diff mbox series

[v7,03/12] mm: vmscan: use shrinker_rwsem to protect shrinker_maps allocation

Message ID 20210209174646.1310591-4-shy828301@gmail.com (mailing list archive)
State New
Headers show
Series [v7,01/12] mm: vmscan: use nid from shrink_control for tracepoint | expand

Commit Message

Yang Shi Feb. 9, 2021, 5:46 p.m. UTC
Since memcg_shrinker_map_size just can be changed under holding shrinker_rwsem
exclusively, the read side can be protected by holding read lock, so it sounds
superfluous to have a dedicated mutex.

Kirill Tkhai suggested use write lock since:

  * We want the assignment to shrinker_maps is visible for shrink_slab_memcg().
  * The rcu_dereference_protected() dereferrencing in shrink_slab_memcg(), but
    in case of we use READ lock in alloc_shrinker_maps(), the dereferrencing
    is not actually protected.
  * READ lock makes alloc_shrinker_info() racy against memory allocation fail.
    alloc_shrinker_info()->free_shrinker_info() may free memory right after
    shrink_slab_memcg() dereferenced it. You may say
    shrink_slab_memcg()->mem_cgroup_online() protects us from it? Yes, sure,
    but this is not the thing we want to remember in the future, since this
    spreads modularity.

And a test with heavy paging workload didn't show write lock makes things worse.

Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: Yang Shi <shy828301@gmail.com>
---
 mm/vmscan.c | 16 ++++++----------
 1 file changed, 6 insertions(+), 10 deletions(-)

Comments

Roman Gushchin Feb. 9, 2021, 8:33 p.m. UTC | #1
On Tue, Feb 09, 2021 at 09:46:37AM -0800, Yang Shi wrote:
> Since memcg_shrinker_map_size just can be changed under holding shrinker_rwsem
> exclusively, the read side can be protected by holding read lock, so it sounds
> superfluous to have a dedicated mutex.
> 
> Kirill Tkhai suggested use write lock since:
> 
>   * We want the assignment to shrinker_maps is visible for shrink_slab_memcg().
>   * The rcu_dereference_protected() dereferrencing in shrink_slab_memcg(), but
>     in case of we use READ lock in alloc_shrinker_maps(), the dereferrencing
>     is not actually protected.
>   * READ lock makes alloc_shrinker_info() racy against memory allocation fail.
>     alloc_shrinker_info()->free_shrinker_info() may free memory right after
>     shrink_slab_memcg() dereferenced it. You may say
>     shrink_slab_memcg()->mem_cgroup_online() protects us from it? Yes, sure,
>     but this is not the thing we want to remember in the future, since this
>     spreads modularity.
> 
> And a test with heavy paging workload didn't show write lock makes things worse.
> 
> Acked-by: Vlastimil Babka <vbabka@suse.cz>
> Acked-by: Kirill Tkhai <ktkhai@virtuozzo.com>
> Signed-off-by: Yang Shi <shy828301@gmail.com>

Acked-by: Roman Gushchin <guro@fb.com>

with a small nit (below):

> ---
>  mm/vmscan.c | 16 ++++++----------
>  1 file changed, 6 insertions(+), 10 deletions(-)
> 
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 96b08c79f18d..e4ddaaaeffe2 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -187,7 +187,6 @@ static DECLARE_RWSEM(shrinker_rwsem);
>  #ifdef CONFIG_MEMCG
>  
>  static int memcg_shrinker_map_size;
> -static DEFINE_MUTEX(memcg_shrinker_map_mutex);
>  
>  static void free_shrinker_map_rcu(struct rcu_head *head)
>  {
> @@ -200,8 +199,6 @@ static int expand_one_shrinker_map(struct mem_cgroup *memcg,
>  	struct memcg_shrinker_map *new, *old;
>  	int nid;
>  
> -	lockdep_assert_held(&memcg_shrinker_map_mutex);
> -

Why not check that shrinker_rwsem is down here?

