1 files changed, 38 insertions, 27 deletions

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 67ab391a5373..a7d6cb912b05 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -442,18 +442,28 @@ static inline int khugepaged_test_exit(struct mm_struct *mm)
 static bool hugepage_vma_check(struct vm_area_struct *vma,
 			       unsigned long vm_flags)
 {
-	if ((!(vm_flags & VM_HUGEPAGE) && !khugepaged_always()) ||
-	    (vm_flags & VM_NOHUGEPAGE) ||
+	/* Explicitly disabled through madvise. */
+	if ((vm_flags & VM_NOHUGEPAGE) ||
 	    test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))
 		return false;
 
-	if (shmem_file(vma->vm_file) ||
-	    (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) &&
-	     vma->vm_file &&
-	     (vm_flags & VM_DENYWRITE))) {
+	/* Enabled via shmem mount options or sysfs settings. */
+	if (shmem_file(vma->vm_file) && shmem_huge_enabled(vma)) {
 		return IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff,
 				HPAGE_PMD_NR);
 	}
+
+	/* THP settings require madvise. */
+	if (!(vm_flags & VM_HUGEPAGE) && !khugepaged_always())
+		return false;
+
+	/* Read-only file mappings need to be aligned for THP to work. */
+	if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && vma->vm_file &&
+	    (vm_flags & VM_DENYWRITE)) {
+		return IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff,
+				HPAGE_PMD_NR);
+	}
+
 	if (!vma->anon_vma || vma->vm_ops)
 		return false;
 	if (vma_is_temporary_stack(vma))
@@ -991,38 +1001,41 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address,
 
 static bool __collapse_huge_page_swapin(struct mm_struct *mm,
 					struct vm_area_struct *vma,
-					unsigned long address, pmd_t *pmd,
+					unsigned long haddr, pmd_t *pmd,
 					int referenced)
 {
 	int swapped_in = 0;
 	vm_fault_t ret = 0;
-	struct vm_fault vmf = {
-		.vma = vma,
-		.address = address,
-		.flags = FAULT_FLAG_ALLOW_RETRY,
-		.pmd = pmd,
-		.pgoff = linear_page_index(vma, address),
-	};
-
-	vmf.pte = pte_offset_map(pmd, address);
-	for (; vmf.address < address + HPAGE_PMD_NR*PAGE_SIZE;
-			vmf.pte++, vmf.address += PAGE_SIZE) {
+	unsigned long address, end = haddr + (HPAGE_PMD_NR * PAGE_SIZE);
+
+	for (address = haddr; address < end; address += PAGE_SIZE) {
+		struct vm_fault vmf = {
+			.vma = vma,
+			.address = address,
+			.pgoff = linear_page_index(vma, haddr),
+			.flags = FAULT_FLAG_ALLOW_RETRY,
+			.pmd = pmd,
+		};
+
+		vmf.pte = pte_offset_map(pmd, address);
 		vmf.orig_pte = *vmf.pte;
-		if (!is_swap_pte(vmf.orig_pte))
+		if (!is_swap_pte(vmf.orig_pte)) {
+			pte_unmap(vmf.pte);
 			continue;
+		}
 		swapped_in++;
 		ret = do_swap_page(&vmf);
 
 		/* do_swap_page returns VM_FAULT_RETRY with released mmap_lock */
 		if (ret & VM_FAULT_RETRY) {
 			mmap_read_lock(mm);
-			if (hugepage_vma_revalidate(mm, address, &vmf.vma)) {
+			if (hugepage_vma_revalidate(mm, haddr, &vma)) {
 				/* vma is no longer available, don't continue to swapin */
 				trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
 				return false;
 			}
 			/* check if the pmd is still valid */
-			if (mm_find_pmd(mm, address) != pmd) {
+			if (mm_find_pmd(mm, haddr) != pmd) {
 				trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
 				return false;
 			}
@@ -1031,11 +1044,7 @@ static bool __collapse_huge_page_swapin(struct mm_struct *mm,
 			trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
 			return false;
 		}
-		/* pte is unmapped now, we need to map it */
-		vmf.pte = pte_offset_map(pmd, vmf.address);
 	}
-	vmf.pte--;
-	pte_unmap(vmf.pte);
 
 	/* Drain LRU add pagevec to remove extra pin on the swapped in pages */
 	if (swapped_in)
@@ -1644,6 +1653,7 @@ static void collapse_file(struct mm_struct *mm,
 	XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER);
 	int nr_none = 0, result = SCAN_SUCCEED;
 	bool is_shmem = shmem_file(file);
+	int nr;
 
 	VM_BUG_ON(!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !is_shmem);
 	VM_BUG_ON(start & (HPAGE_PMD_NR - 1));
@@ -1855,11 +1865,12 @@ out_unlock:
 		put_page(page);
 		goto xa_unlocked;
 	}
+	nr = thp_nr_pages(new_page);
 
 	if (is_shmem)
-		__inc_lruvec_page_state(new_page, NR_SHMEM_THPS);
+		__mod_lruvec_page_state(new_page, NR_SHMEM_THPS, nr);
 	else {
-		__inc_lruvec_page_state(new_page, NR_FILE_THPS);
+		__mod_lruvec_page_state(new_page, NR_FILE_THPS, nr);
 		filemap_nr_thps_inc(mapping);
 	}