/*
* Block driver for the QCOW format
*
- * Copyright (c) 2004 Fabrice Bellard
+ * Copyright (c) 2004-2006 Fabrice Bellard
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
*/
#include "vl.h"
#include "block_int.h"
-#include "zlib.h"
+#include <zlib.h>
#include "aes.h"
/**************************************************************/
#define L2_CACHE_SIZE 16
typedef struct BDRVQcowState {
- int fd;
+ BlockDriverState *hd;
int cluster_bits;
int cluster_size;
int cluster_sectors;
static int qcow_probe(const uint8_t *buf, int buf_size, const char *filename)
{
const QCowHeader *cow_header = (const void *)buf;
-
- if (be32_to_cpu(cow_header->magic) == QCOW_MAGIC &&
+
+ if (buf_size >= sizeof(QCowHeader) &&
+ be32_to_cpu(cow_header->magic) == QCOW_MAGIC &&
be32_to_cpu(cow_header->version) == QCOW_VERSION)
return 100;
else
return 0;
}
-static int qcow_open(BlockDriverState *bs, const char *filename)
+static int qcow_open(BlockDriverState *bs, const char *filename, int flags)
{
BDRVQcowState *s = bs->opaque;
- int fd, len, i, shift;
+ int len, i, shift, ret;
QCowHeader header;
-
- fd = open(filename, O_RDWR | O_BINARY | O_LARGEFILE);
- if (fd < 0) {
- fd = open(filename, O_RDONLY | O_BINARY | O_LARGEFILE);
- if (fd < 0)
- return -1;
- }
- s->fd = fd;
- if (read(fd, &header, sizeof(header)) != sizeof(header))
+
+ ret = bdrv_file_open(&s->hd, filename, flags);
+ if (ret < 0)
+ return ret;
+ if (bdrv_pread(s->hd, 0, &header, sizeof(header)) != sizeof(header))
goto fail;
be32_to_cpus(&header.magic);
be32_to_cpus(&header.version);
s->l1_table = qemu_malloc(s->l1_size * sizeof(uint64_t));
if (!s->l1_table)
goto fail;
- lseek(fd, s->l1_table_offset, SEEK_SET);
- if (read(fd, s->l1_table, s->l1_size * sizeof(uint64_t)) !=
+ if (bdrv_pread(s->hd, s->l1_table_offset, s->l1_table, s->l1_size * sizeof(uint64_t)) !=
s->l1_size * sizeof(uint64_t))
goto fail;
for(i = 0;i < s->l1_size; i++) {
len = header.backing_file_size;
if (len > 1023)
len = 1023;
- lseek(fd, header.backing_file_offset, SEEK_SET);
- if (read(fd, bs->backing_file, len) != len)
+ if (bdrv_pread(s->hd, header.backing_file_offset, bs->backing_file, len) != len)
goto fail;
bs->backing_file[len] = '\0';
}
qemu_free(s->l2_cache);
qemu_free(s->cluster_cache);
qemu_free(s->cluster_data);
- close(fd);
+ bdrv_delete(s->hd);
return -1;
}
if (!allocate)
return 0;
/* allocate a new l2 entry */
- l2_offset = lseek(s->fd, 0, SEEK_END);
+ l2_offset = bdrv_getlength(s->hd);
/* round to cluster size */
l2_offset = (l2_offset + s->cluster_size - 1) & ~(s->cluster_size - 1);
/* update the L1 entry */
s->l1_table[l1_index] = l2_offset;
tmp = cpu_to_be64(l2_offset);
- lseek(s->fd, s->l1_table_offset + l1_index * sizeof(tmp), SEEK_SET);
- if (write(s->fd, &tmp, sizeof(tmp)) != sizeof(tmp))
+ if (bdrv_pwrite(s->hd, s->l1_table_offset + l1_index * sizeof(tmp),
+ &tmp, sizeof(tmp)) != sizeof(tmp))
return 0;
new_l2_table = 1;
}
}
}
l2_table = s->l2_cache + (min_index << s->l2_bits);
- lseek(s->fd, l2_offset, SEEK_SET);
if (new_l2_table) {
memset(l2_table, 0, s->l2_size * sizeof(uint64_t));
- if (write(s->fd, l2_table, s->l2_size * sizeof(uint64_t)) !=
+ if (bdrv_pwrite(s->hd, l2_offset, l2_table, s->l2_size * sizeof(uint64_t)) !=
s->l2_size * sizeof(uint64_t))
return 0;
} else {
- if (read(s->fd, l2_table, s->l2_size * sizeof(uint64_t)) !=
+ if (bdrv_pread(s->hd, l2_offset, l2_table, s->l2_size * sizeof(uint64_t)) !=
s->l2_size * sizeof(uint64_t))
return 0;
}
overwritten */
if (decompress_cluster(s, cluster_offset) < 0)
return 0;
- cluster_offset = lseek(s->fd, 0, SEEK_END);
+ cluster_offset = bdrv_getlength(s->hd);
cluster_offset = (cluster_offset + s->cluster_size - 1) &
~(s->cluster_size - 1);
/* write the cluster content */
- lseek(s->fd, cluster_offset, SEEK_SET);
- if (write(s->fd, s->cluster_cache, s->cluster_size) !=
+ if (bdrv_pwrite(s->hd, cluster_offset, s->cluster_cache, s->cluster_size) !=
s->cluster_size)
return -1;
} else {
- cluster_offset = lseek(s->fd, 0, SEEK_END);
+ cluster_offset = bdrv_getlength(s->hd);
if (allocate == 1) {
/* round to cluster size */
cluster_offset = (cluster_offset + s->cluster_size - 1) &
~(s->cluster_size - 1);
- ftruncate(s->fd, cluster_offset + s->cluster_size);
+ bdrv_truncate(s->hd, cluster_offset + s->cluster_size);
/* if encrypted, we must initialize the cluster
content which won't be written */
if (s->crypt_method &&
(n_end - n_start) < s->cluster_sectors) {
uint64_t start_sect;
start_sect = (offset & ~(s->cluster_size - 1)) >> 9;
- memset(s->cluster_data + 512, 0xaa, 512);
+ memset(s->cluster_data + 512, 0x00, 512);
for(i = 0; i < s->cluster_sectors; i++) {
if (i < n_start || i >= n_end) {
encrypt_sectors(s, start_sect + i,
s->cluster_data,
s->cluster_data + 512, 1, 1,
&s->aes_encrypt_key);
- lseek(s->fd, cluster_offset + i * 512, SEEK_SET);
- if (write(s->fd, s->cluster_data, 512) != 512)
+ if (bdrv_pwrite(s->hd, cluster_offset + i * 512,
+ s->cluster_data, 512) != 512)
return -1;
}
}
/* update L2 table */
tmp = cpu_to_be64(cluster_offset);
l2_table[l2_index] = tmp;
- lseek(s->fd, l2_offset + l2_index * sizeof(tmp), SEEK_SET);
- if (write(s->fd, &tmp, sizeof(tmp)) != sizeof(tmp))
+ if (bdrv_pwrite(s->hd,
+ l2_offset + l2_index * sizeof(tmp), &tmp, sizeof(tmp)) != sizeof(tmp))
return 0;
}
return cluster_offset;
if (s->cluster_cache_offset != coffset) {
csize = cluster_offset >> (63 - s->cluster_bits);
csize &= (s->cluster_size - 1);
- lseek(s->fd, coffset, SEEK_SET);
- ret = read(s->fd, s->cluster_data, csize);
+ ret = bdrv_pread(s->hd, coffset, s->cluster_data, csize);
if (ret != csize)
return -1;
if (decompress_buffer(s->cluster_cache, s->cluster_size,
return 0;
}
+#if 0
+
static int qcow_read(BlockDriverState *bs, int64_t sector_num,
uint8_t *buf, int nb_sectors)
{
if (n > nb_sectors)
n = nb_sectors;
if (!cluster_offset) {
- memset(buf, 0, 512 * n);
+ if (bs->backing_hd) {
+ /* read from the base image */
+ ret = bdrv_read(bs->backing_hd, sector_num, buf, n);
+ if (ret < 0)
+ return -1;
+ } else {
+ memset(buf, 0, 512 * n);
+ }
} else if (cluster_offset & QCOW_OFLAG_COMPRESSED) {
if (decompress_cluster(s, cluster_offset) < 0)
return -1;
memcpy(buf, s->cluster_cache + index_in_cluster * 512, 512 * n);
} else {
- lseek(s->fd, cluster_offset + index_in_cluster * 512, SEEK_SET);
- ret = read(s->fd, buf, n * 512);
+ ret = bdrv_pread(s->hd, cluster_offset + index_in_cluster * 512, buf, n * 512);
