[PATCH iproute2 V1 6/6] rdma: Add initial manual for the tool

From: Leon Romanovsky <leo...@mellanox.com> Signed-off-by: Leon Romanovsky <leo...@mellanox.com> --- man/man8/Makefile | 3 +- man/man8/rdma.8 | 82 +++ 2 files changed, 84 insertions(+), 1 deletion(-) create mode 100644 man

[PATCH iproute2 V1 5/6] rdma: Add FW version to the device output

From: Leon Romanovsky <leo...@mellanox.com> $ rdma dev show mlx5_4 5: mlx5_4: fw 2.8. caps: <BAD_PKEY_CNTR, BAD_QKEY_CNTR, CHANGE_PHY_PORT, PORT_ACTIVE_EVENT, SYS_IMAGE_GUID, RC_RNR_NAK_GEN, MEM_WINDOW, UD_IP_CSUM, UD_TSO, XRC, MEM_MGT_EXTENSIONS, BLOCK_MULTICAST

[PATCH iproute2 V1 2/6] rdma: Add dev object

From: Leon Romanovsky <leo...@mellanox.com> Device (dev) object represents struct ib_device to user space. The supported commands are show, set and help, but it doesn't print anything except device name at this stage. The downstream patches will fill this object with subcommands. Pri

[PATCH iproute2 V1 1/6] rdma: Add basic infrastructure for RDMA tool

From: Leon Romanovsky <leo...@mellanox.com> RDMA devices are cross-functional devices from one side, but very tailored for the specific markets from another. Such diversity caused to spread of RDMA related configuration across various tools, e.g. devlink, ip, ethtool, ib specific and

[PATCH iproute2 V1 0/5] RDMAtool

From: Leon Romanovsky <leo...@mellanox.com> Hi, This is second version of series implementing the RDAMtool - the tool to configure RDMA devices. The initial proposal was sent as RFC [1] and was based on sysfs entries as POC. The current series was rewritten completely to work wit

[PATCH iproute2 V1 3/6] rdma: Add device capability parsing

From: Leon Romanovsky <leo...@mellanox.com> Add parsing interface for the device capability flags $ rdma dev show 1: mlx5_0: caps: <BAD_PKEY_CNTR, BAD_QKEY_CNTR, CHANGE_PHY_PORT, PORT_ACTIVE_EVENT, SYS_IMAGE_GUID, RC_RNR_NAK_GEN, MEM_WINDOW, UD_IP_CSUM, UD_TSO, XRC, MEM_MGT_E

[PATCH iproute2 V1 4/6] rdma: Add link option and parsing

From: Leon Romanovsky <leo...@mellanox.com> Add link object interface together with port capability parsing command $ rdma link 1/1: mlx5_0/1: caps: 2/1: mlx5_1/1: caps: 3/1: mlx5_2/1: caps: 4/1: mlx5_3/1: caps: <CM, IP_BASED_GIDS> 5/1: mlx5_4/1: caps: $ rd

Re: [PATCH iproute2 3/5] rdma: Add device capability parsing

On Tue, Jun 27, 2017 at 10:41:50AM -0600, Jason Gunthorpe wrote: > On Tue, Jun 27, 2017 at 12:21:29PM +0300, Leon Romanovsky wrote: > > > What will be the output of such command? > > > $ rdma dev show mlx5_4 > > > > ip-like style: > > > > $ rdm

Re: [PATCH iproute2 V1 3/6] rdma: Add device capability parsing

On Tue, Jun 27, 2017 at 04:04:49PM -0700, Stephen Hemminger wrote: > On Tue, 27 Jun 2017 17:39:17 +0300 > Leon Romanovsky <l...@kernel.org> wrote: > > > +static const char *dev_caps[64] = { > > + "RESIZE_MAX_WR", > > + "BAD_PKEY_CN

Re: [PATCH net-next] mlx5: work around unused function warning

On Thu, Apr 27, 2017 at 01:04:02PM +0200, Arnd Bergmann wrote: > The previous patch addressed a sparse warning but replaced it with a > compiler warning when CONFIG_MODULES is disabled: > > drivers/net/ethernet/mellanox/mlx5/core/ipoib.c:485:13: error: > 'mlx5_rdma_netdev_free' defined but not

Re: [PATCH net-next] mlx5: work around unused function warning

On Thu, Apr 27, 2017 at 02:04:15PM +0200, Arnd Bergmann wrote: > On Thu, Apr 27, 2017 at 1:55 PM, Leon Romanovsky <leo...@mellanox.com> wrote: > > On Thu, Apr 27, 2017 at 01:04:02PM +0200, Arnd Bergmann wrote: > >> The previous patch addressed a sparse warning but replaced

[PATCH rdma-next] IB/mlx5: Enable IPoIB acceleration

IPoIB acceleration by default (in the mlx5_core Kconfig file). Signed-off-by: Saeed Mahameed <sae...@mellanox.com> Signed-off-by: Erez Shitrit <ere...@mellanox.com> Signed-off-by: Leon Romanovsky <l...@kernel.org> --- Hi Doug, This is connection patch between IPoIB mlx5_core and mlx5_ib

Re: [PATCH V4 net-next 2/8] net: hns3: Add support of the HNAE3 framework

On Thu, Jul 27, 2017 at 11:44:32PM +, Salil Mehta wrote: > Hi Leon > > > -Original Message- > > From: linux-rdma-ow...@vger.kernel.org [mailto:linux-rdma- > > ow...@vger.kernel.org] On Behalf Of Leon Romanovsky > > Sent: Sunday, July 23, 2017 2:16 PM

Re: [PATCH REPOST v5 iproute2 0/8] RDMAtool

On Thu, Aug 17, 2017 at 06:01:18PM -0700, Stephen Hemminger wrote: > On Thu, 17 Aug 2017 09:56:06 +0300 > Leon Romanovsky <leo...@mellanox.com> wrote: > > > This is fifth revision of series implementing the RDAMtool - the tool > > to configure RDMA devices. > &g

Re: [PATCH V2 net-next] net: hns3: Add support to change MTU in HNS3 hardware

On Sun, Aug 20, 2017 at 02:35:58PM +, Salil Mehta wrote: > Hi Leon > > > -Original Message- > > From: Leon Romanovsky [mailto:l...@kernel.org] > > Sent: Sunday, August 20, 2017 8:05 AM > > To: Salil Mehta > > Cc: da...@davemloft.net; Zhuangyuzeng

Re: [PATCH v4] net/mlx4_core: Use min3 to select number of MSI-X vectors

On Sun, May 14, 2017 at 10:01:34PM +0300, Yuval Shaia wrote: > On Fri, May 12, 2017 at 09:10:51AM +0300, Yuval Shaia wrote: > > Signed-off-by: Yuval Shaia > > --- > > v0 -> v1: > > * s/"min_t("/"min_t(int" > > v1 -> v2: > > * Use min3 instead of min_t twice > > v2

Re: [PATCH v4] net/mlx4_core: Use min3 to select number of MSI-X vectors

On Mon, May 15, 2017 at 10:53:24AM +0300, Yuval Shaia wrote: > On Mon, May 15, 2017 at 07:43:04AM +0300, Leon Romanovsky wrote: > > On Sun, May 14, 2017 at 10:01:34PM +0300, Yuval Shaia wrote: > > > On Fri, May 12, 2017 at 09:10:51AM +0300, Yuval Shaia wrote: > > > &

Re: [PATCH] net/smc: mark as BROKEN due to remote memory exposure

On Sun, May 14, 2017 at 11:51:16AM -0400, David Miller wrote: > From: Christoph Hellwig > Date: Sun, 14 May 2017 07:58:48 +0200 > > > this patch has not been superceeded by anything, can you explain why > > it has been marked as such in patchworks? > > I think you're being

Re: [PATCH] net/mlx4_core: Use min_t instead of if for consistency

On Thu, May 11, 2017 at 11:20:52AM +0300, Yuval Shaia wrote: > Signed-off-by: Yuval Shaia > --- > drivers/net/ethernet/mellanox/mlx4/main.c | 9 - > 1 file changed, 4 insertions(+), 5 deletions(-) > > diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c >

Re: [PATCH v2] net/mlx4_core: Use min_t instead of if for consistency

et/ethernet/mellanox/mlx4/main.c | 9 +++-- > 1 file changed, 3 insertions(+), 6 deletions(-) > Thanks, Reviewed-by: Leon Romanovsky <leo...@mellanox.com> signature.asc Description: PGP signature

Re: [PATCH v1] net/mlx4_core: Use min_t instead of if for consistency

On Thu, May 11, 2017 at 11:46:29AM +0300, Yuval Shaia wrote: > Signed-off-by: Yuval Shaia > --- > v0 -> v1: > * s/"min_t("/"min_t(int" > --- > drivers/net/ethernet/mellanox/mlx4/main.c | 9 - > 1 file changed, 4 insertions(+), 5 deletions(-) > > diff --git

Re: [PATCH v3] net/mlx4_core: Use min3 to select number of MSI-X vectors

* Change commit log header message to reflect the changes made in > v2 > --- > drivers/net/ethernet/mellanox/mlx4/main.c | 9 +++-- > 1 file changed, 3 insertions(+), 6 deletions(-) > Thanks, Reviewed-by: Leon Romanovsky <leo...@mellanox.com> signature.asc Description: PGP signature

Re: [RFC iproute2 0/8] RDMA tool

On Mon, May 08, 2017 at 11:55:25AM -0400, Dennis Dalessandro wrote: > On 05/04/2017 03:42 PM, Leon Romanovsky wrote: > > On Thu, May 04, 2017 at 03:26:13PM -0400, Dennis Dalessandro wrote: > > > On 05/04/2017 02:45 PM, Leon Romanovsky wrote: > > > > On Thu, May 04,

Re: [PATCH] net/smc: mark as BROKEN due to remote memory exposure

On Wed, May 17, 2017 at 08:07:00PM -0400, Doug Ledford wrote: > On 5/17/2017 6:37 PM, Parav Pandit wrote: > > Hi Doug, > > > > >> It would have been better with AF_INET/AF_INET6 and an option to enable > >> SMC than AF_SMC. The first implementation simply assumes AF_INET in > >> the presence of

Re: [PATCH V2 net 1/1] smc: switch to usage of IB_PD_UNSAFE_GLOBAL_RKEY

On Fri, May 12, 2017 at 07:09:52PM +0200, Ursula Braun wrote: > This patch makes users aware of the current security implications > when using smc. > > The final fix to resolve the reported security issue is worked on; > respective patches will follow as soon as possible. > > Signed-off-by: Ursula

[PATCH net v1] net/smc: Add warning about remote memory exposure

From: Christoph Hellwig <h...@lst.de> The driver explicitly bypasses APIs to register all memory once a connection is made, and thus allows remote access to memory. Signed-off-by: Christoph Hellwig <h...@lst.de> Signed-off-by: Leon Romanovsky <l...@kernel.org> --- Dave, Can

Re: [PATCH net v1] net/smc: Add warning about remote memory exposure

+ linux-rdma ML. On Tue, May 16, 2017 at 09:51:38AM +0300, Leon Romanovsky wrote: > From: Christoph Hellwig <h...@lst.de> > > The driver explicitly bypasses APIs to register all memory once a > connection is made, and thus allows remote access to memory. > > Signed-off-

[PATCH net-next] bnx2x: Remove open coded carrier check

From: Leon Romanovsky <leo...@mellanox.com> There is inline function to test if carrier present, so it makes open-coded solution redundant. Signed-off-by: Leon Romanovsky <leo...@mellanox.com> --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 2 +- 1 file changed, 1 ins

Re: [PATCH net-next 0/3] LiquidIO: avoid VM low memory crashes

On Wed, Jun 07, 2017 at 08:50:45PM -0700, Felix Manlunas wrote: > From: Rick Farrington > > This patchset addresses issues brought about by low memory conditions > in a VM. These conditions were only seen when VM's were intentionally > created with small amounts of

Re: Netlink messages without NLM_F_REQUEST flag

On Wed, Jun 07, 2017 at 12:35:11PM -0600, Jason Gunthorpe wrote: > On Wed, Jun 07, 2017 at 09:18:10PM +0300, Leon Romanovsky wrote: > > > > AFAIK, that is different, that is acking and retriggering a single shot > > > notification, not completing a kernel initiated handsha

[PATCH rdma-next 08/19] RDMA/core: Expose translation from device name to ib_device

From: Leon Romanovsky <leo...@mellanox.com> Provide ability to convert from device name to ib_device for the IB/core users. Signed-off-by: Leon Romanovsky <leo...@mellanox.com> --- drivers/infiniband/core/core_priv.h | 1 + drivers/infiniband/core/device.c| 3 +-- 2 file

[PATCH rdma-next 10/19] RDMA/netlink: Reduce indirection access to cb_table

From: Leon Romanovsky <leo...@mellanox.com> Introduce intermediate variable to store access to fields of cb_table. Signed-off-by: Leon Romanovsky <leo...@mellanox.com> --- drivers/infiniband/core/netlink.c | 13 - 1 file changed, 8 insertions(+), 5 deletions(-) diff --g

[PATCH rdma-next 11/19] RDMA/netlink: Convert LS to doit callback

From: Leon Romanovsky <leo...@mellanox.com> RDMA_NL_LS protocol is actually is not dump anything, but sets data and it should be handled by doit callback. This patch actually converts RDMA_NL_LS to doit callback, while preserving IWCM and RDMA_CM flows through netlink_dump_start(). Sign

[PATCH rdma-next 13/19] RDMA/netlink: Add netlink device definitions to UAPI

From: Leon Romanovsky <leo...@mellanox.com> Introduce new defines to rdma_netlink.h, so the RDMA configuration tool will be able to communicate with RDMA subsystem by using the shared defines. The addition of new client (NLDEV) revealed the fact that we exposed by mistake the RDMA_NL

[PATCH rdma-next 18/19] RDMA/netlink: Implement nldev port doit callback

From: Leon Romanovsky <leo...@mellanox.com> Provide ability to get specific to device and port information. Signed-off-by: Leon Romanovsky <leo...@mellanox.com> --- drivers/infiniband/core/nldev.c | 45 + 1 file changed, 45 insertions(+)

[PATCH rdma-next 01/19] RDMA/netlink: Add flag to consolidate common handing

From: Leon Romanovsky <leo...@mellanox.com> Add ability to provide flags to control RDMA netlink callbacks and convert addr.c and sa_query.c to be first users of such infrastructure. It allows to move their CAP_NET_ADMIN checks into netlink core. Signed-off-by: Leon Romanovsk

[PATCH rdma-next 00/19] RDMA Netlink Device Client

ien.tin.t...@intel.com> CC: Steve Wise <sw...@opengridcomputing.com> CC: Stephen Hemminger <step...@networkplumber.org> CC: Jiri Pirko <j...@mellanox.com> CC: Ariel Almog <ari...@mellanox.com> CC: Linux RDMA <linux-r...@vger.kernel.org> CC: Linux Netdev <ne

[PATCH rdma-next 02/19] RDMA/netlink: Simplify the put_msg and put_attr

From: Leon Romanovsky <leo...@mellanox.com> Reuse standard macros to cancel the netlink message in case of error. Signed-off-by: Leon Romanovsky <leo...@mellanox.com> --- drivers/infiniband/core/netlink.c | 31 +-- 1 file changed, 9 insertions(+),

[PATCH rdma-next 06/19] RDMA/netlink: Rename netlink callback struct

From: Leon Romanovsky <leo...@mellanox.com> The RDMA netlink client infrastructure was removed and made obsolete the old name (ibnl_client_cbs). This patch renames to the more appropriate name (rdma_nl_cbs). Signed-off-by: Leon Romanovsky <leo...@mellanox.com> --- drivers/infiniban

[PATCH rdma-next 04/19] RDMA/netlink: Rename and remove redundant parameter from ibnl_multicast

From: Leon Romanovsky <leo...@mellanox.com> The pointer to netlink header was not used in the ibnl_multicast function, so let's remove it and simplify the function signature. Signed-off-by: Leon Romanovsky <leo...@mellanox.com> --- drivers/infiniband/core/addr.c | 2 +- driver

[PATCH rdma-next 05/19] RDMA/netlink: Simplify and rename ibnl_chk_listeners

From: Leon Romanovsky <leo...@mellanox.com> Make ibnl_chk_listeners function to be one line by removing unneeded comparison. Rename that function to be complaint to other functions in RDMA netlink. Signed-off-by: Leon Romanovsky <leo...@mellanox.com> --- drivers/infiniband/core/ad

[PATCH rdma-next 16/19] RDMa/netlink: Add nldev device doit implementation

From: Leon Romanovsky <leo...@mellanox.com> Provide ability to query specific device. Signed-off-by: Leon Romanovsky <leo...@mellanox.com> --- drivers/infiniband/core/nldev.c | 40 1 file changed, 40 insertions(+) diff --git a/drivers/inf

[PATCH rdma-next 12/19] RDMA/netlink: Update copyright

From: Leon Romanovsky <leo...@mellanox.com> Add Mellanox to the copyright header. Signed-off-by: Leon Romanovsky <leo...@mellanox.com> --- drivers/infiniband/core/netlink.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/co

[PATCH rdma-next 07/19] RDMA/core: Add iterator over ib_devices

From: Leon Romanovsky <leo...@mellanox.com> The coming nldev needs iterate over all IB devices in the system and in order do not expose the ib_devices list outside the devices.c, it is necessary to provide function iterator. Current version is written explicitly for nldev callback to avoi

[PATCH rdma-next 09/19] RDMA/netlink: Add and implement doit netlink callback

From: Leon Romanovsky <leo...@mellanox.com> The .doit callback is used by netlink core to differentiate between get and set operations. Common convention is to use that call for command operations like (SET, ADD, e.t.c.) and/or access without NLF_M_DUMP flag. This commit adds proper decla

[PATCH rdma-next 03/19] RDMA/netlink: Rename and remove redundant parameter from ibnl_unicast

From: Leon Romanovsky <leo...@mellanox.com> Netlink message header is not needed for unicast reply, hence remove it. Signed-off-by: Leon Romanovsky <leo...@mellanox.com> --- drivers/infiniband/core/iwpm_msg.c | 6 +++--- drivers/infiniband/core/iwpm_util.c | 4 ++-- drivers/inf

[PATCH rdma-next 15/19] RDMA/netlink: Implement nldev device dumpit calback

From: Leon Romanovsky <leo...@mellanox.com> This patch adds the ability to return all available devices together with their properties. Signed-off-by: Leon Romanovsky <leo...@mellanox.com> --- drivers/infiniband/core/nldev.c | 61 - 1 file

[PATCH rdma-next 14/19] RDMA/netlink: Add nldev initialization flows

From: Leon Romanovsky <leo...@mellanox.com> Add nldev init and exit flows to the RDMA/core. Signed-off-by: Leon Romanovsky <leo...@mellanox.com> --- drivers/infiniband/core/Makefile| 4 +++- drivers/infiniband/core/core_priv.h | 4 drivers/infiniband/core/device.c| 2

[PATCH rdma-next 17/19] RDMA/netlink: Add nldev port dumpit implementation

From: Leon Romanovsky <leo...@mellanox.com> This patch implements the query interface to get all ports data for the specific device. Signed-off-by: Leon Romanovsky <leo...@mellanox.com> --- drivers/infiniband/core/nldev.c | 60 + 1 file

[PATCH rdma-next 19/19] RDMA/netlink: Expose device and port capability masks

From: Leon Romanovsky <leo...@mellanox.com> The port capability mask is exposed to user space via sysfs interface, while device capabilities are available for verbs only. This patch provides those capabilities through netlink interface. Signed-off-by: Leon Romanovsky <leo...@mel

Re: [PATCH v4 net-next 0/7] qed*: RDMA and infrastructure for iWARP

On Wed, Jun 21, 2017 at 12:57:36PM +0300, Or Gerlitz wrote: > On Wed, Jun 21, 2017 at 12:56 PM, Or Gerlitz wrote: > > On Tue, Jun 20, 2017 at 7:35 PM, David Miller wrote: > >> From: Yuval Mintz > >> Date: Tue, 20 Jun 2017

Re: [PATCH rdma-next 13/19] RDMA/netlink: Add netlink device definitions to UAPI

On Wed, Jun 21, 2017 at 04:18:54PM +, Tung, Chien Tin wrote: > > From: Jason Gunthorpe [mailto:jguntho...@obsidianresearch.com] > > Sent: Wednesday, June 21, 2017 11:12 AM > > To: Leon Romanovsky <l...@kernel.org> > > Cc: Doug Ledford <dledf...@redhat.com&g

Re: [PATCH rdma-next 08/19] RDMA/core: Expose translation from device name to ib_device

On Wed, Jun 21, 2017 at 10:07:48AM -0600, Jason Gunthorpe wrote: > On Wed, Jun 21, 2017 at 09:05:17AM +0300, Leon Romanovsky wrote: > > From: Leon Romanovsky <leo...@mellanox.com> > > > > Provide ability to convert from device name to ib_device for the > > IB/c

[PATCH rdma-next V1 04/19] RDMA/netlink: Rename and remove redundant parameter from ibnl_multicast

From: Leon Romanovsky <leo...@mellanox.com> The pointer to netlink header was not used in the ibnl_multicast function, so let's remove it and simplify the function signature. Signed-off-by: Leon Romanovsky <leo...@mellanox.com> Reviewed-by: Steve Wise <sw...@opengridcomputing.co

[PATCH rdma-next V1 03/19] RDMA/netlink: Rename and remove redundant parameter from ibnl_unicast

From: Leon Romanovsky <leo...@mellanox.com> Netlink message header is not needed for unicast reply, hence remove it. Signed-off-by: Leon Romanovsky <leo...@mellanox.com> Reviewed-by: Steve Wise <sw...@opengridcomputing.com> --- drivers/infiniband/core/iwpm_msg.c | 6 +++---

[PATCH rdma-next V1 02/19] RDMA/netlink: Simplify the put_msg and put_attr

From: Leon Romanovsky <leo...@mellanox.com> Reuse standard macros to cancel the netlink message in case of error. Signed-off-by: Leon Romanovsky <leo...@mellanox.com> Reviewed-by: Steve Wise <sw...@opengridcomputing.com> --- drivers/infiniband/c

Re: [PATCH rdma-next 17/19] RDMA/netlink: Add nldev port dumpit implementation

On Wed, Jun 21, 2017 at 09:28:12AM -0500, Steve Wise wrote: > > From: Leon Romanovsky <leo...@mellanox.com> > > > > This patch implements the query interface to get all > > ports data for the specific device. > > > > Signed-off-by: Leon Romanovsky <le

Re: [PATCH rdma-next 11/19] RDMA/netlink: Convert LS to doit callback

On Wed, Jun 21, 2017 at 09:18:25AM -0500, Steve Wise wrote: > > From: Leon Romanovsky <leo...@mellanox.com> > > > > RDMA_NL_LS protocol is actually is not dump anything, > > nit: "is not" -> "does not" > > > but sets data and it s

Re: [PATCH rdma-next 08/19] RDMA/core: Expose translation from device name to ib_device

On Wed, Jun 21, 2017 at 09:09:27AM -0500, Steve Wise wrote: > > From: Leon Romanovsky <leo...@mellanox.com> > > > > Provide ability to convert from device name to ib_device for the > > IB/core users. > > > > Signed-off-by: Leon Romanovsky <leo...@mella

[PATCH rdma-next V1 01/19] RDMA/netlink: Add flag to consolidate common handing

From: Leon Romanovsky <leo...@mellanox.com> Add ability to provide flags to control RDMA netlink callbacks and convert addr.c and sa_query.c to be first users of such infrastructure. It allows to move their CAP_NET_ADMIN checks into netlink core. Signed-off-by: Leon Romanovsk

[PATCH rdma-next V1 00/19] RDMA Netlink Device Client

computing.com> CC: Stephen Hemminger <step...@networkplumber.org> CC: Jason Gunthorpe <jguntho...@obsidianresearch.com> CC: Jiri Pirko <j...@mellanox.com> CC: Ariel Almog <ari...@mellanox.com> CC: Linux RDMA <linux-r...@vger.kernel.org> CC: Linux Netdev <netdev@vg

[PATCH rdma-next V1 08/19] RDMA/core: Add and expose static device index

From: Leon Romanovsky <leo...@mellanox.com> This patch adds static device index in similar fashion to already available in netdev world (struct net->ifindex). In downstream patches, the RDMA nelink will use this idx-to-ib_device conversion, so as part of this commit, we are

[PATCH rdma-next V1 16/19] RDMA/netlink: Add nldev device doit implementation

From: Leon Romanovsky <leo...@mellanox.com> Provide ability to query specific device. Signed-off-by: Leon Romanovsky <leo...@mellanox.com> Reviewed-by: Steve Wise <sw...@opengridcomputing.com> --- drivers/infiniband/core/nldev.c | 40

[PATCH rdma-next V1 12/19] RDMA/netlink: Update copyright

From: Leon Romanovsky <leo...@mellanox.com> Add Mellanox to the copyright header. Signed-off-by: Leon Romanovsky <leo...@mellanox.com> Reviewed-by: Steve Wise <sw...@opengridcomputing.com> --- drivers/infiniband/core/netlink.c | 1 + 1 file changed, 1 insertion(+) di

[PATCH rdma-next V1 13/19] RDMA/netlink: Add netlink device definitions to UAPI

From: Leon Romanovsky <leo...@mellanox.com> Introduce new defines to rdma_netlink.h, so the RDMA configuration tool will be able to communicate with RDMA subsystem by using the shared defines. The addition of new client (NLDEV) revealed the fact that we exposed by mistake the RDMA_NL

[PATCH rdma-next V1 09/19] RDMA/netlink: Add and implement doit netlink callback

From: Leon Romanovsky <leo...@mellanox.com> The .doit callback is used by netlink core to differentiate between get and set operations. Common convention is to use that call for command operations like (SET, ADD, e.t.c.) and/or access without NLF_M_DUMP flag. This commit adds proper decla

[PATCH rdma-next V1 06/19] RDMA/netlink: Rename netlink callback struct

From: Leon Romanovsky <leo...@mellanox.com> The RDMA netlink client infrastructure was removed and made obsolete the old name (ibnl_client_cbs). This patch renames to the more appropriate name (rdma_nl_cbs). Signed-off-by: Leon Romanovsky <leo...@mellanox.com> Reviewed-by: St

[PATCH rdma-next V1 15/19] RDMA/netlink: Implement nldev device dumpit calback

From: Leon Romanovsky <leo...@mellanox.com> This patch adds the ability to return all available devices together with their properties. Signed-off-by: Leon Romanovsky <leo...@mellanox.com> Reviewed-by: Steve Wise <sw...@opengridcomputing.com> --- drivers/infiniband

[PATCH iproute2 5/5] rdma: Add initial manual for the tool

From: Leon Romanovsky <leo...@mellanox.com> Signed-off-by: Leon Romanovsky <leo...@mellanox.com> --- man/man8/rdma.8 | 82 + 1 file changed, 82 insertions(+) create mode 100644 man/man8/rdma.8 diff --git a/man/man8/rdma.8 b/m

[PATCH iproute2 2/5] rdma: Add dev object

From: Leon Romanovsky <leo...@mellanox.com> Device (dev) object represents struct ib_device to user space. The supported commands are show, set and help, but it doesn't print anything except device name at this stage. The downstream patches will fill this object with subcommands. Pri

[PATCH iproute2 0/5] RDMAtool

From: Leon Romanovsky <leo...@mellanox.com> Hi, This series is implementing the RDAMtool - the tool to configure RDMA devices. The initial proposal was sent as RFC [1] and was based on sysfs entries as POC. The current series was rewritten completely to work with RDMA netlinks as a

[PATCH iproute2 3/5] rdma: Add device capability parsing

From: Leon Romanovsky <leo...@mellanox.com> Add parsing interface for the device capability flags $ rdma dev show 1: mlx5_0: caps 0x1257e1c26 2: mlx5_1: caps 0x1257e1c26 3: mlx5_2: caps 0x1257e1c26 4: mlx5_3: caps 0x1257e1c26 5: mlx5_4: caps 0x1257e1c26 $ rdma dev show mlx5_4 5: mlx5_4

[PATCH iproute2 4/5] rdma: Add link option and parsing

From: Leon Romanovsky <leo...@mellanox.com> Add link object interface together with port capability parsing command $ rdma link 1/1: mlx5_0/1: caps 0x20 2/1: mlx5_1/1: caps 0x20 3/1: mlx5_2/1: caps 0x20 4/1: mlx5_3/1: caps 0x401 5/1: mlx5_4/1: caps 0x20 $ rdma link show mlx5_4 5/1: ml

[PATCH iproute2 1/5] rdma: Add basic infrastructure for RDMA tool

From: Leon Romanovsky <leo...@mellanox.com> RDMA devices are cross-functional devices from one side, but very tailored for the specific markets from another. Such diversity caused to spread of RDMA related configuration across various tools, e.g. devlink, ip, ethtool, ib specific and

Re: [PATCH iproute2 3/5] rdma: Add device capability parsing

On Mon, Jun 26, 2017 at 12:29:24PM -0600, Jason Gunthorpe wrote: > On Mon, Jun 26, 2017 at 09:21:26PM +0300, Leon Romanovsky wrote: > > From: Leon Romanovsky <leo...@mellanox.com> > > > > Add parsing interface for the device capability flags > > > > $ rdma d

Re: [PATCH iproute2 3/5] rdma: Add device capability parsing

On Mon, Jun 26, 2017 at 02:36:10PM -0600, Jason Gunthorpe wrote: > On Mon, Jun 26, 2017 at 10:21:03PM +0300, Leon Romanovsky wrote: > > On Mon, Jun 26, 2017 at 12:29:24PM -0600, Jason Gunthorpe wrote: > > > On Mon, Jun 26, 2017 at 09:21:26PM +0300, Leon Romanovsky wrote:

Re: [RFC 15/19] RDMA/qedr: Add iWARP support in existing verbs.

On Mon, Jun 26, 2017 at 09:07:05PM +0300, Michal Kalderon wrote: > Make slight modifications to common RoCE/iWARP code. > Add additional doorbell for iWARP post_send. > iWARP QP pbl is allocated in qed and not in qedr. > > Signed-off-by: Michal Kalderon >

Re: [RFC 01/19] qed: Introduce iWARP personality

On Mon, Jun 26, 2017 at 09:06:51PM +0300, Michal Kalderon wrote: > iWARP personality introduced the need for differentiating in several > places in the code whether we are RoCE, iWARP or either. This > leads to introducing new macros for querying the personality. > > Signed-off-by: Michal Kalderon

Re: [RFC 02/19] qed: Implement iWARP initialization, teardown and qp operations

On Mon, Jun 26, 2017 at 09:06:52PM +0300, Michal Kalderon wrote: > This patch adds iWARP support for flows that have common code > between RoCE and iWARP, such as initialization, teardown and > qp setup verbs: create, destroy, modify, query. > It introduces the iWARP specific files qed_iwarp.[ch]

Re: [PATCH] i40e: handle setting administratively set MAC address back to zero

On Fri, Jun 23, 2017 at 09:46:24AM +0200, Stefan Assmann wrote: > When an administratively set MAC was previously set and should now be > switched back to 00:00:00:00:00:00 the pf_set_mac flag did not get > toggled back to false. > As a result VFs were still treated as if an administratively set

Re: [PATCH net-next] liquidio: standardization: use min_t instead of custom macro

On Sat, Jun 24, 2017 at 04:31:56AM -0700, Felix Manlunas wrote: > From: Rick Farrington > > Replaced custom MIN macro with use of standard 'min_t'. > > Signed-off-by: Rick Farrington > Signed-off-by: Derek Chickles

Re: [PATCH net-next] liquidio: fix bug in soft reset failure detection

On Sat, Jun 24, 2017 at 04:00:21AM -0700, Felix Manlunas wrote: > From: Derek Chickles > > The code that detects a failed soft reset of Octeon is comparing the wrong > value against the reset value of the Octeon SLI_SCRATCH_1 register, > resulting in an inability to

[PATCH rdma-next V1 11/19] RDMA/netlink: Convert LS to doit callback

From: Leon Romanovsky <leo...@mellanox.com> RDMA_NL_LS protocol is actually does not dump anything, but sets data and it should be handled by doit callback. This patch actually converts RDMA_NL_LS to doit callback, while preserving IWCM and RDMA_CM flows through netlink_dump_start(). Sign

[PATCH rdma-next V1 10/19] RDMA/netlink: Reduce indirection access to cb_table

From: Leon Romanovsky <leo...@mellanox.com> Introduce intermediate variable to store access to fields of cb_table. Signed-off-by: Leon Romanovsky <leo...@mellanox.com> Reviewed-by: Steve Wise <sw...@opengridcomputing.com> --- drivers/infiniband/core/netlink.c | 13 ---

[PATCH rdma-next V1 18/19] RDMA/netlink: Implement nldev port doit callback

From: Leon Romanovsky <leo...@mellanox.com> Provide ability to get specific to device and port information. Signed-off-by: Leon Romanovsky <leo...@mellanox.com> Reviewed-by: Steve Wise <sw...@opengridcomputing.com> --- drivers/infiniband

[PATCH rdma-next V1 19/19] RDMA/netlink: Expose device and port capability masks

From: Leon Romanovsky <leo...@mellanox.com> The port capability mask is exposed to user space via sysfs interface, while device capabilities are available for verbs only. This patch provides those capabilities through netlink interface. Signed-off-by: Leon Romanovsky <leo...@mel

[PATCH rdma-next V1 07/19] RDMA/core: Add iterator over ib_devices

From: Leon Romanovsky <leo...@mellanox.com> The coming nldev needs to iterate over all IB devices in the system and in order to not expose the ib_devices list outside the devices.c, it is necessary to provide function iterator. Current version is written explicitly for nldev callback to

[PATCH rdma-next V1 05/19] RDMA/netlink: Simplify and rename ibnl_chk_listeners

From: Leon Romanovsky <leo...@mellanox.com> Make ibnl_chk_listeners function to be one line by removing unneeded comparison. Rename that function to be complaint to other functions in RDMA netlink. Signed-off-by: Leon Romanovsky <leo...@mellanox.com> Reviewed-by: St

[PATCH rdma-next V1 17/19] RDMA/netlink: Add nldev port dumpit implementation

From: Leon Romanovsky <leo...@mellanox.com> This patch implements the query interface to get all ports data for the specific device. Signed-off-by: Leon Romanovsky <leo...@mellanox.com> Reviewed-by: Steve Wise <sw...@opengridcomputing.com> --- drivers/infiniband

[PATCH rdma-next V1 14/19] RDMA/netlink: Add nldev initialization flows

From: Leon Romanovsky <leo...@mellanox.com> Add nldev init and exit flows to the RDMA/core. Signed-off-by: Leon Romanovsky <leo...@mellanox.com> Reviewed-by: Steve Wise <sw...@opengridcomputing.com> --- drivers/infiniband/core/Makefile | 4 +++- drivers/infiniband/

Re: [PATCH rdma-next 17/19] RDMA/netlink: Add nldev port dumpit implementation

On Wed, Jun 21, 2017 at 05:42:11PM +0300, Leon Romanovsky wrote: > On Wed, Jun 21, 2017 at 09:28:12AM -0500, Steve Wise wrote: > > > From: Leon Romanovsky <leo...@mellanox.com> > > > > > > This patch implements the query interface to get all >

Re: [PATCH iproute2 3/5] rdma: Add device capability parsing

On Tue, Jun 27, 2017 at 11:37:35AM -0600, Jason Gunthorpe wrote: > On Tue, Jun 27, 2017 at 08:33:01PM +0300, Leon Romanovsky wrote: > > > My initial plan was to put all parsers under their respective names, in > > the similar way as I did for caps: $ rdma dev show mlx5_4 ca

Re: [PATCH iproute2 3/5] rdma: Add device capability parsing

On Tue, Jun 27, 2017 at 07:06:04AM +0300, Leon Romanovsky wrote: > On Mon, Jun 26, 2017 at 02:36:10PM -0600, Jason Gunthorpe wrote: > > On Mon, Jun 26, 2017 at 10:21:03PM +0300, Leon Romanovsky wrote: > > > On Mon, Jun 26, 2017 at 12:29:24PM -0600, Jason Gunthorpe wrote: >

Re: [PATCH v9 06/15] mlx5: Replace PCI pool old API

2 +- > 2 files changed, 7 insertions(+), 6 deletions(-) > Who is supposed to merge this patch series? Acked-by: Leon Romanovsky <leo...@mellanox.com> signature.asc Description: PGP signature

Re: [PATCH net] net/mlx4: Fix the check in attaching steering rules

On Tue, May 23, 2017 at 04:15:13PM +0300, Leon Romanovsky wrote: > On Tue, May 23, 2017 at 03:50:07PM +0300, Tariq Toukan wrote: > > From: Talat Batheesh <tal...@mellanox.com> > > > > Our previous patch (cited below) introduced a regression > > for RAW Eth QPs. >

Re: [PATCH net] net/mlx4: Fix the check in attaching steering rules

On Tue, May 23, 2017 at 03:50:07PM +0300, Tariq Toukan wrote: > From: Talat Batheesh > > Our previous patch (cited below) introduced a regression > for RAW Eth QPs. > > Fix it by checking if the QP number provided by user-space > exists, hence allowing steering rules to be

Re: [for-next 5/6] net/mlx5: Bump driver version

On Fri, May 26, 2017 at 12:55:22PM -0400, Dennis Dalessandro wrote: > On 5/26/2017 12:35 PM, Saeed Mahameed wrote: > > On Fri, May 26, 2017 at 3:56 PM, Dennis Dalessandro > > wrote: > > > On 5/23/2017 7:44 AM, Saeed Mahameed wrote: > > > Anyway i don't think we are

Re: [PATCH v9 06/15] mlx5: Replace PCI pool old API

On Tue, May 23, 2017 at 10:53:36AM +0200, Romain Perier wrote: > Hello, > > > Le 23/05/2017 à 09:27, Leon Romanovsky a écrit : > > On Mon, May 22, 2017 at 06:48:58PM +0200, Romain Perier wrote: > >> The PCI pool API is deprecated. This commit replaces the PCI pool old

Re: [for-next 5/6] net/mlx5: Bump driver version

On Fri, May 26, 2017 at 02:53:18PM -0700, Jakub Kicinski wrote: > On Fri, 26 May 2017 12:55:22 -0400, Dennis Dalessandro wrote: > > >> I realize Dave has already pulled this and I'm not asking for it to be > > >> reverted but maybe some discussion will help guide future patch > > >> submissions >

Re: [pull request][for-next 0/6] Mellanox mlx5 updates 2017-05-23

On Thu, Jun 01, 2017 at 06:57:59PM -0400, Doug Ledford wrote: > On Thu, 2017-05-25 at 12:02 -0400, David Miller wrote: > > From: Saeed Mahameed > > Date: Tue, 23 May 2017 14:43:58 +0300 > > > > > Hi Dave and Doug, > > >  > > > This series introduces some small updates and

<    1   2   3   4   5   6   7   8   9   10   >