There are systems platform information management interfaces (such as
HOST2BMC) for which we cannot disable local loopback multicast traffic.

Separate disable_local_lb_mc and disable_local_lb_uc capability bits so
driver will not disable multicast loopback traffic if not supported.
(It is expected that Firmware will not set disable_local_lb_mc if
HOST2BMC is running for example.)

Function mlx5_nic_vport_update_local_lb will do best effort to
disable/enable UC/MC loopback traffic and return success only in case it
succeeded to changed all allowed by Firmware.

Adapt mlx5_ib and mlx5e to support the new cap bits.

Fixes: 2c43c5a0 ("net/mlx5e: Enable local loopback in loopback selftest")
Fixes: c85023e1 ("IB/mlx5: Add raw ethernet local loopback support")
Fixes: bded747b ("net/mlx5: Add raw ethernet local loopback firmware command")
Signed-off-by: NEran Ben Elisha <eranbe@mellanox.com>
Cc: kernel-team@fb.com
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

Before the offending commit, mlx5 core did the IRQ affinity itself,
and it seems that the new generic code have some drawbacks and one
of them is the lack for user ability to modify irq affinity after
the initial affinity values got assigned.

The issue is still being discussed and a solution in the new generic code
is required, until then we need to revert this patch.

This fixes the following issue:
echo <new affinity> > /proc/irq/<x>/smp_affinity
fails with  -EIO

This reverts commit a435393a.
Note: kept mlx5_get_vector_affinity in include/linux/mlx5/driver.h since
it is used in mlx5_ib driver.

Fixes: a435393a ("mlx5: move affinity hints assignments to generic code")
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Jes Sorensen <jsorensen@fb.com>
Reported-by: NJes Sorensen <jsorensen@fb.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

After the panic teardown firmware command, health_care detects the error
in PCI bus and calls the mlx5_pci_err_detected. This health_care flow is
no longer needed because the panic teardown firmware command will bring
down the PCI bus communication with the HCA.

The solution is to cancel the health care timer and its pending
workqueue request before sending panic teardown firmware command.

Kernel trace:
mlx5_core 0033:01:00.0: Shutdown was called
mlx5_core 0033:01:00.0: health_care:154:(pid 9304): handling bad device here
mlx5_core 0033:01:00.0: mlx5_handle_bad_state:114:(pid 9304): NIC state 1
mlx5_core 0033:01:00.0: mlx5_pci_err_detected was called
mlx5_core 0033:01:00.0: mlx5_enter_error_state:96:(pid 9304): start
mlx5_3:mlx5_ib_event:3061:(pid 9304): warning: event on port 0
mlx5_core 0033:01:00.0: mlx5_enter_error_state:104:(pid 9304): end
Unable to handle kernel paging request for data at address 0x0000003f
Faulting instruction address: 0xc0080000434b8c80

Fixes: 8812c24d ('net/mlx5: Add fast unload support in shutdown flow')
Signed-off-by: NHuy Nguyen <huyn@mellanox.com>
Reviewed-by: NMoshe Shemesh <moshe@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

PTP code is moved to core section of mlx5 driver in order to share
it between ethernet and infiniband. This movement involves the following
changes:
- Change mlx5e_ prefix to be mlx5_
- Add clock structs to Core
- Add clock object to mlx5_core_dev
- Call Init/Uninit clock from core init/cleanup
- Rename mlx5e_tstamp to be mlx5_clock
Signed-off-by: NFeras Daoud <ferasda@mellanox.com>
Signed-off-by: NEitan Rabin <rabin@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

MLX5_INTERFACE_STATE_SHUTDOWN is not used in the code.

Fixes: 5fc7197d ("net/mlx5: Add pci shutdown callback")
Signed-off-by: NHuy Nguyen <huyn@mellanox.com>
Reviewed-by: NDaniel Jurgens <danielj@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

There is an issue where the firmware fails during mlx5_load_one,
the health_care timer detects the issue and schedules a health_care call.
Then the mlx5_load_one detects the issue, cleans up and quits. Then
the health_care starts and calls mlx5_unload_one to clean up the resources
that no longer exist and causes kernel panic.

