kernel_optimize_test/arch/mips/kernel/r4k_switch.S
Paul Burton 1a3d59579b MIPS: Tidy up FPU context switching
Rather than saving the scalar FP or vector context in the assembly
resume function, reuse the existing C code we have in fpu.h to do
exactly that. This reduces duplication, results in a much easier to read
resume function & should allow the compiler to optimise out more MSA
code due to is_msa_enabled()/cpu_has_msa being known-zero at compile
time for kernels without MSA support.

Signed-off-by: Paul Burton <paul.burton@imgtec.com>
Cc: linux-mips@linux-mips.org
Cc: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com>
Cc: Maciej W. Rozycki <macro@linux-mips.org>
Cc: linux-kernel@vger.kernel.org
Cc: James Hogan <james.hogan@imgtec.com>
Cc: Markos Chandras <markos.chandras@imgtec.com>
Cc: Manuel Lauss <manuel.lauss@gmail.com>
Patchwork: https://patchwork.linux-mips.org/patch/10830/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2015-09-03 12:08:05 +02:00

267 lines
5.1 KiB
ArmAsm

/*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*
* Copyright (C) 1994, 1995, 1996, 1998, 1999, 2002, 2003 Ralf Baechle
* Copyright (C) 1996 David S. Miller (davem@davemloft.net)
* Copyright (C) 1994, 1995, 1996, by Andreas Busse
* Copyright (C) 1999 Silicon Graphics, Inc.
* Copyright (C) 2000 MIPS Technologies, Inc.
* written by Carsten Langgaard, carstenl@mips.com
*/
#include <asm/asm.h>
#include <asm/cachectl.h>
#include <asm/fpregdef.h>
#include <asm/mipsregs.h>
#include <asm/asm-offsets.h>
#include <asm/pgtable-bits.h>
#include <asm/regdef.h>
#include <asm/stackframe.h>
#include <asm/thread_info.h>
#include <asm/asmmacro.h>
/* preprocessor replaces the fp in ".set fp=64" with $30 otherwise */
#undef fp
/*
* Offset to the current process status flags, the first 32 bytes of the
* stack are not used.
*/
#define ST_OFF (_THREAD_SIZE - 32 - PT_SIZE + PT_STATUS)
#ifndef USE_ALTERNATE_RESUME_IMPL
/*
* task_struct *resume(task_struct *prev, task_struct *next,
* struct thread_info *next_ti)
*/
.align 5
LEAF(resume)
mfc0 t1, CP0_STATUS
LONG_S t1, THREAD_STATUS(a0)
cpu_save_nonscratch a0
LONG_S ra, THREAD_REG31(a0)
#if defined(CONFIG_CC_STACKPROTECTOR) && !defined(CONFIG_SMP)
PTR_LA t8, __stack_chk_guard
LONG_L t9, TASK_STACK_CANARY(a1)
LONG_S t9, 0(t8)
#endif
/*
* The order of restoring the registers takes care of the race
* updating $28, $29 and kernelsp without disabling ints.
*/
move $28, a2
cpu_restore_nonscratch a1
PTR_ADDU t0, $28, _THREAD_SIZE - 32
set_saved_sp t0, t1, t2
mfc0 t1, CP0_STATUS /* Do we really need this? */
li a3, 0xff01
and t1, a3
LONG_L a2, THREAD_STATUS(a1)
nor a3, $0, a3
and a2, a3
or a2, t1
mtc0 a2, CP0_STATUS
move v0, a0
jr ra
END(resume)
#endif /* USE_ALTERNATE_RESUME_IMPL */
/*
* Save a thread's fp context.
*/
LEAF(_save_fp)
#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) || \
defined(CONFIG_CPU_MIPS32_R6)
