From 95099d4622f8cb224d94e314c7a8e0df60b13f87 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Sat, 09 Dec 2023 08:38:01 +0000
Subject: [PATCH] enable docker ppp
---
kernel/fs/gfs2/log.c | 498 +++++++++++++++++++++++++++++++++++++++---------------
1 files changed, 355 insertions(+), 143 deletions(-)
diff --git a/kernel/fs/gfs2/log.c b/kernel/fs/gfs2/log.c
index 74c1fe9..1955dea 100644
--- a/kernel/fs/gfs2/log.c
+++ b/kernel/fs/gfs2/log.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
* Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved.
- *
- * This copyrighted material is made available to anyone wishing to use,
- * modify, copy, or redistribute it subject to the terms and conditions
- * of the GNU General Public License version 2.
*/
#include <linux/sched.h>
@@ -33,12 +30,14 @@
#include "util.h"
#include "dir.h"
#include "trace_gfs2.h"
+#include "trans.h"
+
+static void gfs2_log_shutdown(struct gfs2_sbd *sdp);
/**
* gfs2_struct2blk - compute stuff
* @sdp: the filesystem
* @nstruct: the number of structures
- * @ssize: the size of the structures
*
* Compute the number of log descriptor blocks needed to hold a certain number
* of structures of a certain size.
@@ -46,18 +45,16 @@
* Returns: the number of blocks needed (minimum is always 1)
*/
-unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
- unsigned int ssize)
+unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct)
{
unsigned int blks;
unsigned int first, second;
blks = 1;
- first = (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_log_descriptor)) / ssize;
+ first = sdp->sd_ldptrs;
if (nstruct > first) {
- second = (sdp->sd_sb.sb_bsize -
- sizeof(struct gfs2_meta_header)) / ssize;
+ second = sdp->sd_inptrs;
blks += DIV_ROUND_UP(nstruct - first, second);
}
@@ -73,7 +70,7 @@
*
*/
-static void gfs2_remove_from_ail(struct gfs2_bufdata *bd)
+void gfs2_remove_from_ail(struct gfs2_bufdata *bd)
{
bd->bd_tr = NULL;
list_del_init(&bd->bd_ail_st_list);
@@ -92,8 +89,7 @@
static int gfs2_ail1_start_one(struct gfs2_sbd *sdp,
struct writeback_control *wbc,
- struct gfs2_trans *tr,
- bool *withdraw)
+ struct gfs2_trans *tr)
__releases(&sdp->sd_ail_lock)
__acquires(&sdp->sd_ail_lock)
{
@@ -101,6 +97,7 @@
struct address_space *mapping;
struct gfs2_bufdata *bd, *s;
struct buffer_head *bh;
+ int ret = 0;
list_for_each_entry_safe_reverse(bd, s, &tr->tr_ail1_list, bd_ail_st_list) {
bh = bd->bd_bh;
@@ -108,16 +105,21 @@
gfs2_assert(sdp, bd->bd_tr == tr);
if (!buffer_busy(bh)) {
- if (!buffer_uptodate(bh) &&
- !test_and_set_bit(SDF_AIL1_IO_ERROR,
- &sdp->sd_flags)) {
- gfs2_io_error_bh(sdp, bh);
- *withdraw = true;
+ if (buffer_uptodate(bh)) {
+ list_move(&bd->bd_ail_st_list,
+ &tr->tr_ail2_list);
+ continue;
}
- list_move(&bd->bd_ail_st_list, &tr->tr_ail2_list);
- continue;
+ if (!cmpxchg(&sdp->sd_log_error, 0, -EIO)) {
+ gfs2_io_error_bh(sdp, bh);
+ gfs2_withdraw_delayed(sdp);
+ }
}
+ if (gfs2_withdrawn(sdp)) {
+ gfs2_remove_from_ail(bd);
+ continue;
+ }
if (!buffer_dirty(bh))
continue;
if (gl == bd->bd_gl)
@@ -128,16 +130,49 @@
if (!mapping)
continue;
spin_unlock(&sdp->sd_ail_lock);
- generic_writepages(mapping, wbc);
+ ret = generic_writepages(mapping, wbc);
spin_lock(&sdp->sd_ail_lock);
- if (wbc->nr_to_write <= 0)
+ if (ret == -ENODATA) /* if a jdata write into a new hole */
