Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:6 as permitted sender) client-ip=2620:137:e000::3:6;
From:   Roman Gushchin <roman.gushchin@linux.dev>
To:     linux-mm@kvack.org
Cc:     linux-kernel@vger.kernel.org, cgroups@vger.kernel.org,
        Johannes Weiner <hannes@cmpxchg.org>,
        Michal Hocko <mhocko@kernel.org>,
        Shakeel Butt <shakeelb@google.com>,
        Muchun Song <muchun.song@linux.dev>,
        Dennis Zhou <dennis@kernel.org>,
        Andrew Morton <akpm@linux-foundation.org>,
        Roman Gushchin <roman.gushchin@linux.dev>
Subject: [PATCH rfc 1/5] mm: kmem: optimize get_obj_cgroup_from_current()
Date:   Wed, 27 Sep 2023 08:08:28 -0700
Message-ID: <20230927150832.335132-2-roman.gushchin@linux.dev>
In-Reply-To: <20230927150832.335132-1-roman.gushchin@linux.dev>
References: <20230927150832.335132-1-roman.gushchin@linux.dev>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Manually inline memcg_kmem_bypass() and active_memcg() to speed up
get_obj_cgroup_from_current() by avoiding duplicate in_task() checks
and active_memcg() readings.

Also add a likely() macro to __get_obj_cgroup_from_memcg():
obj_cgroup_tryget() should succeed at almost all times except a very
unlikely race with the memcg deletion path.

Signed-off-by: Roman Gushchin (Cruise) <roman.gushchin@linux.dev>
Acked-by: Shakeel Butt <shakeelb@google.com>
---
 mm/memcontrol.c | 34 ++++++++++++++--------------------
 1 file changed, 14 insertions(+), 20 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 9741d62d0424..16ac2a5838fb 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1068,19 +1068,6 @@ struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
 }
 EXPORT_SYMBOL(get_mem_cgroup_from_mm);
 
-static __always_inline bool memcg_kmem_bypass(void)
-{
-	/* Allow remote memcg charging from any context. */
-	if (unlikely(active_memcg()))
-		return false;
-
-	/* Memcg to charge can't be determined. */
-	if (!in_task() || !current->mm || (current->flags & PF_KTHREAD))
-		return true;
-
-	return false;
-}
-
 /**
  * mem_cgroup_iter - iterate over memory cgroup hierarchy
  * @root: hierarchy root
@@ -3007,7 +2994,7 @@ static struct obj_cgroup *__get_obj_cgroup_from_memcg(struct mem_cgroup *memcg)
 
 	for (; !mem_cgroup_is_root(memcg); memcg = parent_mem_cgroup(memcg)) {
 		objcg = rcu_dereference(memcg->objcg);
-		if (objcg && obj_cgroup_tryget(objcg))
+		if (likely(objcg && obj_cgroup_tryget(objcg)))
 			break;
 		objcg = NULL;
 	}
@@ -3016,16 +3003,23 @@ static struct obj_cgroup *__get_obj_cgroup_from_memcg(struct mem_cgroup *memcg)
 
 __always_inline struct obj_cgroup *get_obj_cgroup_from_current(void)
 {
-	struct obj_cgroup *objcg = NULL;
 	struct mem_cgroup *memcg;
+	struct obj_cgroup *objcg;
 
-	if (memcg_kmem_bypass())
-		return NULL;
+	if (in_task()) {
+		memcg = current->active_memcg;
+
+		/* Memcg to charge can't be determined. */
+		if (likely(!memcg) && (!current->mm || (current->flags & PF_KTHREAD)))
+			return NULL;
+	} else {
+		memcg = this_cpu_read(int_active_memcg);
+		if (likely(!memcg))
+			return NULL;
+	}
 
 	rcu_read_lock();
-	if (unlikely(active_memcg()))
-		memcg = active_memcg();
-	else
+	if (!memcg)
 		memcg = mem_cgroup_from_task(current);
 	objcg = __get_obj_cgroup_from_memcg(memcg);
 	rcu_read_unlock();
-- 
2.42.0