[12/13] net/mlx5: split hairpin flows
Checks
Commit Message
Since the encap action is not supported in RX, we need to split the
hairpin flow into RX and TX.
Signed-off-by: Ori Kam <orika@mellanox.com>
---
drivers/net/mlx5/mlx5.c | 10 ++
drivers/net/mlx5/mlx5.h | 10 ++
drivers/net/mlx5/mlx5_flow.c | 281 +++++++++++++++++++++++++++++++++++--
drivers/net/mlx5/mlx5_flow.h | 14 +-
drivers/net/mlx5/mlx5_flow_dv.c | 10 +-
drivers/net/mlx5/mlx5_flow_verbs.c | 11 +-
drivers/net/mlx5/mlx5_rxq.c | 26 ++++
drivers/net/mlx5/mlx5_rxtx.h | 2 +
8 files changed, 334 insertions(+), 30 deletions(-)
Comments
> -----Original Message-----
> From: Ori Kam <orika@mellanox.com>
> Sent: Thursday, September 26, 2019 9:29
> To: Matan Azrad <matan@mellanox.com>; Shahaf Shuler
> <shahafs@mellanox.com>; Slava Ovsiienko <viacheslavo@mellanox.com>
> Cc: dev@dpdk.org; Ori Kam <orika@mellanox.com>; jingjing.wu@intel.com;
> stephen@networkplumber.org
> Subject: [PATCH 12/13] net/mlx5: split hairpin flows
>
> Since the encap action is not supported in RX, we need to split the hairpin
> flow into RX and TX.
>
> Signed-off-by: Ori Kam <orika@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
> ---
> drivers/net/mlx5/mlx5.c | 10 ++
> drivers/net/mlx5/mlx5.h | 10 ++
> drivers/net/mlx5/mlx5_flow.c | 281
> +++++++++++++++++++++++++++++++++++--
> drivers/net/mlx5/mlx5_flow.h | 14 +-
> drivers/net/mlx5/mlx5_flow_dv.c | 10 +-
> drivers/net/mlx5/mlx5_flow_verbs.c | 11 +-
> drivers/net/mlx5/mlx5_rxq.c | 26 ++++
> drivers/net/mlx5/mlx5_rxtx.h | 2 +
> 8 files changed, 334 insertions(+), 30 deletions(-)
>
> diff --git a/drivers/net/mlx5/mlx5.c b/drivers/net/mlx5/mlx5.c index
> 940503d..2837cba 100644
> --- a/drivers/net/mlx5/mlx5.c
> +++ b/drivers/net/mlx5/mlx5.c
> @@ -528,6 +528,12 @@ struct mlx5_flow_id_pool *
> err = ENOMEM;
> goto error;
> }
> + sh->flow_id_pool = mlx5_flow_id_pool_alloc();
> + if (!sh->flow_id_pool) {
> + DRV_LOG(ERR, "can't create flow id pool");
> + err = ENOMEM;
> + goto error;
> + }
> #endif /* HAVE_IBV_FLOW_DV_SUPPORT */
> /*
> * Once the device is added to the list of memory event @@ -567,6
> +573,8 @@ struct mlx5_flow_id_pool *
> claim_zero(mlx5_glue->dealloc_pd(sh->pd));
> if (sh->ctx)
> claim_zero(mlx5_glue->close_device(sh->ctx));
> + if (sh->flow_id_pool)
> + mlx5_flow_id_pool_release(sh->flow_id_pool);
> rte_free(sh);
> assert(err > 0);
> rte_errno = err;
> @@ -629,6 +637,8 @@ struct mlx5_flow_id_pool *
> claim_zero(mlx5_devx_cmd_destroy(sh->td));
> if (sh->ctx)
> claim_zero(mlx5_glue->close_device(sh->ctx));
> + if (sh->flow_id_pool)
> + mlx5_flow_id_pool_release(sh->flow_id_pool);
> rte_free(sh);
> exit:
> pthread_mutex_unlock(&mlx5_ibv_list_mutex);
> diff --git a/drivers/net/mlx5/mlx5.h b/drivers/net/mlx5/mlx5.h index
> 5f1a25d..5336554 100644
> --- a/drivers/net/mlx5/mlx5.h
> +++ b/drivers/net/mlx5/mlx5.h
> @@ -574,6 +574,15 @@ struct mlx5_devx_dbr_page {
> uint64_t dbr_bitmap[MLX5_DBR_BITMAP_SIZE]; };
>
> +/* ID generation structure. */
> +struct mlx5_flow_id_pool {
> + uint32_t *free_arr; /**< Pointer to the a array of free values. */
> + uint32_t base_index;
> + /**< The next index that can be used without any free elements. */
> + uint32_t *curr; /**< Pointer to the index to pop. */
> + uint32_t *last; /**< Pointer to the last element in the empty arrray.
> +*/ };
> +
> /*
> * Shared Infiniband device context for Master/Representors
> * which belong to same IB device with multiple IB ports.
> @@ -632,6 +641,7 @@ struct mlx5_ibv_shared {
> struct mlx5dv_devx_cmd_comp *devx_comp; /* DEVX async comp
> obj. */
> struct mlx5_devx_obj *tis; /* TIS object. */
> struct mlx5_devx_obj *td; /* Transport domain. */
> + struct mlx5_flow_id_pool *flow_id_pool; /* Flow ID pool. */
> struct mlx5_ibv_shared_port port[]; /* per device port data array. */
> };
>
> diff --git a/drivers/net/mlx5/mlx5_flow.c b/drivers/net/mlx5/mlx5_flow.c
> index 33ed204..50e1d11 100644
> --- a/drivers/net/mlx5/mlx5_flow.c
> +++ b/drivers/net/mlx5/mlx5_flow.c
> @@ -606,7 +606,7 @@ uint32_t mlx5_flow_adjust_priority(struct
> rte_eth_dev *dev, int32_t priority, {
> struct mlx5_priv *priv = dev->data->dev_private;
> struct rte_flow *flow = dev_flow->flow;
> - const int mark = !!(flow->actions &
> + const int mark = !!(dev_flow->actions &
> (MLX5_FLOW_ACTION_FLAG |
> MLX5_FLOW_ACTION_MARK));
> const int tunnel = !!(dev_flow->layers &
> MLX5_FLOW_LAYER_TUNNEL);
> unsigned int i;
> @@ -669,7 +669,7 @@ uint32_t mlx5_flow_adjust_priority(struct
> rte_eth_dev *dev, int32_t priority, {
> struct mlx5_priv *priv = dev->data->dev_private;
> struct rte_flow *flow = dev_flow->flow;
> - const int mark = !!(flow->actions &
> + const int mark = !!(dev_flow->actions &
> (MLX5_FLOW_ACTION_FLAG |
> MLX5_FLOW_ACTION_MARK));
> const int tunnel = !!(dev_flow->layers &
> MLX5_FLOW_LAYER_TUNNEL);
> unsigned int i;
> @@ -2419,6 +2419,210 @@ uint32_t mlx5_flow_adjust_priority(struct
> rte_eth_dev *dev, int32_t priority, }
>
> /**
> + * Check if the flow should be splited due to hairpin.
> + * The reason for the split is that in current HW we can't
> + * support encap on Rx, so if a flow have encap we move it
> + * to Tx.
> + *
> + * @param dev
> + * Pointer to Ethernet device.
