flow_dissector: Parse multiple MPLS Label Stack Entries

The current MPLS dissector only parses the first MPLS Label Stack
Entry (second LSE can be parsed too, but only to set a key_id).

This patch adds the possibility to parse several LSEs by making
__skb_flow_dissect_mpls() return FLOW_DISSECT_RET_PROTO_AGAIN as long
as the Bottom Of Stack bit hasn't been seen, up to a maximum of
FLOW_DIS_MPLS_MAX entries.

FLOW_DIS_MPLS_MAX is arbitrarily set to 7. This should be enough for
many practical purposes, without wasting too much space.

To record the parsed values, flow_dissector_key_mpls is modified to
store an array of stack entries, instead of just the values of the
first one. A bit field, "used_lses", is also added to keep track of
the LSEs that have been set. The objective is to avoid defining a
new FLOW_DISSECTOR_KEY_MPLS_XX for each level of the MPLS stack.

TC flower is adapted for the new struct flow_dissector_key_mpls layout.
Matching on several MPLS Label Stack Entries will be added in the next
patch.

The NFP and MLX5 drivers are also adapted: nfp_flower_compile_mac() and
mlx5's parse_tunnel() now verify that the rule only uses the first LSE
and fail if it doesn't.

Finally, the behaviour of the FLOW_DISSECTOR_KEY_MPLS_ENTROPY key is
slightly modified. Instead of recording the first Entropy Label, it
now records the last one. This shouldn't have any consequences since
there doesn't seem to have any user of FLOW_DISSECTOR_KEY_MPLS_ENTROPY
in the tree. We'd probably better do a hash of all parsed MPLS labels
instead (excluding reserved labels) anyway. That'd give better entropy
and would probably also simplify the code. But that's not the purpose
of this patch, so I'm keeping that as a future possible improvement.

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 69 insertions, 32 deletions

diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 5dceed467f64..0aeb33572feb 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -480,47 +480,59 @@ EXPORT_SYMBOL(skb_flow_dissect_tunnel_info);
 static enum flow_dissect_ret
 __skb_flow_dissect_mpls(const struct sk_buff *skb,
 			struct flow_dissector *flow_dissector,
-			void *target_container, void *data, int nhoff, int hlen)
+			void *target_container, void *data, int nhoff, int hlen,
+			int lse_index, bool *entropy_label)
 {
-	struct flow_dissector_key_keyid *key_keyid;
-	struct mpls_label *hdr, _hdr[2];
-	u32 entry, label;
+	struct mpls_label *hdr, _hdr;
+	u32 entry, label, bos;
 
 	if (!dissector_uses_key(flow_dissector,
 				FLOW_DISSECTOR_KEY_MPLS_ENTROPY) &&
 	    !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS))
 		return FLOW_DISSECT_RET_OUT_GOOD;
 
+	if (lse_index >= FLOW_DIS_MPLS_MAX)
+		return FLOW_DISSECT_RET_OUT_GOOD;
+
 	hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data,
 				   hlen, &_hdr);
 	if (!hdr)
 		return FLOW_DISSECT_RET_OUT_BAD;
 
-	entry = ntohl(hdr[0].entry);
+	entry = ntohl(hdr->entry);
 	label = (entry & MPLS_LS_LABEL_MASK) >> MPLS_LS_LABEL_SHIFT;
+	bos = (entry & MPLS_LS_S_MASK) >> MPLS_LS_S_SHIFT;
 
 	if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS)) {
 		struct flow_dissector_key_mpls *key_mpls;
+		struct flow_dissector_mpls_lse *lse;
 
 		key_mpls = skb_flow_dissector_target(flow_dissector,
 						     FLOW_DISSECTOR_KEY_MPLS,
 						     target_container);
-		key_mpls->mpls_label = label;
-		key_mpls->mpls_ttl = (entry & MPLS_LS_TTL_MASK)
-					>> MPLS_LS_TTL_SHIFT;
-		key_mpls->mpls_tc = (entry & MPLS_LS_TC_MASK)
-					>> MPLS_LS_TC_SHIFT;
-		key_mpls->mpls_bos = (entry & MPLS_LS_S_MASK)
-					>> MPLS_LS_S_SHIFT;
+		lse = &key_mpls->ls[lse_index];
+
+		lse->mpls_ttl = (entry & MPLS_LS_TTL_MASK) >> MPLS_LS_TTL_SHIFT;
+		lse->mpls_bos = bos;
+		lse->mpls_tc = (entry & MPLS_LS_TC_MASK) >> MPLS_LS_TC_SHIFT;
+		lse->mpls_label = label;
+		dissector_set_mpls_lse(key_mpls, lse_index);
 	}
 
-	if (label == MPLS_LABEL_ENTROPY) {
+	if (*entropy_label &&
+	    dissector_uses_key(flow_dissector,
+			       FLOW_DISSECTOR_KEY_MPLS_ENTROPY)) {
+		struct flow_dissector_key_keyid *key_keyid;
+
 		key_keyid = skb_flow_dissector_target(flow_dissector,
 						      FLOW_DISSECTOR_KEY_MPLS_ENTROPY,
 						      target_container);
-		key_keyid->keyid = hdr[1].entry & htonl(MPLS_LS_LABEL_MASK);
+		key_keyid->keyid = cpu_to_be32(label);
 	}
-	return FLOW_DISSECT_RET_OUT_GOOD;
+
+	*entropy_label = label == MPLS_LABEL_ENTROPY;
+
+	return bos ? FLOW_DISSECT_RET_OUT_GOOD : FLOW_DISSECT_RET_PROTO_AGAIN;
 }
 
