All of lore.kernel.org
 help / color / mirror / Atom feed
From: Nhat Pham <nphamcs@gmail.com>
To: akpm@linux-foundation.org
Cc: hannes@cmpxchg.org, linux-mm@kvack.org,
	linux-kernel@vger.kernel.org, bfoster@redhat.com,
	willy@infradead.org, linux-api@vger.kernel.org,
	kernel-team@meta.com
Subject: [PATCH v13 1/3] workingset: refactor LRU refault to expose refault recency check
Date: Tue,  2 May 2023 18:36:06 -0700	[thread overview]
Message-ID: <20230503013608.2431726-2-nphamcs@gmail.com> (raw)
In-Reply-To: <20230503013608.2431726-1-nphamcs@gmail.com>

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@gmail.com>
---
 include/linux/swap.h |   1 +
 mm/workingset.c      | 150 +++++++++++++++++++++++++++++--------------
 2 files changed, 103 insertions(+), 48 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 3c69cb653cb9..b2128df5edea 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -368,6 +368,7 @@ 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 817758951886..d81f9dafc9f1 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -255,6 +255,29 @@ static void *lru_gen_eviction(struct folio *folio)
 	return pack_shadow(mem_cgroup_id(memcg), pgdat, token, refs);
 }
 
+/*
+ * Tests if the shadow entry is for a folio that was recently evicted.
+ * Fills in @memcgid, @pglist_data, @token, @workingset with the values
+ * unpacked from shadow.
+ */
+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_folio *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;
@@ -269,23 +292,22 @@ 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();
 
+	if (!lru_gen_test_recent(shadow, type, &memcg_id, &pgdat, &token,
+			&workingset))
+		goto unlock;
+
 	memcg = folio_memcg_rcu(folio);
 	if (memcg_id != mem_cgroup_id(memcg))
 		goto unlock;
 
+	if (pgdat != folio_pgdat(folio))
+		return;
+
 	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() */
@@ -317,6 +339,12 @@ static void *lru_gen_eviction(struct folio *folio)
 	return NULL;
 }
 
+static bool lru_gen_test_recent(void *shadow, bool file, int *memcgid,
+		struct pglist_data **pgdat, unsigned long *token, bool *workingset)
+{
+	return false;
+}
+
 static void lru_gen_refault(struct folio *folio, void *shadow)
 {
 }
@@ -385,42 +413,34 @@ 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.
- *
- * 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.
+ * workingset_test_recent - tests if the shadow entry is for a folio that was
+ * recently evicted. Also fills in @workingset with the value unpacked from
+ * shadow.
+ * @shadow: the shadow entry to be tested.
+ * @file: whether the corresponding folio is from the file lru.
+ * @workingset: where the workingset value unpacked from shadow should
+ * be stored.
+ *
+ * Return: true if the shadow is for a recently evicted folio; false otherwise.
  */
-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;
 
-	/* 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
 	 * have been deleted since the folio's eviction.
@@ -439,7 +459,8 @@ 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);
 
@@ -461,20 +482,6 @@ 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);
 	/*
 	 * Compare the distance to the existing workingset size. We
 	 * don't activate pages that couldn't stay resident even if
@@ -495,7 +502,54 @@ 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;
+	}
+
+	/* Flush stats (and potentially sleep) before holding RCU read lock */
+	mem_cgroup_flush_stats_ratelimited();
+
+	rcu_read_lock();
+
+	/*
+	 * 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);
+
+	if (!workingset_test_recent(shadow, file, &workingset))
 		goto out;
 
 	folio_set_active(folio);
-- 
2.34.1

  reply	other threads:[~2023-05-03  1:36 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-05-03  1:36 [PATCH v13 0/3] cachestat: a new syscall for page cache state of files Nhat Pham
2023-05-03  1:36 ` Nhat Pham [this message]
2023-05-03 14:31   ` [PATCH v13 1/3] workingset: refactor LRU refault to expose refault recency check Johannes Weiner
2023-05-03  1:36 ` [PATCH v13 2/3] cachestat: implement cachestat syscall Nhat Pham
2023-05-03 15:04   ` Johannes Weiner
2023-05-04  2:25     ` Nhat Pham
2023-05-04 17:26   ` Geert Uytterhoeven
2023-05-04 18:06     ` Nhat Pham
2023-05-05 20:34     ` Andrew Morton
2023-05-06 17:35       ` Arnd Bergmann
2023-05-10 23:20         ` Nhat Pham
2023-05-03  1:36 ` [PATCH v13 3/3] selftests: Add selftests for cachestat Nhat Pham
2023-05-03 15:22   ` Johannes Weiner
2023-05-11  3:21   ` Michael Ellerman
2023-05-11  3:21     ` Michael Ellerman
2023-05-11 19:33     ` Nhat Pham
2023-05-11 19:33       ` Nhat Pham

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20230503013608.2431726-2-nphamcs@gmail.com \
    --to=nphamcs@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=bfoster@redhat.com \
    --cc=hannes@cmpxchg.org \
    --cc=kernel-team@meta.com \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=willy@infradead.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.