From e9b61f19858a5d6c42ce2298cf138279375d0d9b Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Fri, 15 Jan 2016 16:54:10 -0800
Subject: thp: reintroduce split_huge_page()

This patch adds implementation of split_huge_page() for new
refcountings.

Unlike previous implementation, new split_huge_page() can fail if
somebody holds GUP pin on the page.  It also means that pin on page
would prevent it from bening split under you.  It makes situation in
many places much cleaner.

The basic scheme of split_huge_page():

  - Check that sum of mapcounts of all subpage is equal to page_count()
    plus one (caller pin). Foll off with -EBUSY. This way we can avoid
    useless PMD-splits.

  - Freeze the page counters by splitting all PMD and setup migration
    PTEs.

  - Re-check sum of mapcounts against page_count(). Page's counts are
    stable now. -EBUSY if page is pinned.

  - Split compound page.

  - Unfreeze the page by removing migration entries.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Tested-by: Sasha Levin <sasha.levin@oracle.com>
Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Jerome Marchand <jmarchan@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Steve Capper <steve.capper@linaro.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>

Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/rmap.c | 40 +++++-----------------------------------
 1 file changed, 5 insertions(+), 35 deletions(-)

(limited to 'mm/rmap.c')

diff --git a/mm/rmap.c b/mm/rmap.c
index 2e62571..fc707df 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -567,27 +567,6 @@ void page_unlock_anon_vma_read(struct anon_vma *anon_vma)
 	anon_vma_unlock_read(anon_vma);
 }
 
-/*
- * At what user virtual address is page expected in @vma?
- */
-static inline unsigned long
-__vma_address(struct page *page, struct vm_area_struct *vma)
-{
-	pgoff_t pgoff = page_to_pgoff(page);
-	return vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
-}
-
-inline unsigned long
-vma_address(struct page *page, struct vm_area_struct *vma)
-{
-	unsigned long address = __vma_address(page, vma);
-
-	/* page should be within @vma mapping range */
-	VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
-
-	return address;
-}
-
 #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
 static void percpu_flush_tlb_batch_pages(void *data)
 {
@@ -1155,20 +1134,12 @@ void do_page_add_anon_rmap(struct page *page,
 	bool compound = flags & RMAP_COMPOUND;
 	bool first;
 
-	if (PageTransCompound(page)) {
+	if (compound) {
+		atomic_t *mapcount;
 		VM_BUG_ON_PAGE(!PageLocked(page), page);
-		if (compound) {
-			atomic_t *mapcount;
-
-			VM_BUG_ON_PAGE(!PageTransHuge(page), page);
-			mapcount = compound_mapcount_ptr(page);
-			first = atomic_inc_and_test(mapcount);
-		} else {
-			/* Anon THP always mapped first with PMD */
-			first = 0;
-			VM_BUG_ON_PAGE(!page_mapcount(page), page);
-			atomic_inc(&page->_mapcount);
-		}
+		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
+		mapcount = compound_mapcount_ptr(page);
+		first = atomic_inc_and_test(mapcount);
 	} else {
 		first = atomic_inc_and_test(&page->_mapcount);
 	}
@@ -1182,7 +1153,6 @@ void do_page_add_anon_rmap(struct page *page,
 		 * disabled.
 		 */
 		if (compound) {
-			VM_BUG_ON_PAGE(!PageTransHuge(page), page);
 			__inc_zone_page_state(page,
 					      NR_ANON_TRANSPARENT_HUGEPAGES);
 		}
-- 
cgit v1.1