 static enum flow_dissect_ret
@@ -979,6 +991,8 @@ bool __skb_flow_dissect(const struct net *net,
 	struct bpf_prog *attached = NULL;
 	enum flow_dissect_ret fdret;
 	enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX;
+	bool mpls_el = false;
+	int mpls_lse = 0;
 	int num_hdrs = 0;
 	u8 ip_proto = 0;
 	bool ret;
@@ -1278,7 +1292,10 @@ proto_again:
 	case htons(ETH_P_MPLS_MC):
 		fdret = __skb_flow_dissect_mpls(skb, flow_dissector,
 						target_container, data,
-						nhoff, hlen);
+						nhoff, hlen, mpls_lse,
+						&mpls_el);
+		nhoff += sizeof(struct mpls_label);
+		mpls_lse++;
 		break;
 	case htons(ETH_P_FCOE):
 		if ((hlen - nhoff) < FCOE_HEADER_LEN) {
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 0c574700da75..f524afe0b7f5 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -781,9 +781,17 @@ static int fl_set_key_mpls(struct nlattr **tb,
 			   struct flow_dissector_key_mpls *key_mask,
 			   struct netlink_ext_ack *extack)
 {
+	struct flow_dissector_mpls_lse *lse_mask;
+	struct flow_dissector_mpls_lse *lse_val;
+
+	lse_val = &key_val->ls[0];
+	lse_mask = &key_mask->ls[0];
+
 	if (tb[TCA_FLOWER_KEY_MPLS_TTL]) {
-		key_val->mpls_ttl = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_TTL]);
-		key_mask->mpls_ttl = MPLS_TTL_MASK;
+		lse_val->mpls_ttl = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_TTL]);
+		lse_mask->mpls_ttl = MPLS_TTL_MASK;
+		dissector_set_mpls_lse(key_val, 0);
+		dissector_set_mpls_lse(key_mask, 0);
 	}
 	if (tb[TCA_FLOWER_KEY_MPLS_BOS]) {
 		u8 bos = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_BOS]);
@@ -794,8 +802,10 @@ static int fl_set_key_mpls(struct nlattr **tb,
 					    "Bottom Of Stack (BOS) must be 0 or 1");
 			return -EINVAL;
 		}
-		key_val->mpls_bos = bos;
-		key_mask->mpls_bos = MPLS_BOS_MASK;
+		lse_val->mpls_bos = bos;
+		lse_mask->mpls_bos = MPLS_BOS_MASK;
+		dissector_set_mpls_lse(key_val, 0);
+		dissector_set_mpls_lse(key_mask, 0);
 	}
 	if (tb[TCA_FLOWER_KEY_MPLS_TC]) {
 		u8 tc = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_TC]);
@@ -806,8 +816,10 @@ static int fl_set_key_mpls(struct nlattr **tb,
 					    "Traffic Class (TC) must be between 0 and 7");
 			return -EINVAL;
 		}
-		key_val->mpls_tc = tc;
-		key_mask->mpls_tc = MPLS_TC_MASK;
+		lse_val->mpls_tc = tc;
+		lse_mask->mpls_tc = MPLS_TC_MASK;
+		dissector_set_mpls_lse(key_val, 0);
+		dissector_set_mpls_lse(key_mask, 0);
 	}
 	if (tb[TCA_FLOWER_KEY_MPLS_LABEL]) {
 		u32 label = nla_get_u32(tb[TCA_FLOWER_KEY_MPLS_LABEL]);
@@ -818,8 +830,10 @@ static int fl_set_key_mpls(struct nlattr **tb,
 					    "Label must be between 0 and 1048575");
 			return -EINVAL;
 		}
-		key_val->mpls_label = label;
-		key_mask->mpls_label = MPLS_LABEL_MASK;
+		lse_val->mpls_label = label;
+		lse_mask->mpls_label = MPLS_LABEL_MASK;
+		dissector_set_mpls_lse(key_val, 0);
+		dissector_set_mpls_lse(key_mask, 0);
 	}
 	return 0;
 }
@@ -2222,31 +2236,37 @@ static int fl_dump_key_mpls(struct sk_buff *skb,
 			    struct flow_dissector_key_mpls *mpls_key,
 			    struct flow_dissector_key_mpls *mpls_mask)
 {
+	struct flow_dissector_mpls_lse *lse_mask;
+	struct flow_dissector_mpls_lse *lse_key;
 	int err;
 
 	if (!memchr_inv(mpls_mask, 0, sizeof(*mpls_mask)))
 		return 0;
-	if (mpls_mask->mpls_ttl) {
+
+	lse_mask = &mpls_mask->ls[0];
+	lse_key = &mpls_key->ls[0];
+
+	if (lse_mask->mpls_ttl) {
 		err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_TTL,
-				 mpls_key->mpls_ttl);
+				 lse_key->mpls_ttl);
 		if (err)
 			return err;
 	}
-	if (mpls_mask->mpls_tc) {
+	if (lse_mask->mpls_tc) {
 		err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_TC,
-				 mpls_key->mpls_tc);
+				 lse_key->mpls_tc);
 		if (err)
 			return err;
 	}
-	if (mpls_mask->mpls_label) {
+	if (lse_mask->mpls_label) {
 		err = nla_put_u32(skb, TCA_FLOWER_KEY_MPLS_LABEL,
-				  mpls_key->mpls_label);
+				  lse_key->mpls_label);
 		if (err)
 			return err;
 	}
-	if (mpls_mask->mpls_bos) {
+	if (lse_mask->mpls_bos) {
 		err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_BOS,
-				 mpls_key->mpls_bos);
+				 lse_key->mpls_bos);
 		if (err)
 			return err;
 	}