Hi Roland,

I got another question about your code for mthca HCA. In the 
"mthca_provider.c", the functions "mthca_create_cq(struct ib_device 
*ibdev, int entries, struct ib_ucontext *context, struct ib_udata *udata)" 
and "mthca_alloc_pd(struct ib_device *ibdev, struct ib_ucontext *context, 
struct ib_udata *udata)" all have a parameter "ib_ucontext*", while in the 
"Verbs.c", the calling functions "ib_create_cq" and "ib_alloc_pd" all pass 
"NULL" to this parameter, is the " ib_ucontext *" only needed for fast 
path operation, in which situation the user application can write directly 
to user space? If it's true, how to set up the fast path operation in the 
driver environment?

Thanks!
Yicheng




Roland Dreier <[EMAIL PROTECTED]> 
01/04/2008 02:45 PM

To
Yicheng Jia <[EMAIL PROTECTED]>
cc
[email protected], Jack Morgenstein <[EMAIL PROTECTED]>
Subject
Re: [ofa-general] synchronize commands issued to MTHCA






 > I'm using Duo-core Xeon and I just grep the source of "mmiowb()" in 
kernel 
 > 2.6.23 include/asm-x86_64 /io.h and found that this function does 
nothing 
 > on x86_64 platform, is it true?

Yes -- this is why I kept referring to large SGI Altix systems.

 - R.

_____________________________________________________________________________
Scanned by IBM Email Security Management Services powered by MessageLabs. 
For more information please visit http://www.ers.ibm.com
_____________________________________________________________________________

_______________________________________________
general mailing list
[email protected]
http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general

To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general

Reply via email to