The patch titled
Subject: mm: page_alloc: embed OOM killing naturally into allocation slowpath
has been added to the -mm tree. Its filename is
mm-page_alloc-embed-oom-killing-naturally-into-allocation-slowpath.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-page_alloc-embed-oom-killing-naturally-into-allocation-slowpath.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-page_alloc-embed-oom-killing-naturally-into-allocation-slowpath.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 ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Johannes Weiner <hannes@xxxxxxxxxxx>
Subject: mm: page_alloc: embed OOM killing naturally into allocation slowpath
The OOM killing invocation does a lot of duplicative checks against the
task's allocation context. Rework it to take advantage of the existing
checks in the allocator slowpath.
Signed-off-by: Johannes Weiner <hannes@xxxxxxxxxxx>
Acked-by: Michal Hocko <mhocko@xxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/oom.h | 5 --
mm/page_alloc.c | 80 ++++++++++++++++++------------------------
2 files changed, 35 insertions(+), 50 deletions(-)
diff -puN include/linux/oom.h~mm-page_alloc-embed-oom-killing-naturally-into-allocation-slowpath include/linux/oom.h
--- a/include/linux/oom.h~mm-page_alloc-embed-oom-killing-naturally-into-allocation-slowpath
+++ a/include/linux/oom.h
@@ -85,11 +85,6 @@ static inline void oom_killer_enable(voi
oom_killer_disabled = false;
}
-static inline bool oom_gfp_allowed(gfp_t gfp_mask)
-{
- return (gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY);
-}
-
extern struct task_struct *find_lock_task_mm(struct task_struct *p);
/* sysctls */
diff -puN mm/page_alloc.c~mm-page_alloc-embed-oom-killing-naturally-into-allocation-slowpath mm/page_alloc.c
--- a/mm/page_alloc.c~mm-page_alloc-embed-oom-killing-naturally-into-allocation-slowpath
+++ a/mm/page_alloc.c
@@ -2331,12 +2331,21 @@ static inline struct page *
__alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
struct zonelist *zonelist, enum zone_type high_zoneidx,
nodemask_t *nodemask, struct zone *preferred_zone,
- int classzone_idx, int migratetype)
+ int classzone_idx, int migratetype, unsigned long *did_some_progress)
{
struct page *page;
- /* Acquire the per-zone oom lock for each zone */
+ *did_some_progress = 0;
+
+ if (oom_killer_disabled)
+ return NULL;
+
+ /*
+ * Acquire the per-zone oom lock for each zone. If that
+ * fails, somebody else is making progress for us.
+ */
if (!oom_zonelist_trylock(zonelist, gfp_mask)) {
+ *did_some_progress = 1;
schedule_timeout_uninterruptible(1);
return NULL;
}
@@ -2362,12 +2371,18 @@ __alloc_pages_may_oom(gfp_t gfp_mask, un
goto out;
if (!(gfp_mask & __GFP_NOFAIL)) {
+ /* Coredumps can quickly deplete all memory reserves */
+ if (current->flags & PF_DUMPCORE)
+ goto out;
/* The OOM killer will not help higher order allocs */
if (order > PAGE_ALLOC_COSTLY_ORDER)
goto out;
/* The OOM killer does not needlessly kill tasks for lowmem */
if (high_zoneidx < ZONE_NORMAL)
goto out;
+ /* The OOM killer does not compensate for light reclaim */
+ if (!(gfp_mask & __GFP_FS))
+ goto out;
/*
* GFP_THISNODE contains __GFP_NORETRY and we never hit this.
* Sanity check for bare calls of __GFP_THISNODE, not real OOM.
