summaryrefslogtreecommitdiffstats
path: root/hw/hppa/machine.c
blob: 0fb8fb877e966996b36d332d89e1d0b25f0ac422 (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
/*
 * QEMU HPPA hardware system emulator.
 * Copyright 2018 Helge Deller <deller@gmx.de>
 */

#include "qemu/osdep.h"
#include "qemu-common.h"
#include "cpu.h"
#include "hw/hw.h"
#include "elf.h"
#include "hw/loader.h"
#include "hw/boards.h"
#include "qemu/error-report.h"
#include "sysemu/sysemu.h"
#include "hw/timer/mc146818rtc.h"
#include "hw/ide.h"
#include "hw/timer/i8254.h"
#include "hw/char/serial.h"
#include "hppa_sys.h"
#include "qemu/units.h"
#include "qapi/error.h"
#include "qemu/log.h"

#define MAX_IDE_BUS 2

static ISABus *hppa_isa_bus(void)
{
    ISABus *isa_bus;
    qemu_irq *isa_irqs;
    MemoryRegion *isa_region;

    isa_region = g_new(MemoryRegion, 1);
    memory_region_init_io(isa_region, NULL, &hppa_pci_ignore_ops,
                          NULL, "isa-io", 0x800);
    memory_region_add_subregion(get_system_memory(), IDE_HPA,
                                isa_region);

    isa_bus = isa_bus_new(NULL, get_system_memory(), isa_region,
                          &error_abort);
    isa_irqs = i8259_init(isa_bus,
                          /* qemu_allocate_irq(dino_set_isa_irq, s, 0)); */
                          NULL);
    isa_bus_irqs(isa_bus, isa_irqs);

    return isa_bus;
}

static uint64_t cpu_hppa_to_phys(void *opaque, uint64_t addr)
{
    addr &= (0x10000000 - 1);
    return addr;
}

static HPPACPU *cpu[HPPA_MAX_CPUS];
static uint64_t firmware_entry;

static void machine_hppa_init(MachineState *machine)
{
    const char *kernel_filename = machine->kernel_filename;
    const char *kernel_cmdline = machine->kernel_cmdline;
    const char *initrd_filename = machine->initrd_filename;
    DeviceState *dev;
    PCIBus *pci_bus;
    ISABus *isa_bus;
    qemu_irq rtc_irq, serial_irq;
    char *firmware_filename;
    uint64_t firmware_low, firmware_high;
    long size;
    uint64_t kernel_entry = 0, kernel_low, kernel_high;
    MemoryRegion *addr_space = get_system_memory();
    MemoryRegion *rom_region;
    MemoryRegion *ram_region;
    MemoryRegion *cpu_region;
    long i;

    ram_size = machine->ram_size;

    /* Create CPUs.  */
    for (i = 0; i < smp_cpus; i++) {
        cpu[i] = HPPA_CPU(cpu_create(machine->cpu_type));

        cpu_region = g_new(MemoryRegion, 1);
        memory_region_init_io(cpu_region, OBJECT(cpu[i]), &hppa_io_eir_ops,
                              cpu[i], g_strdup_printf("cpu%ld-io-eir", i), 4);
        memory_region_add_subregion(addr_space, CPU_HPA + i * 0x1000,
                                    cpu_region);
    }

    /* Limit main memory. */
    if (ram_size > FIRMWARE_START) {
        machine->ram_size = ram_size = FIRMWARE_START;
    }

    /* Main memory region. */
    ram_region = g_new(MemoryRegion, 1);
    memory_region_allocate_system_memory(ram_region, OBJECT(machine),
                                         "ram", ram_size);
    memory_region_add_subregion(addr_space, 0, ram_region);

    /* Init Dino (PCI host bus chip).  */
    pci_bus = dino_init(addr_space, &rtc_irq, &serial_irq);
    assert(pci_bus);

    /* Create ISA bus. */
    isa_bus = hppa_isa_bus();
    assert(isa_bus);

    /* Realtime clock, used by firmware for PDC_TOD call. */
    mc146818_rtc_init(isa_bus, 2000, rtc_irq);

    /* Serial code setup.  */
    if (serial_hd(0)) {
        uint32_t addr = DINO_UART_HPA + 0x800;
        serial_mm_init(addr_space, addr, 0, serial_irq,
                       115200, serial_hd(0), DEVICE_BIG_ENDIAN);
    }

    /* SCSI disk setup. */
    dev = DEVICE(pci_create_simple(pci_bus, -1, "lsi53c895a"));
    lsi53c8xx_handle_legacy_cmdline(dev);

    /* Network setup.  e1000 is good enough, failing Tulip support.  */
    for (i = 0; i < nb_nics; i++) {
        pci_nic_init_nofail(&nd_table[i], pci_bus, "e1000", NULL);
    }

    /* Load firmware.  Given that this is not "real" firmware,
       but one explicitly written for the emulation, we might as
       well load it directly from an ELF image.  */
    firmware_filename = qemu_find_file(QEMU_FILE_TYPE_BIOS,
                                       bios_name ? bios_name :
                                       "hppa-firmware.img");
    if (firmware_filename == NULL) {
        error_report("no firmware provided");
        exit(1);
    }

    size = load_elf(firmware_filename, NULL,
                    NULL, &firmware_entry, &firmware_low, &firmware_high,
                    true, EM_PARISC, 0, 0);

    /* Unfortunately, load_elf sign-extends reading elf32.  */
    firmware_entry = (target_ureg)firmware_entry;
    firmware_low = (target_ureg)firmware_low;
    firmware_high = (target_ureg)firmware_high;

    if (size < 0) {
        error_report("could not load firmware '%s'", firmware_filename);
        exit(1);
    }
    qemu_log_mask(CPU_LOG_PAGE, "Firmware loaded at 0x%08" PRIx64
                  "-0x%08" PRIx64 ", entry at 0x%08" PRIx64 ".\n",
                  firmware_low, firmware_high, firmware_entry);
    if (firmware_low < ram_size || firmware_high >= FIRMWARE_END) {
        error_report("Firmware overlaps with memory or IO space");
        exit(1);
    }
    g_free(firmware_filename);

    rom_region = g_new(MemoryRegion, 1);
    memory_region_allocate_system_memory(rom_region, OBJECT(machine),
                                         "firmware",
                                         (FIRMWARE_END - FIRMWARE_START));
    memory_region_add_subregion(addr_space, FIRMWARE_START, rom_region);

    /* Load kernel */
    if (kernel_filename) {
        size = load_elf(kernel_filename, &cpu_hppa_to_phys,
                        NULL, &kernel_entry, &kernel_low, &kernel_high,
                        true, EM_PARISC, 0, 0);

        /* Unfortunately, load_elf sign-extends reading elf32.  */
        kernel_entry = (target_ureg) cpu_hppa_to_phys(NULL, kernel_entry);
        kernel_low = (target_ureg)kernel_low;
        kernel_high = (target_ureg)kernel_high;

        if (size < 0) {
            error_report("could not load kernel '%s'", kernel_filename);
            exit(1);
        }
        qemu_log_mask(CPU_LOG_PAGE, "Kernel loaded at 0x%08" PRIx64
                      "-0x%08" PRIx64 ", entry at 0x%08" PRIx64
                      ", size %" PRIu64 " kB\n",
                      kernel_low, kernel_high, kernel_entry, size / KiB);

        if (kernel_cmdline) {
            cpu[0]->env.gr[24] = 0x4000;
            pstrcpy_targphys("cmdline", cpu[0]->env.gr[24],
                             TARGET_PAGE_SIZE, kernel_cmdline);
        }

        if (initrd_filename) {
            ram_addr_t initrd_base;
            long initrd_size;

            initrd_size = get_image_size(initrd_filename);
            if (initrd_size < 0) {
                error_report("could not load initial ram disk '%s'",
                             initrd_filename);
                exit(1);
            }

            /* Load the initrd image high in memory.
               Mirror the algorithm used by palo:
               (1) Due to sign-extension problems and PDC,
               put the initrd no higher than 1G.
               (2) Reserve 64k for stack.  */
            initrd_base = MIN(ram_size, 1 * GiB);
            initrd_base = initrd_base - 64 * KiB;
            initrd_base = (initrd_base - initrd_size) & TARGET_PAGE_MASK;

            if (initrd_base < kernel_high) {
                error_report("kernel and initial ram disk too large!");
                exit(1);
            }

            load_image_targphys(initrd_filename, initrd_base, initrd_size);
            cpu[0]->env.gr[23] = initrd_base;
            cpu[0]->env.gr[22] = initrd_base + initrd_size;
        }
    }

    if (!kernel_entry) {
        /* When booting via firmware, tell firmware if we want interactive
         * mode (kernel_entry=1), and to boot from CD (gr[24]='d')
         * or hard disc * (gr[24]='c').
         */
        kernel_entry = boot_menu ? 1 : 0;
        cpu[0]->env.gr[24] = machine->boot_order[0];
    }

    /* We jump to the firmware entry routine and pass the
     * various parameters in registers. After firmware initialization,
     * firmware will start the Linux kernel with ramdisk and cmdline.
     */
    cpu[0]->env.gr[26] = ram_size;
    cpu[0]->env.gr[25] = kernel_entry;

    /* tell firmware how many SMP CPUs to present in inventory table */
    cpu[0]->env.gr[21] = smp_cpus;
}

static void hppa_machine_reset(void)
{
    int i;

    qemu_devices_reset();

    /* Start all CPUs at the firmware entry point.
     *  Monarch CPU will initialize firmware, secondary CPUs
     *  will enter a small idle look and wait for rendevouz. */
    for (i = 0; i < smp_cpus; i++) {
        cpu_set_pc(CPU(cpu[i]), firmware_entry);
        cpu[i]->env.gr[5] = CPU_HPA + i * 0x1000;
    }

    /* already initialized by machine_hppa_init()? */
    if (cpu[0]->env.gr[26] == ram_size) {
        return;
    }

    cpu[0]->env.gr[26] = ram_size;
    cpu[0]->env.gr[25] = 0; /* no firmware boot menu */
    cpu[0]->env.gr[24] = 'c';
    /* gr22/gr23 unused, no initrd while reboot. */
    cpu[0]->env.gr[21] = smp_cpus;
}


static void machine_hppa_machine_init(MachineClass *mc)
{
    mc->desc = "HPPA generic machine";
    mc->default_cpu_type = TYPE_HPPA_CPU;
    mc->init = machine_hppa_init;
    mc->reset = hppa_machine_reset;
    mc->block_default_type = IF_SCSI;
    mc->max_cpus = HPPA_MAX_CPUS;
    mc->default_cpus = 1;
    mc->is_default = 1;
    mc->default_ram_size = 512 * MiB;
    mc->default_boot_order = "cd";
}

DEFINE_MACHINE("hppa", machine_hppa_machine_init)
1'>1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 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 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229
/*
 * QEMU disk image utility
 *
 * Copyright (c) 2003-2008 Fabrice Bellard
 *
 * 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 "qemu-version.h"
#include "qapi/error.h"
#include "qapi-visit.h"
#include "qapi/qmp-output-visitor.h"
#include "qapi/qmp/qerror.h"
#include "qapi/qmp/qjson.h"
#include "qemu/cutils.h"
#include "qemu/config-file.h"
#include "qemu/option.h"
#include "qemu/error-report.h"
#include "qemu/log.h"
#include "qom/object_interfaces.h"
#include "sysemu/sysemu.h"
#include "sysemu/block-backend.h"
#include "block/block_int.h"
#include "block/blockjob.h"
#include "block/qapi.h"
#include "crypto/init.h"
#include "trace/control.h"
#include <getopt.h>

#define QEMU_IMG_VERSION "qemu-img version " QEMU_VERSION QEMU_PKGVERSION \
                          "\n" QEMU_COPYRIGHT "\n"

typedef struct img_cmd_t {
    const char *name;
    int (*handler)(int argc, char **argv);
} img_cmd_t;

enum {
    OPTION_OUTPUT = 256,
    OPTION_BACKING_CHAIN = 257,
    OPTION_OBJECT = 258,
    OPTION_IMAGE_OPTS = 259,
    OPTION_PATTERN = 260,
    OPTION_FLUSH_INTERVAL = 261,
    OPTION_NO_DRAIN = 262,
};

typedef enum OutputFormat {
    OFORMAT_JSON,
    OFORMAT_HUMAN,
} OutputFormat;

/* Default to cache=writeback as data integrity is not important for qemu-img */
#define BDRV_DEFAULT_CACHE "writeback"

static void format_print(void *opaque, const char *name)
{
    printf(" %s", name);
}

static void QEMU_NORETURN GCC_FMT_ATTR(1, 2) error_exit(const char *fmt, ...)
{
    va_list ap;

    error_printf("qemu-img: ");

    va_start(ap, fmt);
    error_vprintf(fmt, ap);
    va_end(ap);

    error_printf("\nTry 'qemu-img --help' for more information\n");
    exit(EXIT_FAILURE);
}

/* Please keep in synch with qemu-img.texi */
static void QEMU_NORETURN help(void)
{
    const char *help_msg =
           QEMU_IMG_VERSION
           "usage: qemu-img [standard options] command [command options]\n"
           "QEMU disk image utility\n"
           "\n"
           "    '-h', '--help'       display this help and exit\n"
           "    '-V', '--version'    output version information and exit\n"
           "    '-T', '--trace'      [[enable=]<pattern>][,events=<file>][,file=<file>]\n"
           "                         specify tracing options\n"
           "\n"
           "Command syntax:\n"
#define DEF(option, callback, arg_string)        \
           "  " arg_string "\n"
#include "qemu-img-cmds.h"
#undef DEF
#undef GEN_DOCS
           "\n"
           "Command parameters:\n"
           "  'filename' is a disk image filename\n"
           "  'objectdef' is a QEMU user creatable object definition. See the qemu(1)\n"
           "    manual page for a description of the object properties. The most common\n"
           "    object type is a 'secret', which is used to supply passwords and/or\n"
           "    encryption keys.\n"
           "  'fmt' is the disk image format. It is guessed automatically in most cases\n"
           "  'cache' is the cache mode used to write the output disk image, the valid\n"
           "    options are: 'none', 'writeback' (default, except for convert), 'writethrough',\n"
           "    'directsync' and 'unsafe' (default for convert)\n"
           "  'src_cache' is the cache mode used to read input disk images, the valid\n"
           "    options are the same as for the 'cache' option\n"
           "  'size' is the disk image size in bytes. Optional suffixes\n"
           "    'k' or 'K' (kilobyte, 1024), 'M' (megabyte, 1024k), 'G' (gigabyte, 1024M),\n"
           "    'T' (terabyte, 1024G), 'P' (petabyte, 1024T) and 'E' (exabyte, 1024P)  are\n"
           "    supported. 'b' is ignored.\n"
           "  'output_filename' is the destination disk image filename\n"
           "  'output_fmt' is the destination format\n"
           "  'options' is a comma separated list of format specific options in a\n"
           "    name=value format. Use -o ? for an overview of the options supported by the\n"
           "    used format\n"
           "  'snapshot_param' is param used for internal snapshot, format\n"
           "    is 'snapshot.id=[ID],snapshot.name=[NAME]', or\n"
           "    '[ID_OR_NAME]'\n"
           "  'snapshot_id_or_name' is deprecated, use 'snapshot_param'\n"
           "    instead\n"
           "  '-c' indicates that target image must be compressed (qcow format only)\n"
           "  '-u' enables unsafe rebasing. It is assumed that old and new backing file\n"
           "       match exactly. The image doesn't need a working backing file before\n"
           "       rebasing in this case (useful for renaming the backing file)\n"
           "  '-h' with or without a command shows this help and lists the supported formats\n"
           "  '-p' show progress of command (only certain commands)\n"
           "  '-q' use Quiet mode - do not print any output (except errors)\n"
           "  '-S' indicates the consecutive number of bytes (defaults to 4k) that must\n"
           "       contain only zeros for qemu-img to create a sparse image during\n"
           "       conversion. If the number of bytes is 0, the source will not be scanned for\n"
           "       unallocated or zero sectors, and the destination image will always be\n"
           "       fully allocated\n"
           "  '--output' takes the format in which the output must be done (human or json)\n"
           "  '-n' skips the target volume creation (useful if the volume is created\n"
           "       prior to running qemu-img)\n"
           "\n"
           "Parameters to check subcommand:\n"
           "  '-r' tries to repair any inconsistencies that are found during the check.\n"
           "       '-r leaks' repairs only cluster leaks, whereas '-r all' fixes all\n"
           "       kinds of errors, with a higher risk of choosing the wrong fix or\n"
           "       hiding corruption that has already occurred.\n"
           "\n"
           "Parameters to snapshot subcommand:\n"
           "  'snapshot' is the name of the snapshot to create, apply or delete\n"
           "  '-a' applies a snapshot (revert disk to saved state)\n"
           "  '-c' creates a snapshot\n"
           "  '-d' deletes a snapshot\n"
           "  '-l' lists all snapshots in the given image\n"
           "\n"
           "Parameters to compare subcommand:\n"
           "  '-f' first image format\n"
           "  '-F' second image format\n"
           "  '-s' run in Strict mode - fail on different image size or sector allocation\n"
           "\n"
           "Parameters to dd subcommand:\n"
           "  'bs=BYTES' read and write up to BYTES bytes at a time "
           "(default: 512)\n"
           "  'count=N' copy only N input blocks\n"
           "  'if=FILE' read from FILE\n"
           "  'of=FILE' write to FILE\n"
           "  'skip=N' skip N bs-sized blocks at the start of input\n";