+ ret = 0; /* ignore it */
+ if (ret || wbc->nr_to_write <= 0)
break;
- return 1;
+ return -EBUSY;
}
- return 0;
+ return ret;
}
+static void dump_ail_list(struct gfs2_sbd *sdp)
+{
+ struct gfs2_trans *tr;
+ struct gfs2_bufdata *bd;
+ struct buffer_head *bh;
+
+ list_for_each_entry_reverse(tr, &sdp->sd_ail1_list, tr_list) {
+ list_for_each_entry_reverse(bd, &tr->tr_ail1_list,
+ bd_ail_st_list) {
+ bh = bd->bd_bh;
+ fs_err(sdp, "bd %p: blk:0x%llx bh=%p ", bd,
+ (unsigned long long)bd->bd_blkno, bh);
+ if (!bh) {
+ fs_err(sdp, "\n");
+ continue;
+ }
+ fs_err(sdp, "0x%llx up2:%d dirt:%d lkd:%d req:%d "
+ "map:%d new:%d ar:%d aw:%d delay:%d "
+ "io err:%d unwritten:%d dfr:%d pin:%d esc:%d\n",
+ (unsigned long long)bh->b_blocknr,
+ buffer_uptodate(bh), buffer_dirty(bh),
+ buffer_locked(bh), buffer_req(bh),
+ buffer_mapped(bh), buffer_new(bh),
+ buffer_async_read(bh), buffer_async_write(bh),
+ buffer_delay(bh), buffer_write_io_error(bh),
+ buffer_unwritten(bh),
+ buffer_defer_completion(bh),
+ buffer_pinned(bh), buffer_escaped(bh));
+ }
+ }
+}
/**
* gfs2_ail1_flush - start writeback of some ail1 entries
@@ -153,22 +188,38 @@
struct list_head *head = &sdp->sd_ail1_list;
struct gfs2_trans *tr;
struct blk_plug plug;
- bool withdraw = false;
+ int ret;
+ unsigned long flush_start = jiffies;
trace_gfs2_ail_flush(sdp, wbc, 1);
blk_start_plug(&plug);
spin_lock(&sdp->sd_ail_lock);
restart:
+ ret = 0;
+ if (time_after(jiffies, flush_start + (HZ * 600))) {
+ fs_err(sdp, "Error: In %s for ten minutes! t=%d\n",
+ __func__, current->journal_info ? 1 : 0);
+ dump_ail_list(sdp);
+ goto out;
+ }
list_for_each_entry_reverse(tr, head, tr_list) {
if (wbc->nr_to_write <= 0)
break;
- if (gfs2_ail1_start_one(sdp, wbc, tr, &withdraw))
- goto restart;
+ ret = gfs2_ail1_start_one(sdp, wbc, tr);
+ if (ret) {
+ if (ret == -EBUSY)
+ goto restart;
+ break;
+ }
}
+out:
spin_unlock(&sdp->sd_ail_lock);
blk_finish_plug(&plug);
- if (withdraw)
- gfs2_lm_withdraw(sdp, NULL);
+ if (ret) {
+ gfs2_lm(sdp, "gfs2_ail1_start_one (generic_writepages) "
+ "returned: %d\n", ret);
+ gfs2_withdraw(sdp);
+ }
trace_gfs2_ail_flush(sdp, wbc, 0);
}
@@ -192,49 +243,74 @@
/**
* gfs2_ail1_empty_one - Check whether or not a trans in the AIL has been synced
* @sdp: the filesystem
- * @ai: the AIL entry
+ * @tr: the transaction
+ * @max_revokes: If nonzero, issue revokes for the bd items for written buffers
*
+ * returns: the transaction's count of remaining active items
*/
-static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr,
- bool *withdraw)
+static int gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr,
+ int *max_revokes)
{
struct gfs2_bufdata *bd, *s;
struct buffer_head *bh;
+ int active_count = 0;
list_for_each_entry_safe_reverse(bd, s, &tr->tr_ail1_list,
bd_ail_st_list) {
bh = bd->bd_bh;
gfs2_assert(sdp, bd->bd_tr == tr);
- if (buffer_busy(bh))
+ /*
+ * If another process flagged an io error, e.g. writing to the
+ * journal, error all other bhs and move them off the ail1 to
+ * prevent a tight loop when unmount tries to flush ail1,
+ * regardless of whether they're still busy. If no outside
+ * errors were found and the buffer is busy, move to the next.
+ * If the ail buffer is not busy and caught an error, flag it
+ * for others.
