From: longli@linuxonhyperv.com
To: Ferruh Yigit <ferruh.yigit@intel.com>
Cc: dev@dpdk.org, Ajay Sharma <sharmaajay@microsoft.com>,
Stephen Hemminger <sthemmin@microsoft.com>,
Long Li <longli@microsoft.com>
Subject: [PATCH 15/17] net/mana: add function to send packets
Date: Fri, 1 Jul 2022 02:02:45 -0700 [thread overview]
Message-ID: <1656666167-26035-16-git-send-email-longli@linuxonhyperv.com> (raw)
In-Reply-To: <1656666167-26035-1-git-send-email-longli@linuxonhyperv.com>
From: Long Li <longli@microsoft.com>
With all the TX queues created, MANA can send packets over those queues.
Signed-off-by: Long Li <longli@microsoft.com>
---
doc/guides/nics/features/mana.ini | 1 +
drivers/net/mana/mana.c | 1 +
drivers/net/mana/mana.h | 65 ++++++++
drivers/net/mana/mp.c | 1 +
drivers/net/mana/tx.c | 240 ++++++++++++++++++++++++++++++
5 files changed, 308 insertions(+)
diff --git a/doc/guides/nics/features/mana.ini b/doc/guides/nics/features/mana.ini
index b47860554d..bd50fe81d6 100644
--- a/doc/guides/nics/features/mana.ini
+++ b/doc/guides/nics/features/mana.ini
@@ -4,6 +4,7 @@
; Refer to default.ini for the full list of available PMD features.
;
[Features]
+Free Tx mbuf on demand = Y
Link status = P
Linux = Y
L3 checksum offload = Y
diff --git a/drivers/net/mana/mana.c b/drivers/net/mana/mana.c
index 6d8a0512c1..0ffa2882e0 100644
--- a/drivers/net/mana/mana.c
+++ b/drivers/net/mana/mana.c
@@ -987,6 +987,7 @@ static int mana_pci_probe_mac(struct rte_pci_driver *pci_drv __rte_unused,
/* fd is no not used after mapping doorbell */
close(fd);
+ eth_dev->tx_pkt_burst = mana_tx_burst;
eth_dev->rx_pkt_burst = mana_rx_burst;
rte_spinlock_lock(&mana_shared_data->lock);
diff --git a/drivers/net/mana/mana.h b/drivers/net/mana/mana.h
index 626abc431a..2a74e54007 100644
--- a/drivers/net/mana/mana.h
+++ b/drivers/net/mana/mana.h
@@ -62,6 +62,47 @@ struct mana_shared_data {
#define NOT_USING_CLIENT_DATA_UNIT 0
+enum tx_packet_format_v2 {
+ short_packet_format = 0,
+ long_packet_format = 1
+};
+
+struct transmit_short_oob_v2 {
+ enum tx_packet_format_v2 packet_format : 2;
+ uint32_t tx_is_outer_IPv4 : 1;
+ uint32_t tx_is_outer_IPv6 : 1;
+ uint32_t tx_compute_IP_header_checksum : 1;
+ uint32_t tx_compute_TCP_checksum : 1;
+ uint32_t tx_compute_UDP_checksum : 1;
+ uint32_t suppress_tx_CQE_generation : 1;
+ uint32_t VCQ_number : 24;
+ uint32_t tx_transport_header_offset : 10;
+ uint32_t VSQ_frame_num : 14;
+ uint32_t short_vport_offset : 8;
+};
+
+struct transmit_long_oob_v2 {
+ uint32_t TxIsEncapsulatedPacket : 1;
+ uint32_t TxInnerIsIPv6 : 1;
+ uint32_t TxInnerTcpOptionsPresent : 1;
+ uint32_t InjectVlanPriorTag : 1;
+ uint32_t Reserved1 : 12;
+ uint32_t PriorityCodePoint : 3;
+ uint32_t DropEligibleIndicator : 1;
+ uint32_t VlanIdentifier : 12;
+ uint32_t TxInnerFrameOffset : 10;
