Re: [PATCH v4 05/10] xen/blkfront: negotiate number of queues/rings to be used with backend

2015-11-03 Thread Konrad Rzeszutek Wilk
On Wed, Nov 04, 2015 at 09:11:10AM +0800, Bob Liu wrote:
> 
> On 11/04/2015 04:40 AM, Konrad Rzeszutek Wilk wrote:
> > On Mon, Nov 02, 2015 at 12:21:41PM +0800, Bob Liu wrote:
> >> The number of hardware queues for xen/blkfront is set by parameter
> >> 'max_queues'(default 4), while the max value xen/blkback supported is 
> >> notified
> >> through xenstore("multi-queue-max-queues").
> > 
> > That is not right.
> > 
> > s/The number/The max number/
> > 
> > The second part: ",while the max value xen/blkback supported is..". I think
> > you are trying to say: "it is also capped by the max value that
> > the xen/blkback exposes through XenStore key 'multi-queue-max-queues'.
> > 
> >>
> >> The negotiated number is the smaller one and would be written back to 
> >> xenstore
> >> as "multi-queue-num-queues", blkback need to read this negotiated number.
> > 
> > s/blkback need to read/blkback needs to read this/
> > 
> >>
> >> Signed-off-by: Bob Liu 
> >> ---
> >>  drivers/block/xen-blkfront.c | 166 
> >> +++
> >>  1 file changed, 120 insertions(+), 46 deletions(-)
> >>
> >> diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
> >> index 8cc5995..23096d7 100644
> >> --- a/drivers/block/xen-blkfront.c
> >> +++ b/drivers/block/xen-blkfront.c
> >> @@ -98,6 +98,10 @@ static unsigned int xen_blkif_max_segments = 32;
> >>  module_param_named(max, xen_blkif_max_segments, int, S_IRUGO);
> >>  MODULE_PARM_DESC(max, "Maximum amount of segments in indirect requests 
> >> (default is 32)");
> >>  
> >> +static unsigned int xen_blkif_max_queues = 4;
> >> +module_param_named(max_queues, xen_blkif_max_queues, uint, S_IRUGO);
> >> +MODULE_PARM_DESC(max_queues, "Maximum number of hardware queues/rings 
> >> used per virtual disk");
> >> +
> >>  /*
> >>   * Maximum order of pages to be used for the shared ring between front and
> >>   * backend, 4KB page granularity is used.
> >> @@ -113,6 +117,7 @@ MODULE_PARM_DESC(max_ring_page_order, "Maximum order 
> >> of pages to be used for the
> >>   * characters are enough. Define to 20 to keep consist with backend.
> >>   */
> >>  #define RINGREF_NAME_LEN (20)
> >> +#define QUEUE_NAME_LEN (12)
> > 
> > Little bit of documentation please. Why 12? Why not 31415 for example?
> > I presume it is 'queue-%u' and since so that is 7 + 10 (UINT_MAX is
> > 4294967295) = 17!
> > 
> > 
> >>  
> >>  /*
> >>   *  Per-ring info.
> >> @@ -695,7 +700,7 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, 
> >> u16 sector_size,
> >>  
> >>memset(>tag_set, 0, sizeof(info->tag_set));
> >>info->tag_set.ops = _mq_ops;
> >> -  info->tag_set.nr_hw_queues = 1;
> >> +  info->tag_set.nr_hw_queues = info->nr_rings;
> >>info->tag_set.queue_depth =  BLK_RING_SIZE(info);
> >>info->tag_set.numa_node = NUMA_NO_NODE;
> >>info->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
> >> @@ -1352,6 +1357,51 @@ fail:
> >>return err;
> >>  }
> >>  
> >> +static int write_per_ring_nodes(struct xenbus_transaction xbt,
> >> +  struct blkfront_ring_info *rinfo, const char 
> >> *dir)
> >> +{
> >> +  int err, i;
> > 
> > Please make 'i' be an unsigned int. Especially as you are using '%u' in the 
> > snprintf.
> > 
> > 
> >> +  const char *message = NULL;
> >> +  struct blkfront_info *info = rinfo->dev_info;
> >> +
> >> +  if (info->nr_ring_pages == 1) {
> >> +  err = xenbus_printf(xbt, dir, "ring-ref", "%u", 
> >> rinfo->ring_ref[0]);
> >> +  if (err) {
> >> +  message = "writing ring-ref";
> >> +  goto abort_transaction;
> >> +  }
> >> +  pr_info("%s: write ring-ref:%d\n", dir, rinfo->ring_ref[0]);
> > 
> > Ewww. No.
> > 
> >> +  } else {
> >> +  for (i = 0; i < info->nr_ring_pages; i++) {
> >> +  char ring_ref_name[RINGREF_NAME_LEN];
> >> +
> >> +  snprintf(ring_ref_name, RINGREF_NAME_LEN, "ring-ref%u", 
> >> i);
> >> +  err = xenbus_printf(xbt, dir, ring_ref_name,
> >> +  "%u", rinfo->ring_ref[i]);
> >> +  if (err) {
> >> +  message = "writing ring-ref";
> >> +  goto abort_transaction;
> >> +  }
> >> +  pr_info("%s: write ring-ref:%d\n", dir, 
> >> rinfo->ring_ref[i]);
> > 
> > No no please.
> > 
> >> +  }
> >> +  }
> >> +
> >> +  err = xenbus_printf(xbt, dir, "event-channel", "%u", rinfo->evtchn);
> > 
> > That is not right.
> > 
> > That only creates one. But the blkif.h says (And the example agrees)
> > that there are N 'event-channel' for N-rings.
> > 
> > Shouldn't this be part of the above loop?
> > 
> 
> No, this loop is only for per-ring each with "multipage".
> 
> The loop you want is..
> 
> >> +  if (err) {
> >> +  message = "writing event-channel";
> >> +  goto abort_transaction;
> >> +  }
> >> +  pr_info("%s: write 

