[PATCH v10 1/3] madvise: use zap_page_range_single for madvise dontneed

[Mike Kravetz <mike.kravetz@oracle.com>]

Expose the routine zap_page_range_single to zap a range within a single
vma.  The madvise routine madvise_dontneed_single_vma can use this
routine as it explicitly operates on a single vma.  Also, update the mmu
notification range in zap_page_range_single to take hugetlb pmd sharing
into account.  This is required as MADV_DONTNEED supports hugetlb vmas.

Fixes: 90e7e7f5ef3f ("mm: enable MADV_DONTNEED for hugetlb mappings")
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Reported-by: Wei Chen <harperchen1110@gmail.com>
Cc: <stable@vger.kernel.org>
---
 include/linux/mm.h | 27 +++++++++++++++++++--------
 mm/madvise.c       |  6 +++---
 mm/memory.c        | 23 +++++++++++------------
 3 files changed, 33 insertions(+), 23 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 9838b535fa21..dd5a38682537 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1870,6 +1870,23 @@ static void __maybe_unused show_free_areas(unsigned int flags, nodemask_t *nodem
 	__show_free_areas(flags, nodemask, MAX_NR_ZONES - 1);
 }
 
+/*
+ * Parameter block passed down to zap_pte_range in exceptional cases.
+ */
+struct zap_details {
+	struct folio *single_folio;	/* Locked folio to be unmapped */
+	bool even_cows;			/* Zap COWed private pages too? */
+	zap_flags_t zap_flags;		/* Extra flags for zapping */
+};
+
+/*
+ * Whether to drop the pte markers, for example, the uffd-wp information for
+ * file-backed memory.  This should only be specified when we will completely
+ * drop the page in the mm, either by truncation or unmapping of the vma.  By
+ * default, the flag is not set.
+ */
+#define  ZAP_FLAG_DROP_MARKER        ((__force zap_flags_t) BIT(0))
+
 #ifdef CONFIG_MMU
 extern bool can_do_mlock(void);
 #else
@@ -1887,6 +1904,8 @@ void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
 		  unsigned long size);
 void zap_page_range(struct vm_area_struct *vma, unsigned long address,
 		    unsigned long size);
+void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
+			   unsigned long size, struct zap_details *details);
 void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt,
 		struct vm_area_struct *start_vma, unsigned long start,
 		unsigned long end);
@@ -3518,12 +3537,4 @@ madvise_set_anon_name(struct mm_struct *mm, unsigned long start,
 }
 #endif
 
-/*
- * Whether to drop the pte markers, for example, the uffd-wp information for
- * file-backed memory.  This should only be specified when we will completely
- * drop the page in the mm, either by truncation or unmapping of the vma.  By
- * default, the flag is not set.
- */
-#define  ZAP_FLAG_DROP_MARKER        ((__force zap_flags_t) BIT(0))
-
 #endif /* _LINUX_MM_H */
diff --git a/mm/madvise.c b/mm/madvise.c
index df62d9e1035a..a21b186eb7a0 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -785,8 +785,8 @@ static int madvise_free_single_vma(struct vm_area_struct *vma,
  * Application no longer needs these pages.  If the pages are dirty,
  * it's OK to just throw them away.  The app will be more careful about
  * data it wants to keep.  Be sure to free swap resources too.  The
- * zap_page_range call sets things up for shrink_active_list to actually free
- * these pages later if no one else has touched them in the meantime,
+ * zap_page_range_single call sets things up for shrink_active_list to actually
+ * free these pages later if no one else has touched them in the meantime,
  * although we could add these pages to a global reuse list for
  * shrink_active_list to pick up before reclaiming other pages.
  *
@@ -803,7 +803,7 @@ static int madvise_free_single_vma(struct vm_area_struct *vma,
 static long madvise_dontneed_single_vma(struct vm_area_struct *vma,
 					unsigned long start, unsigned long end)
 {
-	zap_page_range(vma, start, end - start);
+	zap_page_range_single(vma, start, end - start, NULL);
 	return 0;
 }
 
diff --git a/mm/memory.c b/mm/memory.c
index 98ddb91df9a7..a177f6bbfafc 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1294,15 +1294,6 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 	return ret;
 }
 
-/*
- * Parameter block passed down to zap_pte_range in exceptional cases.
- */
-struct zap_details {
-	struct folio *single_folio;	/* Locked folio to be unmapped */
-	bool even_cows;			/* Zap COWed private pages too? */
-	zap_flags_t zap_flags;		/* Extra flags for zapping */
-};
-
 /* Whether we should zap all COWed (private) pages too */
 static inline bool should_zap_cows(struct zap_details *details)
 {
@@ -1736,19 +1727,27 @@ void zap_page_range(struct vm_area_struct *vma, unsigned long start,
  *
  * The range must fit into one VMA.
  */
-static void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
+void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
 		unsigned long size, struct zap_details *details)
 {
+	const unsigned long end = address + size;
 	struct mmu_notifier_range range;
 	struct mmu_gather tlb;
 
 	lru_add_drain();
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
-				address, address + size);
+				address, end);
+	if (is_vm_hugetlb_page(vma))
+		adjust_range_if_pmd_sharing_possible(vma, &range.start,
+						     &range.end);
 	tlb_gather_mmu(&tlb, vma->vm_mm);
 	update_hiwater_rss(vma->vm_mm);
 	mmu_notifier_invalidate_range_start(&range);
-	unmap_single_vma(&tlb, vma, address, range.end, details);
+	/*
+	 * unmap 'address-end' not 'range.start-range.end' as range
+	 * could have been expanded for hugetlb pmd sharing.
+	 */
+	unmap_single_vma(&tlb, vma, address, end, details);
 	mmu_notifier_invalidate_range_end(&range);
 	tlb_finish_mmu(&tlb);
 }
-- 
2.38.1