Commit 673d7ab7 authored by Cosmin Ratiu's avatar Cosmin Ratiu Committed by Jakub Kicinski
Browse files

net/mlx5e: Prepare for using multiple TX doorbells



The driver allocates a single doorbell per device and uses
it for all Send Queues (SQs). This can become a bottleneck due to the
high number of concurrent MMIO accesses when ringing the same doorbell
from many channels.

This patch makes the doorbells used by channel queues configurable.

mlx5e_channel_pick_doorbell() is added to select the doorbell to be used
for a given channel, picking the default for now.

When opening a channel, the selected doorbell is saved to the channel
struct and used whenever channel-related queues are created.

Finally, 'uar_page' is added to 'struct mlx5e_create_sq_param' to
control which doorbell to use when allocating an SQ, since that can
happen outside channel context (e.g. for PTP).

Signed-off-by: default avatarCosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: default avatarDragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: default avatarTariq Toukan <tariqt@nvidia.com>
Reviewed-by: default avatarSimon Horman <horms@kernel.org>
Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent aa4595d0
Loading
Loading
Loading
Loading
+1 −0
Original line number Diff line number Diff line
@@ -788,6 +788,7 @@ struct mlx5e_channel {
	int                        vec_ix;
	int                        sd_ix;
	int                        cpu;
	struct mlx5_sq_bfreg      *bfreg;
	/* Sync between icosq recovery and XSK enable/disable. */
	struct mutex               icosq_recovery_lock;

+1 −0
Original line number Diff line number Diff line
@@ -51,6 +51,7 @@ struct mlx5e_create_sq_param {
	u32                         tisn;
	u8                          tis_lst_sz;
	u8                          min_inline_mode;
	u32                         uar_page;
};

/* Striding RQ dynamic parameters */
+3 −1
Original line number Diff line number Diff line
@@ -334,7 +334,7 @@ static int mlx5e_ptp_alloc_txqsq(struct mlx5e_ptp *c, int txq_ix,
	sq->mdev      = mdev;
	sq->ch_ix     = MLX5E_PTP_CHANNEL_IX;
	sq->txq_ix    = txq_ix;
	sq->uar_map   = mdev->priv.bfreg.map;
	sq->uar_map   = c->bfreg->map;
	sq->min_inline_mode = params->tx_min_inline_mode;
	sq->hw_mtu    = MLX5E_SW2HW_MTU(params, params->sw_mtu);
	sq->stats     = &c->priv->ptp_stats.sq[tc];
@@ -486,6 +486,7 @@ static int mlx5e_ptp_open_txqsq(struct mlx5e_ptp *c, u32 tisn,
	csp.wq_ctrl         = &txqsq->wq_ctrl;
	csp.min_inline_mode = txqsq->min_inline_mode;
	csp.ts_cqe_to_dest_cqn = ptpsq->ts_cq.mcq.cqn;
	csp.uar_page = c->bfreg->index;

	err = mlx5e_create_sq_rdy(c->mdev, sqp, &csp, 0, &txqsq->sqn);
	if (err)
@@ -900,6 +901,7 @@ int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params,
	c->num_tc   = mlx5e_get_dcb_num_tc(params);
	c->stats    = &priv->ptp_stats.ch;
	c->lag_port = lag_port;
	c->bfreg    = &mdev->priv.bfreg;

	err = mlx5e_ptp_set_state(c, params);
	if (err)
+1 −0
Original line number Diff line number Diff line
@@ -66,6 +66,7 @@ struct mlx5e_ptp {
	struct mlx5_core_dev      *mdev;
	struct hwtstamp_config    *tstamp;
	DECLARE_BITMAP(state, MLX5E_PTP_STATE_NUM_STATES);
	struct mlx5_sq_bfreg      *bfreg;
};

static inline bool mlx5e_use_ptpsq(struct sk_buff *skb)
+14 −4
Original line number Diff line number Diff line
@@ -1536,7 +1536,7 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
	sq->pdev      = c->pdev;
	sq->mkey_be   = c->mkey_be;
	sq->channel   = c;
	sq->uar_map   = mdev->priv.bfreg.map;
	sq->uar_map   = c->bfreg->map;
	sq->min_inline_mode = params->tx_min_inline_mode;
	sq->hw_mtu    = MLX5E_SW2HW_MTU(params, params->sw_mtu) - ETH_FCS_LEN;
	sq->xsk_pool  = xsk_pool;
@@ -1621,7 +1621,7 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
	int err;

