Re: [PATCH v7 08/19] mm: memcg/slab: save obj_cgroup for non-root slab objects

[Roman Gushchin <guro@fb.com>]

On Thu, Jul 16, 2020 at 10:25:01PM +0530, Naresh Kamboju wrote:
> On Tue, 23 Jun 2020 at 23:11, Roman Gushchin <guro@fb.com> wrote:
> >
> > Store the obj_cgroup pointer in the corresponding place of
> > page->obj_cgroups for each allocated non-root slab object.  Make sure that
> > each allocated object holds a reference to obj_cgroup.
> >
> > Objcg pointer is obtained from the memcg->objcg dereferencing in
> > memcg_kmem_get_cache() and passed from pre_alloc_hook to post_alloc_hook.
> > Then in case of successful allocation(s) it's getting stored in the
> > page->obj_cgroups vector.
> >
> > The objcg obtaining part look a bit bulky now, but it will be simplified
> > by next commits in the series.
> >
> > Signed-off-by: Roman Gushchin <guro@fb.com>
> > Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
> > Reviewed-by: Shakeel Butt <shakeelb@google.com>
> > ---
> >  include/linux/memcontrol.h |  3 +-
> >  mm/memcontrol.c            | 14 +++++++--
> >  mm/slab.c                  | 18 +++++++-----
> >  mm/slab.h                  | 60 ++++++++++++++++++++++++++++++++++----
> >  mm/slub.c                  | 14 +++++----
> >  5 files changed, 88 insertions(+), 21 deletions(-)
> >
> > diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> > index f2f9d5d6b7d1..b845e908e76e 100644
> > --- a/include/linux/memcontrol.h
> > +++ b/include/linux/memcontrol.h
> > @@ -1404,7 +1404,8 @@ static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg,
> >  }
> >  #endif
> >
> > -struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep);
> > +struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep,
> > +                                       struct obj_cgroup **objcgp);
> >  void memcg_kmem_put_cache(struct kmem_cache *cachep);
> >
> >  #ifdef CONFIG_MEMCG_KMEM
> > diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> > index 60e3f3ca75ca..5e55c7afc18c 100644
> > --- a/mm/memcontrol.c
> > +++ b/mm/memcontrol.c
> > @@ -2973,7 +2973,8 @@ static inline bool memcg_kmem_bypass(void)
> >   * done with it, memcg_kmem_put_cache() must be called to release the
> >   * reference.
> >   */
> > -struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep)
> > +struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep,
> > +                                       struct obj_cgroup **objcgp)
> >  {
> >         struct mem_cgroup *memcg;
> >         struct kmem_cache *memcg_cachep;
> > @@ -3029,8 +3030,17 @@ struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep)
> >          */
> >         if (unlikely(!memcg_cachep))
> >                 memcg_schedule_kmem_cache_create(memcg, cachep);
> > -       else if (percpu_ref_tryget(&memcg_cachep->memcg_params.refcnt))
> > +       else if (percpu_ref_tryget(&memcg_cachep->memcg_params.refcnt)) {
> > +               struct obj_cgroup *objcg = rcu_dereference(memcg->objcg);
> > +
> > +               if (!objcg || !obj_cgroup_tryget(objcg)) {
> > +                       percpu_ref_put(&memcg_cachep->memcg_params.refcnt);
> > +                       goto out_unlock;
> > +               }
> > +
> > +               *objcgp = objcg;
> >                 cachep = memcg_cachep;
> > +       }
> >  out_unlock:
> >         rcu_read_unlock();
> >         return cachep;
> > diff --git a/mm/slab.c b/mm/slab.c
> > index 4c7013eeacd9..a7cc1336221f 100644
> > --- a/mm/slab.c
> > +++ b/mm/slab.c
> > @@ -3222,9 +3222,10 @@ slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
> >         unsigned long save_flags;
> >         void *ptr;
> >         int slab_node = numa_mem_id();
> > +       struct obj_cgroup *objcg = NULL;
> >
> >         flags &= gfp_allowed_mask;
> > -       cachep = slab_pre_alloc_hook(cachep, flags);
> > +       cachep = slab_pre_alloc_hook(cachep, &objcg, 1, flags);
> >         if (unlikely(!cachep))
