qemu-e2k/block/vpc.c

1255 lines
37 KiB
C
Raw Normal View History

/*
* Block driver for Connectix / Microsoft Virtual PC images
*
* Copyright (c) 2005 Alex Beregszaszi
* Copyright (c) 2009 Kevin Wolf <kwolf@suse.de>
*
* 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"
2016-03-14 09:01:28 +01:00
#include "qapi/error.h"
#include "block/block_int.h"
#include "block/qdict.h"
#include "sysemu/block-backend.h"
#include "qemu/module.h"
#include "qemu/option.h"
#include "migration/blocker.h"
#include "qemu/bswap.h"
#include "qemu/uuid.h"
#include "qapi/qmp/qdict.h"
#include "qapi/qobject-input-visitor.h"
#include "qapi/qapi-visit-block-core.h"
/**************************************************************/
//#define CACHE
enum vhd_type {
VHD_FIXED = 2,
VHD_DYNAMIC = 3,
VHD_DIFFERENCING = 4,
};
/* Seconds since Jan 1, 2000 0:00:00 (UTC) */
#define VHD_TIMESTAMP_BASE 946684800
#define VHD_CHS_MAX_C 65535LL
#define VHD_CHS_MAX_H 16
#define VHD_CHS_MAX_S 255
#define VHD_MAX_SECTORS 0xff000000 /* 2040 GiB max image size */
#define VHD_MAX_GEOMETRY (VHD_CHS_MAX_C * VHD_CHS_MAX_H * VHD_CHS_MAX_S)
#define VPC_OPT_FORCE_SIZE "force_size"
/* always big-endian */
typedef struct vhd_footer {
char creator[8]; /* "conectix" */
uint32_t features;
uint32_t version;
/* Offset of next header structure, 0xFFFFFFFF if none */
uint64_t data_offset;
/* Seconds since Jan 1, 2000 0:00:00 (UTC) */
uint32_t timestamp;
char creator_app[4]; /* e.g., "vpc " */
uint16_t major;
uint16_t minor;
char creator_os[4]; /* "Wi2k" */
uint64_t orig_size;
uint64_t current_size;
uint16_t cyls;
uint8_t heads;
uint8_t secs_per_cyl;
uint32_t type;
/* Checksum of the Hard Disk Footer ("one's complement of the sum of all
the bytes in the footer without the checksum field") */
uint32_t checksum;
/* UUID used to identify a parent hard disk (backing file) */
QemuUUID uuid;
uint8_t in_saved_state;
uint8_t reserved[427];
} QEMU_PACKED VHDFooter;
QEMU_BUILD_BUG_ON(sizeof(VHDFooter) != 512);
typedef struct vhd_dyndisk_header {
char magic[8]; /* "cxsparse" */
/* Offset of next header structure, 0xFFFFFFFF if none */
uint64_t data_offset;
/* Offset of the Block Allocation Table (BAT) */
uint64_t table_offset;
uint32_t version;
uint32_t max_table_entries; /* 32bit/entry */
/* 2 MB by default, must be a power of two */
uint32_t block_size;
uint32_t checksum;
uint8_t parent_uuid[16];
uint32_t parent_timestamp;
uint32_t reserved;
/* Backing file name (in UTF-16) */
uint8_t parent_name[512];
struct {
uint32_t platform;
uint32_t data_space;
uint32_t data_length;
uint32_t reserved;
uint64_t data_offset;
} parent_locator[8];
uint8_t reserved2[256];
} QEMU_PACKED VHDDynDiskHeader;
QEMU_BUILD_BUG_ON(sizeof(VHDDynDiskHeader) != 1024);
typedef struct BDRVVPCState {
CoMutex lock;
VHDFooter footer;
uint64_t free_data_block_offset;
int max_table_entries;
uint32_t *pagetable;
uint64_t bat_offset;
uint64_t last_bitmap_offset;
uint32_t block_size;
uint32_t bitmap_size;
block/vpc: choose size calculation method based on creator_app field The VHD file format is used by both Virtual PC, and Hyper-V. However, how the virtual disk size is calculated varies between the two. Virtual PC uses the CHS drive parameters to determine the drive size. Hyper-V, on the other hand, uses the current_size field in the footer when determining image size. This is problematic for a few reasons: * VHD images from Hyper-V, using CHS calculations, will likely be trunctated. * If we just rely always on current_size, then QEMU may have data compatibility issues with Virtual PC (we may write too much data into a VHD file to be used by Virtual PC, for instance). * Existing VHD images created by QEMU have used the CHS calculations, except for images exceeding the 127GB limit. We want to remain compatible with our own generated images. Luckily, the VHD specification defines a 'Creator App' field, that is used to indicate what software created the VHD file. This patch does two things: 1. Uses the 'Creator App' field to help determine how to calculate size, and 2. Adds a VPC format option 'force_size_calc', so that the user can override the 'Creator App' auto-detection, in case there exist VHD images with unknown or contradictory 'Creator App' entries. N.B.: We currently use the maximum CHS value as an indication to use the current_size field. This patch does not change that, even with the 'force_size_calc' option. Signed-off-by: Jeff Cody <jcody@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2016-02-25 18:27:27 +01:00
bool force_use_chs;
bool force_use_sz;
#ifdef CACHE
uint8_t *pageentry_u8;
uint32_t *pageentry_u32;
uint16_t *pageentry_u16;
uint64_t last_bitmap;
#endif
Error *migration_blocker;
} BDRVVPCState;
block/vpc: choose size calculation method based on creator_app field The VHD file format is used by both Virtual PC, and Hyper-V. However, how the virtual disk size is calculated varies between the two. Virtual PC uses the CHS drive parameters to determine the drive size. Hyper-V, on the other hand, uses the current_size field in the footer when determining image size. This is problematic for a few reasons: * VHD images from Hyper-V, using CHS calculations, will likely be trunctated. * If we just rely always on current_size, then QEMU may have data compatibility issues with Virtual PC (we may write too much data into a VHD file to be used by Virtual PC, for instance). * Existing VHD images created by QEMU have used the CHS calculations, except for images exceeding the 127GB limit. We want to remain compatible with our own generated images. Luckily, the VHD specification defines a 'Creator App' field, that is used to indicate what software created the VHD file. This patch does two things: 1. Uses the 'Creator App' field to help determine how to calculate size, and 2. Adds a VPC format option 'force_size_calc', so that the user can override the 'Creator App' auto-detection, in case there exist VHD images with unknown or contradictory 'Creator App' entries. N.B.: We currently use the maximum CHS value as an indication to use the current_size field. This patch does not change that, even with the 'force_size_calc' option. Signed-off-by: Jeff Cody <jcody@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2016-02-25 18:27:27 +01:00
#define VPC_OPT_SIZE_CALC "force_size_calc"
static QemuOptsList vpc_runtime_opts = {
.name = "vpc-runtime-opts",
.head = QTAILQ_HEAD_INITIALIZER(vpc_runtime_opts.head),
.desc = {
{
.name = VPC_OPT_SIZE_CALC,
.type = QEMU_OPT_STRING,
.help = "Force disk size calculation to use either CHS geometry, "
"or use the disk current_size specified in the VHD footer. "
"{chs, current_size}"
},
{ /* end of list */ }
}
};
static QemuOptsList vpc_create_opts;
static uint32_t vpc_checksum(void *p, size_t size)
{
uint8_t *buf = p;
uint32_t res = 0;
int i;
for (i = 0; i < size; i++)
res += buf[i];
return ~res;
}
static int vpc_probe(const uint8_t *buf, int buf_size, const char *filename)
{
if (buf_size >= 8 && !strncmp((char *)buf, "conectix", 8))
avoid TABs in files that only contain a few Most files that have TABs only contain a handful of them. Change them to spaces so that we don't confuse people. disas, standard-headers, linux-headers and libdecnumber are imported from other projects and probably should be exempted from the check. Outside those, after this patch the following files still contain both 8-space and TAB sequences at the beginning of the line. Many of them have a majority of TABs, or were initially committed with all tabs. bsd-user/i386/target_syscall.h bsd-user/x86_64/target_syscall.h crypto/aes.c hw/audio/fmopl.c hw/audio/fmopl.h hw/block/tc58128.c hw/display/cirrus_vga.c hw/display/xenfb.c hw/dma/etraxfs_dma.c hw/intc/sh_intc.c hw/misc/mst_fpga.c hw/net/pcnet.c hw/sh4/sh7750.c hw/timer/m48t59.c hw/timer/sh_timer.c include/crypto/aes.h include/disas/bfd.h include/hw/sh4/sh.h libdecnumber/decNumber.c linux-headers/asm-generic/unistd.h linux-headers/linux/kvm.h linux-user/alpha/target_syscall.h linux-user/arm/nwfpe/double_cpdo.c linux-user/arm/nwfpe/fpa11_cpdt.c linux-user/arm/nwfpe/fpa11_cprt.c linux-user/arm/nwfpe/fpa11.h linux-user/flat.h linux-user/flatload.c linux-user/i386/target_syscall.h linux-user/ppc/target_syscall.h linux-user/sparc/target_syscall.h linux-user/syscall.c linux-user/syscall_defs.h linux-user/x86_64/target_syscall.h slirp/cksum.c slirp/if.c slirp/ip.h slirp/ip_icmp.c slirp/ip_icmp.h slirp/ip_input.c slirp/ip_output.c slirp/mbuf.c slirp/misc.c slirp/sbuf.c slirp/socket.c slirp/socket.h slirp/tcp_input.c slirp/tcpip.h slirp/tcp_output.c slirp/tcp_subr.c slirp/tcp_timer.c slirp/tftp.c slirp/udp.c slirp/udp.h target/cris/cpu.h