summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/driver-api/auxiliary_bus.rst2
-rw-r--r--Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst215
-rw-r--r--Documentation/networking/devlink/devlink-port.rst199
-rw-r--r--Documentation/networking/devlink/index.rst1
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/Kconfig19
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/Makefile9
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/cmd.c8
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/devlink.c19
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/eq.c5
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c2
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c41
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/eswitch.c48
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/eswitch.h78
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c47
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/events.c7
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/main.c60
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h12
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c20
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/sf/cmd.c49
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c275
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h55
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c101
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c556
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c233
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h82
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/sf/priv.h21
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h100
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c189
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h57
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/vport.c3
-rw-r--r--include/linux/mlx5/driver.h16
-rw-r--r--include/net/devlink.h100
-rw-r--r--include/uapi/linux/devlink.h25
-rw-r--r--net/core/devlink.c310
34 files changed, 2917 insertions, 47 deletions
diff --git a/Documentation/driver-api/auxiliary_bus.rst b/Documentation/driver-api/auxiliary_bus.rst
index 2312506b0674..fff96c7ba7a8 100644
--- a/Documentation/driver-api/auxiliary_bus.rst
+++ b/Documentation/driver-api/auxiliary_bus.rst
@@ -1,5 +1,7 @@
.. SPDX-License-Identifier: GPL-2.0-only
+.. _auxiliary_bus:
+
=============
Auxiliary Bus
=============
diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst
index e9b65035cd47..a1b32fcd0d76 100644
--- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst
+++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst
@@ -12,6 +12,8 @@ Contents
- `Enabling the driver and kconfig options`_
- `Devlink info`_
- `Devlink parameters`_
+- `mlx5 subfunction`_
+- `mlx5 port function`_
- `Devlink health reporters`_
- `mlx5 tracepoints`_
@@ -97,6 +99,11 @@ Enabling the driver and kconfig options
| Provides low-level InfiniBand/RDMA and `RoCE <https://community.mellanox.com/s/article/recommended-network-configuration-examples-for-roce-deployment>`_ support.
+**CONFIG_MLX5_SF=(y/n)**
+
+| Build support for subfunction.
+| Subfunctons are more light weight than PCI SRIOV VFs. Choosing this option
+| will enable support for creating subfunction devices.
**External options** ( Choose if the corresponding mlx5 feature is required )
@@ -176,6 +183,214 @@ User command examples:
values:
cmode driverinit value true
+mlx5 subfunction
+================
+mlx5 supports subfunction management using devlink port (see :ref:`Documentation/networking/devlink/devlink-port.rst <devlink_port>`) interface.
+
+A Subfunction has its own function capabilities and its own resources. This
+means a subfunction has its own dedicated queues (txq, rxq, cq, eq). These
+queues are neither shared nor stolen from the parent PCI function.
+
+When a subfunction is RDMA capable, it has its own QP1, GID table and rdma
+resources neither shared nor stolen from the parent PCI function.
+
+A subfunction has a dedicated window in PCI BAR space that is not shared
+with ther other subfunctions or the parent PCI function. This ensures that all
+devices (netdev, rdma, vdpa etc.) of the subfunction accesses only assigned
+PCI BAR space.
+
+A Subfunction supports eswitch representation through which it supports tc
+offloads. The user configures eswitch to send/receive packets from/to
+the subfunction port.
+
+Subfunctions share PCI level resources such as PCI MSI-X IRQs with
+other subfunctions and/or with its parent PCI function.
+
+Example mlx5 software, system and device view::
+
+ _______
+ | admin |
+ | user |----------
+ |_______| |
+ | |
+ ____|____ __|______ _________________
+ | | | | | |
+ | devlink | | tc tool | | user |
+ | tool | |_________| | applications |
+ |_________| | |_________________|
+ | | | |
+ | | | | Userspace
+ +---------|-------------|-------------------|----------|--------------------+
+ | | +----------+ +----------+ Kernel
+ | | | netdev | | rdma dev |
+ | | +----------+ +----------+
+ (devlink port add/del | ^ ^
+ port function set) | | |
+ | | +---------------|
+ _____|___ | | _______|_______
+ | | | | | mlx5 class |
+ | devlink | +------------+ | | drivers |
+ | kernel | | rep netdev | | |(mlx5_core,ib) |
+ |_________| +------------+ | |_______________|
+ | | | ^
+ (devlink ops) | | (probe/remove)
+ _________|________ | | ____|________
+ | subfunction | | +---------------+ | subfunction |
+ | management driver|----- | subfunction |---| driver |
+ | (mlx5_core) | | auxiliary dev | | (mlx5_core) |
+ |__________________| +---------------+ |_____________|
+ | ^
+ (sf add/del, vhca events) |
+ | (device add/del)
+ _____|____ ____|________
+ | | | subfunction |
+ | PCI NIC |---- activate/deactive events---->| host driver |
+ |__________| | (mlx5_core) |
+ |_____________|
+
+Subfunction is created using devlink port interface.