The root cause is that the bit MLX5_INTERFACE_STATE_DOWN is not set
after mlx5_load_one fails. The solution is removing the bit
MLX5_INTERFACE_STATE_DOWN and quit mlx5_unload_one if the
bit MLX5_INTERFACE_STATE_UP is not set. The bit MLX5_INTERFACE_STATE_DOWN
is redundant and we can use MLX5_INTERFACE_STATE_UP instead.

Fixes: 5fc7197d ("net/mlx5: Add pci shutdown callback")
Signed-off-by: NHuy Nguyen <huyn@mellanox.com>
Reviewed-by: NDaniel Jurgens <danielj@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

To fix these checkpatch complaints:

CHECK: Please don't use multiple blank lines
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

The driver core clears the driver data to NULL after device_release
or on probe failure. Thus, it is not necessary to manually clear the
device driver data to NULL.

Cc: Joe Jin <joe.jin@oracle.com>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Signed-off-by: NZhu Yanjun <yanjun.zhu@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

generic api takes care of spreading affinity similar to
what mlx5 open coded (and even handles better asymmetric
configurations). Ask the generic API to spread affinity
for us, and feed him pre_vectors that do not participate
in affinity settings (which is an improvement to what we
had before).

The affinity assignments should match what mlx5 tried to
do earlier but now we do not set affinity to async, cmd
and pages dedicated vectors.

Also, remove mlx5e_get_cpu and introduce mlx5e_get_node
(used for allocation purposes) and mlx5_get_vector_affinity
(for indirection table construction) as they provide the needed
information. Luckily, we have generic helpers to get cpumask
and node given a irq vector. mlx5_get_vector_affinity will
be used by mlx5_ib in a subsequent patch.
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Acked-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Now that we have a generic code to allocate an array
of irq vectors and even correctly spread their affinity,
correctly handle cpu hotplug events and more, were much
better off using it.
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Acked-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

When mlx5_ib registers itself to mlx5_core as an interface, it will
call mlx5_add_device which will call mlx5_ib interface add callback,
in case the latter successfully returns, only then mlx5_core will add
it to the interface list and async events will be forwarded to mlx5_ib.
Between mlx5_ib interface add callback and mlx5_core adding the mlx5_ib
interface to its devices list, arriving mlx5_core events can be missed
by the new mlx5_ib registering interface.

In other words:
thread 1: mlx5_ib: mlx5_register_interface(dev)
thread 1: mlx5_core: mlx5_add_device(dev)
thread 1: mlx5_core: ctx = dev->add => (mlx5_ib)->mlx5_ib_add
thread 2: mlx5_core_event: **new event arrives, forward to dev_list
thread 1: mlx5_core: add_ctx_to_dev_list(ctx)
/* previous event was missed by the new interface.*/
It is ok to miss events before dev->add (mlx5_ib)->mlx5_ib_add_device
but not after.

We fix this race by accumulating the events that come between the
ib_register_device (inside mlx5_add_device->(dev->add)) till the adding
to the list completes and fire them to the new registering interface
after that.

Fixes: f1ee87fe ("net/mlx5: Organize device list API in one place")
Signed-off-by: NErez Shitrit <erezsh@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

Allow to selectively build the driver with or without sriov eswitch, VF
representors and TC offloads.

Also remove the need of two ndo ops structures (sriov & basic)
and keep only one unified ndo ops, compile out VF SRIOV ndos when not
needed (MLX5_ESWITCH=n), and for VF netdev calling those ndos will result
in returning -EPERM.
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Reviewed-by: NOr Gerlitz <ogerlitz@mellanox.com>
Cc: Jes Sorensen <jsorensen@fb.com>
Cc: kernel-team@fb.com

Multi-Physical Function Switch (MPFs) is required for when multi-PF
configuration is enabled to allow passing user configured unicast MAC
addresses to the requesting PF.

