1 files changed, 49 insertions, 43 deletions

diff --git a/mm/gup.c b/mm/gup.c
index 6e2f9e9d6537..948f3b454b00 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -811,7 +811,6 @@ static struct page *follow_page_mask(struct vm_area_struct *vma,
 			      struct follow_page_context *ctx)
 {
 	pgd_t *pgd;
-	struct page *page;
 	struct mm_struct *mm = vma->vm_mm;
 
 	ctx->page_mask = 0;
@@ -820,16 +819,10 @@ static struct page *follow_page_mask(struct vm_area_struct *vma,
 	 * Call hugetlb_follow_page_mask for hugetlb vmas as it will use
 	 * special hugetlb page table walking code.  This eliminates the
 	 * need to check for hugetlb entries in the general walking code.
-	 *
-	 * hugetlb_follow_page_mask is only for follow_page() handling here.
-	 * Ordinary GUP uses follow_hugetlb_page for hugetlb processing.
 	 */
-	if (is_vm_hugetlb_page(vma)) {
-		page = hugetlb_follow_page_mask(vma, address, flags);
-		if (!page)
-			page = no_page_table(vma, flags);
-		return page;
-	}
+	if (is_vm_hugetlb_page(vma))
+		return hugetlb_follow_page_mask(vma, address, flags,
+						&ctx->page_mask);
 
 	pgd = pgd_offset(mm, address);
 
@@ -1215,7 +1208,7 @@ static long __get_user_pages(struct mm_struct *mm,
 			if (!vma && in_gate_area(mm, start)) {
 				ret = get_gate_page(mm, start & PAGE_MASK,
 						gup_flags, &vma,
-						pages ? &pages[i] : NULL);
+						pages ? &page : NULL);
 				if (ret)
 					goto out;
 				ctx.page_mask = 0;
@@ -1229,22 +1222,6 @@ static long __get_user_pages(struct mm_struct *mm,
 			ret = check_vma_flags(vma, gup_flags);
 			if (ret)
 				goto out;
-
-			if (is_vm_hugetlb_page(vma)) {
-				i = follow_hugetlb_page(mm, vma, pages,
-							&start, &nr_pages, i,
-							gup_flags, locked);
-				if (!*locked) {
-					/*
-					 * We've got a VM_FAULT_RETRY
-					 * and we've lost mmap_lock.
-					 * We must stop here.
-					 */
-					BUG_ON(gup_flags & FOLL_NOWAIT);
-					goto out;
-				}
-				continue;
-			}
 		}
 retry:
 		/*
@@ -1285,22 +1262,58 @@ retry:
 				ret = PTR_ERR(page);
 				goto out;
 			}
-
-			goto next_page;
 		} else if (IS_ERR(page)) {
 			ret = PTR_ERR(page);
 			goto out;
 		}
-		if (pages) {
-			pages[i] = page;
-			flush_anon_page(vma, page, start);
-			flush_dcache_page(page);
-			ctx.page_mask = 0;
-		}
 next_page:
 		page_increm = 1 + (~(start >> PAGE_SHIFT) & ctx.page_mask);
 		if (page_increm > nr_pages)
 			page_increm = nr_pages;
+
+		if (pages) {
+			struct page *subpage;
+			unsigned int j;
+
+			/*
+			 * This must be a large folio (and doesn't need to
+			 * be the whole folio; it can be part of it), do
+			 * the refcount work for all the subpages too.
+			 *
+			 * NOTE: here the page may not be the head page
+			 * e.g. when start addr is not thp-size aligned.
+			 * try_grab_folio() should have taken care of tail
+			 * pages.
+			 */
+			if (page_increm > 1) {
+				struct folio *folio;
+
+				/*
+				 * Since we already hold refcount on the
+				 * large folio, this should never fail.
+				 */
+				folio = try_grab_folio(page, page_increm - 1,
+						       foll_flags);
+				if (WARN_ON_ONCE(!folio)) {
+					/*
+					 * Release the 1st page ref if the
+					 * folio is problematic, fail hard.
+					 */
+					gup_put_folio(page_folio(page), 1,
+						      foll_flags);
+					ret = -EFAULT;
+					goto out;
+				}
+			}
+
+			for (j = 0; j < page_increm; j++) {
+				subpage = nth_page(page, j);
+				pages[i + j] = subpage;
+				flush_anon_page(vma, subpage, start + j * PAGE_SIZE);
+				flush_dcache_page(subpage);
+			}
+		}
+
 		i += page_increm;
 		start += page_increm * PAGE_SIZE;
 		nr_pages -= page_increm;
@@ -2231,13 +2244,6 @@ static bool is_valid_gup_args(struct page **pages, int *locked,
 		gup_flags |= FOLL_UNLOCKABLE;
 	}
 
-	/*
-	 * For now, always trigger NUMA hinting faults. Some GUP users like
-	 * KVM require the hint to be as the calling context of GUP is
-	 * functionally similar to a memory reference from task context.
-	 */
-	gup_flags |= FOLL_HONOR_NUMA_FAULT;
-
 	/* FOLL_GET and FOLL_PIN are mutually exclusive. */
 	if (WARN_ON_ONCE((gup_flags & (FOLL_PIN | FOLL_GET)) ==
 			 (FOLL_PIN | FOLL_GET)))
@@ -2594,7 +2600,7 @@ static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
 		if (!folio)
 			goto pte_unmap;
 
-		if (unlikely(page_is_secretmem(page))) {
+		if (unlikely(folio_is_secretmem(folio))) {
 			gup_put_folio(folio, 1, flags);
 			goto pte_unmap;
 		}