don't support lazy counting sb_frextents yet, and thus need
* to also update it directly here. And for that we need to keep
* lazy sb counters and thus no update of sb_fdblocks here. But
* sb_frextents only uses a lazy counter with rtgroups, and thus needs
* to be updated directly here otherwise. And for that we need to keep
* track of the delalloc reservations separately, as they are are
* subtracted from m_frextents, but not included in sb_frextents.
*/
percpu_counter_set(&mp->m_frextents,
fsc->frextents - fsc->frextents_delayed);
if (!xfs_has_rtgroups(mp))
mp->m_sb.sb_frextents = fsc->frextents;
return 0;

54
fs/xfs/scrub/health.c
View File

@ -12,6 +12,7 @@
#include "xfs_btree.h"
#include "xfs_ag.h"
#include "xfs_health.h"
#include "xfs_rtgroup.h"
#include "scrub/scrub.h"
#include "scrub/health.h"
#include "scrub/common.h"
@ -71,9 +72,9 @@
enum xchk_health_group {
XHG_FS = 1,
XHG_RT,
XHG_AG,
XHG_INO,
XHG_RTGROUP,
};
struct xchk_health_map {
@ -100,8 +101,8 @@ static const struct xchk_health_map type_to_health_flag[XFS_SCRUB_TYPE_NR] = {
[XFS_SCRUB_TYPE_XATTR] = { XHG_INO, XFS_SICK_INO_XATTR },
[XFS_SCRUB_TYPE_SYMLINK] = { XHG_INO, XFS_SICK_INO_SYMLINK },
[XFS_SCRUB_TYPE_PARENT] = { XHG_INO, XFS_SICK_INO_PARENT },
[XFS_SCRUB_TYPE_RTBITMAP] = { XHG_RT, XFS_SICK_RT_BITMAP },
[XFS_SCRUB_TYPE_RTSUM] = { XHG_RT, XFS_SICK_RT_SUMMARY },
[XFS_SCRUB_TYPE_RTBITMAP] = { XHG_RTGROUP, XFS_SICK_RG_BITMAP },
[XFS_SCRUB_TYPE_RTSUM] = { XHG_RTGROUP, XFS_SICK_RG_SUMMARY },
[XFS_SCRUB_TYPE_UQUOTA] = { XHG_FS, XFS_SICK_FS_UQUOTA },
[XFS_SCRUB_TYPE_GQUOTA] = { XHG_FS, XFS_SICK_FS_GQUOTA },
[XFS_SCRUB_TYPE_PQUOTA] = { XHG_FS, XFS_SICK_FS_PQUOTA },
@ -109,6 +110,8 @@ static const struct xchk_health_map type_to_health_flag[XFS_SCRUB_TYPE_NR] = {
[XFS_SCRUB_TYPE_QUOTACHECK] = { XHG_FS, XFS_SICK_FS_QUOTACHECK },
[XFS_SCRUB_TYPE_NLINKS] = { XHG_FS, XFS_SICK_FS_NLINKS },
[XFS_SCRUB_TYPE_DIRTREE] = { XHG_INO, XFS_SICK_INO_DIRTREE },
[XFS_SCRUB_TYPE_METAPATH] = { XHG_FS, XFS_SICK_FS_METAPATH },
[XFS_SCRUB_TYPE_RGSUPER] = { XHG_RTGROUP, XFS_SICK_RG_SUPER },
};
/* Return the health status mask for this scrub type. */
@ -160,13 +163,14 @@ STATIC void
xchk_mark_all_healthy(
struct xfs_mount *mp)
{
struct xfs_perag *pag;
xfs_agnumber_t agno;
struct xfs_perag *pag = NULL;
struct xfs_rtgroup *rtg = NULL;
xfs_fs_mark_healthy(mp, XFS_SICK_FS_INDIRECT);
xfs_rt_mark_healthy(mp, XFS_SICK_RT_INDIRECT);
for_each_perag(mp, agno, pag)
xfs_ag_mark_healthy(pag, XFS_SICK_AG_INDIRECT);
while ((pag = xfs_perag_next(mp, pag)))
xfs_group_mark_healthy(pag_group(pag), XFS_SICK_AG_INDIRECT);
while ((rtg = xfs_rtgroup_next(mp, rtg)))
xfs_group_mark_healthy(rtg_group(rtg), XFS_SICK_RG_INDIRECT);
}
/*
@ -184,6 +188,7 @@ xchk_update_health(
struct xfs_scrub *sc)
{
struct xfs_perag *pag;
struct xfs_rtgroup *rtg;
bool bad;
/*
@ -207,9 +212,9 @@ xchk_update_health(
case XHG_AG:
pag = xfs_perag_get(sc->mp, sc->sm->sm_agno);
if (bad)
xfs_ag_mark_corrupt(pag, sc->sick_mask);
xfs_group_mark_corrupt(pag_group(pag), sc->sick_mask);
else
xfs_ag_mark_healthy(pag, sc->sick_mask);
xfs_group_mark_healthy(pag_group(pag), sc->sick_mask);
xfs_perag_put(pag);
break;
case XHG_INO:
@ -236,11 +241,13 @@ xchk_update_health(
else
xfs_fs_mark_healthy(sc->mp, sc->sick_mask);
break;
case XHG_RT:
case XHG_RTGROUP:
rtg = xfs_rtgroup_get(sc->mp, sc->sm->sm_agno);
if (bad)
xfs_rt_mark_corrupt(sc->mp, sc->sick_mask);
xfs_group_mark_corrupt(rtg_group(rtg), sc->sick_mask);
else
xfs_rt_mark_healthy(sc->mp, sc->sick_mask);
xfs_group_mark_healthy(rtg_group(rtg), sc->sick_mask);
xfs_rtgroup_put(rtg);
break;
default:
ASSERT(0);
@ -277,7 +284,7 @@ xchk_ag_btree_del_cursor_if_sick(
type_to_health_flag[sc->sm->sm_type].group == XHG_AG)
mask &= ~sc->sick_mask;
if (xfs_ag_has_sickness((*curp)->bc_ag.pag, mask)) {
if (xfs_group_has_sickness((*curp)->bc_group, mask)) {
sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XFAIL;
xfs_btree_del_cursor(*curp, XFS_BTREE_NOERROR);
*curp = NULL;
@ -294,9 +301,8 @@ xchk_health_record(
struct xfs_scrub *sc)
{
struct xfs_mount *mp = sc->mp;
struct xfs_perag *pag;
xfs_agnumber_t agno;
struct xfs_perag *pag = NULL;
struct xfs_rtgroup *rtg = NULL;
unsigned int sick;
unsigned int checked;
@ -304,15 +310,17 @@ xchk_health_record(
if (sick & XFS_SICK_FS_PRIMARY)
xchk_set_corrupt(sc);
xfs_rt_measure_sickness(mp, &sick, &checked);
if (sick & XFS_SICK_RT_PRIMARY)
xchk_set_corrupt(sc);
for_each_perag(mp, agno, pag) {
xfs_ag_measure_sickness(pag, &sick, &checked);
while ((pag = xfs_perag_next(mp, pag))) {
xfs_group_measure_sickness(pag_group(pag), &sick, &checked);
if (sick & XFS_SICK_AG_PRIMARY)
xchk_set_corrupt(sc);
}
while ((rtg = xfs_rtgroup_next(mp, rtg))) {
xfs_group_measure_sickness(rtg_group(rtg), &sick, &checked);
if (sick & XFS_SICK_RG_PRIMARY)
xchk_set_corrupt(sc);
}
return 0;
}

16
fs/xfs/scrub/ialloc.c
View File

@ -258,7 +258,7 @@ xchk_iallocbt_chunk(
{
struct xfs_scrub *sc = bs->sc;
struct xfs_mount *mp = bs->cur->bc_mp;
struct xfs_perag *pag = bs->cur->bc_ag.pag;
struct xfs_perag *pag = to_perag(bs->cur->bc_group);
xfs_agblock_t agbno;
xfs_extlen_t len;
@ -303,7 +303,6 @@ xchk_iallocbt_check_cluster_ifree(
unsigned int irec_ino,
struct xfs_dinode *dip)
{
struct xfs_mount *mp = bs->cur->bc_mp;
xfs_ino_t fsino;
xfs_agino_t agino;
bool irec_free;
@ -319,7 +318,7 @@ xchk_iallocbt_check_cluster_ifree(
* the record, compute which fs inode we're talking about.
*/
agino = irec->ir_startino + irec_ino;
fsino = XFS_AGINO_TO_INO(mp, bs->cur->bc_ag.pag->pag_agno, agino);
fsino = xfs_agino_to_ino(to_perag(bs->cur->bc_group), agino);
irec_free = (irec->ir_free & XFS_INOBT_MASK(irec_ino));
if (be16_to_cpu(dip->di_magic) != XFS_DINODE_MAGIC ||
@ -368,7 +367,6 @@ xchk_iallocbt_check_cluster(
struct xfs_mount *mp = bs->cur->bc_mp;
struct xfs_buf *cluster_bp;
unsigned int nr_inodes;
xfs_agnumber_t agno = bs->cur->bc_ag.pag->pag_agno;
xfs_agblock_t agbno;
unsigned int cluster_index;
uint16_t cluster_mask = 0;
@ -396,7 +394,7 @@ xchk_iallocbt_check_cluster(
* ir_startino can be large enough to make im_boffset nonzero.
*/
ir_holemask = (irec->ir_holemask & cluster_mask);
imap.im_blkno = XFS_AGB_TO_DADDR(mp, agno, agbno);
imap.im_blkno = xfs_agbno_to_daddr(to_perag(bs->cur->bc_group), agbno);
imap.im_len = XFS_FSB_TO_BB(mp, M_IGEO(mp)->blocks_per_cluster);
imap.im_boffset = XFS_INO_TO_OFFSET(mp, irec->ir_startino) <<
mp->m_sb.sb_inodelog;
@ -407,9 +405,9 @@ xchk_iallocbt_check_cluster(
return 0;
}
trace_xchk_iallocbt_check_cluster(mp, agno, irec->ir_startino,
imap.im_blkno, imap.im_len, cluster_base, nr_inodes,
cluster_mask, ir_holemask,
trace_xchk_iallocbt_check_cluster(to_perag(bs->cur->bc_group),
irec->ir_startino, imap.im_blkno, imap.im_len,
cluster_base, nr_inodes, cluster_mask, ir_holemask,
XFS_INO_TO_OFFSET(mp, irec->ir_startino +
cluster_base));
@ -585,7 +583,7 @@ xchk_iallocbt_rec(
uint16_t holemask;
xfs_inobt_btrec_to_irec(mp, rec, &irec);
if (xfs_inobt_check_irec(bs->cur->bc_ag.pag, &irec) != NULL) {
if (xfs_inobt_check_irec(to_perag(bs->cur->bc_group), &irec) != NULL) {
xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
return 0;
}

27
fs/xfs/scrub/ialloc_repair.c
View File

@ -146,15 +146,12 @@ xrep_ibt_check_ifree(
struct xfs_scrub *sc = ri->sc;
struct xfs_mount *mp = sc->mp;
struct xfs_dinode *dip;
xfs_ino_t fsino;
xfs_agino_t agino;
xfs_agnumber_t agno = ri->sc->sa.pag->pag_agno;
unsigned int cluster_buf_base;
unsigned int offset;
int error;
agino = cluster_ag_base + cluster_index;
fsino = XFS_AGINO_TO_INO(mp, agno, agino);
/* Inode uncached or half assembled, read disk buffer */
cluster_buf_base = XFS_INO_TO_OFFSET(mp, cluster_ag_base);
@ -165,7 +162,8 @@ xrep_ibt_check_ifree(
if (be16_to_cpu(dip->di_magic) != XFS_DINODE_MAGIC)
return -EFSCORRUPTED;
if (dip->di_version >= 3 && be64_to_cpu(dip->di_ino) != fsino)
if (dip->di_version >= 3 &&
be64_to_cpu(dip->di_ino) != xfs_agino_to_ino(ri->sc->sa.pag, agino))
return -EFSCORRUPTED;
/* Will the in-core inode tell us if it's in use? */
@ -194,7 +192,7 @@ xrep_ibt_stash(
if (ri->rie.ir_freecount > 0)
ri->finobt_recs++;
trace_xrep_ibt_found(ri->sc->mp, ri->sc->sa.pag->pag_agno, &ri->rie);
trace_xrep_ibt_found(ri->sc->sa.pag, &ri->rie);
error = xfarray_append(ri->inode_records, &ri->rie);
if (error)
@ -307,7 +305,7 @@ xrep_ibt_process_cluster(
* inobt because imap_to_bp directly maps the buffer without touching
* either inode btree.
*/
imap.im_blkno = XFS_AGB_TO_DADDR(mp, sc->sa.pag->pag_agno, cluster_bno);
imap.im_blkno = xfs_agbno_to_daddr(sc->sa.pag, cluster_bno);
imap.im_len = XFS_FSB_TO_BB(mp, igeo->blocks_per_cluster);
imap.im_boffset = 0;
error = xfs_imap_to_bp(mp, sc->tp, &imap, &cluster_bp);
@ -423,9 +421,7 @@ xrep_ibt_record_inode_blocks(
if (error)
return error;
trace_xrep_ibt_walk_rmap(mp, ri->sc->sa.pag->pag_agno,
rec->rm_startblock, rec->rm_blockcount, rec->rm_owner,
rec->rm_offset, rec->rm_flags);
trace_xrep_ibt_walk_rmap(ri->sc->sa.pag, rec);
/*
* Record the free/hole masks for each inode cluster that could be
@ -634,7 +630,6 @@ xrep_ibt_build_new_trees(
struct xfs_scrub *sc = ri->sc;
struct xfs_btree_cur *ino_cur;
struct xfs_btree_cur *fino_cur = NULL;
xfs_fsblock_t fsbno;
bool need_finobt;
int error;
@ -656,9 +651,8 @@ xrep_ibt_build_new_trees(
*
* Start by setting up the inobt staging cursor.
*/
fsbno = XFS_AGB_TO_FSB(sc->mp, sc->sa.pag->pag_agno,
XFS_IBT_BLOCK(sc->mp));
xrep_newbt_init_ag(&ri->new_inobt, sc, &XFS_RMAP_OINFO_INOBT, fsbno,
xrep_newbt_init_ag(&ri->new_inobt, sc, &XFS_RMAP_OINFO_INOBT,
xfs_agbno_to_fsb(sc->sa.pag, XFS_IBT_BLOCK(sc->mp)),
XFS_AG_RESV_NONE);
ri->new_inobt.bload.claim_block = xrep_ibt_claim_block;
ri->new_inobt.bload.get_records = xrep_ibt_get_records;
@ -677,10 +671,9 @@ xrep_ibt_build_new_trees(
if (sc->mp->m_finobt_nores)
resv = XFS_AG_RESV_NONE;
fsbno = XFS_AGB_TO_FSB(sc->mp, sc->sa.pag->pag_agno,
XFS_FIBT_BLOCK(sc->mp));
xrep_newbt_init_ag(&ri->new_finobt, sc, &XFS_RMAP_OINFO_INOBT,
fsbno, resv);
xfs_agbno_to_fsb(sc->sa.pag, XFS_FIBT_BLOCK(sc->mp)),
resv);
ri->new_finobt.bload.claim_block = xrep_fibt_claim_block;
ri->new_finobt.bload.get_records = xrep_fibt_get_records;
@ -821,7 +814,7 @@ xrep_iallocbt(
sc->sick_mask = XFS_SICK_AG_INOBT | XFS_SICK_AG_FINOBT;
/* Set up enough storage to handle an AG with nothing but inodes. */
xfs_agino_range(mp, sc->sa.pag->pag_agno, &first_agino, &last_agino);
xfs_agino_range(mp, pag_agno(sc->sa.pag), &first_agino, &last_agino);
last_agino /= XFS_INODES_PER_CHUNK;
descr = xchk_xfile_ag_descr(sc, "inode index records");
error = xfarray_create(descr, last_agino,

33
fs/xfs/scrub/inode.c
View File

@ -60,6 +60,22 @@ xchk_install_handle_iscrub(
if (error)
return error;
/*
* Don't allow scrubbing by handle of any non-directory inode records
* in the metadata directory tree. We don't know if any of the scans
* launched by this scrubber will end up indirectly trying to lock this
* file.
*
* Scrubbers of inode-rooted metadata files (e.g. quota files) will
* attach all the resources needed to scrub the inode and call
* xchk_inode directly. Userspace cannot call this directly.
*/
if (xfs_is_metadir_inode(ip) && !S_ISDIR(VFS_I(ip)->i_mode)) {
xchk_irele(sc, ip);
sc->ip = NULL;
return -ENOENT;
}
return xchk_prepare_iscrub(sc);
}
@ -94,9 +110,15 @@ xchk_setup_inode(
return xchk_prepare_iscrub(sc);
}
/* Reject internal metadata files and obviously bad inode numbers. */
if (xfs_internal_inum(mp, sc->sm->sm_ino))
/*
* On pre-metadir filesystems, reject internal metadata files. For
* metadir filesystems, limited scrubbing of any file in the metadata
* directory tree by handle is allowed, because that is the only way to
* validate the lack of parent pointers in the sb-root metadata inodes.
*/
if (!xfs_has_metadir(mp) && xfs_is_sb_inum(mp, sc->sm->sm_ino))
return -ENOENT;
/* Reject obviously bad inode numbers. */
if (!xfs_verify_ino(sc->mp, sc->sm->sm_ino))
return -ENOENT;
@ -421,8 +443,13 @@ xchk_dinode(
break;
case 2:
case 3:
if (dip->di_onlink != 0)
if (xfs_dinode_is_metadir(dip)) {
if (be16_to_cpu(dip->di_metatype) >= XFS_METAFILE_MAX)
xchk_ino_set_corrupt(sc, ino);
} else {
if (dip->di_metatype != 0)
xchk_ino_set_corrupt(sc, ino);
}
if (dip->di_mode == 0 && sc->ip)
xchk_ino_set_corrupt(sc, ino);

