diff --git a/Makefile.objs b/Makefile.objs index 4a1eaa1..a5acb32 100644 --- a/Makefile.objs +++ b/Makefile.objs @@ -14,6 +14,7 @@ block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o block-nested-y += raw.o cow.o qcow.o vdi.o vmdk.o cloop.o dmg.o bochs.o vpc.o vvfat.o block-nested-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o +block-nested-y += qed.o qed-gencb.o qed-l2-cache.o qed-table.o qed-cluster.o block-nested-y += parallels.o nbd.o blkdebug.o sheepdog.o block-nested-$(CONFIG_WIN32) += raw-win32.o block-nested-$(CONFIG_POSIX) += raw-posix.o diff --git a/block/qcow2.c b/block/qcow2.c index a53014d..72c923a 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -767,28 +767,6 @@ static int qcow2_change_backing_file(BlockDriverState *bs, return qcow2_update_ext_header(bs, backing_file, backing_fmt); } -static int get_bits_from_size(size_t size) -{ - int res = 0; - - if (size == 0) { - return -1; - } - - while (size != 1) { - /* Not a power of two */ - if (size & 1) { - return -1; - } - - size >>= 1; - res++; - } - - return res; -} - - static int preallocate(BlockDriverState *bs) { uint64_t nb_sectors; diff --git a/block/qed-cluster.c b/block/qed-cluster.c new file mode 100644 index 0000000..6deea27 --- /dev/null +++ b/block/qed-cluster.c @@ -0,0 +1,136 @@ +/* + * QEMU Enhanced Disk Format Cluster functions + * + * 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" + +/** + * Count the number of contiguous data clusters + * + * @s: QED state + * @table: L2 table + * @index: First cluster index + * @n: Maximum number of clusters + * @offset: Set to first cluster offset + * + * This function scans tables for contiguous allocated or free clusters. + */ +static unsigned int qed_count_contiguous_clusters(BDRVQEDState *s, + QEDTable *table, + unsigned int index, + unsigned int n, + uint64_t *offset) +{ + unsigned int end = MIN(index + n, s->table_nelems); + uint64_t last = table->offsets[index]; + unsigned int i; + + *offset = last; + + for (i = index + 1; i < end; i++) { + if (last == 0) { + /* Counting free clusters */ + if (table->offsets[i] != 0) { + break; + } + } else { + /* Counting allocated clusters */ + if (table->offsets[i] != last + s->header.cluster_size) { + break; + } + last = table->offsets[i]; + } + } + return i - index; +} + +typedef struct { + BDRVQEDState *s; + uint64_t pos; + size_t len; + + QEDRequest *request; + + /* User callback */ + QEDFindClusterFunc *cb; + void *opaque; +} QEDFindClusterCB; + +static void qed_find_cluster_cb(void *opaque, int ret) +{ + QEDFindClusterCB *find_cluster_cb = opaque; + BDRVQEDState *s = find_cluster_cb->s; + QEDRequest *request = find_cluster_cb->request; + uint64_t offset = 0; + size_t len = 0; + unsigned int index; + unsigned int n; + + if (ret) { + ret = QED_CLUSTER_ERROR; + goto out; + } + + index = qed_l2_index(s, find_cluster_cb->pos); + n = qed_bytes_to_clusters(s, + qed_offset_into_cluster(s, find_cluster_cb->pos) + + find_cluster_cb->len); + n = qed_count_contiguous_clusters(s, request->l2_table->table, + index, n, &offset); + + ret = offset ? QED_CLUSTER_FOUND : QED_CLUSTER_L2; + len = MIN(find_cluster_cb->len, n * s->header.cluster_size - + qed_offset_into_cluster(s, find_cluster_cb->pos)); + +out: + find_cluster_cb->cb(find_cluster_cb->opaque, ret, offset, len); + qemu_free(find_cluster_cb); +} + +/** + * Find the offset of a data cluster + * + * @s: QED state + * @pos: Byte position in device + * @len: Number of bytes + * @cb: Completion function + * @opaque: User data for completion function + */ +void qed_find_cluster(BDRVQEDState *s, QEDRequest *request, uint64_t pos, + size_t len, QEDFindClusterFunc *cb, void *opaque) +{ + QEDFindClusterCB *find_cluster_cb; + uint64_t l2_offset; + + /* Limit length to L2 boundary. Requests are broken up at the L2 boundary + * so that a request acts on one L2 table at a time. + */ + len = MIN(len, (((pos >> s->l1_shift) + 1) << s->l1_shift) - pos); + + l2_offset = s->l1_table->offsets[qed_l1_index(s, pos)]; + if (!l2_offset) { + cb(opaque, QED_CLUSTER_L1, 0, len); + return; + } + + find_cluster_cb = qemu_malloc(sizeof(*find_cluster_cb)); + find_cluster_cb->s = s; + find_cluster_cb->pos = pos; + find_cluster_cb->len = len; + find_cluster_cb->cb = cb; + find_cluster_cb->opaque = opaque; + find_cluster_cb->request = request; + + qed_read_l2_table(s, request, l2_offset, + qed_find_cluster_cb, find_cluster_cb); +} diff --git a/block/qed-gencb.c b/block/qed-gencb.c new file mode 100644 index 0000000..d389e12 --- /dev/null +++ b/block/qed-gencb.c @@ -0,0 +1,32 @@ +/* + * QEMU Enhanced Disk Format + * + * Copyright IBM, Corp. 2010 + * + * Authors: + * Stefan Hajnoczi + * + * 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" + +void *gencb_alloc(size_t len, BlockDriverCompletionFunc *cb, void *opaque) +{ + GenericCB *gencb = qemu_malloc(len); + gencb->cb = cb; + gencb->opaque = opaque; + return gencb; +} + +void gencb_complete(void *opaque, int ret) +{ + GenericCB *gencb = opaque; + BlockDriverCompletionFunc *cb = gencb->cb; + void *user_opaque = gencb->opaque; + + qemu_free(gencb); + cb(user_opaque, ret); +} diff --git a/block/qed-l2-cache.c b/block/qed-l2-cache.c