* [Qemu-devel] [RFC PATCH v2] Support vhd type VHD_DIFFERENCING
@ 2014-09-04 14:49 Gordon Gong
2014-09-05 10:04 ` Stefan Hajnoczi
0 siblings, 1 reply; 3+ messages in thread
From: Gordon Gong @ 2014-09-04 14:49 UTC (permalink / raw)
To: Stefan Hajnoczi; +Cc: Xiaoding (B), Liuji (Jeremy), Luohao (brian), qemu-devel
[-- Attachment #1.1: Type: text/plain, Size: 23971 bytes --]
[Qemu-devel][RFC PATCH v2] Support vhd type VHD_DIFFERENCING
>From 5387a2a7b6ad052659a08a1fc7e89595708396d1 Mon Sep 17 00:00:00 2001
From: Xiaodong Gong <gordongong0350@gmail.com>
Date: Thu, 4 Sep 2014 01:14:59 +0800
Subject: [PATCH 2/2] Support vhd type VHD_DIFFERENCING
Now qemu only supports vhd type VHD_FIXED and VHD_DYNAMIC,
so qemu can't read snapshot volume of vhd, and can't support
other storage features of vhd file.
This patch add read parent information in function "vpc_open",
read bitmap in "vpc_read", and change bitmap in "vpc_write".
Signed-off-by: Xiaodong Gong <gordongong0350@gmail.com>
---
block/vpc.c | 329
+++++++++++++++++++++++++++++++++++++++++++++++-------------
1 file changed, 261 insertions(+), 68 deletions(-)
diff --git a/block/vpc.c b/block/vpc.c
index c024b4c..3ba0d57 100644
--- a/block/vpc.c
+++ b/block/vpc.c
@@ -33,13 +33,18 @@
/**************************************************************/
#define HEADER_SIZE 512
+#define DYNAMIC_HEADER_SIZE 1024
+#define PARENT_LOCATOR_NUM 8
+#define PARENT_PREFIX_LEN 7 /* such as file:// */
+#define TBBATMAP_HEAD_SIZE 28
+#define MACX 0x5863614d /* big endian */
//#define CACHE
enum vhd_type {
VHD_FIXED = 2,
VHD_DYNAMIC = 3,
- VHD_DIFFERENCING = 4,
+ VHD_DIFF = 4,
};
// Seconds since Jan 1, 2000 0:00:00 (UTC)
@@ -138,6 +143,15 @@ typedef struct BDRVVPCState {
Error *migration_blocker;
} BDRVVPCState;
+typedef struct vhd_tdbatmap_header {
+ char magic[8]; /* always "tdbatmap" */
+
+ uint64_t batmap_offset;
+ uint32_t batmap_size;
+ uint32_t batmap_version;
+ uint32_t checksum;
+} QEMU_PACKED VHDTdBatmapHeader;
+
static uint32_t vpc_checksum(uint8_t* buf, size_t size)
{
uint32_t res = 0;
@@ -153,7 +167,7 @@ static uint32_t vpc_checksum(uint8_t* buf, size_t size)
static int vpc_probe(const uint8_t *buf, int buf_size, const char *filename)
{
if (buf_size >= 8 && !strncmp((char *)buf, "conectix", 8))
- return 100;
+ return 100;
return 0;
}
@@ -164,11 +178,17 @@ static int vpc_open(BlockDriverState *bs, QDict
*options, int flags,
int i;
VHDFooter *footer;
VHDDynDiskHeader *dyndisk_header;
- uint8_t buf[HEADER_SIZE];
+ uint8_t buf[DYNAMIC_HEADER_SIZE];
+ uint8_t tdbatmap_header_buf[TBBATMAP_HEAD_SIZE];
uint32_t checksum;
uint64_t computed_size;
- int disk_type = VHD_DYNAMIC;
+ uint32_t disk_type;
int ret;
+ VHDTdBatmapHeader *tdbatmap_header;
+ int parent_locator_offset = 0;
+ int64_t data_offset = 0;
+ int data_length = 0;
+ uint32_t platform;
ret = bdrv_pread(bs->file, 0, s->footer_buf, HEADER_SIZE);
if (ret < 0) {
@@ -176,6 +196,8 @@ static int vpc_open(BlockDriverState *bs, QDict
*options, int flags,
}
footer = (VHDFooter *) s->footer_buf;
+ disk_type = be32_to_cpu(footer->type);
+
if (strncmp(footer->creator, "conectix", 8)) {
int64_t offset = bdrv_getlength(bs->file);
if (offset < 0) {
@@ -230,9 +252,9 @@ static int vpc_open(BlockDriverState *bs, QDict
*options, int flags,
goto fail;
}
- if (disk_type == VHD_DYNAMIC) {
+ if (disk_type == VHD_DYNAMIC || disk_type == VHD_DIFF) {
ret = bdrv_pread(bs->file, be64_to_cpu(footer->data_offset), buf,
- HEADER_SIZE);
+ DYNAMIC_HEADER_SIZE);
if (ret < 0) {
goto fail;
}
@@ -286,6 +308,56 @@ static int vpc_open(BlockDriverState *bs, QDict
*options, int flags,
s->free_data_block_offset =
(s->bat_offset + (s->max_table_entries * 4) + 511) & ~511;
+ /* Read tdbatmap header by offset */
+ ret = bdrv_pread(bs->file, s->free_data_block_offset,
+ tdbatmap_header_buf, TBBATMAP_HEAD_SIZE);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ tdbatmap_header = (VHDTdBatmapHeader *) tdbatmap_header_buf;
+ if (!strncmp(tdbatmap_header->magic, "tdbatmap", 8)) {
+ s->free_data_block_offset =
+ be32_to_cpu(tdbatmap_header->batmap_size) * 512
+ + be64_to_cpu(tdbatmap_header->batmap_offset);
+ }
+
+ /* Read backing file location from dyn header table */
+ if (dyndisk_header->parent_name[0] ||
dyndisk_header->parent_name[1]) {
+ for (i = 0; i < PARENT_LOCATOR_NUM; i++) {
+ data_offset =
+
be64_to_cpu(dyndisk_header->parent_locator[i].data_offset);
+ data_length =
+
be32_to_cpu(dyndisk_header->parent_locator[i].data_length);
+ platform = dyndisk_header->parent_locator[i].platform;
+
+ if (MACX == platform) {
+ if (data_offset + PARENT_PREFIX_LEN >
+ s->max_table_entries * s->block_size) {
+ goto fail;
+ }
+ if (data_length - PARENT_PREFIX_LEN > 1024) {
+ goto fail;
+ }
+ ret = bdrv_pread(bs->file, data_offset +
PARENT_PREFIX_LEN,
+ bs->backing_file, data_length - PARENT_PREFIX_LEN);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ bs->backing_file[data_length - PARENT_PREFIX_LEN] =
'\0';
+ }
+
+ if (data_offset > parent_locator_offset) {
+ parent_locator_offset = data_offset;
+ }
+ }
+ }
+
+ if (parent_locator_offset + 512 > s->free_data_block_offset) {
+ s->free_data_block_offset = parent_locator_offset + 512;
+ }
+
for (i = 0; i < s->max_table_entries; i++) {
be32_to_cpus(&s->pagetable[i]);
if (s->pagetable[i] != 0xFFFFFFFF) {
@@ -363,19 +435,6 @@ static inline int64_t
get_sector_offset(BlockDriverState *bs,
bitmap_offset = 512 * (uint64_t) s->pagetable[pagetable_index];
block_offset = bitmap_offset + s->bitmap_size + (512 *
pageentry_index);
- // We must ensure that we don't write to any sectors which are marked
as
- // unused in the bitmap. We get away with setting all bits in the block
- // bitmap each time we write to a new block. This might cause Virtual
PC to
- // miss sparse read optimization, but it's not a problem in terms of
- // correctness.
- if (write && (s->last_bitmap_offset != bitmap_offset)) {
- uint8_t bitmap[s->bitmap_size];
-
- s->last_bitmap_offset = bitmap_offset;
- memset(bitmap, 0xff, s->bitmap_size);
- bdrv_pwrite_sync(bs->file, bitmap_offset, bitmap, s->bitmap_size);
- }
-
// printf("sector: %" PRIx64 ", index: %x, offset: %x, bioff: %" PRIx64
", bloff: %" PRIx64 "\n",
// sector_num, pagetable_index, pageentry_index,
// bitmap_offset, block_offset);
@@ -412,6 +471,53 @@ static inline int64_t
get_sector_offset(BlockDriverState *bs,
}
/*
+ * Returns the absolute byte offset of the given sector in the differencing
+ * image file.