Re: [PATCH v4 05/10] xen/blkfront: negotiate number of queues/rings to be used with backend

2015-11-03 Thread Bob Liu

On 11/04/2015 04:40 AM, Konrad Rzeszutek Wilk wrote:
> On Mon, Nov 02, 2015 at 12:21:41PM +0800, Bob Liu wrote:
>> The number of hardware queues for xen/blkfront is set by parameter
>> 'max_queues'(default 4), while the max value xen/blkback supported is 
>> notified
>> through xenstore("multi-queue-max-queues").
> 
> That is not right.
> 
> s/The number/The max number/
> 
> The second part: ",while the max value xen/blkback supported is..". I think
> you are trying to say: "it is also capped by the max value that
> the xen/blkback exposes through XenStore key 'multi-queue-max-queues'.
> 
>>
>> The negotiated number is the smaller one and would be written back to 
>> xenstore
>> as "multi-queue-num-queues", blkback need to read this negotiated number.
> 
> s/blkback need to read/blkback needs to read this/
> 
>>
>> Signed-off-by: Bob Liu 
>> ---
>>  drivers/block/xen-blkfront.c | 166 
>> +++
>>  1 file changed, 120 insertions(+), 46 deletions(-)
>>
>> diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
>> index 8cc5995..23096d7 100644
>> --- a/drivers/block/xen-blkfront.c
>> +++ b/drivers/block/xen-blkfront.c
>> @@ -98,6 +98,10 @@ static unsigned int xen_blkif_max_segments = 32;
>>  module_param_named(max, xen_blkif_max_segments, int, S_IRUGO);
>>  MODULE_PARM_DESC(max, "Maximum amount of segments in indirect requests 
>> (default is 32)");
>>  
>> +static unsigned int xen_blkif_max_queues = 4;
>> +module_param_named(max_queues, xen_blkif_max_queues, uint, S_IRUGO);
>> +MODULE_PARM_DESC(max_queues, "Maximum number of hardware queues/rings used 
>> per virtual disk");
>> +
>>  /*
>>   * Maximum order of pages to be used for the shared ring between front and
>>   * backend, 4KB page granularity is used.
>> @@ -113,6 +117,7 @@ MODULE_PARM_DESC(max_ring_page_order, "Maximum order of 
>> pages to be used for the
>>   * characters are enough. Define to 20 to keep consist with backend.
>>   */
>>  #define RINGREF_NAME_LEN (20)
>> +#define QUEUE_NAME_LEN (12)
> 
> Little bit of documentation please. Why 12? Why not 31415 for example?
> I presume it is 'queue-%u' and since so that is 7 + 10 (UINT_MAX is
> 4294967295) = 17!
> 
> 
>>  
>>  /*
>>   *  Per-ring info.
>> @@ -695,7 +700,7 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 
>> sector_size,
>>  
>>  memset(>tag_set, 0, sizeof(info->tag_set));
>>  info->tag_set.ops = _mq_ops;
>> -info->tag_set.nr_hw_queues = 1;
>> +info->tag_set.nr_hw_queues = info->nr_rings;
>>  info->tag_set.queue_depth =  BLK_RING_SIZE(info);
>>  info->tag_set.numa_node = NUMA_NO_NODE;
>>  info->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
>> @@ -1352,6 +1357,51 @@ fail:
>>  return err;
>>  }
>>  
>> +static int write_per_ring_nodes(struct xenbus_transaction xbt,
>> +struct blkfront_ring_info *rinfo, const char 
>> *dir)
>> +{
>> +int err, i;
> 
> Please make 'i' be an unsigned int. Especially as you are using '%u' in the 
> snprintf.
> 
> 
>> +const char *message = NULL;
>> +struct blkfront_info *info = rinfo->dev_info;
>> +
>> +if (info->nr_ring_pages == 1) {
>> +err = xenbus_printf(xbt, dir, "ring-ref", "%u", 
>> rinfo->ring_ref[0]);
>> +if (err) {
>> +message = "writing ring-ref";
>> +goto abort_transaction;
>> +}
>> +pr_info("%s: write ring-ref:%d\n", dir, rinfo->ring_ref[0]);
> 
> Ewww. No.
> 
>> +} else {
>> +for (i = 0; i < info->nr_ring_pages; i++) {
>> +char ring_ref_name[RINGREF_NAME_LEN];
>> +
>> +snprintf(ring_ref_name, RINGREF_NAME_LEN, "ring-ref%u", 
>> i);
>> +err = xenbus_printf(xbt, dir, ring_ref_name,
>> +"%u", rinfo->ring_ref[i]);
>> +if (err) {
>> +message = "writing ring-ref";
>> +goto abort_transaction;
>> +}
>> +pr_info("%s: write ring-ref:%d\n", dir, 
>> rinfo->ring_ref[i]);
> 
> No no please.
> 
>> +}
>> +}
>> +
>> +err = xenbus_printf(xbt, dir, "event-channel", "%u", rinfo->evtchn);
> 
> That is not right.
> 
> That only creates one. But the blkif.h says (And the example agrees)
> that there are N 'event-channel' for N-rings.
> 
> Shouldn't this be part of the above loop?
> 

No, this loop is only for per-ring each with "multipage".

The loop you want is..

>> +if (err) {
>> +message = "writing event-channel";
>> +goto abort_transaction;
>> +}
>> +pr_info("%s: write event-channel:%d\n", dir, rinfo->evtchn);
> 
> Please no.
> 
>> +
>> +return 0;
>> +
>> +abort_transaction:
>> +xenbus_transaction_end(xbt, 1);
>> +if (message)
>> +xenbus_dev_fatal(info->xbdev, err, "%s", message);
>> +
>> +return err;
>> +}
>> 

Re: [PATCH v4 05/10] xen/blkfront: negotiate number of queues/rings to be used with backend

2015-11-03 Thread Bob Liu

On 11/04/2015 04:40 AM, Konrad Rzeszutek Wilk wrote:
> On Mon, Nov 02, 2015 at 12:21:41PM +0800, Bob Liu wrote:
>> The number of hardware queues for xen/blkfront is set by parameter
>> 'max_queues'(default 4), while the max value xen/blkback supported is 
>> notified
>> through xenstore("multi-queue-max-queues").
> 
> That is not right.
> 
> s/The number/The max number/
> 
> The second part: ",while the max value xen/blkback supported is..". I think
> you are trying to say: "it is also capped by the max value that
> the xen/blkback exposes through XenStore key 'multi-queue-max-queues'.
> 
>>
>> The negotiated number is the smaller one and would be written back to 
>> xenstore
>> as "multi-queue-num-queues", blkback need to read this negotiated number.
> 
> s/blkback need to read/blkback needs to read this/
> 
>>
>> Signed-off-by: Bob Liu 
>> ---
>>  drivers/block/xen-blkfront.c | 166 
>> +++
>>  1 file changed, 120 insertions(+), 46 deletions(-)
>>
>> diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
>> index 8cc5995..23096d7 100644
>> --- a/drivers/block/xen-blkfront.c
>> +++ b/drivers/block/xen-blkfront.c
>> @@ -98,6 +98,10 @@ static unsigned int xen_blkif_max_segments = 32;
>>  module_param_named(max, xen_blkif_max_segments, int, S_IRUGO);
>>  MODULE_PARM_DESC(max, "Maximum amount of segments in indirect requests 
>> (default is 32)");
>>  
>> +static unsigned int xen_blkif_max_queues = 4;
>> +module_param_named(max_queues, xen_blkif_max_queues, uint, S_IRUGO);
>> +MODULE_PARM_DESC(max_queues, "Maximum number of hardware queues/rings used 
>> per virtual disk");
>> +
>>  /*
>>   * Maximum order of pages to be used for the shared ring between front and
>>   * backend, 4KB page granularity is used.
>> @@ -113,6 +117,7 @@ MODULE_PARM_DESC(max_ring_page_order, "Maximum order of 
>> pages to be used for the
>>   * characters are enough. Define to 20 to keep consist with backend.
>>   */
>>  #define RINGREF_NAME_LEN (20)
>> +#define QUEUE_NAME_LEN (12)
> 
> Little bit of documentation please. Why 12? Why not 31415 for example?
> I presume it is 'queue-%u' and since so that is 7 + 10 (UINT_MAX is
> 4294967295) = 17!
> 
> 
>>  
>>  /*
>>   *  Per-ring info.
>> @@ -695,7 +700,7 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 
>> sector_size,
>>  
>>  memset(>tag_set, 0, sizeof(info->tag_set));
>>  info->tag_set.ops = _mq_ops;
>> -info->tag_set.nr_hw_queues = 1;
>> +info->tag_set.nr_hw_queues = info->nr_rings;
>>  info->tag_set.queue_depth =  BLK_RING_SIZE(info);
>>  info->tag_set.numa_node = NUMA_NO_NODE;
>>  info->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
>> @@ -1352,6 +1357,51 @@ fail:
>>  return err;
>>  }
>>  
>> +static int write_per_ring_nodes(struct xenbus_transaction xbt,
>> +struct blkfront_ring_info *rinfo, const char 
>> *dir)
>> +{
>> +int err, i;
> 
> Please make 'i' be an unsigned int. Especially as you are using '%u' in the 
> snprintf.
> 
> 
>> +const char *message = NULL;
>> +struct blkfront_info *info = rinfo->dev_info;
>> +
>> +if (info->nr_ring_pages == 1) {
>> +err = xenbus_printf(xbt, dir, "ring-ref", "%u", 
>> rinfo->ring_ref[0]);
>> +if (err) {
>> +message = "writing ring-ref";
>> +goto abort_transaction;
>> +}
>> +pr_info("%s: write ring-ref:%d\n", dir, rinfo->ring_ref[0]);
> 
> Ewww. No.
> 
>> +} else {
>> +for (i = 0; i < info->nr_ring_pages; i++) {
>> +char ring_ref_name[RINGREF_NAME_LEN];
>> +
>> +snprintf(ring_ref_name, RINGREF_NAME_LEN, "ring-ref%u", 
>> i);
>> +err = xenbus_printf(xbt, dir, ring_ref_name,
>> +"%u", rinfo->ring_ref[i]);
>> +if (err) {
>> +message = "writing ring-ref";
>> +goto abort_transaction;
>> +}
>> +pr_info("%s: write ring-ref:%d\n", dir, 
>> rinfo->ring_ref[i]);
> 
> No no please.
> 
>> +}
>> +}
>> +
>> +err = xenbus_printf(xbt, dir, "event-channel", "%u", rinfo->evtchn);
> 
> That is not right.
> 
> That only creates one. But the blkif.h says (And the example agrees)
> that there are N 'event-channel' for N-rings.
> 
> Shouldn't this be part of the above loop?
> 

No, this loop is only for per-ring each with "multipage".