@@ -2380,7 +2395,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, un
}
/* Exhausted what can be done so it's blamo time */
out_of_memory(zonelist, gfp_mask, order, nodemask, false);
-
+ *did_some_progress = 1;
out:
oom_zonelist_unlock(zonelist, gfp_mask);
return page;
@@ -2657,7 +2672,6 @@ __alloc_pages_slowpath(gfp_t gfp_mask, u
(gfp_mask & GFP_THISNODE) == GFP_THISNODE)
goto nopage;
-restart:
if (!(gfp_mask & __GFP_NO_KSWAPD))
wake_all_kswapds(order, zonelist, high_zoneidx,
preferred_zone, nodemask);
@@ -2787,51 +2801,27 @@ rebalance:
if (page)
goto got_pg;
- /*
- * If we failed to make any progress reclaiming, then we are
- * running out of options and have to consider going OOM
- */
- if (!did_some_progress) {
- if (oom_gfp_allowed(gfp_mask)) {
- if (oom_killer_disabled)
- goto nopage;
- /* Coredumps can quickly deplete all memory reserves */
- if ((current->flags & PF_DUMPCORE) &&
- !(gfp_mask & __GFP_NOFAIL))
- goto nopage;
- page = __alloc_pages_may_oom(gfp_mask, order,
- zonelist, high_zoneidx,
- nodemask, preferred_zone,
- classzone_idx, migratetype);
- if (page)
- goto got_pg;
-
- if (!(gfp_mask & __GFP_NOFAIL)) {
- /*
- * The oom killer is not called for high-order
- * allocations that may fail, so if no progress
- * is being made, there are no other options and
- * retrying is unlikely to help.
- */
- if (order > PAGE_ALLOC_COSTLY_ORDER)
- goto nopage;
- /*
- * The oom killer is not called for lowmem
- * allocations to prevent needlessly killing
- * innocent tasks.
- */
- if (high_zoneidx < ZONE_NORMAL)
- goto nopage;
- }
-
- goto restart;
- }
- }
-
/* Check if we should retry the allocation */
pages_reclaimed += did_some_progress;
if (should_alloc_retry(gfp_mask, order, did_some_progress,
pages_reclaimed)) {
+ /*
+ * If we fail to make progress by freeing individual
+ * pages, but the allocation wants us to keep going,
+ * start OOM killing tasks.
+ */
+ if (!did_some_progress) {
+ page = __alloc_pages_may_oom(gfp_mask, order, zonelist,
+ high_zoneidx, nodemask,
+ preferred_zone, classzone_idx,
+ migratetype,&did_some_progress);
+ if (page)
+ goto got_pg;
+ if (!did_some_progress) {
+ BUG_ON(gfp_mask & __GFP_NOFAIL);
+ goto nopage;
+ }
+ }
/* Wait for some write requests to complete then retry */
wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50);
goto rebalance;
_
Patches currently in -mm which might be from hannes@xxxxxxxxxxx are
slab-print-slabinfo-header-in-seq-show.patch
mm-memcontrol-lockless-page-counters.patch
mm-memcontrol-lockless-page-counters-fix.patch
mm-memcontrol-lockless-page-counters-fix-fix.patch
mm-memcontrol-lockless-page-counters-fix-2.patch
mm-hugetlb_cgroup-convert-to-lockless-page-counters.patch
kernel-res_counter-remove-the-unused-api.patch
kernel-res_counter-remove-the-unused-api-fix.patch
kernel-res_counter-remove-the-unused-api-fix-2.patch
mm-memcontrol-convert-reclaim-iterator-to-simple-css-refcounting.patch
mm-memcontrol-convert-reclaim-iterator-to-simple-css-refcounting-fix.patch
mm-memcontrol-take-a-css-reference-for-each-charged-page.patch
mm-memcontrol-remove-obsolete-kmemcg-pinning-tricks.patch
mm-memcontrol-continue-cache-reclaim-from-offlined-groups.patch
mm-memcontrol-remove-synchroneous-stock-draining-code.patch
mm-vmscan-count-only-dirty-pages-as-congested.patch
memcg-simplify-unreclaimable-groups-handling-in-soft-limit-reclaim.patch