+ *
+ * If the sector is not allocated, -1 is returned instead. If the sector is
+ * allocated in the backing file, -2 is returned. If the sector is
allocated
+ * in current file, the block offset is returned.
+ */
+static inline int64_t get_sector_offset_diff(BlockDriverState *bs,
+ int64_t sector_num)
+{
+ BDRVVPCState *s = bs->opaque;
+ uint64_t offset = sector_num << BDRV_SECTOR_BITS;
+ uint64_t bitmap_offset;
+ uint64_t block_offset;
+ uint32_t pagetable_index, pageentry_index;
+ uint32_t bitmap_index, bitmapentry_index;
+ uint8_t bitmap[s->bitmap_size];
+ int ret;
+
+ pagetable_index = offset / s->block_size;
+ if (pagetable_index >= s->max_table_entries) {
+ return -1;
+ } else if (0xffffffff == s->pagetable[pagetable_index]) {
+ return -2;
+ }
+
+ bitmap_offset = 512 * (uint64_t) s->pagetable[pagetable_index];
+ if (bitmap_offset > s->max_table_entries * s->block_size) {
+ return -1;
+ }
+ ret = bdrv_pread(bs->file, bitmap_offset, bitmap, s->bitmap_size);
+ if (ret < 0) {
+ return -1;
+ }
+
+ pageentry_index = (offset % s->block_size) / 512;
+ bitmap_index = pageentry_index / 8;
+ bitmapentry_index = 7 - pageentry_index % 8;
+ if (bitmap[bitmap_index] & 0x1 << bitmapentry_index) {
+ block_offset = bitmap_offset + s->bitmap_size + (512 *
pageentry_index);
+ return block_offset;
+ } else {
+ return -2;
+ }
+}
+
+/*
* Writes the footer to the end of the image file. This is needed when the
* file grows as it overwrites the old footer
*
@@ -437,7 +543,8 @@ static int rewrite_footer(BlockDriverState* bs)
*
* Returns the sectors' offset in the image file on success and < 0 on
error
*/
-static int64_t alloc_block(BlockDriverState* bs, int64_t sector_num)
+static int64_t alloc_block(BlockDriverState *bs, int64_t sector_num,
+ bool isdiff)
{
BDRVVPCState *s = bs->opaque;
int64_t bat_offset;
@@ -457,7 +564,11 @@ static int64_t alloc_block(BlockDriverState* bs,
int64_t sector_num)
s->pagetable[index] = s->free_data_block_offset / 512;
// Initialize the block's bitmap
- memset(bitmap, 0xff, s->bitmap_size);
+ if (isdiff) {
+ memset(bitmap, 0x0, s->bitmap_size);
+ } else {
+ memset(bitmap, 0xff, s->bitmap_size);
+ }
ret = bdrv_pwrite_sync(bs->file, s->free_data_block_offset, bitmap,
s->bitmap_size);
if (ret < 0) {
@@ -501,36 +612,62 @@ static int vpc_read(BlockDriverState *bs, int64_t
sector_num,
uint8_t *buf, int nb_sectors)
{
BDRVVPCState *s = bs->opaque;
- int ret;
- int64_t offset;
- int64_t sectors, sectors_per_block;
VHDFooter *footer = (VHDFooter *) s->footer_buf;
+ int64_t sectors_per_block = s->block_size >> BDRV_SECTOR_BITS;
+ int64_t offset, sectors;
+ int ret;
- if (be32_to_cpu(footer->type) == VHD_FIXED) {
+ switch (be32_to_cpu(footer->type)) {
+ case VHD_FIXED:
return bdrv_read(bs->file, sector_num, buf, nb_sectors);
- }
- while (nb_sectors > 0) {
- offset = get_sector_offset(bs, sector_num, 0);
-
- sectors_per_block = s->block_size >> BDRV_SECTOR_BITS;
- sectors = sectors_per_block - (sector_num % sectors_per_block);
- if (sectors > nb_sectors) {
- sectors = nb_sectors;
- }
+ case VHD_DYNAMIC:
+ while (nb_sectors > 0) {
+ sectors = sectors_per_block - (sector_num % sectors_per_block);
+ if (sectors > nb_sectors) {
+ sectors = nb_sectors;
+ }
- if (offset == -1) {
- memset(buf, 0, sectors * BDRV_SECTOR_SIZE);
- } else {
- ret = bdrv_pread(bs->file, offset, buf,
- sectors * BDRV_SECTOR_SIZE);
- if (ret != sectors * BDRV_SECTOR_SIZE) {
- return -1;
+ offset = get_sector_offset(bs, sector_num, 0);
+ if (-1 == offset) {
+ memset(buf, 0, sectors * BDRV_SECTOR_SIZE);
+ } else {
+ ret = bdrv_pread(bs->file, offset, buf,
+ sectors * BDRV_SECTOR_SIZE);
+ if (ret != sectors * BDRV_SECTOR_SIZE) {
+ return -1;
+ }
}
+
+ nb_sectors -= sectors;
+ sector_num += sectors;
+ buf += sectors * BDRV_SECTOR_SIZE;
}
+ break;
+ case VHD_DIFF:
+ while (nb_sectors > 0) {
+ offset = get_sector_offset_diff(bs, sector_num);
+ if (-1 == offset) {
+ memset(buf, 0, BDRV_SECTOR_SIZE);
+ } else if (-2 == offset) {
+ ret = bdrv_pread(bs->backing_hd, sector_num <<
BDRV_SECTOR_BITS
+ , buf, BDRV_SECTOR_SIZE);
+ if (ret < 0) {
+ return -1;
+ }
+ } else {
+ ret = bdrv_pread(bs->file, offset, buf, BDRV_SECTOR_SIZE);
+ if (ret != BDRV_SECTOR_SIZE) {
+ return -1;
+ }
+ }
- nb_sectors -= sectors;
- sector_num += sectors;
- buf += sectors * BDRV_SECTOR_SIZE;
+ nb_sectors--;
+ sector_num++;
+ buf += BDRV_SECTOR_SIZE;
+ }
+ break;
+ default:
+ return -1;
}
return 0;
}
@@ -546,43 +683,98 @@ static coroutine_fn int vpc_co_read(BlockDriverState
*bs, int64_t sector_num,
return ret;
}
+static inline int64_t write_bitmap(BlockDriverState *bs, int64_t
sector_num,
+ int64_t sectors)
+{
+ BDRVVPCState *s = bs->opaque;
+ uint64_t offset = sector_num << BDRV_SECTOR_BITS;
+ uint64_t bitmap_offset;
+ uint32_t pagetable_index, pageentry_index;
+ uint8_t bitmap[s->bitmap_size];
+ uint32_t bitmap_index, bitmapbit_index;
+ int i;
+ int ret;
+
+ pagetable_index = offset / s->block_size;
+ pageentry_index = (offset % s->block_size) / 512;
+ bitmap_offset = 512 * (uint64_t) s->pagetable[pagetable_index];
+
+ if (bitmap_offset > s->max_table_entries * s->block_size) {
+ return -1;
+ }
+ ret = bdrv_pread(bs->file, bitmap_offset, bitmap, s->bitmap_size);
+ if (ret < 0) {
+ return -1;
+ }
+
+ for (i = 0; i < sectors; i++) {
+ bitmap_index = pageentry_index / 8;
+ bitmapbit_index = 7 - pageentry_index % 8;
+ bitmap[bitmap_index] |= (0x1 << bitmapbit_index);
+ pageentry_index++;
+ }
+ ret = bdrv_pwrite(bs->file, bitmap_offset, bitmap, s->bitmap_size);
+ if (ret < 0) {
+ return -1;
+ }
+
+ return 0;
+}
+
static int vpc_write(BlockDriverState *bs, int64_t sector_num,
const uint8_t *buf, int nb_sectors)
{
BDRVVPCState *s = bs->opaque;
- int64_t offset;
- int64_t sectors, sectors_per_block;
+ VHDFooter *footer = (VHDFooter *) s->footer_buf;
+ int64_t sectors_per_block = s->block_size >> BDRV_SECTOR_BITS;
+ int64_t offset, sectors;
+ bool isdiff = true;
int ret;
- VHDFooter *footer = (VHDFooter *) s->footer_buf;
- if (be32_to_cpu(footer->type) == VHD_FIXED) {
+ switch (be32_to_cpu(footer->type)) {
+ case VHD_FIXED:
return bdrv_write(bs->file, sector_num, buf, nb_sectors);
- }
- while (nb_sectors > 0) {
- offset = get_sector_offset(bs, sector_num, 1);
-
- sectors_per_block = s->block_size >> BDRV_SECTOR_BITS;
- sectors = sectors_per_block - (sector_num % sectors_per_block);
- if (sectors > nb_sectors) {
- sectors = nb_sectors;
+ case VHD_DYNAMIC:
+ case VHD_DIFF:
+ if (VHD_DYNAMIC == be32_to_cpu(footer->type)) {
+ isdiff = false;
}
- if (offset == -1) {
- offset = alloc_block(bs, sector_num);
- if (offset < 0)
+ while (nb_sectors > 0) {
+ sectors = sectors_per_block - (sector_num % sectors_per_block);
+ if (sectors > nb_sectors) {
+ sectors = nb_sectors;
+ }
+
+ offset = get_sector_offset(bs, sector_num, 1);
+ if (offset == -1) {
+ offset = alloc_block(bs, sector_num, isdiff);
+ if (offset < 0) {
+ return -1;
+ }
+ }
+
+ ret = bdrv_pwrite(bs->file, offset, buf,
+ sectors * BDRV_SECTOR_SIZE);
+ if (ret != sectors * BDRV_SECTOR_SIZE) {
return -1;
- }
+ }
- ret = bdrv_pwrite(bs->file, offset, buf, sectors *
BDRV_SECTOR_SIZE);
- if (ret != sectors * BDRV_SECTOR_SIZE) {
- return -1;
- }
+ if (true == isdiff) {
+ ret = write_bitmap(bs, sector_num, sectors);
+ if (ret < 0) {
+ return -1;
+ }
+ }
- nb_sectors -= sectors;
- sector_num += sectors;
- buf += sectors * BDRV_SECTOR_SIZE;
+ nb_sectors -= sectors;
+ sector_num += sectors;
+ buf += sectors * BDRV_SECTOR_SIZE;
+ }
+ break;
+ default:
+ return -1;
}
-
return 0;
}
@@ -910,6 +1102,7 @@ static BlockDriver bdrv_vpc = {
.bdrv_close = vpc_close,
.bdrv_reopen_prepare = vpc_reopen_prepare,
.bdrv_create = vpc_create,
+ .supports_backing = true,
.bdrv_read = vpc_co_read,
.bdrv_write = vpc_co_write,
--
1.8.3.1
1. bdrv_preadv and bdrv_pwritev affer get_sector_offset_* is already
checked, others are checked if
version 2.
2. MACX is a big-endian number, so there is no need be32_to_cpu, but
I added a comment to MACX.
3. clean the code no used after in vpc_open.
4. move bdrv_co_readv() to bdrv_preadv in vpc_read.
5. Added some code to make it easy to understand.
6. the wrong use of cpu_to_be32 is fixed with another patch.
-------------------------------------------------------------------------------------------------------------------
On Tue, Jul 01, 2014 at 05:45:19PM +0800, Ding xiao wrote:
Sorry for the delay, I forgot about this patch.
>* +typedef struct vhd_tdbatmap_header {*
>* + char magic[8]; /* "tdbatmap"*/*
>* +*
>* + /* byte offset to batmap*/*
>* + uint64_t batmap_offset;*
>* +*
>* + /* Offset of the Block Allocation Table (BAT)*/*
This comment describes the batmap_offset field? Maybe this should be
dropped since that field already has a comment.
>* + /* read backend file*/*
>* + if (dyndisk_header->parent_name[0] || *
>* dyndisk_header->parent_name[1]) {*
>* + for (i = 0; i < PARENT_LOCATOR_NUM; i++) {*
>* + data_offset = be64_to_cpu(*
>* + *
>* dyndisk_header->parent_locator[i].data_offset);*
>* + data_length = be32_to_cpu(*
>* + *
>* dyndisk_header->parent_locator[i].data_length);*
>* + if (dyndisk_header->parent_locator[i].platform == MACX) {*
Missing be32_to_cpu()?
>* + ret = bdrv_pread(bs->file, data_offset + 7,*
>* + bs->backing_file, data_length - 7);*
Buffer overflow: char bs->backing_file[1024].
All input must be validated!
>* + if (ret < 0) {*
>* + goto fail;*
>* + }*
>* + bs->backing_file[data_length - 7] = '\0';*
Memory corruption if data_length < 7. Missing input validation.
>* + }*
>* + if (data_offset > parent_locator_offset) {*
>* + parent_locator_offset = data_offset;*
>* + }*
>* + }*
>* + }*
>* +*
>* + if (parent_locator_offset + 512 > s->free_data_block_offset) {*
>* + s->free_data_block_offset = parent_locator_offset + 512;*
>* + }*
>* +*
>* for (i = 0; i < s->max_table_entries; i++) {*
>* be32_to_cpus(&s->pagetable[i]);*
>* if (s->pagetable[i] != 0xFFFFFFFF) {*
>* @@ -364,6 +425,9 @@ static inline int64_t get_sector_offset(BlockDriverState *
>* *bs,*
>* // bitmap each time we write to a new block. This might cause Virtual PC *
>* to*
>* // miss sparse read optimization, but it's not a problem in terms of*
>* // correctness.*
>* +*
>* + /*this will not use*/*
>* +#if 0*
Delete the code if it is no longer used.
>* @@ -433,7 +498,7 @@ static int rewrite_footer(BlockDriverState* bs)*
>* **
>* * Returns the sectors' offset in the image file on success and < 0 on error*
>* */*
>* -static int64_t alloc_block(BlockDriverState* bs, int64_t sector_num)*
>* +static int64_t alloc_block(BlockDriverState *bs, int64_t sector_num, int *
>* diff)*
Please use the C99 bool type since it communicates more clearly that
diff is either true or false (not a counter or bitmap).
It would be clearest to check footer->type for VHD_DIFFERENCING in this
function instead of adding a new argument to the function.
>* @@ -501,33 +611,64 @@ static int vpc_read(BlockDriverState *bs, int64_t *
>* sector_num,*
>* int64_t offset;*
>* int64_t sectors, sectors_per_block;*
>* VHDFooter *footer = (VHDFooter *) s->footer_buf;*
>* + QEMUIOVector hd_qiov;*
>* + struct iovec qiov;*
>
>* if (cpu_to_be32(footer->type) == VHD_FIXED) {*
>* return bdrv_read(bs->file, sector_num, buf, nb_sectors);*
>* - }*
>* - while (nb_sectors > 0) {*
>* - offset = get_sector_offset(bs, sector_num, 0);*
>* + } else if (cpu_to_be32(footer->type) == VHD_DYNAMIC) {*
cpu_to_be32() is wrong since VHD_DYNAMIC is an enum constant (just a
regular CPU-endian integer).
Please add a separate patch before this one that cleans up incorrect
cpu_to_be*() usage. For example, cpu_to_be32(footer->type) == VHD_FIXED
a few lines above is wrong too.
>* + while (nb_sectors > 0) {*
>* + offset = get_sector_offset(bs, sector_num, 0);*
>* +*
>* + sectors_per_block = s->block_size >> BDRV_SECTOR_BITS;*
>* + sectors = sectors_per_block - (sector_num % sectors_per_block);*
>* + if (sectors > nb_sectors) {*
>* + sectors = nb_sectors;*
>* + }*
>
>* - sectors_per_block = s->block_size >> BDRV_SECTOR_BITS;*
>* - sectors = sectors_per_block - (sector_num % sectors_per_block);*
>* - if (sectors > nb_sectors) {*
>* - sectors = nb_sectors;*
>* + if (offset == -1) {*
>* + memset(buf, 0, sectors * BDRV_SECTOR_SIZE);*
>* + } else {*
>* + ret = bdrv_pread(bs->file, offset, buf,*
>* + sectors * BDRV_SECTOR_SIZE);*
>* + if (ret != sectors * BDRV_SECTOR_SIZE) {*
Indentation is off
>* + return -1;*
>* + }*
>* + }*
>* +*
>* + nb_sectors -= sectors;*
>* + sector_num += sectors;*
>* + buf += sectors * BDRV_SECTOR_SIZE;*
>* }*
>* + } else {*
>* + while (nb_sectors > 0) {*
>* + offset = get_sector_offset_diff(bs, sector_num);*
>* + if (offset == -1) {*
>* + memset(buf, 0, BDRV_SECTOR_SIZE);*
>* + } else if (offset == -2) {*
>* + qiov.iov_base = (void *)buf;*
This cast is unnecessary. The compiler does not warn about pointer
casts to or from void*.
