* [PATCH] ib/mad: remove Device Mgmt from RMPP class list
@ 2013-07-24 21:44 Ira Weiny
[not found] ` <20130724144426.5a63669ea6107c8a3e6c1867-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
0 siblings, 1 reply; 11+ messages in thread
From: Ira Weiny @ 2013-07-24 21:44 UTC (permalink / raw)
To: linux-rdma-u79uwXL29TY76Z2rM5mHXA
Cc: roland-DgEjT+Ai2ygdnm+yROfE0A, Hal Rosenstock
The specification does not indicate that Device Mgmt is an RMPP class.
Signed-off-by: Ira Weiny <ira.weiny-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/core/mad.c | 1 -
1 files changed, 0 insertions(+), 1 deletions(-)
diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c
index dc3fd1e..309b507 100644
--- a/drivers/infiniband/core/mad.c
+++ b/drivers/infiniband/core/mad.c
@@ -943,7 +943,6 @@ EXPORT_SYMBOL(ib_get_mad_data_offset);
int ib_is_mad_class_rmpp(u8 mgmt_class)
{
if ((mgmt_class == IB_MGMT_CLASS_SUBN_ADM) ||
- (mgmt_class == IB_MGMT_CLASS_DEVICE_MGMT) ||
(mgmt_class == IB_MGMT_CLASS_DEVICE_ADM) ||
(mgmt_class == IB_MGMT_CLASS_BIS) ||
((mgmt_class >= IB_MGMT_CLASS_VENDOR_RANGE2_START) &&
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 11+ messages in thread
* Re: [PATCH] ib/mad: remove Device Mgmt from RMPP class list
[not found] ` <20130724144426.5a63669ea6107c8a3e6c1867-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
@ 2013-07-24 21:59 ` Hal Rosenstock
[not found] ` <51F04E2D.9060708-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
0 siblings, 1 reply; 11+ messages in thread
From: Hal Rosenstock @ 2013-07-24 21:59 UTC (permalink / raw)
To: Ira Weiny
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA, roland-DgEjT+Ai2ygdnm+yROfE0A
On 7/24/2013 5:44 PM, Ira Weiny wrote:
> The specification does not indicate that Device Mgmt is an RMPP class.
See Annex 8; DevMgt class version 2 rather than 1 is currently supported.
-- Hal
> Signed-off-by: Ira Weiny <ira.weiny-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
> ---
> drivers/infiniband/core/mad.c | 1 -
> 1 files changed, 0 insertions(+), 1 deletions(-)
>
> diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c
> index dc3fd1e..309b507 100644
> --- a/drivers/infiniband/core/mad.c
> +++ b/drivers/infiniband/core/mad.c
> @@ -943,7 +943,6 @@ EXPORT_SYMBOL(ib_get_mad_data_offset);
> int ib_is_mad_class_rmpp(u8 mgmt_class)
> {
> if ((mgmt_class == IB_MGMT_CLASS_SUBN_ADM) ||
> - (mgmt_class == IB_MGMT_CLASS_DEVICE_MGMT) ||
> (mgmt_class == IB_MGMT_CLASS_DEVICE_ADM) ||
> (mgmt_class == IB_MGMT_CLASS_BIS) ||
> ((mgmt_class >= IB_MGMT_CLASS_VENDOR_RANGE2_START) &&
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 11+ messages in thread
* RE: [PATCH] ib/mad: remove Device Mgmt from RMPP class list
[not found] ` <51F04E2D.9060708-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
@ 2013-07-24 22:10 ` Weiny, Ira
[not found] ` <2807E5FD2F6FDA4886F6618EAC48510E021B0B9D-8k97q/ur5Z2krb+BlOpmy7fspsVTdybXVpNB7YpNyf8@public.gmane.org>
0 siblings, 1 reply; 11+ messages in thread
From: Weiny, Ira @ 2013-07-24 22:10 UTC (permalink / raw)
To: Hal Rosenstock
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA, roland-DgEjT+Ai2ygdnm+yROfE0A
> -----Original Message-----
> From: Hal Rosenstock [mailto:hal-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org]
> Subject: Re: [PATCH] ib/mad: remove Device Mgmt from RMPP class list
>
> On 7/24/2013 5:44 PM, Ira Weiny wrote:
> > The specification does not indicate that Device Mgmt is an RMPP class.
