/*
- * Copyright (c) 2015, Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2015-2016, Mellanox Technologies. All rights reserved.
*
* This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU
* SOFTWARE.
*/
+#include <net/tc_act/tc_gact.h>
+#include <net/pkt_cls.h>
#include <linux/mlx5/fs.h>
+#include <net/vxlan.h>
#include "en.h"
+#include "en_tc.h"
#include "eswitch.h"
+#include "vxlan.h"
struct mlx5e_rq_param {
u32 rqc[MLX5_ST_SZ_DW(rqc)];
u32 sqc[MLX5_ST_SZ_DW(sqc)];
struct mlx5_wq_param wq;
u16 max_inline;
+ bool icosq;
};
struct mlx5e_cq_param {
struct mlx5e_channel_param {
struct mlx5e_rq_param rq;
struct mlx5e_sq_param sq;
+ struct mlx5e_sq_param icosq;
struct mlx5e_cq_param rx_cq;
struct mlx5e_cq_param tx_cq;
+ struct mlx5e_cq_param icosq_cq;
};
static void mlx5e_update_carrier(struct mlx5e_priv *priv)
kvfree(out);
}
+static void mlx5e_update_q_counter(struct mlx5e_priv *priv)
+{
+ struct mlx5e_qcounter_stats *qcnt = &priv->stats.qcnt;
+
+ if (!priv->q_counter)
+ return;
+
+ mlx5_core_query_out_of_buffer(priv->mdev, priv->q_counter,
+ &qcnt->rx_out_of_buffer);
+}
+
void mlx5e_update_stats(struct mlx5e_priv *priv)
{
struct mlx5_core_dev *mdev = priv->mdev;
s->tx_bytes = 0;
s->tso_packets = 0;
s->tso_bytes = 0;
+ s->tso_inner_packets = 0;
+ s->tso_inner_bytes = 0;
s->tx_queue_stopped = 0;
s->tx_queue_wake = 0;
s->tx_queue_dropped = 0;
+ s->tx_csum_inner = 0;
tx_offload_none = 0;
s->lro_packets = 0;
s->lro_bytes = 0;
s->rx_csum_none = 0;
s->rx_csum_sw = 0;
s->rx_wqe_err = 0;
+ s->rx_mpwqe_filler = 0;
+ s->rx_mpwqe_frag = 0;
for (i = 0; i < priv->params.num_channels; i++) {
rq_stats = &priv->channel[i]->rq.stats;
s->rx_csum_none += rq_stats->csum_none;
s->rx_csum_sw += rq_stats->csum_sw;
s->rx_wqe_err += rq_stats->wqe_err;
+ s->rx_mpwqe_filler += rq_stats->mpwqe_filler;
+ s->rx_mpwqe_frag += rq_stats->mpwqe_frag;
for (j = 0; j < priv->params.num_tc; j++) {
sq_stats = &priv->channel[i]->sq[j].stats;
s->tx_bytes += sq_stats->bytes;
s->tso_packets += sq_stats->tso_packets;
s->tso_bytes += sq_stats->tso_bytes;
+ s->tso_inner_packets += sq_stats->tso_inner_packets;
+ s->tso_inner_bytes += sq_stats->tso_inner_bytes;
s->tx_queue_stopped += sq_stats->stopped;
s->tx_queue_wake += sq_stats->wake;
s->tx_queue_dropped += sq_stats->dropped;
+ s->tx_csum_inner += sq_stats->csum_offload_inner;
tx_offload_none += sq_stats->csum_offload_none;
}
}
MLX5_GET_CTR(out, transmitted_eth_broadcast.octets);
/* Update calculated offload counters */
- s->tx_csum_offload = s->tx_packets - tx_offload_none;
+ s->tx_csum_offload = s->tx_packets - tx_offload_none - s->tx_csum_inner;
s->rx_csum_good = s->rx_packets - s->rx_csum_none -
s->rx_csum_sw;
mlx5e_update_pport_counters(priv);
+ mlx5e_update_q_counter(priv);
+
free_out:
kvfree(out);
}
mutex_unlock(&priv->state_lock);
}
-static void __mlx5e_async_event(struct mlx5e_priv *priv,
- enum mlx5_dev_event event)
+static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv,
+ enum mlx5_dev_event event, unsigned long param)
{
+ struct mlx5e_priv *priv = vpriv;
+
+ if (!test_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLE, &priv->state))
+ return;
+
switch (event) {
case MLX5_DEV_EVENT_PORT_UP:
case MLX5_DEV_EVENT_PORT_DOWN:
}
}
-static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv,
- enum mlx5_dev_event event, unsigned long param)
-{
- struct mlx5e_priv *priv = vpriv;
-
- spin_lock(&priv->async_events_spinlock);
- if (test_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLE, &priv->state))
- __mlx5e_async_event(priv, event);
- spin_unlock(&priv->async_events_spinlock);
-}
-
static void mlx5e_enable_async_events(struct mlx5e_priv *priv)
{
set_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLE, &priv->state);
static void mlx5e_disable_async_events(struct mlx5e_priv *priv)
{
- spin_lock_irq(&priv->async_events_spinlock);
clear_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLE, &priv->state);
- spin_unlock_irq(&priv->async_events_spinlock);
+ synchronize_irq(mlx5_get_msix_vec(priv->mdev, MLX5_EQ_VEC_ASYNC));
}
#define MLX5E_HW2SW_MTU(hwmtu) (hwmtu - (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN))
