From: Kirill Tkhai <ktkhai@virtuozzo.com>
To: Michal Hocko <mhocko@kernel.org>
Cc: akpm@linux-foundation.org, gregkh@linuxfoundation.org,
rafael@kernel.org, viro@zeniv.linux.org.uk,
darrick.wong@oracle.com, paulmck@linux.vnet.ibm.com,
josh@joshtriplett.org, rostedt@goodmis.org,
mathieu.desnoyers@efficios.com, jiangshanlai@gmail.com,
hughd@google.com, shuah@kernel.org, robh@kernel.org,
ulf.hansson@linaro.org, aspriel@gmail.com,
vivek.gautam@codeaurora.org, robin.murphy@arm.com,
joe@perches.com, heikki.krogerus@linux.intel.com,
sfr@canb.auug.org.au, vdavydov.dev@gmail.com,
chris@chris-wilson.co.uk, penguin-kernel@I-love.SAKURA.ne.jp,
aryabinin@virtuozzo.com, willy@infradead.org,
ying.huang@intel.com, shakeelb@google.com, jbacik@fb.com,
mingo@kernel.org, mhiramat@kernel.org,
linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org,
linux-mm@kvack.org
Subject: Re: [PATCH RFC v2 02/10] mm: Make shrink_slab() lockless
Date: Thu, 9 Aug 2018 14:23:28 +0300 [thread overview]
Message-ID: <964ee4fe-bbd1-0caa-4c5e-a73af99ee7bb@virtuozzo.com> (raw)
In-Reply-To: <20180809071418.GA24884@dhcp22.suse.cz>
On 09.08.2018 10:14, Michal Hocko wrote:
> On Wed 08-08-18 16:20:54, Kirill Tkhai wrote:
>> [Added two more places needed srcu_dereference(). All ->shrinker_map
>> dereferences must be under SRCU, and this v2 adds missed in previous]
>>
>> The patch makes shrinker list and shrinker_idr SRCU-safe
>> for readers. This requires synchronize_srcu() on finalize
>> stage unregistering stage, which waits till all parallel
>> shrink_slab() are finished
>>
>> Note, that patch removes rwsem_is_contended() checks from
>> the code, and this does not result in delays during
>> registration, since there is no waiting at all. Unregistration
>> case may be optimized by splitting unregister_shrinker()
>> in tho stages, and this is made in next patches.
>>
>> Also, keep in mind, that in case of SRCU is not allowed
>> to make unconditional (which is done in previous patch),
>> it is possible to use percpu_rw_semaphore instead of it.
>> percpu_down_read() will be used in shrink_slab_memcg()
>> and in shrink_slab(), and consecutive calls
>>
>> percpu_down_write(percpu_rwsem);
>> percpu_up_write(percpu_rwsem);
>>
>> will be used instead of synchronize_srcu().
>
> An obvious question. Why didn't you go that way? What are pros/cons of
> both approaches?
percpu_rw_semaphore based variant looks something like:
commit d581d4ad7ecf
Author: Kirill Tkhai <ktkhai@virtuozzo.com>
Date: Thu Aug 9 14:21:12 2018 +0300
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 0ff97e860759..fe8693775e33 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -168,6 +168,7 @@ unsigned long vm_total_pages;
static LIST_HEAD(shrinker_list);
static DECLARE_RWSEM(shrinker_rwsem);
+DEFINE_STATIC_PERCPU_RWSEM(shrinker_percpu_rwsem);
#ifdef CONFIG_MEMCG_KMEM
@@ -198,7 +199,10 @@ static int prealloc_memcg_shrinker(struct shrinker *shrinker)
goto unlock;
if (id >= shrinker_nr_max) {
- if (memcg_expand_shrinker_maps(id)) {
+ percpu_down_write(&shrinker_percpu_rwsem);
+ ret = memcg_expand_shrinker_maps(id);
+ percpu_up_write(&shrinker_percpu_rwsem);
