summaryrefslogtreecommitdiffhomepage
path: root/src
AgeCommit message (Collapse)Author
2017-07-20qemu: warn on all unseeded random usage when in debug modeJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-07-20global: wireguard.io --> wireguard.comJason A. Donenfeld
Due to concerns with the .io TLD, we are switching to using wireguard.com instead. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-07-20blake2s: fix up alignment issuesJason A. Donenfeld
When it's unclear if block is aligned, we just assume unaligned, rather than branching. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-07-20blake2s: move compression loop to assemblySamuel Neves
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-07-20send: use skb_queue_empty where appropriateSamuel Holland
Signed-off-by: Samuel Holland <samuel@sholland.org> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-07-20data: simplify no-keypair failure caseSamuel Holland
Signed-off-by: Samuel Holland <samuel@sholland.org> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-07-20data: use KMEM_CACHE macroJason A. Donenfeld
Suggested-by: Samuel Holland <samuel@sholland.org> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-07-20ratelimiter: use KMEM_CACHE macroJason A. Donenfeld
Suggested-by: Samuel Holland <samuel@sholland.org> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-07-20global: use pointer to net_deviceJason A. Donenfeld
DaveM prefers it to be this way per [1]. [1] http://www.spinics.net/lists/netdev/msg443992.html Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-07-20device: support 4.13's extact newlink paramJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-07-20send: orphan skbs when buffering longtermJason A. Donenfeld
Otherwise we quickly use up all of a socket's memory, which prevents a socket from sending packets to other interfaces. This also has the nice effect of letting TCP connections continue to attempt to begin, with the older ones being naturally rotated out and freed, so when a connection finally is made, only the later TCP connections are attempted, not the ones that would already have timed out. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-07-20selftests: ensure that there isnt CPU lag when testing rate limiterJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-07-07compat: work around odd kernels that backport kvfreeJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-07-07socket: styleJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-07-07qemu: update default testing kernelJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-07-07ratelimiter: consistently use non-bh rcuJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-07-06version: bump snapshotJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-07-06socket: the checkers distinguish between _bh and non _bhJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-07-06device: cleanup register_netdev logicJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-07-06compat: priv_destructor got backportedJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-07-06counter: use correct unit for indicesJason A. Donenfeld
Even though redundant bits == bits per long, we're indexing into something that uses longs as its unit, so this is correct. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-07-06ratelimiter: add self-testJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-07-04ratelimiter: use IPv6 /64 instead of /96Jason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-07-04ratelimiter: use kvzalloc for hash table allocationJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-07-03compat: workaround Ubuntu 16.10 kernel weirdnessJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-07-03compat: support OpenSUSE's backportsJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-29receive: cleanup error handlersJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-29version: bump snapshotJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-29receive: pull IP header into headJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-29receive: fix off-by-one in packet length checkingJason A. Donenfeld
This caused certain packets to be rejected that shouldn't be rejected, in the case of certain scatter-gather ethernet drivers doing GRO pulling right up to the UDP bounds but not beyond. This caused certain TCP connections to fail. Thanks very much to Reuben for providing access to the machine to debug this regression. Reported-by: Reuben Martin <reuben.m@gmail.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-28version: bump snapshotJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-28compat: support Ubuntu 14.04Jason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-28compat: support EL7.3Jason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-28compat: do not export symbols unnecessarilyJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-26global: cleanup IP header checkingJason A. Donenfeld
This way is more correct and ensures we're within the skb head. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-26device: remove icmp conntrack hacksJason A. Donenfeld
This logic belongs upstream. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-26compat: clean up cruftJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-26device: avoid double icmp send on routing loopJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-26socket: use ip_rt_put instead of dst_releaseJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-26socket: verify saddr belongs to interfaceJason A. Donenfeld
This helps "unstick" stuck source addresses, when changing routes dynamically. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-26ratelimiter: rewrite from scratchJason A. Donenfeld
This not only removes the depenency on x_tables, but it also gives us much better performance and memory usage. Now, systems are able to have millions of WireGuard interfaces, without having to worry about a thundering herd of garbage collection. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-25curve25519: keep certain sandy2x functions in CJason A. Donenfeld
We can let the compiler optimize how it sees fit. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-24curve25519: satisfy sparse and use short typesJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-24receive: extend rate limiting to 1 second after under load detectionJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-24device: only use one sleep notifierJason A. Donenfeld
This greatly improves performance when adding and removing interfaces, since the power registration function does a linear search each time. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-24device: netdevice destruction logic change for 4.12Jason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-24selftest: remove antique siphash self testJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-24main: annotate init/exit functions to save memoryJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-13version: bump snapshotJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-12random: wait for random bytes when generating nonces and ephemeralsJason A. Donenfeld
We can let userspace configure wireguard interfaces before the RNG is fully initialized, since what we mostly care about is having good randomness for ephemerals and xchacha nonces. By deferring the wait to actually asking for the randomness, we give a lot more opportunity for gathering entropy. This won't cover entropy for hash table secrets or cookie secrets (which rotate anyway), but those have far less catastrophic failure modes, so ensuring good randomness for elliptic curve points and nonces should be sufficient. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-27 02:24:26 +0000