summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-05-12 00:51:11 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2023-05-12 00:51:11 +0300
commit849a4f09730ba3c02da01924c7a6e7a000a4d27c (patch)
treed3b804abf05003e1a4b0f56765f7132d653020fb /fs
parent105131df9c3b27673392a6b7ff356360188dc869 (diff)
parent2254a7396a0ca6309854948ee1c0a33fa4268cec (diff)
downloadlinux-849a4f09730ba3c02da01924c7a6e7a000a4d27c.tar.xz
Merge tag 'xfs-6.4-rc1-fixes' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux
Pull xfs bug fixes from Dave Chinner: "Largely minor bug fixes and cleanups, th emost important of which are probably the fixes for regressions in the extent allocation code: - fixes for inode garbage collection shutdown racing with work queue updates - ensure inodegc workers run on the CPU they are supposed to - disable counter scrubbing until we can exclusively freeze the filesystem from the kernel - regression fixes for new allocation related bugs - a couple of minor cleanups" * tag 'xfs-6.4-rc1-fixes' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: xfs: fix xfs_inodegc_stop racing with mod_delayed_work xfs: disable reaping in fscounters scrub xfs: check that per-cpu inodegc workers actually run on that cpu xfs: explicitly specify cpu when forcing inodegc delayed work to run immediately xfs: fix negative array access in xfs_getbmap xfs: don't allocate into the data fork for an unshare request xfs: flush dirty data and drain directios before scrubbing cow fork xfs: set bnobt/cntbt numrecs correctly when formatting new AGs xfs: don't unconditionally null args->pag in xfs_bmap_btalloc_at_eof
Diffstat (limited to 'fs')
-rw-r--r--fs/xfs/libxfs/xfs_ag.c19
-rw-r--r--fs/xfs/libxfs/xfs_bmap.c5
-rw-r--r--fs/xfs/scrub/bmap.c4
-rw-r--r--fs/xfs/scrub/common.c26
-rw-r--r--fs/xfs/scrub/common.h2
-rw-r--r--fs/xfs/scrub/fscounters.c13
-rw-r--r--fs/xfs/scrub/scrub.c2
-rw-r--r--fs/xfs/scrub/scrub.h1
-rw-r--r--fs/xfs/scrub/trace.h1
-rw-r--r--fs/xfs/xfs_bmap_util.c4
-rw-r--r--fs/xfs/xfs_icache.c40
-rw-r--r--fs/xfs/xfs_iomap.c5
-rw-r--r--fs/xfs/xfs_mount.h3
-rw-r--r--fs/xfs/xfs_super.c3
14 files changed, 65 insertions, 63 deletions
diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 1b078bbbf225..9b373a0c7aaf 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -495,10 +495,12 @@ xfs_freesp_init_recs(
ASSERT(start >= mp->m_ag_prealloc_blocks);
if (start != mp->m_ag_prealloc_blocks) {
/*
- * Modify first record to pad stripe align of log
+ * Modify first record to pad stripe align of log and
+ * bump the record count.
*/
arec->ar_blockcount = cpu_to_be32(start -
mp->m_ag_prealloc_blocks);
+ be16_add_cpu(&block->bb_numrecs, 1);
nrec = arec + 1;
/*
@@ -509,7 +511,6 @@ xfs_freesp_init_recs(
be32_to_cpu(arec->ar_startblock) +
be32_to_cpu(arec->ar_blockcount));
arec = nrec;
- be16_add_cpu(&block->bb_numrecs, 1);
}
/*
* Change record start to after the internal log
@@ -518,15 +519,13 @@ xfs_freesp_init_recs(
}
/*
- * Calculate the record block count and check for the case where
- * the log might have consumed all available space in the AG. If
- * so, reset the record count to 0 to avoid exposure of an invalid
- * record start block.
+ * Calculate the block count of this record; if it is nonzero,
+ * increment the record count.
*/
arec->ar_blockcount = cpu_to_be32(id->agsize -
be32_to_cpu(arec->ar_startblock));
- if (!arec->ar_blockcount)
- block->bb_numrecs = 0;
+ if (arec->ar_blockcount)
+ be16_add_cpu(&block->bb_numrecs, 1);
}
/*
@@ -538,7 +537,7 @@ xfs_bnoroot_init(
struct xfs_buf *bp,
struct aghdr_init_data *id)
{
- xfs_btree_init_block(mp, bp, XFS_BTNUM_BNO, 0, 1, id->agno);
+ xfs_btree_init_block(mp, bp, XFS_BTNUM_BNO, 0, 0, id->agno);
xfs_freesp_init_recs(mp, bp, id);
}
@@ -548,7 +547,7 @@ xfs_cntroot_init(
struct xfs_buf *bp,
struct aghdr_init_data *id)
{
- xfs_btree_init_block(mp, bp, XFS_BTNUM_CNT, 0, 1, id->agno);
+ xfs_btree_init_block(mp, bp, XFS_BTNUM_CNT, 0, 0, id->agno);
xfs_freesp_init_recs(mp, bp, id);
}
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index b512de0540d5..cd8870a16fd1 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -3494,8 +3494,10 @@ xfs_bmap_btalloc_at_eof(
if (!caller_pag)
args->pag = xfs_perag_get(mp, XFS_FSB_TO_AGNO(mp, ap->blkno));
error = xfs_alloc_vextent_exact_bno(args, ap->blkno);
- if (!caller_pag)
+ if (!caller_pag) {
xfs_perag_put(args->pag);
+ args->pag = NULL;
+ }
if (error)
return error;
@@ -3505,7 +3507,6 @@ xfs_bmap_btalloc_at_eof(
* Exact allocation failed. Reset to try an aligned allocation
* according to the original allocation specification.
*/
- args->pag = NULL;
args->alignment = stripe_align;
args->minlen = nextminlen;
args->minalignslop = 0;
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index 87ab9f95a487..69bc89d0fc68 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -42,12 +42,12 @@ xchk_setup_inode_bmap(
xfs_ilock(sc->ip, XFS_IOLOCK_EXCL);
/*
- * We don't want any ephemeral data fork updates sitting around
+ * We don't want any ephemeral data/cow fork updates sitting around
* while we inspect block mappings, so wait for directio to finish
* and flush dirty data if we have delalloc reservations.
*/
if (S_ISREG(VFS_I(sc->ip)->i_mode) &&
- sc->sm->sm_type == XFS_SCRUB_TYPE_BMBTD) {
+ sc->sm->sm_type != XFS_SCRUB_TYPE_BMBTA) {
struct address_space *mapping = VFS_I(sc->ip)->i_mapping;
sc->ilock_flags |= XFS_MMAPLOCK_EXCL;
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index 9aa79665c608..7a20256be969 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -1164,32 +1164,6 @@ xchk_metadata_inode_forks(
return 0;
}
-/* Pause background reaping of resources. */
-void
-xchk_stop_reaping(
- struct xfs_scrub *sc)
-{
- sc->flags |= XCHK_REAPING_DISABLED;
- xfs_blockgc_stop(sc->mp);
- xfs_inodegc_stop(sc->mp);
-}
-
-/* Restart background reaping of resources. */
-void
-xchk_start_reaping(
- struct xfs_scrub *sc)
-{
- /*
- * Readonly filesystems do not perform inactivation or speculative
- * preallocation, so there's no need to restart the workers.
- */
- if (!xfs_is_readonly(sc->mp)) {
- xfs_inodegc_start(sc->mp);
- xfs_blockgc_start(sc->mp);
- }
- sc->flags &= ~XCHK_REAPING_DISABLED;
-}
-
/*
* Enable filesystem hooks (i.e. runtime code patching) before starting a scrub
* operation. Callers must not hold any locks that intersect with the CPU
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index 18b5f2b62f13..791235cd9b00 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -156,8 +156,6 @@ static inline bool xchk_skip_xref(struct xfs_scrub_metadata *sm)
}
int xchk_metadata_inode_forks(struct xfs_scrub *sc);
-void xchk_stop_reaping(struct xfs_scrub *sc);
-void xchk_start_reaping(struct xfs_scrub *sc);
/*
* Setting up a hook to wait for intents to drain is costly -- we have to take
diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c
index faa315be7978..e382a35e98d8 100644
--- a/fs/xfs/scrub/fscounters.c
+++ b/fs/xfs/scrub/fscounters.c
@@ -150,13 +150,6 @@ xchk_setup_fscounters(
if (error)
return error;
- /*
- * Pause background reclaim while we're scrubbing to reduce the
- * likelihood of background perturbations to the counters throwing off
- * our calculations.
