The initial assignment to mdev is redundant as mdev is re-assigned
later and the first assigned value is never read. Remove this
redundant assignment.
Cleans up clang warning:
drivers/infiniband/hw/mlx5/main.c:359:24: warning: Value stored
to 'mdev' during its initialization is never read
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Merging in 12 patch series from Bart that required changes in the
current for-rc branch in order to apply cleanly.
Signed-off-by: Doug Ledford <dledford@redhat.com>
When operating in dual port RoCE mode FW doesn't support steering for
raw QPs on the slave port. They still work on the master port, but
the user has no way of knowing which port is the master. The
capability is reported per device, not per port.
Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Route performance query MADs to the correct mlx5_core_dev when using
dual port RoCE mode.
Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
When in dual port mode setting a RoCE GID for any port flows through the
master ports mlx5_core_dev. Provide an interface to set the port when
sending this command.
Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Update the counter interface for multiple ports. Some counter sets
always comes from the primary device.
Port specific counters should be accessed per mlx5_core_dev not always
through the IB master mdev.
Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
When there are multiple ports for single IB(RoCE) device, support
debugfs entries to be available for each port.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Port operations must be routed to their native mlx5_core_dev. A
multiport RoCE device registers itself as having 2 ports even before a
2nd port is affiliated. If an unaffilated port is queried use capability
information from the master port, these values are the same.
Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Because mlx5_ib_event can be called from atomic context move event
handling onto a workqueue. A mutex lock is required to get the IB device
for slave ports, so move event processing onto a work queue. When an IB
event is received, check if the mlx5_core_dev is a slave port, if so
attempt to get the IB device it's affiliated with. If found process the
event for that device, otherwise return.
Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
When mlx5_ib_add is called determine if the mlx5 core device being
added is capable of dual port RoCE operation. If it is, determine
whether it is a master device or a slave device using the
num_vhca_ports and affiliate_nic_vport_criteria capabilities.
If the device is a slave, attempt to find a master device to affiliate it
with. Devices that can be affiliated will share a system image guid. If
none are found place it on a list of unaffiliated ports. If a master is
found bind the port to it by configuring the port affiliation in the NIC
vport context.
Similarly when mlx5_ib_remove is called determine the port type. If it's
a slave port, unaffiliate it from the master device, otherwise just
remove it from the unaffiliated port list.
The IB device is registered as a multiport device, even if a 2nd port is
not available for affiliation. When the 2nd port is affiliated later the
GID cache must be refreshed in order to get the default GIDs for the 2nd
port in the cache. Export roce_rescan_device to provide a mechanism to
refresh the cache after a new port is bound.
In a multiport configuration all IB object (QP, MR, PD, etc) related
commands should flow through the master mlx5_core_dev, other commands
must be sent to the slave port mlx5_core_mdev, an interface is provide
to get the correct mdev for non IB object commands.
Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
When multiple RoCE ports are supported registration for events on
multiple netdevs is required. Refactor the event registration and
handling to support multiple ports.
Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Remove use of the num_ports general capability throughout. The number of
ports will be variable in the future, and reported in a different way.
Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
A DC Target (DCT) QP is represented in the hardware as a unique object.
This object is created by CREATE_DCT command and destroyed by DESTROY_DCT
command. However, in the driver we describe it as a QP.
The hardware command that creates a DCT needs parameters that the verb
create_qp() does not provide. Those remaining parameters are provided
with the call to the verb modify_qp(). Therefore we delay the actual
creation of a DCT in the hardware until the stage of modify_qp() to RTR.
A support for query_qp() was added as well. It uses QUERY_DCT command to
retrieve the applicable fields.
Signed-off-by: Moni Shoua <monis@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
DC Initiator (DCI) QP is represented like any other QP in the hardware.
However, like any other transport QP there are attributes and settings
that are special to DCI QP and needs specific attention and care.
Make necessary changes to configure DCI QP.
