[PATCH 1/2] mm: slub: call account_slab_page() after slab page initialization

[PATCH 1/2] mm: slub: call account_slab_page() after slab page initialization

[Roman Gushchin]

It's convenient to have page->objects initialized before calling
into account_slab_page(). In particular, this information can be
used to pre-alloc the obj_cgroup vector.

Let's call account_slab_page() a bit later, after the initialization
of page->objects.

This commit doesn't bring any functional change, but is required for
further optimizations.

Signed-off-by: Roman Gushchin <guro@fb.com>
---
 mm/slub.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index 8c9fa24ebbf3..ccdbb62e025d 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1622,9 +1622,6 @@ static inline struct page *alloc_slab_page(struct kmem_cache *s,
 	else
 		page = __alloc_pages_node(node, flags, order);
 
-	if (page)
-		account_slab_page(page, order, s);
-
 	return page;
 }
 
@@ -1777,6 +1774,8 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 
 	page->objects = oo_objects(oo);
 
+	account_slab_page(page, oo_order(oo), s, flags);
+
 	page->slab_cache = s;
 	__SetPageSlab(page);
 	if (page_is_pfmemalloc(page))
-- 
2.26.2

[PATCH 2/2] mm: memcg/slab: pre-allocate obj_cgroups for slab caches with SLAB_ACCOUNT

[Roman Gushchin]

In general it's unknown in advance if a slab page will contain
accounted objects or not. In order to avoid memory waste, an
obj_cgroup vector is allocated dynamically when a need to account
of a new object arises. Such approach is memory efficient, but
requires an expensive cmpxchg() to set up the memcg/objcgs pointer,
because an allocation can race with a different allocation on another
cpu.

But in some common cases it's known for sure that a slab page will
contain accounted objects: if the page belongs to a slab cache with a
SLAB_ACCOUNT flag set. It includes such popular objects like
vm_area_struct, anon_vma, task_struct, etc.

In such cases we can pre-allocate the objcgs vector and simple assign
it to the page without any atomic operations, because at this early
stage the page is not visible to anyone else.

Signed-off-by: Roman Gushchin <guro@fb.com>
---
 include/linux/memcontrol.h | 14 ++++++++++----
 mm/memcontrol.c            |  4 ++--
 mm/slab.c                  |  2 +-
 mm/slab.h                  | 14 ++++++++++----
 4 files changed, 23 insertions(+), 11 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 20108e426f84..8271f11152e6 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -485,14 +485,20 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page)
  * set_page_objcgs - associate a page with a object cgroups vector
  * @page: a pointer to the page struct
  * @objcgs: a pointer to the object cgroups vector
+ * @atomic: save the value atomically
  *
  * Atomically associates a page with a vector of object cgroups.
  */
 static inline bool set_page_objcgs(struct page *page,
-					struct obj_cgroup **objcgs)
+				   struct obj_cgroup **objcgs, bool atomic)
 {
-	return !cmpxchg(&page->memcg_data, 0, (unsigned long)objcgs |
-			MEMCG_DATA_OBJCGS);
+	unsigned long memcg_data = (unsigned long) objcgs | MEMCG_DATA_OBJCGS;
+
+	if (atomic)
+		return !cmpxchg(&page->memcg_data, 0, memcg_data);
+
+	page->memcg_data = memcg_data;
+	return true;
 }
 #else
 static inline struct obj_cgroup **page_objcgs(struct page *page)
@@ -506,7 +512,7 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page)
 }
 
 static inline bool set_page_objcgs(struct page *page,
-					struct obj_cgroup **objcgs)
+				   struct obj_cgroup **objcgs, bool atomic)
 {
 	return true;
 }
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 69a2893a6455..37bffd336235 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2874,7 +2874,7 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg)
 
 #ifdef CONFIG_MEMCG_KMEM
 int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
-				 gfp_t gfp)
+				 gfp_t gfp, bool atomic)
 {
 	unsigned int objects = objs_per_slab_page(s, page);
 	void *vec;
@@ -2884,7 +2884,7 @@ int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
 	if (!vec)
 		return -ENOMEM;
 
-	if (!set_page_objcgs(page, vec))
+	if (!set_page_objcgs(page, vec, atomic))
 		kfree(vec);
 	else
 		kmemleak_not_leak(vec);
diff --git a/mm/slab.c b/mm/slab.c
index c0ea4b1c7088..df0299e1d0b9 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1380,7 +1380,7 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags,
 		return NULL;
 	}
 
-	account_slab_page(page, cachep->gfporder, cachep);
+	account_slab_page(page, cachep->gfporder, cachep, flags);
 	__SetPageSlab(page);
 	/* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */
 	if (sk_memalloc_socks() && page_is_pfmemalloc(page))
diff --git a/mm/slab.h b/mm/slab.h
index c73050654b8a..f1d6ba09b630 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -240,7 +240,7 @@ static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t fla
 
