We are generally moving to int64_t for both offset and bytes parameters
on all io paths.
Main motivation is realization of 64-bit write_zeroes operation for
fast zeroing large disk chunks, up to the whole disk.
We chose signed type, to be consistent with off_t (which is signed) and
with possibility for signed return type (where negative value means
error).
Now bdrv layer is converted, convert blk layer too.
Series: 64bit-block-status
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
---
include/sysemu/block-backend.h | 26 +++++++--------
block/block-backend.c | 60 ++++++++++++++++++----------------
2 files changed, 44 insertions(+), 42 deletions(-)
diff --git a/include/sysemu/block-backend.h b/include/sysemu/block-backend.h
index 9bbdbd63d7..0c1eee1778 100644
--- a/include/sysemu/block-backend.h
+++ b/include/sysemu/block-backend.h
@@ -119,14 +119,14 @@ BlockBackend *blk_by_dev(void *dev);
BlockBackend *blk_by_qdev_id(const char *id, Error **errp);
void blk_set_dev_ops(BlockBackend *blk, const BlockDevOps *ops, void *opaque);
int coroutine_fn blk_co_preadv(BlockBackend *blk, int64_t offset,
- unsigned int bytes, QEMUIOVector *qiov,
+ int64_t bytes, QEMUIOVector *qiov,
BdrvRequestFlags flags);
int coroutine_fn blk_co_pwritev_part(BlockBackend *blk, int64_t offset,
- unsigned int bytes,
+ int64_t bytes,
QEMUIOVector *qiov, size_t qiov_offset,
BdrvRequestFlags flags);
int coroutine_fn blk_co_pwritev(BlockBackend *blk, int64_t offset,
- unsigned int bytes, QEMUIOVector *qiov,
+ int64_t bytes, QEMUIOVector *qiov,
BdrvRequestFlags flags);
static inline int coroutine_fn blk_co_pread(BlockBackend *blk, int64_t offset,
@@ -148,13 +148,13 @@ static inline int coroutine_fn blk_co_pwrite(BlockBackend *blk, int64_t offset,
}
int blk_pwrite_zeroes(BlockBackend *blk, int64_t offset,
- int bytes, BdrvRequestFlags flags);
+ int64_t bytes, BdrvRequestFlags flags);
BlockAIOCB *blk_aio_pwrite_zeroes(BlockBackend *blk, int64_t offset,
- int bytes, BdrvRequestFlags flags,
+ int64_t bytes, BdrvRequestFlags flags,
BlockCompletionFunc *cb, void *opaque);
int blk_make_zero(BlockBackend *blk, BdrvRequestFlags flags);
-int blk_pread(BlockBackend *blk, int64_t offset, void *buf, int bytes);
-int blk_pwrite(BlockBackend *blk, int64_t offset, const void *buf, int bytes,
+int blk_pread(BlockBackend *blk, int64_t offset, void *buf, int64_t bytes);
+int blk_pwrite(BlockBackend *blk, int64_t offset, const void *buf, int64_t bytes,
BdrvRequestFlags flags);
int64_t blk_getlength(BlockBackend *blk);
void blk_get_geometry(BlockBackend *blk, uint64_t *nb_sectors_ptr);
@@ -167,14 +167,14 @@ BlockAIOCB *blk_aio_pwritev(BlockBackend *blk, int64_t offset,
BlockCompletionFunc *cb, void *opaque);
BlockAIOCB *blk_aio_flush(BlockBackend *blk,
BlockCompletionFunc *cb, void *opaque);
-BlockAIOCB *blk_aio_pdiscard(BlockBackend *blk, int64_t offset, int bytes,
+BlockAIOCB *blk_aio_pdiscard(BlockBackend *blk, int64_t offset, int64_t bytes,
BlockCompletionFunc *cb, void *opaque);
void blk_aio_cancel(BlockAIOCB *acb);
void blk_aio_cancel_async(BlockAIOCB *acb);
