The coming nldev needs to iterate over all IB devices in the system
and in order to not expose the ib_devices list outside the devices.c,
it is necessary to provide function iterator.

Current version is written explicitly for nldev callback to avoid
over-engineering at this stage, but it can be easily extended for
other types.
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Reviewed-by: NSteve Wise <swise@opengridcomputing.com>

The RDMA netlink client infrastructure was removed and made obsolete.
The old infrastructure defined struct ibnl_client_cbs. Now that all
uses of this have been updated to the new infrastructure, rename the
struct to be compliant with the current stack naming standards:
struct rdma_nl_cbs.
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Reviewed-by: NSteve Wise <swise@opengridcomputing.com>

Make ibnl_chk_listeners function to be one line by removing
unneeded comparison.

Rename that function to be complaint to other functions in RDMA netlink.
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Reviewed-by: NSteve Wise <swise@opengridcomputing.com>

The pointer to netlink header was not used in the ibnl_multicast
function, so let's remove it and simplify the function
signature.
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Reviewed-by: NSteve Wise <swise@opengridcomputing.com>

Netlink message header is not needed for unicast reply, hence remove it.
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Reviewed-by: NSteve Wise <swise@opengridcomputing.com>

Reuse standard macros to cancel the netlink message
in case of error.
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Reviewed-by: NSteve Wise <swise@opengridcomputing.com>

Add ability to provide flags to control RDMA netlink callbacks
and convert addr.c and sa_query.c to be first users of such
infrastructure. It allows to move their CAP_NET_ADMIN checks
into netlink core.
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Reviewed-by: NSteve Wise <swise@opengridcomputing.com>

The iwcm exports functions which are not used outside of ib_core.
This patch simply removes these EXPORT_SYMBOLS.
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Reviewed-by: NChien Tin Tung <chien.tin.tung@intel.com>

RDMA netlink implementation guarantees that supplied
client number is in allowed range.
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Reviewed-by: NChien Tin Tung <chien.tin.tung@intel.com>

The standard netlink_rcv_skb function skips messages without
NLM_F_REQUEST flag in it, while SA netlink client issues them.

In commit bc10ed7d ("IB/core: Add rdma netlink helper functions")
the local function was introduced to allow such messages.

This led to double pass for every incoming message.

In this patch, we unify that local implementation and netlink_rcv_skb
functions, so there will be no need for double pass anymore.

As a outcome, this combined function gained more strict check
for NLM_F_REQUEST flag and it is now allowed for SA pathquery
client only.
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>

Owner field is not needed to be set because netlink is part of ib_core
which will be unloaded last after all other modules are unloaded.
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>

RDMA netlink has a complicated infrastructure for dynamically
registering and de-registering netlink clients to the NETLINK_RDMA
group. The complicated portion of this code is not widely used because
2 of the 3 current clients are statically compiled together with
netlink.c. The infrastructure, therefore, is deemed overkill.

Refactor the code to eliminate the dynamically added clients. Now all
clients are pre-registered in a client array at compile time, and at run
time they merely check-in with the infrastructure to pass their callback
table for inclusion in the pre-sized client array.

This also allows for future cleanups and removal of unneeded code in the
iwcm* netlink handler.
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Reviewed-by: NChien Tin Tung <chien.tin.tung@intel.com>

Add a wait/retry version of ibnl_unicast, ibnl_unicast_wait,
and modify ibnl_unicast to not wait/retry.  This eliminates
the undesirable wait for future users of ibnl_unicast.

Change Portmapper calls originating from kernel to user-space
to use ibnl_unicast_wait and take advantage of the wait/retry
logic in netlink_unicast.
Signed-off-by: NMustafa Ismail <mustafa.ismail@intel.com>
Signed-off-by: NChien Tin Tung <chien.tin.tung@intel.com>
Signed-off-by: NLeon Romanovsky <leon@kernel.org>

The initial patch for changing the stack to use RoCEv2 GIDs by default
set the CMA_PREFERRED_ROCE_GID_TYPE to an incorrect value.  Instead of
an absolute value, we needed to set the right bit in a bitmask.  Correct
the default setting so we use RoCEv2 by default.

Fixes: 63a5f483 (IB/cma: Set default gid type to RoCEv2)
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Enable QP creation with a given source QP number, the created QP will
use the source QPN as its wire QP number.

To create such a QP, root privileges (i.e. CAP_NET_RAW) are required
from the user application.

