Commit 30b678d8 authored by Ben Hutchings's avatar Ben Hutchings Committed by David S. Miller

net: Allow driver to limit number of GSO segments per skb

A peer (or local user) may cause TCP to use a nominal MSS of as little
as 88 (actual MSS of 76 with timestamps).  Given that we have a
sufficiently prodigious local sender and the peer ACKs quickly enough,
it is nevertheless possible to grow the window for such a connection
to the point that we will try to send just under 64K at once.  This
results in a single skb that expands to 861 segments.

In some drivers with TSO support, such an skb will require hundreds of
DMA descriptors; a substantial fraction of a TX ring or even more than
a full ring.  The TX queue selected for the skb may stall and trigger
the TX watchdog repeatedly (since the problem skb will be retried
after the TX reset).  This particularly affects sfc, for which the
issue is designated as CVE-2012-3412.

Therefore:
1. Add the field net_device::gso_max_segs holding the device-specific
   limit.
2. In netif_skb_features(), if the number of segments is too high then
   mask out GSO features to force fall back to software GSO.
Signed-off-by: default avatarBen Hutchings <bhutchings@solarflare.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 1a9b4993
...@@ -1300,6 +1300,8 @@ struct net_device { ...@@ -1300,6 +1300,8 @@ struct net_device {
/* for setting kernel sock attribute on TCP connection setup */ /* for setting kernel sock attribute on TCP connection setup */
#define GSO_MAX_SIZE 65536 #define GSO_MAX_SIZE 65536
unsigned int gso_max_size; unsigned int gso_max_size;
#define GSO_MAX_SEGS 65535
u16 gso_max_segs;
#ifdef CONFIG_DCB #ifdef CONFIG_DCB
/* Data Center Bridging netlink ops */ /* Data Center Bridging netlink ops */
......
...@@ -2134,6 +2134,9 @@ netdev_features_t netif_skb_features(struct sk_buff *skb) ...@@ -2134,6 +2134,9 @@ netdev_features_t netif_skb_features(struct sk_buff *skb)
__be16 protocol = skb->protocol; __be16 protocol = skb->protocol;
netdev_features_t features = skb->dev->features; netdev_features_t features = skb->dev->features;
if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs)
features &= ~NETIF_F_GSO_MASK;
if (protocol == htons(ETH_P_8021Q)) { if (protocol == htons(ETH_P_8021Q)) {
struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
protocol = veh->h_vlan_encapsulated_proto; protocol = veh->h_vlan_encapsulated_proto;
...@@ -5986,6 +5989,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, ...@@ -5986,6 +5989,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
dev_net_set(dev, &init_net); dev_net_set(dev, &init_net);
dev->gso_max_size = GSO_MAX_SIZE; dev->gso_max_size = GSO_MAX_SIZE;
dev->gso_max_segs = GSO_MAX_SEGS;
INIT_LIST_HEAD(&dev->napi_list); INIT_LIST_HEAD(&dev->napi_list);
INIT_LIST_HEAD(&dev->unreg_list); INIT_LIST_HEAD(&dev->unreg_list);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment