mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Huang Ying <ying.huang@intel.com>
To: Ingo Molnar <mingo@elte.hu>,
	Herbert Xu <herbert@gondor.apana.org.au>,
	"H. Peter Anvin" <hpa@zytor.com>
Cc: "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"linux-crypto@vger.kernel.org" <linux-crypto@vger.kernel.org>
Subject: [PATCH 1/2] x86, crypto, Generate .byte code for some new instructions via gas macro
Date: Thu, 05 Nov 2009 14:44:15 +0800	[thread overview]
Message-ID: <1257403455.22519.249.camel@yhuang-dev.sh.intel.com> (raw)

It will take some time for binutils (gas) to support some newly added
instructions, such as SSE4.1 instructions or the AES-NI instructions
found in upcoming Intel CPU.

To make the source code can be compiled by old binutils, .byte code is
used instead of the assembly instruction. But the readability and
flexibility of raw .byte code is not good.

This patch solves the issue of raw .byte code via generating it via
assembly instruction like gas macro. The syntax is as close as
possible to real assembly instruction.

Some helper macros such as MODRM is not a full feature
implementation. It can be extended when necessary.

Signed-off-by: Huang Ying <ying.huang@intel.com>
---
 arch/x86/include/asm/inst.h |  150 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 150 insertions(+)

--- /dev/null
+++ b/arch/x86/include/asm/inst.h
@@ -0,0 +1,150 @@
+/*
+ * Generate .byte code for some instructions not supported by old
+ * binutils.
+ */
+#ifndef X86_ASM_INST_H
+#define X86_ASM_INST_H
+
+#ifdef __ASSEMBLY__
+
+	.macro XMM_NUM opd xmm
+	.ifc \xmm,%xmm0
+	\opd = 0
+	.endif
+	.ifc \xmm,%xmm1
+	\opd = 1
+	.endif
+	.ifc \xmm,%xmm2
+	\opd = 2
+	.endif
+	.ifc \xmm,%xmm3
+	\opd = 3
+	.endif
+	.ifc \xmm,%xmm4
+	\opd = 4
+	.endif
+	.ifc \xmm,%xmm5
+	\opd = 5
+	.endif
+	.ifc \xmm,%xmm6
+	\opd = 6
+	.endif
+	.ifc \xmm,%xmm7
+	\opd = 7
+	.endif
+	.ifc \xmm,%xmm8
+	\opd = 8
+	.endif
+	.ifc \xmm,%xmm9
+	\opd = 9
+	.endif
+	.ifc \xmm,%xmm10
+	\opd = 10
+	.endif
+	.ifc \xmm,%xmm11
+	\opd = 11
+	.endif
+	.ifc \xmm,%xmm12
+	\opd = 12
+	.endif
+	.ifc \xmm,%xmm13
+	\opd = 13
+	.endif
+	.ifc \xmm,%xmm14
+	\opd = 14
+	.endif
+	.ifc \xmm,%xmm15
+	\opd = 15
+	.endif
+	.endm
+
+	.macro PFX_OPD_SIZE
+	.byte 0x66
+	.endm
+
+	.macro PFX_REX opd1 opd2
+	.if (\opd1 | \opd2) & 8
+	.byte 0x40 | ((\opd1 & 8) >> 3) | ((\opd2 & 8) >> 1)
+	.endif
+	.endm
+
+	.macro MODRM mod opd1 opd2
+	.byte \mod | (\opd1 & 7) | ((\opd2 & 7) << 3)
+	.endm
+
+	.macro PSHUFB_XMM xmm1 xmm2
+	XMM_NUM pshufb_opd1 \xmm1
+	XMM_NUM pshufb_opd2 \xmm2
+	PFX_OPD_SIZE
+	PFX_REX pshufb_opd1 pshufb_opd2
+	.byte 0x0f, 0x38, 0x00
+	MODRM 0xc0 pshufb_opd1 pshufb_opd2
+	.endm
+
+	.macro PCLMULQDQ imm8 xmm1 xmm2
+	XMM_NUM clmul_opd1 \xmm1
+	XMM_NUM clmul_opd2 \xmm2
+	PFX_OPD_SIZE
+	PFX_REX clmul_opd1 clmul_opd2
+	.byte 0x0f, 0x3a, 0x44
+	MODRM 0xc0 clmul_opd1 clmul_opd2
+	.byte \imm8
+	.endm
+
+	.macro AESKEYGENASSIST rcon xmm1 xmm2
+	XMM_NUM aeskeygen_opd1 \xmm1
+	XMM_NUM aeskeygen_opd2 \xmm2
+	PFX_OPD_SIZE
+	PFX_REX aeskeygen_opd1 aeskeygen_opd2
+	.byte 0x0f, 0x3a, 0xdf
+	MODRM 0xc0 aeskeygen_opd1 aeskeygen_opd2
+	.byte \rcon
+	.endm
+
+	.macro AESIMC xmm1 xmm2
+	XMM_NUM aesimc_opd1 \xmm1
+	XMM_NUM aesimc_opd2 \xmm2
+	PFX_OPD_SIZE
+	PFX_REX aesimc_opd1 aesimc_opd2
+	.byte 0x0f, 0x38, 0xdb
+	MODRM 0xc0 aesimc_opd1 aesimc_opd2
+	.endm
+
+	.macro AESENC xmm1 xmm2
+	XMM_NUM aesenc_opd1 \xmm1
+	XMM_NUM aesenc_opd2 \xmm2
+	PFX_OPD_SIZE
+	PFX_REX aesenc_opd1 aesenc_opd2
+	.byte 0x0f, 0x38, 0xdc
+	MODRM 0xc0 aesenc_opd1 aesenc_opd2
+	.endm
+
+	.macro AESENCLAST xmm1 xmm2
+	XMM_NUM aesenclast_opd1 \xmm1
+	XMM_NUM aesenclast_opd2 \xmm2
+	PFX_OPD_SIZE
+	PFX_REX aesenclast_opd1 aesenclast_opd2
+	.byte 0x0f, 0x38, 0xdd
+	MODRM 0xc0 aesenclast_opd1 aesenclast_opd2
+	.endm
+
+	.macro AESDEC xmm1 xmm2
+	XMM_NUM aesdec_opd1 \xmm1
+	XMM_NUM aesdec_opd2 \xmm2
+	PFX_OPD_SIZE
+	PFX_REX aesdec_opd1 aesdec_opd2
+	.byte 0x0f, 0x38, 0xde
+	MODRM 0xc0 aesdec_opd1 aesdec_opd2
+	.endm
+
+	.macro AESDECLAST xmm1 xmm2
+	XMM_NUM aesdeclast_opd1 \xmm1
+	XMM_NUM aesdeclast_opd2 \xmm2
+	PFX_OPD_SIZE
+	PFX_REX aesdeclast_opd1 aesdeclast_opd2
+	.byte 0x0f, 0x38, 0xdf
+	MODRM 0xc0 aesdeclast_opd1 aesdeclast_opd2
+	.endm
+#endif
+
+#endif



             reply	other threads:[~2009-11-05  6:44 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-11-05  6:44 Huang Ying [this message]
2009-11-05 14:23 ` Herbert Xu
2009-11-05 16:58   ` H. Peter Anvin
2009-11-08 10:56     ` Ingo Molnar
2009-11-09 18:52       ` Herbert Xu
2009-11-05 14:40 ` Brian Gerst

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=1257403455.22519.249.camel@yhuang-dev.sh.intel.com \
    --to=ying.huang@intel.com \
    --cc=herbert@gondor.apana.org.au \
    --cc=hpa@zytor.com \
    --cc=linux-crypto@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®