This adds the capability to pad disco ping message payloads to reach a
specified size. It also plumbs it through to the tailscale ping -size
flag.
Disco pings used for actual endpoint discovery do not use this yet.
Updates #311.
Signed-off-by: salman <salman@tailscale.com>
Co-authored-by: Val <valerie@tailscale.com>
The nonce value is not read by anything, and di.sharedKey.Seal()
a few lines below generates its own. #cleanup
Signed-off-by: salman <salman@tailscale.com>
This change removes the noV4/noV6 check from addrForSendWireGuardLocked.
On Android, the client panics when reaching `rand.Intn()`, likely due to
the candidates list being containing no candidates. The suspicion is
that the `noV4` and the `noV6` are both being triggered causing the
loop to continue.
Updates tailscale/corp#12938
Updates #7826
Signed-off-by: Charlotte Brandhorst-Satzkorn <charlotte@tailscale.com>
Switch our best address selection to use a scoring-based approach, where
we boost each address based on whether it's a private IP or IPv6.
For users in cloud environments, this biases endpoint selection towards
using an endpoint that is less likely to cost the user money, and should
be less surprising to users.
This also involves updating the tests to not use private IPv4 addresses;
other than that change, the behaviour should be identical for existing
endpoints.
Updates #8097
Signed-off-by: Andrew Dunham <andrew@du.nham.ca>
Change-Id: I069e3b399daea28be66b81f7e44fc27b2943d8af
This change introduces address selection for wireguard only endpoints.
If a endpoint has not been used before, an address is randomly selected
to be used based on information we know about, such as if they are able
to use IPv4 or IPv6. When an address is initially selected, we also
initiate a new ICMP ping to the endpoints addresses to determine which
endpoint offers the best latency. This information is then used to
update which endpoint we should be using based on the best possible
route. If the latency is the same for a IPv4 and an IPv6 address, IPv6
will be used.
Updates #7826
Signed-off-by: Charlotte Brandhorst-Satzkorn <charlotte@tailscale.com>
Avoid selecting an endpoint as "better" than the current endpoint if the
total latency improvement is less than 1%. This adds some hysteresis to
avoid flapping between endpoints for a minimal improvement in latency.
Signed-off-by: Andrew Dunham <andrew@du.nham.ca>
Change-Id: If8312e1768ea65c4b4d4e13d8de284b3825d7a73
On some platforms (notably macOS and iOS) we look up the default
interface to bind outgoing connections to. This is both duplicated
work and results in logspam when the default interface is not available
(i.e. when a phone has no connectivity, we log an error and thus cause
more things that we will try to upload and fail).
Fixed by passing around a netmon.Monitor to more places, so that we can
use its cached interface state.
Fixes#7850
Updates #7621
Signed-off-by: Mihai Parparita <mihai@tailscale.com>
We're using it in more and more places, and it's not really specific to
our use of Wireguard (and does more just link/interface monitoring).
Also removes the separate interface we had for it in sockstats -- it's
a small enough package (we already pull in all of its dependencies
via other paths) that it's not worth the extra complexity.
Updates #7621
Updates #7850
Signed-off-by: Mihai Parparita <mihai@tailscale.com>
This is a follow-up to #7905 that adds two more linters and fixes the corresponding findings. As per the previous PR, this only flags things that are "obviously" wrong, and fixes the issues found.
Signed-off-by: Andrew Dunham <andrew@du.nham.ca>
Change-Id: I8739bdb7bc4f75666a7385a7a26d56ec13741b7c
Previously, when updating endpoints we would immediately stop
advertising any endpoint that wasn't discovered during
determineEndpoints. This could result in, for example, a case where we
performed an incremental netcheck, didn't get any of our three STUN
packets back, and then dropped our STUN endpoint from the set of
advertised endpoints... which would result in clients falling back to a
DERP connection until the next call to determineEndpoints.
Instead, let's cache endpoints that we've discovered and continue
reporting them to clients until a timeout expires. In the above case
where we temporarily don't have a discovered STUN endpoint, we would
continue reporting the old value, then re-discover the STUN endpoint
again and continue reporting it as normal, so clients never see a
withdrawal.
Updates tailscale/coral#108
Signed-off-by: Andrew Dunham <andrew@du.nham.ca>
Change-Id: I42de72e7418ab328a6c732bdefc74549708cf8b9
The comment still said *magicsock.Conn implemented wireguard-go conn.Bind.
That wasn't accurate anymore.
A doc #cleanup.
