On Wed, Jul 23, 2014 at 10:05:23AM +1000, ressy66@xxxxxxxxxx wrote:
Hi,
I am not familiar with git or code writting, I have no idea where to
start.
I was reporting the issue so hopefully someone with a clue who had one
of these dongles might look to see if they experience this and know
how
to resolve it, if I cant figure it out, might have to go back to 3.12,
since this logging in almost every 15 seconds (used for polling on
incoming SMS's), but if I can help in some way i will try, but be
warned, it would be like putting a 4yo in charge of a jumbo jet haha
Thanks for the bug report.
The option driver has always been logging normal interrupt-urb
shutdowns
as errors, but a recent bug fix increased the number of these
false-positives.
Could you apply and test the patch below?
Also, could you provide your name for the reported-by (and tested-by)
credits?
Thanks,
Johan
On 2014-07-20 06:21, Greg KH wrote:
> On Sat, Jul 19, 2014 at 03:11:22PM +1000, ressy66@xxxxxxxxxx wrote:
>> Since upgrading from 3.12.24 kernel to 3.14.10, and today, .12 kernel
>> log
>> and dmesg are flooded with constant messages
>>
>> option1 ttyUSB0: option_instat_callback: error -2
>>
>> The device still works, it sends and receives SMS's as well,
>> I tried setting verbose usb debug to see if it offers any more
>> explanations,
>> but it shows nothing more.
>>
>> The device is Huawei E160, but is identified as (and always has been)
>> an
>> E620
>>
>> ID 12d1:1001 Huawei Technologies Co., Ltd. E620 USB Modem
>>
>> Did somthing break between 3.12 and 3.14? Rather annoying at how fast
>> and
>> large kernel.log is geting.
>
> Any chance you can use 'git bisect' to try to find the problem commit
> in
> the kernel tree?
>
> thanks,
>
> greg k-h
From c6a7a5ab829bab1c42e9add18a242f2a5eb1bfee Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@xxxxxxxxxx>
Date: Tue, 29 Jul 2014 14:14:55 +0200
Subject: [PATCH] USB: option: reduce interrupt-urb logging verbosity
Do not log normal interrupt-urb shutdowns as errors.
The option driver has always been logging any nonzero interrupt-urb
status as an error, including when the urb is killed during normal
operation.
Commit 9096f1fbba91 ("USB: usb_wwan: fix potential NULL-deref at
resume") moved the interrupt urb submission from port probe and release
to open and close, thus potentially increasing the number of these
false-positive error messages dramatically.
Reported-by: <ressy66@xxxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Signed-off-by: Johan Hovold <johan@xxxxxxxxxx>
---
drivers/usb/serial/option.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index ac73f49cd9f0..6d45a29eb91f 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -1914,6 +1914,8 @@ static void option_instat_callback(struct urb
*urb)
dev_dbg(dev, "%s: type %x req %x\n", __func__,
req_pkt->bRequestType, req_pkt->bRequest);
}
+ } else if (status == -ENOENT || status == -ESHUTDOWN) {
+ dev_dbg(dev, "%s: urb stopped: %d\n", __func__, status);
} else
dev_err(dev, "%s: error %d\n", __func__, status);
