From: Mike Galbraith <umgwanakikbuti@gmail.com>
Date: Sat, 21 Jun 2014 10:09:48 +0200
Subject: memcontrol: Prevent scheduling while atomic in cgroup code
Git-repo: git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-rt-devel.git
Git-commit: c77c1cd836bd3d2d4f791bfc5026ddb2140f7792
Patch-mainline: Queued in subsystem maintainer repository
References: SLE Realtime Extension
mm, memcg: make refill_stock() use get_cpu_light()
Nikita reported the following memcg scheduling while atomic bug:
Call Trace:
[e22d5a90] [c0007ea8] show_stack+0x4c/0x168 (unreliable)
[e22d5ad0] [c0618c04] __schedule_bug+0x94/0xb0
[e22d5ae0] [c060b9ec] __schedule+0x530/0x550
[e22d5bf0] [c060bacc] schedule+0x30/0xbc
[e22d5c00] [c060ca24] rt_spin_lock_slowlock+0x180/0x27c
[e22d5c70] [c00b39dc] res_counter_uncharge_until+0x40/0xc4
[e22d5ca0] [c013ca88] drain_stock.isra.20+0x54/0x98
[e22d5cc0] [c01402ac] __mem_cgroup_try_charge+0x2e8/0xbac
[e22d5d70] [c01410d4] mem_cgroup_charge_common+0x3c/0x70
[e22d5d90] [c0117284] __do_fault+0x38c/0x510
[e22d5df0] [c011a5f4] handle_pte_fault+0x98/0x858
[e22d5e50] [c060ed08] do_page_fault+0x42c/0x6fc
[e22d5f40] [c000f5b4] handle_page_fault+0xc/0x80
What happens:
refill_stock()
get_cpu_var()
drain_stock()
res_counter_uncharge()
res_counter_uncharge_until()
spin_lock() <== boom
Fix it by replacing get/put_cpu_var() with get/put_cpu_light().
Reported-by: Nikita Yushchenko <nyushchenko@dev.rtsoft.ru>
Signed-off-by: Mike Galbraith <umgwanakikbuti@gmail.com>
[bigeasy: use memcg_stock_ll as a locallock since it is now IRQ-off region]
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Mike Galbraith <mgalbraith@suse.de>
---
mm/memcontrol.c | 13 +++++++------
1 file changed, 7 insertions(+), 6 deletions(-)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1702,6 +1702,7 @@ struct memcg_stock_pcp {
#define FLUSHING_CACHED_CHARGE 0
};
static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock);
+static DEFINE_LOCAL_IRQ_LOCK(memcg_stock_ll);
static DEFINE_MUTEX(percpu_charge_mutex);
/**
@@ -1724,7 +1725,7 @@ static bool consume_stock(struct mem_cgr
if (nr_pages > CHARGE_BATCH)
return ret;
- local_irq_save(flags);
+ local_lock_irqsave(memcg_stock_ll, flags);
stock = this_cpu_ptr(&memcg_stock);
if (memcg == stock->cached && stock->nr_pages >= nr_pages) {
@@ -1732,7 +1733,7 @@ static bool consume_stock(struct mem_cgr
ret = true;
}
- local_irq_restore(flags);
+ local_unlock_irqrestore(memcg_stock_ll, flags);
return ret;
}
@@ -1759,13 +1760,13 @@ static void drain_local_stock(struct wor
struct memcg_stock_pcp *stock;
unsigned long flags;
- local_irq_save(flags);
+ local_lock_irqsave(memcg_stock_ll, flags);
stock = this_cpu_ptr(&memcg_stock);
drain_stock(stock);
clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags);
- local_irq_restore(flags);
+ local_unlock_irqrestore(memcg_stock_ll, flags);
}
/*
@@ -1777,7 +1778,7 @@ static void refill_stock(struct mem_cgro
struct memcg_stock_pcp *stock;
unsigned long flags;
- local_irq_save(flags);
+ local_lock_irqsave(memcg_stock_ll, flags);
stock = this_cpu_ptr(&memcg_stock);
if (stock->cached != memcg) { /* reset if necessary */
@@ -1786,7 +1787,7 @@ static void refill_stock(struct mem_cgro
}
stock->nr_pages += nr_pages;
- local_irq_restore(flags);
+ local_unlock_irqrestore(memcg_stock_ll, flags);
}
/*