> >                 return NULL;
> >
> > @@ -3260,7 +3261,7 @@ slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
> >         if (unlikely(slab_want_init_on_alloc(flags, cachep)) && ptr)
> >                 memset(ptr, 0, cachep->object_size);
> >
> > -       slab_post_alloc_hook(cachep, flags, 1, &ptr);
> > +       slab_post_alloc_hook(cachep, objcg, flags, 1, &ptr);
> >         return ptr;
> >  }
> >
> > @@ -3301,9 +3302,10 @@ slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller)
> >  {
> >         unsigned long save_flags;
> >         void *objp;
> > +       struct obj_cgroup *objcg = NULL;
> >
> >         flags &= gfp_allowed_mask;
> > -       cachep = slab_pre_alloc_hook(cachep, flags);
> > +       cachep = slab_pre_alloc_hook(cachep, &objcg, 1, flags);
> >         if (unlikely(!cachep))
> >                 return NULL;
> >
> > @@ -3317,7 +3319,7 @@ slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller)
> >         if (unlikely(slab_want_init_on_alloc(flags, cachep)) && objp)
> >                 memset(objp, 0, cachep->object_size);
> >
> > -       slab_post_alloc_hook(cachep, flags, 1, &objp);
> > +       slab_post_alloc_hook(cachep, objcg, flags, 1, &objp);
> >         return objp;
> >  }
> >
> > @@ -3443,6 +3445,7 @@ void ___cache_free(struct kmem_cache *cachep, void *objp,
> >                 memset(objp, 0, cachep->object_size);
> >         kmemleak_free_recursive(objp, cachep->flags);
> >         objp = cache_free_debugcheck(cachep, objp, caller);
> > +       memcg_slab_free_hook(cachep, virt_to_head_page(objp), objp);
> >
> >         /*
> >          * Skip calling cache_free_alien() when the platform is not numa.
> > @@ -3508,8 +3511,9 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
> >                           void **p)
> >  {
> >         size_t i;
> > +       struct obj_cgroup *objcg = NULL;
> >
> > -       s = slab_pre_alloc_hook(s, flags);
> > +       s = slab_pre_alloc_hook(s, &objcg, size, flags);
> >         if (!s)
> >                 return 0;
> >
> > @@ -3532,13 +3536,13 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
> >                 for (i = 0; i < size; i++)
> >                         memset(p[i], 0, s->object_size);
> >
> > -       slab_post_alloc_hook(s, flags, size, p);
> > +       slab_post_alloc_hook(s, objcg, flags, size, p);
> >         /* FIXME: Trace call missing. Christoph would like a bulk variant */
> >         return size;
> >  error:
> >         local_irq_enable();
> >         cache_alloc_debugcheck_after_bulk(s, flags, i, p, _RET_IP_);
> > -       slab_post_alloc_hook(s, flags, i, p);
> > +       slab_post_alloc_hook(s, objcg, flags, i, p);
> >         __kmem_cache_free_bulk(s, i, p);
> >         return 0;
> >  }
> > diff --git a/mm/slab.h b/mm/slab.h
> > index 7d175c2f1a61..c37a50f26e41 100644
> > --- a/mm/slab.h
> > +++ b/mm/slab.h
> > @@ -469,6 +469,41 @@ static inline void memcg_free_page_obj_cgroups(struct page *page)
> >         page->obj_cgroups = NULL;
> >  }
> >
> > +static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
> > +                                             struct obj_cgroup *objcg,
> > +                                             size_t size, void **p)
> > +{
> > +       struct page *page;
> > +       unsigned long off;
> > +       size_t i;
> > +
> > +       for (i = 0; i < size; i++) {
> > +               if (likely(p[i])) {
> > +                       page = virt_to_head_page(p[i]);
> > +                       off = obj_to_index(s, page, p[i]);
> > +                       obj_cgroup_get(objcg);
> > +                       page_obj_cgroups(page)[off] = objcg;
> > +               }
> > +       }
> > +       obj_cgroup_put(objcg);
> > +       memcg_kmem_put_cache(s);
> > +}
> > +
> > +static inline void memcg_slab_free_hook(struct kmem_cache *s, struct page *page,
> > +                                       void *p)
> > +{
> > +       struct obj_cgroup *objcg;
