The patch titled
Subject: mm: memcontrol: rewrite uncharge API fix - page cache migration
has been removed from the -mm tree. Its filename was
mm-memcontrol-rewrite-uncharge-api-fix-page-cache-migration.patch
This patch was dropped because it was folded into mm-memcontrol-rewrite-uncharge-api.patch
------------------------------------------------------
From: Johannes Weiner <hannes@xxxxxxxxxxx>
Subject: mm: memcontrol: rewrite uncharge API fix - page cache migration
It was known that the target page in migration could be on the LRU -
clarify this in mem_cgroup_migrate() and correct the VM_BUG_ON_PAGE().
However, during page cache replacement, the source page can also be on
the LRU, and two things need to be considered:
1. charge moving can race and change pc->mem_cgroup from under us: grab
the page lock in mem_cgroup_move_account() to prevent that.
2. the lruvec of the page changes as we uncharge it, and putback can race
with us: grab the lru lock and isolate the page iff on LRU to prevent
races and to ensure the page is on the right lruvec afterward.
Signed-off-by: Johannes Weiner <hannes@xxxxxxxxxxx>
Reported-by: Michal Hocko <mhocko@xxxxxxx>
Cc: Miklos Szeredi <miklos@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/memcontrol.c | 83 +++++++++++++++++++++++++++++++---------------
1 file changed, 57 insertions(+), 26 deletions(-)
diff -puN mm/memcontrol.c~mm-memcontrol-rewrite-uncharge-api-fix-page-cache-migration mm/memcontrol.c
--- a/mm/memcontrol.c~mm-memcontrol-rewrite-uncharge-api-fix-page-cache-migration
+++ a/mm/memcontrol.c
@@ -2696,13 +2696,42 @@ struct mem_cgroup *try_get_mem_cgroup_fr
return memcg;
}
+static void lock_page_lru(struct page *page, int *isolated)
+{
+ struct zone *zone = page_zone(page);
+
+ spin_lock_irq(&zone->lru_lock);
+ if (PageLRU(page)) {
+ struct lruvec *lruvec;
+
+ lruvec = mem_cgroup_page_lruvec(page, zone);
+ ClearPageLRU(page);
+ del_page_from_lru_list(page, lruvec, page_lru(page));
+ *isolated = 1;
+ } else
+ *isolated = 0;
+}
+
+static void unlock_page_lru(struct page *page, int isolated)
+{
+ struct zone *zone = page_zone(page);
+
+ if (isolated) {
+ struct lruvec *lruvec;
+
+ lruvec = mem_cgroup_page_lruvec(page, zone);
+ VM_BUG_ON_PAGE(PageLRU(page), page);
+ SetPageLRU(page);
+ add_page_to_lru_list(page, lruvec, page_lru(page));
+ }
+ spin_unlock_irq(&zone->lru_lock);
+}
+
static void commit_charge(struct page *page, struct mem_cgroup *memcg,
unsigned int nr_pages, bool lrucare)
{
struct page_cgroup *pc = lookup_page_cgroup(page);
- struct zone *uninitialized_var(zone);
- bool was_on_lru = false;
- struct lruvec *lruvec;
+ int isolated;
VM_BUG_ON_PAGE(PageCgroupUsed(pc), page);
/*
@@ -2714,16 +2743,8 @@ static void commit_charge(struct page *p
* In some cases, SwapCache and FUSE(splice_buf->radixtree), the page
* may already be on some other mem_cgroup's LRU. Take care of it.
*/
- if (lrucare) {
- zone = page_zone(page);
- spin_lock_irq(&zone->lru_lock);
- if (PageLRU(page)) {
- lruvec = mem_cgroup_zone_lruvec(zone, pc->mem_cgroup);
- ClearPageLRU(page);
- del_page_from_lru_list(page, lruvec, page_lru(page));
- was_on_lru = true;
- }
- }
+ if (lrucare)
+ lock_page_lru(page, &isolated);
/*
* Nobody should be changing or seriously looking at
@@ -2742,15 +2763,8 @@ static void commit_charge(struct page *p
pc->mem_cgroup = memcg;
pc->flags = PCG_USED | PCG_MEM | (do_swap_account ? PCG_MEMSW : 0);
- if (lrucare) {
- if (was_on_lru) {
- lruvec = mem_cgroup_zone_lruvec(zone, pc->mem_cgroup);
- VM_BUG_ON_PAGE(PageLRU(page), page);
- SetPageLRU(page);
- add_page_to_lru_list(page, lruvec, page_lru(page));
- }
- spin_unlock_irq(&zone->lru_lock);
- }
+ if (lrucare)
+ unlock_page_lru(page, isolated);
local_irq_disable();
mem_cgroup_charge_statistics(memcg, page, nr_pages);
@@ -3450,9 +3464,17 @@ static int mem_cgroup_move_account(struc
if (nr_pages > 1 && !PageTransHuge(page))
goto out;
+ /*
+ * Prevent mem_cgroup_migrate() from looking at pc->mem_cgroup
+ * of its source page while we change it: page migration takes
+ * both pages off the LRU, but page cache replacement doesn't.
+ */
+ if (!trylock_page(page))
+ goto out;
+
ret = -EINVAL;
if (!PageCgroupUsed(pc) || pc->mem_cgroup != from)
- goto out;
+ goto out_unlock;
move_lock_mem_cgroup(from, &flags);
@@ -3487,6 +3509,8 @@ static int mem_cgroup_move_account(struc
mem_cgroup_charge_statistics(from, page, -nr_pages);
memcg_check_events(from, page);
local_irq_enable();
+out_unlock:
+ unlock_page(page);
out:
return ret;
}
@@ -6581,7 +6605,7 @@ out:
* mem_cgroup_migrate - migrate a charge to another page
* @oldpage: currently charged page
* @newpage: page to transfer the charge to
- * @lrucare: page might be on LRU already
+ * @lrucare: both pages might be on the LRU already
*
* Migrate the charge from @oldpage to @newpage.
