mm/swap: skip readahead for unreferenced swap slots

We can avoid needlessly allocating page for swap slots that are not used by anyone. No pages have to be read in for these slots. Link: http://lkml.kernel.org/r/0784b3f20b9bd3aa5552219624cb78dc4ae710c9.1484082593.git.tim.c.chen@linux.intel.com Signed-off-by: Tim Chen <[email protected]> Signed-off-by: "Huang, Ying" <[email protected]> Cc: Aaron Lu <[email protected]> Cc: Andi Kleen <[email protected]> Cc: Andrea Arcangeli <[email protected]> Cc: Christian Borntraeger <[email protected]> Cc: Dave Hansen <[email protected]> Cc: Hillf Danton <[email protected]> Cc: Huang Ying <[email protected]> Cc: Hugh Dickins <[email protected]> Cc: Johannes Weiner <[email protected]> Cc: Jonathan Corbet <[email protected]> escreveu: Cc: Kirill A. Shutemov <[email protected]> Cc: Michal Hocko <[email protected]> Cc: Minchan Kim <[email protected]> Cc: Rik van Riel <[email protected]> Cc: Shaohua Li <[email protected]> Cc: Vladimir Davydov <[email protected]> Signed-off-by: Andrew Morton <[email protected]> Signed-off-by: Linus Torvalds <[email protected]>
olegshaldybin · Feb 23, 2017 · e8c26ab · e8c26ab
1 parent 4b3ef9d
commit e8c26ab
Show file tree

Hide file tree

Showing 3 changed files with 51 additions and 6 deletions.
diff --git a/include/linux/swap.h b/include/linux/swap.h
@@ -398,6 +398,7 @@ extern unsigned int count_swap_pages(int, int);
 extern sector_t map_swap_page(struct page *, struct block_device **);
 extern sector_t swapdev_block(int, pgoff_t);
 extern int page_swapcount(struct page *);
+extern int __swp_swapcount(swp_entry_t entry);
 extern int swp_swapcount(swp_entry_t entry);
 extern struct swap_info_struct *page_swap_info(struct page *);
 extern bool reuse_swap_page(struct page *, int *);
@@ -492,6 +493,11 @@ static inline int page_swapcount(struct page *page)
 	return 0;
 }
 
+static inline int __swp_swapcount(swp_entry_t entry)
+{
+	return 0;
+}
+
 static inline int swp_swapcount(swp_entry_t entry)
 {
 	return 0;

diff --git a/mm/swap_state.c b/mm/swap_state.c
@@ -323,6 +323,10 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		if (found_page)
 			break;
 
+		/* Just skip read ahead for unused swap slot */
+		if (!__swp_swapcount(entry))
+			return NULL;
+
 		/*
 		 * Get a new page to read into from swap.
 		 */

diff --git a/mm/swapfile.c b/mm/swapfile.c
@@ -798,7 +798,7 @@ swp_entry_t get_swap_page_of_type(int type)
 	return (swp_entry_t) {0};
 }
 
-static struct swap_info_struct *_swap_info_get(swp_entry_t entry)
+static struct swap_info_struct *__swap_info_get(swp_entry_t entry)
 {
 	struct swap_info_struct *p;
 	unsigned long offset, type;
@@ -814,13 +814,8 @@ static struct swap_info_struct *_swap_info_get(swp_entry_t entry)
 	offset = swp_offset(entry);
 	if (offset >= p->max)
 		goto bad_offset;
-	if (!p->swap_map[offset])
-		goto bad_free;
 	return p;
 
-bad_free:
-	pr_err("swap_info_get: %s%08lx\n", Unused_offset, entry.val);
-	goto out;
 bad_offset:
 	pr_err("swap_info_get: %s%08lx\n", Bad_offset, entry.val);
 	goto out;
@@ -833,6 +828,24 @@ static struct swap_info_struct *_swap_info_get(swp_entry_t entry)
 	return NULL;
 }
 
+static struct swap_info_struct *_swap_info_get(swp_entry_t entry)
+{
+	struct swap_info_struct *p;
+
+	p = __swap_info_get(entry);
+	if (!p)
+		goto out;
+	if (!p->swap_map[swp_offset(entry)])
+		goto bad_free;
+	return p;
+
+bad_free:
+	pr_err("swap_info_get: %s%08lx\n", Unused_offset, entry.val);
+	goto out;
+out:
+	return NULL;
+}
+
 static struct swap_info_struct *swap_info_get(swp_entry_t entry)
 {
 	struct swap_info_struct *p;
@@ -986,6 +999,28 @@ int page_swapcount(struct page *page)
 	return count;
 }
 
+/*
+ * How many references to @entry are currently swapped out?
+ * This does not give an exact answer when swap count is continued,
+ * but does include the high COUNT_CONTINUED flag to allow for that.
+ */
+int __swp_swapcount(swp_entry_t entry)
+{
+	int count = 0;
+	pgoff_t offset;
+	struct swap_info_struct *si;
+	struct swap_cluster_info *ci;
+
+	si = __swap_info_get(entry);
+	if (si) {
+		offset = swp_offset(entry);
+		ci = lock_cluster_or_swap_info(si, offset);
+		count = swap_count(si->swap_map[offset]);
+		unlock_cluster_or_swap_info(si, ci);
+	}
+	return count;
+}
+
 /*
  * How many references to @entry are currently swapped out?
  * This considers COUNT_CONTINUED so it returns exact answer.