#include <net/pkt_cls.h>
#include <linux/mlx5/fs.h>
#include <net/vxlan.h>
+#include <linux/bpf.h>
#include "en.h"
#include "en_tc.h"
#include "eswitch.h"
struct mlx5_wq_param wq;
u16 max_inline;
u8 min_inline_mode;
- bool icosq;
+ enum mlx5e_sq_type type;
};
struct mlx5e_cq_param {
struct mlx5e_channel_param {
struct mlx5e_rq_param rq;
struct mlx5e_sq_param sq;
+ struct mlx5e_sq_param xdp_sq;
struct mlx5e_sq_param icosq;
struct mlx5e_cq_param rx_cq;
struct mlx5e_cq_param tx_cq;
static void mlx5e_set_rq_priv_params(struct mlx5e_priv *priv)
{
- u8 rq_type = mlx5e_check_fragmented_striding_rq_cap(priv->mdev) ?
+ u8 rq_type = mlx5e_check_fragmented_striding_rq_cap(priv->mdev) &&
+ !priv->xdp_prog ?
MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ :
MLX5_WQ_TYPE_LINKED_LIST;
mlx5e_set_rq_type_params(priv, rq_type);
s->rx_csum_none += rq_stats->csum_none;
s->rx_csum_complete += rq_stats->csum_complete;
s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner;
+ s->rx_xdp_drop += rq_stats->xdp_drop;
+ s->rx_xdp_tx += rq_stats->xdp_tx;
+ s->rx_xdp_tx_full += rq_stats->xdp_tx_full;
s->rx_wqe_err += rq_stats->wqe_err;
s->rx_mpwqe_filler += rq_stats->mpwqe_filler;
s->rx_buff_alloc_err += rq_stats->buff_alloc_err;
kfree(rq->mpwqe.info);
}
+static bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv)
+{
+ struct mlx5_eswitch_rep *rep = (struct mlx5_eswitch_rep *)priv->ppriv;
+
+ if (rep && rep->vport != FDB_UPLINK_VPORT)
+ return true;
+
+ return false;
+}
+
static int mlx5e_create_rq(struct mlx5e_channel *c,
struct mlx5e_rq_param *param,
struct mlx5e_rq *rq)
rq->channel = c;
rq->ix = c->ix;
rq->priv = c->priv;
+ rq->xdp_prog = priv->xdp_prog;
+
+ rq->buff.map_dir = DMA_FROM_DEVICE;
+ if (rq->xdp_prog)
+ rq->buff.map_dir = DMA_BIDIRECTIONAL;
switch (priv->params.rq_wq_type) {
case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
+ if (mlx5e_is_vf_vport_rep(priv)) {
+ err = -EINVAL;
+ goto err_rq_wq_destroy;
+ }
+
rq->handle_rx_cqe = mlx5e_handle_rx_cqe_mpwrq;
rq->alloc_wqe = mlx5e_alloc_rx_mpwqe;
rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe;
goto err_rq_wq_destroy;
}
- rq->handle_rx_cqe = mlx5e_handle_rx_cqe;
+ if (mlx5e_is_vf_vport_rep(priv))
+ rq->handle_rx_cqe = mlx5e_handle_rx_cqe_rep;
+ else
+ rq->handle_rx_cqe = mlx5e_handle_rx_cqe;
+
rq->alloc_wqe = mlx5e_alloc_rx_wqe;
rq->dealloc_wqe = mlx5e_dealloc_rx_wqe;
rq->page_cache.head = 0;
rq->page_cache.tail = 0;
+ if (rq->xdp_prog)
+ bpf_prog_add(rq->xdp_prog, 1);
+
return 0;
err_rq_wq_destroy:
{
int i;
+ if (rq->xdp_prog)
+ bpf_prog_put(rq->xdp_prog);
+
switch (rq->wq_type) {
case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
mlx5e_rq_free_mpwqe_info(rq);
if (param->am_enabled)
set_bit(MLX5E_RQ_STATE_AM, &c->rq.state);
- sq->ico_wqe_info[pi].opcode = MLX5_OPCODE_NOP;