>* + qiov.iov_len = 512;*
>* + hd_qiov.iov = &qiov;*
>* + hd_qiov.niov = 1;*
>* + hd_qiov.nalloc = -1;*
>* + hd_qiov.size = 512;*
This is not idiomatic. Normally 'qiov' is a QEMUIOVector, not a struct
iovec. The qemu_iovec_*() functions should be used instead of manually
setting QEMUIOVector fields:
iov.iov_base = buf;
iov.iov_len = 512;
qemu_iovec_init_external(&hd_qiov, &iov, 1);
>* + ret = bdrv_co_readv(bs->backing_hd, sector_num, 1, &hd_qiov);*
>* + if (ret < 0) {*
>* + return -1;*
>* + }*
Why are you using bdrv_co_readv() instead of bdrv_pread() like the rest
of this file?
It would be simpler to use bdrv_pread(). Then you don't need the struct
iovec and QEMUIOVector. This function also hasn't been marked
coroutine_fn yet, so it is cleaner to stick with bdrv_pread() until the
file is properly converted to coroutines.
[-- Attachment #1.2: Type: text/html, Size: 110279 bytes --]
[-- Attachment #2: 0002-Support-vhd-type-VHD_DIFFERENCING.patch --]
[-- Type: application/octet-stream, Size: 16577 bytes --]
From 5387a2a7b6ad052659a08a1fc7e89595708396d1 Mon Sep 17 00:00:00 2001
From: Xiaodong Gong <gordongong0350@gmail.com>
Date: Thu, 4 Sep 2014 01:14:59 +0800
Subject: [PATCH 2/2] Support vhd type VHD_DIFFERENCING
Now qemu only supports vhd type VHD_FIXED and VHD_DYNAMIC,
so qemu can't read snapshot volume of vhd, and can't support
other storage features of vhd file.
This patch add read parent information in function "vpc_open",
read bitmap in "vpc_read", and change bitmap in "vpc_write".
Signed-off-by: Xiaodong Gong <gordongong0350@gmail.com>
---
block/vpc.c | 329 +++++++++++++++++++++++++++++++++++++++++++++++-------------
1 file changed, 261 insertions(+), 68 deletions(-)
diff --git a/block/vpc.c b/block/vpc.c
index c024b4c..3ba0d57 100644
--- a/block/vpc.c
+++ b/block/vpc.c
@@ -33,13 +33,18 @@
/**************************************************************/
#define HEADER_SIZE 512
+#define DYNAMIC_HEADER_SIZE 1024
+#define PARENT_LOCATOR_NUM 8
+#define PARENT_PREFIX_LEN 7 /* such as file:// */
+#define TBBATMAP_HEAD_SIZE 28
+#define MACX 0x5863614d /* big endian */
//#define CACHE
enum vhd_type {
VHD_FIXED = 2,
VHD_DYNAMIC = 3,
- VHD_DIFFERENCING = 4,
+ VHD_DIFF = 4,
};
// Seconds since Jan 1, 2000 0:00:00 (UTC)
@@ -138,6 +143,15 @@ typedef struct BDRVVPCState {
Error *migration_blocker;
} BDRVVPCState;
+typedef struct vhd_tdbatmap_header {
+ char magic[8]; /* always "tdbatmap" */
+
+ uint64_t batmap_offset;
+ uint32_t batmap_size;
+ uint32_t batmap_version;
+ uint32_t checksum;
+} QEMU_PACKED VHDTdBatmapHeader;
+
static uint32_t vpc_checksum(uint8_t* buf, size_t size)
{
uint32_t res = 0;
@@ -153,7 +167,7 @@ static uint32_t vpc_checksum(uint8_t* buf, size_t size)
static int vpc_probe(const uint8_t *buf, int buf_size, const char *filename)
{
if (buf_size >= 8 && !strncmp((char *)buf, "conectix", 8))
- return 100;
+ return 100;
return 0;
}
@@ -164,11 +178,17 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
int i;
VHDFooter *footer;
VHDDynDiskHeader *dyndisk_header;
- uint8_t buf[HEADER_SIZE];
+ uint8_t buf[DYNAMIC_HEADER_SIZE];
+ uint8_t tdbatmap_header_buf[TBBATMAP_HEAD_SIZE];
uint32_t checksum;
uint64_t computed_size;
- int disk_type = VHD_DYNAMIC;
+ uint32_t disk_type;
int ret;
+ VHDTdBatmapHeader *tdbatmap_header;
+ int parent_locator_offset = 0;
+ int64_t data_offset = 0;
+ int data_length = 0;
+ uint32_t platform;
ret = bdrv_pread(bs->file, 0, s->footer_buf, HEADER_SIZE);
if (ret < 0) {
@@ -176,6 +196,8 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
}
footer = (VHDFooter *) s->footer_buf;
+ disk_type = be32_to_cpu(footer->type);
+
if (strncmp(footer->creator, "conectix", 8)) {
int64_t offset = bdrv_getlength(bs->file);
if (offset < 0) {
@@ -230,9 +252,9 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
goto fail;
}
- if (disk_type == VHD_DYNAMIC) {
+ if (disk_type == VHD_DYNAMIC || disk_type == VHD_DIFF) {
ret = bdrv_pread(bs->file, be64_to_cpu(footer->data_offset), buf,
- HEADER_SIZE);
+ DYNAMIC_HEADER_SIZE);
if (ret < 0) {
goto fail;
}
@@ -286,6 +308,56 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
s->free_data_block_offset =
(s->bat_offset + (s->max_table_entries * 4) + 511) & ~511;
+ /* Read tdbatmap header by offset */
+ ret = bdrv_pread(bs->file, s->free_data_block_offset,
+ tdbatmap_header_buf, TBBATMAP_HEAD_SIZE);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ tdbatmap_header = (VHDTdBatmapHeader *) tdbatmap_header_buf;
+ if (!strncmp(tdbatmap_header->magic, "tdbatmap", 8)) {
+ s->free_data_block_offset =
+ be32_to_cpu(tdbatmap_header->batmap_size) * 512
+ + be64_to_cpu(tdbatmap_header->batmap_offset);
+ }
+
+ /* Read backing file location from dyn header table */
+ if (dyndisk_header->parent_name[0] || dyndisk_header->parent_name[1]) {
+ for (i = 0; i < PARENT_LOCATOR_NUM; i++) {
+ data_offset =
+ be64_to_cpu(dyndisk_header->parent_locator[i].data_offset);
+ data_length =
+ be32_to_cpu(dyndisk_header->parent_locator[i].data_length);
+ platform = dyndisk_header->parent_locator[i].platform;
+
+ if (MACX == platform) {
+ if (data_offset + PARENT_PREFIX_LEN >
+ s->max_table_entries * s->block_size) {
+ goto fail;
+ }
+ if (data_length - PARENT_PREFIX_LEN > 1024) {
+ goto fail;
+ }
+ ret = bdrv_pread(bs->file, data_offset + PARENT_PREFIX_LEN,
+ bs->backing_file, data_length - PARENT_PREFIX_LEN);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ bs->backing_file[data_length - PARENT_PREFIX_LEN] = '\0';
+ }
+
+ if (data_offset > parent_locator_offset) {
+ parent_locator_offset = data_offset;
+ }
+ }
+ }
+
+ if (parent_locator_offset + 512 > s->free_data_block_offset) {
+ s->free_data_block_offset = parent_locator_offset + 512;
+ }
+
for (i = 0; i < s->max_table_entries; i++) {
be32_to_cpus(&s->pagetable[i]);
if (s->pagetable[i] != 0xFFFFFFFF) {
@@ -363,19 +435,6 @@ static inline int64_t get_sector_offset(BlockDriverState *bs,
bitmap_offset = 512 * (uint64_t) s->pagetable[pagetable_index];
block_offset = bitmap_offset + s->bitmap_size + (512 * pageentry_index);
- // We must ensure that we don't write to any sectors which are marked as
- // unused in the bitmap. We get away with setting all bits in the block
- // bitmap each time we write to a new block. This might cause Virtual PC to
- // miss sparse read optimization, but it's not a problem in terms of
- // correctness.