+
+- Change device to switchdev mode::
+
+ $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev
+
+- Add a devlink port of subfunction flaovur::
+
+ $ devlink port add pci/0000:06:00.0 flavour pcisf pfnum 0 sfnum 88
+ pci/0000:06:00.0/32768: type eth netdev eth6 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false
+ function:
+ hw_addr 00:00:00:00:00:00 state inactive opstate detached
+
+- Show a devlink port of the subfunction::
+
+ $ devlink port show pci/0000:06:00.0/32768
+ pci/0000:06:00.0/32768: type eth netdev enp6s0pf0sf88 flavour pcisf pfnum 0 sfnum 88
+ function:
+ hw_addr 00:00:00:00:00:00 state inactive opstate detached
+
+- Delete a devlink port of subfunction after use::
+
+ $ devlink port del pci/0000:06:00.0/32768
+
+mlx5 function attributes
+========================
+The mlx5 driver provides a mechanism to setup PCI VF/SF function attributes in
+a unified way for SmartNIC and non-SmartNIC.
+
+This is supported only when the eswitch mode is set to switchdev. Port function
+configuration of the PCI VF/SF is supported through devlink eswitch port.
+
+Port function attributes should be set before PCI VF/SF is enumerated by the
+driver.
+
+MAC address setup
+-----------------
+mlx5 driver provides mechanism to setup the MAC address of the PCI VF/SF.
+
+The configured MAC address of the PCI VF/SF will be used by netdevice and rdma
+device created for the PCI VF/SF.
+
+- Get the MAC address of the VF identified by its unique devlink port index::
+
+ $ devlink port show pci/0000:06:00.0/2
+ pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1
+ function:
+ hw_addr 00:00:00:00:00:00
+
+- Set the MAC address of the VF identified by its unique devlink port index::
+
+ $ devlink port function set pci/0000:06:00.0/2 hw_addr 00:11:22:33:44:55
+
+ $ devlink port show pci/0000:06:00.0/2
+ pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1
+ function:
+ hw_addr 00:11:22:33:44:55
+
+- Get the MAC address of the SF identified by its unique devlink port index::
+
+ $ devlink port show pci/0000:06:00.0/32768
+ pci/0000:06:00.0/32768: type eth netdev enp6s0pf0sf88 flavour pcisf pfnum 0 sfnum 88
+ function:
+ hw_addr 00:00:00:00:00:00
+
+- Set the MAC address of the VF identified by its unique devlink port index::
+
+ $ devlink port function set pci/0000:06:00.0/32768 hw_addr 00:00:00:00:88:88
+
+ $ devlink port show pci/0000:06:00.0/32768
+ pci/0000:06:00.0/32768: type eth netdev enp6s0pf0sf88 flavour pcivf pfnum 0 sfnum 88
+ function:
+ hw_addr 00:00:00:00:88:88
+
+SF state setup
+--------------
+To use the SF, the user must active the SF using the SF function state
+attribute.
+
+- Get the state of the SF identified by its unique devlink port index::
+
+ $ devlink port show ens2f0npf0sf88
+ pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false
+ function:
+ hw_addr 00:00:00:00:88:88 state inactive opstate detached
+
+- Activate the function and verify its state is active::
+
+ $ devlink port function set ens2f0npf0sf88 state active
+
+ $ devlink port show ens2f0npf0sf88
+ pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false
+ function:
+ hw_addr 00:00:00:00:88:88 state active opstate detached
+
+Upon function activation, the PF driver instance gets the event from the device
+that a particular SF was activated. It's the cue to put the device on bus, probe
+it and instantiate the devlink instance and class specific auxiliary devices
+for it.
