From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/fs/xfs/xfs_trans.c | 326 +++++++++++++++++++-----------------------------------
1 files changed, 116 insertions(+), 210 deletions(-)
diff --git a/kernel/fs/xfs/xfs_trans.c b/kernel/fs/xfs/xfs_trans.c
index 912b42f..73a1de7 100644
--- a/kernel/fs/xfs/xfs_trans.c
+++ b/kernel/fs/xfs/xfs_trans.c
@@ -9,9 +9,9 @@
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
+#include "xfs_log_priv.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
-#include "xfs_inode.h"
#include "xfs_extent_busy.h"
#include "xfs_quota.h"
#include "xfs_trans.h"
@@ -68,11 +68,11 @@
xfs_extent_busy_clear(tp->t_mountp, &tp->t_busy, false);
trace_xfs_trans_free(tp, _RET_IP_);
- atomic_dec(&tp->t_mountp->m_active_trans);
+ xfs_trans_clear_context(tp);
if (!(tp->t_flags & XFS_TRANS_NO_WRITECOUNT))
sb_end_intwrite(tp->t_mountp->m_super);
xfs_trans_free_dqinfo(tp);
- kmem_zone_free(xfs_trans_zone, tp);
+ kmem_cache_free(xfs_trans_zone, tp);
}
/*
@@ -91,7 +91,7 @@
trace_xfs_trans_dup(tp, _RET_IP_);
- ntp = kmem_zone_zalloc(xfs_trans_zone, KM_SLEEP);
+ ntp = kmem_cache_zalloc(xfs_trans_zone, GFP_KERNEL | __GFP_NOFAIL);
/*
* Initialize the new transaction structure.
@@ -108,7 +108,8 @@
ntp->t_flags = XFS_TRANS_PERM_LOG_RES |
(tp->t_flags & XFS_TRANS_RESERVE) |
- (tp->t_flags & XFS_TRANS_NO_WRITECOUNT);
+ (tp->t_flags & XFS_TRANS_NO_WRITECOUNT) |
+ (tp->t_flags & XFS_TRANS_RES_FDBLKS);
/* We gave our writer reference to the new transaction */
tp->t_flags |= XFS_TRANS_NO_WRITECOUNT;
ntp->t_ticket = xfs_log_ticket_get(tp->t_ticket);
@@ -119,14 +120,13 @@
ntp->t_rtx_res = tp->t_rtx_res - tp->t_rtx_res_used;
tp->t_rtx_res = tp->t_rtx_res_used;
- ntp->t_pflags = tp->t_pflags;
+
+ xfs_trans_switch_context(tp, ntp);
/* move deferred ops over to the new tp */
xfs_defer_move(ntp, tp);
xfs_trans_dup_dqinfo(tp, ntp);
-
- atomic_inc(&tp->t_mountp->m_active_trans);
return ntp;
}
@@ -151,11 +151,9 @@
uint blocks,
uint rtextents)
{
- int error = 0;
- bool rsvd = (tp->t_flags & XFS_TRANS_RESERVE) != 0;
-
- /* Mark this thread as being in a transaction */
- current_set_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
+ struct xfs_mount *mp = tp->t_mountp;
+ int error = 0;
+ bool rsvd = (tp->t_flags & XFS_TRANS_RESERVE) != 0;
/*
* Attempt to reserve the needed disk blocks by decrementing
@@ -163,11 +161,9 @@
* fail if the count would go below zero.
*/
if (blocks > 0) {
- error = xfs_mod_fdblocks(tp->t_mountp, -((int64_t)blocks), rsvd);
- if (error != 0) {
- current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
+ error = xfs_mod_fdblocks(mp, -((int64_t)blocks), rsvd);
+ if (error != 0)
return -ENOSPC;
- }
tp->t_blk_res += blocks;
}
@@ -192,9 +188,9 @@
if (tp->t_ticket != NULL) {
ASSERT(resp->tr_logflags & XFS_TRANS_PERM_LOG_RES);
- error = xfs_log_regrant(tp->t_mountp, tp->t_ticket);
+ error = xfs_log_regrant(mp, tp->t_ticket);
} else {
- error = xfs_log_reserve(tp->t_mountp,
+ error = xfs_log_reserve(mp,
resp->tr_logres,
resp->tr_logcount,
&tp->t_ticket, XFS_TRANSACTION,
@@ -214,7 +210,7 @@
* fail if the count would go below zero.
