[RFC PATCH] mm: memcg/slab: Stop reparented obj_cgroups from charging root
From: Richard Palethorpe
Date: Wed Oct 14 2020 - 15:09:13 EST
SLAB objects which outlive their memcg are moved to their parent
memcg where they may be uncharged. However if they are moved to the
root memcg, uncharging will result in negative page counter values as
root has no page counters.
To prevent this, we check whether we are about to uncharge the root
memcg and skip it if we are. Possibly instead; the obj_cgroups should
be removed from their slabs and any per cpu stocks instead of
reparenting them to root?
The warning can be, unreliably, reproduced with the LTP test
madvise06 if the entire patch series
https://lore.kernel.org/linux-mm/20200623174037.3951353-1-guro@xxxxxx/
is present. Although the listed commit in 'fixes' appears to introduce
the bug, I can not reproduce it with just that commit and bisecting
runs into other bugs.
[ 12.029417] WARNING: CPU: 2 PID: 21 at mm/page_counter.c:57 page_counter_uncharge (mm/page_counter.c:57 mm/page_counter.c:50 mm/page_counter.c:156)
[ 12.029539] Modules linked in:
[ 12.029611] CPU: 2 PID: 21 Comm: ksoftirqd/2 Not tainted 5.9.0-rc7-22-default #76
[ 12.029729] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-48-gd9c812d-rebuilt.opensuse.org 04/01/2014
[ 12.029908] RIP: 0010:page_counter_uncharge (mm/page_counter.c:57 mm/page_counter.c:50 mm/page_counter.c:156)
[ 12.029991] Code: 0f c1 45 00 4c 29 e0 48 89 ef 48 89 c3 48 89 c6 e8 2a fe ff ff 48 85 db 78 10 48 8b 6d 28 48 85 ed 75 d8 5b 5d 41 5c 41 5d c3 <0f> 0b eb ec 90 e8 db 47 36 27 48 8b 17 48 39 d6 72 41 41 54 49 89
[ 12.030258] RSP: 0018:ffffa5d8000efd08 EFLAGS: 00010086
[ 12.030344] RAX: ffffffffffffffff RBX: ffffffffffffffff RCX: 0000000000000009
[ 12.030455] RDX: 000000000000000b RSI: ffffffffffffffff RDI: ffff8ef8c7d2b248
[ 12.030561] RBP: ffff8ef8c7d2b248 R08: ffff8ef8c78b19c8 R09: 0000000000000001
[ 12.030672] R10: 0000000000000000 R11: ffff8ef8c780e0d0 R12: 0000000000000001
[ 12.030784] R13: ffffffffffffffff R14: ffff8ef9478b19c8 R15: 0000000000000000
[ 12.030895] FS: 0000000000000000(0000) GS:ffff8ef8fbc80000(0000) knlGS:0000000000000000
[ 12.031017] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 12.031104] CR2: 00007f72c0af93ec CR3: 000000005c40a000 CR4: 00000000000006e0
[ 12.031209] Call Trace:
[ 12.031267] __memcg_kmem_uncharge (mm/memcontrol.c:3022)
[ 12.031470] drain_obj_stock (./include/linux/rcupdate.h:689 mm/memcontrol.c:3114)
[ 12.031594] refill_obj_stock (mm/memcontrol.c:3166)
[ 12.031733] ? rcu_do_batch (kernel/rcu/tree.c:2438)
[ 12.032075] memcg_slab_free_hook (./include/linux/mm.h:1294 ./include/linux/mm.h:1441 mm/slab.h:368 mm/slab.h:348)
[ 12.032339] kmem_cache_free (mm/slub.c:3107 mm/slub.c:3143 mm/slub.c:3158)
[ 12.032464] rcu_do_batch (kernel/rcu/tree.c:2438)
[ 12.032567] rcu_core (kernel/rcu/tree_plugin.h:2122 kernel/rcu/tree_plugin.h:2157 kernel/rcu/tree.c:2661)
[ 12.032664] __do_softirq (./arch/x86/include/asm/jump_label.h:25 ./include/linux/jump_label.h:200 ./include/trace/events/irq.h:142 kernel/softirq.c:299)
[ 12.032766] run_ksoftirqd (./arch/x86/include/asm/irqflags.h:54 ./arch/x86/include/asm/irqflags.h:94 kernel/softirq.c:653 kernel/softirq.c:644)
[ 12.032852] smpboot_thread_fn (kernel/smpboot.c:165)
[ 12.032940] ? smpboot_register_percpu_thread (kernel/smpboot.c:108)
[ 12.033059] kthread (kernel/kthread.c:292)
[ 12.033148] ? __kthread_bind_mask (kernel/kthread.c:245)
[ 12.033269] ret_from_fork (arch/x86/entry/entry_64.S:300)
[ 12.033357] ---[ end trace 961dbfc01c109d1f ]---
[ 9.841552] ------------[ cut here ]------------
[ 9.841788] WARNING: CPU: 0 PID: 12 at mm/page_counter.c:57 page_counter_uncharge (mm/page_counter.c:57 mm/page_counter.c:50 mm/page_counter.c:156)
[ 9.841982] Modules linked in:
[ 9.842072] CPU: 0 PID: 12 Comm: kworker/0:1 Not tainted 5.9.0-rc7-22-default #77
[ 9.842266] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-48-gd9c812d-rebuilt.opensuse.org 04/01/2014
[ 9.842571] Workqueue: events drain_local_stock
[ 9.842750] RIP: 0010:page_counter_uncharge (mm/page_counter.c:57 mm/page_counter.c:50 mm/page_counter.c:156)
[ 9.842894] Code: 0f c1 45 00 4c 29 e0 48 89 ef 48 89 c3 48 89 c6 e8 2a fe ff ff 48 85 db 78 10 48 8b 6d 28 48 85 ed 75 d8 5b 5d 41 5c 41 5d c3 <0f> 0b eb ec 90 e8 4b f9 88 2a 48 8b 17 48 39 d6 72 41 41 54 49 89
[ 9.843438] RSP: 0018:ffffb1c18006be28 EFLAGS: 00010086
[ 9.843585] RAX: ffffffffffffffff RBX: ffffffffffffffff RCX: ffff94803bc2cae0
[ 9.843806] RDX: 0000000000000001 RSI: ffffffffffffffff RDI: ffff948007d2b248
[ 9.844026] RBP: ffff948007d2b248 R08: ffff948007c58eb0 R09: ffff948007da05ac
[ 9.844248] R10: 0000000000000018 R11: 0000000000000018 R12: 0000000000000001
[ 9.844477] R13: ffffffffffffffff R14: 0000000000000000 R15: ffff94803bc2cac0
[ 9.844696] FS: 0000000000000000(0000) GS:ffff94803bc00000(0000) knlGS:0000000000000000
[ 9.844915] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 9.845096] CR2: 00007f0579ee0384 CR3: 000000002cc0a000 CR4: 00000000000006f0
[ 9.845319] Call Trace:
[ 9.845429] __memcg_kmem_uncharge (mm/memcontrol.c:3022)
[ 9.845582] drain_obj_stock (./include/linux/rcupdate.h:689 mm/memcontrol.c:3114)
[ 9.845684] drain_local_stock (mm/memcontrol.c:2255)
[ 9.845789] process_one_work (./arch/x86/include/asm/jump_label.h:25 ./include/linux/jump_label.h:200 ./include/trace/events/workqueue.h:108 kernel/workqueue.c:2274)
[ 9.845898] worker_thread (./include/linux/list.h:282 kernel/workqueue.c:2416)
[ 9.846034] ? process_one_work (kernel/workqueue.c:2358)
[ 9.846162] kthread (kernel/kthread.c:292)
[ 9.846271] ? __kthread_bind_mask (kernel/kthread.c:245)
[ 9.846420] ret_from_fork (arch/x86/entry/entry_64.S:300)
[ 9.846531] ---[ end trace 8b5647c1eba9d18a ]---
Reported-By: ltp@xxxxxxxxxxxxxx
Signed-off-by: Richard Palethorpe <rpalethorpe@xxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Roman Gushchin <guro@xxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Shakeel Butt <shakeelb@xxxxxxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxxxx>
Cc: Tejun Heo <tj@xxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: linux-mm@xxxxxxxxx
Cc: linux-kernel@xxxxxxxxxxxxxxx
Fixes: bf4f059954dc ("mm: memcg/slab: obj_cgroup API")
---
mm/memcontrol.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6877c765b8d0..214e1fe4e9a2 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -291,7 +291,7 @@ static void obj_cgroup_release(struct percpu_ref *ref)
spin_lock_irqsave(&css_set_lock, flags);
memcg = obj_cgroup_memcg(objcg);
- if (nr_pages)
+ if (nr_pages && !mem_cgroup_is_root(memcg))
__memcg_kmem_uncharge(memcg, nr_pages);
list_del(&objcg->list);
mem_cgroup_put(memcg);
@@ -3100,6 +3100,7 @@ static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
static void drain_obj_stock(struct memcg_stock_pcp *stock)
{
struct obj_cgroup *old = stock->cached_objcg;
+ struct mem_cgroup *memcg;
if (!old)
return;
@@ -3110,7 +3111,9 @@ static void drain_obj_stock(struct memcg_stock_pcp *stock)
if (nr_pages) {
rcu_read_lock();
- __memcg_kmem_uncharge(obj_cgroup_memcg(old), nr_pages);
+ memcg = obj_cgroup_memcg(old);
+ if (!mem_cgroup_is_root(memcg))
+ __memcg_kmem_uncharge(memcg, nr_pages);
rcu_read_unlock();
}
--
2.28.0