summaryrefslogtreecommitdiffstats
path: root/block/bochs.c
blob: 2f010ab40a1ccd3669b64aed3c10aff17435335c (plain) (blame)
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
/*
 * Block driver for the various disk image formats used by Bochs
 * Currently only for "growing" type in read-only mode
 *
 * Copyright (c) 2005 Alex Beregszaszi
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 * THE SOFTWARE.
 */
#include "qemu/osdep.h"
#include "qapi/error.h"
#include "block/block_int.h"
#include "qemu/module.h"
#include "qemu/bswap.h"
#include "qemu/error-report.h"

/**************************************************************/

#define HEADER_MAGIC "Bochs Virtual HD Image"
#define HEADER_VERSION 0x00020000
#define HEADER_V1 0x00010000
#define HEADER_SIZE 512

#define REDOLOG_TYPE "Redolog"
#define GROWING_TYPE "Growing"

// not allocated: 0xffffffff

// always little-endian
struct bochs_header {
    char magic[32];     /* "Bochs Virtual HD Image" */
    char type[16];      /* "Redolog" */
    char subtype[16];   /* "Undoable" / "Volatile" / "Growing" */
    uint32_t version;
    uint32_t header;    /* size of header */

    uint32_t catalog;   /* num of entries */
    uint32_t bitmap;    /* bitmap size */
    uint32_t extent;    /* extent size */

    union {
        struct {
            uint32_t reserved;  /* for ??? */
            uint64_t disk;      /* disk size */
            char padding[HEADER_SIZE - 64 - 20 - 12];
        } QEMU_PACKED redolog;
        struct {
            uint64_t disk;      /* disk size */
            char padding[HEADER_SIZE - 64 - 20 - 8];
        } QEMU_PACKED redolog_v1;
        char padding[HEADER_SIZE - 64 - 20];
    } extra;
} QEMU_PACKED;

typedef struct BDRVBochsState {
    CoMutex lock;
    uint32_t *catalog_bitmap;
    uint32_t catalog_size;

    uint32_t data_offset;

    uint32_t bitmap_blocks;
    uint32_t extent_blocks;
    uint32_t extent_size;
} BDRVBochsState;

static int bochs_probe(const uint8_t *buf, int buf_size, const char *filename)
{
    const struct bochs_header *bochs = (const void *)buf;

    if (buf_size < HEADER_SIZE)
        return 0;

    if (!strcmp(bochs->magic, HEADER_MAGIC) &&
        !strcmp(bochs->type, REDOLOG_TYPE) &&
        !strcmp(bochs->subtype, GROWING_TYPE) &&
        ((le32_to_cpu(bochs->version) == HEADER_VERSION) ||
        (le32_to_cpu(bochs->version) == HEADER_V1)))
        return 100;

    return 0;
}

static int bochs_open(BlockDriverState *bs, QDict *options, int flags,
                      Error **errp)
{
    BDRVBochsState *s = bs->opaque;
    uint32_t i;
    struct bochs_header bochs;
    int ret;

    /* No write support yet */
    ret = bdrv_apply_auto_read_only(bs, NULL, errp);
    if (ret < 0) {
        return ret;
    }

    bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds,
                               BDRV_CHILD_IMAGE, false, errp);
    if (!bs->file) {
        return -EINVAL;
    }

    ret = bdrv_pread(bs->file, 0, &bochs, sizeof(bochs));
    if (ret < 0) {
        return ret;
    }

    if (strcmp(bochs.magic, HEADER_MAGIC) ||
        strcmp(bochs.type, REDOLOG_TYPE) ||
        strcmp(bochs.subtype, GROWING_TYPE) ||
        ((le32_to_cpu(bochs.version) != HEADER_VERSION) &&
        (le32_to_cpu(bochs.version) != HEADER_V1))) {
        error_setg(errp, "Image not in Bochs format");
        return -EINVAL;
    }

    if (le32_to_cpu(bochs.version) == HEADER_V1) {
        bs->total_sectors = le64_to_cpu(bochs.extra.redolog_v1.disk) / 512;
    } else {
        bs->total_sectors = le64_to_cpu(bochs.extra.redolog.disk) / 512;
    }

    /* Limit to 1M entries to avoid unbounded allocation. This is what is
     * needed for the largest image that bximage can create (~8 TB). */
    s->catalog_size = le32_to_cpu(bochs.catalog);
    if (s->catalog_size > 0x100000) {
        error_setg(errp, "Catalog size is too large");
        return -EFBIG;
    }

    s->catalog_bitmap = g_try_new(uint32_t, s->catalog_size);
    if (s->catalog_size && s->catalog_bitmap == NULL) {
        error_setg(errp, "Could not allocate memory for catalog");
        return -ENOMEM;
    }

    ret = bdrv_pread(bs->file, le32_to_cpu(bochs.header), s->catalog_bitmap,
                     s->catalog_size * 4);
    if (ret < 0) {
        goto fail;
    }

    for (i = 0; i < s->catalog_size; i++)
        le32_to_cpus(&s->catalog_bitmap[i]);

    s->data_offset = le32_to_cpu(bochs.header) + (s->catalog_size * 4);

    s->bitmap_blocks = 1 + (le32_to_cpu(bochs.bitmap) - 1) / 512;
    s->extent_blocks = 1 + (le32_to_cpu(bochs.extent) - 1) / 512;

    s->extent_size = le32_to_cpu(bochs.extent);
    if (s->extent_size < BDRV_SECTOR_SIZE) {
        /* bximage actually never creates extents smaller than 4k */
        error_setg(errp, "Extent size must be at least 512");
        ret = -EINVAL;
        goto fail;
    } else if (!is_power_of_2(s->extent_size)) {
        error_setg(errp, "Extent size %" PRIu32 " is not a power of two",
                   s->extent_size);
        ret = -EINVAL;
        goto fail;
    } else if (s->extent_size > 0x800000) {
        error_setg(errp, "Extent size %" PRIu32 " is too large",
                   s->extent_size);
        ret = -EINVAL;
        goto fail;
    }

    if (s->catalog_size < DIV_ROUND_UP(bs->total_sectors,
                                       s->extent_size / BDRV_SECTOR_SIZE))
    {
        error_setg(errp, "Catalog size is too small for this disk size");
        ret = -EINVAL;
        goto fail;
    }

    qemu_co_mutex_init(&s->lock);
    return 0;

fail:
    g_free(s->catalog_bitmap);
    return ret;
}

static void bochs_refresh_limits(BlockDriverState *bs, Error **errp)
{
    bs->bl.request_alignment = BDRV_SECTOR_SIZE; /* No sub-sector I/O */
}

static int64_t seek_to_sector(BlockDriverState *bs, int64_t sector_num)
{
    BDRVBochsState *s = bs->opaque;
    uint64_t offset = sector_num * 512;
    uint64_t extent_index, extent_offset, bitmap_offset;
    char bitmap_entry;
    int ret;

    // seek to sector
    extent_index = offset / s->extent_size;
    extent_offset = (offset % s->extent_size) / 512;

    if (s->catalog_bitmap[extent_index] == 0xffffffff) {
        return 0; /* not allocated */
    }

    bitmap_offset = s->data_offset +
        (512 * (uint64_t) s->catalog_bitmap[extent_index] *
        (s->extent_blocks + s->bitmap_blocks));

    /* read in bitmap for current extent */
    ret = bdrv_pread(bs->file, bitmap_offset + (extent_offset / 8),
                     &bitmap_entry, 1);
    if (ret < 0) {
        return ret;
    }

    if (!((bitmap_entry >> (extent_offset % 8)) & 1)) {
        return 0; /* not allocated */
    }

    return bitmap_offset + (512 * (s->bitmap_blocks + extent_offset));
}

static int coroutine_fn
bochs_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
                QEMUIOVector *qiov, int flags)
{
    BDRVBochsState *s = bs->opaque;
    uint64_t sector_num = offset >> BDRV_SECTOR_BITS;
    int nb_sectors = bytes >> BDRV_SECTOR_BITS;
    uint64_t bytes_done = 0;
    QEMUIOVector local_qiov;
    int ret;

    assert(QEMU_IS_ALIGNED(offset, BDRV_SECTOR_SIZE));
    assert(QEMU_IS_ALIGNED(bytes, BDRV_SECTOR_SIZE));

    qemu_iovec_init(&local_qiov, qiov->niov);
    qemu_co_mutex_lock(&s->lock);

    while (nb_sectors > 0) {
        int64_t block_offset = seek_to_sector(bs, sector_num);
        if (block_offset < 0) {
            ret = block_offset;
            goto fail;
        }

        qemu_iovec_reset(&local_qiov);
        qemu_iovec_concat(&local_qiov, qiov, bytes_done, 512);

        if (block_offset > 0) {
            ret = bdrv_co_preadv(bs->file, block_offset, 512,
                                 &local_qiov, 0);
            if (ret < 0) {
                goto fail;
            }
        } else {
            qemu_iovec_memset(&local_qiov, 0, 0, 512);
        }
        nb_sectors--;
        sector_num++;
        bytes_done += 512;
    }

    ret = 0;
fail:
    qemu_co_mutex_unlock(&s->lock);
    qemu_iovec_destroy(&local_qiov);

    return ret;
}

static void bochs_close(BlockDriverState *bs)
{
    BDRVBochsState *s = bs->opaque;
    g_free(s->catalog_bitmap);
}

static BlockDriver bdrv_bochs = {
    .format_name	= "bochs",
    .instance_size	= sizeof(BDRVBochsState),
    .bdrv_probe		= bochs_probe,
    .bdrv_open		= bochs_open,
    .bdrv_child_perm     = bdrv_default_perms,
    .bdrv_refresh_limits = bochs_refresh_limits,
    .bdrv_co_preadv = bochs_co_preadv,
    .bdrv_close		= bochs_close,
    .is_format          = true,
};

static void bdrv_bochs_init(void)
{
    bdrv_register(&bdrv_bochs);
}

block_init(bdrv_bochs_init);
336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621
/*
 *  Copyright (C) 2016-2020 Red Hat, Inc.
 *  Copyright (C) 2005  Anthony Liguori <anthony@codemonkey.ws>
 *
 *  Network Block Device Server Side
 *
 *  This program is free software; you can redistribute it and/or modify
 *  it under the terms of the GNU General Public License as published by
 *  the Free Software Foundation; under version 2 of the License.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *  GNU General Public License for more details.
 *
 *  You should have received a copy of the GNU General Public License
 *  along with this program; if not, see <http://www.gnu.org/licenses/>.
 */