*/
if (rtextents > 0) {
- error = xfs_mod_frextents(tp->t_mountp, -((int64_t)rtextents));
+ error = xfs_mod_frextents(mp, -((int64_t)rtextents));
if (error) {
error = -ENOSPC;
goto undo_log;
@@ -230,7 +226,7 @@
*/
undo_log:
if (resp->tr_logres > 0) {
- xfs_log_done(tp->t_mountp, tp->t_ticket, NULL, false);
+ xfs_log_ticket_ungrant(mp->m_log, tp->t_ticket);
tp->t_ticket = NULL;
tp->t_log_res = 0;
tp->t_flags &= ~XFS_TRANS_PERM_LOG_RES;
@@ -238,12 +234,9 @@
undo_blocks:
if (blocks > 0) {
- xfs_mod_fdblocks(tp->t_mountp, (int64_t)blocks, rsvd);
+ xfs_mod_fdblocks(mp, (int64_t)blocks, rsvd);
tp->t_blk_res = 0;
}
-
- current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
-
return error;
}
@@ -264,11 +257,10 @@
* GFP_NOFS allocation context so that we avoid lockdep false positives
* by doing GFP_KERNEL allocations inside sb_start_intwrite().
*/
- tp = kmem_zone_zalloc(xfs_trans_zone,
- (flags & XFS_TRANS_NOFS) ? KM_NOFS : KM_SLEEP);
-
+ tp = kmem_cache_zalloc(xfs_trans_zone, GFP_KERNEL | __GFP_NOFAIL);
if (!(flags & XFS_TRANS_NO_WRITECOUNT))
sb_start_intwrite(mp->m_super);
+ xfs_trans_set_context(tp);
/*
* Zero-reservation ("empty") transactions can't modify anything, so
@@ -276,7 +268,8 @@
*/
WARN_ON(resp->tr_logres > 0 &&
mp->m_super->s_writers.frozen == SB_FREEZE_COMPLETE);
- atomic_inc(&mp->m_active_trans);
+ ASSERT(!(flags & XFS_TRANS_RES_FDBLKS) ||
+ xfs_sb_version_haslazysbcount(&mp->m_sb));
tp->t_magic = XFS_TRANS_HEADER_MAGIC;
tp->t_flags = flags;
@@ -300,15 +293,19 @@
/*
* Create an empty transaction with no reservation. This is a defensive
- * mechanism for routines that query metadata without actually modifying
- * them -- if the metadata being queried is somehow cross-linked (think a
- * btree block pointer that points higher in the tree), we risk deadlock.
- * However, blocks grabbed as part of a transaction can be re-grabbed.
- * The verifiers will notice the corrupt block and the operation will fail
- * back to userspace without deadlocking.
+ * mechanism for routines that query metadata without actually modifying them --
+ * if the metadata being queried is somehow cross-linked (think a btree block
+ * pointer that points higher in the tree), we risk deadlock. However, blocks
+ * grabbed as part of a transaction can be re-grabbed. The verifiers will
+ * notice the corrupt block and the operation will fail back to userspace
+ * without deadlocking.
*
- * Note the zero-length reservation; this transaction MUST be cancelled
- * without any dirty data.
+ * Note the zero-length reservation; this transaction MUST be cancelled without
+ * any dirty data.
+ *
+ * Callers should obtain freeze protection to avoid a conflict with fs freezing
+ * where we can be grabbing buffers at the same time that freeze is trying to
+ * drain the buffer LRU list.