Change-Id: I7fd003b939497889cc81147bfb937b93e4f6865c
Signed-off-by: Brad Fitzpatrick <bradfitz@tailscale.com>
So we're staying within the netip.Addr/AddrPort consistently and
avoiding allocs/conversions to the legacy net addr types.
Updates #5162
Change-Id: I59feba60d3de39f773e68292d759766bac98c917
Signed-off-by: Brad Fitzpatrick <bradfitz@tailscale.com>
This also adds a bunch of tests for this function to ensure that we're
returning the proper IP(s) in all cases.
Signed-off-by: Andrew Dunham <andrew@du.nham.ca>
Change-Id: I0d9d57170dbab5f2bf07abdf78ecd17e0e635399
Using log.Printf may end up being printed out to the console, which
is not desirable. I noticed this when I was investigating some client
logs with `sockstats: trace "NetcheckClient" was overwritten by another`.
That turns to be harmless/expected (the netcheck client will fall back
to the DERP client in some cases, which does its own sockstats trace).
However, the log output could be visible to users if running the
`tailscale netcheck` CLI command, which would be needlessly confusing.
Updates tailscale/corp#9230
Signed-off-by: Mihai Parparita <mihai@tailscale.com>
The lazy initialization of the disco key is not necessary, and
contributes to unnecessary locking and state checking.
Updates #cleanup
Signed-off-by: James Tucker <james@tailscale.com>
A peer can have IsWireGuardOnly, which means it will not support DERP or
Disco, and it must have Endpoints filled in order to be usable.
In the present implementation only the first Endpoint will be used as
the bestAddr.
Updates tailscale/corp#10351
Co-authored-by: Charlotte Brandhorst-Satzkorn <charlotte@tailscale.com>
Co-authored-by: James Tucker <james@tailscale.com>
Signed-off-by: James Tucker <james@tailscale.com>
Identified in review in #7821 endpoint.discoKey and endpoint.discoShort
are often accessed without first taking endpoint.mu. The arrangement
with endpoint.mu is inconvenient for a good number of those call-sites,
so it is instead replaced with an atomic pointer to carry both pieces of
disco info. This will also help with #7821 that wants to add explicit
checks/guards to disable disco behaviors when disco keys are missing
which is necessarily implicitly mostly covered by this change.
Updates #7821
Signed-off-by: James Tucker <james@tailscale.com>
Make developing derp easier by:
1. Creating an envknob telling clients to use HTTP to connect to derp
servers, so devs don't have to acquire a valid TLS cert.
2. Creating an envknob telling clients which derp server to connect
to, so devs don't have to edit the ACLs in the admin console to add a
custom DERP map.
3. Explaining how the -dev and -a command lines args to derper
interact.
To use this:
1. Run derper with -dev.
2. Run tailscaled with TS_DEBUG_USE_DERP_HTTP=1 and
TS_DEBUG_USE_DERP_ADDR=localhost
This will result in the client connecting to derp via HTTP on port
3340.
Fixes#7700
Signed-off-by: Val <valerie@tailscale.com>
This commit implements UDP offloading for Linux. GSO size is passed to
and from the kernel via socket control messages. Support is probed at
runtime.
UDP GSO is dependent on checksum offload support on the egress netdev.
UDP GSO will be disabled in the event sendmmsg() returns EIO, which is
a strong signal that the egress netdev does not support checksum
offload.
Updates tailscale/corp#8734
Signed-off-by: Jordan Whited <jordan@tailscale.com>
This adds the util/sysresources package, which currently only contains a
function to return the total memory size of the current system.
Then, we modify magicsock to scale the number of buffered DERP messages
based on the system's available memory, ensuring that we never use a
value lower than the previous constant of 32.
Signed-off-by: Andrew Dunham <andrew@du.nham.ca>
Change-Id: Ib763c877de4d0d4ee88869078e7d512f6a3a148d
This commit updates the wireguard-go dependency to pull in fixes for
the tun package, specifically 052af4a and aad7fca.
Signed-off-by: Jordan Whited <jordan@tailscale.com>
* wgengine/magicsock: add envknob to send CallMeMaybe to non-existent peer
For testing older client version responses to the PeerGone packet format change.
Updates #4326
Signed-off-by: Val <valerie@tailscale.com>
* derp: remove dead sclient struct member replaceLimiter
Leftover from an previous solution to the duplicate client problem.
Updates #2751
Signed-off-by: Val <valerie@tailscale.com>
* derp, derp/derphttp, wgengine/magicsock: add new PeerGone message type Not Here
Extend the PeerGone message type by adding a reason byte. Send a
PeerGone "Not Here" message when an endpoint sends a disco message to
a peer that this server has no record of.