+ uint32_t TxInnerIpHeaderRelativeOffset : 6;
+ uint32_t LongVportOffset : 12;
+ uint32_t Reserved3 : 4;
+ uint32_t Reserved4 : 32;
+ uint32_t Reserved5 : 32;
+};
+
+struct transmit_oob_v2 {
+ struct transmit_short_oob_v2 short_oob;
+ struct transmit_long_oob_v2 long_oob;
+};
+
enum gdma_queue_types {
gdma_queue_type_invalid = 0,
gdma_queue_send,
@@ -183,6 +224,17 @@ enum mana_cqe_type {
CQE_RX_COALESCED_4 = 2,
CQE_RX_OBJECT_FENCE = 3,
CQE_RX_TRUNCATED = 4,
+
+ CQE_TX_OKAY = 32,
+ CQE_TX_SA_DROP = 33,
+ CQE_TX_MTU_DROP = 34,
+ CQE_TX_INVALID_OOB = 35,
+ CQE_TX_INVALID_ETH_TYPE = 36,
+ CQE_TX_HDR_PROCESSING_ERROR = 37,
+ CQE_TX_VF_DISABLED = 38,
+ CQE_TX_VPORT_IDX_OUT_OF_RANGE = 39,
+ CQE_TX_VPORT_DISABLED = 40,
+ CQE_TX_VLAN_TAGGING_VIOLATION = 41,
};
struct mana_cqe_header {
@@ -191,6 +243,17 @@ struct mana_cqe_header {
uint32_t vendor_err : 24;
}; /* HW DATA */
+struct mana_tx_comp_oob {
+ struct mana_cqe_header cqe_hdr;
+
+ uint32_t tx_data_offset;
+
+ uint32_t tx_sgl_offset : 5;
+ uint32_t tx_wqe_offset : 27;
+
+ uint32_t reserved[12];
+}; /* HW DATA */
+
/* NDIS HASH Types */
#define BIT(nr) (1 << (nr))
#define NDIS_HASH_IPV4 BIT(0)
@@ -407,6 +470,8 @@ uint8_t *gdma_get_wqe_pointer(struct mana_gdma_queue *queue);
uint16_t mana_rx_burst(void *dpdk_rxq, struct rte_mbuf **rx_pkts,
uint16_t pkts_n);
+uint16_t mana_tx_burst(void *dpdk_txq, struct rte_mbuf **tx_pkts,
+ uint16_t pkts_n);
uint16_t mana_rx_burst_removed(void *dpdk_rxq, struct rte_mbuf **pkts,
uint16_t pkts_n);
diff --git a/drivers/net/mana/mp.c b/drivers/net/mana/mp.c
index a4c612c1a3..ea9014db8d 100644
--- a/drivers/net/mana/mp.c
+++ b/drivers/net/mana/mp.c
@@ -160,6 +160,7 @@ static int mana_mp_secondary_handle(const struct rte_mp_msg *mp_msg,
case MANA_MP_REQ_START_RXTX:
DRV_LOG(INFO, "Port %u starting datapath", dev->data->port_id);
+ dev->tx_pkt_burst = mana_tx_burst;
dev->rx_pkt_burst = mana_rx_burst;
rte_mb();
diff --git a/drivers/net/mana/tx.c b/drivers/net/mana/tx.c
index dde911e548..211af6e124 100644
--- a/drivers/net/mana/tx.c
+++ b/drivers/net/mana/tx.c
@@ -178,3 +178,243 @@ static inline uint16_t get_vsq_frame_num(uint32_t vsq)
v.gdma_txq_id = vsq;
return v.vsq_frame;
}
+
+uint16_t mana_tx_burst(void *dpdk_txq, struct rte_mbuf **tx_pkts,
+ uint16_t nb_pkts)
+{
+ struct mana_txq *txq = dpdk_txq;
+ struct mana_priv *priv = txq->priv;
+ struct gdma_comp comp;
+ int ret;
+ void *db_page;
+
+ /* Process send completions from GDMA */
+ while (gdma_poll_completion_queue(&txq->gdma_cq, &comp) == 1) {
+ struct mana_txq_desc *desc =
+ &txq->desc_ring[txq->desc_ring_tail];
+ struct mana_tx_comp_oob *oob =
+ (struct mana_tx_comp_oob *)&comp.completion_data[0];
+
+ if (oob->cqe_hdr.cqe_type != CQE_TX_OKAY) {
+ DRV_LOG(ERR,
+ "mana_tx_comp_oob cqe_type %u vendor_err %u",
+ oob->cqe_hdr.cqe_type, oob->cqe_hdr.vendor_err);