>
> See Annex 8; DevMgt class version 2 rather than 1 is currently supported.
Could older devices still return version 1? If so the kernel should allow DevMgt without RMPP, correct?
Ira
>
> -- Hal
>
> > Signed-off-by: Ira Weiny <ira.weiny-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
> > ---
> > drivers/infiniband/core/mad.c | 1 -
> > 1 files changed, 0 insertions(+), 1 deletions(-)
> >
> > diff --git a/drivers/infiniband/core/mad.c
> > b/drivers/infiniband/core/mad.c index dc3fd1e..309b507 100644
> > --- a/drivers/infiniband/core/mad.c
> > +++ b/drivers/infiniband/core/mad.c
> > @@ -943,7 +943,6 @@ EXPORT_SYMBOL(ib_get_mad_data_offset);
> > int ib_is_mad_class_rmpp(u8 mgmt_class) {
> > if ((mgmt_class == IB_MGMT_CLASS_SUBN_ADM) ||
> > - (mgmt_class == IB_MGMT_CLASS_DEVICE_MGMT) ||
> > (mgmt_class == IB_MGMT_CLASS_DEVICE_ADM) ||
> > (mgmt_class == IB_MGMT_CLASS_BIS) ||
> > ((mgmt_class >= IB_MGMT_CLASS_VENDOR_RANGE2_START) &&
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [PATCH] ib/mad: remove Device Mgmt from RMPP class list
[not found] ` <2807E5FD2F6FDA4886F6618EAC48510E021B0B9D-8k97q/ur5Z2krb+BlOpmy7fspsVTdybXVpNB7YpNyf8@public.gmane.org>
@ 2013-07-24 22:21 ` Hal Rosenstock
2013-07-24 22:22 ` Hefty, Sean
1 sibling, 0 replies; 11+ messages in thread
From: Hal Rosenstock @ 2013-07-24 22:21 UTC (permalink / raw)
To: Weiny, Ira
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA, roland-DgEjT+Ai2ygdnm+yROfE0A
On 7/24/2013 6:10 PM, Weiny, Ira wrote:
>> -----Original Message-----
>> From: Hal Rosenstock [mailto:hal-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org]
>> Subject: Re: [PATCH] ib/mad: remove Device Mgmt from RMPP class list
>>
>> On 7/24/2013 5:44 PM, Ira Weiny wrote:
>>> The specification does not indicate that Device Mgmt is an RMPP class.
>>
>> See Annex 8; DevMgt class version 2 rather than 1 is currently supported.
>
> Could older devices still return version 1?
Yes, we can change this to support version 1 too.
> If so the kernel should allow DevMgt without RMPP, correct?
Yes. Both versions 1 and 2 DevMgt could be supported.
-- Hal
>
> Ira
>
>>
>> -- Hal
>>
>>> Signed-off-by: Ira Weiny <ira.weiny-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
>>> ---
>>> drivers/infiniband/core/mad.c | 1 -
>>> 1 files changed, 0 insertions(+), 1 deletions(-)
>>>
>>> diff --git a/drivers/infiniband/core/mad.c
>>> b/drivers/infiniband/core/mad.c index dc3fd1e..309b507 100644
>>> --- a/drivers/infiniband/core/mad.c
>>> +++ b/drivers/infiniband/core/mad.c
>>> @@ -943,7 +943,6 @@ EXPORT_SYMBOL(ib_get_mad_data_offset);
>>> int ib_is_mad_class_rmpp(u8 mgmt_class) {
>>> if ((mgmt_class == IB_MGMT_CLASS_SUBN_ADM) ||
>>> - (mgmt_class == IB_MGMT_CLASS_DEVICE_MGMT) ||
>>> (mgmt_class == IB_MGMT_CLASS_DEVICE_ADM) ||
>>> (mgmt_class == IB_MGMT_CLASS_BIS) ||
>>> ((mgmt_class >= IB_MGMT_CLASS_VENDOR_RANGE2_START) &&
>
>
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 11+ messages in thread
* RE: [PATCH] ib/mad: remove Device Mgmt from RMPP class list
[not found] ` <2807E5FD2F6FDA4886F6618EAC48510E021B0B9D-8k97q/ur5Z2krb+BlOpmy7fspsVTdybXVpNB7YpNyf8@public.gmane.org>
2013-07-24 22:21 ` Hal Rosenstock
@ 2013-07-24 22:22 ` Hefty, Sean
[not found] ` <1828884A29C6694DAF28B7E6B8A8237384567CA1-P5GAC/sN6hkd3b2yrw5b5LfspsVTdybXVpNB7YpNyf8@public.gmane.org>
1 sibling, 1 reply; 11+ messages in thread
From: Hefty, Sean @ 2013-07-24 22:22 UTC (permalink / raw)
To: Weiny, Ira, Hal Rosenstock
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA, roland-DgEjT+Ai2ygdnm+yROfE0A
> > See Annex 8; DevMgt class version 2 rather than 1 is currently supported.