    printf("%s\nSupported formats:", help_msg);
    bdrv_iterate_format(format_print, NULL);
    printf("\n");
    exit(EXIT_SUCCESS);
}

static QemuOptsList qemu_object_opts = {
    .name = "object",
    .implied_opt_name = "qom-type",
    .head = QTAILQ_HEAD_INITIALIZER(qemu_object_opts.head),
    .desc = {
        { }
    },
};

static QemuOptsList qemu_source_opts = {
    .name = "source",
    .implied_opt_name = "file",
    .head = QTAILQ_HEAD_INITIALIZER(qemu_source_opts.head),
    .desc = {
        { }
    },
};

static int GCC_FMT_ATTR(2, 3) qprintf(bool quiet, const char *fmt, ...)
{
    int ret = 0;
    if (!quiet) {
        va_list args;
        va_start(args, fmt);
        ret = vprintf(fmt, args);
        va_end(args);
    }
    return ret;
}


static int print_block_option_help(const char *filename, const char *fmt)
{
    BlockDriver *drv, *proto_drv;
    QemuOptsList *create_opts = NULL;
    Error *local_err = NULL;

    /* Find driver and parse its options */
    drv = bdrv_find_format(fmt);
    if (!drv) {
        error_report("Unknown file format '%s'", fmt);
        return 1;
    }

    create_opts = qemu_opts_append(create_opts, drv->create_opts);
    if (filename) {
        proto_drv = bdrv_find_protocol(filename, true, &local_err);
        if (!proto_drv) {
            error_report_err(local_err);
            qemu_opts_free(create_opts);
            return 1;
        }
        create_opts = qemu_opts_append(create_opts, proto_drv->create_opts);
    }

    qemu_opts_print_help(create_opts);
    qemu_opts_free(create_opts);
    return 0;
}


static int img_open_password(BlockBackend *blk, const char *filename,
                             int flags, bool quiet)
{
    BlockDriverState *bs;
    char password[256];

    bs = blk_bs(blk);
    if (bdrv_is_encrypted(bs) && bdrv_key_required(bs) &&
        !(flags & BDRV_O_NO_IO)) {
        qprintf(quiet, "Disk image '%s' is encrypted.\n", filename);
        if (qemu_read_password(password, sizeof(password)) < 0) {
            error_report("No password given");
            return -1;
        }
        if (bdrv_set_key(bs, password) < 0) {
            error_report("invalid password");
            return -1;
        }
    }
    return 0;
}


static BlockBackend *img_open_opts(const char *optstr,
                                   QemuOpts *opts, int flags, bool writethrough,
                                   bool quiet)
{
    QDict *options;
    Error *local_err = NULL;
    BlockBackend *blk;
    options = qemu_opts_to_qdict(opts, NULL);
    blk = blk_new_open(NULL, NULL, options, flags, &local_err);
    if (!blk) {
        error_reportf_err(local_err, "Could not open '%s': ", optstr);
        return NULL;
    }
    blk_set_enable_write_cache(blk, !writethrough);

    if (img_open_password(blk, optstr, flags, quiet) < 0) {
        blk_unref(blk);
        return NULL;
    }
    return blk;
}

static BlockBackend *img_open_file(const char *filename,
                                   const char *fmt, int flags,
                                   bool writethrough, bool quiet)
{
    BlockBackend *blk;
    Error *local_err = NULL;
    QDict *options = NULL;

    if (fmt) {
        options = qdict_new();
        qdict_put(options, "driver", qstring_from_str(fmt));
    }

    blk = blk_new_open(filename, NULL, options, flags, &local_err);
    if (!blk) {
        error_reportf_err(local_err, "Could not open '%s': ", filename);
        return NULL;
    }
    blk_set_enable_write_cache(blk, !writethrough);

    if (img_open_password(blk, filename, flags, quiet) < 0) {
        blk_unref(blk);
        return NULL;
    }
    return blk;
}


static BlockBackend *img_open(bool image_opts,
                              const char *filename,
                              const char *fmt, int flags, bool writethrough,
                              bool quiet)
{
    BlockBackend *blk;
    if (image_opts) {
        QemuOpts *opts;
        if (fmt) {
            error_report("--image-opts and --format are mutually exclusive");
            return NULL;
        }
        opts = qemu_opts_parse_noisily(qemu_find_opts("source"),
                                       filename, true);
        if (!opts) {
            return NULL;
        }
        blk = img_open_opts(filename, opts, flags, writethrough, quiet);
    } else {
        blk = img_open_file(filename, fmt, flags, writethrough, quiet);
    }
    return blk;
}


static int add_old_style_options(const char *fmt, QemuOpts *opts,
                                 const char *base_filename,
                                 const char *base_fmt)
{
    Error *err = NULL;

    if (base_filename) {
        qemu_opt_set(opts, BLOCK_OPT_BACKING_FILE, base_filename, &err);
        if (err) {
            error_report("Backing file not supported for file format '%s'",
                         fmt);
            error_free(err);
            return -1;
        }
    }
    if (base_fmt) {
        qemu_opt_set(opts, BLOCK_OPT_BACKING_FMT, base_fmt, &err);
        if (err) {
            error_report("Backing file format not supported for file "
                         "format '%s'", fmt);
            error_free(err);
            return -1;
        }
    }
    return 0;
}

static int img_create(int argc, char **argv)
{
    int c;
    uint64_t img_size = -1;
    const char *fmt = "raw";
    const char *base_fmt = NULL;
    const char *filename;
    const char *base_filename = NULL;
    char *options = NULL;
    Error *local_err = NULL;
    bool quiet = false;

    for(;;) {
        static const struct option long_options[] = {
            {"help", no_argument, 0, 'h'},
            {"object", required_argument, 0, OPTION_OBJECT},
            {0, 0, 0, 0}
        };
        c = getopt_long(argc, argv, "F:b:f:he6o:q",
                        long_options, NULL);
        if (c == -1) {
            break;
        }
        switch(c) {
        case '?':
        case 'h':
            help();
            break;
        case 'F':
            base_fmt = optarg;
            break;
        case 'b':
            base_filename = optarg;
            break;
        case 'f':
            fmt = optarg;
            break;
        case 'e':
            error_report("option -e is deprecated, please use \'-o "
                  "encryption\' instead!");
            goto fail;
        case '6':
            error_report("option -6 is deprecated, please use \'-o "
                  "compat6\' instead!");
            goto fail;
        case 'o':
            if (!is_valid_option_list(optarg)) {
                error_report("Invalid option list: %s", optarg);
                goto fail;
            }
            if (!options) {
                options = g_strdup(optarg);
            } else {
                char *old_options = options;
                options = g_strdup_printf("%s,%s", options, optarg);
                g_free(old_options);
            }
            break;
        case 'q':
            quiet = true;
            break;
        case OPTION_OBJECT: {
            QemuOpts *opts;
            opts = qemu_opts_parse_noisily(&qemu_object_opts,
                                           optarg, true);
            if (!opts) {
                goto fail;
            }
        }   break;
        }
    }

    /* Get the filename */
    filename = (optind < argc) ? argv[optind] : NULL;
    if (options && has_help_option(options)) {
        g_free(options);
        return print_block_option_help(filename, fmt);
    }

    if (optind >= argc) {
        error_exit("Expecting image file name");
    }
    optind++;

    if (qemu_opts_foreach(&qemu_object_opts,
                          user_creatable_add_opts_foreach,
                          NULL, NULL)) {
        goto fail;
    }

    /* Get image size, if specified */
    if (optind < argc) {
        int64_t sval;
        char *end;
        sval = qemu_strtosz_suffix(argv[optind++], &end,
                                   QEMU_STRTOSZ_DEFSUFFIX_B);
        if (sval < 0 || *end) {
            if (sval == -ERANGE) {
                error_report("Image size must be less than 8 EiB!");
            } else {
                error_report("Invalid image size specified! You may use k, M, "
                      "G, T, P or E suffixes for ");
                error_report("kilobytes, megabytes, gigabytes, terabytes, "
                             "petabytes and exabytes.");
            }
            goto fail;
        }
        img_size = (uint64_t)sval;
    }
    if (optind != argc) {
        error_exit("Unexpected argument: %s", argv[optind]);
    }

    bdrv_img_create(filename, fmt, base_filename, base_fmt,
                    options, img_size, 0, &local_err, quiet);
    if (local_err) {
        error_reportf_err(local_err, "%s: ", filename);
        goto fail;
    }

    g_free(options);
    return 0;

fail:
    g_free(options);
    return 1;
}

static void dump_json_image_check(ImageCheck *check, bool quiet)
{
    QString *str;
    QObject *obj;
    Visitor *v = qmp_output_visitor_new(&obj);

    visit_type_ImageCheck(v, NULL, &check, &error_abort);
    visit_complete(v, &obj);
    str = qobject_to_json_pretty(obj);
    assert(str != NULL);
    qprintf(quiet, "%s\n", qstring_get_str(str));
    qobject_decref(obj);
    visit_free(v);
    QDECREF(str);
}

static void dump_human_image_check(ImageCheck *check, bool quiet)
{
    if (!(check->corruptions || check->leaks || check->check_errors)) {
        qprintf(quiet, "No errors were found on the image.\n");
    } else {
        if (check->corruptions) {
            qprintf(quiet, "\n%" PRId64 " errors were found on the image.\n"
                    "Data may be corrupted, or further writes to the image "
                    "may corrupt it.\n",
                    check->corruptions);
        }

        if (check->leaks) {
            qprintf(quiet,
                    "\n%" PRId64 " leaked clusters were found on the image.\n"
                    "This means waste of disk space, but no harm to data.\n",
                    check->leaks);
        }

        if (check->check_errors) {
            qprintf(quiet,
                    "\n%" PRId64
                    " internal errors have occurred during the check.\n",
                    check->check_errors);
        }
    }

    if (check->total_clusters != 0 && check->allocated_clusters != 0) {
        qprintf(quiet, "%" PRId64 "/%" PRId64 " = %0.2f%% allocated, "
                "%0.2f%% fragmented, %0.2f%% compressed clusters\n",
                check->allocated_clusters, check->total_clusters,
                check->allocated_clusters * 100.0 / check->total_clusters,
                check->fragmented_clusters * 100.0 / check->allocated_clusters,
                check->compressed_clusters * 100.0 /
                check->allocated_clusters);
    }

    if (check->image_end_offset) {
        qprintf(quiet,
                "Image end offset: %" PRId64 "\n", check->image_end_offset);
    }
}

static int collect_image_check(BlockDriverState *bs,
                   ImageCheck *check,
                   const char *filename,
                   const char *fmt,
                   int fix)
{
    int ret;
    BdrvCheckResult result;

    ret = bdrv_check(bs, &result, fix);
    if (ret < 0) {
        return ret;
    }

    check->filename                 = g_strdup(filename);
    check->format                   = g_strdup(bdrv_get_format_name(bs));
    check->check_errors             = result.check_errors;
    check->corruptions              = result.corruptions;
    check->has_corruptions          = result.corruptions != 0;
    check->leaks                    = result.leaks;
    check->has_leaks                = result.leaks != 0;
    check->corruptions_fixed        = result.corruptions_fixed;
    check->has_corruptions_fixed    = result.corruptions != 0;
    check->leaks_fixed              = result.leaks_fixed;
    check->has_leaks_fixed          = result.leaks != 0;
    check->image_end_offset         = result.image_end_offset;
    check->has_image_end_offset     = result.image_end_offset != 0;
    check->total_clusters           = result.bfi.total_clusters;
    check->has_total_clusters       = result.bfi.total_clusters != 0;
    check->allocated_clusters       = result.bfi.allocated_clusters;
    check->has_allocated_clusters   = result.bfi.allocated_clusters != 0;
    check->fragmented_clusters      = result.bfi.fragmented_clusters;
    check->has_fragmented_clusters  = result.bfi.fragmented_clusters != 0;
    check->compressed_clusters      = result.bfi.compressed_clusters;
    check->has_compressed_clusters  = result.bfi.compressed_clusters != 0;

    return 0;
}

/*
 * Checks an image for consistency. Exit codes:
 *
 *  0 - Check completed, image is good
 *  1 - Check not completed because of internal errors
 *  2 - Check completed, image is corrupted
 *  3 - Check completed, image has leaked clusters, but is good otherwise
 * 63 - Checks are not supported by the image format
 */
static int img_check(int argc, char **argv)
{
    int c, ret;
    OutputFormat output_format = OFORMAT_HUMAN;
    const char *filename, *fmt, *output, *cache;
    BlockBackend *blk;
    BlockDriverState *bs;
    int fix = 0;
    int flags = BDRV_O_CHECK;
    bool writethrough;
    ImageCheck *check;
    bool quiet = false;
    bool image_opts = false;

    fmt = NULL;
    output = NULL;
    cache = BDRV_DEFAULT_CACHE;

