Merge branch 'per-nexthop-offload'

Jiri Pirko says:

====================
ipv4: fib: Provide per-nexthop offload indication

Ido says:

Offload indication for IPv4 routes is currently set in the FIB info's
flags. When multipath routes are employed, this can lead to a route being
marked as offloaded although only one of its nexthops is actually
offloaded.

Instead, this patchset aims to proivde a higher resolution for the offload
indication and report it on a per-nexthop basis.

Example output from patched iproute:

$ ip route show 192.168.200.0/24
192.168.200.0/24
        nexthop via 192.168.100.2 dev enp3s0np7 weight 1 offload
        nexthop via 192.168.101.3 dev enp3s0np8 weight 1

And once the second gateway is resolved:

$ ip route show 192.168.200.0/24
192.168.200.0/24
        nexthop via 192.168.100.2 dev enp3s0np7 weight 1 offload
        nexthop via 192.168.101.3 dev enp3s0np8 weight 1 offload

First patch teaches the kernel to look for the offload indication in the
nexthop flags. Patches 2-5 adjust current capable drivers to provide
offload indication on a per-nexthop basis. Last patch removes no longer
used functions to set offload indication in the FIB info's flags.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c

@@ -394,7 +394,6 @@ struct mlxsw_sp_fib_entry {
 	enum mlxsw_sp_fib_entry_type type;
 	struct list_head nexthop_group_node;
 	struct mlxsw_sp_nexthop_group *nh_group;
-	bool offloaded;
 };
 
 struct mlxsw_sp_fib4_entry {
@@ -1653,6 +1652,24 @@ mlxsw_sp_nexthop_fib_entries_update(struct mlxsw_sp *mlxsw_sp,
 	return 0;
 }
 
+static void
+mlxsw_sp_fib_entry_offload_refresh(struct mlxsw_sp_fib_entry *fib_entry,
+				   enum mlxsw_reg_ralue_op op, int err);
+
+static void
+mlxsw_sp_nexthop_fib_entries_refresh(struct mlxsw_sp_nexthop_group *nh_grp)
+{
+	enum mlxsw_reg_ralue_op op = MLXSW_REG_RALUE_OP_WRITE_WRITE;
+	struct mlxsw_sp_fib_entry *fib_entry;
+
+	list_for_each_entry(fib_entry, &nh_grp->fib_list, nexthop_group_node) {
+		if (!mlxsw_sp_fib_node_entry_is_first(fib_entry->fib_node,
+						      fib_entry))
+			continue;
+		mlxsw_sp_fib_entry_offload_refresh(fib_entry, op, 0);
+	}
+}
+
 static void
 mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_nexthop_group *nh_grp)
@@ -1740,6 +1757,10 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
 		dev_warn(mlxsw_sp->bus_info->dev, "Failed to mass-update adjacency index for nexthop group.\n");
 		goto set_trap;
 	}
+
+	/* Offload state within the group changed, so update the flags. */
+	mlxsw_sp_nexthop_fib_entries_refresh(nh_grp);
+
 	return;
 
 set_trap:
@@ -2103,13 +2124,45 @@ mlxsw_sp_fib_entry_should_offload(const struct mlxsw_sp_fib_entry *fib_entry)
 	}
 }
 
+static void
+mlxsw_sp_fib4_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry)
+{
+	struct mlxsw_sp_nexthop_group *nh_grp = fib_entry->nh_group;
+	int i;
+
+	if (fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_LOCAL) {
+		nh_grp->nexthops->key.fib_nh->nh_flags |= RTNH_F_OFFLOAD;
+		return;
+	}
+
+	for (i = 0; i < nh_grp->count; i++) {
+		struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i];
+
+		if (nh->offloaded)
+			nh->key.fib_nh->nh_flags |= RTNH_F_OFFLOAD;
+		else
+			nh->key.fib_nh->nh_flags &= ~RTNH_F_OFFLOAD;
+	}
+}
+
+static void
+mlxsw_sp_fib4_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry)
+{
+	struct mlxsw_sp_nexthop_group *nh_grp = fib_entry->nh_group;
+	int i;
+
+	for (i = 0; i < nh_grp->count; i++) {
+		struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i];
+
+		nh->key.fib_nh->nh_flags &= ~RTNH_F_OFFLOAD;
+	}
+}
+
 static void mlxsw_sp_fib_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry)
 {
-	fib_entry->offloaded = true;
-
 	switch (fib_entry->fib_node->fib->proto) {
 	case MLXSW_SP_L3_PROTO_IPV4:
-		fib_info_offload_inc(fib_entry->nh_group->key.fi);
+		mlxsw_sp_fib4_entry_offload_set(fib_entry);
 		break;
 	case MLXSW_SP_L3_PROTO_IPV6:
 		WARN_ON_ONCE(1);
@@ -2121,13 +2174,11 @@ mlxsw_sp_fib_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry)
 {
 	switch (fib_entry->fib_node->fib->proto) {
 	case MLXSW_SP_L3_PROTO_IPV4:
-		fib_info_offload_dec(fib_entry->nh_group->key.fi);
+		mlxsw_sp_fib4_entry_offload_unset(fib_entry);
 		break;
 	case MLXSW_SP_L3_PROTO_IPV6:
 		WARN_ON_ONCE(1);
 	}
-
-	fib_entry->offloaded = false;
 }
 
 static void
@@ -2136,17 +2187,13 @@ mlxsw_sp_fib_entry_offload_refresh(struct mlxsw_sp_fib_entry *fib_entry,
 {
 	switch (op) {
 	case MLXSW_REG_RALUE_OP_WRITE_DELETE:
-		if (!fib_entry->offloaded)
-			return;
 		return mlxsw_sp_fib_entry_offload_unset(fib_entry);
 	case MLXSW_REG_RALUE_OP_WRITE_WRITE:
 		if (err)
 			return;
-		if (mlxsw_sp_fib_entry_should_offload(fib_entry) &&
+		if (mlxsw_sp_fib_entry_should_offload(fib_entry))
-		    !fib_entry->offloaded)
 			mlxsw_sp_fib_entry_offload_set(fib_entry);
-		else if (!mlxsw_sp_fib_entry_should_offload(fib_entry) &&
+		else if (!mlxsw_sp_fib_entry_should_offload(fib_entry))
-			 fib_entry->offloaded)
 			mlxsw_sp_fib_entry_offload_unset(fib_entry);
 		return;
 	default:

drivers/net/ethernet/rocker/rocker_ofdpa.c

@@ -2761,7 +2761,7 @@ static int ofdpa_fib4_add(struct rocker *rocker,
 				  fen_info->tb_id, 0);
 	if (err)
 		return err;
-	fib_info_offload_inc(fen_info->fi);
+	fen_info->fi->fib_nh->nh_flags |= RTNH_F_OFFLOAD;
 	return 0;
 }
 
@@ -2776,7 +2776,7 @@ static int ofdpa_fib4_del(struct rocker *rocker,
 	ofdpa_port = ofdpa_port_dev_lower_find(fen_info->fi->fib_dev, rocker);
 	if (!ofdpa_port)
 		return 0;
-	fib_info_offload_dec(fen_info->fi);
+	fen_info->fi->fib_nh->nh_flags &= ~RTNH_F_OFFLOAD;
 	return ofdpa_port_fib_ipv4(ofdpa_port, htonl(fen_info->dst),
 				   fen_info->dst_len, fen_info->fi,
 				   fen_info->tb_id, OFDPA_OP_FLAG_REMOVE);
@@ -2803,7 +2803,7 @@ static void ofdpa_fib4_abort(struct rocker *rocker)
 						       rocker);
 		if (!ofdpa_port)
 			continue;
-		fib_info_offload_dec(flow_entry->fi);
+		flow_entry->fi->fib_nh->nh_flags &= ~RTNH_F_OFFLOAD;
 		ofdpa_flow_tbl_del(ofdpa_port, OFDPA_OP_FLAG_REMOVE,
 				   flow_entry);
 	}

include/net/ip_fib.h

@@ -124,7 +124,6 @@ struct fib_info {
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	int			fib_weight;
 #endif
-	unsigned int		fib_offload_cnt;
 	struct rcu_head		rcu;
 	struct fib_nh		fib_nh[0];
 #define fib_dev		fib_nh[0].nh_dev
@@ -177,18 +176,6 @@ struct fib_result_nl {
 
 __be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh);
 
-static inline void fib_info_offload_inc(struct fib_info *fi)
-{
-	fi->fib_offload_cnt++;
-	fi->fib_flags |= RTNH_F_OFFLOAD;
-}
-
-static inline void fib_info_offload_dec(struct fib_info *fi)
-{
-	if (--fi->fib_offload_cnt == 0)
-		fi->fib_flags &= ~RTNH_F_OFFLOAD;
-}
-
 #define FIB_RES_SADDR(net, res)				\
 	((FIB_RES_NH(res).nh_saddr_genid ==		\
 	  atomic_read(&(net)->ipv4.dev_addr_genid)) ?	\

net/ipv4/fib_semantics.c

@@ -1342,6 +1342,8 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 			    IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev))
 				rtm->rtm_flags |= RTNH_F_DEAD;
 		}
+		if (fi->fib_nh->nh_flags & RTNH_F_OFFLOAD)
+			rtm->rtm_flags |= RTNH_F_OFFLOAD;
 #ifdef CONFIG_IP_ROUTE_CLASSID
 		if (fi->fib_nh[0].nh_tclassid &&
 		    nla_put_u32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid))