mlx5 devices (Connect-IB, ConnectX-4, ConnectX-4-LX) has a limitation
where rdma read work queue entries cannot exceed 512 bytes.
A rdma_read wqe needs to fit in 512 bytes:
- wqe control segment (16 bytes)
- rdma segment (16 bytes)
- scatter elements (16 bytes each)

So max_sge_rd should be: (512 - 16 - 16) / 16 = 30.

Cc: linux-stable@vger.kernel.org
Reported-by: NChristoph Hellwig <hch@lst.de>
Tested-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NSagi Grimberg <sagig@grimberg.me>
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

For set/query MTU port firmware commands the MTU field
is 16 bits, here I changed all the "int mtu" parameters
of the functions wrapping those firmware commands to be u16.
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The previous patch that added a couple of callback functions put
the declarations inside of an #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING,
which causes the build to fail if that option is disabled:

drivers/infiniband/hw/mlx5/main.c: In function 'mlx5_ib_add':
drivers/infiniband/hw/mlx5/main.c:2358:31: error: 'mlx5_ib_get_vf_config' undeclared (first use in this function)

This moves the four declarations below the #ifdef section so they
are always available.
Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Fixes: eff901d3 ("IB/mlx5: Implement callbacks for manipulating VFs")
Reviewed-by: NLeon Romanovsky <leonro@mellanox.com>
Reviewed-by: NEli Cohen <eli@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Implement the IB defined callbacks used to manipulate the policy for the
link state, set GUIDs or get statistics information. This functionality
is added into a new file that will be used to add any SRIOV related
functionality to the mlx5 IB layer.

The following callbacks have been added:

mlx5_ib_get_vf_config
mlx5_ib_set_vf_link_state
mlx5_ib_get_vf_stats
mlx5_ib_set_vf_guid

In addition, publish whether this device is based on a virtual function.

In mlx5 supported devices, virtual functions are implemented as vHCAs.
vHCAs have their own QP number space so it is possible that two vHCAs
will use a QP with the same number at the same time.
Signed-off-by: NEli Cohen <eli@mellanox.com>
Reviewed-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Add a vf parameter to mlx5_core_query_vport_counter so we can call it to
query counters of virtual functions. Also update current users of the
API.

PFs may call mlx5_core_query_vport_counter with other_vport set to
indicate that they are querying a virtual function. The virtual
function to be queried is given by the vf parameter. Virtual function
numbering is zero based so the first VF is 0 and so on. When a PF
queries its own function, the other_vport parameter is cleared.
Signed-off-by: NEli Cohen <eli@mellanox.com>
Reviewed-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Fix the condition that dictates when MAD_IFC should be used. According
to firmware specifications, MAD_IFC commands must be used only if the
ib_virt capability is off.
Signed-off-by: NEli Cohen <eli@mellanox.com>
Reviewed-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Each bypass flow steering priority will be split into two priorities:
1. Priority for don't trap rules.
2. Priority for normal rules.

When user creates a flow using IB_FLOW_ATTR_FLAGS_DONT_TRAP flag, the
driver creates two flow rules, one used for receiving the traffic and
the other one for forwarding the packet to continue matching in lower
or equal priorities.
Signed-off-by: NMaor Gottlieb <maorg@mellanox.com>
Reviewed-by: NMatan Barak <matanb@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Allocate proper context for arbitrary scatterlist registration
If ib_alloc_mr is called with IB_MR_MAP_ARB_SG, the driver
allocate a private klm list instead of a private page list.
Set the UMR wqe correctly when posting the fast registration.

Also, expose device cap IB_DEVICE_MAP_ARB_SG according to the
device id (until we have a FW bit that correctly exposes it).
Signed-off-by: NSagi Grimberg <sagig@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

While documentation indicates that the number of translation
entries per memory key is unlimited, in practice, we can
only fit a finite amount of translation entries in a single
registration wqe (which is log_max_klm_list_size).
Signed-off-by: NSagi Grimberg <sagig@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

These three related functions can't agree whether to put the
umrwr on the stack dirty and then memset it, or to initialize
it on the stack.  Make them all agree.
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Simplifies the code, and makes it more fair vs other users by using a
softirq for polling.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NHaggai Eran <haggaie@mellanox.com>
Reviewed-by: NSagi Grimberg <sagig@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Currently, the inlen field of the vendor's part of the command
doesn't match the command buffer. This happens because the inlen
accommodates ib_uverbs_cmd_hdr which is deducted from the in buffer.
This is problematic since the vendor function could be called either
from the legacy verb (where the input length mismatches the actual
length) or by the extended verb (where the length matches). The vendor
has no idea which function calls it and therefore has no way to know
how the length variable should be treated.

Fixing this by aligning the inlen to the correct length.

All vendor drivers either assumed that inlen >= sizeof(vendor_uhw_cmd)
or just failed wrongly (mlx5) and fixed in this patch.