> + * @param[in] attr
> + * Flow rule attributes.
> + * @param[in] actions
> + * Associated actions (list terminated by the END action).
> + *
> + * @return
> + * > 0 the number of actions and the flow should be split,
> + * 0 when no split required.
> + */
> +static int
> +flow_check_hairpin_split(struct rte_eth_dev *dev,
> + const struct rte_flow_attr *attr,
> + const struct rte_flow_action actions[]) {
> + int queue_action = 0;
> + int action_n = 0;
> + int encap = 0;
> + const struct rte_flow_action_queue *queue;
> + const struct rte_flow_action_rss *rss;
> + const struct rte_flow_action_raw_encap *raw_encap;
> +
> + if (!attr->ingress)
> + return 0;
> + for (; actions->type != RTE_FLOW_ACTION_TYPE_END; actions++) {
> + switch (actions->type) {
> + case RTE_FLOW_ACTION_TYPE_QUEUE:
> + queue = actions->conf;
> + if (mlx5_rxq_get_type(dev, queue->index) !=
> + MLX5_RXQ_TYPE_HAIRPIN)
> + return 0;
> + queue_action = 1;
> + action_n++;
> + break;
> + case RTE_FLOW_ACTION_TYPE_RSS:
> + rss = actions->conf;
> + if (mlx5_rxq_get_type(dev, rss->queue[0]) !=
> + MLX5_RXQ_TYPE_HAIRPIN)
> + return 0;
> + queue_action = 1;
> + action_n++;
> + break;
> + case RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP:
> + case RTE_FLOW_ACTION_TYPE_NVGRE_ENCAP:
> + encap = 1;
> + action_n++;
> + break;
> + case RTE_FLOW_ACTION_TYPE_RAW_ENCAP:
> + raw_encap = actions->conf;
> + if (raw_encap->size >
> + (sizeof(struct rte_flow_item_eth) +
> + sizeof(struct rte_flow_item_ipv4)))
> + encap = 1;
> + action_n++;
> + break;
> + default:
> + action_n++;
> + break;
> + }
> + }
> + if (encap == 1 && queue_action)
> + return action_n;
> + return 0;
> +}
> +
> +#define MLX5_MAX_SPLIT_ACTIONS 24
> +#define MLX5_MAX_SPLIT_ITEMS 24
> +
> +/**
> + * Split the hairpin flow.
> + * Since HW can't support encap on Rx we move the encap to Tx.
> + * If the count action is after the encap then we also
> + * move the count action. in this case the count will also measure
> + * the outer bytes.
> + *
> + * @param dev
> + * Pointer to Ethernet device.
> + * @param[in] actions
> + * Associated actions (list terminated by the END action).
> + * @param[out] actions_rx
> + * Rx flow actions.
> + * @param[out] actions_tx
> + * Tx flow actions..
> + * @param[out] pattern_tx
> + * The pattern items for the Tx flow.
> + * @param[out] flow_id
> + * The flow ID connected to this flow.
> + *
> + * @return
> + * 0 on success.
> + */
> +static int
> +flow_hairpin_split(struct rte_eth_dev *dev,
> + const struct rte_flow_action actions[],
> + struct rte_flow_action actions_rx[],
> + struct rte_flow_action actions_tx[],
> + struct rte_flow_item pattern_tx[],
> + uint32_t *flow_id)
> +{
> + struct mlx5_priv *priv = dev->data->dev_private;
> + const struct rte_flow_action_raw_encap *raw_encap;
> + const struct rte_flow_action_raw_decap *raw_decap;
> + struct mlx5_rte_flow_action_set_tag *set_tag;
> + struct rte_flow_action *tag_action;
> + struct mlx5_rte_flow_item_tag *tag_item;
> + struct rte_flow_item *item;
> + char *addr;
> + struct rte_flow_error error;
> + int encap = 0;
> +
> + mlx5_flow_id_get(priv->sh->flow_id_pool, flow_id);
> + for (; actions->type != RTE_FLOW_ACTION_TYPE_END; actions++) {
> + switch (actions->type) {
> + case RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP:
> + case RTE_FLOW_ACTION_TYPE_NVGRE_ENCAP:
> + rte_memcpy(actions_tx, actions,
> + sizeof(struct rte_flow_action));
> + actions_tx++;
> + break;
> + case RTE_FLOW_ACTION_TYPE_COUNT:
> + if (encap) {
> + rte_memcpy(actions_tx, actions,
> + sizeof(struct rte_flow_action));
> + actions_tx++;
> + } else {
> + rte_memcpy(actions_rx, actions,
> + sizeof(struct rte_flow_action));
> + actions_rx++;
> + }
> + break;
> + case RTE_FLOW_ACTION_TYPE_RAW_ENCAP:
> + raw_encap = actions->conf;
> + if (raw_encap->size >
> + (sizeof(struct rte_flow_item_eth) +
> + sizeof(struct rte_flow_item_ipv4))) {
> + memcpy(actions_tx, actions,
> + sizeof(struct rte_flow_action));
> + actions_tx++;
> + encap = 1;
> + } else {
> + rte_memcpy(actions_rx, actions,
> + sizeof(struct rte_flow_action));
> + actions_rx++;
> + }
> + break;
> + case RTE_FLOW_ACTION_TYPE_RAW_DECAP:
> + raw_decap = actions->conf;
> + if (raw_decap->size <
> + (sizeof(struct rte_flow_item_eth) +
> + sizeof(struct rte_flow_item_ipv4))) {
> + memcpy(actions_tx, actions,
> + sizeof(struct rte_flow_action));
> + actions_tx++;
> + } else {
> + rte_memcpy(actions_rx, actions,
> + sizeof(struct rte_flow_action));
> + actions_rx++;
> + }
> + break;
> + default:
> + rte_memcpy(actions_rx, actions,
> + sizeof(struct rte_flow_action));
> + actions_rx++;
> + break;
> + }
> + }
> + /* Add set meta action and end action for the Rx flow. */
> + tag_action = actions_rx;
> + tag_action->type = MLX5_RTE_FLOW_ACTION_TYPE_TAG;
> + actions_rx++;
> + rte_memcpy(actions_rx, actions, sizeof(struct rte_flow_action));
> + actions_rx++;
> + set_tag = (void *)actions_rx;
> + set_tag->id = flow_get_reg_id(dev, MLX5_HAIRPIN_RX, 0, &error);
> + set_tag->data = rte_cpu_to_be_32(*flow_id);
> + tag_action->conf = set_tag;
> + /* Create Tx item list. */
> + rte_memcpy(actions_tx, actions, sizeof(struct rte_flow_action));
> + addr = (void *)&pattern_tx[2];
> + item = pattern_tx;
> + item->type = MLX5_RTE_FLOW_ITEM_TYPE_TAG;
> + tag_item = (void *)addr;
> + tag_item->data = rte_cpu_to_be_32(*flow_id);
> + tag_item->id = flow_get_reg_id(dev, MLX5_HAIRPIN_TX, 0, &error);
> + item->spec = tag_item;
> + addr += sizeof(struct mlx5_rte_flow_item_tag);
> + tag_item = (void *)addr;
> + tag_item->data = UINT32_MAX;
> + tag_item->id = UINT16_MAX;
> + item->mask = tag_item;
> + addr += sizeof(struct mlx5_rte_flow_item_tag);
> + item->last = NULL;
> + item++;
> + item->type = RTE_FLOW_ITEM_TYPE_END;
> + return 0;
> +}
> +
> +/**
> * Create a flow and add it to @p list.
