Commit graph

634 commits

Author SHA1 Message Date
David Crawshaw c8596328e7 ipc: remove unnecessary error check
os.MkdirAll never returns an os.IsExist error.

Signed-off-by: David Crawshaw <crawshaw@tailscale.com>
2020-05-02 02:02:09 -06:00
Jason A. Donenfeld 28c4d04304 device: use atomic access for unlocked keypair.next
Go's GC semantics might not always guarantee the safety of this, and the
race detector gets upset too, so instead we wrap this all in atomic
accessors.

Reported-by: David Anderson <danderson@tailscale.com>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2020-05-02 01:56:48 -06:00
Simon Rozman fdba6c183a wintun: make remaining HWID comparisons case insensitive
c85e4a410f introduced preliminary HWID
checking to speed up Wintun adapter enumeration. However, all HWID are
case insensitive by Windows convention.

Furthermore, a device might have multiple HWIDs. When DevInfo's
DeviceRegistryProperty(SPDRP_HARDWAREID) method returns []string, all
strings returned should be checked against given hardware ID.

This issue was discovered when researching Wintun and wireguard-go on
Windows 10 ARM64. The Wintun adapter was created using devcon.exe
utility with "wintun" hardware ID, causing wireguard-go fail to
enumerate the adapter properly.

Signed-off-by: Simon Rozman <simon@rozman.si>
2020-05-02 01:50:47 -06:00
Simon Rozman 250b9795f3 setupapi: extend struct size constant definitions for arm(64)
Signed-off-by: Simon Rozman <simon@rozman.si>
2020-05-02 01:50:47 -06:00
Avery Pennarun d60857e1a7 device: add debug logs describing handshake rejection
Useful in testing when bad network stacks repeat or
batch large numbers of packets.

Signed-off-by: Avery Pennarun <apenwarr@tailscale.com>
2020-05-02 01:50:47 -06:00
Brad Fitzpatrick 2fb0a712f0 tun: return a better error message if /dev/net/tun doesn't exist
It was just returning "no such file or directory" (the String of the
syscall.Errno returned by CreateTUN).

Signed-off-by: Brad Fitzpatrick <bradfitz@tailscale.com>
2020-05-02 01:50:47 -06:00
David Anderson f2c6faad44 device: return generic error from Ipc{Get,Set}Operation.
This makes uapi.go's public API conform to Go style in terms
of error types.

Signed-off-by: David Anderson <danderson@tailscale.com>
2020-05-02 01:49:47 -06:00
Avery Pennarun c76b818466 tun: NetlinkListener: don't send EventDown before sending EventUp
This works around a startup race condition when competing with
HackListener, which is trying to do the same job. If HackListener
detects that the tundev is running while there is still an event in the
netlink queue that says it isn't running, then the device receives a
string of events like
	EventUp (HackListener)
	EventDown (NetlinkListener)
	EventUp (NetlinkListener)
Unfortunately, after the first EventDown, the device stops itself,
thinking incorrectly that the administrator has downed its tundev.

The device is ignoring the initial EventDown anyway, so just don't emit
it.

Signed-off-by: Avery Pennarun <apenwarr@tailscale.com>
2020-05-02 01:46:42 -06:00
David Crawshaw de374bfb44 device: give handshake state a type
And unexport handshake constants.

Signed-off-by: David Crawshaw <crawshaw@tailscale.com>
2020-05-02 01:46:42 -06:00
David Crawshaw 1a1c3d0968 tuntest: split out testing package
This code is useful to other packages writing tests.

Signed-off-by: David Crawshaw <crawshaw@tailscale.com>
2020-05-02 01:46:42 -06:00
Brad Fitzpatrick 85a45a9651 tun: fix data race on name field
Signed-off-by: Brad Fitzpatrick <bradfitz@tailscale.com>
2020-05-02 01:46:42 -06:00
Brad Fitzpatrick abd287159e tun: remove unused isUp method
Signed-off-by: Brad Fitzpatrick <bradfitz@tailscale.com>
2020-05-02 01:46:42 -06:00
David Crawshaw 203554620d conn: introduce new package that splits out the Bind and Endpoint types
The sticky socket code stays in the device package for now,
as it reaches deeply into the peer list.

