[PATCH v3 05/11] mm, swap: enable THP swapin for vswap entries

[Nhat Pham]

Swap a large folio back in as a unit when its vswap entries share a
THP-amenable backing (a contiguous physical run, or all zero-filled),
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     | 12 ++++++++----
 mm/swap_state.c | 17 +++++++++++++----
 mm/vswap.h      |  7 +++++++
 mm/zswap.c      | 18 ++++++++++++------
 4 files changed, 40 insertions(+), 14 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index ba84565605a1..a1e106a5c5e6 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4815,11 +4815,15 @@ static unsigned long thp_swapin_suitable_orders(struct vm_fault *vmf)
 	entry = softleaf_from_pte(vmf->orig_pte);
 
 	/*
-	 * THP swapin for vswap is not supported yet. Also, a large swapped
-	 * out folio could be partially or fully in zswap, which we lack
-	 * handling for. In both cases, fall back to order-0 swapin.
+	 * A large swapped out folio could be partially or fully in zswap.
+	 * For vswap entries the THP-amenability of the backing is checked
+	 * later under the cluster lock in __swap_cache_add_check, which
+	 * rejects ZSWAP and mixed batches via -EBUSY and triggers
+	 * order-fallback. For non-vswap entries we still need the
+	 * zswap_never_enabled() bail: zswap_load rejects large folios with
+	 * -EINVAL, which would SIGBUS the fault.
 	 */
-	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 c61bb3eef62a..479814d19f50 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -173,6 +173,9 @@ 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);
 
@@ -201,11 +204,17 @@ static int __swap_cache_add_check(struct swap_cluster_info *ci,
 		return 0;
 
 	/*
-	 * THP swapin for vswap is not supported yet; reject the 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/vswap.h b/mm/vswap.h
index 239b47b577d5..a921620f08be 100644
--- a/mm/vswap.h
+++ b/mm/vswap.h
@@ -378,6 +378,13 @@ static inline struct zswap_entry *vswap_zswap_load(swp_entry_t entry)
 static inline void folio_release_vswap_backing(struct folio *folio) {}
 static inline void folio_release_non_phys_swap_backing(struct folio *folio) {}
 
+static inline int __vswap_check_backing(struct swap_cluster_info_dynamic *ci_dyn,
+					unsigned int voff, int nr,
+					enum vswap_backing_type *typep)
+{
+	return 0;
+}
+
 static inline int vswap_cluster_alloc_vtable(struct swap_cluster_info_dynamic *ci_dyn)
 {
 	return 0;
diff --git a/mm/zswap.c b/mm/zswap.c
index d0c6ce2aa092..5dc338188a29 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -1630,13 +1630,19 @@ int zswap_load(struct folio *folio)
 		return -ENOENT;
 
 	/*
-	 * 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.
+	 * zswap_load() does not support large folios. For non-vswap
+	 * entries this is unexpected on the swapin path: WARN and
+	 * sigbus. For vswap entries __swap_cache_add_check() has already
+	 * filtered out ZSWAP-backed THPs under the cluster lock, so the
+	 * large folio here is zero- or phys-backed; return -ENOENT so the
+	 * phys/zero IO path handles it.
 	 */
-	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