lkml.org 
[lkml]   [2020]   [Jun]   [26]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH v3 2/3] ARM: use VFP assembler mnemonics in register load/store macros
Date
The integrated assembler of Clang 10 and earlier do 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}
^

This has been addressed with Clang 11 [0]. However, to support earlier
versions of Clang and for better readability use of VFP assembler
mnemonics still is preferred.

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.

[0] https://reviews.llvm.org/D59733

Link: https://github.com/ClangBuiltLinux/linux/issues/905
Signed-off-by: Stefan Agner <stefan@agner.ch>
---
Changes in v3:
- Reworded commit message, adding hint that Clang 11 won't have this
restriction any longer

Changes in v2:
- Add link in commit message

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
--
2.27.0
\
 
 \ /
  Last update: 2020-06-26 23:27    [W:0.034 / U:2.020 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site