+
+- Show the auxiliary device and port of the subfunction::
+
+ $ devlink dev show
+ devlink dev show auxiliary/mlx5_core.sf.4
+
+ $ devlink port show auxiliary/mlx5_core.sf.4/1
+ auxiliary/mlx5_core.sf.4/1: type eth netdev p0sf88 flavour virtual port 0 splittable false
+
+ $ rdma link show mlx5_0/1
+ link mlx5_0/1 state ACTIVE physical_state LINK_UP netdev p0sf88
+
+ $ rdma dev show
+ 8: rocep6s0f1: node_type ca fw 16.29.0550 node_guid 248a:0703:00b3:d113 sys_image_guid 248a:0703:00b3:d112
+ 13: mlx5_0: node_type ca fw 16.29.0550 node_guid 0000:00ff:fe00:8888 sys_image_guid 248a:0703:00b3:d112
+
+- Subfunction auxiliary device and class device hierarchy::
+
+ mlx5_core.sf.4
+ (subfunction auxiliary device)
+ /\
+ / \
+ / \
+ / \
+ / \
+ mlx5_core.eth.4 mlx5_core.rdma.4
+ (sf eth aux dev) (sf rdma aux dev)
+ | |
+ | |
+ p0sf88 mlx5_0
+ (sf netdev) (sf rdma device)
+
+Additionally, the SF port also gets the event when the driver attaches to the
+auxiliary device of the subfunction. This results in changing the operational
+state of the function. This provides visiblity to the user to decide when is it
+safe to delete the SF port for graceful termination of the subfunction.
+
+- Show the SF port operational state::
+
+ $ devlink port show ens2f0npf0sf88
+ pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false
+ function:
+ hw_addr 00:00:00:00:88:88 state active opstate attached
+
Devlink health reporters
========================
diff --git a/Documentation/networking/devlink/devlink-port.rst b/Documentation/networking/devlink/devlink-port.rst
new file mode 100644
index 000000000000..e99b41599465
--- /dev/null
+++ b/Documentation/networking/devlink/devlink-port.rst
@@ -0,0 +1,199 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+.. _devlink_port:
+
+============
+Devlink Port
+============
+
+``devlink-port`` is a port that exists on the device. It has a logically
+separate ingress/egress point of the device. A devlink port can be any one
+of many flavours. A devlink port flavour along with port attributes
+describe what a port represents.
+
+A device driver that intends to publish a devlink port sets the
+devlink port attributes and registers the devlink port.
+
+Devlink port flavours are described below.
+
+.. list-table:: List of devlink port flavours
+ :widths: 33 90
+
+ * - Flavour
+ - Description
+ * - ``DEVLINK_PORT_FLAVOUR_PHYSICAL``
+ - Any kind of physical port. This can be an eswitch physical port or any
+ other physical port on the device.
+ * - ``DEVLINK_PORT_FLAVOUR_DSA``
+ - This indicates a DSA interconnect port.
+ * - ``DEVLINK_PORT_FLAVOUR_CPU``
+ - This indicates a CPU port applicable only to DSA.
+ * - ``DEVLINK_PORT_FLAVOUR_PCI_PF``
+ - This indicates an eswitch port representing a port of PCI
+ physical function (PF).
+ * - ``DEVLINK_PORT_FLAVOUR_PCI_VF``
+ - This indicates an eswitch port representing a port of PCI
+ virtual function (VF).
+ * - ``DEVLINK_PORT_FLAVOUR_PCI_SF``
+ - This indicates an eswitch port representing a port of PCI
+ subfunction (SF).
+ * - ``DEVLINK_PORT_FLAVOUR_VIRTUAL``
+ - This indicates a virtual port for the PCI virtual function.
+
+Devlink port can have a different type based on the link layer described below.
+
+.. list-table:: List of devlink port types
+ :widths: 23 90
+
+ * - Type
+ - Description
+ * - ``DEVLINK_PORT_TYPE_ETH``
+ - Driver should set this port type when a link layer of the port is
+ Ethernet.
+ * - ``DEVLINK_PORT_TYPE_IB``
+ - Driver should set this port type when a link layer of the port is
+ InfiniBand.
+ * - ``DEVLINK_PORT_TYPE_AUTO``
+ - This type is indicated by the user when driver should detect the port
+ type automatically.
+
+PCI controllers
+---------------
+In most cases a PCI device has only one controller. A controller consists of
+potentially multiple physical, virtual functions and subfunctions. A function
+consists of one or more ports. This port is represented by the devlink eswitch
+port.