39
fs/xfs/scrub/inode_repair.c
View File

@ -521,10 +521,17 @@ STATIC void
xrep_dinode_nlinks(
struct xfs_dinode *dip)
{
if (dip->di_version > 1)
dip->di_onlink = 0;
else
if (dip->di_version < 2) {
dip->di_nlink = 0;
return;
}
if (xfs_dinode_is_metadir(dip)) {
if (be16_to_cpu(dip->di_metatype) >= XFS_METAFILE_MAX)
dip->di_metatype = cpu_to_be16(XFS_METAFILE_UNKNOWN);
} else {
dip->di_metatype = 0;
}
}
/* Fix any conflicting flags that the verifiers complain about. */
@ -565,6 +572,16 @@ xrep_dinode_flags(
dip->di_nrext64_pad = 0;
else if (dip->di_version >= 3)
dip->di_v3_pad = 0;
if (flags2 & XFS_DIFLAG2_METADATA) {
xfs_failaddr_t fa;
fa = xfs_dinode_verify_metadir(sc->mp, dip, mode, flags,
flags2);
if (fa)
flags2 &= ~XFS_DIFLAG2_METADATA;
}
dip->di_flags = cpu_to_be16(flags);
dip->di_flags2 = cpu_to_be64(flags2);
}
@ -761,14 +778,13 @@ STATIC int
xrep_dinode_count_rmaps(
struct xrep_inode *ri)
{
struct xfs_perag *pag;
xfs_agnumber_t agno;
struct xfs_perag *pag = NULL;
int error;
if (!xfs_has_rmapbt(ri->sc->mp) || xfs_has_realtime(ri->sc->mp))
return -EOPNOTSUPP;
for_each_perag(ri->sc->mp, agno, pag) {
while ((pag = xfs_perag_next(ri->sc->mp, pag))) {
error = xrep_dinode_count_ag_rmaps(ri, pag);
if (error) {
xfs_perag_rele(pag);
@ -1755,15 +1771,8 @@ xrep_inode_pptr(
if (inode->i_nlink == 0 && !(inode->i_state & I_LINKABLE))
return 0;
/* The root directory doesn't have a parent pointer. */
if (ip == mp->m_rootip)
return 0;
/*
* Metadata inodes are rooted in the superblock and do not have any
* parents.
*/
if (xfs_is_metadata_inode(ip))
/* Children of the superblock do not have parent pointers. */
if (xchk_inode_is_sb_rooted(ip))
return 0;
/* Inode already has an attr fork; no further work possible here. */

4
fs/xfs/scrub/iscan.c
View File

@ -67,7 +67,7 @@ xchk_iscan_mask_skipino(
xfs_agnumber_t skip_agno = XFS_INO_TO_AGNO(mp, iscan->skip_ino);
xfs_agnumber_t skip_agino = XFS_INO_TO_AGINO(mp, iscan->skip_ino);
if (pag->pag_agno != skip_agno)
if (pag_agno(pag) != skip_agno)
return;
if (skip_agino < rec->ir_startino)
return;
@ -95,7 +95,7 @@ xchk_iscan_find_next(
struct xfs_btree_cur *cur;
struct xfs_mount *mp = sc->mp;
struct xfs_trans *tp = sc->tp;
xfs_agnumber_t agno = pag->pag_agno;
xfs_agnumber_t agno = pag_agno(pag);
xfs_agino_t lastino = NULLAGINO;
xfs_agino_t first, last;
xfs_agino_t agino = *cursor;

689
fs/xfs/scrub/metapath.c Normal file
View File

@ -0,0 +1,689 @@
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Copyright (c) 2023-2024 Oracle. All Rights Reserved.
* Author: Darrick J. Wong <djwong@kernel.org>
*/
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_log_format.h"
#include "xfs_trans.h"
#include "xfs_inode.h"
#include "xfs_metafile.h"
#include "xfs_quota.h"
#include "xfs_qm.h"
#include "xfs_dir2.h"
#include "xfs_parent.h"
#include "xfs_bmap_btree.h"
#include "xfs_trans_space.h"
#include "xfs_attr.h"
#include "xfs_rtgroup.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/trace.h"
#include "scrub/readdir.h"
#include "scrub/repair.h"
/*
* Metadata Directory Tree Paths
* =============================
*
* A filesystem with metadir enabled expects to find metadata structures
* attached to files that are accessible by walking a path down the metadata
* directory tree. Given the metadir path and the incore inode storing the
* metadata, this scrubber ensures that the ondisk metadir path points to the
* ondisk inode represented by the incore inode.
*/
struct xchk_metapath {
struct xfs_scrub *sc;
/* Name for lookup */
struct xfs_name xname;
/* Directory update for repairs */
struct xfs_dir_update du;
/* Path down to this metadata file from the parent directory */
const char *path;
/* Directory parent of the metadata file. */
struct xfs_inode *dp;
/* Locks held on dp */
unsigned int dp_ilock_flags;
/* Transaction block reservations */
unsigned int link_resblks;
unsigned int unlink_resblks;
/* Parent pointer updates */
struct xfs_parent_args link_ppargs;
struct xfs_parent_args unlink_ppargs;
/* Scratchpads for removing links */
struct xfs_da_args pptr_args;
};
/* Release resources tracked in the buffer. */
static inline void
xchk_metapath_cleanup(
void *buf)
{
struct xchk_metapath *mpath = buf;
if (mpath->dp_ilock_flags)
xfs_iunlock(mpath->dp, mpath->dp_ilock_flags);
kfree(mpath->path);
}
/* Set up a metadir path scan. @path must be dynamically allocated. */
static inline int
xchk_setup_metapath_scan(
struct xfs_scrub *sc,
struct xfs_inode *dp,
const char *path,
struct xfs_inode *ip)
{
struct xchk_metapath *mpath;
int error;
if (!path)
return -ENOMEM;
error = xchk_install_live_inode(sc, ip);
if (error) {
kfree(path);
return error;
}
mpath = kzalloc(sizeof(struct xchk_metapath), XCHK_GFP_FLAGS);
if (!mpath) {
kfree(path);
return -ENOMEM;
}
mpath->sc = sc;
sc->buf = mpath;
sc->buf_cleanup = xchk_metapath_cleanup;
mpath->dp = dp;
mpath->path = path; /* path is now owned by mpath */
mpath->xname.name = mpath->path;
mpath->xname.len = strlen(mpath->path);
mpath->xname.type = xfs_mode_to_ftype(VFS_I(ip)->i_mode);
return 0;
}
#ifdef CONFIG_XFS_RT
/* Scan the /rtgroups directory itself. */
static int
xchk_setup_metapath_rtdir(
struct xfs_scrub *sc)
{
if (!sc->mp->m_rtdirip)
return -ENOENT;
return xchk_setup_metapath_scan(sc, sc->mp->m_metadirip,
kasprintf(GFP_KERNEL, "rtgroups"), sc->mp->m_rtdirip);
}
/* Scan a rtgroup inode under the /rtgroups directory. */
static int
xchk_setup_metapath_rtginode(
struct xfs_scrub *sc,
enum xfs_rtg_inodes type)
{
struct xfs_rtgroup *rtg;
struct xfs_inode *ip;
int error;
rtg = xfs_rtgroup_get(sc->mp, sc->sm->sm_agno);
if (!rtg)
return -ENOENT;
ip = rtg->rtg_inodes[type];
if (!ip) {
error = -ENOENT;
goto out_put_rtg;
}
error = xchk_setup_metapath_scan(sc, sc->mp->m_rtdirip,
xfs_rtginode_path(rtg_rgno(rtg), type), ip);
out_put_rtg:
xfs_rtgroup_put(rtg);
return error;
}
#else
# define xchk_setup_metapath_rtdir(...) (-ENOENT)
# define xchk_setup_metapath_rtginode(...) (-ENOENT)
#endif /* CONFIG_XFS_RT */
#ifdef CONFIG_XFS_QUOTA
/* Scan the /quota directory itself. */
static int
xchk_setup_metapath_quotadir(
struct xfs_scrub *sc)
{
struct xfs_trans *tp;
struct xfs_inode *dp = NULL;
int error;
error = xfs_trans_alloc_empty(sc->mp, &tp);
if (error)
return error;
error = xfs_dqinode_load_parent(tp, &dp);
xfs_trans_cancel(tp);
if (error)
return error;
error = xchk_setup_metapath_scan(sc, sc->mp->m_metadirip,
kasprintf(GFP_KERNEL, "quota"), dp);
xfs_irele(dp);
return error;
}
/* Scan a quota inode under the /quota directory. */
static int
xchk_setup_metapath_dqinode(
struct xfs_scrub *sc,
xfs_dqtype_t type)
{
struct xfs_trans *tp = NULL;
struct xfs_inode *dp = NULL;
struct xfs_inode *ip = NULL;
const char *path;
int error;
error = xfs_trans_alloc_empty(sc->mp, &tp);
if (error)
return error;
error = xfs_dqinode_load_parent(tp, &dp);
if (error)
goto out_cancel;
error = xfs_dqinode_load(tp, dp, type, &ip);
if (error)
goto out_dp;
xfs_trans_cancel(tp);
tp = NULL;
path = kasprintf(GFP_KERNEL, "%s", xfs_dqinode_path(type));
error = xchk_setup_metapath_scan(sc, dp, path, ip);
xfs_irele(ip);
out_dp:
xfs_irele(dp);
out_cancel:
if (tp)
xfs_trans_cancel(tp);
return error;
}
#else
# define xchk_setup_metapath_quotadir(...) (-ENOENT)
# define xchk_setup_metapath_dqinode(...) (-ENOENT)
#endif /* CONFIG_XFS_QUOTA */
int
xchk_setup_metapath(
struct xfs_scrub *sc)
{
if (!xfs_has_metadir(sc->mp))
return -ENOENT;
if (sc->sm->sm_gen)
return -EINVAL;
switch (sc->sm->sm_ino) {
case XFS_SCRUB_METAPATH_PROBE:
/* Just probing, nothing else to do. */
if (sc->sm->sm_agno)
return -EINVAL;
return 0;
case XFS_SCRUB_METAPATH_RTDIR:
return xchk_setup_metapath_rtdir(sc);
case XFS_SCRUB_METAPATH_RTBITMAP:
return xchk_setup_metapath_rtginode(sc, XFS_RTGI_BITMAP);
case XFS_SCRUB_METAPATH_RTSUMMARY:
return xchk_setup_metapath_rtginode(sc, XFS_RTGI_SUMMARY);
case XFS_SCRUB_METAPATH_QUOTADIR:
return xchk_setup_metapath_quotadir(sc);
case XFS_SCRUB_METAPATH_USRQUOTA:
return xchk_setup_metapath_dqinode(sc, XFS_DQTYPE_USER);
case XFS_SCRUB_METAPATH_GRPQUOTA:
return xchk_setup_metapath_dqinode(sc, XFS_DQTYPE_GROUP);
case XFS_SCRUB_METAPATH_PRJQUOTA:
return xchk_setup_metapath_dqinode(sc, XFS_DQTYPE_PROJ);
default:
return -ENOENT;
}
}
/*
* Take the ILOCK on the metadata directory parent and child. We do not know
* that the metadata directory is not corrupt, so we lock the parent and try
* to lock the child. Returns 0 if successful, or -EINTR to abort the scrub.
*/
STATIC int
xchk_metapath_ilock_both(
struct xchk_metapath *mpath)
{
struct xfs_scrub *sc = mpath->sc;
int error = 0;
while (true) {
xfs_ilock(mpath->dp, XFS_ILOCK_EXCL);
if (xchk_ilock_nowait(sc, XFS_ILOCK_EXCL)) {
mpath->dp_ilock_flags |= XFS_ILOCK_EXCL;
return 0;
}
xfs_iunlock(mpath->dp, XFS_ILOCK_EXCL);
if (xchk_should_terminate(sc, &error))
return error;
delay(1);
}
ASSERT(0);
return -EINTR;
}
/* Unlock parent and child inodes. */
static inline void
xchk_metapath_iunlock(
struct xchk_metapath *mpath)
{
struct xfs_scrub *sc = mpath->sc;
xchk_iunlock(sc, XFS_ILOCK_EXCL);
mpath->dp_ilock_flags &= ~XFS_ILOCK_EXCL;
xfs_iunlock(mpath->dp, XFS_ILOCK_EXCL);
}
int
xchk_metapath(
struct xfs_scrub *sc)
{
struct xchk_metapath *mpath = sc->buf;
xfs_ino_t ino = NULLFSINO;
int error;
/* Just probing, nothing else to do. */
if (sc->sm->sm_ino == XFS_SCRUB_METAPATH_PROBE)
return 0;
/* Parent required to do anything else. */
if (mpath->dp == NULL) {
xchk_ino_set_corrupt(sc, sc->ip->i_ino);
return 0;
}
error = xchk_trans_alloc_empty(sc);
if (error)
return error;
error = xchk_metapath_ilock_both(mpath);
if (error)
goto out_cancel;
/* Make sure the parent dir has a dirent pointing to this file. */
error = xchk_dir_lookup(sc, mpath->dp, &mpath->xname, &ino);
trace_xchk_metapath_lookup(sc, mpath->path, mpath->dp, ino);
if (error == -ENOENT) {
/* No directory entry at all */
xchk_ino_set_corrupt(sc, sc->ip->i_ino);
error = 0;
goto out_ilock;
}
if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error))
goto out_ilock;
if (ino != sc->ip->i_ino) {
/* Pointing to wrong inode */
xchk_ino_set_corrupt(sc, sc->ip->i_ino);
}
out_ilock:
xchk_metapath_iunlock(mpath);
out_cancel:
xchk_trans_cancel(sc);
return error;
}
#ifdef CONFIG_XFS_ONLINE_REPAIR
/* Create the dirent represented by the final component of the path. */
STATIC int
xrep_metapath_link(
struct xchk_metapath *mpath)
{
struct xfs_scrub *sc = mpath->sc;
mpath->du.dp = mpath->dp;
mpath->du.name = &mpath->xname;
mpath->du.ip = sc->ip;
if (xfs_has_parent(sc->mp))
mpath->du.ppargs = &mpath->link_ppargs;
else
mpath->du.ppargs = NULL;
trace_xrep_metapath_link(sc, mpath->path, mpath->dp, sc->ip->i_ino);
return xfs_dir_add_child(sc->tp, mpath->link_resblks, &mpath->du);
}
/* Remove the dirent at the final component of the path. */
STATIC int
xrep_metapath_unlink(
struct xchk_metapath *mpath,
xfs_ino_t ino,
struct xfs_inode *ip)
{
struct xfs_parent_rec rec;
struct xfs_scrub *sc = mpath->sc;
struct xfs_mount *mp = sc->mp;
int error;
trace_xrep_metapath_unlink(sc, mpath->path, mpath->dp, ino);
if (!ip) {
/* The child inode isn't allocated. Junk the dirent. */
xfs_trans_log_inode(sc->tp, mpath->dp, XFS_ILOG_CORE);
return xfs_dir_removename(sc->tp, mpath->dp, &mpath->xname,
ino, mpath->unlink_resblks);
}
mpath->du.dp = mpath->dp;
mpath->du.name = &mpath->xname;
mpath->du.ip = ip;
mpath->du.ppargs = NULL;
/* Figure out if we're removing a parent pointer too. */
if (xfs_has_parent(mp)) {
xfs_inode_to_parent_rec(&rec, ip);
error = xfs_parent_lookup(sc->tp, ip, &mpath->xname, &rec,
&mpath->pptr_args);
switch (error) {
case -ENOATTR:
break;
case 0:
mpath->du.ppargs = &mpath->unlink_ppargs;
break;
default:
return error;
}
}
return xfs_dir_remove_child(sc->tp, mpath->unlink_resblks, &mpath->du);
}
/*
* Try to create a dirent in @mpath->dp with the name @mpath->xname that points
* to @sc->ip. Returns:
*
* -EEXIST and an @alleged_child if the dirent that points to the wrong inode;
* 0 if there is now a dirent pointing to @sc->ip; or
* A negative errno on error.
*/
STATIC int
xrep_metapath_try_link(
struct xchk_metapath *mpath,
xfs_ino_t *alleged_child)
{
struct xfs_scrub *sc = mpath->sc;
xfs_ino_t ino;
int error;
/* Allocate transaction, lock inodes, join to transaction. */
error = xchk_trans_alloc(sc, mpath->link_resblks);
if (error)
return error;
error = xchk_metapath_ilock_both(mpath);
if (error) {
xchk_trans_cancel(sc);
return error;
}
xfs_trans_ijoin(sc->tp, mpath->dp, 0);
xfs_trans_ijoin(sc->tp, sc->ip, 0);
error = xchk_dir_lookup(sc, mpath->dp, &mpath->xname, &ino);
trace_xrep_metapath_lookup(sc, mpath->path, mpath->dp, ino);
if (error == -ENOENT) {
/*
* There is no dirent in the directory. Create an entry
* pointing to @sc->ip.
*/
error = xrep_metapath_link(mpath);
if (error)
goto out_cancel;
error = xrep_trans_commit(sc);
xchk_metapath_iunlock(mpath);
return error;
}
if (error)
goto out_cancel;
if (ino == sc->ip->i_ino) {
/* The dirent already points to @sc->ip; we're done. */
error = 0;
goto out_cancel;
}
/*
* The dirent points elsewhere; pass that back so that the caller
* can try to remove the dirent.
*/
*alleged_child = ino;
error = -EEXIST;
out_cancel:
xchk_trans_cancel(sc);
xchk_metapath_iunlock(mpath);
return error;
}
/*
* Take the ILOCK on the metadata directory parent and a bad child, if one is
* supplied. We do not know that the metadata directory is not corrupt, so we
* lock the parent and try to lock the child. Returns 0 if successful, or
* -EINTR to abort the repair. The lock state of @dp is not recorded in @mpath.
*/
STATIC int
xchk_metapath_ilock_parent_and_child(
struct xchk_metapath *mpath,
struct xfs_inode *ip)
{
struct xfs_scrub *sc = mpath->sc;
int error = 0;
while (true) {
xfs_ilock(mpath->dp, XFS_ILOCK_EXCL);
if (!ip || xfs_ilock_nowait(ip, XFS_ILOCK_EXCL))
return 0;
xfs_iunlock(mpath->dp, XFS_ILOCK_EXCL);
if (xchk_should_terminate(sc, &error))
return error;
delay(1);
}
ASSERT(0);
return -EINTR;
}
/*
* Try to remove a dirent in @mpath->dp with the name @mpath->xname that points
* to @alleged_child. Returns:
*
* 0 if there is no longer a dirent;
* -EEXIST if the dirent points to @sc->ip;
* -EAGAIN and an updated @alleged_child if the dirent points elsewhere; or
* A negative errno for any other error.
*/
STATIC int
xrep_metapath_try_unlink(
struct xchk_metapath *mpath,
xfs_ino_t *alleged_child)
{
struct xfs_scrub *sc = mpath->sc;
struct xfs_inode *ip = NULL;
xfs_ino_t ino;
int error;
ASSERT(*alleged_child != sc->ip->i_ino);
trace_xrep_metapath_try_unlink(sc, mpath->path, mpath->dp,
*alleged_child);
/*
* Allocate transaction, grab the alleged child inode, lock inodes,
* join to transaction.
*/
error = xchk_trans_alloc(sc, mpath->unlink_resblks);
if (error)
return error;
error = xchk_iget(sc, *alleged_child, &ip);
if (error == -EINVAL || error == -ENOENT) {
/* inode number is bogus, junk the dirent */
error = 0;
}
if (error) {
xchk_trans_cancel(sc);
return error;
}
error = xchk_metapath_ilock_parent_and_child(mpath, ip);
if (error) {
xchk_trans_cancel(sc);
return error;
}
xfs_trans_ijoin(sc->tp, mpath->dp, 0);
if (ip)
xfs_trans_ijoin(sc->tp, ip, 0);
error = xchk_dir_lookup(sc, mpath->dp, &mpath->xname, &ino);
trace_xrep_metapath_lookup(sc, mpath->path, mpath->dp, ino);
if (error == -ENOENT) {
/*
* There is no dirent in the directory anymore. We're ready to
* try the link operation again.
*/
error = 0;
goto out_cancel;
}
if (error)
goto out_cancel;
if (ino == sc->ip->i_ino) {
/* The dirent already points to @sc->ip; we're done. */
error = -EEXIST;
goto out_cancel;
}
/*
* The dirent does not point to the alleged child. Update the caller
* and signal that we want to be called again.
*/
if (ino != *alleged_child) {
*alleged_child = ino;
error = -EAGAIN;
goto out_cancel;
}
/* Remove the link to the child. */
error = xrep_metapath_unlink(mpath, ino, ip);
if (error)
goto out_cancel;
error = xrep_trans_commit(sc);
goto out_unlock;
out_cancel:
xchk_trans_cancel(sc);
out_unlock:
xfs_iunlock(mpath->dp, XFS_ILOCK_EXCL);
if (ip) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
xchk_irele(sc, ip);
}
return error;
}
/*
* Make sure the metadata directory path points to the child being examined.
*
* Repair needs to be able to create a directory structure, create its own
* transactions, and take ILOCKs. This function /must/ be called after all
* other repairs have completed.
*/
int
xrep_metapath(
struct xfs_scrub *sc)
{
struct xchk_metapath *mpath = sc->buf;
struct xfs_mount *mp = sc->mp;
int error = 0;
/* Just probing, nothing to repair. */
if (sc->sm->sm_ino == XFS_SCRUB_METAPATH_PROBE)
return 0;
/* Parent required to do anything else. */
if (mpath->dp == NULL)
return -EFSCORRUPTED;
/*
* Make sure the child file actually has an attr fork to receive a new
* parent pointer if the fs has parent pointers.
*/
if (xfs_has_parent(mp)) {
error = xfs_attr_add_fork(sc->ip,
sizeof(struct xfs_attr_sf_hdr), 1);
if (error)
return error;
}
/* Compute block reservation required to unlink and link a file. */
mpath->unlink_resblks = xfs_remove_space_res(mp, MAXNAMELEN);
mpath->link_resblks = xfs_link_space_res(mp, MAXNAMELEN);
do {
xfs_ino_t alleged_child;
/* Re-establish the link, or tell us which inode to remove. */
error = xrep_metapath_try_link(mpath, &alleged_child);
if (!error)
return 0;
if (error != -EEXIST)
return error;
/*
* Remove an incorrect link to an alleged child, or tell us
* which inode to remove.
*/
do {
error = xrep_metapath_try_unlink(mpath, &alleged_child);
} while (error == -EAGAIN);
if (error == -EEXIST) {
/* Link established; we're done. */
error = 0;
break;
}
} while (!error);
return error;
}
#endif /* CONFIG_XFS_ONLINE_REPAIR */

