linux-kernel - [RESEND][PATCH v2] mm: don't call lru draining in the nested lru_cache

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-next>] [day] [month] [year] [list]

Message-Id: <20211230193627.495145-1-minchan@kernel.org>
Date:   Thu, 30 Dec 2021 11:36:27 -0800
From:   Minchan Kim <minchan@...nel.org>
To:     Andrew Morton <akpm@...ux-foundation.org>
Cc:     Michal Hocko <mhocko@...e.com>,
        David Hildenbrand <david@...hat.com>,
        linux-mm <linux-mm@...ck.org>,
        LKML <linux-kernel@...r.kernel.org>,
        Suren Baghdasaryan <surenb@...gle.com>,
        John Dias <joaodias@...gle.com>,
        Minchan Kim <minchan@...nel.org>
Subject: [RESEND][PATCH v2] mm: don't call lru draining in the nested lru_cache_disable

lru_cache_disable involves IPIs to drain pagevec of each core,
which sometimes takes quite long time to complete depending
on cpu's business, which makes allocation too slow up to
sveral hundredth milliseconds. Furthermore, the repeated draining
in the alloc_contig_range makes thing worse considering caller
of alloc_contig_range usually tries multiple times in the loop.

This patch makes the lru_cache_disable aware of the fact the
pagevec was already disabled. With that, user of alloc_contig_range
can disable the lru cache in advance in their context during the
repeated trial so they can avoid the multiple costly draining
in cma allocation.

Signed-off-by: Minchan Kim <minchan@...nel.org>
---
 * from v1 - https://lore.kernel.org/lkml/20211206221006.946661-1-minchan@kernel.org/
   * fix lru_cache_disable race - akpm

 include/linux/swap.h | 14 ++------------
 mm/cma.c             |  5 +++++
 mm/swap.c            | 30 ++++++++++++++++++++++++++++--
 3 files changed, 35 insertions(+), 14 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index ba52f3a3478e..fe18e86a4f13 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -348,19 +348,9 @@ extern void lru_note_cost_page(struct page *);
 extern void lru_cache_add(struct page *);
 extern void mark_page_accessed(struct page *);
 
-extern atomic_t lru_disable_count;
-
-static inline bool lru_cache_disabled(void)
-{
-	return atomic_read(&lru_disable_count);
-}
-
-static inline void lru_cache_enable(void)
-{
-	atomic_dec(&lru_disable_count);
-}
-
+extern bool lru_cache_disabled(void);
 extern void lru_cache_disable(void);
+extern void lru_cache_enable(void);
 extern void lru_add_drain(void);
 extern void lru_add_drain_cpu(int cpu);
 extern void lru_add_drain_cpu_zone(struct zone *zone);
diff --git a/mm/cma.c b/mm/cma.c
index 995e15480937..60be555c5b95 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -30,6 +30,7 @@
 #include <linux/cma.h>
 #include <linux/highmem.h>
 #include <linux/io.h>
+#include <linux/swap.h>
 #include <linux/kmemleak.h>
 #include <trace/events/cma.h>
 
@@ -453,6 +454,8 @@ struct page *cma_alloc(struct cma *cma, unsigned long count,
 	if (bitmap_count > bitmap_maxno)
 		goto out;
 
+	lru_cache_disable();
+
 	for (;;) {
 		spin_lock_irq(&cma->lock);
 		bitmap_no = bitmap_find_next_zero_area_off(cma->bitmap,
@@ -492,6 +495,8 @@ struct page *cma_alloc(struct cma *cma, unsigned long count,
 		start = bitmap_no + mask + 1;
 	}
 
+	lru_cache_enable();
+
 	trace_cma_alloc_finish(cma->name, pfn, page, count, align);
 
 	/*
diff --git a/mm/swap.c b/mm/swap.c
index af3cad4e5378..5f89d7c9a54e 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -847,7 +847,17 @@ void lru_add_drain_all(void)
 }
 #endif /* CONFIG_SMP */
 
-atomic_t lru_disable_count = ATOMIC_INIT(0);
+static atomic_t lru_disable_count = ATOMIC_INIT(0);
+
+bool lru_cache_disabled(void)
+{
+	return atomic_read(&lru_disable_count) != 0;
+}
+
+void lru_cache_enable(void)
+{
+	atomic_dec(&lru_disable_count);
+}
 
 /*
  * lru_cache_disable() needs to be called before we start compiling
@@ -859,7 +869,21 @@ atomic_t lru_disable_count = ATOMIC_INIT(0);
  */
 void lru_cache_disable(void)
 {
-	atomic_inc(&lru_disable_count);
+	static DEFINE_MUTEX(lock);
+
+	/*
+	 * The lock gaurantees lru_cache is drained when the function
+	 * returned.
+	 */
+	mutex_lock(&lock);
+	/*
+	 * If someone is already disabled lru_cache, just return with
+	 * increasing the lru_disable_count.
+	 */
+	if (atomic_inc_not_zero(&lru_disable_count)) {
+		mutex_unlock(&lock);
+		return;
+	}
 #ifdef CONFIG_SMP
 	/*
 	 * lru_add_drain_all in the force mode will schedule draining on
@@ -873,6 +897,8 @@ void lru_cache_disable(void)
 #else
 	lru_add_and_bh_lrus_drain();
 #endif
+	atomic_inc(&lru_disable_count);
+	mutex_unlock(&lock);
 }
 
 /**
-- 
2.34.1.448.ga2b2bfdf31-goog