new file mode 100644 index 0000000..747a629 --- /dev/null +++ b/block/qed-l2-cache.c @@ -0,0 +1,131 @@ +/* + * QEMU Enhanced Disk Format L2 Cache + * + * Copyright IBM, Corp. 2010 + * + * Authors: + * 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" + +/* Each L2 holds 2GB so this let's us fully cache a 100GB disk */ +#define MAX_L2_CACHE_SIZE 50 + +/** + * Initialize the L2 cache + */ +void qed_init_l2_cache(L2TableCache *l2_cache, + L2TableAllocFunc *alloc_l2_table, + void *alloc_l2_table_opaque) +{ + QTAILQ_INIT(&l2_cache->entries); + l2_cache->n_entries = 0; + l2_cache->alloc_l2_table = alloc_l2_table; + l2_cache->alloc_l2_table_opaque = alloc_l2_table_opaque; +} + +/** + * Free the L2 cache + */ +void qed_free_l2_cache(L2TableCache *l2_cache) +{ + CachedL2Table *entry, *next_entry; + + QTAILQ_FOREACH_SAFE(entry, &l2_cache->entries, node, next_entry) { + qemu_free(entry->table); + qemu_free(entry); + } +} + +/** + * Allocate an uninitialized entry from the cache + * + * The returned entry has a reference count of 1 and is owned by the caller. + */ +CachedL2Table *qed_alloc_l2_cache_entry(L2TableCache *l2_cache) +{ + CachedL2Table *entry; + + entry = qemu_mallocz(sizeof(*entry)); + entry->table = l2_cache->alloc_l2_table(l2_cache->alloc_l2_table_opaque); + entry->ref++; + + return entry; +} + +/** + * Decrease an entry's reference count and free if necessary when the reference + * count drops to zero. + */ +void qed_unref_l2_cache_entry(L2TableCache *l2_cache, CachedL2Table *entry) +{ + if (!entry) { + return; + } + + entry->ref--; + if (entry->ref == 0) { + qemu_free(entry->table); + qemu_free(entry); + } +} + +/** + * Find an entry in the L2 cache. This may return NULL and it's up to the + * caller to satisfy the cache miss. + * + * For a cached entry, this function increases the reference count and returns + * the entry. + */ +CachedL2Table *qed_find_l2_cache_entry(L2TableCache *l2_cache, uint64_t offset) +{ + CachedL2Table *entry; + + QTAILQ_FOREACH(entry, &l2_cache->entries, node) { + if (entry->offset == offset) { + entry->ref++; + return entry; + } + } + return NULL; +} + +/** + * Commit an L2 cache entry into the cache. This is meant to be used as part of + * the process to satisfy a cache miss. A caller would allocate an entry which + * is not actually in the L2 cache and then once the entry was valid and + * present on disk, the entry can be committed into the cache. + * + * Since the cache is write-through, it's important that this function is not + * called until the entry is present on disk and the L1 has been updated to + * point to the entry. + * + * This function will take a reference to the entry so the caller is still + * responsible for unreferencing the entry. + */ +void qed_commit_l2_cache_entry(L2TableCache *l2_cache, CachedL2Table *l2_table) +{ + CachedL2Table *entry; + + entry = qed_find_l2_cache_entry(l2_cache, l2_table->offset); + if (entry) { + qed_unref_l2_cache_entry(l2_cache, entry); + return; + } + + if (l2_cache->n_entries >= MAX_L2_CACHE_SIZE) { + entry = QTAILQ_FIRST(&l2_cache->entries); + QTAILQ_REMOVE(&l2_cache->entries, entry, node); + l2_cache->n_entries--; + qed_unref_l2_cache_entry(l2_cache, entry); + } + + l2_table->ref++; + l2_cache->n_entries++; + QTAILQ_INSERT_TAIL(&l2_cache->entries, l2_table, node); +} diff --git a/block/qed-table.c b/block/qed-table.c new file mode 100644 index 0000000..9a72582 --- /dev/null +++ b/block/qed-table.c @@ -0,0 +1,242 @@ +/* + * QEMU Enhanced Disk Format Table I/O + * + * 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" + +typedef struct { + GenericCB gencb; + BDRVQEDState *s; + QEDTable *table; + + struct iovec iov; + QEMUIOVector qiov; +} QEDReadTableCB; + +static void qed_read_table_cb(void *opaque, int ret) +{ + QEDReadTableCB *read_table_cb = opaque; + QEDTable *table = read_table_cb->table; + int noffsets = read_table_cb->iov.iov_len / sizeof(uint64_t); + int i; + + /* Handle I/O error */ + if (ret) { + goto out; + } + + /* Byteswap and verify offsets */ + for (i = 0; i < noffsets; i++) { + table->offsets[i] = le64_to_cpu(table->offsets[i]); + } + +out: + /* Completion */ + gencb_complete(&read_table_cb->gencb, ret); +} + +static void qed_read_table(BDRVQEDState *s, uint64_t offset, QEDTable *table, + BlockDriverCompletionFunc *cb, void *opaque) +{ + QEDReadTableCB *read_table_cb = gencb_alloc(sizeof(*read_table_cb), + cb, opaque); + QEMUIOVector *qiov = &read_table_cb->qiov; + BlockDriverAIOCB *aiocb; + + read_table_cb->s = s; + read_table_cb->table = table; + read_table_cb->iov.iov_base = table->offsets, + read_table_cb->iov.iov_len = s->header.cluster_size * s->header.table_size, + + qemu_iovec_init_external(qiov, &read_table_cb->iov, 1); + aiocb = bdrv_aio_readv(s->bs->file, offset / BDRV_SECTOR_SIZE, qiov, + read_table_cb->iov.iov_len / BDRV_SECTOR_SIZE, + qed_read_table_cb, read_table_cb); + if (!aiocb) { + qed_read_table_cb(read_table_cb, -EIO); + } +} + +typedef struct { + GenericCB gencb; + BDRVQEDState *s; + QEDTable *orig_table; + bool flush; /* flush after write? */ + + struct iovec iov; + QEMUIOVector qiov; + + QEDTable table; +} QEDWriteTableCB; + +static