[v9,5/7] config: add check to block layer

Putting zoned/non-zoned BlockDrivers on top of each other is not
allowed.

Signed-off-by: Sam Li <faithilikerun@gmail.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 block.c                          | 14 ++++++++++++++
 block/file-posix.c               | 14 ++++++++++++++
 block/raw-format.c               |  1 +
 include/block/block_int-common.h |  5 +++++
 4 files changed, 34 insertions(+)

On 2022/09/10 14:27, Sam Li wrote:
> Putting zoned/non-zoned BlockDrivers on top of each other is not
> allowed.
> 
> Signed-off-by: Sam Li <faithilikerun@gmail.com>
> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
> ---
>  block.c                          | 14 ++++++++++++++
>  block/file-posix.c               | 14 ++++++++++++++
>  block/raw-format.c               |  1 +
>  include/block/block_int-common.h |  5 +++++
>  4 files changed, 34 insertions(+)
> 
> diff --git a/block.c b/block.c
> index bc85f46eed..dad2ed3959 100644
> --- a/block.c
> +++ b/block.c
> @@ -7947,6 +7947,20 @@ void bdrv_add_child(BlockDriverState *parent_bs, BlockDriverState *child_bs,
>          return;
>      }
>  
> +    /*
> +     * Non-zoned block drivers do not follow zoned storage constraints
> +     * (i.e. sequential writes to zones). Refuse mixing zoned and non-zoned
> +     * drivers in a graph.
> +     */
> +    if (!parent_bs->drv->supports_zoned_children &&
> +        child_bs->bl.zoned == BLK_Z_HM) {

Shouldn't this be "child_bs->bl.zoned != BLK_Z_NONE" ?

> +        error_setg(errp, "Cannot add a %s child to a %s parent",
> +                   child_bs->bl.zoned == BLK_Z_HM ? "zoned" : "non-zoned",
> +                   parent_bs->drv->supports_zoned_children ?
> +                   "support zoned children" : "not support zoned children");
> +        return;
> +    }
> +
>      if (!QLIST_EMPTY(&child_bs->parents)) {
>          error_setg(errp, "The node %s already has a parent",
>                     child_bs->node_name);
> diff --git a/block/file-posix.c b/block/file-posix.c
> index 4edfa25d04..354de22860 100644
> --- a/block/file-posix.c
> +++ b/block/file-posix.c
> @@ -779,6 +779,20 @@ static int raw_open_common(BlockDriverState *bs, QDict *options,
>              goto fail;
>          }
>      }
> +#ifdef CONFIG_BLKZONED
> +    /*
> +     * The kernel page chache does not reliably work for writes to SWR zones
> +     * of zoned block device because it can not guarantee the order of writes.
> +     */
> +    if (strcmp(bs->drv->format_name, "zoned_host_device") == 0) {
> +        if (!(s->open_flags & O_DIRECT)) {
> +            error_setg(errp, "driver=zoned_host_device was specified, but it "
> +                             "requires cache.direct=on, which was not specified.");
> +            ret = -EINVAL;

This line is not needed. Simply "return -EINVAL;".

> +            return ret; /* No host kernel page cache */
> +        }
> +    }
> +#endif
>  
>      if (S_ISBLK(st.st_mode)) {
>  #ifdef BLKDISCARDZEROES
> diff --git a/block/raw-format.c b/block/raw-format.c
> index 6b20bd22ef..9441536819 100644
> --- a/block/raw-format.c
> +++ b/block/raw-format.c
> @@ -614,6 +614,7 @@ static void raw_child_perm(BlockDriverState *bs, BdrvChild *c,
>  BlockDriver bdrv_raw = {
>      .format_name          = "raw",
>      .instance_size        = sizeof(BDRVRawState),
> +    .supports_zoned_children = true,
>      .bdrv_probe           = &raw_probe,
>      .bdrv_reopen_prepare  = &raw_reopen_prepare,
>      .bdrv_reopen_commit   = &raw_reopen_commit,
> diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h
> index 078ddd7e67..043aa161a0 100644
> --- a/include/block/block_int-common.h
> +++ b/include/block/block_int-common.h
> @@ -127,6 +127,11 @@ struct BlockDriver {
>       */
>      bool is_format;
>  
> +    /*
> +     * Set to true if the BlockDriver supports zoned children.
> +     */
> +    bool supports_zoned_children;
> +
>      /*
>       * Drivers not implementing bdrv_parse_filename nor bdrv_open should have
>       * this field set to true, except ones that are defined only by their