- sq->ico_wqe_info[pi].num_wqebbs = 1;
+ sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_NOP;
+ sq->db.ico_wqe[pi].num_wqebbs = 1;
mlx5e_send_nop(sq, true); /* trigger mlx5e_post_rx_wqes() */
return 0;
mlx5e_destroy_rq(rq);
}
-static void mlx5e_free_sq_db(struct mlx5e_sq *sq)
+static void mlx5e_free_sq_xdp_db(struct mlx5e_sq *sq)
{
- kfree(sq->wqe_info);
- kfree(sq->dma_fifo);
- kfree(sq->skb);
+ kfree(sq->db.xdp.di);
+ kfree(sq->db.xdp.wqe_info);
}
-static int mlx5e_alloc_sq_db(struct mlx5e_sq *sq, int numa)
+static int mlx5e_alloc_sq_xdp_db(struct mlx5e_sq *sq, int numa)
{
int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
- int df_sz = wq_sz * MLX5_SEND_WQEBB_NUM_DS;
- sq->skb = kzalloc_node(wq_sz * sizeof(*sq->skb), GFP_KERNEL, numa);
- sq->dma_fifo = kzalloc_node(df_sz * sizeof(*sq->dma_fifo), GFP_KERNEL,
- numa);
- sq->wqe_info = kzalloc_node(wq_sz * sizeof(*sq->wqe_info), GFP_KERNEL,
- numa);
+ sq->db.xdp.di = kzalloc_node(sizeof(*sq->db.xdp.di) * wq_sz,
+ GFP_KERNEL, numa);
+ sq->db.xdp.wqe_info = kzalloc_node(sizeof(*sq->db.xdp.wqe_info) * wq_sz,
+ GFP_KERNEL, numa);
+ if (!sq->db.xdp.di || !sq->db.xdp.wqe_info) {
+ mlx5e_free_sq_xdp_db(sq);
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static void mlx5e_free_sq_ico_db(struct mlx5e_sq *sq)
+{
+ kfree(sq->db.ico_wqe);
+}
+
+static int mlx5e_alloc_sq_ico_db(struct mlx5e_sq *sq, int numa)
+{
+ u8 wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
- if (!sq->skb || !sq->dma_fifo || !sq->wqe_info) {
- mlx5e_free_sq_db(sq);
+ sq->db.ico_wqe = kzalloc_node(sizeof(*sq->db.ico_wqe) * wq_sz,
+ GFP_KERNEL, numa);
+ if (!sq->db.ico_wqe)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static void mlx5e_free_sq_txq_db(struct mlx5e_sq *sq)
+{
+ kfree(sq->db.txq.wqe_info);
+ kfree(sq->db.txq.dma_fifo);
+ kfree(sq->db.txq.skb);
+}
+
+static int mlx5e_alloc_sq_txq_db(struct mlx5e_sq *sq, int numa)
+{
+ int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
+ int df_sz = wq_sz * MLX5_SEND_WQEBB_NUM_DS;
+
+ sq->db.txq.skb = kzalloc_node(wq_sz * sizeof(*sq->db.txq.skb),
+ GFP_KERNEL, numa);
+ sq->db.txq.dma_fifo = kzalloc_node(df_sz * sizeof(*sq->db.txq.dma_fifo),
+ GFP_KERNEL, numa);
+ sq->db.txq.wqe_info = kzalloc_node(wq_sz * sizeof(*sq->db.txq.wqe_info),
+ GFP_KERNEL, numa);
+ if (!sq->db.txq.skb || !sq->db.txq.dma_fifo || !sq->db.txq.wqe_info) {
+ mlx5e_free_sq_txq_db(sq);
return -ENOMEM;
}
return 0;
}
+static void mlx5e_free_sq_db(struct mlx5e_sq *sq)
+{
+ switch (sq->type) {
+ case MLX5E_SQ_TXQ:
+ mlx5e_free_sq_txq_db(sq);
+ break;
+ case MLX5E_SQ_ICO:
+ mlx5e_free_sq_ico_db(sq);
+ break;
+ case MLX5E_SQ_XDP:
+ mlx5e_free_sq_xdp_db(sq);
+ break;
+ }
+}
+
+static int mlx5e_alloc_sq_db(struct mlx5e_sq *sq, int numa)
+{
+ switch (sq->type) {
