On 4/15/2015 8:20 PM, Devesh Sharma wrote:
-Original Message-
From: linux-rdma-ow...@vger.kernel.org [mailto:linux-rdma-
ow...@vger.kernel.org] On Behalf Of Or Gerlitz
Sent: Thursday, April 02, 2015 4:09 PM
To: Roland Dreier; Doug Ledford
Cc: linux-rdma@vger.kernel.org; Erez Shitrit; Tal
Use raw management helpers to reform IB-core mad/agent/user_mad.
Cc: Steve Wise sw...@opengridcomputing.com
Cc: Tom Talpey t...@talpey.com
Cc: Jason Gunthorpe jguntho...@obsidianresearch.com
Cc: Doug Ledford dledf...@redhat.com
Cc: Ira Weiny ira.we...@intel.com
Cc: Sean Hefty
Introduce helper cap_ib_smi() to help us check if the port of an
IB device support Infiniband Subnet Management Interface.
Cc: Steve Wise sw...@opengridcomputing.com
Cc: Tom Talpey t...@talpey.com
Cc: Jason Gunthorpe jguntho...@obsidianresearch.com
Cc: Doug Ledford dledf...@redhat.com
Cc: Ira
Use raw management helpers to reform rest part in IB-core cma.
Cc: Steve Wise sw...@opengridcomputing.com
Cc: Tom Talpey t...@talpey.com
Cc: Jason Gunthorpe jguntho...@obsidianresearch.com
Cc: Doug Ledford dledf...@redhat.com
Cc: Ira Weiny ira.we...@intel.com
Cc: Sean Hefty sean.he...@intel.com
Hi, Hal
On 04/15/2015 08:36 PM, Hal Rosenstock wrote:
On 4/13/2015 8:22 AM, Michael Wang wrote:
[snip]
__attribute_const__ enum rdma_transport_type
@@ -1501,6 +1504,8 @@ struct ib_device {
int(*query_port)(struct ib_device *device,
Since v3:
* Apply suggestions from Sean, Ira, Jason, thanks for the comments :-)
and please remind me if I missed anything :-P
* No more cap_XX_dev(), all the check are per-port now, use port 1 for
cases only care about the cm type, can't support mixing cm type device
in future.
Use raw management helpers to reform mcast related part in IB-core cma.
Cc: Steve Wise sw...@opengridcomputing.com
Cc: Tom Talpey t...@talpey.com
Cc: Jason Gunthorpe jguntho...@obsidianresearch.com
Cc: Doug Ledford dledf...@redhat.com
Cc: Ira Weiny ira.we...@intel.com
Cc: Sean Hefty
Use raw management helpers to reform IB-core verbs/uverbs_cmd/sysfs.
Cc: Steve Wise sw...@opengridcomputing.com
Cc: Tom Talpey t...@talpey.com
Cc: Jason Gunthorpe jguntho...@obsidianresearch.com
Cc: Doug Ledford dledf...@redhat.com
Cc: Ira Weiny ira.we...@intel.com
Cc: Sean Hefty
Use raw management helpers to reform cm related part in IB-core cma/ucm.
These checks focus on the device cm type rather than the port capability,
directly pass port 1 works currently, but can't support mixing cm type
device in future.
Cc: Steve Wise sw...@opengridcomputing.com
Cc: Tom Talpey
Use raw management helpers to reform IB-core sa_query.
Cc: Steve Wise sw...@opengridcomputing.com
Cc: Tom Talpey t...@talpey.com
Cc: Jason Gunthorpe jguntho...@obsidianresearch.com
Cc: Doug Ledford dledf...@redhat.com
Cc: Ira Weiny ira.we...@intel.com
Cc: Sean Hefty sean.he...@intel.com
Use raw management helpers to reform IB-ulp ipoib.
Cc: Steve Wise sw...@opengridcomputing.com
Cc: Tom Talpey t...@talpey.com
Cc: Jason Gunthorpe jguntho...@obsidianresearch.com
Cc: Doug Ledford dledf...@redhat.com
Cc: Ira Weiny ira.we...@intel.com
Cc: Sean Hefty sean.he...@intel.com
Use raw management helpers to reform IB-core cm.
Cc: Steve Wise sw...@opengridcomputing.com
Cc: Tom Talpey t...@talpey.com
Cc: Jason Gunthorpe jguntho...@obsidianresearch.com
Cc: Doug Ledford dledf...@redhat.com
Cc: Ira Weiny ira.we...@intel.com
Cc: Sean Hefty sean.he...@intel.com
Signed-off-by:
Use raw management helpers to reform IB-core multicast.
Cc: Steve Wise sw...@opengridcomputing.com
Cc: Tom Talpey t...@talpey.com
Cc: Jason Gunthorpe jguntho...@obsidianresearch.com
Cc: Doug Ledford dledf...@redhat.com
Cc: Ira Weiny ira.we...@intel.com
Cc: Sean Hefty sean.he...@intel.com
-Original Message-
From: Erez Shitrit [mailto:ere...@dev.mellanox.co.il]
Sent: Thursday, April 16, 2015 12:14 PM
To: Devesh Sharma; Or Gerlitz; Roland Dreier; Doug Ledford
Cc: linux-rdma@vger.kernel.org; Erez Shitrit; Tal Alon; Amir Vadai
Subject: Re: [PATCH for-next 3/6] IB/ipoib:
Reform cma_acquire_dev() with management helpers, introduce
cma_validate_port() to make the code more clean.
Cc: Steve Wise sw...@opengridcomputing.com
Cc: Tom Talpey t...@talpey.com
Cc: Jason Gunthorpe jguntho...@obsidianresearch.com
Cc: Doug Ledford dledf...@redhat.com
Cc: Ira Weiny
Reserve the legacy transport type for the 'transport' member
of 'struct rdma_dev_addr' until we make sure this is no
longer needed.
Cc: Steve Wise sw...@opengridcomputing.com
Cc: Tom Talpey t...@talpey.com
Cc: Jason Gunthorpe jguntho...@obsidianresearch.com
Cc: Doug Ledford dledf...@redhat.com
Introduce helper cap_iw_cm() to help us check if the port of an
IB device support IWARP Communication Manager.
Cc: Steve Wise sw...@opengridcomputing.com
Cc: Tom Talpey t...@talpey.com
Cc: Jason Gunthorpe jguntho...@obsidianresearch.com
Cc: Doug Ledford dledf...@redhat.com
Cc: Ira Weiny
Introduce helper cap_ipoib() to help us check if the port of an
IB device support IP over Infiniband.
Cc: Steve Wise sw...@opengridcomputing.com
Cc: Tom Talpey t...@talpey.com
Cc: Jason Gunthorpe jguntho...@obsidianresearch.com
Cc: Doug Ledford dledf...@redhat.com
Cc: Ira Weiny
Introduce helper cap_ib_sa() to help us check if the port of an
IB device support Infiniband Subnet Administrator.
Cc: Steve Wise sw...@opengridcomputing.com
Cc: Tom Talpey t...@talpey.com
Cc: Jason Gunthorpe jguntho...@obsidianresearch.com
Cc: Doug Ledford dledf...@redhat.com
Cc: Ira Weiny
Introduce helper cap_af_ib() to help us check if the port of an
IB device support Native Infiniband Address.
Cc: Steve Wise sw...@opengridcomputing.com
Cc: Tom Talpey t...@talpey.com
Cc: Jason Gunthorpe jguntho...@obsidianresearch.com
Cc: Doug Ledford dledf...@redhat.com
Cc: Ira Weiny
Introduce helper cap_read_multi_sge() to help us check if the port of an
IB device support RDMA Read Multiple Scatter-Gather Entries.
Cc: Steve Wise sw...@opengridcomputing.com
Cc: Tom Talpey t...@talpey.com
Cc: Jason Gunthorpe jguntho...@obsidianresearch.com
Cc: Doug Ledford dledf...@redhat.com
Introduce helper cap_eth_ah() to help us check if the port of an
IB device support Ethernet Address Handler.
Cc: Steve Wise sw...@opengridcomputing.com
Cc: Tom Talpey t...@talpey.com
Cc: Jason Gunthorpe jguntho...@obsidianresearch.com
Cc: Doug Ledford dledf...@redhat.com
Cc: Ira Weiny
Use raw management helpers to reform route related part in IB-core cma.
Cc: Steve Wise sw...@opengridcomputing.com
Cc: Tom Talpey t...@talpey.com
Cc: Jason Gunthorpe jguntho...@obsidianresearch.com
Cc: Doug Ledford dledf...@redhat.com
Cc: Ira Weiny ira.we...@intel.com
Cc: Sean Hefty
Add new callback query_transport() and implement for each HW.
Mapping List:
node-type link-layer old-transport new-transport
nes RNICETH IWARP IWARP
amso1100RNICETH IWARP IWARP
We have finished introducing the cap_XX(), and raw helper rdma_ib_or_iboe()
is no longer necessary, thus clean it up.
Cc: Steve Wise sw...@opengridcomputing.com
Cc: Tom Talpey t...@talpey.com
Cc: Jason Gunthorpe jguntho...@obsidianresearch.com
Cc: Doug Ledford dledf...@redhat.com
Cc: Ira Weiny
We have get rid of all the scene using legacy rdma_node_get_transport(),
now clean it up.
Cc: Steve Wise sw...@opengridcomputing.com
Cc: Tom Talpey t...@talpey.com
Cc: Jason Gunthorpe jguntho...@obsidianresearch.com
Cc: Doug Ledford dledf...@redhat.com
Cc: Ira Weiny ira.we...@intel.com
Cc: Sean
Add raw helpers:
rdma_tech_ib
rdma_tech_iboe
rdma_tech_iwarp
rdma_ib_or_iboe (transition, clean up later)
To help us detect which technology the port supported.
Cc: Steve Wise sw...@opengridcomputing.com
Cc: Tom Talpey t...@talpey.com
Cc: Jason Gunthorpe
AFAIK, RoCE v2 is the known and official name. Why would we like to come
up with a customized name?
These are indeed two different protocols, thus the comparison to DHCP
assigned addresses and static addresses is (to say the least) a bit off.
Even when comparing IPv4 and IPv6, the most
This was added (by me) in a thought of starting a unification of
all mr allocation and destruction routines but the fact is we have
a single destruction routine already, ib_dereg_mr. So another
verb that essentially does the same thing is really redundant.
And, move mlx5_ib_destroy_mr specific
On Wed, Apr 15, 2015 at 7:08 PM, Hefty, Sean sean.he...@intel.com wrote:
It does not break every app, the choice of which GID type to use is made
by the RDMA-CM based on network topology hint obtained from the IP stack.
Please refer to patch 15/33: IB/Core: Changes to the IB Core
On 4/15/2015 4:33 PM, ira.weiny wrote:
On Wed, Apr 15, 2015 at 02:36:13PM -0400, Hal Rosenstock wrote:
On 4/13/2015 8:22 AM, Michael Wang wrote:
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 65994a1..d54f91e 100644
--- a/include/rdma/ib_verbs.h
+++
On 04/16/2015 02:43 PM, Hal Rosenstock wrote:
[snip]
+
+count++;
}
+
+if (!count) {
+device_unregister(cm_dev-device);
+kfree(cm_dev);
+return;
Nit: alternatively, this could be goto at end of this routine where
there is same 2
On Wed, Apr 15, 2015 at 7:06 PM, Jason Gunthorpe
jguntho...@obsidianresearch.com wrote:
On Wed, Apr 15, 2015 at 09:17:14AM +0300, Erez Shitrit wrote:
+ /* parent interface */
+ if (!test_bit(IPOIB_FLAG_SUBINTERFACE, priv-flags))
+ return dev-ifindex;
+
+ /*
On 4/15/2015 11:45 PM, Doug Ledford wrote:
On Wed, 2015-04-15 at 12:38 -0700, Roland Dreier wrote:
On Wed, Apr 15, 2015 at 11:16 AM, Doug Ledford dledf...@redhat.com wrote:
He has patches that don't conflict available. I can rebase my tree to that if
you want. I just can't do it for a couple
On 4/16/2015 4:05 AM, Michael Wang wrote:
Use raw management helpers to reform IB-core mad/agent/user_mad.
Cc: Steve Wise sw...@opengridcomputing.com
Cc: Tom Talpey t...@talpey.com
Cc: Jason Gunthorpe jguntho...@obsidianresearch.com
Cc: Doug Ledford dledf...@redhat.com
Cc: Ira Weiny
On Apr 15, 2015, at 9:29 AM, Erez Shitrit ere...@dev.mellanox.co.il wrote:
Hi Doug
(now with reply to all :) )
On Wed, Apr 15, 2015 at 3:08 PM, Doug Ledford dledf...@redhat.com wrote:
On Apr 2, 2015, at 6:39 AM, Or Gerlitz ogerl...@mellanox.com wrote:
From: Erez Shitrit
On 4/16/2015 9:35 AM, Michael Wang wrote:
On 04/16/2015 03:19 PM, Hal Rosenstock wrote:
[snip]
+static inline int cma_validate_port(struct ib_device *device, u8 port,
+ union ib_gid *gid, int dev_type)
+{
+ u8 found_port;
+ int ret = -ENODEV;
+
+
On 4/16/2015 9:41 AM, Michael Wang wrote:
On 04/16/2015 03:36 PM, Hal Rosenstock wrote:
[snip]
-EXPORT_SYMBOL(rdma_node_get_transport);
-
enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device, u8
port_num)
{
if (device-get_link_layer)
diff --git
This is equivalent to today where the checks are per node rather than
per port.
Should all checks here be port 1 based or only certain ones like listen
? For example, in connect/reject/disconnect, don't we already have port
? Guess this can be dealt with later as this is not a
On 4/16/2015 4:08 AM, Michael Wang wrote:
Use raw management helpers to reform cm related part in IB-core cma/ucm.
These checks focus on the device cm type rather than the port capability,
directly pass port 1 works currently, but can't support mixing cm type
device in future.
This is
From: Vladimir Koushnir vladim...@mellanox.com
Date: Tue, 14 Apr 2015 18:14:48 +0300
Additional file descriptor for SMP MADs should be closed before running
ibnd_discover_fabric() to avoid parallel usage of two SMP file descriptors
Signed-off-by: Vladimir Koushnir vladim...@mellanox.com
On Mon, Apr 13, 2015 at 3:35 PM, Michael Wang yun.w...@profitbricks.com wrote:
Introduce helper cap_af_ib() to help us check if the port of an
IB device support Native Infiniband Address.
Cc: Steve Wise sw...@opengridcomputing.com
Cc: Tom Talpey t...@talpey.com
Cc: Jason Gunthorpe
From: Vladimir Koushnir vladim...@mellanox.com
Date: Thu, 16 Apr 2015 14:11:16 +0300
Today, process_one_recv calls umad_recv with zero timeout.
That means umad_recv will use non-blocking read() without polling,
In many cases, this causes busy loop.
In the fix, umad_recv is invoked with -1
On Apr 16, 2015, at 10:32 AM, Erez Shitrit ere...@dev.mellanox.co.il wrote:
On Thu, Apr 16, 2015 at 4:29 PM, Doug Ledford dledf...@redhat.com wrote:
On Apr 15, 2015, at 9:29 AM, Erez Shitrit ere...@dev.mellanox.co.il wrote:
Hi Doug
(now with reply to all :) )
On Wed, Apr 15, 2015
RoCE v2 is really Infiniband over UDP over IP. Why don't we just call
it IBoUDP like it is?
RoCEv2 is the name in the IBTA spec (Annex 17)
We call RoCE IBoE in the kernel, because that's what it is. RoCE is an IBTA
marketing name.
Looking through the Annex, I don't see where Ethernet is
diff --git a/drivers/infiniband/core/cma.c
b/drivers/infiniband/core/cma.c
index 65e41f4..7f5815d 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -470,7 +470,7 @@ static int cma_resolve_ib_dev(struct
rdma_id_private *id_priv)
On Thu, Apr 16, 2015 at 10:08:10AM +0200, Michael Wang wrote:
Use raw management helpers to reform cm related part in IB-core cma/ucm.
These checks focus on the device cm type rather than the port capability,
directly pass port 1 works currently, but can't support mixing cm type
device in
On Thu, Apr 16, 2015 at 04:34:34PM +0300, Erez Shitrit wrote:
Currently, iflink of the parent interface was always accessed, even
when interface didn't have a parent and hence we crashed there.
Handle the interface types properly: for a child interface, return
the ifindex of the parent, for
On 04/16/2015 04:31 PM, Hefty, Sean wrote:
This is equivalent to today where the checks are per node rather than
per port.
Should all checks here be port 1 based or only certain ones like listen
? For example, in connect/reject/disconnect, don't we already have port
? Guess this can be
On 04/16/2015 05:09 PM, Hefty, Sean wrote:
[snip]
Sean, can you please put a precise writeup what does it take to
support AF_IB... I am a bit
confused here and wasn't sure if this can be supported with RoCE.
I think this means IB GID addressing is checked (Native Infiniband
Address) and
On Tue, Apr 14, 2015 at 11:13:03AM +0200, Michael Wang wrote:
I would be very happy to see a patch that adds cap_ib_smi to the
current tree and states 'This patch is tested to have no change on the
binary compilation results'
There are too much reform there (per-dev to per-port), I guess
On Thu, Apr 16, 2015 at 9:44 AM, Jason Gunthorpe
jguntho...@obsidianresearch.com wrote:
We can give client-add() callback a return value and make
ib_register_device() return -ENOMEM when it failed, just wondering
why we don't do this at first, any special reason?
No idea, but having
On Wed, Apr 15, 2015 at 09:58:18AM +0200, Michael Wang wrote:
We can give client-add() callback a return value and make
ib_register_device() return -ENOMEM when it failed, just wondering why
we don't do this at first, any special reason?
No idea, but having ib_register_device fail
On Wed, Apr 15, 2015 at 09:58:18AM +0200, Michael Wang wrote:
We can give client-add() callback a return value and make
ib_register_device() return -ENOMEM when it failed, just wondering
why we don't do this at first, any special reason?
No idea, but having ib_register_device fail and unwind
After the discussion settled, I ended up thinking that implementing
explicit device checks, for use by CM, and the BUG_ON at register to
require all ports have the same value was the best option.
Sure, but why not update the other areas anyway? This way when listens become
per port, rather
On Thu, Apr 16, 2015 at 04:55:10PM +, Hefty, Sean wrote:
After the discussion settled, I ended up thinking that implementing
explicit device checks, for use by CM, and the BUG_ON at register to
require all ports have the same value was the best option.
Sure, but why not update the
Hi,
Le jeudi 16 avril 2015 à 16:34 +0300, Erez Shitrit a écrit :
Currently, iflink of the parent interface was always accessed, even
when interface didn't have a parent and hence we crashed there.
+ since commit 5aa7add8f14b ('infiniband/ipoib: implement
ndo_get_iflink').
as there was no
On 4/16/2015 11:22 AM, Michael Wang wrote:
On 04/16/2015 04:31 PM, Hefty, Sean wrote:
This is equivalent to today where the checks are per node rather than
per port.
Should all checks here be port 1 based or only certain ones like listen
? For example, in connect/reject/disconnect, don't we
No idea, but having ib_register_device fail and unwind if a client
fails to attach makes sense to me.
It seems a bit unfriendly to fail an entire device if one ULP has a
problem. Let's say you have a system whose main network connection is
IPoIB. Would you want that connection to come
Currently, iflink of the parent interface was always accessed, event
when interface didn't have a parent and hence we rashed there.
Handle the interface types properly: for a child interface, return
the ifindex of the parent, for parent interface, return its ifindex.
For child devices, make
On 04/16/2015 03:19 PM, Hal Rosenstock wrote:
[snip]
+static inline int cma_validate_port(struct ib_device *device, u8 port,
+ union ib_gid *gid, int dev_type)
+{
+u8 found_port;
+int ret = -ENODEV;
+
+if ((dev_type == ARPHRD_INFINIBAND)
Currently, iflink of the parent interface was always accessed, even
when interface didn't have a parent and hence we crashed there.
Handle the interface types properly: for a child interface, return
the ifindex of the parent, for parent interface, return its ifindex.
For child devices, make
On 4/16/15 8:45 AM, Michael Wang wrote:
On 04/16/2015 03:42 PM, Hal Rosenstock wrote:
On 4/16/2015 9:41 AM, Michael Wang wrote:
On 04/16/2015 03:36 PM, Hal Rosenstock wrote:
[snip]
-EXPORT_SYMBOL(rdma_node_get_transport);
-
enum rdma_link_layer rdma_port_get_link_layer(struct ib_device
Currently, while mapping or unmapping pages for ODP, the umem mutex is locked
and unlocked once for each page. Such lock/unlock operation take few tens to
hundreds of nsecs. This makes a significant impact when mapping or unmapping few
MBs of memory.
To avoid this, the mutex should be locked only
This patchset contains small changes that improve the performance of memory
map updates.
The patches reduce the execution time of ib_umem_odp_unmap_dma_pages when
invalidating 4MB of memory from 46us to 13us. This amounts to a reduction of
about 30% in the total execution time of the invalidation
While unmapping an ODP writable page, the dirty bit of the page is set. In
order to do so, the head of the compound page is found.
Currently, the compound head is found even on non-writable pages, where it is
never used, leading to unnecessary cpu barrier that impacts performance.
This patch
On 4/16/2015 4:09 AM, Michael Wang wrote:
Reform cma_acquire_dev() with management helpers, introduce
cma_validate_port() to make the code more clean.
Cc: Steve Wise sw...@opengridcomputing.com
Cc: Tom Talpey t...@talpey.com
Cc: Jason Gunthorpe jguntho...@obsidianresearch.com
Cc: Doug
On 04/16/2015 03:36 PM, Hal Rosenstock wrote:
On 4/16/2015 4:12 AM, Michael Wang wrote:
Introduce helper cap_ib_sa() to help us check if the port of an
IB device support Infiniband Subnet Administrator.
Nit: Administrator - Administration
Will be in next version :-)
Regards,
Michael
On 04/16/2015 03:36 PM, Hal Rosenstock wrote:
[snip]
-EXPORT_SYMBOL(rdma_node_get_transport);
-
enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device, u8
port_num)
{
if (device-get_link_layer)
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index
On 04/16/2015 03:42 PM, Hal Rosenstock wrote:
On 4/16/2015 9:41 AM, Michael Wang wrote:
On 04/16/2015 03:36 PM, Hal Rosenstock wrote:
[snip]
-EXPORT_SYMBOL(rdma_node_get_transport);
-
enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device,
u8 port_num)
{
if
On 4/16/2015 9:57 AM, Or Gerlitz wrote:
On Mon, Apr 13, 2015 at 3:35 PM, Michael Wang yun.w...@profitbricks.com
wrote:
Introduce helper cap_af_ib() to help us check if the port of an
IB device support Native Infiniband Address.
Cc: Steve Wise sw...@opengridcomputing.com
Cc: Tom Talpey
On 4/16/2015 4:12 AM, Michael Wang wrote:
Introduce helper cap_ib_sa() to help us check if the port of an
IB device support Infiniband Subnet Administrator.
Nit: Administrator - Administration
Cc: Steve Wise sw...@opengridcomputing.com
Cc: Tom Talpey t...@talpey.com
Cc: Jason Gunthorpe
On 4/16/2015 4:15 AM, Michael Wang wrote:
We have get rid of all the scene using legacy rdma_node_get_transport(),
now clean it up.
Cc: Steve Wise sw...@opengridcomputing.com
Cc: Tom Talpey t...@talpey.com
Cc: Jason Gunthorpe jguntho...@obsidianresearch.com
Cc: Doug Ledford
On Thu, Apr 16, 2015 at 4:29 PM, Doug Ledford dledf...@redhat.com wrote:
On Apr 15, 2015, at 9:29 AM, Erez Shitrit ere...@dev.mellanox.co.il wrote:
Hi Doug
(now with reply to all :) )
On Wed, Apr 15, 2015 at 3:08 PM, Doug Ledford dledf...@redhat.com wrote:
On Apr 2, 2015, at 6:39 AM, Or
To be confirmed:
PORT ASSIGNED
rdma_init_qp_attr Y
rdma_destroy_id unknown
cma_listen_on_dev N
cma_bind_loopback N
Bind loopback will attach to a port, but the id does not have on entry.
rdma_listen
On 4/16/2015 11:58 AM, Jason Gunthorpe wrote:
It also looks like hardwired 1 won't work on switch ports, so it is no-go.
AFAIK enhanced switch port 0 is not supported by CM/RDMA CM in the
current code. There is no need for CM/RDMA CM on base switch port 0.
--
To unsubscribe from this list: send
On 4/16/2015 11:58 AM, Jason Gunthorpe wrote:
It also looks like hardwired 1 won't work on switch ports, so it is no-go.
