[PATCH v6 05/12] mm, swap: enable THP swapin for vswap entries

[Nhat Pham]

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@xxxxxxxxx>
---
 mm/memory.c     |  5 +++--
 mm/swap_state.c | 17 +++++++++++++----
 mm/zswap.c      |  6 +++++-
 3 files changed, 21 insertions(+), 7 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index 9f651d247eef..430b83900ba8 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4885,9 +4885,10 @@ 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 3900975c675f..6c8e8f49e349 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 24c4e7a73d56..1b91dba992ab 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -1753,9 +1753,13 @@ int zswap_load(struct folio *folio)
 	 * range on the backing device, so scan the range rather than rejecting
 	 * it outright. The caller has pinned every slot, so zswap cannot start
 	 * a store or a writeback into the range while we look.
+	 *
+	 * A vswap batch is checked when the folio enters the swap cache, and
+	 * its backing cannot change after that.
 	 */
 	if (folio_test_large(folio)) {
-		if (WARN_ON_ONCE(zswap_is_present(swp,
+		if (WARN_ON_ONCE(!swap_is_vswap(si) &&
+				 zswap_is_present(swp,
 						  folio_nr_pages(folio)))) {
 			folio_unlock(folio);
 			return -EIO;
-- 
2.53.0-Meta