	sq->channel   = c;
	sq->uar_map   = mdev->priv.bfreg.map;
	sq->uar_map   = c->bfreg->map;
	sq->reserved_room = param->stop_room;

	param->wq.db_numa_node = cpu_to_node(c->cpu);
@@ -1706,7 +1706,7 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
	sq->priv      = c->priv;
	sq->ch_ix     = c->ix;
	sq->txq_ix    = txq_ix;
	sq->uar_map   = mdev->priv.bfreg.map;
	sq->uar_map   = c->bfreg->map;
	sq->min_inline_mode = params->tx_min_inline_mode;
	sq->hw_mtu    = MLX5E_SW2HW_MTU(params, params->sw_mtu);
	sq->max_sq_mpw_wqebbs = mlx5e_get_max_sq_aligned_wqebbs(mdev);
@@ -1782,7 +1782,7 @@ static int mlx5e_create_sq(struct mlx5_core_dev *mdev,
	MLX5_SET(sqc,  sqc, flush_in_error_en, 1);

	MLX5_SET(wq,   wq, wq_type,       MLX5_WQ_TYPE_CYCLIC);
	MLX5_SET(wq,   wq, uar_page,      mdev->priv.bfreg.index);
	MLX5_SET(wq,   wq, uar_page,      csp->uar_page);
	MLX5_SET(wq,   wq, log_wq_pg_sz,  csp->wq_ctrl->buf.page_shift -
					  MLX5_ADAPTER_PAGE_SHIFT);
	MLX5_SET64(wq, wq, dbr_addr,      csp->wq_ctrl->db.dma);
@@ -1886,6 +1886,7 @@ int mlx5e_open_txqsq(struct mlx5e_channel *c, u32 tisn, int txq_ix,
	csp.cqn             = sq->cq.mcq.cqn;
	csp.wq_ctrl         = &sq->wq_ctrl;
	csp.min_inline_mode = sq->min_inline_mode;
	csp.uar_page        = c->bfreg->index;
	err = mlx5e_create_sq_rdy(c->mdev, param, &csp, qos_queue_group_id, &sq->sqn);
	if (err)
		goto err_free_txqsq;
@@ -2056,6 +2057,7 @@ static int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params
	csp.cqn             = sq->cq.mcq.cqn;
	csp.wq_ctrl         = &sq->wq_ctrl;
	csp.min_inline_mode = params->tx_min_inline_mode;
	csp.uar_page        = c->bfreg->index;
	err = mlx5e_create_sq_rdy(c->mdev, param, &csp, 0, &sq->sqn);
	if (err)
		goto err_free_icosq;
@@ -2116,6 +2118,7 @@ int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params,
	csp.cqn             = sq->cq.mcq.cqn;
	csp.wq_ctrl         = &sq->wq_ctrl;
	csp.min_inline_mode = sq->min_inline_mode;
	csp.uar_page        = c->bfreg->index;
	set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);

	err = mlx5e_create_sq_rdy(c->mdev, param, &csp, 0, &sq->sqn);
@@ -2744,6 +2747,11 @@ void mlx5e_trigger_napi_sched(struct napi_struct *napi)
	local_bh_enable();
}

static void mlx5e_channel_pick_doorbell(struct mlx5e_channel *c)
{
	c->bfreg = &c->mdev->priv.bfreg;
}

static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
			      struct mlx5e_params *params,
			      struct xsk_buff_pool *xsk_pool,
@@ -2798,6 +2806,8 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
	c->aff_mask = irq_get_effective_affinity_mask(irq);
	c->lag_port = mlx5e_enumerate_lag_port(mdev, ix);

	mlx5e_channel_pick_doorbell(c);

	netif_napi_add_config_locked(netdev, &c->napi, mlx5e_napi_poll, ix);
	netif_napi_set_irq_locked(&c->napi, irq);