mm: collect LRU list heads into struct lruvec
Having a unified structure with a LRU list set for both global zones and
per-memcg zones allows to keep that code simple which deals with LRU
lists and does not care about the container itself.
Once the per-memcg LRU lists directly link struct pages, the isolation
function and all other list manipulations are shared between the memcg
case and the global LRU case.
Signed-off-by: Johannes Weiner <jweiner@redhat.com>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Reviewed-by: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Ying Han <yinghan@google.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 8f7d247..e6a7ffe 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -33,7 +33,7 @@
static inline void
add_page_to_lru_list(struct zone *zone, struct page *page, enum lru_list l)
{
- __add_page_to_lru_list(zone, page, l, &zone->lru[l].list);
+ __add_page_to_lru_list(zone, page, l, &zone->lruvec.lists[l]);
}
static inline void
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index ca6ca92..42e544c 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -159,6 +159,10 @@
return (l == LRU_UNEVICTABLE);
}
+struct lruvec {
+ struct list_head lists[NR_LRU_LISTS];
+};
+
/* Mask used at gathering information at once (see memcontrol.c) */
#define LRU_ALL_FILE (BIT(LRU_INACTIVE_FILE) | BIT(LRU_ACTIVE_FILE))
#define LRU_ALL_ANON (BIT(LRU_INACTIVE_ANON) | BIT(LRU_ACTIVE_ANON))
@@ -364,10 +368,8 @@
ZONE_PADDING(_pad1_)
/* Fields commonly accessed by the page reclaim scanner */
- spinlock_t lru_lock;
- struct zone_lru {
- struct list_head list;
- } lru[NR_LRU_LISTS];
+ spinlock_t lru_lock;
+ struct lruvec lruvec;
struct zone_reclaim_stat reclaim_stat;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ad7f36f..6e7f849 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -134,10 +134,7 @@
* per-zone information in memory controller.
*/
struct mem_cgroup_per_zone {
- /*
- * spin_lock to protect the per cgroup LRU
- */
- struct list_head lists[NR_LRU_LISTS];
+ struct lruvec lruvec;
unsigned long count[NR_LRU_LISTS];
struct mem_cgroup_reclaim_iter reclaim_iter[DEF_PRIORITY + 1];
@@ -1061,7 +1058,7 @@
/* Ensure pc->mem_cgroup is visible after reading PCG_USED. */
smp_rmb();
mz = page_cgroup_zoneinfo(pc->mem_cgroup, page);
- list_move_tail(&pc->lru, &mz->lists[lru]);
+ list_move_tail(&pc->lru, &mz->lruvec.lists[lru]);
}
void mem_cgroup_rotate_lru_list(struct page *page, enum lru_list lru)
@@ -1079,7 +1076,7 @@
/* Ensure pc->mem_cgroup is visible after reading PCG_USED. */
smp_rmb();
mz = page_cgroup_zoneinfo(pc->mem_cgroup, page);
- list_move(&pc->lru, &mz->lists[lru]);
+ list_move(&pc->lru, &mz->lruvec.lists[lru]);
}
void mem_cgroup_add_lru_list(struct page *page, enum lru_list lru)
@@ -1109,7 +1106,7 @@
/* huge page split is done under lru_lock. so, we have no races. */
MEM_CGROUP_ZSTAT(mz, lru) += 1 << compound_order(page);
SetPageCgroupAcctLRU(pc);
- list_add(&pc->lru, &mz->lists[lru]);
+ list_add(&pc->lru, &mz->lruvec.lists[lru]);
}
/*
@@ -1307,7 +1304,7 @@
BUG_ON(!mem_cont);
mz = mem_cgroup_zoneinfo(mem_cont, nid, zid);
- src = &mz->lists[lru];
+ src = &mz->lruvec.lists[lru];
scan = 0;
list_for_each_entry_safe_reverse(pc, tmp, src, lru) {
@@ -3738,7 +3735,7 @@
zone = &NODE_DATA(node)->node_zones[zid];
mz = mem_cgroup_zoneinfo(memcg, node, zid);
- list = &mz->lists[lru];
+ list = &mz->lruvec.lists[lru];
loop = MEM_CGROUP_ZSTAT(mz, lru);
/* give some margin against EBUSY etc...*/
@@ -4864,7 +4861,7 @@
for (zone = 0; zone < MAX_NR_ZONES; zone++) {
mz = &pn->zoneinfo[zone];
for_each_lru(l)
- INIT_LIST_HEAD(&mz->lists[l]);
+ INIT_LIST_HEAD(&mz->lruvec.lists[l]);
mz->usage_in_excess = 0;
mz->on_tree = false;
mz->mem = memcg;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 794e671..25c248e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4288,7 +4288,7 @@
zone_pcp_init(zone);
for_each_lru(l)
- INIT_LIST_HEAD(&zone->lru[l].list);
+ INIT_LIST_HEAD(&zone->lruvec.lists[l]);
zone->reclaim_stat.recent_rotated[0] = 0;
zone->reclaim_stat.recent_rotated[1] = 0;
zone->reclaim_stat.recent_scanned[0] = 0;
diff --git a/mm/swap.c b/mm/swap.c
index 67a09a6..76ef79d 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -236,7 +236,7 @@
if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
enum lru_list lru = page_lru_base_type(page);
- list_move_tail(&page->lru, &zone->lru[lru].list);
+ list_move_tail(&page->lru, &zone->lruvec.lists[lru]);
mem_cgroup_rotate_reclaimable_page(page);
(*pgmoved)++;
}
@@ -480,7 +480,7 @@
* The page's writeback ends up during pagevec
* We moves tha page into tail of inactive.
*/
- list_move_tail(&page->lru, &zone->lru[lru].list);
+ list_move_tail(&page->lru, &zone->lruvec.lists[lru]);
mem_cgroup_rotate_reclaimable_page(page);
__count_vm_event(PGROTATED);
}
@@ -654,7 +654,6 @@
int active;
enum lru_list lru;
const int file = 0;
- struct list_head *head;
VM_BUG_ON(!PageHead(page));
VM_BUG_ON(PageCompound(page_tail));
@@ -674,10 +673,10 @@
}
update_page_reclaim_stat(zone, page_tail, file, active);
if (likely(PageLRU(page)))
- head = page->lru.prev;
+ __add_page_to_lru_list(zone, page_tail, lru,
+ page->lru.prev);
else
- head = &zone->lru[lru].list;
- __add_page_to_lru_list(zone, page_tail, lru, head);
+ add_page_to_lru_list(zone, page_tail, lru);
} else {
SetPageUnevictable(page_tail);
add_page_to_lru_list(zone, page_tail, LRU_UNEVICTABLE);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 024168c..93cdc44 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1250,8 +1250,8 @@
lru += LRU_ACTIVE;
if (file)
lru += LRU_FILE;
- return isolate_lru_pages(nr, &z->lru[lru].list, dst, scanned, order,
- mode, file);
+ return isolate_lru_pages(nr, &z->lruvec.lists[lru], dst,
+ scanned, order, mode, file);
}
/*
@@ -1630,7 +1630,7 @@
VM_BUG_ON(PageLRU(page));
SetPageLRU(page);
- list_move(&page->lru, &zone->lru[lru].list);
+ list_move(&page->lru, &zone->lruvec.lists[lru]);
mem_cgroup_add_lru_list(page, lru);
pgmoved += hpage_nr_pages(page);
@@ -3448,7 +3448,7 @@
enum lru_list l = page_lru_base_type(page);
__dec_zone_state(zone, NR_UNEVICTABLE);
- list_move(&page->lru, &zone->lru[l].list);
+ list_move(&page->lru, &zone->lruvec.lists[l]);
mem_cgroup_move_lists(page, LRU_UNEVICTABLE, l);
__inc_zone_state(zone, NR_INACTIVE_ANON + l);
__count_vm_event(UNEVICTABLE_PGRESCUED);
@@ -3457,7 +3457,7 @@
* rotate unevictable list
*/
SetPageUnevictable(page);
- list_move(&page->lru, &zone->lru[LRU_UNEVICTABLE].list);
+ list_move(&page->lru, &zone->lruvec.lists[LRU_UNEVICTABLE]);
mem_cgroup_rotate_lru_list(page, LRU_UNEVICTABLE);
if (page_evictable(page, NULL))
goto retry;