Unwrap VLAN (802.1Q/802.1ad) tags before protocol dispatch

The single highest-value coverage gap so far, and structural rather
than a new dissector: a VLAN-tagged frame's ethertype reads as 0x8100,
so every existing decoder - ARP, IPv4, IPv6, and everything built on
top of them - was completely invisible on any tagged network.

walk_vlan_tags() (ethernet.hpp) is composable and separate from
parse_ethernet(), the same relationship walk_ipv6_extension_headers()
has to parse_ipv6(): the base parse stays an unconditional fixed-header
decode, and this is what a caller reaches for when it needs the real
protocol underneath. Handles stacked (QinQ) tags, bounded at 4 levels
against a corrupt/hostile frame claiming an unbounded chain.

Live-verified with genuine kernel-tagged frames, not synthetic bytes:
a dummy0 interface with an 802.1Q dummy0.42 sub-interface (VLAN 42),
captured on the parent while pinging out the sub-interface. Both
interfaces and the kernel modules they pulled in were torn down
afterward.

2 files changed, 73 insertions, 0 deletions

diff --git a/tests/test_net.cpp b/tests/test_net.cpp
index 19667da..2702758 100644
--- a/tests/test_net.cpp
+++ b/tests/test_net.cpp
@@ -30,6 +30,63 @@ TEST_CASE("parse_ethernet rejects a frame shorter than the header") {
     CHECK_FALSE(parse_ethernet(bytes).has_value());
 }
 
+TEST_CASE("walk_vlan_tags passes an untagged ethertype through unchanged") {
+    std::vector<unsigned char> payload = {0xDE, 0xAD, 0xBE, 0xEF};
+    auto result = walk_vlan_tags(kEthertypeIPv4, payload);
+    CHECK(result.vlan_ids.empty());
+    CHECK(result.ethertype == kEthertypeIPv4);
+    REQUIRE(result.payload.size() == 4);
+    CHECK(result.payload[0] == 0xDE);
+}
+
+TEST_CASE("walk_vlan_tags unwraps a single 802.1Q tag") {
+    std::vector<unsigned char> payload = {
+        0x00, 42,    // TCI: VLAN ID 42 (PCP/DEI bits left zero)
+        0x08, 0x00,  // real ethertype: IPv4
+        0xDE, 0xAD,  // real payload
+    };
+    auto result = walk_vlan_tags(kEthertypeVlan, payload);
+    REQUIRE(result.vlan_ids.size() == 1);
+    CHECK(result.vlan_ids[0] == 42);
+    CHECK(result.ethertype == kEthertypeIPv4);
+    REQUIRE(result.payload.size() == 2);
+    CHECK(result.payload[0] == 0xDE);
+}
+
+TEST_CASE("walk_vlan_tags unwraps a stacked QinQ pair, outer to inner") {
+    std::vector<unsigned char> payload = {
+        0x00, 100,        // outer TCI: VLAN 100
+        0x81, 0x00,       // inner tag's TPID
+        0x00, 42,         // inner TCI: VLAN 42
+        0x08, 0x00,       // real ethertype: IPv4
+        0xBE, 0xEF,
+    };
+    auto result = walk_vlan_tags(kEthertypeVlanQinQ, payload);
+    REQUIRE(result.vlan_ids.size() == 2);
+    CHECK(result.vlan_ids[0] == 100);
+    CHECK(result.vlan_ids[1] == 42);
+    CHECK(result.ethertype == kEthertypeIPv4);
+}
+
+TEST_CASE("walk_vlan_tags stops at a truncated tag rather than reading past it") {
+    std::vector<unsigned char> payload = {0x00, 42};  // 2 bytes: not a full 4-byte tag
+    auto result = walk_vlan_tags(kEthertypeVlan, payload);
+    CHECK(result.vlan_ids.empty());
+    CHECK(result.ethertype == kEthertypeVlan);  // unchanged: nothing was actually unwrapped
+}
+
+TEST_CASE("walk_vlan_tags is bounded against a claimed unbounded tag chain") {
+    // Each 4-byte block claims "the next ethertype is another VLAN
+    // tag" - a corrupt/hostile frame that never actually reaches a
+    // real ethertype. Must stop, not loop indefinitely.
+    std::vector<unsigned char> payload;
+    for (int i = 0; i < 100; ++i) {
+        payload.insert(payload.end(), {0x00, 0x01, 0x81, 0x00});
+    }
+    auto result = walk_vlan_tags(kEthertypeVlan, payload);
+    CHECK(result.vlan_ids.size() <= 4);
+}
+
 TEST_CASE("parse_ipv4 decodes header fields and leaves the right payload") {
     std::vector<unsigned char> bytes(20, 0);
     bytes[0] = 0x45;  // version 4, IHL 5 (20-byte header, no options)
diff --git a/tests/test_summarize.cpp b/tests/test_summarize.cpp
index 27e0dd3..d7b223a 100644
--- a/tests/test_summarize.cpp
+++ b/tests/test_summarize.cpp
@@ -186,6 +186,22 @@ TEST_CASE("summarize_packet decodes an ARP request end to end") {
           "ARP who-has 10.0.0.2 tell 10.0.0.1 (aa:bb:cc:dd:ee:ff)");
 }
 
+TEST_CASE("summarize_packet unwraps a VLAN tag to reach the real ARP payload underneath") {
+    std::vector<unsigned char> bytes = {
+        0x11, 0x22, 0x33, 0x44, 0x55, 0x66, 0xAA, 0xBB, 0xCC, 0xDD, 0xEE, 0xFF,
+        0x81, 0x00,        // ethertype: 802.1Q
+        0x00, 42,          // TCI: VLAN 42
+        0x08, 0x06,        // real ethertype: ARP
+        0x00, 0x01, 0x08, 0x00, 0x06, 0x04, 0x00, 0x01,
+        0xAA, 0xBB, 0xCC, 0xDD, 0xEE, 0xFF, 10, 0, 0, 1,
+        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 10, 0, 0, 2,
+    };
+    auto line = packeteer::summarize_packet(bytes, DLT_EN10MB);
+    CHECK(line ==
+          "ETH aa:bb:cc:dd:ee:ff -> 11:22:33:44:55:66 ethertype=0x8100 vlan=42 | "
+          "ARP who-has 10.0.0.2 tell 10.0.0.1 (aa:bb:cc:dd:ee:ff)");
+}
+
 TEST_CASE("hex_dump_lines produces one line per 16 bytes, with the right byte count") {
     std::vector<unsigned char> bytes(20, 0);
     for (std::size_t i = 0; i < bytes.size(); ++i) bytes[i] = static_cast<unsigned char>(i);