The patch titled
Subject: mm-memcg-slab-pre-allocate-obj_cgroups-for-slab-caches-with-slab_account-v2
has been added to the -mm tree. Its filename is
mm-memcg-slab-pre-allocate-obj_cgroups-for-slab-caches-with-slab_account-v2.patch
This patch should soon appear at
https://ozlabs.org/~akpm/mmots/broken-out/mm-memcg-slab-pre-allocate-obj_cgroups-for-slab-caches-with-slab_account-v2.patch
and later at
https://ozlabs.org/~akpm/mmotm/broken-out/mm-memcg-slab-pre-allocate-obj_cgroups-for-slab-caches-with-slab_account-v2.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
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);
_
Patches currently in -mm which might be from guro@xxxxxx are
mm-memcontrol-use-helpers-to-read-pages-memcg-data.patch
mm-memcontrol-slab-use-helpers-to-access-slab-pages-memcg_data.patch
mm-introduce-page-memcg-flags.patch
mm-convert-page-kmemcg-type-to-a-page-memcg-flag.patch
mm-memcg-fix-obsolete-code-comments.patch
mm-slub-call-account_slab_page-after-slab-page-initialization.patch
mm-memcg-slab-pre-allocate-obj_cgroups-for-slab-caches-with-slab_account.patch
mm-memcg-slab-pre-allocate-obj_cgroups-for-slab-caches-with-slab_account-v2.patch
mm-memcg-deprecate-the-non-hierarchical-mode.patch
docs-cgroup-v1-reflect-the-deprecation-of-the-non-hierarchical-mode.patch
cgroup-remove-obsoleted-broken_hierarchy-and-warned_broken_hierarchy.patch
mm-vmstat-fix-proc-sys-vm-stat_refresh-generating-false-warnings.patch
mm-vmstat-fix-proc-sys-vm-stat_refresh-generating-false-warnings-fix.patch