struct mlx5_core_dev *mdev = priv->mdev;
void *rqc = param->rqc;
void *rqc_wq = MLX5_ADDR_OF(rqc, rqc, wq);
+ u32 byte_count;
int wq_sz;
int err;
int i;
rq->wq.db = &rq->wq.db[MLX5_RCV_DBR];
wq_sz = mlx5_wq_ll_get_size(&rq->wq);
- rq->skb = kzalloc_node(wq_sz * sizeof(*rq->skb), GFP_KERNEL,
- cpu_to_node(c->cpu));
- if (!rq->skb) {
- err = -ENOMEM;
- goto err_rq_wq_destroy;
- }
- rq->wqe_sz = (priv->params.lro_en) ? priv->params.lro_wqe_sz :
- MLX5E_SW2HW_MTU(priv->netdev->mtu);
- rq->wqe_sz = SKB_DATA_ALIGN(rq->wqe_sz + MLX5E_NET_IP_ALIGN);
+ switch (priv->params.rq_wq_type) {
+ case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
+ rq->wqe_info = kzalloc_node(wq_sz * sizeof(*rq->wqe_info),
+ GFP_KERNEL, cpu_to_node(c->cpu));
+ if (!rq->wqe_info) {
+ err = -ENOMEM;
+ goto err_rq_wq_destroy;
+ }
+ rq->handle_rx_cqe = mlx5e_handle_rx_cqe_mpwrq;
+ rq->alloc_wqe = mlx5e_alloc_rx_mpwqe;
+
+ rq->wqe_sz = MLX5_MPWRQ_NUM_STRIDES * MLX5_MPWRQ_STRIDE_SIZE;
+ byte_count = rq->wqe_sz;
+ break;
+ default: /* MLX5_WQ_TYPE_LINKED_LIST */
+ rq->skb = kzalloc_node(wq_sz * sizeof(*rq->skb), GFP_KERNEL,
+ cpu_to_node(c->cpu));
+ if (!rq->skb) {
+ err = -ENOMEM;
+ goto err_rq_wq_destroy;
+ }
+ rq->handle_rx_cqe = mlx5e_handle_rx_cqe;
+ rq->alloc_wqe = mlx5e_alloc_rx_wqe;
+
+ rq->wqe_sz = (priv->params.lro_en) ?
+ priv->params.lro_wqe_sz :
+ MLX5E_SW2HW_MTU(priv->netdev->mtu);
+ rq->wqe_sz = SKB_DATA_ALIGN(rq->wqe_sz);
+ byte_count = rq->wqe_sz;
+ byte_count |= MLX5_HW_START_PADDING;
+ }
for (i = 0; i < wq_sz; i++) {
struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(&rq->wq, i);
- u32 byte_count = rq->wqe_sz - MLX5E_NET_IP_ALIGN;
- wqe->data.lkey = c->mkey_be;
- wqe->data.byte_count =
- cpu_to_be32(byte_count | MLX5_HW_START_PADDING);
+ wqe->data.byte_count = cpu_to_be32(byte_count);
}
+ rq->wq_type = priv->params.rq_wq_type;
rq->pdev = c->pdev;
rq->netdev = c->netdev;
rq->tstamp = &priv->tstamp;
rq->channel = c;
rq->ix = c->ix;
rq->priv = c->priv;
+ rq->mkey_be = c->mkey_be;
+ rq->umr_mkey_be = cpu_to_be32(c->priv->umr_mkey.key);
return 0;
static void mlx5e_destroy_rq(struct mlx5e_rq *rq)
{
- kfree(rq->skb);
+ switch (rq->wq_type) {
+ case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
+ kfree(rq->wqe_info);
+ break;
+ default: /* MLX5_WQ_TYPE_LINKED_LIST */
+ kfree(rq->skb);
+ }
+
mlx5_wq_destroy(&rq->wq_ctrl);
}
struct mlx5e_rq_param *param,
struct mlx5e_rq *rq)
{
+ struct mlx5e_sq *sq = &c->icosq;
+ u16 pi = sq->pc & sq->wq.sz_m1;
int err;
err = mlx5e_create_rq(c, param, rq);
goto err_disable_rq;
set_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state);
- mlx5e_send_nop(&c->sq[0], true); /* trigger mlx5e_post_rx_wqes() */
+
+ sq->ico_wqe_info[pi].opcode = MLX5_OPCODE_NOP;
+ sq->ico_wqe_info[pi].num_wqebbs = 1;
+ mlx5e_send_nop(sq, true); /* trigger mlx5e_post_rx_wqes() */
return 0;
void *sqc = param->sqc;
void *sqc_wq = MLX5_ADDR_OF(sqc, sqc, wq);
- int txq_ix;
int err;
- err = mlx5_alloc_map_uar(mdev, &sq->uar);
+ err = mlx5_alloc_map_uar(mdev, &sq->uar, true);
if (err)
return err;
goto err_unmap_free_uar;
sq->wq.db = &sq->wq.db[MLX5_SND_DBR];
- sq->uar_map = sq->uar.map;
- sq->uar_bf_map = sq->uar.bf_map;
+ if (sq->uar.bf_map) {
+ set_bit(MLX5E_SQ_STATE_BF_ENABLE, &sq->state);
+ sq->uar_map = sq->uar.bf_map;
+ } else {
+ sq->uar_map = sq->uar.map;
+ }
sq->bf_buf_size = (1 << MLX5_CAP_GEN(mdev, log_bf_reg_size)) / 2;
sq->max_inline = param->max_inline;
if (err)
goto err_sq_wq_destroy;
- txq_ix = c->ix + tc * priv->params.num_channels;
- sq->txq = netdev_get_tx_queue(priv->netdev, txq_ix);
+ if (param->icosq) {
+ u8 wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
+
+ sq->ico_wqe_info = kzalloc_node(sizeof(*sq->ico_wqe_info) *
+ wq_sz,
+ GFP_KERNEL,
+ cpu_to_node(c->cpu));
+ if (!sq->ico_wqe_info) {
+ err = -ENOMEM;
+ goto err_free_sq_db;
+ }
+ } else {
+ int txq_ix;
+
+ txq_ix = c->ix + tc * priv->params.num_channels;
+ sq->txq = netdev_get_tx_queue(priv->netdev, txq_ix);
+ priv->txq_to_sq_map[txq_ix] = sq;
+ }
sq->pdev = c->pdev;
sq->tstamp = &priv->tstamp;
