[dpdk-stable] patch 'net/mlx5: support tunnel inner items on E-Switch' has been queued to LTS release 18.11.1

[Kevin Traynor <ktraynor@redhat.com>]

Hi,

FYI, your patch has been queued to LTS release 18.11.1

Note it hasn't been pushed to http://dpdk.org/browse/dpdk-stable yet.
It will be pushed if I get no objections before 02/14/19. So please
shout if anyone has objections.

Also note that after the patch there's a diff of the upstream commit vs the
patch applied to the branch. This will indicate if there was any rebasing
needed to apply to the stable branch. If there were code changes for rebasing
(ie: not only metadata diffs), please double check that the rebase was
correctly done.

Thanks.

Kevin Traynor

---
>From 12e14a863374ed6b22eec4da32e127146dabfea3 Mon Sep 17 00:00:00 2001
From: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Date: Thu, 27 Dec 2018 15:34:43 +0000
Subject: [PATCH] net/mlx5: support tunnel inner items on E-Switch

[ upstream commit 78f5341d71cdb8a2a157081214a214d00586fb37 ]

This patch updates the translation routine for the E-Switch Flows.
Inner tunnel pattern items are translated into Netlink message,
support for tunnel inner IP addresses (v4 or v6), IP protocol,
and TCP and UDP ports is added.

We are going to support Flows matching with outer tunnel items
and not containing the explicit tunnel decap action (this one
might be drop, redirect or table jump, for exapmle).
So we can not rely on presence of tunnel decap action in the
list to decide whether the Flow is for tunnel, instead we will
use the presence of tunnel item. Item translation is rebound
to presence of tunnel items, instead of relying on decap action.

There is no way to tell kernel driver the outer address type
(IPv4 or IPv6) but specify the address flower key. The outer
address key is put on Netlink with zero mask if there is no
RTE item is specified in the list.

Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Shahaf Shuler <shahafs@mellanox.com>
---
 drivers/net/mlx5/mlx5_flow_tcf.c | 174 ++++++++++++++++++++++---------
 1 file changed, 125 insertions(+), 49 deletions(-)

diff --git a/drivers/net/mlx5/mlx5_flow_tcf.c b/drivers/net/mlx5/mlx5_flow_tcf.c
index 5fc50c2b5..688422da6 100644
--- a/drivers/net/mlx5/mlx5_flow_tcf.c
+++ b/drivers/net/mlx5/mlx5_flow_tcf.c
@@ -464,5 +464,7 @@ static const union {
 	struct rte_flow_item_udp udp;
 	struct rte_flow_item_vxlan vxlan;
-} flow_tcf_mask_empty;
+} flow_tcf_mask_empty = {
+	{0},
+};
 
 /** Supported masks for known item types. */
@@ -2293,4 +2295,6 @@ flow_tcf_validate(struct rte_eth_dev *dev,
  * @param[in] items
  *   Pointer to the list of items.
+ * @param[out] action_flags
+ *   Pointer to the detected actions.
  *
  * @return
@@ -2299,5 +2303,6 @@ flow_tcf_validate(struct rte_eth_dev *dev,
 static int
 flow_tcf_get_items_size(const struct rte_flow_attr *attr,
-			const struct rte_flow_item items[])
+			const struct rte_flow_item items[],
+			uint64_t *action_flags)
 {
 	int size = 0;
@@ -2350,4 +2355,14 @@ flow_tcf_get_items_size(const struct rte_flow_attr *attr,
 		case RTE_FLOW_ITEM_TYPE_VXLAN:
 			size += SZ_NLATTR_TYPE_OF(uint32_t);
+			/*
+			 * There might be no VXLAN decap action in the action
+			 * list, nonetheless the VXLAN tunnel flow requires
+			 * the decap structure to be correctly applied to
+			 * VXLAN device, set the flag to create the structure.
+			 * Translation routine will not put the decap action
+			 * in tne Netlink message if there is no actual action
+			 * in the list.
+			 */
+			*action_flags |= MLX5_FLOW_ACTION_VXLAN_DECAP;
 			break;
 		default:
@@ -2598,5 +2613,5 @@ flow_tcf_prepare(const struct rte_flow_attr *attr,
 	uint8_t *sp, *tun = NULL;
 
