| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20221115182901.2755368-3-nphamcs@gmail.com>
Date: Tue, 15 Nov 2022 10:28:59 -0800
From: Nhat Pham <nphamcs@...il.com>
To: linux-mm@...ck.org, linux-kernel@...r.kernel.org
Cc: hannes@...xchg.org
Subject: [PATCH 2/4] workingset: refactor LRU refault to expose refault recency check
In preparation for computing recently evicted pages in cachestat,
refactor workingset_refault and lru_gen_refault to expose a helper
function that would test if an evicted page is recently evicted.
Signed-off-by: Nhat Pham <nphamcs@...il.com>
---
include/linux/swap.h | 1 +
mm/workingset.c | 141 +++++++++++++++++++++++++++++--------------
2 files changed, 98 insertions(+), 44 deletions(-)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index a18cf4b7c724..dae6f6f955eb 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -361,6 +361,7 @@ static inline void folio_set_swap_entry(struct folio *folio, swp_entry_t entry)
}
/* linux/mm/workingset.c */
+bool workingset_test_recent(void *shadow, bool file, bool *workingset);
void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages);
void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg);
void workingset_refault(struct folio *folio, void *shadow);
diff --git a/mm/workingset.c b/mm/workingset.c
index 79585d55c45d..51ed8c836467 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -244,6 +244,30 @@ static void *lru_gen_eviction(struct folio *folio)
return pack_shadow(mem_cgroup_id(memcg), pgdat, token, refs);
}
+/**
+ * Test if the folio is recently evicted.
+ *
+ * As a side effect, also populates the references with
+ * values unpacked from the shadow of the evicted folio.
+ */
+static bool lru_gen_test_recent(void *shadow, bool file, int *memcgid,
+ struct pglist_data **pgdat, unsigned long *token, bool *workingset)
+{
+ struct mem_cgroup *eviction_memcg;
+ struct lruvec *lruvec;
+ struct lru_gen_struct *lrugen;
+ unsigned long min_seq;
+
+ unpack_shadow(shadow, memcgid, pgdat, token, workingset);
+ eviction_memcg = mem_cgroup_from_id(*memcgid);
+
+ lruvec = mem_cgroup_lruvec(eviction_memcg, *pgdat);
+ lrugen = &lruvec->lrugen;
+
+ min_seq = READ_ONCE(lrugen->min_seq[file]);
+ return !((*token >> LRU_REFS_WIDTH) != (min_seq & (EVICTION_MASK >> LRU_REFS_WIDTH)));
+}
+
static void lru_gen_refault(struct folio *folio, void *shadow)
{
int hist, tier, refs;
@@ -258,23 +282,24 @@ static void lru_gen_refault(struct folio *folio, void *shadow)
int type = folio_is_file_lru(folio);
int delta = folio_nr_pages(folio);
- unpack_shadow(shadow, &memcg_id, &pgdat, &token, &workingset);
-
- if (pgdat != folio_pgdat(folio))
- return;
rcu_read_lock();
memcg = folio_memcg_rcu(folio);
+
+ if (!lru_gen_test_recent(shadow, type, &memcg_id, &pgdat, &token,
+ &workingset))
+ goto unlock;
+
if (memcg_id != mem_cgroup_id(memcg))
goto unlock;
+ if (pgdat != folio_pgdat(folio))
+ goto unlock;
+
lruvec = mem_cgroup_lruvec(memcg, pgdat);
lrugen = &lruvec->lrugen;
-
min_seq = READ_ONCE(lrugen->min_seq[type]);
- if ((token >> LRU_REFS_WIDTH) != (min_seq & (EVICTION_MASK >> LRU_REFS_WIDTH)))
- goto unlock;
hist = lru_hist_from_seq(min_seq);
/* see the comment in folio_lru_refs() */
@@ -306,6 +331,12 @@ static void *lru_gen_eviction(struct folio *folio)
return NULL;
}
+static bool lru_gen_test_recent(void *shadow, int type, int *memcgid,
+ struct pglist_data **pgdat, unsigned long *token, bool *workingset)
+{
+ return true;
+}
+
static void lru_gen_refault(struct folio *folio, void *shadow)
{
}
@@ -374,39 +405,31 @@ void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg)
}
/**
- * workingset_refault - Evaluate the refault of a previously evicted folio.
- * @folio: The freshly allocated replacement folio.
- * @shadow: Shadow entry of the evicted folio.