This is the first step in an effort to split some code out of
the very busy device package.

Signed-off-by: David Crawshaw <crawshaw@tailscale.com>
2020-05-02 01:46:42 -06:00
Avery Pennarun 6aefb61355 wintun: split error message for create vs open namespace.
Signed-off-by: Avery Pennarun <apenwarr@tailscale.com>
2020-05-02 01:44:58 -06:00
David Anderson 3dce460c88 device: add test to ensure Peer fields are safe for atomic access on 32-bit
Adds a test that will fail consistently on 32-bit platforms if the
struct ever changes again to violate the rules. This is likely not
needed because unaligned access crashes reliably, but this will reliably
fail even if tests accidentally pass due to lucky alignment.

Signed-Off-By: David Anderson <danderson@tailscale.com>
2020-05-02 01:44:58 -06:00
David Crawshaw 224bc9e60c rwcancel: no-op builds for windows and darwin
This lets us include the package on those platforms in a
followup commit where we split out a conn package from device.
It also lets us run `go test ./...` when developing on macOS.

Signed-off-by: David Crawshaw <crawshaw@tailscale.com>
2020-03-30 18:41:39 +11:00
David Crawshaw 9cd8909df2 ratelimiter: use a fake clock in tests and style cleanups
The existing test would occasionally flake out with:

	--- FAIL: TestRatelimiter (0.12s)
	    ratelimiter_test.go:99: Test failed for 127.0.0.1 , on: 7 ( not having refilled enough ) expected: false got: true
	FAIL
	FAIL    golang.zx2c4.com/wireguard/ratelimiter  0.171s

The fake clock also means the tests run much faster, so
testing this package with -count=1000 now takes < 100ms.

While here, several style cleanups. The most significant one
is unembeding the sync.Mutex fields in the rate limiter objects.
Embedded as they were, the lock methods were accessible
outside the ratelimiter package. As they aren't needed externally,
keep them internal to make them easier to reason about.

Passes `go test -race -count=10000 ./ratelimiter`

Signed-off-by: David Crawshaw <crawshaw@tailscale.com>
2020-03-30 18:38:36 +11:00
Jason A. Donenfeld ae88e2a2cd version: bump snapshot 2020-03-20 12:00:53 -06:00
Jason A. Donenfeld 4739708ca4 noise: unify zero checking of ecdh 2020-03-17 23:07:14 -06:00
Tobias Klauser b33219c2cf global: use RTMGRP_* consts from x/sys/unix
Update the golang.org/x/sys/unix dependency and use the newly introduced
RTMGRP_* consts instead of using the corresponding RTNLGRP_* const to
create a mask.

Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
2020-03-17 23:07:11 -06:00
Jason A. Donenfeld 9cbcff10dd send: account for zero mtu
Don't divide by zero.
2020-02-14 18:53:55 +01:00
Jason A. Donenfeld 6ed56ff2df device: fix private key removal logic 2020-02-04 22:02:53 +01:00
Jason A. Donenfeld cb4bb63030 uapi: allow unsetting device private key with /dev/null 2020-02-04 22:02:53 +01:00
Jason A. Donenfeld 05b03c6750 version: bump snapshot 2020-01-21 16:27:19 +01:00
Jason A. Donenfeld caebdfe9d0 tun: darwin: ignore ENOMEM errors
Coauthored-by: Andrej Mihajlov <and@mullvad.net>
2020-01-15 13:39:37 -05:00
Jason A. Donenfeld 4fa2ea6a2d tun: windows: serialize write calls 2020-01-07 11:40:45 -05:00
Jason A. Donenfeld 89dd065e53 README: update repo urls 2019-12-30 11:53:39 +01:00
Jason A. Donenfeld ddfad453cf device: SendmsgN mutates the input sockaddr
So we take a new granular lock to prevent concurrent writes from
racing.

WARNING: DATA RACE
Write at 0x00c0011f2740 by goroutine 27:
  golang.org/x/sys/unix.(*SockaddrInet4).sockaddr()
      /go/pkg/mod/golang.org/x/sys@v0.0.0-20191105231009-c1f44814a5cd/unix/syscall_linux.go:384
+0x114
  golang.org/x/sys/unix.SendmsgN()
      /go/pkg/mod/golang.org/x/sys@v0.0.0-20191105231009-c1f44814a5cd/unix/syscall_linux.go:1304
+0x288
  golang.zx2c4.com/wireguard/device.send4()
      /go/pkg/mod/golang.zx2c4.com/wireguard@v0.0.20191012/device/conn_linux.go:485
+0x11f
  golang.zx2c4.com/wireguard/device.(*nativeBind).Send()
      /go/pkg/mod/golang.zx2c4.com/wireguard@v0.0.20191012/device/conn_linux.go:268
+0x1d6
  golang.zx2c4.com/wireguard/device.(*Peer).SendBuffer()
      /go/pkg/mod/golang.zx2c4.com/wireguard@v0.0.20191012/device/peer.go:151
+0x285
  golang.zx2c4.com/wireguard/device.(*Peer).SendHandshakeInitiation()
      /go/pkg/mod/golang.zx2c4.com/wireguard@v0.0.20191012/device/send.go:163
+0x692
  golang.zx2c4.com/wireguard/device.(*Device).RoutineReadFromTUN()
      /go/pkg/mod/golang.zx2c4.com/wireguard@v0.0.20191012/device/send.go:318
+0x4b8

Previous write at 0x00c0011f2740 by goroutine 386:
  golang.org/x/sys/unix.(*SockaddrInet4).sockaddr()
      /go/pkg/mod/golang.org/x/sys@v0.0.0-20191105231009-c1f44814a5cd/unix/syscall_linux.go:384
+0x114
  golang.org/x/sys/unix.SendmsgN()
      /go/pkg/mod/golang.org/x/sys@v0.0.0-20191105231009-c1f44814a5cd/unix/syscall_linux.go:1304
+0x288
  golang.zx2c4.com/wireguard/device.send4()
      /go/pkg/mod/golang.zx2c4.com/wireguard@v0.0.20191012/device/conn_linux.go:485
+0x11f
  golang.zx2c4.com/wireguard/device.(*nativeBind).Send()
      /go/pkg/mod/golang.zx2c4.com/wireguard@v0.0.20191012/device/conn_linux.go:268
+0x1d6
  golang.zx2c4.com/wireguard/device.(*Peer).SendBuffer()
      /go/pkg/mod/golang.zx2c4.com/wireguard@v0.0.20191012/device/peer.go:151
+0x285
  golang.zx2c4.com/wireguard/device.(*Peer).SendHandshakeInitiation()
      /go/pkg/mod/golang.zx2c4.com/wireguard@v0.0.20191012/device/send.go:163
+0x692
  golang.zx2c4.com/wireguard/device.expiredRetransmitHandshake()
      /go/pkg/mod/golang.zx2c4.com/wireguard@v0.0.20191012/device/timers.go:110
+0x40c
  golang.zx2c4.com/wireguard/device.(*Peer).NewTimer.func1()
      /go/pkg/mod/golang.zx2c4.com/wireguard@v0.0.20191012/device/timers.go:42
+0xd8

Goroutine 27 (running) created at:
  golang.zx2c4.com/wireguard/device.NewDevice()
      /go/pkg/mod/golang.zx2c4.com/wireguard@v0.0.20191012/device/device.go:322
+0x5e8
  main.main()
      /go/src/x/main.go:102 +0x58e

Goroutine 386 (finished) created at:
  time.goFunc()
      /usr/local/go/src/time/sleep.go:168 +0x51

