summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
authorJohannes Weiner <hannes@cmpxchg.org>2019-11-30 17:55:34 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2019-12-01 12:59:06 -0800
commit867e5e1de14b2b2bde324cdfeec3f3f83eb21424 (patch)
tree22a8f8e2142314de860983c95d89fbe86b39cf1a /mm
parentde3b01506ea494b46aab05dc143b69adbf2aaa9d (diff)
mm: clean up and clarify lruvec lookup procedure
There is a per-memcg lruvec and a NUMA node lruvec. Which one is being used is somewhat confusing right now, and it's easy to make mistakes - especially when it comes to global reclaim. How it works: when memory cgroups are enabled, we always use the root_mem_cgroup's per-node lruvecs. When memory cgroups are not compiled in or disabled at runtime, we use pgdat->lruvec. Document that in a comment. Due to the way the reclaim code is generalized, all lookups use the mem_cgroup_lruvec() helper function, and nobody should have to find the right lruvec manually right now. But to avoid future mistakes, rename the pgdat->lruvec member to pgdat->__lruvec and delete the convenience wrapper that suggests it's a commonly accessed member. While in this area, swap the mem_cgroup_lruvec() argument order. The name suggests a memcg operation, yet it takes a pgdat first and a memcg second. I have to double take every time I call this. Fix that. Link: http://lkml.kernel.org/r/20191022144803.302233-3-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Michal Hocko <mhocko@suse.com> Reviewed-by: Shakeel Butt <shakeelb@google.com> Cc: Roman Gushchin <guro@fb.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/memcontrol.c10
-rw-r--r--mm/page_alloc.c2
-rw-r--r--mm/slab.h4
-rw-r--r--mm/vmscan.c6
-rw-r--r--mm/workingset.c8
5 files changed, 15 insertions, 15 deletions
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 529e12a59131..bc01423277c5 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -777,7 +777,7 @@ void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val)
if (!memcg || memcg == root_mem_cgroup) {
__mod_node_page_state(pgdat, idx, val);
} else {
- lruvec = mem_cgroup_lruvec(pgdat, memcg);
+ lruvec = mem_cgroup_lruvec(memcg, pgdat);
__mod_lruvec_state(lruvec, idx, val);
}
rcu_read_unlock();
@@ -1221,7 +1221,7 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgd
struct lruvec *lruvec;
if (mem_cgroup_disabled()) {
- lruvec = &pgdat->lruvec;
+ lruvec = &pgdat->__lruvec;
goto out;
}
@@ -3634,7 +3634,7 @@ static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css,
static unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
int nid, unsigned int lru_mask)
{
- struct lruvec *lruvec = mem_cgroup_lruvec(NODE_DATA(nid), memcg);
+ struct lruvec *lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(nid));
unsigned long nr = 0;
enum lru_list lru;
@@ -5338,8 +5338,8 @@ static int mem_cgroup_move_account(struct page *page,
anon = PageAnon(page);
pgdat = page_pgdat(page);
- from_vec = mem_cgroup_lruvec(pgdat, from);
- to_vec = mem_cgroup_lruvec(pgdat, to);
+ from_vec = mem_cgroup_lruvec(from, pgdat);
+ to_vec = mem_cgroup_lruvec(to, pgdat);
spin_lock_irqsave(&from->move_lock, flags);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e3a69ba5ec53..4785a8a2040e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6713,7 +6713,7 @@ static void __meminit pgdat_init_internals(struct pglist_data *pgdat)
pgdat_page_ext_init(pgdat);
spin_lock_init(&pgdat->lru_lock);
- lruvec_init(node_lruvec(pgdat));
+ lruvec_init(&pgdat->__lruvec);
}
static void __meminit zone_init_internals(struct zone *zone, enum zone_type idx, int nid,
