mm: kmem: optimize get_obj_cgroup_from_current()

Patch series "mm: improve performance of accounted kernel memory
allocations", v5.

This patchset improves the performance of accounted kernel memory
allocations by ~30% as measured by a micro-benchmark [1].  The benchmark
is very straightforward: 1M of 64 bytes-large kmalloc() allocations.

Below are results with the disabled kernel memory accounting, the original state
and with this patchset applied.

|             | Kmem disabled | Original | Patched |  Delta |
|-------------+---------------+----------+---------+--------|
| User cgroup |         29764 |    84548 |   59078 | -30.0% |
| Root cgroup |         29742 |    48342 |   31501 | -34.8% |

As we can see, the patchset removes the majority of the overhead when
there is no actual accounting (a task belongs to the root memory cgroup)
and almost halves the accounting overhead otherwise.

The main idea is to get rid of unnecessary memcg to objcg conversions and
switch to a scope-based protection of objcgs, which eliminates extra
operations with objcg reference counters under a rcu read lock.  More
details are provided in individual commit descriptions.


This patch (of 5):

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.

Link: https://lkml.kernel.org/r/20231019225346.1822282-1-roman.gushchin@linux.dev
Link: https://lkml.kernel.org/r/20231019225346.1822282-2-roman.gushchin@linux.dev
Signed-off-by: Roman Gushchin (Cruise) <roman.gushchin@linux.dev>
Tested-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Acked-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: David Rientjes <rientjes@google.com>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 14 insertions, 20 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a86e7b445800..975ba766c16f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1086,19 +1086,6 @@ 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;
-}
-
 /**
  * get_mem_cgroup_from_current - Obtain a reference on current task's memcg.
  */
@@ -3089,7 +3076,7 @@ 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;
 	}
@@ -3098,16 +3085,23 @@ 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();