Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1597188 > unrolled thread
| Started by | Greg Kroah-Hartman <gregkh@linuxfoundation.org> |
|---|---|
| First post | 2017-03-10 12:50 +0100 |
| Last post | 2017-03-10 16:40 +0100 |
| Articles | 4 — 3 participants |
Back to article view | Back to linux.kernel
This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by
below is the oldest one visible, not the original post.
[PATCH 4.4 34/91] scsi: storvsc: use tagged SRB requests if supported by the device Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-03-10 12:50 +0100
Re: [PATCH 4.4 34/91] scsi: storvsc: use tagged SRB requests if supported by the device Ben Hutchings <ben@decadent.org.uk> - 2017-03-10 16:00 +0100
Re: [PATCH 4.4 34/91] scsi: storvsc: use tagged SRB requests if supported by the device Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-03-10 16:30 +0100
RE: [PATCH 4.4 34/91] scsi: storvsc: use tagged SRB requests if supported by the device KY Srinivasan <kys@microsoft.com> - 2017-03-10 16:40 +0100
| From | Greg Kroah-Hartman <gregkh@linuxfoundation.org> |
|---|---|
| Date | 2017-03-10 12:50 +0100 |
| Subject | [PATCH 4.4 34/91] scsi: storvsc: use tagged SRB requests if supported by the device |
| Message-ID | <tjrdw-3oE-33@gated-at.bofh.it> |
4.4-stable review patch. If anyone has any objections, please let me know.
------------------
From: Long Li <longli@microsoft.com>
commit 3cd6d3d9b1abab8dcdf0800224ce26daac24eea2 upstream.
Properly set SRB flags when hosting device supports tagged queuing.
This patch improves the performance on Fiber Channel disks.
Signed-off-by: Long Li <longli@microsoft.com>
Reviewed-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/scsi/storvsc_drv.c | 9 +++++++++
1 file changed, 9 insertions(+)
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -135,6 +135,8 @@ struct hv_fc_wwn_packet {
#define SRB_FLAGS_PORT_DRIVER_RESERVED 0x0F000000
#define SRB_FLAGS_CLASS_DRIVER_RESERVED 0xF0000000
+#define SP_UNTAGGED ((unsigned char) ~0)
+#define SRB_SIMPLE_TAG_REQUEST 0x20
/*
* Platform neutral description of a scsi request -
@@ -1409,6 +1411,13 @@ static int storvsc_queuecommand(struct S
vm_srb->win8_extension.srb_flags |=
SRB_FLAGS_DISABLE_SYNCH_TRANSFER;
+ if (scmnd->device->tagged_supported) {
+ vm_srb->win8_extension.srb_flags |=
+ (SRB_FLAGS_QUEUE_ACTION_ENABLE | SRB_FLAGS_NO_QUEUE_FREEZE);
+ vm_srb->win8_extension.queue_tag = SP_UNTAGGED;
+ vm_srb->win8_extension.queue_action = SRB_SIMPLE_TAG_REQUEST;
+ }
+
/* Build the SRB */
switch (scmnd->sc_data_direction) {
case DMA_TO_DEVICE:
[toc] | [next] | [standalone]
| From | Ben Hutchings <ben@decadent.org.uk> |
|---|---|
| Date | 2017-03-10 16:00 +0100 |
| Subject | Re: [PATCH 4.4 34/91] scsi: storvsc: use tagged SRB requests if supported by the device |
| Message-ID | <tjubn-5v7-13@gated-at.bofh.it> |
| In reply to | #1597188 |
[Multipart message — attachments visible in raw view] — view raw
On Fri, 2017-03-10 at 10:08 +0100, Greg Kroah-Hartman wrote: > 4.4-stable review patch. If anyone has any objections, please let me know. > > ------------------ > > From: Long Li <longli@microsoft.com> > > commit 3cd6d3d9b1abab8dcdf0800224ce26daac24eea2 upstream. > > Properly set SRB flags when hosting device supports tagged queuing. > This patch improves the performance on Fiber Channel disks. [...] This looks more like a feature/optimisation than a bug fix. Is this really within the stable rules? Ben. -- Ben Hutchings If you seem to know what you are doing, you'll be given more to do.
[toc] | [prev] | [next] | [standalone]
| From | Greg Kroah-Hartman <gregkh@linuxfoundation.org> |
|---|---|
| Date | 2017-03-10 16:30 +0100 |
| Subject | Re: [PATCH 4.4 34/91] scsi: storvsc: use tagged SRB requests if supported by the device |
| Message-ID | <tjuEq-5UC-27@gated-at.bofh.it> |
| In reply to | #1597900 |
On Fri, Mar 10, 2017 at 02:56:59PM +0000, Ben Hutchings wrote: > On Fri, 2017-03-10 at 10:08 +0100, Greg Kroah-Hartman wrote: > > 4.4-stable review patch. If anyone has any objections, please let me know. > > > > ------------------ > > > > From: Long Li <longli@microsoft.com> > > > > commit 3cd6d3d9b1abab8dcdf0800224ce26daac24eea2 upstream. > > > > Properly set SRB flags when hosting device supports tagged queuing. > > This patch improves the performance on Fiber Channel disks. > [...] > > This looks more like a feature/optimisation than a bug fix. Is this > really within the stable rules? Making things work properly (i.e. i/o does not suck anymore), is ok for stable stuff. KY, that's the case here, right? thanks, greg k-h
[toc] | [prev] | [next] | [standalone]
| From | KY Srinivasan <kys@microsoft.com> |
|---|---|
| Date | 2017-03-10 16:40 +0100 |
| Subject | RE: [PATCH 4.4 34/91] scsi: storvsc: use tagged SRB requests if supported by the device |
| Message-ID | <tjuO6-5ZM-29@gated-at.bofh.it> |
| In reply to | #1597917 |
> -----Original Message----- > From: Greg Kroah-Hartman [mailto:gregkh@linuxfoundation.org] > Sent: Friday, March 10, 2017 7:22 AM > To: Ben Hutchings <ben@decadent.org.uk> > Cc: linux-kernel@vger.kernel.org; stable@vger.kernel.org; Long Li > <longli@microsoft.com>; KY Srinivasan <kys@microsoft.com>; Martin K. > Petersen <martin.petersen@oracle.com> > Subject: Re: [PATCH 4.4 34/91] scsi: storvsc: use tagged SRB requests if > supported by the device > > On Fri, Mar 10, 2017 at 02:56:59PM +0000, Ben Hutchings wrote: > > On Fri, 2017-03-10 at 10:08 +0100, Greg Kroah-Hartman wrote: > > > 4.4-stable review patch. If anyone has any objections, please let me > know. > > > > > > ------------------ > > > > > > From: Long Li <longli@microsoft.com> > > > > > > commit 3cd6d3d9b1abab8dcdf0800224ce26daac24eea2 upstream. > > > > > > Properly set SRB flags when hosting device supports tagged queuing. > > > This patch improves the performance on Fiber Channel disks. > > [...] > > > > This looks more like a feature/optimisation than a bug fix. Is this > > really within the stable rules? > > Making things work properly (i.e. i/o does not suck anymore), is ok for > stable stuff. KY, that's the case here, right? If I recall correctly, this was needed for Fibre Channel SANs where without this fix the performance was so bad to be almost unusable. K. Y > > thanks, > > greg k-h
[toc] | [prev] | [standalone]
Back to top | Article view | linux.kernel
csiph-web