[dpdk-dev] [PATCH v3] net/mlx4: support CRC strip toggling

[Ophir Munk <ophirmu@mellanox.com>]

Previous to this commit mlx4 CRC stripping was executed by default and
there was no verbs API to disable it.

Signed-off-by: Ophir Munk <ophirmu@mellanox.com>
---
v1: initial version
v2: following internal reviews
v3: following dpdk.org mailing list reviews

 drivers/net/mlx4/mlx4.c      |  6 +++++-
 drivers/net/mlx4/mlx4.h      |  1 +
 drivers/net/mlx4/mlx4_rxq.c  | 33 +++++++++++++++++++++++++++++++--
 drivers/net/mlx4/mlx4_rxtx.c |  3 +++
 drivers/net/mlx4/mlx4_rxtx.h |  1 +
 5 files changed, 41 insertions(+), 3 deletions(-)

diff --git a/drivers/net/mlx4/mlx4.c b/drivers/net/mlx4/mlx4.c
index ee93daf..eea6e93 100644
--- a/drivers/net/mlx4/mlx4.c
+++ b/drivers/net/mlx4/mlx4.c
@@ -562,7 +562,7 @@ mlx4_pci_probe(struct rte_pci_driver *pci_drv, struct rte_pci_device *pci_dev)
 			(device_attr.vendor_part_id ==
 			 PCI_DEVICE_ID_MELLANOX_CONNECTX3PRO);
 		DEBUG("L2 tunnel checksum offloads are %ssupported",
-		      (priv->hw_csum_l2tun ? "" : "not "));
+		      priv->hw_csum_l2tun ? "" : "not ");
 		priv->hw_rss_sup = device_attr_ex.rss_caps.rx_hash_fields_mask;
 		if (!priv->hw_rss_sup) {
 			WARN("no RSS capabilities reported; disabling support"
@@ -578,6 +578,10 @@ mlx4_pci_probe(struct rte_pci_driver *pci_drv, struct rte_pci_device *pci_dev)
 		}
 		DEBUG("supported RSS hash fields mask: %016" PRIx64,
 		      priv->hw_rss_sup);
+		priv->hw_fcs_strip = !!(device_attr_ex.raw_packet_caps &
+					 IBV_RAW_PACKET_CAP_SCATTER_FCS);
+		DEBUG("FCS stripping toggling is %ssupported",
+		      priv->hw_fcs_strip ? "" : "not ");
 		/* Configure the first MAC address by default. */
 		if (mlx4_get_mac(priv, &mac.addr_bytes)) {
 			ERROR("cannot get MAC address, is mlx4_en loaded?"
diff --git a/drivers/net/mlx4/mlx4.h b/drivers/net/mlx4/mlx4.h
index 19c8a22..3ae3ce6 100644
--- a/drivers/net/mlx4/mlx4.h
+++ b/drivers/net/mlx4/mlx4.h
@@ -105,6 +105,7 @@ struct priv {
 	uint32_t isolated:1; /**< Toggle isolated mode. */
 	uint32_t hw_csum:1; /**< Checksum offload is supported. */
 	uint32_t hw_csum_l2tun:1; /**< Checksum support for L2 tunnels. */
+	uint32_t hw_fcs_strip:1; /**< FCS stripping toggling is supported. */
 	uint64_t hw_rss_sup; /**< Supported RSS hash fields (Verbs format). */
 	struct rte_intr_handle intr_handle; /**< Port interrupt handle. */
 	struct mlx4_drop *drop; /**< Shared resources for drop flow rules. */
diff --git a/drivers/net/mlx4/mlx4_rxq.c b/drivers/net/mlx4/mlx4_rxq.c
index 7a036ed..b437bb8 100644
--- a/drivers/net/mlx4/mlx4_rxq.c
+++ b/drivers/net/mlx4/mlx4_rxq.c
@@ -491,6 +491,8 @@ mlx4_rxq_attach(struct rxq *rxq)
 	const char *msg;
 	struct ibv_cq *cq = NULL;
 	struct ibv_wq *wq = NULL;
+	uint32_t create_flags = 0;
+	uint32_t comp_mask = 0;
 	volatile struct mlx4_wqe_data_seg (*wqes)[];
 	unsigned int i;
 	int ret;
@@ -503,6 +505,11 @@ mlx4_rxq_attach(struct rxq *rxq)
 		msg = "CQ creation failure";
 		goto error;
 	}
+	/* By default, FCS (CRC) is stripped by hardware. */
+	if (rxq->crc_present) {
+		create_flags |= IBV_WQ_FLAGS_SCATTER_FCS;
+		comp_mask |= IBV_WQ_INIT_ATTR_FLAGS;
+	}
 	wq = mlx4_glue->create_wq
 		(priv->ctx,
 		 &(struct ibv_wq_init_attr){
@@ -511,6 +518,8 @@ mlx4_rxq_attach(struct rxq *rxq)
 			.max_sge = sges_n,
 			.pd = priv->pd,
 			.cq = cq,
+			.comp_mask = comp_mask,
+			.create_flags = create_flags,
 		 });
 	if (!wq) {
 		ret = errno ? errno : EINVAL;
@@ -649,9 +658,10 @@ mlx4_rxq_detach(struct rxq *rxq)
 uint64_t
 mlx4_get_rx_queue_offloads(struct priv *priv)
 {
-	uint64_t offloads = DEV_RX_OFFLOAD_SCATTER |
-			    DEV_RX_OFFLOAD_CRC_STRIP;
+	uint64_t offloads = DEV_RX_OFFLOAD_SCATTER;
 