target/cris/mmu.c target/cris/op_helper.c target/sh4/helper.c target/sh4/op_helper.c target/sh4/translate.c tcg/sparc/tcg-target.inc.c tests/tcg/cris/check_addo.c tests/tcg/cris/check_moveq.c tests/tcg/cris/check_swap.c tests/tcg/multiarch/test-mmap.c ui/vnc-enc-hextile-template.h ui/vnc-enc-zywrle.h util/envlist.c util/readline.c The following have only TABs: bsd-user/i386/target_signal.h bsd-user/sparc64/target_signal.h bsd-user/sparc64/target_syscall.h bsd-user/sparc/target_signal.h bsd-user/sparc/target_syscall.h bsd-user/x86_64/target_signal.h crypto/desrfb.c hw/audio/intel-hda-defs.h hw/core/uboot_image.h hw/sh4/sh7750_regnames.c hw/sh4/sh7750_regs.h include/hw/cris/etraxfs_dma.h linux-user/alpha/termbits.h linux-user/arm/nwfpe/fpopcode.h linux-user/arm/nwfpe/fpsr.h linux-user/arm/syscall_nr.h linux-user/arm/target_signal.h linux-user/cris/target_signal.h linux-user/i386/target_signal.h linux-user/linux_loop.h linux-user/m68k/target_signal.h linux-user/microblaze/target_signal.h linux-user/mips64/target_signal.h linux-user/mips/target_signal.h linux-user/mips/target_syscall.h linux-user/mips/termbits.h linux-user/ppc/target_signal.h linux-user/sh4/target_signal.h linux-user/sh4/termbits.h linux-user/sparc64/target_syscall.h linux-user/sparc/target_signal.h linux-user/x86_64/target_signal.h linux-user/x86_64/termbits.h pc-bios/optionrom/optionrom.h slirp/mbuf.h slirp/misc.h slirp/sbuf.h slirp/tcp.h slirp/tcp_timer.h slirp/tcp_var.h target/i386/svm.h target/sparc/asi.h target/xtensa/core-dc232b/xtensa-modules.inc.c target/xtensa/core-dc233c/xtensa-modules.inc.c target/xtensa/core-de212/core-isa.h target/xtensa/core-de212/xtensa-modules.inc.c target/xtensa/core-fsf/xtensa-modules.inc.c target/xtensa/core-sample_controller/core-isa.h target/xtensa/core-sample_controller/xtensa-modules.inc.c target/xtensa/core-test_kc705_be/core-isa.h target/xtensa/core-test_kc705_be/xtensa-modules.inc.c tests/tcg/cris/check_abs.c tests/tcg/cris/check_addc.c tests/tcg/cris/check_addcm.c tests/tcg/cris/check_addoq.c tests/tcg/cris/check_bound.c tests/tcg/cris/check_ftag.c tests/tcg/cris/check_int64.c tests/tcg/cris/check_lz.c tests/tcg/cris/check_openpf5.c tests/tcg/cris/check_sigalrm.c tests/tcg/cris/crisutils.h tests/tcg/cris/sys.c tests/tcg/i386/test-i386-ssse3.c ui/vgafont.h Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20181213223737.11793-3-pbonzini@redhat.com> Reviewed-by: Aleksandar Markovic <amarkovic@wavecomp.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com> Acked-by: Richard Henderson <richard.henderson@linaro.org> Acked-by: Eric Blake <eblake@redhat.com> Acked-by: David Gibson <david@gibson.dropbear.id.au> Reviewed-by: Stefan Markovic <smarkovic@wavecomp.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2018-12-13 23:37:37 +01:00
return 100;
return 0;
}
block/vpc: choose size calculation method based on creator_app field The VHD file format is used by both Virtual PC, and Hyper-V. However, how the virtual disk size is calculated varies between the two. Virtual PC uses the CHS drive parameters to determine the drive size. Hyper-V, on the other hand, uses the current_size field in the footer when determining image size. This is problematic for a few reasons: * VHD images from Hyper-V, using CHS calculations, will likely be trunctated. * If we just rely always on current_size, then QEMU may have data compatibility issues with Virtual PC (we may write too much data into a VHD file to be used by Virtual PC, for instance). * Existing VHD images created by QEMU have used the CHS calculations, except for images exceeding the 127GB limit. We want to remain compatible with our own generated images. Luckily, the VHD specification defines a 'Creator App' field, that is used to indicate what software created the VHD file. This patch does two things: 1. Uses the 'Creator App' field to help determine how to calculate size, and 2. Adds a VPC format option 'force_size_calc', so that the user can override the 'Creator App' auto-detection, in case there exist VHD images with unknown or contradictory 'Creator App' entries. N.B.: We currently use the maximum CHS value as an indication to use the current_size field. This patch does not change that, even with the 'force_size_calc' option. Signed-off-by: Jeff Cody <jcody@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2016-02-25 18:27:27 +01:00
static void vpc_parse_options(BlockDriverState *bs, QemuOpts *opts,
Error **errp)
{
BDRVVPCState *s = bs->opaque;
const char *size_calc;
size_calc = qemu_opt_get(opts, VPC_OPT_SIZE_CALC);
if (!size_calc) {
/* no override, use autodetect only */
} else if (!strcmp(size_calc, "current_size")) {
s->force_use_sz = true;
} else if (!strcmp(size_calc, "chs")) {
s->force_use_chs = true;
} else {
error_setg(errp, "Invalid size calculation mode: '%s'", size_calc);
}
}
static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
BDRVVPCState *s = bs->opaque;
int i;
VHDFooter *footer;
block/vpc: choose size calculation method based on creator_app field The VHD file format is used by both Virtual PC, and Hyper-V. However, how the virtual disk size is calculated varies between the two. Virtual PC uses the CHS drive parameters to determine the drive size. Hyper-V, on the other hand, uses the current_size field in the footer when determining image size. This is problematic for a few reasons: * VHD images from Hyper-V, using CHS calculations, will likely be trunctated. * If we just rely always on current_size, then QEMU may have data compatibility issues with Virtual PC (we may write too much data into a VHD file to be used by Virtual PC, for instance). * Existing VHD images created by QEMU have used the CHS calculations, except for images exceeding the 127GB limit. We want to remain compatible with our own generated images. Luckily, the VHD specification defines a 'Creator App' field, that is used to indicate what software created the VHD file. This patch does two things: 1. Uses the 'Creator App' field to help determine how to calculate size, and 2. Adds a VPC format option 'force_size_calc', so that the user can override the 'Creator App' auto-detection, in case there exist VHD images with unknown or contradictory 'Creator App' entries. N.B.: We currently use the maximum CHS value as an indication to use the current_size field. This patch does not change that, even with the 'force_size_calc' option. Signed-off-by: Jeff Cody <jcody@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2016-02-25 18:27:27 +01:00
QemuOpts *opts = NULL;
Error *local_err = NULL;
bool use_chs;
VHDDynDiskHeader dyndisk_header;
uint32_t checksum;
uint64_t computed_size;
uint64_t pagetable_size;
int disk_type = VHD_DYNAMIC;
int ret;
int64_t bs_size;
bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds,
BDRV_CHILD_IMAGE, false, errp);
if (!bs->file) {
return -EINVAL;
}
block/vpc: choose size calculation method based on creator_app field The VHD file format is used by both Virtual PC, and Hyper-V. However, how the virtual disk size is calculated varies between the two. Virtual PC uses the CHS drive parameters to determine the drive size. Hyper-V, on the other hand, uses the current_size field in the footer when determining image size. This is problematic for a few reasons: * VHD images from Hyper-V, using CHS calculations, will likely be trunctated. * If we just rely always on current_size, then QEMU may have data compatibility issues with Virtual PC (we may write too much data into a VHD file to be used by Virtual PC, for instance). * Existing VHD images created by QEMU have used the CHS calculations, except for images exceeding the 127GB limit. We want to remain compatible with our own generated images. Luckily, the VHD specification defines a 'Creator App' field, that is used to indicate what software created the VHD file. This patch does two things: 1. Uses the 'Creator App' field to help determine how to calculate size, and 2. Adds a VPC format option 'force_size_calc', so that the user can override the 'Creator App' auto-detection, in case there exist VHD images with unknown or contradictory 'Creator App' entries. N.B.: We currently use the maximum CHS value as an indication to use the current_size field. This patch does not change that, even with the 'force_size_calc' option. Signed-off-by: Jeff Cody <jcody@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2016-02-25 18:27:27 +01:00
opts = qemu_opts_create(&vpc_runtime_opts, NULL, 0, &error_abort);
if (!qemu_opts_absorb_qdict(opts, options, errp)) {