Reported-by: Ben Burkert <ben@benburkert.com>
2019-11-28 11:11:13 +01:00
Jason A. Donenfeld 2b242f9393 wintun: manage ring memory manually
It's large and Go's garbage collector doesn't deal with it especially
well.
2019-11-22 13:13:55 +01:00
Jason A. Donenfeld 4cdf805b29 constants: recalculate rekey max based on a one minute flood
Discussed-with: Mathias Hall-Andersen <mathias@hall-andersen.dk>
2019-10-30 14:29:32 +01:00
Jonathan Tooker f7d0edd2ec global: fix a few typos courtesy of codespell
Signed-off-by: Jonathan Tooker <jonathan.tooker@netprotect.com>
2019-10-22 11:51:25 +02:00
Jason A. Donenfeld ffffbbcc8a device: allow blackholing sockets 2019-10-21 13:29:57 +02:00
Jason A. Donenfeld 47b02c618b device: remove dead error reporting code 2019-10-21 11:46:54 +02:00
Jason A. Donenfeld fd23c66fcd namespaceapi: remove tasteless comment 2019-10-21 09:02:29 +02:00
Jason A. Donenfeld ae492d1b35 device: recheck counters while holding write lock 2019-10-17 15:43:06 +02:00
Jason A. Donenfeld 95fbfccf60 wintun: normalize variable names for their types 2019-10-17 15:30:56 +02:00
Avery Pennarun c85e4a410f wintun: quickly ignore non-Wintun devices
Some devices take ~2 seconds to enumerate on Windows if we try to get
their instance name.  The hardware id property, on the other hand,
is available right away.

Signed-off-by: Avery Pennarun <apenwarr@gmail.com>
[zx2c4: inlined this to where it makes sense, reused setupapi const]
2019-10-17 15:19:20 +02:00
Avery Pennarun 1b6c8ddbe8 tun: match windows CreateTUN signature to the Linux variant
Signed-off-by: Avery Pennarun <apenwarr@gmail.com>
[zx2c4: fix default value]
2019-10-17 15:19:20 +02:00
Avery Pennarun 0abb6b668c rwcancel: handle EINTR and EAGAIN in unixSelect()
On my Chromebook (Linux 4.19.44 in a VM) and on an AWS EC2
machine, select() was sometimes returning EINTR. This is
harmless and just means you should try again. So let's try
again.

This eliminates a problem where the tunnel fails to come up
correctly and the program needs to be restarted.

Signed-off-by: Avery Pennarun <apenwarr@gmail.com>
2019-10-17 15:19:17 +02:00
David Crawshaw 540d01e54a device: test packets between two fake devices
Signed-off-by: David Crawshaw <crawshaw@tailscale.io>
2019-10-16 11:38:28 +02:00
Jason A. Donenfeld f2ea85e9f9 version: bump snapshot 2019-10-12 22:34:10 +02:00
Jason A. Donenfeld 222f0f8000 Makefile: remove v prefix 2019-10-08 16:48:18 +02:00
Jason A. Donenfeld 1f146a5e7a wintun: expose version 2019-10-08 09:58:58 +02:00
Jason A. Donenfeld f2501aa6c8 uapi: allow preventing creation of new peers when updating
This enables race-free updates for wg-dynamic and similar tools.

Suggested-by: Thomas Gschwantner <tharre3@gmail.com>
2019-10-04 11:41:02 +02:00
Jason A. Donenfeld cb8d01f58a mod: bump versions 2019-10-04 11:41:02 +02:00
Jason A. Donenfeld 01f8ef4e84 winpipe: use x/sys/windows instead of syscall 2019-09-16 23:39:16 -06:00
Jason A. Donenfeld 70f6c42556 wintun: use correct length for security attributes 2019-09-16 19:38:33 -06:00
Jason A. Donenfeld bb0b2514c0 tun: windows: unify error message format 2019-09-08 13:52:44 -05:00
Jason A. Donenfeld 7c97fdb1e3 version: bump snapshot 2019-09-08 10:56:55 -05:00
Jason A. Donenfeld 84b5a4d83d main: simplify warnings 2019-09-08 10:56:00 -05:00