+ txq->stats.errors++;
+ } else {
+ DRV_LOG(DEBUG, "mana_tx_comp_oob CQE_TX_OKAY");
+ txq->stats.packets++;
+ }
+
+ if (!desc->pkt) {
+ DRV_LOG(ERR, "mana_txq_desc has a NULL pkt");
+ } else {
+ txq->stats.bytes += desc->pkt->data_len;
+ rte_pktmbuf_free(desc->pkt);
+ }
+
+ desc->pkt = NULL;
+ txq->desc_ring_tail = (txq->desc_ring_tail + 1) % txq->num_desc;
+ txq->gdma_sq.tail += desc->wqe_size_in_bu;
+ }
+
+ /* Post send requests to GDMA */
+ uint16_t pkt_idx;
+
+ for (pkt_idx = 0; pkt_idx < nb_pkts; pkt_idx++) {
+ struct rte_mbuf *m_pkt = tx_pkts[pkt_idx];
+ struct rte_mbuf *m_seg = m_pkt;
+ struct transmit_oob_v2 tx_oob = {0};
+ struct one_sgl sgl = {0};
+
+ /* Drop the packet if it exceeds max segments */
+ if (m_pkt->nb_segs > priv->max_send_sge) {
+ DRV_LOG(ERR, "send packet segments %d exceeding max",
+ m_pkt->nb_segs);
+ continue;
+ }
+
+ /* Fill in the oob */
+ tx_oob.short_oob.packet_format = short_packet_format;
+ tx_oob.short_oob.tx_is_outer_IPv4 =
+ m_pkt->ol_flags & RTE_MBUF_F_TX_IPV4 ? 1 : 0;
+ tx_oob.short_oob.tx_is_outer_IPv6 =
+ m_pkt->ol_flags & RTE_MBUF_F_TX_IPV6 ? 1 : 0;
+
+ tx_oob.short_oob.tx_compute_IP_header_checksum =
+ m_pkt->ol_flags & RTE_MBUF_F_TX_IP_CKSUM ? 1 : 0;
+
+ if ((m_pkt->ol_flags & RTE_MBUF_F_TX_L4_MASK) ==
+ RTE_MBUF_F_TX_TCP_CKSUM) {
+ struct rte_tcp_hdr *tcp_hdr;
+
+ /* HW needs partial TCP checksum */
+
+ tcp_hdr = rte_pktmbuf_mtod_offset(m_pkt,
+ struct rte_tcp_hdr *,
+ m_pkt->l2_len + m_pkt->l3_len);
+
+ if (m_pkt->ol_flags & RTE_MBUF_F_TX_IPV4) {
+ struct rte_ipv4_hdr *ip_hdr;
+
+ ip_hdr = rte_pktmbuf_mtod_offset(m_pkt,
+ struct rte_ipv4_hdr *,
+ m_pkt->l2_len);
+ tcp_hdr->cksum = rte_ipv4_phdr_cksum(ip_hdr,
+ m_pkt->ol_flags);
+
+ } else if (m_pkt->ol_flags & RTE_MBUF_F_TX_IPV6) {
+ struct rte_ipv6_hdr *ip_hdr;
+
+ ip_hdr = rte_pktmbuf_mtod_offset(m_pkt,
+ struct rte_ipv6_hdr *,
+ m_pkt->l2_len);
+ tcp_hdr->cksum = rte_ipv6_phdr_cksum(ip_hdr,
+ m_pkt->ol_flags);
+ } else {
+ DRV_LOG(ERR, "Invalid input for TCP CKSUM");
+ }
+
+ tx_oob.short_oob.tx_compute_TCP_checksum = 1;
+ tx_oob.short_oob.tx_transport_header_offset =
+ m_pkt->l2_len + m_pkt->l3_len;
+ }
+
+ if ((m_pkt->ol_flags & RTE_MBUF_F_TX_L4_MASK) ==
+ RTE_MBUF_F_TX_UDP_CKSUM) {
+ struct rte_udp_hdr *udp_hdr;
+
+ /* HW needs partial UDP checksum */
+ udp_hdr = rte_pktmbuf_mtod_offset(m_pkt,
+ struct rte_udp_hdr *,
+ m_pkt->l2_len + m_pkt->l3_len);
+
+ if (m_pkt->ol_flags & RTE_MBUF_F_TX_IPV4) {
+ struct rte_ipv4_hdr *ip_hdr;
+
+ ip_hdr = rte_pktmbuf_mtod_offset(m_pkt,
+ struct rte_ipv4_hdr *,
+ m_pkt->l2_len);
+
+ udp_hdr->dgram_cksum =
+ rte_ipv4_phdr_cksum(ip_hdr,
+ m_pkt->ol_flags);
+
+ } else if (m_pkt->ol_flags & RTE_MBUF_F_TX_IPV6) {
+ struct rte_ipv6_hdr *ip_hdr;
+
+ ip_hdr = rte_pktmbuf_mtod_offset(m_pkt,
+ struct rte_ipv6_hdr *,