54
fs/xfs/scrub/newbt.c
View File

@ -58,7 +58,7 @@ xrep_newbt_estimate_slack(
if (sc->ops->type == ST_PERAG) {
free = sc->sa.pag->pagf_freeblks;
sz = xfs_ag_block_count(sc->mp, sc->sa.pag->pag_agno);
sz = xfs_ag_block_count(sc->mp, pag_agno(sc->sa.pag));
} else {
free = percpu_counter_sum(&sc->mp->m_fdblocks);
sz = sc->mp->m_sb.sb_dblocks;
@ -186,11 +186,10 @@ xrep_newbt_add_extent(
xfs_agblock_t agbno,
xfs_extlen_t len)
{
struct xfs_mount *mp = xnr->sc->mp;
struct xfs_alloc_arg args = {
.tp = NULL, /* no autoreap */
.oinfo = xnr->oinfo,
.fsbno = XFS_AGB_TO_FSB(mp, pag->pag_agno, agbno),
.fsbno = xfs_agbno_to_fsb(pag, agbno),
.len = len,
.resv = xnr->resv,
};
@ -206,12 +205,12 @@ xrep_newbt_validate_ag_alloc_hint(
struct xfs_scrub *sc = xnr->sc;
xfs_agnumber_t agno = XFS_FSB_TO_AGNO(sc->mp, xnr->alloc_hint);
if (agno == sc->sa.pag->pag_agno &&
if (agno == pag_agno(sc->sa.pag) &&
xfs_verify_fsbno(sc->mp, xnr->alloc_hint))
return;
xnr->alloc_hint = XFS_AGB_TO_FSB(sc->mp, sc->sa.pag->pag_agno,
XFS_AGFL_BLOCK(sc->mp) + 1);
xnr->alloc_hint =
xfs_agbno_to_fsb(sc->sa.pag, XFS_AGFL_BLOCK(sc->mp) + 1);
}
/* Allocate disk space for a new per-AG btree. */
@ -251,16 +250,15 @@ xrep_newbt_alloc_ag_blocks(
return -ENOSPC;
agno = XFS_FSB_TO_AGNO(mp, args.fsbno);
trace_xrep_newbt_alloc_ag_blocks(mp, agno,
XFS_FSB_TO_AGBNO(mp, args.fsbno), args.len,
xnr->oinfo.oi_owner);
if (agno != sc->sa.pag->pag_agno) {
ASSERT(agno == sc->sa.pag->pag_agno);
if (agno != pag_agno(sc->sa.pag)) {
ASSERT(agno == pag_agno(sc->sa.pag));
return -EFSCORRUPTED;
}
trace_xrep_newbt_alloc_ag_blocks(sc->sa.pag,
XFS_FSB_TO_AGBNO(mp, args.fsbno), args.len,
xnr->oinfo.oi_owner);
error = xrep_newbt_add_blocks(xnr, sc->sa.pag, &args);
if (error)
return error;
@ -326,16 +324,16 @@ xrep_newbt_alloc_file_blocks(
agno = XFS_FSB_TO_AGNO(mp, args.fsbno);
trace_xrep_newbt_alloc_file_blocks(mp, agno,
XFS_FSB_TO_AGBNO(mp, args.fsbno), args.len,
xnr->oinfo.oi_owner);
pag = xfs_perag_get(mp, agno);
if (!pag) {
ASSERT(0);
return -EFSCORRUPTED;
}
trace_xrep_newbt_alloc_file_blocks(pag,
XFS_FSB_TO_AGBNO(mp, args.fsbno), args.len,
xnr->oinfo.oi_owner);
error = xrep_newbt_add_blocks(xnr, pag, &args);
xfs_perag_put(pag);
if (error)
@ -376,7 +374,6 @@ xrep_newbt_free_extent(
struct xfs_scrub *sc = xnr->sc;
xfs_agblock_t free_agbno = resv->agbno;
xfs_extlen_t free_aglen = resv->len;
xfs_fsblock_t fsbno;
int error;
if (!btree_committed || resv->used == 0) {
@ -385,8 +382,8 @@ xrep_newbt_free_extent(
* space reservation, let the existing EFI free the entire
* space extent.
*/
trace_xrep_newbt_free_blocks(sc->mp, resv->pag->pag_agno,
free_agbno, free_aglen, xnr->oinfo.oi_owner);
trace_xrep_newbt_free_blocks(resv->pag, free_agbno, free_aglen,
xnr->oinfo.oi_owner);
xfs_alloc_commit_autoreap(sc->tp, &resv->autoreap);
return 1;
}
@ -403,8 +400,8 @@ xrep_newbt_free_extent(
if (free_aglen == 0)
return 0;
trace_xrep_newbt_free_blocks(sc->mp, resv->pag->pag_agno, free_agbno,
free_aglen, xnr->oinfo.oi_owner);
trace_xrep_newbt_free_blocks(resv->pag, free_agbno, free_aglen,
xnr->oinfo.oi_owner);
ASSERT(xnr->resv != XFS_AG_RESV_AGFL);
ASSERT(xnr->resv != XFS_AG_RESV_IGNORE);
@ -413,9 +410,9 @@ xrep_newbt_free_extent(
* Use EFIs to free the reservations. This reduces the chance
* that we leak blocks if the system goes down.
*/
fsbno = XFS_AGB_TO_FSB(sc->mp, resv->pag->pag_agno, free_agbno);
error = xfs_free_extent_later(sc->tp, fsbno, free_aglen, &xnr->oinfo,
xnr->resv, XFS_FREE_EXTENT_SKIP_DISCARD);
error = xfs_free_extent_later(sc->tp,
xfs_agbno_to_fsb(resv->pag, free_agbno), free_aglen,
&xnr->oinfo, xnr->resv, XFS_FREE_EXTENT_SKIP_DISCARD);
if (error)
return error;
@ -516,7 +513,6 @@ xrep_newbt_claim_block(
union xfs_btree_ptr *ptr)
{
struct xrep_newbt_resv *resv;
struct xfs_mount *mp = cur->bc_mp;
xfs_agblock_t agbno;
/*
@ -541,12 +537,10 @@ xrep_newbt_claim_block(
if (resv->used == resv->len)
list_move_tail(&resv->list, &xnr->resv_list);
trace_xrep_newbt_claim_block(mp, resv->pag->pag_agno, agbno, 1,
xnr->oinfo.oi_owner);
trace_xrep_newbt_claim_block(resv->pag, agbno, 1, xnr->oinfo.oi_owner);
if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN)
ptr->l = cpu_to_be64(XFS_AGB_TO_FSB(mp, resv->pag->pag_agno,
agbno));
ptr->l = cpu_to_be64(xfs_agbno_to_fsb(resv->pag, agbno));
else
ptr->s = cpu_to_be32(agbno);

4
fs/xfs/scrub/nlinks.c
View File

@ -279,7 +279,7 @@ xchk_nlinks_collect_dirent(
* determine the backref count.
*/
if (dotdot) {
if (dp == sc->mp->m_rootip)
if (xchk_inode_is_dirtree_root(dp))
error = xchk_nlinks_update_incore(xnc, ino, 1, 0, 0);
else if (!xfs_has_parent(sc->mp))
error = xchk_nlinks_update_incore(xnc, ino, 0, 1, 0);
@ -735,7 +735,7 @@ xchk_nlinks_compare_inode(
}
}
if (ip == sc->mp->m_rootip) {
if (xchk_inode_is_dirtree_root(ip)) {
/*
* For the root of a directory tree, both the '.' and '..'
* entries should point to the root directory. The dotdot

4
fs/xfs/scrub/nlinks_repair.c
View File

@ -60,11 +60,9 @@ xrep_nlinks_is_orphaned(
unsigned int actual_nlink,
const struct xchk_nlink *obs)
{
struct xfs_mount *mp = ip->i_mount;
if (obs->parents != 0)
return false;
if (ip == mp->m_rootip || ip == sc->orphanage)
if (xchk_inode_is_dirtree_root(ip) || ip == sc->orphanage)
return false;
return actual_nlink != 0;
}

4
fs/xfs/scrub/orphanage.c
View File

@ -295,7 +295,9 @@ xrep_orphanage_can_adopt(
return false;
if (sc->ip == sc->orphanage)
return false;
if (xfs_internal_inum(sc->mp, sc->ip->i_ino))
if (xchk_inode_is_sb_rooted(sc->ip))
return false;
if (xfs_is_internal_inode(sc->ip))
return false;
return true;
}

39
fs/xfs/scrub/parent.c
View File

@ -132,6 +132,14 @@ xchk_parent_validate(
return 0;
}
/* Is this the metadata root dir? Then '..' must point to itself. */
if (sc->ip == mp->m_metadirip) {
if (sc->ip->i_ino != mp->m_sb.sb_metadirino ||
sc->ip->i_ino != parent_ino)
xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
return 0;
}
/* '..' must not point to ourselves. */
if (sc->ip->i_ino == parent_ino) {
xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
@ -185,6 +193,12 @@ xchk_parent_validate(
goto out_unlock;
}
/* Metadata and regular inodes cannot cross trees. */
if (xfs_is_metadir_inode(dp) != xfs_is_metadir_inode(sc->ip)) {
xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
goto out_unlock;
}
/* Look for a directory entry in the parent pointing to the child. */
error = xchk_dir_walk(sc, dp, xchk_parent_actor, &spc);
if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error))
@ -300,7 +314,7 @@ xchk_parent_pptr_and_dotdot(
}
/* Is this the root dir? Then '..' must point to itself. */
if (sc->ip == sc->mp->m_rootip) {
if (xchk_inode_is_dirtree_root(sc->ip)) {
if (sc->ip->i_ino != pp->parent_ino)
xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
return 0;
@ -711,7 +725,7 @@ xchk_parent_count_pptrs(
}
if (S_ISDIR(VFS_I(sc->ip)->i_mode)) {
if (sc->ip == sc->mp->m_rootip)
if (xchk_inode_is_dirtree_root(sc->ip))
pp->pptrs_found++;
if (VFS_I(sc->ip)->i_nlink == 0 && pp->pptrs_found > 0)
@ -720,6 +734,14 @@ xchk_parent_count_pptrs(
pp->pptrs_found == 0)
xchk_ino_set_corrupt(sc, sc->ip->i_ino);
} else {
/*
* Starting with metadir, we allow checking of parent pointers
* of non-directory files that are children of the superblock.
* Pretend that we found a parent pointer attr.
*/
if (xfs_has_metadir(sc->mp) && xchk_inode_is_sb_rooted(sc->ip))
pp->pptrs_found++;
if (VFS_I(sc->ip)->i_nlink != pp->pptrs_found)
xchk_ino_set_corrupt(sc, sc->ip->i_ino);
}
@ -885,10 +907,9 @@ bool
xchk_pptr_looks_zapped(
struct xfs_inode *ip)
{
struct xfs_mount *mp = ip->i_mount;
struct inode *inode = VFS_I(ip);
ASSERT(xfs_has_parent(mp));
ASSERT(xfs_has_parent(ip->i_mount));
/*
* Temporary files that cannot be linked into the directory tree do not
@ -902,15 +923,15 @@ xchk_pptr_looks_zapped(
* of a parent pointer scan is always the empty set. It's safe to scan
* them even if the attr fork was zapped.
*/
if (ip == mp->m_rootip)
if (xchk_inode_is_dirtree_root(ip))
return false;
/*
* Metadata inodes are all rooted in the superblock and do not have
* any parents. Hence the attr fork will not be initialized, but
* there are no parent pointers that might have been zapped.
* Metadata inodes that are rooted in the superblock do not have any
* parents. Hence the attr fork will not be initialized, but there are
* no parent pointers that might have been zapped.
*/
if (xfs_is_metadata_inode(ip))
if (xchk_inode_is_sb_rooted(ip))
return false;
/*

