linux/arch/arm/vfp/vfphw.S
Ard Biesheuvel 4708fb0413 ARM: vfp: Reimplement VFP exception entry in C code
En/disabling softirqs from asm code turned out to be trickier than
expected, so vfp_support_entry now returns by tail calling
__local_enable_bh_ip() and passing the same arguments that a C call to
local_bh_enable() would pass. However, this is slightly hacky, as we
don't want to carry our own implementation of local_bh_enable().

So let's bite the bullet, and get rid of the asm logic in
vfp_support_entry that reasons about whether or not to save and/or
reload the VFP state, and about whether or not an FP exception is
pending, and only keep the VFP loading logic as a function that is
callable from C.

Replicate the removed logic in vfp_entry(), and use the exact same
reasoning as in the asm code. To emphasize the correspondence, retain
some of the asm comments in the C version as well.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
2023-05-17 15:08:14 +02:00

153 lines
3.2 KiB
ArmAsm

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* linux/arch/arm/vfp/vfphw.S
*
* Copyright (C) 2004 ARM Limited.
* Written by Deep Blue Solutions Limited.
*/
#include <linux/init.h>
#include <linux/linkage.h>
#include <asm/thread_info.h>
#include <asm/vfpmacros.h>
#include <linux/kern_levels.h>
#include <asm/assembler.h>
#include <asm/asm-offsets.h>
.macro DBGSTR1, str, arg
#ifdef DEBUG
stmfd sp!, {r0-r3, ip, lr}
mov r1, \arg
ldr r0, =1f
bl _printk
ldmfd sp!, {r0-r3, ip, lr}
.pushsection .rodata, "a"
1: .ascii KERN_DEBUG "VFP: \str\n"
.byte 0
.previous
#endif
.endm
ENTRY(vfp_load_state)
@ Load the current VFP state
@ r0 - load location
@ returns FPEXC
DBGSTR1 "load VFP state %p", r0
@ Load the saved state back into the VFP
VFPFLDMIA r0, r1 @ reload the working registers while
@ FPEXC is in a safe state
ldmia r0, {r0-r3} @ load FPEXC, FPSCR, FPINST, FPINST2
tst r0, #FPEXC_EX @ is there additional state to restore?
beq 1f
VFPFMXR FPINST, r2 @ restore FPINST (only if FPEXC.EX is set)
tst r0, #FPEXC_FP2V @ is there an FPINST2 to write?
beq 1f
VFPFMXR FPINST2, r3 @ FPINST2 if needed (and present)
1:
VFPFMXR FPSCR, r1 @ restore status
ret lr
ENDPROC(vfp_load_state)
ENTRY(vfp_save_state)
@ Save the current VFP state
@ r0 - save location
@ r1 - FPEXC
DBGSTR1 "save VFP state %p", r0
VFPFSTMIA r0, r2 @ save the working registers
VFPFMRX r2, FPSCR @ current status
tst r1, #FPEXC_EX @ is there additional state to save?
beq 1f
VFPFMRX r3, FPINST @ FPINST (only if FPEXC.EX is set)
tst r1, #FPEXC_FP2V @ is there an FPINST2 to read?
beq 1f
VFPFMRX r12, FPINST2 @ FPINST2 if needed (and present)
1:
stmia r0, {r1, r2, r3, r12} @ save FPEXC, FPSCR, FPINST, FPINST2
ret lr
ENDPROC(vfp_save_state)
.macro tbl_branch, base, tmp, shift
#ifdef CONFIG_THUMB2_KERNEL
adr \tmp, 1f
add \tmp, \tmp, \base, lsl \shift
ret \tmp
#else
add pc, pc, \base, lsl \shift
mov r0, r0
#endif
1:
.endm
ENTRY(vfp_get_float)
tbl_branch r0, r3, #3
.fpu vfpv2
.irp dr,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
1: vmov r0, s\dr
ret lr
.org 1b + 8
.endr
.irp dr,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31
1: vmov r0, s\dr
ret lr
.org 1b + 8
.endr
ENDPROC(vfp_get_float)
ENTRY(vfp_put_float)
tbl_branch r1, r3, #3
.fpu vfpv2
.irp dr,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
1: vmov s\dr, r0
ret lr
.org 1b + 8
.endr
.irp dr,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31
1: vmov s\dr, r0
ret lr
.org 1b + 8
.endr
ENDPROC(vfp_put_float)
ENTRY(vfp_get_double)
tbl_branch r0, r3, #3
.fpu vfpv2
.irp dr,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
1: vmov r0, r1, d\dr
ret lr
.org 1b + 8
.endr
#ifdef CONFIG_VFPv3
@ d16 - d31 registers
.fpu vfpv3
.irp dr,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31
1: vmov r0, r1, d\dr
ret lr
.org 1b + 8
.endr
#endif
@ virtual register 16 (or 32 if VFPv3) for compare with zero
mov r0, #0
mov r1, #0
ret lr
ENDPROC(vfp_get_double)
ENTRY(vfp_put_double)
tbl_branch r2, r3, #3
.fpu vfpv2
.irp dr,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
1: vmov d\dr, r0, r1
ret lr
.org 1b + 8
.endr
#ifdef CONFIG_VFPv3
.fpu vfpv3
@ d16 - d31 registers
.irp dr,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31
1: vmov d\dr, r0, r1
ret lr
.org 1b + 8
.endr
#endif
ENDPROC(vfp_put_double)