summaryrefslogtreecommitdiff
path: root/arch/x86/lib/usercopy_64.c
blob: c3a5bbc0b41ef4c82163a33cbc5171968c8e4f3b (plain)
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
141
142
143
144
145
146
147
148
149
150
151
152
// SPDX-License-Identifier: GPL-2.0-only
/* 
 * User address space access functions.
 *
 * Copyright 1997 Andi Kleen <ak@muc.de>
 * Copyright 1997 Linus Torvalds
 * Copyright 2002 Andi Kleen <ak@suse.de>
 */
#include <linux/export.h>
#include <linux/uaccess.h>
#include <linux/highmem.h>

/*
 * Zero Userspace
 */

#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
/**
 * clean_cache_range - write back a cache range with CLWB
 * @vaddr:	virtual start address
 * @size:	number of bytes to write back
 *
 * Write back a cache range using the CLWB (cache line write back)
 * instruction. Note that @size is internally rounded up to be cache
 * line size aligned.
 */
static void clean_cache_range(void *addr, size_t size)
{
	u16 x86_clflush_size = boot_cpu_data.x86_clflush_size;
	unsigned long clflush_mask = x86_clflush_size - 1;
	void *vend = addr + size;
	void *p;

	for (p = (void *)((unsigned long)addr & ~clflush_mask);
	     p < vend; p += x86_clflush_size)
		clwb(p);
}

void arch_wb_cache_pmem(void *addr, size_t size)
{
	clean_cache_range(addr, size);
}
EXPORT_SYMBOL_GPL(arch_wb_cache_pmem);

long __copy_user_flushcache(void *dst, const void __user *src, unsigned size)
{
	unsigned long flushed, dest = (unsigned long) dst;
	long rc;

	stac();
	rc = __copy_user_nocache(dst, src, size);
	clac();

	/*
	 * __copy_user_nocache() uses non-temporal stores for the bulk
	 * of the transfer, but we need to manually flush if the
	 * transfer is unaligned. A cached memory copy is used when
	 * destination or size is not naturally aligned. That is:
	 *   - Require 8-byte alignment when size is 8 bytes or larger.
	 *   - Require 4-byte alignment when size is 4 bytes.
	 */
	if (size < 8) {
		if (!IS_ALIGNED(dest, 4) || size != 4)
			clean_cache_range(dst, size);
	} else {
		if (!IS_ALIGNED(dest, 8)) {
			dest = ALIGN(dest, boot_cpu_data.x86_clflush_size);
			clean_cache_range(dst, 1);
		}

		flushed = dest - (unsigned long) dst;
		if (size > flushed && !IS_ALIGNED(size - flushed, 8))
			clean_cache_range(dst + size - 1, 1);
	}

	return rc;
}

void __memcpy_flushcache(void *_dst, const void *_src, size_t size)
{
	unsigned long dest = (unsigned long) _dst;
	unsigned long source = (unsigned long) _src;

	/* cache copy and flush to align dest */
	if (!IS_ALIGNED(dest, 8)) {
		size_t len = min_t(size_t, size, ALIGN(dest, 8) - dest);

		memcpy((void *) dest, (void *) source, len);
		clean_cache_range((void *) dest, len);
		dest += len;
		source += len;
		size -= len;
		if (!size)
			return;
	}

	/* 4x8 movnti loop */
	while (size >= 32) {
		asm("movq    (%0), %%r8\n"
		    "movq   8(%0), %%r9\n"
		    "movq  16(%0), %%r10\n"
		    "movq  24(%0), %%r11\n"
		    "movnti  %%r8,   (%1)\n"
		    "movnti  %%r9,  8(%1)\n"
		    "movnti %%r10, 16(%1)\n"
		    "movnti %%r11, 24(%1)\n"
		    :: "r" (source), "r" (dest)
		    : "memory", "r8", "r9", "r10", "r11");
		dest += 32;
		source += 32;
		size -= 32;
	}

	/* 1x8 movnti loop */
	while (size >= 8) {
		asm("movq    (%0), %%r8\n"
		    "movnti  %%r8,   (%1)\n"
		    :: "r" (source), "r" (dest)
		    : "memory", "r8");
		dest += 8;
		source += 8;
		size -= 8;
	}

	/* 1x4 movnti loop */
	while (size >= 4) {
		asm("movl    (%0), %%r8d\n"
		    "movnti  %%r8d,   (%1)\n"
		    :: "r" (source), "r" (dest)
		    : "memory", "r8");
		dest += 4;
		source += 4;
		size -= 4;
	}

	/* cache copy for remaining bytes */
	if (size) {
		memcpy((void *) dest, (void *) source, size);
		clean_cache_range((void *) dest, size);
	}
}
EXPORT_SYMBOL_GPL(__memcpy_flushcache);

void memcpy_page_flushcache(char *to, struct page *page, size_t offset,
		size_t len)
{
	char *from = kmap_atomic(page);

	memcpy_flushcache(to, from + offset, len);
	kunmap_atomic(from);
}
#endif