>  	for_each_node(nid) {
>  		old = rcu_dereference_protected(
>  			mem_cgroup_nodeinfo(memcg, nid)->shrinker_map, true);
> @@ -249,7 +246,7 @@ int alloc_shrinker_maps(struct mem_cgroup *memcg)
>  	if (mem_cgroup_is_root(memcg))
>  		return 0;
>  
> -	mutex_lock(&memcg_shrinker_map_mutex);
> +	down_write(&shrinker_rwsem);
>  	size = memcg_shrinker_map_size;
>  	for_each_node(nid) {
>  		map = kvzalloc_node(sizeof(*map) + size, GFP_KERNEL, nid);
> @@ -260,7 +257,7 @@ int alloc_shrinker_maps(struct mem_cgroup *memcg)
>  		}
>  		rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_map, map);
>  	}
> -	mutex_unlock(&memcg_shrinker_map_mutex);
> +	up_write(&shrinker_rwsem);
>  
>  	return ret;
>  }
> @@ -275,9 +272,8 @@ static int expand_shrinker_maps(int new_id)
>  	if (size <= old_size)
>  		return 0;
>  
> -	mutex_lock(&memcg_shrinker_map_mutex);

And here as well. It will make the locking model more obvious and will help
to avoid errors in the future.

>  	if (!root_mem_cgroup)
> -		goto unlock;
> +		goto out;
>  
>  	memcg = mem_cgroup_iter(NULL, NULL, NULL);
>  	do {
> @@ -286,13 +282,13 @@ static int expand_shrinker_maps(int new_id)
>  		ret = expand_one_shrinker_map(memcg, size, old_size);
>  		if (ret) {
>  			mem_cgroup_iter_break(NULL, memcg);
> -			goto unlock;
> +			goto out;
>  		}
>  	} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
> -unlock:
> +out:
>  	if (!ret)
>  		memcg_shrinker_map_size = size;
> -	mutex_unlock(&memcg_shrinker_map_mutex);
> +
>  	return ret;
>  }
>  
> -- 
> 2.26.2
>
Yang Shi Feb. 9, 2021, 11:28 p.m. UTC | #2
On Tue, Feb 9, 2021 at 12:33 PM Roman Gushchin <guro@fb.com> wrote:
>
> On Tue, Feb 09, 2021 at 09:46:37AM -0800, Yang Shi wrote:
> > Since memcg_shrinker_map_size just can be changed under holding shrinker_rwsem
> > exclusively, the read side can be protected by holding read lock, so it sounds
> > superfluous to have a dedicated mutex.
> >
> > Kirill Tkhai suggested use write lock since:
> >
> >   * We want the assignment to shrinker_maps is visible for shrink_slab_memcg().
> >   * The rcu_dereference_protected() dereferrencing in shrink_slab_memcg(), but
> >     in case of we use READ lock in alloc_shrinker_maps(), the dereferrencing
> >     is not actually protected.
> >   * READ lock makes alloc_shrinker_info() racy against memory allocation fail.
> >     alloc_shrinker_info()->free_shrinker_info() may free memory right after
> >     shrink_slab_memcg() dereferenced it. You may say
> >     shrink_slab_memcg()->mem_cgroup_online() protects us from it? Yes, sure,
> >     but this is not the thing we want to remember in the future, since this
> >     spreads modularity.
> >
> > And a test with heavy paging workload didn't show write lock makes things worse.
> >
> > Acked-by: Vlastimil Babka <vbabka@suse.cz>
> > Acked-by: Kirill Tkhai <ktkhai@virtuozzo.com>
> > Signed-off-by: Yang Shi <shy828301@gmail.com>
>
> Acked-by: Roman Gushchin <guro@fb.com>
>
> with a small nit (below):
>
> > ---
> >  mm/vmscan.c | 16 ++++++----------
> >  1 file changed, 6 insertions(+), 10 deletions(-)
> >
> > diff --git a/mm/vmscan.c b/mm/vmscan.c
> > index 96b08c79f18d..e4ddaaaeffe2 100644
> > --- a/mm/vmscan.c
> > +++ b/mm/vmscan.c
> > @@ -187,7 +187,6 @@ static DECLARE_RWSEM(shrinker_rwsem);
> >  #ifdef CONFIG_MEMCG
> >
> >  static int memcg_shrinker_map_size;
> > -static DEFINE_MUTEX(memcg_shrinker_map_mutex);
> >
> >  static void free_shrinker_map_rcu(struct rcu_head *head)
> >  {
> > @@ -200,8 +199,6 @@ static int expand_one_shrinker_map(struct mem_cgroup *memcg,
> >       struct memcg_shrinker_map *new, *old;
> >       int nid;
> >
> > -     lockdep_assert_held(&memcg_shrinker_map_mutex);
> > -
>
> Why not check that shrinker_rwsem is down here?

No special reason, just because we know it was acquired before. We
could add the check, but not here. I think it'd be better to have the
assert in expand_shrinker_maps() since the rwsem was acquired before
calling it.