#include "qemu/osdep.h"

#include "block/export.h"
#include "qapi/error.h"
#include "qemu/queue.h"
#include "trace.h"
#include "nbd-internal.h"
#include "qemu/units.h"

#define NBD_META_ID_BASE_ALLOCATION 0
#define NBD_META_ID_ALLOCATION_DEPTH 1
/* Dirty bitmaps use 'NBD_META_ID_DIRTY_BITMAP + i', so keep this id last. */
#define NBD_META_ID_DIRTY_BITMAP 2

/*
 * NBD_MAX_BLOCK_STATUS_EXTENTS: 1 MiB of extents data. An empirical
 * constant. If an increase is needed, note that the NBD protocol
 * recommends no larger than 32 mb, so that the client won't consider
 * the reply as a denial of service attack.
 */
#define NBD_MAX_BLOCK_STATUS_EXTENTS (1 * MiB / 8)

static int system_errno_to_nbd_errno(int err)
{
    switch (err) {
    case 0:
        return NBD_SUCCESS;
    case EPERM:
    case EROFS:
        return NBD_EPERM;
    case EIO:
        return NBD_EIO;
    case ENOMEM:
        return NBD_ENOMEM;
#ifdef EDQUOT
    case EDQUOT:
#endif
    case EFBIG:
    case ENOSPC:
        return NBD_ENOSPC;
    case EOVERFLOW:
        return NBD_EOVERFLOW;
    case ENOTSUP:
#if ENOTSUP != EOPNOTSUPP
    case EOPNOTSUPP:
#endif
        return NBD_ENOTSUP;
    case ESHUTDOWN:
        return NBD_ESHUTDOWN;
    case EINVAL:
    default:
        return NBD_EINVAL;
    }
}

/* Definitions for opaque data types */

typedef struct NBDRequestData NBDRequestData;

struct NBDRequestData {
    QSIMPLEQ_ENTRY(NBDRequestData) entry;
    NBDClient *client;
    uint8_t *data;
    bool complete;
};

struct NBDExport {
    BlockExport common;

    char *name;
    char *description;
    uint64_t size;
    uint16_t nbdflags;
    QTAILQ_HEAD(, NBDClient) clients;
    QTAILQ_ENTRY(NBDExport) next;

    BlockBackend *eject_notifier_blk;
    Notifier eject_notifier;

    bool allocation_depth;
    BdrvDirtyBitmap **export_bitmaps;
    size_t nr_export_bitmaps;
};

static QTAILQ_HEAD(, NBDExport) exports = QTAILQ_HEAD_INITIALIZER(exports);

/* NBDExportMetaContexts represents a list of contexts to be exported,
 * as selected by NBD_OPT_SET_META_CONTEXT. Also used for
 * NBD_OPT_LIST_META_CONTEXT. */
typedef struct NBDExportMetaContexts {
    NBDExport *exp;
    size_t count; /* number of negotiated contexts */
    bool base_allocation; /* export base:allocation context (block status) */
    bool allocation_depth; /* export qemu:allocation-depth */
    bool *bitmaps; /*
                    * export qemu:dirty-bitmap:<export bitmap name>,
                    * sized by exp->nr_export_bitmaps
                    */
} NBDExportMetaContexts;

struct NBDClient {
    int refcount;
    void (*close_fn)(NBDClient *client, bool negotiated);

    NBDExport *exp;
    QCryptoTLSCreds *tlscreds;
    char *tlsauthz;
    QIOChannelSocket *sioc; /* The underlying data channel */
    QIOChannel *ioc; /* The current I/O channel which may differ (eg TLS) */

    Coroutine *recv_coroutine;

    CoMutex send_lock;
    Coroutine *send_coroutine;

    QTAILQ_ENTRY(NBDClient) next;
    int nb_requests;
    bool closing;

    uint32_t check_align; /* If non-zero, check for aligned client requests */

    bool structured_reply;
    NBDExportMetaContexts export_meta;

    uint32_t opt; /* Current option being negotiated */
    uint32_t optlen; /* remaining length of data in ioc for the option being
                        negotiated now */
};

static void nbd_client_receive_next_request(NBDClient *client);

/* Basic flow for negotiation

   Server         Client
   Negotiate

   or

   Server         Client
   Negotiate #1
                  Option
   Negotiate #2

   ----

   followed by

   Server         Client
                  Request
   Response
                  Request
   Response
                  ...
   ...
                  Request (type == 2)

*/

static inline void set_be_option_rep(NBDOptionReply *rep, uint32_t option,
                                     uint32_t type, uint32_t length)
{
    stq_be_p(&rep->magic, NBD_REP_MAGIC);
    stl_be_p(&rep->option, option);
    stl_be_p(&rep->type, type);
    stl_be_p(&rep->length, length);
}

/* Send a reply header, including length, but no payload.
 * Return -errno on error, 0 on success. */
static int nbd_negotiate_send_rep_len(NBDClient *client, uint32_t type,
                                      uint32_t len, Error **errp)
{
    NBDOptionReply rep;

    trace_nbd_negotiate_send_rep_len(client->opt, nbd_opt_lookup(client->opt),
                                     type, nbd_rep_lookup(type), len);

    assert(len < NBD_MAX_BUFFER_SIZE);

    set_be_option_rep(&rep, client->opt, type, len);
    return nbd_write(client->ioc, &rep, sizeof(rep), errp);
}

/* Send a reply header with default 0 length.
 * Return -errno on error, 0 on success. */
static int nbd_negotiate_send_rep(NBDClient *client, uint32_t type,
                                  Error **errp)
{
    return nbd_negotiate_send_rep_len(client, type, 0, errp);
}

/* Send an error reply.
 * Return -errno on error, 0 on success. */
static int GCC_FMT_ATTR(4, 0)
nbd_negotiate_send_rep_verr(NBDClient *client, uint32_t type,
                            Error **errp, const char *fmt, va_list va)
{
    ERRP_GUARD();
    g_autofree char *msg = NULL;
    int ret;
    size_t len;

    msg = g_strdup_vprintf(fmt, va);
    len = strlen(msg);
    assert(len < NBD_MAX_STRING_SIZE);
    trace_nbd_negotiate_send_rep_err(msg);
    ret = nbd_negotiate_send_rep_len(client, type, len, errp);
    if (ret < 0) {
        return ret;
    }
    if (nbd_write(client->ioc, msg, len, errp) < 0) {
        error_prepend(errp, "write failed (error message): ");
        return -EIO;
    }

    return 0;
}

/*
 * Return a malloc'd copy of @name suitable for use in an error reply.
 */
static char *
nbd_sanitize_name(const char *name)
{
    if (strnlen(name, 80) < 80) {
        return g_strdup(name);
    }
    /* XXX Should we also try to sanitize any control characters? */
    return g_strdup_printf("%.80s...", name);
}

/* Send an error reply.
 * Return -errno on error, 0 on success. */
static int GCC_FMT_ATTR(4, 5)
nbd_negotiate_send_rep_err(NBDClient *client, uint32_t type,
                           Error **errp, const char *fmt, ...)
{
    va_list va;
    int ret;

    va_start(va, fmt);
    ret = nbd_negotiate_send_rep_verr(client, type, errp, fmt, va);
    va_end(va);
    return ret;
}

/* Drop remainder of the current option, and send a reply with the
 * given error type and message. Return -errno on read or write
 * failure; or 0 if connection is still live. */
static int GCC_FMT_ATTR(4, 0)
nbd_opt_vdrop(NBDClient *client, uint32_t type, Error **errp,
              const char *fmt, va_list va)
{
    int ret = nbd_drop(client->ioc, client->optlen, errp);

    client->optlen = 0;
    if (!ret) {
        ret = nbd_negotiate_send_rep_verr(client, type, errp, fmt, va);
    }
    return ret;
}

static int GCC_FMT_ATTR(4, 5)
nbd_opt_drop(NBDClient *client, uint32_t type, Error **errp,
             const char *fmt, ...)
{
    int ret;
    va_list va;

    va_start(va, fmt);
    ret = nbd_opt_vdrop(client, type, errp, fmt, va);
    va_end(va);

    return ret;
}

static int GCC_FMT_ATTR(3, 4)
nbd_opt_invalid(NBDClient *client, Error **errp, const char *fmt, ...)
{
    int ret;
    va_list va;

    va_start(va, fmt);
    ret = nbd_opt_vdrop(client, NBD_REP_ERR_INVALID, errp, fmt, va);
    va_end(va);

    return ret;
}

/* Read size bytes from the unparsed payload of the current option.
 * If @check_nul, require that no NUL bytes appear in buffer.
 * Return -errno on I/O error, 0 if option was completely handled by
 * sending a reply about inconsistent lengths, or 1 on success. */
static int nbd_opt_read(NBDClient *client, void *buffer, size_t size,
                        bool check_nul, Error **errp)
{
    if (size > client->optlen) {
        return nbd_opt_invalid(client, errp,
                               "Inconsistent lengths in option %s",
                               nbd_opt_lookup(client->opt));
    }
    client->optlen -= size;
    if (qio_channel_read_all(client->ioc, buffer, size, errp) < 0) {
        return -EIO;
    }

    if (check_nul && strnlen(buffer, size) != size) {
        return nbd_opt_invalid(client, errp,
                               "Unexpected embedded NUL in option %s",
                               nbd_opt_lookup(client->opt));
    }
    return 1;
}

/* Drop size bytes from the unparsed payload of the current option.
 * Return -errno on I/O error, 0 if option was completely handled by
 * sending a reply about inconsistent lengths, or 1 on success. */
static int nbd_opt_skip(NBDClient *client, size_t size, Error **errp)
{
    if (size > client->optlen) {
        return nbd_opt_invalid(client, errp,
                               "Inconsistent lengths in option %s",
                               nbd_opt_lookup(client->opt));
    }
    client->optlen -= size;
    return nbd_drop(client->ioc, size, errp) < 0 ? -EIO : 1;
}

/* nbd_opt_read_name
 *
 * Read a string with the format:
 *   uint32_t len     (<= NBD_MAX_STRING_SIZE)
 *   len bytes string (not 0-terminated)
 *
 * On success, @name will be allocated.
 * If @length is non-null, it will be set to the actual string length.
 *
 * Return -errno on I/O error, 0 if option was completely handled by
 * sending a reply about inconsistent lengths, or 1 on success.
 */
static int nbd_opt_read_name(NBDClient *client, char **name, uint32_t *length,
                             Error **errp)
{
    int ret;
    uint32_t len;
    g_autofree char *local_name = NULL;

