Skip to content
This repository was archived by the owner on Dec 27, 2019. It is now read-only.

extract-keys: add implementation of b64_ntop#2

Open
shawnl wants to merge 4 commits into
WireGuard:masterfrom
shawnl:master
Open

extract-keys: add implementation of b64_ntop#2
shawnl wants to merge 4 commits into
WireGuard:masterfrom
shawnl:master

Conversation

@shawnl

@shawnl shawnl commented Jul 23, 2018

Copy link
Copy Markdown

Fixes (glibc 2.27-3ubuntu1 amd64)

cc -O3 -march=native -Wall -pedantic -std=gnu11  -D_FILE_OFFSET_BITS=64 -o extract-keys -lresolv extract-keys.c
/tmp/ccOwy8hE.o: In function `print_key.part.0':
extract-keys.c:(.text+0x3b5): undefined reference to `__b64_ntop'
extract-keys.c:(.text+0x3ca): undefined reference to `__b64_ntop'
collect2: error: ld returned 1 exit status
Makefile:9: recipe for target 'extract-keys' failed
make: *** [extract-keys] Error 1

@zx2c4-bot zx2c4-bot force-pushed the master branch 7 times, most recently from a74c5fb to 4f9c782 Compare July 31, 2018 05:19
@zx2c4-bot zx2c4-bot force-pushed the master branch 23 times, most recently from 7ebafe2 to 2086e70 Compare August 2, 2018 06:00
@zx2c4-bot zx2c4-bot force-pushed the master branch 10 times, most recently from 091cd27 to 5627157 Compare September 2, 2018 23:46
@zx2c4-bot zx2c4-bot force-pushed the master branch 6 times, most recently from 00798ed to 99db4f8 Compare September 9, 2018 23:00
@zx2c4-bot zx2c4-bot force-pushed the master branch 5 times, most recently from afcba97 to 402eb65 Compare September 17, 2018 21:42
@zx2c4-bot zx2c4-bot force-pushed the master branch 5 times, most recently from 5018c97 to b590279 Compare September 19, 2018 03:51
zx2c4 and others added 4 commits May 11, 2019 21:15
This allows the kernel to generate ipv6 fragments. Apply the same
to ipv4 for consistency.

Signed-off-by: Joe Holden <jwh@zorins.us>
Only runs on the out-bound path, as the in-bound path is in an interrupt,
but that can be fixed in Linux.

Otherwise this is tested (with the VSX code enabled) on Power 9 (ppc64le).
Without this I get 2GiB/s over the loopback (so 4 GiB/s), and with this
I get 2.8 GiB/s (so 5.6 GiB/s), and more time is spent in poly1305 than chacha20.
This is on a 4-thread VPS.

Signed-off-by: Shawn Landden <shawn@git.icu>

v2: more complete simd.h for PPC
    benchmarks
    whitespace issues
v3: honor CONFIG_ALTIVEC (CONFIG_VSX has already honored)
Unfortunately I am not seeing a speed up with this patch,
but it does decrease CPU usage.

Only (currently) runs on the outbound path, as the in-bound path is in
an interrupt, but that can be fixed in Linux.

v2: - Do not include the FPU version, as +10% performance on POWER8
    (admittedly better on really old CPUs, like old world macs) is not
    worth it, especially when there is a fast VSX version available.
    - Honor CONFIG_VSX.
Signed-off-by: Shawn Landden <shawn@git.icu>
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Labels

None yet

Development

Successfully merging this pull request may close these issues.

3 participants