From patchwork Mon Sep 24 08:28:19 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Rahul Lakkireddy X-Patchwork-Id: 45194 X-Patchwork-Delegate: ferruh.yigit@amd.com Return-Path: X-Original-To: patchwork@dpdk.org Delivered-To: patchwork@dpdk.org Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id C88704F94; Mon, 24 Sep 2018 10:28:54 +0200 (CEST) Received: from stargate.chelsio.com (stargate.chelsio.com [12.32.117.8]) by dpdk.org (Postfix) with ESMTP id 5F46D4CC5 for ; Mon, 24 Sep 2018 10:28:51 +0200 (CEST) Received: from localhost (scalar.blr.asicdesigners.com [10.193.185.94]) by stargate.chelsio.com (8.13.8/8.13.8) with ESMTP id w8O8SmFG027417; Mon, 24 Sep 2018 01:28:48 -0700 From: Rahul Lakkireddy To: dev@dpdk.org Cc: indranil@chelsio.com, nirranjan@chelsio.com Date: Mon, 24 Sep 2018 13:58:19 +0530 Message-Id: <8e2942b14f0cb2f2f24f3582b2b51173129501cf.1537776502.git.rahul.lakkireddy@chelsio.com> X-Mailer: git-send-email 2.5.3 In-Reply-To: References: In-Reply-To: References: Subject: [dpdk-dev] [PATCH 3/3] net/cxgbe: add flow actions to modify IP and TCP/UDP port address X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" Query firmware for the new filter work request to offload flows with actions to modify IP and TCP/UDP port addresses. When available, translate IP and TCP/UDP port address modify actions to internal hardware specification and offload the flow to hardware. Original work by Shagun Agrawal Signed-off-by: Rahul Lakkireddy --- Changes since RFC v2: - Re-based to tip. - Updated all instances of fw_filter_wr to new fw_filter2_wr and removed fw_filter_wr. - Ensure correct ULP type is set when offloading NAT actions. - Returning appropriate RTE_FLOW_ERROR_TYPE_ACTION error if a corresponding valid flow pattern item for the header rewrite action is not found. - Updated release notes. doc/guides/rel_notes/release_18_11.rst | 4 +- drivers/net/cxgbe/base/common.h | 1 + drivers/net/cxgbe/base/t4_msg.h | 1 + drivers/net/cxgbe/base/t4fw_interface.h | 23 ++- drivers/net/cxgbe/cxgbe_filter.c | 37 +++-- drivers/net/cxgbe/cxgbe_filter.h | 23 +++ drivers/net/cxgbe/cxgbe_flow.c | 178 +++++++++++++++++++++++- drivers/net/cxgbe/cxgbe_main.c | 10 ++ 8 files changed, 265 insertions(+), 12 deletions(-) diff --git a/doc/guides/rel_notes/release_18_11.rst b/doc/guides/rel_notes/release_18_11.rst index 84b0a6a4b..04d5d26a4 100644 --- a/doc/guides/rel_notes/release_18_11.rst +++ b/doc/guides/rel_notes/release_18_11.rst @@ -59,7 +59,9 @@ New Features Flow API support has been enhanced for CXGBE Poll Mode Driver to offload: * Match items: destination MAC address. - * Action items: push/pop/rewrite vlan header. + * Action items: push/pop/rewrite vlan header, rewrite IP addresses in + outermost IPv4/IPv6 header, rewrite port numbers in outermost TCP/UDP + header. * **Added support for SR-IOV in netvsc PMD.