linux/arch/arm/mm/copypage-xscale.c
Linus Torvalds 12679a2d7e Merge branch 'for-linus' of git://git.linaro.org/people/rmk/linux-arm
Pull more ARM updates from Russell King.

This got a fair number of conflicts with the <asm/system.h> split, but
also with some other sparse-irq and header file include cleanups.  They
all looked pretty trivial, though.

* 'for-linus' of git://git.linaro.org/people/rmk/linux-arm: (59 commits)
  ARM: fix Kconfig warning for HAVE_BPF_JIT
  ARM: 7361/1: provide XIP_VIRT_ADDR for no-MMU builds
  ARM: 7349/1: integrator: convert to sparse irqs
  ARM: 7259/3: net: JIT compiler for packet filters
  ARM: 7334/1: add jump label support
  ARM: 7333/2: jump label: detect %c support for ARM
  ARM: 7338/1: add support for early console output via semihosting
  ARM: use set_current_blocked() and block_sigmask()
  ARM: exec: remove redundant set_fs(USER_DS)
  ARM: 7332/1: extract out code patch function from kprobes
  ARM: 7331/1: extract out insn generation code from ftrace
  ARM: 7330/1: ftrace: use canonical Thumb-2 wide instruction format
  ARM: 7351/1: ftrace: remove useless memory checks
  ARM: 7316/1: kexec: EOI active and mask all interrupts in kexec crash path
  ARM: Versatile Express: add NO_IOPORT
  ARM: get rid of asm/irq.h in asm/prom.h
  ARM: 7319/1: Print debug info for SIGBUS in user faults
  ARM: 7318/1: gic: refactor irq_start assignment
  ARM: 7317/1: irq: avoid NULL check in for_each_irq_desc loop
  ARM: 7315/1: perf: add support for the Cortex-A7 PMU
  ...
2012-03-29 16:53:48 -07:00

136 lines
3.6 KiB
C

/*
* linux/arch/arm/lib/copypage-xscale.S
*
* Copyright (C) 1995-2005 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.
*
* This handles the mini data cache, as found on SA11x0 and XScale
* processors. When we copy a user page page, we map it in such a way
* that accesses to this page will not touch the main data cache, but
* will be cached in the mini data cache. This prevents us thrashing
* the main data cache on page faults.
*/
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/cacheflush.h>
#include "mm.h"
#define minicache_pgprot __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | \
L_PTE_MT_MINICACHE)
static DEFINE_RAW_SPINLOCK(minicache_lock);
/*
* XScale mini-dcache 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.
*/
static void __naked
mc_copy_user_page(void *from, void *to)
{
/*
* Strangely enough, best performance is achieved
* when prefetching destination as well. (NP)
*/
asm volatile(
"stmfd sp!, {r4, r5, lr} \n\
mov lr, %2 \n\
pld [r0, #0] \n\
pld [r0, #32] \n\
pld [r1, #0] \n\
pld [r1, #32] \n\
1: pld [r0, #64] \n\
pld [r0, #96] \n\
pld [r1, #64] \n\
pld [r1, #96] \n\
2: ldrd r2, [r0], #8 \n\
ldrd r4, [r0], #8 \n\
mov ip, r1 \n\
strd r2, [r1], #8 \n\
ldrd r2, [r0], #8 \n\
strd r4, [r1], #8 \n\
ldrd r4, [r0], #8 \n\
strd r2, [r1], #8 \n\
strd r4, [r1], #8 \n\
mcr p15, 0, ip, c7, c10, 1 @ clean D line\n\
ldrd r2, [r0], #8 \n\
mcr p15, 0, ip, c7, c6, 1 @ invalidate D line\n\
ldrd r4, [r0], #8 \n\
mov ip, r1 \n\
strd r2, [r1], #8 \n\
ldrd r2, [r0], #8 \n\
strd r4, [r1], #8 \n\
ldrd r4, [r0], #8 \n\
strd r2, [r1], #8 \n\
strd r4, [r1], #8 \n\
mcr p15, 0, ip, c7, c10, 1 @ clean D line\n\
subs lr, lr, #1 \n\
mcr p15, 0, ip, c7, c6, 1 @ invalidate D line\n\
bgt 1b \n\
beq 2b \n\
ldmfd sp!, {r4, r5, pc} "
:
: "r" (from), "r" (to), "I" (PAGE_SIZE / 64 - 1));
}
void xscale_mc_copy_user_highpage(struct page *to, struct page *from,
unsigned long vaddr, struct vm_area_struct *vma)
{
void *kto = kmap_atomic(to);
if (!test_and_set_bit(PG_dcache_clean, &from->flags))
__flush_dcache_page(page_mapping(from), from);
raw_spin_lock(&minicache_lock);
set_top_pte(COPYPAGE_MINICACHE, mk_pte(from, minicache_pgprot));
mc_copy_user_page((void *)COPYPAGE_MINICACHE, kto);
raw_spin_unlock(&minicache_lock);
kunmap_atomic(kto);
}
/*
* XScale optimised clear_user_page
*/
void
xscale_mc_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\
1: mov ip, %0 \n\
strd r2, [%0], #8 \n\
strd r2, [%0], #8 \n\
strd r2, [%0], #8 \n\
strd r2, [%0], #8 \n\
mcr p15, 0, ip, c7, c10, 1 @ clean D line\n\
subs r1, r1, #1 \n\
mcr p15, 0, ip, c7, c6, 1 @ invalidate D line\n\
bne 1b"
: "=r" (ptr)
: "0" (kaddr), "I" (PAGE_SIZE / 32)
: "r1", "r2", "r3", "ip");
kunmap_atomic(kaddr);
}
struct cpu_user_fns xscale_mc_user_fns __initdata = {
.cpu_clear_user_highpage = xscale_mc_clear_user_highpage,
.cpu_copy_user_highpage = xscale_mc_copy_user_highpage,
};