mm: memcontrol: convert NR_SHMEM_THPS 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_SHMEM_THPS 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/20201228164110.2838-5-songmuchun@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Feng Tang <feng.tang@intel.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: NeilBrown <neilb@suse.de>
Cc: Pankaj Gupta <pankaj.gupta@cloud.ionos.com>
Cc: Rafael. J. Wysocki <rafael@kernel.org>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Roman Gushchin <guro@fb.com>
Cc: Sami Tolvanen <samitolvanen@google.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/drivers/base/node.c b/drivers/base/node.c
index d5952f7549115534359fad78e38a04347a106284..6d5ac6ffb6e1793cdced6cb8d970916c609bfc80 100644 (file)
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -462,8 +462,7 @@ static ssize_t node_read_meminfo(struct device *dev,
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
                             ,
                             nid, K(node_page_state(pgdat, NR_ANON_THPS)),
-                            nid, K(node_page_state(pgdat, NR_SHMEM_THPS) *
-                                   HPAGE_PMD_NR),
+                            nid, K(node_page_state(pgdat, NR_SHMEM_THPS)),
                             nid, K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED) *
                                    HPAGE_PMD_NR),
                             nid, K(node_page_state(pgdat, NR_FILE_THPS)),

diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 7ea4679880c8dfdf197fe621ce056befedc8a2a1..cfb107eaa3e61c8f614ac4f3160757bc54b4333f 100644 (file)
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -131,7 +131,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
        show_val_kb(m, "AnonHugePages:  ",
                    global_node_page_state(NR_ANON_THPS));
        show_val_kb(m, "ShmemHugePages: ",
-                   global_node_page_state(NR_SHMEM_THPS) * HPAGE_PMD_NR);
+                   global_node_page_state(NR_SHMEM_THPS));
        show_val_kb(m, "ShmemPmdMapped: ",
                    global_node_page_state(NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR);
        show_val_kb(m, "FileHugePages:  ",

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index b751a9898bb6895989b523d152b0350f3f0728e5..788837f40b38a080623bc0c24807203e31af1d06 100644 (file)
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -220,7 +220,8 @@ static __always_inline bool vmstat_item_print_in_thp(enum node_stat_item item)
                return false;
 
        return item == NR_ANON_THPS ||
-              item == NR_FILE_THPS;
+              item == NR_FILE_THPS ||
+              item == NR_SHMEM_THPS;
 }
 
 /*

diff --git a/mm/filemap.c b/mm/filemap.c
index c7527f7607123663889348124d2171357e187b03..b7a4b1516aad303a09dca39167835640015ada8c 100644 (file)
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -204,7 +204,7 @@ 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_lruvec_page_state(page, NR_SHMEM_THPS);
+                       __mod_lruvec_page_state(page, NR_SHMEM_THPS, -nr);
        } else if (PageTransHuge(page)) {
                __mod_lruvec_page_state(page, NR_FILE_THPS, -nr);
                filemap_nr_thps_dec(mapping);

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 5f2c9f676bd777b37642374e7870e4c588efe0f0..db1585ee25dbfc2017ee62f9219c9e68fe5a0096 100644 (file)
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2746,7 +2746,8 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
                        int nr = thp_nr_pages(head);
 
                        if (PageSwapBacked(head))
-                               __dec_lruvec_page_state(head, NR_SHMEM_THPS);
+                               __mod_lruvec_page_state(head, NR_SHMEM_THPS,
+                                                       -nr);
                        else
                                __mod_lruvec_page_state(head, NR_FILE_THPS,
                                                        -nr);

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index ca57dec62f26f0a37e79e5130ee1113c6078e145..64b4558737110e6492340e1fe4236632369d2955 100644 (file)
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1859,7 +1859,7 @@ out_unlock:
        nr = thp_nr_pages(new_page);
 
        if (is_shmem)
-               __inc_lruvec_page_state(new_page, NR_SHMEM_THPS);
+               __mod_lruvec_page_state(new_page, NR_SHMEM_THPS, nr);
        else {
                __mod_lruvec_page_state(new_page, NR_FILE_THPS, nr);
                filemap_nr_thps_inc(mapping);