+ case MLX5E_SQ_TXQ:
+ return mlx5e_alloc_sq_txq_db(sq, numa);
+ case MLX5E_SQ_ICO:
+ return mlx5e_alloc_sq_ico_db(sq, numa);
+ case MLX5E_SQ_XDP:
+ return mlx5e_alloc_sq_xdp_db(sq, numa);
+ }
+
+ return 0;
+}
+
+static int mlx5e_sq_get_max_wqebbs(u8 sq_type)
+{
+ switch (sq_type) {
+ case MLX5E_SQ_ICO:
+ return MLX5E_ICOSQ_MAX_WQEBBS;
+ case MLX5E_SQ_XDP:
+ return MLX5E_XDP_TX_WQEBBS;
+ }
+ return MLX5_SEND_WQE_MAX_WQEBBS;
+}
+
static int mlx5e_create_sq(struct mlx5e_channel *c,
int tc,
struct mlx5e_sq_param *param,
void *sqc_wq = MLX5_ADDR_OF(sqc, sqc, wq);
int err;
+ sq->type = param->type;
+ sq->pdev = c->pdev;
+ sq->tstamp = &priv->tstamp;
+ sq->mkey_be = c->mkey_be;
+ sq->channel = c;
+ sq->tc = tc;
+
err = mlx5_alloc_map_uar(mdev, &sq->uar, !!MLX5_CAP_GEN(mdev, bf));
if (err)
return err;
if (err)
goto err_sq_wq_destroy;
- 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 {
+ if (sq->type == MLX5E_SQ_TXQ) {
int txq_ix;
txq_ix = c->ix + tc * priv->params.num_channels;
priv->txq_to_sq_map[txq_ix] = sq;
}
- sq->pdev = c->pdev;
- sq->tstamp = &priv->tstamp;
- sq->mkey_be = c->mkey_be;
- sq->channel = c;
- sq->tc = tc;
- sq->edge = (sq->wq.sz_m1 + 1) - MLX5_SEND_WQE_MAX_WQEBBS;
+ sq->edge = (sq->wq.sz_m1 + 1) - mlx5e_sq_get_max_wqebbs(sq->type);
sq->bf_budget = MLX5E_SQ_BF_BUDGET;
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, param->icosq ? 0 : priv->tisn[sq->tc]);
+ MLX5_SET(sqc, sqc, tis_num_0, param->type == MLX5E_SQ_ICO ?
+ 0 : priv->tisn[sq->tc]);
MLX5_SET(sqc, sqc, cqn, sq->cq.mcq.cqn);
MLX5_SET(sqc, sqc, min_wqe_inline_mode, sq->min_inline_mode);
MLX5_SET(sqc, sqc, state, MLX5_SQC_STATE_RST);
- MLX5_SET(sqc, sqc, tis_lst_sz, param->icosq ? 0 : 1);
+ MLX5_SET(sqc, sqc, tis_lst_sz, param->type == MLX5E_SQ_ICO ? 0 : 1);
MLX5_SET(sqc, sqc, flush_in_error_en, 1);
MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC);
netif_tx_disable_queue(sq->txq);
/* last doorbell out, godspeed .. */
- if (mlx5e_sq_has_room_for(sq, 1))
+ if (mlx5e_sq_has_room_for(sq, 1)) {
+ sq->db.txq.skb[(sq->pc & sq->wq.sz_m1)] = NULL;
mlx5e_send_nop(sq, true);
+ }
}
mlx5e_disable_sq(sq);
- mlx5e_free_tx_descs(sq);
+ mlx5e_free_sq_descs(sq);
mlx5e_destroy_sq(sq);
}
}
}
+ if (priv->xdp_prog) {
+ /* XDP SQ CQ params are same as normal TXQ sq CQ params */
+ err = mlx5e_open_cq(c, &cparam->tx_cq, &c->xdp_sq.cq,
+ priv->params.tx_cq_moderation);
+ if (err)
+ goto err_close_sqs;
+
+ err = mlx5e_open_sq(c, 0, &cparam->xdp_sq, &c->xdp_sq);
+ if (err) {
+ mlx5e_close_cq(&c->xdp_sq.cq);
+ goto err_close_sqs;
+ }
+ }
+
+ c->xdp = !!priv->xdp_prog;
err = mlx5e_open_rq(c, &cparam->rq, &c->rq);
if (err)
- goto err_close_sqs;
+ goto err_close_xdp_sq;
netif_set_xps_queue(netdev, get_cpu_mask(c->cpu), ix);
*cp = c;
return 0;
+err_close_xdp_sq:
+ mlx5e_close_sq(&c->xdp_sq);