+
+A PCI device connected to multiple CPUs or multiple PCI root complexes or a
+SmartNIC, however, may have multiple controllers. For a device with multiple
+controllers, each controller is distinguished by a unique controller number.
+An eswitch is on the PCI device which supports ports of multiple controllers.
+
+An example view of a system with two controllers::
+
+ ---------------------------------------------------------
+ | |
+ | --------- --------- ------- ------- |
+ ----------- | | vf(s) | | sf(s) | |vf(s)| |sf(s)| |
+ | server | | ------- ----/---- ---/----- ------- ---/--- ---/--- |
+ | pci rc |=== | pf0 |______/________/ | pf1 |___/_______/ |
+ | connect | | ------- ------- |
+ ----------- | | controller_num=1 (no eswitch) |
+ ------|--------------------------------------------------
+ (internal wire)
+ |
+ ---------------------------------------------------------
+ | devlink eswitch ports and reps |
+ | ----------------------------------------------------- |
+ | |ctrl-0 | ctrl-0 | ctrl-0 | ctrl-0 | ctrl-0 |ctrl-0 | |
+ | |pf0 | pf0vfN | pf0sfN | pf1 | pf1vfN |pf1sfN | |
+ | ----------------------------------------------------- |
+ | |ctrl-1 | ctrl-1 | ctrl-1 | ctrl-1 | ctrl-1 |ctrl-1 | |
+ | |pf0 | pf0vfN | pf0sfN | pf1 | pf1vfN |pf1sfN | |
+ | ----------------------------------------------------- |
+ | |
+ | |
+ ----------- | --------- --------- ------- ------- |
+ | smartNIC| | | vf(s) | | sf(s) | |vf(s)| |sf(s)| |
+ | pci rc |==| ------- ----/---- ---/----- ------- ---/--- ---/--- |
+ | connect | | | pf0 |______/________/ | pf1 |___/_______/ |
+ ----------- | ------- ------- |
+ | |
+ | local controller_num=0 (eswitch) |
+ ---------------------------------------------------------
+
+In the above example, the external controller (identified by controller number = 1)
+doesn't have the eswitch. Local controller (identified by controller number = 0)
+has the eswitch. The Devlink instance on the local controller has eswitch
+devlink ports for both the controllers.
+
+Function configuration
+======================
+
+A user can configure the function attribute before enumerating the PCI
+function. Usually it means, user should configure function attribute
+before a bus specific device for the function is created. However, when
+SRIOV is enabled, virtual function devices are created on the PCI bus.
+Hence, function attribute should be configured before binding virtual
+function device to the driver. For subfunctions, this means user should
+configure port function attribute before activating the port function.
+
+A user may set the hardware address of the function using
+'devlink port function set hw_addr' command. For Ethernet port function
+this means a MAC address.
+
+Subfunction
+============
+
+Subfunction is a lightweight function that has a parent PCI function on which
+it is deployed. Subfunction is created and deployed in unit of 1. Unlike
+SRIOV VFs, a subfunction doesn't require its own PCI virtual function.
+A subfunction communicates with the hardware through the parent PCI function.
+
+To use a subfunction, 3 steps setup sequence is followed.
+(1) create - create a subfunction;
+(2) configure - configure subfunction attributes;
+(3) deploy - deploy the subfunction;
+
+Subfunction management is done using devlink port user interface.
+User performs setup on the subfunction management device.
+
+(1) Create
+----------
+A subfunction is created using a devlink port interface. A user adds the
+subfunction by adding a devlink port of subfunction flavour. The devlink
+kernel code calls down to subfunction management driver (devlink ops) and asks
+it to create a subfunction devlink port. Driver then instantiates the
+subfunction port and any associated objects such as health reporters and
+representor netdevice.
+
+(2) Configure
+-------------
+A subfunction devlink port is created but it is not active yet. That means the
+entities are created on devlink side, the e-switch port representor is created,
+but the subfunction device itself it not created. A user might use e-switch port
+representor to do settings, putting it into bridge, adding TC rules, etc. A user
+might as well configure the hardware address (such as MAC address) of the
+subfunction while subfunction is inactive.
+
+(3) Deploy
+----------
+Once a subfunction is configured, user must activate it to use it. Upon
+activation, subfunction management driver asks the subfunction management
+device to instantiate the subfunction device on particular PCI function.
