From 8813587a996e7d2ae160be3b79f9f70d9fef4583 Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Wed, 30 Jun 2021 20:54:22 -0400
Subject: [PATCH 1/6] Revert "ext4: consolidate checks for resize of bigalloc
into ext4_resize_begin"
The function ext4_resize_begin() gets called from three different
places, and online resize for bigalloc file systems is disallowed from
the old-style online resize (EXT4_IOC_GROUP_ADD and
EXT4_IOC_GROUP_EXTEND), but it *is* supposed to be allowed via
EXT4_IOC_RESIZE_FS.
This reverts commit e9f9f61d0cdcb7f0b0b5feb2d84aa1c5894751f3.
---
fs/ext4/ioctl.c | 14 ++++++++++++++
fs/ext4/resize.c | 4 ----
2 files changed, 14 insertions(+), 4 deletions(-)
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index e27f34bceb8d..5730aeca563c 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -692,6 +692,13 @@ static long ext4_ioctl_group_add(struct file *file,
if (err)
return err;
+ if (ext4_has_feature_bigalloc(sb)) {
+ ext4_msg(sb, KERN_ERR,
+ "Online resizing not supported with bigalloc");
+ err = -EOPNOTSUPP;
+ goto group_add_out;
+ }
+
err = mnt_want_write_file(file);
if (err)
goto group_add_out;
@@ -914,6 +921,13 @@ setversion_out:
goto group_extend_out;
}
+ if (ext4_has_feature_bigalloc(sb)) {
+ ext4_msg(sb, KERN_ERR,
+ "Online resizing not supported with bigalloc");
+ err = -EOPNOTSUPP;
+ goto group_extend_out;
+ }
+
err = mnt_want_write_file(filp);
if (err)
goto group_extend_out;
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index fc885914c88a..7a9f1adef679 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -74,10 +74,6 @@ int ext4_resize_begin(struct super_block *sb)
return -EPERM;
}
- if (ext4_has_feature_bigalloc(sb)) {
- ext4_msg(sb, KERN_ERR, "Online resizing not supported with bigalloc");
- return -EOPNOTSUPP;
- }
if (ext4_has_feature_sparse_super2(sb)) {
ext4_msg(sb, KERN_ERR, "Online resizing not supported with sparse_super2");
return -EOPNOTSUPP;
From 558d6450c7755aa005d89021204b6cdcae5e848f Mon Sep 17 00:00:00 2001
From: Ye Bin <yebin10@huawei.com>
Date: Tue, 15 Jun 2021 17:05:37 +0800
Subject: [PATCH 2/6] ext4: fix WARN_ON_ONCE(!buffer_uptodate) after an error
writing the superblock
If a writeback of the superblock fails with an I/O error, the buffer
is marked not uptodate. However, this can cause a WARN_ON to trigger
when we attempt to write superblock a second time. (Which might
succeed this time, for cerrtain types of block devices such as iSCSI
devices over a flaky network.)
Try to detect this case in flush_stashed_error_work(), and also change
__ext4_handle_dirty_metadata() so we always set the uptodate flag, not
just in the nojournal case.
