[v3] memcg: nmi-safe kmem charging

[PATCH v3 1/5] memcg: disable kmem charging in nmi for unsupported arch

Posted by Shakeel Butt 7 months, 1 week ago

The memcg accounting and stats uses this_cpu* and atomic* ops. There are
archs which define CONFIG_HAVE_NMI but does not define
CONFIG_ARCH_HAS_NMI_SAFE_THIS_CPU_OPS and ARCH_HAVE_NMI_SAFE_CMPXCHG, so
memcg accounting for such archs in nmi context is not possible to
support. Let's just disable memcg accounting in nmi context for such
archs.

Signed-off-by: Shakeel Butt <shakeel.butt@linux.dev>
---
Changes since v2:
- reorder the in_nmi() check as suggested by Vlastimil

 include/linux/memcontrol.h |  5 +++++
 mm/memcontrol.c            | 15 +++++++++++++++
 2 files changed, 20 insertions(+)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index f7848f73f41c..53920528821f 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -62,6 +62,11 @@ struct mem_cgroup_reclaim_cookie {
 
 #ifdef CONFIG_MEMCG
 
+#if defined(CONFIG_ARCH_HAS_NMI_SAFE_THIS_CPU_OPS) || \
+	!defined(CONFIG_HAVE_NMI) || defined(ARCH_HAVE_NMI_SAFE_CMPXCHG)
+#define MEMCG_SUPPORTS_NMI_CHARGING
+#endif
+
 #define MEM_CGROUP_ID_SHIFT	16
 
 struct mem_cgroup_id {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e17b698f6243..0f182e4a9da0 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2647,11 +2647,26 @@ static struct obj_cgroup *current_objcg_update(void)
 	return objcg;
 }
 
+#ifdef MEMCG_SUPPORTS_NMI_CHARGING
+static inline bool nmi_charging_allowed(void)
+{
+	return true;
+}
+#else
+static inline bool nmi_charging_allowed(void)
+{
+	return false;
+}
+#endif
+
 __always_inline struct obj_cgroup *current_obj_cgroup(void)
 {
 	struct mem_cgroup *memcg;
 	struct obj_cgroup *objcg;
 
+	if (!nmi_charging_allowed() && in_nmi())
+		return NULL;
+
 	if (in_task()) {
 		memcg = current->active_memcg;
 		if (unlikely(memcg))
-- 
2.47.1

Re: [PATCH v3 1/5] memcg: disable kmem charging in nmi for unsupported arch

Posted by Johannes Weiner 7 months ago

On Fri, May 16, 2025 at 11:32:27AM -0700, Shakeel Butt wrote:
> The memcg accounting and stats uses this_cpu* and atomic* ops. There are
> archs which define CONFIG_HAVE_NMI but does not define
> CONFIG_ARCH_HAS_NMI_SAFE_THIS_CPU_OPS and ARCH_HAVE_NMI_SAFE_CMPXCHG, so
> memcg accounting for such archs in nmi context is not possible to
> support. Let's just disable memcg accounting in nmi context for such
> archs.
> 
> Signed-off-by: Shakeel Butt <shakeel.butt@linux.dev>
> ---
> Changes since v2:
> - reorder the in_nmi() check as suggested by Vlastimil
> 
>  include/linux/memcontrol.h |  5 +++++
>  mm/memcontrol.c            | 15 +++++++++++++++
>  2 files changed, 20 insertions(+)
> 
> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> index f7848f73f41c..53920528821f 100644
> --- a/include/linux/memcontrol.h
> +++ b/include/linux/memcontrol.h
> @@ -62,6 +62,11 @@ struct mem_cgroup_reclaim_cookie {
>  
>  #ifdef CONFIG_MEMCG
>  
> +#if defined(CONFIG_ARCH_HAS_NMI_SAFE_THIS_CPU_OPS) || \
> +	!defined(CONFIG_HAVE_NMI) || defined(ARCH_HAVE_NMI_SAFE_CMPXCHG)

                                             CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG?