+ m_pkt->l2_len);
+
+ udp_hdr->dgram_cksum =
+ rte_ipv6_phdr_cksum(ip_hdr,
+ m_pkt->ol_flags);
+
+ } else {
+ DRV_LOG(ERR, "Invalid input for UDP CKSUM");
+ }
+
+ tx_oob.short_oob.tx_compute_UDP_checksum = 1;
+ }
+
+ tx_oob.short_oob.suppress_tx_CQE_generation = 0;
+ tx_oob.short_oob.VCQ_number = txq->gdma_cq.id;
+
+ tx_oob.short_oob.VSQ_frame_num =
+ get_vsq_frame_num(txq->gdma_sq.id);
+ tx_oob.short_oob.short_vport_offset = txq->tx_vp_offset;
+
+ DRV_LOG(DEBUG, "tx_oob packet_format %u ipv4 %u ipv6 %u",
+ tx_oob.short_oob.packet_format,
+ tx_oob.short_oob.tx_is_outer_IPv4,
+ tx_oob.short_oob.tx_is_outer_IPv6);
+
+ DRV_LOG(DEBUG, "tx_oob checksum ip %u tcp %u udp %u offset %u",
+ tx_oob.short_oob.tx_compute_IP_header_checksum,
+ tx_oob.short_oob.tx_compute_TCP_checksum,
+ tx_oob.short_oob.tx_compute_UDP_checksum,
+ tx_oob.short_oob.tx_transport_header_offset);
+
+ DRV_LOG(DEBUG, "pkt[%d]: buf_addr 0x%p, nb_segs %d, pkt_len %d",
+ pkt_idx, m_pkt->buf_addr, m_pkt->nb_segs,
+ m_pkt->pkt_len);
+
+ /* Create SGL for packet data buffers */
+ for (uint16_t seg_idx = 0; seg_idx < m_pkt->nb_segs; seg_idx++) {
+ struct mana_mr_cache *mr =
+ find_pmd_mr(&txq->mr_btree, priv, m_seg);
+
+ if (!mr) {
+ DRV_LOG(ERR, "failed to get MR, pkt_idx %u",
+ pkt_idx);
+ return pkt_idx;
+ }
+
+ sgl.gdma_sgl[seg_idx].address =
+ rte_cpu_to_le_64(rte_pktmbuf_mtod(m_seg,
+ uint64_t));
+ sgl.gdma_sgl[seg_idx].size = m_seg->data_len;
+ sgl.gdma_sgl[seg_idx].memory_key = mr->lkey;
+
+ DRV_LOG(DEBUG, "seg idx %u address %lx size %x key %x",
+ seg_idx, sgl.gdma_sgl[seg_idx].address,
+ sgl.gdma_sgl[seg_idx].size,
+ sgl.gdma_sgl[seg_idx].memory_key);
+
+ m_seg = m_seg->next;
+ }
+
+ struct gdma_work_request work_req = {0};
+ struct gdma_posted_wqe_info wqe_info = {0};
+
+ work_req.gdma_header.struct_size = sizeof(work_req);
+ wqe_info.gdma_header.struct_size = sizeof(wqe_info);
+
+ work_req.sgl = sgl.gdma_sgl;
+ work_req.num_sgl_elements = m_pkt->nb_segs;
+ work_req.inline_oob_size_in_bytes =
+ sizeof(struct transmit_short_oob_v2);
+ work_req.inline_oob_data = &tx_oob;
+ work_req.flags = 0;
+ work_req.client_data_unit = NOT_USING_CLIENT_DATA_UNIT;
+
+ ret = gdma_post_work_request(&txq->gdma_sq, &work_req,
+ &wqe_info);
+ if (!ret) {
+ struct mana_txq_desc *desc =
+ &txq->desc_ring[txq->desc_ring_head];
+
+ /* Update queue for tracking pending requests */
+ desc->pkt = m_pkt;
+ desc->wqe_size_in_bu = wqe_info.wqe_size_in_bu;
+ txq->desc_ring_head =
+ (txq->desc_ring_head + 1) % txq->num_desc;
+
+ DRV_LOG(DEBUG, "nb_pkts %u pkt[%d] sent",
+ nb_pkts, pkt_idx);
+ } else {
+ DRV_LOG(INFO, "pkt[%d] failed to post send ret %d",
+ pkt_idx, ret);
+ break;
+ }
+ }
+
+ /* Ring hardware door bell */
+ db_page = priv->db_page;
+ if (rte_eal_process_type() == RTE_PROC_SECONDARY) {
+ struct rte_eth_dev *dev =
