f2fs: Provide a splice-read wrapper

[linux-block.git] / mm / workingset.c

diff --git a/mm/workingset.c b/mm/workingset.c
index 00c6f4d9d9be5ae8a09a85c87bce47440b1a0a76..817758951886b81ee04a1bed330e3b1c5f7d6d9c 100644 (file)
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -111,9 +111,20 @@
  *
  *   NR_inactive + (R - E) <= NR_inactive + NR_active
  *
- * which can be further simplified to
+ * If we have swap we should consider about NR_inactive_anon and
+ * NR_active_anon, so for page cache and anonymous respectively:
  *
- *   (R - E) <= NR_active
+ *   NR_inactive_file + (R - E) <= NR_inactive_file + NR_active_file
+ *   + NR_inactive_anon + NR_active_anon
+ *
+ *   NR_inactive_anon + (R - E) <= NR_inactive_anon + NR_active_anon
+ *   + NR_inactive_file + NR_active_file
+ *
+ * Which can be further simplified to:
+ *
+ *   (R - E) <= NR_active_file + NR_inactive_anon + NR_active_anon
+ *
+ *   (R - E) <= NR_active_anon + NR_inactive_file + NR_active_file
  *
  * Put into words, the refault distance (out-of-cache) can be seen as
  * a deficit in inactive list space (in-cache).  If the inactive list
@@ -130,14 +141,14 @@
  * are no longer in active use.
  *
  * So when a refault distance of (R - E) is observed and there are at
- * least (R - E) active pages, the refaulting page is activated
- * optimistically in the hope that (R - E) active pages are actually
+ * least (R - E) pages in the userspace workingset, the refaulting page
+ * is activated optimistically in the hope that (R - E) pages are actually
  * used less frequently than the refaulting page - or even not used at
  * all anymore.
  *
  * That means if inactive cache is refaulting with a suitable refault
  * distance, we assume the cache workingset is transitioning and put
- * pressure on the current active list.
+ * pressure on the current workingset.
  *
  * If this is wrong and demotion kicks in, the pages which are truly
  * used more frequently will be reactivated while the less frequently
@@ -406,6 +417,9 @@ void workingset_refault(struct folio *folio, void *shadow)
        unpack_shadow(shadow, &memcgid, &pgdat, &eviction, &workingset);
        eviction <<= bucket_order;
 
+       /* Flush stats (and potentially sleep) before holding RCU read lock */
+       mem_cgroup_flush_stats_ratelimited();
+
        rcu_read_lock();
        /*
         * Look up the memcg associated with the stored ID. It might
@@ -461,14 +475,12 @@ void workingset_refault(struct folio *folio, void *shadow)
        lruvec = mem_cgroup_lruvec(memcg, pgdat);
 
        mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file, nr);
-
-       mem_cgroup_flush_stats_delayed();
        /*
         * Compare the distance to the existing workingset size. We
         * don't activate pages that couldn't stay resident even if
         * all the memory was available to the workingset. Whether
         * workingset competition needs to consider anon or not depends
-        * on having swap.
+        * on having free swap space.
         */
        workingset_size = lruvec_page_state(eviction_lruvec, NR_ACTIVE_FILE);
        if (!file) {