+ */
+ if (!sdp->sd_log_error && buffer_busy(bh)) {
+ active_count++;
continue;
+ }
if (!buffer_uptodate(bh) &&
- !test_and_set_bit(SDF_AIL1_IO_ERROR, &sdp->sd_flags)) {
+ !cmpxchg(&sdp->sd_log_error, 0, -EIO)) {
gfs2_io_error_bh(sdp, bh);
- *withdraw = true;
+ gfs2_withdraw_delayed(sdp);
+ }
+ /*
+ * If we have space for revokes and the bd is no longer on any
+ * buf list, we can just add a revoke for it immediately and
+ * avoid having to put it on the ail2 list, where it would need
+ * to be revoked later.
+ */
+ if (*max_revokes && list_empty(&bd->bd_list)) {
+ gfs2_add_revoke(sdp, bd);
+ (*max_revokes)--;
+ continue;
}
list_move(&bd->bd_ail_st_list, &tr->tr_ail2_list);
}
+ return active_count;
}
/**
* gfs2_ail1_empty - Try to empty the ail1 lists
* @sdp: The superblock
+ * @max_revokes: If non-zero, add revokes where appropriate
*
* Tries to empty the ail1 lists, starting with the oldest first
*/
-static int gfs2_ail1_empty(struct gfs2_sbd *sdp)
+static int gfs2_ail1_empty(struct gfs2_sbd *sdp, int max_revokes)
{
struct gfs2_trans *tr, *s;
int oldest_tr = 1;
int ret;
- bool withdraw = false;
spin_lock(&sdp->sd_ail_lock);
list_for_each_entry_safe_reverse(tr, s, &sdp->sd_ail1_list, tr_list) {
- gfs2_ail1_empty_one(sdp, tr, &withdraw);
- if (list_empty(&tr->tr_ail1_list) && oldest_tr)
+ if (!gfs2_ail1_empty_one(sdp, tr, &max_revokes) && oldest_tr)
list_move(&tr->tr_list, &sdp->sd_ail2_list);
else
oldest_tr = 0;
@@ -242,8 +318,10 @@
ret = list_empty(&sdp->sd_ail1_list);
spin_unlock(&sdp->sd_ail_lock);
- if (withdraw)
- gfs2_lm_withdraw(sdp, "fatal: I/O error(s)\n");
+ if (test_bit(SDF_WITHDRAWING, &sdp->sd_flags)) {
+ gfs2_lm(sdp, "fatal: I/O error(s)\n");
+ gfs2_withdraw(sdp);
+ }
return ret;
}
@@ -271,20 +349,17 @@
}
/**
- * gfs2_ail2_empty_one - Check whether or not a trans in the AIL has been synced
- * @sdp: the filesystem
- * @ai: the AIL entry
- *
+ * gfs2_ail_empty_tr - empty one of the ail lists for a transaction
*/
-static void gfs2_ail2_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
+static void gfs2_ail_empty_tr(struct gfs2_sbd *sdp, struct gfs2_trans *tr,
+ struct list_head *head)
{
- struct list_head *head = &tr->tr_ail2_list;
struct gfs2_bufdata *bd;
while (!list_empty(head)) {
- bd = list_entry(head->prev, struct gfs2_bufdata,
- bd_ail_st_list);
+ bd = list_first_entry(head, struct gfs2_bufdata,
+ bd_ail_st_list);
gfs2_assert(sdp, bd->bd_tr == tr);
gfs2_remove_from_ail(bd);
}
@@ -306,11 +381,11 @@
if (!rm)
continue;
- gfs2_ail2_empty_one(sdp, tr);
+ gfs2_ail_empty_tr(sdp, tr, &tr->tr_ail2_list);
list_del(&tr->tr_list);
gfs2_assert_warn(sdp, list_empty(&tr->tr_ail1_list));
gfs2_assert_warn(sdp, list_empty(&tr->tr_ail2_list));
- kfree(tr);
+ gfs2_trans_free(sdp, tr);
}
spin_unlock(&sdp->sd_ail_lock);
@@ -472,9 +547,8 @@
reserved += DIV_ROUND_UP(dbuf, databuf_limit(sdp));
}
- if (sdp->sd_log_commited_revoke > 0)
- reserved += gfs2_struct2blk(sdp, sdp->sd_log_commited_revoke,
- sizeof(u64));
+ if (sdp->sd_log_committed_revoke > 0)
+ reserved += gfs2_struct2blk(sdp, sdp->sd_log_committed_revoke);
/* One for the overall header */
if (reserved)
reserved++;
@@ -491,7 +565,7 @@
if (list_empty(&sdp->sd_ail1_list)) {
tail = sdp->sd_log_head;
} else {
