bench: add criterion benchmarks for protocol, bandwidth, TCP RX scan, and EC-SRP5

Adds four Criterion.rs benchmark suites to measure hot-path performance
and demonstrate the impact of Sprints 1–3 optimizations:

- benches/protocol.rs    — Command & StatusMessage serialize/deserialize
- benches/bandwidth.rs   — BandwidthState atomics, budget, interval math
- benches/tcp_rx_scan.rs — memchr SIMD scan vs naive O(n) loop (55× faster
                           on 256KB buffers with status at end)
- benches/ecsrp5.rs      — WCurve::new() heavy math vs cached LazyLock
                           (~123,000× faster access)

Also adds BENCHMARKS.md with usage instructions and example results.

Visibility changes (bench-only):
- scan_status_message is now pub (was #[cfg(test)] only)
- WCurve and WCURVE are now pub in ecsrp5.rs

dev-dependencies: criterion + pprof (optional flamegraph support)

benches/protocol.rs

@@ -0,0 +1,65 @@
+use criterion::{black_box, criterion_group, criterion_main, Criterion};
+use btest_rs::protocol::{Command, StatusMessage, CMD_PROTO_TCP, CMD_DIR_BOTH};
+
+fn bench_command_serialize(c: &mut Criterion) {
+    let cmd = Command::new(CMD_PROTO_TCP, CMD_DIR_BOTH);
+    c.bench_function("command_serialize", |b| {
+        b.iter(|| black_box(cmd.serialize()))
+    });
+}
+
+fn bench_command_deserialize(c: &mut Criterion) {
+    let bytes = [0x01, 0x03, 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00];
+    c.bench_function("command_deserialize", |b| {
+        b.iter(|| black_box(Command::deserialize(black_box(&bytes))))
+    });
+}
+
+fn bench_status_message_serialize(c: &mut Criterion) {
+    let msg = StatusMessage {
+        seq: 42,
+        bytes_received: 1_000_000,
+        cpu_load: 50,
+    };
+    c.bench_function("status_message_serialize", |b| {
+        b.iter(|| black_box(msg.serialize()))
+    });
+}
+
+fn bench_status_message_deserialize(c: &mut Criterion) {
+    let bytes = [0x07, 0xB2, 0x00, 0x00, 0x2A, 0x00, 0x00, 0x00, 0x40, 0x42, 0x0F, 0x00];
+    c.bench_function("status_message_deserialize", |b| {
+        b.iter(|| black_box(StatusMessage::deserialize(black_box(&bytes))))
+    });
+}
+
+fn bench_roundtrip(c: &mut Criterion) {
+    let cmd = Command::new(CMD_PROTO_TCP, CMD_DIR_BOTH);
+    let msg = StatusMessage {
+        seq: 99,
+        bytes_received: 50_000,
+        cpu_load: 75,
+    };
+    c.bench_function("command_roundtrip", |b| {
+        b.iter(|| {
+            let s = black_box(cmd.serialize());
+            black_box(Command::deserialize(&s))
+        })
+    });
+    c.bench_function("status_message_roundtrip", |b| {
+        b.iter(|| {
+            let s = black_box(msg.serialize());
+            black_box(StatusMessage::deserialize(&s))
+        })
+    });
+}
+
+criterion_group!(
+    protocol_benches,
+    bench_command_serialize,
+    bench_command_deserialize,
+    bench_status_message_serialize,
+    bench_status_message_deserialize,
+    bench_roundtrip
+);
+criterion_main!(protocol_benches);