>
> Could older devices still return version 1? If so the kernel should allow
> DevMgt without RMPP, correct?
This check has been this way since 2.6.17. I think it's reasonable to say that there aren't any devices using version 1 that are running with Linux.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 11+ messages in thread
* RE: [PATCH] ib/mad: remove Device Mgmt from RMPP class list
[not found] ` <1828884A29C6694DAF28B7E6B8A8237384567CA1-P5GAC/sN6hkd3b2yrw5b5LfspsVTdybXVpNB7YpNyf8@public.gmane.org>
@ 2013-07-24 22:29 ` Weiny, Ira
2013-07-24 22:56 ` Weiny, Ira
1 sibling, 0 replies; 11+ messages in thread
From: Weiny, Ira @ 2013-07-24 22:29 UTC (permalink / raw)
To: Hefty, Sean, Hal Rosenstock
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA, roland-DgEjT+Ai2ygdnm+yROfE0A
Roland,
Please skip this patch. Sean, see below.
> -----Original Message-----
> From: Hefty, Sean
> Sent: Wednesday, July 24, 2013 3:23 PM
> To: Weiny, Ira; Hal Rosenstock
> Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org; roland-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org
> Subject: RE: [PATCH] ib/mad: remove Device Mgmt from RMPP class list
>
> > > See Annex 8; DevMgt class version 2 rather than 1 is currently supported.
> >
> > Could older devices still return version 1? If so the kernel should
> > allow DevMgt without RMPP, correct?
>
> This check has been this way since 2.6.17. I think it's reasonable to say that
> there aren't any devices using version 1 that are running with Linux.
Actually the "check" does not do anything unless you specify an rmpp_version as well.
/* Make sure class supplied is consistent with RMPP */
if (!ib_is_mad_class_rmpp(mad_reg_req->mgmt_class)) {
if (rmpp_version)
goto error1;
}
I did not realize that some management classes optionally support RMPP. So in this case the check is correct.
In some User Space RMPP patches I am working on I wanted to verify that an RMPP management class actually specified rmpp_version. I see that I either need to skip this check or look at the class version as well. :-(
Ira
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 11+ messages in thread
* RE: [PATCH] ib/mad: remove Device Mgmt from RMPP class list
[not found] ` <1828884A29C6694DAF28B7E6B8A8237384567CA1-P5GAC/sN6hkd3b2yrw5b5LfspsVTdybXVpNB7YpNyf8@public.gmane.org>
2013-07-24 22:29 ` Weiny, Ira
@ 2013-07-24 22:56 ` Weiny, Ira
[not found] ` <2807E5FD2F6FDA4886F6618EAC48510E021B1099-8k97q/ur5Z2krb+BlOpmy7fspsVTdybXVpNB7YpNyf8@public.gmane.org>
1 sibling, 1 reply; 11+ messages in thread
From: Weiny, Ira @ 2013-07-24 22:56 UTC (permalink / raw)
To: Hefty, Sean, Hal Rosenstock
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA, roland-DgEjT+Ai2ygdnm+yROfE0A
> -----Original Message-----
> From: Hefty, Sean
> Subject: RE: [PATCH] ib/mad: remove Device Mgmt from RMPP class list
>
> > > See Annex 8; DevMgt class version 2 rather than 1 is currently supported.
> >
> > Could older devices still return version 1? If so the kernel should
> > allow DevMgt without RMPP, correct?
>
> This check has been this way since 2.6.17. I think it's reasonable to say that
> there aren't any devices using version 1 that are running with Linux.
FWIW the ib_srpt module uses a class version of 1:
Ib_srpt.c:
...
reg_req.mgmt_class_version = IB_MGMT_BASE_VERSION;
...
Ira
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 11+ messages in thread
* RE: [PATCH] ib/mad: remove Device Mgmt from RMPP class list
[not found] ` <2807E5FD2F6FDA4886F6618EAC48510E021B1099-8k97q/ur5Z2krb+BlOpmy7fspsVTdybXVpNB7YpNyf8@public.gmane.org>
@ 2013-07-24 23:01 ` Hefty, Sean
[not found] ` <1828884A29C6694DAF28B7E6B8A8237384567D00-P5GAC/sN6hkd3b2yrw5b5LfspsVTdybXVpNB7YpNyf8@public.gmane.org>
0 siblings, 1 reply; 11+ messages in thread
From: Hefty, Sean @ 2013-07-24 23:01 UTC (permalink / raw)
To: Weiny, Ira, Hal Rosenstock
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA, roland-DgEjT+Ai2ygdnm+yROfE0A
> > > > See Annex 8; DevMgt class version 2 rather than 1 is currently supported.
> > >
> > > Could older devices still return version 1? If so the kernel should
> > > allow DevMgt without RMPP, correct?
> >
> > This check has been this way since 2.6.17. I think it's reasonable to say
> that
> > there aren't any devices using version 1 that are running with Linux.
>
> FWIW the ib_srpt module uses a class version of 1:
>
> Ib_srpt.c:
>
> ...
> reg_req.mgmt_class_version = IB_MGMT_BASE_VERSION;
> ...
So, then this just happens to work because of some other check? If that's so, then I agree with Hal, in that we can add the class version to the check.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 11+ messages in thread
* RE: [PATCH] ib/mad: remove Device Mgmt from RMPP class list
[not found] ` <1828884A29C6694DAF28B7E6B8A8237384567D00-P5GAC/sN6hkd3b2yrw5b5LfspsVTdybXVpNB7YpNyf8@public.gmane.org>
@ 2013-07-24 23:05 ` Weiny, Ira
[not found] ` <2807E5FD2F6FDA4886F6618EAC48510E021B1166-8k97q/ur5Z2krb+BlOpmy7fspsVTdybXVpNB7YpNyf8@public.gmane.org>
0 siblings, 1 reply; 11+ messages in thread
From: Weiny, Ira @ 2013-07-24 23:05 UTC (permalink / raw)
To: Hefty, Sean, Hal Rosenstock
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA, roland-DgEjT+Ai2ygdnm+yROfE0A
> -----Original Message-----
> From: Hefty, Sean
> Subject: RE: [PATCH] ib/mad: remove Device Mgmt from RMPP class list
>
> > > > > See Annex 8; DevMgt class version 2 rather than 1 is currently
> supported.
> > > >
> > > > Could older devices still return version 1? If so the kernel
> > > > should allow DevMgt without RMPP, correct?
> > >
> > > This check has been this way since 2.6.17. I think it's reasonable
> > > to say
> > that
> > > there aren't any devices using version 1 that are running with Linux.
> >
> > FWIW the ib_srpt module uses a class version of 1:
> >
> > Ib_srpt.c:
> >
> > ...
> > reg_req.mgmt_class_version = IB_MGMT_BASE_VERSION;
> ...
>
> So, then this just happens to work because of some other check? If that's so,
> then I agree with Hal, in that we can add the class version to the check.