void qed_write_table_cb(void *opaque, int ret) +{ + QEDWriteTableCB *write_table_cb = opaque; + + if (ret) { + goto out; + } + + if (write_table_cb->flush) { + /* We still need to flush first */ + write_table_cb->flush = false; + bdrv_aio_flush(write_table_cb->s->bs, qed_write_table_cb, + write_table_cb); + return; + } + +out: + gencb_complete(&write_table_cb->gencb, ret); + return; +} + +/** + * Write out an updated part or all of a table + * + * @s: QED state + * @offset: Offset of table in image file, in bytes + * @table: Table + * @index: Index of first element + * @n: Number of elements + * @flush: Whether or not to sync to disk + * @cb: Completion function + * @opaque: Argument for completion function + */ +static void qed_write_table(BDRVQEDState *s, uint64_t offset, QEDTable *table, + unsigned int index, unsigned int n, bool flush, + BlockDriverCompletionFunc *cb, void *opaque) +{ + QEDWriteTableCB *write_table_cb; + BlockDriverAIOCB *aiocb; + unsigned int sector_mask = BDRV_SECTOR_SIZE / sizeof(uint64_t) - 1; + unsigned int start, end, i; + size_t len_bytes; + + /* Calculate indices of the first and one after last elements */ + start = index & ~sector_mask; + end = (index + n + sector_mask) & ~sector_mask; + + len_bytes = (end - start) * sizeof(uint64_t); + + write_table_cb = gencb_alloc(sizeof(*write_table_cb) + len_bytes, + cb, opaque); + write_table_cb->s = s; + write_table_cb->orig_table = table; + write_table_cb->flush = flush; + write_table_cb->iov.iov_base = write_table_cb->table.offsets; + write_table_cb->iov.iov_len = len_bytes; + qemu_iovec_init_external(&write_table_cb->qiov, &write_table_cb->iov, 1); + + /* Byteswap table */ + for (i = start; i < end; i++) { + write_table_cb->table.offsets[i - start] = cpu_to_le64(table->offsets[i]); + } + + /* Adjust for offset into table */ + offset += start * sizeof(uint64_t); + + aiocb = bdrv_aio_writev(s->bs->file, offset / BDRV_SECTOR_SIZE, + &write_table_cb->qiov, + write_table_cb->iov.iov_len / BDRV_SECTOR_SIZE, + qed_write_table_cb, write_table_cb); + if (!aiocb) { + qed_write_table_cb(write_table_cb, -EIO); + } +} + +static void qed_read_l1_table_cb(void *opaque, int ret) +{ + *(int *)opaque = ret; +} + +/** + * Read the L1 table synchronously + */ +int qed_read_l1_table(BDRVQEDState *s) +{ + int ret = -EINPROGRESS; + + /* TODO push/pop async context? */ + + qed_read_table(s, s->header.l1_table_offset, + s->l1_table, qed_read_l1_table_cb, &ret); + while (ret == -EINPROGRESS) { + qemu_aio_wait(); + } + return ret; +} + +void qed_write_l1_table(BDRVQEDState *s, unsigned int index, unsigned int n, + BlockDriverCompletionFunc *cb, void *opaque) +{ + qed_write_table(s, s->header.l1_table_offset, + s->l1_table, index, n, false, cb, opaque); +} + +typedef struct { + GenericCB gencb; + BDRVQEDState *s; + uint64_t l2_offset; + QEDRequest *request; +} QEDReadL2TableCB; + +static void qed_read_l2_table_cb(void *opaque, int ret) +{ + QEDReadL2TableCB *read_l2_table_cb = opaque; + QEDRequest *request = read_l2_table_cb->request; + BDRVQEDState *s = read_l2_table_cb->s; + + if (ret) { + /* can't trust loaded L2 table anymore */ + qed_unref_l2_cache_entry(&s->l2_cache, request->l2_table); + request->l2_table = NULL; + } else { + request->l2_table->offset = read_l2_table_cb->l2_offset; + qed_commit_l2_cache_entry(&s->l2_cache, request->l2_table); + } + + gencb_complete(&read_l2_table_cb->gencb, ret); +} + +void qed_read_l2_table(BDRVQEDState *s, QEDRequest *request, uint64_t offset, + BlockDriverCompletionFunc *cb, void *opaque) +{ + QEDReadL2TableCB *read_l2_table_cb; + + qed_unref_l2_cache_entry(&s->l2_cache, request->l2_table); + + /* Check for cached L2 entry */ + request->l2_table = qed_find_l2_cache_entry(&s->l2_cache, offset); + if (request->l2_table) { + cb(opaque, 0); + return; + } + + request->l2_table = qed_alloc_l2_cache_entry(&s->l2_cache); + + read_l2_table_cb = gencb_alloc(sizeof(*read_l2_table_cb), cb, opaque); + read_l2_table_cb->s = s; + read_l2_table_cb->l2_offset = offset; + read_l2_table_cb->request = request; + + qed_read_table(s, offset, request->l2_table->table, + qed_read_l2_table_cb, read_l2_table_cb); +} + +void qed_write_l2_table(BDRVQEDState *s, QEDRequest *request, + unsigned int index, unsigned int n, bool flush, + BlockDriverCompletionFunc *cb, void *opaque) +{ + qed_write_table(s, request->l2_table->offset, + request->l2_table->table, index, n, flush, cb, opaque); +} diff --git a/block/qed.c b/block/qed.c new file mode 100644 index 0000000..cf64418 --- /dev/null +++ b/block/qed.c @@ -0,0 +1,1103 @@ +/* + * 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" + +/* TODO blkdebug support */ +/* TODO BlockDriverState::buffer_alignment */ +/* TODO check L2 table sizes before accessing them? */ +/* TODO skip zero prefill since the filesystem should zero the sectors anyway */ +/* TODO if a table element's offset is invalid then the image is broken. If + * there was a power failure and the table update reached storage but the data + * being pointed to did not, forget about the lost data by clearing the offset. + * However, need to be careful to detect invalid offsets for tables that are + * read *after* more clusters have been allocated. */ + +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, +}; + +static void qed_aio_cancel(BlockDriverAIOCB *acb) +{ + qemu_aio_release(acb); +} + +static AIOPool qed_aio_pool = { + .aiocb_size = sizeof(QEDAIOCB), + .cancel = qed_aio_cancel, +}; + +/** + * Allocate memory that satisfies image file and backing file alignment requirements + * + * TODO make this common and consider propagating max buffer_alignment to the root image + */ +static void *qed_memalign(BDRVQEDState *s, size_t len) +{ + size_t align = s->bs->file->buffer_alignment; + BlockDriverState *backing_hd = s->bs->backing_hd; + + if (backing_hd && backing_hd->buffer_alignment > align) { + align = backing_hd->buffer_alignment; + } + + return qemu_memalign(align, len); +} + +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->first_cluster = le32_to_cpu(le->first_cluster); + 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_file_offset = le32_to_cpu(le->backing_file_offset); + cpu->backing_file_size = le32_to_cpu(le->backing_file_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->first_cluster = cpu_to_le32(cpu->first_cluster); + 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_file_offset = cpu_to_le32(cpu->backing_file_offset); + le->backing_file_size = cpu_to_le32(cpu->backing_file_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) / 8; + 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; +} + +/** + * Test if a byte offset is cluster aligned and within the image file + */ +static bool qed_check_byte_offset(BDRVQEDState *s, uint64_t offset) +{ + if (offset & (s->header.cluster_size - 1)) { + return false; + } + if (offset == 0) { + return false; /* first cluster contains the header and is not valid */ + } + return offset < s->file_size; +} + +/** + * 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; +} + +/** + * Allocate new clusters + * + * @s: QED state + * @n: Number of contiguous clusters to allocate + * @offset: Offset of first allocated cluster, filled in on success + */ +static int qed_alloc_clusters(BDRVQEDState *s, unsigned int n, uint64_t *offset) +{ + *offset = s->file_size; + s->file_size += n * s->header.cluster_size; + return 0; +} + +static QEDTable *qed_alloc_table(void *opaque) +{ + BDRVQEDState *s = opaque; + + /* Honor O_DIRECT memory alignment requirements */ + return qed_memalign(s, s->header.cluster_size * s->header.table_size); +} + +/** + * Allocate a new zeroed L2 table + */ +static CachedL2Table *qed_new_l2_table(BDRVQEDState *s) +{ + uint64_t offset; + int ret; + CachedL2Table *l2_table; + + ret = qed_alloc_clusters(s, s->header.table_size, &offset); + if (ret) { + return NULL; + } + + l2_table = qed_alloc_l2_cache_entry(&s->l2_cache); + l2_table->offset = offset; + + memset(l2_table->table->offsets, 0, + s->header.cluster_size * s->header.table_size); + return l2_table; +} + +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; + QSIMPLEQ_INIT(&s->allocating_write_reqs); + + 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 + s->header.cluster_size - 1); + + 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_byte_offset(s, s->header.l1_table_offset)) { + return -EINVAL; + } + + s->table_nelems = (s->header.cluster_size * s->header.table_size) / + sizeof(s->l1_table->offsets[0]); + 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_file_offset, + s->header.backing_file_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; + } + } + } + + s->l1_table = qed_alloc_table(s); + qed_init_l2_cache(&s->l2_cache, qed_alloc_table, s); + + ret = qed_read_l1_table(s); + if (ret) { + qed_free_l2_cache(&s->l2_cache); + qemu_free(s->l1_table); + } + return ret; +} + +static void bdrv_qed_close(BlockDriverState *bs) +{ + BDRVQEDState *s = bs->opaque; + + qed_free_l2_cache(&s->l2_cache); + qemu_free(s->l1_table); +} + +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, + .first_cluster = 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_file_offset = sizeof(le_header); + header.backing_file_size = strlen(backing_file); + if (backing_fmt) { + header.compat_features |= QED_CF_BACKING_FORMAT; + header.backing_fmt_offset = header.backing_file_offset + + header.backing_file_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_file_size) != header.backing_file_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)) { + fprintf(stderr, + "QED image size must be a non-zero multiple of cluster size and less than %s\n", + bytes_to_str(qed_max_image_size(cluster_size, table_size))); + return -EINVAL; + } + + return qed_create(filename, cluster_size, image_size, table_size, + backing_file, backing_fmt); +} + +typedef struct { + int is_allocated; + int *pnum; +} QEDIsAllocatedCB; + +static void qed_is_allocated_cb(void *opaque, int ret, uint64_t offset, size_t len) +{ + QEDIsAllocatedCB *cb = opaque; + *cb->pnum = len / BDRV_SECTOR_SIZE; + cb->is_allocated = ret == QED_CLUSTER_FOUND; +} + +static int bdrv_qed_is_allocated(BlockDriverState *bs, int64_t sector_num, + int nb_sectors, int *pnum) +{ + BDRVQEDState *s = bs->opaque; + uint64_t pos = (uint64_t)sector_num * BDRV_SECTOR_SIZE; + size_t len = (size_t)nb_sectors * BDRV_SECTOR_SIZE; + QEDIsAllocatedCB cb = { + .is_allocated = -1, + .pnum = pnum, + }; + QEDRequest request = { .l2_table = NULL }; + + /* TODO push/pop async context? */ + + qed_find_cluster(s, &request, pos, len, qed_is_allocated_cb, &cb); + + while (cb.is_allocated == -1) { + qemu_aio_wait(); + } + + qed_unref_l2_cache_entry(&s->l2_cache, request.l2_table); + + return cb.is_allocated; +} + +static int bdrv_qed_make_empty(BlockDriverState *bs) +{ + return -ENOTSUP; /* TODO */ +} + +static BDRVQEDState *acb_to_s(QEDAIOCB *acb) +{ + return acb->common.bs->opaque; +} + +typedef struct { + GenericCB gencb; + BDRVQEDState *s; + QEMUIOVector qiov; + struct iovec iov; + uint64_t offset; +} CopyFromBackingFileCB; + +static void qed_copy_from_backing_file_cb(void *opaque, int ret) +{ + CopyFromBackingFileCB *copy_cb = opaque; + qemu_vfree(copy_cb->iov.iov_base); + gencb_complete(©_cb->gencb, ret); +} + +static void qed_copy_from_backing_file_write(void *opaque, int ret) +{ + CopyFromBackingFileCB *copy_cb = opaque; + BDRVQEDState *s = copy_cb->s; + BlockDriverAIOCB *aiocb; + + if (ret) { + qed_copy_from_backing_file_cb(copy_cb, ret); + return; + } + + aiocb = bdrv_aio_writev(s->bs->file, copy_cb->offset / BDRV_SECTOR_SIZE, + ©_cb->qiov, + copy_cb->qiov.size / BDRV_SECTOR_SIZE, + qed_copy_from_backing_file_cb, copy_cb); + if (!aiocb) { + qed_copy_from_backing_file_cb(copy_cb, -EIO); + } +} + +/** + * Copy data from backing file into the image + * + * @s: QED state + * @pos: Byte position in device + * @len: Number of bytes + * @offset: Byte offset in image file + * @cb: Completion function + * @opaque: User data for completion function + */ +static void qed_copy_from_backing_file(BDRVQEDState *s, uint64_t pos, + uint64_t len, uint64_t offset, + BlockDriverCompletionFunc *cb, + void *opaque) +{ + CopyFromBackingFileCB *copy_cb; + BlockDriverAIOCB *aiocb; + + /* Skip copy entirely if there is no work to do */ + if (len == 0) { + cb(opaque, 0); + return; + } + + copy_cb = gencb_alloc(sizeof(*copy_cb), cb, opaque); + copy_cb->s = s; + copy_cb->offset = offset; + copy_cb->iov.iov_base = qed_memalign(s, len); + copy_cb->iov.iov_len = len; + qemu_iovec_init_external(©_cb->qiov, ©_cb->iov, 1); + + /* Zero sectors if there is no backing file */ + if (!s->bs->backing_hd) { + memset(copy_cb->iov.iov_base, 0, len); + qed_copy_from_backing_file_write(copy_cb, 0); + return; + } + + aiocb = bdrv_aio_readv(s->bs->backing_hd, pos / BDRV_SECTOR_SIZE, + ©_cb->qiov, len / BDRV_SECTOR_SIZE, + qed_copy_from_backing_file_write, copy_cb); + if (!aiocb) { + qed_copy_from_backing_file_cb(copy_cb, -EIO); + } +} + +/** + * Link one or more contiguous clusters into a table + * + * @s: QED state + * @table: L2 table + * @index: First cluster index + * @n: Number of contiguous clusters + * @cluster: First cluster byte offset in image file + */ +static void qed_update_l2_table(BDRVQEDState *s, QEDTable *table, int index, + unsigned int n, uint64_t cluster) +{ + int i; + for (i = index; i < index + n; i++) { + table->offsets[i] = cluster; + cluster += s->header.cluster_size; + } +} + +static void qed_aio_next_io(void *opaque, int ret); + +static void qed_aio_complete_bh(void *opaque) +{ + QEDAIOCB *acb = opaque; + BlockDriverCompletionFunc *cb = acb->common.cb; + void *user_opaque = acb->common.opaque; + int ret = acb->bh_ret; + + qemu_bh_delete(acb->bh); + qemu_aio_release(acb); + + /* Invoke callback */ + cb(user_opaque, ret); +} + +static void qed_aio_complete(QEDAIOCB *acb, int ret) +{ + BDRVQEDState *s = acb_to_s(acb); + + /* Free resources */ + qemu_iovec_destroy(&acb->cur_qiov); + qed_unref_l2_cache_entry(&s->l2_cache, acb->request.l2_table); + + /* Arrange for a bh to invoke the completion function */ + acb->bh_ret = ret; + acb->bh = qemu_bh_new(qed_aio_complete_bh, acb); + qemu_bh_schedule(acb->bh); + + /* Start next allocating write request waiting behind this one. Note that + * requests enqueue themselves when they first hit an unallocated cluster + * but they wait until the entire request is finished before waking up the + * next request in the queue. This ensures that we don't cycle through + * requests multiple times but rather finish one at a time completely. + */ + if (acb == QSIMPLEQ_FIRST(&s->allocating_write_reqs)) { + QSIMPLEQ_REMOVE_HEAD(&s->allocating_write_reqs, next); + acb = QSIMPLEQ_FIRST(&s->allocating_write_reqs); + if (acb) { + qed_aio_next_io(acb, 0); + } + } +} + +/** + * Construct an iovec array for the current cluster + * + * @acb: I/O request + * @len: Maximum number of bytes + */ +static void qed_acb_build_qiov(QEDAIOCB *acb, size_t len) +{ + struct iovec *iov_end = &acb->qiov->iov[acb->qiov->niov]; + size_t iov_offset = acb->cur_iov_offset; + struct iovec *iov = acb->cur_iov; + + /* Fill in one cluster's worth of iovecs */ + while (iov != iov_end && len > 0) { + size_t nbytes = MIN(iov->iov_len - iov_offset, len); + + qemu_iovec_add(&acb->cur_qiov, iov->iov_base + iov_offset, nbytes); + iov_offset += nbytes; + len -= nbytes; + + if (iov_offset >= iov->iov_len) { + iov_offset = 0; + iov++; + } + } + + /* Stash state for next time */ + acb->cur_iov = iov; + acb->cur_iov_offset = iov_offset; +} + +/** + * Commit the current L2 table to the cache + */ +static void qed_commit_l2_update(void *opaque, int ret) +{ + QEDAIOCB *acb = opaque; + BDRVQEDState *s = acb_to_s(acb); + + qed_commit_l2_cache_entry(&s->l2_cache, acb->request.l2_table); + qed_aio_next_io(opaque, ret); +} + +/** + * Update L1 table with new L2 table offset and write it out + */ +static void qed_aio_write_l1_update(void *opaque, int ret) +{ + QEDAIOCB *acb = opaque; + BDRVQEDState *s = acb_to_s(acb); + int index; + + if (ret) { + qed_aio_complete(acb, ret); + return; + } + + index = qed_l1_index(s, acb->cur_pos); + s->l1_table->offsets[index] = acb->request.l2_table->offset; + + qed_write_l1_table(s, index, 1, qed_commit_l2_update, acb); +} + +/** + * Update L2 table with new cluster offsets and write them out + */ +static void qed_aio_write_l2_update(void *opaque, int ret) +{ + QEDAIOCB *acb = opaque; + BDRVQEDState *s = acb_to_s(acb); + bool need_alloc = acb->find_cluster_ret == QED_CLUSTER_L1; + int index; + + if (ret) { + goto err; + } + + if (need_alloc) { + qed_unref_l2_cache_entry(&s->l2_cache, acb->request.l2_table); + acb->request.l2_table = qed_new_l2_table(s); + if (!acb->request.l2_table) { + ret = -EIO; + goto err; + } + } + + index = qed_l2_index(s, acb->cur_pos); + qed_update_l2_table(s, acb->request.l2_table->table, index, acb->cur_nclusters, + acb->cur_cluster); + + if (need_alloc) { + /* Write out the whole new L2 table */ + qed_write_l2_table(s, &acb->request, 0, s->table_nelems, true, + qed_aio_write_l1_update, acb); + } else { + /* Write out only the updated part of the L2 table */ + qed_write_l2_table(s, &acb->request, index, acb->cur_nclusters, false, + qed_aio_next_io, acb); + } + return; + +err: + qed_aio_complete(acb, ret); +} + +/** + * Write data to the image file + */ +static void qed_aio_write_main(void *opaque, int ret) +{ + QEDAIOCB *acb = opaque; + BDRVQEDState *s = acb_to_s(acb); + bool need_alloc = acb->find_cluster_ret != QED_CLUSTER_FOUND; + uint64_t offset = acb->cur_cluster; + BlockDriverAIOCB *file_acb; + + if (ret) { + qed_aio_complete(acb, ret); + return; + } + + offset += qed_offset_into_cluster(s, acb->cur_pos); + file_acb = bdrv_aio_writev(s->bs->file, offset / BDRV_SECTOR_SIZE, + &acb->cur_qiov, + acb->cur_qiov.size / BDRV_SECTOR_SIZE, + need_alloc ? qed_aio_write_l2_update : + qed_aio_next_io, + acb); + if (!file_acb) { + qed_aio_complete(acb, -EIO); + } +} + +/** + * Populate back untouched region of new data cluster + */ +static void qed_aio_write_postfill(void *opaque, int ret) +{ + QEDAIOCB *acb = opaque; + BDRVQEDState *s = acb_to_s(acb); + uint64_t start = acb->cur_pos + acb->cur_qiov.size; + uint64_t len = qed_start_of_cluster(s, start + s->header.cluster_size - 1) - start; + uint64_t offset = acb->cur_cluster + qed_offset_into_cluster(s, acb->cur_pos) + acb->cur_qiov.size; + + if (ret) { + qed_aio_complete(acb, ret); + return; + } + + qed_copy_from_backing_file(s, start, len, offset, + qed_aio_write_main, acb); +} + +/** + * Populate front untouched region of new data cluster + */ +static void qed_aio_write_prefill(QEDAIOCB *acb) +{ + BDRVQEDState *s = acb_to_s(acb); + uint64_t start = qed_start_of_cluster(s, acb->cur_pos); + uint64_t len = qed_offset_into_cluster(s, acb->cur_pos); + + qed_copy_from_backing_file(s, start, len, acb->cur_cluster, + qed_aio_write_postfill, acb); +} + +/** + * Write data cluster + * + * @opaque: Write request + * @ret: QED_CLUSTER_FOUND, QED_CLUSTER_L2, QED_CLUSTER_L1, + * or QED_CLUSTER_ERROR + * @offset: Cluster offset in bytes + * @len: Length in bytes + * + * Callback from qed_find_cluster(). + */ +static void qed_aio_write_data(void *opaque, int ret, + uint64_t offset, size_t len) +{ + QEDAIOCB *acb = opaque; + BDRVQEDState *s = acb_to_s(acb); + bool need_alloc = ret != QED_CLUSTER_FOUND; + + if (ret == QED_CLUSTER_ERROR) { + goto err; + } + + /* Freeze this request if another allocating write is in progress */ + if (need_alloc) { + if (acb != QSIMPLEQ_FIRST(&s->allocating_write_reqs)) { + QSIMPLEQ_INSERT_TAIL(&s->allocating_write_reqs, acb, next); + } + if (acb != QSIMPLEQ_FIRST(&s->allocating_write_reqs)) { + return; /* wait for existing request to finish */ + } + } + + acb->cur_nclusters = qed_bytes_to_clusters(s, + qed_offset_into_cluster(s, acb->cur_pos) + len); + + if (need_alloc) { + if (qed_alloc_clusters(s, acb->cur_nclusters, &offset) != 0) { + goto err; + } + } + + acb->find_cluster_ret = ret; + acb->cur_cluster = offset; + qed_acb_build_qiov(acb, len); + + if (need_alloc) { + qed_aio_write_prefill(acb); + } else { + qed_aio_write_main(acb, 0); + } + return; + +err: + qed_aio_complete(acb, -EIO); +} + +/** + * Read data cluster + * + * @opaque: Read request + * @ret: QED_CLUSTER_FOUND, QED_CLUSTER_L2, QED_CLUSTER_L1, + * or QED_CLUSTER_ERROR + * @offset: Cluster offset in bytes + * @len: Length in bytes + * + * Callback from qed_find_cluster(). + */ +static void qed_aio_read_data(void *opaque, int ret, + uint64_t offset, size_t len) +{ + QEDAIOCB *acb = opaque; + BDRVQEDState *s = acb_to_s(acb); + BlockDriverState *bs = acb->common.bs; + BlockDriverState *file = bs->file; + BlockDriverAIOCB *file_acb; + + if (ret == QED_CLUSTER_ERROR) { + goto err; + } + + qed_acb_build_qiov(acb, len); + + /* Adjust offset into cluster */ + offset += qed_offset_into_cluster(s, acb->cur_pos); + + /* Handle backing file and unallocated sparse hole reads */ + if (ret != QED_CLUSTER_FOUND) { + if (!bs->backing_hd) { + qemu_iovec_zero(&acb->cur_qiov); + qed_aio_next_io(acb, 0); + return; + } + + /* Pass through read to backing file */ + offset = acb->cur_pos; + file = bs->backing_hd; + } + + file_acb = bdrv_aio_readv(file, offset / BDRV_SECTOR_SIZE, + &acb->cur_qiov, + acb->cur_qiov.size / BDRV_SECTOR_SIZE, + qed_aio_next_io, acb); + if (!file_acb) { + goto err; + } + return; + +err: + qed_aio_complete(acb, -EIO); +} + +/** + * Begin next I/O or complete the request + */ +static void qed_aio_next_io(void *opaque, int ret) +{ + QEDAIOCB *acb = opaque; + BDRVQEDState *s = acb_to_s(acb); + QEDFindClusterFunc *io_fn = + acb->is_write ? qed_aio_write_data : qed_aio_read_data; + + /* Handle I/O error */ + if (ret) { + qed_aio_complete(acb, ret); + return; + } + + acb->cur_pos += acb->cur_qiov.size; + qemu_iovec_reset(&acb->cur_qiov); + + /* Complete request */ + if (acb->cur_pos >= acb->end_pos) { + qed_aio_complete(acb, 0); + return; + } + + /* Find next cluster and start I/O */ + qed_find_cluster(s, &acb->request, + acb->cur_pos, acb->end_pos - acb->cur_pos, + io_fn, acb); +} + +static BlockDriverAIOCB *qed_aio_setup(BlockDriverState *bs, + int64_t sector_num, + QEMUIOVector *qiov, int nb_sectors, + BlockDriverCompletionFunc *cb, + void *opaque, bool is_write) +{ + QEDAIOCB *acb = qemu_aio_get(&qed_aio_pool, bs, cb, opaque); + + acb->is_write = is_write; + acb->qiov = qiov; + acb->cur_iov = acb->qiov->iov; + acb->cur_iov_offset = 0; + acb->cur_pos = (uint64_t)sector_num * BDRV_SECTOR_SIZE; + acb->end_pos = acb->cur_pos + nb_sectors * BDRV_SECTOR_SIZE; + acb->request.l2_table = NULL; + qemu_iovec_init(&acb->cur_qiov, qiov->niov); + + /* Start request */ + qed_aio_next_io(acb, 0); + return &acb->common; +} + +static BlockDriverAIOCB *bdrv_qed_aio_readv(BlockDriverState *bs, + int64_t sector_num, + QEMUIOVector *qiov, int nb_sectors, + BlockDriverCompletionFunc *cb, + void *opaque) +{ + return qed_aio_setup(bs, sector_num, qiov, nb_sectors, cb, opaque, false); +} + +static BlockDriverAIOCB *bdrv_qed_aio_writev(BlockDriverState *bs, + int64_t sector_num, + QEMUIOVector *qiov, int nb_sectors, + BlockDriverCompletionFunc *cb, + void *opaque) +{ + return qed_aio_setup(bs, sector_num, qiov, nb_sectors, cb, opaque, true); +} + +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; /* TODO */ +} + +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) +{ + return -ENOTSUP; /* TODO */ +} + +static int bdrv_qed_check(BlockDriverState* bs, BdrvCheckResult *result) +{ + return -ENOTSUP; /* TODO */ +} + +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..4711fbd --- /dev/null +++ b/block/qed.h @@ -0,0 +1,212 @@ +/* + * 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. + */ + +typedef struct { + uint32_t magic; /* QED */ + + uint32_t cluster_size; /* in bytes */ + uint32_t table_size; /* table size, in clusters */ + uint32_t first_cluster; /* first usable cluster */ + + uint64_t features; /* format feature bits */ + uint64_t compat_features; /* compatible feature bits */ + uint64_t l1_table_offset; /* L1 table offset, in bytes */ + uint64_t image_size; /* total image size, in bytes */ + + uint32_t backing_file_offset; /* in bytes from start of header */ + uint32_t backing_file_size; /* in bytes */ + uint32_t backing_fmt_offset; /* in bytes from start of header */ + uint32_t backing_fmt_size; /* in bytes */ +} QEDHeader; + +typedef struct { + uint64_t offsets[0]; /* in bytes */ +} QEDTable; + +/* The L2 cache is a simple write-through cache for L2 structures */ +typedef struct CachedL2Table { + QEDTable *table; + uint64_t offset; /* offset=0 indicates an invalidate entry */ + QTAILQ_ENTRY(CachedL2Table) node; + int ref; +} CachedL2Table; + +/** + * Allocate an L2 table + * + * This callback is used by the L2 cache to allocate tables without knowing + * their size or alignment requirements. + */ +typedef QEDTable *L2TableAllocFunc(void *opaque); + +typedef struct { + QTAILQ_HEAD(, CachedL2Table) entries; + unsigned int n_entries; + L2TableAllocFunc *alloc_l2_table; + void *alloc_l2_table_opaque; +} L2TableCache; + +typedef struct QEDRequest { + CachedL2Table *l2_table; +} QEDRequest; + +typedef struct QEDAIOCB { + BlockDriverAIOCB common; + QEMUBH *bh; + int bh_ret; /* final return status for completion bh */ + QSIMPLEQ_ENTRY(QEDAIOCB) next; /* next request */ + bool is_write; /* false - read, true - write */ + + /* User scatter-gather list */ + QEMUIOVector *qiov; + struct iovec *cur_iov; /* current iovec to process */ + size_t cur_iov_offset; /* byte count already processed in iovec */ + + /* Current cluster scatter-gather list */ + QEMUIOVector cur_qiov; + uint64_t cur_pos; /* position on block device, in bytes */ + uint64_t end_pos; + uint64_t cur_cluster; /* cluster offset in image file */ + unsigned int cur_nclusters; /* number of clusters being accessed */ + int