The loop you want is..

>> +if (err) {
>> +message = "writing event-channel";
>> +goto abort_transaction;
>> +}
>> +pr_info("%s: write event-channel:%d\n", dir, rinfo->evtchn);
> 
> Please no.
> 
>> +
>> +return 0;
>> +
>> +abort_transaction:
>> +xenbus_transaction_end(xbt, 1);
>> +if (message)
>> +xenbus_dev_fatal(info->xbdev, err, "%s", message);
>> +
>> +

Re: [PATCH v4 05/10] xen/blkfront: negotiate number of queues/rings to be used with backend

2015-11-03 Thread Konrad Rzeszutek Wilk
On Wed, Nov 04, 2015 at 09:11:10AM +0800, Bob Liu wrote:
> 
> On 11/04/2015 04:40 AM, Konrad Rzeszutek Wilk wrote:
> > On Mon, Nov 02, 2015 at 12:21:41PM +0800, Bob Liu wrote:
> >> The number of hardware queues for xen/blkfront is set by parameter
> >> 'max_queues'(default 4), while the max value xen/blkback supported is 
> >> notified
> >> through xenstore("multi-queue-max-queues").
> > 
> > That is not right.
> > 
> > s/The number/The max number/
> > 
> > The second part: ",while the max value xen/blkback supported is..". I think
> > you are trying to say: "it is also capped by the max value that
> > the xen/blkback exposes through XenStore key 'multi-queue-max-queues'.
> > 
> >>
> >> The negotiated number is the smaller one and would be written back to 
> >> xenstore
> >> as "multi-queue-num-queues", blkback need to read this negotiated number.
> > 
> > s/blkback need to read/blkback needs to read this/
> > 
> >>
> >> Signed-off-by: Bob Liu 
> >> ---
> >>  drivers/block/xen-blkfront.c | 166 
> >> +++
> >>  1 file changed, 120 insertions(+), 46 deletions(-)
> >>
> >> diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
> >> index 8cc5995..23096d7 100644
> >> --- a/drivers/block/xen-blkfront.c
> >> +++ b/drivers/block/xen-blkfront.c
> >> @@ -98,6 +98,10 @@ static unsigned int xen_blkif_max_segments = 32;
> >>  module_param_named(max, xen_blkif_max_segments, int, S_IRUGO);
> >>  MODULE_PARM_DESC(max, "Maximum amount of segments in indirect requests 
> >> (default is 32)");
> >>  
> >> +static unsigned int xen_blkif_max_queues = 4;
> >> +module_param_named(max_queues, xen_blkif_max_queues, uint, S_IRUGO);
> >> +MODULE_PARM_DESC(max_queues, "Maximum number of hardware queues/rings 
> >> used per virtual disk");
> >> +
> >>  /*
> >>   * Maximum order of pages to be used for the shared ring between front and
> >>   * backend, 4KB page granularity is used.
> >> @@ -113,6 +117,7 @@ MODULE_PARM_DESC(max_ring_page_order, "Maximum order 
> >> of pages to be used for the
> >>   * characters are enough. Define to 20 to keep consist with backend.
