[PATCH 1/2] b43legacy: fix a lower bounds test

[PATCH 1/2] b43legacy: fix a lower bounds test

[Dan Carpenter]

The problem is that "channel" is an unsigned int, when it's less 5 the
value of "channel - 5" is not a negative number as one would expect but
is very high positive value instead.

This means that "start" becomes a very high positive value.  The result
of that is that we never enter the "for (i = start; i <= end; i++) {"
loop.  Instead of storing the result from b43legacy_radio_aci_detect()
it just uses zero.

Fixes: 75388acd0cd8 ("[B43LEGACY]: add mac80211-based driver for legacy BCM43xx devices")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
---
This fix is correct, but making dead code go live can sometimes expose
bugs which were previously hiding and is always carries a slight risk.

 drivers/net/wireless/broadcom/b43legacy/radio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/broadcom/b43legacy/radio.c b/drivers/net/wireless/broadcom/b43legacy/radio.c
index 06891b4f837b..fdf78c10a05c 100644
--- a/drivers/net/wireless/broadcom/b43legacy/radio.c
+++ b/drivers/net/wireless/broadcom/b43legacy/radio.c
@@ -283,7 +283,7 @@ u8 b43legacy_radio_aci_scan(struct b43legacy_wldev *dev)
 			    & 0x7FFF);
 	b43legacy_set_all_gains(dev, 3, 8, 1);
 
-	start = (channel - 5 > 0) ? channel - 5 : 1;
+	start = (channel > 5) ? channel - 5 : 1;
 	end = (channel + 5 < 14) ? channel + 5 : 13;
 
 	for (i = start; i <= end; i++) {
-- 
2.20.1


_______________________________________________
b43-dev mailing list
b43-dev@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/b43-dev

[PATCH 2/2] b43: fix a lower bounds test

[Dan Carpenter]

The problem is that "channel" is an unsigned int, when it's less 5 the
value of "channel - 5" is not a negative number as one would expect but
is very high positive value instead.

This means that "start" becomes a very high positive value.  The result
of that is that we never enter the "for (i = start; i <= end; i++) {"
loop.  Instead of storing the result from b43legacy_radio_aci_detect()
it just uses zero.

Fixes: ef1a628d83fc ("b43: Implement dynamic PHY API")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
---
 drivers/net/wireless/broadcom/b43/phy_g.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/broadcom/b43/phy_g.c b/drivers/net/wireless/broadcom/b43/phy_g.c
index d5a1a5c58236..ac72ca39e409 100644
--- a/drivers/net/wireless/broadcom/b43/phy_g.c
+++ b/drivers/net/wireless/broadcom/b43/phy_g.c
@@ -2297,7 +2297,7 @@ static u8 b43_gphy_aci_scan(struct b43_wldev *dev)
 	b43_phy_mask(dev, B43_PHY_G_CRS, 0x7FFF);
 	b43_set_all_gains(dev, 3, 8, 1);
 
-	start = (channel - 5 > 0) ? channel - 5 : 1;
+	start = (channel > 5) ? channel - 5 : 1;
 	end = (channel + 5 < 14) ? channel + 5 : 13;
 
 	for (i = start; i <= end; i++) {
-- 
2.20.1


_______________________________________________
b43-dev mailing list
b43-dev@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/b43-dev

Re: [PATCH 2/2] b43: fix a lower bounds test

[Michael Büsch]

[-- Attachment #1.1: Type: text/plain, Size: 1455 bytes --]

On Wed, 6 Oct 2021 10:36:22 +0300
Dan Carpenter <dan.carpenter@oracle.com> wrote:

> The problem is that "channel" is an unsigned int, when it's less 5 the
> value of "channel - 5" is not a negative number as one would expect but
> is very high positive value instead.
> 
> This means that "start" becomes a very high positive value.  The result
> of that is that we never enter the "for (i = start; i <= end; i++) {"
> loop.  Instead of storing the result from b43legacy_radio_aci_detect()
> it just uses zero.
> 
> Fixes: ef1a628d83fc ("b43: Implement dynamic PHY API")
> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
> ---
>  drivers/net/wireless/broadcom/b43/phy_g.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/drivers/net/wireless/broadcom/b43/phy_g.c b/drivers/net/wireless/broadcom/b43/phy_g.c
> index d5a1a5c58236..ac72ca39e409 100644
> --- a/drivers/net/wireless/broadcom/b43/phy_g.c
> +++ b/drivers/net/wireless/broadcom/b43/phy_g.c
> @@ -2297,7 +2297,7 @@ static u8 b43_gphy_aci_scan(struct b43_wldev *dev)
>  	b43_phy_mask(dev, B43_PHY_G_CRS, 0x7FFF);
>  	b43_set_all_gains(dev, 3, 8, 1);
>  
> -	start = (channel - 5 > 0) ? channel - 5 : 1;
> +	start = (channel > 5) ? channel - 5 : 1;
>  	end = (channel + 5 < 14) ? channel + 5 : 13;
>  
>  	for (i = start; i <= end; i++) {

