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
Jason A. Donenfeld
4cd06c0925
tun: openbsd: check for interface already being up
...
In some cases, we operate on an already-up interface, or the user brings
up the interface before we start monitoring. For those situations, we
should first check if the interface is already up.
This still technically races between the initial check and the start of
the route loop, but fixing that is a bit ugly and probably not worth it
at the moment.
Reported-by: Theo Buehler <tb@theobuehler.org>
2019-09-07 00:13:23 -05:00
Jason A. Donenfeld
d12eb91f9a
namespaceapi: AddSIDToBoundaryDescriptor modifies the handle
2019-09-05 21:48:21 -06:00
Jason A. Donenfeld
73d3bd9cd5
wintun: take mutex first always
...
This prevents an ABA deadlock with setupapi's internal locks.
2019-09-01 21:32:28 -06:00
Jason A. Donenfeld
f3dba4c194
wintun: consider abandoned mutexes as released
2019-09-01 21:25:47 -06:00
Jason A. Donenfeld
7937840f96
ipc: windows: use protected prefix
2019-08-31 07:48:42 -06:00
Jason A. Donenfeld
e4b957183c
winpipe: enforce ownership of client connection
2019-08-30 13:21:47 -06:00
Jason A. Donenfeld
950ca2ba8c
wintun: put mutex into private namespace
2019-08-30 11:03:21 -06:00
Jason A. Donenfeld
df2bf34373
namespaceapi: fix mistake
2019-08-30 09:59:36 -06:00
Simon Rozman
a12b765784
namespaceapi: initial version
...
Signed-off-by: Simon Rozman <simon@rozman.si>
2019-08-30 15:34:17 +02:00
Jason A. Donenfeld
14df9c3e75
wintun: take mutex so that deletion uses the right name
2019-08-30 15:34:17 +02:00
Jason A. Donenfeld
353f0956bc
wintun: move ring constants into module
2019-08-29 13:22:17 -06:00
Jason A. Donenfeld
fa7763c268
wintun: delete all interfaces is not used anymore
2019-08-29 12:22:15 -06:00
Jason A. Donenfeld
d94bae8348
wintun: Wintun->Interface
2019-08-29 12:20:40 -06:00
Jason A. Donenfeld
7689d09336
wintun: keep reference to pool in wintun object
2019-08-29 12:13:16 -06:00
Simon Rozman
69c26dc258
wintun: introduce adapter pools
...
This makes wintun package reusable for non-WireGuard applications.
Signed-off-by: Simon Rozman <simon@rozman.si>
2019-08-29 18:00:44 +02:00
Jason A. Donenfeld
e862131d3c
wintun: simplify rename logic
2019-08-28 19:31:20 -06:00
Jason A. Donenfeld
da28a3e9f3
wintun: give better errors when ndis interface listing fails
2019-08-28 08:39:26 -06:00
Jason A. Donenfeld
3bf3322b2c
wintun: also check for numbered suffix and friendly name
2019-08-28 08:08:07 -06:00
Simon Rozman
7305b4ce93
wintun: upgrade deleting all interfaces and make it reusable
...
DeleteAllInterfaces() didn't check if SPDRP_DEVICEDESC == "WireGuard
Tunnel". It deleted _all_ Wintun adapters, not just WireGuard's.
Furthermore, the DeleteAllInterfaces() was upgraded into a new function
called DeleteMatchingInterfaces() for selectively deletion. This will
be used by WireGuard to clean stale Wintun adapters.
Signed-off-by: Simon Rozman <simon@rozman.si>
2019-08-28 11:39:01 +02:00
Jason A. Donenfeld
26fb615b11
wintun: cleanup earlier
2019-08-27 11:59:15 -06:00
Jason A. Donenfeld
7fbb24afaa
wintun: rename duplicate adapters instead of ourselves
2019-08-27 11:59:15 -06:00
Jason A. Donenfeld
d9008ac35c
wintun: match suffix numbers
2019-08-26 14:46:43 -06:00
Jason A. Donenfeld
f8198c0428
device: getsockname on linux to determine port
...
It turns out Go isn't passing the pointer properly so we wound up with a
zero port every time.
2019-08-25 12:45:13 -06:00
Jason A. Donenfeld
0c540ad60e
wintun: make description consistent across fields
2019-08-24 12:29:17 +02:00
Jason A. Donenfeld
3cedc22d7b
wintun: try multiple names until one isn't a duplicate
2019-08-22 08:52:59 +02:00
Jason A. Donenfeld
68fea631d8
wintun: use nci.dll directly instead of buggy netshell
2019-08-21 09:16:12 +02:00
Jason A. Donenfeld
ef23100a4f
wintun: set friendly a bit better
...
This is still wrong, but NETSETUPPKEY_Driver_FriendlyName seems a bit
tricky to use.
2019-08-20 16:06:55 +02:00
Jason A. Donenfeld
eb786cd7c1
wintun: also set friendly name after setting interface name
2019-08-19 10:12:50 +02:00
Jason A. Donenfeld
333de75370
wintun: defer requires unique variable
2019-08-19 10:12:50 +02:00
Jason A. Donenfeld
d20459dc69
wintun: set adapter description name
2019-08-19 10:12:50 +02:00
Jason A. Donenfeld
01786286c1
tun: windows: don't spin unless we really need it
2019-08-19 10:12:50 +02:00
Jason A. Donenfeld
b16dba47a7
version: bump snapshot
2019-08-05 19:29:12 +02:00
Jason A. Donenfeld
4be9630ddc
device: drop lock before expiring keys
2019-08-05 17:46:34 +02:00
Jason A. Donenfeld
4e3018a967
uapi: skip peers with invalid keys
2019-08-05 16:57:41 +02:00
Jason A. Donenfeld
b4010123f7
tun: windows: spin for only a millisecond/80
...
Performance stays the same as before.
2019-08-03 19:11:21 +02:00
Simon Rozman
1ff37e2b07
wintun: merge opening device registry key
...
This also introduces waiting for key to appear on initial access.
See if this resolves the issue caused by HDD power-up delay resulting in
failure to create the adapter.
Signed-off-by: Simon Rozman <simon@rozman.si>
2019-08-02 16:08:49 +02:00
Simon Rozman
f5e54932e6
wintun: simplify checking reboot requirement
...
We never checked checkReboot() reported error anyway.
Signed-off-by: Simon Rozman <simon@rozman.si>
2019-08-02 16:08:49 +02:00
Simon Rozman
73698066d1
wintun: refactor err == nil
error checking
...
Signed-off-by: Simon Rozman <simon@rozman.si>
2019-08-02 15:18:58 +02:00
Jason A. Donenfeld
05ece4d167
wintun: handle error for deadgwdetect
2019-08-02 14:37:09 +02:00
Jason A. Donenfeld
6d78f89557
tun: darwin: do not attempt to close tun.event twice
...
Previously it was possible for this to race. It turns out we really
don't need to set anything to -1 anyway.
2019-08-02 12:24:17 +02:00