Add support for tx_queue_setup_dqo ops.

DQO format has submission and completion queue pair for each Tx/Rx
queue. Note that with DQO format all descriptors and doorbells, as
well as counters are written in little-endian.

Signed-off-by: Junfeng Guo <junfeng....@intel.com>
Signed-off-by: Rushil Gupta <rush...@google.com>
Signed-off-by: Joshua Washington <joshw...@google.com>
Signed-off-by: Jeroen de Borst <jeroe...@google.com>
---
 drivers/net/gve/gve_ethdev.c |  21 +++-
 drivers/net/gve/gve_ethdev.h |  27 ++++-
 drivers/net/gve/gve_tx_dqo.c | 185 +++++++++++++++++++++++++++++++++++
 drivers/net/gve/meson.build  |   1 +
 4 files changed, 230 insertions(+), 4 deletions(-)
 create mode 100644 drivers/net/gve/gve_tx_dqo.c

diff --git a/drivers/net/gve/gve_ethdev.c b/drivers/net/gve/gve_ethdev.c
index cf28a4a3b7..90345b193d 100644
--- a/drivers/net/gve/gve_ethdev.c
+++ b/drivers/net/gve/gve_ethdev.c
@@ -298,6 +298,7 @@ gve_dev_info_get(struct rte_eth_dev *dev, struct 
rte_eth_dev_info *dev_info)
 
        dev_info->default_txconf = (struct rte_eth_txconf) {
                .tx_free_thresh = GVE_DEFAULT_TX_FREE_THRESH,
+               .tx_rs_thresh = GVE_DEFAULT_TX_RS_THRESH,
                .offloads = 0,
        };
 
@@ -528,6 +529,21 @@ static const struct eth_dev_ops gve_eth_dev_ops = {
        .xstats_get_names     = gve_xstats_get_names,
 };
 
+static const struct eth_dev_ops gve_eth_dev_ops_dqo = {
+       .dev_configure        = gve_dev_configure,
+       .dev_start            = gve_dev_start,
+       .dev_stop             = gve_dev_stop,
+       .dev_close            = gve_dev_close,
+       .dev_infos_get        = gve_dev_info_get,
+       .tx_queue_setup       = gve_tx_queue_setup_dqo,
+       .link_update          = gve_link_update,
+       .stats_get            = gve_dev_stats_get,
+       .stats_reset          = gve_dev_stats_reset,
+       .mtu_set              = gve_dev_mtu_set,
+       .xstats_get           = gve_xstats_get,
+       .xstats_get_names     = gve_xstats_get_names,
+};
+
 static void
 gve_free_counter_array(struct gve_priv *priv)
 {
@@ -770,8 +786,6 @@ gve_dev_init(struct rte_eth_dev *eth_dev)
        rte_be32_t *db_bar;
        int err;
 
-       eth_dev->dev_ops = &gve_eth_dev_ops;
-
        if (rte_eal_process_type() != RTE_PROC_PRIMARY)
                return 0;
 
@@ -807,10 +821,11 @@ gve_dev_init(struct rte_eth_dev *eth_dev)
                return err;
 
        if (gve_is_gqi(priv)) {
+               eth_dev->dev_ops = &gve_eth_dev_ops;
                eth_dev->rx_pkt_burst = gve_rx_burst;
                eth_dev->tx_pkt_burst = gve_tx_burst;
        } else {
-               PMD_DRV_LOG(ERR, "DQO_RDA is not implemented and will be added 
in the future");
+               eth_dev->dev_ops = &gve_eth_dev_ops_dqo;
        }
 
        eth_dev->data->mac_addrs = &priv->dev_addr;
diff --git a/drivers/net/gve/gve_ethdev.h b/drivers/net/gve/gve_ethdev.h
index 0b825113f6..6c6defa045 100644
--- a/drivers/net/gve/gve_ethdev.h
+++ b/drivers/net/gve/gve_ethdev.h
@@ -28,7 +28,8 @@
 #define PCI_MSIX_FLAGS_QSIZE   0x07FF  /* Table size */
 
 #define GVE_DEFAULT_RX_FREE_THRESH  512
-#define GVE_DEFAULT_TX_FREE_THRESH  256
+#define GVE_DEFAULT_TX_FREE_THRESH   32
+#define GVE_DEFAULT_TX_RS_THRESH     32
 #define GVE_TX_MAX_FREE_SZ          512
 
 #define GVE_MIN_BUF_SIZE           1024
@@ -53,6 +54,13 @@ union gve_tx_desc {
        struct gve_tx_seg_desc seg; /* subsequent descs for a packet */
 };
 
+/* Tx desc for DQO format */
+union gve_tx_desc_dqo {
+       struct gve_tx_pkt_desc_dqo pkt;
+       struct gve_tx_tso_context_desc_dqo tso_ctx;
+       struct gve_tx_general_context_desc_dqo general_ctx;
+};
+
 /* Offload features */
 union gve_tx_offload {
        uint64_t data;
@@ -100,8 +108,10 @@ struct gve_tx_queue {
        uint32_t tx_tail;
        uint16_t nb_tx_desc;
        uint16_t nb_free;
+       uint16_t nb_used;
        uint32_t next_to_clean;
        uint16_t free_thresh;
+       uint16_t rs_thresh;
 
