Subject: + mm-numa-avoid-unnecessary-disruption-of-numa-hinting-during-migration.patch added to -mm tree
To: mgorman@xxxxxxx,athorlton@xxxxxxx,riel@xxxxxxxxxx,stable@xxxxxxxxxxxxxxx
From: akpm@xxxxxxxxxxxxxxxxxxxx
Date: Tue, 10 Dec 2013 14:20:26 -0800
The patch titled
Subject: mm: numa: avoid unnecessary disruption of NUMA hinting during migration
has been added to the -mm tree. Its filename is
mm-numa-avoid-unnecessary-disruption-of-numa-hinting-during-migration.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-numa-avoid-unnecessary-disruption-of-numa-hinting-during-migration.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-numa-avoid-unnecessary-disruption-of-numa-hinting-during-migration.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: Mel Gorman <mgorman@xxxxxxx>
Subject: mm: numa: avoid unnecessary disruption of NUMA hinting during migration
do_huge_pmd_numa_page() handles the case where there is parallel THP
migration. However, by the time it is checked the NUMA hinting
information has already been disrupted. This patch adds an earlier check
with some helpers.
Signed-off-by: Mel Gorman <mgorman@xxxxxxx>
Reviewed-by: Rik van Riel <riel@xxxxxxxxxx>
Cc: Alex Thorlton <athorlton@xxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/migrate.h | 9 +++++++++
mm/huge_memory.c | 22 ++++++++++++++++------
mm/migrate.c | 12 ++++++++++++
3 files changed, 37 insertions(+), 6 deletions(-)
diff -puN include/linux/migrate.h~mm-numa-avoid-unnecessary-disruption-of-numa-hinting-during-migration include/linux/migrate.h
--- a/include/linux/migrate.h~mm-numa-avoid-unnecessary-disruption-of-numa-hinting-during-migration
+++ a/include/linux/migrate.h
@@ -90,10 +90,19 @@ static inline int migrate_huge_page_move
#endif /* CONFIG_MIGRATION */
#ifdef CONFIG_NUMA_BALANCING
+extern bool pmd_trans_migrating(pmd_t pmd);
+extern void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd);
extern int migrate_misplaced_page(struct page *page,
struct vm_area_struct *vma, int node);
extern bool migrate_ratelimited(int node);
#else
+static inline bool pmd_trans_migrating(pmd_t pmd)
+{
+ return false;
+}
+static inline void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd)
+{
+}
static inline int migrate_misplaced_page(struct page *page,
struct vm_area_struct *vma, int node)
{
diff -puN mm/huge_memory.c~mm-numa-avoid-unnecessary-disruption-of-numa-hinting-during-migration mm/huge_memory.c
--- a/mm/huge_memory.c~mm-numa-avoid-unnecessary-disruption-of-numa-hinting-during-migration
+++ a/mm/huge_memory.c
@@ -882,6 +882,10 @@ int copy_huge_pmd(struct mm_struct *dst_
ret = 0;
goto out_unlock;
}
+
+ /* mmap_sem prevents this happening but warn if that changes */
+ WARN_ON(pmd_trans_migrating(pmd));
+
if (unlikely(pmd_trans_splitting(pmd))) {
/* split huge page running from under us */
spin_unlock(src_ptl);
@@ -1299,6 +1303,17 @@ int do_huge_pmd_numa_page(struct mm_stru
if (unlikely(!pmd_same(pmd, *pmdp)))
goto out_unlock;
+ /*
+ * If there are potential migrations, wait for completion and retry
+ * without disrupting NUMA hinting information. Do not relock and
+ * check_same as the page may no longer be mapped.
+ */
+ if (unlikely(pmd_trans_migrating(*pmdp))) {
+ spin_unlock(ptl);
+ wait_migrate_huge_page(vma->anon_vma, pmdp);
+ goto out;
+ }
+
page = pmd_page(pmd);
BUG_ON(is_huge_zero_page(page));
page_nid = page_to_nid(page);
@@ -1329,12 +1344,7 @@ int do_huge_pmd_numa_page(struct mm_stru
goto clear_pmdnuma;
}
- /*
- * If there are potential migrations, wait for completion and retry. We
- * do not relock and check_same as the page may no longer be mapped.
- * Furtermore, even if the page is currently misplaced, there is no
- * guarantee it is still misplaced after the migration completes.
