mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
43ae286b7d
In all cases the kaddr is assigned an input register even though it is modified in the assembly code. Let's assign a new variable to the modified value and mark those inline asm with volatile otherwise they get optimized away because the output variable is otherwise not used. Also fix a few conversion errors in copypage-feroceon.c and copypage-v4mc.c. Signed-off-by: Nicolas Pitre <nico@marvell.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
112 lines
3.1 KiB
C
112 lines
3.1 KiB
C
/*
|
|
* linux/arch/arm/mm/copypage-feroceon.S
|
|
*
|
|
* Copyright (C) 2008 Marvell Semiconductors
|
|
*
|
|
* 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 handles copy_user_highpage and clear_user_page on Feroceon
|
|
* more optimally than the generic implementations.
|
|
*/
|
|
#include <linux/init.h>
|
|
#include <linux/highmem.h>
|
|
|
|
static void __attribute__((naked))
|
|
feroceon_copy_user_page(void *kto, const void *kfrom)
|
|
{
|
|
asm("\
|
|
stmfd sp!, {r4-r9, lr} \n\
|
|
mov ip, %0 \n\
|
|
1: mov lr, r1 \n\
|
|
ldmia r1!, {r2 - r9} \n\
|
|
pld [lr, #32] \n\
|
|
pld [lr, #64] \n\
|
|
pld [lr, #96] \n\
|
|
pld [lr, #128] \n\
|
|
pld [lr, #160] \n\
|
|
pld [lr, #192] \n\
|
|
pld [lr, #224] \n\
|
|
stmia r0, {r2 - r9} \n\
|
|
ldmia r1!, {r2 - r9} \n\
|
|
mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\
|
|
add r0, r0, #32 \n\
|
|
stmia r0, {r2 - r9} \n\
|
|
ldmia r1!, {r2 - r9} \n\
|
|
mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\
|
|
add r0, r0, #32 \n\
|
|
stmia r0, {r2 - r9} \n\
|
|
ldmia r1!, {r2 - r9} \n\
|
|
mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\
|
|
add r0, r0, #32 \n\
|
|
stmia r0, {r2 - r9} \n\
|
|
ldmia r1!, {r2 - r9} \n\
|
|
mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\
|
|
add r0, r0, #32 \n\
|
|
stmia r0, {r2 - r9} \n\
|
|
ldmia r1!, {r2 - r9} \n\
|
|
mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\
|
|
add r0, r0, #32 \n\
|
|
stmia r0, {r2 - r9} \n\
|
|
ldmia r1!, {r2 - r9} \n\
|
|
mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\
|
|
add r0, r0, #32 \n\
|
|
stmia r0, {r2 - r9} \n\
|
|
ldmia r1!, {r2 - r9} \n\
|
|
mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\
|
|
add r0, r0, #32 \n\
|
|
stmia r0, {r2 - r9} \n\
|
|
subs ip, ip, #(32 * 8) \n\
|
|
mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\
|
|
add r0, r0, #32 \n\
|
|
bne 1b \n\
|
|
mcr p15, 0, ip, c7, c10, 4 @ drain WB\n\
|
|
ldmfd sp!, {r4-r9, pc}"
|
|
:
|
|
: "I" (PAGE_SIZE));
|
|
}
|
|
|
|
void feroceon_copy_user_highpage(struct page *to, struct page *from,
|
|
unsigned long vaddr)
|
|
{
|
|
void *kto, *kfrom;
|
|
|
|
kto = kmap_atomic(to, KM_USER0);
|
|
kfrom = kmap_atomic(from, KM_USER1);
|
|
feroceon_copy_user_page(kto, kfrom);
|
|
kunmap_atomic(kfrom, KM_USER1);
|
|
kunmap_atomic(kto, KM_USER0);
|
|
}
|
|
|
|
void feroceon_clear_user_highpage(struct page *page, unsigned long vaddr)
|
|
{
|
|
void *ptr, *kaddr = kmap_atomic(page, KM_USER0);
|
|
asm volatile ("\
|
|
mov r1, %2 \n\
|
|
mov r2, #0 \n\
|
|
mov r3, #0 \n\
|
|
mov r4, #0 \n\
|
|
mov r5, #0 \n\
|
|
mov r6, #0 \n\
|
|
mov r7, #0 \n\
|
|
mov ip, #0 \n\
|
|
mov lr, #0 \n\
|
|
1: stmia %0, {r2-r7, ip, lr} \n\
|
|
subs r1, r1, #1 \n\
|
|
mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\
|
|
add %0, %0, #32 \n\
|
|
bne 1b \n\
|
|
mcr p15, 0, r1, c7, c10, 4 @ drain WB"
|
|
: "=r" (ptr)
|
|
: "0" (kaddr), "I" (PAGE_SIZE / 32)
|
|
: "r1", "r2", "r3", "r4", "r5", "r6", "r7", "ip", "lr");
|
|
kunmap_atomic(kaddr, KM_USER0);
|
|
}
|
|
|
|
struct cpu_user_fns feroceon_user_fns __initdata = {
|
|
.cpu_clear_user_highpage = feroceon_clear_user_highpage,
|
|
.cpu_copy_user_highpage = feroceon_copy_user_highpage,
|
|
};
|
|
|