sq->tc = tc;
sq->edge = (sq->wq.sz_m1 + 1) - MLX5_SEND_WQE_MAX_WQEBBS;
sq->bf_budget = MLX5E_SQ_BF_BUDGET;
- priv->txq_to_sq_map[txq_ix] = sq;
return 0;
+err_free_sq_db:
+ mlx5e_free_sq_db(sq);
+
err_sq_wq_destroy:
mlx5_wq_destroy(&sq->wq_ctrl);
struct mlx5e_channel *c = sq->channel;
struct mlx5e_priv *priv = c->priv;
+ kfree(sq->ico_wqe_info);
mlx5e_free_sq_db(sq);
mlx5_wq_destroy(&sq->wq_ctrl);
mlx5_unmap_free_uar(priv->mdev, &sq->uar);
memcpy(sqc, param->sqc, sizeof(param->sqc));
- MLX5_SET(sqc, sqc, tis_num_0, priv->tisn[sq->tc]);
- MLX5_SET(sqc, sqc, cqn, c->sq[sq->tc].cq.mcq.cqn);
+ MLX5_SET(sqc, sqc, tis_num_0, param->icosq ? 0 : priv->tisn[sq->tc]);
+ MLX5_SET(sqc, sqc, cqn, sq->cq.mcq.cqn);
MLX5_SET(sqc, sqc, state, MLX5_SQC_STATE_RST);
- MLX5_SET(sqc, sqc, tis_lst_sz, 1);
+ MLX5_SET(sqc, sqc, tis_lst_sz, param->icosq ? 0 : 1);
MLX5_SET(sqc, sqc, flush_in_error_en, 1);
MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC);
if (err)
goto err_disable_sq;
- set_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state);
- netdev_tx_reset_queue(sq->txq);
- netif_tx_start_queue(sq->txq);
+ if (sq->txq) {
+ set_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state);
+ netdev_tx_reset_queue(sq->txq);
+ netif_tx_start_queue(sq->txq);
+ }
return 0;
static void mlx5e_close_sq(struct mlx5e_sq *sq)
{
- clear_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state);
- napi_synchronize(&sq->channel->napi); /* prevent netif_tx_wake_queue */
- netif_tx_disable_queue(sq->txq);
+ if (sq->txq) {
+ clear_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state);
+ /* prevent netif_tx_wake_queue */
+ napi_synchronize(&sq->channel->napi);
+ netif_tx_disable_queue(sq->txq);
+
+ /* ensure hw is notified of all pending wqes */
+ if (mlx5e_sq_has_room_for(sq, 1))
+ mlx5e_send_nop(sq, true);
- /* ensure hw is notified of all pending wqes */
- if (mlx5e_sq_has_room_for(sq, 1))
- mlx5e_send_nop(sq, true);
+ mlx5e_modify_sq(sq, MLX5_SQC_STATE_RDY, MLX5_SQC_STATE_ERR);
+ }
- mlx5e_modify_sq(sq, MLX5_SQC_STATE_RDY, MLX5_SQC_STATE_ERR);
while (sq->cc != sq->pc) /* wait till sq is empty */
msleep(20);
if (err)
goto err_destroy_cq;
- err = mlx5_core_modify_cq_moderation(mdev, &cq->mcq,
- moderation_usecs,
- moderation_frames);
- if (err)
- goto err_destroy_cq;
-
+ if (MLX5_CAP_GEN(mdev, cq_moderation))
+ mlx5_core_modify_cq_moderation(mdev, &cq->mcq,
+ moderation_usecs,
+ moderation_frames);
return 0;
err_destroy_cq:
c->cpu = cpu;
c->pdev = &priv->mdev->pdev->dev;
c->netdev = priv->netdev;
- c->mkey_be = cpu_to_be32(priv->mr.key);
+ c->mkey_be = cpu_to_be32(priv->mkey.key);
c->num_tc = priv->params.num_tc;
mlx5e_build_channeltc_to_txq_map(priv, ix);
netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64);
- err = mlx5e_open_tx_cqs(c, cparam);
+ err = mlx5e_open_cq(c, &cparam->icosq_cq, &c->icosq.cq, 0, 0);
if (err)
goto err_napi_del;
+ err = mlx5e_open_tx_cqs(c, cparam);
+ if (err)
+ goto err_close_icosq_cq;
+
err = mlx5e_open_cq(c, &cparam->rx_cq, &c->rq.cq,
priv->params.rx_cq_moderation_usec,
priv->params.rx_cq_moderation_pkts);
napi_enable(&c->napi);
- err = mlx5e_open_sqs(c, cparam);
+ err = mlx5e_open_sq(c, 0, &cparam->icosq, &c->icosq);
if (err)
goto err_disable_napi;
+ err = mlx5e_open_sqs(c, cparam);
+ if (err)
+ goto err_close_icosq;
+
err = mlx5e_open_rq(c, &cparam->rq, &c->rq);
if (err)
goto err_close_sqs;
err_close_sqs:
mlx5e_close_sqs(c);
+err_close_icosq:
+ mlx5e_close_sq(&c->icosq);
+
err_disable_napi:
napi_disable(&c->napi);
mlx5e_close_cq(&c->rq.cq);
err_close_tx_cqs:
mlx5e_close_tx_cqs(c);
+err_close_icosq_cq:
+ mlx5e_close_cq(&c->icosq.cq);
+
err_napi_del:
netif_napi_del(&c->napi);
napi_hash_del(&c->napi);
{
mlx5e_close_rq(&c->rq);
mlx5e_close_sqs(c);
+ mlx5e_close_sq(&c->icosq);
napi_disable(&c->napi);
mlx5e_close_cq(&c->rq.cq);
mlx5e_close_tx_cqs(c);
+ mlx5e_close_cq(&c->icosq.cq);
netif_napi_del(&c->napi);
napi_hash_del(&c->napi);
void *rqc = param->rqc;
void *wq = MLX5_ADDR_OF(rqc, rqc, wq);
- MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST);
+ switch (priv->params.rq_wq_type) {