- tr = list_entry(sdp->sd_ail1_list.prev, struct gfs2_trans,
+ tr = list_last_entry(&sdp->sd_ail1_list, struct gfs2_trans,
tr_list);
tail = tr->tr_first;
}
@@ -516,7 +590,7 @@
}
-static void log_flush_wait(struct gfs2_sbd *sdp)
+void log_flush_wait(struct gfs2_sbd *sdp)
{
DEFINE_WAIT(wait);
@@ -545,18 +619,23 @@
return 0;
}
+static void __ordered_del_inode(struct gfs2_inode *ip)
+{
+ if (!list_empty(&ip->i_ordered))
+ list_del_init(&ip->i_ordered);
+}
+
static void gfs2_ordered_write(struct gfs2_sbd *sdp)
{
struct gfs2_inode *ip;
LIST_HEAD(written);
spin_lock(&sdp->sd_ordered_lock);
- list_sort(NULL, &sdp->sd_log_le_ordered, &ip_cmp);
- while (!list_empty(&sdp->sd_log_le_ordered)) {
- ip = list_entry(sdp->sd_log_le_ordered.next, struct gfs2_inode, i_ordered);
+ list_sort(NULL, &sdp->sd_log_ordered, &ip_cmp);
+ while (!list_empty(&sdp->sd_log_ordered)) {
+ ip = list_first_entry(&sdp->sd_log_ordered, struct gfs2_inode, i_ordered);
if (ip->i_inode.i_mapping->nrpages == 0) {
- test_and_clear_bit(GIF_ORDERED, &ip->i_flags);
- list_del(&ip->i_ordered);
+ __ordered_del_inode(ip);
continue;
}
list_move(&ip->i_ordered, &written);
@@ -564,7 +643,7 @@
filemap_fdatawrite(ip->i_inode.i_mapping);
spin_lock(&sdp->sd_ordered_lock);
}
- list_splice(&written, &sdp->sd_log_le_ordered);
+ list_splice(&written, &sdp->sd_log_ordered);
spin_unlock(&sdp->sd_ordered_lock);
}
@@ -573,10 +652,9 @@
struct gfs2_inode *ip;
spin_lock(&sdp->sd_ordered_lock);
- while (!list_empty(&sdp->sd_log_le_ordered)) {
- ip = list_entry(sdp->sd_log_le_ordered.next, struct gfs2_inode, i_ordered);
- list_del(&ip->i_ordered);
- WARN_ON(!test_and_clear_bit(GIF_ORDERED, &ip->i_flags));
+ while (!list_empty(&sdp->sd_log_ordered)) {
+ ip = list_first_entry(&sdp->sd_log_ordered, struct gfs2_inode, i_ordered);
+ __ordered_del_inode(ip);
if (ip->i_inode.i_mapping->nrpages == 0)
continue;
spin_unlock(&sdp->sd_ordered_lock);
@@ -591,8 +669,7 @@
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
spin_lock(&sdp->sd_ordered_lock);
- if (test_and_clear_bit(GIF_ORDERED, &ip->i_flags))
- list_del(&ip->i_ordered);
+ __ordered_del_inode(ip);
spin_unlock(&sdp->sd_ordered_lock);
}
@@ -601,16 +678,15 @@
struct buffer_head *bh = bd->bd_bh;
struct gfs2_glock *gl = bd->bd_gl;
+ sdp->sd_log_num_revoke++;
+ if (atomic_inc_return(&gl->gl_revokes) == 1)
+ gfs2_glock_hold(gl);
bh->b_private = NULL;
bd->bd_blkno = bh->b_blocknr;
gfs2_remove_from_ail(bd); /* drops ref on bh */
bd->bd_bh = NULL;
- bd->bd_ops = &gfs2_revoke_lops;
- sdp->sd_log_num_revoke++;
- if (atomic_inc_return(&gl->gl_revokes) == 1)
- gfs2_glock_hold(gl);
set_bit(GLF_LFLUSH, &gl->gl_flags);
- list_add(&bd->bd_list, &sdp->sd_log_le_revoke);
+ list_add(&bd->bd_list, &sdp->sd_log_revokes);
}
void gfs2_glock_remove_revoke(struct gfs2_glock *gl)
@@ -621,27 +697,24 @@
}
}
+/**
+ * gfs2_write_revokes - Add as many revokes to the system transaction as we can
+ * @sdp: The GFS2 superblock
+ *
+ * Our usual strategy is to defer writing revokes as much as we can in the hope
+ * that we'll eventually overwrite the journal, which will make those revokes
+ * go away. This changes when we flush the log: at that point, there will
+ * likely be some left-over space in the last revoke block of that transaction.
