openwrt/target/linux/generic/backport-5.4/080-wireguard-0064-crypto-poly1305-x86_64-Use-XORL-r32-32.patch
Jason A. Donenfeld d540725871 kernel-5.4: backport fd16931a2f51 for chacha neon
Without this patch, the chacha block counter is not incremented on neon
rounds, resulting in incorrect calculations and corrupt packets.

This also switches to using `--no-numbered --zero-commit` so that future
diffs are smaller.

Reported-by: Hans Geiblinger <cybrnook2002@yahoo.com>
Reviewed-by: Ilya Lipnitskiy <ilya.lipnitskiy@gmail.com>
Cc: David Bauer <mail@david-bauer.net>
Cc: Petr Štetiar <ynezz@true.cz>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2021-03-02 09:30:22 +01:00

60 lines
1.9 KiB
Diff

From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Thu, 27 Aug 2020 19:38:31 +0200
Subject: [PATCH] crypto: poly1305-x86_64 - Use XORL r32,32
commit 7dfd1e01b3dfc13431b1b25720cf2692a7e111ef upstream.
x86_64 zero extends 32bit operations, so for 64bit operands,
XORL r32,r32 is functionally equal to XORQ r64,r64, but avoids
a REX prefix byte when legacy registers are used.
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: "David S. Miller" <davem@davemloft.net>
Acked-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
---
arch/x86/crypto/poly1305-x86_64-cryptogams.pl | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
--- a/arch/x86/crypto/poly1305-x86_64-cryptogams.pl
+++ b/arch/x86/crypto/poly1305-x86_64-cryptogams.pl
@@ -246,7 +246,7 @@ $code.=<<___ if (!$kernel);
___
&declare_function("poly1305_init_x86_64", 32, 3);
$code.=<<___;
- xor %rax,%rax
+ xor %eax,%eax
mov %rax,0($ctx) # initialize hash value
mov %rax,8($ctx)
mov %rax,16($ctx)
@@ -2869,7 +2869,7 @@ $code.=<<___;
.type poly1305_init_base2_44,\@function,3
.align 32
poly1305_init_base2_44:
- xor %rax,%rax
+ xor %eax,%eax
mov %rax,0($ctx) # initialize hash value
mov %rax,8($ctx)
mov %rax,16($ctx)
@@ -3963,7 +3963,7 @@ xor128_decrypt_n_pad:
mov \$16,$len
sub %r10,$len
xor %eax,%eax
- xor %r11,%r11
+ xor %r11d,%r11d
.Loop_dec_byte:
mov ($inp,$otp),%r11b
mov ($otp),%al
@@ -4101,7 +4101,7 @@ avx_handler:
.long 0xa548f3fc # cld; rep movsq
mov $disp,%rsi
- xor %rcx,%rcx # arg1, UNW_FLAG_NHANDLER
+ xor %ecx,%ecx # arg1, UNW_FLAG_NHANDLER
mov 8(%rsi),%rdx # arg2, disp->ImageBase
mov 0(%rsi),%r8 # arg3, disp->ControlPc
mov 16(%rsi),%r9 # arg4, disp->FunctionEntry