RDMA/bnxt_re: Remove an unused variable

This patch does not change any functionality.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Selvin Xavier <selvin.xavier@broadcom.com>
Cc: Devesh Sharma <devesh.sharma@broadcom.com>
Cc: Somnath Kotur <somnath.kotur@broadcom.com>
Cc: Sriharsha Basavapatna <sriharsha.basavapatna@broadcom.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/hfi1: Fix a kernel-doc warning

Avoid that building with W=1 causes the following warning to appear:

drivers/infiniband/hw/hfi1/qp.c:484: warning: Cannot understand * on line 484 - I thought it was a doc line

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Mike Marciniszyn <mike.marciniszyn@intel.com>
Cc: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

Merge tag 'mlx5-updates-2018-02-28-2' of git://git./linux/kernel/git/mellanox/linux into k.o/wip/dl-for-next

mlx5-updates-2018-02-28-2 (IPSec-2)

This series follows our previous one to lay out the foundations for IPSec
in user-space and extend current kernel netdev IPSec support. As noted in
our previous pull request cover letter "mlx5-updates-2018-02-28-1 (IPSec-1)",
the IPSec mechanism will be supported through our flow steering mechanism.
Therefore, we need to change the initialization order. Furthermore, IPsec
is also supported in both egress and ingress. Since our current flow
steering is egress only, we add an empty (only implemented through FPGA
steering ops) egress namespace to handle that case. We also implement
the required flow steering callbacks and logic in our FPGA driver.

We extend the FPGA support for ESN and modifying a xfrm too. Therefore, we
add support for some new FPGA command interface that supports them. The
other required bits are added too. The new features and requirements are
advertised via cap bits.

Last but not least, we revise our driver's accel_esp API. This API will be
shared between our netdev and IB driver, so we need to have all the required
functionality from both worlds.

Regards,
Aviad and Matan

Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/nldev: provide detailed PD information

Implement the RDMA nldev netlink interface for dumping detailed PD
information.

Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

mlx4_ib: zero out struct ib_pd when allocating

Zero out the fields of the struct ib_pd for user mode pds so that
users querying pds via nldev will not get garbage.  For simplicity,
use kzalloc() to allocate the mlx4_ib_pd struct.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/nldev: provide detailed MR information

Implement the RDMA nldev netlink interface for dumping detailed
MR information.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

mlx4_ib: set user mr attributes in struct ib_mr

Setting iova, length, and page_size allows this information to be
seen via NLDEV netlink queries, which can aid in user rdma debugging.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

iw_cxgb4: initialize ib_mr fields for user mrs

Some of the struct ib_mr fields weren't getting initialized.  This was
benign, but will cause problems when dumping the mr resource via
nldev/restrack.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/nldev: provide detailed CQ information

Implement the RDMA nldev netlink interface for dumping detailed
CQ information.

Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/nldev: provide detailed CM_ID information

Implement RDMA nldev netlink interface to get detailed CM_ID information.

Because cm_id's are attached to rdma devices in various work queue
contexts, the pid and task information at restrak_add() time is sometimes
not useful.  For example, an nvme/f host connection cm_id ends up being
bound to a device in a work queue context and the resulting pid at attach
time no longer exists after connection setup.  So instead we mark all
cm_id's created via the rdma_ucm as "user", and all others as "kernel".
This required tweaking the restrack code a little.  It also required
wrapping some rdma_cm functions to allow passing the module name string.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/CM: move rdma_id_private to cma_priv.h

Move struct rdma_id_private to a new header cma_priv.h so the resource
tracking services in core/nldev.c can read useful information about cm_ids.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/nldev: common resource dumpit function

Create a common dumpit function that can be used by all common resource
types.  This reduces code replication and simplifies the code as we add
more resource types.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/restrack: clean up res_to_dev()

Simplify res_to_dev() to make it easier to read/maintain.

Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

net/mlx5: Fix wrongly assigned CQ reference counter

The kernel compiled with CONFIG_REFCOUNT_FULL produces the following
error. The reason to it that initial value of refcount_t is supposed
to be more than 0, change it.

[    3.106634] ------------[ cut here ]------------
[    3.107756] refcount_t: increment on 0; use-after-free.
[    3.109130] WARNING: CPU: 0 PID: 1 at lib/refcount.c:153 refcount_inc+0x27/0x30
[    3.110085] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.16.0-rc1-00028-gf683e04bdccc #137
[    3.110085] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.7.5-0-ge51488c-20140602_164612-nilsson.home.kraxel.org 04/01/2014
[    3.110085] RIP: 0010:refcount_inc+0x27/0x30
[    3.110085] RSP: 0000:ffffaa620000fba0 EFLAGS: 00010286
[    3.110085] RAX: 0000000000000000 RBX: ffff9a6d1a1821c8 RCX: ffffffff98a50f48
[    3.110085] RDX: 0000000000000001 RSI: 0000000000000086 RDI: 0000000000000246
[    3.110085] RBP: ffff9a6d1ac800a0 R08: 0000000000000289 R09: 000000000000000a
[    3.110085] R10: fffff03bc0682840 R11: ffffffff9949856d R12: ffff9a6d1b4a4000
[    3.110085] R13: 0000000000000000 R14: ffff9a6d1a0a6c00 R15: ffffaa620000fc5c
[    3.110085] FS:  0000000000000000(0000) GS:ffff9a6d1fc00000(0000) knlGS:0000000000000000
[    3.110085] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    3.110085] CR2: 0000000000000000 CR3: 000000000ba0a000 CR4: 00000000000006b0
[    3.110085] Call Trace:
[    3.110085]  mlx5_core_create_cq+0xde/0x250
[    3.110085]  ? __kmalloc+0x1ce/0x1e0
[    3.110085]  mlx5e_create_cq+0x15c/0x1e0
[    3.110085]  mlx5e_open_drop_rq+0xea/0x190
[    3.110085]  mlx5e_attach_netdev+0x53/0x140
[    3.110085]  mlx5e_attach+0x3d/0x60
[    3.110085]  mlx5e_add+0x11d/0x2f0
[    3.110085]  mlx5_add_device+0x77/0x170
[    3.110085]  mlx5_register_interface+0x74/0xc0
[    3.110085]  ? set_debug_rodata+0x11/0x11
[    3.110085]  init+0x67/0x72
[    3.110085]  ? mlx4_en_init_ptys2ethtool_map+0x346/0x346
[    3.110085]  do_one_initcall+0x98/0x147
[    3.110085]  ? set_debug_rodata+0x11/0x11
[    3.110085]  kernel_init_freeable+0x164/0x1e0
[    3.110085]  ? rest_init+0xb0/0xb0
[    3.110085]  kernel_init+0xa/0x100
[    3.110085]  ret_from_fork+0x35/0x40
[    3.110085] Code: 00 00 00 00 e8 ab ff ff ff 84 c0 74 02 f3 c3 80 3d 3b c3 64 01 00 75 f5 48 c7 c7 68 0b 81 98 c6 05 2b c3 64 01 01 e8 79 d7 a3 ff <0f> ff c3 66 0f 1f 44 00 00 8b 06 83 f8 ff 74 39 31 c9 39 f8 89
[    3.110085] ---[ end trace a0068e1c68438a74 ]---

