aboutsummaryrefslogtreecommitdiff
path: root/include/exec/ram_addr.h
blob: 6cbc02aa0fffb1f301184e5e0a864f0b961bf2d0 (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
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
/*
 * Declarations for cpu physical memory functions
 *
 * Copyright 2011 Red Hat, Inc. and/or its affiliates
 *
 * Authors:
 *  Avi Kivity <avi@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.
 *
 */

/*
 * This header is for use by exec.c and memory.c ONLY.  Do not include it.
 * The functions declared here will be removed soon.
 */

#ifndef RAM_ADDR_H
#define RAM_ADDR_H

#ifndef CONFIG_USER_ONLY
#include "hw/xen/xen.h"
#include "exec/ramlist.h"

struct RAMBlock {
    struct rcu_head rcu;
    struct MemoryRegion *mr;
    uint8_t *host;
    ram_addr_t offset;
    ram_addr_t used_length;
    ram_addr_t max_length;
    void (*resized)(const char*, uint64_t length, void *host);
    uint32_t flags;
    /* Protected by iothread lock.  */
    char idstr[256];
    /* RCU-enabled, writes protected by the ramlist lock */
    QLIST_ENTRY(RAMBlock) next;
    QLIST_HEAD(, RAMBlockNotifier) ramblock_notifiers;
    int fd;
    size_t page_size;
    /* dirty bitmap used during migration */
    unsigned long *bmap;
    /* bitmap of pages that haven't been sent even once
     * only maintained and used in postcopy at the moment
     * where it's used to send the dirtymap at the start
     * of the postcopy phase
     */
    unsigned long *unsentmap;
    /* bitmap of already received pages in postcopy */
    unsigned long *receivedmap;
};

static inline bool offset_in_ramblock(RAMBlock *b, ram_addr_t offset)
{
    return (b && b->host && offset < b->used_length) ? true : false;
}

static inline void *ramblock_ptr(RAMBlock *block, ram_addr_t offset)
{
    assert(offset_in_ramblock(block, offset));
    return (char *)block->host + offset;
}

static inline unsigned long int ramblock_recv_bitmap_offset(void *host_addr,
                                                            RAMBlock *rb)
{
    uint64_t host_addr_offset =
            (uint64_t)(uintptr_t)(host_addr - (void *)rb->host);
    return host_addr_offset >> TARGET_PAGE_BITS;
}

long qemu_getrampagesize(void);
unsigned long last_ram_page(void);
RAMBlock *qemu_ram_alloc_from_file(ram_addr_t size, MemoryRegion *mr,
                                   bool share, const char *mem_path,
                                   Error **errp);
RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr,
                                 bool share, int fd,
                                 Error **errp);
RAMBlock *qemu_ram_alloc_from_ptr(ram_addr_t size, void *host,
                                  MemoryRegion *mr, Error **errp);
RAMBlock *qemu_ram_alloc(ram_addr_t size, MemoryRegion *mr, Error **errp);
RAMBlock *qemu_ram_alloc_resizeable(ram_addr_t size, ram_addr_t max_size,
                                    void (*resized)(const char*,
                                                    uint64_t length,
                                                    void *host),
                                    MemoryRegion *mr, Error **errp);
void qemu_ram_free(RAMBlock *block);

int qemu_ram_resize(RAMBlock *block, ram_addr_t newsize, Error **errp);

#define DIRTY_CLIENTS_ALL     ((1 << DIRTY_MEMORY_NUM) - 1)
#define DIRTY_CLIENTS_NOCODE  (DIRTY_CLIENTS_ALL & ~(1 << DIRTY_MEMORY_CODE))

static inline bool cpu_physical_memory_get_dirty(ram_addr_t start,
                                                 ram_addr_t length,
                                                 unsigned client)
{
    DirtyMemoryBlocks *blocks;
    unsigned long end, page;
    unsigned long idx, offset, base;
    bool dirty = false;

    assert(client < DIRTY_MEMORY_NUM);

    end = TARGET_PAGE_ALIGN(start + length) >> TARGET_PAGE_BITS;
    page = start >> TARGET_PAGE_BITS;

    rcu_read_lock();

    blocks = atomic_rcu_read(&ram_list.dirty_memory[client]);

