2023-07-12 17:47:22

by Mark Brown

[permalink] [raw]
Subject: [PATCH] pinctrl: sunxi: Add some defensiveness for regulators array

The sunxi pinctrl has a fixed size array it uses to store regulators used
in the driver. There is currently nothing that ensures that the number of
elements in the array is large enough to map the regulators defined by the
individual SoCs. While this is currently the case having an explicit check
in there will make life easier for anyone debugging memory issues that
manifest in the driver so let's add one.

Signed-off-by: Mark Brown <[email protected]>
---
drivers/pinctrl/sunxi/pinctrl-sunxi.c | 3 +++
1 file changed, 3 insertions(+)

diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
index 1dc1882cbdd7..1d1cd3d6d379 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
@@ -848,6 +848,9 @@ static int sunxi_pmx_request(struct pinctrl_dev *pctldev, unsigned offset)
char supply[16];
int ret;

+ if (WARN_ON_ONCE(bank_offset >= ARRAY_SIZE(pctl->regulators)))
+ return -EINVAL;
+
if (reg) {
refcount_inc(&s_reg->refcount);
return 0;

---
base-commit: 06c2afb862f9da8dc5efa4b6076a0e48c3fbaaa5
change-id: 20230711-pinctrl-sunxi-boudns-95bf5da3d075

Best regards,
--
Mark Brown <[email protected]>



2023-07-12 18:13:26

by Chen-Yu Tsai

[permalink] [raw]
Subject: Re: [PATCH] pinctrl: sunxi: Add some defensiveness for regulators array

On Thu, Jul 13, 2023 at 1:20 AM Mark Brown <[email protected]> wrote:
>
> The sunxi pinctrl has a fixed size array it uses to store regulators used
> in the driver. There is currently nothing that ensures that the number of
> elements in the array is large enough to map the regulators defined by the
> individual SoCs. While this is currently the case having an explicit check
> in there will make life easier for anyone debugging memory issues that
> manifest in the driver so let's add one.
>
> Signed-off-by: Mark Brown <[email protected]>

Reviewed-by: Chen-Yu Tsai <[email protected]>

2023-07-12 18:15:25

by Jernej Škrabec

[permalink] [raw]
Subject: Re: [PATCH] pinctrl: sunxi: Add some defensiveness for regulators array

Dne sreda, 12. julij 2023 ob 19:19:59 CEST je Mark Brown napisal(a):
> The sunxi pinctrl has a fixed size array it uses to store regulators used
> in the driver. There is currently nothing that ensures that the number of
> elements in the array is large enough to map the regulators defined by the
> individual SoCs. While this is currently the case having an explicit check
> in there will make life easier for anyone debugging memory issues that
> manifest in the driver so let's add one.
>
> Signed-off-by: Mark Brown <[email protected]>

Reviewed-by: Jernej Skrabec <[email protected]>

Best regards,
Jernej

> ---
> drivers/pinctrl/sunxi/pinctrl-sunxi.c | 3 +++
> 1 file changed, 3 insertions(+)
>
> diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c
> b/drivers/pinctrl/sunxi/pinctrl-sunxi.c index 1dc1882cbdd7..1d1cd3d6d379
> 100644
> --- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c
> +++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
> @@ -848,6 +848,9 @@ static int sunxi_pmx_request(struct pinctrl_dev
> *pctldev, unsigned offset) char supply[16];
> int ret;
>
> + if (WARN_ON_ONCE(bank_offset >= ARRAY_SIZE(pctl->regulators)))
> + return -EINVAL;
> +
> if (reg) {
> refcount_inc(&s_reg->refcount);
> return 0;
>
> ---
> base-commit: 06c2afb862f9da8dc5efa4b6076a0e48c3fbaaa5
> change-id: 20230711-pinctrl-sunxi-boudns-95bf5da3d075
>
> Best regards,





2023-07-20 19:54:55

by Linus Walleij

[permalink] [raw]
Subject: Re: [PATCH] pinctrl: sunxi: Add some defensiveness for regulators array

On Wed, Jul 12, 2023 at 7:20 PM Mark Brown <[email protected]> wrote:

> The sunxi pinctrl has a fixed size array it uses to store regulators used
> in the driver. There is currently nothing that ensures that the number of
> elements in the array is large enough to map the regulators defined by the
> individual SoCs. While this is currently the case having an explicit check
> in there will make life easier for anyone debugging memory issues that
> manifest in the driver so let's add one.
>
> Signed-off-by: Mark Brown <[email protected]>

Patch applied.

Yours,
Linus Walleij