From patchwork Fri Oct 8 15:48:31 2010 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Stefan Hajnoczi X-Patchwork-Id: 67240 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Received: from lists.gnu.org (lists.gnu.org [199.232.76.165]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by ozlabs.org (Postfix) with ESMTPS id C10A4B6F07 for ; Sat, 9 Oct 2010 04:02:49 +1100 (EST) Received: from localhost ([127.0.0.1]:44905 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.43) id 1P4GLE-0004JW-5Q for incoming@patchwork.ozlabs.org; Fri, 08 Oct 2010 13:02:44 -0400 Received: from [140.186.70.92] (port=49330 helo=eggs.gnu.org) by lists.gnu.org with esmtp (Exim 4.43) id 1P4FrB-000304-T5 for qemu-devel@nongnu.org; Fri, 08 Oct 2010 12:31:49 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1P4FBo-0007vJ-AK for qemu-devel@nongnu.org; Fri, 08 Oct 2010 11:48:58 -0400 Received: from mtagate5.de.ibm.com ([195.212.17.165]:34538) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1P4FBn-0007u5-MM for qemu-devel@nongnu.org; Fri, 08 Oct 2010 11:48:56 -0400 Received: from d12nrmr1607.megacenter.de.ibm.com (d12nrmr1607.megacenter.de.ibm.com [9.149.167.49]) by mtagate5.de.ibm.com (8.13.1/8.13.1) with ESMTP id o98FmjH2030613 for ; Fri, 8 Oct 2010 15:48:46 GMT Received: from d12av02.megacenter.de.ibm.com (d12av02.megacenter.de.ibm.com [9.149.165.228]) by d12nrmr1607.megacenter.de.ibm.com (8.13.8/8.13.8/NCO v10.0) with ESMTP id o98FmjwJ3567770 for ; Fri, 8 Oct 2010 17:48:45 +0200 Received: from d12av02.megacenter.de.ibm.com (loopback [127.0.0.1]) by d12av02.megacenter.de.ibm.com (8.12.11.20060308/8.13.3) with ESMTP id o98Fmi7w019696 for ; Fri, 8 Oct 2010 17:48:45 +0200 Received: from stefan-thinkpad.manchester-maybrook.uk.ibm.com (dyn-9-174-218-53.manchester-maybrook.uk.ibm.com [9.174.218.53]) by d12av02.megacenter.de.ibm.com (8.12.11.20060308/8.12.11) with ESMTP id o98Fmgen019417; Fri, 8 Oct 2010 17:48:44 +0200 From: Stefan Hajnoczi To: Date: Fri, 8 Oct 2010 16:48:31 +0100 Message-Id: <1286552914-27014-5-git-send-email-stefanha@linux.vnet.ibm.com> X-Mailer: git-send-email 1.7.1 In-Reply-To: <1286552914-27014-1-git-send-email-stefanha@linux.vnet.ibm.com> References: <1286552914-27014-1-git-send-email-stefanha@linux.vnet.ibm.com> X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.6, seldom 2.4 (older, 4) Cc: Kevin Wolf , Anthony Liguori , Christoph Hellwig , Stefan Hajnoczi , Avi Kivity Subject: [Qemu-devel] [PATCH v2 4/7] qed: Add QEMU Enhanced Disk image format X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: qemu-devel.nongnu.org List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org Errors-To: qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org This patch introduces the qed on-disk layout and implements image creation. Later patches add read/write and other functionality. Signed-off-by: Stefan Hajnoczi --- Makefile.objs | 1 + block/qed.c | 530 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++ block/qed.h | 148 ++++++++++++++++ 3 files changed, 679 insertions(+), 0 deletions(-) create mode 100644 block/qed.c create mode 100644 block/qed.h diff --git a/Makefile.objs b/Makefile.objs index 816194a..ff15795 100644 --- a/Makefile.objs +++ b/Makefile.objs @@ -14,6 +14,7 @@ block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o block-nested-y += raw.o cow.o qcow.o vdi.o vmdk.o cloop.o dmg.o bochs.o vpc.o vvfat.o block-nested-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o +block-nested-y += qed.o block-nested-y += parallels.o nbd.o blkdebug.o sheepdog.o blkverify.o block-nested-$(CONFIG_WIN32) += raw-win32.o block-nested-$(CONFIG_POSIX) += raw-posix.o diff --git a/block/qed.c b/block/qed.c new file mode 100644 index 0000000..ea03798 --- /dev/null +++ b/block/qed.c @@ -0,0 +1,530 @@ +/* + * QEMU Enhanced Disk Format + * + * Copyright IBM, Corp. 2010 + * + * Authors: + * Stefan Hajnoczi + * Anthony Liguori + * + * This work is licensed under the terms of the GNU LGPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qed.h" + +static int bdrv_qed_probe(const uint8_t *buf, int buf_size, + const char *filename) +{ + const QEDHeader *header = (const void *)buf; + + if (buf_size < sizeof(*header)) { + return 0; + } + if (le32_to_cpu(header->magic) != QED_MAGIC) { + return 0; + } + return 100; +} + +static void qed_header_le_to_cpu(const QEDHeader *le, QEDHeader *cpu) +{ + cpu->magic = le32_to_cpu(le->magic); + cpu->cluster_size = le32_to_cpu(le->cluster_size); + cpu->table_size = le32_to_cpu(le->table_size); + cpu->header_size = le32_to_cpu(le->header_size); + cpu->features = le64_to_cpu(le->features); + cpu->compat_features = le64_to_cpu(le->compat_features); + cpu->l1_table_offset = le64_to_cpu(le->l1_table_offset); + cpu->image_size = le64_to_cpu(le->image_size); + cpu->backing_filename_offset = le32_to_cpu(le->backing_filename_offset); + cpu->backing_filename_size = le32_to_cpu(le->backing_filename_size); + cpu->backing_fmt_offset = le32_to_cpu(le->backing_fmt_offset); + cpu->backing_fmt_size = le32_to_cpu(le->backing_fmt_size); +} + +static void qed_header_cpu_to_le(const QEDHeader *cpu, QEDHeader *le) +{ + le->magic = cpu_to_le32(cpu->magic); + le->cluster_size = cpu_to_le32(cpu->cluster_size); + le->table_size = cpu_to_le32(cpu->table_size); + le->header_size = cpu_to_le32(cpu->header_size); + le->features = cpu_to_le64(cpu->features); + le->compat_features = cpu_to_le64(cpu->compat_features); + le->l1_table_offset = cpu_to_le64(cpu->l1_table_offset); + le->image_size = cpu_to_le64(cpu->image_size); + le->backing_filename_offset = cpu_to_le32(cpu->backing_filename_offset); + le->backing_filename_size = cpu_to_le32(cpu->backing_filename_size); + le->backing_fmt_offset = cpu_to_le32(cpu->backing_fmt_offset); + le->backing_fmt_size = cpu_to_le32(cpu->backing_fmt_size); +} + +static uint64_t qed_max_image_size(uint32_t cluster_size, uint32_t table_size) +{ + uint64_t table_entries; + uint64_t l2_size; + + table_entries = (table_size * cluster_size) / sizeof(uint64_t); + l2_size = table_entries * cluster_size; + + return l2_size * table_entries; +} + +static bool qed_is_cluster_size_valid(uint32_t cluster_size) +{ + if (cluster_size < QED_MIN_CLUSTER_SIZE || + cluster_size > QED_MAX_CLUSTER_SIZE) { + return false; + } + if (cluster_size & (cluster_size - 1)) { + return false; /* not power of 2 */ + } + return true; +} + +static bool qed_is_table_size_valid(uint32_t table_size) +{ + if (table_size < QED_MIN_TABLE_SIZE || + table_size > QED_MAX_TABLE_SIZE) { + return false; + } + if (table_size & (table_size - 1)) { + return false; /* not power of 2 */ + } + return true; +} + +static bool qed_is_image_size_valid(uint64_t image_size, uint32_t cluster_size, + uint32_t table_size) +{ + if (image_size == 0) { + /* Supporting zero size images makes life harder because even the L1 + * table is not needed. Make life simple and forbid zero size images. + */ + return false; + } + if (image_size & (cluster_size - 1)) { + return false; /* not multiple of cluster size */ + } + if (image_size > qed_max_image_size(cluster_size, table_size)) { + return false; /* image is too large */ + } + return true; +} + +/** + * Read a string of known length from the image file + * + * @file: Image file + * @offset: File offset to start of string, in bytes + * @n: String length in bytes + * @buf: Destination buffer + * @buflen: Destination buffer length in bytes + * + * The string is NUL-terminated. + */ +static