mirror of
https://github.com/jart/cosmopolitan.git
synced 2025-02-07 23:13:34 +00:00
398f0c16fb
This change makes SSL virtual hosting possible. You can now load
multiple certificates for multiple domains and redbean will just
figure out which one to use, even if you only have 1 ip address.
You can also use a jumbo certificate that lists all your domains
in the the subject alternative names.
This change also makes performance improvements to MbedTLS. Here
are some benchmarks vs. cc1920749e
BEFORE AFTER (microsecs)
suite_ssl.com 2512881 191738 13.11x faster
suite_pkparse.com 36291 3295 11.01x faster
suite_x509parse.com 854669 120293 7.10x faster
suite_pkwrite.com 6549 1265 5.18x faster
suite_ecdsa.com 53347 18778 2.84x faster
suite_pk.com 49051 18717 2.62x faster
suite_ecdh.com 19535 9502 2.06x faster
suite_shax.com 15848 7965 1.99x faster
suite_rsa.com 353257 184828 1.91x faster
suite_x509write.com 162646 85733 1.90x faster
suite_ecp.com 20503 11050 1.86x faster
suite_hmac_drbg.no_reseed.com 19528 11417 1.71x faster
suite_hmac_drbg.nopr.com 12460 8010 1.56x faster
suite_mpi.com 687124 442661 1.55x faster
suite_hmac_drbg.pr.com 11890 7752 1.53x faster
There aren't any special tricks to the performance imporvements.
It's mostly due to code cleanup, assembly and intel instructions
like mulx, adox, and adcx.
182 lines
4.6 KiB
ArmAsm
182 lines
4.6 KiB
ArmAsm
/*-*- mode:unix-assembly; indent-tabs-mode:t; tab-width:8; coding:utf-8 -*-│
|
|
│vi: set et ft=asm ts=8 tw=8 fenc=utf-8 :vi│
|
|
╞══════════════════════════════════════════════════════════════════════════════╡
|
|
│ Copyright 2021 Justine Alexandra Roberts Tunney │
|
|
│ │
|
|
│ Permission to use, copy, modify, and/or distribute this software for │
|
|
│ any purpose with or without fee is hereby granted, provided that the │
|
|
│ above copyright notice and this permission notice appear in all copies. │
|
|
│ │
|
|
│ THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL │
|
|
│ WARRANTIES WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED │
|
|
│ WARRANTIES OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE │
|
|
│ AUTHOR BE LIABLE FOR ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL │
|
|
│ DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR │
|
|
│ PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER │
|
|
│ TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR │
|
|
│ PERFORMANCE OF THIS SOFTWARE. │
|
|
╚─────────────────────────────────────────────────────────────────────────────*/
|
|
#include "libc/macros.internal.h"
|
|
|
|
Mul6x6Adx:
|
|
push %rbp
|
|
mov %rsp,%rbp
|
|
.profilable
|
|
push %r15
|
|
push %r14
|
|
push %r13
|
|
push %r12
|
|
push %rbx
|
|
mov %rdx,%rbx
|
|
sub $24,%rsp
|
|
mov (%rdx),%rdx
|
|
xor %r8d,%r8d
|
|
mulx (%rsi),%rcx,%rax
|
|
mulx 8(%rsi),%rdx,%r12
|
|
mov %rcx,-48(%rbp)
|
|
adox %rdx,%rax
|
|
mov (%rbx),%rdx
|
|
mulx 16(%rsi),%rdx,%r15
|
|
adox %rdx,%r12
|
|
mov (%rbx),%rdx
|
|