37
fs/xfs/scrub/parent_repair.c
View File

@ -1334,7 +1334,7 @@ xrep_parent_rebuild_pptrs(
* so that we can decide if we're moving this file to the orphanage.
* For this purpose, root directories are their own parents.
*/
if (sc->ip == sc->mp->m_rootip) {
if (xchk_inode_is_dirtree_root(sc->ip)) {
xrep_findparent_scan_found(&rp->pscan, sc->ip->i_ino);
} else {
error = xrep_parent_lookup_pptrs(sc, &parent_ino);
@ -1354,21 +1354,40 @@ STATIC int
xrep_parent_rebuild_tree(
struct xrep_parent *rp)
{
struct xfs_scrub *sc = rp->sc;
bool try_adoption;
int error;
if (xfs_has_parent(rp->sc->mp)) {
if (xfs_has_parent(sc->mp)) {
error = xrep_parent_rebuild_pptrs(rp);
if (error)
return error;
}
if (rp->pscan.parent_ino == NULLFSINO) {
if (xrep_orphanage_can_adopt(rp->sc))
/*
* Any file with no parent could be adopted. This check happens after
* rebuilding the parent pointer structure because we might have cycled
* the ILOCK during that process.
*/
try_adoption = rp->pscan.parent_ino == NULLFSINO;
/*
* Starting with metadir, we allow checking of parent pointers
* of non-directory files that are children of the superblock.
* Lack of parent is ok here.
*/
if (try_adoption && xfs_has_metadir(sc->mp) &&
xchk_inode_is_sb_rooted(sc->ip))
try_adoption = false;
if (try_adoption) {
if (xrep_orphanage_can_adopt(sc))
return xrep_parent_move_to_orphanage(rp);
return -EFSCORRUPTED;
}
if (S_ISDIR(VFS_I(rp->sc->ip)->i_mode))
if (S_ISDIR(VFS_I(sc->ip)->i_mode))
return xrep_parent_reset_dotdot(rp);
return 0;
@ -1422,6 +1441,14 @@ xrep_parent_set_nondir_nlink(
if (error)
return error;
/*
* Starting with metadir, we allow checking of parent pointers of
* non-directory files that are children of the superblock. Pretend
* that we found a parent pointer attr.
*/
if (xfs_has_metadir(sc->mp) && xchk_inode_is_sb_rooted(sc->ip))
rp->parents++;
if (rp->parents > 0 && xfs_inode_on_unlinked_list(ip)) {
xfs_trans_ijoin(sc->tp, sc->ip, 0);
joined = true;

7
fs/xfs/scrub/quotacheck.c
View File

@ -398,10 +398,13 @@ xqcheck_collect_inode(
bool isreg = S_ISREG(VFS_I(ip)->i_mode);
int error = 0;
if (xfs_is_quota_inode(&tp->t_mountp->m_sb, ip->i_ino)) {
if (xfs_is_metadir_inode(ip) ||
xfs_is_quota_inode(&tp->t_mountp->m_sb, ip->i_ino)) {
/*
* Quota files are never counted towards quota, so we do not
* need to take the lock.
* need to take the lock. Files do not switch between the
* metadata and regular directory trees without a reallocation,
* so we do not need to ILOCK them either.
*/
xchk_iscan_mark_visited(&xqc->iscan, ip);
return 0;

10
fs/xfs/scrub/reap.c
View File

@ -137,7 +137,7 @@ xreap_put_freelist(
agfl_bp, agbno, 0);
if (error)
return error;
xfs_extent_busy_insert(sc->tp, sc->sa.pag, agbno, 1,
xfs_extent_busy_insert(sc->tp, pag_group(sc->sa.pag), agbno, 1,
XFS_EXTENT_BUSY_SKIP_DISCARD);
return 0;
@ -263,7 +263,6 @@ xreap_agextent_binval(
struct xfs_scrub *sc = rs->sc;
struct xfs_perag *pag = sc->sa.pag;
struct xfs_mount *mp = sc->mp;
xfs_agnumber_t agno = sc->sa.pag->pag_agno;
xfs_agblock_t agbno_next = agbno + *aglenp;
xfs_agblock_t bno = agbno;
@ -284,7 +283,7 @@ xreap_agextent_binval(
*/
while (bno < agbno_next) {
struct xrep_bufscan scan = {
.daddr = XFS_AGB_TO_DADDR(mp, agno, bno),
.daddr = xfs_agbno_to_daddr(pag, bno),
.max_sectors = xrep_bufscan_max_sectors(mp,
agbno_next - bno),
.daddr_step = XFS_FSB_TO_BB(mp, 1),
@ -391,7 +390,7 @@ xreap_agextent_iter(
xfs_fsblock_t fsbno;
int error = 0;
fsbno = XFS_AGB_TO_FSB(sc->mp, sc->sa.pag->pag_agno, agbno);
fsbno = xfs_agbno_to_fsb(sc->sa.pag, agbno);
/*
* If there are other rmappings, this block is cross linked and must
@ -780,7 +779,6 @@ xreap_bmapi_binval(
xfs_fileoff_t off;
xfs_fileoff_t max_off;
xfs_extlen_t scan_blocks;
xfs_agnumber_t agno = sc->sa.pag->pag_agno;
xfs_agblock_t bno;
xfs_agblock_t agbno;
xfs_agblock_t agbno_next;
@ -837,7 +835,7 @@ xreap_bmapi_binval(
*/
while (bno < agbno_next) {
struct xrep_bufscan scan = {
.daddr = XFS_AGB_TO_DADDR(mp, agno, bno),
.daddr = xfs_agbno_to_daddr(pag, bno),
.max_sectors = xrep_bufscan_max_sectors(mp,
scan_blocks),
.daddr_step = XFS_FSB_TO_BB(mp, 1),

3
fs/xfs/scrub/refcount.c
View File

@ -453,7 +453,8 @@ xchk_refcountbt_rec(
struct xchk_refcbt_records *rrc = bs->private;
xfs_refcount_btrec_to_irec(rec, &irec);
if (xfs_refcount_check_irec(bs->cur->bc_ag.pag, &irec) != NULL) {
if (xfs_refcount_check_irec(to_perag(bs->cur->bc_group), &irec) !=
NULL) {
xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
return 0;
}

7
fs/xfs/scrub/refcount_repair.c
View File

@ -215,7 +215,7 @@ xrep_refc_rmap_shareable(
return false;
/* Metadata in files are never shareable */
if (xfs_internal_inum(mp, rmap->rm_owner))
if (xfs_is_sb_inum(mp, rmap->rm_owner))
return false;
/* Metadata and unwritten file blocks are not shareable. */
@ -590,7 +590,6 @@ xrep_refc_build_new_tree(
struct xfs_scrub *sc = rr->sc;
struct xfs_btree_cur *refc_cur;
struct xfs_perag *pag = sc->sa.pag;
xfs_fsblock_t fsbno;
int error;
error = xrep_refc_sort_records(rr);
@ -603,8 +602,8 @@ xrep_refc_build_new_tree(
* to root the new btree while it's under construction and before we
* attach it to the AG header.
*/
fsbno = XFS_AGB_TO_FSB(sc->mp, pag->pag_agno, xfs_refc_block(sc->mp));
xrep_newbt_init_ag(&rr->new_btree, sc, &XFS_RMAP_OINFO_REFC, fsbno,
xrep_newbt_init_ag(&rr->new_btree, sc, &XFS_RMAP_OINFO_REFC,
xfs_agbno_to_fsb(pag, xfs_refc_block(sc->mp)),
XFS_AG_RESV_METADATA);
rr->new_btree.bload.get_records = xrep_refc_get_records;
rr->new_btree.bload.claim_block = xrep_refc_claim_block;

61
fs/xfs/scrub/repair.c
View File

@ -21,6 +21,7 @@
#include "xfs_rmap.h"
#include "xfs_rmap_btree.h"
#include "xfs_refcount_btree.h"
#include "xfs_rtbitmap.h"
#include "xfs_extent_busy.h"
#include "xfs_ag.h"
#include "xfs_ag_resv.h"
@ -305,7 +306,7 @@ xrep_calc_ag_resblks(
/* Now grab the block counters from the AGF. */
error = xfs_alloc_read_agf(pag, NULL, 0, &bp);
if (error) {
aglen = pag->block_count;
aglen = pag_group(pag)->xg_block_count;
freelen = aglen;
usedlen = aglen;
} else {
@ -325,16 +326,14 @@ xrep_calc_ag_resblks(
/* If the block counts are impossible, make worst-case assumptions. */
if (aglen == NULLAGBLOCK ||
aglen != pag->block_count ||
aglen != pag_group(pag)->xg_block_count ||
freelen >= aglen) {
aglen = pag->block_count;
aglen = pag_group(pag)->xg_block_count;
freelen = aglen;
usedlen = aglen;
}
xfs_perag_put(pag);
trace_xrep_calc_ag_resblks(mp, sm->sm_agno, icount, aglen,
freelen, usedlen);
trace_xrep_calc_ag_resblks(pag, icount, aglen, freelen, usedlen);
/*
* Figure out how many blocks we'd need worst case to rebuild
@ -372,8 +371,9 @@ xrep_calc_ag_resblks(
rmapbt_sz = 0;
}
trace_xrep_calc_ag_resblks_btsize(mp, sm->sm_agno, bnobt_sz,
inobt_sz, rmapbt_sz, refcbt_sz);
trace_xrep_calc_ag_resblks_btsize(pag, bnobt_sz, inobt_sz, rmapbt_sz,
refcbt_sz);
xfs_perag_put(pag);
return max(max(bnobt_sz, inobt_sz), max(rmapbt_sz, refcbt_sz));
}
@ -414,7 +414,7 @@ xrep_fix_freelist(
args.mp = sc->mp;
args.tp = sc->tp;
args.agno = sc->sa.pag->pag_agno;
args.agno = pag_agno(sc->sa.pag);
args.alignment = 1;
args.pag = sc->sa.pag;
@ -483,7 +483,7 @@ xrep_findroot_block(
int block_level;
int error = 0;
daddr = XFS_AGB_TO_DADDR(mp, ri->sc->sa.pag->pag_agno, agbno);
daddr = xfs_agbno_to_daddr(ri->sc->sa.pag, agbno);
/*
* Blocks in the AGFL have stale contents that might just happen to
@ -612,7 +612,7 @@ xrep_findroot_block(
else
fab->root = NULLAGBLOCK;
trace_xrep_findroot_block(mp, ri->sc->sa.pag->pag_agno, agbno,
trace_xrep_findroot_block(ri->sc->sa.pag, agbno,
be32_to_cpu(btblock->bb_magic), fab->height - 1);
out:
xfs_trans_brelse(ri->sc->tp, bp);
@ -953,6 +953,29 @@ xrep_ag_init(
return 0;
}
#ifdef CONFIG_XFS_RT
/*
* Given a reference to a rtgroup structure, lock rtgroup btree inodes and
* create btree cursors. Must only be called to repair a regular rt file.
*/
int
xrep_rtgroup_init(
struct xfs_scrub *sc,
struct xfs_rtgroup *rtg,
struct xchk_rt *sr,
unsigned int rtglock_flags)
{
ASSERT(sr->rtg == NULL);
xfs_rtgroup_lock(rtg, rtglock_flags);
sr->rtlock_flags = rtglock_flags;
/* Grab our own passive reference from the caller's ref. */
sr->rtg = xfs_rtgroup_hold(rtg);
return 0;
}
#endif /* CONFIG_XFS_RT */
/* Reinitialize the per-AG block reservation for the AG we just fixed. */
int
xrep_reset_perag_resv(
@ -973,7 +996,7 @@ xrep_reset_perag_resv(
if (error == -ENOSPC) {
xfs_err(sc->mp,
"Insufficient free space to reset per-AG reservation for AG %u after repair.",
sc->sa.pag->pag_agno);
pag_agno(sc->sa.pag));
error = 0;
}
@ -1083,7 +1106,12 @@ xrep_metadata_inode_forks(
if (error)
return error;
/* Make sure the attr fork looks ok before we delete it. */
/*
* Metadata files can only have extended attributes on metadir
* filesystems, either for parent pointers or for actual xattr data.
* For a non-metadir filesystem, make sure the attr fork looks ok
* before we delete it.
*/
if (xfs_inode_hasattr(sc->ip)) {
error = xrep_metadata_inode_subtype(sc, XFS_SCRUB_TYPE_BMBTA);
if (error)
@ -1099,8 +1127,11 @@ xrep_metadata_inode_forks(
return error;
}
/* Clear the attr forks since metadata shouldn't have that. */
if (xfs_inode_hasattr(sc->ip)) {
/*
* Metadata files on non-metadir filesystems cannot have attr forks,
* so clear them now.
*/
if (xfs_inode_hasattr(sc->ip) && !xfs_has_metadir(sc->mp)) {
if (!dirty) {
dirty = true;
xfs_trans_ijoin(sc->tp, sc->ip, 0);

13
fs/xfs/scrub/repair.h
View File

@ -8,6 +8,7 @@
#include "xfs_quota_defs.h"
struct xfs_rtgroup;
struct xchk_stats_run;
static inline int xrep_notsupported(struct xfs_scrub *sc)
@ -106,6 +107,12 @@ int xrep_setup_inode(struct xfs_scrub *sc, const struct xfs_imap *imap);
void xrep_ag_btcur_init(struct xfs_scrub *sc, struct xchk_ag *sa);
int xrep_ag_init(struct xfs_scrub *sc, struct xfs_perag *pag,
struct xchk_ag *sa);
#ifdef CONFIG_XFS_RT
int xrep_rtgroup_init(struct xfs_scrub *sc, struct xfs_rtgroup *rtg,
struct xchk_rt *sr, unsigned int rtglock_flags);
#else
# define xrep_rtgroup_init(sc, rtg, sr, lockflags) (-ENOSYS)
#endif /* CONFIG_XFS_RT */
/* Metadata revalidators */
@ -134,13 +141,16 @@ int xrep_directory(struct xfs_scrub *sc);
int xrep_parent(struct xfs_scrub *sc);
int xrep_symlink(struct xfs_scrub *sc);
int xrep_dirtree(struct xfs_scrub *sc);
int xrep_metapath(struct xfs_scrub *sc);
#ifdef CONFIG_XFS_RT
int xrep_rtbitmap(struct xfs_scrub *sc);
int xrep_rtsummary(struct xfs_scrub *sc);
int xrep_rgsuperblock(struct xfs_scrub *sc);
#else
# define xrep_rtbitmap xrep_notsupported
# define xrep_rtsummary xrep_notsupported
# define xrep_rgsuperblock xrep_notsupported
#endif /* CONFIG_XFS_RT */
#ifdef CONFIG_XFS_QUOTA
@ -208,6 +218,7 @@ xrep_setup_nothing(
#define xrep_setup_parent xrep_setup_nothing
#define xrep_setup_nlinks xrep_setup_nothing
#define xrep_setup_dirtree xrep_setup_nothing
#define xrep_setup_metapath xrep_setup_nothing
#define xrep_setup_inode(sc, imap) ((void)0)
@ -243,6 +254,8 @@ static inline int xrep_setup_symlink(struct xfs_scrub *sc, unsigned int *x)
#define xrep_parent xrep_notsupported
#define xrep_symlink xrep_notsupported
#define xrep_dirtree xrep_notsupported
#define xrep_metapath xrep_notsupported
#define xrep_rgsuperblock xrep_notsupported
#endif /* CONFIG_XFS_ONLINE_REPAIR */