find_cluster_ret; /* used for L1/L2 update */ + + QEDRequest request; +} QEDAIOCB; + +typedef struct { + BlockDriverState *bs; /* device */ + uint64_t file_size; /* length of image file, in bytes */ + + QEDHeader header; /* always cpu-endian */ + QEDTable *l1_table; + L2TableCache l2_cache; /* l2 table cache */ + uint32_t table_nelems; + uint32_t l1_shift; + uint32_t l2_shift; + uint32_t l2_mask; + + /* Allocating write request queue */ + QSIMPLEQ_HEAD(, QEDAIOCB) allocating_write_reqs; +} BDRVQEDState; + +enum { + QED_CLUSTER_FOUND, /* cluster found */ + QED_CLUSTER_L2, /* cluster missing in L2 */ + QED_CLUSTER_L1, /* cluster missing in L1 */ + QED_CLUSTER_ERROR, /* error looking up cluster */ +}; + +typedef void QEDFindClusterFunc(void *opaque, int ret, uint64_t offset, size_t len); + +/** + * Generic callback for chaining async callbacks + */ +typedef struct { + BlockDriverCompletionFunc *cb; + void *opaque; +} GenericCB; + +void *gencb_alloc(size_t len, BlockDriverCompletionFunc *cb, void *opaque); +void gencb_complete(void *opaque, int ret); + +/** + * L2 cache functions + */ +void qed_init_l2_cache(L2TableCache *l2_cache, L2TableAllocFunc *alloc_l2_table, void *alloc_l2_table_opaque); +void qed_free_l2_cache(L2TableCache *l2_cache); +CachedL2Table *qed_alloc_l2_cache_entry(L2TableCache *l2_cache); +void qed_unref_l2_cache_entry(L2TableCache *l2_cache, CachedL2Table *entry); +CachedL2Table *qed_find_l2_cache_entry(L2TableCache *l2_cache, uint64_t offset); +void qed_commit_l2_cache_entry(L2TableCache *l2_cache, CachedL2Table *l2_table); + +/** + * Table I/O functions + */ +int qed_read_l1_table(BDRVQEDState *s); +void qed_write_l1_table(BDRVQEDState *s, unsigned int index, unsigned int n, + BlockDriverCompletionFunc *cb, void *opaque); +void qed_read_l2_table(BDRVQEDState *s, QEDRequest *request, uint64_t offset, + BlockDriverCompletionFunc *cb, void *opaque); +void qed_write_l2_table(BDRVQEDState *s, QEDRequest *request, + unsigned int index, unsigned int n, bool flush, + BlockDriverCompletionFunc *cb, void *opaque); + +/** + * Cluster functions + */ +void qed_find_cluster(BDRVQEDState *s, QEDRequest *request, uint64_t pos, + size_t len, QEDFindClusterFunc *cb, void *opaque); + +/** + * Utility functions + */ +static inline uint64_t qed_start_of_cluster(BDRVQEDState *s, uint64_t offset) +{ + return offset & ~(uint64_t)(s->header.cluster_size - 1); +} + +static inline uint64_t qed_offset_into_cluster(BDRVQEDState *s, uint64_t offset) +{ + return offset & (s->header.cluster_size - 1); +} + +static inline unsigned int qed_bytes_to_clusters(BDRVQEDState *s, size_t bytes) +{ + return qed_start_of_cluster(s, bytes + (s->header.cluster_size - 1)) / + (s->header.cluster_size - 1); +} + +static inline unsigned int qed_l1_index(BDRVQEDState *s, uint64_t pos) +{ + return pos >> s->l1_shift; +} + +static inline unsigned int qed_l2_index(BDRVQEDState *s, uint64_t pos) +{ + return (pos >> s->l2_shift) & s->l2_mask; +} + +#endif /* BLOCK_QED_H */ diff --git a/cutils.c b/cutils.c index 036ae3c..e5b6fae 100644 --- a/cutils.c +++ b/cutils.c @@ -234,6 +234,14 @@ void qemu_iovec_from_buffer(QEMUIOVector *qiov, const void *buf, size_t count) } } +void qemu_iovec_zero(QEMUIOVector *qiov) +{ + struct iovec *iov; + for (iov = qiov->iov; iov != &qiov->iov[qiov->niov]; iov++) { + memset(iov->iov_base, 0, iov->iov_len); + } +} + #ifndef _WIN32 /* Sets a specific flag */ int fcntl_setfl(int fd, int flag) @@ -251,3 +259,48 @@ int fcntl_setfl(int fd, int flag) } #endif +/** + * Get the number of bits for a power of 2 + * + * The following is true for powers of 2: + * n == 1 << get_bits_from_size(n) + */ +int get_bits_from_size(size_t size) +{ + int res = 0; + + if (size == 0) { + return -1; + } + + while (size != 1) { + /* Not a power of two */ + if (size & 1) { + return -1; + } + + size >>= 1; + res++; + } + + return res; +} + +const char *bytes_to_str(uint64_t size) +{ + static char buffer[64]; + + if (size < (1ULL << 10)) { + snprintf(buffer, sizeof(buffer), "%" PRIu64 " byte(s)", size); + } else if (size < (1ULL << 20)) { + snprintf(buffer, sizeof(buffer), "%" PRIu64 " KB(s)", size >> 10); + } else if (size < (1ULL << 30)) { + snprintf(buffer, sizeof(buffer), "%" PRIu64 " MB(s)", size >> 20); + } else if (size < (1ULL << 40)) { + snprintf(buffer, sizeof(buffer), "%" PRIu64 " GB(s)", size >> 30); + } else { + snprintf(buffer, sizeof(buffer), "%" PRIu64 " TB(s)", size >> 40); + } + + return buffer; +} diff --git a/qemu-common.h b/qemu-common.h index dfd3dc0..754b107 100644 --- a/qemu-common.h +++ b/qemu-common.h @@ -137,6 +137,8 @@ time_t mktimegm(struct tm *tm); int qemu_fls(int i); int qemu_fdatasync(int fd); int fcntl_setfl(int fd, int flag); +int get_bits_from_size(size_t size); +const char *bytes_to_str(uint64_t size); /* path.c */ void init_paths(const char *prefix); @@ -283,6 +285,7 @@ void qemu_iovec_destroy(QEMUIOVector *qiov); void qemu_iovec_reset(QEMUIOVector *qiov); void qemu_iovec_to_buffer(QEMUIOVector *qiov, void *buf); void qemu_iovec_from_buffer(QEMUIOVector *qiov, const void *buf, size_t count); +void qemu_iovec_zero(QEMUIOVector *qiov); struct Monitor; typedef struct Monitor Monitor;