mfc0 t0, CP0_STATUS
#endif
fpu_save_double a0 t0 t1 # clobbers t1
jr ra
END(_save_fp)
/*
* Restore a thread's fp context.
*/
LEAF(_restore_fp)
#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) || \
defined(CONFIG_CPU_MIPS32_R6)
mfc0 t0, CP0_STATUS
#endif
fpu_restore_double a0 t0 t1 # clobbers t1
jr ra
END(_restore_fp)
#ifdef CONFIG_CPU_HAS_MSA
/*
* Save a thread's MSA vector context.
*/
LEAF(_save_msa)
msa_save_all a0
jr ra
END(_save_msa)
/*
* Restore a thread's MSA vector context.
*/
LEAF(_restore_msa)
msa_restore_all a0
jr ra
END(_restore_msa)
LEAF(_init_msa_upper)
msa_init_all_upper
jr ra
END(_init_msa_upper)
#endif
/*
* Load the FPU with signalling NANS. This bit pattern we're using has
* the property that no matter whether considered as single or as double
* precision represents signaling NANS.
*
* The value to initialize fcr31 to comes in $a0.
*/
.set push
SET_HARDFLOAT
LEAF(_init_fpu)
mfc0 t0, CP0_STATUS
li t1, ST0_CU1
or t0, t1
mtc0 t0, CP0_STATUS
enable_fpu_hazard
ctc1 a0, fcr31
li t1, -1 # SNaN
#ifdef CONFIG_64BIT
sll t0, t0, 5
bgez t0, 1f # 16 / 32 register mode?
dmtc1 t1, $f1
dmtc1 t1, $f3
dmtc1 t1, $f5
dmtc1 t1, $f7
dmtc1 t1, $f9
dmtc1 t1, $f11
dmtc1 t1, $f13
dmtc1 t1, $f15
dmtc1 t1, $f17
dmtc1 t1, $f19
dmtc1 t1, $f21
dmtc1 t1, $f23
dmtc1 t1, $f25
dmtc1 t1, $f27
dmtc1 t1, $f29
dmtc1 t1, $f31
1:
#endif
#ifdef CONFIG_CPU_MIPS32
mtc1 t1, $f0
mtc1 t1, $f1
mtc1 t1, $f2
mtc1 t1, $f3
mtc1 t1, $f4
mtc1 t1, $f5
mtc1 t1, $f6
mtc1 t1, $f7
mtc1 t1, $f8
mtc1 t1, $f9
mtc1 t1, $f10
mtc1 t1, $f11
mtc1 t1, $f12
mtc1 t1, $f13
mtc1 t1, $f14
mtc1 t1, $f15
mtc1 t1, $f16
mtc1 t1, $f17
mtc1 t1, $f18
mtc1 t1, $f19
mtc1 t1, $f20
mtc1 t1, $f21
mtc1 t1, $f22
mtc1 t1, $f23
mtc1 t1, $f24
mtc1 t1, $f25
mtc1 t1, $f26
mtc1 t1, $f27
mtc1 t1, $f28
mtc1 t1, $f29
mtc1 t1, $f30
mtc1 t1, $f31
#if defined(CONFIG_CPU_MIPS32_R2) || defined(CONFIG_CPU_MIPS32_R6)
.set push
.set MIPS_ISA_LEVEL_RAW
.set fp=64
sll t0, t0, 5 # is Status.FR set?
bgez t0, 1f # no: skip setting upper 32b
mthc1 t1, $f0
mthc1 t1, $f1
mthc1 t1, $f2
mthc1 t1, $f3
mthc1 t1, $f4
mthc1 t1, $f5
mthc1 t1, $f6
mthc1 t1, $f7
mthc1 t1, $f8
mthc1 t1, $f9
mthc1 t1, $f10
mthc1 t1, $f11
mthc1 t1, $f12
mthc1 t1, $f13
mthc1 t1, $f14
mthc1 t1, $f15
mthc1 t1, $f16
mthc1 t1, $f17
mthc1 t1, $f18
mthc1 t1, $f19
mthc1 t1, $f20
mthc1 t1, $f21
mthc1 t1, $f22
mthc1 t1, $f23
mthc1 t1, $f24
mthc1 t1, $f25
mthc1 t1, $f26
mthc1 t1, $f27
mthc1 t1, $f28
mthc1 t1, $f29
mthc1 t1, $f30
mthc1 t1, $f31
1: .set pop
#endif /* CONFIG_CPU_MIPS32_R2 || CONFIG_CPU_MIPS32_R6 */
#else
.set MIPS_ISA_ARCH_LEVEL_RAW
dmtc1 t1, $f0
dmtc1 t1, $f2
dmtc1 t1, $f4
dmtc1 t1, $f6
dmtc1 t1, $f8
dmtc1 t1, $f10
dmtc1 t1, $f12
dmtc1 t1, $f14
dmtc1 t1, $f16
dmtc1 t1, $f18
dmtc1 t1, $f20
dmtc1 t1, $f22
dmtc1 t1, $f24
dmtc1 t1, $f26
dmtc1 t1, $f28
dmtc1 t1, $f30
#endif
jr ra
END(_init_fpu)
.set pop /* SET_HARDFLOAT */