mm: change the interface for __tlb_remove_page()

This updates the generic and arch specific implementation to return true
if we need to do a tlb flush.  That means if a __tlb_remove_page
indicate a flush is needed, the page we try to remove need to be tracked
and added again after the flush.  We need to track it because we have
already update the pte to none and we can't just loop back.

This change is done to enable us to do a tlb_flush when we try to flush
a range that consists of different page sizes.  For architectures like
ppc64, we can do a range based tlb flush and we need to track page size
for that.  When we try to remove a huge page, we will force a tlb flush
and starts a new mmu gather.

[aneesh.kumar@linux.vnet.ibm.com: mm-change-the-interface-for-__tlb_remove_page-v3]
  Link: http://lkml.kernel.org/r/1465049193-22197-2-git-send-email-aneesh.kumar@linux.vnet.ibm.com
Link: http://lkml.kernel.org/r/1464860389-29019-2-git-send-email-aneesh.kumar@linux.vnet.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Hugh Dickins <hughd@google.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Minchan Kim <minchan.kim@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 13 insertions, 6 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 9e046819e619..12f31501c323 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -292,23 +292,24 @@ void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long e
  *	handling the additional races in SMP caused by other CPUs caching valid
  *	mappings in their TLBs. Returns the number of free page slots left.
  *	When out of page slots we must call tlb_flush_mmu().
+ *returns true if the caller should flush.
  */
-int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
 	struct mmu_gather_batch *batch;
 
 	VM_BUG_ON(!tlb->end);
 
 	batch = tlb->active;
-	batch->pages[batch->nr++] = page;
 	if (batch->nr == batch->max) {
 		if (!tlb_next_batch(tlb))
-			return 0;
+			return true;
 		batch = tlb->active;
 	}
 	VM_BUG_ON_PAGE(batch->nr > batch->max, page);
 
-	return batch->max - batch->nr;
+	batch->pages[batch->nr++] = page;
+	return false;
 }
 
 #endif /* HAVE_GENERIC_MMU_GATHER */
@@ -1109,6 +1110,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 	pte_t *start_pte;
 	pte_t *pte;
 	swp_entry_t entry;
+	struct page *pending_page = NULL;
 
 again:
 	init_rss_vec(rss);
@@ -1160,8 +1162,9 @@ again:
 			page_remove_rmap(page, false);
 			if (unlikely(page_mapcount(page) < 0))
 				print_bad_pte(vma, addr, ptent, page);
-			if (unlikely(!__tlb_remove_page(tlb, page))) {
+			if (unlikely(__tlb_remove_page(tlb, page))) {
 				force_flush = 1;
+				pending_page = page;
 				addr += PAGE_SIZE;
 				break;
 			}
@@ -1202,7 +1205,11 @@ again:
 	if (force_flush) {
 		force_flush = 0;
 		tlb_flush_mmu_free(tlb);
-
+		if (pending_page) {
+			/* remove the page with new size */
+			__tlb_remove_pte_page(tlb, pending_page);
+			pending_page = NULL;
+		}
 		if (addr != end)
 			goto again;
 	}