+ case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
+ MLX5_SET(wq, wq, log_wqe_num_of_strides,
+ MLX5_MPWRQ_LOG_NUM_STRIDES - 9);
+ MLX5_SET(wq, wq, log_wqe_stride_size,
+ MLX5_MPWRQ_LOG_STRIDE_SIZE - 6);
+ MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ);
+ break;
+ default: /* MLX5_WQ_TYPE_LINKED_LIST */
+ MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST);
+ }
+
MLX5_SET(wq, wq, end_padding_mode, MLX5_WQ_END_PAD_MODE_ALIGN);
MLX5_SET(wq, wq, log_wq_stride, ilog2(sizeof(struct mlx5e_rx_wqe)));
MLX5_SET(wq, wq, log_wq_sz, priv->params.log_rq_size);
MLX5_SET(wq, wq, pd, priv->pdn);
+ MLX5_SET(rqc, rqc, counter_set_id, priv->q_counter);
param->wq.buf_numa_node = dev_to_node(&priv->mdev->pdev->dev);
param->wq.linear = 1;
}
-static void mlx5e_build_sq_param(struct mlx5e_priv *priv,
- struct mlx5e_sq_param *param)
+static void mlx5e_build_drop_rq_param(struct mlx5e_rq_param *param)
+{
+ void *rqc = param->rqc;
+ void *wq = MLX5_ADDR_OF(rqc, rqc, wq);
+
+ MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST);
+ MLX5_SET(wq, wq, log_wq_stride, ilog2(sizeof(struct mlx5e_rx_wqe)));
+}
+
+static void mlx5e_build_sq_param_common(struct mlx5e_priv *priv,
+ struct mlx5e_sq_param *param)
{
void *sqc = param->sqc;
void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
- MLX5_SET(wq, wq, log_wq_sz, priv->params.log_sq_size);
MLX5_SET(wq, wq, log_wq_stride, ilog2(MLX5_SEND_WQE_BB));
MLX5_SET(wq, wq, pd, priv->pdn);
param->wq.buf_numa_node = dev_to_node(&priv->mdev->pdev->dev);
+}
+
+static void mlx5e_build_sq_param(struct mlx5e_priv *priv,
+ struct mlx5e_sq_param *param)
+{
+ void *sqc = param->sqc;
+ void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
+
+ mlx5e_build_sq_param_common(priv, param);
+ MLX5_SET(wq, wq, log_wq_sz, priv->params.log_sq_size);
+
param->max_inline = priv->params.tx_max_inline;
}
struct mlx5e_cq_param *param)
{
void *cqc = param->cqc;
+ u8 log_cq_size;
- MLX5_SET(cqc, cqc, log_cq_size, priv->params.log_rq_size);
+ switch (priv->params.rq_wq_type) {
+ case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
+ log_cq_size = priv->params.log_rq_size +
+ MLX5_MPWRQ_LOG_NUM_STRIDES;
+ break;
+ default: /* MLX5_WQ_TYPE_LINKED_LIST */
+ log_cq_size = priv->params.log_rq_size;
+ }
+
+ MLX5_SET(cqc, cqc, log_cq_size, log_cq_size);
mlx5e_build_common_cq_param(priv, param);
}
{
void *cqc = param->cqc;
- MLX5_SET(cqc, cqc, log_cq_size, priv->params.log_sq_size);
+ MLX5_SET(cqc, cqc, log_cq_size, priv->params.log_sq_size);
+
+ mlx5e_build_common_cq_param(priv, param);
+}
+
+static void mlx5e_build_ico_cq_param(struct mlx5e_priv *priv,
+ struct mlx5e_cq_param *param,
+ u8 log_wq_size)
+{
+ void *cqc = param->cqc;
+
+ MLX5_SET(cqc, cqc, log_cq_size, log_wq_size);
mlx5e_build_common_cq_param(priv, param);
}
+static void mlx5e_build_icosq_param(struct mlx5e_priv *priv,
+ struct mlx5e_sq_param *param,
+ u8 log_wq_size)
+{
+ void *sqc = param->sqc;
+ void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
+
+ mlx5e_build_sq_param_common(priv, param);
+
+ MLX5_SET(wq, wq, log_wq_sz, log_wq_size);
+ MLX5_SET(sqc, sqc, reg_umr, MLX5_CAP_ETH(priv->mdev, reg_umr_sq));
+
+ param->icosq = true;
+}
+
static void mlx5e_build_channel_param(struct mlx5e_priv *priv,
struct mlx5e_channel_param *cparam)
{
+ u8 icosq_log_wq_sz = MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
+
memset(cparam, 0, sizeof(*cparam));
mlx5e_build_rq_param(priv, &cparam->rq);
mlx5e_build_sq_param(priv, &cparam->sq);
+ mlx5e_build_icosq_param(priv, &cparam->icosq, icosq_log_wq_sz);
mlx5e_build_rx_cq_param(priv, &cparam->rx_cq);
mlx5e_build_tx_cq_param(priv, &cparam->tx_cq);
+ mlx5e_build_ico_cq_param(priv, &cparam->icosq_cq, icosq_log_wq_sz);
}
static int mlx5e_open_channels(struct mlx5e_priv *priv)
return 0;
}
+static void mlx5e_netdev_set_tcs(struct net_device *netdev)
+{
+ struct mlx5e_priv *priv = netdev_priv(netdev);
+ int nch = priv->params.num_channels;
+ int ntc = priv->params.num_tc;
+ int tc;
+
+ netdev_reset_tc(netdev);
+
+ if (ntc == 1)
+ return;
+
+ netdev_set_num_tc(netdev, ntc);
+
+ for (tc = 0; tc < ntc; tc++)
