aboutsummaryrefslogtreecommitdiff
path: root/util/mmap-alloc.c
blob: f7f177d0eaf53e34cd1a756deacd1ef6ea562362 (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
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
/*
 * 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.
 */

#ifdef CONFIG_LINUX
#include <linux/mman.h>
#else  /* !CONFIG_LINUX */
#define MAP_SYNC              0x0
#define MAP_SHARED_VALIDATE   0x0
#endif /* CONFIG_LINUX */

#include "qemu/osdep.h"
#include "qemu/mmap-alloc.h"
#include "qemu/host-utils.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;
        }
    }
#ifdef __sparc__
    /* SPARC Linux needs greater alignment than the pagesize */
    return QEMU_VMALLOC_ALIGN;
#endif
#endif

    return getpagesize();
}

size_t qemu_mempath_getpagesize(const char *mem_path)
{
#ifdef CONFIG_LINUX
    struct statfs fs;
    int ret;

    if (mem_path) {
        do {
            ret = statfs(mem_path, &fs);
        } while (ret != 0 && errno == EINTR);

        if (ret != 0) {
            fprintf(stderr, "Couldn't statfs() memory path: %s\n",
                    strerror(errno));
            exit(1);
        }

        if (fs.f_type == HUGETLBFS_MAGIC) {
            /* It's hugepage, return the huge page size */
            return fs.f_bsize;
        }
    }
#ifdef __sparc__
    /* SPARC Linux needs greater alignment than the pagesize */
    return QEMU_VMALLOC_ALIGN;
#endif
#endif

    return getpagesize();
}

void *qemu_ram_mmap(int fd,
                    size_t size,
                    size_t align,
                    bool shared,
                    bool is_pmem)
{
    int flags;
    int map_sync_flags = 0;
    int guardfd;
    size_t offset;
    size_t pagesize;
    size_t total;
    void *guardptr;
    void *ptr;

    /*
     * Note: this always allocates at least one extra page of virtual address
     * space, even if size is already aligned.
     */
    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.
     */
    flags = MAP_PRIVATE;
    pagesize = qemu_fd_getpagesize(fd);
    if (fd == -1 || pagesize == getpagesize()) {
        guardfd = -1;
        flags |= MAP_ANONYMOUS;
    } else {
        guardfd = fd;
        flags |= MAP_NORESERVE;
    }
#else
    guardfd = -1;
    pagesize = getpagesize();
    flags = MAP_PRIVATE | MAP_ANONYMOUS;
#endif

    guardptr = mmap(0, total, PROT_NONE, flags, guardfd, 0);

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

    assert(is_power_of_2(align));
    /* Always align to host page size */
    assert(align >= pagesize);

    flags = MAP_FIXED;
    flags |= fd == -1 ? MAP_ANONYMOUS : 0;
    flags |= shared ? MAP_SHARED : MAP_PRIVATE;
    if (shared && is_pmem) {
        map_sync_flags = MAP_SYNC | MAP_SHARED_VALIDATE;
    }

    offset = QEMU_ALIGN_UP((uintptr_t)guardptr, align) - (uintptr_t)guardptr;

    ptr = mmap(guardptr + offset, size, PROT_READ | PROT_WRITE,
               flags | map_sync_flags, fd, 0);

    if (ptr == MAP_FAILED && map_sync_flags) {
        if (errno == ENOTSUP) {
            char *proc_link, *file_name;
            int len;
            proc_link = g_strdup_printf("/proc/self/fd/%d", fd);
            file_name = g_malloc0(PATH_MAX);
            len = readlink(proc_link, file_name, PATH_MAX - 1);
            if (len < 0) {
                len = 0;
            }
            file_name[len] = '\0';
            fprintf(stderr, "Warning: requesting persistence across crashes "
                    "for backend file %s failed. Proceeding without "
                    "persistence, data might become corrupted in case of host "
                    "crash.\n", file_name);
            g_free(proc_link);
            g_free(file_name);
        }
        /*
         * if map failed with MAP_SHARED_VALIDATE | MAP_SYNC,
         * we will remove these flags to handle compatibility.
         */
        ptr = mmap(guardptr + offset, size, PROT_READ | PROT_WRITE,
                   flags, fd, 0);
    }

    if (ptr == MAP_FAILED) {
        munmap(guardptr, total);
        return MAP_FAILED;
    }

    if (offset > 0) {
        munmap(guardptr, offset);
    }

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

    return ptr;
}

void qemu_ram_munmap(int fd, void *ptr, size_t size)
{
    size_t pagesize;

    if (ptr) {
        /* Unmap both the RAM block and the guard page */
#if defined(__powerpc64__) && defined(__linux__)
        pagesize = qemu_fd_getpagesize(fd);
#else
        pagesize = getpagesize();
#endif
        munmap(ptr, size + pagesize);
    }
}