> >>   */
> >>  #define RINGREF_NAME_LEN (20)
> >> +#define QUEUE_NAME_LEN (12)
> > 
> > Little bit of documentation please. Why 12? Why not 31415 for example?
> > I presume it is 'queue-%u' and since so that is 7 + 10 (UINT_MAX is
> > 4294967295) = 17!
> > 
> > 
> >>  
> >>  /*
> >>   *  Per-ring info.
> >> @@ -695,7 +700,7 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, 
> >> u16 sector_size,
> >>  
> >>memset(>tag_set, 0, sizeof(info->tag_set));
> >>info->tag_set.ops = _mq_ops;
> >> -  info->tag_set.nr_hw_queues = 1;
> >> +  info->tag_set.nr_hw_queues = info->nr_rings;
> >>info->tag_set.queue_depth =  BLK_RING_SIZE(info);
> >>info->tag_set.numa_node = NUMA_NO_NODE;
> >>info->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
> >> @@ -1352,6 +1357,51 @@ fail:
> >>return err;
> >>  }
> >>  
> >> +static int write_per_ring_nodes(struct xenbus_transaction xbt,
> >> +  struct blkfront_ring_info *rinfo, const char 
> >> *dir)
> >> +{
> >> +  int err, i;
> > 
> > Please make 'i' be an unsigned int. Especially as you are using '%u' in the 
> > snprintf.
> > 
> > 
> >> +  const char *message = NULL;
> >> +  struct blkfront_info *info = rinfo->dev_info;
> >> +
> >> +  if (info->nr_ring_pages == 1) {
> >> +  err = xenbus_printf(xbt, dir, "ring-ref", "%u", 
> >> rinfo->ring_ref[0]);
> >> +  if (err) {
> >> +  message = "writing ring-ref";
> >> +  goto abort_transaction;
> >> +  }
> >> +  pr_info("%s: write ring-ref:%d\n", dir, rinfo->ring_ref[0]);
> > 
> > Ewww. No.
> > 
> >> +  } else {
> >> +  for (i = 0; i < info->nr_ring_pages; i++) {
> >> +  char ring_ref_name[RINGREF_NAME_LEN];
> >> +
> >> +  snprintf(ring_ref_name, RINGREF_NAME_LEN, "ring-ref%u", 
> >> i);
> >> +  err = xenbus_printf(xbt, dir, ring_ref_name,
> >> +  "%u", rinfo->ring_ref[i]);
> >> +  if (err) {
> >> +  message = "writing ring-ref";
> >> +  goto abort_transaction;
> >> +  }
> >> +  pr_info("%s: write ring-ref:%d\n", dir, 
> >> rinfo->ring_ref[i]);
> > 
> > No no please.
> > 
> >> +  }
> >> +  }
> >> +
> >> +  err = xenbus_printf(xbt, dir, "event-channel", "%u", rinfo->evtchn);
> > 
> > That is not right.
> > 
> > That only creates one. But the blkif.h says (And the example agrees)
> > that there are N 'event-channel' for N-rings.
> > 
> > Shouldn't this be part of the above loop?
> > 
> 
> No, this loop is only for per-ring each with "multipage".
> 
> The loop you want is..
> 
> >> +  if (err) {
> >> +  message = "writing event-channel";
> >> +  goto abort_transaction;
> >> +  }
> >> +  pr_info("%s: 