Fixes: f105b45bf77c ("net/mlx5: CQ hold/put API")
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: IPSec, Add support for ESN

Currently ESN is not supported with IPSec device offload.

This patch adds ESN support to IPsec device offload.
Implementing new xfrm device operation to synchronize offloading device
ESN with xfrm received SN. New QP command to update SA state at the
following:

           ESN 1                    ESN 2                  ESN 3
|-----------*-----------|-----------*-----------|-----------*
^           ^           ^           ^           ^           ^

^ - marks where QP command invoked to update the SA ESN state
    machine.
| - marks the start of the ESN scope (0-2^32-1). At this point move SA
    ESN overlap bit to zero and increment ESN.
* - marks the middle of the ESN scope (2^31). At this point move SA
    ESN overlap bit to one.

Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Yossef Efraim <yossefe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5e: Added common function for to_ipsec_sa_entry

New function for getting driver internal sa entry from xfrm state.
All checks are done in one function.

Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: Add flow-steering commands for FPGA IPSec implementation

In order to add a context to the FPGA, we need to get both the software
transform context (which includes the keys, etc) and the
source/destination IPs (which are included in the steering
rule). Therefore, we register new set of firmware like commands for
the FPGA. Each time a rule is added, the steering core infrastructure
calls the FPGA command layer. If the rule is intended for the FPGA,
it combines the IPs information with the software transformation
context and creates the respective hardware transform.
Afterwards, it calls the standard steering command layer.

Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: Refactor accel IPSec code

The current code has one layer that executed FPGA commands and
the Ethernet part directly used this code. Since downstream patches
introduces support for IPSec in mlx5_ib, we need to provide some
abstractions. This patch refactors the accel code into one layer
that creates a software IPSec transformation and another one which
creates the actual hardware context.
The internal command implementation is now hidden in the FPGA
core layer. The code also adds the ability to share FPGA hardware
contexts. If two contexts are the same, only a reference count
is taken.

Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: Added required metadata capability for ipsec

Currently our device requires additional metadata in packet
to perform ipsec crypto offload.

Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: Export ipsec capabilities

We will need that for ipsec verbs.

Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: IPSec, Add command V2 support

This patch adds V2 command support.
New fpga devices support extended features (udp encap, esn etc...), this
features require new hardware sadb format therefore we have a new version
of commands to manipulate it.

Signed-off-by: Yossef Efraim <yossefe@mellanox.com>
Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5e: IPSec, Add support for ESP trailer removal by hardware

Current hardware decrypts and authenticates incoming ESP packets.
Subsequently, the software extracts the nexthdr field, truncates the
trailer and adjusts csum accordingly.

With this patch and a capable device, the trailer is being removed
by the hardware and the nexthdr field is conveyed via PET. This way
we avoid both the need to access the trailer (cache miss) and to
compute its relative checksum, which significantly improve
the performance.

Experiment shows that trailer removal improves the performance by
2Gbps, (netperf). Both forwarding and host-to-host configurations.

Signed-off-by: Yossi Kuperman <yossiku@mellanox.com>
Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: IPSec, Generalize sandbox QP commands

The current code assume only SA QP commands.
Refactor in order to pave the way for new QP commands:
1. Generic cmd response format.
2. SA cmd checks are in dedicated functions.
3. Aligned debug prints.

Signed-off-by: Yossi Kuperman <yossiku@mellanox.com>
Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: Use MLX5_IPSEC_DEV macro for ipsec caps

Fix build break of mlx5_accel_ipsec_device_caps is not defined when
MLX5_ACCEL is not selected, use MLX5_IPSEC_DEV instead which handles
such case.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reported-by: Doug Ledford <dledford@redhat.com>

IB/mlx4: Move mlx4_uverbs_ex_query_device_resp to include/uapi/

This struct is involved in the user API for mlx4 and should not be hidden
inside a driver header file.

Fixes: 09d208b258a2 ("IB/mlx4: Add report for RSS capabilities by vendor channel")
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

Merge tag 'mlx5-updates-2018-02-28-1' of git://git./linux/kernel/git/mellanox/linux into k.o/wip/dl-for-next

mlx5-updates-2018-02-28-1 (IPSec-1)

This series consists of some fixes and refactors for the mlx5 drivers,
especially around the FPGA and flow steering. Most of them are trivial
fixes and are the foundation of allowing IPSec acceleration from user-space.

We use flow steering abstraction in order to accelerate IPSec packets.
When a user creates a steering rule, [s]he states that we'll carry an
encrypt/decrypt flow action (using a specific configuration) for every
packet which conforms to a certain match. Since currently offloading these
packets is done via FPGA, we'll add another set of flow steering ops.
These ops will execute the required FPGA commands and then call the
standard steering ops.

In order to achieve this, we need that the commands will get all the
required information. Therefore, we pass the fte object and embed the
flow_action struct inside the fte. In addition, we add the shim layer
that will later be used for alternating between the standard and the
FPGA steering commands.