Fixes#4326
Signed-off-by: Val <valerie@tailscale.com>
---------
Signed-off-by: Val <valerie@tailscale.com>
This change adds a ringbuffer to each magicsock endpoint that keeps a
fixed set of "changes"–debug information about what updates have been
made to that endpoint.
Additionally, this adds a LocalAPI endpoint and associated
"debug peer-status" CLI subcommand to fetch the set of changes for a given
IP or hostname.
Updates tailscale/corp#9364
Signed-off-by: Andrew Dunham <andrew@du.nham.ca>
Change-Id: I34f726a71bddd0dfa36ec05ebafffb24f6e0516a
Makes it cheaper/simpler to persist values, and encourages reuse of
labels as opposed to generating an arbitrary number.
Updates tailscale/corp#9230
Updates #3363
Signed-off-by: Mihai Parparita <mihai@tailscale.com>
The debug flag on tailscaled isn't available in the macOS App Store
build, since we don't have a tailscaled binary; move it to the
'tailscale debug' CLI that is available on all platforms instead,
accessed over LocalAPI.
Updates #7377
Signed-off-by: Andrew Dunham <andrew@du.nham.ca>
Change-Id: I47bffe4461e036fab577c2e51e173f4003592ff7
Uses the hooks added by tailscale/go#45 to instrument the reads and
writes on the major code paths that do network I/O in the client. The
convention is to use "<package>.<type>:<label>" as the annotation for
the responsible code path.
Enabled on iOS, macOS and Android only, since mobile platforms are the
ones we're most interested in, and we are less sensitive to any
throughput degradation due to the per-I/O callback overhead (macOS is
also enabled for ease of testing during development).
For now just exposed as counters on a /v0/sockstats PeerAPI endpoint.
We also keep track of the current interface so that we can break out
the stats by interface.
Updates tailscale/corp#9230
Updates #3363
Signed-off-by: Mihai Parparita <mihai@tailscale.com>
To aid in debugging where a customer has static port-forwards set up and
there are issues establishing a connection through that port.
Signed-off-by: Andrew Dunham <andrew@du.nham.ca>
Change-Id: Ic5558bcdb40c9119b83f79dcacf2233b07777f2a
Update all code generation tools, and those that check for license
headers to use the new standard header.
Also update copyright statement in LICENSE file.
Fixes#6865
Signed-off-by: Will Norris <will@tailscale.com>
This updates all source files to use a new standard header for copyright
and license declaration. Notably, copyright no longer includes a date,
and we now use the standard SPDX-License-Identifier header.
This commit was done almost entirely mechanically with perl, and then
some minimal manual fixes.
Updates #6865
Signed-off-by: Will Norris <will@tailscale.com>
The single packet WriteTo() through RebindingUDPConn.WriteBatch() was
not checking for a rebind between loading the PacketConn and writing to
it. Same with ReadFrom()/ReadBatch().
Fixes#6989
Signed-off-by: Jordan Whited <jordan@tailscale.com>
When you hit control-C on a tailscaled (notably in dev mode, but
also on any systemctl stop/restart), there is a flood of messages like:
magicsock: doing cleanup for discovery key d:aa9c92321db0807f
magicsock: doing cleanup for discovery key d:bb0f16aacadbfd46
magicsock: doing cleanup for discovery key d:b5b2d386296536f2
magicsock: doing cleanup for discovery key d:3b640649f6796c91
magicsock: doing cleanup for discovery key d:71d7b1afbcce52cd
magicsock: doing cleanup for discovery key d:315b61d7e0111377
magicsock: doing cleanup for discovery key d:9301f63dce69bf45
magicsock: doing cleanup for discovery key d:376141884d6fe072
....
It can be hundreds or even tens of thousands.
So don't do that. Not a useful log message during shutdown.
Change-Id: I029a8510741023f740877df28adff778246c18e5
Signed-off-by: Brad Fitzpatrick <bradfitz@tailscale.com>
This is temporary while we work to upstream performance work in
https://github.com/WireGuard/wireguard-go/pull/64. A replace directive
is less ideal as it breaks dependent code without duplication of the
directive.
Signed-off-by: Jordan Whited <jordan@tailscale.com>
This commit updates the wireguard-go dependency and implements the
necessary changes to the tun.Device and conn.Bind implementations to
support passing vectors of packets in tailscaled. This significantly
improves throughput performance on Linux.
Updates #414
Signed-off-by: Jordan Whited <jordan@tailscale.com>
Signed-off-by: James Tucker <james@tailscale.com>
Co-authored-by: James Tucker <james@tailscale.com>
We would replace the existing real implementation of nettype.PacketConn
with a blockForeverConn, but that violates the contract of atomic.Value
(where the type cannot change). Fix by switching to a pointer value
(atomic.Pointer[nettype.PacketConn]).