block/vpc: choose size calculation method based on creator_app field The VHD file format is used by both Virtual PC, and Hyper-V. However, how the virtual disk size is calculated varies between the two. Virtual PC uses the CHS drive parameters to determine the drive size. Hyper-V, on the other hand, uses the current_size field in the footer when determining image size. This is problematic for a few reasons: * VHD images from Hyper-V, using CHS calculations, will likely be trunctated. * If we just rely always on current_size, then QEMU may have data compatibility issues with Virtual PC (we may write too much data into a VHD file to be used by Virtual PC, for instance). * Existing VHD images created by QEMU have used the CHS calculations, except for images exceeding the 127GB limit. We want to remain compatible with our own generated images. Luckily, the VHD specification defines a 'Creator App' field, that is used to indicate what software created the VHD file. This patch does two things: 1. Uses the 'Creator App' field to help determine how to calculate size, and 2. Adds a VPC format option 'force_size_calc', so that the user can override the 'Creator App' auto-detection, in case there exist VHD images with unknown or contradictory 'Creator App' entries. N.B.: We currently use the maximum CHS value as an indication to use the current_size field. This patch does not change that, even with the 'force_size_calc' option. Signed-off-by: Jeff Cody <jcody@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2016-02-25 18:27:27 +01:00
ret = -EINVAL;
goto fail;
}
vpc_parse_options(bs, opts, &local_err);
if (local_err) {
error_propagate(errp, local_err);
ret = -EINVAL;
goto fail;
}
ret = bdrv_pread(bs->file, 0, &s->footer, sizeof(s->footer));
if (ret < 0) {
error_setg(errp, "Unable to read VHD header");
goto fail;
}
footer = &s->footer;
if (strncmp(footer->creator, "conectix", 8)) {
int64_t offset = bdrv_getlength(bs->file->bs);
if (offset < 0) {
ret = offset;
error_setg(errp, "Invalid file size");
goto fail;
} else if (offset < sizeof(*footer)) {
ret = -EINVAL;
error_setg(errp, "File too small for a VHD header");
goto fail;
}
/* If a fixed disk, the footer is found only at the end of the file */
ret = bdrv_pread(bs->file, offset - sizeof(*footer),
footer, sizeof(*footer));
if (ret < 0) {
goto fail;
}
if (strncmp(footer->creator, "conectix", 8)) {
error_setg(errp, "invalid VPC image");
ret = -EINVAL;
goto fail;
}
disk_type = VHD_FIXED;
}
checksum = be32_to_cpu(footer->checksum);
footer->checksum = 0;
if (vpc_checksum(footer, sizeof(*footer)) != checksum) {
error_setg(errp, "Incorrect header checksum");
ret = -EINVAL;
goto fail;
}
/* Write 'checksum' back to footer, or else will leave it with zero. */
footer->checksum = cpu_to_be32(checksum);
/* The visible size of a image in Virtual PC depends on the geometry
rather than on the size stored in the footer (the size in the footer
is too large usually) */
bs->total_sectors = (int64_t)
be16_to_cpu(footer->cyls) * footer->heads * footer->secs_per_cyl;
block/vpc: choose size calculation method based on creator_app field The VHD file format is used by both Virtual PC, and Hyper-V. However, how the virtual disk size is calculated varies between the two. Virtual PC uses the CHS drive parameters to determine the drive size. Hyper-V, on the other hand, uses the current_size field in the footer when determining image size. This is problematic for a few reasons: * VHD images from Hyper-V, using CHS calculations, will likely be trunctated. * If we just rely always on current_size, then QEMU may have data compatibility issues with Virtual PC (we may write too much data into a VHD file to be used by Virtual PC, for instance). * Existing VHD images created by QEMU have used the CHS calculations, except for images exceeding the 127GB limit. We want to remain compatible with our own generated images. Luckily, the VHD specification defines a 'Creator App' field, that is used to indicate what software created the VHD file. This patch does two things: 1. Uses the 'Creator App' field to help determine how to calculate size, and 2. Adds a VPC format option 'force_size_calc', so that the user can override the 'Creator App' auto-detection, in case there exist VHD images with unknown or contradictory 'Creator App' entries. N.B.: We currently use the maximum CHS value as an indication to use the current_size field. This patch does not change that, even with the 'force_size_calc' option. Signed-off-by: Jeff Cody <jcody@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2016-02-25 18:27:27 +01:00
/* Microsoft Virtual PC and Microsoft Hyper-V produce and read
* VHD image sizes differently. VPC will rely on CHS geometry,
* while Hyper-V and disk2vhd use the size specified in the footer.
*
* We use a couple of approaches to try and determine the correct method:
* look at the Creator App field, and look for images that have CHS
* geometry that is the maximum value.
*
* If the CHS geometry is the maximum CHS geometry, then we assume that
* the size is the footer->current_size to avoid truncation. Otherwise,
* we follow the table based on footer->creator_app:
*
* Known creator apps:
* 'vpc ' : CHS Virtual PC (uses disk geometry)
* 'qemu' : CHS QEMU (uses disk geometry)
* 'qem2' : current_size QEMU (uses current_size)
block/vpc: choose size calculation method based on creator_app field The VHD file format is used by both Virtual PC, and Hyper-V. However, how the virtual disk size is calculated varies between the two. Virtual PC uses the CHS drive parameters to determine the drive size. Hyper-V, on the other hand, uses the current_size field in the footer when determining image size. This is problematic for a few reasons: * VHD images from Hyper-V, using CHS calculations, will likely be trunctated. * If we just rely always on current_size, then QEMU may have data compatibility issues with Virtual PC (we may write too much data into a VHD file to be used by Virtual PC, for instance). * Existing VHD images created by QEMU have used the CHS calculations, except for images exceeding the 127GB limit. We want to remain compatible with our own generated images. Luckily, the VHD specification defines a 'Creator App' field, that is used to indicate what software created the VHD file. This patch does two things: 1. Uses the 'Creator App' field to help determine how to calculate size, and 2. Adds a VPC format option 'force_size_calc', so that the user can override the 'Creator App' auto-detection, in case there exist VHD images with unknown or contradictory 'Creator App' entries. N.B.: We currently use the maximum CHS value as an indication to use the current_size field. This patch does not change that, even with the 'force_size_calc' option. Signed-off-by: Jeff Cody <jcody@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2016-02-25 18:27:27 +01:00
* 'win ' : current_size Hyper-V
* 'd2v ' : current_size Disk2vhd
* 'tap\0' : current_size XenServer
* 'CTXS' : current_size XenConverter
block/vpc: choose size calculation method based on creator_app field The VHD file format is used by both Virtual PC, and Hyper-V. However, how the virtual disk size is calculated varies between the two. Virtual PC uses the CHS drive parameters to determine the drive size. Hyper-V, on the other hand, uses the current_size field in the footer when determining image size. This is problematic for a few reasons: * VHD images from Hyper-V, using CHS calculations, will likely be trunctated. * If we just rely always on current_size, then QEMU may have data compatibility issues with Virtual PC (we may write too much data into a VHD file to be used by Virtual PC, for instance). * Existing VHD images created by QEMU have used the CHS calculations, except for images exceeding the 127GB limit. We want to remain compatible with our own generated images. Luckily, the VHD specification defines a 'Creator App' field, that is used to indicate what software created the VHD file. This patch does two things: 1. Uses the 'Creator App' field to help determine how to calculate size, and 2. Adds a VPC format option 'force_size_calc', so that the user can override the 'Creator App' auto-detection, in case there exist VHD images with unknown or contradictory 'Creator App' entries. N.B.: We currently use the maximum CHS value as an indication to use the current_size field. This patch does not change that, even with the 'force_size_calc' option. Signed-off-by: Jeff Cody <jcody@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2016-02-25 18:27:27 +01:00
*
* The user can override the table values via drive options, however
* even with an override we will still use current_size for images
* that have CHS geometry of the maximum size.
