Re: [for-next V3 00/15][PULL request] Mellanox mlx5 core driver updates 2016-08-20

2 messages, 2 authors, 2016-08-23 · open the first message on its own page

Re: [for-next V3 00/15][PULL request] Mellanox mlx5 core driver updates 2016-08-20

From: Saeed Mahameed <hidden>
Date: 2016-08-23 16:10:53

On Tue, Aug 23, 2016 at 6:57 PM, Doug Ledford [off-list ref] wrote:
On 8/23/2016 4:49 AM, Saeed Mahameed wrote:
quoted
Hi Dave and Doug,

This series contains several low level and API updates for mlx5 core
commands interface and mlx5_ifc.h to be shared as base code for net-next and
rdma mlx5 4.9 submissions.

From Saeed, ten patches that refactors old layouts of firmware commands which
were manually generated before we introduced the mlx5_ifc, now all of the firmware
commands inbox/outbox layouts moved to use mlx5_ifc and we remove the old
manually generated structures.
These all looked fine to me.
quoted
Plus to those ten patches, we add two patches
that unifies mlx5 commands execution interface and improve the driver log messages
in that area.
These are the patches that made my eyes want to bleed.  But, since it's
all changes to the mailbox commands being sent to your device, they are
easy to verify operationally, so I only gave these a cursory review and
expect if any of your commands broke because of this you'll be
submitting fixes ASAP.
Thanks Doug for your review those patches already passed all kinds of
our internal regression testings.
What is nice about those patches is that they remove  ~1K  LOC from
driver and unify the command interface.
quoted
From Hadar and Ilya, added the needed hardware bits and infrastructure for
minimum inline headers setting and encap/decap commands and capabilities,
needed for E-Switch offloads.
These looked fine to me, but aren't really in the RDMA area anyway.
quoted
This series applies on top latest net-next and rdma/master, and smoothly merges with
the latest "Mellanox 100G mlx5 fixes 2016-08-16" series already applied into net branch.

The following changes since commit 29b4817d4018df78086157ea3a55c1d9424a7cfc:
    Linux 4.8-rc1

are available in the git repository at:
    git://git.kernel.org/pub/scm/linux/kernel/git/leon/linux-rdma.git tags/shared-for-4.9-1
I've pulled these into a local branch and they look fine.  Once Dave
gives his ack/nack, we'll go from there.
quoted
for you to fetch changes up to 575ddf5888eaf8f271cb3df7b0806cb2db2c333a:
    net/mlx5: Introduce alloc_encap and dealloc_encap commands

Changes since V2 and V1:
    - Reduce the number of patches and changed the cover letter respectively.

Thanks,
Saeed & Leon.

Hadar Hen Zion (2):
  net/mlx5: Enable setting minimum inline header mode for VFs
  net/mlx5: Update mlx5_ifc.h for vxlan encap/decap

Ilya Lesokhin (1):
  net/mlx5: Introduce alloc_encap and dealloc_encap commands

Saeed Mahameed (12):
  net/mlx5: Init/Teardown hca commands via mlx5 ifc
  net/mlx5: Access register and MAD IFC commands via mlx5 ifc
  net/mlx5: PD and UAR commands via mlx5 ifc
  net/mlx5: MCG commands via mlx5 ifc
  net/mlx5: Pages management commands via mlx5 ifc
  net/mlx5: EQ commands via mlx5 ifc
  {net,IB}/mlx5: CQ commands via mlx5 ifc
  {net,IB}/mlx5: MKey/PSV commands via mlx5 ifc
  {net,IB}/mlx5: QP/XRCD commands via mlx5 ifc
  {net,IB}/mlx5: Modify QP commands via mlx5 ifc
  net/mlx5: Unify and improve command interface
  net/mlx5: Improve driver log messages

 drivers/infiniband/hw/mlx5/cq.c                    | 110 +++---
 drivers/infiniband/hw/mlx5/main.c                  |  10 +-
 drivers/infiniband/hw/mlx5/mlx5_ib.h               |   2 +-
 drivers/infiniband/hw/mlx5/mr.c                    | 184 +++++----
 drivers/infiniband/hw/mlx5/qp.c                    | 189 ++++-----
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c      | 261 +++++++------
 drivers/net/ethernet/mellanox/mlx5/core/cq.c       | 109 ++----
 drivers/net/ethernet/mellanox/mlx5/core/debugfs.c  |  50 +--
 .../net/ethernet/mellanox/mlx5/core/en_common.c    |  23 +-
 .../net/ethernet/mellanox/mlx5/core/en_ethtool.c   |   3 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |  47 +--
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c   |   4 +-
 drivers/net/ethernet/mellanox/mlx5/core/eq.c       |  80 ++--
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c  |  98 ++---
 drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c   | 178 ++++-----
 drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h   |   7 +
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c  |  18 +-
 drivers/net/ethernet/mellanox/mlx5/core/fw.c       |  43 +--
 drivers/net/ethernet/mellanox/mlx5/core/mad.c      |  41 +-
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |  91 ++---
 drivers/net/ethernet/mellanox/mlx5/core/mcg.c      |  72 +---
 .../net/ethernet/mellanox/mlx5/core/mlx5_core.h    |  17 +-
 drivers/net/ethernet/mellanox/mlx5/core/mr.c       | 189 ++++-----
 .../net/ethernet/mellanox/mlx5/core/pagealloc.c    | 156 +++-----
 drivers/net/ethernet/mellanox/mlx5/core/pd.c       |  61 +--
 drivers/net/ethernet/mellanox/mlx5/core/port.c     | 149 +++----
 drivers/net/ethernet/mellanox/mlx5/core/qp.c       | 299 ++++++++------
 drivers/net/ethernet/mellanox/mlx5/core/rl.c       |  11 +-
 drivers/net/ethernet/mellanox/mlx5/core/sriov.c    |   7 +-
 drivers/net/ethernet/mellanox/mlx5/core/srq.c      |  49 +--
 drivers/net/ethernet/mellanox/mlx5/core/transobj.c | 183 +++------
 drivers/net/ethernet/mellanox/mlx5/core/uar.c      |  67 +---
 drivers/net/ethernet/mellanox/mlx5/core/vport.c    |  94 ++---
 drivers/net/ethernet/mellanox/mlx5/core/vxlan.c    |  29 +-
 include/linux/mlx5/cq.h                            |   6 +-
 include/linux/mlx5/device.h                        | 429 +--------------------
 include/linux/mlx5/driver.h                        |  20 +-
 include/linux/mlx5/mlx5_ifc.h                      | 116 +++++-
 include/linux/mlx5/qp.h                            | 128 +-----
 include/linux/mlx5/vport.h                         |   2 +
 40 files changed, 1390 insertions(+), 2242 deletions(-)

--
Doug Ledford [off-list ref]
    GPG Key ID: 0E572FDD
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [for-next V3 00/15][PULL request] Mellanox mlx5 core driver updates 2016-08-20

From: Leon Romanovsky <hidden>
Date: 2016-08-23 18:39:29

On Tue, Aug 23, 2016 at 07:10:53PM +0300, Saeed Mahameed wrote:
On Tue, Aug 23, 2016 at 6:57 PM, Doug Ledford [off-list ref] wrote:
quoted
On 8/23/2016 4:49 AM, Saeed Mahameed wrote:
quoted
Hi Dave and Doug,

This series contains several low level and API updates for mlx5 core
commands interface and mlx5_ifc.h to be shared as base code for net-next and
rdma mlx5 4.9 submissions.

From Saeed, ten patches that refactors old layouts of firmware commands which
were manually generated before we introduced the mlx5_ifc, now all of the firmware
commands inbox/outbox layouts moved to use mlx5_ifc and we remove the old
manually generated structures.
These all looked fine to me.
quoted
Plus to those ten patches, we add two patches
that unifies mlx5 commands execution interface and improve the driver log messages
in that area.
These are the patches that made my eyes want to bleed.  But, since it's
all changes to the mailbox commands being sent to your device, they are
easy to verify operationally, so I only gave these a cursory review and
expect if any of your commands broke because of this you'll be
submitting fixes ASAP.
Thanks Doug for your review those patches already passed all kinds of
our internal regression testings.
What is nice about those patches is that they remove  ~1K  LOC from
driver and unify the command interface.
Thanks for taking them.
One of the reasons for such a long delay of shared code submission was our
desire to take extra care and test these patches again and again.
quoted
quoted
From Hadar and Ilya, added the needed hardware bits and infrastructure for
minimum inline headers setting and encap/decap commands and capabilities,
needed for E-Switch offloads.
These looked fine to me, but aren't really in the RDMA area anyway.
Our internal goal is to have 0-merge conflicts between RDMA and net
trees.
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help