summaryrefslogtreecommitdiffstats
path: root/fs/xfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/xfs')
-rw-r--r--fs/xfs/Kconfig2
-rw-r--r--fs/xfs/libxfs/xfs_ag.c6
-rw-r--r--fs/xfs/libxfs/xfs_log_recover.h22
-rw-r--r--fs/xfs/libxfs/xfs_sb.c3
-rw-r--r--fs/xfs/libxfs/xfs_trans_inode.c6
-rw-r--r--fs/xfs/scrub/scrub.c4
-rw-r--r--fs/xfs/scrub/stats.c5
-rw-r--r--fs/xfs/scrub/xfile.c1
-rw-r--r--fs/xfs/xfs_attr_inactive.c1
-rw-r--r--fs/xfs/xfs_attr_item.c7
-rw-r--r--fs/xfs/xfs_bmap_item.c4
-rw-r--r--fs/xfs/xfs_discard.c266
-rw-r--r--fs/xfs/xfs_discard.h6
-rw-r--r--fs/xfs/xfs_export.c14
-rw-r--r--fs/xfs/xfs_extent_busy.c35
-rw-r--r--fs/xfs/xfs_extent_busy.h24
-rw-r--r--fs/xfs/xfs_extfree_item.c4
-rw-r--r--fs/xfs/xfs_fsmap.c25
-rw-r--r--fs/xfs/xfs_icache.c80
-rw-r--r--fs/xfs/xfs_icache.h1
-rw-r--r--fs/xfs/xfs_inode.c231
-rw-r--r--fs/xfs/xfs_inode.h34
-rw-r--r--fs/xfs/xfs_iops.c11
-rw-r--r--fs/xfs/xfs_itable.c11
-rw-r--r--fs/xfs/xfs_log.c17
-rw-r--r--fs/xfs/xfs_log_cil.c145
-rw-r--r--fs/xfs/xfs_log_priv.h19
-rw-r--r--fs/xfs/xfs_log_recover.c4
-rw-r--r--fs/xfs/xfs_mount.h17
-rw-r--r--fs/xfs/xfs_notify_failure.c6
-rw-r--r--fs/xfs/xfs_qm.c16
-rw-r--r--fs/xfs/xfs_refcount_item.c6
-rw-r--r--fs/xfs/xfs_rmap_item.c6
-rw-r--r--fs/xfs/xfs_super.c88
-rw-r--r--fs/xfs/xfs_trace.h45
-rw-r--r--fs/xfs/xfs_xattr.c11
36 files changed, 815 insertions, 368 deletions
diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig
index c9d653168ad0..ed0bc8cbc703 100644
--- a/fs/xfs/Kconfig
+++ b/fs/xfs/Kconfig
@@ -147,7 +147,7 @@ config XFS_ONLINE_SCRUB_STATS
bool "XFS online metadata check usage data collection"
default y
depends on XFS_ONLINE_SCRUB
- select FS_DEBUG
+ select XFS_DEBUG
help
If you say Y here, the kernel will gather usage data about
the online metadata check subsystem. This includes the number
diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index e9cc481b4ddf..f9f4d694640d 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -1001,6 +1001,12 @@ xfs_ag_shrink_space(
error = -ENOSPC;
goto resv_init_out;
}
+
+ /* Update perag geometry */
+ pag->block_count -= delta;
+ __xfs_agino_range(pag->pag_mount, pag->block_count, &pag->agino_min,
+ &pag->agino_max);
+
xfs_ialloc_log_agi(*tpp, agibp, XFS_AGI_LENGTH);
xfs_alloc_log_agf(*tpp, agfbp, XFS_AGF_LENGTH);
return 0;
diff --git a/fs/xfs/libxfs/xfs_log_recover.h b/fs/xfs/libxfs/xfs_log_recover.h
index 2420865f3007..a5100a11faf9 100644
--- a/fs/xfs/libxfs/xfs_log_recover.h
+++ b/fs/xfs/libxfs/xfs_log_recover.h
@@ -131,4 +131,26 @@ void xlog_check_buf_cancel_table(struct xlog *log);
#define xlog_check_buf_cancel_table(log) do { } while (0)
#endif
+/*
+ * Transform a regular reservation into one suitable for recovery of a log
+ * intent item.
+ *
+ * Intent recovery only runs a single step of the transaction chain and defers
+ * the rest to a separate transaction. Therefore, we reduce logcount to 1 here
+ * to avoid livelocks if the log grant space is nearly exhausted due to the
+ * recovered intent pinning the tail. Keep the same logflags to avoid tripping
+ * asserts elsewhere. Struct copies abound below.
+ */
+static inline struct xfs_trans_res
+xlog_recover_resv(const struct xfs_trans_res *r)
+{
+ struct xfs_trans_res ret = {
+ .tr_logres = r->tr_logres,
+ .tr_logcount = 1,
+ .tr_logflags = r->tr_logflags,
+ };
+
+ return ret;
+}
+
#endif /* __XFS_LOG_RECOVER_H__ */
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 5e174685a77c..6264daaab37b 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -266,7 +266,8 @@ xfs_validate_sb_write(
return -EFSCORRUPTED;
}
- if (xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) {
+ if (!xfs_is_readonly(mp) &&
+ xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) {
xfs_alert(mp,
"Corruption detected in superblock read-only compatible features (0x%x)!",
(sbp->sb_features_ro_compat &
diff --git a/fs/xfs/libxfs/xfs_trans_inode.c b/fs/xfs/libxfs/xfs_trans_inode.c
index ad22656376d3..6b2296ff248a 100644
--- a/fs/xfs/libxfs/xfs_trans_inode.c
+++ b/fs/xfs/libxfs/xfs_trans_inode.c
@@ -62,12 +62,12 @@ xfs_trans_ichgtime(
ASSERT(tp);
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
- /* If the mtime changes, then ctime must also change */
- ASSERT(flags & XFS_ICHGTIME_CHG);
+ tv = current_time(inode);
- tv = inode_set_ctime_current(inode);
if (flags & XFS_ICHGTIME_MOD)
inode->i_mtime = tv;
+ if (flags & XFS_ICHGTIME_CHG)
+ inode_set_ctime_to_ts(inode, tv);
if (flags & XFS_ICHGTIME_CREATE)
ip->i_crtime = tv;
}
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 7d3aa14d81b5..4849efcaa33a 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -588,6 +588,8 @@ out_nofix:
out_teardown:
error = xchk_teardown(sc, error);
out_sc:
+ if (error != -ENOENT)
+ xchk_stats_merge(mp, sm, &run);
kfree(sc);
out:
trace_xchk_done(XFS_I(file_inode(file)), sm, error);
@@ -595,8 +597,6 @@ out:
sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
error = 0;
}
- if (error != -ENOENT)
- xchk_stats_merge(mp, sm, &run);
return error;
need_drain:
error = xchk_teardown(sc, 0);
diff --git a/fs/xfs/scrub/stats.c b/fs/xfs/scrub/stats.c
index aeb92624176b..cd91db4a5548 100644
--- a/fs/xfs/scrub/stats.c
+++ b/fs/xfs/scrub/stats.c
@@ -185,7 +185,10 @@ xchk_stats_merge_one(
{
struct xchk_scrub_stats *css;
- ASSERT(sm->sm_type < XFS_SCRUB_TYPE_NR);
+ if (sm->sm_type >= XFS_SCRUB_TYPE_NR) {
+ ASSERT(sm->sm_type < XFS_SCRUB_TYPE_NR);
+ return;
+ }
css = &cs->cs_stats[sm->sm_type];
spin_lock(&css->css_lock);
diff --git a/fs/xfs/scrub/xfile.c b/fs/xfs/scrub/xfile.c
index d98e8e77c684..090c3ead43fd 100644
--- a/fs/xfs/scrub/xfile.c
+++ b/fs/xfs/scrub/xfile.c
@@ -10,7 +10,6 @@
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
-#include "xfs_format.h"
#include "scrub/xfile.h"
#include "scrub/xfarray.h"
#include "scrub/scrub.h"
diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c
index 5db87b34fb6e..89c7a9f4f930 100644
--- a/fs/xfs/xfs_attr_inactive.c
+++ b/fs/xfs/xfs_attr_inactive.c
@@ -333,7 +333,6 @@ xfs_attr_inactive(
int error = 0;
mp = dp->i_mount;
- ASSERT(! XFS_NOT_DQATTACHED(mp, dp));
xfs_ilock(dp, lock_mode);
if (!xfs_inode_has_attr_fork(dp))
diff --git a/fs/xfs/xfs_attr_item.c b/fs/xfs/xfs_attr_item.c
index 2788a6f2edcd..36fe2abb16e6 100644
--- a/fs/xfs/xfs_attr_item.c
+++ b/fs/xfs/xfs_attr_item.c
@@ -547,7 +547,7 @@ xfs_attri_item_recover(
struct xfs_inode *ip;
struct xfs_da_args *args;
struct xfs_trans *tp;
- struct xfs_trans_res tres;
+ struct xfs_trans_res resv;
struct xfs_attri_log_format *attrp;
struct xfs_attri_log_nameval *nv = attrip->attri_nameval;
int error;
@@ -618,8 +618,9 @@ xfs_attri_item_recover(
goto out;
}
- xfs_init_attr_trans(args, &tres, &total);
- error = xfs_trans_alloc(mp, &tres, total, 0, XFS_TRANS_RESERVE, &tp);
+ xfs_init_attr_trans(args, &resv, &total);
+ resv = xlog_recover_resv(&resv);
+ error = xfs_trans_alloc(mp, &resv, total, 0, XFS_TRANS_RESERVE, &tp);
if (error)
goto out;
diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index 7551c3ec4ea5..e736a0844c89 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -490,6 +490,7 @@ xfs_bui_item_recover(
struct list_head *capture_list)
{
struct xfs_bmap_intent fake = { };
+ struct xfs_trans_res resv;
struct xfs_bui_log_item *buip = BUI_ITEM(lip);
struct xfs_trans *tp;
struct xfs_inode *ip = NULL;
@@ -515,7 +516,8 @@ xfs_bui_item_recover(
return error;
/* Allocate transaction and do the work. */
- error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate,
+ resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate);
+ error = xfs_trans_alloc(mp, &resv,
XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK), 0, 0, &tp);
if (error)
goto err_rele;
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index afc4c78b9eed..d5787991bb5b 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
/*
- * Copyright (C) 2010 Red Hat, Inc.
+ * Copyright (C) 2010, 2023 Red Hat, Inc.
* All Rights Reserved.
