Re: [openib-general] IB/ipath - Implement new verbs DMA mapping functions

2006-11-12 Thread Muli Ben-Yehuda
On Thu, Nov 02, 2006 at 02:30:26PM -0800, Ralph Campbell wrote: +static dma_addr_t ipath_dma_map_single(struct ib_device *dev, +void *cpu_addr, size_t size, +enum dma_data_direction direction) +{ + BUG_ON(direction

Re: [openib-general] Installation on openSUSE 10.2 Beta1 fails

2006-11-12 Thread Moni Levy
On 11/10/06, Diego Guella [EMAIL PROTECTED] wrote: Hi Vladimir, Thanks for your answer. I have installed: compat-libstdc++ (version 5.0.7-35) libstdc++-32bit (version 4.1.2_20060705-2) libstdc++41 (version 4.1.2_20061024-3) libstdc++41-devel (version 4.1.2_20061024-3) libstdc++-devel

Re: [openib-general] [PATCH] osm: comparing InformInfo records

2006-11-12 Thread Yevgeny Kliteynik
Hal Rosenstock wrote: Hi Yevgeny, On Mon, 2006-11-06 at 02:00, Yevgeny Kliteynik wrote: Hi Hal [From Vu Pham] 1. sending InformInfo set subscribe for trap 64,65,144 - this works; however, osm.log outputs wrong value for subscribe field What code issues these subscriptions ? How

[openib-general] [PATCH v2] osm: comparing InformInfo records

2006-11-12 Thread Yevgeny Kliteynik
Hi Hal Here's the fixed InformInfo patch Yevgeny Signed-off-by: Yevgeny Kliteynik [EMAIL PROTECTED] Index: opensm/osm_inform.c === --- opensm/osm_inform.c (revision 10100) +++ opensm/osm_inform.c (working copy) @@ -206,30 +206,123

[openib-general] Fwd: [ANNOUNCE] GIT 1.4.3.5

2006-11-12 Thread Michael S. Tsirkin
FYI I don't see any updates openfabrics server needs. -- MST ---BeginMessage--- The latest maintenance release GIT 1.4.3.5 is available at the usual places: http://www.kernel.org/pub/software/scm/git/ git-1.4.3.5.tar.{gz,bz2} (tarball)

[openib-general] ehca build on 2.6.18.2??

2006-11-12 Thread Troy Benjegerdes
what is up with subversion? it does not build with errors like this: CC [M] drivers/infiniband/core/uverbs_main.o drivers/infiniband/core/uverbs_main.c: In function 'uverbs_event_get_sb': drivers/infiniband/core/uverbs_main.c:811: error: too few arguments to function 'get_sb_pseudo'

Re: [openib-general] ehca build on 2.6.18.2??

2006-11-12 Thread Troy Benjegerdes
Um. So I built openib-1.1 from the OFED-1.1 tarball, and now I get: * p5l9:/usr/src/openib-1.1/src/userspace/libehca# ibv_devinfo libibverbs: Warning: no userspace device-specific driver found for uverbs0 driver search path: /usr/local/lib/infiniband No IB devices found On Nov 12,

Re: [openib-general] ehca build on 2.6.18.2??

2006-11-12 Thread Tziporet Koren
Troy Benjegerdes wrote: Um. So I built openib-1.1 from the OFED-1.1 tarball, and now I get: * p5l9:/usr/src/openib-1.1/src/userspace/libehca# ibv_devinfo libibverbs: Warning: no userspace device-specific driver found for uverbs0 driver search path: /usr/local/lib/infiniband No

[openib-general] compile error

2006-11-12 Thread zhu shi song
openib src: svn the latest from openfabrics kernel : 2.6.18 FC5 error: ipoib_multicast.c: in struct net_device there is no xmit_lock member name how to handle it? tks zhu Cheap talk? Check out Yahoo!

Re: [openib-general] [Fwd: [PATCH] RDMA/iwcm: Fix memory leak]

2006-11-12 Thread Krishna Kumar2
Hi Tom, if (len) kfree(ptr) or if (ptr) kfree(ptr) is correct is contingent upon how you couple the two variables. But I don't' think this has anything to do with the Roland's point. That is correct. I stated somewhat differently by saying that the two variables may not be

Re: [openib-general] [PATCH] RDMA/iwcm: Get rid of extra call to list_empty()

2006-11-12 Thread Krishna Kumar2
Hi Tom Sean, There may be a race here, but... Why wouldn't the second call into cm_work_handler simply find the list empty on entry into the call? Basically, you've got a free work queue element sitting on the iwcm_wq. What typically would happen is you'd end up corrupting the list

Re: [openib-general] [PATCH 1/6] Add pci_find_ht_capability() for finding Hypertransport capabilities

2006-11-12 Thread Michael Ellerman
On Thu, 2006-11-09 at 09:01 +0100, Segher Boessenkool wrote: +int pci_find_next_ht_capability(struct pci_dev *dev, int pos, int ht_cap) +{ + int rc; + u8 cap, mask; + + if (ht_cap == HT_CAPTYPE_SLAVE || ht_cap == HT_CAPTYPE_HOST) + mask = HT_3BIT_CAP_MASK; +

Re: [openib-general] [PATCH 5/6] Use pci_find_ht_capability() in drivers/pci/quirks.c

2006-11-12 Thread Michael Ellerman
On Thu, 2006-11-09 at 15:43 +0100, Segher Boessenkool wrote: While yes, we should not in general add new workarounds before we need them, for this quirk, you should keep the original functionality, unless you wrote the quirk, or unless you have the hardware that needs it and you can

Re: [openib-general] [PATCH 5/6] Use pci_find_ht_capability() in drivers/pci/quirks.c

2006-11-12 Thread Benjamin Herrenschmidt
It's not pretty I admit. pci_find_next_ht_capability() would also take a ttl, and pass it through to pci_find_next_capability(). AFAICT that would avoid any infinite hang scenarios? What if we didn't try to solve a problem we don't have ? Have we yet encountered an HT device with that sort

Re: [openib-general] ehca build on 2.6.18.2??

2006-11-12 Thread Or Gerlitz
Troy Benjegerdes wrote: what is up with subversion? it does not build with errors like this: CC [M] drivers/infiniband/core/uverbs_main.o drivers/infiniband/core/uverbs_main.c: In function 'uverbs_event_get_sb': drivers/infiniband/core/uverbs_main.c:811: error: too few arguments to

Re: [openib-general] compile error

2006-11-12 Thread Or Gerlitz
zhu shi song wrote: openib src: svn the latest from openfabrics kernel : 2.6.18 FC5 error: ipoib_multicast.c: in struct net_device there is no xmit_lock member name how to handle it? Did you have any problems using the IB code that comes with your OS/kernel ? = snip