> *
> * @param dev
> @@ -2446,6 +2650,7 @@ uint32_t mlx5_flow_adjust_priority(struct
> rte_eth_dev *dev, int32_t priority,
> const struct rte_flow_action actions[],
> bool external, struct rte_flow_error *error) {
> + struct mlx5_priv *priv = dev->data->dev_private;
> struct rte_flow *flow = NULL;
> struct mlx5_flow *dev_flow;
> const struct rte_flow_action_rss *rss; @@ -2453,16 +2658,44 @@
> uint32_t mlx5_flow_adjust_priority(struct rte_eth_dev *dev, int32_t priority,
> struct rte_flow_expand_rss buf;
> uint8_t buffer[2048];
> } expand_buffer;
> + union {
> + struct rte_flow_action actions[MLX5_MAX_SPLIT_ACTIONS];
> + uint8_t buffer[2048];
> + } actions_rx;
> + union {
> + struct rte_flow_action actions[MLX5_MAX_SPLIT_ACTIONS];
> + uint8_t buffer[2048];
> + } actions_hairpin_tx;
> + union {
> + struct rte_flow_item items[MLX5_MAX_SPLIT_ITEMS];
> + uint8_t buffer[2048];
> + } items_tx;
> struct rte_flow_expand_rss *buf = &expand_buffer.buf;
> + const struct rte_flow_action *p_actions_rx = actions;
> int ret;
> uint32_t i;
> uint32_t flow_size;
> + int hairpin_flow = 0;
> + uint32_t hairpin_id = 0;
> + struct rte_flow_attr attr_tx = { .priority = 0 };
>
> - ret = flow_drv_validate(dev, attr, items, actions, external, error);
> + hairpin_flow = flow_check_hairpin_split(dev, attr, actions);
> + if (hairpin_flow > 0) {
> + if (hairpin_flow > MLX5_MAX_SPLIT_ACTIONS) {
> + rte_errno = EINVAL;
> + return NULL;
> + }
> + flow_hairpin_split(dev, actions, actions_rx.actions,
> + actions_hairpin_tx.actions, items_tx.items,
> + &hairpin_id);
> + p_actions_rx = actions_rx.actions;
> + }
> + ret = flow_drv_validate(dev, attr, items, p_actions_rx, external,
> + error);
> if (ret < 0)
> - return NULL;
> + goto error_before_flow;
> flow_size = sizeof(struct rte_flow);
> - rss = flow_get_rss_action(actions);
> + rss = flow_get_rss_action(p_actions_rx);
> if (rss)
> flow_size += RTE_ALIGN_CEIL(rss->queue_num *
> sizeof(uint16_t),
> sizeof(void *));
> @@ -2471,11 +2704,13 @@ uint32_t mlx5_flow_adjust_priority(struct
> rte_eth_dev *dev, int32_t priority,
> flow = rte_calloc(__func__, 1, flow_size, 0);
> if (!flow) {
> rte_errno = ENOMEM;
> - return NULL;
> + goto error_before_flow;
> }
> flow->drv_type = flow_get_drv_type(dev, attr);
> flow->ingress = attr->ingress;
> flow->transfer = attr->transfer;
> + if (hairpin_id != 0)
> + flow->hairpin_flow_id = hairpin_id;
> assert(flow->drv_type > MLX5_FLOW_TYPE_MIN &&
> flow->drv_type < MLX5_FLOW_TYPE_MAX);
> flow->queue = (void *)(flow + 1);
> @@ -2496,7 +2731,7 @@ uint32_t mlx5_flow_adjust_priority(struct
> rte_eth_dev *dev, int32_t priority,
> }
> for (i = 0; i < buf->entries; ++i) {
> dev_flow = flow_drv_prepare(flow, attr, buf-
> >entry[i].pattern,
> - actions, error);
> + p_actions_rx, error);
> if (!dev_flow)
> goto error;
> dev_flow->flow = flow;
> @@ -2504,7 +2739,24 @@ uint32_t mlx5_flow_adjust_priority(struct
> rte_eth_dev *dev, int32_t priority,
> LIST_INSERT_HEAD(&flow->dev_flows, dev_flow, next);
> ret = flow_drv_translate(dev, dev_flow, attr,
> buf->entry[i].pattern,
> - actions, error);
> + p_actions_rx, error);
> + if (ret < 0)
> + goto error;
> + }
> + /* Create the tx flow. */
> + if (hairpin_flow) {
> + attr_tx.group = MLX5_HAIRPIN_TX_TABLE;
> + attr_tx.ingress = 0;
> + attr_tx.egress = 1;
> + dev_flow = flow_drv_prepare(flow, &attr_tx, items_tx.items,
> + actions_hairpin_tx.actions, error);
> + if (!dev_flow)
> + goto error;
> + dev_flow->flow = flow;
> + LIST_INSERT_HEAD(&flow->dev_flows, dev_flow, next);
> + ret = flow_drv_translate(dev, dev_flow, &attr_tx,
> + items_tx.items,
> + actions_hairpin_tx.actions, error);
> if (ret < 0)
> goto error;
> }
> @@ -2516,8 +2768,16 @@ uint32_t mlx5_flow_adjust_priority(struct
> rte_eth_dev *dev, int32_t priority,
> TAILQ_INSERT_TAIL(list, flow, next);
> flow_rxq_flags_set(dev, flow);
> return flow;
> +error_before_flow:
> + if (hairpin_id)
> + mlx5_flow_id_release(priv->sh->flow_id_pool,
> + hairpin_id);
> + return NULL;
> error:
> ret = rte_errno; /* Save rte_errno before cleanup. */
> + if (flow->hairpin_flow_id)
> + mlx5_flow_id_release(priv->sh->flow_id_pool,
> + flow->hairpin_flow_id);
> assert(flow);
> flow_drv_destroy(dev, flow);
> rte_free(flow);
> @@ -2607,12 +2867,17 @@ struct rte_flow * flow_list_destroy(struct
> rte_eth_dev *dev, struct mlx5_flows *list,
> struct rte_flow *flow)
> {
> + struct mlx5_priv *priv = dev->data->dev_private;
> +
> /*
> * Update RX queue flags only if port is started, otherwise it is
> * already clean.
