Re: [Qemu-devel] [PATCH v10 4/9] block: introduce BDRV_REQ_ALLOCATE flag

[Anton Nefedov]

On 5/12/2018 3:59 PM, Vladimir Sementsov-Ogievskiy wrote:
> 03.12.2018 13:14, Anton Nefedov wrote:
>> The flag is supposed to indicate that the region of the disk image has
>> to be sufficiently allocated so it reads as zeroes.
>>
>> The call with the flag set must return -ENOTSUP if allocation cannot
>> be done efficiently.
>> This has to be made sure of by both
>>     - the drivers that support the flag
>>     - and the common block layer (so it will not fall back to any slowpath
>>       (like writing zero buffers) in case the driver does not support
>>       the flag).
>>
>> Signed-off-by: Anton Nefedov <address@hidden>
>> Reviewed-by: Alberto Garcia <address@hidden>
>> ---
>>    include/block/block.h     |  9 ++++++++-
>>    include/block/block_int.h |  2 +-
>>    block/io.c                | 18 ++++++++++++++++--
>>    3 files changed, 25 insertions(+), 4 deletions(-)
>>
>> diff --git a/include/block/block.h b/include/block/block.h
>> index 7f5453b45b..f571082415 100644
>> --- a/include/block/block.h
>> +++ b/include/block/block.h
>> @@ -83,8 +83,15 @@ typedef enum {
>>         */
>>        BDRV_REQ_SERIALISING        = 0x80,
>>    
>> +    /* The BDRV_REQ_ALLOCATE flag is used to indicate that the driver has to
>> +     * efficiently allocate the space so it reads as zeroes, or return an 
>> error.
>> +     * If this flag is set then BDRV_REQ_ZERO_WRITE must also be set.
>> +     * This flag cannot be set together with BDRV_REQ_MAY_UNMAP.
> 
> and, may be, it can't be set with FUA too?
> 

I don't quite see why it cannot. Even the efficient allocate call
usually implies some Unit Access, it's up to the protocol driver to
decide which exactly.

>> +     */
>> +    BDRV_REQ_ALLOCATE           = 0x100,
>> +
>>        /* Mask of valid flags */
>> -    BDRV_REQ_MASK               = 0xff,
>> +    BDRV_REQ_MASK               = 0x1ff,
>>    } BdrvRequestFlags;
>>    
>>    typedef struct BlockSizes {
>> diff --git a/include/block/block_int.h b/include/block/block_int.h
>> index f605622216..ff84c5d8aa 100644
>> --- a/include/block/block_int.h
>> +++ b/include/block/block_int.h
>> @@ -724,7 +724,7 @@ struct BlockDriverState {
>>         * their children. */
>>        unsigned int supported_write_flags;
>>        /* Flags honored during pwrite_zeroes (so far: BDRV_REQ_FUA,
>> -     * BDRV_REQ_MAY_UNMAP, BDRV_REQ_WRITE_UNCHANGED) */
>> +     * BDRV_REQ_MAY_UNMAP, BDRV_REQ_WRITE_UNCHANGED, BDRV_REQ_ALLOCATE) */
>>        unsigned int supported_zero_flags;
>>    
>>        /* the following member gives a name to every node on the bs graph. */
>> diff --git a/block/io.c b/block/io.c
>> index bd9d688f8b..d9d7644858 100644
>> --- a/block/io.c
>> +++ b/block/io.c
>> @@ -1534,7 +1534,7 @@ static int coroutine_fn 
>> bdrv_co_do_pwrite_zeroes(BlockDriverState *bs,
>>                assert(!bs->supported_zero_flags);
>>            }
>>    
>> -        if (ret == -ENOTSUP) {
>> +        if (ret == -ENOTSUP && !(flags & BDRV_REQ_ALLOCATE)) {
>>                /* Fall back to bounce buffer if write zeroes is unsupported 
>> */
>>                BdrvRequestFlags write_flags = flags & ~BDRV_REQ_ZERO_WRITE;
>>    
>> @@ -1702,7 +1702,9 @@ static int coroutine_fn bdrv_aligned_pwritev(BdrvChild 
>> *child,
>>            !(flags & BDRV_REQ_ZERO_WRITE) && drv->bdrv_co_pwrite_zeroes &&
>>            qemu_iovec_is_zero(qiov)) {
>>            flags |= BDRV_REQ_ZERO_WRITE;
>> -        if (bs->detect_zeroes == BLOCKDEV_DETECT_ZEROES_OPTIONS_UNMAP) {
>> +        if (bs->detect_zeroes == BLOCKDEV_DETECT_ZEROES_OPTIONS_UNMAP &&
>> +            !(flags & BDRV_REQ_ALLOCATE))
> 
> 
> dead check. we are in if (!(flags & BDRV_REQ_ZERO_WRITE)), so (flags & 
> BDRV_REQ_ALLOCATE) must be zero as well.
> 

Agree.

>> +        {
>>                flags |= BDRV_REQ_MAY_UNMAP;
>>            }
>>        }
>> @@ -1773,6 +1775,9 @@ static int coroutine_fn 
>> bdrv_co_do_zero_pwritev(BdrvChild *child,
>>    
>>        assert(flags & BDRV_REQ_ZERO_WRITE);
>>        if (head_padding_bytes || tail_padding_bytes) {
>> +        if (flags & BDRV_REQ_ALLOCATE) {
>> +            return -ENOTSUP;
>> +        }
>>            buf = qemu_blockalign(bs, align);
>>            iov = (struct iovec) {
>>                .iov_base   = buf,
>> @@ -1858,6 +1863,9 @@ int coroutine_fn bdrv_co_pwritev(BdrvChild *child,
>>        bool use_local_qiov = false;
>>        int ret;
>>    
>> +    assert(!((flags & BDRV_REQ_ALLOCATE) && (flags & BDRV_REQ_MAY_UNMAP)));
>> +    assert(!((flags & BDRV_REQ_ALLOCATE) && !(flags & 
>> BDRV_REQ_ZERO_WRITE)));
> 
> what about FUA?
> 

pls see above

>> +
>>        trace_bdrv_co_pwritev(child->bs, offset, bytes, flags);
>>    
>>        if (!bs->drv) {
>> @@ -1980,6 +1988,12 @@ int coroutine_fn bdrv_co_pwrite_zeroes(BdrvChild 
>> *child, int64_t offset,
>>    {
>>        trace_bdrv_co_pwrite_zeroes(child->bs, offset, bytes, flags);
>>    
>> +    if ((flags & BDRV_REQ_ALLOCATE) &&
>> +        !(child->bs->supported_zero_flags & BDRV_REQ_ALLOCATE))
>> +    {
>> +        return -ENOTSUP;
>> +    }
>> +
>>        if (!(child->bs->open_flags & BDRV_O_UNMAP)) {
>>            flags &= ~BDRV_REQ_MAY_UNMAP;
>>        }
>>
> 
>