Shlomo Pongratz reported GRO L2 header check was suited for Ethernet
only, and failed on IB/ipoib traffic.

He provided a patch faking a zeroed header to let GRO aggregates frames.

Roland Dreier, Herbert Xu, and others suggested we change GRO L2 header
check to be more generic.

This patch introduces a new netdevice field, gro_mac_header_len, giving
L2 header length, default to ETH_HLEN (14 bytes)

A device setup function can override this default value.

__napi_gro_receive() has special handling for the common case (Ethernet)
to avoid a memcmp() call and use an inline optimized function instead.

Signed-off-by: Eric Dumazet <eric.duma...@gmail.com>
Reported-by: Shlomo Pongratz <shlo...@mellanox.com>
Cc: Roland Dreier <rol...@kernel.org>
Cc: Or Gerlitz <ogerl...@mellanox.com>
Cc: Herbert Xu <herb...@gondor.apana.org.au>
---
 include/linux/netdevice.h |    1 +
 net/core/dev.c            |   11 +++++++++--
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 0eac07c..d17192b 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1095,6 +1095,7 @@ struct net_device {
        unsigned int            mtu;    /* interface MTU value          */
        unsigned short          type;   /* interface hardware type      */
        unsigned short          hard_header_len;        /* hardware hdr length  
*/
+       unsigned int            gro_mac_header_len;
 
        /* extra head- and tailroom the hardware may need, but not in all cases
         * can this be guaranteed, especially tailroom. Some cases also use
diff --git a/net/core/dev.c b/net/core/dev.c
index f124947..0b43939 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3491,14 +3491,20 @@ static inline gro_result_t
 __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
        struct sk_buff *p;
+       unsigned int maclen = skb->dev->gro_mac_header_len;
 
        for (p = napi->gro_list; p; p = p->next) {
                unsigned long diffs;
 
                diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev;
                diffs |= p->vlan_tci ^ skb->vlan_tci;
-               diffs |= compare_ether_header(skb_mac_header(p),
-                                             skb_gro_mac_header(skb));
+               if (maclen == ETH_HLEN)
+                       diffs |= compare_ether_header(skb_mac_header(p),
+                                                     skb_gro_mac_header(skb));
+               else if (!diffs)
+                       diffs = memcmp(skb_mac_header(p),
+                                      skb_gro_mac_header(skb),
+                                      maclen);
                NAPI_GRO_CB(p)->same_flow = !diffs;
                NAPI_GRO_CB(p)->flush = 0;
        }
@@ -5962,6 +5968,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, 
const char *name,
        INIT_LIST_HEAD(&dev->unreg_list);
        INIT_LIST_HEAD(&dev->link_watch_list);
        dev->priv_flags = IFF_XMIT_DST_RELEASE;
+       dev->gro_mac_header_len = ETH_HLEN;
        setup(dev);
 
        dev->num_tx_queues = txqs;


--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Reply via email to