** diff --git a/drivers/net/cxgbe/base/common.h b/drivers/net/cxgbe/base/common.h index d9f74d995..fd2006682 100644 --- a/drivers/net/cxgbe/base/common.h +++ b/drivers/net/cxgbe/base/common.h @@ -271,6 +271,7 @@ struct adapter_params { bool ulptx_memwrite_dsgl; /* use of T5 DSGL allowed */ u8 fw_caps_support; /* 32-bit Port Capabilities */ + u8 filter2_wr_support; /* FW support for FILTER2_WR */ }; /* Firmware Port Capabilities types. diff --git a/drivers/net/cxgbe/base/t4_msg.h b/drivers/net/cxgbe/base/t4_msg.h index 2128da64f..6494f1827 100644 --- a/drivers/net/cxgbe/base/t4_msg.h +++ b/drivers/net/cxgbe/base/t4_msg.h @@ -32,6 +32,7 @@ enum CPL_error { enum { ULP_MODE_NONE = 0, + ULP_MODE_TCPDDP = 5, }; enum { diff --git a/drivers/net/cxgbe/base/t4fw_interface.h b/drivers/net/cxgbe/base/t4fw_interface.h index e2d2ee897..b4c95c588 100644 --- a/drivers/net/cxgbe/base/t4fw_interface.h +++ b/drivers/net/cxgbe/base/t4fw_interface.h @@ -61,6 +61,7 @@ enum fw_wr_opcodes { FW_ETH_TX_PKTS_WR = 0x09, FW_ETH_TX_PKT_VM_WR = 0x11, FW_ETH_TX_PKTS_VM_WR = 0x12, + FW_FILTER2_WR = 0x77, FW_ETH_TX_PKTS2_WR = 0x78, }; @@ -165,7 +166,7 @@ enum fw_filter_wr_cookie { FW_FILTER_WR_EINVAL, }; -struct fw_filter_wr { +struct fw_filter2_wr { __be32 op_pkd; __be32 len16_pkd; __be64 r3; @@ -195,6 +196,19 @@ struct fw_filter_wr { __be16 fpm; __be16 r7; __u8 sma[6]; + __be16 r8; + __u8 filter_type_swapmac; + __u8 natmode_to_ulp_type; + __be16 newlport; + __be16 newfport; + __u8 newlip[16]; + __u8 newfip[16]; + __be32 natseqcheck; + __be32 r9; + __be64 r10; + __be64 r11; + __be64 r12; + __be64 r13; }; #define S_FW_FILTER_WR_TID 12 @@ -300,6 +314,12 @@ struct fw_filter_wr { #define S_FW_FILTER_WR_MATCHTYPEM 0 #define V_FW_FILTER_WR_MATCHTYPEM(x) ((x) << S_FW_FILTER_WR_MATCHTYPEM) +#define S_FW_FILTER2_WR_NATMODE 5 +#define V_FW_FILTER2_WR_NATMODE(x) ((x) << S_FW_FILTER2_WR_NATMODE) + +#define S_FW_FILTER2_WR_ULP_TYPE 0 +#define V_FW_FILTER2_WR_ULP_TYPE(x) ((x) << S_FW_FILTER2_WR_ULP_TYPE) + /****************************************************************************** * C O M M A N D s *********************/ @@ -655,6 +675,7 @@ enum fw_params_param_dev { FW_PARAMS_PARAM_DEV_FWREV = 0x0B, /* fw version */ FW_PARAMS_PARAM_DEV_TPREV = 0x0C, /* tp version */ FW_PARAMS_PARAM_DEV_ULPTX_MEMWRITE_DSGL = 0x17, + FW_PARAMS_PARAM_DEV_FILTER2_WR = 0x1D, }; /* diff --git a/drivers/net/cxgbe/cxgbe_filter.c b/drivers/net/cxgbe/cxgbe_filter.c index dcb1dd03e..b876abf43 100644 --- a/drivers/net/cxgbe/cxgbe_filter.c +++ b/drivers/net/cxgbe/cxgbe_filter.c @@ -89,6 +89,9 @@ int validate_filter(struct adapter *adapter, struct ch_filter_specification *fs) if (fs->val.iport >= adapter->params.nports) return -ERANGE; + if (!fs->cap && fs->nat_mode && !adapter->params.filter2_wr_support) + return -EOPNOTSUPP; + return 0; } @@ -627,6 +630,7 @@ void clear_filter(struct filter_entry *f) /** * t4_mk_filtdelwr - create a delete filter WR + * @adap: adapter context * @ftid: the filter ID * @wr: the filter work request to populate * @qid: ingress queue to receive the delete notification @@ -634,10 +638,14 @@ void clear_filter(struct filter_entry *f) * Creates a filter work request to delete the supplied filter. If @qid is * negative the delete notification is suppressed. */ -static void