*/
use_chs = (!!strncmp(footer->creator_app, "win ", 4) &&
!!strncmp(footer->creator_app, "qem2", 4) &&
!!strncmp(footer->creator_app, "d2v ", 4) &&
!!strncmp(footer->creator_app, "CTXS", 4) &&
!!memcmp(footer->creator_app, "tap", 4)) || s->force_use_chs;
block/vpc: choose size calculation method based on creator_app field The VHD file format is used by both Virtual PC, and Hyper-V. However, how the virtual disk size is calculated varies between the two. Virtual PC uses the CHS drive parameters to determine the drive size. Hyper-V, on the other hand, uses the current_size field in the footer when determining image size. This is problematic for a few reasons: * VHD images from Hyper-V, using CHS calculations, will likely be trunctated. * If we just rely always on current_size, then QEMU may have data compatibility issues with Virtual PC (we may write too much data into a VHD file to be used by Virtual PC, for instance). * Existing VHD images created by QEMU have used the CHS calculations, except for images exceeding the 127GB limit. We want to remain compatible with our own generated images. Luckily, the VHD specification defines a 'Creator App' field, that is used to indicate what software created the VHD file. This patch does two things: 1. Uses the 'Creator App' field to help determine how to calculate size, and 2. Adds a VPC format option 'force_size_calc', so that the user can override the 'Creator App' auto-detection, in case there exist VHD images with unknown or contradictory 'Creator App' entries. N.B.: We currently use the maximum CHS value as an indication to use the current_size field. This patch does not change that, even with the 'force_size_calc' option. Signed-off-by: Jeff Cody <jcody@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2016-02-25 18:27:27 +01:00
if (!use_chs || bs->total_sectors == VHD_MAX_GEOMETRY || s->force_use_sz) {
bs->total_sectors = be64_to_cpu(footer->current_size) /
block/vpc: choose size calculation method based on creator_app field The VHD file format is used by both Virtual PC, and Hyper-V. However, how the virtual disk size is calculated varies between the two. Virtual PC uses the CHS drive parameters to determine the drive size. Hyper-V, on the other hand, uses the current_size field in the footer when determining image size. This is problematic for a few reasons: * VHD images from Hyper-V, using CHS calculations, will likely be trunctated. * If we just rely always on current_size, then QEMU may have data compatibility issues with Virtual PC (we may write too much data into a VHD file to be used by Virtual PC, for instance). * Existing VHD images created by QEMU have used the CHS calculations, except for images exceeding the 127GB limit. We want to remain compatible with our own generated images. Luckily, the VHD specification defines a 'Creator App' field, that is used to indicate what software created the VHD file. This patch does two things: 1. Uses the 'Creator App' field to help determine how to calculate size, and 2. Adds a VPC format option 'force_size_calc', so that the user can override the 'Creator App' auto-detection, in case there exist VHD images with unknown or contradictory 'Creator App' entries. N.B.: We currently use the maximum CHS value as an indication to use the current_size field. This patch does not change that, even with the 'force_size_calc' option. Signed-off-by: Jeff Cody <jcody@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2016-02-25 18:27:27 +01:00
BDRV_SECTOR_SIZE;
}
/* Allow a maximum disk size of 2040 GiB */
if (bs->total_sectors > VHD_MAX_SECTORS) {
ret = -EFBIG;
block/vpc.c: Detect too-large vpc file VHD files technically can be up to 2Tb, but virtual pc is limited to 127G. Currently qemu-img refused to create vpc files > 127G, but it is failing to return error when converting from a non-vpc VHD file which is >127G. It returns success, but creates a truncated converted image. Also, qemu-img info claims the vpc file is 127G (and clean). This patch detects a too-large vpc file and returns -EFBIG. Without this patch, ============================================================= root@ip-10-38-123-242:~/qemu-fixed# qemu-img info /mnt/140g-dynamic.vhd image: /mnt/140g-dynamic.vhd file format: vpc virtual size: 127G (136899993600 bytes) disk size: 284K root@ip-10-38-123-242:~/qemu-fixed# qemu-img convert -f vpc -O raw /mnt/140g-dynamic.vhd /mnt/y root@ip-10-38-123-242:~/qemu-fixed# echo $? 0 root@ip-10-38-123-242:~/qemu-fixed# qemu-img info /mnt/y image: /mnt/y file format: raw virtual size: 127G (136899993600 bytes) disk size: 0 ============================================================= (The 140G image was truncated with no warning or error.) With the patch, I get: ============================================================= root@ip-10-38-123-242:~/qemu-fixed# ./qemu-img info /mnt/140g-dynamic.vhd qemu-img: Could not open '/mnt/140g-dynamic.vhd': File too large root@ip-10-38-123-242:~/qemu-fixed# ./qemu-img convert -f vpc -O raw /mnt/140g-dynamic.vhd /mnt/y qemu-img: Could not open '/mnt/140g-dynamic.vhd': File too large qemu-img: Could not open '/mnt/140g-dynamic.vhd' ============================================================= See https://bugs.launchpad.net/qemu/+bug/814222 for details. Signed-off-by: Serge Hallyn <serge.hallyn@canonical.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2011-07-25 20:34:35 +02:00
goto fail;
}
if (disk_type == VHD_DYNAMIC) {
ret = bdrv_pread(bs->file, be64_to_cpu(footer->data_offset),
&dyndisk_header, sizeof(dyndisk_header));
if (ret < 0) {
error_setg(errp, "Error reading dynamic VHD header");
goto fail;
}
if (strncmp(dyndisk_header.magic, "cxsparse", 8)) {
error_setg(errp, "Invalid header magic");
ret = -EINVAL;
goto fail;
}
s->block_size = be32_to_cpu(dyndisk_header.block_size);
if (!is_power_of_2(s->block_size) || s->block_size < BDRV_SECTOR_SIZE) {
error_setg(errp, "Invalid block size %" PRIu32, s->block_size);
ret = -EINVAL;
goto fail;
}
s->bitmap_size = ((s->block_size / (8 * 512)) + 511) & ~511;
s->max_table_entries = be32_to_cpu(dyndisk_header.max_table_entries);
if ((bs->total_sectors * 512) / s->block_size > 0xffffffffU) {
error_setg(errp, "Too many blocks");
ret = -EINVAL;
goto fail;
}
computed_size = (uint64_t) s->max_table_entries * s->block_size;
if (computed_size < bs->total_sectors * 512) {
error_setg(errp, "Page table too small");
ret = -EINVAL;
goto fail;
}
if (s->max_table_entries > SIZE_MAX / 4 ||
s->max_table_entries > (int) INT_MAX / 4) {
error_setg(errp, "Max Table Entries too large (%" PRId32 ")",
s->max_table_entries);
ret = -EINVAL;
goto fail;
}
pagetable_size = (uint64_t) s->max_table_entries * 4;
s->pagetable = qemu_try_blockalign(bs->file->bs, pagetable_size);
if (s->pagetable == NULL) {
error_setg(errp, "Unable to allocate memory for page table");
ret = -ENOMEM;
goto fail;
}
s->bat_offset = be64_to_cpu(dyndisk_header.table_offset);
ret = bdrv_pread(bs->file, s->bat_offset, s->pagetable,
pagetable_size);
if (ret < 0) {
error_setg(errp, "Error reading pagetable");
goto fail;
}
s->free_data_block_offset =
ROUND_UP(s->bat_offset + pagetable_size, 512);
for (i = 0; i < s->max_table_entries; i++) {
be32_to_cpus(&s->pagetable[i]);
if (s->pagetable[i] != 0xFFFFFFFF) {
int64_t next = (512 * (int64_t) s->pagetable[i]) +
s->bitmap_size + s->block_size;
if (next > s->free_data_block_offset) {
s->free_data_block_offset = next;
}
}
}
bs_size = bdrv_getlength(bs->file->bs);
if (bs_size < 0) {
error_setg_errno(errp, -bs_size, "Unable to learn image size");
ret = bs_size;
goto fail;
}
if (s->free_data_block_offset > bs_size) {
error_setg(errp, "block-vpc: free_data_block_offset points after "
"the end of file. The image has been truncated.");
ret = -EINVAL;
goto fail;
}
s->last_bitmap_offset = (int64_t) -1;
#ifdef CACHE
s->pageentry_u8 = g_malloc(512);
s->pageentry_u32 = s->pageentry_u8;
s->pageentry_u16 = s->pageentry_u8;
s->last_pagetable = -1;
#endif
}
/* Disable migration when VHD images are used */
error_setg(&s->migration_blocker, "The vpc format used by node '%s' "
"does not support live migration",
bdrv_get_device_or_node_name(bs));
ret = migrate_add_blocker(s->migration_blocker, errp);
if (ret < 0) {
error_free(s->migration_blocker);
goto fail;
}
qemu_co_mutex_init(&s->lock);
qemu_opts_del(opts);
return 0;
fail:
qemu_opts_del(opts);
qemu_vfree(s->pagetable);
#ifdef CACHE
g_free(s->pageentry_u8);
#endif
return ret;
}
static int vpc_reopen_prepare(BDRVReopenState *state,
BlockReopenQueue *queue, Error **errp)
{
return 0;
}
/*
* Returns the absolute byte offset of the given sector in the image file.
