mm: memcontrol: add file_thp, shmem_thp to memory.stat

As huge page usage in the page cache and for shmem files proliferates in
our production environment, the performance monitoring team has asked for
per-cgroup stats on those pages.

We already track and export anon_thp per cgroup.  We already track file
THP and shmem THP per node, so making them per-cgroup is only a matter of
switching from node to lruvec counters.  All callsites are in places where
the pages are charged and locked, so page->memcg is stable.

[hannes@cmpxchg.org: add documentation]
  Link: https://lkml.kernel.org/r/20201026174029.GC548555@cmpxchg.org

Link: https://lkml.kernel.org/r/20201022151844.489337-1-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@surriel.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: David Rientjes <rientjes@google.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

6 files changed, 20 insertions, 8 deletions

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 608d7c279396..515bb13084a0 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1300,6 +1300,14 @@ PAGE_SIZE multiple when read back.
 		Amount of memory used in anonymous mappings backed by
 		transparent hugepages
 
+	  file_thp
+		Amount of cached filesystem data backed by transparent
+		hugepages
+
+	  shmem_thp
+		Amount of shm, tmpfs, shared anonymous mmap()s backed by
+		transparent hugepages
+
 	  inactive_anon, active_anon, inactive_file, active_file, unevictable
 		Amount of memory, swap-backed and filesystem-backed,
 		on the internal memory management lists used by the
diff --git a/mm/filemap.c b/mm/filemap.c
index 343ba8571ff9..39bb88140680 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -204,9 +204,9 @@ static void unaccount_page_cache_page(struct address_space *mapping,
 	if (PageSwapBacked(page)) {
 		__mod_lruvec_page_state(page, NR_SHMEM, -nr);
 		if (PageTransHuge(page))
-			__dec_node_page_state(page, NR_SHMEM_THPS);
+			__dec_lruvec_page_state(page, NR_SHMEM_THPS);
 	} else if (PageTransHuge(page)) {
-		__dec_node_page_state(page, NR_FILE_THPS);
+		__dec_lruvec_page_state(page, NR_FILE_THPS);
 		filemap_nr_thps_dec(mapping);
 	}
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index ec2bb93f7431..42b18d461086 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2710,9 +2710,9 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		spin_unlock(&ds_queue->split_queue_lock);
 		if (mapping) {
 			if (PageSwapBacked(head))
-				__dec_node_page_state(head, NR_SHMEM_THPS);
+				__dec_lruvec_page_state(head, NR_SHMEM_THPS);
 			else
-				__dec_node_page_state(head, NR_FILE_THPS);
+				__dec_lruvec_page_state(head, NR_FILE_THPS);
 		}
 
 		__split_huge_page(page, list, end, flags);
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 4e3dff13eb70..757292532767 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1845,9 +1845,9 @@ out_unlock:
 	}
 
 	if (is_shmem)
-		__inc_node_page_state(new_page, NR_SHMEM_THPS);
+		__inc_lruvec_page_state(new_page, NR_SHMEM_THPS);
 	else {
-		__inc_node_page_state(new_page, NR_FILE_THPS);
+		__inc_lruvec_page_state(new_page, NR_FILE_THPS);
 		filemap_nr_thps_inc(mapping);
 	}
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 29459a6ce1c7..c3654510fb70 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1512,6 +1512,8 @@ static struct memory_stat memory_stats[] = {
 	 * constant(e.g. powerpc).
 	 */
 	{ "anon_thp", 0, NR_ANON_THPS },
+	{ "file_thp", 0, NR_FILE_THPS },
+	{ "shmem_thp", 0, NR_SHMEM_THPS },
 #endif
 	{ "inactive_anon", PAGE_SIZE, NR_INACTIVE_ANON },
 	{ "active_anon", PAGE_SIZE, NR_ACTIVE_ANON },
@@ -1542,7 +1544,9 @@ static int __init memory_stats_init(void)
 
 	for (i = 0; i < ARRAY_SIZE(memory_stats); i++) {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-		if (memory_stats[i].idx == NR_ANON_THPS)
+		if (memory_stats[i].idx == NR_ANON_THPS ||
+		    memory_stats[i].idx == NR_FILE_THPS ||
+		    memory_stats[i].idx == NR_SHMEM_THPS)
 			memory_stats[i].ratio = HPAGE_PMD_SIZE;
 #endif
 		VM_BUG_ON(!memory_stats[i].ratio);
diff --git a/mm/shmem.c b/mm/shmem.c
index b7361fce50bc..67ff829e2f0e 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -713,7 +713,7 @@ next:
 		}
 		if (PageTransHuge(page)) {
 			count_vm_event(THP_FILE_ALLOC);
-			__inc_node_page_state(page, NR_SHMEM_THPS);
+			__inc_lruvec_page_state(page, NR_SHMEM_THPS);
 		}
 		mapping->nrpages += nr;
 		__mod_lruvec_page_state(page, NR_FILE_PAGES, nr);