Commit f10b7cc7 authored by Saeed Mahameed's avatar Saeed Mahameed Committed by David S. Miller

net/mlx5e: Have a clear separation between different SQ types

Make a clear separate between Regular SQ (TXQ) and ICO SQ creation,
destruction and union their mutual information structures.

Don't allocate redundant TXQ skb/wqe_info/dma_fifo arrays for ICO SQ.
And have a different SQ edge for ICO SQ than TXQ SQ, to be more
accurate.

In preparation for XDP TX support.
Signed-off-by: default avatarSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: default avatarTariq Toukan <tariqt@mellanox.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 86994156
......@@ -101,6 +101,9 @@
#define MLX5E_UPDATE_STATS_INTERVAL 200 /* msecs */
#define MLX5E_SQ_BF_BUDGET 16
#define MLX5E_ICOSQ_MAX_WQEBBS \
(DIV_ROUND_UP(sizeof(struct mlx5e_umr_wqe), MLX5_SEND_WQE_BB))
#define MLX5E_NUM_MAIN_GROUPS 9
static inline u16 mlx5_min_rx_wqes(int wq_type, u32 wq_size)
......@@ -386,6 +389,11 @@ struct mlx5e_ico_wqe_info {
u8 num_wqebbs;
};
enum mlx5e_sq_type {
MLX5E_SQ_TXQ,
MLX5E_SQ_ICO
};
struct mlx5e_sq {
/* data path */
......@@ -403,10 +411,15 @@ struct mlx5e_sq {
struct mlx5e_cq cq;
/* pointers to per packet info: write@xmit, read@completion */
struct sk_buff **skb;
struct mlx5e_sq_dma *dma_fifo;
struct mlx5e_tx_wqe_info *wqe_info;
/* pointers to per tx element info: write@xmit, read@completion */
union {
struct {
struct sk_buff **skb;
struct mlx5e_sq_dma *dma_fifo;
struct mlx5e_tx_wqe_info *wqe_info;
} txq;
struct mlx5e_ico_wqe_info *ico_wqe;
} db;
/* read only */
struct mlx5_wq_cyc wq;
......@@ -428,8 +441,8 @@ struct mlx5e_sq {
struct mlx5_uar uar;
struct mlx5e_channel *channel;
int tc;
struct mlx5e_ico_wqe_info *ico_wqe_info;
u32 rate_limit;
u8 type;
} ____cacheline_aligned_in_smp;
static inline bool mlx5e_sq_has_room_for(struct mlx5e_sq *sq, u16 n)
......
......@@ -51,7 +51,7 @@ struct mlx5e_sq_param {
struct mlx5_wq_param wq;
u16 max_inline;
u8 min_inline_mode;
bool icosq;
enum mlx5e_sq_type type;
};
struct mlx5e_cq_param {
......@@ -740,8 +740,8 @@ static int mlx5e_open_rq(struct mlx5e_channel *c,
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;
......@@ -765,26 +765,43 @@ static void mlx5e_close_rq(struct mlx5e_rq *rq)
mlx5e_destroy_rq(rq);
}
static void mlx5e_free_sq_db(struct mlx5e_sq *sq)
static void mlx5e_free_sq_ico_db(struct mlx5e_sq *sq)
{
kfree(sq->wqe_info);
kfree(sq->dma_fifo);
kfree(sq->skb);
kfree(sq->db.ico_wqe);
}
static int mlx5e_alloc_sq_db(struct mlx5e_sq *sq, int numa)
static int mlx5e_alloc_sq_ico_db(struct mlx5e_sq *sq, int numa)
{
u8 wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
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->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);
if (!sq->skb || !sq->dma_fifo || !sq->wqe_info) {
mlx5e_free_sq_db(sq);
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;
}
......@@ -793,6 +810,30 @@ static int mlx5e_alloc_sq_db(struct mlx5e_sq *sq, int numa)
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;
}
}
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);
}
return 0;
}
static int mlx5e_create_sq(struct mlx5e_channel *c,
int tc,
struct mlx5e_sq_param *param,
......@@ -803,8 +844,16 @@ static int mlx5e_create_sq(struct mlx5e_channel *c,
void *sqc = param->sqc;
void *sqc_wq = MLX5_ADDR_OF(sqc, sqc, wq);
u16 sq_max_wqebbs;
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;
......@@ -833,18 +882,8 @@ static int mlx5e_create_sq(struct mlx5e_channel *c,
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 {
sq_max_wqebbs = MLX5_SEND_WQE_MAX_WQEBBS;
if (sq->type == MLX5E_SQ_TXQ) {
int txq_ix;
txq_ix = c->ix + tc * priv->params.num_channels;
......@@ -852,19 +891,14 @@ static int mlx5e_create_sq(struct mlx5e_channel *c,
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;
if (sq->type == MLX5E_SQ_ICO)
sq_max_wqebbs = MLX5E_ICOSQ_MAX_WQEBBS;
sq->edge = (sq->wq.sz_m1 + 1) - sq_max_wqebbs;
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);
......@@ -879,7 +913,6 @@ static void mlx5e_destroy_sq(struct mlx5e_sq *sq)
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);
......@@ -908,11 +941,12 @@ static int mlx5e_enable_sq(struct mlx5e_sq *sq, struct mlx5e_sq_param *param)