+ if (ret) {
idr_remove(&shrinker_idr, id);
goto unlock;
}
@@ -406,7 +410,7 @@ void free_prealloced_shrinker(struct shrinker *shrinker)
void register_shrinker_prepared(struct shrinker *shrinker)
{
down_write(&shrinker_rwsem);
- list_add_tail(&shrinker->list, &shrinker_list);
+ list_add_tail_rcu(&shrinker->list, &shrinker_list);
#ifdef CONFIG_MEMCG_KMEM
idr_replace(&shrinker_idr, shrinker, shrinker->id);
#endif
@@ -434,8 +438,14 @@ void unregister_shrinker(struct shrinker *shrinker)
if (shrinker->flags & SHRINKER_MEMCG_AWARE)
unregister_memcg_shrinker(shrinker);
down_write(&shrinker_rwsem);
- list_del(&shrinker->list);
+ list_del_rcu(&shrinker->list);
up_write(&shrinker_rwsem);
+
+ synchronize_rcu();
+
+ percpu_down_write(&shrinker_percpu_rwsem);
+ percpu_up_write(&shrinker_percpu_rwsem);
+
kfree(shrinker->nr_deferred);
shrinker->nr_deferred = NULL;
}
@@ -574,11 +584,11 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
if (!memcg_kmem_enabled() || !mem_cgroup_online(memcg))
return 0;
- if (!down_read_trylock(&shrinker_rwsem))
+ if (!percpu_down_read_trylock(&shrinker_percpu_rwsem))
return 0;
map = rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_map,
- true);
+ true /* shrinker_percpu_rwsem */);
if (unlikely(!map))
goto unlock;
@@ -590,7 +600,22 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
};
struct shrinker *shrinker;
+ /*
+ * See shutdown sequence in unregister_shrinker().
+ * RCU allows us to iterate IDR locklessly (this
+ * is the way to synchronize with IDR changing by
+ * idr_alloc()).
+ *
+ * If we see shrinker pointer undex RCU, this means
+ * synchronize_rcu() in unregister_shrinker() has not
+ * finished yet. Then, we unlock RCU, and synchronize_rcu()
+ * can complete, but unregister_shrinker() can't proceed,
+ * before we unlock shrinker_percpu_rwsem.
+ */
+ rcu_read_lock();
shrinker = idr_find(&shrinker_idr, i);
+ rcu_read_unlock();
+
if (unlikely(!shrinker || shrinker == SHRINKER_REGISTERING)) {
if (!shrinker)
clear_bit(i, map->map);
@@ -624,13 +649,13 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
}
freed += ret;
- if (rwsem_is_contended(&shrinker_rwsem)) {
+ if (!rcu_sync_is_idle(&shrinker_percpu_rwsem.rss)) {
freed = freed ? : 1;
break;
}
}
unlock:
- up_read(&shrinker_rwsem);
+ percpu_up_read(&shrinker_percpu_rwsem);
return freed;
}
#else /* CONFIG_MEMCG_KMEM */
@@ -672,15 +697,17 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
if (!mem_cgroup_is_root(memcg))
return shrink_slab_memcg(gfp_mask, nid, memcg, priority);
- if (!down_read_trylock(&shrinker_rwsem))
+ if (!percpu_down_read_trylock(&shrinker_percpu_rwsem))
goto out;
- list_for_each_entry(shrinker, &shrinker_list, list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(shrinker, &shrinker_list, list) {
struct shrink_control sc = {
.gfp_mask = gfp_mask,
.nid = nid,
.memcg = memcg,
};
+ rcu_read_unlock();
ret = do_shrink_slab(&sc, shrinker, priority);
if (ret == SHRINK_EMPTY)
@@ -691,13 +718,16 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
* prevent the regsitration from being stalled for long periods
* by parallel ongoing shrinking.
