* [PATCH v3 1/6] btrfs: Add a lockdep model for the num_writers wait event
2022-07-20 23:38 [PATCH v3 0/6] btrfs: Annotate wait events with lockdep Ioannis Angelakopoulos
@ 2022-07-20 23:38 ` Ioannis Angelakopoulos
2022-07-21 0:42 ` Wang Yugui
2022-07-20 23:38 ` [PATCH v3 2/6] btrfs: Add a lockdep model for the num_extwriters " Ioannis Angelakopoulos
` (5 subsequent siblings)
6 siblings, 1 reply; 10+ messages in thread
From: Ioannis Angelakopoulos @ 2022-07-20 23:38 UTC (permalink / raw)
To: linux-btrfs, kernel-team
Annotate the num_writers wait event in fs/btrfs/transaction.c with lockdep
in order to catch deadlocks involving this wait event.
Use a read/write lockdep map for the annotation. A thread starting/joining
the transaction acquires the map as a reader when it increments
cur_trans->num_writers and it acquires the map as a writer before it
blocks on the wait event.
Signed-off-by: Ioannis Angelakopoulos <iangelak@fb.com>
---
fs/btrfs/ctree.h | 47 ++++++++++++++++++++++++++++++++++++++++++
fs/btrfs/disk-io.c | 2 ++
fs/btrfs/transaction.c | 37 ++++++++++++++++++++++++++++-----
3 files changed, 81 insertions(+), 5 deletions(-)
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 202496172059..d4d69c0e001e 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1095,6 +1095,8 @@ struct btrfs_fs_info {
/* Updates are not protected by any lock */
struct btrfs_commit_stats commit_stats;
+ struct lockdep_map btrfs_trans_num_writers_map;
+
#ifdef CONFIG_BTRFS_FS_REF_VERIFY
spinlock_t ref_verify_lock;
struct rb_root block_tree;
@@ -1175,6 +1177,51 @@ enum {
BTRFS_ROOT_UNFINISHED_DROP,
};
+/*
+ * Lockdep annotation for wait events.
+ *
+ * @b: The struct where the lockdep map is defined
+ * @lock: The lockdep map corresponding to a wait event
+ *
+ * This macro is used to annotate a wait event. In this case a thread acquires
+ * the lockdep map as writer (exclusive lock) because it has to block until all
+ * the threads that hold the lock as readers signal the condition for the wait
+ * event and release their locks.
+ */
+#define btrfs_might_wait_for_event(b, lock) \
+ do { \
+ rwsem_acquire(&b->lock##_map, 0, 0, _THIS_IP_); \
+ rwsem_release(&b->lock##_map, _THIS_IP_); \
+ } while (0)
+
+/*
+ * Protection for the resource/condition of a wait event.
+ *
+ * @b: The struct where the lockdep map is defined
+ * @lock: The lockdep map corresponding to a wait event
+ *
+ * Many threads can modify the condition for the wait event at the same time
+ * and signal the threads that block on the wait event. The threads that
+ * modify the condition and do the signaling acquire the lock as readers
+ * (shared lock).
+ */
+#define btrfs_lockdep_acquire(b, lock) \
+ rwsem_acquire_read(&b->lock##_map, 0, 0, _THIS_IP_)
+
+/*
+ * Used after signaling the condition for a wait event to release the
+ * lockdep map held by a reader thread.
+ */
+#define btrfs_lockdep_release(b, lock) \
+ rwsem_release(&b->lock##_map, _THIS_IP_)
+
+/* Initialization of the lockdep map */
+#define btrfs_lockdep_init_map(b, lock) \
+ do { \
+ static struct lock_class_key lock##_key; \
+ lockdep_init_map(&b->lock##_map, #lock, &lock##_key, 0); \
+ } while (0)
+
static inline void btrfs_wake_unfinished_drop(struct btrfs_fs_info *fs_info)
{
clear_and_wake_up_bit(BTRFS_FS_UNFINISHED_DROPS, &fs_info->flags);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 3fac429cf8a4..38831c730d61 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3074,6 +3074,8 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
mutex_init(&fs_info->zoned_data_reloc_io_lock);
seqlock_init(&fs_info->profiles_lock);
+ btrfs_lockdep_init_map(fs_info, btrfs_trans_num_writers);
+
INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
INIT_LIST_HEAD(&fs_info->space_info);
INIT_LIST_HEAD(&fs_info->tree_mod_seq_list);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 0bec10740ad3..d8287ec890bc 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -313,6 +313,7 @@ static noinline int join_transaction(struct btrfs_fs_info *fs_info,
atomic_inc(&cur_trans->num_writers);
extwriter_counter_inc(cur_trans, type);
spin_unlock(&fs_info->trans_lock);
+ btrfs_lockdep_acquire(fs_info, btrfs_trans_num_writers);
return 0;
}
spin_unlock(&fs_info->trans_lock);
@@ -334,16 +335,20 @@ static noinline int join_transaction(struct btrfs_fs_info *fs_info,
if (!cur_trans)
return -ENOMEM;
+ btrfs_lockdep_acquire(fs_info, btrfs_trans_num_writers);
+
spin_lock(&fs_info->trans_lock);
if (fs_info->running_transaction) {
/*
* someone started a transaction after we unlocked. Make sure
* to redo the checks above
*/
+ btrfs_lockdep_release(fs_info, btrfs_trans_num_writers);
kfree(cur_trans);
goto loop;
} else if (BTRFS_FS_ERROR(fs_info)) {
spin_unlock(&fs_info->trans_lock);
+ btrfs_lockdep_release(fs_info, btrfs_trans_num_writers);
kfree(cur_trans);
return -EROFS;
}
@@ -1022,6 +1027,9 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
extwriter_counter_dec(cur_trans, trans->type);
cond_wake_up(&cur_trans->writer_wait);
+
+ btrfs_lockdep_release(info, btrfs_trans_num_writers);
+
btrfs_put_transaction(cur_trans);
if (current->journal_info == trans)
@@ -1994,6 +2002,12 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans, int err)
if (cur_trans == fs_info->running_transaction) {
cur_trans->state = TRANS_STATE_COMMIT_DOING;
spin_unlock(&fs_info->trans_lock);
+
+ /*
+ * The thread has already released the lockdep map as reader already in
+ * btrfs_commit_transaction().
+ */
+ btrfs_might_wait_for_event(fs_info, btrfs_trans_num_writers);
wait_event(cur_trans->writer_wait,
atomic_read(&cur_trans->num_writers) == 1);
@@ -2222,7 +2236,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
btrfs_put_transaction(prev_trans);
if (ret)
- goto cleanup_transaction;
+ goto lockdep_release;
} else {
spin_unlock(&fs_info->trans_lock);
}
@@ -2236,7 +2250,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
*/
if (BTRFS_FS_ERROR(fs_info)) {
ret = -EROFS;
- goto cleanup_transaction;
+ goto lockdep_release;
}
}
@@ -2250,19 +2264,21 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
ret = btrfs_start_delalloc_flush(fs_info);
if (ret)
- goto cleanup_transaction;
+ goto lockdep_release;
ret = btrfs_run_delayed_items(trans);
if (ret)
- goto cleanup_transaction;
+ goto lockdep_release;
wait_event(cur_trans->writer_wait,
extwriter_counter_read(cur_trans) == 0);
/* some pending stuffs might be added after the previous flush. */
ret = btrfs_run_delayed_items(trans);
- if (ret)
+ if (ret) {
+ btrfs_lockdep_release(fs_info, btrfs_trans_num_writers);
goto cleanup_transaction;
+ }
btrfs_wait_delalloc_flush(fs_info);
@@ -2284,6 +2300,14 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
add_pending_snapshot(trans);
cur_trans->state = TRANS_STATE_COMMIT_DOING;
spin_unlock(&fs_info->trans_lock);
+
+ /*
+ * The thread has started/joined the transaction thus it holds the lockdep
+ * map as a reader. It has to release it before acquiring the lockdep map
+ * as a writer.
