Merge branch 'ice-pfcp-filter'

Alexander Lobakin says:

====================
ice: add PFCP filter support

Add support for creating PFCP filters in switchdev mode. Add pfcp module
that allows to create a PFCP-type netdev. The netdev then can be passed to
tc when creating a filter to indicate that PFCP filter should be created.

To add a PFCP filter, a special netdev must be created and passed to tc
command:

  ip link add pfcp0 type pfcp
  tc filter add dev eth0 ingress prio 1 flower pfcp_opts \
    1:12ab/ff:fffffffffffffff0 skip_hw action mirred egress redirect \
    dev pfcp0

Changes in iproute2 [1] are required to use pfcp_opts in tc.

ICE COMMS package is required as it contains PFCP profiles.

Part of this patchset modifies IP_TUNNEL_*_OPTs, which were previously
stored in a __be16. All possible values have already been used, making
it impossible to add new ones.

* 1-3: add new bitmap_{read,write}(), which is used later in the IP
       tunnel flags code (from Alexander's ARM64 MTE series[2]);
* 4-14: some bitmap code preparations also used later in IP tunnels;
* 15-17: convert IP tunnel flags from __be16 to a bitmap;
* 18-21: add PFCP module and support for it in ice.

[1] https://lore.kernel.org/netdev/20230614091758.11180-1-marcin.szycik@linux.intel.com
[2] https://lore.kernel.org/linux-kernel/20231218124033.551770-1-glider@google.com
====================

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

drivers/md/dm-clone-metadata.c

@@ -465,11 +465,6 @@ static void __destroy_persistent_data_structures(struct dm_clone_metadata *cmd)
 
 /*---------------------------------------------------------------------------*/
 
-static size_t bitmap_size(unsigned long nr_bits)
-{
-	return BITS_TO_LONGS(nr_bits) * sizeof(long);
-}
-
 static int __dirty_map_init(struct dirty_map *dmap, unsigned long nr_words,
 			    unsigned long nr_regions)
 {

drivers/net/Kconfig

@@ -290,6 +290,19 @@ config GTP
 	  To compile this drivers as a module, choose M here: the module
 	  will be called gtp.
 
+config PFCP
+	tristate "Packet Forwarding Control Protocol (PFCP)"
+	depends on INET
+	select NET_UDP_TUNNEL
+	help
+	  This allows one to create PFCP virtual interfaces that allows to
+	  set up software and hardware offload of PFCP packets.
+	  Note that this module does not support PFCP protocol in the kernel space.
+	  There is no support for parsing any PFCP messages.
+
+	  To compile this drivers as a module, choose M here: the module
+	  will be called pfcp.
+
 config AMT
 	tristate "Automatic Multicast Tunneling (AMT)"
 	depends on INET && IP_MULTICAST

drivers/net/Makefile

@@ -38,6 +38,7 @@ obj-$(CONFIG_GENEVE) += geneve.o
 obj-$(CONFIG_BAREUDP) += bareudp.o
 obj-$(CONFIG_GTP) += gtp.o
 obj-$(CONFIG_NLMON) += nlmon.o
+obj-$(CONFIG_PFCP) += pfcp.o
 obj-$(CONFIG_NET_VRF) += vrf.o
 obj-$(CONFIG_VSOCKMON) += vsockmon.o
 obj-$(CONFIG_MHI_NET) += mhi_net.o

drivers/net/bareudp.c

@@ -61,6 +61,7 @@ struct bareudp_dev {
 static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 {
 	struct metadata_dst *tun_dst = NULL;
+	IP_TUNNEL_DECLARE_FLAGS(key) = { };
 	struct bareudp_dev *bareudp;
 	unsigned short family;
 	unsigned int len;
@@ -137,7 +138,10 @@ static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 		bareudp->dev->stats.rx_dropped++;
 		goto drop;
 	}
-	tun_dst = udp_tun_rx_dst(skb, family, TUNNEL_KEY, 0, 0);
+
+	__set_bit(IP_TUNNEL_KEY_BIT, key);
+
+	tun_dst = udp_tun_rx_dst(skb, family, key, 0, 0);
 	if (!tun_dst) {
 		bareudp->dev->stats.rx_dropped++;
 		goto drop;
@@ -285,10 +289,10 @@ static int bareudp_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 			    struct bareudp_dev *bareudp,
 			    const struct ip_tunnel_info *info)
 {
+	bool udp_sum = test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags);
 	bool xnet = !net_eq(bareudp->net, dev_net(bareudp->dev));
 	bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
 	struct socket *sock = rcu_dereference(bareudp->sock);
-	bool udp_sum = !!(info->key.tun_flags & TUNNEL_CSUM);
 	const struct ip_tunnel_key *key = &info->key;
 	struct rtable *rt;
 	__be16 sport, df;
@@ -316,7 +320,8 @@ static int bareudp_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 
 	tos = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb);
 	ttl = key->ttl;
-	df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0;
+	df = test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags) ?
+	     htons(IP_DF) : 0;
 	skb_scrub_packet(skb, xnet);
 
 	err = -ENOSPC;
@@ -338,7 +343,8 @@ static int bareudp_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	udp_tunnel_xmit_skb(rt, sock->sk, skb, saddr, info->key.u.ipv4.dst,
 			    tos, ttl, df, sport, bareudp->port,
 			    !net_eq(bareudp->net, dev_net(bareudp->dev)),
-			    !(info->key.tun_flags & TUNNEL_CSUM));
+			    !test_bit(IP_TUNNEL_CSUM_BIT,
+				      info->key.tun_flags));
 	return 0;
 
 free_dst:
@@ -350,10 +356,10 @@ static int bareudp6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 			     struct bareudp_dev *bareudp,
 			     const struct ip_tunnel_info *info)
 {
+	bool udp_sum = test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags);
 	bool xnet = !net_eq(bareudp->net, dev_net(bareudp->dev));
 	bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
 	struct socket *sock  = rcu_dereference(bareudp->sock);
-	bool udp_sum = !!(info->key.tun_flags & TUNNEL_CSUM);
 	const struct ip_tunnel_key *key = &info->key;
 	struct dst_entry *dst = NULL;
 	struct in6_addr saddr, daddr;
@@ -402,7 +408,8 @@ static int bareudp6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	udp_tunnel6_xmit_skb(dst, sock->sk, skb, dev,
 			     &saddr, &daddr, prio, ttl,
 			     info->key.label, sport, bareudp->port,
-			     !(info->key.tun_flags & TUNNEL_CSUM));
+			     !test_bit(IP_TUNNEL_CSUM_BIT,
+				       info->key.tun_flags));
 	return 0;
 
 free_dst:

drivers/net/ethernet/intel/ice/ice_ddp.c

@@ -721,6 +721,12 @@ static bool ice_is_gtp_c_profile(u16 prof_idx)
 	}
 }
 
+static bool ice_is_pfcp_profile(u16 prof_idx)
+{
+	return prof_idx >= ICE_PROFID_IPV4_PFCP_NODE &&
+	       prof_idx <= ICE_PROFID_IPV6_PFCP_SESSION;
+}
+
 /**
  * ice_get_sw_prof_type - determine switch profile type
  * @hw: pointer to the HW structure
@@ -738,6 +744,9 @@ static enum ice_prof_type ice_get_sw_prof_type(struct ice_hw *hw,
 	if (ice_is_gtp_u_profile(prof_idx))
 		return ICE_PROF_TUN_GTPU;
 
+	if (ice_is_pfcp_profile(prof_idx))
+		return ICE_PROF_TUN_PFCP;
+
 	for (i = 0; i < hw->blk[ICE_BLK_SW].es.fvw; i++) {
 		/* UDP tunnel will have UDP_OF protocol ID and VNI offset */
 		if (fv->ew[i].prot_id == (u8)ICE_PROT_UDP_OF &&

drivers/net/ethernet/intel/ice/ice_flex_type.h

@@ -93,6 +93,7 @@ enum ice_tunnel_type {
 	TNL_GRETAP,
 	TNL_GTPC,
 	TNL_GTPU,
+	TNL_PFCP,
 	__TNL_TYPE_CNT,
 	TNL_LAST = 0xFF,
 	TNL_ALL = 0xFF,
@@ -358,7 +359,8 @@ enum ice_prof_type {
 	ICE_PROF_TUN_GRE = 0x4,
 	ICE_PROF_TUN_GTPU = 0x8,
 	ICE_PROF_TUN_GTPC = 0x10,
-	ICE_PROF_TUN_ALL = 0x1E,
+	ICE_PROF_TUN_PFCP = 0x20,
+	ICE_PROF_TUN_ALL = 0x3E,
 	ICE_PROF_ALL = 0xFF,
 };
 

drivers/net/ethernet/intel/ice/ice_protocol_type.h

@@ -43,6 +43,7 @@ enum ice_protocol_type {
 	ICE_NVGRE,
 	ICE_GTP,
 	ICE_GTP_NO_PAY,
+	ICE_PFCP,
 	ICE_PPPOE,
 	ICE_L2TPV3,
 	ICE_VLAN_EX,
@@ -61,6 +62,7 @@ enum ice_sw_tunnel_type {
 	ICE_SW_TUN_NVGRE,
 	ICE_SW_TUN_GTPU,
 	ICE_SW_TUN_GTPC,
+	ICE_SW_TUN_PFCP,
 	ICE_ALL_TUNNELS /* All tunnel types including NVGRE */
 };
 
@@ -202,6 +204,15 @@ struct ice_udp_gtp_hdr {
 	u8 rsvrd;
 };
 
+struct ice_pfcp_hdr {
+	u8 flags;
+	u8 msg_type;
+	__be16 length;
+	__be64 seid;
+	__be32 seq;
+	u8 spare;
+} __packed __aligned(__alignof__(u16));
+
 struct ice_pppoe_hdr {
 	u8 rsrvd_ver_type;
 	u8 rsrvd_code;
@@ -418,6 +429,7 @@ union ice_prot_hdr {
 	struct ice_udp_tnl_hdr tnl_hdr;
 	struct ice_nvgre_hdr nvgre_hdr;
 	struct ice_udp_gtp_hdr gtp_hdr;
+	struct ice_pfcp_hdr pfcp_hdr;
 	struct ice_pppoe_hdr pppoe_hdr;
 	struct ice_l2tpv3_sess_hdr l2tpv3_sess_hdr;
 	struct ice_hw_metadata metadata;

drivers/net/ethernet/intel/ice/ice_switch.c

@@ -42,6 +42,7 @@ enum {
 	ICE_PKT_KMALLOC		= BIT(9),
 	ICE_PKT_PPPOE		= BIT(10),
 	ICE_PKT_L2TPV3		= BIT(11),
+	ICE_PKT_PFCP		= BIT(12),
 };
 
 struct ice_dummy_pkt_offsets {
@@ -1110,6 +1111,77 @@ ICE_DECLARE_PKT_TEMPLATE(ipv6_gtp) = {
 	0x00, 0x00,
 };
 
+ICE_DECLARE_PKT_OFFSETS(pfcp_session_ipv4) = {
+	{ ICE_MAC_OFOS,		0 },
+	{ ICE_ETYPE_OL,		12 },
+	{ ICE_IPV4_OFOS,	14 },
+	{ ICE_UDP_ILOS,		34 },
+	{ ICE_PFCP,		42 },
+	{ ICE_PROTOCOL_LAST,	0 },
+};
+
+ICE_DECLARE_PKT_TEMPLATE(pfcp_session_ipv4) = {
+	0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+
+	0x08, 0x00,		/* ICE_ETYPE_OL 12 */
+
+	0x45, 0x00, 0x00, 0x2c, /* ICE_IPV4_OFOS 14 */
+	0x00, 0x01, 0x00, 0x00,
+	0x00, 0x11, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+
+	0x00, 0x00, 0x22, 0x65, /* ICE_UDP_ILOS 34 */
+	0x00, 0x18, 0x00, 0x00,
+
+	0x21, 0x01, 0x00, 0x0c, /* ICE_PFCP 42 */
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+
+	0x00, 0x00,		/* 2 bytes for 4 byte alignment */
+};
+
+ICE_DECLARE_PKT_OFFSETS(pfcp_session_ipv6) = {
+	{ ICE_MAC_OFOS,		0 },
+	{ ICE_ETYPE_OL,		12 },
+	{ ICE_IPV6_OFOS,	14 },
+	{ ICE_UDP_ILOS,		54 },
+	{ ICE_PFCP,		62 },
+	{ ICE_PROTOCOL_LAST,	0 },
+};
+
+ICE_DECLARE_PKT_TEMPLATE(pfcp_session_ipv6) = {
+	0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+
+	0x86, 0xdd,		/* ICE_ETYPE_OL 12 */
+
+	0x60, 0x00, 0x00, 0x00, /* ICE_IPV6_OFOS 14 */
+	0x00, 0x10, 0x11, 0x00, /* Next header UDP */
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+
+	0x00, 0x00, 0x22, 0x65, /* ICE_UDP_ILOS 54 */
+	0x00, 0x18, 0x00, 0x00,
+
+	0x21, 0x01, 0x00, 0x0c, /* ICE_PFCP 62 */
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+
+	0x00, 0x00,		/* 2 bytes for 4 byte alignment */
+};
+
 ICE_DECLARE_PKT_OFFSETS(pppoe_ipv4_tcp) = {
 	{ ICE_MAC_OFOS,		0 },
 	{ ICE_ETYPE_OL,		12 },
@@ -1343,6 +1415,8 @@ static const struct ice_dummy_pkt_profile ice_dummy_pkt_profiles[] = {
 	ICE_PKT_PROFILE(ipv4_gtpu_ipv4_tcp, ICE_PKT_TUN_GTPU),
 	ICE_PKT_PROFILE(ipv6_gtp, ICE_PKT_TUN_GTPC | ICE_PKT_OUTER_IPV6),
 	ICE_PKT_PROFILE(ipv4_gtpu_ipv4, ICE_PKT_TUN_GTPC),
+	ICE_PKT_PROFILE(pfcp_session_ipv6, ICE_PKT_PFCP | ICE_PKT_OUTER_IPV6),
+	ICE_PKT_PROFILE(pfcp_session_ipv4, ICE_PKT_PFCP),
 	ICE_PKT_PROFILE(pppoe_ipv6_udp, ICE_PKT_PPPOE | ICE_PKT_OUTER_IPV6 |
 					ICE_PKT_INNER_UDP),
 	ICE_PKT_PROFILE(pppoe_ipv6_tcp, ICE_PKT_PPPOE | ICE_PKT_OUTER_IPV6),
@@ -4532,6 +4606,7 @@ static const struct ice_prot_ext_tbl_entry ice_prot_ext[ICE_PROTOCOL_LAST] = {
 	ICE_PROTOCOL_ENTRY(ICE_NVGRE, 0, 2, 4, 6),
 	ICE_PROTOCOL_ENTRY(ICE_GTP, 8, 10, 12, 14, 16, 18, 20, 22),
 	ICE_PROTOCOL_ENTRY(ICE_GTP_NO_PAY, 8, 10, 12, 14),
+	ICE_PROTOCOL_ENTRY(ICE_PFCP, 8, 10, 12, 14, 16, 18, 20, 22),
 	ICE_PROTOCOL_ENTRY(ICE_PPPOE, 0, 2, 4, 6),
 	ICE_PROTOCOL_ENTRY(ICE_L2TPV3, 0, 2, 4, 6, 8, 10),
 	ICE_PROTOCOL_ENTRY(ICE_VLAN_EX, 2, 0),
@@ -4565,6 +4640,7 @@ static struct ice_protocol_entry ice_prot_id_tbl[ICE_PROTOCOL_LAST] = {
 	{ ICE_NVGRE,		ICE_GRE_OF_HW },
 	{ ICE_GTP,		ICE_UDP_OF_HW },
 	{ ICE_GTP_NO_PAY,	ICE_UDP_ILOS_HW },
+	{ ICE_PFCP,		ICE_UDP_ILOS_HW },
 	{ ICE_PPPOE,		ICE_PPPOE_HW },
 	{ ICE_L2TPV3,		ICE_L2TPV3_HW },
 	{ ICE_VLAN_EX,          ICE_VLAN_OF_HW },
@@ -5272,6 +5348,9 @@ ice_get_compat_fv_bitmap(struct ice_hw *hw, struct ice_adv_rule_info *rinfo,
 	case ICE_SW_TUN_GTPC:
 		prof_type = ICE_PROF_TUN_GTPC;
 		break;
+	case ICE_SW_TUN_PFCP:
+		prof_type = ICE_PROF_TUN_PFCP;
+		break;
 	case ICE_SW_TUN_AND_NON_TUN:
 	default:
 		prof_type = ICE_PROF_ALL;
@@ -5556,6 +5635,9 @@ ice_find_dummy_packet(struct ice_adv_lkup_elem *lkups, u16 lkups_cnt,
 	case ICE_SW_TUN_VXLAN:
 		match |= ICE_PKT_TUN_UDP;
 		break;
+	case ICE_SW_TUN_PFCP:
+		match |= ICE_PKT_PFCP;
+		break;
 	default:
 		break;
 	}
@@ -5696,6 +5778,9 @@ ice_fill_adv_dummy_packet(struct ice_adv_lkup_elem *lkups, u16 lkups_cnt,
 		case ICE_GTP:
 			len = sizeof(struct ice_udp_gtp_hdr);
 			break;
+		case ICE_PFCP:
+			len = sizeof(struct ice_pfcp_hdr);
+			break;
 		case ICE_PPPOE:
 			len = sizeof(struct ice_pppoe_hdr);
 			break;

drivers/net/ethernet/intel/ice/ice_switch.h

@@ -22,6 +22,8 @@
 #define ICE_PROFID_IPV6_GTPC_NO_TEID			45
 #define ICE_PROFID_IPV6_GTPU_TEID			46
 #define ICE_PROFID_IPV6_GTPU_IPV6_TCP_INNER		70
+#define ICE_PROFID_IPV4_PFCP_NODE			79
+#define ICE_PROFID_IPV6_PFCP_SESSION			82
 
 #define ICE_SW_RULE_VSI_LIST_SIZE(s, n)		struct_size((s), vsi, (n))
 #define ICE_SW_RULE_RX_TX_HDR_SIZE(s, l)	struct_size((s), hdr_data, (l))