*/
#include "xfs.h"
@@ -19,21 +19,147 @@
#include "xfs_log.h"
#include "xfs_ag.h"
-STATIC int
-xfs_trim_extents(
+/*
+ * Notes on an efficient, low latency fstrim algorithm
+ *
+ * We need to walk the filesystem free space and issue discards on the free
+ * space that meet the search criteria (size and location). We cannot issue
+ * discards on extents that might be in use, or are so recently in use they are
+ * still marked as busy. To serialise against extent state changes whilst we are
+ * gathering extents to trim, we must hold the AGF lock to lock out other
+ * allocations and extent free operations that might change extent state.
+ *
+ * However, we cannot just hold the AGF for the entire AG free space walk whilst
+ * we issue discards on each free space that is found. Storage devices can have
+ * extremely slow discard implementations (e.g. ceph RBD) and so walking a
+ * couple of million free extents and issuing synchronous discards on each
+ * extent can take a *long* time. Whilst we are doing this walk, nothing else
+ * can access the AGF, and we can stall transactions and hence the log whilst
+ * modifications wait for the AGF lock to be released. This can lead hung tasks
+ * kicking the hung task timer and rebooting the system. This is bad.
+ *
+ * Hence we need to take a leaf from the bulkstat playbook. It takes the AGI
+ * lock, gathers a range of inode cluster buffers that are allocated, drops the
+ * AGI lock and then reads all the inode cluster buffers and processes them. It
+ * loops doing this, using a cursor to keep track of where it is up to in the AG
+ * for each iteration to restart the INOBT lookup from.
+ *
+ * We can't do this exactly with free space - once we drop the AGF lock, the
+ * state of the free extent is out of our control and we cannot run a discard
+ * safely on it in this situation. Unless, of course, we've marked the free
+ * extent as busy and undergoing a discard operation whilst we held the AGF
+ * locked.
+ *
+ * This is exactly how online discard works - free extents are marked busy when
+ * they are freed, and once the extent free has been committed to the journal,
+ * the busy extent record is marked as "undergoing discard" and the discard is
+ * then issued on the free extent. Once the discard completes, the busy extent
+ * record is removed and the extent is able to be allocated again.
+ *
+ * In the context of fstrim, if we find a free extent we need to discard, we
+ * don't have to discard it immediately. All we need to do it record that free
+ * extent as being busy and under discard, and all the allocation routines will
+ * now avoid trying to allocate it. Hence if we mark the extent as busy under
+ * the AGF lock, we can safely discard it without holding the AGF lock because
+ * nothing will attempt to allocate that free space until the discard completes.
+ *
+ * This also allows us to issue discards asynchronously like we do with online
+ * discard, and so for fast devices fstrim will run much faster as we can have
+ * multiple discard operations in flight at once, as well as pipeline the free
+ * extent search so that it overlaps in flight discard IO.
+ */
+
+struct workqueue_struct *xfs_discard_wq;
+
+static void
+xfs_discard_endio_work(
+ struct work_struct *work)
+{
+ struct xfs_busy_extents *extents =
+ container_of(work, struct xfs_busy_extents, endio_work);
+
+ xfs_extent_busy_clear(extents->mount, &extents->extent_list, false);
+ kmem_free(extents->owner);
+}
+
+/*
+ * Queue up the actual completion to a thread to avoid IRQ-safe locking for
+ * pagb_lock.
+ */
+static void
+xfs_discard_endio(
+ struct bio *bio)
+{
+ struct xfs_busy_extents *extents = bio->bi_private;
+
+ INIT_WORK(&extents->endio_work, xfs_discard_endio_work);
+ queue_work(xfs_discard_wq, &extents->endio_work);
+ bio_put(bio);
+}
+
+/*
+ * Walk the discard list and issue discards on all the busy extents in the
+ * list. We plug and chain the bios so that we only need a single completion
+ * call to clear all the busy extents once the discards are complete.
+ */
+int
+xfs_discard_extents(
+ struct xfs_mount *mp,
+ struct xfs_busy_extents *extents)
+{
+ struct xfs_extent_busy *busyp;
+ struct bio *bio = NULL;
+ struct blk_plug plug;
+ int error = 0;
+
+ blk_start_plug(&plug);
+ list_for_each_entry(busyp, &extents->extent_list, list) {
+ trace_xfs_discard_extent(mp, busyp->agno, busyp->bno,
+ busyp->length);
+
+ error = __blkdev_issue_discard(mp->m_ddev_targp->bt_bdev,
+ XFS_AGB_TO_DADDR(mp, busyp->agno, busyp->bno),
+ XFS_FSB_TO_BB(mp, busyp->length),
+ GFP_NOFS, &bio);
+ if (error && error != -EOPNOTSUPP) {
+ xfs_info(mp,
+ "discard failed for extent [0x%llx,%u], error %d",
+ (unsigned long long)busyp->bno,
+ busyp->length,
+ error);
+ break;
+ }
+ }
+
+ if (bio) {
+ bio->bi_private = extents;
+ bio->bi_end_io = xfs_discard_endio;
+ submit_bio(bio);
+ } else {
+ xfs_discard_endio_work(&extents->endio_work);
+ }
+ blk_finish_plug(&plug);
+
+ return error;
+}
+
+
+static int
+xfs_trim_gather_extents(
struct xfs_perag *pag,
xfs_daddr_t start,
xfs_daddr_t end,
xfs_daddr_t minlen,
+ struct xfs_alloc_rec_incore *tcur,
+ struct xfs_busy_extents *extents,
uint64_t *blocks_trimmed)
{
struct xfs_mount *mp = pag->pag_mount;
- struct block_device *bdev = mp->m_ddev_targp->bt_bdev;
struct xfs_btree_cur *cur;
struct xfs_buf *agbp;
- struct xfs_agf *agf;
int error;
int i;
+ int batch = 100;
/*
* Force out the log. This means any transactions that might have freed
@@ -45,20 +171,28 @@ xfs_trim_extents(
error = xfs_alloc_read_agf(pag, NULL, 0, &agbp);
if (error)
return error;
- agf = agbp->b_addr;
cur = xfs_allocbt_init_cursor(mp, NULL, agbp, pag, XFS_BTNUM_CNT);
/*
- * Look up the longest btree in the AGF and start with it.
+ * Look up the extent length requested in the AGF and start with it.
*/
- error = xfs_alloc_lookup_ge(cur, 0, be32_to_cpu(agf->agf_longest), &i);
+ if (tcur->ar_startblock == NULLAGBLOCK)
+ error = xfs_alloc_lookup_ge(cur, 0, tcur->ar_blockcount, &i);
+ else
+ error = xfs_alloc_lookup_le(cur, tcur->ar_startblock,
+ tcur->ar_blockcount, &i);
if (error)
goto out_del_cursor;
+ if (i == 0) {
+ /* nothing of that length left in the AG, we are done */
+ tcur->ar_blockcount = 0;
+ goto out_del_cursor;
+ }
/*
* Loop until we are done with all extents that are large
- * enough to be worth discarding.
+ * enough to be worth discarding or we hit batch limits.
*/
while (i) {
xfs_agblock_t fbno;
@@ -73,7 +207,16 @@ xfs_trim_extents(
error = -EFSCORRUPTED;
break;
}
- ASSERT(flen <= be32_to_cpu(agf->agf_longest));
+
+ if (--batch <= 0) {
+ /*
+ * Update the cursor to point at this extent so we
+ * restart the next batch from this extent.
+ */
+ tcur->ar_startblock = fbno;
+ tcur->ar_blockcount = flen;
+ break;
+ }
/*
* use daddr format for all range/len calculations as that is
@@ -88,6 +231,7 @@ xfs_trim_extents(
*/
if (dlen < minlen) {
trace_xfs_discard_toosmall(mp, pag->pag_agno, fbno, flen);
+ tcur->ar_blockcount = 0;
break;
}
@@ -110,29 +254,103 @@ xfs_trim_extents(
goto next_extent;
}
- trace_xfs_discard_extent(mp, pag->pag_agno, fbno, flen);
- error = blkdev_issue_discard(bdev, dbno, dlen, GFP_NOFS);
- if (error)
- break;
+ xfs_extent_busy_insert_discard(pag, fbno, flen,
+ &extents->extent_list);
*blocks_trimmed += flen;
-
next_extent:
error = xfs_btree_decrement(cur, 0, &i);
if (error)
break;
- if (fatal_signal_pending(current)) {
- error = -ERESTARTSYS;
- break;
- }
+ /*
+ * If there's no more records in the tree, we are done. Set the
+ * cursor block count to 0 to indicate to the caller that there
+ * is no more extents to search.
+ */
+ if (i == 0)
+ tcur->ar_blockcount = 0;
}
+ /*
+ * If there was an error, release all the gathered busy extents because
+ * we aren't going to issue a discard on them any more.
+ */
+ if (error)
+ xfs_extent_busy_clear(mp, &extents->extent_list, false);
out_del_cursor:
xfs_btree_del_cursor(cur, error);
xfs_buf_relse(agbp);
return error;
}
+static bool
+xfs_trim_should_stop(void)
+{
+ return fatal_signal_pending(current) || freezing(current);
+}
+
+/*
+ * Iterate the free list gathering extents and discarding them. We need a cursor
+ * for the repeated iteration of gather/discard loop, so use the longest extent
+ * we found in the last batch as the key to start the next.
+ */
+static int
+xfs_trim_extents(
+ struct xfs_perag *pag,
+ xfs_daddr_t start,
+ xfs_daddr_t end,
+ xfs_daddr_t minlen,
+ uint64_t *blocks_trimmed)
+{
+ struct xfs_alloc_rec_incore tcur = {
+ .ar_blockcount = pag->pagf_longest,
+ .ar_startblock = NULLAGBLOCK,
+ };
+ int error = 0;
+
+ do {
+ struct xfs_busy_extents *extents;
+
+ extents = kzalloc(sizeof(*extents), GFP_KERNEL);
+ if (!extents) {
+ error = -ENOMEM;
+ break;
+ }
+
+ extents->mount = pag->pag_mount;
+ extents->owner = extents;
+ INIT_LIST_HEAD(&extents->extent_list);
+
+ error = xfs_trim_gather_extents(pag, start, end, minlen,
+ &tcur, extents, blocks_trimmed);
+ if (error) {
+ kfree(extents);
+ break;
+ }
+
+ /*
+ * We hand the extent list to the discard function here so the
+ * discarded extents can be removed from the busy extent list.
+ * This allows the discards to run asynchronously with gathering
+ * the next round of extents to discard.
