a2faac3986
Similar to commita6c30873ee("ARM: 8989/1: use .fpu assembler directives instead of assembler arguments"). GCC and GNU binutils support setting the "sub arch" via -march=, -Wa,-march, target function attribute, and .arch assembler directive. Clang was missing support for -Wa,-march=, but this was implemented in clang-13. The behavior of both GCC and Clang is to prefer -Wa,-march= over -march= for assembler and assembler-with-cpp sources, but Clang will warn about the -march= being unused. clang: warning: argument unused during compilation: '-march=armv6k' [-Wunused-command-line-argument] Since most assembler is non-conditionally assembled with one sub arch (modulo arch/arm/delay-loop.S which conditionally is assembled as armv4 based on CONFIG_ARCH_RPC, and arch/arm/mach-at91/pm-suspend.S which is conditionally assembled as armv7-a based on CONFIG_CPU_V7), prefer the .arch assembler directive. Add a few more instances found in compile testing as found by Arnd and Nathan. Link:1d51c699b9Link: https://bugs.llvm.org/show_bug.cgi?id=48894 Link: https://github.com/ClangBuiltLinux/linux/issues/1195 Link: https://github.com/ClangBuiltLinux/linux/issues/1315 Suggested-by: Arnd Bergmann <arnd@arndb.de> Suggested-by: Nathan Chancellor <nathan@kernel.org> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Tested-by: Nathan Chancellor <nathan@kernel.org> Signed-off-by: Nick Desaulniers <ndesaulniers@google.com> Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
109 lines
3.1 KiB
C
109 lines
3.1 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/*
|
|
* linux/arch/arm/mm/copypage-feroceon.S
|
|
*
|
|
* Copyright (C) 2008 Marvell Semiconductors
|
|
*
|
|
* 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 feroceon_copy_user_page(void *kto, const void *kfrom)
|
|
{
|
|
int tmp;
|
|
|
|
asm volatile ("\
|
|
.arch armv5te \n\
|
|
1: ldmia %1!, {r2 - r7, ip, lr} \n\
|
|
pld [%1, #0] \n\
|
|
pld [%1, #32] \n\
|
|
pld [%1, #64] \n\
|
|
pld [%1, #96] \n\
|
|
pld [%1, #128] \n\
|
|
pld [%1, #160] \n\
|
|
pld [%1, #192] \n\
|
|
stmia %0, {r2 - r7, ip, lr} \n\
|
|
ldmia %1!, {r2 - r7, ip, lr} \n\
|
|
mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\
|
|
add %0, %0, #32 \n\
|
|
stmia %0, {r2 - r7, ip, lr} \n\
|
|
ldmia %1!, {r2 - r7, ip, lr} \n\
|
|
mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\
|
|
add %0, %0, #32 \n\
|
|
stmia %0, {r2 - r7, ip, lr} \n\
|
|
ldmia %1!, {r2 - r7, ip, lr} \n\
|
|
mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\
|
|
add %0, %0, #32 \n\
|
|
stmia %0, {r2 - r7, ip, lr} \n\
|
|
ldmia %1!, {r2 - r7, ip, lr} \n\
|
|
mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\
|
|
add %0, %0, #32 \n\
|
|
stmia %0, {r2 - r7, ip, lr} \n\
|
|
ldmia %1!, {r2 - r7, ip, lr} \n\
|
|
mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\
|
|
add %0, %0, #32 \n\
|
|
stmia %0, {r2 - r7, ip, lr} \n\
|
|
ldmia %1!, {r2 - r7, ip, lr} \n\
|
|
mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\
|
|
add %0, %0, #32 \n\
|
|
stmia %0, {r2 - r7, ip, lr} \n\
|
|
ldmia %1!, {r2 - r7, ip, lr} \n\
|
|
mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\
|
|
add %0, %0, #32 \n\
|
|
stmia %0, {r2 - r7, ip, lr} \n\
|
|
subs %2, %2, #(32 * 8) \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, %2, c7, c10, 4 @ drain WB"
|
|
: "+&r" (kto), "+&r" (kfrom), "=&r" (tmp)
|
|
: "2" (PAGE_SIZE)
|
|
: "r2", "r3", "r4", "r5", "r6", "r7", "ip", "lr");
|
|
}
|
|
|
|
void feroceon_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));
|
|
feroceon_copy_user_page(kto, kfrom);
|
|
kunmap_atomic(kfrom);
|
|
kunmap_atomic(kto);
|
|
}
|
|
|
|
void feroceon_clear_user_highpage(struct page *page, unsigned long vaddr)
|
|
{
|
|
void *ptr, *kaddr = kmap_atomic(page);
|
|
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);
|
|
}
|
|
|
|
struct cpu_user_fns feroceon_user_fns __initdata = {
|
|
.cpu_clear_user_highpage = feroceon_clear_user_highpage,
|
|
.cpu_copy_user_highpage = feroceon_copy_user_highpage,
|
|
};
|
|
|