From: Yang Shi <shy828301@gmail.com>
To: guro@fb.com, ktkhai@virtuozzo.com, vbabka@suse.cz,
shakeelb@google.com, david@fromorbit.com, hannes@cmpxchg.org,
mhocko@suse.com, akpm@linux-foundation.org
Cc: shy828301@gmail.com, linux-mm@kvack.org,
linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [v7 PATCH 02/12] mm: vmscan: consolidate shrinker_maps handling code
Date: Tue, 9 Feb 2021 09:46:36 -0800 [thread overview]
Message-ID: <20210209174646.1310591-3-shy828301@gmail.com> (raw)
In-Reply-To: <20210209174646.1310591-1-shy828301@gmail.com>
The shrinker map management is not purely memcg specific, it is at the intersection
between memory cgroup and shrinkers. It's allocation and assignment of a structure,
and the only memcg bit is the map is being stored in a memcg structure. So move the
shrinker_maps handling code into vmscan.c for tighter integration with shrinker code,
and remove the "memcg_" prefix. There is no functional change.
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: Yang Shi <shy828301@gmail.com>
---
include/linux/memcontrol.h | 11 ++--
mm/huge_memory.c | 4 +-
mm/list_lru.c | 6 +-
mm/memcontrol.c | 129 +-----------------------------------
mm/vmscan.c | 131 ++++++++++++++++++++++++++++++++++++-
5 files changed, 141 insertions(+), 140 deletions(-)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index eeb0b52203e9..1739f17e0939 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1581,10 +1581,9 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
return false;
}
-extern int memcg_expand_shrinker_maps(int new_id);
-
-extern void memcg_set_shrinker_bit(struct mem_cgroup *memcg,
- int nid, int shrinker_id);
+int alloc_shrinker_maps(struct mem_cgroup *memcg);
+void free_shrinker_maps(struct mem_cgroup *memcg);
+void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id);
#else
#define mem_cgroup_sockets_enabled 0
static inline void mem_cgroup_sk_alloc(struct sock *sk) { };
@@ -1594,8 +1593,8 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
return false;
}
-static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg,
- int nid, int shrinker_id)
+static inline void set_shrinker_bit(struct mem_cgroup *memcg,
+ int nid, int shrinker_id)
{
}
#endif
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 9237976abe72..05190d7f32ae 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2823,8 +2823,8 @@ void deferred_split_huge_page(struct page *page)
ds_queue->split_queue_len++;
#ifdef CONFIG_MEMCG
if (memcg)
- memcg_set_shrinker_bit(memcg, page_to_nid(page),
- deferred_split_shrinker.id);
+ set_shrinker_bit(memcg, page_to_nid(page),
+ deferred_split_shrinker.id);
#endif
}
spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
diff --git a/mm/list_lru.c b/mm/list_lru.c
index fe230081690b..628030fa5f69 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -125,8 +125,8 @@ bool list_lru_add(struct list_lru *lru, struct list_head *item)
list_add_tail(item, &l->list);
/* Set shrinker bit if the first element was added */
if (!l->nr_items++)
- memcg_set_shrinker_bit(memcg, nid,
- lru_shrinker_id(lru));
+ set_shrinker_bit(memcg, nid,
+ lru_shrinker_id(lru));
nlru->nr_items++;
spin_unlock(&nlru->lock);
return true;
@@ -548,7 +548,7 @@ static void memcg_drain_list_lru_node(struct list_lru *lru, int nid,
if (src->nr_items) {
dst->nr_items += src->nr_items;
- memcg_set_shrinker_bit(dst_memcg, nid, lru_shrinker_id(lru));
+ set_shrinker_bit(dst_memcg, nid, lru_shrinker_id(lru));
src->nr_items = 0;