    *name = NULL;
    ret = nbd_opt_read(client, &len, sizeof(len), false, errp);
    if (ret <= 0) {
        return ret;
    }
    len = cpu_to_be32(len);

    if (len > NBD_MAX_STRING_SIZE) {
        return nbd_opt_invalid(client, errp,
                               "Invalid name length: %" PRIu32, len);
    }

    local_name = g_malloc(len + 1);
    ret = nbd_opt_read(client, local_name, len, true, errp);
    if (ret <= 0) {
        return ret;
    }
    local_name[len] = '\0';

    if (length) {
        *length = len;
    }
    *name = g_steal_pointer(&local_name);

    return 1;
}

/* Send a single NBD_REP_SERVER reply to NBD_OPT_LIST, including payload.
 * Return -errno on error, 0 on success. */
static int nbd_negotiate_send_rep_list(NBDClient *client, NBDExport *exp,
                                       Error **errp)
{
    ERRP_GUARD();
    size_t name_len, desc_len;
    uint32_t len;
    const char *name = exp->name ? exp->name : "";
    const char *desc = exp->description ? exp->description : "";
    QIOChannel *ioc = client->ioc;
    int ret;

    trace_nbd_negotiate_send_rep_list(name, desc);
    name_len = strlen(name);
    desc_len = strlen(desc);
    assert(name_len <= NBD_MAX_STRING_SIZE && desc_len <= NBD_MAX_STRING_SIZE);
    len = name_len + desc_len + sizeof(len);
    ret = nbd_negotiate_send_rep_len(client, NBD_REP_SERVER, len, errp);
    if (ret < 0) {
        return ret;
    }

    len = cpu_to_be32(name_len);
    if (nbd_write(ioc, &len, sizeof(len), errp) < 0) {
        error_prepend(errp, "write failed (name length): ");
        return -EINVAL;
    }

    if (nbd_write(ioc, name, name_len, errp) < 0) {
        error_prepend(errp, "write failed (name buffer): ");
        return -EINVAL;
    }

    if (nbd_write(ioc, desc, desc_len, errp) < 0) {
        error_prepend(errp, "write failed (description buffer): ");
        return -EINVAL;
    }

    return 0;
}

/* Process the NBD_OPT_LIST command, with a potential series of replies.
 * Return -errno on error, 0 on success. */
static int nbd_negotiate_handle_list(NBDClient *client, Error **errp)
{
    NBDExport *exp;
    assert(client->opt == NBD_OPT_LIST);

    /* For each export, send a NBD_REP_SERVER reply. */
    QTAILQ_FOREACH(exp, &exports, next) {
        if (nbd_negotiate_send_rep_list(client, exp, errp)) {
            return -EINVAL;
        }
    }
    /* Finish with a NBD_REP_ACK. */
    return nbd_negotiate_send_rep(client, NBD_REP_ACK, errp);
}

static void nbd_check_meta_export(NBDClient *client)
{
    if (client->exp != client->export_meta.exp) {
        client->export_meta.count = 0;
    }
}

/* Send a reply to NBD_OPT_EXPORT_NAME.
 * Return -errno on error, 0 on success. */
static int nbd_negotiate_handle_export_name(NBDClient *client, bool no_zeroes,
                                            Error **errp)
{
    ERRP_GUARD();
    g_autofree char *name = NULL;
    char buf[NBD_REPLY_EXPORT_NAME_SIZE] = "";
    size_t len;
    int ret;
    uint16_t myflags;

    /* Client sends:
        [20 ..  xx]   export name (length bytes)
       Server replies:
        [ 0 ..   7]   size
        [ 8 ..   9]   export flags
        [10 .. 133]   reserved     (0) [unless no_zeroes]
     */
    trace_nbd_negotiate_handle_export_name();
    if (client->optlen > NBD_MAX_STRING_SIZE) {
        error_setg(errp, "Bad length received");
        return -EINVAL;
    }
    name = g_malloc(client->optlen + 1);
    if (nbd_read(client->ioc, name, client->optlen, "export name", errp) < 0) {
        return -EIO;
    }
    name[client->optlen] = '\0';
    client->optlen = 0;

    trace_nbd_negotiate_handle_export_name_request(name);

    client->exp = nbd_export_find(name);
    if (!client->exp) {
        error_setg(errp, "export not found");
        return -EINVAL;
    }

    myflags = client->exp->nbdflags;
    if (client->structured_reply) {
        myflags |= NBD_FLAG_SEND_DF;
    }
    trace_nbd_negotiate_new_style_size_flags(client->exp->size, myflags);
    stq_be_p(buf, client->exp->size);
    stw_be_p(buf + 8, myflags);
    len = no_zeroes ? 10 : sizeof(buf);
    ret = nbd_write(client->ioc, buf, len, errp);
    if (ret < 0) {
        error_prepend(errp, "write failed: ");
        return ret;
    }

    QTAILQ_INSERT_TAIL(&client->exp->clients, client, next);
    blk_exp_ref(&client->exp->common);
    nbd_check_meta_export(client);

    return 0;
}

/* Send a single NBD_REP_INFO, with a buffer @buf of @length bytes.
 * The buffer does NOT include the info type prefix.
 * Return -errno on error, 0 if ready to send more. */
static int nbd_negotiate_send_info(NBDClient *client,
                                   uint16_t info, uint32_t length, void *buf,
                                   Error **errp)
{
    int rc;

    trace_nbd_negotiate_send_info(info, nbd_info_lookup(info), length);
    rc = nbd_negotiate_send_rep_len(client, NBD_REP_INFO,
                                    sizeof(info) + length, errp);
    if (rc < 0) {
        return rc;
    }
    info = cpu_to_be16(info);
    if (nbd_write(client->ioc, &info, sizeof(info), errp) < 0) {
        return -EIO;
    }
    if (nbd_write(client->ioc, buf, length, errp) < 0) {
        return -EIO;
    }
    return 0;
}

/* nbd_reject_length: Handle any unexpected payload.
 * @fatal requests that we quit talking to the client, even if we are able
 * to successfully send an error reply.
 * Return:
 * -errno  transmission error occurred or @fatal was requested, errp is set
 * 0       error message successfully sent to client, errp is not set
 */
static int nbd_reject_length(NBDClient *client, bool fatal, Error **errp)
{
    int ret;

    assert(client->optlen);
    ret = nbd_opt_invalid(client, errp, "option '%s' has unexpected length",
                          nbd_opt_lookup(client->opt));
    if (fatal && !ret) {
        error_setg(errp, "option '%s' has unexpected length",
                   nbd_opt_lookup(client->opt));
        return -EINVAL;
    }
    return ret;
}

/* Handle NBD_OPT_INFO and NBD_OPT_GO.
 * Return -errno on error, 0 if ready for next option, and 1 to move
 * into transmission phase.  */
static int nbd_negotiate_handle_info(NBDClient *client, Error **errp)
{
    int rc;
    g_autofree char *name = NULL;
    NBDExport *exp;
    uint16_t requests;
    uint16_t request;
    uint32_t namelen = 0;
    bool sendname = false;
    bool blocksize = false;
    uint32_t sizes[3];
    char buf[sizeof(uint64_t) + sizeof(uint16_t)];
    uint32_t check_align = 0;
    uint16_t myflags;

    /* Client sends:
        4 bytes: L, name length (can be 0)
        L bytes: export name
        2 bytes: N, number of requests (can be 0)
        N * 2 bytes: N requests
    */
    rc = nbd_opt_read_name(client, &name, &namelen, errp);
    if (rc <= 0) {
        return rc;
    }
    trace_nbd_negotiate_handle_export_name_request(name);

    rc = nbd_opt_read(client, &requests, sizeof(requests), false, errp);
    if (rc <= 0) {
        return rc;
    }
    requests = be16_to_cpu(requests);
    trace_nbd_negotiate_handle_info_requests(requests);
    while (requests--) {
        rc = nbd_opt_read(client, &request, sizeof(request), false, errp);
        if (rc <= 0) {
            return rc;
        }
        request = be16_to_cpu(request);
        trace_nbd_negotiate_handle_info_request(request,
                                                nbd_info_lookup(request));
        /* We care about NBD_INFO_NAME and NBD_INFO_BLOCK_SIZE;
         * everything else is either a request we don't know or
         * something we send regardless of request */
        switch (request) {
        case NBD_INFO_NAME:
            sendname = true;
            break;
        case NBD_INFO_BLOCK_SIZE:
            blocksize = true;
            break;
        }
    }
    if (client->optlen) {
        return nbd_reject_length(client, false, errp);
    }

    exp = nbd_export_find(name);
    if (!exp) {
        g_autofree char *sane_name = nbd_sanitize_name(name);

        return nbd_negotiate_send_rep_err(client, NBD_REP_ERR_UNKNOWN,
                                          errp, "export '%s' not present",
                                          sane_name);
    }

    /* Don't bother sending NBD_INFO_NAME unless client requested it */
    if (sendname) {
        rc = nbd_negotiate_send_info(client, NBD_INFO_NAME, namelen, name,
                                     errp);
        if (rc < 0) {
            return rc;
        }
    }

    /* Send NBD_INFO_DESCRIPTION only if available, regardless of
     * client request */
    if (exp->description) {
        size_t len = strlen(exp->description);

        assert(len <= NBD_MAX_STRING_SIZE);
        rc = nbd_negotiate_send_info(client, NBD_INFO_DESCRIPTION,
                                     len, exp->description, errp);
        if (rc < 0) {
            return rc;
        }
    }