+ */
+ btrfs_lockdep_release(fs_info, btrfs_trans_num_writers);
+ btrfs_might_wait_for_event(fs_info, btrfs_trans_num_writers);
wait_event(cur_trans->writer_wait,
atomic_read(&cur_trans->num_writers) == 1);
@@ -2515,6 +2539,9 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
cleanup_transaction(trans, ret);
return ret;
+lockdep_release:
+ btrfs_lockdep_release(fs_info, btrfs_trans_num_writers);
+ goto cleanup_transaction;
}
/*
--
2.30.2
^ permalink raw reply related [flat|nested] 10+ messages in thread* Re: [PATCH v3 1/6] btrfs: Add a lockdep model for the num_writers wait event
2022-07-20 23:38 ` [PATCH v3 1/6] btrfs: Add a lockdep model for the num_writers wait event Ioannis Angelakopoulos
@ 2022-07-21 0:42 ` Wang Yugui
2022-07-21 16:37 ` Ioannis Angelakopoulos
0 siblings, 1 reply; 10+ messages in thread
From: Wang Yugui @ 2022-07-21 0:42 UTC (permalink / raw)
To: Ioannis Angelakopoulos; +Cc: linux-btrfs, kernel-team
Hi,
> Annotate the num_writers wait event in fs/btrfs/transaction.c with lockdep
> in order to catch deadlocks involving this wait event.
>
> Use a read/write lockdep map for the annotation. A thread starting/joining
> the transaction acquires the map as a reader when it increments
> cur_trans->num_writers and it acquires the map as a writer before it
> blocks on the wait event.
>
> Signed-off-by: Ioannis Angelakopoulos <iangelak@fb.com>
> ---
> fs/btrfs/ctree.h | 47 ++++++++++++++++++++++++++++++++++++++++++
> fs/btrfs/disk-io.c | 2 ++
> fs/btrfs/transaction.c | 37 ++++++++++++++++++++++++++++-----
> 3 files changed, 81 insertions(+), 5 deletions(-)
>
> diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
> index 202496172059..d4d69c0e001e 100644
> --- a/fs/btrfs/ctree.h
> +++ b/fs/btrfs/ctree.h
> @@ -1095,6 +1095,8 @@ struct btrfs_fs_info {
> /* Updates are not protected by any lock */
> struct btrfs_commit_stats commit_stats;
>
> + struct lockdep_map btrfs_trans_num_writers_map;
> +
> #ifdef CONFIG_BTRFS_FS_REF_VERIFY
> spinlock_t ref_verify_lock;
> struct rb_root block_tree;
> @@ -1175,6 +1177,51 @@ enum {
> BTRFS_ROOT_UNFINISHED_DROP,
> };
>
> +/*
> + * Lockdep annotation for wait events.
> + *
> + * @b: The struct where the lockdep map is defined
> + * @lock: The lockdep map corresponding to a wait event
> + *
> + * This macro is used to annotate a wait event. In this case a thread acquires
> + * the lockdep map as writer (exclusive lock) because it has to block until all
> + * the threads that hold the lock as readers signal the condition for the wait
> + * event and release their locks.
> + */
> +#define btrfs_might_wait_for_event(b, lock) \
> + do { \
> + rwsem_acquire(&b->lock##_map, 0, 0, _THIS_IP_); \
> + rwsem_release(&b->lock##_map, _THIS_IP_); \
> + } while (0)
> +
> +/*
> + * Protection for the resource/condition of a wait event.
> + *
> + * @b: The struct where the lockdep map is defined
> + * @lock: The lockdep map corresponding to a wait event
> + *
> + * Many threads can modify the condition for the wait event at the same time
> + * and signal the threads that block on the wait event. The threads that
> + * modify the condition and do the signaling acquire the lock as readers
> + * (shared lock).
> + */
> +#define btrfs_lockdep_acquire(b, lock) \
> + rwsem_acquire_read(&b->lock##_map, 0, 0, _THIS_IP_)
> +
> +/*
> + * Used after signaling the condition for a wait event to release the
> + * lockdep map held by a reader thread.
> + */
> +#define btrfs_lockdep_release(b, lock) \
> + rwsem_release(&b->lock##_map, _THIS_IP_)
> +
> +/* Initialization of the lockdep map */
> +#define btrfs_lockdep_init_map(b, lock) \
> + do { \
> + static struct lock_class_key lock##_key; \
> + lockdep_init_map(&b->lock##_map, #lock, &lock##_key, 0); \
> + } while (0)
> +
> static inline void btrfs_wake_unfinished_drop(struct btrfs_fs_info *fs_info)
> {
> clear_and_wake_up_bit(BTRFS_FS_UNFINISHED_DROPS, &fs_info->flags);
> diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
> index 3fac429cf8a4..38831c730d61 100644
> --- a/fs/btrfs/disk-io.c
> +++ b/fs/btrfs/disk-io.c
> @@ -3074,6 +3074,8 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
> mutex_init(&fs_info->zoned_data_reloc_io_lock);
> seqlock_init(&fs_info->profiles_lock);
>
> + btrfs_lockdep_init_map(fs_info, btrfs_trans_num_writers);
> +
> INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
> INIT_LIST_HEAD(&fs_info->space_info);
> INIT_LIST_HEAD(&fs_info->tree_mod_seq_list);
> diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
> index 0bec10740ad3..d8287ec890bc 100644
> --- a/fs/btrfs/transaction.c
> +++ b/fs/btrfs/transaction.c
> @@ -313,6 +313,7 @@ static noinline int join_transaction(struct btrfs_fs_info *fs_info,
> atomic_inc(&cur_trans->num_writers);
> extwriter_counter_inc(cur_trans, type);
> spin_unlock(&fs_info->trans_lock);
> + btrfs_lockdep_acquire(fs_info, btrfs_trans_num_writers);
> return 0;
> }
> spin_unlock(&fs_info->trans_lock);
> @@ -334,16 +335,20 @@ static noinline int join_transaction(struct btrfs_fs_info *fs_info,
> if (!cur_trans)
> return -ENOMEM;
>
> + btrfs_lockdep_acquire(fs_info, btrfs_trans_num_writers);
> +
> spin_lock(&fs_info->trans_lock);
> if (fs_info->running_transaction) {
> /*
> * someone started a transaction after we unlocked. Make sure
> * to redo the checks above
> */
> + btrfs_lockdep_release(fs_info, btrfs_trans_num_writers);
> kfree(cur_trans);
> goto loop;
> } else if (BTRFS_FS_ERROR(fs_info)) {
> spin_unlock(&fs_info->trans_lock);
> + btrfs_lockdep_release(fs_info, btrfs_trans_num_writers);
> kfree(cur_trans);
> return -EROFS;
> }
> @@ -1022,6 +1027,9 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
> extwriter_counter_dec(cur_trans, trans->type);
>
> cond_wake_up(&cur_trans->writer_wait);
> +
> + btrfs_lockdep_release(info, btrfs_trans_num_writers);
> +
> btrfs_put_transaction(cur_trans);
>
> if (current->journal_info == trans)
> @@ -1994,6 +2002,12 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans, int err)
> if (cur_trans == fs_info->running_transaction) {
> cur_trans->state = TRANS_STATE_COMMIT_DOING;
> spin_unlock(&fs_info->trans_lock);
> +
> + /*
> + * The thread has already released the lockdep map as reader already in
> + * btrfs_commit_transaction().
> + */
> + btrfs_might_wait_for_event(fs_info, btrfs_trans_num_writers);
> wait_event(cur_trans->writer_wait,
> atomic_read(&cur_trans->num_writers) == 1);
>
> @@ -2222,7 +2236,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
>
> btrfs_put_transaction(prev_trans);
> if (ret)
> - goto cleanup_transaction;
> + goto lockdep_release;
> } else {
> spin_unlock(&fs_info->trans_lock);
> }
> @@ -2236,7 +2250,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
> */
> if (BTRFS_FS_ERROR(fs_info)) {
> ret = -EROFS;
> - goto cleanup_transaction;
> + goto lockdep_release;
> }
> }
>
> @@ -2250,19 +2264,21 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
>
> ret = btrfs_start_delalloc_flush(fs_info);
> if (ret)
> - goto cleanup_transaction;
> + goto lockdep_release;
>
> ret = btrfs_run_delayed_items(trans);
> if (ret)
> - goto cleanup_transaction;
> + goto lockdep_release;
>
> wait_event(cur_trans->writer_wait,
> extwriter_counter_read(cur_trans) == 0);
>
> /* some pending stuffs might be added after the previous flush. */
> ret = btrfs_run_delayed_items(trans);
> - if (ret)
> + if (ret) {
> + btrfs_lockdep_release(fs_info, btrfs_trans_num_writers);
> goto cleanup_transaction;
> + }
>
> btrfs_wait_delalloc_flush(fs_info);
>
> @@ -2284,6 +2300,14 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
> add_pending_snapshot(trans);
> cur_trans->state = TRANS_STATE_COMMIT_DOING;
> spin_unlock(&fs_info->trans_lock);
> +
> + /*
> + * The thread has started/joined the transaction thus it holds the lockdep
> + * map as a reader. It has to release it before acquiring the lockdep map
> + * as a writer.
> + */
> + btrfs_lockdep_release(fs_info, btrfs_trans_num_writers);
> + btrfs_might_wait_for_event(fs_info, btrfs_trans_num_writers);
> wait_event(cur_trans->writer_wait,
> atomic_read(&cur_trans->num_writers) == 1);
>
> @@ -2515,6 +2539,9 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
> cleanup_transaction(trans, ret);
>
> return ret;
> +lockdep_release:
> + btrfs_lockdep_release(fs_info, btrfs_trans_num_writers);
> + goto cleanup_transaction;
> }
Could we rename 'lockdep_release' to 'cleanup_transaction_with_lockdep_release',
and put it just before 'cleanup_transaction:'?
Best Regards
Wang Yugui (wangyugui@e16-tech.com)
2022/07/21
^ permalink raw reply [flat|nested] 10+ messages in thread* Re: [PATCH v3 1/6] btrfs: Add a lockdep model for the num_writers wait event
2022-07-21 0:42 ` Wang Yugui
@ 2022-07-21 16:37 ` Ioannis Angelakopoulos
0 siblings, 0 replies; 10+ messages in thread
From: Ioannis Angelakopoulos @ 2022-07-21 16:37 UTC (permalink / raw)
To: Wang Yugui; +Cc: linux-btrfs@vger.kernel.org, Kernel Team
On 7/20/22 5:42 PM, Wang Yugui wrote:
> Hi,
>
>
>> Annotate the num_writers wait event in fs/btrfs/transaction.c with lockdep
>> in order to catch deadlocks involving this wait event.
>>
>> Use a read/write lockdep map for the annotation. A thread starting/joining
>> the transaction acquires the map as a reader when it increments
>> cur_trans->num_writers and it acquires the map as a writer before it
>> blocks on the wait event.
>>
>> Signed-off-by: Ioannis Angelakopoulos <iangelak@fb.com>
>> ---
>> fs/btrfs/ctree.h | 47 ++++++++++++++++++++++++++++++++++++++++++
>> fs/btrfs/disk-io.c | 2 ++
>> fs/btrfs/transaction.c | 37 ++++++++++++++++++++++++++++-----
>> 3 files changed, 81 insertions(+), 5 deletions(-)
>>
>> diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
>> index 202496172059..d4d69c0e001e 100644
>> --- a/fs/btrfs/ctree.h
>> +++ b/fs/btrfs/ctree.h
>> @@ -1095,6 +1095,8 @@ struct btrfs_fs_info {
>> /* Updates are not protected by any lock */
>> struct btrfs_commit_stats commit_stats;
>>
>> + struct lockdep_map btrfs_trans_num_writers_map;
>> +
>> #ifdef CONFIG_BTRFS_FS_REF_VERIFY
>> spinlock_t ref_verify_lock;
>> struct rb_root block_tree;
>> @@ -1175,6 +1177,51 @@ enum {
>> BTRFS_ROOT_UNFINISHED_DROP,
>> };
>>
>> +/*
>> + * Lockdep annotation for wait events.
>> + *
>> + * @b: The struct where the lockdep map is defined
>> + * @lock: The lockdep map corresponding to a wait event
>> + *
>> + * This macro is used to annotate a wait event. In this case a thread acquires
>> + * the lockdep map as writer (exclusive lock) because it has to block until all
>> + * the threads that hold the lock as readers signal the condition for the wait
>> + * event and release their locks.
>> + */
>> +#define btrfs_might_wait_for_event(b, lock) \
>> + do { \
>> + rwsem_acquire(&b->lock##_map, 0, 0, _THIS_IP_); \
>> + rwsem_release(&b->lock##_map, _THIS_IP_); \
>> + } while (0)
>> +
>> +/*
>> + * Protection for the resource/condition of a wait event.
>> + *
>> + * @b: The struct where the lockdep map is defined
>> + * @lock: The lockdep map corresponding to a wait event
>> + *
>> + * Many threads can modify the condition for the wait event at the same time
>> + * and signal the threads that block on the wait event. The threads that
>> + * modify the condition and do the signaling acquire the lock as readers
>> + * (shared lock).
>> + */
>> +#define btrfs_lockdep_acquire(b, lock) \
>> + rwsem_acquire_read(&b->lock##_map, 0, 0, _THIS_IP_)
>> +
>> +/*
>> + * Used after signaling the condition for a wait event to release the
>> + * lockdep map held by a reader thread.
