mm: memcontrol: switch to native NR_ANON_MAPPED counter

Memcg maintains a private MEMCG_RSS counter.  This divergence from the
generic VM accounting means unnecessary code overhead, and creates a
dependency for memcg that page->mapping is set up at the time of charging,
so that page types can be told apart.

Convert the generic accounting sites to mod_lruvec_page_state and friends
to maintain the per-cgroup vmstat counter of NR_ANON_MAPPED.  We use
lock_page_memcg() to stabilize page->mem_cgroup during rmap changes, the
same way we do for NR_FILE_MAPPED.

With the previous patch removing MEMCG_CACHE and the private NR_SHMEM
counter, this patch finally eliminates the need to have page->mapping set
up at charge time.  However, we need to have page->mem_cgroup set up by
the time rmap runs and does the accounting, so switch the commit and the
rmap callbacks around.

v2: fix temporary accounting bug by switching rmap<->commit (Joonsoo)

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Alex Shi <alex.shi@linux.alibaba.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Link: http://lkml.kernel.org/r/20200508183105.225460-11-hannes@cmpxchg.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 29 insertions, 18 deletions

diff --git a/mm/rmap.c b/mm/rmap.c
index f79a206b271a..150513d31efa 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1114,6 +1114,11 @@ void do_page_add_anon_rmap(struct page *page,
 	bool compound = flags & RMAP_COMPOUND;
 	bool first;
 
+	if (unlikely(PageKsm(page)))
+		lock_page_memcg(page);
+	else
+		VM_BUG_ON_PAGE(!PageLocked(page), page);
+
 	if (compound) {
 		atomic_t *mapcount;
 		VM_BUG_ON_PAGE(!PageLocked(page), page);
@@ -1134,12 +1139,13 @@ void do_page_add_anon_rmap(struct page *page,
 		 */
 		if (compound)
 			__inc_node_page_state(page, NR_ANON_THPS);
-		__mod_node_page_state(page_pgdat(page), NR_ANON_MAPPED, nr);
+		__mod_lruvec_page_state(page, NR_ANON_MAPPED, nr);
 	}
-	if (unlikely(PageKsm(page)))
-		return;
 
-	VM_BUG_ON_PAGE(!PageLocked(page), page);
+	if (unlikely(PageKsm(page))) {
+		unlock_page_memcg(page);
+		return;
+	}
 
 	/* address might be in next vma when migration races vma_adjust */
 	if (first)
@@ -1181,7 +1187,7 @@ void page_add_new_anon_rmap(struct page *page,
 		/* increment count (starts at -1) */
 		atomic_set(&page->_mapcount, 0);
 	}
-	__mod_node_page_state(page_pgdat(page), NR_ANON_MAPPED, nr);
+	__mod_lruvec_page_state(page, NR_ANON_MAPPED, nr);
 	__page_set_anon_rmap(page, vma, address, 1);
 }
 
@@ -1230,13 +1236,12 @@ static void page_remove_file_rmap(struct page *page, bool compound)
 	int i, nr = 1;
 
 	VM_BUG_ON_PAGE(compound && !PageHead(page), page);
-	lock_page_memcg(page);
 
 	/* Hugepages are not counted in NR_FILE_MAPPED for now. */
 	if (unlikely(PageHuge(page))) {
 		/* hugetlb pages are always mapped with pmds */
 		atomic_dec(compound_mapcount_ptr(page));
-		goto out;
+		return;
 	}
 
 	/* page still mapped by someone else? */
@@ -1246,14 +1251,14 @@ static void page_remove_file_rmap(struct page *page, bool compound)
 				nr++;
 		}
 		if (!atomic_add_negative(-1, compound_mapcount_ptr(page)))
-			goto out;
+			return;
 		if (PageSwapBacked(page))
 			__dec_node_page_state(page, NR_SHMEM_PMDMAPPED);
 		else
 			__dec_node_page_state(page, NR_FILE_PMDMAPPED);
 	} else {
 		if (!atomic_add_negative(-1, &page->_mapcount))
-			goto out;
+			return;
 	}
 
 	/*
@@ -1265,8 +1270,6 @@ static void page_remove_file_rmap(struct page *page, bool compound)
 
 	if (unlikely(PageMlocked(page)))
 		clear_page_mlock(page);
-out:
-	unlock_page_memcg(page);
 }
 
 static void page_remove_anon_compound_rmap(struct page *page)
@@ -1310,7 +1313,7 @@ static void page_remove_anon_compound_rmap(struct page *page)
 		clear_page_mlock(page);
 
 	if (nr)
-		__mod_node_page_state(page_pgdat(page), NR_ANON_MAPPED, -nr);
+		__mod_lruvec_page_state(page, NR_ANON_MAPPED, -nr);
 }
 
 /**
@@ -1322,22 +1325,28 @@ static void page_remove_anon_compound_rmap(struct page *page)
  */
 void page_remove_rmap(struct page *page, bool compound)
 {
-	if (!PageAnon(page))
-		return page_remove_file_rmap(page, compound);
+	lock_page_memcg(page);
 
-	if (compound)
-		return page_remove_anon_compound_rmap(page);
+	if (!PageAnon(page)) {
+		page_remove_file_rmap(page, compound);
+		goto out;
+	}
+
+	if (compound) {
+		page_remove_anon_compound_rmap(page);
+		goto out;
+	}
 
 	/* page still mapped by someone else? */
 	if (!atomic_add_negative(-1, &page->_mapcount))
-		return;
+		goto out;
 
 	/*
 	 * We use the irq-unsafe __{inc|mod}_zone_page_stat because
 	 * these counters are not modified in interrupt context, and
 	 * pte lock(a spinlock) is held, which implies preemption disabled.
 	 */
-	__dec_node_page_state(page, NR_ANON_MAPPED);
+	__dec_lruvec_page_state(page, NR_ANON_MAPPED);
 
 	if (unlikely(PageMlocked(page)))
 		clear_page_mlock(page);
@@ -1354,6 +1363,8 @@ void page_remove_rmap(struct page *page, bool compound)
 	 * Leaving it set also helps swapoff to reinstate ptes
 	 * faster for those pages still in swapcache.
 	 */
+out:
+	unlock_page_memcg(page);
 }
 
 /*