    for(;;) {
        int option_index = 0;
        static const struct option long_options[] = {
            {"help", no_argument, 0, 'h'},
            {"format", required_argument, 0, 'f'},
            {"repair", required_argument, 0, 'r'},
            {"output", required_argument, 0, OPTION_OUTPUT},
            {"object", required_argument, 0, OPTION_OBJECT},
            {"image-opts", no_argument, 0, OPTION_IMAGE_OPTS},
            {0, 0, 0, 0}
        };
        c = getopt_long(argc, argv, "hf:r:T:q",
                        long_options, &option_index);
        if (c == -1) {
            break;
        }
        switch(c) {
        case '?':
        case 'h':
            help();
            break;
        case 'f':
            fmt = optarg;
            break;
        case 'r':
            flags |= BDRV_O_RDWR;

            if (!strcmp(optarg, "leaks")) {
                fix = BDRV_FIX_LEAKS;
            } else if (!strcmp(optarg, "all")) {
                fix = BDRV_FIX_LEAKS | BDRV_FIX_ERRORS;
            } else {
                error_exit("Unknown option value for -r "
                           "(expecting 'leaks' or 'all'): %s", optarg);
            }
            break;
        case OPTION_OUTPUT:
            output = optarg;
            break;
        case 'T':
            cache = optarg;
            break;
        case 'q':
            quiet = true;
            break;
        case OPTION_OBJECT: {
            QemuOpts *opts;
            opts = qemu_opts_parse_noisily(&qemu_object_opts,
                                           optarg, true);
            if (!opts) {
                return 1;
            }
        }   break;
        case OPTION_IMAGE_OPTS:
            image_opts = true;
            break;
        }
    }
    if (optind != argc - 1) {
        error_exit("Expecting one image file name");
    }
    filename = argv[optind++];

    if (output && !strcmp(output, "json")) {
        output_format = OFORMAT_JSON;
    } else if (output && !strcmp(output, "human")) {
        output_format = OFORMAT_HUMAN;
    } else if (output) {
        error_report("--output must be used with human or json as argument.");
        return 1;
    }

    if (qemu_opts_foreach(&qemu_object_opts,
                          user_creatable_add_opts_foreach,
                          NULL, NULL)) {
        return 1;
    }

    ret = bdrv_parse_cache_mode(cache, &flags, &writethrough);
    if (ret < 0) {
        error_report("Invalid source cache option: %s", cache);
        return 1;
    }

    blk = img_open(image_opts, filename, fmt, flags, writethrough, quiet);
    if (!blk) {
        return 1;
    }
    bs = blk_bs(blk);

    check = g_new0(ImageCheck, 1);
    ret = collect_image_check(bs, check, filename, fmt, fix);

    if (ret == -ENOTSUP) {
        error_report("This image format does not support checks");
        ret = 63;
        goto fail;
    }

    if (check->corruptions_fixed || check->leaks_fixed) {
        int corruptions_fixed, leaks_fixed;

        leaks_fixed         = check->leaks_fixed;
        corruptions_fixed   = check->corruptions_fixed;

        if (output_format == OFORMAT_HUMAN) {
            qprintf(quiet,
                    "The following inconsistencies were found and repaired:\n\n"
                    "    %" PRId64 " leaked clusters\n"
                    "    %" PRId64 " corruptions\n\n"
                    "Double checking the fixed image now...\n",
                    check->leaks_fixed,
                    check->corruptions_fixed);
        }

        ret = collect_image_check(bs, check, filename, fmt, 0);

        check->leaks_fixed          = leaks_fixed;
        check->corruptions_fixed    = corruptions_fixed;
    }

    if (!ret) {
        switch (output_format) {
        case OFORMAT_HUMAN:
            dump_human_image_check(check, quiet);
            break;
        case OFORMAT_JSON:
            dump_json_image_check(check, quiet);
            break;
        }
    }

    if (ret || check->check_errors) {
        if (ret) {
            error_report("Check failed: %s", strerror(-ret));
        } else {
            error_report("Check failed");
        }
        ret = 1;
        goto fail;
    }

    if (check->corruptions) {
        ret = 2;
    } else if (check->leaks) {
        ret = 3;
    } else {
        ret = 0;
    }

fail:
    qapi_free_ImageCheck(check);
    blk_unref(blk);
    return ret;
}

typedef struct CommonBlockJobCBInfo {
    BlockDriverState *bs;
    Error **errp;
} CommonBlockJobCBInfo;

static void common_block_job_cb(void *opaque, int ret)
{
    CommonBlockJobCBInfo *cbi = opaque;

    if (ret < 0) {
        error_setg_errno(cbi->errp, -ret, "Block job failed");
    }
}

static void run_block_job(BlockJob *job, Error **errp)
{
    AioContext *aio_context = blk_get_aio_context(job->blk);

    do {
        aio_poll(aio_context, true);
        qemu_progress_print(job->len ?
                            ((float)job->offset / job->len * 100.f) : 0.0f, 0);
    } while (!job->ready);

    block_job_complete_sync(job, errp);

    /* A block job may finish instantaneously without publishing any progress,
     * so just signal completion here */
    qemu_progress_print(100.f, 0);
}

static int img_commit(int argc, char **argv)
{
    int c, ret, flags;
    const char *filename, *fmt, *cache, *base;
    BlockBackend *blk;
    BlockDriverState *bs, *base_bs;
    bool progress = false, quiet = false, drop = false;
    bool writethrough;
    Error *local_err = NULL;
    CommonBlockJobCBInfo cbi;
    bool image_opts = false;

    fmt = NULL;
    cache = BDRV_DEFAULT_CACHE;
    base = NULL;
    for(;;) {
        static const struct option long_options[] = {
            {"help", no_argument, 0, 'h'},
            {"object", required_argument, 0, OPTION_OBJECT},
            {"image-opts", no_argument, 0, OPTION_IMAGE_OPTS},
            {0, 0, 0, 0}
        };
        c = getopt_long(argc, argv, "f:ht:b:dpq",
                        long_options, NULL);
        if (c == -1) {
            break;
        }
        switch(c) {
        case '?':
        case 'h':
            help();
            break;
        case 'f':
            fmt = optarg;
            break;
        case 't':
            cache = optarg;
            break;
        case 'b':
            base = optarg;
            /* -b implies -d */
            drop = true;
            break;
        case 'd':
            drop = true;
            break;
        case 'p':
            progress = true;
            break;
        case 'q':
            quiet = true;
            break;
        case OPTION_OBJECT: {
            QemuOpts *opts;
            opts = qemu_opts_parse_noisily(&qemu_object_opts,
                                           optarg, true);
            if (!opts) {
                return 1;
            }
        }   break;
        case OPTION_IMAGE_OPTS:
            image_opts = true;
            break;
        }
    }

    /* Progress is not shown in Quiet mode */
    if (quiet) {
        progress = false;
    }

    if (optind != argc - 1) {
        error_exit("Expecting one image file name");
    }
    filename = argv[optind++];

    if (qemu_opts_foreach(&qemu_object_opts,
                          user_creatable_add_opts_foreach,
                          NULL, NULL)) {
        return 1;
    }

    flags = BDRV_O_RDWR | BDRV_O_UNMAP;
    ret = bdrv_parse_cache_mode(cache, &flags, &writethrough);
    if (ret < 0) {
        error_report("Invalid cache option: %s", cache);
        return 1;
    }

    blk = img_open(image_opts, filename, fmt, flags, writethrough, quiet);
    if (!blk) {
        return 1;
    }
    bs = blk_bs(blk);

    qemu_progress_init(progress, 1.f);
    qemu_progress_print(0.f, 100);

    if (base) {
        base_bs = bdrv_find_backing_image(bs, base);
        if (!base_bs) {
            error_setg(&local_err, QERR_BASE_NOT_FOUND, base);
            goto done;
        }
    } else {
        /* This is different from QMP, which by default uses the deepest file in
         * the backing chain (i.e., the very base); however, the traditional
         * behavior of qemu-img commit is using the immediate backing file. */
        base_bs = backing_bs(bs);
        if (!base_bs) {
            error_setg(&local_err, "Image does not have a backing file");
            goto done;
        }
    }

    cbi = (CommonBlockJobCBInfo){
        .errp = &local_err,
        .bs   = bs,
    };

    commit_active_start("commit", bs, base_bs, 0, BLOCKDEV_ON_ERROR_REPORT,
                        common_block_job_cb, &cbi, &local_err, false);
    if (local_err) {
        goto done;
    }

    /* When the block job completes, the BlockBackend reference will point to
     * the old backing file. In order to avoid that the top image is already
     * deleted, so we can still empty it afterwards, increment the reference
     * counter here preemptively. */
    if (!drop) {
        bdrv_ref(bs);
    }

    run_block_job(bs->job, &local_err);
    if (local_err) {
        goto unref_backing;
    }

    if (!drop && bs->drv->bdrv_make_empty) {
        ret = bs->drv->bdrv_make_empty(bs);
        if (ret) {
            error_setg_errno(&local_err, -ret, "Could not empty %s",
                             filename);
            goto unref_backing;
        }
    }

unref_backing:
    if (!drop) {
        bdrv_unref(bs);
    }

done:
    qemu_progress_end();

    blk_unref(blk);

    if (local_err) {
        error_report_err(local_err);
        return 1;
    }

    qprintf(quiet, "Image committed.\n");
    return 0;
}

/*
 * Returns true iff the first sector pointed to by 'buf' contains at least
 * a non-NUL byte.
 *
 * 'pnum' is set to the number of sectors (including and immediately following
 * the first one) that are known to be in the same allocated/unallocated state.
 */
static int is_allocated_sectors(const uint8_t *buf, int n, int *pnum)
{
    bool is_zero;
    int i;

    if (n <= 0) {
        *pnum = 0;
        return 0;
    }
    is_zero = buffer_is_zero(buf, 512);
    for(i = 1; i < n; i++) {
        buf += 512;
        if (is_zero != buffer_is_zero(buf, 512)) {
            break;
        }
    }
    *pnum = i;
    return !is_zero;
}

/*
 * Like is_allocated_sectors, but if the buffer starts with a used sector,
 * up to 'min' consecutive sectors containing zeros are ignored. This avoids
 * breaking up write requests for only small sparse areas.
 */
static int is_allocated_sectors_min(const uint8_t *buf, int n, int *pnum,
    int min)
{
    int ret;
    int num_checked, num_used;

    if (n < min) {
        min = n;
    }

    ret = is_allocated_sectors(buf, n, pnum);
    if (!ret) {
        return ret;
    }

    num_used = *pnum;
    buf += BDRV_SECTOR_SIZE * *pnum;
    n -= *pnum;
    num_checked = num_used;

    while (n > 0) {
        ret = is_allocated_sectors(buf, n, pnum);

        buf += BDRV_SECTOR_SIZE * *pnum;
        n -= *pnum;
        num_checked += *pnum;
        if (ret) {
            num_used = num_checked;
        } else if (*pnum >= min) {
            break;
        }
    }

    *pnum = num_used;
    return 1;
}

/*
 * Compares two buffers sector by sector. Returns 0 if the first sector of both
 * buffers matches, non-zero otherwise.
 *
 * pnum is set to the number of sectors (including and immediately following
 * the first one) that are known to have the same comparison result
 */
static int compare_sectors(const uint8_t *buf1, const uint8_t *buf2, int n,
    int *pnum)
{
    bool res;
    int i;

    if (n <= 0) {
        *pnum = 0;
        return 0;
    }

    res = !!memcmp(buf1, buf2, 512);
    for(i = 1; i < n; i++) {
        buf1 += 512;
        buf2 += 512;

        if (!!memcmp(buf1, buf2, 512) != res) {
            break;
        }
    }

    *pnum = i;
    return res;
}

#define IO_BUF_SIZE (2 * 1024 * 1024)

static int64_t sectors_to_bytes(int64_t sectors)
{
    return sectors << BDRV_SECTOR_BITS;
}

static int64_t sectors_to_process(int64_t total, int64_t from)
{
    return MIN(total - from, IO_BUF_SIZE >> BDRV_SECTOR_BITS);
}

/*
 * Check if passed sectors are empty (not allocated or contain only 0 bytes)
 *
 * Returns 0 in case sectors are filled with 0, 1 if sectors contain non-zero
 * data and negative value on error.
 *
 * @param blk:  BlockBackend for the image
 * @param sect_num: Number of first sector to check
 * @param sect_count: Number of sectors to check
 * @param filename: Name of disk file we are checking (logging purpose)
 * @param buffer: Allocated buffer for storing read data
 * @param quiet: Flag for quiet mode
 */
static int check_empty_sectors(BlockBackend *blk, int64_t sect_num,
                               int sect_count, const char *filename,
                               uint8_t *buffer, bool quiet)
{
    int pnum, ret = 0;
    ret = blk_pread(blk, sect_num << BDRV_SECTOR_BITS, buffer,
                    sect_count << BDRV_SECTOR_BITS);
    if (ret < 0) {
        error_report("Error while reading offset %" PRId64 " of %s: %s",
                     sectors_to_bytes(sect_num), filename, strerror(-ret));
        return ret;
    }
    ret = is_allocated_sectors(buffer, sect_count, &pnum);
    if (ret || pnum != sect_count) {
        qprintf(quiet, "Content mismatch at offset %" PRId64 "!\n",
                sectors_to_bytes(ret ? sect_num : sect_num + pnum));
        return 1;
    }

    return 0;
}

/*
 * Compares two images. Exit codes:
 *
 * 0 - Images are identical
 * 1 - Images differ
 * >1 - Error occurred
 */
static int img_compare(int argc, char **argv)
{
    const char *fmt1 = NULL, *fmt2 = NULL, *cache, *filename1, *filename2;
    BlockBackend *blk1, *blk2;
    BlockDriverState *bs1, *bs2;
    int64_t total_sectors1, total_sectors2;
    uint8_t *buf1 = NULL, *buf2 = NULL;
    int pnum1, pnum2;
    int allocated1, allocated2;
    int ret = 0; /* return value - 0 Ident, 1 Different, >1 Error */
    bool progress = false, quiet = false, strict = false;
    int flags;
    bool writethrough;
    int64_t total_sectors;
    int64_t sector_num = 0;
    int64_t nb_sectors;
    int c, pnum;
    uint64_t progress_base;
    bool image_opts = false;

    cache = BDRV_DEFAULT_CACHE;
    for (;;) {
        static const struct option long_options[] = {
            {"help", no_argument, 0, 'h'},
            {"object", required_argument, 0, OPTION_OBJECT},
            {"image-opts", no_argument, 0, OPTION_IMAGE_OPTS},
            {0, 0, 0, 0}
        };
        c = getopt_long(argc, argv, "hf:F:T:pqs",
                        long_options, NULL);
        if (c == -1) {
            break;
        }
        switch (c) {
        case '?':
        case 'h':
            help();
            break;
        case 'f':
            fmt1 = optarg;
            break;
        case 'F':
            fmt2 = optarg;
            break;
        case 'T':
            cache = optarg;
            break;
        case 'p':
            progress = true;
            break;
        case 'q':
            quiet = true;
            break;
        case 's':
            strict = true;
            break;
        case OPTION_OBJECT: {
            QemuOpts *opts;
            opts = qemu_opts_parse_noisily(&qemu_object_opts,
                                           optarg, true);
            if (!opts) {
                ret = 2;
                goto out4;
            }
        }   break;
        case OPTION_IMAGE_OPTS:
            image_opts = true;
            break;
        }
    }