This comes as a pre-patch for downstream patches in this series to
allow user space applications to accelerate traffic which is typically
handled by IPoIB ULP.
Signed-off-by: NYishai Hadas <yishaih@mellanox.com>
Reviewed-by: NMaor Gottlieb <maorg@mellanox.com>
Signed-off-by: NLeon Romanovsky <leon@kernel.org>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

When creating address handle from multicast GID, set MAC according to
the appropriate formula instead of searching for it in the GID table:
- For IPv4 multicast GID use ip_eth_mc_map().
- For IPv6 multicast GID use ipv6_eth_mc_map().
Signed-off-by: NNoa Osherovich <noaos@mellanox.com>
Reviewed-by: NMoni Shoua <monis@mellanox.com>
Signed-off-by: NLeon Romanovsky <leon@kernel.org>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

RoCEv2 Annex states that for RoCEv2 over IPv4, the corresponding
IPv4 address is encoded into the GID according to the following rule:
GID= :ffff:<IPv4 address>

Remove the 0xff0e prefix for RoCEv2 packets with IPv4 and leave it
zeroed and change rdma_is_multicast_addr() to consider the new logic.
Signed-off-by: NNoa Osherovich <noaos@mellanox.com>
Reviewed-by: NMoni Shoua <monis@mellanox.com>
Signed-off-by: NLeon Romanovsky <leon@kernel.org>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

RoCE Annex (A16.9.10/11) declares that during attach (detach) QP to a
multicast group, if the QP is associated with a RoCE port, the
multicast group MLID is unused and is ignored.

During attach or detach multicast, when the QP is associated with a
port, it is enough to check the port's link layer and validate the
LID only if it is Infiniband. Otherwise, avoid validating the
multicast LID.

Fixes: 8561eae6 ("IB/core: For multicast functions, verify that LIDs are multicast LIDs")
Signed-off-by: NNoa Osherovich <noaos@mellanox.com>
Reviewed-by: NMoni Shoua <monis@mellanox.com>
Signed-off-by: NLeon Romanovsky <leon@kernel.org>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Logic of retrieving netdev speed from net_device and translating it to
IB speed is implemented in rxe, in usnic and in bnxt drivers.

Define new function which merges all.
Signed-off-by: NYuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: NChristian Benvenuti <benve@cisco.com>
Reviewed-by: NSelvin Xavier <selvin.xavier@broadcom.com>
Reviewed-by: NMoni Shoua <monis@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

RoCEv2 is the preferred RDMA protocol for Ethernet link layer because
of its advantages over RoCEv1. For better user experience make it the
default choice for RDMA_CM connections if device/port support it.
Signed-off-by: NMoni Shoua <monis@mellanox.com>
Reviewed-by: NMatan Barak <matanb@mellanox.com>
Signed-off-by: NLeon Romanovsky <leon@kernel.org>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Initialize the port_num for iWARP in rdma_init_qp_attr.

Fixes: 5ecce4c9("Check port number supplied by user verbs cmds")
Cc: <stable@vger.kernel.org> # v2.6.14+
Reviewed-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NMustafa Ismail <mustafa.ismail@intel.com>
Tested-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

The port number is only valid if IB_QP_PORT is set in the mask.
So only check port number if it is valid to prevent modify_qp from
failing due to an invalid port number.

Fixes: 5ecce4c9("Check port number supplied by user verbs cmds")
Cc: <stable@vger.kernel.org> # v2.6.14+
Reviewed-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NMustafa Ismail <mustafa.ismail@intel.com>
Tested-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Delete unused variables to prevent sparse warnings.

Fixes: db1b5ddd ("IB/core: Rename uverbs event file structure")
Fixes: fd3c7904 ("IB/core: Change idr objects to use the new schema")
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Playing with IP-O-IB interface can trigger a warning message:
"ib0: Failed to modify QP to ERROR state" to be logged.
This happens when the QP is in IB_QPS_RESET state and the stack
is trying to transition it to IB_QPS_ERR state in ipoib_ib_dev_stop().

According to the IB spec, Table 91 - "QP State Transition Properties"
it looks like the transition from reset to error is valid:

Transition: Any State to Error
Required Attributes: None
Optional Attributes: None allowed
Actions: Queue processing is stopped. Work Requests pending or in
process are completed in error, when possible.

