RDMA/cma: Provide a function to set RoCE path record L2 parameters

Introduce a helper function to set path record L2 fields for RoCE.
This includes setting GID type, destination mac address and netdev
ifindex.

Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

RDMA/cma: Use the right net namespace for the rdma_cm_id

The net namespace is set in addr during create_rdma_id(),
cma_resolve_iboe_route() should use that instead of the
init namespace.

The original code was added in commit fa20105e09e9 ("IB/cma: Add support
for network namespaces"), but this path wasn't in use back then.

This patch updates the code to use right namespace, as preparation
for improving namespace support.

Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

IB/core: Increase number of char device minors

There is a need to increase number of possible char devices to support
large number of SR-IOV instances. The current limit is in the range of
64-128 devices/ports. Increase it to support up to 1024.

The patch performs the following steps to refactor the code:
1. Removes the split bitmap for fixed and overflow dev numbers.
2. Pre-allocates the non-legacy major number range during driver
   initialization, choosen for simplicity.
3. Add new define (RDMA_MAX_PORTS) that is shared between all drivers.
   This is the maximum total number of ports on all struct ib_devices.
4. Set RDMA_MAX_PORTS to 1024.

Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

IB/core: Remove the locking for character device bitmaps

Remove the locks that protect character device bitmaps of
uverbs, umad and issm.

The character device bitmaps are accessed in "client->add" and
"client->remove" calls from ib_register_device and ib_unregister_device
respectively. These calls are already protected by the "device_mutex"
mutex. Thus, the spinlocks are not needed.

Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

RDMA/rxe: Fix a race condition related to the QP error state

The following sequence:
* Change queue pair state into IB_QPS_ERR.
* Post a work request on the queue pair.

Triggers the following race condition in the rdma_rxe driver:
* rxe_qp_error() triggers an asynchronous call of rxe_completer(), the function
  that examines the QP send queue.
* rxe_post_send() posts a work request on the QP send queue.

If rxe_completer() runs prior to rxe_post_send(), it will drain the send
queue and the driver will assume no further action is necessary.
However, once we post the send to the send queue, because the queue is
in error, no send completion will ever happen and the send will get
stuck.  In order to process the send, we need to make sure that
rxe_completer() gets run after a send is posted to a queue pair in an
error state.  This patch ensures that happens.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Moni Shoua <monis@mellanox.com>
Cc: <stable@vger.kernel.org> # v4.8
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/mlx5: remove redundant assignment of mdev

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>

IB/rxe: remove unnecessary skb_clone in xmit

In xmit, there is a skb_clone. This function copies the struct sk_buff.
And some parameters are changed to the new skb. Then the new skb is sent
while the old skb is freed.

While the function skb_clone is removed, the parameter changes are made on
the old skb, then the old skb is sent. It can also work well.

The following tests are made.

 server                       client
---------                    ---------
|1.1.1.1|<----rxe-channel--->|1.1.1.2|
---------                    ---------

On server: rping -s -a 1.1.1.1 -v -C 1000 -S 512
On client: rping -c -a 1.1.1.1 -v -C 1000 -S 512

The kernel config CONFIG_DEBUG_KMEMLEAK is enabled on both server
and client.

This test runs for several hours. There is no memory leak and the whole
system can work well.

As the above network, the following tests are made.

Server: ibv_rc_pingpong -d rxe0 -g 1
Client: ibv_rc_pingpong -d rxe0 -g 1 1.1.1.1

The result on Server.
Before:
8192000 bytes in 0.88 seconds = 74.36 Mbit/sec
1000 iters in 0.88 seconds = 881.30 usec/iter

After:
8192000 bytes in 0.81 seconds = 81.15 Mbit/sec
1000 iters in 0.81 seconds = 807.62 usec/iter

The throughput is enhanced and the latency is reduced.

CC: Srinivas Eeda <srinivas.eeda@oracle.com>
CC: Joe Jin <joe.jin@oracle.com>
CC: Junxiao Bi <junxiao.bi@oracle.com>
Signed-off-by: Zhu Yanjun <yanjun.zhu@oracle.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/rxe: add the static type to the variable

The variable recv_sockets is only used in the file rxe_net.c. So
it is better to add static type to it.

