mm: memcontrol: per-lruvec stats infrastructure

lruvecs are at the intersection of the NUMA node and memcg, which is the
scope for most paging activity.

Introduce a convenient accounting infrastructure that maintains
statistics per node, per memcg, and the lruvec itself.

Then convert over accounting sites for statistics that are already
tracked in both nodes and memcgs and can be easily switched.

[hannes@cmpxchg.org: fix crash in the new cgroup stat keeping code]
  Link: http://lkml.kernel.org/r/20170531171450.GA10481@cmpxchg.org
[hannes@cmpxchg.org: don't track uncharged pages at all
  Link: http://lkml.kernel.org/r/20170605175254.GA8547@cmpxchg.org
[hannes@cmpxchg.org: add missing free_percpu()]
  Link: http://lkml.kernel.org/r/20170605175354.GB8547@cmpxchg.org
[linux@roeck-us.net: hexagon: fix build error caused by include file order]
  Link: http://lkml.kernel.org/r/20170617153721.GA4382@roeck-us.net
Link: http://lkml.kernel.org/r/20170530181724.27197-6-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Josef Bacik <josef@toxicpanda.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

4 files changed, 21 insertions, 22 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index dceb0de..425aa0c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4122,6 +4122,12 @@ static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 	if (!pn)
 		return 1;
 
+	pn->lruvec_stat = alloc_percpu(struct lruvec_stat);
+	if (!pn->lruvec_stat) {
+		kfree(pn);
+		return 1;
+	}
+
 	lruvec_init(&pn->lruvec);
 	pn->usage_in_excess = 0;
 	pn->on_tree = false;
@@ -4133,7 +4139,10 @@ static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 
 static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 {
-	kfree(memcg->nodeinfo[node]);
+	struct mem_cgroup_per_node *pn = memcg->nodeinfo[node];
+
+	free_percpu(pn->lruvec_stat);
+	kfree(pn);
 }
 
 static void __mem_cgroup_free(struct mem_cgroup *memcg)
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 143c1c2..8989ead 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2433,8 +2433,7 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
 		inode_attach_wb(inode, page);
 		wb = inode_to_wb(inode);
 
-		inc_memcg_page_state(page, NR_FILE_DIRTY);
-		__inc_node_page_state(page, NR_FILE_DIRTY);
+		__inc_lruvec_page_state(page, NR_FILE_DIRTY);
 		__inc_zone_page_state(page, NR_ZONE_WRITE_PENDING);
 		__inc_node_page_state(page, NR_DIRTIED);
 		__inc_wb_stat(wb, WB_RECLAIMABLE);
@@ -2455,8 +2454,7 @@ void account_page_cleaned(struct page *page, struct address_space *mapping,
 			  struct bdi_writeback *wb)
 {
 	if (mapping_cap_account_dirty(mapping)) {
-		dec_memcg_page_state(page, NR_FILE_DIRTY);
-		dec_node_page_state(page, NR_FILE_DIRTY);
+		dec_lruvec_page_state(page, NR_FILE_DIRTY);
 		dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
 		dec_wb_stat(wb, WB_RECLAIMABLE);
 		task_io_account_cancelled_write(PAGE_SIZE);
@@ -2712,8 +2710,7 @@ int clear_page_dirty_for_io(struct page *page)
 		 */
 		wb = unlocked_inode_to_wb_begin(inode, &locked);
 		if (TestClearPageDirty(page)) {
-			dec_memcg_page_state(page, NR_FILE_DIRTY);
-			dec_node_page_state(page, NR_FILE_DIRTY);
+			dec_lruvec_page_state(page, NR_FILE_DIRTY);
 			dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
 			dec_wb_stat(wb, WB_RECLAIMABLE);
 			ret = 1;
@@ -2759,8 +2756,7 @@ int test_clear_page_writeback(struct page *page)
 		ret = TestClearPageWriteback(page);
 	}
 	if (ret) {
-		dec_memcg_page_state(page, NR_WRITEBACK);
-		dec_node_page_state(page, NR_WRITEBACK);
+		dec_lruvec_page_state(page, NR_WRITEBACK);
 		dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
 		inc_node_page_state(page, NR_WRITTEN);
 	}
@@ -2814,8 +2810,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
 		ret = TestSetPageWriteback(page);
 	}
 	if (!ret) {
-		inc_memcg_page_state(page, NR_WRITEBACK);
-		inc_node_page_state(page, NR_WRITEBACK);
+		inc_lruvec_page_state(page, NR_WRITEBACK);
 		inc_zone_page_state(page, NR_ZONE_WRITE_PENDING);
 	}
 	unlock_page_memcg(page);
diff --git a/mm/rmap.c b/mm/rmap.c
index b255743..ced14f1 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1145,8 +1145,7 @@ void page_add_file_rmap(struct page *page, bool compound)
 		if (!atomic_inc_and_test(&page->_mapcount))
 			goto out;
 	}
-	__mod_node_page_state(page_pgdat(page), NR_FILE_MAPPED, nr);
-	mod_memcg_page_state(page, NR_FILE_MAPPED, nr);
+	__mod_lruvec_page_state(page, NR_FILE_MAPPED, nr);
 out:
 	unlock_page_memcg(page);
 }
@@ -1181,12 +1180,11 @@ static void page_remove_file_rmap(struct page *page, bool compound)
 	}
 
 	/*
-	 * We use the irq-unsafe __{inc|mod}_zone_page_state because
+	 * We use the irq-unsafe __{inc|mod}_lruvec_page_state because
 	 * these counters are not modified in interrupt context, and
 	 * pte lock(a spinlock) is held, which implies preemption disabled.
 	 */
-	__mod_node_page_state(page_pgdat(page), NR_FILE_MAPPED, -nr);
-	mod_memcg_page_state(page, NR_FILE_MAPPED, -nr);
+	__mod_lruvec_page_state(page, NR_FILE_MAPPED, -nr);
 
 	if (unlikely(PageMlocked(page)))
 		clear_page_mlock(page);
diff --git a/mm/workingset.c b/mm/workingset.c
index b8c9ab6..7119cd7 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -288,12 +288,10 @@ bool workingset_refault(void *shadow)
 	 */
 	refault_distance = (refault - eviction) & EVICTION_MASK;
 
-	inc_node_state(pgdat, WORKINGSET_REFAULT);
-	inc_memcg_state(memcg, WORKINGSET_REFAULT);
+	inc_lruvec_state(lruvec, WORKINGSET_REFAULT);
 
 	if (refault_distance <= active_file) {
-		inc_node_state(pgdat, WORKINGSET_ACTIVATE);
-		inc_memcg_state(memcg, WORKINGSET_ACTIVATE);
+		inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE);
 		rcu_read_unlock();
 		return true;
 	}
@@ -474,8 +472,7 @@ static enum lru_status shadow_lru_isolate(struct list_head *item,
 	}
 	if (WARN_ON_ONCE(node->exceptional))
 		goto out_invalid;
-	inc_node_state(page_pgdat(virt_to_page(node)), WORKINGSET_NODERECLAIM);
-	inc_memcg_page_state(virt_to_page(node), WORKINGSET_NODERECLAIM);
+	inc_lruvec_page_state(virt_to_page(node), WORKINGSET_NODERECLAIM);
 	__radix_tree_delete_node(&mapping->page_tree, node,
 				 workingset_update_node, mapping);