Before this patch eswitch.c used to manage the HW MPFS l2 table,
E-Switch always (regardless of sriov) enabled vport(0) (NIC PF) vport's
contexts update on unicast mac address list changes, to populate the PF's
MPFS L2 table accordingly.

In downstream patch we would like to allow compiling the driver without
E-Switch functionalities, for that we move MPFS l2 table logic out
of eswitch.c into its own file, and provide Kconfig flag (MLX5_MPFS) to
allow compiling out MPFS for those who don't want Multi-PF support.

NIC PF netdevice will now directly update MPFS l2 table via the new MPFS
API. VF netdevice has no access to MPFS L2 table, so E-Switch will remain
responsible of updating its MPFS l2 table on behalf of its VFs.

Due to this change we also don't require enabling vport(0) (PF vport)
unicast mac changes events anymore, for when SRIOV is not enabled.
Which means E-Switch is now activated only on SRIOV activation, and not
required otherwise.
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Cc: Jes Sorensen <jsorensen@fb.com>
Cc: kernel-team@fb.com

Currently, unicast/multicast loopback raw ethernet
(non-RDMA) packets are sent back to the vport.
A unicast loopback packet is the packet with destination
MAC address the same as the source MAC address.
For multicast, the destination MAC address is in the
vport's multicast filter list.

Moreover, the local loopback is not needed if
there is one or none user space context.

After this patch, the raw ethernet unicast and multicast
local loopback are disabled by default. When there is more
than one user space context, the local loopback is enabled.

Note that when local loopback is disabled, raw ethernet
packets are not looped back to the vport and are forwarded
to the next routing level (eswitch, or multihost switch,
or out to the wire depending on the configuration).
Signed-off-by: NHuy Nguyen <huyn@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>

Add routines for manipulating the hardware IPSec SA database (SADB).

In Innova IPSec, a Security Association (SA) is added or deleted
via a command message over the SBU connection.
The HW then sends a response message over the same connection.

Add implementation for Innova IPSec (FPGA-based) hardware.

These routines will be used by the IPSec offload support in a later patch
However they may also be used by others such as RDMA and RoCE IPSec.

mlx5/accel is a middle acceleration layer to allow mlx5e and other ULPs
to work directly with mlx5_core rather than Innova FPGA or other mlx5
acceleration providers.

In this patchset we add Innova IPSec support and mlx5/accel delegates
IPSec offloads to Innova routines.

In the future, when IPSec/TLS or any other acceleration gets integrated
into ConnectX chip, mlx5/accel layer will provide the integrated
acceleration, rather than the Innova one.
Signed-off-by: NIlan Tayari <ilant@mellanox.com>
Signed-off-by: NBoris Pismenny <borisp@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

The FPGA init and cleanup routines should be called just once per
device.
Move them to the init_once and cleanup_once routines.
Signed-off-by: NIlan Tayari <ilant@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

Reserved GIDs are entries in the GID table in use by the mlx5_core
and its submodules (e.g. FPGA, SRIOV, E-Swtich, netdev).
The entries are reserved at the high indexes of the GID table.

A mlx5 submodule may reserve a certain amount of GIDs for its own use
during the load sequence by calling mlx5_core_reserve_gids, and must
also take care to un-reserve these GIDs when it closes.
Reservation is only allowed during the load sequence and before any
interfaces (e.g. mlx5_ib or mlx5_en) are up.

After reservation, a submodule may call mlx5_core_reserved_gid_alloc/
free to allocate entries from the reserved GIDs pool.

Reserve a GID table entry for every supported FPGA QP.

A later patch in the patchset will remove them from being reported to
IB core.
Another such patch will make use of these for FPGA QPs in Innova NIC.

Added lib/mlx5.h to serve as a library for mlx5 submodlues, and to
expose only public mlx5 API, more mlx5 library files will be added in
future submissions.
Signed-off-by: NIlan Tayari <ilant@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

In load_one, the interface flags are changed from down to up,
only after initializing the interfaces.
In unload_one, the flags are changed from up to down before the
interface cleanup.

