ibmveth: set correct gso_size and gso_type

This patch is based on an earlier one submitted
by Jon Maxwell with the following commit message:

"We recently encountered a bug where a few customers using ibmveth on the
same LPAR hit an issue where a TCP session hung when large receive was
enabled. Closer analysis revealed that the session was stuck because the
one side was advertising a zero window repeatedly.

We narrowed this down to the fact the ibmveth driver did not set gso_size
which is translated by TCP into the MSS later up the stack. The MSS is
used to calculate the TCP window size and as that was abnormally large,
it was calculating a zero window, even although the sockets receive buffer
was completely empty."

We rely on the Virtual I/O Server partition in a pseries
environment to provide the MSS through the TCP header checksum
field. The stipulation is that users should not disable checksum
offloading if rx packet aggregation is enabled through VIOS.

Some firmware offerings provide the MSS in the RX buffer.
This is signalled by a bit in the RX queue descriptor.

Reviewed-by: Brian King <brking@linux.vnet.ibm.com>
Reviewed-by: Pradeep Satyanarayana <pradeeps@linux.vnet.ibm.com>
Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Reviewed-by: Jonathan Maxwell <jmaxwell37@gmail.com>
Reviewed-by: David Dai <zdai@us.ibm.com>
Signed-off-by: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 63 insertions, 2 deletions

diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index ebe60719e489..a36022ba4e42 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -58,7 +58,7 @@ static struct kobj_type ktype_veth_pool;
 
 static const char ibmveth_driver_name[] = "ibmveth";
 static const char ibmveth_driver_string[] = "IBM Power Virtual Ethernet Driver";
-#define ibmveth_driver_version "1.05"
+#define ibmveth_driver_version "1.06"
 
 MODULE_AUTHOR("Santiago Leon <santil@linux.vnet.ibm.com>");
 MODULE_DESCRIPTION("IBM Power Virtual Ethernet Driver");
@@ -137,6 +137,11 @@ static inline int ibmveth_rxq_frame_offset(struct ibmveth_adapter *adapter)
 	return ibmveth_rxq_flags(adapter) & IBMVETH_RXQ_OFF_MASK;
 }
 
+static inline int ibmveth_rxq_large_packet(struct ibmveth_adapter *adapter)
+{
+	return ibmveth_rxq_flags(adapter) & IBMVETH_RXQ_LRG_PKT;
+}
+
 static inline int ibmveth_rxq_frame_length(struct ibmveth_adapter *adapter)
 {
 	return be32_to_cpu(adapter->rx_queue.queue_addr[adapter->rx_queue.index].length);
@@ -1174,6 +1179,45 @@ map_failed:
 	goto retry_bounce;
 }
 
+static void ibmveth_rx_mss_helper(struct sk_buff *skb, u16 mss, int lrg_pkt)
+{
+	int offset = 0;
+
+	/* only TCP packets will be aggregated */
+	if (skb->protocol == htons(ETH_P_IP)) {
+		struct iphdr *iph = (struct iphdr *)skb->data;
+
+		if (iph->protocol == IPPROTO_TCP) {
+			offset = iph->ihl * 4;
+			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
+		} else {
+			return;
+		}
+	} else if (skb->protocol == htons(ETH_P_IPV6)) {
+		struct ipv6hdr *iph6 = (struct ipv6hdr *)skb->data;
+
+		if (iph6->nexthdr == IPPROTO_TCP) {
+			offset = sizeof(struct ipv6hdr);
+			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
+		} else {
+			return;
+		}
+	} else {
+		return;
+	}
+	/* if mss is not set through Large Packet bit/mss in rx buffer,
+	 * expect that the mss will be written to the tcp header checksum.
+	 */
+	if (lrg_pkt) {
+		skb_shinfo(skb)->gso_size = mss;
+	} else if (offset) {
+		struct tcphdr *tcph = (struct tcphdr *)(skb->data + offset);
+
+		skb_shinfo(skb)->gso_size = ntohs(tcph->check);
+		tcph->check = 0;
+	}
+}
+
 static int ibmveth_poll(struct napi_struct *napi, int budget)
 {
 	struct ibmveth_adapter *adapter =
@@ -1182,6 +1226,7 @@ static int ibmveth_poll(struct napi_struct *napi, int budget)
 	int frames_processed = 0;
 	unsigned long lpar_rc;
 	struct iphdr *iph;
+	u16 mss = 0;
 
 restart_poll:
 	while (frames_processed < budget) {
@@ -1199,9 +1244,21 @@ restart_poll:
 			int length = ibmveth_rxq_frame_length(adapter);
 			int offset = ibmveth_rxq_frame_offset(adapter);
 			int csum_good = ibmveth_rxq_csum_good(adapter);
+			int lrg_pkt = ibmveth_rxq_large_packet(adapter);
 
 			skb = ibmveth_rxq_get_buffer(adapter);
 
+			/* if the large packet bit is set in the rx queue
+			 * descriptor, the mss will be written by PHYP eight
+			 * bytes from the start of the rx buffer, which is
+			 * skb->data at this stage
+			 */
+			if (lrg_pkt) {
+				__be64 *rxmss = (__be64 *)(skb->data + 8);
+
+				mss = (u16)be64_to_cpu(*rxmss);
+			}
+
 			new_skb = NULL;
 			if (length < rx_copybreak)
 				new_skb = netdev_alloc_skb(netdev, length);
@@ -1235,11 +1292,15 @@ restart_poll:
 					if (iph->check == 0xffff) {
 						iph->check = 0;
 						iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
-						adapter->rx_large_packets++;
 					}
 				}
 			}
 
+			if (length > netdev->mtu + ETH_HLEN) {
+				ibmveth_rx_mss_helper(skb, mss, lrg_pkt);
+				adapter->rx_large_packets++;
+			}
+
 			napi_gro_receive(napi, skb);	/* send it up */
 
 			netdev->stats.rx_packets++;