>> + */
>> +#define btrfs_lockdep_release(b, lock) \
>> + rwsem_release(&b->lock##_map, _THIS_IP_)
>> +
>> +/* Initialization of the lockdep map */
>> +#define btrfs_lockdep_init_map(b, lock) \
>> + do { \
>> + static struct lock_class_key lock##_key; \
>> + lockdep_init_map(&b->lock##_map, #lock, &lock##_key, 0); \
>> + } while (0)
>> +
>> static inline void btrfs_wake_unfinished_drop(struct btrfs_fs_info *fs_info)
>> {
>> clear_and_wake_up_bit(BTRFS_FS_UNFINISHED_DROPS, &fs_info->flags);
>> diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
>> index 3fac429cf8a4..38831c730d61 100644
>> --- a/fs/btrfs/disk-io.c
>> +++ b/fs/btrfs/disk-io.c
>> @@ -3074,6 +3074,8 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
>> mutex_init(&fs_info->zoned_data_reloc_io_lock);
>> seqlock_init(&fs_info->profiles_lock);
>>
>> + btrfs_lockdep_init_map(fs_info, btrfs_trans_num_writers);
>> +
>> INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
>> INIT_LIST_HEAD(&fs_info->space_info);
>> INIT_LIST_HEAD(&fs_info->tree_mod_seq_list);
>> diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
>> index 0bec10740ad3..d8287ec890bc 100644
>> --- a/fs/btrfs/transaction.c
>> +++ b/fs/btrfs/transaction.c
>> @@ -313,6 +313,7 @@ static noinline int join_transaction(struct btrfs_fs_info *fs_info,
>> atomic_inc(&cur_trans->num_writers);
>> extwriter_counter_inc(cur_trans, type);
>> spin_unlock(&fs_info->trans_lock);
>> + btrfs_lockdep_acquire(fs_info, btrfs_trans_num_writers);
>> return 0;
>> }
>> spin_unlock(&fs_info->trans_lock);
>> @@ -334,16 +335,20 @@ static noinline int join_transaction(struct btrfs_fs_info *fs_info,
>> if (!cur_trans)
>> return -ENOMEM;
>>
>> + btrfs_lockdep_acquire(fs_info, btrfs_trans_num_writers);
>> +
>> spin_lock(&fs_info->trans_lock);
>> if (fs_info->running_transaction) {
>> /*
>> * someone started a transaction after we unlocked. Make sure
>> * to redo the checks above
>> */
>> + btrfs_lockdep_release(fs_info, btrfs_trans_num_writers);
>> kfree(cur_trans);
>> goto loop;
>> } else if (BTRFS_FS_ERROR(fs_info)) {
>> spin_unlock(&fs_info->trans_lock);
>> + btrfs_lockdep_release(fs_info, btrfs_trans_num_writers);
>> kfree(cur_trans);
>> return -EROFS;
>> }
>> @@ -1022,6 +1027,9 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
>> extwriter_counter_dec(cur_trans, trans->type);
>>
>> cond_wake_up(&cur_trans->writer_wait);
>> +
>> + btrfs_lockdep_release(info, btrfs_trans_num_writers);
>> +
>> btrfs_put_transaction(cur_trans);
>>
>> if (current->journal_info == trans)
>> @@ -1994,6 +2002,12 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans, int err)
>> if (cur_trans == fs_info->running_transaction) {
>> cur_trans->state = TRANS_STATE_COMMIT_DOING;
>> spin_unlock(&fs_info->trans_lock);
>> +
>> + /*
>> + * The thread has already released the lockdep map as reader already in
>> + * btrfs_commit_transaction().
>> + */
>> + btrfs_might_wait_for_event(fs_info, btrfs_trans_num_writers);
>> wait_event(cur_trans->writer_wait,
>> atomic_read(&cur_trans->num_writers) == 1);
>>
>> @@ -2222,7 +2236,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
>>
>> btrfs_put_transaction(prev_trans);
>> if (ret)
>> - goto cleanup_transaction;
>> + goto lockdep_release;
>> } else {
>> spin_unlock(&fs_info->trans_lock);
>> }
>> @@ -2236,7 +2250,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
>> */
>> if (BTRFS_FS_ERROR(fs_info)) {
>> ret = -EROFS;
>> - goto cleanup_transaction;
>> + goto lockdep_release;
>> }
>> }
>>
>> @@ -2250,19 +2264,21 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
>>
>> ret = btrfs_start_delalloc_flush(fs_info);
>> if (ret)
>> - goto cleanup_transaction;
>> + goto lockdep_release;
>>
>> ret = btrfs_run_delayed_items(trans);
>> if (ret)
>> - goto cleanup_transaction;
>> + goto lockdep_release;
>>
>> wait_event(cur_trans->writer_wait,
>> extwriter_counter_read(cur_trans) == 0);
>>
>> /* some pending stuffs might be added after the previous flush. */
>> ret = btrfs_run_delayed_items(trans);
>> - if (ret)
>> + if (ret) {
>> + btrfs_lockdep_release(fs_info, btrfs_trans_num_writers);
>> goto cleanup_transaction;
>> + }
>>
>> btrfs_wait_delalloc_flush(fs_info);
>>
>> @@ -2284,6 +2300,14 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
>> add_pending_snapshot(trans);
>> cur_trans->state = TRANS_STATE_COMMIT_DOING;
>> spin_unlock(&fs_info->trans_lock);
>> +
>> + /*
>> + * The thread has started/joined the transaction thus it holds the lockdep
>> + * map as a reader. It has to release it before acquiring the lockdep map
>> + * as a writer.
>> + */
>> + btrfs_lockdep_release(fs_info, btrfs_trans_num_writers);
>> + btrfs_might_wait_for_event(fs_info, btrfs_trans_num_writers);
>> wait_event(cur_trans->writer_wait,
>> atomic_read(&cur_trans->num_writers) == 1);
>>
>> @@ -2515,6 +2539,9 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
>> cleanup_transaction(trans, ret);
>>
>> return ret;
>> +lockdep_release:
>> + btrfs_lockdep_release(fs_info, btrfs_trans_num_writers);
>> + goto cleanup_transaction;
>> }
>
>
> Could we rename 'lockdep_release' to 'cleanup_transaction_with_lockdep_release',
> and put it just before 'cleanup_transaction:'?
>
> Best Regards
> Wang Yugui (wangyugui@e16-tech.com)
> 2022/07/21
>
Unfortunately no, since there are error paths within
btrfs_commit_transaction() that jump to labels prior to
cleanup_transaction after the btrfs_trans_num_writers lock is already
released. Moving the lockdep_release label above cleanup_transaction
would result in lockdep complaining about double lock release.
Thanks,
Ioannis
>
>
^ permalink raw reply [flat|nested] 10+ messages in thread
* [PATCH v3 2/6] btrfs: Add a lockdep model for the num_extwriters wait event
2022-07-20 23:38 [PATCH v3 0/6] btrfs: Annotate wait events with lockdep Ioannis Angelakopoulos
2022-07-20 23:38 ` [PATCH v3 1/6] btrfs: Add a lockdep model for the num_writers wait event Ioannis Angelakopoulos
@ 2022-07-20 23:38 ` Ioannis Angelakopoulos
2022-07-20 23:38 ` [PATCH v3 3/6] btrfs: Add lockdep models for the transaction states wait events Ioannis Angelakopoulos
` (4 subsequent siblings)
6 siblings, 0 replies; 10+ messages in thread
From: Ioannis Angelakopoulos @ 2022-07-20 23:38 UTC (permalink / raw)
To: linux-btrfs, kernel-team
Similarly to the num_writers wait event in fs/btrfs/transaction.c add a
lockdep annotation for the num_extwriters wait event.
Use a read/write lockdep map for the annotation. A thread starting/joining
the transaction acquires the map as a reader when it increments
cur_trans->num_writers and it acquires the map as a writer before it
blocks on the wait event.
