The patch titled
Subject: mm: memcg/slab: create a new set of kmalloc-cg-<n> caches
has been added to the -mm tree. Its filename is
mm-memcg-slab-create-a-new-set-of-kmalloc-cg-n-caches.patch
This patch should soon appear at
https://ozlabs.org/~akpm/mmots/broken-out/mm-memcg-slab-create-a-new-set-of-kmalloc-cg-n-caches.patch
and later at
https://ozlabs.org/~akpm/mmotm/broken-out/mm-memcg-slab-create-a-new-set-of-kmalloc-cg-n-caches.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: Waiman Long <longman@xxxxxxxxxx>
Subject: mm: memcg/slab: create a new set of kmalloc-cg-<n> caches
There are currently two problems in the way the objcg pointer array
(memcg_data) in the page structure is being allocated and freed.
On its allocation, it is possible that the allocated objcg pointer array
comes from the same slab that requires memory accounting. If this
happens, the slab will never become empty again as there is at least one
object left (the obj_cgroup array) in the slab.
When it is freed, the objcg pointer array object may be the last one in
its slab and hence causes kfree() to be called again. With the right
workload, the slab cache may be set up in a way that allows the recursive
kfree() calling loop to nest deep enough to cause a kernel stack overflow
and panic the system.
One way to solve this problem is to split the kmalloc-<n> caches
(KMALLOC_NORMAL) into two separate sets - a new set of kmalloc-<n>
(KMALLOC_NORMAL) caches for unaccounted objects only and a new set of
kmalloc-cg-<n> (KMALLOC_CGROUP) caches for accounted objects only. All
the other caches can still allow a mix of accounted and unaccounted
objects.
With this change, all the objcg pointer array objects will come from
KMALLOC_NORMAL caches which won't have their objcg pointer arrays. So
both the recursive kfree() problem and non-freeable slab problem are gone.
Since both the KMALLOC_NORMAL and KMALLOC_CGROUP caches no longer have
mixed accounted and unaccounted objects, this will slightly reduce the
number of objcg pointer arrays that need to be allocated and save a bit of
memory. On the other hand, creating a new set of kmalloc caches does have
the effect of reducing cache utilization. So it is properly a wash.
The new KMALLOC_CGROUP is added between KMALLOC_NORMAL and KMALLOC_RECLAIM
so that the first for loop in create_kmalloc_caches() will include the
newly added caches without change.
Link: https://lkml.kernel.org/r/20210505200610.13943-3-longman@xxxxxxxxxx
Signed-off-by: Waiman Long <longman@xxxxxxxxxx>
Suggested-by: Vlastimil Babka <vbabka@xxxxxxx>
Reviewed-by: Shakeel Butt <shakeelb@xxxxxxxxxx>
Acked-by: Roman Gushchin <guro@xxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxxxx>
Cc: Pekka Enberg <penberg@xxxxxxxxxx>
Cc: Vladimir Davydov <vdavydov.dev@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/slab.h | 41 ++++++++++++++++++++++++++++++++---------
mm/slab_common.c | 25 +++++++++++++++++--------
2 files changed, 49 insertions(+), 17 deletions(-)
--- a/include/linux/slab.h~mm-memcg-slab-create-a-new-set-of-kmalloc-cg-n-caches
+++ a/include/linux/slab.h
@@ -305,12 +305,23 @@ static inline void __check_heap_object(c
/*
* Whenever changing this, take care of that kmalloc_type() and
* create_kmalloc_caches() still work as intended.
+ *
+ * KMALLOC_NORMAL can contain only unaccounted objects whereas KMALLOC_CGROUP
+ * is for accounted but unreclaimable and non-dma objects. All the other
+ * kmem caches can have both accounted and unaccounted objects.
*/
enum kmalloc_cache_type {
KMALLOC_NORMAL = 0,
+#ifdef CONFIG_MEMCG_KMEM
+ KMALLOC_CGROUP,
+#else
+ KMALLOC_CGROUP = KMALLOC_NORMAL,
+#endif
KMALLOC_RECLAIM,
#ifdef CONFIG_ZONE_DMA
KMALLOC_DMA,
+#else
+ KMALLOC_DMA = KMALLOC_NORMAL,
#endif
NR_KMALLOC_TYPES
};
@@ -319,24 +330,36 @@ enum kmalloc_cache_type {
extern struct kmem_cache *
kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1];
+/*
+ * Define gfp bits that should not be set for KMALLOC_NORMAL.
+ */
+#define KMALLOC_NOT_NORMAL_BITS \
+ (__GFP_RECLAIMABLE | \
+ (IS_ENABLED(CONFIG_ZONE_DMA) ? __GFP_DMA : 0) | \
+ (IS_ENABLED(CONFIG_MEMCG_KMEM) ? __GFP_ACCOUNT : 0))
+
static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags)
{
-#ifdef CONFIG_ZONE_DMA
/*
* The most common case is KMALLOC_NORMAL, so test for it
- * with a single branch for both flags.
