On Mon, 2004-10-25 at 00:27, Roland Dreier wrote:
Because the first declaration of convert_mgmt_class() had no body, gcc
doesn't actually inline the function. Fix that by moving the body
before the first use of the function.
Thanks. Applied.
-- Hal
On Fri, 2004-10-22 at 17:25, Roland Dreier wrote:
Hal The registration interface will need to be extended somehow
Hal for this. I don't think we want to add an attribute ID mask
Hal :-) The simplest way I can think of is to add an issm bit to
Hal the registration request
On Fri, 2004-10-22 at 16:26, Roland Dreier wrote:
In any case I think I'll integrate the new MAD stuff on Monday no
matter where it stands, and we can just deal with merging changes back
and forth.
It appears we now (as of late yesterday) need to deal with merging
changes back and forth.
When
Hal What are the other special cases for registration ?
Not just registration... I just meant that having an extra snoop_mad
entry point and a special issm bit and hard-coding different treatment
of SMInfo in the MAD layer starts to smell to me like the MAD layer is
at the wrong level of
Hal OK. It's pretty straightforward to change the MAD layer to
Hal use PLM rather than snoop MAD (and remove snoop_mad (undo
Hal that patch)). Should I post the changes ?
It's my idea so I certainly like the approach :)
Sean, what do you think?
- R.
On Mon, 25 Oct 2004 12:39:36 -0400
Hal Rosenstock [EMAIL PROTECTED] wrote:
OK. It's pretty straightforward to change the MAD layer to use PLM
rather than snoop MAD (and remove snoop_mad (undo that patch)). Should I
post the changes ?
I think that this makes sense.
- Sean
By the way, in case someone else wants to use the same approach,
here's how I make sure my changes build across multiple archs:
I'm using toolchains built with http://www.kegel.com/crosstool/ and
the attached script to make sure my tree builds on i386, x86_64,
ppc64, ia64, ppc, sparc64 and
On Sun, 24 Oct 2004 13:38:01 -0400
Hal Rosenstock [EMAIL PROTECTED] wrote:
ib_mad: In ib_mad_complete_recv, decrement agent reference count when
receive is not fully reassembled, and also when solicited and no
matching request is found. This allows deregistration to complete rather
than
On Mon, 25 Oct 2004 10:08:51 -0700
Roland Dreier [EMAIL PROTECTED] wrote:
Hal OK. It's pretty straightforward to change the MAD layer to
Hal use PLM rather than snoop MAD (and remove snoop_mad (undo
Hal that patch)). Should I post the changes ?
It's my idea so I certainly like
Sean I think that it makes sense, but just to make sure that I'm
Sean clear on this. We want to pass every received MAD to the
Sean HCA driver before any processing has occurred on the MAD,
Sean correct?
That's my plan...
Sean If the MAD is not consumed by the driver, the
On Mon, 2004-10-25 at 13:14, Sean Hefty wrote:
On Sun, 24 Oct 2004 13:38:01 -0400
Hal Rosenstock [EMAIL PROTECTED] wrote:
ib_mad: In ib_mad_complete_recv, decrement agent reference count when
receive is not fully reassembled, and also when solicited and no
matching request is found. This
On Mon, 25 Oct 2004 10:34:09 -0700
Roland Dreier [EMAIL PROTECTED] wrote:
Sean If the MAD is not consumed by the driver, the MAD
Sean layer may update the MAD and call process_local_mad a second
Sean time, correct?
Sure, I guess so -- nothing should break if the MAD layer does
Grant Up to you (or whoever maintains the code). Some drivers
Grant that have their own subdir keep the prefixes. e1000 and
Grant sym2 drivers are the counter examples I had in mind.
Good point... well, I'm getting sick of typing ib_ :)
Also I'd argue that the e1000_ or sym_
On Mon, 2004-10-25 at 14:22, Sean Hefty wrote:
The reference taken for the receive is made by the MAD layer itself, so the client
isn't aware that
one was taken. If the client deregisters the MAD service at the same time that a
MAD is received,
then the reference from the registration
On Mon, 2004-10-25 at 22:12, Roland Dreier wrote:
This is no good:
+ if (wc.status != IB_WC_SUCCESS) {
+ printk(KERN_ERR PFX Completion error %d WRID 0x%Lx\n,
+ wc.status, (unsigned long long)
wc.wr_id);
+ }
15 matches
Mail list logo