- if (write && (s->last_bitmap_offset != bitmap_offset)) {
- uint8_t bitmap[s->bitmap_size];
-
- s->last_bitmap_offset = bitmap_offset;
- memset(bitmap, 0xff, s->bitmap_size);
- bdrv_pwrite_sync(bs->file, bitmap_offset, bitmap, s->bitmap_size);
- }
-
// printf("sector: %" PRIx64 ", index: %x, offset: %x, bioff: %" PRIx64 ", bloff: %" PRIx64 "\n",
// sector_num, pagetable_index, pageentry_index,
// bitmap_offset, block_offset);
@@ -412,6 +471,53 @@ static inline int64_t get_sector_offset(BlockDriverState *bs,
}
/*
+ * Returns the absolute byte offset of the given sector in the differencing
+ * image file.
+ *
+ * If the sector is not allocated, -1 is returned instead. If the sector is
+ * allocated in the backing file, -2 is returned. If the sector is allocated
+ * in current file, the block offset is returned.
+ */
+static inline int64_t get_sector_offset_diff(BlockDriverState *bs,
+ int64_t sector_num)
+{
+ BDRVVPCState *s = bs->opaque;
+ uint64_t offset = sector_num << BDRV_SECTOR_BITS;
+ uint64_t bitmap_offset;
+ uint64_t block_offset;
+ uint32_t pagetable_index, pageentry_index;
+ uint32_t bitmap_index, bitmapentry_index;
+ uint8_t bitmap[s->bitmap_size];
+ int ret;
+
+ pagetable_index = offset / s->block_size;
+ if (pagetable_index >= s->max_table_entries) {
+ return -1;
+ } else if (0xffffffff == s->pagetable[pagetable_index]) {
+ return -2;
+ }
+
+ bitmap_offset = 512 * (uint64_t) s->pagetable[pagetable_index];
+ if (bitmap_offset > s->max_table_entries * s->block_size) {
+ return -1;
+ }
+ ret = bdrv_pread(bs->file, bitmap_offset, bitmap, s->bitmap_size);
+ if (ret < 0) {
+ return -1;
+ }
+
+ pageentry_index = (offset % s->block_size) / 512;
+ bitmap_index = pageentry_index / 8;
+ bitmapentry_index = 7 - pageentry_index % 8;
+ if (bitmap[bitmap_index] & 0x1 << bitmapentry_index) {
+ block_offset = bitmap_offset + s->bitmap_size + (512 * pageentry_index);
+ return block_offset;
+ } else {
+ return -2;
+ }
+}
+
+/*
* Writes the footer to the end of the image file. This is needed when the
* file grows as it overwrites the old footer
*
@@ -437,7 +543,8 @@ static int rewrite_footer(BlockDriverState* bs)
*
* Returns the sectors' offset in the image file on success and < 0 on error
*/
-static int64_t alloc_block(BlockDriverState* bs, int64_t sector_num)
+static int64_t alloc_block(BlockDriverState *bs, int64_t sector_num,
+ bool isdiff)
{
BDRVVPCState *s = bs->opaque;
int64_t bat_offset;
@@ -457,7 +564,11 @@ static int64_t alloc_block(BlockDriverState* bs, int64_t sector_num)
s->pagetable[index] = s->free_data_block_offset / 512;
// Initialize the block's bitmap
- memset(bitmap, 0xff, s->bitmap_size);
+ if (isdiff) {
+ memset(bitmap, 0x0, s->bitmap_size);
+ } else {
+ memset(bitmap, 0xff, s->bitmap_size);
+ }
ret = bdrv_pwrite_sync(bs->file, s->free_data_block_offset, bitmap,
s->bitmap_size);
if (ret < 0) {
@@ -501,36 +612,62 @@ static int vpc_read(BlockDriverState *bs, int64_t sector_num,
uint8_t *buf, int nb_sectors)
{
BDRVVPCState *s = bs->opaque;
- int ret;
- int64_t offset;
- int64_t sectors, sectors_per_block;
VHDFooter *footer = (VHDFooter *) s->footer_buf;
+ int64_t sectors_per_block = s->block_size >> BDRV_SECTOR_BITS;
+ int64_t offset, sectors;
+ int ret;
- if (be32_to_cpu(footer->type) == VHD_FIXED) {
+ switch (be32_to_cpu(footer->type)) {
+ case VHD_FIXED:
return bdrv_read(bs->file, sector_num, buf, nb_sectors);
- }
- while (nb_sectors > 0) {
- offset = get_sector_offset(bs, sector_num, 0);
-
- sectors_per_block = s->block_size >> BDRV_SECTOR_BITS;
- sectors = sectors_per_block - (sector_num % sectors_per_block);
- if (sectors > nb_sectors) {
- sectors = nb_sectors;
- }
+ case VHD_DYNAMIC:
+ while (nb_sectors > 0) {
+ sectors = sectors_per_block - (sector_num % sectors_per_block);
+ if (sectors > nb_sectors) {
+ sectors = nb_sectors;
+ }
- if (offset == -1) {
- memset(buf, 0, sectors * BDRV_SECTOR_SIZE);
- } else {
- ret = bdrv_pread(bs->file, offset, buf,
- sectors * BDRV_SECTOR_SIZE);
- if (ret != sectors * BDRV_SECTOR_SIZE) {
- return -1;
+ offset = get_sector_offset(bs, sector_num, 0);
+ if (-1 == offset) {
+ memset(buf, 0, sectors * BDRV_SECTOR_SIZE);
+ } else {
+ ret = bdrv_pread(bs->file, offset, buf,
+ sectors * BDRV_SECTOR_SIZE);
+ if (ret != sectors * BDRV_SECTOR_SIZE) {
+ return -1;
+ }
}
+
+ nb_sectors -= sectors;
+ sector_num += sectors;
+ buf += sectors * BDRV_SECTOR_SIZE;
}
+ break;
+ case VHD_DIFF:
+ while (nb_sectors > 0) {
+ offset = get_sector_offset_diff(bs, sector_num);
+ if (-1 == offset) {
+ memset(buf, 0, BDRV_SECTOR_SIZE);
+ } else if (-2 == offset) {
+ ret = bdrv_pread(bs->backing_hd, sector_num << BDRV_SECTOR_BITS
+ , buf, BDRV_SECTOR_SIZE);
+ if (ret < 0) {
+ return -1;
+ }
+ } else {
+ ret = bdrv_pread(bs->file, offset, buf, BDRV_SECTOR_SIZE);
+ if (ret != BDRV_SECTOR_SIZE) {
+ return -1;
+ }
+ }
- nb_sectors -= sectors;
- sector_num += sectors;
- buf += sectors * BDRV_SECTOR_SIZE;
+ nb_sectors--;
+ sector_num++;
+ buf += BDRV_SECTOR_SIZE;
+ }
+ break;
+ default:
+ return -1;
}
return 0;
}
@@ -546,43 +683,98 @@ static coroutine_fn int vpc_co_read(BlockDriverState *bs, int64_t sector_num,
return ret;
}
+static inline int64_t write_bitmap(BlockDriverState *bs, int64_t sector_num,
+ int64_t sectors)
+{
+ BDRVVPCState *s = bs->opaque;
+ uint64_t offset = sector_num << BDRV_SECTOR_BITS;
