linux-kernel - [PATCH 1/6] mm/swap: Introduce lru_cpu_needs

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: <20210921161323.607817-2-nsaenzju@redhat.com>
Date:   Tue, 21 Sep 2021 18:13:19 +0200
From:   Nicolas Saenz Julienne <nsaenzju@...hat.com>
To:     akpm@...ux-foundation.org, frederic@...nel.org
Cc:     linux-kernel@...r.kernel.org, linux-mm@...ck.org,
        tglx@...utronix.de, cl@...ux.com, peterz@...radead.org,
        juri.lelli@...hat.com, mingo@...hat.com, mtosatti@...hat.com,
        nilal@...hat.com, mgorman@...e.de, ppandit@...hat.com,
        williams@...hat.com, bigeasy@...utronix.de,
        anna-maria@...utronix.de, linux-rt-users@...r.kernel.org,
        Nicolas Saenz Julienne <nsaenzju@...hat.com>
Subject: [PATCH 1/6] mm/swap: Introduce lru_cpu_needs_drain()

Upcoming patches will need to check whether a CPU needs to drain its LRU
pagevecs on multiple locations. So move the check into its own function.

Signed-off-by: Nicolas Saenz Julienne <nsaenzju@...hat.com>
---
 mm/swap.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/mm/swap.c b/mm/swap.c
index 04b678342c02..e7f9e4018ccf 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -726,6 +726,17 @@ static void lru_add_drain_per_cpu(struct work_struct *dummy)
 	lru_add_drain();
 }
 
+static bool lru_cpu_needs_drain(int cpu)
+{
+	return pagevec_count(&per_cpu(lru_pvecs.lru_add, cpu)) ||
+	       data_race(pagevec_count(&per_cpu(lru_rotate.pvec, cpu))) ||
+	       pagevec_count(&per_cpu(lru_pvecs.lru_deactivate_file, cpu)) ||
+	       pagevec_count(&per_cpu(lru_pvecs.lru_deactivate, cpu)) ||
+	       pagevec_count(&per_cpu(lru_pvecs.lru_lazyfree, cpu)) ||
+	       need_activate_page_drain(cpu) ||
+	       has_bh_in_lru(cpu, NULL);
+}
+
 /*
  * Doesn't need any cpu hotplug locking because we do rely on per-cpu
  * kworkers being shut down before our page_alloc_cpu_dead callback is
@@ -808,14 +819,7 @@ inline void __lru_add_drain_all(bool force_all_cpus)
 	for_each_online_cpu(cpu) {
 		struct work_struct *work = &per_cpu(lru_add_drain_work, cpu);
 
-		if (force_all_cpus ||
-		    pagevec_count(&per_cpu(lru_pvecs.lru_add, cpu)) ||
-		    data_race(pagevec_count(&per_cpu(lru_rotate.pvec, cpu))) ||
-		    pagevec_count(&per_cpu(lru_pvecs.lru_deactivate_file, cpu)) ||
-		    pagevec_count(&per_cpu(lru_pvecs.lru_deactivate, cpu)) ||
-		    pagevec_count(&per_cpu(lru_pvecs.lru_lazyfree, cpu)) ||
-		    need_activate_page_drain(cpu) ||
-		    has_bh_in_lru(cpu, NULL)) {
+		if (force_all_cpus || lru_cpu_needs_drain(cpu)) {
 			INIT_WORK(work, lru_add_drain_per_cpu);
 			queue_work_on(cpu, mm_percpu_wq, work);
 			__cpumask_set_cpu(cpu, &has_work);
-- 
2.31.1