The patch titled
Subject: mm: memcg/slab: allocate obj_cgroups for non-root slab pages
has been added to the -mm tree. Its filename is
mm-memcg-slab-allocate-obj_cgroups-for-non-root-slab-pages.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-memcg-slab-allocate-obj_cgroups-for-non-root-slab-pages.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-memcg-slab-allocate-obj_cgroups-for-non-root-slab-pages.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: allocate obj_cgroups for non-root slab pages
Allocate and release memory to store obj_cgroup pointers for each non-root
slab page. Reuse page->mem_cgroup pointer to store a pointer to the
allocated space.
To distinguish between obj_cgroups and memcg pointers in case when it's
not obvious which one is used (as in page_cgroup_ino()), let's always set
the lowest bit in the obj_cgroup case.
Link: http://lkml.kernel.org/r/20200608230654.828134-8-guro@xxxxxx
Signed-off-by: Roman Gushchin <guro@xxxxxx>
Reviewed-by: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxxxx>
Cc: Pekka Enberg <penberg@xxxxxxxxxx>
Cc: Shakeel Butt <shakeelb@xxxxxxxxxx>
Cc: Tejun Heo <tj@xxxxxxxxxx>
Cc: Tobin C. Harding <tobin@xxxxxxxxxx>
Cc: Waiman Long <longman@xxxxxxxxxx>
Cc: Dennis Zhou <dennis@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/mm_types.h | 5 +++
include/linux/slab_def.h | 6 ++++
include/linux/slub_def.h | 5 +++
mm/memcontrol.c | 17 ++++++++++--
mm/slab.h | 49 +++++++++++++++++++++++++++++++++++++
5 files changed, 78 insertions(+), 4 deletions(-)
--- a/include/linux/mm_types.h~mm-memcg-slab-allocate-obj_cgroups-for-non-root-slab-pages
+++ a/include/linux/mm_types.h
@@ -198,7 +198,10 @@ struct page {
atomic_t _refcount;
#ifdef CONFIG_MEMCG
- struct mem_cgroup *mem_cgroup;
+ union {
+ struct mem_cgroup *mem_cgroup;
+ struct obj_cgroup **obj_cgroups;
+ };
#endif
/*
--- a/include/linux/slab_def.h~mm-memcg-slab-allocate-obj_cgroups-for-non-root-slab-pages
+++ a/include/linux/slab_def.h
@@ -114,4 +114,10 @@ static inline unsigned int obj_to_index(
return reciprocal_divide(offset, cache->reciprocal_buffer_size);
}
+static inline int objs_per_slab_page(const struct kmem_cache *cache,
+ const struct page *page)
+{
+ return cache->num;
+}
+
#endif /* _LINUX_SLAB_DEF_H */
--- a/include/linux/slub_def.h~mm-memcg-slab-allocate-obj_cgroups-for-non-root-slab-pages
+++ a/include/linux/slub_def.h
@@ -198,4 +198,9 @@ static inline unsigned int obj_to_index(
return __obj_to_index(cache, page_address(page), obj);
}
+static inline int objs_per_slab_page(const struct kmem_cache *cache,
+ const struct page *page)
+{
+ return page->objects;
+}
#endif /* _LINUX_SLUB_DEF_H */
--- a/mm/memcontrol.c~mm-memcg-slab-allocate-obj_cgroups-for-non-root-slab-pages
+++ a/mm/memcontrol.c
@@ -569,10 +569,21 @@ ino_t page_cgroup_ino(struct page *page)
unsigned long ino = 0;
rcu_read_lock();
- if (PageSlab(page) && !PageTail(page))
+ if (PageSlab(page) && !PageTail(page)) {
memcg = memcg_from_slab_page(page);
- else
- memcg = READ_ONCE(page->mem_cgroup);
+ } else {
+ memcg = page->mem_cgroup;
+
+ /*
+ * The lowest bit set means that memcg isn't a valid
+ * memcg pointer, but a obj_cgroups pointer.
+ * In this case the page is shared and doesn't belong
+ * to any specific memory cgroup.
+ */
+ if ((unsigned long) memcg & 0x1UL)
+ memcg = NULL;
+ }
+
while (memcg && !(memcg->css.flags & CSS_ONLINE))
memcg = parent_mem_cgroup(memcg);
if (memcg)
--- a/mm/slab.h~mm-memcg-slab-allocate-obj_cgroups-for-non-root-slab-pages
+++ a/mm/slab.h
@@ -319,6 +319,18 @@ static inline struct kmem_cache *memcg_r
return s->memcg_params.root_cache;
}
+static inline struct obj_cgroup **page_obj_cgroups(struct page *page)
+{
+ /*
+ * page->mem_cgroup and page->obj_cgroups are sharing the same
+ * space. To distinguish between them in case we don't know for sure
+ * that the page is a slab page (e.g. page_cgroup_ino()), let's
+ * always set the lowest bit of obj_cgroups.
