aboutsummaryrefslogtreecommitdiff
path: root/hw/vfio/spapr.c
blob: 0af342332c71a81c5cd068f38dae056cf6e4d3fe (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
/*
 * DMA memory preregistration
 *
 * Authors:
 *  Alexey Kardashevskiy <aik@ozlabs.ru>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 */

#include "qemu/osdep.h"
#include "cpu.h"
#include <sys/ioctl.h>
#include <linux/vfio.h>

#include "hw/vfio/vfio-common.h"
#include "hw/hw.h"
#include "qemu/error-report.h"
#include "trace.h"

static bool vfio_prereg_listener_skipped_section(MemoryRegionSection *section)
{
    if (memory_region_is_iommu(section->mr)) {
        hw_error("Cannot possibly preregister IOMMU memory");
    }

    return !memory_region_is_ram(section->mr) ||
            memory_region_is_skip_dump(section->mr);
}

static void *vfio_prereg_gpa_to_vaddr(MemoryRegionSection *section, hwaddr gpa)
{
    return memory_region_get_ram_ptr(section->mr) +
        section->offset_within_region +
        (gpa - section->offset_within_address_space);
}

static void vfio_prereg_listener_region_add(MemoryListener *listener,
                                            MemoryRegionSection *section)
{
    VFIOContainer *container = container_of(listener, VFIOContainer,
                                            prereg_listener);
    const hwaddr gpa = section->offset_within_address_space;
    hwaddr end;
    int ret;
    hwaddr page_mask = qemu_real_host_page_mask;
    struct vfio_iommu_spapr_register_memory reg = {
        .argsz = sizeof(reg),
        .flags = 0,
    };

    if (vfio_prereg_listener_skipped_section(section)) {
        trace_vfio_prereg_listener_region_add_skip(
                section->offset_within_address_space,
                section->offset_within_address_space +
                int128_get64(int128_sub(section->size, int128_one())));
        return;
    }

    if (unlikely((section->offset_within_address_space & ~page_mask) ||
                 (section->offset_within_region & ~page_mask) ||
                 (int128_get64(section->size) & ~page_mask))) {
        error_report("%s received unaligned region", __func__);
        return;
    }

    end = section->offset_within_address_space + int128_get64(section->size);
    if (gpa >= end) {
        return;
    }

    memory_region_ref(section->mr);

    reg.vaddr = (uintptr_t) vfio_prereg_gpa_to_vaddr(section, gpa);
    reg.size = end - gpa;

    ret = ioctl(container->fd, VFIO_IOMMU_SPAPR_REGISTER_MEMORY, &reg);
    trace_vfio_prereg_register(reg.vaddr, reg.size, ret ? -errno : 0);
    if (ret) {
        /*
         * On the initfn path, store the first error in the container so we
         * can gracefully fail.  Runtime, there's not much we can do other
         * than throw a hardware error.
         */
        if (!container->initialized) {
            if (!container->error) {
                container->error = ret;
            }
        } else {
            hw_error("vfio: Memory registering failed, unable to continue");
        }
    }
}

static void vfio_prereg_listener_region_del(MemoryListener *listener,
                                            MemoryRegionSection *section)
{
    VFIOContainer *container = container_of(listener, VFIOContainer,
                                            prereg_listener);
    const hwaddr gpa = section->offset_within_address_space;
    hwaddr end;
    int ret;
    hwaddr page_mask = qemu_real_host_page_mask;
    struct vfio_iommu_spapr_register_memory reg = {
        .argsz = sizeof(reg),
        .flags = 0,
    };

    if (vfio_prereg_listener_skipped_section(section)) {
        trace_vfio_prereg_listener_region_del_skip(
                section->offset_within_address_space,
                section->offset_within_address_space +
                int128_get64(int128_sub(section->size, int128_one())));
        return;
    }

    if (unlikely((section->offset_within_address_space & ~page_mask) ||
                 (section->offset_within_region & ~page_mask) ||
                 (int128_get64(section->size) & ~page_mask))) {
        error_report("%s received unaligned region", __func__);
        return;
    }

    end = section->offset_within_address_space + int128_get64(section->size);
    if (gpa >= end) {
        return;
    }

    reg.vaddr = (uintptr_t) vfio_prereg_gpa_to_vaddr(section, gpa);
    reg.size = end - gpa;

    ret = ioctl(container->fd, VFIO_IOMMU_SPAPR_UNREGISTER_MEMORY, &reg);
    trace_vfio_prereg_unregister(reg.vaddr, reg.size, ret ? -errno : 0);
}

const MemoryListener vfio_prereg_listener = {
    .region_add = vfio_prereg_listener_region_add,
    .region_del = vfio_prereg_listener_region_del,
};

int vfio_spapr_create_window(VFIOContainer *container,
                             MemoryRegionSection *section,
                             hwaddr *pgsize)
{
    int ret;
    unsigned pagesize = memory_region_iommu_get_min_page_size(section->mr);
    unsigned entries, pages;
    struct vfio_iommu_spapr_tce_create create = { .argsz = sizeof(create) };

    /*
     * FIXME: For VFIO iommu types which have KVM acceleration to
     * avoid bouncing all map/unmaps through qemu this way, this
     * would be the right place to wire that up (tell the KVM
     * device emulation the VFIO iommu handles to use).
     */
    create.window_size = int128_get64(section->size);
    create.page_shift = ctz64(pagesize);
    /*
     * SPAPR host supports multilevel TCE tables, there is some
     * heuristic to decide how many levels we want for our table:
     * 0..64 = 1; 65..4096 = 2; 4097..262144 = 3; 262145.. = 4
     */
    entries = create.window_size >> create.page_shift;
    pages = MAX((entries * sizeof(uint64_t)) / getpagesize(), 1);
    pages = MAX(pow2ceil(pages) - 1, 1); /* Round up */
    create.levels = ctz64(pages) / 6 + 1;

    ret = ioctl(container->fd, VFIO_IOMMU_SPAPR_TCE_CREATE, &create);
    if (ret) {
        error_report("Failed to create a window, ret = %d (%m)", ret);
        return -errno;
    }

    if (create.start_addr != section->offset_within_address_space) {
        vfio_spapr_remove_window(container, create.start_addr);

        error_report("Host doesn't support DMA window at %"HWADDR_PRIx", must be %"PRIx64,
                     section->offset_within_address_space,
                     (uint64_t)create.start_addr);
        ioctl(container->fd, VFIO_IOMMU_SPAPR_TCE_REMOVE, &remove);
        return -EINVAL;
    }
    trace_vfio_spapr_create_window(create.page_shift,
                                   create.window_size,
                                   create.start_addr);
    *pgsize = pagesize;

    return 0;
}

int vfio_spapr_remove_window(VFIOContainer *container,
                             hwaddr offset_within_address_space)
{
    struct vfio_iommu_spapr_tce_remove remove = {
        .argsz = sizeof(remove),
        .start_addr = offset_within_address_space,
    };
    int ret;

    ret = ioctl(container->fd, VFIO_IOMMU_SPAPR_TCE_REMOVE, &remove);
    if (ret) {
        error_report("Failed to remove window at %"PRIx64,
                     (uint64_t)remove.start_addr);
        return -errno;
    }

    trace_vfio_spapr_remove_window(offset_within_address_space);

    return 0;
}