+ uint64_t bitmap_offset;
+ uint32_t pagetable_index, pageentry_index;
+ uint8_t bitmap[s->bitmap_size];
+ uint32_t bitmap_index, bitmapbit_index;
+ int i;
+ int ret;
+
+ pagetable_index = offset / s->block_size;
+ pageentry_index = (offset % s->block_size) / 512;
+ bitmap_offset = 512 * (uint64_t) s->pagetable[pagetable_index];
+
+ if (bitmap_offset > s->max_table_entries * s->block_size) {
+ return -1;
+ }
+ ret = bdrv_pread(bs->file, bitmap_offset, bitmap, s->bitmap_size);
+ if (ret < 0) {
+ return -1;
+ }
+
+ for (i = 0; i < sectors; i++) {
+ bitmap_index = pageentry_index / 8;
+ bitmapbit_index = 7 - pageentry_index % 8;
+ bitmap[bitmap_index] |= (0x1 << bitmapbit_index);
+ pageentry_index++;
+ }
+ ret = bdrv_pwrite(bs->file, bitmap_offset, bitmap, s->bitmap_size);
+ if (ret < 0) {
+ return -1;
+ }
+
+ return 0;
+}
+
static int vpc_write(BlockDriverState *bs, int64_t sector_num,
const uint8_t *buf, int nb_sectors)
{
BDRVVPCState *s = bs->opaque;
- int64_t offset;
- int64_t sectors, sectors_per_block;
+ VHDFooter *footer = (VHDFooter *) s->footer_buf;
+ int64_t sectors_per_block = s->block_size >> BDRV_SECTOR_BITS;
+ int64_t offset, sectors;
+ bool isdiff = true;
int ret;
- VHDFooter *footer = (VHDFooter *) s->footer_buf;
- if (be32_to_cpu(footer->type) == VHD_FIXED) {
+ switch (be32_to_cpu(footer->type)) {
+ case VHD_FIXED:
return bdrv_write(bs->file, sector_num, buf, nb_sectors);
- }
- while (nb_sectors > 0) {
- offset = get_sector_offset(bs, sector_num, 1);
-
- sectors_per_block = s->block_size >> BDRV_SECTOR_BITS;
- sectors = sectors_per_block - (sector_num % sectors_per_block);
- if (sectors > nb_sectors) {
- sectors = nb_sectors;
+ case VHD_DYNAMIC:
+ case VHD_DIFF:
+ if (VHD_DYNAMIC == be32_to_cpu(footer->type)) {
+ isdiff = false;
}
- if (offset == -1) {
- offset = alloc_block(bs, sector_num);
- if (offset < 0)
+ while (nb_sectors > 0) {
+ sectors = sectors_per_block - (sector_num % sectors_per_block);
+ if (sectors > nb_sectors) {
+ sectors = nb_sectors;
+ }
+
+ offset = get_sector_offset(bs, sector_num, 1);
+ if (offset == -1) {
+ offset = alloc_block(bs, sector_num, isdiff);
+ if (offset < 0) {
+ return -1;
+ }
+ }
+
+ ret = bdrv_pwrite(bs->file, offset, buf,
+ sectors * BDRV_SECTOR_SIZE);
+ if (ret != sectors * BDRV_SECTOR_SIZE) {
return -1;
- }
+ }
- ret = bdrv_pwrite(bs->file, offset, buf, sectors * BDRV_SECTOR_SIZE);
- if (ret != sectors * BDRV_SECTOR_SIZE) {
- return -1;
- }
+ if (true == isdiff) {
+ ret = write_bitmap(bs, sector_num, sectors);
+ if (ret < 0) {
+ return -1;
+ }
+ }
- nb_sectors -= sectors;
- sector_num += sectors;
- buf += sectors * BDRV_SECTOR_SIZE;
+ nb_sectors -= sectors;
+ sector_num += sectors;
+ buf += sectors * BDRV_SECTOR_SIZE;
+ }
+ break;
+ default:
+ return -1;
}
-
return 0;
}
@@ -910,6 +1102,7 @@ static BlockDriver bdrv_vpc = {
.bdrv_close = vpc_close,
.bdrv_reopen_prepare = vpc_reopen_prepare,
.bdrv_create = vpc_create,
+ .supports_backing = true,
.bdrv_read = vpc_co_read,
.bdrv_write = vpc_co_write,
--
1.8.3.1
^ permalink raw reply related [flat|nested] 3+ messages in thread
* Re: [Qemu-devel] [RFC PATCH v2] Support vhd type VHD_DIFFERENCING
2014-09-04 14:49 Gordon Gong
@ 2014-09-05 10:04 ` Stefan Hajnoczi
0 siblings, 0 replies; 3+ messages in thread
From: Stefan Hajnoczi @ 2014-09-05 10:04 UTC (permalink / raw)
To: Gordon Gong
Cc: Xiaoding (B), Liuji (Jeremy), Luohao (brian), qemu-devel,
Stefan Hajnoczi
[-- Attachment #1: Type: text/plain, Size: 1050 bytes --]
On Thu, Sep 04, 2014 at 10:49:43PM +0800, Gordon Gong wrote:
> [Qemu-devel][RFC PATCH v2] Support vhd type VHD_DIFFERENCING
>
>
>
> From 5387a2a7b6ad052659a08a1fc7e89595708396d1 Mon Sep 17 00:00:00 2001
>
> From: Xiaodong Gong <gordongong0350@gmail.com>
>
> Date: Thu, 4 Sep 2014 01:14:59 +0800
>
> Subject: [PATCH 2/2] Support vhd type VHD_DIFFERENCING
>
>
>
> Now qemu only supports vhd type VHD_FIXED and VHD_DYNAMIC,
>
> so qemu can't read snapshot volume of vhd, and can't support
>
> other storage features of vhd file.
>
>
>
> This patch add read parent information in function "vpc_open",
>
> read bitmap in "vpc_read", and change bitmap in "vpc_write".
>
>
>
> Signed-off-by: Xiaodong Gong <gordongong0350@gmail.com>
>
> ---
>
> block/vpc.c | 329
> +++++++++++++++++++++++++++++++++++++++++++++++-------------
>
> 1 file changed, 261 insertions(+), 68 deletions(-)
This patch is malformed. Please use git-send-email(1):
http://qemu-project.org/Contribute/SubmitAPatch
Stefan
[-- Attachment #2: Type: application/pgp-signature, Size: 473 bytes --]
^ permalink raw reply [flat|nested] 3+ messages in thread
* [Qemu-devel] [RFC PATCH v2] Support vhd type VHD_DIFFERENCING
@ 2014-09-05 18:55 =?gb18030?B?MjFH?=
0 siblings, 0 replies; 3+ messages in thread
From: =?gb18030?B?MjFH?= @ 2014-09-05 18:55 UTC (permalink / raw)
To: =?gb18030?B?a3dvbGY=?=, =?gb18030?B?c3RlZmFuaGE=?=
Cc: =?gb18030?B?cWVtdS1kZXZlbA==?=
[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain; charset="gb18030", Size: 17667 bytes --]
Now qemu only supports vhd type VHD_FIXED and VHD_DYNAMIC,
so qemu can't read snapshot volume of vhd, and can't support
other storage features of vhd file.
This patch add read parent information in function "vpc_open",
read bitmap in "vpc_read", and change bitmap in "vpc_write".
