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 <tim.c.chen@linux.intel.com>
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Cc: Aaron Lu <aaron.lu@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net> escreveu:
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Shaohua Li <shli@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 45 insertions, 6 deletions

diff --git a/mm/swap_state.c b/mm/swap_state.c
index 3863acd6189c..3d76d80c07d6 100644
--- 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
index 66e95eb73040..7e888de35c41 100644
--- 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 @@ out:
 	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;
@@ -988,6 +1001,28 @@ int page_swapcount(struct page *page)
 
 /*
  * 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.
  */
 int swp_swapcount(swp_entry_t entry)