> */
> if (dev->data->dev_started)
> flow_rxq_flags_trim(dev, flow);
> + if (flow->hairpin_flow_id)
> + mlx5_flow_id_release(priv->sh->flow_id_pool,
> + flow->hairpin_flow_id);
> flow_drv_destroy(dev, flow);
> TAILQ_REMOVE(list, flow, next);
> rte_free(flow->fdir);
> diff --git a/drivers/net/mlx5/mlx5_flow.h b/drivers/net/mlx5/mlx5_flow.h
> index bb67380..90a289e 100644
> --- a/drivers/net/mlx5/mlx5_flow.h
> +++ b/drivers/net/mlx5/mlx5_flow.h
> @@ -434,6 +434,8 @@ struct mlx5_flow {
> struct rte_flow *flow; /**< Pointer to the main flow. */
> uint64_t layers;
> /**< Bit-fields of present layers, see MLX5_FLOW_LAYER_*. */
> + uint64_t actions;
> + /**< Bit-fields of detected actions, see MLX5_FLOW_ACTION_*. */
> union {
> #ifdef HAVE_IBV_FLOW_DV_SUPPORT
> struct mlx5_flow_dv dv;
> @@ -455,12 +457,11 @@ struct rte_flow {
> uint16_t (*queue)[]; /**< Destination queues to redirect traffic to. */
> LIST_HEAD(dev_flows, mlx5_flow) dev_flows;
> /**< Device flows that are part of the flow. */
> - uint64_t actions;
> - /**< Bit-fields of detected actions, see MLX5_FLOW_ACTION_*. */
> struct mlx5_fdir *fdir; /**< Pointer to associated FDIR if any. */
> uint8_t ingress; /**< 1 if the flow is ingress. */
> uint32_t group; /**< The group index. */
> uint8_t transfer; /**< 1 if the flow is E-Switch flow. */
> + uint32_t hairpin_flow_id; /**< The flow id used for hairpin. */
> };
>
> typedef int (*mlx5_flow_validate_t)(struct rte_eth_dev *dev, @@ -504,15
> +505,6 @@ struct mlx5_flow_driver_ops { #define
> MLX5_CNT_CONTAINER_UNUSED(sh, batch, thread) (&(sh)->cmng.ccont \
> [(~((sh)->cmng.mhi[batch] >> (thread)) & 0x1) * 2 + (batch)])
>
> -/* ID generation structure. */
> -struct mlx5_flow_id_pool {
> - uint32_t *free_arr; /**< Pointer to the a array of free values. */
> - uint32_t base_index;
> - /**< The next index that can be used without any free elements. */
> - uint32_t *curr; /**< Pointer to the index to pop. */
> - uint32_t *last; /**< Pointer to the last element in the empty arrray.
> */
> -};
> -
> /* mlx5_flow.c */
>
> struct mlx5_flow_id_pool *mlx5_flow_id_pool_alloc(void); diff --git
> a/drivers/net/mlx5/mlx5_flow_dv.c b/drivers/net/mlx5/mlx5_flow_dv.c
> index 2b48680..6828bd1 100644
> --- a/drivers/net/mlx5/mlx5_flow_dv.c
> +++ b/drivers/net/mlx5/mlx5_flow_dv.c
> @@ -5763,7 +5763,7 @@ struct field_modify_info modify_tcp[] = {
> modify_action_position = actions_n++;
> }
> dev_flow->dv.actions_n = actions_n;
> - flow->actions = action_flags;
> + dev_flow->actions = action_flags;
> for (; items->type != RTE_FLOW_ITEM_TYPE_END; items++) {
> int tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL);
> int item_type = items->type;
> @@ -5985,7 +5985,7 @@ struct field_modify_info modify_tcp[] = {
> LIST_FOREACH(dev_flow, &flow->dev_flows, next) {
> dv = &dev_flow->dv;
> n = dv->actions_n;
> - if (flow->actions & MLX5_FLOW_ACTION_DROP) {
> + if (dev_flow->actions & MLX5_FLOW_ACTION_DROP) {
> if (flow->transfer) {
> dv->actions[n++] = priv->sh-
> >esw_drop_action;
> } else {
> @@ -6000,7 +6000,7 @@ struct field_modify_info modify_tcp[] = {
> }
> dv->actions[n++] = dv->hrxq->action;
> }
> - } else if (flow->actions &
> + } else if (dev_flow->actions &
> (MLX5_FLOW_ACTION_QUEUE |
> MLX5_FLOW_ACTION_RSS)) {
> struct mlx5_hrxq *hrxq;
>
> @@ -6056,7 +6056,7 @@ struct field_modify_info modify_tcp[] = {
> LIST_FOREACH(dev_flow, &flow->dev_flows, next) {
> struct mlx5_flow_dv *dv = &dev_flow->dv;
> if (dv->hrxq) {
> - if (flow->actions & MLX5_FLOW_ACTION_DROP)
> + if (dev_flow->actions &
> MLX5_FLOW_ACTION_DROP)
> mlx5_hrxq_drop_release(dev);
> else
> mlx5_hrxq_release(dev, dv->hrxq);
> @@ -6290,7 +6290,7 @@ struct field_modify_info modify_tcp[] = {
> dv->flow = NULL;
> }
> if (dv->hrxq) {
> - if (flow->actions & MLX5_FLOW_ACTION_DROP)
> + if (dev_flow->actions &
> MLX5_FLOW_ACTION_DROP)
> mlx5_hrxq_drop_release(dev);
> else
> mlx5_hrxq_release(dev, dv->hrxq);
> diff --git a/drivers/net/mlx5/mlx5_flow_verbs.c
> b/drivers/net/mlx5/mlx5_flow_verbs.c
> index 23110f2..fd27f6c 100644
> --- a/drivers/net/mlx5/mlx5_flow_verbs.c
> +++ b/drivers/net/mlx5/mlx5_flow_verbs.c
> @@ -191,7 +191,7 @@
> {
> #if defined(HAVE_IBV_DEVICE_COUNTERS_SET_V42) || \
> defined(HAVE_IBV_DEVICE_COUNTERS_SET_V45)
> - if (flow->actions & MLX5_FLOW_ACTION_COUNT) {
> + if (flow->counter->cs) {
> struct rte_flow_query_count *qc = data;
> uint64_t counters[2] = {0, 0};
> #if defined(HAVE_IBV_DEVICE_COUNTERS_SET_V42)
> @@ -1410,7 +1410,6 @@
> const struct rte_flow_action actions[],
> struct rte_flow_error *error)
> {
> - struct rte_flow *flow = dev_flow->flow;
> uint64_t item_flags = 0;
> uint64_t action_flags = 0;
> uint64_t priority = attr->priority;
> @@ -1460,7 +1459,7 @@
> "action not supported");
> }
> }
> - flow->actions = action_flags;
> + dev_flow->actions = action_flags;
> for (; items->type != RTE_FLOW_ITEM_TYPE_END; items++) {
> int tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL);
>
> @@ -1592,7 +1591,7 @@
> verbs->flow = NULL;
> }
> if (verbs->hrxq) {
> - if (flow->actions & MLX5_FLOW_ACTION_DROP)
> + if (dev_flow->actions &
> MLX5_FLOW_ACTION_DROP)
> mlx5_hrxq_drop_release(dev);
> else
> mlx5_hrxq_release(dev, verbs->hrxq); @@ -
> 1656,7 +1655,7 @@
>
> LIST_FOREACH(dev_flow, &flow->dev_flows, next) {
> verbs = &dev_flow->verbs;
> - if (flow->actions & MLX5_FLOW_ACTION_DROP) {
> + if (dev_flow->actions & MLX5_FLOW_ACTION_DROP) {
> verbs->hrxq = mlx5_hrxq_drop_new(dev);
> if (!verbs->hrxq) {
> rte_flow_error_set
> @@ -1717,7 +1716,7 @@
> LIST_FOREACH(dev_flow, &flow->dev_flows, next) {
> verbs = &dev_flow->verbs;
> if (verbs->hrxq) {
> - if (flow->actions & MLX5_FLOW_ACTION_DROP)
> + if (dev_flow->actions &
> MLX5_FLOW_ACTION_DROP)
> mlx5_hrxq_drop_release(dev);
> else
> mlx5_hrxq_release(dev, verbs->hrxq); diff --
> git a/drivers/net/mlx5/mlx5_rxq.c b/drivers/net/mlx5/mlx5_rxq.c index
> bf39112..e51a0c6 100644
> --- a/drivers/net/mlx5/mlx5_rxq.c
> +++ b/drivers/net/mlx5/mlx5_rxq.c
> @@ -2113,6 +2113,32 @@ struct mlx5_rxq_ctrl * }
>
> /**
> + * Get a Rx queue type.