+ &rte_eth_devices[priv->dev_data->port_id];
+ struct mana_process_priv *process_priv = dev->process_private;
+
+ db_page = process_priv->db_page;
+ }
+
+ ret = mana_ring_doorbell(db_page, gdma_queue_send,
+ txq->gdma_sq.id,
+ txq->gdma_sq.head *
+ GDMA_WQE_ALIGNMENT_UNIT_SIZE);
+ if (ret)
+ DRV_LOG(ERR, "mana_ring_doorbell failed ret %d", ret);
+
+ return pkt_idx;
+}
--
2.17.1
next prev parent reply other threads:[~2022-07-01 9:04 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-07-01 9:02 [PATCH 00/17] Introduce Microsoft Azure Network Adatper (MANA) PMD longli
2022-07-01 9:02 ` [PATCH 01/17] net/mana: add basic driver, build environment and doc longli
2022-07-01 16:29 ` Stephen Hemminger
2022-07-01 16:44 ` Stephen Hemminger
2022-07-01 16:45 ` Stephen Hemminger
2022-07-01 16:47 ` Stephen Hemminger
2022-07-03 7:56 ` Long Li
2022-07-04 16:35 ` Stephen Hemminger
2022-07-04 16:41 ` Stephen Hemminger
2022-07-05 19:50 ` Long Li
2022-07-01 16:49 ` Stephen Hemminger
2022-07-01 19:40 ` Long Li
2022-07-01 9:02 ` [PATCH 02/17] net/mana: add device configuration and stop longli
2022-07-01 16:34 ` Stephen Hemminger
2022-07-01 9:02 ` [PATCH 03/17] net/mana: add function to report support ptypes longli
2022-07-01 9:02 ` [PATCH 04/17] net/mana: add link update longli
2022-07-01 9:02 ` [PATCH 05/17] net/mana: add function for device removal interrupts longli
2022-07-01 9:02 ` [PATCH 06/17] net/mana: add device info longli
2022-07-01 9:02 ` [PATCH 07/17] net/mana: add function to configure RSS longli
2022-07-01 9:02 ` [PATCH 08/17] net/mana: add function to configure RX queues longli
2022-07-01 9:02 ` [PATCH 09/17] net/mana: add function to configure TX queues longli
2022-07-01 9:02 ` [PATCH 10/17] net/mana: implement memory registration longli
2022-07-01 16:37 ` Stephen Hemminger
2022-07-01 9:02 ` [PATCH 11/17] net/mana: implement the hardware layer operations longli
2022-07-01 16:38 ` Stephen Hemminger
2022-07-01 9:02 ` [PATCH 12/17] net/mana: add function to start/stop TX queues longli
2022-07-01 16:39 ` Stephen Hemminger
2022-07-01 9:02 ` [PATCH 13/17] net/mana: add function to start/stop RX queues longli
2022-07-01 16:40 ` Stephen Hemminger
2022-07-02 8:42 ` Long Li
2022-07-01 9:02 ` [PATCH 14/17] net/mana: add function to receive packets longli
2022-07-01 9:02 ` longli [this message]
2022-07-01 9:02 ` [PATCH 16/17] net/mana: add function to start/stop device longli
2022-07-01 9:02 ` [PATCH 17/17] net/mana: add function to report queue stats longli
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1656666167-26035-16-git-send-email-longli@linuxonhyperv.com \
--to=longli@linuxonhyperv.com \
--cc=dev@dpdk.org \
--cc=ferruh.yigit@intel.com \
--cc=longli@microsoft.com \
--cc=sharmaajay@microsoft.com \
--cc=sthemmin@microsoft.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).