Fix issue with the sleeping calling hid_hw_request under spinlock.
When i2c is used as HID transport, this is calling kmalloc, which
can sleep. So remove call to this function while under spinlock.
[ 1067.021961] Call Trace:
[ 1067.021970] [<
ffffffff8192f5f2>] dump_stack+0x4d/0x6f
[ 1067.021976] [<
ffffffff811109f2>] __might_sleep+0xd2/0xf0
[ 1067.021981] [<
ffffffff811ea15b>] __kmalloc+0xeb/0x200
[ 1067.021989] [<
ffffffff816e0cb3>] ? hid_alloc_report_buf+0x23/0x30
[ 1067.021993] [<
ffffffff816e0cb3>] hid_alloc_report_buf+0x23/0x30
[ 1067.021997] [<
ffffffff816f4cb7>] i2c_hid_request+0x57/0x110
[ 1067.022006] [<
ffffffffa02bc61c>] sensor_hub_input_attr_get_raw_value+0xbc/0x100 [hid_sensor_hub]
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
spin_lock_irqsave(&data->lock, flags);
data->pending.status = true;
+ spin_unlock_irqrestore(&data->lock, flags);
report = sensor_hub_report(report_id, hsdev->hdev, HID_INPUT_REPORT);
- if (!report) {
- spin_unlock_irqrestore(&data->lock, flags);
+ if (!report)
goto err_free;
- }
+
hid_hw_request(hsdev->hdev, report, HID_REQ_GET_REPORT);
- spin_unlock_irqrestore(&data->lock, flags);
wait_for_completion_interruptible_timeout(&data->pending.ready, HZ*5);
switch (data->pending.raw_size) {
case 1: