mirror of
https://github.com/edk2-porting/linux-next.git
synced 2024-12-22 20:23:57 +08:00
6917c857e3
Alternate macro mode is not a property of a macro definition, but a
gas runtime state that alters the way macros are expanded for ever
after (until .noaltmacro is seen).
This means that subsequent assembly code that calls other macros can
break if fpsimdmacros.h is included.
Since these instruction sequences are simple (if dull -- but in a
good way), this patch solves the problem by simply expanding the
.irp loops. The pre-existing fpsimd_{save,restore} macros weren't
rolled with .irp anyway and the sequences affected are short, so
this change restores consistency at little cost.
Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
134 lines
4.1 KiB
C
134 lines
4.1 KiB
C
/*
|
|
* FP/SIMD state saving and restoring macros
|
|
*
|
|
* Copyright (C) 2012 ARM Ltd.
|
|
* Author: Catalin Marinas <catalin.marinas@arm.com>
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License version 2 as
|
|
* published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
* GNU General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* along with this program. If not, see <http://www.gnu.org/licenses/>.
|
|
*/
|
|
|
|
.macro fpsimd_save state, tmpnr
|
|
stp q0, q1, [\state, #16 * 0]
|
|
stp q2, q3, [\state, #16 * 2]
|
|
stp q4, q5, [\state, #16 * 4]
|
|
stp q6, q7, [\state, #16 * 6]
|
|
stp q8, q9, [\state, #16 * 8]
|
|
stp q10, q11, [\state, #16 * 10]
|
|
stp q12, q13, [\state, #16 * 12]
|
|
stp q14, q15, [\state, #16 * 14]
|
|
stp q16, q17, [\state, #16 * 16]
|
|
stp q18, q19, [\state, #16 * 18]
|
|
stp q20, q21, [\state, #16 * 20]
|
|
stp q22, q23, [\state, #16 * 22]
|
|
stp q24, q25, [\state, #16 * 24]
|
|
stp q26, q27, [\state, #16 * 26]
|
|
stp q28, q29, [\state, #16 * 28]
|
|
stp q30, q31, [\state, #16 * 30]!
|
|
mrs x\tmpnr, fpsr
|
|
str w\tmpnr, [\state, #16 * 2]
|
|
mrs x\tmpnr, fpcr
|
|
str w\tmpnr, [\state, #16 * 2 + 4]
|
|
.endm
|
|
|
|
.macro fpsimd_restore_fpcr state, tmp
|
|
/*
|
|
* Writes to fpcr may be self-synchronising, so avoid restoring
|
|
* the register if it hasn't changed.
|
|
*/
|
|
mrs \tmp, fpcr
|
|
cmp \tmp, \state
|
|
b.eq 9999f
|
|
msr fpcr, \state
|
|
9999:
|
|
.endm
|
|
|
|
/* Clobbers \state */
|
|
.macro fpsimd_restore state, tmpnr
|
|
ldp q0, q1, [\state, #16 * 0]
|
|
ldp q2, q3, [\state, #16 * 2]
|
|
ldp q4, q5, [\state, #16 * 4]
|
|
ldp q6, q7, [\state, #16 * 6]
|
|
ldp q8, q9, [\state, #16 * 8]
|
|
ldp q10, q11, [\state, #16 * 10]
|
|
ldp q12, q13, [\state, #16 * 12]
|
|
ldp q14, q15, [\state, #16 * 14]
|
|
ldp q16, q17, [\state, #16 * 16]
|
|
ldp q18, q19, [\state, #16 * 18]
|
|
ldp q20, q21, [\state, #16 * 20]
|
|
ldp q22, q23, [\state, #16 * 22]
|
|
ldp q24, q25, [\state, #16 * 24]
|
|
ldp q26, q27, [\state, #16 * 26]
|
|
ldp q28, q29, [\state, #16 * 28]
|
|
ldp q30, q31, [\state, #16 * 30]!