Signed-off-by: Ioannis Angelakopoulos <iangelak@fb.com>
---
fs/btrfs/ctree.h | 1 +
fs/btrfs/disk-io.c | 1 +
fs/btrfs/transaction.c | 13 +++++++++++++
3 files changed, 15 insertions(+)
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index d4d69c0e001e..5fcdd54994f9 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1096,6 +1096,7 @@ struct btrfs_fs_info {
struct btrfs_commit_stats commit_stats;
struct lockdep_map btrfs_trans_num_writers_map;
+ struct lockdep_map btrfs_trans_num_extwriters_map;
#ifdef CONFIG_BTRFS_FS_REF_VERIFY
spinlock_t ref_verify_lock;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 38831c730d61..43330a92e7ae 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3075,6 +3075,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
seqlock_init(&fs_info->profiles_lock);
btrfs_lockdep_init_map(fs_info, btrfs_trans_num_writers);
+ btrfs_lockdep_init_map(fs_info, btrfs_trans_num_extwriters);
INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
INIT_LIST_HEAD(&fs_info->space_info);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index d8287ec890bc..c9751a05c029 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -314,6 +314,7 @@ static noinline int join_transaction(struct btrfs_fs_info *fs_info,
extwriter_counter_inc(cur_trans, type);
spin_unlock(&fs_info->trans_lock);
btrfs_lockdep_acquire(fs_info, btrfs_trans_num_writers);
+ btrfs_lockdep_acquire(fs_info, btrfs_trans_num_extwriters);
return 0;
}
spin_unlock(&fs_info->trans_lock);
@@ -336,6 +337,7 @@ static noinline int join_transaction(struct btrfs_fs_info *fs_info,
return -ENOMEM;
btrfs_lockdep_acquire(fs_info, btrfs_trans_num_writers);
+ btrfs_lockdep_acquire(fs_info, btrfs_trans_num_extwriters);
spin_lock(&fs_info->trans_lock);
if (fs_info->running_transaction) {
@@ -343,11 +345,13 @@ static noinline int join_transaction(struct btrfs_fs_info *fs_info,
* someone started a transaction after we unlocked. Make sure
* to redo the checks above
*/
+ btrfs_lockdep_release(fs_info, btrfs_trans_num_extwriters);
btrfs_lockdep_release(fs_info, btrfs_trans_num_writers);
kfree(cur_trans);
goto loop;
} else if (BTRFS_FS_ERROR(fs_info)) {
spin_unlock(&fs_info->trans_lock);
+ btrfs_lockdep_release(fs_info, btrfs_trans_num_extwriters);
btrfs_lockdep_release(fs_info, btrfs_trans_num_writers);
kfree(cur_trans);
return -EROFS;
@@ -1028,6 +1032,7 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
cond_wake_up(&cur_trans->writer_wait);
+ btrfs_lockdep_release(info, btrfs_trans_num_extwriters);
btrfs_lockdep_release(info, btrfs_trans_num_writers);
btrfs_put_transaction(cur_trans);
@@ -2270,6 +2275,13 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
if (ret)
goto lockdep_release;
+ /*
+ * The thread has started/joined the transaction thus it holds the lockdep
+ * map as a reader. It has to release it before acquiring the lockdep map
+ * as a writer.
+ */
+ btrfs_lockdep_release(fs_info, btrfs_trans_num_extwriters);
+ btrfs_might_wait_for_event(fs_info, btrfs_trans_num_extwriters);
wait_event(cur_trans->writer_wait,
extwriter_counter_read(cur_trans) == 0);
@@ -2540,6 +2552,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
return ret;
lockdep_release:
+ btrfs_lockdep_release(fs_info, btrfs_trans_num_extwriters);
btrfs_lockdep_release(fs_info, btrfs_trans_num_writers);
goto cleanup_transaction;
}
--
2.30.2
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH v3 3/6] btrfs: Add lockdep models for the transaction states wait events
2022-07-20 23:38 [PATCH v3 0/6] btrfs: Annotate wait events with lockdep Ioannis Angelakopoulos
2022-07-20 23:38 ` [PATCH v3 1/6] btrfs: Add a lockdep model for the num_writers wait event Ioannis Angelakopoulos
2022-07-20 23:38 ` [PATCH v3 2/6] btrfs: Add a lockdep model for the num_extwriters " Ioannis Angelakopoulos
@ 2022-07-20 23:38 ` Ioannis Angelakopoulos
2022-07-20 23:38 ` [PATCH v3 4/6] btrfs: Add a lockdep model for the pending_ordered wait event Ioannis Angelakopoulos
` (3 subsequent siblings)
6 siblings, 0 replies; 10+ messages in thread
From: Ioannis Angelakopoulos @ 2022-07-20 23:38 UTC (permalink / raw)
To: linux-btrfs, kernel-team
Add a lockdep annotation for the transaction states that have wait
events; 1) TRANS_STATE_COMMIT_START, 2) TRANS_STATE_UNBLOCKED, 3)
TRANS_STATE_SUPER_COMMITTED, and 4) TRANS_STATE_COMPLETED in
fs/btrfs/transaction.c.
With the exception of the lockdep annotation for TRANS_STATE_COMMIT_START
the transaction thread has to acquire the lockdep maps for the transaction
states as reader after the lockdep map for num_writers is released so that
lockdep does not complain.
Signed-off-by: Ioannis Angelakopoulos <iangelak@fb.com>
---
fs/btrfs/ctree.h | 32 ++++++++++++++++++++++++
fs/btrfs/disk-io.c | 8 ++++++
fs/btrfs/transaction.c | 55 +++++++++++++++++++++++++++++++++++++-----
3 files changed, 89 insertions(+), 6 deletions(-)
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 5fcdd54994f9..8f86e8d5e810 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1097,6 +1097,7 @@ struct btrfs_fs_info {
struct lockdep_map btrfs_trans_num_writers_map;
struct lockdep_map btrfs_trans_num_extwriters_map;
+ struct lockdep_map btrfs_state_change_map[4];
#ifdef CONFIG_BTRFS_FS_REF_VERIFY
spinlock_t ref_verify_lock;
@@ -1178,6 +1179,13 @@ enum {
BTRFS_ROOT_UNFINISHED_DROP,
};
+enum btrfs_lockdep_trans_states {
+ BTRFS_LOCKDEP_TRANS_COMMIT_START,
+ BTRFS_LOCKDEP_TRANS_UNBLOCKED,
+ BTRFS_LOCKDEP_TRANS_SUPER_COMMITTED,
+ BTRFS_LOCKDEP_TRANS_COMPLETED,
+};
+
/*
* Lockdep annotation for wait events.
*
@@ -1216,6 +1224,22 @@ enum {
#define btrfs_lockdep_release(b, lock) \
rwsem_release(&b->lock##_map, _THIS_IP_)
+/*
+ * Macros for the transaction states wait events, similar to the generic wait
+ * event macros.