[PATCH v4 05/10] xen/blkfront: negotiate number of queues/rings to be used with backend

2015-11-01 Thread Bob Liu
The number of hardware queues for xen/blkfront is set by parameter
'max_queues'(default 4), while the max value xen/blkback supported is notified
through xenstore("multi-queue-max-queues").

The negotiated number is the smaller one and would be written back to xenstore
as "multi-queue-num-queues", blkback need to read this negotiated number.

Signed-off-by: Bob Liu 
---
 drivers/block/xen-blkfront.c | 166 +++
 1 file changed, 120 insertions(+), 46 deletions(-)

diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 8cc5995..23096d7 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -98,6 +98,10 @@ static unsigned int xen_blkif_max_segments = 32;
 module_param_named(max, xen_blkif_max_segments, int, S_IRUGO);
 MODULE_PARM_DESC(max, "Maximum amount of segments in indirect requests 
(default is 32)");
 
+static unsigned int xen_blkif_max_queues = 4;
+module_param_named(max_queues, xen_blkif_max_queues, uint, S_IRUGO);
+MODULE_PARM_DESC(max_queues, "Maximum number of hardware queues/rings used per 
virtual disk");
+
 /*
  * Maximum order of pages to be used for the shared ring between front and
  * backend, 4KB page granularity is used.
@@ -113,6 +117,7 @@ MODULE_PARM_DESC(max_ring_page_order, "Maximum order of 
pages to be used for the
  * characters are enough. Define to 20 to keep consist with backend.
  */
 #define RINGREF_NAME_LEN (20)
+#define QUEUE_NAME_LEN (12)
 
 /*
  *  Per-ring info.
@@ -695,7 +700,7 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 
sector_size,
 
memset(>tag_set, 0, sizeof(info->tag_set));
info->tag_set.ops = _mq_ops;
-   info->tag_set.nr_hw_queues = 1;
+   info->tag_set.nr_hw_queues = info->nr_rings;
info->tag_set.queue_depth =  BLK_RING_SIZE(info);
info->tag_set.numa_node = NUMA_NO_NODE;
info->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
@@ -1352,6 +1357,51 @@ fail:
return err;
 }
 
