Thread (66 messages) 66 messages, 4 authors, 2020-07-21

Re: [PATCH v16 20/22] mm/vmscan: use relock for move_pages_to_lru

From: Alexander Duyck <hidden>
Date: 2020-07-17 21:44:27
Also in: linux-mm, lkml

On Fri, Jul 10, 2020 at 5:59 PM Alex Shi [off-list ref] wrote:
quoted hunk ↗ jump to hunk
From: Hugh Dickins <redacted>

Use the relock function to replace relocking action. And try to save few
lock times.

Signed-off-by: Hugh Dickins <redacted>
Signed-off-by: Alex Shi <alex.shi-KPsoFbNs7GizrGE5bRqYAgC/G2K4zDHf@public.gmane.org>
Cc: Andrew Morton <akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>
Cc: Tejun Heo <redacted>
Cc: Andrey Ryabinin <redacted>
Cc: Jann Horn <redacted>
Cc: Mel Gorman <redacted>
Cc: Johannes Weiner <redacted>
Cc: Matthew Wilcox <redacted>
Cc: Hugh Dickins <redacted>
Cc: cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Cc: linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Cc: linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org
---
 mm/vmscan.c | 17 ++++++-----------
 1 file changed, 6 insertions(+), 11 deletions(-)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index bdb53a678e7e..078a1640ec60 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1854,15 +1854,15 @@ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec,
        enum lru_list lru;

        while (!list_empty(list)) {
-               struct lruvec *new_lruvec = NULL;
-
                page = lru_to_page(list);
                VM_BUG_ON_PAGE(PageLRU(page), page);
                list_del(&page->lru);
                if (unlikely(!page_evictable(page))) {
-                       spin_unlock_irq(&lruvec->lru_lock);
+                       if (lruvec) {
+                               spin_unlock_irq(&lruvec->lru_lock);
+                               lruvec = NULL;
+                       }
                        putback_lru_page(page);
-                       spin_lock_irq(&lruvec->lru_lock);
                        continue;
                }
@@ -1876,12 +1876,7 @@ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec,
                 *                                        list_add(&page->lru,)
                 *     list_add(&page->lru,) //corrupt
                 */
-               new_lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
-               if (new_lruvec != lruvec) {
-                       if (lruvec)
-                               spin_unlock_irq(&lruvec->lru_lock);
-                       lruvec = lock_page_lruvec_irq(page);
-               }
+               lruvec = relock_page_lruvec_irq(page, lruvec);
                SetPageLRU(page);

                if (unlikely(put_page_testzero(page))) {
@@ -1890,8 +1885,8 @@ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec,

                        if (unlikely(PageCompound(page))) {
                                spin_unlock_irq(&lruvec->lru_lock);
+                               lruvec = NULL;
                                destroy_compound_page(page);
-                               spin_lock_irq(&lruvec->lru_lock);
                        } else
                                list_add(&page->lru, &pages_to_free);
It seems like this should just be rolled into patch 19. Otherwise if
you are wanting to consider it as a "further optimization" type patch
you might pull some of the optimizations you were pushing in patch 18
into this patch as well and just call it out as adding relocks where
there previously were none.
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help