+ * We can fill that space with additional revokes for blocks that have already
+ * been written back. This will basically come at no cost now, and will save
+ * us from having to keep track of those blocks on the AIL2 list later.
+ */
void gfs2_write_revokes(struct gfs2_sbd *sdp)
{
- struct gfs2_trans *tr;
- struct gfs2_bufdata *bd, *tmp;
- int have_revokes = 0;
+ /* number of revokes we still have room for */
int max_revokes = (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_log_descriptor)) / sizeof(u64);
- gfs2_ail1_empty(sdp);
- spin_lock(&sdp->sd_ail_lock);
- list_for_each_entry(tr, &sdp->sd_ail1_list, tr_list) {
- list_for_each_entry(bd, &tr->tr_ail2_list, bd_ail_st_list) {
- if (list_empty(&bd->bd_list)) {
- have_revokes = 1;
- goto done;
- }
- }
- }
-done:
- spin_unlock(&sdp->sd_ail_lock);
- if (have_revokes == 0)
- return;
+ gfs2_log_lock(sdp);
while (sdp->sd_log_num_revoke > max_revokes)
max_revokes += (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_meta_header)) / sizeof(u64);
max_revokes -= sdp->sd_log_num_revoke;
@@ -649,38 +722,34 @@
atomic_dec(&sdp->sd_log_blks_free);
/* If no blocks have been reserved, we need to also
* reserve a block for the header */
- if (!sdp->sd_log_blks_reserved)
+ if (!sdp->sd_log_blks_reserved) {
atomic_dec(&sdp->sd_log_blks_free);
- }
- gfs2_log_lock(sdp);
- spin_lock(&sdp->sd_ail_lock);
- list_for_each_entry(tr, &sdp->sd_ail1_list, tr_list) {
- list_for_each_entry_safe(bd, tmp, &tr->tr_ail2_list, bd_ail_st_list) {
- if (max_revokes == 0)
- goto out_of_blocks;
- if (!list_empty(&bd->bd_list))
- continue;
- gfs2_add_revoke(sdp, bd);
- max_revokes--;
+ trace_gfs2_log_blocks(sdp, -2);
+ } else {
+ trace_gfs2_log_blocks(sdp, -1);
}
}
-out_of_blocks:
- spin_unlock(&sdp->sd_ail_lock);
+ gfs2_ail1_empty(sdp, max_revokes);
gfs2_log_unlock(sdp);
if (!sdp->sd_log_num_revoke) {
atomic_inc(&sdp->sd_log_blks_free);
- if (!sdp->sd_log_blks_reserved)
+ if (!sdp->sd_log_blks_reserved) {
atomic_inc(&sdp->sd_log_blks_free);
+ trace_gfs2_log_blocks(sdp, 2);
+ } else {
+ trace_gfs2_log_blocks(sdp, 1);
+ }
}
}
/**
- * write_log_header - Write a journal log header buffer at sd_log_flush_head
+ * gfs2_write_log_header - Write a journal log header buffer at lblock
* @sdp: The GFS2 superblock
* @jd: journal descriptor of the journal to which we are writing
* @seq: sequence number
* @tail: tail of the log
+ * @lblock: value for lh_blkno (block number relative to start of journal)
* @flags: log header flags GFS2_LOG_HEAD_*
* @op_flags: flags to pass to the bio
*
@@ -688,16 +757,21 @@
*/
void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
- u64 seq, u32 tail, u32 flags, int op_flags)
+ u64 seq, u32 tail, u32 lblock, u32 flags,
+ int op_flags)
{
struct gfs2_log_header *lh;
u32 hash, crc;
- struct page *page = mempool_alloc(gfs2_page_pool, GFP_NOIO);
+ struct page *page;
struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
struct timespec64 tv;
struct super_block *sb = sdp->sd_vfs;
- u64 addr;
+ u64 dblock;
+ if (gfs2_withdrawn(sdp))
+ goto out;
+
+ page = mempool_alloc(gfs2_page_pool, GFP_NOIO);
lh = page_address(page);
clear_page(lh);
@@ -709,15 +783,21 @@
lh->lh_sequence = cpu_to_be64(seq);
lh->lh_flags = cpu_to_be32(flags);
lh->lh_tail = cpu_to_be32(tail);