}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 1bdb93ee8e72..f5c9a0d2160b 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -397,129 +397,6 @@ DEFINE_STATIC_KEY_FALSE(memcg_kmem_enabled_key);
EXPORT_SYMBOL(memcg_kmem_enabled_key);
#endif
-static int memcg_shrinker_map_size;
-static DEFINE_MUTEX(memcg_shrinker_map_mutex);
-
-static void memcg_free_shrinker_map_rcu(struct rcu_head *head)
-{
- kvfree(container_of(head, struct memcg_shrinker_map, rcu));
-}
-
-static int memcg_expand_one_shrinker_map(struct mem_cgroup *memcg,
- int size, int old_size)
-{
- 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);
- /* Not yet online memcg */
- if (!old)
- return 0;
-
- new = kvmalloc_node(sizeof(*new) + size, GFP_KERNEL, nid);
- if (!new)
- return -ENOMEM;
-
- /* Set all old bits, clear all new bits */
- memset(new->map, (int)0xff, old_size);
- memset((void *)new->map + old_size, 0, size - old_size);
-
- rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_map, new);
- call_rcu(&old->rcu, memcg_free_shrinker_map_rcu);
- }
-
- return 0;
-}
-
-static void memcg_free_shrinker_maps(struct mem_cgroup *memcg)
-{
- struct mem_cgroup_per_node *pn;
- struct memcg_shrinker_map *map;
- int nid;
-
- if (mem_cgroup_is_root(memcg))
- return;
-
- for_each_node(nid) {
- pn = mem_cgroup_nodeinfo(memcg, nid);
- map = rcu_dereference_protected(pn->shrinker_map, true);
- kvfree(map);
- rcu_assign_pointer(pn->shrinker_map, NULL);
- }
-}
-
-static int memcg_alloc_shrinker_maps(struct mem_cgroup *memcg)
-{
- struct memcg_shrinker_map *map;
- int nid, size, ret = 0;
-
- if (mem_cgroup_is_root(memcg))
- return 0;
-
- mutex_lock(&memcg_shrinker_map_mutex);
- size = memcg_shrinker_map_size;
- for_each_node(nid) {
- map = kvzalloc_node(sizeof(*map) + size, GFP_KERNEL, nid);
- if (!map) {
- memcg_free_shrinker_maps(memcg);
- ret = -ENOMEM;
- break;
- }
- rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_map, map);
- }
- mutex_unlock(&memcg_shrinker_map_mutex);
-
- return ret;
-}
-
-int memcg_expand_shrinker_maps(int new_id)
-{
- int size, old_size, ret = 0;
- struct mem_cgroup *memcg;
-
- size = DIV_ROUND_UP(new_id + 1, BITS_PER_LONG) * sizeof(unsigned long);
- old_size = memcg_shrinker_map_size;
- if (size <= old_size)
- return 0;
-
- mutex_lock(&memcg_shrinker_map_mutex);
- if (!root_mem_cgroup)
- goto unlock;
-
- for_each_mem_cgroup(memcg) {
- if (mem_cgroup_is_root(memcg))
- continue;
- ret = memcg_expand_one_shrinker_map(memcg, size, old_size);
- if (ret) {
- mem_cgroup_iter_break(NULL, memcg);
- goto unlock;
- }
- }
-unlock:
- if (!ret)
- memcg_shrinker_map_size = size;
- mutex_unlock(&memcg_shrinker_map_mutex);
- return ret;
-}
-
-void memcg_set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id)
-{
- if (shrinker_id >= 0 && memcg && !mem_cgroup_is_root(memcg)) {
- struct memcg_shrinker_map *map;
-
- rcu_read_lock();
- map = rcu_dereference(memcg->nodeinfo[nid]->shrinker_map);
- /* Pairs with smp mb in shrink_slab() */
- smp_mb__before_atomic();
- set_bit(shrinker_id, map->map);
- rcu_read_unlock();
- }
-}
-
/**
* mem_cgroup_css_from_page - css of the memcg associated with a page
* @page: page of interest
@@ -5369,11 +5246,11 @@ static int mem_cgroup_css_online(struct cgroup_subsys_state *css)
struct mem_cgroup *memcg = mem_cgroup_from_css(css);
/*
- * A memcg must be visible for memcg_expand_shrinker_maps()
+ * A memcg must be visible for expand_shrinker_maps()
* by the time the maps are allocated. So, we allocate maps
* here, when for_each_mem_cgroup() can't skip it.
