mm, swap: remove swap slot cache

Slot cache is no longer needed now, removing it and all related code.

- vm-scalability with: `usemem --init-time -O -y -x -R -31 1G`,
12G memory cgroup using simulated pmem as SWAP (32G pmem, 32 CPUs),
16 test runs for each case, measuring the total throughput:

                      Before (KB/s) (stdev)  After (KB/s) (stdev)
Random (4K):          424907.60 (24410.78)   414745.92  (34554.78)
Random (64K):         163308.82 (11635.72)   167314.50  (18434.99)
Sequential (4K, !-R): 6150056.79 (103205.90) 6321469.06 (115878.16)

The performance changes are below noise level.

- Build linux kernel with make -j96, using 4K folio with 1.5G memory
cgroup limit and 64K folio with 2G memory cgroup limit, on top of tmpfs,
12 test runs, measuring the system time:

                  Before (s) (stdev)  After (s) (stdev)
make -j96 (4K):   6445.69 (61.95)     6408.80 (69.46)
make -j96 (64K):  6841.71 (409.04)    6437.99 (435.55)

Similar to above, 64k mTHP case showed a slight improvement.

Link: https://lkml.kernel.org/r/20250313165935.63303-7-ryncsn@gmail.com
Signed-off-by: Kairui Song <kasong@tencent.com>
Reviewed-by: Baoquan He <bhe@redhat.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <v-songbaohua@oppo.com>
Cc: Chris Li <chrisl@kernel.org>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: Matthew Wilcow (Oracle) <willy@infradead.org>
Cc: Nhat Pham <nphamcs@gmail.com>
Cc: Yosry Ahmed <yosryahmed@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Author: ryncsn

include/linux/swap.h

@@ -465,7 +465,6 @@ void free_pages_and_swap_cache(struct encoded_page **, int);
 extern atomic_long_t nr_swap_pages;
 extern long total_swap_pages;
 extern atomic_t nr_rotate_swap;
-extern bool has_usable_swap(void);
 
 /* Swap 50% full? Release swapcache more aggressively.. */
 static inline bool vm_swap_full(void)
@@ -483,13 +482,11 @@ swp_entry_t folio_alloc_swap(struct folio *folio);
 bool folio_free_swap(struct folio *folio);
 void put_swap_folio(struct folio *folio, swp_entry_t entry);
 extern swp_entry_t get_swap_page_of_type(int);
-extern int get_swap_pages(int n, swp_entry_t swp_entries[], int order);
 extern int add_swap_count_continuation(swp_entry_t, gfp_t);
 extern void swap_shmem_alloc(swp_entry_t, int);
 extern int swap_duplicate(swp_entry_t);
 extern int swapcache_prepare(swp_entry_t entry, int nr);
 extern void swap_free_nr(swp_entry_t entry, int nr_pages);
-extern void swapcache_free_entries(swp_entry_t *entries, int n);
 extern void free_swap_and_cache_nr(swp_entry_t entry, int nr);
 int swap_type_of(dev_t device, sector_t offset);
 int find_first_swap(dev_t *device);

include/linux/swap_slots.h

@@ -75,7 +75,7 @@ ifdef CONFIG_MMU
 	obj-$(CONFIG_ADVISE_SYSCALLS)	+= madvise.o
 endif
 
-obj-$(CONFIG_SWAP)	+= page_io.o swap_state.o swapfile.o swap_slots.o
+obj-$(CONFIG_SWAP)	+= page_io.o swap_state.o swapfile.o
 obj-$(CONFIG_ZSWAP)	+= zswap.o
 obj-$(CONFIG_HAS_DMA)	+= dmapool.o
 obj-$(CONFIG_HUGETLBFS)	+= hugetlb.o

mm/Makefile

@@ -20,7 +20,6 @@
 #include <linux/blkdev.h>
 #include <linux/migrate.h>
 #include <linux/vmalloc.h>
-#include <linux/swap_slots.h>
 #include <linux/huge_mm.h>
 #include <linux/shmem_fs.h>
 #include "internal.h"
@@ -447,13 +446,8 @@ struct folio *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 
 		/*
 		 * Just skip read ahead for unused swap slot.
-		 * During swap_off when swap_slot_cache is disabled,
-		 * we have to handle the race between putting
-		 * swap entry in swap cache and marking swap slot
-		 * as SWAP_HAS_CACHE.  That's done in later part of code or
-		 * else swap_off will be aborted if we return NULL.
 		 */
-		if (!swap_entry_swapped(si, entry) && swap_slot_cache_enabled)
+		if (!swap_entry_swapped(si, entry))
 			goto put_and_return;
 
 		/*