For an Ethernet RQ, packets received when receive WQEs are exhausted
are dropped. This behavior prevents slow or malicious software
entities at the host from affecting the network. While for hairpin
cases, even if there is no software involved during the packet
forwarding from Rx to Tx side, some hiccup in the hardware or back
pressure from Tx side may still cause the WQEs to be exhausted. In
certain scenarios it may be preferred to configure the device to
avoid such packet drops, assuming the posting of WQEs will resume
shortly.
To support this, a new devarg "delay_drop_en" is introduced, by
default, the delay drop is enabled for hairpin Rx queues and
disabled for standard Rx queues. This value is used as a bit mask:
- bit 0: enablement of standard Rx queue
- bit 1: enablement of hairpin Rx queue
And this attribute will be applied to all Rx queues of a device.
The "rq_delay_drop" capability in the HCA_CAP is checked before
creating any queue. If the hardware capabilities do not support
this delay drop, all the Rx queues will still be created without
this attribute, and the devarg setting will be ignored even if it
is specified explicitly.
Signed-off-by: Bing Zhao <bingz@nvidia.com>
---
drivers/common/mlx5/mlx5_devx_cmds.c | 1 +
drivers/common/mlx5/mlx5_devx_cmds.h | 1 +
drivers/net/mlx5/linux/mlx5_os.c | 11 +++++++++++
drivers/net/mlx5/mlx5.c | 7 +++++++
drivers/net/mlx5/mlx5.h | 9 +++++++++
drivers/net/mlx5/mlx5_devx.c | 5 +++++
drivers/net/mlx5/mlx5_rx.h | 1 +
7 files changed, 35 insertions(+)
@@ -962,6 +962,7 @@ mlx5_devx_cmd_query_hca_attr(void *ctx,
attr->ct_offload = !!(MLX5_GET64(cmd_hca_cap, hcattr,
general_obj_types) &
MLX5_GENERAL_OBJ_TYPES_CAP_CONN_TRACK_OFFLOAD);
+ attr->rq_delay_drop = MLX5_GET(cmd_hca_cap, hcattr, rq_delay_drop);
if (attr->qos.sup) {
hcattr = mlx5_devx_get_hca_cap(ctx, in, out, &rc,
MLX5_GET_HCA_CAP_OP_MOD_QOS_CAP |
@@ -176,6 +176,7 @@ struct mlx5_hca_attr {
uint32_t swp_csum:1;
uint32_t swp_lso:1;
uint32_t lro_max_msg_sz_mode:2;
+ uint32_t rq_delay_drop:1;
uint32_t lro_timer_supported_periods[MLX5_LRO_NUM_SUPP_PERIODS];
uint16_t lro_min_mss_size;
uint32_t flex_parser_protocols;
@@ -1506,6 +1506,15 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
goto error;
#endif
}
+ if (config->std_delay_drop || config->hp_delay_drop) {
+ if (!config->hca_attr.rq_delay_drop) {
+ config->std_delay_drop = 0;
+ config->hp_delay_drop = 0;
+ DRV_LOG(WARNING,
+ "dev_port-%u: Rxq delay drop is not supported",
+ priv->dev_port);
+ }
+ }
if (sh->devx) {
uint32_t reg[MLX5_ST_SZ_DW(register_mtutc)];
@@ -2075,6 +2084,8 @@ mlx5_os_config_default(struct mlx5_dev_config *config)
config->decap_en = 1;
config->log_hp_size = MLX5_ARG_UNSET;
config->allow_duplicate_pattern = 1;
+ config->std_delay_drop = 0;
+ config->hp_delay_drop = 0;
}
/**
@@ -183,6 +183,9 @@
/* Device parameter to configure implicit registration of mempool memory. */
#define MLX5_MR_MEMPOOL_REG_EN "mr_mempool_reg_en"
+/* Device parameter to configure the delay drop when creating Rxqs. */
+#define MLX5_DELAY_DROP_EN "delay_drop_en"
+
/* Shared memory between primary and secondary processes. */
struct mlx5_shared_data *mlx5_shared_data;
