[PATCH v2 1/3] mm, swap: make SWAPFILE_CLUSTER runtime

[Ritesh Harjani (IBM)]

On PowerPC Book3S64, MMU is selected at runtime, so macros like
PMD_SHIFT are effectively runtime variables in the Book3S64 code. THP
swap code uses these macros to size some of its array data structures
based on PMD_ORDER e.g. SWAPFILE_CLUSTER macro is used for this very
purpose.
Hence this patch initializes SWAPFILE_CLUSTER at runtime and also
modifies swap_table and swap_memcg_table which were earlier using this
macro for defining the number of table entries.

Signed-off-by: Ritesh Harjani (IBM) <ritesh.list@xxxxxxxxx>
---
 mm/swap.h       |  5 +++--
 mm/swap_table.h |  6 ++----
 mm/swapfile.c   | 27 ++++++++++++++++++++++-----
 3 files changed, 27 insertions(+), 11 deletions(-)

diff --git a/mm/swap.h b/mm/swap.h
index 77d2d14eda42..956879a69ddd 100644
--- a/mm/swap.h
+++ b/mm/swap.h
@@ -26,11 +26,12 @@ extern int page_cluster;
 #define SWAP_TABLE_HAS_ZEROFLAG		((BITS_PER_LONG - SWAP_CACHE_PFN_MARK_BITS - \
 					  SWAP_CACHE_PFN_BITS) > SWAP_COUNT_MIN_BITS)
 
+extern unsigned int swap_slots_in_cluster __read_mostly;
+#define SWAPFILE_CLUSTER	swap_slots_in_cluster
+
 #ifdef CONFIG_THP_SWAP
-#define SWAPFILE_CLUSTER	HPAGE_PMD_NR
 #define swap_entry_order(order)	(order)
 #else
-#define SWAPFILE_CLUSTER	256
 #define swap_entry_order(order)	0
 #endif
 
diff --git a/mm/swap_table.h b/mm/swap_table.h
index e6613e62f8d0..90e2a7852300 100644
--- a/mm/swap_table.h
+++ b/mm/swap_table.h
@@ -8,16 +8,14 @@
 
 /* A typical flat array in each cluster as swap table */
 struct swap_table {
-	atomic_long_t entries[SWAPFILE_CLUSTER];
+	DECLARE_FLEX_ARRAY(atomic_long_t, entries);
 };
 
 /* For storing memcg private id */
 struct swap_memcg_table {
-	unsigned short id[SWAPFILE_CLUSTER];
+	DECLARE_FLEX_ARRAY(unsigned short, id);
 };
 
-#define SWP_TABLE_USE_PAGE (sizeof(struct swap_table) == PAGE_SIZE)
-
 /*
  * A swap table entry represents the status of a swap slot on a swap
  * (physical or virtual) device. The swap table in each cluster is a
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 78b49b0658ad..016a5aa0cb93 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -129,6 +129,17 @@ static DEFINE_PER_CPU(struct percpu_swap_cluster, percpu_swap_cluster) = {
 	.lock = INIT_LOCAL_LOCK(),
 };
 
+unsigned int swap_slots_in_cluster __read_mostly;
+bool swap_table_use_page __read_mostly;
+
+static unsigned int generic_swap_slots_in_clusters(void)
+{
+	if (IS_ENABLED(CONFIG_THP_SWAP))
+		return HPAGE_PMD_NR;
+	else
+		return 256;
+}
+
 /* May return NULL on invalid type, caller must check for NULL return */
 static struct swap_info_struct *swap_type_to_info(int type)
 {
@@ -437,7 +448,7 @@ static void swap_cluster_free_table(struct swap_cluster_info *ci)
 		return;
 
 	rcu_assign_pointer(ci->table, NULL);
-	if (!SWP_TABLE_USE_PAGE) {
+	if (!swap_table_use_page) {
 		kmem_cache_free(swap_table_cachep, table);
 		return;
 	}
@@ -456,7 +467,7 @@ static int swap_cluster_alloc_table(struct swap_cluster_info *ci, gfp_t gfp)
 	if (rcu_access_pointer(ci->table))
 		return 0;
 
-	if (SWP_TABLE_USE_PAGE) {
+	if (swap_table_use_page) {
 		folio = folio_alloc(gfp | __GFP_ZERO, 0);
 		if (folio)
 			table = folio_address(folio);
@@ -471,7 +482,8 @@ static int swap_cluster_alloc_table(struct swap_cluster_info *ci, gfp_t gfp)
 #ifdef CONFIG_MEMCG
 	if (!mem_cgroup_disabled()) {
 		VM_WARN_ON_ONCE(ci->memcg_table);
-		ci->memcg_table = kzalloc_obj(*ci->memcg_table, gfp);
+		ci->memcg_table = kzalloc_flex(*ci->memcg_table, id,
+					       SWAPFILE_CLUSTER, gfp);
 		if (!ci->memcg_table) {
 			swap_cluster_free_table(ci);
 			return -ENOMEM;
@@ -3912,14 +3924,19 @@ static int __init swapfile_init(void)
 {
 	swapfile_maximum_size = arch_max_swapfile_size();
 
+	swap_slots_in_cluster = generic_swap_slots_in_clusters();
+	swap_table_use_page =
+		(swap_slots_in_cluster * sizeof(atomic_long_t) == PAGE_SIZE);
+
 	/*
 	 * Once a cluster is freed, it's swap table content is read
 	 * only, and all swap cache readers (swap_cache_*) verifies
 	 * the content before use. So it's safe to use RCU slab here.
 	 */
-	if (!SWP_TABLE_USE_PAGE)
+	if (!swap_table_use_page)
 		swap_table_cachep = kmem_cache_create("swap_table",
-				    sizeof(struct swap_table),
+				    struct_size_t(struct swap_table, entries,
+					    SWAPFILE_CLUSTER),
 				    0, SLAB_PANIC | SLAB_TYPESAFE_BY_RCU, NULL);
 
 #ifdef CONFIG_MIGRATION
-- 
2.39.5