84
fs/xfs/scrub/rgsuper.c Normal file
View File

@ -0,0 +1,84 @@
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Copyright (c) 2022-2024 Oracle. All Rights Reserved.
* Author: Darrick J. Wong <djwong@kernel.org>
*/
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_rtgroup.h"
#include "xfs_log_format.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/repair.h"
/* Set us up with a transaction and an empty context. */
int
xchk_setup_rgsuperblock(
struct xfs_scrub *sc)
{
return xchk_trans_alloc(sc, 0);
}
/* Cross-reference with the other rt metadata. */
STATIC void
xchk_rgsuperblock_xref(
struct xfs_scrub *sc)
{
if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
return;
xchk_xref_is_used_rt_space(sc, xfs_rgbno_to_rtb(sc->sr.rtg, 0), 1);
}
int
xchk_rgsuperblock(
struct xfs_scrub *sc)
{
xfs_rgnumber_t rgno = sc->sm->sm_agno;
int error;
/*
* Only rtgroup 0 has a superblock. We may someday want to use higher
* rgno for other functions, similar to what we do with the primary
* super scrub function.
*/
if (rgno != 0)
return -ENOENT;
/*
* Grab an active reference to the rtgroup structure. If we can't get
* it, we're racing with something that's tearing down the group, so
* signal that the group no longer exists. Take the rtbitmap in shared
* mode so that the group can't change while we're doing things.
*/
error = xchk_rtgroup_init_existing(sc, rgno, &sc->sr);
if (!xchk_xref_process_error(sc, 0, 0, &error))
return error;
xchk_rtgroup_lock(&sc->sr, XFS_RTGLOCK_BITMAP_SHARED);
/*
* Since we already validated the rt superblock at mount time, we don't
* need to check its contents again. All we need is to cross-reference.
*/
xchk_rgsuperblock_xref(sc);
return 0;
}
#ifdef CONFIG_XFS_ONLINE_REPAIR
int
xrep_rgsuperblock(
struct xfs_scrub *sc)
{
ASSERT(rtg_rgno(sc->sr.rtg) == 0);
xfs_log_sb(sc->tp);
return 0;
}
#endif /* CONFIG_XFS_ONLINE_REPAIR */

4
fs/xfs/scrub/rmap.c
View File

@ -358,7 +358,7 @@ xchk_rmapbt_rec(
struct xfs_rmap_irec irec;
if (xfs_rmap_btrec_to_irec(rec, &irec) != NULL ||
xfs_rmap_check_irec(bs->cur->bc_ag.pag, &irec) != NULL) {
xfs_rmap_check_irec(to_perag(bs->cur->bc_group), &irec) != NULL) {
xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
return 0;
}
@ -410,7 +410,7 @@ xchk_rmapbt_walk_ag_metadata(
goto out;
/* OWN_LOG: Internal log */
if (xfs_ag_contains_log(mp, sc->sa.pag->pag_agno)) {
if (xfs_ag_contains_log(mp, pag_agno(sc->sa.pag))) {
error = xagb_bitmap_set(&cr->log_owned,
XFS_FSB_TO_AGBNO(mp, mp->m_sb.sb_logstart),
mp->m_sb.sb_logblocks);

25
fs/xfs/scrub/rmap_repair.c
View File

@ -231,7 +231,7 @@ xrep_rmap_stash(
if (xchk_iscan_aborted(&rr->iscan))
return -EFSCORRUPTED;
trace_xrep_rmap_found(sc->mp, sc->sa.pag->pag_agno, &rmap);
trace_xrep_rmap_found(sc->sa.pag, &rmap);
mutex_lock(&rr->lock);
mcur = xfs_rmapbt_mem_cursor(sc->sa.pag, sc->tp, &rr->rmap_btree);
@ -344,7 +344,7 @@ xrep_rmap_visit_bmbt(
int error;
if (XFS_FSB_TO_AGNO(mp, rec->br_startblock) !=
rf->rr->sc->sa.pag->pag_agno)
pag_agno(rf->rr->sc->sa.pag))
return 0;
agbno = XFS_FSB_TO_AGBNO(mp, rec->br_startblock);
@ -391,7 +391,7 @@ xrep_rmap_visit_iroot_btree_block(
return 0;
fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, xfs_buf_daddr(bp));
if (XFS_FSB_TO_AGNO(cur->bc_mp, fsbno) != rf->rr->sc->sa.pag->pag_agno)
if (XFS_FSB_TO_AGNO(cur->bc_mp, fsbno) != pag_agno(rf->rr->sc->sa.pag))
return 0;
agbno = XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno);
@ -622,7 +622,7 @@ xrep_rmap_walk_inobt(
return error;
xfs_inobt_btrec_to_irec(mp, rec, &irec);
if (xfs_inobt_check_irec(cur->bc_ag.pag, &irec) != NULL)
if (xfs_inobt_check_irec(to_perag(cur->bc_group), &irec) != NULL)
return -EFSCORRUPTED;
agino = irec.ir_startino;
@ -801,7 +801,7 @@ xrep_rmap_find_log_rmaps(
{
struct xfs_scrub *sc = rr->sc;
if (!xfs_ag_contains_log(sc->mp, sc->sa.pag->pag_agno))
if (!xfs_ag_contains_log(sc->mp, pag_agno(sc->sa.pag)))
return 0;
return xrep_rmap_stash(rr,
@ -976,7 +976,7 @@ xrep_rmap_try_reserve(
{
struct xrep_rmap_agfl ra = {
.bitmap = freesp_blocks,
.agno = rr->sc->sa.pag->pag_agno,
.agno = pag_agno(rr->sc->sa.pag),
};
struct xfs_scrub *sc = rr->sc;
struct xrep_newbt_resv *resv, *n;
@ -1272,7 +1272,6 @@ xrep_rmap_build_new_tree(
struct xfs_perag *pag = sc->sa.pag;
struct xfs_agf *agf = sc->sa.agf_bp->b_addr;
struct xfs_btree_cur *rmap_cur;
xfs_fsblock_t fsbno;
int error;
/*
@ -1290,9 +1289,9 @@ xrep_rmap_build_new_tree(
* rmapbt per-AG reservation, which we will adjust further after
* committing the new btree.
*/
fsbno = XFS_AGB_TO_FSB(sc->mp, pag->pag_agno, XFS_RMAP_BLOCK(sc->mp));
xrep_newbt_init_ag(&rr->new_btree, sc, &XFS_RMAP_OINFO_SKIP_UPDATE,
fsbno, XFS_AG_RESV_RMAPBT);
xfs_agbno_to_fsb(pag, XFS_RMAP_BLOCK(sc->mp)),
XFS_AG_RESV_RMAPBT);
rr->new_btree.bload.get_records = xrep_rmap_get_records;
rr->new_btree.bload.claim_block = xrep_rmap_claim_block;
rr->new_btree.alloc_vextent = xrep_rmap_alloc_vextent;
@ -1553,7 +1552,7 @@ xrep_rmapbt_live_update(
if (!xrep_rmapbt_want_live_update(&rr->iscan, &p->oinfo))
goto out_unlock;
trace_xrep_rmap_live_update(mp, rr->sc->sa.pag->pag_agno, action, p);
trace_xrep_rmap_live_update(rr->sc->sa.pag, action, p);
error = xrep_trans_alloc_hook_dummy(mp, &txcookie, &tp);
if (error)
@ -1597,7 +1596,7 @@ xrep_rmap_setup_scan(
/* Set up in-memory rmap btree */
error = xfs_rmapbt_mem_init(sc->mp, &rr->rmap_btree, sc->xmbtp,
sc->sa.pag->pag_agno);
pag_agno(sc->sa.pag));
if (error)
goto out_mutex;
@ -1612,7 +1611,7 @@ xrep_rmap_setup_scan(
*/
ASSERT(sc->flags & XCHK_FSGATES_RMAP);
xfs_rmap_hook_setup(&rr->rhook, xrep_rmapbt_live_update);
error = xfs_rmap_hook_add(sc->sa.pag, &rr->rhook);
error = xfs_rmap_hook_add(pag_group(sc->sa.pag), &rr->rhook);
if (error)
goto out_iscan;
return 0;
@ -1633,7 +1632,7 @@ xrep_rmap_teardown(
struct xfs_scrub *sc = rr->sc;
xchk_iscan_abort(&rr->iscan);
xfs_rmap_hook_del(sc->sa.pag, &rr->rhook);
xfs_rmap_hook_del(pag_group(sc->sa.pag), &rr->rhook);
xchk_iscan_teardown(&rr->iscan);
xfbtree_destroy(&rr->rmap_btree);
mutex_destroy(&rr->lock);

54
fs/xfs/scrub/rtbitmap.c
View File

@ -35,6 +35,10 @@ xchk_setup_rtbitmap(
return -ENOMEM;
sc->buf = rtb;
error = xchk_rtgroup_init(sc, sc->sm->sm_agno, &sc->sr);
if (error)
return error;
if (xchk_could_repair(sc)) {
error = xrep_setup_rtbitmap(sc, rtb);
if (error)
@ -45,7 +49,8 @@ xchk_setup_rtbitmap(
if (error)
return error;
error = xchk_install_live_inode(sc, sc->mp->m_rbmip);
error = xchk_install_live_inode(sc,
sc->sr.rtg->rtg_inodes[XFS_RTGI_BITMAP]);
if (error)
return error;
@ -53,18 +58,18 @@ xchk_setup_rtbitmap(
if (error)
return error;
xchk_ilock(sc, XFS_ILOCK_EXCL | XFS_ILOCK_RTBITMAP);
/*
* Now that we've locked the rtbitmap, we can't race with growfsrt
* trying to expand the bitmap or change the size of the rt volume.
* Hence it is safe to compute and check the geometry values.
*/
xchk_rtgroup_lock(&sc->sr, XFS_RTGLOCK_BITMAP);
if (mp->m_sb.sb_rblocks) {
rtb->rextents = xfs_rtb_to_rtx(mp, mp->m_sb.sb_rblocks);
rtb->rextents = xfs_blen_to_rtbxlen(mp, mp->m_sb.sb_rblocks);
rtb->rextslog = xfs_compute_rextslog(rtb->rextents);
rtb->rbmblocks = xfs_rtbitmap_blockcount(mp, rtb->rextents);
rtb->rbmblocks = xfs_rtbitmap_blockcount(mp);
}
return 0;
}
@ -73,7 +78,7 @@ xchk_setup_rtbitmap(
/* Scrub a free extent record from the realtime bitmap. */
STATIC int
xchk_rtbitmap_rec(
struct xfs_mount *mp,
struct xfs_rtgroup *rtg,
struct xfs_trans *tp,
const struct xfs_rtalloc_rec *rec,
void *priv)
@ -82,10 +87,10 @@ xchk_rtbitmap_rec(
xfs_rtblock_t startblock;
xfs_filblks_t blockcount;
startblock = xfs_rtx_to_rtb(mp, rec->ar_startext);
blockcount = xfs_rtx_to_rtb(mp, rec->ar_extcount);
startblock = xfs_rtx_to_rtb(rtg, rec->ar_startext);
blockcount = xfs_rtxlen_to_extlen(rtg_mount(rtg), rec->ar_extcount);
if (!xfs_verify_rtbext(mp, startblock, blockcount))
if (!xfs_verify_rtbext(rtg_mount(rtg), startblock, blockcount))
xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
return 0;
}
@ -140,18 +145,20 @@ xchk_rtbitmap(
struct xfs_scrub *sc)
{
struct xfs_mount *mp = sc->mp;
struct xfs_rtgroup *rtg = sc->sr.rtg;
struct xfs_inode *rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP];
struct xchk_rtbitmap *rtb = sc->buf;
int error;
/* Is sb_rextents correct? */
if (mp->m_sb.sb_rextents != rtb->rextents) {
xchk_ino_set_corrupt(sc, mp->m_rbmip->i_ino);
xchk_ino_set_corrupt(sc, rbmip->i_ino);
return 0;
}
/* Is sb_rextslog correct? */
if (mp->m_sb.sb_rextslog != rtb->rextslog) {
xchk_ino_set_corrupt(sc, mp->m_rbmip->i_ino);
xchk_ino_set_corrupt(sc, rbmip->i_ino);
return 0;
}
@ -160,17 +167,17 @@ xchk_rtbitmap(
* case can we exceed 4bn bitmap blocks since the super field is a u32.
*/
if (rtb->rbmblocks > U32_MAX) {
xchk_ino_set_corrupt(sc, mp->m_rbmip->i_ino);
xchk_ino_set_corrupt(sc, rbmip->i_ino);
return 0;
}
if (mp->m_sb.sb_rbmblocks != rtb->rbmblocks) {
xchk_ino_set_corrupt(sc, mp->m_rbmip->i_ino);
xchk_ino_set_corrupt(sc, rbmip->i_ino);
return 0;
}
/* The bitmap file length must be aligned to an fsblock. */
if (mp->m_rbmip->i_disk_size & mp->m_blockmask) {
xchk_ino_set_corrupt(sc, mp->m_rbmip->i_ino);
if (rbmip->i_disk_size & mp->m_blockmask) {
xchk_ino_set_corrupt(sc, rbmip->i_ino);
return 0;
}
@ -179,8 +186,8 @@ xchk_rtbitmap(
* growfsrt expands the bitmap file before updating sb_rextents, so the
* file can be larger than sb_rbmblocks.
*/
if (mp->m_rbmip->i_disk_size < XFS_FSB_TO_B(mp, rtb->rbmblocks)) {
xchk_ino_set_corrupt(sc, mp->m_rbmip->i_ino);
if (rbmip->i_disk_size < XFS_FSB_TO_B(mp, rtb->rbmblocks)) {
xchk_ino_set_corrupt(sc, rbmip->i_ino);
return 0;
}
@ -193,7 +200,7 @@ xchk_rtbitmap(
if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
return error;
error = xfs_rtalloc_query_all(mp, sc->tp, xchk_rtbitmap_rec, sc);
error = xfs_rtalloc_query_all(rtg, sc->tp, xchk_rtbitmap_rec, sc);
if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
return error;
@ -207,6 +214,8 @@ xchk_xref_is_used_rt_space(
xfs_rtblock_t rtbno,
xfs_extlen_t len)
{
struct xfs_rtgroup *rtg = sc->sr.rtg;
struct xfs_inode *rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP];
xfs_rtxnum_t startext;
xfs_rtxnum_t endext;
bool is_free;
@ -217,13 +226,10 @@ xchk_xref_is_used_rt_space(
startext = xfs_rtb_to_rtx(sc->mp, rtbno);
endext = xfs_rtb_to_rtx(sc->mp, rtbno + len - 1);
xfs_ilock(sc->mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
error = xfs_rtalloc_extent_is_free(sc->mp, sc->tp, startext,
error = xfs_rtalloc_extent_is_free(rtg, sc->tp, startext,
endext - startext + 1, &is_free);
if (!xchk_should_check_xref(sc, &error, NULL))
goto out_unlock;
return;
if (is_free)
xchk_ino_xref_set_corrupt(sc, sc->mp->m_rbmip->i_ino);
out_unlock:
xfs_iunlock(sc->mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
xchk_ino_xref_set_corrupt(sc, rbmip->i_ino);
}