- lh->lh_blkno = cpu_to_be32(sdp->sd_log_flush_head);
+ lh->lh_blkno = cpu_to_be32(lblock);
hash = ~crc32(~0, lh, LH_V1_SIZE);
lh->lh_hash = cpu_to_be32(hash);
ktime_get_coarse_real_ts64(&tv);
lh->lh_nsec = cpu_to_be32(tv.tv_nsec);
lh->lh_sec = cpu_to_be64(tv.tv_sec);
- addr = gfs2_log_bmap(sdp);
- lh->lh_addr = cpu_to_be64(addr);
+ if (!list_empty(&jd->extent_list))
+ dblock = gfs2_log_bmap(jd, lblock);
+ else {
+ int ret = gfs2_lblk_to_dblk(jd->jd_inode, lblock, &dblock);
+ if (gfs2_assert_withdraw(sdp, ret == 0))
+ return;
+ }
+ lh->lh_addr = cpu_to_be64(dblock);
lh->lh_jinode = cpu_to_be64(GFS2_I(jd->jd_inode)->i_no_addr);
/* We may only write local statfs, quota, etc., when writing to our
@@ -742,8 +822,9 @@
sb->s_blocksize - LH_V1_SIZE - 4);
lh->lh_crc = cpu_to_be32(crc);
- gfs2_log_write(sdp, page, sb->s_blocksize, 0, addr);
- gfs2_log_flush_bio(sdp, REQ_OP_WRITE, op_flags);
+ gfs2_log_write(sdp, page, sb->s_blocksize, 0, dblock);
+ gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE | op_flags);
+out:
log_flush_wait(sdp);
}
@@ -771,10 +852,101 @@
}
sdp->sd_log_idle = (tail == sdp->sd_log_flush_head);
gfs2_write_log_header(sdp, sdp->sd_jdesc, sdp->sd_log_sequence++, tail,
- flags, op_flags);
+ sdp->sd_log_flush_head, flags, op_flags);
+ gfs2_log_incr_head(sdp);
if (sdp->sd_log_tail != tail)
log_pull_tail(sdp, tail);
+}
+
+/**
+ * ail_drain - drain the ail lists after a withdraw
+ * @sdp: Pointer to GFS2 superblock
+ */
+static void ail_drain(struct gfs2_sbd *sdp)
+{
+ struct gfs2_trans *tr;
+
+ spin_lock(&sdp->sd_ail_lock);
+ /*
+ * For transactions on the sd_ail1_list we need to drain both the
+ * ail1 and ail2 lists. That's because function gfs2_ail1_start_one
+ * (temporarily) moves items from its tr_ail1 list to tr_ail2 list
+ * before revokes are sent for that block. Items on the sd_ail2_list
+ * should have already gotten beyond that point, so no need.
+ */
+ while (!list_empty(&sdp->sd_ail1_list)) {
+ tr = list_first_entry(&sdp->sd_ail1_list, struct gfs2_trans,
+ tr_list);
+ gfs2_ail_empty_tr(sdp, tr, &tr->tr_ail1_list);
+ gfs2_ail_empty_tr(sdp, tr, &tr->tr_ail2_list);
+ list_del(&tr->tr_list);
+ gfs2_trans_free(sdp, tr);
+ }
+ while (!list_empty(&sdp->sd_ail2_list)) {
+ tr = list_first_entry(&sdp->sd_ail2_list, struct gfs2_trans,
+ tr_list);
+ gfs2_ail_empty_tr(sdp, tr, &tr->tr_ail2_list);
+ list_del(&tr->tr_list);
+ gfs2_trans_free(sdp, tr);
+ }
+ spin_unlock(&sdp->sd_ail_lock);
+}
+
+/**
+ * empty_ail1_list - try to start IO and empty the ail1 list
+ * @sdp: Pointer to GFS2 superblock
+ */
+static void empty_ail1_list(struct gfs2_sbd *sdp)
+{
+ unsigned long start = jiffies;
+
+ for (;;) {
+ if (time_after(jiffies, start + (HZ * 600))) {
+ fs_err(sdp, "Error: In %s for 10 minutes! t=%d\n",
+ __func__, current->journal_info ? 1 : 0);
+ dump_ail_list(sdp);
+ return;
+ }
+ gfs2_ail1_start(sdp);
+ gfs2_ail1_wait(sdp);
+ if (gfs2_ail1_empty(sdp, 0))
+ return;
+ }
+}
+
+/**
+ * trans_drain - drain the buf and databuf queue for a failed transaction
+ * @tr: the transaction to drain
+ *
+ * When this is called, we're taking an error exit for a log write that failed
+ * but since we bypassed the after_commit functions, we need to remove the
+ * items from the buf and databuf queue.
