LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Stefan Agner <stefan@agner.ch>
To: linux@armlinux.org.uk
Cc: arnd@arndb.de, ard.biesheuvel@linaro.org, robin.murphy@arm.com,
	yamada.masahiro@socionext.com, ndesaulniers@google.com,
	manojgupta@google.com, jiancai@google.com,
	linux-arm-kernel@lists.infradead.org,
	linux-kernel@vger.kernel.org, clang-built-linux@googlegroups.com,
	Stefan Agner <stefan@agner.ch>
Subject: [PATCH 2/3] ARM: use VFP assembler mnemonics in register load/store macros
Date: Tue, 10 Mar 2020 23:01:20 +0100	[thread overview]
Message-ID: <5a0ae07ce1eae117dcda1f7b2f0b4d13eb90f1d6.1583360296.git.stefan@agner.ch> (raw)
In-Reply-To: <cover.1583360296.git.stefan@agner.ch>

Clang's integrated assembler does not allow to access the VFP registers
through the coprocessor load/store instructions:
<instantiation>:4:6: error: invalid operand for instruction
 LDC p11, cr0, [r10],#32*4 @ FLDMIAD r10!, {d0-d15}
     ^

Replace the coprocessor load/store instructions with explicit assembler
mnemonics to accessing the floating point coprocessor registers. Use
assembler directives to select the appropriate FPU version.

This allows to build these macros with GNU assembler as well as with
Clang's built-in assembler.

Signed-off-by: Stefan Agner <stefan@agner.ch>
---
 arch/arm/include/asm/vfpmacros.h | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/arch/arm/include/asm/vfpmacros.h b/arch/arm/include/asm/vfpmacros.h
index 628c336e8e3b..947ee5395e1f 100644
--- a/arch/arm/include/asm/vfpmacros.h
+++ b/arch/arm/include/asm/vfpmacros.h
@@ -19,23 +19,25 @@
 
 	@ read all the working registers back into the VFP
 	.macro	VFPFLDMIA, base, tmp
+	.fpu	vfpv2
 #if __LINUX_ARM_ARCH__ < 6
-	LDC	p11, cr0, [\base],#33*4		    @ FLDMIAX \base!, {d0-d15}
+	fldmiax	\base!, {d0-d15}
 #else
-	LDC	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d0-d15}
+	vldmia	\base!, {d0-d15}
 #endif
 #ifdef CONFIG_VFPv3
+	.fpu	vfpv3
 #if __LINUX_ARM_ARCH__ <= 6
 	ldr	\tmp, =elf_hwcap		    @ may not have MVFR regs
 	ldr	\tmp, [\tmp, #0]
 	tst	\tmp, #HWCAP_VFPD32
-	ldclne	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
+	vldmiane \base!, {d16-d31}
 	addeq	\base, \base, #32*4		    @ step over unused register space
 #else
 	VFPFMRX	\tmp, MVFR0			    @ Media and VFP Feature Register 0
 	and	\tmp, \tmp, #MVFR0_A_SIMD_MASK	    @ A_SIMD field
 	cmp	\tmp, #2			    @ 32 x 64bit registers?
-	ldcleq	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
+	vldmiaeq \base!, {d16-d31}
 	addne	\base, \base, #32*4		    @ step over unused register space
 #endif
 #endif
@@ -44,22 +46,23 @@
 	@ write all the working registers out of the VFP
 	.macro	VFPFSTMIA, base, tmp
 #if __LINUX_ARM_ARCH__ < 6
-	STC	p11, cr0, [\base],#33*4		    @ FSTMIAX \base!, {d0-d15}
+	fstmiax	\base!, {d0-d15}
 #else
-	STC	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d0-d15}
+	vstmia	\base!, {d0-d15}
 #endif
 #ifdef CONFIG_VFPv3
+	.fpu	vfpv3
 #if __LINUX_ARM_ARCH__ <= 6
 	ldr	\tmp, =elf_hwcap		    @ may not have MVFR regs
 	ldr	\tmp, [\tmp, #0]
 	tst	\tmp, #HWCAP_VFPD32
-	stclne	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
+	vstmiane \base!, {d16-d31}
 	addeq	\base, \base, #32*4		    @ step over unused register space
 #else
 	VFPFMRX	\tmp, MVFR0			    @ Media and VFP Feature Register 0
 	and	\tmp, \tmp, #MVFR0_A_SIMD_MASK	    @ A_SIMD field
 	cmp	\tmp, #2			    @ 32 x 64bit registers?
-	stcleq	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
+	vstmiaeq \base!, {d16-d31}
 	addne	\base, \base, #32*4		    @ step over unused register space
 #endif
 #endif
-- 
2.25.1


  parent reply	other threads:[~2020-03-10 22:01 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-10 22:01 [PATCH 0/3] ARM: make use of UAL VFP mnemonics when possible Stefan Agner
2020-03-10 22:01 ` [PATCH 1/3] ARM: use .fpu assembler directives instead of assembler arguments Stefan Agner
2020-03-10 22:01 ` Stefan Agner [this message]
2020-03-10 22:01 ` [PATCH 3/3] ARM: use VFP assembler mnemonics if available Stefan Agner

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=5a0ae07ce1eae117dcda1f7b2f0b4d13eb90f1d6.1583360296.git.stefan@agner.ch \
    --to=stefan@agner.ch \
    --cc=ard.biesheuvel@linaro.org \
    --cc=arnd@arndb.de \
    --cc=clang-built-linux@googlegroups.com \
    --cc=jiancai@google.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux@armlinux.org.uk \
    --cc=manojgupta@google.com \
    --cc=ndesaulniers@google.com \
    --cc=robin.murphy@arm.com \
    --cc=yamada.masahiro@socionext.com \
    --subject='Re: [PATCH 2/3] ARM: use VFP assembler mnemonics in register load/store macros' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).