[PATCH v3 0/2] mm: folio conversion and refactoring in do_swap_page()

[PATCH v3 0/2] mm: folio conversion and refactoring in do_swap_page()

[Hongfu Li]

From: Hongfu Li <lihongfu@kylinos.cn>

Convert the device-private migration path in do_swap_page() to use
folio APIs, then extract all non-swap entry handling into a new
do_non_swap_page() helper to improve readability and reduce the
size of the main swap fault function.

Hongfu Li (2):
  mm: Use a folio in the softleaf_is_device_private path
  mm: Extract non-swap entry handling to do_nonswap_softleaf()

 mm/memory.c | 118 ++++++++++++++++++++++++++++++----------------------
 1 file changed, 68 insertions(+), 50 deletions(-)

---
v3:
- Rename do_non_swap_page() to do_nonswap_softleaf().
- Update the commit subject and body of patch 2/2 accordingly.
- Drop a blank line after the device_private condition in
  do_nonswap_softleaf().
v2:
- Drop fault_folio, reuse the existing folio variable instead
- Refresh commit messages
- Update comment to use "folio" instead of "page" in the
  device_private path
- Add Acked-by: David Hildenbrand
- Add patch 2/2 to extract do_non_swap_page() from do_swap_page()
- Link to v1: https://lore.kernel.org/all/20260721013347.65698-1-hongfu.li@linux.dev/
-- 
2.54.0

[PATCH v3 1/2] mm: Use a folio in the softleaf_is_device_private path

[Hongfu Li]

From: Hongfu Li <lihongfu@kylinos.cn>

Use the folio APIs in the device_private migration path of do_swap_page(),
replacing four calls to compound_head() with one.

Signed-off-by: Hongfu Li <lihongfu@kylinos.cn>
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
---
 mm/memory.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index 56b244552f13..bbb289ba09d3 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4873,18 +4873,19 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 				goto unlock;
 
 			/*
-			 * Get a page reference while we know the page can't be
+			 * Get a folio reference while we know the folio can't be
 			 * freed.
 			 */
-			if (trylock_page(vmf->page)) {
+			folio = page_folio(vmf->page);
+			if (folio_trylock(folio)) {
 				struct dev_pagemap *pgmap;
 
-				get_page(vmf->page);
+				folio_get(folio);
 				pte_unmap_unlock(vmf->pte, vmf->ptl);
 				pgmap = page_pgmap(vmf->page);
 				ret = pgmap->ops->migrate_to_ram(vmf);
-				unlock_page(vmf->page);
-				put_page(vmf->page);
+				folio_unlock(folio);
+				folio_put(folio);
 			} else {
 				pte_unmap(vmf->pte);
 				softleaf_entry_wait_on_locked(entry, vmf->ptl);
-- 
2.54.0

[PATCH v3 2/2] mm: Extract non-swap entry handling to do_nonswap_softleaf()

[Hongfu Li]

From: Hongfu Li <lihongfu@kylinos.cn>

Factor non-swap entry logic out of bloated do_swap_page() to simplify
the main swap fault flow and improve readability.

The new do_nonswap_softleaf() handles migration, device private/exclusive,
hwpoison, marker and bad PTE entries.

Signed-off-by: Hongfu Li <lihongfu@kylinos.cn>
---
 mm/memory.c | 119 ++++++++++++++++++++++++++++++----------------------
 1 file changed, 68 insertions(+), 51 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index bbb289ba09d3..ff3da0aa3e11 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4817,6 +4817,73 @@ static void check_swap_exclusive(struct folio *folio, swp_entry_t entry,
 	} while (--nr_pages);
 }
 