CC: Srinivas Eeda <srinivas.eeda@oracle.com>
CC: Joe Jin <joe.jin@oracle.com>
CC: Junxiao Bi <junxiao.bi@oracle.com>
Signed-off-by: Zhu Yanjun <yanjun.zhu@oracle.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

Merge branch 'bart-srpt-for-next' into k.o/wip/dl-for-next

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>

IB/srpt: Micro-optimize I/O context state manipulation

Since all I/O context state changes are already serialized, it is
not necessary to protect I/O context state changes with the I/O
context spinlock. Hence remove that spinlock.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/srpt: Inline srpt_get_cmd_state()

It is not necessary to obtain ioctx->spinlock when reading the ioctx
state. Since after removal of this locking only a single line remains,
inline the srpt_get_cmd_state() function.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/srpt: Introduce srpt_format_guid()

Introduce a function for converting a GUID into an ASCII string. This
patch does not change any functionality.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/srpt: Reduce frequency of receive failure messages

Disabling an SRP target port causes the state of all QPs associated
with a port to be changed into IB_QPS_ERR. Avoid that this causes
one error message per I/O context to be reported.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/srpt: Convert a warning into a debug message

At least when running the ib_srpt driver on top of the rdma_rxe
driver it is easy to trigger a zero-length write completion in
the CH_DISCONNECTED state. Hence make the message that reports
this less noisy.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/srpt: Use the IPv6 format for GIDs in log messages

Make the ib_srpt driver use the IPv6 format for GIDs in log messages
to improve consistency of this driver with other RDMA kernel drivers.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/srpt: Verify port numbers in srpt_event_handler()

Verify whether port numbers are in the expected range before using
these as an array index. Complain if a port number is out of range.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/srpt: Reduce the severity level of a log message

Since the SRQ event message is only useful for debugging purposes,
reduce its severity from "informational" to "debug".

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/srpt: Rename a local variable, a member variable and a constant

Rename rsp_size into max_rsp_size and SRPT_RQ_SIZE into MAX_SRPT_RQ_SIZE.
The new names better reflect the role of this member variable and constant.
Since the prefix "srp_" is superfluous in the context of the function
that creates an RDMA channel, rename srp_sq_size into sq_size.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/srpt: Document all structure members in ib_srpt.h

This patch avoids that the following command reports any warnings:

scripts/kernel-doc -none drivers/infiniband/ulp/srpt/ib_srpt.h

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/srpt: Fix kernel-doc warnings in ib_srpt.c

Avoid that warnings about missing parameter descriptions are reported
when building with W=1.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/srpt: Remove an unused structure member

Fixes: commit a42d985bd5b2 ("ib_srpt: Initial SRP Target merge for v3.3-rc1")
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

net/mlx5: Set num_vhca_ports capability

Set the current capability to the max capability. Doing so enables dual
port RoCE functionality if supported by the firmware.

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>

IB/mlx5: Don't advertise RAW QP support in dual port mode

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>

IB/mlx5: Route MADs for dual port RoCE

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>

{net, IB}/mlx5: Change set_roce_gid to take a port number

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>

IB/mlx5: Update counter implementation for dual port RoCE

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>

IB/mlx5: Change debugfs to have per port contents

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>

IB/mlx5: Implement dual port functionality in query routines

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>

IB/mlx5: Move IB event processing onto a workqueue

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>

{net, IB}/mlx5: Manage port association for multiport RoCE

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>

IB/mlx5: Make netdev notifications multiport capable

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>

IB/mlx5: Reduce the use of num_port capability

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>

IB/core: Change roce_rescan_device to return void

It always returns 0. Change return type to void.

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>

net/mlx5: Set software owner ID during init HCA

Generate a unique 128bit identifier for each host and pass that value to
firmware in the INIT_HCA command if it reports the sw_owner_id
capability. Each device bound to the mlx5_core driver will have the same
software owner ID.

