diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-12-15 14:55:10 -0800 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-12-15 14:55:10 -0800 |
| commit | 5b200f578960a9635918a0ed41be3d8dc90186bf (patch) | |
| tree | 8190f2278adec6e7dfc3bcdc00abf8e9b467af5d /include/linux/mmzone.h | |
| parent | 3db1a3fa98808aa90f95ec3e0fa2fc7abf28f5c9 (diff) | |
| parent | 15b447361794271f4d03c04d82276a841fe06328 (diff) | |
Merge branch 'akpm' (patches from Andrew)
Merge more updates from Andrew Morton:
"More MM work: a memcg scalability improvememt"
* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
mm/lru: revise the comments of lru_lock
mm/lru: introduce relock_page_lruvec()
mm/lru: replace pgdat lru_lock with lruvec lock
mm/swap.c: serialize memcg changes in pagevec_lru_move_fn
mm/compaction: do page isolation first in compaction
mm/lru: introduce TestClearPageLRU()
mm/mlock: remove __munlock_isolate_lru_page()
mm/mlock: remove lru_lock on TestClearPageMlocked
mm/vmscan: remove lruvec reget in move_pages_to_lru
mm/lru: move lock into lru_note_cost
mm/swap.c: fold vm event PGROTATED into pagevec_move_tail_fn
mm/memcg: add debug checking in lock_page_memcg
mm: page_idle_get_page() does not need lru_lock
mm/rmap: stop store reordering issue on page->mapping
mm/vmscan: remove unnecessary lruvec adding
mm/thp: narrow lru locking
mm/thp: simplify lru_add_page_tail()
mm/thp: use head for head page in lru_add_page_tail()
mm/thp: move lru_add_page_tail() to huge_memory.c
Diffstat (limited to 'include/linux/mmzone.h')
| -rw-r--r-- | include/linux/mmzone.h | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 98a80c01d150..b593316bff3d 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -113,8 +113,7 @@ static inline bool free_area_empty(struct free_area *area, int migratetype) struct pglist_data; /* - * zone->lock and the zone lru_lock are two of the hottest locks in the kernel. - * So add a wild amount of padding here to ensure that they fall into separate + * Add a wild amount of padding here to ensure datas fall into separate * cachelines. There are very few zone structures in the machine, so space * consumption is not a concern here. */ @@ -276,6 +275,8 @@ enum lruvec_flags { struct lruvec { struct list_head lists[NR_LRU_LISTS]; + /* per lruvec lru_lock for memcg */ + spinlock_t lru_lock; /* * These track the cost of reclaiming one LRU - file or anon - * over the other. As the observed cost of reclaiming one LRU @@ -782,7 +783,6 @@ typedef struct pglist_data { /* Write-intensive fields used by page reclaim */ ZONE_PADDING(_pad1_) - spinlock_t lru_lock; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* |