Change the cleanup order to be opposite to initialization order.

This fixes flag consistency between init and cleanup.
Signed-off-by: NIlan Tayari <ilant@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

Draining the health workqueue will ignore future health works including
the one that report hardware failure and thus we can't enter error state
Instead cancel the recovery flow and make sure only recovery flow won't
be scheduled.

Fixes: 5e44fca5 ('net/mlx5: Only cancel recovery work when cleaning up device')
Signed-off-by: NMohamad Haj Yahia <mohamad@mellanox.com>
Signed-off-by: NMoshe Shemesh <moshe@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

When wait for firmware init fails, previous code would mistakenly
return success and cause inconsistency in the driver state.

Fixes: 6c780a02 ("net/mlx5: Wait for FW readiness before initializing command interface")
Signed-off-by: NGal Pressman <galp@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

Use Mellanox device ID definitions in the driver's mlx5 ID table so tools
such as 'grep' and 'cscope' can be used to help find correlated material
(such as INTx Masking quirks: d76d2fe0 PCI: Convert Mellanox broken
INTx quirks to be for listed devices only).

No functional change intended.
Signed-off-by: NMyron Stowe <myron.stowe@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Adding a support to flush all HW resources with one FW command and
skip all the heavy unload flows of the driver on kernel shutdown.
There's no need to free all the SW context since a new fresh kernel
will be loaded afterwards.

Regarding the FW resources, they should be closed, otherwise we will
have leakage in the FW. To accelerate this flow, we execute one command
in the beginning that tells the FW that the driver isn't going to close
any of the FW resources and asks the FW to clean up everything.
Once the commands complete, it's safe to close the PCI resources and
finish the routine.
Signed-off-by: NMajd Dibbiny <majd@mellanox.com>
Signed-off-by: NMaor Gottlieb <maorg@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

Fixed bunch of this checkpatch complaint:

 CHECK: Please don't use multiple blank lines
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

Fixed few places where endianness was misspelled and
one spot whwere output was:

CHECK: 'endianess' may be misspelled - perhaps 'endianness'?
CHECK: 'ouput' may be misspelled - perhaps 'output'?
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

Before attempting to initialize the command interface we must wait till
the fw_initializing bit is clear.

If we fail to meet this condition the hardware will drop our
configuration, specifically the descriptors page address.  This scenario
can happen when the firmware is still executing an FLR flow and did not
finish yet so the driver needs to wait for that to finish.

Fixes: e3297246 ('net/mlx5_core: Wait for FW readiness on startup')
Signed-off-by: NEli Cohen <eli@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

When the page size isn't bigger than 4K, there is no added value of enabling 4K
UAR feature in the Firmware.

Modified the condition of enabling the 4K UAR accordingly.

Fixes: f502d834 ("net/mlx5: Activate support for 4K UARs")
Signed-off-by: NMajd Dibbiny <majd@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

Building the driver with CONFIG_SMP disabled results in a harmless
warning:

ethernet/mellanox/mlx5/core/main.c: In function 'mlx5_irq_set_affinity_hint':
ethernet/mellanox/mlx5/core/main.c:615:6: error: unused variable 'irq' [-Werror=unused-variable]

It's better to express the conditional compilation using IS_ENABLED()
here, as that lets the compiler see what the intented use for the variable
is, and that it can be silently discarded.

Fixes: b665d98e ("net/mlx5: Tolerate irq_set_affinity_hint() failures")
Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Acked-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add tolerance to failures of irq_set_affinity_hint().
Its role is to give hints that optimizes performance,
and should not block the driver load.

In non-SMP systems, functionality is not available as
there is a single core, and all these calls definitely
fail.  Hence, do not call the function and avoid the
warning prints.

Fixes: db058a18 ("net/mlx5_core: Set irq affinity hints")
Signed-off-by: NTariq Toukan <tariqt@mellanox.com>
Cc: kernel-team@fb.com
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

Mellanox Innova is a NIC with ConnectX and an FPGA on the same
board. The FPGA is a bump-on-the-wire and thus affects operation of
the mlx5_core driver on the ConnectX ASIC.