> + *
> + * @param dev
> + * Pointer to Ethernet device.
> + * @param idx
> + * Rx queue index.
> + *
> + * @return
> + * The Rx queue type.
> + */
> +enum mlx5_rxq_type
> +mlx5_rxq_get_type(struct rte_eth_dev *dev, uint16_t idx) {
> + struct mlx5_priv *priv = dev->data->dev_private;
> + struct mlx5_rxq_ctrl *rxq_ctrl = NULL;
> +
> + if ((*priv->rxqs)[idx]) {
> + rxq_ctrl = container_of((*priv->rxqs)[idx],
> + struct mlx5_rxq_ctrl,
> + rxq);
> + return rxq_ctrl->type;
> + }
> + return MLX5_RXQ_TYPE_UNDEFINED;
> +}
> +
> +/**
> * Create an indirection table.
> *
> * @param dev
> diff --git a/drivers/net/mlx5/mlx5_rxtx.h b/drivers/net/mlx5/mlx5_rxtx.h
> index 8fa22e5..4707b29 100644
> --- a/drivers/net/mlx5/mlx5_rxtx.h
> +++ b/drivers/net/mlx5/mlx5_rxtx.h
> @@ -166,6 +166,7 @@ enum mlx5_rxq_obj_type { enum mlx5_rxq_type {
> MLX5_RXQ_TYPE_STANDARD, /* Standard Rx queue. */
> MLX5_RXQ_TYPE_HAIRPIN, /* Hairpin Rx queue. */
> + MLX5_RXQ_TYPE_UNDEFINED,
> };
>
> /* Verbs/DevX Rx queue elements. */
> @@ -408,6 +409,7 @@ struct mlx5_hrxq *mlx5_hrxq_get(struct rte_eth_dev
> *dev,
> const uint16_t *queues, uint32_t queues_n);
> int mlx5_hrxq_release(struct rte_eth_dev *dev, struct mlx5_hrxq *hxrq); int
> mlx5_hrxq_verify(struct rte_eth_dev *dev);
> +enum mlx5_rxq_type mlx5_rxq_get_type(struct rte_eth_dev *dev, uint16_t
> +idx);
> struct mlx5_hrxq *mlx5_hrxq_drop_new(struct rte_eth_dev *dev); void
> mlx5_hrxq_drop_release(struct rte_eth_dev *dev); uint64_t
> mlx5_get_rx_port_offloads(void);
> --
> 1.8.3.1
@@ -528,6 +528,12 @@ struct mlx5_flow_id_pool *
err = ENOMEM;
goto error;
}
+ sh->flow_id_pool = mlx5_flow_id_pool_alloc();
+ if (!sh->flow_id_pool) {
+ DRV_LOG(ERR, "can't create flow id pool");
+ err = ENOMEM;
+ goto error;
+ }
#endif /* HAVE_IBV_FLOW_DV_SUPPORT */
/*
* Once the device is added to the list of memory event
@@ -567,6 +573,8 @@ struct mlx5_flow_id_pool *
claim_zero(mlx5_glue->dealloc_pd(sh->pd));
if (sh->ctx)
claim_zero(mlx5_glue->close_device(sh->ctx));
+ if (sh->flow_id_pool)
+ mlx5_flow_id_pool_release(sh->flow_id_pool);
rte_free(sh);
assert(err > 0);
rte_errno = err;
@@ -629,6 +637,8 @@ struct mlx5_flow_id_pool *
claim_zero(mlx5_devx_cmd_destroy(sh->td));
if (sh->ctx)
claim_zero(mlx5_glue->close_device(sh->ctx));
+ if (sh->flow_id_pool)
+ mlx5_flow_id_pool_release(sh->flow_id_pool);
rte_free(sh);
exit:
pthread_mutex_unlock(&mlx5_ibv_list_mutex);
@@ -574,6 +574,15 @@ struct mlx5_devx_dbr_page {
uint64_t dbr_bitmap[MLX5_DBR_BITMAP_SIZE];
};
+/* ID generation structure. */
+struct mlx5_flow_id_pool {
+ uint32_t *free_arr; /**< Pointer to the a array of free values. */
+ uint32_t base_index;
+ /**< The next index that can be used without any free elements. */
+ uint32_t *curr; /**< Pointer to the index to pop. */
+ uint32_t *last; /**< Pointer to the last element in the empty arrray. */
+};
+
/*
* Shared Infiniband device context for Master/Representors
* which belong to same IB device with multiple IB ports.
@@ -632,6 +641,7 @@ struct mlx5_ibv_shared {
struct mlx5dv_devx_cmd_comp *devx_comp; /* DEVX async comp obj. */
struct mlx5_devx_obj *tis; /* TIS object. */
struct mlx5_devx_obj *td; /* Transport domain. */
+ struct mlx5_flow_id_pool *flow_id_pool; /* Flow ID pool. */
struct mlx5_ibv_shared_port port[]; /* per device port data array. */
};
@@ -606,7 +606,7 @@ uint32_t mlx5_flow_adjust_priority(struct rte_eth_dev *dev, int32_t priority,
{
struct mlx5_priv *priv = dev->data->dev_private;
struct rte_flow *flow = dev_flow->flow;
- const int mark = !!(flow->actions &
+ const int mark = !!(dev_flow->actions &
(MLX5_FLOW_ACTION_FLAG | MLX5_FLOW_ACTION_MARK));
const int tunnel = !!(dev_flow->layers & MLX5_FLOW_LAYER_TUNNEL);
unsigned int i;
@@ -669,7 +669,7 @@ uint32_t mlx5_flow_adjust_priority(struct rte_eth_dev *dev, int32_t priority,
{
struct mlx5_priv *priv = dev->data->dev_private;
struct rte_flow *flow = dev_flow->flow;
- const int mark = !!(flow->actions &
+ const int mark = !!(dev_flow->actions &
(MLX5_FLOW_ACTION_FLAG | MLX5_FLOW_ACTION_MARK));
const int tunnel = !!(dev_flow->layers & MLX5_FLOW_LAYER_TUNNEL);
unsigned int i;
@@ -2419,6 +2419,210 @@ uint32_t mlx5_flow_adjust_priority(struct rte_eth_dev *dev, int32_t priority,
}
/**
+ * Check if the flow should be splited due to hairpin.
+ * The reason for the split is that in current HW we can't
+ * support encap on Rx, so if a flow have encap we move it
+ * to Tx.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param[in] attr
+ * Flow rule attributes.
+ * @param[in] actions
+ * Associated actions (list terminated by the END action).
+ *
+ * @return
+ * > 0 the number of actions and the flow should be split,
+ * 0 when no split required.