Before this commit, this problem can be repliciated via:
1. dmsetup create dust1 --table '0 2097152 dust /dev/sdc 0 4096'
2. mount /dev/mapper/dust1 /home/test
3. dmsetup message dust1 0 addbadblock 0 10
4. cd /home/test
5. echo "XXXXXXX" > t
After a few seconds, we got following warning:
[ 80.654487] end_buffer_async_write: bh=0xffff88842f18bdd0
[ 80.656134] Buffer I/O error on dev dm-0, logical block 0, lost async page write
[ 85.774450] EXT4-fs error (device dm-0): ext4_check_bdev_write_error:193: comm kworker/u16:8: Error while async write back metadata
[ 91.415513] mark_buffer_dirty: bh=0xffff88842f18bdd0
[ 91.417038] ------------[ cut here ]------------
[ 91.418450] WARNING: CPU: 1 PID: 1944 at fs/buffer.c:1092 mark_buffer_dirty.cold+0x1c/0x5e
[ 91.440322] Call Trace:
[ 91.440652] __jbd2_journal_temp_unlink_buffer+0x135/0x220
[ 91.441354] __jbd2_journal_unfile_buffer+0x24/0x90
[ 91.441981] __jbd2_journal_refile_buffer+0x134/0x1d0
[ 91.442628] jbd2_journal_commit_transaction+0x249a/0x3240
[ 91.443336] ? put_prev_entity+0x2a/0x200
[ 91.443856] ? kjournald2+0x12e/0x510
[ 91.444324] kjournald2+0x12e/0x510
[ 91.444773] ? woken_wake_function+0x30/0x30
[ 91.445326] kthread+0x150/0x1b0
[ 91.445739] ? commit_timeout+0x20/0x20
[ 91.446258] ? kthread_flush_worker+0xb0/0xb0
[ 91.446818] ret_from_fork+0x1f/0x30
[ 91.447293] ---[ end trace 66f0b6bf3d1abade ]---
Signed-off-by: Ye Bin <yebin10@huawei.com>
Link: https://lore.kernel.org/r/20210615090537.3423231-1-yebin10@huawei.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
fs/ext4/ext4_jbd2.c | 2 +-
fs/ext4/super.c | 12 ++++++++++--
2 files changed, 11 insertions(+), 3 deletions(-)
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index be799040a415..b96ecba91899 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -327,6 +327,7 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
set_buffer_meta(bh);
set_buffer_prio(bh);
+ set_buffer_uptodate(bh);
if (ext4_handle_valid(handle)) {
err = jbd2_journal_dirty_metadata(handle, bh);
/* Errors can only happen due to aborted journal or a nasty bug */
@@ -355,7 +356,6 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
err);
}
} else {
- set_buffer_uptodate(bh);
if (inode)
mark_buffer_dirty_inode(bh, inode);
else
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 20344633bdd9..cdbe71d935e8 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -705,15 +705,23 @@ static void flush_stashed_error_work(struct work_struct *work)
* ext4 error handling code during handling of previous errors.
*/
if (!sb_rdonly(sbi->s_sb) && journal) {
+ struct buffer_head *sbh = sbi->s_sbh;
handle = jbd2_journal_start(journal, 1);
if (IS_ERR(handle))
goto write_directly;
- if (jbd2_journal_get_write_access(handle, sbi->s_sbh)) {
+ if (jbd2_journal_get_write_access(handle, sbh)) {
jbd2_journal_stop(handle);
goto write_directly;
}
ext4_update_super(sbi->s_sb);
- if (jbd2_journal_dirty_metadata(handle, sbi->s_sbh)) {
+ if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) {
+ ext4_msg(sbi->s_sb, KERN_ERR, "previous I/O error to "
+ "superblock detected");
+ clear_buffer_write_io_error(sbh);
+ set_buffer_uptodate(sbh);
+ }
+
+ if (jbd2_journal_dirty_metadata(handle, sbh)) {
jbd2_journal_stop(handle);
goto write_directly;
}
From cd84bbbac12a173a381a64c6ec8b76a5277b87b5 Mon Sep 17 00:00:00 2001
From: Stephen Brennan <stephen.s.brennan@oracle.com>
Date: Wed, 23 Jun 2021 16:21:14 -0700
Subject: [PATCH 3/6] ext4: use ext4_grp_locked_error in mb_find_extent
Commit 5d1b1b3f492f ("ext4: fix BUG when calling ext4_error with locked
block group") introduces ext4_grp_locked_error to handle unlocking a
group in error cases. Otherwise, there is a possibility of a sleep while
atomic. However, since 43c73221b3b1 ("ext4: replace BUG_ON with WARN_ON
in mb_find_extent()"), mb_find_extent() has contained a ext4_error()
call while a group spinlock is held. Replace this with
ext4_grp_locked_error.