    /* Send NBD_INFO_BLOCK_SIZE always, but tweak the minimum size
     * according to whether the client requested it, and according to
     * whether this is OPT_INFO or OPT_GO. */
    /* minimum - 1 for back-compat, or actual if client will obey it. */
    if (client->opt == NBD_OPT_INFO || blocksize) {
        check_align = sizes[0] = blk_get_request_alignment(exp->common.blk);
    } else {
        sizes[0] = 1;
    }
    assert(sizes[0] <= NBD_MAX_BUFFER_SIZE);
    /* preferred - Hard-code to 4096 for now.
     * TODO: is blk_bs(blk)->bl.opt_transfer appropriate? */
    sizes[1] = MAX(4096, sizes[0]);
    /* maximum - At most 32M, but smaller as appropriate. */
    sizes[2] = MIN(blk_get_max_transfer(exp->common.blk), NBD_MAX_BUFFER_SIZE);
    trace_nbd_negotiate_handle_info_block_size(sizes[0], sizes[1], sizes[2]);
    sizes[0] = cpu_to_be32(sizes[0]);
    sizes[1] = cpu_to_be32(sizes[1]);
    sizes[2] = cpu_to_be32(sizes[2]);
    rc = nbd_negotiate_send_info(client, NBD_INFO_BLOCK_SIZE,
                                 sizeof(sizes), sizes, errp);
    if (rc < 0) {
        return rc;
    }

    /* Send NBD_INFO_EXPORT always */
    myflags = exp->nbdflags;
    if (client->structured_reply) {
        myflags |= NBD_FLAG_SEND_DF;
    }
    trace_nbd_negotiate_new_style_size_flags(exp->size, myflags);
    stq_be_p(buf, exp->size);
    stw_be_p(buf + 8, myflags);
    rc = nbd_negotiate_send_info(client, NBD_INFO_EXPORT,
                                 sizeof(buf), buf, errp);
    if (rc < 0) {
        return rc;
    }

    /*
     * If the client is just asking for NBD_OPT_INFO, but forgot to
     * request block sizes in a situation that would impact
     * performance, then return an error. But for NBD_OPT_GO, we
     * tolerate all clients, regardless of alignments.
     */
    if (client->opt == NBD_OPT_INFO && !blocksize &&
        blk_get_request_alignment(exp->common.blk) > 1) {
        return nbd_negotiate_send_rep_err(client,
                                          NBD_REP_ERR_BLOCK_SIZE_REQD,
                                          errp,
                                          "request NBD_INFO_BLOCK_SIZE to "
                                          "use this export");
    }

    /* Final reply */
    rc = nbd_negotiate_send_rep(client, NBD_REP_ACK, errp);
    if (rc < 0) {
        return rc;
    }

    if (client->opt == NBD_OPT_GO) {
        client->exp = exp;
        client->check_align = check_align;
        QTAILQ_INSERT_TAIL(&client->exp->clients, client, next);
        blk_exp_ref(&client->exp->common);
        nbd_check_meta_export(client);
        rc = 1;
    }
    return rc;
}


/* Handle NBD_OPT_STARTTLS. Return NULL to drop connection, or else the
 * new channel for all further (now-encrypted) communication. */
static QIOChannel *nbd_negotiate_handle_starttls(NBDClient *client,
                                                 Error **errp)
{
    QIOChannel *ioc;
    QIOChannelTLS *tioc;
    struct NBDTLSHandshakeData data = { 0 };

    assert(client->opt == NBD_OPT_STARTTLS);

    trace_nbd_negotiate_handle_starttls();
    ioc = client->ioc;

    if (nbd_negotiate_send_rep(client, NBD_REP_ACK, errp) < 0) {
        return NULL;
    }

    tioc = qio_channel_tls_new_server(ioc,
                                      client->tlscreds,
                                      client->tlsauthz,
                                      errp);
    if (!tioc) {
        return NULL;
    }

    qio_channel_set_name(QIO_CHANNEL(tioc), "nbd-server-tls");
    trace_nbd_negotiate_handle_starttls_handshake();
    data.loop = g_main_loop_new(g_main_context_default(), FALSE);
    qio_channel_tls_handshake(tioc,
                              nbd_tls_handshake,
                              &data,
                              NULL,
                              NULL);

    if (!data.complete) {
        g_main_loop_run(data.loop);
    }
    g_main_loop_unref(data.loop);
    if (data.error) {
        object_unref(OBJECT(tioc));
        error_propagate(errp, data.error);
        return NULL;
    }

    return QIO_CHANNEL(tioc);
}

/* nbd_negotiate_send_meta_context
 *
 * Send one chunk of reply to NBD_OPT_{LIST,SET}_META_CONTEXT
 *
 * For NBD_OPT_LIST_META_CONTEXT @context_id is ignored, 0 is used instead.
 */
static int nbd_negotiate_send_meta_context(NBDClient *client,
                                           const char *context,
                                           uint32_t context_id,
                                           Error **errp)
{
    NBDOptionReplyMetaContext opt;
    struct iovec iov[] = {
        {.iov_base = &opt, .iov_len = sizeof(opt)},
        {.iov_base = (void *)context, .iov_len = strlen(context)}
    };

    assert(iov[1].iov_len <= NBD_MAX_STRING_SIZE);
    if (client->opt == NBD_OPT_LIST_META_CONTEXT) {
        context_id = 0;
    }

    trace_nbd_negotiate_meta_query_reply(context, context_id);
    set_be_option_rep(&opt.h, client->opt, NBD_REP_META_CONTEXT,
                      sizeof(opt) - sizeof(opt.h) + iov[1].iov_len);
    stl_be_p(&opt.context_id, context_id);

    return qio_channel_writev_all(client->ioc, iov, 2, errp) < 0 ? -EIO : 0;
}

/*
 * Return true if @query matches @pattern, or if @query is empty when
 * the @client is performing _LIST_.
 */
static bool nbd_meta_empty_or_pattern(NBDClient *client, const char *pattern,
                                      const char *query)
{
    if (!*query) {
        trace_nbd_negotiate_meta_query_parse("empty");
        return client->opt == NBD_OPT_LIST_META_CONTEXT;
    }
    if (strcmp(query, pattern) == 0) {
        trace_nbd_negotiate_meta_query_parse(pattern);
        return true;
    }
    trace_nbd_negotiate_meta_query_skip("pattern not matched");
    return false;
}

/*
 * Return true and adjust @str in place if it begins with @prefix.
 */
static bool nbd_strshift(const char **str, const char *prefix)
{
    size_t len = strlen(prefix);

    if (strncmp(*str, prefix, len) == 0) {
        *str += len;
        return true;
    }
    return false;
}

/* nbd_meta_base_query
 *
 * Handle queries to 'base' namespace. For now, only the base:allocation
 * context is available.  Return true if @query has been handled.
 */
static bool nbd_meta_base_query(NBDClient *client, NBDExportMetaContexts *meta,
                                const char *query)
{
    if (!nbd_strshift(&query, "base:")) {
        return false;
    }
    trace_nbd_negotiate_meta_query_parse("base:");

    if (nbd_meta_empty_or_pattern(client, "allocation", query)) {
        meta->base_allocation = true;
    }
    return true;
}

/* nbd_meta_qemu_query
 *
 * Handle queries to 'qemu' namespace. For now, only the qemu:dirty-bitmap:
 * and qemu:allocation-depth contexts are available.  Return true if @query
 * has been handled.
 */
static bool nbd_meta_qemu_query(NBDClient *client, NBDExportMetaContexts *meta,
                                const char *query)
{
    size_t i;

    if (!nbd_strshift(&query, "qemu:")) {
        return false;
    }
    trace_nbd_negotiate_meta_query_parse("qemu:");

    if (!*query) {
        if (client->opt == NBD_OPT_LIST_META_CONTEXT) {
            meta->allocation_depth = meta->exp->allocation_depth;
            memset(meta->bitmaps, 1, meta->exp->nr_export_bitmaps);
        }
        trace_nbd_negotiate_meta_query_parse("empty");
        return true;
    }

    if (strcmp(query, "allocation-depth") == 0) {
        trace_nbd_negotiate_meta_query_parse("allocation-depth");
        meta->allocation_depth = meta->exp->allocation_depth;
        return true;
    }

    if (nbd_strshift(&query, "dirty-bitmap:")) {
        trace_nbd_negotiate_meta_query_parse("dirty-bitmap:");
        if (!*query) {
            if (client->opt == NBD_OPT_LIST_META_CONTEXT) {
                memset(meta->bitmaps, 1, meta->exp->nr_export_bitmaps);
            }
            trace_nbd_negotiate_meta_query_parse("empty");
            return true;
        }

        for (i = 0; i < meta->exp->nr_export_bitmaps; i++) {
            const char *bm_name;

            bm_name = bdrv_dirty_bitmap_name(meta->exp->export_bitmaps[i]);
            if (strcmp(bm_name, query) == 0) {
                meta->bitmaps[i] = true;
                trace_nbd_negotiate_meta_query_parse(query);
                return true;
            }
        }
        trace_nbd_negotiate_meta_query_skip("no dirty-bitmap match");
        return true;
    }

    trace_nbd_negotiate_meta_query_skip("unknown qemu context");
    return true;
}

/* nbd_negotiate_meta_query
 *
 * Parse namespace name and call corresponding function to parse body of the
 * query.
 *
 * The only supported namespaces are 'base' and 'qemu'.
 *
 * Return -errno on I/O error, 0 if option was completely handled by
 * sending a reply about inconsistent lengths, or 1 on success. */
static int nbd_negotiate_meta_query(NBDClient *client,
                                    NBDExportMetaContexts *meta, Error **errp)
{
    int ret;
    g_autofree char *query = NULL;
    uint32_t len;

    ret = nbd_opt_read(client, &len, sizeof(len), false, errp);
    if (ret <= 0) {
        return ret;
    }
    len = cpu_to_be32(len);

    if (len > NBD_MAX_STRING_SIZE) {
        trace_nbd_negotiate_meta_query_skip("length too long");
        return nbd_opt_skip(client, len, errp);
    }

    query = g_malloc(len + 1);
    ret = nbd_opt_read(client, query, len, true, errp);
    if (ret <= 0) {
        return ret;
    }
    query[len] = '\0';

    if (nbd_meta_base_query(client, meta, query)) {
        return 1;
    }
    if (nbd_meta_qemu_query(client, meta, query)) {
        return 1;
    }

    trace_nbd_negotiate_meta_query_skip("unknown namespace");
    return 1;
}

/* nbd_negotiate_meta_queries
 * Handle NBD_OPT_LIST_META_CONTEXT and NBD_OPT_SET_META_CONTEXT
 *
 * Return -errno on I/O error, or 0 if option was completely handled. */
static int nbd_negotiate_meta_queries(NBDClient *client,
                                      NBDExportMetaContexts *meta, Error **errp)
{
    int ret;
    g_autofree char *export_name = NULL;
    g_autofree bool *bitmaps = NULL;
    NBDExportMetaContexts local_meta = {0};
    uint32_t nb_queries;
    size_t i;
    size_t count = 0;