+ *
+ * However, we must ensure that we do not reference the extent
+ * list after this function call, as it may have been freed by
+ * the time control returns to us.
+ */
+ error = xfs_discard_extents(pag->pag_mount, extents);
+ if (error)
+ break;
+
+ if (xfs_trim_should_stop())
+ break;
+
+ } while (tcur.ar_blockcount != 0);
+
+ return error;
+
+}
+
/*
* trim a range of the filesystem.
*
@@ -195,12 +413,12 @@ xfs_ioc_trim(
for_each_perag_range(mp, agno, xfs_daddr_to_agno(mp, end), pag) {
error = xfs_trim_extents(pag, start, end, minlen,
&blocks_trimmed);
- if (error) {
+ if (error)
last_error = error;
- if (error == -ERESTARTSYS) {
- xfs_perag_rele(pag);
- break;
- }
+
+ if (xfs_trim_should_stop()) {
+ xfs_perag_rele(pag);
+ break;
}
}
diff --git a/fs/xfs/xfs_discard.h b/fs/xfs/xfs_discard.h
index de92d9cc958f..2b1a85223a56 100644
--- a/fs/xfs/xfs_discard.h
+++ b/fs/xfs/xfs_discard.h
@@ -3,8 +3,10 @@
#define XFS_DISCARD_H 1
struct fstrim_range;
-struct list_head;
+struct xfs_mount;
+struct xfs_busy_extents;
-extern int xfs_ioc_trim(struct xfs_mount *, struct fstrim_range __user *);
+int xfs_discard_extents(struct xfs_mount *mp, struct xfs_busy_extents *busy);
+int xfs_ioc_trim(struct xfs_mount *mp, struct fstrim_range __user *fstrim);
#endif /* XFS_DISCARD_H */
diff --git a/fs/xfs/xfs_export.c b/fs/xfs/xfs_export.c
index 1064c2342876..7cd09c3a82cb 100644
--- a/fs/xfs/xfs_export.c
+++ b/fs/xfs/xfs_export.c
@@ -146,6 +146,20 @@ xfs_nfs_get_inode(
return ERR_PTR(error);
}
+ /*
+ * Reload the incore unlinked list to avoid failure in inodegc.
+ * Use an unlocked check here because unrecovered unlinked inodes
+ * should be somewhat rare.
+ */
+ if (xfs_inode_unlinked_incomplete(ip)) {
+ error = xfs_inode_reload_unlinked(ip);
+ if (error) {
+ xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+ xfs_irele(ip);
+ return ERR_PTR(error);
+ }
+ }
+
if (VFS_I(ip)->i_generation != generation) {
xfs_irele(ip);
return ERR_PTR(-ESTALE);
diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c
index 7c2fdc71e42d..9ecfdcdc752f 100644
--- a/fs/xfs/xfs_extent_busy.c
+++ b/fs/xfs/xfs_extent_busy.c
@@ -19,13 +19,13 @@
#include "xfs_log.h"
#include "xfs_ag.h"
-void
-xfs_extent_busy_insert(
- struct xfs_trans *tp,
+static void
+xfs_extent_busy_insert_list(
struct xfs_perag *pag,
xfs_agblock_t bno,
xfs_extlen_t len,
- unsigned int flags)
+ unsigned int flags,
+ struct list_head *busy_list)
{
struct xfs_extent_busy *new;
struct xfs_extent_busy *busyp;
@@ -40,7 +40,7 @@ xfs_extent_busy_insert(
new->flags = flags;
/* trace before insert to be able to see failed inserts */
- trace_xfs_extent_busy(tp->t_mountp, pag->pag_agno, bno, len);
+ trace_xfs_extent_busy(pag->pag_mount, pag->pag_agno, bno, len);
spin_lock(&pag->pagb_lock);
rbp = &pag->pagb_tree.rb_node;
@@ -62,10 +62,33 @@ xfs_extent_busy_insert(
rb_link_node(&new->rb_node, parent, rbp);
rb_insert_color(&new->rb_node, &pag->pagb_tree);
- list_add(&new->list, &tp->t_busy);
+ /* always process discard lists in fifo order */
+ list_add_tail(&new->list, busy_list);
spin_unlock(&pag->pagb_lock);
}
+void
+xfs_extent_busy_insert(
+ struct xfs_trans *tp,
+ struct xfs_perag *pag,
+ xfs_agblock_t bno,
+ xfs_extlen_t len,
+ unsigned int flags)
+{
+ xfs_extent_busy_insert_list(pag, bno, len, flags, &tp->t_busy);
+}
+
+void
+xfs_extent_busy_insert_discard(
+ struct xfs_perag *pag,
+ xfs_agblock_t bno,
+ xfs_extlen_t len,
+ struct list_head *busy_list)
+{
+ xfs_extent_busy_insert_list(pag, bno, len, XFS_EXTENT_BUSY_DISCARDED,
+ busy_list);
+}
+
/*
* Search for a busy extent within the range of the extent we are about to
* allocate. You need to be holding the busy extent tree lock when calling
diff --git a/fs/xfs/xfs_extent_busy.h b/fs/xfs/xfs_extent_busy.h
index c37bf87e6781..0639aab336f3 100644
--- a/fs/xfs/xfs_extent_busy.h
+++ b/fs/xfs/xfs_extent_busy.h
@@ -16,9 +16,6 @@ struct xfs_alloc_arg;
/*
* Busy block/extent entry. Indexed by a rbtree in perag to mark blocks that
* have been freed but whose transactions aren't committed to disk yet.
- *
- * Note that we use the transaction ID to record the transaction, not the
- * transaction structure itself. See xfs_extent_busy_insert() for details.
*/
struct xfs_extent_busy {
struct rb_node rb_node; /* ag by-bno indexed search tree */
@@ -31,11 +28,32 @@ struct xfs_extent_busy {
#define XFS_EXTENT_BUSY_SKIP_DISCARD 0x02 /* do not discard */
};
+/*
+ * List used to track groups of related busy extents all the way through
+ * to discard completion.
+ */
+struct xfs_busy_extents {
+ struct xfs_mount *mount;
+ struct list_head extent_list;
+ struct work_struct endio_work;
+
+ /*
+ * Owner is the object containing the struct xfs_busy_extents to free
+ * once the busy extents have been processed. If only the
+ * xfs_busy_extents object needs freeing, then point this at itself.
+ */
+ void *owner;
+};
+
void
xfs_extent_busy_insert(struct xfs_trans *tp, struct xfs_perag *pag,
xfs_agblock_t bno, xfs_extlen_t len, unsigned int flags);
void
+xfs_extent_busy_insert_discard(struct xfs_perag *pag, xfs_agblock_t bno,
+ xfs_extlen_t len, struct list_head *busy_list);
+
+void
xfs_extent_busy_clear(struct xfs_mount *mp, struct list_head *list,
bool do_discard);
diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
index f1a5ecf099aa..3fa8789820ad 100644
--- a/fs/xfs/xfs_extfree_item.c
+++ b/fs/xfs/xfs_extfree_item.c
@@ -660,6 +660,7 @@ xfs_efi_item_recover(
struct xfs_log_item *lip,
struct list_head *capture_list)
{
+ struct xfs_trans_res resv;
struct xfs_efi_log_item *efip = EFI_ITEM(lip);
struct xfs_mount *mp = lip->li_log->l_mp;
struct xfs_efd_log_item *efdp;
@@ -683,7 +684,8 @@ xfs_efi_item_recover(
}
}
- error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
+ resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate);
+ error = xfs_trans_alloc(mp, &resv, 0, 0, 0, &tp);
if (error)
return error;
efdp = xfs_trans_get_efd(tp, efip, efip->efi_format.efi_nextents);
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index 10403ba9b58f..736e5545f584 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -565,6 +565,19 @@ err:
}
#endif /* CONFIG_XFS_RT */
+static inline bool
+rmap_not_shareable(struct xfs_mount *mp, const struct xfs_rmap_irec *r)
+{
+ if (!xfs_has_reflink(mp))
+ return true;
+ if (XFS_RMAP_NON_INODE_OWNER(r->rm_owner))
+ return true;
+ if (r->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK |
+ XFS_RMAP_UNWRITTEN))
+ return true;
+ return false;
+}
+
/* Execute a getfsmap query against the regular data device. */
STATIC int
__xfs_getfsmap_datadev(
@@ -598,7 +611,6 @@ __xfs_getfsmap_datadev(
* low to the fsmap low key and max out the high key to the end
* of the AG.
*/
- info->low.rm_startblock = XFS_FSB_TO_AGBNO(mp, start_fsb);
info->low.rm_offset = XFS_BB_TO_FSBT(mp, keys[0].fmr_offset);
error = xfs_fsmap_owner_to_rmap(&info->low, &keys[0]);
if (error)
@@ -608,12 +620,9 @@ __xfs_getfsmap_datadev(
/* Adjust the low key if we are continuing from where we left off. */
if (info->low.rm_blockcount == 0) {
- /* empty */
- } else if (XFS_RMAP_NON_INODE_OWNER(info->low.rm_owner) ||
- (info->low.rm_flags & (XFS_RMAP_ATTR_FORK |
- XFS_RMAP_BMBT_BLOCK |
- XFS_RMAP_UNWRITTEN))) {
- info->low.rm_startblock += info->low.rm_blockcount;
+ /* No previous record from which to continue */
+ } else if (rmap_not_shareable(mp, &info->low)) {
+ /* Last record seen was an unshareable extent */
info->low.rm_owner = 0;
info->low.rm_offset = 0;
@@ -621,8 +630,10 @@ __xfs_getfsmap_datadev(
if (XFS_FSB_TO_DADDR(mp, start_fsb) >= eofs)
return 0;
} else {
+ /* Last record seen was a shareable file data extent */
info->low.rm_offset += info->low.rm_blockcount;
}
+ info->low.rm_startblock = XFS_FSB_TO_AGBNO(mp, start_fsb);
info->high.rm_startblock = -1U;
info->high.rm_owner = ULLONG_MAX;
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index e541f5c0bc25..3c210ac83713 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -113,7 +113,7 @@ xfs_inode_alloc(
INIT_LIST_HEAD(&ip->i_ioend_list);
spin_lock_init(&ip->i_ioend_lock);
ip->i_next_unlinked = NULLAGINO;
- ip->i_prev_unlinked = NULLAGINO;
+ ip->i_prev_unlinked = 0;
return ip;
}
@@ -443,7 +443,7 @@ xfs_inodegc_queue_all(
int cpu;
bool ret = false;
- for_each_online_cpu(cpu) {
+ for_each_cpu(cpu, &mp->m_inodegc_cpumask) {
gc = per_cpu_ptr(mp->m_inodegc, cpu);
if (!llist_empty(&gc->list)) {
mod_delayed_work_on(cpu, mp->m_inodegc_wq, &gc->work, 0);
@@ -463,7 +463,7 @@ xfs_inodegc_wait_all(
int error = 0;
flush_workqueue(mp->m_inodegc_wq);
- for_each_online_cpu(cpu) {
+ for_each_cpu(cpu, &mp->m_inodegc_cpumask) {
struct xfs_inodegc *gc;
gc = per_cpu_ptr(mp->m_inodegc, cpu);
@@ -1845,9 +1845,17 @@ xfs_inodegc_worker(
struct xfs_inodegc, work);
struct llist_node *node = llist_del_all(&gc->list);
struct xfs_inode *ip, *n;
+ struct xfs_mount *mp = gc->mp;
unsigned int nofs_flag;
- ASSERT(gc->cpu == smp_processor_id());
+ /*
+ * Clear the cpu mask bit and ensure that we have seen the latest
+ * update of the gc structure associated with this CPU. This matches
+ * with the release semantics used when setting the cpumask bit in
+ * xfs_inodegc_queue.