+ */
+static void trans_drain(struct gfs2_trans *tr)
+{
+ struct gfs2_bufdata *bd;
+ struct list_head *head;
+
+ if (!tr)
+ return;
+
+ head = &tr->tr_buf;
+ while (!list_empty(head)) {
+ bd = list_first_entry(head, struct gfs2_bufdata, bd_list);
+ list_del_init(&bd->bd_list);
+ if (!list_empty(&bd->bd_ail_st_list))
+ gfs2_remove_from_ail(bd);
+ kmem_cache_free(gfs2_bufdata_cachep, bd);
+ }
+ head = &tr->tr_databuf;
+ while (!list_empty(head)) {
+ bd = list_first_entry(head, struct gfs2_bufdata, bd_list);
+ list_del_init(&bd->bd_list);
+ if (!list_empty(&bd->bd_ail_st_list))
+ gfs2_remove_from_ail(bd);
+ kmem_cache_free(gfs2_bufdata_cachep, bd);
+ }
}
/**
@@ -787,16 +959,21 @@
void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags)
{
- struct gfs2_trans *tr;
+ struct gfs2_trans *tr = NULL;
enum gfs2_freeze_state state = atomic_read(&sdp->sd_freeze_state);
down_write(&sdp->sd_log_flush_lock);
+ /*
+ * Do this check while holding the log_flush_lock to prevent new
+ * buffers from being added to the ail via gfs2_pin()
+ */
+ if (gfs2_withdrawn(sdp))
+ goto out;
+
/* Log might have been flushed while we waited for the flush lock */
- if (gl && !test_bit(GLF_LFLUSH, &gl->gl_flags)) {
- up_write(&sdp->sd_log_flush_lock);
- return;
- }
+ if (gl && !test_bit(GLF_LFLUSH, &gl->gl_flags))
+ goto out;
trace_gfs2_log_flush(sdp, 1, flags);
if (flags & GFS2_LOG_HEAD_FLUSH_SHUTDOWN)
@@ -808,17 +985,27 @@
sdp->sd_log_tr = NULL;
tr->tr_first = sdp->sd_log_flush_head;
if (unlikely (state == SFS_FROZEN))
- gfs2_assert_withdraw(sdp, !tr->tr_num_buf_new && !tr->tr_num_databuf_new);
+ if (gfs2_assert_withdraw_delayed(sdp,
+ !tr->tr_num_buf_new && !tr->tr_num_databuf_new))
+ goto out_withdraw;
}
if (unlikely(state == SFS_FROZEN))
- gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
- gfs2_assert_withdraw(sdp,
- sdp->sd_log_num_revoke == sdp->sd_log_commited_revoke);
+ if (gfs2_assert_withdraw_delayed(sdp, !sdp->sd_log_num_revoke))
+ goto out_withdraw;
+ if (gfs2_assert_withdraw_delayed(sdp,
+ sdp->sd_log_num_revoke == sdp->sd_log_committed_revoke))
+ goto out_withdraw;
gfs2_ordered_write(sdp);
+ if (gfs2_withdrawn(sdp))
+ goto out_withdraw;
lops_before_commit(sdp, tr);
- gfs2_log_flush_bio(sdp, REQ_OP_WRITE, 0);
+ if (gfs2_withdrawn(sdp))
+ goto out_withdraw;
+ gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE);
+ if (gfs2_withdrawn(sdp))
+ goto out_withdraw;
if (sdp->sd_log_head != sdp->sd_log_flush_head) {
log_flush_wait(sdp);
@@ -828,12 +1015,14 @@
trace_gfs2_log_blocks(sdp, -1);
log_write_header(sdp, flags);
}
+ if (gfs2_withdrawn(sdp))
+ goto out_withdraw;
lops_after_commit(sdp, tr);
gfs2_log_lock(sdp);
sdp->sd_log_head = sdp->sd_log_flush_head;
sdp->sd_log_blks_reserved = 0;
- sdp->sd_log_commited_revoke = 0;
+ sdp->sd_log_committed_revoke = 0;
spin_lock(&sdp->sd_ail_lock);
if (tr && !list_empty(&tr->tr_ail1_list)) {
@@ -845,12 +1034,9 @@
if (!(flags & GFS2_LOG_HEAD_FLUSH_NORMAL)) {
if (!sdp->sd_log_idle) {
- for (;;) {
