linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Roman Gushchin <guro@fb.com>
To: Andrew Morton <akpm@linux-foundation.org>,
	Christoph Lameter <cl@linux.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>,
	Michal Hocko <mhocko@kernel.org>,
	Shakeel Butt <shakeelb@google.com>, <linux-mm@kvack.org>,
	Vlastimil Babka <vbabka@suse.cz>, <kernel-team@fb.com>,
	<linux-kernel@vger.kernel.org>, Roman Gushchin <guro@fb.com>
Subject: [PATCH v7 07/19] mm: memcg/slab: allocate obj_cgroups for non-root slab pages
Date: Mon, 22 Jun 2020 18:58:34 -0700	[thread overview]
Message-ID: <20200623015846.1141975-8-guro@fb.com> (raw)
In-Reply-To: <20200623015846.1141975-1-guro@fb.com>

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.

This commit temporarily increases the memory footprint of the kernel memory
accounting. To store obj_cgroup pointers we'll need a place for an
objcg_pointer for each allocated object. However, the following patches
in the series will enable sharing of slab pages between memory cgroups,
which will dramatically increase the total slab utilization. And the final
memory footprint will be significantly smaller than before.

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. The original obj_cgroups
pointer is marked to be ignored by kmemleak, which otherwise would
report a memory leak for each allocated vector.

Signed-off-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
---
 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                | 52 ++++++++++++++++++++++++++++++++++++++++
 5 files changed, 81 insertions(+), 4 deletions(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 64ede5f150dc..0277fbab7c93 100644
--- a/include/linux/mm_types.h
+++ b/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
 
 	/*
diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index abc7de77b988..ccda7b9669a5 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -114,4 +114,10 @@ static inline unsigned int obj_to_index(const struct kmem_cache *cache,
 	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 */
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 30e91c83d401..f87302dcfe8c 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -198,4 +198,9 @@ static inline unsigned int obj_to_index(const struct kmem_cache *cache,
 	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 */
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 407f90f7a2f7..60e3f3ca75ca 100644
--- a/mm/memcontrol.c
+++ b/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)
diff --git a/mm/slab.h b/mm/slab.h
index 1e2d80991904..7d175c2f1a61 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -109,6 +109,7 @@ struct memcg_cache_params {
 #include <linux/kmemleak.h>
 #include <linux/random.h>
 #include <linux/sched/mm.h>
+#include <linux/kmemleak.h>
 
 /*
  * State of the slab allocator.
@@ -347,6 +348,18 @@ static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
 	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,
@@ -434,6 +447,28 @@ static __always_inline void memcg_uncharge_slab(struct page *page, int order,
 	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_node(objects, sizeof(struct obj_cgroup *), gfp,
+			   page_to_nid(page));
+	if (!vec)
+		return -ENOMEM;
+
+	kmemleak_not_leak(vec);
+	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);
 
@@ -483,6 +518,16 @@ static inline void memcg_uncharge_slab(struct page *page, int order,
 {
 }
 
+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)
 {
 }
@@ -509,12 +554,18 @@ static __always_inline int charge_slab_page(struct page *page,
 					    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);
 }
 
@@ -527,6 +578,7 @@ static __always_inline void uncharge_slab_page(struct page *page, int order,
 		return;
 	}
 
+	memcg_free_page_obj_cgroups(page);
 	memcg_uncharge_slab(page, order, s);
 }
 
-- 
2.26.2



  parent reply	other threads:[~2020-06-23  1:59 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-06-23  1:58 [PATCH v7 00/19] The new cgroup slab memory controller Roman Gushchin
2020-06-23  1:58 ` [PATCH v7 01/19] mm: memcg: factor out memcg- and lruvec-level changes out of __mod_lruvec_state() Roman Gushchin
2020-06-23  1:58 ` [PATCH v7 02/19] mm: memcg: prepare for byte-sized vmstat items Roman Gushchin
2020-06-23  1:58 ` [PATCH v7 03/19] mm: memcg: convert vmstat slab counters to bytes Roman Gushchin
2020-06-23  1:58 ` [PATCH v7 04/19] mm: slub: implement SLUB version of obj_to_index() Roman Gushchin
2020-06-23  1:58 ` [PATCH v7 05/19] mm: memcontrol: decouple reference counting from page accounting Roman Gushchin
2020-06-23  1:58 ` [PATCH v7 06/19] mm: memcg/slab: obj_cgroup API Roman Gushchin
2020-06-23  1:58 ` Roman Gushchin [this message]
2020-06-23  1:58 ` [PATCH v7 08/19] mm: memcg/slab: save obj_cgroup for non-root slab objects Roman Gushchin
2020-06-23  1:58 ` [PATCH v7 09/19] mm: memcg/slab: charge individual slab objects instead of pages Roman Gushchin
2020-06-23  5:19   ` Shakeel Butt
2020-06-23  1:58 ` [PATCH v7 10/19] mm: memcg/slab: deprecate memory.kmem.slabinfo Roman Gushchin
2020-06-23  1:58 ` [PATCH v7 11/19] mm: memcg/slab: move memcg_kmem_bypass() to memcontrol.h Roman Gushchin
2020-06-23  1:58 ` [PATCH v7 12/19] mm: memcg/slab: use a single set of kmem_caches for all accounted allocations Roman Gushchin
2020-06-23  1:58 ` [PATCH v7 13/19] mm: memcg/slab: simplify memcg cache creation Roman Gushchin
2020-06-23  1:58 ` [PATCH v7 14/19] mm: memcg/slab: remove memcg_kmem_get_cache() Roman Gushchin
2020-06-23  1:58 ` [PATCH v7 15/19] mm: memcg/slab: deprecate slab_root_caches Roman Gushchin
2020-06-23  1:58 ` [PATCH v7 16/19] mm: memcg/slab: remove redundant check in memcg_accumulate_slabinfo() Roman Gushchin
2020-06-23  1:58 ` [PATCH v7 17/19] mm: memcg/slab: use a single set of kmem_caches for all allocations Roman Gushchin
2020-06-23  5:25   ` Shakeel Butt
2020-06-23  1:58 ` [PATCH v7 18/19] kselftests: cgroup: add kernel memory accounting tests Roman Gushchin
2020-06-23  1:58 ` [PATCH v7 19/19] tools/cgroup: add memcg_slabinfo.py tool Roman Gushchin
2020-06-23 13:53 ` [PATCH v7 00/19] The new cgroup slab memory controller Vlastimil Babka
2020-06-23 15:39   ` Roman Gushchin
2020-06-23 17:40 Roman Gushchin
2020-06-23 17:40 ` [PATCH v7 07/19] mm: memcg/slab: allocate obj_cgroups for non-root slab pages Roman Gushchin

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200623015846.1141975-8-guro@fb.com \
    --to=guro@fb.com \
    --cc=akpm@linux-foundation.org \
    --cc=cl@linux.com \
    --cc=hannes@cmpxchg.org \
    --cc=kernel-team@fb.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@kernel.org \
    --cc=shakeelb@google.com \
    --cc=vbabka@suse.cz \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).