[RFC,v3,03/22] scsi: core: Implement reserved command handling

Message ID 1666693096-180008-4-git-send-email-john.garry@huawei.com
State New
Headers
Series blk-mq/libata/scsi: SCSI driver tagging improvements Part I |

Commit Message

John Garry Oct. 25, 2022, 10:17 a.m. UTC
  From: Hannes Reinecke <hare@suse.de>

Quite some drivers are using management commands internally, which
typically use the same hardware tag pool (ie they are being allocated
from the same hardware resources) as the 'normal' I/O commands.
These commands are set aside before allocating the block-mq tag bitmap,
so they'll never show up as busy in the tag map.
The block-layer, OTOH, already has 'reserved_tags' to handle precisely
this situation.
So this patch adds a new field 'nr_reserved_cmds' to the SCSI host
template to instruct the block layer to set aside a tag space for these
management commands by using reserved tags.

Signed-off-by: Hannes Reinecke <hare@suse.de>
#jpg: Set tag_set->queue_depth = shost->can_queue, and not
= shost->can_queue + shost->nr_reserved_cmds;
Signed-off-by: John Garry <john.garry@huawei.com>
---
 drivers/scsi/hosts.c     |  3 +++
 drivers/scsi/scsi_lib.c  |  2 ++
 include/scsi/scsi_host.h | 15 ++++++++++++++-
 3 files changed, 19 insertions(+), 1 deletion(-)
  

Comments

Damien Le Moal Oct. 27, 2022, 1:18 a.m. UTC | #1
On 10/25/22 19:17, John Garry wrote:
> From: Hannes Reinecke <hare@suse.de>
> 
> Quite some drivers are using management commands internally, which
> typically use the same hardware tag pool (ie they are being allocated
> from the same hardware resources) as the 'normal' I/O commands.
> These commands are set aside before allocating the block-mq tag bitmap,
> so they'll never show up as busy in the tag map.
> The block-layer, OTOH, already has 'reserved_tags' to handle precisely
> this situation.
> So this patch adds a new field 'nr_reserved_cmds' to the SCSI host
> template to instruct the block layer to set aside a tag space for these
> management commands by using reserved tags.
> 
> Signed-off-by: Hannes Reinecke <hare@suse.de>
> #jpg: Set tag_set->queue_depth = shost->can_queue, and not
> = shost->can_queue + shost->nr_reserved_cmds;
> Signed-off-by: John Garry <john.garry@huawei.com>
> ---
>  drivers/scsi/hosts.c     |  3 +++
>  drivers/scsi/scsi_lib.c  |  2 ++
>  include/scsi/scsi_host.h | 15 ++++++++++++++-
>  3 files changed, 19 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
> index 12346e2297fd..db89afc37bc9 100644
> --- a/drivers/scsi/hosts.c
> +++ b/drivers/scsi/hosts.c
> @@ -489,6 +489,9 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize)
>  	if (sht->virt_boundary_mask)
>  		shost->virt_boundary_mask = sht->virt_boundary_mask;
>  
> +	if (sht->nr_reserved_cmds)
> +		shost->nr_reserved_cmds = sht->nr_reserved_cmds;
> +

Nit: the if is not really necessary I think. But it does not hurt.

>  	device_initialize(&shost->shost_gendev);
>  	dev_set_name(&shost->shost_gendev, "host%d", shost->host_no);
>  	shost->shost_gendev.bus = &scsi_bus_type;
> diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
> index 39d4fd124375..a8c4e7c037ae 100644
> --- a/drivers/scsi/scsi_lib.c
> +++ b/drivers/scsi/scsi_lib.c
> @@ -1978,6 +1978,8 @@ int scsi_mq_setup_tags(struct Scsi_Host *shost)
>  	tag_set->nr_hw_queues = shost->nr_hw_queues ? : 1;
>  	tag_set->nr_maps = shost->nr_maps ? : 1;
>  	tag_set->queue_depth = shost->can_queue;
> +	tag_set->reserved_tags = shost->nr_reserved_cmds;
> +

Why the blank line ?