>
> >       for_each_node(nid) {
> >               old = rcu_dereference_protected(
> >                       mem_cgroup_nodeinfo(memcg, nid)->shrinker_map, true);
> > @@ -249,7 +246,7 @@ int alloc_shrinker_maps(struct mem_cgroup *memcg)
> >       if (mem_cgroup_is_root(memcg))
> >               return 0;
> >
> > -     mutex_lock(&memcg_shrinker_map_mutex);
> > +     down_write(&shrinker_rwsem);
> >       size = memcg_shrinker_map_size;
> >       for_each_node(nid) {
> >               map = kvzalloc_node(sizeof(*map) + size, GFP_KERNEL, nid);
> > @@ -260,7 +257,7 @@ int alloc_shrinker_maps(struct mem_cgroup *memcg)
> >               }
> >               rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_map, map);
> >       }
> > -     mutex_unlock(&memcg_shrinker_map_mutex);
> > +     up_write(&shrinker_rwsem);
> >
> >       return ret;
> >  }
> > @@ -275,9 +272,8 @@ static int expand_shrinker_maps(int new_id)
> >       if (size <= old_size)
> >               return 0;
> >
> > -     mutex_lock(&memcg_shrinker_map_mutex);
>
> And here as well. It will make the locking model more obvious and will help
> to avoid errors in the future.
>
> >       if (!root_mem_cgroup)
> > -             goto unlock;
> > +             goto out;
> >
> >       memcg = mem_cgroup_iter(NULL, NULL, NULL);
> >       do {
> > @@ -286,13 +282,13 @@ static int int new_id)
> >               ret = expand_one_shrinker_map(memcg, size, old_size);
> >               if (ret) {
> >                       mem_cgroup_iter_break(NULL, memcg);
> > -                     goto unlock;
> > +                     goto out;
> >               }
> >       } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
> > -unlock:
> > +out:
> >       if (!ret)
> >               memcg_shrinker_map_size = size;
> > -     mutex_unlock(&memcg_shrinker_map_mutex);
> > +
> >       return ret;
> >  }
> >
> > --
> > 2.26.2
> >
diff mbox series

Patch

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 96b08c79f18d..e4ddaaaeffe2 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -187,7 +187,6 @@  static DECLARE_RWSEM(shrinker_rwsem);
 #ifdef CONFIG_MEMCG
 
 static int memcg_shrinker_map_size;
-static DEFINE_MUTEX(memcg_shrinker_map_mutex);
 
 static void free_shrinker_map_rcu(struct rcu_head *head)
 {
@@ -200,8 +199,6 @@  static int expand_one_shrinker_map(struct mem_cgroup *memcg,
 	struct memcg_shrinker_map *new, *old;
 	int nid;
 
-	lockdep_assert_held(&memcg_shrinker_map_mutex);
-
 	for_each_node(nid) {
 		old = rcu_dereference_protected(
 			mem_cgroup_nodeinfo(memcg, nid)->shrinker_map, true);
@@ -249,7 +246,7 @@  int alloc_shrinker_maps(struct mem_cgroup *memcg)
 	if (mem_cgroup_is_root(memcg))
 		return 0;
 
-	mutex_lock(&memcg_shrinker_map_mutex);
+	down_write(&shrinker_rwsem);
 	size = memcg_shrinker_map_size;
 	for_each_node(nid) {
 		map = kvzalloc_node(sizeof(*map) + size, GFP_KERNEL, nid);
@@ -260,7 +257,7 @@  int alloc_shrinker_maps(struct mem_cgroup *memcg)
 		}
 		rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_map, map);
 	}
-	mutex_unlock(&memcg_shrinker_map_mutex);
+	up_write(&shrinker_rwsem);
 
 	return ret;
 }
@@ -275,9 +272,8 @@  static int expand_shrinker_maps(int new_id)
 	if (size <= old_size)
 		return 0;
 
-	mutex_lock(&memcg_shrinker_map_mutex);
 	if (!root_mem_cgroup)
-		goto unlock;
+		goto out;
 
 	memcg = mem_cgroup_iter(NULL, NULL, NULL);
 	do {
@@ -286,13 +282,13 @@  static int expand_shrinker_maps(int new_id)
 		ret = expand_one_shrinker_map(memcg, size, old_size);
 		if (ret) {
 			mem_cgroup_iter_break(NULL, memcg);
-			goto unlock;
+			goto out;
 		}
 	} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
-unlock:
+out:
 	if (!ret)
 		memcg_shrinker_map_size = size;
-	mutex_unlock(&memcg_shrinker_map_mutex);
+
 	return ret;
 }