if (ret != n * 512)
return -1;
if (s->crypt_method) {
}
return 0;
}
+#endif
static int qcow_write(BlockDriverState *bs, int64_t sector_num,
const uint8_t *buf, int nb_sectors)
index_in_cluster + n);
if (!cluster_offset)
return -1;
- lseek(s->fd, cluster_offset + index_in_cluster * 512, SEEK_SET);
if (s->crypt_method) {
encrypt_sectors(s, sector_num, s->cluster_data, buf, n, 1,
&s->aes_encrypt_key);
- ret = write(s->fd, s->cluster_data, n * 512);
+ ret = bdrv_pwrite(s->hd, cluster_offset + index_in_cluster * 512,
+ s->cluster_data, n * 512);
} else {
- ret = write(s->fd, buf, n * 512);
+ ret = bdrv_pwrite(s->hd, cluster_offset + index_in_cluster * 512, buf, n * 512);
}
if (ret != n * 512)
return -1;
return 0;
}
+typedef struct QCowAIOCB {
+ BlockDriverAIOCB common;
+ int64_t sector_num;
+ uint8_t *buf;
+ int nb_sectors;
+ int n;
+ uint64_t cluster_offset;
+ uint8_t *cluster_data;
+ BlockDriverAIOCB *hd_aiocb;
+} QCowAIOCB;
+
+static void qcow_aio_read_cb(void *opaque, int ret)
+{
+ QCowAIOCB *acb = opaque;
+ BlockDriverState *bs = acb->common.bs;
+ BDRVQcowState *s = bs->opaque;
+ int index_in_cluster;
+
+ acb->hd_aiocb = NULL;
+ if (ret < 0) {
+ fail:
+ acb->common.cb(acb->common.opaque, ret);
+ qemu_aio_release(acb);
+ return;
+ }
+
+ redo:
+ /* post process the read buffer */
+ if (!acb->cluster_offset) {
+ /* nothing to do */
+ } else if (acb->cluster_offset & QCOW_OFLAG_COMPRESSED) {
+ /* nothing to do */
+ } else {
+ if (s->crypt_method) {
+ encrypt_sectors(s, acb->sector_num, acb->buf, acb->buf,
+ acb->n, 0,
+ &s->aes_decrypt_key);
+ }
+ }
+
+ acb->nb_sectors -= acb->n;
+ acb->sector_num += acb->n;
+ acb->buf += acb->n * 512;
+
+ if (acb->nb_sectors == 0) {
+ /* request completed */
+ acb->common.cb(acb->common.opaque, 0);
+ qemu_aio_release(acb);
+ return;
+ }
+
+ /* prepare next AIO request */
+ acb->cluster_offset = get_cluster_offset(bs, acb->sector_num << 9,
+ 0, 0, 0, 0);
+ index_in_cluster = acb->sector_num & (s->cluster_sectors - 1);
+ acb->n = s->cluster_sectors - index_in_cluster;
+ if (acb->n > acb->nb_sectors)
+ acb->n = acb->nb_sectors;
+
+ if (!acb->cluster_offset) {
+ if (bs->backing_hd) {
+ /* read from the base image */
+ acb->hd_aiocb = bdrv_aio_read(bs->backing_hd,
+ acb->sector_num, acb->buf, acb->n, qcow_aio_read_cb, acb);
+ if (acb->hd_aiocb == NULL)
+ goto fail;
+ } else {
+ /* Note: in this case, no need to wait */
+ memset(acb->buf, 0, 512 * acb->n);
+ goto redo;
+ }
+ } else if (acb->cluster_offset & QCOW_OFLAG_COMPRESSED) {
+ /* add AIO support for compressed blocks ? */
+ if (decompress_cluster(s, acb->cluster_offset) < 0)
+ goto fail;
+ memcpy(acb->buf,
+ s->cluster_cache + index_in_cluster * 512, 512 * acb->n);
+ goto redo;
+ } else {
+ if ((acb->cluster_offset & 511) != 0) {
+ ret = -EIO;
+ goto fail;
+ }
+ acb->hd_aiocb = bdrv_aio_read(s->hd,
+ (acb->cluster_offset >> 9) + index_in_cluster,
+ acb->buf, acb->n, qcow_aio_read_cb, acb);
+ if (acb->hd_aiocb == NULL)
+ goto fail;
+ }
+}
+
+static BlockDriverAIOCB *qcow_aio_read(BlockDriverState *bs,
+ int64_t sector_num, uint8_t *buf, int nb_sectors,
+ BlockDriverCompletionFunc *cb, void *opaque)
+{
+ QCowAIOCB *acb;
+
+ acb = qemu_aio_get(bs, cb, opaque);
+ if (!acb)
+ return NULL;
+ acb->hd_aiocb = NULL;
+ acb->sector_num = sector_num;
+ acb->buf = buf;
+ acb->nb_sectors = nb_sectors;
+ acb->n = 0;
+ acb->cluster_offset = 0;
+
+ qcow_aio_read_cb(acb, 0);
+ return &acb->common;
+}
+
+static void qcow_aio_write_cb(void *opaque, int ret)
+{
+ QCowAIOCB *acb = opaque;
+ BlockDriverState *bs = acb->common.bs;
+ BDRVQcowState *s = bs->opaque;
+ int index_in_cluster;
+ uint64_t cluster_offset;
+ const uint8_t *src_buf;
+
+ acb->hd_aiocb = NULL;
+
+ if (ret < 0) {
+ fail:
+ acb->common.cb(acb->common.opaque, ret);
+ qemu_aio_release(acb);
+ return;
+ }
+
+ acb->nb_sectors -= acb->n;
+ acb->sector_num += acb->n;
+ acb->buf += acb->n * 512;
+
+ if (acb->nb_sectors == 0) {
+ /* request completed */
+ acb->common.cb(acb->common.opaque, 0);
+ qemu_aio_release(acb);
+ return;
+ }
+
+ index_in_cluster = acb->sector_num & (s->cluster_sectors - 1);
+ acb->n = s->cluster_sectors - index_in_cluster;
+ if (acb->n > acb->nb_sectors)
+ acb->n = acb->nb_sectors;
+ cluster_offset = get_cluster_offset(bs, acb->sector_num << 9, 1, 0,
+ index_in_cluster,
+ index_in_cluster + acb->n);
+ if (!cluster_offset || (cluster_offset & 511) != 0) {
+ ret = -EIO;
+ goto fail;
+ }
+ if (s->crypt_method) {
+ if (!acb->cluster_data) {
+ acb->cluster_data = qemu_mallocz(s->cluster_size);
+ if (!acb->cluster_data) {
+ ret = -ENOMEM;
+ goto fail;
+ }
+ }
+ encrypt_sectors(s, acb->sector_num, acb->cluster_data, acb->buf,
+ acb->n, 1, &s->aes_encrypt_key);
+ src_buf = acb->cluster_data;
+ } else {
+ src_buf = acb->buf;
+ }
+ acb->hd_aiocb = bdrv_aio_write(s->hd,
+ (cluster_offset >> 9) + index_in_cluster,
+ src_buf, acb->n,
+ qcow_aio_write_cb, acb);
+ if (acb->hd_aiocb == NULL)
+ goto fail;
+}
+
+static BlockDriverAIOCB *qcow_aio_write(BlockDriverState *bs,
+ int64_t sector_num, const uint8_t *buf, int nb_sectors,
+ BlockDriverCompletionFunc *cb, void *opaque)
+{
+ BDRVQcowState *s = bs->opaque;
+ QCowAIOCB *acb;
+
+ s->cluster_cache_offset = -1; /* disable compressed cache */
+
+ acb = qemu_aio_get(bs, cb, opaque);
+ if (!acb)
+ return NULL;
+ acb->hd_aiocb = NULL;
+ acb->sector_num = sector_num;
+ acb->buf = (uint8_t *)buf;
+ acb->nb_sectors = nb_sectors;
+ acb->n = 0;
+
+ qcow_aio_write_cb(acb, 0);
+ return &acb->common;
+}
+
+static void qcow_aio_cancel(BlockDriverAIOCB *blockacb)
+{
+ QCowAIOCB *acb = (QCowAIOCB *)blockacb;
+ if (acb->hd_aiocb)
+ bdrv_aio_cancel(acb->hd_aiocb);
+ qemu_aio_release(acb);
+}
+
static void qcow_close(BlockDriverState *bs)
{
BDRVQcowState *s = bs->opaque;
qemu_free(s->l2_cache);
qemu_free(s->cluster_cache);
qemu_free(s->cluster_data);
- close(s->fd);
+ bdrv_delete(s->hd);
}
static int qcow_create(const char *filename, int64_t total_size,
{
int fd, header_size, backing_filename_len, l1_size, i, shift;
QCowHeader header;
- char backing_filename[1024];
uint64_t tmp;
- struct stat st;
- fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY | O_LARGEFILE,
- 0644);
+ fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY, 0644);
if (fd < 0)
return -1;
memset(&header, 0, sizeof(header));
header_size = sizeof(header);
backing_filename_len = 0;
if (backing_file) {