116
fs/xfs/scrub/rtsummary.c
View File

@ -18,6 +18,7 @@
#include "xfs_bmap.h"
#include "xfs_sb.h"
#include "xfs_exchmaps.h"
#include "xfs_rtgroup.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/trace.h"
@ -46,12 +47,19 @@ xchk_setup_rtsummary(
struct xchk_rtsummary *rts;
int error;
if (xchk_need_intent_drain(sc))
xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN);
rts = kvzalloc(struct_size(rts, words, mp->m_blockwsize),
XCHK_GFP_FLAGS);
if (!rts)
return -ENOMEM;
sc->buf = rts;
error = xchk_rtgroup_init(sc, sc->sm->sm_agno, &sc->sr);
if (error)
return error;
if (xchk_could_repair(sc)) {
error = xrep_setup_rtsummary(sc, rts);
if (error)
@ -73,7 +81,8 @@ xchk_setup_rtsummary(
if (error)
return error;
error = xchk_install_live_inode(sc, mp->m_rsumip);
error = xchk_install_live_inode(sc,
sc->sr.rtg->rtg_inodes[XFS_RTGI_SUMMARY]);
if (error)
return error;
@ -81,30 +90,24 @@ xchk_setup_rtsummary(
if (error)
return error;
/*
* Locking order requires us to take the rtbitmap first. We must be
* careful to unlock it ourselves when we are done with the rtbitmap
* file since the scrub infrastructure won't do that for us. Only
* then we can lock the rtsummary inode.
*/
xfs_ilock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
xchk_ilock(sc, XFS_ILOCK_EXCL | XFS_ILOCK_RTSUM);
/*
* Now that we've locked the rtbitmap and rtsummary, we can't race with
* growfsrt trying to expand the summary or change the size of the rt
* volume. Hence it is safe to compute and check the geometry values.
*
* Note that there is no strict requirement for an exclusive lock on the
* summary here, but to keep the locking APIs simple we lock both inodes
* exclusively here. If we ever start caring about running concurrent
* fsmap with scrub this could be changed.
*/
xchk_rtgroup_lock(&sc->sr, XFS_RTGLOCK_BITMAP);
if (mp->m_sb.sb_rblocks) {
int rextslog;
rts->rextents = xfs_rtb_to_rtx(mp, mp->m_sb.sb_rblocks);
rextslog = xfs_compute_rextslog(rts->rextents);
rts->rsumlevels = rextslog + 1;
rts->rbmblocks = xfs_rtbitmap_blockcount(mp, rts->rextents);
rts->rsumblocks = xfs_rtsummary_blockcount(mp, rts->rsumlevels,
rts->rbmblocks);
rts->rextents = xfs_blen_to_rtbxlen(mp, mp->m_sb.sb_rblocks);
rts->rbmblocks = xfs_rtbitmap_blockcount(mp);
rts->rsumblocks =
xfs_rtsummary_blockcount(mp, &rts->rsumlevels);
}
return 0;
}
@ -148,6 +151,11 @@ xchk_rtsum_inc(
struct xfs_mount *mp,
union xfs_suminfo_raw *v)
{
if (xfs_has_rtgroups(mp)) {
be32_add_cpu(&v->rtg, 1);
return be32_to_cpu(v->rtg);
}
v->old += 1;
return v->old;
}
@ -155,11 +163,12 @@ xchk_rtsum_inc(
/* Update the summary file to reflect the free extent that we've accumulated. */
STATIC int
xchk_rtsum_record_free(
struct xfs_mount *mp,
struct xfs_rtgroup *rtg,
struct xfs_trans *tp,
const struct xfs_rtalloc_rec *rec,
void *priv)
{
struct xfs_mount *mp = rtg_mount(rtg);
struct xfs_scrub *sc = priv;
xfs_fileoff_t rbmoff;
xfs_rtblock_t rtbno;
@ -178,11 +187,12 @@ xchk_rtsum_record_free(
lenlog = xfs_highbit64(rec->ar_extcount);
offs = xfs_rtsumoffs(mp, lenlog, rbmoff);
rtbno = xfs_rtx_to_rtb(mp, rec->ar_startext);
rtlen = xfs_rtx_to_rtb(mp, rec->ar_extcount);
rtbno = xfs_rtx_to_rtb(rtg, rec->ar_startext);
rtlen = xfs_rtxlen_to_extlen(mp, rec->ar_extcount);
if (!xfs_verify_rtbext(mp, rtbno, rtlen)) {
xchk_ino_xref_set_corrupt(sc, mp->m_rbmip->i_ino);
xchk_ino_xref_set_corrupt(sc,
rtg->rtg_inodes[XFS_RTGI_BITMAP]->i_ino);
return -EFSCORRUPTED;
}
@ -204,15 +214,14 @@ xchk_rtsum_compute(
struct xfs_scrub *sc)
{
struct xfs_mount *mp = sc->mp;
unsigned long long rtbmp_blocks;
struct xfs_rtgroup *rtg = sc->sr.rtg;
/* If the bitmap size doesn't match the computed size, bail. */
rtbmp_blocks = xfs_rtbitmap_blockcount(mp, mp->m_sb.sb_rextents);
if (XFS_FSB_TO_B(mp, rtbmp_blocks) != mp->m_rbmip->i_disk_size)
if (XFS_FSB_TO_B(mp, xfs_rtbitmap_blockcount(mp)) !=
rtg->rtg_inodes[XFS_RTGI_BITMAP]->i_disk_size)
return -EFSCORRUPTED;
return xfs_rtalloc_query_all(sc->mp, sc->tp, xchk_rtsum_record_free,
sc);
return xfs_rtalloc_query_all(rtg, sc->tp, xchk_rtsum_record_free, sc);
}
/* Compare the rtsummary file against the one we computed. */
@ -231,8 +240,9 @@ xchk_rtsum_compare(
xfs_rtsumoff_t sumoff = 0;
int error = 0;
rts->args.mp = sc->mp;
rts->args.mp = mp;
rts->args.tp = sc->tp;
rts->args.rtg = sc->sr.rtg;
/* Mappings may not cross or lie beyond EOF. */
endoff = XFS_B_TO_FSB(mp, ip->i_disk_size);
@ -299,31 +309,34 @@ xchk_rtsummary(
struct xfs_scrub *sc)
{
struct xfs_mount *mp = sc->mp;
struct xfs_rtgroup *rtg = sc->sr.rtg;
struct xfs_inode *rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP];
struct xfs_inode *rsumip = rtg->rtg_inodes[XFS_RTGI_SUMMARY];
struct xchk_rtsummary *rts = sc->buf;
int error = 0;
int error;
/* Is sb_rextents correct? */
if (mp->m_sb.sb_rextents != rts->rextents) {
xchk_ino_set_corrupt(sc, mp->m_rbmip->i_ino);
goto out_rbm;
xchk_ino_set_corrupt(sc, rbmip->i_ino);
return 0;
}
/* Is m_rsumlevels correct? */
if (mp->m_rsumlevels != rts->rsumlevels) {
xchk_ino_set_corrupt(sc, mp->m_rsumip->i_ino);
goto out_rbm;
xchk_ino_set_corrupt(sc, rsumip->i_ino);
return 0;
}
/* Is m_rsumsize correct? */
if (mp->m_rsumblocks != rts->rsumblocks) {
xchk_ino_set_corrupt(sc, mp->m_rsumip->i_ino);
goto out_rbm;
xchk_ino_set_corrupt(sc, rsumip->i_ino);
return 0;
}
/* The summary file length must be aligned to an fsblock. */
if (mp->m_rsumip->i_disk_size & mp->m_blockmask) {
xchk_ino_set_corrupt(sc, mp->m_rsumip->i_ino);
goto out_rbm;
if (rsumip->i_disk_size & mp->m_blockmask) {
xchk_ino_set_corrupt(sc, rsumip->i_ino);
return 0;
}
/*
@ -331,15 +344,15 @@ xchk_rtsummary(
* growfsrt expands the summary file before updating sb_rextents, so
* the file can be larger than rsumsize.
*/
if (mp->m_rsumip->i_disk_size < XFS_FSB_TO_B(mp, rts->rsumblocks)) {
xchk_ino_set_corrupt(sc, mp->m_rsumip->i_ino);
goto out_rbm;
if (rsumip->i_disk_size < XFS_FSB_TO_B(mp, rts->rsumblocks)) {
xchk_ino_set_corrupt(sc, rsumip->i_ino);
return 0;
}
/* Invoke the fork scrubber. */
error = xchk_metadata_inode_forks(sc);
if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
goto out_rbm;
return error;
/* Construct the new summary file from the rtbitmap. */
error = xchk_rtsum_compute(sc);
@ -348,23 +361,12 @@ xchk_rtsummary(
* EFSCORRUPTED means the rtbitmap is corrupt, which is an xref
* error since we're checking the summary file.
*/
xchk_ino_xref_set_corrupt(sc, mp->m_rbmip->i_ino);
error = 0;
goto out_rbm;
xchk_ino_set_corrupt(sc, rbmip->i_ino);
return 0;
}
if (error)
goto out_rbm;
return error;
/* Does the computed summary file match the actual rtsummary file? */
error = xchk_rtsum_compare(sc);
out_rbm:
/*
* Unlock the rtbitmap since we're done with it. All other writers of
* the rt free space metadata grab the bitmap and summary ILOCKs in
* that order, so we're still protected against allocation activities
* even if we continue on to the repair function.
*/
xfs_iunlock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
return error;
return xchk_rtsum_compare(sc);
}

22
fs/xfs/scrub/rtsummary_repair.c
View File

@ -76,18 +76,30 @@ xrep_rtsummary_prep_buf(
union xfs_suminfo_raw *ondisk;
int error;
rts->args.mp = sc->mp;
rts->args.mp = mp;
rts->args.tp = sc->tp;
rts->args.rtg = sc->sr.rtg;
rts->args.sumbp = bp;
ondisk = xfs_rsumblock_infoptr(&rts->args, 0);
rts->args.sumbp = NULL;
bp->b_ops = &xfs_rtbuf_ops;
error = xfsum_copyout(sc, rts->prep_wordoff, ondisk, mp->m_blockwsize);
if (error)
return error;
if (xfs_has_rtgroups(sc->mp)) {
struct xfs_rtbuf_blkinfo *hdr = bp->b_addr;
hdr->rt_magic = cpu_to_be32(XFS_RTSUMMARY_MAGIC);
hdr->rt_owner = cpu_to_be64(sc->ip->i_ino);
hdr->rt_blkno = cpu_to_be64(xfs_buf_daddr(bp));
hdr->rt_lsn = 0;
uuid_copy(&hdr->rt_uuid, &sc->mp->m_sb.sb_meta_uuid);
bp->b_ops = &xfs_rtsummary_buf_ops;
} else {
bp->b_ops = &xfs_rtbuf_ops;
}
rts->prep_wordoff += mp->m_blockwsize;
xfs_trans_buf_set_type(sc->tp, bp, XFS_BLFT_RTSUMMARY_BUF);
return 0;
@ -162,8 +174,8 @@ xrep_rtsummary(
return error;
/* Reset incore state and blow out the summary cache. */
if (mp->m_rsum_cache)
memset(mp->m_rsum_cache, 0xFF, mp->m_sb.sb_rbmblocks);
if (sc->sr.rtg->rtg_rsum_cache)
memset(sc->sr.rtg->rtg_rsum_cache, 0xFF, mp->m_sb.sb_rbmblocks);
mp->m_rsumlevels = rts->rsumlevels;
mp->m_rsumblocks = rts->rsumblocks;

52
fs/xfs/scrub/scrub.c
View File

@ -225,6 +225,8 @@ xchk_teardown(
xfs_trans_cancel(sc->tp);
sc->tp = NULL;
}
if (sc->sr.rtg)
xchk_rtgroup_free(sc, &sc->sr);
if (sc->ip) {
if (sc->ilock_flags)
xchk_iunlock(sc, sc->ilock_flags);
@ -382,13 +384,13 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
.repair = xrep_parent,
},
[XFS_SCRUB_TYPE_RTBITMAP] = { /* realtime bitmap */
.type = ST_FS,
.type = ST_RTGROUP,
.setup = xchk_setup_rtbitmap,
.scrub = xchk_rtbitmap,
.repair = xrep_rtbitmap,
},
[XFS_SCRUB_TYPE_RTSUM] = { /* realtime summary */
.type = ST_FS,
.type = ST_RTGROUP,
.setup = xchk_setup_rtsummary,
.scrub = xchk_rtsummary,
.repair = xrep_rtsummary,
@ -442,6 +444,20 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
.has = xfs_has_parent,
.repair = xrep_dirtree,
},
[XFS_SCRUB_TYPE_METAPATH] = { /* metadata directory tree path */
.type = ST_GENERIC,
.setup = xchk_setup_metapath,
.scrub = xchk_metapath,
.has = xfs_has_metadir,
.repair = xrep_metapath,
},
[XFS_SCRUB_TYPE_RGSUPER] = { /* realtime group superblock */
.type = ST_RTGROUP,
.setup = xchk_setup_rgsuperblock,
.scrub = xchk_rgsuperblock,
.has = xfs_has_rtsb,
.repair = xrep_rgsuperblock,
},
};
static int
@ -489,6 +505,35 @@ xchk_validate_inputs(
if (sm->sm_agno || (sm->sm_gen && !sm->sm_ino))
goto out;
break;
case ST_GENERIC:
break;
case ST_RTGROUP:
if (sm->sm_ino || sm->sm_gen)
goto out;
if (xfs_has_rtgroups(mp)) {
/*
* On a rtgroups filesystem, there won't be an rtbitmap
* or rtsummary file for group 0 unless there's
* actually a realtime volume attached. However, older
* xfs_scrub always calls the rtbitmap/rtsummary
* scrubbers with sm_agno==0 so transform the error
* code to ENOENT.
*/
if (sm->sm_agno >= mp->m_sb.sb_rgcount) {
if (sm->sm_agno == 0)
error = -ENOENT;
goto out;
}
} else {
/*
* Prior to rtgroups, the rtbitmap/rtsummary scrubbers
* accepted sm_agno==0, so we still accept that for
* scrubbing pre-rtgroups filesystems.
*/
if (sm->sm_agno != 0)
goto out;
}
break;
default:
goto out;
}
@ -605,8 +650,7 @@ xfs_scrub_metadata(
if (error)
goto out;
xfs_warn_mount(mp, XFS_OPSTATE_WARNED_SCRUB,
"EXPERIMENTAL online scrub feature in use. Use at your own risk!");
xfs_warn_experimental(mp, XFS_EXPERIMENTAL_SCRUB);
sc = kzalloc(sizeof(struct xfs_scrub), XCHK_GFP_FLAGS);
if (!sc) {

17
fs/xfs/scrub/scrub.h
View File

@ -73,6 +73,8 @@ enum xchk_type {
ST_PERAG, /* per-AG metadata */
ST_FS, /* per-FS metadata */
ST_INODE, /* per-inode metadata */
ST_GENERIC, /* determined by the scrubber */
ST_RTGROUP, /* rtgroup metadata */
};
struct xchk_meta_ops {
@ -117,6 +119,15 @@ struct xchk_ag {
struct xfs_btree_cur *refc_cur;
};
/* Inode lock state for the RT volume. */
struct xchk_rt {
/* incore rtgroup, if applicable */
struct xfs_rtgroup *rtg;
/* XFS_RTGLOCK_* lock state if locked */
unsigned int rtlock_flags;
};
struct xfs_scrub {
/* General scrub state. */
struct xfs_mount *mp;
@ -178,6 +189,9 @@ struct xfs_scrub {
/* State tracking for single-AG operations. */
struct xchk_ag sa;
/* State tracking for realtime operations. */
struct xchk_rt sr;
};
/* XCHK state flags grow up from zero, XREP state flags grown down from 2^31 */
@ -255,12 +269,15 @@ int xchk_xattr(struct xfs_scrub *sc);
int xchk_symlink(struct xfs_scrub *sc);
int xchk_parent(struct xfs_scrub *sc);
int xchk_dirtree(struct xfs_scrub *sc);
int xchk_metapath(struct xfs_scrub *sc);
#ifdef CONFIG_XFS_RT
int xchk_rtbitmap(struct xfs_scrub *sc);
int xchk_rtsummary(struct xfs_scrub *sc);
int xchk_rgsuperblock(struct xfs_scrub *sc);
#else
# define xchk_rtbitmap xchk_nothing
# define xchk_rtsummary xchk_nothing
# define xchk_rgsuperblock xchk_nothing
#endif
#ifdef CONFIG_XFS_QUOTA
int xchk_quota(struct xfs_scrub *sc);

2
fs/xfs/scrub/stats.c
View File

@ -80,6 +80,8 @@ static const char *name_map[XFS_SCRUB_TYPE_NR] = {
[XFS_SCRUB_TYPE_QUOTACHECK] = "quotacheck",
[XFS_SCRUB_TYPE_NLINKS] = "nlinks",
[XFS_SCRUB_TYPE_DIRTREE] = "dirtree",
[XFS_SCRUB_TYPE_METAPATH] = "metapath",
[XFS_SCRUB_TYPE_RGSUPER] = "rgsuper",
};
/* Format the scrub stats into a text buffer, similar to pcp style. */

105
fs/xfs/scrub/tempfile.c
View File

@ -22,6 +22,7 @@
#include "xfs_exchmaps.h"
#include "xfs_defer.h"
#include "xfs_symlink_remote.h"
#include "xfs_metafile.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/repair.h"
@ -182,6 +183,101 @@ xrep_tempfile_create(
return error;
}
/*
* Temporary files have to be created before we even know which inode we're
* going to scrub, so we assume that they will be part of the regular directory
* tree. If it turns out that we're actually scrubbing a file from the
* metadata directory tree, we have to subtract the temp file from the root
* dquots and detach the dquots.
*/
int
xrep_tempfile_adjust_directory_tree(
struct xfs_scrub *sc)
{
int error;
if (!sc->tempip)
return 0;
ASSERT(sc->tp == NULL);
ASSERT(!xfs_is_metadir_inode(sc->tempip));
if (!sc->ip || !xfs_is_metadir_inode(sc->ip))
return 0;
xfs_ilock(sc->tempip, XFS_IOLOCK_EXCL);
sc->temp_ilock_flags |= XFS_IOLOCK_EXCL;
error = xchk_trans_alloc(sc, 0);
if (error)
goto out_iolock;
xrep_tempfile_ilock(sc);
xfs_trans_ijoin(sc->tp, sc->tempip, 0);
/* Metadir files are not accounted in quota, so drop icount */
xfs_trans_mod_dquot_byino(sc->tp, sc->tempip, XFS_TRANS_DQ_ICOUNT, -1L);
xfs_metafile_set_iflag(sc->tp, sc->tempip, XFS_METAFILE_UNKNOWN);
error = xrep_trans_commit(sc);
if (error)
goto out_ilock;
xfs_qm_dqdetach(sc->tempip);
out_ilock:
xrep_tempfile_iunlock(sc);
out_iolock:
xrep_tempfile_iounlock(sc);
return error;
}
/*
* Remove this temporary file from the metadata directory tree so that it can
* be inactivated the normal way.
*/
STATIC int
xrep_tempfile_remove_metadir(
struct xfs_scrub *sc)
{
int error;
if (!sc->tempip || !xfs_is_metadir_inode(sc->tempip))
return 0;
ASSERT(sc->tp == NULL);
xfs_ilock(sc->tempip, XFS_IOLOCK_EXCL);
sc->temp_ilock_flags |= XFS_IOLOCK_EXCL;
error = xchk_trans_alloc(sc, 0);
if (error)
goto out_iolock;
xrep_tempfile_ilock(sc);
xfs_trans_ijoin(sc->tp, sc->tempip, 0);
xfs_metafile_clear_iflag(sc->tp, sc->tempip);
/* Non-metadir files are accounted in quota, so bump bcount/icount */
error = xfs_qm_dqattach_locked(sc->tempip, false);
if (error)
goto out_cancel;
xfs_trans_mod_dquot_byino(sc->tp, sc->tempip, XFS_TRANS_DQ_ICOUNT, 1L);
xfs_trans_mod_dquot_byino(sc->tp, sc->tempip, XFS_TRANS_DQ_BCOUNT,
sc->tempip->i_nblocks);
error = xrep_trans_commit(sc);
goto out_ilock;
out_cancel:
xchk_trans_cancel(sc);
out_ilock:
xrep_tempfile_iunlock(sc);
out_iolock:
xrep_tempfile_iounlock(sc);
return error;
}
/* Take IOLOCK_EXCL on the temporary file, maybe. */
bool
xrep_tempfile_iolock_nowait(
@ -290,6 +386,7 @@ xrep_tempfile_rele(
sc->temp_ilock_flags = 0;
}
xrep_tempfile_remove_metadir(sc);
xchk_irele(sc, sc->tempip);
sc->tempip = NULL;
}
@ -844,6 +941,14 @@ xrep_is_tempfile(
const struct xfs_inode *ip)
{
const struct inode *inode = &ip->i_vnode;
struct xfs_mount *mp = ip->i_mount;
/*
* Files in the metadata directory tree also have S_PRIVATE set and
* IOP_XATTR unset, so we must distinguish them separately.
*/
if (xfs_has_metadir(mp) && (ip->i_diflags2 & XFS_DIFLAG2_METADATA))
return false;
if (IS_PRIVATE(inode) && !(inode->i_opflags & IOP_XATTR))
return true;

3
fs/xfs/scrub/tempfile.h
View File

@ -10,6 +10,8 @@
int xrep_tempfile_create(struct xfs_scrub *sc, uint16_t mode);
void xrep_tempfile_rele(struct xfs_scrub *sc);
int xrep_tempfile_adjust_directory_tree(struct xfs_scrub *sc);
bool xrep_tempfile_iolock_nowait(struct xfs_scrub *sc);
int xrep_tempfile_iolock_polled(struct xfs_scrub *sc);
void xrep_tempfile_iounlock(struct xfs_scrub *sc);
@ -42,6 +44,7 @@ static inline void xrep_tempfile_iolock_both(struct xfs_scrub *sc)
xchk_ilock(sc, XFS_IOLOCK_EXCL);
}
# define xrep_is_tempfile(ip) (false)
# define xrep_tempfile_adjust_directory_tree(sc) (0)
# define xrep_tempfile_rele(sc)
#endif /* CONFIG_XFS_ONLINE_REPAIR */

1
fs/xfs/scrub/trace.c
View File

@ -20,6 +20,7 @@
#include "xfs_dir2.h"
#include "xfs_rmap.h"
#include "xfs_parent.h"
#include "xfs_metafile.h"
#include "scrub/scrub.h"
#include "scrub/xfile.h"
#include "scrub/xfarray.h"