err_close_sqs:
mlx5e_close_sqs(c);
static void mlx5e_close_channel(struct mlx5e_channel *c)
{
mlx5e_close_rq(&c->rq);
+ if (c->xdp)
+ mlx5e_close_sq(&c->xdp_sq);
mlx5e_close_sqs(c);
mlx5e_close_sq(&c->icosq);
napi_disable(&c->napi);
+ if (c->xdp)
+ mlx5e_close_cq(&c->xdp_sq.cq);
mlx5e_close_cq(&c->rq.cq);
mlx5e_close_tx_cqs(c);
mlx5e_close_cq(&c->icosq.cq);
param->max_inline = priv->params.tx_max_inline;
param->min_inline_mode = priv->params.tx_min_inline_mode;
+ param->type = MLX5E_SQ_TXQ;
}
static void mlx5e_build_common_cq_param(struct mlx5e_priv *priv,
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;
+ param->type = MLX5E_SQ_ICO;
+}
+
+static void mlx5e_build_xdpsq_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;
+ /* FOR XDP SQs will support only L2 inline mode */
+ param->min_inline_mode = MLX5_INLINE_MODE_NONE;
+ param->type = MLX5E_SQ_XDP;
}
static void mlx5e_build_channel_param(struct mlx5e_priv *priv, struct mlx5e_channel_param *cparam)
mlx5e_build_rq_param(priv, &cparam->rq);
mlx5e_build_sq_param(priv, &cparam->sq);
+ mlx5e_build_xdpsq_param(priv, &cparam->xdp_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);
return mlx5_eswitch_set_vport_mac(mdev->priv.eswitch, vf + 1, mac);
}
-static int mlx5e_set_vf_vlan(struct net_device *dev, int vf, u16 vlan, u8 qos)
+static int mlx5e_set_vf_vlan(struct net_device *dev, int vf, u16 vlan, u8 qos,
+ __be16 vlan_proto)
{
struct mlx5e_priv *priv = netdev_priv(dev);
struct mlx5_core_dev *mdev = priv->mdev;
+ if (vlan_proto != htons(ETH_P_8021Q))
+ return -EPROTONOSUPPORT;
+
return mlx5_eswitch_set_vport_vlan(mdev->priv.eswitch, vf + 1,
vlan, qos);
}
schedule_work(&priv->tx_timeout_work);
}
+static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
+{
+ struct mlx5e_priv *priv = netdev_priv(netdev);
+ struct bpf_prog *old_prog;
+ int err = 0;
+ bool reset, was_opened;
+ int i;
+
+ mutex_lock(&priv->state_lock);
+
+ if ((netdev->features & NETIF_F_LRO) && prog) {
+ netdev_warn(netdev, "can't set XDP while LRO is on, disable LRO first\n");
+ err = -EINVAL;
+ goto unlock;
+ }
+
+ was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
+ /* no need for full reset when exchanging programs */
+ reset = (!priv->xdp_prog || !prog);
+
+ if (was_opened && reset)
+ mlx5e_close_locked(netdev);
+
+ /* exchange programs */
+ old_prog = xchg(&priv->xdp_prog, prog);
+ if (prog)
+ bpf_prog_add(prog, 1);
+ if (old_prog)
+ bpf_prog_put(old_prog);
+
+ if (reset) /* change RQ type according to priv->xdp_prog */
+ mlx5e_set_rq_priv_params(priv);
+
+ if (was_opened && reset)
+ mlx5e_open_locked(netdev);
+
+ if (!test_bit(MLX5E_STATE_OPENED, &priv->state) || reset)
+ goto unlock;
+
+ /* exchanging programs w/o reset, we update ref counts on behalf
+ * of the channels RQs here.