> > +       unsigned int off;
> > +
> > +       if (!memcg_kmem_enabled() || is_root_cache(s))
> > +               return;
> > +
> > +       off = obj_to_index(s, page, p);
> > +       objcg = page_obj_cgroups(page)[off];
> > +       page_obj_cgroups(page)[off] = NULL;
> > +       obj_cgroup_put(objcg);
> > +}
> > +
> >  extern void slab_init_memcg_params(struct kmem_cache *);
> >  extern void memcg_link_cache(struct kmem_cache *s, struct mem_cgroup *memcg);
> >
> > @@ -528,6 +563,17 @@ static inline void memcg_free_page_obj_cgroups(struct page *page)
> >  {
> >  }
> >
> > +static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
> > +                                             struct obj_cgroup *objcg,
> > +                                             size_t size, void **p)
> > +{
> > +}
> > +
> > +static inline void memcg_slab_free_hook(struct kmem_cache *s, struct page *page,
> > +                                       void *p)
> > +{
> > +}
> > +
> >  static inline void slab_init_memcg_params(struct kmem_cache *s)
> >  {
> >  }
> > @@ -630,7 +676,8 @@ static inline size_t slab_ksize(const struct kmem_cache *s)
> >  }
> >
> >  static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s,
> > -                                                    gfp_t flags)
> > +                                                    struct obj_cgroup **objcgp,
> > +                                                    size_t size, gfp_t flags)
> >  {
> >         flags &= gfp_allowed_mask;
> >
> > @@ -644,13 +691,14 @@ static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s,
> >
> >         if (memcg_kmem_enabled() &&
> >             ((flags & __GFP_ACCOUNT) || (s->flags & SLAB_ACCOUNT)))
> > -               return memcg_kmem_get_cache(s);
> > +               return memcg_kmem_get_cache(s, objcgp);
> >
> >         return s;
> >  }
> >
> > -static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags,
> > -                                       size_t size, void **p)
> > +static inline void slab_post_alloc_hook(struct kmem_cache *s,
> > +                                       struct obj_cgroup *objcg,
> > +                                       gfp_t flags, size_t size, void **p)
> >  {
> >         size_t i;
> >
> > @@ -662,8 +710,8 @@ static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags,
> >                                          s->flags, flags);
> >         }
> >
> > -       if (memcg_kmem_enabled())
> > -               memcg_kmem_put_cache(s);
> > +       if (memcg_kmem_enabled() && !is_root_cache(s))
> > +               memcg_slab_post_alloc_hook(s, objcg, size, p);
> >  }
> >
> >  #ifndef CONFIG_SLOB
> > diff --git a/mm/slub.c b/mm/slub.c
> > index aa8d18824e62..25810980a26c 100644
> > --- a/mm/slub.c
> > +++ b/mm/slub.c
> > @@ -2821,8 +2821,9 @@ static __always_inline void *slab_alloc_node(struct kmem_cache *s,
> >         struct kmem_cache_cpu *c;
> >         struct page *page;
> >         unsigned long tid;
> > +       struct obj_cgroup *objcg = NULL;
> >
> > -       s = slab_pre_alloc_hook(s, gfpflags);
> > +       s = slab_pre_alloc_hook(s, &objcg, 1, gfpflags);
> >         if (!s)
> >                 return NULL;
> >  redo:
> > @@ -2898,7 +2899,7 @@ static __always_inline void *slab_alloc_node(struct kmem_cache *s,
> >         if (unlikely(slab_want_init_on_alloc(gfpflags, s)) && object)
> >                 memset(object, 0, s->object_size);
> >
> > -       slab_post_alloc_hook(s, gfpflags, 1, &object);
> > +       slab_post_alloc_hook(s, objcg, gfpflags, 1, &object);
> >
> >         return object;
> >  }
> > @@ -3103,6 +3104,8 @@ static __always_inline void do_slab_free(struct kmem_cache *s,
> >         void *tail_obj = tail ? : head;
> >         struct kmem_cache_cpu *c;
> >         unsigned long tid;
> > +
> > +       memcg_slab_free_hook(s, page, head);
> >  redo:
> >         /*
> >          * Determine the currently cpus per cpu slab.