> +#define MEMCG_SUPPORTS_NMI_CHARGING
> +#endif

Since it's derived from config symbols, it's better to make this an
internal symbol as well. Something like:

	config MEMCG_NMI_UNSAFE
		bool
		depends on HAVE_NMI
		depends on !ARCH_HAS_NMI_SAFE_THIS_CPU_OPS && !ARCH_HAVE_NMI_SAFE_CMPXCHG

>  #define MEM_CGROUP_ID_SHIFT	16
>  
>  struct mem_cgroup_id {
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index e17b698f6243..0f182e4a9da0 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -2647,11 +2647,26 @@ static struct obj_cgroup *current_objcg_update(void)
>  	return objcg;
>  }
>  
> +#ifdef MEMCG_SUPPORTS_NMI_CHARGING
> +static inline bool nmi_charging_allowed(void)
> +{
> +	return true;
> +}
> +#else
> +static inline bool nmi_charging_allowed(void)
> +{
> +	return false;
> +}
> +#endif

...drop these...

> +
>  __always_inline struct obj_cgroup *current_obj_cgroup(void)
>  {
>  	struct mem_cgroup *memcg;
>  	struct obj_cgroup *objcg;
>  
> +	if (!nmi_charging_allowed() && in_nmi())
> +		return NULL;

..and finally do

	if (IS_ENABLED(CONFIG_MEMCG_NMI_UNSAFE && in_nmi())
		return NULL;

here.

Re: [PATCH v3 1/5] memcg: disable kmem charging in nmi for unsupported arch

Posted by Shakeel Butt 7 months ago

On Sat, May 17, 2025 at 7:06 AM Johannes Weiner <hannes@cmpxchg.org> wrote:
>
> On Fri, May 16, 2025 at 11:32:27AM -0700, Shakeel Butt wrote:
> > The memcg accounting and stats uses this_cpu* and atomic* ops. There are
> > archs which define CONFIG_HAVE_NMI but does not define
> > CONFIG_ARCH_HAS_NMI_SAFE_THIS_CPU_OPS and ARCH_HAVE_NMI_SAFE_CMPXCHG, so
> > memcg accounting for such archs in nmi context is not possible to
> > support. Let's just disable memcg accounting in nmi context for such
> > archs.
> >
> > Signed-off-by: Shakeel Butt <shakeel.butt@linux.dev>
> > ---
> > Changes since v2:
> > - reorder the in_nmi() check as suggested by Vlastimil
> >
> >  include/linux/memcontrol.h |  5 +++++
> >  mm/memcontrol.c            | 15 +++++++++++++++
> >  2 files changed, 20 insertions(+)
> >
> > diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> > index f7848f73f41c..53920528821f 100644
> > --- a/include/linux/memcontrol.h
> > +++ b/include/linux/memcontrol.h
> > @@ -62,6 +62,11 @@ struct mem_cgroup_reclaim_cookie {
> >
> >  #ifdef CONFIG_MEMCG
> >
> > +#if defined(CONFIG_ARCH_HAS_NMI_SAFE_THIS_CPU_OPS) || \
> > +     !defined(CONFIG_HAVE_NMI) || defined(ARCH_HAVE_NMI_SAFE_CMPXCHG)
>
>                                              CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG?
>
> > +#define MEMCG_SUPPORTS_NMI_CHARGING
> > +#endif
>
> Since it's derived from config symbols, it's better to make this an
> internal symbol as well. Something like:
>
>         config MEMCG_NMI_UNSAFE
>                 bool
>                 depends on HAVE_NMI
>                 depends on !ARCH_HAS_NMI_SAFE_THIS_CPU_OPS && !ARCH_HAVE_NMI_SAFE_CMPXCHG
>
> >  #define MEM_CGROUP_ID_SHIFT  16
> >
> >  struct mem_cgroup_id {
> > diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> > index e17b698f6243..0f182e4a9da0 100644
> > --- a/mm/memcontrol.c
> > +++ b/mm/memcontrol.c
> > @@ -2647,11 +2647,26 @@ static struct obj_cgroup *current_objcg_update(void)
> >       return objcg;
> >  }
> >
> > +#ifdef MEMCG_SUPPORTS_NMI_CHARGING
> > +static inline bool nmi_charging_allowed(void)
> > +{
> > +     return true;
> > +}
> > +#else
> > +static inline bool nmi_charging_allowed(void)
> > +{
> > +     return false;
> > +}
> > +#endif
>
> ...drop these...
>
> > +
> >  __always_inline struct obj_cgroup *current_obj_cgroup(void)
> >  {
> >       struct mem_cgroup *memcg;
> >       struct obj_cgroup *objcg;
> >
> > +     if (!nmi_charging_allowed() && in_nmi())
> > +             return NULL;
>
> ..and finally do
>
>         if (IS_ENABLED(CONFIG_MEMCG_NMI_UNSAFE && in_nmi())
>                 return NULL;
>
> here.

Thanks Johannes, will do in the next version.