Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:18 as permitted sender) client-ip=2620:137:e000::1:18;
From:   Baolin Wang <baolin.wang@linux.alibaba.com>
To:     akpm@linux-foundation.org, mike.kravetz@oracle.com
Cc:     almasrymina@google.com, songmuchun@bytedance.com,
        baolin.wang@linux.alibaba.com, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org
Subject: [PATCH v2 3/3] mm: rmap: Use flush_cache_range() to flush cache for hugetlb pages
Date:   Wed, 27 Apr 2022 18:52:07 +0800
Message-Id: <dc903b378d1e2d26bbbe85409ab9d009631f175c.1651056365.git.baolin.wang@linux.alibaba.com>
In-Reply-To: <cover.1651056365.git.baolin.wang@linux.alibaba.com>
References: <cover.1651056365.git.baolin.wang@linux.alibaba.com>
In-Reply-To: <cover.1651056365.git.baolin.wang@linux.alibaba.com>
References: <cover.1651056365.git.baolin.wang@linux.alibaba.com>
Precedence: bulk

Now we will use flush_cache_page() to flush cache for anonymous hugetlb
pages when unmapping or migrating a hugetlb page mapping, but the
flush_cache_page() only handles a PAGE_SIZE range on some architectures
(like arm32, arc and so on), which will cause potential cache issues.
Thus change to use flush_cache_range() to cover the whole size of a
hugetlb page.

Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
---
 mm/rmap.c | 90 ++++++++++++++++++++++++++++++++++-----------------------------
 1 file changed, 48 insertions(+), 42 deletions(-)

diff --git a/mm/rmap.c b/mm/rmap.c
index 4f0d115..6fdd198 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1528,13 +1528,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 		anon_exclusive = folio_test_anon(folio) &&
 				 PageAnonExclusive(subpage);
 
-		if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) {
-			/*
-			 * To call huge_pmd_unshare, i_mmap_rwsem must be
-			 * held in write mode.  Caller needs to explicitly
-			 * do this outside rmap routines.
-			 */
-			VM_BUG_ON(!(flags & TTU_RMAP_LOCKED));
+		if (folio_test_hugetlb(folio)) {
 			/*
 			 * huge_pmd_unshare may unmap an entire PMD page.
 			 * There is no way of knowing exactly which PMDs may
@@ -1544,22 +1538,31 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 			 */
 			flush_cache_range(vma, range.start, range.end);
 
-			if (huge_pmd_unshare(mm, vma, &address, pvmw.pte)) {
-				flush_tlb_range(vma, range.start, range.end);
-				mmu_notifier_invalidate_range(mm, range.start,
-							      range.end);
-
+			if (!folio_test_anon(folio)) {
 				/*
-				 * The ref count of the PMD page was dropped
-				 * which is part of the way map counting
-				 * is done for shared PMDs.  Return 'true'
-				 * here.  When there is no other sharing,
-				 * huge_pmd_unshare returns false and we will
-				 * unmap the actual page and drop map count
-				 * to zero.
+				 * To call huge_pmd_unshare, i_mmap_rwsem must be
+				 * held in write mode.  Caller needs to explicitly
+				 * do this outside rmap routines.
 				 */
-				page_vma_mapped_walk_done(&pvmw);
-				break;
+				VM_BUG_ON(!(flags & TTU_RMAP_LOCKED));
+
+				if (huge_pmd_unshare(mm, vma, &address, pvmw.pte)) {
+					flush_tlb_range(vma, range.start, range.end);
+					mmu_notifier_invalidate_range(mm, range.start,
+								      range.end);
+
+					/*
+					 * The ref count of the PMD page was dropped
+					 * which is part of the way map counting
+					 * is done for shared PMDs.  Return 'true'
+					 * here.  When there is no other sharing,
+					 * huge_pmd_unshare returns false and we will
+					 * unmap the actual page and drop map count
+					 * to zero.
+					 */
+					page_vma_mapped_walk_done(&pvmw);
+					break;
+				}
 			}
 		} else {
 			flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
@@ -1885,13 +1888,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 		anon_exclusive = folio_test_anon(folio) &&
 				 PageAnonExclusive(subpage);
 
-		if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) {
-			/*
-			 * To call huge_pmd_unshare, i_mmap_rwsem must be
-			 * held in write mode.  Caller needs to explicitly
-			 * do this outside rmap routines.
-			 */
-			VM_BUG_ON(!(flags & TTU_RMAP_LOCKED));
+		if (folio_test_hugetlb(folio)) {
 			/*
 			 * huge_pmd_unshare may unmap an entire PMD page.
 			 * There is no way of knowing exactly which PMDs may
@@ -1901,22 +1898,31 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			 */
 			flush_cache_range(vma, range.start, range.end);
 
-			if (huge_pmd_unshare(mm, vma, &address, pvmw.pte)) {
-				flush_tlb_range(vma, range.start, range.end);
-				mmu_notifier_invalidate_range(mm, range.start,
-							      range.end);
-
+			if (!folio_test_anon(folio)) {
 				/*
-				 * The ref count of the PMD page was dropped
-				 * which is part of the way map counting
-				 * is done for shared PMDs.  Return 'true'
-				 * here.  When there is no other sharing,
-				 * huge_pmd_unshare returns false and we will
-				 * unmap the actual page and drop map count
-				 * to zero.
+				 * To call huge_pmd_unshare, i_mmap_rwsem must be
+				 * held in write mode.  Caller needs to explicitly
+				 * do this outside rmap routines.
 				 */
-				page_vma_mapped_walk_done(&pvmw);
-				break;
+				VM_BUG_ON(!(flags & TTU_RMAP_LOCKED));
+
+				if (huge_pmd_unshare(mm, vma, &address, pvmw.pte)) {
+					flush_tlb_range(vma, range.start, range.end);
+					mmu_notifier_invalidate_range(mm, range.start,
+								      range.end);
+
+					/*
+					 * The ref count of the PMD page was dropped
+					 * which is part of the way map counting
+					 * is done for shared PMDs.  Return 'true'
+					 * here.  When there is no other sharing,
+					 * huge_pmd_unshare returns false and we will
+					 * unmap the actual page and drop map count
+					 * to zero.
+					 */
+					page_vma_mapped_walk_done(&pvmw);
+					break;
+				}
 			}
 		} else {
 			flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
-- 
1.8.3.1