    /* Progress is not shown in Quiet mode */
    if (quiet) {
        progress = false;
    }


    if (optind != argc - 2) {
        error_exit("Expecting two image file names");
    }
    filename1 = argv[optind++];
    filename2 = argv[optind++];

    if (qemu_opts_foreach(&qemu_object_opts,
                          user_creatable_add_opts_foreach,
                          NULL, NULL)) {
        ret = 2;
        goto out4;
    }

    /* Initialize before goto out */
    qemu_progress_init(progress, 2.0);

    flags = 0;
    ret = bdrv_parse_cache_mode(cache, &flags, &writethrough);
    if (ret < 0) {
        error_report("Invalid source cache option: %s", cache);
        ret = 2;
        goto out3;
    }

    blk1 = img_open(image_opts, filename1, fmt1, flags, writethrough, quiet);
    if (!blk1) {
        ret = 2;
        goto out3;
    }

    blk2 = img_open(image_opts, filename2, fmt2, flags, writethrough, quiet);
    if (!blk2) {
        ret = 2;
        goto out2;
    }
    bs1 = blk_bs(blk1);
    bs2 = blk_bs(blk2);

    buf1 = blk_blockalign(blk1, IO_BUF_SIZE);
    buf2 = blk_blockalign(blk2, IO_BUF_SIZE);
    total_sectors1 = blk_nb_sectors(blk1);
    if (total_sectors1 < 0) {
        error_report("Can't get size of %s: %s",
                     filename1, strerror(-total_sectors1));
        ret = 4;
        goto out;
    }
    total_sectors2 = blk_nb_sectors(blk2);
    if (total_sectors2 < 0) {
        error_report("Can't get size of %s: %s",
                     filename2, strerror(-total_sectors2));
        ret = 4;
        goto out;
    }
    total_sectors = MIN(total_sectors1, total_sectors2);
    progress_base = MAX(total_sectors1, total_sectors2);

    qemu_progress_print(0, 100);

    if (strict && total_sectors1 != total_sectors2) {
        ret = 1;
        qprintf(quiet, "Strict mode: Image size mismatch!\n");
        goto out;
    }

    for (;;) {
        int64_t status1, status2;
        BlockDriverState *file;

        nb_sectors = sectors_to_process(total_sectors, sector_num);
        if (nb_sectors <= 0) {
            break;
        }
        status1 = bdrv_get_block_status_above(bs1, NULL, sector_num,
                                              total_sectors1 - sector_num,
                                              &pnum1, &file);
        if (status1 < 0) {
            ret = 3;
            error_report("Sector allocation test failed for %s", filename1);
            goto out;
        }
        allocated1 = status1 & BDRV_BLOCK_ALLOCATED;

        status2 = bdrv_get_block_status_above(bs2, NULL, sector_num,
                                              total_sectors2 - sector_num,
                                              &pnum2, &file);
        if (status2 < 0) {
            ret = 3;
            error_report("Sector allocation test failed for %s", filename2);
            goto out;
        }
        allocated2 = status2 & BDRV_BLOCK_ALLOCATED;
        if (pnum1) {
            nb_sectors = MIN(nb_sectors, pnum1);
        }
        if (pnum2) {
            nb_sectors = MIN(nb_sectors, pnum2);
        }

        if (strict) {
            if ((status1 & ~BDRV_BLOCK_OFFSET_MASK) !=
                (status2 & ~BDRV_BLOCK_OFFSET_MASK)) {
                ret = 1;
                qprintf(quiet, "Strict mode: Offset %" PRId64
                        " block status mismatch!\n",
                        sectors_to_bytes(sector_num));
                goto out;
            }
        }
        if ((status1 & BDRV_BLOCK_ZERO) && (status2 & BDRV_BLOCK_ZERO)) {
            nb_sectors = MIN(pnum1, pnum2);
        } else if (allocated1 == allocated2) {
            if (allocated1) {
                ret = blk_pread(blk1, sector_num << BDRV_SECTOR_BITS, buf1,
                                nb_sectors << BDRV_SECTOR_BITS);
                if (ret < 0) {
                    error_report("Error while reading offset %" PRId64 " of %s:"
                                 " %s", sectors_to_bytes(sector_num), filename1,
                                 strerror(-ret));
                    ret = 4;
                    goto out;
                }
                ret = blk_pread(blk2, sector_num << BDRV_SECTOR_BITS, buf2,
                                nb_sectors << BDRV_SECTOR_BITS);
                if (ret < 0) {
                    error_report("Error while reading offset %" PRId64
                                 " of %s: %s", sectors_to_bytes(sector_num),
                                 filename2, strerror(-ret));
                    ret = 4;
                    goto out;
                }
                ret = compare_sectors(buf1, buf2, nb_sectors, &pnum);
                if (ret || pnum != nb_sectors) {
                    qprintf(quiet, "Content mismatch at offset %" PRId64 "!\n",
                            sectors_to_bytes(
                                ret ? sector_num : sector_num + pnum));
                    ret = 1;
                    goto out;
                }
            }
        } else {

            if (allocated1) {
                ret = check_empty_sectors(blk1, sector_num, nb_sectors,
                                          filename1, buf1, quiet);
            } else {
                ret = check_empty_sectors(blk2, sector_num, nb_sectors,
                                          filename2, buf1, quiet);
            }
            if (ret) {
                if (ret < 0) {
                    error_report("Error while reading offset %" PRId64 ": %s",
                                 sectors_to_bytes(sector_num), strerror(-ret));
                    ret = 4;
                }
                goto out;
            }
        }
        sector_num += nb_sectors;
        qemu_progress_print(((float) nb_sectors / progress_base)*100, 100);
    }

    if (total_sectors1 != total_sectors2) {
        BlockBackend *blk_over;
        int64_t total_sectors_over;
        const char *filename_over;

        qprintf(quiet, "Warning: Image size mismatch!\n");
        if (total_sectors1 > total_sectors2) {
            total_sectors_over = total_sectors1;
            blk_over = blk1;
            filename_over = filename1;
        } else {
            total_sectors_over = total_sectors2;
            blk_over = blk2;
            filename_over = filename2;
        }

        for (;;) {
            nb_sectors = sectors_to_process(total_sectors_over, sector_num);
            if (nb_sectors <= 0) {
                break;
            }
            ret = bdrv_is_allocated_above(blk_bs(blk_over), NULL, sector_num,
                                          nb_sectors, &pnum);
            if (ret < 0) {
                ret = 3;
                error_report("Sector allocation test failed for %s",
                             filename_over);
                goto out;

            }
            nb_sectors = pnum;
            if (ret) {
                ret = check_empty_sectors(blk_over, sector_num, nb_sectors,
                                          filename_over, buf1, quiet);
                if (ret) {
                    if (ret < 0) {
                        error_report("Error while reading offset %" PRId64
                                     " of %s: %s", sectors_to_bytes(sector_num),
                                     filename_over, strerror(-ret));
                        ret = 4;
                    }
                    goto out;
                }
            }
            sector_num += nb_sectors;
            qemu_progress_print(((float) nb_sectors / progress_base)*100, 100);
        }
    }

    qprintf(quiet, "Images are identical.\n");
    ret = 0;

out:
    qemu_vfree(buf1);
    qemu_vfree(buf2);
    blk_unref(blk2);
out2:
    blk_unref(blk1);
out3:
    qemu_progress_end();
out4:
    return ret;
}

enum ImgConvertBlockStatus {
    BLK_DATA,
    BLK_ZERO,
    BLK_BACKING_FILE,
};

typedef struct ImgConvertState {
    BlockBackend **src;
    int64_t *src_sectors;
    int src_cur, src_num;
    int64_t src_cur_offset;
    int64_t total_sectors;
    int64_t allocated_sectors;
    enum ImgConvertBlockStatus status;
    int64_t sector_next_status;
    BlockBackend *target;
    bool has_zero_init;
    bool compressed;
    bool target_has_backing;
    int min_sparse;
    size_t cluster_sectors;
    size_t buf_sectors;
} ImgConvertState;

static void convert_select_part(ImgConvertState *s, int64_t sector_num)
{
    assert(sector_num >= s->src_cur_offset);
    while (sector_num - s->src_cur_offset >= s->src_sectors[s->src_cur]) {
        s->src_cur_offset += s->src_sectors[s->src_cur];
        s->src_cur++;
        assert(s->src_cur < s->src_num);
    }
}

static int convert_iteration_sectors(ImgConvertState *s, int64_t sector_num)
{
    int64_t ret;
    int n;

    convert_select_part(s, sector_num);

    assert(s->total_sectors > sector_num);
    n = MIN(s->total_sectors - sector_num, BDRV_REQUEST_MAX_SECTORS);

    if (s->sector_next_status <= sector_num) {
        BlockDriverState *file;
        ret = bdrv_get_block_status(blk_bs(s->src[s->src_cur]),
                                    sector_num - s->src_cur_offset,
                                    n, &n, &file);
        if (ret < 0) {
            return ret;
        }

        if (ret & BDRV_BLOCK_ZERO) {
            s->status = BLK_ZERO;
        } else if (ret & BDRV_BLOCK_DATA) {
            s->status = BLK_DATA;
        } else if (!s->target_has_backing) {
            /* Without a target backing file we must copy over the contents of
             * the backing file as well. */
            /* Check block status of the backing file chain to avoid
             * needlessly reading zeroes and limiting the iteration to the
             * buffer size */
            ret = bdrv_get_block_status_above(blk_bs(s->src[s->src_cur]), NULL,
                                              sector_num - s->src_cur_offset,
                                              n, &n, &file);
            if (ret < 0) {
                return ret;
            }

            if (ret & BDRV_BLOCK_ZERO) {
                s->status = BLK_ZERO;
            } else {
                s->status = BLK_DATA;
            }
        } else {
            s->status = BLK_BACKING_FILE;
        }

        s->sector_next_status = sector_num + n;
    }

    n = MIN(n, s->sector_next_status - sector_num);
    if (s->status == BLK_DATA) {
        n = MIN(n, s->buf_sectors);
    }

    /* We need to write complete clusters for compressed images, so if an
     * unallocated area is shorter than that, we must consider the whole
     * cluster allocated. */
    if (s->compressed) {
        if (n < s->cluster_sectors) {
            n = MIN(s->cluster_sectors, s->total_sectors - sector_num);
            s->status = BLK_DATA;
        } else {
            n = QEMU_ALIGN_DOWN(n, s->cluster_sectors);
        }
    }

    return n;
}

static int convert_read(ImgConvertState *s, int64_t sector_num, int nb_sectors,
                        uint8_t *buf)
{
    int n;
    int ret;

    assert(nb_sectors <= s->buf_sectors);
    while (nb_sectors > 0) {
        BlockBackend *blk;
        int64_t bs_sectors;

        /* In the case of compression with multiple source files, we can get a
         * nb_sectors that spreads into the next part. So we must be able to
         * read across multiple BDSes for one convert_read() call. */
        convert_select_part(s, sector_num);
        blk = s->src[s->src_cur];
        bs_sectors = s->src_sectors[s->src_cur];

        n = MIN(nb_sectors, bs_sectors - (sector_num - s->src_cur_offset));
        ret = blk_pread(blk,
                        (sector_num - s->src_cur_offset) << BDRV_SECTOR_BITS,
                        buf, n << BDRV_SECTOR_BITS);
        if (ret < 0) {
            return ret;
        }

        sector_num += n;
        nb_sectors -= n;
        buf += n * BDRV_SECTOR_SIZE;
    }

    return 0;
}

static int convert_write(ImgConvertState *s, int64_t sector_num, int nb_sectors,
                         const uint8_t *buf)
{
    int ret;

    while (nb_sectors > 0) {
        int n = nb_sectors;

        switch (s->status) {
        case BLK_BACKING_FILE:
            /* If we have a backing file, leave clusters unallocated that are
             * unallocated in the source image, so that the backing file is
             * visible at the respective offset. */
            assert(s->target_has_backing);
            break;

        case BLK_DATA:
            /* We must always write compressed clusters as a whole, so don't
             * try to find zeroed parts in the buffer. We can only save the
             * write if the buffer is completely zeroed and we're allowed to
             * keep the target sparse. */
            if (s->compressed) {
                if (s->has_zero_init && s->min_sparse &&
                    buffer_is_zero(buf, n * BDRV_SECTOR_SIZE))
                {
                    assert(!s->target_has_backing);
                    break;
                }

                ret = blk_pwrite_compressed(s->target,
                                            sector_num << BDRV_SECTOR_BITS,
                                            buf, n << BDRV_SECTOR_BITS);
                if (ret < 0) {
                    return ret;
                }
                break;
            }

            /* If there is real non-zero data or we're told to keep the target
             * fully allocated (-S 0), we must write it. Otherwise we can treat
             * it as zero sectors. */
            if (!s->min_sparse ||
                is_allocated_sectors_min(buf, n, &n, s->min_sparse))
            {
                ret = blk_pwrite(s->target, sector_num << BDRV_SECTOR_BITS,
                                 buf, n << BDRV_SECTOR_BITS, 0);
                if (ret < 0) {
                    return ret;
                }
                break;
            }
            /* fall-through */

        case BLK_ZERO:
            if (s->has_zero_init) {
                break;
            }
            ret = blk_pwrite_zeroes(s->target, sector_num << BDRV_SECTOR_BITS,
                                    n << BDRV_SECTOR_BITS, 0);
            if (ret < 0) {
                return ret;
            }
            break;
        }

        sector_num += n;
        nb_sectors -= n;
        buf += n * BDRV_SECTOR_SIZE;
    }

    return 0;
}

static int convert_do_copy(ImgConvertState *s)
{
    uint8_t *buf = NULL;
    int64_t sector_num, allocated_done;
    int ret;
    int n;

    /* Check whether we have zero initialisation or can get it efficiently */
    s->has_zero_init = s->min_sparse && !s->target_has_backing
                     ? bdrv_has_zero_init(blk_bs(s->target))
                     : false;

    if (!s->has_zero_init && !s->target_has_backing &&
        bdrv_can_write_zeroes_with_unmap(blk_bs(s->target)))
    {
        ret = blk_make_zero(s->target, BDRV_REQ_MAY_UNMAP);
        if (ret == 0) {
            s->has_zero_init = true;
        }
    }

    /* Allocate buffer for copied data. For compressed images, only one cluster
     * can be copied at a time. */
    if (s->compressed) {
        if (s->cluster_sectors <= 0 || s->cluster_sectors > s->buf_sectors) {
            error_report("invalid cluster size");
            ret = -EINVAL;
            goto fail;
        }
        s->buf_sectors = s->cluster_sectors;
    }
    buf = blk_blockalign(s->target, s->buf_sectors * BDRV_SECTOR_SIZE);

    /* Calculate allocated sectors for progress */
    s->allocated_sectors = 0;
    sector_num = 0;
    while (sector_num < s->total_sectors) {
        n = convert_iteration_sectors(s, sector_num);
        if (n < 0) {
            ret = n;
            goto fail;
        }
        if (s->status == BLK_DATA || (!s->min_sparse && s->status == BLK_ZERO))
        {
            s->allocated_sectors += n;
        }
        sector_num += n;
    }