+ netdev_set_tc_queue(netdev, tc, nch, tc * nch);
+}
+
int mlx5e_open_locked(struct net_device *netdev)
{
struct mlx5e_priv *priv = netdev_priv(netdev);
set_bit(MLX5E_STATE_OPENED, &priv->state);
+ mlx5e_netdev_set_tcs(netdev);
+
num_txqs = priv->params.num_channels * priv->params.num_tc;
netif_set_real_num_tx_queues(netdev, num_txqs);
netif_set_real_num_rx_queues(netdev, priv->params.num_channels);
goto err_close_channels;
}
- mlx5e_update_carrier(priv);
mlx5e_redirect_rqts(priv);
+ mlx5e_update_carrier(priv);
mlx5e_timestamp_init(priv);
schedule_delayed_work(&priv->update_stats_work, 0);
clear_bit(MLX5E_STATE_OPENED, &priv->state);
mlx5e_timestamp_cleanup(priv);
- mlx5e_redirect_rqts(priv);
netif_carrier_off(priv->netdev);
+ mlx5e_redirect_rqts(priv);
mlx5e_close_channels(priv);
return 0;
memset(&cq_param, 0, sizeof(cq_param));
memset(&rq_param, 0, sizeof(rq_param));
- mlx5e_build_rx_cq_param(priv, &cq_param);
- mlx5e_build_rq_param(priv, &rq_param);
+ mlx5e_build_drop_rq_param(&rq_param);
err = mlx5e_create_drop_cq(priv, cq, &cq_param);
if (err)
memset(in, 0, sizeof(in));
- MLX5_SET(tisc, tisc, prio, tc);
+ MLX5_SET(tisc, tisc, prio, tc << 1);
MLX5_SET(tisc, tisc, transport_domain, priv->tdn);
return mlx5_core_create_tis(mdev, in, sizeof(in), &priv->tisn[tc]);
int err;
int tc;
- for (tc = 0; tc < priv->params.num_tc; tc++) {
+ for (tc = 0; tc < MLX5E_MAX_NUM_TC; tc++) {
err = mlx5e_create_tis(priv, tc);
if (err)
goto err_close_tises;
{
int tc;
- for (tc = 0; tc < priv->params.num_tc; tc++)
+ for (tc = 0; tc < MLX5E_MAX_NUM_TC; tc++)
mlx5e_destroy_tis(priv, tc);
}
mlx5e_destroy_tir(priv, i);
}
+static int mlx5e_setup_tc(struct net_device *netdev, u8 tc)
+{
+ struct mlx5e_priv *priv = netdev_priv(netdev);
+ bool was_opened;
+ int err = 0;
+
+ if (tc && tc != MLX5E_MAX_NUM_TC)
+ return -EINVAL;
+
+ mutex_lock(&priv->state_lock);
+
+ was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
+ if (was_opened)
+ mlx5e_close_locked(priv->netdev);
+
+ priv->params.num_tc = tc ? tc : 1;
+
+ if (was_opened)
+ err = mlx5e_open_locked(priv->netdev);
+
+ mutex_unlock(&priv->state_lock);
+
+ return err;
+}
+
+static int mlx5e_ndo_setup_tc(struct net_device *dev, u32 handle,
+ __be16 proto, struct tc_to_netdev *tc)
+{
+ struct mlx5e_priv *priv = netdev_priv(dev);
+
+ if (TC_H_MAJ(handle) != TC_H_MAJ(TC_H_INGRESS))
+ goto mqprio;
+
+ switch (tc->type) {
+ case TC_SETUP_CLSFLOWER:
+ switch (tc->cls_flower->command) {
+ case TC_CLSFLOWER_REPLACE:
+ return mlx5e_configure_flower(priv, proto, tc->cls_flower);
+ case TC_CLSFLOWER_DESTROY:
+ return mlx5e_delete_flower(priv, tc->cls_flower);
+ }
+ default:
+ return -EOPNOTSUPP;
+ }
+
+mqprio:
+ if (tc->type != TC_SETUP_MQPRIO)
+ return -EINVAL;
+
+ return mlx5e_setup_tc(dev, tc->tc);
+}
+
static struct rtnl_link_stats64 *
mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
{
if (changes & NETIF_F_LRO) {
bool was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
- if (was_opened)
+ if (was_opened && (priv->params.rq_wq_type ==
+ MLX5_WQ_TYPE_LINKED_LIST))
mlx5e_close_locked(priv->netdev);
priv->params.lro_en = !!(features & NETIF_F_LRO);
mlx5_core_warn(priv->mdev, "lro modify failed, %d\n",
err);
- if (was_opened)
+ if (was_opened && (priv->params.rq_wq_type ==
+ MLX5_WQ_TYPE_LINKED_LIST))
err = mlx5e_open_locked(priv->netdev);
}
mlx5e_disable_vlan_filter(priv);
}
+ if ((changes & NETIF_F_HW_TC) && !(features & NETIF_F_HW_TC) &&
+ mlx5e_tc_num_filters(priv)) {
+ netdev_err(netdev,
+ "Active offloaded tc filters, can't turn hw_tc_offload off\n");
+ return -EINVAL;
+ }
+
return err;
}
vf_stats);
}
+static void mlx5e_add_vxlan_port(struct net_device *netdev,
+ sa_family_t sa_family, __be16 port)
+{
+ struct mlx5e_priv *priv = netdev_priv(netdev);
+
+ if (!mlx5e_vxlan_allowed(priv->mdev))
+ return;
+
+ mlx5e_vxlan_add_port(priv, be16_to_cpu(port));
+}
+
+static void mlx5e_del_vxlan_port(struct net_device *netdev,
+ sa_family_t sa_family, __be16 port)
+{
+ struct mlx5e_priv *priv = netdev_priv(netdev);
+
+ if (!mlx5e_vxlan_allowed(priv->mdev))
+ return;
+
+ mlx5e_vxlan_del_port(priv, be16_to_cpu(port));
