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@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Alex Thorlton <athorlton@sgi.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index f5096b5..b7717d7 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -90,10 +90,19 @@
#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 --git a/mm/huge_memory.c b/mm/huge_memory.c
index 70e7429..7de1bf8 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -882,6 +882,10 @@
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 @@
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 @@
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 --git a/mm/migrate.c b/mm/migrate.c
index a987525..cfb4190 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1655,6 +1655,18 @@
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