+ */
+static int
+flow_check_hairpin_split(struct rte_eth_dev *dev,
+ const struct rte_flow_attr *attr,
+ const struct rte_flow_action actions[])
+{
+ int queue_action = 0;
+ int action_n = 0;
+ int encap = 0;
+ const struct rte_flow_action_queue *queue;
+ const struct rte_flow_action_rss *rss;
+ const struct rte_flow_action_raw_encap *raw_encap;
+
+ if (!attr->ingress)
+ return 0;
+ for (; actions->type != RTE_FLOW_ACTION_TYPE_END; actions++) {
+ switch (actions->type) {
+ case RTE_FLOW_ACTION_TYPE_QUEUE:
+ queue = actions->conf;
+ if (mlx5_rxq_get_type(dev, queue->index) !=
+ MLX5_RXQ_TYPE_HAIRPIN)
+ return 0;
+ queue_action = 1;
+ action_n++;
+ break;
+ case RTE_FLOW_ACTION_TYPE_RSS:
+ rss = actions->conf;
+ if (mlx5_rxq_get_type(dev, rss->queue[0]) !=
+ MLX5_RXQ_TYPE_HAIRPIN)
+ return 0;
+ queue_action = 1;
+ action_n++;
+ break;
+ case RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP:
+ case RTE_FLOW_ACTION_TYPE_NVGRE_ENCAP:
+ encap = 1;
+ action_n++;
+ break;
+ case RTE_FLOW_ACTION_TYPE_RAW_ENCAP:
+ raw_encap = actions->conf;
+ if (raw_encap->size >
+ (sizeof(struct rte_flow_item_eth) +
+ sizeof(struct rte_flow_item_ipv4)))
+ encap = 1;
+ action_n++;
+ break;
+ default:
+ action_n++;
+ break;
+ }
+ }
+ if (encap == 1 && queue_action)
+ return action_n;
+ return 0;
+}
+
+#define MLX5_MAX_SPLIT_ACTIONS 24
+#define MLX5_MAX_SPLIT_ITEMS 24
+
+/**
+ * Split the hairpin flow.
+ * Since HW can't support encap on Rx we move the encap to Tx.
+ * If the count action is after the encap then we also
+ * move the count action. in this case the count will also measure
+ * the outer bytes.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param[in] actions
+ * Associated actions (list terminated by the END action).
+ * @param[out] actions_rx
+ * Rx flow actions.
+ * @param[out] actions_tx
+ * Tx flow actions..
+ * @param[out] pattern_tx
+ * The pattern items for the Tx flow.
+ * @param[out] flow_id
+ * The flow ID connected to this flow.
+ *
+ * @return
+ * 0 on success.
+ */
+static int
+flow_hairpin_split(struct rte_eth_dev *dev,
+ const struct rte_flow_action actions[],
+ struct rte_flow_action actions_rx[],
+ struct rte_flow_action actions_tx[],
+ struct rte_flow_item pattern_tx[],
+ uint32_t *flow_id)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ const struct rte_flow_action_raw_encap *raw_encap;
+ const struct rte_flow_action_raw_decap *raw_decap;
+ struct mlx5_rte_flow_action_set_tag *set_tag;
+ struct rte_flow_action *tag_action;
+ struct mlx5_rte_flow_item_tag *tag_item;
+ struct rte_flow_item *item;
+ char *addr;
+ struct rte_flow_error error;
+ int encap = 0;
+
+ mlx5_flow_id_get(priv->sh->flow_id_pool, flow_id);
+ for (; actions->type != RTE_FLOW_ACTION_TYPE_END; actions++) {
+ switch (actions->type) {
+ case RTE_FLOW_ACTION_TYPE_VXLAN_ENCAP:
+ case RTE_FLOW_ACTION_TYPE_NVGRE_ENCAP:
+ rte_memcpy(actions_tx, actions,
+ sizeof(struct rte_flow_action));
+ actions_tx++;
+ break;
+ case RTE_FLOW_ACTION_TYPE_COUNT:
+ if (encap) {
+ rte_memcpy(actions_tx, actions,
+ sizeof(struct rte_flow_action));
+ actions_tx++;
+ } else {
+ rte_memcpy(actions_rx, actions,
+ sizeof(struct rte_flow_action));
+ actions_rx++;
+ }
+ break;
+ case RTE_FLOW_ACTION_TYPE_RAW_ENCAP:
+ raw_encap = actions->conf;
+ if (raw_encap->size >
+ (sizeof(struct rte_flow_item_eth) +
+ sizeof(struct rte_flow_item_ipv4))) {
+ memcpy(actions_tx, actions,
+ sizeof(struct rte_flow_action));
+ actions_tx++;
+ encap = 1;
+ } else {
+ rte_memcpy(actions_rx, actions,
+ sizeof(struct rte_flow_action));
+ actions_rx++;
+ }
+ break;
+ case RTE_FLOW_ACTION_TYPE_RAW_DECAP:
+ raw_decap = actions->conf;
+ if (raw_decap->size <
+ (sizeof(struct rte_flow_item_eth) +
+ sizeof(struct rte_flow_item_ipv4))) {
+ memcpy(actions_tx, actions,
+ sizeof(struct rte_flow_action));
+ actions_tx++;
+ } else {
+ rte_memcpy(actions_rx, actions,
+ sizeof(struct rte_flow_action));
+ actions_rx++;
+ }
+ break;
+ default:
+ rte_memcpy(actions_rx, actions,
+ sizeof(struct rte_flow_action));
+ actions_rx++;
+ break;
+ }
+ }
+ /* Add set meta action and end action for the Rx flow. */
+ tag_action = actions_rx;
+ tag_action->type = MLX5_RTE_FLOW_ACTION_TYPE_TAG;
+ actions_rx++;
+ rte_memcpy(actions_rx, actions, sizeof(struct rte_flow_action));
+ actions_rx++;
+ set_tag = (void *)actions_rx;
+ set_tag->id = flow_get_reg_id(dev, MLX5_HAIRPIN_RX, 0, &error);
+ set_tag->data = rte_cpu_to_be_32(*flow_id);
+ tag_action->conf = set_tag;
+ /* Create Tx item list. */
+ rte_memcpy(actions_tx, actions, sizeof(struct rte_flow_action));
+ addr = (void *)&pattern_tx[2];
+ item = pattern_tx;
+ item->type = MLX5_RTE_FLOW_ITEM_TYPE_TAG;
+ tag_item = (void *)addr;
+ tag_item->data = rte_cpu_to_be_32(*flow_id);
+ tag_item->id = flow_get_reg_id(dev, MLX5_HAIRPIN_TX, 0, &error);
+ item->spec = tag_item;
+ addr += sizeof(struct mlx5_rte_flow_item_tag);
+ tag_item = (void *)addr;
+ tag_item->data = UINT32_MAX;
+ tag_item->id = UINT16_MAX;
+ item->mask = tag_item;
+ addr += sizeof(struct mlx5_rte_flow_item_tag);
+ item->last = NULL;
+ item++;
+ item->type = RTE_FLOW_ITEM_TYPE_END;
+ return 0;
+}
+
+/**
* Create a flow and add it to @p list.
