X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fmlx4%2Fmlx4_flow.c;h=e3d7aa8efa77708f7603bfdd7c7b7719e82ada9e;hb=01764b20c2ffd4b5755a6da40b307a12d8185b46;hp=4c498f0bee4f9903d7fb2f4528942589f9deef28;hpb=31c629c6f7689fb19656c384b5782a2414a2710b;p=dpdk.git diff --git a/drivers/net/mlx4/mlx4_flow.c b/drivers/net/mlx4/mlx4_flow.c index 4c498f0bee..e3d7aa8efa 100644 --- a/drivers/net/mlx4/mlx4_flow.c +++ b/drivers/net/mlx4/mlx4_flow.c @@ -1,34 +1,6 @@ -/*- - * BSD LICENSE - * - * Copyright 2017 6WIND S.A. - * Copyright 2017 Mellanox - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in - * the documentation and/or other materials provided with the - * distribution. - * * Neither the name of 6WIND S.A. nor the names of its - * contributors may be used to endorse or promote products derived - * from this software without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright 2017 6WIND S.A. + * Copyright 2017 Mellanox Technologies, Ltd */ /** @@ -57,7 +29,7 @@ #include #include #include -#include +#include #include #include #include @@ -65,6 +37,7 @@ /* PMD headers. */ #include "mlx4.h" +#include "mlx4_glue.h" #include "mlx4_flow.h" #include "mlx4_rxtx.h" #include "mlx4_utils.h" @@ -103,17 +76,22 @@ struct mlx4_drop { }; /** - * Convert DPDK RSS hash fields to their Verbs equivalent. + * Convert DPDK RSS hash types to their Verbs equivalent. * - * @param rss_hf - * Hash fields in DPDK format (see struct rte_eth_rss_conf). + * This function returns the supported (default) set when @p types has + * special value (uint64_t)-1. + * + * @param priv + * Pointer to private structure. + * @param types + * Hash types in DPDK format (see struct rte_eth_rss_conf). * * @return * A valid Verbs RSS hash fields mask for mlx4 on success, (uint64_t)-1 * otherwise and rte_errno is set. */ -static uint64_t -mlx4_conv_rss_hf(uint64_t rss_hf) +uint64_t +mlx4_conv_rss_types(struct priv *priv, uint64_t types) { enum { IPV4, IPV6, TCP, UDP, }; const uint64_t in[] = { @@ -133,11 +111,9 @@ mlx4_conv_rss_hf(uint64_t rss_hf) [TCP] = (ETH_RSS_NONFRAG_IPV4_TCP | ETH_RSS_NONFRAG_IPV6_TCP | ETH_RSS_IPV6_TCP_EX), - /* - * UDP support is temporarily disabled due to an - * implementation issue in the kernel. - */ - [UDP] = 0, + [UDP] = (ETH_RSS_NONFRAG_IPV4_UDP | + ETH_RSS_NONFRAG_IPV6_UDP | + ETH_RSS_IPV6_UDP_EX), }; const uint64_t out[RTE_DIM(in)] = { [IPV4] = IBV_RX_HASH_SRC_IPV4 | IBV_RX_HASH_DST_IPV4, @@ -150,12 +126,19 @@ mlx4_conv_rss_hf(uint64_t rss_hf) unsigned int i; for (i = 0; i != RTE_DIM(in); ++i) - if (rss_hf & in[i]) { - seen |= rss_hf & in[i]; + if (types & in[i]) { + seen |= types & in[i]; conv |= out[i]; } - if (!(rss_hf & ~seen)) - return conv; + if ((conv & priv->hw_rss_sup) == conv) { + if (types == (uint64_t)-1) { + /* Include inner RSS by default if supported. */ + conv |= priv->hw_rss_sup & IBV_RX_HASH_INNER; + return conv; + } + if (!