+ * Test if the folio is recently evicted by checking if
+ * refault distance of shadow exceeds workingset size.
*
- * Calculates and evaluates the refault distance of the previously
- * evicted folio in the context of the node and the memcg whose memory
- * pressure caused the eviction.
+ * As a side effect, populate workingset with the value
+ * unpacked from shadow.
*/
-void workingset_refault(struct folio *folio, void *shadow)
+bool workingset_test_recent(void *shadow, bool file, bool *workingset)
{
- bool file = folio_is_file_lru(folio);
struct mem_cgroup *eviction_memcg;
struct lruvec *eviction_lruvec;
unsigned long refault_distance;
unsigned long workingset_size;
- struct pglist_data *pgdat;
- struct mem_cgroup *memcg;
- unsigned long eviction;
- struct lruvec *lruvec;
unsigned long refault;
- bool workingset;
+
int memcgid;
- long nr;
+ struct pglist_data *pgdat;
+ unsigned long eviction;
- if (lru_gen_enabled()) {
- lru_gen_refault(folio, shadow);
- return;
- }
+ if (lru_gen_enabled())
+ return lru_gen_test_recent(shadow, file, &memcgid,
+ &pgdat, &eviction, workingset);
- unpack_shadow(shadow, &memcgid, &pgdat, &eviction, &workingset);
+ unpack_shadow(shadow, &memcgid, &pgdat, &eviction, workingset);
eviction <<= bucket_order;
- rcu_read_lock();
/*
* Look up the memcg associated with the stored ID. It might
* have been deleted since the folio's eviction.
@@ -425,7 +448,8 @@ void workingset_refault(struct folio *folio, void *shadow)
*/
eviction_memcg = mem_cgroup_from_id(memcgid);
if (!mem_cgroup_disabled() && !eviction_memcg)
- goto out;
+ return false;
+
eviction_lruvec = mem_cgroup_lruvec(eviction_memcg, pgdat);
refault = atomic_long_read(&eviction_lruvec->nonresident_age);
@@ -447,21 +471,6 @@ void workingset_refault(struct folio *folio, void *shadow)
*/
refault_distance = (refault - eviction) & EVICTION_MASK;
- /*
- * The activation decision for this folio is made at the level
- * where the eviction occurred, as that is where the LRU order
- * during folio reclaim is being determined.
- *
- * However, the cgroup that will own the folio is the one that
- * is actually experiencing the refault event.
- */
- nr = folio_nr_pages(folio);
- memcg = folio_memcg(folio);
- pgdat = folio_pgdat(folio);
- 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
@@ -483,8 +492,51 @@ void workingset_refault(struct folio *folio, void *shadow)
NR_INACTIVE_ANON);
}
}
- if (refault_distance > workingset_size)
+
+ return refault_distance <= workingset_size;
+}
+
+/**
+ * workingset_refault - Evaluate the refault of a previously evicted folio.
+ * @folio: The freshly allocated replacement folio.
+ * @shadow: Shadow entry of the evicted folio.
+ *
+ * Calculates and evaluates the refault distance of the previously
+ * evicted folio in the context of the node and the memcg whose memory
+ * pressure caused the eviction.
+ */
+void workingset_refault(struct folio *folio, void *shadow)
+{
+ bool file = folio_is_file_lru(folio);
+ struct pglist_data *pgdat;
+ struct mem_cgroup *memcg;
+ struct lruvec *lruvec;
+ bool workingset;
+ long nr;
+
+ if (lru_gen_enabled()) {
+ lru_gen_refault(folio, shadow);
+ return;
+ }
+
+ rcu_read_lock();
+
+ nr = folio_nr_pages(folio);
+ memcg = folio_memcg(folio);
+ pgdat = folio_pgdat(folio);
+ lruvec = mem_cgroup_lruvec(memcg, pgdat);
+
+ if (!workingset_test_recent(shadow, file, &workingset)) {
+ /*
+ * The activation decision for this folio is made at the level
+ * where the eviction occurred, as that is where the LRU order
+ * during folio reclaim is being determined.
+ *
+ * However, the cgroup that will own the folio is the one that
+ * is actually experiencing the refault event.
+ */
goto out;
+ }
folio_set_active(folio);
workingset_age_nonresident(lruvec, nr);
@@ -498,6 +550,7 @@ void workingset_refault(struct folio *folio, void *shadow)
mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + file, nr);
}
out:
+ mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file, nr);
rcu_read_unlock();
}
--
2.30.2
Powered by blists - more mailing lists