mm: use the light version __mod_zone_page_state in mlocked_vma_newpage()

mlocked_vma_newpage() is called with pte lock held(a spinlock), which
implies preemtion disabled, and the vm stat counter is not modified from
interrupt context, so we need not use an irq-safe mod_zone_page_state()
here, using a light-weight version __mod_zone_page_state() would be OK.

This patch also documents __mod_zone_page_state() and some of its
callsites.  The comment above __mod_zone_page_state() is from Hugh
Dickins, and acked by Christoph.

Most credits to Hugh and Christoph for the clarification on the usage of
the __mod_zone_page_state().

[akpm@linux-foundation.org: coding-style fixes]
Suggested-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Jianyu Zhan <nasa4836@gmail.com>
Reviewed-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/internal.h b/mm/internal.h
index a25424a24e0ce5ab0090d1acc8808d1937bf66bf..e067984bafa07c4ab34ef32419406c92e95a4902 100644 (file)
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -201,7 +201,12 @@ static inline int mlocked_vma_newpage(struct vm_area_struct *vma,
                return 0;
 
        if (!TestSetPageMlocked(page)) {
-               mod_zone_page_state(page_zone(page), NR_MLOCK,
+               /*
+                * We use the irq-unsafe __mod_zone_page_stat because this
+                * counter is not modified from interrupt context, and the pte
+                * lock is held(spinlock), which implies preemption disabled.
+                */
+               __mod_zone_page_state(page_zone(page), NR_MLOCK,
                                    hpage_nr_pages(page));
                count_vm_event(UNEVICTABLE_PGMLOCKED);
        }

diff --git a/mm/rmap.c b/mm/rmap.c
index 8754e1fa83b60e979b81c6be09397cd31f05f810..4644e10248f0f096c631484877be64a95194dbf2 100644 (file)
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -988,6 +988,12 @@ void do_page_add_anon_rmap(struct page *page,
 {
        int first = atomic_inc_and_test(&page->_mapcount);
        if (first) {
+               /*
+                * 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.
+                */
                if (PageTransHuge(page))
                        __inc_zone_page_state(page,
                                              NR_ANON_TRANSPARENT_HUGEPAGES);
@@ -1079,6 +1085,11 @@ void page_remove_rmap(struct page *page)
        /*
         * Hugepages are not counted in NR_ANON_PAGES nor NR_FILE_MAPPED
         * and not charged by memcg for now.
+        *
+        * We use the irq-unsafe __{inc|mod}_zone_page_stat because
+        * these counters are not modified in interrupt context, and
+        * these counters are not modified in interrupt context, and
+        * pte lock(a spinlock) is held, which implies preemption disabled.
         */
        if (unlikely(PageHuge(page)))
                goto out;

diff --git a/mm/vmstat.c b/mm/vmstat.c
index 376bd2d214824789842fb65f315c607d91ae3e3e..b37bd49bfd55e206e0845535bc42e7817502ce3b 100644 (file)
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -207,7 +207,9 @@ void set_pgdat_percpu_threshold(pg_data_t *pgdat,
 }
 
 /*
- * For use when we know that interrupts are disabled.
+ * For use when we know that interrupts are disabled,
+ * or when we know that preemption is disabled and that
+ * particular counter cannot be updated from interrupt context.
  */
 void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
                                int delta)