swap: add per-partition lock for swapfile

swap_lock is heavily contended when I test swap to 3 fast SSD (even
slightly slower than swap to 2 such SSD).  The main contention comes
from swap_info_get().  This patch tries to fix the gap with adding a new
per-partition lock.

Global data like nr_swapfiles, total_swap_pages, least_priority and
swap_list are still protected by swap_lock.

nr_swap_pages is an atomic now, it can be changed without swap_lock.  In
theory, it's possible get_swap_page() finds no swap pages but actually
there are free swap pages.  But sounds not a big problem.

Accessing partition specific data (like scan_swap_map and so on) is only
protected by swap_info_struct.lock.

Changing swap_info_struct.flags need hold swap_lock and
swap_info_struct.lock, because scan_scan_map() will check it.  read the
flags is ok with either the locks hold.

If both swap_lock and swap_info_struct.lock must be hold, we always hold
the former first to avoid deadlock.

swap_entry_free() can change swap_list.  To delete that code, we add a
new highest_priority_index.  Whenever get_swap_page() is called, we
check it.  If it's valid, we use it.

It's a pity get_swap_page() still holds swap_lock().  But in practice,
swap_lock() isn't heavily contended in my test with this patch (or I can
say there are other much more heavier bottlenecks like TLB flush).  And
BTW, looks get_swap_page() doesn't really need the lock.  We never free
swap_info[] and we check SWAP_WRITEOK flag.  The only risk without the
lock is we could swapout to some low priority swap, but we can quickly
recover after several rounds of swap, so sounds not a big deal to me.
But I'd prefer to fix this if it's a real problem.

"swap: make each swap partition have one address_space" improved the
swapout speed from 1.7G/s to 2G/s.  This patch further improves the
speed to 2.3G/s, so around 15% improvement.  It's a multi-process test,
so TLB flush isn't the biggest bottleneck before the patches.

[arnd@arndb.de: fix it for nommu]
[hughd@google.com: add missing unlock]
[minchan@kernel.org: get rid of lockdep whinge on sys_swapon]
Signed-off-by: Shaohua Li <shli@fusionio.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Seth Jennings <sjenning@linux.vnet.ibm.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Dan Magenheimer <dan.magenheimer@oracle.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/sparc/mm/init_32.c

@@ -57,7 +57,7 @@ void show_mem(unsigned int filter)
 	printk("Mem-info:\n");
 	show_free_areas(filter);
 	printk("Free swap:       %6ldkB\n",
-	       nr_swap_pages << (PAGE_SHIFT-10));
+	       get_nr_swap_pages() << (PAGE_SHIFT-10));
 	printk("%ld pages of RAM\n", totalram_pages);
 	printk("%ld free pages\n", nr_free_pages());
 }

arch/tile/mm/pgtable.c

@@ -61,7 +61,7 @@ void show_mem(unsigned int filter)
 	       global_page_state(NR_PAGETABLE),
 	       global_page_state(NR_BOUNCE),
 	       global_page_state(NR_FILE_PAGES),
-	       nr_swap_pages);
+	       get_nr_swap_pages());
 
 	for_each_zone(zone) {
 		unsigned long flags, order, total = 0, largest_order = -1;

include/linux/swap.h

@@ -202,6 +202,18 @@ struct swap_info_struct {
 	unsigned long *frontswap_map;	/* frontswap in-use, one bit per page */
 	atomic_t frontswap_pages;	/* frontswap pages in-use counter */
 #endif
+	spinlock_t lock;		/*
+					 * protect map scan related fields like
+					 * swap_map, lowest_bit, highest_bit,
+					 * inuse_pages, cluster_next,
+					 * cluster_nr, lowest_alloc and
+					 * highest_alloc. other fields are only
+					 * changed at swapon/swapoff, so are
+					 * protected by swap_lock. changing
+					 * flags need hold this lock and
+					 * swap_lock. If both locks need hold,
+					 * hold swap_lock first.
+					 */
 };
 
 struct swap_list_t {
@@ -209,9 +221,6 @@ struct swap_list_t {
 	int next;	/* swapfile to be used next */
 };
 
