summaryrefslogtreecommitdiffstats
path: root/fs/jbd2
diff options
context:
space:
mode:
authorThomas Gleixner <tglx@linutronix.de>2019-08-09 14:42:33 +0200
committerTheodore Ts'o <tytso@mit.edu>2019-10-21 09:16:46 -0400
commit7855a57d008b2354dd52078974529e08b889f98a (patch)
treed7c1b3ed45c254a44bbe540f771a567835b08939 /fs/jbd2
parent464170647b5648bb81f3615567485fcb9a685bed (diff)
downloadlinux-7855a57d008b2354dd52078974529e08b889f98a.tar.bz2
jbd2: Free journal head outside of locked region
On PREEMPT_RT bit-spinlocks have the same semantics as on PREEMPT_RT=n, i.e. they disable preemption. That means functions which are not safe to be called in preempt disabled context on RT trigger a might_sleep() assert. The journal head bit spinlock is mostly held for short code sequences with trivial RT safe functionality, except for one place: jbd2_journal_put_journal_head() invokes __journal_remove_journal_head() with the journal head bit spinlock held. __journal_remove_journal_head() invokes kmem_cache_free() which must not be called with preemption disabled on RT. Jan suggested to rework the removal function so the actual free happens outside the bit-spinlocked region. Split it into two parts: - Do the sanity checks and the buffer head detach under the lock - Do the actual free after dropping the lock There is error case handling in the free part which needs to dereference the b_size field of the now detached buffer head. Due to paranoia (caused by ignorance) the size is retrieved in the detach function and handed into the free function. Might be over-engineered, but better safe than sorry. This makes the journal head bit-spinlock usage RT compliant and also avoids nested locking which is not covered by lockdep. Suggested-by: Jan Kara <jack@suse.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: linux-ext4@vger.kernel.org Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Jan Kara <jack@suse.com> Signed-off-by: Jan Kara <jack@suse.cz> Link: https://lore.kernel.org/r/20190809124233.13277-8-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Diffstat (limited to 'fs/jbd2')
-rw-r--r--fs/jbd2/journal.c20
1 files changed, 14 insertions, 6 deletions
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 5d4192f05879..f6034ce4a107 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -2531,17 +2531,23 @@ static void __journal_remove_journal_head(struct buffer_head *bh)
J_ASSERT_BH(bh, buffer_jbd(bh));
J_ASSERT_BH(bh, jh2bh(jh) == bh);
BUFFER_TRACE(bh, "remove journal_head");
+
+ /* Unlink before dropping the lock */
+ bh->b_private = NULL;
+ jh->b_bh = NULL; /* debug, really */
+ clear_buffer_jbd(bh);
+}
+
+static void journal_release_journal_head(struct journal_head *jh, size_t b_size)
+{
if (jh->b_frozen_data) {
printk(KERN_WARNING "%s: freeing b_frozen_data\n", __func__);
- jbd2_free(jh->b_frozen_data, bh->b_size);
+ jbd2_free(jh->b_frozen_data, b_size);
}
if (jh->b_committed_data) {
printk(KERN_WARNING "%s: freeing b_committed_data\n", __func__);
- jbd2_free(jh->b_committed_data, bh->b_size);
+ jbd2_free(jh->b_committed_data, b_size);
}
- bh->b_private = NULL;
- jh->b_bh = NULL; /* debug, really */
- clear_buffer_jbd(bh);
journal_free_journal_head(jh);
}
@@ -2559,9 +2565,11 @@ void jbd2_journal_put_journal_head(struct journal_head *jh)
if (!jh->b_jcount) {
__journal_remove_journal_head(bh);
jbd_unlock_bh_journal_head(bh);
+ journal_release_journal_head(jh, bh->b_size);
__brelse(bh);
- } else
+ } else {
jbd_unlock_bh_journal_head(bh);
+ }
}
/*