-	size += flow_tcf_get_items_size(attr, items);
+	size += flow_tcf_get_items_size(attr, items, &action_flags);
 	size += flow_tcf_get_actions_and_size(actions, &action_flags);
 	dev_flow = rte_zmalloc(__func__, size, MNL_ALIGNTO);
@@ -3002,4 +3017,5 @@ flow_tcf_translate(struct rte_eth_dev *dev, struct mlx5_flow *dev_flow,
 	bool vlan_eth_type_set = 0;
 	bool ip_proto_set = 0;
+	bool tunnel_outer = 0;
 	struct nlattr *na_flower;
 	struct nlattr *na_flower_act;
@@ -3015,4 +3031,5 @@ flow_tcf_translate(struct rte_eth_dev *dev, struct mlx5_flow *dev_flow,
 		case FLOW_TCF_TUNACT_VXLAN_DECAP:
 			decap.vxlan = dev_flow->tcf.vxlan_decap;
+			tunnel_outer = 1;
 			break;
 		case FLOW_TCF_TUNACT_VXLAN_ENCAP:
@@ -3069,5 +3086,5 @@ flow_tcf_translate(struct rte_eth_dev *dev, struct mlx5_flow *dev_flow,
 			break;
 		case RTE_FLOW_ITEM_TYPE_ETH:
-			item_flags |= (item_flags & MLX5_FLOW_LAYER_VXLAN) ?
+			item_flags |= (item_flags & MLX5_FLOW_LAYER_TUNNEL) ?
 				      MLX5_FLOW_LAYER_INNER_L2 :
 				      MLX5_FLOW_LAYER_OUTER_L2;
@@ -3082,10 +3099,9 @@ flow_tcf_translate(struct rte_eth_dev *dev, struct mlx5_flow *dev_flow,
 				break;
 			spec.eth = items->spec;
-			if (decap.vxlan &&
-			    !(item_flags & MLX5_FLOW_LAYER_VXLAN)) {
+			if (tunnel_outer) {
 				DRV_LOG(WARNING,
-					"outer L2 addresses cannot be forced"
-					" for vxlan decapsulation, parameter"
-					" ignored");
+					"outer L2 addresses cannot be"
+					" forced is outer ones for tunnel,"
+					" parameter is ignored");
 				break;
 			}
@@ -3116,4 +3132,5 @@ flow_tcf_translate(struct rte_eth_dev *dev, struct mlx5_flow *dev_flow,
 			assert(!encap.hdr);
 			assert(!decap.hdr);
+			assert(!tunnel_outer);
 			item_flags |= MLX5_FLOW_LAYER_OUTER_VLAN;
 			mask.vlan = flow_tcf_item_mask
@@ -3150,5 +3167,7 @@ flow_tcf_translate(struct rte_eth_dev *dev, struct mlx5_flow *dev_flow,
 			break;
 		case RTE_FLOW_ITEM_TYPE_IPV4:
-			item_flags |= MLX5_FLOW_LAYER_OUTER_L3_IPV4;
+			item_flags |= (item_flags & MLX5_FLOW_LAYER_TUNNEL) ?
+				      MLX5_FLOW_LAYER_INNER_L3_IPV4 :
+				      MLX5_FLOW_LAYER_OUTER_L3_IPV4;
 			mask.ipv4 = flow_tcf_item_mask
 				(items, &rte_flow_item_ipv4_mask,
@@ -3159,5 +3178,5 @@ flow_tcf_translate(struct rte_eth_dev *dev, struct mlx5_flow *dev_flow,
 			assert(mask.ipv4);
 			spec.ipv4 = items->spec;
-			if (!decap.vxlan) {
+			if (!tunnel_outer) {
 				if (!eth_type_set ||
 				    (!vlan_eth_type_set && vlan_present))
@@ -3170,23 +3189,44 @@ flow_tcf_translate(struct rte_eth_dev *dev, struct mlx5_flow *dev_flow,
 				eth_type_set = 1;
 				vlan_eth_type_set = 1;
-				if (mask.ipv4 == &flow_tcf_mask_empty.ipv4)
+			}
+			if (!tunnel_outer && mask.ipv4->hdr.next_proto_id) {
+				/*
+				 * No way to set IP protocol for outer tunnel
+				 * layers. Usually it is fixed, for example,
+				 * to UDP for VXLAN/GPE.
+				 */
+				assert(spec.ipv4); /* Mask is not empty. */
