summaryrefslogtreecommitdiff
path: root/util/mmap-alloc.c
blob: 5a85aa3c899b1d006ea91ba3f5dec7fd0bc4b97e (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
/*
 * Support for RAM backed by mmaped host memory.
 *
 * Copyright (c) 2015 Red Hat, Inc.
 *
 * Authors:
 *  Michael S. Tsirkin <mst@redhat.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2 or
 * later.  See the COPYING file in the top-level directory.
 */

#include "qemu/osdep.h"
#include "qemu/mmap-alloc.h"

#define HUGETLBFS_MAGIC       0x958458f6

#ifdef CONFIG_LINUX
#include <sys/vfs.h>
#endif

size_t qemu_fd_getpagesize(int fd)
{
#ifdef CONFIG_LINUX
    struct statfs fs;
    int ret;

    if (fd != -1) {
        do {
            ret = fstatfs(fd, &fs);
        } while (ret != 0 && errno == EINTR);

        if (ret == 0 && fs.f_type == HUGETLBFS_MAGIC) {
            return fs.f_bsize;
        }
    }
#endif

    return getpagesize();
}

void *qemu_ram_mmap(int fd, size_t size, size_t align, bool shared)
{
    /*
     * Note: this always allocates at least one extra page of virtual address
     * space, even if size is already aligned.
     */
    size_t total = size + align;
#if defined(__powerpc64__) && defined(__linux__)
    /* On ppc64 mappings in the same segment (aka slice) must share the same
     * page size. Since we will be re-allocating part of this segment
     * from the supplied fd, we should make sure to use the same page size, to
     * this end we mmap the supplied fd.  In this case, set MAP_NORESERVE to
     * avoid allocating backing store memory.
     * We do this unless we are using the system page size, in which case
     * anonymous memory is OK.
     */
    int anonfd = fd == -1 || qemu_fd_getpagesize(fd) == getpagesize() ? -1 : fd;
    int flags = anonfd == -1 ? MAP_ANONYMOUS : MAP_NORESERVE;
    void *ptr = mmap(0, total, PROT_NONE, flags | MAP_PRIVATE, anonfd, 0);
#else
    void *ptr = mmap(0, total, PROT_NONE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
#endif
    size_t offset = QEMU_ALIGN_UP((uintptr_t)ptr, align) - (uintptr_t)ptr;
    void *ptr1;

    if (ptr == MAP_FAILED) {
        return MAP_FAILED;
    }

    /* Make sure align is a power of 2 */
    assert(!(align & (align - 1)));
    /* Always align to host page size */
    assert(align >= getpagesize());

    ptr1 = mmap(ptr + offset, size, PROT_READ | PROT_WRITE,
                MAP_FIXED |
                (fd == -1 ? MAP_ANONYMOUS : 0) |
                (shared ? MAP_SHARED : MAP_PRIVATE),
                fd, 0);
    if (ptr1 == MAP_FAILED) {
        munmap(ptr, total);
        return MAP_FAILED;
    }

    ptr += offset;
    total -= offset;

    if (offset > 0) {
        munmap(ptr - offset, offset);
    }

    /*
     * Leave a single PROT_NONE page allocated after the RAM block, to serve as
     * a guard page guarding against potential buffer overflows.
     */
    if (total > size + getpagesize()) {
        munmap(ptr + size + getpagesize(), total - size - getpagesize());
    }

    return ptr;
}

void qemu_ram_munmap(void *ptr, size_t size)
{
    if (ptr) {
        /* Unmap both the RAM block and the guard page */
        munmap(ptr, size + getpagesize());
    }
}