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index cb3e495920a9911f325756e864c1574b5fa3026e..9515522d60d66ae4c518d4944686ad6eddb47fe3 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1516,7 +1516,7 @@ struct memory_stat {
        unsigned int idx;
 };
 
-static struct memory_stat memory_stats[] = {
+static const struct memory_stat memory_stats[] = {
        { "anon", PAGE_SIZE, NR_ANON_MAPPED },
        { "file", PAGE_SIZE, NR_FILE_PAGES },
        { "kernel_stack", 1024, NR_KERNEL_STACK_KB },
@@ -1528,14 +1528,9 @@ static struct memory_stat memory_stats[] = {
        { "file_dirty", PAGE_SIZE, NR_FILE_DIRTY },
        { "file_writeback", PAGE_SIZE, NR_WRITEBACK },
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-       /*
-        * The ratio will be initialized in memory_stats_init(). Because
-        * on some architectures, the macro of HPAGE_PMD_SIZE is not
-        * constant(e.g. powerpc).
-        */
        { "anon_thp", PAGE_SIZE, NR_ANON_THPS },
        { "file_thp", PAGE_SIZE, NR_FILE_THPS },
-       { "shmem_thp", 0, NR_SHMEM_THPS },
+       { "shmem_thp", PAGE_SIZE, NR_SHMEM_THPS },
 #endif
        { "inactive_anon", PAGE_SIZE, NR_INACTIVE_ANON },
        { "active_anon", PAGE_SIZE, NR_ACTIVE_ANON },
@@ -1560,23 +1555,6 @@ static struct memory_stat memory_stats[] = {
        { "workingset_nodereclaim", 1, WORKINGSET_NODERECLAIM },
 };
 
-static int __init memory_stats_init(void)
-{
-       int i;
-
-       for (i = 0; i < ARRAY_SIZE(memory_stats); i++) {
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-               if (memory_stats[i].idx == NR_SHMEM_THPS)
-                       memory_stats[i].ratio = HPAGE_PMD_SIZE;
-#endif
-               VM_BUG_ON(!memory_stats[i].ratio);
-               VM_BUG_ON(memory_stats[i].idx >= MEMCG_NR_STAT);
-       }
-
-       return 0;
-}
-pure_initcall(memory_stats_init);
-
 static char *memory_stat_format(struct mem_cgroup *memcg)
 {
        struct seq_buf s;

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8fb5b23e186abdcffcff3cddade551af0793832c..cf60678a7280cf898233f08f2bdecaf9f1f31efa 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5580,7 +5580,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
                        K(node_page_state(pgdat, NR_WRITEBACK)),
                        K(node_page_state(pgdat, NR_SHMEM)),
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-                       K(node_page_state(pgdat, NR_SHMEM_THPS) * HPAGE_PMD_NR),
+                       K(node_page_state(pgdat, NR_SHMEM_THPS)),
                        K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED)
                                        * HPAGE_PMD_NR),
                        K(node_page_state(pgdat, NR_ANON_THPS)),

diff --git a/mm/shmem.c b/mm/shmem.c
index 7c6b6d8f6c396d5c9f608a17983fbe7691c6b9cf..8da789140ca54ecb1a72f35d7f5d9660a403548d 100644 (file)
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -713,7 +713,7 @@ next:
                }
                if (PageTransHuge(page)) {
                        count_vm_event(THP_FILE_ALLOC);
-                       __inc_lruvec_page_state(page, NR_SHMEM_THPS);
+                       __mod_lruvec_page_state(page, NR_SHMEM_THPS, nr);
                }
                mapping->nrpages += nr;
                __mod_lruvec_page_state(page, NR_FILE_PAGES, nr);