The patch titled
Subject: memcg: make mem_cgroup_split_huge_fixup() more efficient
has been added to the -mm tree. Its filename is
memcg-make-mem_cgroup_split_huge_fixup-more-efficient.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Subject: memcg: make mem_cgroup_split_huge_fixup() more efficient
In split_huge_page(), mem_cgroup_split_huge_fixup() is called to handle
page_cgroup modifcations. It takes move_lock_page_cgroup() and modifies
page_cgroup and LRU accounting jobs and called HPAGE_PMD_SIZE - 1 times.
But thinking again,
- compound_lock() is held at move_accout...then, it's not necessary
to take move_lock_page_cgroup().
- LRU is locked and all tail pages will go into the same LRU as
head is now on.
- page_cgroup is contiguous in huge page range.
This patch fixes mem_cgroup_split_huge_fixup() as to be called once per
hugepage and reduce costs for spliting.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxx>
Cc: Balbir Singh <bsingharora@xxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/memcontrol.h | 5 ++---
mm/huge_memory.c | 3 ++-
mm/memcontrol.c | 32 ++++++++++++++++----------------
3 files changed, 20 insertions(+), 20 deletions(-)
diff -puN include/linux/memcontrol.h~memcg-make-mem_cgroup_split_huge_fixup-more-efficient include/linux/memcontrol.h
--- a/include/linux/memcontrol.h~memcg-make-mem_cgroup_split_huge_fixup-more-efficient
+++ a/include/linux/memcontrol.h
@@ -158,7 +158,7 @@ u64 mem_cgroup_get_limit(struct mem_cgro
void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx);
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-void mem_cgroup_split_huge_fixup(struct page *head, struct page *tail);
+void mem_cgroup_split_huge_fixup(struct page *head);
#endif
#ifdef CONFIG_DEBUG_VM
@@ -374,8 +374,7 @@ u64 mem_cgroup_get_limit(struct mem_cgro
return 0;
}
-static inline void mem_cgroup_split_huge_fixup(struct page *head,
- struct page *tail)
+static inline void mem_cgroup_split_huge_fixup(struct page *head)
{
}
diff -puN mm/huge_memory.c~memcg-make-mem_cgroup_split_huge_fixup-more-efficient mm/huge_memory.c
--- a/mm/huge_memory.c~memcg-make-mem_cgroup_split_huge_fixup-more-efficient
+++ a/mm/huge_memory.c
@@ -1207,6 +1207,8 @@ static void __split_huge_page_refcount(s
/* prevent PageLRU to go away from under us, and freeze lru stats */
spin_lock_irq(&zone->lru_lock);
compound_lock(page);
+ /* complete memcg works before add pages to LRU */
+ mem_cgroup_split_huge_fixup(page);
for (i = 1; i < HPAGE_PMD_NR; i++) {
struct page *page_tail = page + i;
@@ -1278,7 +1280,6 @@ static void __split_huge_page_refcount(s
BUG_ON(!PageDirty(page_tail));
BUG_ON(!PageSwapBacked(page_tail));
- mem_cgroup_split_huge_fixup(page, page_tail);
lru_add_page_tail(zone, page, page_tail);
}
diff -puN mm/memcontrol.c~memcg-make-mem_cgroup_split_huge_fixup-more-efficient mm/memcontrol.c
--- a/mm/memcontrol.c~memcg-make-mem_cgroup_split_huge_fixup-more-efficient
+++ a/mm/memcontrol.c
@@ -2488,38 +2488,38 @@ static void __mem_cgroup_commit_charge(s
/*
* Because tail pages are not marked as "used", set it. We're under
* zone->lru_lock, 'splitting on pmd' and compund_lock.
+ * charge/uncharge will be never happen and move_account() is done under
+ * compound_lock(), so we don't have to take care of races.
*/
-void mem_cgroup_split_huge_fixup(struct page *head, struct page *tail)
+void mem_cgroup_split_huge_fixup(struct page *head)
{
struct page_cgroup *head_pc = lookup_page_cgroup(head);
- struct page_cgroup *tail_pc = lookup_page_cgroup(tail);
- unsigned long flags;
+ struct page_cgroup *pc;
+ int i;
if (mem_cgroup_disabled())
return;
- /*
- * We have no races with charge/uncharge but will have races with
- * page state accounting.
- */
- move_lock_page_cgroup(head_pc, &flags);
+ for (i = 1; i < HPAGE_PMD_NR; i++) {
+ pc = head_pc + i;
+ pc->mem_cgroup = head_pc->mem_cgroup;
+ smp_wmb();/* see __commit_charge() */
+ /*
+ * LRU flags cannot be copied because we need to add tail
+ * page to LRU by generic call and our hooks will be called.
+ */
+ pc->flags = head_pc->flags & ~PCGF_NOCOPY_AT_SPLIT;
+ }
- tail_pc->mem_cgroup = head_pc->mem_cgroup;
- smp_wmb(); /* see __commit_charge() */
if (PageCgroupAcctLRU(head_pc)) {
enum lru_list lru;
struct mem_cgroup_per_zone *mz;
-
/*
- * LRU flags cannot be copied because we need to add tail
- *.page to LRU by generic call and our hook will be called.
* We hold lru_lock, then, reduce counter directly.
*/
lru = page_lru(head);
mz = page_cgroup_zoneinfo(head_pc->mem_cgroup, head);
- MEM_CGROUP_ZSTAT(mz, lru) -= 1;
+ MEM_CGROUP_ZSTAT(mz, lru) -= HPAGE_PMD_NR - 1;
}
- tail_pc->flags = head_pc->flags & ~PCGF_NOCOPY_AT_SPLIT;
- move_unlock_page_cgroup(head_pc, &flags);
}
#endif
_
Subject: Subject: memcg: make mem_cgroup_split_huge_fixup() more efficient
Patches currently in -mm which might be from kamezawa.hiroyu@xxxxxxxxxxxxxx are
origin.patch
linux-next.patch
vmscan-promote-shared-file-mapped-pages.patch
vmscan-activate-executable-pages-after-first-usage.patch
mm-avoid-livelock-on-__gfp_fs-allocations.patch
mm-avoid-livelock-on-__gfp_fs-allocations-fix.patch
cgroup-fix-task-counter-common-ancestor-logic.patch
mm-memcg-consolidate-hierarchy-iteration-primitives.patch
mm-vmscan-distinguish-global-reclaim-from-global-lru-scanning.patch
mm-vmscan-distinguish-between-memcg-triggering-reclaim-and-memcg-being-scanned.patch
mm-memcg-per-priority-per-zone-hierarchy-scan-generations.patch
mm-move-memcg-hierarchy-reclaim-to-generic-reclaim-code.patch
mm-memcg-remove-optimization-of-keeping-the-root_mem_cgroup-lru-lists-empty.patch
mm-vmscan-convert-global-reclaim-to-per-memcg-lru-lists.patch
mm-collect-lru-list-heads-into-struct-lruvec.patch
mm-make-per-memcg-lru-lists-exclusive.patch
mm-memcg-remove-unused-node-section-info-from-pc-flags.patch
mm-memcg-remove-unused-node-section-info-from-pc-flags-fix.patch
memcg-make-mem_cgroup_split_huge_fixup-more-efficient.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