* If the sector is not allocated, -1 is returned instead.
* If an error occurred trying to write an updated block bitmap back to
* the file, -2 is returned, and the error value is written to *err.
* This can only happen for a write operation.
*
* The parameter write must be 1 if the offset will be used for a write
* operation (the block bitmaps is updated then), 0 otherwise.
* If write is true then err must not be NULL.
*/
static inline int64_t get_image_offset(BlockDriverState *bs, uint64_t offset,
bool write, int *err)
{
BDRVVPCState *s = bs->opaque;
uint64_t bitmap_offset, block_offset;
uint32_t pagetable_index, offset_in_block;
assert(!(write && err == NULL));
pagetable_index = offset / s->block_size;
offset_in_block = offset % s->block_size;
if (pagetable_index >= s->max_table_entries || s->pagetable[pagetable_index] == 0xffffffff)
return -1; /* not allocated */
bitmap_offset = 512 * (uint64_t) s->pagetable[pagetable_index];
block_offset = bitmap_offset + s->bitmap_size + offset_in_block;
/* We must ensure that we don't write to any sectors which are marked as
unused in the bitmap. We get away with setting all bits in the block
bitmap each time we write to a new block. This might cause Virtual PC to
miss sparse read optimization, but it's not a problem in terms of
correctness. */
if (write && (s->last_bitmap_offset != bitmap_offset)) {
uint8_t bitmap[s->bitmap_size];
int r;
s->last_bitmap_offset = bitmap_offset;
memset(bitmap, 0xff, s->bitmap_size);
r = bdrv_pwrite_sync(bs->file, bitmap_offset, bitmap, s->bitmap_size);
if (r < 0) {
*err = r;
return -2;
}
}
return block_offset;
}
/*
* Writes the footer to the end of the image file. This is needed when the
* file grows as it overwrites the old footer
*
* Returns 0 on success and < 0 on error
*/
static int rewrite_footer(BlockDriverState *bs)
{
int ret;
BDRVVPCState *s = bs->opaque;
int64_t offset = s->free_data_block_offset;
ret = bdrv_pwrite_sync(bs->file, offset, &s->footer, sizeof(s->footer));
if (ret < 0)
return ret;
return 0;
}
/*
* Allocates a new block. This involves writing a new footer and updating
* the Block Allocation Table to use the space at the old end of the image
* file (overwriting the old footer)
*
* Returns the sectors' offset in the image file on success and < 0 on error
*/
static int64_t alloc_block(BlockDriverState *bs, int64_t offset)
{
BDRVVPCState *s = bs->opaque;
int64_t bat_offset;
uint32_t index, bat_value;
int ret;
uint8_t bitmap[s->bitmap_size];
/* Check if sector_num is valid */
if ((offset < 0) || (offset > bs->total_sectors * BDRV_SECTOR_SIZE)) {
return -EINVAL;
}
/* Write entry into in-memory BAT */
index = offset / s->block_size;
assert(s->pagetable[index] == 0xFFFFFFFF);
s->pagetable[index] = s->free_data_block_offset / 512;
/* Initialize the block's bitmap */
memset(bitmap, 0xff, s->bitmap_size);
ret = bdrv_pwrite_sync(bs->file, s->free_data_block_offset, bitmap,
s->bitmap_size);
if (ret < 0) {
return ret;
}
/* Write new footer (the old one will be overwritten) */
s->free_data_block_offset += s->block_size + s->bitmap_size;
ret = rewrite_footer(bs);
if (ret < 0)
goto fail;
/* Write BAT entry to disk */
bat_offset = s->bat_offset + (4 * index);
bat_value = cpu_to_be32(s->pagetable[index]);
ret = bdrv_pwrite_sync(bs->file, bat_offset, &bat_value, 4);
if (ret < 0)
goto fail;
return get_image_offset(bs, offset, false, NULL);
fail:
s->free_data_block_offset -= (s->block_size + s->bitmap_size);
return ret;
}
static int vpc_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
{
BDRVVPCState *s = (BDRVVPCState *)bs->opaque;
if (be32_to_cpu(s->footer.type) != VHD_FIXED) {
bdi->cluster_size = s->block_size;
}
return 0;
}
static int coroutine_fn
block: use int64_t instead of uint64_t in driver read handlers We are generally moving to int64_t for both offset and bytes parameters on all io paths. Main motivation is realization of 64-bit write_zeroes operation for fast zeroing large disk chunks, up to the whole disk. We chose signed type, to be consistent with off_t (which is signed) and with possibility for signed return type (where negative value means error). So, convert driver read handlers parameters which are already 64bit to signed type. While being here, convert also flags parameter to be BdrvRequestFlags. Now let's consider all callers. Simple git grep '\->bdrv_\(aio\|co\)_preadv\(_part\)\?' shows that's there three callers of driver function: bdrv_driver_preadv() in block/io.c, passes int64_t, checked by bdrv_check_qiov_request() to be non-negative. qcow2_load_vmstate() does bdrv_check_qiov_request(). do_perform_cow_read() has uint64_t argument. And a lot of things in qcow2 driver are uint64_t, so converting it is big job. But we must not work with requests that don't satisfy bdrv_check_qiov_request(), so let's just assert it here. Still, the functions may be called directly, not only by drv->... Let's check: git grep '\.bdrv_\(aio\|co\)_preadv\(_part\)\?\s*=' | \ awk '{print $4}' | sed 's/,//' | sed 's/&//' | sort | uniq | \ while read func; do git grep "$func(" | \ grep -v "$func(BlockDriverState"; done The only one such caller: QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, &data, 1); ... ret = bdrv_replace_test_co_preadv(bs, 0, 1, &qiov, 0); in tests/unit/test-bdrv-drain.c, and it's OK obviously. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20210903102807.27127-4-vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> [eblake: fix typos] Signed-off-by: Eric Blake <eblake@redhat.com>
2021-09-03 12:27:59 +02:00
vpc_co_preadv(BlockDriverState *bs, int64_t offset, int64_t bytes,
QEMUIOVector *qiov, BdrvRequestFlags flags)
{
BDRVVPCState *s = bs->opaque;
int ret;
int64_t image_offset;
int64_t n_bytes;
int64_t bytes_done = 0;
QEMUIOVector local_qiov;
if (be32_to_cpu(s->footer.type) == VHD_FIXED) {
return bdrv_co_preadv(bs->file, offset, bytes, qiov, 0);
}
qemu_co_mutex_lock(&s->lock);
qemu_iovec_init(&local_qiov, qiov->niov);
while (bytes > 0) {
image_offset = get_image_offset(bs, offset, false, NULL);
n_bytes = MIN(bytes, s->block_size - (offset % s->block_size));
if (image_offset == -1) {
qemu_iovec_memset(qiov, bytes_done, 0, n_bytes);
} else {
qemu_iovec_reset(&local_qiov);
qemu_iovec_concat(&local_qiov, qiov, bytes_done, n_bytes);
qemu_co_mutex_unlock(&s->lock);
ret = bdrv_co_preadv(bs->file, image_offset, n_bytes,
&local_qiov, 0);
qemu_co_mutex_lock(&s->lock);
if (ret < 0) {
goto fail;
}
}
bytes -= n_bytes;
offset += n_bytes;
bytes_done += n_bytes;
}
ret = 0;
fail:
qemu_iovec_destroy(&local_qiov);
qemu_co_mutex_unlock(&s->lock);
return ret;
}
static int coroutine_fn