*/
- if (rwsem_is_contended(&shrinker_rwsem)) {
+ if (!rcu_sync_is_idle(&shrinker_percpu_rwsem.rss)) {
freed = freed ? : 1;
break;
}
+
+ rcu_read_lock();
}
+ rcu_read_unlock();
- up_read(&shrinker_rwsem);
+ percpu_up_read(&shrinker_percpu_rwsem);
out:
cond_resched();
return freed;
next prev parent reply other threads:[~2018-08-09 11:23 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-08-07 15:37 [PATCH RFC 00/10] Introduce lockless shrink_slab() Kirill Tkhai
2018-08-07 15:37 ` [PATCH RFC 01/10] rcu: Make CONFIG_SRCU unconditionally enabled Kirill Tkhai
2018-08-08 0:55 ` Steven Rostedt
2018-08-08 1:05 ` Stephen Rothwell
2018-08-08 9:46 ` Kirill Tkhai
2018-08-08 1:08 ` Stephen Rothwell
2018-08-08 9:59 ` Kirill Tkhai
2018-08-08 11:04 ` Stephen Rothwell
2018-08-08 7:20 ` Michal Hocko
2018-08-08 10:17 ` Kirill Tkhai
2018-08-08 10:27 ` Michal Hocko
2018-08-08 21:31 ` Dave Chinner
2018-08-09 0:07 ` Matthew Wilcox
2018-08-09 7:45 ` Greg KH
2018-08-09 10:22 ` Kirill Tkhai
2018-08-08 16:13 ` Josh Triplett
2018-08-08 16:23 ` Kirill Tkhai
2018-08-08 16:30 ` Kirill Tkhai
2018-08-08 18:01 ` Josh Triplett
2018-08-08 23:02 ` Shakeel Butt
2018-08-08 23:09 ` Josh Triplett
2018-08-07 15:37 ` [PATCH RFC 02/10] mm: Make shrink_slab() lockless Kirill Tkhai
2018-08-08 11:51 ` Kirill Tkhai
2018-08-08 13:20 ` [PATCH RFC v2 " Kirill Tkhai
2018-08-09 7:14 ` Michal Hocko
2018-08-09 9:21 ` Kirill Tkhai
2018-08-09 10:37 ` Tetsuo Handa
2018-08-09 10:58 ` Kirill Tkhai
2018-08-09 11:23 ` Kirill Tkhai [this message]
2018-08-07 15:38 ` [PATCH RFC 03/10] mm: Convert shrinker_rwsem to mutex Kirill Tkhai
2018-08-07 15:38 ` [PATCH RFC 04/10] mm: Split unregister_shrinker() Kirill Tkhai
2018-08-07 15:38 ` [PATCH RFC 05/10] fs: Move list_lru_destroy() to destroy_super_work() Kirill Tkhai
2018-08-07 15:38 ` [PATCH RFC 06/10] fs: Shrink only (SB_ACTIVE|SB_BORN) superblocks in super_cache_scan() Kirill Tkhai
2018-08-07 15:38 ` [PATCH RFC 07/10] fs: Introduce struct super_operations::destroy_super() callback Kirill Tkhai
2018-08-07 15:39 ` [PATCH RFC 08/10] xfs: Introduce xfs_fs_destroy_super() Kirill Tkhai
2018-08-07 15:39 ` [PATCH RFC 09/10] shmem: Implement shmem_destroy_super() Kirill Tkhai
2018-08-07 15:39 ` [PATCH RFC 10/10] fs: Use unregister_shrinker_delayed_{initiate, finalize} for super_block shrinker Kirill Tkhai
2018-08-08 1:12 ` [PATCH RFC 00/10] Introduce lockless shrink_slab() Stephen Rothwell
2018-08-08 5:39 ` Shakeel Butt
2018-08-08 10:18 ` Kirill Tkhai
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=964ee4fe-bbd1-0caa-4c5e-a73af99ee7bb@virtuozzo.com \
--to=ktkhai@virtuozzo.com \
--cc=akpm@linux-foundation.org \
--cc=aryabinin@virtuozzo.com \
--cc=aspriel@gmail.com \
--cc=chris@chris-wilson.co.uk \
--cc=darrick.wong@oracle.com \
--cc=gregkh@linuxfoundation.org \
--cc=heikki.krogerus@linux.intel.com \
--cc=hughd@google.com \
--cc=jbacik@fb.com \
--cc=jiangshanlai@gmail.com \
--cc=joe@perches.com \
--cc=josh@joshtriplett.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=mhiramat@kernel.org \
--cc=mhocko@kernel.org \
--cc=mingo@kernel.org \
--cc=paulmck@linux.vnet.ibm.com \
--cc=penguin-kernel@I-love.SAKURA.ne.jp \
--cc=rafael@kernel.org \
--cc=robh@kernel.org \
--cc=robin.murphy@arm.com \
--cc=rostedt@goodmis.org \
--cc=sfr@canb.auug.org.au \
--cc=shakeelb@google.com \
--cc=shuah@kernel.org \
--cc=ulf.hansson@linaro.org \
--cc=vdavydov.dev@gmail.com \
--cc=viro@zeniv.linux.org.uk \
--cc=vivek.gautam@codeaurora.org \
--cc=willy@infradead.org \
--cc=ying.huang@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).