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

From: Andrew Morton
Date: Thu Nov 12 2020 - 20:12:43 EST


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

> >From 8b28d91475d54c552e503e66f169e1e00475c856 Mon Sep 17 00:00:00 2001
> From: Roman Gushchin <guro@xxxxxx>
> 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@xxxxxx>
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@xxxxxxxxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Roman Gushchin <guro@xxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxxxx>
Cc: Shakeel Butt <shakeelb@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---

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);
_