[Devel] [PATCH RHEL7 COMMIT] ms/mm: workingset: separate shadow unpacking and refault calculation

[Konstantin Khorenko]

The commit is pushed to "branch-rh7-3.10.0-957.5.1.vz7.84.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh7-3.10.0-957.5.1.vz7.84.2
------>
commit 94b50f7b7cb147330888e994e25173c0409c424c
Author: Johannes Weiner <hannes at cmpxchg.org>
Date:   Mon Mar 4 17:52:19 2019 +0300

    ms/mm: workingset: separate shadow unpacking and refault calculation
    
    Per-cgroup thrash detection will need to derive a live memcg from the
    eviction cookie, and doing that inside unpack_shadow() will get nasty
    with the reference handling spread over two functions.
    
    In preparation, make unpack_shadow() clearly about extracting static
    data, and let workingset_refault() do all the higher-level handling.
    
    Signed-off-by: Johannes Weiner <hannes at cmpxchg.org>
    Reviewed-by: Vladimir Davydov <vdavydov at virtuozzo.com>
    Cc: Michal Hocko <mhocko at suse.cz>
    Cc: David Rientjes <rientjes at google.com>
    Signed-off-by: Andrew Morton <akpm at linux-foundation.org>
    Signed-off-by: Linus Torvalds <torvalds at linux-foundation.org>
    
    https://pmc.acronis.com/browse/VSTOR-19037
    https://jira.sw.ru/browse/PSBM-91933
    
    (cherry picked from commit 162453bfbdf4c0f58cb3058aad9ad8cda1044cda)
    Signed-off-by: Andrey Ryabinin <aryabinin at virtuozzo.com>
---
 mm/workingset.c | 56 ++++++++++++++++++++++++++++----------------------------
 1 file changed, 28 insertions(+), 28 deletions(-)

diff --git a/mm/workingset.c b/mm/workingset.c
index 150223b6b161..22b66359d92d 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -165,13 +165,10 @@ static void *pack_shadow(unsigned long eviction, struct zone *zone)
 	return (void *)(eviction | RADIX_TREE_EXCEPTIONAL_ENTRY);
 }
 
-static void unpack_shadow(void *shadow,
-			  struct zone **zone,
-			  unsigned long *distance)
+static void unpack_shadow(void *shadow, struct zone **zonep,
+			  unsigned long *evictionp)
 {
 	unsigned long entry = (unsigned long)shadow;
-	unsigned long eviction;
-	unsigned long refault;
 	int zid, nid;
 
 	entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT;
@@ -179,29 +176,9 @@ static void unpack_shadow(void *shadow,
 	entry >>= ZONES_SHIFT;
 	nid = entry & ((1UL << NODES_SHIFT) - 1);
 	entry >>= NODES_SHIFT;
-	eviction = entry;
-
-	*zone = NODE_DATA(nid)->node_zones + zid;
 
-	refault = atomic_long_read(&(*zone)->inactive_age);
-
-	/*
-	 * The unsigned subtraction here gives an accurate distance
-	 * across inactive_age overflows in most cases.
-	 *
-	 * There is a special case: usually, shadow entries have a
-	 * short lifetime and are either refaulted or reclaimed along
-	 * with the inode before they get too old.  But it is not
-	 * impossible for the inactive_age to lap a shadow entry in
-	 * the field, which can then can result in a false small
-	 * refault distance, leading to a false activation should this
-	 * old entry actually refault again.  However, earlier kernels
-	 * used to deactivate unconditionally with *every* reclaim
-	 * invocation for the longest time, so the occasional
-	 * inappropriate activation leading to pressure on the active
-	 * list is not a problem.
-	 */
-	*distance = (refault - eviction) & EVICTION_MASK;
+	*zonep = NODE_DATA(nid)->node_zones + zid;
+	*evictionp = entry;
 }
 
 /**
@@ -233,9 +210,32 @@ void *workingset_eviction(struct address_space *mapping, struct page *page)
 bool workingset_refault(void *shadow)
 {
 	unsigned long refault_distance;
+	unsigned long eviction;
+	unsigned long refault;
 	struct zone *zone;
 
-	unpack_shadow(shadow, &zone, &refault_distance);
+	unpack_shadow(shadow, &zone, &eviction);
+
+	refault = atomic_long_read(&zone->inactive_age);
+
+	/*
+	 * The unsigned subtraction here gives an accurate distance
+	 * across inactive_age overflows in most cases.
+	 *
+	 * There is a special case: usually, shadow entries have a
+	 * short lifetime and are either refaulted or reclaimed along
+	 * with the inode before they get too old.  But it is not
+	 * impossible for the inactive_age to lap a shadow entry in
+	 * the field, which can then can result in a false small
+	 * refault distance, leading to a false activation should this
+	 * old entry actually refault again.  However, earlier kernels
+	 * used to deactivate unconditionally with *every* reclaim
+	 * invocation for the longest time, so the occasional
+	 * inappropriate activation leading to pressure on the active
+	 * list is not a problem.
+	 */
+	refault_distance = (refault - eviction) & EVICTION_MASK;
+
 	inc_zone_state(zone, WORKINGSET_REFAULT);
 
 	if (refault_distance <= zone_page_state(zone, NR_ACTIVE_FILE)) {