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
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
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
Hello:
This patch was applied to netdev/net.git (main) by David S. Miller davem@davemloft.net:
On Thu, 25 Jul 2024 10:29:42 +0800 you 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.
[...]
Here is the summary with links: - [net,v4] net: usb: sr9700: fix uninitialized variable use in sr_mdio_read https://git.kernel.org/netdev/net/c/08f3a5c38087
You are awesome, thank you!
linux-stable-mirror@lists.linaro.org
-
Hariprasad Kelam -
Ma Ke -
patchwork-bot+netdevbpf＠kernel.org -
Shigeru Yoshida