*/
int
xfs_trans_alloc_empty(
@@ -366,6 +363,20 @@
tp->t_blk_res_used += (uint)-delta;
if (tp->t_blk_res_used > tp->t_blk_res)
xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+ } else if (delta > 0 && (tp->t_flags & XFS_TRANS_RES_FDBLKS)) {
+ int64_t blkres_delta;
+
+ /*
+ * Return freed blocks directly to the reservation
+ * instead of the global pool, being careful not to
+ * overflow the trans counter. This is used to preserve
+ * reservation across chains of transaction rolls that
+ * repeatedly free and allocate blocks.
+ */
+ blkres_delta = min_t(int64_t, delta,
+ UINT_MAX - tp->t_blk_res);
+ tp->t_blk_res += blkres_delta;
+ delta -= blkres_delta;
}
tp->t_fdblocks_delta += delta;
if (xfs_sb_version_haslazysbcount(&mp->m_sb))
@@ -452,8 +463,8 @@
xfs_buf_t *bp;
int whole = 0;
- bp = xfs_trans_getsb(tp, tp->t_mountp, 0);
- sbp = XFS_BUF_TO_SBP(bp);
+ bp = xfs_trans_getsb(tp);
+ sbp = bp->b_addr;
/*
* Check that superblock mods match the mods made to AGF counters.
@@ -530,57 +541,9 @@
sizeof(sbp->sb_frextents) - 1);
}
-STATIC int
-xfs_sb_mod8(
- uint8_t *field,
- int8_t delta)
-{
- int8_t counter = *field;
-
- counter += delta;
- if (counter < 0) {
- ASSERT(0);
- return -EINVAL;
- }
- *field = counter;
- return 0;
-}
-
-STATIC int
-xfs_sb_mod32(
- uint32_t *field,
- int32_t delta)
-{
- int32_t counter = *field;
-
- counter += delta;
- if (counter < 0) {
- ASSERT(0);
- return -EINVAL;
- }
- *field = counter;
- return 0;
-}
-
-STATIC int
-xfs_sb_mod64(
- uint64_t *field,
- int64_t delta)
-{
- int64_t counter = *field;
-
- counter += delta;
- if (counter < 0) {
- ASSERT(0);
- return -EINVAL;
- }
- *field = counter;
- return 0;
-}
-
/*
- * xfs_trans_unreserve_and_mod_sb() is called to release unused reservations
- * and apply superblock counter changes to the in-core superblock. The
+ * xfs_trans_unreserve_and_mod_sb() is called to release unused reservations and
+ * apply superblock counter changes to the in-core superblock. The
* t_res_fdblocks_delta and t_res_frextents_delta fields are explicitly NOT
* applied to the in-core superblock. The idea is that that has already been
* done.
@@ -589,7 +552,12 @@
* used block counts are not updated in the on disk superblock. In this case,
* XFS_TRANS_SB_DIRTY will not be set when the transaction is updated but we
* still need to update the incore superblock with the changes.
+ *
+ * Deltas for the inode count are +/-64, hence we use a large batch size of 128
+ * so we don't need to take the counter lock on every update.