+ */
+ cpumask_clear_cpu(gc->cpu, &mp->m_inodegc_cpumask);
+ smp_mb__after_atomic();
WRITE_ONCE(gc->items, 0);
@@ -1862,7 +1870,7 @@ xfs_inodegc_worker(
nofs_flag = memalloc_nofs_save();
ip = llist_entry(node, struct xfs_inode, i_gclist);
- trace_xfs_inodegc_worker(ip->i_mount, READ_ONCE(gc->shrinker_hits));
+ trace_xfs_inodegc_worker(mp, READ_ONCE(gc->shrinker_hits));
WRITE_ONCE(gc->shrinker_hits, 0);
llist_for_each_entry_safe(ip, n, node, i_gclist) {
@@ -2057,6 +2065,7 @@ xfs_inodegc_queue(
struct xfs_inodegc *gc;
int items;
unsigned int shrinker_hits;
+ unsigned int cpu_nr;
unsigned long queue_delay = 1;
trace_xfs_inode_set_need_inactive(ip);
@@ -2064,18 +2073,28 @@ xfs_inodegc_queue(
ip->i_flags |= XFS_NEED_INACTIVE;
spin_unlock(&ip->i_flags_lock);
- gc = get_cpu_ptr(mp->m_inodegc);
+ cpu_nr = get_cpu();
+ gc = this_cpu_ptr(mp->m_inodegc);
llist_add(&ip->i_gclist, &gc->list);
items = READ_ONCE(gc->items);
WRITE_ONCE(gc->items, items + 1);
shrinker_hits = READ_ONCE(gc->shrinker_hits);
/*
+ * Ensure the list add is always seen by anyone who finds the cpumask
+ * bit set. This effectively gives the cpumask bit set operation
+ * release ordering semantics.
+ */
+ smp_mb__before_atomic();
+ if (!cpumask_test_cpu(cpu_nr, &mp->m_inodegc_cpumask))
+ cpumask_test_and_set_cpu(cpu_nr, &mp->m_inodegc_cpumask);
+
+ /*
* We queue the work while holding the current CPU so that the work
* is scheduled to run on this CPU.
*/
if (!xfs_is_inodegc_enabled(mp)) {
- put_cpu_ptr(gc);
+ put_cpu();
return;
}
@@ -2085,7 +2104,7 @@ xfs_inodegc_queue(
trace_xfs_inodegc_queue(mp, __return_address);
mod_delayed_work_on(current_cpu(), mp->m_inodegc_wq, &gc->work,
queue_delay);
- put_cpu_ptr(gc);
+ put_cpu();
if (xfs_inodegc_want_flush_work(ip, items, shrinker_hits)) {
trace_xfs_inodegc_throttle(mp, __return_address);
@@ -2094,47 +2113,6 @@ xfs_inodegc_queue(
}
/*
- * Fold the dead CPU inodegc queue into the current CPUs queue.
- */
-void
-xfs_inodegc_cpu_dead(
- struct xfs_mount *mp,
- unsigned int dead_cpu)
-{
- struct xfs_inodegc *dead_gc, *gc;
- struct llist_node *first, *last;
- unsigned int count = 0;
-
- dead_gc = per_cpu_ptr(mp->m_inodegc, dead_cpu);
- cancel_delayed_work_sync(&dead_gc->work);
-
- if (llist_empty(&dead_gc->list))
- return;
-
- first = dead_gc->list.first;
- last = first;
- while (last->next) {
- last = last->next;
- count++;
- }
- dead_gc->list.first = NULL;
- dead_gc->items = 0;
-
- /* Add pending work to current CPU */
- gc = get_cpu_ptr(mp->m_inodegc);
- llist_add_batch(first, last, &gc->list);
- count += READ_ONCE(gc->items);
- WRITE_ONCE(gc->items, count);
-
- if (xfs_is_inodegc_enabled(mp)) {
- trace_xfs_inodegc_queue(mp, __return_address);
- mod_delayed_work_on(current_cpu(), mp->m_inodegc_wq, &gc->work,
- 0);
- }
- put_cpu_ptr(gc);
-}
-
-/*
* We set the inode flag atomically with the radix tree tag. Once we get tag
* lookups on the radix tree, this inode flag can go away.
*
@@ -2195,7 +2173,7 @@ xfs_inodegc_shrinker_count(
if (!xfs_is_inodegc_enabled(mp))
return 0;
- for_each_online_cpu(cpu) {
+ for_each_cpu(cpu, &mp->m_inodegc_cpumask) {
gc = per_cpu_ptr(mp->m_inodegc, cpu);
if (!llist_empty(&gc->list))
return XFS_INODEGC_SHRINKER_COUNT;
@@ -2220,7 +2198,7 @@ xfs_inodegc_shrinker_scan(
trace_xfs_inodegc_shrinker_scan(mp, sc, __return_address);
- for_each_online_cpu(cpu) {
+ for_each_cpu(cpu, &mp->m_inodegc_cpumask) {
gc = per_cpu_ptr(mp->m_inodegc, cpu);
if (!llist_empty(&gc->list)) {
unsigned int h = READ_ONCE(gc->shrinker_hits);
diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h
index 2fa6f2e09d07..905944dafbe5 100644
--- a/fs/xfs/xfs_icache.h
+++ b/fs/xfs/xfs_icache.h
@@ -79,7 +79,6 @@ void xfs_inodegc_push(struct xfs_mount *mp);
int xfs_inodegc_flush(struct xfs_mount *mp);
void xfs_inodegc_stop(struct xfs_mount *mp);
void xfs_inodegc_start(struct xfs_mount *mp);
-void xfs_inodegc_cpu_dead(struct xfs_mount *mp, unsigned int cpu);
int xfs_inodegc_register_shrinker(struct xfs_mount *mp);
#endif
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 360fe83a334f..4d55f58d99b7 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1642,8 +1642,11 @@ xfs_inode_needs_inactive(
if (VFS_I(ip)->i_mode == 0)
return false;
- /* If this is a read-only mount, don't do this (would generate I/O) */
- if (xfs_is_readonly(mp))
+ /*
+ * If this is a read-only mount, don't do this (would generate I/O)
+ * unless we're in log recovery and cleaning the iunlinked list.
+ */
+ if (xfs_is_readonly(mp) && !xlog_recovery_needed(mp->m_log))
return false;
/* If the log isn't running, push inodes straight to reclaim. */
@@ -1703,8 +1706,11 @@ xfs_inactive(
mp = ip->i_mount;
ASSERT(!xfs_iflags_test(ip, XFS_IRECOVERY));
- /* If this is a read-only mount, don't do this (would generate I/O) */
- if (xfs_is_readonly(mp))
+ /*
+ * If this is a read-only mount, don't do this (would generate I/O)
+ * unless we're in log recovery and cleaning the iunlinked list.
+ */
+ if (xfs_is_readonly(mp) && !xlog_recovery_needed(mp->m_log))
goto out;
/* Metadata inodes require explicit resource cleanup. */
@@ -1736,9 +1742,21 @@ xfs_inactive(
ip->i_df.if_nextents > 0 || ip->i_delayed_blks > 0))
truncate = 1;
- error = xfs_qm_dqattach(ip);
- if (error)
- goto out;
+ if (xfs_iflags_test(ip, XFS_IQUOTAUNCHECKED)) {
+ /*
+ * If this inode is being inactivated during a quotacheck and
+ * has not yet been scanned by quotacheck, we /must/ remove
+ * the dquots from the inode before inactivation changes the
+ * block and inode counts. Most probably this is a result of
+ * reloading the incore iunlinked list to purge unrecovered
+ * unlinked inodes.
+ */
+ xfs_qm_dqdetach(ip);
+ } else {
+ error = xfs_qm_dqattach(ip);
+ if (error)
+ goto out;
+ }
if (S_ISLNK(VFS_I(ip)->i_mode))
error = xfs_inactive_symlink(ip);
@@ -1822,12 +1840,17 @@ xfs_iunlink_lookup(
rcu_read_lock();
ip = radix_tree_lookup(&pag->pag_ici_root, agino);
+ if (!ip) {
+ /* Caller can handle inode not being in memory. */
+ rcu_read_unlock();
+ return NULL;
+ }
/*
- * Inode not in memory or in RCU freeing limbo should not happen.
- * Warn about this and let the caller handle the failure.
+ * Inode in RCU freeing limbo should not happen. Warn about this and
+ * let the caller handle the failure.
*/
- if (WARN_ON_ONCE(!ip || !ip->i_ino)) {
+ if (WARN_ON_ONCE(!ip->i_ino)) {
rcu_read_unlock();
return NULL;
}
@@ -1836,7 +1859,10 @@ xfs_iunlink_lookup(
return ip;
}
-/* Update the prev pointer of the next agino. */
+/*
+ * Update the prev pointer of the next agino. Returns -ENOLINK if the inode
+ * is not in cache.
+ */
static int
xfs_iunlink_update_backref(
struct xfs_perag *pag,
@@ -1851,7 +1877,8 @@ xfs_iunlink_update_backref(
ip = xfs_iunlink_lookup(pag, next_agino);
if (!ip)
- return -EFSCORRUPTED;
+ return -ENOLINK;
+
ip->i_prev_unlinked = prev_agino;
return 0;
}
@@ -1895,6 +1922,64 @@ xfs_iunlink_update_bucket(
return 0;
}
+/*
+ * Load the inode @next_agino into the cache and set its prev_unlinked pointer
+ * to @prev_agino. Caller must hold the AGI to synchronize with other changes
+ * to the unlinked list.
