sfc: implement encapsulated TSO on EF10
>From the 8000 series onwards, EF10 NICs with suitable firmware are able
to perform TSO within VXLAN or NVGRE encapsulation.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index c6507d1..4775b82 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -2179,10 +2179,11 @@ int efx_ef10_tx_tso_desc(struct efx_tx_queue *tx_queue, struct sk_buff *skb,
bool *data_mapped)
{
struct efx_tx_buffer *buffer;
+ u16 inner_ipv4_id = 0;
+ u16 outer_ipv4_id = 0;
struct tcphdr *tcp;
struct iphdr *ip;
-
- u16 ipv4_id;
+ u16 ip_tot_len;
u32 seqnum;
u32 mss;
@@ -2195,21 +2196,43 @@ int efx_ef10_tx_tso_desc(struct efx_tx_queue *tx_queue, struct sk_buff *skb,
return -EINVAL;
}
- ip = ip_hdr(skb);
- if (ip->version == 4) {
- /* Modify IPv4 header if needed. */
- ip->tot_len = 0;
- ip->check = 0;
- ipv4_id = ntohs(ip->id);
- } else {
- /* Modify IPv6 header if needed. */
- struct ipv6hdr *ipv6 = ipv6_hdr(skb);
+ if (skb->encapsulation) {
+ if (!tx_queue->tso_encap)
+ return -EINVAL;
+ ip = ip_hdr(skb);
+ if (ip->version == 4)
+ outer_ipv4_id = ntohs(ip->id);
- ipv6->payload_len = 0;
- ipv4_id = 0;
+ ip = inner_ip_hdr(skb);
+ tcp = inner_tcp_hdr(skb);
+ } else {
+ ip = ip_hdr(skb);
+ tcp = tcp_hdr(skb);
}
- tcp = tcp_hdr(skb);
+ /* 8000-series EF10 hardware requires that IP Total Length be
+ * greater than or equal to the value it will have in each segment
+ * (which is at most mss + 208 + TCP header length), but also less
+ * than (0x10000 - inner_network_header). Otherwise the TCP
+ * checksum calculation will be broken for encapsulated packets.
+ * We fill in ip->tot_len with 0xff30, which should satisfy the
+ * first requirement unless the MSS is ridiculously large (which
+ * should be impossible as the driver max MTU is 9216); it is
+ * guaranteed to satisfy the second as we only attempt TSO if
+ * inner_network_header <= 208.
+ */
+ ip_tot_len = -EFX_TSO2_MAX_HDRLEN;
+ EFX_WARN_ON_ONCE_PARANOID(mss + EFX_TSO2_MAX_HDRLEN +
+ (tcp->doff << 2u) > ip_tot_len);
+
+ if (ip->version == 4) {
+ ip->tot_len = htons(ip_tot_len);
+ ip->check = 0;
+ inner_ipv4_id = ntohs(ip->id);
+ } else {
+ ((struct ipv6hdr *)ip)->payload_len = htons(ip_tot_len);
+ }
+
seqnum = ntohl(tcp->seq);
buffer = efx_tx_queue_get_insert_buffer(tx_queue);
@@ -2222,7 +2245,7 @@ int efx_ef10_tx_tso_desc(struct efx_tx_queue *tx_queue, struct sk_buff *skb,
ESF_DZ_TX_OPTION_TYPE, ESE_DZ_TX_OPTION_DESC_TSO,
ESF_DZ_TX_TSO_OPTION_TYPE,
ESE_DZ_TX_TSO_OPTION_DESC_FATSO2A,
- ESF_DZ_TX_TSO_IP_ID, ipv4_id,
+ ESF_DZ_TX_TSO_IP_ID, inner_ipv4_id,
ESF_DZ_TX_TSO_TCP_SEQNO, seqnum
);
++tx_queue->insert_count;
@@ -2232,11 +2255,12 @@ int efx_ef10_tx_tso_desc(struct efx_tx_queue *tx_queue, struct sk_buff *skb,
buffer->flags = EFX_TX_BUF_OPTION;
buffer->len = 0;
buffer->unmap_len = 0;
- EFX_POPULATE_QWORD_4(buffer->option,
+ EFX_POPULATE_QWORD_5(buffer->option,
ESF_DZ_TX_DESC_IS_OPT, 1,
ESF_DZ_TX_OPTION_TYPE, ESE_DZ_TX_OPTION_DESC_TSO,
ESF_DZ_TX_TSO_OPTION_TYPE,
ESE_DZ_TX_TSO_OPTION_DESC_FATSO2B,
+ ESF_DZ_TX_TSO_OUTER_IPID, outer_ipv4_id,
ESF_DZ_TX_TSO_TCP_MSS, mss
);
++tx_queue->insert_count;
@@ -2322,6 +2346,9 @@ static void efx_ef10_tx_init(struct efx_tx_queue *tx_queue)
ESF_DZ_TX_TIMESTAMP, tx_queue->timestamping);
tx_queue->write_count = 1;
+ if (tx_queue->tso_version == 2 && efx_has_cap(efx, TX_TSO_V2_ENCAP))
+ tx_queue->tso_encap = true;
+
wmb();
efx_ef10_push_tx_desc(tx_queue, txd);
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index ddcd1c4..a4c0445 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -77,6 +77,9 @@
/* Minimum MTU, from RFC791 (IP) */
#define EFX_MIN_MTU 68
+/* Maximum total header length for TSOv2 */
+#define EFX_TSO2_MAX_HDRLEN 208
+
/* Size of an RX scatter buffer. Small enough to pack 2 into a 4K page,
* and should be a multiple of the cache line size.
*/
@@ -195,6 +198,7 @@ struct efx_tx_buffer {
* Is our index within @channel->tx_queue array.
* @type: configuration type of this TX queue. A bitmask of %EFX_TXQ_TYPE_* flags.
* @tso_version: Version of TSO in use for this queue.
+ * @tso_encap: Is encapsulated TSO supported? Supported in TSOv2 on 8000 series.
* @channel: The associated channel
* @core_txq: The networking core TX queue structure
* @buffer: The software buffer ring
@@ -258,6 +262,7 @@ struct efx_tx_queue {
unsigned int label;
unsigned int type;
unsigned int tso_version;
+ bool tso_encap;
struct efx_channel *channel;
struct netdev_queue *core_txq;
struct efx_tx_buffer *buffer;