Merge branch '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue

Tony Nguyen says:

====================
ice: PPPoE offload support

Marcin Szycik says:

Add support for dissecting PPPoE and PPP-specific fields in flow dissector:
PPPoE session id and PPP protocol type. Add support for those fields in
tc-flower and support offloading PPPoE. Finally, add support for hardware
offload of PPPoE packets in switchdev mode in ice driver.

Example filter:
tc filter add dev $PF1 ingress protocol ppp_ses prio 1 flower pppoe_sid \
    1234 ppp_proto ip skip_sw action mirred egress redirect dev $VF1_PR

Changes in iproute2 are required to use the new fields (will be submitted
soon).

ICE COMMS DDP package is required to create a filter in ice.

* '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue:
  ice: Add support for PPPoE hardware offload
  flow_offload: Introduce flow_match_pppoe
  net/sched: flower: Add PPPoE filter
  flow_dissector: Add PPPoE dissectors
====================

Link: https://lore.kernel.org/r/20220726203133.2171332-1-anthony.l.nguyen@intel.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

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

@@ -52,6 +52,7 @@
 #include <net/udp_tunnel.h>
 #include <net/vxlan.h>
 #include <net/gtp.h>
+#include <linux/ppp_defs.h>
 #include "ice_devids.h"
 #include "ice_type.h"
 #include "ice_txrx.h"

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

@@ -1964,8 +1964,11 @@ ice_get_sw_fv_list(struct ice_hw *hw, struct ice_prot_lkup_ext *lkups,
 			}
 		}
 	} while (fv);
-	if (list_empty(fv_list))
+	if (list_empty(fv_list)) {
+		dev_warn(ice_hw_to_dev(hw), "Required profiles not found in currently loaded DDP package");
 		return -EIO;
+	}
+
 	return 0;
 
 err:

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_PPPOE,
 	ICE_VLAN_EX,
 	ICE_VLAN_IN,
 	ICE_VXLAN_GPE,
@@ -109,6 +110,7 @@ enum ice_prot_id {
 #define ICE_TCP_IL_HW		49
 #define ICE_UDP_ILOS_HW		53
 #define ICE_GRE_OF_HW		64
+#define ICE_PPPOE_HW		103
 
 #define ICE_UDP_OF_HW	52 /* UDP Tunnels */
 #define ICE_META_DATA_ID_HW 255 /* this is used for tunnel and VLAN type */
@@ -207,6 +209,14 @@ struct ice_udp_gtp_hdr {
 	u8 rsvrd;
 };
 
+struct ice_pppoe_hdr {
+	u8 rsrvd_ver_type;
+	u8 rsrvd_code;
+	__be16 session_id;
+	__be16 length;
+	__be16 ppp_prot_id; /* control and data only */
+};
+
 struct ice_nvgre_hdr {
 	__be16 flags;
 	__be16 protocol;
@@ -224,6 +234,7 @@ 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_pppoe_hdr pppoe_hdr;
 };
 
 /* This is mapping table entry that maps every word within a given protocol

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

@@ -41,6 +41,7 @@ enum {
 	ICE_PKT_INNER_UDP	= BIT(7),
 	ICE_PKT_GTP_NOPAY	= BIT(8),
 	ICE_PKT_KMALLOC		= BIT(9),
+	ICE_PKT_PPPOE		= BIT(10),
 };
 
 struct ice_dummy_pkt_offsets {
@@ -1109,6 +1110,154 @@ ICE_DECLARE_PKT_TEMPLATE(ipv6_gtp) = {
 	0x00, 0x00,
 };
 
+ICE_DECLARE_PKT_OFFSETS(pppoe_ipv4_tcp) = {
+	{ ICE_MAC_OFOS,		0 },
+	{ ICE_ETYPE_OL,		12 },
+	{ ICE_PPPOE,		14 },
+	{ ICE_IPV4_OFOS,	22 },
+	{ ICE_TCP_IL,		42 },
+	{ ICE_PROTOCOL_LAST,	0 },
+};
+
+ICE_DECLARE_PKT_TEMPLATE(pppoe_ipv4_tcp) = {
+	0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+
+	0x88, 0x64,		/* ICE_ETYPE_OL 12 */
+
+	0x11, 0x00, 0x00, 0x00, /* ICE_PPPOE 14 */
+	0x00, 0x16,
+
+	0x00, 0x21,		/* PPP Link Layer 20 */
+
+	0x45, 0x00, 0x00, 0x28, /* ICE_IPV4_OFOS 22 */
+	0x00, 0x01, 0x00, 0x00,
+	0x00, 0x06, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+
+	0x00, 0x00, 0x00, 0x00, /* ICE_TCP_IL 42 */
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x50, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+
+	0x00, 0x00,		/* 2 bytes for 4 bytes alignment */
+};
+
+ICE_DECLARE_PKT_OFFSETS(pppoe_ipv4_udp) = {
+	{ ICE_MAC_OFOS,		0 },
+	{ ICE_ETYPE_OL,		12 },
+	{ ICE_PPPOE,		14 },
+	{ ICE_IPV4_OFOS,	22 },
+	{ ICE_UDP_ILOS,		42 },
+	{ ICE_PROTOCOL_LAST,	0 },
+};
+
+ICE_DECLARE_PKT_TEMPLATE(pppoe_ipv4_udp) = {
+	0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+
+	0x88, 0x64,		/* ICE_ETYPE_OL 12 */
+
+	0x11, 0x00, 0x00, 0x00, /* ICE_PPPOE 14 */
+	0x00, 0x16,
+
+	0x00, 0x21,		/* PPP Link Layer 20 */
+
+	0x45, 0x00, 0x00, 0x1c, /* ICE_IPV4_OFOS 22 */
+	0x00, 0x01, 0x00, 0x00,
+	0x00, 0x11, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+
+	0x00, 0x00, 0x00, 0x00, /* ICE_UDP_ILOS 42 */
+	0x00, 0x08, 0x00, 0x00,
+
+	0x00, 0x00,		/* 2 bytes for 4 bytes alignment */
+};
+
+ICE_DECLARE_PKT_OFFSETS(pppoe_ipv6_tcp) = {
+	{ ICE_MAC_OFOS,		0 },
+	{ ICE_ETYPE_OL,		12 },
+	{ ICE_PPPOE,		14 },
+	{ ICE_IPV6_OFOS,	22 },
+	{ ICE_TCP_IL,		62 },
+	{ ICE_PROTOCOL_LAST,	0 },
+};
+
+ICE_DECLARE_PKT_TEMPLATE(pppoe_ipv6_tcp) = {
+	0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+
+	0x88, 0x64,		/* ICE_ETYPE_OL 12 */
+
+	0x11, 0x00, 0x00, 0x00, /* ICE_PPPOE 14 */
+	0x00, 0x2a,
+
+	0x00, 0x57,		/* PPP Link Layer 20 */
+
+	0x60, 0x00, 0x00, 0x00, /* ICE_IPV6_OFOS 22 */
+	0x00, 0x14, 0x06, 0x00, /* Next header is TCP */
+	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, 0x00, 0x00, /* ICE_TCP_IL 62 */
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x50, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+
+	0x00, 0x00,		/* 2 bytes for 4 bytes alignment */
+};
+
+ICE_DECLARE_PKT_OFFSETS(pppoe_ipv6_udp) = {
+	{ ICE_MAC_OFOS,		0 },
+	{ ICE_ETYPE_OL,		12 },
+	{ ICE_PPPOE,		14 },
+	{ ICE_IPV6_OFOS,	22 },
+	{ ICE_UDP_ILOS,		62 },
+	{ ICE_PROTOCOL_LAST,	0 },
+};
+
+ICE_DECLARE_PKT_TEMPLATE(pppoe_ipv6_udp) = {
+	0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+
+	0x88, 0x64,		/* ICE_ETYPE_OL 12 */
+
+	0x11, 0x00, 0x00, 0x00, /* ICE_PPPOE 14 */
+	0x00, 0x2a,
+
+	0x00, 0x57,		/* PPP Link Layer 20 */
+
+	0x60, 0x00, 0x00, 0x00, /* ICE_IPV6_OFOS 22 */
+	0x00, 0x08, 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, 0x00, 0x00, /* ICE_UDP_ILOS 62 */
+	0x00, 0x08, 0x00, 0x00,
+
+	0x00, 0x00,		/* 2 bytes for 4 bytes alignment */
+};
+
 static const struct ice_dummy_pkt_profile ice_dummy_pkt_profiles[] = {
 	ICE_PKT_PROFILE(ipv6_gtp, ICE_PKT_TUN_GTPU | ICE_PKT_OUTER_IPV6 |
 				  ICE_PKT_GTP_NOPAY),
@@ -1135,6 +1284,11 @@ 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(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),
+	ICE_PKT_PROFILE(pppoe_ipv4_udp, ICE_PKT_PPPOE | ICE_PKT_INNER_UDP),
+	ICE_PKT_PROFILE(pppoe_ipv4_tcp, ICE_PKT_PPPOE),
 	ICE_PKT_PROFILE(gre_ipv6_tcp, ICE_PKT_TUN_NVGRE | ICE_PKT_INNER_IPV6 |
 				      ICE_PKT_INNER_TCP),
 	ICE_PKT_PROFILE(gre_tcp, ICE_PKT_TUN_NVGRE | ICE_PKT_INNER_TCP),
@@ -4480,6 +4634,7 @@ static const struct ice_prot_ext_tbl_entry ice_prot_ext[ICE_PROTOCOL_LAST] = {
 	{ ICE_NVGRE,		{ 0, 2, 4, 6 } },
 	{ ICE_GTP,		{ 8, 10, 12, 14, 16, 18, 20, 22 } },
 	{ ICE_GTP_NO_PAY,	{ 8, 10, 12, 14 } },
+	{ ICE_PPPOE,		{ 0, 2, 4, 6 } },
 	{ ICE_VLAN_EX,          { 2, 0 } },
 	{ ICE_VLAN_IN,          { 2, 0 } },
 };
@@ -4502,6 +4657,7 @@ 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_PPPOE,		ICE_PPPOE_HW },
 	{ ICE_VLAN_EX,          ICE_VLAN_OF_HW },
 	{ ICE_VLAN_IN,          ICE_VLAN_OL_HW },
 };
@@ -5580,6 +5736,12 @@ ice_find_dummy_packet(struct ice_adv_lkup_elem *lkups, u16 lkups_cnt,
 			match |= ICE_PKT_INNER_IPV6;
 		else if (lkups[i].type == ICE_GTP_NO_PAY)
 			match |= ICE_PKT_GTP_NOPAY;
+		else if (lkups[i].type == ICE_PPPOE) {
+			match |= ICE_PKT_PPPOE;
+			if (lkups[i].h_u.pppoe_hdr.ppp_prot_id ==
+			    htons(PPP_IPV6))
+				match |= ICE_PKT_OUTER_IPV6;
+		}
 	}
 
 	while (ret->match && (match & ret->match) != ret->match)
@@ -5677,6 +5839,9 @@ 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_PPPOE:
+			len = sizeof(struct ice_pppoe_hdr);
+			break;
 		default:
 			return -EINVAL;
 		}

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

@@ -54,6 +54,11 @@ ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers,
 	if (flags & ICE_TC_FLWR_FIELD_CVLAN)
 		lkups_cnt++;
 
+	/* are PPPoE options specified? */
+	if (flags & (ICE_TC_FLWR_FIELD_PPPOE_SESSID |
+		     ICE_TC_FLWR_FIELD_PPP_PROTO))
+		lkups_cnt++;
+
 	/* are IPv[4|6] fields specified? */
 	if (flags & (ICE_TC_FLWR_FIELD_DEST_IPV4 | ICE_TC_FLWR_FIELD_SRC_IPV4 |
 		     ICE_TC_FLWR_FIELD_DEST_IPV6 | ICE_TC_FLWR_FIELD_SRC_IPV6))
@@ -350,6 +355,28 @@ ice_tc_fill_rules(struct ice_hw *hw, u32 flags,
 		i++;
 	}
 
+	if (flags & (ICE_TC_FLWR_FIELD_PPPOE_SESSID |
+		     ICE_TC_FLWR_FIELD_PPP_PROTO)) {
+		struct ice_pppoe_hdr *vals, *masks;
+
+		vals = &list[i].h_u.pppoe_hdr;
+		masks = &list[i].m_u.pppoe_hdr;
+
+		list[i].type = ICE_PPPOE;
+
+		if (flags & ICE_TC_FLWR_FIELD_PPPOE_SESSID) {
+			vals->session_id = headers->pppoe_hdr.session_id;
+			masks->session_id = cpu_to_be16(0xFFFF);
+		}
+
+		if (flags & ICE_TC_FLWR_FIELD_PPP_PROTO) {
+			vals->ppp_prot_id = headers->pppoe_hdr.ppp_proto;
+			masks->ppp_prot_id = cpu_to_be16(0xFFFF);
+		}
+
+		i++;
+	}
+
 	/* copy L3 (IPv[4|6]: src, dest) address */
 	if (flags & (ICE_TC_FLWR_FIELD_DEST_IPV4 |
 		     ICE_TC_FLWR_FIELD_SRC_IPV4)) {
@@ -693,6 +720,31 @@ exit:
 	return ret;
 }
 
+/**
+ * ice_tc_set_pppoe - Parse PPPoE fields from TC flower filter
+ * @match: Pointer to flow match structure
+ * @fltr: Pointer to filter structure
+ * @headers: Pointer to outer header fields
+ * @returns PPP protocol used in filter (ppp_ses or ppp_disc)
+ */
+static u16
+ice_tc_set_pppoe(struct flow_match_pppoe *match,
+		 struct ice_tc_flower_fltr *fltr,
+		 struct ice_tc_flower_lyr_2_4_hdrs *headers)
+{
+	if (match->mask->session_id) {
+		fltr->flags |= ICE_TC_FLWR_FIELD_PPPOE_SESSID;
+		headers->pppoe_hdr.session_id = match->key->session_id;
+	}
+
+	if (match->mask->ppp_proto) {
+		fltr->flags |= ICE_TC_FLWR_FIELD_PPP_PROTO;
+		headers->pppoe_hdr.ppp_proto = match->key->ppp_proto;
+	}
+
+	return be16_to_cpu(match->key->type);
+}
+
 /**
  * ice_tc_set_ipv4 - Parse IPv4 addresses from TC flower filter
  * @match: Pointer to flow match structure
@@ -988,7 +1040,8 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi,
 	      BIT(FLOW_DISSECTOR_KEY_ENC_PORTS) |
 	      BIT(FLOW_DISSECTOR_KEY_ENC_OPTS) |
 	      BIT(FLOW_DISSECTOR_KEY_ENC_IP) |
-	      BIT(FLOW_DISSECTOR_KEY_PORTS))) {
+	      BIT(FLOW_DISSECTOR_KEY_PORTS) |
+	      BIT(FLOW_DISSECTOR_KEY_PPPOE))) {
 		NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported key used");
 		return -EOPNOTSUPP;
 	}
@@ -1124,6 +1177,22 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi,
 			headers->cvlan_hdr.vlan_prio = match.key->vlan_priority;
 	}
 
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PPPOE)) {
+		struct flow_match_pppoe match;
+
+		flow_rule_match_pppoe(rule, &match);
+		n_proto_key = ice_tc_set_pppoe(&match, fltr, headers);
+
+		/* If ethertype equals ETH_P_PPP_SES, n_proto might be
+		 * overwritten by encapsulated protocol (ppp_proto field) or set
+		 * to 0. To correct this, flow_match_pppoe provides the type
+		 * field, which contains the actual ethertype (ETH_P_PPP_SES).
+		 */
+		headers->l2_key.n_proto = cpu_to_be16(n_proto_key);
+		headers->l2_mask.n_proto = cpu_to_be16(0xFFFF);
+		fltr->flags |= ICE_TC_FLWR_FIELD_ETH_TYPE_ID;
+	}
+
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
 		struct flow_match_control match;
 

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

@@ -24,6 +24,8 @@
 #define ICE_TC_FLWR_FIELD_ETH_TYPE_ID		BIT(17)
 #define ICE_TC_FLWR_FIELD_ENC_OPTS		BIT(18)
 #define ICE_TC_FLWR_FIELD_CVLAN			BIT(19)
+#define ICE_TC_FLWR_FIELD_PPPOE_SESSID		BIT(20)
+#define ICE_TC_FLWR_FIELD_PPP_PROTO		BIT(21)
 
 #define ICE_TC_FLOWER_MASK_32   0xFFFFFFFF
 
@@ -44,6 +46,11 @@ struct ice_tc_vlan_hdr {
 	__be16 vlan_tpid;
 };
 
+struct ice_tc_pppoe_hdr {
+	__be16 session_id;
+	__be16 ppp_proto;
+};
+
 struct ice_tc_l2_hdr {
 	u8 dst_mac[ETH_ALEN];
 	u8 src_mac[ETH_ALEN];
@@ -84,6 +91,7 @@ struct ice_tc_flower_lyr_2_4_hdrs {
 	struct ice_tc_l2_hdr l2_mask;
 	struct ice_tc_vlan_hdr vlan_hdr;
 	struct ice_tc_vlan_hdr cvlan_hdr;
+	struct ice_tc_pppoe_hdr pppoe_hdr;
 	/* L3 (IPv4[6]) layer fields with their mask */
 	struct ice_tc_l3_hdr l3_key;
 	struct ice_tc_l3_hdr l3_mask;

include/linux/ppp_defs.h

@@ -11,4 +11,18 @@
 #include <uapi/linux/ppp_defs.h>
 
 #define PPP_FCS(fcs, c) crc_ccitt_byte(fcs, c)
+
+/**
+ * ppp_proto_is_valid - checks if PPP protocol is valid
+ * @proto: PPP protocol
+ *
+ * Assumes proto is not compressed.
+ * Protocol is valid if the value is odd and the least significant bit of the
+ * most significant octet is 0 (see RFC 1661, section 2).
+ */
+static inline bool ppp_proto_is_valid(u16 proto)
+{
+	return !!((proto & 0x0101) == 0x0001);
+}
+
 #endif /* _PPP_DEFS_H_ */

include/net/flow_dissector.h

@@ -277,6 +277,18 @@ struct flow_dissector_key_num_of_vlans {
 	u8 num_of_vlans;
 };
 
+/**
+ * struct flow_dissector_key_pppoe:
+ * @session_id: pppoe session id
+ * @ppp_proto: ppp protocol
+ * @type: pppoe eth type
+ */
+struct flow_dissector_key_pppoe {
+	__be16 session_id;
+	__be16 ppp_proto;
+	__be16 type;
+};
+
 enum flow_dissector_key_id {
 	FLOW_DISSECTOR_KEY_CONTROL, /* struct flow_dissector_key_control */
 	FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */
@@ -307,6 +319,7 @@ enum flow_dissector_key_id {
 	FLOW_DISSECTOR_KEY_CT, /* struct flow_dissector_key_ct */
 	FLOW_DISSECTOR_KEY_HASH, /* struct flow_dissector_key_hash */
 	FLOW_DISSECTOR_KEY_NUM_OF_VLANS, /* struct flow_dissector_key_num_of_vlans */
+	FLOW_DISSECTOR_KEY_PPPOE, /* struct flow_dissector_key_pppoe */
 
 	FLOW_DISSECTOR_KEY_MAX,
 };

include/net/flow_offload.h

@@ -76,6 +76,10 @@ struct flow_match_ct {
 	struct flow_dissector_key_ct *key, *mask;
 };
 
+struct flow_match_pppoe {
+	struct flow_dissector_key_pppoe *key, *mask;
+};
+
 struct flow_rule;
 
 void flow_rule_match_meta(const struct flow_rule *rule,
@@ -122,6 +126,8 @@ void flow_rule_match_enc_opts(const struct flow_rule *rule,
 			      struct flow_match_enc_opts *out);
 void flow_rule_match_ct(const struct flow_rule *rule,
 			struct flow_match_ct *out);
+void flow_rule_match_pppoe(const struct flow_rule *rule,
+			   struct flow_match_pppoe *out);
 
 enum flow_action_id {
 	FLOW_ACTION_ACCEPT		= 0,

include/uapi/linux/pkt_cls.h

@@ -589,6 +589,9 @@ enum {
 
 	TCA_FLOWER_KEY_NUM_OF_VLANS,    /* u8 */
 
+	TCA_FLOWER_KEY_PPPOE_SID,	/* be16 */
+	TCA_FLOWER_KEY_PPP_PROTO,	/* be16 */
+
 	__TCA_FLOWER_MAX,
 };
 

net/core/flow_dissector.c

@@ -895,6 +895,11 @@ bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,
 	return result == BPF_OK;
 }
 
+static bool is_pppoe_ses_hdr_valid(struct pppoe_hdr hdr)
+{
+	return hdr.ver == 1 && hdr.type == 1 && hdr.code == 0;
+}
+
 /**
  * __skb_flow_dissect - extract the flow_keys struct and return it
  * @net: associated network namespace, derived from @skb if NULL
@@ -1214,26 +1219,60 @@ proto_again:
 			struct pppoe_hdr hdr;
 			__be16 proto;
 		} *hdr, _hdr;
+		u16 ppp_proto;
+
 		hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
 		if (!hdr) {
 			fdret = FLOW_DISSECT_RET_OUT_BAD;
 			break;
 		}
 
