The current QP FetchBurstMax value is 256B, which
is incorrect since a WR can exceed that value.  The
result being a partial WR fetched by hardware, and
a fatal "bad WR" error posted by the SGE.

So bump the FetchBurstMax to 512B.
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

This patch series adds a driver for a paravirtual RDMA device. The
device is developed for VMware's Virtual Machines and allows existing RDMA
applications to continue to use existing Verbs API when deployed in VMs
on ESXi. We recently did a presentation in the OFA Workshop [1] regarding
this device.

Description and RDMA Support
============================
The virtual device is exposed as a dual function PCIe device. One part
is a virtual network device (VMXNet3) which provides networking properties
like MAC, IP addresses to the RDMA part of the device. The networking
properties are used to register GIDs required by RDMA applications to
communicate.

These patches add support and the all required infrastructure for
letting applications use such a device. We support the mandatory Verbs API as
well as the base memory management extensions (Local Inv, Send with Inv and
Fast Register Work Requests). We currently support both Reliable Connected
and Unreliable Datagram QPs but do not support Shared Receive Queues
(SRQs).

Also, we support the following types of Work Requests:
 o Send/Receive (with or without Immediate Data)
 o RDMA Write (with or without Immediate Data)
 o RDMA Read
 o Local Invalidate
 o Send with Invalidate
 o Fast Register Work Requests

This version only adds support for version 1 of RoCE. We will add RoCEv2
support in a future patch. We do support registration of both MAC-based
and IP-based GIDs. I have also created a git tree for our user-level driver
[2].

Testing
=======
We have tested this internally for various types of Guest OS - Red Hat,
Centos, Ubuntu 12.04/14.04/16.04, Oracle Enterprise Linux, SLES 12
using backported versions of this driver. The tests included several
runs of the performance tests (included with OFED), Intel MPI PingPong
benchmark on OpenMPI, krping for FRWRs. Mellanox has been kind enough
to test the backported version of the driver internally on their hardware
using a VMware provided ESX build. I have also applied and tested this
with Doug's k.o/for-4.9 branch (commit 5603910b). Note, that this patch
series should be applied all together. I split out the commits so that
it may be easier to review.

PVRDMA Resources
================
[1] OFA Workshop Presentation -
https://openfabrics.org/images/eventpresos/2016presentations/102parardma.pdf

[2] Libpvrdma User-level library -
http://git.openfabrics.org/?p=~aditr/libpvrdma.git;a=summaryReviewed-by: NJorgen Hansen <jhansen@vmware.com>
Reviewed-by: NGeorge Zhang <georgezhang@vmware.com>
Reviewed-by: NAditya Sarwade <asarwade@vmware.com>
Reviewed-by: NBryan Tan <bryantan@vmware.com>
Reviewed-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NAdit Ranadive <aditr@vmware.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

If uhw->inlen is non-zero, the value of variable err is 0 if the copy
succeeds. Then, if kzalloc() or kmalloc() returns a NULL pointer, it
will return 0 to the callers. As a result, the callers cannot detect the
errors. This patch fixes the bug, assign "-ENOMEM" to err before the
NULL pointer checks, and remove the initialization of err at the
beginning.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=189031Signed-off-by: NPan Bian <bianpan2016@163.com>
Reviewed-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

In function ocrdma_mbx_create_ah_tbl(), returns the value of status on
errors. However, because status is initialized with 0, 0 will be
returned even if on error paths. This patch initialize status with
"-ENOMEM".

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=188831Signed-off-by: NPan Bian <bianpan2016@163.com>
Reviewed-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Return value of skb_linearize should be handled in function
nes_netdev_start_xmit.

Compiled in x86_64
Signed-off-by: NZhouyi Zhou <yizhouzhou@ict.ac.cn>
Reviewed-by: NYuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

In mthca_create_ah(), pci_pool_alloc() followed by memset will be
replaced by pci_pool_zalloc()
Signed-off-by: NSouptick joarder <jrdr.linux@gmail.com>
Reviewed-by: NYuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Make it clear that qp->sq.wqe_cnt is not the number of WQEs.
Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com>
Cc: Eli Cohen <eli@mellanox.com>
Acked-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

This has been detected by building the mlx5 driver with W=1.

