[PATCH v3 03/11] mm: handle PMD swap entries in fork path

[Usama Arif <usama.arif@linux.dev>]

Teach copy_huge_pmd()/copy_huge_non_present_pmd() about swap entries,
mirroring copy_nonpresent_pte().

swap_dup_entry_direct() gains a nr parameter (and is renamed to
swap_dup_entries_direct()) so it can duplicate a contiguous range of
swap slots in one call, matching the existing
swap_put_entries_direct(entry, nr) API.  Existing callers pass 1.

copy_huge_non_present_pmd() "copies" PMD swap entries during fork
instead of splitting, preserving the THP.  This mirrors
copy_nonpresent_pte() which duplicates the swap slot refcount,
clears the exclusive bit on the source, and adds the destination
mm to mmlist.  If swap_dup_entries_direct() fails (GFP_ATOMIC table
alloc), copy_huge_pmd() retries after swap_retry_table_alloc() with
GFP_KERNEL, matching the PTE retry in copy_pte_range().  The PMD is
stable across the retry because dup_mmap() holds write mmap_lock on
both mm_structs.

Signed-off-by: Usama Arif <usama.arif@linux.dev>
---
 include/linux/swap.h |  4 ++--
 mm/huge_memory.c     | 53 ++++++++++++++++++++++++++++++++++++++------
 mm/memory.c          |  2 +-
 mm/swapfile.c        |  7 +++---
 4 files changed, 53 insertions(+), 13 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 8d19be675baf..0b1db19e6ae3 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -451,7 +451,7 @@ sector_t swap_folio_sector(struct folio *folio);
  * All entries must be allocated by folio_alloc_swap(). And they must have
  * a swap count > 1. See comments of folio_*_swap helpers for more info.
  */
-int swap_dup_entry_direct(swp_entry_t entry);
+int swap_dup_entries_direct(swp_entry_t entry, int nr);
 void swap_put_entries_direct(swp_entry_t entry, int nr);
 
 /*
@@ -495,7 +495,7 @@ static inline void free_swap_cache(struct folio *folio)
 {
 }
 
-static inline int swap_dup_entry_direct(swp_entry_t ent)
+static inline int swap_dup_entries_direct(swp_entry_t ent, int nr)
 {
 	return 0;
 }
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 201193ce0373..69e4e09ac1f6 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1805,7 +1805,7 @@ bool touch_pmd(struct vm_area_struct *vma, unsigned long addr,
 	return false;
 }
 
-static void copy_huge_non_present_pmd(
+static int copy_huge_non_present_pmd(
 		struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
 		struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
@@ -1851,14 +1851,35 @@ static void copy_huge_non_present_pmd(
 		 */
 		folio_try_dup_anon_rmap_pmd(src_folio, &src_folio->page,
 					    dst_vma, src_vma);
+	} else if (softleaf_is_swap(entry)) {
+		int err;
+
+		/*
+		 * PMD swap entry: duplicate swap references and clear
+		 * exclusive on source, matching copy_nonpresent_pte().
+		 */
+		err = swap_dup_entries_direct(entry, HPAGE_PMD_NR);
+		if (err < 0)
+			return err;
+
+		mm_prepare_for_swap_entries(dst_mm);
+
+		if (pmd_swp_exclusive(pmd)) {
+			pmd = pmd_swp_clear_exclusive(pmd);
+			set_pmd_at(src_mm, addr, src_pmd, pmd);
+		}
 	}
 
-	add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
+	if (softleaf_is_swap(entry))
+		add_mm_counter(dst_mm, MM_SWAPENTS, HPAGE_PMD_NR);
+	else
+		add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
 	mm_inc_nr_ptes(dst_mm);
 	pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
 	if (!userfaultfd_wp(dst_vma))
 		pmd = pmd_swp_clear_uffd_wp(pmd);
 	set_pmd_at(dst_mm, addr, dst_pmd, pmd);
+	return 0;
 }
 
 int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
@@ -1899,6 +1920,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	if (unlikely(!pgtable))
 		goto out;
 
+retry:
 	dst_ptl = pmd_lock(dst_mm, dst_pmd);
 	src_ptl = pmd_lockptr(src_mm, src_pmd);
 	spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
@@ -1906,11 +1928,28 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	ret = -EAGAIN;
 	pmd = *src_pmd;
 
-	if (unlikely(thp_migration_supported() &&
-		     pmd_is_valid_softleaf(pmd))) {
-		copy_huge_non_present_pmd(dst_mm, src_mm, dst_pmd, src_pmd, addr,
-					  dst_vma, src_vma, pmd, pgtable);
-		ret = 0;
+	if (unlikely(pmd_is_valid_softleaf(pmd))) {
+		ret = copy_huge_non_present_pmd(dst_mm, src_mm, dst_pmd, src_pmd,
+						addr, dst_vma, src_vma, pmd,
+						pgtable);
+		if (ret) {
+			spin_unlock(src_ptl);
+			spin_unlock(dst_ptl);
+			/*
+			 * For PMD swap entries -ENOMEM means the per-cluster
+			 * swap-extend table couldn't be GFP_ATOMIC-allocated.
+			 * try the GFP_KERNEL fallback once before giving up.
+			 */
+			if (ret == -ENOMEM) {
+				softleaf_t entry = softleaf_from_pmd(pmd);
+
+				if (softleaf_is_swap(entry) &&
+				    !swap_retry_table_alloc(entry, GFP_KERNEL))
+					goto retry;
+			}
+			pte_free(dst_mm, pgtable);
+			goto out;
+		}
 		goto out_unlock;
 	}
 
diff --git a/mm/memory.c b/mm/memory.c
index 6637c5b13c9b..e0819a562187 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -950,7 +950,7 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	struct page *page;
 
 	if (likely(softleaf_is_swap(entry))) {
-		if (swap_dup_entry_direct(entry) < 0)
+		if (swap_dup_entries_direct(entry, 1) < 0)
 			return -EIO;
 
 		mm_prepare_for_swap_entries(dst_mm);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 5a69716b2052..0695dbd1a8b1 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3899,8 +3899,9 @@ void si_swapinfo(struct sysinfo *val)
 }
 
 /*
- * swap_dup_entry_direct() - Increase reference count of a swap entry by one.
+ * swap_dup_entries_direct() - Increase reference count of swap entries by one.
  * @entry: first swap entry from which we want to increase the refcount.
+ * @nr: number of contiguous swap entries to duplicate.
  *
  * Returns 0 for success, or -ENOMEM if the extend table is required
  * but could not be atomically allocated.  Returns -EINVAL if the swap
@@ -3912,7 +3913,7 @@ void si_swapinfo(struct sysinfo *val)
  * Also the swap entry must have a count >= 1. Otherwise folio_dup_swap should
  * be used.
  */
-int swap_dup_entry_direct(swp_entry_t entry)
+int swap_dup_entries_direct(swp_entry_t entry, int nr)
 {
 	struct swap_info_struct *si;
 
@@ -3929,7 +3930,7 @@ int swap_dup_entry_direct(swp_entry_t entry)
 	 */
 	VM_WARN_ON_ONCE(!swap_entry_swapped(si, entry));
 
-	return swap_dup_entries_cluster(si, swp_offset(entry), 1);
+	return swap_dup_entries_cluster(si, swp_offset(entry), nr);
 }
 
 #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
-- 
2.53.0-Meta