aboutsummaryrefslogtreecommitdiff
path: root/hw/mem/memory-device.c
blob: 49f86ec8a887ee425611bdf6b26734cf2b3d7f8a (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
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
/*
 * Memory Device Interface
 *
 * Copyright ProfitBricks GmbH 2012
 * Copyright (C) 2014 Red Hat Inc
 * Copyright (c) 2018 Red Hat Inc
 *
 * 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/error-report.h"
#include "hw/mem/memory-device.h"
#include "qapi/error.h"
#include "hw/boards.h"
#include "qemu/range.h"
#include "hw/virtio/vhost.h"
#include "sysemu/kvm.h"
#include "trace.h"

static gint memory_device_addr_sort(gconstpointer a, gconstpointer b)
{
    const MemoryDeviceState *md_a = MEMORY_DEVICE(a);
    const MemoryDeviceState *md_b = MEMORY_DEVICE(b);
    const MemoryDeviceClass *mdc_a = MEMORY_DEVICE_GET_CLASS(a);
    const MemoryDeviceClass *mdc_b = MEMORY_DEVICE_GET_CLASS(b);
    const uint64_t addr_a = mdc_a->get_addr(md_a);
    const uint64_t addr_b = mdc_b->get_addr(md_b);

    if (addr_a > addr_b) {
        return 1;
    } else if (addr_a < addr_b) {
        return -1;
    }
    return 0;
}

static int memory_device_build_list(Object *obj, void *opaque)
{
    GSList **list = opaque;

    if (object_dynamic_cast(obj, TYPE_MEMORY_DEVICE)) {
        DeviceState *dev = DEVICE(obj);
        if (dev->realized) { /* only realized memory devices matter */
            *list = g_slist_insert_sorted(*list, dev, memory_device_addr_sort);
        }
    }

    object_child_foreach(obj, memory_device_build_list, opaque);
    return 0;
}

static int memory_device_used_region_size(Object *obj, void *opaque)
{
    uint64_t *size = opaque;

    if (object_dynamic_cast(obj, TYPE_MEMORY_DEVICE)) {
        const DeviceState *dev = DEVICE(obj);
        const MemoryDeviceState *md = MEMORY_DEVICE(obj);

        if (dev->realized) {
            *size += memory_device_get_region_size(md, &error_abort);
        }
    }

    object_child_foreach(obj, memory_device_used_region_size, opaque);
    return 0;
}

static void memory_device_check_addable(MachineState *ms, uint64_t size,
                                        Error **errp)
{
    uint64_t used_region_size = 0;

    /* we will need a new memory slot for kvm and vhost */
    if (kvm_enabled() && !kvm_has_free_slot(ms)) {
        error_setg(errp, "hypervisor has no free memory slots left");
        return;
    }
    if (!vhost_has_free_slot()) {
        error_setg(errp, "a used vhost backend has no free memory slots left");
        return;
    }

    /* will we exceed the total amount of memory specified */
    memory_device_used_region_size(OBJECT(ms), &used_region_size);
    if (used_region_size + size < used_region_size ||
        used_region_size + size > ms->maxram_size - ms->ram_size) {
        error_setg(errp, "not enough space, currently 0x%" PRIx64
                   " in use of total space for memory devices 0x" RAM_ADDR_FMT,
                   used_region_size, ms->maxram_size - ms->ram_size);
        return;
    }

}

static uint64_t memory_device_get_free_addr(MachineState *ms,
                                            const uint64_t *hint,
                                            uint64_t align, uint64_t size,
                                            Error **errp)
{
    Error *err = NULL;
    GSList *list = NULL, *item;
    Range as, new = range_empty;

    if (!ms->device_memory || !memory_region_size(&ms->device_memory->mr)) {
        error_setg(errp, "the configuration is not prepared for memory devices"
                         " (e.g., for memory hotplug), consider specifying the"
                         " maxmem option");
        return 0;
    }
    range_init_nofail(&as, ms->device_memory->base,
                      memory_region_size(&ms->device_memory->mr));