+ */
+#define btrfs_might_wait_for_state(b, i) \
+ do { \
+ rwsem_acquire(&b->btrfs_state_change_map[i], 0, 0, _THIS_IP_); \
+ rwsem_release(&b->btrfs_state_change_map[i], _THIS_IP_); \
+ } while (0)
+
+#define btrfs_trans_state_lockdep_acquire(b, i) \
+ rwsem_acquire_read(&b->btrfs_state_change_map[i], 0, 0, _THIS_IP_)
+
+#define btrfs_trans_state_lockdep_release(b, i) \
+ rwsem_release(&b->btrfs_state_change_map[i], _THIS_IP_)
+
/* Initialization of the lockdep map */
#define btrfs_lockdep_init_map(b, lock) \
do { \
@@ -1223,6 +1247,14 @@ enum {
lockdep_init_map(&b->lock##_map, #lock, &lock##_key, 0); \
} while (0)
+/* Initialization of the transaction states lockdep maps. */
+#define btrfs_state_lockdep_init_map(b, lock, state) \
+ do { \
+ static struct lock_class_key lock##_key; \
+ lockdep_init_map(&b->btrfs_state_change_map[state], #lock, \
+ &lock##_key, 0); \
+ } while (0)
+
static inline void btrfs_wake_unfinished_drop(struct btrfs_fs_info *fs_info)
{
clear_and_wake_up_bit(BTRFS_FS_UNFINISHED_DROPS, &fs_info->flags);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 43330a92e7ae..b2ceaa65eed1 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3076,6 +3076,14 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
btrfs_lockdep_init_map(fs_info, btrfs_trans_num_writers);
btrfs_lockdep_init_map(fs_info, btrfs_trans_num_extwriters);
+ btrfs_state_lockdep_init_map(fs_info, btrfs_trans_commit_start,
+ BTRFS_LOCKDEP_TRANS_COMMIT_START);
+ btrfs_state_lockdep_init_map(fs_info, btrfs_trans_unblocked,
+ BTRFS_LOCKDEP_TRANS_UNBLOCKED);
+ btrfs_state_lockdep_init_map(fs_info, btrfs_trans_super_committed,
+ BTRFS_LOCKDEP_TRANS_SUPER_COMMITTED);
+ btrfs_state_lockdep_init_map(fs_info, btrfs_trans_completed,
+ BTRFS_LOCKDEP_TRANS_COMPLETED);
INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
INIT_LIST_HEAD(&fs_info->space_info);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index c9751a05c029..f2ee407564da 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -550,6 +550,7 @@ static void wait_current_trans(struct btrfs_fs_info *fs_info)
refcount_inc(&cur_trans->use_count);
spin_unlock(&fs_info->trans_lock);
+ btrfs_might_wait_for_state(fs_info, BTRFS_LOCKDEP_TRANS_UNBLOCKED);
wait_event(fs_info->transaction_wait,
cur_trans->state >= TRANS_STATE_UNBLOCKED ||
TRANS_ABORTED(cur_trans));
@@ -868,6 +869,16 @@ static noinline void wait_for_commit(struct btrfs_transaction *commit,
u64 transid = commit->transid;
bool put = false;
+ /*
+ * At the moment this function is called with min_state either being
+ * TRANS_STATE_COMPLETED or TRANS_STATE_SUPER_COMMITTED
+ */
+ if (min_state == TRANS_STATE_COMPLETED)
+ btrfs_might_wait_for_state(fs_info, BTRFS_LOCKDEP_TRANS_COMPLETED);
+ else
+ btrfs_might_wait_for_state(fs_info,
+ BTRFS_LOCKDEP_TRANS_SUPER_COMMITTED);
+
while (1) {
wait_event(commit->commit_wait, commit->state >= min_state);
if (put)
@@ -1980,6 +1991,7 @@ void btrfs_commit_transaction_async(struct btrfs_trans_handle *trans)
* Wait for the current transaction commit to start and block
* subsequent transaction joins
*/
+ btrfs_might_wait_for_state(fs_info, BTRFS_LOCKDEP_TRANS_COMMIT_START);
wait_event(fs_info->transaction_blocked_wait,
cur_trans->state >= TRANS_STATE_COMMIT_START ||
TRANS_ABORTED(cur_trans));
@@ -2137,14 +2149,16 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
ktime_t interval;
ASSERT(refcount_read(&trans->use_count) == 1);
+ btrfs_trans_state_lockdep_acquire(fs_info,
+ BTRFS_LOCKDEP_TRANS_COMMIT_START);
/* Stop the commit early if ->aborted is set */
if (TRANS_ABORTED(cur_trans)) {
ret = cur_trans->aborted;
- btrfs_end_transaction(trans);
- return ret;
+ goto lockdep_trans_commit_start_release;
}
+
btrfs_trans_release_metadata(trans);
trans->block_rsv = NULL;
@@ -2160,8 +2174,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
*/
ret = btrfs_run_delayed_refs(trans, 0);
if (ret) {
- btrfs_end_transaction(trans);
- return ret;
+ goto lockdep_trans_commit_start_release;
}
}
@@ -2192,8 +2205,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
if (run_it) {
ret = btrfs_start_dirty_block_groups(trans);
if (ret) {
- btrfs_end_transaction(trans);
- return ret;
+ goto lockdep_trans_commit_start_release;
}
}
}
@@ -2209,6 +2221,9 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
if (trans->in_fsync)
want_state = TRANS_STATE_SUPER_COMMITTED;
+
+ btrfs_trans_state_lockdep_release(fs_info,
+ BTRFS_LOCKDEP_TRANS_COMMIT_START);
ret = btrfs_end_transaction(trans);
wait_for_commit(cur_trans, want_state);
@@ -2222,6 +2237,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
cur_trans->state = TRANS_STATE_COMMIT_START;
wake_up(&fs_info->transaction_blocked_wait);
+ btrfs_trans_state_lockdep_release(fs_info,
+ BTRFS_LOCKDEP_TRANS_COMMIT_START);
if (cur_trans->list.prev != &fs_info->trans_list) {
enum btrfs_trans_state want_state = TRANS_STATE_COMPLETED;
@@ -2323,6 +2340,17 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
wait_event(cur_trans->writer_wait,
atomic_read(&cur_trans->num_writers) == 1);
+ /*
+ * Make lockdep happy by acquiring the state locks after
+ * btrfs_trans_num_writers is released. If we acquired the state locks
+ * before releasing the btrfs_trans_num_writers lock then lockdep would
+ * complain because we did not follow the reverse order unlocking rule.
+ */
+ btrfs_trans_state_lockdep_acquire(fs_info, BTRFS_LOCKDEP_TRANS_COMPLETED);
+ btrfs_trans_state_lockdep_acquire(fs_info,
+ BTRFS_LOCKDEP_TRANS_SUPER_COMMITTED);
+ btrfs_trans_state_lockdep_acquire(fs_info, BTRFS_LOCKDEP_TRANS_UNBLOCKED);
+
/*
* We've started the commit, clear the flag in case we were triggered to
* do an async commit but somebody else started before the transaction
@@ -2332,6 +2360,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
if (TRANS_ABORTED(cur_trans)) {
ret = cur_trans->aborted;
+ btrfs_trans_state_lockdep_release(fs_info,
+ BTRFS_LOCKDEP_TRANS_UNBLOCKED);
goto scrub_continue;
}
/*
@@ -2466,6 +2496,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
mutex_unlock(&fs_info->reloc_mutex);
wake_up(&fs_info->transaction_wait);
+ btrfs_trans_state_lockdep_release(fs_info, BTRFS_LOCKDEP_TRANS_UNBLOCKED);
ret = btrfs_write_and_wait_transaction(trans);
if (ret) {
@@ -2497,6 +2528,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
*/
cur_trans->state = TRANS_STATE_SUPER_COMMITTED;
wake_up(&cur_trans->commit_wait);
+ btrfs_trans_state_lockdep_release(fs_info,
+ BTRFS_LOCKDEP_TRANS_SUPER_COMMITTED);
btrfs_finish_extent_commit(trans);
@@ -2510,6 +2543,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
*/
cur_trans->state = TRANS_STATE_COMPLETED;
wake_up(&cur_trans->commit_wait);
+ btrfs_trans_state_lockdep_release(fs_info, BTRFS_LOCKDEP_TRANS_COMPLETED);
spin_lock(&fs_info->trans_lock);
list_del_init(&cur_trans->list);
@@ -2538,7 +2572,11 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
unlock_reloc:
mutex_unlock(&fs_info->reloc_mutex);
+ btrfs_trans_state_lockdep_release(fs_info, BTRFS_LOCKDEP_TRANS_UNBLOCKED);
scrub_continue:
+ btrfs_trans_state_lockdep_release(fs_info,
+ BTRFS_LOCKDEP_TRANS_SUPER_COMMITTED);
+ btrfs_trans_state_lockdep_release(fs_info, BTRFS_LOCKDEP_TRANS_COMPLETED);
btrfs_scrub_continue(fs_info);
cleanup_transaction:
btrfs_trans_release_metadata(trans);
@@ -2555,6 +2593,11 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
btrfs_lockdep_release(fs_info, btrfs_trans_num_extwriters);
btrfs_lockdep_release(fs_info, btrfs_trans_num_writers);
goto cleanup_transaction;
+lockdep_trans_commit_start_release:
+ btrfs_trans_state_lockdep_release(fs_info,
+ BTRFS_LOCKDEP_TRANS_COMMIT_START);
+ btrfs_end_transaction(trans);
+ return ret;
}
/*
--
2.30.2
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH v3 4/6] btrfs: Add a lockdep model for the pending_ordered wait event
2022-07-20 23:38 [PATCH v3 0/6] btrfs: Annotate wait events with lockdep Ioannis Angelakopoulos
` (2 preceding siblings ...)