+ */
+STATIC int
+xfs_iunlink_reload_next(
+ struct xfs_trans *tp,
+ struct xfs_buf *agibp,
+ xfs_agino_t prev_agino,
+ xfs_agino_t next_agino)
+{
+ struct xfs_perag *pag = agibp->b_pag;
+ struct xfs_mount *mp = pag->pag_mount;
+ struct xfs_inode *next_ip = NULL;
+ xfs_ino_t ino;
+ int error;
+
+ ASSERT(next_agino != NULLAGINO);
+
+#ifdef DEBUG
+ rcu_read_lock();
+ next_ip = radix_tree_lookup(&pag->pag_ici_root, next_agino);
+ ASSERT(next_ip == NULL);
+ rcu_read_unlock();
+#endif
+
+ xfs_info_ratelimited(mp,
+ "Found unrecovered unlinked inode 0x%x in AG 0x%x. Initiating recovery.",
+ next_agino, pag->pag_agno);
+
+ /*
+ * Use an untrusted lookup just to be cautious in case the AGI has been
+ * corrupted and now points at a free inode. That shouldn't happen,
+ * but we'd rather shut down now since we're already running in a weird
+ * situation.
+ */
+ ino = XFS_AGINO_TO_INO(mp, pag->pag_agno, next_agino);
+ error = xfs_iget(mp, tp, ino, XFS_IGET_UNTRUSTED, 0, &next_ip);
+ if (error)
+ return error;
+
+ /* If this is not an unlinked inode, something is very wrong. */
+ if (VFS_I(next_ip)->i_nlink != 0) {
+ error = -EFSCORRUPTED;
+ goto rele;
+ }
+
+ next_ip->i_prev_unlinked = prev_agino;
+ trace_xfs_iunlink_reload_next(next_ip);
+rele:
+ ASSERT(!(VFS_I(next_ip)->i_state & I_DONTCACHE));
+ if (xfs_is_quotacheck_running(mp) && next_ip)
+ xfs_iflags_set(next_ip, XFS_IQUOTAUNCHECKED);
+ xfs_irele(next_ip);
+ return error;
+}
+
static int
xfs_iunlink_insert_inode(
struct xfs_trans *tp,
@@ -1926,6 +2011,8 @@ xfs_iunlink_insert_inode(
* inode.
*/
error = xfs_iunlink_update_backref(pag, agino, next_agino);
+ if (error == -ENOLINK)
+ error = xfs_iunlink_reload_next(tp, agibp, agino, next_agino);
if (error)
return error;
@@ -1941,6 +2028,7 @@ xfs_iunlink_insert_inode(
}
/* Point the head of the list to point to this inode. */
+ ip->i_prev_unlinked = NULLAGINO;
return xfs_iunlink_update_bucket(tp, pag, agibp, bucket_index, agino);
}
@@ -2020,6 +2108,9 @@ xfs_iunlink_remove_inode(
*/
error = xfs_iunlink_update_backref(pag, ip->i_prev_unlinked,
ip->i_next_unlinked);
+ if (error == -ENOLINK)
+ error = xfs_iunlink_reload_next(tp, agibp, ip->i_prev_unlinked,
+ ip->i_next_unlinked);
if (error)
return error;
@@ -2040,7 +2131,7 @@ xfs_iunlink_remove_inode(
}
ip->i_next_unlinked = NULLAGINO;
- ip->i_prev_unlinked = NULLAGINO;
+ ip->i_prev_unlinked = 0;
return error;
}
@@ -3529,3 +3620,117 @@ xfs_iunlock2_io_mmap(
if (ip1 != ip2)
inode_unlock(VFS_I(ip1));
}
+
+/*
+ * Reload the incore inode list for this inode. Caller should ensure that
+ * the link count cannot change, either by taking ILOCK_SHARED or otherwise
+ * preventing other threads from executing.
+ */
+int
+xfs_inode_reload_unlinked_bucket(
+ struct xfs_trans *tp,
+ struct xfs_inode *ip)
+{
+ struct xfs_mount *mp = tp->t_mountp;
+ struct xfs_buf *agibp;
+ struct xfs_agi *agi;
+ struct xfs_perag *pag;
+ xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, ip->i_ino);
+ xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
+ xfs_agino_t prev_agino, next_agino;
+ unsigned int bucket;
+ bool foundit = false;
+ int error;
+
+ /* Grab the first inode in the list */
+ pag = xfs_perag_get(mp, agno);
+ error = xfs_ialloc_read_agi(pag, tp, &agibp);
+ xfs_perag_put(pag);
+ if (error)
+ return error;
+
+ /*
+ * We've taken ILOCK_SHARED and the AGI buffer lock to stabilize the
+ * incore unlinked list pointers for this inode. Check once more to
+ * see if we raced with anyone else to reload the unlinked list.
+ */
+ if (!xfs_inode_unlinked_incomplete(ip)) {
+ foundit = true;
+ goto out_agibp;
+ }
+
+ bucket = agino % XFS_AGI_UNLINKED_BUCKETS;
+ agi = agibp->b_addr;
+
+ trace_xfs_inode_reload_unlinked_bucket(ip);
+
+ xfs_info_ratelimited(mp,
+ "Found unrecovered unlinked inode 0x%x in AG 0x%x. Initiating list recovery.",
+ agino, agno);
+
+ prev_agino = NULLAGINO;
+ next_agino = be32_to_cpu(agi->agi_unlinked[bucket]);
+ while (next_agino != NULLAGINO) {
+ struct xfs_inode *next_ip = NULL;
+
+ /* Found this caller's inode, set its backlink. */
+ if (next_agino == agino) {
+ next_ip = ip;
+ next_ip->i_prev_unlinked = prev_agino;
+ foundit = true;
+ goto next_inode;
+ }
+
+ /* Try in-memory lookup first. */
+ next_ip = xfs_iunlink_lookup(pag, next_agino);
+ if (next_ip)
+ goto next_inode;
+
+ /* Inode not in memory, try reloading it. */
+ error = xfs_iunlink_reload_next(tp, agibp, prev_agino,
+ next_agino);
+ if (error)
+ break;
+
+ /* Grab the reloaded inode. */
+ next_ip = xfs_iunlink_lookup(pag, next_agino);
+ if (!next_ip) {
+ /* No incore inode at all? We reloaded it... */
+ ASSERT(next_ip != NULL);
+ error = -EFSCORRUPTED;
+ break;
+ }
+
+next_inode:
+ prev_agino = next_agino;
+ next_agino = next_ip->i_next_unlinked;
+ }
+
+out_agibp:
+ xfs_trans_brelse(tp, agibp);
+ /* Should have found this inode somewhere in the iunlinked bucket. */
+ if (!error && !foundit)
+ error = -EFSCORRUPTED;
+ return error;
+}
+
+/* Decide if this inode is missing its unlinked list and reload it. */
+int
+xfs_inode_reload_unlinked(
+ struct xfs_inode *ip)
+{
+ struct xfs_trans *tp;
+ int error;
+
+ error = xfs_trans_alloc_empty(ip->i_mount, &tp);
+ if (error)
+ return error;
+
+ xfs_ilock(ip, XFS_ILOCK_SHARED);
+ if (xfs_inode_unlinked_incomplete(ip))
+ error = xfs_inode_reload_unlinked_bucket(tp, ip);
+ xfs_iunlock(ip, XFS_ILOCK_SHARED);
+ xfs_trans_cancel(tp);
+
+ return error;
+}
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 7547caf2f2ab..0c5bdb91152e 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -68,8 +68,21 @@ typedef struct xfs_inode {
uint64_t i_diflags2; /* XFS_DIFLAG2_... */
struct timespec64 i_crtime; /* time created */
- /* unlinked list pointers */
+ /*
+ * Unlinked list pointers. These point to the next and previous inodes
+ * in the AGI unlinked bucket list, respectively. These fields can
+ * only be updated with the AGI locked.
+ *
+ * i_next_unlinked caches di_next_unlinked.
+ */
xfs_agino_t i_next_unlinked;
+
+ /*
+ * If the inode is not on an unlinked list, this field is zero. If the
+ * inode is the first element in an unlinked list, this field is
+ * NULLAGINO. Otherwise, i_prev_unlinked points to the previous inode
+ * in the unlinked list.
+ */
xfs_agino_t i_prev_unlinked;
/* VFS inode */
@@ -81,6 +94,11 @@ typedef struct xfs_inode {
struct list_head i_ioend_list;
} xfs_inode_t;
+static inline bool xfs_inode_on_unlinked_list(const struct xfs_inode *ip)
+{
+ return ip->i_prev_unlinked != 0;
+}
+
static inline bool xfs_inode_has_attr_fork(struct xfs_inode *ip)
{
return ip->i_forkoff > 0;
@@ -326,6 +344,9 @@ static inline bool xfs_inode_has_large_extent_counts(struct xfs_inode *ip)
*/
#define XFS_INACTIVATING (1 << 13)
+/* Quotacheck is running but inode has not been added to quota counts. */
+#define XFS_IQUOTAUNCHECKED (1 << 14)
+
/* All inode state flags related to inode reclaim. */
#define XFS_ALL_IRECLAIM_FLAGS (XFS_IRECLAIMABLE | \
XFS_IRECLAIM | \
@@ -340,7 +361,7 @@ static inline bool xfs_inode_has_large_extent_counts(struct xfs_inode *ip)
#define XFS_IRECLAIM_RESET_FLAGS \
(XFS_IRECLAIMABLE | XFS_IRECLAIM | \
XFS_IDIRTY_RELEASE | XFS_ITRUNCATED | XFS_NEED_INACTIVE | \
- XFS_INACTIVATING)
+ XFS_INACTIVATING | XFS_IQUOTAUNCHECKED)
/*
* Flags for inode locking.
