block/block-backend.c | 6 ++++++ block/file-posix.c | 2 +- block/io.c | 1 + hw/scsi/scsi-generic.c | 2 +- include/block/block_int.h | 7 +++++++ include/sysemu/block-backend.h | 1 + 6 files changed, 17 insertions(+), 2 deletions(-)
Linux limits the size of iovecs to 1024 (UIO_MAXIOV in the kernel
sources, IOV_MAX in POSIX). Because of this, on some host adapters
requests with many iovecs are rejected with -EINVAL by the
io_submit() or readv()/writev() system calls.
In fact, the same limit applies to SG_IO as well. To fix both the
EINVAL and the possible performance issues from using fewer iovecs
than allowed by Linux (some HBAs have max_segments as low as 128),
introduce a separate entry in BlockLimits to hold the max_segments
value from sysfs. This new limit is used only for SG_IO and clamped
to bs->bl.max_iov anyway, just like max_hw_transfer is clamped to
bs->bl.max_transfer.
Reported-by: Halil Pasic <pasic@linux.ibm.com>
Cc: Hanna Reitz <hreitz@redhat.com>
Cc: Kevin Wolf <kwolf@redhat.com>
Cc: qemu-block@nongnu.org
Fixes: 18473467d5 ("file-posix: try BLKSECTGET on block devices too, do not round to power of 2", 2021-06-25)
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
block/block-backend.c | 6 ++++++
block/file-posix.c | 2 +-
block/io.c | 1 +
hw/scsi/scsi-generic.c | 2 +-
include/block/block_int.h | 7 +++++++
include/sysemu/block-backend.h | 1 +
6 files changed, 17 insertions(+), 2 deletions(-)
diff --git a/block/block-backend.c b/block/block-backend.c
index 6140d133e2..ba2b5ebb10 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -1986,6 +1986,12 @@ uint32_t blk_get_max_transfer(BlockBackend *blk)
return ROUND_DOWN(max, blk_get_request_alignment(blk));
}
+int blk_get_max_hw_iov(BlockBackend *blk)
+{
+ return MIN_NON_ZERO(blk->root->bs->bl.max_hw_iov,
+ blk->root->bs->bl.max_iov);
+}
+
int blk_get_max_iov(BlockBackend *blk)
{
return blk->root->bs->bl.max_iov;
diff --git a/block/file-posix.c b/block/file-posix.c
index cb9bffe047..1567edb3d5 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -1273,7 +1273,7 @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp)
ret = hdev_get_max_segments(s->fd, &st);
if (ret > 0) {
- bs->bl.max_iov = ret;
+ bs->bl.max_hw_iov = ret;
}
}
}
diff --git a/block/io.c b/block/io.c
index a19942718b..f38e7f81d8 100644
--- a/block/io.c
+++ b/block/io.c
@@ -136,6 +136,7 @@ static void bdrv_merge_limits(BlockLimits *dst, const BlockLimits *src)
dst->min_mem_alignment = MAX(dst->min_mem_alignment,
src->min_mem_alignment);
dst->max_iov = MIN_NON_ZERO(dst->max_iov, src->max_iov);
+ dst->max_hw_iov = MIN_NON_ZERO(dst->max_hw_iov, src->max_hw_iov);
}
typedef struct BdrvRefreshLimitsState {
diff --git a/hw/scsi/scsi-generic.c b/hw/scsi/scsi-generic.c
index 665baf900e..0306ccc7b1 100644
--- a/hw/scsi/scsi-generic.c
+++ b/hw/scsi/scsi-generic.c
@@ -180,7 +180,7 @@ static int scsi_handle_inquiry_reply(SCSIGenericReq *r, SCSIDevice *s, int len)
page = r->req.cmd.buf[2];
if (page == 0xb0) {
uint64_t max_transfer = blk_get_max_hw_transfer(s->conf.blk);
- uint32_t max_iov = blk_get_max_iov(s->conf.blk);
+ uint32_t max_iov = blk_get_max_hw_iov(s->conf.blk);
assert(max_transfer);
max_transfer = MIN_NON_ZERO(max_transfer, max_iov * qemu_real_host_page_size)
diff --git a/include/block/block_int.h b/include/block/block_int.h
index f1a54db0f8..c31cbd034a 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -702,6 +702,13 @@ typedef struct BlockLimits {
*/
uint64_t max_hw_transfer;
+ /* Maximal number of scatter/gather elements allowed by the hardware.
+ * Applies whenever transfers to the device bypass the kernel I/O
+ * scheduler, for example with SG_IO. If larger than max_iov
+ * or if zero, blk_get_max_hw_iov will fall back to max_iov.