-/* Swap 50% full? Release swapcache more aggressively.. */
-#define vm_swap_full() (nr_swap_pages*2 < total_swap_pages)
-
 /* linux/mm/page_alloc.c */
 extern unsigned long totalram_pages;
 extern unsigned long totalreserve_pages;
@@ -347,8 +356,20 @@ extern struct page *swapin_readahead(swp_entry_t, gfp_t,
 			struct vm_area_struct *vma, unsigned long addr);
 
 /* linux/mm/swapfile.c */
-extern long nr_swap_pages;
+extern atomic_long_t nr_swap_pages;
 extern long total_swap_pages;
+
+/* Swap 50% full? Release swapcache more aggressively.. */
+static inline bool vm_swap_full(void)
+{
+	return atomic_long_read(&nr_swap_pages) * 2 < total_swap_pages;
+}
+
+static inline long get_nr_swap_pages(void)
+{
+	return atomic_long_read(&nr_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);
@@ -381,9 +402,10 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout)
 
 #else /* CONFIG_SWAP */
 
-#define nr_swap_pages				0L
+#define get_nr_swap_pages()			0L
 #define total_swap_pages			0L
 #define total_swapcache_pages()			0UL
+#define vm_swap_full()				0
 
 #define si_swapinfo(val) \
 	do { (val)->freeswap = (val)->totalswap = 0; } while (0)

mm/mmap.c

@@ -144,7 +144,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 		 */
 		free -= global_page_state(NR_SHMEM);
 
-		free += nr_swap_pages;
+		free += get_nr_swap_pages();
 
 		/*
 		 * Any slabs which are created with the

mm/nommu.c

@@ -1907,7 +1907,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 		 */
 		free -= global_page_state(NR_SHMEM);
 
-		free += nr_swap_pages;
+		free += get_nr_swap_pages();
 
 		/*
 		 * Any slabs which are created with the

mm/swap_state.c

@@ -69,7 +69,8 @@ void show_swap_cache_info(void)
 	printk("Swap cache stats: add %lu, delete %lu, find %lu/%lu\n",
 		swap_cache_info.add_total, swap_cache_info.del_total,
 		swap_cache_info.find_success, swap_cache_info.find_total);
-	printk("Free swap  = %ldkB\n", nr_swap_pages << (PAGE_SHIFT - 10));
+	printk("Free swap  = %ldkB\n",
+		get_nr_swap_pages() << (PAGE_SHIFT - 10));
 	printk("Total swap = %lukB\n", total_swap_pages << (PAGE_SHIFT - 10));
 }
 

mm/vmscan.c

@@ -1684,7 +1684,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 		force_scan = true;
 
 	/* If we have no swap space, do not bother scanning anon pages. */
-	if (!sc->may_swap || (nr_swap_pages <= 0)) {
+	if (!sc->may_swap || (get_nr_swap_pages() <= 0)) {
 		scan_balance = SCAN_FILE;
 		goto out;
 	}
@@ -1933,7 +1933,7 @@ static inline bool should_continue_reclaim(struct zone *zone,
 	 */
 	pages_for_compaction = (2UL << sc->order);
 	inactive_lru_pages = zone_page_state(zone, NR_INACTIVE_FILE);
-	if (nr_swap_pages > 0)
+	if (get_nr_swap_pages() > 0)
 		inactive_lru_pages += zone_page_state(zone, NR_INACTIVE_ANON);
 	if (sc->nr_reclaimed < pages_for_compaction &&
 			inactive_lru_pages > pages_for_compaction)
@@ -3085,7 +3085,7 @@ unsigned long global_reclaimable_pages(void)
 	nr = global_page_state(NR_ACTIVE_FILE) +
 	     global_page_state(NR_INACTIVE_FILE);
 
-	if (nr_swap_pages > 0)
+	if (get_nr_swap_pages() > 0)
 		nr += global_page_state(NR_ACTIVE_ANON) +
 		      global_page_state(NR_INACTIVE_ANON);
 
@@ -3099,7 +3099,7 @@ unsigned long zone_reclaimable_pages(struct zone *zone)
 	nr = zone_page_state(zone, NR_ACTIVE_FILE) +
 	     zone_page_state(zone, NR_INACTIVE_FILE);
 
-	if (nr_swap_pages > 0)
+	if (get_nr_swap_pages() > 0)
 		nr += zone_page_state(zone, NR_ACTIVE_ANON) +
 		      zone_page_state(zone, NR_INACTIVE_ANON);