*/
+#define XFS_ICOUNT_BATCH 128
+
void
xfs_trans_unreserve_and_mod_sb(
struct xfs_trans *tp)
@@ -625,20 +593,21 @@
/* apply the per-cpu counters */
if (blkdelta) {
error = xfs_mod_fdblocks(mp, blkdelta, rsvd);
- if (error)
- goto out;
+ ASSERT(!error);
}
if (idelta) {
- error = xfs_mod_icount(mp, idelta);
- if (error)
- goto out_undo_fdblocks;
+ percpu_counter_add_batch(&mp->m_icount, idelta,
+ XFS_ICOUNT_BATCH);
+ if (idelta < 0)
+ ASSERT(__percpu_counter_compare(&mp->m_icount, 0,
+ XFS_ICOUNT_BATCH) >= 0);
}
if (ifreedelta) {
- error = xfs_mod_ifree(mp, ifreedelta);
- if (error)
- goto out_undo_icount;
+ percpu_counter_add(&mp->m_ifree, ifreedelta);
+ if (ifreedelta < 0)
+ ASSERT(percpu_counter_compare(&mp->m_ifree, 0) >= 0);
}
if (rtxdelta == 0 && !(tp->t_flags & XFS_TRANS_SB_DIRTY))
@@ -646,95 +615,26 @@
/* apply remaining deltas */
spin_lock(&mp->m_sb_lock);
- if (rtxdelta) {
- error = xfs_sb_mod64(&mp->m_sb.sb_frextents, rtxdelta);
- if (error)
- goto out_undo_ifree;
- }
-
- if (tp->t_dblocks_delta != 0) {
- error = xfs_sb_mod64(&mp->m_sb.sb_dblocks, tp->t_dblocks_delta);
- if (error)
- goto out_undo_frextents;
- }
- if (tp->t_agcount_delta != 0) {
- error = xfs_sb_mod32(&mp->m_sb.sb_agcount, tp->t_agcount_delta);
- if (error)
- goto out_undo_dblocks;
- }
- if (tp->t_imaxpct_delta != 0) {
- error = xfs_sb_mod8(&mp->m_sb.sb_imax_pct, tp->t_imaxpct_delta);
- if (error)
- goto out_undo_agcount;
- }
- if (tp->t_rextsize_delta != 0) {
- error = xfs_sb_mod32(&mp->m_sb.sb_rextsize,
- tp->t_rextsize_delta);
- if (error)
- goto out_undo_imaxpct;
- }
- if (tp->t_rbmblocks_delta != 0) {
- error = xfs_sb_mod32(&mp->m_sb.sb_rbmblocks,
- tp->t_rbmblocks_delta);
- if (error)
- goto out_undo_rextsize;
- }
- if (tp->t_rblocks_delta != 0) {
- error = xfs_sb_mod64(&mp->m_sb.sb_rblocks, tp->t_rblocks_delta);
- if (error)
- goto out_undo_rbmblocks;
- }
- if (tp->t_rextents_delta != 0) {
- error = xfs_sb_mod64(&mp->m_sb.sb_rextents,
- tp->t_rextents_delta);
- if (error)
- goto out_undo_rblocks;
- }
- if (tp->t_rextslog_delta != 0) {
- error = xfs_sb_mod8(&mp->m_sb.sb_rextslog,
- tp->t_rextslog_delta);
- if (error)
- goto out_undo_rextents;
- }
+ mp->m_sb.sb_fdblocks += tp->t_fdblocks_delta + tp->t_res_fdblocks_delta;
+ mp->m_sb.sb_icount += idelta;
+ mp->m_sb.sb_ifree += ifreedelta;
+ mp->m_sb.sb_frextents += rtxdelta;
+ mp->m_sb.sb_dblocks += tp->t_dblocks_delta;
+ mp->m_sb.sb_agcount += tp->t_agcount_delta;
+ mp->m_sb.sb_imax_pct += tp->t_imaxpct_delta;
+ mp->m_sb.sb_rextsize += tp->t_rextsize_delta;
+ mp->m_sb.sb_rbmblocks += tp->t_rbmblocks_delta;
+ mp->m_sb.sb_rblocks += tp->t_rblocks_delta;
+ mp->m_sb.sb_rextents += tp->t_rextents_delta;
+ mp->m_sb.sb_rextslog += tp->t_rextslog_delta;
spin_unlock(&mp->m_sb_lock);
- return;
-out_undo_rextents:
- if (tp->t_rextents_delta)