>  	tag_set->cmd_size = cmd_size;
>  	tag_set->numa_node = dev_to_node(shost->dma_dev);
>  	tag_set->flags = BLK_MQ_F_SHOULD_MERGE;
> diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
> index 750ccf126377..91678c77398e 100644
> --- a/include/scsi/scsi_host.h
> +++ b/include/scsi/scsi_host.h
> @@ -360,10 +360,17 @@ struct scsi_host_template {
>  	/*
>  	 * This determines if we will use a non-interrupt driven
>  	 * or an interrupt driven scheme.  It is set to the maximum number
> -	 * of simultaneous commands a single hw queue in HBA will accept.
> +	 * of simultaneous commands a single hw queue in HBA will accept
> +	 * including reserved commands.
>  	 */
>  	int can_queue;
>  
> +	/*
> +	 * This determines how many commands the HBA will set aside
> +	 * for reserved commands.
> +	 */
> +	int nr_reserved_cmds;
> +
>  	/*
>  	 * In many instances, especially where disconnect / reconnect are
>  	 * supported, our host also has an ID on the SCSI bus.  If this is
> @@ -611,6 +618,12 @@ struct Scsi_Host {
>  	 */
>  	unsigned nr_hw_queues;
>  	unsigned nr_maps;
> +
> +	/*
> +	 * Number of reserved commands to allocate, if any.
> +	 */
> +	unsigned int nr_reserved_cmds;
> +
>  	unsigned active_mode:2;
>  
>  	/*
  
Hannes Reinecke Oct. 27, 2022, 7:51 a.m. UTC | #2
On 10/27/22 03:18, Damien Le Moal wrote:
> On 10/25/22 19:17, John Garry wrote:
>> From: Hannes Reinecke <hare@suse.de>
>>
>> Quite some drivers are using management commands internally, which
>> typically use the same hardware tag pool (ie they are being allocated
>> from the same hardware resources) as the 'normal' I/O commands.
>> These commands are set aside before allocating the block-mq tag bitmap,
>> so they'll never show up as busy in the tag map.
>> The block-layer, OTOH, already has 'reserved_tags' to handle precisely
>> this situation.
>> So this patch adds a new field 'nr_reserved_cmds' to the SCSI host
>> template to instruct the block layer to set aside a tag space for these
>> management commands by using reserved tags.
>>
>> Signed-off-by: Hannes Reinecke <hare@suse.de>
>> #jpg: Set tag_set->queue_depth = shost->can_queue, and not
>> = shost->can_queue + shost->nr_reserved_cmds;
>> Signed-off-by: John Garry <john.garry@huawei.com>
>> ---
>>   drivers/scsi/hosts.c     |  3 +++
>>   drivers/scsi/scsi_lib.c  |  2 ++
>>   include/scsi/scsi_host.h | 15 ++++++++++++++-
>>   3 files changed, 19 insertions(+), 1 deletion(-)
>>
>> diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
>> index 12346e2297fd..db89afc37bc9 100644
>> --- a/drivers/scsi/hosts.c
>> +++ b/drivers/scsi/hosts.c
>> @@ -489,6 +489,9 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize)
>>   	if (sht->virt_boundary_mask)
>>   		shost->virt_boundary_mask = sht->virt_boundary_mask;
>>   
>> +	if (sht->nr_reserved_cmds)
>> +		shost->nr_reserved_cmds = sht->nr_reserved_cmds;
>> +
> 
> Nit: the if is not really necessary I think. But it does not hurt.
> 
Yes, we do.
Not all HBAs are able to figure out the number of reserved commands 
upfront; some modify that based on the PCI device used etc.
So I'd keep it for now.

Cheers,

Hannes
  
John Garry Oct. 27, 2022, 8:16 a.m. UTC | #3
On 27/10/2022 08:51, Hannes Reinecke wrote:
>>>
>>> Signed-off-by: Hannes Reinecke <hare@suse.de>
>>> #jpg: Set tag_set->queue_depth = shost->can_queue, and not
>>> = shost->can_queue + shost->nr_reserved_cmds;
>>> Signed-off-by: John Garry <john.garry@huawei.com>
>>> ---
>>>   drivers/scsi/hosts.c     |  3 +++
>>>   drivers/scsi/scsi_lib.c  |  2 ++
>>>   include/scsi/scsi_host.h | 15 ++++++++++++++-
>>>   3 files changed, 19 insertions(+), 1 deletion(-)
>>>
>>> diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
>>> index 12346e2297fd..db89afc37bc9 100644
>>> --- a/drivers/scsi/hosts.c
>>> +++ b/drivers/scsi/hosts.c
>>> @@ -489,6 +489,9 @@ struct Scsi_Host *scsi_host_alloc(struct 
>>> scsi_host_template *sht, int privsize)
>>>       if (sht->virt_boundary_mask)
>>>           shost->virt_boundary_mask = sht->virt_boundary_mask;
>>> +    if (sht->nr_reserved_cmds)
>>> +        shost->nr_reserved_cmds = sht->nr_reserved_cmds;
>>> +
>>
>> Nit: the if is not really necessary I think. But it does not hurt.
>>
> Yes, we do.
> Not all HBAs are able to figure out the number of reserved commands 
> upfront; some modify that based on the PCI device used etc.
> So I'd keep it for now.