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);
......@@ -1027,8 +1061,10 @@ static void mlx5e_close_sq(struct mlx5e_sq *sq)
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);
......@@ -1505,6 +1541,7 @@ static void mlx5e_build_sq_param(struct mlx5e_priv *priv,
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,
......@@ -1578,7 +1615,7 @@ static void mlx5e_build_icosq_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_channel_param(struct mlx5e_priv *priv, struct mlx5e_channel_param *cparam)
......
......@@ -337,8 +337,8 @@ static inline void mlx5e_post_umr_wqe(struct mlx5e_rq *rq, u16 ix)
/* fill sq edge with nops to avoid wqe wrap around */
while ((pi = (sq->pc & wq->sz_m1)) > sq->edge) {
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);
}
......@@ -348,8 +348,8 @@ static inline void mlx5e_post_umr_wqe(struct mlx5e_rq *rq, u16 ix)
cpu_to_be32((sq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) |
MLX5_OPCODE_UMR);
sq->ico_wqe_info[pi].opcode = MLX5_OPCODE_UMR;
sq->ico_wqe_info[pi].num_wqebbs = num_wqebbs;
sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_UMR;
sq->db.ico_wqe[pi].num_wqebbs = num_wqebbs;
sq->pc += num_wqebbs;
mlx5e_tx_notify_hw(sq, &wqe->ctrl, 0);
}
......
......@@ -52,7 +52,6 @@ void mlx5e_send_nop(struct mlx5e_sq *sq, bool notify_hw)
cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | MLX5_OPCODE_NOP);
cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | 0x01);
sq->skb[pi] = NULL;
sq->pc++;
sq->stats.nop++;
......@@ -82,15 +81,17 @@ static inline void mlx5e_dma_push(struct mlx5e_sq *sq,
u32 size,
enum mlx5e_dma_map_type map_type)
{
sq->dma_fifo[sq->dma_fifo_pc & sq->dma_fifo_mask].addr = addr;
sq->dma_fifo[sq->dma_fifo_pc & sq->dma_fifo_mask].size = size;
sq->dma_fifo[sq->dma_fifo_pc & sq->dma_fifo_mask].type = map_type;
u32 i = sq->dma_fifo_pc & sq->dma_fifo_mask;
sq->db.txq.dma_fifo[i].addr = addr;
sq->db.txq.dma_fifo[i].size = size;
sq->db.txq.dma_fifo[i].type = map_type;
sq->dma_fifo_pc++;
}
static inline struct mlx5e_sq_dma *mlx5e_dma_get(struct mlx5e_sq *sq, u32 i)
{
return &sq->dma_fifo[i & sq->dma_fifo_mask];
return &sq->db.txq.dma_fifo[i & sq->dma_fifo_mask];
}
static void mlx5e_dma_unmap_wqe_err(struct mlx5e_sq *sq, u8 num_dma)
......@@ -221,7 +222,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
u16 pi = sq->pc & wq->sz_m1;
struct mlx5e_tx_wqe *wqe = mlx5_wq_cyc_get_wqe(wq, pi);
struct mlx5e_tx_wqe_info *wi = &sq->wqe_info[pi];
struct mlx5e_tx_wqe_info *wi = &sq->db.txq.wqe_info[pi];
struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
struct mlx5_wqe_eth_seg *eseg = &wqe->eth;
......@@ -341,7 +342,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | opcode);
cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt);
sq->skb[pi] = skb;
sq->db.txq.skb[pi] = skb;
wi->num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS);
sq->pc += wi->num_wqebbs;
......@@ -368,8 +369,10 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
}
/* fill sq edge with nops to avoid wqe wrap around */
while ((sq->pc & wq->sz_m1) > sq->edge)
while ((pi = (sq->pc & wq->sz_m1)) > sq->edge) {
sq->db.txq.skb[pi] = NULL;
mlx5e_send_nop(sq, false);
}
if (bf)
sq->bf_budget--;
......@@ -442,8 +445,8 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
last_wqe = (sqcc == wqe_counter);
ci = sqcc & sq->wq.sz_m1;
skb = sq->skb[ci];
wi = &sq->wqe_info[ci];
skb = sq->db.txq.skb[ci];
wi = &sq->db.txq.wqe_info[ci];
if (unlikely(!skb)) { /* nop */
sqcc++;
......@@ -499,10 +502,13 @@ void mlx5e_free_tx_descs(struct mlx5e_sq *sq)
u16 ci;
int i;
if (sq->type != MLX5E_SQ_TXQ)
return;
while (sq->cc != sq->pc) {
ci = sq->cc & sq->wq.sz_m1;
skb = sq->skb[ci];
wi = &sq->wqe_info[ci];
skb = sq->db.txq.skb[ci];
wi = &sq->db.txq.wqe_info[ci];
if (!skb) { /* nop */
sq->cc++;
......
......@@ -72,7 +72,7 @@ static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
do {
u16 ci = be16_to_cpu(cqe->wqe_counter) & wq->sz_m1;
struct mlx5e_ico_wqe_info *icowi = &sq->ico_wqe_info[ci];
struct mlx5e_ico_wqe_info *icowi = &sq->db.ico_wqe[ci];
mlx5_cqwq_pop(&cq->wq);
sqcc += icowi->num_wqebbs;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment