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>

3 files changed, 117 insertions, 7 deletions

diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 6aee04f75e3e..237d396b6e41 100644
--- a/net/core/flow_dissector.c
+++ b/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;
-		switch (hdr->proto) {
-		case htons(PPP_IP):
+		if (!is_pppoe_ses_hdr_valid(hdr->hdr)) {
+			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;
-			break;
-		case htons(PPP_IPV6):
+		} else if (ppp_proto == PPP_IPV6) {
 			proto = htons(ETH_P_IPV6);
 			fdret = FLOW_DISSECT_RET_PROTO_AGAIN;
-			break;
-		default:
+		} 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): {
diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c
index 0d3075d3c8fb..8cfb63528d18 100644
--- a/net/core/flow_offload.c
+++ b/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))
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 1a1e34480b7e..041d63ff809a 100644
--- a/net/sched/cls_flower.c
+++ b/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,