summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJiri Slaby <jslaby@suse.cz>2019-05-31 22:30:26 -0700
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2019-06-11 12:24:10 +0200
commit7a47d18731205a1659359083ef75e001e20cd648 (patch)
tree54043d0e6a5fd4b0b3917242a09972d36a1516b3
parent5db0a9c3cc525a57e0caa0f8d4d29ca845adc9e6 (diff)
memcg: make it work on sparse non-0-node systems
commit 3e8589963773a5c23e2f1fe4bcad0e9a90b7f471 upstream. We have a single node system with node 0 disabled: Scanning NUMA topology in Northbridge 24 Number of physical nodes 2 Skipping disabled node 0 Node 1 MemBase 0000000000000000 Limit 00000000fbff0000 NODE_DATA(1) allocated [mem 0xfbfda000-0xfbfeffff] This causes crashes in memcg when system boots: BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 #PF error: [normal kernel read fault] ... RIP: 0010:list_lru_add+0x94/0x170 ... Call Trace: d_lru_add+0x44/0x50 dput.part.34+0xfc/0x110 __fput+0x108/0x230 task_work_run+0x9f/0xc0 exit_to_usermode_loop+0xf5/0x100 It is reproducible as far as 4.12. I did not try older kernels. You have to have a new enough systemd, e.g. 241 (the reason is unknown -- was not investigated). Cannot be reproduced with systemd 234. The system crashes because the size of lru array is never updated in memcg_update_all_list_lrus and the reads are past the zero-sized array, causing dereferences of random memory. The root cause are list_lru_memcg_aware checks in the list_lru code. The test in list_lru_memcg_aware is broken: it assumes node 0 is always present, but it is not true on some systems as can be seen above. So fix this by avoiding checks on node 0. Remember the memcg-awareness by a bool flag in struct list_lru. Link: http://lkml.kernel.org/r/20190522091940.3615-1-jslaby@suse.cz Fixes: 60d3fd32a7a9 ("list_lru: introduce per-memcg lists") Signed-off-by: Jiri Slaby <jslaby@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Suggested-by: Vladimir Davydov <vdavydov.dev@gmail.com> Acked-by: Vladimir Davydov <vdavydov.dev@gmail.com> Reviewed-by: Shakeel Butt <shakeelb@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-rw-r--r--include/linux/list_lru.h1
-rw-r--r--mm/list_lru.c8
2 files changed, 4 insertions, 5 deletions
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index 743b34f56f2b..f9a8889e134a 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -51,6 +51,7 @@ struct list_lru {
struct list_lru_node *node;
#ifdef CONFIG_MEMCG_KMEM
struct list_head list;
+ bool memcg_aware;
#endif
};
diff --git a/mm/list_lru.c b/mm/list_lru.c
index 786176b1a0ee..732a066e3d3a 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -42,11 +42,7 @@ static void list_lru_unregister(struct list_lru *lru)
#ifdef CONFIG_MEMCG_KMEM
static inline bool list_lru_memcg_aware(struct list_lru *lru)
{
- /*
- * This needs node 0 to be always present, even
- * in the systems supporting sparse numa ids.
- */
- return !!lru->node[0].memcg_lrus;
+ return lru->memcg_aware;
}
static inline struct list_lru_one *
@@ -389,6 +385,8 @@ static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware)
{
int i;
+ lru->memcg_aware = memcg_aware;
+
if (!memcg_aware)
return 0;