+ */
+ int max_hw_iov;
+
/* memory alignment, in bytes so that no bounce buffer is needed */
size_t min_mem_alignment;
diff --git a/include/sysemu/block-backend.h b/include/sysemu/block-backend.h
index 29d4fdbf63..82bae55161 100644
--- a/include/sysemu/block-backend.h
+++ b/include/sysemu/block-backend.h
@@ -211,6 +211,7 @@ uint32_t blk_get_request_alignment(BlockBackend *blk);
uint32_t blk_get_max_transfer(BlockBackend *blk);
uint64_t blk_get_max_hw_transfer(BlockBackend *blk);
int blk_get_max_iov(BlockBackend *blk);
+int blk_get_max_hw_iov(BlockBackend *blk);
void blk_set_guest_block_size(BlockBackend *blk, int align);
void *blk_try_blockalign(BlockBackend *blk, size_t size);
void *blk_blockalign(BlockBackend *blk, size_t size);
--
2.27.0
On Thu, 23 Sep 2021 09:04:36 -0400
Paolo Bonzini <pbonzini@redhat.com> wrote:
> Linux limits the size of iovecs to 1024 (UIO_MAXIOV in the kernel
> sources, IOV_MAX in POSIX). Because of this, on some host adapters
> requests with many iovecs are rejected with -EINVAL by the
> io_submit() or readv()/writev() system calls.
>
> In fact, the same limit applies to SG_IO as well. To fix both the
> EINVAL and the possible performance issues from using fewer iovecs
> than allowed by Linux (some HBAs have max_segments as low as 128),
> introduce a separate entry in BlockLimits to hold the max_segments
> value from sysfs. This new limit is used only for SG_IO and clamped
> to bs->bl.max_iov anyway, just like max_hw_transfer is clamped to
> bs->bl.max_transfer.
Doesn't this patch render bs->bl.max_iov a constant?
$ git grep -p -e 'bl\(.\|->\)max_iov'
block/block-backend.c=int blk_get_max_iov(BlockBackend *blk)
block/block-backend.c: return blk->root->bs->bl.max_iov;
block/file-posix.c=static void raw_refresh_limits(BlockDriverState *bs, Error **errp)
block/file-posix.c: bs->bl.max_iov = ret;
block/io.c=void bdrv_refresh_limits(BlockDriverState *bs, Transaction *tran, Error **errp)
block/io.c: bs->bl.max_iov = IOV_MAX;
block/mirror.c=static int coroutine_fn mirror_run(Job *job, Error **errp)
block/mirror.c: s->max_iov = MIN(bs->bl.max_iov, target_bs->bl.max_iov);
Can't we use some of the established constants instead of hard coding a
qemu specific IOV_MAX?
POSIX.1 seems to guarantee the availability of IOV_MAX in <limits.h>
according to: https://man7.org/linux/man-pages/man2/readv.2.html
and <sys/uio.h> may have UIO_MAXIOV defined.
>
> Reported-by: Halil Pasic <pasic@linux.ibm.com>
> Cc: Hanna Reitz <hreitz@redhat.com>
> Cc: Kevin Wolf <kwolf@redhat.com>
> Cc: qemu-block@nongnu.org
> Fixes: 18473467d5 ("file-posix: try BLKSECTGET on block devices too, do not round to power of 2", 2021-06-25)
> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
> ---
> block/block-backend.c | 6 ++++++
> block/file-posix.c | 2 +-
> block/io.c | 1 +
> hw/scsi/scsi-generic.c | 2 +-
> include/block/block_int.h | 7 +++++++
> include/sysemu/block-backend.h | 1 +
> 6 files changed, 17 insertions(+), 2 deletions(-)
>
> diff --git a/block/block-backend.c b/block/block-backend.c
> index 6140d133e2..ba2b5ebb10 100644
> --- a/block/block-backend.c
> +++ b/block/block-backend.c
> @@ -1986,6 +1986,12 @@ uint32_t blk_get_max_transfer(BlockBackend *blk)
> return ROUND_DOWN(max, blk_get_request_alignment(blk));
> }
>
> +int blk_get_max_hw_iov(BlockBackend *blk)
> +{
> + return MIN_NON_ZERO(blk->root->bs->bl.max_hw_iov,
> + blk->root->bs->bl.max_iov);
> +}
> +
> int blk_get_max_iov(BlockBackend *blk)
> {
> return blk->root->bs->bl.max_iov;
> diff --git a/block/file-posix.c b/block/file-posix.c
> index cb9bffe047..1567edb3d5 100644
> --- a/block/file-posix.c
> +++ b/block/file-posix.c
> @@ -1273,7 +1273,7 @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp)
>
> ret = hdev_get_max_segments(s->fd, &st);
> if (ret > 0) {
> - bs->bl.max_iov = ret;
> + bs->bl.max_hw_iov = ret;
> }
> }
> }
> diff --git a/block/io.c b/block/io.c
> index a19942718b..f38e7f81d8 100644
> --- a/block/io.c
> +++ b/block/io.c
> @@ -136,6 +136,7 @@ static void bdrv_merge_limits(BlockLimits *dst, const BlockLimits *src)
> dst->min_mem_alignment = MAX(dst->min_mem_alignment,
> src->min_mem_alignment);
> dst->max_iov = MIN_NON_ZERO(dst->max_iov, src->max_iov);
> + dst->max_hw_iov = MIN_NON_ZERO(dst->max_hw_iov, src->max_hw_iov);
> }
>
> typedef struct BdrvRefreshLimitsState {
> diff --git a/hw/scsi/scsi-generic.c b/hw/scsi/scsi-generic.c
> index 665baf900e..0306ccc7b1 100644
> --- a/hw/scsi/scsi-generic.c
> +++ b/hw/scsi/scsi-generic.c
> @@ -180,7 +180,7 @@ static int scsi_handle_inquiry_reply(SCSIGenericReq *r, SCSIDevice *s, int len)
> page = r->req.cmd.buf[2];
> if (page == 0xb0) {
> uint64_t max_transfer = blk_get_max_hw_transfer(s->conf.blk);
> - uint32_t max_iov = blk_get_max_iov(s->conf.blk);
> + uint32_t max_iov = blk_get_max_hw_iov(s->conf.blk);
>
> assert(max_transfer);
> max_transfer = MIN_NON_ZERO(max_transfer, max_iov * qemu_real_host_page_size)
> diff --git a/include/block/block_int.h b/include/block/block_int.h
> index f1a54db0f8..c31cbd034a 100644
> --- a/include/block/block_int.h
> +++ b/include/block/block_int.h
> @@ -702,6 +702,13 @@ typedef struct BlockLimits {
> */
> uint64_t max_hw_transfer;
>
> + /* Maximal number of scatter/gather elements allowed by the hardware.
