All of lore.kernel.org
 help / color / mirror / Atom feed
From: Ard Biesheuvel <ardb@kernel.org>
To: linux-crypto@vger.kernel.org
Cc: Ard Biesheuvel <ardb@kernel.org>,
	Herbert Xu <herbert@gondor.apana.org.au>,
	Eric Biggers <ebiggers@kernel.org>,
	Kees Cook <keescook@chromium.org>
Subject: [PATCH v2 06/13] crypto: x86/cast6 - Use RIP-relative addressing
Date: Wed, 12 Apr 2023 13:00:28 +0200	[thread overview]
Message-ID: <20230412110035.361447-7-ardb@kernel.org> (raw)
In-Reply-To: <20230412110035.361447-1-ardb@kernel.org>

Prefer RIP-relative addressing where possible, which removes the need
for boot time relocation fixups.

Co-developed-by: Thomas Garnier <thgarnie@chromium.org>
Signed-off-by: Thomas Garnier <thgarnie@chromium.org>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 arch/x86/crypto/cast6-avx-x86_64-asm_64.S | 32 +++++++++++---------
 1 file changed, 18 insertions(+), 14 deletions(-)

diff --git a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
index 82b716fd5dbac65a..9e86d460b4092826 100644
--- a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
@@ -84,15 +84,19 @@
 
 #define lookup_32bit(src, dst, op1, op2, op3, interleave_op, il_reg) \
 	movzbl		src ## bh,     RID1d;    \
+	leaq		s1(%rip),      RID2;     \
+	movl		(RID2,RID1,4), dst ## d; \
 	movzbl		src ## bl,     RID2d;    \
+	leaq		s2(%rip),      RID1;     \
+	op1		(RID1,RID2,4), dst ## d; \
 	shrq $16,	src;                     \
-	movl		s1(, RID1, 4), dst ## d; \
-	op1		s2(, RID2, 4), dst ## d; \
 	movzbl		src ## bh,     RID1d;    \
+	leaq		s3(%rip),      RID2;     \
+	op2		(RID2,RID1,4), dst ## d; \
 	movzbl		src ## bl,     RID2d;    \
 	interleave_op(il_reg);			 \
-	op2		s3(, RID1, 4), dst ## d; \
-	op3		s4(, RID2, 4), dst ## d;
+	leaq		s4(%rip),      RID1;     \
+	op3		(RID1,RID2,4), dst ## d;
 
 #define dummy(d) /* do nothing */
 
@@ -175,10 +179,10 @@
 	qop(RD, RC, 1);
 
 #define shuffle(mask) \
-	vpshufb		mask,            RKR, RKR;
+	vpshufb		mask(%rip),            RKR, RKR;
 
 #define preload_rkr(n, do_mask, mask) \
-	vbroadcastss	.L16_mask,                RKR;      \
+	vbroadcastss	.L16_mask(%rip),          RKR;      \
 	/* add 16-bit rotation to key rotations (mod 32) */ \
 	vpxor		(kr+n*16)(CTX),           RKR, RKR; \
 	do_mask(mask);
@@ -258,9 +262,9 @@ SYM_FUNC_START_LOCAL(__cast6_enc_blk8)
 
 	movq %rdi, CTX;
 
-	vmovdqa .Lbswap_mask, RKM;
-	vmovd .Lfirst_mask, R1ST;
-	vmovd .L32_mask, R32;
+	vmovdqa .Lbswap_mask(%rip), RKM;
+	vmovd .Lfirst_mask(%rip), R1ST;
+	vmovd .L32_mask(%rip), R32;
 
 	inpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
 	inpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
@@ -284,7 +288,7 @@ SYM_FUNC_START_LOCAL(__cast6_enc_blk8)
 	popq %rbx;
 	popq %r15;
 
-	vmovdqa .Lbswap_mask, RKM;
+	vmovdqa .Lbswap_mask(%rip), RKM;
 
 	outunpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
 	outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
@@ -306,9 +310,9 @@ SYM_FUNC_START_LOCAL(__cast6_dec_blk8)
 
 	movq %rdi, CTX;
 
-	vmovdqa .Lbswap_mask, RKM;
-	vmovd .Lfirst_mask, R1ST;
-	vmovd .L32_mask, R32;
+	vmovdqa .Lbswap_mask(%rip), RKM;
+	vmovd .Lfirst_mask(%rip), R1ST;
+	vmovd .L32_mask(%rip), R32;
 
 	inpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
 	inpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
@@ -332,7 +336,7 @@ SYM_FUNC_START_LOCAL(__cast6_dec_blk8)
 	popq %rbx;
 	popq %r15;
 
-	vmovdqa .Lbswap_mask, RKM;
+	vmovdqa .Lbswap_mask(%rip), RKM;
 	outunpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
 	outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
 
-- 
2.39.2


  parent reply	other threads:[~2023-04-12 11:01 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-04-12 11:00 [PATCH v2 00/13] crypto: x86 - avoid absolute references Ard Biesheuvel
2023-04-12 11:00 ` [PATCH v2 01/13] crypto: x86/aegis128 - Use RIP-relative addressing Ard Biesheuvel
2023-04-12 11:00 ` [PATCH v2 02/13] crypto: x86/aesni " Ard Biesheuvel
2023-04-12 11:00 ` [PATCH v2 03/13] crypto: x86/aria " Ard Biesheuvel
2023-04-12 11:00 ` [PATCH v2 04/13] crypto: x86/camellia " Ard Biesheuvel
2023-04-12 11:00 ` [PATCH v2 05/13] crypto: x86/cast5 " Ard Biesheuvel
2023-04-12 11:00 ` Ard Biesheuvel [this message]
2023-04-12 11:00 ` [PATCH v2 07/13] crypto: x86/crc32c " Ard Biesheuvel
2023-04-12 11:00 ` [PATCH v2 08/13] crypto: x86/des3 " Ard Biesheuvel
2023-04-12 11:00 ` [PATCH v2 09/13] crypto: x86/ghash " Ard Biesheuvel
2023-04-12 11:00 ` [PATCH v2 10/13] crypto: x86/sha256 " Ard Biesheuvel
2023-04-12 11:00 ` [PATCH v2 11/13] crypto: x86/aesni - Use local .L symbols for code Ard Biesheuvel
2023-04-12 11:00 ` [PATCH v2 12/13] crypto: x86/crc32 " Ard Biesheuvel
2023-04-12 11:00 ` [PATCH v2 13/13] crypto: x86/sha " Ard Biesheuvel
2023-04-12 18:38 ` [PATCH v2 00/13] crypto: x86 - avoid absolute references Kees Cook
2023-04-20 10:21 ` Herbert Xu

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20230412110035.361447-7-ardb@kernel.org \
    --to=ardb@kernel.org \
    --cc=ebiggers@kernel.org \
    --cc=herbert@gondor.apana.org.au \
    --cc=keescook@chromium.org \
    --cc=linux-crypto@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.