    idx = page / DIRTY_MEMORY_BLOCK_SIZE;
    offset = page % DIRTY_MEMORY_BLOCK_SIZE;
    base = page - offset;
    while (page < end) {
        unsigned long next = MIN(end, base + DIRTY_MEMORY_BLOCK_SIZE);
        unsigned long num = next - base;
        unsigned long found = find_next_bit(blocks->blocks[idx], num, offset);
        if (found < num) {
            dirty = true;
            break;
        }

        page = next;
        idx++;
        offset = 0;
        base += DIRTY_MEMORY_BLOCK_SIZE;
    }

    rcu_read_unlock();

    return dirty;
}

static inline bool cpu_physical_memory_all_dirty(ram_addr_t start,
                                                 ram_addr_t length,
                                                 unsigned client)
{
    DirtyMemoryBlocks *blocks;
    unsigned long end, page;
    unsigned long idx, offset, base;
    bool dirty = true;

    assert(client < DIRTY_MEMORY_NUM);

    end = TARGET_PAGE_ALIGN(start + length) >> TARGET_PAGE_BITS;
    page = start >> TARGET_PAGE_BITS;

    rcu_read_lock();

    blocks = atomic_rcu_read(&ram_list.dirty_memory[client]);

    idx = page / DIRTY_MEMORY_BLOCK_SIZE;
    offset = page % DIRTY_MEMORY_BLOCK_SIZE;
    base = page - offset;
    while (page < end) {
        unsigned long next = MIN(end, base + DIRTY_MEMORY_BLOCK_SIZE);
        unsigned long num = next - base;
        unsigned long found = find_next_zero_bit(blocks->blocks[idx], num, offset);
        if (found < num) {
            dirty = false;
            break;
        }

        page = next;
        idx++;
        offset = 0;
        base += DIRTY_MEMORY_BLOCK_SIZE;
    }

    rcu_read_unlock();

    return dirty;
}

static inline bool cpu_physical_memory_get_dirty_flag(ram_addr_t addr,
                                                      unsigned client)
{
    return cpu_physical_memory_get_dirty(addr, 1, client);
}

static inline bool cpu_physical_memory_is_clean(ram_addr_t addr)
{
    bool vga = cpu_physical_memory_get_dirty_flag(addr, DIRTY_MEMORY_VGA);
    bool code = cpu_physical_memory_get_dirty_flag(addr, DIRTY_MEMORY_CODE);
    bool migration =
        cpu_physical_memory_get_dirty_flag(addr, DIRTY_MEMORY_MIGRATION);
    return !(vga && code && migration);
}

static inline uint8_t cpu_physical_memory_range_includes_clean(ram_addr_t start,
                                                               ram_addr_t length,
                                                               uint8_t mask)
{
    uint8_t ret = 0;

    if (mask & (1 << DIRTY_MEMORY_VGA) &&
        !cpu_physical_memory_all_dirty(start, length, DIRTY_MEMORY_VGA)) {
        ret |= (1 << DIRTY_MEMORY_VGA);
    }
    if (mask & (1 << DIRTY_MEMORY_CODE) &&
        !cpu_physical_memory_all_dirty(start, length, DIRTY_MEMORY_CODE)) {
        ret |= (1 << DIRTY_MEMORY_CODE);
    }
    if (mask & (1 << DIRTY_MEMORY_MIGRATION) &&
        !cpu_physical_memory_all_dirty(start, length, DIRTY_MEMORY_MIGRATION)) {
        ret |= (1 << DIRTY_MEMORY_MIGRATION);
    }
    return ret;
}

static inline void cpu_physical_memory_set_dirty_flag(ram_addr_t addr,
                                                      unsigned client)
{
    unsigned long page, idx, offset;
    DirtyMemoryBlocks *blocks;

    assert(client < DIRTY_MEMORY_NUM);

    page = addr >> TARGET_PAGE_BITS;
    idx = page / DIRTY_MEMORY_BLOCK_SIZE;
    offset = page % DIRTY_MEMORY_BLOCK_SIZE;

    rcu_read_lock();

    blocks = atomic_rcu_read(&ram_list.dirty_memory[client]);

    set_bit_atomic(offset, blocks->blocks[idx]);