Damien Le Moal <damien.lemoal@opensource.wdc.com> 于2022年9月11日周日 13:34写道：
>
> On 2022/09/10 14:27, Sam Li wrote:
> > Putting zoned/non-zoned BlockDrivers on top of each other is not
> > allowed.
> >
> > Signed-off-by: Sam Li <faithilikerun@gmail.com>
> > Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
> > ---
> >  block.c                          | 14 ++++++++++++++
> >  block/file-posix.c               | 14 ++++++++++++++
> >  block/raw-format.c               |  1 +
> >  include/block/block_int-common.h |  5 +++++
> >  4 files changed, 34 insertions(+)
> >
> > diff --git a/block.c b/block.c
> > index bc85f46eed..dad2ed3959 100644
> > --- a/block.c
> > +++ b/block.c
> > @@ -7947,6 +7947,20 @@ void bdrv_add_child(BlockDriverState *parent_bs, BlockDriverState *child_bs,
> >          return;
> >      }
> >
> > +    /*
> > +     * Non-zoned block drivers do not follow zoned storage constraints
> > +     * (i.e. sequential writes to zones). Refuse mixing zoned and non-zoned
> > +     * drivers in a graph.
> > +     */
> > +    if (!parent_bs->drv->supports_zoned_children &&
> > +        child_bs->bl.zoned == BLK_Z_HM) {
>
> Shouldn't this be "child_bs->bl.zoned != BLK_Z_NONE" ?

The host-aware model allows zoned storage constraints(sequentially
write) and random write. Is mixing HA and non-zoned drivers allowed?
What's the difference?

>
> > +        error_setg(errp, "Cannot add a %s child to a %s parent",
> > +                   child_bs->bl.zoned == BLK_Z_HM ? "zoned" : "non-zoned",
> > +                   parent_bs->drv->supports_zoned_children ?
> > +                   "support zoned children" : "not support zoned children");
> > +        return;
> > +    }
> > +
> >      if (!QLIST_EMPTY(&child_bs->parents)) {
> >          error_setg(errp, "The node %s already has a parent",
> >                     child_bs->node_name);
> > diff --git a/block/file-posix.c b/block/file-posix.c
> > index 4edfa25d04..354de22860 100644
> > --- a/block/file-posix.c
> > +++ b/block/file-posix.c
> > @@ -779,6 +779,20 @@ static int raw_open_common(BlockDriverState *bs, QDict *options,
> >              goto fail;
> >          }
> >      }
> > +#ifdef CONFIG_BLKZONED
> > +    /*
> > +     * The kernel page chache does not reliably work for writes to SWR zones
> > +     * of zoned block device because it can not guarantee the order of writes.
> > +     */
> > +    if (strcmp(bs->drv->format_name, "zoned_host_device") == 0) {
> > +        if (!(s->open_flags & O_DIRECT)) {
> > +            error_setg(errp, "driver=zoned_host_device was specified, but it "
> > +                             "requires cache.direct=on, which was not specified.");
> > +            ret = -EINVAL;
>
> This line is not needed. Simply "return -EINVAL;".
>
> > +            return ret; /* No host kernel page cache */
> > +        }
> > +    }
> > +#endif
> >
> >      if (S_ISBLK(st.st_mode)) {
> >  #ifdef BLKDISCARDZEROES
> > diff --git a/block/raw-format.c b/block/raw-format.c
> > index 6b20bd22ef..9441536819 100644
> > --- a/block/raw-format.c
> > +++ b/block/raw-format.c
> > @@ -614,6 +614,7 @@ static void raw_child_perm(BlockDriverState *bs, BdrvChild *c,
> >  BlockDriver bdrv_raw = {
> >      .format_name          = "raw",
> >      .instance_size        = sizeof(BDRVRawState),
> > +    .supports_zoned_children = true,
> >      .bdrv_probe           = &raw_probe,
> >      .bdrv_reopen_prepare  = &raw_reopen_prepare,
> >      .bdrv_reopen_commit   = &raw_reopen_commit,
> > diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h
> > index 078ddd7e67..043aa161a0 100644
> > --- a/include/block/block_int-common.h
> > +++ b/include/block/block_int-common.h
> > @@ -127,6 +127,11 @@ struct BlockDriver {
> >       */
> >      bool is_format;
> >
> > +    /*
> > +     * Set to true if the BlockDriver supports zoned children.
> > +     */
> > +    bool supports_zoned_children;
> > +
> >      /*
> >       * Drivers not implementing bdrv_parse_filename nor bdrv_open should have
> >       * this field set to true, except ones that are defined only by their
>
> --
> Damien Le Moal
> Western Digital Research
>

On 2022/09/11 15:54, Sam Li wrote:
> Damien Le Moal <damien.lemoal@opensource.wdc.com> 于2022年9月11日周日 13:34写道：
>>
>> On 2022/09/10 14:27, Sam Li wrote:
>>> Putting zoned/non-zoned BlockDrivers on top of each other is not
>>> allowed.
>>>
>>> Signed-off-by: Sam Li <faithilikerun@gmail.com>
>>> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
>>> ---
>>>  block.c                          | 14 ++++++++++++++
>>>  block/file-posix.c               | 14 ++++++++++++++
>>>  block/raw-format.c               |  1 +
>>>  include/block/block_int-common.h |  5 +++++
>>>  4 files changed, 34 insertions(+)
>>>
>>> diff --git a/block.c b/block.c
>>> index bc85f46eed..dad2ed3959 100644
>>> --- a/block.c
>>> +++ b/block.c
>>> @@ -7947,6 +7947,20 @@ void bdrv_add_child(BlockDriverState *parent_bs, BlockDriverState *child_bs,
>>>          return;
>>>      }
>>>
>>> +    /*
>>> +     * Non-zoned block drivers do not follow zoned storage constraints
>>> +     * (i.e. sequential writes to zones). Refuse mixing zoned and non-zoned
>>> +     * drivers in a graph.
>>> +     */
>>> +    if (!parent_bs->drv->supports_zoned_children &&
>>> +        child_bs->bl.zoned == BLK_Z_HM) {
>>
>> Shouldn't this be "child_bs->bl.zoned != BLK_Z_NONE" ?
> 
> The host-aware model allows zoned storage constraints(sequentially
> write) and random write. Is mixing HA and non-zoned drivers allowed?
> What's the difference?

Yes, HA devices can be used as regular devices too. If you are allowing this
here, then add a comment explaining it. It may also be good to add a message
like "Using host-aware device as a regular device" here for the HA case.
> 
>>
>>> +        error_setg(errp, "Cannot add a %s child to a %s parent",
>>> +                   child_bs->bl.zoned == BLK_Z_HM ? "zoned" : "non-zoned",
>>> +                   parent_bs->drv->supports_zoned_children ?
>>> +                   "support zoned children" : "not support zoned children");
>>> +        return;
>>> +    }
>>> +
>>>      if (!QLIST_EMPTY(&child_bs->parents)) {
>>>          error_setg(errp, "The node %s already has a parent",
>>>                     child_bs->node_name);
>>> diff --git a/block/file-posix.c b/block/file-posix.c
>>> index 4edfa25d04..354de22860 100644
>>> --- a/block/file-posix.c
>>> +++ b/block/file-posix.c
>>> @@ -779,6 +779,20 @@ static int raw_open_common(BlockDriverState *bs, QDict *options,
>>>              goto fail;
>>>          }
>>>      }
>>> +#ifdef CONFIG_BLKZONED
>>> +    /*
>>> +     * The kernel page chache does not reliably work for writes to SWR zones
>>> +     * of zoned block device because it can not guarantee the order of writes.
>>> +     */
>>> +    if (strcmp(bs->drv->format_name, "zoned_host_device") == 0) {
>>> +        if (!(s->open_flags & O_DIRECT)) {
>>> +            error_setg(errp, "driver=zoned_host_device was specified, but it "
>>> +                             "requires cache.direct=on, which was not specified.");
>>> +            ret = -EINVAL;
>>
>> This line is not needed. Simply "return -EINVAL;".
>>
>>> +            return ret; /* No host kernel page cache */
>>> +        }
>>> +    }
>>> +#endif
>>>
>>>      if (S_ISBLK(st.st_mode)) {
>>>  #ifdef BLKDISCARDZEROES
>>> diff --git a/block/raw-format.c b/block/raw-format.c
>>> index 6b20bd22ef..9441536819 100644
>>> --- a/block/raw-format.c
>>> +++ b/block/raw-format.c
>>> @@ -614,6 +614,7 @@ static void raw_child_perm(BlockDriverState *bs, BdrvChild *c,
>>>  BlockDriver bdrv_raw = {
>>>      .format_name          = "raw",
>>>      .instance_size        = sizeof(BDRVRawState),
>>> +    .supports_zoned_children = true,
>>>      .bdrv_probe           = &raw_probe,
>>>      .bdrv_reopen_prepare  = &raw_reopen_prepare,
>>>      .bdrv_reopen_commit   = &raw_reopen_commit,
>>> diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h
>>> index 078ddd7e67..043aa161a0 100644
>>> --- a/include/block/block_int-common.h
>>> +++ b/include/block/block_int-common.h
>>> @@ -127,6 +127,11 @@ struct BlockDriver {
>>>       */
>>>      bool is_format;
>>>
>>> +    /*
>>> +     * Set to true if the BlockDriver supports zoned children.
>>> +     */
>>> +    bool supports_zoned_children;
>>> +
>>>      /*
>>>       * Drivers not implementing bdrv_parse_filename nor bdrv_open should have
>>>       * this field set to true, except ones that are defined only by their
>>
>> --
>> Damien Le Moal
>> Western Digital Research
>>

On Sat, Sep 10, 2022 at 01:27:57PM +0800, Sam Li wrote:
> diff --git a/block/file-posix.c b/block/file-posix.c
> index 4edfa25d04..354de22860 100644
> --- a/block/file-posix.c
> +++ b/block/file-posix.c
> @@ -779,6 +779,20 @@ static int raw_open_common(BlockDriverState *bs, QDict *options,
>              goto fail;
>          }
>      }
> +#ifdef CONFIG_BLKZONED
> +    /*
> +     * The kernel page chache does not reliably work for writes to SWR zones

s/chache/cache/