@@ -2095,6 +2098,9 @@ mlx5_args_check(const char *key, const char *val, void *opaque)
config->decap_en = !!tmp;
} else if (strcmp(MLX5_ALLOW_DUPLICATE_PATTERN, key) == 0) {
config->allow_duplicate_pattern = !!tmp;
+ } else if (strcmp(MLX5_DELAY_DROP_EN, key) == 0) {
+ config->std_delay_drop = tmp & MLX5_DELAY_DROP_STANDARD;
+ config->hp_delay_drop = tmp & MLX5_DELAY_DROP_HAIRPIN;
} else {
DRV_LOG(WARNING, "%s: unknown parameter", key);
rte_errno = EINVAL;
@@ -2157,6 +2163,7 @@ mlx5_args(struct mlx5_dev_config *config, struct rte_devargs *devargs)
MLX5_DECAP_EN,
MLX5_ALLOW_DUPLICATE_PATTERN,
MLX5_MR_MEMPOOL_REG_EN,
+ MLX5_DELAY_DROP_EN,
NULL,
};
struct rte_kvargs *kvlist;
@@ -99,6 +99,13 @@ enum mlx5_flow_type {
MLX5_FLOW_TYPE_MAXI,
};
+/* The mode of delay drop for Rx queues. */
+enum mlx5_delay_drop_mode {
+ MLX5_DELAY_DROP_NONE = 0, /* All disabled. */
+ MLX5_DELAY_DROP_STANDARD = RTE_BIT32(0), /* Standard queues enable. */
+ MLX5_DELAY_DROP_HAIRPIN = RTE_BIT32(1), /* Hairpin queues enable. */
+};
+
/* Hlist and list callback context. */
struct mlx5_flow_cb_ctx {
struct rte_eth_dev *dev;
@@ -264,6 +271,8 @@ struct mlx5_dev_config {
unsigned int dv_miss_info:1; /* restore packet after partial hw miss */
unsigned int allow_duplicate_pattern:1;
/* Allow/Prevent the duplicate rules pattern. */
+ unsigned int std_delay_drop:1; /* Enable standard Rxq delay drop. */
+ unsigned int hp_delay_drop:1; /* Enable hairpin Rxq delay drop. */
struct {
unsigned int enabled:1; /* Whether MPRQ is enabled. */
unsigned int stride_num_n; /* Number of strides. */
@@ -280,6 +280,7 @@ mlx5_rxq_create_devx_rq_resources(struct rte_eth_dev *dev,
MLX5_WQ_END_PAD_MODE_NONE;
rq_attr.wq_attr.pd = cdev->pdn;
rq_attr.counter_set_id = priv->counter_set_id;
+ rq_attr.delay_drop_en = rxq_data->delay_drop;
/* Create RQ using DevX API. */
return mlx5_devx_rq_create(cdev->ctx, &rxq_ctrl->obj->rq_obj, wqe_size,
log_desc_n, &rq_attr, rxq_ctrl->socket);
@@ -443,6 +444,8 @@ mlx5_rxq_obj_hairpin_new(struct rte_eth_dev *dev, uint16_t idx)
attr.wq_attr.log_hairpin_data_sz -
MLX5_HAIRPIN_QUEUE_STRIDE;
attr.counter_set_id = priv->counter_set_id;
+ rxq_data->delay_drop = priv->config.hp_delay_drop;
+ attr.delay_drop_en = priv->config.hp_delay_drop;
tmpl->rq = mlx5_devx_cmd_create_rq(priv->sh->cdev->ctx, &attr,
rxq_ctrl->socket);
if (!tmpl->rq) {
@@ -503,6 +506,7 @@ mlx5_rxq_devx_obj_new(struct rte_eth_dev *dev, uint16_t idx)
DRV_LOG(ERR, "Failed to create CQ.");
goto error;
}
+ rxq_data->delay_drop = priv->config.std_delay_drop;
/* Create RQ using DevX API. */
ret = mlx5_rxq_create_devx_rq_resources(dev, rxq_data);
if (ret) {
@@ -921,6 +925,7 @@ mlx5_rxq_devx_obj_drop_create(struct rte_eth_dev *dev)
rxq_ctrl->priv = priv;
rxq_ctrl->obj = rxq;
rxq_data = &rxq_ctrl->rxq;
+ rxq_data->delay_drop = 0;
/* Create CQ using DevX API. */
ret = mlx5_rxq_create_devx_cq_resources(dev, rxq_data);
if (ret != 0) {
@@ -92,6 +92,7 @@ struct mlx5_rxq_data {
unsigned int lro:1; /* Enable LRO. */
unsigned int dynf_meta:1; /* Dynamic metadata is configured. */
unsigned int mcqe_format:3; /* CQE compression format. */
+ unsigned int delay_drop:1; /* Enable delay drop. */
volatile uint32_t *rq_db;
volatile uint32_t *cq_db;
uint16_t port_id;