*
@@ -6592,11 +6616,12 @@ void mem_cgroup_migrate(struct page *old
{
unsigned int nr_pages = 1;
struct page_cgroup *pc;
+ int isolated;
VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage);
VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);
- VM_BUG_ON_PAGE(PageLRU(oldpage), oldpage);
- VM_BUG_ON_PAGE(PageLRU(newpage), newpage);
+ VM_BUG_ON_PAGE(!lrucare && PageLRU(oldpage), oldpage);
+ VM_BUG_ON_PAGE(!lrucare && PageLRU(newpage), newpage);
VM_BUG_ON_PAGE(PageAnon(oldpage) != PageAnon(newpage), newpage);
if (mem_cgroup_disabled())
@@ -6615,8 +6640,14 @@ void mem_cgroup_migrate(struct page *old
VM_BUG_ON_PAGE(!PageTransHuge(newpage), newpage);
}
+ if (lrucare)
+ lock_page_lru(oldpage, &isolated);
+
pc->flags = 0;
+ if (lrucare)
+ unlock_page_lru(oldpage, isolated);
+
local_irq_disable();
mem_cgroup_charge_statistics(pc->mem_cgroup, oldpage, -nr_pages);
memcg_check_events(pc->mem_cgroup, oldpage);
_
Patches currently in -mm which might be from hannes@xxxxxxxxxxx are
origin.patch
vmalloc-use-rcu-list-iterator-to-reduce-vmap_area_lock-contention.patch
mm-page-flags-clean-up-the-page-flag-test-set-clear-macros.patch
mm-memcontrol-fold-mem_cgroup_do_charge.patch
mm-memcontrol-rearrange-charging-fast-path.patch
mm-memcontrol-reclaim-at-least-once-for-__gfp_noretry.patch
mm-huge_memory-use-gfp_transhuge-when-charging-huge-pages.patch
mm-memcontrol-retry-reclaim-for-oom-disabled-and-__gfp_nofail-charges.patch
mm-memcontrol-remove-explicit-oom-parameter-in-charge-path.patch
mm-memcontrol-simplify-move-precharge-function.patch
mm-memcontrol-catch-root-bypass-in-move-precharge.patch
mm-memcontrol-use-root_mem_cgroup-res_counter.patch
mm-memcontrol-remove-ordering-between-pc-mem_cgroup-and-pagecgroupused.patch
mm-memcontrol-do-not-acquire-page_cgroup-lock-for-kmem-pages.patch
mm-memcontrol-rewrite-charge-api.patch
mm-memcontrol-rewrite-uncharge-api.patch
mm-memcontrol-rewrite-uncharge-api-fix-page-cache-migration-2.patch
mm-memcontrol-rewrite-uncharge-api-fix-clear-page-mapping-in-migration.patch
mm-memcontrol-use-page-lists-for-uncharge-batching.patch
mm-memcontrol-use-page-lists-for-uncharge-batching-fix-hugetlb-page-lru.patch
page-cgroup-trivial-cleanup.patch
page-cgroup-get-rid-of-nr_pcg_flags.patch
memcg-remove-lookup_cgroup_page-prototype.patch
mm-vmscan-remove-remains-of-kswapd-managed-zone-all_unreclaimable.patch
mm-vmscan-rework-compaction-ready-signaling-in-direct-reclaim.patch
mm-vmscan-rework-compaction-ready-signaling-in-direct-reclaim-fix.patch
mm-vmscan-remove-all_unreclaimable.patch
mm-vmscan-remove-all_unreclaimable-fix.patch
mm-vmscan-move-swappiness-out-of-scan_control.patch
mm-vmscan-clean-up-struct-scan_control-v2.patch
mm-export-nr_shmem-via-sysinfo2-si_meminfo-interfaces.patch
mm-replace-init_page_accessed-by-__setpagereferenced.patch
mm-update-the-description-for-vm_total_pages.patch
mm-vmscan-report-the-number-of-file-anon-pages-respectively.patch
mm-pagemap-avoid-unnecessary-overhead-when-tracepoints-are-deactivated.patch
mm-rearrange-zone-fields-into-read-only-page-alloc-statistics-and-page-reclaim-lines.patch
mm-move-zone-pages_scanned-into-a-vmstat-counter.patch
mm-vmscan-only-update-per-cpu-thresholds-for-online-cpu.patch
mm-page_alloc-abort-fair-zone-allocation-policy-when-remotes-nodes-are-encountered.patch
mm-page_alloc-reduce-cost-of-the-fair-zone-allocation-policy.patch
mm-writeback-prevent-race-when-calculating-dirty-limits.patch
slub-remove-kmemcg-id-from-create_unique_id.patch
mm-oom-ensure-memoryless-node-zonelist-always-includes-zones.patch
mm-oom-ensure-memoryless-node-zonelist-always-includes-zones-fix.patch
mm-oom-rename-zonelist-locking-functions.patch
mm-thp-restructure-thp-avoidance-of-light-synchronous-migration.patch
mm-vmscan-fix-an-outdated-comment-still-mentioning-get_scan_ratio.patch
memcg-vmscan-fix-forced-scan-of-anonymous-pages.patch
memcg-vmscan-fix-forced-scan-of-anonymous-pages-fix-cleanups.patch
mm-memcontrol-avoid-charge-statistics-churn-during-page-migration.patch
mm-memcontrol-clean-up-reclaim-size-variable-use-in-try_charge.patch
nilfs2-integrate-sysfs-support-into-driver-fix.patch
linux-next.patch
debugging-keep-track-of-page-owners.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