Some fixes, like " net/mlx5e: Wait for FPGA command responses with a timeout"
are very relevant for user-space applications, as these applications could
be killed, but we still want to wait for the FPGA and update the kernel's
database.

Regards,
Aviad and Matan

Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/rxe: change the function rxe_init_device_param type

The function rxe_init_device_param always return 0. So the function
type is changed to void.

CC: Srinivas Eeda <srinivas.eeda@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: remove unnecessary rxe in rxe_send

In the function rxe_send, the variable rxe is not used in it.
So it should be removed.

CC: Srinivas Eeda <srinivas.eeda@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: remove unnecessary skb_clone

In send_atomic_ack function, it is not necessary to make a
skb_clone. To gain better performance (high throughput and
low latency), this skb_clone is removed.

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.

Based on 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 test results on Server(10 tests are made).
Before:
Throughput is 137.07 Mbit/sec
Latency is 517.76 usec/iter

After:
Throughput is 148.85 Mbit/sec
Latency is 476.64 usec/iter

The throughput is enhanced and the latency is reduced.

CC: Srinivas Eeda <srinivas.eeda@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/srpt: Add RDMA/CM support

Add a parameter for configuring the port on which the ib_srpt driver
listens for incoming RDMA/CM connections, namely
/sys/kernel/config/target/srpt/discovery_auth/rdma_cm_port. The default
value for this parameter is 0 which means "do not listen for incoming
RDMA/CM connections". Add RDMA/CM support to all code that handles
connection state changes. Modify srpt_init_nodeacl() such that ACLs can
be configured for IPv4 and IPv6 addresses.

Note: incoming connection requests are only accepted for ports that
have been enabled. See also the "if (!sport->enabled)" code in the
connection request handler. See also the following configfs attribute:
/sys/kernel/config/target/srpt/$port/$port/enable.

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

net/mlx5: Flow steering cmd interface should get the fte when deleting

Previously, deleting a flow steering entry only got the index.
Since the FPGA implementation of FTE's deletion might need to dig
inside the FTE itself, we would like to get the FTE's context.
Changing the interface to pass the FTE context.

Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

{net,IB}/mlx5: Add flow steering helpers

Add helper functions that check if a protocol is
part of a flow steering match criteria.

Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: Embed mlx5_flow_act into fs_fte

fte objects contain the match value and action. Currently, extending
the actions require in adding them both to the API and fs_fte.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: Add empty egress namespace to flow steering core

Currently, we don't support egress flow steering namespace in mlx5
flow steering core implementation. However, when we want to encrypt
a packet, we model it as a flow steering rule in the egress path.
To overcome this, we add an empty egress namespace to flow steering.
This namespace is initialized only when ipsec support exists.
In the future, this will grow to a full blown full steering
implementation, resembling the ingress path.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: Add shim layer between fs and cmd

The shim layer allows each namespace to define possibly different
functionality for add/delete/update commands. The shim layer
introduced here, will be used to support flow steering with the FPGA.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

{net,IB}/mlx5: Add has_tag to mlx5_flow_act

The has_tag member will indicate whether a tag action was specified
in flow specification.

A flow tag 0 = MLX5_FS_DEFAULT_FLOW_TAG is assumed a valid flow tag
that is currently used by mlx5 RDMA driver, whereas in HW flow_tag = 0
means that the user doesn't care about flow_tag.  HW always provide
a flow_tag = 0 if all flow tags requested on a specific flow are 0.

So we need a way (in the driver) to differentiate between a user really
requesting flow_tag = 0 and a user who does not care, in order to be
able to report conflicting flow tags on a specific flow.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

IB/mlx5: Pass mlx5_flow_act struct instead of multiple arguments

Group and pass all function arguments of parse_flow_attr call in one
common struct mlx5_flow_act.

This patch passes all the action arguments of parse_flow_attr in one common
struct mlx5_flow_act. It allows us to scale the number of actions without adding
new arguments to the function.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Acked-by: Jason Gunthorpe <jgg@mellanox.com>

net/mlx5: FPGA and IPSec initialization to be before flow steering

Some flow steering namespace initialization (i.e. egress namespace)
might depend on FPGA capabilities. Changing the initialization order
such that the FPGA will be initialized before flow steering.

Flow steering fs cmds initialization might depend on
IPSec capabilities. Changing the initialization order such
that the IPSec will be initialized before flow steering as well.

Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5e: Removed not need synchronize_rcu

This is already done by xfrm layer between state_dev_del callback
to state_dev_free callback.

Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5e: Fixed sleeping inside atomic context

We can't allocate with GFP_KERNEL inside spinlock.
Actually ida_simple doesn't require spinlock so remove it.

Fixes: 547eede070eb ("net/mlx5e: IPSec, Innova IPSec offload infrastructure")
Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5e: Wait for FPGA command responses with a timeout

Generally, FPGA IPSec commands must always complete.
We want to wait for one minute for them to complete gracefully also
when killing a process.

Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: Fixed compilation issue when CONFIG_MLX5_ACCEL is disabled

IPSec init and cleanup functions also depends on linux/mlx5/driver.h.

Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

IB/mlx5: Removed not used parameters

Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Acked-by: Jason Gunthorpe <jgg@mellanox.com>

RDMA/bnxt_re/qplib_sp: Use true and false for boolean values

Assign true or false to boolean variables instead of an integer value.

This issue was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

IB/srp: Use the IB_DEVICE_SG_GAPS_REG HCA feature if supported

If a HCA supports the SG_GAPS_REG feature then fewer memory regions
are required per command. This patch reduces the number of memory
regions that is allocated per SRP session.

Signed-off-by: Sergey Gorenko <sergeygo@mellanox.com>
Reviewed-by: Max Gurtovoy <maxg@mellanox.com>
Tested-by: Laurence Oberman <loberman@redhat.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Acked-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

IB/hfi1: Add a missing rcu_read_unlock()

This patch avoids that sparse reports the following:

drivers/infiniband/hw/hfi1/driver.c:251:13: warning: context imbalance in 'rcv_hdrerr' - different lock contexts for basic block

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Mike Marciniszyn <mike.marciniszyn@intel.com>
Cc: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

infiniband: hw: Drop unnecessary continue

Continue at the bottom of a loop are removed.
Issue found using drop_continue.cocci Coccinelle script.