247
fs/xfs/scrub/trace.h
View File

@ -70,6 +70,8 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_NLINKS);
TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_HEALTHY);
TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_DIRTREE);
TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_BARRIER);
TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_METAPATH);
TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_RGSUPER);
#define XFS_SCRUB_TYPE_STRINGS \
{ XFS_SCRUB_TYPE_PROBE, "probe" }, \
@ -101,7 +103,9 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_BARRIER);
{ XFS_SCRUB_TYPE_NLINKS, "nlinks" }, \
{ XFS_SCRUB_TYPE_HEALTHY, "healthy" }, \
{ XFS_SCRUB_TYPE_DIRTREE, "dirtree" }, \
{ XFS_SCRUB_TYPE_BARRIER, "barrier" }
{ XFS_SCRUB_TYPE_BARRIER, "barrier" }, \
{ XFS_SCRUB_TYPE_METAPATH, "metapath" }, \
{ XFS_SCRUB_TYPE_RGSUPER, "rgsuper" }
#define XFS_SCRUB_FLAG_STRINGS \
{ XFS_SCRUB_IFLAG_REPAIR, "repair" }, \
@ -772,12 +776,12 @@ TRACE_EVENT(xchk_xref_error,
);
TRACE_EVENT(xchk_iallocbt_check_cluster,
TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
xfs_agino_t startino, xfs_daddr_t map_daddr,
unsigned short map_len, unsigned int chunk_ino,
unsigned int nr_inodes, uint16_t cluster_mask,
uint16_t holemask, unsigned int cluster_ino),
TP_ARGS(mp, agno, startino, map_daddr, map_len, chunk_ino, nr_inodes,
TP_PROTO(const struct xfs_perag *pag, xfs_agino_t startino,
xfs_daddr_t map_daddr, unsigned short map_len,
unsigned int chunk_ino, unsigned int nr_inodes,
uint16_t cluster_mask, uint16_t holemask,
unsigned int cluster_ino),
TP_ARGS(pag, startino, map_daddr, map_len, chunk_ino, nr_inodes,
cluster_mask, holemask, cluster_ino),
TP_STRUCT__entry(
__field(dev_t, dev)
@ -792,8 +796,8 @@ TRACE_EVENT(xchk_iallocbt_check_cluster,
__field(uint16_t, holemask)
),
TP_fast_assign(
__entry->dev = mp->m_super->s_dev;
__entry->agno = agno;
__entry->dev = pag_mount(pag)->m_super->s_dev;
__entry->agno = pag_agno(pag);
__entry->startino = startino;
__entry->map_daddr = map_daddr;
__entry->map_len = map_len;
@ -922,7 +926,8 @@ DEFINE_XCHK_FSFREEZE_EVENT(xchk_fsfreeze);
DEFINE_XCHK_FSFREEZE_EVENT(xchk_fsthaw);
TRACE_EVENT(xchk_refcount_incorrect,
TP_PROTO(struct xfs_perag *pag, const struct xfs_refcount_irec *irec,
TP_PROTO(const struct xfs_perag *pag,
const struct xfs_refcount_irec *irec,
xfs_nlink_t seen),
TP_ARGS(pag, irec, seen),
TP_STRUCT__entry(
@ -935,8 +940,8 @@ TRACE_EVENT(xchk_refcount_incorrect,
__field(xfs_nlink_t, seen)
),
TP_fast_assign(
__entry->dev = pag->pag_mount->m_super->s_dev;
__entry->agno = pag->pag_agno;
__entry->dev = pag_mount(pag)->m_super->s_dev;
__entry->agno = pag_agno(pag);
__entry->domain = irec->rc_domain;
__entry->startblock = irec->rc_startblock;
__entry->blockcount = irec->rc_blockcount;
@ -1752,6 +1757,7 @@ DEFINE_XCHK_DIRPATH_EVENT(xchk_dirpath_badgen);
DEFINE_XCHK_DIRPATH_EVENT(xchk_dirpath_nondir_parent);
DEFINE_XCHK_DIRPATH_EVENT(xchk_dirpath_unlinked_parent);
DEFINE_XCHK_DIRPATH_EVENT(xchk_dirpath_found_next_step);
DEFINE_XCHK_DIRPATH_EVENT(xchk_dirpath_crosses_tree);
TRACE_DEFINE_ENUM(XCHK_DIRPATH_SCANNING);
TRACE_DEFINE_ENUM(XCHK_DIRPATH_DELETE);
@ -1914,11 +1920,44 @@ TRACE_EVENT(xchk_dirtree_live_update,
__get_str(name))
);
DECLARE_EVENT_CLASS(xchk_metapath_class,
TP_PROTO(struct xfs_scrub *sc, const char *path,
struct xfs_inode *dp, xfs_ino_t ino),
TP_ARGS(sc, path, dp, ino),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(xfs_ino_t, scrub_ino)
__field(xfs_ino_t, parent_ino)
__field(xfs_ino_t, ino)
__string(name, path)
),
TP_fast_assign(
__entry->dev = sc->mp->m_super->s_dev;
__entry->scrub_ino = sc->ip ? sc->ip->i_ino : NULLFSINO;
__entry->parent_ino = dp ? dp->i_ino : NULLFSINO;
__entry->ino = ino;
__assign_str(name);
),
TP_printk("dev %d:%d ino 0x%llx parent_ino 0x%llx name '%s' ino 0x%llx",
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->scrub_ino,
__entry->parent_ino,
__get_str(name),
__entry->ino)
);
#define DEFINE_XCHK_METAPATH_EVENT(name) \
DEFINE_EVENT(xchk_metapath_class, name, \
TP_PROTO(struct xfs_scrub *sc, const char *path, \
struct xfs_inode *dp, xfs_ino_t ino), \
TP_ARGS(sc, path, dp, ino))
DEFINE_XCHK_METAPATH_EVENT(xchk_metapath_lookup);
/* repair tracepoints */
#if IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR)
DECLARE_EVENT_CLASS(xrep_extent_class,
TP_PROTO(struct xfs_perag *pag, xfs_agblock_t agbno, xfs_extlen_t len),
TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno,
xfs_extlen_t len),
TP_ARGS(pag, agbno, len),
TP_STRUCT__entry(
__field(dev_t, dev)
@ -1927,8 +1966,8 @@ DECLARE_EVENT_CLASS(xrep_extent_class,
__field(xfs_extlen_t, len)
),
TP_fast_assign(
__entry->dev = pag->pag_mount->m_super->s_dev;
__entry->agno = pag->pag_agno;
__entry->dev = pag_mount(pag)->m_super->s_dev;
__entry->agno = pag_agno(pag);
__entry->agbno = agbno;
__entry->len = len;
),
@ -1940,7 +1979,8 @@ DECLARE_EVENT_CLASS(xrep_extent_class,
);
#define DEFINE_REPAIR_EXTENT_EVENT(name) \
DEFINE_EVENT(xrep_extent_class, name, \
TP_PROTO(struct xfs_perag *pag, xfs_agblock_t agbno, xfs_extlen_t len), \
TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno, \
xfs_extlen_t len), \
TP_ARGS(pag, agbno, len))
DEFINE_REPAIR_EXTENT_EVENT(xreap_dispose_unmap_extent);
DEFINE_REPAIR_EXTENT_EVENT(xreap_dispose_free_extent);
@ -1949,8 +1989,8 @@ DEFINE_REPAIR_EXTENT_EVENT(xreap_bmapi_binval);
DEFINE_REPAIR_EXTENT_EVENT(xrep_agfl_insert);
DECLARE_EVENT_CLASS(xrep_reap_find_class,
TP_PROTO(struct xfs_perag *pag, xfs_agblock_t agbno, xfs_extlen_t len,
bool crosslinked),
TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno,
xfs_extlen_t len, bool crosslinked),
TP_ARGS(pag, agbno, len, crosslinked),
TP_STRUCT__entry(
__field(dev_t, dev)
@ -1960,8 +2000,8 @@ DECLARE_EVENT_CLASS(xrep_reap_find_class,
__field(bool, crosslinked)
),
TP_fast_assign(
__entry->dev = pag->pag_mount->m_super->s_dev;
__entry->agno = pag->pag_agno;
__entry->dev = pag_mount(pag)->m_super->s_dev;
__entry->agno = pag_agno(pag);
__entry->agbno = agbno;
__entry->len = len;
__entry->crosslinked = crosslinked;
@ -1975,17 +2015,15 @@ DECLARE_EVENT_CLASS(xrep_reap_find_class,
);
#define DEFINE_REPAIR_REAP_FIND_EVENT(name) \
DEFINE_EVENT(xrep_reap_find_class, name, \
TP_PROTO(struct xfs_perag *pag, xfs_agblock_t agbno, xfs_extlen_t len, \
bool crosslinked), \
TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno, \
xfs_extlen_t len, bool crosslinked), \
TP_ARGS(pag, agbno, len, crosslinked))
DEFINE_REPAIR_REAP_FIND_EVENT(xreap_agextent_select);
DEFINE_REPAIR_REAP_FIND_EVENT(xreap_bmapi_select);
DECLARE_EVENT_CLASS(xrep_rmap_class,
TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
xfs_agblock_t agbno, xfs_extlen_t len,
uint64_t owner, uint64_t offset, unsigned int flags),
TP_ARGS(mp, agno, agbno, len, owner, offset, flags),
TRACE_EVENT(xrep_ibt_walk_rmap,
TP_PROTO(const struct xfs_perag *pag, const struct xfs_rmap_irec *rec),
TP_ARGS(pag, rec),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(xfs_agnumber_t, agno)
@ -1996,13 +2034,13 @@ DECLARE_EVENT_CLASS(xrep_rmap_class,
__field(unsigned int, flags)
),
TP_fast_assign(
__entry->dev = mp->m_super->s_dev;
__entry->agno = agno;
__entry->agbno = agbno;
__entry->len = len;
__entry->owner = owner;
__entry->offset = offset;
__entry->flags = flags;
__entry->dev = pag_mount(pag)->m_super->s_dev;
__entry->agno = pag_agno(pag);
__entry->agbno = rec->rm_startblock;
__entry->len = rec->rm_blockcount;
__entry->owner = rec->rm_owner;
__entry->offset = rec->rm_offset;
__entry->flags = rec->rm_flags;
),
TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x",
MAJOR(__entry->dev), MINOR(__entry->dev),
@ -2013,19 +2051,11 @@ DECLARE_EVENT_CLASS(xrep_rmap_class,
__entry->offset,
__entry->flags)
);
#define DEFINE_REPAIR_RMAP_EVENT(name) \
DEFINE_EVENT(xrep_rmap_class, name, \
TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
xfs_agblock_t agbno, xfs_extlen_t len, \
uint64_t owner, uint64_t offset, unsigned int flags), \
TP_ARGS(mp, agno, agbno, len, owner, offset, flags))
DEFINE_REPAIR_RMAP_EVENT(xrep_ibt_walk_rmap);
DEFINE_REPAIR_RMAP_EVENT(xrep_bmap_walk_rmap);
TRACE_EVENT(xrep_abt_found,
TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
TP_PROTO(const struct xfs_perag *pag,
const struct xfs_alloc_rec_incore *rec),
TP_ARGS(mp, agno, rec),
TP_ARGS(pag, rec),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(xfs_agnumber_t, agno)
@ -2033,8 +2063,8 @@ TRACE_EVENT(xrep_abt_found,
__field(xfs_extlen_t, blockcount)
),
TP_fast_assign(
__entry->dev = mp->m_super->s_dev;
__entry->agno = agno;
__entry->dev = pag_mount(pag)->m_super->s_dev;
__entry->agno = pag_agno(pag);
__entry->startblock = rec->ar_startblock;
__entry->blockcount = rec->ar_blockcount;
),
@ -2046,9 +2076,9 @@ TRACE_EVENT(xrep_abt_found,
)
TRACE_EVENT(xrep_ibt_found,
TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
TP_PROTO(const struct xfs_perag *pag,
const struct xfs_inobt_rec_incore *rec),
TP_ARGS(mp, agno, rec),
TP_ARGS(pag, rec),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(xfs_agnumber_t, agno)
@ -2059,8 +2089,8 @@ TRACE_EVENT(xrep_ibt_found,
__field(uint64_t, freemask)
),
TP_fast_assign(
__entry->dev = mp->m_super->s_dev;
__entry->agno = agno;
__entry->dev = pag_mount(pag)->m_super->s_dev;
__entry->agno = pag_agno(pag);
__entry->startino = rec->ir_startino;
__entry->holemask = rec->ir_holemask;
__entry->count = rec->ir_count;
@ -2078,7 +2108,8 @@ TRACE_EVENT(xrep_ibt_found,
)
TRACE_EVENT(xrep_refc_found,
TP_PROTO(struct xfs_perag *pag, const struct xfs_refcount_irec *rec),
TP_PROTO(const struct xfs_perag *pag,
const struct xfs_refcount_irec *rec),
TP_ARGS(pag, rec),
TP_STRUCT__entry(
__field(dev_t, dev)
@ -2089,8 +2120,8 @@ TRACE_EVENT(xrep_refc_found,
__field(xfs_nlink_t, refcount)
),
TP_fast_assign(
__entry->dev = pag->pag_mount->m_super->s_dev;
__entry->agno = pag->pag_agno;
__entry->dev = pag_mount(pag)->m_super->s_dev;
__entry->agno = pag_agno(pag);
__entry->domain = rec->rc_domain;
__entry->startblock = rec->rc_startblock;
__entry->blockcount = rec->rc_blockcount;
@ -2138,9 +2169,8 @@ TRACE_EVENT(xrep_bmap_found,
);
TRACE_EVENT(xrep_rmap_found,
TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
const struct xfs_rmap_irec *rec),
TP_ARGS(mp, agno, rec),
TP_PROTO(const struct xfs_perag *pag, const struct xfs_rmap_irec *rec),
TP_ARGS(pag, rec),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(xfs_agnumber_t, agno)
@ -2151,8 +2181,8 @@ TRACE_EVENT(xrep_rmap_found,
__field(unsigned int, flags)
),
TP_fast_assign(
__entry->dev = mp->m_super->s_dev;
__entry->agno = agno;
__entry->dev = pag_mount(pag)->m_super->s_dev;
__entry->agno = pag_agno(pag);
__entry->agbno = rec->rm_startblock;
__entry->len = rec->rm_blockcount;
__entry->owner = rec->rm_owner;
@ -2170,9 +2200,9 @@ TRACE_EVENT(xrep_rmap_found,
);
TRACE_EVENT(xrep_findroot_block,
TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t agbno,
TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno,
uint32_t magic, uint16_t level),
TP_ARGS(mp, agno, agbno, magic, level),
TP_ARGS(pag, agbno, magic, level),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(xfs_agnumber_t, agno)
@ -2181,8 +2211,8 @@ TRACE_EVENT(xrep_findroot_block,
__field(uint16_t, level)
),
TP_fast_assign(
__entry->dev = mp->m_super->s_dev;
__entry->agno = agno;
__entry->dev = pag_mount(pag)->m_super->s_dev;
__entry->agno = pag_agno(pag);
__entry->agbno = agbno;
__entry->magic = magic;
__entry->level = level;
@ -2195,10 +2225,10 @@ TRACE_EVENT(xrep_findroot_block,
__entry->level)
)
TRACE_EVENT(xrep_calc_ag_resblks,
TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
xfs_agino_t icount, xfs_agblock_t aglen, xfs_agblock_t freelen,
TP_PROTO(const struct xfs_perag *pag, xfs_agino_t icount,
xfs_agblock_t aglen, xfs_agblock_t freelen,
xfs_agblock_t usedlen),
TP_ARGS(mp, agno, icount, aglen, freelen, usedlen),
TP_ARGS(pag, icount, aglen, freelen, usedlen),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(xfs_agnumber_t, agno)
@ -2208,8 +2238,8 @@ TRACE_EVENT(xrep_calc_ag_resblks,
__field(xfs_agblock_t, usedlen)
),
TP_fast_assign(
__entry->dev = mp->m_super->s_dev;
__entry->agno = agno;
__entry->dev = pag_mount(pag)->m_super->s_dev;
__entry->agno = pag_agno(pag);
__entry->icount = icount;
__entry->aglen = aglen;
__entry->freelen = freelen;
@ -2224,10 +2254,10 @@ TRACE_EVENT(xrep_calc_ag_resblks,
__entry->usedlen)
)
TRACE_EVENT(xrep_calc_ag_resblks_btsize,
TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
xfs_agblock_t bnobt_sz, xfs_agblock_t inobt_sz,
xfs_agblock_t rmapbt_sz, xfs_agblock_t refcbt_sz),
TP_ARGS(mp, agno, bnobt_sz, inobt_sz, rmapbt_sz, refcbt_sz),
TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t bnobt_sz,
xfs_agblock_t inobt_sz, xfs_agblock_t rmapbt_sz,
xfs_agblock_t refcbt_sz),
TP_ARGS(pag, bnobt_sz, inobt_sz, rmapbt_sz, refcbt_sz),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(xfs_agnumber_t, agno)
@ -2237,8 +2267,8 @@ TRACE_EVENT(xrep_calc_ag_resblks_btsize,
__field(xfs_agblock_t, refcbt_sz)
),
TP_fast_assign(
__entry->dev = mp->m_super->s_dev;
__entry->agno = agno;
__entry->dev = pag_mount(pag)->m_super->s_dev;
__entry->agno = pag_agno(pag);
__entry->bnobt_sz = bnobt_sz;
__entry->inobt_sz = inobt_sz;
__entry->rmapbt_sz = rmapbt_sz;
@ -2278,10 +2308,9 @@ TRACE_EVENT(xrep_reset_counters,
)
DECLARE_EVENT_CLASS(xrep_newbt_extent_class,
TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
xfs_agblock_t agbno, xfs_extlen_t len,
int64_t owner),
TP_ARGS(mp, agno, agbno, len, owner),
TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno,
xfs_extlen_t len, int64_t owner),
TP_ARGS(pag, agbno, len, owner),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(xfs_agnumber_t, agno)
@ -2290,8 +2319,8 @@ DECLARE_EVENT_CLASS(xrep_newbt_extent_class,
__field(int64_t, owner)
),
TP_fast_assign(
__entry->dev = mp->m_super->s_dev;
__entry->agno = agno;
__entry->dev = pag_mount(pag)->m_super->s_dev;
__entry->agno = pag_agno(pag);
__entry->agbno = agbno;
__entry->len = len;
__entry->owner = owner;
@ -2305,10 +2334,9 @@ DECLARE_EVENT_CLASS(xrep_newbt_extent_class,
);
#define DEFINE_NEWBT_EXTENT_EVENT(name) \
DEFINE_EVENT(xrep_newbt_extent_class, name, \
TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
xfs_agblock_t agbno, xfs_extlen_t len, \
int64_t owner), \
TP_ARGS(mp, agno, agbno, len, owner))
TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno, \
xfs_extlen_t len, int64_t owner), \
TP_ARGS(pag, agbno, len, owner))
DEFINE_NEWBT_EXTENT_EVENT(xrep_newbt_alloc_ag_blocks);
DEFINE_NEWBT_EXTENT_EVENT(xrep_newbt_alloc_file_blocks);
DEFINE_NEWBT_EXTENT_EVENT(xrep_newbt_free_blocks);
@ -2596,7 +2624,7 @@ TRACE_EVENT(xrep_cow_replace_mapping,
);
TRACE_EVENT(xrep_cow_free_staging,
TP_PROTO(struct xfs_perag *pag, xfs_agblock_t agbno,
TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno,
xfs_extlen_t blockcount),
TP_ARGS(pag, agbno, blockcount),
TP_STRUCT__entry(
@ -2606,8 +2634,8 @@ TRACE_EVENT(xrep_cow_free_staging,
__field(xfs_extlen_t, blockcount)
),
TP_fast_assign(
__entry->dev = pag->pag_mount->m_super->s_dev;
__entry->agno = pag->pag_agno;
__entry->dev = pag_mount(pag)->m_super->s_dev;
__entry->agno = pag_agno(pag);
__entry->agbno = agbno;
__entry->blockcount = blockcount;
),
@ -2652,9 +2680,9 @@ DEFINE_SCRUB_NLINKS_DIFF_EVENT(xrep_nlinks_update_inode);
DEFINE_SCRUB_NLINKS_DIFF_EVENT(xrep_nlinks_unfixable_inode);
TRACE_EVENT(xrep_rmap_live_update,
TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, unsigned int op,
TP_PROTO(const struct xfs_perag *pag, unsigned int op,
const struct xfs_rmap_update_params *p),
TP_ARGS(mp, agno, op, p),
TP_ARGS(pag, op, p),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(xfs_agnumber_t, agno)
@ -2666,8 +2694,8 @@ TRACE_EVENT(xrep_rmap_live_update,
__field(unsigned int, flags)
),
TP_fast_assign(
__entry->dev = mp->m_super->s_dev;
__entry->agno = agno;
__entry->dev = pag_mount(pag)->m_super->s_dev;
__entry->agno = pag_agno(pag);
__entry->op = op;
__entry->agbno = p->startblock;
__entry->len = p->blockcount;
@ -3313,7 +3341,7 @@ DEFINE_XREP_SYMLINK_EVENT(xrep_symlink_rebuild);
DEFINE_XREP_SYMLINK_EVENT(xrep_symlink_reset_fork);
TRACE_EVENT(xrep_iunlink_visit,
TP_PROTO(struct xfs_perag *pag, unsigned int bucket,
TP_PROTO(const struct xfs_perag *pag, unsigned int bucket,
xfs_agino_t bucket_agino, struct xfs_inode *ip),
TP_ARGS(pag, bucket, bucket_agino, ip),
TP_STRUCT__entry(
@ -3326,9 +3354,9 @@ TRACE_EVENT(xrep_iunlink_visit,
__field(xfs_agino_t, next_agino)
),
TP_fast_assign(
__entry->dev = pag->pag_mount->m_super->s_dev;
__entry->agno = pag->pag_agno;
__entry->agino = XFS_INO_TO_AGINO(pag->pag_mount, ip->i_ino);
__entry->dev = pag_mount(pag)->m_super->s_dev;
__entry->agno = pag_agno(pag);
__entry->agino = XFS_INO_TO_AGINO(pag_mount(pag), ip->i_ino);
__entry->bucket = bucket;
__entry->bucket_agino = bucket_agino;
__entry->prev_agino = ip->i_prev_unlinked;
@ -3403,7 +3431,7 @@ TRACE_EVENT(xrep_iunlink_reload_ondisk,
);
TRACE_EVENT(xrep_iunlink_walk_ondisk_bucket,
TP_PROTO(struct xfs_perag *pag, unsigned int bucket,
TP_PROTO(const struct xfs_perag *pag, unsigned int bucket,
xfs_agino_t prev_agino, xfs_agino_t next_agino),
TP_ARGS(pag, bucket, prev_agino, next_agino),
TP_STRUCT__entry(
@ -3414,8 +3442,8 @@ TRACE_EVENT(xrep_iunlink_walk_ondisk_bucket,
__field(xfs_agino_t, next_agino)
),
TP_fast_assign(
__entry->dev = pag->pag_mount->m_super->s_dev;
__entry->agno = pag->pag_agno;
__entry->dev = pag_mount(pag)->m_super->s_dev;
__entry->agno = pag_agno(pag);
__entry->bucket = bucket;
__entry->prev_agino = prev_agino;
__entry->next_agino = next_agino;
@ -3429,7 +3457,7 @@ TRACE_EVENT(xrep_iunlink_walk_ondisk_bucket,
);
DECLARE_EVENT_CLASS(xrep_iunlink_resolve_class,
TP_PROTO(struct xfs_perag *pag, unsigned int bucket,
TP_PROTO(const struct xfs_perag *pag, unsigned int bucket,
xfs_agino_t prev_agino, xfs_agino_t next_agino),
TP_ARGS(pag, bucket, prev_agino, next_agino),
TP_STRUCT__entry(
@ -3440,8 +3468,8 @@ DECLARE_EVENT_CLASS(xrep_iunlink_resolve_class,
__field(xfs_agino_t, next_agino)
),
TP_fast_assign(
__entry->dev = pag->pag_mount->m_super->s_dev;
__entry->agno = pag->pag_agno;
__entry->dev = pag_mount(pag)->m_super->s_dev;
__entry->agno = pag_agno(pag);
__entry->bucket = bucket;
__entry->prev_agino = prev_agino;
__entry->next_agino = next_agino;
@ -3455,7 +3483,7 @@ DECLARE_EVENT_CLASS(xrep_iunlink_resolve_class,
);
#define DEFINE_REPAIR_IUNLINK_RESOLVE_EVENT(name) \
DEFINE_EVENT(xrep_iunlink_resolve_class, name, \
TP_PROTO(struct xfs_perag *pag, unsigned int bucket, \
TP_PROTO(const struct xfs_perag *pag, unsigned int bucket, \
xfs_agino_t prev_agino, xfs_agino_t next_agino), \
TP_ARGS(pag, bucket, prev_agino, next_agino))
DEFINE_REPAIR_IUNLINK_RESOLVE_EVENT(xrep_iunlink_resolve_uncached);
@ -3516,7 +3544,7 @@ TRACE_EVENT(xrep_iunlink_relink_prev,
);
TRACE_EVENT(xrep_iunlink_add_to_bucket,
TP_PROTO(struct xfs_perag *pag, unsigned int bucket,
TP_PROTO(const struct xfs_perag *pag, unsigned int bucket,
xfs_agino_t agino, xfs_agino_t curr_head),
TP_ARGS(pag, bucket, agino, curr_head),
TP_STRUCT__entry(
@ -3527,8 +3555,8 @@ TRACE_EVENT(xrep_iunlink_add_to_bucket,
__field(xfs_agino_t, next_agino)
),
TP_fast_assign(
__entry->dev = pag->pag_mount->m_super->s_dev;
__entry->agno = pag->pag_agno;
__entry->dev = pag_mount(pag)->m_super->s_dev;
__entry->agno = pag_agno(pag);
__entry->bucket = bucket;
__entry->agino = agino;
__entry->next_agino = curr_head;
@ -3542,7 +3570,7 @@ TRACE_EVENT(xrep_iunlink_add_to_bucket,
);
TRACE_EVENT(xrep_iunlink_commit_bucket,
TP_PROTO(struct xfs_perag *pag, unsigned int bucket,
TP_PROTO(const struct xfs_perag *pag, unsigned int bucket,
xfs_agino_t old_agino, xfs_agino_t agino),
TP_ARGS(pag, bucket, old_agino, agino),
TP_STRUCT__entry(
@ -3553,8 +3581,8 @@ TRACE_EVENT(xrep_iunlink_commit_bucket,
__field(xfs_agino_t, agino)
),
TP_fast_assign(
__entry->dev = pag->pag_mount->m_super->s_dev;
__entry->agno = pag->pag_agno;
__entry->dev = pag_mount(pag)->m_super->s_dev;
__entry->agno = pag_agno(pag);
__entry->bucket = bucket;
__entry->old_agino = old_agino;
__entry->agino = agino;
@ -3572,6 +3600,11 @@ DEFINE_XCHK_DIRTREE_EVENT(xrep_dirtree_delete_path);
DEFINE_XCHK_DIRTREE_EVENT(xrep_dirtree_create_adoption);
DEFINE_XCHK_DIRTREE_EVALUATE_EVENT(xrep_dirtree_decided_fate);
DEFINE_XCHK_METAPATH_EVENT(xrep_metapath_lookup);
DEFINE_XCHK_METAPATH_EVENT(xrep_metapath_try_unlink);
DEFINE_XCHK_METAPATH_EVENT(xrep_metapath_unlink);
DEFINE_XCHK_METAPATH_EVENT(xrep_metapath_link);
#endif /* IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) */
#endif /* _TRACE_XFS_SCRUB_TRACE_H */

26
fs/xfs/xfs_bmap_item.c
View File

@ -318,14 +318,16 @@ xfs_bmap_update_create_done(
return &budp->bud_item;
}
/* Take a passive ref to the AG containing the space we're mapping. */
/* Take a passive ref to the group containing the space we're mapping. */
static inline void
xfs_bmap_update_get_group(
struct xfs_mount *mp,
struct xfs_bmap_intent *bi)
{
enum xfs_group_type type = XG_TYPE_AG;
if (xfs_ifork_is_realtime(bi->bi_owner, bi->bi_whichfork))
return;
type = XG_TYPE_RTG;
/*
* Bump the intent count on behalf of the deferred rmap and refcount
@ -334,7 +336,8 @@ xfs_bmap_update_get_group(
* intent drops the intent count, ensuring that the intent count
* remains nonzero across the transaction roll.
*/
bi->bi_pag = xfs_perag_intent_get(mp, bi->bi_bmap.br_startblock);
bi->bi_group = xfs_group_intent_get(mp, bi->bi_bmap.br_startblock,
type);
}
/* Add this deferred BUI to the transaction. */
@ -343,8 +346,6 @@ xfs_bmap_defer_add(
struct xfs_trans *tp,
struct xfs_bmap_intent *bi)
{
trace_xfs_bmap_defer(bi);
xfs_bmap_update_get_group(tp->t_mountp, bi);
/*
@ -357,20 +358,11 @@ xfs_bmap_defer_add(
*/
if (bi->bi_type == XFS_BMAP_MAP)
bi->bi_owner->i_delayed_blks += bi->bi_bmap.br_blockcount;
trace_xfs_bmap_defer(bi);
xfs_defer_add(tp, &bi->bi_list, &xfs_bmap_update_defer_type);
}
/* Release a passive AG ref after finishing mapping work. */
static inline void
xfs_bmap_update_put_group(
struct xfs_bmap_intent *bi)
{
if (xfs_ifork_is_realtime(bi->bi_owner, bi->bi_whichfork))
return;
xfs_perag_intent_put(bi->bi_pag);
}
/* Cancel a deferred bmap update. */
STATIC void
xfs_bmap_update_cancel_item(
@ -381,7 +373,7 @@ xfs_bmap_update_cancel_item(
if (bi->bi_type == XFS_BMAP_MAP)
bi->bi_owner->i_delayed_blks -= bi->bi_bmap.br_blockcount;
xfs_bmap_update_put_group(bi);
xfs_group_intent_put(bi->bi_group);
kmem_cache_free(xfs_bmap_intent_cache, bi);
}

Some files were not shown because too many files have changed in this diff Show More