Daniel Jurgens [Thu, 4 Jan 2018 15:25:38 +0000 (17:25 +0200)]
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>
Daniel Jurgens [Thu, 4 Jan 2018 15:25:37 +0000 (17:25 +0200)]
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>
Daniel Jurgens [Thu, 4 Jan 2018 15:25:36 +0000 (17:25 +0200)]
{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>
Daniel Jurgens [Thu, 4 Jan 2018 15:25:35 +0000 (17:25 +0200)]
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>
Daniel Jurgens [Thu, 4 Jan 2018 15:25:32 +0000 (17:25 +0200)]
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>
Daniel Jurgens [Thu, 4 Jan 2018 15:25:31 +0000 (17:25 +0200)]
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>
Moni Shoua [Tue, 2 Jan 2018 14:19:33 +0000 (16:19 +0200)]
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>
Moni Shoua [Tue, 2 Jan 2018 14:19:32 +0000 (16:19 +0200)]
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>
Moni Shoua [Tue, 2 Jan 2018 14:19:31 +0000 (16:19 +0200)]
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>
Moni Shoua [Tue, 2 Jan 2018 14:19:30 +0000 (16:19 +0200)]
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>
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.
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: HÃ¥kon Bugge <haakon.bugge@oracle.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
Jia-Ju Bai [Sun, 24 Dec 2017 10:39:40 +0000 (18:39 +0800)]
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>
Kaike Wan [Tue, 19 Dec 2017 03:57:28 +0000 (19:57 -0800)]
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>
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>
Mike Marciniszyn [Tue, 19 Dec 2017 03:57:06 +0000 (19:57 -0800)]
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>
Mike Marciniszyn [Tue, 19 Dec 2017 03:56:52 +0000 (19:56 -0800)]
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>
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>
Michael J. Ruhl [Tue, 19 Dec 2017 03:56:37 +0000 (19:56 -0800)]
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>
Kaike Wan [Tue, 19 Dec 2017 03:56:30 +0000 (19:56 -0800)]
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>
Mark Bloch [Mon, 1 Jan 2018 11:07:03 +0000 (13:07 +0200)]
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>
Mark Bloch [Mon, 1 Jan 2018 11:06:58 +0000 (13:06 +0200)]
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>
Michael J. Ruhl [Fri, 22 Dec 2017 16:45:44 +0000 (08:45 -0800)]
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>
oulijun [Wed, 3 Jan 2018 02:44:04 +0000 (10:44 +0800)]
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>
oulijun [Wed, 3 Jan 2018 02:44:03 +0000 (10:44 +0800)]
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>
Alex Estrin [Wed, 3 Jan 2018 12:39:50 +0000 (07:39 -0500)]
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>
Leon Romanovsky [Mon, 1 Jan 2018 11:07:17 +0000 (13:07 +0200)]
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>
Leon Romanovsky [Mon, 1 Jan 2018 11:07:14 +0000 (13:07 +0200)]
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>
Himanshu Jha [Sun, 31 Dec 2017 12:34:10 +0000 (18:04 +0530)]
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>
Himanshu Jha [Sun, 31 Dec 2017 12:32:38 +0000 (18:02 +0530)]
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>
Himanshu Jha [Sun, 31 Dec 2017 12:29:00 +0000 (17:59 +0530)]
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>
Yixian Liu [Fri, 29 Dec 2017 11:26:18 +0000 (19:26 +0800)]
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>
Yishai Hadas [Sun, 24 Dec 2017 14:31:36 +0000 (16:31 +0200)]
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>
Yishai Hadas [Sun, 24 Dec 2017 14:31:35 +0000 (16:31 +0200)]
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>
Yishai Hadas [Sun, 24 Dec 2017 14:31:34 +0000 (16:31 +0200)]
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>
Maor Gottlieb [Sun, 24 Dec 2017 12:51:25 +0000 (14:51 +0200)]
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>
Guy Levi [Sun, 24 Dec 2017 12:51:24 +0000 (14:51 +0200)]
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>
Jason Gunthorpe [Thu, 28 Dec 2017 04:50:46 +0000 (21:50 -0700)]
Merge branch 'from-rc' of git://git.kernel.org/pub/scm/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
Bryan Tan [Wed, 20 Dec 2017 17:50:57 +0000 (09:50 -0800)]
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.
