From 47299b9e7ac4a8318e0cf3c88cc3f24cc214da1b Mon Sep 17 00:00:00 2001 From: Jeffrey Cody Date: Wed, 20 Nov 2013 19:43:51 +0100 Subject: [PATCH 08/25] block: vhdx - add header update capability. RH-Author: Jeffrey Cody Message-id: <42b5dd4b297781538d090b292503c89e2dcb9ed5.1384975172.git.jcody@redhat.com> Patchwork-id: 55801 O-Subject: [RHEL7 qemu-kvm PATCH 08/26] block: vhdx - add header update capability. Bugzilla: 879234 RH-Acked-by: Stefan Hajnoczi RH-Acked-by: Paolo Bonzini RH-Acked-by: Fam Zheng This adds the ability to update the headers in a VHDX image, including generating a new MS-compatible GUID. As VHDX depends on uuid.h, VHDX is now a configurable build option. If VHDX support is enabled, that will also enable uuid as well. The default is to have VHDX enabled. To enable/disable VHDX: --enable-vhdx, --disable-vhdx Signed-off-by: Jeff Cody Signed-off-by: Stefan Hajnoczi (cherry picked from commit 4f18b7824ab5eda9fe051f5b24e90e5f34d08a23) Conflicts: configure RHEL7 Notes: Conflict due to the changes for VHDX enable/disable in the same area of the file as the RHEL7 live block differentiation. Signed-off-by: Jeff Cody --- block/Makefile.objs | 2 +- block/vhdx.c | 161 +++++++++++++++++++++++++++++++++++++++++++++++++++- block/vhdx.h | 14 ++++- configure | 26 ++++++++- 4 files changed, 197 insertions(+), 6 deletions(-) Signed-off-by: Miroslav Rezanina --- block/Makefile.objs | 2 +- block/vhdx.c | 161 ++++++++++++++++++++++++++++++++++++++++++++++++++- block/vhdx.h | 14 ++++- configure | 26 ++++++++- 4 files changed, 197 insertions(+), 6 deletions(-) diff --git a/block/Makefile.objs b/block/Makefile.objs index 3db1839..114f8a5 100644 --- a/block/Makefile.objs +++ b/block/Makefile.objs @@ -2,7 +2,7 @@ block-obj-y += raw.o cow.o qcow.o vdi.o vmdk.o cloop.o dmg.o bochs.o vpc.o vvfat block-obj-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o qcow2-cache.o block-obj-y += qed.o qed-gencb.o qed-l2-cache.o qed-table.o qed-cluster.o block-obj-y += qed-check.o -block-obj-y += vhdx.o +block-obj-$(CONFIG_VHDX) += vhdx.o block-obj-y += parallels.o blkdebug.o blkverify.o block-obj-y += snapshot.o qapi.o block-obj-$(CONFIG_WIN32) += raw-win32.o win32-aio.o diff --git a/block/vhdx.c b/block/vhdx.c index 23be4e3..fba2aa9 100644 --- a/block/vhdx.c +++ b/block/vhdx.c @@ -22,6 +22,7 @@ #include "block/vhdx.h" #include "migration/migration.h" +#include /* Several metadata and region table data entries are identified by * guids in a MS-specific GUID format. */ @@ -157,12 +158,41 @@ typedef struct BDRVVHDXState { VHDXBatEntry *bat; uint64_t bat_offset; + MSGUID session_guid; + + VHDXParentLocatorHeader parent_header; VHDXParentLocatorEntry *parent_entries; Error *migration_blocker; } BDRVVHDXState; +/* Calculates new checksum. + * + * Zero is substituted during crc calculation for the original crc field + * crc_offset: byte offset in buf of the buffer crc + * buf: buffer pointer + * size: size of buffer (must be > crc_offset+4) + * + * Note: The resulting checksum is in the CPU endianness, not necessarily + * in the file format endianness (LE). Any header export to disk should + * make sure that vhdx_header_le_export() is used to convert to the + * correct endianness + */ +uint32_t vhdx_update_checksum(uint8_t *buf, size_t size, int crc_offset) +{ + uint32_t crc; + + assert(buf != NULL); + assert(size > (crc_offset + sizeof(crc))); + + memset(buf + crc_offset, 0, sizeof(crc)); + crc = crc32c(0xffffffff, buf, size); + memcpy(buf + crc_offset, &crc, sizeof(crc)); + + return crc; +} + uint32_t vhdx_checksum_calc(uint32_t crc, uint8_t *buf, size_t size, int crc_offset) { @@ -214,6 +244,19 @@ bool vhdx_checksum_is_valid(uint8_t *buf, size_t size, int crc_offset) /* + * This generates a UUID that is compliant with the MS GUIDs used + * in the VHDX spec (and elsewhere). + */ +void vhdx_guid_generate(MSGUID *guid) +{ + uuid_t uuid; + assert(guid != NULL); + + uuid_generate(uuid); + memcpy(guid, uuid, sizeof(MSGUID)); +} + +/* * Per the MS VHDX Specification, for every VHDX file: * - The header section is fixed size - 1 MB * - The header section is always the first "object" @@ -251,6 +294,113 @@ static void vhdx_header_le_import(VHDXHeader *h) le64_to_cpus(&h->log_offset); } +/* All VHDX structures on disk are little endian */ +static void vhdx_header_le_export(VHDXHeader *orig_h, VHDXHeader *new_h) +{ + assert(orig_h != NULL); + assert(new_h != NULL); + + new_h->signature = cpu_to_le32(orig_h->signature); + new_h->checksum = cpu_to_le32(orig_h->checksum); + new_h->sequence_number = cpu_to_le64(orig_h->sequence_number); + + new_h->file_write_guid = orig_h->file_write_guid; + new_h->data_write_guid = orig_h->data_write_guid; + new_h->log_guid = orig_h->log_guid; + + cpu_to_leguids(&new_h->file_write_guid); + cpu_to_leguids(&new_h->data_write_guid); + cpu_to_leguids(&new_h->log_guid); + + new_h->log_version = cpu_to_le16(orig_h->log_version); + new_h->version = cpu_to_le16(orig_h->version); + new_h->log_length = cpu_to_le32(orig_h->log_length); + new_h->log_offset = cpu_to_le64(orig_h->log_offset); +} + +/* Update the VHDX headers + * + * This follows the VHDX spec procedures for header updates. + * + * - non-current header is updated with largest sequence number + */ +static int vhdx_update_header(BlockDriverState *bs, BDRVVHDXState *s, + bool generate_data_write_guid) +{ + int ret = 0; + int hdr_idx = 0; + uint64_t header_offset = VHDX_HEADER1_OFFSET; + + VHDXHeader *active_header; + VHDXHeader *inactive_header; + VHDXHeader header_le; + uint8_t *buffer; + + /* operate on the non-current header */ + if (s->curr_header == 0) { + hdr_idx = 1; + header_offset = VHDX_HEADER2_OFFSET; + } + + active_header = s->headers[s->curr_header]; + inactive_header = s->headers[hdr_idx]; + + inactive_header->sequence_number = active_header->sequence_number + 1; + + /* a new file guid must be generated before any file write, including + * headers */ + inactive_header->file_write_guid = s->session_guid; + + /* a new data guid only needs to be generated before any guest-visible + * writes (i.e. something observable via virtual disk read) */ + if (generate_data_write_guid) { + vhdx_guid_generate(&inactive_header->data_write_guid); + } + + /* the header checksum is not over just the packed size of VHDXHeader, + * but rather over the entire 'reserved' range for the header, which is + * 4KB (VHDX_HEADER_SIZE). */ + + buffer = qemu_blockalign(bs, VHDX_HEADER_SIZE); + /* we can't assume the extra reserved bytes are 0 */ + ret = bdrv_pread(bs->file, header_offset, buffer, VHDX_HEADER_SIZE); + if (ret < 0) { + goto exit; + } + /* overwrite the actual VHDXHeader portion */ + memcpy(buffer, inactive_header, sizeof(VHDXHeader)); + inactive_header->checksum = + vhdx_update_checksum(buffer, VHDX_HEADER_SIZE, + offsetof(VHDXHeader, checksum)); + vhdx_header_le_export(inactive_header, &header_le); + ret = bdrv_pwrite_sync(bs->file, header_offset, &header_le, + sizeof(VHDXHeader)); + if (ret < 0) { + goto exit; + } + s->curr_header = hdr_idx; + +exit: + qemu_vfree(buffer); + return ret; +} + +/* + * The VHDX spec calls for header updates to be performed twice, so that both + * the current and non-current header have valid info + */ +static int vhdx_update_headers(BlockDriverState *bs, BDRVVHDXState *s, + bool generate_data_write_guid) +{ + int ret; + + ret = vhdx_update_header(bs, s, generate_data_write_guid); + if (ret < 0) { + return ret; + } + ret = vhdx_update_header(bs, s, generate_data_write_guid); + return ret; +} /* opens the specified header block from the VHDX file header section */ static int vhdx_parse_header(BlockDriverState *bs, BDRVVHDXState *s) @@ -742,6 +892,11 @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags, goto fail; } + /* This is used for any header updates, for the file_write_guid. + * The spec dictates that a new value should be used for the first + * header update */ + vhdx_guid_generate(&s->session_guid); + ret = vhdx_parse_header(bs, s); if (ret) { goto fail; @@ -804,8 +959,10 @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags, } if (flags & BDRV_O_RDWR) { - ret = -ENOTSUP; - goto fail; + ret = vhdx_update_headers(bs, s, false); + if (ret < 0) { + goto fail; + } } /* TODO: differencing files, write */ diff --git a/block/vhdx.h b/block/vhdx.h index 1dbb320..2223b15 100644 --- a/block/vhdx.h +++ b/block/vhdx.h @@ -67,7 +67,7 @@ typedef struct VHDXFileIdentifier { * Microsoft is not just 16 bytes though - it is a structure that is defined, * so we need to follow it here so that endianness does not trip us up */ -typedef struct MSGUID { +typedef struct QEMU_PACKED MSGUID { uint32_t data1; uint16_t data2; uint16_t data3; @@ -309,17 +309,27 @@ typedef struct QEMU_PACKED VHDXParentLocatorEntry { /* ----- END VHDX SPECIFICATION STRUCTURES ---- */ +void vhdx_guid_generate(MSGUID *guid); + +uint32_t vhdx_update_checksum(uint8_t *buf, size_t size, int crc_offset); uint32_t vhdx_checksum_calc(uint32_t crc, uint8_t *buf, size_t size, int crc_offset); bool vhdx_checksum_is_valid(uint8_t *buf, size_t size, int crc_offset); -static void leguid_to_cpus(MSGUID *guid) +static inline void leguid_to_cpus(MSGUID *guid) { le32_to_cpus(&guid->data1); le16_to_cpus(&guid->data2); le16_to_cpus(&guid->data3); } +static inline void cpu_to_leguids(MSGUID *guid) +{ + cpu_to_le32s(&guid->data1); + cpu_to_le16s(&guid->data2); + cpu_to_le16s(&guid->data3); +} + #endif diff --git a/configure b/configure index 33235c4..5161fec 100755 --- a/configure +++ b/configure @@ -245,6 +245,7 @@ libssh2="" live_block_ops="yes" live_block_migration="no" ceph_support="yes" +vhdx="" # parse CC options first for opt do @@ -950,7 +951,11 @@ for opt do ;; --enable-ceph-support) ceph_support=="yes" ;; -*) echo "ERROR: unknown option $opt"; show_help="yes" + --enable-vhdx) vhdx="yes" + ;; + --disable-vhdx) vhdx="no" + ;; + *) echo "ERROR: unknown option $opt"; show_help="yes" ;; esac done @@ -1227,6 +1232,8 @@ echo " --disable-live-block-migration disable live block migration" echo " --enable-live-block-migration enable live block migration" echo " --disable-ceph-support disable support for rbd block driver support" echo " --enable-ceph-support enable support for rbd block driver support" +echo " --disable-vhdx disables support for the Microsoft VHDX image format" +echo " --enable-vhdx enable support for the Microsoft VHDX image format" echo "" echo "NOTE: The object files are built at the place where configure is launched" exit 1 @@ -2027,6 +2034,18 @@ EOF fi fi +if test "$vhdx" = "yes" ; then + if test "$uuid" = "no" ; then + error_exit "uuid required for VHDX support" + fi +elif test "$vhdx" != "no" ; then + if test "$uuid" = "yes" ; then + vhdx=yes + else + vhdx=no + fi +fi + ########################################## # xfsctl() probe, used for raw-posix if test "$xfs" != "no" ; then @@ -3615,6 +3634,7 @@ echo "TPM passthrough $tpm_passthrough" echo "QOM debugging $qom_cast_debug" echo "Live block operations $live_block_ops" echo "Live block migration $live_block_migration" +echo "vhdx $vhdx" if test "$sdl_too_old" = "yes"; then echo "-> Your SDL version is too old - please upgrade to have SDL support" @@ -4011,6 +4031,10 @@ if test "ceph_support" = "yes"; then echo "CONFIG_CEPH_SUPPORT=y" >> $config_host_mak fi +if test "$vhdx" = "yes" ; then + echo "CONFIG_VHDX=y" >> $config_host_mak +fi + # USB host support if test "$libusb" = "yes"; then echo "HOST_USB=libusb legacy" >> $config_host_mak -- 1.7.1