In subsequent patches mlx5_core devices will be bound via a new VPort
command so that they can operate together under a single InfiniBand
device. Only devices that have the same software owner ID can be bound,
to prevent traffic intended for one host arriving at another.

The INIT_HCA command length was expanded by 128 bits. The command
length is provided as an input FW commands. Older FW does not have a
problem receiving this command in the new longer form.

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>

net/mlx5: Fix race for multiple RoCE enable

There are two potential problems with the existing implementation.

1. Enable and disable can race after the atomic operations.
2. If a command fails the refcount is left in an inconsistent state.

Introduce a lock and perform error checking.

Fixes: a6f7d2aff623 ("net/mlx5: Add support for multiple RoCE enable")
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>

IB/mlx5: Add support for DC target QP

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>

IB/mlx5: Add support for DC Initiator QP

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>

IB/mlx5: Handle type IB_QPT_DRIVER when creating a QP

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>

IB/core: Introduce driver QP type

Vendors can implement type of QPs that are not described in the
InfiniBand specification. To still be able to use the IB/core layer
services (e.g. user object management) without tainting this layer with
driver proprietary logic, a new QP type is added - IB_QPT_DRIVER. This
will be a general QP type that the core layer doesn't know about its true nature.
When a command like create_qp() is passed to a hardware driver the extra
data that is required is taken from the driver channel.
Downstream patches from this series will use that QP type in the mlx5
driver.

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>

net/mlx5: Enable DC transport

Enable DC transport in the firmware to provide its functionality.

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>

net/mlx5: Add DCT command interface

Add a missing command interface to work with a DCT. It includes: creating,
destroying and get events for.

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>

bnxt_re: report RoCE device support at info level

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>

RDMA/core: Add encode/decode FDR/EDR rates

The cases for FDR/EDR signalling speed, were missing in
ib_rate_to_mult and mult_to_ib_rate giving wrong return values when
drivers convert static rate to/from inter-packet-delay.

Signed-off-by: Hans Westgaard Ry <hans.westgaard.ry@oracle.com>
Reviewed-by: Håkon Bugge <haakon.bugge@oracle.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

i40iw: Replace mdelay with msleep in i40iw_wait_pe_ready

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>

IB/rdmavt: Add trace for RNRNAK timer

This patch adds static trace for RNRNAK timer. Currently the output from
hrtimer static trace only shows the addresses of hrtimers in the system
and there is no easy way to correlate an RNRNAK timer with its entries in
the hrtimer trace. This patch adds the correlation among a QP, its RNRNAK
timer, and its entries in the hrtimer trace. This correlation will be
enormously helpful when debugging RNRNAK related issues. In addition, this
patch cleans up rvt_stop_rnr_timer() to be void while here.

Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/{hfi1, qib}: Fix a concurrency issue with device name in logging

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>

IB/rdmavt: Allocate CQ memory on the correct node

CQ allocation does not ensure that completion queue entries
and the completion queue structure are allocated on the correct
numa node.

Fix by allocating the rvt_cq and kernel CQ entries on the device node,
leaving the user CQ entries on the default local node.  Also ensure
CQ resizes use the correct allocator when extending a CQ.

Reviewed-by: Sebastian Sanchez <sebastian.sanchez@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/hfi1: Fix infinite loop in 8051 command error path

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: 9be6a5d788b0 ("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>

IB/rdmavt: Use correct numa node for SRQ allocation

Normal receive queue allocation ensures that kernel receive queues
are allocated on the local numa node. Shared receive queues
do not behave the same way.

Ensure that kernel shared receive queues are allocated on the device
local node.

Reviewed-by: Sebastian Sanchez <sebastian.sanchez@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/{rdmavt, hfi1, qib}: Remove get_card_name() downcall

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>

IB/{rdmavt, hfi1, qib}: Self determine driver name

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>

IB/rdmavt: No need to cancel RNRNAK retry timer when it is running

When the rdmavt's RNRNAK timer is fired, it tries to cancel the timer by
calling hrtimer_try_to_cancel(), which always returns -1 because the timer
is currently running. This patch removes this useless call.

Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/srpt: Fix ACL lookup during login

Make sure that the initiator port GUID is stored in ch->ini_guid.
Note: when initiating a connection sgid and dgid members in struct
sa_path_rec represent the source and destination GIDs. When accepting
a connection however sgid represents the destination GID and dgid the
source GID.

Fixes: commit 2bce1a6d2209 ("IB/srpt: Accept GUIDs as port names")
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

IB/srpt: Disable RDMA access by the initiator

With the SRP protocol all RDMA operations are initiated by the target.
Since no RDMA operations are initiated by the initiator, do not grant
the initiator permission to submit RDMA reads or writes to the target.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

IB/core: Fix two kernel warnings triggered by rxe registration

Eliminate the WARN_ONs that create following two warnings when
registering an rxe device:

WARNING: CPU: 2 PID: 1005 at drivers/infiniband/core/device.c:449 ib_register_device+0x591/0x640 [ib_core]
CPU: 2 PID: 1005 Comm: run_tests Not tainted 4.15.0-rc4-dbg+ #2
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.0.0-prebuilt.qemu-project.org 04/01/2014
RIP: 0010:ib_register_device+0x591/0x640 [ib_core]
Call Trace:
 rxe_register_device+0x3c6/0x470 [rdma_rxe]
 rxe_add+0x543/0x5e0 [rdma_rxe]
 rxe_net_add+0x37/0xb0 [rdma_rxe]
 rxe_param_set_add+0x5a/0x120 [rdma_rxe]
 param_attr_store+0x5e/0xc0
 module_attr_store+0x19/0x30
 sysfs_kf_write+0x3d/0x50
 kernfs_fop_write+0x116/0x1a0
 __vfs_write+0x23/0x120
 vfs_write+0xbe/0x1b0
 SyS_write+0x44/0xa0
 entry_SYSCALL_64_fastpath+0x23/0x9a

WARNING: CPU: 2 PID: 1005 at drivers/infiniband/core/sysfs.c:1279 ib_device_register_sysfs+0x11d/0x160 [ib_core]
CPU: 2 PID: 1005 Comm: run_tests Tainted: G        W        4.15.0-rc4-dbg+ #2
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.0.0-prebuilt.qemu-project.org 04/01/2014
RIP: 0010:ib_device_register_sysfs+0x11d/0x160 [ib_core]
Call Trace:
 ib_register_device+0x3f7/0x640 [ib_core]
 rxe_register_device+0x3c6/0x470 [rdma_rxe]
 rxe_add+0x543/0x5e0 [rdma_rxe]
 rxe_net_add+0x37/0xb0 [rdma_rxe]
 rxe_param_set_add+0x5a/0x120 [rdma_rxe]
 param_attr_store+0x5e/0xc0
 module_attr_store+0x19/0x30
 sysfs_kf_write+0x3d/0x50
 kernfs_fop_write+0x116/0x1a0
 __vfs_write+0x23/0x120
 vfs_write+0xbe/0x1b0
 SyS_write+0x44/0xa0
 entry_SYSCALL_64_fastpath+0x23/0x9a

The code should accept either a parent pointer or a fully specified DMA
specification without producing warnings.

Fixes: 99db9494035f ("IB/core: Remove ib_device.dma_device")
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Leon Romanovsky <leon@kernel.org>
Cc: stable@vger.kernel.org # v4.11
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

IB/mlx5: Move locks initialization to the corresponding stage

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>

IB/mlx5: Move loopback initialization to the corresponding stage

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>

IB/mlx5: Move hardware counters initialization to the corresponding stage

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>

IB/mlx5: Move ODP initialization to the corresponding stage

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>

IB/mlx5: Move RoCE/ETH initialization to the corresponding stage

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>

IB/mlx5: Create profile infrastructure to add and remove stages

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>

IB/hfi1: Add RQ/SRQ information to QP stats

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>

RDMA/hns: Assign dest_qp when deregistering mr

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>

RDMA/hns: Fix QP state judgement before sending work requests

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>

RDMA/hns: Filter for zero length of sge in hip08 kernel mode

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>

RDMA/hns: Set access flags of hip08 RoCE

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>

RDMA/hns: Update the usage of sr_max and rr_max field

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>

RDMA/hns: Add rq inline data support for hip08 RoCE

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>

IB/ipoib: Fix for notify send CQ failure messages

If IB_CQ_REPORT_MISSED_EVENTS flag is passed in ib_req_notify_cq()
it may return positive value indicating non-empty CQ.
If return code not verified the log might be flooded with false
warning messages "request notify on send CQ failed".