    /* Do the copy */
    s->src_cur = 0;
    s->src_cur_offset = 0;
    s->sector_next_status = 0;

    sector_num = 0;
    allocated_done = 0;

    while (sector_num < s->total_sectors) {
        n = convert_iteration_sectors(s, sector_num);
        if (n < 0) {
            ret = n;
            goto fail;
        }
        if (s->status == BLK_DATA || (!s->min_sparse && s->status == BLK_ZERO))
        {
            allocated_done += n;
            qemu_progress_print(100.0 * allocated_done / s->allocated_sectors,
                                0);
        }

        if (s->status == BLK_DATA) {
            ret = convert_read(s, sector_num, n, buf);
            if (ret < 0) {
                error_report("error while reading sector %" PRId64
                             ": %s", sector_num, strerror(-ret));
                goto fail;
            }
        } else if (!s->min_sparse && s->status == BLK_ZERO) {
            n = MIN(n, s->buf_sectors);
            memset(buf, 0, n * BDRV_SECTOR_SIZE);
            s->status = BLK_DATA;
        }

        ret = convert_write(s, sector_num, n, buf);
        if (ret < 0) {
            error_report("error while writing sector %" PRId64
                         ": %s", sector_num, strerror(-ret));
            goto fail;
        }

        sector_num += n;
    }

    if (s->compressed) {
        /* signal EOF to align */
        ret = blk_pwrite_compressed(s->target, 0, NULL, 0);
        if (ret < 0) {
            goto fail;
        }
    }

    ret = 0;
fail:
    qemu_vfree(buf);
    return ret;
}

static int img_convert(int argc, char **argv)
{
    int c, bs_n, bs_i, compress, cluster_sectors, skip_create;
    int64_t ret = 0;
    int progress = 0, flags, src_flags;
    bool writethrough, src_writethrough;
    const char *fmt, *out_fmt, *cache, *src_cache, *out_baseimg, *out_filename;
    BlockDriver *drv, *proto_drv;
    BlockBackend **blk = NULL, *out_blk = NULL;
    BlockDriverState **bs = NULL, *out_bs = NULL;
    int64_t total_sectors;
    int64_t *bs_sectors = NULL;
    size_t bufsectors = IO_BUF_SIZE / BDRV_SECTOR_SIZE;
    BlockDriverInfo bdi;
    QemuOpts *opts = NULL;
    QemuOptsList *create_opts = NULL;
    const char *out_baseimg_param;
    char *options = NULL;
    const char *snapshot_name = NULL;
    int min_sparse = 8; /* Need at least 4k of zeros for sparse detection */
    bool quiet = false;
    Error *local_err = NULL;
    QemuOpts *sn_opts = NULL;
    ImgConvertState state;
    bool image_opts = false;

    fmt = NULL;
    out_fmt = "raw";
    cache = "unsafe";
    src_cache = BDRV_DEFAULT_CACHE;
    out_baseimg = NULL;
    compress = 0;
    skip_create = 0;
    for(;;) {
        static const struct option long_options[] = {
            {"help", no_argument, 0, 'h'},
            {"object", required_argument, 0, OPTION_OBJECT},
            {"image-opts", no_argument, 0, OPTION_IMAGE_OPTS},
            {0, 0, 0, 0}
        };
        c = getopt_long(argc, argv, "hf:O:B:ce6o:s:l:S:pt:T:qn",
                        long_options, NULL);
        if (c == -1) {
            break;
        }
        switch(c) {
        case '?':
        case 'h':
            help();
            break;
        case 'f':
            fmt = optarg;
            break;
        case 'O':
            out_fmt = optarg;
            break;
        case 'B':
            out_baseimg = optarg;
            break;
        case 'c':
            compress = 1;
            break;
        case 'e':
            error_report("option -e is deprecated, please use \'-o "
                  "encryption\' instead!");
            ret = -1;
            goto fail_getopt;
        case '6':
            error_report("option -6 is deprecated, please use \'-o "
                  "compat6\' instead!");
            ret = -1;
            goto fail_getopt;
        case 'o':
            if (!is_valid_option_list(optarg)) {
                error_report("Invalid option list: %s", optarg);
                ret = -1;
                goto fail_getopt;
            }
            if (!options) {
                options = g_strdup(optarg);
            } else {
                char *old_options = options;
                options = g_strdup_printf("%s,%s", options, optarg);
                g_free(old_options);
            }
            break;
        case 's':
            snapshot_name = optarg;
            break;
        case 'l':
            if (strstart(optarg, SNAPSHOT_OPT_BASE, NULL)) {
                sn_opts = qemu_opts_parse_noisily(&internal_snapshot_opts,
                                                  optarg, false);
                if (!sn_opts) {
                    error_report("Failed in parsing snapshot param '%s'",
                                 optarg);
                    ret = -1;
                    goto fail_getopt;
                }
            } else {
                snapshot_name = optarg;
            }
            break;
        case 'S':
        {
            int64_t sval;
            char *end;
            sval = qemu_strtosz_suffix(optarg, &end, QEMU_STRTOSZ_DEFSUFFIX_B);
            if (sval < 0 || *end) {
                error_report("Invalid minimum zero buffer size for sparse output specified");
                ret = -1;
                goto fail_getopt;
            }

            min_sparse = sval / BDRV_SECTOR_SIZE;
            break;
        }
        case 'p':
            progress = 1;
            break;
        case 't':
            cache = optarg;
            break;
        case 'T':
            src_cache = optarg;
            break;
        case 'q':
            quiet = true;
            break;
        case 'n':
            skip_create = 1;
            break;
        case OPTION_OBJECT:
            opts = qemu_opts_parse_noisily(&qemu_object_opts,
                                           optarg, true);
            if (!opts) {
                goto fail_getopt;
            }
            break;
        case OPTION_IMAGE_OPTS:
            image_opts = true;
            break;
        }
    }

    if (qemu_opts_foreach(&qemu_object_opts,
                          user_creatable_add_opts_foreach,
                          NULL, NULL)) {
        goto fail_getopt;
    }

    /* Initialize before goto out */
    if (quiet) {
        progress = 0;
    }
    qemu_progress_init(progress, 1.0);

    bs_n = argc - optind - 1;
    out_filename = bs_n >= 1 ? argv[argc - 1] : NULL;

    if (options && has_help_option(options)) {
        ret = print_block_option_help(out_filename, out_fmt);
        goto out;
    }

    if (bs_n < 1) {
        error_exit("Must specify image file name");
    }


    if (bs_n > 1 && out_baseimg) {
        error_report("-B makes no sense when concatenating multiple input "
                     "images");
        ret = -1;
        goto out;
    }

    src_flags = 0;
    ret = bdrv_parse_cache_mode(src_cache, &src_flags, &src_writethrough);
    if (ret < 0) {
        error_report("Invalid source cache option: %s", src_cache);
        goto out;
    }

    qemu_progress_print(0, 100);

    blk = g_new0(BlockBackend *, bs_n);
    bs = g_new0(BlockDriverState *, bs_n);
    bs_sectors = g_new(int64_t, bs_n);

    total_sectors = 0;
    for (bs_i = 0; bs_i < bs_n; bs_i++) {
        blk[bs_i] = img_open(image_opts, argv[optind + bs_i],
                             fmt, src_flags, src_writethrough, quiet);
        if (!blk[bs_i]) {
            ret = -1;
            goto out;
        }
        bs[bs_i] = blk_bs(blk[bs_i]);
        bs_sectors[bs_i] = blk_nb_sectors(blk[bs_i]);
        if (bs_sectors[bs_i] < 0) {
            error_report("Could not get size of %s: %s",
                         argv[optind + bs_i], strerror(-bs_sectors[bs_i]));
            ret = -1;
            goto out;
        }
        total_sectors += bs_sectors[bs_i];
    }

    if (sn_opts) {
        ret = bdrv_snapshot_load_tmp(bs[0],
                                     qemu_opt_get(sn_opts, SNAPSHOT_OPT_ID),
                                     qemu_opt_get(sn_opts, SNAPSHOT_OPT_NAME),
                                     &local_err);
    } else if (snapshot_name != NULL) {
        if (bs_n > 1) {
            error_report("No support for concatenating multiple snapshot");
            ret = -1;
            goto out;
        }

        bdrv_snapshot_load_tmp_by_id_or_name(bs[0], snapshot_name, &local_err);
    }
    if (local_err) {
        error_reportf_err(local_err, "Failed to load snapshot: ");
        ret = -1;
        goto out;
    }

    /* Find driver and parse its options */
    drv = bdrv_find_format(out_fmt);
    if (!drv) {
        error_report("Unknown file format '%s'", out_fmt);
        ret = -1;
        goto out;
    }

    proto_drv = bdrv_find_protocol(out_filename, true, &local_err);
    if (!proto_drv) {
        error_report_err(local_err);
        ret = -1;
        goto out;
    }

    if (!skip_create) {
        if (!drv->create_opts) {
            error_report("Format driver '%s' does not support image creation",
                         drv->format_name);
            ret = -1;
            goto out;
        }

        if (!proto_drv->create_opts) {
            error_report("Protocol driver '%s' does not support image creation",
                         proto_drv->format_name);
            ret = -1;
            goto out;
        }

        create_opts = qemu_opts_append(create_opts, drv->create_opts);
        create_opts = qemu_opts_append(create_opts, proto_drv->create_opts);

        opts = qemu_opts_create(create_opts, NULL, 0, &error_abort);
        if (options) {
            qemu_opts_do_parse(opts, options, NULL, &local_err);
            if (local_err) {
                error_report_err(local_err);
                ret = -1;
                goto out;
            }
        }

        qemu_opt_set_number(opts, BLOCK_OPT_SIZE, total_sectors * 512,
                            &error_abort);
        ret = add_old_style_options(out_fmt, opts, out_baseimg, NULL);
        if (ret < 0) {
            goto out;
        }
    }

    /* Get backing file name if -o backing_file was used */
    out_baseimg_param = qemu_opt_get(opts, BLOCK_OPT_BACKING_FILE);
    if (out_baseimg_param) {
        out_baseimg = out_baseimg_param;
    }

    /* Check if compression is supported */
    if (compress) {
        bool encryption =
            qemu_opt_get_bool(opts, BLOCK_OPT_ENCRYPT, false);
        const char *preallocation =
            qemu_opt_get(opts, BLOCK_OPT_PREALLOC);

        if (!drv->bdrv_co_pwritev_compressed) {
            error_report("Compression not supported for this file format");
            ret = -1;
            goto out;
        }

        if (encryption) {
            error_report("Compression and encryption not supported at "
                         "the same time");
            ret = -1;
            goto out;
        }

        if (preallocation
            && strcmp(preallocation, "off"))
        {
            error_report("Compression and preallocation not supported at "
                         "the same time");
            ret = -1;
            goto out;
        }
    }

    if (!skip_create) {
        /* Create the new image */
        ret = bdrv_create(drv, out_filename, opts, &local_err);
        if (ret < 0) {
            error_reportf_err(local_err, "%s: error while converting %s: ",
                              out_filename, out_fmt);
            goto out;
        }
    }

    flags = min_sparse ? (BDRV_O_RDWR | BDRV_O_UNMAP) : BDRV_O_RDWR;
    ret = bdrv_parse_cache_mode(cache, &flags, &writethrough);
    if (ret < 0) {
        error_report("Invalid cache option: %s", cache);
        goto out;
    }

    /* XXX we should allow --image-opts to trigger use of
     * img_open() here, but then we have trouble with
     * the bdrv_create() call which takes different params.
     * Not critical right now, so fix can wait...
     */
    out_blk = img_open_file(out_filename, out_fmt, flags, writethrough, quiet);
    if (!out_blk) {
        ret = -1;
        goto out;
    }
    out_bs = blk_bs(out_blk);

    /* increase bufsectors from the default 4096 (2M) if opt_transfer
     * or discard_alignment of the out_bs is greater. Limit to 32768 (16MB)
     * as maximum. */
    bufsectors = MIN(32768,
                     MAX(bufsectors,
                         MAX(out_bs->bl.opt_transfer >> BDRV_SECTOR_BITS,
                             out_bs->bl.pdiscard_alignment >>
                             BDRV_SECTOR_BITS)));

    if (skip_create) {
        int64_t output_sectors = blk_nb_sectors(out_blk);
        if (output_sectors < 0) {
            error_report("unable to get output image length: %s",
                         strerror(-output_sectors));
            ret = -1;
            goto out;
        } else if (output_sectors < total_sectors) {
            error_report("output file is smaller than input file");
            ret = -1;
            goto out;
        }
    }

    cluster_sectors = 0;
    ret = bdrv_get_info(out_bs, &bdi);
    if (ret < 0) {
        if (compress) {
            error_report("could not get block driver info");
            goto out;
        }
    } else {
        compress = compress || bdi.needs_compressed_writes;
        cluster_sectors = bdi.cluster_size / BDRV_SECTOR_SIZE;
    }

    state = (ImgConvertState) {
        .src                = blk,
        .src_sectors        = bs_sectors,
        .src_num            = bs_n,
        .total_sectors      = total_sectors,
        .target             = out_blk,
        .compressed         = compress,
        .target_has_backing = (bool) out_baseimg,
        .min_sparse         = min_sparse,
        .cluster_sectors    = cluster_sectors,
        .buf_sectors        = bufsectors,
    };
    ret = convert_do_copy(&state);

out:
    if (!ret) {
        qemu_progress_print(100, 0);
    }
    qemu_progress_end();
    qemu_opts_del(opts);
    qemu_opts_free(create_opts);
    qemu_opts_del(sn_opts);
    blk_unref(out_blk);
    g_free(bs);
    if (blk) {
        for (bs_i = 0; bs_i < bs_n; bs_i++) {
            blk_unref(blk[bs_i]);
        }
        g_free(blk);
    }
    g_free(bs_sectors);
fail_getopt:
    g_free(options);

    if (ret) {
        return 1;
    }
    return 0;
}


static void dump_snapshots(BlockDriverState *bs)
{
    QEMUSnapshotInfo *sn_tab, *sn;
    int nb_sns, i;

    nb_sns = bdrv_snapshot_list(bs, &sn_tab);
    if (nb_sns <= 0)
        return;
    printf("Snapshot list:\n");
    bdrv_snapshot_dump(fprintf, stdout, NULL);
    printf("\n");
    for(i = 0; i < nb_sns; i++) {
        sn = &sn_tab[i];
        bdrv_snapshot_dump(fprintf, stdout, sn);
        printf("\n");
    }
    g_free(sn_tab);
}

static void dump_json_image_info_list(ImageInfoList *list)
{
    QString *str;
    QObject *obj;
    Visitor *v = qmp_output_visitor_new(&obj);

    visit_type_ImageInfoList(v, NULL, &list, &error_abort);
    visit_complete(v, &obj);
    str = qobject_to_json_pretty(obj);
    assert(str != NULL);
    printf("%s\n", qstring_get_str(str));
    qobject_decref(obj);
    visit_free(v);
    QDECREF(str);
}

static void dump_json_image_info(ImageInfo *info)
{
    QString *str;
    QObject *obj;
    Visitor *v = qmp_output_visitor_new(&obj);

    visit_type_ImageInfo(v, NULL, &info, &error_abort);
    visit_complete(v, &obj);
    str = qobject_to_json_pretty(obj);
    assert(str != NULL);
    printf("%s\n", qstring_get_str(str));
    qobject_decref(obj);
    visit_free(v);
    QDECREF(str);
}

static void dump_human_image_info_list(ImageInfoList *list)
{
    ImageInfoList *elem;
    bool delim = false;

    for (elem = list; elem; elem = elem->next) {
        if (delim) {
            printf("\n");
        }
        delim = true;

        bdrv_image_info_dump(fprintf, stdout, elem->value);
    }
}

static gboolean str_equal_func(gconstpointer a, gconstpointer b)
{
    return strcmp(a, b) == 0;
}