Fixes: 1a412fb1 ('net/mlx5: Fixes: 1a412fb1 (IB/mlx5: Modify QP
commands via mlx5 ifc')
Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com>
Cc: Eli Cohen <eli@mellanox.com>
Acked-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Detected by sparse.
Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com>
Cc: Eli Cohen <eli@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

The special QP creation error path relies on offset_of(struct mlx4_ib_sqp,
qp) == 0. Remove this assumption because that makes the QP creation
code easier to understand.
Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com>
Cc: Yishai Hadas <yishaih@mellanox.com>
Reviewed-by: NLaurence Oberman <loberman@redhat.com>
Reviewed-by: NYishai Hadas <yishaih@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

The function usnic_ib_qp_grp_get_chunk only returns an ERR_PTR value or a
valid pointer, never NULL.  The same is true of get_qp_res_chunk, which
just returns the result of calling usnic_ib_qp_grp_get_chunk.  Simplify
IS_ERR_OR_NULL to IS_ERR in both cases.

The semantic patch that makes this change is as follows:
(http://coccinelle.lip6.fr/)

// <smpl>
@@
expression t,e;
@@

t = \(usnic_ib_qp_grp_get_chunk(...)\|get_qp_res_chunk(...)\)
... when != t=e
- IS_ERR_OR_NULL(t)
+ IS_ERR(t)

@@
expression t,e,e1;
@@

t = \(usnic_ib_qp_grp_get_chunk(...)\|get_qp_res_chunk(...)\)
... when != t=e
?- t ? PTR_ERR(t) : e1
+ PTR_ERR(t)
... when any
// </smpl>
Signed-off-by: NJulia Lawall <Julia.Lawall@lip6.fr>
Reviewed-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

The ethtool api {get|set}_settings is deprecated.
We move this driver to new api {get|set}_link_ksettings.
Signed-off-by: NPhilippe Reynes <tremyfr@gmail.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

We get a false-positive warning in linux-next for the mlx5 driver:

infiniband/hw/mlx5/mr.c: In function ‘mlx5_ib_reg_user_mr’:
infiniband/hw/mlx5/mr.c:1172:5: error: ‘order’ may be used uninitialized in this function [-Werror=maybe-uninitialized]
infiniband/hw/mlx5/mr.c:1161:6: note: ‘order’ was declared here
infiniband/hw/mlx5/mr.c:1173:6: error: ‘ncont’ may be used uninitialized in this function [-Werror=maybe-uninitialized]
infiniband/hw/mlx5/mr.c:1160:6: note: ‘ncont’ was declared here
infiniband/hw/mlx5/mr.c:1173:6: error: ‘page_shift’ may be used uninitialized in this function [-Werror=maybe-uninitialized]
infiniband/hw/mlx5/mr.c:1158:6: note: ‘page_shift’ was declared here
infiniband/hw/mlx5/mr.c:1143:13: error: ‘npages’ may be used uninitialized in this function [-Werror=maybe-uninitialized]
infiniband/hw/mlx5/mr.c:1159:6: note: ‘npages’ was declared here

I had a trivial workaround for gcc-5 or higher, but that didn't work
on gcc-4.9 unfortunately.

The only way I found to avoid the warnings for gcc-4.9, short of
initializing each of the arguments first was to change the calling
conventions to separate the error code from the umem pointer. This
avoids casting the error codes from one pointer to another incompatible
pointer, and lets gcc figure out when that the data is actually valid
whenever we return successfully.
Acked-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Remove pointless NULL check for 'wr' in qedr_post_send().
Signed-off-by: NWei Yongjun <weiyongjun1@huawei.com>
Acked-by: NRam Amrani <Ram.Amrani@cavium.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Using list_move_tail() instead of list_del() + list_add_tail().
Signed-off-by: NWei Yongjun <weiyongjun1@huawei.com>
Reviewed-by: NLeon Romanovsky <leonro@mellanox.com>
Acked-by: NRam Amrani <Ram.Amrani@cavium.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

'qp' is malloced in qedr_create_qp() and should be freed before leaving
from the error handling cases, otherwise it will cause memory leak.
Signed-off-by: NWei Yongjun <weiyongjun1@huawei.com>
Acked-by: NRam Amrani <Ram.Amrani@cavium.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Currently, if pd is null then we hit a null pointer derference
on accessing pd->pd_id.  Instead of just printing an error message
we should also return -EINVAL immediately.
Signed-off-by: NColin Ian King <colin.king@canonical.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

and rename class version define to indicate SM rather than SMP or SMI
Signed-off-by: NHal Rosenstock <hal@mellanox.com>
Reviewed-by: NIra Weiny <ira.weiny@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

- Add MODIFY_QP_EX CMD to extend modify_qp.
- Rate limit will be updated in the following state transactions: RTR2RTS,
  RTS2RTS. The limit will be removed when SQ is in RST and ERR state.
Signed-off-by: NBodong Wang <bodong@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>

Enable mlx5 based hardware to report packet pacing capabilities
from kernel to user space. Packet pacing allows to limit the rate to any
number between the maximum and minimum, based on user settings.