+				mnl_attr_put_u8(nlh, TCA_FLOWER_KEY_IP_PROTO,
+						spec.ipv4->hdr.next_proto_id);
+				ip_proto_set = 1;
+			}
+			if (mask.ipv4 == &flow_tcf_mask_empty.ipv4 ||
+			     (!mask.ipv4->hdr.src_addr &&
+			      !mask.ipv4->hdr.dst_addr)) {
+				if (!tunnel_outer)
 					break;
-				if (mask.ipv4->hdr.next_proto_id) {
-					mnl_attr_put_u8
-						(nlh, TCA_FLOWER_KEY_IP_PROTO,
-						 spec.ipv4->hdr.next_proto_id);
-					ip_proto_set = 1;
-				}
-			} else {
-				assert(mask.ipv4 != &flow_tcf_mask_empty.ipv4);
+				/*
+				 * For tunnel outer we must set outer IP key
+				 * anyway, even if the specification/mask is
+				 * empty. There is no another way to tell
+				 * kernel about he outer layer protocol.
+				 */
+				mnl_attr_put_u32
+					(nlh, TCA_FLOWER_KEY_ENC_IPV4_SRC,
+					 mask.ipv4->hdr.src_addr);
+				mnl_attr_put_u32
+					(nlh, TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK,
+					 mask.ipv4->hdr.src_addr);
+				assert(dev_flow->tcf.nlsize >= nlh->nlmsg_len);
+				break;
 			}
 			if (mask.ipv4->hdr.src_addr) {
 				mnl_attr_put_u32
-					(nlh, decap.vxlan ?
+					(nlh, tunnel_outer ?
 					 TCA_FLOWER_KEY_ENC_IPV4_SRC :
 					 TCA_FLOWER_KEY_IPV4_SRC,
 					 spec.ipv4->hdr.src_addr);
 				mnl_attr_put_u32
-					(nlh, decap.vxlan ?
+					(nlh, tunnel_outer ?
 					 TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK :
 					 TCA_FLOWER_KEY_IPV4_SRC_MASK,
@@ -3195,10 +3235,10 @@ flow_tcf_translate(struct rte_eth_dev *dev, struct mlx5_flow *dev_flow,
 			if (mask.ipv4->hdr.dst_addr) {
 				mnl_attr_put_u32
-					(nlh, decap.vxlan ?
+					(nlh, tunnel_outer ?
 					 TCA_FLOWER_KEY_ENC_IPV4_DST :
 					 TCA_FLOWER_KEY_IPV4_DST,
 					 spec.ipv4->hdr.dst_addr);
 				mnl_attr_put_u32
-					(nlh, decap.vxlan ?
+					(nlh, tunnel_outer ?
 					 TCA_FLOWER_KEY_ENC_IPV4_DST_MASK :
 					 TCA_FLOWER_KEY_IPV4_DST_MASK,
@@ -3207,6 +3247,10 @@ flow_tcf_translate(struct rte_eth_dev *dev, struct mlx5_flow *dev_flow,
 			assert(dev_flow->tcf.nlsize >= nlh->nlmsg_len);
 			break;
-		case RTE_FLOW_ITEM_TYPE_IPV6:
-			item_flags |= MLX5_FLOW_LAYER_OUTER_L3_IPV6;
+		case RTE_FLOW_ITEM_TYPE_IPV6: {
+			bool ipv6_src, ipv6_dst;
+
+			item_flags |= (item_flags & MLX5_FLOW_LAYER_TUNNEL) ?
+				      MLX5_FLOW_LAYER_INNER_L3_IPV6 :
+				      MLX5_FLOW_LAYER_OUTER_L3_IPV6;
 			mask.ipv6 = flow_tcf_item_mask
 				(items, &rte_flow_item_ipv6_mask,
@@ -3217,5 +3261,5 @@ flow_tcf_translate(struct rte_eth_dev *dev, struct mlx5_flow *dev_flow,
 			assert(mask.ipv6);
 			spec.ipv6 = items->spec;
-			if (!decap.vxlan) {
+			if (!tunnel_outer) {
 				if (!eth_type_set ||
 				    (!vlan_eth_type_set && vlan_present))
@@ -3228,22 +3272,48 @@ flow_tcf_translate(struct rte_eth_dev *dev, struct mlx5_flow *dev_flow,
 				eth_type_set = 1;
 				vlan_eth_type_set = 1;
-				if (mask.ipv6 == &flow_tcf_mask_empty.ipv6)
+			}
+			if (!tunnel_outer && mask.ipv6->hdr.proto) {
+				/*