 #ifdef CONFIG_MEMCG_KMEM
 int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
-				 gfp_t gfp);
+				 gfp_t gfp, bool atomic);
 
 static inline void memcg_free_page_obj_cgroups(struct page *page)
 {
@@ -307,7 +307,8 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
 			page = virt_to_head_page(p[i]);
 
 			if (!page_objcgs(page) &&
-			    memcg_alloc_page_obj_cgroups(page, s, flags)) {
+			    memcg_alloc_page_obj_cgroups(page, s, flags,
+							 true)) {
 				obj_cgroup_uncharge(objcg, obj_full_size(s));
 				continue;
 			}
@@ -371,7 +372,8 @@ static inline struct mem_cgroup *memcg_from_slab_obj(void *ptr)
 }
 
 static inline int memcg_alloc_page_obj_cgroups(struct page *page,
-					       struct kmem_cache *s, gfp_t gfp)
+					       struct kmem_cache *s, gfp_t gfp,
+					       bool atomic)
 {
 	return 0;
 }
@@ -412,8 +414,12 @@ static inline struct kmem_cache *virt_to_cache(const void *obj)
 }
 
 static __always_inline void account_slab_page(struct page *page, int order,
-					      struct kmem_cache *s)
+					      struct kmem_cache *s,
+					      gfp_t gfp)
 {
+	if (memcg_kmem_enabled() && (s->flags & SLAB_ACCOUNT))
+		memcg_alloc_page_obj_cgroups(page, s, gfp, false);
+
 	mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
 			    PAGE_SIZE << order);
 }
-- 
2.26.2

Re: [PATCH 2/2] mm: memcg/slab: pre-allocate obj_cgroups for slab caches with SLAB_ACCOUNT

[Andrew Morton]

On Tue, 10 Nov 2020 11:57:53 -0800 Roman Gushchin <guro@fb.com> wrote:

> In general it's unknown in advance if a slab page will contain
> accounted objects or not. In order to avoid memory waste, an
> obj_cgroup vector is allocated dynamically when a need to account
> of a new object arises. Such approach is memory efficient, but
> requires an expensive cmpxchg() to set up the memcg/objcgs pointer,
> because an allocation can race with a different allocation on another
> cpu.
> 
> But in some common cases it's known for sure that a slab page will
> contain accounted objects: if the page belongs to a slab cache with a
> SLAB_ACCOUNT flag set. It includes such popular objects like
> vm_area_struct, anon_vma, task_struct, etc.
> 
> In such cases we can pre-allocate the objcgs vector and simple assign
> it to the page without any atomic operations, because at this early
> stage the page is not visible to anyone else.

Was there any measurable performance change from this?

Re: [PATCH 2/2] mm: memcg/slab: pre-allocate obj_cgroups for slab caches with SLAB_ACCOUNT

[Roman Gushchin]

On Tue, Nov 10, 2020 at 12:50:08PM -0800, Andrew Morton wrote:
> On Tue, 10 Nov 2020 11:57:53 -0800 Roman Gushchin <guro@fb.com> wrote:
> 
> > In general it's unknown in advance if a slab page will contain
> > accounted objects or not. In order to avoid memory waste, an
> > obj_cgroup vector is allocated dynamically when a need to account
> > of a new object arises. Such approach is memory efficient, but
> > requires an expensive cmpxchg() to set up the memcg/objcgs pointer,
> > because an allocation can race with a different allocation on another
> > cpu.
> > 
> > But in some common cases it's known for sure that a slab page will
> > contain accounted objects: if the page belongs to a slab cache with a
> > SLAB_ACCOUNT flag set. It includes such popular objects like
> > vm_area_struct, anon_vma, task_struct, etc.
> > 
> > In such cases we can pre-allocate the objcgs vector and simple assign
> > it to the page without any atomic operations, because at this early
> > stage the page is not visible to anyone else.
> 
> Was there any measurable performance change from this?

A very simplistic benchmark (allocating 10000000 64-bytes objects in a row)
shows ~15% win. In the real life it seems that most workloads are not very
sensitive to the speed of (accounted) slab allocations.

Re: [PATCH 1/2] mm: slub: call account_slab_page() after slab page initialization

[Johannes Weiner]

On Tue, Nov 10, 2020 at 11:57:52AM -0800, Roman Gushchin wrote:
> It's convenient to have page->objects initialized before calling
> into account_slab_page(). In particular, this information can be
> used to pre-alloc the obj_cgroup vector.
> 
> Let's call account_slab_page() a bit later, after the initialization
> of page->objects.
> 
> This commit doesn't bring any functional change, but is required for
> further optimizations.
> 
> Signed-off-by: Roman Gushchin <guro@fb.com>

Acked-by: Johannes Weiner <hannes@cmpxchg.org>

Re: [PATCH 2/2] mm: memcg/slab: pre-allocate obj_cgroups for slab caches with SLAB_ACCOUNT

[Johannes Weiner]

On Tue, Nov 10, 2020 at 11:57:53AM -0800, Roman Gushchin wrote:
> In general it's unknown in advance if a slab page will contain
> accounted objects or not. In order to avoid memory waste, an
> obj_cgroup vector is allocated dynamically when a need to account
> of a new object arises. Such approach is memory efficient, but
> requires an expensive cmpxchg() to set up the memcg/objcgs pointer,
> because an allocation can race with a different allocation on another
> cpu.
> 
> But in some common cases it's known for sure that a slab page will
> contain accounted objects: if the page belongs to a slab cache with a
> SLAB_ACCOUNT flag set. It includes such popular objects like
> vm_area_struct, anon_vma, task_struct, etc.
> 
> In such cases we can pre-allocate the objcgs vector and simple assign
> it to the page without any atomic operations, because at this early
> stage the page is not visible to anyone else.
> 
> Signed-off-by: Roman Gushchin <guro@fb.com>

That's a nice optimization!

Some comments inline:

> @@ -485,14 +485,20 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page)
>   * set_page_objcgs - associate a page with a object cgroups vector
>   * @page: a pointer to the page struct
>   * @objcgs: a pointer to the object cgroups vector
> + * @atomic: save the value atomically
>   *
>   * Atomically associates a page with a vector of object cgroups.
>   */
>  static inline bool set_page_objcgs(struct page *page,
> -					struct obj_cgroup **objcgs)
> +				   struct obj_cgroup **objcgs, bool atomic)

bool parameters make callsites pretty hard to understand - unless the
function interface obviously has two modes (read vs write etc.), which
isn't the case here.

> -	return !cmpxchg(&page->memcg_data, 0, (unsigned long)objcgs |
> -			MEMCG_DATA_OBJCGS);
> +	unsigned long memcg_data = (unsigned long) objcgs | MEMCG_DATA_OBJCGS;
> +
> +	if (atomic)
> +		return !cmpxchg(&page->memcg_data, 0, memcg_data);
> +
> +	page->memcg_data = memcg_data;
> +	return true;
>  }
>  #else
>  static inline struct obj_cgroup **page_objcgs(struct page *page)
> @@ -506,7 +512,7 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page)
>  }
>  
>  static inline bool set_page_objcgs(struct page *page,
> -					struct obj_cgroup **objcgs)
> +				   struct obj_cgroup **objcgs, bool atomic)
>  {
>  	return true;
>  }
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 69a2893a6455..37bffd336235 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -2874,7 +2874,7 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg)
>  
>  #ifdef CONFIG_MEMCG_KMEM
>  int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
> -				 gfp_t gfp)
> +				 gfp_t gfp, bool atomic)
>  {
>  	unsigned int objects = objs_per_slab_page(s, page);
>  	void *vec;
> @@ -2884,7 +2884,7 @@ int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
>  	if (!vec)
>  		return -ENOMEM;
>  
> -	if (!set_page_objcgs(page, vec))
> +	if (!set_page_objcgs(page, vec, atomic))
>  		kfree(vec);
>  	else
>  		kmemleak_not_leak(vec);

The life of page->memcg_data and this optimization could use a central
comment somewhere, because it's hard to understand what's going on
from the code alone. This function here seems like a good place?

I don't see a way to eliminate the bool on the allocation function,
but maybe it could be more descriptive. Maybe bool slab_account?

set_page_objcgs() can be inlined at this point. It made some sense to
abstract away the atomics with setter and matching getter, but with a
non-atomic mode, inlining makes things clearer and allows for better
in-place documentation in the sole callsite.

How about something like this?

	vec = kcalloc(...);

	memcg_data = (unsigned long)vec | MEMCG_DATA_OBJCGS;
	/*
	 * Set up the objcg vector for the page.
	 *
	 * When only some objects in a slab are tracked (think GFP_ACCOUNT
	 * kmalloc allocations), the objcg vector is set up when the first
	 * tracked object in the slab page is allocated. Multiple concurrent
	 * slab allocations can race to this, so synchronization is required.
	 *
	 * When SLAB_ACCOUNT is set on the cache, however, all objects in the
	 * slab page will be tracked, and the vector is allocated along with
	 * the page itself, while it's still exclusive; no atomics necessary.
	 */
	if (slab_account) {
		page->memcg_data = memcg_data;
	} else {
		if (cmpxchg(&page->memcg_data, 0, memcg_data)) {
			/* Somebody else beat us, use their vec */
			kfree(vec);
			return 0;
		}
	}
	kmemleak_not_leak(vec);
	return 0;

Re: [PATCH 2/2] mm: memcg/slab: pre-allocate obj_cgroups for slab caches with SLAB_ACCOUNT

[Roman Gushchin]

On Thu, Nov 12, 2020 at 11:23:03AM -0500, Johannes Weiner wrote:
> On Tue, Nov 10, 2020 at 11:57:53AM -0800, Roman Gushchin wrote:
> > In general it's unknown in advance if a slab page will contain
> > accounted objects or not. In order to avoid memory waste, an
> > obj_cgroup vector is allocated dynamically when a need to account
> > of a new object arises. Such approach is memory efficient, but
> > requires an expensive cmpxchg() to set up the memcg/objcgs pointer,
> > because an allocation can race with a different allocation on another
> > cpu.
> > 
> > But in some common cases it's known for sure that a slab page will
> > contain accounted objects: if the page belongs to a slab cache with a
> > SLAB_ACCOUNT flag set. It includes such popular objects like
> > vm_area_struct, anon_vma, task_struct, etc.
> > 
> > In such cases we can pre-allocate the objcgs vector and simple assign
> > it to the page without any atomic operations, because at this early
> > stage the page is not visible to anyone else.
> > 
> > Signed-off-by: Roman Gushchin <guro@fb.com>
> 
> That's a nice optimization!
> 
> Some comments inline:
> 
> > @@ -485,14 +485,20 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page)
> >   * set_page_objcgs - associate a page with a object cgroups vector
> >   * @page: a pointer to the page struct
> >   * @objcgs: a pointer to the object cgroups vector
> > + * @atomic: save the value atomically
> >   *
> >   * Atomically associates a page with a vector of object cgroups.
> >   */
> >  static inline bool set_page_objcgs(struct page *page,
> > -					struct obj_cgroup **objcgs)
> > +				   struct obj_cgroup **objcgs, bool atomic)
> 
> bool parameters make callsites pretty hard to understand - unless the
> function interface obviously has two modes (read vs write etc.), which
> isn't the case here.
> 
> > -	return !cmpxchg(&page->memcg_data, 0, (unsigned long)objcgs |
> > -			MEMCG_DATA_OBJCGS);
> > +	unsigned long memcg_data = (unsigned long) objcgs | MEMCG_DATA_OBJCGS;
> > +
> > +	if (atomic)
> > +		return !cmpxchg(&page->memcg_data, 0, memcg_data);
> > +
> > +	page->memcg_data = memcg_data;
> > +	return true;
> >  }
> >  #else
> >  static inline struct obj_cgroup **page_objcgs(struct page *page)
> > @@ -506,7 +512,7 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page)
> >  }
> >  
> >  static inline bool set_page_objcgs(struct page *page,
> > -					struct obj_cgroup **objcgs)
> > +				   struct obj_cgroup **objcgs, bool atomic)
> >  {
> >  	return true;
> >  }
> > diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> > index 69a2893a6455..37bffd336235 100644
> > --- a/mm/memcontrol.c
> > +++ b/mm/memcontrol.c
> > @@ -2874,7 +2874,7 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg)
> >  
> >  #ifdef CONFIG_MEMCG_KMEM
> >  int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
> > -				 gfp_t gfp)
> > +				 gfp_t gfp, bool atomic)
> >  {
> >  	unsigned int objects = objs_per_slab_page(s, page);
> >  	void *vec;
> > @@ -2884,7 +2884,7 @@ int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
> >  	if (!vec)
> >  		return -ENOMEM;
> >  
> > -	if (!set_page_objcgs(page, vec))
> > +	if (!set_page_objcgs(page, vec, atomic))
> >  		kfree(vec);
> >  	else
> >  		kmemleak_not_leak(vec);
> 
> The life of page->memcg_data and this optimization could use a central
> comment somewhere, because it's hard to understand what's going on
> from the code alone. This function here seems like a good place?
> 
> I don't see a way to eliminate the bool on the allocation function,
> but maybe it could be more descriptive. Maybe bool slab_account?
> 
> set_page_objcgs() can be inlined at this point. It made some sense to
> abstract away the atomics with setter and matching getter, but with a
> non-atomic mode, inlining makes things clearer and allows for better
> in-place documentation in the sole callsite.

I agree, inlining makes sense here.

I'd prefer not to spill details about SLAB_ACCOUNT into memcg_alloc_page_obj_cgroups().
What's important there is only whether we have an exclusive access to the page or not.

How about the version below?

Thanks!

--

From 8b28d91475d54c552e503e66f169e1e00475c856 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Wed, 16 Sep 2020 15:43:48 -0700
Subject: [PATCH v2 2/2] mm: memcg/slab: pre-allocate obj_cgroups for slab
 caches with SLAB_ACCOUNT

In general it's unknown in advance if a slab page will contain
accounted objects or not. In order to avoid memory waste, an
obj_cgroup vector is allocated dynamically when a need to account
of a new object arises. Such approach is memory efficient, but
requires an expensive cmpxchg() to set up the memcg/objcgs pointer,
because an allocation can race with a different allocation on another
cpu.

But in some common cases it's known for sure that a slab page will
contain accounted objects: if the page belongs to a slab cache with a
SLAB_ACCOUNT flag set. It includes such popular objects like
vm_area_struct, anon_vma, task_struct, etc.

In such cases we can pre-allocate the objcgs vector and simple assign
it to the page without any atomic operations, because at this early
stage the page is not visible to anyone else.

v2: inline set_page_objcgs() and add some comments, by Johannes

Signed-off-by: Roman Gushchin <guro@fb.com>
---
 include/linux/memcontrol.h | 19 -------------------
 mm/memcontrol.c            | 23 +++++++++++++++++++----
 mm/slab.c                  |  2 +-
 mm/slab.h                  | 14 ++++++++++----
 4 files changed, 30 insertions(+), 28 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 20108e426f84..bfcdcb2d2976 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -481,19 +481,6 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page)
 	return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
 }
 
-/*
- * set_page_objcgs - associate a page with a object cgroups vector
- * @page: a pointer to the page struct
- * @objcgs: a pointer to the object cgroups vector
- *
- * Atomically associates a page with a vector of object cgroups.
- */
-static inline bool set_page_objcgs(struct page *page,
-					struct obj_cgroup **objcgs)
-{
-	return !cmpxchg(&page->memcg_data, 0, (unsigned long)objcgs |
-			MEMCG_DATA_OBJCGS);
-}
 #else
 static inline struct obj_cgroup **page_objcgs(struct page *page)
 {
@@ -504,12 +491,6 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page)
 {
 	return NULL;
 }
-
-static inline bool set_page_objcgs(struct page *page,
-					struct obj_cgroup **objcgs)
-{
-	return true;
-}
 #endif
 
 static __always_inline bool memcg_stat_item_in_bytes(int idx)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 69a2893a6455..6ca8c23d7816 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2874,9 +2874,10 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg)
 
 #ifdef CONFIG_MEMCG_KMEM
 int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
-				 gfp_t gfp)
+				 gfp_t gfp, bool new_page)
 {
 	unsigned int objects = objs_per_slab_page(s, page);
+	unsigned long memcg_data;
 	void *vec;
 
 	vec = kcalloc_node(objects, sizeof(struct obj_cgroup *), gfp,
@@ -2884,11 +2885,25 @@ int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
 	if (!vec)
 		return -ENOMEM;
 
-	if (!set_page_objcgs(page, vec))
+	memcg_data = (unsigned long) vec | MEMCG_DATA_OBJCGS;
+	if (new_page) {
+		/*
+		 * If the slab page is brand new and nobody can yet access
+		 * it's memcg_data, no synchronization is required and
+		 * memcg_data can be simply assigned.
+		 */
+		page->memcg_data = memcg_data;
+	} else if (cmpxchg(&page->memcg_data, 0, memcg_data)) {
+		/*
+		 * If the slab page is already in use, somebody can allocate
+		 * and assign obj_cgroups in parallel. In this case the existing
+		 * objcg vector should be reused.
+		 */
 		kfree(vec);
-	else
-		kmemleak_not_leak(vec);
+		return 0;
+	}
 
+	kmemleak_not_leak(vec);
 	return 0;
 }
 
diff --git a/mm/slab.c b/mm/slab.c
index c0ea4b1c7088..df0299e1d0b9 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1380,7 +1380,7 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags,
 		return NULL;
 	}
 
-	account_slab_page(page, cachep->gfporder, cachep);
+	account_slab_page(page, cachep->gfporder, cachep, flags);
 	__SetPageSlab(page);
 	/* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */
 	if (sk_memalloc_socks() && page_is_pfmemalloc(page))
diff --git a/mm/slab.h b/mm/slab.h
index c73050654b8a..59aeb0d9f11b 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -240,7 +240,7 @@ static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t fla
 
 #ifdef CONFIG_MEMCG_KMEM
 int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
-				 gfp_t gfp);
+				 gfp_t gfp, bool new_page);
 
 static inline void memcg_free_page_obj_cgroups(struct page *page)
 {
@@ -307,7 +307,8 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
 			page = virt_to_head_page(p[i]);
 
 			if (!page_objcgs(page) &&
-			    memcg_alloc_page_obj_cgroups(page, s, flags)) {
+			    memcg_alloc_page_obj_cgroups(page, s, flags,
+							 false)) {
 				obj_cgroup_uncharge(objcg, obj_full_size(s));
 				continue;
 			}
@@ -371,7 +372,8 @@ static inline struct mem_cgroup *memcg_from_slab_obj(void *ptr)
 }
 
 static inline int memcg_alloc_page_obj_cgroups(struct page *page,
-					       struct kmem_cache *s, gfp_t gfp)
+					       struct kmem_cache *s, gfp_t gfp,
+					       bool new_page)
 {
 	return 0;
 }
@@ -412,8 +414,12 @@ static inline struct kmem_cache *virt_to_cache(const void *obj)
 }
 
 static __always_inline void account_slab_page(struct page *page, int order,
-					      struct kmem_cache *s)
+					      struct kmem_cache *s,
+					      gfp_t gfp)
 {
+	if (memcg_kmem_enabled() && (s->flags & SLAB_ACCOUNT))
+		memcg_alloc_page_obj_cgroups(page, s, gfp, true);
+
 	mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
 			    PAGE_SIZE << order);
 }
-- 
2.26.2

Re: [PATCH 2/2] mm: memcg/slab: pre-allocate obj_cgroups for slab caches with SLAB_ACCOUNT

[Andrew Morton]

On Thu, 12 Nov 2020 16:19:26 -0800 Roman Gushchin <guro@fb.com> wrote:

> >From 8b28d91475d54c552e503e66f169e1e00475c856 Mon Sep 17 00:00:00 2001
> From: Roman Gushchin <guro@fb.com>
> Date: Wed, 16 Sep 2020 15:43:48 -0700
> Subject: [PATCH v2 2/2] mm: memcg/slab: pre-allocate obj_cgroups for slab
>  caches with SLAB_ACCOUNT
> 
> In general it's unknown in advance if a slab page will contain
> accounted objects or not. In order to avoid memory waste, an
> obj_cgroup vector is allocated dynamically when a need to account
> of a new object arises. Such approach is memory efficient, but
> requires an expensive cmpxchg() to set up the memcg/objcgs pointer,
> because an allocation can race with a different allocation on another
> cpu.
> 
> But in some common cases it's known for sure that a slab page will
> contain accounted objects: if the page belongs to a slab cache with a
> SLAB_ACCOUNT flag set. It includes such popular objects like
> vm_area_struct, anon_vma, task_struct, etc.
> 
> In such cases we can pre-allocate the objcgs vector and simple assign
> it to the page without any atomic operations, because at this early
> stage the page is not visible to anyone else.
> 
> v2: inline set_page_objcgs() and add some comments, by Johannes

Had me confused!  I was looking for the inlined function
set_page_objcgs().  I think "open-code" is a better term here than
"inline".

