net/mlx5e: Don't wait for SQ completions on close

Instead of asking the firmware to flush the SQ (Send Queue) via
asynchronous completions when moved to error, we handle SQ flush
manually (mlx5e_free_tx_descs) same as we did when SQ flush got
timed out or on tx_timeout.

This will reduce SQs flush time and speedup interface down procedure.

Moved mlx5e_free_tx_descs to the end of en_tx.c for tx
critical code locality.

Fixes: 29429f3300 ('net/mlx5e: Timeout if SQ doesn't flush during close')
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Saeed Mahameed 2016-08-29 01:13:45 +03:00 committed by David S. Miller
parent 8484f9ed13
commit 6e8dd6d6f4
4 changed files with 50 additions and 76 deletions

View File

@ -369,9 +369,8 @@ struct mlx5e_sq_dma {
};
enum {
MLX5E_SQ_STATE_WAKE_TXQ_ENABLE,
MLX5E_SQ_STATE_FLUSH,
MLX5E_SQ_STATE_BF_ENABLE,
MLX5E_SQ_STATE_TX_TIMEOUT,
};
struct mlx5e_ico_wqe_info {

View File

@ -39,13 +39,6 @@
#include "eswitch.h"
#include "vxlan.h"
enum {
MLX5_EN_QP_FLUSH_TIMEOUT_MS = 5000,
MLX5_EN_QP_FLUSH_MSLEEP_QUANT = 20,
MLX5_EN_QP_FLUSH_MAX_ITER = MLX5_EN_QP_FLUSH_TIMEOUT_MS /
MLX5_EN_QP_FLUSH_MSLEEP_QUANT,
};
struct mlx5e_rq_param {
u32 rqc[MLX5_ST_SZ_DW(rqc)];
struct mlx5_wq_param wq;
@ -827,7 +820,6 @@ static int mlx5e_open_sq(struct mlx5e_channel *c,
goto err_disable_sq;
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);
}
@ -851,38 +843,20 @@ static inline void netif_tx_disable_queue(struct netdev_queue *txq)
static void mlx5e_close_sq(struct mlx5e_sq *sq)
{
int tout = 0;
int err;
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);
err = mlx5e_modify_sq(sq, MLX5_SQC_STATE_RDY,
MLX5_SQC_STATE_ERR, false, 0);
if (err)
set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state);
}
/* wait till sq is empty, unless a TX timeout occurred on this SQ */
while (sq->cc != sq->pc &&
!test_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state)) {
msleep(MLX5_EN_QP_FLUSH_MSLEEP_QUANT);
if (tout++ > MLX5_EN_QP_FLUSH_MAX_ITER)
set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state);
}
/* avoid destroying sq before mlx5e_poll_tx_cq() is done with it */
set_bit(MLX5E_SQ_STATE_FLUSH, &sq->state);
/* prevent netif_tx_wake_queue */
napi_synchronize(&sq->channel->napi);
mlx5e_free_tx_descs(sq);
if (sq->txq) {
netif_tx_disable_queue(sq->txq);
/* last doorbell out, godspeed .. */
if (mlx5e_sq_has_room_for(sq, 1))
mlx5e_send_nop(sq, true);
}
mlx5e_disable_sq(sq);
mlx5e_free_tx_descs(sq);
mlx5e_destroy_sq(sq);
}
@ -2802,7 +2776,7 @@ static void mlx5e_tx_timeout(struct net_device *dev)
if (!netif_xmit_stopped(netdev_get_tx_queue(dev, i)))
continue;
sched_work = true;
set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state);
set_bit(MLX5E_SQ_STATE_FLUSH, &sq->state);
netdev_err(dev, "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x\n",
i, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc);
}

View File

@ -394,35 +394,6 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
return mlx5e_sq_xmit(sq, skb);
}
void mlx5e_free_tx_descs(struct mlx5e_sq *sq)
{
struct mlx5e_tx_wqe_info *wi;
struct sk_buff *skb;
u16 ci;
int i;
while (sq->cc != sq->pc) {
ci = sq->cc & sq->wq.sz_m1;
skb = sq->skb[ci];
wi = &sq->wqe_info[ci];
if (!skb) { /* nop */
sq->cc++;
continue;
}
for (i = 0; i < wi->num_dma; i++) {
struct mlx5e_sq_dma *dma =
mlx5e_dma_get(sq, sq->dma_fifo_cc++);
mlx5e_tx_dma_unmap(sq->pdev, dma);
}
dev_kfree_skb_any(skb);
sq->cc += wi->num_wqebbs;
}
}
bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
{
struct mlx5e_sq *sq;
@ -434,7 +405,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
sq = container_of(cq, struct mlx5e_sq, cq);
if (unlikely(test_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state)))
if (unlikely(test_bit(MLX5E_SQ_STATE_FLUSH, &sq->state)))
return false;
npkts = 0;
@ -512,11 +483,39 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
netdev_tx_completed_queue(sq->txq, npkts, nbytes);
if (netif_tx_queue_stopped(sq->txq) &&
mlx5e_sq_has_room_for(sq, MLX5E_SQ_STOP_ROOM) &&
likely(test_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state))) {
netif_tx_wake_queue(sq->txq);
sq->stats.wake++;
mlx5e_sq_has_room_for(sq, MLX5E_SQ_STOP_ROOM)) {
netif_tx_wake_queue(sq->txq);
sq->stats.wake++;
}
return (i == MLX5E_TX_CQ_POLL_BUDGET);
}
void mlx5e_free_tx_descs(struct mlx5e_sq *sq)
{
struct mlx5e_tx_wqe_info *wi;
struct sk_buff *skb;
u16 ci;
int i;
while (sq->cc != sq->pc) {
ci = sq->cc & sq->wq.sz_m1;
skb = sq->skb[ci];
wi = &sq->wqe_info[ci];
if (!skb) { /* nop */
sq->cc++;
continue;
}
for (i = 0; i < wi->num_dma; i++) {
struct mlx5e_sq_dma *dma =
mlx5e_dma_get(sq, sq->dma_fifo_cc++);
mlx5e_tx_dma_unmap(sq->pdev, dma);
}
dev_kfree_skb_any(skb);
sq->cc += wi->num_wqebbs;
}
}

View File

@ -51,16 +51,18 @@ struct mlx5_cqe64 *mlx5e_get_cqe(struct mlx5e_cq *cq)
static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
{
struct mlx5e_sq *sq = container_of(cq, struct mlx5e_sq, cq);
struct mlx5_wq_cyc *wq;
struct mlx5_cqe64 *cqe;
struct mlx5e_sq *sq;
u16 sqcc;
if (unlikely(test_bit(MLX5E_SQ_STATE_FLUSH, &sq->state)))
return;
cqe = mlx5e_get_cqe(cq);
if (likely(!cqe))
return;
sq = container_of(cq, struct mlx5e_sq, cq);
wq = &sq->wq;
/* sq->cc must be updated only after mlx5_cqwq_update_db_record(),