        /* Only valid for DQO_QPL queue format */
        uint16_t sw_tail;
@@ -128,7 +138,15 @@ struct gve_tx_queue {
        struct gve_queue_resources *qres;
 
        /* newly added for DQO */
+       volatile union gve_tx_desc_dqo *tx_ring;
+       struct gve_tx_compl_desc *compl_ring;
+       const struct rte_memzone *compl_ring_mz;
        uint64_t compl_ring_phys_addr;
+       uint32_t complq_tail;
+       uint16_t sw_size;
+       uint8_t cur_gen_bit;
+       uint32_t last_desc_cleaned;
+       void **txqs;
 
        /* Only valid for DQO_RDA queue format */
        struct gve_tx_queue *complq;
@@ -342,4 +360,11 @@ gve_rx_burst(void *rxq, struct rte_mbuf **rx_pkts, 
uint16_t nb_pkts);
 uint16_t
 gve_tx_burst(void *txq, struct rte_mbuf **tx_pkts, uint16_t nb_pkts);
 
+/* Below functions are used for DQO */
+
+int
+gve_tx_queue_setup_dqo(struct rte_eth_dev *dev, uint16_t queue_id,
+                      uint16_t nb_desc, unsigned int socket_id,
+                      const struct rte_eth_txconf *conf);
+
 #endif /* _GVE_ETHDEV_H_ */
diff --git a/drivers/net/gve/gve_tx_dqo.c b/drivers/net/gve/gve_tx_dqo.c
new file mode 100644
index 0000000000..22d20ff16f
--- /dev/null
+++ b/drivers/net/gve/gve_tx_dqo.c
@@ -0,0 +1,185 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (c) 2022-2023 Google LLC
+ * Copyright (c) 2022-2023 Intel Corporation
+ */
+
+#include "gve_ethdev.h"
+#include "base/gve_adminq.h"
+
+static int
+check_tx_thresh_dqo(uint16_t nb_desc, uint16_t tx_rs_thresh,
+                   uint16_t tx_free_thresh)
+{
+       if (tx_rs_thresh >= (nb_desc - 2)) {
+               PMD_DRV_LOG(ERR, "tx_rs_thresh (%u) must be less than the "
+                           "number of TX descriptors (%u) minus 2",
+                           tx_rs_thresh, nb_desc);
+               return -EINVAL;
+       }
+       if (tx_free_thresh >= (nb_desc - 3)) {
+               PMD_DRV_LOG(ERR, "tx_free_thresh (%u) must be less than the "
+                           "number of TX descriptors (%u) minus 3.",
+                           tx_free_thresh, nb_desc);
+               return -EINVAL;
+       }
+       if (tx_rs_thresh > tx_free_thresh) {
+               PMD_DRV_LOG(ERR, "tx_rs_thresh (%u) must be less than or "
+                           "equal to tx_free_thresh (%u).",
+                           tx_rs_thresh, tx_free_thresh);
+               return -EINVAL;
+       }
+       if ((nb_desc % tx_rs_thresh) != 0) {
+               PMD_DRV_LOG(ERR, "tx_rs_thresh (%u) must be a divisor of the "
+                           "number of TX descriptors (%u).",
+                           tx_rs_thresh, nb_desc);
+               return -EINVAL;
+       }
+
+       return 0;
+}
+
+static void
+gve_reset_txq_dqo(struct gve_tx_queue *txq)
+{
+       struct rte_mbuf **sw_ring;
+       uint32_t size, i;
+
+       if (txq == NULL) {
+               PMD_DRV_LOG(DEBUG, "Pointer to txq is NULL");
+               return;
+       }
+
+       size = txq->nb_tx_desc * sizeof(union gve_tx_desc_dqo);
+       for (i = 0; i < size; i++)
+               ((volatile char *)txq->tx_ring)[i] = 0;
+
+       size = txq->sw_size * sizeof(struct gve_tx_compl_desc);
+       for (i = 0; i < size; i++)
+               ((volatile char *)txq->compl_ring)[i] = 0;
+
+       sw_ring = txq->sw_ring;
+       for (i = 0; i < txq->sw_size; i++)
+               sw_ring[i] = NULL;
+
+       txq->tx_tail = 0;
+       txq->nb_used = 0;
+
+       txq->last_desc_cleaned = 0;
+       txq->sw_tail = 0;
+       txq->nb_free = txq->nb_tx_desc - 1;
+
+       txq->complq_tail = 0;
+       txq->cur_gen_bit = 1;
+}
+
+int
+gve_tx_queue_setup_dqo(struct rte_eth_dev *dev, uint16_t queue_id,
+                      uint16_t nb_desc, unsigned int socket_id,
+                      const struct rte_eth_txconf *conf)
+{
+       struct gve_priv *hw = dev->data->dev_private;
+       const struct rte_memzone *mz;
+       struct gve_tx_queue *txq;
+       uint16_t free_thresh;
+       uint16_t rs_thresh;
+       uint16_t sw_size;
+       int err = 0;
+
+       if (nb_desc != hw->tx_desc_cnt) {
+               PMD_DRV_LOG(WARNING, "gve doesn't support nb_desc config, use 