block: use int64_t instead of uint64_t in driver write handlers We are generally moving to int64_t for both offset and bytes parameters on all io paths. Main motivation is realization of 64-bit write_zeroes operation for fast zeroing large disk chunks, up to the whole disk. We chose signed type, to be consistent with off_t (which is signed) and with possibility for signed return type (where negative value means error). So, convert driver write handlers parameters which are already 64bit to signed type. While being here, convert also flags parameter to be BdrvRequestFlags. Now let's consider all callers. Simple git grep '\->bdrv_\(aio\|co\)_pwritev\(_part\)\?' shows that's there three callers of driver function: bdrv_driver_pwritev() and bdrv_driver_pwritev_compressed() in block/io.c, both pass int64_t, checked by bdrv_check_qiov_request() to be non-negative. qcow2_save_vmstate() does bdrv_check_qiov_request(). Still, the functions may be called directly, not only by drv->... Let's check: git grep '\.bdrv_\(aio\|co\)_pwritev\(_part\)\?\s*=' | \ awk '{print $4}' | sed 's/,//' | sed 's/&//' | sort | uniq | \ while read func; do git grep "$func(" | \ grep -v "$func(BlockDriverState"; done shows several callers: qcow2: qcow2_co_truncate() write at most up to @offset, which is checked in generic qcow2_co_truncate() by bdrv_check_request(). qcow2_co_pwritev_compressed_task() pass the request (or part of the request) that already went through normal write path, so it should be OK qcow: qcow_co_pwritev_compressed() pass int64_t, it's updated by this patch quorum: quorum_co_pwrite_zeroes() pass int64_t and int - OK throttle: throttle_co_pwritev_compressed() pass int64_t, it's updated by this patch vmdk: vmdk_co_pwritev_compressed() pass int64_t, it's updated by this patch Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20210903102807.27127-5-vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Eric Blake <eblake@redhat.com>
2021-09-03 12:28:00 +02:00
vpc_co_pwritev(BlockDriverState *bs, int64_t offset, int64_t bytes,
QEMUIOVector *qiov, BdrvRequestFlags flags)
{
BDRVVPCState *s = bs->opaque;
int64_t image_offset;
int64_t n_bytes;
int64_t bytes_done = 0;
int ret = 0;
QEMUIOVector local_qiov;
if (be32_to_cpu(s->footer.type) == VHD_FIXED) {
return bdrv_co_pwritev(bs->file, offset, bytes, qiov, 0);
}
qemu_co_mutex_lock(&s->lock);
qemu_iovec_init(&local_qiov, qiov->niov);
while (bytes > 0) {
image_offset = get_image_offset(bs, offset, true, &ret);
if (image_offset == -2) {
/* Failed to write block bitmap: can't proceed with write */
goto fail;
}
n_bytes = MIN(bytes, s->block_size - (offset % s->block_size));
if (image_offset == -1) {
image_offset = alloc_block(bs, offset);
if (image_offset < 0) {
ret = image_offset;
goto fail;
}
}
qemu_iovec_reset(&local_qiov);
qemu_iovec_concat(&local_qiov, qiov, bytes_done, n_bytes);
qemu_co_mutex_unlock(&s->lock);
ret = bdrv_co_pwritev(bs->file, image_offset, n_bytes,
&local_qiov, 0);
qemu_co_mutex_lock(&s->lock);
if (ret < 0) {
goto fail;
}
bytes -= n_bytes;
offset += n_bytes;
bytes_done += n_bytes;
}
ret = 0;
fail:
qemu_iovec_destroy(&local_qiov);
qemu_co_mutex_unlock(&s->lock);
return ret;
}
static int coroutine_fn vpc_co_block_status(BlockDriverState *bs,
bool want_zero,
int64_t offset, int64_t bytes,
int64_t *pnum, int64_t *map,
BlockDriverState **file)
{
BDRVVPCState *s = bs->opaque;
int64_t image_offset;
bool allocated;
int ret;
int64_t n;
if (be32_to_cpu(s->footer.type) == VHD_FIXED) {
*pnum = bytes;
*map = offset;
*file = bs->file->bs;
return BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | BDRV_BLOCK_RECURSE;
}
qemu_co_mutex_lock(&s->lock);
image_offset = get_image_offset(bs, offset, false, NULL);
allocated = (image_offset != -1);
*pnum = 0;
block/vpc: return ZERO block-status when appropriate In case when get_image_offset() returns -1, we do zero out the corresponding chunk of qiov. So, this should be reported as ZERO. Note that this changes visible output of "qemu-img map --output=json" and "qemu-io -c map" commands. For qemu-img map, the change is obvious: we just mark as zero what is really zero. For qemu-io it's less obvious: what was unallocated now is allocated. There is an inconsistency in understanding of unallocated regions in Qemu: backing-supporting format-drivers return 0 block-status to report go-to-backing logic for this area. Some protocol-drivers (iscsi) return 0 to report fs-unallocated-non-zero status (i.e., don't occupy space on disk, read result is undefined). BDRV_BLOCK_ALLOCATED is defined as something more close to go-to-backing logic. Still it is calculated as ZERO | DATA, so 0 from iscsi is treated as unallocated. It doesn't influence backing-chain behavior, as iscsi can't have backing file. But it does influence "qemu-io -c map". We should solve this inconsistency at some future point. Now, let's just make backing-not-supporting format drivers (vdi in the previous patch and vpc now) to behave more like backing-supporting drivers and not report 0 block-status. More over, returning ZERO status is absolutely valid thing, and again, corresponds to how the other format-drivers (backing-supporting) work. After block-status update, it never reports 0, so setting unallocated_blocks_are_zero doesn't make sense (as the only user of it is bdrv_co_block_status and it checks unallocated_blocks_are_zero only for unallocated areas). Drop it. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-Id: <20200528094405.145708-5-vsementsov@virtuozzo.com> [mreitz: qemu-io -c map as used by iotest 146 now reports everything as allocated; in order to make the test do something useful, we use qemu-img map --output=json now] Signed-off-by: Max Reitz <mreitz@redhat.com>
2020-05-28 11:43:59 +02:00
ret = BDRV_BLOCK_ZERO;
do {
/* All sectors in a block are contiguous (without using the bitmap) */
n = ROUND_UP(offset + 1, s->block_size) - offset;
n = MIN(n, bytes);
*pnum += n;
offset += n;
bytes -= n;
/* *pnum can't be greater than one block for allocated
* sectors since there is always a bitmap in between. */
if (allocated) {
*file = bs->file->bs;
*map = image_offset;
ret = BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID;
break;
}
if (bytes == 0) {
break;
}
image_offset = get_image_offset(bs, offset, false, NULL);
} while (image_offset == -1);
qemu_co_mutex_unlock(&s->lock);
return ret;
}
/*
* Calculates the number of cylinders, heads and sectors per cylinder
* based on a given number of sectors. This is the algorithm described
* in the VHD specification.
*
* Note that the geometry doesn't always exactly match total_sectors but
* may round it down.
*
* Returns 0 on success, -EFBIG if the size is larger than 2040 GiB. Override
* the hardware EIDE and ATA-2 limit of 16 heads (max disk size of 127 GB)
* and instead allow up to 255 heads.