int blk_ioctl(BlockBackend *blk, unsigned long int req, void *buf);
BlockAIOCB *blk_aio_ioctl(BlockBackend *blk, unsigned long int req, void *buf,
BlockCompletionFunc *cb, void *opaque);
-int blk_co_pdiscard(BlockBackend *blk, int64_t offset, int bytes);
+int blk_co_pdiscard(BlockBackend *blk, int64_t offset, int64_t bytes);
int blk_co_flush(BlockBackend *blk);
int blk_flush(BlockBackend *blk);
int blk_commit_all(void);
@@ -233,12 +233,12 @@ int blk_get_open_flags_from_root_state(BlockBackend *blk);
void *blk_aio_get(const AIOCBInfo *aiocb_info, BlockBackend *blk,
BlockCompletionFunc *cb, void *opaque);
int coroutine_fn blk_co_pwrite_zeroes(BlockBackend *blk, int64_t offset,
- int bytes, BdrvRequestFlags flags);
+ int64_t bytes, BdrvRequestFlags flags);
int blk_pwrite_compressed(BlockBackend *blk, int64_t offset, const void *buf,
- int bytes);
+ int64_t bytes);
int blk_truncate(BlockBackend *blk, int64_t offset, bool exact,
PreallocMode prealloc, Error **errp);
-int blk_pdiscard(BlockBackend *blk, int64_t offset, int bytes);
+int blk_pdiscard(BlockBackend *blk, int64_t offset, int64_t bytes);
int blk_save_vmstate(BlockBackend *blk, const uint8_t *buf,
int64_t pos, int size);
int blk_load_vmstate(BlockBackend *blk, uint8_t *buf, int64_t pos, int size);
@@ -259,7 +259,7 @@ void blk_unregister_buf(BlockBackend *blk, void *host);
int coroutine_fn blk_co_copy_range(BlockBackend *blk_in, int64_t off_in,
BlockBackend *blk_out, int64_t off_out,
- int bytes, BdrvRequestFlags read_flags,
+ int64_t bytes, BdrvRequestFlags read_flags,
BdrvRequestFlags write_flags);
const BdrvChild *blk_root(BlockBackend *blk);
diff --git a/block/block-backend.c b/block/block-backend.c
index 38ae413826..b3f6edfc70 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -1110,11 +1110,11 @@ void blk_set_disable_request_queuing(BlockBackend *blk, bool disable)
}
static int blk_check_byte_request(BlockBackend *blk, int64_t offset,
- size_t size)
+ int64_t bytes)
{
int64_t len;
- if (size > INT_MAX) {
+ if (bytes > INT_MAX) {
return -EIO;
}
@@ -1122,7 +1122,7 @@ static int blk_check_byte_request(BlockBackend *blk, int64_t offset,
return -ENOMEDIUM;
}
- if (offset < 0) {
+ if (offset < 0 || bytes < 0) {
return -EIO;
}
@@ -1132,7 +1132,7 @@ static int blk_check_byte_request(BlockBackend *blk, int64_t offset,
return len;
}
- if (offset > len || len - offset < size) {
+ if (offset > len || len - offset < bytes) {
return -EIO;
}
}
@@ -1154,7 +1154,7 @@ static void coroutine_fn blk_wait_while_drained(BlockBackend *blk)
/* To be called between exactly one pair of blk_inc/dec_in_flight() */
static int coroutine_fn
-blk_do_preadv(BlockBackend *blk, int64_t offset, unsigned int bytes,
+blk_do_preadv(BlockBackend *blk, int64_t offset, int64_t bytes,
QEMUIOVector *qiov, BdrvRequestFlags flags)
{
int ret;
@@ -1185,7 +1185,7 @@ blk_do_preadv(BlockBackend *blk, int64_t offset, unsigned int bytes,
}
int coroutine_fn blk_co_preadv(BlockBackend *blk, int64_t offset,
- unsigned int bytes, QEMUIOVector *qiov,
+ int64_t bytes, QEMUIOVector *qiov,