Fixes: 43c73221b3b1 ("ext4: replace BUG_ON with WARN_ON in mb_find_extent()")
Cc: <stable@vger.kernel.org> # 4.14+
Signed-off-by: Stephen Brennan <stephen.s.brennan@oracle.com>
Reviewed-by: Lukas Czerner <lczerner@redhat.com>
Reviewed-by: Junxiao Bi <junxiao.bi@oracle.com>
Link: https://lore.kernel.org/r/20210623232114.34457-1-stephen.s.brennan@oracle.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
fs/ext4/mballoc.c | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index c2c22c2baac0..089c958aa2c3 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1909,10 +1909,11 @@ static int mb_find_extent(struct ext4_buddy *e4b, int block,
if (ex->fe_start + ex->fe_len > EXT4_CLUSTERS_PER_GROUP(e4b->bd_sb)) {
/* Should never happen! (but apparently sometimes does?!?) */
WARN_ON(1);
- ext4_error(e4b->bd_sb, "corruption or bug in mb_find_extent "
- "block=%d, order=%d needed=%d ex=%u/%d/%d@%u",
- block, order, needed, ex->fe_group, ex->fe_start,
- ex->fe_len, ex->fe_logical);
+ ext4_grp_locked_error(e4b->bd_sb, e4b->bd_group, 0, 0,
+ "corruption or bug in mb_find_extent "
+ "block=%d, order=%d needed=%d ex=%u/%d/%d@%u",
+ block, order, needed, ex->fe_group, ex->fe_start,
+ ex->fe_len, ex->fe_logical);
ex->fe_len = 0;
ex->fe_start = 0;
ex->fe_group = 0;
From 61bb4a1c417e5b95d9edb4f887f131de32e419cb Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Fri, 2 Jul 2021 12:45:02 -0400
Subject: [PATCH 4/6] ext4: fix possible UAF when remounting r/o a
mmp-protected file system
After commit 618f003199c6 ("ext4: fix memory leak in
ext4_fill_super"), after the file system is remounted read-only, there
is a race where the kmmpd thread can exit, causing sbi->s_mmp_tsk to
point at freed memory, which the call to ext4_stop_mmpd() can trip
over.
Fix this by only allowing kmmpd() to exit when it is stopped via
ext4_stop_mmpd().
Link: https://lore.kernel.org/r/20210707002433.3719773-1-tytso@mit.edu
Reported-by: Ye Bin <yebin10@huawei.com>
Bug-Report-Link: <20210629143603.2166962-1-yebin10@huawei.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Reviewed-by: Jan Kara <jack@suse.cz>
---
fs/ext4/mmp.c | 31 +++++++++++++++----------------
fs/ext4/super.c | 6 +++++-
2 files changed, 20 insertions(+), 17 deletions(-)
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 6cb598b549ca..bc364c119af6 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -156,7 +156,12 @@ static int kmmpd(void *data)
memcpy(mmp->mmp_nodename, init_utsname()->nodename,
sizeof(mmp->mmp_nodename));
- while (!kthread_should_stop()) {
+ while (!kthread_should_stop() && !sb_rdonly(sb)) {
+ if (!ext4_has_feature_mmp(sb)) {
+ ext4_warning(sb, "kmmpd being stopped since MMP feature"
+ " has been disabled.");
+ goto wait_to_exit;
+ }
if (++seq > EXT4_MMP_SEQ_MAX)
seq = 1;
@@ -177,16 +182,6 @@ static int kmmpd(void *data)
failed_writes++;
}
- if (!(le32_to_cpu(es->s_feature_incompat) &
- EXT4_FEATURE_INCOMPAT_MMP)) {
- ext4_warning(sb, "kmmpd being stopped since MMP feature"
- " has been disabled.");
- goto exit_thread;
- }
-
- if (sb_rdonly(sb))
- break;
-
diff = jiffies - last_update_time;
if (diff < mmp_update_interval * HZ)
schedule_timeout_interruptible(mmp_update_interval *
@@ -207,7 +202,7 @@ static int kmmpd(void *data)
ext4_error_err(sb, -retval,
"error reading MMP data: %d",
retval);
- goto exit_thread;
+ goto wait_to_exit;
}
mmp_check = (struct mmp_struct *)(bh_check->b_data);
@@ -221,7 +216,7 @@ static int kmmpd(void *data)
ext4_error_err(sb, EBUSY, "abort");
put_bh(bh_check);
retval = -EBUSY;
- goto exit_thread;
+ goto wait_to_exit;
}
put_bh(bh_check);
}
@@ -244,7 +239,13 @@ static int kmmpd(void *data)
retval = write_mmp_block(sb, bh);
-exit_thread:
+wait_to_exit:
+ while (!kthread_should_stop()) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ if (!kthread_should_stop())
+ schedule();
+ }
+ set_current_state(TASK_RUNNING);
return retval;
}
@@ -391,5 +392,3 @@ failed:
brelse(bh);
return 1;
}
-
-
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index cdbe71d935e8..b8ff0399e171 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -5993,7 +5993,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
*/
ext4_mark_recovery_complete(sb, es);
}
- ext4_stop_mmpd(sbi);
} else {
/* Make sure we can mount this feature set readwrite */
if (ext4_has_feature_readonly(sb) ||
@@ -6107,6 +6106,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks)
ext4_release_system_zone(sb);
+ if (!ext4_has_feature_mmp(sb) || sb_rdonly(sb))
+ ext4_stop_mmpd(sbi);
+
/*
* Some options can be enabled by ext4 and/or by VFS mount flag
* either way we need to make sure it matches in both *flags and
@@ -6140,6 +6142,8 @@ restore_opts:
for (i = 0; i < EXT4_MAXQUOTAS; i++)
kfree(to_free[i]);
#endif
+ if (!ext4_has_feature_mmp(sb) || sb_rdonly(sb))
+ ext4_stop_mmpd(sbi);
kfree(orig_data);
return err;
}
From 0955901908e80384592ed85aa164d7e5be6cc067 Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Fri, 2 Jul 2021 13:21:06 -0400
Subject: [PATCH 5/6] ext4: fix flags validity checking for EXT4_IOC_CHECKPOINT
Use the correct bitmask when checking for any not-yet-supported flags.