mulx 24(%rsi),%rdx,%r10
|
|
adox %rdx,%r15
|
|
mov (%rbx),%rdx
|
|
mulx 32(%rsi),%rdx,%r9
|
|
adox %rdx,%r10
|
|
mov (%rbx),%rdx
|
|
mulx 40(%rsi),%rdx,%rcx
|
|
adox %rdx,%r9
|
|
mov 8(%rbx),%rdx
|
|
adox %r8,%rcx
|
|
mulx (%rsi),%r13,%r11
|
|
xor %r8d,%r8d
|
|
adox %r13,%rax
|
|
adcx %r11,%r12
|
|
mov %rax,-56(%rbp)
|
|
mulx 8(%rsi),%r11,%rax
|
|
adox %r11,%r12
|
|
adcx %rax,%r15
|
|
mov %r12,%r14
|
|
mulx 16(%rsi),%r11,%rax
|
|
adox %r11,%r15
|
|
adcx %rax,%r10
|
|
mulx 24(%rsi),%r11,%rax
|
|
adox %r11,%r10
|
|
adcx %rax,%r9
|
|
mulx 32(%rsi),%r11,%rax
|
|
adox %r11,%r9
|
|
adcx %rax,%rcx
|
|
mulx 40(%rsi),%rdx,%rax
|
|
adox %rdx,%rcx
|
|
adcx %r8,%rax
|
|
mov 16(%rbx),%rdx
|
|
adox %r8,%rax
|
|
mulx (%rsi),%r13,%r8
|
|
xor %r11d,%r11d
|
|
adox %r13,%r14
|
|
mov %r14,-64(%rbp)
|
|
adcx %r8,%r15
|
|
mulx 8(%rsi),%r12,%r8
|
|
adox %r12,%r15
|
|
adcx %r8,%r10
|
|
mulx 16(%rsi),%r12,%r8
|
|
adox %r12,%r10
|
|
adcx %r8,%r9
|
|
mulx 24(%rsi),%r12,%r8
|
|
adox %r12,%r9
|
|
adcx %r8,%rcx
|
|
mulx 32(%rsi),%r12,%r8
|
|
adox %r12,%rcx
|
|
adcx %r8,%rax
|
|
mulx 40(%rsi),%rdx,%r8
|
|
adox %rdx,%rax
|
|
adcx %r11,%r8
|
|
mov 24(%rbx),%rdx
|
|
adox %r11,%r8
|
|
mulx (%rsi),%r13,%r11
|
|
xor %r12d,%r12d
|
|
adox %r13,%r15
|
|
adcx %r11,%r10
|
|
mulx 8(%rsi),%r13,%r11
|
|
adox %r13,%r10
|
|
adcx %r11,%r9
|
|
mulx 16(%rsi),%r13,%r11
|
|
adox %r13,%r9
|
|
adcx %r11,%rcx
|
|
mulx 24(%rsi),%r13,%r11
|
|
adox %r13,%rcx
|
|
adcx %r11,%rax
|
|
mulx 32(%rsi),%r13,%r11
|
|
adox %r13,%rax
|
|
adcx %r11,%r8
|
|
mulx 40(%rsi),%rdx,%r11
|
|
adox %rdx,%r8
|
|
mov 32(%rbx),%rdx
|
|
adcx %r12,%r11
|
|
mulx (%rsi),%r14,%r13
|
|
adox %r12,%r11
|
|
xor %r12d,%r12d
|
|
adox %r14,%r10
|
|
adcx %r13,%r9
|
|
mulx 8(%rsi),%r14,%r13
|
|
adox %r14,%r9
|
|
adcx %r13,%rcx
|
|
mulx 16(%rsi),%r14,%r13
|
|
adox %r14,%rcx
|
|
adcx %r13,%rax
|
|
mulx 24(%rsi),%r14,%r13
|
|
adox %r14,%rax
|
|
adcx %r13,%r8
|
|
mulx 32(%rsi),%r14,%r13
|
|
adox %r14,%r8
|
|
adcx %r13,%r11
|
|
mulx 40(%rsi),%rdx,%r13
|
|
adox %rdx,%r11
|
|
adcx %r12,%r13
|
|
mov 40(%rbx),%rdx
|
|
adox %r12,%r13
|
|
mulx (%rsi),%r14,%rbx
|
|
xor %r12d,%r12d
|
|
adox %r14,%r9
|
|
adcx %rbx,%rcx
|
|
mulx 8(%rsi),%r14,%rbx
|
|
adox %r14,%rcx
|
|
adcx %rbx,%rax
|
|
mulx 16(%rsi),%r14,%rbx
|
|
adox %r14,%rax
|
|
adcx %rbx,%r8
|
|
mulx 24(%rsi),%r14,%rbx
|
|
adox %r14,%r8
|
|
adcx %rbx,%r11
|
|
mulx 32(%rsi),%r14,%rbx
|
|
mulx 40(%rsi),%rsi,%rdx
|
|
adox %r14,%r11
|
|
adcx %rbx,%r13
|
|
adox %rsi,%r13
|
|
adcx %r12,%rdx
|
|
adox %r12,%rdx
|
|
mov -48(%rbp),%rsi
|
|
mov -56(%rbp),%rbx
|
|
mov %r15,24(%rdi)
|
|
mov -64(%rbp),%r14
|
|
mov %r13,80(%rdi)
|
|
mov %rbx,8(%rdi)
|
|
mov %r14,16(%rdi)
|
|
mov %rsi,(%rdi)
|
|
mov %r10,32(%rdi)
|
|
mov %r9,40(%rdi)
|
|
mov %rcx,48(%rdi)
|
|
mov %rax,56(%rdi)
|
|
mov %r8,64(%rdi)
|
|
mov %r11,72(%rdi)
|
|
mov %rdx,88(%rdi)
|
|
add $24,%rsp
|
|
pop %rbx
|
|
pop %r12
|
|
pop %r13
|
|
pop %r14
|
|
pop %r15
|
|
pop %rbp
|
|
ret
|
|
.endfn Mul6x6Adx,globl
|