- gfs2_ail1_start(sdp);
- gfs2_ail1_wait(sdp);
- if (gfs2_ail1_empty(sdp))
- break;
- }
+ empty_ail1_list(sdp);
+ if (gfs2_withdrawn(sdp))
+ goto out_withdraw;
atomic_dec(&sdp->sd_log_blks_free); /* Adjust for unreserved buffer */
trace_gfs2_log_blocks(sdp, -1);
log_write_header(sdp, flags);
@@ -863,10 +1049,30 @@
atomic_set(&sdp->sd_freeze_state, SFS_FROZEN);
}
+out_end:
trace_gfs2_log_flush(sdp, 0, flags);
+out:
up_write(&sdp->sd_log_flush_lock);
+ gfs2_trans_free(sdp, tr);
+ if (gfs2_withdrawing(sdp))
+ gfs2_withdraw(sdp);
+ return;
- kfree(tr);
+out_withdraw:
+ trans_drain(tr);
+ /**
+ * If the tr_list is empty, we're withdrawing during a log
+ * flush that targets a transaction, but the transaction was
+ * never queued onto any of the ail lists. Here we add it to
+ * ail1 just so that ail_drain() will find and free it.
+ */
+ spin_lock(&sdp->sd_ail_lock);
+ if (tr && list_empty(&tr->tr_list))
+ list_add(&tr->tr_list, &sdp->sd_ail1_list);
+ spin_unlock(&sdp->sd_ail_lock);
+ ail_drain(sdp); /* frees all transactions */
+ tr = NULL;
+ goto out_end;
}
/**
@@ -913,7 +1119,7 @@
set_bit(TR_ATTACHED, &tr->tr_flags);
}
- sdp->sd_log_commited_revoke += tr->tr_num_revoke - tr->tr_num_revoke_rm;
+ sdp->sd_log_committed_revoke += tr->tr_num_revoke - tr->tr_num_revoke_rm;
reserved = calc_reserved(sdp);
maxres = sdp->sd_log_blks_reserved + tr->tr_reserved;
gfs2_assert_withdraw(sdp, maxres >= reserved);
@@ -936,7 +1142,7 @@
* or the total number of used blocks (pinned blocks plus AIL blocks)
* is greater than thresh2.
*
- * At mount time thresh1 is 1/3rd of journal size, thresh2 is 2/3rd of
+ * At mount time thresh1 is 2/5ths of journal size, thresh2 is 4/5ths of
* journal size.
*
* Returns: errno
@@ -958,7 +1164,7 @@
*
*/
-void gfs2_log_shutdown(struct gfs2_sbd *sdp)
+static void gfs2_log_shutdown(struct gfs2_sbd *sdp)
{
gfs2_assert_withdraw(sdp, !sdp->sd_log_blks_reserved);
gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
@@ -1010,18 +1216,24 @@
while (!kthread_should_stop()) {
+ if (gfs2_withdrawn(sdp)) {
+ msleep_interruptible(HZ);
+ continue;
+ }
/* Check for errors writing to the journal */
if (sdp->sd_log_error) {
- gfs2_lm_withdraw(sdp,
- "GFS2: fsid=%s: error %d: "
- "withdrawing the file system to "
- "prevent further damage.\n",
- sdp->sd_fsname, sdp->sd_log_error);
+ gfs2_lm(sdp,
+ "GFS2: fsid=%s: error %d: "
+ "withdrawing the file system to "
+ "prevent further damage.\n",
+ sdp->sd_fsname, sdp->sd_log_error);
+ gfs2_withdraw(sdp);
+ continue;
}
did_flush = false;
if (gfs2_jrnl_flush_reqd(sdp) || t == 0) {
- gfs2_ail1_empty(sdp);
+ gfs2_ail1_empty(sdp, 0);
gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL |
GFS2_LFC_LOGD_JFLUSH_REQD);
did_flush = true;
@@ -1030,7 +1242,7 @@
if (gfs2_ail_flush_reqd(sdp)) {
gfs2_ail1_start(sdp);
gfs2_ail1_wait(sdp);
- gfs2_ail1_empty(sdp);
+ gfs2_ail1_empty(sdp, 0);
gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL |
GFS2_LFC_LOGD_AIL_FLUSH_REQD);
did_flush = true;
--
Gitblit v1.6.2