aboutsummaryrefslogtreecommitdiffstatshomepage
Commit message (Collapse)AuthorAgeFilesLines
* tools: add syncconf commandjd/syncconfJason A. Donenfeld2019-06-112-0/+89
|
* blake2s: spacingJason A. Donenfeld2019-06-032-123/+123
|
* curve25519: not all linkers support bmi2 and adxJason A. Donenfeld2019-06-023-6/+58
|
* version: bump snapshot0.0.20190601Jason A. Donenfeld2019-06-012-2/+2
|
* compat: don't call xgetbv on cpus with no XSAVEJason A. Donenfeld2019-05-311-1/+1
|
* blake2s: add ssse3 to nobsJason A. Donenfeld2019-05-311-1/+2
|
* blake2s: do not use xgetbv for ssse3 detectionJason A. Donenfeld2019-05-311-3/+1
|
* tools: pass WG_ENDPOINT_RESOLUTION_RETRIES=infinity to systemd unitJason A. Donenfeld2019-05-311-0/+1
|
* version: bump snapshot0.0.20190531Jason A. Donenfeld2019-05-312-2/+2
|
* tools: add wincompat layer to wg(8)Jason A. Donenfeld2019-05-3115-0/+321
|
* tools: allow setting WG_ENDPOINT_RESOLUTION_RETRIESJason A. Donenfeld2019-05-292-4/+25
|
* zinc: update copyrightJason A. Donenfeld2019-05-292-2/+2
|
* blake2s: shorten ssse3 loopSamuel Neves2019-05-291-857/+66
| | | | | | | This (mostly) preserves the performance (as measured on Haswell and *lake) of last commit, but it drastically reduces code size. Signed-off-by: Samuel Neves <sneves@dei.uc.pt>
* blake2s,chacha: latency tweakSamuel Neves2019-05-295-618/+982
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In every odd-numbered round, instead of operating over the state x00 x01 x02 x03 x05 x06 x07 x04 x10 x11 x08 x09 x15 x12 x13 x14 we operate over the rotated state x03 x00 x01 x02 x04 x05 x06 x07 x09 x10 x11 x08 x14 x15 x12 x13 The advantage here is that this requires no changes to the 'x04 x05 x06 x07' row, which is in the critical path. This results in a noticeable latency improvement of roughly R cycles, for R diagonal rounds in the primitive. In the case of BLAKE2s, which I also moved from requiring AVX to only requiring SSSE3, we save approximately 30 cycles per compression function call on Haswell and Skylake. In other words, this is an improvement of ~0.6 cpb. This idea was pointed out to me by Shunsuke Shimizu, though it appears to have been around for longer. Signed-off-by: Samuel Neves <sneves@dei.uc.pt>
* qemu: do not check for alignment with ubsanJason A. Donenfeld2019-05-291-0/+1
| | | | It insta-crashes on x86.
* zinc: arm64: use cpu_get_elf_hwcap accessor for 5.2Jason A. Donenfeld2019-05-293-2/+6
|
* kbuild: account for recent upstream changesJason A. Donenfeld2019-05-292-11/+11
| | | | | | | Apparently cdd750bfb1f76fe9be8cfb53cbe77b2e811081ab changed things, so we fall back onto this hack. Reported-by: Alex Xu <alex@alxu.ca>
* timers: add jitter on ack failure reinitiationJason A. Donenfeld2019-05-291-2/+4
|
* qemu: build iproute2 with libmnl supportJason A. Donenfeld2019-05-291-1/+1
|
* wg-quick: specify protocol to ip(8), because of inconsistenciesJason A. Donenfeld2019-05-291-3/+7
|
* netlink: use new strict length types in policy for 5.2Jason A. Donenfeld2019-05-293-14/+29
| | | | Reported-by: Bruno Wolff III <bruno@wolff.to>
* wg-quick: look up existing routes properlyJason A. Donenfeld2019-05-291-1/+1
| | | | | | This was never really correct, and then 5.1 broke it entirely. Reported-by: piraty1@inbox.ru
* qemu: use newer iproute2 and kernelJason A. Donenfeld2019-05-291-9/+4
|
* socket: set ignore_df=1 on xmitJoe Holden2019-05-292-0/+6
| | | | | | | This allows the kernel to generate ipv6 fragments. Apply the same to ipv4 for consistency. Signed-off-by: Joe Holden <jwh@zorins.us>
* wg-quick: make darwin and freebsd path search strict like linuxJason A. Donenfeld2019-04-232-2/+4
|
* wg-quick: freebsd: workaround SIOCGIFSTATUS race in FreeBSD kernelJason A. Donenfeld2019-04-231-9/+22
|
* compat: udp_tunnel: force cast sk_data_readyJason A. Donenfeld2019-04-141-1/+3
| | | | Reference: https://lists.zx2c4.com/pipermail/wireguard/2019-April/004081.html
* version: bump snapshot0.0.20190406Jason A. Donenfeld2019-04-062-2/+2
|