diff --git a/mm/slab.h b/mm/slab.h
index 8b77f973a6ab..7e94700aa78c 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -369,7 +369,7 @@ static __always_inline int memcg_charge_slab(struct page *page,
if (ret)
goto out;
- lruvec = mem_cgroup_lruvec(page_pgdat(page), memcg);
+ lruvec = mem_cgroup_lruvec(memcg, page_pgdat(page));
mod_lruvec_state(lruvec, cache_vmstat_idx(s), 1 << order);
/* transer try_charge() page references to kmem_cache */
@@ -393,7 +393,7 @@ static __always_inline void memcg_uncharge_slab(struct page *page, int order,
rcu_read_lock();
memcg = READ_ONCE(s->memcg_params.memcg);
if (likely(!mem_cgroup_is_root(memcg))) {
- lruvec = mem_cgroup_lruvec(page_pgdat(page), memcg);
+ lruvec = mem_cgroup_lruvec(memcg, page_pgdat(page));
mod_lruvec_state(lruvec, cache_vmstat_idx(s), -(1 << order));
memcg_kmem_uncharge_memcg(page, order, memcg);
} else {
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 266620f7c814..94d73725813d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2545,7 +2545,7 @@ out:
static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memcg,
struct scan_control *sc)
{
- struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg);
+ struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
unsigned long nr[NR_LRU_LISTS];
unsigned long targets[NR_LRU_LISTS];
unsigned long nr_to_scan;
@@ -3023,7 +3023,7 @@ static void snapshot_refaults(struct mem_cgroup *root_memcg, pg_data_t *pgdat)
unsigned long refaults;
struct lruvec *lruvec;
- lruvec = mem_cgroup_lruvec(pgdat, memcg);
+ lruvec = mem_cgroup_lruvec(memcg, pgdat);
refaults = lruvec_page_state_local(lruvec, WORKINGSET_ACTIVATE);
lruvec->refaults = refaults;
} while ((memcg = mem_cgroup_iter(root_memcg, memcg, NULL)));
@@ -3379,7 +3379,7 @@ static void age_active_anon(struct pglist_data *pgdat,
memcg = mem_cgroup_iter(NULL, NULL, NULL);
do {
- struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg);
+ struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
if (inactive_list_is_low(lruvec, false, sc, true))
shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
diff --git a/mm/workingset.c b/mm/workingset.c
index c963831d354f..e8212123c1c3 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -233,7 +233,7 @@ void *workingset_eviction(struct page *page)
VM_BUG_ON_PAGE(page_count(page), page);
VM_BUG_ON_PAGE(!PageLocked(page), page);
- lruvec = mem_cgroup_lruvec(pgdat, memcg);
+ lruvec = mem_cgroup_lruvec(memcg, pgdat);
eviction = atomic_long_inc_return(&lruvec->inactive_age);
return pack_shadow(memcgid, pgdat, eviction, PageWorkingset(page));
}
@@ -280,7 +280,7 @@ void workingset_refault(struct page *page, void *shadow)
memcg = mem_cgroup_from_id(memcgid);
if (!mem_cgroup_disabled() && !memcg)
goto out;
- lruvec = mem_cgroup_lruvec(pgdat, memcg);
+ lruvec = mem_cgroup_lruvec(memcg, pgdat);
refault = atomic_long_read(&lruvec->inactive_age);
active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES);
@@ -345,7 +345,7 @@ void workingset_activation(struct page *page)
memcg = page_memcg_rcu(page);
if (!mem_cgroup_disabled() && !memcg)
goto out;
- lruvec = mem_cgroup_lruvec(page_pgdat(page), memcg);
+ lruvec = mem_cgroup_lruvec(memcg, page_pgdat(page));
atomic_long_inc(&lruvec->inactive_age);
out:
rcu_read_unlock();
@@ -426,7 +426,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker,
struct lruvec *lruvec;
int i;
- lruvec = mem_cgroup_lruvec(NODE_DATA(sc->nid), sc->memcg);
+ lruvec = mem_cgroup_lruvec(sc->memcg, NODE_DATA(sc->nid));
for (pages = 0, i = 0; i < NR_LRU_LISTS; i++)
pages += lruvec_page_state_local(lruvec,
NR_LRU_BASE + i);