linux-kernel - Re: RFC: Bug in error handling in gpiolib.c

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Fri, 30 Aug 2013 10:50:38 +0900
From:	Alexandre Courbot <gnurou@...il.com>
To:	Linus Walleij <linus.walleij@...aro.org>
Cc:	Tim Bird <tbird20d@...il.com>,
	Alexandre Courbot <acourbot@...dia.com>,
	Grant Likely <grant.likely@...aro.org>,
	"linux-gpio@...r.kernel.org" <linux-gpio@...r.kernel.org>,
	"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
	"Bird, Tim" <tim.bird@...ymobile.com>
Subject: Re: RFC: Bug in error handling in gpiolib.c

On Fri, Aug 30, 2013 at 2:45 AM, Linus Walleij <linus.walleij@...aro.org> wrote:
> On Tue, Aug 27, 2013 at 9:17 PM, Tim Bird <tbird20d@...il.com> wrote:
>
>> Hi all,
>>
>> There appears to be a bug in the error handling in
>> drivers/gpi/gpiolib.c  In certain error cases
>> desc_to_gpio() is called to get the gpio number
>> for an error message, but this may happen on code
>> paths where desc->chip is NULL.  This causes a panic
>> on my system in gpiod_request(), as follows:
> (...)
>> Here's my patch:
>> Subject: [PATCH] gpio: avoid panic on NULL desc->chip in gpiod_request
>
> Patch applied. Unless we come up with something better,
> there is some parallel discussion on how to handle NULL
> descriptors.
>
> Alexandre: OK to apply this?

For this particular case I think the following would be preferable:

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index ff0fd65..d900bf1 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1398,7 +1398,7 @@ static int gpiod_request(struct gpio_desc *desc,
const char *label)
        int                     status = -EPROBE_DEFER;
        unsigned long           flags;

-       if (!desc) {
+       if (!desc || !desc->chip) {
                pr_warn("%s: invalid GPIO\n", __func__);
                return -EINVAL;
        }
@@ -1406,8 +1406,6 @@ static int gpiod_request(struct gpio_desc *desc,
const char *label)
        spin_lock_irqsave(&gpio_lock, flags);

        chip = desc->chip;
-       if (chip == NULL)
-               goto done;

        if (!try_module_get(chip->owner))
                goto done;

Since we are going to fail because the chip is missing anyway, we can
as well do it from the start. A descriptor without a chip is invalid
anyway.

But this (and the other thread) stresses the fact that error handling
in gpiolib needs some more love. I'm convinced it can be simplified -
will try to look at it sometime soon.

Alex.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/