Swap a large anon folio back in as a unit when its vswap entries share a
contiguous run of physical swap slots on a synchronous IO device,
instead of always falling back to order-0 faults.

A zswap-backed or mixed-backing batch is still refused, and the fault
retries at a smaller order.

Signed-off-by: Nhat Pham <nphamcs@gmail.com>
---
 mm/memory.c     |  5 +++--
 mm/swap_state.c | 17 +++++++++++++----
 mm/zswap.c      | 19 +++++++++++++------
 3 files changed, 29 insertions(+), 12 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index dc4dd72ce73b..62f7b82427e2 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4823,9 +4823,10 @@ static unsigned long thp_swapin_suitable_orders(struct vm_fault *vmf)
 	 * lack handling for such cases, so fallback to swapping in order-0
 	 * folio.
 	 *
-	 * THP swapin for vswap is not supported yet either.
+	 * Vswap entries are checked later, under the cluster lock in
+	 * __swap_cache_add_check().
 	 */
-	if (is_vswap_entry(entry) || !zswap_never_enabled())
+	if (!is_vswap_entry(entry) && !zswap_never_enabled())
 		return 0;
 
 	/*
diff --git a/mm/swap_state.c b/mm/swap_state.c
index c0441783b8e7..5cfddec8633b 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -174,6 +174,9 @@ static int __swap_cache_add_check(struct swap_cluster_info *ci,
 	unsigned int ci_off, ci_end;
 	unsigned long old_tb;
 	bool is_zero;
+	struct swap_cluster_info_dynamic *ci_dyn;
+	enum vswap_backing_type type;
+	int ret;
 
 	lockdep_assert_held(&ci->lock);
 
@@ -202,11 +205,17 @@ static int __swap_cache_add_check(struct swap_cluster_info *ci,
 		return 0;
 
 	/*
-	 * Reject a vswap batch so swap_cache_alloc_folio falls back to
-	 * order 0.
+	 * For a vswap entry batch, reject if the backing is not THP-amenable
+	 * (e.g. uniformly ZSWAP, or mixed). The order-fallback loop in
+	 * swap_cache_alloc_folio will retry with a smaller order on -EBUSY.
 	 */
-	if (is_vswap_entry(targ_entry))
-		return -EBUSY;
+	if (is_vswap_entry(targ_entry)) {
+		ci_dyn = container_of(ci, struct swap_cluster_info_dynamic, ci);
+		ret = __vswap_check_backing(ci_dyn, round_down(ci_off, nr),
+					    nr, &type);
+		if (ret != nr || type == VSWAP_ZSWAP)
+			return -EBUSY;
+	}
 
 	is_zero = __swap_table_test_zero(ci, ci_off);
 	ci_off = round_down(ci_off, nr);
diff --git a/mm/zswap.c b/mm/zswap.c
index 9a00ee049cf4..f16c0b44b5d5 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -1629,9 +1629,9 @@ bool zswap_store(struct folio *folio)
  *  will SIGBUS).
  *
  *  -EINVAL: if the swapped out content was in zswap, but the page belongs
- *  to a large folio, which is not supported by zswap. The folio is unlocked,
- *  but NOT marked up-to-date, so that an IO error is emitted (e.g.
- *  do_swap_page() will SIGBUS).
+ *  to a large non-vswap folio, which is not supported by zswap. The folio
+ *  is unlocked, but NOT marked up-to-date, so that an IO error is emitted
+ *  (e.g. do_swap_page() will SIGBUS).
  *
  *  -ENOENT: if the swapped out content was not in zswap. The folio remains
  *  locked on return.
@@ -1652,10 +1652,17 @@ int zswap_load(struct folio *folio)
 	 * Large folios should not be swapped in while zswap is being used, as
 	 * they are not properly handled. Zswap does not properly load large
 	 * folios, and a large folio may only be partially in zswap.
+	 *
+	 * A large vswap folio cannot reach here ZSWAP-backed, since
+	 * __swap_cache_add_check() refuses such a batch, so hand it to the
+	 * phys path without warning.
 	 */
-	if (WARN_ON_ONCE(folio_test_large(folio))) {
-		folio_unlock(folio);
-		return -EINVAL;
+	if (folio_test_large(folio)) {
+		if (WARN_ON_ONCE(!swap_is_vswap(si))) {
+			folio_unlock(folio);
+			return -EINVAL;
+		}
+		return -ENOENT;
 	}
 
 	entry = zswap_entry_load(swp);
-- 
2.53.0-Meta