+ * with a single branch for all the relevant flags.
*/
- if (likely((flags & (__GFP_DMA | __GFP_RECLAIMABLE)) == 0))
+ if (likely((flags & KMALLOC_NOT_NORMAL_BITS) == 0))
return KMALLOC_NORMAL;
/*
- * At least one of the flags has to be set. If both are, __GFP_DMA
- * is more important.
+ * At least one of the flags has to be set. Their priorities in
+ * decreasing order are:
+ * 1) __GFP_DMA
+ * 2) __GFP_RECLAIMABLE
+ * 3) __GFP_ACCOUNT
*/
- return flags & __GFP_DMA ? KMALLOC_DMA : KMALLOC_RECLAIM;
-#else
- return flags & __GFP_RECLAIMABLE ? KMALLOC_RECLAIM : KMALLOC_NORMAL;
-#endif
+ if (IS_ENABLED(CONFIG_ZONE_DMA) && (flags & __GFP_DMA))
+ return KMALLOC_DMA;
+ if (!IS_ENABLED(CONFIG_MEMCG_KMEM) || (flags & __GFP_RECLAIMABLE))
+ return KMALLOC_RECLAIM;
+ else
+ return KMALLOC_CGROUP;
}
/*
--- a/mm/slab_common.c~mm-memcg-slab-create-a-new-set-of-kmalloc-cg-n-caches
+++ a/mm/slab_common.c
@@ -737,21 +737,25 @@ struct kmem_cache *kmalloc_slab(size_t s
}
#ifdef CONFIG_ZONE_DMA
-#define INIT_KMALLOC_INFO(__size, __short_size) \
-{ \
- .name[KMALLOC_NORMAL] = "kmalloc-" #__short_size, \
- .name[KMALLOC_RECLAIM] = "kmalloc-rcl-" #__short_size, \
- .name[KMALLOC_DMA] = "dma-kmalloc-" #__short_size, \
- .size = __size, \
-}
+#define KMALLOC_DMA_NAME(sz) .name[KMALLOC_DMA] = "dma-kmalloc-" #sz,
#else
+#define KMALLOC_DMA_NAME(sz)
+#endif
+
+#ifdef CONFIG_MEMCG_KMEM
+#define KMALLOC_CGROUP_NAME(sz) .name[KMALLOC_CGROUP] = "kmalloc-cg-" #sz,
+#else
+#define KMALLOC_CGROUP_NAME(sz)
+#endif
+
#define INIT_KMALLOC_INFO(__size, __short_size) \
{ \
.name[KMALLOC_NORMAL] = "kmalloc-" #__short_size, \
.name[KMALLOC_RECLAIM] = "kmalloc-rcl-" #__short_size, \
+ KMALLOC_CGROUP_NAME(__short_size) \
+ KMALLOC_DMA_NAME(__short_size) \
.size = __size, \
}
-#endif
/*
* kmalloc_info[] is to make slub_debug=,kmalloc-xx option work at boot time.
@@ -840,6 +844,8 @@ new_kmalloc_cache(int idx, enum kmalloc_
{
if (type == KMALLOC_RECLAIM)
flags |= SLAB_RECLAIM_ACCOUNT;
+ else if (IS_ENABLED(CONFIG_MEMCG_KMEM) && (type == KMALLOC_CGROUP))
+ flags |= SLAB_ACCOUNT;
kmalloc_caches[type][idx] = create_kmalloc_cache(
kmalloc_info[idx].name[type],
@@ -857,6 +863,9 @@ void __init create_kmalloc_caches(slab_f
int i;
enum kmalloc_cache_type type;
+ /*
+ * Including KMALLOC_CGROUP if CONFIG_MEMCG_KMEM defined
+ */
for (type = KMALLOC_NORMAL; type <= KMALLOC_RECLAIM; type++) {
for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) {
if (!kmalloc_caches[type][i])
_
Patches currently in -mm which might be from longman@xxxxxxxxxx are
mm-memcg-move-mod_objcg_state-to-memcontrolc.patch
mm-memcg-cache-vmstat-data-in-percpu-memcg_stock_pcp.patch
mm-memcg-improve-refill_obj_stock-performance.patch
mm-memcg-optimize-user-context-object-stock-access.patch
mm-memcg-slab-properly-set-up-gfp-flags-for-objcg-pointer-array.patch
mm-memcg-slab-create-a-new-set-of-kmalloc-cg-n-caches.patch
mm-memcg-slab-disable-cache-merging-for-kmalloc_normal-caches.patch