> + * Applies whenever transfers to the device bypass the kernel I/O
> + * scheduler, for example with SG_IO. If larger than max_iov
> + * or if zero, blk_get_max_hw_iov will fall back to max_iov.
> + */
> + int max_hw_iov;
> +
> /* memory alignment, in bytes so that no bounce buffer is needed */
> size_t min_mem_alignment;
>
> diff --git a/include/sysemu/block-backend.h b/include/sysemu/block-backend.h
> index 29d4fdbf63..82bae55161 100644
> --- a/include/sysemu/block-backend.h
> +++ b/include/sysemu/block-backend.h
> @@ -211,6 +211,7 @@ uint32_t blk_get_request_alignment(BlockBackend *blk);
> uint32_t blk_get_max_transfer(BlockBackend *blk);
> uint64_t blk_get_max_hw_transfer(BlockBackend *blk);
> int blk_get_max_iov(BlockBackend *blk);
> +int blk_get_max_hw_iov(BlockBackend *blk);
> void blk_set_guest_block_size(BlockBackend *blk, int align);
> void *blk_try_blockalign(BlockBackend *blk, size_t size);
> void *blk_blockalign(BlockBackend *blk, size_t size);
On Thu, 23 Sep 2021 16:28:11 +0200 Halil Pasic <pasic@linux.ibm.com> wrote: > Can't we use some of the established constants instead of hard coding a > qemu specific IOV_MAX? > > POSIX.1 seems to guarantee the availability of IOV_MAX in <limits.h> > according to: https://man7.org/linux/man-pages/man2/readv.2.html > and <sys/uio.h> may have UIO_MAXIOV defined. Never mind, the #define IOV_MAX 1024 in osdep.h is conditional and I guess we already use IOV_MAX from limit when CONFIG_IOVEC is defined, i.e. when we don't emulate the interface. Sorry for the noise. Regards, Halil
Am 23.09.21 um 15:04 schrieb Paolo Bonzini:
> Linux limits the size of iovecs to 1024 (UIO_MAXIOV in the kernel
> sources, IOV_MAX in POSIX). Because of this, on some host adapters
> requests with many iovecs are rejected with -EINVAL by the
> io_submit() or readv()/writev() system calls.
>
> In fact, the same limit applies to SG_IO as well. To fix both the
> EINVAL and the possible performance issues from using fewer iovecs
> than allowed by Linux (some HBAs have max_segments as low as 128),
> introduce a separate entry in BlockLimits to hold the max_segments
> value from sysfs. This new limit is used only for SG_IO and clamped
> to bs->bl.max_iov anyway, just like max_hw_transfer is clamped to
> bs->bl.max_transfer.
>
> Reported-by: Halil Pasic <pasic@linux.ibm.com>
> Cc: Hanna Reitz <hreitz@redhat.com>
> Cc: Kevin Wolf <kwolf@redhat.com>
> Cc: qemu-block@nongnu.org
> Fixes: 18473467d5 ("file-posix: try BLKSECTGET on block devices too, do not round to power of 2", 2021-06-25)
This sneaked in shortly before the 6.1 release (between rc0 and rc1 I think).
Shouldnt that go to stable in cass this still exist?
> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
> ---
> block/block-backend.c | 6 ++++++
> block/file-posix.c | 2 +-
> block/io.c | 1 +
> hw/scsi/scsi-generic.c | 2 +-
> include/block/block_int.h | 7 +++++++
> include/sysemu/block-backend.h | 1 +
> 6 files changed, 17 insertions(+), 2 deletions(-)
>
> diff --git a/block/block-backend.c b/block/block-backend.c
> index 6140d133e2..ba2b5ebb10 100644
> --- a/block/block-backend.c
> +++ b/block/block-backend.c
> @@ -1986,6 +1986,12 @@ uint32_t blk_get_max_transfer(BlockBackend *blk)
> return ROUND_DOWN(max, blk_get_request_alignment(blk));
> }
>
> +int blk_get_max_hw_iov(BlockBackend *blk)
> +{
> + return MIN_NON_ZERO(blk->root->bs->bl.max_hw_iov,
> + blk->root->bs->bl.max_iov);
> +}
> +
> int blk_get_max_iov(BlockBackend *blk)
> {
> return blk->root->bs->bl.max_iov;
> diff --git a/block/file-posix.c b/block/file-posix.c
> index cb9bffe047..1567edb3d5 100644
> --- a/block/file-posix.c
> +++ b/block/file-posix.c
> @@ -1273,7 +1273,7 @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp)
>
> ret = hdev_get_max_segments(s->fd, &st);
> if (ret > 0) {
> - bs->bl.max_iov = ret;
> + bs->bl.max_hw_iov = ret;
> }
> }
> }
> diff --git a/block/io.c b/block/io.c
> index a19942718b..f38e7f81d8 100644
> --- a/block/io.c
> +++ b/block/io.c
> @@ -136,6 +136,7 @@ static void bdrv_merge_limits(BlockLimits *dst, const BlockLimits *src)
> dst->min_mem_alignment = MAX(dst->min_mem_alignment,
> src->min_mem_alignment);
> dst->max_iov = MIN_NON_ZERO(dst->max_iov, src->max_iov);
> + dst->max_hw_iov = MIN_NON_ZERO(dst->max_hw_iov, src->max_hw_iov);
> }
>
> typedef struct BdrvRefreshLimitsState {
> diff --git a/hw/scsi/scsi-generic.c b/hw/scsi/scsi-generic.c
> index 665baf900e..0306ccc7b1 100644
> --- a/hw/scsi/scsi-generic.c
> +++ b/hw/scsi/scsi-generic.c
> @@ -180,7 +180,7 @@ static int scsi_handle_inquiry_reply(SCSIGenericReq *r, SCSIDevice *s, int len)
> page = r->req.cmd.buf[2];
> if (page == 0xb0) {
> uint64_t max_transfer = blk_get_max_hw_transfer(s->conf.blk);
> - uint32_t max_iov = blk_get_max_iov(s->conf.blk);
> + uint32_t max_iov = blk_get_max_hw_iov(s->conf.blk);
>
> assert(max_transfer);
> max_transfer = MIN_NON_ZERO(max_transfer, max_iov * qemu_real_host_page_size)
> diff --git a/include/block/block_int.h b/include/block/block_int.h
> index f1a54db0f8..c31cbd034a 100644
> --- a/include/block/block_int.h
> +++ b/include/block/block_int.h
> @@ -702,6 +702,13 @@ typedef struct BlockLimits {
> */
> uint64_t max_hw_transfer;
>
> + /* Maximal number of scatter/gather elements allowed by the hardware.
> + * Applies whenever transfers to the device bypass the kernel I/O
> + * scheduler, for example with SG_IO. If larger than max_iov
> + * or if zero, blk_get_max_hw_iov will fall back to max_iov.
> + */
> + int max_hw_iov;
> +
> /* memory alignment, in bytes so that no bounce buffer is needed */
> size_t min_mem_alignment;
>
> diff --git a/include/sysemu/block-backend.h b/include/sysemu/block-backend.h
> index 29d4fdbf63..82bae55161 100644
> --- a/include/sysemu/block-backend.h
> +++ b/include/sysemu/block-backend.h
> @@ -211,6 +211,7 @@ uint32_t blk_get_request_alignment(BlockBackend *blk);
> uint32_t blk_get_max_transfer(BlockBackend *blk);
> uint64_t blk_get_max_hw_transfer(BlockBackend *blk);
> int blk_get_max_iov(BlockBackend *blk);
> +int blk_get_max_hw_iov(BlockBackend *blk);
> void blk_set_guest_block_size(BlockBackend *blk, int align);
> void *blk_try_blockalign(BlockBackend *blk, size_t size);
> void *blk_blockalign(BlockBackend *blk, size_t size);
>
Yes, the question is whether it still exists...
Paolo
El jue., 23 sept. 2021 16:48, Christian Borntraeger <borntraeger@de.ibm.com>
escribió:
>
>
> Am 23.09.21 um 15:04 schrieb Paolo Bonzini:
> > Linux limits the size of iovecs to 1024 (UIO_MAXIOV in the kernel
> > sources, IOV_MAX in POSIX). Because of this, on some host adapters
> > requests with many iovecs are rejected with -EINVAL by the
> > io_submit() or readv()/writev() system calls.
> >
> > In fact, the same limit applies to SG_IO as well. To fix both the
> > EINVAL and the possible performance issues from using fewer iovecs
> > than allowed by Linux (some HBAs have max_segments as low as 128),
> > introduce a separate entry in BlockLimits to hold the max_segments
> > value from sysfs. This new limit is used only for SG_IO and clamped
> > to bs->bl.max_iov anyway, just like max_hw_transfer is clamped to
> > bs->bl.max_transfer.
> >
> > Reported-by: Halil Pasic <pasic@linux.ibm.com>
> > Cc: Hanna Reitz <hreitz@redhat.com>
> > Cc: Kevin Wolf <kwolf@redhat.com>
> > Cc: qemu-block@nongnu.org
> > Fixes: 18473467d5 ("file-posix: try BLKSECTGET on block devices too, do
> not round to power of 2", 2021-06-25)
>
> This sneaked in shortly before the 6.1 release (between rc0 and rc1 I
> think).
> Shouldnt that go to stable in cass this still exist?
>
>
> > Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
> > ---
> > block/block-backend.c | 6 ++++++
> > block/file-posix.c | 2 +-
> > block/io.c | 1 +
> > hw/scsi/scsi-generic.c | 2 +-
> > include/block/block_int.h | 7 +++++++
> > include/sysemu/block-backend.h | 1 +
> > 6 files changed, 17 insertions(+), 2 deletions(-)
> >
> > diff --git a/block/block-backend.c b/block/block-backend.c
> > index 6140d133e2..ba2b5ebb10 100644
> > --- a/block/block-backend.c
> > +++ b/block/block-backend.c
> > @@ -1986,6 +1986,12 @@ uint32_t blk_get_max_transfer(BlockBackend *blk)
> > return ROUND_DOWN(max, blk_get_request_alignment(blk));
> > }
> >
> > +int blk_get_max_hw_iov(BlockBackend *blk)
> > +{
> > + return MIN_NON_ZERO(blk->root->bs->bl.max_hw_iov,
> > + blk->root->bs->bl.max_iov);
> > +}
> > +
> > int blk_get_max_iov(BlockBackend *blk)
> > {
> > return blk->root->bs->bl.max_iov;
> > diff --git a/block/file-posix.c b/block/file-posix.c
> > index cb9bffe047..1567edb3d5 100644
> > --- a/block/file-posix.c
> > +++ b/block/file-posix.c
> > @@ -1273,7 +1273,7 @@ static void raw_refresh_limits(BlockDriverState
> *bs, Error **errp)
> >
> > ret = hdev_get_max_segments(s->fd, &st);
> > if (ret > 0) {
> > - bs->bl.max_iov = ret;
> > + bs->bl.max_hw_iov = ret;
> > }
> > }
> > }
> > diff --git a/block/io.c b/block/io.c
> > index a19942718b..f38e7f81d8 100644
> > --- a/block/io.c
> > +++ b/block/io.c
> > @@ -136,6 +136,7 @@ static void bdrv_merge_limits(BlockLimits *dst,
> const BlockLimits *src)
> > dst->min_mem_alignment = MAX(dst->min_mem_alignment,
> > src->min_mem_alignment);
> > dst->max_iov = MIN_NON_ZERO(dst->max_iov, src->max_iov);
> > + dst->max_hw_iov = MIN_NON_ZERO(dst->max_hw_iov, src->max_hw_iov);
> > }
> >
> > typedef struct BdrvRefreshLimitsState {
> > diff --git a/hw/scsi/scsi-generic.c b/hw/scsi/scsi-generic.c
> > index 665baf900e..0306ccc7b1 100644
> > --- a/hw/scsi/scsi-generic.c
> > +++ b/hw/scsi/scsi-generic.c
> > @@ -180,7 +180,7 @@ static int scsi_handle_inquiry_reply(SCSIGenericReq
> *r, SCSIDevice *s, int len)
> > page = r->req.cmd.buf[2];
> > if (page == 0xb0) {
> > uint64_t max_transfer =
> blk_get_max_hw_transfer(s->conf.blk);
> > - uint32_t max_iov = blk_get_max_iov(s->conf.blk);
> > + uint32_t max_iov = blk_get_max_hw_iov(s->conf.blk);
> >
> > assert(max_transfer);
> > max_transfer = MIN_NON_ZERO(max_transfer, max_iov *
> qemu_real_host_page_size)
> > diff --git a/include/block/block_int.h b/include/block/block_int.h
> > index f1a54db0f8..c31cbd034a 100644
> > --- a/include/block/block_int.h
> > +++ b/include/block/block_int.h
> > @@ -702,6 +702,13 @@ typedef struct BlockLimits {
> > */
> > uint64_t max_hw_transfer;
> >
> > + /* Maximal number of scatter/gather elements allowed by the
> hardware.
> > + * Applies whenever transfers to the device bypass the kernel I/O
> > + * scheduler, for example with SG_IO. If larger than max_iov
> > + * or if zero, blk_get_max_hw_iov will fall back to max_iov.
> > + */
> > + int max_hw_iov;
> > +
> > /* memory alignment, in bytes so that no bounce buffer is needed */
> > size_t min_mem_alignment;
> >
> > diff --git a/include/sysemu/block-backend.h
> b/include/sysemu/block-backend.h
> > index 29d4fdbf63..82bae55161 100644
> > --- a/include/sysemu/block-backend.h
> > +++ b/include/sysemu/block-backend.h
> > @@ -211,6 +211,7 @@ uint32_t blk_get_request_alignment(BlockBackend
> *blk);
> > uint32_t blk_get_max_transfer(BlockBackend *blk);
> > uint64_t blk_get_max_hw_transfer(BlockBackend *blk);
> > int blk_get_max_iov(BlockBackend *blk);
> > +int blk_get_max_hw_iov(BlockBackend *blk);
> > void blk_set_guest_block_size(BlockBackend *blk, int align);
> > void *blk_try_blockalign(BlockBackend *blk, size_t size);
> > void *blk_blockalign(BlockBackend *blk, size_t size);
> >
>
>
Peter, Michael,
do we still do stable releases for QEMU or has this stopped?
Am 24.09.21 um 07:27 schrieb Paolo Bonzini:
> Yes, the question is whether it still exists... Paolo El jue., 23 sept. 2021 16:48, Christian Borntraeger <borntraeger@de.ibm.com> escribió: Am 23.09.21 um 15:04 schrieb Paolo Bonzini: > Linux limits the size of iovecs to 1024 (UIO_MAXIOV ZjQcmQRYFpfptBannerStart
> This Message Is From an External Sender
> This message came from outside your organization.
> ZjQcmQRYFpfptBannerEnd
> Yes, the question is whether it still exists...
>
> Paolo
>
> El jue., 23 sept. 2021 16:48, Christian Borntraeger <borntraeger@de.ibm.com <mailto:borntraeger@de.ibm.com>> escribió:
>
>
>
> Am 23.09.21 um 15:04 schrieb Paolo Bonzini:
> > Linux limits the size of iovecs to 1024 (UIO_MAXIOV in the kernel
> > sources, IOV_MAX in POSIX). Because of this, on some host adapters
> > requests with many iovecs are rejected with -EINVAL by the
> > io_submit() or readv()/writev() system calls.
> >
> > In fact, the same limit applies to SG_IO as well. To fix both the
> > EINVAL and the possible performance issues from using fewer iovecs
> > than allowed by Linux (some HBAs have max_segments as low as 128),
> > introduce a separate entry in BlockLimits to hold the max_segments
> > value from sysfs. This new limit is used only for SG_IO and clamped
> > to bs->bl.max_iov anyway, just like max_hw_transfer is clamped to
> > bs->bl.max_transfer.
> >
> > Reported-by: Halil Pasic <pasic@linux.ibm.com <mailto:pasic@linux.ibm.com>>
> > Cc: Hanna Reitz <hreitz@redhat.com <mailto:hreitz@redhat.com>>
> > Cc: Kevin Wolf <kwolf@redhat.com <mailto:kwolf@redhat.com>>
> > Cc: qemu-block@nongnu.org <mailto:qemu-block@nongnu.org>
> > Fixes: 18473467d5 ("file-posix: try BLKSECTGET on block devices too, do not round to power of 2", 2021-06-25)
>
> This sneaked in shortly before the 6.1 release (between rc0 and rc1 I think).
> Shouldnt that go to stable in cass this still exist?
>
>
> > Signed-off-by: Paolo Bonzini <pbonzini@redhat.com <mailto:pbonzini@redhat.com>>
> > ---
> > block/block-backend.c | 6 ++++++
> > block/file-posix.c | 2 +-
> > block/io.c | 1 +
> > hw/scsi/scsi-generic.c | 2 +-
> > include/block/block_int.h | 7 +++++++
> > include/sysemu/block-backend.h | 1 +
> > 6 files changed, 17 insertions(+), 2 deletions(-)
> >
> > diff --git a/block/block-backend.c b/block/block-backend.c
> > index 6140d133e2..ba2b5ebb10 100644
> > --- a/block/block-backend.c
> > +++ b/block/block-backend.c
> > @@ -1986,6 +1986,12 @@ uint32_t blk_get_max_transfer(BlockBackend *blk)
> > return ROUND_DOWN(max, blk_get_request_alignment(blk));
> > }
> >
> > +int blk_get_max_hw_iov(BlockBackend *blk)
> > +{
> > + return MIN_NON_ZERO(blk->root->bs->bl.max_hw_iov,
> > + blk->root->bs->bl.max_iov);
> > +}
> > +
> > int blk_get_max_iov(BlockBackend *blk)
> > {
> > return blk->root->bs->bl.max_iov;
> > diff --git a/block/file-posix.c b/block/file-posix.c
> > index cb9bffe047..1567edb3d5 100644
> > --- a/block/file-posix.c
> > +++ b/block/file-posix.c
> > @@ -1273,7 +1273,7 @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp)
> >
> > ret = hdev_get_max_segments(s->fd, &st);
> > if (ret > 0) {
> > - bs->bl.max_iov = ret;
> > + bs->bl.max_hw_iov = ret;
> > }
> > }
> > }
> > diff --git a/block/io.c b/block/io.c
> > index a19942718b..f38e7f81d8 100644
> > --- a/block/io.c
> > +++ b/block/io.c
> > @@ -136,6 +136,7 @@ static void bdrv_merge_limits(BlockLimits *dst, const BlockLimits *src)
> > dst->min_mem_alignment = MAX(dst->min_mem_alignment,
> > src->min_mem_alignment);
> > dst->max_iov = MIN_NON_ZERO(dst->max_iov, src->max_iov);
> > + dst->max_hw_iov = MIN_NON_ZERO(dst->max_hw_iov, src->max_hw_iov);
> > }
> >
> > typedef struct BdrvRefreshLimitsState {
> > diff --git a/hw/scsi/scsi-generic.c b/hw/scsi/scsi-generic.c
> > index 665baf900e..0306ccc7b1 100644
> > --- a/hw/scsi/scsi-generic.c
> > +++ b/hw/scsi/scsi-generic.c
> > @@ -180,7 +180,7 @@ static int scsi_handle_inquiry_reply(SCSIGenericReq *r, SCSIDevice *s, int len)
> > page = r->req.cmd.buf[2];
> > if (page == 0xb0) {
> > uint64_t max_transfer = blk_get_max_hw_transfer(s->conf.blk);
> > - uint32_t max_iov = blk_get_max_iov(s->conf.blk);
> > + uint32_t max_iov = blk_get_max_hw_iov(s->conf.blk);
> >
> > assert(max_transfer);
> > max_transfer = MIN_NON_ZERO(max_transfer, max_iov * qemu_real_host_page_size)
> > diff --git a/include/block/block_int.h b/include/block/block_int.h
> > index f1a54db0f8..c31cbd034a 100644
> > --- a/include/block/block_int.h
> > +++ b/include/block/block_int.h
> > @@ -702,6 +702,13 @@ typedef struct BlockLimits {
> > */
> > uint64_t max_hw_transfer;
> >
> > + /* Maximal number of scatter/gather elements allowed by the hardware.
> > + * Applies whenever transfers to the device bypass the kernel I/O
> > + * scheduler, for example with SG_IO. If larger than max_iov
> > + * or if zero, blk_get_max_hw_iov will fall back to max_iov.
> > + */
> > + int max_hw_iov;
> > +
> > /* memory alignment, in bytes so that no bounce buffer is needed */
> > size_t min_mem_alignment;
> >
> > diff --git a/include/sysemu/block-backend.h b/include/sysemu/block-backend.h
> > index 29d4fdbf63..82bae55161 100644
> > --- a/include/sysemu/block-backend.h
> > +++ b/include/sysemu/block-backend.h
> > @@ -211,6 +211,7 @@ uint32_t blk_get_request_alignment(BlockBackend *blk);
> > uint32_t blk_get_max_transfer(BlockBackend *blk);
> > uint64_t blk_get_max_hw_transfer(BlockBackend *blk);
> > int blk_get_max_iov(BlockBackend *blk);
> > +int blk_get_max_hw_iov(BlockBackend *blk);
> > void blk_set_guest_block_size(BlockBackend *blk, int align);
> > void *blk_try_blockalign(BlockBackend *blk, size_t size);
> > void *blk_blockalign(BlockBackend *blk, size_t size);
> >
>
On Fri, Sep 24, 2021 at 08:50:05AM +0200, Christian Borntraeger wrote:
> Peter, Michael,
>
> do we still do stable releases for QEMU or has this stopped?
Hi Christian,
Yes, it's just been a perfect storm of job moves / bad timing / much-needed
testing rework. I plan to restart the stable releases starting with 6.0.1 and
6.1.1 shortly after. I'll get the release schedules posted on the release wiki
week.
Sorry for the delays on this.
-Mike
>
> Am 24.09.21 um 07:27 schrieb Paolo Bonzini:
> > Yes, the question is whether it still exists... Paolo El jue., 23 sept. 2021 16:48, Christian Borntraeger <borntraeger@de.ibm.com> escribió: Am 23.09.21 um 15:04 schrieb Paolo Bonzini: > Linux limits the size of iovecs to 1024 (UIO_MAXIOV ZjQcmQRYFpfptBannerStart
> > This Message Is From an External Sender
> > This message came from outside your organization.
> > ZjQcmQRYFpfptBannerEnd
> > Yes, the question is whether it still exists...
> >
> > Paolo
> >
> > El jue., 23 sept. 2021 16:48, Christian Borntraeger <borntraeger@de.ibm.com <mailto:borntraeger@de.ibm.com>> escribió:
> >
> >
> >
> > Am 23.09.21 um 15:04 schrieb Paolo Bonzini:
> > > Linux limits the size of iovecs to 1024 (UIO_MAXIOV in the kernel
> > > sources, IOV_MAX in POSIX). Because of this, on some host adapters
> > > requests with many iovecs are rejected with -EINVAL by the
> > > io_submit() or readv()/writev() system calls.
> > >
> > > In fact, the same limit applies to SG_IO as well. To fix both the
> > > EINVAL and the possible performance issues from using fewer iovecs
> > > than allowed by Linux (some HBAs have max_segments as low as 128),
> > > introduce a separate entry in BlockLimits to hold the max_segments
> > > value from sysfs. This new limit is used only for SG_IO and clamped
> > > to bs->bl.max_iov anyway, just like max_hw_transfer is clamped to
> > > bs->bl.max_transfer.
> > >
> > > Reported-by: Halil Pasic <pasic@linux.ibm.com <mailto:pasic@linux.ibm.com>>
> > > Cc: Hanna Reitz <hreitz@redhat.com <mailto:hreitz@redhat.com>>
> > > Cc: Kevin Wolf <kwolf@redhat.com <mailto:kwolf@redhat.com>>
> > > Cc: qemu-block@nongnu.org <mailto:qemu-block@nongnu.org>
> > > Fixes: 18473467d5 ("file-posix: try BLKSECTGET on block devices too, do not round to power of 2", 2021-06-25)
> >
> > This sneaked in shortly before the 6.1 release (between rc0 and rc1 I think).
> > Shouldnt that go to stable in cass this still exist?
> >
> >
> > > Signed-off-by: Paolo Bonzini <pbonzini@redhat.com <mailto:pbonzini@redhat.com>>
> > > ---
> > > block/block-backend.c | 6 ++++++
> > > block/file-posix.c | 2 +-
> > > block/io.c | 1 +
> > > hw/scsi/scsi-generic.c | 2 +-
> > > include/block/block_int.h | 7 +++++++
> > > include/sysemu/block-backend.h | 1 +
> > > 6 files changed, 17 insertions(+), 2 deletions(-)
> > >
> > > diff --git a/block/block-backend.c b/block/block-backend.c
> > > index 6140d133e2..ba2b5ebb10 100644
> > > --- a/block/block-backend.c
> > > +++ b/block/block-backend.c
> > > @@ -1986,6 +1986,12 @@ uint32_t blk_get_max_transfer(BlockBackend *blk)
> > > return ROUND_DOWN(max, blk_get_request_alignment(blk));
> > > }
> > >
> > > +int blk_get_max_hw_iov(BlockBackend *blk)
> > > +{
> > > + return MIN_NON_ZERO(blk->root->bs->bl.max_hw_iov,
> > > + blk->root->bs->bl.max_iov);
> > > +}
> > > +
> > > int blk_get_max_iov(BlockBackend *blk)
> > > {
> > > return blk->root->bs->bl.max_iov;
> > > diff --git a/block/file-posix.c b/block/file-posix.c
> > > index cb9bffe047..1567edb3d5 100644
> > > --- a/block/file-posix.c
> > > +++ b/block/file-posix.c
> > > @@ -1273,7 +1273,7 @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp)
> > >
> > > ret = hdev_get_max_segments(s->fd, &st);
> > > if (ret > 0) {
> > > - bs->bl.max_iov = ret;
> > > + bs->bl.max_hw_iov = ret;
> > > }
> > > }
> > > }
> > > diff --git a/block/io.c b/block/io.c
> > > index a19942718b..f38e7f81d8 100644
> > > --- a/block/io.c
> > > +++ b/block/io.c
> > > @@ -136,6 +136,7 @@ static void bdrv_merge_limits(BlockLimits *dst, const BlockLimits *src)
> > > dst->min_mem_alignment = MAX(dst->min_mem_alignment,
> > > src->min_mem_alignment);
> > > dst->max_iov = MIN_NON_ZERO(dst->max_iov, src->max_iov);
> > > + dst->max_hw_iov = MIN_NON_ZERO(dst->max_hw_iov, src->max_hw_iov);
> > > }
> > >
> > > typedef struct BdrvRefreshLimitsState {
> > > diff --git a/hw/scsi/scsi-generic.c b/hw/scsi/scsi-generic.c
> > > index 665baf900e..0306ccc7b1 100644
> > > --- a/hw/scsi/scsi-generic.c
> > > +++ b/hw/scsi/scsi-generic.c
> > > @@ -180,7 +180,7 @@ static int scsi_handle_inquiry_reply(SCSIGenericReq *r, SCSIDevice *s, int len)
> > > page = r->req.cmd.buf[2];
> > > if (page == 0xb0) {
> > > uint64_t max_transfer = blk_get_max_hw_transfer(s->conf.blk);
> > > - uint32_t max_iov = blk_get_max_iov(s->conf.blk);
> > > + uint32_t max_iov = blk_get_max_hw_iov(s->conf.blk);
> > >
> > > assert(max_transfer);
> > > max_transfer = MIN_NON_ZERO(max_transfer, max_iov * qemu_real_host_page_size)
> > > diff --git a/include/block/block_int.h b/include/block/block_int.h
> > > index f1a54db0f8..c31cbd034a 100644
> > > --- a/include/block/block_int.h
> > > +++ b/include/block/block_int.h
> > > @@ -702,6 +702,13 @@ typedef struct BlockLimits {
> > > */
> > > uint64_t max_hw_transfer;
> > >
> > > + /* Maximal number of scatter/gather elements allowed by the hardware.
> > > + * Applies whenever transfers to the device bypass the kernel I/O
> > > + * scheduler, for example with SG_IO. If larger than max_iov
> > > + * or if zero, blk_get_max_hw_iov will fall back to max_iov.
> > > + */
> > > + int max_hw_iov;
> > > +
> > > /* memory alignment, in bytes so that no bounce buffer is needed */
> > > size_t min_mem_alignment;
> > >
> > > diff --git a/include/sysemu/block-backend.h b/include/sysemu/block-backend.h
> > > index 29d4fdbf63..82bae55161 100644
> > > --- a/include/sysemu/block-backend.h
> > > +++ b/include/sysemu/block-backend.h
> > > @@ -211,6 +211,7 @@ uint32_t blk_get_request_alignment(BlockBackend *blk);
> > > uint32_t blk_get_max_transfer(BlockBackend *blk);
> > > uint64_t blk_get_max_hw_transfer(BlockBackend *blk);
> > > int blk_get_max_iov(BlockBackend *blk);
> > > +int blk_get_max_hw_iov(BlockBackend *blk);
> > > void blk_set_guest_block_size(BlockBackend *blk, int align);
> > > void *blk_try_blockalign(BlockBackend *blk, size_t size);
> > > void *blk_blockalign(BlockBackend *blk, size_t size);
> > >
> >
© 2016 - 2026 Red Hat, Inc.