On Mon, Sep 21, 2015 at 7:41 PM, Sagi Grimberg wrote:
> Changes from v0:
> - Replace xprtrdma patch to Chuck's one
> - Fixed typo in iser modparam description
The change log of patch #3 needs isn't phrased clearly, this is quick
feedback I provided you for V0 and you didn't apply here, please do.
On Fri, Sep 18, 2015 at 5:46 AM, Doug Ledford wrote:
> On 09/16/2015 11:56 AM, Bodong Wang wrote:
>> Signed-off-by: Bodong Wang
>> ---
>> drivers/infiniband/hw/mlx4/main.c | 3 +++
>> 1 file changed, 3 insertions(+)
>>
>> diff --git a/drivers/infiniband/hw/mlx4/main.c
>> b/drivers/infiniband/hw
On Tue, Sep 22, 2015 at 12:59 AM, Doug Ledford wrote:
> Here's the only matrix of IP checksumming that makes sense:
>
> 1) UD over IB (because it is one of the supported IPoIB types)
> 2) RC over IB (same as above)
> 3) Raw ETH over Eth (because IP over Eth makes sense and is a common
> type of p
On 9/24/2015 5:10 AM, Wengang Wang wrote:
Use __vmalloc to allocate memory for mlx4_ib_wq.wrid and mlx4_ib_srq.wrid.
Several hits that the kmalloc for wrid failed with the following like
call back stack:
Using vmalloc and friends should be done with care, specifically, we'd like
to go there on
On 9/23/2015 9:41 PM, Christoph Hellwig wrote:
On Wed, Sep 23, 2015 at 10:23:15AM -0700, Chuck Lever wrote:
Getting rid of ib_query_device() makes sense. Moving the device
attributes into ib_device is nice. Getting rid of ib_device_attr
is of questionable value. Why do we need to go there?
IB c
On 9/24/2015 9:52 AM, Wengang Wang wrote:
} else {
- kfree(qp->sq.wrid);
- kfree(qp->rq.wrid);
+ if (is_vmalloc_addr(qp->sq.wrid))
+ vfree(qp->sq.wrid);
+ else
+ kfree(qp->sq.wrid);
+
+
On Thu, Sep 24, 2015 at 1:49 PM, Wengang Wang wrote:
> @@ -786,8 +787,14 @@ static int create_qp_common(struct mlx4_ib_dev *dev,
> struct ib_pd *pd,
> if (err)
> goto err_mtt;
>
> - qp->sq.wrid = kmalloc(qp->sq.wqe_cnt * sizeof (u64), gfp);
>
On Mon, Dec 8, 2014 at 7:45 PM, Yuval Shaia wrote:
> This value is used to calculate max_qp_dest_rdma.
> Default value of 4 brings us to 16 while HW supports 128
> (max_requester_per_qp).
> Although this value can be changed by module param it is best that default be
> optimized.
Do you have an
On Sun, Dec 7, 2014 at 7:05 PM, Yuval Shaia wrote:
> This patch is merely makes code more nice and readable.
> Instead of checking for DPDP on every loop cycle the check moves out of the
> loop.
Few short comments:
1. avoid saying "this patch does this and that" in the change-log
2. change the
On Mon, Dec 8, 2014 at 1:48 AM, Yuval Shaia wrote:
> 1. Add indication whether feature is supported or not.
> 2. Add descriptions of all features.
> Without this fix there is no way to tell if feature is not supported or that
> description is not exist.
The problem with this patch is that the c
On Tue, Dec 9, 2014 at 7:49 PM, Roland Dreier wrote:
> Thanks, applied for 3.19.
Can you please rebase today your public clown so we can see where
things are 1-2 days before you issue the pull request to Linus? where
does ODP stands from your POV?
Or.
--
To unsubscribe from this list: send the l
On Sun, Dec 7, 2014 at 6:58 PM, Matan Barak wrote:
> On 12/7/2014 2:59 PM, Or Gerlitz wrote:
>> On 12/7/2014 2:22 PM, Matan Barak wrote:
>>> Applications might want to create a CQ on n different cores
>> You mean like an IRQ can flush on a mask potentially made of mult
On Wed, Dec 10, 2014 at 12:36 AM, Weiny, Ira wrote:
>> On Mon, Dec 8, 2014 at 2:23 AM, Weiny, Ira wrote:
>> 1. add a struct ib_device_attr field to struct ib_device
>> 2. when the device registers itself with the IB core, go and run the
>> query_device verb with the param being pointer to that f
On Thu, Dec 11, 2014 at 2:39 PM, Yann Droneaud wrote:
> Le jeudi 11 décembre 2014 à 13:09 +0200, Haggai Eran a écrit :
>> On 10/12/2014 18:22, Yann Droneaud wrote:
>> > Hi,
>> >
>> > Le mardi 11 novembre 2014 à 18:36 +0200, Haggai Eran a écrit :
>> >> In some drivers there's a need to read data fr
On Wed, Oct 29, 2014 at 4:32 PM, Or Gerlitz wrote:
[...]
> Using one jiffie as the minimum delay value results in a less optimized
> scheduling of executing this work item by the workqueue, which on the
> below testbed costs about 3-4ms out of 12ms total time.
Hi Roland,
Hope the mer
On Mon, Dec 15, 2014 at 11:21 AM, Yuval Shaia wrote:
> On Wed, Dec 10, 2014 at 12:10:07PM +0200, Matan Barak wrote:
>>
>>
>> On 12/8/2014 1:48 AM, Yuval Shaia wrote:
>> >1. Add indication whether feature is supported or not.
>> >2. Add descriptions of all features.
>> >Without this fix there is no
On Mon, Dec 15, 2014 at 2:25 PM, Yuval Shaia wrote:
> On Mon, Dec 15, 2014 at 11:35:52AM +0200, Or Gerlitz wrote:
>> On Mon, Dec 15, 2014 at 11:21 AM, Yuval Shaia wrote:
>> > On Wed, Dec 10, 2014 at 12:10:07PM +0200, Matan Barak wrote:
>> >>
>> >>
>
On 12/16/2014 3:56 AM, Roland Dreier wrote:
On Mon, Dec 15, 2014 at 5:47 PM, Stephen Rothwell wrote:
Hi all,
After merging the infiniband tree, today's linux-next build (x86_64
allmodconfig) failed like this:
drivers/infiniband/hw/mlx5/main.c: In function 'mlx5_ib_query_device':
drivers/infin
On 11/16/2014 11:04 AM, Shachar Raindel wrote:
-Original Message-
From: linux-rdma-ow...@vger.kernel.org [mailto:linux-rdma-
ow...@vger.kernel.org] On Behalf Of Hefty, Sean
Sent: Thursday, November 13, 2014 6:24 PM
To: Or Gerlitz
Cc: linux-rdma@vger.kernel.org; Roland Dreier; Yotam
On Tue, Dec 16, 2014 at 7:41 PM, Roland Dreier wrote:
> On Tue, Dec 16, 2014 at 4:33 AM, Yann Droneaud wrote:
>>
>> With the suggested change here, buffer overflow won't happen,
>> but the error is silently ignored, allowing uverb to return a
>> partial result, which is likely not expected by use
On 12/16/2014 8:38 PM, Hefty, Sean wrote:
Any comment? can you please ack the patch or continue the discussion?
My concerns were addressed, so I have no further issues.
OK, thanks, Roland, can you please move fwd and pick this one for the
merge window too?
Or.
--
To unsubscribe from this li
We are dumping device capabilities which are supported both by the
firmware and the driver. Align the arrary that holds the capability
strings with this practice.
Reported-by: Yuval Shaia
Signed-off-by: Or Gerlitz
---
drivers/net/ethernet/mellanox/mlx4/fw.c |8 ++--
1 files changed, 2
On 12/16/2014 5:43 PM, Jack Wang wrote:
If user attach private data for AF_IB,
Just out of curiosity, can you share what was the motivation for you to
use AF_IB?
Or.
the first byte will
be overwritten, because we always set the cma version no matter
family is AF_IB, so move the version se
The MLX4_PROT_IB_IPV4 protocol should only be used with RoCEv2 and such.
Removing this wrong usage allows to run multicast applications over RoCE.
Fixes: d487ee77740c ('IB/mlx4: Use IBoE (RoCE) IP based GIDs in the port GID
table')
Reported-by: Carol Soto
Signed-off-by: Or Gerlitz
--
On Wed, Dec 17, 2014 at 9:15 PM, Hal Rosenstock wrote:
> There is a new 3.3.19 release of OpenSM. [...] Full list of changes is below.
It would be helpful if future opensm release announces will have few
liner writeup of the major
features/fixes in the release. As for this one... what are they?
On 12/23/2014 4:47 PM, Vasiliy Tolstov wrote:
Hello. I want to develop some software under linux 3.14 and using
infiniband libraries.
You can use the inbox libraries and install them through your distro
package installer, with RHEL, Fedora and such
it would be just
$ yum groupinstall "infini
On 12/24/2014 12:20 PM, Vasiliy Tolstov wrote:
Thanks, last question - i'm try to use rsocket and AF_IB in my app,
what minimal kernel version does support this?
AF_IB was merged in 3.11, BTW - can you share what's your motivation to
use it? as for rsockets, basically any kernel thatsupports the
From: Roi Dayan
We always unmap SGs with the same direction instead of unmapping
with the direction the mapping was done, fix that.
Fixes: 9a8b08fad2ef "IB/iser: Generalize iser_unmap_task_data and [...]"
Signed-off-by: Roi Dayan
Signed-off-by: Or Gerlitz
---
drivers/infiniban
utilize this capability.
Signed-off-by: Eyal Perry
Signed-off-by: Moshe Lazer
Signed-off-by: Or Gerlitz
---
include/infiniband/verbs.h |4 +++-
man/ibv_post_send.3|4
2 files changed, 7 insertions(+), 1 deletions(-)
diff --git a/include/infiniband/verbs.h b/include
Signed-off-by: Or Gerlitz
---
src/qp.c | 11 ++-
src/wqe.h |2 ++
2 files changed, 12 insertions(+), 1 deletions(-)
diff --git a/src/qp.c b/src/qp.c
index 721bed4..5b800e7 100644
--- a/src/qp.c
+++ b/src/qp.c
@@ -286,6 +286,10 @@ int mlx4_post_send(struct ibv_qp *ibqp, struct
From: Erez Shitrit
Following commit 016d9fb25cd9 "IPoIB: fix MCAST_FLAG_BUSY usage"
both IPv6 traffic and for the most cases all IPv4 multicast traffic
aren't working.
After this change there is no mechanism to handle the work that does the
join process for the rest of the mcg's. For example if
er the SA agent initialized the relevant
multicast object.
Fixes: 016d9fb25cd9 ('IPoIB: fix MCAST_FLAG_BUSY usage')
Reported-by: Eyal Perry
Signed-off-by: Erez Shitrit
Signed-off-by: Or Gerlitz
---
V0 --> V1 changes: Added credits (...) and furnished the change-log abit.
On 1/7/2015 6:32 PM, Weiny, Ira wrote:
>On 11/27/2014 3:51 PM, Sagi Grimberg wrote:
> >We're already short on bits in device_cap_flags
>
>no shortage @ the kernel... we can add more 32 bits if/when we need it
Why is there a gap in the bits?
enum ib_device_cap_flags {
...
IB_DEVICE_ME
On Wed, Jan 7, 2015 at 5:04 PM, Or Gerlitz wrote:
> From: Erez Shitrit
>
> Following commit 016d9fb25cd9 "IPoIB: fix MCAST_FLAG_BUSY usage"
> both IPv6 traffic and for the most cases all IPv4 multicast traffic
> aren't working.
Doug, can you ack the breakage int
On 1/12/2015 9:08 PM, Hal Rosenstock wrote:
Add support for ConnectX-3 and ConnectX-4
So... ConnectX-3 isn't supported today?! on what infrastructure/tools
exactly?
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majord...@vger.kernel.org
M
On 1/13/2015 3:09 PM, Hal Rosenstock wrote:
On 1/13/2015 2:05 AM, Or Gerlitz wrote:
>On 1/12/2015 9:08 PM, Hal Rosenstock wrote:
>>Add support for ConnectX-3 and ConnectX-4
>
>So... ConnectX-3 isn't supported today?!
It's just device IDs 0x1012 and 0x1013
I don
On Tue, Jan 13, 2015 at 6:45 PM, Doug Ledford wrote:
> On Fri, 2015-01-09 at 10:32 +0200, Or Gerlitz wrote:
>> On Wed, Jan 7, 2015 at 5:04 PM, Or Gerlitz wrote:
>> > From: Erez Shitrit
>> >
>> > Following commit 016d9fb25cd9 "IPoIB: fix MCAST_FLAG_BUSY
On 1/14/2015 8:01 AM, Doug Ledford wrote:
I've tested my patch on a plain upstream kernel and it resolves the
problem there too.
Good, please make a proper submission on the list so we can review it
inline and send questions/feedback.
Or.
So, I feel confident that the issue is resolved pro
On 1/12/2015 7:10 PM, ira.we...@intel.com wrote:
From: Ira Weiny
Save dereference and clarifies that rcv_has_same_class can process both IB and
OPA MADs.
I don't see any clarification below... something missing here?
Signed-off-by: Ira Weiny
---
drivers/infiniband/core/mad.c |2 +-
On 1/12/2015 7:10 PM, ira.we...@intel.com wrote:
Change all IB drivers to report the IB management size.
Do you mean the maximal size of IB MADs they support? if this is the
case, please reflect it in the field name.
Add check to verify that all devices support at least IB_MGMT_MAD_SIZE
-
On 1/12/2015 7:11 PM, ira.we...@intel.com wrote:
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
enum ib_signature_prot_cap {
IB_PROT_T10DIF_TYPE_1 = 1,
IB_PROT_T10DIF_TYPE_2 = 1 << 1,
@@ -210,6 +214,7 @@ struct ib_device_attr {
int sig_pro
On 1/12/2015 7:11 PM, ira.we...@intel.com wrote:
Define jumbo_mad and jumbo_rmpp_mad
For the sake of review and maintenance, please add few more words here
on what are these creatures...
Create an RMPP Base header to share between ib_rmpp_mad and jumbo_rmpp_mad
--
To unsubscribe from this
On 1/12/2015 7:10 PM, ira.we...@intel.com wrote:
From: Ira Weiny
Please avoid empty change-logs, e.g one liner will perfectly do here.
Signed-off-by: Ira Weiny
---
drivers/infiniband/core/device.c |2 ++
include/rdma/ib_verbs.h |1 +
2 files changed, 3 insertions(+), 0 d
On 1/12/2015 7:11 PM, ira.we...@intel.com wrote:
Add a device capability flag to flag OPA MAD support on devices.
You should put few words here telling what is OPA/OPA MADs and why
supporting them fits the IB core.
See for example the IB core patch [1] that added signature verbs API is
stat
On 1/14/2015 8:38 AM, Doug Ledford wrote:
The usage of IPOIB_MCAST_RUN as a flag is inconsistent. In some places
it is used to mean "our device is administratively allowed to send
multicast joins/leaves/packets" [...]
what? please tell which of these upstream hits (prior to any fix) has
this se
On Wed, Jan 21, 2015 at 7:19 PM, Roland Dreier wrote:
> On Tue, Jan 20, 2015 at 8:16 AM, Erez Shitrit
> wrote:
>> After trying your V4 patch series, I can tell that first, the endless
>> scheduling of
>> the mcast task is indeed over, but still, the multicast functionality in
>> ipoib is unst
On Wed, Jan 21, 2015 at 10:37 PM, Roland Dreier wrote:
> On Wed, Jan 21, 2015 at 12:34 PM, Or Gerlitz wrote:
>>> Because Doug's changes fixed some bad, easy-to-reproduce issues. On
>>> the other hand we don't want to introduce new regressions to fix the
>>
b25cd9 ('IPoIB: fix MCAST_FLAG_BUSY usage')
Reported-by: Eyal Perry
Signed-off-by: Erez Shitrit
Signed-off-by: Or Gerlitz
---
Changes from V1:
1. always do clear_bit(IPOIB_MCAST_FLAG_BUSY)
inipoib_mcast_sendonly_join_complete()
2. Sync between ipoib_mcast_sendonly_join() to
On Thu, Jan 22, 2015 at 4:31 PM, Doug Ledford wrote:
> My 8 patch set taken into 3.19 caused some regressions. This patch
> set resolves those issues.
Doug, Roland - eight rc1 patches followed ten rc6 fixes - sounds a bit
too much to me. If we (and Linus) like or not, probably the right
thing to
On Thu, Jan 22, 2015 at 10:40 PM, Doug Ledford wrote:
> On Thu, 2015-01-22 at 15:31 +0200, Or Gerlitz wrote:
>> Changes from V1:
>> 1. always do clear_bit(IPOIB_MCAST_FLAG_BUSY)
>> inipoib_mcast_sendonly_join_complete()
> This part is good.
good to kno
On Mon, Jan 26, 2015 at 3:00 PM, Erez Shitrit wrote:
> Following commit 016d9fb25cd9 "IPoIB: fix MCAST_FLAG_BUSY usage" both
> IPv6 traffic and for the most cases all IPv4 multicast traffic aren't
> working.
Hi Doug + Roland
Erez was very patiently reviewing and testing all the six (V0...V5)
pa
On Mon, Jan 26, 2015 at 9:38 PM, Doug Ledford wrote:
> On Mon, 2015-01-26 at 15:16 +0200, Or Gerlitz wrote:
>> On Mon, Jan 26, 2015 at 3:00 PM, Erez Shitrit wrote:
>> > Following commit 016d9fb25cd9 "IPoIB: fix MCAST_FLAG_BUSY usage" both
>> > IPv6 tr
On 1/27/2015 12:00 AM, Doug Ledford wrote:
However, I didn't get more than 5 minutes into testing before I was able
to livelock the system. In this case, from machine A running my
patchset, I did
ping6 -I mlx4_ib0 -i .25
On machine B running Erez's patch, I did:
rmmod ib_ipoib; modprobe ib_i
From: Majd Dibbiny
In case handle_eth_ud_smac_index fails, we need to free the allocated resources.
Fixes: 2f5bb473 ('mlx4: Add ref counting to port MAC table for RoCE')
Signed-off-by: Majd Dibbiny
Signed-off-by: Or Gerlitz
---
drivers/infiniband/hw/mlx4/qp.c |6 --
1 fil
: Or Gerlitz
---
drivers/infiniband/hw/mlx4/cm.c |2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/drivers/infiniband/hw/mlx4/cm.c b/drivers/infiniband/hw/mlx4/cm.c
index 56a593e..39a4888 100644
--- a/drivers/infiniband/hw/mlx4/cm.c
+++ b/drivers/infiniband/hw/mlx4/cm.c
Hi Roland,
This is small batch of mlx4 IB driver fixes, please apply for for 3.20
Note that there's another mlx4 IB driver fix I sent for 3.19 and you
didn't pick yet, "IB/mlx4: Fix wrong usage of IPv4 protocol for multicast
attach/detach" https://patchwork.kernel.org/patch/5507181 -- add it to
g
operation has completed.
3. If the users asks to resize the CQ with entries less than the oustanding cqes
we should fail instead of returning 0.
Signed-off-by: Majd Dibbiny
Signed-off-by: Or Gerlitz
---
drivers/infiniband/hw/mlx4/cq.c |7 +++
1 files changed, 3 insertions(+), 4 deletions
tes in verbs/cm structures")
Signed-off-by: Ilya Nelkenbaum
Signed-off-by: Or Gerlitz
---
FYI Sean, an easy way to reproduce the bug (and test the fix..) is have
ibacm running plus librdmacm instance which uses it (the default in
latest releases) and use rstream with gids, e.g
$ rstream
From: Majd Dibbiny
When ib_register_mad_agent fails, it returns a pointer with error which is not
NULL, therefore when calling ib_unregister_mad_agent we need to check that the
passed mad_agent is valid and not erroneous.
Signed-off-by: Majd Dibbiny
Signed-off-by: Or Gerlitz
---
drivers
Sending V1 as the wrong instance was sent for patch #2 (Gerrit hardows)
Hi Roland,
This is a batch with IB core fixes, please apply for 3.20
The patch that deals with PSN touches the HW drivers b/c we added the
qp attributes provided by the ULP as a param to the ib_modify_qp_is_ok()
IB core he
)
Signed-off-by: Moshe Lazer
Signed-off-by: Or Gerlitz
---
drivers/infiniband/core/uverbs_cmd.c |9 +
1 files changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/infiniband/core/uverbs_cmd.c
b/drivers/infiniband/core/uverbs_cmd.c
index ecb6430..a602ce9 100644
--- a/drivers/
ant bits
for User-space applications.
>From now on, we check in ib_modify_qp_is_ok that the PSN doesn't overflow, and
we fail if so.
Signed-off-by: Majd Dibbiny
Signed-off-by: Or Gerlitz
---
drivers/infiniband/core/cma.c |6 +++---
drivers/infiniband/core/uverbs_cmd
)
Signed-off-by: Moshe Lazer
Signed-off-by: Or Gerlitz
---
drivers/infiniband/core/uverbs_cmd.c |9 +
1 files changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/infiniband/core/uverbs_cmd.c
b/drivers/infiniband/core/uverbs_cmd.c
index ecb6430..a602ce9 100644
--- a/drivers/
ant bits
for User-space applications.
>From now on, we check in ib_modify_qp_is_ok that the PSN doesn't overflow, and
we fail if so.
Signed-off-by: Majd Dibbiny
Signed-off-by: Or Gerlitz
---
drivers/infiniband/core/cma.c |6 +++---
drivers/infiniband/core/uverbs_cmd
Hi Roland,
This is a batch with IB core fixes, please apply for 3.20
The patch that deals with PSN touches the HW drivers b/c we added
the qp attributes provided by the ULP as a param to the
ib_modify_qp_is_ok() IB core helper.
Or.
Ilya Nelkenbaum (1):
IB/core: When marshaling ucma path fro
From: Majd Dibbiny
When ib_register_mad_agent fails, it returns a pointer with error which is not
NULL, therefore when calling ib_unregister_mad_agent we need to check that the
passed mad_agent is valid and not erroneous.
Signed-off-by: Majd Dibbiny
Signed-off-by: Or Gerlitz
---
drivers
tes in verbs/cm structures")
Signed-off-by: Ilya Nelkenbaum
Signed-off-by: Or Gerlitz
---
FYI Sean, an easy way to reproduce the bug (and test the fix..) is have
ibacm running plus librdmacm instance which uses it (the default in
latest releases) and use rstream with gids, e.g
$ rstream
On 1/27/2015 7:02 PM, Doug Ledford wrote:
[...]
I haven't heard an argument from you yet that I believe beats the points
I've made above. So I believe a solution that does not revert back to
having two separate code paths to be maintained is preferable to your patch.
Doug,
It's not going to w
On Fri, Jan 30, 2015, Yann Droneaud wrote:
> [..] I have not the chance
> of owning HCA with the support for this feature, nor the patches
> libibverbs / libmlx5 ... (anyway I would not have the time to test). [...]
Yann, have you ever run Linux over RDMA capable HW (IB, RoCE, iWARP or alike?)
--
On 1/29/2015 7:42 PM, Jason Gunthorpe wrote:
If there is a bug, then it is at a call site, not in the unregister.
Agree, will drop this patch and dig in our regression data-base to find
the offending caller and fix it up, if it's not already fixed by now.
Majd - looking into the mlx4 IB drive
On 1/29/2015 7:54 PM, Jason Gunthorpe wrote:
On Thu, Jan 29, 2015 at 11:14:30AM +0200, Or Gerlitz wrote:
From: Majd Dibbiny
The rq/sq->psn is 24 bits as defined in the IB spec, therefore ULPs and User
space applications shouldn't use the 8 most significant bits in the 32 bits
vari
tes in verbs/cm structures")
Signed-off-by: Ilya Nelkenbaum
Signed-off-by: Or Gerlitz
---
drivers/infiniband/core/ucma.c |3 +++
1 files changed, 3 insertions(+), 0 deletions(-)
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 56a4b7c..45d67e9
Hi Roland,
This is a batch with small IB core fixes, please apply for 3.20
There's one fix which touches few HW drivers to make sure
they invoke ib_unregister_mad_agent() only for valid cases
in their error flows.
There's a pending CMA patch we sent for 3.19 and was approved
by Sean, please pick
ant bits,
also mask out these bits in uverbs for attributes provided by user-space.
issue: 416925
Change-Id: I7db9acc42564462de15bae84f4c512233fa8a62c
Signed-off-by: Majd Dibbiny
Signed-off-by: Or Gerlitz
---
drivers/infiniband/core/cma.c|1 +
drivers/infiniband/core/uverbs_cmd.
cases where
ib_register_mad_agent succeeded.
issue: 312895
Change-Id: Iaff4289ff3668e7ec91484f3d82a7d15f88678c8
Signed-off-by: Majd Dibbiny
Signed-off-by: Or Gerlitz
---
drivers/infiniband/hw/mlx4/mad.c|2 +-
drivers/infiniband/hw/mthca/mthca_mad.c |2 +-
drivers/infiniband/hw/qib
)
Signed-off-by: Moshe Lazer
Signed-off-by: Or Gerlitz
---
drivers/infiniband/core/uverbs_cmd.c |9 +
1 files changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/infiniband/core/uverbs_cmd.c
b/drivers/infiniband/core/uverbs_cmd.c
index ecb6430..a602ce9 100644
--- a/drivers/
Dibbiny
Signed-off-by: Or Gerlitz
---
drivers/infiniband/core/sa_query.c | 10 +++---
1 files changed, 7 insertions(+), 3 deletions(-)
diff --git a/drivers/infiniband/core/sa_query.c
b/drivers/infiniband/core/sa_query.c
index c38f030..80461af 100644
--- a/drivers/infiniband/core/sa_query.c
-- resent due to Gerrit IDs that were left by mistake, sorry for spamming you
over
Hi Roland,
This is a batch with small IB core fixes, please apply for 3.20
There's one fix which touches few HW drivers to make sure
they invoke ib_unregister_mad_agent() only for valid cases
in their error flows
tes in verbs/cm structures")
Signed-off-by: Ilya Nelkenbaum
Signed-off-by: Or Gerlitz
---
drivers/infiniband/core/ucma.c |3 +++
1 files changed, 3 insertions(+), 0 deletions(-)
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 56a4b7c..45d67e9
cases where
ib_register_mad_agent succeeded.
issue: 312895
Change-Id: Iaff4289ff3668e7ec91484f3d82a7d15f88678c8
Signed-off-by: Majd Dibbiny
Signed-off-by: Or Gerlitz
---
drivers/infiniband/hw/mlx4/mad.c|2 +-
drivers/infiniband/hw/mthca/mthca_mad.c |2 +-
drivers/infiniband/hw/qib
ant bits,
also mask out these bits in uverbs for attributes provided by user-space.
issue: 416925
Change-Id: I7db9acc42564462de15bae84f4c512233fa8a62c
Signed-off-by: Majd Dibbiny
Signed-off-by: Or Gerlitz
---
drivers/infiniband/core/cma.c|1 +
drivers/infiniband/core/uverbs_cmd.
Dibbiny
Signed-off-by: Or Gerlitz
---
drivers/infiniband/core/sa_query.c | 10 +++---
1 files changed, 7 insertions(+), 3 deletions(-)
diff --git a/drivers/infiniband/core/sa_query.c
b/drivers/infiniband/core/sa_query.c
index c38f030..80461af 100644
--- a/drivers/infiniband/core/sa_query.c
)
Signed-off-by: Moshe Lazer
Signed-off-by: Or Gerlitz
---
drivers/infiniband/core/uverbs_cmd.c |9 +
1 files changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/infiniband/core/uverbs_cmd.c
b/drivers/infiniband/core/uverbs_cmd.c
index ecb6430..a602ce9 100644
--- a/drivers/
cases where
ib_register_mad_agent succeeded.
Signed-off-by: Majd Dibbiny
Signed-off-by: Or Gerlitz
---
drivers/infiniband/hw/mlx4/mad.c|2 +-
drivers/infiniband/hw/mthca/mthca_mad.c |2 +-
drivers/infiniband/hw/qib/qib_mad.c |2 +-
3 files changed, 3 insertions(+), 3
error
flow. If the call to ib_register_event_handler fails, the client data must be
reset to NULL, (in case at some point ib_register_event_handler() is modified so
that it may return a non-zero (error) value).
Signed-off-by: Majd Dibbiny
Signed-off-by: Or Gerlitz
---
drivers/infiniband/core
tes in verbs/cm structures")
Signed-off-by: Ilya Nelkenbaum
Signed-off-by: Or Gerlitz
---
drivers/infiniband/core/ucma.c |3 +++
1 files changed, 3 insertions(+), 0 deletions(-)
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 56a4b7c..45d67e9
-- re-resent due to Gerrit IDs that were left by mistake, sorry for spamming
you over (and over)
Hi Roland,
This is a batch with small IB core fixes, please apply for 3.20
There's one fix which touches few HW drivers to make sure
they invoke ib_unregister_mad_agent() only for valid cases
in the
ant bits,
also mask out these bits in uverbs for attributes provided by user-space.
Signed-off-by: Majd Dibbiny
Signed-off-by: Or Gerlitz
---
drivers/infiniband/core/cma.c|1 +
drivers/infiniband/core/uverbs_cmd.c |4 ++--
2 files changed, 3 insertions(+), 2 deletions(-)
diff
)
Signed-off-by: Moshe Lazer
Signed-off-by: Or Gerlitz
---
drivers/infiniband/core/uverbs_cmd.c |9 +
1 files changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/infiniband/core/uverbs_cmd.c
b/drivers/infiniband/core/uverbs_cmd.c
index ecb6430..a602ce9 100644
--- a/drivers/
On Fri, Feb 6, 2015 at 12:27 AM, Weiny, Ira wrote:
>> Subject: [PATCH RE-RESEND V2 for-next 4/5] IB/core: Make sure that the PSN
>> does not overflow
>
> Is there a particular bug which this fixes?
Not something that I am aware too (but we can take a look @ our
regression data-base - Majd, pleas
On Tue, Feb 3, 2015 at 11:42 PM, Roland Dreier wrote:
> Last minute InfiniBand/RDMA changes for 3.19:
> - Revert IPoIB driver back to 3.18 state. We had a number of fixes go
>into 3.19, but they introduced regressions. We tried to get everything
>fixed up but ran out of time, so we'll t
On 2/11/2015 8:43 PM, Doug Ledford wrote:
This patchset revives the 8 patches that were reverted from 3.19,
the 11 patches that fixed the problems with the first 8, the single
patch that was related to reaping of ah's and failure to dealloc
resources on shutdown, and then adds two new patches tha
On 2/11/2015 11:55 PM, Doug Ledford wrote:
I tried, but the most appropriate squashes were things like patch 18 and
19 squashed into patch 3, and some other similar jumping around of
patches. The number of conflicts that created in both the original
squash and the follow on patches was perverse.
On 01/23/2015 12:02 AM, Doug Ledford wrote:
The introduction of garbage collection for neighbors in the ipoib stack
caused a leak of resources. In particular, an ah can have a refcount
from a mcast struct, from a neigh struct, and from a path struct. When
we put an ah ref, the ah gets moved to
On 02/12/2015 03:43 AM, Doug Ledford wrote:
In b2d408f78b3 (IB/ipoib: make delayed tasks not hold up everything) I
added the ability to have some joins processed around delayed joins.
Because the join task processes one join at a time, we needed to queue
the task to run again immediately and then
On 02/12/2015 03:43 AM, Doug Ledford wrote:
The introduction of garbage collection for neighbors in the ipoib stack
caused a leak of resources. In particular, an ah can have a refcount
from a mcast struct, from a neigh struct, and from a path struct. When
we put an ah ref, the ah gets moved to
On 02/12/2015 09:47 PM, Doug Ledford wrote:
So, I'll keep a new branch and this branch, and I'll reorder things (like the
singleton fix you brought
up in another email being first) and squash things, and when I get done,
I'll do a diff between the two branches to make sure that there are no
logi
On Thu, Feb 12, 2015 at 3:43 AM, Doug Ledford wrote:
> The one I removed in particular can prevent progress in the driver from
> happening because it isn't rate limited.
So isn't the right thing to do would be to rate-limit that?! note you
need not solve the whole world (ipoib...)
problems for 3.
On 02/12/2015 03:43 AM, Doug Ledford wrote:
During the various work I've done on this, some extra locking has crept
in when things weren't working right. This is one of those spots.
Remove the unneeded spinlocks.
we need a more concrete/precise text here explaining why these locking
spots can
On Sun, Jan 18, 2015 at 9:51 AM, Sagi Grimberg wrote:
> This set consist of two fixes error flows (cleanup resources).
Hi Roland, I see now that you started to pull the updates for 3.20,
please remember to take these two too they are @ your patchworks
Or.
>
> Ariel Nahum (1):
> IB/iser: Relea
101 - 200 of 2427 matches
Mail list logo