Majd Dibbiny [Tue, 14 Nov 2017 12:51:56 +0000 (14:51 +0200)]
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>
Nitzan Carmi [Tue, 26 Dec 2017 09:20:20 +0000 (11:20 +0200)]
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>
Moni Shoua [Sun, 24 Dec 2017 11:54:58 +0000 (13:54 +0200)]
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>
Moni Shoua [Sun, 24 Dec 2017 11:54:57 +0000 (13:54 +0200)]
IB/uverbs: Fix command checking as part of ib_uverbs_ex_modify_qp()
If the input command length is larger than the kernel supports an error should
be returned in case the unsupported bytes are not cleared, instead of the
other way aroudn. This matches what all other callers of ib_is_udata_cleared
do and will avoid user ABI problems in the future.
Cc: <stable@vger.kernel.org> # v4.10 Fixes: 189aba99e700 ("IB/uverbs: Extend modify_qp and support packet pacing") Reviewed-by: Yishai Hadas <yishaih@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>
Majd Dibbiny [Sun, 24 Dec 2017 11:54:56 +0000 (13:54 +0200)]
IB/mlx5: Serialize access to the VMA list
User-space applications can do mmap and munmap directly at
any time.
Since the VMA list is not protected with a mutex, concurrent
accesses to the VMA list from the mmap and munmap can cause
data corruption. Add a mutex around the list.
Cc: <stable@vger.kernel.org> # v4.7 Fixes: 7c2344c3bbf9 ("IB/mlx5: Implements disassociate_ucontext API") Reviewed-by: Yishai Hadas <yishaih@mellanox.com> Signed-off-by: Majd Dibbiny <majd@mellanox.com> Signed-off-by: Leon Romanovsky <leon@kernel.org> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Don Hiatt [Fri, 22 Dec 2017 16:46:00 +0000 (08:46 -0800)]
IB/hfi1: Change slid arg in ingress_pkey_table_fail to 32bit
Change the slid arg to ingress_pkey_table_fail() to a full
32Bits and do not convert to 16Bits in caller. This is so we
can keep everything 32bit in the kernel and only change to
16bit at the uapi boundary.
Signed-off-by: Don Hiatt <don.hiatt@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Don Hiatt [Fri, 22 Dec 2017 16:45:52 +0000 (08:45 -0800)]
IB/core: Use rdma_cap_opa_mad to check for OPA
Use rdma_cap_opa_mad() to check for OPA to promote code reuse.
Signed-off-by: Don Hiatt <don.hiatt@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Tatyana Nikolova [Fri, 22 Dec 2017 15:47:02 +0000 (09:47 -0600)]
i40iw: Fix the connection ORD value for loopback
The accepting QP ORD value should be adjusted not to
exceed the peer QP IRD value (RFC 6581). This is
skipped for loopback. After the ORD is validated
by i40iw_record_ird_ord(), adjust the ORD value of
the loopback accepting QP to prevent overrunning the
IRD space of the peer QP. Also move the ORD accounting
for 0-byte RDMA read to i40iw_record_ird_ord().
Casting to u16 before validating IRD/ORD connection
parameters could cause recording wrong IRD/ORD values
in the cm_node. Validate the IRD/ORD parameters as
they are passed by the application before recording
them.
Shiraz Saleem [Fri, 22 Dec 2017 15:47:00 +0000 (09:47 -0600)]
i40iw: Ignore LLP_DOUBT_REACHABILITY AE
The LLP_DOUBT_REACHABILITY Asynchronous Event (AE) is an early
warning of a connection issue. It is followed by LLP_TOO_MANY_RETRIES
AE, if the retransmit threshold is reached and recovery is not possible
for the connection.
Currently we terminate the connection on receiving the
LLP_DOUBT_REACHABILITY AE. Ignore this AE and
terminate the connection only on LLP_TOO_MANY_RETRIES AE.
This improves the user experience on cable disconnect/reconnect
scenario while running iWARP traffic. On cable disconnect,
the QP traffic is paused and the user has a larger and more
reasonable timeout within which if the cable is reconnected,
traffic can continue.
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Shiraz Saleem [Fri, 22 Dec 2017 15:46:59 +0000 (09:46 -0600)]
i40iw: Fix sequence number for the first partial FPDU
Partial FPDU processing is broken as the sequence number
for the first partial FPDU is wrong due to incorrect
Q2 buffer offset. The offset should be 64 rather than 16.