Fixes: cfb5e088 ('IB/mlx5: Add CQE version 1 support to user QPs and SRQs')
Signed-off-by: NMajd Dibbiny <majd@mellanox.com>
Reviewed-by: NMatan Barak <matanb@mellanox.com>
Reviewed-by: NHaggai Eran <haggaie@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Normal SRQs, unlike XRC SRQs, don't have user-index, therefore
avoid verifying it and using it.

Fixes: cfb5e088 ('IB/mlx5: Add CQE version 1 support to user QPs and SRQs')
Signed-off-by: NMajd Dibbiny <majd@mellanox.com>
Reviewed-by: NMatan Barak <matanb@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

This patch adds user-space support for memory windows allocation and
deallocation. It also exposes the supported types via
query_device_caps verb.
Signed-off-by: NMatan Barak <matanb@mellanox.com>
Reviewed-by: NYishai Hadas <yishaih@mellanox.com>
Tested-by: NMax Gurtovoy <maxg@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Mlx5's mkey mechanism is also used for memory windows.
The current code base uses MR (memory region) naming, which is
inaccurate. Changing MR to mkey in order to represent its different
usages more accurately.
Signed-off-by: NMatan Barak <matanb@mellanox.com>
Reviewed-by: NYishai Hadas <yishaih@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

This patch adds support for re-registration of memory regions in MLX5.
The functionality is basically the same as deregister followed by
register, but attempts to reuse the existing resources as much as
possible.
Original memory keys are kept if possible, saving the need to
communicate new ones to remote peers.
Signed-off-by: NNoa Osherovich <noaos@mellanox.com>
Reviewed-by: NMatan Barak <matanb@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

In order to add re-registration of memory region, some logic was
extracted to separate functions:
- ODP related logic.
- Some of the UMR WQE preparation code.
- DMA mapping.
- Umem creation.
- Creating MKey using FW interface.
- MR fields assignments after successful creation.
Signed-off-by: NNoa Osherovich <noaos@mellanox.com>
Reviewed-by: NMatan Barak <matanb@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Now that the transmission of GSI MADs is done with the special transmission
QPs, eliminate the send buffers in the GSI receive QP.
Reviewed-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NHaggai Eran <haggaie@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Pick the QP to use according to the wr.ud.pkey_index field in the work
request. If the QP doesn't exist, it means the P_Key is zero and the packet
would have been dropped, so just generate a completion and move on.
Reviewed-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NHaggai Eran <haggaie@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

The emulated GSI QP's send completions are generated by multiple hardware
QPs, so their completions could arrive out of order with respect to the
order their work request were submitted.

Reorder the completions by keeping a list of the posted work request and
their completions. A newly received completion from the hardware updates
the list and marks its work request as completed. However, the completions
are only reported to the client according to the list order.

In order to support that, create a new private CQ to handle the hardware
completions.
Signed-off-by: NHaggai Eran <haggaie@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

The GSI QP emulation requires also emulating completions for transmitted
MADs. The CQ on which these completions are generated can also be used by
the hardware, and the MAD layer is free to use any CQ of the device for the
GSI QP.

Add a method for generating software completions to each mlx5 CQ. Software
completions are polled first, and generate calls to the completion handler
callback if necessary.
Reviewed-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NHaggai Eran <haggaie@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Whenever the P_Key table is changed, we create the required GSI
transmission QPs on-demand.
Reviewed-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NHaggai Eran <haggaie@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

In order to send GSI MADs on different P_Keys, mlx5 needs different QPs to
be created, each with a different P_Key set when the QP is modified to the
INIT state.

Create QPs for each non-zero P_Key in the P_Key table.
Signed-off-by: NHaggai Eran <haggaie@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

mlx5 creates special GSI QPs that has limited ability to control the P_Key
of transmitted packets. The sent P_Key is taken from the QP object,
similarly to what happens with regular UD QPs.

Create a software wrapper around GSI QPs that with the following patches
will be able to emulate the functionality of a GSI QP including control of
the P_Key per work request.
Reviewed-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NHaggai Eran <haggaie@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Add debugging prints to the modify QP verb to help understand the cause a
returned error.
Reviewed-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NHaggai Eran <haggaie@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

In order to create multiple GSI QPs, we need to set the source QP number to
one on all these QPs. Add the necessary definitions and infrastructure to
do that.
Reviewed-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NHaggai Eran <haggaie@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

The driver checks the csum from the HW when completion arrived and marks
it in the wc->wc_flags field for the ulp drivers.
These is for packets from type IB_WC_RECV only.
Signed-off-by: NErez Shitrit <erezsh@mellanox.com>
Signed-off-by: NEran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

In order to support LSO and CSUM in the TX flow the driver does the
following:
* LSO bit for the enum mlx5_ib_qp_flags was added, indicates QP that
  supports LSO offloads.
* Enables the special offload when the QP is created, and enable the
  special work request id (IB_WR_LSO) when comes.
* Calculates the size of the WQE according to the new WQE format that
  support these offloads.
* Handles the new WQE format when arrived, sets the relevant
  fields, and copies the needed data.
Signed-off-by: NErez Shitrit <erezsh@mellanox.com>
Signed-off-by: NEran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Modify mlx5_ib_process_mad to use PPCNT and query_vport commands
instead of MAD_IFC, as MAD_IFC is deprecated on new firmware
versions (and doesn't support RoCE anyway).