    if (!client->structured_reply) {
        return nbd_opt_invalid(client, errp,
                               "request option '%s' when structured reply "
                               "is not negotiated",
                               nbd_opt_lookup(client->opt));
    }

    if (client->opt == NBD_OPT_LIST_META_CONTEXT) {
        /* Only change the caller's meta on SET. */
        meta = &local_meta;
    }

    g_free(meta->bitmaps);
    memset(meta, 0, sizeof(*meta));

    ret = nbd_opt_read_name(client, &export_name, NULL, errp);
    if (ret <= 0) {
        return ret;
    }

    meta->exp = nbd_export_find(export_name);
    if (meta->exp == NULL) {
        g_autofree char *sane_name = nbd_sanitize_name(export_name);

        return nbd_opt_drop(client, NBD_REP_ERR_UNKNOWN, errp,
                            "export '%s' not present", sane_name);
    }
    meta->bitmaps = g_new0(bool, meta->exp->nr_export_bitmaps);
    if (client->opt == NBD_OPT_LIST_META_CONTEXT) {
        bitmaps = meta->bitmaps;
    }

    ret = nbd_opt_read(client, &nb_queries, sizeof(nb_queries), false, errp);
    if (ret <= 0) {
        return ret;
    }
    nb_queries = cpu_to_be32(nb_queries);
    trace_nbd_negotiate_meta_context(nbd_opt_lookup(client->opt),
                                     export_name, nb_queries);

    if (client->opt == NBD_OPT_LIST_META_CONTEXT && !nb_queries) {
        /* enable all known contexts */
        meta->base_allocation = true;
        meta->allocation_depth = meta->exp->allocation_depth;
        memset(meta->bitmaps, 1, meta->exp->nr_export_bitmaps);
    } else {
        for (i = 0; i < nb_queries; ++i) {
            ret = nbd_negotiate_meta_query(client, meta, errp);
            if (ret <= 0) {
                return ret;
            }
        }
    }

    if (meta->base_allocation) {
        ret = nbd_negotiate_send_meta_context(client, "base:allocation",
                                              NBD_META_ID_BASE_ALLOCATION,
                                              errp);
        if (ret < 0) {
            return ret;
        }
        count++;
    }

    if (meta->allocation_depth) {
        ret = nbd_negotiate_send_meta_context(client, "qemu:allocation-depth",
                                              NBD_META_ID_ALLOCATION_DEPTH,
                                              errp);
        if (ret < 0) {
            return ret;
        }
        count++;
    }

    for (i = 0; i < meta->exp->nr_export_bitmaps; i++) {
        const char *bm_name;
        g_autofree char *context = NULL;

        if (!meta->bitmaps[i]) {
            continue;
        }

        bm_name = bdrv_dirty_bitmap_name(meta->exp->export_bitmaps[i]);
        context = g_strdup_printf("qemu:dirty-bitmap:%s", bm_name);

        ret = nbd_negotiate_send_meta_context(client, context,
                                              NBD_META_ID_DIRTY_BITMAP + i,
                                              errp);
        if (ret < 0) {
            return ret;
        }
        count++;
    }

    ret = nbd_negotiate_send_rep(client, NBD_REP_ACK, errp);
    if (ret == 0) {
        meta->count = count;
    }

    return ret;
}

/* nbd_negotiate_options
 * Process all NBD_OPT_* client option commands, during fixed newstyle
 * negotiation.
 * Return:
 * -errno  on error, errp is set
 * 0       on successful negotiation, errp is not set
 * 1       if client sent NBD_OPT_ABORT, i.e. on valid disconnect,
 *         errp is not set
 */
static int nbd_negotiate_options(NBDClient *client, Error **errp)
{
    uint32_t flags;
    bool fixedNewstyle = false;
    bool no_zeroes = false;

    /* Client sends:
        [ 0 ..   3]   client flags

       Then we loop until NBD_OPT_EXPORT_NAME or NBD_OPT_GO:
        [ 0 ..   7]   NBD_OPTS_MAGIC
        [ 8 ..  11]   NBD option
        [12 ..  15]   Data length
        ...           Rest of request

        [ 0 ..   7]   NBD_OPTS_MAGIC
        [ 8 ..  11]   Second NBD option
        [12 ..  15]   Data length
        ...           Rest of request
    */

    if (nbd_read32(client->ioc, &flags, "flags", errp) < 0) {
        return -EIO;
    }
    trace_nbd_negotiate_options_flags(flags);
    if (flags & NBD_FLAG_C_FIXED_NEWSTYLE) {
        fixedNewstyle = true;
        flags &= ~NBD_FLAG_C_FIXED_NEWSTYLE;
    }
    if (flags & NBD_FLAG_C_NO_ZEROES) {
        no_zeroes = true;
        flags &= ~NBD_FLAG_C_NO_ZEROES;
    }
    if (flags != 0) {
        error_setg(errp, "Unknown client flags 0x%" PRIx32 " received", flags);
        return -EINVAL;
    }

    while (1) {
        int ret;
        uint32_t option, length;
        uint64_t magic;

        if (nbd_read64(client->ioc, &magic, "opts magic", errp) < 0) {
            return -EINVAL;
        }
        trace_nbd_negotiate_options_check_magic(magic);
        if (magic != NBD_OPTS_MAGIC) {
            error_setg(errp, "Bad magic received");
            return -EINVAL;
        }

        if (nbd_read32(client->ioc, &option, "option", errp) < 0) {
            return -EINVAL;
        }
        client->opt = option;

        if (nbd_read32(client->ioc, &length, "option length", errp) < 0) {
            return -EINVAL;
        }
        assert(!client->optlen);
        client->optlen = length;

        if (length > NBD_MAX_BUFFER_SIZE) {
            error_setg(errp, "len (%" PRIu32" ) is larger than max len (%u)",
                       length, NBD_MAX_BUFFER_SIZE);
            return -EINVAL;
        }

        trace_nbd_negotiate_options_check_option(option,
                                                 nbd_opt_lookup(option));
        if (client->tlscreds &&
            client->ioc == (QIOChannel *)client->sioc) {
            QIOChannel *tioc;
            if (!fixedNewstyle) {
                error_setg(errp, "Unsupported option 0x%" PRIx32, option);
                return -EINVAL;
            }
            switch (option) {
            case NBD_OPT_STARTTLS:
                if (length) {
                    /* Unconditionally drop the connection if the client
                     * can't start a TLS negotiation correctly */
                    return nbd_reject_length(client, true, errp);
                }
                tioc = nbd_negotiate_handle_starttls(client, errp);
                if (!tioc) {
                    return -EIO;
                }
                ret = 0;
                object_unref(OBJECT(client->ioc));
                client->ioc = QIO_CHANNEL(tioc);
                break;

            case NBD_OPT_EXPORT_NAME:
                /* No way to return an error to client, so drop connection */
                error_setg(errp, "Option 0x%x not permitted before TLS",
                           option);
                return -EINVAL;

            default:
                /* Let the client keep trying, unless they asked to
                 * quit. Always try to give an error back to the
                 * client; but when replying to OPT_ABORT, be aware
                 * that the client may hang up before receiving the
                 * error, in which case we are fine ignoring the
                 * resulting EPIPE. */
                ret = nbd_opt_drop(client, NBD_REP_ERR_TLS_REQD,
                                   option == NBD_OPT_ABORT ? NULL : errp,
                                   "Option 0x%" PRIx32
                                   " not permitted before TLS", option);
                if (option == NBD_OPT_ABORT) {
                    return 1;
                }
                break;
            }
        } else if (fixedNewstyle) {
            switch (option) {
            case NBD_OPT_LIST:
                if (length) {
                    ret = nbd_reject_length(client, false, errp);
                } else {
                    ret = nbd_negotiate_handle_list(client, errp);
                }
                break;

            case NBD_OPT_ABORT:
                /* NBD spec says we must try to reply before
                 * disconnecting, but that we must also tolerate
                 * guests that don't wait for our reply. */
                nbd_negotiate_send_rep(client, NBD_REP_ACK, NULL);
                return 1;

            case NBD_OPT_EXPORT_NAME:
                return nbd_negotiate_handle_export_name(client, no_zeroes,
                                                        errp);

            case NBD_OPT_INFO:
            case NBD_OPT_GO:
                ret = nbd_negotiate_handle_info(client, errp);
                if (ret == 1) {
                    assert(option == NBD_OPT_GO);
                    return 0;
                }
                break;

            case NBD_OPT_STARTTLS:
                if (length) {
                    ret = nbd_reject_length(client, false, errp);
                } else if (client->tlscreds) {
                    ret = nbd_negotiate_send_rep_err(client,
                                                     NBD_REP_ERR_INVALID, errp,
                                                     "TLS already enabled");
                } else {
                    ret = nbd_negotiate_send_rep_err(client,
                                                     NBD_REP_ERR_POLICY, errp,
                                                     "TLS not configured");
                }
                break;

            case NBD_OPT_STRUCTURED_REPLY:
                if (length) {
                    ret = nbd_reject_length(client, false, errp);
                } else if (client->structured_reply) {
                    ret = nbd_negotiate_send_rep_err(
                        client, NBD_REP_ERR_INVALID, errp,
                        "structured reply already negotiated");
                } else {
                    ret = nbd_negotiate_send_rep(client, NBD_REP_ACK, errp);
                    client->structured_reply = true;
                }
                break;

            case NBD_OPT_LIST_META_CONTEXT:
            case NBD_OPT_SET_META_CONTEXT:
                ret = nbd_negotiate_meta_queries(client, &client->export_meta,
                                                 errp);
                break;

            default:
                ret = nbd_opt_drop(client, NBD_REP_ERR_UNSUP, errp,
                                   "Unsupported option %" PRIu32 " (%s)",
                                   option, nbd_opt_lookup(option));
                break;
            }
        } else {
            /*
             * If broken new-style we should drop the connection
             * for anything except NBD_OPT_EXPORT_NAME
             */
            switch (option) {
            case NBD_OPT_EXPORT_NAME:
                return nbd_negotiate_handle_export_name(client, no_zeroes,
                                                        errp);

            default:
                error_setg(errp, "Unsupported option %" PRIu32 " (%s)",
                           option, nbd_opt_lookup(option));
                return -EINVAL;
            }
        }
        if (ret < 0) {
            return ret;
        }
    }
}

/* nbd_negotiate
 * Return:
 * -errno  on error, errp is set
 * 0       on successful negotiation, errp is not set
 * 1       if client sent NBD_OPT_ABORT, i.e. on valid disconnect,
 *         errp is not set
 */
static coroutine_fn int nbd_negotiate(NBDClient *client, Error **errp)
{
    ERRP_GUARD();
    char buf[NBD_OLDSTYLE_NEGOTIATE_SIZE] = "";
    int ret;

    /* Old style negotiation header, no room for options
        [ 0 ..   7]   passwd       ("NBDMAGIC")
        [ 8 ..  15]   magic        (NBD_CLIENT_MAGIC)
        [16 ..  23]   size
        [24 ..  27]   export flags (zero-extended)
        [28 .. 151]   reserved     (0)

       New style negotiation header, client can send options
        [ 0 ..   7]   passwd       ("NBDMAGIC")
        [ 8 ..  15]   magic        (NBD_OPTS_MAGIC)
        [16 ..  17]   server flags (0)
        ....options sent, ending in NBD_OPT_EXPORT_NAME or NBD_OPT_GO....
     */

    qio_channel_set_blocking(client->ioc, false, NULL);

    trace_nbd_negotiate_begin();
    memcpy(buf, "NBDMAGIC", 8);

    stq_be_p(buf + 8, NBD_OPTS_MAGIC);
    stw_be_p(buf + 16, NBD_FLAG_FIXED_NEWSTYLE | NBD_FLAG_NO_ZEROES);

    if (nbd_write(client->ioc, buf, 18, errp) < 0) {
        error_prepend(errp, "write failed: ");
        return -EINVAL;
    }
    ret = nbd_negotiate_options(client, errp);
    if (ret != 0) {
        if (ret < 0) {
            error_prepend(errp, "option negotiation failed: ");
        }
        return ret;
    }

    /* Attach the channel to the same AioContext as the export */
    if (client->exp && client->exp->common.ctx) {
        qio_channel_attach_aio_context(client->ioc, client->exp->common.ctx);
    }

    assert(!client->optlen);
    trace_nbd_negotiate_success();

    return 0;
}

static int nbd_receive_request(QIOChannel *ioc, NBDRequest *request,
                               Error **errp)
{
    uint8_t buf[NBD_REQUEST_SIZE];
    uint32_t magic;
    int ret;

    ret = nbd_read(ioc, buf, sizeof(buf), "request", errp);
    if (ret < 0) {
        return ret;
    }

    /* Request
       [ 0 ..  3]   magic   (NBD_REQUEST_MAGIC)
       [ 4 ..  5]   flags   (NBD_CMD_FLAG_FUA, ...)
       [ 6 ..  7]   type    (NBD_CMD_READ, ...)
       [ 8 .. 15]   handle
       [16 .. 23]   from
       [24 .. 27]   len
     */

    magic = ldl_be_p(buf);
    request->flags  = lduw_be_p(buf + 4);
    request->type   = lduw_be_p(buf + 6);
    request->handle = ldq_be_p(buf + 8);
    request->from   = ldq_be_p(buf + 16);
    request->len    = ldl_be_p(buf + 24);

    trace_nbd_receive_request(magic, request->flags, request->type,
                              request->from, request->len);

    if (magic != NBD_REQUEST_MAGIC) {
        error_setg(errp, "invalid magic (got 0x%" PRIx32 ")", magic);
        return -EINVAL;
    }
    return 0;
}

#define MAX_NBD_REQUESTS 16

void nbd_client_get(NBDClient *client)
{
    client->refcount++;
}

void nbd_client_put(NBDClient *client)
{
    if (--client->refcount == 0) {
        /* The last reference should be dropped by client->close,
         * which is called by client_close.
         */
        assert(client->closing);

        qio_channel_detach_aio_context(client->ioc);
        object_unref(OBJECT(client->sioc));
        object_unref(OBJECT(client->ioc));
        if (client->tlscreds) {
            object_unref(OBJECT(client->tlscreds));
        }
        g_free(client->tlsauthz);
        if (client->exp) {
            QTAILQ_REMOVE(&client->exp->clients, client, next);
            blk_exp_unref(&client->exp->common);
        }
        g_free(client->export_meta.bitmaps);
        g_free(client);
    }
}

static void client_close(NBDClient *client, bool negotiated)
{
    if (client->closing) {
        return;
    }

    client->closing = true;

    /* Force requests to finish.  They will drop their own references,
     * then we'll close the socket and free the NBDClient.
     */
    qio_channel_shutdown(client->ioc, QIO_CHANNEL_SHUTDOWN_BOTH,
                         NULL);

    /* Also tell the client, so that they release their reference.  */
    if (client->close_fn) {
        client->close_fn(client, negotiated);
    }
}

static NBDRequestData *nbd_request_get(NBDClient *client)
{
    NBDRequestData *req;

    assert(client->nb_requests <= MAX_NBD_REQUESTS - 1);
    client->nb_requests++;

    req = g_new0(NBDRequestData, 1);
    nbd_client_get(client);
    req->client = client;
    return req;
}

static void nbd_request_put(NBDRequestData *req)
{
    NBDClient *client = req->client;

    if (req->data) {
        qemu_vfree(req->data);
    }
    g_free(req);

    client->nb_requests--;
    nbd_client_receive_next_request(client);

    nbd_client_put(client);
}

static void blk_aio_attached(AioContext *ctx, void *opaque)
{
    NBDExport *exp = opaque;
    NBDClient *client;

    trace_nbd_blk_aio_attached(exp->name, ctx);

    exp->common.ctx = ctx;

    QTAILQ_FOREACH(client, &exp->clients, next) {
        qio_channel_attach_aio_context(client->ioc, ctx);
        if (client->recv_coroutine) {
            aio_co_schedule(ctx, client->recv_coroutine);
        }
        if (client->send_coroutine) {
            aio_co_schedule(ctx, client->send_coroutine);
        }
    }
}

static void blk_aio_detach(void *opaque)
{
    NBDExport *exp = opaque;
    NBDClient *client;

    trace_nbd_blk_aio_detach(exp->name, exp->common.ctx);

    QTAILQ_FOREACH(client, &exp->clients, next) {
        qio_channel_detach_aio_context(client->ioc);
    }

    exp->common.ctx = NULL;
}

static void nbd_eject_notifier(Notifier *n, void *data)
{
    NBDExport *exp = container_of(n, NBDExport, eject_notifier);

    blk_exp_request_shutdown(&exp->common);
}

void nbd_export_set_on_eject_blk(BlockExport *exp, BlockBackend *blk)
{
    NBDExport *nbd_exp = container_of(exp, NBDExport, common);
    assert(exp->drv == &blk_exp_nbd);
    assert(nbd_exp->eject_notifier_blk == NULL);

    blk_ref(blk);
    nbd_exp->eject_notifier_blk = blk;
    nbd_exp->eject_notifier.notify = nbd_eject_notifier;
    blk_add_remove_bs_notifier(blk, &nbd_exp->eject_notifier);
}

static int nbd_export_create(BlockExport *blk_exp, BlockExportOptions *exp_args,
                             Error **errp)
{
    NBDExport *exp = container_of(blk_exp, NBDExport, common);
    BlockExportOptionsNbd *arg = &exp_args->u.nbd;
    BlockBackend *blk = blk_exp->blk;
    int64_t size;
    uint64_t perm, shared_perm;
    bool readonly = !exp_args->writable;
    bool shared = !exp_args->writable;
    strList *bitmaps;
    size_t i;
    int ret;

    assert(exp_args->type == BLOCK_EXPORT_TYPE_NBD);

    if (!nbd_server_is_running()) {
        error_setg(errp, "NBD server not running");
        return -EINVAL;
    }

    if (!arg->has_name) {
        arg->name = exp_args->node_name;
    }

    if (strlen(arg->name) > NBD_MAX_STRING_SIZE) {
        error_setg(errp, "export name '%s' too long", arg->name);
        return -EINVAL;
    }

    if (arg->description && strlen(arg->description) > NBD_MAX_STRING_SIZE) {
        error_setg(errp, "description '%s' too long", arg->description);
        return -EINVAL;
    }

    if (nbd_export_find(arg->name)) {
        error_setg(errp, "NBD server already has export named '%s'", arg->name);
        return -EEXIST;
    }

    size = blk_getlength(blk);
    if (size < 0) {
        error_setg_errno(errp, -size,
                         "Failed to determine the NBD export's length");
        return size;
    }

    /* Don't allow resize while the NBD server is running, otherwise we don't
     * care what happens with the node. */
    blk_get_perm(blk, &perm, &shared_perm);
    ret = blk_set_perm(blk, perm, shared_perm & ~BLK_PERM_RESIZE, errp);
    if (ret < 0) {
        return ret;
    }

    QTAILQ_INIT(&exp->clients);
    exp->name = g_strdup(arg->name);
    exp->description = g_strdup(arg->description);
    exp->nbdflags = (NBD_FLAG_HAS_FLAGS | NBD_FLAG_SEND_FLUSH |
                     NBD_FLAG_SEND_FUA | NBD_FLAG_SEND_CACHE);
    if (readonly) {
        exp->nbdflags |= NBD_FLAG_READ_ONLY;
        if (shared) {
            exp->nbdflags |= NBD_FLAG_CAN_MULTI_CONN;
        }
    } else {
        exp->nbdflags |= (NBD_FLAG_SEND_TRIM | NBD_FLAG_SEND_WRITE_ZEROES |
                          NBD_FLAG_SEND_FAST_ZERO);
    }
    exp->size = QEMU_ALIGN_DOWN(size, BDRV_SECTOR_SIZE);

    for (bitmaps = arg->bitmaps; bitmaps; bitmaps = bitmaps->next) {
        exp->nr_export_bitmaps++;
    }
    exp->export_bitmaps = g_new0(BdrvDirtyBitmap *, exp->nr_export_bitmaps);
    for (i = 0, bitmaps = arg->bitmaps; bitmaps;
         i++, bitmaps = bitmaps->next) {
        const char *bitmap = bitmaps->value;
        BlockDriverState *bs = blk_bs(blk);
        BdrvDirtyBitmap *bm = NULL;

        while (bs) {
            bm = bdrv_find_dirty_bitmap(bs, bitmap);
            if (bm != NULL) {
                break;
            }

            bs = bdrv_filter_or_cow_bs(bs);
        }

        if (bm == NULL) {
            ret = -ENOENT;
            error_setg(errp, "Bitmap '%s' is not found", bitmap);
            goto fail;
        }

        if (bdrv_dirty_bitmap_check(bm, BDRV_BITMAP_ALLOW_RO, errp)) {
            ret = -EINVAL;
            goto fail;
        }

        if (readonly && bdrv_is_writable(bs) &&
            bdrv_dirty_bitmap_enabled(bm)) {
            ret = -EINVAL;
            error_setg(errp,
                       "Enabled bitmap '%s' incompatible with readonly export",
                       bitmap);
            goto fail;
        }

        exp->export_bitmaps[i] = bm;
        assert(strlen(bitmap) <= BDRV_BITMAP_MAX_NAME_SIZE);
    }