-		nhoff += PPPOE_SES_HLEN;
+		if (!is_pppoe_ses_hdr_valid(hdr->hdr)) {
-		switch (hdr->proto) {
-		case htons(PPP_IP):
-			proto = htons(ETH_P_IP);
-			fdret = FLOW_DISSECT_RET_PROTO_AGAIN;
-			break;
-		case htons(PPP_IPV6):
-			proto = htons(ETH_P_IPV6);
-			fdret = FLOW_DISSECT_RET_PROTO_AGAIN;
-			break;
-		default:
 			fdret = FLOW_DISSECT_RET_OUT_BAD;
 			break;
 		}
+
+		/* least significant bit of the most significant octet
+		 * indicates if protocol field was compressed
+		 */
+		ppp_proto = ntohs(hdr->proto);
+		if (ppp_proto & 0x0100) {
+			ppp_proto = ppp_proto >> 8;
+			nhoff += PPPOE_SES_HLEN - 1;
+		} else {
+			nhoff += PPPOE_SES_HLEN;
+		}
+
+		if (ppp_proto == PPP_IP) {
+			proto = htons(ETH_P_IP);
+			fdret = FLOW_DISSECT_RET_PROTO_AGAIN;
+		} else if (ppp_proto == PPP_IPV6) {
+			proto = htons(ETH_P_IPV6);
+			fdret = FLOW_DISSECT_RET_PROTO_AGAIN;
+		} else if (ppp_proto == PPP_MPLS_UC) {
+			proto = htons(ETH_P_MPLS_UC);
+			fdret = FLOW_DISSECT_RET_PROTO_AGAIN;
+		} else if (ppp_proto == PPP_MPLS_MC) {
+			proto = htons(ETH_P_MPLS_MC);
+			fdret = FLOW_DISSECT_RET_PROTO_AGAIN;
+		} else if (ppp_proto_is_valid(ppp_proto)) {
+			fdret = FLOW_DISSECT_RET_OUT_GOOD;
+		} else {
+			fdret = FLOW_DISSECT_RET_OUT_BAD;
+			break;
+		}
+
+		if (dissector_uses_key(flow_dissector,
+				       FLOW_DISSECTOR_KEY_PPPOE)) {
+			struct flow_dissector_key_pppoe *key_pppoe;
+
+			key_pppoe = skb_flow_dissector_target(flow_dissector,
+							      FLOW_DISSECTOR_KEY_PPPOE,
+							      target_container);
+			key_pppoe->session_id = hdr->hdr.sid;
+			key_pppoe->ppp_proto = htons(ppp_proto);
+			key_pppoe->type = htons(ETH_P_PPP_SES);
+		}
 		break;
 	}
 	case htons(ETH_P_TIPC): {

net/core/flow_offload.c

@@ -230,6 +230,13 @@ void flow_rule_match_ct(const struct flow_rule *rule,
 }
 EXPORT_SYMBOL(flow_rule_match_ct);
 
+void flow_rule_match_pppoe(const struct flow_rule *rule,
+			   struct flow_match_pppoe *out)
+{
+	FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_PPPOE, out);
+}
+EXPORT_SYMBOL(flow_rule_match_pppoe);
+
 struct flow_block_cb *flow_block_cb_alloc(flow_setup_cb_t *cb,
 					  void *cb_ident, void *cb_priv,
 					  void (*release)(void *cb_priv))

net/sched/cls_flower.c

@@ -16,6 +16,7 @@
 #include <linux/in6.h>
 #include <linux/ip.h>
 #include <linux/mpls.h>
+#include <linux/ppp_defs.h>
 
 #include <net/sch_generic.h>
 #include <net/pkt_cls.h>
@@ -67,6 +68,7 @@ struct fl_flow_key {
 	struct flow_dissector_key_ct ct;
 	struct flow_dissector_key_hash hash;
 	struct flow_dissector_key_num_of_vlans num_of_vlans;
+	struct flow_dissector_key_pppoe pppoe;
 } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
 
 struct fl_flow_mask_range {
@@ -708,6 +710,8 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
 	[TCA_FLOWER_KEY_HASH]		= { .type = NLA_U32 },
 	[TCA_FLOWER_KEY_HASH_MASK]	= { .type = NLA_U32 },
 	[TCA_FLOWER_KEY_NUM_OF_VLANS]	= { .type = NLA_U8 },
+	[TCA_FLOWER_KEY_PPPOE_SID]	= { .type = NLA_U16 },
+	[TCA_FLOWER_KEY_PPP_PROTO]	= { .type = NLA_U16 },
 
