1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
|
/*
* 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"
/*
* 0xffff8000 to 0xffffffff is reserved for any ARM architecture
* specific hacks for copying pages efficiently.
*/
#define COPYPAGE_MINICACHE 0xffff8000
#define minicache_pgprot __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | \
L_PTE_MT_MINICACHE)
static DEFINE_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 __attribute__((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)
{
void *kto = kmap_atomic(to, KM_USER1);
if (test_and_clear_bit(PG_dcache_dirty, &from->flags))
__flush_dcache_page(page_mapping(from), from);
spin_lock(&minicache_lock);
set_pte_ext(TOP_PTE(COPYPAGE_MINICACHE), pfn_pte(page_to_pfn(from), minicache_pgprot), 0);
flush_tlb_kernel_page(COPYPAGE_MINICACHE);
mc_copy_user_page((void *)COPYPAGE_MINICACHE, kto);
spin_unlock(&minicache_lock);
kunmap_atomic(kto, KM_USER1);
}
/*
* XScale optimised clear_user_page
*/
void __attribute__((naked))
xscale_mc_clear_user_page(void *kaddr, unsigned long vaddr)
{
asm volatile(
"mov r1, %0 \n\
mov r2, #0 \n\
mov r3, #0 \n\
1: mov ip, r0 \n\
strd r2, [r0], #8 \n\
strd r2, [r0], #8 \n\
strd r2, [r0], #8 \n\
strd r2, [r0], #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 \n\
mov pc, lr"
:
: "I" (PAGE_SIZE / 32));
}
struct cpu_user_fns xscale_mc_user_fns __initdata = {
.cpu_clear_user_page = xscale_mc_clear_user_page,
.cpu_copy_user_highpage = xscale_mc_copy_user_highpage,
};
|