AFAIK enhanced switch port 0 is not supported by CM/RDMA CM in the current
code. There is no need for CM/RDMA CM on base switch port 0.
I concur and I thought I
On Thu, Apr 16, 2015 at 10:02:46AM -0700, Roland Dreier wrote:
On Thu, Apr 16, 2015 at 9:44 AM, Jason Gunthorpe
jguntho...@obsidianresearch.com wrote:
We can give client-add() callback a return value and make
ib_register_device() return -ENOMEM when it failed, just wondering
why we don't
On Thu, Apr 16, 2015 at 01:38:07PM -0400, Hal Rosenstock wrote:
On 4/16/2015 11:58 AM, Jason Gunthorpe wrote:
It also looks like hardwired 1 won't work on switch ports, so it is no-go.
AFAIK enhanced switch port 0 is not supported by CM/RDMA CM in the
current code. There is no need for
On Thu, 2015-04-16 at 15:37 -0600, Jason Gunthorpe wrote:
On Fri, Apr 17, 2015 at 12:26:47AM +0300, Or Gerlitz wrote:
On Thu, Apr 16, 2015 at 11:13 PM, Jason Gunthorpe
jguntho...@obsidianresearch.com wrote:
On Wed, Apr 15, 2015 at 08:39:13AM -0400, Doug Ledford wrote:
Let’s take this
On Fri, Apr 17, 2015 at 12:26:47AM +0300, Or Gerlitz wrote:
On Thu, Apr 16, 2015 at 11:13 PM, Jason Gunthorpe
jguntho...@obsidianresearch.com wrote:
On Wed, Apr 15, 2015 at 08:39:13AM -0400, Doug Ledford wrote:
Let’s take this as a starting point. If there are other patches
people think
On Wed, Apr 15, 2015 at 08:39:13AM -0400, Doug Ledford wrote:
Let’s take this as a starting point. If there are other patches
people think should make 4.1, please bring them to my attention and
I’ll add them for review and possible addition to the list.
git://github.com/dledford/linux.git
On Thu, Apr 16, 2015 at 11:13 PM, Jason Gunthorpe
jguntho...@obsidianresearch.com wrote:
On Wed, Apr 15, 2015 at 08:39:13AM -0400, Doug Ledford wrote:
Let’s take this as a starting point. If there are other patches
people think should make 4.1, please bring them to my attention and
I’ll add
Attendees:
Jeff Becker (NASA)
Wendy Cheng (Intel)
Chuck Lever (Oracle)
Doug Ledford (RedHat)
Shirley Ma (Oracle)
Anna Schumaker (Net App)
Steve Wise (OpenGridComputing, Chelsio)
Today's meeting notes:
NFSoRDMA server support:
---
NFSoRDMA Server is still technology preview
The RoCE Verbs interface references the HCA GID table in QPs and AHs, for
all RoCE versions.
The IBTA specifically does not define software interfaces. The concern here is
the architecture and definition of the linux rdma software stack, not verbs,
despite the fact that the layer is named
On Thu, Apr 16, 2015, Yann Droneaud ydrone...@opteya.com wrote:
Hi,
Le jeudi 16 avril 2015 à 16:34 +0300, Erez Shitrit a écrit :
Currently, iflink of the parent interface was always accessed, even
when interface didn't have a parent and hence we crashed there.
+ since commit 5aa7add8f14b
RoCE v2 is really Infiniband over UDP over IP. Why don't we just
call
it IBoUDP like it is?
RoCEv2 is the name in the IBTA spec (Annex 17)
We call RoCE IBoE in the kernel, because that's what it is. RoCE is an IBTA
marketing name.
Looking through the Annex, I don't see where
The RoCE Verbs interface references the HCA GID table in QPs and AHs,
for all RoCE versions.
The IBTA specifically does not define software interfaces. The concern here
is
the architecture and definition of the linux rdma software stack, not verbs,
despite the fact that the layer is
-Original Message-
From: Jason Gunthorpe [mailto:jguntho...@obsidianresearch.com]
Sent: Thursday, April 16, 2015 11:43 AM
To: Michael Wang
Cc: Roland Dreier; Sean Hefty; Hal Rosenstock; linux-rdma@vger.kernel.org;
linux-ker...@vger.kernel.org; Tom Tucker; Steve Wise;
Hoang-Nam
89 matches
Mail list logo