[dpdk-dev] [RFC v2 3/3] net/cxgbe: add flow actions to modify IP and TCP/UDP port address

[Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>]

From: Shagun Agrawal <shaguna@chelsio.com>

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.

Signed-off-by: Shagun Agrawal <shaguna@chelsio.com>
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
---
v2:
- Re-based to tip.

 drivers/net/cxgbe/base/common.h         |   1 +
 drivers/net/cxgbe/base/t4fw_interface.h |  50 ++++++++++++++++
 drivers/net/cxgbe/cxgbe_filter.c        |  21 ++++++-
 drivers/net/cxgbe/cxgbe_filter.h        |  23 ++++++++
 drivers/net/cxgbe/cxgbe_flow.c          | 100 +++++++++++++++++++++++++++++++-
 drivers/net/cxgbe/cxgbe_main.c          |  10 ++++
 6 files changed, 200 insertions(+), 5 deletions(-)

diff --git a/drivers/net/cxgbe/base/common.h b/drivers/net/cxgbe/base/common.h
index 157201da2..bbd915f29 100644
--- a/drivers/net/cxgbe/base/common.h
+++ b/drivers/net/cxgbe/base/common.h
@@ -270,6 +270,7 @@ struct adapter_params {
 
 	bool ulptx_memwrite_dsgl;          /* use of T5 DSGL allowed */
 	u8 fw_caps_support;		  /* 32-bit Port Capabilities */
+	bool filter2_wr_support;	/* FW support for FILTER2_WR */
 };
 
 /* Firmware Port Capabilities types.
diff --git a/drivers/net/cxgbe/base/t4fw_interface.h b/drivers/net/cxgbe/base/t4fw_interface.h
index e80b58a32..832d22f93 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,
 };
 
@@ -197,6 +198,51 @@ struct fw_filter_wr {
 	__u8   sma[6];
 };
 
+struct fw_filter2_wr {
+	__be32 op_pkd;
+	__be32 len16_pkd;
+	__be64 r3;
+	__be32 tid_to_iq;
+	__be32 del_filter_to_l2tix;
+	__be16 ethtype;
+	__be16 ethtypem;
+	__u8   frag_to_ovlan_vldm;
+	__u8   smac_sel;
+	__be16 rx_chan_rx_rpl_iq;
+	__be32 maci_to_matchtypem;
+	__u8   ptcl;
+	__u8   ptclm;
+	__u8   ttyp;
+	__u8   ttypm;
+	__be16 ivlan;
+	__be16 ivlanm;
+	__be16 ovlan;
+	__be16 ovlanm;
+	__u8   lip[16];
+	__u8   lipm[16];
+	__u8   fip[16];
+	__u8   fipm[16];
+	__be16 lp;
+	__be16 lpm;
+	__be16 fp;
+	__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
 #define V_FW_FILTER_WR_TID(x)	((x) << S_FW_FILTER_WR_TID)
 
@@ -300,6 +346,9 @@ 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)
+
 /******************************************************************************
  *  C O M M A N D s
  *********************/
@@ -655,6 +704,7 @@ 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 7f0d38001..deae1c37b 100644
--- a/drivers/net/cxgbe/cxgbe_filter.c
+++ b/drivers/net/cxgbe/cxgbe_filter.c
@@ -87,6 +87,9 @@ 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;
 }
 
@@ -648,7 +651,7 @@ 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;
@@ -663,13 +666,16 @@ 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) |
@@ -704,6 +710,15 @@ 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_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 af8fa7529..c85fa6d2c 100644
--- a/drivers/net/cxgbe/cxgbe_filter.h
+++ b/drivers/net/cxgbe/cxgbe_filter.h
@@ -100,6 +100,18 @@ struct ch_filter_specification {
 
 	uint32_t eport:2;	/* egress port to switch packet out */
 
+	/*
+	 * 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 Ethernet 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 to use after NAT'ing */
+	uint16_t nat_fport;	/* foreign port to use after NAT'ing */
+
 	/* Filter rule value/mask pairs. */
 	struct ch_filter_tuple val;
 	struct ch_filter_tuple mask;
@@ -111,6 +123,17 @@ enum {
 	FILTER_SWITCH
 };
 
+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 01c945f1b..099aca61e 100644
--- a/drivers/net/cxgbe/cxgbe_flow.c
+++ b/drivers/net/cxgbe/cxgbe_flow.c
@@ -327,10 +327,54 @@ static int cxgbe_get_fidx(struct rte_flow *flow, unsigned int *fidx)
 }
 
 static int
-ch_rte_parse_atype_switch(const struct rte_flow_action *a,
+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: /* 1110 */
+		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, uint8_t *nmode,
 			  struct ch_filter_specification *fs,
 			  struct rte_flow_error *e)
 {
+	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;
 
 	switch (a->type) {
@@ -338,6 +382,36 @@ 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:
+		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:
+		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:
+		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:
+		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:
+		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:
+		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,
@@ -358,6 +432,7 @@ cxgbe_rtef_parse_actions(struct rte_flow *flow,
 	const struct rte_flow_action *a;
 	char abit = 0;
 	int ret;
+	uint8_t nmode = 0, nat_ipv4 = 0, nat_ipv6 = 0;
 
 	for (a = action; a->type != RTE_FLOW_ACTION_TYPE_END; a++) {
 		switch (a->type) {
@@ -391,7 +466,18 @@ cxgbe_rtef_parse_actions(struct rte_flow *flow,
 		case RTE_FLOW_ACTION_TYPE_COUNT:
 			fs->hitcnts = 1;
 			break;
+		/* switch actions */
+		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:
 		case RTE_FLOW_ACTION_TYPE_PHY_PORT:
+action_switch:
 			/* We allow multiple switch actions, but switch is
 			 * not compatible with either queue or drop
 			 */
@@ -399,7 +485,13 @@ 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, &nmode, fs, e);
 			if (ret)
 				return ret;
 			fs->action = FILTER_SWITCH;
@@ -412,6 +504,10 @@ 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;
 }
 
diff --git a/drivers/net/cxgbe/cxgbe_main.c b/drivers/net/cxgbe/cxgbe_main.c
index c3938e8db..4aeb3e074 100644
--- a/drivers/net/cxgbe/cxgbe_main.c
+++ b/drivers/net/cxgbe/cxgbe_main.c
@@ -1170,6 +1170,16 @@ 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,
-- 
2.14.1