@@ -575,4 +596,13 @@ void xfs_end_io(struct work_struct *work);
int xfs_ilock2_io_mmap(struct xfs_inode *ip1, struct xfs_inode *ip2);
void xfs_iunlock2_io_mmap(struct xfs_inode *ip1, struct xfs_inode *ip2);
+static inline bool
+xfs_inode_unlinked_incomplete(
+ struct xfs_inode *ip)
+{
+ return VFS_I(ip)->i_nlink == 0 && !xfs_inode_on_unlinked_list(ip);
+}
+int xfs_inode_reload_unlinked_bucket(struct xfs_trans *tp, struct xfs_inode *ip);
+int xfs_inode_reload_unlinked(struct xfs_inode *ip);
+
#endif /* __XFS_INODE_H__ */
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 2ededd3f6b8c..2b3b05c28e9e 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -573,10 +573,10 @@ xfs_vn_getattr(
stat->gid = vfsgid_into_kgid(vfsgid);
stat->ino = ip->i_ino;
stat->atime = inode->i_atime;
+ stat->mtime = inode->i_mtime;
+ stat->ctime = inode_get_ctime(inode);
stat->blocks = XFS_FSB_TO_BB(mp, ip->i_nblocks + ip->i_delayed_blks);
- fill_mg_cmtime(stat, request_mask, inode);
-
if (xfs_has_v3inodes(mp)) {
if (request_mask & STATX_BTIME) {
stat->result_mask |= STATX_BTIME;
@@ -584,6 +584,11 @@ xfs_vn_getattr(
}
}
+ if ((request_mask & STATX_CHANGE_COOKIE) && IS_I_VERSION(inode)) {
+ stat->change_cookie = inode_query_iversion(inode);
+ stat->result_mask |= STATX_CHANGE_COOKIE;
+ }
+
/*
* Note: If you add another clause to set an attribute flag, please
* update attributes_mask below.
@@ -917,7 +922,7 @@ xfs_setattr_size(
if (newsize != oldsize &&
!(iattr->ia_valid & (ATTR_CTIME | ATTR_MTIME))) {
iattr->ia_ctime = iattr->ia_mtime =
- current_mgtime(inode);
+ current_time(inode);
iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME;
}
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index c2093cb56092..f5377ba5967a 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -80,6 +80,17 @@ xfs_bulkstat_one_int(
if (error)
goto out;
+ /* Reload the incore unlinked list to avoid failure in inodegc. */
+ if (xfs_inode_unlinked_incomplete(ip)) {
+ error = xfs_inode_reload_unlinked_bucket(tp, ip);
+ if (error) {
+ xfs_iunlock(ip, XFS_ILOCK_SHARED);
+ xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+ xfs_irele(ip);
+ return error;
+ }
+ }
+
ASSERT(ip != NULL);
ASSERT(ip->i_imap.im_blkno != 0);
inode = VFS_I(ip);
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 79004d193e54..51c100c86177 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -715,15 +715,7 @@ xfs_log_mount(
* just worked.
*/
if (!xfs_has_norecovery(mp)) {
- /*
- * log recovery ignores readonly state and so we need to clear
- * mount-based read only state so it can write to disk.
- */
- bool readonly = test_and_clear_bit(XFS_OPSTATE_READONLY,
- &mp->m_opstate);
error = xlog_recover(log);
- if (readonly)
- set_bit(XFS_OPSTATE_READONLY, &mp->m_opstate);
if (error) {
xfs_warn(mp, "log mount/recovery failed: error %d",
error);
@@ -772,7 +764,6 @@ xfs_log_mount_finish(
struct xfs_mount *mp)
{
struct xlog *log = mp->m_log;
- bool readonly;
int error = 0;
if (xfs_has_norecovery(mp)) {
@@ -781,12 +772,6 @@ xfs_log_mount_finish(
}
/*
- * log recovery ignores readonly state and so we need to clear
- * mount-based read only state so it can write to disk.
- */
- readonly = test_and_clear_bit(XFS_OPSTATE_READONLY, &mp->m_opstate);
-
- /*
* During the second phase of log recovery, we need iget and
* iput to behave like they do for an active filesystem.
* xfs_fs_drop_inode needs to be able to prevent the deletion
@@ -835,8 +820,6 @@ xfs_log_mount_finish(
xfs_buftarg_drain(mp->m_ddev_targp);
clear_bit(XLOG_RECOVERY_NEEDED, &log->l_opstate);
- if (readonly)
- set_bit(XFS_OPSTATE_READONLY, &mp->m_opstate);
/* Make sure the log is dead if we're returning failure. */
ASSERT(!error || xlog_is_shutdown(log));
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index eccbfb99e894..67a99d94701e 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -16,8 +16,7 @@
#include "xfs_log.h"
#include "xfs_log_priv.h"
#include "xfs_trace.h"
-
-struct workqueue_struct *xfs_discard_wq;
+#include "xfs_discard.h"
/*
* Allocate a new ticket. Failing to get a new ticket makes it really hard to
@@ -103,7 +102,7 @@ xlog_cil_ctx_alloc(void)
ctx = kmem_zalloc(sizeof(*ctx), KM_NOFS);
INIT_LIST_HEAD(&ctx->committing);
- INIT_LIST_HEAD(&ctx->busy_extents);
+ INIT_LIST_HEAD(&ctx->busy_extents.extent_list);
INIT_LIST_HEAD(&ctx->log_items);
INIT_LIST_HEAD(&ctx->lv_chain);
INIT_WORK(&ctx->push_work, xlog_cil_push_work);
@@ -124,7 +123,7 @@ xlog_cil_push_pcp_aggregate(
struct xlog_cil_pcp *cilpcp;
int cpu;
- for_each_online_cpu(cpu) {
+ for_each_cpu(cpu, &ctx->cil_pcpmask) {
cilpcp = per_cpu_ptr(cil->xc_pcp, cpu);
ctx->ticket->t_curr_res += cilpcp->space_reserved;
@@ -132,7 +131,7 @@ xlog_cil_push_pcp_aggregate(
if (!list_empty(&cilpcp->busy_extents)) {
list_splice_init(&cilpcp->busy_extents,
- &ctx->busy_extents);
+ &ctx->busy_extents.extent_list);
}
if (!list_empty(&cilpcp->log_items))
list_splice_init(&cilpcp->log_items, &ctx->log_items);
@@ -165,7 +164,13 @@ xlog_cil_insert_pcp_aggregate(
if (!test_and_clear_bit(XLOG_CIL_PCP_SPACE, &cil->xc_flags))
return;
- for_each_online_cpu(cpu) {
+ /*
+ * We can race with other cpus setting cil_pcpmask. However, we've
+ * atomically cleared PCP_SPACE which forces other threads to add to
+ * the global space used count. cil_pcpmask is a superset of cilpcp
+ * structures that could have a nonzero space_used.
+ */
+ for_each_cpu(cpu, &ctx->cil_pcpmask) {
int old, prev;
cilpcp = per_cpu_ptr(cil->xc_pcp, cpu);
@@ -554,6 +559,7 @@ xlog_cil_insert_items(
int iovhdr_res = 0, split_res = 0, ctx_res = 0;
int space_used;
int order;
+ unsigned int cpu_nr;
struct xlog_cil_pcp *cilpcp;
ASSERT(tp);
@@ -577,7 +583,12 @@ xlog_cil_insert_items(
* can't be scheduled away between split sample/update operations that
* are done without outside locking to serialise them.
*/
- cilpcp = get_cpu_ptr(cil->xc_pcp);
+ cpu_nr = get_cpu();
+ cilpcp = this_cpu_ptr(cil->xc_pcp);
+
+ /* Tell the future push that there was work added by this CPU. */
+ if (!cpumask_test_cpu(cpu_nr, &ctx->cil_pcpmask))
+ cpumask_test_and_set_cpu(cpu_nr, &ctx->cil_pcpmask);
/*
* We need to take the CIL checkpoint unit reservation on the first
@@ -663,7 +674,7 @@ xlog_cil_insert_items(
continue;
list_add_tail(&lip->li_cil, &cilpcp->log_items);
}
- put_cpu_ptr(cilpcp);
+ put_cpu();
/*
* If we've overrun the reservation, dump the tx details before we move
@@ -696,76 +707,6 @@ xlog_cil_free_logvec(
}
}
-static void
-xlog_discard_endio_work(
- struct work_struct *work)
-{
- struct xfs_cil_ctx *ctx =
- container_of(work, struct xfs_cil_ctx, discard_endio_work);
- struct xfs_mount *mp = ctx->cil->xc_log->l_mp;
-
- xfs_extent_busy_clear(mp, &ctx->busy_extents, false);
- kmem_free(ctx);
-}
-
-/*
- * Queue up the actual completion to a thread to avoid IRQ-safe locking for
- * pagb_lock. Note that we need a unbounded workqueue, otherwise we might
- * get the execution delayed up to 30 seconds for weird reasons.
- */
-static void
-xlog_discard_endio(
- struct bio *bio)
-{
- struct xfs_cil_ctx *ctx = bio->bi_private;
-
- INIT_WORK(&ctx->discard_endio_work, xlog_discard_endio_work);
- queue_work(xfs_discard_wq, &ctx->discard_endio_work);
- bio_put(bio);
-}
-
-static void
-xlog_discard_busy_extents(
- struct xfs_mount *mp,
- struct xfs_cil_ctx *ctx)
-{
- struct list_head *list = &ctx->busy_extents;
- struct xfs_extent_busy *busyp;
- struct bio *bio = NULL;
- struct blk_plug plug;
- int error = 0;
-
- ASSERT(xfs_has_discard(mp));
-
- blk_start_plug(&plug);
- list_for_each_entry(busyp, list, list) {
- trace_xfs_discard_extent(mp, busyp->agno, busyp->bno,
- busyp->length);
-
- error = __blkdev_issue_discard(mp->m_ddev_targp->bt_bdev,
- XFS_AGB_TO_DADDR(mp, busyp->agno, busyp->bno),
- XFS_FSB_TO_BB(mp, busyp->length),
- GFP_NOFS, &bio);
- if (error && error != -EOPNOTSUPP) {
- xfs_info(mp,
- "discard failed for extent [0x%llx,%u], error %d",
- (unsigned long long)busyp->bno,
- busyp->length,
- error);
- break;
- }
- }
-
- if (bio) {
- bio->bi_private = ctx;
- bio->bi_end_io = xlog_discard_endio;
- submit_bio(bio);
- } else {
- xlog_discard_endio_work(&ctx->discard_endio_work);
- }
- blk_finish_plug(&plug);
-}
-
/*
* Mark all items committed and clear busy extents. We free the log vector
* chains in a separate pass so that we unpin the log items as quickly as
@@ -795,8 +736,8 @@ xlog_cil_committed(
xfs_trans_committed_bulk(ctx->cil->xc_log->l_ailp, &ctx->lv_chain,
ctx->start_lsn, abort);
- xfs_extent_busy_sort(&ctx->busy_extents);
- xfs_extent_busy_clear(mp, &ctx->busy_extents,
+ xfs_extent_busy_sort(&ctx->busy_extents.extent_list);
+ xfs_extent_busy_clear(mp, &ctx->busy_extents.extent_list,
xfs_has_discard(mp) && !abort);
spin_lock(&ctx->cil->xc_push_lock);
@@ -805,10 +746,14 @@ xlog_cil_committed(
xlog_cil_free_logvec(&ctx->lv_chain);
- if (!list_empty(&ctx->busy_extents))
- xlog_discard_busy_extents(mp, ctx);
- else
- kmem_free(ctx);
+ if (!list_empty(&ctx->busy_extents.extent_list)) {
+ ctx->busy_extents.mount = mp;
+ ctx->busy_extents.owner = ctx;
+ xfs_discard_extents(mp, &ctx->busy_extents);
+ return;
+ }
+
+ kmem_free(ctx);
}
void
@@ -1791,38 +1736,6 @@ out_shutdown:
}
/*
- * Move dead percpu state to the relevant CIL context structures.