*/
static int calculate_geometry(int64_t total_sectors, uint16_t *cyls,
uint8_t *heads, uint8_t *secs_per_cyl)
{
uint32_t cyls_times_heads;
total_sectors = MIN(total_sectors, VHD_MAX_GEOMETRY);
if (total_sectors >= 65535LL * 16 * 63) {
*secs_per_cyl = 255;
*heads = 16;
cyls_times_heads = total_sectors / *secs_per_cyl;
} else {
*secs_per_cyl = 17;
cyls_times_heads = total_sectors / *secs_per_cyl;
*heads = DIV_ROUND_UP(cyls_times_heads, 1024);
if (*heads < 4) {
*heads = 4;
}
if (cyls_times_heads >= (*heads * 1024) || *heads > 16) {
*secs_per_cyl = 31;
*heads = 16;
cyls_times_heads = total_sectors / *secs_per_cyl;
}
if (cyls_times_heads >= (*heads * 1024)) {
*secs_per_cyl = 63;
*heads = 16;
cyls_times_heads = total_sectors / *secs_per_cyl;
}
}
*cyls = cyls_times_heads / *heads;
return 0;
}
static int create_dynamic_disk(BlockBackend *blk, VHDFooter *footer,
int64_t total_sectors)
{
VHDDynDiskHeader dyndisk_header;
uint8_t bat_sector[512];
size_t block_size, num_bat_entries;
int i;
int ret;
int64_t offset = 0;
/* Write the footer (twice: at the beginning and at the end) */
block_size = 0x200000;
num_bat_entries = DIV_ROUND_UP(total_sectors, block_size / 512);
ret = blk_pwrite(blk, offset, footer, sizeof(*footer), 0);
if (ret < 0) {
goto fail;
}
offset = 1536 + ((num_bat_entries * 4 + 511) & ~511);
ret = blk_pwrite(blk, offset, footer, sizeof(*footer), 0);
if (ret < 0) {
goto fail;
}
/* Write the initial BAT */
offset = 3 * 512;
memset(bat_sector, 0xFF, 512);
for (i = 0; i < DIV_ROUND_UP(num_bat_entries * 4, 512); i++) {
ret = blk_pwrite(blk, offset, bat_sector, 512, 0);
if (ret < 0) {
goto fail;
}
offset += 512;
}
/* Prepare the Dynamic Disk Header */
memset(&dyndisk_header, 0, sizeof(dyndisk_header));
memcpy(dyndisk_header.magic, "cxsparse", 8);
/*
* Note: The spec is actually wrong here for data_offset, it says
* 0xFFFFFFFF, but MS tools expect all 64 bits to be set.
*/
dyndisk_header.data_offset = cpu_to_be64(0xFFFFFFFFFFFFFFFFULL);
dyndisk_header.table_offset = cpu_to_be64(3 * 512);
dyndisk_header.version = cpu_to_be32(0x00010000);
dyndisk_header.block_size = cpu_to_be32(block_size);
dyndisk_header.max_table_entries = cpu_to_be32(num_bat_entries);
dyndisk_header.checksum = cpu_to_be32(
vpc_checksum(&dyndisk_header, sizeof(dyndisk_header)));
/* Write the header */
offset = 512;
ret = blk_pwrite(blk, offset, &dyndisk_header, sizeof(dyndisk_header), 0);
if (ret < 0) {
goto fail;
}
ret = 0;
fail:
return ret;
}
static int create_fixed_disk(BlockBackend *blk, VHDFooter *footer,
int64_t total_size, Error **errp)
{
int ret;
/* Add footer to total size */
total_size += sizeof(*footer);
ret = blk_truncate(blk, total_size, false, PREALLOC_MODE_OFF, 0, errp);
if (ret < 0) {
return ret;
}
ret = blk_pwrite(blk, total_size - sizeof(*footer),
footer, sizeof(*footer), 0);
if (ret < 0) {
error_setg_errno(errp, -ret, "Unable to write VHD header");
return ret;
}
return 0;
}
static int calculate_rounded_image_size(BlockdevCreateOptionsVpc *vpc_opts,
uint16_t *out_cyls,
uint8_t *out_heads,
uint8_t *out_secs_per_cyl,
int64_t *out_total_sectors,
Error **errp)
{
int64_t total_size = vpc_opts->size;
uint16_t cyls = 0;
uint8_t heads = 0;
uint8_t secs_per_cyl = 0;
int64_t total_sectors;
int i;
/*
* Calculate matching total_size and geometry. Increase the number of
* sectors requested until we get enough (or fail). This ensures that
* qemu-img convert doesn't truncate images, but rather rounds up.
*
* If the image size can't be represented by a spec conformant CHS geometry,
* we set the geometry to 65535 x 16 x 255 (CxHxS) sectors and use
* the image size from the VHD footer to calculate total_sectors.
*/
if (vpc_opts->force_size) {
/* This will force the use of total_size for sector count, below */
cyls = VHD_CHS_MAX_C;
heads = VHD_CHS_MAX_H;
secs_per_cyl = VHD_CHS_MAX_S;
} else {
total_sectors = MIN(VHD_MAX_GEOMETRY, total_size / BDRV_SECTOR_SIZE);
for (i = 0; total_sectors > (int64_t)cyls * heads * secs_per_cyl; i++) {
calculate_geometry(total_sectors + i, &cyls, &heads, &secs_per_cyl);
}
}
if ((int64_t)cyls * heads * secs_per_cyl == VHD_MAX_GEOMETRY) {
total_sectors = total_size / BDRV_SECTOR_SIZE;
/* Allow a maximum disk size of 2040 GiB */
if (total_sectors > VHD_MAX_SECTORS) {
error_setg(errp, "Disk size is too large, max size is 2040 GiB");
return -EFBIG;
}
} else {
total_sectors = (int64_t) cyls * heads * secs_per_cyl;
}
*out_total_sectors = total_sectors;
if (out_cyls) {
*out_cyls = cyls;
*out_heads = heads;
*out_secs_per_cyl = secs_per_cyl;
}
return 0;
}
static int coroutine_fn vpc_co_create(BlockdevCreateOptions *opts,
Error **errp)
{
BlockdevCreateOptionsVpc *vpc_opts;
BlockBackend *blk = NULL;
BlockDriverState *bs = NULL;
VHDFooter footer;
uint16_t cyls = 0;
uint8_t heads = 0;
uint8_t secs_per_cyl = 0;
int64_t total_sectors;
int64_t total_size;
int disk_type;
int ret = -EIO;
QemuUUID uuid;
assert(opts->driver == BLOCKDEV_DRIVER_VPC);
vpc_opts = &opts->u.vpc;
/* Validate options and set default values */
total_size = vpc_opts->size;
if (!vpc_opts->has_subformat) {
vpc_opts->subformat = BLOCKDEV_VPC_SUBFORMAT_DYNAMIC;
}
switch (vpc_opts->subformat) {
case BLOCKDEV_VPC_SUBFORMAT_DYNAMIC:
disk_type = VHD_DYNAMIC;
break;
case BLOCKDEV_VPC_SUBFORMAT_FIXED:
disk_type = VHD_FIXED;
break;
default:
g_assert_not_reached();
}
/* Create BlockBackend to write to the image */
bs = bdrv_open_blockdev_ref(vpc_opts->file, errp);
if (bs == NULL) {
return -EIO;
}
blk = blk_new_with_bs(bs, BLK_PERM_WRITE | BLK_PERM_RESIZE, BLK_PERM_ALL,
errp);
if (!blk) {
ret = -EPERM;
goto out;
}
blk_set_allow_write_beyond_eof(blk, true);
/* Get geometry and check that it matches the image size*/
ret = calculate_rounded_image_size(vpc_opts, &cyls, &heads, &secs_per_cyl,
&total_sectors, errp);
if (ret < 0) {
goto out;
}
if (total_size != total_sectors * BDRV_SECTOR_SIZE) {
error_setg(errp, "The requested image size cannot be represented in "
"CHS geometry");
error_append_hint(errp, "Try size=%llu or force-size=on (the "
"latter makes the image incompatible with "
"Virtual PC)",
total_sectors * BDRV_SECTOR_SIZE);
ret = -EINVAL;
goto out;
}
/* Prepare the Hard Disk Footer */
memset(&footer, 0, sizeof(footer));
memcpy(footer.creator, "conectix", 8);
if (vpc_opts->force_size) {
memcpy(footer.creator_app, "qem2", 4);
} else {
memcpy(footer.creator_app, "qemu", 4);
}
memcpy(footer.creator_os, "Wi2k", 4);
footer.features = cpu_to_be32(0x02);
footer.version = cpu_to_be32(0x00010000);
if (disk_type == VHD_DYNAMIC) {
footer.data_offset = cpu_to_be64(sizeof(footer));
} else {
footer.data_offset = cpu_to_be64(0xFFFFFFFFFFFFFFFFULL);
}
footer.timestamp = cpu_to_be32(time(NULL) - VHD_TIMESTAMP_BASE);