This patch allows the transition and quiets the message.
Reviewed-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NTadeusz Struk <tadeusz.struk@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Reviewed-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Currently the RoCE GID management uses the ib_wq to do add and delete new GIDs
according to the netdev events.

The ib_wq isn't an ordered workqueue and thus two work elements can be executed
concurrently which will result in unexpected behavior and inconsistency of the
GIDs cache content.

Example:
ifconfig eth1 11.11.11.11/16 up

This command will invoke the following netdev events in the following order:
1. NETDEV_UP
2. NETDEV_DOWN
3. NETDEV_UP

If (2) and (3) will be executed concurrently or in reverse order, instead of
having a new GID with 11.11.11.11 IP, we will end up without any new GIDs.
Signed-off-by: NMajd Dibbiny <majd@mellanox.com>
Signed-off-by: NLeon Romanovsky <leon@kernel.org>
Reviewed-by: NYuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

This patch makes use of IB core's ib_modify_qp_with_udata function that
also resolves the DMAC and handles udata.
Signed-off-by: NParav Pandit <parav@mellanox.com>
Reviewed-by: NEli Cohen <eli@mellanox.com>
Reviewed-by: NDaniel Jurgens <danielj@mellanox.com>
Signed-off-by: NLeon Romanovsky <leon@kernel.org>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

This patch adds new function ib_modify_qp_with_udata so that
uverbs layer can avoid handling L2 mac address at verbs layer
and depend on the core layer to resolve the mac address consistently
for all required QPs.
Signed-off-by: NParav Pandit <parav@mellanox.com>
Reviewed-by: NEli Cohen <eli@mellanox.com>
Reviewed-by: NDaniel Jurgens <danielj@mellanox.com>
Signed-off-by: NLeon Romanovsky <leon@kernel.org>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

When resolving an IP address that is on the host of the caller the
result from querying the routing table is the loopback device. This is
not a valid response, because it doesn't represent the RDMA device and
the port.

Therefore, callers need to check the resolved device and if it is a
loopback device find an alternative way to resolve it. To avoid this we
make sure that the response from rdma_resolve_ip() will not be the
loopback device.

While that, we fix an static checker warning about dereferencing an
unintitialized pointer using the same solution as in commit abeffce9
("net/mlx5e: Fix a -Wmaybe-uninitialized warning") as a reference.
Signed-off-by: NMoni Shoua <monis@mellanox.com>
Signed-off-by: NLeon Romanovsky <leon@kernel.org>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

In function addr_resolve() the namespace is a required input parameter
and not an output. It is passed later for searching the routing table
and device addresses. Also, it shouldn't be copied back to the caller.

Fixes: 565edd1d ('IB/addr: Pass network namespace as a parameter')
Cc: <stable@vger.kernel.org> # v4.3+
Signed-off-by: NMoni Shoua <monis@mellanox.com>
Signed-off-by: NLeon Romanovsky <leon@kernel.org>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

While looking into Coverity ID 1351047 I ran into the following
piece of code at
drivers/infiniband/core/verbs.c:496:

ret = rdma_addr_find_l2_eth_by_grh(&dgid, &sgid,
                                   ah_attr->dmac,
                                   wc->wc_flags & IB_WC_WITH_VLAN ?
                                   NULL : &vlan_id,
                                   &if_index, &hoplimit);

The issue here is that the position of arguments in the call to
rdma_addr_find_l2_eth_by_grh() function do not match the order of
the parameters:

&dgid is passed to sgid
&sgid is passed to dgid

This is the function prototype:

int rdma_addr_find_l2_eth_by_grh(const union ib_gid *sgid,
 				 const union ib_gid *dgid,
 				 u8 *dmac, u16 *vlan_id, int *if_index,
 				 int *hoplimit)

My question here is if this is intentional?

Answer:
Yes. ib_init_ah_from_wc() creates ah from the incoming packet.
Incoming packet has dgid of the receiver node on which this code is
getting executed and sgid contains the GID of the sender.

When resolving mac address of destination, you use arrived dgid as
sgid and use sgid as dgid because sgid contains destinations GID whom to
respond to.
Signed-off-by: NGustavo A. R. Silva <garsilva@embeddedor.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

ib_get_cached_subnet_prefix can technically fail, but the only way it
could is not possible based on the loop conditions. Check the return
value before using the variable sp to resolve a static analysis warning.