+ */
+ bpf_prog_add(prog, priv->params.num_channels);
+ for (i = 0; i < priv->params.num_channels; i++) {
+ struct mlx5e_channel *c = priv->channel[i];
+
+ set_bit(MLX5E_RQ_STATE_FLUSH, &c->rq.state);
+ napi_synchronize(&c->napi);
+ /* prevent mlx5e_poll_rx_cq from accessing rq->xdp_prog */
+
+ old_prog = xchg(&c->rq.xdp_prog, prog);
+
+ clear_bit(MLX5E_RQ_STATE_FLUSH, &c->rq.state);
+ /* napi_schedule in case we have missed anything */
+ set_bit(MLX5E_CHANNEL_NAPI_SCHED, &c->flags);
+ napi_schedule(&c->napi);
+
+ if (old_prog)
+ bpf_prog_put(old_prog);
+ }
+
+unlock:
+ mutex_unlock(&priv->state_lock);
+ return err;
+}
+
+static bool mlx5e_xdp_attached(struct net_device *dev)
+{
+ struct mlx5e_priv *priv = netdev_priv(dev);
+
+ return !!priv->xdp_prog;
+}
+
+static int mlx5e_xdp(struct net_device *dev, struct netdev_xdp *xdp)
+{
+ switch (xdp->command) {
+ case XDP_SETUP_PROG:
+ return mlx5e_xdp_set(dev, xdp->prog);
+ case XDP_QUERY_PROG:
+ xdp->prog_attached = mlx5e_xdp_attached(dev);
+ return 0;
+ default:
+ return -EINVAL;
+ }
+}
+
+#ifdef CONFIG_NET_POLL_CONTROLLER
+/* Fake "interrupt" called by netpoll (eg netconsole) to send skbs without
+ * reenabling interrupts.
+ */
+static void mlx5e_netpoll(struct net_device *dev)
+{
+ struct mlx5e_priv *priv = netdev_priv(dev);
+ int i;
+
+ for (i = 0; i < priv->params.num_channels; i++)
+ napi_schedule(&priv->channel[i]->napi);
+}
+#endif
+
static const struct net_device_ops mlx5e_netdev_ops_basic = {
.ndo_open = mlx5e_open,
.ndo_stop = mlx5e_close,
.ndo_rx_flow_steer = mlx5e_rx_flow_steer,
#endif
.ndo_tx_timeout = mlx5e_tx_timeout,
+ .ndo_xdp = mlx5e_xdp,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+ .ndo_poll_controller = mlx5e_netpoll,
+#endif
};
static const struct net_device_ops mlx5e_netdev_ops_sriov = {
.ndo_set_vf_link_state = mlx5e_set_vf_link_state,
.ndo_get_vf_stats = mlx5e_get_vf_stats,
.ndo_tx_timeout = mlx5e_tx_timeout,
+ .ndo_xdp = mlx5e_xdp,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+ .ndo_poll_controller = mlx5e_netpoll,
+#endif
};
static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev)
mlx5_query_nic_vport_mac_address(mdev, 0, rep.hw_id);
rep.load = mlx5e_nic_rep_load;
rep.unload = mlx5e_nic_rep_unload;
- rep.vport = 0;
+ rep.vport = FDB_UPLINK_VPORT;
rep.priv_data = priv;
- mlx5_eswitch_register_vport_rep(esw, &rep);
+ mlx5_eswitch_register_vport_rep(esw, 0, &rep);
}
}
rep.unload = mlx5e_vport_rep_unload;
rep.vport = vport;
ether_addr_copy(rep.hw_id, mac);
- mlx5_eswitch_register_vport_rep(esw, &rep);
+ mlx5_eswitch_register_vport_rep(esw, vport, &rep);
}
}