[v4] net: usb: sr9700: fix uninitialized variable use in sr_mdio_read

[PATCH net v4] net: usb: sr9700: fix uninitialized variable use in sr_mdio_read

Posted by Ma Ke 1 year, 6 months ago

It could lead to error happen because the variable res is not updated if
the call to sr_share_read_word returns an error. In this particular case
error code was returned and res stayed uninitialized. Same issue also
applies to sr_read_reg.

This can be avoided by checking the return value of sr_share_read_word
and sr_read_reg, and propagating the error if the read operation failed.

Found by code review.

Cc: stable@vger.kernel.org
Fixes: c9b37458e956 ("USB2NET : SR9700 : One chip USB 1.1 USB2NET SR9700Device Driver Support")
Signed-off-by: Ma Ke <make24@iscas.ac.cn>
---
Changes in v4:
- added a check for sr_read_reg() as suggestions.
Changes in v3:
- added Cc stable line as suggestions.
Changes in v2:
- modified the subject as suggestions.
---
 drivers/net/usb/sr9700.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c
index 0a662e42ed96..cb7d2f798fb4 100644
--- a/drivers/net/usb/sr9700.c
+++ b/drivers/net/usb/sr9700.c
@@ -179,6 +179,7 @@ static int sr_mdio_read(struct net_device *netdev, int phy_id, int loc)
 	struct usbnet *dev = netdev_priv(netdev);
 	__le16 res;
 	int rc = 0;
+	int err;
 
 	if (phy_id) {
 		netdev_dbg(netdev, "Only internal phy supported\n");
@@ -189,11 +190,17 @@ static int sr_mdio_read(struct net_device *netdev, int phy_id, int loc)
 	if (loc == MII_BMSR) {
 		u8 value;
 
-		sr_read_reg(dev, SR_NSR, &value);
+		err = sr_read_reg(dev, SR_NSR, &value);
+		if (err < 0)
+			return err;
+
 		if (value & NSR_LINKST)
 			rc = 1;
 	}
-	sr_share_read_word(dev, 1, loc, &res);
+	err = sr_share_read_word(dev, 1, loc, &res);
+	if (err < 0)
+		return err;
+
 	if (rc == 1)
 		res = le16_to_cpu(res) | BMSR_LSTATUS;
 	else
-- 
2.25.1

Re: [PATCH net v4] net: usb: sr9700: fix uninitialized variable use in sr_mdio_read

Posted by Shigeru Yoshida 1 year, 6 months ago

On Thu, 25 Jul 2024 10:29:42 +0800, Ma Ke wrote:
> It could lead to error happen because the variable res is not updated if
> the call to sr_share_read_word returns an error. In this particular case
> error code was returned and res stayed uninitialized. Same issue also
> applies to sr_read_reg.
> 
> This can be avoided by checking the return value of sr_share_read_word
> and sr_read_reg, and propagating the error if the read operation failed.
> 
> Found by code review.
> 
> Cc: stable@vger.kernel.org
> Fixes: c9b37458e956 ("USB2NET : SR9700 : One chip USB 1.1 USB2NET SR9700Device Driver Support")
> Signed-off-by: Ma Ke <make24@iscas.ac.cn>

I did a quick check for sr9700.c and there seems to be other
suspicious usage of sr_read_reg().  But, for sr_mdio_read(), I think
the patch is sufficient.

Reviewed-by: Shigeru Yoshida <syoshida@redhat.com>

> ---
> Changes in v4:
> - added a check for sr_read_reg() as suggestions.
> Changes in v3:
> - added Cc stable line as suggestions.
> Changes in v2:
> - modified the subject as suggestions.
> ---
>  drivers/net/usb/sr9700.c | 11 +++++++++--
>  1 file changed, 9 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c
> index 0a662e42ed96..cb7d2f798fb4 100644
> --- a/drivers/net/usb/sr9700.c
> +++ b/drivers/net/usb/sr9700.c
> @@ -179,6 +179,7 @@ static int sr_mdio_read(struct net_device *netdev, int phy_id, int loc)
>  	struct usbnet *dev = netdev_priv(netdev);
>  	__le16 res;
>  	int rc = 0;
> +	int err;
>  
>  	if (phy_id) {
>  		netdev_dbg(netdev, "Only internal phy supported\n");
> @@ -189,11 +190,17 @@ static int sr_mdio_read(struct net_device *netdev, int phy_id, int loc)
>  	if (loc == MII_BMSR) {
>  		u8 value;
>  
> -		sr_read_reg(dev, SR_NSR, &value);
> +		err = sr_read_reg(dev, SR_NSR, &value);
> +		if (err < 0)
> +			return err;
> +
>  		if (value & NSR_LINKST)
>  			rc = 1;
>  	}
> -	sr_share_read_word(dev, 1, loc, &res);
> +	err = sr_share_read_word(dev, 1, loc, &res);
> +	if (err < 0)
> +		return err;
> +
>  	if (rc == 1)
>  		res = le16_to_cpu(res) | BMSR_LSTATUS;
>  	else
> -- 
> 2.25.1
>

Re: [PATCH net v4] net: usb: sr9700: fix uninitialized variable use in sr_mdio_read

Posted by Hariprasad Kelam 1 year, 6 months ago

On 2024-07-25 at 08:31:00, Shigeru Yoshida (syoshida@redhat.com) wrote:
> On Thu, 25 Jul 2024 10:29:42 +0800, Ma Ke wrote:
> > It could lead to error happen because the variable res is not updated if
> > the call to sr_share_read_word returns an error. In this particular case
> > error code was returned and res stayed uninitialized. Same issue also
> > applies to sr_read_reg.
> > 
> > This can be avoided by checking the return value of sr_share_read_word
> > and sr_read_reg, and propagating the error if the read operation failed.
> > 
> > Found by code review.
> > 
> > Cc: stable@vger.kernel.org
> > Fixes: c9b37458e956 ("USB2NET : SR9700 : One chip USB 1.1 USB2NET SR9700Device Driver Support")
> > Signed-off-by: Ma Ke <make24@iscas.ac.cn>
> 
> I did a quick check for sr9700.c and there seems to be other
> suspicious usage of sr_read_reg().  But, for sr_mdio_read(), I think
> the patch is sufficient.
> 
> Reviewed-by: Shigeru Yoshida <syoshida@redhat.com>
> 
>  Agree with Shigeru, may be you can submit another patch addressing
>  "suspicious usage of sr_read_reg" this patch looks good

Reviewed-by: Hariprasad Kelam <hkelam@marvell.com>