-v1:
- Fix check to !ret. Paul Moore

Fixes: 8f408ab6 ("selinux lsm IB/core: Implement LSM notification
system")
Signed-off-by: NDaniel Jurgens <danielj@mellanox.com>
Reported-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NPaul Moore <paul@paul-moore.com>
Signed-off-by: NJames Morris <james.l.morris@oracle.com>

Check the return value from get_pkey_and_subnet_prefix to prevent using
uninitialized variables.

Fixes: d291f1a6 ("IB/core: Enforce PKey security on QPs")
Signed-off-by: NDaniel Jurgens <danielj@mellanox.com>
Reported-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NPaul Moore <paul@paul-moore.com>
Signed-off-by: NJames Morris <james.l.morris@oracle.com>

The ib_uverbs_create_ah() ind ib_uverbs_modify_qp() calls receive
the port number from user input as part of its attributes and assumes
it is valid. Down on the stack, that parameter is used to access kernel
data structures.  If the value is invalid, the kernel accesses memory
it should not.  To prevent this, verify the port number before using it.

BUG: KASAN: use-after-free in ib_uverbs_create_ah+0x6d5/0x7b0
Read of size 4 at addr ffff880018d67ab8 by task syz-executor/313

BUG: KASAN: slab-out-of-bounds in modify_qp.isra.4+0x19d0/0x1ef0
Read of size 4 at addr ffff88006c40ec58 by task syz-executor/819

Fixes: 67cdb40c ("[IB] uverbs: Implement more commands")
Fixes: 189aba99 ("IB/uverbs: Extend modify_qp and support packet pacing")
Cc: <stable@vger.kernel.org> # v2.6.14+
Cc: <security@kernel.org>
Cc: Yevgeny Kliteynik <kliteyn@mellanox.com>
Cc: Tziporet Koren <tziporet@mellanox.com>
Cc: Alex Polak <alexpo@mellanox.com>
Signed-off-by: NBoris Pismenny <borisp@mellanox.com>
Signed-off-by: NLeon Romanovsky <leon@kernel.org>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Playing with IP-O-IB interface can trigger a warning message:
"ib0: Failed to modify QP to ERROR state" to be logged.
This happens when the QP is in IB_QPS_RESET state and the stack
is trying to transition it to IB_QPS_ERR state in ipoib_ib_dev_stop().

According to the IB spec, Table 91 - "QP State Transition Properties"
it looks like the transition from reset to error is valid:

Transition: Any State to Error
Required Attributes: None
Optional Attributes: None allowed
Actions: Queue processing is stopped. Work Requests pending or in
process are completed in error, when possible.

This patch allows the transition and quiets the message.
Reviewed-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NTadeusz Struk <tadeusz.struk@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Reviewed-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

It seems like a historic accident that these return unsigned char *,
and in many places that means casts are required, more often than not.

Make these functions (skb_put, __skb_put and pskb_put) return void *
and remove all the casts across the tree, adding a (u8 *) cast only
where the unsigned char pointer was used directly, all done with the
following spatch:

    @@
    expression SKB, LEN;
    typedef u8;
    identifier fn = { skb_put, __skb_put };
    @@
    - *(fn(SKB, LEN))
    + *(u8 *)fn(SKB, LEN)

    @@
    expression E, SKB, LEN;
    identifier fn = { skb_put, __skb_put };
    type T;
    @@
    - E = ((T *)(fn(SKB, LEN)))
    + E = fn(SKB, LEN)

which actually doesn't cover pskb_put since there are only three
users overall.

A handful of stragglers were converted manually, notably a macro in
drivers/isdn/i4l/isdn_bsdcomp.c and, oddly enough, one of the many
instances in net/bluetooth/hci_sock.c. In the former file, I also
had to fix one whitespace problem spatch introduced.
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Commit eea40b8f ("infiniband: call ipv6 route lookup via the stub
interface") introduced a regression in address resolution when connecting
to IPv6 destination addresses.  The old code called ip6_route_output(),
while the new code calls ipv6_stub->ipv6_dst_lookup().  The two are almost
the same, except that ipv6_dst_lookup() also calls ip6_route_get_saddr()
if the source address is in6addr_any.

This means that the test of ipv6_addr_any(&fl6.saddr) now never succeeds,
and so we never copy the source address out.  This ends up causing
rdma_resolve_addr() to fail, because without a resolved source address,
cma_acquire_dev() will fail to find an RDMA device to use.  For me, this
causes connecting to an NVMe over Fabrics target via RoCE / IPv6 to fail.

