mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-18 15:36:46 +07:00
b99afae139
The naked attribute is known to confuse some old gcc versions when
function arguments aren't explicitly listed as inline assembly operands
despite the gcc documentation. That resulted in commit 9a40ac8615
("ARM: 6164/1: Add kto and kfrom to input operands list.").
Yet that commit has problems of its own by having assembly operand
constraints completely wrong. If the generated code has been OK since
then, it is due to luck rather than correctness. So this patch also
provides proper assembly operand constraints, and removes two instances
of redundant register usages in the implementation while at it.
Inspection of the generated code with this patch doesn't show any
obvious quality degradation either, so not relying on __naked at all
will make the code less fragile, and avoid some issues with clang.
The only remaining __naked instances (excluding the kprobes test cases)
are exynos_pm_power_up_setup(), tc2_pm_power_up_setup() and
cci_enable_port_for_self(. But in the first two cases, only the function
address is used by the compiler with no chance of inlining it by
mistake, and the third case is called from assembly code only. And the
fact that no stack is available when the corresponding code is executed
does warrant the __naked usage in those cases.
Signed-off-by: Nicolas Pitre <nico@linaro.org>
Reviewed-by: Stefan Agner <stefan@agner.ch>
Tested-by: Stefan Agner <stefan@agner.ch>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
95 lines
2.8 KiB
C
95 lines
2.8 KiB
C
/*
|
|
* linux/arch/arm/mm/copypage-v4wb.c
|
|
*
|
|
* Copyright (C) 1995-1999 Russell King
|
|
*
|
|
* 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.
|
|
*/
|
|
#include <linux/init.h>
|
|
#include <linux/highmem.h>
|
|
|
|
/*
|
|
* ARMv4 optimised copy_user_highpage
|
|
*
|
|
* We flush the destination cache lines just before we write the data into the
|
|
* corresponding address. Since the Dcache is read-allocate, this removes the
|
|
* Dcache aliasing issue. The writes will be forwarded to the write buffer,
|
|
* and merged as appropriate.
|
|
*
|
|
* Note: We rely on all ARMv4 processors implementing the "invalidate D line"
|
|
* instruction. If your processor does not supply this, you have to write your
|
|
* own copy_user_highpage that does the right thing.
|
|
*/
|
|
static void v4wb_copy_user_page(void *kto, const void *kfrom)
|
|
{
|
|
int tmp;
|
|
|
|
asm volatile ("\
|
|
ldmia %1!, {r3, r4, ip, lr} @ 4\n\
|
|
1: mcr p15, 0, %0, c7, c6, 1 @ 1 invalidate D line\n\
|
|
stmia %0!, {r3, r4, ip, lr} @ 4\n\
|
|
ldmia %1!, {r3, r4, ip, lr} @ 4+1\n\
|
|
stmia %0!, {r3, r4, ip, lr} @ 4\n\
|
|
ldmia %1!, {r3, r4, ip, lr} @ 4\n\
|
|
mcr p15, 0, %0, c7, c6, 1 @ 1 invalidate D line\n\
|
|
stmia %0!, {r3, r4, ip, lr} @ 4\n\
|
|
ldmia %1!, {r3, r4, ip, lr} @ 4\n\
|
|
subs %2, %2, #1 @ 1\n\
|
|
stmia %0!, {r3, r4, ip, lr} @ 4\n\
|
|
ldmneia %1!, {r3, r4, ip, lr} @ 4\n\
|
|
bne 1b @ 1\n\
|
|
mcr p15, 0, %1, c7, c10, 4 @ 1 drain WB"
|
|
: "+&r" (kto), "+&r" (kfrom), "=&r" (tmp)
|
|
: "2" (PAGE_SIZE / 64)
|
|
: "r3", "r4", "ip", "lr");
|
|
}
|
|
|
|
void v4wb_copy_user_highpage(struct page *to, struct page *from,
|
|
unsigned long vaddr, struct vm_area_struct *vma)
|
|
{
|
|
void *kto, *kfrom;
|
|
|
|
kto = kmap_atomic(to);
|
|
kfrom = kmap_atomic(from);
|
|
flush_cache_page(vma, vaddr, page_to_pfn(from));
|
|
v4wb_copy_user_page(kto, kfrom);
|
|
kunmap_atomic(kfrom);
|
|
kunmap_atomic(kto);
|
|
}
|
|
|
|
/*
|
|
* ARMv4 optimised clear_user_page
|
|
*
|
|
* Same story as above.
|
|
*/
|
|
void v4wb_clear_user_highpage(struct page *page, unsigned long vaddr)
|
|
{
|
|
void *ptr, *kaddr = kmap_atomic(page);
|
|
asm volatile("\
|
|
mov r1, %2 @ 1\n\
|
|
mov r2, #0 @ 1\n\
|
|
mov r3, #0 @ 1\n\
|
|
mov ip, #0 @ 1\n\
|
|
mov lr, #0 @ 1\n\
|
|
1: mcr p15, 0, %0, c7, c6, 1 @ 1 invalidate D line\n\
|
|
stmia %0!, {r2, r3, ip, lr} @ 4\n\
|
|
stmia %0!, {r2, r3, ip, lr} @ 4\n\
|
|
mcr p15, 0, %0, c7, c6, 1 @ 1 invalidate D line\n\
|
|
stmia %0!, {r2, r3, ip, lr} @ 4\n\
|
|
stmia %0!, {r2, r3, ip, lr} @ 4\n\
|
|
subs r1, r1, #1 @ 1\n\
|
|
bne 1b @ 1\n\
|
|
mcr p15, 0, r1, c7, c10, 4 @ 1 drain WB"
|
|
: "=r" (ptr)
|
|
: "0" (kaddr), "I" (PAGE_SIZE / 64)
|
|
: "r1", "r2", "r3", "ip", "lr");
|
|
kunmap_atomic(kaddr);
|
|
}
|
|
|
|
struct cpu_user_fns v4wb_user_fns __initdata = {
|
|
.cpu_clear_user_highpage = v4wb_clear_user_highpage,
|
|
.cpu_copy_user_highpage = v4wb_copy_user_highpage,
|
|
};
|