Signed-off-by: Arushi Singhal <arushisinghal19971997@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

i40iw: Implement get_vector_affinity API

Storage ULPs (like NVMEoF) benefit from exposing affinity mapping
per completion vector to find the optimal multi-queue affinity
assignments. The ULPs call the verbs API ib_get_vector_affinity
introduced in commit c66cd353bbe ("RDMA/core: expose affinity mappings per
completion vector") to get the underlying devices affinity mappings.

Add support in driver to expose the affinity masks per MSI-X
completion vector.

Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

i40iw: Improve CM node lookup time on connection setup

Currently all CM nodes involved in a connection are
maintained in a connected_node list per dev. During
connection setup, we need to search this every time
we receive a packet on the iWARP LAN Queue (ILQ) and
this can be pretty inefficient for large number of
connections.

Fix this by organizing the CM nodes in two lists -
accelerated list and non-accelerated list. The search
on ILQ receive would be limited to only non accelerated
nodes. When a node moves to RTS, it is added to the
accelerated list.

Benchmarking ucmatose 16k connections shows a 20%
improvement in test completion time.

Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

i40iw: Refactor handling of txpend list

Currently the TX pending lists for IEQ and ILQ are
handled separately. The handling of both can be
consolidated in i40iw_poll_completion.

Signed-off-by: Mustafa Ismail <mustafa.ismail@intel.com>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

IB/srpt: Fix an out-of-bounds stack access in srpt_zerolength_write()

Avoid triggering an out-of-bounds stack access by changing the type
of 'wr' from ib_send_wr into ib_rdma_wr.

This patch fixes the following KASAN bug report:

BUG: KASAN: stack-out-of-bounds in rxe_post_send+0x7a9/0x9a0 [rdma_rxe]
Read of size 8 at addr ffff880068197a48 by task kworker/2:1/44

Workqueue: ib_cm cm_work_handler [ib_cm]
Call Trace:
 dump_stack+0x8e/0xcd
 print_address_description+0x6f/0x280
 kasan_report+0x25a/0x380
 __asan_load8+0x54/0x90
 rxe_post_send+0x7a9/0x9a0 [rdma_rxe]
 srpt_zerolength_write+0xf0/0x180 [ib_srpt]
 srpt_cm_rtu_recv+0x68/0x110 [ib_srpt]
 srpt_rdma_cm_handler+0xbb/0x15b [ib_srpt]
 cma_ib_handler+0x1aa/0x4a0 [rdma_cm]
 cm_process_work+0x30/0x100 [ib_cm]
 cm_work_handler+0xa86/0x351b [ib_cm]
 process_one_work+0x475/0x9f0
 worker_thread+0x69/0x690
 kthread+0x1ad/0x1d0
 ret_from_fork+0x3a/0x50

Fixes: aaf45bd83eba ("IB/srpt: Detect session shutdown reliably")
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: stable@vger.kernel.org
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

RDMA/rxe: Fix an out-of-bounds read

This patch avoids that KASAN reports the following when the SRP initiator
calls srp_post_send():

==================================================================
BUG: KASAN: stack-out-of-bounds in rxe_post_send+0x5c4/0x980 [rdma_rxe]
Read of size 8 at addr ffff880066606e30 by task 02-mq/1074

CPU: 2 PID: 1074 Comm: 02-mq Not tainted 4.16.0-rc3-dbg+ #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.0.0-prebuilt.qemu-project.org 04/01/2014
Call Trace:
dump_stack+0x85/0xc7
print_address_description+0x65/0x270
kasan_report+0x231/0x350
rxe_post_send+0x5c4/0x980 [rdma_rxe]
srp_post_send.isra.16+0x149/0x190 [ib_srp]
srp_queuecommand+0x94d/0x1670 [ib_srp]
scsi_dispatch_cmd+0x1c2/0x550 [scsi_mod]
scsi_queue_rq+0x843/0xa70 [scsi_mod]
blk_mq_dispatch_rq_list+0x143/0xac0
blk_mq_do_dispatch_ctx+0x1c5/0x260
blk_mq_sched_dispatch_requests+0x2bf/0x2f0
__blk_mq_run_hw_queue+0xdb/0x160
__blk_mq_delay_run_hw_queue+0xba/0x100
blk_mq_run_hw_queue+0xf2/0x190
blk_mq_sched_insert_request+0x163/0x2f0
blk_execute_rq+0xb0/0x130
scsi_execute+0x14e/0x260 [scsi_mod]
scsi_probe_and_add_lun+0x366/0x13d0 [scsi_mod]
__scsi_scan_target+0x18a/0x810 [scsi_mod]
scsi_scan_target+0x11e/0x130 [scsi_mod]
srp_create_target+0x1522/0x19e0 [ib_srp]
kernfs_fop_write+0x180/0x210
__vfs_write+0xb1/0x2e0
vfs_write+0xf6/0x250
SyS_write+0x99/0x110
do_syscall_64+0xee/0x2b0
entry_SYSCALL_64_after_hwframe+0x42/0xb7

The buggy address belongs to the page:
page:ffffea0001998180 count:0 mapcount:0 mapping:0000000000000000 index:0x0
flags: 0x4000000000000000()
raw: 4000000000000000 0000000000000000 0000000000000000 00000000ffffffff
raw: dead000000000100 dead000000000200 0000000000000000 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
ffff880066606d00: 00 00 00 00 00 00 00 00 00 00 00 00 00 f1 f1 f1
ffff880066606d80: f1 00 f2 f2 f2 f2 f2 f2 f2 00 00 f2 f2 f2 f2 f2
>ffff880066606e00: f2 00 00 00 00 00 f2 f2 f2 f3 f3 f3 f3 00 00 00
                                    ^
ffff880066606e80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
ffff880066606f00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
==================================================================