2022-07-20 23:38 ` [PATCH v3 3/6] btrfs: Add lockdep models for the transaction states wait events Ioannis Angelakopoulos
@ 2022-07-20 23:38 ` Ioannis Angelakopoulos
2022-07-20 23:38 ` [PATCH v3 5/6] btrfs: Change the lockdep class of struct inode's invalidate_lock Ioannis Angelakopoulos
` (2 subsequent siblings)
6 siblings, 0 replies; 10+ messages in thread
From: Ioannis Angelakopoulos @ 2022-07-20 23:38 UTC (permalink / raw)
To: linux-btrfs, kernel-team
In contrast to the num_writers and num_extwriters wait events, the
condition for the pending ordered wait event is signaled in a different
context from the wait event itself. The condition signaling occurs in
btrfs_remove_ordered_extent() in fs/btrfs/ordered-data.c while the wait
event is implemented in btrfs_commit_transaction() in
fs/btrfs/transaction.c
Thus the thread signaling the condition has to acquire the lockdep map as a
reader at the start of btrfs_remove_ordered_extent() and release it after
it has signaled the condition. In this case some dependencies might be left
out due to the placement of the annotation, but it is better than no
annotation at all.
Signed-off-by: Ioannis Angelakopoulos <iangelak@fb.com>
---
fs/btrfs/ctree.h | 1 +
fs/btrfs/disk-io.c | 1 +
fs/btrfs/ordered-data.c | 3 +++
fs/btrfs/transaction.c | 1 +
4 files changed, 6 insertions(+)
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 8f86e8d5e810..d83950ac10ab 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1098,6 +1098,7 @@ struct btrfs_fs_info {
struct lockdep_map btrfs_trans_num_writers_map;
struct lockdep_map btrfs_trans_num_extwriters_map;
struct lockdep_map btrfs_state_change_map[4];
+ struct lockdep_map btrfs_trans_pending_ordered_map;
#ifdef CONFIG_BTRFS_FS_REF_VERIFY
spinlock_t ref_verify_lock;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index b2ceaa65eed1..07c0fd9af83f 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3076,6 +3076,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
btrfs_lockdep_init_map(fs_info, btrfs_trans_num_writers);
btrfs_lockdep_init_map(fs_info, btrfs_trans_num_extwriters);
+ btrfs_lockdep_init_map(fs_info, btrfs_trans_pending_ordered);
btrfs_state_lockdep_init_map(fs_info, btrfs_trans_commit_start,
BTRFS_LOCKDEP_TRANS_COMMIT_START);
btrfs_state_lockdep_init_map(fs_info, btrfs_trans_unblocked,
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 1952ac85222c..2a4cb6db42d1 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -525,6 +525,7 @@ void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode,
struct rb_node *node;
bool pending;
+ btrfs_lockdep_acquire(fs_info, btrfs_trans_pending_ordered);
/* This is paired with btrfs_add_ordered_extent. */
spin_lock(&btrfs_inode->lock);
btrfs_mod_outstanding_extents(btrfs_inode, -1);
@@ -580,6 +581,8 @@ void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode,
}
}
+ btrfs_lockdep_release(fs_info, btrfs_trans_pending_ordered);
+
spin_lock(&root->ordered_extent_lock);
list_del_init(&entry->root_extent_list);
root->nr_ordered_extents--;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index f2ee407564da..33c14ff4a726 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -2316,6 +2316,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
* transaction. Otherwise if this transaction commits before the ordered
* extents complete we lose logged data after a power failure.
*/
+ btrfs_might_wait_for_event(fs_info, btrfs_trans_pending_ordered);
wait_event(cur_trans->pending_wait,
atomic_read(&cur_trans->pending_ordered) == 0);
--
2.30.2
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH v3 5/6] btrfs: Change the lockdep class of struct inode's invalidate_lock
2022-07-20 23:38 [PATCH v3 0/6] btrfs: Annotate wait events with lockdep Ioannis Angelakopoulos
` (3 preceding siblings ...)
2022-07-20 23:38 ` [PATCH v3 4/6] btrfs: Add a lockdep model for the pending_ordered wait event Ioannis Angelakopoulos
@ 2022-07-20 23:38 ` Ioannis Angelakopoulos
2022-07-20 23:38 ` [PATCH v3 6/6] btrfs: Add a lockdep model for the ordered extents wait event Ioannis Angelakopoulos
2022-07-22 13:36 ` [PATCH v3 0/6] btrfs: Annotate wait events with lockdep Josef Bacik
6 siblings, 0 replies; 10+ messages in thread
From: Ioannis Angelakopoulos @ 2022-07-20 23:38 UTC (permalink / raw)
To: linux-btrfs, kernel-team
Reinitialize the class of the lockdep map for
inode->mapping->invalidate_lock in load_free_space_cache() function in
fs/btrfs/free-space-cache.c This will prevent lockdep from producing false
positives related to execution paths that make use of free space inodes and
paths that make use of normal inodes.
Specifically, with this change lockdep will create separate lock
dependencies that include the invalidate_lock, in the case that free space
inodes are used and in the case that normal inodes are used.
Signed-off-by: Ioannis Angelakopoulos <iangelak@fb.com>
---
fs/btrfs/free-space-cache.c | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 996da650ecdc..a2b2329ae558 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -914,6 +914,8 @@ static int copy_free_space_cache(struct btrfs_block_group *block_group,
return ret;
}
+static struct lock_class_key btrfs_free_space_inode_key;
+
int load_free_space_cache(struct btrfs_block_group *block_group)
{
struct btrfs_fs_info *fs_info = block_group->fs_info;
@@ -924,6 +926,7 @@ int load_free_space_cache(struct btrfs_block_group *block_group)
int ret = 0;
bool matched;
u64 used = block_group->used;
+ struct address_space *mapping;
/*
* Because we could potentially discard our loaded free space, we want
@@ -983,6 +986,14 @@ int load_free_space_cache(struct btrfs_block_group *block_group)
}
spin_unlock(&block_group->lock);
+ /*
+ * Reinitialize the class of the inode->mapping->invalidate_lock for free
+ * space inodes to prevent false positives related to locks for normal
+ * inodes.
+ */
+ mapping = &inode->i_data;
+ lockdep_set_class(&mapping->invalidate_lock, &btrfs_free_space_inode_key);
+
ret = __load_free_space_cache(fs_info->tree_root, inode, &tmp_ctl,
path, block_group->start);
btrfs_free_path(path);
--
2.30.2
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH v3 6/6] btrfs: Add a lockdep model for the ordered extents wait event
2022-07-20 23:38 [PATCH v3 0/6] btrfs: Annotate wait events with lockdep Ioannis Angelakopoulos
` (4 preceding siblings ...)
2022-07-20 23:38 ` [PATCH v3 5/6] btrfs: Change the lockdep class of struct inode's invalidate_lock Ioannis Angelakopoulos
@ 2022-07-20 23:38 ` Ioannis Angelakopoulos
2022-07-22 13:36 ` [PATCH v3 0/6] btrfs: Annotate wait events with lockdep Josef Bacik
6 siblings, 0 replies; 10+ messages in thread
From: Ioannis Angelakopoulos @ 2022-07-20 23:38 UTC (permalink / raw)
To: linux-btrfs, kernel-team
This wait event is very similar to the pending ordered wait event in the
sense that it occurs in a different context than the condition signaling
for the event. The signaling occurs in btrfs_remove_ordered_extent() while
the wait event is implemented in btrfs_start_ordered_extent() in
fs/btrfs/ordered-data.c
However, in this case a thread must not acquire the lockdep map for the
ordered extents wait event when the ordered extent is related to a free
space inode. That is because lockdep creates dependencies between locks
acquired both in execution paths related to normal inodes and paths related
to free space inodes, thus leading to false positives.