Nice finding.

Acked-by: Michael Büsch <m@bues.ch>


-- 
Michael

https://bues.ch/

[-- Attachment #1.2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

[-- Attachment #2: Type: text/plain, Size: 149 bytes --]

_______________________________________________
b43-dev mailing list
b43-dev@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/b43-dev

Re: [PATCH 1/2] b43legacy: fix a lower bounds test

[Michael Büsch]

[-- Attachment #1.1: Type: text/plain, Size: 1657 bytes --]

On Wed, 6 Oct 2021 10:35:42 +0300
Dan Carpenter <dan.carpenter@oracle.com> wrote:

> The problem is that "channel" is an unsigned int, when it's less 5 the
> value of "channel - 5" is not a negative number as one would expect but
> is very high positive value instead.
> 
> This means that "start" becomes a very high positive value.  The result
> of that is that we never enter the "for (i = start; i <= end; i++) {"
> loop.  Instead of storing the result from b43legacy_radio_aci_detect()
> it just uses zero.
> 
> Fixes: 75388acd0cd8 ("[B43LEGACY]: add mac80211-based driver for legacy BCM43xx devices")
> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
> ---
> This fix is correct, but making dead code go live can sometimes expose
> bugs which were previously hiding and is always carries a slight risk.
> 
>  drivers/net/wireless/broadcom/b43legacy/radio.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/drivers/net/wireless/broadcom/b43legacy/radio.c b/drivers/net/wireless/broadcom/b43legacy/radio.c
> index 06891b4f837b..fdf78c10a05c 100644
> --- a/drivers/net/wireless/broadcom/b43legacy/radio.c
> +++ b/drivers/net/wireless/broadcom/b43legacy/radio.c
> @@ -283,7 +283,7 @@ u8 b43legacy_radio_aci_scan(struct b43legacy_wldev *dev)
>  			    & 0x7FFF);
>  	b43legacy_set_all_gains(dev, 3, 8, 1);
>  
> -	start = (channel - 5 > 0) ? channel - 5 : 1;
> +	start = (channel > 5) ? channel - 5 : 1;
>  	end = (channel + 5 < 14) ? channel + 5 : 13;
>  
>  	for (i = start; i <= end; i++) {

Nice finding.

Acked-by: Michael Büsch <m@bues.ch>


-- 
Michael

https://bues.ch/

[-- Attachment #1.2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

[-- Attachment #2: Type: text/plain, Size: 149 bytes --]

_______________________________________________
b43-dev mailing list
b43-dev@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/b43-dev

Re: [PATCH 1/2] b43legacy: fix a lower bounds test

[Kalle Valo]

Dan Carpenter <dan.carpenter@oracle.com> wrote:

> The problem is that "channel" is an unsigned int, when it's less 5 the
> value of "channel - 5" is not a negative number as one would expect but
> is very high positive value instead.
> 
> This means that "start" becomes a very high positive value.  The result
> of that is that we never enter the "for (i = start; i <= end; i++) {"
> loop.  Instead of storing the result from b43legacy_radio_aci_detect()
> it just uses zero.
> 
> Fixes: 75388acd0cd8 ("[B43LEGACY]: add mac80211-based driver for legacy BCM43xx devices")
> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
> Acked-by: Michael Büsch <m@bues.ch>

2 patches applied to wireless-drivers-next.git, thanks.

c1c8380b0320 b43legacy: fix a lower bounds test
9b793db5fca4 b43: fix a lower bounds test

-- 
https://patchwork.kernel.org/project/linux-wireless/patch/20211006073542.GD8404@kili/

https://wireless.wiki.kernel.org/en/developers/documentation/submittingpatches


_______________________________________________
b43-dev mailing list
b43-dev@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/b43-dev