Received-SPF: pass (google.com: domain of linux-crypto-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
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
Message-Id: <20230412110035.361447-7-ardb@kernel.org>
In-Reply-To: <20230412110035.361447-1-ardb@kernel.org>
References: <20230412110035.361447-1-ardb@kernel.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

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