- */
+ /* Migration could have started since the pmd_trans_migrating check */
if (!page_locked) {
spin_unlock(ptl);
wait_on_page_locked(page);
diff -puN mm/migrate.c~mm-numa-avoid-unnecessary-disruption-of-numa-hinting-during-migration mm/migrate.c
--- a/mm/migrate.c~mm-numa-avoid-unnecessary-disruption-of-numa-hinting-during-migration
+++ a/mm/migrate.c
@@ -1660,6 +1660,18 @@ int numamigrate_isolate_page(pg_data_t *
return 1;
}
+bool pmd_trans_migrating(pmd_t pmd)
+{
+ struct page *page = pmd_page(pmd);
+ return PageLocked(page);
+}
+
+void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd)
+{
+ struct page *page = pmd_page(*pmd);
+ wait_on_page_locked(page);
+}
+
/*
* Attempt to migrate a misplaced page to the specified destination
* node. Caller is expected to have an elevated reference count on
_
Patches currently in -mm which might be from mgorman@xxxxxxx are
mm-hugetlbfs-add-some-vm_bug_ons-to-catch-non-hugetlbfs-pages.patch
mm-hugetlb-use-get_page_foll-in-follow_hugetlb_page.patch
mm-hugetlbfs-move-the-put-get_page-slab-and-hugetlbfs-optimization-in-a-faster-path.patch
mm-thp-optimize-compound_trans_huge.patch
mm-tail-page-refcounting-optimization-for-slab-and-hugetlbfs.patch
mm-hugetlbfs-use-__compound_tail_refcounted-in-__get_page_tail-too.patch
mm-hugetlbc-simplify-pageheadhuge-and-pagehuge.patch
mm-swapc-reorganize-put_compound_page.patch
mm-hugetlbc-defer-pageheadhuge-symbol-export.patch
mm-get-rid-of-unnecessary-pageblock-scanning-in-setup_zone_migrate_reserve.patch
mm-get-rid-of-unnecessary-pageblock-scanning-in-setup_zone_migrate_reserve-fix.patch
mm-call-mmu-notifiers-when-copying-a-hugetlb-page-range.patch
mm-show_mem-remove-show_mem_filter_page_count.patch
x86-get-pg_data_ts-memory-from-other-node.patch
memblock-numa-introduce-flags-field-into-memblock.patch
memblock-mem_hotplug-introduce-memblock_hotplug-flag-to-mark-hotpluggable-regions.patch
memblock-make-memblock_set_node-support-different-memblock_type.patch
acpi-numa-mem_hotplug-mark-hotpluggable-memory-in-memblock.patch
acpi-numa-mem_hotplug-mark-all-nodes-the-kernel-resides-un-hotpluggable.patch
memblock-mem_hotplug-make-memblock-skip-hotpluggable-regions-if-needed.patch
x86-numa-acpi-memory-hotplug-make-movable_node-have-higher-priority.patch
mm-rmap-recompute-pgoff-for-huge-page.patch
mm-rmap-factor-nonlinear-handling-out-of-try_to_unmap_file.patch
mm-rmap-factor-lock-function-out-of-rmap_walk_anon.patch
mm-rmap-make-rmap_walk-to-get-the-rmap_walk_control-argument.patch
mm-rmap-extend-rmap_walk_xxx-to-cope-with-different-cases.patch
mm-rmap-use-rmap_walk-in-try_to_unmap.patch
mm-rmap-use-rmap_walk-in-try_to_munlock.patch
mm-rmap-use-rmap_walk-in-page_referenced.patch
mm-rmap-use-rmap_walk-in-page_mkclean.patch
mm-page_alloc-allow-__gfp_nofail-to-allocate-below-watermarks-after-reclaim.patch
mm-numa-serialise-parallel-get_user_page-against-thp-migration.patch
mm-numa-call-mmu-notifiers-on-thp-migration.patch
mm-clear-pmd_numa-before-invalidating.patch
mm-numa-do-not-clear-pmd-during-pte-update-scan.patch
mm-numa-do-not-clear-pte-for-pte_numa-update.patch
mm-numa-ensure-anon_vma-is-locked-to-prevent-parallel-thp-splits.patch
mm-numa-avoid-unnecessary-work-on-the-failure-path.patch
sched-numa-skip-inaccessible-vmas.patch
mm-numa-clear-numa-hinting-information-on-mprotect.patch
mm-numa-avoid-unnecessary-disruption-of-numa-hinting-during-migration.patch
mm-fix-tlb-flush-race-between-migration-and-change_protection_range.patch
mm-numa-defer-tlb-flush-for-thp-migration-as-long-as-possible.patch
mm-numa-make-numa-migrate-related-functions-static.patch
mm-numa-limit-scope-of-lock-for-numa-migrate-rate-limiting.patch
mm-numa-trace-tasks-that-fail-migration-due-to-rate-limiting.patch
mm-numa-do-not-automatically-migrate-ksm-pages.patch
sched-add-tracepoints-related-to-numa-task-migration.patch
linux-next.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