+				 * No way to set IP protocol for outer tunnel
+				 * layers. Usually it is fixed, for example,
+				 * to UDP for VXLAN/GPE.
+				 */
+				assert(spec.ipv6); /* Mask is not empty. */
+				mnl_attr_put_u8(nlh, TCA_FLOWER_KEY_IP_PROTO,
+						spec.ipv6->hdr.proto);
+				ip_proto_set = 1;
+			}
+			ipv6_dst = !IN6_IS_ADDR_UNSPECIFIED
+						(mask.ipv6->hdr.dst_addr);
+			ipv6_src = !IN6_IS_ADDR_UNSPECIFIED
+						(mask.ipv6->hdr.src_addr);
+			if (mask.ipv6 == &flow_tcf_mask_empty.ipv6 ||
+			     (!ipv6_dst && !ipv6_src)) {
+				if (!tunnel_outer)
 					break;
-				if (mask.ipv6->hdr.proto) {
-					mnl_attr_put_u8
-						(nlh, TCA_FLOWER_KEY_IP_PROTO,
-						 spec.ipv6->hdr.proto);
-					ip_proto_set = 1;
-				}
-			} else {
-				assert(mask.ipv6 != &flow_tcf_mask_empty.ipv6);
+				/*
+				 * For tunnel outer we must set outer IP key
+				 * anyway, even if the specification/mask is
+				 * empty. There is no another way to tell
+				 * kernel about he outer layer protocol.
+				 */
+				mnl_attr_put(nlh,
+					     TCA_FLOWER_KEY_ENC_IPV6_SRC,
+					     IPV6_ADDR_LEN,
+					     mask.ipv6->hdr.src_addr);
+				mnl_attr_put(nlh,
+					     TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK,
+					     IPV6_ADDR_LEN,
+					     mask.ipv6->hdr.src_addr);
+				assert(dev_flow->tcf.nlsize >= nlh->nlmsg_len);
+				break;
 			}
-			if (!IN6_IS_ADDR_UNSPECIFIED(mask.ipv6->hdr.src_addr)) {
-				mnl_attr_put(nlh, decap.vxlan ?
+			if (ipv6_src) {
+				mnl_attr_put(nlh, tunnel_outer ?
 					     TCA_FLOWER_KEY_ENC_IPV6_SRC :
 					     TCA_FLOWER_KEY_IPV6_SRC,
 					     IPV6_ADDR_LEN,
 					     spec.ipv6->hdr.src_addr);
-				mnl_attr_put(nlh, decap.vxlan ?
+				mnl_attr_put(nlh, tunnel_outer ?
 					     TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK :
 					     TCA_FLOWER_KEY_IPV6_SRC_MASK,
@@ -3251,11 +3321,11 @@ flow_tcf_translate(struct rte_eth_dev *dev, struct mlx5_flow *dev_flow,
 					     mask.ipv6->hdr.src_addr);
 			}
-			if (!IN6_IS_ADDR_UNSPECIFIED(mask.ipv6->hdr.dst_addr)) {
-				mnl_attr_put(nlh, decap.vxlan ?
+			if (ipv6_dst) {
+				mnl_attr_put(nlh, tunnel_outer ?
 					     TCA_FLOWER_KEY_ENC_IPV6_DST :
 					     TCA_FLOWER_KEY_IPV6_DST,
 					     IPV6_ADDR_LEN,
 					     spec.ipv6->hdr.dst_addr);
-				mnl_attr_put(nlh, decap.vxlan ?
+				mnl_attr_put(nlh, tunnel_outer ?
 					     TCA_FLOWER_KEY_ENC_IPV6_DST_MASK :
 					     TCA_FLOWER_KEY_IPV6_DST_MASK,
@@ -3265,6 +3335,9 @@ flow_tcf_translate(struct rte_eth_dev *dev, struct mlx5_flow *dev_flow,
 			assert(dev_flow->tcf.nlsize >= nlh->nlmsg_len);
 			break;
+		}
 		case RTE_FLOW_ITEM_TYPE_UDP:
-			item_flags |= MLX5_FLOW_LAYER_OUTER_L4_UDP;
+			item_flags |= (item_flags & MLX5_FLOW_LAYER_TUNNEL) ?
+				      MLX5_FLOW_LAYER_INNER_L4_UDP :
+				      MLX5_FLOW_LAYER_OUTER_L4_UDP;
 			mask.udp = flow_tcf_item_mask
 				(items, &rte_flow_item_udp_mask,