A longstanding issue, but became more prevalent when we started binding
connections to interfaces on macOS and iOS (#6566), which could lead to
the bind call failing if the interface was no longer available.
Fixes#6641
Signed-off-by: Mihai Parparita <mihai@tailscale.com>
Previously, tstun.Wrapper and magicsock.Conn managed their
own statistics data structure and relied on an external call to
Extract to extract (and reset) the statistics.
This makes it difficult to ensure a maximum size on the statistics
as the caller has no introspection into whether the number
of unique connections is getting too large.
Invert the control flow such that a *connstats.Statistics
is registered with tstun.Wrapper and magicsock.Conn.
Methods on non-nil *connstats.Statistics are called for every packet.
This allows the implementation of connstats.Statistics (in the future)
to better control when it needs to flush to ensure
bounds on maximum sizes.
The value registered into tstun.Wrapper and magicsock.Conn could
be an interface, but that has two performance detriments:
1. Method calls on interface values are more expensive since
they must go through a virtual method dispatch.
2. The implementation would need a sync.Mutex to protect the
statistics value instead of using an atomic.Pointer.
Given that methods on constats.Statistics are called for every packet,
we want reduce the CPU cost on this hot path.
Signed-off-by: Joe Tsai <joetsai@digital-static.net>
There aren't any in the wild, other than one we ran on purpose to keep
us honest, but we can bump that one forward to 0.100.
Change-Id: I129e70724b2d3f8edf3b496dc01eba3ac5a2a907
Signed-off-by: Brad Fitzpatrick <bradfitz@tailscale.com>
This renames canP2P in magicsock to canP2PLocked to reflect
expectation of mutex lock, fixes a race we discovered in the meantime,
and updates the current stats.
Co-authored-by: Brad Fitzpatrick <bradfitz@tailscale.com>
Signed-off-by: Jenny Zhang <jz@tailscale.com>
There is utility in logging traffic statistics that occurs at the physical layer.
That is, in order to send packets virtually to a particular tailscale IP address,
what physical endpoints did we need to communicate with?
This functionality logs IP addresses identical to
what had always been logged in magicsock prior to #5823,
so there is no increase in PII being logged.
ExtractStatistics returns a mapping of connections to counts.
The source is always a Tailscale IP address (without port),
while the destination is some endpoint reachable on WAN or LAN.
As a special case, traffic routed through DERP will use 127.3.3.40
as the destination address with the port being the DERP region.
This entire feature is only enabled if data-plane audit logging
is enabled on the tailnet (by default it is disabled).
Example of type of information logged:
------------------------------------ Tx[P/s] Tx[B/s] Rx[P/s] Rx[B/s]
PhysicalTraffic: 25.80 3.39Ki 38.80 5.57Ki
100.1.2.3 -> 143.11.22.33:41641 15.40 2.00Ki 23.20 3.37Ki
100.4.5.6 -> 192.168.0.100:41641 10.20 1.38Ki 15.60 2.20Ki
100.7.8.9 -> 127.3.3.40:2 0.20 6.40 0.00 0.00
Signed-off-by: Joe Tsai <joetsai@digital-static.net>
We had previously added this to the netcheck report in #5087 but never
copied it into the NetInfo struct. Additionally, add it to log lines so
it's visible to support.
Change-Id: Ib6266f7c6aeb2eb2a28922aeafd950fe1bf5627e
Signed-off-by: Andrew Dunham <andrew@tailscale.com>
Sets up new file for separate silent disco goroutine, tentatively named
pathfinder for now.
Updates #540
Co-authored-by: Brad Fitzpatrick <bradfitz@tailscale.com>
Signed-off-by: Jenny Zhang <jz@tailscale.com>
During development of silent disco (#540), an alternate send policy
for magicsock that doesn't wake up the radio frequently with
heartbeats, we want the old & new policies to coexist, like we did
previously pre- and post-disco.
We started to do that earlier in 5c42990c2f but only set up the
env+control knob plumbing to set a bool about which path should be
used.
This starts to add a way for the silent disco code to update the send
path from a separate goroutine. (Part of the effort is going to
de-state-machinify the event based soup that is the current disco
code and make it more Go synchronous style.)
So far this does nothing. (It does add an atomic load on each send
but that should be noise in the grand scheme of things, and a even more
rare atomic store of nil on node config changes.)
Baby steps.