+static int write_per_ring_nodes(struct xenbus_transaction xbt,
+   struct blkfront_ring_info *rinfo, const char 
*dir)
+{
+   int err, i;
+   const char *message = NULL;
+   struct blkfront_info *info = rinfo->dev_info;
+
+   if (info->nr_ring_pages == 1) {
+   err = xenbus_printf(xbt, dir, "ring-ref", "%u", 
rinfo->ring_ref[0]);
+   if (err) {
+   message = "writing ring-ref";
+   goto abort_transaction;
+   }
+   pr_info("%s: write ring-ref:%d\n", dir, rinfo->ring_ref[0]);
+   } else {
+   for (i = 0; i < info->nr_ring_pages; i++) {
+   char ring_ref_name[RINGREF_NAME_LEN];
+
+   snprintf(ring_ref_name, RINGREF_NAME_LEN, "ring-ref%u", 
i);
+   err = xenbus_printf(xbt, dir, ring_ref_name,
+   "%u", rinfo->ring_ref[i]);
+   if (err) {
+   message = "writing ring-ref";
+   goto abort_transaction;
+   }
+   pr_info("%s: write ring-ref:%d\n", dir, 
rinfo->ring_ref[i]);
+   }
+   }
+
+   err = xenbus_printf(xbt, dir, "event-channel", "%u", rinfo->evtchn);
+   if (err) {
+   message = "writing event-channel";
+   goto abort_transaction;
+   }
+   pr_info("%s: write event-channel:%d\n", dir, rinfo->evtchn);
+
+   return 0;
+
+abort_transaction:
+   xenbus_transaction_end(xbt, 1);
+   if (message)
+   xenbus_dev_fatal(info->xbdev, err, "%s", message);
+
+   return err;
+}
 
 /* Common code used when first setting up, and when resuming. */
 static int talk_to_blkback(struct xenbus_device *dev,
@@ -1362,7 +1412,6 @@ static int talk_to_blkback(struct xenbus_device *dev,
int err, i;
unsigned int max_page_order = 0;
unsigned int ring_page_order = 0;
-   struct blkfront_ring_info *rinfo;
 
err = xenbus_scanf(XBT_NIL, info->xbdev->otherend,
   "max-ring-page-order", "%u", _page_order);
@@ -1374,7 +1423,8 @@ static int talk_to_blkback(struct xenbus_device *dev,
}
 
for (i = 0; i < info->nr_rings; i++) {
-   rinfo = >rinfo[i];
+   struct blkfront_ring_info *rinfo = >rinfo[i];
+
/* Create shared ring, alloc event channel. */
err = setup_blkring(dev, rinfo);
if (err)
@@ -1388,45 +1438,51 @@ again:
goto destroy_blkring;
}
 
-   if (info->nr_rings == 1) {
-   rinfo = >rinfo[0];
-   if (info->nr_ring_pages == 1) {
-   err = xenbus_printf(xbt, dev->nodename,
-   "ring-ref", "%u", 
rinfo->ring_ref[0]);
-   if (err) {
- 

[PATCH v4 05/10] xen/blkfront: negotiate number of queues/rings to be used with backend

2015-11-01 Thread Bob Liu
The number of hardware queues for xen/blkfront is set by parameter
'max_queues'(default 4), while the max value xen/blkback supported is notified
through xenstore("multi-queue-max-queues").

The negotiated number is the smaller one and would be written back to xenstore
as "multi-queue-num-queues", blkback need to read this negotiated number.