hw nb_desc %u.",
+                           hw->tx_desc_cnt);
+       }
+       nb_desc = hw->tx_desc_cnt;
+
+       /* Allocate the TX queue data structure. */
+       txq = rte_zmalloc_socket("gve txq",
+                                sizeof(struct gve_tx_queue),
+                                RTE_CACHE_LINE_SIZE, socket_id);
+       if (txq == NULL) {
+               PMD_DRV_LOG(ERR, "Failed to allocate memory for tx queue 
structure");
+               return -ENOMEM;
+       }
+
+       /* need to check free_thresh here */
+       free_thresh = conf->tx_free_thresh ?
+                       conf->tx_free_thresh : GVE_DEFAULT_TX_FREE_THRESH;
+       rs_thresh = conf->tx_rs_thresh ?
+                       conf->tx_rs_thresh : GVE_DEFAULT_TX_RS_THRESH;
+       if (check_tx_thresh_dqo(nb_desc, rs_thresh, free_thresh))
+               return -EINVAL;
+
+       txq->nb_tx_desc = nb_desc;
+       txq->free_thresh = free_thresh;
+       txq->rs_thresh = rs_thresh;
+       txq->queue_id = queue_id;
+       txq->port_id = dev->data->port_id;
+       txq->ntfy_id = queue_id;
+       txq->hw = hw;
+       txq->ntfy_addr = 
&hw->db_bar2[rte_be_to_cpu_32(hw->irq_dbs[txq->ntfy_id].id)];
+
+       /* Allocate software ring */
+       sw_size = nb_desc * DQO_TX_MULTIPLIER;
+       txq->sw_ring = rte_zmalloc_socket("gve tx sw ring",
+                                         sw_size * sizeof(struct rte_mbuf *),
+                                         RTE_CACHE_LINE_SIZE, socket_id);
+       if (txq->sw_ring == NULL) {
+               PMD_DRV_LOG(ERR, "Failed to allocate memory for SW TX ring");
+               err = -ENOMEM;
+               goto free_txq;
+       }
+       txq->sw_size = sw_size;
+
+       /* Allocate TX hardware ring descriptors. */
+       mz = rte_eth_dma_zone_reserve(dev, "tx_ring", queue_id,
+                                     nb_desc * sizeof(union gve_tx_desc_dqo),
+                                     PAGE_SIZE, socket_id);
+       if (mz == NULL) {
+               PMD_DRV_LOG(ERR, "Failed to reserve DMA memory for TX");
+               err = -ENOMEM;
+               goto free_txq_sw_ring;
+       }
+       txq->tx_ring = (union gve_tx_desc_dqo *)mz->addr;
+       txq->tx_ring_phys_addr = mz->iova;
+       txq->mz = mz;
+
+       /* Allocate TX completion ring descriptors. */
+       mz = rte_eth_dma_zone_reserve(dev, "tx_compl_ring", queue_id,
+                                     sw_size * sizeof(struct 
gve_tx_compl_desc),
+                                     PAGE_SIZE, socket_id);
+       if (mz == NULL) {
+               PMD_DRV_LOG(ERR, "Failed to reserve DMA memory for TX 
completion queue");
+               err = -ENOMEM;
+               goto free_txq_mz;
+       }
+       txq->compl_ring = (struct gve_tx_compl_desc *)mz->addr;
+       txq->compl_ring_phys_addr = mz->iova;
+       txq->compl_ring_mz = mz;
+       txq->txqs = dev->data->tx_queues;
+
+       mz = rte_eth_dma_zone_reserve(dev, "txq_res", queue_id,
+                                     sizeof(struct gve_queue_resources),
+                                     PAGE_SIZE, socket_id);
+       if (mz == NULL) {
+               PMD_DRV_LOG(ERR, "Failed to reserve DMA memory for TX 
resource");
+               err = -ENOMEM;
+               goto free_txq_cq_mz;
+       }
+       txq->qres = (struct gve_queue_resources *)mz->addr;
+       txq->qres_mz = mz;
+
+       gve_reset_txq_dqo(txq);
+
+       dev->data->tx_queues[queue_id] = txq;
+
+       return 0;
+
+free_txq_cq_mz:
+       rte_memzone_free(txq->compl_ring_mz);
+free_txq_mz:
+       rte_memzone_free(txq->mz);
+free_txq_sw_ring:
+       rte_free(txq->sw_ring);
+free_txq:
+       rte_free(txq);
+       return err;
+}
diff --git a/drivers/net/gve/meson.build b/drivers/net/gve/meson.build
index af0010c01c..2ddb0cbf9e 100644
--- a/drivers/net/gve/meson.build
+++ b/drivers/net/gve/meson.build
@@ -11,6 +11,7 @@ sources = files(
         'base/gve_adminq.c',
         'gve_rx.c',
         'gve_tx.c',
+        'gve_tx_dqo.c',
         'gve_ethdev.c',
 )
 includes += include_directories('base')
-- 
2.34.1

Reply via email to