Fix this by copying out fl6.saddr if ipv6_addr_any() is true for the original
source address passed into addr6_resolve().  We can drop our call to
ipv6_dev_get_saddr() because ipv6_dst_lookup() already does that work.

Fixes: eea40b8f ("infiniband: call ipv6 route lookup via the stub interface")
Cc: <stable@vger.kernel.org> # 3.12+
Signed-off-by: NRoland Dreier <roland@purestorage.com>
Acked-by: NPaolo Abeni <pabeni@redhat.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Commit 9fdca4da (IB/SA: Split struct sa_path_rec based on IB and
ROCE specific fields) moved the service_id to be specific attribute
for IB and OPA SA Path Record, and thus wasn't assigned for RoCE.

This caused to the following kernel panic in the CMA request handler flow:

[   27.074594] BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
[   27.074731] IP: __radix_tree_lookup+0x1d/0xe0
...
[   27.075356] Workqueue: ib_cm cm_work_handler [ib_cm]
[   27.075401] task: ffff88022e3b8000 task.stack: ffffc90001298000
[   27.075449] RIP: 0010:__radix_tree_lookup+0x1d/0xe0
...
[   27.075979] Call Trace:
[   27.076015]  radix_tree_lookup+0xd/0x10
[   27.076055]  cma_ps_find+0x59/0x70 [rdma_cm]
[   27.076097]  cma_id_from_event+0xd2/0x470 [rdma_cm]
[   27.076144]  ? ib_init_ah_from_path+0x39a/0x590 [ib_core]
[   27.076193]  cma_req_handler+0x25/0x480 [rdma_cm]
[   27.076237]  cm_process_work+0x25/0x120 [ib_cm]
[   27.076280]  ? cm_get_bth_pkey.isra.62+0x3c/0xa0 [ib_cm]
[   27.076350]  cm_req_handler+0xb03/0xd40 [ib_cm]
[   27.076430]  ? sched_clock_cpu+0x11/0xb0
[   27.076478]  cm_work_handler+0x194/0x1588 [ib_cm]
[   27.076525]  process_one_work+0x160/0x410
[   27.076565]  worker_thread+0x137/0x4a0
[   27.076614]  kthread+0x112/0x150
[   27.076684]  ? max_active_store+0x60/0x60
[   27.077642]  ? kthread_park+0x90/0x90
[   27.078530]  ret_from_fork+0x2c/0x40

This patch moves it back to the common SA Path Record structure
and removes the redundant setter and getter.

Tested on Connect-IB and Connect-X4 in Infiniband and RoCE respectively.

Fixes: 9fdca4da (IB/SA: Split struct sa_path_rec based on IB ands
	ROCE specific fields)
Signed-off-by: NMajd Dibbiny <majd@mellanox.com>
Reviewed-by: NParav Pandit <parav@mellanox.com>
Signed-off-by: NLeon Romanovsky <leon@kernel.org>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Add mmap_sem lock around VMA inspection in ib_umem_odp_get().

Fixes: 0008b84e ('IB/umem: Add support to huge ODP')
Signed-off-by: NArtemy Kovalyov <artemyko@mellanox.com>
Reviewed-by: NEli Cohen <eli@mellanox.com>
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

This change will optimize kernel memory deregistration operations.
__ib_umem_release() used to call set_page_dirty_lock() against every
writable page in its memory region. Its purpose is to keep data
synced between CPU and DMA device when swapping happens after mem
deregistration ops. Now we choose not to set page dirty bit if it's
already set by kernel prior to calling __ib_umem_release(). This
reduces memory deregistration time by half or even more when we ran
application simulation test program.
Signed-off-by: NQing Huang <qing.huang@oracle.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Commit 57520751 ("IB/SA: Add OPA path record type") introduced
new local function __ib_copy_path_rec_to_user, but didn't limit its
scope. This produces the following sparse warning:

	drivers/infiniband/core/uverbs_marshall.c:99:6: warning:
	symbol '__ib_copy_path_rec_to_user' was not declared. Should it be
	static?

In addition, it used sizeof ... notations instead of sizeof(...), which
is correct in C, but a little bit misleading. Let's change it too.

Fixes: 57520751 ("IB/SA: Add OPA path record type")
Reviewed-by: NYuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>