Signed-off-by: Bob Liu 
---
 drivers/block/xen-blkfront.c | 166 +++
 1 file changed, 120 insertions(+), 46 deletions(-)

diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 8cc5995..23096d7 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -98,6 +98,10 @@ static unsigned int xen_blkif_max_segments = 32;
 module_param_named(max, xen_blkif_max_segments, int, S_IRUGO);
 MODULE_PARM_DESC(max, "Maximum amount of segments in indirect requests 
(default is 32)");
 
+static unsigned int xen_blkif_max_queues = 4;
+module_param_named(max_queues, xen_blkif_max_queues, uint, S_IRUGO);
+MODULE_PARM_DESC(max_queues, "Maximum number of hardware queues/rings used per 
virtual disk");
+
 /*
  * Maximum order of pages to be used for the shared ring between front and
  * backend, 4KB page granularity is used.
@@ -113,6 +117,7 @@ MODULE_PARM_DESC(max_ring_page_order, "Maximum order of 
pages to be used for the
  * characters are enough. Define to 20 to keep consist with backend.
  */
 #define RINGREF_NAME_LEN (20)
+#define QUEUE_NAME_LEN (12)
 
 /*
  *  Per-ring info.
@@ -695,7 +700,7 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 
sector_size,
 
memset(>tag_set, 0, sizeof(info->tag_set));
info->tag_set.ops = _mq_ops;
-   info->tag_set.nr_hw_queues = 1;
+   info->tag_set.nr_hw_queues = info->nr_rings;
info->tag_set.queue_depth =  BLK_RING_SIZE(info);
info->tag_set.numa_node = NUMA_NO_NODE;
info->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
@@ -1352,6 +1357,51 @@ fail:
return err;
 }
 
+static int write_per_ring_nodes(struct xenbus_transaction xbt,
+   struct blkfront_ring_info *rinfo, const char 
*dir)
+{
+   int err, i;
+   const char *message = NULL;
+   struct blkfront_info *info = rinfo->dev_info;
+
+   if (info->nr_ring_pages == 1) {
+   err = xenbus_printf(xbt, dir, "ring-ref", "%u", 
rinfo->ring_ref[0]);
+   if (err) {
+   message = "writing ring-ref";
+   goto abort_transaction;
+   }
+   pr_info("%s: write ring-ref:%d\n", dir, rinfo->ring_ref[0]);
+   } else {
+   for (i = 0; i < info->nr_ring_pages; i++) {
+   char ring_ref_name[RINGREF_NAME_LEN];
+
+   snprintf(ring_ref_name, RINGREF_NAME_LEN, "ring-ref%u", 
i);
+   err = xenbus_printf(xbt, dir, ring_ref_name,
+   "%u", rinfo->ring_ref[i]);
+   if (err) {
+   message = "writing ring-ref";
+   goto abort_transaction;
+   }
+   pr_info("%s: write ring-ref:%d\n", dir, 
rinfo->ring_ref[i]);
+   }
+   }
+
+   err = xenbus_printf(xbt, dir, "event-channel", "%u", rinfo->evtchn);
+   if (err) {
+   message = "writing event-channel";
+   goto abort_transaction;
+   }
+   pr_info("%s: write event-channel:%d\n", dir, rinfo->evtchn);
+
+   return 0;
+
+abort_transaction:
+   xenbus_transaction_end(xbt, 1);
+   if (message)
+   xenbus_dev_fatal(info->xbdev, err, "%s", message);
+
+   return err;
+}
 
 /* Common code used when first setting up, and when resuming. */
 static int talk_to_blkback(struct xenbus_device *dev,
@@ -1362,7 +1412,6 @@ static int talk_to_blkback(struct xenbus_device *dev,
int err, i;
unsigned int max_page_order = 0;
unsigned int ring_page_order = 0;
-   struct blkfront_ring_info *rinfo;
 
err = xenbus_scanf(XBT_NIL, info->xbdev->otherend,
   "max-ring-page-order", "%u", _page_order);
@@ -1374,7 +1423,8 @@ static int talk_to_blkback(struct xenbus_device *dev,
}
 
for (i = 0; i < info->nr_rings; i++) {
-   rinfo = >rinfo[i];
+   struct blkfront_ring_info *rinfo = >rinfo[i];
+
/* Create shared ring, alloc event channel. */
err = setup_blkring(dev, rinfo);
if (err)
@@ -1388,45 +1438,51 @@ again:
goto destroy_blkring;
}
 
-   if (info->nr_rings == 1) {
-   rinfo = >rinfo[0];
-   if (info->nr_ring_pages == 1) {
-   err = xenbus_printf(xbt, dev->nodename,
-   "ring-ref", "%u", 
rinfo->ring_ref[0]);
-   if (err) {
-