I think this works because the MAD stack triggers off of rmpp_version (in the agent) and RMPP_ACTIVE (in the individual MAD's). Since rmpp_version == 0 in this registration and likely all the MAD sent have a 0'ed out RMPP Header (ie the MAD stack thinks all MADs are RMPP _in_active) I think the stack passes all the MAD's without invoking the RMPP processing.
But I have never run this ib_srpt code...
Ira
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [PATCH] ib/mad: remove Device Mgmt from RMPP class list
[not found] ` <2807E5FD2F6FDA4886F6618EAC48510E021B1166-8k97q/ur5Z2krb+BlOpmy7fspsVTdybXVpNB7YpNyf8@public.gmane.org>
@ 2013-07-25 8:20 ` Bart Van Assche
[not found] ` <51F0DFBE.10608-HInyCGIudOg@public.gmane.org>
0 siblings, 1 reply; 11+ messages in thread
From: Bart Van Assche @ 2013-07-25 8:20 UTC (permalink / raw)
To: Weiny, Ira
Cc: Hefty, Sean, Hal Rosenstock, linux-rdma-u79uwXL29TY76Z2rM5mHXA,
roland-DgEjT+Ai2ygdnm+yROfE0A, Vu Pham, Sagi Grimberg
On 07/25/13 01:05, Weiny, Ira wrote:
>> -----Original Message-----
>> From: Hefty, Sean
>> Subject: RE: [PATCH] ib/mad: remove Device Mgmt from RMPP class list
>>
>>>>>> See Annex 8; DevMgt class version 2 rather than 1 is currently
>> supported.
>>>>>
>>>>> Could older devices still return version 1? If so the kernel
>>>>> should allow DevMgt without RMPP, correct?
>>>>
>>>> This check has been this way since 2.6.17. I think it's reasonable
>>>> to say
>>> that
>>>> there aren't any devices using version 1 that are running with Linux.
>>>
>>> FWIW the ib_srpt module uses a class version of 1:
>>>
>>> Ib_srpt.c:
>>>
>>> ...
>>> reg_req.mgmt_class_version = IB_MGMT_BASE_VERSION;
>> ...
>>
>> So, then this just happens to work because of some other check? If that's so,
>> then I agree with Hal, in that we can add the class version to the check.
>
> I think this works because the MAD stack triggers off of rmpp_version (in the
> agent) and RMPP_ACTIVE (in the individual MAD's). Since rmpp_version
> == 0 in this registration and likely all the MAD sent have a 0'ed out
> RMPP Header (ie the MAD stack thinks all MADs are RMPP _in_active) I
> think the stack passes all the MAD's without invoking the RMPP
> processing.
Changing the mgmt_class_version in ib_srpt.c from 1 into 2 would break
existing SRP device management clients (srp_daemon and ibsrpdm) since
these set mgmt_class_version to 1.
I'm not sure changing the rmpp_version argument in the
ib_register_mad_agent() call in ib_srpt.c would be sufficient to enable
RMPP for DM MAD's. Wouldn't the clients (srp_daemon and ibsrpdm) have to
be updated as well to set the rmpp_version in the MAD header as well ?
Bart.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [PATCH] ib/mad: remove Device Mgmt from RMPP class list
[not found] ` <51F0DFBE.10608-HInyCGIudOg@public.gmane.org>
@ 2013-07-25 10:26 ` Hal Rosenstock
0 siblings, 0 replies; 11+ messages in thread
From: Hal Rosenstock @ 2013-07-25 10:26 UTC (permalink / raw)
To: Bart Van Assche
Cc: Weiny, Ira, Hefty, Sean, linux-rdma-u79uwXL29TY76Z2rM5mHXA,
roland-DgEjT+Ai2ygdnm+yROfE0A, Vu Pham, Sagi Grimberg
On 7/25/2013 4:20 AM, Bart Van Assche wrote:
> On 07/25/13 01:05, Weiny, Ira wrote:
>>> -----Original Message-----
>>> From: Hefty, Sean
>>> Subject: RE: [PATCH] ib/mad: remove Device Mgmt from RMPP class list
>>>
>>>>>>> See Annex 8; DevMgt class version 2 rather than 1 is currently
>>> supported.