Fixes: 8700e3e7c485 ("Soft RoCE driver")
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Moni Shoua <monis@mellanox.com>
Cc: stable@vger.kernel.org
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

RDMA/core: Avoid that ib_drain_qp() triggers an out-of-bounds stack access

This patch fixes the following KASAN complaint:

==================================================================
BUG: KASAN: stack-out-of-bounds in rxe_post_send+0x77d/0x9b0 [rdma_rxe]
Read of size 8 at addr ffff880061aef860 by task 01/1080

CPU: 2 PID: 1080 Comm: 01 Not tainted 4.16.0-rc3-dbg+ #2
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.0.0-prebuilt.qemu-project.org 04/01/2014
Call Trace:
dump_stack+0x85/0xc7
print_address_description+0x65/0x270
kasan_report+0x231/0x350
rxe_post_send+0x77d/0x9b0 [rdma_rxe]
__ib_drain_sq+0x1ad/0x250 [ib_core]
ib_drain_qp+0x9/0x30 [ib_core]
srp_destroy_qp+0x51/0x70 [ib_srp]
srp_free_ch_ib+0xfc/0x380 [ib_srp]
srp_create_target+0x1071/0x19e0 [ib_srp]
kernfs_fop_write+0x180/0x210
__vfs_write+0xb1/0x2e0
vfs_write+0xf6/0x250
SyS_write+0x99/0x110
do_syscall_64+0xee/0x2b0
entry_SYSCALL_64_after_hwframe+0x42/0xb7

The buggy address belongs to the page:
page:ffffea000186bbc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0
flags: 0x4000000000000000()
raw: 4000000000000000 0000000000000000 0000000000000000 00000000ffffffff
raw: 0000000000000000 ffffea000186bbe0 0000000000000000 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
ffff880061aef700: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
ffff880061aef780: 00 00 00 00 00 00 00 00 00 00 00 f1 f1 f1 f1 00
>ffff880061aef800: f2 f2 f2 f2 f2 f2 f2 00 00 00 00 00 f2 f2 f2 f2
                                                      ^
ffff880061aef880: f2 f2 f2 00 00 00 00 00 00 00 00 00 00 00 f2 f2
ffff880061aef900: f2 f2 f2 00 00 00 00 00 00 00 00 00 00 00 00 00
==================================================================

Fixes: 765d67748bcf ("IB: new common API for draining queues")
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Steve Wise <swise@opengridcomputing.com>
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: stable@vger.kernel.org
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

infiniband: remove redundant assignment to pointer 'rdi'

The pointer rdi is being initialized with a value that is never read
and re-assigned immediately after, hence the initialization is redundant
and can be removed.

Cleans up clang warning:
drivers/infiniband/sw/rdmavt/vt.c:94:23: warning: Value stored to 'rdi'
during its initialization is never read

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

IB/rxe: Remove unused variable (char *rxe_qp_state_name[])

Note: This is compile only tested as I have no access to the hw.  This
variable was not used anywhere in the code. Removing it saves 24 bytes.

add/remove: 0/1 grow/shrink: 0/0 up/down: 0/-24 (-24)
Function                                     old     new   delta
rxe_qp_state_name                             24       -     -24
Total: Before=3348732, After=3348708, chg -0.00%

Signed-off-by: Hernán Gonzalez <hernan@vanguardiasur.com.ar>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

IB/qib: Move char *qib_sdma_state_names[] and constify while there.

Note: This is compile only tested as I have no access to the hw.
This variable was not used in qib_sdma.c but in qib_iba7322.c. Declaring it
there, as static, saves 56 bytes.

add/remove: 0/2 grow/shrink: 0/0 up/down: 0/-144 (-144)
Function                                     old     new   delta
qib_sdma_state_names                          56       -     -56
qib_sdma_event_names                          88       -     -88
Total: Before=2874565, After=2874421, chg -0.01%

Signed-off-by: Hernán Gonzalez <hernan@vanguardiasur.com.ar>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

IB/qib: Remove unused variable (char *qib_sdma_event_names[])

Note: This is compile only tested as I have no access to the hw.

This variable was not used anywhere in the code. Removing it saves 88
bytes.

add/remove: 0/1 grow/shrink: 0/0 up/down: 0/-88 (-88)
Function                                     old     new   delta
qib_sdma_event_names                          88       -     -88
Total: Before=2874565, After=2874477, chg -0.00%

Signed-off-by: Hernán Gonzalez <hernan@vanguardiasur.com.ar>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

IB/srp: Use %pIS instead of inet_ntop()

Except for a minor log message change, this patch does not change
any functionality. For the introduction of %pIS, see also commit
1067964305df ("lib: vsprintf: add IPv4/v6 generic %p[Ii]S[pfs]
format specifier").

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

Revert "IB/srp: Avoid that a cable pull can trigger a kernel crash"

The caller of srp_ib_lookup_path() is responsible for holding a reference
on the SCSI host. That means that commit 8a0d18c62121 was not necessary.
Hence revert it.

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

IB/srp: Fix srp_abort()

Before commit e494f6a72839 ("[SCSI] improved eh timeout handler") it
did not really matter whether or not abort handlers like srp_abort()
called .scsi_done() when returning another value than SUCCESS. Since
that commit however this matters. Hence only call .scsi_done() when
returning SUCCESS.

