linux-kernel - [PATCH] mm/memcg: Disable task obj_stock for PREEMPT

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: <20210803175519.22298-1-longman@redhat.com>
Date:   Tue,  3 Aug 2021 13:55:19 -0400
From:   Waiman Long <longman@...hat.com>
To:     Johannes Weiner <hannes@...xchg.org>,
        Michal Hocko <mhocko@...nel.org>,
        Vladimir Davydov <vdavydov.dev@...il.com>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Vlastimil Babka <vbabka@...e.cz>, Roman Gushchin <guro@...com>
Cc:     linux-kernel@...r.kernel.org, cgroups@...r.kernel.org,
        linux-mm@...ck.org, Shakeel Butt <shakeelb@...gle.com>,
        Muchun Song <songmuchun@...edance.com>,
        Luis Goncalves <lgoncalv@...hat.com>,
        Waiman Long <longman@...hat.com>
Subject: [PATCH] mm/memcg: Disable task obj_stock for PREEMPT_RT

For PREEMPT_RT kernel, preempt_disable() and local_irq_save()
are typically converted to local_lock() and local_lock_irqsave()
respectively. These two variants of local_lock() are essentially
the same. Thus, there is no performance advantage in choosing one
over the other.

As there is no point in maintaining two different sets of obj_stock,
it is simpler and more efficient to just disable task_obj and use
only irq_obj for PREEMPT_RT. However, task_obj will still be there
in the memcg_stock_pcp structure even though it is not used in this
configuration.

Signed-off-by: Waiman Long <longman@...hat.com>
---
 mm/memcontrol.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 87c883227f90..4f80770cb97b 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2120,12 +2120,22 @@ static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
  * which is cheap in non-preempt kernel. The interrupt context object stock
  * can only be accessed after disabling interrupt. User context code can
  * access interrupt object stock, but not vice versa.
+ *
+ * For PREEMPT_RT kernel, preempt_disable() and local_irq_save() may have
+ * to be changed to variants of local_lock(). This eliminates the
+ * performance advantage of using preempt_disable(). Fall back to always
+ * use local_irq_save() and use only irq_obj for simplicity.
  */
+static inline bool use_task_obj_stock(void)
+{
+	return !IS_ENABLED(CONFIG_PREEMPT_RT) && likely(in_task());
+}
+
 static inline struct obj_stock *get_obj_stock(unsigned long *pflags)
 {
 	struct memcg_stock_pcp *stock;
 
-	if (likely(in_task())) {
+	if (use_task_obj_stock()) {
 		*pflags = 0UL;
 		preempt_disable();
 		stock = this_cpu_ptr(&memcg_stock);
@@ -2139,7 +2149,7 @@ static inline struct obj_stock *get_obj_stock(unsigned long *pflags)
 
 static inline void put_obj_stock(unsigned long flags)
 {
-	if (likely(in_task()))
+	if (use_task_obj_stock())
 		preempt_enable();
 	else
 		local_irq_restore(flags);
@@ -2212,7 +2222,7 @@ static void drain_local_stock(struct work_struct *dummy)
 
 	stock = this_cpu_ptr(&memcg_stock);
 	drain_obj_stock(&stock->irq_obj);
-	if (in_task())
+	if (use_task_obj_stock())
 		drain_obj_stock(&stock->task_obj);
 	drain_stock(stock);
 	clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags);
@@ -3217,7 +3227,7 @@ static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
 {
 	struct mem_cgroup *memcg;
 
-	if (in_task() && stock->task_obj.cached_objcg) {
+	if (use_task_obj_stock() && stock->task_obj.cached_objcg) {
 		memcg = obj_cgroup_memcg(stock->task_obj.cached_objcg);
 		if (memcg && mem_cgroup_is_descendant(memcg, root_memcg))
 			return true;
-- 
2.18.1