Signed-off-by: Moni Shoua <monis@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The QP type IB_QPT_DRIVER doesn't describe the transport or the service
that the QP provides but those are known only to the hardware driver.
The actual type of the QP is stored in the hardware driver context (i.e.
mlx5_qp) under the field qp_sub_type.
Take the real QP type and any extra data that is required to create the QP
from the driver channel and modify the QP initial attributes before continuing
with create_qp().
Downstream patches from this series will add support for both DCI and
DCT driver QPs.
Signed-off-by: Moni Shoua <monis@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Reporting that a device doesn't support RoCE seems like a valuable piece
of information to have when trying to determine why a driver is not binding
to a device. Better to report this at info log level instead of requiring
a user to enable all debug messages in the driver.
Signed-off-by: Jonathan Toppins <jtoppins@redhat.com>
Acked-By: Devesh Sharma <devesh.sharma@broadcom.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
i40iw_wait_pe_ready is not called in an interrupt handler
nor holding a spinlock.
The function mdelay in it can be replaced with msleep,
to reduce busy wait.
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Acked-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
The get_unit_name() function crafts a string based on the device name
and the device unit number. It then stores this in a static variable.
This has concurrency issues as can be seen with this log:
hfi1 0000:02:00.0: hfi1_1: read_idle_message: read idle message 0x203
hfi1 0000:01:00.0: hfi1_1: read_idle_message: read idle message 0x203
The PCI device ID (0000:02:00.0 vs. 0000:01:00.0) is correct for the
message, but the device string hfi1_1 is incorrect (it should be
hfi1_0 for the second log message).
Remove get_unit_name() function.
Instead, use the rvt accessor rvt_get_ibdev_name() to get the IB name
string.
Clean up any hfi1_early_xx calls that can now use the new path.
QIB has the same (qib_get_unit_name()) issue. Updating as necessary.
Remove qib_get_unit_name() function.
Update log message that has redundant device name.
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
When an 8051 command times out, the entire DC block is restarted. During
the restart, the host interface version bit is set, which calls
do_8051_command() recursively. The host version bit needs to be set
before the link moves into polling, so the host version bit can be set
in set_local_link_attributes() instead. Thus, the 8051 command functions
can be simplied as a non-locking version (dd->dc8051_lock) of those
functions are no longer needed.
Fixes: 9be6a5d788 ("IB/hfi1: Prevent LNI out of sync by resetting host interface version")
Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: Sebastian Sanchez <sebastian.sanchez@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
rdmavt has a down call to client drivers to retrieve a crafted card
name.
This name should be the IB defined name.
Rather than craft the name each time it is needed, simply retrieve
the IB allocated name from the IB device.
Update the function name to reflect its application.
Clean up driver code to match this change.
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Currently the HFI and QIB drivers allow the IB core to assign a unit
number to the driver name string.
If multiple devices exist in a system, there is a possibility that the
device unit number and the IB core number will be mismatched.
Fix by using the driver defined unit number to generate the device
name.
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Unconditional locks/list and ODP srcu initialization should be done in
the INIT stage. Remove those from the CAPS stage and move them to the
proper stage.
Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The loopback stage only initializes a lock, move it to be in
the CAPS initialization phase and get rid loopback step completely.
Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Now that we have a stage just for hardware counters, move all relevant
initialization logic into one place.
Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Now that we have a stage just for ODP, move all relevant
initialization logic into one place.
Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Now that we have a stage just for RoCE/ETH, move all relevant
initialization logic into one place.
Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Today we have single function which is used when we add an IB interface,
break this function into multiple functions.
Create stages and a generic mechanism to execute each stage.
This is in preparation for RDMA/IB representors which might not need
all stages or will do things differently in some of the stages.
This patch doesn't change any functionality.
Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
When debugging issues with RC QPs, it is useful to know if a QP
has an associated RQ or SRQ, the size of the RQ, and any RNR timeout
values.
Add the necessary information to the QP stats output.
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
It needs to create eight reserve QPs for resolving
a bug of hip06. When deregistering mr, it will issue
a rdma write for every reserve QPs.
When modify qp from init to rtr, it needs to set
the value of dest_qp_num. Otherwise, it will lead
an error of freeing mr.
Signed-off-by: Lijun Ou <oulijun@huawei.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The QP can accept send work requests only when the QP is
in the states that allow them to be submitted.
This patch updates the QP state judgement based on the
specification.
Signed-off-by: Yixian Liu <liuyixian@huawei.com>
Signed-off-by: Shaobo Xu <xushaobo2@huawei.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
When the length of sge is zero, the driver need to filter it
Signed-off-by: Lijun Ou <oulijun@huawei.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This patch refactors the code of setting access flags
for RDMA operation as well as adds the scene when
attr->max_dest_rd_atomic is zero.
Signed-off-by: Lijun Ou <oulijun@huawei.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This patch fixes the usage with sr_max filed and rr_max of qp
context when modify qp. Its modifications include:
1. Adjust location of filling sr_max filed of qpc
2. Only assign the number of responder resource if
IB_QP_MAX_DEST_RD_ATOMIC bit is set
3. Only assign the number of outstanding resource if
IB_QP_MAX_QP_RD_ATOMIC
4. Fix the assgin algorithms for the field of sr_max
and rr_max of qp context
Signed-off-by: Lijun Ou <oulijun@huawei.com>
Signed-off-by: Yixian Liu <liuyixian@huawei.com>
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This patch mainly implement rq inline data feature for hip08
RoCE in kernel mode.
Signed-off-by: Lijun Ou <oulijun@huawei.com>
Signed-off-by: Yixian Liu <liuyixian@huawei.com>
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Use dma_zalloc_coherent for allocating zeroed
memory and remove unnecessary memset function.
Done using Coccinelle.
Generated-by: scripts/coccinelle/api/alloc/kzalloc-simple.cocci
0-day tested with no failures.
Suggested-by: Luis R. Rodriguez <mcgrof@kernel.org>
Signed-off-by: Himanshu Jha <himanshujha199640@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Use dma_zalloc_coherent for allocating zeroed
memory and remove unnecessary memset function.
Done using Coccinelle.
Generated-by: scripts/coccinelle/api/alloc/kzalloc-simple.cocci
0-day tested with no failures.
Suggested-by: Luis R. Rodriguez <mcgrof@kernel.org>
Signed-off-by: Himanshu Jha <himanshujha199640@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Use dma_zalloc_coherent for allocating zeroed
memory and remove unnecessary memset function.
Done using Coccinelle.
Generated-by: scripts/coccinelle/api/alloc/kzalloc-simple.cocci
0-day tested with no failures.
Suggested-by: Luis R. Rodriguez <mcgrof@kernel.org>
Signed-off-by: Himanshu Jha <himanshujha199640@gmail.com>
Acked-by: Ram Amrani <Ram.Amrani@cavium.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Use dma_zalloc_coherent for allocating zeroed
memory and remove unnecessary memset function.
Done using Coccinelle.
Generated-by: scripts/coccinelle/api/alloc/kzalloc-simple.cocci
0-day tested with no failures.
Suggested-by: Luis R. Rodriguez <mcgrof@kernel.org>
Signed-off-by: Himanshu Jha <himanshujha199640@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Use dma_zalloc_coherent for allocating zeroed
memory and remove unnecessary memset function.
Done using Coccinelle.
Generated-by: scripts/coccinelle/api/alloc/kzalloc-simple.cocci
0-day tested with no failures.
Suggested-by: Luis R. Rodriguez <mcgrof@kernel.org>
Signed-off-by: Himanshu Jha <himanshujha199640@gmail.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Acked-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
ibmr.device is being set only after ib_alloc_mr() is successfully complete.
Therefore, in case imlx4_mr_enable() returns with error, the error flow
unwinder calls to mlx4_free_priv_pages(), which uses ibmr.device.
Such usage causes to NULL dereference oops and to fix it, the IB device
should be set in the mr struct earlier stage (e.g. prior to calling
mlx4_free_priv_pages()).
Fixes: 1b2cd0fc67 ("IB/mlx4: Support the new memory registration API")
Signed-off-by: Nitzan Carmi <nitzanc@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
These prints not neccesarily mean error/warning, so changing them to
debug.
Signed-off-by: Potnuri Bharat Teja <bharat@chelsio.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This patch adds more detailed comments when we call the
memory barrier function, such as rmb, wmb and mb. Three
mb() callers are deleted since they are unnecessary.
Suggested-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Yixian Liu <liuyixian@huawei.com>
Signed-off-by: Lijun Ou <oulijun@huawei.com>
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This patch enables QP creation with a given BF index, this allows the
user space driver to share same BF between few QPs or alternatively have
a dedicated BF per QP.
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This patch exposes the option to dynamic allocates a UAR, this
functionality will be used in downstream patch in this series as
part of QP creation.
Specifically, the user space driver asks for a UAR allocation in a given
page index, upon success this UAR and its bfregs can be used as part of
QP creation by the user space driver.
To enable allocating more than 256 UARs the page index is encoded in an
extra one byte just after the command byte.
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This patch extends the alloc context flow to be prepared for working
with dynamic UAR allocations.
Currently upon alloc context there is some fix size of UARs that are
allocated (named 'static allocation') and there is no option to user
application to ask for more or control which UAR will be used by which
QP.
In this patch the driver prepares its data structures to manage both the
static and the dynamic allocations and let the user driver knows about
the max value of dynamic blue-flame registers that are allowed.
Downstream patches from this series will enable the dynamic allocation
and the association as part of QP creation.
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Add missing inner RSS support capability as part of
the RSS supported fields.
In addition change MLX5_RX_HASH_INNER to 1UL << 31 in
order to define it as unsigned.
Fixes: 309fa3470f ("IB/mlx5: Add support for RSS on the inner packet")
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Support RSS hash for inner headers according to a new flag,
MLX4_IB_RX_HASH_INNER provided by the vendor channel.
In case the flag is set, RSS hash will be done on the inner headers of
VXLAN packets (which are encapsulated).
Non-encapsulated packets will be hashed according to the outer headers.
Signed-off-by: Guy Levi <guyle@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Patches for 4.16 that are dependent on patches sent to 4.15-rc.
These are small clean ups for the vmw_pvrdma and i40iw drivers.
* 'from-rc' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma.git:
RDMA/vmw_pvrdma: Remove usage of BIT() from UAPI header
RDMA/vmw_pvrdma: Use refcount_t instead of atomic_t
RDMA/vmw_pvrdma: Use more specific sizeof in kcalloc
RDMA/vmw_pvrdma: Clarify QP and CQ is_kernel logic
RDMA/vmw_pvrdma: Add UAR SRQ macros in ABI header file
i40iw: Change accelerated flag to bool
refcount_t is the preferred type for refcounts. Change the
QP and CQ refcnt fields to use refcount_t.
Reviewed-by: Adit Ranadive <aditr@vmware.com>
Reviewed-by: Aditya Sarwade <asarwade@vmware.com>
Reviewed-by: Jorgen Hansen <jhansen@vmware.com>
Signed-off-by: Bryan Tan <bryantan@vmware.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Convert the sizeof(void *) in two kcalloc calls to be more
specific for the arrays that are being allocated.
Reviewed-by: Adit Ranadive <aditr@vmware.com>
Reviewed-by: Aditya Sarwade <asarwade@vmware.com>
Reviewed-by: Jorgen Hansen <jhansen@vmware.com>
Signed-off-by: Bryan Tan <bryantan@vmware.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