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

infiniband: bnxt_re: use BIT_ULL() for 64-bit bit masks

On 32-bit targets, we otherwise get a warning about an impossible constant
integer expression:

In file included from include/linux/kernel.h:11,
                 from include/linux/interrupt.h:6,
                 from drivers/infiniband/hw/bnxt_re/ib_verbs.c:39:
drivers/infiniband/hw/bnxt_re/ib_verbs.c: In function 'bnxt_re_query_device':
include/linux/bitops.h:7:24: error: left shift count >= width of type [-Werror=shift-count-overflow]
 #define BIT(nr)   (1UL << (nr))
                        ^~
drivers/infiniband/hw/bnxt_re/bnxt_re.h:61:34: note: in expansion of macro 'BIT'
 #define BNXT_RE_MAX_MR_SIZE_HIGH BIT(39)
                                  ^~~
drivers/infiniband/hw/bnxt_re/bnxt_re.h:62:30: note: in expansion of macro 'BNXT_RE_MAX_MR_SIZE_HIGH'
 #define BNXT_RE_MAX_MR_SIZE  BNXT_RE_MAX_MR_SIZE_HIGH
                              ^~~~~~~~~~~~~~~~~~~~~~~~
drivers/infiniband/hw/bnxt_re/ib_verbs.c:149:25: note: in expansion of macro 'BNXT_RE_MAX_MR_SIZE'
  ib_attr->max_mr_size = BNXT_RE_MAX_MR_SIZE;
                         ^~~~~~~~~~~~~~~~~~~

Fixes: 872f3578241d ("RDMA/bnxt_re: Add support for MRs with Huge pages")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

infiniband: qplib_fp: fix pointer cast

Building for a 32-bit target results in a couple of warnings from casting
between a 32-bit pointer and a 64-bit integer:

drivers/infiniband/hw/bnxt_re/qplib_fp.c: In function 'bnxt_qplib_service_nq':
drivers/infiniband/hw/bnxt_re/qplib_fp.c:333:23: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast]
    bnxt_qplib_arm_srq((struct bnxt_qplib_srq *)q_handle,
                       ^
drivers/infiniband/hw/bnxt_re/qplib_fp.c:336:12: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast]
            (struct bnxt_qplib_srq *)q_handle,
            ^
In file included from include/linux/byteorder/little_endian.h:5,
                 from arch/arm/include/uapi/asm/byteorder.h:22,
                 from include/asm-generic/bitops/le.h:6,
                 from arch/arm/include/asm/bitops.h:342,
                 from include/linux/bitops.h:38,
                 from include/linux/kernel.h:11,
                 from include/linux/interrupt.h:6,
                 from drivers/infiniband/hw/bnxt_re/qplib_fp.c:39:
drivers/infiniband/hw/bnxt_re/qplib_fp.c: In function 'bnxt_qplib_create_srq':
include/uapi/linux/byteorder/little_endian.h:31:43: error: cast from pointer to integer of different size [-Werror=pointer-to-int-cast]
 #define __cpu_to_le64(x) ((__force __le64)(__u64)(x))
                                           ^
include/linux/byteorder/generic.h:86:21: note: in expansion of macro '__cpu_to_le64'
 #define cpu_to_le64 __cpu_to_le64
                     ^~~~~~~~~~~~~
drivers/infiniband/hw/bnxt_re/qplib_fp.c:569:19: note: in expansion of macro 'cpu_to_le64'
  req.srq_handle = cpu_to_le64(srq);

Using a uintptr_t as an intermediate works on all architectures.

Fixes: 37cb11acf1f7 ("RDMA/bnxt_re: Add SRQ support for Broadcom adapters")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

RDMA/iwpm: Delete an error message for a failed memory allocation in iwpm_create_nlmsg()

Omit an extra message for a memory allocation failure in this function.

This issue was detected by using the Coccinelle software.

Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

IB/usnic: Delete an error message for a failed memory allocation in usnic_transport_init()

Omit an extra message for a memory allocation failure in this function.

This issue was detected by using the Coccinelle software.

Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

RDMA/mlx5: Refactor QP type check to be as early as possible

Perform QP type check in one place and fail as early as possible.

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

mailmap: Map Leon Romanovsky's emails

Update .mailmap file to point to my primary open-source
related e-mail address.

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

IB/uverbs: Tidy uverbs_uobject_add

Maintaining the uobjects list is mandatory, hoist it into the common
rdma_alloc_commit_uobject() function and inline it as there is now
only one caller.

Signed-off-by: Leon Romanovsky <leon@kernel.org>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

Merge tag 'mlx5-updates-2018-02-23' of git://git./linux/kernel/git/mellanox/linux into k.o/wip/dl-for-next

mlx5-update-2018-02-23 (IB representors)

From: Mark Bloch <markb@mellanox.com>
=========
Add IB representor when in switchdev mode

The following series adds support for an IB (RAW Ethernet only) device
representor which is created when the user switches to switchdev mode.

Today when switching to switchdev mode the only representors which are
created are net devices. Each netdev is a representor of a virtual
function and any data sent via the representor is received on the virtual
function, and any data sent via the virtual function is received by the
representor.

For the mlx5 driver the main use of this functionality is to be able to
use Open vSwitch on the hypervisor in order to manage/control traffic
from/to the virtual functions. Open vSwitch can also work with  DPDK
devices and not just net devices, this series exposes an IB device, which
Mellanox PMD driver uses, which then can be used by Open vSwitch DPDK.

An IB device representor exposes only RAW Ethernet QP capabilities and
the ability to create flow rules to direct traffic to its RX queues. The
state of the IB device (ACTIVE/DOWN etc..) is based on the state of the
corresponding net device representor. No other RDMA/RoCE functionality is
currently supported and no GID table is exposed.
=========

Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/mlx5: Disable self loopback check when in switchdev mode

When in switchdev mode, there is no need to do self loopback checks
as we can't receive those packets, we insert steering rules to the
eswitch that make sure packets can't be looped back.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: E-Switch, Reload IB interface when switching devlink modes

Up until this point it wasn't possible to activate IB representors
when switching to switchdev mode, remove this limitation.

We trigger reload of the PF IB interface in order to make sure that
already allocated resources are invalid and new resources will be opened
correctly with all the limitations of switchdev mode applied (only raw
packet capabilities, without RoCE). We also move the remove/add to a
place where the E-Switch mode is set/unset to better control when to
trigger this action, this will allow the IB side to start in the correct
mode.