+}
+
+static netdev_features_t mlx5e_vxlan_features_check(struct mlx5e_priv *priv,
+ struct sk_buff *skb,
+ netdev_features_t features)
+{
+ struct udphdr *udph;
+ u16 proto;
+ u16 port = 0;
+
+ switch (vlan_get_protocol(skb)) {
+ case htons(ETH_P_IP):
+ proto = ip_hdr(skb)->protocol;
+ break;
+ case htons(ETH_P_IPV6):
+ proto = ipv6_hdr(skb)->nexthdr;
+ break;
+ default:
+ goto out;
+ }
+
+ if (proto == IPPROTO_UDP) {
+ udph = udp_hdr(skb);
+ port = be16_to_cpu(udph->dest);
+ }
+
+ /* Verify if UDP port is being offloaded by HW */
+ if (port && mlx5e_vxlan_lookup_port(priv, port))
+ return features;
+
+out:
+ /* Disable CSUM and GSO if the udp dport is not offloaded by HW */
+ return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
+}
+
+static netdev_features_t mlx5e_features_check(struct sk_buff *skb,
+ struct net_device *netdev,
+ netdev_features_t features)
+{
+ struct mlx5e_priv *priv = netdev_priv(netdev);
+
+ features = vlan_features_check(skb, features);
+ features = vxlan_features_check(skb, features);
+
+ /* Validate if the tunneled packet is being offloaded by HW */
+ if (skb->encapsulation &&
+ (features & NETIF_F_CSUM_MASK || features & NETIF_F_GSO_MASK))
+ return mlx5e_vxlan_features_check(priv, skb, features);
+
+ return features;
+}
+
static const struct net_device_ops mlx5e_netdev_ops_basic = {
.ndo_open = mlx5e_open,
.ndo_stop = mlx5e_close,
.ndo_start_xmit = mlx5e_xmit,
+ .ndo_setup_tc = mlx5e_ndo_setup_tc,
+ .ndo_select_queue = mlx5e_select_queue,
.ndo_get_stats64 = mlx5e_get_stats,
.ndo_set_rx_mode = mlx5e_set_rx_mode,
.ndo_set_mac_address = mlx5e_set_mac,
.ndo_open = mlx5e_open,
.ndo_stop = mlx5e_close,
.ndo_start_xmit = mlx5e_xmit,
+ .ndo_setup_tc = mlx5e_ndo_setup_tc,
+ .ndo_select_queue = mlx5e_select_queue,
.ndo_get_stats64 = mlx5e_get_stats,
.ndo_set_rx_mode = mlx5e_set_rx_mode,
.ndo_set_mac_address = mlx5e_set_mac,
.ndo_set_features = mlx5e_set_features,
.ndo_change_mtu = mlx5e_change_mtu,
.ndo_do_ioctl = mlx5e_ioctl,
+ .ndo_add_vxlan_port = mlx5e_add_vxlan_port,
+ .ndo_del_vxlan_port = mlx5e_del_vxlan_port,
+ .ndo_features_check = mlx5e_features_check,
.ndo_set_vf_mac = mlx5e_set_vf_mac,
.ndo_set_vf_vlan = mlx5e_set_vf_vlan,
.ndo_get_vf_config = mlx5e_get_vf_config,
}
if (!MLX5_CAP_ETH(mdev, self_lb_en_modifiable))
mlx5_core_warn(mdev, "Self loop back prevention is not supported\n");
+ if (!MLX5_CAP_GEN(mdev, cq_moderation))
+ mlx5_core_warn(mdev, "CQ modiration is not supported\n");
return 0;
}
2 /*sizeof(mlx5e_tx_wqe.inline_hdr_start)*/;
}
-void mlx5e_build_default_indir_rqt(u32 *indirection_rqt, int len,
+#ifdef CONFIG_MLX5_CORE_EN_DCB
+static void mlx5e_ets_init(struct mlx5e_priv *priv)
+{
+ int i;
+
+ priv->params.ets.ets_cap = mlx5_max_tc(priv->mdev) + 1;
+ for (i = 0; i < priv->params.ets.ets_cap; i++) {
+ priv->params.ets.tc_tx_bw[i] = MLX5E_MAX_BW_ALLOC;
+ priv->params.ets.tc_tsa[i] = IEEE_8021QAZ_TSA_VENDOR;
+ priv->params.ets.prio_tc[i] = i;
+ }
+
+ /* tclass[prio=0]=1, tclass[prio=1]=0, tclass[prio=i]=i (for i>1) */
+ priv->params.ets.prio_tc[0] = 1;
+ priv->params.ets.prio_tc[1] = 0;
+}
+#endif
+
+void mlx5e_build_default_indir_rqt(struct mlx5_core_dev *mdev,
+ u32 *indirection_rqt, int len,
int num_channels)
{
+ int node = mdev->priv.numa_node;
+ int node_num_of_cores;
int i;
+ if (node == -1)
+ node = first_online_node;
+
+ node_num_of_cores = cpumask_weight(cpumask_of_node(node));
+
+ if (node_num_of_cores)
+ num_channels = min_t(int, num_channels, node_num_of_cores);
+
for (i = 0; i < len; i++)
indirection_rqt[i] = i % num_channels;
}
+static bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
+{
+ return MLX5_CAP_GEN(mdev, striding_rq) &&
+ MLX5_CAP_GEN(mdev, umr_ptr_rlky) &&
+ MLX5_CAP_ETH(mdev, reg_umr_sq);
+}
+
static void mlx5e_build_netdev_priv(struct mlx5_core_dev *mdev,
struct net_device *netdev,
int num_channels)
priv->params.log_sq_size =
MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE;
- priv->params.log_rq_size =
- MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE;
+ priv->params.rq_wq_type = mlx5e_check_fragmented_striding_rq_cap(mdev) ?
+ MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ :
+ MLX5_WQ_TYPE_LINKED_LIST;
+
+ switch (priv->params.rq_wq_type) {
+ case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
+ priv->params.log_rq_size = MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE_MPW;
+ priv->params.lro_en = true;
+ break;
+ default: /* MLX5_WQ_TYPE_LINKED_LIST */
+ priv->params.log_rq_size = MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE;
+ }
+
+ priv->params.min_rx_wqes = mlx5_min_rx_wqes(priv->params.rq_wq_type,
+ BIT(priv->params.log_rq_size));
priv->params.rx_cq_moderation_usec =
MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC;
priv->params.rx_cq_moderation_pkts =
priv->params.tx_cq_moderation_pkts =
MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS;
priv->params.tx_max_inline = mlx5e_get_max_inline_cap(mdev);
- priv->params.min_rx_wqes =
- MLX5E_PARAMS_DEFAULT_MIN_RX_WQES;
priv->params.num_tc = 1;
- priv->params.default_vlan_prio = 0;
priv->params.rss_hfunc = ETH_RSS_HASH_XOR;
netdev_rss_key_fill(priv->params.toeplitz_hash_key,
sizeof(priv->params.toeplitz_hash_key));
- mlx5e_build_default_indir_rqt(priv->params.indirection_rqt,
+ mlx5e_build_default_indir_rqt(mdev, priv->params.indirection_rqt,
MLX5E_INDIR_RQT_SIZE, num_channels);
priv->params.lro_wqe_sz =
priv->mdev = mdev;
priv->netdev = netdev;
priv->params.num_channels = num_channels;
- priv->default_vlan_prio = priv->params.default_vlan_prio;
- spin_lock_init(&priv->async_events_spinlock);
+#ifdef CONFIG_MLX5_CORE_EN_DCB
+ mlx5e_ets_init(priv);
+#endif
+
mutex_init(&priv->state_lock);
INIT_WORK(&priv->update_carrier_work, mlx5e_update_carrier_work);
SET_NETDEV_DEV(netdev, &mdev->pdev->dev);
- if (MLX5_CAP_GEN(mdev, vport_group_manager))
+ if (MLX5_CAP_GEN(mdev, vport_group_manager)) {
netdev->netdev_ops = &mlx5e_netdev_ops_sriov;
- else
+#ifdef CONFIG_MLX5_CORE_EN_DCB
+ netdev->dcbnl_ops = &mlx5e_dcbnl_ops;
+#endif
+ } else {
netdev->netdev_ops = &mlx5e_netdev_ops_basic;
+ }
netdev->watchdog_timeo = 15 * HZ;
netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX;
netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+ if (mlx5e_vxlan_allowed(mdev)) {
+ netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL;
+ netdev->hw_enc_features |= NETIF_F_IP_CSUM;
+ netdev->hw_enc_features |= NETIF_F_RXCSUM;
+ netdev->hw_enc_features |= NETIF_F_TSO;
+ netdev->hw_enc_features |= NETIF_F_TSO6;
+ netdev->hw_enc_features |= NETIF_F_RXHASH;
+ netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL;
+ }
+
netdev->features = netdev->hw_features;
if (!priv->params.lro_en)
netdev->features &= ~NETIF_F_LRO;
+#define FT_CAP(f) MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive.f)
+ if (FT_CAP(flow_modify_en) &&
+ FT_CAP(modify_root) &&
+ FT_CAP(identified_miss_table_mode) &&
+ FT_CAP(flow_table_modify))
+ priv->netdev->hw_features |= NETIF_F_HW_TC;
+
netdev->features |= NETIF_F_HIGHDMA;
netdev->priv_flags |= IFF_UNICAST_FLT;
}
static int mlx5e_create_mkey(struct mlx5e_priv *priv, u32 pdn,
- struct mlx5_core_mr *mr)
+ struct mlx5_core_mkey *mkey)
{
struct mlx5_core_dev *mdev = priv->mdev;
struct mlx5_create_mkey_mbox_in *in;
in->seg.flags_pd = cpu_to_be32(pdn | MLX5_MKEY_LEN64);
in->seg.qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
- err = mlx5_core_create_mkey(mdev, mr, in, sizeof(*in), NULL, NULL,
+ err = mlx5_core_create_mkey(mdev, mkey, in, sizeof(*in), NULL, NULL,
NULL);
kvfree(in);
return err;
}
+static void mlx5e_create_q_counter(struct mlx5e_priv *priv)
+{
+ struct mlx5_core_dev *mdev = priv->mdev;
+ int err;
+
+ err = mlx5_core_alloc_q_counter(mdev, &priv->q_counter);
+ if (err) {
+ mlx5_core_warn(mdev, "alloc queue counter failed, %d\n", err);
+ priv->q_counter = 0;
+ }
+}
+
+static void mlx5e_destroy_q_counter(struct mlx5e_priv *priv)
+{
+ if (!priv->q_counter)
+ return;
+
+ mlx5_core_dealloc_q_counter(priv->mdev, priv->q_counter);