+ */
+ return (struct obj_cgroup **)
+ ((unsigned long)page->obj_cgroups & ~0x1UL);
+}
+
/*
* Expects a pointer to a slab page. Please note, that PageSlab() check
* isn't sufficient, as it returns true also for tail compound slab pages,
@@ -406,6 +418,26 @@ static __always_inline void memcg_unchar
percpu_ref_put_many(&s->memcg_params.refcnt, nr_pages);
}
+static inline int memcg_alloc_page_obj_cgroups(struct page *page,
+ struct kmem_cache *s, gfp_t gfp)
+{
+ unsigned int objects = objs_per_slab_page(s, page);
+ void *vec;
+
+ vec = kcalloc(objects, sizeof(struct obj_cgroup *), gfp);
+ if (!vec)
+ return -ENOMEM;
+
+ page->obj_cgroups = (struct obj_cgroup **) ((unsigned long)vec | 0x1UL);
+ return 0;
+}
+
+static inline void memcg_free_page_obj_cgroups(struct page *page)
+{
+ kfree(page_obj_cgroups(page));
+ page->obj_cgroups = NULL;
+}
+
extern void slab_init_memcg_params(struct kmem_cache *);
extern void memcg_link_cache(struct kmem_cache *s, struct mem_cgroup *memcg);
@@ -455,6 +487,16 @@ static inline void memcg_uncharge_slab(s
{
}
+static inline int memcg_alloc_page_obj_cgroups(struct page *page,
+ struct kmem_cache *s, gfp_t gfp)
+{
+ return 0;
+}
+
+static inline void memcg_free_page_obj_cgroups(struct page *page)
+{
+}
+
static inline void slab_init_memcg_params(struct kmem_cache *s)
{
}
@@ -481,12 +523,18 @@ static __always_inline int charge_slab_p
gfp_t gfp, int order,
struct kmem_cache *s)
{
+ int ret;
+
if (is_root_cache(s)) {
mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
PAGE_SIZE << order);
return 0;
}
+ ret = memcg_alloc_page_obj_cgroups(page, s, gfp);
+ if (ret)
+ return ret;
+
return memcg_charge_slab(page, gfp, order, s);
}
@@ -499,6 +547,7 @@ static __always_inline void uncharge_sla
return;
}
+ memcg_free_page_obj_cgroups(page);
memcg_uncharge_slab(page, order, s);
}
_
Patches currently in -mm which might be from guro@xxxxxx are
mm-memcg-factor-out-memcg-and-lruvec-level-changes-out-of-__mod_lruvec_state.patch
mm-memcg-prepare-for-byte-sized-vmstat-items.patch
mm-memcg-convert-vmstat-slab-counters-to-bytes.patch
mm-slub-implement-slub-version-of-obj_to_index.patch
mm-memcg-slab-obj_cgroup-api.patch
mm-memcg-slab-allocate-obj_cgroups-for-non-root-slab-pages.patch
mm-memcg-slab-save-obj_cgroup-for-non-root-slab-objects.patch
mm-memcg-slab-charge-individual-slab-objects-instead-of-pages.patch
mm-memcg-slab-deprecate-memorykmemslabinfo.patch
mm-memcg-slab-move-memcg_kmem_bypass-to-memcontrolh.patch
mm-memcg-slab-use-a-single-set-of-kmem_caches-for-all-accounted-allocations.patch
mm-memcg-slab-simplify-memcg-cache-creation.patch
mm-memcg-slab-remove-memcg_kmem_get_cache.patch
mm-memcg-slab-deprecate-slab_root_caches.patch
mm-memcg-slab-remove-redundant-check-in-memcg_accumulate_slabinfo.patch
mm-memcg-slab-use-a-single-set-of-kmem_caches-for-all-allocations.patch
kselftests-cgroup-add-kernel-memory-accounting-tests.patch
tools-cgroup-add-memcg_slabinfopy-tool.patch
percpu-return-number-of-released-bytes-from-pcpu_free_area.patch
mm-memcg-percpu-account-percpu-memory-to-memory-cgroups.patch
mm-memcg-percpu-per-memcg-percpu-memory-statistics.patch
mm-memcg-charge-memcg-percpu-memory-to-the-parent-cgroup.patch
kselftests-cgroup-add-perpcu-memory-accounting-test.patch