Traffic counters exist in both 32-bit and 64-bit forms.
Declaring support of extended coutners results in traffic counters
to be read in their 64-bit form only via the query_vport command.
Error counters exist only in 32-bit form and read via PPCNT command.

This commit also adds counters support in RoCE.
Signed-off-by: NMeny Yossefi <menyy@mellanox.com>
Signed-off-by: NMajd Dibbiny <majd@mellanox.com>
Reviewed-by: NMatan Barak <matanb@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

All the device physical port access functions are implemented in the
port.c file.
We just extract the exposure of these functions from driver.h into a
dedicated header file called port.h.
Signed-off-by: NAchiad Shochat <achiad@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fix the RC QPs send queue overhead computation to take into account
two additional segments in the WQE which are needed for registration
operations.

The ATOMIC and UMR segments can't coexist together, so chose maximum out
of them.

The commit 9e65dc37 ("IB/mlx5: Fix RC transport send queue overhead
computation") was intended to update RC transport as commit messages
states, but added the code to UC transport.

Fixes: 9e65dc37 ("IB/mlx5: Fix RC transport send queue overhead computation")
Signed-off-by: NKamal Heib <kamalh@mellanox.com>
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Reviewed-by: NSagi Grimberg <sagig@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

MLX5_GET64 was used on end_padding_mode, which is a 2-bit field.
This is wrong as the calculated offset is incorrect. Using MLX5_GET
instead of MLX5_GET64 to fix that.

Fixes: 0fb2ed66 ('IB/mlx5: Add create and destroy functionality
                     for Raw Packet QP')
Signed-off-by: NMaor Gottlieb <maorg@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

When a Raw Ethernet QP is created, a NULL pointer PD could be used.
Fixing that by only using the PD after validating it's valid.
smatch also reported this error:
drivers/infiniband/hw/mlx5/qp.c:1629 mlx5_ib_create_qp()
	 error: we previously assumed 'pd' could be null (see line 1616)

Fixes: 0fb2ed66 ('IB/mlx5: Add create and destroy functionality for Raw Packet QP')
Signed-off-by: NMajd Dibbiny <majd@mellanox.com>
Reported-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Older libraries that don't have all the new req_v2 fields
should be able to work as well. Today, if the library uses v2, it
will fail to allocate context since the size of reqlen is smaller
than the req_v2 size.

Fix the validation to be with the original req_v2 size and not
the current.

Fixes: f72300c5 ('IB/mlx5: Expose CQE version to user-space')
Signed-off-by: NMajd Dibbiny <majd@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

The mlx5_ib driver supports the extended create_cq and create_qp user
verbs. In the current mechanism, a vendor supporting an extended uverb
should set the appropriate bit in the uverbs_ex_cmd_mask field.
Adding the actual support by setting the required bits in order to
support features like completion time-stamping and cross-channel.

Fixes: 972ecb82 ('IB/mlx5: Add create_cq extended command')
Fixes: ddf9529b ('IB/core: Allow setting create flags in QP init
                      attribute')
Signed-off-by: NMatan Barak <matanb@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

The create_cq() can receive creation flags which were used
differently by two commits which added create_cq extended
command and cross-channel. The merged code caused to not
accept any flags at all.

This patch unifies the check into one function and one return
error code.

Fixes: 972ecb82 ("IB/mlx5: Add create_cq extended command")
Fixes: 051f2630 ("IB/mlx5: Add driver cross-channel support")
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Added Raw Packet QP modify functionality which will enable user
space consumers to use it.

Since Raw Packet QP is built of SQ and RQ sub-objects, therefore
Raw Packet QP state changes are implemented by changing the state
of the sub-objects.
Signed-off-by: NMajd Dibbiny <majd@mellanox.com>
Reviewed-by: NMatan Barak <matanb@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

When modifying a QP, the desired operation was determined in
the mlx5_core using a transition table that takes the current
state, the final state, and returns the desired operation.

Since this logic will be used for Raw Packet QP, move the
operation table to the mlx5_ib.
Signed-off-by: NMajd Dibbiny <majd@mellanox.com>
Reviewed-by: NMatan Barak <matanb@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

When the user changes the Address Vector(AV) in the modify QP, he
provides an SL. This SL should be translated to Ethernet Priority
by taking the 3 LSB bits, and modify the QP's TIS according to this
Ethernet priority.
Signed-off-by: NMajd Dibbiny <majd@mellanox.com>
Reviewed-by: NMatan Barak <matanb@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Since Raw Packet QP is composed of RQ and SQ, the IB QP's
state is derived from the sub-objects. Therefore we need
to query each one of the sub-objects, and decide on the
IB QP's state.
Signed-off-by: NMajd Dibbiny <majd@mellanox.com>
Reviewed-by: NMatan Barak <matanb@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>