I think logically Damien is right as in the shost alloc 
shost->nr_reserved_cmds is initially zero, so:

if (sht->nr_reserved_cmds)
        shost->nr_reserved_cmds = sht->nr_reserved_cmds;

is same as simply:

	shost->nr_reserved_cmds = sht->nr_reserved_cmds;

However I am just copying the coding style.

Thanks,
John
  
John Garry Oct. 27, 2022, 9:11 a.m. UTC | #4
> 
>>   	device_initialize(&shost->shost_gendev);
>>   	dev_set_name(&shost->shost_gendev, "host%d", shost->host_no);
>>   	shost->shost_gendev.bus = &scsi_bus_type;
>> diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
>> index 39d4fd124375..a8c4e7c037ae 100644
>> --- a/drivers/scsi/scsi_lib.c
>> +++ b/drivers/scsi/scsi_lib.c
>> @@ -1978,6 +1978,8 @@ int scsi_mq_setup_tags(struct Scsi_Host *shost)
>>   	tag_set->nr_hw_queues = shost->nr_hw_queues ? : 1;
>>   	tag_set->nr_maps = shost->nr_maps ? : 1;
>>   	tag_set->queue_depth = shost->can_queue;
>> +	tag_set->reserved_tags = shost->nr_reserved_cmds;
>> +
> Why the blank line ?
> 

I don't think that it is required, I can remedy.

>>   	tag_set->cmd_size = cmd_size;

Thanks,
John
  

Patch

diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index 12346e2297fd..db89afc37bc9 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -489,6 +489,9 @@  struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize)
 	if (sht->virt_boundary_mask)
 		shost->virt_boundary_mask = sht->virt_boundary_mask;
 
+	if (sht->nr_reserved_cmds)
+		shost->nr_reserved_cmds = sht->nr_reserved_cmds;
+
 	device_initialize(&shost->shost_gendev);
 	dev_set_name(&shost->shost_gendev, "host%d", shost->host_no);
 	shost->shost_gendev.bus = &scsi_bus_type;
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 39d4fd124375..a8c4e7c037ae 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1978,6 +1978,8 @@  int scsi_mq_setup_tags(struct Scsi_Host *shost)
 	tag_set->nr_hw_queues = shost->nr_hw_queues ? : 1;
 	tag_set->nr_maps = shost->nr_maps ? : 1;
 	tag_set->queue_depth = shost->can_queue;
+	tag_set->reserved_tags = shost->nr_reserved_cmds;
+
 	tag_set->cmd_size = cmd_size;
 	tag_set->numa_node = dev_to_node(shost->dma_dev);
 	tag_set->flags = BLK_MQ_F_SHOULD_MERGE;
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 750ccf126377..91678c77398e 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -360,10 +360,17 @@  struct scsi_host_template {
 	/*
 	 * This determines if we will use a non-interrupt driven
 	 * or an interrupt driven scheme.  It is set to the maximum number
-	 * of simultaneous commands a single hw queue in HBA will accept.
+	 * of simultaneous commands a single hw queue in HBA will accept
+	 * including reserved commands.
 	 */
 	int can_queue;
 
+	/*
+	 * This determines how many commands the HBA will set aside
+	 * for reserved commands.
+	 */
+	int nr_reserved_cmds;
+
 	/*
 	 * In many instances, especially where disconnect / reconnect are
 	 * supported, our host also has an ID on the SCSI bus.  If this is
@@ -611,6 +618,12 @@  struct Scsi_Host {
 	 */
 	unsigned nr_hw_queues;
 	unsigned nr_maps;
+
+	/*
+	 * Number of reserved commands to allocate, if any.
+	 */
+	unsigned int nr_reserved_cmds;
+
 	unsigned active_mode:2;
 
 	/*