+}
+
+static int mlx5e_create_umr_mkey(struct mlx5e_priv *priv)
+{
+ struct mlx5_core_dev *mdev = priv->mdev;
+ struct mlx5_create_mkey_mbox_in *in;
+ struct mlx5_mkey_seg *mkc;
+ int inlen = sizeof(*in);
+ u64 npages =
+ mlx5e_get_max_num_channels(mdev) * MLX5_CHANNEL_MAX_NUM_MTTS;
+ int err;
+
+ in = mlx5_vzalloc(inlen);
+ if (!in)
+ return -ENOMEM;
+
+ mkc = &in->seg;
+ mkc->status = MLX5_MKEY_STATUS_FREE;
+ mkc->flags = MLX5_PERM_UMR_EN |
+ MLX5_PERM_LOCAL_READ |
+ MLX5_PERM_LOCAL_WRITE |
+ MLX5_ACCESS_MODE_MTT;
+
+ mkc->qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
+ mkc->flags_pd = cpu_to_be32(priv->pdn);
+ mkc->len = cpu_to_be64(npages << PAGE_SHIFT);
+ mkc->xlt_oct_size = cpu_to_be32(mlx5e_get_mtt_octw(npages));
+ mkc->log2_page_size = PAGE_SHIFT;
+
+ err = mlx5_core_create_mkey(mdev, &priv->umr_mkey, in, inlen, NULL,
+ NULL, NULL);
+
+ kvfree(in);
+
+ return err;
+}
+
static void *mlx5e_create_netdev(struct mlx5_core_dev *mdev)
{
struct net_device *netdev;
if (mlx5e_check_required_hca_cap(mdev))
return NULL;
- netdev = alloc_etherdev_mqs(sizeof(struct mlx5e_priv), nch, nch);
+ netdev = alloc_etherdev_mqs(sizeof(struct mlx5e_priv),
+ nch * MLX5E_MAX_NUM_TC,
+ nch);
if (!netdev) {
mlx5_core_err(mdev, "alloc_etherdev_mqs() failed\n");
return NULL;
priv = netdev_priv(netdev);
- err = mlx5_alloc_map_uar(mdev, &priv->cq_uar);
+ err = mlx5_alloc_map_uar(mdev, &priv->cq_uar, false);
if (err) {
mlx5_core_err(mdev, "alloc_map uar failed, %d\n", err);
goto err_free_netdev;
goto err_dealloc_pd;
}
- err = mlx5e_create_mkey(priv, priv->pdn, &priv->mr);
+ err = mlx5e_create_mkey(priv, priv->pdn, &priv->mkey);
if (err) {
mlx5_core_err(mdev, "create mkey failed, %d\n", err);
goto err_dealloc_transport_domain;
}
+ err = mlx5e_create_umr_mkey(priv);
+ if (err) {
+ mlx5_core_err(mdev, "create umr mkey failed, %d\n", err);
+ goto err_destroy_mkey;
+ }
+
err = mlx5e_create_tises(priv);
if (err) {
mlx5_core_warn(mdev, "create tises failed, %d\n", err);
- goto err_destroy_mkey;
+ goto err_destroy_umr_mkey;
}
err = mlx5e_open_drop_rq(priv);
goto err_destroy_tirs;
}
+ mlx5e_create_q_counter(priv);
+
mlx5e_init_eth_addr(priv);
+ mlx5e_vxlan_init(priv);
+
+ err = mlx5e_tc_init(priv);
+ if (err)
+ goto err_dealloc_q_counters;
+
+#ifdef CONFIG_MLX5_CORE_EN_DCB
+ mlx5e_dcbnl_ieee_setets_core(priv, &priv->params.ets);
+#endif
+
err = register_netdev(netdev);
if (err) {
mlx5_core_err(mdev, "register_netdev failed, %d\n", err);
- goto err_destroy_flow_tables;
+ goto err_tc_cleanup;
}
+ if (mlx5e_vxlan_allowed(mdev))
+ vxlan_get_rx_port(netdev);
+
mlx5e_enable_async_events(priv);
schedule_work(&priv->set_rx_mode_work);
return priv;
-err_destroy_flow_tables:
+err_tc_cleanup:
+ mlx5e_tc_cleanup(priv);
+
+err_dealloc_q_counters:
+ mlx5e_destroy_q_counter(priv);
mlx5e_destroy_flow_tables(priv);
err_destroy_tirs:
err_destroy_tises:
mlx5e_destroy_tises(priv);
+err_destroy_umr_mkey:
+ mlx5_core_destroy_mkey(mdev, &priv->umr_mkey);
+
err_destroy_mkey:
- mlx5_core_destroy_mkey(mdev, &priv->mr);
+ mlx5_core_destroy_mkey(mdev, &priv->mkey);
err_dealloc_transport_domain:
mlx5_core_dealloc_transport_domain(mdev, priv->tdn);
mlx5e_disable_async_events(priv);
flush_scheduled_work();
unregister_netdev(netdev);
+ mlx5e_tc_cleanup(priv);
+ mlx5e_vxlan_cleanup(priv);
+ mlx5e_destroy_q_counter(priv);
mlx5e_destroy_flow_tables(priv);
mlx5e_destroy_tirs(priv);
mlx5e_destroy_rqt(priv, MLX5E_SINGLE_RQ_RQT);
mlx5e_destroy_rqt(priv, MLX5E_INDIRECTION_RQT);
mlx5e_close_drop_rq(priv);
mlx5e_destroy_tises(priv);
- mlx5_core_destroy_mkey(priv->mdev, &priv->mr);
+ mlx5_core_destroy_mkey(priv->mdev, &priv->umr_mkey);
+ mlx5_core_destroy_mkey(priv->mdev, &priv->mkey);
mlx5_core_dealloc_transport_domain(priv->mdev, priv->tdn);
mlx5_core_dealloc_pd(priv->mdev, priv->pdn);
mlx5_unmap_free_uar(priv->mdev, &priv->cq_uar);
projects / cascardo / linux.git / blobdiff