Fixes: 8966e28d2e40 ("IB/ipoib: Use NAPI in UD/TX flows")
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Alex Estrin <alex.estrin@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

RDMA/cma: Mark end of CMA ID messages

The commit 1a1c116f3dcf ("RDMA/netlink: Simplify the put_msg and put_attr")
removes nlmsg_len calculation in ibnl_put_attr causing netlink messages and
caused to miss source and destination addresses.

Fixes: 1a1c116f3dcf ("RDMA/netlink: Simplify the put_msg and put_attr")
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

RDMA/netlink: Fix locking around __ib_get_device_by_index

Holding locks is mandatory when calling __ib_device_get_by_index,
otherwise there are races during the list iteration with device removal.

Since the locks are static to device.c, __ib_device_get_by_index can
never be called correctly by any user out side the file.

Make the function static and provide a safe function that gets the
correct locks and returns a kref'd pointer. Fix all callers.

Fixes: e5c9469efcb1 ("RDMA/netlink: Add nldev device doit implementation")
Fixes: c3f66f7b0052 ("RDMA/netlink: Implement nldev port doit callback")
Fixes: 7d02f605f0dc ("RDMA/netlink: Add nldev port dumpit implementation")
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

RDMA/nldev: Refactor setting the nldev handle to a common function

The NLDEV commands are using IB device indexes and names as a handle
for netlink communications. Put all relevant code into one function
to remove code duplication in followup patches.

Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

RDMA/core: Replace open-coded variant of put_device

There is an existing function to decrease reference counter
of the device, let's use it.

Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

RDMA/netlink: Simplify code of autoload modules

The request_module() call is internally wrapped by CONFIG_MODULE,
so there is no need to check it in our RDMA code too.

Refactor to simplify the code.

Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

RDMA/rxe: Remove useless EXPORT_SYMBOL

The RXE driver is standalone module and hence doesn't need to export
symbols, nor does this one line function deserve to be not inlined.

Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

IB/mthca: Use zeroing memory allocator than allocator/memset

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>

RDMA/bnxt_re: Use zeroing memory allocator than allocator/memset

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>

RDMA/qedr: Use zeroing memory allocator than allocator/memset

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>

RDMA/vmw_pvrdma: Use zeroing memory allocator than allocator/memset

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>

IB/ocrdma: Use zeroing memory allocator than allocator/memset

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>

IB/ipoib: Fix race condition in neigh creation

When using enhanced mode for IPoIB, two threads may execute xmit in
parallel to two different TX queues while the target is the same.
In this case, both of them will add the same neighbor to the path's
neigh link list and we might see the following message:

  list_add double add: new=ffff88024767a348, prev=ffff88024767a348...
  WARNING: lib/list_debug.c:31__list_add_valid+0x4e/0x70
  ipoib_start_xmit+0x477/0x680 [ib_ipoib]
  dev_hard_start_xmit+0xb9/0x3e0
  sch_direct_xmit+0xf9/0x250
  __qdisc_run+0x176/0x5d0
  __dev_queue_xmit+0x1f5/0xb10
  __dev_queue_xmit+0x55/0xb10

Analysis:
Two SKB are scheduled to be transmitted from two cores.
In ipoib_start_xmit, both gets NULL when calling ipoib_neigh_get.
Two calls to neigh_add_path are made. One thread takes the spin-lock
and calls ipoib_neigh_alloc which creates the neigh structure,
then (after the __path_find) the neigh is added to the path's neigh
link list. When the second thread enters the critical section it also
calls ipoib_neigh_alloc but in this case it gets the already allocated
ipoib_neigh structure, which is already linked to the path's neigh
link list and adds it again to the list. Which beside of triggering
the list, it creates a loop in the linked list. This loop leads to
endless loop inside path_rec_completion.

Solution:
Check list_empty(&neigh->list) before adding to the list.
Add a similar fix in "ipoib_multicast.c::ipoib_mcast_send"

Fixes: b63b70d87741 ('IPoIB: Use a private hash table for path lookup in xmit path')
Signed-off-by: Erez Shitrit <erezsh@mellanox.com>
Reviewed-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

IB/mlx4: Fix mlx4_ib_alloc_mr error flow

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: 1b2cd0fc673c ("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>

iw_cxgb4: Change error/warn prints to pr_debug

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>

RDMA/hns: Add detailed comments for mb() call

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>

IB/mlx5: Enable QP creation with a given blue flame index

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>

IB/mlx5: Expose dynamic mmap allocation

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>

IB/mlx5: Extend UAR stuff to support dynamic allocation

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>

IB/mlx5: Report inner RSS capability

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: 309fa3470fca ("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>

IB/mlx4: Add support to RSS hash for inner headers

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>

Merge branch 'from-rc' of git://git./linux/kernel/git/rdma/rdma.git

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

RDMA/vmw_pvrdma: Remove usage of BIT() from UAPI header

BIT() should not be used in the UAPI header. Remove it.

Signed-off-by: Bryan Tan <bryantan@vmware.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

RDMA/vmw_pvrdma: Use refcount_t instead of atomic_t

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>

RDMA/vmw_pvrdma: Use more specific sizeof in kcalloc

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>

RDMA/vmw_pvrdma: Clarify QP and CQ is_kernel logic

Be more consistent in setting and checking is_kernel
flag for QPs and CQs.

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>

RDMA/vmw_pvrdma: Add UAR SRQ macros in ABI header file

Support for SRQs were added in the vmw_pvrdma userlevel library
before two necessary macros were added into the kernel ABI header
file. Add the two UAR SRQ macros that are required by the userlevel
library so that the library can rely on the kernel ABI header file
for these SRQ macro definitions.

Fixes: 8b10ba783c9d ("RDMA/vmw_pvrdma: Add shared receive queue support")
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>

i40iw: Change accelerated flag to bool

The accelerated flag only utilizes two values: 0 and 1.
Modify accelerated flag in struct i40iw_cm_node to bool.

Signed-off-by: Henry Orosco <henry.orosco@intel.com>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

infiniband: drop unknown function from core_priv.h

Delete ibnl_chk_listeners() and its kernel-doc comments from the
core_priv.h header file.  There is no such function.

Fixes: 233c1955835b ("RDMA/netlink: Reduce exposure of RDMA netlink functions")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

IB/core: Make sure that PSN does not overflow

The rq/sq->psn is 24 bits as defined in the IB spec, therefore we mask
out the 8 most significant bits to avoid overflow in modify_qp.

Signed-off-by: Majd Dibbiny <majd@mellanox.com>
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>

IB/mlx5: Fix mlx5_ib_alloc_mr error flow

ibmr.device is being set only after ib_alloc_mr() is
(successfully) complete. Therefore, in case mlx5_core_create_mkey()
return with error, the error flow calls mlx5_free_priv_descs()
which uses ibmr.device (which doesn't exist yet), causing
a NULL dereference oops.

To fix this, the IB device should be set in the mr struct earlier
stage (e.g. prior to calling mlx5_core_create_mkey()).

Fixes: 8a187ee52b04 ("IB/mlx5: Support the new memory registration API")
Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Nitzan Carmi <nitzanc@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

IB/core: Verify that QP is security enabled in create and destroy

The XRC target QP create flow sets up qp_sec only if there is an IB link with
LSM security enabled. However, several other related uAPI entry points blindly
follow the qp_sec NULL pointer, resulting in a possible oops.

Check for NULL before using qp_sec.

Cc: <stable@vger.kernel.org> # v4.12
Fixes: d291f1a65232 ("IB/core: Enforce PKey security on QPs")
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>