Signed-off-by: Xiaodong Gong <gordongong0350@gmail.com>
---
block/vpc.c | 329 +++++++++++++++++++++++++++++++++++++++++++++++-------------
1 file changed, 261 insertions(+), 68 deletions(-)
diff --git a/block/vpc.c b/block/vpc.c
index c024b4c..3ba0d57 100644
--- a/block/vpc.c
+++ b/block/vpc.c
@@ -33,13 +33,18 @@
/**************************************************************/
#define HEADER_SIZE 512
+#define DYNAMIC_HEADER_SIZE 1024
+#define PARENT_LOCATOR_NUM 8
+#define PARENT_PREFIX_LEN 7 /* such as file:// */
+#define TBBATMAP_HEAD_SIZE 28
+#define MACX 0x5863614d /* big endian */
//#define CACHE
enum vhd_type {
VHD_FIXED = 2,
VHD_DYNAMIC = 3,
- VHD_DIFFERENCING = 4,
+ VHD_DIFF = 4,
};
// Seconds since Jan 1, 2000 0:00:00 (UTC)
@@ -138,6 +143,15 @@ typedef struct BDRVVPCState {
Error *migration_blocker;
} BDRVVPCState;
+typedef struct vhd_tdbatmap_header {
+ char magic[8]; /* always "tdbatmap" */
+
+ uint64_t batmap_offset;
+ uint32_t batmap_size;
+ uint32_t batmap_version;
+ uint32_t checksum;
+} QEMU_PACKED VHDTdBatmapHeader;
+
static uint32_t vpc_checksum(uint8_t* buf, size_t size)
{
uint32_t res = 0;
@@ -153,7 +167,7 @@ static uint32_t vpc_checksum(uint8_t* buf, size_t size)
static int vpc_probe(const uint8_t *buf, int buf_size, const char *filename)
{
if (buf_size >= 8 && !strncmp((char *)buf, "conectix", 8))
- return 100;
+ return 100;
return 0;
}
@@ -164,11 +178,17 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
int i;
VHDFooter *footer;
VHDDynDiskHeader *dyndisk_header;
- uint8_t buf[HEADER_SIZE];
+ uint8_t buf[DYNAMIC_HEADER_SIZE];
+ uint8_t tdbatmap_header_buf[TBBATMAP_HEAD_SIZE];
uint32_t checksum;
uint64_t computed_size;
- int disk_type = VHD_DYNAMIC;
+ uint32_t disk_type;
int ret;
+ VHDTdBatmapHeader *tdbatmap_header;
+ int parent_locator_offset = 0;
+ int64_t data_offset = 0;
+ int data_length = 0;
+ uint32_t platform;
ret = bdrv_pread(bs->file, 0, s->footer_buf, HEADER_SIZE);
if (ret < 0) {
@@ -176,6 +196,8 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
}
footer = (VHDFooter *) s->footer_buf;
+ disk_type = be32_to_cpu(footer->type);
+
if (strncmp(footer->creator, "conectix", 8)) {
int64_t offset = bdrv_getlength(bs->file);
if (offset < 0) {
@@ -230,9 +252,9 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
goto fail;
}
- if (disk_type == VHD_DYNAMIC) {
+ if (disk_type == VHD_DYNAMIC || disk_type == VHD_DIFF) {
ret = bdrv_pread(bs->file, be64_to_cpu(footer->data_offset), buf,
- HEADER_SIZE);
+ DYNAMIC_HEADER_SIZE);
if (ret < 0) {
goto fail;
}
@@ -286,6 +308,56 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
s->free_data_block_offset =
(s->bat_offset + (s->max_table_entries * 4) + 511) & ~511;
+ /* Read tdbatmap header by offset */
+ ret = bdrv_pread(bs->file, s->free_data_block_offset,
+ tdbatmap_header_buf, TBBATMAP_HEAD_SIZE);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ tdbatmap_header = (VHDTdBatmapHeader *) tdbatmap_header_buf;
+ if (!strncmp(tdbatmap_header->magic, "tdbatmap", 8)) {
+ s->free_data_block_offset =
+ be32_to_cpu(tdbatmap_header->batmap_size) * 512
+ + be64_to_cpu(tdbatmap_header->batmap_offset);
+ }
+
+ /* Read backing file location from dyn header table */
+ if (dyndisk_header->parent_name[0] || dyndisk_header->parent_name[1]) {
+ for (i = 0; i < PARENT_LOCATOR_NUM; i++) {
+ data_offset =
+ be64_to_cpu(dyndisk_header->parent_locator[i].data_offset);
+ data_length =
+ be32_to_cpu(dyndisk_header->parent_locator[i].data_length);
+ platform = dyndisk_header->parent_locator[i].platform;
+
+ if (MACX == platform) {
+ if (data_offset + PARENT_PREFIX_LEN >
+ s->max_table_entries * s->block_size) {
+ goto fail;
+ }
+ if (data_length - PARENT_PREFIX_LEN > 1024) {
+ goto fail;
+ }
+ ret = bdrv_pread(bs->file, data_offset + PARENT_PREFIX_LEN,
+ bs->backing_file, data_length - PARENT_PREFIX_LEN);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ bs->backing_file[data_length - PARENT_PREFIX_LEN] = '\0';
+ }
+
+ if (data_offset > parent_locator_offset) {
+ parent_locator_offset = data_offset;
+ }
+ }
+ }
+
+ if (parent_locator_offset + 512 > s->free_data_block_offset) {
+ s->free_data_block_offset = parent_locator_offset + 512;
+ }
+
for (i = 0; i < s->max_table_entries; i++) {
be32_to_cpus(&s->pagetable[i]);
if (s->pagetable[i] != 0xFFFFFFFF) {
@@ -363,19 +435,6 @@ static inline int64_t get_sector_offset(BlockDriverState *bs,
bitmap_offset = 512 * (uint64_t) s->pagetable[pagetable_index];
block_offset = bitmap_offset + s->bitmap_size + (512 * pageentry_index);
- // We must ensure that we don't write to any sectors which are marked as
- // unused in the bitmap. We get away with setting all bits in the block
- // bitmap each time we write to a new block. This might cause Virtual PC to
- // miss sparse read optimization, but it's not a problem in terms of
- // correctness.
- if (write && (s->last_bitmap_offset != bitmap_offset)) {
- uint8_t bitmap[s->bitmap_size];
-
- s->last_bitmap_offset = bitmap_offset;
- memset(bitmap, 0xff, s->bitmap_size);
- bdrv_pwrite_sync(bs->file, bitmap_offset, bitmap, s->bitmap_size);
- }
-
// printf("sector: %" PRIx64 ", index: %x, offset: %x, bioff: %" PRIx64 ", bloff: %" PRIx64 "\n",
// sector_num, pagetable_index, pageentry_index,
// bitmap_offset, block_offset);
@@ -412,6 +471,53 @@ static inline int64_t get_sector_offset(BlockDriverState *bs,
}
/*
+ * Returns the absolute byte offset of the given sector in the differencing
+ * image file.
+ *
+ * If the sector is not allocated, -1 is returned instead. If the sector is
+ * allocated in the backing file, -2 is returned. If the sector is allocated
+ * in current file, the block offset is returned.
+ */
+static inline int64_t get_sector_offset_diff(BlockDriverState *bs,
+ int64_t sector_num)
+{
+ BDRVVPCState *s = bs->opaque;
+ uint64_t offset = sector_num << BDRV_SECTOR_BITS;
+ uint64_t bitmap_offset;
+ uint64_t block_offset;
+ uint32_t pagetable_index, pageentry_index;
+ uint32_t bitmap_index, bitmapentry_index;
+ uint8_t bitmap[s->bitmap_size];
+ int ret;
+
+ pagetable_index = offset / s->block_size;
+ if (pagetable_index >= s->max_table_entries) {
+ return -1;
+ } else if (0xffffffff == s->pagetable[pagetable_index]) {
+ return -2;
+ }
+
+ bitmap_offset = 512 * (uint64_t) s->pagetable[pagetable_index];
+ if (bitmap_offset > s->max_table_entries * s->block_size) {
+ return -1;
+ }
+ ret = bdrv_pread(bs->file, bitmap_offset, bitmap, s->bitmap_size);
+ if (ret < 0) {
+ return -1;
+ }
+
+ pageentry_index = (offset % s->block_size) / 512;
+ bitmap_index = pageentry_index / 8;
+ bitmapentry_index = 7 - pageentry_index % 8;
+ if (bitmap[bitmap_index] & 0x1 << bitmapentry_index) {
+ block_offset = bitmap_offset + s->bitmap_size + (512 * pageentry_index);
+ return block_offset;
+ } else {
+ return -2;
+ }
+}
+
+/*
* Writes the footer to the end of the image file. This is needed when the
* file grows as it overwrites the old footer
*
@@ -437,7 +543,8 @@ static int rewrite_footer(BlockDriverState* bs)
*
* Returns the sectors' offset in the image file on success and < 0 on error
*/
-static int64_t alloc_block(BlockDriverState* bs, int64_t sector_num)
+static int64_t alloc_block(BlockDriverState *bs, int64_t sector_num,
