linux-kernel - [PATCH mm-unstable v1 2/6] mm/mglru: optimize deactivation

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

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20241202032823.2741019-3-yuzhao@google.com>
Date: Sun,  1 Dec 2024 20:28:19 -0700
From: Yu Zhao <yuzhao@...gle.com>
To: Andrew Morton <akpm@...ux-foundation.org>
Cc: linux-mm@...ck.org, linux-kernel@...r.kernel.org, 
	Yu Zhao <yuzhao@...gle.com>, Bharata B Rao <bharata@....com>, 
	Kalesh Singh <kaleshsingh@...gle.com>
Subject: [PATCH mm-unstable v1 2/6] mm/mglru: optimize deactivation

Do not shuffle a folio in the deactivation paths if it is already in
the oldest generation. This reduces the LRU lock contention.

Before this patch, the contention is reproducible by FIO, e.g.,

  fio -filename=/dev/nvme1n1p2 -direct=0 -thread -size=1024G \
      -rwmixwrite=30  --norandommap --randrepeat=0 -ioengine=sync \
      -bs=4k -numjobs=400 -runtime=25000 --time_based \
      -group_reporting -name=mglru

  98.96%--_raw_spin_lock_irqsave
          folio_lruvec_lock_irqsave
          |
           --98.78%--folio_batch_move_lru
               |
                --98.63%--deactivate_file_folio
                          mapping_try_invalidate
                          invalidate_mapping_pages
                          invalidate_bdev
                          blkdev_common_ioctl
                          blkdev_ioctl

After this patch, deactivate_file_folio() bails out early without
taking the LRU lock.

A side effect is that a folio can be left at the head of the oldest
generation, rather than the tail. If reclaim happens at the same time,
it cannot reclaim this folio immediately. Since there is no known
correlation between truncation and reclaim, this side effect is
considered insignificant.

Reported-by: Bharata B Rao <bharata@....com>
Closes: https://lore.kernel.org/CAOUHufawNerxqLm7L9Yywp3HJFiYVrYO26ePUb1jH-qxNGWzyA@mail.gmail.com/
Signed-off-by: Yu Zhao <yuzhao@...gle.com>
Tested-by: Kalesh Singh <kaleshsingh@...gle.com>
---
 mm/swap.c | 44 +++++++++++++++++++++++++++++++++++++-------
 1 file changed, 37 insertions(+), 7 deletions(-)

diff --git a/mm/swap.c b/mm/swap.c
index 3a01acfd5a89..15a94be8b0af 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -379,7 +379,8 @@ static void __lru_cache_activate_folio(struct folio *folio)
 }
 
 #ifdef CONFIG_LRU_GEN
-static void folio_inc_refs(struct folio *folio)
+
+static void lru_gen_inc_refs(struct folio *folio)
 {
 	unsigned long new_flags, old_flags = READ_ONCE(folio->flags);
 
@@ -406,10 +407,30 @@ static void folio_inc_refs(struct folio *folio)
 		new_flags |= old_flags & ~LRU_REFS_MASK;
 	} while (!try_cmpxchg(&folio->flags, &old_flags, new_flags));
 }
-#else
-static void folio_inc_refs(struct folio *folio)
+
+static bool lru_gen_clear_refs(struct folio *folio)
 {
+	int gen = folio_lru_gen(folio);
+	int type = folio_is_file_lru(folio);
+	struct lru_gen_folio *lrugen = &folio_lruvec(folio)->lrugen;
+
+	set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS, 0);
+
+	/* whether can do without shuffling under the LRU lock */
+	return gen == lru_gen_from_seq(READ_ONCE(lrugen->min_seq[type]));
 }
+
+#else /* !CONFIG_LRU_GEN */
+
+static void lru_gen_inc_refs(struct folio *folio)
+{
+}
+
+static bool lru_gen_clear_refs(struct folio *folio)
+{
+	return false;
+}
+
 #endif /* CONFIG_LRU_GEN */
 
 /**
@@ -428,7 +449,7 @@ static void folio_inc_refs(struct folio *folio)
 void folio_mark_accessed(struct folio *folio)
 {
 	if (lru_gen_enabled()) {
-		folio_inc_refs(folio);
+		lru_gen_inc_refs(folio);
 		return;
 	}
 
@@ -524,7 +545,7 @@ void folio_add_lru_vma(struct folio *folio, struct vm_area_struct *vma)
  */
 static void lru_deactivate_file(struct lruvec *lruvec, struct folio *folio)
 {
-	bool active = folio_test_active(folio);
+	bool active = folio_test_active(folio) || lru_gen_enabled();
 	long nr_pages = folio_nr_pages(folio);
 
 	if (folio_test_unevictable(folio))
@@ -589,7 +610,10 @@ static void lru_lazyfree(struct lruvec *lruvec, struct folio *folio)
 
 	lruvec_del_folio(lruvec, folio);
 	folio_clear_active(folio);
-	folio_clear_referenced(folio);
+	if (lru_gen_enabled())
+		lru_gen_clear_refs(folio);
+	else
+		folio_clear_referenced(folio);
 	/*
 	 * Lazyfree folios are clean anonymous folios.  They have
 	 * the swapbacked flag cleared, to distinguish them from normal
@@ -657,6 +681,9 @@ void deactivate_file_folio(struct folio *folio)
 	if (folio_test_unevictable(folio))
 		return;
 
+	if (lru_gen_enabled() && lru_gen_clear_refs(folio))
+		return;
+
 	folio_batch_add_and_move(folio, lru_deactivate_file, true);
 }
 
@@ -670,7 +697,10 @@ void deactivate_file_folio(struct folio *folio)
  */
 void folio_deactivate(struct folio *folio)
 {
-	if (folio_test_unevictable(folio) || !(folio_test_active(folio) || lru_gen_enabled()))
+	if (folio_test_unevictable(folio))
+		return;
+
+	if (lru_gen_enabled() ? lru_gen_clear_refs(folio) : !folio_test_active(folio))
 		return;
 
 	folio_batch_add_and_move(folio, lru_deactivate, true);
-- 
2.47.0.338.g60cca15819-goog