BdrvRequestFlags flags)
{
int ret;
@@ -1199,7 +1199,7 @@ int coroutine_fn blk_co_preadv(BlockBackend *blk, int64_t offset,
/* To be called between exactly one pair of blk_inc/dec_in_flight() */
static int coroutine_fn
-blk_do_pwritev_part(BlockBackend *blk, int64_t offset, unsigned int bytes,
+blk_do_pwritev_part(BlockBackend *blk, int64_t offset, int64_t bytes,
QEMUIOVector *qiov, size_t qiov_offset,
BdrvRequestFlags flags)
{
@@ -1235,7 +1235,7 @@ blk_do_pwritev_part(BlockBackend *blk, int64_t offset, unsigned int bytes,
}
int coroutine_fn blk_co_pwritev_part(BlockBackend *blk, int64_t offset,
- unsigned int bytes,
+ int64_t bytes,
QEMUIOVector *qiov, size_t qiov_offset,
BdrvRequestFlags flags)
{
@@ -1249,7 +1249,7 @@ int coroutine_fn blk_co_pwritev_part(BlockBackend *blk, int64_t offset,
}
int coroutine_fn blk_co_pwritev(BlockBackend *blk, int64_t offset,
- unsigned int bytes, QEMUIOVector *qiov,
+ int64_t bytes, QEMUIOVector *qiov,
BdrvRequestFlags flags)
{
return blk_co_pwritev_part(blk, offset, bytes, qiov, 0, flags);
@@ -1311,7 +1311,7 @@ static int blk_prw(BlockBackend *blk, int64_t offset, uint8_t *buf,
}
int blk_pwrite_zeroes(BlockBackend *blk, int64_t offset,
- int bytes, BdrvRequestFlags flags)
+ int64_t bytes, BdrvRequestFlags flags)
{
return blk_prw(blk, offset, NULL, bytes, blk_write_entry,
flags | BDRV_REQ_ZERO_WRITE);
@@ -1361,7 +1361,7 @@ BlockAIOCB *blk_abort_aio_request(BlockBackend *blk,
typedef struct BlkAioEmAIOCB {
BlockAIOCB common;
BlkRwCo rwco;
- int bytes;
+ int64_t bytes;
bool has_returned;
} BlkAioEmAIOCB;
@@ -1385,7 +1385,8 @@ static void blk_aio_complete_bh(void *opaque)
blk_aio_complete(acb);
}
-static BlockAIOCB *blk_aio_prwv(BlockBackend *blk, int64_t offset, int bytes,
+static BlockAIOCB *blk_aio_prwv(BlockBackend *blk,
+ int64_t offset, int64_t bytes,
void *iobuf, CoroutineEntry co_entry,
BdrvRequestFlags flags,
BlockCompletionFunc *cb, void *opaque)
@@ -1442,31 +1443,31 @@ static void blk_aio_write_entry(void *opaque)
}
BlockAIOCB *blk_aio_pwrite_zeroes(BlockBackend *blk, int64_t offset,
- int count, BdrvRequestFlags flags,
+ int64_t bytes, BdrvRequestFlags flags,
BlockCompletionFunc *cb, void *opaque)
{
- return blk_aio_prwv(blk, offset, count, NULL, blk_aio_write_entry,
+ return blk_aio_prwv(blk, offset, bytes, NULL, blk_aio_write_entry,
flags | BDRV_REQ_ZERO_WRITE, cb, opaque);
}
-int blk_pread(BlockBackend *blk, int64_t offset, void *buf, int count)
+int blk_pread(BlockBackend *blk, int64_t offset, void *buf, int64_t bytes)
{
- int ret = blk_prw(blk, offset, buf, count, blk_read_entry, 0);
+ int ret = blk_prw(blk, offset, buf, bytes, blk_read_entry, 0);
if (ret < 0) {
return ret;
}
- return count;
+ return bytes;
}
-int blk_pwrite(BlockBackend *blk, int64_t offset, const void *buf, int count,
- BdrvRequestFlags flags)
+int blk_pwrite(BlockBackend *blk, int64_t offset, const void *buf,
+ int64_t bytes, BdrvRequestFlags flags)
{
- int ret = blk_prw(blk, offset, (void *) buf, count, blk_write_entry,
+ int ret = blk_prw(blk, offset, (void *) buf, bytes, blk_write_entry,