> > @@ -3282,9 +3285,10 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
> >  {
> >         struct kmem_cache_cpu *c;
> >         int i;
> > +       struct obj_cgroup *objcg = NULL;
> >
> >         /* memcg and kmem_cache debug support */
> > -       s = slab_pre_alloc_hook(s, flags);
> > +       s = slab_pre_alloc_hook(s, &objcg, size, flags);
> >         if (unlikely(!s))
> >                 return false;
> >         /*
> > @@ -3338,11 +3342,11 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
> >         }
> >
> >         /* memcg and kmem_cache debug support */
> > -       slab_post_alloc_hook(s, flags, size, p);
> > +       slab_post_alloc_hook(s, objcg, flags, size, p);
> >         return i;
> >  error:
> >         local_irq_enable();
> > -       slab_post_alloc_hook(s, flags, i, p);
> > +       slab_post_alloc_hook(s, objcg, flags, i, p);
> >         __kmem_cache_free_bulk(s, i, p);
> >         return 0;
> >  }
> >
> 
> I am not sure if this is the related patch or not that is causing
> mips architecture build failure on linux -next.

Hello, Naresh!

Thank you for the report, interesting...
There is nothing arch-specific in the code, so there must be something
compiler-dependent. My wild guess is that the problem is caused by a memory
allocation from the memcg_slab_post_alloc_hook(), but it's added by a later
patch in the series. So if it really fails at this patch, there must be something
different. I'll try to reproduce it, but I have to install the MIPS toolchain first,
so it might take some time. If it creates some troubles, can you, please, check
if s/__always_inline/inline helps?

Thanks!

> 
> make -sk KBUILD_BUILD_USER=TuxBuild -C/linux -j16 ARCH=mips
> CROSS_COMPILE=mips-linux-gnu- HOSTCC=gcc CC="sccache
> mips-linux-gnu-gcc" O=build
> #
> ../mm/slub.c: In function ‘slab_alloc.constprop’:
> ../mm/slub.c:2897:30: error: inlining failed in call to always_inline
> ‘slab_alloc.constprop’: recursive inlining
>  2897 | static __always_inline void *slab_alloc(struct kmem_cache *s,
>       |                              ^~~~~~~~~~
> ../mm/slub.c:2905:14: note: called from here
>  2905 |  void *ret = slab_alloc(s, gfpflags, _RET_IP_);
>       |              ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
> ../mm/slub.c: In function ‘sysfs_slab_alias’:
> ../mm/slub.c:2897:30: error: inlining failed in call to always_inline
> ‘slab_alloc.constprop’: recursive inlining
>  2897 | static __always_inline void *slab_alloc(struct kmem_cache *s,
>       |                              ^~~~~~~~~~
> ../mm/slub.c:2905:14: note: called from here
>  2905 |  void *ret = slab_alloc(s, gfpflags, _RET_IP_);
>       |              ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
> ../mm/slub.c: In function ‘sysfs_slab_add’:
> ../mm/slub.c:2897:30: error: inlining failed in call to always_inline
> ‘slab_alloc.constprop’: recursive inlining
>  2897 | static __always_inline void *slab_alloc(struct kmem_cache *s,
>       |                              ^~~~~~~~~~
> ../mm/slub.c:2905:14: note: called from here
>  2905 |  void *ret = slab_alloc(s, gfpflags, _RET_IP_);
>       |              ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
> 
> 
> Full build log link,
> https://urldefense.proofpoint.com/v2/url?u=https-3A__builds.tuxbuild.com_jBgeEp1SD-2DbUldWES782yQ_build.log&d=DwIFaQ&c=5VD0RTtNlTh3ycd41b3MUw&r=jJYgtDM7QT-W-Fz_d29HYQ&m=XO4W3q0FbuSIPvvA7_av_jFzLvJw7jfRpBhtUGJfpKE&s=tlrwIrPSvEYT8QV4wnWxOnXQQMA8EYeYS-4O-BxVLOA&e= 
> 
> -- 
> Linaro LKFT
> https://urldefense.proofpoint.com/v2/url?u=https-3A__lkft.linaro.org&d=DwIFaQ&c=5VD0RTtNlTh3ycd41b3MUw&r=jJYgtDM7QT-W-Fz_d29HYQ&m=XO4W3q0FbuSIPvvA7_av_jFzLvJw7jfRpBhtUGJfpKE&s=WFK6dW0eWT7ZY1HBBJeLSUgOxE2J11TOhbqdnCIdvCE&e=