Link: https://lore.kernel.org/r/20210702173425.1276158-1-tytso@mit.edu
Fixes: 351a0a3fbc35 ("ext4: add ioctl EXT4_IOC_CHECKPOINT")
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Reviewed-by: Leah Rumancik <leah.rumancik@gmail.com>
---
fs/ext4/ioctl.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 5730aeca563c..6eed6170aded 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -823,7 +823,7 @@ static int ext4_ioctl_checkpoint(struct file *filp, unsigned long arg)
if (!EXT4_SB(sb)->s_journal)
return -ENODEV;
- if (flags & ~JBD2_JOURNAL_FLUSH_VALID)
+ if (flags & ~EXT4_IOC_CHECKPOINT_FLAG_VALID)
return -EINVAL;
q = bdev_get_queue(EXT4_SB(sb)->s_journal->j_dev);
From 0705e8d1e2207ceeb83dc6e1751b6b82718b353a Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Fri, 2 Jul 2021 18:05:03 -0400
Subject: [PATCH 6/6] ext4: inline jbd2_journal_[un]register_shrinker()
The function jbd2_journal_unregister_shrinker() was getting called
twice when the file system was getting unmounted. On Power and ARM
platforms this was causing kernel crash when unmounting the file
system, when a percpu_counter was destroyed twice.
Fix this by removing jbd2_journal_[un]register_shrinker() functions,
and inlining the shrinker setup and teardown into
journal_init_common() and jbd2_journal_destroy(). This means that
ext4 and ocfs2 now no longer need to know about registering and
unregistering jbd2's shrinker.
Also, while we're at it, rename the percpu counter from
j_jh_shrink_count to j_checkpoint_jh_count, since this makes it
clearer what this counter is intended to track.
Link: https://lore.kernel.org/r/20210705145025.3363130-1-tytso@mit.edu
Fixes: 4ba3fcdde7e3 ("jbd2,ext4: add a shrinker to release checkpointed buffers")
Reported-by: Jon Hunter <jonathanh@nvidia.com>
Reported-by: Sachin Sant <sachinp@linux.vnet.ibm.com>
Tested-by: Sachin Sant <sachinp@linux.vnet.ibm.com>
Tested-by: Jon Hunter <jonathanh@nvidia.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
fs/ext4/super.c | 8 ---
fs/jbd2/checkpoint.c | 4 +-
fs/jbd2/journal.c | 149 +++++++++++++++++--------------------------
include/linux/jbd2.h | 6 +-
4 files changed, 64 insertions(+), 103 deletions(-)
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index b8ff0399e171..dfa09a277b56 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1184,7 +1184,6 @@ static void ext4_put_super(struct super_block *sb)
ext4_unregister_sysfs(sb);
if (sbi->s_journal) {
- jbd2_journal_unregister_shrinker(sbi->s_journal);
aborted = is_journal_aborted(sbi->s_journal);
err = jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
@@ -5176,7 +5175,6 @@ failed_mount_wq:
sbi->s_ea_block_cache = NULL;
if (sbi->s_journal) {
- jbd2_journal_unregister_shrinker(sbi->s_journal);
jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
}
@@ -5502,12 +5500,6 @@ static int ext4_load_journal(struct super_block *sb,
ext4_commit_super(sb);
}
- err = jbd2_journal_register_shrinker(journal);
- if (err) {
- EXT4_SB(sb)->s_journal = NULL;
- goto err_out;
- }
-
return 0;
err_out:
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 51d1eb2ffeb9..746132998c57 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -701,7 +701,7 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
__buffer_unlink(jh);
jh->b_cp_transaction = NULL;
- percpu_counter_dec(&journal->j_jh_shrink_count);
+ percpu_counter_dec(&journal->j_checkpoint_jh_count);
jbd2_journal_put_journal_head(jh);
/* Is this transaction empty? */
@@ -764,7 +764,7 @@ void __jbd2_journal_insert_checkpoint(struct journal_head *jh,
jh->b_cpnext->b_cpprev = jh;
}
transaction->t_checkpoint_list = jh;
- percpu_counter_inc(&transaction->t_journal->j_jh_shrink_count);
+ percpu_counter_inc(&transaction->t_journal->j_checkpoint_jh_count);
}
/*
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 152880c298ca..35302bc192eb 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1283,6 +1283,48 @@ static int jbd2_min_tag_size(void)
return sizeof(journal_block_tag_t) - 4;
}
+/**
+ * jbd2_journal_shrink_scan()
+ *
+ * Scan the checkpointed buffer on the checkpoint list and release the
+ * journal_head.
