mm: modify swap_map and add SWAP_HAS_CACHE flag

This is a part of the patches for fixing memcg's swap accountinf leak.
But, IMHO, not a bad patch even if no memcg.

There are 2 kinds of references to swap.
 - reference from swap entry
 - reference from swap cache

Then,

 - If there is swap cache && swap's refcnt is 1, there is only swap cache.
  (*) swapcount(entry) == 1 && find_get_page(swapper_space, entry) != NULL

This counting logic have worked well for a long time.  But considering
that we cannot know there is a _real_ reference or not by swap_map[],
current usage of counter is not very good.

This patch adds a flag SWAP_HAS_CACHE and recored information that a swap
entry has a cache or not.  This will remove -1 magic used in swapfile.c
and be a help to avoid unnecessary find_get_page().

Signed-off-by: KAMEZAWA Hiroyuki <[email protected]>
Tested-by: Daisuke Nishimura <[email protected]>
Cc: Balbir Singh <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Li Zefan <[email protected]>
Cc: Dhaval Giani <[email protected]>
Cc: YAMAMOTO Takashi <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

include/linux/swap.h

@@ -129,9 +129,10 @@ enum {
 
 #define SWAP_CLUSTER_MAX 32
 
-#define SWAP_MAP_MAX	0x7fff
-#define SWAP_MAP_BAD	0x8000
-
+#define SWAP_MAP_MAX	0x7ffe
+#define SWAP_MAP_BAD	0x7fff
+#define SWAP_HAS_CACHE  0x8000		/* There is a swap cache of entry. */
+#define SWAP_COUNT_MASK (~SWAP_HAS_CACHE)
 /*
  * The in-memory structure used to track swap areas.
  */
@@ -281,7 +282,7 @@ extern long total_swap_pages;
 extern void si_swapinfo(struct sysinfo *);
 extern swp_entry_t get_swap_page(void);
 extern swp_entry_t get_swap_page_of_type(int);
-extern int swap_duplicate(swp_entry_t);
+extern void swap_duplicate(swp_entry_t);
 extern int swapcache_prepare(swp_entry_t);
 extern int valid_swaphandles(swp_entry_t, unsigned long *);
 extern void swap_free(swp_entry_t);
@@ -353,9 +354,12 @@ static inline void show_swap_cache_info(void)
 }
 
 #define free_swap_and_cache(swp)	is_migration_entry(swp)
-#define swap_duplicate(swp)		is_migration_entry(swp)
 #define swapcache_prepare(swp)		is_migration_entry(swp)
 
+static inline void swap_duplicate(swp_entry_t swp)
+{
+}
+
 static inline void swap_free(swp_entry_t swp)
 {
 }

mm/swap_state.c

@@ -292,7 +292,10 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		/*
 		 * Swap entry may have been freed since our caller observed it.
 		 */
-		if (!swapcache_prepare(entry))
+		err = swapcache_prepare(entry);
+		if (err == -EEXIST) /* seems racy */
+			continue;
+		if (err)           /* swp entry is obsolete ? */
 			break;
 
 		/*