res_counter_charge/uncharge are called where the thread can sleep and IRQ is
disabled. When enabling DEBUG_ATOMIC_SLEEP and running ksm03, which is a
test case about Kernel Samepage Merging for Memory Resource Controller,
rt kernel reports below BUG.
BUG: sleeping function called from invalid context at kernel/rtmutex.c:646
in_atomic(): 1, irqs_disabled(): 0, pid: 17730, name: ksm03
Pid: 17730, comm: ksm03 Tainted: G WC 3.4.10-rt17 #8
Call Trace:
[<ffffffff8106708c>] __might_sleep+0xcc/0xf0
[<ffffffff817adc24>] rt_spin_lock+0x24/0x50
[<ffffffff810a14c2>] res_counter_uncharge_until+0x32/0x60
[<ffffffff8113abf2>] drain_stock.isra.13+0x62/0xa0
[<ffffffff8113ac60>] drain_local_stock+0x30/0x40
[<ffffffff8113ade4>] drain_all_stock+0x174/0x190
[<ffffffff8113f0d1>] mem_cgroup_force_empty+0xd1/0x5e0
[<ffffffff817b1dbd>] ? sub_preempt_count+0x9d/0xd0
[<ffffffff81069e97>] ? migrate_enable+0x87/0x1b0
[<ffffffff8113f5f4>] mem_cgroup_pre_destroy+0x14/0x20
[<ffffffff8109b2fe>] cgroup_rmdir+0xbe/0x560
[<ffffffff8105a1d0>] ? __init_waitqueue_head+0x50/0x50
[<ffffffff81152665>] vfs_rmdir+0xd5/0x140
[<ffffffff811527db>] do_rmdir+0x10b/0x120
[<ffffffff81153f66>] sys_rmdir+0x16/0x20
[<ffffffff817b5812>] system_call_fastpath+0x16/0x1b
Since res_counter is not in hot paths and the lock is not held for long time,
replace res_counter rt spin lock to raw spin lock to avoid the BUG report.
Signed-off-by: Yang Shi <yang.shi@xxxxxxxxxxxxx>
---
include/linux/res_counter.h | 26 +++++++++++++-------------
kernel/res_counter.c | 26 +++++++++++++-------------
2 files changed, 26 insertions(+), 26 deletions(-)
diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h
index da81af0..b4cfd6b 100644
--- a/include/linux/res_counter.h
+++ b/include/linux/res_counter.h
@@ -46,7 +46,7 @@ struct res_counter {
* the lock to protect all of the above.
* the routines below consider this to be IRQ-safe
*/
- spinlock_t lock;
+ raw_spinlock_t lock;
/*
* Parent counter, used for hierarchial resource accounting
*/
@@ -147,12 +147,12 @@ static inline unsigned long long res_counter_margin(struct res_counter *cnt)
unsigned long long margin;
unsigned long flags;
- spin_lock_irqsave(&cnt->lock, flags);
+ raw_spin_lock_irqsave(&cnt->lock, flags);
if (cnt->limit > cnt->usage)
margin = cnt->limit - cnt->usage;
else
margin = 0;
- spin_unlock_irqrestore(&cnt->lock, flags);
+ raw_spin_unlock_irqrestore(&cnt->lock, flags);
return margin;
}
@@ -169,12 +169,12 @@ res_counter_soft_limit_excess(struct res_counter *cnt)
unsigned long long excess;
unsigned long flags;
- spin_lock_irqsave(&cnt->lock, flags);
+ raw_spin_lock_irqsave(&cnt->lock, flags);
if (cnt->usage <= cnt->soft_limit)
excess = 0;
else
excess = cnt->usage - cnt->soft_limit;
- spin_unlock_irqrestore(&cnt->lock, flags);
+ raw_spin_unlock_irqrestore(&cnt->lock, flags);
return excess;
}
@@ -182,18 +182,18 @@ static inline void res_counter_reset_max(struct res_counter *cnt)
{
unsigned long flags;
- spin_lock_irqsave(&cnt->lock, flags);
+ raw_spin_lock_irqsave(&cnt->lock, flags);
cnt->max_usage = cnt->usage;
- spin_unlock_irqrestore(&cnt->lock, flags);
+ raw_spin_unlock_irqrestore(&cnt->lock, flags);
}
static inline void res_counter_reset_failcnt(struct res_counter *cnt)
{
unsigned long flags;
- spin_lock_irqsave(&cnt->lock, flags);
+ raw_spin_lock_irqsave(&cnt->lock, flags);
cnt->failcnt = 0;
- spin_unlock_irqrestore(&cnt->lock, flags);
+ raw_spin_unlock_irqrestore(&cnt->lock, flags);
}
static inline int res_counter_set_limit(struct res_counter *cnt,
@@ -202,12 +202,12 @@ static inline int res_counter_set_limit(struct res_counter *cnt,
unsigned long flags;
int ret = -EBUSY;
- spin_lock_irqsave(&cnt->lock, flags);
+ raw_spin_lock_irqsave(&cnt->lock, flags);
if (cnt->usage <= limit) {
cnt->limit = limit;
ret = 0;
}
- spin_unlock_irqrestore(&cnt->lock, flags);
+ raw_spin_unlock_irqrestore(&cnt->lock, flags);
return ret;
}
@@ -217,9 +217,9 @@ res_counter_set_soft_limit(struct res_counter *cnt,
{
unsigned long flags;
- spin_lock_irqsave(&cnt->lock, flags);
+ raw_spin_lock_irqsave(&cnt->lock, flags);
cnt->soft_limit = soft_limit;
- spin_unlock_irqrestore(&cnt->lock, flags);
+ raw_spin_unlock_irqrestore(&cnt->lock, flags);
return 0;
}
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index 402f91a..540ce63 100644
--- a/kernel/res_counter.c
+++ b/kernel/res_counter.c
@@ -16,7 +16,7 @@
void res_counter_init(struct res_counter *counter, struct res_counter *parent)
{
- spin_lock_init(&counter->lock);
+ raw_spin_lock_init(&counter->lock);
counter->limit = RESOURCE_MAX;
counter->soft_limit = RESOURCE_MAX;
counter->parent = parent;
@@ -45,9 +45,9 @@ int res_counter_charge(struct res_counter *counter, unsigned long val,
*limit_fail_at = NULL;
local_irq_save_nort(flags);
for (c = counter; c != NULL; c = c->parent) {
- spin_lock(&c->lock);
+ raw_spin_lock(&c->lock);
ret = res_counter_charge_locked(c, val);
- spin_unlock(&c->lock);
+ raw_spin_unlock(&c->lock);
if (ret < 0) {
*limit_fail_at = c;
goto undo;
@@ -57,9 +57,9 @@ int res_counter_charge(struct res_counter *counter, unsigned long val,
goto done;
undo:
for (u = counter; u != c; u = u->parent) {
- spin_lock(&u->lock);
+ raw_spin_lock(&u->lock);
res_counter_uncharge_locked(u, val);
- spin_unlock(&u->lock);
+ raw_spin_unlock(&u->lock);
}
done:
local_irq_restore_nort(flags);
@@ -77,11 +77,11 @@ int res_counter_charge_nofail(struct res_counter *counter, unsigned long val,
*limit_fail_at = NULL;
local_irq_save(flags);
for (c = counter; c != NULL; c = c->parent) {
- spin_lock(&c->lock);
+ raw_spin_lock(&c->lock);
r = res_counter_charge_locked(c, val);
if (r)
c->usage += val;
- spin_unlock(&c->lock);
+ raw_spin_unlock(&c->lock);
if (r < 0 && ret == 0) {
*limit_fail_at = c;
ret = r;
@@ -106,9 +106,9 @@ void res_counter_uncharge(struct res_counter *counter, unsigned long val)
local_irq_save_nort(flags);
for (c = counter; c != NULL; c = c->parent) {
- spin_lock(&c->lock);
+ raw_spin_lock(&c->lock);
res_counter_uncharge_locked(c, val);
- spin_unlock(&c->lock);
+ raw_spin_unlock(&c->lock);
}
local_irq_restore_nort(flags);
}
@@ -157,9 +157,9 @@ u64 res_counter_read_u64(struct res_counter *counter, int member)
unsigned long flags;
u64 ret;
- spin_lock_irqsave(&counter->lock, flags);
+ raw_spin_lock_irqsave(&counter->lock, flags);
ret = *res_counter_member(counter, member);
- spin_unlock_irqrestore(&counter->lock, flags);
+ raw_spin_unlock_irqrestore(&counter->lock, flags);
return ret;
}
@@ -207,9 +207,9 @@ int res_counter_write(struct res_counter *counter, int member,
if (*end != '\0')
return -EINVAL;
}
- spin_lock_irqsave(&counter->lock, flags);
+ raw_spin_lock_irqsave(&counter->lock, flags);
val = res_counter_member(counter, member);
*val = tmp;
- spin_unlock_irqrestore(&counter->lock, flags);
+ raw_spin_unlock_irqrestore(&counter->lock, flags);
return 0;
}
--
1.7.5.4
--
To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