|
|
ldr w\tmpnr, [\state, #16 * 2]
|
|
msr fpsr, x\tmpnr
|
|
ldr w\tmpnr, [\state, #16 * 2 + 4]
|
|
fpsimd_restore_fpcr x\tmpnr, \state
|
|
.endm
|
|
|
|
.macro fpsimd_save_partial state, numnr, tmpnr1, tmpnr2
|
|
mrs x\tmpnr1, fpsr
|
|
str w\numnr, [\state, #8]
|
|
mrs x\tmpnr2, fpcr
|
|
stp w\tmpnr1, w\tmpnr2, [\state]
|
|
adr x\tmpnr1, 0f
|
|
add \state, \state, x\numnr, lsl #4
|
|
sub x\tmpnr1, x\tmpnr1, x\numnr, lsl #1
|
|
br x\tmpnr1
|
|
stp q30, q31, [\state, #-16 * 30 - 16]
|
|
stp q28, q29, [\state, #-16 * 28 - 16]
|
|
stp q26, q27, [\state, #-16 * 26 - 16]
|
|
stp q24, q25, [\state, #-16 * 24 - 16]
|
|
stp q22, q23, [\state, #-16 * 22 - 16]
|
|
stp q20, q21, [\state, #-16 * 20 - 16]
|
|
stp q18, q19, [\state, #-16 * 18 - 16]
|
|
stp q16, q17, [\state, #-16 * 16 - 16]
|
|
stp q14, q15, [\state, #-16 * 14 - 16]
|
|
stp q12, q13, [\state, #-16 * 12 - 16]
|
|
stp q10, q11, [\state, #-16 * 10 - 16]
|
|
stp q8, q9, [\state, #-16 * 8 - 16]
|
|
stp q6, q7, [\state, #-16 * 6 - 16]
|
|
stp q4, q5, [\state, #-16 * 4 - 16]
|
|
stp q2, q3, [\state, #-16 * 2 - 16]
|
|
stp q0, q1, [\state, #-16 * 0 - 16]
|
|
0:
|
|
.endm
|
|
|
|
.macro fpsimd_restore_partial state, tmpnr1, tmpnr2
|
|
ldp w\tmpnr1, w\tmpnr2, [\state]
|
|
msr fpsr, x\tmpnr1
|
|
fpsimd_restore_fpcr x\tmpnr2, x\tmpnr1
|
|
adr x\tmpnr1, 0f
|
|
ldr w\tmpnr2, [\state, #8]
|
|
add \state, \state, x\tmpnr2, lsl #4
|
|
sub x\tmpnr1, x\tmpnr1, x\tmpnr2, lsl #1
|
|
br x\tmpnr1
|
|
ldp q30, q31, [\state, #-16 * 30 - 16]
|
|
ldp q28, q29, [\state, #-16 * 28 - 16]
|
|
ldp q26, q27, [\state, #-16 * 26 - 16]
|
|
ldp q24, q25, [\state, #-16 * 24 - 16]
|
|
ldp q22, q23, [\state, #-16 * 22 - 16]
|
|
ldp q20, q21, [\state, #-16 * 20 - 16]
|
|
ldp q18, q19, [\state, #-16 * 18 - 16]
|
|
ldp q16, q17, [\state, #-16 * 16 - 16]
|
|
ldp q14, q15, [\state, #-16 * 14 - 16]
|
|
ldp q12, q13, [\state, #-16 * 12 - 16]
|
|
ldp q10, q11, [\state, #-16 * 10 - 16]
|
|
ldp q8, q9, [\state, #-16 * 8 - 16]
|
|
ldp q6, q7, [\state, #-16 * 6 - 16]
|
|
ldp q4, q5, [\state, #-16 * 4 - 16]
|
|
ldp q2, q3, [\state, #-16 * 2 - 16]
|
|
ldp q0, q1, [\state, #-16 * 0 - 16]
|
|
0:
|
|
.endm
|