Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.34 as permitted sender) client-ip=23.128.96.34;
Message-ID: <9f6883fb-d628-4077-bb94-f5ba620bdd57@gmail.com>
Date:   Thu, 7 Dec 2023 13:21:18 +0100
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Cc:     savicaleksa83@gmail.com, linux-hwmon@vger.kernel.org,
        Jean Delvare <jdelvare@suse.com>,
        Jonathan Corbet <corbet@lwn.net>,
        "open list:DOCUMENTATION" <linux-doc@vger.kernel.org>,
        open list <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH v2] hwmon: Add driver for Gigabyte AORUS Waterforce AIO
 coolers
Content-Language: en-US
To:     Guenter Roeck <linux@roeck-us.net>
References: <20231203120651.371429-1-savicaleksa83@gmail.com>
 <b45529ba-619c-41d7-a890-3b81cf699ebe@roeck-us.net>
 <da9fe05a-a12d-4a2d-a81a-1195d65b1d51@gmail.com>
 <34638d1a-55c2-4dfe-ab9b-d8591a32b950@roeck-us.net>
From:   Aleksa Savic <savicaleksa83@gmail.com>
In-Reply-To: <34638d1a-55c2-4dfe-ab9b-d8591a32b950@roeck-us.net>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Precedence: bulk

On 2023-12-05 15:35:19 GMT+01:00, Guenter Roeck wrote:
> On 12/5/23 06:22, Aleksa Savic wrote:
>> On 2023-12-03 18:36:35 GMT+01:00, Guenter Roeck wrote:
>>> On Sun, Dec 03, 2023 at 01:06:48PM +0100, Aleksa Savic wrote:
>>>> This driver exposes hardware sensors of the Gigabyte AORUS Waterforce
>>>> all-in-one CPU liquid coolers, which communicate through a proprietary
>>>> USB HID protocol. Report offsets were initially discovered in [1] and
>>>> confirmed by me on a Waterforce X240 by observing the sent reports from
>>>> the official software.
>>>>
>>>> Available sensors are pump and fan speed in RPM, as well as coolant
>>>> temperature. Also available through debugfs is the firmware version.
>>>>
>>>> Attaching a fan is optional and allows it to be controlled from the
>>>> device. If it's not connected, the fan-related sensors will report
>>>> zeroes.
>>>>
>>>> The addressable RGB LEDs and LCD screen are not supported in this
>>>> driver and should be controlled through userspace tools.
>>>>
>>>> [1]: https://github.com/liquidctl/liquidctl/issues/167
>>>>
>>>> Signed-off-by: Aleksa Savic <savicaleksa83@gmail.com>
>>>> ---
> ...
>>>> +static int waterforce_get_status(struct waterforce_data *priv)
>>>> +{
>>>> +    int ret = 0;
>>>> +
>>>> +    if (!mutex_lock_interruptible(&priv->status_report_request_mutex)) {
>>>> +        if (!time_after(jiffies, priv->updated + msecs_to_jiffies(STATUS_VALIDITY))) {
>>>> +            /* Data is up to date */
>>>> +            goto unlock_and_return;
>>>> +        }
>>>
>>> What is the point of this check ? The calling code already checks it.
>>> Checking it twice, once inside and once outside the lock, seems
>>> excessive.
>>>
>>
>> If there are multiple readers here, only the first one should request the status,
>> so when others enter the mutex they can exit early if the data is there.
>>
> 
> Please change the code to only check once from within the mutex.
> 
> Guenter
> 

Done in v3.

Thanks,
Aleksa