The capabilities are exposed to user space through query_device by uhw.
The following capabilities are reported:

1. The maximum and minimum rate limit in kbps supported by packet pacing.
2. Bitmap showing which QP types are supported by packet pacing operation.
Signed-off-by: NBodong Wang <bodong@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>

On some environments, such as certain SRIOV VF configurations, RoCE is
not supported for mlx5 Ethernet ports. Currently, the driver will not
open IB device on that port.

This is problematic, since we do want user-space RAW Ethernet (RAW_PACKET
QPs) functionality to remain in place. For that end, enhance the relevant
driver flows such that we do create a device instance in that case.
Signed-off-by: NOr Gerlitz <ogerlitz@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>

This is a pre-step towards having mlx5 IB device also over Eth ports where
RoCE is not supported. We change the roce enable/disable and roce_lag
init/fini function names to have _eth instead of _roce.

This patch doesn't change any functionality.
Signed-off-by: NOr Gerlitz <ogerlitz@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>

Refactor the netdev notifier registration into a small helper function.

This is a pre-step towards having mlx5 IB device over an Ethernet port
which doesn't support RoCE. Also, renamed the de-registration helper
and the new helper as netdev notifier and not roce, to make it clear
this is not only used with roce.

This patch doesn't change any functionality.
Signed-off-by: NOr Gerlitz <ogerlitz@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>

The fast_registration length is used to convey length for memory
registrations through UMR which can be of any size up to 2^64.

Change the length type to be u64.

Fixes: 968e78dd ('IB/mlx5: Enhance UMR support to allow partial page table update')
Signed-off-by: NMaor Gottlieb <maorg@mellanox.com>
Signed-off-by: NLeon Romanovsky <leon@kernel.org>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

When enabling many VFs, the total amount of DMA mappings increase
significantly. This causes DMA allocations to take a lot of time
since they are serialized in the kernel.

As a result the driver enters into fatal condition due to
timeout and the system hangs. To recover from this we disable
MR cache for VFs.

PFs will still have a full cache and VFs cache can be manipulated
as usual after driver load.

Fixes: e126ba97 ('mlx5: Add driver for Mellanox Connect-IB adapters')
Signed-off-by: NEli Cohen <eli@mellanox.com>
Signed-off-by: NMaor Gottlieb <maorg@mellanox.com>
Signed-off-by: NLeon Romanovsky <leon@kernel.org>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Move the SRQ type assignment to be before actually using it
in create_srq_user() and in create_srq_kernel() functions.

Fixes: af1ba291 ('{net, IB}/mlx5: Refactor internal SRQ API')
Signed-off-by: NMaor Gottlieb <maorg@mellanox.com>
Reviewed-by: NMajd Dibbiny <majd@mellanox.com>
Signed-off-by: NLeon Romanovsky <leon@kernel.org>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

For non-special QPs, the port value becomes non-zero only at the
RESET-to-INIT transition. If the QP has not undergone that transition,
its port number value is still zero.

If such a QP is destroyed before being moved out of the RESET state,
subtracting one from the qp port number results in a negative value.
Using that negative value as an index into the qp1_proxy array
results in an out-of-bounds array reference.

Fix this by testing that the QP type is one that uses qp1_proxy before
using the port number. For special QPs of all types, the port number is
specified at QP creation time.

Fixes: 9433c188 ("IB/mlx4: Invoke UPDATE_QP for proxy QP1 on MAC changes")
Signed-off-by: NJack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: NLeon Romanovsky <leon@kernel.org>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Advertise that create_ah and destroy_ah verbs are accessible from
uverbs interface.
Signed-off-by: NMoni Shoua <monis@mellanox.com>
Reviewed-by: NYishai Hadas <yishaih@mellanox.com>
Signed-off-by: NLeon Romanovsky <leon@kernel.org>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Resolving a MAC address for a given IP address in userspace is inefficient.
This patch lets mlx5 user driver using the kernel driver to resolve the mac
and get the answer in the private section of the response.
Signed-off-by: NMoni Shoua <monis@mellanox.com>
Reviewed-by: NYishai Hadas <yishaih@mellanox.com>
Signed-off-by: NLeon Romanovsky <leon@kernel.org>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Add struct ib_udata to the signature of create_ah callback that is
implemented by IB device drivers. This allows HW drivers to return extra
data to the userspace library.
This patch prepares the ground for mlx5 driver to resolve destination
mac address for a given GID and return it to userspace.
This patch was previously submitted by Knut Omang as a part of the
patch set to support Oracle's Infiniband HCA (SIF).
Signed-off-by: NKnut Omang <knut.omang@oracle.com>
Signed-off-by: NMoni Shoua <monis@mellanox.com>
Reviewed-by: NYishai Hadas <yishaih@mellanox.com>
Signed-off-by: NLeon Romanovsky <leon@kernel.org>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

To make mlx5 user driver aware of whether kernel driver returns dmac
in user data response add a new flag that will be returned back to
user-space through alloc_ucontext.
Signed-off-by: NMoni Shoua <monis@mellanox.com>
Reviewed-by: NYishai Hadas <yishaih@mellanox.com>
Signed-off-by: NLeon Romanovsky <leon@kernel.org>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Add support to match packet fields which are tunneled,
i.e. support matching the header of the inner packet which is the result of
or bit operation of the original header and the IB_FLOW_SPEC_INNER type.

The combination of IB_FLOW_SPEC_INNER | IB_FLOW_SPEC_VXLAN_TUNNEL is not
needed to be checked, because the IB core has this check already.
Signed-off-by: NMoses Reuben <mosesr@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>

Add support to receive specific Vxlan packet in ConnectX-4.
Signed-off-by: NMoses Reuben <mosesr@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>

CQE compressing reduces PCI overhead by coalescing and compressing
multiple CQEs into a single merged CQE. Successful compressing
improves message rate especially for small packet traffic.

CQE compressing is supported for all 64B CQE formats (with certain
limitations) generated by RQ/Responder or by SQ/Requestor.
Signed-off-by: NBodong Wang <bodong@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>

The capabilities include:
- Max number of compressed and aggregated CQEs in a single session,
  while zero means unsupported.
- For Responder, there are two formats of mini CQE: mini CQE with Rx
  hash and mini CQE with checksum. They're mutual exclusive.
Signed-off-by: NBodong Wang <bodong@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>

The capabilities whether hardware support multi packet WQE or not is
exposed to user space through query_device by uhw.
Signed-off-by: NBodong Wang <bodong@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>

Before reading GRH attributes, need to make sure AH contains GRH,
and in addition, initialize GID type.

Fixes: dbf727de ('IB/core: Use GID table in AH creation and dmac resolution')
Signed-off-by: NEran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: NDaniel Jurgens <danielj@mellanox.com>
Reviewed-by: NMark Bloch <markb@mellanox.com>
Signed-off-by: NLeon Romanovsky <leon@kernel.org>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

According to the firmware spec, FLOW_STEERING_IB_UC_QP_RANGE command is
supported only if dmfs_ipoib bit is set.

If it isn't set we want to ensure allocating NET_IF QPs fail. We do so
by filling out the allocation bitmap. By thus, the NET_IF QPs allocating
function won't find any free QP and will fail.

Fixes: c1c98501 ('IB/mlx4: Add support for steerable IB UD QPs')
Signed-off-by: NEran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: NDaniel Jurgens <danielj@mellanox.com>
Reviewed-by: NMark Bloch <markb@mellanox.com>
Signed-off-by: NLeon Romanovsky <leon@kernel.org>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Some resources are incorrectly organized and at odds with
HW capabilities. Specifically, ILQ, IEQ, QPs, MSS, QOS
and statistics belong in a VSI.
Signed-off-by: NFaisal Latif <faisal.latif@intel.com>
Signed-off-by: NMustafa Ismail <mustafa.ismail@intel.com>
Signed-off-by: NHenry Orosco <henry.orosco@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

In i40iw_ieq_handle_partial() the check for !status is incorrect.
Signed-off-by: NMustafa Ismail <mustafa.ismail@intel.com>
Signed-off-by: NHenry Orosco <henry.orosco@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>