[3.11.y.z extended stable] Patch "mm: numa: call MMU notifiers on THP migration" has been added to staging queue

[Luis Henriques]

This is a note to let you know that I have just added a patch titled

    mm: numa: call MMU notifiers on THP migration

to the linux-3.11.y-queue branch of the 3.11.y.z extended stable tree 
which can be found at:

 http://kernel.ubuntu.com/git?p=ubuntu/linux.git;a=shortlog;h=refs/heads/linux-3.11.y-queue

If you, or anyone else, feels it should not be added to this tree, please 
reply to this email.

For more information about the 3.11.y.z tree, see
https://wiki.ubuntu.com/Kernel/Dev/ExtendedStable

Thanks.
-Luis

------

>From e47f1df5c505b515de5846fef4d04d095dc477c2 Mon Sep 17 00:00:00 2001
From: Mel Gorman <mgorman at suse.de>
Date: Tue, 7 Jan 2014 14:00:37 +0000
Subject: mm: numa: call MMU notifiers on THP migration

commit f714f4f20e59ea6eea264a86b9a51fd51b88fc54 upstream.

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

Signed-off-by: Mel Gorman <mgorman at suse.de>
Reviewed-by: Rik van Riel <riel at redhat.com>
Cc: Alex Thorlton <athorlton at sgi.com>
Signed-off-by: Andrew Morton <akpm at linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds at linux-foundation.org>
Signed-off-by: Luis Henriques <luis.henriques at canonical.com>
---
 mm/migrate.c | 22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

diff --git a/mm/migrate.c b/mm/migrate.c
index b3ffb81..65bbca5 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>

@@ -1652,12 +1653,13 @@ 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;

 	/*
@@ -1699,10 +1701,12 @@ 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))
@@ -1743,15 +1747,16 @@ 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) {
-		set_pmd_at(mm, haddr, pmd, orig_entry);
-		flush_tlb_range(vma, haddr, haddr + HPAGE_PMD_SIZE);
+		set_pmd_at(mm, mmun_start, pmd, orig_entry);
+		flush_tlb_range(vma, mmun_start, mmun_end);
 		update_mmu_cache_pmd(vma, address, &entry);
 		page_remove_rmap(new_page);
 		goto fail_putback;
@@ -1766,6 +1771,7 @@ 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);
@@ -1786,7 +1792,7 @@ 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);
--
1.8.3.2