    rcu_read_unlock();
}

static inline void cpu_physical_memory_set_dirty_range(ram_addr_t start,
                                                       ram_addr_t length,
                                                       uint8_t mask)
{
    DirtyMemoryBlocks *blocks[DIRTY_MEMORY_NUM];
    unsigned long end, page;
    unsigned long idx, offset, base;
    int i;

    if (!mask && !xen_enabled()) {
        return;
    }

    end = TARGET_PAGE_ALIGN(start + length) >> TARGET_PAGE_BITS;
    page = start >> TARGET_PAGE_BITS;

    rcu_read_lock();

    for (i = 0; i < DIRTY_MEMORY_NUM; i++) {
        blocks[i] = atomic_rcu_read(&ram_list.dirty_memory[i]);
    }

    idx = page / DIRTY_MEMORY_BLOCK_SIZE;
    offset = page % DIRTY_MEMORY_BLOCK_SIZE;
    base = page - offset;
    while (page < end) {
        unsigned long next = MIN(end, base + DIRTY_MEMORY_BLOCK_SIZE);

        if (likely(mask & (1 << DIRTY_MEMORY_MIGRATION))) {
            bitmap_set_atomic(blocks[DIRTY_MEMORY_MIGRATION]->blocks[idx],
                              offset, next - page);
        }
        if (unlikely(mask & (1 << DIRTY_MEMORY_VGA))) {
            bitmap_set_atomic(blocks[DIRTY_MEMORY_VGA]->blocks[idx],
                              offset, next - page);
        }
        if (unlikely(mask & (1 << DIRTY_MEMORY_CODE))) {
            bitmap_set_atomic(blocks[DIRTY_MEMORY_CODE]->blocks[idx],
                              offset, next - page);
        }

        page = next;
        idx++;
        offset = 0;
        base += DIRTY_MEMORY_BLOCK_SIZE;
    }

    rcu_read_unlock();

    xen_hvm_modified_memory(start, length);
}

#if !defined(_WIN32)
static inline void cpu_physical_memory_set_dirty_lebitmap(unsigned long *bitmap,
                                                          ram_addr_t start,
                                                          ram_addr_t pages)
{
    unsigned long i, j;
    unsigned long page_number, c;
    hwaddr addr;
    ram_addr_t ram_addr;
    unsigned long len = (pages + HOST_LONG_BITS - 1) / HOST_LONG_BITS;
    unsigned long hpratio = getpagesize() / TARGET_PAGE_SIZE;
    unsigned long page = BIT_WORD(start >> TARGET_PAGE_BITS);

    /* start address is aligned at the start of a word? */
    if ((((page * BITS_PER_LONG) << TARGET_PAGE_BITS) == start) &&
        (hpratio == 1)) {
        unsigned long **blocks[DIRTY_MEMORY_NUM];
        unsigned long idx;
        unsigned long offset;
        long k;
        long nr = BITS_TO_LONGS(pages);

        idx = (start >> TARGET_PAGE_BITS) / DIRTY_MEMORY_BLOCK_SIZE;
        offset = BIT_WORD((start >> TARGET_PAGE_BITS) %
                          DIRTY_MEMORY_BLOCK_SIZE);

        rcu_read_lock();

        for (i = 0; i < DIRTY_MEMORY_NUM; i++) {
            blocks[i] = atomic_rcu_read(&ram_list.dirty_memory[i])->blocks;
        }

        for (k = 0; k < nr; k++) {
            if (bitmap[k]) {
                unsigned long temp = leul_to_cpu(bitmap[k]);

                atomic_or(&blocks[DIRTY_MEMORY_MIGRATION][idx][offset], temp);
                atomic_or(&blocks[DIRTY_MEMORY_VGA][idx][offset], temp);
                if (tcg_enabled()) {
                    atomic_or(&blocks[DIRTY_MEMORY_CODE][idx][offset], temp);
                }
            }

            if (++offset >= BITS_TO_LONGS(DIRTY_MEMORY_BLOCK_SIZE)) {
                offset = 0;
                idx++;
            }
        }

        rcu_read_unlock();

