From: Andrey Shvetsov andrey.shvetsov@k2l.de
commit 4d1356ac12f4d5180d0df345d85ff0ee42b89c72 upstream.
If the length of the socket buffer is 0xFFFFFFFF (max size for an unsigned int), then payload_len becomes 0xFFFFFFF1 after subtracting 14 (ETH_HLEN). Then, mdp_len is set to payload_len + 16 (MDP_HDR_LEN) which overflows and results in a value of 2. These values for payload_len and mdp_len will pass current buffer size checks.
This patch checks if derived from skb->len sum may overflow.
The check is based on the following idea:
For any `unsigned V1, V2` and derived `unsigned SUM = V1 + V2`, `V1 + V2` overflows iif `SUM < V1`.
Reported-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Andrey Shvetsov andrey.shvetsov@k2l.de Cc: stable stable@vger.kernel.org Link: https://lore.kernel.org/r/20200116172238.6046-1-andrey.shvetsov@microchip.co... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/staging/most/net/net.c | 10 ++++++++++ 1 file changed, 10 insertions(+)
diff --git a/drivers/staging/most/net/net.c b/drivers/staging/most/net/net.c index 30d816b..ff80834 100644 --- a/drivers/staging/most/net/net.c +++ b/drivers/staging/most/net/net.c @@ -81,6 +81,11 @@ static int skb_to_mamac(const struct sk_buff *skb, struct mbo *mbo) unsigned int payload_len = skb->len - ETH_HLEN; unsigned int mdp_len = payload_len + MDP_HDR_LEN;
+ if (mdp_len < skb->len) { + pr_err("drop: too large packet! (%u)\n", skb->len); + return -EINVAL; + } + if (mbo->buffer_length < mdp_len) { pr_err("drop: too small buffer! (%d for %d)\n", mbo->buffer_length, mdp_len); @@ -128,6 +133,11 @@ static int skb_to_mep(const struct sk_buff *skb, struct mbo *mbo) u8 *buff = mbo->virt_address; unsigned int mep_len = skb->len + MEP_HDR_LEN;
+ if (mep_len < skb->len) { + pr_err("drop: too large packet! (%u)\n", skb->len); + return -EINVAL; + } + if (mbo->buffer_length < mep_len) { pr_err("drop: too small buffer! (%d for %d)\n", mbo->buffer_length, mep_len);