summaryrefslogtreecommitdiffstatshomepage
path: root/src (follow)
Commit message (Collapse)AuthorAgeFilesLines
* version: bump snapshotexperimental-0.0.20161129Jason A. Donenfeld2016-11-291-1/+1
|
* send: send packet initiation only after requeuing to prevent raceJason A. Donenfeld2016-11-291-6/+11
|
* tests: be sure we get all messagesJason A. Donenfeld2016-11-291-1/+6
|
* siphash: add types to headerJason A. Donenfeld2016-11-291-0/+2
|
* noise: update to new notationJason A. Donenfeld2016-11-291-2/+2
|
* tools: warn about clock going backwardJason A. Donenfeld2016-11-291-16/+20
|
* main: unify the adjective trifectaJason A. Donenfeld2016-11-291-1/+1
|
* ratelimiter: load hashlimit at modinsert timeJason A. Donenfeld2016-11-294-46/+72
| | | | This fixes a potential race with net_lock and rtnl_lock.
* device: conntrack is optionalJason A. Donenfeld2016-11-222-5/+12
|
* tests: veth does not come up immediatelyJason A. Donenfeld2016-11-211-0/+7
|
* headers: cleanup noticesJason A. Donenfeld2016-11-2155-54/+58
|
* main: add version to dmesgJason A. Donenfeld2016-11-214-5/+14
|
* chacha20poly1305: sse/ymm should be implicitexperimental-0.0.20161116.1Jason A. Donenfeld2016-11-161-1/+1
|
* chacha20poly1305: rely on avx and avx2experimental-0.0.20161116Jason A. Donenfeld2016-11-161-1/+1
| | | | | | It turns out some FrankenVMs disable AVX but keep AVX2, causing issues. The crypto code now relies on having both AVX and AVX2 and the right features.
* device: better debug messageJason A. Donenfeld2016-11-161-1/+1
|
* device: we need NONE for libpcapJason A. Donenfeld2016-11-161-2/+2
| | | | | This makes addrconf add a temporary IPv6 address, which is annoying, and currently there's not a work around for this.
* packets: consolidate constantsJason A. Donenfeld2016-11-165-24/+21
|
* various: nits from willyJason A. Donenfeld2016-11-154-8/+6
|
* tests: trim outputJason A. Donenfeld2016-11-151-20/+4
|
* tests: use private ipv6 addressesJason A. Donenfeld2016-11-151-18/+18
|
* socket: ensure that saddr routing can deal with interface removalJason A. Donenfeld2016-11-152-0/+43
|
* compat: rearrangeJason A. Donenfeld2016-11-151-7/+7
|
* debug: cleanup skb printingJason A. Donenfeld2016-11-154-52/+37
|
* socket: keep track of src address in sending packetsJason A. Donenfeld2016-11-1511-122/+135
|
* curve25519: use kmalloc in order to not overflow stackexperimental-0.0.20161110Jason A. Donenfeld2016-11-101-89/+260
| | | | | | | | | | | | | | | | | On MIPS, the IRQ and SoftIRQ handlers share the stack with whatever kernel thread was interrupted. This means that Curve25519 can be interrupted by, say, an ethernet controller, that then gets handled by a SoftIRQ. If something like l2tp is being used, which uses quite a bit of stack, then by the time the SoftIRQ handler gets to WireGuard code and calls into the stack-heavy ChaPoly functions, our 8k stack is shot. In other words, since Curve25519 is such a big consumer of stack, if it's interrupted by anything else that uses a healthy amount of stack, then disaster strikes. The solution here is just to allocate using kmalloc. This is quite ugly, and if performance becomes an issue, we might consider moving to a kmem_cache allocator, or even having each peer keep its own preallocated space. But for now, we'll try this.
* chacha20poly1305: don't forget version headerJason A. Donenfeld2016-11-091-0/+1
|
* routing-table: mask self for better IP displayJason A. Donenfeld2016-11-071-2/+6
|
* selftest: add routing table tests for small subnetsJason A. Donenfeld2016-11-071-0/+12
|
* send: simplify handshake initiation queueing and introduce lockJason A. Donenfeld2016-11-074-36/+41
|
* chacha20poly1305: it's just as fast to use these more simple unaligned access helpersJason A. Donenfeld2016-11-071-36/+7
|
* socket: use more reasonable skb paddingJason A. Donenfeld2016-11-071-1/+1
|
* data: only uses kmem_cache for parallismJason A. Donenfeld2016-11-063-0/+11
|
* debug: support dynamic debug on skb addrJason A. Donenfeld2016-11-063-6/+6
|
* cookie: avoid void pointer arithmaticJason A. Donenfeld2016-11-061-3/+3
|
* send: remove redundant time stampJason A. Donenfeld2016-11-061-1/+0
|
* qemu: kasan needs more memoryJason A. Donenfeld2016-11-061-1/+1
|
* qemu: use sparsemem always, for kasanJason A. Donenfeld2016-11-061-0/+1
|
* socket: release dst on routing loopJason A. Donenfeld2016-11-061-0/+2
|
* data: squelch compiler warning on PARALLEL=nJason A. Donenfeld2016-11-061-1/+1
|
* data: we care about per-peer, not per-device, inflight encryptionsJason A. Donenfeld2016-11-063-21/+14
|
* chacha20poly1305: cleanup magic constantsexperimental-0.0.20161105Jason A. Donenfeld2016-11-051-3/+2
|
* c89: the static keyword is okay in c99, but not in c89Jason A. Donenfeld2016-11-0513-48/+48
|
* tools: chill modern gcc outJason A. Donenfeld2016-11-051-22/+12
|
* qemu: fail if module selftests failJason A. Donenfeld2016-11-051-2/+12
|
* qemu: move marker to top and flushJason A. Donenfeld2016-11-051-3/+3
|
* qemu: work around termio race conditionJason A. Donenfeld2016-11-051-1/+6
|
* compat: fix variable assumptionsJason A. Donenfeld2016-11-051-1/+1
|
* qemu: move build outside of kernel dir to avoid kernel's make cleanJason A. Donenfeld2016-11-053-6/+1
|
* socket: big refactoringJason A. Donenfeld2016-11-053-193/+170
|
* socket: route() returns an error pointer, not NULL on failureJason A. Donenfeld2016-11-041-2/+2
| | | | Reported-by: Cedric Buxin <cedric.buxin@izri.org>
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.