    /* start of address space indicates the maximum alignment we expect */
    if (!QEMU_IS_ALIGNED(range_lob(&as), align)) {
        warn_report("the alignment (0x%" PRIx64 ") exceeds the expected"
                    " maximum alignment, memory will get fragmented and not"
                    " all 'maxmem' might be usable for memory devices.",
                    align);
    }

    memory_device_check_addable(ms, size, &err);
    if (err) {
        error_propagate(errp, err);
        return 0;
    }

    if (hint && !QEMU_IS_ALIGNED(*hint, align)) {
        error_setg(errp, "address must be aligned to 0x%" PRIx64 " bytes",
                   align);
        return 0;
    }

    if (!QEMU_IS_ALIGNED(size, align)) {
        error_setg(errp, "backend memory size must be multiple of 0x%"
                   PRIx64, align);
        return 0;
    }

    if (hint) {
        if (range_init(&new, *hint, size) || !range_contains_range(&as, &new)) {
            error_setg(errp, "can't add memory device [0x%" PRIx64 ":0x%" PRIx64
                       "], usable range for memory devices [0x%" PRIx64 ":0x%"
                       PRIx64 "]", *hint, size, range_lob(&as),
                       range_size(&as));
            return 0;
        }
    } else {
        if (range_init(&new, QEMU_ALIGN_UP(range_lob(&as), align), size)) {
            error_setg(errp, "can't add memory device, device too big");
            return 0;
        }
    }

    /* find address range that will fit new memory device */
    object_child_foreach(OBJECT(ms), memory_device_build_list, &list);
    for (item = list; item; item = g_slist_next(item)) {
        const MemoryDeviceState *md = item->data;
        const MemoryDeviceClass *mdc = MEMORY_DEVICE_GET_CLASS(OBJECT(md));
        uint64_t next_addr;
        Range tmp;

        range_init_nofail(&tmp, mdc->get_addr(md),
                          memory_device_get_region_size(md, &error_abort));

        if (range_overlaps_range(&tmp, &new)) {
            if (hint) {
                const DeviceState *d = DEVICE(md);
                error_setg(errp, "address range conflicts with memory device"
                           " id='%s'", d->id ? d->id : "(unnamed)");
                goto out;
            }

            next_addr = QEMU_ALIGN_UP(range_upb(&tmp) + 1, align);
            if (!next_addr || range_init(&new, next_addr, range_size(&new))) {
                range_make_empty(&new);
                break;
            }
        } else if (range_lob(&tmp) > range_upb(&new)) {
            break;
        }
    }

    if (!range_contains_range(&as, &new)) {
        error_setg(errp, "could not find position in guest address space for "
                   "memory device - memory fragmented due to alignments");
    }
out:
    g_slist_free(list);
    return range_lob(&new);
}

MemoryDeviceInfoList *qmp_memory_device_list(void)
{
    GSList *devices = NULL, *item;
    MemoryDeviceInfoList *list = NULL, **tail = &list;

    object_child_foreach(qdev_get_machine(), memory_device_build_list,
                         &devices);

    for (item = devices; item; item = g_slist_next(item)) {
        const MemoryDeviceState *md = MEMORY_DEVICE(item->data);
        const MemoryDeviceClass *mdc = MEMORY_DEVICE_GET_CLASS(item->data);
        MemoryDeviceInfo *info = g_new0(MemoryDeviceInfo, 1);

        mdc->fill_device_info(md, info);