*/
- if (memcg_alloc_shrinker_maps(memcg)) {
+ if (alloc_shrinker_maps(memcg)) {
mem_cgroup_id_remove(memcg);
return -ENOMEM;
}
@@ -5437,7 +5314,7 @@ static void mem_cgroup_css_free(struct cgroup_subsys_state *css)
vmpressure_cleanup(&memcg->vmpressure);
cancel_work_sync(&memcg->high_work);
mem_cgroup_remove_from_trees(memcg);
- memcg_free_shrinker_maps(memcg);
+ free_shrinker_maps(memcg);
memcg_free_kmem(memcg);
mem_cgroup_free(memcg);
}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b512dd5e3a1c..96b08c79f18d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -185,6 +185,131 @@ static LIST_HEAD(shrinker_list);
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)
+{
+ kvfree(container_of(head, struct memcg_shrinker_map, rcu));
+}
+
+static int expand_one_shrinker_map(struct mem_cgroup *memcg,
+ int size, int old_size)
+{
+ 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);
+ /* Not yet online memcg */
+ if (!old)
+ return 0;
+
+ new = kvmalloc_node(sizeof(*new) + size, GFP_KERNEL, nid);
+ if (!new)
+ return -ENOMEM;
+
+ /* Set all old bits, clear all new bits */
+ memset(new->map, (int)0xff, old_size);
+ memset((void *)new->map + old_size, 0, size - old_size);
+
+ rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_map, new);
+ call_rcu(&old->rcu, free_shrinker_map_rcu);
+ }
+
+ return 0;
+}
+
+void free_shrinker_maps(struct mem_cgroup *memcg)
+{
+ struct mem_cgroup_per_node *pn;
+ struct memcg_shrinker_map *map;
+ int nid;
+
+ if (mem_cgroup_is_root(memcg))
+ return;
+
+ for_each_node(nid) {
+ pn = mem_cgroup_nodeinfo(memcg, nid);
+ map = rcu_dereference_protected(pn->shrinker_map, true);
+ kvfree(map);
+ rcu_assign_pointer(pn->shrinker_map, NULL);
+ }
+}
+
+int alloc_shrinker_maps(struct mem_cgroup *memcg)
+{
+ struct memcg_shrinker_map *map;
+ int nid, size, ret = 0;
+
+ if (mem_cgroup_is_root(memcg))
+ return 0;
+
+ mutex_lock(&memcg_shrinker_map_mutex);
+ size = memcg_shrinker_map_size;
+ for_each_node(nid) {
+ map = kvzalloc_node(sizeof(*map) + size, GFP_KERNEL, nid);
+ if (!map) {
+ free_shrinker_maps(memcg);
+ ret = -ENOMEM;
+ break;
+ }
+ rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_map, map);
+ }
+ mutex_unlock(&memcg_shrinker_map_mutex);
+
+ return ret;
+}
+
+static int expand_shrinker_maps(int new_id)
+{
+ int size, old_size, ret = 0;
+ struct mem_cgroup *memcg;
+
+ size = DIV_ROUND_UP(new_id + 1, BITS_PER_LONG) * sizeof(unsigned long);
+ old_size = memcg_shrinker_map_size;
+ if (size <= old_size)
+ return 0;
+
+ mutex_lock(&memcg_shrinker_map_mutex);
+ if (!root_mem_cgroup)
+ goto unlock;
+
+ memcg = mem_cgroup_iter(NULL, NULL, NULL);
+ do {
+ if (mem_cgroup_is_root(memcg))
+ continue;
+ ret = expand_one_shrinker_map(memcg, size, old_size);
+ if (ret) {
+ mem_cgroup_iter_break(NULL, memcg);
+ goto unlock;
+ }
+ } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
+unlock:
+ if (!ret)
+ memcg_shrinker_map_size = size;
+ mutex_unlock(&memcg_shrinker_map_mutex);
+ return ret;
+}
+
+void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id)
+{
+ if (shrinker_id >= 0 && memcg && !mem_cgroup_is_root(memcg)) {
+ struct memcg_shrinker_map *map;
+
+ rcu_read_lock();
+ map = rcu_dereference(memcg->nodeinfo[nid]->shrinker_map);
+ /* Pairs with smp mb in shrink_slab() */
+ smp_mb__before_atomic();
+ set_bit(shrinker_id, map->map);
+ rcu_read_unlock();
+ }
+}
+
/*
* We allow subsystems to populate their shrinker-related
* LRU lists before register_shrinker_prepared() is called
@@ -212,7 +337,7 @@ static int prealloc_memcg_shrinker(struct shrinker *shrinker)
goto unlock;
if (id >= shrinker_nr_max) {
- if (memcg_expand_shrinker_maps(id)) {
+ if (expand_shrinker_maps(id)) {
idr_remove(&shrinker_idr, id);
goto unlock;
}
@@ -589,7 +714,7 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
* case, we invoke the shrinker one more time and reset
* the bit if it reports that it is not empty anymore.
