[PATCH v3 1/2] mm, swap: distinguish a malformed swap entry from a dying device

get_swap_device() returns NULL for two different things: an entry whose
type names no swap device or whose offset is past the end of one, and a
device that swapoff is taking away. The first never becomes valid, the
second does, and callers cannot tell them apart.

Return ERR_PTR(-EIO) for the two malformed cases and keep NULL for
swapoff. copy_nonpresent_pte() already reports -EIO for an entry whose
type names no device.

Callers bail out on failure either way, so switch them to
IS_ERR_OR_NULL(), and let the two paths that drop the reference skip an
error pointer. No functional change.

Reviewed-by: Barry Song <[email protected]>
Acked-by: Kairui Song <[email protected]>
Signed-off-by: Breno Leitao <[email protected]>
---
 mm/memory.c      |  6 +++---
 mm/mincore.c     |  2 +-
 mm/shmem.c       |  2 +-
 mm/swap_state.c  |  4 ++--
 mm/swapfile.c    | 14 +++++++++-----
 mm/userfaultfd.c |  4 ++--
 mm/zswap.c       |  2 +-
 7 files changed, 19 insertions(+), 15 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index d9cf941967cf0..03d8cf111d0be 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4954,9 +4954,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 		goto out;
 	}
 
-	/* Prevent swapoff from happening to us. */
+	/* Prevent swapoff from happening to us, and reject a bad entry. */
 	si = get_swap_device(entry);
-	if (unlikely(!si))
+	if (IS_ERR_OR_NULL(si))
 		goto out;
 
 	folio = swap_cache_get_folio(entry);
@@ -5266,7 +5266,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	if (vmf->pte)
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
 out:
-	if (si)
+	if (!IS_ERR_OR_NULL(si))
 		put_swap_device(si);
 	return ret;
 out_nomap:
diff --git a/mm/mincore.c b/mm/mincore.c
index ff4ac82817683..c086836bc4bcc 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -71,7 +71,7 @@ static unsigned char mincore_swap(swp_entry_t entry, bool shmem)
 	 */
 	if (shmem) {
 		si = get_swap_device(entry);
-		if (!si)
+		if (IS_ERR_OR_NULL(si))
 			return 0;
 	}
 	folio = swap_cache_get_folio(entry);
diff --git a/mm/shmem.c b/mm/shmem.c
index 65572cbf1bd3c..d0a9f52bfed71 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2276,7 +2276,7 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
 
 	si = get_swap_device(index_entry);
 	order = shmem_confirm_swap(mapping, index, index_entry);
-	if (unlikely(!si)) {
+	if (IS_ERR_OR_NULL(si)) {
 		if (order < 0)
 			return -EEXIST;
 		else
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 4b7a3303c463b..f2e86d6626ecc 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -715,7 +715,7 @@ struct folio *read_swap_cache_async(struct swap_io_ctx *ctx, swp_entry_t entry,
 	struct folio *folio;
 
 	si = get_swap_device(entry);
-	if (!si)
+	if (IS_ERR_OR_NULL(si))
 		return NULL;
 
 	mpol = get_vma_policy(vma, addr, 0, &ilx);
@@ -951,7 +951,7 @@ static struct folio *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask,
 		 */
 		if (swp_type(entry) != swp_type(targ_entry)) {
 			si = get_swap_device(entry);
-			if (!si)
+			if (IS_ERR_OR_NULL(si))
 				continue;
 		}
 		folio = swap_cache_read_folio(&ctx, entry, gfp_mask, mpol, ilx,
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 4d4e3e3059f6b..3b1883930e943 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1504,7 +1504,7 @@ int swap_retry_table_alloc(swp_entry_t entry, gfp_t gfp)
 	unsigned long offset = swp_offset(entry);
 
 	si = get_swap_device(entry);
-	if (!si)
+	if (IS_ERR_OR_NULL(si))
 		return 0;
 
 	ci = __swap_offset_to_cluster(si, offset);
@@ -1859,7 +1859,10 @@ void folio_put_swap(struct folio *folio, struct page *page)
  * Check whether swap entry is valid in the swap device.  If so,
  * return pointer to swap_info_struct, and keep the swap entry valid
  * via preventing the swap device from being swapoff, until
- * put_swap_device() is called.  Otherwise return NULL.
+ * put_swap_device() is called.  Return NULL for an empty entry or a
+ * device that is going away, and ERR_PTR(-EIO) if the entry's type
+ * names no swap device or its offset is past the end of one. These EIOs
+ * are preceded by pr_err().
  *
  * Notice that swapoff or swapoff+swapon can still happen before the
  * percpu_ref_tryget_live() in get_swap_device() or after the
@@ -1900,12 +1903,13 @@ struct swap_info_struct *get_swap_device(swp_entry_t entry)
 	return si;
 bad_nofile:
 	pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val);
+	return ERR_PTR(-EIO);
 out:
 	return NULL;
 put_out:
 	pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val);
 	percpu_ref_put(&si->users);
-	return NULL;
+	return ERR_PTR(-EIO);
 }
 
 /*
@@ -2001,7 +2005,7 @@ int swp_swapcount(swp_entry_t entry)
 	int count;
 
 	si = get_swap_device(entry);
-	if (!si)
+	if (IS_ERR_OR_NULL(si))
 		return 0;
 
 	ci = swap_cluster_lock(si, swp_offset(entry));
@@ -2127,7 +2131,7 @@ void swap_put_entries_direct(swp_entry_t entry, int nr)
 	struct swap_info_struct *si;
 
 	si = get_swap_device(entry);
-	if (WARN_ON_ONCE(!si))
+	if (WARN_ON_ONCE(IS_ERR_OR_NULL(si)))
 		return;
 	if (WARN_ON_ONCE(end_offset > si->max))
 		goto out;
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 24a4d92ffa3c2..cba5e20a641ed 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -1700,7 +1700,7 @@ static long move_pages_ptes(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd
 		}
 
 		si = get_swap_device(entry);
-		if (unlikely(!si)) {
+		if (IS_ERR_OR_NULL(si)) {
 			ret = -EAGAIN;
 			goto out;
 		}
@@ -1757,7 +1757,7 @@ static long move_pages_ptes(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd
 	if (dst_pte)
 		pte_unmap(dst_pte);
 	mmu_notifier_invalidate_range_end(&range);
-	if (si)
+	if (!IS_ERR_OR_NULL(si))
 		put_swap_device(si);
 
 	return ret;
diff --git a/mm/zswap.c b/mm/zswap.c
index f7c9c89f6449c..bc9b931d6f447 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -997,7 +997,7 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
 
 	/* try to allocate swap cache folio */
 	si = get_swap_device(swpentry);
-	if (!si)
+	if (IS_ERR_OR_NULL(si))
 		return -EEXIST;
 
 	mpol = get_task_policy(current);

-- 
2.53.0-Meta