The patch titled
Subject: mm, page_alloc: move cpuset seqcount checking to slowpath
has been added to the -mm tree. Its filename is
mm-page_alloc-move-cpuset-seqcount-checking-to-slowpath.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-page_alloc-move-cpuset-seqcount-checking-to-slowpath.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-page_alloc-move-cpuset-seqcount-checking-to-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: Vlastimil Babka <vbabka@xxxxxxx>
Subject: mm, page_alloc: move cpuset seqcount checking to slowpath
This is a preparation for the following patch to make review simpler.
While the primary motivation is a bug fix, this also simplifies the fast
path, although the moved code is only enabled when cpusets are in use.
Link: http://lkml.kernel.org/r/20170120103843.24587-4-vbabka@xxxxxxx
Signed-off-by: Vlastimil Babka <vbabka@xxxxxxx>
Acked-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Cc: Ganapatrao Kulkarni <gpkulkarni@xxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/page_alloc.c | 47 +++++++++++++++++++++++++---------------------
1 file changed, 26 insertions(+), 21 deletions(-)
diff -puN mm/page_alloc.c~mm-page_alloc-move-cpuset-seqcount-checking-to-slowpath mm/page_alloc.c
--- a/mm/page_alloc.c~mm-page_alloc-move-cpuset-seqcount-checking-to-slowpath
+++ a/mm/page_alloc.c
@@ -3523,12 +3523,13 @@ __alloc_pages_slowpath(gfp_t gfp_mask, u
struct page *page = NULL;
unsigned int alloc_flags;
unsigned long did_some_progress;
- enum compact_priority compact_priority = DEF_COMPACT_PRIORITY;
+ enum compact_priority compact_priority;
enum compact_result compact_result;
- int compaction_retries = 0;
- int no_progress_loops = 0;
+ int compaction_retries;
+ int no_progress_loops;
unsigned long alloc_start = jiffies;
unsigned int stall_timeout = 10 * HZ;
+ unsigned int cpuset_mems_cookie;
/*
* In the slowpath, we sanity check order to avoid ever trying to
@@ -3549,6 +3550,12 @@ __alloc_pages_slowpath(gfp_t gfp_mask, u
(__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)))
gfp_mask &= ~__GFP_ATOMIC;
+retry_cpuset:
+ compaction_retries = 0;
+ no_progress_loops = 0;
+ compact_priority = DEF_COMPACT_PRIORITY;
+ cpuset_mems_cookie = read_mems_allowed_begin();
+
/*
* The fast path uses conservative alloc_flags to succeed only until
* kswapd needs to be woken up, and to avoid the cost of setting up
@@ -3720,6 +3727,15 @@ retry:
}
nopage:
+ /*
+ * When updating a task's mems_allowed, it is possible to race with
+ * parallel threads in such a way that an allocation can fail while
+ * the mask is being updated. If a page allocation is about to fail,
+ * check if the cpuset changed during allocation and if so, retry.
+ */
+ if (read_mems_allowed_retry(cpuset_mems_cookie))
+ goto retry_cpuset;
+
warn_alloc(gfp_mask,
"page allocation failure: order:%u", order);
got_pg:
@@ -3734,7 +3750,6 @@ __alloc_pages_nodemask(gfp_t gfp_mask, u
struct zonelist *zonelist, nodemask_t *nodemask)
{
struct page *page;
- unsigned int cpuset_mems_cookie;
unsigned int alloc_flags = ALLOC_WMARK_LOW;
gfp_t alloc_mask = gfp_mask; /* The gfp_t that was actually used for allocation */
struct alloc_context ac = {
@@ -3771,9 +3786,6 @@ __alloc_pages_nodemask(gfp_t gfp_mask, u
if (IS_ENABLED(CONFIG_CMA) && ac.migratetype == MIGRATE_MOVABLE)
alloc_flags |= ALLOC_CMA;
-retry_cpuset:
- cpuset_mems_cookie = read_mems_allowed_begin();
-
/* Dirty zone balancing only done in the fast path */
ac.spread_dirty_pages = (gfp_mask & __GFP_WRITE);
@@ -3786,6 +3798,11 @@ retry_cpuset:
ac.high_zoneidx, ac.nodemask);
if (!ac.preferred_zoneref->zone) {
page = NULL;
+ /*
+ * This might be due to race with cpuset_current_mems_allowed
+ * update, so make sure we retry with original nodemask in the
+ * slow path.
+ */
goto no_zone;
}
@@ -3794,6 +3811,7 @@ retry_cpuset:
if (likely(page))
goto out;
+no_zone:
/*
* Runtime PM, block IO and its error handling path can deadlock
* because I/O on the device might not complete.
@@ -3811,24 +3829,11 @@ retry_cpuset:
ac.nodemask = nodemask;
ac.preferred_zoneref = first_zones_zonelist(ac.zonelist,
ac.high_zoneidx, ac.nodemask);
- if (!ac.preferred_zoneref->zone)
- goto no_zone;
+ /* If we have NULL preferred zone, slowpath wll handle that */
}
page = __alloc_pages_slowpath(alloc_mask, order, &ac);
-no_zone:
- /*
- * When updating a task's mems_allowed, it is possible to race with
- * parallel threads in such a way that an allocation can fail while
- * the mask is being updated. If a page allocation is about to fail,
- * check if the cpuset changed during allocation and if so, retry.
- */
- if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) {
- alloc_mask = gfp_mask;
- goto retry_cpuset;
- }
-
out:
if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page &&
unlikely(memcg_kmem_charge(page, gfp_mask, order) != 0)) {
_
Patches currently in -mm which might be from vbabka@xxxxxxx are
mm-mempolicyc-do-not-put-mempolicy-before-using-its-nodemask.patch
mm-page_alloc-fix-check-for-null-preferred_zone.patch
mm-page_alloc-fix-fast-path-race-with-cpuset-update-or-removal.patch
mm-page_alloc-move-cpuset-seqcount-checking-to-slowpath.patch
mm-page_alloc-fix-premature-oom-when-racing-with-cpuset-mems-update.patch
mm-page_alloc-dont-convert-pfn-to-idx-when-merging.patch
mm-page_alloc-avoid-page_to_pfn-when-merging-buddies.patch
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html