@@ -3275,5 +3348,5 @@ flow_tcf_translate(struct rte_eth_dev *dev, struct mlx5_flow *dev_flow,
 			assert(mask.udp);
 			spec.udp = items->spec;
-			if (!decap.vxlan) {
+			if (!tunnel_outer) {
 				if (!ip_proto_set)
 					mnl_attr_put_u8
@@ -3290,10 +3363,10 @@ flow_tcf_translate(struct rte_eth_dev *dev, struct mlx5_flow *dev_flow,
 			if (mask.udp->hdr.src_port) {
 				mnl_attr_put_u16
-					(nlh, decap.vxlan ?
+					(nlh, tunnel_outer ?
 					 TCA_FLOWER_KEY_ENC_UDP_SRC_PORT :
 					 TCA_FLOWER_KEY_UDP_SRC,
 					 spec.udp->hdr.src_port);
 				mnl_attr_put_u16
-					(nlh, decap.vxlan ?
+					(nlh, tunnel_outer ?
 					 TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK :
 					 TCA_FLOWER_KEY_UDP_SRC_MASK,
@@ -3302,10 +3375,10 @@ flow_tcf_translate(struct rte_eth_dev *dev, struct mlx5_flow *dev_flow,
 			if (mask.udp->hdr.dst_port) {
 				mnl_attr_put_u16
-					(nlh, decap.vxlan ?
+					(nlh, tunnel_outer ?
 					 TCA_FLOWER_KEY_ENC_UDP_DST_PORT :
 					 TCA_FLOWER_KEY_UDP_DST,
 					 spec.udp->hdr.dst_port);
 				mnl_attr_put_u16
-					(nlh, decap.vxlan ?
+					(nlh, tunnel_outer ?
 					 TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK :
 					 TCA_FLOWER_KEY_UDP_DST_MASK,
@@ -3315,5 +3388,7 @@ flow_tcf_translate(struct rte_eth_dev *dev, struct mlx5_flow *dev_flow,
 			break;
 		case RTE_FLOW_ITEM_TYPE_TCP:
-			item_flags |= MLX5_FLOW_LAYER_OUTER_L4_TCP;
+			item_flags |= (item_flags & MLX5_FLOW_LAYER_TUNNEL) ?
+				      MLX5_FLOW_LAYER_INNER_L4_TCP :
+				      MLX5_FLOW_LAYER_OUTER_L4_TCP;
 			mask.tcp = flow_tcf_item_mask
 				(items, &rte_flow_item_tcp_mask,
@@ -3359,4 +3434,5 @@ flow_tcf_translate(struct rte_eth_dev *dev, struct mlx5_flow *dev_flow,
 		case RTE_FLOW_ITEM_TYPE_VXLAN:
 			assert(decap.vxlan);
+			tunnel_outer = 0;
 			item_flags |= MLX5_FLOW_LAYER_VXLAN;
 			spec.vxlan = items->spec;
-- 
2.19.0

---
  Diff of the applied patch vs upstream commit (please double-check if non-empty:
---
--- -	2019-02-07 13:19:55.559309596 +0000
+++ 0003-net-mlx5-support-tunnel-inner-items-on-E-Switch.patch	2019-02-07 13:19:55.000000000 +0000
@@ -1,8 +1,10 @@
-From 78f5341d71cdb8a2a157081214a214d00586fb37 Mon Sep 17 00:00:00 2001
+From 12e14a863374ed6b22eec4da32e127146dabfea3 Mon Sep 17 00:00:00 2001
 From: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
 Date: Thu, 27 Dec 2018 15:34:43 +0000
 Subject: [PATCH] net/mlx5: support tunnel inner items on E-Switch
 
+[ upstream commit 78f5341d71cdb8a2a157081214a214d00586fb37 ]
+
 This patch updates the translation routine for the E-Switch Flows.
 Inner tunnel pattern items are translated into Netlink message,
 support for tunnel inner IP addresses (v4 or v6), IP protocol,
@@ -21,8 +23,6 @@
 address key is put on Netlink with zero mask if there is no
 RTE item is specified in the list.
 
-Cc: stable@dpdk.org
-
 Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
 Acked-by: Shahaf Shuler <shahafs@mellanox.com>
 ---