[PATCH 05/15] mm: numa: Call MMU notifiers on THP migration

[Mel Gorman]

MMU notifiers must be called on THP page migration or secondary MMUs will
get very confused.

Signed-off-by: Mel Gorman <mgorman@xxxxxxx>
---
 mm/migrate.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/mm/migrate.c b/mm/migrate.c
index c4743d6..3a87511 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -36,6 +36,7 @@
 #include <linux/hugetlb_cgroup.h>
 #include <linux/gfp.h>
 #include <linux/balloon_compaction.h>
+#include <linux/mmu_notifier.h>
 
 #include <asm/tlbflush.h>
 
@@ -1703,12 +1704,13 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 				unsigned long address,
 				struct page *page, int node)
 {
-	unsigned long haddr = address & HPAGE_PMD_MASK;
 	pg_data_t *pgdat = NODE_DATA(node);
 	int isolated = 0;
 	struct page *new_page = NULL;
 	struct mem_cgroup *memcg = NULL;
 	int page_lru = page_is_file_cache(page);
+	unsigned long mmun_start = address & HPAGE_PMD_MASK;
+	unsigned long mmun_end = mmun_start + HPAGE_PMD_SIZE;
 	pmd_t orig_entry;
 
 	/*
@@ -1750,10 +1752,12 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	WARN_ON(PageLRU(new_page));
 
 	/* Recheck the target PMD */
+	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 	spin_lock(&mm->page_table_lock);
 	if (unlikely(!pmd_same(*pmd, entry) || page_count(page) != 2)) {
 fail_putback:
 		spin_unlock(&mm->page_table_lock);
+		mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 
 		/* Reverse changes made by migrate_page_copy() */
 		if (TestClearPageActive(new_page))
@@ -1794,10 +1798,11 @@ fail_putback:
 	 * The SetPageUptodate on the new page and page_add_new_anon_rmap
 	 * guarantee the copy is visible before the pagetable update.
 	 */
-	flush_cache_range(vma, haddr, haddr + HPAGE_PMD_SIZE);
-	page_add_new_anon_rmap(new_page, vma, haddr);
-	pmdp_clear_flush(vma, haddr, pmd);
-	set_pmd_at(mm, haddr, pmd, entry);
+	flush_cache_range(vma, mmun_start, mmun_end);
+	page_add_new_anon_rmap(new_page, vma, mmun_start);
+	pmdp_clear_flush(vma, mmun_start, pmd);
+	set_pmd_at(mm, mmun_start, pmd, entry);
+	flush_tlb_range(vma, mmun_start, mmun_end);
 	update_mmu_cache_pmd(vma, address, &entry);
 
 	if (page_count(page) != 2) {
@@ -1817,6 +1822,7 @@ fail_putback:
 	 */
 	mem_cgroup_end_migration(memcg, page, new_page, true);
 	spin_unlock(&mm->page_table_lock);
+	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 
 	unlock_page(new_page);
 	unlock_page(page);
@@ -1837,7 +1843,7 @@ out_dropref:
 	spin_lock(&mm->page_table_lock);
 	if (pmd_same(*pmd, entry)) {
 		entry = pmd_mknonnuma(entry);
-		set_pmd_at(mm, haddr, pmd, entry);
+		set_pmd_at(mm, mmun_start, pmd, entry);
 		update_mmu_cache_pmd(vma, address, &entry);
 	}
 	spin_unlock(&mm->page_table_lock);
-- 
1.8.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/