- *
- * We have to lock the CIL context here to ensure that nothing is modifying
- * the percpu state, either addition or removal. Both of these are done under
- * the CIL context lock, so grabbing that exclusively here will ensure we can
- * safely drain the cilpcp for the CPU that is dying.
- */
-void
-xlog_cil_pcp_dead(
- struct xlog *log,
- unsigned int cpu)
-{
- struct xfs_cil *cil = log->l_cilp;
- struct xlog_cil_pcp *cilpcp = per_cpu_ptr(cil->xc_pcp, cpu);
- struct xfs_cil_ctx *ctx;
-
- down_write(&cil->xc_ctx_lock);
- ctx = cil->xc_ctx;
- if (ctx->ticket)
- ctx->ticket->t_curr_res += cilpcp->space_reserved;
- cilpcp->space_reserved = 0;
-
- if (!list_empty(&cilpcp->log_items))
- list_splice_init(&cilpcp->log_items, &ctx->log_items);
- if (!list_empty(&cilpcp->busy_extents))
- list_splice_init(&cilpcp->busy_extents, &ctx->busy_extents);
- atomic_add(cilpcp->space_used, &ctx->space_used);
- cilpcp->space_used = 0;
- up_write(&cil->xc_ctx_lock);
-}
-
-/*
* Perform initial CIL structure initialisation.
*/
int
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index 1bd2963e8fbd..fa3ad1d7b31c 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -6,6 +6,8 @@
#ifndef __XFS_LOG_PRIV_H__
#define __XFS_LOG_PRIV_H__
+#include "xfs_extent_busy.h" /* for struct xfs_busy_extents */
+
struct xfs_buf;
struct xlog;
struct xlog_ticket;
@@ -223,14 +225,19 @@ struct xfs_cil_ctx {
struct xlog_in_core *commit_iclog;
struct xlog_ticket *ticket; /* chkpt ticket */
atomic_t space_used; /* aggregate size of regions */
- struct list_head busy_extents; /* busy extents in chkpt */
+ struct xfs_busy_extents busy_extents;
struct list_head log_items; /* log items in chkpt */
struct list_head lv_chain; /* logvecs being pushed */
struct list_head iclog_entry;
struct list_head committing; /* ctx committing list */
- struct work_struct discard_endio_work;
struct work_struct push_work;
atomic_t order_id;
+
+ /*
+ * CPUs that could have added items to the percpu CIL data. Access is
+ * coordinated with xc_ctx_lock.
+ */
+ struct cpumask cil_pcpmask;
};
/*
@@ -278,9 +285,6 @@ struct xfs_cil {
wait_queue_head_t xc_push_wait; /* background push throttle */
void __percpu *xc_pcp; /* percpu CIL structures */
-#ifdef CONFIG_HOTPLUG_CPU
- struct list_head xc_pcp_list;
-#endif
} ____cacheline_aligned_in_smp;
/* xc_flags bit values */
@@ -705,9 +709,4 @@ xlog_kvmalloc(
return p;
}
-/*
- * CIL CPU dead notifier
- */
-void xlog_cil_pcp_dead(struct xlog *log, unsigned int cpu);
-
#endif /* __XFS_LOG_PRIV_H__ */
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 82c81d20459d..13b94d2e605b 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -329,7 +329,7 @@ xlog_find_verify_cycle(
* try a smaller size. We need to be able to read at least
* a log sector, or we're out of luck.
*/
- bufblks = 1 << ffs(nbblks);
+ bufblks = roundup_pow_of_two(nbblks);
while (bufblks > log->l_logBBsize)
bufblks >>= 1;
while (!(buffer = xlog_alloc_buffer(log, bufblks))) {
@@ -1528,7 +1528,7 @@ xlog_write_log_records(
* a smaller size. We need to be able to write at least a
* log sector, or we're out of luck.
*/
- bufblks = 1 << ffs(blocks);
+ bufblks = roundup_pow_of_two(blocks);
while (bufblks > log->l_logBBsize)
bufblks >>= 1;
while (!(buffer = xlog_alloc_buffer(log, bufblks))) {
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index a25eece3be2b..d19cca099bc3 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -60,6 +60,7 @@ struct xfs_error_cfg {
* Per-cpu deferred inode inactivation GC lists.
*/
struct xfs_inodegc {
+ struct xfs_mount *mp;
struct llist_head list;
struct delayed_work work;
int error;
@@ -67,9 +68,7 @@ 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
};
/*
@@ -98,7 +97,6 @@ typedef struct xfs_mount {
xfs_buftarg_t *m_ddev_targp; /* saves taking the address */
xfs_buftarg_t *m_logdev_targp;/* ptr to log device */
xfs_buftarg_t *m_rtdev_targp; /* ptr to rt device */
- struct list_head m_mount_list; /* global mount list */
void __percpu *m_inodegc; /* percpu inodegc structures */
/*
@@ -249,6 +247,9 @@ typedef struct xfs_mount {
unsigned int *m_errortag;
struct xfs_kobj m_errortag_kobj;
#endif
+
+ /* cpus that have inodes queued for inactivation */
+ struct cpumask m_inodegc_cpumask;
} xfs_mount_t;
#define M_IGEO(mp) (&(mp)->m_ino_geo)
@@ -404,6 +405,8 @@ __XFS_HAS_FEAT(nouuid, NOUUID)
#define XFS_OPSTATE_WARNED_SHRINK 8
/* Kernel has logged a warning about logged xattr updates being used. */
#define XFS_OPSTATE_WARNED_LARP 9
+/* Mount time quotacheck is running */
+#define XFS_OPSTATE_QUOTACHECK_RUNNING 10
#define __XFS_IS_OPSTATE(name, NAME) \
static inline bool xfs_is_ ## name (struct xfs_mount *mp) \
@@ -426,6 +429,11 @@ __XFS_IS_OPSTATE(inode32, INODE32)
__XFS_IS_OPSTATE(readonly, READONLY)
__XFS_IS_OPSTATE(inodegc_enabled, INODEGC_ENABLED)
__XFS_IS_OPSTATE(blockgc_enabled, BLOCKGC_ENABLED)
+#ifdef CONFIG_XFS_QUOTA
+__XFS_IS_OPSTATE(quotacheck_running, QUOTACHECK_RUNNING)
+#else
+# define xfs_is_quotacheck_running(mp) (false)
+#endif
static inline bool
xfs_should_warn(struct xfs_mount *mp, long nr)
@@ -443,7 +451,8 @@ xfs_should_warn(struct xfs_mount *mp, long nr)
{ (1UL << XFS_OPSTATE_BLOCKGC_ENABLED), "blockgc" }, \
{ (1UL << XFS_OPSTATE_WARNED_SCRUB), "wscrub" }, \
{ (1UL << XFS_OPSTATE_WARNED_SHRINK), "wshrink" }, \
- { (1UL << XFS_OPSTATE_WARNED_LARP), "wlarp" }
+ { (1UL << XFS_OPSTATE_WARNED_LARP), "wlarp" }, \
+ { (1UL << XFS_OPSTATE_QUOTACHECK_RUNNING), "quotacheck" }
/*
* Max and min values for mount-option defined I/O
diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c
index 4a9bbd3fe120..a7daa522e00f 100644
--- a/fs/xfs/xfs_notify_failure.c
+++ b/fs/xfs/xfs_notify_failure.c
@@ -126,8 +126,8 @@ xfs_dax_notify_ddev_failure(
struct xfs_rmap_irec ri_low = { };
struct xfs_rmap_irec ri_high;
struct xfs_agf *agf;
- xfs_agblock_t agend;
struct xfs_perag *pag;
+ xfs_agblock_t range_agend;
pag = xfs_perag_get(mp, agno);
error = xfs_alloc_read_agf(pag, tp, 0, &agf_bp);
@@ -148,10 +148,10 @@ xfs_dax_notify_ddev_failure(
ri_high.rm_startblock = XFS_FSB_TO_AGBNO(mp, end_fsbno);
agf = agf_bp->b_addr;
- agend = min(be32_to_cpu(agf->agf_length),
+ range_agend = min(be32_to_cpu(agf->agf_length) - 1,
ri_high.rm_startblock);
notify.startblock = ri_low.rm_startblock;
- notify.blockcount = agend - ri_low.rm_startblock;
+ notify.blockcount = range_agend + 1 - ri_low.rm_startblock;
error = xfs_rmap_query_range(cur, &ri_low, &ri_high,
xfs_dax_failure_fn, &notify);
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 6abcc34fafd8..086e78a6143a 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -1160,6 +1160,19 @@ xfs_qm_dqusage_adjust(
if (error)
return error;
+ /*
+ * Reload the incore unlinked list to avoid failure in inodegc.
+ * Use an unlocked check here because unrecovered unlinked inodes
+ * should be somewhat rare.