t4_mk_filtdelwr(unsigned int ftid, struct fw_filter_wr *wr, int qid) +static void t4_mk_filtdelwr(struct adapter *adap, unsigned int ftid, + struct fw_filter2_wr *wr, int qid) { memset(wr, 0, sizeof(*wr)); - wr->op_pkd = cpu_to_be32(V_FW_WR_OP(FW_FILTER_WR)); + if (adap->params.filter2_wr_support) + wr->op_pkd = cpu_to_be32(V_FW_WR_OP(FW_FILTER2_WR)); + else + wr->op_pkd = cpu_to_be32(V_FW_WR_OP(FW_FILTER_WR)); wr->len16_pkd = cpu_to_be32(V_FW_WR_LEN16(sizeof(*wr) / 16)); wr->tid_to_iq = cpu_to_be32(V_FW_FILTER_WR_TID(ftid) | V_FW_FILTER_WR_NOREPLY(qid < 0)); @@ -655,7 +663,7 @@ static int del_filter_wr(struct rte_eth_dev *dev, unsigned int fidx) struct adapter *adapter = ethdev2adap(dev); struct filter_entry *f = &adapter->tids.ftid_tab[fidx]; struct rte_mbuf *mbuf; - struct fw_filter_wr *fwr; + struct fw_filter2_wr *fwr; struct sge_ctrl_txq *ctrlq; unsigned int port_id = ethdev2pinfo(dev)->port_id; @@ -667,8 +675,8 @@ static int del_filter_wr(struct rte_eth_dev *dev, unsigned int fidx) mbuf->data_len = sizeof(*fwr); mbuf->pkt_len = mbuf->data_len; - fwr = rte_pktmbuf_mtod(mbuf, struct fw_filter_wr *); - t4_mk_filtdelwr(f->tid, fwr, adapter->sge.fw_evtq.abs_id); + fwr = rte_pktmbuf_mtod(mbuf, struct fw_filter2_wr *); + t4_mk_filtdelwr(adapter, f->tid, fwr, adapter->sge.fw_evtq.abs_id); /* * Mark the filter as "pending" and ship off the Filter Work Request. @@ -684,7 +692,7 @@ int set_filter_wr(struct rte_eth_dev *dev, unsigned int fidx) struct adapter *adapter = ethdev2adap(dev); struct filter_entry *f = &adapter->tids.ftid_tab[fidx]; struct rte_mbuf *mbuf; - struct fw_filter_wr *fwr; + struct fw_filter2_wr *fwr; struct sge_ctrl_txq *ctrlq; unsigned int port_id = ethdev2pinfo(dev)->port_id; int ret; @@ -712,13 +720,16 @@ int set_filter_wr(struct rte_eth_dev *dev, unsigned int fidx) mbuf->data_len = sizeof(*fwr); mbuf->pkt_len = mbuf->data_len; - fwr = rte_pktmbuf_mtod(mbuf, struct fw_filter_wr *); + fwr = rte_pktmbuf_mtod(mbuf, struct fw_filter2_wr *); memset(fwr, 0, sizeof(*fwr)); /* * Construct the work request to set the filter. */ - fwr->op_pkd = cpu_to_be32(V_FW_WR_OP(FW_FILTER_WR)); + if (adapter->params.filter2_wr_support) + fwr->op_pkd = cpu_to_be32(V_FW_WR_OP(FW_FILTER2_WR)); + else + fwr->op_pkd = cpu_to_be32(V_FW_WR_OP(FW_FILTER_WR)); fwr->len16_pkd = cpu_to_be32(V_FW_WR_LEN16(sizeof(*fwr) / 16)); fwr->tid_to_iq = cpu_to_be32(V_FW_FILTER_WR_TID(f->tid) | @@ -762,6 +773,16 @@ int set_filter_wr(struct rte_eth_dev *dev, unsigned int fidx) fwr->fp = cpu_to_be16(f->fs.val.fport); fwr->fpm = cpu_to_be16(f->fs.mask.fport); + if (adapter->params.filter2_wr_support && f->fs.nat_mode) { + fwr->natmode_to_ulp_type = + V_FW_FILTER2_WR_ULP_TYPE(ULP_MODE_TCPDDP) | + V_FW_FILTER2_WR_NATMODE(f->fs.nat_mode); + memcpy(fwr->newlip, f->fs.nat_lip, sizeof(fwr->newlip)); + memcpy(fwr->newfip, f->fs.nat_fip, sizeof(fwr->newfip)); + fwr->newlport = cpu_to_be16(f->fs.nat_lport); + fwr->newfport = cpu_to_be16(f->fs.nat_fport); + } + /* * Mark the filter as "pending" and ship off the Filter Work Request. * When we get the Work Request Reply