Here's the -fix:

From: Roman Gushchin <guro@fb.com>
Subject: mm-memcg-slab-pre-allocate-obj_cgroups-for-slab-caches-with-slab_account-v2

open-code set_page_objcgs() and add some comments, by Johannes

Link: https://lkml.kernel.org/r/20201113001926.GA2934489@carbon.dhcp.thefacebook.com
Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Shakeel Butt <shakeelb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 include/linux/memcontrol.h |   25 -------------------------
 mm/memcontrol.c            |   23 +++++++++++++++++++----
 mm/slab.h                  |    8 ++++----
 3 files changed, 23 insertions(+), 33 deletions(-)

--- a/include/linux/memcontrol.h~mm-memcg-slab-pre-allocate-obj_cgroups-for-slab-caches-with-slab_account-v2
+++ a/include/linux/memcontrol.h
@@ -480,25 +480,6 @@ static inline struct obj_cgroup **page_o
 	return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
 }
 
-/*
- * set_page_objcgs - associate a page with a object cgroups vector
- * @page: a pointer to the page struct
- * @objcgs: a pointer to the object cgroups vector
- * @atomic: save the value atomically
- *
- * Atomically associates a page with a vector of object cgroups.
- */
-static inline bool set_page_objcgs(struct page *page,
-				   struct obj_cgroup **objcgs, bool atomic)
-{
-	unsigned long memcg_data = (unsigned long) objcgs | MEMCG_DATA_OBJCGS;
-
-	if (atomic)
-		return !cmpxchg(&page->memcg_data, 0, memcg_data);
-
-	page->memcg_data = memcg_data;
-	return true;
-}
 #else
 static inline struct obj_cgroup **page_objcgs(struct page *page)
 {
@@ -509,12 +490,6 @@ static inline struct obj_cgroup **page_o
 {
 	return NULL;
 }
-
-static inline bool set_page_objcgs(struct page *page,
-				   struct obj_cgroup **objcgs, bool atomic)
-{
-	return true;
-}
 #endif
 
 static __always_inline bool memcg_stat_item_in_bytes(int idx)
--- a/mm/memcontrol.c~mm-memcg-slab-pre-allocate-obj_cgroups-for-slab-caches-with-slab_account-v2
+++ a/mm/memcontrol.c
@@ -2879,9 +2879,10 @@ static void commit_charge(struct page *p
 
 #ifdef CONFIG_MEMCG_KMEM
 int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
-				 gfp_t gfp, bool atomic)
+				 gfp_t gfp, bool new_page)
 {
 	unsigned int objects = objs_per_slab_page(s, page);
+	unsigned long memcg_data;
 	void *vec;
 
 	vec = kcalloc_node(objects, sizeof(struct obj_cgroup *), gfp,
@@ -2889,11 +2890,25 @@ int memcg_alloc_page_obj_cgroups(struct
 	if (!vec)
 		return -ENOMEM;
 
-	if (!set_page_objcgs(page, vec, atomic))
+	memcg_data = (unsigned long) vec | MEMCG_DATA_OBJCGS;
+	if (new_page) {
+		/*
+		 * If the slab page is brand new and nobody can yet access
+		 * it's memcg_data, no synchronization is required and
+		 * memcg_data can be simply assigned.
+		 */
+		page->memcg_data = memcg_data;
+	} else if (cmpxchg(&page->memcg_data, 0, memcg_data)) {
+		/*
+		 * If the slab page is already in use, somebody can allocate
+		 * and assign obj_cgroups in parallel. In this case the existing
+		 * objcg vector should be reused.
+		 */
 		kfree(vec);
-	else
-		kmemleak_not_leak(vec);
+		return 0;
+	}
 
+	kmemleak_not_leak(vec);
 	return 0;
 }
 
--- a/mm/slab.h~mm-memcg-slab-pre-allocate-obj_cgroups-for-slab-caches-with-slab_account-v2
+++ a/mm/slab.h
@@ -240,7 +240,7 @@ static inline bool kmem_cache_debug_flag
 
 #ifdef CONFIG_MEMCG_KMEM
 int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
-				 gfp_t gfp, bool atomic);
+				 gfp_t gfp, bool new_page);
 
 static inline void memcg_free_page_obj_cgroups(struct page *page)
 {
@@ -308,7 +308,7 @@ static inline void memcg_slab_post_alloc
 
 			if (!page_objcgs(page) &&
 			    memcg_alloc_page_obj_cgroups(page, s, flags,
-							 true)) {
+							 false)) {
 				obj_cgroup_uncharge(objcg, obj_full_size(s));
 				continue;
 			}
@@ -373,7 +373,7 @@ static inline struct mem_cgroup *memcg_f
 
 static inline int memcg_alloc_page_obj_cgroups(struct page *page,
 					       struct kmem_cache *s, gfp_t gfp,
-					       bool atomic)
+					       bool new_page)
 {
 	return 0;
 }
@@ -418,7 +418,7 @@ static __always_inline void account_slab
 					      gfp_t gfp)
 {
 	if (memcg_kmem_enabled() && (s->flags & SLAB_ACCOUNT))
-		memcg_alloc_page_obj_cgroups(page, s, gfp, false);
+		memcg_alloc_page_obj_cgroups(page, s, gfp, true);
 
 	mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
 			    PAGE_SIZE << order);
_