+ */
+ if (xfs_inode_unlinked_incomplete(ip)) {
+ error = xfs_inode_reload_unlinked(ip);
+ if (error) {
+ xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+ goto error0;
+ }
+ }
+
ASSERT(ip->i_delayed_blks == 0);
if (XFS_IS_REALTIME_INODE(ip)) {
@@ -1173,6 +1186,7 @@ xfs_qm_dqusage_adjust(
}
nblks = (xfs_qcnt_t)ip->i_nblocks - rtblks;
+ xfs_iflags_clear(ip, XFS_IQUOTAUNCHECKED);
/*
* Add the (disk blocks and inode) resources occupied by this
@@ -1319,8 +1333,10 @@ xfs_qm_quotacheck(
flags |= XFS_PQUOTA_CHKD;
}
+ xfs_set_quotacheck_running(mp);
error = xfs_iwalk_threaded(mp, 0, 0, xfs_qm_dqusage_adjust, 0, true,
NULL);
+ xfs_clear_quotacheck_running(mp);
/*
* On error, the inode walk may have partially populated the dquot
diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c
index edd8587658d5..2d4444d61e98 100644
--- a/fs/xfs/xfs_refcount_item.c
+++ b/fs/xfs/xfs_refcount_item.c
@@ -477,6 +477,7 @@ xfs_cui_item_recover(
struct xfs_log_item *lip,
struct list_head *capture_list)
{
+ struct xfs_trans_res resv;
struct xfs_cui_log_item *cuip = CUI_ITEM(lip);
struct xfs_cud_log_item *cudp;
struct xfs_trans *tp;
@@ -514,8 +515,9 @@ xfs_cui_item_recover(
* doesn't fit. We need to reserve enough blocks to handle a
* full btree split on either end of the refcount range.
*/
- error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate,
- mp->m_refc_maxlevels * 2, 0, XFS_TRANS_RESERVE, &tp);
+ resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate);
+ error = xfs_trans_alloc(mp, &resv, mp->m_refc_maxlevels * 2, 0,
+ XFS_TRANS_RESERVE, &tp);
if (error)
return error;
diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c
index 520c7ebdfed8..0e0e747028da 100644
--- a/fs/xfs/xfs_rmap_item.c
+++ b/fs/xfs/xfs_rmap_item.c
@@ -507,6 +507,7 @@ xfs_rui_item_recover(
struct xfs_log_item *lip,
struct list_head *capture_list)
{
+ struct xfs_trans_res resv;
struct xfs_rui_log_item *ruip = RUI_ITEM(lip);
struct xfs_rud_log_item *rudp;
struct xfs_trans *tp;
@@ -530,8 +531,9 @@ xfs_rui_item_recover(
}
}
- error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate,
- mp->m_rmap_maxlevels, 0, XFS_TRANS_RESERVE, &tp);
+ resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate);
+ error = xfs_trans_alloc(mp, &resv, mp->m_rmap_maxlevels, 0,
+ XFS_TRANS_RESERVE, &tp);
if (error)
return error;
rudp = xfs_trans_get_rud(tp, ruip);
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 1f77014c6e1a..819a3568b28f 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -56,28 +56,6 @@ static struct kset *xfs_kset; /* top-level xfs sysfs dir */
static struct xfs_kobj xfs_dbg_kobj; /* global debug sysfs attrs */
#endif
-#ifdef CONFIG_HOTPLUG_CPU
-static LIST_HEAD(xfs_mount_list);
-static DEFINE_SPINLOCK(xfs_mount_list_lock);
-
-static inline void xfs_mount_list_add(struct xfs_mount *mp)
-{
- spin_lock(&xfs_mount_list_lock);
- list_add(&mp->m_mount_list, &xfs_mount_list);
- spin_unlock(&xfs_mount_list_lock);
-}
-
-static inline void xfs_mount_list_del(struct xfs_mount *mp)
-{
- spin_lock(&xfs_mount_list_lock);
- list_del(&mp->m_mount_list);
- spin_unlock(&xfs_mount_list_lock);
-}
-#else /* !CONFIG_HOTPLUG_CPU */
-static inline void xfs_mount_list_add(struct xfs_mount *mp) {}
-static inline void xfs_mount_list_del(struct xfs_mount *mp) {}
-#endif
-
enum xfs_dax_mode {
XFS_DAX_INODE = 0,
XFS_DAX_ALWAYS = 1,
@@ -1135,9 +1113,8 @@ 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
+ gc->mp = mp;
init_llist_head(&gc->list);
gc->items = 0;
gc->error = 0;
@@ -1168,7 +1145,6 @@ xfs_fs_put_super(
xfs_freesb(mp);
xchk_mount_stats_free(mp);
free_percpu(mp->m_stats.xs_stats);
- xfs_mount_list_del(mp);
xfs_inodegc_free_percpu(mp);
xfs_destroy_percpu_counters(mp);
xfs_destroy_mount_workqueues(mp);
@@ -1577,13 +1553,6 @@ xfs_fs_fill_super(
if (error)
goto out_destroy_counters;
- /*
- * All percpu data structures requiring cleanup when a cpu goes offline
- * must be allocated before adding this @mp to the cpu-dead handler's
- * mount list.
- */
- xfs_mount_list_add(mp);
-
/* Allocate stats memory before we do operations that might use it */
mp->m_stats.xs_stats = alloc_percpu(struct xfsstats);
if (!mp->m_stats.xs_stats) {
@@ -1781,7 +1750,6 @@ xfs_fs_fill_super(
out_free_stats:
free_percpu(mp->m_stats.xs_stats);
out_destroy_inodegc:
- xfs_mount_list_del(mp);
xfs_inodegc_free_percpu(mp);
out_destroy_counters:
xfs_destroy_percpu_counters(mp);
@@ -2065,7 +2033,7 @@ static struct file_system_type xfs_fs_type = {
.init_fs_context = xfs_init_fs_context,
.parameters = xfs_fs_parameters,
.kill_sb = xfs_kill_sb,
- .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP | FS_MGTIME,
+ .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP,
};
MODULE_ALIAS_FS("xfs");
@@ -2326,49 +2294,6 @@ xfs_destroy_workqueues(void)
destroy_workqueue(xfs_alloc_wq);
}
-#ifdef CONFIG_HOTPLUG_CPU
-static int
-xfs_cpu_dead(
- unsigned int cpu)
-{
- struct xfs_mount *mp, *n;
-
- spin_lock(&xfs_mount_list_lock);
- list_for_each_entry_safe(mp, n, &xfs_mount_list, m_mount_list) {
- spin_unlock(&xfs_mount_list_lock);
- xfs_inodegc_cpu_dead(mp, cpu);
- xlog_cil_pcp_dead(mp->m_log, cpu);
- spin_lock(&xfs_mount_list_lock);
- }
- spin_unlock(&xfs_mount_list_lock);
- return 0;
-}
-
-static int __init
-xfs_cpu_hotplug_init(void)
-{
- int error;
-
- error = cpuhp_setup_state_nocalls(CPUHP_XFS_DEAD, "xfs:dead", NULL,
- xfs_cpu_dead);
- if (error < 0)
- xfs_alert(NULL,
-"Failed to initialise CPU hotplug, error %d. XFS is non-functional.",
- error);
- return error;
-}
-
-static void
-xfs_cpu_hotplug_destroy(void)
-{
- cpuhp_remove_state_nocalls(CPUHP_XFS_DEAD);
-}
-
-#else /* !CONFIG_HOTPLUG_CPU */
-static inline int xfs_cpu_hotplug_init(void) { return 0; }
-static inline void xfs_cpu_hotplug_destroy(void) {}
-#endif
-
STATIC int __init
init_xfs_fs(void)
{
@@ -2385,13 +2310,9 @@ init_xfs_fs(void)
xfs_dir_startup();
- error = xfs_cpu_hotplug_init();
- if (error)
- goto out;
-
error = xfs_init_caches();
if (error)
- goto out_destroy_hp;
+ goto out;
error = xfs_init_workqueues();
if (error)
@@ -2475,8 +2396,6 @@ init_xfs_fs(void)
xfs_destroy_workqueues();
out_destroy_caches:
xfs_destroy_caches();
- out_destroy_hp:
- xfs_cpu_hotplug_destroy();
out:
return error;
}
@@ -2500,7 +2419,6 @@ exit_xfs_fs(void)
xfs_destroy_workqueues();
xfs_destroy_caches();
xfs_uuid_table_free();
- xfs_cpu_hotplug_destroy();
}
module_init(init_xfs_fs);
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 902c7f67a117..3926cf7f2a6e 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -3824,6 +3824,51 @@ TRACE_EVENT(xfs_iunlink_update_dinode,
__entry->new_ptr)
);
+TRACE_EVENT(xfs_iunlink_reload_next,
+ TP_PROTO(struct xfs_inode *ip),
+ TP_ARGS(ip),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_agnumber_t, agno)
+ __field(xfs_agino_t, agino)
+ __field(xfs_agino_t, prev_agino)
+ __field(xfs_agino_t, next_agino)
+ ),
+ TP_fast_assign(
+ __entry->dev = ip->i_mount->m_super->s_dev;
+ __entry->agno = XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino);
+ __entry->agino = XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino);
+ __entry->prev_agino = ip->i_prev_unlinked;
+ __entry->next_agino = ip->i_next_unlinked;
+ ),
+ TP_printk("dev %d:%d agno 0x%x agino 0x%x prev_unlinked 0x%x next_unlinked 0x%x",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->agno,
+ __entry->agino,
+ __entry->prev_agino,
+ __entry->next_agino)
+);
+
+TRACE_EVENT(xfs_inode_reload_unlinked_bucket,
+ TP_PROTO(struct xfs_inode *ip),
+ TP_ARGS(ip),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_agnumber_t, agno)
+ __field(xfs_agino_t, agino)
+ ),
+ TP_fast_assign(
+ __entry->dev = ip->i_mount->m_super->s_dev;
+ __entry->agno = XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino);
+ __entry->agino = XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino);
+ ),
+ TP_printk("dev %d:%d agno 0x%x agino 0x%x bucket %u",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->agno,
+ __entry->agino,
+ __entry->agino % XFS_AGI_UNLINKED_BUCKETS)
+);
+
DECLARE_EVENT_CLASS(xfs_ag_inode_class,
TP_PROTO(struct xfs_inode *ip),
TP_ARGS(ip),
diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c
index 43e5c219aaed..a3975f325f4e 100644
--- a/fs/xfs/xfs_xattr.c
+++ b/fs/xfs/xfs_xattr.c
@@ -46,6 +46,17 @@ xfs_attr_grab_log_assist(
if (xfs_sb_version_haslogxattrs(&mp->m_sb))
return 0;
+ /*
+ * Check if the filesystem featureset is new enough to set this log
+ * incompat feature bit. Strictly speaking, the minimum requirement is
+ * a V5 filesystem for the superblock field, but we'll require rmap
+ * or reflink to avoid having to deal with really old kernels.
+ */
+ if (!xfs_has_reflink(mp) && !xfs_has_rmapbt(mp)) {
+ error = -EOPNOTSUPP;
+ goto drop_incompat;
+ }
+
/* Enable log-assisted xattrs. */
error = xfs_add_incompat_log_feature(mp,
XFS_SB_FEAT_INCOMPAT_LOG_XATTRS);