we'll clear the pending status. diff --git a/drivers/net/cxgbe/cxgbe_filter.h b/drivers/net/cxgbe/cxgbe_filter.h index 83d647de6..950fa0bca 100644 --- a/drivers/net/cxgbe/cxgbe_filter.h +++ b/drivers/net/cxgbe/cxgbe_filter.h @@ -104,6 +104,18 @@ struct ch_filter_specification { uint8_t dmac[ETHER_ADDR_LEN]; /* new destination MAC address */ uint16_t vlan; /* VLAN Tag to insert */ + /* + * Switch proxy/rewrite fields. An ingress packet which matches a + * filter with "switch" set will be looped back out as an egress + * packet -- potentially with some header rewriting. + */ + uint32_t nat_mode:3; /* specify NAT operation mode */ + + uint8_t nat_lip[16]; /* local IP to use after NAT'ing */ + uint8_t nat_fip[16]; /* foreign IP to use after NAT'ing */ + uint16_t nat_lport; /* local port number to use after NAT'ing */ + uint16_t nat_fport; /* foreign port number to use after NAT'ing */ + /* Filter rule value/mask pairs. */ struct ch_filter_tuple val; struct ch_filter_tuple mask; @@ -121,6 +133,17 @@ enum { VLAN_REWRITE }; +enum { + NAT_MODE_NONE = 0, /* No NAT performed */ + NAT_MODE_DIP, /* NAT on Dst IP */ + NAT_MODE_DIP_DP, /* NAT on Dst IP, Dst Port */ + NAT_MODE_DIP_DP_SIP, /* NAT on Dst IP, Dst Port and Src IP */ + NAT_MODE_DIP_DP_SP, /* NAT on Dst IP, Dst Port and Src Port */ + NAT_MODE_SIP_SP, /* NAT on Src IP and Src Port */ + NAT_MODE_DIP_SIP_SP, /* NAT on Dst IP, Src IP and Src Port */ + NAT_MODE_ALL /* NAT on entire 4-tuple */ +}; + enum filter_type { FILTER_TYPE_IPV4 = 0, FILTER_TYPE_IPV6, diff --git a/drivers/net/cxgbe/cxgbe_flow.c b/drivers/net/cxgbe/cxgbe_flow.c index bee3bd640..52cb3bdf4 100644 --- a/drivers/net/cxgbe/cxgbe_flow.c +++ b/drivers/net/cxgbe/cxgbe_flow.c @@ -368,14 +368,77 @@ static int cxgbe_get_fidx(struct rte_flow *flow, unsigned int *fidx) return 0; } +static int +cxgbe_get_flow_item_index(const struct rte_flow_item items[], u32 type) +{ + const struct rte_flow_item *i; + int j, index = -ENOENT; + + for (i = items, j = 0; i->type != RTE_FLOW_ITEM_TYPE_END; i++, j++) { + if (i->type == type) { + index = j; + break; + } + } + + return index; +} + +static int +ch_rte_parse_nat(uint8_t nmode, struct ch_filter_specification *fs) +{ + /* nmode: + * BIT_0 = [src_ip], BIT_1 = [dst_ip] + * BIT_2 = [src_port], BIT_3 = [dst_port] + * + * Only below cases are supported as per our spec. + */ + switch (nmode) { + case 0: /* 0000b */ + fs->nat_mode = NAT_MODE_NONE; + break; + case 2: /* 0010b */ + fs->nat_mode = NAT_MODE_DIP; + break; + case 5: /* 0101b */ + fs->nat_mode = NAT_MODE_SIP_SP; + break; + case 7: /* 0111b */ + fs->nat_mode = NAT_MODE_DIP_SIP_SP; + break; + case 10: /* 1010b */ + fs->nat_mode = NAT_MODE_DIP_DP; + break; + case 11: /* 1011b */ + fs->nat_mode = NAT_MODE_DIP_DP_SIP; + break; + case 14: /* 1110b */ + fs->nat_mode = NAT_MODE_DIP_DP_SP; + break; + case 15: /* 1111b */ + fs->nat_mode = NAT_MODE_ALL; + break; + default: + return -EINVAL; + } + + return 0; +} + static int ch_rte_parse_atype_switch(const struct rte_flow_action *a, + const struct rte_flow_item items[], + uint8_t *nmode, struct ch_filter_specification *fs, struct rte_flow_error *e) { const struct rte_flow_action_of_set_vlan_vid *vlanid; const struct rte_flow_action_of_push_vlan *pushvlan; + const struct rte_flow_action_set_ipv4 *ipv4; + const struct rte_flow_action_set_ipv6 *ipv6; + const struct rte_flow_action_set_tp *tp_port; const struct rte_flow_action_phy_port *port; + int item_index; switch (a->type) { case RTE_FLOW_ACTION_TYPE_OF_SET_VLAN_VID: @@ -401,6 +464,94 @@ ch_rte_parse_atype_switch(const struct rte_flow_action *a, port = (const struct rte_flow_action_phy_port *)a->conf; fs->eport = port->index; break; + case RTE_FLOW_ACTION_TYPE_SET_IPV4_SRC: + item_index = cxgbe_get_flow_item_index(items, + RTE_FLOW_ITEM_TYPE_IPV4); + if (item_index < 0) + return rte_flow_error_set(e, EINVAL, + RTE_FLOW_ERROR_TYPE_ACTION, a, + "No RTE_FLOW_ITEM_TYPE_IPV4 " + "found."); + + ipv4 = (const struct rte_flow_action_set_ipv4 *)a->conf; + memcpy(fs->nat_fip, &ipv4->ipv4_addr, sizeof(ipv4->ipv4_addr)); + *nmode |= 1 << 0; + break; + case RTE_FLOW_ACTION_TYPE_SET_IPV4_DST: + item_index = cxgbe_get_flow_item_index(items, + RTE_FLOW_ITEM_TYPE_IPV4); + if (item_index < 0) + return rte_flow_error_set(e, EINVAL, + RTE_FLOW_ERROR_TYPE_ACTION, a, + "No RTE_FLOW_ITEM_TYPE_IPV4 " + "found."); + + ipv4 = (const struct rte_flow_action_set_ipv4 *)a->conf; + memcpy(fs->nat_lip, &ipv4->ipv4_addr, sizeof(ipv4->ipv4_addr)); + *nmode |= 1 << 1; + break; + case RTE_FLOW_ACTION_TYPE_SET_IPV6_SRC: + item_index = cxgbe_get_flow_item_index(items, + RTE_FLOW_ITEM_TYPE_IPV6); + if (item_index < 0) + return rte_flow_error_set(e, EINVAL, + RTE_FLOW_ERROR_TYPE_ACTION, a, + "No RTE_FLOW_ITEM_TYPE_IPV6 " + "found."); + + ipv6 = (const struct rte_flow_action_set_ipv6 *)a->conf; + memcpy(fs->nat_fip, ipv6->ipv6_addr, sizeof(ipv6->ipv6_addr)); + *nmode |= 1 << 0; + break; + case RTE_FLOW_ACTION_TYPE_SET_IPV6_DST: + item_index = cxgbe_get_flow_item_index(items, + RTE_FLOW_ITEM_TYPE_IPV6); + if (item_index < 0) + return rte_flow_error_set(e, EINVAL, + RTE_FLOW_ERROR_TYPE_ACTION, a, + "No RTE_FLOW_ITEM_TYPE_IPV6 " + "found."); + + ipv6 = (const struct rte_flow_action_set_ipv6 *)a->conf; + memcpy(fs->nat_lip, ipv6->ipv6_addr, sizeof(ipv6->ipv6_addr)); + *nmode |= 1 << 1; + break; + case RTE_FLOW_ACTION_TYPE_SET_TP_SRC: + item_index = cxgbe_get_flow_item_index(items, + RTE_FLOW_ITEM_TYPE_TCP); + if (item_index < 0) { + item_index = + cxgbe_get_flow_item_index(items, + RTE_FLOW_ITEM_TYPE_UDP); + if (item_index < 0) + return rte_flow_error_set(e, EINVAL, + RTE_FLOW_ERROR_TYPE_ACTION, a, + "No RTE_FLOW_ITEM_TYPE_TCP or " + "RTE_FLOW_ITEM_TYPE_UDP found"); + } + + tp_port = (const struct rte_flow_action_set_tp *)a->conf; + fs->nat_fport = be16_to_cpu(tp_port->port); + *nmode |= 1 << 2; + break; + case RTE_FLOW_ACTION_TYPE_SET_TP_DST: + item_index = cxgbe_get_flow_item_index(items, + RTE_FLOW_ITEM_TYPE_TCP); + if (item_index < 0) { + item_index = + cxgbe_get_flow_item_index(items, + RTE_FLOW_ITEM_TYPE_UDP); + if (item_index < 0) + return rte_flow_error_set(e, EINVAL, + RTE_FLOW_ERROR_TYPE_ACTION, a, + "No