flags);
if (ret < 0) {
return ret;
}
- return count;
+ return bytes;
}
int64_t blk_getlength(BlockBackend *blk)
@@ -1567,7 +1568,7 @@ BlockAIOCB *blk_aio_ioctl(BlockBackend *blk, unsigned long int req, void *buf,
/* To be called between exactly one pair of blk_inc/dec_in_flight() */
static int coroutine_fn
-blk_do_pdiscard(BlockBackend *blk, int64_t offset, int bytes)
+blk_do_pdiscard(BlockBackend *blk, int64_t offset, int64_t bytes)
{
int ret;
@@ -1591,14 +1592,15 @@ static void blk_aio_pdiscard_entry(void *opaque)
}
BlockAIOCB *blk_aio_pdiscard(BlockBackend *blk,
- int64_t offset, int bytes,
+ int64_t offset, int64_t bytes,
BlockCompletionFunc *cb, void *opaque)
{
return blk_aio_prwv(blk, offset, bytes, NULL, blk_aio_pdiscard_entry, 0,
cb, opaque);
}
-int coroutine_fn blk_co_pdiscard(BlockBackend *blk, int64_t offset, int bytes)
+int coroutine_fn blk_co_pdiscard(BlockBackend *blk, int64_t offset,
+ int64_t bytes)
{
int ret;
@@ -1618,7 +1620,7 @@ static void blk_pdiscard_entry(void *opaque)
aio_wait_kick();
}
-int blk_pdiscard(BlockBackend *blk, int64_t offset, int bytes)
+int blk_pdiscard(BlockBackend *blk, int64_t offset, int64_t bytes)
{
return blk_prw(blk, offset, NULL, bytes, blk_pdiscard_entry, 0);
}
@@ -2123,16 +2125,16 @@ void *blk_aio_get(const AIOCBInfo *aiocb_info, BlockBackend *blk,
}
int coroutine_fn blk_co_pwrite_zeroes(BlockBackend *blk, int64_t offset,
- int bytes, BdrvRequestFlags flags)
+ int64_t bytes, BdrvRequestFlags flags)
{
return blk_co_pwritev(blk, offset, bytes, NULL,
flags | BDRV_REQ_ZERO_WRITE);
}
int blk_pwrite_compressed(BlockBackend *blk, int64_t offset, const void *buf,
- int count)
+ int64_t bytes)
{
- return blk_prw(blk, offset, (void *) buf, count, blk_write_entry,
+ return blk_prw(blk, offset, (void *) buf, bytes, blk_write_entry,
BDRV_REQ_WRITE_COMPRESSED);
}
@@ -2358,7 +2360,7 @@ void blk_unregister_buf(BlockBackend *blk, void *host)
int coroutine_fn blk_co_copy_range(BlockBackend *blk_in, int64_t off_in,
BlockBackend *blk_out, int64_t off_out,
- int bytes, BdrvRequestFlags read_flags,
+ int64_t bytes, BdrvRequestFlags read_flags,
BdrvRequestFlags write_flags)
{
int r;
--
2.21.0
On 4/30/20 6:10 AM, Vladimir Sementsov-Ogievskiy wrote:
> We are generally moving to int64_t for both offset and bytes parameters
> on all io paths.
>
> Main motivation is realization of 64-bit write_zeroes operation for
> fast zeroing large disk chunks, up to the whole disk.
>
> We chose signed type, to be consistent with off_t (which is signed) and
> with possibility for signed return type (where negative value means
> error).
>
> Now bdrv layer is converted, convert blk layer too.
In fact, I just discovered thanks to
https://bugs.launchpad.net/qemu/+bug/1884831 that NBD is a case of a
client that can currently pass values larger than 2G into
blk_co_pdiscard() which in turn appears as a negative value and instant
EIO failure. So this is a bug fix visible to NBD clients.
$ gdb --args ./qemu-nbd --trace=nbd_\* -f raw f --port 10810
...
(gdb) b blk_co_pdiscard
(gdb) r
...
$ nbdsh -u nbd://localhost:10810 -c 'h.trim(3*1024*1024*1024,0)'
...
Thread 1 "qemu-nbd" hit Breakpoint 3, blk_co_pdiscard (blk=0x555555832dc0,
offset=0, bytes=-1073741824)
Looks like I now have even more reason to accelerate my review of the
remainder of this series, and to take some (if not all) of it through
the NBD tree.
> +++ b/include/sysemu/block-backend.h
> @@ -119,14 +119,14 @@ BlockBackend *blk_by_dev(void *dev);
> BlockBackend *blk_by_qdev_id(const char *id, Error **errp);
> void blk_set_dev_ops(BlockBackend *blk, const BlockDevOps *ops, void *opaque);
> int coroutine_fn blk_co_preadv(BlockBackend *blk, int64_t offset,
> - unsigned int bytes, QEMUIOVector *qiov,
> + int64_t bytes, QEMUIOVector *qiov,
> BdrvRequestFlags flags);
> int coroutine_fn blk_co_pwritev_part(BlockBackend *blk, int64_t offset,
> - unsigned int bytes,
> + int64_t bytes,
> QEMUIOVector *qiov, size_t qiov_offset,
> BdrvRequestFlags flags);
> int coroutine_fn blk_co_pwritev(BlockBackend *blk, int64_t offset,
> - unsigned int bytes, QEMUIOVector *qiov,
> + int64_t bytes, QEMUIOVector *qiov,
> BdrvRequestFlags flags);
pread and pwrite weren't necessarily problems for NBD (since our NBD
implementation caps things to 32M per packet).
>
> static inline int coroutine_fn blk_co_pread(BlockBackend *blk, int64_t offset,
> @@ -148,13 +148,13 @@ static inline int coroutine_fn blk_co_pwrite(BlockBackend *blk, int64_t offset,
> }
>
> int blk_pwrite_zeroes(BlockBackend *blk, int64_t offset,
> - int bytes, BdrvRequestFlags flags);
> + int64_t bytes, BdrvRequestFlags flags);
> BlockAIOCB *blk_aio_pwrite_zeroes(BlockBackend *blk, int64_t offset,
> - int bytes, BdrvRequestFlags flags,
> + int64_t bytes, BdrvRequestFlags flags,
> BlockCompletionFunc *cb, void *opaque);
But this change to writing zeroes,
> int blk_make_zero(BlockBackend *blk, BdrvRequestFlags flags);
> -int blk_pread(BlockBackend *blk, int64_t offset, void *buf, int bytes);
> -int blk_pwrite(BlockBackend *blk, int64_t offset, const void *buf, int bytes,
> +int blk_pread(BlockBackend *blk, int64_t offset, void *buf, int64_t bytes);
> +int blk_pwrite(BlockBackend *blk, int64_t offset, const void *buf, int64_t bytes,
> BdrvRequestFlags flags);
> int64_t blk_getlength(BlockBackend *blk);
> void blk_get_geometry(BlockBackend *blk, uint64_t *nb_sectors_ptr);
> @@ -167,14 +167,14 @@ BlockAIOCB *blk_aio_pwritev(BlockBackend *blk, int64_t offset,
> BlockCompletionFunc *cb, void *opaque);
> BlockAIOCB *blk_aio_flush(BlockBackend *blk,
> BlockCompletionFunc *cb, void *opaque);
> -BlockAIOCB *blk_aio_pdiscard(BlockBackend *blk, int64_t offset, int bytes,
> +BlockAIOCB *blk_aio_pdiscard(BlockBackend *blk, int64_t offset, int64_t bytes,
> BlockCompletionFunc *cb, void *opaque);
and this change to discard are definitely both bug fixes for NBD
clients, especially now that we have a real-world case of a client
(namely the blkdiscard app triggering ioctl(BLKDISCARD) handling through
nbd.ko as client) that actually triggers a >2G trim request.
--
Eric Blake, Principal Software Engineer
Red Hat, Inc. +1-919-301-3226
Virtualization: qemu.org | libvirt.org
© 2016 - 2026 Red Hat, Inc.