summaryrefslogtreecommitdiffhomepage
AgeCommit message (Collapse)Author
2020-01-21version: bumpJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2020-01-21curve25519: x86_64: replace with formally verified implementationJason A. Donenfeld
This comes from INRIA's HACL*/Vale. It implements the same algorithm and implementation strategy as the code it replaces, only this code has been formally verified, sans the base point multiplication, which uses code similar to prior, only it uses the formally verified field arithmetic alongside reproducable ladder generation steps. This doesn't have a pure-bmi2 version, which means haswell no longer benefits, but the increased (doubled) code complexity is not worth it for a single generation of chips that's already old. Performance-wise, this is around 1% slower on older microarchitectures, and slightly faster on newer microarchitectures, mainly 10nm ones or backports of 10nm to 14nm. This implementation is "everest" below: Xeon E5-2680 v4 (Broadwell) armfazh: 133340 cycles per call everest: 133436 cycles per call Xeon Gold 5120 (Sky Lake Server) armfazh: 112636 cycles per call everest: 113906 cycles per call Core i5-6300U (Sky Lake Client) armfazh: 116810 cycles per call everest: 117916 cycles per call Core i7-7600U (Kaby Lake) armfazh: 119523 cycles per call everest: 119040 cycles per call Core i7-8750H (Coffee Lake) armfazh: 113914 cycles per call everest: 113650 cycles per call Core i9-9880H (Coffee Lake Refresh) armfazh: 112616 cycles per call everest: 114082 cycles per call Core i3-8121U (Cannon Lake) armfazh: 113202 cycles per call everest: 111382 cycles per call Core i7-8265U (Whiskey Lake) armfazh: 127307 cycles per call everest: 127697 cycles per call Core i7-8550U (Kaby Lake Refresh) armfazh: 127522 cycles per call everest: 127083 cycles per call Xeon Platinum 8275CL (Cascade Lake) armfazh: 114380 cycles per call everest: 114656 cycles per call Achieving these kind of results with formally verified code is quite remarkable, especialy considering that performance is favorable for newer chips. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2020-01-11device: skb_list_walk_safe moved upstreamJason A. Donenfeld
This won't be ported to 5.6, of course, but it's still cleaner to get this out of the way. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2020-01-11Makefile: strip prefixed v from version.hJason A. Donenfeld
We also no longer do anything dynamic with dkms.conf, and we don't rewrite any files at all, but rather pass this through as a cflag to the compiler optionally. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Reported-by: Egbert Verhage <egbert@eggiecode.org>
2020-01-05version: bumpJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2020-01-02qemu: only compare archs when deciding whether to use kvmJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2020-01-02qemu: re-add dependency on wireguard sourcesJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2020-01-02socket: mark skbs as not on list when receiving via groJason A. Donenfeld
Certain drivers will pass gro skbs to udp, at which point the udp driver simply iterates through them and passes them off to encap_rcv, which is where we pick up. At the moment, we're not attempting to coalesce these into bundles, but we also don't want to wind up having cascaded lists of skbs treated separately. The right behavior here, then, is to just mark each incoming one as not on a list. This can be seen in practice, for example, with Qualcomm's rmnet_perf driver. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Tested-by: Yaroslav Furman <yaro330@gmail.com>
2020-01-01qemu: bump packages and support m68k properlyJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-12-26version: bumpJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-12-26dkms: set maximum kernel to 5.5Jason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-12-26global: remove remaining tools referencesJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-12-26README: shorten for new purposeJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-12-19version: bump snapshotJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-12-19compat: ipv6_dst_lookup_flow was backported to 5.3 and 5.4Jason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-12-12version: bump snapshotJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-12-12main: remove unused include <linux/version.h>YueHaibing
Remove including <linux/version.h> that we don't need. Signed-off-by: YueHaibing <yuehaibing@huawei.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-12-12global: fix up spellingJosh Soref
Signed-off-by: Josh Soref <jsoref@gmail.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-12-12compat: support building for RHEL-8.1 instead of RHEL-8.0Sergey Ivanov
RedHat backported to their kernel 4.18.0-147.el8 a couple features. This patch enables compiling for this kernel. Signed-off-by: Sergey Ivanov <seriv@cs.umd.edu> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-12-12socket: convert to ipv6_dst_lookup_flow for 5.5Jason A. Donenfeld
Upstream changed the API, so we introduce this super insane compat hack to make everything work again. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-12-06version: bump snapshotJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-12-06chacha20poly1305: double check the sgmiter logic with testJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-12-05crypto: use new assembler macros for 5.5Jason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-12-05chacha20poly1305: port to sgmitter for 5.5Jason A. Donenfeld
I'm not totally comfortable with these changes yet, and it'll require some more scrutiny. But it's a start. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-12-05netlink: prepare for removal of genl_family_attrbuf in 5.5Jason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-12-05version: bump snapshotJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-12-05send: avoid touching skb->{next,prev} directlyJason A. Donenfeld
This isn't quite the same, since mark_not_on_list doesn't touch skb->prev, but hopefully it doesn't matter. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-12-05device: prepare skb_list_walk_safe for upstreamingJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-12-05send: use kfree_skb_listJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-11-27version: bump snapshotJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-11-27qemu: bump versionJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-11-27qemu: respect PATH when finding CBUILDJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-11-27qemu: work around build bug with powerpc64leJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-11-26allowedips: avoid double lock in selftest error caseJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-11-26socket: remove redundant check of new4Jason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-11-26allowedips: safely dereference rcu rootsJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-10-30messages: recalculate rekey max based on a one minute floodJason A. Donenfeld
Discussed-with: Mathias Hall-Andersen <mathias@hall-andersen.dk> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-10-12version: bump snapshotJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-10-11noise: recompare stamps after taking write lockJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-10-11netlink: allow preventing creation of new peers when updatingJason A. Donenfeld
This enables race-free updates for wg-dynamic and similar tools. Suggested-by: Thomas Gschwantner <tharre3@gmail.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-10-11netns: add test for failing 5.3 FIB changesJason A. Donenfeld
Reference: https://lore.kernel.org/netdev/20190924073615.31704-1-Jason@zx2c4.com/ Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-10-11qemu: bump default versionJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-09-13version: bump snapshotJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-09-13compat: support rhel/centos 7.7Jason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-09-13Kbuild: squelch warnings for stack limit on broken kernel configsJason A. Donenfeld
1280 is considered the absolute minimum for 64bit archs. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-09-13compat: don't rewrite siphash when it's from compatJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-09-11compat: support newer PaXJason A. Donenfeld
Reported-by: PaX Team <pageexec@freemail.hu> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-09-05version: bump snapshotJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-09-05compat: work around ubuntu breakageJason A. Donenfeld
They forgot to backport hsiphash. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2019-08-28Makefile: allow specifying kernel releaseMikk Mar
This makes depmod work when building/installing the module for a kernel other than the currently running one. Signed-off-by: Mikk Mar <mikkmar@airmail.cc> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-04 06:45:48 +0000