* The memory barrier here pairs with the barrier in
- * memcg_set_shrinker_bit():
+ * set_shrinker_bit():
*
* list_lru_add() shrink_slab_memcg()
* list_add_tail() clear_bit()
@@ -601,7 +726,7 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
if (ret == SHRINK_EMPTY)
ret = 0;
else
- memcg_set_shrinker_bit(memcg, nid, i);
+ set_shrinker_bit(memcg, nid, i);
}
freed += ret;
--
2.26.2
next prev parent reply other threads:[~2021-02-09 17:54 UTC|newest]
Thread overview: 53+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20210209174646.1310591-1-shy828301@gmail.com>
2021-02-09 17:46 ` [v7 PATCH 01/12] mm: vmscan: use nid from shrink_control for tracepoint Yang Shi
2021-02-09 19:14 ` Shakeel Butt
2021-02-10 16:58 ` Yang Shi
2021-02-09 19:21 ` Roman Gushchin
2021-02-09 17:46 ` Yang Shi [this message]
2021-02-09 20:27 ` [v7 PATCH 02/12] mm: vmscan: consolidate shrinker_maps handling code Roman Gushchin
2021-02-10 14:19 ` Shakeel Butt
2021-02-09 17:46 ` [v7 PATCH 03/12] mm: vmscan: use shrinker_rwsem to protect shrinker_maps allocation Yang Shi
2021-02-09 20:33 ` Roman Gushchin
2021-02-09 23:28 ` Yang Shi
2021-02-09 17:46 ` [v7 PATCH 04/12] mm: vmscan: remove memcg_shrinker_map_size Yang Shi
2021-02-09 20:43 ` Roman Gushchin
2021-02-09 23:31 ` Yang Shi
2021-02-10 18:14 ` Vlastimil Babka
2021-02-09 17:46 ` [v7 PATCH 05/12] mm: memcontrol: rename shrinker_map to shrinker_info Yang Shi
2021-02-09 20:50 ` Roman Gushchin
2021-02-09 23:33 ` Yang Shi
2021-02-10 0:16 ` Roman Gushchin
2021-02-11 16:47 ` Kirill Tkhai
2021-02-11 17:29 ` Yang Shi
2021-02-09 17:46 ` [v7 PATCH 06/12] mm: vmscan: add shrinker_info_protected() helper Yang Shi
2021-02-10 0:22 ` Roman Gushchin
2021-02-10 1:07 ` Yang Shi
2021-02-10 1:29 ` Roman Gushchin
2021-02-10 12:12 ` Kirill Tkhai
2021-02-10 18:17 ` Vlastimil Babka
2021-02-12 6:54 ` [mm] bd741fb2ad: WARNING:suspicious_RCU_usage kernel test robot
2021-02-09 17:46 ` [v7 PATCH 07/12] mm: vmscan: use a new flag to indicate shrinker is registered Yang Shi
2021-02-10 0:39 ` Roman Gushchin
2021-02-10 1:12 ` Yang Shi
2021-02-10 1:34 ` Roman Gushchin
2021-02-10 1:55 ` Yang Shi
2021-02-10 18:45 ` Yang Shi
2021-02-10 18:23 ` Vlastimil Babka
2021-02-09 17:46 ` [v7 PATCH 08/12] mm: vmscan: add per memcg shrinker nr_deferred Yang Shi
2021-02-10 1:10 ` Roman Gushchin
2021-02-10 1:25 ` Yang Shi
2021-02-10 1:40 ` Roman Gushchin
2021-02-10 1:57 ` Yang Shi
2021-02-09 17:46 ` [v7 PATCH 09/12] mm: vmscan: use per memcg nr_deferred of shrinker Yang Shi
2021-02-10 1:27 ` Roman Gushchin
2021-02-10 1:52 ` Yang Shi
2021-02-10 14:36 ` Kirill Tkhai
2021-02-10 16:41 ` Yang Shi
2021-02-09 17:46 ` [v7 PATCH 10/12] mm: vmscan: don't need allocate shrinker->nr_deferred for memcg aware shrinkers Yang Shi
2021-02-10 1:23 ` Roman Gushchin
2021-02-09 17:46 ` [v7 PATCH 11/12] mm: memcontrol: reparent nr_deferred when memcg offline Yang Shi
2021-02-10 1:18 ` Roman Gushchin
2021-02-09 17:46 ` [v7 PATCH 12/12] mm: vmscan: shrink deferred objects proportional to priority Yang Shi
2021-02-11 13:10 ` Vlastimil Babka
2021-02-11 17:29 ` Yang Shi
2021-02-11 18:52 ` Vlastimil Babka
2021-02-11 19:15 ` Yang Shi
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=20210209174646.1310591-3-shy828301@gmail.com \
--to=shy828301@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=david@fromorbit.com \
--cc=guro@fb.com \
--cc=hannes@cmpxchg.org \
--cc=ktkhai@virtuozzo.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@suse.com \
--cc=shakeelb@google.com \
--cc=vbabka@suse.cz \
/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).