*
* @param dev
@@ -2446,6 +2650,7 @@ uint32_t mlx5_flow_adjust_priority(struct rte_eth_dev *dev, int32_t priority,
const struct rte_flow_action actions[],
bool external, struct rte_flow_error *error)
{
+ struct mlx5_priv *priv = dev->data->dev_private;
struct rte_flow *flow = NULL;
struct mlx5_flow *dev_flow;
const struct rte_flow_action_rss *rss;
@@ -2453,16 +2658,44 @@ uint32_t mlx5_flow_adjust_priority(struct rte_eth_dev *dev, int32_t priority,
struct rte_flow_expand_rss buf;
uint8_t buffer[2048];
} expand_buffer;
+ union {
+ struct rte_flow_action actions[MLX5_MAX_SPLIT_ACTIONS];
+ uint8_t buffer[2048];
+ } actions_rx;
+ union {
+ struct rte_flow_action actions[MLX5_MAX_SPLIT_ACTIONS];
+ uint8_t buffer[2048];
+ } actions_hairpin_tx;
+ union {
+ struct rte_flow_item items[MLX5_MAX_SPLIT_ITEMS];
+ uint8_t buffer[2048];
+ } items_tx;
struct rte_flow_expand_rss *buf = &expand_buffer.buf;
+ const struct rte_flow_action *p_actions_rx = actions;
int ret;
uint32_t i;
uint32_t flow_size;
+ int hairpin_flow = 0;
+ uint32_t hairpin_id = 0;
+ struct rte_flow_attr attr_tx = { .priority = 0 };
- ret = flow_drv_validate(dev, attr, items, actions, external, error);
+ hairpin_flow = flow_check_hairpin_split(dev, attr, actions);
+ if (hairpin_flow > 0) {
+ if (hairpin_flow > MLX5_MAX_SPLIT_ACTIONS) {
+ rte_errno = EINVAL;
+ return NULL;
+ }
+ flow_hairpin_split(dev, actions, actions_rx.actions,
+ actions_hairpin_tx.actions, items_tx.items,
+ &hairpin_id);
+ p_actions_rx = actions_rx.actions;
+ }
+ ret = flow_drv_validate(dev, attr, items, p_actions_rx, external,
+ error);
if (ret < 0)
- return NULL;
+ goto error_before_flow;
flow_size = sizeof(struct rte_flow);
- rss = flow_get_rss_action(actions);
+ rss = flow_get_rss_action(p_actions_rx);
if (rss)
flow_size += RTE_ALIGN_CEIL(rss->queue_num * sizeof(uint16_t),
sizeof(void *));
@@ -2471,11 +2704,13 @@ uint32_t mlx5_flow_adjust_priority(struct rte_eth_dev *dev, int32_t priority,
flow = rte_calloc(__func__, 1, flow_size, 0);
if (!flow) {
rte_errno = ENOMEM;
- return NULL;
+ goto error_before_flow;
}
flow->drv_type = flow_get_drv_type(dev, attr);
flow->ingress = attr->ingress;
flow->transfer = attr->transfer;
+ if (hairpin_id != 0)
+ flow->hairpin_flow_id = hairpin_id;
assert(flow->drv_type > MLX5_FLOW_TYPE_MIN &&
flow->drv_type < MLX5_FLOW_TYPE_MAX);
flow->queue = (void *)(flow + 1);
@@ -2496,7 +2731,7 @@ uint32_t mlx5_flow_adjust_priority(struct rte_eth_dev *dev, int32_t priority,
}
for (i = 0; i < buf->entries; ++i) {
dev_flow = flow_drv_prepare(flow, attr, buf->entry[i].pattern,
- actions, error);
+ p_actions_rx, error);
if (!dev_flow)
goto error;
dev_flow->flow = flow;
@@ -2504,7 +2739,24 @@ uint32_t mlx5_flow_adjust_priority(struct rte_eth_dev *dev, int32_t priority,
LIST_INSERT_HEAD(&flow->dev_flows, dev_flow, next);
ret = flow_drv_translate(dev, dev_flow, attr,
buf->entry[i].pattern,
- actions, error);
+ p_actions_rx, error);
+ if (ret < 0)
+ goto error;
+ }
+ /* Create the tx flow. */
+ if (hairpin_flow) {
+ attr_tx.group = MLX5_HAIRPIN_TX_TABLE;
+ attr_tx.ingress = 0;
+ attr_tx.egress = 1;
+ dev_flow = flow_drv_prepare(flow, &attr_tx, items_tx.items,
+ actions_hairpin_tx.actions, error);
+ if (!dev_flow)
+ goto error;
+ dev_flow->flow = flow;
+ LIST_INSERT_HEAD(&flow->dev_flows, dev_flow, next);
+ ret = flow_drv_translate(dev, dev_flow, &attr_tx,
+ items_tx.items,
+ actions_hairpin_tx.actions, error);
if (ret < 0)
goto error;
}
@@ -2516,8 +2768,16 @@ uint32_t mlx5_flow_adjust_priority(struct rte_eth_dev *dev, int32_t priority,
TAILQ_INSERT_TAIL(list, flow, next);
flow_rxq_flags_set(dev, flow);
return flow;
+error_before_flow:
+ if (hairpin_id)
+ mlx5_flow_id_release(priv->sh->flow_id_pool,
+ hairpin_id);
+ return NULL;
error:
ret = rte_errno; /* Save rte_errno before cleanup. */
+ if (flow->hairpin_flow_id)
+ mlx5_flow_id_release(priv->sh->flow_id_pool,
+ flow->hairpin_flow_id);
assert(flow);
flow_drv_destroy(dev, flow);
rte_free(flow);
@@ -2607,12 +2867,17 @@ struct rte_flow *
flow_list_destroy(struct rte_eth_dev *dev, struct mlx5_flows *list,
struct rte_flow *flow)
{
+ struct mlx5_priv *priv = dev->data->dev_private;
+
/*
* Update RX queue flags only if port is started, otherwise it is
* already clean.