>>>>>>
>>>>>> Could older devices still return version 1? If so the kernel
>>>>>> should allow DevMgt without RMPP, correct?
>>>>>
>>>>> This check has been this way since 2.6.17. I think it's reasonable
>>>>> to say
>>>> that
>>>>> there aren't any devices using version 1 that are running with Linux.
>>>>
>>>> FWIW the ib_srpt module uses a class version of 1:
>>>>
>>>> Ib_srpt.c:
>>>>
>>>> ...
>>>> reg_req.mgmt_class_version = IB_MGMT_BASE_VERSION;
>>> ...
>>>
>>> So, then this just happens to work because of some other check? If
>>> that's so,
>>> then I agree with Hal, in that we can add the class version to the
>>> check.
>>
>> I think this works because the MAD stack triggers off of rmpp_version
>> (in the
>> agent) and RMPP_ACTIVE (in the individual MAD's). Since rmpp_version
>> == 0 in this registration and likely all the MAD sent have a 0'ed out
>> RMPP Header (ie the MAD stack thinks all MADs are RMPP _in_active) I
>> think the stack passes all the MAD's without invoking the RMPP
>> processing.
>
> Changing the mgmt_class_version in ib_srpt.c from 1 into 2 would break
> existing SRP device management clients (srp_daemon and ibsrpdm) since
> these set mgmt_class_version to 1.
>
> I'm not sure changing the rmpp_version argument in the
> ib_register_mad_agent() call in ib_srpt.c would be sufficient to enable
> RMPP for DM MAD's. Wouldn't the clients (srp_daemon and ibsrpdm) have to
> be updated as well to set the rmpp_version in the MAD header as well ?
There's a whole set of rules on DevMgt class version backward
compatibility in Annex A8.
I think it's simpler to continue use of class version 1 for DevMgt.
There may be a modification to the kernel MAD module to indicate that
for DevMgt class version 1 is not RMPP capable whereas class version 2
is. I think that's the only takeaway. This should have no impact on any
DevMgt clients.
-- Hal
> Bart.
>
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 11+ messages in thread
end of thread, other threads:[~2013-07-25 10:26 UTC | newest]
Thread overview: 11+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2013-07-24 21:44 [PATCH] ib/mad: remove Device Mgmt from RMPP class list Ira Weiny
[not found] ` <20130724144426.5a63669ea6107c8a3e6c1867-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
2013-07-24 21:59 ` Hal Rosenstock
[not found] ` <51F04E2D.9060708-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
2013-07-24 22:10 ` Weiny, Ira
[not found] ` <2807E5FD2F6FDA4886F6618EAC48510E021B0B9D-8k97q/ur5Z2krb+BlOpmy7fspsVTdybXVpNB7YpNyf8@public.gmane.org>
2013-07-24 22:21 ` Hal Rosenstock
2013-07-24 22:22 ` Hefty, Sean
[not found] ` <1828884A29C6694DAF28B7E6B8A8237384567CA1-P5GAC/sN6hkd3b2yrw5b5LfspsVTdybXVpNB7YpNyf8@public.gmane.org>
2013-07-24 22:29 ` Weiny, Ira
2013-07-24 22:56 ` Weiny, Ira
[not found] ` <2807E5FD2F6FDA4886F6618EAC48510E021B1099-8k97q/ur5Z2krb+BlOpmy7fspsVTdybXVpNB7YpNyf8@public.gmane.org>
2013-07-24 23:01 ` Hefty, Sean
[not found] ` <1828884A29C6694DAF28B7E6B8A8237384567D00-P5GAC/sN6hkd3b2yrw5b5LfspsVTdybXVpNB7YpNyf8@public.gmane.org>
2013-07-24 23:05 ` Weiny, Ira
[not found] ` <2807E5FD2F6FDA4886F6618EAC48510E021B1166-8k97q/ur5Z2krb+BlOpmy7fspsVTdybXVpNB7YpNyf8@public.gmane.org>
2013-07-25 8:20 ` Bart Van Assche
[not found] ` <51F0DFBE.10608-HInyCGIudOg@public.gmane.org>
2013-07-25 10:26 ` Hal Rosenstock
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.