int qed_read_string(BlockDriverState *file, uint64_t offset, size_t n, + char *buf, size_t buflen) +{ + int ret; + if (n >= buflen) { + return -EINVAL; + } + ret = bdrv_pread(file, offset, buf, n); + if (ret != n) { + return ret; + } + buf[n] = '\0'; + return 0; +} + +static int bdrv_qed_open(BlockDriverState *bs, int flags) +{ + BDRVQEDState *s = bs->opaque; + QEDHeader le_header; + int64_t file_size; + int ret; + + s->bs = bs; + + ret = bdrv_pread(bs->file, 0, &le_header, sizeof(le_header)); + if (ret != sizeof(le_header)) { + return ret; + } + qed_header_le_to_cpu(&le_header, &s->header); + + if (s->header.magic != QED_MAGIC) { + return -ENOENT; + } + if (s->header.features & ~QED_FEATURE_MASK) { + return -ENOTSUP; /* image uses unsupported feature bits */ + } + if (!qed_is_cluster_size_valid(s->header.cluster_size)) { + return -EINVAL; + } + + /* Round up file size to the next cluster */ + file_size = bdrv_getlength(bs->file); + if (file_size < 0) { + return file_size; + } + s->file_size = qed_start_of_cluster(s, file_size); + + if (!qed_is_table_size_valid(s->header.table_size)) { + return -EINVAL; + } + if (!qed_is_image_size_valid(s->header.image_size, + s->header.cluster_size, + s->header.table_size)) { + return -EINVAL; + } + if (!qed_check_table_offset(s, s->header.l1_table_offset)) { + return -EINVAL; + } + + s->table_nelems = (s->header.cluster_size * s->header.table_size) / + sizeof(uint64_t); + s->l2_shift = get_bits_from_size(s->header.cluster_size); + s->l2_mask = s->table_nelems - 1; + s->l1_shift = s->l2_shift + get_bits_from_size(s->l2_mask + 1); + + if ((s->header.features & QED_F_BACKING_FILE)) { + ret = qed_read_string(bs->file, s->header.backing_filename_offset, + s->header.backing_filename_size, bs->backing_file, + sizeof(bs->backing_file)); + if (ret < 0) { + return ret; + } + + if ((s->header.compat_features & QED_CF_BACKING_FORMAT)) { + ret = qed_read_string(bs->file, s->header.backing_fmt_offset, + s->header.backing_fmt_size, + bs->backing_format, + sizeof(bs->backing_format)); + if (ret < 0) { + return ret; + } + } + } + return ret; +} + +static void bdrv_qed_close(BlockDriverState *bs) +{ +} + +static void bdrv_qed_flush(BlockDriverState *bs) +{ + bdrv_flush(bs->file); +} + +static int qed_create(const char *filename, uint32_t cluster_size, + uint64_t image_size, uint32_t table_size, + const char *backing_file, const char *backing_fmt) +{ + QEDHeader header = { + .magic = QED_MAGIC, + .cluster_size = cluster_size, + .table_size = table_size, + .header_size = 1, + .features = 0, + .compat_features = 0, + .l1_table_offset = cluster_size, + .image_size = image_size, + }; + QEDHeader le_header; + uint8_t *l1_table = NULL; + size_t l1_size = header.cluster_size * header.table_size; + int ret = 0; + int fd; + + fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY, 0644); + if (fd < 0) { + return -errno; + } + + if (backing_file) { + header.features |= QED_F_BACKING_FILE; + header.backing_filename_offset = sizeof(le_header); + header.backing_filename_size = strlen(backing_file); + if (backing_fmt) { + header.compat_features |= QED_CF_BACKING_FORMAT; + header.backing_fmt_offset = header.backing_filename_offset + + header.backing_filename_size; + header.backing_fmt_size = strlen(backing_fmt); + } + } + + qed_header_cpu_to_le(&header, &le_header); + if (qemu_write_full(fd, &le_header, sizeof(le_header)) != sizeof(le_header)) { + ret = -errno; + goto out; + } + if (qemu_write_full(fd, backing_file, header.backing_filename_size) != header.backing_filename_size) { + ret = -errno; + goto out; + } + if (qemu_write_full(fd, backing_fmt, header.backing_fmt_size) != header.backing_fmt_size) { + ret = -errno; + goto out; + } + + l1_table = qemu_mallocz(l1_size); + lseek(fd, header.l1_table_offset, SEEK_SET); + if (qemu_write_full(fd, l1_table, l1_size) != l1_size) { + ret = -errno; + goto out; + } + +out: + qemu_free(l1_table); + close(fd); + return ret; +} + +static int bdrv_qed_create(const char *filename, QEMUOptionParameter *options) +{ + uint64_t image_size = 0; + uint32_t cluster_size = QED_DEFAULT_CLUSTER_SIZE; + uint32_t table_size = QED_DEFAULT_TABLE_SIZE; + const char *backing_file = NULL; + const char *backing_fmt = NULL; + + while (options && options->name) { + if (!strcmp(options->name, BLOCK_OPT_SIZE)) { + image_size = options->value.n; + } else if (!strcmp(options->name, BLOCK_OPT_BACKING_FILE)) { + backing_file = options->value.s; + } else if (!strcmp(options->name, BLOCK_OPT_BACKING_FMT)) { + backing_fmt = options->value.s; + } else if (!strcmp(options->name, BLOCK_OPT_CLUSTER_SIZE)) { + if (options->value.n) { + cluster_size = options->value.n; + } + } else if (!strcmp(options->name, "table_size")) { + if (options->value.n) { + table_size = options->value.n; + } + } + options++; + } + + if (!qed_is_cluster_size_valid(cluster_size)) { + fprintf(stderr, "QED cluster size must be within range [%u, %u] and power of 2\n", + QED_MIN_CLUSTER_SIZE, QED_MAX_CLUSTER_SIZE); + return -EINVAL; + } + if (!qed_is_table_size_valid(table_size)) { + fprintf(stderr, "QED table size must be within range [%u, %u] and power of 2\n", + QED_MIN_TABLE_SIZE, QED_MAX_TABLE_SIZE); + return -EINVAL; + } + if (!qed_is_image_size_valid(image_size, cluster_size, table_size)) { + char buffer[64]; + + bytes_to_str(buffer, sizeof(buffer), + qed_max_image_size(cluster_size, table_size)); + + fprintf(stderr, + "QED image size must be a non-zero multiple of cluster size and less than %s\n", + buffer); + return -EINVAL; + } + + return qed_create(filename, cluster_size, image_size, table_size, + backing_file, backing_fmt); +} + +static int bdrv_qed_is_allocated(BlockDriverState *bs, int64_t sector_num, + int nb_sectors, int *pnum) +{ + return -ENOTSUP; +} + +static int bdrv_qed_make_empty(BlockDriverState *bs) +{ + return -ENOTSUP; +} + +static BlockDriverAIOCB *bdrv_qed_aio_readv(BlockDriverState *bs, + int64_t sector_num, + QEMUIOVector *qiov, int nb_sectors, + BlockDriverCompletionFunc *cb, + void *opaque) +{ + return NULL; +} + +static BlockDriverAIOCB *bdrv_qed_aio_writev(BlockDriverState *bs, + int64_t sector_num, + QEMUIOVector *qiov, int nb_sectors, + BlockDriverCompletionFunc *cb, + void *opaque) +{ + return NULL; +} + +static BlockDriverAIOCB *bdrv_qed_aio_flush(BlockDriverState *bs, + BlockDriverCompletionFunc *cb, + void *opaque) +{ + return bdrv_aio_flush(bs->file, cb, opaque); +} + +static int bdrv_qed_truncate(BlockDriverState *bs, int64_t offset) +{ + return -ENOTSUP; +} + +static int64_t bdrv_qed_getlength(BlockDriverState *bs) +{ + BDRVQEDState *s = bs->opaque; + return s->header.image_size; +} + +static int bdrv_qed_get_info(BlockDriverState *bs, BlockDriverInfo *bdi) +{ + BDRVQEDState *s = bs->opaque; + + memset(bdi, 0, sizeof(*bdi)); + bdi->cluster_size = s->header.cluster_size; + return 0; +} + +static int bdrv_qed_change_backing_file(BlockDriverState *bs, + const char *backing_file, + const char *backing_fmt) +{ + BDRVQEDState *s = bs->opaque; + QEDHeader new_header, le_header; + void *buffer; + size_t buffer_len, backing_file_len, backing_fmt_len; + int ret; + + /* Refuse to set backing filename if unknown compat feature bits are + * active. If the image uses an unknown compat feature then we may not + * know the layout of data following the header structure and cannot safely + * add a new string. + */ + if (backing_file && (s->header.compat_features & + ~QED_COMPAT_FEATURE_MASK)) { + return -ENOTSUP; + } + + memcpy(&new_header, &s->header, sizeof(new_header)); + + new_header.features &= ~QED_F_BACKING_FILE; + new_header.compat_features &= ~QED_CF_BACKING_FORMAT; + + /* Adjust feature flags */ + if (backing_file) { + new_header.features |= QED_F_BACKING_FILE; + if (backing_fmt) { + new_header.compat_features |= QED_CF_BACKING_FORMAT; + } + } + + /* Calculate new header size */ + backing_file_len = backing_fmt_len = 0; + + if (backing_file) { + backing_file_len = strlen(backing_file); + if (backing_fmt) { + backing_fmt_len = strlen(backing_fmt); + } + } + + buffer_len = sizeof(new_header); + new_header.backing_filename_offset = buffer_len; + new_header.backing_filename_size = backing_file_len; + buffer_len += backing_file_len; + new_header.backing_fmt_offset = buffer_len; + new_header.backing_fmt_size = backing_fmt_len; + buffer_len += backing_fmt_len; + + /* Make sure we can rewrite header without failing */ + if (buffer_len > new_header.header_size * new_header.cluster_size) { + return -ENOSPC; + } + + /* Prepare new header */ + buffer = qemu_malloc(buffer_len); + + qed_header_cpu_to_le(&new_header, &le_header); + memcpy(buffer, &le_header, sizeof(le_header)); + buffer_len = sizeof(le_header); + + memcpy(buffer + buffer_len, backing_file, backing_file_len); + buffer_len += backing_file_len; + + memcpy(buffer + buffer_len, backing_fmt, backing_fmt_len); + buffer_len += backing_fmt_len; + + /* Write new header */ + ret = bdrv_pwrite_sync(bs->file, 0, buffer, buffer_len); + qemu_free(buffer); + if (ret == 0) { + memcpy(&s->header, &new_header, sizeof(new_header)); + } + return ret; +} + +static int bdrv_qed_check(BlockDriverState *bs, BdrvCheckResult *result) +{ + return -ENOTSUP; +} + +static QEMUOptionParameter qed_create_options[] = { + { + .name = BLOCK_OPT_SIZE, + .type = OPT_SIZE, + .help = "Virtual disk size (in bytes)" + }, { + .name = BLOCK_OPT_BACKING_FILE, + .type = OPT_STRING, + .help = "File name of a base image" + }, { + .name = BLOCK_OPT_BACKING_FMT, + .type = OPT_STRING, + .help = "Image format of the base image" + }, { + .name = BLOCK_OPT_CLUSTER_SIZE, + .type = OPT_SIZE, + .help = "Cluster size (in bytes)" + }, { + .name = "table_size", + .type = OPT_SIZE, + .help = "L1/L2 table size (in clusters)" + }, + { /* end of list */ } +}; + +static BlockDriver bdrv_qed = { + .format_name = "qed", + .instance_size = sizeof(BDRVQEDState), + .create_options = qed_create_options, + + .bdrv_probe = bdrv_qed_probe, + .bdrv_open = bdrv_qed_open, + .bdrv_close = bdrv_qed_close, + .bdrv_create = bdrv_qed_create, + .bdrv_flush = bdrv_qed_flush, + .bdrv_is_allocated = bdrv_qed_is_allocated, + .bdrv_make_empty = bdrv_qed_make_empty, + .bdrv_aio_readv = bdrv_qed_aio_readv, + .bdrv_aio_writev = bdrv_qed_aio_writev, + .bdrv_aio_flush = bdrv_qed_aio_flush, + .bdrv_truncate = bdrv_qed_truncate, + .bdrv_getlength = bdrv_qed_getlength, + .bdrv_get_info = bdrv_qed_get_info, + .bdrv_change_backing_file = bdrv_qed_change_backing_file, + .bdrv_check = bdrv_qed_check, +}; + +static void bdrv_qed_init(void) +{ + bdrv_register(&bdrv_qed); +} + +block_init(bdrv_qed_init); diff --git a/block/qed.h b/block/qed.h new file mode 100644 index 0000000..7ce95a7 --- /dev/null +++ b/block/qed.h @@ -0,0 +1,148 @@ +/* + * QEMU Enhanced Disk Format + * + * Copyright IBM, Corp. 2010 + * + * Authors: + * Stefan Hajnoczi + * Anthony Liguori + * + * This work is licensed under the terms of the GNU LGPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef BLOCK_QED_H +#define BLOCK_QED_H + +#include "block_int.h" + +/* The layout of a QED file is as follows: + * + * +--------+----------+----------+----------+-----+ + * | header | L1 table | cluster0 | cluster1 | ... | + * +--------+----------+----------+----------+-----+ + * + * There is a 2-level pagetable for cluster allocation: + * + * +----------+ + * | L1 table | + * +----------+ + * ,------' | '------. + * +----------+ | +----------+ + * | L2 table | ... | L2 table | + * +----------+ +----------+ + * ,------' | '------. + * +----------+ | +----------+ + * | Data | ... | Data | + * +----------+ +----------+ + * + * The L1 table is fixed size and always present. L2 tables are allocated on + * demand. The L1 table size determines the maximum possible image size; it + * can be influenced using the cluster_size and table_size values. + * + * All fields are little-endian on disk. + */ + +enum { + QED_MAGIC = 'Q' | 'E' << 8 | 'D' << 16 | '\0' << 24, + + /* The image supports a backing file */ + QED_F_BACKING_FILE = 0x01, + + /* The image has the backing file format */ + QED_CF_BACKING_FORMAT = 0x01, + + /* Feature bits must be used when the on-disk format changes */ + QED_FEATURE_MASK = QED_F_BACKING_FILE, /* supported feature bits */ + QED_COMPAT_FEATURE_MASK = QED_CF_BACKING_FORMAT, /* supported compat feature bits */ + + /* Data is stored in groups of sectors called clusters. Cluster size must + * be large to avoid keeping too much metadata. I/O requests that have + * sub-cluster size will require read-modify-write. + */ + QED_MIN_CLUSTER_SIZE = 4 * 1024, /* in bytes */ + QED_MAX_CLUSTER_SIZE = 64 * 1024 * 1024, + QED_DEFAULT_CLUSTER_SIZE = 64 * 1024, + + /* Allocated clusters are tracked using a 2-level pagetable. Table size is + * a multiple of clusters so large maximum image sizes can be supported + * without jacking up the cluster size too much. + */ + QED_MIN_TABLE_SIZE = 1, /* in clusters */ + QED_MAX_TABLE_SIZE = 16, + QED_DEFAULT_TABLE_SIZE = 4, +}; + +typedef struct { + uint32_t magic; /* QED\0 */ + + uint32_t cluster_size; /* in bytes */ + uint32_t table_size; /* for L1 and L2 tables, in clusters */ + uint32_t header_size; /* in clusters */ + + uint64_t features; /* format feature bits */ + uint64_t compat_features; /* compatible feature bits */ + uint64_t l1_table_offset; /* in bytes */ + uint64_t image_size; /* total logical image size, in bytes */ + + /* if (features & QED_F_BACKING_FILE) */ + uint32_t backing_filename_offset; /* in bytes from start of header */ + uint32_t backing_filename_size; /* in bytes */ + + /* if (compat_features & QED_CF_BACKING_FORMAT) */ + uint32_t backing_fmt_offset; /* in bytes from start of header */ + uint32_t backing_fmt_size; /* in bytes */ +} QEDHeader; + +typedef struct { + BlockDriverState *bs; /* device */ + uint64_t file_size; /* length of image file, in bytes */ + + QEDHeader header; /* always cpu-endian */ + uint32_t table_nelems; + uint32_t l1_shift; + uint32_t l2_shift; + uint32_t l2_mask; +} BDRVQEDState; + +/** + * Utility functions + */ +static inline uint64_t qed_start_of_cluster(BDRVQEDState *s, uint64_t offset) +{ + return offset & ~(uint64_t)(s->header.cluster_size - 1); +} + +/** + * Test if a cluster offset is valid + */ +static inline bool qed_check_cluster_offset(BDRVQEDState *s, uint64_t offset) +{ + uint64_t header_size = (uint64_t)s->header.header_size * + s->header.cluster_size; + + if (offset & (s->header.cluster_size - 1)) { + return false; + } + return offset >= header_size && offset < s->file_size; +} + +/** + * Test if a table offset is valid + */ +static inline bool qed_check_table_offset(BDRVQEDState *s, uint64_t offset) +{ + uint64_t end_offset = offset + (s->header.table_size - 1) * + s->header.cluster_size; + + /* Overflow check */ + if (end_offset <= offset) { + return false; + } + + return qed_check_cluster_offset(s, offset) && + qed_check_cluster_offset(s, end_offset); +} + +#endif /* BLOCK_QED_H */