/**
 * Open an image file chain and return an ImageInfoList
 *
 * @filename: topmost image filename
 * @fmt: topmost image format (may be NULL to autodetect)
 * @chain: true  - enumerate entire backing file chain
 *         false - only topmost image file
 *
 * Returns a list of ImageInfo objects or NULL if there was an error opening an
 * image file.  If there was an error a message will have been printed to
 * stderr.
 */
static ImageInfoList *collect_image_info_list(bool image_opts,
                                              const char *filename,
                                              const char *fmt,
                                              bool chain)
{
    ImageInfoList *head = NULL;
    ImageInfoList **last = &head;
    GHashTable *filenames;
    Error *err = NULL;

    filenames = g_hash_table_new_full(g_str_hash, str_equal_func, NULL, NULL);

    while (filename) {
        BlockBackend *blk;
        BlockDriverState *bs;
        ImageInfo *info;
        ImageInfoList *elem;

        if (g_hash_table_lookup_extended(filenames, filename, NULL, NULL)) {
            error_report("Backing file '%s' creates an infinite loop.",
                         filename);
            goto err;
        }
        g_hash_table_insert(filenames, (gpointer)filename, NULL);

        blk = img_open(image_opts, filename, fmt,
                       BDRV_O_NO_BACKING | BDRV_O_NO_IO, false, false);
        if (!blk) {
            goto err;
        }
        bs = blk_bs(blk);

        bdrv_query_image_info(bs, &info, &err);
        if (err) {
            error_report_err(err);
            blk_unref(blk);
            goto err;
        }

        elem = g_new0(ImageInfoList, 1);
        elem->value = info;
        *last = elem;
        last = &elem->next;

        blk_unref(blk);

        filename = fmt = NULL;
        if (chain) {
            if (info->has_full_backing_filename) {
                filename = info->full_backing_filename;
            } else if (info->has_backing_filename) {
                error_report("Could not determine absolute backing filename,"
                             " but backing filename '%s' present",
                             info->backing_filename);
                goto err;
            }
            if (info->has_backing_filename_format) {
                fmt = info->backing_filename_format;
            }
        }
    }
    g_hash_table_destroy(filenames);
    return head;

err:
    qapi_free_ImageInfoList(head);
    g_hash_table_destroy(filenames);
    return NULL;
}

static int img_info(int argc, char **argv)
{
    int c;
    OutputFormat output_format = OFORMAT_HUMAN;
    bool chain = false;
    const char *filename, *fmt, *output;
    ImageInfoList *list;
    bool image_opts = false;

    fmt = NULL;
    output = NULL;
    for(;;) {
        int option_index = 0;
        static const struct option long_options[] = {
            {"help", no_argument, 0, 'h'},
            {"format", required_argument, 0, 'f'},
            {"output", required_argument, 0, OPTION_OUTPUT},
            {"backing-chain", no_argument, 0, OPTION_BACKING_CHAIN},
            {"object", required_argument, 0, OPTION_OBJECT},
            {"image-opts", no_argument, 0, OPTION_IMAGE_OPTS},
            {0, 0, 0, 0}
        };
        c = getopt_long(argc, argv, "f:h",
                        long_options, &option_index);
        if (c == -1) {
            break;
        }
        switch(c) {
        case '?':
        case 'h':
            help();
            break;
        case 'f':
            fmt = optarg;
            break;
        case OPTION_OUTPUT:
            output = optarg;
            break;
        case OPTION_BACKING_CHAIN:
            chain = true;
            break;
        case OPTION_OBJECT: {
            QemuOpts *opts;
            opts = qemu_opts_parse_noisily(&qemu_object_opts,
                                           optarg, true);
            if (!opts) {
                return 1;
            }
        }   break;
        case OPTION_IMAGE_OPTS:
            image_opts = true;
            break;
        }
    }
    if (optind != argc - 1) {
        error_exit("Expecting one image file name");
    }
    filename = argv[optind++];

    if (output && !strcmp(output, "json")) {
        output_format = OFORMAT_JSON;
    } else if (output && !strcmp(output, "human")) {
        output_format = OFORMAT_HUMAN;
    } else if (output) {
        error_report("--output must be used with human or json as argument.");
        return 1;
    }

    if (qemu_opts_foreach(&qemu_object_opts,
                          user_creatable_add_opts_foreach,
                          NULL, NULL)) {
        return 1;
    }

    list = collect_image_info_list(image_opts, filename, fmt, chain);
    if (!list) {
        return 1;
    }

    switch (output_format) {
    case OFORMAT_HUMAN:
        dump_human_image_info_list(list);
        break;
    case OFORMAT_JSON:
        if (chain) {
            dump_json_image_info_list(list);
        } else {
            dump_json_image_info(list->value);
        }
        break;
    }

    qapi_free_ImageInfoList(list);
    return 0;
}

static void dump_map_entry(OutputFormat output_format, MapEntry *e,
                           MapEntry *next)
{
    switch (output_format) {
    case OFORMAT_HUMAN:
        if (e->data && !e->has_offset) {
            error_report("File contains external, encrypted or compressed clusters.");
            exit(1);
        }
        if (e->data && !e->zero) {
            printf("%#-16"PRIx64"%#-16"PRIx64"%#-16"PRIx64"%s\n",
                   e->start, e->length,
                   e->has_offset ? e->offset : 0,
                   e->has_filename ? e->filename : "");
        }
        /* This format ignores the distinction between 0, ZERO and ZERO|DATA.
         * Modify the flags here to allow more coalescing.
         */
        if (next && (!next->data || next->zero)) {
            next->data = false;
            next->zero = true;
        }
        break;
    case OFORMAT_JSON:
        printf("%s{ \"start\": %"PRId64", \"length\": %"PRId64","
               " \"depth\": %"PRId64", \"zero\": %s, \"data\": %s",
               (e->start == 0 ? "[" : ",\n"),
               e->start, e->length, e->depth,
               e->zero ? "true" : "false",
               e->data ? "true" : "false");
        if (e->has_offset) {
            printf(", \"offset\": %"PRId64"", e->offset);
        }
        putchar('}');

        if (!next) {
            printf("]\n");
        }
        break;
    }
}

static int get_block_status(BlockDriverState *bs, int64_t sector_num,
                            int nb_sectors, MapEntry *e)
{
    int64_t ret;
    int depth;
    BlockDriverState *file;
    bool has_offset;

    /* As an optimization, we could cache the current range of unallocated
     * clusters in each file of the chain, and avoid querying the same
     * range repeatedly.
     */

    depth = 0;
    for (;;) {
        ret = bdrv_get_block_status(bs, sector_num, nb_sectors, &nb_sectors,
                                    &file);
        if (ret < 0) {
            return ret;
        }
        assert(nb_sectors);
        if (ret & (BDRV_BLOCK_ZERO|BDRV_BLOCK_DATA)) {
            break;
        }
        bs = backing_bs(bs);
        if (bs == NULL) {
            ret = 0;
            break;
        }

        depth++;
    }

    has_offset = !!(ret & BDRV_BLOCK_OFFSET_VALID);

    *e = (MapEntry) {
        .start = sector_num * BDRV_SECTOR_SIZE,
        .length = nb_sectors * BDRV_SECTOR_SIZE,
        .data = !!(ret & BDRV_BLOCK_DATA),
        .zero = !!(ret & BDRV_BLOCK_ZERO),
        .offset = ret & BDRV_BLOCK_OFFSET_MASK,
        .has_offset = has_offset,
        .depth = depth,
        .has_filename = file && has_offset,
        .filename = file && has_offset ? file->filename : NULL,
    };

    return 0;
}

static inline bool entry_mergeable(const MapEntry *curr, const MapEntry *next)
{
    if (curr->length == 0) {
        return false;
    }
    if (curr->zero != next->zero ||
        curr->data != next->data ||
        curr->depth != next->depth ||
        curr->has_filename != next->has_filename ||
        curr->has_offset != next->has_offset) {
        return false;
    }
    if (curr->has_filename && strcmp(curr->filename, next->filename)) {
        return false;
    }
    if (curr->has_offset && curr->offset + curr->length != next->offset) {
        return false;
    }
    return true;
}

static int img_map(int argc, char **argv)
{
    int c;
    OutputFormat output_format = OFORMAT_HUMAN;
    BlockBackend *blk;
    BlockDriverState *bs;
    const char *filename, *fmt, *output;
    int64_t length;
    MapEntry curr = { .length = 0 }, next;
    int ret = 0;
    bool image_opts = false;

    fmt = NULL;
    output = NULL;
    for (;;) {
        int option_index = 0;
        static const struct option long_options[] = {
            {"help", no_argument, 0, 'h'},
            {"format", required_argument, 0, 'f'},
            {"output", required_argument, 0, OPTION_OUTPUT},
            {"object", required_argument, 0, OPTION_OBJECT},
            {"image-opts", no_argument, 0, OPTION_IMAGE_OPTS},
            {0, 0, 0, 0}
        };
        c = getopt_long(argc, argv, "f:h",
                        long_options, &option_index);
        if (c == -1) {
            break;
        }
        switch (c) {
        case '?':
        case 'h':
            help();
            break;
        case 'f':
            fmt = optarg;
            break;
        case OPTION_OUTPUT:
            output = optarg;
            break;
        case OPTION_OBJECT: {
            QemuOpts *opts;
            opts = qemu_opts_parse_noisily(&qemu_object_opts,
                                           optarg, true);
            if (!opts) {
                return 1;
            }
        }   break;
        case OPTION_IMAGE_OPTS:
            image_opts = true;
            break;
        }
    }
    if (optind != argc - 1) {
        error_exit("Expecting one image file name");
    }
    filename = argv[optind];

    if (output && !strcmp(output, "json")) {
        output_format = OFORMAT_JSON;
    } else if (output && !strcmp(output, "human")) {
        output_format = OFORMAT_HUMAN;
    } else if (output) {
        error_report("--output must be used with human or json as argument.");
        return 1;
    }

    if (qemu_opts_foreach(&qemu_object_opts,
                          user_creatable_add_opts_foreach,
                          NULL, NULL)) {
        return 1;
    }

    blk = img_open(image_opts, filename, fmt, 0, false, false);
    if (!blk) {
        return 1;
    }
    bs = blk_bs(blk);

    if (output_format == OFORMAT_HUMAN) {
        printf("%-16s%-16s%-16s%s\n", "Offset", "Length", "Mapped to", "File");
    }

    length = blk_getlength(blk);
    while (curr.start + curr.length < length) {
        int64_t nsectors_left;
        int64_t sector_num;
        int n;

        sector_num = (curr.start + curr.length) >> BDRV_SECTOR_BITS;

        /* Probe up to 1 GiB at a time.  */
        nsectors_left = DIV_ROUND_UP(length, BDRV_SECTOR_SIZE) - sector_num;
        n = MIN(1 << (30 - BDRV_SECTOR_BITS), nsectors_left);
        ret = get_block_status(bs, sector_num, n, &next);

        if (ret < 0) {
            error_report("Could not read file metadata: %s", strerror(-ret));
            goto out;
        }

        if (entry_mergeable(&curr, &next)) {
            curr.length += next.length;
            continue;
        }

        if (curr.length > 0) {
            dump_map_entry(output_format, &curr, &next);
        }
        curr = next;
    }

    dump_map_entry(output_format, &curr, NULL);

out:
    blk_unref(blk);
    return ret < 0;
}

#define SNAPSHOT_LIST   1
#define SNAPSHOT_CREATE 2
#define SNAPSHOT_APPLY  3
#define SNAPSHOT_DELETE 4

static int img_snapshot(int argc, char **argv)
{
    BlockBackend *blk;
    BlockDriverState *bs;
    QEMUSnapshotInfo sn;
    char *filename, *snapshot_name = NULL;
    int c, ret = 0, bdrv_oflags;
    int action = 0;
    qemu_timeval tv;
    bool quiet = false;
    Error *err = NULL;
    bool image_opts = false;

    bdrv_oflags = BDRV_O_RDWR;
    /* Parse commandline parameters */
    for(;;) {
        static const struct option long_options[] = {
            {"help", no_argument, 0, 'h'},
            {"object", required_argument, 0, OPTION_OBJECT},
            {"image-opts", no_argument, 0, OPTION_IMAGE_OPTS},
            {0, 0, 0, 0}
        };
        c = getopt_long(argc, argv, "la:c:d:hq",
                        long_options, NULL);
        if (c == -1) {
            break;
        }
        switch(c) {
        case '?':
        case 'h':
            help();
            return 0;
        case 'l':
            if (action) {
                error_exit("Cannot mix '-l', '-a', '-c', '-d'");
                return 0;
            }
            action = SNAPSHOT_LIST;
            bdrv_oflags &= ~BDRV_O_RDWR; /* no need for RW */
            break;
        case 'a':
            if (action) {
                error_exit("Cannot mix '-l', '-a', '-c', '-d'");
                return 0;
            }
            action = SNAPSHOT_APPLY;
            snapshot_name = optarg;
            break;
        case 'c':
            if (action) {
                error_exit("Cannot mix '-l', '-a', '-c', '-d'");
                return 0;
            }
            action = SNAPSHOT_CREATE;
            snapshot_name = optarg;
            break;
        case 'd':
            if (action) {
                error_exit("Cannot mix '-l', '-a', '-c', '-d'");
                return 0;
            }
            action = SNAPSHOT_DELETE;
            snapshot_name = optarg;
            break;
        case 'q':
            quiet = true;
            break;
        case OPTION_OBJECT: {
            QemuOpts *opts;
            opts = qemu_opts_parse_noisily(&qemu_object_opts,
                                           optarg, true);
            if (!opts) {
                return 1;
            }
        }   break;
        case OPTION_IMAGE_OPTS:
            image_opts = true;
            break;
        }
    }

    if (optind != argc - 1) {
        error_exit("Expecting one image file name");
    }
    filename = argv[optind++];

    if (qemu_opts_foreach(&qemu_object_opts,
                          user_creatable_add_opts_foreach,
                          NULL, NULL)) {
        return 1;
    }

    /* Open the image */
    blk = img_open(image_opts, filename, NULL, bdrv_oflags, false, quiet);
    if (!blk) {
        return 1;
    }
    bs = blk_bs(blk);