RTE_FLOW_ITEM_TYPE_TCP or " + "RTE_FLOW_ITEM_TYPE_UDP found"); + } + + tp_port = (const struct rte_flow_action_set_tp *)a->conf; + fs->nat_lport = be16_to_cpu(tp_port->port); + *nmode |= 1 << 3; + break; default: /* We are not supposed to come here */ return rte_flow_error_set(e, EINVAL, @@ -413,10 +564,12 @@ ch_rte_parse_atype_switch(const struct rte_flow_action *a, static int cxgbe_rtef_parse_actions(struct rte_flow *flow, + const struct rte_flow_item items[], const struct rte_flow_action action[], struct rte_flow_error *e) { struct ch_filter_specification *fs = &flow->fs; + uint8_t nmode = 0, nat_ipv4 = 0, nat_ipv6 = 0; const struct rte_flow_action_queue *q; const struct rte_flow_action *a; char abit = 0; @@ -458,6 +611,16 @@ cxgbe_rtef_parse_actions(struct rte_flow *flow, case RTE_FLOW_ACTION_TYPE_OF_PUSH_VLAN: case RTE_FLOW_ACTION_TYPE_OF_POP_VLAN: case RTE_FLOW_ACTION_TYPE_PHY_PORT: + case RTE_FLOW_ACTION_TYPE_SET_IPV4_SRC: + case RTE_FLOW_ACTION_TYPE_SET_IPV4_DST: + nat_ipv4++; + goto action_switch; + case RTE_FLOW_ACTION_TYPE_SET_IPV6_SRC: + case RTE_FLOW_ACTION_TYPE_SET_IPV6_DST: + nat_ipv6++; + case RTE_FLOW_ACTION_TYPE_SET_TP_SRC: + case RTE_FLOW_ACTION_TYPE_SET_TP_DST: +action_switch: /* We allow multiple switch actions, but switch is * not compatible with either queue or drop */ @@ -465,7 +628,14 @@ cxgbe_rtef_parse_actions(struct rte_flow *flow, return rte_flow_error_set(e, EINVAL, RTE_FLOW_ERROR_TYPE_ACTION, a, "overlapping action specified"); - ret = ch_rte_parse_atype_switch(a, fs, e); + if (nat_ipv4 && nat_ipv6) + return rte_flow_error_set(e, EINVAL, + RTE_FLOW_ERROR_TYPE_ACTION, a, + "Can't have one address ipv4 and the" + " other ipv6"); + + ret = ch_rte_parse_atype_switch(a, items, &nmode, fs, + e); if (ret) return ret; fs->action = FILTER_SWITCH; @@ -478,6 +648,10 @@ cxgbe_rtef_parse_actions(struct rte_flow *flow, } } + if (ch_rte_parse_nat(nmode, fs)) + return rte_flow_error_set(e, EINVAL, + RTE_FLOW_ERROR_TYPE_ACTION, a, + "invalid settings for swich action"); return 0; } @@ -586,7 +760,7 @@ cxgbe_flow_parse(struct rte_flow *flow, ret = cxgbe_rtef_parse_items(flow, item, e); if (ret) return ret; - return cxgbe_rtef_parse_actions(flow, action, e); + return cxgbe_rtef_parse_actions(flow, item, action, e); } static int __cxgbe_flow_create(struct rte_eth_dev *dev, struct rte_flow *flow) diff --git a/drivers/net/cxgbe/cxgbe_main.c b/drivers/net/cxgbe/cxgbe_main.c index 9c40f51b2..a135df9c7 100644 --- a/drivers/net/cxgbe/cxgbe_main.c +++ b/drivers/net/cxgbe/cxgbe_main.c @@ -1180,6 +1180,16 @@ static int adap_init0(struct adapter *adap) goto bye; } + /* See if FW supports FW_FILTER2 work request */ + if (is_t4(adap->params.chip)) { + adap->params.filter2_wr_support = 0; + } else { + params[0] = FW_PARAM_DEV(FILTER2_WR); + ret = t4_query_params(adap, adap->mbox, adap->pf, 0, + 1, params, val); + adap->params.filter2_wr_support = (ret == 0 && val[0] != 0); + } + /* query tid-related parameters */ params[0] = FW_PARAM_DEV(NTID); ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1,