+A subfunction device is created on the :ref:`Documentation/driver-api/auxiliary_bus.rst <auxiliary_bus>`.
+At this point a matching subfunction driver binds to the subfunction's auxiliary device.
+
+Terms and Definitions
+=====================
+
+.. list-table:: Terms and Definitions
+ :widths: 22 90
+
+ * - Term
+ - Definitions
+ * - ``PCI device``
+ - A physical PCI device having one or more PCI bus consists of one or
+ more PCI controllers.
+ * - ``PCI controller``
+ - A controller consists of potentially multiple physical functions,
+ virtual functions and subfunctions.
+ * - ``Port function``
+ - An object to manage the function of a port.
+ * - ``Subfunction``
+ - A lightweight function that has parent PCI function on which it is
+ deployed.
+ * - ``Subfunction device``
+ - A bus device of the subfunction, usually on a auxiliary bus.
+ * - ``Subfunction driver``
+ - A device driver for the subfunction auxiliary device.
+ * - ``Subfunction management device``
+ - A PCI physical function that supports subfunction management.
+ * - ``Subfunction management driver``
+ - A device driver for PCI physical function that supports
+ subfunction management using devlink port interface.
+ * - ``Subfunction host driver``
+ - A device driver for PCI physical function that hosts subfunction
+ devices. In most cases it is same as subfunction management driver. When
+ subfunction is used on external controller, subfunction management and
+ host drivers are different.
diff --git a/Documentation/networking/devlink/index.rst b/Documentation/networking/devlink/index.rst
index d82874760ae2..aab79667f97b 100644
--- a/Documentation/networking/devlink/index.rst
+++ b/Documentation/networking/devlink/index.rst
@@ -18,6 +18,7 @@ general.
devlink-info
devlink-flash
devlink-params
+ devlink-port
devlink-region
devlink-resource
devlink-reload
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 6e4d7bb7fea2..ad45d20f9d44 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -203,3 +203,22 @@ config MLX5_SW_STEERING
default y
help
Build support for software-managed steering in the NIC.
+
+config MLX5_SF
+ bool "Mellanox Technologies subfunction device support using auxiliary device"
+ depends on MLX5_CORE && MLX5_CORE_EN
+ default n
+ help
+ Build support for subfuction device in the NIC. A Mellanox subfunction
+ device can support RDMA, netdevice and vdpa device.
+ It is similar to a SRIOV VF but it doesn't require SRIOV support.
+
+config MLX5_SF_MANAGER
+ bool
+ depends on MLX5_SF && MLX5_ESWITCH
+ default y
+ help
+ Build support for subfuction port in the NIC. A Mellanox subfunction
+ port is managed through devlink. A subfunction supports RDMA, netdevice
+ and vdpa device. It is similar to a SRIOV VF but it doesn't require
+ SRIOV support.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index d44f5f6ee449..f61ee7110243 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -88,3 +88,12 @@ mlx5_core-$(CONFIG_MLX5_SW_STEERING) += steering/dr_domain.o steering/dr_table.o
steering/dr_ste_v0.o \
steering/dr_cmd.o steering/dr_fw.o \
steering/dr_action.o steering/fs_dr.o
+#
+# SF device
+#
+mlx5_core-$(CONFIG_MLX5_SF) += sf/vhca_event.o sf/dev/dev.o sf/dev/driver.o
+
+#
+# SF manager
+#
+mlx5_core-$(CONFIG_MLX5_SF_MANAGER) += sf/cmd.o sf/hw_table.o sf/devlink.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 50c7b9ee80c3..e8cecd50558d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -333,6 +333,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
case MLX5_CMD_OP_DEALLOC_MEMIC:
case MLX5_CMD_OP_PAGE_FAULT_RESUME:
case MLX5_CMD_OP_QUERY_ESW_FUNCTIONS:
+ case MLX5_CMD_OP_DEALLOC_SF:
