sfc: create inner-csum queues on EF10 if supported

If the MC reports the VXLAN_NVGRE datapath capability, then these queues
 can be used for checksum offload of encapsulated packets.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

drivers/net/ethernet/sfc/ef10.c

@@ -601,10 +601,14 @@ static int efx_ef10_probe(struct efx_nic *efx)
 	efx_ef10_read_licensed_features(efx);
 
 	/* We can have one VI for each vi_stride-byte region.
-	 * However, until we use TX option descriptors we need two TX queues
-	 * per channel.
+	 * However, until we use TX option descriptors we need up to four
+	 * TX queues per channel for different checksumming combinations.
 	 */
-	efx->tx_queues_per_channel = 2;
+	if (nic_data->datapath_caps &
+	    (1 << MC_CMD_GET_CAPABILITIES_OUT_VXLAN_NVGRE_LBN))
+		efx->tx_queues_per_channel = 4;
+	else
+		efx->tx_queues_per_channel = 2;
 	efx->max_vis = efx_ef10_mem_map_size(efx) / efx->vi_stride;
 	if (!efx->max_vis) {
 		netif_err(efx, drv, efx->net_dev, "error determining max VIs\n");
@@ -2146,7 +2150,9 @@ static int efx_ef10_irq_test_generate(struct efx_nic *efx)
 
 static int efx_ef10_tx_probe(struct efx_tx_queue *tx_queue)
 {
-	tx_queue->type = tx_queue->label & EFX_TXQ_TYPE_OUTER_CSUM;
+	/* low two bits of label are what we want for type */
+	BUILD_BUG_ON((EFX_TXQ_TYPE_OUTER_CSUM | EFX_TXQ_TYPE_INNER_CSUM) != 3);
+	tx_queue->type = tx_queue->label & 3;
 	return efx_nic_alloc_buffer(tx_queue->efx, &tx_queue->txd.buf,
 				    (tx_queue->ptr_mask + 1) *
 				    sizeof(efx_qword_t),
@@ -2256,6 +2262,7 @@ static u32 efx_ef10_tso_versions(struct efx_nic *efx)
 static void efx_ef10_tx_init(struct efx_tx_queue *tx_queue)
 {
 	bool csum_offload = tx_queue->type & EFX_TXQ_TYPE_OUTER_CSUM;
+	bool inner_csum = tx_queue->type & EFX_TXQ_TYPE_INNER_CSUM;
 	struct efx_channel *channel = tx_queue->channel;
 	struct efx_nic *efx = tx_queue->efx;
 	struct efx_ef10_nic_data *nic_data;
@@ -2282,7 +2289,7 @@ static void efx_ef10_tx_init(struct efx_tx_queue *tx_queue)
 	 * TSOv2 cannot be used with Hardware timestamping, and is never needed
 	 * for XDP tx.
 	 */
-	if (csum_offload && (nic_data->datapath_caps2 &
+	if ((csum_offload || inner_csum) && (nic_data->datapath_caps2 &
 			(1 << MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_LBN)) &&
 	    !tx_queue->timestamping && !tx_queue->xdp_tx) {
 		tso_v2 = true;
@@ -2303,12 +2310,14 @@ static void efx_ef10_tx_init(struct efx_tx_queue *tx_queue)
 	tx_queue->buffer[0].flags = EFX_TX_BUF_OPTION;
 	tx_queue->insert_count = 1;
 	txd = efx_tx_desc(tx_queue, 0);
-	EFX_POPULATE_QWORD_5(*txd,
+	EFX_POPULATE_QWORD_7(*txd,
 			     ESF_DZ_TX_DESC_IS_OPT, true,
 			     ESF_DZ_TX_OPTION_TYPE,
 			     ESE_DZ_TX_OPTION_DESC_CRC_CSUM,
 			     ESF_DZ_TX_OPTION_UDP_TCP_CSUM, csum_offload,
-			     ESF_DZ_TX_OPTION_IP_CSUM, csum_offload,
+			     ESF_DZ_TX_OPTION_IP_CSUM, csum_offload && !tso_v2,
+			     ESF_DZ_TX_OPTION_INNER_UDP_TCP_CSUM, inner_csum,
+			     ESF_DZ_TX_OPTION_INNER_IP_CSUM, inner_csum && !tso_v2,
 			     ESF_DZ_TX_TIMESTAMP, tx_queue->timestamping);
 	tx_queue->write_count = 1;
 

drivers/net/ethernet/sfc/mcdi_functions.c

@@ -165,6 +165,7 @@ int efx_mcdi_tx_init(struct efx_tx_queue *tx_queue, bool tso_v2)
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_INIT_TXQ_IN_LEN(EFX_MAX_DMAQ_SIZE * 8 /
 						       EFX_BUF_SIZE));
 	bool csum_offload = tx_queue->type & EFX_TXQ_TYPE_OUTER_CSUM;
+	bool inner_csum = tx_queue->type & EFX_TXQ_TYPE_INNER_CSUM;
 	size_t entries = tx_queue->txd.buf.len / EFX_BUF_SIZE;
 	struct efx_channel *channel = tx_queue->channel;
 	struct efx_nic *efx = tx_queue->efx;
@@ -194,16 +195,23 @@ int efx_mcdi_tx_init(struct efx_tx_queue *tx_queue, bool tso_v2)
 	inlen = MC_CMD_INIT_TXQ_IN_LEN(entries);
 
 	do {
-		MCDI_POPULATE_DWORD_4(inbuf, INIT_TXQ_IN_FLAGS,
+		/* TSOv2 implies IP header checksum offload for TSO frames,
+		 * so we can safely disable IP header checksum offload for
+		 * everything else.  If we don't have TSOv2, then we have to
+		 * enable IP header checksum offload, which is strictly
+		 * incorrect but better than breaking TSO.
+		 */
+		MCDI_POPULATE_DWORD_6(inbuf, INIT_TXQ_IN_FLAGS,
 				/* This flag was removed from mcdi_pcol.h for
 				 * the non-_EXT version of INIT_TXQ.  However,
 				 * firmware still honours it.
 				 */
 				INIT_TXQ_EXT_IN_FLAG_TSOV2_EN, tso_v2,
-				INIT_TXQ_IN_FLAG_IP_CSUM_DIS, !csum_offload,
+				INIT_TXQ_IN_FLAG_IP_CSUM_DIS, !(csum_offload && tso_v2),
 				INIT_TXQ_IN_FLAG_TCP_CSUM_DIS, !csum_offload,
-				INIT_TXQ_EXT_IN_FLAG_TIMESTAMP,
-						tx_queue->timestamping);
+				INIT_TXQ_EXT_IN_FLAG_TIMESTAMP, tx_queue->timestamping,
+				INIT_TXQ_IN_FLAG_INNER_IP_CSUM_EN, inner_csum && !tso_v2,
+				INIT_TXQ_IN_FLAG_INNER_TCP_CSUM_EN, inner_csum);
 
 		rc = efx_mcdi_rpc_quiet(efx, MC_CMD_INIT_TXQ, inbuf, inlen,
 					NULL, 0, NULL);