- */
- xchk_stop_reaping(sc);
-
return xchk_trans_alloc(sc, 0);
}
@@ -454,6 +447,12 @@ xchk_fscounters(
xchk_set_corrupt(sc);
/*
+ * XXX: We can't quiesce percpu counter updates, so exit early.
+ * This can be re-enabled when we gain exclusive freeze functionality.
+ */
+ return 0;
+
+ /*
* If ifree exceeds icount by more than the minimum variance then
* something's probably wrong with the counters.
*/
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 02819bedc5b1..3d98f604765e 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -186,8 +186,6 @@ xchk_teardown(
}
if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR)
mnt_drop_write_file(sc->file);
- if (sc->flags & XCHK_REAPING_DISABLED)
- xchk_start_reaping(sc);
if (sc->buf) {
if (sc->buf_cleanup)
sc->buf_cleanup(sc->buf);
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index e71903474cd7..b38e93830dde 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -106,7 +106,6 @@ struct xfs_scrub {
/* XCHK state flags grow up from zero, XREP state flags grown down from 2^31 */
#define XCHK_TRY_HARDER (1 << 0) /* can't get resources, try again */
-#define XCHK_REAPING_DISABLED (1 << 1) /* background block reaping paused */
#define XCHK_FSGATES_DRAIN (1 << 2) /* defer ops draining enabled */
#define XCHK_NEED_DRAIN (1 << 3) /* scrub needs to drain defer ops */
#define XREP_ALREADY_FIXED (1 << 31) /* checking our repair work */
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 68efd6fda61c..b3894daeb86a 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -98,7 +98,6 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_FSCOUNTERS);
#define XFS_SCRUB_STATE_STRINGS \
{ XCHK_TRY_HARDER, "try_harder" }, \
- { XCHK_REAPING_DISABLED, "reaping_disabled" }, \
{ XCHK_FSGATES_DRAIN, "fsgates_drain" }, \
{ XCHK_NEED_DRAIN, "need_drain" }, \
{ XREP_ALREADY_FIXED, "already_fixed" }
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index f032d3a4b727..fbb675563208 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -558,7 +558,9 @@ xfs_getbmap(
if (!xfs_iext_next_extent(ifp, &icur, &got)) {
xfs_fileoff_t end = XFS_B_TO_FSB(mp, XFS_ISIZE(ip));
- out[bmv->bmv_entries - 1].bmv_oflags |= BMV_OF_LAST;
+ if (bmv->bmv_entries > 0)
+ out[bmv->bmv_entries - 1].bmv_oflags |=
+ BMV_OF_LAST;
if (whichfork != XFS_ATTR_FORK && bno < end &&
!xfs_getbmap_full(bmv)) {
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 351849fc18ff..0f60e301eb1f 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -435,18 +435,23 @@ xfs_iget_check_free_state(
}
/* Make all pending inactivation work start immediately. */
-static void
+static bool
xfs_inodegc_queue_all(
struct xfs_mount *mp)
{
struct xfs_inodegc *gc;
int cpu;
+ bool ret = false;
for_each_online_cpu(cpu) {
gc = per_cpu_ptr(mp->m_inodegc, cpu);
- if (!llist_empty(&gc->list))
+ if (!llist_empty(&gc->list)) {
mod_delayed_work_on(cpu, mp->m_inodegc_wq, &gc->work, 0);
+ ret = true;
+ }
}
+
+ return ret;
}
/*
@@ -1856,6 +1861,8 @@ xfs_inodegc_worker(
struct xfs_inode *ip, *n;
unsigned int nofs_flag;
+ ASSERT(gc->cpu == smp_processor_id());
+
WRITE_ONCE(gc->items, 0);
if (!node)
@@ -1909,24 +1916,41 @@ xfs_inodegc_flush(
/*
* Flush all the pending work and then disable the inode inactivation background
- * workers and wait for them to stop.
+ * workers and wait for them to stop. Caller must hold sb->s_umount to
+ * coordinate changes in the inodegc_enabled state.
*/
void
xfs_inodegc_stop(
struct xfs_mount *mp)
{
+ bool rerun;
+
if (!xfs_clear_inodegc_enabled(mp))
return;
+ /*
+ * Drain all pending inodegc work, including inodes that could be
+ * queued by racing xfs_inodegc_queue or xfs_inodegc_shrinker_scan
+ * threads that sample the inodegc state just prior to us clearing it.
+ * The inodegc flag state prevents new threads from queuing more
+ * inodes, so we queue pending work items and flush the workqueue until
+ * all inodegc lists are empty. IOWs, we cannot use drain_workqueue
+ * here because it does not allow other unserialized mechanisms to
+ * reschedule inodegc work while this draining is in progress.
+ */
xfs_inodegc_queue_all(mp);
- drain_workqueue(mp->m_inodegc_wq);
+ do {
+ flush_workqueue(mp->m_inodegc_wq);
+ rerun = xfs_inodegc_queue_all(mp);
+ } while (rerun);
trace_xfs_inodegc_stop(mp, __return_address);
}
/*
* Enable the inode inactivation background workers and schedule deferred inode
- * inactivation work if there is any.
+ * inactivation work if there is any. Caller must hold sb->s_umount to
+ * coordinate changes in the inodegc_enabled state.
*/
void
xfs_inodegc_start(
@@ -2069,7 +2093,8 @@ xfs_inodegc_queue(
queue_delay = 0;
trace_xfs_inodegc_queue(mp, __return_address);
- mod_delayed_work(mp->m_inodegc_wq, &gc->work, queue_delay);
+ mod_delayed_work_on(current_cpu(), mp->m_inodegc_wq, &gc->work,
+ queue_delay);
put_cpu_ptr(gc);
if (xfs_inodegc_want_flush_work(ip, items, shrinker_hits)) {
@@ -2113,7 +2138,8 @@ xfs_inodegc_cpu_dead(
if (xfs_is_inodegc_enabled(mp)) {
trace_xfs_inodegc_queue(mp, __return_address);
- mod_delayed_work(mp->m_inodegc_wq, &gc->work, 0);
+ mod_delayed_work_on(current_cpu(), mp->m_inodegc_wq, &gc->work,
+ 0);
}
put_cpu_ptr(gc);
}
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 285885c308bd..18c8f168b153 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -1006,8 +1006,9 @@ xfs_buffered_write_iomap_begin(
if (eof)
imap.br_startoff = end_fsb; /* fake hole until the end */
- /* We never need to allocate blocks for zeroing a hole. */
- if ((flags & IOMAP_ZERO) && imap.br_startoff > offset_fsb) {
+ /* We never need to allocate blocks for zeroing or unsharing a hole. */
+ if ((flags & (IOMAP_UNSHARE | IOMAP_ZERO)) &&
+ imap.br_startoff > offset_fsb) {
xfs_hole_to_iomap(ip, iomap, offset_fsb, imap.br_startoff);
goto out_unlock;
}
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index f3269c0626f0..aaaf5ec13492 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -66,6 +66,9 @@ struct xfs_inodegc {
/* approximate count of inodes in the list */
unsigned int items;
unsigned int shrinker_hits;
+#if defined(DEBUG) || defined(XFS_WARN)
+ unsigned int cpu;
+#endif
};
/*
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 4d2e87462ac4..7e706255f165 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1095,6 +1095,9 @@ xfs_inodegc_init_percpu(
for_each_possible_cpu(cpu) {
gc = per_cpu_ptr(mp->m_inodegc, cpu);
+#if defined(DEBUG) || defined(XFS_WARN)
+ gc->cpu = cpu;
+#endif
init_llist_head(&gc->list);
gc->items = 0;
INIT_DELAYED_WORK(&gc->work, xfs_inodegc_worker);