+ */
+static unsigned long jbd2_journal_shrink_scan(struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ journal_t *journal = container_of(shrink, journal_t, j_shrinker);
+ unsigned long nr_to_scan = sc->nr_to_scan;
+ unsigned long nr_shrunk;
+ unsigned long count;
+
+ count = percpu_counter_read_positive(&journal->j_checkpoint_jh_count);
+ trace_jbd2_shrink_scan_enter(journal, sc->nr_to_scan, count);
+
+ nr_shrunk = jbd2_journal_shrink_checkpoint_list(journal, &nr_to_scan);
+
+ count = percpu_counter_read_positive(&journal->j_checkpoint_jh_count);
+ trace_jbd2_shrink_scan_exit(journal, nr_to_scan, nr_shrunk, count);
+
+ return nr_shrunk;
+}
+
+/**
+ * jbd2_journal_shrink_count()
+ *
+ * Count the number of checkpoint buffers on the checkpoint list.
+ */
+static unsigned long jbd2_journal_shrink_count(struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ journal_t *journal = container_of(shrink, journal_t, j_shrinker);
+ unsigned long count;
+
+ count = percpu_counter_read_positive(&journal->j_checkpoint_jh_count);
+ trace_jbd2_shrink_count(journal, sc->nr_to_scan, count);
+
+ return count;
+}
+
/*
* Management for journal control blocks: functions to create and
* destroy journal_t structures, and to initialise and read existing
@@ -1361,9 +1403,23 @@ static journal_t *journal_init_common(struct block_device *bdev,
journal->j_sb_buffer = bh;
journal->j_superblock = (journal_superblock_t *)bh->b_data;
+ journal->j_shrink_transaction = NULL;
+ journal->j_shrinker.scan_objects = jbd2_journal_shrink_scan;
+ journal->j_shrinker.count_objects = jbd2_journal_shrink_count;
+ journal->j_shrinker.seeks = DEFAULT_SEEKS;
+ journal->j_shrinker.batch = journal->j_max_transaction_buffers;
+
+ if (percpu_counter_init(&journal->j_checkpoint_jh_count, 0, GFP_KERNEL))
+ goto err_cleanup;
+
+ if (register_shrinker(&journal->j_shrinker)) {
+ percpu_counter_destroy(&journal->j_checkpoint_jh_count);
+ goto err_cleanup;
+ }
return journal;
err_cleanup:
+ brelse(journal->j_sb_buffer);
kfree(journal->j_wbuf);
jbd2_journal_destroy_revoke(journal);
kfree(journal);
@@ -2050,93 +2106,6 @@ recovery_error:
return -EIO;
}
-/**
- * jbd2_journal_shrink_scan()
- *
- * Scan the checkpointed buffer on the checkpoint list and release the
- * journal_head.