- realpath(backing_file, backing_filename);
- if (stat(backing_filename, &st) != 0) {
- return -1;
- }
- header.mtime = cpu_to_be32(st.st_mtime);
header.backing_file_offset = cpu_to_be64(header_size);
- backing_filename_len = strlen(backing_filename);
+ backing_filename_len = strlen(backing_file);
header.backing_file_size = cpu_to_be32(backing_filename_len);
header_size += backing_filename_len;
+ header.mtime = cpu_to_be32(0);
header.cluster_bits = 9; /* 512 byte cluster to avoid copying
unmodifyed sectors */
header.l2_bits = 12; /* 32 KB L2 tables */
/* write all the data */
write(fd, &header, sizeof(header));
if (backing_file) {
- write(fd, backing_filename, backing_filename_len);
+ write(fd, backing_file, backing_filename_len);
}
lseek(fd, header_size, SEEK_SET);
tmp = 0;
return 0;
}
-int qcow_get_cluster_size(BlockDriverState *bs)
+static int qcow_make_empty(BlockDriverState *bs)
{
BDRVQcowState *s = bs->opaque;
- if (bs->drv != &bdrv_qcow)
- return -1;
- return s->cluster_size;
+ uint32_t l1_length = s->l1_size * sizeof(uint64_t);
+ int ret;
+
+ memset(s->l1_table, 0, l1_length);
+ if (bdrv_pwrite(s->hd, s->l1_table_offset, s->l1_table, l1_length) < 0)
+ return -1;
+ ret = bdrv_truncate(s->hd, s->l1_table_offset + l1_length);
+ if (ret < 0)
+ return ret;
+
+ memset(s->l2_cache, 0, s->l2_size * L2_CACHE_SIZE * sizeof(uint64_t));
+ memset(s->l2_cache_offsets, 0, L2_CACHE_SIZE * sizeof(uint64_t));
+ memset(s->l2_cache_counts, 0, L2_CACHE_SIZE * sizeof(uint32_t));
+
+ return 0;
}
/* XXX: put compressed sectors first, then all the cluster aligned
tables to avoid losing bytes in alignment */
-int qcow_compress_cluster(BlockDriverState *bs, int64_t sector_num,
- const uint8_t *buf)
+static int qcow_write_compressed(BlockDriverState *bs, int64_t sector_num,
+ const uint8_t *buf, int nb_sectors)
{
BDRVQcowState *s = bs->opaque;
z_stream strm;
uint8_t *out_buf;
uint64_t cluster_offset;
- if (bs->drv != &bdrv_qcow)
- return -1;
+ if (nb_sectors != s->cluster_sectors)
+ return -EINVAL;
out_buf = qemu_malloc(s->cluster_size + (s->cluster_size / 1000) + 128);
if (!out_buf)
cluster_offset = get_cluster_offset(bs, sector_num << 9, 2,
out_len, 0, 0);
cluster_offset &= s->cluster_offset_mask;
- lseek(s->fd, cluster_offset, SEEK_SET);
- if (write(s->fd, out_buf, out_len) != out_len) {
+ if (bdrv_pwrite(s->hd, cluster_offset, out_buf, out_len) != out_len) {
qemu_free(out_buf);
return -1;
}
return 0;
}
+static void qcow_flush(BlockDriverState *bs)
+{
+ BDRVQcowState *s = bs->opaque;
+ bdrv_flush(s->hd);
+}
+
+static int qcow_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
+{
+ BDRVQcowState *s = bs->opaque;
+ bdi->cluster_size = s->cluster_size;
+ return 0;
+}
+
BlockDriver bdrv_qcow = {
"qcow",
sizeof(BDRVQcowState),
qcow_probe,
qcow_open,
- qcow_read,
- qcow_write,
+ NULL,
+ NULL,
qcow_close,
qcow_create,
+ qcow_flush,
qcow_is_allocated,
qcow_set_key,
+ qcow_make_empty,
+
+ .bdrv_aio_read = qcow_aio_read,
+ .bdrv_aio_write = qcow_aio_write,
+ .bdrv_aio_cancel = qcow_aio_cancel,
+ .aiocb_size = sizeof(QCowAIOCB),
+ .bdrv_write_compressed = qcow_write_compressed,
+ .bdrv_get_info = qcow_get_info,
};
-
-
projects / qemu / blobdiff