*/
if (dev->data->dev_started)
flow_rxq_flags_trim(dev, flow);
+ if (flow->hairpin_flow_id)
+ mlx5_flow_id_release(priv->sh->flow_id_pool,
+ flow->hairpin_flow_id);
flow_drv_destroy(dev, flow);
TAILQ_REMOVE(list, flow, next);
rte_free(flow->fdir);
@@ -434,6 +434,8 @@ struct mlx5_flow {
struct rte_flow *flow; /**< Pointer to the main flow. */
uint64_t layers;
/**< Bit-fields of present layers, see MLX5_FLOW_LAYER_*. */
+ uint64_t actions;
+ /**< Bit-fields of detected actions, see MLX5_FLOW_ACTION_*. */
union {
#ifdef HAVE_IBV_FLOW_DV_SUPPORT
struct mlx5_flow_dv dv;
@@ -455,12 +457,11 @@ struct rte_flow {
uint16_t (*queue)[]; /**< Destination queues to redirect traffic to. */
LIST_HEAD(dev_flows, mlx5_flow) dev_flows;
/**< Device flows that are part of the flow. */
- uint64_t actions;
- /**< Bit-fields of detected actions, see MLX5_FLOW_ACTION_*. */
struct mlx5_fdir *fdir; /**< Pointer to associated FDIR if any. */
uint8_t ingress; /**< 1 if the flow is ingress. */
uint32_t group; /**< The group index. */
uint8_t transfer; /**< 1 if the flow is E-Switch flow. */
+ uint32_t hairpin_flow_id; /**< The flow id used for hairpin. */
};
typedef int (*mlx5_flow_validate_t)(struct rte_eth_dev *dev,
@@ -504,15 +505,6 @@ struct mlx5_flow_driver_ops {
#define MLX5_CNT_CONTAINER_UNUSED(sh, batch, thread) (&(sh)->cmng.ccont \
[(~((sh)->cmng.mhi[batch] >> (thread)) & 0x1) * 2 + (batch)])
-/* ID generation structure. */
-struct mlx5_flow_id_pool {
- uint32_t *free_arr; /**< Pointer to the a array of free values. */
- uint32_t base_index;
- /**< The next index that can be used without any free elements. */
- uint32_t *curr; /**< Pointer to the index to pop. */
- uint32_t *last; /**< Pointer to the last element in the empty arrray. */
-};
-
/* mlx5_flow.c */
struct mlx5_flow_id_pool *mlx5_flow_id_pool_alloc(void);
@@ -5763,7 +5763,7 @@ struct field_modify_info modify_tcp[] = {
modify_action_position = actions_n++;
}
dev_flow->dv.actions_n = actions_n;
- flow->actions = action_flags;
+ dev_flow->actions = action_flags;
for (; items->type != RTE_FLOW_ITEM_TYPE_END; items++) {
int tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL);
int item_type = items->type;
@@ -5985,7 +5985,7 @@ struct field_modify_info modify_tcp[] = {
LIST_FOREACH(dev_flow, &flow->dev_flows, next) {
dv = &dev_flow->dv;
n = dv->actions_n;
- if (flow->actions & MLX5_FLOW_ACTION_DROP) {
+ if (dev_flow->actions & MLX5_FLOW_ACTION_DROP) {
if (flow->transfer) {
dv->actions[n++] = priv->sh->esw_drop_action;
} else {
@@ -6000,7 +6000,7 @@ struct field_modify_info modify_tcp[] = {
}
dv->actions[n++] = dv->hrxq->action;
}
- } else if (flow->actions &
+ } else if (dev_flow->actions &
(MLX5_FLOW_ACTION_QUEUE | MLX5_FLOW_ACTION_RSS)) {
struct mlx5_hrxq *hrxq;
@@ -6056,7 +6056,7 @@ struct field_modify_info modify_tcp[] = {
LIST_FOREACH(dev_flow, &flow->dev_flows, next) {
struct mlx5_flow_dv *dv = &dev_flow->dv;
if (dv->hrxq) {
- if (flow->actions & MLX5_FLOW_ACTION_DROP)
+ if (dev_flow->actions & MLX5_FLOW_ACTION_DROP)
mlx5_hrxq_drop_release(dev);
else
mlx5_hrxq_release(dev, dv->hrxq);
@@ -6290,7 +6290,7 @@ struct field_modify_info modify_tcp[] = {
dv->flow = NULL;
}
if (dv->hrxq) {
- if (flow->actions & MLX5_FLOW_ACTION_DROP)
+ if (dev_flow->actions & MLX5_FLOW_ACTION_DROP)
mlx5_hrxq_drop_release(dev);
else
mlx5_hrxq_release(dev, dv->hrxq);
@@ -191,7 +191,7 @@
{
#if defined(HAVE_IBV_DEVICE_COUNTERS_SET_V42) || \
defined(HAVE_IBV_DEVICE_COUNTERS_SET_V45)
- if (flow->actions & MLX5_FLOW_ACTION_COUNT) {
+ if (flow->counter->cs) {
struct rte_flow_query_count *qc = data;
uint64_t counters[2] = {0, 0};
#if defined(HAVE_IBV_DEVICE_COUNTERS_SET_V42)
@@ -1410,7 +1410,6 @@
const struct rte_flow_action actions[],
struct rte_flow_error *error)
{
- struct rte_flow *flow = dev_flow->flow;
uint64_t item_flags = 0;
uint64_t action_flags = 0;
uint64_t priority = attr->priority;
@@ -1460,7 +1459,7 @@
"action not supported");
}
}
- flow->actions = action_flags;
+ dev_flow->actions = action_flags;
for (; items->type != RTE_FLOW_ITEM_TYPE_END; items++) {
int tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL);
@@ -1592,7 +1591,7 @@
verbs->flow = NULL;
}
if (verbs->hrxq) {
- if (flow->actions & MLX5_FLOW_ACTION_DROP)
+ if (dev_flow->actions & MLX5_FLOW_ACTION_DROP)
mlx5_hrxq_drop_release(dev);
else
mlx5_hrxq_release(dev, verbs->hrxq);
@@ -1656,7 +1655,7 @@
LIST_FOREACH(dev_flow, &flow->dev_flows, next) {
verbs = &dev_flow->verbs;
- if (flow->actions & MLX5_FLOW_ACTION_DROP) {
+ if (dev_flow->actions & MLX5_FLOW_ACTION_DROP) {
verbs->hrxq = mlx5_hrxq_drop_new(dev);
if (!verbs->hrxq) {
rte_flow_error_set
@@ -1717,7 +1716,7 @@
LIST_FOREACH(dev_flow, &flow->dev_flows, next) {
verbs = &dev_flow->verbs;
if (verbs->hrxq) {
- if (flow->actions & MLX5_FLOW_ACTION_DROP)
+ if (dev_flow->actions & MLX5_FLOW_ACTION_DROP)
mlx5_hrxq_drop_release(dev);
else
mlx5_hrxq_release(dev, verbs->hrxq);
@@ -2113,6 +2113,32 @@ struct mlx5_rxq_ctrl *
}
/**
+ * Get a Rx queue type.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param idx
+ * Rx queue index.
+ *
+ * @return
+ * The Rx queue type.
+ */
+enum mlx5_rxq_type
+mlx5_rxq_get_type(struct rte_eth_dev *dev, uint16_t idx)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_rxq_ctrl *rxq_ctrl = NULL;
+
+ if ((*priv->rxqs)[idx]) {
+ rxq_ctrl = container_of((*priv->rxqs)[idx],
+ struct mlx5_rxq_ctrl,
+ rxq);
+ return rxq_ctrl->type;
+ }
+ return MLX5_RXQ_TYPE_UNDEFINED;
+}
+
+/**
* Create an indirection table.
*
* @param dev
@@ -166,6 +166,7 @@ enum mlx5_rxq_obj_type {
enum mlx5_rxq_type {
MLX5_RXQ_TYPE_STANDARD, /* Standard Rx queue. */
MLX5_RXQ_TYPE_HAIRPIN, /* Hairpin Rx queue. */
+ MLX5_RXQ_TYPE_UNDEFINED,
};
/* Verbs/DevX Rx queue elements. */
@@ -408,6 +409,7 @@ struct mlx5_hrxq *mlx5_hrxq_get(struct rte_eth_dev *dev,
const uint16_t *queues, uint32_t queues_n);
int mlx5_hrxq_release(struct rte_eth_dev *dev, struct mlx5_hrxq *hxrq);
int mlx5_hrxq_verify(struct rte_eth_dev *dev);
+enum mlx5_rxq_type mlx5_rxq_get_type(struct rte_eth_dev *dev, uint16_t idx);
struct mlx5_hrxq *mlx5_hrxq_drop_new(struct rte_eth_dev *dev);
void mlx5_hrxq_drop_release(struct rte_eth_dev *dev);
uint64_t mlx5_get_rx_port_offloads(void);