On Thu, Jun 23, 2016 at 08:27:01AM +0300, Leon Romanovsky wrote:
> On Wed, Jun 22, 2016 at 11:23:59AM -0700, Joe Perches wrote:
> > The logging macros create a bit of duplicated code/text.
> >
> > Use specialized functions to reduce the duplication.
> >
> > (def
; PATCH v9:
> This fixes comments given by Leon Romanovsky over the PATCH v8:
> Link: https://lkml.org/lkml/2016/6/9/56
>
> PATCH v8/v7/v6:
> - No change over the PATCH v5
>
> PATCH v5:
> - The initial patch which was redesigned based on the second patch
> i
f module, we only call it in RoCE driver when needed.
>
> Signed-off-by: Wei Hu
> Signed-off-by: Nenglong Zhao
> Signed-off-by: Lijun Ou
> Signed-off-by: Sheng Li
> ---
> PATCH v9/v8/v7:
> - No change over PATCH v6
>
> PATCH v6:
> This fixes the comments given by
On Wed, Jun 01, 2016 at 11:37:53PM +0800, Lijun Ou wrote:
> This patch registered IB device when loaded, and unregistered
> IB device when removed.
>
> Signed-off-by: Wei Hu
> Signed-off-by: Nenglong Zhao
> Signed-off-by: Lijun Ou
> ---
> drivers/infiniband/hw/hns/hns_roce_main.c | 46
> +
On Wed, Jun 01, 2016 at 11:37:45PM +0800, Lijun Ou wrote:
> This patch mainly added the initial bare main driver. It
> could get the relative configure information of net node.
>
> Signed-off-by: Wei Hu
> Signed-off-by: Nenglong Zhao
> Signed-off-by: Lijun Ou
> ---
> drivers/infiniband/hw/hns/
On Wed, Jun 01, 2016 at 11:37:50PM +0800, Lijun Ou wrote:
> This patch mainly added icm support for RoCE. It initializes icm
> which managers the relative memory blocks for RoCE. The data
> structures of RoCE will be located in it. For example, CQ table,
> QP table and MTPT table so on.
I wonder i
On Wed, Jun 01, 2016 at 11:37:47PM +0800, Lijun Ou wrote:
> This patch mainly configured some profile resoure. For example,
> vendor_id, hardware version, and some data structure sizes so on.
>
> Signed-off-by: Wei Hu
> Signed-off-by: Nenglong Zhao
> Signed-off-by: Lijun Ou
> ---
<...>
> +#de
On Wed, Jun 01, 2016 at 11:37:51PM +0800, Lijun Ou wrote:
> This patch mainly setup hca for RoCE. It will do a series of
> initial works, as follows:
> 1. init uar table, allocate uar resource
> 2. init pd table
> 3. init cq table
> 4. init mr table
> 5. init qp table
>
> Signe
On Thu, Jul 14, 2016 at 11:43:59AM +0800, oulijun wrote:
> 在 2016/7/2 17:39, Lijun Ou 写道:
> >
> Hi, Doug & Sean Hefty & Hal Rosenstock
> "Hello, I understand that maintainer is dealing with lots of patches not just
> mine. Also, I could not see any further review comments from the community.
> I
t;
> PATCH v10/v9/v8/v7/v6/v5:
> - No change over the PATCH v4
>
> PATCH v4:
> This fixes the comments given by Christoph Hellwig over the PATCH v3:
> Link: https://lkml.org/lkml/2016/3/22/609
>
> PATCH V3:
> This fixes the comments given by Leon Romanovsky over
On Thu, Jul 14, 2016 at 09:46:14AM +0300, Netanel Belgazal wrote:
> This is a driver for the ENA family of networking devices.
>
> Signed-off-by: Netanel Belgazal
> ---
>
> Notes:
...
> - Increase driver version to 1.0.2
...
> +static void ena_get_drvinfo(struct net_device *dev,
> +
On Tue, Jul 19, 2016 at 10:49:57AM -0700, Joe Perches wrote:
> On Tue, 2016-07-19 at 20:26 +0300, Leon Romanovsky wrote:
> > On Tue, Jul 19, 2016 at 02:09:25PM +0300, Netanel Belgazal wrote:
> > > This is the debugging message interface.
> > > https://www.kernel.org/d
> This issue was detected by using the Coccinelle software.
>
> Signed-off-by: Markus Elfring
Thanks,
Reviewed-by: Leon Romanovsky
signature.asc
Description: Digital signature
bridge_header"
> and "hca_header" contained a null pointer.
>
> Adjust jump targets according to the Linux coding style convention.
>
> Signed-off-by: Markus Elfring
Thanks,
Reviewed-by: Leon Romanovsky
signature.asc
Description: Digital signature
no pending tasks while disconnecting the driver.
>
> Signed-off-by: Bhaktipriya Shridhar
> ---
> Changes in v2:
> -Updated commit description as per the feedback received.
>
> drivers/net/ethernet/mellanox/mlx5/core/health.c | 7 ++-
> 1 file cha
On Tue, Jul 26, 2016 at 07:05:37PM -0700, k...@exchange.microsoft.com wrote:
> From: K. Y. Srinivasan
>
> This driver is a bridge driver that surfaces a Mellanox device in the Linux
> guest and plugs into
> the "NetworkDirect" RDMA infrastructure on the Windows host. Only a subset of
> the ibve
On Sat, Jul 02, 2016 at 05:39:02PM +0800, Lijun Ou wrote:
This v11
> 28 files changed, 10626 insertions(+), 1 deletion(-)
First version
> 27 files changed, 11670 insertions(+), 11 deletions(-)
1K LOC less, we are moving in right direction.
signature.asc
Description: Digital signature
t of the
> corresponding 'switch' block.
>
> Signed-off-by: Christophe JAILLET
Thanks
Reviewed-by: Leon Romanovsky
signature.asc
Description: Digital signature
On Tue, Oct 25, 2016 at 06:46:58PM +0530, Binoy Jayan wrote:
> On 25 October 2016 at 17:56, Leon Romanovsky wrote:
> > On Tue, Oct 25, 2016 at 05:31:59PM +0530, Binoy Jayan wrote:
>
> > In case of success (err == 0), you will call to unmap_dma instead of
> > normal flo
On Wed, Oct 26, 2016 at 01:31:13PM +0530, Binoy Jayan wrote:
> Clean up the following common code (to post a list of work requests to the
> send queue of the specified QP) at various places and add a helper function
> 'mlx5_ib_post_send_wait' to implement the same.
>
> - Initialize 'mlx5_ib_umr_co
dded patch - Replace semaphore umr_common:sem with wait_event
> IB/mlx5: Fixed a bug pointed out by Leon Romanovsky
Please keep full changelog for your next submissions/respins.
Thanks
signature.asc
Description: PGP signature
On Tue, Nov 08, 2016 at 01:06:23PM +1100, Stephen Rothwell wrote:
> Hi Leon,
>
> Today's linux-next merge of the rdma-leon-test tree got a conflict in:
>
> drivers/infiniband/core/roce_gid_mgmt.c
>
> between commit:
>
> 453d39329ad0 ("IB/core: Flip to the new dev walk API")
>
> from the net-nex
On Fri, Nov 04, 2016 at 04:36:25PM +, Salil Mehta wrote:
> From: "Wei Hu (Xavier)"
>
> This patch modified the logic of allocating memory using APIs in
> hns RoCE driver. We used kcalloc instead of kmalloc_array and
> bitmap_zero. And When kcalloc failed, call vzalloc to alloc
> memory.
>
> Si
ed the round-robin
> mode for allocating resources using bitmap. We use round-robin mode
> for qp number and non round-robing mode for other resources like
> cq number, pd number etc.
>
> Signed-off-by: Wei Hu (Xavier)
> Signed-off-by: Salil Mehta
Reviewed-by: Leon Romanovsky
signature.asc
Description: PGP signature
On Tue, Nov 15, 2016 at 03:52:46PM +, Salil Mehta wrote:
> > -Original Message-
> > From: Leon Romanovsky [mailto:l...@kernel.org]
> > Sent: Wednesday, November 09, 2016 7:22 AM
> > To: Salil Mehta
> > Cc: dledf...@redhat.com; Huwei (Xavier); oulijun;
R_OR_NULL(t)
> + IS_ERR(t)
>
> @@
> expression t,e,e1;
> @@
>
> t = \(usnic_ib_qp_grp_get_chunk(...)\|get_qp_res_chunk(...)\)
> ... when != t=e
> ?- t ? PTR_ERR(t) : e1
> + PTR_ERR(t)
> ... when any
> //
>
> Signed-off-by: Julia Lawall
Thanks, Julia.