Shiraz Saleem [Fri, 22 Dec 2017 15:46:58 +0000 (09:46 -0600)]
i40iw: Selectively teardown QPs on IP addr change event
On IP address change event, all connected QPs are torn down
irrespective of whether IP address is involved in a connection.
Only teardown connections those source or destination address
matches the netdev interface IP address being changed, and if
they are on the same VLAN as the netdev.
Fixes: e5e74b61b165 ("i40iw: Add IP addr handling on netdev events") Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Shiraz Saleem [Fri, 22 Dec 2017 15:46:56 +0000 (09:46 -0600)]
i40iw: Correct Q1/XF object count equation
Lower Inbound RDMA Read Queue (Q1) object count by a factor of 2
as it is incorrectly doubled. Also, round up Q1 and Transmit FIFO (XF)
object count to power of 2 to satisfy hardware requirement.
Fixes: 86dbcd0f12e9 ("i40iw: add file to handle cqp calls") Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
rdma: Update maintainer contact for Intel RDMA drivers
Ensure both Mike and I are listed as maintainer contacts for Intel's qib,
hfi1, and rdmavt drivers.
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
IB/SA: Check dlid before SA agent queries for ClassPortInfo
SA queries SM for class port info when there is a LID_CHANGE event.
When a base lid is configured before fm is started ie when smlid is
not yet assigned, SA handles the LID_CHANGE event and tries query SM
with lid 0. This will cause an hang.
Always ensure a proper smlid is assigned before querying SM for cpi.
Fixes: ee1c60b1bff ("IB/SA: Modify SA to implicitly cache Class Port info") Reviewed-by: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Venkata Sandeep Dhanalakota <venkata.s.dhanalakota@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Michael J. Ruhl [Fri, 22 Dec 2017 16:47:20 +0000 (08:47 -0800)]
IB/hfi: Only read capability registers if the capability exists
During driver init, various registers are saved to allow restoration
after an FLR or gen3 bump. Some of these registers are not available
in some circumstances (i.e. Virtual machines).
This bug makes the driver unusable when the PCI device is passed into
a VM, it fails during probe.
Delete unnecessary register read/write, and only access register if
the capability exists.
Cc: <stable@vger.kernel.org> # 4.14.x Fixes: a618b7e40af2 ("IB/hfi1: Move saving PCI values to a separate function") 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>
Yixian Liu [Tue, 14 Nov 2017 09:26:17 +0000 (17:26 +0800)]
RDMA/hns: Add eq support of hip08
This patch adds eq support for hip08. The eq table can
be multi-hop addressed.
Signed-off-by: Yixian Liu <liuyixian@huawei.com> Reviewed-by: Lijun Ou <oulijun@huawei.com> Reviewed-by: Wei Hu (Xavier) <xavier.huwei@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Yixian Liu [Tue, 14 Nov 2017 09:26:16 +0000 (17:26 +0800)]
RDMA/hns: Refactor eq code for hip06
Considering the compatibility of supporting hip08's eq
process and possible changes of data structure, this patch
refactors the eq code structure of hip06.
We move all the eq process code for hip06 from hns_roce_eq.c
into hns_roce_hw_v1.c, and also for hns_roce_eq.h. With
these changes, it will be convenient to add the eq support
for later hardware version.
Signed-off-by: Yixian Liu <liuyixian@huawei.com> Reviewed-by: Lijun Ou <oulijun@huawei.com> Reviewed-by: Wei Hu (Xavier) <xavier.huwei@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Alex Vesker [Thu, 21 Dec 2017 15:38:27 +0000 (17:38 +0200)]
IB/ipoib: Fix lockdep issue found on ipoib_ib_dev_heavy_flush
The locking order of vlan_rwsem (LOCK A) and then rtnl (LOCK B),
contradicts other flows such as ipoib_open possibly causing a deadlock.
To prevent this deadlock heavy flush is called with RTNL locked and
only then tries to acquire vlan_rwsem.
This deadlock is possible only when there are child interfaces.
other info that might help us debug this:
[ 141.088967] Possible unsafe locking scenario:
[ 141.094280] CPU0 CPU1
[ 141.097953] ---- ----
[ 141.101640] lock(&priv->vlan_rwsem);
[ 141.104771] lock(rtnl_mutex);
[ 141.109207] lock(&priv->vlan_rwsem);
[ 141.114032] lock(rtnl_mutex);
[ 141.116800]
*** DEADLOCK ***
Fixes: b4b678b06f6e ("IB/ipoib: Grab rtnl lock on heavy flush when calling ndo_open/stop") Signed-off-by: Alex Vesker <valex@mellanox.com> Signed-off-by: Leon Romanovsky <leon@kernel.org> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Majd Dibbiny [Thu, 21 Dec 2017 15:38:26 +0000 (17:38 +0200)]
IB/mlx5: Fix congestion counters in LAG mode
Congestion counters are counted and queried per physical function.
