diff mbox series

[RFC] block, bfq: switch 'bfqg->ref' to use atomic refcount apis

Message ID 20221227031541.2595647-1-yukuai1@huaweicloud.com (mailing list archive)
State New, archived
Headers show
Series [RFC] block, bfq: switch 'bfqg->ref' to use atomic refcount apis | expand

Commit Message

Yu Kuai Dec. 27, 2022, 3:15 a.m. UTC 
From: Yu Kuai <yukuai3@huawei.com>

The updating of 'bfqg->ref' should be protected by 'bfqd->lock', however,
during code review, we found that bfq_pd_free() update 'bfqg->ref'
without holding the lock, which is problematic:

1) bfq_pd_free() triggered by removing cgroup is called asynchronously;
2) bfqq will grab bfqg reference, and exit bfqq will drop the reference,
which can concurrenty with 1).

Unfortunately, 'bfqd->lock' can't be held here because 'bfqd' might already
be freed in bfq_pd_free(). Fix the problem by using atomic refcount apis.

Signed-off-by: Yu Kuai <yukuai3@huawei.com>
---
 block/bfq-cgroup.c  | 8 +++-----
 block/bfq-iosched.h | 2 +-
 2 files changed, 4 insertions(+), 6 deletions(-)

Comments

Yu Kuai Dec. 27, 2022, 6:09 a.m. UTC | #1 
Hi, Jan!

在 2022/12/27 11:15, Yu Kuai 写道:
> From: Yu Kuai <yukuai3@huawei.com>
> 
> The updating of 'bfqg->ref' should be protected by 'bfqd->lock', however,
> during code review, we found that bfq_pd_free() update 'bfqg->ref'
> without holding the lock, which is problematic:
> 
> 1) bfq_pd_free() triggered by removing cgroup is called asynchronously;
> 2) bfqq will grab bfqg reference, and exit bfqq will drop the reference,
> which can concurrenty with 1).
> 
> Unfortunately, 'bfqd->lock' can't be held here because 'bfqd' might already
> be freed in bfq_pd_free(). Fix the problem by using atomic refcount apis.
> 
> Signed-off-by: Yu Kuai <yukuai3@huawei.com>
> ---
>   block/bfq-cgroup.c  | 8 +++-----
>   block/bfq-iosched.h | 2 +-
>   2 files changed, 4 insertions(+), 6 deletions(-)
> 
> diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
> index 1b2829e99dad..aa9c4f02e3a3 100644
> --- a/block/bfq-cgroup.c
> +++ b/block/bfq-cgroup.c
> @@ -316,14 +316,12 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq)
>   
>   static void bfqg_get(struct bfq_group *bfqg)
>   {
> -	bfqg->ref++;
> +	refcount_inc(&bfqg->ref);
>   }
>   
>   static void bfqg_put(struct bfq_group *bfqg)
>   {
> -	bfqg->ref--;
> -
> -	if (bfqg->ref == 0)
> +	if (refcount_dec_and_test(bfqg->ref))
Sorry that here should be '&bfqg->ref'.

Anyway, I'll wait for you, and send a new version if you think this
patch make sense.

Thanks,
Kuai

>   		kfree(bfqg);
>   }
>   
> @@ -530,7 +528,7 @@ static struct blkg_policy_data *bfq_pd_alloc(gfp_t gfp, struct request_queue *q,
>   	}
>   
>   	/* see comments in bfq_bic_update_cgroup for why refcounting */
> -	bfqg_get(bfqg);
> +	refcount_set(&bfqg->ref, 1);
>   	return &bfqg->pd;
>   }
>   
> diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
> index 41aa151ccc22..466e4865ace6 100644
> --- a/block/bfq-iosched.h
> +++ b/block/bfq-iosched.h
> @@ -928,7 +928,7 @@ struct bfq_group {
>   	char blkg_path[128];
>   
>   	/* reference counter (see comments in bfq_bic_update_cgroup) */
> -	int ref;
> +	refcount_t ref;
>   	/* Is bfq_group still online? */
>   	bool online;
>   
>
Jan Kara Jan. 2, 2023, 11:22 a.m. UTC | #2 
On Tue 27-12-22 14:09:40, Yu Kuai wrote:
> Hi, Jan!
> 
> 在 2022/12/27 11:15, Yu Kuai 写道:
> > From: Yu Kuai <yukuai3@huawei.com>
> > 
> > The updating of 'bfqg->ref' should be protected by 'bfqd->lock', however,
> > during code review, we found that bfq_pd_free() update 'bfqg->ref'
> > without holding the lock, which is problematic:
> > 
> > 1) bfq_pd_free() triggered by removing cgroup is called asynchronously;
> > 2) bfqq will grab bfqg reference, and exit bfqq will drop the reference,
> > which can concurrenty with 1).
> > 
> > Unfortunately, 'bfqd->lock' can't be held here because 'bfqd' might already
> > be freed in bfq_pd_free(). Fix the problem by using atomic refcount apis.
> > 
> > Signed-off-by: Yu Kuai <yukuai3@huawei.com>
> > ---
> >   block/bfq-cgroup.c  | 8 +++-----
> >   block/bfq-iosched.h | 2 +-
> >   2 files changed, 4 insertions(+), 6 deletions(-)
> > 
> > diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
> > index 1b2829e99dad..aa9c4f02e3a3 100644
> > --- a/block/bfq-cgroup.c
> > +++ b/block/bfq-cgroup.c
> > @@ -316,14 +316,12 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq)
> >   static void bfqg_get(struct bfq_group *bfqg)
> >   {
> > -	bfqg->ref++;
> > +	refcount_inc(&bfqg->ref);
> >   }
> >   static void bfqg_put(struct bfq_group *bfqg)
> >   {
> > -	bfqg->ref--;
> > -
> > -	if (bfqg->ref == 0)
> > +	if (refcount_dec_and_test(bfqg->ref))
> Sorry that here should be '&bfqg->ref'.
> 
> Anyway, I'll wait for you, and send a new version if you think this
> patch make sense.

Yes, the patch makes sense to me so feel free to send fixed version.

								Honza
diff mbox series

Patch

diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index 1b2829e99dad..aa9c4f02e3a3 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -316,14 +316,12 @@  struct bfq_group *bfqq_group(struct bfq_queue *bfqq)
 
 static void bfqg_get(struct bfq_group *bfqg)
 {
-	bfqg->ref++;
+	refcount_inc(&bfqg->ref);
 }
 
 static void bfqg_put(struct bfq_group *bfqg)
 {
-	bfqg->ref--;
-
-	if (bfqg->ref == 0)
+	if (refcount_dec_and_test(bfqg->ref))
 		kfree(bfqg);
 }
 
@@ -530,7 +528,7 @@  static struct blkg_policy_data *bfq_pd_alloc(gfp_t gfp, struct request_queue *q,
 	}
 
 	/* see comments in bfq_bic_update_cgroup for why refcounting */
-	bfqg_get(bfqg);
+	refcount_set(&bfqg->ref, 1);
 	return &bfqg->pd;
 }
 
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index 41aa151ccc22..466e4865ace6 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -928,7 +928,7 @@  struct bfq_group {
 	char blkg_path[128];
 
 	/* reference counter (see comments in bfq_bic_update_cgroup) */
-	int ref;
+	refcount_t ref;
 	/* Is bfq_group still online? */
 	bool online;