Signed-off-by: Ioannis Angelakopoulos <iangelak@fb.com>
---
fs/btrfs/ctree.h | 1 +
fs/btrfs/disk-io.c | 1 +
fs/btrfs/inode.c | 13 +++++++++++++
fs/btrfs/ordered-data.c | 18 ++++++++++++++++++
4 files changed, 33 insertions(+)
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index d83950ac10ab..301bf4308e9b 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1099,6 +1099,7 @@ struct btrfs_fs_info {
struct lockdep_map btrfs_trans_num_extwriters_map;
struct lockdep_map btrfs_state_change_map[4];
struct lockdep_map btrfs_trans_pending_ordered_map;
+ struct lockdep_map btrfs_ordered_extent_map;
#ifdef CONFIG_BTRFS_FS_REF_VERIFY
spinlock_t ref_verify_lock;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 07c0fd9af83f..9325cfa57a25 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3077,6 +3077,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
btrfs_lockdep_init_map(fs_info, btrfs_trans_num_writers);
btrfs_lockdep_init_map(fs_info, btrfs_trans_num_extwriters);
btrfs_lockdep_init_map(fs_info, btrfs_trans_pending_ordered);
+ btrfs_lockdep_init_map(fs_info, btrfs_ordered_extent);
btrfs_state_lockdep_init_map(fs_info, btrfs_trans_commit_start,
BTRFS_LOCKDEP_TRANS_COMMIT_START);
btrfs_state_lockdep_init_map(fs_info, btrfs_trans_unblocked,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index f20740812e5b..36f973ffbd26 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3223,6 +3223,8 @@ int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
clear_bits |= EXTENT_DELALLOC_NEW;
freespace_inode = btrfs_is_free_space_inode(inode);
+ if (!freespace_inode)
+ btrfs_lockdep_acquire(fs_info, btrfs_ordered_extent);
if (test_bit(BTRFS_ORDERED_IOERR, &ordered_extent->flags)) {
ret = -EIO;
@@ -8952,6 +8954,7 @@ void btrfs_destroy_inode(struct inode *vfs_inode)
struct btrfs_ordered_extent *ordered;
struct btrfs_inode *inode = BTRFS_I(vfs_inode);
struct btrfs_root *root = inode->root;
+ bool freespace_inode;
WARN_ON(!hlist_empty(&vfs_inode->i_dentry));
WARN_ON(vfs_inode->i_data.nrpages);
@@ -8973,6 +8976,12 @@ void btrfs_destroy_inode(struct inode *vfs_inode)
if (!root)
return;
+ /*
+ * If this is a free space inode do not take the ordered extents lockdep
+ * map.
+ */
+ freespace_inode = btrfs_is_free_space_inode(inode);
+
while (1) {
ordered = btrfs_lookup_first_ordered_extent(inode, (u64)-1);
if (!ordered)
@@ -8981,6 +8990,10 @@ void btrfs_destroy_inode(struct inode *vfs_inode)
btrfs_err(root->fs_info,
"found ordered extent %llu %llu on inode cleanup",
ordered->file_offset, ordered->num_bytes);
+
+ if (!freespace_inode)
+ btrfs_lockdep_acquire(root->fs_info, btrfs_ordered_extent);
+
btrfs_remove_ordered_extent(inode, ordered);
btrfs_put_ordered_extent(ordered);
btrfs_put_ordered_extent(ordered);
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 2a4cb6db42d1..eb24a6d20ff8 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -524,6 +524,13 @@ void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode,
struct btrfs_fs_info *fs_info = root->fs_info;
struct rb_node *node;
bool pending;
+ bool freespace_inode;
+
+ /*
+ * If this is a free space inode the thread has not acquired the ordered
+ * extents lockdep map.
+ */
+ freespace_inode = btrfs_is_free_space_inode(btrfs_inode);
btrfs_lockdep_acquire(fs_info, btrfs_trans_pending_ordered);
/* This is paired with btrfs_add_ordered_extent. */
@@ -597,6 +604,8 @@ void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode,
}
spin_unlock(&root->ordered_extent_lock);
wake_up(&entry->wait);
+ if (!freespace_inode)
+ btrfs_lockdep_release(fs_info, btrfs_ordered_extent);
}
static void btrfs_run_ordered_extent_work(struct btrfs_work *work)
@@ -715,9 +724,16 @@ void btrfs_start_ordered_extent(struct btrfs_ordered_extent *entry, int wait)
u64 start = entry->file_offset;
u64 end = start + entry->num_bytes - 1;
struct btrfs_inode *inode = BTRFS_I(entry->inode);
+ bool freespace_inode;
trace_btrfs_ordered_extent_start(inode, entry);
+ /*
+ * If this is a free space inode do not take the ordered extents lockdep
+ * map.
+ */
+ freespace_inode = btrfs_is_free_space_inode(inode);
+
/*
* pages in the range can be dirty, clean or writeback. We
* start IO on any dirty ones so the wait doesn't stall waiting
@@ -726,6 +742,8 @@ void btrfs_start_ordered_extent(struct btrfs_ordered_extent *entry, int wait)
if (!test_bit(BTRFS_ORDERED_DIRECT, &entry->flags))
filemap_fdatawrite_range(inode->vfs_inode.i_mapping, start, end);
if (wait) {
+ if (!freespace_inode)
+ btrfs_might_wait_for_event(inode->root->fs_info, btrfs_ordered_extent);
wait_event(entry->wait, test_bit(BTRFS_ORDERED_COMPLETE,
&entry->flags));
}
--
2.30.2
^ permalink raw reply related [flat|nested] 10+ messages in thread* Re: [PATCH v3 0/6] btrfs: Annotate wait events with lockdep
2022-07-20 23:38 [PATCH v3 0/6] btrfs: Annotate wait events with lockdep Ioannis Angelakopoulos
` (5 preceding siblings ...)
2022-07-20 23:38 ` [PATCH v3 6/6] btrfs: Add a lockdep model for the ordered extents wait event Ioannis Angelakopoulos
@ 2022-07-22 13:36 ` Josef Bacik
6 siblings, 0 replies; 10+ messages in thread
From: Josef Bacik @ 2022-07-22 13:36 UTC (permalink / raw)
To: Ioannis Angelakopoulos; +Cc: linux-btrfs, kernel-team
On Wed, Jul 20, 2022 at 04:38:13PM -0700, Ioannis Angelakopoulos wrote:
> Hello,
>
> With this patch series we annotate wait events in btrfs with lockdep to
> catch deadlocks involving these wait events.
>
> Recently the btrfs developers fixed a non trivial deadlock involving
> wait events
> https://lore.kernel.org/linux-btrfs/20220614131413.GJ20633@twin.jikos.cz/
>
> Currently lockdep is unable to catch these deadlocks since it does not
> support wait events by default.
>
> With our lockdep annotations we train lockdep to track these wait events
> and catch more potential deadlocks.
>
> Specifically, we annotate the below wait events in fs/btrfs/transaction.c
> and in fs/btrfs/ordered-data.c:
>
> 1) The num_writers wait event
> 2) The num_extwriters wait event
> 3) The transaction states wait events
> 4) The pending_ordered wait event
> 5) The ordered extents wait event
>
You can add
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
to the series, thanks,
Josef
^ permalink raw reply [flat|nested] 10+ messages in thread