For better code reuse, create a function which reloads an interface and
export it.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

IB/mlx5: Add proper representors support

This commit adds full support for IB representor:

1) Representors profile, We add two new profiles:
   nic_rep_profile - This profile will be used to create an IB device that
   represents the PF/UPLINK.
   rep_profile - This profile will be used to create an IB device that
   represents VFs. Each VF will be its own representor.
2) Proper load/unload callbacks, Those are called by the E-Switch when
   moving to/from switchdev mode.
3) Different flow DB handling for when we in switchdev mode.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

IB/mlx5: E-Switch, Add rule to forward traffic to vport

In order to forward traffic from representor's SQ to the right virtual
function, every time an SQ is created also add the corresponding flow rule
to the FDB.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

IB/mlx5: Don't expose MR cache in switchdev mode

When enabling many VFs and switching to switchdev mode, the total amount
of mkeys we try to allocate when loading representors is very large and
may cause timeouts on allocations, the same issues was observed on VFs
and we employ the same fix that was done for them. We avoid allocating
the full MR cache on load but still allow it to be manipulated once the
IB device is loaded.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

IB/mlx5: When in switchdev mode, expose only raw packet capabilities

Currently in switchdev mode we allow only for raw packet QPs.
Expose the right capabilities and set the gid table length to 0, also
make sure we don't try to enable RoCE, so split the function
to enable RoCE so representors can enable only the notifier needed for
net device events.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

IB/mlx5: Listen to netdev register/unresiter events in switchdev mode

Currently we listen to netdev register/unregister event based on PCI
device. When in switchdev mode PF and representors share the same PCI
device, so in order to pair ib device and netdev in switchdev mode
compare the netdev that triggered the event to that of the representor.

Expose a function that lets you receive the netdev associated what
a given representor.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

IB/mlx5: Add match on vport when in switchdev mode

When we point to a representor, it means we are in switchdev mode.
The flow db is shared between PF and virtual function representors
so each rule created needs to have a match on its specific source port.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

IB/mlx5: Allocate flow DB only on PF IB device

A flow DB is a shared resource between PF and representors,
need to allocate it only when creating the PF IB device.
Once we add IB representors, they will use the flow db which was
created by the PF.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

IB/mlx5: Add basic regiser/unregister representors code

Create the basic infrastructure of registering and unregistering
IB representors. The load/unload callbacks are left empty and
proper implementation will be introduced in following patches.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: E-Switch, Add definition of IB representor

Create a new representor type: REP_IB. which will be initialized by an IB
device that is used as a logical representor of a eswitch vport (VF or
uplink) just like we have a net device today in switchdev mode.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: E-Switch, Optimize HW steering tables in switchdev mode

Under switchdev mode we insert an eswitch miss rule causing any
unmatched traffic to be sent towards the PF vport. This miss rule can
be optimized if we break it to two, one case is for multicast traffic and
the other for unicast.

Breaking the miss rule into two (unicast and multicast) allows the firmware
to program the hardware in a more efficient way.

Using ConncetX-5 Ex with IXIA and testpmd (which use IB representors):

IXIA -> NIC -> PF -> IB representor -> NIC -> VF:
    - Without this optimization: 9.2 MPPS.
    - With this optimization: 18 MPPS.

VF -> NIC -> IB representor-> PF -> NIC -> IXIA:
    - Without this optimization: 17 MPPS.
    - With this optimization: 23.4 MPPS.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: E-Switch, Increase number of FTEs in FDB in switchdev mode

The max FTE number should be the max number of SQs that can be opened.
Ethernet representors open one SQ each. Once we add IB representor this
will increase (depends on the user). For now lets start with 31
per IB representor and if needed increase in the future.

This increase only affects the number of FTEs in the slow path FDB,
offloaded rules (done via TC on the fast path portion of the FDB)
aren't affected.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: E-Switch, Move representors definition to a global scope

In preparation for IB representors, move representors structs to a global
scope, also expose functions needed for registration, unregistration,
eswitch mode and creating a flow rule to direct traffic from SQs to the
right VF.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: E-Switch, Add callback to get representor device

Add a callback interface to get a protocol device (per representor type).
The Ethernet representors will expose their netdev via this interface.

This functionality can be later used by IB representor in order to find the
corresponding net device representor.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

RDMA/verbs: Return proper error code for not supported system call

The proper return error is -EOPNOTSUPP and not -ENOSYS, so update
all places in verbs.c to match this semantics.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/uverbs: Reduce number of command header flags checks

Simplify the code by directly checking the availability of extended
command flog instead of doing multiple shift operations.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/uverbs: Replace user's types with kernel's types

The internal to kernel variable declarations don't need to be
declared with user types. This patch converts such occurrences
appeared in ib_uverbs_write().

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/uverbs: Refactor the header validation logic

Move all header validation logic to be performed before SRCU read lock.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMa/uverbs: Copy ex_hdr outside of SRCU read lock

The SRCU read lock protects the IB device pointer
and doesn't need to be called before copying user
provided header.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/uverbs: Move uncontext check before SRCU read lock

There is no need to take SRCU lock before checking
file->ucontext, so move it do it before it.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/uverbs: Properly check command supported mask

The check based on index is not sufficient because

  IB_USER_VERBS_EX_CMD_CREATE_CQ = IB_USER_VERBS_CMD_CREATE_CQ

and IB_USER_VERBS_CMD_CREATE_CQ <= IB_USER_VERBS_CMD_OPEN_QP,
so if we execute IB_USER_VERBS_EX_CMD_CREATE_CQ this code checks
ib_dev->uverbs_cmd_mask not ib_dev->uverbs_ex_cmd_mask.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/uverbs: Refactor command header processing

Move all command header processing into separate function
and perform those checks before acquiring SRCU read lock.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/uverbs: Unify return values of not supported command

The non-existing command is supposed to return -EOPNOTSUPP, but the
current code returns different errors for different flows for the
same failure. This patch unifies those flows.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/uverbs: Return not supported error code for unsupported commands

Command that doesn't exist means that it is not supported,
so update code to return -EOPNOTSUPP in case of failure.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/uverbs: Fail as early as possible if not enough header data was provided

Fail as early as possible if not enough header data
was provided.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/uverbs: Refactor flags checks and update return value

Since commit f21519b23c1b ("IB/core: extended command: an
improved infrastructure for uverbs commands"), the uverbs
supports extra flags as an input to the command interface.