- xfs_sb_mod64(&mp->m_sb.sb_rextents, -tp->t_rextents_delta);
-out_undo_rblocks:
- if (tp->t_rblocks_delta)
- xfs_sb_mod64(&mp->m_sb.sb_rblocks, -tp->t_rblocks_delta);
-out_undo_rbmblocks:
- if (tp->t_rbmblocks_delta)
- xfs_sb_mod32(&mp->m_sb.sb_rbmblocks, -tp->t_rbmblocks_delta);
-out_undo_rextsize:
- if (tp->t_rextsize_delta)
- xfs_sb_mod32(&mp->m_sb.sb_rextsize, -tp->t_rextsize_delta);
-out_undo_imaxpct:
- if (tp->t_rextsize_delta)
- xfs_sb_mod8(&mp->m_sb.sb_imax_pct, -tp->t_imaxpct_delta);
-out_undo_agcount:
- if (tp->t_agcount_delta)
- xfs_sb_mod32(&mp->m_sb.sb_agcount, -tp->t_agcount_delta);
-out_undo_dblocks:
- if (tp->t_dblocks_delta)
- xfs_sb_mod64(&mp->m_sb.sb_dblocks, -tp->t_dblocks_delta);
-out_undo_frextents:
- if (rtxdelta)
- xfs_sb_mod64(&mp->m_sb.sb_frextents, -rtxdelta);
-out_undo_ifree:
- spin_unlock(&mp->m_sb_lock);
- if (ifreedelta)
- xfs_mod_ifree(mp, -ifreedelta);
-out_undo_icount:
- if (idelta)
- xfs_mod_icount(mp, -idelta);
-out_undo_fdblocks:
- if (blkdelta)
- xfs_mod_fdblocks(mp, -blkdelta, rsvd);
-out:
- ASSERT(error == 0);
+ /*
+ * Debug checks outside of the spinlock so they don't lock up the
+ * machine if they fail.
+ */
+ ASSERT(mp->m_sb.sb_imax_pct >= 0);
+ ASSERT(mp->m_sb.sb_rextslog >= 0);
return;
}
@@ -767,10 +667,9 @@
}
/* Detach and unlock all of the items in a transaction */
-void
+static void
xfs_trans_free_items(
struct xfs_trans *tp,
- xfs_lsn_t commit_lsn,
bool abort)
{
struct xfs_log_item *lip, *next;
@@ -779,11 +678,10 @@
list_for_each_entry_safe(lip, next, &tp->t_items, li_trans) {
xfs_trans_del_item(lip);
- if (commit_lsn != NULLCOMMITLSN)
- lip->li_ops->iop_committing(lip, commit_lsn);
if (abort)
set_bit(XFS_LI_ABORTED, &lip->li_flags);
- lip->li_ops->iop_unlock(lip);
+ if (lip->li_ops->iop_release)
+ lip->li_ops->iop_release(lip);
}
}
@@ -804,7 +702,8 @@
for (i = 0; i < nr_items; i++) {
struct xfs_log_item *lip = log_items[i];
- lip->li_ops->iop_unpin(lip, 0);
+ if (lip->li_ops->iop_unpin)
+ lip->li_ops->iop_unpin(lip, 0);
}
}
@@ -815,7 +714,7 @@
*
* If we are called with the aborted flag set, it is because a log write during
* a CIL checkpoint commit has failed. In this case, all the items in the
- * checkpoint have already gone through iop_commited and iop_unlock, which
+ * checkpoint have already gone through iop_committed and iop_committing, which
* means that checkpoint commit abort handling is treated exactly the same
* as an iclog write error even though we haven't started any IO yet. Hence in
* this case all we need to do is iop_committed processing, followed by an
@@ -833,7 +732,7 @@
struct xfs_ail *ailp,
struct xfs_log_vec *log_vector,
xfs_lsn_t commit_lsn,
- int aborted)
+ bool aborted)
{
#define LOG_ITEM_BATCH_SIZE 32
struct xfs_log_item *log_items[LOG_ITEM_BATCH_SIZE];
@@ -852,7 +751,16 @@
if (aborted)