    /* Mark bitmaps busy in a separate loop, to simplify roll-back concerns. */
    for (i = 0; i < exp->nr_export_bitmaps; i++) {
        bdrv_dirty_bitmap_set_busy(exp->export_bitmaps[i], true);
    }

    exp->allocation_depth = arg->allocation_depth;

    blk_add_aio_context_notifier(blk, blk_aio_attached, blk_aio_detach, exp);

    QTAILQ_INSERT_TAIL(&exports, exp, next);

    return 0;

fail:
    g_free(exp->export_bitmaps);
    g_free(exp->name);
    g_free(exp->description);
    return ret;
}

NBDExport *nbd_export_find(const char *name)
{
    NBDExport *exp;
    QTAILQ_FOREACH(exp, &exports, next) {
        if (strcmp(name, exp->name) == 0) {
            return exp;
        }
    }

    return NULL;
}

AioContext *
nbd_export_aio_context(NBDExport *exp)
{
    return exp->common.ctx;
}

static void nbd_export_request_shutdown(BlockExport *blk_exp)
{
    NBDExport *exp = container_of(blk_exp, NBDExport, common);
    NBDClient *client, *next;

    blk_exp_ref(&exp->common);
    /*
     * TODO: Should we expand QMP NbdServerRemoveNode enum to allow a
     * close mode that stops advertising the export to new clients but
     * still permits existing clients to run to completion? Because of
     * that possibility, nbd_export_close() can be called more than
     * once on an export.
     */
    QTAILQ_FOREACH_SAFE(client, &exp->clients, next, next) {
        client_close(client, true);
    }
    if (exp->name) {
        g_free(exp->name);
        exp->name = NULL;
        QTAILQ_REMOVE(&exports, exp, next);
    }
    blk_exp_unref(&exp->common);
}

static void nbd_export_delete(BlockExport *blk_exp)
{
    size_t i;
    NBDExport *exp = container_of(blk_exp, NBDExport, common);

    assert(exp->name == NULL);
    assert(QTAILQ_EMPTY(&exp->clients));

    g_free(exp->description);
    exp->description = NULL;

    if (exp->common.blk) {
        if (exp->eject_notifier_blk) {
            notifier_remove(&exp->eject_notifier);
            blk_unref(exp->eject_notifier_blk);
        }
        blk_remove_aio_context_notifier(exp->common.blk, blk_aio_attached,
                                        blk_aio_detach, exp);
    }

    for (i = 0; i < exp->nr_export_bitmaps; i++) {
        bdrv_dirty_bitmap_set_busy(exp->export_bitmaps[i], false);
    }
}

const BlockExportDriver blk_exp_nbd = {
    .type               = BLOCK_EXPORT_TYPE_NBD,
    .instance_size      = sizeof(NBDExport),
    .create             = nbd_export_create,
    .delete             = nbd_export_delete,
    .request_shutdown   = nbd_export_request_shutdown,
};

static int coroutine_fn nbd_co_send_iov(NBDClient *client, struct iovec *iov,
                                        unsigned niov, Error **errp)
{
    int ret;

    g_assert(qemu_in_coroutine());
    qemu_co_mutex_lock(&client->send_lock);
    client->send_coroutine = qemu_coroutine_self();

    ret = qio_channel_writev_all(client->ioc, iov, niov, errp) < 0 ? -EIO : 0;

    client->send_coroutine = NULL;
    qemu_co_mutex_unlock(&client->send_lock);

    return ret;
}

static inline void set_be_simple_reply(NBDSimpleReply *reply, uint64_t error,
                                       uint64_t handle)
{
    stl_be_p(&reply->magic, NBD_SIMPLE_REPLY_MAGIC);
    stl_be_p(&reply->error, error);
    stq_be_p(&reply->handle, handle);
}

static int nbd_co_send_simple_reply(NBDClient *client,
                                    uint64_t handle,
                                    uint32_t error,
                                    void *data,
                                    size_t len,
                                    Error **errp)
{
    NBDSimpleReply reply;
    int nbd_err = system_errno_to_nbd_errno(error);
    struct iovec iov[] = {
        {.iov_base = &reply, .iov_len = sizeof(reply)},
        {.iov_base = data, .iov_len = len}
    };

    trace_nbd_co_send_simple_reply(handle, nbd_err, nbd_err_lookup(nbd_err),
                                   len);
    set_be_simple_reply(&reply, nbd_err, handle);

    return nbd_co_send_iov(client, iov, len ? 2 : 1, errp);
}

static inline void set_be_chunk(NBDStructuredReplyChunk *chunk, uint16_t flags,
                                uint16_t type, uint64_t handle, uint32_t length)
{
    stl_be_p(&chunk->magic, NBD_STRUCTURED_REPLY_MAGIC);
    stw_be_p(&chunk->flags, flags);
    stw_be_p(&chunk->type, type);
    stq_be_p(&chunk->handle, handle);
    stl_be_p(&chunk->length, length);
}

static int coroutine_fn nbd_co_send_structured_done(NBDClient *client,
                                                    uint64_t handle,
                                                    Error **errp)
{
    NBDStructuredReplyChunk chunk;
    struct iovec iov[] = {
        {.iov_base = &chunk, .iov_len = sizeof(chunk)},
    };

    trace_nbd_co_send_structured_done(handle);
    set_be_chunk(&chunk, NBD_REPLY_FLAG_DONE, NBD_REPLY_TYPE_NONE, handle, 0);

    return nbd_co_send_iov(client, iov, 1, errp);
}

static int coroutine_fn nbd_co_send_structured_read(NBDClient *client,
                                                    uint64_t handle,
                                                    uint64_t offset,
                                                    void *data,
                                                    size_t size,
                                                    bool final,
                                                    Error **errp)
{
    NBDStructuredReadData chunk;
    struct iovec iov[] = {
        {.iov_base = &chunk, .iov_len = sizeof(chunk)},
        {.iov_base = data, .iov_len = size}
    };

    assert(size);
    trace_nbd_co_send_structured_read(handle, offset, data, size);
    set_be_chunk(&chunk.h, final ? NBD_REPLY_FLAG_DONE : 0,
                 NBD_REPLY_TYPE_OFFSET_DATA, handle,
                 sizeof(chunk) - sizeof(chunk.h) + size);
    stq_be_p(&chunk.offset, offset);

    return nbd_co_send_iov(client, iov, 2, errp);
}

static int coroutine_fn nbd_co_send_structured_error(NBDClient *client,
                                                     uint64_t handle,
                                                     uint32_t error,
                                                     const char *msg,
                                                     Error **errp)
{
    NBDStructuredError chunk;
    int nbd_err = system_errno_to_nbd_errno(error);
    struct iovec iov[] = {
        {.iov_base = &chunk, .iov_len = sizeof(chunk)},
        {.iov_base = (char *)msg, .iov_len = msg ? strlen(msg) : 0},
    };

    assert(nbd_err);
    trace_nbd_co_send_structured_error(handle, nbd_err,
                                       nbd_err_lookup(nbd_err), msg ? msg : "");
    set_be_chunk(&chunk.h, NBD_REPLY_FLAG_DONE, NBD_REPLY_TYPE_ERROR, handle,
                 sizeof(chunk) - sizeof(chunk.h) + iov[1].iov_len);
    stl_be_p(&chunk.error, nbd_err);
    stw_be_p(&chunk.message_length, iov[1].iov_len);

    return nbd_co_send_iov(client, iov, 1 + !!iov[1].iov_len, errp);
}

/* Do a sparse read and send the structured reply to the client.
 * Returns -errno if sending fails. bdrv_block_status_above() failure is
 * reported to the client, at which point this function succeeds.
 */
static int coroutine_fn nbd_co_send_sparse_read(NBDClient *client,
                                                uint64_t handle,
                                                uint64_t offset,
                                                uint8_t *data,
                                                size_t size,
                                                Error **errp)
{
    int ret = 0;
    NBDExport *exp = client->exp;
    size_t progress = 0;

    while (progress < size) {
        int64_t pnum;
        int status = bdrv_block_status_above(blk_bs(exp->common.blk), NULL,
                                             offset + progress,
                                             size - progress, &pnum, NULL,
                                             NULL);
        bool final;

        if (status < 0) {
            char *msg = g_strdup_printf("unable to check for holes: %s",
                                        strerror(-status));

            ret = nbd_co_send_structured_error(client, handle, -status, msg,
                                               errp);
            g_free(msg);
            return ret;
        }
        assert(pnum && pnum <= size - progress);
        final = progress + pnum == size;
        if (status & BDRV_BLOCK_ZERO) {
            NBDStructuredReadHole chunk;
            struct iovec iov[] = {
                {.iov_base = &chunk, .iov_len = sizeof(chunk)},
            };

            trace_nbd_co_send_structured_read_hole(handle, offset + progress,
                                                   pnum);
            set_be_chunk(&chunk.h, final ? NBD_REPLY_FLAG_DONE : 0,
                         NBD_REPLY_TYPE_OFFSET_HOLE,
                         handle, sizeof(chunk) - sizeof(chunk.h));
            stq_be_p(&chunk.offset, offset + progress);
            stl_be_p(&chunk.length, pnum);
            ret = nbd_co_send_iov(client, iov, 1, errp);
        } else {
            ret = blk_pread(exp->common.blk, offset + progress,
                            data + progress, pnum);
            if (ret < 0) {
                error_setg_errno(errp, -ret, "reading from file failed");
                break;
            }
            ret = nbd_co_send_structured_read(client, handle, offset + progress,
                                              data + progress, pnum, final,
                                              errp);
        }

        if (ret < 0) {
            break;
        }
        progress += pnum;
    }
    return ret;
}

typedef struct NBDExtentArray {
    NBDExtent *extents;
    unsigned int nb_alloc;
    unsigned int count;
    uint64_t total_length;
    bool can_add;
    bool converted_to_be;
} NBDExtentArray;

static NBDExtentArray *nbd_extent_array_new(unsigned int nb_alloc)
{
    NBDExtentArray *ea = g_new0(NBDExtentArray, 1);

    ea->nb_alloc = nb_alloc;
    ea->extents = g_new(NBDExtent, nb_alloc);
    ea->can_add = true;

    return ea;
}

static void nbd_extent_array_free(NBDExtentArray *ea)
{
    g_free(ea->extents);
    g_free(ea);
}
G_DEFINE_AUTOPTR_CLEANUP_FUNC(NBDExtentArray, nbd_extent_array_free);

/* Further modifications of the array after conversion are abandoned */
static void nbd_extent_array_convert_to_be(NBDExtentArray *ea)
{
    int i;

    assert(!ea->converted_to_be);
    ea->can_add = false;
    ea->converted_to_be = true;

    for (i = 0; i < ea->count; i++) {
        ea->extents[i].flags = cpu_to_be32(ea->extents[i].flags);
        ea->extents[i].length = cpu_to_be32(ea->extents[i].length);
    }
}

/*
 * Add extent to NBDExtentArray. If extent can't be added (no available space),
 * return -1.
 * For safety, when returning -1 for the first time, .can_add is set to false,
 * further call to nbd_extent_array_add() will crash.
 * (to avoid the situation, when after failing to add an extent (returned -1),
 * user miss this failure and add another extent, which is successfully added
 * (array is full, but new extent may be squashed into the last one), then we
 * have invalid array with skipped extent)
 */
static int nbd_extent_array_add(NBDExtentArray *ea,
                                uint32_t length, uint32_t flags)
{
    assert(ea->can_add);

    if (!length) {
        return 0;
    }

    /* Extend previous extent if flags are the same */
    if (ea->count > 0 && flags == ea->extents[ea->count - 1].flags) {
        uint64_t sum = (uint64_t)length + ea->extents[ea->count - 1].length;

        if (sum <= UINT32_MAX) {
            ea->extents[ea->count - 1].length = sum;
            ea->total_length += length;
            return 0;
        }
    }

    if (ea->count >= ea->nb_alloc) {
        ea->can_add = false;
        return -1;
    }

    ea->total_length += length;
    ea->extents[ea->count] = (NBDExtent) {.length = length, .flags = flags};
    ea->count++;

    return 0;
}

static int blockstatus_to_extents(BlockDriverState *bs, uint64_t offset,
                                  uint64_t bytes, NBDExtentArray *ea)
{
    while (bytes) {
        uint32_t flags;
        int64_t num;
        int ret = bdrv_block_status_above(bs, NULL, offset, bytes, &num,
                                          NULL, NULL);

        if (ret < 0) {
            return ret;
        }

        flags = (ret & BDRV_BLOCK_ALLOCATED ? 0 : NBD_STATE_HOLE) |
                (ret & BDRV_BLOCK_ZERO      ? NBD_STATE_ZERO : 0);

        if (nbd_extent_array_add(ea, num, flags) < 0) {
            return 0;
        }

        offset += num;
        bytes -= num;
    }

    return 0;
}

static int blockalloc_to_extents(BlockDriverState *bs, uint64_t offset,
                                 uint64_t bytes, NBDExtentArray *ea)
{
    while (bytes) {
        int64_t num;
        int ret = bdrv_is_allocated_above(bs, NULL, false, offset, bytes,
                                          &num);

        if (ret < 0) {
            return ret;
        }

        if (nbd_extent_array_add(ea, num, ret) < 0) {
            return 0;
        }

        offset += num;
        bytes -= num;
    }

    return 0;
}

/*
 * nbd_co_send_extents
 *
 * @ea is converted to BE by the function
 * @last controls whether NBD_REPLY_FLAG_DONE is sent.
 */
static int nbd_co_send_extents(NBDClient *client, uint64_t handle,
                               NBDExtentArray *ea,
                               bool last, uint32_t context_id, Error **errp)
{
    NBDStructuredMeta chunk;
    struct iovec iov[] = {
        {.iov_base = &chunk, .iov_len = sizeof(chunk)},
        {.iov_base = ea->extents, .iov_len = ea->count * sizeof(ea->extents[0])}
    };

    nbd_extent_array_convert_to_be(ea);

    trace_nbd_co_send_extents(handle, ea->count, context_id, ea->total_length,
                              last);
    set_be_chunk(&chunk.h, last ? NBD_REPLY_FLAG_DONE : 0,
                 NBD_REPLY_TYPE_BLOCK_STATUS,
                 handle, sizeof(chunk) - sizeof(chunk.h) + iov[1].iov_len);
    stl_be_p(&chunk.context_id, context_id);

    return nbd_co_send_iov(client, iov, 2, errp);
}

/* Get block status from the exported device and send it to the client */
static int nbd_co_send_block_status(NBDClient *client, uint64_t handle,
                                    BlockDriverState *bs, uint64_t offset,
                                    uint32_t length, bool dont_fragment,
                                    bool last, uint32_t context_id,
                                    Error **errp)
{
    int ret;
    unsigned int nb_extents = dont_fragment ? 1 : NBD_MAX_BLOCK_STATUS_EXTENTS;
    g_autoptr(NBDExtentArray) ea = nbd_extent_array_new(nb_extents);

    if (context_id == NBD_META_ID_BASE_ALLOCATION) {
        ret = blockstatus_to_extents(bs, offset, length, ea);
    } else {
        ret = blockalloc_to_extents(bs, offset, length, ea);
    }
    if (ret < 0) {
        return nbd_co_send_structured_error(
                client, handle, -ret, "can't get block status", errp);
    }

    return nbd_co_send_extents(client, handle, ea, last, context_id, errp);
}

/* Populate @ea from a dirty bitmap. */
static void bitmap_to_extents(BdrvDirtyBitmap *bitmap,
                              uint64_t offset, uint64_t length,
                              NBDExtentArray *es)
{
    int64_t start, dirty_start, dirty_count;
    int64_t end = offset + length;
    bool full = false;

    bdrv_dirty_bitmap_lock(bitmap);

    for (start = offset;
         bdrv_dirty_bitmap_next_dirty_area(bitmap, start, end, INT32_MAX,
                                           &dirty_start, &dirty_count);
         start = dirty_start + dirty_count)
    {
        if ((nbd_extent_array_add(es, dirty_start - start, 0) < 0) ||
            (nbd_extent_array_add(es, dirty_count, NBD_STATE_DIRTY) < 0))
        {
            full = true;
            break;
        }
    }

    if (!full) {
        /* last non dirty extent, nothing to do if array is now full */
        (void) nbd_extent_array_add(es, end - start, 0);
    }

    bdrv_dirty_bitmap_unlock(bitmap);
}

static int nbd_co_send_bitmap(NBDClient *client, uint64_t handle,
                              BdrvDirtyBitmap *bitmap, uint64_t offset,
                              uint32_t length, bool dont_fragment, bool last,
                              uint32_t context_id, Error **errp)
{
    unsigned int nb_extents = dont_fragment ? 1 : NBD_MAX_BLOCK_STATUS_EXTENTS;
    g_autoptr(NBDExtentArray) ea = nbd_extent_array_new(nb_extents);

    bitmap_to_extents(bitmap, offset, length, ea);

    return nbd_co_send_extents(client, handle, ea, last, context_id, errp);
}

/* nbd_co_receive_request
 * Collect a client request. Return 0 if request looks valid, -EIO to drop
 * connection right away, and any other negative value to report an error to
 * the client (although the caller may still need to disconnect after reporting
 * the error).
 */
static int nbd_co_receive_request(NBDRequestData *req, NBDRequest *request,
                                  Error **errp)
{
    NBDClient *client = req->client;
    int valid_flags;

    g_assert(qemu_in_coroutine());
    assert(client->recv_coroutine == qemu_coroutine_self());
    if (nbd_receive_request(client->ioc, request, errp) < 0) {
        return -EIO;
    }

    trace_nbd_co_receive_request_decode_type(request->handle, request->type,
                                             nbd_cmd_lookup(request->type));

    if (request->type != NBD_CMD_WRITE) {
        /* No payload, we are ready to read the next request.  */
        req->complete = true;
    }

    if (request->type == NBD_CMD_DISC) {
        /* Special case: we're going to disconnect without a reply,
         * whether or not flags, from, or len are bogus */
        return -EIO;
    }

    if (request->type == NBD_CMD_READ || request->type == NBD_CMD_WRITE ||
        request->type == NBD_CMD_CACHE)
    {
        if (request->len > NBD_MAX_BUFFER_SIZE) {
            error_setg(errp, "len (%" PRIu32" ) is larger than max len (%u)",
                       request->len, NBD_MAX_BUFFER_SIZE);
            return -EINVAL;
        }

        if (request->type != NBD_CMD_CACHE) {
            req->data = blk_try_blockalign(client->exp->common.blk,
                                           request->len);
            if (req->data == NULL) {
                error_setg(errp, "No memory");
                return -ENOMEM;
            }
        }
    }

    if (request->type == NBD_CMD_WRITE) {
        if (nbd_read(client->ioc, req->data, request->len, "CMD_WRITE data",
                     errp) < 0)
        {
            return -EIO;
        }
        req->complete = true;

        trace_nbd_co_receive_request_payload_received(request->handle,
                                                      request->len);
    }

    /* Sanity checks. */
    if (client->exp->nbdflags & NBD_FLAG_READ_ONLY &&
        (request->type == NBD_CMD_WRITE ||
         request->type == NBD_CMD_WRITE_ZEROES ||
         request->type == NBD_CMD_TRIM)) {
        error_setg(errp, "Export is read-only");
        return -EROFS;
    }
    if (request->from > client->exp->size ||
        request->len > client->exp->size - request->from) {
        error_setg(errp, "operation past EOF; From: %" PRIu64 ", Len: %" PRIu32
                   ", Size: %" PRIu64, request->from, request->len,
                   client->exp->size);
        return (request->type == NBD_CMD_WRITE ||
                request->type == NBD_CMD_WRITE_ZEROES) ? -ENOSPC : -EINVAL;
    }
    if (client->check_align && !QEMU_IS_ALIGNED(request->from | request->len,
                                                client->check_align)) {
        /*