ibata: get rid of ATA_MAX_QUEUE loop in ata_qc_complete_multiple() v2

ibata: get rid of ATA_MAX_QUEUE loop in ata_qc_complete_multiple() v2

[Jens Axboe]

We very rarely (if ever) complete more than one command in the
sactive mask at the time, even for extremely high IO rates. So
looping over the entire range of possible tags is pointless,
instead use __ffs() to just find the completed tags directly.

Updated to clear the tag from the done_mask instead of shifting
done_mask down as suggested by From: Tejun Heo <htejun@gmail.com>
Verified with a user space tester to produce the same results.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 drivers/ata/libata-core.c |   11 +++++------
 1 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index c924230..ca4d208 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -5031,7 +5031,6 @@ int ata_qc_complete_multiple(struct ata_port *ap, u32 qc_active)
 {
 	int nr_done = 0;
 	u32 done_mask;
-	int i;
 
 	done_mask = ap->qc_active ^ qc_active;
 
@@ -5041,16 +5040,16 @@ int ata_qc_complete_multiple(struct ata_port *ap, u32 qc_active)
 		return -EINVAL;
 	}
 
-	for (i = 0; i < ATA_MAX_QUEUE; i++) {
+	while (done_mask) {
 		struct ata_queued_cmd *qc;
+		unsigned int tag = __ffs(done_mask);
 
-		if (!(done_mask & (1 << i)))
-			continue;
-
-		if ((qc = ata_qc_from_tag(ap, i))) {
+		qc = ata_qc_from_tag(ap, tag);
+		if (qc) {
 			ata_qc_complete(qc);
 			nr_done++;
 		}
+		done_mask &= ~(1 << tag);
 	}
 
 	return nr_done;
-- 
1.6.3.rc0.1.gf800

-- 
Jens Axboe

Re: ibata: get rid of ATA_MAX_QUEUE loop in ata_qc_complete_multiple() v2

[Tejun Heo]

Jens Axboe wrote:
> We very rarely (if ever) complete more than one command in the
> sactive mask at the time, even for extremely high IO rates. So
> looping over the entire range of possible tags is pointless,
> instead use __ffs() to just find the completed tags directly.
> 
> Updated to clear the tag from the done_mask instead of shifting
> done_mask down as suggested by From: Tejun Heo <htejun@gmail.com>
> Verified with a user space tester to produce the same results.
> 
> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

Acked-by: Tejun Heo <tj@kernel.org>

Thanks.

-- 
tejun

Re: ibata: get rid of ATA_MAX_QUEUE loop in ata_qc_complete_multiple() v2

[Jeff Garzik]

Jens Axboe wrote:
> We very rarely (if ever) complete more than one command in the
> sactive mask at the time, even for extremely high IO rates. So
> looping over the entire range of possible tags is pointless,
> instead use __ffs() to just find the completed tags directly.
> 
> Updated to clear the tag from the done_mask instead of shifting
> done_mask down as suggested by From: Tejun Heo <htejun@gmail.com>
> Verified with a user space tester to produce the same results.
> 
> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
> ---
>  drivers/ata/libata-core.c |   11 +++++------
>  1 files changed, 5 insertions(+), 6 deletions(-)

Much cleaner.  Queued...

Separately, I wonder if we shouldn't add code to report when the 
hardware gives us an unknown tag.

The code always correctly handles invalid tags passed to us from 
hardware "if (qc)", but we should probably squawk when that happens, I 
suspect.

	Jeff

Re: ibata: get rid of ATA_MAX_QUEUE loop in ata_qc_complete_multiple() v2

[Jens Axboe]

On Wed, May 20 2009, Jeff Garzik wrote:
> Jens Axboe wrote:
>> We very rarely (if ever) complete more than one command in the
>> sactive mask at the time, even for extremely high IO rates. So
>> looping over the entire range of possible tags is pointless,
>> instead use __ffs() to just find the completed tags directly.
>>
>> Updated to clear the tag from the done_mask instead of shifting
>> done_mask down as suggested by From: Tejun Heo <htejun@gmail.com>
>> Verified with a user space tester to produce the same results.
>>
>> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
>> ---
>>  drivers/ata/libata-core.c |   11 +++++------
>>  1 files changed, 5 insertions(+), 6 deletions(-)
>
> Much cleaner.  Queued...

Thanks!

> Separately, I wonder if we shouldn't add code to report when the  
> hardware gives us an unknown tag.
>
> The code always correctly handles invalid tags passed to us from  
> hardware "if (qc)", but we should probably squawk when that happens, I  
> suspect.

Probably a good idea, it is a sign of bigger problems if the hardware
completes tags that we don't know about.

-- 
Jens Axboe

Re: ibata: get rid of ATA_MAX_QUEUE loop in ata_qc_complete_multiple() v2

[Jeff Garzik]

Jens Axboe wrote:
> We very rarely (if ever) complete more than one command in the
> sactive mask at the time, even for extremely high IO rates. So
> looping over the entire range of possible tags is pointless,
> instead use __ffs() to just find the completed tags directly.
> 
> Updated to clear the tag from the done_mask instead of shifting
> done_mask down as suggested by From: Tejun Heo <htejun@gmail.com>
> Verified with a user space tester to produce the same results.
> 
> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
> ---
>  drivers/ata/libata-core.c |   11 +++++------
>  1 files changed, 5 insertions(+), 6 deletions(-)

applied