perf: reduce packet buffer slicing churn (#2381)

* bench: add packet bytes extraction Criterion benchmark

Adds a Criterion benchmark under easytier/benches/ covering
ZCPacket::payload_bytes and tunnel_payload_bytes at 1280/4096-byte payload
sizes, using iter_batched so ZCPacket construction stays in the setup phase
and is excluded from the timed region.

- Register the [[bench]] entry in easytier/Cargo.toml.
- Document the bench and PACKET_BYTES_* env vars in benches/README.md.

* perf: reduce packet buffer slicing churn

Replace BytesMut::split_off with Buf::advance in ZCPacket bytes
extraction paths (payload_bytes, tunnel_payload_bytes, convert_type,
drop_foreign_header) and in TunZCPacketToBytes, and simplify the
copy_from_slice in new_from_payload.

When the buffer is in its unique (VEC) representation, split_off promotes
it to the shared (ARC) representation, allocating a Shared control block
and bumping the refcount on every call, and pins the buffer in shared
mode. advance only mutates the in-place ptr/len/cap fields, avoiding that
allocation/refcount churn on the TX hot path. The byte data itself is not
copied by either path.

easytier/src/instance/virtual_nic.rs

@@ -24,7 +24,7 @@ use crate::{
 };
 
 use byteorder::WriteBytesExt as _;
-use bytes::{BufMut, BytesMut};
+use bytes::{Buf, BufMut, BytesMut};
 use cidr::{Ipv4Inet, Ipv6Inet};
 use futures::{SinkExt, Stream, StreamExt, lock::BiLock, ready};
 use pin_project_lite::pin_project;
@@ -180,12 +180,13 @@ impl ZCPacketToBytes for TunZCPacketToBytes {
         assert!(payload_offset >= 4);
 
         let ret = if self.has_packet_info {
-            let mut inner = inner.split_off(payload_offset - 4);
+            inner.advance(payload_offset - 4);
             let proto = infer_proto(&inner[4..]);
             self.fill_packet_info(&mut inner[0..4], proto)?;
             inner
         } else {
-            inner.split_off(payload_offset)
+            inner.advance(payload_offset);
+            inner
         };
 
         tracing::debug!(?ret, ?payload_offset, "convert zc packet to tun packet");

easytier/src/tunnel/packet_def.rs

@@ -1,3 +1,4 @@
+use bytes::Buf;
 use bytes::Bytes;
 use bytes::BytesMut;
 use zerocopy::AsBytes;
@@ -486,7 +487,7 @@ impl ZCPacket {
         let total_len = payload_off + payload.len();
         ret.inner.reserve(total_len);
         unsafe { ret.inner.set_len(total_len) };
-        ret.mut_payload()[..payload.len()].copy_from_slice(payload);
+        ret.mut_payload().copy_from_slice(payload);
         ret
     }
 
@@ -587,7 +588,8 @@ impl ZCPacket {
     }
 
     pub fn payload_bytes(mut self) -> BytesMut {
-        self.inner.split_off(self.payload_offset())
+        self.inner.advance(self.payload_offset());
+        self.inner
     }
 
     pub fn peer_manager_header(&self) -> Option<&PeerManagerHeader> {
@@ -652,11 +654,12 @@ impl ZCPacket {
     }
 
     pub fn tunnel_payload_bytes(mut self) -> BytesMut {
-        self.inner.split_off(
+        self.inner.advance(
             self.packet_type
                 .get_packet_offsets()
                 .peer_manager_header_offset,
-        )
+        );
+        self.inner
     }
 
     pub fn convert_type(mut self, target_packet_type: ZCPacketType) -> Self {
@@ -702,7 +705,8 @@ impl ZCPacket {
             return Self::new_from_buf(buf, target_packet_type);
         }
 
-        Self::new_from_buf(self.inner.split_off(new_offset), target_packet_type)
+        self.inner.advance(new_offset);
+        Self::new_from_buf(self.inner, target_packet_type)
     }
 
     pub fn into_bytes(self) -> Bytes {
@@ -748,8 +752,10 @@ impl ZCPacket {
         let foreign_hdr_len = hdr.get_header_len();
 
         Self::new_from_buf(
-            self.inner
-                .split_off(foreign_hdr_len + self.payload_offset()),
+            {
+                self.inner.advance(foreign_hdr_len + self.payload_offset());
+                self.inner
+            },
             ZCPacketType::DummyTunnel,
         )
     }