    /* Perform the requested action */
    switch(action) {
    case SNAPSHOT_LIST:
        dump_snapshots(bs);
        break;

    case SNAPSHOT_CREATE:
        memset(&sn, 0, sizeof(sn));
        pstrcpy(sn.name, sizeof(sn.name), snapshot_name);

        qemu_gettimeofday(&tv);
        sn.date_sec = tv.tv_sec;
        sn.date_nsec = tv.tv_usec * 1000;

        ret = bdrv_snapshot_create(bs, &sn);
        if (ret) {
            error_report("Could not create snapshot '%s': %d (%s)",
                snapshot_name, ret, strerror(-ret));
        }
        break;

    case SNAPSHOT_APPLY:
        ret = bdrv_snapshot_goto(bs, snapshot_name);
        if (ret) {
            error_report("Could not apply snapshot '%s': %d (%s)",
                snapshot_name, ret, strerror(-ret));
        }
        break;

    case SNAPSHOT_DELETE:
        bdrv_snapshot_delete_by_id_or_name(bs, snapshot_name, &err);
        if (err) {
            error_reportf_err(err, "Could not delete snapshot '%s': ",
                              snapshot_name);
            ret = 1;
        }
        break;
    }

    /* Cleanup */
    blk_unref(blk);
    if (ret) {
        return 1;
    }
    return 0;
}

static int img_rebase(int argc, char **argv)
{
    BlockBackend *blk = NULL, *blk_old_backing = NULL, *blk_new_backing = NULL;
    uint8_t *buf_old = NULL;
    uint8_t *buf_new = NULL;
    BlockDriverState *bs = NULL;
    char *filename;
    const char *fmt, *cache, *src_cache, *out_basefmt, *out_baseimg;
    int c, flags, src_flags, ret;
    bool writethrough, src_writethrough;
    int unsafe = 0;
    int progress = 0;
    bool quiet = false;
    Error *local_err = NULL;
    bool image_opts = false;

    /* Parse commandline parameters */
    fmt = NULL;
    cache = BDRV_DEFAULT_CACHE;
    src_cache = BDRV_DEFAULT_CACHE;
    out_baseimg = NULL;
    out_basefmt = NULL;
    for(;;) {
        static const struct option long_options[] = {
            {"help", no_argument, 0, 'h'},
            {"object", required_argument, 0, OPTION_OBJECT},
            {"image-opts", no_argument, 0, OPTION_IMAGE_OPTS},
            {0, 0, 0, 0}
        };
        c = getopt_long(argc, argv, "hf:F:b:upt:T:q",
                        long_options, NULL);
        if (c == -1) {
            break;
        }
        switch(c) {
        case '?':
        case 'h':
            help();
            return 0;
        case 'f':
            fmt = optarg;
            break;
        case 'F':
            out_basefmt = optarg;
            break;
        case 'b':
            out_baseimg = optarg;
            break;
        case 'u':
            unsafe = 1;
            break;
        case 'p':
            progress = 1;
            break;
        case 't':
            cache = optarg;
            break;
        case 'T':
            src_cache = optarg;
            break;
        case 'q':
            quiet = true;
            break;
        case OPTION_OBJECT: {
            QemuOpts *opts;
            opts = qemu_opts_parse_noisily(&qemu_object_opts,
                                           optarg, true);
            if (!opts) {
                return 1;
            }
        }   break;
        case OPTION_IMAGE_OPTS:
            image_opts = true;
            break;
        }
    }

    if (quiet) {
        progress = 0;
    }

    if (optind != argc - 1) {
        error_exit("Expecting one image file name");
    }
    if (!unsafe && !out_baseimg) {
        error_exit("Must specify backing file (-b) or use unsafe mode (-u)");
    }
    filename = argv[optind++];

    if (qemu_opts_foreach(&qemu_object_opts,
                          user_creatable_add_opts_foreach,
                          NULL, NULL)) {
        return 1;
    }

    qemu_progress_init(progress, 2.0);
    qemu_progress_print(0, 100);

    flags = BDRV_O_RDWR | (unsafe ? BDRV_O_NO_BACKING : 0);
    ret = bdrv_parse_cache_mode(cache, &flags, &writethrough);
    if (ret < 0) {
        error_report("Invalid cache option: %s", cache);
        goto out;
    }

    src_flags = 0;
    ret = bdrv_parse_cache_mode(src_cache, &src_flags, &src_writethrough);
    if (ret < 0) {
        error_report("Invalid source cache option: %s", src_cache);
        goto out;
    }

    /* The source files are opened read-only, don't care about WCE */
    assert((src_flags & BDRV_O_RDWR) == 0);
    (void) src_writethrough;

    /*
     * Open the images.
     *
     * Ignore the old backing file for unsafe rebase in case we want to correct
     * the reference to a renamed or moved backing file.
     */
    blk = img_open(image_opts, filename, fmt, flags, writethrough, quiet);
    if (!blk) {
        ret = -1;
        goto out;
    }
    bs = blk_bs(blk);

    if (out_basefmt != NULL) {
        if (bdrv_find_format(out_basefmt) == NULL) {
            error_report("Invalid format name: '%s'", out_basefmt);
            ret = -1;
            goto out;
        }
    }

    /* For safe rebasing we need to compare old and new backing file */
    if (!unsafe) {
        char backing_name[PATH_MAX];
        QDict *options = NULL;

        if (bs->backing_format[0] != '\0') {
            options = qdict_new();
            qdict_put(options, "driver", qstring_from_str(bs->backing_format));
        }

        bdrv_get_backing_filename(bs, backing_name, sizeof(backing_name));
        blk_old_backing = blk_new_open(backing_name, NULL,
                                       options, src_flags, &local_err);
        if (!blk_old_backing) {
            error_reportf_err(local_err,
                              "Could not open old backing file '%s': ",
                              backing_name);
            goto out;
        }

        if (out_baseimg[0]) {
            if (out_basefmt) {
                options = qdict_new();
                qdict_put(options, "driver", qstring_from_str(out_basefmt));
            } else {
                options = NULL;
            }

            blk_new_backing = blk_new_open(out_baseimg, NULL,
                                           options, src_flags, &local_err);
            if (!blk_new_backing) {
                error_reportf_err(local_err,
                                  "Could not open new backing file '%s': ",
                                  out_baseimg);
                goto out;
            }
        }
    }

    /*
     * Check each unallocated cluster in the COW file. If it is unallocated,
     * accesses go to the backing file. We must therefore compare this cluster
     * in the old and new backing file, and if they differ we need to copy it
     * from the old backing file into the COW file.
     *
     * If qemu-img crashes during this step, no harm is done. The content of
     * the image is the same as the original one at any time.
     */
    if (!unsafe) {
        int64_t num_sectors;
        int64_t old_backing_num_sectors;
        int64_t new_backing_num_sectors = 0;
        uint64_t sector;
        int n;
        float local_progress = 0;

        buf_old = blk_blockalign(blk, IO_BUF_SIZE);
        buf_new = blk_blockalign(blk, IO_BUF_SIZE);

        num_sectors = blk_nb_sectors(blk);
        if (num_sectors < 0) {
            error_report("Could not get size of '%s': %s",
                         filename, strerror(-num_sectors));
            ret = -1;
            goto out;
        }
        old_backing_num_sectors = blk_nb_sectors(blk_old_backing);
        if (old_backing_num_sectors < 0) {
            char backing_name[PATH_MAX];

            bdrv_get_backing_filename(bs, backing_name, sizeof(backing_name));
            error_report("Could not get size of '%s': %s",
                         backing_name, strerror(-old_backing_num_sectors));
            ret = -1;
            goto out;
        }
        if (blk_new_backing) {
            new_backing_num_sectors = blk_nb_sectors(blk_new_backing);
            if (new_backing_num_sectors < 0) {
                error_report("Could not get size of '%s': %s",
                             out_baseimg, strerror(-new_backing_num_sectors));
                ret = -1;
                goto out;
            }
        }

        if (num_sectors != 0) {
            local_progress = (float)100 /
                (num_sectors / MIN(num_sectors, IO_BUF_SIZE / 512));
        }

        for (sector = 0; sector < num_sectors; sector += n) {

            /* How many sectors can we handle with the next read? */
            if (sector + (IO_BUF_SIZE / 512) <= num_sectors) {
                n = (IO_BUF_SIZE / 512);
            } else {
                n = num_sectors - sector;
            }

            /* If the cluster is allocated, we don't need to take action */
            ret = bdrv_is_allocated(bs, sector, n, &n);
            if (ret < 0) {
                error_report("error while reading image metadata: %s",
                             strerror(-ret));
                goto out;
            }
            if (ret) {
                continue;
            }

            /*
             * Read old and new backing file and take into consideration that
             * backing files may be smaller than the COW image.
             */
            if (sector >= old_backing_num_sectors) {
                memset(buf_old, 0, n * BDRV_SECTOR_SIZE);
            } else {
                if (sector + n > old_backing_num_sectors) {
                    n = old_backing_num_sectors - sector;
                }

                ret = blk_pread(blk_old_backing, sector << BDRV_SECTOR_BITS,
                                buf_old, n << BDRV_SECTOR_BITS);
                if (ret < 0) {
                    error_report("error while reading from old backing file");
                    goto out;
                }
            }

            if (sector >= new_backing_num_sectors || !blk_new_backing) {
                memset(buf_new, 0, n * BDRV_SECTOR_SIZE);
            } else {
                if (sector + n > new_backing_num_sectors) {
                    n = new_backing_num_sectors - sector;
                }

                ret = blk_pread(blk_new_backing, sector << BDRV_SECTOR_BITS,
                                buf_new, n << BDRV_SECTOR_BITS);
                if (ret < 0) {
                    error_report("error while reading from new backing file");
                    goto out;
                }
            }

            /* If they differ, we need to write to the COW file */
            uint64_t written = 0;

            while (written < n) {
                int pnum;

                if (compare_sectors(buf_old + written * 512,
                    buf_new + written * 512, n - written, &pnum))
                {
                    ret = blk_pwrite(blk,
                                     (sector + written) << BDRV_SECTOR_BITS,
                                     buf_old + written * 512,
                                     pnum << BDRV_SECTOR_BITS, 0);
                    if (ret < 0) {
                        error_report("Error while writing to COW image: %s",
                            strerror(-ret));
                        goto out;
                    }
                }

                written += pnum;
            }
            qemu_progress_print(local_progress, 100);
        }
    }

    /*
     * Change the backing file. All clusters that are different from the old
     * backing file are overwritten in the COW file now, so the visible content
     * doesn't change when we switch the backing file.
     */
    if (out_baseimg && *out_baseimg) {
        ret = bdrv_change_backing_file(bs, out_baseimg, out_basefmt);
    } else {
        ret = bdrv_change_backing_file(bs, NULL, NULL);
    }

    if (ret == -ENOSPC) {
        error_report("Could not change the backing file to '%s': No "
                     "space left in the file header", out_baseimg);
    } else if (ret < 0) {
        error_report("Could not change the backing file to '%s': %s",
            out_baseimg, strerror(-ret));
    }

    qemu_progress_print(100, 0);
    /*
     * TODO At this point it is possible to check if any clusters that are
     * allocated in the COW file are the same in the backing file. If so, they
     * could be dropped from the COW file. Don't do this before switching the
     * backing file, in case of a crash this would lead to corruption.
     */
out:
    qemu_progress_end();
    /* Cleanup */
    if (!unsafe) {
        blk_unref(blk_old_backing);
        blk_unref(blk_new_backing);
    }
    qemu_vfree(buf_old);
    qemu_vfree(buf_new);

    blk_unref(blk);
    if (ret) {
        return 1;
    }
    return 0;
}

static int img_resize(int argc, char **argv)
{
    Error *err = NULL;
    int c, ret, relative;
    const char *filename, *fmt, *size;
    int64_t n, total_size;
    bool quiet = false;
    BlockBackend *blk = NULL;
    QemuOpts *param;

    static QemuOptsList resize_options = {
        .name = "resize_options",
        .head = QTAILQ_HEAD_INITIALIZER(resize_options.head),
        .desc = {
            {
                .name = BLOCK_OPT_SIZE,
                .type = QEMU_OPT_SIZE,
                .help = "Virtual disk size"
            }, {
                /* end of list */
            }
        },
    };
    bool image_opts = false;

    /* Remove size from argv manually so that negative numbers are not treated
     * as options by getopt. */
    if (argc < 3) {
        error_exit("Not enough arguments");
        return 1;
    }

    size = argv[--argc];

    /* Parse getopt arguments */
    fmt = NULL;
    for(;;) {
        static const struct option long_options[] = {
            {"help", no_argument, 0, 'h'},
            {"object", required_argument, 0, OPTION_OBJECT},
            {"image-opts", no_argument, 0, OPTION_IMAGE_OPTS},
            {0, 0, 0, 0}
        };
        c = getopt_long(argc, argv, "f:hq",
                        long_options, NULL);
        if (c == -1) {
            break;
        }
        switch(c) {
        case '?':
        case 'h':
            help();
            break;
        case 'f':
            fmt = optarg;
            break;
        case 'q':
            quiet = true;
            break;
        case OPTION_OBJECT: {
            QemuOpts *opts;
            opts = qemu_opts_parse_noisily(&qemu_object_opts,
                                           optarg, true);
            if (!opts) {
                return 1;
            }
        }   break;
        case OPTION_IMAGE_OPTS:
            image_opts = true;
            break;
        }
    }
    if (optind != argc - 1) {
        error_exit("Expecting one image file name");
    }
    filename = argv[optind++];

    if (qemu_opts_foreach(&qemu_object_opts,
                          user_creatable_add_opts_foreach,
                          NULL, NULL)) {
        return 1;
    }

    /* Choose grow, shrink, or absolute resize mode */
    switch (size[0]) {
    case '+':
        relative = 1;
        size++;
        break;
    case '-':
        relative = -1;
        size++;
        break;
    default:
        relative = 0;
        break;
    }

