mm: memcontrol: convert NR_FILE_PMDMAPPED account to pages

Currently we use struct per_cpu_nodestat to cache the vmstat counters,
which leads to inaccurate statistics especially THP vmstat counters.  In
the systems with hundreds of processors it can be GBs of memory.  For
example, for a 96 CPUs system, the threshold is the maximum number of 125.
And the per cpu counters can cache 23.4375 GB in total.

The THP page is already a form of batched addition (it will add 512 worth
of memory in one go) so skipping the batching seems like sensible.
Although every THP stats update overflows the per-cpu counter, resorting
to atomic global updates.  But it can make the statistics more accuracy
for the THP vmstat counters.

So we convert the NR_FILE_PMDMAPPED account to pages.  This patch is
consistent with 8f182270dfec ("mm/swap.c: flush lru pvecs on compound page
arrival").  Doing this also can make the unit of vmstat counters more
unified.  Finally, the unit of the vmstat counters are pages, kB and
bytes.  The B/KB suffix can tell us that the unit is bytes or kB.  The
rest which is without suffix are pages.

Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Muchun Song <[email protected]>
Cc: Alexey Dobriyan <[email protected]>
Cc: Feng Tang <[email protected]>
Cc: Greg Kroah-Hartman <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Joonsoo Kim <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: NeilBrown <[email protected]>
Cc: Pankaj Gupta <[email protected]>
Cc: Rafael. J. Wysocki <[email protected]>
Cc: Randy Dunlap <[email protected]>
Cc: Roman Gushchin <[email protected]>
Cc: Sami Tolvanen <[email protected]>
Cc: Shakeel Butt <[email protected]>
Cc: Vladimir Davydov <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

diff --git a/drivers/base/node.c b/drivers/base/node.c
index 7a66aefe4e46e38ec887c5e22b7cd48008d399a2..d02d86aec19f5edb9de43081616079d2935e97de 100644 (file)
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -465,8 +465,7 @@ static ssize_t node_read_meminfo(struct device *dev,
                             nid, K(node_page_state(pgdat, NR_SHMEM_THPS)),
                             nid, K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED)),
                             nid, K(node_page_state(pgdat, NR_FILE_THPS)),
-                            nid, K(node_page_state(pgdat, NR_FILE_PMDMAPPED) *
-                                   HPAGE_PMD_NR)
+                            nid, K(node_page_state(pgdat, NR_FILE_PMDMAPPED))
 #endif
                            );
        len += hugetlb_report_node_meminfo(buf, len, nid);

diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index c61f440570f9387e4558d57c0f275b07220de1c5..6fa761c9cc78e0864479717b5ff1c362b1046030 100644 (file)
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -137,7 +137,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
        show_val_kb(m, "FileHugePages:  ",
                    global_node_page_state(NR_FILE_THPS));
        show_val_kb(m, "FilePmdMapped:  ",
-                   global_node_page_state(NR_FILE_PMDMAPPED) * HPAGE_PMD_NR);
+                   global_node_page_state(NR_FILE_PMDMAPPED));
 #endif
 
 #ifdef CONFIG_CMA

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 7bdbfeeb5c8c4d688fb2491b8a45eaadecdc0807..66d68e5d5a0f8ecb95db058282fc41cf9b0c666e 100644 (file)
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -222,7 +222,8 @@ static __always_inline bool vmstat_item_print_in_thp(enum node_stat_item item)
        return item == NR_ANON_THPS ||
               item == NR_FILE_THPS ||
               item == NR_SHMEM_THPS ||
-              item == NR_SHMEM_PMDMAPPED;
+              item == NR_SHMEM_PMDMAPPED ||
+              item == NR_FILE_PMDMAPPED;
 }
 
 /*

diff --git a/mm/rmap.c b/mm/rmap.c
index 1c1b576c06277541ca3e26bcd90bb5729d15574e..5ebf16fae4b9e14da45c60c0a267d9b06016f0bd 100644 (file)
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1223,7 +1223,8 @@ void page_add_file_rmap(struct page *page, bool compound)
                        __mod_lruvec_page_state(page, NR_SHMEM_PMDMAPPED,
                                                nr_pages);
                else
-                       __inc_node_page_state(page, NR_FILE_PMDMAPPED);
+                       __mod_lruvec_page_state(page, NR_FILE_PMDMAPPED,
+                                               nr_pages);
        } else {
                if (PageTransCompound(page) && page_mapping(page)) {
                        VM_WARN_ON_ONCE(!PageLocked(page));
@@ -1267,7 +1268,8 @@ static void page_remove_file_rmap(struct page *page, bool compound)
                        __mod_lruvec_page_state(page, NR_SHMEM_PMDMAPPED,
                                                -nr_pages);
                else
-                       __dec_node_page_state(page, NR_FILE_PMDMAPPED);
+                       __mod_lruvec_page_state(page, NR_FILE_PMDMAPPED,
+                                               -nr_pages);
        } else {
                if (!atomic_add_negative(-1, &page->_mapcount))
                        return;