+static vm_fault_t do_nonswap_softleaf(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct folio *folio;
+	softleaf_t entry;
+	vm_fault_t ret = 0;
+
+	entry = softleaf_from_pte(vmf->orig_pte);
+	if (softleaf_is_migration(entry)) {
+		migration_entry_wait(vma->vm_mm, vmf->pmd,
+				     vmf->address);
+	} else if (softleaf_is_device_exclusive(entry)) {
+		vmf->page = softleaf_to_page(entry);
+		ret = remove_device_exclusive_entry(vmf);
+	} else if (softleaf_is_device_private(entry)) {
+		if (vmf->flags & FAULT_FLAG_VMA_LOCK) {
+			/*
+			 * migrate_to_ram is not yet ready to operate
+			 * under VMA lock.
+			 */
+			vma_end_read(vma);
+			return VM_FAULT_RETRY;
+		}
+
+		vmf->page = softleaf_to_page(entry);
+		vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
+						vmf->address, &vmf->ptl);
+		if (unlikely(!vmf->pte ||
+			     !pte_same(ptep_get(vmf->pte),
+					vmf->orig_pte)))
+			goto unlock;
+
+		/*
+		 * Get a folio reference while we know the folio can't be
+		 * freed.
+		 */
+		folio = page_folio(vmf->page);
+		if (folio_trylock(folio)) {
+			struct dev_pagemap *pgmap;
+
+			folio_get(folio);
+			pte_unmap_unlock(vmf->pte, vmf->ptl);
+			pgmap = page_pgmap(vmf->page);
+			ret = pgmap->ops->migrate_to_ram(vmf);
+			folio_unlock(folio);
+			folio_put(folio);
+		} else {
+			pte_unmap(vmf->pte);
+			softleaf_entry_wait_on_locked(entry, vmf->ptl);
+		}
+	} else if (softleaf_is_hwpoison(entry)) {
+		ret = VM_FAULT_HWPOISON;
+	} else if (softleaf_is_marker(entry)) {
+		ret = handle_pte_marker(vmf);
+	} else {
+		print_bad_pte(vma, vmf->address, vmf->orig_pte, NULL);
+		ret = VM_FAULT_SIGBUS;
+	}
+
+	return ret;
+
+unlock:
+	if (vmf->pte)
+		pte_unmap_unlock(vmf->pte, vmf->ptl);
+	return ret;
+}
+
 /*
  * We enter with either the VMA lock or the mmap_lock held (see
  * FAULT_FLAG_VMA_LOCK), and pte mapped but not yet locked.
@@ -4847,57 +4914,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 
 	entry = softleaf_from_pte(vmf->orig_pte);
 	if (unlikely(!softleaf_is_swap(entry))) {
-		if (softleaf_is_migration(entry)) {
-			migration_entry_wait(vma->vm_mm, vmf->pmd,
-					     vmf->address);
-		} else if (softleaf_is_device_exclusive(entry)) {
-			vmf->page = softleaf_to_page(entry);
-			ret = remove_device_exclusive_entry(vmf);
-		} else if (softleaf_is_device_private(entry)) {
-			if (vmf->flags & FAULT_FLAG_VMA_LOCK) {
-				/*
-				 * migrate_to_ram is not yet ready to operate
-				 * under VMA lock.
-				 */
-				vma_end_read(vma);
-				ret = VM_FAULT_RETRY;
-				goto out;
-			}
-
-			vmf->page = softleaf_to_page(entry);
-			vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
-					vmf->address, &vmf->ptl);
-			if (unlikely(!vmf->pte ||
-				     !pte_same(ptep_get(vmf->pte),
-							vmf->orig_pte)))
-				goto unlock;
-
-			/*
-			 * Get a folio reference while we know the folio can't be
-			 * freed.
-			 */
-			folio = page_folio(vmf->page);
-			if (folio_trylock(folio)) {
-				struct dev_pagemap *pgmap;
-
-				folio_get(folio);
-				pte_unmap_unlock(vmf->pte, vmf->ptl);
-				pgmap = page_pgmap(vmf->page);
-				ret = pgmap->ops->migrate_to_ram(vmf);
-				folio_unlock(folio);
-				folio_put(folio);
-			} else {
-				pte_unmap(vmf->pte);
-				softleaf_entry_wait_on_locked(entry, vmf->ptl);
-			}
-		} else if (softleaf_is_hwpoison(entry)) {
-			ret = VM_FAULT_HWPOISON;
-		} else if (softleaf_is_marker(entry)) {
-			ret = handle_pte_marker(vmf);
-		} else {
-			print_bad_pte(vma, vmf->address, vmf->orig_pte, NULL);
-			ret = VM_FAULT_SIGBUS;
-		}
+		ret = do_nonswap_softleaf(vmf);
 		goto out;
 	}
 
-- 
2.54.0

Re: [PATCH v3 0/2] mm: folio conversion and refactoring in do_swap_page()

[Hongfu Li]

> Convert the device-private migration path in do_swap_page() to use
> folio APIs, then extract all non-swap entry handling into a new
> do_non_swap_page() helper to improve readability and reduce the
> size of the main swap fault function.

Please disregard this email. There is something I got wrong. Sorry for the noise.