mm-memcontrol-update-mem_cgroup_page_lruvec-documentation.patch
mm-memcontrol-clarify-migration-where-old-page-is-uncharged.patch
memcg-remove-activate_kmem_mutex.patch
mm-memcontrol-micro-optimize-mem_cgroup_split_huge_fixup.patch
mm-memcontrol-uncharge-pages-on-swapout.patch
mm-memcontrol-uncharge-pages-on-swapout-fix.patch
mm-memcontrol-remove-unnecessary-pcg_memsw-memoryswap-charge-flag.patch
mm-memcontrol-remove-unnecessary-pcg_mem-memory-charge-flag.patch
mm-memcontrol-remove-unnecessary-pcg_used-pc-mem_cgroup-valid-flag.patch
mm-memcontrol-remove-unnecessary-pcg_used-pc-mem_cgroup-valid-flag-fix.patch
mm-memcontrol-inline-memcg-move_lock-locking.patch
mm-memcontrol-dont-pass-a-null-memcg-to-mem_cgroup_end_move.patch
mm-memcontrol-fold-mem_cgroup_start_move-mem_cgroup_end_move.patch
mm-memcontrol-fold-mem_cgroup_start_move-mem_cgroup_end_move-fix.patch
memcg-remove-mem_cgroup_reclaimable-check-from-soft-reclaim.patch
memcg-use-generic-slab-iterators-for-showing-slabinfo.patch
mm-memcontrol-shorten-the-page-statistics-update-slowpath.patch
mm-memcontrol-remove-bogus-null-check-after-mem_cgroup_from_task.patch
mm-memcontrol-pull-the-null-check-from-__mem_cgroup_same_or_subtree.patch
mm-memcontrol-drop-bogus-rcu-locking-from-mem_cgroup_same_or_subtree.patch
mm-memcg-fix-potential-undefined-when-for-page-stat-accounting.patch
mm-memcontrol-remove-stale-page_cgroup_lock-comment.patch
mm-embed-the-memcg-pointer-directly-into-struct-page.patch
mm-embed-the-memcg-pointer-directly-into-struct-page-fix.patch
mm-page_cgroup-rename-file-to-mm-swap_cgroupc.patch
mm-move-page-mem_cgroup-bad-page-handling-into-generic-code.patch
mm-move-page-mem_cgroup-bad-page-handling-into-generic-code-fix.patch
mm-move-page-mem_cgroup-bad-page-handling-into-generic-code-fix-2.patch
memcg-__mem_cgroup_free-remove-stale-disarm_static_keys-comment.patch
memcg-dont-check-mm-in-__memcg_kmem_get_cachenewpage_charge.patch
memcg-do-not-abuse-memcg_kmem_skip_account.patch
mm-page_allocc-__alloc_pages_nodemask-dont-alter-arg-gfp_mask.patch
mm-mincore-add-hwpoison-page-handle.patch
memcg-zap-kmem_account_flags.patch
memcg-only-check-memcg_kmem_skip_account-in-__memcg_kmem_get_cache.patch
memcg-turn-memcg_kmem_skip_account-into-a-bit-field.patch
mm-move-swp_entry_t-definition-to-include-linux-mm_typesh.patch
mm-gfp-escalatedly-define-gfp_highuser-and-gfp_highuser_movable.patch
mm-page_ext-resurrect-struct-page-extending-code-for-debugging.patch
mm-page_ext-resurrect-struct-page-extending-code-for-debugging-fix.patch
mm-debug-pagealloc-prepare-boottime-configurable-on-off.patch
mm-debug-pagealloc-make-debug-pagealloc-boottime-configurable.patch
mm-debug-pagealloc-make-debug-pagealloc-boottime-configurable-fix.patch
mm-nommu-use-alloc_pages_exact-rather-than-its-own-implementation.patch
stacktrace-introduce-snprint_stack_trace-for-buffer-output.patch
mm-page_owner-keep-track-of-page-owners.patch
mm-page_owner-correct-owner-information-for-early-allocated-pages.patch
documentation-add-new-page_owner-document.patch
mm-vmscan-invoke-slab-shrinkers-from-shrink_zone.patch
mm-page_alloc-embed-oom-killing-naturally-into-allocation-slowpath.patch
mm-oom-remove-gfp-helper-function.patch
mm-memcontrol-fix-defined-but-not-used-compiler-warning.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
