Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 55827458 authored by David S. Miller's avatar David S. Miller
Browse files

Merge branch 'mlxsw-Add-one-armed-router-support' 



Ido Schimmel says:

====================
mlxsw: Add one-armed router support

Up until now, when a packet was routed by the ASIC through the same
router interface (RIF) from which it ingressed from, the ASIC passed the
sole copy of the packet to the kernel. This allowed the kernel to route
the packet and also potentially generate an ICMP redirect.

There are scenarios (e.g., "one-armed router") where packets are
intentionally routed this way and are therefore not deemed as
exceptions. In such scenarios the current method of trapping packets to
the CPU is problematic, as it results in major packet loss.

This patchset solves the problem by having the ASIC forward the packet,
but also send a copy to the CPU, which gives the kernel the opportunity
to generate required exceptions.

To prevent the kernel from forwarding such packets again, the driver
marks them with 'offload_l3_fwd_mark', which causes the kernel to
consume them in ip{,6}_forward_finish().

Patch #1 renames 'offload_mr_fwd_mark' to 'offload_l3_fwd_mark'. When
set, the field indicates that a packet was already forwarded in L3
(unicast / multicast) by a capable device.

Patch #2 teaches the kernel to consume unicast packets that have
'offload_l3_fwd_mark' set.

Patch #3 changes mlxsw to mirror loopbacked (iRIF == eRIF) packets,
instead of trapping them.

Patch #4 adds a test case for above mentioned scenario.
====================

Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents d9bbd6a1 b6f153d3

drivers/net/ethernet/mellanox/mlxsw/reg.h

+1 −0
Original line number Diff line number Diff line
@@ -5072,6 +5072,7 @@ enum mlxsw_reg_htgt_trap_group { 
	MLXSW_REG_HTGT_TRAP_GROUP_SP_EVENT,

	MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_MLD,

	MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_ND,

	MLXSW_REG_HTGT_TRAP_GROUP_SP_LBERROR,

};



/* reg_htgt_trap_group

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

+8 −6
Original line number Diff line number Diff line
@@ -3554,10 +3554,10 @@ static void mlxsw_sp_rx_listener_mark_func(struct sk_buff *skb, u8 local_port, 
	return mlxsw_sp_rx_listener_no_mark_func(skb, local_port, priv);

}



static void mlxsw_sp_rx_listener_mr_mark_func(struct sk_buff *skb,

static void mlxsw_sp_rx_listener_l3_mark_func(struct sk_buff *skb,

					      u8 local_port, void *priv)

{

	skb->offload_mr_fwd_mark = 1;

	skb->offload_l3_fwd_mark = 1;

	skb->offload_fwd_mark = 1;

	return mlxsw_sp_rx_listener_no_mark_func(skb, local_port, priv);

}
@@ -3605,8 +3605,8 @@ static void mlxsw_sp_rx_listener_sample_func(struct sk_buff *skb, u8 local_port, 
	MLXSW_RXL(mlxsw_sp_rx_listener_mark_func, _trap_id, _action,	\

		_is_ctrl, SP_##_trap_group, DISCARD)



#define MLXSW_SP_RXL_MR_MARK(_trap_id, _action, _trap_group, _is_ctrl)	\

	MLXSW_RXL(mlxsw_sp_rx_listener_mr_mark_func, _trap_id, _action,	\

#define MLXSW_SP_RXL_L3_MARK(_trap_id, _action, _trap_group, _is_ctrl)	\

	MLXSW_RXL(mlxsw_sp_rx_listener_l3_mark_func, _trap_id, _action,	\

		_is_ctrl, SP_##_trap_group, DISCARD)



#define MLXSW_SP_EVENTL(_func, _trap_id)		\
@@ -3639,7 +3639,7 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = { 
	/* L3 traps */

	MLXSW_SP_RXL_MARK(MTUERROR, TRAP_TO_CPU, ROUTER_EXP, false),

	MLXSW_SP_RXL_MARK(TTLERROR, TRAP_TO_CPU, ROUTER_EXP, false),

	MLXSW_SP_RXL_MARK(LBERROR, TRAP_TO_CPU, ROUTER_EXP, false),

	MLXSW_SP_RXL_L3_MARK(LBERROR, MIRROR_TO_CPU, LBERROR, false),

	MLXSW_SP_RXL_MARK(IP2ME, TRAP_TO_CPU, IP2ME, false),

	MLXSW_SP_RXL_MARK(IPV6_UNSPECIFIED_ADDRESS, TRAP_TO_CPU, ROUTER_EXP,

			  false),
@@ -3683,7 +3683,7 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = { 
	MLXSW_SP_RXL_MARK(IPV6_PIM, TRAP_TO_CPU, PIM, false),

	MLXSW_SP_RXL_MARK(RPF, TRAP_TO_CPU, RPF, false),

	MLXSW_SP_RXL_MARK(ACL1, TRAP_TO_CPU, MULTICAST, false),

	MLXSW_SP_RXL_MR_MARK(ACL2, TRAP_TO_CPU, MULTICAST, false),

	MLXSW_SP_RXL_L3_MARK(ACL2, TRAP_TO_CPU, MULTICAST, false),

	/* NVE traps */

	MLXSW_SP_RXL_MARK(NVE_ENCAP_ARP, TRAP_TO_CPU, ARP, false),

};
@@ -3713,6 +3713,7 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core) 
		case MLXSW_REG_HTGT_TRAP_GROUP_SP_OSPF:

		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PIM:

		case MLXSW_REG_HTGT_TRAP_GROUP_SP_RPF:

		case MLXSW_REG_HTGT_TRAP_GROUP_SP_LBERROR:

			rate = 128;

			burst_size = 7;

			break;
@@ -3798,6 +3799,7 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core) 
		case MLXSW_REG_HTGT_TRAP_GROUP_SP_ROUTER_EXP:

		case MLXSW_REG_HTGT_TRAP_GROUP_SP_REMOTE_ROUTE:

		case MLXSW_REG_HTGT_TRAP_GROUP_SP_MULTICAST:

		case MLXSW_REG_HTGT_TRAP_GROUP_SP_LBERROR:

			priority = 1;

			tc = 1;

			break;

include/linux/skbuff.h

+3 −1
Original line number Diff line number Diff line
@@ -616,6 +616,8 @@ typedef unsigned char *sk_buff_data_t; 
 *	@pkt_type: Packet class

 *	@fclone: skbuff clone status

 *	@ipvs_property: skbuff is owned by ipvs

 *	@offload_fwd_mark: Packet was L2-forwarded in hardware

 *	@offload_l3_fwd_mark: Packet was L3-forwarded in hardware

 *	@tc_skip_classify: do not classify packet. set by IFB device

 *	@tc_at_ingress: used within tc_classify to distinguish in/egress

 *	@tc_redirected: packet was redirected by a tc action
@@ -799,7 +801,7 @@ struct sk_buff { 
	__u8			remcsum_offload:1;

#ifdef CONFIG_NET_SWITCHDEV

	__u8			offload_fwd_mark:1;

	__u8			offload_mr_fwd_mark:1;

	__u8			offload_l3_fwd_mark:1;

#endif

#ifdef CONFIG_NET_CLS_ACT

	__u8			tc_skip_classify:1;

net/core/skbuff.c

+1 −1
Original line number Diff line number Diff line
@@ -4885,7 +4885,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet) 


#ifdef CONFIG_NET_SWITCHDEV

	skb->offload_fwd_mark = 0;

	skb->offload_mr_fwd_mark = 0;

	skb->offload_l3_fwd_mark = 0;

#endif



	if (!xnet)

net/ipv4/ip_forward.c

+7 −0
Original line number Diff line number Diff line
@@ -69,6 +69,13 @@ static int ip_forward_finish(struct net *net, struct sock *sk, struct sk_buff *s 
	__IP_INC_STATS(net, IPSTATS_MIB_OUTFORWDATAGRAMS);

	__IP_ADD_STATS(net, IPSTATS_MIB_OUTOCTETS, skb->len);



#ifdef CONFIG_NET_SWITCHDEV

	if (skb->offload_l3_fwd_mark) {

		consume_skb(skb);

		return 0;

	}

#endif



	if (unlikely(opt->optlen))

		ip_forward_options(skb);