Il 20/11/2012 16:51, Stefan Hajnoczi ha scritto:
> Poalo: Could be
> done when merging the patch?
>
> Reviewed-by: Stefan Hajnoczi
Yes. Applying this to scsi-next branch.
Paolo
On Mon, Nov 19, 2012 at 03:58:31PM +0100, Peter Lieven wrote:
> libiscsi expects all write16 data in a linear buffer. If the
> iovec only contains one buffer we can skip the linearization
> step as well as the additional malloc/free and pass the
> buffer directly.
>
> Reported-by: Ronnie Sahlberg
On Mon, Nov 19, 2012 at 7:18 AM, Paolo Bonzini wrote:
> Il 19/11/2012 15:58, Peter Lieven ha scritto:
>>
>> -/* XXX we should pass the iovec to write16 to avoid the extra copy */
>> -/* this will allow us to get rid of 'buf' completely */
>> size = nb_sectors * BDRV_SECTOR_SIZE;
>> -
Am 19.11.2012 um 16:18 schrieb Paolo Bonzini :
> Il 19/11/2012 15:58, Peter Lieven ha scritto:
>>
>> -/* XXX we should pass the iovec to write16 to avoid the extra copy */
>> -/* this will allow us to get rid of 'buf' completely */
>> size = nb_sectors * BDRV_SECTOR_SIZE;
>> -acb
Il 19/11/2012 15:58, Peter Lieven ha scritto:
>
> -/* XXX we should pass the iovec to write16 to avoid the extra copy */
> -/* this will allow us to get rid of 'buf' completely */
> size = nb_sectors * BDRV_SECTOR_SIZE;
> -acb->buf = g_malloc(size);
> -qemu_iovec_to_buf(acb->q
libiscsi expects all write16 data in a linear buffer. If the
iovec only contains one buffer we can skip the linearization
step as well as the additional malloc/free and pass the
buffer directly.
Reported-by: Ronnie Sahlberg
Signed-off-by: Peter Lieven
---
block/iscsi.c | 24 +++--