* allowedips: initialize list head when removing intermediate nodesJason A. Donenfeld2019-04-062-1/+5
| | | | | | | | | | Otherwise if this list item is later reused, we'll crash on list poison or worse. Also, add a version of Mimka's reproducer to netns.sh to catch these types of bugs in the future. Reported-by: Mimka <mikma.wg@lists.m7n.se>
* compat: backport skb_mark_not_on_listJason A. Donenfeld2019-03-291-0/+7
|
* blake2s: remove outlen parameter from finalJason A. Donenfeld2019-03-274-12/+11
|
* blake2s: simplifySamuel Neves2019-03-272-40/+12
| | | | Signed-off-by: Samuel Neves <sneves@dei.uc.pt>
* qemu: set framewarn 1280 for 64bit and 1024 for 32bitJason A. Donenfeld2019-03-2514-4/+14
|
* device: use skb accessor functions where possibleJason A. Donenfeld2019-03-251-2/+2
| | | | Suggested-by: David Miller <davem@davemloft.net>
* allowedips: do not use __always_inlineJason A. Donenfeld2019-03-251-9/+9
| | | | | | DaveM doth forbid. Suggested-by: David Miller <davem@davemloft.net>
* peerlookup: rename from hashtablesJason A. Donenfeld2019-03-257-9/+9
|
* tools: avoid unneccessary next_peer assignments in sort_peers()Luis Ressel2019-03-231-2/+1
| | | | Signed-off-by: Luis Ressel <aranea@aixah.de>
* wg-quick: add 'strip' subcommandLuis Ressel2019-03-235-5/+50
| | | | | | | | | `wg-quick strip` prints the config file to stdout after stripping it of all wg-quick-specific options. This enables tricks such as `wg addconf $DEV <(wg-quick strip $DEV)`. Signed-off-by: Luis Ressel <aranea@aixah.de>
* tools: warn if an AllowedIP has a nonzero host partLuis Ressel2019-03-231-0/+34
| | | | Signed-off-by: Luis Ressel <aranea@aixah.de>
* wg-quick: freebsd: export TMPDIR when restoring and don't make emptyJason A. Donenfeld2019-03-181-1/+2
| | | | Otherwise mktemp doesn't see it, and if it's empty we wind up in /.
* global: the _bh variety of rcu helpers have been unifiedJason A. Donenfeld2019-03-177-12/+57
|
* compat: nf_nat_core.h was removed upstreamBruno Wolff III2019-03-141-0/+2
| | | | | | | In d2c5c103b133 ("netfilter: nat: remove nf_nat_l3proto.h and nf_nat_core.h"). Signed-off-by: Bruno Wolff III <bruno@wolff.to>
* tools: add support for HaikuAlexander von Gluck IV2019-02-281-0/+3
| | | | Signed-off-by: Alexander von Gluck IV <kallisti5@unixzen.com>
* tools: genkey: account for short reads of /dev/urandomJason A. Donenfeld2019-02-282-18/+35
| | | | | | | | | | Apparently Haiku has a misbehaving /dev/urandom. While we're at it, simplify the function signature to completely succeed or completely fail and make sure the caller checks the result. Reported-by: Alexander von Gluck IV <kallisti5@unixzen.com> Nitpicked-by: Aaron Jones <aaronmdjones@gmail.com>
* wg-quick: freebsd: rebreak interface loopback, while fixing localhostJason A. Donenfeld2019-02-281-1/+1
| | | | | | | | | | | The commit 7c833642 ("wg-quick: freebsd: allow loopback to work") was supposed to make things better, but actually it just started sending legitimate localhost traffic over the WireGuard interface, which is really quite bad. This reverts commit 7c833642dfa342218602ab18e7091e86408d2982. Reported-by: Matt Smith <matt.xtaz@gmail.com>
* version: bump snapshot0.0.20190227Jason A. Donenfeld2019-02-272-2/+2
|
* queueing: net-next has changed signature of skb_probe_transport_headerJason A. Donenfeld2019-02-272-1/+7
|
* allowedips: maintain per-peer list of allowedipsJason A. Donenfeld2019-02-266-160/+129
| | | | | | | | This makes `wg show` and `wg showconf` and the like significantly faster, since we don't have to iterate through every node of the trie for every single peer. It also makes netlink cursor resumption much less problematic, since we're just iterating through a list, rather than having to save a traversal stack.
* peer: only synchronize_rcu_bh and traverse trie once when removing all peersJason A. Donenfeld2019-02-252-20/+42
|
* netlink: don't remove allowed ips for new peersJason A. Donenfeld2019-02-251-0/+3
| | | | This causes needless traversal of the trie.
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.