 };
 
@@ -1035,6 +1039,50 @@ static void fl_set_key_vlan(struct nlattr **tb,
 	}
 }
 
+static void fl_set_key_pppoe(struct nlattr **tb,
+			     struct flow_dissector_key_pppoe *key_val,
+			     struct flow_dissector_key_pppoe *key_mask,
+			     struct fl_flow_key *key,
+			     struct fl_flow_key *mask)
+{
+	/* key_val::type must be set to ETH_P_PPP_SES
+	 * because ETH_P_PPP_SES was stored in basic.n_proto
+	 * which might get overwritten by ppp_proto
+	 * or might be set to 0, the role of key_val::type
+	 * is simmilar to vlan_key::tpid
+	 */
+	key_val->type = htons(ETH_P_PPP_SES);
+	key_mask->type = cpu_to_be16(~0);
+
+	if (tb[TCA_FLOWER_KEY_PPPOE_SID]) {
+		key_val->session_id =
+			nla_get_be16(tb[TCA_FLOWER_KEY_PPPOE_SID]);
+		key_mask->session_id = cpu_to_be16(~0);
+	}
+	if (tb[TCA_FLOWER_KEY_PPP_PROTO]) {
+		key_val->ppp_proto =
+			nla_get_be16(tb[TCA_FLOWER_KEY_PPP_PROTO]);
+		key_mask->ppp_proto = cpu_to_be16(~0);
+
+		if (key_val->ppp_proto == htons(PPP_IP)) {
+			key->basic.n_proto = htons(ETH_P_IP);
+			mask->basic.n_proto = cpu_to_be16(~0);
+		} else if (key_val->ppp_proto == htons(PPP_IPV6)) {
+			key->basic.n_proto = htons(ETH_P_IPV6);
+			mask->basic.n_proto = cpu_to_be16(~0);
+		} else if (key_val->ppp_proto == htons(PPP_MPLS_UC)) {
+			key->basic.n_proto = htons(ETH_P_MPLS_UC);
+			mask->basic.n_proto = cpu_to_be16(~0);
+		} else if (key_val->ppp_proto == htons(PPP_MPLS_MC)) {
+			key->basic.n_proto = htons(ETH_P_MPLS_MC);
+			mask->basic.n_proto = cpu_to_be16(~0);
+		}
+	} else {
+		key->basic.n_proto = 0;
+		mask->basic.n_proto = cpu_to_be16(0);
+	}
+}
+
 static void fl_set_key_flag(u32 flower_key, u32 flower_mask,
 			    u32 *dissector_key, u32 *dissector_mask,
 			    u32 flower_flag_bit, u32 dissector_flag_bit)
@@ -1645,6 +1693,9 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
 		}
 	}
 
+	if (key->basic.n_proto == htons(ETH_P_PPP_SES))
+		fl_set_key_pppoe(tb, &key->pppoe, &mask->pppoe, key, mask);
+
 	if (key->basic.n_proto == htons(ETH_P_IP) ||
 	    key->basic.n_proto == htons(ETH_P_IPV6)) {
 		fl_set_key_val(tb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO,
@@ -1917,6 +1968,8 @@ static void fl_init_dissector(struct flow_dissector *dissector,
 			     FLOW_DISSECTOR_KEY_HASH, hash);
 	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_NUM_OF_VLANS, num_of_vlans);
+	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
+			     FLOW_DISSECTOR_KEY_PPPOE, pppoe);
 
 	skb_flow_dissector_init(dissector, keys, cnt);
 }
@@ -3045,6 +3098,17 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net,
 	    fl_dump_key_ip(skb, false, &key->ip, &mask->ip)))
 		goto nla_put_failure;
 
+	if (mask->pppoe.session_id) {
+		if (nla_put_be16(skb, TCA_FLOWER_KEY_PPPOE_SID,
+				 key->pppoe.session_id))
+			goto nla_put_failure;
+	}
+	if (mask->basic.n_proto && mask->pppoe.ppp_proto) {
+		if (nla_put_be16(skb, TCA_FLOWER_KEY_PPP_PROTO,
+				 key->pppoe.ppp_proto))
+			goto nla_put_failure;
+	}
+
 	if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS &&
 	    (fl_dump_key_val(skb, &key->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC,
 			     &mask->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC_MASK,