However actually, there is only one flag available and used,
so it is better to refactor the code, so the resolution and
report to the users is done as early as possible.

As part of this change, we changed the return value of failure case
from ENOSYS to be EINVAL to be consistent with the rest flags checks.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/uverbs: Update sizeof users

Update sizeof() users to be consistent with coding style.

Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/uverbs: Convert command mask validity check function to be bool

The function validate_command_mask() returns only two results: success
or failure, so convert it to return bool instead of 0 and -1.

Reported-by: Noa Osherovich <noaos@mellanox.com>
Reviewed-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

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

There is a 14 patch series waiting to come into for-next that has a
dependecy on code submitted into this kernel's for-rc series.  So, merge
the for-rc branch into the current for-next in order to make the patch
series apply cleanly.

Signed-off-by: Doug Ledford <dledford@redhat.com>

Merge tag 'mlx5-updates-2018-02-21' of git://git./linux/kernel/git/mellanox/linux into k.o/wip/dl-for-next

mlx5-updates-2018-02-21

This series includes shared code updates for mlx5 core driver for both
netdev and rdma subsystems.

By Saeed,
First six patches of the series are meant to address a performance issue
and should provide a performance boost for multi core IRQ interrupt hungry
workloads.  The issue is fixed in the first patch, all other patches are
meant to refactor the code in light of this fix.

The problem it comes to fix, is a shared spinlock accessed across all HCA
IRQs which protects the CQ database.  To solve this we simply move the CQ
database and its spinlock to be per EQ (IRQ), thus per core.

By Yonatan,
Fragmented completion queue (CQ) for RDMA,
core driver implementation to create fragmented CQ buffers rather than
one large contiguous memory buffer, the implementation scheme already
exist and used by the netdev CQs, the patch shares that code with the
rdma CQ creation flow and makes use of the new API in mlx5_ib driver.

Thanks,
Saeed.

Merged into rdma-next tree as well as net-next tree to prevent conflicts
in future patches between the two trees.

Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/uverbs: Fix kernel panic while using XRC_TGT QP type

Attempt to modify XRC_TGT QP type from the user space (ibv_xsrq_pingpong
invocation) will trigger the following kernel panic. It is caused by the
fact that such QPs missed uobject initialization.

[   17.408845] BUG: unable to handle kernel NULL pointer dereference at 0000000000000048
[   17.412645] IP: rdma_lookup_put_uobject+0x9/0x50
[   17.416567] PGD 0 P4D 0
[   17.419262] Oops: 0000 [#1] SMP PTI
[   17.422915] CPU: 0 PID: 455 Comm: ibv_xsrq_pingpo Not tainted 4.16.0-rc1+ #86
[   17.424765] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.7.5-0-ge51488c-20140602_164612-nilsson.home.kraxel.org 04/01/2014
[   17.427399] RIP: 0010:rdma_lookup_put_uobject+0x9/0x50
[   17.428445] RSP: 0018:ffffb8c7401e7c90 EFLAGS: 00010246
[   17.429543] RAX: 0000000000000000 RBX: ffffb8c7401e7cf8 RCX: 0000000000000000
[   17.432426] RDX: 0000000000000001 RSI: 0000000000000000 RDI: 0000000000000000
[   17.437448] RBP: 0000000000000000 R08: 00000000000218f0 R09: ffffffff8ebc4cac
[   17.440223] R10: fffff6038052cd80 R11: ffff967694b36400 R12: ffff96769391f800
[   17.442184] R13: ffffb8c7401e7cd8 R14: 0000000000000000 R15: ffff967699f60000
[   17.443971] FS:  00007fc29207d700(0000) GS:ffff96769fc00000(0000) knlGS:0000000000000000
[   17.446623] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   17.448059] CR2: 0000000000000048 CR3: 000000001397a000 CR4: 00000000000006b0
[   17.449677] Call Trace:
[   17.450247]  modify_qp.isra.20+0x219/0x2f0
[   17.451151]  ib_uverbs_modify_qp+0x90/0xe0
[   17.452126]  ib_uverbs_write+0x1d2/0x3c0
[   17.453897]  ? __handle_mm_fault+0x93c/0xe40
[   17.454938]  __vfs_write+0x36/0x180
[   17.455875]  vfs_write+0xad/0x1e0
[   17.456766]  SyS_write+0x52/0xc0
[   17.457632]  do_syscall_64+0x75/0x180
[   17.458631]  entry_SYSCALL_64_after_hwframe+0x21/0x86
[   17.460004] RIP: 0033:0x7fc29198f5a0
[   17.460982] RSP: 002b:00007ffccc71f018 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
[   17.463043] RAX: ffffffffffffffda RBX: 0000000000000078 RCX: 00007fc29198f5a0
[   17.464581] RDX: 0000000000000078 RSI: 00007ffccc71f050 RDI: 0000000000000003
[   17.466148] RBP: 0000000000000000 R08: 0000000000000078 R09: 00007ffccc71f050
[   17.467750] R10: 000055b6cf87c248 R11: 0000000000000246 R12: 00007ffccc71f300
[   17.469541] R13: 000055b6cf8733a0 R14: 0000000000000000 R15: 0000000000000000
[   17.471151] Code: 00 00 0f 1f 44 00 00 48 8b 47 48 48 8b 00 48 8b 40 10 e9 0b 8b 68 00 90 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 55 53 89 f5 <48> 8b 47 48 48 89 fb 40 0f b6 f6 48 8b 00 48 8b 40 20 e8 e0 8a
[   17.475185] RIP: rdma_lookup_put_uobject+0x9/0x50 RSP: ffffb8c7401e7c90
[   17.476841] CR2: 0000000000000048
[   17.477764] ---[ end trace 1dbcc5354071a712 ]---
[   17.478880] Kernel panic - not syncing: Fatal exception
[   17.480277] Kernel Offset: 0xd000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff)

Fixes: 2f08ee363fe0 ("RDMA/restrack: don't use uaccess_kernel()")
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>