        QAPI_LIST_APPEND(tail, info);
    }

    g_slist_free(devices);

    return list;
}

static int memory_device_plugged_size(Object *obj, void *opaque)
{
    uint64_t *size = opaque;

    if (object_dynamic_cast(obj, TYPE_MEMORY_DEVICE)) {
        const DeviceState *dev = DEVICE(obj);
        const MemoryDeviceState *md = MEMORY_DEVICE(obj);
        const MemoryDeviceClass *mdc = MEMORY_DEVICE_GET_CLASS(obj);

        if (dev->realized) {
            *size += mdc->get_plugged_size(md, &error_abort);
        }
    }

    object_child_foreach(obj, memory_device_plugged_size, opaque);
    return 0;
}

uint64_t get_plugged_memory_size(void)
{
    uint64_t size = 0;

    memory_device_plugged_size(qdev_get_machine(), &size);

    return size;
}

void memory_device_pre_plug(MemoryDeviceState *md, MachineState *ms,
                            const uint64_t *legacy_align, Error **errp)
{
    const MemoryDeviceClass *mdc = MEMORY_DEVICE_GET_CLASS(md);
    Error *local_err = NULL;
    uint64_t addr, align = 0;
    MemoryRegion *mr;

    mr = mdc->get_memory_region(md, &local_err);
    if (local_err) {
        goto out;
    }

    if (legacy_align) {
        align = *legacy_align;
    } else {
        if (mdc->get_min_alignment) {
            align = mdc->get_min_alignment(md);
        }
        align = MAX(align, memory_region_get_alignment(mr));
    }
    addr = mdc->get_addr(md);
    addr = memory_device_get_free_addr(ms, !addr ? NULL : &addr, align,
                                       memory_region_size(mr), &local_err);
    if (local_err) {
        goto out;
    }
    mdc->set_addr(md, addr, &local_err);
    if (!local_err) {
        trace_memory_device_pre_plug(DEVICE(md)->id ? DEVICE(md)->id : "",
                                     addr);
    }
out:
    error_propagate(errp, local_err);
}

void memory_device_plug(MemoryDeviceState *md, MachineState *ms)
{
    const MemoryDeviceClass *mdc = MEMORY_DEVICE_GET_CLASS(md);
    const uint64_t addr = mdc->get_addr(md);
    MemoryRegion *mr;

    /*
     * We expect that a previous call to memory_device_pre_plug() succeeded, so
     * it can't fail at this point.
     */
    mr = mdc->get_memory_region(md, &error_abort);
    g_assert(ms->device_memory);

    memory_region_add_subregion(&ms->device_memory->mr,
                                addr - ms->device_memory->base, mr);
    trace_memory_device_plug(DEVICE(md)->id ? DEVICE(md)->id : "", addr);
}

void memory_device_unplug(MemoryDeviceState *md, MachineState *ms)
{
    const MemoryDeviceClass *mdc = MEMORY_DEVICE_GET_CLASS(md);
    MemoryRegion *mr;

    /*
     * We expect that a previous call to memory_device_pre_plug() succeeded, so
     * it can't fail at this point.
     */
    mr = mdc->get_memory_region(md, &error_abort);
    g_assert(ms->device_memory);

    memory_region_del_subregion(&ms->device_memory->mr, mr);
    trace_memory_device_unplug(DEVICE(md)->id ? DEVICE(md)->id : "",
                               mdc->get_addr(md));
}

uint64_t memory_device_get_region_size(const MemoryDeviceState *md,
                                       Error **errp)
{
    const MemoryDeviceClass *mdc = MEMORY_DEVICE_GET_CLASS(md);
    MemoryRegion *mr;

    /* dropping const here is fine as we don't touch the memory region */
    mr = mdc->get_memory_region((MemoryDeviceState *)md, errp);
    if (!mr) {
        return 0;
    }

    return memory_region_size(mr);
}

static const TypeInfo memory_device_info = {
    .name          = TYPE_MEMORY_DEVICE,
    .parent        = TYPE_INTERFACE,
    .class_size = sizeof(MemoryDeviceClass),
};

static void memory_device_register_types(void)
{
    type_register_static(&memory_device_info);
}

type_init(memory_device_register_types)