Re: [PATCH 2/2] mm: memcg/slab: pre-allocate obj_cgroups for slab caches with SLAB_ACCOUNT

[Roman Gushchin]

On Thu, Nov 12, 2020 at 05:12:39PM -0800, Andrew Morton wrote:
> On Thu, 12 Nov 2020 16:19:26 -0800 Roman Gushchin <guro@fb.com> wrote:
> 
> > >From 8b28d91475d54c552e503e66f169e1e00475c856 Mon Sep 17 00:00:00 2001
> > From: Roman Gushchin <guro@fb.com>
> > Date: Wed, 16 Sep 2020 15:43:48 -0700
> > Subject: [PATCH v2 2/2] mm: memcg/slab: pre-allocate obj_cgroups for slab
> >  caches with SLAB_ACCOUNT
> > 
> > In general it's unknown in advance if a slab page will contain
> > accounted objects or not. In order to avoid memory waste, an
> > obj_cgroup vector is allocated dynamically when a need to account
> > of a new object arises. Such approach is memory efficient, but
> > requires an expensive cmpxchg() to set up the memcg/objcgs pointer,
> > because an allocation can race with a different allocation on another
> > cpu.
> > 
> > But in some common cases it's known for sure that a slab page will
> > contain accounted objects: if the page belongs to a slab cache with a
> > SLAB_ACCOUNT flag set. It includes such popular objects like
> > vm_area_struct, anon_vma, task_struct, etc.
> > 
> > In such cases we can pre-allocate the objcgs vector and simple assign
> > it to the page without any atomic operations, because at this early
> > stage the page is not visible to anyone else.
> > 
> > v2: inline set_page_objcgs() and add some comments, by Johannes
> 
> Had me confused!  I was looking for the inlined function
> set_page_objcgs().  I think "open-code" is a better term here than
> "inline".

Sorry for the confusion! And thanks for picking up the new version!

Roman

Re: [PATCH 2/2] mm: memcg/slab: pre-allocate obj_cgroups for slab caches with SLAB_ACCOUNT

[Johannes Weiner]

On Thu, Nov 12, 2020 at 05:12:39PM -0800, Andrew Morton wrote:
> On Thu, 12 Nov 2020 16:19:26 -0800 Roman Gushchin <guro@fb.com> wrote:
> 
> > >From 8b28d91475d54c552e503e66f169e1e00475c856 Mon Sep 17 00:00:00 2001
> > From: Roman Gushchin <guro@fb.com>
> > Date: Wed, 16 Sep 2020 15:43:48 -0700
> > Subject: [PATCH v2 2/2] mm: memcg/slab: pre-allocate obj_cgroups for slab
> >  caches with SLAB_ACCOUNT
> > 
> > In general it's unknown in advance if a slab page will contain
> > accounted objects or not. In order to avoid memory waste, an
> > obj_cgroup vector is allocated dynamically when a need to account
> > of a new object arises. Such approach is memory efficient, but
> > requires an expensive cmpxchg() to set up the memcg/objcgs pointer,
> > because an allocation can race with a different allocation on another
> > cpu.
> > 
> > But in some common cases it's known for sure that a slab page will
> > contain accounted objects: if the page belongs to a slab cache with a
> > SLAB_ACCOUNT flag set. It includes such popular objects like
> > vm_area_struct, anon_vma, task_struct, etc.
> > 
> > In such cases we can pre-allocate the objcgs vector and simple assign
> > it to the page without any atomic operations, because at this early
> > stage the page is not visible to anyone else.
> > 
> > v2: inline set_page_objcgs() and add some comments, by Johannes
> 
> Had me confused!  I was looking for the inlined function
> set_page_objcgs().  I think "open-code" is a better term here than
> "inline".
> 
> Here's the -fix:
> 
> From: Roman Gushchin <guro@fb.com>
> Subject: mm-memcg-slab-pre-allocate-obj_cgroups-for-slab-caches-with-slab_account-v2
> 
> open-code set_page_objcgs() and add some comments, by Johannes
> 
> Link: https://lkml.kernel.org/r/20201113001926.GA2934489@carbon.dhcp.thefacebook.com
> Signed-off-by: Roman Gushchin <guro@fb.com>
> Cc: Christoph Lameter <cl@linux.com>
> Cc: Johannes Weiner <hannes@cmpxchg.org>
> Cc: Michal Hocko <mhocko@kernel.org>
> Cc: Shakeel Butt <shakeelb@google.com>
> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Thanks! For the combined patch:

Acked-by: Johannes Weiner <hannes@cmpxchg.org>

Re: [PATCH 1/2] mm: slub: call account_slab_page() after slab page initialization

[Shakeel Butt]