return MLX5_CMD_STAT_OK;
case MLX5_CMD_OP_QUERY_HCA_CAP:
@@ -464,6 +465,9 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
case MLX5_CMD_OP_ALLOC_MEMIC:
case MLX5_CMD_OP_MODIFY_XRQ:
case MLX5_CMD_OP_RELEASE_XRQ_ERROR:
+ case MLX5_CMD_OP_QUERY_VHCA_STATE:
+ case MLX5_CMD_OP_MODIFY_VHCA_STATE:
+ case MLX5_CMD_OP_ALLOC_SF:
*status = MLX5_DRIVER_STATUS_ABORTED;
*synd = MLX5_DRIVER_SYND;
return -EIO;
@@ -657,6 +661,10 @@ const char *mlx5_command_str(int command)
MLX5_COMMAND_STR_CASE(DESTROY_UMEM);
MLX5_COMMAND_STR_CASE(RELEASE_XRQ_ERROR);
MLX5_COMMAND_STR_CASE(MODIFY_XRQ);
+ MLX5_COMMAND_STR_CASE(QUERY_VHCA_STATE);
+ MLX5_COMMAND_STR_CASE(MODIFY_VHCA_STATE);
+ MLX5_COMMAND_STR_CASE(ALLOC_SF);
+ MLX5_COMMAND_STR_CASE(DEALLOC_SF);
default: return "unknown command opcode";
}
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index b23b54814356..aa76a6e0dae8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -7,6 +7,8 @@
#include "fw_reset.h"
#include "fs_core.h"
#include "eswitch.h"
+#include "sf/dev/dev.h"
+#include "sf/sf.h"
static int mlx5_devlink_flash_update(struct devlink *devlink,
struct devlink_flash_update_params *params,
@@ -127,6 +129,17 @@ static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change,
struct netlink_ext_ack *extack)
{
struct mlx5_core_dev *dev = devlink_priv(devlink);
+ bool sf_dev_allocated;
+
+ sf_dev_allocated = mlx5_sf_dev_allocated(dev);
+ if (sf_dev_allocated) {
+ /* Reload results in deleting SF device which further results in
+ * unregistering devlink instance while holding devlink_mutext.
+ * Hence, do not support reload.
+ */
+ NL_SET_ERR_MSG_MOD(extack, "reload is unsupported when SFs are allocated\n");
+ return -EOPNOTSUPP;
+ }
switch (action) {
case DEVLINK_RELOAD_ACTION_DRIVER_REINIT:
@@ -264,6 +277,12 @@ static const struct devlink_ops mlx5_devlink_ops = {
.port_function_hw_addr_get = mlx5_devlink_port_function_hw_addr_get,
.port_function_hw_addr_set = mlx5_devlink_port_function_hw_addr_set,
#endif
+#ifdef CONFIG_MLX5_SF_MANAGER
+ .port_new = mlx5_devlink_sf_port_new,
+ .port_del = mlx5_devlink_sf_port_del,
+ .port_fn_state_get = mlx5_devlink_sf_port_fn_state_get,
+ .port_fn_state_set = mlx5_devlink_sf_port_fn_state_set,
+#endif
.flash_update = mlx5_devlink_flash_update,
.info_get = mlx5_devlink_info_get,
.reload_actions = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT) |
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index fc0afa03d407..174dfbc996c6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -467,7 +467,7 @@ int mlx5_eq_table_init(struct mlx5_core_dev *dev)
for (i = 0; i < MLX5_EVENT_TYPE_MAX; i++)
ATOMIC_INIT_NOTIFIER_HEAD(&eq_table->nh[i]);
- eq_table->irq_table = dev->priv.irq_table;
+ eq_table->irq_table = mlx5_irq_table_get(dev);
return 0;
}
@@ -595,6 +595,9 @@ static void gather_async_events_mask(struct mlx5_core_dev *dev, u64 mask[4])
async_event_mask |=
(1ull << MLX5_EVENT_TYPE_ESW_FUNCTIONS_CHANGED);
+ if (MLX5_CAP_GEN_MAX(dev, vhca_state))
+ async_event_mask |= (1ull << MLX5_EVENT_TYPE_VHCA_STATE_CHANGE);
+
mask[0] = async_event_mask;
if (MLX5_CAP_GEN(dev, event_cap))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c
index 4c74e2690d57..26b37a0f8762 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c
@@ -150,7 +150,7 @@ static void esw_acl_egress_ofld_groups_destroy(struct mlx5_vport *vport)
static bool esw_acl_egress_needed(const struct mlx5_eswitch *esw, u16 vport_num)
{
- return mlx5_eswitch_is_vf_vport(esw, vport_num);
+ return mlx5_eswitch_is_vf_vport(esw, vport_num) || mlx5_esw_is_sf_vport(esw, vport_num);
}
int esw_acl_egress_ofld_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/