- */
-static unsigned long jbd2_journal_shrink_scan(struct shrinker *shrink,
- struct shrink_control *sc)
-{
- journal_t *journal = container_of(shrink, journal_t, j_shrinker);
- unsigned long nr_to_scan = sc->nr_to_scan;
- unsigned long nr_shrunk;
- unsigned long count;
-
- count = percpu_counter_read_positive(&journal->j_jh_shrink_count);
- trace_jbd2_shrink_scan_enter(journal, sc->nr_to_scan, count);
-
- nr_shrunk = jbd2_journal_shrink_checkpoint_list(journal, &nr_to_scan);
-
- count = percpu_counter_read_positive(&journal->j_jh_shrink_count);
- trace_jbd2_shrink_scan_exit(journal, nr_to_scan, nr_shrunk, count);
-
- return nr_shrunk;
-}
-
-/**
- * jbd2_journal_shrink_count()
- *
- * Count the number of checkpoint buffers on the checkpoint list.
- */
-static unsigned long jbd2_journal_shrink_count(struct shrinker *shrink,
- struct shrink_control *sc)
-{
- journal_t *journal = container_of(shrink, journal_t, j_shrinker);
- unsigned long count;
-
- count = percpu_counter_read_positive(&journal->j_jh_shrink_count);
- trace_jbd2_shrink_count(journal, sc->nr_to_scan, count);
-
- return count;
-}
-
-/**
- * jbd2_journal_register_shrinker()
- * @journal: Journal to act on.
- *
- * Init a percpu counter to record the checkpointed buffers on the checkpoint
- * list and register a shrinker to release their journal_head.
- */
-int jbd2_journal_register_shrinker(journal_t *journal)
-{
- int err;
-
- journal->j_shrink_transaction = NULL;
-
- err = percpu_counter_init(&journal->j_jh_shrink_count, 0, GFP_KERNEL);
- if (err)
- return err;
-
- journal->j_shrinker.scan_objects = jbd2_journal_shrink_scan;
- journal->j_shrinker.count_objects = jbd2_journal_shrink_count;
- journal->j_shrinker.seeks = DEFAULT_SEEKS;
- journal->j_shrinker.batch = journal->j_max_transaction_buffers;
-
- err = register_shrinker(&journal->j_shrinker);
- if (err) {
- percpu_counter_destroy(&journal->j_jh_shrink_count);
- return err;
- }
-
- return 0;
-}
-EXPORT_SYMBOL(jbd2_journal_register_shrinker);
-
-/**
- * jbd2_journal_unregister_shrinker()
- * @journal: Journal to act on.
- *
- * Unregister the checkpointed buffer shrinker and destroy the percpu counter.
- */
-void jbd2_journal_unregister_shrinker(journal_t *journal)
-{
- percpu_counter_destroy(&journal->j_jh_shrink_count);
- unregister_shrinker(&journal->j_shrinker);
-}
-EXPORT_SYMBOL(jbd2_journal_unregister_shrinker);
-
/**
* jbd2_journal_destroy() - Release a journal_t structure.
* @journal: Journal to act on.
@@ -2209,8 +2178,10 @@ int jbd2_journal_destroy(journal_t *journal)
brelse(journal->j_sb_buffer);
}
- jbd2_journal_unregister_shrinker(journal);
-
+ if (journal->j_shrinker.flags & SHRINKER_REGISTERED) {
+ percpu_counter_destroy(&journal->j_checkpoint_jh_count);
+ unregister_shrinker(&journal->j_shrinker);
+ }
if (journal->j_proc_entry)
jbd2_stats_proc_exit(journal);
iput(journal->j_inode);
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 6cc035321562..fd933c45281a 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -918,11 +918,11 @@ struct journal_s
struct shrinker j_shrinker;
/**
- * @j_jh_shrink_count:
+ * @j_checkpoint_jh_count:
*
* Number of journal buffers on the checkpoint list. [j_list_lock]
*/
- struct percpu_counter j_jh_shrink_count;
+ struct percpu_counter j_checkpoint_jh_count;
/**
* @j_shrink_transaction:
@@ -1556,8 +1556,6 @@ extern int jbd2_journal_set_features
(journal_t *, unsigned long, unsigned long, unsigned long);
extern void jbd2_journal_clear_features
(journal_t *, unsigned long, unsigned long, unsigned long);
-extern int jbd2_journal_register_shrinker(journal_t *journal);
-extern void jbd2_journal_unregister_shrinker(journal_t *journal);
extern int jbd2_journal_load (journal_t *journal);
extern int jbd2_journal_destroy (journal_t *);
extern int jbd2_journal_recover (journal_t *journal);