(types & ~seen)) + return conv; + } rte_errno = ENOTSUP; return (uint64_t)-1; } @@ -404,7 +387,7 @@ mlx4_flow_merge_udp(struct rte_flow *flow, struct ibv_flow_spec_tcp_udp *udp; const char *msg; - if (!mask || + if (mask && ((uint16_t)(mask->hdr.src_port + 1) > UINT16_C(1) || (uint16_t)(mask->hdr.dst_port + 1) > UINT16_C(1))) { msg = "mlx4 does not support matching partial UDP fields"; @@ -464,7 +447,7 @@ mlx4_flow_merge_tcp(struct rte_flow *flow, struct ibv_flow_spec_tcp_udp *tcp; const char *msg; - if (!mask || + if (mask && ((uint16_t)(mask->hdr.src_port + 1) > UINT16_C(1) || (uint16_t)(mask->hdr.dst_port + 1) > UINT16_C(1))) { msg = "mlx4 does not support matching partial TCP fields"; @@ -654,6 +637,7 @@ mlx4_flow_prepare(struct priv *priv, struct rte_flow temp = { .ibv_attr_size = sizeof(*temp.ibv_attr) }; struct rte_flow *flow = &temp; const char *msg = NULL; + int overlap; if (attr->group) return rte_flow_error_set @@ -668,11 +652,16 @@ mlx4_flow_prepare(struct priv *priv, return rte_flow_error_set (error, ENOTSUP, RTE_FLOW_ERROR_TYPE_ATTR_EGRESS, NULL, "egress is not supported"); + if (attr->transfer) + return rte_flow_error_set + (error, ENOTSUP, RTE_FLOW_ERROR_TYPE_ATTR_TRANSFER, + NULL, "transfer is not supported"); if (!attr->ingress) return rte_flow_error_set (error, ENOTSUP, RTE_FLOW_ERROR_TYPE_ATTR_INGRESS, NULL, "only ingress is supported"); fill: + overlap = 0; proc = mlx4_flow_proc_item_list; /* Go over pattern. */ for (item = pattern; item->type; ++item) { @@ -719,14 +708,24 @@ fill: } /* Go over actions list. */ for (action = actions; action->type; ++action) { + /* This one may appear anywhere multiple times. */ + if (action->type == RTE_FLOW_ACTION_TYPE_VOID) + continue; + /* Fate-deciding actions may appear exactly once. */ + if (overlap) { + msg = "cannot combine several fate-deciding actions," + " choose between DROP, QUEUE or RSS"; + goto exit_action_not_supported; + } + overlap = 1; switch (action->type) { const struct rte_flow_action_queue *queue; const struct rte_flow_action_rss *rss; - const struct rte_eth_rss_conf *rss_conf; + const uint8_t *rss_key; + uint32_t rss_key_len; + uint64_t fields; unsigned int i; - case RTE_FLOW_ACTION_TYPE_VOID: - continue; case RTE_FLOW_ACTION_TYPE_DROP: flow->drop = 1; break; @@ -734,6 +733,11 @@ fill: if (flow->rss) break; queue = action->conf; + if (queue->index >= priv->dev->data->nb_rx_queues) { + msg = "queue target index beyond number of" + " configured Rx queues"; + goto exit_action_not_supported; + } flow->rss = mlx4_rss_get (priv, 0, mlx4_rss_hash_key_default, 1, &queue->index); @@ -748,47 +752,68 @@ fill: break; rss = action->conf; /* Default RSS configuration if none is provided. */ - rss_conf = - rss->rss_conf ? - rss->rss_conf : - &(struct rte_eth_rss_conf){ - .rss_key = mlx4_rss_hash_key_default, - .rss_key_len = MLX4_RSS_HASH_KEY_SIZE, - .rss_hf = (ETH_RSS_IPV4 | - ETH_RSS_NONFRAG_IPV4_TCP | - ETH_RSS_IPV6 | - ETH_RSS_NONFRAG_IPV6_TCP), - }; + if (rss->key_len) { + rss_key = rss->key; + rss_key_len = rss->key_len; + } else { + rss_key = mlx4_rss_hash_key_default; + rss_key_len = MLX4_RSS_HASH_KEY_SIZE; + } /* Sanity checks. */ - if (!rte_is_power_of_2(rss->num)) { + for (i = 0; i < rss->queue_num; ++i) + if (rss->queue[i] >= + priv->dev->data->nb_rx_queues) + break; + if (i != rss->queue_num) { + msg = "queue index target beyond number of" + " configured Rx queues"; + goto exit_action_not_supported; + } + if (!rte_is_power_of_2(rss->queue_num)) { msg = "for RSS, mlx4 requires the number of" " queues to be a power of two"; goto exit_action_not_supported; } - if (rss_conf->rss_key_len != - sizeof(flow->rss->key)) { + if (rss_key_len != sizeof(flow->rss->key)) { msg = "mlx4 supports exactly one RSS hash key" " length: " MLX4_STR_EXPAND(MLX4_RSS_HASH_KEY_SIZE); goto exit_action_not_supported; } - for (i = 1; i < rss->num; ++i) + for (i = 1; i < rss->queue_num; ++i) if (rss->queue[i] - rss->queue[i - 1] != 1) break; - if (i != rss->num) { + if (i != rss->queue_num) { msg = "mlx4 requires RSS contexts to use" " consecutive queue indices only"; goto exit_action_not_supported; } - if (rss->queue[0] % rss->num) { + if (rss->queue[0] % rss->queue_num) { msg = "mlx4 requires the first queue of a RSS" " context to be aligned on a multiple" " of the context size"; goto exit_action_not_supported; } + if (rss->func && + rss->func != RTE_ETH_HASH_FUNCTION_TOEPLITZ) { + msg = "the only supported RSS hash function" + " is Toeplitz"; + goto exit_action_not_supported; + } + if (rss->level) { + msg = "a nonzero RSS encapsulation level is" + " not supported"; + goto exit_action_not_supported; + } + rte_errno = 0; + fields = mlx4_conv_rss_types(priv, rss->types); + if (fields == (uint64_t)-1 && rte_errno) { + msg = "unsupported RSS hash type requested"; + goto exit_action_not_supported; + } flow->rss = mlx4_rss_get - (priv, mlx4_conv_rss_hf(rss_conf->rss_hf), - rss_conf->rss_key, rss->num, rss->queue); + (priv, fields, rss_key, rss->queue_num, + rss->queue); if (!flow->rss) { msg = "either invalid parameters or not enough" " resources for additional multi-queue" @@ -800,10 +825,9 @@ fill: goto exit_action_not_supported; } } - if (!flow->rss && !flow->drop) - return rte_flow_error_set - (error, ENOTSUP, RTE_FLOW_ERROR_TYPE_UNSPECIFIED, - NULL, "no valid action"); + /* When fate is unknown, drop traffic. */ + if (!overlap) + flow->drop = 1; /* Validation ends here. */ if (!addr) { if (flow->rss) @@ -825,11 +849,14 @@ fill: }, }; - if (!mlx4_zmallocv(__func__, vec, RTE_DIM(vec))) + if (!mlx4_zmallocv(__func__, vec, RTE_DIM(vec))) { + if (temp.rss) + mlx4_rss_put(temp.rss); return rte_flow_error_set (error, -rte_errno, RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL, "flow rule handle allocation failure"); + } /* Most fields will be updated by second pass. */ *flow = (struct rte_flow){ .ibv_attr = temp.ibv_attr, @@ -900,24 +927,25 @@ mlx4_drop_get(struct priv *priv) .priv = priv, .refcnt = 1, }; - drop->cq = ibv_create_cq(priv->ctx, 1, NULL, NULL, 0); + drop->cq = mlx4_glue->create_cq(priv->ctx, 1, NULL, NULL, 0); if (!drop->cq) goto error; - drop->qp = ibv_create_qp(priv->pd, - &(struct ibv_qp_init_attr){ - .send_cq = drop->cq, - .recv_cq = drop->cq, - .qp_type = IBV_QPT_RAW_PACKET, - }); + drop->qp = mlx4_glue->create_qp + (priv->pd, + &(struct ibv_qp_init_attr){ + .send_cq = drop->cq, + .recv_cq = drop->cq, + .qp_type = IBV_QPT_RAW_PACKET, + }); if (!drop->qp) goto error; priv->drop = drop; return drop; error: if (drop->qp) - claim_zero(ibv_destroy_qp(drop->qp)); + claim_zero(mlx4_glue->destroy_qp(drop->qp)); if (drop->cq) - claim_zero(ibv_destroy_cq(drop->cq)); + claim_zero(mlx4_glue->destroy_cq(drop->cq)); if (drop) rte_free(drop); rte_errno = ENOMEM; @@ -937,8 +965,8 @@ mlx4_drop_put(struct mlx4_drop *drop) if (--drop->refcnt) return; drop->priv->drop = NULL; - claim_zero(ibv_destroy_qp(drop->qp)); - claim_zero(ibv_destroy_cq(drop->cq)); + claim_zero(mlx4_glue->destroy_qp(drop->qp)); + claim_zero(mlx4_glue->destroy_cq(drop->cq)); rte_free(drop); } @@ -970,7 +998,7 @@ mlx4_flow_toggle(struct priv *priv, if (!enable) { if (!flow->ibv_flow) return 0; - claim_zero(ibv_destroy_flow(flow->ibv_flow)); + claim_zero(mlx4_glue->destroy_flow(flow->ibv_flow)); flow->ibv_flow = NULL; if (flow->drop) mlx4_drop_put(priv->drop); @@ -983,7 +1011,7 @@ mlx4_flow_toggle(struct priv *priv, !priv->isolated && flow->ibv_attr->priority == MLX4_FLOW_PRIORITY_LAST) { if (flow->ibv_flow) { - claim_zero(ibv_destroy_flow(flow->ibv_flow)); + claim_zero(mlx4_glue->destroy_flow(flow->ibv_flow)); flow->ibv_flow = NULL; if (flow->drop) mlx4_drop_put(priv->drop); @@ -1013,7 +1041,7 @@ mlx4_flow_toggle(struct priv *priv, if (missing ^ !flow->drop) return 0; /* Verbs flow needs updating. */ - claim_zero(ibv_destroy_flow(flow->ibv_flow)); + claim_zero(mlx4_glue->destroy_flow(flow->ibv_flow)); flow->ibv_flow = NULL; if (flow->drop) mlx4_drop_put(priv->drop); @@ -1034,6 +1062,8 @@ mlx4_flow_toggle(struct priv *priv, flow->drop = missing; } if (flow->drop) { + if (flow->ibv_flow) + return 0; mlx4_drop_get(priv); if (!priv->drop) { err = rte_errno; @@ -1045,7 +1075,7 @@ mlx4_flow_toggle(struct priv *priv, assert(qp); if (flow->ibv_flow) return 0; - flow->ibv_flow = ibv_create_flow(qp, flow->ibv_attr); + flow->ibv_flow = mlx4_glue->create_flow(qp, flow->ibv_attr); if (flow->ibv_flow) return 0; if (flow->drop) @@ -1201,16 +1231,19 @@ mlx4_flow_internal_next_vlan(struct priv *priv, uint16_t vlan) * * Various flow rules are created depending on the mode the device is in: * - * 1. Promiscuous: port MAC + catch-all (VLAN filtering is ignored). - * 2. All multicast: port MAC/VLAN + catch-all multicast. - * 3. Otherwise: port MAC/VLAN + broadcast MAC/VLAN. + * 1. Promiscuous: + * port MAC + broadcast + catch-all (VLAN filtering is ignored). + * 2. All multicast: + * port MAC/VLAN + broadcast + catch-all multicast. + * 3. Otherwise: + * port MAC/VLAN + broadcast MAC/VLAN. * * About MAC flow rules: * * - MAC flow rules are generated from @p dev->data->mac_addrs * (@p priv->mac array). * - An additional flow rule for Ethernet broadcasts is also generated. - * - All these are per-VLAN if @p dev->data->dev_conf.rxmode.hw_vlan_filter + * - All these are per-VLAN if @p DEV_RX_OFFLOAD_VLAN_FILTER * is enabled and VLAN filters are configured. * * @param priv @@ -1256,12 +1289,27 @@ mlx4_flow_internal(struct priv *priv, struct rte_flow_error *error) .type = RTE_FLOW_ITEM_TYPE_END, }, }; + /* + * Round number of queues down to their previous power of 2 to + * comply with RSS context limitations. Extra queues silently do not + * get RSS by default. + */ + uint32_t queues = + rte_align32pow2(priv->dev->data->nb_rx_queues + 1) >> 1; + uint16_t queue[queues]; + struct rte_flow_action_rss action_rss = { + .func = RTE_ETH_HASH_FUNCTION_DEFAULT, + .level = 0, + .types = -1, + .key_len = MLX4_RSS_HASH_KEY_SIZE, + .queue_num = queues, + .key = mlx4_rss_hash_key_default, + .queue = queue, + }; struct rte_flow_action actions[] = { { - .type = RTE_FLOW_ACTION_TYPE_QUEUE, - .conf = &(struct rte_flow_action_queue){ - .index = 0, - }, + .type = RTE_FLOW_ACTION_TYPE_RSS, + .conf = &action_rss, }, { .type = RTE_FLOW_ACTION_TYPE_END, @@ -1269,18 +1317,22 @@ mlx4_flow_internal(struct priv *priv, struct rte_flow_error *error) }; struct ether_addr *rule_mac = ð_spec.dst; rte_be16_t *rule_vlan = - priv->dev->data->dev_conf.rxmode.hw_vlan_filter && + (priv->dev->data->dev_conf.rxmode.offloads & + DEV_RX_OFFLOAD_VLAN_FILTER) && !priv->dev->data->promiscuous ? &vlan_spec.tci : NULL; - int broadcast = - !priv->dev->data->promiscuous && - !priv->dev->data->all_multicast; uint16_t vlan = 0; struct rte_flow *flow; unsigned int i; int err = 0; + /* Nothing to be done if there are no Rx queues. */ + if (!queues) + goto error; + /* Prepare default RSS configuration. */ + for (i = 0; i != queues; ++i) + queue[i] = i; /* * Set up VLAN item if filtering is enabled and at least one VLAN * filter is configured. @@ -1299,7 +1351,7 @@ next_vlan: rule_vlan = NULL; } } - for (i = 0; i != RTE_DIM(priv->mac) + broadcast; ++i) { + for (i = 0; i != RTE_DIM(priv->mac) + 1; ++i) { const struct ether_addr *mac; /* Broadcasts are handled by an extra iteration. */ @@ -1323,6 +1375,7 @@ next_vlan: assert(flow->ibv_attr->type == IBV_FLOW_ATTR_NORMAL); assert(flow->ibv_attr->num_of_specs == 1); assert(eth->type == IBV_FLOW_SPEC_ETH); + assert(flow->rss); if (rule_vlan && (eth->val.vlan_tag != *rule_vlan || eth->mask.vlan_tag != RTE_BE16(0x0fff))) @@ -1335,8 +1388,13 @@ next_vlan: eth->val.src_mac[j] != UINT8_C(0x00) || eth->mask.src_mac[j] != UINT8_C(0x00)) break; - if (j == sizeof(mac->addr_bytes)) - break; + if (j != sizeof(mac->addr_bytes)) + continue; + if (flow->rss->queues != queues || + memcmp(flow->rss->queue_id, action_rss.queue, + queues * sizeof(flow->rss->queue_id[0]))) + continue; + break; } if (!flow || !flow->internal) { /* Not found, create a new flow rule. */ @@ -1357,7 +1415,7 @@ next_vlan: goto next_vlan; } /* Take care of promiscuous and all multicast flow rules. */ - if (!broadcast) { + if (priv->dev->data->promiscuous || priv->dev->data->all_multicast) { for (flow = LIST_FIRST(&priv->flows); flow && flow->internal; flow = LIST_NEXT(flow, next)) { @@ -1370,6 +1428,13 @@ next_vlan: break; } } + if (flow && flow->internal) { + assert(flow->rss); + if (flow->rss->queues != queues || + memcmp(flow->rss->queue_id, action_rss.queue, + queues * sizeof(flow->rss->queue_id[0]))) + flow = NULL; + } if (!flow || !flow->internal) { /* Not found, create a new flow rule. */ if (priv->dev->data->promiscuous) { @@ -1444,9 +1509,7 @@ mlx4_flow_sync(struct priv *priv, struct rte_flow_error *error) return ret; } /* Toggle the remaining flow rules . */ - for (flow = LIST_FIRST(&priv->flows); - flow; - flow = LIST_NEXT(flow, next)) { + LIST_FOREACH(flow, &priv->flows, next) { ret = mlx4_flow_toggle(priv, flow, priv->started, error); if (ret) return ret;