        xen_hvm_modified_memory(start, pages << TARGET_PAGE_BITS);
    } else {
        uint8_t clients = tcg_enabled() ? DIRTY_CLIENTS_ALL : DIRTY_CLIENTS_NOCODE;
        /*
         * bitmap-traveling is faster than memory-traveling (for addr...)
         * especially when most of the memory is not dirty.
         */
        for (i = 0; i < len; i++) {
            if (bitmap[i] != 0) {
                c = leul_to_cpu(bitmap[i]);
                do {
                    j = ctzl(c);
                    c &= ~(1ul << j);
                    page_number = (i * HOST_LONG_BITS + j) * hpratio;
                    addr = page_number * TARGET_PAGE_SIZE;
                    ram_addr = start + addr;
                    cpu_physical_memory_set_dirty_range(ram_addr,
                                       TARGET_PAGE_SIZE * hpratio, clients);
                } while (c != 0);
            }
        }
    }
}
#endif /* not _WIN32 */

bool cpu_physical_memory_test_and_clear_dirty(ram_addr_t start,
                                              ram_addr_t length,
                                              unsigned client);

DirtyBitmapSnapshot *cpu_physical_memory_snapshot_and_clear_dirty
    (ram_addr_t start, ram_addr_t length, unsigned client);

bool cpu_physical_memory_snapshot_get_dirty(DirtyBitmapSnapshot *snap,
                                            ram_addr_t start,
                                            ram_addr_t length);

static inline void cpu_physical_memory_clear_dirty_range(ram_addr_t start,
                                                         ram_addr_t length)
{
    cpu_physical_memory_test_and_clear_dirty(start, length, DIRTY_MEMORY_MIGRATION);
    cpu_physical_memory_test_and_clear_dirty(start, length, DIRTY_MEMORY_VGA);
    cpu_physical_memory_test_and_clear_dirty(start, length, DIRTY_MEMORY_CODE);
}


static inline
uint64_t cpu_physical_memory_sync_dirty_bitmap(RAMBlock *rb,
                                               ram_addr_t start,
                                               ram_addr_t length,
                                               uint64_t *real_dirty_pages)
{
    ram_addr_t addr;
    unsigned long word = BIT_WORD((start + rb->offset) >> TARGET_PAGE_BITS);
    uint64_t num_dirty = 0;
    unsigned long *dest = rb->bmap;

    /* start address is aligned at the start of a word? */
    if (((word * BITS_PER_LONG) << TARGET_PAGE_BITS) ==
         (start + rb->offset)) {
        int k;
        int nr = BITS_TO_LONGS(length >> TARGET_PAGE_BITS);
        unsigned long * const *src;
        unsigned long idx = (word * BITS_PER_LONG) / DIRTY_MEMORY_BLOCK_SIZE;
        unsigned long offset = BIT_WORD((word * BITS_PER_LONG) %
                                        DIRTY_MEMORY_BLOCK_SIZE);
        unsigned long page = BIT_WORD(start >> TARGET_PAGE_BITS);

        rcu_read_lock();

        src = atomic_rcu_read(
                &ram_list.dirty_memory[DIRTY_MEMORY_MIGRATION])->blocks;

        for (k = page; k < page + nr; k++) {
            if (src[idx][offset]) {
                unsigned long bits = atomic_xchg(&src[idx][offset], 0);
                unsigned long new_dirty;
                *real_dirty_pages += ctpopl(bits);
                new_dirty = ~dest[k];
                dest[k] |= bits;
                new_dirty &= bits;
                num_dirty += ctpopl(new_dirty);
            }

            if (++offset >= BITS_TO_LONGS(DIRTY_MEMORY_BLOCK_SIZE)) {
                offset = 0;
                idx++;
            }
        }

        rcu_read_unlock();
    } else {
        ram_addr_t offset = rb->offset;

        for (addr = 0; addr < length; addr += TARGET_PAGE_SIZE) {
            if (cpu_physical_memory_test_and_clear_dirty(
                        start + addr + offset,
                        TARGET_PAGE_SIZE,
                        DIRTY_MEMORY_MIGRATION)) {
                *real_dirty_pages += 1;
                long k = (start + addr) >> TARGET_PAGE_BITS;
                if (!test_and_set_bit(k, dest)) {
                    num_dirty++;
                }
            }
        }
    }

    return num_dirty;
}
#endif
#endif