mm, swap: use offset of swap entry as key of swap cache

This patch is to improve the performance of swap cache operations when
the type of the swap device is not 0. Originally, the whole swap entry
value is used as the key of the swap cache, even though there is one
radix tree for each swap device. If the type of the swap device is not
0, the height of the radix tree of the swap cache will be increased
unnecessary, especially on 64bit architecture. For example, for a 1GB
swap device on the x86_64 architecture, the height of the radix tree of
the swap cache is 11. But if the offset of the swap entry is used as
the key of the swap cache, the height of the radix tree of the swap
cache is 4. The increased height causes unnecessary radix tree
descending and increased cache footprint.

This patch reduces the height of the radix tree of the swap cache via
using the offset of the swap entry instead of the whole swap entry value
as the key of the swap cache. In 32 processes sequential swap out test
case on a Xeon E5 v3 system with RAM disk as swap, the lock contention
for the spinlock of the swap cache is reduced from 20.15% to 12.19%,
when the type of the swap device is 1.

Use the whole swap entry as key,

perf-profile.calltrace.cycles-pp._raw_spin_lock_irq.__add_to_swap_cache.add_to_swap_cache.add_to_swap.shrink_page_list: 10.37,
perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.__remove_mapping.shrink_page_list.shrink_inactive_list.shrink_node_memcg: 9.78,

Use the swap offset as key,

perf-profile.calltrace.cycles-pp._raw_spin_lock_irq.__add_to_swap_cache.add_to_swap_cache.add_to_swap.shrink_page_list: 6.25,
perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.__remove_mapping.shrink_page_list.shrink_inactive_list.shrink_node_memcg: 5.94,

Link: http://lkml.kernel.org/r/[e-mail]
Signed-off-by: "Huang, Ying" <[e-mail]>
Cc: Johannes Weiner <[e-mail]>
Cc: Michal Hocko <[e-mail]>
Cc: Vladimir Davydov <[e-mail]>
Cc: "Kirill A. Shutemov" <[e-mail]>
Cc: Dave Hansen <[e-mail]>
Cc: Dan Williams <[e-mail]>
Cc: Joonsoo Kim <[e-mail]>
Cc: Hugh Dickins <[e-mail]>
Cc: Mel Gorman <[e-mail]>
Cc: Minchan Kim <[e-mail]>
Cc: Aaron Lu <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

include/linux/mm.h

···
 	return page->mapping;
 }
 
+extern pgoff_t __page_file_index(struct page *page);
+
 /*
  * Return the pagecache index of the passed page.  Regular pagecache pages
- * use ->index whereas swapcache pages use ->private
+ * use ->index whereas swapcache pages use swp_offset(->private)
  */
 static inline pgoff_t page_index(struct page *page)
 {
 	if (unlikely(PageSwapCache(page)))
-		return page_private(page);
+		return __page_file_index(page);
 	return page->index;
 }
-
-extern pgoff_t __page_file_index(struct page *page);
 
 /*
  * Return the file index of the page. Regular pagecache pages use ->index

mm/memcontrol.c

···
 	 * Because lookup_swap_cache() updates some statistics counter,
 	 * we call find_get_page() with swapper_space directly.
 	 */
-	page = find_get_page(swap_address_space(ent), ent.val);
+	page = find_get_page(swap_address_space(ent), swp_offset(ent));
 	if (do_memsw_account())
 		entry->val = ent.val;
 
···
 			swp_entry_t swp = radix_to_swp_entry(page);
 			if (do_memsw_account())
 				*entry = swp;
-			page = find_get_page(swap_address_space(swp), swp.val);
+			page = find_get_page(swap_address_space(swp),
+					     swp_offset(swp));
 		}
 	} else
 		page = find_get_page(mapping, pgoff);

mm/mincore.c

···
 		 */
 		if (radix_tree_exceptional_entry(page)) {
 			swp_entry_t swp = radix_to_swp_entry(page);
-			page = find_get_page(swap_address_space(swp), swp.val);
+			page = find_get_page(swap_address_space(swp),
+					     swp_offset(swp));
 		}
 	} else
 		page = find_get_page(mapping, pgoff);
···
 			} else {
 #ifdef CONFIG_SWAP
 				*vec = mincore_page(swap_address_space(entry),
-					entry.val);
+						    swp_offset(entry));
 #else
 				WARN_ON(1);
 				*vec = 1;

mm/swap_state.c

···
 	address_space = swap_address_space(entry);
 	spin_lock_irq(&address_space->tree_lock);
 	error = radix_tree_insert(&address_space->page_tree,
-					entry.val, page);
+				  swp_offset(entry), page);
 	if (likely(!error)) {
 		address_space->nrpages++;
 		__inc_node_page_state(page, NR_FILE_PAGES);
···
 
 	entry.val = page_private(page);
 	address_space = swap_address_space(entry);
-	radix_tree_delete(&address_space->page_tree, page_private(page));
+	radix_tree_delete(&address_space->page_tree, swp_offset(entry));
 	set_page_private(page, 0);
 	ClearPageSwapCache(page);
 	address_space->nrpages--;
···
 {
 	struct page *page;
 
-	page = find_get_page(swap_address_space(entry), entry.val);
+	page = find_get_page(swap_address_space(entry), swp_offset(entry));
 
 	if (page) {
 		INC_CACHE_INFO(find_success);
···
 		 * called after lookup_swap_cache() failed, re-calling
 		 * that would confuse statistics.
 		 */
-		found_page = find_get_page(swapper_space, entry.val);
+		found_page = find_get_page(swapper_space, swp_offset(entry));
 		if (found_page)
 			break;
 

mm/swapfile.c

···
 	struct page *page;
 	int ret = 0;
 
-	page = find_get_page(swap_address_space(entry), entry.val);
+	page = find_get_page(swap_address_space(entry), swp_offset(entry));
 	if (!page)
 		return 0;
 	/*
···
 	if (p) {
 		if (swap_entry_free(p, entry, 1) == SWAP_HAS_CACHE) {
 			page = find_get_page(swap_address_space(entry),
-						entry.val);
+					     swp_offset(entry));
 			if (page && !trylock_page(page)) {
 				put_page(page);
 				page = NULL;