+ bool isdiff)
{
BDRVVPCState *s = bs->opaque;
int64_t bat_offset;
@@ -457,7 +564,11 @@ static int64_t alloc_block(BlockDriverState* bs, int64_t sector_num)
s->pagetable[index] = s->free_data_block_offset / 512;
// Initialize the block's bitmap
- memset(bitmap, 0xff, s->bitmap_size);
+ if (isdiff) {
+ memset(bitmap, 0x0, s->bitmap_size);
+ } else {
+ memset(bitmap, 0xff, s->bitmap_size);
+ }
ret = bdrv_pwrite_sync(bs->file, s->free_data_block_offset, bitmap,
s->bitmap_size);
if (ret < 0) {
@@ -501,36 +612,62 @@ static int vpc_read(BlockDriverState *bs, int64_t sector_num,
uint8_t *buf, int nb_sectors)
{
BDRVVPCState *s = bs->opaque;
- int ret;
- int64_t offset;
- int64_t sectors, sectors_per_block;
VHDFooter *footer = (VHDFooter *) s->footer_buf;
+ int64_t sectors_per_block = s->block_size >> BDRV_SECTOR_BITS;
+ int64_t offset, sectors;
+ int ret;
- if (be32_to_cpu(footer->type) == VHD_FIXED) {
+ switch (be32_to_cpu(footer->type)) {
+ case VHD_FIXED:
return bdrv_read(bs->file, sector_num, buf, nb_sectors);
- }
- while (nb_sectors > 0) {
- offset = get_sector_offset(bs, sector_num, 0);
-
- sectors_per_block = s->block_size >> BDRV_SECTOR_BITS;
- sectors = sectors_per_block - (sector_num % sectors_per_block);
- if (sectors > nb_sectors) {
- sectors = nb_sectors;
- }
+ case VHD_DYNAMIC:
+ while (nb_sectors > 0) {
+ sectors = sectors_per_block - (sector_num % sectors_per_block);
+ if (sectors > nb_sectors) {
+ sectors = nb_sectors;
+ }
- if (offset == -1) {
- memset(buf, 0, sectors * BDRV_SECTOR_SIZE);
- } else {
- ret = bdrv_pread(bs->file, offset, buf,
- sectors * BDRV_SECTOR_SIZE);
- if (ret != sectors * BDRV_SECTOR_SIZE) {
- return -1;
+ offset = get_sector_offset(bs, sector_num, 0);
+ if (-1 == offset) {
+ memset(buf, 0, sectors * BDRV_SECTOR_SIZE);
+ } else {
+ ret = bdrv_pread(bs->file, offset, buf,
+ sectors * BDRV_SECTOR_SIZE);
+ if (ret != sectors * BDRV_SECTOR_SIZE) {
+ return -1;
+ }
}
+
+ nb_sectors -= sectors;
+ sector_num += sectors;
+ buf += sectors * BDRV_SECTOR_SIZE;
}
+ break;
+ case VHD_DIFF:
+ while (nb_sectors > 0) {
+ offset = get_sector_offset_diff(bs, sector_num);
+ if (-1 == offset) {
+ memset(buf, 0, BDRV_SECTOR_SIZE);
+ } else if (-2 == offset) {
+ ret = bdrv_pread(bs->backing_hd, sector_num << BDRV_SECTOR_BITS
+ , buf, BDRV_SECTOR_SIZE);
+ if (ret < 0) {
+ return -1;
+ }
+ } else {
+ ret = bdrv_pread(bs->file, offset, buf, BDRV_SECTOR_SIZE);
+ if (ret != BDRV_SECTOR_SIZE) {
+ return -1;
+ }
+ }
- nb_sectors -= sectors;
- sector_num += sectors;
- buf += sectors * BDRV_SECTOR_SIZE;
+ nb_sectors--;
+ sector_num++;
+ buf += BDRV_SECTOR_SIZE;
+ }
+ break;
+ default:
+ return -1;
}
return 0;
}
@@ -546,43 +683,98 @@ static coroutine_fn int vpc_co_read(BlockDriverState *bs, int64_t sector_num,
return ret;
}
+static inline int64_t write_bitmap(BlockDriverState *bs, int64_t sector_num,
+ int64_t sectors)
+{
+ BDRVVPCState *s = bs->opaque;
+ uint64_t offset = sector_num << BDRV_SECTOR_BITS;
+ uint64_t bitmap_offset;
+ uint32_t pagetable_index, pageentry_index;
+ uint8_t bitmap[s->bitmap_size];
+ uint32_t bitmap_index, bitmapbit_index;
+ int i;
+ int ret;
+
+ pagetable_index = offset / s->block_size;
+ pageentry_index = (offset % s->block_size) / 512;
+ bitmap_offset = 512 * (uint64_t) s->pagetable[pagetable_index];
+
+ if (bitmap_offset > s->max_table_entries * s->block_size) {
+ return -1;
+ }
+ ret = bdrv_pread(bs->file, bitmap_offset, bitmap, s->bitmap_size);
+ if (ret < 0) {
+ return -1;
+ }
+
+ for (i = 0; i < sectors; i++) {
+ bitmap_index = pageentry_index / 8;
+ bitmapbit_index = 7 - pageentry_index % 8;
+ bitmap[bitmap_index] |= (0x1 << bitmapbit_index);
+ pageentry_index++;
+ }
+ ret = bdrv_pwrite(bs->file, bitmap_offset, bitmap, s->bitmap_size);
+ if (ret < 0) {
+ return -1;
+ }
+
+ return 0;
+}
+
static int vpc_write(BlockDriverState *bs, int64_t sector_num,
const uint8_t *buf, int nb_sectors)
{
BDRVVPCState *s = bs->opaque;
- int64_t offset;
- int64_t sectors, sectors_per_block;
+ VHDFooter *footer = (VHDFooter *) s->footer_buf;
+ int64_t sectors_per_block = s->block_size >> BDRV_SECTOR_BITS;
+ int64_t offset, sectors;
+ bool isdiff = true;
int ret;
- VHDFooter *footer = (VHDFooter *) s->footer_buf;
- if (be32_to_cpu(footer->type) == VHD_FIXED) {
+ switch (be32_to_cpu(footer->type)) {
+ case VHD_FIXED:
return bdrv_write(bs->file, sector_num, buf, nb_sectors);
- }
- while (nb_sectors > 0) {
- offset = get_sector_offset(bs, sector_num, 1);
-
- sectors_per_block = s->block_size >> BDRV_SECTOR_BITS;
- sectors = sectors_per_block - (sector_num % sectors_per_block);
- if (sectors > nb_sectors) {
- sectors = nb_sectors;
+ case VHD_DYNAMIC:
+ case VHD_DIFF:
+ if (VHD_DYNAMIC == be32_to_cpu(footer->type)) {
+ isdiff = false;
}
- if (offset == -1) {
- offset = alloc_block(bs, sector_num);
- if (offset < 0)
+ while (nb_sectors > 0) {
+ sectors = sectors_per_block - (sector_num % sectors_per_block);
+ if (sectors > nb_sectors) {
+ sectors = nb_sectors;
+ }
+
+ offset = get_sector_offset(bs, sector_num, 1);
+ if (offset == -1) {
+ offset = alloc_block(bs, sector_num, isdiff);
+ if (offset < 0) {
+ return -1;
+ }
+ }
+
+ ret = bdrv_pwrite(bs->file, offset, buf,
+ sectors * BDRV_SECTOR_SIZE);
+ if (ret != sectors * BDRV_SECTOR_SIZE) {
return -1;
- }
+ }
- ret = bdrv_pwrite(bs->file, offset, buf, sectors * BDRV_SECTOR_SIZE);
- if (ret != sectors * BDRV_SECTOR_SIZE) {
- return -1;
- }
+ if (true == isdiff) {
+ ret = write_bitmap(bs, sector_num, sectors);
+ if (ret < 0) {
+ return -1;
+ }
+ }
- nb_sectors -= sectors;
- sector_num += sectors;
- buf += sectors * BDRV_SECTOR_SIZE;
+ nb_sectors -= sectors;
+ sector_num += sectors;
+ buf += sectors * BDRV_SECTOR_SIZE;
+ }
+ break;
+ default:
+ return -1;
}
-
return 0;
}
@@ -910,6 +1102,7 @@ static BlockDriver bdrv_vpc = {
.bdrv_close = vpc_close,
.bdrv_reopen_prepare = vpc_reopen_prepare,
.bdrv_create = vpc_create,
+ .supports_backing = true,
.bdrv_read = vpc_co_read,
.bdrv_write = vpc_co_write,
--
1.8.3.1
1. bdrv_preadv and bdrv_pwritev affer get_sector_offset_* is already checked, others are checked.
2. MACX is a big-endian number, so there is no need be32_to_cpu, but I added a comment to MACX.
3. clean the code no used after in vpc_open.
4. move bdrv_co_readv() to bdrv_preadv in vpc_read.
5. Added some code to make it easy to understand.
6. the wrong use of cpu_to_be32 is fixed with another patch.
Last, it is hard to use "git sendmail" to your mailbox through gmail, because of GFW in china, so I only could
send to my mail.qq.com and forward to it. Hope that could run ! '
I am so sorry for the last mail, I must add a fixed subject prefix in my email that out of company, so copy the
code£¬ screwed up.
[-- Attachment #2: Type: text/html, Size: 35854 bytes --]
^ permalink raw reply related [flat|nested] 3+ messages in thread
end of thread, other threads:[~2014-09-05 18:56 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2014-09-05 18:55 [Qemu-devel] [RFC PATCH v2] Support vhd type VHD_DIFFERENCING =?gb18030?B?MjFH?=
-- strict thread matches above, loose matches on Subject: below --
2014-09-04 14:49 Gordon Gong
2014-09-05 10:04 ` Stefan Hajnoczi
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).