summaryrefslogtreecommitdiff
path: root/drivers/net
diff options
context:
space:
mode:
authorLv Yunlong <lyl2019@mail.ustc.edu.cn>2021-04-26 19:06:25 +0300
committerDavid S. Miller <davem@davemloft.net>2021-04-26 23:07:30 +0300
commit6d72e7c767acbbdd44ebc7d89c6690b405b32b57 (patch)
tree7aaccf01bd1be481d9662bee62901264654a91fc /drivers/net
parentf77bd544a6bbe69aa50d9ed09f13494cf36ff806 (diff)
downloadlinux-6d72e7c767acbbdd44ebc7d89c6690b405b32b57.tar.xz
net:emac/emac-mac: Fix a use after free in emac_mac_tx_buf_send
In emac_mac_tx_buf_send, it calls emac_tx_fill_tpd(..,skb,..). If some error happens in emac_tx_fill_tpd(), the skb will be freed via dev_kfree_skb(skb) in error branch of emac_tx_fill_tpd(). But the freed skb is still used via skb->len by netdev_sent_queue(,skb->len). As i observed that emac_tx_fill_tpd() haven't modified the value of skb->len, thus my patch assigns skb->len to 'len' before the possible free and use 'len' instead of skb->len later. Fixes: b9b17debc69d2 ("net: emac: emac gigabit ethernet controller driver") Signed-off-by: Lv Yunlong <lyl2019@mail.ustc.edu.cn> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'drivers/net')
-rw-r--r--drivers/net/ethernet/qualcomm/emac/emac-mac.c4
1 files changed, 3 insertions, 1 deletions
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c
index 117188e3c7de..87b8c032195d 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c
@@ -1437,6 +1437,7 @@ netdev_tx_t emac_mac_tx_buf_send(struct emac_adapter *adpt,
{
struct emac_tpd tpd;
u32 prod_idx;
+ int len;
memset(&tpd, 0, sizeof(tpd));
@@ -1456,9 +1457,10 @@ netdev_tx_t emac_mac_tx_buf_send(struct emac_adapter *adpt,
if (skb_network_offset(skb) != ETH_HLEN)
TPD_TYP_SET(&tpd, 1);
+ len = skb->len;
emac_tx_fill_tpd(adpt, tx_q, skb, &tpd);
- netdev_sent_queue(adpt->netdev, skb->len);
+ netdev_sent_queue(adpt->netdev, len);
/* Make sure the are enough free descriptors to hold one
* maximum-sized SKB. We need one desc for each fragment,