When working in LAG mode, CNP packets can be sent or received on both
of the functions, thus congestion counters should be aggregated from
the two physical functions.
Fixes: e1f24a79f424 ("IB/mlx5: Support congestion related counters") Signed-off-by: Majd Dibbiny <majd@mellanox.com> Reviewed-by: Aviv Heller <avivh@mellanox.com> Signed-off-by: Leon Romanovsky <leon@kernel.org> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Steve Wise [Tue, 19 Dec 2017 22:02:10 +0000 (14:02 -0800)]
iw_cxgb4: when flushing, complete all wrs in a chain
If a wr chain was posted and needed to be flushed, only the first
wr in the chain was completed with FLUSHED status. The rest were
never completed. This caused isert to hang on shutdown due to the
missing completions which left iscsi IO commands referenced, stalling
the shutdown.
Fixes: 4fe7c2962e11 ("iw_cxgb4: refactor sq/rq drain logic") Cc: stable@vger.kernel.org Signed-off-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Steve Wise [Tue, 19 Dec 2017 18:29:25 +0000 (10:29 -0800)]
iw_cxgb4: reflect the original WR opcode in drain cqes
The flush/drain logic was not retaining the original wr opcode in
its completion. This can cause problems if the application uses
the completion opcode to make decisions.
Use bit 10 of the CQE header word to indicate the CQE is a special
drain completion, and save the original WR opcode in the cqe header
opcode field.
Fixes: 4fe7c2962e11 ("iw_cxgb4: refactor sq/rq drain logic") Cc: stable@vger.kernel.org Signed-off-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Steve Wise [Mon, 18 Dec 2017 21:10:00 +0000 (13:10 -0800)]
iw_cxgb4: Only validate the MSN for successful completions
If the RECV CQE is in error, ignore the MSN check. This was causing
recvs that were flushed into the sw cq to be completed with the wrong
status (BAD_MSN instead of FLUSHED).
Cc: stable@vger.kernel.org Signed-off-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Anton Vasilyev [Tue, 8 Aug 2017 15:56:37 +0000 (18:56 +0300)]
RDMA/ocrdma: Fix permissions for OCRDMA_RESET_STATS
Debugfs file reset_stats is created with S_IRUSR permissions,
but ocrdma_dbgfs_ops_read() doesn't support OCRDMA_RESET_STATS,
whereas ocrdma_dbgfs_ops_write() supports only OCRDMA_RESET_STATS.
The patch fixes misstype with permissions.
Found by Linux Driver Verification project (linuxtesting.org).
Signed-off-by: Anton Vasilyev <vasilyev@ispras.ru> Acked-by: Selvin Xavier <selvin.xavier@broadcom.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Bharat Potnuri [Tue, 28 Nov 2017 18:28:07 +0000 (23:58 +0530)]
iser-target: avoid reinitializing rdma contexts for isert commands
isert commands that failed during isert_rdma_rw_ctx_post() are queued to
Queue-Full(QF) queue and are scheduled to be reposted during queue-full
queue processing. During this reposting, the rdma contexts are initialised
again in isert_rdma_rw_ctx_post(), which is leaking significant memory.
Parav Pandit [Tue, 14 Nov 2017 12:52:18 +0000 (14:52 +0200)]
IB/cm: Refactor to avoid setting path record software only fields
When path ah_attr initialization from path record
fails, ib_cm_send_rej() uses av.ah_attr fields to send out reject
message. In such cases initialization of path record software fields
is not needed. Code is simplified for same.
Additionally in current code in cm_req_handler, when ib_get_cached_gid
fails for a given sgid_index of the GID of the GRH of the incoming CM MAD,
error code 12 is sent. This error code refers to primary GID in incoming
CM REQ and not for the GID in in MAD packet.
Therefore code is refactored to send code 5 (unsupported request) for such
error.
Signed-off-by: Parav Pandit <parav@mellanox.com> Reviewed-by: Hal Rosenstock <hal@mellanox.com> Signed-off-by: Leon Romanovsky <leon@kernel.org> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>