Reviewed-by: Leon Romanovsky
signature.asc
Description: PGP signature
tions(+), 3 deletions(-)
Thanks,
Reviewed-by: Leon Romanovsky
> diff --git a/drivers/infiniband/hw/qib/qib_user_sdma.c
> b/drivers/infiniband/hw/qib/qib_user_sdma.c
> index 3e0677c..926f3c8 100644
> --- a/drivers/infiniband/hw/qib/qib_user_sdma.c
> +++ b/drivers/infiniband/hw/qi
On Tue, Dec 20, 2016 at 10:02:18PM +0800, Geliang Tang wrote:
> To make the code clearer, use rb_entry() instead of container_of() to
> deal with rbtree.
>
> Signed-off-by: Geliang Tang
> ---
> net/rds/rdma.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
Than
ed, 1 insertion(+), 1 deletion(-)
Thanks,
Acked-by: Leon Romanovsky
>
> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
> b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
> index 3b026c1..7431f63 100644
> --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cou
lly valid
> whenever we return successfully.
>
> Signed-off-by: Arnd Bergmann
Thanks Arnd for fixing it.
I have a very small comment which is not related to functionality.
Rather than that,
Acked-by: Leon Romanovsky
> ---
> drivers/infiniband/hw/mlx5/mr.c | 39 +
c-4.9, short of
> initializing each of the arguments first was to change the calling
> conventions to separate the error code from the umem pointer. This
> avoids casting the error codes from one pointer to another incompatible
> pointer, and lets gcc figure out when that the data is ac
m);
> - err = ib_post_send(umrc->qp, &umrwr.wr, &bad);
> - if (err) {
> - mlx5_ib_warn(dev, "post send failed, err %d\n", err);
> + err = mlx5_ib_post_send_wait(dev, &umr_context, &umrwr);
> + if (err != -EFAULT)
>
On Fri, Dec 30, 2016 at 06:18:29PM +0800, Kenneth Lee wrote:
> There are two bugfixes in this patch:
>
> Fixes: 87773dd56d54 ("IB: ib_umem_release() should decrement mm->pinned_vm
> from ib_umem_get")
> This patch introduce the get_task_pid but not put it back on all error
> path
>
> F
On Tue, Jan 03, 2017 at 03:56:08PM +1100, Stephen Rothwell wrote:
> Hi all,
>
> Changes since 20161224:
>
> Dropped tree: rdma-leon (complex conflicts)
Thanks Stephen,
It is our fault.
https://www.mail-archive.com/netdev@vger.kernel.org/msg145455.html
I'm fixing it right now.
signature.asc
Desc
On Tue, Jan 03, 2017 at 10:32:50AM +0800, Kenneth Lee wrote:
> On Sun, Jan 01, 2017 at 08:47:12AM +0200, Leon Romanovsky wrote:
> > Date: Sun, 1 Jan 2017 08:47:12 +0200
> > From: Leon Romanovsky
> > To: Kenneth Lee
> > CC: dledf...@redhat.com, sean.he...@intel.co
On Wed, Jan 04, 2017 at 03:07:04PM +0800, Kenneth Lee wrote:
> On Tue, Jan 03, 2017 at 12:12:24PM +0200, Leon Romanovsky wrote:
> > Date: Tue, 3 Jan 2017 12:12:24 +0200
> > From: Leon Romanovsky
> > To: Kenneth Lee
> > CC: dledf...@redhat.com, sean.he...@intel.co
em->offset);
See the patch inline which removes this BUG_ON in proper and safe way.
From 7babe807affa2b27d51d3610afb75b693929ea1a Mon Sep 17 00:00:00 2001
From: Leon Romanovsky
Date: Mon, 12 Dec 2016 20:02:45 +0200
Subject: [PATCH] net/mlx4: Remove BUG_ON from ICM allocation routine
This patch removes BUG_ON() ma
On Wed, Dec 14, 2016 at 01:16:45PM -0500, Doug Ledford wrote:
> On 11/21/2016 12:38 PM, Leon Romanovsky wrote:
> > On Mon, Nov 21, 2016 at 09:52:53AM -0700, Jason Gunthorpe wrote:
> >> On Mon, Nov 21, 2016 at 02:14:08PM +0200, Leon Romanovsky wrote:
> >>>>
> &g
On Thu, Dec 29, 2016 at 10:24:43AM +0800, Kenneth Lee wrote:
> There are two bugfixes in this patch:
>
> 1. When the execution go to the ib_umem_odp_get() path, pid should be put
>back.
> 2. When the memory allocation fail, the pid also should be put back before
>exit.
>
> Signed-off-by: Ke
On Thu, Dec 29, 2016 at 04:27:28PM +0800, Kenneth Lee wrote:
> There are two bugfixes in this patch:
>
> 1. When the execution go to the ib_umem_odp_get() path, pid should be put
>back.
> 2. When the memory allocation fail, the pid also should be put back before
>exit.
>
> Signed-off-by: Ke
se() to
modules")
>
> Could you please give more suggestion? Thanks.
Please, don't use top-posting for this mailing list.
It is really-really annoying.
>
> On Thu, Dec 29, 2016 at 10:17:56AM +0200, Leon Romanovsky wrote:
> > Date: Thu, 29 Dec 2016 10:17:56 +0200
> &
ase, the err initialization at the beginning of
mlx4_ib_query_device function is not necessary. Can you please remove it?
Besides that, look good.
Reviewed-by: Leon Romanovsky
>
> --
> 1.9.1
>
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-
with
> "-ENOMEM".
>
> Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=188831
>
> Signed-off-by: Pan Bian
Thanks,
Reviewed-by: Leon Romanovsky
signature.asc
Description: PGP signature
cannot detect the
> errors. This patch fixes the bug, assign "-ENOMEM" to err before the
> NULL pointer checks, and remove the initialization of err at the
> beginning.
>
> Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=189031
> Signed-off-by: Pan Bian
Thanks,
On Sat, Nov 19, 2016 at 06:11:22PM -0500, Doug Ledford wrote:
> On 11/19/2016 2:46 PM, Or Gerlitz wrote:
> > On Fri, Nov 18, 2016 at 4:01 AM, Doug Ledford wrote:
> >> On 11/17/2016 5:24 PM, Or Gerlitz wrote:
> >
> > [...]
> > Are you going to comment on that to the submitter? if not, they are
> >
error
> >> or a malicious attempt. This is not a kernel bug, remove it.
> >>
> >> BUG/WARNs that are not kernel bugs hinder automated testing effots.
> >>
> >> Signed-off-by: Dmitry Vyukov
> >> Cc: Doug Ledford
> >> Cc: Sean Hefty
>
On Mon, Nov 21, 2016 at 12:48:35PM +0100, Dmitry Vyukov wrote:
> On Mon, Nov 21, 2016 at 12:44 PM, Leon Romanovsky wrote:
> > On Mon, Nov 21, 2016 at 11:30:21AM +0100, Dmitry Vyukov wrote:
> >> On Mon, Nov 21, 2016 at 11:25 AM, Miroslav Benes wrote:
> >> > On M
On Mon, Nov 21, 2016 at 04:12:38PM +, Salil Mehta wrote:
> > -Original Message-
> > From: Leon Romanovsky [mailto:l...@kernel.org]
> > Sent: Wednesday, November 16, 2016 8:36 AM
> > To: Salil Mehta
> > Cc: dledf...@redhat.com; Huwei (Xavier); oulijun;
On Mon, Nov 21, 2016 at 09:52:53AM -0700, Jason Gunthorpe wrote:
> On Mon, Nov 21, 2016 at 02:14:08PM +0200, Leon Romanovsky wrote:
> > >
> > > In ib_ucm_write function there is a wrong prefix:
> > >
> > > + pr_err_once("ucm_write: process %d (%s) trie
On Mon, Dec 12, 2016 at 12:58:59PM +0200, Ozgur Karatas wrote:
> Hello all,
> I think should be use to "WARN_ON" and checkpatch script give to error, I
> fixed and I think should don't use "BUG_ON".
> Regards,
>
> Signed-off-by: Ozgur Karatas
NA
drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 11 ++-
> include/linux/mlx5/driver.h | 2 +-
> 2 files changed, 7 insertions(+), 6 deletions(-)
>
Thanks,
Acked-by: Leon Romanovsky
signature.asc
Description: PGP signature
ter Senna Tschudin
> ---
> drivers/net/ethernet/mellanox/mlx4/cmd.c | 10 +-
> drivers/net/ethernet/mellanox/mlx4/mlx4.h | 2 +-
> 2 files changed, 6 insertions(+), 6 deletions(-)
>
Thanks,
Reviewed-by: Leon Romanovsky
signature.asc
Description: PGP signature
On Fri, Feb 24, 2017 at 04:16:31PM +, Bart Van Assche wrote:
> On Fri, 2017-02-24 at 16:44 +0800, Minfei Huang wrote:
> > "if (0)" is used to make this block of debug code not be executed. There
> > is a more elegant way to let compiler ignore this code, using
> > "#if 0 .. #endif" instead.
> >
On Thu, Jun 16, 2016 at 10:35:16PM +0800, Lijun Ou wrote:
> This patch mainly added icm support for RoCE. It initializes icm
> which managers the relative memory blocks for RoCE. The data
> structures of RoCE will be located in it. For example, CQ table,
> QP table and MTPT table so on.
>
> Signed
On Fri, Jun 17, 2016 at 05:02:33PM +0200, Arnd Bergmann wrote:
> On Friday, June 17, 2016 5:50:14 PM CEST Saeed Mahameed wrote:
> > On Wed, Jun 15, 2016 at 11:50 PM, Arnd Bergmann wrote:
> > > On Wednesday, June 15, 2016 7:04:54 PM CEST Saeed Mahameed wrote:
> > > Ok, I see. It would be nice if th
On Sun, Oct 30, 2016 at 11:17:57PM +0200, Sagi Grimberg wrote:
>
>
> On 27/10/16 09:59, Binoy Jayan wrote:
> >Convert the completion 'mlx5_ib_umr_context:done' to a wait_event as it
> >just waits for the return value to be filled.
On top of Sagi's response, I'm failing to understand why it is need
)
> Signed-off-by: Arnd Bergmann
> ---
> drivers/infiniband/hw/hfi1/verbs.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
Thanks,
Reviewed-by: Leon Romanovsky
signature.asc
Description: PGP signature
On Wed, Feb 08, 2017 at 10:22:28PM +0100, SF Markus Elfring wrote:
> From: Markus Elfring
> Date: Wed, 8 Feb 2017 21:07:07 +0100
>
> The local variable "ret" will be set to an appropriate value a bit later.
> Thus omit the explicit initialisation at the beginning in this function.
>
> Signed-off-b
On Wed, Feb 08, 2017 at 10:19:41PM +0100, SF Markus Elfring wrote:
> From: Markus Elfring
> Date: Wed, 8 Feb 2017 18:08:08 +0100
>
> Add a jump target so that a bit of exception handling can be better reused
> from an in branch in this function.
>
> Signed-off-by: Markus Elfring
> ---
> drivers/
t; include/rdma/ib_verbs.h | 11 +++
> net/rds/ib.h| 6 +++---
> 2 files changed, 6 insertions(+), 11 deletions(-)
>
Thanks,
Reviewed-by: Leon Romanovsky
signature.asc
Description: PGP signature
On Tue, Jan 10, 2017 at 04:56:44PM -0800, Bart Van Assche wrote:
> The qib DMA mapping code is no longer built since commit eb636ac0e49e
> ("IB/qib: Remove dma.c and use rdmavt version of dma functions"). Hence
> remove it.
>
> Signed-off-by: Bart Van Assche
> Cc: Mike Marciniszyn
> Cc: Dennis Da
rtions(+), 548 deletions(-)
> delete mode 100644 drivers/infiniband/sw/rdmavt/dma.c
> delete mode 100644 drivers/infiniband/sw/rdmavt/dma.h
> delete mode 100644 drivers/infiniband/sw/rxe/rxe_dma.c
>
Thanks,
Reviewed-by: Leon Romanovsky
signature.asc
Description: PGP signature
| 4 +-
> drivers/infiniband/core/umem_odp.c | 6 +-
> drivers/infiniband/hw/mlx4/cq.c| 2 +-
> drivers/infiniband/hw/mlx4/mad.c | 28 +--
> drivers/infiniband/hw/mlx4/mr.c| 4 +-
> drivers/in
On Mon, Aug 8, 2016 at 6:37 PM, Doug Ledford wrote:
> On 8/7/2016 9:58 PM, Stephen Rothwell wrote:
>> Hi all,
>>
>> With Linus' tree, today's linux-next build (powerpc allyesconfig) failed
>> like this:
>>
>> drivers/infiniband/sw/built-in.o:(.opd+0x1698): multiple definition of
>> `copy_data'
>>
On Mon, Aug 01, 2016 at 11:11:19AM -0400, Tejun Heo wrote:
> > Right now, I'm feeling that I'm participating in soapie where one sends
> > patch for every line, waits and sends the same patch for another file.
> > It is worth to send one patch set and let us to test it all in once.
>
> Yeah, I gue
onding macro,
> and that using macro can improve the robustness and readability of the code,
> thus, I suggest replacing the numeric parameter with the macro.
>
> Signed-off-by: Chuansheng Liu
> Signed-off-by: Baole Ni
> ---
Thanks,
Acked-by: Leon Romanovsky
> drivers/infi
onding macro,
> and that using macro can improve the robustness and readability of the code,
> thus, I suggest replacing the numeric parameter with the macro.
>
> Signed-off-by: Chuansheng Liu
> Signed-off-by: Baole Ni
Looks good,
Reviewed-By: Leon Romanovsky
> ---
> d
x27;.
>
> It is likely that the number of bits of 'tmp' was expected here. So use
> BITS_PER_LONG instead.
>
> It has been spotted by the following coccinelle script:
> @@
> expression ret, x;
>
> @@
> * ret = \(find_first_bit \| find_first_zero_bit\) (x
On Fri, Aug 26, 2016 at 02:01:55PM -0400, Doug Ledford wrote:
> On 8/26/2016 9:35 AM, Doug Ledford wrote:
> > On 8/26/2016 12:49 AM, Christophe JAILLET wrote:
> >> The 2nd parameter of 'find_first_bit' is the number of bits to search.
> >> In this case, we are passing 'sizeof(unsigned long)' which
On Fri, Aug 26, 2016 at 03:34:48PM -0400, Doug Ledford wrote:
> On 8/26/2016 3:29 PM, Leon Romanovsky wrote:
> > On Fri, Aug 26, 2016 at 02:01:55PM -0400, Doug Ledford wrote:
> >> On 8/26/2016 9:35 AM, Doug Ledford wrote:
> >>> On 8/26/2016 12:49 AM, Christophe
Except the fact that we have a little bit different format for title
==> "IB/cxgb4: Mark symbols static for _free_qp"
Looks ok,
Reviewed-by: Leon Romanovsky
signature.asc
Description: PGP signature
On Mon, Jun 06, 2016 at 10:15:06PM +0100, Sudip Mukherjee wrote:
> prot_sg_cnt has been assigned with the value of ret which we have
> already checked to be non-zero so prot_sg_cnt can never be zero at this
> point of the code and hence the else part can never execute.
> And since we know prot_sg_c
e Coccinelle software.
>
> Signed-off-by: Markus Elfring
Reviewed-by: Leon Romanovsky
signature.asc
Description: PGP signature
On Fri, Aug 19, 2016 at 03:42:29PM +, Marciniszyn, Mike wrote:
> > >
> > > The bail_tmp: label is then not needed.
> >
> > You still need to free tmp allocation if qib_eeprom_write failed and this is
> > your bail_tmp.
> >
>
> Typo. The bail: label is not needed.
Yeah, it makes sense.
Th
On Mon, Aug 15, 2016 at 11:27:01PM +0530, Bhaktipriya Shridhar wrote:
> This patch set removes the instances of deprecated
> create_singlethread_workqueue (scheduled for removal) in
> drivers/infiniband by making the appropriate conversions.
>
> Bhaktipriya Shridhar (22):
> IB/sa : Remove deprec
em &qp_pfault->work.
> It has been identity converted.
>
> WQ_MEM_RECLAIM has been set to ensure forward progress under
> memory pressure.
>
> Signed-off-by: Bhaktipriya Shridhar
Thanks,
Acked-by: Leon Romanovsky
> ---
> drivers/infiniband/hw/mlx5/odp.c
gt;work and the workqueue "ud_wq"
> queues work item &dm[i]->work.
>
> Both the workqueues have been identity converted.
>
> WQ_MEM_RECLAIM has been set to ensure forward progress under
> memory pressure.
>
> Signed-off-by: Bhaktipriya Shridhar
Thanks,
Rev
s/infiniband/hw/mlx5/mr.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
Thanks,
Acked-by: Leon Romanovsky
>
> diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
> index 8cf2ce5..fb0194d 100644
> --- a/drivers/infiniband/hw/mlx5/mr.c
> ++
;work
> and &group->timeout_work.
>
> The workqueue "clean_wq" queues work item mcg_clean_task.
>
> Both have been identity converted.
>
> WQ_MEM_RECLAIM has been set to ensure forward progress under
> memory pressure.
>
> Signed-off-by: Bhaktipriy
_guid_work.
> It has been identity converted.
>
> WQ_MEM_RECLAIM has been set to ensure forward progress under
> memory pressure.
>
> Signed-off-by: Bhaktipriya Shridhar
Thanks,
Reviewed-by: Leon Romanovsky
> ---
> drivers/infiniband/hw/mlx4/alias_GUID.c | 2
On Fri, Aug 19, 2016 at 03:27:20PM +, Marciniszyn, Mike wrote:
> > Subject: [PATCH] IB/qib: Use memdup_user() rather than duplicating its
> > diff --git a/drivers/infiniband/hw/qib/qib_fs.c
>
> I would be even more aggressive at reducing lines of code.
>
> For example do direct returns when o
rk items &ent->work (maps to
> cache_work_func) and &ent->dwork(maps to delayed_cache_work_func).
> It has been identity converted.
>
> WQ_MEM_RECLAIM has been set to ensure forward progress under
> memory pressure.
>
> Signed-off-by: Bhaktipriya Shridhar
Thanks,
Acked-by:
t;work, &ew->work.
> It has been identity converted.
>
> WQ_MEM_RECLAIM has been set to ensure forward progress under
> memory pressure.
>
> Signed-off-by: Bhaktipriya Shridhar
> ---
> drivers/infiniband/hw/mlx4/main.c | 2 +-
> 1 file changed, 1 insertion(+), 1
On Sun, Jun 12, 2016 at 05:41:06PM +0800, Wei Hu (Xavier) wrote:
>
>
> On 2016/6/9 14:26, Leon Romanovsky wrote:
> >On Wed, Jun 01, 2016 at 11:37:53PM +0800, Lijun Ou wrote:
> >>This patch registered IB device when loaded, and unregistered
> >>IB device when rem
On Mon, Jun 13, 2016 at 02:54:53PM +0200, Arnd Bergmann wrote:
> The rxe driver fails to build on 32-bit because of a 64-bit division:
>
> In function `rxe_qp_from_attr':
> :(.text+0x53158): undefined reference to `__aeabi_uldivmod'
>
> We can easily avoid this division by converting the nanoseco
On Mon, Jun 13, 2016 at 09:53:41AM +0300, Dan Carpenter wrote:
> If copy_to_user() fails then it returns the number of bytes not copied.
> It would be between 1-4 here. Later the callers dereference it leading
> to an Oops.
>
> It was sort of hard to fix this without making the code confusing so
execute
> once trying to free hsag->attrs[0]. But hsag is NULL still now leading
> to a NULL pointer dereference.
>
> Signed-off-by: Sudip Mukherjee
Thanks,
Reviewed-by: Leon Romanovsky
> ---
> drivers/infiniband/core/sysfs.c | 2 +-
> 1 file changed, 1 insertion(+), 1
On Sun, Jun 05, 2016 at 09:13:56PM +0100, Sudip Mukherjee wrote:
> If the allocation of hsag fails we were just returning but stats was
> not released.
>
> Signed-off-by: Sudip Mukherjee
Thanks,
Reviewed-by: Leon Romanovsky
> ---
> drivers/infiniband/core/sysfs.c | 2 +-
&g
On Sun, Jun 05, 2016 at 09:45:52PM +0100, Sudip Mukherjee wrote:
> prot_sg_cnt has been assigned with the value of ret which we have
> already checked to be non-zero so prot_sg_cnt can never be zero at this
> point of the code and hence the else part can never execute.
>
> Signed-off-by: Sudip Muk
On Mon, Jun 06, 2016 at 09:34:54AM +0300, Leon Romanovsky wrote:
> On Sun, Jun 05, 2016 at 09:13:56PM +0100, Sudip Mukherjee wrote:
> > If the allocation of hsag fails we were just returning but stats was
> > not released.
> >
> > Signed-off-by: Sudip Mukherjee
>
TCH v9/v8:
> - No change over the PATCH v7
>
> PATCH v7:
> This fixes the comments given by Leon Romanovsky over the PATCH v6:
> Link: https://lkml.org/lkml/2016/5/3/733
>
> PATCH v6:
> - No change over the PATCH v5
>
> PATCH v5:
> - The initial patch which
TCH v9:
> This fixes the comments given by Leon Romanovsky over the PATCH v8:
> Link: https://lkml.org/lkml/2016/6/9/65
>
> PATCH v8/v7/v6:
> - No change over the PATCH v5
>
> PATCH v5:
> - The initial patch which was redesigned based on the second patch
> i
On Thu, Jun 16, 2016 at 10:35:15PM +0800, Lijun Ou wrote:
> This patch added event queue support for RoCE driver. It is used
> for RoCE interrupt. RoCE includes 32 synchronous event irqs, 1
> asynchronous event irq and 1 common overflow irq.
>
> Signed-off-by: Wei Hu
> Signed-off-by: Nenglong Zha
5. init qp table
>
> Signed-off-by: Wei Hu
> Signed-off-by: Nenglong Zhao
> Signed-off-by: Lijun Ou
> ---
> PATCH v9:
> This fixes the comments given by Leon Romanovsky over the PATCH v8
> Link: https://lkml.org/lkml/2016/6/9/67
>
> PATCH v8/v7/v6:
> - No change
On Thu, Jun 16, 2016 at 10:35:08PM +0800, Lijun Ou wrote:
> The HiSilicon Network Substem is a long term evolution IP which is
> supposed to be used in HiSilicon ICT SoCs. HNS (HiSilicon Network
> Sybsystem) also has a hardware support of performing RDMA with
> RoCEE.
> The driver for HiSilicon RoC
On Sat, Jun 25, 2016 at 06:29:31PM +0800, Wei Hu (Xavier) wrote:
>
>
> On 2016/6/24 19:48, Leon Romanovsky wrote:
> >On Thu, Jun 16, 2016 at 10:35:11PM +0800, Lijun Ou wrote:
> >>This patch mainly added the initial bare main driver. It
> >>could get the relative
On Sat, Jun 25, 2016 at 06:25:37PM +0800, Wei Hu (Xavier) wrote:
>
>
> On 2016/6/24 22:59, Leon Romanovsky wrote:
> >On Thu, Jun 16, 2016 at 10:35:12PM +0800, Lijun Ou wrote:
> >>This patch mainly added reset flow of RoCE engine in RoCE
> >>driver. It is necessar
On Tue, Jun 28, 2016 at 02:31:41PM +0800, Wei Hu (Xavier) wrote:
>
>
> On 2016/6/27 16:31, oulijun wrote:
> >Hi, Leon
> >在 2016/6/27 16:01, Leon Romanovsky 写道:
> >>On Sat, Jun 25, 2016 at 06:25:37PM +0800, Wei Hu (Xavier) wrote:
> >>>
> >>>O
On Wed, Jun 29, 2016 at 04:53:39PM +0800, oulijun wrote:
> >> +
> >> + for (i = 0; i < npages; ++i)
> >> + if (eq->buf_list[i].buf)
> >
> > Is it possible situation to have eq->buf_list[i].buf == NULL at the
> > middle of iteration?
> >
> We have analysized it according to your reivews
On Fri, Mar 11, 2016 at 06:37:10PM +0800, Lijun Ou wrote:
> It added hns_dsaf_roce_reset routine for roce driver.
> RoCE is a feature of hns.
> In hip06 SOC, in roce reset process, it's needed to configure
> dsaf channel reset,port and sl map info.
>
> Signed-off-by: Lijun Ou
> Signed-off-by: Wei
601 - 700 of 1087 matches
Mail list logo