/* Version of Virtual PC 2007 */
footer.major = cpu_to_be16(0x0005);
footer.minor = cpu_to_be16(0x0003);
footer.orig_size = cpu_to_be64(total_size);
footer.current_size = cpu_to_be64(total_size);
footer.cyls = cpu_to_be16(cyls);
footer.heads = heads;
footer.secs_per_cyl = secs_per_cyl;
footer.type = cpu_to_be32(disk_type);
qemu_uuid_generate(&uuid);
footer.uuid = uuid;
footer.checksum = cpu_to_be32(vpc_checksum(&footer, sizeof(footer)));
if (disk_type == VHD_DYNAMIC) {
ret = create_dynamic_disk(blk, &footer, total_sectors);
if (ret < 0) {
error_setg(errp, "Unable to create or write VHD header");
}
} else {
ret = create_fixed_disk(blk, &footer, total_size, errp);
}
out:
blk_unref(blk);
bdrv_unref(bs);
return ret;
}
static int coroutine_fn vpc_co_create_opts(BlockDriver *drv,
const char *filename,
QemuOpts *opts,
Error **errp)
{
BlockdevCreateOptions *create_options = NULL;
QDict *qdict;
Visitor *v;
BlockDriverState *bs = NULL;
int ret;
static const QDictRenames opt_renames[] = {
{ VPC_OPT_FORCE_SIZE, "force-size" },
{ NULL, NULL },
};
/* Parse options and convert legacy syntax */
qdict = qemu_opts_to_qdict_filtered(opts, NULL, &vpc_create_opts, true);
if (!qdict_rename_keys(qdict, opt_renames, errp)) {
ret = -EINVAL;
goto fail;
}
/* Create and open the file (protocol layer) */
error: Eliminate error_propagate() with Coccinelle, part 1 When all we do with an Error we receive into a local variable is propagating to somewhere else, we can just as well receive it there right away. Convert if (!foo(..., &err)) { ... error_propagate(errp, err); ... return ... } to if (!foo(..., errp)) { ... ... return ... } where nothing else needs @err. Coccinelle script: @rule1 forall@ identifier fun, err, errp, lbl; expression list args, args2; binary operator op; constant c1, c2; symbol false; @@ if ( ( - fun(args, &err, args2) + fun(args, errp, args2) | - !fun(args, &err, args2) + !fun(args, errp, args2) | - fun(args, &err, args2) op c1 + fun(args, errp, args2) op c1 ) ) { ... when != err when != lbl: when strict - error_propagate(errp, err); ... when != err ( return; | return c2; | return false; ) } @rule2 forall@ identifier fun, err, errp, lbl; expression list args, args2; expression var; binary operator op; constant c1, c2; symbol false; @@ - var = fun(args, &err, args2); + var = fun(args, errp, args2); ... when != err if ( ( var | !var | var op c1 ) ) { ... when != err when != lbl: when strict - error_propagate(errp, err); ... when != err ( return; | return c2; | return false; | return var; ) } @depends on rule1 || rule2@ identifier err; @@ - Error *err = NULL; ... when != err Not exactly elegant, I'm afraid. The "when != lbl:" is necessary to avoid transforming if (fun(args, &err)) { goto out } ... out: error_propagate(errp, err); even though other paths to label out still need the error_propagate(). For an actual example, see sclp_realize(). Without the "when strict", Coccinelle transforms vfio_msix_setup(), incorrectly. I don't know what exactly "when strict" does, only that it helps here. The match of return is narrower than what I want, but I can't figure out how to express "return where the operand doesn't use @err". For an example where it's too narrow, see vfio_intx_enable(). Silently fails to convert hw/arm/armsse.c, because Coccinelle gets confused by ARMSSE being used both as typedef and function-like macro there. Converted manually. Line breaks tidied up manually. One nested declaration of @local_err deleted manually. Preexisting unwanted blank line dropped in hw/riscv/sifive_e.c. Signed-off-by: Markus Armbruster <armbru@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-Id: <20200707160613.848843-35-armbru@redhat.com>
2020-07-07 18:06:02 +02:00
ret = bdrv_create_file(filename, opts, errp);
if (ret < 0) {
goto fail;
}
bs = bdrv_open(filename, NULL, NULL,
BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, errp);
if (bs == NULL) {
ret = -EIO;
goto fail;
}
/* Now get the QAPI type BlockdevCreateOptions */
qdict_put_str(qdict, "driver", "vpc");
qdict_put_str(qdict, "file", bs->node_name);
v = qobject_input_visitor_new_flat_confused(qdict, errp);
if (!v) {
ret = -EINVAL;
goto fail;
}
visit_type_BlockdevCreateOptions(v, NULL, &create_options, errp);
visit_free(v);
if (!create_options) {
ret = -EINVAL;
goto fail;
}
/* Silently round up size */
assert(create_options->driver == BLOCKDEV_DRIVER_VPC);
create_options->u.vpc.size =
ROUND_UP(create_options->u.vpc.size, BDRV_SECTOR_SIZE);
if (!create_options->u.vpc.force_size) {
int64_t total_sectors;
ret = calculate_rounded_image_size(&create_options->u.vpc, NULL, NULL,
NULL, &total_sectors, errp);
if (ret < 0) {
goto fail;
}
create_options->u.vpc.size = total_sectors * BDRV_SECTOR_SIZE;
}
/* Create the vpc image (format layer) */
ret = vpc_co_create(create_options, errp);
fail:
qobject_unref(qdict);
bdrv_unref(bs);
qapi_free_BlockdevCreateOptions(create_options);
return ret;
}
static int vpc_has_zero_init(BlockDriverState *bs)
{
BDRVVPCState *s = bs->opaque;
if (be32_to_cpu(s->footer.type) == VHD_FIXED) {
return bdrv_has_zero_init(bs->file->bs);
} else {
return 1;
}
}
static void vpc_close(BlockDriverState *bs)
{
BDRVVPCState *s = bs->opaque;
qemu_vfree(s->pagetable);
#ifdef CACHE
g_free(s->pageentry_u8);
#endif
migrate_del_blocker(s->migration_blocker);
error_free(s->migration_blocker);
}
static QemuOptsList vpc_create_opts = {
.name = "vpc-create-opts",
.head = QTAILQ_HEAD_INITIALIZER(vpc_create_opts.head),
.desc = {
{
.name = BLOCK_OPT_SIZE,
.type = QEMU_OPT_SIZE,
.help = "Virtual disk size"
},
{
.name = BLOCK_OPT_SUBFMT,
.type = QEMU_OPT_STRING,
.help =
"Type of virtual hard disk format. Supported formats are "
"{dynamic (default) | fixed} "
},
{
.name = VPC_OPT_FORCE_SIZE,
.type = QEMU_OPT_BOOL,
.help = "Force disk size calculation to use the actual size "
"specified, rather than using the nearest CHS-based "
"calculation"
},
{ /* end of list */ }
}
};
static const char *const vpc_strong_runtime_opts[] = {
VPC_OPT_SIZE_CALC,
NULL
};
static BlockDriver bdrv_vpc = {
.format_name = "vpc",
.instance_size = sizeof(BDRVVPCState),
.bdrv_probe = vpc_probe,
.bdrv_open = vpc_open,
.bdrv_close = vpc_close,
.bdrv_reopen_prepare = vpc_reopen_prepare,
.bdrv_child_perm = bdrv_default_perms,
.bdrv_co_create = vpc_co_create,
.bdrv_co_create_opts = vpc_co_create_opts,
.bdrv_co_preadv = vpc_co_preadv,
.bdrv_co_pwritev = vpc_co_pwritev,
.bdrv_co_block_status = vpc_co_block_status,
.bdrv_get_info = vpc_get_info,
.is_format = true,
.create_opts = &vpc_create_opts,
.bdrv_has_zero_init = vpc_has_zero_init,
.strong_runtime_opts = vpc_strong_runtime_opts,
};
static void bdrv_vpc_init(void)
{
bdrv_register(&bdrv_vpc);
}
block_init(bdrv_vpc_init);