Merge pull request #3708 from AkihiroSuda/fix-3685-2

CI: test and fix portfwd issue (`w3m -dump` hangs)

Author: jandubois

.github/workflows/test.yml

@@ -264,7 +264,8 @@ jobs:
  # QEMU: required by Lima itself
  # bash: required by test-templates.sh (OS version of bash is too old)
  # coreutils: required by test-templates.sh for the "timeout" command
- run: brew install qemu bash coreutils
+ # w3m : required by test-templates.sh for port forwarding tests
+ run: brew install qemu bash coreutils w3m
  - name: "Adjust LIMACTL_CREATE_ARGS"
  run: echo "LIMACTL_CREATE_ARGS=${LIMACTL_CREATE_ARGS} --vm-type=qemu" >>$GITHUB_ENV
  - name: "Inject `no_timer_check` to kernel cmdline"
@@ -331,7 +332,7 @@ jobs:
  - name: Install test dependencies
  run: |
  sudo apt-get update
- sudo apt-get install -y --no-install-recommends ovmf qemu-system-x86 qemu-utils
+ sudo apt-get install -y --no-install-recommends ovmf qemu-system-x86 qemu-utils w3m
  sudo modprobe kvm
  # `sudo usermod -aG kvm $(whoami)` does not take an effect on GHA
  sudo chown $(whoami) /dev/kvm
@@ -430,7 +431,7 @@ jobs:
  with:
  template: templates/default.yaml
  - name: Install test dependencies
- run: brew install qemu bash coreutils
+ run: brew install qemu bash coreutils w3m
  - name: Install socket_vmnet
  env:
  SOCKET_VMNET_VERSION: v1.2.0
@@ -525,7 +526,7 @@ jobs:
  with:
  template: templates/${{ matrix.template }}
  - name: Install test dependencies
- run: brew install bash coreutils
+ run: brew install bash coreutils w3m
  - name: Uninstall qemu
  run: brew uninstall --ignore-dependencies --force qemu
  - name: Test

hack/test-templates.sh

@@ -381,6 +381,15 @@ if [[ -n ${CHECKS["port-forwards"]} ]]; then
 limactl shell "$NAME" $sudo $CONTAINER_ENGINE rm -f nginx
 fi
 fi
+if [[ ${NAME} != "alpine"* && ${NAME} != "wsl2"* ]] && command -v w3m >/dev/null; then
+INFO "Testing https://github.com/lima-vm/lima/issues/3685 ([gRPC portfwd] client connection is not closed immediately when server closed the connection)"
+# Skip the test on Alpine, as systemd-run is missing
+# Skip the test on WSL2, as port forwarding is half broken https://github.com/lima-vm/lima/pull/3686#issuecomment-3034842616
+limactl shell "$NAME" systemd-run --user python3 -m http.server 3685
+# curl is not enough to reproduce https://github.com/lima-vm/lima/issues/3685
+# `w3m -dump` exits with status code 0 even on "Can't load" error.
+timeout 30s bash -euxc "until w3m -dump http://localhost:3685 | grep -v \"w3m: Can't load\"; do sleep 3; done"
+fi
 fi
 set +x
 fi

pkg/portfwdserver/server.go

@@ -4,11 +4,16 @@
 package portfwdserver
 
 import (
+"context"
 "errors"
 "io"
 "net"
+"os"
+"strings"
 "time"
 
+"github.com/containers/gvisor-tap-vsock/pkg/tcpproxy"
+
 "github.com/lima-vm/lima/pkg/bicopy"
 "github.com/lima-vm/lima/pkg/guestagent/api"
 )
@@ -35,7 +40,23 @@ func (s *TunnelServer) Start(stream api.GuestService_TunnelServer) error {
 return err
 }
 rw := &GRPCServerRW{stream: stream, id: in.Id}
-bicopy.Bicopy(rw, conn, nil)
+
+// FIXME: consolidate bicopy and tcpproxy into one
+//
+// The bicopy package does not seem to work with `w3m -dump`:
+// https://github.com/lima-vm/lima/issues/3685
+//
+// However, the tcpproxy package can't pass the CI for WSL2 (experimental):
+// https://github.com/lima-vm/lima/pull/3686#issuecomment-3034842616
+if wsl2, _ := seemsWSL2(); wsl2 {
+bicopy.Bicopy(rw, conn, nil)
+} else {
+proxy := tcpproxy.DialProxy{DialContext: func(_ context.Context, _, _ string) (net.Conn, error) {
+return conn, nil
+}}
+proxy.HandleConn(rw)
+}
+
 return nil
 }
 
@@ -83,3 +104,13 @@ func (g *GRPCServerRW) SetReadDeadline(_ time.Time) error {
 func (g *GRPCServerRW) SetWriteDeadline(_ time.Time) error {
 return nil
 }
+
+// seemsWSL2 returns whether lima.env contains LIMA_CIDATA_VMTYPE=wsl2 .
+// This is a temporary workaround and has to be removed.
+func seemsWSL2() (bool, error) {
+b, err := os.ReadFile("/mnt/lima-cidata/lima.env")
+if err != nil {
+return false, err
+}
+return strings.Contains(string(b), "LIMA_CIDATA_VMTYPE=wsl2"), nil
+}