Updates #540
Co-authored-by: Jenny Zhang <jz@tailscale.com>
Signed-off-by: Brad Fitzpatrick <bradfitz@tailscale.com>
The wireguard-go code unfortunately calls this unconditionally
even when verbose logging is disabled.
Partial revert of #5911.
Signed-off-by: Joe Tsai <joetsai@digital-static.net>
This field seems seldom used and the documentation is wrong.
It is simpler to just derive its original value dynamically
when endpoint.DstToString is called.
This method is potentially used by wireguard-go,
but not in any code path is performance sensitive.
All calls to it use it in conjunction with fmt.Printf,
which is going to be slow anyways since it uses Go reflection.
Signed-off-by: Joe Tsai <joetsai@digital-static.net>
- At high data rates more buffer space is required in order to avoid
packet loss during any cause of delay.
- On slower machines more buffer space is required in order to avoid
packet loss while decryption & tun writing is underway.
- On higher latency network paths more buffer space is required in order
to overcome BDP.
- On Linux set with SO_*BUFFORCE to bypass net.core.{r,w}mem_max.
- 7MB is the current default maximum on macOS 12.6
- Windows test is omitted, as Windows does not support getsockopt for
these options.
Signed-off-by: James Tucker <james@tailscale.com>
And add a CLI/localapi and c2n mechanism to enable it for a fixed
amount of time.
Updates #1548
Change-Id: I71674aaf959a9c6761ff33bbf4a417ffd42195a7
Signed-off-by: Brad Fitzpatrick <bradfitz@tailscale.com>
This fixes a race condition which caused `c.muCond.Broadcast()` to
never fire in the `firstDerp` if block. It resulted in `Close()`
hanging forever.
Signed-off-by: Kyle Carberry <kyle@carberry.com>
From 5c42990c2f, not yet released in a stable build.
Caught by existing tests.
Fixes#5685
Change-Id: Ia76bb328809d9644e8b96910767facf627830600
Signed-off-by: Brad Fitzpatrick <bradfitz@tailscale.com>
Baby steps towards turning off heartbeat pings entirely as per #540.
This doesn't change any current magicsock functionality and requires additional
changes to send/disco paths before the flag can be turned on.
Updates #540
Change-Id: Idc9a72748e74145b068d67e6dd4a4ffe3932efd0
Signed-off-by: Jenny Zhang <jz@tailscale.com>
Signed-off-by: Jenny Zhang <jz@tailscale.com>
Incoming disco packets are now dropped unless they match one of the
current bound ports, or have a zero port*.
The BPF filter passes all packets with a disco header to the raw packet
sockets regardless of destination port (in order to avoid needing to
reconfigure BPF on rebind).
If a BPF enabled node has just rebound, due to restart or rebind, it may
receive and reply to disco ping packets destined for ports other than
those which are presently bound. If the pong is accepted, the pinging
node will now assume that it can send WireGuard traffic to the pinged
port - such traffic will not reach the node as it is not destined for a
bound port.
*The zero port is ignored, if received. This is a speculative defense
and would indicate a problem in the receive path, or the BPF filter.
This condition is allowed to pass as it may enable traffic to flow,
however it will also enable problems with the same symptoms this patch
otherwise fixes.
Fixes#5536
Signed-off-by: James Tucker <james@tailscale.com>
1f959edeb0 introduced a regression for JS
where the initial bind no longer occurred at all for JS.
The condition is moved deeper in the call tree to avoid proliferation of
higher level conditions.
Updates #5537
Signed-off-by: James Tucker <james@tailscale.com>
Both RebindingUDPConns now always exist. the initial bind (which now
just calls rebind) now ensures that bind is called for both, such that
they both at least contain a blockForeverConn. Calling code no longer
needs to assert their state.
Signed-off-by: James Tucker <james@tailscale.com>
This is entirely optional (i.e. failing in this code is non-fatal) and
only enabled on Linux for now. Additionally, this new behaviour can be
disabled by setting the TS_DEBUG_DISABLE_AF_PACKET environment variable.
Updates #3824
Replaces #5474
Co-authored-by: Andrew Dunham <andrew@du.nham.ca>
Signed-off-by: David Anderson <danderson@tailscale.com>
The Start method was removed in 4c27e2fa22, but the comment on NewConn
still mentioned it doesn't do anything until this method is called.
Signed-off-by: Kris Brandow <kris.brandow@gmail.com>
This adds a lighter mechanism for endpoint updates from control.
Change-Id: If169c26becb76d683e9877dc48cfb35f90cc5f24
Signed-off-by: Brad Fitzpatrick <bradfitz@tailscale.com>