Add basic support for Innova in mlx5_core.

This allows using the Innova card as a regular NIC, by detecting
the FPGA capability bit, and verifying its load state before
initializing ConnectX interfaces.

Also detect FPGA fatal runtime failures and enter error state if
they ever happen.

All new FPGA-related logic is placed in its own subdirectory 'fpga',
which may be built by selecting CONFIG_MLX5_FPGA.
This prepares for further support of various Innova features in later
patchsets.
Additional details about hardware architecture will be provided as
more features get submitted.
Signed-off-by: NIlan Tayari <ilant@mellanox.com>
Reviewed-by: NBoris Pismenny <borisp@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

Add the BlueField device and VF IDs to the supported devices list.
Signed-off-by: NNoa Osherovich <noaos@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

If FW is stuck in initializing state we will skip the driver load, but
current error handling flow doesn't clean previously allocated command
interface resources.

Fixes: e3297246 ('net/mlx5_core: Wait for FW readiness on startup')
Signed-off-by: NMohamad Haj Yahia <mohamad@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

Implement the devlink e-switch encapsulation control set and get
callbacks. Apply the value set by the user on the switchdev offloads
mode when creating the fast FDB table where offloaded rules will be set.
Signed-off-by: NRoi Dayan <roid@mellanox.com>
Reviewed-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

Rename the ConnectX-5 PCIe 4.0 to be ConnectX-5 Ex.
Also add the upcoming ConnectX-6 and it's VF IDs to the list.
Signed-off-by: NMajd Dibbiny <majd@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

With ConnectX-4 sharing SRQs from the same space as QPs, we hit a
limit preventing some applications to allocate needed QPs amount.
Double the size to 256K.

Fixes: e126ba97 ('mlx5: Add driver for Mellanox Connect-IB adapters')
Signed-off-by: NMaor Gottlieb <maorg@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When a PCI error is detected the PCI state could be corrupt, don't save
it in that flow. Save the state after initialization. After restoring the
PCI state during slot reset save it again, restoring the state destroys
the previously saved state info.

Fixes: 05ac2c0b ('net/mlx5: Fix race between PCI error handlers and
health work')
Signed-off-by: NDaniel Jurgens <danielj@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There is a hardware feature that will pad the start or end of a DMA to
be cache line aligned to avoid RMWs on the last cache line. The default
cache line size setting for this feature is 64B. This change configures
the hardware to use 128B alignment on systems with 128B cache lines.

In addition we lower bound MPWRQ stride by HCA cacheline in mlx5e,
MPWRQ stride should be at least the HCA cacheline, the current default
is 64B and in case HCA_CAP.cach_line_128byte capability is set, MPWRQ RX
stride will automatically be aligned to 128B.
Signed-off-by: NDaniel Jurgens <danielj@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

As ENOTSUPP is specific to NFS, change the return error value to
EOPNOTSUPP in various places in the mlx5 driver.
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Suggested-by: NYotam Gigi <yotamg@mellanox.com>
Reviewed-by: NMatan Barak <matanb@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

The caps structure consists of hca caps and port/management caps,
all under one roof.
Signed-off-by: NGal Pressman <galp@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

Infiniband part of mlx5 driver can be compiled as a module
or as a part of bzImage (compiled in). In the second case,
the call to request_module will return an error -ENOENT.
It will cause to a misleading print "failed request module
on mlx5_ib".

This patch removes this print, In order to comply with mlx4.

Fixes: f66f049f ("net/mlx5_core: Request the mlx5 IB module on driver load")
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

Do not attempt to drain the health workqueue when unloading the device in
the recovery flow, this can cause a deadlock when the recovery work
tries to cancel itself with sync.

Because the work is no longer unconditionally canceled when unloading, it
must be explicitly canceled in the AER flow.

fixes: 689a248d ("net/mlx5: Cancel recovery work in remove flow")
Signed-off-by: NDaniel Jurgens <danielj@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>