set_bit(XFS_LI_ABORTED, &lip->li_flags);
- item_lsn = lip->li_ops->iop_committed(lip, commit_lsn);
+
+ if (lip->li_ops->flags & XFS_ITEM_RELEASE_WHEN_COMMITTED) {
+ lip->li_ops->iop_release(lip);
+ continue;
+ }
+
+ if (lip->li_ops->iop_committed)
+ item_lsn = lip->li_ops->iop_committed(lip, commit_lsn);
+ else
+ item_lsn = commit_lsn;
/* item_lsn of -1 means the item needs no further processing */
if (XFS_LSN_CMP(item_lsn, (xfs_lsn_t)-1) == 0)
@@ -864,7 +772,8 @@
*/
if (aborted) {
ASSERT(XFS_FORCED_SHUTDOWN(ailp->ail_mount));
- lip->li_ops->iop_unpin(lip, 1);
+ if (lip->li_ops->iop_unpin)
+ lip->li_ops->iop_unpin(lip, 1);
continue;
}
@@ -882,7 +791,8 @@
xfs_trans_ail_update(ailp, lip, item_lsn);
else
spin_unlock(&ailp->ail_lock);
- lip->li_ops->iop_unpin(lip, 0);
+ if (lip->li_ops->iop_unpin)
+ lip->li_ops->iop_unpin(lip, 0);
continue;
}
@@ -922,7 +832,7 @@
bool regrant)
{
struct xfs_mount *mp = tp->t_mountp;
- xfs_lsn_t commit_lsn = -1;
+ xfs_csn_t commit_seq = 0;
int error = 0;
int sync = tp->t_flags & XFS_TRANS_SYNC;
@@ -964,9 +874,8 @@
xfs_trans_apply_sb_deltas(tp);
xfs_trans_apply_dquot_deltas(tp);
- xfs_log_commit_cil(mp, tp, &commit_lsn, regrant);
+ xlog_cil_commit(mp->m_log, tp, &commit_seq, regrant);
- current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
xfs_trans_free(tp);
/*
@@ -974,7 +883,7 @@
* log out now and wait for it.
*/
if (sync) {
- error = xfs_log_force_lsn(mp, commit_lsn, XFS_LOG_SYNC, NULL);
+ error = xfs_log_force_seq(mp, commit_seq, XFS_LOG_SYNC, NULL);
XFS_STATS_INC(mp, xs_trans_sync);
} else {
XFS_STATS_INC(mp, xs_trans_async);
@@ -992,13 +901,13 @@
*/
xfs_trans_unreserve_and_mod_dquots(tp);
if (tp->t_ticket) {
- commit_lsn = xfs_log_done(mp, tp->t_ticket, NULL, regrant);
- if (commit_lsn == -1 && !error)
- error = -EIO;
+ if (regrant && !XLOG_FORCED_SHUTDOWN(mp->m_log))
+ xfs_log_ticket_regrant(mp->m_log, tp->t_ticket);
+ else
+ xfs_log_ticket_ungrant(mp->m_log, tp->t_ticket);
tp->t_ticket = NULL;
}
- current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
- xfs_trans_free_items(tp, NULLCOMMITLSN, !!error);
+ xfs_trans_free_items(tp, !!error);
xfs_trans_free(tp);
XFS_STATS_INC(mp, xs_trans_empty);
@@ -1046,21 +955,18 @@
struct xfs_log_item *lip;
list_for_each_entry(lip, &tp->t_items, li_trans)
- ASSERT(!(lip->li_type == XFS_LI_EFD));
+ ASSERT(!xlog_item_is_intent_done(lip));
}
#endif
xfs_trans_unreserve_and_mod_sb(tp);
xfs_trans_unreserve_and_mod_dquots(tp);
if (tp->t_ticket) {
- xfs_log_done(mp, tp->t_ticket, NULL, false);
+ xfs_log_ticket_ungrant(mp->m_log, tp->t_ticket);
tp->t_ticket = NULL;
}
- /* mark this thread as no longer being in a transaction */
- current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
-
- xfs_trans_free_items(tp, NULLCOMMITLSN, dirty);
+ xfs_trans_free_items(tp, dirty);
xfs_trans_free(tp);
}
--
Gitblit v1.6.2