aboutsummaryrefslogtreecommitdiff
path: root/include/linux
diff options
context:
space:
mode:
authorDouglas Miller <dougmill@linux.vnet.ibm.com>2017-01-28 06:42:20 -0600
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2017-02-09 08:02:46 +0100
commitb3c8c31ed24c39f9a9fb9bee1e42b16640ff0bee (patch)
treeaec4492aa64ed3b01c083d5b6452f75dff0e6dfc /include/linux
parent3a8e217851c9854b3f122ed1651d68a05884c730 (diff)
percpu-refcount: fix reference leak during percpu-atomic transition
commit 966d2b04e070bc040319aaebfec09e0144dc3341 upstream. percpu_ref_tryget() and percpu_ref_tryget_live() should return "true" IFF they acquire a reference. But the return value from atomic_long_inc_not_zero() is a long and may have high bits set, e.g. PERCPU_COUNT_BIAS, and the return value of the tryget routines is bool so the reference may actually be acquired but the routines return "false" which results in a reference leak since the caller assumes it does not need to do a corresponding percpu_ref_put(). This was seen when performing CPU hotplug during I/O, as hangs in blk_mq_freeze_queue_wait where percpu_ref_kill (blk_mq_freeze_queue_start) raced with percpu_ref_tryget (blk_mq_timeout_work). Sample stack trace: __switch_to+0x2c0/0x450 __schedule+0x2f8/0x970 schedule+0x48/0xc0 blk_mq_freeze_queue_wait+0x94/0x120 blk_mq_queue_reinit_work+0xb8/0x180 blk_mq_queue_reinit_prepare+0x84/0xa0 cpuhp_invoke_callback+0x17c/0x600 cpuhp_up_callbacks+0x58/0x150 _cpu_up+0xf0/0x1c0 do_cpu_up+0x120/0x150 cpu_subsys_online+0x64/0xe0 device_online+0xb4/0x120 online_store+0xb4/0xc0 dev_attr_store+0x68/0xa0 sysfs_kf_write+0x80/0xb0 kernfs_fop_write+0x17c/0x250 __vfs_write+0x6c/0x1e0 vfs_write+0xd0/0x270 SyS_write+0x6c/0x110 system_call+0x38/0xe0 Examination of the queue showed a single reference (no PERCPU_COUNT_BIAS, and __PERCPU_REF_DEAD, __PERCPU_REF_ATOMIC set) and no requests. However, conditions at the time of the race are count of PERCPU_COUNT_BIAS + 0 and __PERCPU_REF_DEAD and __PERCPU_REF_ATOMIC set. The fix is to make the tryget routines use an actual boolean internally instead of the atomic long result truncated to a int. Fixes: e625305b3907 percpu-refcount: make percpu_ref based on longs instead of ints Link: https://bugzilla.kernel.org/show_bug.cgi?id=190751 Signed-off-by: Douglas Miller <dougmill@linux.vnet.ibm.com> Reviewed-by: Jens Axboe <axboe@fb.com> Signed-off-by: Tejun Heo <tj@kernel.org> Fixes: e625305b3907 ("percpu-refcount: make percpu_ref based on longs instead of ints") Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'include/linux')
-rw-r--r--include/linux/percpu-refcount.h4
1 files changed, 2 insertions, 2 deletions
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 12c9b485beb7..abd7c01c84db 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -206,7 +206,7 @@ static inline void percpu_ref_get(struct percpu_ref *ref)
static inline bool percpu_ref_tryget(struct percpu_ref *ref)
{
unsigned long __percpu *percpu_count;
- int ret;
+ bool ret;
rcu_read_lock_sched();
@@ -240,7 +240,7 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref)
static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
{
unsigned long __percpu *percpu_count;
- int ret = false;
+ bool ret = false;
rcu_read_lock_sched();