thp: split_huge_page anon_vma ordering dependency

This documents how split_huge_page is safe vs new vma inserctions into the
anon_vma that may have already released the anon_vma->lock but not
established pmds yet when split_huge_page starts.

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 20 insertions, 0 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 0c1e8f939f7c..763507932898 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -841,6 +841,19 @@ static void __split_huge_page(struct page *page,
 			continue;
 		mapcount += __split_huge_page_splitting(page, vma, addr);
 	}
+	/*
+	 * It is critical that new vmas are added to the tail of the
+	 * anon_vma list. This guarantes that if copy_huge_pmd() runs
+	 * and establishes a child pmd before
+	 * __split_huge_page_splitting() freezes the parent pmd (so if
+	 * we fail to prevent copy_huge_pmd() from running until the
+	 * whole __split_huge_page() is complete), we will still see
+	 * the newly established pmd of the child later during the
+	 * walk, to be able to set it as pmd_trans_splitting too.
+	 */
+	if (mapcount != page_mapcount(page))
+		printk(KERN_ERR "mapcount %d page_mapcount %d\n",
+		       mapcount, page_mapcount(page));
 	BUG_ON(mapcount != page_mapcount(page));
 
 	__split_huge_page_refcount(page);
@@ -854,6 +867,9 @@ static void __split_huge_page(struct page *page,
 			continue;
 		mapcount2 += __split_huge_page_map(page, vma, addr);
 	}
+	if (mapcount != mapcount2)
+		printk(KERN_ERR "mapcount %d mapcount2 %d page_mapcount %d\n",
+		       mapcount, mapcount2, page_mapcount(page));
 	BUG_ON(mapcount != mapcount2);
 }
 
diff --git a/mm/rmap.c b/mm/rmap.c
index e41375a6b029..92e14dcfe737 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -177,6 +177,10 @@ static void anon_vma_chain_link(struct vm_area_struct *vma,
 	list_add(&avc->same_vma, &vma->anon_vma_chain);
 
 	anon_vma_lock(anon_vma);
+	/*
+	 * It's critical to add new vmas to the tail of the anon_vma,
+	 * see comment in huge_memory.c:__split_huge_page().
+	 */
 	list_add_tail(&avc->same_anon_vma, &anon_vma->head);
 	anon_vma_unlock(anon_vma);
 }