+	if (priv->hw_fcs_strip)
+		offloads |= DEV_RX_OFFLOAD_CRC_STRIP;
 	if (priv->hw_csum)
 		offloads |= DEV_RX_OFFLOAD_CHECKSUM;
 	return offloads;
@@ -736,6 +746,7 @@ mlx4_rx_queue_setup(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
 		},
 	};
 	int ret;
+	uint32_t crc_present;
 
 	(void)conf; /* Thresholds configuration (ignored). */
 	DEBUG("%p: configuring queue %u for %u descriptors",
@@ -774,6 +785,23 @@ mlx4_rx_queue_setup(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
 		     " to the next power of two (%u)",
 		     (void *)dev, idx, desc);
 	}
+	/* By default, FCS (CRC) is stripped by hardware. */
+	if (conf->offloads & DEV_RX_OFFLOAD_CRC_STRIP) {
+		crc_present = 0;
+	} else if (priv->hw_fcs_strip) {
+		crc_present = 1;
+	} else {
+		WARN("%p: CRC stripping has been disabled but will still"
+		     " be performed by hardware, make sure MLNX_OFED and"
+		     " firmware are up to date",
+		     (void *)dev);
+		crc_present = 0;
+	}
+	DEBUG("%p: CRC stripping is %s, %u bytes will be subtracted from"
+	      " incoming frames to hide it",
+	      (void *)dev,
+	      crc_present ? "disabled" : "enabled",
+	      crc_present << 2);
 	/* Allocate and initialize Rx queue. */
 	mlx4_zmallocv_socket("RXQ", vec, RTE_DIM(vec), socket);
 	if (!rxq) {
@@ -793,6 +821,7 @@ mlx4_rx_queue_setup(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
 			(conf->offloads & DEV_RX_OFFLOAD_CHECKSUM),
 		.csum_l2tun = priv->hw_csum_l2tun &&
 			      (conf->offloads & DEV_RX_OFFLOAD_CHECKSUM),
+		.crc_present = crc_present,
 		.l2tun_offload = priv->hw_csum_l2tun,
 		.stats = {
 			.idx = idx,
diff --git a/drivers/net/mlx4/mlx4_rxtx.c b/drivers/net/mlx4/mlx4_rxtx.c
index 8ca8b77..2a10058 100644
--- a/drivers/net/mlx4/mlx4_rxtx.c
+++ b/drivers/net/mlx4/mlx4_rxtx.c
@@ -934,11 +934,14 @@ mlx4_rx_burst(void *dpdk_rxq, struct rte_mbuf **pkts, uint16_t pkts_n)
 				goto skip;
 			}
 			pkt = seg;
+			assert(len >= (rxq->crc_present << 2));
 			/* Update packet information. */
 			pkt->packet_type =
 				rxq_cq_to_pkt_type(cqe, rxq->l2tun_offload);
 			pkt->ol_flags = PKT_RX_RSS_HASH;
 			pkt->hash.rss = cqe->immed_rss_invalid;
+			if (rxq->crc_present)
+				len -= ETHER_CRC_LEN;
 			pkt->pkt_len = len;
 			if (rxq->csum | rxq->csum_l2tun) {
 				uint32_t flags =
diff --git a/drivers/net/mlx4/mlx4_rxtx.h b/drivers/net/mlx4/mlx4_rxtx.h
index c12bd39..a0633bf 100644
--- a/drivers/net/mlx4/mlx4_rxtx.h
+++ b/drivers/net/mlx4/mlx4_rxtx.h
@@ -52,6 +52,7 @@ struct rxq {
 	volatile uint32_t *rq_db; /**< RQ doorbell record. */
 	uint32_t csum:1; /**< Enable checksum offloading. */
 	uint32_t csum_l2tun:1; /**< Same for L2 tunnels. */
+	uint32_t crc_present:1; /**< CRC must be subtracted. */
 	uint32_t l2tun_offload:1; /**< L2 tunnel offload is enabled. */
 	struct mlx4_cq mcq;  /**< Info for directly manipulating the CQ. */
 	struct mlx4_rxq_stats stats; /**< Rx queue counters. */
-- 
2.7.4