    /* Parse size */
    param = qemu_opts_create(&resize_options, NULL, 0, &error_abort);
    qemu_opt_set(param, BLOCK_OPT_SIZE, size, &err);
    if (err) {
        error_report_err(err);
        ret = -1;
        qemu_opts_del(param);
        goto out;
    }
    n = qemu_opt_get_size(param, BLOCK_OPT_SIZE, 0);
    qemu_opts_del(param);

    blk = img_open(image_opts, filename, fmt,
                   BDRV_O_RDWR, false, quiet);
    if (!blk) {
        ret = -1;
        goto out;
    }

    if (relative) {
        total_size = blk_getlength(blk) + n * relative;
    } else {
        total_size = n;
    }
    if (total_size <= 0) {
        error_report("New image size must be positive");
        ret = -1;
        goto out;
    }

    ret = blk_truncate(blk, total_size);
    switch (ret) {
    case 0:
        qprintf(quiet, "Image resized.\n");
        break;
    case -ENOTSUP:
        error_report("This image does not support resize");
        break;
    case -EACCES:
        error_report("Image is read-only");
        break;
    default:
        error_report("Error resizing image: %s", strerror(-ret));
        break;
    }
out:
    blk_unref(blk);
    if (ret) {
        return 1;
    }
    return 0;
}

static void amend_status_cb(BlockDriverState *bs,
                            int64_t offset, int64_t total_work_size,
                            void *opaque)
{
    qemu_progress_print(100.f * offset / total_work_size, 0);
}

static int img_amend(int argc, char **argv)
{
    Error *err = NULL;
    int c, ret = 0;
    char *options = NULL;
    QemuOptsList *create_opts = NULL;
    QemuOpts *opts = NULL;
    const char *fmt = NULL, *filename, *cache;
    int flags;
    bool writethrough;
    bool quiet = false, progress = false;
    BlockBackend *blk = NULL;
    BlockDriverState *bs = NULL;
    bool image_opts = false;

    cache = BDRV_DEFAULT_CACHE;
    for (;;) {
        static const struct option long_options[] = {
            {"help", no_argument, 0, 'h'},
            {"object", required_argument, 0, OPTION_OBJECT},
            {"image-opts", no_argument, 0, OPTION_IMAGE_OPTS},
            {0, 0, 0, 0}
        };
        c = getopt_long(argc, argv, "ho:f:t:pq",
                        long_options, NULL);
        if (c == -1) {
            break;
        }

        switch (c) {
            case 'h':
            case '?':
                help();
                break;
            case 'o':
                if (!is_valid_option_list(optarg)) {
                    error_report("Invalid option list: %s", optarg);
                    ret = -1;
                    goto out_no_progress;
                }
                if (!options) {
                    options = g_strdup(optarg);
                } else {
                    char *old_options = options;
                    options = g_strdup_printf("%s,%s", options, optarg);
                    g_free(old_options);
                }
                break;
            case 'f':
                fmt = optarg;
                break;
            case 't':
                cache = optarg;
                break;
            case 'p':
                progress = true;
                break;
            case 'q':
                quiet = true;
                break;
            case OPTION_OBJECT:
                opts = qemu_opts_parse_noisily(&qemu_object_opts,
                                               optarg, true);
                if (!opts) {
                    ret = -1;
                    goto out_no_progress;
                }
                break;
            case OPTION_IMAGE_OPTS:
                image_opts = true;
                break;
        }
    }

    if (!options) {
        error_exit("Must specify options (-o)");
    }

    if (qemu_opts_foreach(&qemu_object_opts,
                          user_creatable_add_opts_foreach,
                          NULL, NULL)) {
        ret = -1;
        goto out_no_progress;
    }

    if (quiet) {
        progress = false;
    }
    qemu_progress_init(progress, 1.0);

    filename = (optind == argc - 1) ? argv[argc - 1] : NULL;
    if (fmt && has_help_option(options)) {
        /* If a format is explicitly specified (and possibly no filename is
         * given), print option help here */
        ret = print_block_option_help(filename, fmt);
        goto out;
    }

    if (optind != argc - 1) {
        error_report("Expecting one image file name");
        ret = -1;
        goto out;
    }

    flags = BDRV_O_RDWR;
    ret = bdrv_parse_cache_mode(cache, &flags, &writethrough);
    if (ret < 0) {
        error_report("Invalid cache option: %s", cache);
        goto out;
    }

    blk = img_open(image_opts, filename, fmt, flags, writethrough, quiet);
    if (!blk) {
        ret = -1;
        goto out;
    }
    bs = blk_bs(blk);

    fmt = bs->drv->format_name;

    if (has_help_option(options)) {
        /* If the format was auto-detected, print option help here */
        ret = print_block_option_help(filename, fmt);
        goto out;
    }

    if (!bs->drv->create_opts) {
        error_report("Format driver '%s' does not support any options to amend",
                     fmt);
        ret = -1;
        goto out;
    }

    create_opts = qemu_opts_append(create_opts, bs->drv->create_opts);
    opts = qemu_opts_create(create_opts, NULL, 0, &error_abort);
    if (options) {
        qemu_opts_do_parse(opts, options, NULL, &err);
        if (err) {
            error_report_err(err);
            ret = -1;
            goto out;
        }
    }

    /* In case the driver does not call amend_status_cb() */
    qemu_progress_print(0.f, 0);
    ret = bdrv_amend_options(bs, opts, &amend_status_cb, NULL);
    qemu_progress_print(100.f, 0);
    if (ret < 0) {
        error_report("Error while amending options: %s", strerror(-ret));
        goto out;
    }

out:
    qemu_progress_end();

out_no_progress:
    blk_unref(blk);
    qemu_opts_del(opts);
    qemu_opts_free(create_opts);
    g_free(options);

    if (ret) {
        return 1;
    }
    return 0;
}

typedef struct BenchData {
    BlockBackend *blk;
    uint64_t image_size;
    bool write;
    int bufsize;
    int step;
    int nrreq;
    int n;
    int flush_interval;
    bool drain_on_flush;
    uint8_t *buf;
    QEMUIOVector *qiov;

    int in_flight;
    bool in_flush;
    uint64_t offset;
} BenchData;

static void bench_undrained_flush_cb(void *opaque, int ret)
{
    if (ret < 0) {
        error_report("Failed flush request: %s", strerror(-ret));
        exit(EXIT_FAILURE);
    }
}

static void bench_cb(void *opaque, int ret)
{
    BenchData *b = opaque;
    BlockAIOCB *acb;

    if (ret < 0) {
        error_report("Failed request: %s", strerror(-ret));
        exit(EXIT_FAILURE);
    }

    if (b->in_flush) {
        /* Just finished a flush with drained queue: Start next requests */
        assert(b->in_flight == 0);
        b->in_flush = false;
    } else if (b->in_flight > 0) {
        int remaining = b->n - b->in_flight;

        b->n--;
        b->in_flight--;

        /* Time for flush? Drain queue if requested, then flush */
        if (b->flush_interval && remaining % b->flush_interval == 0) {
            if (!b->in_flight || !b->drain_on_flush) {
                BlockCompletionFunc *cb;

                if (b->drain_on_flush) {
                    b->in_flush = true;
                    cb = bench_cb;
                } else {
                    cb = bench_undrained_flush_cb;
                }

                acb = blk_aio_flush(b->blk, cb, b);
                if (!acb) {
                    error_report("Failed to issue flush request");
                    exit(EXIT_FAILURE);
                }
            }
            if (b->drain_on_flush) {
                return;
            }
        }
    }

    while (b->n > b->in_flight && b->in_flight < b->nrreq) {
        if (b->write) {
            acb = blk_aio_pwritev(b->blk, b->offset, b->qiov, 0,
                                  bench_cb, b);
        } else {
            acb = blk_aio_preadv(b->blk, b->offset, b->qiov, 0,
                                 bench_cb, b);
        }
        if (!acb) {
            error_report("Failed to issue request");
            exit(EXIT_FAILURE);
        }
        b->in_flight++;
        b->offset += b->step;
        b->offset %= b->image_size;
    }
}

static int img_bench(int argc, char **argv)
{
    int c, ret = 0;
    const char *fmt = NULL, *filename;
    bool quiet = false;
    bool image_opts = false;
    bool is_write = false;
    int count = 75000;
    int depth = 64;
    int64_t offset = 0;
    size_t bufsize = 4096;
    int pattern = 0;
    size_t step = 0;
    int flush_interval = 0;
    bool drain_on_flush = true;
    int64_t image_size;
    BlockBackend *blk = NULL;
    BenchData data = {};
    int flags = 0;
    bool writethrough = false;
    struct timeval t1, t2;
    int i;

    for (;;) {
        static const struct option long_options[] = {
            {"help", no_argument, 0, 'h'},
            {"flush-interval", required_argument, 0, OPTION_FLUSH_INTERVAL},
            {"image-opts", no_argument, 0, OPTION_IMAGE_OPTS},
            {"pattern", required_argument, 0, OPTION_PATTERN},
            {"no-drain", no_argument, 0, OPTION_NO_DRAIN},
            {0, 0, 0, 0}
        };
        c = getopt_long(argc, argv, "hc:d:f:no:qs:S:t:w", long_options, NULL);
        if (c == -1) {
            break;
        }

        switch (c) {
        case 'h':
        case '?':
            help();
            break;
        case 'c':
        {
            char *end;
            errno = 0;
            count = strtoul(optarg, &end, 0);
            if (errno || *end || count > INT_MAX) {
                error_report("Invalid request count specified");
                return 1;
            }
            break;
        }
        case 'd':
        {
            char *end;
            errno = 0;
            depth = strtoul(optarg, &end, 0);
            if (errno || *end || depth > INT_MAX) {
                error_report("Invalid queue depth specified");
                return 1;
            }
            break;
        }
        case 'f':
            fmt = optarg;
            break;
        case 'n':
            flags |= BDRV_O_NATIVE_AIO;
            break;
        case 'o':
        {
            char *end;
            errno = 0;
            offset = qemu_strtosz_suffix(optarg, &end,
                                         QEMU_STRTOSZ_DEFSUFFIX_B);
            if (offset < 0|| *end) {
                error_report("Invalid offset specified");
                return 1;
            }
            break;
        }
            break;
        case 'q':
            quiet = true;
            break;
        case 's':
        {
            int64_t sval;
            char *end;

            sval = qemu_strtosz_suffix(optarg, &end, QEMU_STRTOSZ_DEFSUFFIX_B);
            if (sval < 0 || sval > INT_MAX || *end) {
                error_report("Invalid buffer size specified");
                return 1;
            }

            bufsize = sval;
            break;
        }
        case 'S':
        {
            int64_t sval;
            char *end;

            sval = qemu_strtosz_suffix(optarg, &end, QEMU_STRTOSZ_DEFSUFFIX_B);
            if (sval < 0 || sval > INT_MAX || *end) {
                error_report("Invalid step size specified");
                return 1;
            }

            step = sval;
            break;
        }
        case 't':
            ret = bdrv_parse_cache_mode(optarg, &flags, &writethrough);
            if (ret < 0) {
                error_report("Invalid cache mode");
                ret = -1;
                goto out;
            }
            break;
        case 'w':
            flags |= BDRV_O_RDWR;
            is_write = true;
            break;
        case OPTION_PATTERN:
        {
            char *end;
            errno = 0;
            pattern = strtoul(optarg, &end, 0);
            if (errno || *end || pattern > 0xff) {
                error_report("Invalid pattern byte specified");
                return 1;
            }
            break;
        }
        case OPTION_FLUSH_INTERVAL:
        {
            char *end;
            errno = 0;
            flush_interval = strtoul(optarg, &end, 0);
            if (errno || *end || flush_interval > INT_MAX) {
                error_report("Invalid flush interval specified");
                return 1;
            }
            break;
        }
        case OPTION_NO_DRAIN:
            drain_on_flush = false;
            break;
        case OPTION_IMAGE_OPTS:
            image_opts = true;
            break;
        }
    }

    if (optind != argc - 1) {
        error_exit("Expecting one image file name");
    }
    filename = argv[argc - 1];

    if (!is_write && flush_interval) {
        error_report("--flush-interval is only available in write tests");
        ret = -1;
        goto out;
    }
    if (flush_interval && flush_interval < depth) {
        error_report("Flush interval can't be smaller than depth");
        ret = -1;
        goto out;
    }

    blk = img_open(image_opts, filename, fmt, flags, writethrough, quiet);
    if (!blk) {
        ret = -1;
        goto out;
    }

    image_size = blk_getlength(blk);
    if (image_size < 0) {
        ret = image_size;
        goto out;
    }

    data = (BenchData) {
        .blk            = blk,
        .image_size     = image_size,
        .bufsize        = bufsize,
        .step           = step ?: bufsize,
        .nrreq          = depth,
        .n              = count,
        .offset         = offset,
        .write          = is_write,
        .flush_interval = flush_interval,
        .drain_on_flush = drain_on_flush,
    };
    printf("Sending %d %s requests, %d bytes each, %d in parallel "
           "(starting at offset %" PRId64 ", step size %d)\n",
           data.n, data.write ? "write" : "read", data.bufsize, data.nrreq,
           data.offset, data.step);
    if (flush_interval) {
        printf("Sending flush every %d requests\n", flush_interval);
    }

    data.buf = blk_blockalign(blk, data.nrreq * data.bufsize);
    memset(data.buf, pattern, data.nrreq * data.bufsize);

    data.qiov = g_new(QEMUIOVector, data.nrreq);
    for (i = 0; i < data.nrreq; i++) {
        qemu_iovec_init(&data.qiov[i], 1);
        qemu_iovec_add(&data.qiov[i],
                       data.buf + i * data.bufsize, data.bufsize);
    }

    gettimeofday(&t1, NULL);
    bench_cb(&data, 0);

    while (data.n > 0) {
        main_loop_wait(false);
    }
    gettimeofday(&t2, NULL);

    printf("Run completed in %3.3f seconds.\n",
           (t2.tv_sec - t1.tv_sec)
           + ((double)(t2.tv_usec - t1.tv_usec) / 1000000));

out:
    qemu_vfree(data.buf);
    blk_unref(blk);

    if (ret) {
        return 1;
    }
    return 0;
}

#define C_BS      01
#define C_COUNT   02
#define C_IF      04
#define C_OF      010
#define C_SKIP    020

struct DdInfo {
    unsigned int flags;
    int64_t count;
};

struct DdIo {
    int bsz;    /* Block size */
    char *filename;
    uint8_t *buf;
    int64_t offset;
};

struct DdOpts {
    const char *name;
    int (*f)(const char *, struct DdIo *, struct DdIo *, struct DdInfo *);
    unsigned int flag;
};

static int img_dd_bs(const char *arg,
                     struct DdIo *in, struct DdIo *out,
                     struct DdInfo *dd)
{
    char *end;
    int64_t res;

    res = qemu_strtosz_suffix(arg, &end, QEMU_STRTOSZ_DEFSUFFIX_B);

    if (res <= 0 || res > INT_MAX || *end) {
        error_report("invalid number: '%s'", arg);
        return 1;
    }
    in->bsz = out->bsz = res;

    return 0;
}

static int img_dd_count(const char *arg,
                        struct DdIo *in, struct DdIo *out,
                        struct DdInfo *dd)
{
    char *end;

    dd->count = qemu_strtosz_suffix(arg, &end, QEMU_STRTOSZ_DEFSUFFIX_B);

    if (dd->count < 0 || *end) {
        error_report("invalid number: '%s'", arg);
        return 1;
    }

    return 0;
}

static int img_dd_if(const char *arg,
                     struct DdIo *in, struct DdIo *out,
                     struct DdInfo *dd)
{
    in->filename = g_strdup(arg);

    return 0;
}

static int img_dd_of(const char *arg,
                     struct DdIo *in, struct DdIo *out,
                     struct DdInfo *dd)
{
    out->filename = g_strdup(arg);

    return 0;
}

static int img_dd_skip(const char *arg,
                       struct DdIo *in, struct DdIo *out,
                       struct DdInfo *dd)
{
    char *end;

    in->offset = qemu_strtosz_suffix(arg, &end, QEMU_STRTOSZ_DEFSUFFIX_B);

    if (in->offset < 0 || *end) {
        error_report("invalid number: '%s'", arg);
        return 1;
    }

    return 0;
}

static int img_dd(int argc, char **argv)
{
    int ret = 0;
    char *arg = NULL;
    char *tmp;
    BlockDriver *drv = NULL, *proto_drv = NULL;
    BlockBackend *blk1 = NULL, *blk2 = NULL;
    QemuOpts *opts = NULL;
    QemuOptsList *create_opts = NULL;
    Error *local_err = NULL;
    bool image_opts = false;
    int c, i;
    const char *out_fmt = "raw";
    const char *fmt = NULL;
    int64_t size = 0;
    int64_t block_count = 0, out_pos, in_pos;
    struct DdInfo dd = {
        .flags = 0,
        .count = 0,
    };
    struct DdIo in = {