On Tue, Nov 10, 2020 at 11:58 AM Roman Gushchin <guro@fb.com> wrote:
>
> It's convenient to have page->objects initialized before calling
> into account_slab_page(). In particular, this information can be
> used to pre-alloc the obj_cgroup vector.
>
> Let's call account_slab_page() a bit later, after the initialization
> of page->objects.
>
> This commit doesn't bring any functional change, but is required for
> further optimizations.
>
> Signed-off-by: Roman Gushchin <guro@fb.com>

Reviewed-by: Shakeel Butt <shakeelb@google.com>

Re: [PATCH 2/2] mm: memcg/slab: pre-allocate obj_cgroups for slab caches with SLAB_ACCOUNT

[Shakeel Butt]

On Thu, Nov 12, 2020 at 4:19 PM Roman Gushchin <guro@fb.com> wrote:
>
[snip]
>
> From 8b28d91475d54c552e503e66f169e1e00475c856 Mon Sep 17 00:00:00 2001
> From: Roman Gushchin <guro@fb.com>
> Date: Wed, 16 Sep 2020 15:43:48 -0700
> Subject: [PATCH v2 2/2] mm: memcg/slab: pre-allocate obj_cgroups for slab
>  caches with SLAB_ACCOUNT
>
> In general it's unknown in advance if a slab page will contain
> accounted objects or not. In order to avoid memory waste, an
> obj_cgroup vector is allocated dynamically when a need to account
> of a new object arises. Such approach is memory efficient, but
> requires an expensive cmpxchg() to set up the memcg/objcgs pointer,
> because an allocation can race with a different allocation on another
> cpu.
>
> But in some common cases it's known for sure that a slab page will
> contain accounted objects: if the page belongs to a slab cache with a
> SLAB_ACCOUNT flag set. It includes such popular objects like
> vm_area_struct, anon_vma, task_struct, etc.
>
> In such cases we can pre-allocate the objcgs vector and simple assign
> it to the page without any atomic operations, because at this early
> stage the page is not visible to anyone else.
>
> v2: inline set_page_objcgs() and add some comments, by Johannes
>
> Signed-off-by: Roman Gushchin <guro@fb.com>
[snip]
>
>  static __always_inline void account_slab_page(struct page *page, int order,
> -                                             struct kmem_cache *s)
> +                                             struct kmem_cache *s,
> +                                             gfp_t gfp)
>  {
> +       if (memcg_kmem_enabled() && (s->flags & SLAB_ACCOUNT))
> +               memcg_alloc_page_obj_cgroups(page, s, gfp, true);
> +

I was wondering why not add (gfp & __GFP_ACCOUNT) check as well but it
seems like for that some additional plumbing is required.

Anyways:

Reviewed-by: Shakeel Butt <shakeelb@google.com>

Re: [PATCH 2/2] mm: memcg/slab: pre-allocate obj_cgroups for slab caches with SLAB_ACCOUNT

[Roman Gushchin]

On Tue, Nov 17, 2020 at 09:42:53AM -0800, Shakeel Butt wrote:
> On Thu, Nov 12, 2020 at 4:19 PM Roman Gushchin <guro@fb.com> wrote:
> >
> [snip]
> >
> > From 8b28d91475d54c552e503e66f169e1e00475c856 Mon Sep 17 00:00:00 2001
> > From: Roman Gushchin <guro@fb.com>
> > Date: Wed, 16 Sep 2020 15:43:48 -0700
> > Subject: [PATCH v2 2/2] mm: memcg/slab: pre-allocate obj_cgroups for slab
> >  caches with SLAB_ACCOUNT
> >
> > In general it's unknown in advance if a slab page will contain
> > accounted objects or not. In order to avoid memory waste, an
> > obj_cgroup vector is allocated dynamically when a need to account
> > of a new object arises. Such approach is memory efficient, but
> > requires an expensive cmpxchg() to set up the memcg/objcgs pointer,
> > because an allocation can race with a different allocation on another
> > cpu.
> >
> > But in some common cases it's known for sure that a slab page will
> > contain accounted objects: if the page belongs to a slab cache with a
> > SLAB_ACCOUNT flag set. It includes such popular objects like
> > vm_area_struct, anon_vma, task_struct, etc.
> >
> > In such cases we can pre-allocate the objcgs vector and simple assign
> > it to the page without any atomic operations, because at this early
> > stage the page is not visible to anyone else.
> >
> > v2: inline set_page_objcgs() and add some comments, by Johannes
> >
> > Signed-off-by: Roman Gushchin <guro@fb.com>
> [snip]
> >
> >  static __always_inline void account_slab_page(struct page *page, int order,
> > -                                             struct kmem_cache *s)
> > +                                             struct kmem_cache *s,
> > +                                             gfp_t gfp)
> >  {
> > +       if (memcg_kmem_enabled() && (s->flags & SLAB_ACCOUNT))
> > +               memcg_alloc_page_obj_cgroups(page, s, gfp, true);
> > +
> 
> I was wondering why not add (gfp & __GFP_ACCOUNT) check as well but it
> seems like for that some additional plumbing is required.

Yes, it's doable, but requires passing another argument through the whole stack.

> 
> Anyways:
> 
> Reviewed-by: Shakeel Butt <shakeelb@google.com>

Thank you!