summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorRoman Gushchin <guro@fb.com>2020-10-17 16:13:50 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2020-10-18 09:27:09 -0700
commit37d5985c003daab138a72dd4af9853b396d91c26 (patch)
treefd28f77d84c3ee56f93561590cc3e0aa90055d19 /mm
parent67f0286498d7486a9c35f081df1dffe2ffcd02b9 (diff)
downloadlinux-37d5985c003daab138a72dd4af9853b396d91c26.tar.bz2
mm: kmem: prepare remote memcg charging infra for interrupt contexts
Remote memcg charging API uses current->active_memcg to store the currently active memory cgroup, which overwrites the memory cgroup of the current process. It works well for normal contexts, but doesn't work for interrupt contexts: indeed, if an interrupt occurs during the execution of a section with an active memcg set, all allocations inside the interrupt will be charged to the active memcg set (given that we'll enable accounting for allocations from an interrupt context). But because the interrupt might have no relation to the active memcg set outside, it's obviously wrong from the accounting prospective. To resolve this problem, let's add a global percpu int_active_memcg variable, which will be used to store an active memory cgroup which will be used from interrupt contexts. set_active_memcg() will transparently use current->active_memcg or int_active_memcg depending on the context. To make the read part simple and transparent for the caller, let's introduce two new functions: - struct mem_cgroup *active_memcg(void), - struct mem_cgroup *get_active_memcg(void). They are returning the active memcg if it's set, hiding all implementation details: where to get it depending on the current context. Signed-off-by: Roman Gushchin <guro@fb.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Shakeel Butt <shakeelb@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@kernel.org> Link: http://lkml.kernel.org/r/20200827225843.1270629-4-guro@fb.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/memcontrol.c48
1 files changed, 34 insertions, 14 deletions
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 51b1698bf06c..a3318b66e41e 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -73,6 +73,9 @@ EXPORT_SYMBOL(memory_cgrp_subsys);
struct mem_cgroup *root_mem_cgroup __read_mostly;
+/* Active memory cgroup to use from an interrupt context */
+DEFINE_PER_CPU(struct mem_cgroup *, int_active_memcg);
+
/* Socket memory accounting disabled? */
static bool cgroup_memory_nosocket;
@@ -1061,26 +1064,43 @@ struct mem_cgroup *get_mem_cgroup_from_page(struct page *page)
}
EXPORT_SYMBOL(get_mem_cgroup_from_page);
-/**
- * If current->active_memcg is non-NULL, do not fallback to current->mm->memcg.
- */
-static __always_inline struct mem_cgroup *get_mem_cgroup_from_current(void)
+static __always_inline struct mem_cgroup *active_memcg(void)
{
- if (memcg_kmem_bypass())
- return NULL;
+ if (in_interrupt())
+ return this_cpu_read(int_active_memcg);
+ else
+ return current->active_memcg;
+}
- if (unlikely(current->active_memcg)) {
- struct mem_cgroup *memcg;
+static __always_inline struct mem_cgroup *get_active_memcg(void)
+{
+ struct mem_cgroup *memcg;
- rcu_read_lock();
+ rcu_read_lock();
+ memcg = active_memcg();
+ if (memcg) {
/* current->active_memcg must hold a ref. */
- if (WARN_ON_ONCE(!css_tryget(&current->active_memcg->css)))
+ if (WARN_ON_ONCE(!css_tryget(&memcg->css)))
memcg = root_mem_cgroup;
else
memcg = current->active_memcg;
- rcu_read_unlock();
- return memcg;
}
+ rcu_read_unlock();
+
+ return memcg;
+}
+
+/**
+ * If active memcg is set, do not fallback to current->mm->memcg.
+ */
+static __always_inline struct mem_cgroup *get_mem_cgroup_from_current(void)
+{
+ if (memcg_kmem_bypass())
+ return NULL;
+
+ if (unlikely(active_memcg()))
+ return get_active_memcg();
+
return get_mem_cgroup_from_mm(current->mm);
}
@@ -2940,8 +2960,8 @@ __always_inline struct obj_cgroup *get_obj_cgroup_from_current(void)
return NULL;
rcu_read_lock();
- if (unlikely(current->active_memcg))
- memcg = rcu_dereference(current->active_memcg);
+ if (unlikely(active_memcg()))
+ memcg = active_memcg();
else
memcg = mem_cgroup_from_task(current);